| 115 9 115 9 9 115 115 115 105 115 115 115 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * sha1_base.h - core logic for SHA-1 implementations * * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org> */ #ifndef _CRYPTO_SHA1_BASE_H #define _CRYPTO_SHA1_BASE_H #include <crypto/internal/hash.h> #include <crypto/sha1.h> #include <linux/crypto.h> #include <linux/module.h> #include <linux/string.h> #include <asm/unaligned.h> typedef void (sha1_block_fn)(struct sha1_state *sst, u8 const *src, int blocks); static inline int sha1_base_init(struct shash_desc *desc) { struct sha1_state *sctx = shash_desc_ctx(desc); sctx->state[0] = SHA1_H0; sctx->state[1] = SHA1_H1; sctx->state[2] = SHA1_H2; sctx->state[3] = SHA1_H3; sctx->state[4] = SHA1_H4; sctx->count = 0; return 0; } static inline int sha1_base_do_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha1_block_fn *block_fn) { struct sha1_state *sctx = shash_desc_ctx(desc); unsigned int partial = sctx->count % SHA1_BLOCK_SIZE; sctx->count += len; if (unlikely((partial + len) >= SHA1_BLOCK_SIZE)) { int blocks; if (partial) { int p = SHA1_BLOCK_SIZE - partial; memcpy(sctx->buffer + partial, data, p); data += p; len -= p; block_fn(sctx, sctx->buffer, 1); } blocks = len / SHA1_BLOCK_SIZE; len %= SHA1_BLOCK_SIZE; if (blocks) { block_fn(sctx, data, blocks); data += blocks * SHA1_BLOCK_SIZE; } partial = 0; } if (len) memcpy(sctx->buffer + partial, data, len); return 0; } static inline int sha1_base_do_finalize(struct shash_desc *desc, sha1_block_fn *block_fn) { const int bit_offset = SHA1_BLOCK_SIZE - sizeof(__be64); struct sha1_state *sctx = shash_desc_ctx(desc); __be64 *bits = (__be64 *)(sctx->buffer + bit_offset); unsigned int partial = sctx->count % SHA1_BLOCK_SIZE; sctx->buffer[partial++] = 0x80; if (partial > bit_offset) { memset(sctx->buffer + partial, 0x0, SHA1_BLOCK_SIZE - partial); partial = 0; block_fn(sctx, sctx->buffer, 1); } memset(sctx->buffer + partial, 0x0, bit_offset - partial); *bits = cpu_to_be64(sctx->count << 3); block_fn(sctx, sctx->buffer, 1); return 0; } static inline int sha1_base_finish(struct shash_desc *desc, u8 *out) { struct sha1_state *sctx = shash_desc_ctx(desc); __be32 *digest = (__be32 *)out; int i; for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++) put_unaligned_be32(sctx->state[i], digest++); memzero_explicit(sctx, sizeof(*sctx)); return 0; } #endif /* _CRYPTO_SHA1_BASE_H */ |
| 274 71 470 10 10 9 336 11 33 8 3 8 3 9 57 330 811 829 828 24 644 51 848 848 845 848 848 137 164 95 469 438 438 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * vma.h * * Core VMA manipulation API implemented in vma.c. */ #ifndef __MM_VMA_H #define __MM_VMA_H /* * VMA lock generalization */ struct vma_prepare { struct vm_area_struct *vma; struct vm_area_struct *adj_next; struct file *file; struct address_space *mapping; struct anon_vma *anon_vma; struct vm_area_struct *insert; struct vm_area_struct *remove; struct vm_area_struct *remove2; }; struct unlink_vma_file_batch { int count; struct vm_area_struct *vmas[8]; }; /* * vma munmap operation */ struct vma_munmap_struct { struct vma_iterator *vmi; struct vm_area_struct *vma; /* The first vma to munmap */ struct vm_area_struct *prev; /* vma before the munmap area */ struct vm_area_struct *next; /* vma after the munmap area */ struct list_head *uf; /* Userfaultfd list_head */ unsigned long start; /* Aligned start addr (inclusive) */ unsigned long end; /* Aligned end addr (exclusive) */ unsigned long unmap_start; /* Unmap PTE start */ unsigned long unmap_end; /* Unmap PTE end */ int vma_count; /* Number of vmas that will be removed */ bool unlock; /* Unlock after the munmap */ bool clear_ptes; /* If there are outstanding PTE to be cleared */ bool closed_vm_ops; /* call_mmap() was encountered, so vmas may be closed */ /* 1 byte hole */ unsigned long nr_pages; /* Number of pages being removed */ unsigned long locked_vm; /* Number of locked pages */ unsigned long nr_accounted; /* Number of VM_ACCOUNT pages */ unsigned long exec_vm; unsigned long stack_vm; unsigned long data_vm; }; enum vma_merge_state { VMA_MERGE_START, VMA_MERGE_ERROR_NOMEM, VMA_MERGE_NOMERGE, VMA_MERGE_SUCCESS, }; /* Represents a VMA merge operation. */ struct vma_merge_struct { struct mm_struct *mm; struct vma_iterator *vmi; pgoff_t pgoff; struct vm_area_struct *prev; struct vm_area_struct *next; /* Modified by vma_merge(). */ struct vm_area_struct *vma; /* Either a new VMA or the one being modified. */ unsigned long start; unsigned long end; unsigned long flags; struct file *file; struct anon_vma *anon_vma; struct mempolicy *policy; struct vm_userfaultfd_ctx uffd_ctx; struct anon_vma_name *anon_name; enum vma_merge_state state; }; static inline bool vmg_nomem(struct vma_merge_struct *vmg) { return vmg->state == VMA_MERGE_ERROR_NOMEM; } /* Assumes addr >= vma->vm_start. */ static inline pgoff_t vma_pgoff_offset(struct vm_area_struct *vma, unsigned long addr) { return vma->vm_pgoff + PHYS_PFN(addr - vma->vm_start); } #define VMG_STATE(name, mm_, vmi_, start_, end_, flags_, pgoff_) \ struct vma_merge_struct name = { \ .mm = mm_, \ .vmi = vmi_, \ .start = start_, \ .end = end_, \ .flags = flags_, \ .pgoff = pgoff_, \ .state = VMA_MERGE_START, \ } #define VMG_VMA_STATE(name, vmi_, prev_, vma_, start_, end_) \ struct vma_merge_struct name = { \ .mm = vma_->vm_mm, \ .vmi = vmi_, \ .prev = prev_, \ .next = NULL, \ .vma = vma_, \ .start = start_, \ .end = end_, \ .flags = vma_->vm_flags, \ .pgoff = vma_pgoff_offset(vma_, start_), \ .file = vma_->vm_file, \ .anon_vma = vma_->anon_vma, \ .policy = vma_policy(vma_), \ .uffd_ctx = vma_->vm_userfaultfd_ctx, \ .anon_name = anon_vma_name(vma_), \ .state = VMA_MERGE_START, \ } #ifdef CONFIG_DEBUG_VM_MAPLE_TREE void validate_mm(struct mm_struct *mm); #else #define validate_mm(mm) do { } while (0) #endif /* Required for expand_downwards(). */ void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma); /* Required for expand_downwards(). */ void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma); int vma_expand(struct vma_merge_struct *vmg); int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff); static inline int vma_iter_store_gfp(struct vma_iterator *vmi, struct vm_area_struct *vma, gfp_t gfp) { if (vmi->mas.status != ma_start && ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) vma_iter_invalidate(vmi); __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); mas_store_gfp(&vmi->mas, vma, gfp); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; return 0; } #ifdef CONFIG_MMU /* * init_vma_munmap() - Initializer wrapper for vma_munmap_struct * @vms: The vma munmap struct * @vmi: The vma iterator * @vma: The first vm_area_struct to munmap * @start: The aligned start address to munmap * @end: The aligned end address to munmap * @uf: The userfaultfd list_head * @unlock: Unlock after the operation. Only unlocked on success */ static inline void init_vma_munmap(struct vma_munmap_struct *vms, struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { vms->vmi = vmi; vms->vma = vma; if (vma) { vms->start = start; vms->end = end; } else { vms->start = vms->end = 0; } vms->unlock = unlock; vms->uf = uf; vms->vma_count = 0; vms->nr_pages = vms->locked_vm = vms->nr_accounted = 0; vms->exec_vm = vms->stack_vm = vms->data_vm = 0; vms->unmap_start = FIRST_USER_ADDRESS; vms->unmap_end = USER_PGTABLES_CEILING; vms->clear_ptes = false; vms->closed_vm_ops = false; } #endif int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach); void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach); void vms_clean_up_area(struct vma_munmap_struct *vms, struct ma_state *mas_detach); /* * reattach_vmas() - Undo any munmap work and free resources * @mas_detach: The maple state with the detached maple tree * * Reattach any detached vmas and free up the maple tree used to track the vmas. */ static inline void reattach_vmas(struct ma_state *mas_detach) { struct vm_area_struct *vma; mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) vma_mark_detached(vma, false); __mt_destroy(mas_detach->tree); } /* * vms_abort_munmap_vmas() - Undo as much as possible from an aborted munmap() * operation. * @vms: The vma unmap structure * @mas_detach: The maple state with the detached maple tree * * Reattach any detached vmas, free up the maple tree used to track the vmas. * If that's not possible because the ptes are cleared (and vm_ops->closed() may * have been called), then a NULL is written over the vmas and the vmas are * removed (munmap() completed). */ static inline void vms_abort_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct ma_state *mas = &vms->vmi->mas; if (!vms->nr_pages) return; if (vms->clear_ptes) return reattach_vmas(mas_detach); /* * Aborting cannot just call the vm_ops open() because they are often * not symmetrical and state data has been lost. Resort to the old * failure method of leaving a gap where the MAP_FIXED mapping failed. */ mas_set_range(mas, vms->start, vms->end - 1); if (unlikely(mas_store_gfp(mas, NULL, GFP_KERNEL))) { pr_warn_once("%s: (%d) Unable to abort munmap() operation\n", current->comm, current->pid); /* Leaving vmas detached and in-tree may hamper recovery */ reattach_vmas(mas_detach); } else { /* Clean up the insertion of the unfortunate gap */ vms_complete_munmap_vmas(vms, mas_detach); } } int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf, bool unlock); int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); void remove_vma(struct vm_area_struct *vma, bool unreachable, bool closed); void unmap_region(struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next); /* We are about to modify the VMA's flags. */ struct vm_area_struct *vma_modify_flags(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags); /* We are about to modify the VMA's flags and/or anon_name. */ struct vm_area_struct *vma_modify_flags_name(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, struct anon_vma_name *new_name); /* We are about to modify the VMA's memory policy. */ struct vm_area_struct *vma_modify_policy(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct mempolicy *new_pol); /* We are about to modify the VMA's flags and/or uffd context. */ struct vm_area_struct *vma_modify_flags_uffd(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, struct vm_userfaultfd_ctx new_ctx); struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg); struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long delta); void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb); void unlink_file_vma_batch_final(struct unlink_vma_file_batch *vb); void unlink_file_vma_batch_add(struct unlink_vma_file_batch *vb, struct vm_area_struct *vma); void unlink_file_vma(struct vm_area_struct *vma); void vma_link_file(struct vm_area_struct *vma); int vma_link(struct mm_struct *mm, struct vm_area_struct *vma); struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma); bool vma_needs_dirty_tracking(struct vm_area_struct *vma); bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); int mm_take_all_locks(struct mm_struct *mm); void mm_drop_all_locks(struct mm_struct *mm); static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) { /* * We want to check manually if we can change individual PTEs writable * if we can't do that automatically for all PTEs in a mapping. For * private mappings, that's always the case when we have write * permissions as we properly have to handle COW. */ if (vma->vm_flags & VM_SHARED) return vma_wants_writenotify(vma, vma->vm_page_prot); return !!(vma->vm_flags & VM_WRITE); } #ifdef CONFIG_MMU static inline pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) { return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); } #endif static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi, unsigned long min) { return mas_prev(&vmi->mas, min); } /* * These three helpers classifies VMAs for virtual memory accounting. */ /* * Executable code area - executable, not writable, not stack */ static inline bool is_exec_mapping(vm_flags_t flags) { return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; } /* * Stack area (including shadow stacks) * * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: * do_mmap() forbids all other combinations. */ static inline bool is_stack_mapping(vm_flags_t flags) { return ((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK); } /* * Data area - private, writable, not stack */ static inline bool is_data_mapping(vm_flags_t flags) { return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; } static inline void vma_iter_config(struct vma_iterator *vmi, unsigned long index, unsigned long last) { __mas_set_range(&vmi->mas, index, last - 1); } static inline void vma_iter_reset(struct vma_iterator *vmi) { mas_reset(&vmi->mas); } static inline struct vm_area_struct *vma_iter_prev_range_limit(struct vma_iterator *vmi, unsigned long min) { return mas_prev_range(&vmi->mas, min); } static inline struct vm_area_struct *vma_iter_next_range_limit(struct vma_iterator *vmi, unsigned long max) { return mas_next_range(&vmi->mas, max); } static inline int vma_iter_area_lowest(struct vma_iterator *vmi, unsigned long min, unsigned long max, unsigned long size) { return mas_empty_area(&vmi->mas, min, max - 1, size); } static inline int vma_iter_area_highest(struct vma_iterator *vmi, unsigned long min, unsigned long max, unsigned long size) { return mas_empty_area_rev(&vmi->mas, min, max - 1, size); } /* * VMA Iterator functions shared between nommu and mmap */ static inline int vma_iter_prealloc(struct vma_iterator *vmi, struct vm_area_struct *vma) { return mas_preallocate(&vmi->mas, vma, GFP_KERNEL); } static inline void vma_iter_clear(struct vma_iterator *vmi) { mas_store_prealloc(&vmi->mas, NULL); } static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi) { return mas_walk(&vmi->mas); } /* Store a VMA with preallocated memory */ static inline void vma_iter_store(struct vma_iterator *vmi, struct vm_area_struct *vma) { #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && vmi->mas.index > vma->vm_start)) { pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n", vmi->mas.index, vma->vm_start, vma->vm_start, vma->vm_end, vmi->mas.index, vmi->mas.last); } if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && vmi->mas.last < vma->vm_start)) { pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n", vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end, vmi->mas.index, vmi->mas.last); } #endif if (vmi->mas.status != ma_start && ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) vma_iter_invalidate(vmi); __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); mas_store_prealloc(&vmi->mas, vma); } static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) { return vmi->mas.index; } static inline unsigned long vma_iter_end(struct vma_iterator *vmi) { return vmi->mas.last + 1; } static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi, unsigned long count) { return mas_expected_entries(&vmi->mas, count); } static inline struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi) { return mas_prev_range(&vmi->mas, 0); } /* * Retrieve the next VMA and rewind the iterator to end of the previous VMA, or * if no previous VMA, to index 0. */ static inline struct vm_area_struct *vma_iter_next_rewind(struct vma_iterator *vmi, struct vm_area_struct **pprev) { struct vm_area_struct *next = vma_next(vmi); struct vm_area_struct *prev = vma_prev(vmi); /* * Consider the case where no previous VMA exists. We advance to the * next VMA, skipping any gap, then rewind to the start of the range. * * If we were to unconditionally advance to the next range we'd wind up * at the next VMA again, so we check to ensure there is a previous VMA * to skip over. */ if (prev) vma_iter_next_range(vmi); if (pprev) *pprev = prev; return next; } #ifdef CONFIG_64BIT static inline bool vma_is_sealed(struct vm_area_struct *vma) { return (vma->vm_flags & VM_SEALED); } /* * check if a vma is sealed for modification. * return true, if modification is allowed. */ static inline bool can_modify_vma(struct vm_area_struct *vma) { if (unlikely(vma_is_sealed(vma))) return false; return true; } bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior); #else static inline bool can_modify_vma(struct vm_area_struct *vma) { return true; } static inline bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior) { return true; } #endif #endif /* __MM_VMA_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BOOTMEM_INFO_H #define __LINUX_BOOTMEM_INFO_H #include <linux/mm.h> #include <linux/kmemleak.h> /* * Types for free bootmem stored in page->lru.next. These have to be in * some random range in unsigned long space for debugging purposes. */ enum { MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, MIX_SECTION_INFO, NODE_INFO, MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, }; #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE void __init register_page_bootmem_info_node(struct pglist_data *pgdat); void get_page_bootmem(unsigned long info, struct page *page, unsigned long type); void put_page_bootmem(struct page *page); /* * Any memory allocated via the memblock allocator and not via the * buddy will be marked reserved already in the memmap. For those * pages, we can call this function to free it to buddy allocator. */ static inline void free_bootmem_page(struct page *page) { unsigned long magic = page->index; /* * The reserve_bootmem_region sets the reserved flag on bootmem * pages. */ VM_BUG_ON_PAGE(page_ref_count(page) != 2, page); if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) put_page_bootmem(page); else VM_BUG_ON_PAGE(1, page); } #else static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) { } static inline void put_page_bootmem(struct page *page) { } static inline void get_page_bootmem(unsigned long info, struct page *page, unsigned long type) { } static inline void free_bootmem_page(struct page *page) { kmemleak_free_part_phys(PFN_PHYS(page_to_pfn(page)), PAGE_SIZE); free_reserved_page(page); } #endif #endif /* __LINUX_BOOTMEM_INFO_H */ |
| 1 1 1 1 1 1 2 2 1 1 1 2 1 2 1 1 1 1 2 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 | /* * net/tipc/net.c: TIPC network routing code * * Copyright (c) 1995-2006, 2014, Ericsson AB * Copyright (c) 2005, 2010-2011, 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 "core.h" #include "net.h" #include "name_distr.h" #include "subscr.h" #include "socket.h" #include "node.h" #include "bcast.h" #include "link.h" #include "netlink.h" #include "monitor.h" /* * The TIPC locking policy is designed to ensure a very fine locking * granularity, permitting complete parallel access to individual * port and node/link instances. The code consists of four major * locking domains, each protected with their own disjunct set of locks. * * 1: The bearer level. * RTNL lock is used to serialize the process of configuring bearer * on update side, and RCU lock is applied on read side to make * bearer instance valid on both paths of message transmission and * reception. * * 2: The node and link level. * All node instances are saved into two tipc_node_list and node_htable * lists. The two lists are protected by node_list_lock on write side, * and they are guarded with RCU lock on read side. Especially node * instance is destroyed only when TIPC module is removed, and we can * confirm that there has no any user who is accessing the node at the * moment. Therefore, Except for iterating the two lists within RCU * protection, it's no needed to hold RCU that we access node instance * in other places. * * In addition, all members in node structure including link instances * are protected by node spin lock. * * 3: The transport level of the protocol. * This consists of the structures port, (and its user level * representations, such as user_port and tipc_sock), reference and * tipc_user (port.c, reg.c, socket.c). * * This layer has four different locks: * - The tipc_port spin_lock. This is protecting each port instance * from parallel data access and removal. Since we can not place * this lock in the port itself, it has been placed in the * corresponding reference table entry, which has the same life * cycle as the module. This entry is difficult to access from * outside the TIPC core, however, so a pointer to the lock has * been added in the port instance, -to be used for unlocking * only. * - A read/write lock to protect the reference table itself (teg.c). * (Nobody is using read-only access to this, so it can just as * well be changed to a spin_lock) * - A spin lock to protect the registry of kernel/driver users (reg.c) * - A global spin_lock (tipc_port_lock), which only task is to ensure * consistency where more than one port is involved in an operation, * i.e., when a port is part of a linked list of ports. * There are two such lists; 'port_list', which is used for management, * and 'wait_list', which is used to queue ports during congestion. * * 4: The name table (name_table.c, name_distr.c, subscription.c) * - There is one big read/write-lock (tipc_nametbl_lock) protecting the * overall name table structure. Nothing must be added/removed to * this structure without holding write access to it. * - There is one local spin_lock per sub_sequence, which can be seen * as a sub-domain to the tipc_nametbl_lock domain. It is used only * for translation operations, and is needed because a translation * steps the root of the 'publication' linked list between each lookup. * This is always used within the scope of a tipc_nametbl_lock(read). * - A local spin_lock protecting the queue of subscriber events. */ static void tipc_net_finalize(struct net *net, u32 addr); int tipc_net_init(struct net *net, u8 *node_id, u32 addr) { if (tipc_own_id(net)) { pr_info("Cannot configure node identity twice\n"); return -1; } pr_info("Started in network mode\n"); if (node_id) tipc_set_node_id(net, node_id); if (addr) tipc_net_finalize(net, addr); return 0; } static void tipc_net_finalize(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net); struct tipc_socket_addr sk = {0, addr}; struct tipc_uaddr ua; tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_CLUSTER_SCOPE, TIPC_NODE_STATE, addr, addr); if (cmpxchg(&tn->node_addr, 0, addr)) return; tipc_set_node_addr(net, addr); tipc_named_reinit(net); tipc_sk_reinit(net); tipc_mon_reinit_self(net); tipc_nametbl_publish(net, &ua, &sk, addr); } void tipc_net_finalize_work(struct work_struct *work) { struct tipc_net *tn = container_of(work, struct tipc_net, work); tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr); } void tipc_net_stop(struct net *net) { if (!tipc_own_id(net)) return; rtnl_lock(); tipc_bearer_stop(net); tipc_node_stop(net); rtnl_unlock(); pr_info("Left network mode\n"); } static int __tipc_nl_add_net(struct net *net, struct tipc_nl_msg *msg) { struct tipc_net *tn = net_generic(net, tipc_net_id); u64 *w0 = (u64 *)&tn->node_id[0]; u64 *w1 = (u64 *)&tn->node_id[8]; struct nlattr *attrs; void *hdr; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_NET_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NET); if (!attrs) goto msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_NET_ID, tn->net_id)) goto attr_msg_full; if (nla_put_u64_64bit(msg->skb, TIPC_NLA_NET_NODEID, *w0, 0)) goto attr_msg_full; if (nla_put_u64_64bit(msg->skb, TIPC_NLA_NET_NODEID_W1, *w1, 0)) goto attr_msg_full; nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int err; int done = cb->args[0]; struct tipc_nl_msg msg; if (done) return 0; msg.skb = skb; msg.portid = NETLINK_CB(cb->skb).portid; msg.seq = cb->nlh->nlmsg_seq; err = __tipc_nl_add_net(net, &msg); if (err) goto out; done = 1; out: cb->args[0] = done; return skb->len; } int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attrs[TIPC_NLA_NET_MAX + 1]; struct net *net = sock_net(skb->sk); struct tipc_net *tn = tipc_net(net); int err; if (!info->attrs[TIPC_NLA_NET]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_NET_MAX, info->attrs[TIPC_NLA_NET], tipc_nl_net_policy, info->extack); if (err) return err; /* Can't change net id once TIPC has joined a network */ if (tipc_own_addr(net)) return -EPERM; if (attrs[TIPC_NLA_NET_ID]) { u32 val; val = nla_get_u32(attrs[TIPC_NLA_NET_ID]); if (val < 1 || val > 9999) return -EINVAL; tn->net_id = val; } if (attrs[TIPC_NLA_NET_ADDR]) { u32 addr; addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]); if (!addr) return -EINVAL; tn->legacy_addr_format = true; tipc_net_init(net, NULL, addr); } if (attrs[TIPC_NLA_NET_NODEID]) { u8 node_id[NODE_ID_LEN]; u64 *w0 = (u64 *)&node_id[0]; u64 *w1 = (u64 *)&node_id[8]; if (!attrs[TIPC_NLA_NET_NODEID_W1]) return -EINVAL; *w0 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID]); *w1 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID_W1]); tipc_net_init(net, node_id, 0); } return 0; } int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) { int err; rtnl_lock(); err = __tipc_nl_net_set(skb, info); rtnl_unlock(); return err; } static int __tipc_nl_addr_legacy_get(struct net *net, struct tipc_nl_msg *msg) { struct tipc_net *tn = tipc_net(net); struct nlattr *attrs; void *hdr; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, 0, TIPC_NL_ADDR_LEGACY_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start(msg->skb, TIPC_NLA_NET); if (!attrs) goto msg_full; if (tn->legacy_addr_format) if (nla_put_flag(msg->skb, TIPC_NLA_NET_ADDR_LEGACY)) goto attr_msg_full; nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); struct tipc_nl_msg msg; struct sk_buff *rep; int err; rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!rep) return -ENOMEM; msg.skb = rep; msg.portid = info->snd_portid; msg.seq = info->snd_seq; err = __tipc_nl_addr_legacy_get(net, &msg); if (err) { nlmsg_free(msg.skb); return err; } return genlmsg_reply(msg.skb, info); } |
| 20 20 20 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 | // SPDX-License-Identifier: GPL-2.0 /* -*- linux-c -*- * sysctl_net_core.c: sysctl interface to net core subsystem. * * Begun April 1, 1996, Mike Shaver. * Added /proc/sys/net/core directory entry (empty =) ). [MS] */ #include <linux/filter.h> #include <linux/mm.h> #include <linux/sysctl.h> #include <linux/module.h> #include <linux/socket.h> #include <linux/netdevice.h> #include <linux/ratelimit.h> #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/sched/isolation.h> #include <net/ip.h> #include <net/sock.h> #include <net/net_ratelimit.h> #include <net/busy_poll.h> #include <net/pkt_sched.h> #include <net/hotdata.h> #include <net/proto_memory.h> #include <net/rps.h> #include "dev.h" static int int_3600 = 3600; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE; static int net_msg_warn; /* Unused, but still a sysctl */ int sysctl_fb_tunnels_only_for_init_net __read_mostly = 0; EXPORT_SYMBOL(sysctl_fb_tunnels_only_for_init_net); /* 0 - Keep current behavior: * IPv4: inherit all current settings from init_net * IPv6: reset all settings to default * 1 - Both inherit all current settings from init_net * 2 - Both reset all settings to default * 3 - Both inherit all settings from current netns */ int sysctl_devconf_inherit_init_net __read_mostly; EXPORT_SYMBOL(sysctl_devconf_inherit_init_net); #if IS_ENABLED(CONFIG_NET_FLOW_LIMIT) || IS_ENABLED(CONFIG_RPS) static void dump_cpumask(void *buffer, size_t *lenp, loff_t *ppos, struct cpumask *mask) { char kbuf[128]; int len; if (*ppos || !*lenp) { *lenp = 0; return; } len = min(sizeof(kbuf) - 1, *lenp); len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask)); if (!len) { *lenp = 0; return; } if (len < *lenp) kbuf[len++] = '\n'; memcpy(buffer, kbuf, len); *lenp = len; *ppos += len; } #endif #ifdef CONFIG_RPS static struct cpumask *rps_default_mask_cow_alloc(struct net *net) { struct cpumask *rps_default_mask; if (net->core.rps_default_mask) return net->core.rps_default_mask; rps_default_mask = kzalloc(cpumask_size(), GFP_KERNEL); if (!rps_default_mask) return NULL; /* pairs with READ_ONCE in rx_queue_default_mask() */ WRITE_ONCE(net->core.rps_default_mask, rps_default_mask); return rps_default_mask; } static int rps_default_mask_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)table->data; int err = 0; rtnl_lock(); if (write) { struct cpumask *rps_default_mask = rps_default_mask_cow_alloc(net); err = -ENOMEM; if (!rps_default_mask) goto done; err = cpumask_parse(buffer, rps_default_mask); if (err) goto done; err = rps_cpumask_housekeeping(rps_default_mask); if (err) goto done; } else { dump_cpumask(buffer, lenp, ppos, net->core.rps_default_mask ? : cpu_none_mask); } done: rtnl_unlock(); return err; } static int rps_sock_flow_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned int orig_size, size; int ret, i; struct ctl_table tmp = { .data = &size, .maxlen = sizeof(size), .mode = table->mode }; struct rps_sock_flow_table *orig_sock_table, *sock_table; static DEFINE_MUTEX(sock_flow_mutex); mutex_lock(&sock_flow_mutex); orig_sock_table = rcu_dereference_protected( net_hotdata.rps_sock_flow_table, lockdep_is_held(&sock_flow_mutex)); size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0; ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (write) { if (size) { if (size > 1<<29) { /* Enforce limit to prevent overflow */ mutex_unlock(&sock_flow_mutex); return -EINVAL; } size = roundup_pow_of_two(size); if (size != orig_size) { sock_table = vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size)); if (!sock_table) { mutex_unlock(&sock_flow_mutex); return -ENOMEM; } net_hotdata.rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1; sock_table->mask = size - 1; } else sock_table = orig_sock_table; for (i = 0; i < size; i++) sock_table->ents[i] = RPS_NO_CPU; } else sock_table = NULL; if (sock_table != orig_sock_table) { rcu_assign_pointer(net_hotdata.rps_sock_flow_table, sock_table); if (sock_table) { static_branch_inc(&rps_needed); static_branch_inc(&rfs_needed); } if (orig_sock_table) { static_branch_dec(&rps_needed); static_branch_dec(&rfs_needed); kvfree_rcu_mightsleep(orig_sock_table); } } } mutex_unlock(&sock_flow_mutex); return ret; } #endif /* CONFIG_RPS */ #ifdef CONFIG_NET_FLOW_LIMIT static DEFINE_MUTEX(flow_limit_update_mutex); static int flow_limit_cpu_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct sd_flow_limit *cur; struct softnet_data *sd; cpumask_var_t mask; int i, len, ret = 0; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; if (write) { ret = cpumask_parse(buffer, mask); if (ret) goto done; mutex_lock(&flow_limit_update_mutex); len = sizeof(*cur) + netdev_flow_limit_table_len; for_each_possible_cpu(i) { sd = &per_cpu(softnet_data, i); cur = rcu_dereference_protected(sd->flow_limit, lockdep_is_held(&flow_limit_update_mutex)); if (cur && !cpumask_test_cpu(i, mask)) { RCU_INIT_POINTER(sd->flow_limit, NULL); kfree_rcu_mightsleep(cur); } else if (!cur && cpumask_test_cpu(i, mask)) { cur = kzalloc_node(len, GFP_KERNEL, cpu_to_node(i)); if (!cur) { /* not unwinding previous changes */ ret = -ENOMEM; goto write_unlock; } cur->num_buckets = netdev_flow_limit_table_len; rcu_assign_pointer(sd->flow_limit, cur); } } write_unlock: mutex_unlock(&flow_limit_update_mutex); } else { cpumask_clear(mask); rcu_read_lock(); for_each_possible_cpu(i) { sd = &per_cpu(softnet_data, i); if (rcu_dereference(sd->flow_limit)) cpumask_set_cpu(i, mask); } rcu_read_unlock(); dump_cpumask(buffer, lenp, ppos, mask); } done: free_cpumask_var(mask); return ret; } static int flow_limit_table_len_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned int old, *ptr; int ret; mutex_lock(&flow_limit_update_mutex); ptr = table->data; old = *ptr; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write && !is_power_of_2(*ptr)) { *ptr = old; ret = -EINVAL; } mutex_unlock(&flow_limit_update_mutex); return ret; } #endif /* CONFIG_NET_FLOW_LIMIT */ #ifdef CONFIG_NET_SCHED static int set_default_qdisc(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char id[IFNAMSIZ]; struct ctl_table tbl = { .data = id, .maxlen = IFNAMSIZ, }; int ret; qdisc_get_default(id, IFNAMSIZ); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = qdisc_set_default(id); return ret; } #endif static int proc_do_dev_weight(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { static DEFINE_MUTEX(dev_weight_mutex); int ret, weight; mutex_lock(&dev_weight_mutex); ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write) { weight = READ_ONCE(weight_p); WRITE_ONCE(net_hotdata.dev_rx_weight, weight * dev_weight_rx_bias); WRITE_ONCE(net_hotdata.dev_tx_weight, weight * dev_weight_tx_bias); } mutex_unlock(&dev_weight_mutex); return ret; } static int proc_do_rss_key(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table fake_table; char buf[NETDEV_RSS_KEY_LEN * 3]; snprintf(buf, sizeof(buf), "%*phC", NETDEV_RSS_KEY_LEN, netdev_rss_key); fake_table.data = buf; fake_table.maxlen = sizeof(buf); return proc_dostring(&fake_table, write, buffer, lenp, ppos); } #ifdef CONFIG_BPF_JIT static int proc_dointvec_minmax_bpf_enable(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, jit_enable = *(int *)table->data; int min = *(int *)table->extra1; int max = *(int *)table->extra2; struct ctl_table tmp = *table; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; tmp.data = &jit_enable; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret) { if (jit_enable < 2 || (jit_enable == 2 && bpf_dump_raw_ok(current_cred()))) { *(int *)table->data = jit_enable; if (jit_enable == 2) pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n"); } else { ret = -EPERM; } } if (write && ret && min == max) pr_info_once("CONFIG_BPF_JIT_ALWAYS_ON is enabled, bpf_jit_enable is permanently set to 1.\n"); return ret; } # ifdef CONFIG_HAVE_EBPF_JIT static int proc_dointvec_minmax_bpf_restricted(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } # endif /* CONFIG_HAVE_EBPF_JIT */ static int proc_dolongvec_minmax_bpf_restricted(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif static struct ctl_table net_core_table[] = { { .procname = "mem_pcpu_rsv", .data = &net_hotdata.sysctl_mem_pcpu_rsv, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_mem_pcpu_rsv, }, { .procname = "dev_weight", .data = &weight_p, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_dev_weight, }, { .procname = "dev_weight_rx_bias", .data = &dev_weight_rx_bias, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_dev_weight, }, { .procname = "dev_weight_tx_bias", .data = &dev_weight_tx_bias, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_dev_weight, }, { .procname = "netdev_max_backlog", .data = &net_hotdata.max_backlog, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "netdev_rss_key", .data = &netdev_rss_key, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_do_rss_key, }, #ifdef CONFIG_BPF_JIT { .procname = "bpf_jit_enable", .data = &bpf_jit_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax_bpf_enable, # ifdef CONFIG_BPF_JIT_ALWAYS_ON .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_ONE, # else .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, # endif }, # ifdef CONFIG_HAVE_EBPF_JIT { .procname = "bpf_jit_harden", .data = &bpf_jit_harden, .maxlen = sizeof(int), .mode = 0600, .proc_handler = proc_dointvec_minmax_bpf_restricted, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "bpf_jit_kallsyms", .data = &bpf_jit_kallsyms, .maxlen = sizeof(int), .mode = 0600, .proc_handler = proc_dointvec_minmax_bpf_restricted, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, # endif { .procname = "bpf_jit_limit", .data = &bpf_jit_limit, .maxlen = sizeof(long), .mode = 0600, .proc_handler = proc_dolongvec_minmax_bpf_restricted, .extra1 = SYSCTL_LONG_ONE, .extra2 = &bpf_jit_limit_max, }, #endif { .procname = "netdev_tstamp_prequeue", .data = &net_hotdata.tstamp_prequeue, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "message_cost", .data = &net_ratelimit_state.interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "message_burst", .data = &net_ratelimit_state.burst, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "tstamp_allow_data", .data = &sysctl_tstamp_allow_data, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, #ifdef CONFIG_RPS { .procname = "rps_sock_flow_entries", .maxlen = sizeof(int), .mode = 0644, .proc_handler = rps_sock_flow_sysctl }, #endif #ifdef CONFIG_NET_FLOW_LIMIT { .procname = "flow_limit_cpu_bitmap", .mode = 0644, .proc_handler = flow_limit_cpu_sysctl }, { .procname = "flow_limit_table_len", .data = &netdev_flow_limit_table_len, .maxlen = sizeof(int), .mode = 0644, .proc_handler = flow_limit_table_len_sysctl }, #endif /* CONFIG_NET_FLOW_LIMIT */ #ifdef CONFIG_NET_RX_BUSY_POLL { .procname = "busy_poll", .data = &sysctl_net_busy_poll, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "busy_read", .data = &sysctl_net_busy_read, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #endif #ifdef CONFIG_NET_SCHED { .procname = "default_qdisc", .mode = 0644, .maxlen = IFNAMSIZ, .proc_handler = set_default_qdisc }, #endif { .procname = "netdev_budget", .data = &net_hotdata.netdev_budget, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "warnings", .data = &net_msg_warn, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_skb_frags", .data = &net_hotdata.sysctl_max_skb_frags, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &max_skb_frags, }, { .procname = "netdev_budget_usecs", .data = &net_hotdata.netdev_budget_usecs, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "fb_tunnels_only_for_init_net", .data = &sysctl_fb_tunnels_only_for_init_net, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "devconf_inherit_init_net", .data = &sysctl_devconf_inherit_init_net, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_THREE, }, { .procname = "high_order_alloc_disable", .data = &net_high_order_alloc_disable_key.key, .maxlen = sizeof(net_high_order_alloc_disable_key), .mode = 0644, .proc_handler = proc_do_static_key, }, { .procname = "gro_normal_batch", .data = &net_hotdata.gro_normal_batch, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, { .procname = "netdev_unregister_timeout_secs", .data = &netdev_unregister_timeout_secs, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &int_3600, }, { .procname = "skb_defer_max", .data = &net_hotdata.sysctl_skb_defer_max, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, }; static struct ctl_table netns_core_table[] = { #if IS_ENABLED(CONFIG_RPS) { .procname = "rps_default_mask", .data = &init_net, .mode = 0644, .proc_handler = rps_default_mask_sysctl }, #endif { .procname = "somaxconn", .data = &init_net.core.sysctl_somaxconn, .maxlen = sizeof(int), .mode = 0644, .extra1 = SYSCTL_ZERO, .proc_handler = proc_dointvec_minmax }, { .procname = "optmem_max", .data = &init_net.core.sysctl_optmem_max, .maxlen = sizeof(int), .mode = 0644, .extra1 = SYSCTL_ZERO, .proc_handler = proc_dointvec_minmax }, { .procname = "txrehash", .data = &init_net.core.sysctl_txrehash, .maxlen = sizeof(u8), .mode = 0644, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, .proc_handler = proc_dou8vec_minmax, }, /* sysctl_core_net_init() will set the values after this * to readonly in network namespaces */ { .procname = "wmem_max", .data = &sysctl_wmem_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_sndbuf, }, { .procname = "rmem_max", .data = &sysctl_rmem_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, }, { .procname = "wmem_default", .data = &sysctl_wmem_default, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_sndbuf, }, { .procname = "rmem_default", .data = &sysctl_rmem_default, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, }, }; static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str) { /* fallback tunnels for initns only */ if (!strncmp(str, "initns", 6)) sysctl_fb_tunnels_only_for_init_net = 1; /* no fallback tunnels anywhere */ else if (!strncmp(str, "none", 4)) sysctl_fb_tunnels_only_for_init_net = 2; return 1; } __setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup); static __net_init int sysctl_core_net_init(struct net *net) { size_t table_size = ARRAY_SIZE(netns_core_table); struct ctl_table *tbl; tbl = netns_core_table; if (!net_eq(net, &init_net)) { int i; tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL); if (tbl == NULL) goto err_dup; for (i = 0; i < table_size; ++i) { if (tbl[i].data == &sysctl_wmem_max) break; tbl[i].data += (char *)net - (char *)&init_net; } for (; i < table_size; ++i) tbl[i].mode &= ~0222; } net->core.sysctl_hdr = register_net_sysctl_sz(net, "net/core", tbl, table_size); if (net->core.sysctl_hdr == NULL) goto err_reg; return 0; err_reg: if (tbl != netns_core_table) kfree(tbl); err_dup: return -ENOMEM; } static __net_exit void sysctl_core_net_exit(struct net *net) { const struct ctl_table *tbl; tbl = net->core.sysctl_hdr->ctl_table_arg; unregister_net_sysctl_table(net->core.sysctl_hdr); BUG_ON(tbl == netns_core_table); #if IS_ENABLED(CONFIG_RPS) kfree(net->core.rps_default_mask); #endif kfree(tbl); } static __net_initdata struct pernet_operations sysctl_core_ops = { .init = sysctl_core_net_init, .exit = sysctl_core_net_exit, }; static __init int sysctl_core_init(void) { register_net_sysctl(&init_net, "net/core", net_core_table); return register_pernet_subsys(&sysctl_core_ops); } fs_initcall(sysctl_core_init); |
| 2250 2132 270 112 112 143 143 1941 1941 1311 1311 1252 912 913 913 912 912 818 103 175 188 234 89 212 4 184 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGE_REF_H #define _LINUX_PAGE_REF_H #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/tracepoint-defs.h> DECLARE_TRACEPOINT(page_ref_set); DECLARE_TRACEPOINT(page_ref_mod); DECLARE_TRACEPOINT(page_ref_mod_and_test); DECLARE_TRACEPOINT(page_ref_mod_and_return); DECLARE_TRACEPOINT(page_ref_mod_unless); DECLARE_TRACEPOINT(page_ref_freeze); DECLARE_TRACEPOINT(page_ref_unfreeze); #ifdef CONFIG_DEBUG_PAGE_REF /* * Ideally we would want to use the trace_<tracepoint>_enabled() helper * functions. But due to include header file issues, that is not * feasible. Instead we have to open code the static key functions. * * See trace_##name##_enabled(void) in include/linux/tracepoint.h */ #define page_ref_tracepoint_active(t) tracepoint_enabled(t) extern void __page_ref_set(struct page *page, int v); extern void __page_ref_mod(struct page *page, int v); extern void __page_ref_mod_and_test(struct page *page, int v, int ret); extern void __page_ref_mod_and_return(struct page *page, int v, int ret); extern void __page_ref_mod_unless(struct page *page, int v, int u); extern void __page_ref_freeze(struct page *page, int v, int ret); extern void __page_ref_unfreeze(struct page *page, int v); #else #define page_ref_tracepoint_active(t) false static inline void __page_ref_set(struct page *page, int v) { } static inline void __page_ref_mod(struct page *page, int v) { } static inline void __page_ref_mod_and_test(struct page *page, int v, int ret) { } static inline void __page_ref_mod_and_return(struct page *page, int v, int ret) { } static inline void __page_ref_mod_unless(struct page *page, int v, int u) { } static inline void __page_ref_freeze(struct page *page, int v, int ret) { } static inline void __page_ref_unfreeze(struct page *page, int v) { } #endif static inline int page_ref_count(const struct page *page) { return atomic_read(&page->_refcount); } /** * folio_ref_count - The reference count on this folio. * @folio: The folio. * * The refcount is usually incremented by calls to folio_get() and * decremented by calls to folio_put(). Some typical users of the * folio refcount: * * - Each reference from a page table * - The page cache * - Filesystem private data * - The LRU list * - Pipes * - Direct IO which references this page in the process address space * * Return: The number of references to this folio. */ static inline int folio_ref_count(const struct folio *folio) { return page_ref_count(&folio->page); } static inline int page_count(const struct page *page) { return folio_ref_count(page_folio(page)); } static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_refcount, v); if (page_ref_tracepoint_active(page_ref_set)) __page_ref_set(page, v); } static inline void folio_set_count(struct folio *folio, int v) { set_page_count(&folio->page, v); } /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) */ static inline void init_page_count(struct page *page) { set_page_count(page, 1); } static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, nr); } static inline void folio_ref_add(struct folio *folio, int nr) { page_ref_add(&folio->page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -nr); } static inline void folio_ref_sub(struct folio *folio, int nr) { page_ref_sub(&folio->page, nr); } static inline int folio_ref_sub_return(struct folio *folio, int nr) { int ret = atomic_sub_return(nr, &folio->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(&folio->page, -nr, ret); return ret; } static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, 1); } static inline void folio_ref_inc(struct folio *folio) { page_ref_inc(&folio->page); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -1); } static inline void folio_ref_dec(struct folio *folio) { page_ref_dec(&folio->page); } static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -nr, ret); return ret; } static inline int folio_ref_sub_and_test(struct folio *folio, int nr) { return page_ref_sub_and_test(&folio->page, nr); } static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, 1, ret); return ret; } static inline int folio_ref_inc_return(struct folio *folio) { return page_ref_inc_return(&folio->page); } static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -1, ret); return ret; } static inline int folio_ref_dec_and_test(struct folio *folio) { return page_ref_dec_and_test(&folio->page); } static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -1, ret); return ret; } static inline int folio_ref_dec_return(struct folio *folio) { return page_ref_dec_return(&folio->page); } static inline bool page_ref_add_unless(struct page *page, int nr, int u) { bool ret = false; rcu_read_lock(); /* avoid writing to the vmemmap area being remapped */ if (!page_is_fake_head(page) && page_ref_count(page) != u) ret = atomic_add_unless(&page->_refcount, nr, u); rcu_read_unlock(); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u) { return page_ref_add_unless(&folio->page, nr, u); } /** * folio_try_get - Attempt to increase the refcount on a folio. * @folio: The folio. * * If you do not already have a reference to a folio, you can attempt to * get one using this function. It may fail if, for example, the folio * has been freed since you found a pointer to it, or it is frozen for * the purposes of splitting or migration. * * Return: True if the reference count was successfully incremented. */ static inline bool folio_try_get(struct folio *folio) { return folio_ref_add_unless(folio, 1, 0); } static inline bool folio_ref_try_add(struct folio *folio, int count) { return folio_ref_add_unless(folio, count, 0); } static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); if (page_ref_tracepoint_active(page_ref_freeze)) __page_ref_freeze(page, count, ret); return ret; } static inline int folio_ref_freeze(struct folio *folio, int count) { return page_ref_freeze(&folio->page, count); } static inline void page_ref_unfreeze(struct page *page, int count) { VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); atomic_set_release(&page->_refcount, count); if (page_ref_tracepoint_active(page_ref_unfreeze)) __page_ref_unfreeze(page, count); } static inline void folio_ref_unfreeze(struct folio *folio, int count) { page_ref_unfreeze(&folio->page, count); } #endif |
| 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 | #include <linux/gfp.h> #include <linux/initrd.h> #include <linux/ioport.h> #include <linux/swap.h> #include <linux/memblock.h> #include <linux/swapfile.h> #include <linux/swapops.h> #include <linux/kmemleak.h> #include <linux/sched/task.h> #include <linux/execmem.h> #include <asm/set_memory.h> #include <asm/cpu_device_id.h> #include <asm/e820/api.h> #include <asm/init.h> #include <asm/page.h> #include <asm/page_types.h> #include <asm/sections.h> #include <asm/setup.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <asm/proto.h> #include <asm/dma.h> /* for MAX_DMA_PFN */ #include <asm/kaslr.h> #include <asm/hypervisor.h> #include <asm/cpufeature.h> #include <asm/pti.h> #include <asm/text-patching.h> #include <asm/memtype.h> #include <asm/paravirt.h> /* * We need to define the tracepoints somewhere, and tlb.c * is only compiled when SMP=y. */ #include <trace/events/tlb.h> #include "mm_internal.h" /* * Tables translating between page_cache_type_t and pte encoding. * * The default values are defined statically as minimal supported mode; * WC and WT fall back to UC-. pat_init() updates these values to support * more cache modes, WC and WT, when it is safe to do so. See pat_init() * for the details. Note, __early_ioremap() used during early boot-time * takes pgprot_t (pte encoding) and does not use these tables. * * Index into __cachemode2pte_tbl[] is the cachemode. * * Index into __pte2cachemode_tbl[] are the caching attribute bits of the pte * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT) at index bit positions 0, 1, 2. */ static uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = { [_PAGE_CACHE_MODE_WB ] = 0 | 0 , [_PAGE_CACHE_MODE_WC ] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC_MINUS] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC ] = _PAGE_PWT | _PAGE_PCD, [_PAGE_CACHE_MODE_WT ] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_WP ] = 0 | _PAGE_PCD, }; unsigned long cachemode2protval(enum page_cache_mode pcm) { if (likely(pcm == 0)) return 0; return __cachemode2pte_tbl[pcm]; } EXPORT_SYMBOL(cachemode2protval); static uint8_t __pte2cachemode_tbl[8] = { [__pte2cm_idx( 0 | 0 | 0 )] = _PAGE_CACHE_MODE_WB, [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx( 0 | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC, [__pte2cm_idx( 0 | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB, [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(0 | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC, }; /* * Check that the write-protect PAT entry is set for write-protect. * To do this without making assumptions how PAT has been set up (Xen has * another layout than the kernel), translate the _PAGE_CACHE_MODE_WP cache * mode via the __cachemode2pte_tbl[] into protection bits (those protection * bits will select a cache mode of WP or better), and then translate the * protection bits back into the cache mode using __pte2cm_idx() and the * __pte2cachemode_tbl[] array. This will return the really used cache mode. */ bool x86_has_pat_wp(void) { uint16_t prot = __cachemode2pte_tbl[_PAGE_CACHE_MODE_WP]; return __pte2cachemode_tbl[__pte2cm_idx(prot)] == _PAGE_CACHE_MODE_WP; } enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) { unsigned long masked; masked = pgprot_val(pgprot) & _PAGE_CACHE_MASK; if (likely(masked == 0)) return 0; return __pte2cachemode_tbl[__pte2cm_idx(masked)]; } static unsigned long __initdata pgt_buf_start; static unsigned long __initdata pgt_buf_end; static unsigned long __initdata pgt_buf_top; static unsigned long min_pfn_mapped; static bool __initdata can_use_brk_pgt = true; /* * Pages returned are already directly mapped. * * Changing that is likely to break Xen, see commit: * * 279b706 x86,xen: introduce x86_init.mapping.pagetable_reserve * * for detailed information. */ __ref void *alloc_low_pages(unsigned int num) { unsigned long pfn; int i; if (after_bootmem) { unsigned int order; order = get_order((unsigned long)num << PAGE_SHIFT); return (void *)__get_free_pages(GFP_ATOMIC | __GFP_ZERO, order); } if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) { unsigned long ret = 0; if (min_pfn_mapped < max_pfn_mapped) { ret = memblock_phys_alloc_range( PAGE_SIZE * num, PAGE_SIZE, min_pfn_mapped << PAGE_SHIFT, max_pfn_mapped << PAGE_SHIFT); } if (!ret && can_use_brk_pgt) ret = __pa(extend_brk(PAGE_SIZE * num, PAGE_SIZE)); if (!ret) panic("alloc_low_pages: can not alloc memory"); pfn = ret >> PAGE_SHIFT; } else { pfn = pgt_buf_end; pgt_buf_end += num; } for (i = 0; i < num; i++) { void *adr; adr = __va((pfn + i) << PAGE_SHIFT); clear_page(adr); } return __va(pfn << PAGE_SHIFT); } /* * By default need to be able to allocate page tables below PGD firstly for * the 0-ISA_END_ADDRESS range and secondly for the initial PMD_SIZE mapping. * With KASLR memory randomization, depending on the machine e820 memory and the * PUD alignment, twice that many pages may be needed when KASLR memory * randomization is enabled. */ #ifndef CONFIG_X86_5LEVEL #define INIT_PGD_PAGE_TABLES 3 #else #define INIT_PGD_PAGE_TABLES 4 #endif #ifndef CONFIG_RANDOMIZE_MEMORY #define INIT_PGD_PAGE_COUNT (2 * INIT_PGD_PAGE_TABLES) #else #define INIT_PGD_PAGE_COUNT (4 * INIT_PGD_PAGE_TABLES) #endif #define INIT_PGT_BUF_SIZE (INIT_PGD_PAGE_COUNT * PAGE_SIZE) RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); void __init early_alloc_pgt_buf(void) { unsigned long tables = INIT_PGT_BUF_SIZE; phys_addr_t base; base = __pa(extend_brk(tables, PAGE_SIZE)); pgt_buf_start = base >> PAGE_SHIFT; pgt_buf_end = pgt_buf_start; pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT); } int after_bootmem; early_param_on_off("gbpages", "nogbpages", direct_gbpages, CONFIG_X86_DIRECT_GBPAGES); struct map_range { unsigned long start; unsigned long end; unsigned page_size_mask; }; static int page_size_mask; /* * Save some of cr4 feature set we're using (e.g. Pentium 4MB * enable and PPro Global page enable), so that any CPU's that boot * up after us can get the correct flags. Invoked on the boot CPU. */ static inline void cr4_set_bits_and_update_boot(unsigned long mask) { mmu_cr4_features |= mask; if (trampoline_cr4_features) *trampoline_cr4_features = mmu_cr4_features; cr4_set_bits(mask); } static void __init probe_page_size_mask(void) { /* * For pagealloc debugging, identity mapping will use small pages. * This will simplify cpa(), which otherwise needs to support splitting * large pages into small in interrupt context, etc. */ if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled()) page_size_mask |= 1 << PG_LEVEL_2M; else direct_gbpages = 0; /* Enable PSE if available */ if (boot_cpu_has(X86_FEATURE_PSE)) cr4_set_bits_and_update_boot(X86_CR4_PSE); /* Enable PGE if available */ __supported_pte_mask &= ~_PAGE_GLOBAL; if (boot_cpu_has(X86_FEATURE_PGE)) { cr4_set_bits_and_update_boot(X86_CR4_PGE); __supported_pte_mask |= _PAGE_GLOBAL; } /* By the default is everything supported: */ __default_kernel_pte_mask = __supported_pte_mask; /* Except when with PTI where the kernel is mostly non-Global: */ if (cpu_feature_enabled(X86_FEATURE_PTI)) __default_kernel_pte_mask &= ~_PAGE_GLOBAL; /* Enable 1 GB linear kernel mappings if available: */ if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) { printk(KERN_INFO "Using GB pages for direct mapping\n"); page_size_mask |= 1 << PG_LEVEL_1G; } else { direct_gbpages = 0; } } /* * INVLPG may not properly flush Global entries * on these CPUs when PCIDs are enabled. */ static const struct x86_cpu_id invlpg_miss_ids[] = { X86_MATCH_VFM(INTEL_ALDERLAKE, 0), X86_MATCH_VFM(INTEL_ALDERLAKE_L, 0), X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, 0), X86_MATCH_VFM(INTEL_RAPTORLAKE, 0), X86_MATCH_VFM(INTEL_RAPTORLAKE_P, 0), X86_MATCH_VFM(INTEL_RAPTORLAKE_S, 0), {} }; static void setup_pcid(void) { if (!IS_ENABLED(CONFIG_X86_64)) return; if (!boot_cpu_has(X86_FEATURE_PCID)) return; if (x86_match_cpu(invlpg_miss_ids)) { pr_info("Incomplete global flushes, disabling PCID"); setup_clear_cpu_cap(X86_FEATURE_PCID); return; } if (boot_cpu_has(X86_FEATURE_PGE)) { /* * This can't be cr4_set_bits_and_update_boot() -- the * trampoline code can't handle CR4.PCIDE and it wouldn't * do any good anyway. Despite the name, * cr4_set_bits_and_update_boot() doesn't actually cause * the bits in question to remain set all the way through * the secondary boot asm. * * Instead, we brute-force it and set CR4.PCIDE manually in * start_secondary(). */ cr4_set_bits(X86_CR4_PCIDE); } else { /* * flush_tlb_all(), as currently implemented, won't work if * PCID is on but PGE is not. Since that combination * doesn't exist on real hardware, there's no reason to try * to fully support it, but it's polite to avoid corrupting * data if we're on an improperly configured VM. */ setup_clear_cpu_cap(X86_FEATURE_PCID); } } #ifdef CONFIG_X86_32 #define NR_RANGE_MR 3 #else /* CONFIG_X86_64 */ #define NR_RANGE_MR 5 #endif static int __meminit save_mr(struct map_range *mr, int nr_range, unsigned long start_pfn, unsigned long end_pfn, unsigned long page_size_mask) { if (start_pfn < end_pfn) { if (nr_range >= NR_RANGE_MR) panic("run out of range for init_memory_mapping\n"); mr[nr_range].start = start_pfn<<PAGE_SHIFT; mr[nr_range].end = end_pfn<<PAGE_SHIFT; mr[nr_range].page_size_mask = page_size_mask; nr_range++; } return nr_range; } /* * adjust the page_size_mask for small range to go with * big page size instead small one if nearby are ram too. */ static void __ref adjust_range_page_size_mask(struct map_range *mr, int nr_range) { int i; for (i = 0; i < nr_range; i++) { if ((page_size_mask & (1<<PG_LEVEL_2M)) && !(mr[i].page_size_mask & (1<<PG_LEVEL_2M))) { unsigned long start = round_down(mr[i].start, PMD_SIZE); unsigned long end = round_up(mr[i].end, PMD_SIZE); #ifdef CONFIG_X86_32 if ((end >> PAGE_SHIFT) > max_low_pfn) continue; #endif if (memblock_is_region_memory(start, end - start)) mr[i].page_size_mask |= 1<<PG_LEVEL_2M; } if ((page_size_mask & (1<<PG_LEVEL_1G)) && !(mr[i].page_size_mask & (1<<PG_LEVEL_1G))) { unsigned long start = round_down(mr[i].start, PUD_SIZE); unsigned long end = round_up(mr[i].end, PUD_SIZE); if (memblock_is_region_memory(start, end - start)) mr[i].page_size_mask |= 1<<PG_LEVEL_1G; } } } static const char *page_size_string(struct map_range *mr) { static const char str_1g[] = "1G"; static const char str_2m[] = "2M"; static const char str_4m[] = "4M"; static const char str_4k[] = "4k"; if (mr->page_size_mask & (1<<PG_LEVEL_1G)) return str_1g; /* * 32-bit without PAE has a 4M large page size. * PG_LEVEL_2M is misnamed, but we can at least * print out the right size in the string. */ if (IS_ENABLED(CONFIG_X86_32) && !IS_ENABLED(CONFIG_X86_PAE) && mr->page_size_mask & (1<<PG_LEVEL_2M)) return str_4m; if (mr->page_size_mask & (1<<PG_LEVEL_2M)) return str_2m; return str_4k; } static int __meminit split_mem_range(struct map_range *mr, int nr_range, unsigned long start, unsigned long end) { unsigned long start_pfn, end_pfn, limit_pfn; unsigned long pfn; int i; limit_pfn = PFN_DOWN(end); /* head if not big page alignment ? */ pfn = start_pfn = PFN_DOWN(start); #ifdef CONFIG_X86_32 /* * Don't use a large page for the first 2/4MB of memory * because there are often fixed size MTRRs in there * and overlapping MTRRs into large pages can cause * slowdowns. */ if (pfn == 0) end_pfn = PFN_DOWN(PMD_SIZE); else end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #else /* CONFIG_X86_64 */ end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #endif if (end_pfn > limit_pfn) end_pfn = limit_pfn; if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); pfn = end_pfn; } /* big page (2M) range */ start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #ifdef CONFIG_X86_32 end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); #else /* CONFIG_X86_64 */ end_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE)); if (end_pfn > round_down(limit_pfn, PFN_DOWN(PMD_SIZE))) end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); #endif if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & (1<<PG_LEVEL_2M)); pfn = end_pfn; } #ifdef CONFIG_X86_64 /* big page (1G) range */ start_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE)); end_pfn = round_down(limit_pfn, PFN_DOWN(PUD_SIZE)); if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G))); pfn = end_pfn; } /* tail is not big page (1G) alignment */ start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & (1<<PG_LEVEL_2M)); pfn = end_pfn; } #endif /* tail is not big page (2M) alignment */ start_pfn = pfn; end_pfn = limit_pfn; nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); if (!after_bootmem) adjust_range_page_size_mask(mr, nr_range); /* try to merge same page size and continuous */ for (i = 0; nr_range > 1 && i < nr_range - 1; i++) { unsigned long old_start; if (mr[i].end != mr[i+1].start || mr[i].page_size_mask != mr[i+1].page_size_mask) continue; /* move it */ old_start = mr[i].start; memmove(&mr[i], &mr[i+1], (nr_range - 1 - i) * sizeof(struct map_range)); mr[i--].start = old_start; nr_range--; } for (i = 0; i < nr_range; i++) pr_debug(" [mem %#010lx-%#010lx] page %s\n", mr[i].start, mr[i].end - 1, page_size_string(&mr[i])); return nr_range; } struct range pfn_mapped[E820_MAX_ENTRIES]; int nr_pfn_mapped; static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn) { nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_MAX_ENTRIES, nr_pfn_mapped, start_pfn, end_pfn); nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_MAX_ENTRIES); max_pfn_mapped = max(max_pfn_mapped, end_pfn); if (start_pfn < (1UL<<(32-PAGE_SHIFT))) max_low_pfn_mapped = max(max_low_pfn_mapped, min(end_pfn, 1UL<<(32-PAGE_SHIFT))); } bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn) { int i; for (i = 0; i < nr_pfn_mapped; i++) if ((start_pfn >= pfn_mapped[i].start) && (end_pfn <= pfn_mapped[i].end)) return true; return false; } /* * Setup the direct mapping of the physical memory at PAGE_OFFSET. * This runs before bootmem is initialized and gets pages directly from * the physical memory. To access them they are temporarily mapped. */ unsigned long __ref init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot) { struct map_range mr[NR_RANGE_MR]; unsigned long ret = 0; int nr_range, i; pr_debug("init_memory_mapping: [mem %#010lx-%#010lx]\n", start, end - 1); memset(mr, 0, sizeof(mr)); nr_range = split_mem_range(mr, 0, start, end); for (i = 0; i < nr_range; i++) ret = kernel_physical_mapping_init(mr[i].start, mr[i].end, mr[i].page_size_mask, prot); add_pfn_range_mapped(start >> PAGE_SHIFT, ret >> PAGE_SHIFT); return ret >> PAGE_SHIFT; } /* * We need to iterate through the E820 memory map and create direct mappings * for only E820_TYPE_RAM and E820_KERN_RESERVED regions. We cannot simply * create direct mappings for all pfns from [0 to max_low_pfn) and * [4GB to max_pfn) because of possible memory holes in high addresses * that cannot be marked as UC by fixed/variable range MTRRs. * Depending on the alignment of E820 ranges, this may possibly result * in using smaller size (i.e. 4K instead of 2M or 1G) page tables. * * init_mem_mapping() calls init_range_memory_mapping() with big range. * That range would have hole in the middle or ends, and only ram parts * will be mapped in init_range_memory_mapping(). */ static unsigned long __init init_range_memory_mapping( unsigned long r_start, unsigned long r_end) { unsigned long start_pfn, end_pfn; unsigned long mapped_ram_size = 0; int i; for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { u64 start = clamp_val(PFN_PHYS(start_pfn), r_start, r_end); u64 end = clamp_val(PFN_PHYS(end_pfn), r_start, r_end); if (start >= end) continue; /* * if it is overlapping with brk pgt, we need to * alloc pgt buf from memblock instead. */ can_use_brk_pgt = max(start, (u64)pgt_buf_end<<PAGE_SHIFT) >= min(end, (u64)pgt_buf_top<<PAGE_SHIFT); init_memory_mapping(start, end, PAGE_KERNEL); mapped_ram_size += end - start; can_use_brk_pgt = true; } return mapped_ram_size; } static unsigned long __init get_new_step_size(unsigned long step_size) { /* * Initial mapped size is PMD_SIZE (2M). * We can not set step_size to be PUD_SIZE (1G) yet. * In worse case, when we cross the 1G boundary, and * PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k) * to map 1G range with PTE. Hence we use one less than the * difference of page table level shifts. * * Don't need to worry about overflow in the top-down case, on 32bit, * when step_size is 0, round_down() returns 0 for start, and that * turns it into 0x100000000ULL. * In the bottom-up case, round_up(x, 0) returns 0 though too, which * needs to be taken into consideration by the code below. */ return step_size << (PMD_SHIFT - PAGE_SHIFT - 1); } /** * memory_map_top_down - Map [map_start, map_end) top down * @map_start: start address of the target memory range * @map_end: end address of the target memory range * * This function will setup direct mapping for memory range * [map_start, map_end) in top-down. That said, the page tables * will be allocated at the end of the memory, and we map the * memory in top-down. */ static void __init memory_map_top_down(unsigned long map_start, unsigned long map_end) { unsigned long real_end, last_start; unsigned long step_size; unsigned long addr; unsigned long mapped_ram_size = 0; /* * Systems that have many reserved areas near top of the memory, * e.g. QEMU with less than 1G RAM and EFI enabled, or Xen, will * require lots of 4K mappings which may exhaust pgt_buf. * Start with top-most PMD_SIZE range aligned at PMD_SIZE to ensure * there is enough mapped memory that can be allocated from * memblock. */ addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start, map_end); memblock_phys_free(addr, PMD_SIZE); real_end = addr + PMD_SIZE; /* step_size need to be small so pgt_buf from BRK could cover it */ step_size = PMD_SIZE; max_pfn_mapped = 0; /* will get exact value next */ min_pfn_mapped = real_end >> PAGE_SHIFT; last_start = real_end; /* * We start from the top (end of memory) and go to the bottom. * The memblock_find_in_range() gets us a block of RAM from the * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages * for page table. */ while (last_start > map_start) { unsigned long start; if (last_start > step_size) { start = round_down(last_start - 1, step_size); if (start < map_start) start = map_start; } else start = map_start; mapped_ram_size += init_range_memory_mapping(start, last_start); last_start = start; min_pfn_mapped = last_start >> PAGE_SHIFT; if (mapped_ram_size >= step_size) step_size = get_new_step_size(step_size); } if (real_end < map_end) init_range_memory_mapping(real_end, map_end); } /** * memory_map_bottom_up - Map [map_start, map_end) bottom up * @map_start: start address of the target memory range * @map_end: end address of the target memory range * * This function will setup direct mapping for memory range * [map_start, map_end) in bottom-up. Since we have limited the * bottom-up allocation above the kernel, the page tables will * be allocated just above the kernel and we map the memory * in [map_start, map_end) in bottom-up. */ static void __init memory_map_bottom_up(unsigned long map_start, unsigned long map_end) { unsigned long next, start; unsigned long mapped_ram_size = 0; /* step_size need to be small so pgt_buf from BRK could cover it */ unsigned long step_size = PMD_SIZE; start = map_start; min_pfn_mapped = start >> PAGE_SHIFT; /* * We start from the bottom (@map_start) and go to the top (@map_end). * The memblock_find_in_range() gets us a block of RAM from the * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages * for page table. */ while (start < map_end) { if (step_size && map_end - start > step_size) { next = round_up(start + 1, step_size); if (next > map_end) next = map_end; } else { next = map_end; } mapped_ram_size += init_range_memory_mapping(start, next); start = next; if (mapped_ram_size >= step_size) step_size = get_new_step_size(step_size); } } /* * The real mode trampoline, which is required for bootstrapping CPUs * occupies only a small area under the low 1MB. See reserve_real_mode() * for details. * * If KASLR is disabled the first PGD entry of the direct mapping is copied * to map the real mode trampoline. * * If KASLR is enabled, copy only the PUD which covers the low 1MB * area. This limits the randomization granularity to 1GB for both 4-level * and 5-level paging. */ static void __init init_trampoline(void) { #ifdef CONFIG_X86_64 /* * The code below will alias kernel page-tables in the user-range of the * address space, including the Global bit. So global TLB entries will * be created when using the trampoline page-table. */ if (!kaslr_memory_enabled()) trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)]; else init_trampoline_kaslr(); #endif } void __init init_mem_mapping(void) { unsigned long end; pti_check_boottime_disable(); probe_page_size_mask(); setup_pcid(); #ifdef CONFIG_X86_64 end = max_pfn << PAGE_SHIFT; #else end = max_low_pfn << PAGE_SHIFT; #endif /* the ISA range is always mapped regardless of memory holes */ init_memory_mapping(0, ISA_END_ADDRESS, PAGE_KERNEL); /* Init the trampoline, possibly with KASLR memory offset */ init_trampoline(); /* * If the allocation is in bottom-up direction, we setup direct mapping * in bottom-up, otherwise we setup direct mapping in top-down. */ if (memblock_bottom_up()) { unsigned long kernel_end = __pa_symbol(_end); /* * we need two separate calls here. This is because we want to * allocate page tables above the kernel. So we first map * [kernel_end, end) to make memory above the kernel be mapped * as soon as possible. And then use page tables allocated above * the kernel to map [ISA_END_ADDRESS, kernel_end). */ memory_map_bottom_up(kernel_end, end); memory_map_bottom_up(ISA_END_ADDRESS, kernel_end); } else { memory_map_top_down(ISA_END_ADDRESS, end); } #ifdef CONFIG_X86_64 if (max_pfn > max_low_pfn) { /* can we preserve max_low_pfn ?*/ max_low_pfn = max_pfn; } #else early_ioremap_page_table_range_init(); #endif load_cr3(swapper_pg_dir); __flush_tlb_all(); x86_init.hyper.init_mem_mapping(); early_memtest(0, max_pfn_mapped << PAGE_SHIFT); } /* * Initialize an mm_struct to be used during poking and a pointer to be used * during patching. */ void __init poking_init(void) { spinlock_t *ptl; pte_t *ptep; poking_mm = mm_alloc(); BUG_ON(!poking_mm); /* Xen PV guests need the PGD to be pinned. */ paravirt_enter_mmap(poking_mm); /* * Randomize the poking address, but make sure that the following page * will be mapped at the same PMD. We need 2 pages, so find space for 3, * and adjust the address if the PMD ends after the first one. */ poking_addr = TASK_UNMAPPED_BASE; if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) poking_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) % (TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE); if (((poking_addr + PAGE_SIZE) & ~PMD_MASK) == 0) poking_addr += PAGE_SIZE; /* * We need to trigger the allocation of the page-tables that will be * needed for poking now. Later, poking may be performed in an atomic * section, which might cause allocation to fail. */ ptep = get_locked_pte(poking_mm, poking_addr, &ptl); BUG_ON(!ptep); pte_unmap_unlock(ptep, ptl); } /* * devmem_is_allowed() checks to see if /dev/mem access to a certain address * is valid. The argument is a physical page number. * * On x86, access has to be given to the first megabyte of RAM because that * area traditionally contains BIOS code and data regions used by X, dosemu, * and similar apps. Since they map the entire memory range, the whole range * must be allowed (for mapping), but any areas that would otherwise be * disallowed are flagged as being "zero filled" instead of rejected. * Access has to be given to non-kernel-ram areas as well, these contain the * PCI mmio resources as well as potential bios/acpi data regions. */ int devmem_is_allowed(unsigned long pagenr) { if (region_intersects(PFN_PHYS(pagenr), PAGE_SIZE, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE) != REGION_DISJOINT) { /* * For disallowed memory regions in the low 1MB range, * request that the page be shown as all zeros. */ if (pagenr < 256) return 2; return 0; } /* * This must follow RAM test, since System RAM is considered a * restricted resource under CONFIG_STRICT_DEVMEM. */ if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) { /* Low 1MB bypasses iomem restrictions. */ if (pagenr < 256) return 1; return 0; } return 1; } void free_init_pages(const char *what, unsigned long begin, unsigned long end) { unsigned long begin_aligned, end_aligned; /* Make sure boundaries are page aligned */ begin_aligned = PAGE_ALIGN(begin); end_aligned = end & PAGE_MASK; if (WARN_ON(begin_aligned != begin || end_aligned != end)) { begin = begin_aligned; end = end_aligned; } if (begin >= end) return; /* * If debugging page accesses then do not free this memory but * mark them not present - any buggy init-section access will * create a kernel page fault: */ if (debug_pagealloc_enabled()) { pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n", begin, end - 1); /* * Inform kmemleak about the hole in the memory since the * corresponding pages will be unmapped. */ kmemleak_free_part((void *)begin, end - begin); set_memory_np(begin, (end - begin) >> PAGE_SHIFT); } else { /* * We just marked the kernel text read only above, now that * we are going to free part of that, we need to make that * writeable and non-executable first. */ set_memory_nx(begin, (end - begin) >> PAGE_SHIFT); set_memory_rw(begin, (end - begin) >> PAGE_SHIFT); free_reserved_area((void *)begin, (void *)end, POISON_FREE_INITMEM, what); } } /* * begin/end can be in the direct map or the "high kernel mapping" * used for the kernel image only. free_init_pages() will do the * right thing for either kind of address. */ void free_kernel_image_pages(const char *what, void *begin, void *end) { unsigned long begin_ul = (unsigned long)begin; unsigned long end_ul = (unsigned long)end; unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT; free_init_pages(what, begin_ul, end_ul); /* * PTI maps some of the kernel into userspace. For performance, * this includes some kernel areas that do not contain secrets. * Those areas might be adjacent to the parts of the kernel image * being freed, which may contain secrets. Remove the "high kernel * image mapping" for these freed areas, ensuring they are not even * potentially vulnerable to Meltdown regardless of the specific * optimizations PTI is currently using. * * The "noalias" prevents unmapping the direct map alias which is * needed to access the freed pages. * * This is only valid for 64bit kernels. 32bit has only one mapping * which can't be treated in this way for obvious reasons. */ if (IS_ENABLED(CONFIG_X86_64) && cpu_feature_enabled(X86_FEATURE_PTI)) set_memory_np_noalias(begin_ul, len_pages); } void __ref free_initmem(void) { e820__reallocate_tables(); mem_encrypt_free_decrypted_mem(); free_kernel_image_pages("unused kernel image (initmem)", &__init_begin, &__init_end); } #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { /* * end could be not aligned, and We can not align that, * decompressor could be confused by aligned initrd_end * We already reserve the end partial page before in * - i386_start_kernel() * - x86_64_start_kernel() * - relocate_initrd() * So here We can do PAGE_ALIGN() safely to get partial page to be freed */ free_init_pages("initrd", start, PAGE_ALIGN(end)); } #endif void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(MAX_DMA_PFN, max_low_pfn); #endif #ifdef CONFIG_ZONE_DMA32 max_zone_pfns[ZONE_DMA32] = min(MAX_DMA32_PFN, max_low_pfn); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM max_zone_pfns[ZONE_HIGHMEM] = max_pfn; #endif free_area_init(max_zone_pfns); } __visible DEFINE_PER_CPU_ALIGNED(struct tlb_state, cpu_tlbstate) = { .loaded_mm = &init_mm, .next_asid = 1, .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ }; #ifdef CONFIG_ADDRESS_MASKING DEFINE_PER_CPU(u64, tlbstate_untag_mask); EXPORT_PER_CPU_SYMBOL(tlbstate_untag_mask); #endif void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache) { /* entry 0 MUST be WB (hardwired to speed up translations) */ BUG_ON(!entry && cache != _PAGE_CACHE_MODE_WB); __cachemode2pte_tbl[cache] = __cm_idx2pte(entry); __pte2cachemode_tbl[entry] = cache; } #ifdef CONFIG_SWAP unsigned long arch_max_swapfile_size(void) { unsigned long pages; pages = generic_max_swapfile_size(); if (boot_cpu_has_bug(X86_BUG_L1TF) && l1tf_mitigation != L1TF_MITIGATION_OFF) { /* Limit the swap file size to MAX_PA/2 for L1TF workaround */ unsigned long long l1tf_limit = l1tf_pfn_limit(); /* * We encode swap offsets also with 3 bits below those for pfn * which makes the usable limit higher. */ #if CONFIG_PGTABLE_LEVELS > 2 l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT; #endif pages = min_t(unsigned long long, l1tf_limit, pages); } return pages; } #endif #ifdef CONFIG_EXECMEM static struct execmem_info execmem_info __ro_after_init; struct execmem_info __init *execmem_arch_setup(void) { unsigned long start, offset = 0; if (kaslr_enabled()) offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE; start = MODULES_VADDR + offset; execmem_info = (struct execmem_info){ .ranges = { [EXECMEM_DEFAULT] = { .flags = EXECMEM_KASAN_SHADOW, .start = start, .end = MODULES_END, .pgprot = PAGE_KERNEL, .alignment = MODULE_ALIGN, }, }, }; return &execmem_info; } #endif /* CONFIG_EXECMEM */ |
| 26 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Dynamic byte queue limits. See include/linux/dynamic_queue_limits.h * * Copyright (c) 2011, Tom Herbert <therbert@google.com> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/dynamic_queue_limits.h> #include <linux/compiler.h> #include <linux/export.h> #include <trace/events/napi.h> #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0) #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0) static void dql_check_stall(struct dql *dql, unsigned short stall_thrs) { unsigned long now; if (!stall_thrs) return; now = jiffies; /* Check for a potential stall */ if (time_after_eq(now, dql->last_reap + stall_thrs)) { unsigned long hist_head, t, start, end; /* We are trying to detect a period of at least @stall_thrs * jiffies without any Tx completions, but during first half * of which some Tx was posted. */ dqs_again: hist_head = READ_ONCE(dql->history_head); /* pairs with smp_wmb() in dql_queued() */ smp_rmb(); /* Get the previous entry in the ring buffer, which is the * oldest sample. */ start = (hist_head - DQL_HIST_LEN + 1) * BITS_PER_LONG; /* Advance start to continue from the last reap time */ if (time_before(start, dql->last_reap + 1)) start = dql->last_reap + 1; /* Newest sample we should have already seen a completion for */ end = hist_head * BITS_PER_LONG + (BITS_PER_LONG - 1); /* Shrink the search space to [start, (now - start_thrs/2)] if * `end` is beyond the stall zone */ if (time_before(now, end + stall_thrs / 2)) end = now - stall_thrs / 2; /* Search for the queued time in [t, end] */ for (t = start; time_before_eq(t, end); t++) if (test_bit(t % (DQL_HIST_LEN * BITS_PER_LONG), dql->history)) break; /* Variable t contains the time of the queue */ if (!time_before_eq(t, end)) goto no_stall; /* The ring buffer was modified in the meantime, retry */ if (hist_head != READ_ONCE(dql->history_head)) goto dqs_again; dql->stall_cnt++; dql->stall_max = max_t(unsigned short, dql->stall_max, now - t); trace_dql_stall_detected(dql->stall_thrs, now - t, dql->last_reap, dql->history_head, now, dql->history); } no_stall: dql->last_reap = now; } /* Records completed count and recalculates the queue limit */ void dql_completed(struct dql *dql, unsigned int count) { unsigned int inprogress, prev_inprogress, limit; unsigned int ovlimit, completed, num_queued; unsigned short stall_thrs; bool all_prev_completed; num_queued = READ_ONCE(dql->num_queued); /* Read stall_thrs in advance since it belongs to the same (first) * cache line as ->num_queued. This way, dql_check_stall() does not * need to touch the first cache line again later, reducing the window * of possible false sharing. */ stall_thrs = READ_ONCE(dql->stall_thrs); /* Can't complete more than what's in queue */ BUG_ON(count > num_queued - dql->num_completed); completed = dql->num_completed + count; limit = dql->limit; ovlimit = POSDIFF(num_queued - dql->num_completed, limit); inprogress = num_queued - completed; prev_inprogress = dql->prev_num_queued - dql->num_completed; all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued); if ((ovlimit && !inprogress) || (dql->prev_ovlimit && all_prev_completed)) { /* * Queue considered starved if: * - The queue was over-limit in the last interval, * and there is no more data in the queue. * OR * - The queue was over-limit in the previous interval and * when enqueuing it was possible that all queued data * had been consumed. This covers the case when queue * may have becomes starved between completion processing * running and next time enqueue was scheduled. * * When queue is starved increase the limit by the amount * of bytes both sent and completed in the last interval, * plus any previous over-limit. */ limit += POSDIFF(completed, dql->prev_num_queued) + dql->prev_ovlimit; dql->slack_start_time = jiffies; dql->lowest_slack = UINT_MAX; } else if (inprogress && prev_inprogress && !all_prev_completed) { /* * Queue was not starved, check if the limit can be decreased. * A decrease is only considered if the queue has been busy in * the whole interval (the check above). * * If there is slack, the amount of excess data queued above * the amount needed to prevent starvation, the queue limit * can be decreased. To avoid hysteresis we consider the * minimum amount of slack found over several iterations of the * completion routine. */ unsigned int slack, slack_last_objs; /* * Slack is the maximum of * - The queue limit plus previous over-limit minus twice * the number of objects completed. Note that two times * number of completed bytes is a basis for an upper bound * of the limit. * - Portion of objects in the last queuing operation that * was not part of non-zero previous over-limit. That is * "round down" by non-overlimit portion of the last * queueing operation. */ slack = POSDIFF(limit + dql->prev_ovlimit, 2 * (completed - dql->num_completed)); slack_last_objs = dql->prev_ovlimit ? POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0; slack = max(slack, slack_last_objs); if (slack < dql->lowest_slack) dql->lowest_slack = slack; if (time_after(jiffies, dql->slack_start_time + dql->slack_hold_time)) { limit = POSDIFF(limit, dql->lowest_slack); dql->slack_start_time = jiffies; dql->lowest_slack = UINT_MAX; } } /* Enforce bounds on limit */ limit = clamp(limit, dql->min_limit, dql->max_limit); if (limit != dql->limit) { dql->limit = limit; ovlimit = 0; } dql->adj_limit = limit + completed; dql->prev_ovlimit = ovlimit; dql->prev_last_obj_cnt = dql->last_obj_cnt; dql->num_completed = completed; dql->prev_num_queued = num_queued; dql_check_stall(dql, stall_thrs); } EXPORT_SYMBOL(dql_completed); void dql_reset(struct dql *dql) { /* Reset all dynamic values */ dql->limit = 0; dql->num_queued = 0; dql->num_completed = 0; dql->last_obj_cnt = 0; dql->prev_num_queued = 0; dql->prev_last_obj_cnt = 0; dql->prev_ovlimit = 0; dql->lowest_slack = UINT_MAX; dql->slack_start_time = jiffies; dql->last_reap = jiffies; dql->history_head = jiffies / BITS_PER_LONG; memset(dql->history, 0, sizeof(dql->history)); } EXPORT_SYMBOL(dql_reset); void dql_init(struct dql *dql, unsigned int hold_time) { dql->max_limit = DQL_MAX_LIMIT; dql->min_limit = 0; dql->slack_hold_time = hold_time; dql->stall_thrs = 0; dql_reset(dql); } EXPORT_SYMBOL(dql_init); |
| 1 28 28 2 28 1 28 7 7 6 7 7 7 7 7 7 7 7 6 7 7 7 7 7 7 7 7 7 7 7 7 7 4 4 4 49 3 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/runtime.c - Helper functions for device runtime PM * * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. * Copyright (C) 2010 Alan Stern <stern@rowland.harvard.edu> */ #include <linux/sched/mm.h> #include <linux/ktime.h> #include <linux/hrtimer.h> #include <linux/export.h> #include <linux/pm_runtime.h> #include <linux/pm_wakeirq.h> #include <linux/rculist.h> #include <trace/events/rpm.h> #include "../base.h" #include "power.h" typedef int (*pm_callback_t)(struct device *); static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset) { pm_callback_t cb; const struct dev_pm_ops *ops; if (dev->pm_domain) ops = &dev->pm_domain->ops; else if (dev->type && dev->type->pm) ops = dev->type->pm; else if (dev->class && dev->class->pm) ops = dev->class->pm; else if (dev->bus && dev->bus->pm) ops = dev->bus->pm; else ops = NULL; if (ops) cb = *(pm_callback_t *)((void *)ops + cb_offset); else cb = NULL; if (!cb && dev->driver && dev->driver->pm) cb = *(pm_callback_t *)((void *)dev->driver->pm + cb_offset); return cb; } #define RPM_GET_CALLBACK(dev, callback) \ __rpm_get_callback(dev, offsetof(struct dev_pm_ops, callback)) static int rpm_resume(struct device *dev, int rpmflags); static int rpm_suspend(struct device *dev, int rpmflags); /** * update_pm_runtime_accounting - Update the time accounting of power states * @dev: Device to update the accounting for * * In order to be able to have time accounting of the various power states * (as used by programs such as PowerTOP to show the effectiveness of runtime * PM), we need to track the time spent in each state. * update_pm_runtime_accounting must be called each time before the * runtime_status field is updated, to account the time in the old state * correctly. */ static void update_pm_runtime_accounting(struct device *dev) { u64 now, last, delta; if (dev->power.disable_depth > 0) return; last = dev->power.accounting_timestamp; now = ktime_get_mono_fast_ns(); dev->power.accounting_timestamp = now; /* * Because ktime_get_mono_fast_ns() is not monotonic during * timekeeping updates, ensure that 'now' is after the last saved * timesptamp. */ if (now < last) return; delta = now - last; if (dev->power.runtime_status == RPM_SUSPENDED) dev->power.suspended_time += delta; else dev->power.active_time += delta; } static void __update_runtime_status(struct device *dev, enum rpm_status status) { update_pm_runtime_accounting(dev); trace_rpm_status(dev, status); dev->power.runtime_status = status; } static u64 rpm_get_accounted_time(struct device *dev, bool suspended) { u64 time; unsigned long flags; spin_lock_irqsave(&dev->power.lock, flags); update_pm_runtime_accounting(dev); time = suspended ? dev->power.suspended_time : dev->power.active_time; spin_unlock_irqrestore(&dev->power.lock, flags); return time; } u64 pm_runtime_active_time(struct device *dev) { return rpm_get_accounted_time(dev, false); } u64 pm_runtime_suspended_time(struct device *dev) { return rpm_get_accounted_time(dev, true); } EXPORT_SYMBOL_GPL(pm_runtime_suspended_time); /** * pm_runtime_deactivate_timer - Deactivate given device's suspend timer. * @dev: Device to handle. */ static void pm_runtime_deactivate_timer(struct device *dev) { if (dev->power.timer_expires > 0) { hrtimer_try_to_cancel(&dev->power.suspend_timer); dev->power.timer_expires = 0; } } /** * pm_runtime_cancel_pending - Deactivate suspend timer and cancel requests. * @dev: Device to handle. */ static void pm_runtime_cancel_pending(struct device *dev) { pm_runtime_deactivate_timer(dev); /* * In case there's a request pending, make sure its work function will * return without doing anything. */ dev->power.request = RPM_REQ_NONE; } /* * pm_runtime_autosuspend_expiration - Get a device's autosuspend-delay expiration time. * @dev: Device to handle. * * Compute the autosuspend-delay expiration time based on the device's * power.last_busy time. If the delay has already expired or is disabled * (negative) or the power.use_autosuspend flag isn't set, return 0. * Otherwise return the expiration time in nanoseconds (adjusted to be nonzero). * * This function may be called either with or without dev->power.lock held. * Either way it can be racy, since power.last_busy may be updated at any time. */ u64 pm_runtime_autosuspend_expiration(struct device *dev) { int autosuspend_delay; u64 expires; if (!dev->power.use_autosuspend) return 0; autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay); if (autosuspend_delay < 0) return 0; expires = READ_ONCE(dev->power.last_busy); expires += (u64)autosuspend_delay * NSEC_PER_MSEC; if (expires > ktime_get_mono_fast_ns()) return expires; /* Expires in the future */ return 0; } EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration); static int dev_memalloc_noio(struct device *dev, void *data) { return dev->power.memalloc_noio; } /* * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag. * @dev: Device to handle. * @enable: True for setting the flag and False for clearing the flag. * * Set the flag for all devices in the path from the device to the * root device in the device tree if @enable is true, otherwise clear * the flag for devices in the path whose siblings don't set the flag. * * The function should only be called by block device, or network * device driver for solving the deadlock problem during runtime * resume/suspend: * * If memory allocation with GFP_KERNEL is called inside runtime * resume/suspend callback of any one of its ancestors(or the * block device itself), the deadlock may be triggered inside the * memory allocation since it might not complete until the block * device becomes active and the involed page I/O finishes. The * situation is pointed out first by Alan Stern. Network device * are involved in iSCSI kind of situation. * * The lock of dev_hotplug_mutex is held in the function for handling * hotplug race because pm_runtime_set_memalloc_noio() may be called * in async probe(). * * The function should be called between device_add() and device_del() * on the affected device(block/network device). */ void pm_runtime_set_memalloc_noio(struct device *dev, bool enable) { static DEFINE_MUTEX(dev_hotplug_mutex); mutex_lock(&dev_hotplug_mutex); for (;;) { bool enabled; /* hold power lock since bitfield is not SMP-safe. */ spin_lock_irq(&dev->power.lock); enabled = dev->power.memalloc_noio; dev->power.memalloc_noio = enable; spin_unlock_irq(&dev->power.lock); /* * not need to enable ancestors any more if the device * has been enabled. */ if (enabled && enable) break; dev = dev->parent; /* * clear flag of the parent device only if all the * children don't set the flag because ancestor's * flag was set by any one of the descendants. */ if (!dev || (!enable && device_for_each_child(dev, NULL, dev_memalloc_noio))) break; } mutex_unlock(&dev_hotplug_mutex); } EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio); /** * rpm_check_suspend_allowed - Test whether a device may be suspended. * @dev: Device to test. */ static int rpm_check_suspend_allowed(struct device *dev) { int retval = 0; if (dev->power.runtime_error) retval = -EINVAL; else if (dev->power.disable_depth > 0) retval = -EACCES; else if (atomic_read(&dev->power.usage_count)) retval = -EAGAIN; else if (!dev->power.ignore_children && atomic_read(&dev->power.child_count)) retval = -EBUSY; /* Pending resume requests take precedence over suspends. */ else if ((dev->power.deferred_resume && dev->power.runtime_status == RPM_SUSPENDING) || (dev->power.request_pending && dev->power.request == RPM_REQ_RESUME)) retval = -EAGAIN; else if (__dev_pm_qos_resume_latency(dev) == 0) retval = -EPERM; else if (dev->power.runtime_status == RPM_SUSPENDED) retval = 1; return retval; } static int rpm_get_suppliers(struct device *dev) { struct device_link *link; list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) { int retval; if (!(link->flags & DL_FLAG_PM_RUNTIME)) continue; retval = pm_runtime_get_sync(link->supplier); /* Ignore suppliers with disabled runtime PM. */ if (retval < 0 && retval != -EACCES) { pm_runtime_put_noidle(link->supplier); return retval; } refcount_inc(&link->rpm_active); } return 0; } /** * pm_runtime_release_supplier - Drop references to device link's supplier. * @link: Target device link. * * Drop all runtime PM references associated with @link to its supplier device. */ void pm_runtime_release_supplier(struct device_link *link) { struct device *supplier = link->supplier; /* * The additional power.usage_count check is a safety net in case * the rpm_active refcount becomes saturated, in which case * refcount_dec_not_one() would return true forever, but it is not * strictly necessary. */ while (refcount_dec_not_one(&link->rpm_active) && atomic_read(&supplier->power.usage_count) > 0) pm_runtime_put_noidle(supplier); } static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend) { struct device_link *link; list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) { pm_runtime_release_supplier(link); if (try_to_suspend) pm_request_idle(link->supplier); } } static void rpm_put_suppliers(struct device *dev) { __rpm_put_suppliers(dev, true); } static void rpm_suspend_suppliers(struct device *dev) { struct device_link *link; int idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) pm_request_idle(link->supplier); device_links_read_unlock(idx); } /** * __rpm_callback - Run a given runtime PM callback for a given device. * @cb: Runtime PM callback to run. * @dev: Device to run the callback for. */ static int __rpm_callback(int (*cb)(struct device *), struct device *dev) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int retval = 0, idx; bool use_links = dev->power.links_count > 0; if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); } else { spin_unlock_irq(&dev->power.lock); /* * Resume suppliers if necessary. * * The device's runtime PM status cannot change until this * routine returns, so it is safe to read the status outside of * the lock. */ if (use_links && dev->power.runtime_status == RPM_RESUMING) { idx = device_links_read_lock(); retval = rpm_get_suppliers(dev); if (retval) { rpm_put_suppliers(dev); goto fail; } device_links_read_unlock(idx); } } if (cb) retval = cb(dev); if (dev->power.irq_safe) { spin_lock(&dev->power.lock); } else { /* * If the device is suspending and the callback has returned * success, drop the usage counters of the suppliers that have * been reference counted on its resume. * * Do that if resume fails too. */ if (use_links && ((dev->power.runtime_status == RPM_SUSPENDING && !retval) || (dev->power.runtime_status == RPM_RESUMING && retval))) { idx = device_links_read_lock(); __rpm_put_suppliers(dev, false); fail: device_links_read_unlock(idx); } spin_lock_irq(&dev->power.lock); } return retval; } /** * rpm_callback - Run a given runtime PM callback for a given device. * @cb: Runtime PM callback to run. * @dev: Device to run the callback for. */ static int rpm_callback(int (*cb)(struct device *), struct device *dev) { int retval; if (dev->power.memalloc_noio) { unsigned int noio_flag; /* * Deadlock might be caused if memory allocation with * GFP_KERNEL happens inside runtime_suspend and * runtime_resume callbacks of one block device's * ancestor or the block device itself. Network * device might be thought as part of iSCSI block * device, so network device and its ancestor should * be marked as memalloc_noio too. */ noio_flag = memalloc_noio_save(); retval = __rpm_callback(cb, dev); memalloc_noio_restore(noio_flag); } else { retval = __rpm_callback(cb, dev); } dev->power.runtime_error = retval; return retval != -EACCES ? retval : -EIO; } /** * rpm_idle - Notify device bus type if the device can be suspended. * @dev: Device to notify the bus type about. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be suspended. If * another idle notification has been started earlier, return immediately. If * the RPM_ASYNC flag is set then queue an idle-notification request; otherwise * run the ->runtime_idle() callback directly. If the ->runtime_idle callback * doesn't exist or if it returns 0, call rpm_suspend with the RPM_AUTO flag. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_idle(struct device *dev, int rpmflags) { int (*callback)(struct device *); int retval; trace_rpm_idle(dev, rpmflags); retval = rpm_check_suspend_allowed(dev); if (retval < 0) ; /* Conditions are wrong. */ /* Idle notifications are allowed only in the RPM_ACTIVE state. */ else if (dev->power.runtime_status != RPM_ACTIVE) retval = -EAGAIN; /* * Any pending request other than an idle notification takes * precedence over us, except that the timer may be running. */ else if (dev->power.request_pending && dev->power.request > RPM_REQ_IDLE) retval = -EAGAIN; /* Act as though RPM_NOWAIT is always set. */ else if (dev->power.idle_notification) retval = -EINPROGRESS; if (retval) goto out; /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; callback = RPM_GET_CALLBACK(dev, runtime_idle); /* If no callback assume success. */ if (!callback || dev->power.no_callbacks) goto out; /* Carry out an asynchronous or a synchronous idle notification. */ if (rpmflags & RPM_ASYNC) { dev->power.request = RPM_REQ_IDLE; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } trace_rpm_return_int(dev, _THIS_IP_, 0); return 0; } dev->power.idle_notification = true; if (dev->power.irq_safe) spin_unlock(&dev->power.lock); else spin_unlock_irq(&dev->power.lock); retval = callback(dev); if (dev->power.irq_safe) spin_lock(&dev->power.lock); else spin_lock_irq(&dev->power.lock); dev->power.idle_notification = false; wake_up_all(&dev->power.wait_queue); out: trace_rpm_return_int(dev, _THIS_IP_, retval); return retval ? retval : rpm_suspend(dev, rpmflags | RPM_AUTO); } /** * rpm_suspend - Carry out runtime suspend of given device. * @dev: Device to suspend. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be suspended. * Cancel a pending idle notification, autosuspend or suspend. If * another suspend has been started earlier, either return immediately * or wait for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC * flags. If the RPM_ASYNC flag is set then queue a suspend request; * otherwise run the ->runtime_suspend() callback directly. When * ->runtime_suspend succeeded, if a deferred resume was requested while * the callback was running then carry it out, otherwise send an idle * notification for its parent (if the suspend succeeded and both * ignore_children of parent->power and irq_safe of dev->power are not set). * If ->runtime_suspend failed with -EAGAIN or -EBUSY, and if the RPM_AUTO * flag is set and the next autosuspend-delay expiration time is in the * future, schedule another autosuspend attempt. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_suspend(struct device *dev, int rpmflags) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int (*callback)(struct device *); struct device *parent = NULL; int retval; trace_rpm_suspend(dev, rpmflags); repeat: retval = rpm_check_suspend_allowed(dev); if (retval < 0) goto out; /* Conditions are wrong. */ /* Synchronous suspends are not allowed in the RPM_RESUMING state. */ if (dev->power.runtime_status == RPM_RESUMING && !(rpmflags & RPM_ASYNC)) retval = -EAGAIN; if (retval) goto out; /* If the autosuspend_delay time hasn't expired yet, reschedule. */ if ((rpmflags & RPM_AUTO) && dev->power.runtime_status != RPM_SUSPENDING) { u64 expires = pm_runtime_autosuspend_expiration(dev); if (expires != 0) { /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; /* * Optimization: If the timer is already running and is * set to expire at or before the autosuspend delay, * avoid the overhead of resetting it. Just let it * expire; pm_suspend_timer_fn() will take care of the * rest. */ if (!(dev->power.timer_expires && dev->power.timer_expires <= expires)) { /* * We add a slack of 25% to gather wakeups * without sacrificing the granularity. */ u64 slack = (u64)READ_ONCE(dev->power.autosuspend_delay) * (NSEC_PER_MSEC >> 2); dev->power.timer_expires = expires; hrtimer_start_range_ns(&dev->power.suspend_timer, ns_to_ktime(expires), slack, HRTIMER_MODE_ABS); } dev->power.timer_autosuspends = 1; goto out; } } /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); if (dev->power.runtime_status == RPM_SUSPENDING) { DEFINE_WAIT(wait); if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { retval = -EINPROGRESS; goto out; } if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); cpu_relax(); spin_lock(&dev->power.lock); goto repeat; } /* Wait for the other suspend running in parallel with us. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_SUSPENDING) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); goto repeat; } if (dev->power.no_callbacks) goto no_callback; /* Assume success. */ /* Carry out an asynchronous or a synchronous suspend. */ if (rpmflags & RPM_ASYNC) { dev->power.request = (rpmflags & RPM_AUTO) ? RPM_REQ_AUTOSUSPEND : RPM_REQ_SUSPEND; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } goto out; } __update_runtime_status(dev, RPM_SUSPENDING); callback = RPM_GET_CALLBACK(dev, runtime_suspend); dev_pm_enable_wake_irq_check(dev, true); retval = rpm_callback(callback, dev); if (retval) goto fail; dev_pm_enable_wake_irq_complete(dev); no_callback: __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_deactivate_timer(dev); if (dev->parent) { parent = dev->parent; atomic_add_unless(&parent->power.child_count, -1, 0); } wake_up_all(&dev->power.wait_queue); if (dev->power.deferred_resume) { dev->power.deferred_resume = false; rpm_resume(dev, 0); retval = -EAGAIN; goto out; } if (dev->power.irq_safe) goto out; /* Maybe the parent is now able to suspend. */ if (parent && !parent->power.ignore_children) { spin_unlock(&dev->power.lock); spin_lock(&parent->power.lock); rpm_idle(parent, RPM_ASYNC); spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); } /* Maybe the suppliers are now able to suspend. */ if (dev->power.links_count > 0) { spin_unlock_irq(&dev->power.lock); rpm_suspend_suppliers(dev); spin_lock_irq(&dev->power.lock); } out: trace_rpm_return_int(dev, _THIS_IP_, retval); return retval; fail: dev_pm_disable_wake_irq_check(dev, true); __update_runtime_status(dev, RPM_ACTIVE); dev->power.deferred_resume = false; wake_up_all(&dev->power.wait_queue); if (retval == -EAGAIN || retval == -EBUSY) { dev->power.runtime_error = 0; /* * If the callback routine failed an autosuspend, and * if the last_busy time has been updated so that there * is a new autosuspend expiration time, automatically * reschedule another autosuspend. */ if ((rpmflags & RPM_AUTO) && pm_runtime_autosuspend_expiration(dev) != 0) goto repeat; } else { pm_runtime_cancel_pending(dev); } goto out; } /** * rpm_resume - Carry out runtime resume of given device. * @dev: Device to resume. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be resumed. Cancel * any scheduled or pending requests. If another resume has been started * earlier, either return immediately or wait for it to finish, depending on the * RPM_NOWAIT and RPM_ASYNC flags. Similarly, if there's a suspend running in * parallel with this function, either tell the other process to resume after * suspending (deferred_resume) or wait for it to finish. If the RPM_ASYNC * flag is set then queue a resume request; otherwise run the * ->runtime_resume() callback directly. Queue an idle notification for the * device if the resume succeeded. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_resume(struct device *dev, int rpmflags) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int (*callback)(struct device *); struct device *parent = NULL; int retval = 0; trace_rpm_resume(dev, rpmflags); repeat: if (dev->power.runtime_error) { retval = -EINVAL; } else if (dev->power.disable_depth > 0) { if (dev->power.runtime_status == RPM_ACTIVE && dev->power.last_status == RPM_ACTIVE) retval = 1; else retval = -EACCES; } if (retval) goto out; /* * Other scheduled or pending requests need to be canceled. Small * optimization: If an autosuspend timer is running, leave it running * rather than cancelling it now only to restart it again in the near * future. */ dev->power.request = RPM_REQ_NONE; if (!dev->power.timer_autosuspends) pm_runtime_deactivate_timer(dev); if (dev->power.runtime_status == RPM_ACTIVE) { retval = 1; goto out; } if (dev->power.runtime_status == RPM_RESUMING || dev->power.runtime_status == RPM_SUSPENDING) { DEFINE_WAIT(wait); if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { if (dev->power.runtime_status == RPM_SUSPENDING) { dev->power.deferred_resume = true; if (rpmflags & RPM_NOWAIT) retval = -EINPROGRESS; } else { retval = -EINPROGRESS; } goto out; } if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); cpu_relax(); spin_lock(&dev->power.lock); goto repeat; } /* Wait for the operation carried out in parallel with us. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_RESUMING && dev->power.runtime_status != RPM_SUSPENDING) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); goto repeat; } /* * See if we can skip waking up the parent. This is safe only if * power.no_callbacks is set, because otherwise we don't know whether * the resume will actually succeed. */ if (dev->power.no_callbacks && !parent && dev->parent) { spin_lock_nested(&dev->parent->power.lock, SINGLE_DEPTH_NESTING); if (dev->parent->power.disable_depth > 0 || dev->parent->power.ignore_children || dev->parent->power.runtime_status == RPM_ACTIVE) { atomic_inc(&dev->parent->power.child_count); spin_unlock(&dev->parent->power.lock); retval = 1; goto no_callback; /* Assume success. */ } spin_unlock(&dev->parent->power.lock); } /* Carry out an asynchronous or a synchronous resume. */ if (rpmflags & RPM_ASYNC) { dev->power.request = RPM_REQ_RESUME; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } retval = 0; goto out; } if (!parent && dev->parent) { /* * Increment the parent's usage counter and resume it if * necessary. Not needed if dev is irq-safe; then the * parent is permanently resumed. */ parent = dev->parent; if (dev->power.irq_safe) goto skip_parent; spin_unlock(&dev->power.lock); pm_runtime_get_noresume(parent); spin_lock(&parent->power.lock); /* * Resume the parent if it has runtime PM enabled and not been * set to ignore its children. */ if (!parent->power.disable_depth && !parent->power.ignore_children) { rpm_resume(parent, 0); if (parent->power.runtime_status != RPM_ACTIVE) retval = -EBUSY; } spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); if (retval) goto out; goto repeat; } skip_parent: if (dev->power.no_callbacks) goto no_callback; /* Assume success. */ __update_runtime_status(dev, RPM_RESUMING); callback = RPM_GET_CALLBACK(dev, runtime_resume); dev_pm_disable_wake_irq_check(dev, false); retval = rpm_callback(callback, dev); if (retval) { __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_cancel_pending(dev); dev_pm_enable_wake_irq_check(dev, false); } else { no_callback: __update_runtime_status(dev, RPM_ACTIVE); pm_runtime_mark_last_busy(dev); if (parent) atomic_inc(&parent->power.child_count); } wake_up_all(&dev->power.wait_queue); if (retval >= 0) rpm_idle(dev, RPM_ASYNC); out: if (parent && !dev->power.irq_safe) { spin_unlock_irq(&dev->power.lock); pm_runtime_put(parent); spin_lock_irq(&dev->power.lock); } trace_rpm_return_int(dev, _THIS_IP_, retval); return retval; } /** * pm_runtime_work - Universal runtime PM work function. * @work: Work structure used for scheduling the execution of this function. * * Use @work to get the device object the work is to be done for, determine what * is to be done and execute the appropriate runtime PM function. */ static void pm_runtime_work(struct work_struct *work) { struct device *dev = container_of(work, struct device, power.work); enum rpm_request req; spin_lock_irq(&dev->power.lock); if (!dev->power.request_pending) goto out; req = dev->power.request; dev->power.request = RPM_REQ_NONE; dev->power.request_pending = false; switch (req) { case RPM_REQ_NONE: break; case RPM_REQ_IDLE: rpm_idle(dev, RPM_NOWAIT); break; case RPM_REQ_SUSPEND: rpm_suspend(dev, RPM_NOWAIT); break; case RPM_REQ_AUTOSUSPEND: rpm_suspend(dev, RPM_NOWAIT | RPM_AUTO); break; case RPM_REQ_RESUME: rpm_resume(dev, RPM_NOWAIT); break; } out: spin_unlock_irq(&dev->power.lock); } /** * pm_suspend_timer_fn - Timer function for pm_schedule_suspend(). * @timer: hrtimer used by pm_schedule_suspend(). * * Check if the time is right and queue a suspend request. */ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) { struct device *dev = container_of(timer, struct device, power.suspend_timer); unsigned long flags; u64 expires; spin_lock_irqsave(&dev->power.lock, flags); expires = dev->power.timer_expires; /* * If 'expires' is after the current time, we've been called * too early. */ if (expires > 0 && expires < ktime_get_mono_fast_ns()) { dev->power.timer_expires = 0; rpm_suspend(dev, dev->power.timer_autosuspends ? (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC); } spin_unlock_irqrestore(&dev->power.lock, flags); return HRTIMER_NORESTART; } /** * pm_schedule_suspend - Set up a timer to submit a suspend request in future. * @dev: Device to suspend. * @delay: Time to wait before submitting a suspend request, in milliseconds. */ int pm_schedule_suspend(struct device *dev, unsigned int delay) { unsigned long flags; u64 expires; int retval; spin_lock_irqsave(&dev->power.lock, flags); if (!delay) { retval = rpm_suspend(dev, RPM_ASYNC); goto out; } retval = rpm_check_suspend_allowed(dev); if (retval) goto out; /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC; dev->power.timer_expires = expires; dev->power.timer_autosuspends = 0; hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS); out: spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(pm_schedule_suspend); static int rpm_drop_usage_count(struct device *dev) { int ret; ret = atomic_sub_return(1, &dev->power.usage_count); if (ret >= 0) return ret; /* * Because rpm_resume() does not check the usage counter, it will resume * the device even if the usage counter is 0 or negative, so it is * sufficient to increment the usage counter here to reverse the change * made above. */ atomic_inc(&dev->power.usage_count); dev_warn(dev, "Runtime PM usage count underflow!\n"); return -EINVAL; } /** * __pm_runtime_idle - Entry point for runtime idle operations. * @dev: Device to send idle notification for. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and * return immediately if it is larger than zero (if it becomes negative, log a * warning, increment it, and return an error). Then carry out an idle * notification, either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_idle(struct device *dev, int rpmflags) { unsigned long flags; int retval; if (rpmflags & RPM_GET_PUT) { retval = rpm_drop_usage_count(dev); if (retval < 0) { return retval; } else if (retval > 0) { trace_rpm_usage(dev, rpmflags); return 0; } } might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_idle(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_idle); /** * __pm_runtime_suspend - Entry point for runtime put/suspend operations. * @dev: Device to suspend. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and * return immediately if it is larger than zero (if it becomes negative, log a * warning, increment it, and return an error). Then carry out a suspend, * either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_suspend(struct device *dev, int rpmflags) { unsigned long flags; int retval; if (rpmflags & RPM_GET_PUT) { retval = rpm_drop_usage_count(dev); if (retval < 0) { return retval; } else if (retval > 0) { trace_rpm_usage(dev, rpmflags); return 0; } } might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_suspend(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_suspend); /** * __pm_runtime_resume - Entry point for runtime resume operations. * @dev: Device to resume. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, increment the device's usage count. Then * carry out a resume, either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_resume(struct device *dev, int rpmflags) { unsigned long flags; int retval; might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe && dev->power.runtime_status != RPM_ACTIVE); if (rpmflags & RPM_GET_PUT) atomic_inc(&dev->power.usage_count); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_resume(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_resume); /** * pm_runtime_get_conditional - Conditionally bump up device usage counter. * @dev: Device to handle. * @ign_usage_count: Whether or not to look at the current usage counter value. * * Return -EINVAL if runtime PM is disabled for @dev. * * Otherwise, if the runtime PM status of @dev is %RPM_ACTIVE and either * @ign_usage_count is %true or the runtime PM usage counter of @dev is not * zero, increment the usage counter of @dev and return 1. Otherwise, return 0 * without changing the usage counter. * * If @ign_usage_count is %true, this function can be used to prevent suspending * the device when its runtime PM status is %RPM_ACTIVE. * * If @ign_usage_count is %false, this function can be used to prevent * suspending the device when both its runtime PM status is %RPM_ACTIVE and its * runtime PM usage counter is not zero. * * The caller is responsible for decrementing the runtime PM usage counter of * @dev after this function has returned a positive value for it. */ static int pm_runtime_get_conditional(struct device *dev, bool ign_usage_count) { unsigned long flags; int retval; spin_lock_irqsave(&dev->power.lock, flags); if (dev->power.disable_depth > 0) { retval = -EINVAL; } else if (dev->power.runtime_status != RPM_ACTIVE) { retval = 0; } else if (ign_usage_count) { retval = 1; atomic_inc(&dev->power.usage_count); } else { retval = atomic_inc_not_zero(&dev->power.usage_count); } trace_rpm_usage(dev, 0); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } /** * pm_runtime_get_if_active - Bump up runtime PM usage counter if the device is * in active state * @dev: Target device. * * Increment the runtime PM usage counter of @dev if its runtime PM status is * %RPM_ACTIVE, in which case it returns 1. If the device is in a different * state, 0 is returned. -EINVAL is returned if runtime PM is disabled for the * device, in which case also the usage_count will remain unmodified. */ int pm_runtime_get_if_active(struct device *dev) { return pm_runtime_get_conditional(dev, true); } EXPORT_SYMBOL_GPL(pm_runtime_get_if_active); /** * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. * @dev: Target device. * * Increment the runtime PM usage counter of @dev if its runtime PM status is * %RPM_ACTIVE and its runtime PM usage counter is greater than 0, in which case * it returns 1. If the device is in a different state or its usage_count is 0, * 0 is returned. -EINVAL is returned if runtime PM is disabled for the device, * in which case also the usage_count will remain unmodified. */ int pm_runtime_get_if_in_use(struct device *dev) { return pm_runtime_get_conditional(dev, false); } EXPORT_SYMBOL_GPL(pm_runtime_get_if_in_use); /** * __pm_runtime_set_status - Set runtime PM status of a device. * @dev: Device to handle. * @status: New runtime PM status of the device. * * If runtime PM of the device is disabled or its power.runtime_error field is * different from zero, the status may be changed either to RPM_ACTIVE, or to * RPM_SUSPENDED, as long as that reflects the actual state of the device. * However, if the device has a parent and the parent is not active, and the * parent's power.ignore_children flag is unset, the device's status cannot be * set to RPM_ACTIVE, so -EBUSY is returned in that case. * * If successful, __pm_runtime_set_status() clears the power.runtime_error field * and the device parent's counter of unsuspended children is modified to * reflect the new status. If the new status is RPM_SUSPENDED, an idle * notification request for the parent is submitted. * * If @dev has any suppliers (as reflected by device links to them), and @status * is RPM_ACTIVE, they will be activated upfront and if the activation of one * of them fails, the status of @dev will be changed to RPM_SUSPENDED (instead * of the @status value) and the suppliers will be deacticated on exit. The * error returned by the failing supplier activation will be returned in that * case. */ int __pm_runtime_set_status(struct device *dev, unsigned int status) { struct device *parent = dev->parent; bool notify_parent = false; unsigned long flags; int error = 0; if (status != RPM_ACTIVE && status != RPM_SUSPENDED) return -EINVAL; spin_lock_irqsave(&dev->power.lock, flags); /* * Prevent PM-runtime from being enabled for the device or return an * error if it is enabled already and working. */ if (dev->power.runtime_error || dev->power.disable_depth) dev->power.disable_depth++; else error = -EAGAIN; spin_unlock_irqrestore(&dev->power.lock, flags); if (error) return error; /* * If the new status is RPM_ACTIVE, the suppliers can be activated * upfront regardless of the current status, because next time * rpm_put_suppliers() runs, the rpm_active refcounts of the links * involved will be dropped down to one anyway. */ if (status == RPM_ACTIVE) { int idx = device_links_read_lock(); error = rpm_get_suppliers(dev); if (error) status = RPM_SUSPENDED; device_links_read_unlock(idx); } spin_lock_irqsave(&dev->power.lock, flags); if (dev->power.runtime_status == status || !parent) goto out_set; if (status == RPM_SUSPENDED) { atomic_add_unless(&parent->power.child_count, -1, 0); notify_parent = !parent->power.ignore_children; } else { spin_lock_nested(&parent->power.lock, SINGLE_DEPTH_NESTING); /* * It is invalid to put an active child under a parent that is * not active, has runtime PM enabled and the * 'power.ignore_children' flag unset. */ if (!parent->power.disable_depth && !parent->power.ignore_children && parent->power.runtime_status != RPM_ACTIVE) { dev_err(dev, "runtime PM trying to activate child device %s but parent (%s) is not active\n", dev_name(dev), dev_name(parent)); error = -EBUSY; } else if (dev->power.runtime_status == RPM_SUSPENDED) { atomic_inc(&parent->power.child_count); } spin_unlock(&parent->power.lock); if (error) { status = RPM_SUSPENDED; goto out; } } out_set: __update_runtime_status(dev, status); if (!error) dev->power.runtime_error = 0; out: spin_unlock_irqrestore(&dev->power.lock, flags); if (notify_parent) pm_request_idle(parent); if (status == RPM_SUSPENDED) { int idx = device_links_read_lock(); rpm_put_suppliers(dev); device_links_read_unlock(idx); } pm_runtime_enable(dev); return error; } EXPORT_SYMBOL_GPL(__pm_runtime_set_status); /** * __pm_runtime_barrier - Cancel pending requests and wait for completions. * @dev: Device to handle. * * Flush all pending requests for the device from pm_wq and wait for all * runtime PM operations involving the device in progress to complete. * * Should be called under dev->power.lock with interrupts disabled. */ static void __pm_runtime_barrier(struct device *dev) { pm_runtime_deactivate_timer(dev); if (dev->power.request_pending) { dev->power.request = RPM_REQ_NONE; spin_unlock_irq(&dev->power.lock); cancel_work_sync(&dev->power.work); spin_lock_irq(&dev->power.lock); dev->power.request_pending = false; } if (dev->power.runtime_status == RPM_SUSPENDING || dev->power.runtime_status == RPM_RESUMING || dev->power.idle_notification) { DEFINE_WAIT(wait); /* Suspend, wake-up or idle notification in progress. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_SUSPENDING && dev->power.runtime_status != RPM_RESUMING && !dev->power.idle_notification) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); } } /** * pm_runtime_barrier - Flush pending requests and wait for completions. * @dev: Device to handle. * * Prevent the device from being suspended by incrementing its usage counter and * if there's a pending resume request for the device, wake the device up. * Next, make sure that all pending requests for the device have been flushed * from pm_wq and wait for all runtime PM operations involving the device in * progress to complete. * * Return value: * 1, if there was a resume request pending and the device had to be woken up, * 0, otherwise */ int pm_runtime_barrier(struct device *dev) { int retval = 0; pm_runtime_get_noresume(dev); spin_lock_irq(&dev->power.lock); if (dev->power.request_pending && dev->power.request == RPM_REQ_RESUME) { rpm_resume(dev, 0); retval = 1; } __pm_runtime_barrier(dev); spin_unlock_irq(&dev->power.lock); pm_runtime_put_noidle(dev); return retval; } EXPORT_SYMBOL_GPL(pm_runtime_barrier); /** * __pm_runtime_disable - Disable runtime PM of a device. * @dev: Device to handle. * @check_resume: If set, check if there's a resume request for the device. * * Increment power.disable_depth for the device and if it was zero previously, * cancel all pending runtime PM requests for the device and wait for all * operations in progress to complete. The device can be either active or * suspended after its runtime PM has been disabled. * * If @check_resume is set and there's a resume request pending when * __pm_runtime_disable() is called and power.disable_depth is zero, the * function will wake up the device before disabling its runtime PM. */ void __pm_runtime_disable(struct device *dev, bool check_resume) { spin_lock_irq(&dev->power.lock); if (dev->power.disable_depth > 0) { dev->power.disable_depth++; goto out; } /* * Wake up the device if there's a resume request pending, because that * means there probably is some I/O to process and disabling runtime PM * shouldn't prevent the device from processing the I/O. */ if (check_resume && dev->power.request_pending && dev->power.request == RPM_REQ_RESUME) { /* * Prevent suspends and idle notifications from being carried * out after we have woken up the device. */ pm_runtime_get_noresume(dev); rpm_resume(dev, 0); pm_runtime_put_noidle(dev); } /* Update time accounting before disabling PM-runtime. */ update_pm_runtime_accounting(dev); if (!dev->power.disable_depth++) { __pm_runtime_barrier(dev); dev->power.last_status = dev->power.runtime_status; } out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(__pm_runtime_disable); /** * pm_runtime_enable - Enable runtime PM of a device. * @dev: Device to handle. */ void pm_runtime_enable(struct device *dev) { unsigned long flags; spin_lock_irqsave(&dev->power.lock, flags); if (!dev->power.disable_depth) { dev_warn(dev, "Unbalanced %s!\n", __func__); goto out; } if (--dev->power.disable_depth > 0) goto out; dev->power.last_status = RPM_INVALID; dev->power.accounting_timestamp = ktime_get_mono_fast_ns(); if (dev->power.runtime_status == RPM_SUSPENDED && !dev->power.ignore_children && atomic_read(&dev->power.child_count) > 0) dev_warn(dev, "Enabling runtime PM for inactive device with active children\n"); out: spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_runtime_enable); static void pm_runtime_disable_action(void *data) { pm_runtime_dont_use_autosuspend(data); pm_runtime_disable(data); } /** * devm_pm_runtime_enable - devres-enabled version of pm_runtime_enable. * * NOTE: this will also handle calling pm_runtime_dont_use_autosuspend() for * you at driver exit time if needed. * * @dev: Device to handle. */ int devm_pm_runtime_enable(struct device *dev) { pm_runtime_enable(dev); return devm_add_action_or_reset(dev, pm_runtime_disable_action, dev); } EXPORT_SYMBOL_GPL(devm_pm_runtime_enable); /** * pm_runtime_forbid - Block runtime PM of a device. * @dev: Device to handle. * * Increase the device's usage count and clear its power.runtime_auto flag, * so that it cannot be suspended at run time until pm_runtime_allow() is called * for it. */ void pm_runtime_forbid(struct device *dev) { spin_lock_irq(&dev->power.lock); if (!dev->power.runtime_auto) goto out; dev->power.runtime_auto = false; atomic_inc(&dev->power.usage_count); rpm_resume(dev, 0); out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_forbid); /** * pm_runtime_allow - Unblock runtime PM of a device. * @dev: Device to handle. * * Decrease the device's usage count and set its power.runtime_auto flag. */ void pm_runtime_allow(struct device *dev) { int ret; spin_lock_irq(&dev->power.lock); if (dev->power.runtime_auto) goto out; dev->power.runtime_auto = true; ret = rpm_drop_usage_count(dev); if (ret == 0) rpm_idle(dev, RPM_AUTO | RPM_ASYNC); else if (ret > 0) trace_rpm_usage(dev, RPM_AUTO | RPM_ASYNC); out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_allow); /** * pm_runtime_no_callbacks - Ignore runtime PM callbacks for a device. * @dev: Device to handle. * * Set the power.no_callbacks flag, which tells the PM core that this * device is power-managed through its parent and has no runtime PM * callbacks of its own. The runtime sysfs attributes will be removed. */ void pm_runtime_no_callbacks(struct device *dev) { spin_lock_irq(&dev->power.lock); dev->power.no_callbacks = 1; spin_unlock_irq(&dev->power.lock); if (device_is_registered(dev)) rpm_sysfs_remove(dev); } EXPORT_SYMBOL_GPL(pm_runtime_no_callbacks); /** * pm_runtime_irq_safe - Leave interrupts disabled during callbacks. * @dev: Device to handle * * Set the power.irq_safe flag, which tells the PM core that the * ->runtime_suspend() and ->runtime_resume() callbacks for this device should * always be invoked with the spinlock held and interrupts disabled. It also * causes the parent's usage counter to be permanently incremented, preventing * the parent from runtime suspending -- otherwise an irq-safe child might have * to wait for a non-irq-safe parent. */ void pm_runtime_irq_safe(struct device *dev) { if (dev->parent) pm_runtime_get_sync(dev->parent); spin_lock_irq(&dev->power.lock); dev->power.irq_safe = 1; spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_irq_safe); /** * update_autosuspend - Handle a change to a device's autosuspend settings. * @dev: Device to handle. * @old_delay: The former autosuspend_delay value. * @old_use: The former use_autosuspend value. * * Prevent runtime suspend if the new delay is negative and use_autosuspend is * set; otherwise allow it. Send an idle notification if suspends are allowed. * * This function must be called under dev->power.lock with interrupts disabled. */ static void update_autosuspend(struct device *dev, int old_delay, int old_use) { int delay = dev->power.autosuspend_delay; /* Should runtime suspend be prevented now? */ if (dev->power.use_autosuspend && delay < 0) { /* If it used to be allowed then prevent it. */ if (!old_use || old_delay >= 0) { atomic_inc(&dev->power.usage_count); rpm_resume(dev, 0); } else { trace_rpm_usage(dev, 0); } } /* Runtime suspend should be allowed now. */ else { /* If it used to be prevented then allow it. */ if (old_use && old_delay < 0) atomic_dec(&dev->power.usage_count); /* Maybe we can autosuspend now. */ rpm_idle(dev, RPM_AUTO); } } /** * pm_runtime_set_autosuspend_delay - Set a device's autosuspend_delay value. * @dev: Device to handle. * @delay: Value of the new delay in milliseconds. * * Set the device's power.autosuspend_delay value. If it changes to negative * and the power.use_autosuspend flag is set, prevent runtime suspends. If it * changes the other way, allow runtime suspends. */ void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) { int old_delay, old_use; spin_lock_irq(&dev->power.lock); old_delay = dev->power.autosuspend_delay; old_use = dev->power.use_autosuspend; dev->power.autosuspend_delay = delay; update_autosuspend(dev, old_delay, old_use); spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_set_autosuspend_delay); /** * __pm_runtime_use_autosuspend - Set a device's use_autosuspend flag. * @dev: Device to handle. * @use: New value for use_autosuspend. * * Set the device's power.use_autosuspend flag, and allow or prevent runtime * suspends as needed. */ void __pm_runtime_use_autosuspend(struct device *dev, bool use) { int old_delay, old_use; spin_lock_irq(&dev->power.lock); old_delay = dev->power.autosuspend_delay; old_use = dev->power.use_autosuspend; dev->power.use_autosuspend = use; update_autosuspend(dev, old_delay, old_use); spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend); /** * pm_runtime_init - Initialize runtime PM fields in given device object. * @dev: Device object to initialize. */ void pm_runtime_init(struct device *dev) { dev->power.runtime_status = RPM_SUSPENDED; dev->power.last_status = RPM_INVALID; dev->power.idle_notification = false; dev->power.disable_depth = 1; atomic_set(&dev->power.usage_count, 0); dev->power.runtime_error = 0; atomic_set(&dev->power.child_count, 0); pm_suspend_ignore_children(dev, false); dev->power.runtime_auto = true; dev->power.request_pending = false; dev->power.request = RPM_REQ_NONE; dev->power.deferred_resume = false; dev->power.needs_force_resume = 0; INIT_WORK(&dev->power.work, pm_runtime_work); dev->power.timer_expires = 0; hrtimer_init(&dev->power.suspend_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); dev->power.suspend_timer.function = pm_suspend_timer_fn; init_waitqueue_head(&dev->power.wait_queue); } /** * pm_runtime_reinit - Re-initialize runtime PM fields in given device object. * @dev: Device object to re-initialize. */ void pm_runtime_reinit(struct device *dev) { if (!pm_runtime_enabled(dev)) { if (dev->power.runtime_status == RPM_ACTIVE) pm_runtime_set_suspended(dev); if (dev->power.irq_safe) { spin_lock_irq(&dev->power.lock); dev->power.irq_safe = 0; spin_unlock_irq(&dev->power.lock); if (dev->parent) pm_runtime_put(dev->parent); } } } /** * pm_runtime_remove - Prepare for removing a device from device hierarchy. * @dev: Device object being removed from device hierarchy. */ void pm_runtime_remove(struct device *dev) { __pm_runtime_disable(dev, false); pm_runtime_reinit(dev); } /** * pm_runtime_get_suppliers - Resume and reference-count supplier devices. * @dev: Consumer device. */ void pm_runtime_get_suppliers(struct device *dev) { struct device_link *link; int idx; idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) if (link->flags & DL_FLAG_PM_RUNTIME) { link->supplier_preactivated = true; pm_runtime_get_sync(link->supplier); } device_links_read_unlock(idx); } /** * pm_runtime_put_suppliers - Drop references to supplier devices. * @dev: Consumer device. */ void pm_runtime_put_suppliers(struct device *dev) { struct device_link *link; int idx; idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) if (link->supplier_preactivated) { link->supplier_preactivated = false; pm_runtime_put(link->supplier); } device_links_read_unlock(idx); } void pm_runtime_new_link(struct device *dev) { spin_lock_irq(&dev->power.lock); dev->power.links_count++; spin_unlock_irq(&dev->power.lock); } static void pm_runtime_drop_link_count(struct device *dev) { spin_lock_irq(&dev->power.lock); WARN_ON(dev->power.links_count == 0); dev->power.links_count--; spin_unlock_irq(&dev->power.lock); } /** * pm_runtime_drop_link - Prepare for device link removal. * @link: Device link going away. * * Drop the link count of the consumer end of @link and decrement the supplier * device's runtime PM usage counter as many times as needed to drop all of the * PM runtime reference to it from the consumer. */ void pm_runtime_drop_link(struct device_link *link) { if (!(link->flags & DL_FLAG_PM_RUNTIME)) return; pm_runtime_drop_link_count(link->consumer); pm_runtime_release_supplier(link); pm_request_idle(link->supplier); } static bool pm_runtime_need_not_resume(struct device *dev) { return atomic_read(&dev->power.usage_count) <= 1 && (atomic_read(&dev->power.child_count) == 0 || dev->power.ignore_children); } /** * pm_runtime_force_suspend - Force a device into suspend state if needed. * @dev: Device to suspend. * * Disable runtime PM so we safely can check the device's runtime PM status and * if it is active, invoke its ->runtime_suspend callback to suspend it and * change its runtime PM status field to RPM_SUSPENDED. Also, if the device's * usage and children counters don't indicate that the device was in use before * the system-wide transition under way, decrement its parent's children counter * (if there is a parent). Keep runtime PM disabled to preserve the state * unless we encounter errors. * * Typically this function may be invoked from a system suspend callback to make * sure the device is put into low power state and it should only be used during * system-wide PM transitions to sleep states. It assumes that the analogous * pm_runtime_force_resume() will be used to resume the device. * * Do not use with DPM_FLAG_SMART_SUSPEND as this can lead to an inconsistent * state where this function has called the ->runtime_suspend callback but the * PM core marks the driver as runtime active. */ int pm_runtime_force_suspend(struct device *dev) { int (*callback)(struct device *); int ret; pm_runtime_disable(dev); if (pm_runtime_status_suspended(dev)) return 0; callback = RPM_GET_CALLBACK(dev, runtime_suspend); dev_pm_enable_wake_irq_check(dev, true); ret = callback ? callback(dev) : 0; if (ret) goto err; dev_pm_enable_wake_irq_complete(dev); /* * If the device can stay in suspend after the system-wide transition * to the working state that will follow, drop the children counter of * its parent, but set its status to RPM_SUSPENDED anyway in case this * function will be called again for it in the meantime. */ if (pm_runtime_need_not_resume(dev)) { pm_runtime_set_suspended(dev); } else { __update_runtime_status(dev, RPM_SUSPENDED); dev->power.needs_force_resume = 1; } return 0; err: dev_pm_disable_wake_irq_check(dev, true); pm_runtime_enable(dev); return ret; } EXPORT_SYMBOL_GPL(pm_runtime_force_suspend); /** * pm_runtime_force_resume - Force a device into resume state if needed. * @dev: Device to resume. * * Prior invoking this function we expect the user to have brought the device * into low power state by a call to pm_runtime_force_suspend(). Here we reverse * those actions and bring the device into full power, if it is expected to be * used on system resume. In the other case, we defer the resume to be managed * via runtime PM. * * Typically this function may be invoked from a system resume callback. */ int pm_runtime_force_resume(struct device *dev) { int (*callback)(struct device *); int ret = 0; if (!pm_runtime_status_suspended(dev) || !dev->power.needs_force_resume) goto out; /* * The value of the parent's children counter is correct already, so * just update the status of the device. */ __update_runtime_status(dev, RPM_ACTIVE); callback = RPM_GET_CALLBACK(dev, runtime_resume); dev_pm_disable_wake_irq_check(dev, false); ret = callback ? callback(dev) : 0; if (ret) { pm_runtime_set_suspended(dev); dev_pm_enable_wake_irq_check(dev, false); goto out; } pm_runtime_mark_last_busy(dev); out: dev->power.needs_force_resume = 0; pm_runtime_enable(dev); return ret; } EXPORT_SYMBOL_GPL(pm_runtime_force_resume); |
| 20 24 24 23 24 23 23 24 23 24 24 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 | // SPDX-License-Identifier: GPL-2.0-only /* -*- linux-c -*- * sysctl_net.c: sysctl interface to net subsystem. * * Begun April 1, 1996, Mike Shaver. * Added /proc/sys/net directories for each protocol family. [MS] * * Revision 1.2 1996/05/08 20:24:40 shaver * Added bits for NET_BRIDGE and the NET_IPV4_ARP stuff and * NET_IPV4_IP_FORWARD. * * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/sysctl.h> #include <linux/nsproxy.h> #include <net/sock.h> #ifdef CONFIG_INET #include <net/ip.h> #endif #ifdef CONFIG_NET #include <linux/if_ether.h> #endif static struct ctl_table_set * net_ctl_header_lookup(struct ctl_table_root *root) { return ¤t->nsproxy->net_ns->sysctls; } static int is_seen(struct ctl_table_set *set) { return ¤t->nsproxy->net_ns->sysctls == set; } /* Return standard mode bits for table entry. */ static int net_ctl_permissions(struct ctl_table_header *head, const struct ctl_table *table) { struct net *net = container_of(head->set, struct net, sysctls); /* Allow network administrator to have same access as root. */ if (ns_capable_noaudit(net->user_ns, CAP_NET_ADMIN)) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } return table->mode; } static void net_ctl_set_ownership(struct ctl_table_header *head, kuid_t *uid, kgid_t *gid) { struct net *net = container_of(head->set, struct net, sysctls); kuid_t ns_root_uid; kgid_t ns_root_gid; ns_root_uid = make_kuid(net->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; ns_root_gid = make_kgid(net->user_ns, 0); if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } static struct ctl_table_root net_sysctl_root = { .lookup = net_ctl_header_lookup, .permissions = net_ctl_permissions, .set_ownership = net_ctl_set_ownership, }; static int __net_init sysctl_net_init(struct net *net) { setup_sysctl_set(&net->sysctls, &net_sysctl_root, is_seen); return 0; } static void __net_exit sysctl_net_exit(struct net *net) { retire_sysctl_set(&net->sysctls); } static struct pernet_operations sysctl_pernet_ops = { .init = sysctl_net_init, .exit = sysctl_net_exit, }; static struct ctl_table_header *net_header; __init int net_sysctl_init(void) { static struct ctl_table empty[1]; int ret = -ENOMEM; /* Avoid limitations in the sysctl implementation by * registering "/proc/sys/net" as an empty directory not in a * network namespace. */ net_header = register_sysctl_sz("net", empty, 0); if (!net_header) goto out; ret = register_pernet_subsys(&sysctl_pernet_ops); if (ret) goto out1; out: return ret; out1: unregister_sysctl_table(net_header); net_header = NULL; goto out; } /* Verify that sysctls for non-init netns are safe by either: * 1) being read-only, or * 2) having a data pointer which points outside of the global kernel/module * data segment, and rather into the heap where a per-net object was * allocated. */ static void ensure_safe_net_sysctl(struct net *net, const char *path, struct ctl_table *table, size_t table_size) { struct ctl_table *ent; pr_debug("Registering net sysctl (net %p): %s\n", net, path); ent = table; for (size_t i = 0; i < table_size; ent++, i++) { unsigned long addr; const char *where; pr_debug(" procname=%s mode=%o proc_handler=%ps data=%p\n", ent->procname, ent->mode, ent->proc_handler, ent->data); /* If it's not writable inside the netns, then it can't hurt. */ if ((ent->mode & 0222) == 0) { pr_debug(" Not writable by anyone\n"); continue; } /* Where does data point? */ addr = (unsigned long)ent->data; if (is_module_address(addr)) where = "module"; else if (is_kernel_core_data(addr)) where = "kernel"; else continue; /* If it is writable and points to kernel/module global * data, then it's probably a netns leak. */ WARN(1, "sysctl %s/%s: data points to %s global data: %ps\n", path, ent->procname, where, ent->data); /* Make it "safe" by dropping writable perms */ ent->mode &= ~0222; } } struct ctl_table_header *register_net_sysctl_sz(struct net *net, const char *path, struct ctl_table *table, size_t table_size) { if (!net_eq(net, &init_net)) ensure_safe_net_sysctl(net, path, table, table_size); return __register_sysctl_table(&net->sysctls, path, table, table_size); } EXPORT_SYMBOL_GPL(register_net_sysctl_sz); void unregister_net_sysctl_table(struct ctl_table_header *header) { unregister_sysctl_table(header); } EXPORT_SYMBOL_GPL(unregister_net_sysctl_table); |
| 22 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright 2019 Google LLC */ #ifndef __LINUX_BLK_CRYPTO_H #define __LINUX_BLK_CRYPTO_H #include <linux/types.h> enum blk_crypto_mode_num { BLK_ENCRYPTION_MODE_INVALID, BLK_ENCRYPTION_MODE_AES_256_XTS, BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV, BLK_ENCRYPTION_MODE_ADIANTUM, BLK_ENCRYPTION_MODE_SM4_XTS, BLK_ENCRYPTION_MODE_MAX, }; #define BLK_CRYPTO_MAX_KEY_SIZE 64 /** * struct blk_crypto_config - an inline encryption key's crypto configuration * @crypto_mode: encryption algorithm this key is for * @data_unit_size: the data unit size for all encryption/decryptions with this * key. This is the size in bytes of each individual plaintext and * ciphertext. This is always a power of 2. It might be e.g. the * filesystem block size or the disk sector size. * @dun_bytes: the maximum number of bytes of DUN used when using this key */ struct blk_crypto_config { enum blk_crypto_mode_num crypto_mode; unsigned int data_unit_size; unsigned int dun_bytes; }; /** * struct blk_crypto_key - an inline encryption key * @crypto_cfg: the crypto configuration (like crypto_mode, key size) for this * key * @data_unit_size_bits: log2 of data_unit_size * @size: size of this key in bytes (determined by @crypto_cfg.crypto_mode) * @raw: the raw bytes of this key. Only the first @size bytes are used. * * A blk_crypto_key is immutable once created, and many bios can reference it at * the same time. It must not be freed until all bios using it have completed * and it has been evicted from all devices on which it may have been used. */ struct blk_crypto_key { struct blk_crypto_config crypto_cfg; unsigned int data_unit_size_bits; unsigned int size; u8 raw[BLK_CRYPTO_MAX_KEY_SIZE]; }; #define BLK_CRYPTO_MAX_IV_SIZE 32 #define BLK_CRYPTO_DUN_ARRAY_SIZE (BLK_CRYPTO_MAX_IV_SIZE / sizeof(u64)) /** * struct bio_crypt_ctx - an inline encryption context * @bc_key: the key, algorithm, and data unit size to use * @bc_dun: the data unit number (starting IV) to use * * A bio_crypt_ctx specifies that the contents of the bio will be encrypted (for * write requests) or decrypted (for read requests) inline by the storage device * or controller, or by the crypto API fallback. */ struct bio_crypt_ctx { const struct blk_crypto_key *bc_key; u64 bc_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; }; #include <linux/blk_types.h> #include <linux/blkdev.h> #ifdef CONFIG_BLK_INLINE_ENCRYPTION static inline bool bio_has_crypt_ctx(struct bio *bio) { return bio->bi_crypt_context; } void bio_crypt_set_ctx(struct bio *bio, const struct blk_crypto_key *key, const u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], gfp_t gfp_mask); bool bio_crypt_dun_is_contiguous(const struct bio_crypt_ctx *bc, unsigned int bytes, const u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]); int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, enum blk_crypto_mode_num crypto_mode, unsigned int dun_bytes, unsigned int data_unit_size); int blk_crypto_start_using_key(struct block_device *bdev, const struct blk_crypto_key *key); void blk_crypto_evict_key(struct block_device *bdev, const struct blk_crypto_key *key); bool blk_crypto_config_supported_natively(struct block_device *bdev, const struct blk_crypto_config *cfg); bool blk_crypto_config_supported(struct block_device *bdev, const struct blk_crypto_config *cfg); #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool bio_has_crypt_ctx(struct bio *bio) { return false; } #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask); /** * bio_crypt_clone - clone bio encryption context * @dst: destination bio * @src: source bio * @gfp_mask: memory allocation flags * * If @src has an encryption context, clone it to @dst. * * Return: 0 on success, -ENOMEM if out of memory. -ENOMEM is only possible if * @gfp_mask doesn't include %__GFP_DIRECT_RECLAIM. */ static inline int bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask) { if (bio_has_crypt_ctx(src)) return __bio_crypt_clone(dst, src, gfp_mask); return 0; } #endif /* __LINUX_BLK_CRYPTO_H */ |
| 20 20 20 20 20 20 20 20 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/seq_file.h> #include <net/protocol.h> #include <net/netfilter/nf_log.h> #include "nf_internals.h" /* Internal logging interface, which relies on the real LOG target modules */ #define NFLOGGER_NAME_LEN 64 int sysctl_nf_log_all_netns __read_mostly; EXPORT_SYMBOL(sysctl_nf_log_all_netns); static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly; static DEFINE_MUTEX(nf_log_mutex); #define nft_log_dereference(logger) \ rcu_dereference_protected(logger, lockdep_is_held(&nf_log_mutex)) static struct nf_logger *__find_logger(int pf, const char *str_logger) { struct nf_logger *log; int i; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { log = nft_log_dereference(loggers[pf][i]); if (!log) continue; if (!strncasecmp(str_logger, log->name, strlen(log->name))) return log; } return NULL; } int nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger) { const struct nf_logger *log; if (pf == NFPROTO_UNSPEC || pf >= ARRAY_SIZE(net->nf.nf_loggers)) return -EOPNOTSUPP; mutex_lock(&nf_log_mutex); log = nft_log_dereference(net->nf.nf_loggers[pf]); if (log == NULL) rcu_assign_pointer(net->nf.nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } EXPORT_SYMBOL(nf_log_set); void nf_log_unset(struct net *net, const struct nf_logger *logger) { int i; const struct nf_logger *log; mutex_lock(&nf_log_mutex); for (i = 0; i < NFPROTO_NUMPROTO; i++) { log = nft_log_dereference(net->nf.nf_loggers[i]); if (log == logger) RCU_INIT_POINTER(net->nf.nf_loggers[i], NULL); } mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unset); /* return EEXIST if the same logger is registered, 0 on success. */ int nf_log_register(u_int8_t pf, struct nf_logger *logger) { int i; int ret = 0; if (pf >= ARRAY_SIZE(init_net.nf.nf_loggers)) return -EINVAL; mutex_lock(&nf_log_mutex); if (pf == NFPROTO_UNSPEC) { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { if (rcu_access_pointer(loggers[i][logger->type])) { ret = -EEXIST; goto unlock; } } for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) rcu_assign_pointer(loggers[i][logger->type], logger); } else { if (rcu_access_pointer(loggers[pf][logger->type])) { ret = -EEXIST; goto unlock; } rcu_assign_pointer(loggers[pf][logger->type], logger); } unlock: mutex_unlock(&nf_log_mutex); return ret; } EXPORT_SYMBOL(nf_log_register); void nf_log_unregister(struct nf_logger *logger) { const struct nf_logger *log; int i; mutex_lock(&nf_log_mutex); for (i = 0; i < NFPROTO_NUMPROTO; i++) { log = nft_log_dereference(loggers[i][logger->type]); if (log == logger) RCU_INIT_POINTER(loggers[i][logger->type], NULL); } mutex_unlock(&nf_log_mutex); synchronize_rcu(); } EXPORT_SYMBOL(nf_log_unregister); int nf_log_bind_pf(struct net *net, u_int8_t pf, const struct nf_logger *logger) { if (pf >= ARRAY_SIZE(net->nf.nf_loggers)) return -EINVAL; mutex_lock(&nf_log_mutex); if (__find_logger(pf, logger->name) == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; } rcu_assign_pointer(net->nf.nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } EXPORT_SYMBOL(nf_log_bind_pf); void nf_log_unbind_pf(struct net *net, u_int8_t pf) { if (pf >= ARRAY_SIZE(net->nf.nf_loggers)) return; mutex_lock(&nf_log_mutex); RCU_INIT_POINTER(net->nf.nf_loggers[pf], NULL); mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unbind_pf); int nf_logger_find_get(int pf, enum nf_log_type type) { struct nf_logger *logger; int ret = -ENOENT; if (pf >= ARRAY_SIZE(loggers)) return -EINVAL; if (type >= NF_LOG_TYPE_MAX) return -EINVAL; if (pf == NFPROTO_INET) { ret = nf_logger_find_get(NFPROTO_IPV4, type); if (ret < 0) return ret; ret = nf_logger_find_get(NFPROTO_IPV6, type); if (ret < 0) { nf_logger_put(NFPROTO_IPV4, type); return ret; } return 0; } rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); if (logger == NULL) goto out; if (try_module_get(logger->me)) ret = 0; out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(nf_logger_find_get); void nf_logger_put(int pf, enum nf_log_type type) { struct nf_logger *logger; if (pf == NFPROTO_INET) { nf_logger_put(NFPROTO_IPV4, type); nf_logger_put(NFPROTO_IPV6, type); return; } rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); if (!logger) WARN_ON_ONCE(1); else module_put(logger->me); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_logger_put); void nf_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *loginfo, const char *fmt, ...) { va_list args; char prefix[NF_LOG_PREFIXLEN]; const struct nf_logger *logger; rcu_read_lock(); if (loginfo != NULL) logger = rcu_dereference(loggers[pf][loginfo->type]); else logger = rcu_dereference(net->nf.nf_loggers[pf]); if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); } rcu_read_unlock(); } EXPORT_SYMBOL(nf_log_packet); void nf_log_trace(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *loginfo, const char *fmt, ...) { va_list args; char prefix[NF_LOG_PREFIXLEN]; const struct nf_logger *logger; rcu_read_lock(); logger = rcu_dereference(net->nf.nf_loggers[pf]); if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); } rcu_read_unlock(); } EXPORT_SYMBOL(nf_log_trace); #define S_SIZE (1024 - (sizeof(unsigned int) + 1)) struct nf_log_buf { unsigned int count; char buf[S_SIZE + 1]; }; static struct nf_log_buf emergency, *emergency_ptr = &emergency; __printf(2, 3) int nf_log_buf_add(struct nf_log_buf *m, const char *f, ...) { va_list args; int len; if (likely(m->count < S_SIZE)) { va_start(args, f); len = vsnprintf(m->buf + m->count, S_SIZE - m->count, f, args); va_end(args); if (likely(m->count + len < S_SIZE)) { m->count += len; return 0; } } m->count = S_SIZE; printk_once(KERN_ERR KBUILD_MODNAME " please increase S_SIZE\n"); return -1; } EXPORT_SYMBOL_GPL(nf_log_buf_add); struct nf_log_buf *nf_log_buf_open(void) { struct nf_log_buf *m = kmalloc(sizeof(*m), GFP_ATOMIC); if (unlikely(!m)) { local_bh_disable(); do { m = xchg(&emergency_ptr, NULL); } while (!m); } m->count = 0; return m; } EXPORT_SYMBOL_GPL(nf_log_buf_open); void nf_log_buf_close(struct nf_log_buf *m) { m->buf[m->count] = 0; printk("%s\n", m->buf); if (likely(m != &emergency)) kfree(m); else { emergency_ptr = m; local_bh_enable(); } } EXPORT_SYMBOL_GPL(nf_log_buf_close); #ifdef CONFIG_PROC_FS static void *seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); mutex_lock(&nf_log_mutex); if (*pos >= ARRAY_SIZE(net->nf.nf_loggers)) return NULL; return pos; } static void *seq_next(struct seq_file *s, void *v, loff_t *pos) { struct net *net = seq_file_net(s); (*pos)++; if (*pos >= ARRAY_SIZE(net->nf.nf_loggers)) return NULL; return pos; } static void seq_stop(struct seq_file *s, void *v) { mutex_unlock(&nf_log_mutex); } static int seq_show(struct seq_file *s, void *v) { loff_t *pos = v; const struct nf_logger *logger; int i; struct net *net = seq_file_net(s); logger = nft_log_dereference(net->nf.nf_loggers[*pos]); if (!logger) seq_printf(s, "%2lld NONE (", *pos); else seq_printf(s, "%2lld %s (", *pos, logger->name); if (seq_has_overflowed(s)) return -ENOSPC; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { if (loggers[*pos][i] == NULL) continue; logger = nft_log_dereference(loggers[*pos][i]); seq_puts(s, logger->name); if (i == 0 && loggers[*pos][i + 1] != NULL) seq_puts(s, ","); if (seq_has_overflowed(s)) return -ENOSPC; } seq_puts(s, ")\n"); if (seq_has_overflowed(s)) return -ENOSPC; return 0; } static const struct seq_operations nflog_seq_ops = { .start = seq_start, .next = seq_next, .stop = seq_stop, .show = seq_show, }; #endif /* PROC_FS */ #ifdef CONFIG_SYSCTL static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO]; static struct ctl_table_header *nf_log_sysctl_fhdr; static struct ctl_table nf_log_sysctl_ftable[] = { { .procname = "nf_log_all_netns", .data = &sysctl_nf_log_all_netns, .maxlen = sizeof(sysctl_nf_log_all_netns), .mode = 0644, .proc_handler = proc_dointvec, }, }; static int nf_log_proc_dostring(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; char buf[NFLOGGER_NAME_LEN]; int r = 0; int tindex = (unsigned long)table->extra1; struct net *net = table->extra2; if (write) { struct ctl_table tmp = *table; /* proc_dostring() can append to existing strings, so we need to * initialize it as an empty string. */ buf[0] = '\0'; tmp.data = buf; r = proc_dostring(&tmp, write, buffer, lenp, ppos); if (r) return r; if (!strcmp(buf, "NONE")) { nf_log_unbind_pf(net, tindex); return 0; } mutex_lock(&nf_log_mutex); logger = __find_logger(tindex, buf); if (logger == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; } rcu_assign_pointer(net->nf.nf_loggers[tindex], logger); mutex_unlock(&nf_log_mutex); } else { struct ctl_table tmp = *table; tmp.data = buf; mutex_lock(&nf_log_mutex); logger = nft_log_dereference(net->nf.nf_loggers[tindex]); if (!logger) strscpy(buf, "NONE", sizeof(buf)); else strscpy(buf, logger->name, sizeof(buf)); mutex_unlock(&nf_log_mutex); r = proc_dostring(&tmp, write, buffer, lenp, ppos); } return r; } static int netfilter_log_sysctl_init(struct net *net) { int i; struct ctl_table *table; table = nf_log_sysctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(nf_log_sysctl_table, sizeof(nf_log_sysctl_table), GFP_KERNEL); if (!table) goto err_alloc; } else { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { snprintf(nf_log_sysctl_fnames[i], 3, "%d", i); nf_log_sysctl_table[i].procname = nf_log_sysctl_fnames[i]; nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN; nf_log_sysctl_table[i].mode = 0644; nf_log_sysctl_table[i].proc_handler = nf_log_proc_dostring; nf_log_sysctl_table[i].extra1 = (void *)(unsigned long) i; } nf_log_sysctl_fhdr = register_net_sysctl(net, "net/netfilter", nf_log_sysctl_ftable); if (!nf_log_sysctl_fhdr) goto err_freg; } for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) table[i].extra2 = net; net->nf.nf_log_dir_header = register_net_sysctl_sz(net, "net/netfilter/nf_log", table, ARRAY_SIZE(nf_log_sysctl_table)); if (!net->nf.nf_log_dir_header) goto err_reg; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); else unregister_net_sysctl_table(nf_log_sysctl_fhdr); err_freg: err_alloc: return -ENOMEM; } static void netfilter_log_sysctl_exit(struct net *net) { const struct ctl_table *table; table = net->nf.nf_log_dir_header->ctl_table_arg; unregister_net_sysctl_table(net->nf.nf_log_dir_header); if (!net_eq(net, &init_net)) kfree(table); else unregister_net_sysctl_table(nf_log_sysctl_fhdr); } #else static int netfilter_log_sysctl_init(struct net *net) { return 0; } static void netfilter_log_sysctl_exit(struct net *net) { } #endif /* CONFIG_SYSCTL */ static int __net_init nf_log_net_init(struct net *net) { int ret = -ENOMEM; #ifdef CONFIG_PROC_FS if (!proc_create_net("nf_log", 0444, net->nf.proc_netfilter, &nflog_seq_ops, sizeof(struct seq_net_private))) return ret; #endif ret = netfilter_log_sysctl_init(net); if (ret < 0) goto out_sysctl; return 0; out_sysctl: #ifdef CONFIG_PROC_FS remove_proc_entry("nf_log", net->nf.proc_netfilter); #endif return ret; } static void __net_exit nf_log_net_exit(struct net *net) { netfilter_log_sysctl_exit(net); #ifdef CONFIG_PROC_FS remove_proc_entry("nf_log", net->nf.proc_netfilter); #endif } static struct pernet_operations nf_log_net_ops = { .init = nf_log_net_init, .exit = nf_log_net_exit, }; int __init netfilter_log_init(void) { return register_pernet_subsys(&nf_log_net_ops); } |
| 14 15 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 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 | /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* Copyright (C) 2016-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * SipHash: a fast short-input PRF * https://131002.net/siphash/ * * This implementation is specifically for SipHash2-4 for a secure PRF * and HalfSipHash1-3/SipHash1-3 for an insecure PRF only suitable for * hashtables. */ #ifndef _LINUX_SIPHASH_H #define _LINUX_SIPHASH_H #include <linux/types.h> #include <linux/kernel.h> #define SIPHASH_ALIGNMENT __alignof__(u64) typedef struct { u64 key[2]; } siphash_key_t; #define siphash_aligned_key_t siphash_key_t __aligned(16) static inline bool siphash_key_is_zero(const siphash_key_t *key) { return !(key->key[0] | key->key[1]); } u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key); u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key); u64 siphash_1u64(const u64 a, const siphash_key_t *key); u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key); u64 siphash_3u64(const u64 a, const u64 b, const u64 c, const siphash_key_t *key); u64 siphash_4u64(const u64 a, const u64 b, const u64 c, const u64 d, const siphash_key_t *key); u64 siphash_1u32(const u32 a, const siphash_key_t *key); u64 siphash_3u32(const u32 a, const u32 b, const u32 c, const siphash_key_t *key); static inline u64 siphash_2u32(const u32 a, const u32 b, const siphash_key_t *key) { return siphash_1u64((u64)b << 32 | a, key); } static inline u64 siphash_4u32(const u32 a, const u32 b, const u32 c, const u32 d, const siphash_key_t *key) { return siphash_2u64((u64)b << 32 | a, (u64)d << 32 | c, key); } static inline u64 ___siphash_aligned(const __le64 *data, size_t len, const siphash_key_t *key) { if (__builtin_constant_p(len) && len == 4) return siphash_1u32(le32_to_cpup((const __le32 *)data), key); if (__builtin_constant_p(len) && len == 8) return siphash_1u64(le64_to_cpu(data[0]), key); if (__builtin_constant_p(len) && len == 16) return siphash_2u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]), key); if (__builtin_constant_p(len) && len == 24) return siphash_3u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]), le64_to_cpu(data[2]), key); if (__builtin_constant_p(len) && len == 32) return siphash_4u64(le64_to_cpu(data[0]), le64_to_cpu(data[1]), le64_to_cpu(data[2]), le64_to_cpu(data[3]), key); return __siphash_aligned(data, len, key); } /** * siphash - compute 64-bit siphash PRF value * @data: buffer to hash * @size: size of @data * @key: the siphash key */ static inline u64 siphash(const void *data, size_t len, const siphash_key_t *key) { if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || !IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT)) return __siphash_unaligned(data, len, key); return ___siphash_aligned(data, len, key); } #define HSIPHASH_ALIGNMENT __alignof__(unsigned long) typedef struct { unsigned long key[2]; } hsiphash_key_t; u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key); u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key); u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key); u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key); u32 hsiphash_3u32(const u32 a, const u32 b, const u32 c, const hsiphash_key_t *key); u32 hsiphash_4u32(const u32 a, const u32 b, const u32 c, const u32 d, const hsiphash_key_t *key); static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len, const hsiphash_key_t *key) { if (__builtin_constant_p(len) && len == 4) return hsiphash_1u32(le32_to_cpu(data[0]), key); if (__builtin_constant_p(len) && len == 8) return hsiphash_2u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]), key); if (__builtin_constant_p(len) && len == 12) return hsiphash_3u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]), le32_to_cpu(data[2]), key); if (__builtin_constant_p(len) && len == 16) return hsiphash_4u32(le32_to_cpu(data[0]), le32_to_cpu(data[1]), le32_to_cpu(data[2]), le32_to_cpu(data[3]), key); return __hsiphash_aligned(data, len, key); } /** * hsiphash - compute 32-bit hsiphash PRF value * @data: buffer to hash * @size: size of @data * @key: the hsiphash key */ static inline u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key) { if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || !IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT)) return __hsiphash_unaligned(data, len, key); return ___hsiphash_aligned(data, len, key); } /* * These macros expose the raw SipHash and HalfSipHash permutations. * Do not use them directly! If you think you have a use for them, * be sure to CC the maintainer of this file explaining why. */ #define SIPHASH_PERMUTATION(a, b, c, d) ( \ (a) += (b), (b) = rol64((b), 13), (b) ^= (a), (a) = rol64((a), 32), \ (c) += (d), (d) = rol64((d), 16), (d) ^= (c), \ (a) += (d), (d) = rol64((d), 21), (d) ^= (a), \ (c) += (b), (b) = rol64((b), 17), (b) ^= (c), (c) = rol64((c), 32)) #define SIPHASH_CONST_0 0x736f6d6570736575ULL #define SIPHASH_CONST_1 0x646f72616e646f6dULL #define SIPHASH_CONST_2 0x6c7967656e657261ULL #define SIPHASH_CONST_3 0x7465646279746573ULL #define HSIPHASH_PERMUTATION(a, b, c, d) ( \ (a) += (b), (b) = rol32((b), 5), (b) ^= (a), (a) = rol32((a), 16), \ (c) += (d), (d) = rol32((d), 8), (d) ^= (c), \ (a) += (d), (d) = rol32((d), 7), (d) ^= (a), \ (c) += (b), (b) = rol32((b), 13), (b) ^= (c), (c) = rol32((c), 16)) #define HSIPHASH_CONST_0 0U #define HSIPHASH_CONST_1 0U #define HSIPHASH_CONST_2 0x6c796765U #define HSIPHASH_CONST_3 0x74656462U #endif /* _LINUX_SIPHASH_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NET_TIMESTAMPING_H_ #define _LINUX_NET_TIMESTAMPING_H_ #include <uapi/linux/net_tstamp.h> #define SOF_TIMESTAMPING_SOFTWARE_MASK (SOF_TIMESTAMPING_RX_SOFTWARE | \ SOF_TIMESTAMPING_TX_SOFTWARE | \ SOF_TIMESTAMPING_SOFTWARE) #define SOF_TIMESTAMPING_HARDWARE_MASK (SOF_TIMESTAMPING_RX_HARDWARE | \ SOF_TIMESTAMPING_TX_HARDWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) enum hwtstamp_source { HWTSTAMP_SOURCE_UNSPEC, HWTSTAMP_SOURCE_NETDEV, HWTSTAMP_SOURCE_PHYLIB, }; /** * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config * * @flags: see struct hwtstamp_config * @tx_type: see struct hwtstamp_config * @rx_filter: see struct hwtstamp_config * @ifr: pointer to ifreq structure from the original ioctl request, to pass to * a legacy implementation of a lower driver * @copied_to_user: request was passed to a legacy implementation which already * copied the ioctl request back to user space * @source: indication whether timestamps should come from the netdev or from * an attached phylib PHY * * Prefer using this structure for in-kernel processing of hardware * timestamping configuration, over the inextensible struct hwtstamp_config * exposed to the %SIOCGHWTSTAMP and %SIOCSHWTSTAMP ioctl UAPI. */ struct kernel_hwtstamp_config { int flags; int tx_type; int rx_filter; struct ifreq *ifr; bool copied_to_user; enum hwtstamp_source source; }; static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg, const struct hwtstamp_config *cfg) { kernel_cfg->flags = cfg->flags; kernel_cfg->tx_type = cfg->tx_type; kernel_cfg->rx_filter = cfg->rx_filter; } static inline void hwtstamp_config_from_kernel(struct hwtstamp_config *cfg, const struct kernel_hwtstamp_config *kernel_cfg) { cfg->flags = kernel_cfg->flags; cfg->tx_type = kernel_cfg->tx_type; cfg->rx_filter = kernel_cfg->rx_filter; } static inline bool kernel_hwtstamp_config_changed(const struct kernel_hwtstamp_config *a, const struct kernel_hwtstamp_config *b) { return a->flags != b->flags || a->tx_type != b->tx_type || a->rx_filter != b->rx_filter; } #endif /* _LINUX_NET_TIMESTAMPING_H_ */ |
| 3 50 7 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * pm_runtime.h - Device run-time power management helper functions. * * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl> */ #ifndef _LINUX_PM_RUNTIME_H #define _LINUX_PM_RUNTIME_H #include <linux/device.h> #include <linux/notifier.h> #include <linux/pm.h> #include <linux/jiffies.h> /* Runtime PM flag argument bits */ #define RPM_ASYNC 0x01 /* Request is asynchronous */ #define RPM_NOWAIT 0x02 /* Don't wait for concurrent state change */ #define RPM_GET_PUT 0x04 /* Increment/decrement the usage_count */ #define RPM_AUTO 0x08 /* Use autosuspend_delay */ /* * Use this for defining a set of PM operations to be used in all situations * (system suspend, hibernation or runtime PM). * * Note that the behaviour differs from the deprecated UNIVERSAL_DEV_PM_OPS() * macro, which uses the provided callbacks for both runtime PM and system * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend() * and pm_runtime_force_resume() for its system sleep callbacks. * * If the underlying dev_pm_ops struct symbol has to be exported, use * EXPORT_RUNTIME_DEV_PM_OPS() or EXPORT_GPL_RUNTIME_DEV_PM_OPS() instead. */ #define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \ pm_runtime_force_resume, suspend_fn, \ resume_fn, idle_fn) #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_GPL_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; static inline bool queue_pm_work(struct work_struct *work) { return queue_work(pm_wq, work); } extern int pm_generic_runtime_suspend(struct device *dev); extern int pm_generic_runtime_resume(struct device *dev); extern int pm_runtime_force_suspend(struct device *dev); extern int pm_runtime_force_resume(struct device *dev); extern int __pm_runtime_idle(struct device *dev, int rpmflags); extern int __pm_runtime_suspend(struct device *dev, int rpmflags); extern int __pm_runtime_resume(struct device *dev, int rpmflags); extern int pm_runtime_get_if_active(struct device *dev); extern int pm_runtime_get_if_in_use(struct device *dev); extern int pm_schedule_suspend(struct device *dev, unsigned int delay); extern int __pm_runtime_set_status(struct device *dev, unsigned int status); extern int pm_runtime_barrier(struct device *dev); extern void pm_runtime_enable(struct device *dev); extern void __pm_runtime_disable(struct device *dev, bool check_resume); extern void pm_runtime_allow(struct device *dev); extern void pm_runtime_forbid(struct device *dev); extern void pm_runtime_no_callbacks(struct device *dev); extern void pm_runtime_irq_safe(struct device *dev); extern void __pm_runtime_use_autosuspend(struct device *dev, bool use); extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay); extern u64 pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); extern void pm_runtime_release_supplier(struct device_link *link); extern int devm_pm_runtime_enable(struct device *dev); /** * pm_suspend_ignore_children - Set runtime PM behavior regarding children. * @dev: Target device. * @enable: Whether or not to ignore possible dependencies on children. * * The dependencies of @dev on its children will not be taken into account by * the runtime PM framework going forward if @enable is %true, or they will * be taken into account otherwise. */ static inline void pm_suspend_ignore_children(struct device *dev, bool enable) { dev->power.ignore_children = enable; } /** * pm_runtime_get_noresume - Bump up runtime PM usage counter of a device. * @dev: Target device. */ static inline void pm_runtime_get_noresume(struct device *dev) { atomic_inc(&dev->power.usage_count); } /** * pm_runtime_put_noidle - Drop runtime PM usage counter of a device. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev unless it is 0 already. */ static inline void pm_runtime_put_noidle(struct device *dev) { atomic_add_unless(&dev->power.usage_count, -1, 0); } /** * pm_runtime_suspended - Check whether or not a device is runtime-suspended. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev and its runtime PM status is * %RPM_SUSPENDED, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED && !dev->power.disable_depth; } /** * pm_runtime_active - Check whether or not a device is runtime-active. * @dev: Target device. * * Return %true if runtime PM is disabled for @dev or its runtime PM status is * %RPM_ACTIVE, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_active(struct device *dev) { return dev->power.runtime_status == RPM_ACTIVE || dev->power.disable_depth; } /** * pm_runtime_status_suspended - Check if runtime PM status is "suspended". * @dev: Target device. * * Return %true if the runtime PM status of @dev is %RPM_SUSPENDED, or %false * otherwise, regardless of whether or not runtime PM has been enabled for @dev. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which the * runtime PM status of @dev cannot change. */ static inline bool pm_runtime_status_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED; } /** * pm_runtime_enabled - Check if runtime PM is enabled. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev. */ static inline bool pm_runtime_enabled(struct device *dev) { return !dev->power.disable_depth; } /** * pm_runtime_has_no_callbacks - Check if runtime PM callbacks may be present. * @dev: Target device. * * Return %true if @dev is a special device without runtime PM callbacks or * %false otherwise. */ static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return dev->power.no_callbacks; } /** * pm_runtime_mark_last_busy - Update the last access time of a device. * @dev: Target device. * * Update the last access time of @dev used by the runtime PM autosuspend * mechanism to the current time as returned by ktime_get_mono_fast_ns(). */ static inline void pm_runtime_mark_last_busy(struct device *dev) { WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } /** * pm_runtime_is_irq_safe - Check if runtime PM can work in interrupt context. * @dev: Target device. * * Return %true if @dev has been marked as an "IRQ-safe" device (with respect * to runtime PM), in which case its runtime PM callabcks can be expected to * work correctly when invoked from interrupt handlers. */ static inline bool pm_runtime_is_irq_safe(struct device *dev) { return dev->power.irq_safe; } extern u64 pm_runtime_suspended_time(struct device *dev); #else /* !CONFIG_PM */ static inline bool queue_pm_work(struct work_struct *work) { return false; } static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; } static inline int pm_generic_runtime_resume(struct device *dev) { return 0; } static inline int pm_runtime_force_suspend(struct device *dev) { return 0; } static inline int pm_runtime_force_resume(struct device *dev) { return 0; } static inline int __pm_runtime_idle(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_suspend(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_resume(struct device *dev, int rpmflags) { return 1; } static inline int pm_schedule_suspend(struct device *dev, unsigned int delay) { return -ENOSYS; } static inline int pm_runtime_get_if_in_use(struct device *dev) { return -EINVAL; } static inline int pm_runtime_get_if_active(struct device *dev) { return -EINVAL; } static inline int __pm_runtime_set_status(struct device *dev, unsigned int status) { return 0; } static inline int pm_runtime_barrier(struct device *dev) { return 0; } static inline void pm_runtime_enable(struct device *dev) {} static inline void __pm_runtime_disable(struct device *dev, bool c) {} static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} static inline int devm_pm_runtime_enable(struct device *dev) { return 0; } static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } static inline bool pm_runtime_active(struct device *dev) { return true; } static inline bool pm_runtime_status_suspended(struct device *dev) { return false; } static inline bool pm_runtime_enabled(struct device *dev) { return false; } static inline void pm_runtime_no_callbacks(struct device *dev) {} static inline void pm_runtime_irq_safe(struct device *dev) {} static inline bool pm_runtime_is_irq_safe(struct device *dev) { return false; } static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return false; } static inline void pm_runtime_mark_last_busy(struct device *dev) {} static inline void __pm_runtime_use_autosuspend(struct device *dev, bool use) {} static inline void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) {} static inline u64 pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } static inline void pm_runtime_set_memalloc_noio(struct device *dev, bool enable){} static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device_link *link) {} static inline void pm_runtime_release_supplier(struct device_link *link) {} #endif /* !CONFIG_PM */ /** * pm_runtime_idle - Conditionally set up autosuspend of a device or suspend it. * @dev: Target device. * * Invoke the "idle check" callback of @dev and, depending on its return value, * set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend has been enabled for it). */ static inline int pm_runtime_idle(struct device *dev) { return __pm_runtime_idle(dev, 0); } /** * pm_runtime_suspend - Suspend a device synchronously. * @dev: Target device. */ static inline int pm_runtime_suspend(struct device *dev) { return __pm_runtime_suspend(dev, 0); } /** * pm_runtime_autosuspend - Set up autosuspend of a device or suspend it. * @dev: Target device. * * Set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend is enabled for it) without engaging its "idle check" callback. */ static inline int pm_runtime_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_AUTO); } /** * pm_runtime_resume - Resume a device synchronously. * @dev: Target device. */ static inline int pm_runtime_resume(struct device *dev) { return __pm_runtime_resume(dev, 0); } /** * pm_request_idle - Queue up "idle check" execution for a device. * @dev: Target device. * * Queue up a work item to run an equivalent of pm_runtime_idle() for @dev * asynchronously. */ static inline int pm_request_idle(struct device *dev) { return __pm_runtime_idle(dev, RPM_ASYNC); } /** * pm_request_resume - Queue up runtime-resume of a device. * @dev: Target device. */ static inline int pm_request_resume(struct device *dev) { return __pm_runtime_resume(dev, RPM_ASYNC); } /** * pm_request_autosuspend - Queue up autosuspend of a device. * @dev: Target device. * * Queue up a work item to run an equivalent pm_runtime_autosuspend() for @dev * asynchronously. */ static inline int pm_request_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_get - Bump up usage counter and queue up resume of a device. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and queue up a work item to * carry out runtime-resume of it. */ static inline int pm_runtime_get(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT | RPM_ASYNC); } /** * pm_runtime_get_sync - Bump up usage counter of a device and resume it. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and carry out runtime-resume of * it synchronously. * * The possible return values of this function are the same as for * pm_runtime_resume() and the runtime PM usage counter of @dev remains * incremented in all cases, even if it returns an error code. * Consider using pm_runtime_resume_and_get() instead of it, especially * if its return value is checked by the caller, as this is likely to result * in cleaner code. */ static inline int pm_runtime_get_sync(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT); } /** * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it. * @dev: Target device. * * Resume @dev synchronously and if that is successful, increment its runtime * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been * incremented or a negative error code otherwise. */ static inline int pm_runtime_resume_and_get(struct device *dev) { int ret; ret = __pm_runtime_resume(dev, RPM_GET_PUT); if (ret < 0) { pm_runtime_put_noidle(dev); return ret; } return 0; } /** * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_idle(). */ static inline int pm_runtime_put(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); } /** * __pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). */ static inline int __pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). */ static inline int pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_put_sync - Drop device usage counter and run "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, invoke the "idle check" callback of @dev and, depending on its * return value, set up autosuspend of @dev or suspend it (depending on whether * or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_idle() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_suspend - Drop device usage counter and suspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, carry out runtime-suspend of @dev synchronously. * * The possible return values of this function are the same as for * pm_runtime_suspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_suspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_autosuspend - Drop device usage counter and autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, set up autosuspend of @dev or suspend it synchronously (depending * on whether or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_autosuspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_AUTO); } /** * pm_runtime_set_active - Set runtime PM status to "active". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_ACTIVE and ensure that dependencies * of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_active(struct device *dev) { return __pm_runtime_set_status(dev, RPM_ACTIVE); } /** * pm_runtime_set_suspended - Set runtime PM status to "suspended". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_SUSPENDED and ensure that * dependencies of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_suspended(struct device *dev) { return __pm_runtime_set_status(dev, RPM_SUSPENDED); } /** * pm_runtime_disable - Disable runtime PM for a device. * @dev: Target device. * * Prevent the runtime PM framework from working with @dev (by incrementing its * "blocking" counter). * * For each invocation of this function for @dev there must be a matching * pm_runtime_enable() call in order for runtime PM to be enabled for it. */ static inline void pm_runtime_disable(struct device *dev) { __pm_runtime_disable(dev, true); } /** * pm_runtime_use_autosuspend - Allow autosuspend to be used for a device. * @dev: Target device. * * Allow the runtime PM autosuspend mechanism to be used for @dev whenever * requested (or "autosuspend" will be handled as direct runtime-suspend for * it). * * NOTE: It's important to undo this with pm_runtime_dont_use_autosuspend() * at driver exit time unless your driver initially enabled pm_runtime * with devm_pm_runtime_enable() (which handles it for you). */ static inline void pm_runtime_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, true); } /** * pm_runtime_dont_use_autosuspend - Prevent autosuspend from being used. * @dev: Target device. * * Prevent the runtime PM autosuspend mechanism from being used for @dev which * means that "autosuspend" will be handled as direct runtime-suspend for it * going forward. */ static inline void pm_runtime_dont_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, false); } #endif |
| 2 39 1 38 39 28 52 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 | /* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _LINUX_RSEQ_H #define _LINUX_RSEQ_H #ifdef CONFIG_RSEQ #include <linux/preempt.h> #include <linux/sched.h> /* * Map the event mask on the user-space ABI enum rseq_cs_flags * for direct mask checks. */ enum rseq_event_mask_bits { RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, }; enum rseq_event_mask { RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), }; static inline void rseq_set_notify_resume(struct task_struct *t) { if (t->rseq) set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); } void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); static inline void rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { if (current->rseq) __rseq_handle_notify_resume(ksig, regs); } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { preempt_disable(); __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); preempt_enable(); rseq_handle_notify_resume(ksig, regs); } /* rseq_preempt() requires preemption to be disabled. */ static inline void rseq_preempt(struct task_struct *t) { __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); rseq_set_notify_resume(t); } /* rseq_migrate() requires preemption to be disabled. */ static inline void rseq_migrate(struct task_struct *t) { __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); rseq_set_notify_resume(t); } /* * If parent process has a registered restartable sequences area, the * child inherits. Unregister rseq for a clone with CLONE_VM set. */ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { if (clone_flags & CLONE_VM) { t->rseq = NULL; t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } else { t->rseq = current->rseq; t->rseq_len = current->rseq_len; t->rseq_sig = current->rseq_sig; t->rseq_event_mask = current->rseq_event_mask; } } static inline void rseq_execve(struct task_struct *t) { t->rseq = NULL; t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } #else static inline void rseq_set_notify_resume(struct task_struct *t) { } static inline void rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_preempt(struct task_struct *t) { } static inline void rseq_migrate(struct task_struct *t) { } static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { } static inline void rseq_execve(struct task_struct *t) { } #endif #ifdef CONFIG_DEBUG_RSEQ void rseq_syscall(struct pt_regs *regs); #else static inline void rseq_syscall(struct pt_regs *regs) { } #endif #endif /* _LINUX_RSEQ_H */ |
| 249 249 248 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X_TABLES_H #define _X_TABLES_H #include <linux/netdevice.h> #include <linux/static_key.h> #include <linux/netfilter.h> #include <uapi/linux/netfilter/x_tables.h> /* Test a struct->invflags and a boolean for inequality */ #define NF_INVF(ptr, flag, boolean) \ ((boolean) ^ !!((ptr)->invflags & (flag))) /** * struct xt_action_param - parameters for matches/targets * * @match: the match extension * @target: the target extension * @matchinfo: per-match data * @targetinfo: per-target data * @state: pointer to hook state this packet came from * @fragoff: packet is a fragment, this is the data offset * @thoff: position of transport header relative to skb->data * * Fields written to by extensions: * * @hotdrop: drop packet if we had inspection problems */ struct xt_action_param { union { const struct xt_match *match; const struct xt_target *target; }; union { const void *matchinfo, *targinfo; }; const struct nf_hook_state *state; unsigned int thoff; u16 fragoff; bool hotdrop; }; static inline struct net *xt_net(const struct xt_action_param *par) { return par->state->net; } static inline struct net_device *xt_in(const struct xt_action_param *par) { return par->state->in; } static inline const char *xt_inname(const struct xt_action_param *par) { return par->state->in->name; } static inline struct net_device *xt_out(const struct xt_action_param *par) { return par->state->out; } static inline const char *xt_outname(const struct xt_action_param *par) { return par->state->out->name; } static inline unsigned int xt_hooknum(const struct xt_action_param *par) { return par->state->hook; } static inline u_int8_t xt_family(const struct xt_action_param *par) { return par->state->pf; } /** * struct xt_mtchk_param - parameters for match extensions' * checkentry functions * * @net: network namespace through which the check was invoked * @table: table the rule is tried to be inserted into * @entryinfo: the family-specific rule data * (struct ipt_ip, ip6t_ip, arpt_arp or (note) ebt_entry) * @match: struct xt_match through which this function was invoked * @matchinfo: per-match data * @hook_mask: via which hooks the new rule is reachable * Other fields as above. */ struct xt_mtchk_param { struct net *net; const char *table; const void *entryinfo; const struct xt_match *match; void *matchinfo; unsigned int hook_mask; u_int8_t family; bool nft_compat; }; /** * struct xt_mdtor_param - match destructor parameters * Fields as above. */ struct xt_mtdtor_param { struct net *net; const struct xt_match *match; void *matchinfo; u_int8_t family; }; /** * struct xt_tgchk_param - parameters for target extensions' * checkentry functions * * @entryinfo: the family-specific rule data * (struct ipt_entry, ip6t_entry, arpt_entry, ebt_entry) * * Other fields see above. */ struct xt_tgchk_param { struct net *net; const char *table; const void *entryinfo; const struct xt_target *target; void *targinfo; unsigned int hook_mask; u_int8_t family; bool nft_compat; }; /* Target destructor parameters */ struct xt_tgdtor_param { struct net *net; const struct xt_target *target; void *targinfo; u_int8_t family; }; struct xt_match { struct list_head list; const char name[XT_EXTENSION_MAXNAMELEN]; u_int8_t revision; /* Return true or false: return FALSE and set *hotdrop = 1 to force immediate packet drop. */ /* Arguments changed since 2.6.9, as this must now handle non-linear skb, using skb_header_pointer and skb_ip_make_writable. */ bool (*match)(const struct sk_buff *skb, struct xt_action_param *); /* Called when user tries to insert an entry of this type. */ int (*checkentry)(const struct xt_mtchk_param *); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_mtdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, const void *src); int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; const char *table; unsigned int matchsize; unsigned int usersize; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT unsigned int compatsize; #endif unsigned int hooks; unsigned short proto; unsigned short family; }; /* Registration hooks for targets. */ struct xt_target { struct list_head list; const char name[XT_EXTENSION_MAXNAMELEN]; u_int8_t revision; /* Returns verdict. Argument order changed since 2.6.9, as this must now handle non-linear skbs, using skb_copy_bits and skb_ip_make_writable. */ unsigned int (*target)(struct sk_buff *skb, const struct xt_action_param *); /* Called when user tries to insert an entry of this type: hook_mask is a bitmask of hooks from which it can be called. */ /* Should return 0 on success or an error code otherwise (-Exxxx). */ int (*checkentry)(const struct xt_tgchk_param *); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_tgdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, const void *src); int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; const char *table; unsigned int targetsize; unsigned int usersize; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT unsigned int compatsize; #endif unsigned int hooks; unsigned short proto; unsigned short family; }; /* Furniture shopping... */ struct xt_table { struct list_head list; /* What hooks you will enter on */ unsigned int valid_hooks; /* Man behind the curtain... */ struct xt_table_info *private; /* hook ops that register the table with the netfilter core */ struct nf_hook_ops *ops; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; u_int8_t af; /* address/protocol family */ int priority; /* hook order */ /* A unique name... */ const char name[XT_TABLE_MAXNAMELEN]; }; #include <linux/netfilter_ipv4.h> /* The table itself */ struct xt_table_info { /* Size per table */ unsigned int size; /* Number of entries: FIXME. --RR */ unsigned int number; /* Initial number of entries. Needed for module usage count */ unsigned int initial_entries; /* Entry points and underflows */ unsigned int hook_entry[NF_INET_NUMHOOKS]; unsigned int underflow[NF_INET_NUMHOOKS]; /* * Number of user chains. Since tables cannot have loops, at most * @stacksize jumps (number of user chains) can possibly be made. */ unsigned int stacksize; void ***jumpstack; unsigned char entries[] __aligned(8); }; int xt_register_target(struct xt_target *target); void xt_unregister_target(struct xt_target *target); int xt_register_targets(struct xt_target *target, unsigned int n); void xt_unregister_targets(struct xt_target *target, unsigned int n); int xt_register_match(struct xt_match *target); void xt_unregister_match(struct xt_match *target); int xt_register_matches(struct xt_match *match, unsigned int n); void xt_unregister_matches(struct xt_match *match, unsigned int n); int xt_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); int xt_check_table_hooks(const struct xt_table_info *info, unsigned int valid_hooks); unsigned int *xt_alloc_entry_offsets(unsigned int size); bool xt_find_jump_offset(const unsigned int *offsets, unsigned int target, unsigned int size); int xt_check_proc_name(const char *name, unsigned int size); int xt_check_match(struct xt_mtchk_param *, unsigned int size, u16 proto, bool inv_proto); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u16 proto, bool inv_proto); int xt_match_to_user(const struct xt_entry_match *m, struct xt_entry_match __user *u); int xt_target_to_user(const struct xt_entry_target *t, struct xt_entry_target __user *u); int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size); void *xt_copy_counters(sockptr_t arg, unsigned int len, struct xt_counters_info *info); struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, const struct xt_table *table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo); void *xt_unregister_table(struct xt_table *table); struct xt_table_info *xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error); struct xt_match *xt_find_match(u8 af, const char *name, u8 revision); struct xt_match *xt_request_find_match(u8 af, const char *name, u8 revision); struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision); int xt_find_revision(u8 af, const char *name, u8 revision, int target, int *err); struct xt_table *xt_find_table(struct net *net, u8 af, const char *name); struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name); struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af, const char *name); void xt_table_unlock(struct xt_table *t); int xt_proto_init(struct net *net, u_int8_t af); void xt_proto_fini(struct net *net, u_int8_t af); struct xt_table_info *xt_alloc_table_info(unsigned int size); void xt_free_table_info(struct xt_table_info *info); /** * xt_recseq - recursive seqcount for netfilter use * * Packet processing changes the seqcount only if no recursion happened * get_counters() can use read_seqcount_begin()/read_seqcount_retry(), * because we use the normal seqcount convention : * Low order bit set to 1 if a writer is active. */ DECLARE_PER_CPU(seqcount_t, xt_recseq); /* xt_tee_enabled - true if x_tables needs to handle reentrancy * * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. */ extern struct static_key xt_tee_enabled; /** * xt_write_recseq_begin - start of a write section * * Begin packet processing : all readers must wait the end * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) * Returns : * 1 if no recursion on this cpu * 0 if recursion detected */ static inline unsigned int xt_write_recseq_begin(void) { unsigned int addend; /* * Low order bit of sequence is set if we already * called xt_write_recseq_begin(). */ addend = (__this_cpu_read(xt_recseq.sequence) + 1) & 1; /* * This is kind of a write_seqcount_begin(), but addend is 0 or 1 * We dont check addend value to avoid a test and conditional jump, * since addend is most likely 1 */ __this_cpu_add(xt_recseq.sequence, addend); smp_mb(); return addend; } /** * xt_write_recseq_end - end of a write section * @addend: return value from previous xt_write_recseq_begin() * * End packet processing : all readers can proceed * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) */ static inline void xt_write_recseq_end(unsigned int addend) { /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ smp_wmb(); __this_cpu_add(xt_recseq.sequence, addend); } /* * This helper is performance critical and must be inlined */ static inline unsigned long ifname_compare_aligned(const char *_a, const char *_b, const char *_mask) { const unsigned long *a = (const unsigned long *)_a; const unsigned long *b = (const unsigned long *)_b; const unsigned long *mask = (const unsigned long *)_mask; unsigned long ret; ret = (a[0] ^ b[0]) & mask[0]; if (IFNAMSIZ > sizeof(unsigned long)) ret |= (a[1] ^ b[1]) & mask[1]; if (IFNAMSIZ > 2 * sizeof(unsigned long)) ret |= (a[2] ^ b[2]) & mask[2]; if (IFNAMSIZ > 3 * sizeof(unsigned long)) ret |= (a[3] ^ b[3]) & mask[3]; BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); return ret; } struct xt_percpu_counter_alloc_state { unsigned int off; const char __percpu *mem; }; bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state, struct xt_counters *counter); void xt_percpu_counter_free(struct xt_counters *cnt); static inline struct xt_counters * xt_get_this_cpu_counter(struct xt_counters *cnt) { if (nr_cpu_ids > 1) return this_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt); return cnt; } static inline struct xt_counters * xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) { if (nr_cpu_ids > 1) return per_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt, cpu); return cnt; } struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); int xt_register_template(const struct xt_table *t, int(*table_init)(struct net *net)); void xt_unregister_template(const struct xt_table *t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT #include <net/compat.h> struct compat_xt_entry_match { union { struct { u_int16_t match_size; char name[XT_FUNCTION_MAXNAMELEN - 1]; u_int8_t revision; } user; struct { u_int16_t match_size; compat_uptr_t match; } kernel; u_int16_t match_size; } u; unsigned char data[]; }; struct compat_xt_entry_target { union { struct { u_int16_t target_size; char name[XT_FUNCTION_MAXNAMELEN - 1]; u_int8_t revision; } user; struct { u_int16_t target_size; compat_uptr_t target; } kernel; u_int16_t target_size; } u; unsigned char data[]; }; /* FIXME: this works only on 32 bit tasks * need to change whole approach in order to calculate align as function of * current task alignment */ struct compat_xt_counters { compat_u64 pcnt, bcnt; /* Packet and byte counters */ }; struct compat_xt_counters_info { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t num_counters; struct compat_xt_counters counters[]; }; struct _compat_xt_align { __u8 u8; __u16 u16; __u32 u32; compat_u64 u64; }; #define COMPAT_XT_ALIGN(s) __ALIGN_KERNEL((s), __alignof__(struct _compat_xt_align)) void xt_compat_lock(u_int8_t af); void xt_compat_unlock(u_int8_t af); int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta); void xt_compat_flush_offsets(u_int8_t af); int xt_compat_init_offsets(u8 af, unsigned int number); int xt_compat_calc_jump(u_int8_t af, unsigned int offset); int xt_compat_match_offset(const struct xt_match *match); void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, unsigned int *size); int xt_compat_match_to_user(const struct xt_entry_match *m, void __user **dstptr, unsigned int *size); int xt_compat_target_offset(const struct xt_target *target); void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, unsigned int *size); int xt_compat_target_to_user(const struct xt_entry_target *t, void __user **dstptr, unsigned int *size); int xt_compat_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); #endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ #endif /* _X_TABLES_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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _ACKVEC_H #define _ACKVEC_H /* * net/dccp/ackvec.h * * An implementation of Ack Vectors for the DCCP protocol * Copyright (c) 2007 University of Aberdeen, Scotland, UK * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@mandriva.com> */ #include <linux/dccp.h> #include <linux/compiler.h> #include <linux/list.h> #include <linux/types.h> /* * Ack Vector buffer space is static, in multiples of %DCCP_SINGLE_OPT_MAXLEN, * the maximum size of a single Ack Vector. Setting %DCCPAV_NUM_ACKVECS to 1 * will be sufficient for most cases of low Ack Ratios, using a value of 2 gives * more headroom if Ack Ratio is higher or when the sender acknowledges slowly. * The maximum value is bounded by the u16 types for indices and functions. */ #define DCCPAV_NUM_ACKVECS 2 #define DCCPAV_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * DCCPAV_NUM_ACKVECS) /* Estimated minimum average Ack Vector length - used for updating MPS */ #define DCCPAV_MIN_OPTLEN 16 /* Threshold for coping with large bursts of losses */ #define DCCPAV_BURST_THRESH (DCCPAV_MAX_ACKVEC_LEN / 8) enum dccp_ackvec_states { DCCPAV_RECEIVED = 0x00, DCCPAV_ECN_MARKED = 0x40, DCCPAV_RESERVED = 0x80, DCCPAV_NOT_RECEIVED = 0xC0 }; #define DCCPAV_MAX_RUNLEN 0x3F static inline u8 dccp_ackvec_runlen(const u8 *cell) { return *cell & DCCPAV_MAX_RUNLEN; } static inline u8 dccp_ackvec_state(const u8 *cell) { return *cell & ~DCCPAV_MAX_RUNLEN; } /** * struct dccp_ackvec - Ack Vector main data structure * * This implements a fixed-size circular buffer within an array and is largely * based on Appendix A of RFC 4340. * * @av_buf: circular buffer storage area * @av_buf_head: head index; begin of live portion in @av_buf * @av_buf_tail: tail index; first index _after_ the live portion in @av_buf * @av_buf_ackno: highest seqno of acknowledgeable packet recorded in @av_buf * @av_tail_ackno: lowest seqno of acknowledgeable packet recorded in @av_buf * @av_buf_nonce: ECN nonce sums, each covering subsequent segments of up to * %DCCP_SINGLE_OPT_MAXLEN cells in the live portion of @av_buf * @av_overflow: if 1 then buf_head == buf_tail indicates buffer wraparound * @av_records: list of %dccp_ackvec_record (Ack Vectors sent previously) */ struct dccp_ackvec { u8 av_buf[DCCPAV_MAX_ACKVEC_LEN]; u16 av_buf_head; u16 av_buf_tail; u64 av_buf_ackno:48; u64 av_tail_ackno:48; bool av_buf_nonce[DCCPAV_NUM_ACKVECS]; u8 av_overflow:1; struct list_head av_records; }; /** * struct dccp_ackvec_record - Records information about sent Ack Vectors * * These list entries define the additional information which the HC-Receiver * keeps about recently-sent Ack Vectors; again refer to RFC 4340, Appendix A. * * @avr_node: the list node in @av_records * @avr_ack_seqno: sequence number of the packet the Ack Vector was sent on * @avr_ack_ackno: the Ack number that this record/Ack Vector refers to * @avr_ack_ptr: pointer into @av_buf where this record starts * @avr_ack_runlen: run length of @avr_ack_ptr at the time of sending * @avr_ack_nonce: the sum of @av_buf_nonce's at the time this record was sent * * The list as a whole is sorted in descending order by @avr_ack_seqno. */ struct dccp_ackvec_record { struct list_head avr_node; u64 avr_ack_seqno:48; u64 avr_ack_ackno:48; u16 avr_ack_ptr; u8 avr_ack_runlen; u8 avr_ack_nonce:1; }; int dccp_ackvec_init(void); void dccp_ackvec_exit(void); struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority); void dccp_ackvec_free(struct dccp_ackvec *av); void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb); int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seq, u8 sum); void dccp_ackvec_clear_state(struct dccp_ackvec *av, const u64 ackno); u16 dccp_ackvec_buflen(const struct dccp_ackvec *av); static inline bool dccp_ackvec_is_empty(const struct dccp_ackvec *av) { return av->av_overflow == 0 && av->av_buf_head == av->av_buf_tail; } /** * struct dccp_ackvec_parsed - Record offsets of Ack Vectors in skb * @vec: start of vector (offset into skb) * @len: length of @vec * @nonce: whether @vec had an ECN nonce of 0 or 1 * @node: FIFO - arranged in descending order of ack_ackno * * This structure is used by CCIDs to access Ack Vectors in a received skb. */ struct dccp_ackvec_parsed { u8 *vec, len, nonce:1; struct list_head node; }; int dccp_ackvec_parsed_add(struct list_head *head, u8 *vec, u8 len, u8 nonce); void dccp_ackvec_parsed_cleanup(struct list_head *parsed_chunks); #endif /* _ACKVEC_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #ifndef _NET_BATMAN_ADV_ORIGINATOR_H_ #define _NET_BATMAN_ADV_ORIGINATOR_H_ #include "main.h" #include <linux/compiler.h> #include <linux/if_ether.h> #include <linux/jhash.h> #include <linux/kref.h> #include <linux/netlink.h> #include <linux/skbuff.h> #include <linux/types.h> bool batadv_compare_orig(const struct hlist_node *node, const void *data2); int batadv_originator_init(struct batadv_priv *bat_priv); void batadv_originator_free(struct batadv_priv *bat_priv); void batadv_purge_orig_ref(struct batadv_priv *bat_priv); void batadv_orig_node_release(struct kref *ref); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const u8 *addr); struct batadv_hardif_neigh_node * batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface, const u8 *neigh_addr); void batadv_hardif_neigh_release(struct kref *ref); struct batadv_neigh_node * batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node, struct batadv_hard_iface *hard_iface, const u8 *neigh_addr); void batadv_neigh_node_release(struct kref *ref); struct batadv_neigh_node * batadv_orig_router_get(struct batadv_orig_node *orig_node, const struct batadv_hard_iface *if_outgoing); struct batadv_neigh_node * batadv_orig_to_router(struct batadv_priv *bat_priv, u8 *orig_addr, struct batadv_hard_iface *if_outgoing); struct batadv_neigh_ifinfo * batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing); struct batadv_neigh_ifinfo * batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing); void batadv_neigh_ifinfo_release(struct kref *ref); int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb); struct batadv_orig_ifinfo * batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing); struct batadv_orig_ifinfo * batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing); void batadv_orig_ifinfo_release(struct kref *ref); int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb); struct batadv_orig_node_vlan * batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, unsigned short vid); struct batadv_orig_node_vlan * batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node, unsigned short vid); void batadv_orig_node_vlan_release(struct kref *ref); /** * batadv_choose_orig() - Return the index of the orig entry in the hash table * @data: mac address of the originator node * @size: the size of the hash table * * Return: the hash index where the object represented by @data should be * stored at. */ static inline u32 batadv_choose_orig(const void *data, u32 size) { u32 hash = 0; hash = jhash(data, ETH_ALEN, hash); return hash % size; } struct batadv_orig_node * batadv_orig_hash_find(struct batadv_priv *bat_priv, const void *data); /** * batadv_orig_node_vlan_put() - decrement the refcounter and possibly release * the originator-vlan object * @orig_vlan: the originator-vlan object to release */ static inline void batadv_orig_node_vlan_put(struct batadv_orig_node_vlan *orig_vlan) { if (!orig_vlan) return; kref_put(&orig_vlan->refcount, batadv_orig_node_vlan_release); } /** * batadv_neigh_ifinfo_put() - decrement the refcounter and possibly release * the neigh_ifinfo * @neigh_ifinfo: the neigh_ifinfo object to release */ static inline void batadv_neigh_ifinfo_put(struct batadv_neigh_ifinfo *neigh_ifinfo) { if (!neigh_ifinfo) return; kref_put(&neigh_ifinfo->refcount, batadv_neigh_ifinfo_release); } /** * batadv_hardif_neigh_put() - decrement the hardif neighbors refcounter * and possibly release it * @hardif_neigh: hardif neigh neighbor to free */ static inline void batadv_hardif_neigh_put(struct batadv_hardif_neigh_node *hardif_neigh) { if (!hardif_neigh) return; kref_put(&hardif_neigh->refcount, batadv_hardif_neigh_release); } /** * batadv_neigh_node_put() - decrement the neighbors refcounter and possibly * release it * @neigh_node: neigh neighbor to free */ static inline void batadv_neigh_node_put(struct batadv_neigh_node *neigh_node) { if (!neigh_node) return; kref_put(&neigh_node->refcount, batadv_neigh_node_release); } /** * batadv_orig_ifinfo_put() - decrement the refcounter and possibly release * the orig_ifinfo * @orig_ifinfo: the orig_ifinfo object to release */ static inline void batadv_orig_ifinfo_put(struct batadv_orig_ifinfo *orig_ifinfo) { if (!orig_ifinfo) return; kref_put(&orig_ifinfo->refcount, batadv_orig_ifinfo_release); } /** * batadv_orig_node_put() - decrement the orig node refcounter and possibly * release it * @orig_node: the orig node to free */ static inline void batadv_orig_node_put(struct batadv_orig_node *orig_node) { if (!orig_node) return; kref_put(&orig_node->refcount, batadv_orig_node_release); } #endif /* _NET_BATMAN_ADV_ORIGINATOR_H_ */ |
| 1223 185 185 46 46 46 39 39 39 39 171 95 169 171 169 171 95 95 171 171 171 171 171 95 95 75 65 65 75 40 40 17 40 8 8 8 8 4 4 5 5 5 3 3 3 3 46 46 46 46 3 3 3 3 1005 1000 1004 35 35 34 269 269 17 17 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/gfp.h> #include <linux/hugetlb.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/fixmap.h> #include <asm/mtrr.h> #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; EXPORT_SYMBOL(physical_mask); #endif #ifdef CONFIG_HIGHPTE #define PGTABLE_HIGHMEM __GFP_HIGHMEM #else #define PGTABLE_HIGHMEM 0 #endif #ifndef CONFIG_PARAVIRT static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table) { tlb_remove_page(tlb, table); } #endif gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM; pgtable_t pte_alloc_one(struct mm_struct *mm) { return __pte_alloc_one(mm, __userpte_alloc_gfp); } static int __init setup_userpte(char *arg) { if (!arg) return -EINVAL; /* * "userpte=nohigh" disables allocation of user pagetables in * high memory. */ if (strcmp(arg, "nohigh") == 0) __userpte_alloc_gfp &= ~__GFP_HIGHMEM; else return -EINVAL; return 0; } early_param("userpte", setup_userpte); void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { pagetable_pte_dtor(page_ptdesc(pte)); paravirt_release_pte(page_to_pfn(pte)); paravirt_tlb_remove_table(tlb, pte); } #if CONFIG_PGTABLE_LEVELS > 2 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { struct ptdesc *ptdesc = virt_to_ptdesc(pmd); paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); /* * NOTE! For PAE, any changes to the top page-directory-pointer-table * entries need a full cr3 reload to flush. */ #ifdef CONFIG_X86_PAE tlb->need_flush_all = 1; #endif pagetable_pmd_dtor(ptdesc); paravirt_tlb_remove_table(tlb, ptdesc_page(ptdesc)); } #if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { struct ptdesc *ptdesc = virt_to_ptdesc(pud); pagetable_pud_dtor(ptdesc); paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); paravirt_tlb_remove_table(tlb, virt_to_page(pud)); } #if CONFIG_PGTABLE_LEVELS > 4 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d) { paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT); paravirt_tlb_remove_table(tlb, virt_to_page(p4d)); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ static inline void pgd_list_add(pgd_t *pgd) { struct ptdesc *ptdesc = virt_to_ptdesc(pgd); list_add(&ptdesc->pt_list, &pgd_list); } static inline void pgd_list_del(pgd_t *pgd) { struct ptdesc *ptdesc = virt_to_ptdesc(pgd); list_del(&ptdesc->pt_list); } #define UNSHARED_PTRS_PER_PGD \ (SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD) #define MAX_UNSHARED_PTRS_PER_PGD \ MAX_T(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD) static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm) { virt_to_ptdesc(pgd)->pt_mm = mm; } struct mm_struct *pgd_page_get_mm(struct page *page) { return page_ptdesc(page)->pt_mm; } static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) { /* If the pgd points to a shared pagetable level (either the ptes in non-PAE, or shared PMD in PAE), then just copy the references from swapper_pg_dir. */ if (CONFIG_PGTABLE_LEVELS == 2 || (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) || CONFIG_PGTABLE_LEVELS >= 4) { clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, KERNEL_PGD_PTRS); } /* list required to sync kernel mapping updates */ if (!SHARED_KERNEL_PMD) { pgd_set_mm(pgd, mm); pgd_list_add(pgd); } } static void pgd_dtor(pgd_t *pgd) { if (SHARED_KERNEL_PMD) return; spin_lock(&pgd_lock); pgd_list_del(pgd); spin_unlock(&pgd_lock); } /* * List of all pgd's needed for non-PAE so it can invalidate entries * in both cached and uncached pgd's; not needed for PAE since the * kernel pmd is shared. If PAE were not to share the pmd a similar * tactic would be needed. This is essentially codepath-based locking * against pageattr.c; it is the unique case in which a valid change * of kernel pagetables can't be lazily synchronized by vmalloc faults. * vmalloc faults work because attached pagetables are never freed. * -- nyc */ #ifdef CONFIG_X86_PAE /* * In PAE mode, we need to do a cr3 reload (=tlb flush) when * updating the top-level pagetable entries to guarantee the * processor notices the update. Since this is expensive, and * all 4 top-level entries are used almost immediately in a * new process's life, we just pre-populate them here. * * Also, if we're in a paravirt environment where the kernel pmd is * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate * and initialize the kernel pmds here. */ #define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD #define MAX_PREALLOCATED_PMDS MAX_UNSHARED_PTRS_PER_PGD /* * We allocate separate PMDs for the kernel part of the user page-table * when PTI is enabled. We need them to map the per-process LDT into the * user-space page-table. */ #define PREALLOCATED_USER_PMDS (boot_cpu_has(X86_FEATURE_PTI) ? \ KERNEL_PGD_PTRS : 0) #define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); /* Note: almost everything apart from _PAGE_PRESENT is reserved at the pmd (PDPT) level. */ set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT)); /* * According to Intel App note "TLBs, Paging-Structure Caches, * and Their Invalidation", April 2007, document 317080-001, * section 8.1: in PAE mode we explicitly have to flush the * TLB via cr3 if the top-level pgd is changed... */ flush_tlb_mm(mm); } #else /* !CONFIG_X86_PAE */ /* No need to prepopulate any pagetable entries in non-PAE modes. */ #define PREALLOCATED_PMDS 0 #define MAX_PREALLOCATED_PMDS 0 #define PREALLOCATED_USER_PMDS 0 #define MAX_PREALLOCATED_USER_PMDS 0 #endif /* CONFIG_X86_PAE */ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; struct ptdesc *ptdesc; for (i = 0; i < count; i++) if (pmds[i]) { ptdesc = virt_to_ptdesc(pmds[i]); pagetable_pmd_dtor(ptdesc); pagetable_free(ptdesc); mm_dec_nr_pmds(mm); } } static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; bool failed = false; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; gfp &= ~__GFP_HIGHMEM; for (i = 0; i < count; i++) { pmd_t *pmd = NULL; struct ptdesc *ptdesc = pagetable_alloc(gfp, 0); if (!ptdesc) failed = true; if (ptdesc && !pagetable_pmd_ctor(ptdesc)) { pagetable_free(ptdesc); ptdesc = NULL; failed = true; } if (ptdesc) { mm_inc_nr_pmds(mm); pmd = ptdesc_address(ptdesc); } pmds[i] = pmd; } if (failed) { free_pmds(mm, pmds, count); return -ENOMEM; } return 0; } /* * Mop up any pmd pages which may still be attached to the pgd. * Normally they will be freed by munmap/exit_mmap, but any pmd we * preallocate which never got a corresponding vma will need to be * freed manually. */ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp) { pgd_t pgd = *pgdp; if (pgd_val(pgd) != 0) { pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); pgd_clear(pgdp); paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); mm_dec_nr_pmds(mm); } } static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) { int i; for (i = 0; i < PREALLOCATED_PMDS; i++) mop_up_one_pmd(mm, &pgdp[i]); #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!boot_cpu_has(X86_FEATURE_PTI)) return; pgdp = kernel_to_user_pgdp(pgdp); for (i = 0; i < PREALLOCATED_USER_PMDS; i++) mop_up_one_pmd(mm, &pgdp[i + KERNEL_PGD_BOUNDARY]); #endif } static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) { p4d_t *p4d; pud_t *pud; int i; p4d = p4d_offset(pgd, 0); pud = pud_offset(p4d, 0); for (i = 0; i < PREALLOCATED_PMDS; i++, pud++) { pmd_t *pmd = pmds[i]; if (i >= KERNEL_PGD_BOUNDARY) memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]), sizeof(pmd_t) * PTRS_PER_PMD); pud_populate(mm, pud, pmd); } } #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { pgd_t *s_pgd = kernel_to_user_pgdp(swapper_pg_dir); pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd); p4d_t *u_p4d; pud_t *u_pud; int i; u_p4d = p4d_offset(u_pgd, 0); u_pud = pud_offset(u_p4d, 0); s_pgd += KERNEL_PGD_BOUNDARY; u_pud += KERNEL_PGD_BOUNDARY; for (i = 0; i < PREALLOCATED_USER_PMDS; i++, u_pud++, s_pgd++) { pmd_t *pmd = pmds[i]; memcpy(pmd, (pmd_t *)pgd_page_vaddr(*s_pgd), sizeof(pmd_t) * PTRS_PER_PMD); pud_populate(mm, u_pud, pmd); } } #else static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { } #endif /* * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also * assumes that pgd should be in one page. * * But kernel with PAE paging that is not running as a Xen domain * only needs to allocate 32 bytes for pgd instead of one page. */ #ifdef CONFIG_X86_PAE #include <linux/slab.h> #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #define PGD_ALIGN 32 static struct kmem_cache *pgd_cache; void __init pgtable_cache_init(void) { /* * When PAE kernel is running as a Xen domain, it does not use * shared kernel pmd. And this requires a whole page for pgd. */ if (!SHARED_KERNEL_PMD) return; /* * when PAE kernel is not running as a Xen domain, it uses * shared kernel pmd. Shared kernel pmd does not require a whole * page for pgd. We are able to just allocate a 32-byte for pgd. * During boot time, we create a 32-byte slab for pgd table allocation. */ pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN, SLAB_PANIC, NULL); } static inline pgd_t *_pgd_alloc(void) { /* * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain. * We allocate one page for pgd. */ if (!SHARED_KERNEL_PMD) return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, PGD_ALLOCATION_ORDER); /* * Now PAE kernel is not running as a Xen domain. We can allocate * a 32-byte slab for pgd to save memory space. */ return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER); } static inline void _pgd_free(pgd_t *pgd) { if (!SHARED_KERNEL_PMD) free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); else kmem_cache_free(pgd_cache, pgd); } #else static inline pgd_t *_pgd_alloc(void) { return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, PGD_ALLOCATION_ORDER); } static inline void _pgd_free(pgd_t *pgd) { free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); } #endif /* CONFIG_X86_PAE */ pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS]; pmd_t *pmds[MAX_PREALLOCATED_PMDS]; pgd = _pgd_alloc(); if (pgd == NULL) goto out; mm->pgd = pgd; if (sizeof(pmds) != 0 && preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0) goto out_free_pgd; if (sizeof(u_pmds) != 0 && preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0) goto out_free_pmds; if (paravirt_pgd_alloc(mm) != 0) goto out_free_user_pmds; /* * Make sure that pre-populating the pmds is atomic with * respect to anything walking the pgd_list, so that they * never see a partially populated pgd. */ spin_lock(&pgd_lock); pgd_ctor(mm, pgd); if (sizeof(pmds) != 0) pgd_prepopulate_pmd(mm, pgd, pmds); if (sizeof(u_pmds) != 0) pgd_prepopulate_user_pmd(mm, pgd, u_pmds); spin_unlock(&pgd_lock); return pgd; out_free_user_pmds: if (sizeof(u_pmds) != 0) free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS); out_free_pmds: if (sizeof(pmds) != 0) free_pmds(mm, pmds, PREALLOCATED_PMDS); out_free_pgd: _pgd_free(pgd); out: return NULL; } void pgd_free(struct mm_struct *mm, pgd_t *pgd) { pgd_mop_up_pmds(mm, pgd); pgd_dtor(pgd); paravirt_pgd_free(mm, pgd); _pgd_free(pgd); } /* * Used to set accessed or dirty bits in the page table entries * on other architectures. On x86, the accessed and dirty bits * are tracked by hardware. However, do_wp_page calls this function * to also make the pte writeable at the same time the dirty bit is * set. In that case we do actually need to write the PTE. */ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { int changed = !pte_same(*ptep, entry); if (changed && dirty) set_pte(ptep, entry); return changed; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { int changed = !pmd_same(*pmdp, entry); VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed && dirty) { set_pmd(pmdp, entry); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, * #PF is architecturally guaranteed to do that and in the * worst-case we'll generate a spurious fault. */ } return changed; } int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty) { int changed = !pud_same(*pudp, entry); VM_BUG_ON(address & ~HPAGE_PUD_MASK); if (changed && dirty) { set_pud(pudp, entry); /* * We had a write-protection fault here and changed the pud * to to more permissive. No need to flush the TLB for that, * #PF is architecturally guaranteed to do that and in the * worst-case we'll generate a spurious fault. */ } return changed; } #endif int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { int ret = 0; if (pte_young(*ptep)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *) &ptep->pte); return ret; } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { int ret = 0; if (pmd_young(*pmdp)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pmdp); return ret; } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp) { int ret = 0; if (pud_young(*pudp)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pudp); return ret; } #endif int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { /* * On x86 CPUs, clearing the accessed bit without a TLB flush * doesn't cause data corruption. [ It could cause incorrect * page aging and the (mistaken) reclaim of hot pages, but the * chance of that should be relatively low. ] * * So as a performance optimization don't flush the TLB when * clearing the accessed bit, it will eventually be flushed by * a context switch or a VM operation anyway. [ In the rare * event of it not getting flushed for a long time the delay * shouldn't really matter because there's no real memory * pressure for swapout to react to. ] */ return ptep_test_and_clear_young(vma, address, ptep); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { int young; VM_BUG_ON(address & ~HPAGE_PMD_MASK); young = pmdp_test_and_clear_young(vma, address, pmdp); if (young) flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return young; } pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { VM_WARN_ON_ONCE(!pmd_present(*pmdp)); /* * No flush is necessary. Once an invalid PTE is established, the PTE's * access and dirty bits cannot be updated. */ return pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); } #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, pud_t *pudp) { VM_WARN_ON_ONCE(!pud_present(*pudp)); pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp)); flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); return old; } #endif /** * reserve_top_address - reserves a hole in the top of kernel address space * @reserve - size of hole to reserve * * Can be used to relocate the fixmap area and poke a hole in the top * of kernel address space to make room for a hypervisor. */ void __init reserve_top_address(unsigned long reserve) { #ifdef CONFIG_X86_32 BUG_ON(fixmaps_set > 0); __FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE; printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n", -reserve, __FIXADDR_TOP + PAGE_SIZE); #endif } int fixmaps_set; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) { unsigned long address = __fix_to_virt(idx); #ifdef CONFIG_X86_64 /* * Ensure that the static initial page tables are covering the * fixmap completely. */ BUILD_BUG_ON(__end_of_permanent_fixed_addresses > (FIXMAP_PMD_NUM * PTRS_PER_PTE)); #endif if (idx >= __end_of_fixed_addresses) { BUG(); return; } set_pte_vaddr(address, pte); fixmaps_set++; } void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) { /* Sanitize 'prot' against any unsupported bits: */ pgprot_val(flags) &= __default_kernel_pte_mask; __native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags)); } #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #ifdef CONFIG_X86_5LEVEL /** * p4d_set_huge - setup kernel P4D mapping * * No 512GB pages yet -- always return 0 */ int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } /** * p4d_clear_huge - clear kernel P4D mapping when it is set * * No 512GB pages yet -- always return 0 */ void p4d_clear_huge(p4d_t *p4d) { } #endif /** * pud_set_huge - setup kernel PUD mapping * * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this * function sets up a huge page only if the complete range has the same MTRR * caching mode. * * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger * page mapping attempt fails. * * Returns 1 on success and 0 on failure. */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { u8 uniform; mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform); if (!uniform) return 0; /* Bail out if we are we on a populated non-leaf entry: */ if (pud_present(*pud) && !pud_leaf(*pud)) return 0; set_pte((pte_t *)pud, pfn_pte( (u64)addr >> PAGE_SHIFT, __pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE))); return 1; } /** * pmd_set_huge - setup kernel PMD mapping * * See text over pud_set_huge() above. * * Returns 1 on success and 0 on failure. */ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { u8 uniform; mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform); if (!uniform) { pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n", __func__, addr, addr + PMD_SIZE); return 0; } /* Bail out if we are we on a populated non-leaf entry: */ if (pmd_present(*pmd) && !pmd_leaf(*pmd)) return 0; set_pte((pte_t *)pmd, pfn_pte( (u64)addr >> PAGE_SHIFT, __pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE))); return 1; } /** * pud_clear_huge - clear kernel PUD mapping when it is set * * Returns 1 on success and 0 on failure (no PUD map is found). */ int pud_clear_huge(pud_t *pud) { if (pud_leaf(*pud)) { pud_clear(pud); return 1; } return 0; } /** * pmd_clear_huge - clear kernel PMD mapping when it is set * * Returns 1 on success and 0 on failure (no PMD map is found). */ int pmd_clear_huge(pmd_t *pmd) { if (pmd_leaf(*pmd)) { pmd_clear(pmd); return 1; } return 0; } #ifdef CONFIG_X86_64 /** * pud_free_pmd_page - Clear pud entry and free pmd page. * @pud: Pointer to a PUD. * @addr: Virtual address associated with pud. * * Context: The pud range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. * * NOTE: Callers must allow a single page allocation. */ int pud_free_pmd_page(pud_t *pud, unsigned long addr) { pmd_t *pmd, *pmd_sv; pte_t *pte; int i; pmd = pud_pgtable(*pud); pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL); if (!pmd_sv) return 0; for (i = 0; i < PTRS_PER_PMD; i++) { pmd_sv[i] = pmd[i]; if (!pmd_none(pmd[i])) pmd_clear(&pmd[i]); } pud_clear(pud); /* INVLPG to clear all paging-structure caches */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); for (i = 0; i < PTRS_PER_PMD; i++) { if (!pmd_none(pmd_sv[i])) { pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]); free_page((unsigned long)pte); } } free_page((unsigned long)pmd_sv); pagetable_pmd_dtor(virt_to_ptdesc(pmd)); free_page((unsigned long)pmd); return 1; } /** * pmd_free_pte_page - Clear pmd entry and free pte page. * @pmd: Pointer to a PMD. * @addr: Virtual address associated with pmd. * * Context: The pmd range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. */ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { pte_t *pte; pte = (pte_t *)pmd_page_vaddr(*pmd); pmd_clear(pmd); /* INVLPG to clear all paging-structure caches */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); free_page((unsigned long)pte); return 1; } #else /* !CONFIG_X86_64 */ /* * Disable free page handling on x86-PAE. This assures that ioremap() * does not update sync'd pmd entries. See vmalloc_sync_one(). */ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return pmd_none(*pmd); } #endif /* CONFIG_X86_64 */ #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHADOW_STACK) return pte_mkwrite_shstk(pte); pte = pte_mkwrite_novma(pte); return pte_clear_saveddirty(pte); } pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHADOW_STACK) return pmd_mkwrite_shstk(pmd); pmd = pmd_mkwrite_novma(pmd); return pmd_clear_saveddirty(pmd); } void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte) { /* * Hardware before shadow stack can (rarely) set Dirty=1 * on a Write=0 PTE. So the below condition * only indicates a software bug when shadow stack is * supported by the HW. This checking is covered in * pte_shstk(). */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pte_shstk(pte)); } void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd) { /* See note in arch_check_zapped_pte() */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pmd_shstk(pmd)); } void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud) { /* See note in arch_check_zapped_pte() */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pud_shstk(pud)); } |
| 12 11 1 17 1 14 12 14 12 11 15 15 1 15 14 15 15 10 15 15 14 15 11 11 11 1 15 15 15 15 15 2 2 2 2 2 2 2 2 2 2 2 2 2 11 11 11 11 11 11 15 11 15 15 15 4 15 15 21 20 6 5 2 18 2 16 1 15 11 4 4 4 1 4 2 21 13 15 15 12 2 12 1 12 2 12 2 1 1 2 1 12 12 1 1 11 15 12 1 4 3 1 2 1 1 1 1 1 4 4 3 1 4 2 1 1 1 1 1 1 2 2 2 2 2 2 1 3 2 1 1 3 3 3 3 3 1 2 1 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Network block device - make block devices work over TCP * * Note that you can not swap over this thing, yet. Seems to work but * deadlocks sometimes - you can not swap over TCP in general. * * Copyright 1997-2000, 2008 Pavel Machek <pavel@ucw.cz> * Parts copyright 2001 Steven Whitehouse <steve@chygwyn.com> * * (part of code stolen from loop.c) */ #define pr_fmt(fmt) "nbd: " fmt #include <linux/major.h> #include <linux/blkdev.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/fs.h> #include <linux/bio.h> #include <linux/stat.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/ioctl.h> #include <linux/mutex.h> #include <linux/compiler.h> #include <linux/completion.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/slab.h> #include <net/sock.h> #include <linux/net.h> #include <linux/kthread.h> #include <linux/types.h> #include <linux/debugfs.h> #include <linux/blk-mq.h> #include <linux/uaccess.h> #include <asm/types.h> #include <linux/nbd.h> #include <linux/nbd-netlink.h> #include <net/genetlink.h> #define CREATE_TRACE_POINTS #include <trace/events/nbd.h> static DEFINE_IDR(nbd_index_idr); static DEFINE_MUTEX(nbd_index_mutex); static struct workqueue_struct *nbd_del_wq; static int nbd_total_devices = 0; struct nbd_sock { struct socket *sock; struct mutex tx_lock; struct request *pending; int sent; bool dead; int fallback_index; int cookie; }; struct recv_thread_args { struct work_struct work; struct nbd_device *nbd; struct nbd_sock *nsock; int index; }; struct link_dead_args { struct work_struct work; int index; }; #define NBD_RT_TIMEDOUT 0 #define NBD_RT_DISCONNECT_REQUESTED 1 #define NBD_RT_DISCONNECTED 2 #define NBD_RT_HAS_PID_FILE 3 #define NBD_RT_HAS_CONFIG_REF 4 #define NBD_RT_BOUND 5 #define NBD_RT_DISCONNECT_ON_CLOSE 6 #define NBD_RT_HAS_BACKEND_FILE 7 #define NBD_DESTROY_ON_DISCONNECT 0 #define NBD_DISCONNECT_REQUESTED 1 struct nbd_config { u32 flags; unsigned long runtime_flags; u64 dead_conn_timeout; struct nbd_sock **socks; int num_connections; atomic_t live_connections; wait_queue_head_t conn_wait; atomic_t recv_threads; wait_queue_head_t recv_wq; unsigned int blksize_bits; loff_t bytesize; #if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbg_dir; #endif }; static inline unsigned int nbd_blksize(struct nbd_config *config) { return 1u << config->blksize_bits; } struct nbd_device { struct blk_mq_tag_set tag_set; int index; refcount_t config_refs; refcount_t refs; struct nbd_config *config; struct mutex config_lock; struct gendisk *disk; struct workqueue_struct *recv_workq; struct work_struct remove_work; struct list_head list; struct task_struct *task_setup; unsigned long flags; pid_t pid; /* pid of nbd-client, if attached */ char *backend; }; #define NBD_CMD_REQUEUED 1 /* * This flag will be set if nbd_queue_rq() succeed, and will be checked and * cleared in completion. Both setting and clearing of the flag are protected * by cmd->lock. */ #define NBD_CMD_INFLIGHT 2 struct nbd_cmd { struct nbd_device *nbd; struct mutex lock; int index; int cookie; int retries; blk_status_t status; unsigned long flags; u32 cmd_cookie; }; #if IS_ENABLED(CONFIG_DEBUG_FS) static struct dentry *nbd_dbg_dir; #endif #define nbd_name(nbd) ((nbd)->disk->disk_name) #define NBD_DEF_BLKSIZE_BITS 10 static unsigned int nbds_max = 16; static int max_part = 16; static int part_shift; static int nbd_dev_dbg_init(struct nbd_device *nbd); static void nbd_dev_dbg_close(struct nbd_device *nbd); static void nbd_config_put(struct nbd_device *nbd); static void nbd_connect_reply(struct genl_info *info, int index); static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info); static void nbd_dead_link_work(struct work_struct *work); static void nbd_disconnect_and_put(struct nbd_device *nbd); static inline struct device *nbd_to_dev(struct nbd_device *nbd) { return disk_to_dev(nbd->disk); } static void nbd_requeue_cmd(struct nbd_cmd *cmd) { struct request *req = blk_mq_rq_from_pdu(cmd); lockdep_assert_held(&cmd->lock); /* * Clear INFLIGHT flag so that this cmd won't be completed in * normal completion path * * INFLIGHT flag will be set when the cmd is queued to nbd next * time. */ __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags)) blk_mq_requeue_request(req, true); } #define NBD_COOKIE_BITS 32 static u64 nbd_cmd_handle(struct nbd_cmd *cmd) { struct request *req = blk_mq_rq_from_pdu(cmd); u32 tag = blk_mq_unique_tag(req); u64 cookie = cmd->cmd_cookie; return (cookie << NBD_COOKIE_BITS) | tag; } static u32 nbd_handle_to_tag(u64 handle) { return (u32)handle; } static u32 nbd_handle_to_cookie(u64 handle) { return (u32)(handle >> NBD_COOKIE_BITS); } static const char *nbdcmd_to_ascii(int cmd) { switch (cmd) { case NBD_CMD_READ: return "read"; case NBD_CMD_WRITE: return "write"; case NBD_CMD_DISC: return "disconnect"; case NBD_CMD_FLUSH: return "flush"; case NBD_CMD_TRIM: return "trim/discard"; } return "invalid"; } static ssize_t pid_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); struct nbd_device *nbd = disk->private_data; return sprintf(buf, "%d\n", nbd->pid); } static const struct device_attribute pid_attr = { .attr = { .name = "pid", .mode = 0444}, .show = pid_show, }; static ssize_t backend_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); struct nbd_device *nbd = disk->private_data; return sprintf(buf, "%s\n", nbd->backend ?: ""); } static const struct device_attribute backend_attr = { .attr = { .name = "backend", .mode = 0444}, .show = backend_show, }; static void nbd_dev_remove(struct nbd_device *nbd) { struct gendisk *disk = nbd->disk; del_gendisk(disk); blk_mq_free_tag_set(&nbd->tag_set); /* * Remove from idr after del_gendisk() completes, so if the same ID is * reused, the following add_disk() will succeed. */ mutex_lock(&nbd_index_mutex); idr_remove(&nbd_index_idr, nbd->index); mutex_unlock(&nbd_index_mutex); destroy_workqueue(nbd->recv_workq); put_disk(disk); } static void nbd_dev_remove_work(struct work_struct *work) { nbd_dev_remove(container_of(work, struct nbd_device, remove_work)); } static void nbd_put(struct nbd_device *nbd) { if (!refcount_dec_and_test(&nbd->refs)) return; /* Call del_gendisk() asynchrounously to prevent deadlock */ if (test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) queue_work(nbd_del_wq, &nbd->remove_work); else nbd_dev_remove(nbd); } static int nbd_disconnected(struct nbd_config *config) { return test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags) || test_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags); } static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock, int notify) { if (!nsock->dead && notify && !nbd_disconnected(nbd->config)) { struct link_dead_args *args; args = kmalloc(sizeof(struct link_dead_args), GFP_NOIO); if (args) { INIT_WORK(&args->work, nbd_dead_link_work); args->index = nbd->index; queue_work(system_wq, &args->work); } } if (!nsock->dead) { kernel_sock_shutdown(nsock->sock, SHUT_RDWR); if (atomic_dec_return(&nbd->config->live_connections) == 0) { if (test_and_clear_bit(NBD_RT_DISCONNECT_REQUESTED, &nbd->config->runtime_flags)) { set_bit(NBD_RT_DISCONNECTED, &nbd->config->runtime_flags); dev_info(nbd_to_dev(nbd), "Disconnected due to user request.\n"); } } } nsock->dead = true; nsock->pending = NULL; nsock->sent = 0; } static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize) { struct queue_limits lim; int error; if (!blksize) blksize = 1u << NBD_DEF_BLKSIZE_BITS; if (blk_validate_block_size(blksize)) return -EINVAL; if (bytesize < 0) return -EINVAL; nbd->config->bytesize = bytesize; nbd->config->blksize_bits = __ffs(blksize); if (!nbd->pid) return 0; lim = queue_limits_start_update(nbd->disk->queue); if (nbd->config->flags & NBD_FLAG_SEND_TRIM) lim.max_hw_discard_sectors = UINT_MAX >> SECTOR_SHIFT; else lim.max_hw_discard_sectors = 0; if (!(nbd->config->flags & NBD_FLAG_SEND_FLUSH)) { lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA); } else if (nbd->config->flags & NBD_FLAG_SEND_FUA) { lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA; } else { lim.features |= BLK_FEAT_WRITE_CACHE; lim.features &= ~BLK_FEAT_FUA; } if (nbd->config->flags & NBD_FLAG_ROTATIONAL) lim.features |= BLK_FEAT_ROTATIONAL; if (nbd->config->flags & NBD_FLAG_SEND_WRITE_ZEROES) lim.max_write_zeroes_sectors = UINT_MAX >> SECTOR_SHIFT; lim.logical_block_size = blksize; lim.physical_block_size = blksize; error = queue_limits_commit_update(nbd->disk->queue, &lim); if (error) return error; if (max_part) set_bit(GD_NEED_PART_SCAN, &nbd->disk->state); if (!set_capacity_and_notify(nbd->disk, bytesize >> 9)) kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE); return 0; } static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize) { int error; blk_mq_freeze_queue(nbd->disk->queue); error = __nbd_set_size(nbd, bytesize, blksize); blk_mq_unfreeze_queue(nbd->disk->queue); return error; } static void nbd_complete_rq(struct request *req) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", req, cmd->status ? "failed" : "done"); blk_mq_end_request(req, cmd->status); } /* * Forcibly shutdown the socket causing all listeners to error */ static void sock_shutdown(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; int i; if (config->num_connections == 0) return; if (test_and_set_bit(NBD_RT_DISCONNECTED, &config->runtime_flags)) return; for (i = 0; i < config->num_connections; i++) { struct nbd_sock *nsock = config->socks[i]; mutex_lock(&nsock->tx_lock); nbd_mark_nsock_dead(nbd, nsock, 0); mutex_unlock(&nsock->tx_lock); } dev_warn(disk_to_dev(nbd->disk), "shutting down sockets\n"); } static u32 req_to_nbd_cmd_type(struct request *req) { switch (req_op(req)) { case REQ_OP_DISCARD: return NBD_CMD_TRIM; case REQ_OP_FLUSH: return NBD_CMD_FLUSH; case REQ_OP_WRITE: return NBD_CMD_WRITE; case REQ_OP_READ: return NBD_CMD_READ; case REQ_OP_WRITE_ZEROES: return NBD_CMD_WRITE_ZEROES; default: return U32_MAX; } } static struct nbd_config *nbd_get_config_unlocked(struct nbd_device *nbd) { if (refcount_inc_not_zero(&nbd->config_refs)) { /* * Add smp_mb__after_atomic to ensure that reading nbd->config_refs * and reading nbd->config is ordered. The pair is the barrier in * nbd_alloc_and_init_config(), avoid nbd->config_refs is set * before nbd->config. */ smp_mb__after_atomic(); return nbd->config; } return NULL; } static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); struct nbd_device *nbd = cmd->nbd; struct nbd_config *config; if (!mutex_trylock(&cmd->lock)) return BLK_EH_RESET_TIMER; if (!test_bit(NBD_CMD_INFLIGHT, &cmd->flags)) { mutex_unlock(&cmd->lock); return BLK_EH_DONE; } config = nbd_get_config_unlocked(nbd); if (!config) { cmd->status = BLK_STS_TIMEOUT; __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); mutex_unlock(&cmd->lock); goto done; } if (config->num_connections > 1 || (config->num_connections == 1 && nbd->tag_set.timeout)) { dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out, retrying (%d/%d alive)\n", atomic_read(&config->live_connections), config->num_connections); /* * Hooray we have more connections, requeue this IO, the submit * path will put it on a real connection. Or if only one * connection is configured, the submit path will wait util * a new connection is reconfigured or util dead timeout. */ if (config->socks) { if (cmd->index < config->num_connections) { struct nbd_sock *nsock = config->socks[cmd->index]; mutex_lock(&nsock->tx_lock); /* We can have multiple outstanding requests, so * we don't want to mark the nsock dead if we've * already reconnected with a new socket, so * only mark it dead if its the same socket we * were sent out on. */ if (cmd->cookie == nsock->cookie) nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); } nbd_requeue_cmd(cmd); mutex_unlock(&cmd->lock); nbd_config_put(nbd); return BLK_EH_DONE; } } if (!nbd->tag_set.timeout) { /* * Userspace sets timeout=0 to disable socket disconnection, * so just warn and reset the timer. */ struct nbd_sock *nsock = config->socks[cmd->index]; cmd->retries++; dev_info(nbd_to_dev(nbd), "Possible stuck request %p: control (%s@%llu,%uB). Runtime %u seconds\n", req, nbdcmd_to_ascii(req_to_nbd_cmd_type(req)), (unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req), (req->timeout / HZ) * cmd->retries); mutex_lock(&nsock->tx_lock); if (cmd->cookie != nsock->cookie) { nbd_requeue_cmd(cmd); mutex_unlock(&nsock->tx_lock); mutex_unlock(&cmd->lock); nbd_config_put(nbd); return BLK_EH_DONE; } mutex_unlock(&nsock->tx_lock); mutex_unlock(&cmd->lock); nbd_config_put(nbd); return BLK_EH_RESET_TIMER; } dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out\n"); set_bit(NBD_RT_TIMEDOUT, &config->runtime_flags); cmd->status = BLK_STS_IOERR; __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); mutex_unlock(&cmd->lock); sock_shutdown(nbd); nbd_config_put(nbd); done: blk_mq_complete_request(req); return BLK_EH_DONE; } static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, struct iov_iter *iter, int msg_flags, int *sent) { int result; struct msghdr msg = {} ; unsigned int noreclaim_flag; if (unlikely(!sock)) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Attempted %s on closed socket in sock_xmit\n", (send ? "send" : "recv")); return -EINVAL; } msg.msg_iter = *iter; noreclaim_flag = memalloc_noreclaim_save(); do { sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC; sock->sk->sk_use_task_frag = false; msg.msg_flags = msg_flags | MSG_NOSIGNAL; if (send) result = sock_sendmsg(sock, &msg); else result = sock_recvmsg(sock, &msg, msg.msg_flags); if (result <= 0) { if (result == 0) result = -EPIPE; /* short read */ break; } if (sent) *sent += result; } while (msg_data_left(&msg)); memalloc_noreclaim_restore(noreclaim_flag); return result; } /* * Send or receive packet. Return a positive value on success and * negtive value on failure, and never return 0. */ static int sock_xmit(struct nbd_device *nbd, int index, int send, struct iov_iter *iter, int msg_flags, int *sent) { struct nbd_config *config = nbd->config; struct socket *sock = config->socks[index]->sock; return __sock_xmit(nbd, sock, send, iter, msg_flags, sent); } /* * Different settings for sk->sk_sndtimeo can result in different return values * if there is a signal pending when we enter sendmsg, because reasons? */ static inline int was_interrupted(int result) { return result == -ERESTARTSYS || result == -EINTR; } /* * Returns BLK_STS_RESOURCE if the caller should retry after a delay. * Returns BLK_STS_IOERR if sending failed. */ static blk_status_t nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); struct nbd_config *config = nbd->config; struct nbd_sock *nsock = config->socks[index]; int result; struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)}; struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)}; struct iov_iter from; struct bio *bio; u64 handle; u32 type; u32 nbd_cmd_flags = 0; int sent = nsock->sent, skip = 0; lockdep_assert_held(&cmd->lock); lockdep_assert_held(&nsock->tx_lock); iov_iter_kvec(&from, ITER_SOURCE, &iov, 1, sizeof(request)); type = req_to_nbd_cmd_type(req); if (type == U32_MAX) return BLK_STS_IOERR; if (rq_data_dir(req) == WRITE && (config->flags & NBD_FLAG_READ_ONLY)) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Write on read-only\n"); return BLK_STS_IOERR; } if (req->cmd_flags & REQ_FUA) nbd_cmd_flags |= NBD_CMD_FLAG_FUA; if ((req->cmd_flags & REQ_NOUNMAP) && (type == NBD_CMD_WRITE_ZEROES)) nbd_cmd_flags |= NBD_CMD_FLAG_NO_HOLE; /* We did a partial send previously, and we at least sent the whole * request struct, so just go and send the rest of the pages in the * request. */ if (sent) { if (sent >= sizeof(request)) { skip = sent - sizeof(request); /* initialize handle for tracing purposes */ handle = nbd_cmd_handle(cmd); goto send_pages; } iov_iter_advance(&from, sent); } else { cmd->cmd_cookie++; } cmd->index = index; cmd->cookie = nsock->cookie; cmd->retries = 0; request.type = htonl(type | nbd_cmd_flags); if (type != NBD_CMD_FLUSH) { request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); request.len = htonl(blk_rq_bytes(req)); } handle = nbd_cmd_handle(cmd); request.cookie = cpu_to_be64(handle); trace_nbd_send_request(&request, nbd->index, blk_mq_rq_from_pdu(cmd)); dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n", req, nbdcmd_to_ascii(type), (unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req)); result = sock_xmit(nbd, index, 1, &from, (type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent); trace_nbd_header_sent(req, handle); if (result < 0) { if (was_interrupted(result)) { /* If we haven't sent anything we can just return BUSY, * however if we have sent something we need to make * sure we only allow this req to be sent until we are * completely done. */ if (sent) { nsock->pending = req; nsock->sent = sent; } set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), "Send control failed (result %d)\n", result); goto requeue; } send_pages: if (type != NBD_CMD_WRITE) goto out; bio = req->bio; while (bio) { struct bio *next = bio->bi_next; struct bvec_iter iter; struct bio_vec bvec; bio_for_each_segment(bvec, bio, iter) { bool is_last = !next && bio_iter_last(bvec, iter); int flags = is_last ? 0 : MSG_MORE; dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n", req, bvec.bv_len); iov_iter_bvec(&from, ITER_SOURCE, &bvec, 1, bvec.bv_len); if (skip) { if (skip >= iov_iter_count(&from)) { skip -= iov_iter_count(&from); continue; } iov_iter_advance(&from, skip); skip = 0; } result = sock_xmit(nbd, index, 1, &from, flags, &sent); if (result < 0) { if (was_interrupted(result)) { /* We've already sent the header, we * have no choice but to set pending and * return BUSY. */ nsock->pending = req; nsock->sent = sent; set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), "Send data failed (result %d)\n", result); goto requeue; } /* * The completion might already have come in, * so break for the last one instead of letting * the iterator do it. This prevents use-after-free * of the bio. */ if (is_last) break; } bio = next; } out: trace_nbd_payload_sent(req, handle); nsock->pending = NULL; nsock->sent = 0; __set_bit(NBD_CMD_INFLIGHT, &cmd->flags); return BLK_STS_OK; requeue: /* retry on a different socket */ dev_err_ratelimited(disk_to_dev(nbd->disk), "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); nbd_requeue_cmd(cmd); return BLK_STS_OK; } static int nbd_read_reply(struct nbd_device *nbd, struct socket *sock, struct nbd_reply *reply) { struct kvec iov = {.iov_base = reply, .iov_len = sizeof(*reply)}; struct iov_iter to; int result; reply->magic = 0; iov_iter_kvec(&to, ITER_DEST, &iov, 1, sizeof(*reply)); result = __sock_xmit(nbd, sock, 0, &to, MSG_WAITALL, NULL); if (result < 0) { if (!nbd_disconnected(nbd->config)) dev_err(disk_to_dev(nbd->disk), "Receive control failed (result %d)\n", result); return result; } if (ntohl(reply->magic) != NBD_REPLY_MAGIC) { dev_err(disk_to_dev(nbd->disk), "Wrong magic (0x%lx)\n", (unsigned long)ntohl(reply->magic)); return -EPROTO; } return 0; } /* NULL returned = something went wrong, inform userspace */ static struct nbd_cmd *nbd_handle_reply(struct nbd_device *nbd, int index, struct nbd_reply *reply) { int result; struct nbd_cmd *cmd; struct request *req = NULL; u64 handle; u16 hwq; u32 tag; int ret = 0; handle = be64_to_cpu(reply->cookie); tag = nbd_handle_to_tag(handle); hwq = blk_mq_unique_tag_to_hwq(tag); if (hwq < nbd->tag_set.nr_hw_queues) req = blk_mq_tag_to_rq(nbd->tag_set.tags[hwq], blk_mq_unique_tag_to_tag(tag)); if (!req || !blk_mq_request_started(req)) { dev_err(disk_to_dev(nbd->disk), "Unexpected reply (%d) %p\n", tag, req); return ERR_PTR(-ENOENT); } trace_nbd_header_received(req, handle); cmd = blk_mq_rq_to_pdu(req); mutex_lock(&cmd->lock); if (!test_bit(NBD_CMD_INFLIGHT, &cmd->flags)) { dev_err(disk_to_dev(nbd->disk), "Suspicious reply %d (status %u flags %lu)", tag, cmd->status, cmd->flags); ret = -ENOENT; goto out; } if (cmd->index != index) { dev_err(disk_to_dev(nbd->disk), "Unexpected reply %d from different sock %d (expected %d)", tag, index, cmd->index); ret = -ENOENT; goto out; } if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) { dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n", req, cmd->cmd_cookie, nbd_handle_to_cookie(handle)); ret = -ENOENT; goto out; } if (cmd->status != BLK_STS_OK) { dev_err(disk_to_dev(nbd->disk), "Command already handled %p\n", req); ret = -ENOENT; goto out; } if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) { dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n", req); ret = -ENOENT; goto out; } if (ntohl(reply->error)) { dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n", ntohl(reply->error)); cmd->status = BLK_STS_IOERR; goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req); if (rq_data_dir(req) != WRITE) { struct req_iterator iter; struct bio_vec bvec; struct iov_iter to; rq_for_each_segment(bvec, req, iter) { iov_iter_bvec(&to, ITER_DEST, &bvec, 1, bvec.bv_len); result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); if (result < 0) { dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n", result); /* * If we've disconnected, we need to make sure we * complete this request, otherwise error out * and let the timeout stuff handle resubmitting * this request onto another connection. */ if (nbd_disconnected(nbd->config)) { cmd->status = BLK_STS_IOERR; goto out; } ret = -EIO; goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n", req, bvec.bv_len); } } out: trace_nbd_payload_received(req, handle); mutex_unlock(&cmd->lock); return ret ? ERR_PTR(ret) : cmd; } static void recv_work(struct work_struct *work) { struct recv_thread_args *args = container_of(work, struct recv_thread_args, work); struct nbd_device *nbd = args->nbd; struct nbd_config *config = nbd->config; struct request_queue *q = nbd->disk->queue; struct nbd_sock *nsock = args->nsock; struct nbd_cmd *cmd; struct request *rq; while (1) { struct nbd_reply reply; if (nbd_read_reply(nbd, nsock->sock, &reply)) break; /* * Grab .q_usage_counter so request pool won't go away, then no * request use-after-free is possible during nbd_handle_reply(). * If queue is frozen, there won't be any inflight requests, we * needn't to handle the incoming garbage message. */ if (!percpu_ref_tryget(&q->q_usage_counter)) { dev_err(disk_to_dev(nbd->disk), "%s: no io inflight\n", __func__); break; } cmd = nbd_handle_reply(nbd, args->index, &reply); if (IS_ERR(cmd)) { percpu_ref_put(&q->q_usage_counter); break; } rq = blk_mq_rq_from_pdu(cmd); if (likely(!blk_should_fake_timeout(rq->q))) { bool complete; mutex_lock(&cmd->lock); complete = __test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); mutex_unlock(&cmd->lock); if (complete) blk_mq_complete_request(rq); } percpu_ref_put(&q->q_usage_counter); } mutex_lock(&nsock->tx_lock); nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); nbd_config_put(nbd); atomic_dec(&config->recv_threads); wake_up(&config->recv_wq); kfree(args); } static bool nbd_clear_req(struct request *req, void *data) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); /* don't abort one completed request */ if (blk_mq_request_completed(req)) return true; mutex_lock(&cmd->lock); if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) { mutex_unlock(&cmd->lock); return true; } cmd->status = BLK_STS_IOERR; mutex_unlock(&cmd->lock); blk_mq_complete_request(req); return true; } static void nbd_clear_que(struct nbd_device *nbd) { blk_mq_quiesce_queue(nbd->disk->queue); blk_mq_tagset_busy_iter(&nbd->tag_set, nbd_clear_req, NULL); blk_mq_unquiesce_queue(nbd->disk->queue); dev_dbg(disk_to_dev(nbd->disk), "queue cleared\n"); } static int find_fallback(struct nbd_device *nbd, int index) { struct nbd_config *config = nbd->config; int new_index = -1; struct nbd_sock *nsock = config->socks[index]; int fallback = nsock->fallback_index; if (test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags)) return new_index; if (config->num_connections <= 1) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Dead connection, failed to find a fallback\n"); return new_index; } if (fallback >= 0 && fallback < config->num_connections && !config->socks[fallback]->dead) return fallback; if (nsock->fallback_index < 0 || nsock->fallback_index >= config->num_connections || config->socks[nsock->fallback_index]->dead) { int i; for (i = 0; i < config->num_connections; i++) { if (i == index) continue; if (!config->socks[i]->dead) { new_index = i; break; } } nsock->fallback_index = new_index; if (new_index < 0) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Dead connection, failed to find a fallback\n"); return new_index; } } new_index = nsock->fallback_index; return new_index; } static int wait_for_reconnect(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; if (!config->dead_conn_timeout) return 0; if (!wait_event_timeout(config->conn_wait, test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags) || atomic_read(&config->live_connections) > 0, config->dead_conn_timeout)) return 0; return !test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags); } static blk_status_t nbd_handle_cmd(struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); struct nbd_device *nbd = cmd->nbd; struct nbd_config *config; struct nbd_sock *nsock; blk_status_t ret; lockdep_assert_held(&cmd->lock); config = nbd_get_config_unlocked(nbd); if (!config) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Socks array is empty\n"); return BLK_STS_IOERR; } if (index >= config->num_connections) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Attempted send on invalid socket\n"); nbd_config_put(nbd); return BLK_STS_IOERR; } cmd->status = BLK_STS_OK; again: nsock = config->socks[index]; mutex_lock(&nsock->tx_lock); if (nsock->dead) { int old_index = index; index = find_fallback(nbd, index); mutex_unlock(&nsock->tx_lock); if (index < 0) { if (wait_for_reconnect(nbd)) { index = old_index; goto again; } /* All the sockets should already be down at this point, * we just want to make sure that DISCONNECTED is set so * any requests that come in that were queue'ed waiting * for the reconnect timer don't trigger the timer again * and instead just error out. */ sock_shutdown(nbd); nbd_config_put(nbd); return BLK_STS_IOERR; } goto again; } /* Handle the case that we have a pending request that was partially * transmitted that _has_ to be serviced first. We need to call requeue * here so that it gets put _after_ the request that is already on the * dispatch list. */ blk_mq_start_request(req); if (unlikely(nsock->pending && nsock->pending != req)) { nbd_requeue_cmd(cmd); ret = BLK_STS_OK; goto out; } ret = nbd_send_cmd(nbd, cmd, index); out: mutex_unlock(&nsock->tx_lock); nbd_config_put(nbd); return ret; } static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); blk_status_t ret; /* * Since we look at the bio's to send the request over the network we * need to make sure the completion work doesn't mark this request done * before we are done doing our send. This keeps us from dereferencing * freed data if we have particularly fast completions (ie we get the * completion before we exit sock_xmit on the last bvec) or in the case * that the server is misbehaving (or there was an error) before we're * done sending everything over the wire. */ mutex_lock(&cmd->lock); clear_bit(NBD_CMD_REQUEUED, &cmd->flags); /* We can be called directly from the user space process, which means we * could possibly have signals pending so our sendmsg will fail. In * this case we need to return that we are busy, otherwise error out as * appropriate. */ ret = nbd_handle_cmd(cmd, hctx->queue_num); mutex_unlock(&cmd->lock); return ret; } static struct socket *nbd_get_socket(struct nbd_device *nbd, unsigned long fd, int *err) { struct socket *sock; *err = 0; sock = sockfd_lookup(fd, err); if (!sock) return NULL; if (sock->ops->shutdown == sock_no_shutdown) { dev_err(disk_to_dev(nbd->disk), "Unsupported socket: shutdown callout must be supported.\n"); *err = -EINVAL; sockfd_put(sock); return NULL; } return sock; } static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, bool netlink) { struct nbd_config *config = nbd->config; struct socket *sock; struct nbd_sock **socks; struct nbd_sock *nsock; int err; /* Arg will be cast to int, check it to avoid overflow */ if (arg > INT_MAX) return -EINVAL; sock = nbd_get_socket(nbd, arg, &err); if (!sock) return err; /* * We need to make sure we don't get any errant requests while we're * reallocating the ->socks array. */ blk_mq_freeze_queue(nbd->disk->queue); if (!netlink && !nbd->task_setup && !test_bit(NBD_RT_BOUND, &config->runtime_flags)) nbd->task_setup = current; if (!netlink && (nbd->task_setup != current || test_bit(NBD_RT_BOUND, &config->runtime_flags))) { dev_err(disk_to_dev(nbd->disk), "Device being setup by another task"); err = -EBUSY; goto put_socket; } nsock = kzalloc(sizeof(*nsock), GFP_KERNEL); if (!nsock) { err = -ENOMEM; goto put_socket; } socks = krealloc(config->socks, (config->num_connections + 1) * sizeof(struct nbd_sock *), GFP_KERNEL); if (!socks) { kfree(nsock); err = -ENOMEM; goto put_socket; } config->socks = socks; nsock->fallback_index = -1; nsock->dead = false; mutex_init(&nsock->tx_lock); nsock->sock = sock; nsock->pending = NULL; nsock->sent = 0; nsock->cookie = 0; socks[config->num_connections++] = nsock; atomic_inc(&config->live_connections); blk_mq_unfreeze_queue(nbd->disk->queue); return 0; put_socket: blk_mq_unfreeze_queue(nbd->disk->queue); sockfd_put(sock); return err; } static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) { struct nbd_config *config = nbd->config; struct socket *sock, *old; struct recv_thread_args *args; int i; int err; sock = nbd_get_socket(nbd, arg, &err); if (!sock) return err; args = kzalloc(sizeof(*args), GFP_KERNEL); if (!args) { sockfd_put(sock); return -ENOMEM; } for (i = 0; i < config->num_connections; i++) { struct nbd_sock *nsock = config->socks[i]; if (!nsock->dead) continue; mutex_lock(&nsock->tx_lock); if (!nsock->dead) { mutex_unlock(&nsock->tx_lock); continue; } sk_set_memalloc(sock->sk); if (nbd->tag_set.timeout) sock->sk->sk_sndtimeo = nbd->tag_set.timeout; atomic_inc(&config->recv_threads); refcount_inc(&nbd->config_refs); old = nsock->sock; nsock->fallback_index = -1; nsock->sock = sock; nsock->dead = false; INIT_WORK(&args->work, recv_work); args->index = i; args->nbd = nbd; args->nsock = nsock; nsock->cookie++; mutex_unlock(&nsock->tx_lock); sockfd_put(old); clear_bit(NBD_RT_DISCONNECTED, &config->runtime_flags); /* We take the tx_mutex in an error path in the recv_work, so we * need to queue_work outside of the tx_mutex. */ queue_work(nbd->recv_workq, &args->work); atomic_inc(&config->live_connections); wake_up(&config->conn_wait); return 0; } sockfd_put(sock); kfree(args); return -ENOSPC; } static void nbd_bdev_reset(struct nbd_device *nbd) { if (disk_openers(nbd->disk) > 1) return; set_capacity(nbd->disk, 0); } static void nbd_parse_flags(struct nbd_device *nbd) { if (nbd->config->flags & NBD_FLAG_READ_ONLY) set_disk_ro(nbd->disk, true); else set_disk_ro(nbd->disk, false); } static void send_disconnects(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; struct nbd_request request = { .magic = htonl(NBD_REQUEST_MAGIC), .type = htonl(NBD_CMD_DISC), }; struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)}; struct iov_iter from; int i, ret; for (i = 0; i < config->num_connections; i++) { struct nbd_sock *nsock = config->socks[i]; iov_iter_kvec(&from, ITER_SOURCE, &iov, 1, sizeof(request)); mutex_lock(&nsock->tx_lock); ret = sock_xmit(nbd, i, 1, &from, 0, NULL); if (ret < 0) dev_err(disk_to_dev(nbd->disk), "Send disconnect failed %d\n", ret); mutex_unlock(&nsock->tx_lock); } } static int nbd_disconnect(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n"); set_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags); set_bit(NBD_DISCONNECT_REQUESTED, &nbd->flags); send_disconnects(nbd); return 0; } static void nbd_clear_sock(struct nbd_device *nbd) { sock_shutdown(nbd); nbd_clear_que(nbd); nbd->task_setup = NULL; } static void nbd_config_put(struct nbd_device *nbd) { if (refcount_dec_and_mutex_lock(&nbd->config_refs, &nbd->config_lock)) { struct nbd_config *config = nbd->config; nbd_dev_dbg_close(nbd); invalidate_disk(nbd->disk); if (nbd->config->bytesize) kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE); if (test_and_clear_bit(NBD_RT_HAS_PID_FILE, &config->runtime_flags)) device_remove_file(disk_to_dev(nbd->disk), &pid_attr); nbd->pid = 0; if (test_and_clear_bit(NBD_RT_HAS_BACKEND_FILE, &config->runtime_flags)) { device_remove_file(disk_to_dev(nbd->disk), &backend_attr); kfree(nbd->backend); nbd->backend = NULL; } nbd_clear_sock(nbd); if (config->num_connections) { int i; for (i = 0; i < config->num_connections; i++) { sockfd_put(config->socks[i]->sock); kfree(config->socks[i]); } kfree(config->socks); } kfree(nbd->config); nbd->config = NULL; nbd->tag_set.timeout = 0; mutex_unlock(&nbd->config_lock); nbd_put(nbd); module_put(THIS_MODULE); } } static int nbd_start_device(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; int num_connections = config->num_connections; int error = 0, i; if (nbd->pid) return -EBUSY; if (!config->socks) return -EINVAL; if (num_connections > 1 && !(config->flags & NBD_FLAG_CAN_MULTI_CONN)) { dev_err(disk_to_dev(nbd->disk), "server does not support multiple connections per device.\n"); return -EINVAL; } blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections); nbd->pid = task_pid_nr(current); nbd_parse_flags(nbd); error = device_create_file(disk_to_dev(nbd->disk), &pid_attr); if (error) { dev_err(disk_to_dev(nbd->disk), "device_create_file failed for pid!\n"); return error; } set_bit(NBD_RT_HAS_PID_FILE, &config->runtime_flags); nbd_dev_dbg_init(nbd); for (i = 0; i < num_connections; i++) { struct recv_thread_args *args; args = kzalloc(sizeof(*args), GFP_KERNEL); if (!args) { sock_shutdown(nbd); /* * If num_connections is m (2 < m), * and NO.1 ~ NO.n(1 < n < m) kzallocs are successful. * But NO.(n + 1) failed. We still have n recv threads. * So, add flush_workqueue here to prevent recv threads * dropping the last config_refs and trying to destroy * the workqueue from inside the workqueue. */ if (i) flush_workqueue(nbd->recv_workq); return -ENOMEM; } sk_set_memalloc(config->socks[i]->sock->sk); if (nbd->tag_set.timeout) config->socks[i]->sock->sk->sk_sndtimeo = nbd->tag_set.timeout; atomic_inc(&config->recv_threads); refcount_inc(&nbd->config_refs); INIT_WORK(&args->work, recv_work); args->nbd = nbd; args->nsock = config->socks[i]; args->index = i; queue_work(nbd->recv_workq, &args->work); } return nbd_set_size(nbd, config->bytesize, nbd_blksize(config)); } static int nbd_start_device_ioctl(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; int ret; ret = nbd_start_device(nbd); if (ret) return ret; if (max_part) set_bit(GD_NEED_PART_SCAN, &nbd->disk->state); mutex_unlock(&nbd->config_lock); ret = wait_event_interruptible(config->recv_wq, atomic_read(&config->recv_threads) == 0); if (ret) { sock_shutdown(nbd); nbd_clear_que(nbd); } flush_workqueue(nbd->recv_workq); mutex_lock(&nbd->config_lock); nbd_bdev_reset(nbd); /* user requested, ignore socket errors */ if (test_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags)) ret = 0; if (test_bit(NBD_RT_TIMEDOUT, &config->runtime_flags)) ret = -ETIMEDOUT; return ret; } static void nbd_clear_sock_ioctl(struct nbd_device *nbd) { nbd_clear_sock(nbd); disk_force_media_change(nbd->disk); nbd_bdev_reset(nbd); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); } static void nbd_set_cmd_timeout(struct nbd_device *nbd, u64 timeout) { nbd->tag_set.timeout = timeout * HZ; if (timeout) blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ); else blk_queue_rq_timeout(nbd->disk->queue, 30 * HZ); } /* Must be called with config_lock held */ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, unsigned int cmd, unsigned long arg) { struct nbd_config *config = nbd->config; loff_t bytesize; switch (cmd) { case NBD_DISCONNECT: return nbd_disconnect(nbd); case NBD_CLEAR_SOCK: nbd_clear_sock_ioctl(nbd); return 0; case NBD_SET_SOCK: return nbd_add_socket(nbd, arg, false); case NBD_SET_BLKSIZE: return nbd_set_size(nbd, config->bytesize, arg); case NBD_SET_SIZE: return nbd_set_size(nbd, arg, nbd_blksize(config)); case NBD_SET_SIZE_BLOCKS: if (check_shl_overflow(arg, config->blksize_bits, &bytesize)) return -EINVAL; return nbd_set_size(nbd, bytesize, nbd_blksize(config)); case NBD_SET_TIMEOUT: nbd_set_cmd_timeout(nbd, arg); return 0; case NBD_SET_FLAGS: config->flags = arg; return 0; case NBD_DO_IT: return nbd_start_device_ioctl(nbd); case NBD_CLEAR_QUE: /* * This is for compatibility only. The queue is always cleared * by NBD_DO_IT or NBD_CLEAR_SOCK. */ return 0; case NBD_PRINT_DEBUG: /* * For compatibility only, we no longer keep a list of * outstanding requests. */ return 0; } return -ENOTTY; } static int nbd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct nbd_device *nbd = bdev->bd_disk->private_data; struct nbd_config *config = nbd->config; int error = -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* The block layer will pass back some non-nbd ioctls in case we have * special handling for them, but we don't so just return an error. */ if (_IOC_TYPE(cmd) != 0xab) return -EINVAL; mutex_lock(&nbd->config_lock); /* Don't allow ioctl operations on a nbd device that was created with * netlink, unless it's DISCONNECT or CLEAR_SOCK, which are fine. */ if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) || (cmd == NBD_DISCONNECT || cmd == NBD_CLEAR_SOCK)) error = __nbd_ioctl(bdev, nbd, cmd, arg); else dev_err(nbd_to_dev(nbd), "Cannot use ioctl interface on a netlink controlled device.\n"); mutex_unlock(&nbd->config_lock); return error; } static int nbd_alloc_and_init_config(struct nbd_device *nbd) { struct nbd_config *config; if (WARN_ON(nbd->config)) return -EINVAL; if (!try_module_get(THIS_MODULE)) return -ENODEV; config = kzalloc(sizeof(struct nbd_config), GFP_NOFS); if (!config) { module_put(THIS_MODULE); return -ENOMEM; } atomic_set(&config->recv_threads, 0); init_waitqueue_head(&config->recv_wq); init_waitqueue_head(&config->conn_wait); config->blksize_bits = NBD_DEF_BLKSIZE_BITS; atomic_set(&config->live_connections, 0); nbd->config = config; /* * Order refcount_set(&nbd->config_refs, 1) and nbd->config assignment, * its pair is the barrier in nbd_get_config_unlocked(). * So nbd_get_config_unlocked() won't see nbd->config as null after * refcount_inc_not_zero() succeed. */ smp_mb__before_atomic(); refcount_set(&nbd->config_refs, 1); return 0; } static int nbd_open(struct gendisk *disk, blk_mode_t mode) { struct nbd_device *nbd; struct nbd_config *config; int ret = 0; mutex_lock(&nbd_index_mutex); nbd = disk->private_data; if (!nbd) { ret = -ENXIO; goto out; } if (!refcount_inc_not_zero(&nbd->refs)) { ret = -ENXIO; goto out; } config = nbd_get_config_unlocked(nbd); if (!config) { mutex_lock(&nbd->config_lock); if (refcount_inc_not_zero(&nbd->config_refs)) { mutex_unlock(&nbd->config_lock); goto out; } ret = nbd_alloc_and_init_config(nbd); if (ret) { mutex_unlock(&nbd->config_lock); goto out; } refcount_inc(&nbd->refs); mutex_unlock(&nbd->config_lock); if (max_part) set_bit(GD_NEED_PART_SCAN, &disk->state); } else if (nbd_disconnected(config)) { if (max_part) set_bit(GD_NEED_PART_SCAN, &disk->state); } out: mutex_unlock(&nbd_index_mutex); return ret; } static void nbd_release(struct gendisk *disk) { struct nbd_device *nbd = disk->private_data; if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && disk_openers(disk) == 0) nbd_disconnect_and_put(nbd); nbd_config_put(nbd); nbd_put(nbd); } static void nbd_free_disk(struct gendisk *disk) { struct nbd_device *nbd = disk->private_data; kfree(nbd); } static const struct block_device_operations nbd_fops = { .owner = THIS_MODULE, .open = nbd_open, .release = nbd_release, .ioctl = nbd_ioctl, .compat_ioctl = nbd_ioctl, .free_disk = nbd_free_disk, }; #if IS_ENABLED(CONFIG_DEBUG_FS) static int nbd_dbg_tasks_show(struct seq_file *s, void *unused) { struct nbd_device *nbd = s->private; if (nbd->pid) seq_printf(s, "recv: %d\n", nbd->pid); return 0; } DEFINE_SHOW_ATTRIBUTE(nbd_dbg_tasks); static int nbd_dbg_flags_show(struct seq_file *s, void *unused) { struct nbd_device *nbd = s->private; u32 flags = nbd->config->flags; seq_printf(s, "Hex: 0x%08x\n\n", flags); seq_puts(s, "Known flags:\n"); if (flags & NBD_FLAG_HAS_FLAGS) seq_puts(s, "NBD_FLAG_HAS_FLAGS\n"); if (flags & NBD_FLAG_READ_ONLY) seq_puts(s, "NBD_FLAG_READ_ONLY\n"); if (flags & NBD_FLAG_SEND_FLUSH) seq_puts(s, "NBD_FLAG_SEND_FLUSH\n"); if (flags & NBD_FLAG_SEND_FUA) seq_puts(s, "NBD_FLAG_SEND_FUA\n"); if (flags & NBD_FLAG_SEND_TRIM) seq_puts(s, "NBD_FLAG_SEND_TRIM\n"); if (flags & NBD_FLAG_SEND_WRITE_ZEROES) seq_puts(s, "NBD_FLAG_SEND_WRITE_ZEROES\n"); if (flags & NBD_FLAG_ROTATIONAL) seq_puts(s, "NBD_FLAG_ROTATIONAL\n"); return 0; } DEFINE_SHOW_ATTRIBUTE(nbd_dbg_flags); static int nbd_dev_dbg_init(struct nbd_device *nbd) { struct dentry *dir; struct nbd_config *config = nbd->config; if (!nbd_dbg_dir) return -EIO; dir = debugfs_create_dir(nbd_name(nbd), nbd_dbg_dir); if (IS_ERR(dir)) { dev_err(nbd_to_dev(nbd), "Failed to create debugfs dir for '%s'\n", nbd_name(nbd)); return -EIO; } config->dbg_dir = dir; debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_fops); debugfs_create_u64("size_bytes", 0444, dir, &config->bytesize); debugfs_create_u32("timeout", 0444, dir, &nbd->tag_set.timeout); debugfs_create_u32("blocksize_bits", 0444, dir, &config->blksize_bits); debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_fops); return 0; } static void nbd_dev_dbg_close(struct nbd_device *nbd) { debugfs_remove_recursive(nbd->config->dbg_dir); } static int nbd_dbg_init(void) { struct dentry *dbg_dir; dbg_dir = debugfs_create_dir("nbd", NULL); if (IS_ERR(dbg_dir)) return -EIO; nbd_dbg_dir = dbg_dir; return 0; } static void nbd_dbg_close(void) { debugfs_remove_recursive(nbd_dbg_dir); } #else /* IS_ENABLED(CONFIG_DEBUG_FS) */ static int nbd_dev_dbg_init(struct nbd_device *nbd) { return 0; } static void nbd_dev_dbg_close(struct nbd_device *nbd) { } static int nbd_dbg_init(void) { return 0; } static void nbd_dbg_close(void) { } #endif static int nbd_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, unsigned int numa_node) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq); cmd->nbd = set->driver_data; cmd->flags = 0; mutex_init(&cmd->lock); return 0; } static const struct blk_mq_ops nbd_mq_ops = { .queue_rq = nbd_queue_rq, .complete = nbd_complete_rq, .init_request = nbd_init_request, .timeout = nbd_xmit_timeout, }; static struct nbd_device *nbd_dev_add(int index, unsigned int refs) { struct queue_limits lim = { .max_hw_sectors = 65536, .io_opt = 256 << SECTOR_SHIFT, .max_segments = USHRT_MAX, .max_segment_size = UINT_MAX, }; struct nbd_device *nbd; struct gendisk *disk; int err = -ENOMEM; nbd = kzalloc(sizeof(struct nbd_device), GFP_KERNEL); if (!nbd) goto out; nbd->tag_set.ops = &nbd_mq_ops; nbd->tag_set.nr_hw_queues = 1; nbd->tag_set.queue_depth = 128; nbd->tag_set.numa_node = NUMA_NO_NODE; nbd->tag_set.cmd_size = sizeof(struct nbd_cmd); nbd->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING; nbd->tag_set.driver_data = nbd; INIT_WORK(&nbd->remove_work, nbd_dev_remove_work); nbd->backend = NULL; err = blk_mq_alloc_tag_set(&nbd->tag_set); if (err) goto out_free_nbd; mutex_lock(&nbd_index_mutex); if (index >= 0) { err = idr_alloc(&nbd_index_idr, nbd, index, index + 1, GFP_KERNEL); if (err == -ENOSPC) err = -EEXIST; } else { err = idr_alloc(&nbd_index_idr, nbd, 0, (MINORMASK >> part_shift) + 1, GFP_KERNEL); if (err >= 0) index = err; } nbd->index = index; mutex_unlock(&nbd_index_mutex); if (err < 0) goto out_free_tags; disk = blk_mq_alloc_disk(&nbd->tag_set, &lim, NULL); if (IS_ERR(disk)) { err = PTR_ERR(disk); goto out_free_idr; } nbd->disk = disk; nbd->recv_workq = alloc_workqueue("nbd%d-recv", WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 0, nbd->index); if (!nbd->recv_workq) { dev_err(disk_to_dev(nbd->disk), "Could not allocate knbd recv work queue.\n"); err = -ENOMEM; goto out_err_disk; } mutex_init(&nbd->config_lock); refcount_set(&nbd->config_refs, 0); /* * Start out with a zero references to keep other threads from using * this device until it is fully initialized. */ refcount_set(&nbd->refs, 0); INIT_LIST_HEAD(&nbd->list); disk->major = NBD_MAJOR; disk->first_minor = index << part_shift; disk->minors = 1 << part_shift; disk->fops = &nbd_fops; disk->private_data = nbd; sprintf(disk->disk_name, "nbd%d", index); err = add_disk(disk); if (err) goto out_free_work; /* * Now publish the device. */ refcount_set(&nbd->refs, refs); nbd_total_devices++; return nbd; out_free_work: destroy_workqueue(nbd->recv_workq); out_err_disk: put_disk(disk); out_free_idr: mutex_lock(&nbd_index_mutex); idr_remove(&nbd_index_idr, index); mutex_unlock(&nbd_index_mutex); out_free_tags: blk_mq_free_tag_set(&nbd->tag_set); out_free_nbd: kfree(nbd); out: return ERR_PTR(err); } static struct nbd_device *nbd_find_get_unused(void) { struct nbd_device *nbd; int id; lockdep_assert_held(&nbd_index_mutex); idr_for_each_entry(&nbd_index_idr, nbd, id) { if (refcount_read(&nbd->config_refs) || test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) continue; if (refcount_inc_not_zero(&nbd->refs)) return nbd; } return NULL; } /* Netlink interface. */ static const struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = { [NBD_ATTR_INDEX] = { .type = NLA_U32 }, [NBD_ATTR_SIZE_BYTES] = { .type = NLA_U64 }, [NBD_ATTR_BLOCK_SIZE_BYTES] = { .type = NLA_U64 }, [NBD_ATTR_TIMEOUT] = { .type = NLA_U64 }, [NBD_ATTR_SERVER_FLAGS] = { .type = NLA_U64 }, [NBD_ATTR_CLIENT_FLAGS] = { .type = NLA_U64 }, [NBD_ATTR_SOCKETS] = { .type = NLA_NESTED}, [NBD_ATTR_DEAD_CONN_TIMEOUT] = { .type = NLA_U64 }, [NBD_ATTR_DEVICE_LIST] = { .type = NLA_NESTED}, [NBD_ATTR_BACKEND_IDENTIFIER] = { .type = NLA_STRING}, }; static const struct nla_policy nbd_sock_policy[NBD_SOCK_MAX + 1] = { [NBD_SOCK_FD] = { .type = NLA_U32 }, }; /* We don't use this right now since we don't parse the incoming list, but we * still want it here so userspace knows what to expect. */ static const struct nla_policy __attribute__((unused)) nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = { [NBD_DEVICE_INDEX] = { .type = NLA_U32 }, [NBD_DEVICE_CONNECTED] = { .type = NLA_U8 }, }; static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd) { struct nbd_config *config = nbd->config; u64 bsize = nbd_blksize(config); u64 bytes = config->bytesize; if (info->attrs[NBD_ATTR_SIZE_BYTES]) bytes = nla_get_u64(info->attrs[NBD_ATTR_SIZE_BYTES]); if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) bsize = nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]); if (bytes != config->bytesize || bsize != nbd_blksize(config)) return nbd_set_size(nbd, bytes, bsize); return 0; } static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info) { struct nbd_device *nbd; struct nbd_config *config; int index = -1; int ret; bool put_dev = false; if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; if (info->attrs[NBD_ATTR_INDEX]) { index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]); /* * Too big first_minor can cause duplicate creation of * sysfs files/links, since index << part_shift might overflow, or * MKDEV() expect that the max bits of first_minor is 20. */ if (index < 0 || index > MINORMASK >> part_shift) { pr_err("illegal input index %d\n", index); return -EINVAL; } } if (GENL_REQ_ATTR_CHECK(info, NBD_ATTR_SOCKETS)) { pr_err("must specify at least one socket\n"); return -EINVAL; } if (GENL_REQ_ATTR_CHECK(info, NBD_ATTR_SIZE_BYTES)) { pr_err("must specify a size in bytes for the device\n"); return -EINVAL; } again: mutex_lock(&nbd_index_mutex); if (index == -1) { nbd = nbd_find_get_unused(); } else { nbd = idr_find(&nbd_index_idr, index); if (nbd) { if ((test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags) && test_bit(NBD_DISCONNECT_REQUESTED, &nbd->flags)) || !refcount_inc_not_zero(&nbd->refs)) { mutex_unlock(&nbd_index_mutex); pr_err("device at index %d is going down\n", index); return -EINVAL; } } } mutex_unlock(&nbd_index_mutex); if (!nbd) { nbd = nbd_dev_add(index, 2); if (IS_ERR(nbd)) { pr_err("failed to add new device\n"); return PTR_ERR(nbd); } } mutex_lock(&nbd->config_lock); if (refcount_read(&nbd->config_refs)) { mutex_unlock(&nbd->config_lock); nbd_put(nbd); if (index == -1) goto again; pr_err("nbd%d already in use\n", index); return -EBUSY; } ret = nbd_alloc_and_init_config(nbd); if (ret) { mutex_unlock(&nbd->config_lock); nbd_put(nbd); pr_err("couldn't allocate config\n"); return ret; } config = nbd->config; set_bit(NBD_RT_BOUND, &config->runtime_flags); ret = nbd_genl_size_set(info, nbd); if (ret) goto out; if (info->attrs[NBD_ATTR_TIMEOUT]) nbd_set_cmd_timeout(nbd, nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT])); if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) { config->dead_conn_timeout = nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]); config->dead_conn_timeout *= HZ; } if (info->attrs[NBD_ATTR_SERVER_FLAGS]) config->flags = nla_get_u64(info->attrs[NBD_ATTR_SERVER_FLAGS]); if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) { u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]); if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) { /* * We have 1 ref to keep the device around, and then 1 * ref for our current operation here, which will be * inherited by the config. If we already have * DESTROY_ON_DISCONNECT set then we know we don't have * that extra ref already held so we don't need the * put_dev. */ if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) put_dev = true; } else { if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) refcount_inc(&nbd->refs); } if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { set_bit(NBD_RT_DISCONNECT_ON_CLOSE, &config->runtime_flags); } } if (info->attrs[NBD_ATTR_SOCKETS]) { struct nlattr *attr; int rem, fd; nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS], rem) { struct nlattr *socks[NBD_SOCK_MAX+1]; if (nla_type(attr) != NBD_SOCK_ITEM) { pr_err("socks must be embedded in a SOCK_ITEM attr\n"); ret = -EINVAL; goto out; } ret = nla_parse_nested_deprecated(socks, NBD_SOCK_MAX, attr, nbd_sock_policy, info->extack); if (ret != 0) { pr_err("error processing sock list\n"); ret = -EINVAL; goto out; } if (!socks[NBD_SOCK_FD]) continue; fd = (int)nla_get_u32(socks[NBD_SOCK_FD]); ret = nbd_add_socket(nbd, fd, true); if (ret) goto out; } } ret = nbd_start_device(nbd); if (ret) goto out; if (info->attrs[NBD_ATTR_BACKEND_IDENTIFIER]) { nbd->backend = nla_strdup(info->attrs[NBD_ATTR_BACKEND_IDENTIFIER], GFP_KERNEL); if (!nbd->backend) { ret = -ENOMEM; goto out; } } ret = device_create_file(disk_to_dev(nbd->disk), &backend_attr); if (ret) { dev_err(disk_to_dev(nbd->disk), "device_create_file failed for backend!\n"); goto out; } set_bit(NBD_RT_HAS_BACKEND_FILE, &config->runtime_flags); out: mutex_unlock(&nbd->config_lock); if (!ret) { set_bit(NBD_RT_HAS_CONFIG_REF, &config->runtime_flags); refcount_inc(&nbd->config_refs); nbd_connect_reply(info, nbd->index); } nbd_config_put(nbd); if (put_dev) nbd_put(nbd); return ret; } static void nbd_disconnect_and_put(struct nbd_device *nbd) { mutex_lock(&nbd->config_lock); nbd_disconnect(nbd); sock_shutdown(nbd); wake_up(&nbd->config->conn_wait); /* * Make sure recv thread has finished, we can safely call nbd_clear_que() * to cancel the inflight I/Os. */ flush_workqueue(nbd->recv_workq); nbd_clear_que(nbd); nbd->task_setup = NULL; mutex_unlock(&nbd->config_lock); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); } static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info) { struct nbd_device *nbd; int index; if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; if (GENL_REQ_ATTR_CHECK(info, NBD_ATTR_INDEX)) { pr_err("must specify an index to disconnect\n"); return -EINVAL; } index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]); mutex_lock(&nbd_index_mutex); nbd = idr_find(&nbd_index_idr, index); if (!nbd) { mutex_unlock(&nbd_index_mutex); pr_err("couldn't find device at index %d\n", index); return -EINVAL; } if (!refcount_inc_not_zero(&nbd->refs)) { mutex_unlock(&nbd_index_mutex); pr_err("device at index %d is going down\n", index); return -EINVAL; } mutex_unlock(&nbd_index_mutex); if (!refcount_inc_not_zero(&nbd->config_refs)) goto put_nbd; nbd_disconnect_and_put(nbd); nbd_config_put(nbd); put_nbd: nbd_put(nbd); return 0; } static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) { struct nbd_device *nbd = NULL; struct nbd_config *config; int index; int ret = 0; bool put_dev = false; if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; if (GENL_REQ_ATTR_CHECK(info, NBD_ATTR_INDEX)) { pr_err("must specify a device to reconfigure\n"); return -EINVAL; } index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]); mutex_lock(&nbd_index_mutex); nbd = idr_find(&nbd_index_idr, index); if (!nbd) { mutex_unlock(&nbd_index_mutex); pr_err("couldn't find a device at index %d\n", index); return -EINVAL; } if (nbd->backend) { if (info->attrs[NBD_ATTR_BACKEND_IDENTIFIER]) { if (nla_strcmp(info->attrs[NBD_ATTR_BACKEND_IDENTIFIER], nbd->backend)) { mutex_unlock(&nbd_index_mutex); dev_err(nbd_to_dev(nbd), "backend image doesn't match with %s\n", nbd->backend); return -EINVAL; } } else { mutex_unlock(&nbd_index_mutex); dev_err(nbd_to_dev(nbd), "must specify backend\n"); return -EINVAL; } } if (!refcount_inc_not_zero(&nbd->refs)) { mutex_unlock(&nbd_index_mutex); pr_err("device at index %d is going down\n", index); return -EINVAL; } mutex_unlock(&nbd_index_mutex); config = nbd_get_config_unlocked(nbd); if (!config) { dev_err(nbd_to_dev(nbd), "not configured, cannot reconfigure\n"); nbd_put(nbd); return -EINVAL; } mutex_lock(&nbd->config_lock); if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) || !nbd->pid) { dev_err(nbd_to_dev(nbd), "not configured, cannot reconfigure\n"); ret = -EINVAL; goto out; } ret = nbd_genl_size_set(info, nbd); if (ret) goto out; if (info->attrs[NBD_ATTR_TIMEOUT]) nbd_set_cmd_timeout(nbd, nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT])); if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) { config->dead_conn_timeout = nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]); config->dead_conn_timeout *= HZ; } if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) { u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]); if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) { if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) put_dev = true; } else { if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) refcount_inc(&nbd->refs); } if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { set_bit(NBD_RT_DISCONNECT_ON_CLOSE, &config->runtime_flags); } else { clear_bit(NBD_RT_DISCONNECT_ON_CLOSE, &config->runtime_flags); } } if (info->attrs[NBD_ATTR_SOCKETS]) { struct nlattr *attr; int rem, fd; nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS], rem) { struct nlattr *socks[NBD_SOCK_MAX+1]; if (nla_type(attr) != NBD_SOCK_ITEM) { pr_err("socks must be embedded in a SOCK_ITEM attr\n"); ret = -EINVAL; goto out; } ret = nla_parse_nested_deprecated(socks, NBD_SOCK_MAX, attr, nbd_sock_policy, info->extack); if (ret != 0) { pr_err("error processing sock list\n"); ret = -EINVAL; goto out; } if (!socks[NBD_SOCK_FD]) continue; fd = (int)nla_get_u32(socks[NBD_SOCK_FD]); ret = nbd_reconnect_socket(nbd, fd); if (ret) { if (ret == -ENOSPC) ret = 0; goto out; } dev_info(nbd_to_dev(nbd), "reconnected socket\n"); } } out: mutex_unlock(&nbd->config_lock); nbd_config_put(nbd); nbd_put(nbd); if (put_dev) nbd_put(nbd); return ret; } static const struct genl_small_ops nbd_connect_genl_ops[] = { { .cmd = NBD_CMD_CONNECT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nbd_genl_connect, }, { .cmd = NBD_CMD_DISCONNECT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nbd_genl_disconnect, }, { .cmd = NBD_CMD_RECONFIGURE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nbd_genl_reconfigure, }, { .cmd = NBD_CMD_STATUS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nbd_genl_status, }, }; static const struct genl_multicast_group nbd_mcast_grps[] = { { .name = NBD_GENL_MCAST_GROUP_NAME, }, }; static struct genl_family nbd_genl_family __ro_after_init = { .hdrsize = 0, .name = NBD_GENL_FAMILY_NAME, .version = NBD_GENL_VERSION, .module = THIS_MODULE, .small_ops = nbd_connect_genl_ops, .n_small_ops = ARRAY_SIZE(nbd_connect_genl_ops), .resv_start_op = NBD_CMD_STATUS + 1, .maxattr = NBD_ATTR_MAX, .netnsok = 1, .policy = nbd_attr_policy, .mcgrps = nbd_mcast_grps, .n_mcgrps = ARRAY_SIZE(nbd_mcast_grps), }; MODULE_ALIAS_GENL_FAMILY(NBD_GENL_FAMILY_NAME); static int populate_nbd_status(struct nbd_device *nbd, struct sk_buff *reply) { struct nlattr *dev_opt; u8 connected = 0; int ret; /* This is a little racey, but for status it's ok. The * reason we don't take a ref here is because we can't * take a ref in the index == -1 case as we would need * to put under the nbd_index_mutex, which could * deadlock if we are configured to remove ourselves * once we're disconnected. */ if (refcount_read(&nbd->config_refs)) connected = 1; dev_opt = nla_nest_start_noflag(reply, NBD_DEVICE_ITEM); if (!dev_opt) return -EMSGSIZE; ret = nla_put_u32(reply, NBD_DEVICE_INDEX, nbd->index); if (ret) return -EMSGSIZE; ret = nla_put_u8(reply, NBD_DEVICE_CONNECTED, connected); if (ret) return -EMSGSIZE; nla_nest_end(reply, dev_opt); return 0; } static int status_cb(int id, void *ptr, void *data) { struct nbd_device *nbd = ptr; return populate_nbd_status(nbd, (struct sk_buff *)data); } static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info) { struct nlattr *dev_list; struct sk_buff *reply; void *reply_head; size_t msg_size; int index = -1; int ret = -ENOMEM; if (info->attrs[NBD_ATTR_INDEX]) index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]); mutex_lock(&nbd_index_mutex); msg_size = nla_total_size(nla_attr_size(sizeof(u32)) + nla_attr_size(sizeof(u8))); msg_size *= (index == -1) ? nbd_total_devices : 1; reply = genlmsg_new(msg_size, GFP_KERNEL); if (!reply) goto out; reply_head = genlmsg_put_reply(reply, info, &nbd_genl_family, 0, NBD_CMD_STATUS); if (!reply_head) { nlmsg_free(reply); goto out; } dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST); if (!dev_list) { nlmsg_free(reply); ret = -EMSGSIZE; goto out; } if (index == -1) { ret = idr_for_each(&nbd_index_idr, &status_cb, reply); if (ret) { nlmsg_free(reply); goto out; } } else { struct nbd_device *nbd; nbd = idr_find(&nbd_index_idr, index); if (nbd) { ret = populate_nbd_status(nbd, reply); if (ret) { nlmsg_free(reply); goto out; } } } nla_nest_end(reply, dev_list); genlmsg_end(reply, reply_head); ret = genlmsg_reply(reply, info); out: mutex_unlock(&nbd_index_mutex); return ret; } static void nbd_connect_reply(struct genl_info *info, int index) { struct sk_buff *skb; void *msg_head; int ret; skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL); if (!skb) return; msg_head = genlmsg_put_reply(skb, info, &nbd_genl_family, 0, NBD_CMD_CONNECT); if (!msg_head) { nlmsg_free(skb); return; } ret = nla_put_u32(skb, NBD_ATTR_INDEX, index); if (ret) { nlmsg_free(skb); return; } genlmsg_end(skb, msg_head); genlmsg_reply(skb, info); } static void nbd_mcast_index(int index) { struct sk_buff *skb; void *msg_head; int ret; skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL); if (!skb) return; msg_head = genlmsg_put(skb, 0, 0, &nbd_genl_family, 0, NBD_CMD_LINK_DEAD); if (!msg_head) { nlmsg_free(skb); return; } ret = nla_put_u32(skb, NBD_ATTR_INDEX, index); if (ret) { nlmsg_free(skb); return; } genlmsg_end(skb, msg_head); genlmsg_multicast(&nbd_genl_family, skb, 0, 0, GFP_KERNEL); } static void nbd_dead_link_work(struct work_struct *work) { struct link_dead_args *args = container_of(work, struct link_dead_args, work); nbd_mcast_index(args->index); kfree(args); } static int __init nbd_init(void) { int i; BUILD_BUG_ON(sizeof(struct nbd_request) != 28); if (max_part < 0) { pr_err("max_part must be >= 0\n"); return -EINVAL; } part_shift = 0; if (max_part > 0) { part_shift = fls(max_part); /* * Adjust max_part according to part_shift as it is exported * to user space so that user can know the max number of * partition kernel should be able to manage. * * Note that -1 is required because partition 0 is reserved * for the whole disk. */ max_part = (1UL << part_shift) - 1; } if ((1UL << part_shift) > DISK_MAX_PARTS) return -EINVAL; if (nbds_max > 1UL << (MINORBITS - part_shift)) return -EINVAL; if (register_blkdev(NBD_MAJOR, "nbd")) return -EIO; nbd_del_wq = alloc_workqueue("nbd-del", WQ_UNBOUND, 0); if (!nbd_del_wq) { unregister_blkdev(NBD_MAJOR, "nbd"); return -ENOMEM; } if (genl_register_family(&nbd_genl_family)) { destroy_workqueue(nbd_del_wq); unregister_blkdev(NBD_MAJOR, "nbd"); return -EINVAL; } nbd_dbg_init(); for (i = 0; i < nbds_max; i++) nbd_dev_add(i, 1); return 0; } static int nbd_exit_cb(int id, void *ptr, void *data) { struct list_head *list = (struct list_head *)data; struct nbd_device *nbd = ptr; /* Skip nbd that is being removed asynchronously */ if (refcount_read(&nbd->refs)) list_add_tail(&nbd->list, list); return 0; } static void __exit nbd_cleanup(void) { struct nbd_device *nbd; LIST_HEAD(del_list); /* * Unregister netlink interface prior to waiting * for the completion of netlink commands. */ genl_unregister_family(&nbd_genl_family); nbd_dbg_close(); mutex_lock(&nbd_index_mutex); idr_for_each(&nbd_index_idr, &nbd_exit_cb, &del_list); mutex_unlock(&nbd_index_mutex); while (!list_empty(&del_list)) { nbd = list_first_entry(&del_list, struct nbd_device, list); list_del_init(&nbd->list); if (refcount_read(&nbd->config_refs)) pr_err("possibly leaking nbd_config (ref %d)\n", refcount_read(&nbd->config_refs)); if (refcount_read(&nbd->refs) != 1) pr_err("possibly leaking a device\n"); nbd_put(nbd); } /* Also wait for nbd_dev_remove_work() completes */ destroy_workqueue(nbd_del_wq); idr_destroy(&nbd_index_idr); unregister_blkdev(NBD_MAJOR, "nbd"); } module_init(nbd_init); module_exit(nbd_cleanup); MODULE_DESCRIPTION("Network Block Device"); MODULE_LICENSE("GPL"); module_param(nbds_max, int, 0444); MODULE_PARM_DESC(nbds_max, "number of network block devices to initialize (default: 16)"); module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "number of partitions per device (default: 16)"); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Function to determine if a thread group is single threaded or not * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * - Derived from security/selinux/hooks.c */ #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/sched/mm.h> /* * Returns true if the task does not share ->mm with another thread/process. */ bool current_is_single_threaded(void) { struct task_struct *task = current; struct mm_struct *mm = task->mm; struct task_struct *p, *t; bool ret; if (atomic_read(&task->signal->live) != 1) return false; if (atomic_read(&mm->mm_users) == 1) return true; ret = false; rcu_read_lock(); for_each_process(p) { if (unlikely(p->flags & PF_KTHREAD)) continue; if (unlikely(p == task->group_leader)) continue; for_each_thread(p, t) { if (unlikely(t->mm == mm)) goto found; if (likely(t->mm)) break; /* * t->mm == NULL. Make sure next_thread/next_task * will see other CLONE_VM tasks which might be * forked before exiting. */ smp_rmb(); } } ret = true; found: rcu_read_unlock(); return ret; } |
| 56 56 56 55 55 55 55 55 56 56 68 69 67 70 68 22 21 22 19 20 20 22 9 9 9 99 98 95 98 96 95 77 54 22 2 2 2 2 95 5 93 95 92 94 7 94 63 49 95 4 1 94 4 92 95 93 97 1 3 117 109 94 111 5 5 113 116 31 31 21 20 19 30 20 5 4 19 19 19 19 18 12 19 19 19 18 18 19 7 19 19 18 19 1 19 12 18 19 19 19 100 99 8 92 91 101 37 36 22 22 106 95 92 94 16 89 14 94 4 91 91 90 52 54 58 59 55 27 2 37 57 21 22 21 17 19 18 1 94 8 6 6 37 5 3 3 2 31 30 32 33 35 334 333 27 332 171 176 46 39 46 46 22 46 26 25 1 1 25 16 12 8 9 9 24 26 46 8 7 3 2 1 4 4 28 46 15 15 52 96 8 4 4 4 20 20 20 20 20 20 20 20 20 20 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * PF_INET protocol family socket handler. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> * Alan Cox, <A.Cox@swansea.ac.uk> * * Changes (see also sock.c) * * piggy, * Karl Knutson : Socket protocol table * A.N.Kuznetsov : Socket death error in accept(). * John Richardson : Fix non blocking error in connect() * so sockets that fail to connect * don't return -EINPROGRESS. * Alan Cox : Asynchronous I/O support * Alan Cox : Keep correct socket pointer on sock * structures * when accept() ed * Alan Cox : Semantics of SO_LINGER aren't state * moved to close when you look carefully. * With this fixed and the accept bug fixed * some RPC stuff seems happier. * Niibe Yutaka : 4.4BSD style write async I/O * Alan Cox, * Tony Gale : Fixed reuse semantics. * Alan Cox : bind() shouldn't abort existing but dead * sockets. Stops FTP netin:.. I hope. * Alan Cox : bind() works correctly for RAW sockets. * Note that FreeBSD at least was broken * in this respect so be careful with * compatibility tests... * Alan Cox : routing cache support * Alan Cox : memzero the socket structure for * compactness. * Matt Day : nonblock connect error handler * Alan Cox : Allow large numbers of pending sockets * (eg for big web sites), but only if * specifically application requested. * Alan Cox : New buffering throughout IP. Used * dumbly. * Alan Cox : New buffering now used smartly. * Alan Cox : BSD rather than common sense * interpretation of listen. * Germano Caronni : Assorted small races. * Alan Cox : sendmsg/recvmsg basic support. * Alan Cox : Only sendmsg/recvmsg now supported. * Alan Cox : Locked down bind (see security list). * Alan Cox : Loosened bind a little. * Mike McLagan : ADD/DEL DLCI Ioctls * Willy Konynenberg : Transparent proxying support. * David S. Miller : New socket lookup architecture. * Some other random speedups. * Cyrus Durgin : Cleaned up file for kmod hacks. * Andi Kleen : Fix inet_stream_connect TCP race. */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/err.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/sched.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/inet.h> #include <linux/igmp.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <net/checksum.h> #include <net/ip.h> #include <net/protocol.h> #include <net/arp.h> #include <net/route.h> #include <net/ip_fib.h> #include <net/inet_connection_sock.h> #include <net/gro.h> #include <net/gso.h> #include <net/tcp.h> #include <net/udp.h> #include <net/udplite.h> #include <net/ping.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/raw.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/ip_tunnels.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/secure_seq.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #include <net/l3mdev.h> #include <net/compat.h> #include <net/rps.h> #include <trace/events/sock.h> /* The inetsw table contains everything that inet_create needs to * build a new socket. */ static struct list_head inetsw[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw_lock); /* New destruction routine */ void inet_sock_destruct(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_error_queue); sk_mem_reclaim_final(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) { pr_err("Attempt to release TCP socket in state %d %p\n", sk->sk_state, sk); return; } if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive inet socket %p\n", sk); return; } WARN_ON_ONCE(atomic_read(&sk->sk_rmem_alloc)); WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); WARN_ON_ONCE(sk->sk_wmem_queued); WARN_ON_ONCE(sk_forward_alloc_get(sk)); kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1)); } EXPORT_SYMBOL(inet_sock_destruct); /* * The routines beyond this point handle the behaviour of an AF_INET * socket object. Mostly it punts to the subprotocols of IP to do * the work. */ /* * Automatically bind an unbound socket. */ static int inet_autobind(struct sock *sk) { struct inet_sock *inet; /* We may need to bind the socket. */ lock_sock(sk); inet = inet_sk(sk); if (!inet->inet_num) { if (sk->sk_prot->get_port(sk, 0)) { release_sock(sk); return -EAGAIN; } inet->inet_sport = htons(inet->inet_num); } release_sock(sk); return 0; } int __inet_listen_sk(struct sock *sk, int backlog) { unsigned char old_state = sk->sk_state; int err, tcp_fastopen; if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN))) return -EINVAL; WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state * we can only allow the backlog to be adjusted. */ if (old_state != TCP_LISTEN) { /* Enable TFO w/o requiring TCP_FASTOPEN socket option. * Note that only TCP sockets (SOCK_STREAM) will reach here. * Also fastopen backlog may already been set via the option * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); tcp_fastopen_init_key_once(sock_net(sk)); } err = inet_csk_listen_start(sk); if (err) return err; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL); } return 0; } /* * Move a socket into listening state. */ int inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; int err = -EINVAL; lock_sock(sk); if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) goto out; err = __inet_listen_sk(sk, backlog); out: release_sock(sk); return err; } EXPORT_SYMBOL(inet_listen); /* * Create an inet socket. */ static int inet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct inet_protosw *answer; struct inet_sock *inet; struct proto *answer_prot; unsigned char answer_flags; int try_loading_module = 0; int err; if (protocol < 0 || protocol >= IPPROTO_MAX) return -EINVAL; sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */ lookup_protocol: err = -ESOCKTNOSUPPORT; rcu_read_lock(); list_for_each_entry_rcu(answer, &inetsw[sock->type], list) { err = 0; /* Check the non-wild match. */ if (protocol == answer->protocol) { if (protocol != IPPROTO_IP) break; } else { /* Check for the two wild cases. */ if (IPPROTO_IP == protocol) { protocol = answer->protocol; break; } if (IPPROTO_IP == answer->protocol) break; } err = -EPROTONOSUPPORT; } if (unlikely(err)) { if (try_loading_module < 2) { rcu_read_unlock(); /* * Be more specific, e.g. net-pf-2-proto-132-type-1 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM) */ if (++try_loading_module == 1) request_module("net-pf-%d-proto-%d-type-%d", PF_INET, protocol, sock->type); /* * Fall back to generic, e.g. net-pf-2-proto-132 * (net-pf-PF_INET-proto-IPPROTO_SCTP) */ else request_module("net-pf-%d-proto-%d", PF_INET, protocol); goto lookup_protocol; } else goto out_rcu_unlock; } err = -EPERM; if (sock->type == SOCK_RAW && !kern && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; answer_prot = answer->prot; answer_flags = answer->flags; rcu_read_unlock(); WARN_ON(!answer_prot->slab); err = -ENOMEM; sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern); if (!sk) goto out; err = 0; if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; if (INET_PROTOSW_ICSK & answer_flags) inet_init_csk_locks(sk); inet = inet_sk(sk); inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); inet_clear_bit(NODEFRAG, sk); if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet_set_bit(HDRINCL, sk); } if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; atomic_set(&inet->inet_id, 0); sock_init_data(sock, sk); sk->sk_destruct = inet_sock_destruct; sk->sk_protocol = protocol; sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; inet_set_bit(MC_LOOP, sk); inet->mc_ttl = 1; inet_set_bit(MC_ALL, sk); inet->mc_index = 0; inet->mc_list = NULL; inet->rcv_tos = 0; if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically * shares. */ inet->inet_sport = htons(inet->inet_num); /* Add to protocol hash chains. */ err = sk->sk_prot->hash(sk); if (err) { sk_common_release(sk); goto out; } } if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); if (err) { sk_common_release(sk); goto out; } } if (!kern) { err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); if (err) { sk_common_release(sk); goto out; } } out: return err; out_rcu_unlock: rcu_read_unlock(); goto out; } /* * The peer socket should always be NULL (or else). When we call this * function we are destroying the object and from then on nobody * should refer to it. */ int inet_release(struct socket *sock) { struct sock *sk = sock->sk; if (sk) { long timeout; if (!sk->sk_kern_sock) BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk); /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); /* If linger is set, we don't return until the close * is complete. Otherwise we return immediately. The * actually closing is done the same either way. * * If the close is due to the process exiting, we never * linger.. */ timeout = 0; if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING)) timeout = sk->sk_lingertime; sk->sk_prot->close(sk, timeout); sock->sk = NULL; } return 0; } EXPORT_SYMBOL(inet_release); int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) { u32 flags = BIND_WITH_LOCK; int err; /* If the socket has its own bind function then use it. (RAW) */ if (sk->sk_prot->bind) { return sk->sk_prot->bind(sk, uaddr, addr_len); } if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len, CGROUP_INET4_BIND, &flags); if (err) return err; return __inet_bind(sk, uaddr, addr_len, flags); } int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { return inet_bind_sk(sock->sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_bind); int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; u32 tb_id = RT_TABLE_LOCAL; int err; if (addr->sin_family != AF_INET) { /* Compatibility games : accept AF_UNSPEC (mapped to AF_INET) * only if s_addr is INADDR_ANY. */ err = -EAFNOSUPPORT; if (addr->sin_family != AF_UNSPEC || addr->sin_addr.s_addr != htonl(INADDR_ANY)) goto out; } tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); /* Not specified by any standard per-se, however it breaks too * many applications when removed. It is unfortunate since * allowing applications to make a non-local bind solves * several problems with systems using dynamic addressing. * (ie. your servers still start up even if your ISDN link * is temporarily down) */ err = -EADDRNOTAVAIL; if (!inet_addr_valid_or_nonlocal(net, inet, addr->sin_addr.s_addr, chk_addr_ret)) goto out; snum = ntohs(addr->sin_port); err = -EACCES; if (!(flags & BIND_NO_CAP_NET_BIND_SERVICE) && snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) goto out; /* We keep a pair of addresses. rcv_saddr is the one * used by hash lookups, and saddr is used for transmit. * * In the BSD API these are the same except where it * would be illegal to use them (multicast/broadcast) in * which case the sending device address is used. */ if (flags & BIND_WITH_LOCK) lock_sock(sk); /* Check these errors (active socket, double bind). */ err = -EINVAL; if (sk->sk_state != TCP_CLOSE || inet->inet_num) goto out_release_sock; inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ /* Make sure we are allowed to bind here. */ if (snum || !(inet_test_bit(BIND_ADDRESS_NO_PORT, sk) || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { err = sk->sk_prot->get_port(sk, snum); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; goto out_release_sock; } if (!(flags & BIND_FROM_BPF)) { err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; if (sk->sk_prot->put_port) sk->sk_prot->put_port(sk); goto out_release_sock; } } } if (inet->inet_rcv_saddr) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; inet->inet_sport = htons(inet->inet_num); inet->inet_daddr = 0; inet->inet_dport = 0; sk_dst_reset(sk); err = 0; out_release_sock: if (flags & BIND_WITH_LOCK) release_sock(sk); out: return err; } int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; const struct proto *prot; int err; if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); if (uaddr->sa_family == AF_UNSPEC) return prot->disconnect(sk, flags); if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) { err = prot->pre_connect(sk, uaddr, addr_len); if (err) return err; } if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk)) return -EAGAIN; return prot->connect(sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_dgram_connect); static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. * Connect() does not allow to get error notifications * without closing the socket. */ while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); if (signal_pending(current) || !timeo) break; } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; return timeo; } /* * Connect to a remote host. There is regrettably still a little * TCP 'magic' in here. */ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags, int is_sendmsg) { struct sock *sk = sock->sk; int err; long timeo; /* * uaddr can be NULL and addr_len can be 0 if: * sk is a TCP fastopen active socket and * TCP_FASTOPEN_CONNECT sockopt is set and * we already have a valid cookie for this socket. * In this case, user can call write() after connect(). * write() will invoke tcp_sendmsg_fastopen() which calls * __inet_stream_connect(). */ if (uaddr) { if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) { sk->sk_disconnects++; err = sk->sk_prot->disconnect(sk, flags); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; goto out; } } switch (sock->state) { default: err = -EINVAL; goto out; case SS_CONNECTED: err = -EISCONN; goto out; case SS_CONNECTING: if (inet_test_bit(DEFER_CONNECT, sk)) err = is_sendmsg ? -EINPROGRESS : -EISCONN; else err = -EALREADY; /* Fall out of switch with err, set for this state */ break; case SS_UNCONNECTED: err = -EISCONN; if (sk->sk_state != TCP_CLOSE) goto out; if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) { err = sk->sk_prot->pre_connect(sk, uaddr, addr_len); if (err) goto out; } err = sk->sk_prot->connect(sk, uaddr, addr_len); if (err < 0) goto out; sock->state = SS_CONNECTING; if (!err && inet_test_bit(DEFER_CONNECT, sk)) goto out; /* Just entered SS_CONNECTING state; the only * difference is that return value in non-blocking * case is EINPROGRESS, rather than EALREADY. */ err = -EINPROGRESS; break; } timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { int writebias = (sk->sk_protocol == IPPROTO_TCP) && tcp_sk(sk)->fastopen_req && tcp_sk(sk)->fastopen_req->data ? 1 : 0; int dis = sk->sk_disconnects; /* Error code is set above */ if (!timeo || !inet_wait_for_connect(sk, timeo, writebias)) goto out; err = sock_intr_errno(timeo); if (signal_pending(current)) goto out; if (dis != sk->sk_disconnects) { err = -EPIPE; goto out; } } /* Connection was closed by RST, timeout, ICMP error * or another process disconnected us. */ if (sk->sk_state == TCP_CLOSE) goto sock_error; /* sk->sk_err may be not zero now, if RECVERR was ordered by user * and error was received after socket entered established state. * Hence, it is handled normally after connect() return successfully. */ sock->state = SS_CONNECTED; err = 0; out: return err; sock_error: err = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; sk->sk_disconnects++; if (sk->sk_prot->disconnect(sk, flags)) sock->state = SS_DISCONNECTING; goto out; } EXPORT_SYMBOL(__inet_stream_connect); int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { int err; lock_sock(sock->sk); err = __inet_stream_connect(sock, uaddr, addr_len, flags, 0); release_sock(sock->sk); return err; } EXPORT_SYMBOL(inet_stream_connect); void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *newsk) { sock_rps_record_flow(newsk); WARN_ON(!((1 << newsk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_RECV | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_CLOSE))); if (test_bit(SOCK_SUPPORT_ZC, &sock->flags)) set_bit(SOCK_SUPPORT_ZC, &newsock->flags); sock_graft(newsk, newsock); newsock->state = SS_CONNECTED; } /* * Accept a pending connection. The TCP layer now gives BSD semantics. */ int inet_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct sock *sk1 = sock->sk, *sk2; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ arg->err = -EINVAL; sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, arg); if (!sk2) return arg->err; lock_sock(sk2); __inet_accept(sock, newsock, sk2); release_sock(sk2); return 0; } EXPORT_SYMBOL(inet_accept); /* * This does both peername and sockname. */ int inet_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr); int sin_addr_len = sizeof(*sin); sin->sin_family = AF_INET; lock_sock(sk); if (peer) { if (!inet->inet_dport || (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1)) { release_sock(sk); return -ENOTCONN; } sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET4_GETPEERNAME); } else { __be32 addr = inet->inet_rcv_saddr; if (!addr) addr = inet->inet_saddr; sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET4_GETSOCKNAME); } release_sock(sk); memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); return sin_addr_len; } EXPORT_SYMBOL(inet_getname); int inet_send_prepare(struct sock *sk) { sock_rps_record_flow(sk); /* We may need to bind the socket. */ if (data_race(!inet_sk(sk)->inet_num) && !sk->sk_prot->no_autobind && inet_autobind(sk)) return -EAGAIN; return 0; } EXPORT_SYMBOL_GPL(inet_send_prepare); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; if (unlikely(inet_send_prepare(sk))) return -EAGAIN; return INDIRECT_CALL_2(sk->sk_prot->sendmsg, tcp_sendmsg, udp_sendmsg, sk, msg, size); } EXPORT_SYMBOL(inet_sendmsg); void inet_splice_eof(struct socket *sock) { const struct proto *prot; struct sock *sk = sock->sk; if (unlikely(inet_send_prepare(sk))) return; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); if (prot->splice_eof) prot->splice_eof(sock); } EXPORT_SYMBOL_GPL(inet_splice_eof); INDIRECT_CALLABLE_DECLARE(int udp_recvmsg(struct sock *, struct msghdr *, size_t, int, int *)); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; int addr_len = 0; int err; if (likely(!(flags & MSG_ERRQUEUE))) sock_rps_record_flow(sk); err = INDIRECT_CALL_2(sk->sk_prot->recvmsg, tcp_recvmsg, udp_recvmsg, sk, msg, size, flags, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; return err; } EXPORT_SYMBOL(inet_recvmsg); int inet_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int err = 0; /* This should really check to make sure * the socket is a TCP socket. (WHY AC...) */ how++; /* maps 0->1 has the advantage of making bit 1 rcvs and 1->2 bit 2 snds. 2->3 */ if ((how & ~SHUTDOWN_MASK) || !how) /* MAXINT->0 */ return -EINVAL; lock_sock(sk); if (sock->state == SS_CONNECTING) { if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE)) sock->state = SS_DISCONNECTING; else sock->state = SS_CONNECTED; } switch (sk->sk_state) { case TCP_CLOSE: err = -ENOTCONN; /* Hack to wake up other listeners, who can poll for EPOLLHUP, even on eg. unconnected UDP sockets -- RR */ fallthrough; default: WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how); if (sk->sk_prot->shutdown) sk->sk_prot->shutdown(sk, how); break; /* Remaining two branches are temporary solution for missing * close() in multithreaded environment. It is _not_ a good idea, * but we have no choice until close() is repaired at VFS level. */ case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; fallthrough; case TCP_SYN_SENT: err = sk->sk_prot->disconnect(sk, O_NONBLOCK); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; break; } /* Wake up anyone sleeping in poll. */ sk->sk_state_change(sk); release_sock(sk); return err; } EXPORT_SYMBOL(inet_shutdown); /* * ioctl() calls you can issue on an INET socket. Most of these are * device configuration and stuff and very rarely used. Some ioctls * pass on to the socket itself. * * NOTE: I like the idea of a module for the config stuff. ie ifconfig * loads the devconfigure module does its configuring and unloads it. * There's a good 20K of config code hanging around the kernel. */ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; int err = 0; struct net *net = sock_net(sk); void __user *p = (void __user *)arg; struct ifreq ifr; struct rtentry rt; switch (cmd) { case SIOCADDRT: case SIOCDELRT: if (copy_from_user(&rt, p, sizeof(struct rtentry))) return -EFAULT; err = ip_rt_ioctl(net, cmd, &rt); break; case SIOCRTMSG: err = -EINVAL; break; case SIOCDARP: case SIOCGARP: case SIOCSARP: err = arp_ioctl(net, cmd, (void __user *)arg); break; case SIOCGIFADDR: case SIOCGIFBRDADDR: case SIOCGIFNETMASK: case SIOCGIFDSTADDR: case SIOCGIFPFLAGS: if (get_user_ifreq(&ifr, NULL, p)) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); if (!err && put_user_ifreq(&ifr, p)) err = -EFAULT; break; case SIOCSIFADDR: case SIOCSIFBRDADDR: case SIOCSIFNETMASK: case SIOCSIFDSTADDR: case SIOCSIFPFLAGS: case SIOCSIFFLAGS: if (get_user_ifreq(&ifr, NULL, p)) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); break; default: if (sk->sk_prot->ioctl) err = sk_ioctl(sk, cmd, (void __user *)arg); else err = -ENOIOCTLCMD; break; } return err; } EXPORT_SYMBOL(inet_ioctl); #ifdef CONFIG_COMPAT static int inet_compat_routing_ioctl(struct sock *sk, unsigned int cmd, struct compat_rtentry __user *ur) { compat_uptr_t rtdev; struct rtentry rt; if (copy_from_user(&rt.rt_dst, &ur->rt_dst, 3 * sizeof(struct sockaddr)) || get_user(rt.rt_flags, &ur->rt_flags) || get_user(rt.rt_metric, &ur->rt_metric) || get_user(rt.rt_mtu, &ur->rt_mtu) || get_user(rt.rt_window, &ur->rt_window) || get_user(rt.rt_irtt, &ur->rt_irtt) || get_user(rtdev, &ur->rt_dev)) return -EFAULT; rt.rt_dev = compat_ptr(rtdev); return ip_rt_ioctl(sock_net(sk), cmd, &rt); } static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; switch (cmd) { case SIOCADDRT: case SIOCDELRT: return inet_compat_routing_ioctl(sk, cmd, argp); default: if (!sk->sk_prot->compat_ioctl) return -ENOIOCTLCMD; return sk->sk_prot->compat_ioctl(sk, cmd, arg); } } #endif /* CONFIG_COMPAT */ const struct proto_ops inet_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = inet_getname, .poll = tcp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = inet_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, #ifdef CONFIG_MMU .mmap = tcp_mmap, #endif .splice_eof = inet_splice_eof, .splice_read = tcp_splice_read, .set_peek_off = sk_set_peek_off, .read_sock = tcp_read_sock, .read_skb = tcp_read_skb, .sendmsg_locked = tcp_sendmsg_locked, .peek_len = tcp_peek_len, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif .set_rcvlowat = tcp_set_rcvlowat, }; EXPORT_SYMBOL(inet_stream_ops); const struct proto_ops inet_dgram_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = inet_getname, .poll = udp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .read_skb = udp_read_skb, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .splice_eof = inet_splice_eof, .set_peek_off = udp_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif }; EXPORT_SYMBOL(inet_dgram_ops); /* * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without * udp_poll */ static const struct proto_ops inet_sockraw_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = inet_getname, .poll = datagram_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .splice_eof = inet_splice_eof, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif }; static const struct net_proto_family inet_family_ops = { .family = PF_INET, .create = inet_create, .owner = THIS_MODULE, }; /* Upon startup we insert all the elements in inetsw_array[] into * the linked list inetsw. */ static struct inet_protosw inetsw_array[] = { { .type = SOCK_STREAM, .protocol = IPPROTO_TCP, .prot = &tcp_prot, .ops = &inet_stream_ops, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }, { .type = SOCK_DGRAM, .protocol = IPPROTO_UDP, .prot = &udp_prot, .ops = &inet_dgram_ops, .flags = INET_PROTOSW_PERMANENT, }, { .type = SOCK_DGRAM, .protocol = IPPROTO_ICMP, .prot = &ping_prot, .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, }, { .type = SOCK_RAW, .protocol = IPPROTO_IP, /* wild card */ .prot = &raw_prot, .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, } }; #define INETSW_ARRAY_LEN ARRAY_SIZE(inetsw_array) void inet_register_protosw(struct inet_protosw *p) { struct list_head *lh; struct inet_protosw *answer; int protocol = p->protocol; struct list_head *last_perm; spin_lock_bh(&inetsw_lock); if (p->type >= SOCK_MAX) goto out_illegal; /* If we are trying to override a permanent protocol, bail. */ last_perm = &inetsw[p->type]; list_for_each(lh, &inetsw[p->type]) { answer = list_entry(lh, struct inet_protosw, list); /* Check only the non-wild match. */ if ((INET_PROTOSW_PERMANENT & answer->flags) == 0) break; if (protocol == answer->protocol) goto out_permanent; last_perm = lh; } /* Add the new entry after the last permanent entry if any, so that * the new entry does not override a permanent entry when matched with * a wild-card protocol. But it is allowed to override any existing * non-permanent entry. This means that when we remove this entry, the * system automatically returns to the old behavior. */ list_add_rcu(&p->list, last_perm); out: spin_unlock_bh(&inetsw_lock); return; out_permanent: pr_err("Attempt to override permanent protocol %d\n", protocol); goto out; out_illegal: pr_err("Ignoring attempt to register invalid socket type %d\n", p->type); goto out; } EXPORT_SYMBOL(inet_register_protosw); void inet_unregister_protosw(struct inet_protosw *p) { if (INET_PROTOSW_PERMANENT & p->flags) { pr_err("Attempt to unregister permanent protocol %d\n", p->protocol); } else { spin_lock_bh(&inetsw_lock); list_del_rcu(&p->list); spin_unlock_bh(&inetsw_lock); synchronize_net(); } } EXPORT_SYMBOL(inet_unregister_protosw); static int inet_sk_reselect_saddr(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); __be32 old_saddr = inet->inet_saddr; __be32 daddr = inet->inet_daddr; struct flowi4 *fl4; struct rtable *rt; __be32 new_saddr; struct ip_options_rcu *inet_opt; int err; inet_opt = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* Query new route. */ fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, daddr, 0, sk->sk_bound_dev_if, sk->sk_protocol, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) return PTR_ERR(rt); new_saddr = fl4->saddr; if (new_saddr == old_saddr) { sk_setup_caps(sk, &rt->dst); return 0; } err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET); if (err) { ip_rt_put(rt); return err; } sk_setup_caps(sk, &rt->dst); if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) { pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n", __func__, &old_saddr, &new_saddr); } /* * XXX The only one ugly spot where we need to * XXX really change the sockets identity after * XXX it has entered the hashes. -DaveM * * Besides that, it does not check for connection * uniqueness. Wait for troubles. */ return __sk_prot_rehash(sk); } int inet_sk_rebuild_header(struct sock *sk) { struct rtable *rt = dst_rtable(__sk_dst_check(sk, 0)); struct inet_sock *inet = inet_sk(sk); __be32 daddr; struct ip_options_rcu *inet_opt; struct flowi4 *fl4; int err; /* Route is OK, nothing to do. */ if (rt) return 0; /* Reroute. */ rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); daddr = inet->inet_daddr; if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; rcu_read_unlock(); fl4 = &inet->cork.fl.u.ip4; rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (!IS_ERR(rt)) { err = 0; sk_setup_caps(sk, &rt->dst); } else { err = PTR_ERR(rt); /* Routing failed... */ sk->sk_route_caps = 0; /* * Other protocols have to map its equivalent state to TCP_SYN_SENT. * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme */ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) || sk->sk_state != TCP_SYN_SENT || (sk->sk_userlocks & SOCK_BINDADDR_LOCK) || (err = inet_sk_reselect_saddr(sk)) != 0) WRITE_ONCE(sk->sk_err_soft, -err); } return err; } EXPORT_SYMBOL(inet_sk_rebuild_header); void inet_sk_set_state(struct sock *sk, int state) { trace_inet_sock_set_state(sk, sk->sk_state, state); sk->sk_state = state; } EXPORT_SYMBOL(inet_sk_set_state); void inet_sk_state_store(struct sock *sk, int newstate) { trace_inet_sock_set_state(sk, sk->sk_state, newstate); smp_store_release(&sk->sk_state, newstate); } struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { bool udpfrag = false, fixedid = false, gso_partial, encap; struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; unsigned int offset = 0; struct iphdr *iph; int proto, tot_len; int nhoff; int ihl; int id; skb_reset_network_header(skb); nhoff = skb_network_header(skb) - skb_mac_header(skb); if (unlikely(!pskb_may_pull(skb, sizeof(*iph)))) goto out; iph = ip_hdr(skb); ihl = iph->ihl * 4; if (ihl < sizeof(*iph)) goto out; id = ntohs(iph->id); proto = iph->protocol; /* Warning: after this point, iph might be no longer valid */ if (unlikely(!pskb_may_pull(skb, ihl))) goto out; __skb_pull(skb, ihl); encap = SKB_GSO_CB(skb)->encap_level > 0; if (encap) features &= skb->dev->hw_enc_features; SKB_GSO_CB(skb)->encap_level += ihl; skb_reset_transport_header(skb); segs = ERR_PTR(-EPROTONOSUPPORT); if (!skb->encapsulation || encap) { udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP); fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID); /* fixed ID is invalid if DF bit is not set */ if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF))) goto out; } ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { segs = ops->callbacks.gso_segment(skb, features); if (!segs) skb->network_header = skb_mac_header(skb) + nhoff - skb->head; } if (IS_ERR_OR_NULL(segs)) goto out; gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); skb = segs; do { iph = (struct iphdr *)(skb_mac_header(skb) + nhoff); if (udpfrag) { iph->frag_off = htons(offset >> 3); if (skb->next) iph->frag_off |= htons(IP_MF); offset += skb->len - nhoff - ihl; tot_len = skb->len - nhoff; } else if (skb_is_gso(skb)) { if (!fixedid) { iph->id = htons(id); id += skb_shinfo(skb)->gso_segs; } if (gso_partial) tot_len = skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)iph; else tot_len = skb->len - nhoff; } else { if (!fixedid) iph->id = htons(id++); tot_len = skb->len - nhoff; } iph->tot_len = htons(tot_len); ip_send_check(iph); if (encap) skb_reset_inner_headers(skb); skb->network_header = (u8 *)iph - skb->head; skb_reset_mac_len(skb); } while ((skb = skb->next)); out: return segs; } static struct sk_buff *ipip_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP4)) return ERR_PTR(-EINVAL); return inet_gso_segment(skb, features); } struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct net_offload *ops; struct sk_buff *pp = NULL; const struct iphdr *iph; struct sk_buff *p; unsigned int hlen; unsigned int off; int flush = 1; int proto; off = skb_gro_offset(skb); hlen = off + sizeof(*iph); iph = skb_gro_header(skb, hlen, off); if (unlikely(!iph)) goto out; proto = iph->protocol; ops = rcu_dereference(inet_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) goto out; if (*(u8 *)iph != 0x45) goto out; if (ip_is_fragment(iph)) goto out; if (unlikely(ip_fast_csum((u8 *)iph, 5))) goto out; NAPI_GRO_CB(skb)->proto = proto; flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (ntohl(*(__be32 *)&iph->id) & ~IP_DF)); list_for_each_entry(p, head, list) { struct iphdr *iph2; if (!NAPI_GRO_CB(p)->same_flow) continue; iph2 = (struct iphdr *)(p->data + off); /* The above works because, with the exception of the top * (inner most) layer, we only aggregate pkts with the same * hdr length so all the hdrs we'll need to verify will start * at the same offset. */ if ((iph->protocol ^ iph2->protocol) | ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) | ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } NAPI_GRO_CB(skb)->flush |= flush; NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off; /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 */ skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); pp = indirect_call_gro_receive(tcp4_gro_receive, udp4_gro_receive, ops->callbacks.gro_receive, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } static struct sk_buff *ipip_gro_receive(struct list_head *head, struct sk_buff *skb) { if (NAPI_GRO_CB(skb)->encap_mark) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } NAPI_GRO_CB(skb)->encap_mark = 1; return inet_gro_receive(head, skb); } #define SECONDS_PER_DAY 86400 /* inet_current_timestamp - Return IP network timestamp * * Return milliseconds since midnight in network byte order. */ __be32 inet_current_timestamp(void) { u32 secs; u32 msecs; struct timespec64 ts; ktime_get_real_ts64(&ts); /* Get secs since midnight. */ (void)div_u64_rem(ts.tv_sec, SECONDS_PER_DAY, &secs); /* Convert to msecs. */ msecs = secs * MSEC_PER_SEC; /* Convert nsec to msec. */ msecs += (u32)ts.tv_nsec / NSEC_PER_MSEC; /* Convert to network byte order. */ return htonl(msecs); } EXPORT_SYMBOL(inet_current_timestamp); int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { unsigned int family = READ_ONCE(sk->sk_family); if (family == AF_INET) return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6) return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len); #endif return -EINVAL; } EXPORT_SYMBOL(inet_recv_error); int inet_gro_complete(struct sk_buff *skb, int nhoff) { struct iphdr *iph = (struct iphdr *)(skb->data + nhoff); const struct net_offload *ops; __be16 totlen = iph->tot_len; int proto = iph->protocol; int err = -ENOSYS; if (skb->encapsulation) { skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP)); skb_set_inner_network_header(skb, nhoff); } iph_set_totlen(iph, skb->len - nhoff); csum_replace2(&iph->check, totlen, iph->tot_len); ops = rcu_dereference(inet_offloads[proto]); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out; /* Only need to add sizeof(*iph) to get to the next hdr below * because any hdr with option will have been flushed in * inet_gro_receive(). */ err = INDIRECT_CALL_2(ops->callbacks.gro_complete, tcp4_gro_complete, udp4_gro_complete, skb, nhoff + sizeof(*iph)); out: return err; } static int ipip_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4; return inet_gro_complete(skb, nhoff); } int inet_ctl_sock_create(struct sock **sk, unsigned short family, unsigned short type, unsigned char protocol, struct net *net) { struct socket *sock; int rc = sock_create_kern(net, family, type, protocol, &sock); if (rc == 0) { *sk = sock->sk; (*sk)->sk_allocation = GFP_ATOMIC; (*sk)->sk_use_task_frag = false; /* * Unhash it so that IP input processing does not even see it, * we do not wish this socket to see incoming packets. */ (*sk)->sk_prot->unhash(*sk); } return rc; } EXPORT_SYMBOL_GPL(inet_ctl_sock_create); unsigned long snmp_fold_field(void __percpu *mib, int offt) { unsigned long res = 0; int i; for_each_possible_cpu(i) res += snmp_get_cpu_field(mib, i, offt); return res; } EXPORT_SYMBOL_GPL(snmp_fold_field); #if BITS_PER_LONG==32 u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offt, size_t syncp_offset) { void *bhptr; struct u64_stats_sync *syncp; u64 v; unsigned int start; bhptr = per_cpu_ptr(mib, cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { start = u64_stats_fetch_begin(syncp); v = *(((u64 *)bhptr) + offt); } while (u64_stats_fetch_retry(syncp, start)); return v; } EXPORT_SYMBOL_GPL(snmp_get_cpu_field64); u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_offset) { u64 res = 0; int cpu; for_each_possible_cpu(cpu) { res += snmp_get_cpu_field64(mib, cpu, offt, syncp_offset); } return res; } EXPORT_SYMBOL_GPL(snmp_fold_field64); #endif #ifdef CONFIG_IP_MULTICAST static const struct net_protocol igmp_protocol = { .handler = igmp_rcv, }; #endif static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = icmp_err, .no_policy = 1, }; static __net_init int ipv4_mib_init_net(struct net *net) { int i; net->mib.tcp_statistics = alloc_percpu(struct tcp_mib); if (!net->mib.tcp_statistics) goto err_tcp_mib; net->mib.ip_statistics = alloc_percpu(struct ipstats_mib); if (!net->mib.ip_statistics) goto err_ip_mib; for_each_possible_cpu(i) { struct ipstats_mib *af_inet_stats; af_inet_stats = per_cpu_ptr(net->mib.ip_statistics, i); u64_stats_init(&af_inet_stats->syncp); } net->mib.net_statistics = alloc_percpu(struct linux_mib); if (!net->mib.net_statistics) goto err_net_mib; net->mib.udp_statistics = alloc_percpu(struct udp_mib); if (!net->mib.udp_statistics) goto err_udp_mib; net->mib.udplite_statistics = alloc_percpu(struct udp_mib); if (!net->mib.udplite_statistics) goto err_udplite_mib; net->mib.icmp_statistics = alloc_percpu(struct icmp_mib); if (!net->mib.icmp_statistics) goto err_icmp_mib; net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib), GFP_KERNEL); if (!net->mib.icmpmsg_statistics) goto err_icmpmsg_mib; tcp_mib_init(net); return 0; err_icmpmsg_mib: free_percpu(net->mib.icmp_statistics); err_icmp_mib: free_percpu(net->mib.udplite_statistics); err_udplite_mib: free_percpu(net->mib.udp_statistics); err_udp_mib: free_percpu(net->mib.net_statistics); err_net_mib: free_percpu(net->mib.ip_statistics); err_ip_mib: free_percpu(net->mib.tcp_statistics); err_tcp_mib: return -ENOMEM; } static __net_exit void ipv4_mib_exit_net(struct net *net) { kfree(net->mib.icmpmsg_statistics); free_percpu(net->mib.icmp_statistics); free_percpu(net->mib.udplite_statistics); free_percpu(net->mib.udp_statistics); free_percpu(net->mib.net_statistics); free_percpu(net->mib.ip_statistics); free_percpu(net->mib.tcp_statistics); #ifdef CONFIG_MPTCP /* allocated on demand, see mptcp_init_sock() */ free_percpu(net->mib.mptcp_statistics); #endif } static __net_initdata struct pernet_operations ipv4_mib_ops = { .init = ipv4_mib_init_net, .exit = ipv4_mib_exit_net, }; static int __init init_ipv4_mibs(void) { return register_pernet_subsys(&ipv4_mib_ops); } static __net_init int inet_init_net(struct net *net) { /* * Set defaults for local port range */ net->ipv4.ip_local_ports.range = 60999u << 16 | 32768u; seqlock_init(&net->ipv4.ping_group_range.lock); /* * Sane defaults - nobody may create ping sockets. * Boot scripts should set this to distro-specific group. */ net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1); net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0); /* Default values for sysctl-controlled parameters. * We set them here, in case sysctl is not compiled. */ net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; net->ipv4.sysctl_ip_fwd_update_priority = 1; net->ipv4.sysctl_ip_dynaddr = 0; net->ipv4.sysctl_ip_early_demux = 1; net->ipv4.sysctl_udp_early_demux = 1; net->ipv4.sysctl_tcp_early_demux = 1; net->ipv4.sysctl_nexthop_compat_mode = 1; #ifdef CONFIG_SYSCTL net->ipv4.sysctl_ip_prot_sock = PROT_SOCK; #endif /* Some igmp sysctl, whose values are always used */ net->ipv4.sysctl_igmp_max_memberships = 20; net->ipv4.sysctl_igmp_max_msf = 10; /* IGMP reports for link-local multicast groups are enabled by default */ net->ipv4.sysctl_igmp_llm_reports = 1; net->ipv4.sysctl_igmp_qrv = 2; net->ipv4.sysctl_fib_notify_on_flag_change = 0; return 0; } static __net_initdata struct pernet_operations af_inet_ops = { .init = inet_init_net, }; static int __init init_inet_pernet_ops(void) { return register_pernet_subsys(&af_inet_ops); } static int ipv4_proc_init(void); /* * IP protocol layer initialiser */ static const struct net_offload ipip_offload = { .callbacks = { .gso_segment = ipip_gso_segment, .gro_receive = ipip_gro_receive, .gro_complete = ipip_gro_complete, }, }; static int __init ipip_offload_init(void) { return inet_add_offload(&ipip_offload, IPPROTO_IPIP); } static int __init ipv4_offload_init(void) { /* * Add offloads */ if (udpv4_offload_init() < 0) pr_crit("%s: Cannot add UDP protocol offload\n", __func__); if (tcpv4_offload_init() < 0) pr_crit("%s: Cannot add TCP protocol offload\n", __func__); if (ipip_offload_init() < 0) pr_crit("%s: Cannot add IPIP protocol offload\n", __func__); net_hotdata.ip_packet_offload = (struct packet_offload) { .type = cpu_to_be16(ETH_P_IP), .callbacks = { .gso_segment = inet_gso_segment, .gro_receive = inet_gro_receive, .gro_complete = inet_gro_complete, }, }; dev_add_offload(&net_hotdata.ip_packet_offload); return 0; } fs_initcall(ipv4_offload_init); static struct packet_type ip_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .func = ip_rcv, .list_func = ip_list_rcv, }; static int __init inet_init(void) { struct inet_protosw *q; struct list_head *r; int rc; sock_skb_cb_check_size(sizeof(struct inet_skb_parm)); raw_hashinfo_init(&raw_v4_hashinfo); rc = proto_register(&tcp_prot, 1); if (rc) goto out; rc = proto_register(&udp_prot, 1); if (rc) goto out_unregister_tcp_proto; rc = proto_register(&raw_prot, 1); if (rc) goto out_unregister_udp_proto; rc = proto_register(&ping_prot, 1); if (rc) goto out_unregister_raw_proto; /* * Tell SOCKET that we are alive... */ (void)sock_register(&inet_family_ops); #ifdef CONFIG_SYSCTL ip_static_sysctl_init(); #endif /* * Add all the base protocols. */ if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0) pr_crit("%s: Cannot add ICMP protocol\n", __func__); net_hotdata.udp_protocol = (struct net_protocol) { .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, }; if (inet_add_protocol(&net_hotdata.udp_protocol, IPPROTO_UDP) < 0) pr_crit("%s: Cannot add UDP protocol\n", __func__); net_hotdata.tcp_protocol = (struct net_protocol) { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, .icmp_strict_tag_validation = 1, }; if (inet_add_protocol(&net_hotdata.tcp_protocol, IPPROTO_TCP) < 0) pr_crit("%s: Cannot add TCP protocol\n", __func__); #ifdef CONFIG_IP_MULTICAST if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0) pr_crit("%s: Cannot add IGMP protocol\n", __func__); #endif /* Register the socket-side information for inet_create. */ for (r = &inetsw[0]; r < &inetsw[SOCK_MAX]; ++r) INIT_LIST_HEAD(r); for (q = inetsw_array; q < &inetsw_array[INETSW_ARRAY_LEN]; ++q) inet_register_protosw(q); /* * Set the ARP module up */ arp_init(); /* * Set the IP module up */ ip_init(); /* Initialise per-cpu ipv4 mibs */ if (init_ipv4_mibs()) panic("%s: Cannot init ipv4 mibs\n", __func__); /* Setup TCP slab cache for open requests. */ tcp_init(); /* Setup UDP memory threshold */ udp_init(); /* Add UDP-Lite (RFC 3828) */ udplite4_register(); raw_init(); ping_init(); /* * Set the ICMP layer up */ if (icmp_init() < 0) panic("Failed to create the ICMP control socket.\n"); /* * Initialise the multicast router */ #if defined(CONFIG_IP_MROUTE) if (ip_mr_init()) pr_crit("%s: Cannot init ipv4 mroute\n", __func__); #endif if (init_inet_pernet_ops()) pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__); ipv4_proc_init(); ipfrag_init(); dev_add_pack(&ip_packet_type); ip_tunnel_core_init(); rc = 0; out: return rc; out_unregister_raw_proto: proto_unregister(&raw_prot); out_unregister_udp_proto: proto_unregister(&udp_prot); out_unregister_tcp_proto: proto_unregister(&tcp_prot); goto out; } fs_initcall(inet_init); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS static int __init ipv4_proc_init(void) { int rc = 0; if (raw_proc_init()) goto out_raw; if (tcp4_proc_init()) goto out_tcp; if (udp4_proc_init()) goto out_udp; if (ping_proc_init()) goto out_ping; if (ip_misc_proc_init()) goto out_misc; out: return rc; out_misc: ping_proc_exit(); out_ping: udp4_proc_exit(); out_udp: tcp4_proc_exit(); out_tcp: raw_proc_exit(); out_raw: rc = -ENOMEM; goto out; } #else /* CONFIG_PROC_FS */ static int __init ipv4_proc_init(void) { return 0; } #endif /* CONFIG_PROC_FS */ |
| 599 313 315 6 199 188 20 10 6 6 129 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIME64_H #define _LINUX_TIME64_H #include <linux/math64.h> #include <vdso/time64.h> typedef __s64 time64_t; typedef __u64 timeu64_t; #include <uapi/linux/time.h> struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; struct itimerspec64 { struct timespec64 it_interval; struct timespec64 it_value; }; /* Parameters used to convert the timespec values: */ #define PSEC_PER_NSEC 1000L /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_MIN (-KTIME_MAX - 1) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) #define KTIME_SEC_MIN (KTIME_MIN / NSEC_PER_SEC) /* * Limits for settimeofday(): * * To prevent setting the time close to the wraparound point time setting * is limited so a reasonable uptime can be accomodated. Uptime of 30 years * should be really sufficient, which means the cutoff is 2232. At that * point the cutoff is just a small part of the larger problem. */ #define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) #define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } /* * lhs < rhs: return <0 * lhs == rhs: return 0 * lhs > rhs: return >0 */ static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; if (lhs->tv_sec > rhs->tv_sec) return 1; return lhs->tv_nsec - rhs->tv_nsec; } extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); static inline struct timespec64 timespec64_add(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); return ts_delta; } /* * sub = lhs - rhs, in normalized form */ static inline struct timespec64 timespec64_sub(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, lhs.tv_nsec - rhs.tv_nsec); return ts_delta; } /* * Returns true if the timespec64 is norm, false if denorm: */ static inline bool timespec64_valid(const struct timespec64 *ts) { /* Dates before 1970 are bogus */ if (ts->tv_sec < 0) return false; /* Can't have more nanoseconds then a second */ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return false; return true; } static inline bool timespec64_valid_strict(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values that could overflow ktime_t */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return false; return true; } static inline bool timespec64_valid_settod(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) return false; return true; } /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted * * Returns the scalar nanosecond representation of the timespec64 * parameter. */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { /* Prevent multiplication overflow / underflow */ if (ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; if (ts->tv_sec <= KTIME_SEC_MIN) return KTIME_MIN; return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ extern struct timespec64 ns_to_timespec64(s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 * @a: pointer to timespec64 to be incremented * @ns: unsigned nanoseconds value to be added * * This must always be inlined because its used from the x86-64 vdso, * which cannot call other kernel functions. */ static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) { a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } /* * timespec64_add_safe assumes both values are positive and checks for * overflow. It will return TIME64_MAX in case of overflow. */ extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs); #endif /* _LINUX_TIME64_H */ |
| 8 8 8 8 8 5 8 7 7 7 7 172 21 172 172 172 172 172 172 40 21 172 172 172 170 168 172 172 175 175 175 60 174 173 174 175 166 167 167 166 59 59 43 43 59 51 19 59 6 4 174 62 88 7 7 7 187 50 185 44 1 1 117 116 186 187 184 187 187 187 187 187 187 7 187 187 1 1 186 187 187 7 187 187 146 144 145 142 7 6 143 6 6 6 5 5 5 5 5 187 5 187 183 29 183 29 182 183 8 6 5 184 183 173 3 3 172 172 171 172 171 21 172 168 167 167 166 167 177 1 1 177 5 5 5 175 177 177 3 176 110 110 14 2 14 14 14 14 21 35 35 117 117 117 115 28 116 116 325 326 329 329 327 328 6 6 6 181 112 28 28 28 112 189 120 181 181 181 181 181 3 3 181 179 7 1 26 26 26 8 8 8 8 8 7 7 25 1 1 1 1 24 24 24 23 24 24 23 24 24 49 1 1 1 1 1 1 1 1 1 1 1 1 1 1 7 7 7 2 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 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 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 1 1 1 8 8 1 1 8 7 7 7 7 7 7 7 7 7 4 7 7 7 7 7 1 1 1 1 1 1 1 1 2 7 1 7 7 7 7 1 1 1 7 7 2 7 7 6 5 7 7 7 7 7 7 7 7 7 7 7 7 7 7 1 7 7 7 7 7 7 7 7 7 3 5 5 5 5 5 2 5 5 5 5 7 7 4 5 5 5 7 7 5 7 7 3 7 7 7 7 7 7 7 7 6 6 6 5 6 8 8 8 8 8 8 8 8 8 8 3 3 8 8 8 8 7 8 8 1 8 8 7 7 6 7 8 8 8 6 8 8 8 7 7 7 8 8 8 8 8 8 8 8 7 7 5 7 2 8 8 8 8 7 8 7 6 7 6 7 7 7 6 7 7 7 6 7 6 1 8 8 8 8 8 7 7 7 8 7 8 8 8 8 2 2 2 5 5 5 5 5 5 5 5 7 8 8 8 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, Stephen Tweedie. * kswapd added: 7.1.96 sct * Removed kswapd_ctl limits, and swap out as many pages as needed * to bring the system back to freepages.high: 2.4.97, Rik van Riel. * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). * Multiqueue VM started 5.8.00, Rik van Riel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> /* for buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/memcontrol.h> #include <linux/migrate.h> #include <linux/delayacct.h> #include <linux/sysctl.h> #include <linux/memory-tiers.h> #include <linux/oom.h> #include <linux/pagevec.h> #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> #include <linux/psi.h> #include <linux/pagewalk.h> #include <linux/shmem_fs.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> #include <linux/balloon_compaction.h> #include <linux/sched/sysctl.h> #include "internal.h" #include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> struct scan_control { /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; /* * Nodemask of nodes allowed by the caller. If NULL, all nodes * are scanned. */ nodemask_t *nodemask; /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. */ struct mem_cgroup *target_mem_cgroup; /* * Scan pressure balancing between anon and file LRUs */ unsigned long anon_cost; unsigned long file_cost; #ifdef CONFIG_MEMCG /* Swappiness value for proactive reclaim. Always use sc_swappiness()! */ int *proactive_swappiness; #endif /* Can active folios be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 unsigned int may_deactivate:2; unsigned int force_deactivate:1; unsigned int skipped_deactivate:1; /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; /* Can mapped folios be reclaimed? */ unsigned int may_unmap:1; /* Can folios be swapped as part of reclaim? */ unsigned int may_swap:1; /* Not allow cache_trim_mode to be turned on as part of reclaim? */ unsigned int no_cache_trim_mode:1; /* Has cache_trim_mode failed at least once? */ unsigned int cache_trim_mode_failed:1; /* Proactive reclaim invoked by userspace through memory.reclaim */ unsigned int proactive:1; /* * Cgroup memory below memory.low is protected as long as we * don't threaten to OOM. If any cgroup is reclaimed at * reduced force or passed over entirely due to its memory.low * setting (memcg_low_skipped), and nothing is reclaimed as a * result, then go back for one more cycle that reclaims the protected * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; /* Shared cgroup tree walk failed, rescan the whole tree */ unsigned int memcg_full_walk:1; unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ unsigned int compaction_ready:1; /* There is easily reclaimable cold cache in the current node */ unsigned int cache_trim_mode:1; /* The file folios on the current node are dangerously low */ unsigned int file_is_tiny:1; /* Always discard instead of demoting to lower tier memory */ unsigned int no_demotion:1; /* Allocation order */ s8 order; /* Scan (total_size >> priority) pages at once */ s8 priority; /* The highest zone to isolate folios for reclaim from */ s8 reclaim_idx; /* This context's GFP mask */ gfp_t gfp_mask; /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; struct { unsigned int dirty; unsigned int unqueued_dirty; unsigned int congested; unsigned int writeback; unsigned int immediate; unsigned int file_taken; unsigned int taken; } nr; /* for recording the reclaimed slab by now */ struct reclaim_state reclaim_state; }; #ifdef ARCH_HAS_PREFETCHW #define prefetchw_prev_lru_folio(_folio, _base, _field) \ do { \ if ((_folio)->lru.prev != _base) { \ struct folio *prev; \ \ prev = lru_to_folio(&(_folio->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else #define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0) #endif /* * From 0 .. MAX_SWAPPINESS. Higher means more swappy. */ int vm_swappiness = 60; #ifdef CONFIG_MEMCG /* Returns true for reclaim through cgroup limits or cgroup interfaces. */ static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; } /* * Returns true for reclaim on the root cgroup. This is true for direct * allocator reclaim and reclaim through cgroup interfaces on the root cgroup. */ static bool root_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup || mem_cgroup_is_root(sc->target_mem_cgroup); } /** * writeback_throttling_sane - is the usual dirty throttling mechanism available? * @sc: scan_control in question * * The normal page dirty throttling mechanism in balance_dirty_pages() is * completely broken with the legacy memcg and direct stalling in * shrink_folio_list() is used for throttling instead, which lacks all the * niceties such as fairness, adaptive pausing, bandwidth proportional * allocation and configurability. * * This function tests whether the vmscan currently in progress can assume * that the normal dirty throttling mechanism is operational. */ static bool writeback_throttling_sane(struct scan_control *sc) { if (!cgroup_reclaim(sc)) return true; #ifdef CONFIG_CGROUP_WRITEBACK if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return true; #endif return false; } static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) { if (sc->proactive && sc->proactive_swappiness) return *sc->proactive_swappiness; return mem_cgroup_swappiness(memcg); } #else static bool cgroup_reclaim(struct scan_control *sc) { return false; } static bool root_reclaim(struct scan_control *sc) { return true; } static bool writeback_throttling_sane(struct scan_control *sc) { return true; } static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) { return READ_ONCE(vm_swappiness); } #endif static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { /* Check for an overwrite */ WARN_ON_ONCE(rs && task->reclaim_state); /* Check for the nulling of an already-nulled member */ WARN_ON_ONCE(!rs && !task->reclaim_state); task->reclaim_state = rs; } /* * flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to * scan_control->nr_reclaimed. */ static void flush_reclaim_state(struct scan_control *sc) { /* * Currently, reclaim_state->reclaimed includes three types of pages * freed outside of vmscan: * (1) Slab pages. * (2) Clean file pages from pruned inodes (on highmem systems). * (3) XFS freed buffer pages. * * For all of these cases, we cannot universally link the pages to a * single memcg. For example, a memcg-aware shrinker can free one object * charged to the target memcg, causing an entire page to be freed. * If we count the entire page as reclaimed from the memcg, we end up * overestimating the reclaimed amount (potentially under-reclaiming). * * Only count such pages for global reclaim to prevent under-reclaiming * from the target memcg; preventing unnecessary retries during memcg * charging and false positives from proactive reclaim. * * For uncommon cases where the freed pages were actually mostly * charged to the target memcg, we end up underestimating the reclaimed * amount. This should be fine. The freed pages will be uncharged * anyway, even if they are not counted here properly, and we will be * able to make forward progress in charging (which is usually in a * retry loop). * * We can go one step further, and report the uncharged objcg pages in * memcg reclaim, to make reporting more accurate and reduce * underestimation, but it's probably not worth the complexity for now. */ if (current->reclaim_state && root_reclaim(sc)) { sc->nr_reclaimed += current->reclaim_state->reclaimed; current->reclaim_state->reclaimed = 0; } } static bool can_demote(int nid, struct scan_control *sc) { if (!numa_demotion_enabled) return false; if (sc && sc->no_demotion) return false; if (next_demotion_node(nid) == NUMA_NO_NODE) return false; return true; } static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, int nid, struct scan_control *sc) { if (memcg == NULL) { /* * For non-memcg reclaim, is there * space in any swap device? */ if (get_nr_swap_pages() > 0) return true; } else { /* Is the memcg below its swap limit? */ if (mem_cgroup_get_nr_swap_pages(memcg) > 0) return true; } /* * The page can not be swapped. * * Can it be reclaimed from this node via demotion? */ return can_demote(nid, sc); } /* * This misses isolated folios which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is * not expected that isolated folios will be a dominating factor. */ unsigned long zone_reclaimable_pages(struct zone *zone) { unsigned long nr; nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); return nr; } /** * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector * @lru: lru to use * @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list) */ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { unsigned long size = 0; int zid; for (zid = 0; zid <= zone_idx; zid++) { struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; if (!managed_zone(zone)) continue; if (!mem_cgroup_disabled()) size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); else size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); } return size; } static unsigned long drop_slab_node(int nid) { unsigned long freed = 0; struct mem_cgroup *memcg = NULL; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); return freed; } void drop_slab(void) { int nid; int shift = 0; unsigned long freed; do { freed = 0; for_each_online_node(nid) { if (fatal_signal_pending(current)) return; freed += drop_slab_node(nid); } } while ((freed >> shift++) > 1); } static int reclaimer_offset(void) { BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD != PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD); BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD != PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD); BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD != PGSCAN_DIRECT - PGSCAN_KSWAPD); BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD != PGSCAN_KHUGEPAGED - PGSCAN_KSWAPD); if (current_is_kswapd()) return 0; if (current_is_khugepaged()) return PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD; return PGSTEAL_DIRECT - PGSTEAL_KSWAPD; } static inline int is_page_cache_freeable(struct folio *folio) { /* * A freeable page cache folio is referenced only by the caller * that isolated the folio, the page cache and optional filesystem * private data at folio->private. */ return folio_ref_count(folio) - folio_test_private(folio) == 1 + folio_nr_pages(folio); } /* * We detected a synchronous write error writing a folio out. Probably * -ENOSPC. We need to propagate that into the address_space for a subsequent * fsync(), msync() or close(). * * The tricky part is that after writepage we cannot touch the mapping: nothing * prevents it from being freed up. But we have a ref on the folio and once * that folio is locked, the mapping is pinned. * * We're allowed to run sleeping folio_lock() here because we know the caller has * __GFP_FS. */ static void handle_write_error(struct address_space *mapping, struct folio *folio, int error) { folio_lock(folio); if (folio_mapping(folio) == mapping) mapping_set_error(mapping, error); folio_unlock(folio); } static bool skip_throttle_noprogress(pg_data_t *pgdat) { int reclaimable = 0, write_pending = 0; int i; /* * If kswapd is disabled, reschedule if necessary but do not * throttle as the system is likely near OOM. */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; /* * If there are a lot of dirty/writeback folios then do not * throttle as throttling will occur when the folios cycle * towards the end of the LRU if still under writeback. */ for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; reclaimable += zone_reclaimable_pages(zone); write_pending += zone_page_state_snapshot(zone, NR_ZONE_WRITE_PENDING); } if (2 * write_pending <= reclaimable) return true; return false; } void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; long timeout, ret; DEFINE_WAIT(wait); /* * Do not throttle user workers, kthreads other than kswapd or * workqueues. They may be required for reclaim to make * forward progress (e.g. journalling workqueues or kthreads). */ if (!current_is_kswapd() && current->flags & (PF_USER_WORKER|PF_KTHREAD)) { cond_resched(); return; } /* * These figures are pulled out of thin air. * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many * parallel reclaimers which is a short-lived event so the timeout is * short. Failing to make progress or waiting on writeback are * potentially long-lived events so use a longer timeout. This is shaky * logic as a failure to make progress could be due to anything from * writeback to a slow device to excessive referenced folios at the tail * of the inactive LRU. */ switch(reason) { case VMSCAN_THROTTLE_WRITEBACK: timeout = HZ/10; if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { WRITE_ONCE(pgdat->nr_reclaim_start, node_page_state(pgdat, NR_THROTTLED_WRITTEN)); } break; case VMSCAN_THROTTLE_CONGESTED: fallthrough; case VMSCAN_THROTTLE_NOPROGRESS: if (skip_throttle_noprogress(pgdat)) { cond_resched(); return; } timeout = 1; break; case VMSCAN_THROTTLE_ISOLATED: timeout = HZ/50; break; default: WARN_ON_ONCE(1); timeout = HZ; break; } prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = schedule_timeout(timeout); finish_wait(wqh, &wait); if (reason == VMSCAN_THROTTLE_WRITEBACK) atomic_dec(&pgdat->nr_writeback_throttled); trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), jiffies_to_usecs(timeout - ret), reason); } /* * Account for folios written if tasks are throttled waiting on dirty * folios to clean. If enough folios have been cleaned since throttling * started then wakeup the throttled tasks. */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled) { unsigned long nr_written; node_stat_add_folio(folio, NR_THROTTLED_WRITTEN); /* * This is an inaccurate read as the per-cpu deltas may not * be synchronised. However, given that the system is * writeback throttled, it is not worth taking the penalty * of getting an accurate count. At worst, the throttle * timeout guarantees forward progress. */ nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) - READ_ONCE(pgdat->nr_reclaim_start); if (nr_written > SWAP_CLUSTER_MAX * nr_throttled) wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]); } /* possible outcome of pageout() */ typedef enum { /* failed to write folio out, folio is locked */ PAGE_KEEP, /* move folio to the active list, folio is locked */ PAGE_ACTIVATE, /* folio has been sent to the disk successfully, folio is unlocked */ PAGE_SUCCESS, /* folio is clean and locked */ PAGE_CLEAN, } pageout_t; /* * pageout is called by shrink_folio_list() for each dirty folio. * Calls ->writepage(). */ static pageout_t pageout(struct folio *folio, struct address_space *mapping, struct swap_iocb **plug, struct list_head *folio_list) { /* * If the folio is dirty, only perform writeback if that write * will be non-blocking. To prevent this allocation from being * stalled by pagecache activity. But note that there may be * stalls if we need to run get_block(). We could test * PagePrivate for that. * * If this process is currently in __generic_file_write_iter() against * this folio's queue, we can perform writeback even if that * will block. * * If the folio is swapcache, write it back even if that would * block, for some throttling. This happens by accident, because * swap_backing_dev_info is bust: it doesn't reflect the * congestion state of the swapdevs. Easy to fix, if needed. */ if (!is_page_cache_freeable(folio)) return PAGE_KEEP; if (!mapping) { /* * Some data journaling orphaned folios can have * folio->mapping == NULL while being dirty with clean buffers. */ if (folio_test_private(folio)) { if (try_to_free_buffers(folio)) { folio_clear_dirty(folio); pr_info("%s: orphaned folio\n", __func__); return PAGE_CLEAN; } } return PAGE_KEEP; } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; if (folio_clear_dirty_for_io(folio)) { int res; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1, .swap_plug = plug, }; /* * The large shmem folio can be split if CONFIG_THP_SWAP is * not enabled or contiguous swap entries are failed to * allocate. */ if (shmem_mapping(mapping) && folio_test_large(folio)) wbc.list = folio_list; folio_set_reclaim(folio); res = mapping->a_ops->writepage(&folio->page, &wbc); if (res < 0) handle_write_error(mapping, folio, res); if (res == AOP_WRITEPAGE_ACTIVATE) { folio_clear_reclaim(folio); return PAGE_ACTIVATE; } if (!folio_test_writeback(folio)) { /* synchronous write or broken a_ops? */ folio_clear_reclaim(folio); } trace_mm_vmscan_write_folio(folio); node_stat_add_folio(folio, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } return PAGE_CLEAN; } /* * Same as remove_mapping, but if the folio is removed from the mapping, it * gets returned with a refcount of 0. */ static int __remove_mapping(struct address_space *mapping, struct folio *folio, bool reclaimed, struct mem_cgroup *target_memcg) { int refcount; void *shadow = NULL; BUG_ON(!folio_test_locked(folio)); BUG_ON(mapping != folio_mapping(folio)); if (!folio_test_swapcache(folio)) spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); /* * The non racy check for a busy folio. * * Must be careful with the order of the tests. When someone has * a ref to the folio, it may be possible that they dirty it then * drop the reference. So if the dirty flag is tested before the * refcount here, then the following race may occur: * * get_user_pages(&page); * [user mapping goes away] * write_to(page); * !folio_test_dirty(folio) [good] * folio_set_dirty(folio); * folio_put(folio); * !refcount(folio) [good, discard it] * * [oops, our write_to data is lost] * * Reversing the order of the tests ensures such a situation cannot * escape unnoticed. The smp_rmb is needed to ensure the folio->flags * load is not satisfied before that of folio->_refcount. * * Note that if the dirty flag is always set via folio_mark_dirty, * and thus under the i_pages lock, then this ordering is not required. */ refcount = 1 + folio_nr_pages(folio); if (!folio_ref_freeze(folio, refcount)) goto cannot_free; /* note: atomic_cmpxchg in folio_ref_freeze provides the smp_rmb */ if (unlikely(folio_test_dirty(folio))) { folio_ref_unfreeze(folio, refcount); goto cannot_free; } if (folio_test_swapcache(folio)) { swp_entry_t swap = folio->swap; if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(folio, target_memcg); __delete_from_swap_cache(folio, swap, shadow); mem_cgroup_swapout(folio, swap); xa_unlock_irq(&mapping->i_pages); put_swap_folio(folio, swap); } else { void (*free_folio)(struct folio *); free_folio = mapping->a_ops->free_folio; /* * Remember a shadow entry for reclaimed file cache in * order to detect refaults, thus thrashing, later on. * * But don't store shadows in an address space that is * already exiting. This is not just an optimization, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. * * We also don't store shadows for DAX mappings because the * only page cache folios found in these are zero pages * covering holes, and because we don't want to mix DAX * exceptional entries and shadow exceptional entries in the * same address_space. */ if (reclaimed && folio_is_file_lru(folio) && !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(folio, target_memcg); __filemap_remove_folio(folio, shadow); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); if (free_folio) free_folio(folio); } return 1; cannot_free: xa_unlock_irq(&mapping->i_pages); if (!folio_test_swapcache(folio)) spin_unlock(&mapping->host->i_lock); return 0; } /** * remove_mapping() - Attempt to remove a folio from its mapping. * @mapping: The address space. * @folio: The folio to remove. * * If the folio is dirty, under writeback or if someone else has a ref * on it, removal will fail. * Return: The number of pages removed from the mapping. 0 if the folio * could not be removed. * Context: The caller should have a single refcount on the folio and * hold its lock. */ long remove_mapping(struct address_space *mapping, struct folio *folio) { if (__remove_mapping(mapping, folio, false, NULL)) { /* * Unfreezing the refcount with 1 effectively * drops the pagecache ref for us without requiring another * atomic operation. */ folio_ref_unfreeze(folio, 1); return folio_nr_pages(folio); } return 0; } /** * folio_putback_lru - Put previously isolated folio onto appropriate LRU list. * @folio: Folio to be returned to an LRU list. * * Add previously isolated @folio to appropriate LRU list. * The folio may still be unevictable for other reasons. * * Context: lru_lock must not be held, interrupts must be enabled. */ void folio_putback_lru(struct folio *folio) { folio_add_lru(folio); folio_put(folio); /* drop ref from isolate */ } enum folio_references { FOLIOREF_RECLAIM, FOLIOREF_RECLAIM_CLEAN, FOLIOREF_KEEP, FOLIOREF_ACTIVATE, }; static enum folio_references folio_check_references(struct folio *folio, struct scan_control *sc) { int referenced_ptes, referenced_folio; unsigned long vm_flags; referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup, &vm_flags); referenced_folio = folio_test_clear_referenced(folio); /* * The supposedly reclaimable folio was found to be in a VM_LOCKED vma. * Let the folio, now marked Mlocked, be moved to the unevictable list. */ if (vm_flags & VM_LOCKED) return FOLIOREF_ACTIVATE; /* * There are two cases to consider. * 1) Rmap lock contention: rotate. * 2) Skip the non-shared swapbacked folio mapped solely by * the exiting or OOM-reaped process. */ if (referenced_ptes == -1) return FOLIOREF_KEEP; if (referenced_ptes) { /* * All mapped folios start out with page table * references from the instantiating fault, so we need * to look twice if a mapped file/anon folio is used more * than once. * * Mark it and spare it for another trip around the * inactive list. Another page table reference will * lead to its activation. * * Note: the mark is set for activated folios as well * so that recently deactivated but used folios are * quickly recovered. */ folio_set_referenced(folio); if (referenced_folio || referenced_ptes > 1) return FOLIOREF_ACTIVATE; /* * Activate file-backed executable folios after first usage. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) return FOLIOREF_ACTIVATE; return FOLIOREF_KEEP; } /* Reclaim if clean, defer dirty folios to writeback */ if (referenced_folio && folio_is_file_lru(folio)) return FOLIOREF_RECLAIM_CLEAN; return FOLIOREF_RECLAIM; } /* Check if a folio is dirty or under writeback */ static void folio_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct address_space *mapping; /* * Anonymous folios are not handled by flushers and must be written * from reclaim context. Do not stall reclaim based on them. * MADV_FREE anonymous folios are put into inactive file list too. * They could be mistakenly treated as file lru. So further anon * test is needed. */ if (!folio_is_file_lru(folio) || (folio_test_anon(folio) && !folio_test_swapbacked(folio))) { *dirty = false; *writeback = false; return; } /* By default assume that the folio flags are accurate */ *dirty = folio_test_dirty(folio); *writeback = folio_test_writeback(folio); /* Verify dirty/writeback state if the filesystem supports it */ if (!folio_test_private(folio)) return; mapping = folio_mapping(folio); if (mapping && mapping->a_ops->is_dirty_writeback) mapping->a_ops->is_dirty_writeback(folio, dirty, writeback); } struct folio *alloc_migrate_folio(struct folio *src, unsigned long private) { struct folio *dst; nodemask_t *allowed_mask; struct migration_target_control *mtc; mtc = (struct migration_target_control *)private; allowed_mask = mtc->nmask; /* * make sure we allocate from the target node first also trying to * demote or reclaim pages from the target node via kswapd if we are * low on free memory on target node. If we don't do this and if * we have free memory on the slower(lower) memtier, we would start * allocating pages from slower(lower) memory tiers without even forcing * a demotion of cold pages from the target memtier. This can result * in the kernel placing hot pages in slower(lower) memory tiers. */ mtc->nmask = NULL; mtc->gfp_mask |= __GFP_THISNODE; dst = alloc_migration_target(src, (unsigned long)mtc); if (dst) return dst; mtc->gfp_mask &= ~__GFP_THISNODE; mtc->nmask = allowed_mask; return alloc_migration_target(src, (unsigned long)mtc); } /* * Take folios on @demote_folios and attempt to demote them to another node. * Folios which are not demoted are left on @demote_folios. */ static unsigned int demote_folio_list(struct list_head *demote_folios, struct pglist_data *pgdat) { int target_nid = next_demotion_node(pgdat->node_id); unsigned int nr_succeeded; nodemask_t allowed_mask; struct migration_target_control mtc = { /* * Allocate from 'node', or fail quickly and quietly. * When this happens, 'page' will likely just be discarded * instead of migrated. */ .gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN | __GFP_NOMEMALLOC | GFP_NOWAIT, .nid = target_nid, .nmask = &allowed_mask, .reason = MR_DEMOTION, }; if (list_empty(demote_folios)) return 0; if (target_nid == NUMA_NO_NODE) return 0; node_get_allowed_targets(pgdat, &allowed_mask); /* Demotion ignores all cpuset and mempolicy settings */ migrate_pages(demote_folios, alloc_migrate_folio, NULL, (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); return nr_succeeded; } static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask) { if (gfp_mask & __GFP_FS) return true; if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO)) return false; /* * We can "enter_fs" for swap-cache with only __GFP_IO * providing this isn't SWP_FS_OPS. * ->flags can be updated non-atomicially (scan_swap_map_slots), * but that will never affect SWP_FS_OPS, so the data_race * is safe. */ return !data_race(folio_swap_flags(folio) & SWP_FS_OPS); } /* * shrink_folio_list() returns the number of reclaimed pages */ static unsigned int shrink_folio_list(struct list_head *folio_list, struct pglist_data *pgdat, struct scan_control *sc, struct reclaim_stat *stat, bool ignore_references) { struct folio_batch free_folios; LIST_HEAD(ret_folios); LIST_HEAD(demote_folios); unsigned int nr_reclaimed = 0; unsigned int pgactivate = 0; bool do_demote_pass; struct swap_iocb *plug = NULL; folio_batch_init(&free_folios); memset(stat, 0, sizeof(*stat)); cond_resched(); do_demote_pass = can_demote(pgdat->node_id, sc); retry: while (!list_empty(folio_list)) { struct address_space *mapping; struct folio *folio; enum folio_references references = FOLIOREF_RECLAIM; bool dirty, writeback; unsigned int nr_pages; cond_resched(); folio = lru_to_folio(folio_list); list_del(&folio->lru); if (!folio_trylock(folio)) goto keep; VM_BUG_ON_FOLIO(folio_test_active(folio), folio); nr_pages = folio_nr_pages(folio); /* Account the number of base pages */ sc->nr_scanned += nr_pages; if (unlikely(!folio_evictable(folio))) goto activate_locked; if (!sc->may_unmap && folio_mapped(folio)) goto keep_locked; /* folio_update_gen() tried to promote this page? */ if (lru_gen_enabled() && !ignore_references && folio_mapped(folio) && folio_test_referenced(folio)) goto keep_locked; /* * The number of dirty pages determines if a node is marked * reclaim_congested. kswapd will stall and start writing * folios if the tail of the LRU is all dirty unqueued folios. */ folio_check_dirty_writeback(folio, &dirty, &writeback); if (dirty || writeback) stat->nr_dirty += nr_pages; if (dirty && !writeback) stat->nr_unqueued_dirty += nr_pages; /* * Treat this folio as congested if folios are cycling * through the LRU so quickly that the folios marked * for immediate reclaim are making it to the end of * the LRU a second time. */ if (writeback && folio_test_reclaim(folio)) stat->nr_congested += nr_pages; /* * If a folio at the tail of the LRU is under writeback, there * are three cases to consider. * * 1) If reclaim is encountering an excessive number * of folios under writeback and this folio has both * the writeback and reclaim flags set, then it * indicates that folios are being queued for I/O but * are being recycled through the LRU before the I/O * can complete. Waiting on the folio itself risks an * indefinite stall if it is impossible to writeback * the folio due to I/O error or disconnected storage * so instead note that the LRU is being scanned too * quickly and the caller can stall after the folio * list has been processed. * * 2) Global or new memcg reclaim encounters a folio that is * not marked for immediate reclaim, or the caller does not * have __GFP_FS (or __GFP_IO if it's simply going to swap, * not to fs). In this case mark the folio for immediate * reclaim and continue scanning. * * Require may_enter_fs() because we would wait on fs, which * may not have submitted I/O yet. And the loop driver might * enter reclaim, and deadlock if it waits on a folio for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * * 3) Legacy memcg encounters a folio that already has the * reclaim flag set. memcg does not have any dirty folio * throttling so we could easily OOM just because too many * folios are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. * * In cases 1) and 2) we activate the folios to get them out of * the way while we continue scanning for clean folios on the * inactive list and refilling from the active list. The * observation here is that waiting for disk writes is more * expensive than potentially causing reloads down the line. * Since they're marked for immediate reclaim, they won't put * memory pressure on the cache working set any longer than it * takes to write them to disk. */ if (folio_test_writeback(folio)) { /* Case 1 above */ if (current_is_kswapd() && folio_test_reclaim(folio) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { stat->nr_immediate += nr_pages; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || !folio_test_reclaim(folio) || !may_enter_fs(folio, sc->gfp_mask)) { /* * This is slightly racy - * folio_end_writeback() might have * just cleared the reclaim flag, then * setting the reclaim flag here ends up * interpreted as the readahead flag - but * that does not matter enough to care. * What we do want is for this folio to * have the reclaim flag set next time * memcg reclaim reaches the tests above, * so it will then wait for writeback to * avoid OOM; and it's also appropriate * in global reclaim. */ folio_set_reclaim(folio); stat->nr_writeback += nr_pages; goto activate_locked; /* Case 3 above */ } else { folio_unlock(folio); folio_wait_writeback(folio); /* then go back and try same folio again */ list_add_tail(&folio->lru, folio_list); continue; } } if (!ignore_references) references = folio_check_references(folio, sc); switch (references) { case FOLIOREF_ACTIVATE: goto activate_locked; case FOLIOREF_KEEP: stat->nr_ref_keep += nr_pages; goto keep_locked; case FOLIOREF_RECLAIM: case FOLIOREF_RECLAIM_CLEAN: ; /* try to reclaim the folio below */ } /* * Before reclaiming the folio, try to relocate * its contents to another node. */ if (do_demote_pass && (thp_migration_supported() || !folio_test_large(folio))) { list_add(&folio->lru, &demote_folios); folio_unlock(folio); continue; } /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. * Lazyfree folio could be freed directly */ if (folio_test_anon(folio) && folio_test_swapbacked(folio)) { if (!folio_test_swapcache(folio)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (folio_maybe_dma_pinned(folio)) goto keep_locked; if (folio_test_large(folio)) { /* cannot split folio, skip it */ if (!can_split_folio(folio, 1, NULL)) goto activate_locked; /* * Split partially mapped folios right away. * We can free the unmapped pages without IO. */ if (data_race(!list_empty(&folio->_deferred_list) && folio_test_partially_mapped(folio)) && split_folio_to_list(folio, folio_list)) goto activate_locked; } if (!add_to_swap(folio)) { int __maybe_unused order = folio_order(folio); if (!folio_test_large(folio)) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_folio_to_list(folio, folio_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (nr_pages >= HPAGE_PMD_NR) { count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); } count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); #endif if (!add_to_swap(folio)) goto activate_locked_split; } } } /* * If the folio was split above, the tail pages will make * their own pass through this function and be accounted * then. */ if ((nr_pages > 1) && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* * The folio is mapped into the page tables of one or more * processes. Try to unmap it here. */ if (folio_mapped(folio)) { enum ttu_flags flags = TTU_BATCH_FLUSH; bool was_swapbacked = folio_test_swapbacked(folio); if (folio_test_pmd_mappable(folio)) flags |= TTU_SPLIT_HUGE_PMD; /* * Without TTU_SYNC, try_to_unmap will only begin to * hold PTL from the first present PTE within a large * folio. Some initial PTEs might be skipped due to * races with parallel PTE writes in which PTEs can be * cleared temporarily before being written new present * values. This will lead to a large folio is still * mapped while some subpages have been partially * unmapped after try_to_unmap; TTU_SYNC helps * try_to_unmap acquire PTL from the first PTE, * eliminating the influence of temporary PTE values. */ if (folio_test_large(folio)) flags |= TTU_SYNC; try_to_unmap(folio, flags); if (folio_mapped(folio)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && folio_test_swapbacked(folio)) stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } /* * Folio is unmapped now so it cannot be newly pinned anymore. * No point in trying to reclaim folio if it is pinned. * Furthermore we don't want to reclaim underlying fs metadata * if the folio is pinned and thus potentially modified by the * pinning process as that may upset the filesystem. */ if (folio_maybe_dma_pinned(folio)) goto activate_locked; mapping = folio_mapping(folio); if (folio_test_dirty(folio)) { /* * Only kswapd can writeback filesystem folios * to avoid risk of stack overflow. But avoid * injecting inefficient single-folio I/O into * flusher writeback as much as possible: only * write folios when we've encountered many * dirty folios, and when we've already scanned * the rest of the LRU for clean folios and see * the same dirty folios again (with the reclaim * flag set). */ if (folio_is_file_lru(folio) && (!current_is_kswapd() || !folio_test_reclaim(folio) || !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principle to folio_deactivate() * except we already have the folio isolated * and know it's dirty */ node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE, nr_pages); folio_set_reclaim(folio); goto activate_locked; } if (references == FOLIOREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs(folio, sc->gfp_mask)) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* * Folio is dirty. Flush the TLB if a writable entry * potentially exists to avoid CPU writes after I/O * starts and then write it out here. */ try_to_unmap_flush_dirty(); switch (pageout(folio, mapping, &plug, folio_list)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: /* * If shmem folio is split when writeback to swap, * the tail pages will make their own pass through * this function and be accounted then. */ if (nr_pages > 1 && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } goto activate_locked; case PAGE_SUCCESS: if (nr_pages > 1 && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } stat->nr_pageout += nr_pages; if (folio_test_writeback(folio)) goto keep; if (folio_test_dirty(folio)) goto keep; /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the folio. */ if (!folio_trylock(folio)) goto keep; if (folio_test_dirty(folio) || folio_test_writeback(folio)) goto keep_locked; mapping = folio_mapping(folio); fallthrough; case PAGE_CLEAN: ; /* try to free the folio below */ } } /* * If the folio has buffers, try to free the buffer * mappings associated with this folio. If we succeed * we try to free the folio as well. * * We do this even if the folio is dirty. * filemap_release_folio() does not perform I/O, but it * is possible for a folio to have the dirty flag set, * but it is actually clean (all its buffers are clean). * This happens if the buffers were written out directly, * with submit_bh(). ext3 will do this, as well as * the blockdev mapping. filemap_release_folio() will * discover that cleanness and will drop the buffers * and mark the folio clean - it can be freed. * * Rarely, folios can have buffers and no ->mapping. * These are the folios which were not successfully * invalidated in truncate_cleanup_folio(). We try to * drop those buffers here and if that worked, and the * folio is no longer mapped into process address space * (refcount == 1) it can be freed. Otherwise, leave * the folio on the LRU so it is swappable. */ if (folio_needs_release(folio)) { if (!filemap_release_folio(folio, sc->gfp_mask)) goto activate_locked; if (!mapping && folio_ref_count(folio) == 1) { folio_unlock(folio); if (folio_put_testzero(folio)) goto free_it; else { /* * rare race with speculative reference. * the speculative reference will free * this folio shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ nr_reclaimed += nr_pages; continue; } } } if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) { /* follow __remove_mapping for reference */ if (!folio_ref_freeze(folio, 1)) goto keep_locked; /* * The folio has only one reference left, which is * from the isolation. After the caller puts the * folio back on the lru and drops the reference, the * folio will be freed anyway. It doesn't matter * which lru it goes on. So we don't bother checking * the dirty flag here. */ count_vm_events(PGLAZYFREED, nr_pages); count_memcg_folio_events(folio, PGLAZYFREED, nr_pages); } else if (!mapping || !__remove_mapping(mapping, folio, true, sc->target_mem_cgroup)) goto keep_locked; folio_unlock(folio); free_it: /* * Folio may get swapped out as a whole, need to account * all pages in it. */ nr_reclaimed += nr_pages; folio_undo_large_rmappable(folio); if (folio_batch_add(&free_folios, folio) == 0) { mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); free_unref_folios(&free_folios); } continue; activate_locked_split: /* * The tail pages that are failed to add into swap cache * reach here. Fixup nr_scanned and nr_pages. */ if (nr_pages > 1) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (folio_test_swapcache(folio) && (mem_cgroup_swap_full(folio) || folio_test_mlocked(folio))) folio_free_swap(folio); VM_BUG_ON_FOLIO(folio_test_active(folio), folio); if (!folio_test_mlocked(folio)) { int type = folio_is_file_lru(folio); folio_set_active(folio); stat->nr_activate[type] += nr_pages; count_memcg_folio_events(folio, PGACTIVATE, nr_pages); } keep_locked: folio_unlock(folio); keep: list_add(&folio->lru, &ret_folios); VM_BUG_ON_FOLIO(folio_test_lru(folio) || folio_test_unevictable(folio), folio); } /* 'folio_list' is always empty here */ /* Migrate folios selected for demotion */ stat->nr_demoted = demote_folio_list(&demote_folios, pgdat); nr_reclaimed += stat->nr_demoted; /* Folios that could not be demoted are still in @demote_folios */ if (!list_empty(&demote_folios)) { /* Folios which weren't demoted go back on @folio_list */ list_splice_init(&demote_folios, folio_list); /* * goto retry to reclaim the undemoted folios in folio_list if * desired. * * Reclaiming directly from top tier nodes is not often desired * due to it breaking the LRU ordering: in general memory * should be reclaimed from lower tier nodes and demoted from * top tier nodes. * * However, disabling reclaim from top tier nodes entirely * would cause ooms in edge scenarios where lower tier memory * is unreclaimable for whatever reason, eg memory being * mlocked or too hot to reclaim. We can disable reclaim * from top tier nodes in proactive reclaim though as that is * not real memory pressure. */ if (!sc->proactive) { do_demote_pass = false; goto retry; } } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); free_unref_folios(&free_folios); list_splice(&ret_folios, folio_list); count_vm_events(PGACTIVATE, pgactivate); if (plug) swap_write_unplug(plug); return nr_reclaimed; } unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_unmap = 1, }; struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio, *next; LIST_HEAD(clean_folios); unsigned int noreclaim_flag; list_for_each_entry_safe(folio, next, folio_list, lru) { if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) && !folio_test_dirty(folio) && !__folio_test_movable(folio) && !folio_test_unevictable(folio)) { folio_clear_active(folio); list_move(&folio->lru, &clean_folios); } } /* * We should be safe here since we are only dealing with file pages and * we are not kswapd and therefore cannot write dirty file pages. But * call memalloc_noreclaim_save() anyway, just in case these conditions * change in the future. */ noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = shrink_folio_list(&clean_folios, zone->zone_pgdat, &sc, &stat, true); memalloc_noreclaim_restore(noreclaim_flag); list_splice(&clean_folios, folio_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to * discard so isolated count will be mismatched. * Compensate the isolated count for both LRU lists. */ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } /* * Update LRU sizes after isolating pages. The LRU size updates must * be complete before mem_cgroup_update_lru_size due to a sanity check. */ static __always_inline void update_lru_sizes(struct lruvec *lruvec, enum lru_list lru, unsigned long *nr_zone_taken) { int zid; for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_zone_taken[zid]) continue; update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); } } /* * Isolating page from the lruvec to fill in @dst list by nr_to_scan times. * * lruvec->lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * * For pagecache intensive workloads, this function is the hottest * spot in the kernel (apart from copy_*_user functions). * * Lru_lock must be held before calling this function. * * @nr_to_scan: The number of eligible pages to look through on the list. * @lruvec: The LRU vector to pull pages from. * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. */ static unsigned long isolate_lru_folios(unsigned long nr_to_scan, struct lruvec *lruvec, struct list_head *dst, unsigned long *nr_scanned, struct scan_control *sc, enum lru_list lru) { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; LIST_HEAD(folios_skipped); total_scan = 0; scan = 0; while (scan < nr_to_scan && !list_empty(src)) { struct list_head *move_to = src; struct folio *folio; folio = lru_to_folio(src); prefetchw_prev_lru_folio(folio, src, flags); nr_pages = folio_nr_pages(folio); total_scan += nr_pages; if (folio_zonenum(folio) > sc->reclaim_idx) { nr_skipped[folio_zonenum(folio)] += nr_pages; move_to = &folios_skipped; goto move; } /* * Do not count skipped folios because that makes the function * return with no isolated folios if the LRU mostly contains * ineligible folios. This causes the VM to not reclaim any * folios, triggering a premature OOM. * Account all pages in a folio. */ scan += nr_pages; if (!folio_test_lru(folio)) goto move; if (!sc->may_unmap && folio_mapped(folio)) goto move; /* * Be careful not to clear the lru flag until after we're * sure the folio is not being freed elsewhere -- the * folio release code relies on it. */ if (unlikely(!folio_try_get(folio))) goto move; if (!folio_test_clear_lru(folio)) { /* Another thread is already isolating this folio */ folio_put(folio); goto move; } nr_taken += nr_pages; nr_zone_taken[folio_zonenum(folio)] += nr_pages; move_to = dst; move: list_move(&folio->lru, move_to); } /* * Splice any skipped folios to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX * scanning would soon rescan the same folios to skip and waste lots * of cpu cycles. */ if (!list_empty(&folios_skipped)) { int zid; list_splice(&folios_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); skipped += nr_skipped[zid]; } } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, total_scan, skipped, nr_taken, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } /** * folio_isolate_lru() - Try to isolate a folio from its LRU list. * @folio: Folio to isolate from its LRU list. * * Isolate a @folio from an LRU list and adjust the vmstat statistic * corresponding to whatever LRU list the folio was on. * * The folio will have its LRU flag cleared. If it was found on the * active list, it will have the Active flag set. If it was found on the * unevictable list, it will have the Unevictable flag set. These flags * may need to be cleared by the caller before letting the page go. * * Context: * * (1) Must be called with an elevated refcount on the folio. This is a * fundamental difference from isolate_lru_folios() (which is called * without a stable reference). * (2) The lru_lock must not be held. * (3) Interrupts must be enabled. * * Return: true if the folio was removed from an LRU list. * false if the folio was not on an LRU list. */ bool folio_isolate_lru(struct folio *folio) { bool ret = false; VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio); if (folio_test_clear_lru(folio)) { struct lruvec *lruvec; folio_get(folio); lruvec = folio_lruvec_lock_irq(folio); lruvec_del_folio(lruvec, folio); unlock_page_lruvec_irq(lruvec); ret = true; } return ret; } /* * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and * then get rescheduled. When there are massive number of tasks doing page * allocation, such sleeping direct reclaimers may keep piling up on each CPU, * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ static bool too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; bool too_many; if (current_is_kswapd()) return false; if (!writeback_throttling_sane(sc)) return false; if (file) { inactive = node_page_state(pgdat, NR_INACTIVE_FILE); isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { inactive = node_page_state(pgdat, NR_INACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ if (gfp_has_io_fs(sc->gfp_mask)) inactive >>= 3; too_many = isolated > inactive; /* Wake up tasks throttled due to too_many_isolated. */ if (!too_many) wake_throttle_isolated(pgdat); return too_many; } /* * move_folios_to_lru() moves folios from private @list to appropriate LRU list. * * Returns the number of pages moved to the given lruvec. */ static unsigned int move_folios_to_lru(struct lruvec *lruvec, struct list_head *list) { int nr_pages, nr_moved = 0; struct folio_batch free_folios; folio_batch_init(&free_folios); while (!list_empty(list)) { struct folio *folio = lru_to_folio(list); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { spin_unlock_irq(&lruvec->lru_lock); folio_putback_lru(folio); spin_lock_irq(&lruvec->lru_lock); continue; } /* * The folio_set_lru needs to be kept here for list integrity. * Otherwise: * #0 move_folios_to_lru #1 release_pages * if (!folio_put_testzero()) * if (folio_put_testzero()) * !lru //skip lru_lock * folio_set_lru() * list_add(&folio->lru,) * list_add(&folio->lru,) */ folio_set_lru(folio); if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); folio_undo_large_rmappable(folio); if (folio_batch_add(&free_folios, folio) == 0) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); free_unref_folios(&free_folios); spin_lock_irq(&lruvec->lru_lock); } continue; } /* * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); lruvec_add_folio(lruvec, folio); nr_pages = folio_nr_pages(folio); nr_moved += nr_pages; if (folio_test_active(folio)) workingset_age_nonresident(lruvec, nr_pages); } if (free_folios.nr) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); free_unref_folios(&free_folios); spin_lock_irq(&lruvec->lru_lock); } return nr_moved; } /* * If a kernel thread (such as nfsd for loop-back mounts) services a backing * device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case * we should not throttle. Otherwise it is safe to do so. */ static int current_may_throttle(void) { return !(current->flags & PF_LOCAL_THROTTLE); } /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { LIST_HEAD(folio_list); unsigned long nr_scanned; unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { if (stalled) return 0; /* wait a bit for the reclaimer. */ stalled = true; reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) return SWAP_CLUSTER_MAX; } lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &folio_list, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); item = PGSCAN_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); __count_vm_events(PGSCAN_ANON + file, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); if (nr_taken == 0) return 0; nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false); spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &folio_list); __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(), stat.nr_demoted); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); spin_unlock_irq(&lruvec->lru_lock); lru_note_cost(lruvec, file, stat.nr_pageout, nr_scanned - nr_reclaimed); /* * If dirty folios are scanned that are not queued for IO, it * implies that flushers are not doing their job. This can * happen when memory pressure pushes dirty folios to the end of * the LRU before the dirty limits are breached and the dirty * data has expired. It can also happen when the proportion of * dirty folios grows not through writes but through memory * pressure reclaiming all the clean cache. And in some cases, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ if (stat.nr_unqueued_dirty == nr_taken) { wakeup_flusher_threads(WB_REASON_VMSCAN); /* * For cgroupv1 dirty throttling is achieved by waking up * the kernel flusher here and later waiting on folios * which are in writeback to finish (see shrink_folio_list()). * * Flusher may not be able to issue writeback quickly * enough for cgroupv1 writeback throttling to work * on a large system. */ if (!writeback_throttling_sane(sc)) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr.writeback += stat.nr_writeback; sc->nr.immediate += stat.nr_immediate; sc->nr.taken += nr_taken; if (file) sc->nr.file_taken += nr_taken; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_scanned, nr_reclaimed, &stat, sc->priority, file); return nr_reclaimed; } /* * shrink_active_list() moves folios from the active LRU to the inactive LRU. * * We move them the other way if the folio is referenced by one or more * processes. * * If the folios are mostly unmapped, the processing is fast and it is * appropriate to hold lru_lock across the whole operation. But if * the folios are mapped, the processing is slow (folio_referenced()), so * we should drop lru_lock around each folio. It's impossible to balance * this, so instead we remove the folios from the LRU while processing them. * It is safe to rely on the active flag against the non-LRU folios in here * because nobody will play with that bit on a non-LRU folio. * * The downside is that we have to touch folio->_refcount against each folio. * But we had to alter folio->flags anyway. */ static void shrink_active_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { unsigned long nr_taken; unsigned long nr_scanned; unsigned long vm_flags; LIST_HEAD(l_hold); /* The folios which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; bool file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); if (!cgroup_reclaim(sc)) __count_vm_events(PGREFILL, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); while (!list_empty(&l_hold)) { struct folio *folio; cond_resched(); folio = lru_to_folio(&l_hold); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { folio_putback_lru(folio); continue; } if (unlikely(buffer_heads_over_limit)) { if (folio_needs_release(folio) && folio_trylock(folio)) { filemap_release_folio(folio, 0); folio_unlock(folio); } } /* Referenced or rmap lock contention: rotate */ if (folio_referenced(folio, 0, sc->target_mem_cgroup, &vm_flags) != 0) { /* * Identify referenced, file-backed active folios and * give them one more trip around the active list. So * that executable code get better chances to stay in * memory under moderate memory pressure. Anon folios * are not likely to be evicted by use-once streaming * IO, plus JVM can create lots of anon VM_EXEC folios, * so we ignore them here. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) { nr_rotated += folio_nr_pages(folio); list_add(&folio->lru, &l_active); continue; } } folio_clear_active(folio); /* we are de-activating */ folio_set_workingset(folio); list_add(&folio->lru, &l_inactive); } /* * Move folios back to the lru list. */ spin_lock_irq(&lruvec->lru_lock); nr_activate = move_folios_to_lru(lruvec, &l_active); nr_deactivate = move_folios_to_lru(lruvec, &l_inactive); __count_vm_events(PGDEACTIVATE, nr_deactivate); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&lruvec->lru_lock); if (nr_rotated) lru_note_cost(lruvec, file, 0, nr_rotated); trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, nr_deactivate, nr_rotated, sc->priority, file); } static unsigned int reclaim_folio_list(struct list_head *folio_list, struct pglist_data *pgdat) { struct reclaim_stat dummy_stat; unsigned int nr_reclaimed; struct folio *folio; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .no_demotion = 1, }; nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &dummy_stat, true); while (!list_empty(folio_list)) { folio = lru_to_folio(folio_list); list_del(&folio->lru); folio_putback_lru(folio); } return nr_reclaimed; } unsigned long reclaim_pages(struct list_head *folio_list) { int nid; unsigned int nr_reclaimed = 0; LIST_HEAD(node_folio_list); unsigned int noreclaim_flag; if (list_empty(folio_list)) return nr_reclaimed; noreclaim_flag = memalloc_noreclaim_save(); nid = folio_nid(lru_to_folio(folio_list)); do { struct folio *folio = lru_to_folio(folio_list); if (nid == folio_nid(folio)) { folio_clear_active(folio); list_move(&folio->lru, &node_folio_list); continue; } nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); nid = folio_nid(lru_to_folio(folio_list)); } while (!list_empty(folio_list)); nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); memalloc_noreclaim_restore(noreclaim_flag); return nr_reclaimed; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) shrink_active_list(nr_to_scan, lruvec, sc, lru); else sc->skipped_deactivate = 1; return 0; } return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } /* * The inactive anon list should be small enough that the VM never has * to do too much work. * * The inactive file list should be small enough to leave most memory * to the established workingset on the scan-resistant active list, * but large enough to avoid thrashing the aggregate readahead window. * * Both inactive lists should also be large enough that each inactive * folio has a chance to be referenced again before it is reclaimed. * * If that fails and refaulting is observed, the inactive list grows. * * The inactive_ratio is the target ratio of ACTIVE to INACTIVE folios * on this LRU, maintained by the pageout code. An inactive_ratio * of 3 means 3:1 or 25% of the folios are kept on the inactive list. * * total target max * memory ratio inactive * ------------------------------------- * 10MB 1 5MB * 100MB 1 50MB * 1GB 3 250MB * 10GB 10 0.9GB * 100GB 31 3GB * 1TB 101 10GB * 10TB 320 32GB */ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; unsigned long gb; inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; } enum scan_balance { SCAN_EQUAL, SCAN_FRACT, SCAN_ANON, SCAN_FILE, }; static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc) { unsigned long file; struct lruvec *target_lruvec; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); /* * Flush the memory cgroup stats in rate-limited way as we don't need * most accurate stats here. We may switch to regular stats flushing * in the future once it is cheap enough. */ mem_cgroup_flush_stats_ratelimited(sc->target_mem_cgroup); /* * Determine the scan balance between anon and file LRUs. */ spin_lock_irq(&target_lruvec->lru_lock); sc->anon_cost = target_lruvec->anon_cost; sc->file_cost = target_lruvec->file_cost; spin_unlock_irq(&target_lruvec->lru_lock); /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. */ if (!sc->force_deactivate) { unsigned long refaults; /* * When refaults are being observed, it means a new * workingset is being established. Deactivate to get * rid of any stale active pages quickly. */ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); if (refaults != target_lruvec->refaults[WORKINGSET_ANON] || inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) sc->may_deactivate |= DEACTIVATE_ANON; else sc->may_deactivate &= ~DEACTIVATE_ANON; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); if (refaults != target_lruvec->refaults[WORKINGSET_FILE] || inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) sc->may_deactivate |= DEACTIVATE_FILE; else sc->may_deactivate &= ~DEACTIVATE_FILE; } else sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; /* * If we have plenty of inactive file pages that aren't * thrashing, try to reclaim those first before touching * anonymous pages. */ file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE) && !sc->no_cache_trim_mode) sc->cache_trim_mode = 1; else sc->cache_trim_mode = 0; /* * Prevent the reclaimer from falling into the cache trap: as * cache pages start out inactive, every cache fault will tip * the scan balance towards the file LRU. And as the file LRU * shrinks, so does the window for rotation from references. * This means we have a runaway feedback loop where a tiny * thrashing file LRU becomes infinitely more attractive than * anon pages. Try to detect this based on file LRU size. */ if (!cgroup_reclaim(sc)) { unsigned long total_high_wmark = 0; unsigned long free, anon; int z; free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); file = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_FILE); for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; total_high_wmark += high_wmark_pages(zone); } /* * Consider anon: if that's low too, this isn't a * runaway file reclaim problem, but rather just * extreme pressure. Reclaim as per usual then. */ anon = node_page_state(pgdat, NR_INACTIVE_ANON); sc->file_is_tiny = file + free <= total_high_wmark && !(sc->may_deactivate & DEACTIVATE_ANON) && anon >> sc->priority; } } /* * Determine how aggressively the anon and file LRU lists should be * scanned. * * nr[0] = anon inactive folios to scan; nr[1] = anon active folios to scan * nr[2] = file inactive folios to scan; nr[3] = file active folios to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); unsigned long anon_cost, file_cost, total_cost; int swappiness = sc_swappiness(sc, memcg); u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ enum scan_balance scan_balance; unsigned long ap, fp; enum lru_list lru; /* If we have no swap space, do not bother scanning anon folios. */ if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) { scan_balance = SCAN_FILE; goto out; } /* * Global reclaim will swap to prevent OOM even with no * swappiness, but memcg users want to use this knob to * disable swapping for individual groups completely when * using the memory controller's swap limit feature would be * too expensive. */ if (cgroup_reclaim(sc) && !swappiness) { scan_balance = SCAN_FILE; goto out; } /* * Do not apply any pressure balancing cleverness when the * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ if (!sc->priority && swappiness) { scan_balance = SCAN_EQUAL; goto out; } /* * If the system is almost out of file pages, force-scan anon. */ if (sc->file_is_tiny) { scan_balance = SCAN_ANON; goto out; } /* * If there is enough inactive page cache, we do not reclaim * anything from the anonymous working right now. */ if (sc->cache_trim_mode) { scan_balance = SCAN_FILE; goto out; } scan_balance = SCAN_FRACT; /* * Calculate the pressure balance between anon and file pages. * * The amount of pressure we put on each LRU is inversely * proportional to the cost of reclaiming each list, as * determined by the share of pages that are refaulting, times * the relative IO cost of bringing back a swapped out * anonymous page vs reloading a filesystem page (swappiness). * * Although we limit that influence to ensure no list gets * left behind completely: at least a third of the pressure is * applied, before swappiness. * * With swappiness at 100, anon and file have equal IO cost. */ total_cost = sc->anon_cost + sc->file_cost; anon_cost = total_cost + sc->anon_cost; file_cost = total_cost + sc->file_cost; total_cost = anon_cost + file_cost; ap = swappiness * (total_cost + 1); ap /= anon_cost + 1; fp = (MAX_SWAPPINESS - swappiness) * (total_cost + 1); fp /= file_cost + 1; fraction[0] = ap; fraction[1] = fp; denominator = ap + fp; out: for_each_evictable_lru(lru) { bool file = is_file_lru(lru); unsigned long lruvec_size; unsigned long low, min; unsigned long scan; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low); if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min * setting. * * This is important, as otherwise scanning aggression * becomes extremely binary -- from nothing as we * approach the memory protection threshold, to totally * nominal as we exceed it. This results in requiring * setting extremely liberal protection thresholds. It * also means we simply get no protection at all if we * set it too low, which is not ideal. * * If there is any protection in place, we reduce scan * pressure by how much of the total memory used is * within protection thresholds. * * There is one special case: in the first reclaim pass, * we skip over all groups that are within their low * protection. If that fails to reclaim enough pages to * satisfy the reclaim goal, we come back and override * the best-effort low protection. However, we still * ideally want to honor how well-behaved groups are in * that case instead of simply punishing them all * equally. As such, we reclaim them based on how much * memory they are using, reducing the scan pressure * again by how much of the total memory used is under * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); unsigned long protection; /* memory.low scaling, make sure we retry before OOM */ if (!sc->memcg_low_reclaim && low > min) { protection = low; sc->memcg_low_skipped = 1; } else { protection = min; } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); scan = lruvec_size - lruvec_size * protection / (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep * reclaim moving forwards, avoiding decrementing * sc->priority further than desirable. */ scan = max(scan, SWAP_CLUSTER_MAX); } else { scan = lruvec_size; } scan >>= sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: /* Scan lists relative to size */ break; case SCAN_FRACT: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. * Make sure we don't miss the last page on * the offlined memory cgroups because of a * round-off error. */ scan = mem_cgroup_online(memcg) ? div64_u64(scan * fraction[file], denominator) : DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) scan = 0; break; default: /* Look ma, no brain */ BUG(); } nr[lru] = scan; } } /* * Anonymous LRU management is a waste if there is * ultimately no way to reclaim the memory. */ static bool can_age_anon_pages(struct pglist_data *pgdat, struct scan_control *sc) { /* Aging the anon LRU is valuable if swap is present: */ if (total_swap_pages > 0) return true; /* Also valuable if anon pages can be demoted: */ return can_demote(pgdat->node_id, sc); } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_likely(&lru_gen_caps[cap]) #else DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_unlikely(&lru_gen_caps[cap]) #endif static bool should_walk_mmu(void) { return arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK); } static bool should_clear_pmd_young(void) { return arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG); } /****************************************************************************** * shorthand helpers ******************************************************************************/ #define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) #define DEFINE_MAX_SEQ(lruvec) \ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq) #define DEFINE_MIN_SEQ(lruvec) \ unsigned long min_seq[ANON_AND_FILE] = { \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_ANON]), \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]), \ } #define for_each_gen_type_zone(gen, type, zone) \ for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++) #define get_memcg_gen(seq) ((seq) % MEMCG_NR_GENS) #define get_memcg_bin(bin) ((bin) % MEMCG_NR_BINS) static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid) { struct pglist_data *pgdat = NODE_DATA(nid); #ifdef CONFIG_MEMCG if (memcg) { struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec; /* see the comment in mem_cgroup_lruvec() */ if (!lruvec->pgdat) lruvec->pgdat = pgdat; return lruvec; } #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &pgdat->__lruvec; } static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc) { struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); if (!sc->may_swap) return 0; if (!can_demote(pgdat->node_id, sc) && mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) return 0; return sc_swappiness(sc, memcg); } static int get_nr_gens(struct lruvec *lruvec, int type) { return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1; } static bool __maybe_unused seq_is_valid(struct lruvec *lruvec) { /* see the comment on lru_gen_folio */ return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS && get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) && get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS; } /****************************************************************************** * Bloom filters ******************************************************************************/ /* * Bloom filters with m=1<<15, k=2 and the false positive rates of ~1/5 when * n=10,000 and ~1/2 when n=20,000, where, conventionally, m is the number of * bits in a bitmap, k is the number of hash functions and n is the number of * inserted items. * * Page table walkers use one of the two filters to reduce their search space. * To get rid of non-leaf entries that no longer have enough leaf entries, the * aging uses the double-buffering technique to flip to the other filter each * time it produces a new generation. For non-leaf entries that have enough * leaf entries, the aging carries them over to the next generation in * walk_pmd_range(); the eviction also report them when walking the rmap * in lru_gen_look_around(). * * For future optimizations: * 1. It's not necessary to keep both filters all the time. The spare one can be * freed after the RCU grace period and reallocated if needed again. * 2. And when reallocating, it's worth scaling its size according to the number * of inserted entries in the other filter, to reduce the memory overhead on * small systems and false positives on large systems. * 3. Jenkins' hash function is an alternative to Knuth's. */ #define BLOOM_FILTER_SHIFT 15 static inline int filter_gen_from_seq(unsigned long seq) { return seq % NR_BLOOM_FILTERS; } static void get_item_key(void *item, int *key) { u32 hash = hash_ptr(item, BLOOM_FILTER_SHIFT * 2); BUILD_BUG_ON(BLOOM_FILTER_SHIFT * 2 > BITS_PER_TYPE(u32)); key[0] = hash & (BIT(BLOOM_FILTER_SHIFT) - 1); key[1] = hash >> BLOOM_FILTER_SHIFT; } static bool test_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return true; get_item_key(item, key); return test_bit(key[0], filter) && test_bit(key[1], filter); } static void update_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return; get_item_key(item, key); if (!test_bit(key[0], filter)) set_bit(key[0], filter); if (!test_bit(key[1], filter)) set_bit(key[1], filter); } static void reset_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq) { unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = mm_state->filters[gen]; if (filter) { bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT)); return; } filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); WRITE_ONCE(mm_state->filters[gen], filter); } /****************************************************************************** * mm_struct list ******************************************************************************/ #ifdef CONFIG_LRU_GEN_WALKS_MMU static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { static struct lru_gen_mm_list mm_list = { .fifo = LIST_HEAD_INIT(mm_list.fifo), .lock = __SPIN_LOCK_UNLOCKED(mm_list.lock), }; #ifdef CONFIG_MEMCG if (memcg) return &memcg->mm_list; #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &mm_list; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return &lruvec->mm_state; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { int key; struct mm_struct *mm; struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list); key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap); if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap)) return NULL; clear_bit(key, &mm->lru_gen.bitmap); return mmget_not_zero(mm) ? mm : NULL; } void lru_gen_add_mm(struct mm_struct *mm) { int nid; struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(!list_empty(&mm->lru_gen.list)); #ifdef CONFIG_MEMCG VM_WARN_ON_ONCE(mm->lru_gen.memcg); mm->lru_gen.memcg = memcg; #endif spin_lock(&mm_list->lock); for_each_node_state(nid, N_MEMORY) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* the first addition since the last iteration */ if (mm_state->tail == &mm_list->fifo) mm_state->tail = &mm->lru_gen.list; } list_add_tail(&mm->lru_gen.list, &mm_list->fifo); spin_unlock(&mm_list->lock); } void lru_gen_del_mm(struct mm_struct *mm) { int nid; struct lru_gen_mm_list *mm_list; struct mem_cgroup *memcg = NULL; if (list_empty(&mm->lru_gen.list)) return; #ifdef CONFIG_MEMCG memcg = mm->lru_gen.memcg; #endif mm_list = get_mm_list(memcg); spin_lock(&mm_list->lock); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* where the current iteration continues after */ if (mm_state->head == &mm->lru_gen.list) mm_state->head = mm_state->head->prev; /* where the last iteration ended before */ if (mm_state->tail == &mm->lru_gen.list) mm_state->tail = mm_state->tail->next; } list_del_init(&mm->lru_gen.list); spin_unlock(&mm_list->lock); #ifdef CONFIG_MEMCG mem_cgroup_put(mm->lru_gen.memcg); mm->lru_gen.memcg = NULL; #endif } #ifdef CONFIG_MEMCG void lru_gen_migrate_mm(struct mm_struct *mm) { struct mem_cgroup *memcg; struct task_struct *task = rcu_dereference_protected(mm->owner, true); VM_WARN_ON_ONCE(task->mm != mm); lockdep_assert_held(&task->alloc_lock); /* for mm_update_next_owner() */ if (mem_cgroup_disabled()) return; /* migration can happen before addition */ if (!mm->lru_gen.memcg) return; rcu_read_lock(); memcg = mem_cgroup_from_task(task); rcu_read_unlock(); if (memcg == mm->lru_gen.memcg) return; VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list)); lru_gen_del_mm(mm); lru_gen_add_mm(mm); } #endif #else /* !CONFIG_LRU_GEN_WALKS_MMU */ static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { return NULL; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return NULL; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { return NULL; } #endif static void reset_mm_stats(struct lru_gen_mm_walk *walk, bool last) { int i; int hist; struct lruvec *lruvec = walk->lruvec; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock); hist = lru_hist_from_seq(walk->seq); for (i = 0; i < NR_MM_STATS; i++) { WRITE_ONCE(mm_state->stats[hist][i], mm_state->stats[hist][i] + walk->mm_stats[i]); walk->mm_stats[i] = 0; } if (NR_HIST_GENS > 1 && last) { hist = lru_hist_from_seq(walk->seq + 1); for (i = 0; i < NR_MM_STATS; i++) WRITE_ONCE(mm_state->stats[hist][i], 0); } } static bool iterate_mm_list(struct lru_gen_mm_walk *walk, struct mm_struct **iter) { bool first = false; bool last = false; struct mm_struct *mm = NULL; struct lruvec *lruvec = walk->lruvec; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* * mm_state->seq is incremented after each iteration of mm_list. There * are three interesting cases for this page table walker: * 1. It tries to start a new iteration with a stale max_seq: there is * nothing left to do. * 2. It started the next iteration: it needs to reset the Bloom filter * so that a fresh set of PTE tables can be recorded. * 3. It ended the current iteration: it needs to reset the mm stats * counters and tell its caller to increment max_seq. */ spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->seq); if (walk->seq <= mm_state->seq) goto done; if (!mm_state->head) mm_state->head = &mm_list->fifo; if (mm_state->head == &mm_list->fifo) first = true; do { mm_state->head = mm_state->head->next; if (mm_state->head == &mm_list->fifo) { WRITE_ONCE(mm_state->seq, mm_state->seq + 1); last = true; break; } /* force scan for those added after the last iteration */ if (!mm_state->tail || mm_state->tail == mm_state->head) { mm_state->tail = mm_state->head->next; walk->force_scan = true; } } while (!(mm = get_next_mm(walk))); done: if (*iter || last) reset_mm_stats(walk, last); spin_unlock(&mm_list->lock); if (mm && first) reset_bloom_filter(mm_state, walk->seq + 1); if (*iter) mmput_async(*iter); *iter = mm; return last; } static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long seq) { bool success = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < seq); if (seq > mm_state->seq) { mm_state->head = NULL; mm_state->tail = NULL; WRITE_ONCE(mm_state->seq, mm_state->seq + 1); success = true; } spin_unlock(&mm_list->lock); return success; } /****************************************************************************** * PID controller ******************************************************************************/ /* * A feedback loop based on Proportional-Integral-Derivative (PID) controller. * * The P term is refaulted/(evicted+protected) from a tier in the generation * currently being evicted; the I term is the exponential moving average of the * P term over the generations previously evicted, using the smoothing factor * 1/2; the D term isn't supported. * * The setpoint (SP) is always the first tier of one type; the process variable * (PV) is either any tier of the other type or any other tier of the same * type. * * The error is the difference between the SP and the PV; the correction is to * turn off protection when SP>PV or turn on protection when SP<PV. * * For future optimizations: * 1. The D term may discount the other two terms over time so that long-lived * generations can resist stale information. */ struct ctrl_pos { unsigned long refaulted; unsigned long total; int gain; }; static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain, struct ctrl_pos *pos) { struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); pos->refaulted = lrugen->avg_refaulted[type][tier] + atomic_long_read(&lrugen->refaulted[hist][type][tier]); pos->total = lrugen->avg_total[type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) pos->total += lrugen->protected[hist][type][tier - 1]; pos->gain = gain; } static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover) { int hist, tier; struct lru_gen_folio *lrugen = &lruvec->lrugen; bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1; unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1; lockdep_assert_held(&lruvec->lru_lock); if (!carryover && !clear) return; hist = lru_hist_from_seq(seq); for (tier = 0; tier < MAX_NR_TIERS; tier++) { if (carryover) { unsigned long sum; sum = lrugen->avg_refaulted[type][tier] + atomic_long_read(&lrugen->refaulted[hist][type][tier]); WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2); sum = lrugen->avg_total[type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) sum += lrugen->protected[hist][type][tier - 1]; WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2); } if (clear) { atomic_long_set(&lrugen->refaulted[hist][type][tier], 0); atomic_long_set(&lrugen->evicted[hist][type][tier], 0); if (tier) WRITE_ONCE(lrugen->protected[hist][type][tier - 1], 0); } } } static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv) { /* * Return true if the PV has a limited number of refaults or a lower * refaulted/total than the SP. */ return pv->refaulted < MIN_LRU_BATCH || pv->refaulted * (sp->total + MIN_LRU_BATCH) * sp->gain <= (sp->refaulted + 1) * pv->total * pv->gain; } /****************************************************************************** * the aging ******************************************************************************/ /* promote pages accessed through page tables */ static int folio_update_gen(struct folio *folio, int gen) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(!rcu_read_lock_held()); do { /* lru_gen_del_folio() has isolated this page? */ if (!(old_flags & LRU_GEN_MASK)) { /* for shrink_folio_list() */ new_flags = old_flags | BIT(PG_referenced); continue; } new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); new_flags |= (gen + 1UL) << LRU_GEN_PGOFF; } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } /* protect pages accessed multiple times through file descriptors */ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int type = folio_is_file_lru(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE_FOLIO(!(old_flags & LRU_GEN_MASK), folio); do { new_gen = ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; /* folio_update_gen() has promoted this page? */ if (new_gen >= 0 && new_gen != old_gen) return new_gen; new_gen = (old_gen + 1) % MAX_NR_GENS; new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF; /* for folio_end_writeback() */ if (reclaiming) new_flags |= BIT(PG_reclaim); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); lru_gen_update_size(lruvec, folio, old_gen, new_gen); return new_gen; } static void update_batch_size(struct lru_gen_mm_walk *walk, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE(old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen >= MAX_NR_GENS); walk->batched++; walk->nr_pages[old_gen][type][zone] -= delta; walk->nr_pages[new_gen][type][zone] += delta; } static void reset_batch_size(struct lru_gen_mm_walk *walk) { int gen, type, zone; struct lruvec *lruvec = walk->lruvec; struct lru_gen_folio *lrugen = &lruvec->lrugen; walk->batched = 0; for_each_gen_type_zone(gen, type, zone) { enum lru_list lru = type * LRU_INACTIVE_FILE; int delta = walk->nr_pages[gen][type][zone]; if (!delta) continue; walk->nr_pages[gen][type][zone] = 0; WRITE_ONCE(lrugen->nr_pages[gen][type][zone], lrugen->nr_pages[gen][type][zone] + delta); if (lru_gen_is_active(lruvec, gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); } } static int should_skip_vma(unsigned long start, unsigned long end, struct mm_walk *args) { struct address_space *mapping; struct vm_area_struct *vma = args->vma; struct lru_gen_mm_walk *walk = args->private; if (!vma_is_accessible(vma)) return true; if (is_vm_hugetlb_page(vma)) return true; if (!vma_has_recency(vma)) return true; if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) return true; if (vma == get_gate_vma(vma->vm_mm)) return true; if (vma_is_anonymous(vma)) return !walk->can_swap; if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping)) return true; mapping = vma->vm_file->f_mapping; if (mapping_unevictable(mapping)) return true; if (shmem_mapping(mapping)) return !walk->can_swap; /* to exclude special mappings like dax, etc. */ return !mapping->a_ops->read_folio; } /* * Some userspace memory allocators map many single-page VMAs. Instead of * returning back to the PGD table for each of such VMAs, finish an entire PMD * table to reduce zigzags and improve cache performance. */ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk *args, unsigned long *vm_start, unsigned long *vm_end) { unsigned long start = round_up(*vm_end, size); unsigned long end = (start | ~mask) + 1; VMA_ITERATOR(vmi, args->mm, start); VM_WARN_ON_ONCE(mask & size); VM_WARN_ON_ONCE((start & mask) != (*vm_start & mask)); for_each_vma(vmi, args->vma) { if (end && end <= args->vma->vm_start) return false; if (should_skip_vma(args->vma->vm_start, args->vma->vm_end, args)) continue; *vm_start = max(start, args->vma->vm_start); *vm_end = min(end - 1, args->vma->vm_end - 1) + 1; return true; } return false; } static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr) { unsigned long pfn = pte_pfn(pte); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pte_present(pte) || is_zero_pfn(pfn)) return -1; if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; return pfn; } static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr) { unsigned long pfn = pmd_pfn(pmd); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pmd_present(pmd) || is_huge_zero_pmd(pmd)) return -1; if (WARN_ON_ONCE(pmd_devmap(pmd))) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; return pfn; } static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, struct pglist_data *pgdat, bool can_swap) { struct folio *folio; /* try to avoid unnecessary memory loads */ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) return NULL; folio = pfn_folio(pfn); if (folio_nid(folio) != pgdat->node_id) return NULL; if (folio_memcg_rcu(folio) != memcg) return NULL; /* file VMAs can contain anon pages from COW */ if (!folio_is_file_lru(folio) && !can_swap) return NULL; return folio; } static bool suitable_to_scan(int total, int young) { int n = clamp_t(int, cache_line_size() / sizeof(pte_t), 2, 8); /* suitable if the average number of young PTEs per cacheline is >=1 */ return young * n >= total; } static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pte_t *pte; spinlock_t *ptl; unsigned long addr; int total = 0; int young = 0; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int old_gen, new_gen = lru_gen_from_seq(max_seq); pte = pte_offset_map_nolock(args->mm, pmd, start & PMD_MASK, &ptl); if (!pte) return false; if (!spin_trylock(ptl)) { pte_unmap(pte); return false; } arch_enter_lazy_mmu_mode(); restart: for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; struct folio *folio; pte_t ptent = ptep_get(pte + i); total++; walk->mm_stats[MM_LEAF_TOTAL]++; pfn = get_pte_pfn(ptent, args->vma, addr); if (pfn == -1) continue; if (!pte_young(ptent)) { walk->mm_stats[MM_LEAF_OLD]++; continue; } folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) continue; if (!ptep_test_and_clear_young(args->vma, addr, pte + i)) VM_WARN_ON_ONCE(true); young++; walk->mm_stats[MM_LEAF_YOUNG]++; if (pte_dirty(ptent) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); } if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end)) goto restart; arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte, ptl); return suitable_to_scan(total, young); } static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area_struct *vma, struct mm_walk *args, unsigned long *bitmap, unsigned long *first) { int i; pmd_t *pmd; spinlock_t *ptl; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int old_gen, new_gen = lru_gen_from_seq(max_seq); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* try to batch at most 1+MIN_LRU_BATCH+1 entries */ if (*first == -1) { *first = addr; bitmap_zero(bitmap, MIN_LRU_BATCH); return; } i = addr == -1 ? 0 : pmd_index(addr) - pmd_index(*first); if (i && i <= MIN_LRU_BATCH) { __set_bit(i - 1, bitmap); return; } pmd = pmd_offset(pud, *first); ptl = pmd_lockptr(args->mm, pmd); if (!spin_trylock(ptl)) goto done; arch_enter_lazy_mmu_mode(); do { unsigned long pfn; struct folio *folio; /* don't round down the first address */ addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first; pfn = get_pmd_pfn(pmd[i], vma, addr); if (pfn == -1) goto next; if (!pmd_trans_huge(pmd[i])) { if (!walk->force_scan && should_clear_pmd_young()) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; } folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) goto next; if (!pmdp_test_and_clear_young(vma, addr, pmd + i)) goto next; walk->mm_stats[MM_LEAF_YOUNG]++; if (pmd_dirty(pmd[i]) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); next: i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1; } while (i <= MIN_LRU_BATCH); arch_leave_lazy_mmu_mode(); spin_unlock(ptl); done: *first = -1; } static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pmd_t *pmd; unsigned long next; unsigned long addr; struct vm_area_struct *vma; DECLARE_BITMAP(bitmap, MIN_LRU_BATCH); unsigned long first = -1; struct lru_gen_mm_walk *walk = args->private; struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* * Finish an entire PMD in two passes: the first only reaches to PTE * tables to avoid taking the PMD lock; the second, if necessary, takes * the PMD lock to clear the accessed bit in PMD entries. */ pmd = pmd_offset(pud, start & PUD_MASK); restart: /* walk_pte_range() may call get_next_vma() */ vma = args->vma; for (i = pmd_index(start), addr = start; addr != end; i++, addr = next) { pmd_t val = pmdp_get_lockless(pmd + i); next = pmd_addr_end(addr, end); if (!pmd_present(val) || is_huge_zero_pmd(val)) { walk->mm_stats[MM_LEAF_TOTAL]++; continue; } if (pmd_trans_huge(val)) { unsigned long pfn = pmd_pfn(val); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); walk->mm_stats[MM_LEAF_TOTAL]++; if (!pmd_young(val)) { walk->mm_stats[MM_LEAF_OLD]++; continue; } /* try to avoid unnecessary memory loads */ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); continue; } walk->mm_stats[MM_NONLEAF_TOTAL]++; if (!walk->force_scan && should_clear_pmd_young()) { if (!pmd_young(val)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); } if (!walk->force_scan && !test_bloom_filter(mm_state, walk->seq, pmd + i)) continue; walk->mm_stats[MM_NONLEAF_FOUND]++; if (!walk_pte_range(&val, addr, next, args)) continue; walk->mm_stats[MM_NONLEAF_ADDED]++; /* carry over to the next generation */ update_bloom_filter(mm_state, walk->seq + 1, pmd + i); } walk_pmd_range_locked(pud, -1, vma, args, bitmap, &first); if (i < PTRS_PER_PMD && get_next_vma(PUD_MASK, PMD_SIZE, args, &start, &end)) goto restart; } static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pud_t *pud; unsigned long addr; unsigned long next; struct lru_gen_mm_walk *walk = args->private; VM_WARN_ON_ONCE(p4d_leaf(*p4d)); pud = pud_offset(p4d, start & P4D_MASK); restart: for (i = pud_index(start), addr = start; addr != end; i++, addr = next) { pud_t val = READ_ONCE(pud[i]); next = pud_addr_end(addr, end); if (!pud_present(val) || WARN_ON_ONCE(pud_leaf(val))) continue; walk_pmd_range(&val, addr, next, args); if (need_resched() || walk->batched >= MAX_LRU_BATCH) { end = (addr | ~PUD_MASK) + 1; goto done; } } if (i < PTRS_PER_PUD && get_next_vma(P4D_MASK, PUD_SIZE, args, &start, &end)) goto restart; end = round_up(end, P4D_SIZE); done: if (!end || !args->vma) return 1; walk->next_addr = max(end, args->vma->vm_start); return -EAGAIN; } static void walk_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) { static const struct mm_walk_ops mm_walk_ops = { .test_walk = should_skip_vma, .p4d_entry = walk_pud_range, .walk_lock = PGWALK_RDLOCK, }; int err; struct lruvec *lruvec = walk->lruvec; struct mem_cgroup *memcg = lruvec_memcg(lruvec); walk->next_addr = FIRST_USER_ADDRESS; do { DEFINE_MAX_SEQ(lruvec); err = -EBUSY; /* another thread might have called inc_max_seq() */ if (walk->seq != max_seq) break; /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) break; /* the caller might be holding the lock for write */ if (mmap_read_trylock(mm)) { err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk); mmap_read_unlock(mm); } mem_cgroup_unlock_pages(); if (walk->batched) { spin_lock_irq(&lruvec->lru_lock); reset_batch_size(walk); spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while (err == -EAGAIN); } static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat, bool force_alloc) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; if (pgdat && current_is_kswapd()) { VM_WARN_ON_ONCE(walk); walk = &pgdat->mm_walk; } else if (!walk && force_alloc) { VM_WARN_ON_ONCE(current_is_kswapd()); walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); } current->reclaim_state->mm_walk = walk; return walk; } static void clear_mm_walk(void) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; VM_WARN_ON_ONCE(walk && memchr_inv(walk->nr_pages, 0, sizeof(walk->nr_pages))); VM_WARN_ON_ONCE(walk && memchr_inv(walk->mm_stats, 0, sizeof(walk->mm_stats))); current->reclaim_state->mm_walk = NULL; if (!current_is_kswapd()) kfree(walk); } static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) { int zone; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); if (type == LRU_GEN_ANON && !can_swap) goto done; /* prevent cold/hot inversion if force_scan is true */ for (zone = 0; zone < MAX_NR_ZONES; zone++) { struct list_head *head = &lrugen->folios[old_gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); new_gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]); if (!--remaining) return false; } } done: reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1); return true; } static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap) { int gen, type, zone; bool success = false; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); /* find the oldest populated generation */ for (type = !can_swap; type < ANON_AND_FILE; type++) { while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) { gen = lru_gen_from_seq(min_seq[type]); for (zone = 0; zone < MAX_NR_ZONES; zone++) { if (!list_empty(&lrugen->folios[gen][type][zone])) goto next; } min_seq[type]++; } next: ; } /* see the comment on lru_gen_folio */ if (can_swap) { min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]); min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]); } for (type = !can_swap; type < ANON_AND_FILE; type++) { if (min_seq[type] == lrugen->min_seq[type]) continue; reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], min_seq[type]); success = true; } return success; } static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, bool can_swap, bool force_scan) { bool success; int prev, next; int type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; restart: if (seq < READ_ONCE(lrugen->max_seq)) return false; spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); success = seq == lrugen->max_seq; if (!success) goto unlock; for (type = ANON_AND_FILE - 1; type >= 0; type--) { if (get_nr_gens(lruvec, type) != MAX_NR_GENS) continue; VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap)); if (inc_min_seq(lruvec, type, can_swap)) continue; spin_unlock_irq(&lruvec->lru_lock); cond_resched(); goto restart; } /* * Update the active/inactive LRU sizes for compatibility. Both sides of * the current max_seq need to be covered, since max_seq+1 can overlap * with min_seq[LRU_GEN_ANON] if swapping is constrained. And if they do * overlap, cold/hot inversion happens. */ prev = lru_gen_from_seq(lrugen->max_seq - 1); next = lru_gen_from_seq(lrugen->max_seq + 1); for (type = 0; type < ANON_AND_FILE; type++) { for (zone = 0; zone < MAX_NR_ZONES; zone++) { enum lru_list lru = type * LRU_INACTIVE_FILE; long delta = lrugen->nr_pages[prev][type][zone] - lrugen->nr_pages[next][type][zone]; if (!delta) continue; __update_lru_size(lruvec, lru, zone, delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta); } } for (type = 0; type < ANON_AND_FILE; type++) reset_ctrl_pos(lruvec, type, false); WRITE_ONCE(lrugen->timestamps[next], jiffies); /* make sure preceding modifications appear */ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1); unlock: spin_unlock_irq(&lruvec->lru_lock); return success; } static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq, bool can_swap, bool force_scan) { bool success; struct lru_gen_mm_walk *walk; struct mm_struct *mm = NULL; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(seq > READ_ONCE(lrugen->max_seq)); if (!mm_state) return inc_max_seq(lruvec, seq, can_swap, force_scan); /* see the comment in iterate_mm_list() */ if (seq <= READ_ONCE(mm_state->seq)) return false; /* * If the hardware doesn't automatically set the accessed bit, fallback * to lru_gen_look_around(), which only clears the accessed bit in a * handful of PTEs. Spreading the work out over a period of time usually * is less efficient, but it avoids bursty page faults. */ if (!should_walk_mmu()) { success = iterate_mm_list_nowalk(lruvec, seq); goto done; } walk = set_mm_walk(NULL, true); if (!walk) { success = iterate_mm_list_nowalk(lruvec, seq); goto done; } walk->lruvec = lruvec; walk->seq = seq; walk->can_swap = can_swap; walk->force_scan = force_scan; do { success = iterate_mm_list(walk, &mm); if (mm) walk_mm(mm, walk); } while (mm); done: if (success) { success = inc_max_seq(lruvec, seq, can_swap, force_scan); WARN_ON_ONCE(!success); } return success; } /****************************************************************************** * working set protection ******************************************************************************/ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc) { int priority; unsigned long reclaimable; if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) return; /* * Determine the initial priority based on * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, * where reclaimed_to_scanned_ratio = inactive / total. */ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); /* round down reclaimable and round up sc->nr_to_reclaim */ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); /* * The estimation is based on LRU pages only, so cap it to prevent * overshoots of shrinker objects by large margins. */ sc->priority = clamp(priority, DEF_PRIORITY / 2, DEF_PRIORITY); } static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc) { int gen, type, zone; unsigned long total = 0; bool can_swap = get_swappiness(lruvec, sc); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); for (type = !can_swap; type < ANON_AND_FILE; type++) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) total += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); } } /* whether the size is big enough to be helpful */ return mem_cgroup_online(memcg) ? (total >> sc->priority) : total; } static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc, unsigned long min_ttl) { int gen; unsigned long birth; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MIN_SEQ(lruvec); if (mem_cgroup_below_min(NULL, memcg)) return false; if (!lruvec_is_sizable(lruvec, sc)) return false; /* see the comment on lru_gen_folio */ gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]); birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); return time_is_before_jiffies(birth + min_ttl); } /* to protect the working set of the last N jiffies */ static unsigned long lru_gen_min_ttl __read_mostly; static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl); bool reclaimable = !min_ttl; VM_WARN_ON_ONCE(!current_is_kswapd()); set_initial_priority(pgdat, sc); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); mem_cgroup_calculate_protection(NULL, memcg); if (!reclaimable) reclaimable = lruvec_is_reclaimable(lruvec, sc, min_ttl); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); /* * The main goal is to OOM kill if every generation from all memcgs is * younger than min_ttl. However, another possibility is all memcgs are * either too small or below min. */ if (!reclaimable && mutex_trylock(&oom_lock)) { struct oom_control oc = { .gfp_mask = sc->gfp_mask, }; out_of_memory(&oc); mutex_unlock(&oom_lock); } } /****************************************************************************** * rmap/PT walk feedback ******************************************************************************/ /* * This function exploits spatial locality when shrink_folio_list() walks the * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. If * the scan was done cacheline efficiently, it adds the PMD entry pointing to * the PTE table to the Bloom filter. This forms a feedback loop between the * eviction and the aging. */ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; unsigned long start; unsigned long end; struct lru_gen_mm_walk *walk; int young = 0; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; struct folio *folio = pfn_folio(pvmw->pfn); bool can_swap = !folio_is_file_lru(folio); struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = folio_pgdat(folio); struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); DEFINE_MAX_SEQ(lruvec); int old_gen, new_gen = lru_gen_from_seq(max_seq); lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); if (spin_is_contended(pvmw->ptl)) return; /* exclude special VMAs containing anon pages from COW */ if (vma->vm_flags & VM_SPECIAL) return; /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; start = max(addr & PMD_MASK, vma->vm_start); end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) end = start + MIN_LRU_BATCH * PAGE_SIZE; else if (end - addr < MIN_LRU_BATCH * PAGE_SIZE / 2) start = end - MIN_LRU_BATCH * PAGE_SIZE; else { start = addr - MIN_LRU_BATCH * PAGE_SIZE / 2; end = addr + MIN_LRU_BATCH * PAGE_SIZE / 2; } } /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) return; arch_enter_lazy_mmu_mode(); pte -= (addr - start) / PAGE_SIZE; for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; pte_t ptent = ptep_get(pte + i); pfn = get_pte_pfn(ptent, vma, addr); if (pfn == -1) continue; if (!pte_young(ptent)) continue; folio = get_pfn_folio(pfn, memcg, pgdat, can_swap); if (!folio) continue; if (!ptep_test_and_clear_young(vma, addr, pte + i)) VM_WARN_ON_ONCE(true); young++; if (pte_dirty(ptent) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); if (walk) { old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); continue; } old_gen = folio_lru_gen(folio); if (old_gen < 0) folio_set_referenced(folio); else if (old_gen != new_gen) folio_activate(folio); } arch_leave_lazy_mmu_mode(); mem_cgroup_unlock_pages(); /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) update_bloom_filter(mm_state, max_seq, pvmw->pmd); } /****************************************************************************** * memcg LRU ******************************************************************************/ /* see the comment on MEMCG_NR_GENS */ enum { MEMCG_LRU_NOP, MEMCG_LRU_HEAD, MEMCG_LRU_TAIL, MEMCG_LRU_OLD, MEMCG_LRU_YOUNG, }; static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) { int seg; int old, new; unsigned long flags; int bin = get_random_u32_below(MEMCG_NR_BINS); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irqsave(&pgdat->memcg_lru.lock, flags); VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); seg = 0; new = old = lruvec->lrugen.gen; /* see the comment on MEMCG_NR_GENS */ if (op == MEMCG_LRU_HEAD) seg = MEMCG_LRU_HEAD; else if (op == MEMCG_LRU_TAIL) seg = MEMCG_LRU_TAIL; else if (op == MEMCG_LRU_OLD) new = get_memcg_gen(pgdat->memcg_lru.seq); else if (op == MEMCG_LRU_YOUNG) new = get_memcg_gen(pgdat->memcg_lru.seq + 1); else VM_WARN_ON_ONCE(true); WRITE_ONCE(lruvec->lrugen.seg, seg); WRITE_ONCE(lruvec->lrugen.gen, new); hlist_nulls_del_rcu(&lruvec->lrugen.list); if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) hlist_nulls_add_head_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); else hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); pgdat->memcg_lru.nr_memcgs[old]--; pgdat->memcg_lru.nr_memcgs[new]++; if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); spin_unlock_irqrestore(&pgdat->memcg_lru.lock, flags); } #ifdef CONFIG_MEMCG void lru_gen_online_memcg(struct mem_cgroup *memcg) { int gen; int nid; int bin = get_random_u32_below(MEMCG_NR_BINS); for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list)); gen = get_memcg_gen(pgdat->memcg_lru.seq); lruvec->lrugen.gen = gen; hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); pgdat->memcg_lru.nr_memcgs[gen]++; spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_offline_memcg(struct mem_cgroup *memcg) { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); lru_gen_rotate_memcg(lruvec, MEMCG_LRU_OLD); } } void lru_gen_release_memcg(struct mem_cgroup *memcg) { int gen; int nid; for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); if (hlist_nulls_unhashed(&lruvec->lrugen.list)) goto unlock; gen = lruvec->lrugen.gen; hlist_nulls_del_init_rcu(&lruvec->lrugen.list); pgdat->memcg_lru.nr_memcgs[gen]--; if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); unlock: spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_HEAD) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD); } #endif /* CONFIG_MEMCG */ /****************************************************************************** * the eviction ******************************************************************************/ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc, int tier_idx) { bool success; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); int tier = lru_tier_from_refs(refs); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio); /* unevictable */ if (!folio_evictable(folio)) { success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); folio_set_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, delta); return true; } /* promoted */ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } /* protected */ if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); WRITE_ONCE(lrugen->protected[hist][type][tier - 1], lrugen->protected[hist][type][tier - 1] + delta); return true; } /* ineligible */ if (!folio_test_lru(folio) || zone > sc->reclaim_idx) { gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } /* waiting for writeback */ if (folio_test_locked(folio) || folio_test_writeback(folio) || (type == LRU_GEN_FILE && folio_test_dirty(folio))) { gen = folio_inc_gen(lruvec, folio, true); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } return false; } static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc) { bool success; /* swap constrained */ if (!(sc->gfp_mask & __GFP_IO) && (folio_test_dirty(folio) || (folio_test_anon(folio) && !folio_test_swapcache(folio)))) return false; /* raced with release_pages() */ if (!folio_try_get(folio)) return false; /* raced with another isolation */ if (!folio_test_clear_lru(folio)) { folio_put(folio); return false; } /* see the comment on MAX_NR_TIERS */ if (!folio_test_referenced(folio)) set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); /* for shrink_folio_list() */ folio_clear_reclaim(folio); folio_clear_referenced(folio); success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); return true; } static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, int type, int tier, struct list_head *list) { int i; int gen; enum vm_event_item item; int sorted = 0; int scanned = 0; int isolated = 0; int skipped = 0; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); VM_WARN_ON_ONCE(!list_empty(list)); if (get_nr_gens(lruvec, type) == MIN_NR_GENS) return 0; gen = lru_gen_from_seq(lrugen->min_seq[type]); for (i = MAX_NR_ZONES; i > 0; i--) { LIST_HEAD(moved); int skipped_zone = 0; int zone = (sc->reclaim_idx + i) % MAX_NR_ZONES; struct list_head *head = &lrugen->folios[gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); scanned += delta; if (sort_folio(lruvec, folio, sc, tier)) sorted += delta; else if (isolate_folio(lruvec, folio, sc)) { list_add(&folio->lru, list); isolated += delta; } else { list_move(&folio->lru, &moved); skipped_zone += delta; } if (!--remaining || max(isolated, skipped_zone) >= MIN_LRU_BATCH) break; } if (skipped_zone) { list_splice(&moved, head); __count_zid_vm_events(PGSCAN_SKIP, zone, skipped_zone); skipped += skipped_zone; } if (!remaining || isolated >= MIN_LRU_BATCH) break; } item = PGSCAN_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) { __count_vm_events(item, isolated); __count_vm_events(PGREFILL, sorted); } __count_memcg_events(memcg, item, isolated); __count_memcg_events(memcg, PGREFILL, sorted); __count_vm_events(PGSCAN_ANON + type, isolated); trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH, scanned, skipped, isolated, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); /* * There might not be eligible folios due to reclaim_idx. Check the * remaining to prevent livelock if it's not making progress. */ return isolated || !remaining ? scanned : 0; } static int get_tier_idx(struct lruvec *lruvec, int type) { int tier; struct ctrl_pos sp, pv; /* * To leave a margin for fluctuations, use a larger gain factor (1:2). * This value is chosen because any other tier would have at least twice * as many refaults as the first tier. */ read_ctrl_pos(lruvec, type, 0, 1, &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { read_ctrl_pos(lruvec, type, tier, 2, &pv); if (!positive_ctrl_err(&sp, &pv)) break; } return tier - 1; } static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx) { int type, tier; struct ctrl_pos sp, pv; int gain[ANON_AND_FILE] = { swappiness, MAX_SWAPPINESS - swappiness }; /* * Compare the first tier of anon with that of file to determine which * type to scan. Also need to compare other tiers of the selected type * with the first tier of the other type to determine the last tier (of * the selected type) to evict. */ read_ctrl_pos(lruvec, LRU_GEN_ANON, 0, gain[LRU_GEN_ANON], &sp); read_ctrl_pos(lruvec, LRU_GEN_FILE, 0, gain[LRU_GEN_FILE], &pv); type = positive_ctrl_err(&sp, &pv); read_ctrl_pos(lruvec, !type, 0, gain[!type], &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { read_ctrl_pos(lruvec, type, tier, gain[type], &pv); if (!positive_ctrl_err(&sp, &pv)) break; } *tier_idx = tier - 1; return type; } static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness, int *type_scanned, struct list_head *list) { int i; int type; int scanned; int tier = -1; DEFINE_MIN_SEQ(lruvec); /* * Try to make the obvious choice first, and if anon and file are both * available from the same generation, * 1. Interpret swappiness 1 as file first and MAX_SWAPPINESS as anon * first. * 2. If !__GFP_IO, file first since clean pagecache is more likely to * exist than clean swapcache. */ if (!swappiness) type = LRU_GEN_FILE; else if (min_seq[LRU_GEN_ANON] < min_seq[LRU_GEN_FILE]) type = LRU_GEN_ANON; else if (swappiness == 1) type = LRU_GEN_FILE; else if (swappiness == MAX_SWAPPINESS) type = LRU_GEN_ANON; else if (!(sc->gfp_mask & __GFP_IO)) type = LRU_GEN_FILE; else type = get_type_to_scan(lruvec, swappiness, &tier); for (i = !swappiness; i < ANON_AND_FILE; i++) { if (tier < 0) tier = get_tier_idx(lruvec, type); scanned = scan_folios(lruvec, sc, type, tier, list); if (scanned) break; type = !type; tier = -1; } *type_scanned = type; return scanned; } static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness) { int type; int scanned; int reclaimed; LIST_HEAD(list); LIST_HEAD(clean); struct folio *folio; struct folio *next; enum vm_event_item item; struct reclaim_stat stat; struct lru_gen_mm_walk *walk; bool skip_retry = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irq(&lruvec->lru_lock); scanned = isolate_folios(lruvec, sc, swappiness, &type, &list); scanned += try_to_inc_min_seq(lruvec, swappiness); if (get_nr_gens(lruvec, !swappiness) == MIN_NR_GENS) scanned = 0; spin_unlock_irq(&lruvec->lru_lock); if (list_empty(&list)) return scanned; retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false); sc->nr_reclaimed += reclaimed; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, scanned, reclaimed, &stat, sc->priority, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); list_for_each_entry_safe_reverse(folio, next, &list, lru) { if (!folio_evictable(folio)) { list_del(&folio->lru); folio_putback_lru(folio); continue; } if (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* restore LRU_REFS_FLAGS cleared by isolate_folio() */ if (folio_test_workingset(folio)) folio_set_referenced(folio); continue; } if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) || folio_mapped(folio) || folio_test_locked(folio) || folio_test_dirty(folio) || folio_test_writeback(folio)) { /* don't add rejected folios to the oldest generation */ set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, BIT(PG_active)); continue; } /* retry folios that may have missed folio_rotate_reclaimable() */ list_move(&folio->lru, &clean); } spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &list); walk = current->reclaim_state->mm_walk; if (walk && walk->batched) { walk->lruvec = lruvec; reset_batch_size(walk); } item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); __count_memcg_events(memcg, item, reclaimed); __count_vm_events(PGSTEAL_ANON + type, reclaimed); spin_unlock_irq(&lruvec->lru_lock); list_splice_init(&clean, &list); if (!list_empty(&list)) { skip_retry = true; goto retry; } return scanned; } static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, bool can_swap, unsigned long *nr_to_scan) { int gen, type, zone; unsigned long old = 0; unsigned long young = 0; unsigned long total = 0; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); /* whether this lruvec is completely out of cold folios */ if (min_seq[!can_swap] + MIN_NR_GENS > max_seq) { *nr_to_scan = 0; return true; } for (type = !can_swap; type < ANON_AND_FILE; type++) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { unsigned long size = 0; gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); total += size; if (seq == max_seq) young += size; else if (seq + MIN_NR_GENS == max_seq) old += size; } } *nr_to_scan = total; /* * The aging tries to be lazy to reduce the overhead, while the eviction * stalls when the number of generations reaches MIN_NR_GENS. Hence, the * ideal number of generations is MIN_NR_GENS+1. */ if (min_seq[!can_swap] + MIN_NR_GENS < max_seq) return false; /* * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1) * of the total number of pages for each generation. A reasonable range * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The * aging cares about the upper bound of hot pages, while the eviction * cares about the lower bound of cold pages. */ if (young * MIN_NR_GENS > total) return true; if (old * (MIN_NR_GENS + 2) < total) return true; return false; } /* * For future optimizations: * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg * reclaim. */ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool can_swap) { bool success; unsigned long nr_to_scan; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) return -1; success = should_run_aging(lruvec, max_seq, can_swap, &nr_to_scan); /* try to scrape all its memory if this memcg was deleted */ if (nr_to_scan && !mem_cgroup_online(memcg)) return nr_to_scan; /* try to get away with not aging at the default priority */ if (!success || sc->priority == DEF_PRIORITY) return nr_to_scan >> sc->priority; /* stop scanning this lruvec as it's low on cold folios */ return try_to_inc_max_seq(lruvec, max_seq, can_swap, false) ? -1 : 0; } static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) { int i; enum zone_watermarks mark; /* don't abort memcg reclaim to ensure fairness */ if (!root_reclaim(sc)) return false; if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order))) return true; /* check the order to exclude compaction-induced reclaim */ if (!current_is_kswapd() || sc->order) return false; mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ? WMARK_PROMO : WMARK_HIGH; for (i = 0; i <= sc->reclaim_idx; i++) { struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH; if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0)) return false; } /* kswapd should abort if all eligible zones are safe */ return true; } static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { long nr_to_scan; unsigned long scanned = 0; int swappiness = get_swappiness(lruvec, sc); while (true) { int delta; nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness); if (nr_to_scan <= 0) break; delta = evict_folios(lruvec, sc, swappiness); if (!delta) break; scanned += delta; if (scanned >= nr_to_scan) break; if (should_abort_scan(lruvec, sc)) break; cond_resched(); } /* whether this lruvec should be rotated */ return nr_to_scan < 0; } static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) { bool success; unsigned long scanned = sc->nr_scanned; unsigned long reclaimed = sc->nr_reclaimed; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); /* lru_gen_age_node() called mem_cgroup_calculate_protection() */ if (mem_cgroup_below_min(NULL, memcg)) return MEMCG_LRU_YOUNG; if (mem_cgroup_below_low(NULL, memcg)) { /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL) return MEMCG_LRU_TAIL; memcg_memory_event(memcg, MEMCG_LOW); } success = try_to_shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); flush_reclaim_state(sc); if (success && mem_cgroup_online(memcg)) return MEMCG_LRU_YOUNG; if (!success && lruvec_is_sizable(lruvec, sc)) return 0; /* one retry if offlined or too small */ return READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; } static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) { int op; int gen; int bin; int first_bin; struct lruvec *lruvec; struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; struct hlist_nulls_node *pos; gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: op = 0; memcg = NULL; rcu_read_lock(); hlist_nulls_for_each_entry_rcu(lrugen, pos, &pgdat->memcg_lru.fifo[gen][bin], list) { if (op) { lru_gen_rotate_memcg(lruvec, op); op = 0; } mem_cgroup_put(memcg); memcg = NULL; if (gen != READ_ONCE(lrugen->gen)) continue; lruvec = container_of(lrugen, struct lruvec, lrugen); memcg = lruvec_memcg(lruvec); if (!mem_cgroup_tryget(memcg)) { lru_gen_release_memcg(memcg); memcg = NULL; continue; } rcu_read_unlock(); op = shrink_one(lruvec, sc); rcu_read_lock(); if (should_abort_scan(lruvec, sc)) break; } rcu_read_unlock(); if (op) lru_gen_rotate_memcg(lruvec, op); mem_cgroup_put(memcg); if (!is_a_nulls(pos)) return; /* restart if raced with lru_gen_rotate_memcg() */ if (gen != get_nulls_value(pos)) goto restart; /* try the rest of the bins of the current generation */ bin = get_memcg_bin(bin + 1); if (bin != first_bin) goto restart; } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { struct blk_plug plug; VM_WARN_ON_ONCE(root_reclaim(sc)); VM_WARN_ON_ONCE(!sc->may_writepage || !sc->may_unmap); lru_add_drain(); blk_start_plug(&plug); set_mm_walk(NULL, sc->proactive); if (try_to_shrink_lruvec(lruvec, sc)) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG); clear_mm_walk(); blk_finish_plug(&plug); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { struct blk_plug plug; unsigned long reclaimed = sc->nr_reclaimed; VM_WARN_ON_ONCE(!root_reclaim(sc)); /* * Unmapped clean folios are already prioritized. Scanning for more of * them is likely futile and can cause high reclaim latency when there * is a large number of memcgs. */ if (!sc->may_writepage || !sc->may_unmap) goto done; lru_add_drain(); blk_start_plug(&plug); set_mm_walk(pgdat, sc->proactive); set_initial_priority(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed = 0; if (mem_cgroup_disabled()) shrink_one(&pgdat->__lruvec, sc); else shrink_many(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed += reclaimed; clear_mm_walk(); blk_finish_plug(&plug); done: /* kswapd should never fail */ pgdat->kswapd_failures = 0; } /****************************************************************************** * state change ******************************************************************************/ static bool __maybe_unused state_is_valid(struct lruvec *lruvec) { struct lru_gen_folio *lrugen = &lruvec->lrugen; if (lrugen->enabled) { enum lru_list lru; for_each_evictable_lru(lru) { if (!list_empty(&lruvec->lists[lru])) return false; } } else { int gen, type, zone; for_each_gen_type_zone(gen, type, zone) { if (!list_empty(&lrugen->folios[gen][type][zone])) return false; } } return true; } static bool fill_evictable(struct lruvec *lruvec) { enum lru_list lru; int remaining = MAX_LRU_BATCH; for_each_evictable_lru(lru) { int type = is_file_lru(lru); bool active = is_active_lru(lru); struct list_head *head = &lruvec->lists[lru]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio) != active, folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_lru_gen(folio) != -1, folio); lruvec_del_folio(lruvec, folio); success = lru_gen_add_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); if (!--remaining) return false; } } return true; } static bool drain_evictable(struct lruvec *lruvec) { int gen, type, zone; int remaining = MAX_LRU_BATCH; for_each_gen_type_zone(gen, type, zone) { struct list_head *head = &lruvec->lrugen.folios[gen][type][zone]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); success = lru_gen_del_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); lruvec_add_folio(lruvec, folio); if (!--remaining) return false; } } return true; } static void lru_gen_change_state(bool enabled) { static DEFINE_MUTEX(state_mutex); struct mem_cgroup *memcg; cgroup_lock(); cpus_read_lock(); get_online_mems(); mutex_lock(&state_mutex); if (enabled == lru_gen_enabled()) goto unlock; if (enabled) static_branch_enable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); else static_branch_disable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); VM_WARN_ON_ONCE(!state_is_valid(lruvec)); lruvec->lrugen.enabled = enabled; while (!(enabled ? fill_evictable(lruvec) : drain_evictable(lruvec))) { spin_unlock_irq(&lruvec->lru_lock); cond_resched(); spin_lock_irq(&lruvec->lru_lock); } spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); unlock: mutex_unlock(&state_mutex); put_online_mems(); cpus_read_unlock(); cgroup_unlock(); } /****************************************************************************** * sysfs interface ******************************************************************************/ static ssize_t min_ttl_ms_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl))); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t min_ttl_ms_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned int msecs; if (kstrtouint(buf, 0, &msecs)) return -EINVAL; WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs)); return len; } static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR_RW(min_ttl_ms); static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned int caps = 0; if (get_cap(LRU_GEN_CORE)) caps |= BIT(LRU_GEN_CORE); if (should_walk_mmu()) caps |= BIT(LRU_GEN_MM_WALK); if (should_clear_pmd_young()) caps |= BIT(LRU_GEN_NONLEAF_YOUNG); return sysfs_emit(buf, "0x%04x\n", caps); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { int i; unsigned int caps; if (tolower(*buf) == 'n') caps = 0; else if (tolower(*buf) == 'y') caps = -1; else if (kstrtouint(buf, 0, &caps)) return -EINVAL; for (i = 0; i < NR_LRU_GEN_CAPS; i++) { bool enabled = caps & BIT(i); if (i == LRU_GEN_CORE) lru_gen_change_state(enabled); else if (enabled) static_branch_enable(&lru_gen_caps[i]); else static_branch_disable(&lru_gen_caps[i]); } return len; } static struct kobj_attribute lru_gen_enabled_attr = __ATTR_RW(enabled); static struct attribute *lru_gen_attrs[] = { &lru_gen_min_ttl_attr.attr, &lru_gen_enabled_attr.attr, NULL }; static const struct attribute_group lru_gen_attr_group = { .name = "lru_gen", .attrs = lru_gen_attrs, }; /****************************************************************************** * debugfs interface ******************************************************************************/ static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos) { struct mem_cgroup *memcg; loff_t nr_to_skip = *pos; m->private = kvmalloc(PATH_MAX, GFP_KERNEL); if (!m->private) return ERR_PTR(-ENOMEM); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node_state(nid, N_MEMORY) { if (!nr_to_skip--) return get_lruvec(memcg, nid); } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); return NULL; } static void lru_gen_seq_stop(struct seq_file *m, void *v) { if (!IS_ERR_OR_NULL(v)) mem_cgroup_iter_break(NULL, lruvec_memcg(v)); kvfree(m->private); m->private = NULL; } static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos) { int nid = lruvec_pgdat(v)->node_id; struct mem_cgroup *memcg = lruvec_memcg(v); ++*pos; nid = next_memory_node(nid); if (nid == MAX_NUMNODES) { memcg = mem_cgroup_iter(NULL, memcg, NULL); if (!memcg) return NULL; nid = first_memory_node; } return get_lruvec(memcg, nid); } static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq, unsigned long seq) { int i; int type, tier; int hist = lru_hist_from_seq(seq); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); for (type = 0; type < ANON_AND_FILE; type++) { const char *s = " "; unsigned long n[3] = {}; if (seq == max_seq) { s = "RT "; n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); n[1] = READ_ONCE(lrugen->avg_total[type][tier]); } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { s = "rep"; n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]); n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]); } for (i = 0; i < 3; i++) seq_printf(m, " %10lu%c", n[i], s[i]); } seq_putc(m, '\n'); } if (!mm_state) return; seq_puts(m, " "); for (i = 0; i < NR_MM_STATS; i++) { const char *s = " "; unsigned long n = 0; if (seq == max_seq && NR_HIST_GENS == 1) { s = "LOYNFA"; n = READ_ONCE(mm_state->stats[hist][i]); } else if (seq != max_seq && NR_HIST_GENS > 1) { s = "loynfa"; n = READ_ONCE(mm_state->stats[hist][i]); } seq_printf(m, " %10lu%c", n, s[i]); } seq_putc(m, '\n'); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static int lru_gen_seq_show(struct seq_file *m, void *v) { unsigned long seq; bool full = !debugfs_real_fops(m->file)->write; struct lruvec *lruvec = v; struct lru_gen_folio *lrugen = &lruvec->lrugen; int nid = lruvec_pgdat(lruvec)->node_id; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (nid == first_memory_node) { const char *path = memcg ? m->private : ""; #ifdef CONFIG_MEMCG if (memcg) cgroup_path(memcg->css.cgroup, m->private, PATH_MAX); #endif seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path); } seq_printf(m, " node %5d\n", nid); if (!full) seq = min_seq[LRU_GEN_ANON]; else if (max_seq >= MAX_NR_GENS) seq = max_seq - MAX_NR_GENS + 1; else seq = 0; for (; seq <= max_seq; seq++) { int type, zone; int gen = lru_gen_from_seq(seq); unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth)); for (type = 0; type < ANON_AND_FILE; type++) { unsigned long size = 0; char mark = full && seq < min_seq[type] ? 'x' : ' '; for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); seq_printf(m, " %10lu%c", size, mark); } seq_putc(m, '\n'); if (full) lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq); } return 0; } static const struct seq_operations lru_gen_seq_ops = { .start = lru_gen_seq_start, .stop = lru_gen_seq_stop, .next = lru_gen_seq_next, .show = lru_gen_seq_show, }; static int run_aging(struct lruvec *lruvec, unsigned long seq, bool can_swap, bool force_scan) { DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (seq < max_seq) return 0; if (seq > max_seq) return -EINVAL; if (!force_scan && min_seq[!can_swap] + MAX_NR_GENS - 1 <= max_seq) return -ERANGE; try_to_inc_max_seq(lruvec, max_seq, can_swap, force_scan); return 0; } static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long nr_to_reclaim) { DEFINE_MAX_SEQ(lruvec); if (seq + MIN_NR_GENS > max_seq) return -EINVAL; sc->nr_reclaimed = 0; while (!signal_pending(current)) { DEFINE_MIN_SEQ(lruvec); if (seq < min_seq[!swappiness]) return 0; if (sc->nr_reclaimed >= nr_to_reclaim) return 0; if (!evict_folios(lruvec, sc, swappiness)) return 0; cond_resched(); } return -EINTR; } static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long opt) { struct lruvec *lruvec; int err = -EINVAL; struct mem_cgroup *memcg = NULL; if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY)) return -EINVAL; if (!mem_cgroup_disabled()) { rcu_read_lock(); memcg = mem_cgroup_from_id(memcg_id); if (!mem_cgroup_tryget(memcg)) memcg = NULL; rcu_read_unlock(); if (!memcg) return -EINVAL; } if (memcg_id != mem_cgroup_id(memcg)) goto done; lruvec = get_lruvec(memcg, nid); if (swappiness < MIN_SWAPPINESS) swappiness = get_swappiness(lruvec, sc); else if (swappiness > MAX_SWAPPINESS) goto done; switch (cmd) { case '+': err = run_aging(lruvec, seq, swappiness, opt); break; case '-': err = run_eviction(lruvec, seq, sc, swappiness, opt); break; } done: mem_cgroup_put(memcg); return err; } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t lru_gen_seq_write(struct file *file, const char __user *src, size_t len, loff_t *pos) { void *buf; char *cur, *next; unsigned int flags; struct blk_plug plug; int err = -EINVAL; struct scan_control sc = { .may_writepage = true, .may_unmap = true, .may_swap = true, .reclaim_idx = MAX_NR_ZONES - 1, .gfp_mask = GFP_KERNEL, }; buf = kvmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_user(buf, src, len)) { kvfree(buf); return -EFAULT; } set_task_reclaim_state(current, &sc.reclaim_state); flags = memalloc_noreclaim_save(); blk_start_plug(&plug); if (!set_mm_walk(NULL, true)) { err = -ENOMEM; goto done; } next = buf; next[len] = '\0'; while ((cur = strsep(&next, ",;\n"))) { int n; int end; char cmd; unsigned int memcg_id; unsigned int nid; unsigned long seq; unsigned int swappiness = -1; unsigned long opt = -1; cur = skip_spaces(cur); if (!*cur) continue; n = sscanf(cur, "%c %u %u %lu %n %u %n %lu %n", &cmd, &memcg_id, &nid, &seq, &end, &swappiness, &end, &opt, &end); if (n < 4 || cur[end]) { err = -EINVAL; break; } err = run_cmd(cmd, memcg_id, nid, seq, &sc, swappiness, opt); if (err) break; } done: clear_mm_walk(); blk_finish_plug(&plug); memalloc_noreclaim_restore(flags); set_task_reclaim_state(current, NULL); kvfree(buf); return err ? : len; } static int lru_gen_seq_open(struct inode *inode, struct file *file) { return seq_open(file, &lru_gen_seq_ops); } static const struct file_operations lru_gen_rw_fops = { .open = lru_gen_seq_open, .read = seq_read, .write = lru_gen_seq_write, .llseek = seq_lseek, .release = seq_release, }; static const struct file_operations lru_gen_ro_fops = { .open = lru_gen_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; /****************************************************************************** * initialization ******************************************************************************/ void lru_gen_init_pgdat(struct pglist_data *pgdat) { int i, j; spin_lock_init(&pgdat->memcg_lru.lock); for (i = 0; i < MEMCG_NR_GENS; i++) { for (j = 0; j < MEMCG_NR_BINS; j++) INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i); } } void lru_gen_init_lruvec(struct lruvec *lruvec) { int i; int gen, type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lrugen->max_seq = MIN_NR_GENS + 1; lrugen->enabled = lru_gen_enabled(); for (i = 0; i <= MIN_NR_GENS + 1; i++) lrugen->timestamps[i] = jiffies; for_each_gen_type_zone(gen, type, zone) INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]); if (mm_state) mm_state->seq = MIN_NR_GENS; } #ifdef CONFIG_MEMCG void lru_gen_init_memcg(struct mem_cgroup *memcg) { struct lru_gen_mm_list *mm_list = get_mm_list(memcg); if (!mm_list) return; INIT_LIST_HEAD(&mm_list->fifo); spin_lock_init(&mm_list->lock); } void lru_gen_exit_memcg(struct mem_cgroup *memcg) { int i; int nid; struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(mm_list && !list_empty(&mm_list->fifo)); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0, sizeof(lruvec->lrugen.nr_pages))); lruvec->lrugen.list.next = LIST_POISON1; if (!mm_state) continue; for (i = 0; i < NR_BLOOM_FILTERS; i++) { bitmap_free(mm_state->filters[i]); mm_state->filters[i] = NULL; } } } #endif /* CONFIG_MEMCG */ static int __init init_lru_gen(void) { BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS); BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS); if (sysfs_create_group(mm_kobj, &lru_gen_attr_group)) pr_err("lru_gen: failed to create sysfs group\n"); debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops); debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops); return 0; }; late_initcall(init_lru_gen); #else /* !CONFIG_LRU_GEN */ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } #endif /* CONFIG_LRU_GEN */ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; bool proportional_reclaim; struct blk_plug plug; if (lru_gen_enabled() && !root_reclaim(sc)) { lru_gen_shrink_lruvec(lruvec, sc); return; } get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); /* * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal * event that can occur when there is little memory pressure e.g. * multiple streaming readers/writers. Hence, we do not abort scanning * when the requested number of pages are reclaimed when scanning at * DEF_PRIORITY on the assumption that the fact we are direct * reclaiming implies that kswapd is not keeping up and it is best to * do a batch of work at once. For memcg reclaim one check is made to * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { unsigned long nr_anon, nr_file, percentage; unsigned long nr_scanned; for_each_evictable_lru(lru) { if (nr[lru]) { nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, sc); } } cond_resched(); if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; /* * For kswapd and memcg, reclaim at least the number of pages * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. */ nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; /* * It's just vindictive to attack the larger once the smaller * has gone to zero. And given the way we stop scanning the * smaller below, this makes sure that we only make one nudge * towards proportionality once we've got nr_to_reclaim. */ if (!nr_file || !nr_anon) break; if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; lru = LRU_BASE; percentage = nr_anon * 100 / scan_target; } else { unsigned long scan_target = targets[LRU_INACTIVE_FILE] + targets[LRU_ACTIVE_FILE] + 1; lru = LRU_FILE; percentage = nr_file * 100 / scan_target; } /* Stop scanning the smaller of the LRU */ nr[lru] = 0; nr[lru + LRU_ACTIVE] = 0; /* * Recalculate the other LRU scan count based on its original * scan target and the percentage scanning already complete */ lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); lru += LRU_ACTIVE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ if (can_age_anon_pages(lruvec_pgdat(lruvec), sc) && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { if (gfp_compaction_allowed(sc->gfp_mask) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; return false; } /* * Reclaim/compaction is used for high-order allocation requests. It reclaims * order-0 pages before compacting the zone. should_continue_reclaim() returns * true if more pages should be reclaimed such that when the page allocator * calls try_to_compact_pages() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; int z; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) return false; /* * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX * number of pages that were scanned. This will return to the caller * with the risk reclaim/compaction and the resulting allocation attempt * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL * allocations through requiring that the full LRU list has been scanned * first, by assuming that zero delta of sc->nr_scanned means full LRU * scan, but that approximation was wrong, and there were corner cases * where always a non-zero amount of pages were scanned. */ if (!nr_reclaimed) return false; /* If compaction would go ahead or the allocation would succeed, stop */ for (z = 0; z <= sc->reclaim_idx; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; /* Allocation can already succeed, nothing to do */ if (zone_watermark_ok(zone, sc->order, min_wmark_pages(zone), sc->reclaim_idx, 0)) return false; if (compaction_suitable(zone, sc->order, sc->reclaim_idx)) return false; } /* * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction; } static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) { struct mem_cgroup *target_memcg = sc->target_mem_cgroup; struct mem_cgroup_reclaim_cookie reclaim = { .pgdat = pgdat, }; struct mem_cgroup_reclaim_cookie *partial = &reclaim; struct mem_cgroup *memcg; /* * In most cases, direct reclaimers can do partial walks * through the cgroup tree, using an iterator state that * persists across invocations. This strikes a balance between * fairness and allocation latency. * * For kswapd, reliable forward progress is more important * than a quick return to idle. Always do full walks. */ if (current_is_kswapd() || sc->memcg_full_walk) partial = NULL; memcg = mem_cgroup_iter(target_memcg, NULL, partial); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long reclaimed; unsigned long scanned; /* * This loop can become CPU-bound when target memcgs * aren't eligible for reclaim - either because they * don't have any reclaimable pages, or because their * memory is explicitly protected. Avoid soft lockups. */ cond_resched(); mem_cgroup_calculate_protection(target_memcg, memcg); if (mem_cgroup_below_min(target_memcg, memcg)) { /* * Hard protection. * If there is no reclaimable memory, OOM. */ continue; } else if (mem_cgroup_below_low(target_memcg, memcg)) { /* * Soft protection. * Respect the protection only as long as * there is an unprotected supply * of reclaimable memory from other cgroups. */ if (!sc->memcg_low_reclaim) { sc->memcg_low_skipped = 1; continue; } memcg_memory_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); /* Record the group's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); /* If partial walks are allowed, bail once goal is reached */ if (partial && sc->nr_reclaimed >= sc->nr_to_reclaim) { mem_cgroup_iter_break(target_memcg, memcg); break; } } while ((memcg = mem_cgroup_iter(target_memcg, memcg, partial))); } static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) { unsigned long nr_reclaimed, nr_scanned, nr_node_reclaimed; struct lruvec *target_lruvec; bool reclaimable = false; if (lru_gen_enabled() && root_reclaim(sc)) { lru_gen_shrink_node(pgdat, sc); return; } target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); again: memset(&sc->nr, 0, sizeof(sc->nr)); nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; prepare_scan_control(pgdat, sc); shrink_node_memcgs(pgdat, sc); flush_reclaim_state(sc); nr_node_reclaimed = sc->nr_reclaimed - nr_reclaimed; /* Record the subtree's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, nr_node_reclaimed); if (nr_node_reclaimed) reclaimable = true; if (current_is_kswapd()) { /* * If reclaim is isolating dirty pages under writeback, * it implies that the long-lived page allocation rate * is exceeding the page laundering rate. Either the * global limits are not being effective at throttling * processes due to the page distribution throughout * zones or there is heavy usage of a slow backing * device. The only option is to throttle from reclaim * context which is not ideal as there is no guarantee * the dirtying process is throttled in the same way * balance_dirty_pages() manages. * * Once a node is flagged PGDAT_WRITEBACK, kswapd will * count the number of pages under pages flagged for * immediate reclaim and stall if any are encountered * in the nr_immediate check below. */ if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* Allow kswapd to start writing pages during reclaim.*/ if (sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); /* * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU * faster than they are written so forcibly stall * until some pages complete writeback. */ if (sc->nr.immediate) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } /* * Tag a node/memcg as congested if all the dirty pages were marked * for writeback and immediate reclaim (counted in nr.congested). * * Legacy memcg will stall in page writeback so avoid forcibly * stalling in reclaim_throttle(). */ if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested) { if (cgroup_reclaim(sc) && writeback_throttling_sane(sc)) set_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags); if (current_is_kswapd()) set_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags); } /* * Stall direct reclaim for IO completions if the lruvec is * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && (test_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags) || test_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags))) reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED); if (should_continue_reclaim(pgdat, nr_node_reclaimed, sc)) goto again; /* * Kswapd gives up on balancing particular nodes after too * many failures to reclaim anything from them and goes to * sleep. On reclaim progress, reset the failure counter. A * successful direct reclaim run will revive a dormant kswapd. */ if (reclaimable) pgdat->kswapd_failures = 0; else if (sc->cache_trim_mode) sc->cache_trim_mode_failed = 1; } /* * Returns true if compaction should go ahead for a costly-order request, or * the allocation would already succeed without compaction. Return false if we * should reclaim first. */ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) { unsigned long watermark; if (!gfp_compaction_allowed(sc->gfp_mask)) return false; /* Allocation can already succeed, nothing to do */ if (zone_watermark_ok(zone, sc->order, min_wmark_pages(zone), sc->reclaim_idx, 0)) return true; /* Compaction cannot yet proceed. Do reclaim. */ if (!compaction_suitable(zone, sc->order, sc->reclaim_idx)) return false; /* * Compaction is already possible, but it takes time to run and there * are potentially other callers using the pages just freed. So proceed * with reclaim to make a buffer of free pages available to give * compaction a reasonable chance of completing and allocating the page. * Note that we won't actually reclaim the whole buffer in one attempt * as the target watermark in should_continue_reclaim() is lower. But if * we are already above the high+gap watermark, don't reclaim at all. */ watermark = high_wmark_pages(zone) + compact_gap(sc->order); return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) { /* * If reclaim is making progress greater than 12% efficiency then * wake all the NOPROGRESS throttled tasks. */ if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS]; if (waitqueue_active(wqh)) wake_up(wqh); return; } /* * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages * under writeback and marked for immediate reclaim at the tail of the * LRU. */ if (current_is_kswapd() || cgroup_reclaim(sc)) return; /* Throttle if making no progress at high prioities. */ if (sc->priority == 1 && !sc->nr_reclaimed) reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS); } /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation * request. * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; pg_data_t *first_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) { sc->gfp_mask |= __GFP_HIGHMEM; sc->reclaim_idx = gfp_zone(sc->gfp_mask); } for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { /* * Take care memory controller reclaiming has small influence * to global LRU. */ if (!cgroup_reclaim(sc)) { if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) continue; /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. * Even though compaction is invoked for any * non-zero order, only frequent costly order * reclamation is disruptive enough to become a * noticeable problem, like transparent huge * page allocations. */ if (IS_ENABLED(CONFIG_COMPACTION) && sc->order > PAGE_ALLOC_COSTLY_ORDER && compaction_ready(zone, sc)) { sc->compaction_ready = true; continue; } /* * Shrink each node in the zonelist once. If the * zonelist is ordered by zone (not the default) then a * node may be shrunk multiple times but in that case * the user prefers lower zones being preserved. */ if (zone->zone_pgdat == last_pgdat) continue; /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and * scanned pages. This works for global memory pressure * and balancing, not for a memcg's limit. */ nr_soft_scanned = 0; nr_soft_reclaimed = memcg1_soft_limit_reclaim(zone->zone_pgdat, sc->order, sc->gfp_mask, &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } if (!first_pgdat) first_pgdat = zone->zone_pgdat; /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); } if (first_pgdat) consider_reclaim_throttle(first_pgdat, sc); /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; } static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { struct lruvec *target_lruvec; unsigned long refaults; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); target_lruvec->refaults[WORKINGSET_ANON] = refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); target_lruvec->refaults[WORKINGSET_FILE] = refaults; } /* * This is the main entry point to direct page reclaim. * * If a full scan of the inactive list fails to free enough memory then we * are "out of memory" and something needs to be killed. * * If the caller is !__GFP_FS then the probability of a failure is reasonably * high - the zone may be full of dirty or under-writeback pages, which this * caller can't do much about. We kick the writeback threads and take explicit * naps in the hope that some of these pages can be written. But if the * allocating task holds filesystem locks which prevent writeout this might not * work, and the allocation attempt will fail. * * returns: 0, if no pages reclaimed * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int initial_priority = sc->priority; pg_data_t *last_pgdat; struct zoneref *z; struct zone *zone; retry: delayacct_freepages_start(); if (!cgroup_reclaim(sc)) __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { if (!sc->proactive) vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; shrink_zones(zonelist, sc); if (sc->nr_reclaimed >= sc->nr_to_reclaim) break; if (sc->compaction_ready) break; /* * If we're getting trouble reclaiming, start doing * writepage even in laptop mode. */ if (sc->priority < DEF_PRIORITY - 2) sc->may_writepage = 1; } while (--sc->priority >= 0); last_pgdat = NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); if (cgroup_reclaim(sc)) { struct lruvec *lruvec; lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, zone->zone_pgdat); clear_bit(LRUVEC_CGROUP_CONGESTED, &lruvec->flags); } } delayacct_freepages_end(); if (sc->nr_reclaimed) return sc->nr_reclaimed; /* Aborted reclaim to try compaction? don't OOM, then */ if (sc->compaction_ready) return 1; /* * In most cases, direct reclaimers can do partial walks * through the cgroup tree to meet the reclaim goal while * keeping latency low. Since the iterator state is shared * among all direct reclaim invocations (to retain fairness * among cgroups), though, high concurrency can result in * individual threads not seeing enough cgroups to make * meaningful forward progress. Avoid false OOMs in this case. */ if (!sc->memcg_full_walk) { sc->priority = initial_priority; sc->memcg_full_walk = 1; goto retry; } /* * We make inactive:active ratio decisions based on the node's * composition of memory, but a restrictive reclaim_idx or a * memory.low cgroup setting can exempt large amounts of * memory from reclaim. Neither of which are very common, so * instead of doing costly eligibility calculations of the * entire cgroup subtree up front, we assume the estimates are * good, and retry with forcible deactivation if that fails. */ if (sc->skipped_deactivate) { sc->priority = initial_priority; sc->force_deactivate = 1; sc->skipped_deactivate = 0; goto retry; } /* Untapped cgroup reserves? Don't OOM, retry. */ if (sc->memcg_low_skipped) { sc->priority = initial_priority; sc->force_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; } return 0; } static bool allow_direct_reclaim(pg_data_t *pgdat) { struct zone *zone; unsigned long pfmemalloc_reserve = 0; unsigned long free_pages = 0; int i; bool wmark_ok; if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; if (!managed_zone(zone)) continue; if (!zone_reclaimable_pages(zone)) continue; pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state_snapshot(zone, NR_FREE_PAGES); } /* If there are no reserves (unexpected config) then do not throttle */ if (!pfmemalloc_reserve) return true; wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } return wmark_ok; } /* * Throttle direct reclaimers if backing storage is backed by the network * and the PFMEMALLOC reserve for the preferred node is getting dangerously * depleted. kswapd will continue to make progress and wake the processes * when the low watermark is reached. * * Returns true if a fatal signal was delivered during throttling. If this * happens, the page allocator should not consider triggering the OOM killer. */ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { struct zoneref *z; struct zone *zone; pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly * responsible for cleaning pages necessary for reclaim to make forward * progress. kjournald for example may enter direct reclaim while * committing a transaction where throttling it could forcing other * processes to block on log_wait_commit(). */ if (current->flags & PF_KTHREAD) goto out; /* * If a fatal signal is pending, this process should not throttle. * It should return quickly so it can exit and free its memory */ if (fatal_signal_pending(current)) goto out; /* * Check if the pfmemalloc reserves are ok by finding the first node * with a usable ZONE_NORMAL or lower zone. The expectation is that * GFP_KERNEL will be required for allocating network buffers when * swapping over the network so ZONE_HIGHMEM is unusable. * * Throttling is based on the first usable node and throttled processes * wait on a queue until kswapd makes progress and wakes them. There * is an affinity then between processes waking up and where reclaim * progress has been made assuming the process wakes on the same node. * More importantly, processes running on remote nodes will not compete * for remote pfmemalloc reserves and processes on different nodes * should make reasonable progress. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) { if (zone_idx(zone) > ZONE_NORMAL) continue; /* Throttle based on the first usable node */ pgdat = zone->zone_pgdat; if (allow_direct_reclaim(pgdat)) goto out; break; } /* If no zone was usable by the allocation flags then do not throttle */ if (!pgdat) goto out; /* Account for the throttling */ count_vm_event(PGSCAN_DIRECT_THROTTLE); /* * If the caller cannot enter the filesystem, it's possible that it * is due to the caller holding an FS lock or performing a journal * transaction in the case of a filesystem like ext[3|4]. In this case, * it is not safe to block on pfmemalloc_wait as kswapd could be * blocked waiting on the same lock. Instead, throttle for up to a * second before continuing. */ if (!(gfp_mask & __GFP_FS)) wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat), HZ); else /* Throttle until kswapd wakes the process */ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat)); if (fatal_signal_pending(current)) return true; out: return false; } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { unsigned long nr_reclaimed; struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .gfp_mask = current_gfp_context(gfp_mask), .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, }; /* * scan_control uses s8 fields for order, priority, and reclaim_idx. * Confirm they are large enough for max values. */ BUILD_BUG_ON(MAX_PAGE_ORDER >= S8_MAX); BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); /* * Do not enter reclaim if fatal signal was delivered while throttled. * 1 is returned so that the page allocator does not OOM kill at this * point. */ if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask)) return 1; set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #ifdef CONFIG_MEMCG /* Only used by soft limit reclaim. Do not reuse for anything else. */ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned) { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .target_mem_cgroup = memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, }; WARN_ON_ONCE(!current->reclaim_state); sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, sc.gfp_mask); /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. * if we don't reclaim here, the shrink_node from balance_pgdat * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ shrink_lruvec(lruvec, &sc); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); *nr_scanned = sc.nr_scanned; return sc.nr_reclaimed; } unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options, int *swappiness) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .proactive_swappiness = swappiness, .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put * equal pressure on all the nodes. This is based on the assumption that * the reclaim does not bail out early. */ struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #endif static void kswapd_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; struct lruvec *lruvec; if (lru_gen_enabled()) { lru_gen_age_node(pgdat, sc); return; } if (!can_age_anon_pages(pgdat, sc)) return; lruvec = mem_cgroup_lruvec(NULL, pgdat); if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) return; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { lruvec = mem_cgroup_lruvec(memcg, pgdat); shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); memcg = mem_cgroup_iter(NULL, memcg, NULL); } while (memcg); } static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) { int i; struct zone *zone; /* * Check for watermark boosts top-down as the higher zones * are more likely to be boosted. Both watermarks and boosts * should not be checked at the same time as reclaim would * start prematurely when there is no boosting and a lower * zone is balanced. */ for (i = highest_zoneidx; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (zone->watermark_boost) return true; } return false; } /* * Returns true if there is an eligible zone balanced for the request order * and highest_zoneidx */ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long mark = -1; struct zone *zone; /* * Check watermarks bottom-up as lower zones are more likely to * meet watermarks. */ for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) mark = promo_wmark_pages(zone); else mark = high_wmark_pages(zone); if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) return true; } /* * If a node has no managed zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ if (mark == -1) return true; return false; } /* Clear pgdat state for congested, dirty or under writeback. */ static void clear_pgdat_congested(pg_data_t *pgdat) { struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); clear_bit(LRUVEC_NODE_CONGESTED, &lruvec->flags); clear_bit(LRUVEC_CGROUP_CONGESTED, &lruvec->flags); clear_bit(PGDAT_DIRTY, &pgdat->flags); clear_bit(PGDAT_WRITEBACK, &pgdat->flags); } /* * Prepare kswapd for sleeping. This verifies that there are no processes * waiting in throttle_direct_reclaim() and that watermarks have been met. * * Returns true if kswapd is ready to sleep */ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int highest_zoneidx) { /* * The throttled processes are normally woken up in balance_pgdat() as * soon as allow_direct_reclaim() is true. But there is a potential * race between when kswapd checks the watermarks and a process gets * throttled. There is also a potential race if processes get * throttled, kswapd wakes, a large process exits thereby balancing the * zones, which causes kswapd to exit balance_pgdat() before reaching * the wake up checks. If kswapd is going to sleep, no process should * be sleeping on pfmemalloc_wait, so wake them now if necessary. If * the wake up is premature, processes will wake kswapd and get * throttled again. The difference from wake ups in balance_pgdat() is * that here we are under prepare_to_wait(). */ if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait); /* Hopeless node, leave it to direct reclaim */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; if (pgdat_balanced(pgdat, order, highest_zoneidx)) { clear_pgdat_congested(pgdat); return true; } return false; } /* * kswapd shrinks a node of pages that are at or below the highest usable * zone that is currently unbalanced. * * Returns true if kswapd scanned at least the requested number of pages to * reclaim or if the lack of progress was due to pages under writeback. * This is used to determine if the scanning priority needs to be raised. */ static bool kswapd_shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct zone *zone; int z; unsigned long nr_reclaimed = sc->nr_reclaimed; /* Reclaim a number of pages proportional to the number of zones */ sc->nr_to_reclaim = 0; for (z = 0; z <= sc->reclaim_idx; z++) { zone = pgdat->node_zones + z; if (!managed_zone(zone)) continue; sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); } /* * Historically care was taken to put equal pressure on all zones but * now pressure is applied based on node LRU order. */ shrink_node(pgdat, sc); /* * Fragmentation may mean that the system cannot be rebalanced for * high-order allocations. If twice the allocation size has been * reclaimed then recheck watermarks only at order-0 to prevent * excessive reclaim. Assume that a process requested a high-order * can direct reclaim/compact. */ if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) sc->order = 0; /* account for progress from mm_account_reclaimed_pages() */ return max(sc->nr_scanned, sc->nr_reclaimed - nr_reclaimed) >= sc->nr_to_reclaim; } /* Page allocator PCP high watermark is lowered if reclaim is active. */ static inline void update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active) { int i; struct zone *zone; for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (active) set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); else clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); } } static inline void set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, true); } static inline void clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, false); } /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is * balanced. * * Returns the order kswapd finished reclaiming at. * * kswapd scans the zones in the highmem->normal->dma direction. It skips * zones which have free_pages > high_wmark_pages(zone), but once a zone is * found to have free_pages <= high_wmark_pages(zone), any page in that zone * or lower is eligible for reclaim until at least one usable zone is * balanced. */ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; unsigned long pflags; unsigned long nr_boost_reclaim; unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; bool boosted; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .order = order, .may_unmap = 1, }; set_task_reclaim_state(current, &sc.reclaim_state); psi_memstall_enter(&pflags); __fs_reclaim_acquire(_THIS_IP_); count_vm_event(PAGEOUTRUN); /* * Account for the reclaim boost. Note that the zone boost is left in * place so that parallel allocations that are near the watermark will * stall or direct reclaim until kswapd is finished. */ nr_boost_reclaim = 0; for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; nr_boost_reclaim += zone->watermark_boost; zone_boosts[i] = zone->watermark_boost; } boosted = nr_boost_reclaim; restart: set_reclaim_active(pgdat, highest_zoneidx); sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true; bool balanced; bool ret; bool was_frozen; sc.reclaim_idx = highest_zoneidx; /* * If the number of buffer_heads exceeds the maximum allowed * then consider reclaiming from all zones. This has a dual * purpose -- on 64-bit systems it is expected that * buffer_heads are stripped during active rotation. On 32-bit * systems, highmem pages can pin lowmem memory and shrinking * buffers can relieve lowmem pressure. Reclaim may still not * go ahead if all eligible zones for the original allocation * request are balanced to avoid excessive reclaim from kswapd. */ if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; sc.reclaim_idx = i; break; } } /* * If the pgdat is imbalanced then ignore boosting and preserve * the watermarks for a later time and restart. Note that the * zone watermarks will be still reset at the end of balancing * on the grounds that the normal reclaim should be enough to * re-evaluate if boosting is required when kswapd next wakes. */ balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); if (!balanced && nr_boost_reclaim) { nr_boost_reclaim = 0; goto restart; } /* * If boosting is not active then only reclaim if there are no * eligible zones. Note that sc.reclaim_idx is not used as * buffer_heads_over_limit may have adjusted it. */ if (!nr_boost_reclaim && balanced) goto out; /* Limit the priority of boosting to avoid reclaim writeback */ if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) raise_priority = false; /* * Do not writeback or swap pages for boosted reclaim. The * intent is to relieve pressure not issue sub-optimal IO * from reclaim context. If no pages are reclaimed, the * reclaim will be aborted. */ sc.may_writepage = !laptop_mode && !nr_boost_reclaim; sc.may_swap = !nr_boost_reclaim; /* * Do some background aging, to give pages a chance to be * referenced before reclaiming. All pages are rotated * regardless of classzone as this is about consistent aging. */ kswapd_age_node(pgdat, &sc); /* * If we're getting trouble reclaiming, start doing writepage * even in laptop mode. */ if (sc.priority < DEF_PRIORITY - 2) sc.may_writepage = 1; /* Call soft limit reclaim before calling shrink_node. */ sc.nr_scanned = 0; nr_soft_scanned = 0; nr_soft_reclaimed = memcg1_soft_limit_reclaim(pgdat, sc.order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; /* * There should be no need to raise the scanning priority if * enough pages are already being scanned that that high * watermark would be met at 100% efficiency. */ if (kswapd_shrink_node(pgdat, &sc)) raise_priority = false; /* * If the low watermark is met there is no need for processes * to be throttled on pfmemalloc_wait as they should not be * able to safely make forward progress. Wake them */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && allow_direct_reclaim(pgdat)) wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ __fs_reclaim_release(_THIS_IP_); ret = kthread_freezable_should_stop(&was_frozen); __fs_reclaim_acquire(_THIS_IP_); if (was_frozen || ret) break; /* * Raise priority if scanning rate is too low or there was no * progress in reclaiming pages */ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); /* * If reclaim made no progress for a boost, stop reclaim as * IO cannot be queued and it could be an infinite loop in * extreme circumstances. */ if (nr_boost_reclaim && !nr_reclaimed) break; if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1); /* * Restart only if it went through the priority loop all the way, * but cache_trim_mode didn't work. */ if (!sc.nr_reclaimed && sc.priority < 1 && !sc.no_cache_trim_mode && sc.cache_trim_mode_failed) { sc.no_cache_trim_mode = 1; goto restart; } if (!sc.nr_reclaimed) pgdat->kswapd_failures++; out: clear_reclaim_active(pgdat, highest_zoneidx); /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; for (i = 0; i <= highest_zoneidx; i++) { if (!zone_boosts[i]) continue; /* Increments are under the zone lock */ zone = pgdat->node_zones + i; spin_lock_irqsave(&zone->lock, flags); zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); spin_unlock_irqrestore(&zone->lock, flags); } /* * As there is now likely space, wakeup kcompact to defragment * pageblocks. */ wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); } snapshot_refaults(NULL, pgdat); __fs_reclaim_release(_THIS_IP_); psi_memstall_leave(&pflags); set_task_reclaim_state(current, NULL); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller * entered the allocator slow path while kswapd was awake, order will * remain at the higher level. */ return sc.order; } /* * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is * not a valid index then either kswapd runs for first time or kswapd couldn't * sleep after previous reclaim attempt (node is still unbalanced). In that * case return the zone index of the previous kswapd reclaim cycle. */ static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, enum zone_type prev_highest_zoneidx) { enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, unsigned int highest_zoneidx) { long remaining = 0; DEFINE_WAIT(wait); if (freezing(current) || kthread_should_stop()) return; prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* * Try to sleep for a short interval. Note that kcompactd will only be * woken if it is possible to sleep for a short interval. This is * deliberate on the assumption that if reclaim cannot keep an * eligible zone balanced that it's also unlikely that compaction will * succeed. */ if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. * When kswapd is going to sleep, it is reasonable to assume * that pages and compaction may succeed so reset the cache. */ reset_isolation_suitable(pgdat); /* * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); remaining = schedule_timeout(HZ/10); /* * If woken prematurely then reset kswapd_highest_zoneidx and * order. The values will either be from a wakeup request or * the previous request that slept prematurely. */ if (remaining) { WRITE_ONCE(pgdat->kswapd_highest_zoneidx, kswapd_highest_zoneidx(pgdat, highest_zoneidx)); if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); } /* * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ if (!remaining && prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* * vmstat counters are not perfectly accurate and the estimated * value for counters such as NR_FREE_PAGES can deviate from the * true value by nr_online_cpus * threshold. To avoid the zone * watermarks being breached while under pressure, we reduce the * per-cpu vmstat threshold while kswapd is awake and restore * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); if (!kthread_should_stop()) schedule(); set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); else count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); } finish_wait(&pgdat->kswapd_wait, &wait); } /* * The background pageout daemon, started as a kernel thread * from the init process. * * This basically trickles out pages so that we have _some_ * free memory available even if there is no other activity * that frees anything up. This is needed for things like routing * etc, where we otherwise might have all activity going on in * asynchronous contexts that cannot page things out. * * If there are applications that are active memory-allocators * (most normal use), this basically shouldn't matter. */ static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; unsigned int highest_zoneidx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t *)p; struct task_struct *tsk = current; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(tsk, cpumask); /* * Tell the memory management that we're a "memory allocator", * and that if we need more memory we should get access to it * regardless (see "__alloc_pages()"). "kswapd" should * never get caught in the normal page freeing logic. * * (Kswapd normally doesn't need memory anyway, but sometimes * you need a small amount of memory in order to be able to * page out something else, and this flag essentially protects * us from recursively trying to free more memory as we're * trying to free the first piece of memory in the first place). */ tsk->flags |= PF_MEMALLOC | PF_KSWAPD; set_freezable(); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); atomic_set(&pgdat->nr_writeback_throttled, 0); for ( ; ; ) { bool was_frozen; alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, highest_zoneidx); /* Read the new order and highest_zoneidx */ alloc_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); if (kthread_freezable_should_stop(&was_frozen)) break; /* * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ if (was_frozen) continue; /* * Reclaim begins at the requested order but if a high-order * reclaim fails then kswapd falls back to reclaiming for * order-0. If that happens, kswapd will consider sleeping * for the order it finished reclaiming at (reclaim_order) * but kcompactd is woken to compact for the original * request (alloc_order). */ trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); reclaim_order = balance_pgdat(pgdat, alloc_order, highest_zoneidx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; } tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD); return 0; } /* * A zone is low on free memory or too fragmented for high-order memory. If * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's * pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim * has failed or is not needed, still wake up kcompactd if only compaction is * needed. */ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, enum zone_type highest_zoneidx) { pg_data_t *pgdat; enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; pgdat = zone->zone_pgdat; curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); if (READ_ONCE(pgdat->kswapd_order) < order) WRITE_ONCE(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || (pgdat_balanced(pgdat, order, highest_zoneidx) && !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd * and rely on compaction_suitable() to determine if it's * needed. If it fails, it will defer subsequent attempts to * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) wakeup_kcompactd(pgdat, order, highest_zoneidx); return; } trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, gfp_flags); wake_up_interruptible(&pgdat->kswapd_wait); } #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of * freed pages. * * Rather than trying to age LRUs the aim is to preserve the overall * LRU order by reclaiming preferentially * inactive > active > active referenced > active mapped */ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) { struct scan_control sc = { .nr_to_reclaim = nr_to_reclaim, .gfp_mask = GFP_HIGHUSER_MOVABLE, .reclaim_idx = MAX_NR_ZONES - 1, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .hibernation_mode = 1, }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); unsigned long nr_reclaimed; unsigned int noreclaim_flag; fs_reclaim_acquire(sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(current, &sc.reclaim_state); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); set_task_reclaim_state(current, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); return nr_reclaimed; } #endif /* CONFIG_HIBERNATION */ /* * This kswapd start function will be called by init and node-hot-add. */ void __meminit kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); pgdat_kswapd_lock(pgdat); if (!pgdat->kswapd) { pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ pr_err("Failed to start kswapd on node %d，ret=%ld\n", nid, PTR_ERR(pgdat->kswapd)); BUG_ON(system_state < SYSTEM_RUNNING); pgdat->kswapd = NULL; } } pgdat_kswapd_unlock(pgdat); } /* * Called by memory hotplug when all memory in a node is offlined. Caller must * be holding mem_hotplug_begin/done(). */ void __meminit kswapd_stop(int nid) { pg_data_t *pgdat = NODE_DATA(nid); struct task_struct *kswapd; pgdat_kswapd_lock(pgdat); kswapd = pgdat->kswapd; if (kswapd) { kthread_stop(kswapd); pgdat->kswapd = NULL; } pgdat_kswapd_unlock(pgdat); } static int __init kswapd_init(void) { int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); return 0; } module_init(kswapd_init) #ifdef CONFIG_NUMA /* * Node reclaim mode * * If non-zero call node_reclaim when the number of free pages falls below * the watermarks. */ int node_reclaim_mode __read_mostly; /* * Priority for NODE_RECLAIM. This determines the fraction of pages * of a node considered for each zone_reclaim. 4 scans 1/16th of * a zone. */ #define NODE_RECLAIM_PRIORITY 4 /* * Percentage of pages in a zone that must be unmapped for node_reclaim to * occur. */ int sysctl_min_unmapped_ratio = 1; /* * If the number of slab pages in a zone grows beyond this percentage then * slab reclaim needs to occur. */ int sysctl_min_slab_ratio = 5; static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) { unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + node_page_state(pgdat, NR_ACTIVE_FILE); /* * It's possible for there to be more file mapped pages than * accounted for by the pages on the file LRU lists because * tmpfs pages accounted for as ANON can also be FILE_MAPPED */ return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; } /* Work out how many page cache pages we can reclaim in this reclaim_mode */ static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) { unsigned long nr_pagecache_reclaimable; unsigned long delta = 0; /* * If RECLAIM_UNMAP is set, then all file pages are considered * potentially reclaimable. Otherwise, we have to worry about * pages like swapcache and node_unmapped_file_pages() provides * a better estimate */ if (node_reclaim_mode & RECLAIM_UNMAP) nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); else nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); /* If we can't clean pages, remove dirty pages from consideration */ if (!(node_reclaim_mode & RECLAIM_WRITE)) delta += node_page_state(pgdat, NR_FILE_DIRTY); /* Watch for any possible underflows due to delta */ if (unlikely(delta > nr_pagecache_reclaimable)) delta = nr_pagecache_reclaimable; return nr_pagecache_reclaimable - delta; } /* * Try to free up some pages from this node through reclaim. */ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { /* Minimum pages needed in order to stay on node */ const unsigned long nr_pages = 1 << order; struct task_struct *p = current; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = current_gfp_context(gfp_mask), .order = order, .priority = NODE_RECLAIM_PRIORITY, .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), .may_swap = 1, .reclaim_idx = gfp_zone(gfp_mask), }; unsigned long pflags; trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, sc.gfp_mask); cond_resched(); psi_memstall_enter(&pflags); delayacct_freepages_start(); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP */ noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(p, &sc.reclaim_state); if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages || node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) { /* * Free memory by calling shrink node with increasing * priorities until we have enough memory freed. */ do { shrink_node(pgdat, &sc); } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); } set_task_reclaim_state(p, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); psi_memstall_leave(&pflags); delayacct_freepages_end(); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); return sc.nr_reclaimed >= nr_pages; } int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { int ret; /* * Node reclaim reclaims unmapped file backed pages and * slab pages if we are over the defined limits. * * A small portion of unmapped file backed pages is needed for * file I/O otherwise pages read by file I/O will be immediately * thrown out if the node is overallocated. So we do not reclaim * if less than a specified percentage of the node is used by * unmapped file backed pages. */ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL; /* * Do not scan if the allocation should not be delayed. */ if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) return NODE_RECLAIM_NOSCAN; /* * Only run node reclaim on the local node or on nodes that do not * have associated processors. This will favor the local processor * over remote processors and spread off node memory allocations * as wide as possible. */ if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) return NODE_RECLAIM_NOSCAN; if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) return NODE_RECLAIM_NOSCAN; ret = __node_reclaim(pgdat, gfp_mask, order); clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags); if (ret) count_vm_event(PGSCAN_ZONE_RECLAIM_SUCCESS); else count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); return ret; } #endif /** * check_move_unevictable_folios - Move evictable folios to appropriate zone * lru list * @fbatch: Batch of lru folios to check. * * Checks folios for evictability, if an evictable folio is in the unevictable * lru list, moves it to the appropriate evictable lru list. This function * should be only used for lru folios. */ void check_move_unevictable_folios(struct folio_batch *fbatch) { struct lruvec *lruvec = NULL; int pgscanned = 0; int pgrescued = 0; int i; for (i = 0; i < fbatch->nr; i++) { struct folio *folio = fbatch->folios[i]; int nr_pages = folio_nr_pages(folio); pgscanned += nr_pages; /* block memcg migration while the folio moves between lrus */ if (!folio_test_clear_lru(folio)) continue; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (folio_evictable(folio) && folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); pgrescued += nr_pages; } folio_set_lru(folio); } if (lruvec) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); unlock_page_lruvec_irq(lruvec); } else if (pgscanned) { count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); } } EXPORT_SYMBOL_GPL(check_move_unevictable_folios); |
| 4 1 4 22 14 14 14 1 2 2 2 11 11 11 11 23 23 22 23 23 23 23 23 22 1 1 1 2 23 22 23 23 23 23 22 22 22 23 23 1 23 22 22 21 23 3 3 3 3 22 3 11 34 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * inode.c - part of debugfs, a tiny little debug file system * * Copyright (C) 2004,2019 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Inc. * Copyright (C) 2019 Linux Foundation <gregkh@linuxfoundation.org> * * debugfs is for people to use instead of /proc or /sys. * See ./Documentation/core-api/kernel-api.rst for more details. */ #define pr_fmt(fmt) "debugfs: " fmt #include <linux/module.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/kobject.h> #include <linux/namei.h> #include <linux/debugfs.h> #include <linux/fsnotify.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/security.h> #include "internal.h" #define DEBUGFS_DEFAULT_MODE 0700 static struct vfsmount *debugfs_mount; static int debugfs_mount_count; static bool debugfs_registered; static unsigned int debugfs_allow __ro_after_init = DEFAULT_DEBUGFS_ALLOW_BITS; /* * Don't allow access attributes to be changed whilst the kernel is locked down * so that we can use the file mode as part of a heuristic to determine whether * to lock down individual files. */ static int debugfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *ia) { int ret; if (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) { ret = security_locked_down(LOCKDOWN_DEBUGFS); if (ret) return ret; } return simple_setattr(&nop_mnt_idmap, dentry, ia); } static const struct inode_operations debugfs_file_inode_operations = { .setattr = debugfs_setattr, }; static const struct inode_operations debugfs_dir_inode_operations = { .lookup = simple_lookup, .setattr = debugfs_setattr, }; static const struct inode_operations debugfs_symlink_inode_operations = { .get_link = simple_get_link, .setattr = debugfs_setattr, }; static struct inode *debugfs_get_inode(struct super_block *sb) { struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); simple_inode_init_ts(inode); } return inode; } struct debugfs_fs_info { kuid_t uid; kgid_t gid; umode_t mode; /* Opt_* bitfield. */ unsigned int opts; }; enum { Opt_uid, Opt_gid, Opt_mode, Opt_source, }; static const struct fs_parameter_spec debugfs_param_specs[] = { fsparam_gid ("gid", Opt_gid), fsparam_u32oct ("mode", Opt_mode), fsparam_uid ("uid", Opt_uid), fsparam_string ("source", Opt_source), {} }; static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct debugfs_fs_info *opts = fc->s_fs_info; struct fs_parse_result result; int opt; opt = fs_parse(fc, debugfs_param_specs, param, &result); if (opt < 0) { /* * We might like to report bad mount options here; but * traditionally debugfs has ignored all mount options */ if (opt == -ENOPARAM) return 0; return opt; } switch (opt) { case Opt_uid: opts->uid = result.uid; break; case Opt_gid: opts->gid = result.gid; break; case Opt_mode: opts->mode = result.uint_32 & S_IALLUGO; break; case Opt_source: if (fc->source) return invalfc(fc, "Multiple sources specified"); fc->source = param->string; param->string = NULL; break; /* * We might like to report bad mount options here; * but traditionally debugfs has ignored all mount options */ } opts->opts |= BIT(opt); return 0; } static void _debugfs_apply_options(struct super_block *sb, bool remount) { struct debugfs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); /* * On remount, only reset mode/uid/gid if they were provided as mount * options. */ if (!remount || fsi->opts & BIT(Opt_mode)) { inode->i_mode &= ~S_IALLUGO; inode->i_mode |= fsi->mode; } if (!remount || fsi->opts & BIT(Opt_uid)) inode->i_uid = fsi->uid; if (!remount || fsi->opts & BIT(Opt_gid)) inode->i_gid = fsi->gid; } static void debugfs_apply_options(struct super_block *sb) { _debugfs_apply_options(sb, false); } static void debugfs_apply_options_remount(struct super_block *sb) { _debugfs_apply_options(sb, true); } static int debugfs_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct debugfs_fs_info *sb_opts = sb->s_fs_info; struct debugfs_fs_info *new_opts = fc->s_fs_info; sync_filesystem(sb); /* structure copy of new mount options to sb */ *sb_opts = *new_opts; debugfs_apply_options_remount(sb); return 0; } static int debugfs_show_options(struct seq_file *m, struct dentry *root) { struct debugfs_fs_info *fsi = root->d_sb->s_fs_info; if (!uid_eq(fsi->uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, fsi->uid)); if (!gid_eq(fsi->gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, fsi->gid)); if (fsi->mode != DEBUGFS_DEFAULT_MODE) seq_printf(m, ",mode=%o", fsi->mode); return 0; } static void debugfs_free_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); free_inode_nonrcu(inode); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .show_options = debugfs_show_options, .free_inode = debugfs_free_inode, }; static void debugfs_release_dentry(struct dentry *dentry) { struct debugfs_fsdata *fsd = dentry->d_fsdata; if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) return; /* check it wasn't a dir (no fsdata) or automount (no real_fops) */ if (fsd && fsd->real_fops) { WARN_ON(!list_empty(&fsd->cancellations)); mutex_destroy(&fsd->cancellations_mtx); } kfree(fsd); } static struct vfsmount *debugfs_automount(struct path *path) { struct debugfs_fsdata *fsd = path->dentry->d_fsdata; return fsd->automount(path->dentry, d_inode(path->dentry)->i_private); } static const struct dentry_operations debugfs_dops = { .d_delete = always_delete_dentry, .d_release = debugfs_release_dentry, .d_automount = debugfs_automount, }; static int debugfs_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr debug_files[] = {{""}}; int err; err = simple_fill_super(sb, DEBUGFS_MAGIC, debug_files); if (err) return err; sb->s_op = &debugfs_super_operations; sb->s_d_op = &debugfs_dops; debugfs_apply_options(sb); return 0; } static int debugfs_get_tree(struct fs_context *fc) { if (!(debugfs_allow & DEBUGFS_ALLOW_API)) return -EPERM; return get_tree_single(fc, debugfs_fill_super); } static void debugfs_free_fc(struct fs_context *fc) { kfree(fc->s_fs_info); } static const struct fs_context_operations debugfs_context_ops = { .free = debugfs_free_fc, .parse_param = debugfs_parse_param, .get_tree = debugfs_get_tree, .reconfigure = debugfs_reconfigure, }; static int debugfs_init_fs_context(struct fs_context *fc) { struct debugfs_fs_info *fsi; fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL); if (!fsi) return -ENOMEM; fsi->mode = DEBUGFS_DEFAULT_MODE; fc->s_fs_info = fsi; fc->ops = &debugfs_context_ops; return 0; } static struct file_system_type debug_fs_type = { .owner = THIS_MODULE, .name = "debugfs", .init_fs_context = debugfs_init_fs_context, .parameters = debugfs_param_specs, .kill_sb = kill_litter_super, }; MODULE_ALIAS_FS("debugfs"); /** * debugfs_lookup() - look up an existing debugfs file * @name: a pointer to a string containing the name of the file to look up. * @parent: a pointer to the parent dentry of the file. * * This function will return a pointer to a dentry if it succeeds. If the file * doesn't exist or an error occurs, %NULL will be returned. The returned * dentry must be passed to dput() when it is no longer needed. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) { struct dentry *dentry; if (!debugfs_initialized() || IS_ERR_OR_NULL(name) || IS_ERR(parent)) return NULL; if (!parent) parent = debugfs_mount->mnt_root; dentry = lookup_positive_unlocked(name, parent, strlen(name)); if (IS_ERR(dentry)) return NULL; return dentry; } EXPORT_SYMBOL_GPL(debugfs_lookup); static struct dentry *start_creating(const char *name, struct dentry *parent) { struct dentry *dentry; int error; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) return ERR_PTR(-EPERM); if (!debugfs_initialized()) return ERR_PTR(-ENOENT); pr_debug("creating file '%s'\n", name); if (IS_ERR(parent)) return parent; error = simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); if (error) { pr_err("Unable to pin filesystem for file '%s'\n", name); return ERR_PTR(error); } /* If the parent is not specified, we create it in the root. * We need the root dentry to do this, which is in the super * block. A pointer to that is in the struct vfsmount that we * have around. */ if (!parent) parent = debugfs_mount->mnt_root; inode_lock(d_inode(parent)); if (unlikely(IS_DEADDIR(d_inode(parent)))) dentry = ERR_PTR(-ENOENT); else dentry = lookup_one_len(name, parent, strlen(name)); if (!IS_ERR(dentry) && d_really_is_positive(dentry)) { if (d_is_dir(dentry)) pr_err("Directory '%s' with parent '%s' already present!\n", name, parent->d_name.name); else pr_err("File '%s' in directory '%s' already present!\n", name, parent->d_name.name); dput(dentry); dentry = ERR_PTR(-EEXIST); } if (IS_ERR(dentry)) { inode_unlock(d_inode(parent)); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } return dentry; } static struct dentry *failed_creating(struct dentry *dentry) { inode_unlock(d_inode(dentry->d_parent)); dput(dentry); simple_release_fs(&debugfs_mount, &debugfs_mount_count); return ERR_PTR(-ENOMEM); } static struct dentry *end_creating(struct dentry *dentry) { inode_unlock(d_inode(dentry->d_parent)); return dentry; } static struct dentry *__debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *proxy_fops, const struct file_operations *real_fops) { struct dentry *dentry; struct inode *inode; if (!(mode & S_IFMT)) mode |= S_IFREG; BUG_ON(!S_ISREG(mode)); dentry = start_creating(name, parent); if (IS_ERR(dentry)) return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create file '%s'\n", name); return failed_creating(dentry); } inode->i_mode = mode; inode->i_private = data; inode->i_op = &debugfs_file_inode_operations; inode->i_fop = proxy_fops; dentry->d_fsdata = (void *)((unsigned long)real_fops | DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); d_instantiate(dentry, inode); fsnotify_create(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } /** * debugfs_create_file - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * * This is the basic "create a file" function for debugfs. It allows for a * wide range of flexibility in creating a file, or a directory (if you want * to create a directory, the debugfs_create_dir() function is * recommended to be used instead.) * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. * * NOTE: it's expected that most callers should _ignore_ the errors returned * by this function. Other debugfs functions handle the fact that the "dentry" * passed to them could be an error and they don't crash in that case. * Drivers should generally work fine even if debugfs fails to init anyway. */ struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { return __debugfs_create_file(name, mode, parent, data, fops ? &debugfs_full_proxy_file_operations : &debugfs_noop_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file); /** * debugfs_create_file_unsafe - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * * debugfs_create_file_unsafe() is completely analogous to * debugfs_create_file(), the only difference being that the fops * handed it will not get protected against file removals by the * debugfs core. * * It is your responsibility to protect your struct file_operation * methods against file removals by means of debugfs_file_get() * and debugfs_file_put(). ->open() is still protected by * debugfs though. * * Any struct file_operations defined by means of * DEFINE_DEBUGFS_ATTRIBUTE() is protected against file removals and * thus, may be used here. */ struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { return __debugfs_create_file(name, mode, parent, data, fops ? &debugfs_open_proxy_file_operations : &debugfs_noop_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); /** * debugfs_create_file_size - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * @file_size: initial file size * * This is the basic "create a file" function for debugfs. It allows for a * wide range of flexibility in creating a file, or a directory (if you want * to create a directory, the debugfs_create_dir() function is * recommended to be used instead.) */ void debugfs_create_file_size(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops, loff_t file_size) { struct dentry *de = debugfs_create_file(name, mode, parent, data, fops); if (!IS_ERR(de)) d_inode(de)->i_size = file_size; } EXPORT_SYMBOL_GPL(debugfs_create_file_size); /** * debugfs_create_dir - create a directory in the debugfs filesystem * @name: a pointer to a string containing the name of the directory to * create. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * directory will be created in the root of the debugfs filesystem. * * This function creates a directory in debugfs with the given name. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. * * NOTE: it's expected that most callers should _ignore_ the errors returned * by this function. Other debugfs functions handle the fact that the "dentry" * passed to them could be an error and they don't crash in that case. * Drivers should generally work fine even if debugfs fails to init anyway. */ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) { struct dentry *dentry = start_creating(name, parent); struct inode *inode; if (IS_ERR(dentry)) return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create directory '%s'\n", name); return failed_creating(dentry); } inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; inode->i_op = &debugfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_dir); /** * debugfs_create_automount - create automount point in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @f: function to be called when pathname resolution steps on that one. * @data: opaque argument to pass to f(). * * @f should return what ->d_automount() would. */ struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, debugfs_automount_t f, void *data) { struct dentry *dentry = start_creating(name, parent); struct debugfs_fsdata *fsd; struct inode *inode; if (IS_ERR(dentry)) return dentry; fsd = kzalloc(sizeof(*fsd), GFP_KERNEL); if (!fsd) { failed_creating(dentry); return ERR_PTR(-ENOMEM); } fsd->automount = f; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); kfree(fsd); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create automount '%s'\n", name); kfree(fsd); return failed_creating(dentry); } make_empty_dir_inode(inode); inode->i_flags |= S_AUTOMOUNT; inode->i_private = data; dentry->d_fsdata = fsd; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } EXPORT_SYMBOL(debugfs_create_automount); /** * debugfs_create_symlink- create a symbolic link in the debugfs filesystem * @name: a pointer to a string containing the name of the symbolic link to * create. * @parent: a pointer to the parent dentry for this symbolic link. This * should be a directory dentry if set. If this parameter is NULL, * then the symbolic link will be created in the root of the debugfs * filesystem. * @target: a pointer to a string containing the path to the target of the * symbolic link. * * This function creates a symbolic link with the given name in debugfs that * links to the given target path. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the symbolic * link is to be removed (no automatic cleanup happens if your module is * unloaded, you are responsible here.) If an error occurs, ERR_PTR(-ERROR) * will be returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *target) { struct dentry *dentry; struct inode *inode; char *link = kstrdup(target, GFP_KERNEL); if (!link) return ERR_PTR(-ENOMEM); dentry = start_creating(name, parent); if (IS_ERR(dentry)) { kfree(link); return dentry; } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create symlink '%s'\n", name); kfree(link); return failed_creating(dentry); } inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_op = &debugfs_symlink_inode_operations; inode->i_link = link; d_instantiate(dentry, inode); return end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_symlink); static void __debugfs_file_removed(struct dentry *dentry) { struct debugfs_fsdata *fsd; /* * Paired with the closing smp_mb() implied by a successful * cmpxchg() in debugfs_file_get(): either * debugfs_file_get() must see a dead dentry or we must see a * debugfs_fsdata instance at ->d_fsdata here (or both). */ smp_mb(); fsd = READ_ONCE(dentry->d_fsdata); if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) return; /* if this was the last reference, we're done */ if (refcount_dec_and_test(&fsd->active_users)) return; /* * If there's still a reference, the code that obtained it can * be in different states: * - The common case of not using cancellations, or already * after debugfs_leave_cancellation(), where we just need * to wait for debugfs_file_put() which signals the completion; * - inside a cancellation section, i.e. between * debugfs_enter_cancellation() and debugfs_leave_cancellation(), * in which case we need to trigger the ->cancel() function, * and then wait for debugfs_file_put() just like in the * previous case; * - before debugfs_enter_cancellation() (but obviously after * debugfs_file_get()), in which case we may not see the * cancellation in the list on the first round of the loop, * but debugfs_enter_cancellation() signals the completion * after adding it, so this code gets woken up to call the * ->cancel() function. */ while (refcount_read(&fsd->active_users)) { struct debugfs_cancellation *c; /* * Lock the cancellations. Note that the cancellations * structs are meant to be on the stack, so we need to * ensure we either use them here or don't touch them, * and debugfs_leave_cancellation() will wait for this * to be finished processing before exiting one. It may * of course win and remove the cancellation, but then * chances are we never even got into this bit, we only * do if the refcount isn't zero already. */ mutex_lock(&fsd->cancellations_mtx); while ((c = list_first_entry_or_null(&fsd->cancellations, typeof(*c), list))) { list_del_init(&c->list); c->cancel(dentry, c->cancel_data); } mutex_unlock(&fsd->cancellations_mtx); wait_for_completion(&fsd->active_users_drained); } } static void remove_one(struct dentry *victim) { if (d_is_reg(victim)) __debugfs_file_removed(victim); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } /** * debugfs_remove - recursively removes a directory * @dentry: a pointer to a the dentry of the directory to be removed. If this * parameter is NULL or an error value, nothing will be done. * * This function recursively removes a directory tree in debugfs that * was previously created with a call to another debugfs function * (like debugfs_create_file() or variants thereof.) * * This function is required to be called in order for the file to be * removed, no automatic cleanup of files will happen when a module is * removed, you are responsible here. */ void debugfs_remove(struct dentry *dentry) { if (IS_ERR_OR_NULL(dentry)) return; simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); simple_recursive_removal(dentry, remove_one); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } EXPORT_SYMBOL_GPL(debugfs_remove); /** * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it * @name: a pointer to a string containing the name of the item to look up. * @parent: a pointer to the parent dentry of the item. * * This is the equlivant of doing something like * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting * handled for the directory being looked up. */ void debugfs_lookup_and_remove(const char *name, struct dentry *parent) { struct dentry *dentry; dentry = debugfs_lookup(name, parent); if (!dentry) return; debugfs_remove(dentry); dput(dentry); } EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); /** * debugfs_rename - rename a file/directory in the debugfs filesystem * @old_dir: a pointer to the parent dentry for the renamed object. This * should be a directory dentry. * @old_dentry: dentry of an object to be renamed. * @new_dir: a pointer to the parent dentry where the object should be * moved. This should be a directory dentry. * @new_name: a pointer to a string containing the target name. * * This function renames a file/directory in debugfs. The target must not * exist for rename to succeed. * * This function will return a pointer to old_dentry (which is updated to * reflect renaming) if it succeeds. If an error occurs, ERR_PTR(-ERROR) * will be returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *new_dir, const char *new_name) { int error; struct dentry *dentry = NULL, *trap; struct name_snapshot old_name; if (IS_ERR(old_dir)) return old_dir; if (IS_ERR(new_dir)) return new_dir; if (IS_ERR_OR_NULL(old_dentry)) return old_dentry; trap = lock_rename(new_dir, old_dir); /* Source or destination directories don't exist? */ if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir)) goto exit; /* Source does not exist, cyclic rename, or mountpoint? */ if (d_really_is_negative(old_dentry) || old_dentry == trap || d_mountpoint(old_dentry)) goto exit; dentry = lookup_one_len(new_name, new_dir, strlen(new_name)); /* Lookup failed, cyclic rename or target exists? */ if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry)) goto exit; take_dentry_name_snapshot(&old_name, old_dentry); error = simple_rename(&nop_mnt_idmap, d_inode(old_dir), old_dentry, d_inode(new_dir), dentry, 0); if (error) { release_dentry_name_snapshot(&old_name); goto exit; } d_move(old_dentry, dentry); fsnotify_move(d_inode(old_dir), d_inode(new_dir), &old_name.name, d_is_dir(old_dentry), NULL, old_dentry); release_dentry_name_snapshot(&old_name); unlock_rename(new_dir, old_dir); dput(dentry); return old_dentry; exit: if (dentry && !IS_ERR(dentry)) dput(dentry); unlock_rename(new_dir, old_dir); if (IS_ERR(dentry)) return dentry; return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(debugfs_rename); /** * debugfs_initialized - Tells whether debugfs has been registered */ bool debugfs_initialized(void) { return debugfs_registered; } EXPORT_SYMBOL_GPL(debugfs_initialized); static int __init debugfs_kernel(char *str) { if (str) { if (!strcmp(str, "on")) debugfs_allow = DEBUGFS_ALLOW_API | DEBUGFS_ALLOW_MOUNT; else if (!strcmp(str, "no-mount")) debugfs_allow = DEBUGFS_ALLOW_API; else if (!strcmp(str, "off")) debugfs_allow = 0; } return 0; } early_param("debugfs", debugfs_kernel); static int __init debugfs_init(void) { int retval; if (!(debugfs_allow & DEBUGFS_ALLOW_MOUNT)) return -EPERM; retval = sysfs_create_mount_point(kernel_kobj, "debug"); if (retval) return retval; retval = register_filesystem(&debug_fs_type); if (retval) sysfs_remove_mount_point(kernel_kobj, "debug"); else debugfs_registered = true; return retval; } core_initcall(debugfs_init); |
| 499 494 293 293 495 236 292 234 293 492 492 491 91 7 7 7 7 7 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/irq_work.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/tick.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/smp.h> #include <linux/smpboot.h> #include <asm/processor.h> #include <linux/kasan.h> #include <trace/events/ipi.h> static DEFINE_PER_CPU(struct llist_head, raised_list); static DEFINE_PER_CPU(struct llist_head, lazy_list); static DEFINE_PER_CPU(struct task_struct *, irq_workd); static void wake_irq_workd(void) { struct task_struct *tsk = __this_cpu_read(irq_workd); if (!llist_empty(this_cpu_ptr(&lazy_list)) && tsk) wake_up_process(tsk); } #ifdef CONFIG_SMP static void irq_work_wake(struct irq_work *entry) { wake_irq_workd(); } static DEFINE_PER_CPU(struct irq_work, irq_work_wakeup) = IRQ_WORK_INIT_HARD(irq_work_wake); #endif static int irq_workd_should_run(unsigned int cpu) { return !llist_empty(this_cpu_ptr(&lazy_list)); } /* * Claim the entry so that no one else will poke at it. */ static bool irq_work_claim(struct irq_work *work) { int oflags; oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags); /* * If the work is already pending, no need to raise the IPI. * The pairing smp_mb() in irq_work_single() makes sure * everything we did before is visible. */ if (oflags & IRQ_WORK_PENDING) return false; return true; } void __weak arch_irq_work_raise(void) { /* * Lame architectures will get the timer tick callback */ } static __always_inline void irq_work_raise(struct irq_work *work) { if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt()) trace_ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func); arch_irq_work_raise(); } /* Enqueue on current CPU, work must already be claimed and preempt disabled */ static void __irq_work_queue_local(struct irq_work *work) { struct llist_head *list; bool rt_lazy_work = false; bool lazy_work = false; int work_flags; work_flags = atomic_read(&work->node.a_flags); if (work_flags & IRQ_WORK_LAZY) lazy_work = true; else if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(work_flags & IRQ_WORK_HARD_IRQ)) rt_lazy_work = true; if (lazy_work || rt_lazy_work) list = this_cpu_ptr(&lazy_list); else list = this_cpu_ptr(&raised_list); if (!llist_add(&work->node.llist, list)) return; /* If the work is "lazy", handle it from next tick if any */ if (!lazy_work || tick_nohz_tick_stopped()) irq_work_raise(work); } /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; /* Queue the entry and raise the IPI if needed. */ preempt_disable(); __irq_work_queue_local(work); preempt_enable(); return true; } EXPORT_SYMBOL_GPL(irq_work_queue); /* * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. * * Can be re-enqueued while the callback is still in progress. */ bool irq_work_queue_on(struct irq_work *work, int cpu) { #ifndef CONFIG_SMP return irq_work_queue(work); #else /* CONFIG_SMP: */ /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; kasan_record_aux_stack_noalloc(work); preempt_disable(); if (cpu != smp_processor_id()) { /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); /* * On PREEMPT_RT the items which are not marked as * IRQ_WORK_HARD_IRQ are added to the lazy list and a HARD work * item is used on the remote CPU to wake the thread. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ)) { if (!llist_add(&work->node.llist, &per_cpu(lazy_list, cpu))) goto out; work = &per_cpu(irq_work_wakeup, cpu); if (!irq_work_claim(work)) goto out; } __smp_call_single_queue(cpu, &work->node.llist); } else { __irq_work_queue_local(work); } out: preempt_enable(); return true; #endif /* CONFIG_SMP */ } bool irq_work_needs_cpu(void) { struct llist_head *raised, *lazy; raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); if (llist_empty(raised) || arch_irq_work_has_interrupt()) if (llist_empty(lazy)) return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); return true; } void irq_work_single(void *arg) { struct irq_work *work = arg; int flags; /* * Clear the PENDING bit, after this point the @work can be re-used. * The PENDING bit acts as a lock, and we own it, so we can clear it * without atomic ops. */ flags = atomic_read(&work->node.a_flags); flags &= ~IRQ_WORK_PENDING; atomic_set(&work->node.a_flags, flags); /* * See irq_work_claim(). */ smp_mb(); lockdep_irq_work_enter(flags); work->func(work); lockdep_irq_work_exit(flags); /* * Clear the BUSY bit, if set, and return to the free state if no-one * else claimed it meanwhile. */ (void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) rcuwait_wake_up(&work->irqwait); } static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; /* * On PREEMPT_RT IRQ-work which is not marked as HARD will be processed * in a per-CPU thread in preemptible context. Only the items which are * marked as IRQ_WORK_HARD_IRQ will be processed in hardirq context. */ BUG_ON(!irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT)); if (llist_empty(list)) return; llnode = llist_del_all(list); llist_for_each_entry_safe(work, tmp, llnode, node.llist) irq_work_single(work); } /* * hotplug calls this through: * hotplug_cfd() -> flush_smp_call_function_queue() */ void irq_work_run(void) { irq_work_run_list(this_cpu_ptr(&raised_list)); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } EXPORT_SYMBOL_GPL(irq_work_run); void irq_work_tick(void) { struct llist_head *raised = this_cpu_ptr(&raised_list); if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) irq_work_run_list(raised); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } /* * Synchronize against the irq_work @entry, ensures the entry is not * currently in use. */ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); might_sleep(); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) { rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work), TASK_UNINTERRUPTIBLE); return; } while (irq_work_is_busy(work)) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); static void run_irq_workd(unsigned int cpu) { irq_work_run_list(this_cpu_ptr(&lazy_list)); } static void irq_workd_setup(unsigned int cpu) { sched_set_fifo_low(current); } static struct smp_hotplug_thread irqwork_threads = { .store = &irq_workd, .setup = irq_workd_setup, .thread_should_run = irq_workd_should_run, .thread_fn = run_irq_workd, .thread_comm = "irq_work/%u", }; static __init int irq_work_init_threads(void) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) BUG_ON(smpboot_register_percpu_thread(&irqwork_threads)); return 0; } early_initcall(irq_work_init_threads); |
| 23 246 101 249 244 117 135 7 5 249 248 249 245 245 72 86 61 97 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NETFILTER_H #define __LINUX_NETFILTER_H #include <linux/init.h> #include <linux/skbuff.h> #include <linux/net.h> #include <linux/if.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/wait.h> #include <linux/list.h> #include <linux/static_key.h> #include <linux/module.h> #include <linux/netfilter_defs.h> #include <linux/netdevice.h> #include <linux/sockptr.h> #include <net/net_namespace.h> static inline int NF_DROP_GETERR(int verdict) { return -(verdict >> NF_VERDICT_QBITS); } static __always_inline int NF_DROP_REASON(struct sk_buff *skb, enum skb_drop_reason reason, u32 err) { BUILD_BUG_ON(err > 0xffff); kfree_skb_reason(skb, reason); return ((err << 16) | NF_STOLEN); } static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ul2 = (const unsigned long *)a2; return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; #else return a1->all[0] == a2->all[0] && a1->all[1] == a2->all[1] && a1->all[2] == a2->all[2] && a1->all[3] == a2->all[3]; #endif } static inline void nf_inet_addr_mask(const union nf_inet_addr *a1, union nf_inet_addr *result, const union nf_inet_addr *mask) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ua = (const unsigned long *)a1; unsigned long *ur = (unsigned long *)result; const unsigned long *um = (const unsigned long *)mask; ur[0] = ua[0] & um[0]; ur[1] = ua[1] & um[1]; #else result->all[0] = a1->all[0] & mask->all[0]; result->all[1] = a1->all[1] & mask->all[1]; result->all[2] = a1->all[2] & mask->all[2]; result->all[3] = a1->all[3] & mask->all[3]; #endif } int netfilter_init(void); struct sk_buff; struct nf_hook_ops; struct sock; struct nf_hook_state { u8 hook; u8 pf; struct net_device *in; struct net_device *out; struct sock *sk; struct net *net; int (*okfn)(struct net *, struct sock *, struct sk_buff *); }; typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); enum nf_hook_ops_type { NF_HOOK_OP_UNDEFINED, NF_HOOK_OP_NF_TABLES, NF_HOOK_OP_BPF, }; struct nf_hook_ops { /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; void *priv; u8 pf; enum nf_hook_ops_type hook_ops_type:8; unsigned int hooknum; /* Hooks are ordered in ascending priority. */ int priority; }; struct nf_hook_entry { nf_hookfn *hook; void *priv; }; struct nf_hook_entries_rcu_head { struct rcu_head head; void *allocation; }; struct nf_hook_entries { u16 num_hook_entries; /* padding */ struct nf_hook_entry hooks[]; /* trailer: pointers to original orig_ops of each hook, * followed by rcu_head and scratch space used for freeing * the structure via call_rcu. * * This is not part of struct nf_hook_entry since its only * needed in slow path (hook register/unregister): * const struct nf_hook_ops *orig_ops[] * * For the same reason, we store this at end -- its * only needed when a hook is deleted, not during * packet path processing: * struct nf_hook_entries_rcu_head head */ }; #ifdef CONFIG_NETFILTER static inline struct nf_hook_ops **nf_hook_entries_get_hook_ops(const struct nf_hook_entries *e) { unsigned int n = e->num_hook_entries; const void *hook_end; hook_end = &e->hooks[n]; /* this is *past* ->hooks[]! */ return (struct nf_hook_ops **)hook_end; } static inline int nf_hook_entry_hookfn(const struct nf_hook_entry *entry, struct sk_buff *skb, struct nf_hook_state *state) { return entry->hook(entry->priv, skb, state); } static inline void nf_hook_state_init(struct nf_hook_state *p, unsigned int hook, u_int8_t pf, struct net_device *indev, struct net_device *outdev, struct sock *sk, struct net *net, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { p->hook = hook; p->pf = pf; p->in = indev; p->out = outdev; p->sk = sk; p->net = net; p->okfn = okfn; } struct nf_sockopt_ops { struct list_head list; u_int8_t pf; /* Non-inclusive ranges: use 0/0/NULL to never get called. */ int set_optmin; int set_optmax; int (*set)(struct sock *sk, int optval, sockptr_t arg, unsigned int len); int get_optmin; int get_optmax; int (*get)(struct sock *sk, int optval, void __user *user, int *len); /* Use the module struct to lock set/get code in place */ struct module *owner; }; /* Function to register/unregister hook points. */ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *ops); void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *ops); int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n); void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n); /* Functions to register get/setsockopt ranges (non-inclusive). You need to check permissions yourself! */ int nf_register_sockopt(struct nf_sockopt_ops *reg); void nf_unregister_sockopt(struct nf_sockopt_ops *reg); #ifdef CONFIG_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; #endif int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *e, unsigned int i); void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, const struct nf_hook_entries *e); /** * nf_hook - call a netfilter hook * * Returns 1 if the hook has allowed the packet to pass. The function * okfn must be invoked by the caller in this case. Any other return * value indicates the packet has been consumed by the hook. */ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { struct nf_hook_entries *hook_head = NULL; int ret = 1; #ifdef CONFIG_JUMP_LABEL if (__builtin_constant_p(pf) && __builtin_constant_p(hook) && !static_key_false(&nf_hooks_needed[pf][hook])) return 1; #endif rcu_read_lock(); switch (pf) { case NFPROTO_IPV4: hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); break; case NFPROTO_IPV6: hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); break; case NFPROTO_ARP: #ifdef CONFIG_NETFILTER_FAMILY_ARP if (WARN_ON_ONCE(hook >= ARRAY_SIZE(net->nf.hooks_arp))) break; hook_head = rcu_dereference(net->nf.hooks_arp[hook]); #endif break; case NFPROTO_BRIDGE: #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE hook_head = rcu_dereference(net->nf.hooks_bridge[hook]); #endif break; default: WARN_ON_ONCE(1); break; } if (hook_head) { struct nf_hook_state state; nf_hook_state_init(&state, hook, pf, indev, outdev, sk, net, okfn); ret = nf_hook_slow(skb, &state, hook_head, 0); } rcu_read_unlock(); return ret; } /* Activate hook; either okfn or kfree_skb called, unless a hook returns NF_STOLEN (in which case, it's up to the hook to deal with the consequences). Returns -ERRNO if packet dropped. Zero means queued, stolen or accepted. */ /* RR: > I don't want nf_hook to return anything because people might forget > about async and trust the return value to mean "packet was ok". AK: Just document it clearly, then you can expect some sense from kernel coders :) */ static inline int NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *), bool cond) { int ret; if (!cond || ((ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn)) == 1)) ret = okfn(net, sk, skb); return ret; } static inline int NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn); if (ret == 1) ret = okfn(net, sk, skb); return ret; } static inline void NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct list_head *head, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { struct nf_hook_entries *hook_head = NULL; #ifdef CONFIG_JUMP_LABEL if (__builtin_constant_p(pf) && __builtin_constant_p(hook) && !static_key_false(&nf_hooks_needed[pf][hook])) return; #endif rcu_read_lock(); switch (pf) { case NFPROTO_IPV4: hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); break; case NFPROTO_IPV6: hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); break; default: WARN_ON_ONCE(1); break; } if (hook_head) { struct nf_hook_state state; nf_hook_state_init(&state, hook, pf, in, out, sk, net, okfn); nf_hook_slow_list(head, &state, hook_head); } rcu_read_unlock(); } /* Call setsockopt() */ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, sockptr_t opt, unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); struct flowi; struct nf_queue_entry; __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol, unsigned short family); __sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, unsigned int len, u_int8_t protocol, unsigned short family); int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict, unsigned short family); #include <net/flow.h> struct nf_conn; enum nf_nat_manip_type; struct nlattr; struct nf_nat_hook { int (*parse_nat_setup)(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr); void (*decode_session)(struct sk_buff *skb, struct flowi *fl); void (*remove_nat_bysrc)(struct nf_conn *ct); }; extern const struct nf_nat_hook __rcu *nf_nat_hook; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { #if IS_ENABLED(CONFIG_NF_NAT) const struct nf_nat_hook *nat_hook; rcu_read_lock(); nat_hook = rcu_dereference(nf_nat_hook); if (nat_hook && nat_hook->decode_session) nat_hook->decode_session(skb, fl); rcu_read_unlock(); #endif } #else /* !CONFIG_NETFILTER */ static inline int NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *), bool cond) { return okfn(net, sk, skb); } static inline int NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return okfn(net, sk, skb); } static inline void NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct list_head *head, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { /* nothing to do */ } static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return 1; } struct flowi; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { } #endif /*CONFIG_NETFILTER*/ #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_zones_common.h> void nf_ct_attach(struct sk_buff *, const struct sk_buff *); void nf_ct_set_closing(struct nf_conntrack *nfct); struct nf_conntrack_tuple; bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb); #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} static inline void nf_ct_set_closing(struct nf_conntrack *nfct) {} struct nf_conntrack_tuple; static inline bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { return false; } #endif struct nf_conn; enum ip_conntrack_info; struct nf_ct_hook { int (*update)(struct net *net, struct sk_buff *skb); void (*destroy)(struct nf_conntrack *); bool (*get_tuple_skb)(struct nf_conntrack_tuple *, const struct sk_buff *); void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb); void (*set_closing)(struct nf_conntrack *nfct); int (*confirm)(struct sk_buff *skb); }; extern const struct nf_ct_hook __rcu *nf_ct_hook; struct nlattr; struct nfnl_ct_hook { size_t (*build_size)(const struct nf_conn *ct); int (*build)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, u_int16_t ct_attr, u_int16_t ct_info_attr); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report); void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off); }; extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; struct nf_defrag_hook { struct module *owner; int (*enable)(struct net *net); void (*disable)(struct net *net); }; extern const struct nf_defrag_hook __rcu *nf_defrag_v4_hook; extern const struct nf_defrag_hook __rcu *nf_defrag_v6_hook; /* * nf_skb_duplicated - TEE target has sent a packet * * When a xtables target sends a packet, the OUTPUT and POSTROUTING * hooks are traversed again, i.e. nft and xtables are invoked recursively. * * This is used by xtables TEE target to prevent the duplicated skb from * being duplicated again. */ DECLARE_PER_CPU(bool, nf_skb_duplicated); /* * Contains bitmask of ctnetlink event subscribers, if any. * Can't be pernet due to NETLINK_LISTEN_ALL_NSID setsockopt flag. */ extern u8 nf_ctnetlink_has_listener; #endif /*__LINUX_NETFILTER_H*/ |
| 39 2 40 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/init.h> #include <linux/module.h> #include <linux/netfilter.h> #include <net/flow_offload.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_offload.h> #include <net/pkt_cls.h> static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) { struct nft_flow_rule *flow; flow = kzalloc(sizeof(struct nft_flow_rule), GFP_KERNEL); if (!flow) return NULL; flow->rule = flow_rule_alloc(num_actions); if (!flow->rule) { kfree(flow); return NULL; } flow->rule->match.dissector = &flow->match.dissector; flow->rule->match.mask = &flow->match.mask; flow->rule->match.key = &flow->match.key; return flow; } void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, enum flow_dissector_key_id addr_type) { struct nft_flow_match *match = &flow->match; struct nft_flow_key *mask = &match->mask; struct nft_flow_key *key = &match->key; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) return; key->control.addr_type = addr_type; mask->control.addr_type = 0xffff; match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL); match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] = offsetof(struct nft_flow_key, control); } struct nft_offload_ethertype { __be16 value; __be16 mask; }; static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow) { struct nft_flow_match *match = &flow->match; struct nft_offload_ethertype ethertype = { .value = match->key.basic.n_proto, .mask = match->mask.basic.n_proto, }; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) && (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || match->key.vlan.vlan_tpid == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.cvlan.vlan_tpid; match->mask.basic.n_proto = match->mask.cvlan.vlan_tpid; match->key.cvlan.vlan_tpid = match->key.vlan.vlan_tpid; match->mask.cvlan.vlan_tpid = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = offsetof(struct nft_flow_key, cvlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN); } else if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) && (match->key.basic.n_proto == htons(ETH_P_8021Q) || match->key.basic.n_proto == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.vlan.vlan_tpid; match->mask.basic.n_proto = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = offsetof(struct nft_flow_key, vlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_VLAN); } } struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule) { struct nft_offload_ctx *ctx; struct nft_flow_rule *flow; int num_actions = 0, err; struct nft_expr *expr; expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { if (expr->ops->offload_action && expr->ops->offload_action(expr)) num_actions++; expr = nft_expr_next(expr); } if (num_actions == 0) return ERR_PTR(-EOPNOTSUPP); flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); expr = nft_expr_first(rule); ctx = kzalloc(sizeof(struct nft_offload_ctx), GFP_KERNEL); if (!ctx) { err = -ENOMEM; goto err_out; } ctx->net = net; ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; while (nft_expr_more(rule, expr)) { if (!expr->ops->offload) { err = -EOPNOTSUPP; goto err_out; } err = expr->ops->offload(ctx, flow, expr); if (err < 0) goto err_out; expr = nft_expr_next(expr); } nft_flow_rule_transfer_vlan(ctx, flow); flow->proto = ctx->dep.l3num; kfree(ctx); return flow; err_out: kfree(ctx); nft_flow_rule_destroy(flow); return ERR_PTR(err); } void nft_flow_rule_destroy(struct nft_flow_rule *flow) { struct flow_action_entry *entry; int i; flow_action_for_each(i, entry, &flow->rule->action) { switch (entry->id) { case FLOW_ACTION_REDIRECT: case FLOW_ACTION_MIRRED: dev_put(entry->dev); break; default: break; } } kfree(flow->rule); kfree(flow); } void nft_offload_set_dependency(struct nft_offload_ctx *ctx, enum nft_offload_dep_type type) { ctx->dep.type = type; } void nft_offload_update_dependency(struct nft_offload_ctx *ctx, const void *data, u32 len) { switch (ctx->dep.type) { case NFT_OFFLOAD_DEP_NETWORK: WARN_ON(len != sizeof(__u16)); memcpy(&ctx->dep.l3num, data, sizeof(__u16)); break; case NFT_OFFLOAD_DEP_TRANSPORT: WARN_ON(len != sizeof(__u8)); memcpy(&ctx->dep.protonum, data, sizeof(__u8)); break; default: break; } ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; } static void nft_flow_offload_common_init(struct flow_cls_common_offload *common, __be16 proto, int priority, struct netlink_ext_ack *extack) { common->protocol = proto; common->prio = priority; common->extack = extack; } static int nft_setup_cb_call(enum tc_setup_type type, void *type_data, struct list_head *cb_list) { struct flow_block_cb *block_cb; int err; list_for_each_entry(block_cb, cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err < 0) return err; } return 0; } static int nft_chain_offload_priority(const struct nft_base_chain *basechain) { if (basechain->ops.priority <= 0 || basechain->ops.priority > USHRT_MAX) return -1; return 0; } bool nft_chain_offload_support(const struct nft_base_chain *basechain) { struct net_device *dev; struct nft_hook *hook; if (nft_chain_offload_priority(basechain) < 0) return false; list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.pf != NFPROTO_NETDEV || hook->ops.hooknum != NF_NETDEV_INGRESS) return false; dev = hook->ops.dev; if (!dev->netdev_ops->ndo_setup_tc && !flow_indr_dev_exists()) return false; } return true; } static void nft_flow_cls_offload_setup(struct flow_cls_offload *cls_flow, const struct nft_base_chain *basechain, const struct nft_rule *rule, const struct nft_flow_rule *flow, struct netlink_ext_ack *extack, enum flow_cls_command command) { __be16 proto = ETH_P_ALL; memset(cls_flow, 0, sizeof(*cls_flow)); if (flow) proto = flow->proto; nft_flow_offload_common_init(&cls_flow->common, proto, basechain->ops.priority, extack); cls_flow->command = command; cls_flow->cookie = (unsigned long) rule; if (flow) cls_flow->rule = flow->rule; } static int nft_flow_offload_cmd(const struct nft_chain *chain, const struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command, struct flow_cls_offload *cls_flow) { struct netlink_ext_ack extack = {}; struct nft_base_chain *basechain; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); nft_flow_cls_offload_setup(cls_flow, basechain, rule, flow, &extack, command); return nft_setup_cb_call(TC_SETUP_CLSFLOWER, cls_flow, &basechain->flow_block.cb_list); } static int nft_flow_offload_rule(const struct nft_chain *chain, struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command) { struct flow_cls_offload cls_flow; return nft_flow_offload_cmd(chain, rule, flow, command, &cls_flow); } int nft_flow_rule_stats(const struct nft_chain *chain, const struct nft_rule *rule) { struct flow_cls_offload cls_flow = {}; struct nft_expr *expr, *next; int err; err = nft_flow_offload_cmd(chain, rule, NULL, FLOW_CLS_STATS, &cls_flow); if (err < 0) return err; nft_rule_for_each_expr(expr, next, rule) { if (expr->ops->offload_stats) expr->ops->offload_stats(expr, &cls_flow.stats); } return 0; } static int nft_flow_offload_bind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { list_splice(&bo->cb_list, &basechain->flow_block.cb_list); return 0; } static int nft_flow_offload_unbind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { struct flow_block_cb *block_cb, *next; struct flow_cls_offload cls_flow; struct netlink_ext_ack extack; struct nft_chain *chain; struct nft_rule *rule; chain = &basechain->chain; list_for_each_entry(rule, &chain->rules, list) { memset(&extack, 0, sizeof(extack)); nft_flow_cls_offload_setup(&cls_flow, basechain, rule, NULL, &extack, FLOW_CLS_DESTROY); nft_setup_cb_call(TC_SETUP_CLSFLOWER, &cls_flow, &bo->cb_list); } list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { list_del(&block_cb->list); flow_block_cb_free(block_cb); } return 0; } static int nft_block_setup(struct nft_base_chain *basechain, struct flow_block_offload *bo, enum flow_block_command cmd) { int err; switch (cmd) { case FLOW_BLOCK_BIND: err = nft_flow_offload_bind(bo, basechain); break; case FLOW_BLOCK_UNBIND: err = nft_flow_offload_unbind(bo, basechain); break; default: WARN_ON_ONCE(1); err = -EOPNOTSUPP; } return err; } static void nft_flow_block_offload_init(struct flow_block_offload *bo, struct net *net, enum flow_block_command cmd, struct nft_base_chain *basechain, struct netlink_ext_ack *extack) { memset(bo, 0, sizeof(*bo)); bo->net = net; bo->block = &basechain->flow_block; bo->command = cmd; bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo->extack = extack; bo->cb_list_head = &basechain->flow_block.cb_list; INIT_LIST_HEAD(&bo->cb_list); } static int nft_block_offload_cmd(struct nft_base_chain *chain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, chain, &extack); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); if (err < 0) return err; return nft_block_setup(chain, &bo, cmd); } static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) { struct nft_base_chain *basechain = block_cb->indr.data; struct net_device *dev = block_cb->indr.dev; struct netlink_ext_ack extack = {}; struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct flow_block_offload bo; nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); mutex_unlock(&nft_net->commit_mutex); } static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, basechain, &extack); err = flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_BLOCK, basechain, &bo, nft_indr_block_cleanup); if (err < 0) return err; if (list_empty(&bo.cb_list)) return -EOPNOTSUPP; return nft_block_setup(basechain, &bo, cmd); } static int nft_chain_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { int err; if (dev->netdev_ops->ndo_setup_tc) err = nft_block_offload_cmd(basechain, dev, cmd); else err = nft_indr_block_offload_cmd(basechain, dev, cmd); return err; } static int nft_flow_block_chain(struct nft_base_chain *basechain, const struct net_device *this_dev, enum flow_block_command cmd) { struct net_device *dev; struct nft_hook *hook; int err, i = 0; list_for_each_entry(hook, &basechain->hook_list, list) { dev = hook->ops.dev; if (this_dev && this_dev != dev) continue; err = nft_chain_offload_cmd(basechain, dev, cmd); if (err < 0 && cmd == FLOW_BLOCK_BIND) { if (!this_dev) goto err_flow_block; return err; } i++; } return 0; err_flow_block: list_for_each_entry(hook, &basechain->hook_list, list) { if (i-- <= 0) break; dev = hook->ops.dev; nft_chain_offload_cmd(basechain, dev, FLOW_BLOCK_UNBIND); } return err; } static int nft_flow_offload_chain(struct nft_chain *chain, u8 *ppolicy, enum flow_block_command cmd) { struct nft_base_chain *basechain; u8 policy; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); policy = ppolicy ? *ppolicy : basechain->policy; /* Only default policy to accept is supported for now. */ if (cmd == FLOW_BLOCK_BIND && policy == NF_DROP) return -EOPNOTSUPP; return nft_flow_block_chain(basechain, NULL, cmd); } static void nft_flow_rule_offload_abort(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); int err = 0; list_for_each_entry_continue_reverse(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_UNBIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_BIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; } if (WARN_ON_ONCE(err)) break; } } int nft_flow_rule_offload_commit(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; int err = 0; u8 policy; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_BIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_UNBIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; if (trans->flags & NLM_F_REPLACE || !(trans->flags & NLM_F_APPEND)) { err = -EOPNOTSUPP; break; } err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; } if (err) { nft_flow_rule_offload_abort(net, trans); break; } } return err; } static struct nft_chain *__nft_offload_get_chain(const struct nftables_pernet *nft_net, struct net_device *dev) { struct nft_base_chain *basechain; struct nft_hook *hook, *found; const struct nft_table *table; struct nft_chain *chain; list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain) || !(chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; found = NULL; basechain = nft_base_chain(chain); list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.dev != dev) continue; found = hook; break; } if (!found) continue; return chain; } } return NULL; } static int nft_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct nft_chain *chain; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); chain = __nft_offload_get_chain(nft_net, dev); if (chain) nft_flow_block_chain(nft_base_chain(chain), dev, FLOW_BLOCK_UNBIND); mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nft_offload_netdev_notifier = { .notifier_call = nft_offload_netdev_event, }; int nft_offload_init(void) { return register_netdevice_notifier(&nft_offload_netdev_notifier); } void nft_offload_exit(void) { unregister_netdevice_notifier(&nft_offload_netdev_notifier); } |
| 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_SYNPROXY_SHARED_H #define _NF_SYNPROXY_SHARED_H #include <linux/module.h> #include <linux/skbuff.h> #include <net/ip6_checksum.h> #include <net/ip6_route.h> #include <net/tcp.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_synproxy.h> struct synproxy_stats { unsigned int syn_received; unsigned int cookie_invalid; unsigned int cookie_valid; unsigned int cookie_retrans; unsigned int conn_reopened; }; struct synproxy_net { struct nf_conn *tmpl; struct synproxy_stats __percpu *stats; unsigned int hook_ref4; unsigned int hook_ref6; }; extern unsigned int synproxy_net_id; static inline struct synproxy_net *synproxy_pernet(struct net *net) { return net_generic(net, synproxy_net_id); } struct synproxy_options { u8 options; u8 wscale; u16 mss_option; u16 mss_encode; u32 tsval; u32 tsecr; }; struct nf_synproxy_info; bool synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, const struct tcphdr *th, struct synproxy_options *opts); void synproxy_init_timestamp_cookie(const struct nf_synproxy_info *info, struct synproxy_options *opts); void synproxy_send_client_synack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts); bool synproxy_recv_client_ack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq); struct nf_hook_state; unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs); int nf_synproxy_ipv4_init(struct synproxy_net *snet, struct net *net); void nf_synproxy_ipv4_fini(struct synproxy_net *snet, struct net *net); #if IS_ENABLED(CONFIG_IPV6) void synproxy_send_client_synack_ipv6(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts); bool synproxy_recv_client_ack_ipv6(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq); unsigned int ipv6_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs); int nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net); void nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net); #else static inline int nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net) { return 0; } static inline void nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net) {}; #endif /* CONFIG_IPV6 */ #endif /* _NF_SYNPROXY_SHARED_H */ |
| 21 12 2 6 18 21 19 21 18 17 5 3 2 5 4 7 5 2 7 6 6 7 6 5 2 3 5 4 4 4 2 4 2 18 9 7 7 7 4 7 2 2 2 12 13 14 14 3 1 2 3 2 4 2 2 4 3 3 3 2 3 5 3 2 5 4 4 4 4 4 3 4 1 14 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/ioprio.c * * Copyright (C) 2004 Jens Axboe <axboe@kernel.dk> * * Helper functions for setting/querying io priorities of processes. The * system calls closely mimmick getpriority/setpriority, see the man page for * those. The prio argument is a composite of prio class and prio data, where * the data argument has meaning within that class. The standard scheduling * classes have 8 distinct prio levels, with 0 being the highest prio and 7 * being the lowest. * * IOW, setting BE scheduling class with prio 2 is done ala: * * unsigned int prio = (IOPRIO_CLASS_BE << IOPRIO_CLASS_SHIFT) | 2; * * ioprio_set(PRIO_PROCESS, pid, prio); * * See also Documentation/block/ioprio.rst * */ #include <linux/gfp.h> #include <linux/kernel.h> #include <linux/ioprio.h> #include <linux/cred.h> #include <linux/blkdev.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/security.h> #include <linux/pid_namespace.h> int ioprio_check_cap(int ioprio) { int class = IOPRIO_PRIO_CLASS(ioprio); int level = IOPRIO_PRIO_LEVEL(ioprio); switch (class) { case IOPRIO_CLASS_RT: /* * Originally this only checked for CAP_SYS_ADMIN, * which was implicitly allowed for pid 0 by security * modules such as SELinux. Make sure we check * CAP_SYS_ADMIN first to avoid a denial/avc for * possibly missing CAP_SYS_NICE permission. */ if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE)) return -EPERM; fallthrough; /* rt has prio field too */ case IOPRIO_CLASS_BE: if (level >= IOPRIO_NR_LEVELS) return -EINVAL; break; case IOPRIO_CLASS_IDLE: break; case IOPRIO_CLASS_NONE: if (level) return -EINVAL; break; case IOPRIO_CLASS_INVALID: default: return -EINVAL; } return 0; } SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio) { struct task_struct *p, *g; struct user_struct *user; struct pid *pgrp; kuid_t uid; int ret; ret = ioprio_check_cap(ioprio); if (ret) return ret; ret = -ESRCH; rcu_read_lock(); switch (which) { case IOPRIO_WHO_PROCESS: if (!who) p = current; else p = find_task_by_vpid(who); if (p) ret = set_task_ioprio(p, ioprio); break; case IOPRIO_WHO_PGRP: if (!who) pgrp = task_pgrp(current); else pgrp = find_vpid(who); read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { ret = set_task_ioprio(p, ioprio); if (ret) { read_unlock(&tasklist_lock); goto out; } } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); read_unlock(&tasklist_lock); break; case IOPRIO_WHO_USER: uid = make_kuid(current_user_ns(), who); if (!uid_valid(uid)) break; if (!who) user = current_user(); else user = find_user(uid); if (!user) break; for_each_process_thread(g, p) { if (!uid_eq(task_uid(p), uid) || !task_pid_vnr(p)) continue; ret = set_task_ioprio(p, ioprio); if (ret) goto free_uid; } free_uid: if (who) free_uid(user); break; default: ret = -EINVAL; } out: rcu_read_unlock(); return ret; } static int get_task_ioprio(struct task_struct *p) { int ret; ret = security_task_getioprio(p); if (ret) goto out; task_lock(p); ret = __get_task_ioprio(p); task_unlock(p); out: return ret; } /* * Return raw IO priority value as set by userspace. We use this for * ioprio_get(pid, IOPRIO_WHO_PROCESS) so that we keep historical behavior and * also so that userspace can distinguish unset IO priority (which just gets * overriden based on task's nice value) from IO priority set to some value. */ static int get_task_raw_ioprio(struct task_struct *p) { int ret; ret = security_task_getioprio(p); if (ret) goto out; task_lock(p); if (p->io_context) ret = p->io_context->ioprio; else ret = IOPRIO_DEFAULT; task_unlock(p); out: return ret; } static int ioprio_best(unsigned short aprio, unsigned short bprio) { return min(aprio, bprio); } SYSCALL_DEFINE2(ioprio_get, int, which, int, who) { struct task_struct *g, *p; struct user_struct *user; struct pid *pgrp; kuid_t uid; int ret = -ESRCH; int tmpio; rcu_read_lock(); switch (which) { case IOPRIO_WHO_PROCESS: if (!who) p = current; else p = find_task_by_vpid(who); if (p) ret = get_task_raw_ioprio(p); break; case IOPRIO_WHO_PGRP: if (!who) pgrp = task_pgrp(current); else pgrp = find_vpid(who); read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { tmpio = get_task_ioprio(p); if (tmpio < 0) continue; if (ret == -ESRCH) ret = tmpio; else ret = ioprio_best(ret, tmpio); } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); read_unlock(&tasklist_lock); break; case IOPRIO_WHO_USER: uid = make_kuid(current_user_ns(), who); if (!who) user = current_user(); else user = find_user(uid); if (!user) break; for_each_process_thread(g, p) { if (!uid_eq(task_uid(p), user->uid) || !task_pid_vnr(p)) continue; tmpio = get_task_ioprio(p); if (tmpio < 0) continue; if (ret == -ESRCH) ret = tmpio; else ret = ioprio_best(ret, tmpio); } if (who) free_uid(user); break; default: ret = -EINVAL; } rcu_read_unlock(); return ret; } |
| 24 2 2 2 2 26 26 26 24 24 24 24 24 24 24 24 24 26 24 26 2 2 2 26 2 2 26 26 26 24 24 26 24 24 24 24 14 24 25 24 24 26 2 2 2 25 24 24 24 2 2 2 2 26 26 26 26 2 2 27 25 2 2 25 25 24 1 25 24 24 24 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net-sysfs.c - network device class and attributes * * Copyright (c) 2003 Stephen Hemminger <shemminger@osdl.org> */ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/sched/isolation.h> #include <linux/nsproxy.h> #include <net/sock.h> #include <net/net_namespace.h> #include <linux/rtnetlink.h> #include <linux/vmalloc.h> #include <linux/export.h> #include <linux/jiffies.h> #include <linux/pm_runtime.h> #include <linux/of.h> #include <linux/of_net.h> #include <linux/cpu.h> #include <net/netdev_rx_queue.h> #include <net/rps.h> #include "dev.h" #include "net-sysfs.h" #ifdef CONFIG_SYSFS static const char fmt_hex[] = "%#x\n"; static const char fmt_dec[] = "%d\n"; static const char fmt_uint[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; /* Caller holds RTNL or RCU */ static inline int dev_isalive(const struct net_device *dev) { return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED; } /* use same locking rules as GIF* ioctl's */ static ssize_t netdev_show(const struct device *dev, struct device_attribute *attr, char *buf, ssize_t (*format)(const struct net_device *, char *)) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; rcu_read_lock(); if (dev_isalive(ndev)) ret = (*format)(ndev, buf); rcu_read_unlock(); return ret; } /* generate a show function for simple field */ #define NETDEVICE_SHOW(field, format_string) \ static ssize_t format_##field(const struct net_device *dev, char *buf) \ { \ return sysfs_emit(buf, format_string, READ_ONCE(dev->field)); \ } \ static ssize_t field##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ return netdev_show(dev, attr, buf, format_##field); \ } \ #define NETDEVICE_SHOW_RO(field, format_string) \ NETDEVICE_SHOW(field, format_string); \ static DEVICE_ATTR_RO(field) #define NETDEVICE_SHOW_RW(field, format_string) \ NETDEVICE_SHOW(field, format_string); \ static DEVICE_ATTR_RW(field) /* use same locking and permission rules as SIF* ioctl's */ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len, int (*set)(struct net_device *, unsigned long)) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); unsigned long new; int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = kstrtoul(buf, 0, &new); if (ret) goto err; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { ret = (*set)(netdev, new); if (ret == 0) ret = len; } rtnl_unlock(); err: return ret; } NETDEVICE_SHOW_RO(dev_id, fmt_hex); NETDEVICE_SHOW_RO(dev_port, fmt_dec); NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec); NETDEVICE_SHOW_RO(addr_len, fmt_dec); NETDEVICE_SHOW_RO(ifindex, fmt_dec); NETDEVICE_SHOW_RO(type, fmt_dec); NETDEVICE_SHOW_RO(link_mode, fmt_dec); static ssize_t iflink_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, dev_get_iflink(ndev)); } static DEVICE_ATTR_RO(iflink); static ssize_t format_name_assign_type(const struct net_device *dev, char *buf) { return sysfs_emit(buf, fmt_dec, READ_ONCE(dev->name_assign_type)); } static ssize_t name_assign_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; if (READ_ONCE(ndev->name_assign_type) != NET_NAME_UNKNOWN) ret = netdev_show(dev, attr, buf, format_name_assign_type); return ret; } static DEVICE_ATTR_RO(name_assign_type); /* use same locking rules as GIFHWADDR ioctl's (dev_get_mac_address()) */ static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; down_read(&dev_addr_sem); rcu_read_lock(); if (dev_isalive(ndev)) ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len); rcu_read_unlock(); up_read(&dev_addr_sem); return ret; } static DEVICE_ATTR_RO(address); static ssize_t broadcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); int ret = -EINVAL; rcu_read_lock(); if (dev_isalive(ndev)) ret = sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len); rcu_read_unlock(); return ret; } static DEVICE_ATTR_RO(broadcast); static int change_carrier(struct net_device *dev, unsigned long new_carrier) { if (!netif_running(dev)) return -EINVAL; return dev_change_carrier(dev, (bool)new_carrier); } static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); /* The check is also done in change_carrier; this helps returning early * without hitting the trylock/restart in netdev_store. */ if (!netdev->netdev_ops->ndo_change_carrier) return -EOPNOTSUPP; return netdev_store(dev, attr, buf, len, change_carrier); } static ssize_t carrier_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; if (!rtnl_trylock()) return restart_syscall(); if (netif_running(netdev)) { /* Synchronize carrier state with link watch, * see also rtnl_getlink(). */ linkwatch_sync_dev(netdev); ret = sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev)); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RW(carrier); static ssize_t speed_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; if (!rtnl_trylock()) return restart_syscall(); if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) ret = sysfs_emit(buf, fmt_dec, cmd.base.speed); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(speed); static ssize_t duplex_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; if (!rtnl_trylock()) return restart_syscall(); if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) { const char *duplex; switch (cmd.base.duplex) { case DUPLEX_HALF: duplex = "half"; break; case DUPLEX_FULL: duplex = "full"; break; default: duplex = "unknown"; break; } ret = sysfs_emit(buf, "%s\n", duplex); } } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(duplex); static ssize_t testing_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sysfs_emit(buf, fmt_dec, !!netif_testing(netdev)); return -EINVAL; } static DEVICE_ATTR_RO(testing); static ssize_t dormant_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sysfs_emit(buf, fmt_dec, !!netif_dormant(netdev)); return -EINVAL; } static DEVICE_ATTR_RO(dormant); static const char *const operstates[] = { "unknown", "notpresent", /* currently unused */ "down", "lowerlayerdown", "testing", "dormant", "up" }; static ssize_t operstate_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); unsigned char operstate; operstate = READ_ONCE(netdev->operstate); if (!netif_running(netdev)) operstate = IF_OPER_DOWN; if (operstate >= ARRAY_SIZE(operstates)) return -EINVAL; /* should not happen */ return sysfs_emit(buf, "%s\n", operstates[operstate]); } static DEVICE_ATTR_RO(operstate); static ssize_t carrier_changes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, atomic_read(&netdev->carrier_up_count) + atomic_read(&netdev->carrier_down_count)); } static DEVICE_ATTR_RO(carrier_changes); static ssize_t carrier_up_count_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, atomic_read(&netdev->carrier_up_count)); } static DEVICE_ATTR_RO(carrier_up_count); static ssize_t carrier_down_count_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, atomic_read(&netdev->carrier_down_count)); } static DEVICE_ATTR_RO(carrier_down_count); /* read-write attributes */ static int change_mtu(struct net_device *dev, unsigned long new_mtu) { return dev_set_mtu(dev, (int)new_mtu); } static ssize_t mtu_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_mtu); } NETDEVICE_SHOW_RW(mtu, fmt_dec); static int change_flags(struct net_device *dev, unsigned long new_flags) { return dev_change_flags(dev, (unsigned int)new_flags, NULL); } static ssize_t flags_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_flags); } NETDEVICE_SHOW_RW(flags, fmt_hex); static ssize_t tx_queue_len_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_store(dev, attr, buf, len, dev_change_tx_queue_len); } NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec); static int change_gro_flush_timeout(struct net_device *dev, unsigned long val) { WRITE_ONCE(dev->gro_flush_timeout, val); return 0; } static ssize_t gro_flush_timeout_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_store(dev, attr, buf, len, change_gro_flush_timeout); } NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong); static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val) { if (val > S32_MAX) return -ERANGE; WRITE_ONCE(dev->napi_defer_hard_irqs, val); return 0; } static ssize_t napi_defer_hard_irqs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_store(dev, attr, buf, len, change_napi_defer_hard_irqs); } NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_uint); static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); size_t count = len; ssize_t ret = 0; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* ignore trailing newline */ if (len > 0 && buf[len - 1] == '\n') --count; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { ret = dev_set_alias(netdev, buf, count); if (ret < 0) goto err; ret = len; netdev_state_change(netdev); } err: rtnl_unlock(); return ret; } static ssize_t ifalias_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); char tmp[IFALIASZ]; ssize_t ret = 0; ret = dev_get_alias(netdev, tmp, sizeof(tmp)); if (ret > 0) ret = sysfs_emit(buf, "%s\n", tmp); return ret; } static DEVICE_ATTR_RW(ifalias); static int change_group(struct net_device *dev, unsigned long new_group) { dev_set_group(dev, (int)new_group); return 0; } static ssize_t group_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_group); } NETDEVICE_SHOW(group, fmt_dec); static DEVICE_ATTR(netdev_group, 0644, group_show, group_store); static int change_proto_down(struct net_device *dev, unsigned long proto_down) { return dev_change_proto_down(dev, (bool)proto_down); } static ssize_t proto_down_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_proto_down); } NETDEVICE_SHOW_RW(proto_down, fmt_dec); static ssize_t phys_port_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The check is also done in dev_get_phys_port_id; this helps returning * early without hitting the trylock/restart below. */ if (!netdev->netdev_ops->ndo_get_phys_port_id) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { struct netdev_phys_item_id ppid; ret = dev_get_phys_port_id(netdev, &ppid); if (!ret) ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_port_id); static ssize_t phys_port_name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->netdev_ops->ndo_get_phys_port_name && !netdev->devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { char name[IFNAMSIZ]; ret = dev_get_phys_port_name(netdev, name, sizeof(name)); if (!ret) ret = sysfs_emit(buf, "%s\n", name); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_port_name); static ssize_t phys_switch_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the trylock/restart below. This works * because recurse is false when calling dev_get_port_parent_id. */ if (!netdev->netdev_ops->ndo_get_port_parent_id && !netdev->devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { struct netdev_phys_item_id ppid = { }; ret = dev_get_port_parent_id(netdev, &ppid, false); if (!ret) ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_switch_id); static ssize_t threaded_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; rcu_read_lock(); if (dev_isalive(netdev)) ret = sysfs_emit(buf, fmt_dec, READ_ONCE(netdev->threaded)); rcu_read_unlock(); return ret; } static int modify_napi_threaded(struct net_device *dev, unsigned long val) { int ret; if (list_empty(&dev->napi_list)) return -EOPNOTSUPP; if (val != 0 && val != 1) return -EOPNOTSUPP; ret = dev_set_threaded(dev, val); return ret; } static ssize_t threaded_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, modify_napi_threaded); } static DEVICE_ATTR_RW(threaded); static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_netdev_group.attr, &dev_attr_type.attr, &dev_attr_dev_id.attr, &dev_attr_dev_port.attr, &dev_attr_iflink.attr, &dev_attr_ifindex.attr, &dev_attr_name_assign_type.attr, &dev_attr_addr_assign_type.attr, &dev_attr_addr_len.attr, &dev_attr_link_mode.attr, &dev_attr_address.attr, &dev_attr_broadcast.attr, &dev_attr_speed.attr, &dev_attr_duplex.attr, &dev_attr_dormant.attr, &dev_attr_testing.attr, &dev_attr_operstate.attr, &dev_attr_carrier_changes.attr, &dev_attr_ifalias.attr, &dev_attr_carrier.attr, &dev_attr_mtu.attr, &dev_attr_flags.attr, &dev_attr_tx_queue_len.attr, &dev_attr_gro_flush_timeout.attr, &dev_attr_napi_defer_hard_irqs.attr, &dev_attr_phys_port_id.attr, &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, &dev_attr_proto_down.attr, &dev_attr_carrier_up_count.attr, &dev_attr_carrier_down_count.attr, &dev_attr_threaded.attr, NULL, }; ATTRIBUTE_GROUPS(net_class); /* Show a given an attribute in the statistics group */ static ssize_t netstat_show(const struct device *d, struct device_attribute *attr, char *buf, unsigned long offset) { struct net_device *dev = to_net_dev(d); ssize_t ret = -EINVAL; WARN_ON(offset > sizeof(struct rtnl_link_stats64) || offset % sizeof(u64) != 0); rcu_read_lock(); if (dev_isalive(dev)) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); ret = sysfs_emit(buf, fmt_u64, *(u64 *)(((u8 *)stats) + offset)); } rcu_read_unlock(); return ret; } /* generate a read-only statistics attribute */ #define NETSTAT_ENTRY(name) \ static ssize_t name##_show(struct device *d, \ struct device_attribute *attr, char *buf) \ { \ return netstat_show(d, attr, buf, \ offsetof(struct rtnl_link_stats64, name)); \ } \ static DEVICE_ATTR_RO(name) NETSTAT_ENTRY(rx_packets); NETSTAT_ENTRY(tx_packets); NETSTAT_ENTRY(rx_bytes); NETSTAT_ENTRY(tx_bytes); NETSTAT_ENTRY(rx_errors); NETSTAT_ENTRY(tx_errors); NETSTAT_ENTRY(rx_dropped); NETSTAT_ENTRY(tx_dropped); NETSTAT_ENTRY(multicast); NETSTAT_ENTRY(collisions); NETSTAT_ENTRY(rx_length_errors); NETSTAT_ENTRY(rx_over_errors); NETSTAT_ENTRY(rx_crc_errors); NETSTAT_ENTRY(rx_frame_errors); NETSTAT_ENTRY(rx_fifo_errors); NETSTAT_ENTRY(rx_missed_errors); NETSTAT_ENTRY(tx_aborted_errors); NETSTAT_ENTRY(tx_carrier_errors); NETSTAT_ENTRY(tx_fifo_errors); NETSTAT_ENTRY(tx_heartbeat_errors); NETSTAT_ENTRY(tx_window_errors); NETSTAT_ENTRY(rx_compressed); NETSTAT_ENTRY(tx_compressed); NETSTAT_ENTRY(rx_nohandler); static struct attribute *netstat_attrs[] __ro_after_init = { &dev_attr_rx_packets.attr, &dev_attr_tx_packets.attr, &dev_attr_rx_bytes.attr, &dev_attr_tx_bytes.attr, &dev_attr_rx_errors.attr, &dev_attr_tx_errors.attr, &dev_attr_rx_dropped.attr, &dev_attr_tx_dropped.attr, &dev_attr_multicast.attr, &dev_attr_collisions.attr, &dev_attr_rx_length_errors.attr, &dev_attr_rx_over_errors.attr, &dev_attr_rx_crc_errors.attr, &dev_attr_rx_frame_errors.attr, &dev_attr_rx_fifo_errors.attr, &dev_attr_rx_missed_errors.attr, &dev_attr_tx_aborted_errors.attr, &dev_attr_tx_carrier_errors.attr, &dev_attr_tx_fifo_errors.attr, &dev_attr_tx_heartbeat_errors.attr, &dev_attr_tx_window_errors.attr, &dev_attr_rx_compressed.attr, &dev_attr_tx_compressed.attr, &dev_attr_rx_nohandler.attr, NULL }; static const struct attribute_group netstat_group = { .name = "statistics", .attrs = netstat_attrs, }; static struct attribute *wireless_attrs[] = { NULL }; static const struct attribute_group wireless_group = { .name = "wireless", .attrs = wireless_attrs, }; static bool wireless_group_needed(struct net_device *ndev) { #if IS_ENABLED(CONFIG_CFG80211) if (ndev->ieee80211_ptr) return true; #endif #if IS_ENABLED(CONFIG_WIRELESS_EXT) if (ndev->wireless_handlers) return true; #endif return false; } #else /* CONFIG_SYSFS */ #define net_class_groups NULL #endif /* CONFIG_SYSFS */ #ifdef CONFIG_SYSFS #define to_rx_queue_attr(_attr) \ container_of(_attr, struct rx_queue_attribute, attr) #define to_rx_queue(obj) container_of(obj, struct netdev_rx_queue, kobj) static ssize_t rx_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->show) return -EIO; return attribute->show(queue, buf); } static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->store) return -EIO; return attribute->store(queue, buf, count); } static const struct sysfs_ops rx_queue_sysfs_ops = { .show = rx_queue_attr_show, .store = rx_queue_attr_store, }; #ifdef CONFIG_RPS static ssize_t show_rps_map(struct netdev_rx_queue *queue, char *buf) { struct rps_map *map; cpumask_var_t mask; int i, len; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; rcu_read_lock(); map = rcu_dereference(queue->rps_map); if (map) for (i = 0; i < map->len; i++) cpumask_set_cpu(map->cpus[i], mask); len = sysfs_emit(buf, "%*pb\n", cpumask_pr_args(mask)); rcu_read_unlock(); free_cpumask_var(mask); return len < PAGE_SIZE ? len : -EINVAL; } static int netdev_rx_queue_set_rps_mask(struct netdev_rx_queue *queue, cpumask_var_t mask) { static DEFINE_MUTEX(rps_map_mutex); struct rps_map *old_map, *map; int cpu, i; map = kzalloc(max_t(unsigned int, RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), GFP_KERNEL); if (!map) return -ENOMEM; i = 0; for_each_cpu_and(cpu, mask, cpu_online_mask) map->cpus[i++] = cpu; if (i) { map->len = i; } else { kfree(map); map = NULL; } mutex_lock(&rps_map_mutex); old_map = rcu_dereference_protected(queue->rps_map, mutex_is_locked(&rps_map_mutex)); rcu_assign_pointer(queue->rps_map, map); if (map) static_branch_inc(&rps_needed); if (old_map) static_branch_dec(&rps_needed); mutex_unlock(&rps_map_mutex); if (old_map) kfree_rcu(old_map, rcu); return 0; } int rps_cpumask_housekeeping(struct cpumask *mask) { if (!cpumask_empty(mask)) { cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); if (cpumask_empty(mask)) return -EINVAL; } return 0; } static ssize_t store_rps_map(struct netdev_rx_queue *queue, const char *buf, size_t len) { cpumask_var_t mask; int err; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); if (err) goto out; err = rps_cpumask_housekeeping(mask); if (err) goto out; err = netdev_rx_queue_set_rps_mask(queue, mask); out: free_cpumask_var(mask); return err ? : len; } static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, char *buf) { struct rps_dev_flow_table *flow_table; unsigned long val = 0; rcu_read_lock(); flow_table = rcu_dereference(queue->rps_flow_table); if (flow_table) val = (unsigned long)flow_table->mask + 1; rcu_read_unlock(); return sysfs_emit(buf, "%lu\n", val); } static void rps_dev_flow_table_release(struct rcu_head *rcu) { struct rps_dev_flow_table *table = container_of(rcu, struct rps_dev_flow_table, rcu); vfree(table); } static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, const char *buf, size_t len) { unsigned long mask, count; struct rps_dev_flow_table *table, *old_table; static DEFINE_SPINLOCK(rps_dev_flow_lock); int rc; if (!capable(CAP_NET_ADMIN)) return -EPERM; rc = kstrtoul(buf, 0, &count); if (rc < 0) return rc; if (count) { mask = count - 1; /* mask = roundup_pow_of_two(count) - 1; * without overflows... */ while ((mask | (mask >> 1)) != mask) mask |= (mask >> 1); /* On 64 bit arches, must check mask fits in table->mask (u32), * and on 32bit arches, must check * RPS_DEV_FLOW_TABLE_SIZE(mask + 1) doesn't overflow. */ #if BITS_PER_LONG > 32 if (mask > (unsigned long)(u32)mask) return -EINVAL; #else if (mask > (ULONG_MAX - RPS_DEV_FLOW_TABLE_SIZE(1)) / sizeof(struct rps_dev_flow)) { /* Enforce a limit to prevent overflow */ return -EINVAL; } #endif table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(mask + 1)); if (!table) return -ENOMEM; table->mask = mask; for (count = 0; count <= mask; count++) table->flows[count].cpu = RPS_NO_CPU; } else { table = NULL; } spin_lock(&rps_dev_flow_lock); old_table = rcu_dereference_protected(queue->rps_flow_table, lockdep_is_held(&rps_dev_flow_lock)); rcu_assign_pointer(queue->rps_flow_table, table); spin_unlock(&rps_dev_flow_lock); if (old_table) call_rcu(&old_table->rcu, rps_dev_flow_table_release); return len; } static struct rx_queue_attribute rps_cpus_attribute __ro_after_init = __ATTR(rps_cpus, 0644, show_rps_map, store_rps_map); static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute __ro_after_init = __ATTR(rps_flow_cnt, 0644, show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); #endif /* CONFIG_RPS */ static struct attribute *rx_queue_default_attrs[] __ro_after_init = { #ifdef CONFIG_RPS &rps_cpus_attribute.attr, &rps_dev_flow_table_cnt_attribute.attr, #endif NULL }; ATTRIBUTE_GROUPS(rx_queue_default); static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); #ifdef CONFIG_RPS struct rps_map *map; struct rps_dev_flow_table *flow_table; map = rcu_dereference_protected(queue->rps_map, 1); if (map) { RCU_INIT_POINTER(queue->rps_map, NULL); kfree_rcu(map, rcu); } flow_table = rcu_dereference_protected(queue->rps_flow_table, 1); if (flow_table) { RCU_INIT_POINTER(queue->rps_flow_table, NULL); call_rcu(&flow_table->rcu, rps_dev_flow_table_release); } #endif memset(kobj, 0, sizeof(*kobj)); netdev_put(queue->dev, &queue->dev_tracker); } static const void *rx_queue_namespace(const struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); struct device *dev = &queue->dev->dev; const void *ns = NULL; if (dev->class && dev->class->namespace) ns = dev->class->namespace(dev); return ns; } static void rx_queue_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { const struct net *net = rx_queue_namespace(kobj); net_ns_get_ownership(net, uid, gid); } static const struct kobj_type rx_queue_ktype = { .sysfs_ops = &rx_queue_sysfs_ops, .release = rx_queue_release, .default_groups = rx_queue_default_groups, .namespace = rx_queue_namespace, .get_ownership = rx_queue_get_ownership, }; static int rx_queue_default_mask(struct net_device *dev, struct netdev_rx_queue *queue) { #if IS_ENABLED(CONFIG_RPS) && IS_ENABLED(CONFIG_SYSCTL) struct cpumask *rps_default_mask = READ_ONCE(dev_net(dev)->core.rps_default_mask); if (rps_default_mask && !cpumask_empty(rps_default_mask)) return netdev_rx_queue_set_rps_mask(queue, rps_default_mask); #endif return 0; } static int rx_queue_add_kobject(struct net_device *dev, int index) { struct netdev_rx_queue *queue = dev->_rx + index; struct kobject *kobj = &queue->kobj; int error = 0; /* Kobject_put later will trigger rx_queue_release call which * decreases dev refcount: Take that reference here */ netdev_hold(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto err; if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) goto err; } error = rx_queue_default_mask(dev, queue); if (error) goto err; kobject_uevent(kobj, KOBJ_ADD); return error; err: kobject_put(kobj); return error; } static int rx_queue_change_owner(struct net_device *dev, int index, kuid_t kuid, kgid_t kgid) { struct netdev_rx_queue *queue = dev->_rx + index; struct kobject *kobj = &queue->kobj; int error; error = sysfs_change_owner(kobj, kuid, kgid); if (error) return error; if (dev->sysfs_rx_queue_group) error = sysfs_group_change_owner( kobj, dev->sysfs_rx_queue_group, kuid, kgid); return error; } #endif /* CONFIG_SYSFS */ int net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; #ifndef CONFIG_RPS if (!dev->sysfs_rx_queue_group) return 0; #endif for (i = old_num; i < new_num; i++) { error = rx_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; } } while (--i >= new_num) { struct kobject *kobj = &dev->_rx[i].kobj; if (!refcount_read(&dev_net(dev)->ns.count)) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); kobject_put(kobj); } return error; #else return 0; #endif } static int net_rx_queue_change_owner(struct net_device *dev, int num, kuid_t kuid, kgid_t kgid) { #ifdef CONFIG_SYSFS int error = 0; int i; #ifndef CONFIG_RPS if (!dev->sysfs_rx_queue_group) return 0; #endif for (i = 0; i < num; i++) { error = rx_queue_change_owner(dev, i, kuid, kgid); if (error) break; } return error; #else return 0; #endif } #ifdef CONFIG_SYSFS /* * netdev_queue sysfs structures and functions. */ struct netdev_queue_attribute { struct attribute attr; ssize_t (*show)(struct netdev_queue *queue, char *buf); ssize_t (*store)(struct netdev_queue *queue, const char *buf, size_t len); }; #define to_netdev_queue_attr(_attr) \ container_of(_attr, struct netdev_queue_attribute, attr) #define to_netdev_queue(obj) container_of(obj, struct netdev_queue, kobj) static ssize_t netdev_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { const struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->show) return -EIO; return attribute->show(queue, buf); } static ssize_t netdev_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { const struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->store) return -EIO; return attribute->store(queue, buf, count); } static const struct sysfs_ops netdev_queue_sysfs_ops = { .show = netdev_queue_attr_show, .store = netdev_queue_attr_store, }; static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) { unsigned long trans_timeout = atomic_long_read(&queue->trans_timeout); return sysfs_emit(buf, fmt_ulong, trans_timeout); } static unsigned int get_netdev_queue_index(struct netdev_queue *queue) { struct net_device *dev = queue->dev; unsigned int i; i = queue - dev->_tx; BUG_ON(i >= dev->num_tx_queues); return i; } static ssize_t traffic_class_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; int num_tc, tc; int index; if (!netif_is_multiqueue(dev)) return -ENOENT; if (!rtnl_trylock()) return restart_syscall(); index = get_netdev_queue_index(queue); /* If queue belongs to subordinate dev use its TC mapping */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; num_tc = dev->num_tc; tc = netdev_txq_to_tc(dev, index); rtnl_unlock(); if (tc < 0) return -EINVAL; /* We can report the traffic class one of two ways: * Subordinate device traffic classes are reported with the traffic * class first, and then the subordinate class so for example TC0 on * subordinate device 2 will be reported as "0-2". If the queue * belongs to the root device it will be reported with just the * traffic class, so just "0" for TC 0 for example. */ return num_tc < 0 ? sysfs_emit(buf, "%d%d\n", tc, num_tc) : sysfs_emit(buf, "%d\n", tc); } #ifdef CONFIG_XPS static ssize_t tx_maxrate_show(struct netdev_queue *queue, char *buf) { return sysfs_emit(buf, "%lu\n", queue->tx_maxrate); } static ssize_t tx_maxrate_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; int err, index = get_netdev_queue_index(queue); u32 rate = 0; if (!capable(CAP_NET_ADMIN)) return -EPERM; /* The check is also done later; this helps returning early without * hitting the trylock/restart below. */ if (!dev->netdev_ops->ndo_set_tx_maxrate) return -EOPNOTSUPP; err = kstrtou32(buf, 10, &rate); if (err < 0) return err; if (!rtnl_trylock()) return restart_syscall(); err = -EOPNOTSUPP; if (dev->netdev_ops->ndo_set_tx_maxrate) err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate); rtnl_unlock(); if (!err) { queue->tx_maxrate = rate; return len; } return err; } static struct netdev_queue_attribute queue_tx_maxrate __ro_after_init = __ATTR_RW(tx_maxrate); #endif static struct netdev_queue_attribute queue_trans_timeout __ro_after_init = __ATTR_RO(tx_timeout); static struct netdev_queue_attribute queue_traffic_class __ro_after_init = __ATTR_RO(traffic_class); #ifdef CONFIG_BQL /* * Byte queue limits sysfs structures and functions. */ static ssize_t bql_show(char *buf, unsigned int value) { return sysfs_emit(buf, "%u\n", value); } static ssize_t bql_set(const char *buf, const size_t count, unsigned int *pvalue) { unsigned int value; int err; if (!strcmp(buf, "max") || !strcmp(buf, "max\n")) { value = DQL_MAX_LIMIT; } else { err = kstrtouint(buf, 10, &value); if (err < 0) return err; if (value > DQL_MAX_LIMIT) return -EINVAL; } *pvalue = value; return count; } static ssize_t bql_show_hold_time(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time)); } static ssize_t bql_set_hold_time(struct netdev_queue *queue, const char *buf, size_t len) { struct dql *dql = &queue->dql; unsigned int value; int err; err = kstrtouint(buf, 10, &value); if (err < 0) return err; dql->slack_hold_time = msecs_to_jiffies(value); return len; } static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init = __ATTR(hold_time, 0644, bql_show_hold_time, bql_set_hold_time); static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs)); } static ssize_t bql_set_stall_thrs(struct netdev_queue *queue, const char *buf, size_t len) { struct dql *dql = &queue->dql; unsigned int value; int err; err = kstrtouint(buf, 10, &value); if (err < 0) return err; value = msecs_to_jiffies(value); if (value && (value < 4 || value > 4 / 2 * BITS_PER_LONG)) return -ERANGE; if (!dql->stall_thrs && value) dql->last_reap = jiffies; /* Force last_reap to be live */ smp_wmb(); dql->stall_thrs = value; return len; } static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init = __ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs); static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf) { return sysfs_emit(buf, "%u\n", READ_ONCE(queue->dql.stall_max)); } static ssize_t bql_set_stall_max(struct netdev_queue *queue, const char *buf, size_t len) { WRITE_ONCE(queue->dql.stall_max, 0); return len; } static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init = __ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max); static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%lu\n", dql->stall_cnt); } static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init = __ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL); static ssize_t bql_show_inflight(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", dql->num_queued - dql->num_completed); } static struct netdev_queue_attribute bql_inflight_attribute __ro_after_init = __ATTR(inflight, 0444, bql_show_inflight, NULL); #define BQL_ATTR(NAME, FIELD) \ static ssize_t bql_show_ ## NAME(struct netdev_queue *queue, \ char *buf) \ { \ return bql_show(buf, queue->dql.FIELD); \ } \ \ static ssize_t bql_set_ ## NAME(struct netdev_queue *queue, \ const char *buf, size_t len) \ { \ return bql_set(buf, len, &queue->dql.FIELD); \ } \ \ static struct netdev_queue_attribute bql_ ## NAME ## _attribute __ro_after_init \ = __ATTR(NAME, 0644, \ bql_show_ ## NAME, bql_set_ ## NAME) BQL_ATTR(limit, limit); BQL_ATTR(limit_max, max_limit); BQL_ATTR(limit_min, min_limit); static struct attribute *dql_attrs[] __ro_after_init = { &bql_limit_attribute.attr, &bql_limit_max_attribute.attr, &bql_limit_min_attribute.attr, &bql_hold_time_attribute.attr, &bql_inflight_attribute.attr, &bql_stall_thrs_attribute.attr, &bql_stall_cnt_attribute.attr, &bql_stall_max_attribute.attr, NULL }; static const struct attribute_group dql_group = { .name = "byte_queue_limits", .attrs = dql_attrs, }; #else /* Fake declaration, all the code using it should be dead */ static const struct attribute_group dql_group = {}; #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS static ssize_t xps_queue_show(struct net_device *dev, unsigned int index, int tc, char *buf, enum xps_map_type type) { struct xps_dev_maps *dev_maps; unsigned long *mask; unsigned int nr_ids; int j, len; rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_maps[type]); /* Default to nr_cpu_ids/dev->num_rx_queues and do not just return 0 * when dev_maps hasn't been allocated yet, to be backward compatible. */ nr_ids = dev_maps ? dev_maps->nr_ids : (type == XPS_CPUS ? nr_cpu_ids : dev->num_rx_queues); mask = bitmap_zalloc(nr_ids, GFP_NOWAIT); if (!mask) { rcu_read_unlock(); return -ENOMEM; } if (!dev_maps || tc >= dev_maps->num_tc) goto out_no_maps; for (j = 0; j < nr_ids; j++) { int i, tci = j * dev_maps->num_tc + tc; struct xps_map *map; map = rcu_dereference(dev_maps->attr_map[tci]); if (!map) continue; for (i = map->len; i--;) { if (map->queues[i] == index) { __set_bit(j, mask); break; } } } out_no_maps: rcu_read_unlock(); len = bitmap_print_to_pagebuf(false, buf, mask, nr_ids); bitmap_free(mask); return len < PAGE_SIZE ? len : -EINVAL; } static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int len, tc; if (!netif_is_multiqueue(dev)) return -ENOENT; index = get_netdev_queue_index(queue); if (!rtnl_trylock()) return restart_syscall(); /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); if (tc < 0) { rtnl_unlock(); return -EINVAL; } /* Make sure the subordinate device can't be freed */ get_device(&dev->dev); rtnl_unlock(); len = xps_queue_show(dev, index, tc, buf, XPS_CPUS); put_device(&dev->dev); return len; } static ssize_t xps_cpus_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; unsigned int index; cpumask_var_t mask; int err; if (!netif_is_multiqueue(dev)) return -ENOENT; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; index = get_netdev_queue_index(queue); err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); if (err) { free_cpumask_var(mask); return err; } if (!rtnl_trylock()) { free_cpumask_var(mask); return restart_syscall(); } err = netif_set_xps_queue(dev, mask, index); rtnl_unlock(); free_cpumask_var(mask); return err ? : len; } static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init = __ATTR_RW(xps_cpus); static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int tc; index = get_netdev_queue_index(queue); if (!rtnl_trylock()) return restart_syscall(); tc = netdev_txq_to_tc(dev, index); rtnl_unlock(); if (tc < 0) return -EINVAL; return xps_queue_show(dev, index, tc, buf, XPS_RXQS); } static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; struct net *net = dev_net(dev); unsigned long *mask; unsigned int index; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL); if (!mask) return -ENOMEM; index = get_netdev_queue_index(queue); err = bitmap_parse(buf, len, mask, dev->num_rx_queues); if (err) { bitmap_free(mask); return err; } if (!rtnl_trylock()) { bitmap_free(mask); return restart_syscall(); } cpus_read_lock(); err = __netif_set_xps_queue(dev, mask, index, XPS_RXQS); cpus_read_unlock(); rtnl_unlock(); bitmap_free(mask); return err ? : len; } static struct netdev_queue_attribute xps_rxqs_attribute __ro_after_init = __ATTR_RW(xps_rxqs); #endif /* CONFIG_XPS */ static struct attribute *netdev_queue_default_attrs[] __ro_after_init = { &queue_trans_timeout.attr, &queue_traffic_class.attr, #ifdef CONFIG_XPS &xps_cpus_attribute.attr, &xps_rxqs_attribute.attr, &queue_tx_maxrate.attr, #endif NULL }; ATTRIBUTE_GROUPS(netdev_queue_default); static void netdev_queue_release(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); memset(kobj, 0, sizeof(*kobj)); netdev_put(queue->dev, &queue->dev_tracker); } static const void *netdev_queue_namespace(const struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); struct device *dev = &queue->dev->dev; const void *ns = NULL; if (dev->class && dev->class->namespace) ns = dev->class->namespace(dev); return ns; } static void netdev_queue_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { const struct net *net = netdev_queue_namespace(kobj); net_ns_get_ownership(net, uid, gid); } static const struct kobj_type netdev_queue_ktype = { .sysfs_ops = &netdev_queue_sysfs_ops, .release = netdev_queue_release, .default_groups = netdev_queue_default_groups, .namespace = netdev_queue_namespace, .get_ownership = netdev_queue_get_ownership, }; static bool netdev_uses_bql(const struct net_device *dev) { if (dev->lltx || (dev->priv_flags & IFF_NO_QUEUE)) return false; return IS_ENABLED(CONFIG_BQL); } static int netdev_queue_add_kobject(struct net_device *dev, int index) { struct netdev_queue *queue = dev->_tx + index; struct kobject *kobj = &queue->kobj; int error = 0; /* Kobject_put later will trigger netdev_queue_release call * which decreases dev refcount: Take that reference here */ netdev_hold(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); if (error) goto err; if (netdev_uses_bql(dev)) { error = sysfs_create_group(kobj, &dql_group); if (error) goto err; } kobject_uevent(kobj, KOBJ_ADD); return 0; err: kobject_put(kobj); return error; } static int tx_queue_change_owner(struct net_device *ndev, int index, kuid_t kuid, kgid_t kgid) { struct netdev_queue *queue = ndev->_tx + index; struct kobject *kobj = &queue->kobj; int error; error = sysfs_change_owner(kobj, kuid, kgid); if (error) return error; if (netdev_uses_bql(ndev)) error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid); return error; } #endif /* CONFIG_SYSFS */ int netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; /* Tx queue kobjects are allowed to be updated when a device is being * unregistered, but solely to remove queues from qdiscs. Any path * adding queues should be fixed. */ WARN(dev->reg_state == NETREG_UNREGISTERING && new_num > old_num, "New queues can't be registered after device unregistration."); for (i = old_num; i < new_num; i++) { error = netdev_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; } } while (--i >= new_num) { struct netdev_queue *queue = dev->_tx + i; if (!refcount_read(&dev_net(dev)->ns.count)) queue->kobj.uevent_suppress = 1; if (netdev_uses_bql(dev)) sysfs_remove_group(&queue->kobj, &dql_group); kobject_put(&queue->kobj); } return error; #else return 0; #endif /* CONFIG_SYSFS */ } static int net_tx_queue_change_owner(struct net_device *dev, int num, kuid_t kuid, kgid_t kgid) { #ifdef CONFIG_SYSFS int error = 0; int i; for (i = 0; i < num; i++) { error = tx_queue_change_owner(dev, i, kuid, kgid); if (error) break; } return error; #else return 0; #endif /* CONFIG_SYSFS */ } static int register_queue_kobjects(struct net_device *dev) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS dev->queues_kset = kset_create_and_add("queues", NULL, &dev->dev.kobj); if (!dev->queues_kset) return -ENOMEM; real_rx = dev->real_num_rx_queues; #endif real_tx = dev->real_num_tx_queues; error = net_rx_queue_update_kobjects(dev, 0, real_rx); if (error) goto error; rxq = real_rx; error = netdev_queue_update_kobjects(dev, 0, real_tx); if (error) goto error; txq = real_tx; return 0; error: netdev_queue_update_kobjects(dev, txq, 0); net_rx_queue_update_kobjects(dev, rxq, 0); #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif return error; } static int queue_change_owner(struct net_device *ndev, kuid_t kuid, kgid_t kgid) { int error = 0, real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS if (ndev->queues_kset) { error = sysfs_change_owner(&ndev->queues_kset->kobj, kuid, kgid); if (error) return error; } real_rx = ndev->real_num_rx_queues; #endif real_tx = ndev->real_num_tx_queues; error = net_rx_queue_change_owner(ndev, real_rx, kuid, kgid); if (error) return error; error = net_tx_queue_change_owner(ndev, real_tx, kuid, kgid); if (error) return error; return 0; } static void remove_queue_kobjects(struct net_device *dev) { int real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS real_rx = dev->real_num_rx_queues; #endif real_tx = dev->real_num_tx_queues; net_rx_queue_update_kobjects(dev, real_rx, 0); netdev_queue_update_kobjects(dev, real_tx, 0); dev->real_num_rx_queues = 0; dev->real_num_tx_queues = 0; #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif } static bool net_current_may_mount(void) { struct net *net = current->nsproxy->net_ns; return ns_capable(net->user_ns, CAP_SYS_ADMIN); } static void *net_grab_current_ns(void) { struct net *ns = current->nsproxy->net_ns; #ifdef CONFIG_NET_NS if (ns) refcount_inc(&ns->passive); #endif return ns; } static const void *net_initial_ns(void) { return &init_net; } static const void *net_netlink_ns(struct sock *sk) { return sock_net(sk); } const struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, .current_may_mount = net_current_may_mount, .grab_current_ns = net_grab_current_ns, .netlink_ns = net_netlink_ns, .initial_ns = net_initial_ns, .drop_ns = net_drop_ns, }; EXPORT_SYMBOL_GPL(net_ns_type_operations); static int netdev_uevent(const struct device *d, struct kobj_uevent_env *env) { const struct net_device *dev = to_net_dev(d); int retval; /* pass interface to uevent. */ retval = add_uevent_var(env, "INTERFACE=%s", dev->name); if (retval) goto exit; /* pass ifindex to uevent. * ifindex is useful as it won't change (interface name may change) * and is what RtNetlink uses natively. */ retval = add_uevent_var(env, "IFINDEX=%d", dev->ifindex); exit: return retval; } /* * netdev_release -- destroy and free a dead device. * Called when last reference to device kobject is gone. */ static void netdev_release(struct device *d) { struct net_device *dev = to_net_dev(d); BUG_ON(dev->reg_state != NETREG_RELEASED); /* no need to wait for rcu grace period: * device is dead and about to be freed. */ kfree(rcu_access_pointer(dev->ifalias)); kvfree(dev); } static const void *net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d); return dev_net(dev); } static void net_get_ownership(const struct device *d, kuid_t *uid, kgid_t *gid) { const struct net_device *dev = to_net_dev(d); const struct net *net = dev_net(dev); net_ns_get_ownership(net, uid, gid); } static const struct class net_class = { .name = "net", .dev_release = netdev_release, .dev_groups = net_class_groups, .dev_uevent = netdev_uevent, .ns_type = &net_ns_type_operations, .namespace = net_namespace, .get_ownership = net_get_ownership, }; #ifdef CONFIG_OF static int of_dev_node_match(struct device *dev, const void *data) { for (; dev; dev = dev->parent) { if (dev->of_node == data) return 1; } return 0; } /* * of_find_net_device_by_node - lookup the net device for the device node * @np: OF device node * * Looks up the net_device structure corresponding with the device node. * If successful, returns a pointer to the net_device with the embedded * struct device refcount incremented by one, or NULL on failure. The * refcount must be dropped when done with the net_device. */ struct net_device *of_find_net_device_by_node(struct device_node *np) { struct device *dev; dev = class_find_device(&net_class, NULL, np, of_dev_node_match); if (!dev) return NULL; return to_net_dev(dev); } EXPORT_SYMBOL(of_find_net_device_by_node); #endif /* Delete sysfs entries but hold kobject reference until after all * netdev references are gone. */ void netdev_unregister_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; if (!refcount_read(&dev_net(ndev)->ns.count)) dev_set_uevent_suppress(dev, 1); kobject_get(&dev->kobj); remove_queue_kobjects(ndev); pm_runtime_set_memalloc_noio(dev, false); device_del(dev); } /* Create sysfs entries for network device. */ int netdev_register_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; const struct attribute_group **groups = ndev->sysfs_groups; int error = 0; device_initialize(dev); dev->class = &net_class; dev->platform_data = ndev; dev->groups = groups; dev_set_name(dev, "%s", ndev->name); #ifdef CONFIG_SYSFS /* Allow for a device specific group */ if (*groups) groups++; *groups++ = &netstat_group; if (wireless_group_needed(ndev)) *groups++ = &wireless_group; #endif /* CONFIG_SYSFS */ error = device_add(dev); if (error) return error; error = register_queue_kobjects(ndev); if (error) { device_del(dev); return error; } pm_runtime_set_memalloc_noio(dev, true); return error; } /* Change owner for sysfs entries when moving network devices across network * namespaces owned by different user namespaces. */ int netdev_change_owner(struct net_device *ndev, const struct net *net_old, const struct net *net_new) { kuid_t old_uid = GLOBAL_ROOT_UID, new_uid = GLOBAL_ROOT_UID; kgid_t old_gid = GLOBAL_ROOT_GID, new_gid = GLOBAL_ROOT_GID; struct device *dev = &ndev->dev; int error; net_ns_get_ownership(net_old, &old_uid, &old_gid); net_ns_get_ownership(net_new, &new_uid, &new_gid); /* The network namespace was changed but the owning user namespace is * identical so there's no need to change the owner of sysfs entries. */ if (uid_eq(old_uid, new_uid) && gid_eq(old_gid, new_gid)) return 0; error = device_change_owner(dev, new_uid, new_gid); if (error) return error; error = queue_change_owner(ndev, new_uid, new_gid); if (error) return error; return 0; } int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns) { return class_create_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_create_file_ns); void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns) { class_remove_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_remove_file_ns); int __init netdev_kobject_init(void) { kobj_ns_type_register(&net_ns_type_operations); return class_register(&net_class); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2008, 2009 open80211s Ltd. * Copyright (C) 2023-2024 Intel Corporation * Authors: Luis Carlos Cobo <luisca@cozybit.com> * Javier Cardona <javier@cozybit.com> */ #ifndef IEEE80211S_H #define IEEE80211S_H #include <linux/types.h> #include <linux/jhash.h> #include "ieee80211_i.h" /* Data structures */ /** * enum mesh_path_flags - mac80211 mesh path flags * * @MESH_PATH_ACTIVE: the mesh path can be used for forwarding * @MESH_PATH_RESOLVING: the discovery process is running for this mesh path * @MESH_PATH_SN_VALID: the mesh path contains a valid destination sequence * number * @MESH_PATH_FIXED: the mesh path has been manually set and should not be * modified * @MESH_PATH_RESOLVED: the mesh path can has been resolved * @MESH_PATH_REQ_QUEUED: there is an unsent path request for this destination * already queued up, waiting for the discovery process to start. * @MESH_PATH_DELETED: the mesh path has been deleted and should no longer * be used * * MESH_PATH_RESOLVED is used by the mesh path timer to * decide when to stop or cancel the mesh path discovery. */ enum mesh_path_flags { MESH_PATH_ACTIVE = BIT(0), MESH_PATH_RESOLVING = BIT(1), MESH_PATH_SN_VALID = BIT(2), MESH_PATH_FIXED = BIT(3), MESH_PATH_RESOLVED = BIT(4), MESH_PATH_REQ_QUEUED = BIT(5), MESH_PATH_DELETED = BIT(6), }; /** * enum mesh_deferred_task_flags - mac80211 mesh deferred tasks * * * * @MESH_WORK_HOUSEKEEPING: run the periodic mesh housekeeping tasks * @MESH_WORK_ROOT: the mesh root station needs to send a frame * @MESH_WORK_DRIFT_ADJUST: time to compensate for clock drift relative to other * mesh nodes * @MESH_WORK_MBSS_CHANGED: rebuild beacon and notify driver of BSS changes */ enum mesh_deferred_task_flags { MESH_WORK_HOUSEKEEPING, MESH_WORK_ROOT, MESH_WORK_DRIFT_ADJUST, MESH_WORK_MBSS_CHANGED, }; /** * struct mesh_path - mac80211 mesh path structure * * @dst: mesh path destination mac address * @mpp: mesh proxy mac address * @rhash: rhashtable list pointer * @walk_list: linked list containing all mesh_path objects. * @gate_list: list pointer for known gates list * @sdata: mesh subif * @next_hop: mesh neighbor to which frames for this destination will be * forwarded * @timer: mesh path discovery timer * @frame_queue: pending queue for frames sent to this destination while the * path is unresolved * @rcu: rcu head for freeing mesh path * @sn: target sequence number * @metric: current metric to this destination * @hop_count: hops to destination * @exp_time: in jiffies, when the path will expire or when it expired * @discovery_timeout: timeout (lapse in jiffies) used for the last discovery * retry * @discovery_retries: number of discovery retries * @flags: mesh path flags, as specified on &enum mesh_path_flags * @state_lock: mesh path state lock used to protect changes to the * mpath itself. No need to take this lock when adding or removing * an mpath to a hash bucket on a path table. * @rann_snd_addr: the RANN sender address * @rann_metric: the aggregated path metric towards the root node * @last_preq_to_root: Timestamp of last PREQ sent to root * @is_root: the destination station of this path is a root node * @is_gate: the destination station of this path is a mesh gate * @path_change_count: the number of path changes to destination * @fast_tx_check: timestamp of last fast-xmit enable attempt * * * The dst address is unique in the mesh path table. Since the mesh_path is * protected by RCU, deleting the next_hop STA must remove / substitute the * mesh_path structure and wait until that is no longer reachable before * destroying the STA completely. */ struct mesh_path { u8 dst[ETH_ALEN]; u8 mpp[ETH_ALEN]; /* used for MPP or MAP */ struct rhash_head rhash; struct hlist_node walk_list; struct hlist_node gate_list; struct ieee80211_sub_if_data *sdata; struct sta_info __rcu *next_hop; struct timer_list timer; struct sk_buff_head frame_queue; struct rcu_head rcu; u32 sn; u32 metric; u8 hop_count; unsigned long exp_time; u32 discovery_timeout; u8 discovery_retries; enum mesh_path_flags flags; spinlock_t state_lock; u8 rann_snd_addr[ETH_ALEN]; u32 rann_metric; unsigned long last_preq_to_root; unsigned long fast_tx_check; bool is_root; bool is_gate; u32 path_change_count; }; #define MESH_FAST_TX_CACHE_MAX_SIZE 512 #define MESH_FAST_TX_CACHE_THRESHOLD_SIZE 384 #define MESH_FAST_TX_CACHE_TIMEOUT 8000 /* msecs */ /** * enum ieee80211_mesh_fast_tx_type - cached mesh fast tx entry type * * @MESH_FAST_TX_TYPE_LOCAL: tx from the local vif address as SA * @MESH_FAST_TX_TYPE_PROXIED: local tx with a different SA (e.g. bridged) * @MESH_FAST_TX_TYPE_FORWARDED: forwarded from a different mesh point * @NUM_MESH_FAST_TX_TYPE: number of entry types */ enum ieee80211_mesh_fast_tx_type { MESH_FAST_TX_TYPE_LOCAL, MESH_FAST_TX_TYPE_PROXIED, MESH_FAST_TX_TYPE_FORWARDED, /* must be last */ NUM_MESH_FAST_TX_TYPE }; /** * struct ieee80211_mesh_fast_tx_key - cached mesh fast tx entry key * * @addr: The Ethernet DA for this entry * @type: cache entry type */ struct ieee80211_mesh_fast_tx_key { u8 addr[ETH_ALEN] __aligned(2); u16 type; }; /** * struct ieee80211_mesh_fast_tx - cached mesh fast tx entry * @rhash: rhashtable pointer * @key: the lookup key for this cache entry * @fast_tx: base fast_tx data * @hdr: cached mesh and rfc1042 headers * @hdrlen: length of mesh + rfc1042 * @walk_list: list containing all the fast tx entries * @mpath: mesh path corresponding to the Mesh DA * @mppath: MPP entry corresponding to this DA * @timestamp: Last used time of this entry */ struct ieee80211_mesh_fast_tx { struct rhash_head rhash; struct ieee80211_mesh_fast_tx_key key; struct ieee80211_fast_tx fast_tx; u8 hdr[sizeof(struct ieee80211s_hdr) + sizeof(rfc1042_header)]; u16 hdrlen; struct mesh_path *mpath, *mppath; struct hlist_node walk_list; unsigned long timestamp; }; /* Recent multicast cache */ /* RMC_BUCKETS must be a power of 2, maximum 256 */ #define RMC_BUCKETS 256 #define RMC_QUEUE_MAX_LEN 4 #define RMC_TIMEOUT (3 * HZ) /** * struct rmc_entry - entry in the Recent Multicast Cache * * @seqnum: mesh sequence number of the frame * @exp_time: expiration time of the entry, in jiffies * @sa: source address of the frame * @list: hashtable list pointer * * The Recent Multicast Cache keeps track of the latest multicast frames that * have been received by a mesh interface and discards received multicast frames * that are found in the cache. */ struct rmc_entry { struct hlist_node list; unsigned long exp_time; u32 seqnum; u8 sa[ETH_ALEN]; }; struct mesh_rmc { struct hlist_head bucket[RMC_BUCKETS]; u32 idx_mask; }; #define IEEE80211_MESH_HOUSEKEEPING_INTERVAL (60 * HZ) #define MESH_PATH_EXPIRE (600 * HZ) /* Default maximum number of plinks per interface */ #define MESH_MAX_PLINKS 256 /* Maximum number of paths per interface */ #define MESH_MAX_MPATHS 1024 /* Number of frames buffered per destination for unresolved destinations */ #define MESH_FRAME_QUEUE_LEN 10 /* Public interfaces */ /* Various */ int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, const u8 *da, const u8 *sa); unsigned int ieee80211_new_mesh_header(struct ieee80211_sub_if_data *sdata, struct ieee80211s_hdr *meshhdr, const char *addr4or5, const char *addr6); int mesh_rmc_check(struct ieee80211_sub_if_data *sdata, const u8 *addr, struct ieee80211s_hdr *mesh_hdr); bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *ie); int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_meshid_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_rsn_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_vendor_ies(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_ht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_ht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_vht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_he_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u8 ie_len); int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_he_6ghz_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_eht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u8 ie_len); int mesh_add_eht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); void ieee80211s_init(void); void ieee80211s_update_metric(struct ieee80211_local *local, struct sta_info *sta, struct ieee80211_tx_status *st); void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_teardown_sdata(struct ieee80211_sub_if_data *sdata); int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh); const struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method); /* wrapper for ieee80211_bss_info_change_notify() */ void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata, u64 changed); /* mesh power save */ u64 ieee80211_mps_local_status_update(struct ieee80211_sub_if_data *sdata); u64 ieee80211_mps_set_sta_local_pm(struct sta_info *sta, enum nl80211_mesh_power_mode pm); void ieee80211_mps_set_frame_flags(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_hdr *hdr); void ieee80211_mps_sta_status_update(struct sta_info *sta); void ieee80211_mps_rx_h_sta_process(struct sta_info *sta, struct ieee80211_hdr *hdr); void ieee80211_mpsp_trigger_process(u8 *qc, struct sta_info *sta, bool tx, bool acked); void ieee80211_mps_frame_release(struct sta_info *sta, struct ieee802_11_elems *elems); /* Mesh paths */ int mesh_nexthop_lookup(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata); struct mesh_path *mesh_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst); struct mesh_path *mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst); int mpp_path_add(struct ieee80211_sub_if_data *sdata, const u8 *dst, const u8 *mpp); struct mesh_path * mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx); struct mesh_path * mpp_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx); void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop); void mesh_path_expire(struct ieee80211_sub_if_data *sdata); void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len); struct mesh_path * mesh_path_add(struct ieee80211_sub_if_data *sdata, const u8 *dst); int mesh_path_add_gate(struct mesh_path *mpath); int mesh_path_send_to_gates(struct mesh_path *mpath); int mesh_gate_num(struct ieee80211_sub_if_data *sdata); u32 airtime_link_metric_get(struct ieee80211_local *local, struct sta_info *sta); /* Mesh plinks */ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, u8 *hw_addr, struct ieee802_11_elems *ie, struct ieee80211_rx_status *rx_status); bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie); u64 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata); void mesh_plink_timer(struct timer_list *t); void mesh_plink_broken(struct sta_info *sta); u64 mesh_plink_deactivate(struct sta_info *sta); u64 mesh_plink_open(struct sta_info *sta); u64 mesh_plink_block(struct sta_info *sta); void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status); void mesh_sta_cleanup(struct sta_info *sta); /* Private interfaces */ /* Mesh paths */ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, u8 ttl, const u8 *target, u32 target_sn, u16 target_rcode, const u8 *ra); void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta); void mesh_path_flush_pending(struct mesh_path *mpath); void mesh_path_tx_pending(struct mesh_path *mpath); void mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata); void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata); int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr); void mesh_path_timer(struct timer_list *t); void mesh_path_flush_by_nexthop(struct sta_info *sta); void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata); bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt); struct ieee80211_mesh_fast_tx * mesh_fast_tx_get(struct ieee80211_sub_if_data *sdata, struct ieee80211_mesh_fast_tx_key *key); bool ieee80211_mesh_xmit_fast(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 ctrl_flags); void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, struct mesh_path *mpath); void mesh_fast_tx_gc(struct ieee80211_sub_if_data *sdata); void mesh_fast_tx_flush_addr(struct ieee80211_sub_if_data *sdata, const u8 *addr); void mesh_fast_tx_flush_mpath(struct mesh_path *mpath); void mesh_fast_tx_flush_sta(struct ieee80211_sub_if_data *sdata, struct sta_info *sta); void mesh_path_refresh(struct ieee80211_sub_if_data *sdata, struct mesh_path *mpath, const u8 *addr); #ifdef CONFIG_MAC80211_MESH static inline u64 mesh_plink_inc_estab_count(struct ieee80211_sub_if_data *sdata) { atomic_inc(&sdata->u.mesh.estab_plinks); return mesh_accept_plinks_update(sdata) | BSS_CHANGED_BEACON; } static inline u64 mesh_plink_dec_estab_count(struct ieee80211_sub_if_data *sdata) { atomic_dec(&sdata->u.mesh.estab_plinks); return mesh_accept_plinks_update(sdata) | BSS_CHANGED_BEACON; } static inline int mesh_plink_free_count(struct ieee80211_sub_if_data *sdata) { return sdata->u.mesh.mshcfg.dot11MeshMaxPeerLinks - atomic_read(&sdata->u.mesh.estab_plinks); } static inline bool mesh_plink_availables(struct ieee80211_sub_if_data *sdata) { return (min_t(long, mesh_plink_free_count(sdata), MESH_MAX_PLINKS - sdata->local->num_sta)) > 0; } static inline void mesh_path_activate(struct mesh_path *mpath) { mpath->flags |= MESH_PATH_ACTIVE | MESH_PATH_RESOLVED; } static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return sdata->u.mesh.mesh_pp_id == IEEE80211_PATH_PROTOCOL_HWMP; } void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata); void mesh_sync_adjust_tsf(struct ieee80211_sub_if_data *sdata); void ieee80211s_stop(void); #else static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return false; } static inline void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) {} static inline void ieee80211s_stop(void) {} #endif #endif /* IEEE80211S_H */ |
| 82 38 116 6 315 46 117 1 22 22 22 1 3 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for inet_sock * * Authors: Many, reorganised here by * Arnaldo Carvalho de Melo <acme@mandriva.com> */ #ifndef _INET_SOCK_H #define _INET_SOCK_H #include <linux/bitops.h> #include <linux/string.h> #include <linux/types.h> #include <linux/jhash.h> #include <linux/netdevice.h> #include <net/flow.h> #include <net/sock.h> #include <net/request_sock.h> #include <net/netns/hash.h> #include <net/tcp_states.h> #include <net/l3mdev.h> /** struct ip_options - IP Options * * @faddr - Saved first hop address * @nexthop - Saved nexthop address in LSRR and SSRR * @is_strictroute - Strict source route * @srr_is_hit - Packet destination addr was our one * @is_changed - IP checksum more not valid * @rr_needaddr - Need to record addr of outgoing dev * @ts_needtime - Need to record timestamp * @ts_needaddr - Need to record addr of outgoing dev */ struct ip_options { __be32 faddr; __be32 nexthop; unsigned char optlen; unsigned char srr; unsigned char rr; unsigned char ts; unsigned char is_strictroute:1, srr_is_hit:1, is_changed:1, rr_needaddr:1, ts_needtime:1, ts_needaddr:1; unsigned char router_alert; unsigned char cipso; unsigned char __pad2; unsigned char __data[]; }; struct ip_options_rcu { struct rcu_head rcu; struct ip_options opt; }; struct ip_options_data { struct ip_options_rcu opt; char data[40]; }; struct inet_request_sock { struct request_sock req; #define ir_loc_addr req.__req_common.skc_rcv_saddr #define ir_rmt_addr req.__req_common.skc_daddr #define ir_num req.__req_common.skc_num #define ir_rmt_port req.__req_common.skc_dport #define ir_v6_rmt_addr req.__req_common.skc_v6_daddr #define ir_v6_loc_addr req.__req_common.skc_v6_rcv_saddr #define ir_iif req.__req_common.skc_bound_dev_if #define ir_cookie req.__req_common.skc_cookie #define ireq_net req.__req_common.skc_net #define ireq_state req.__req_common.skc_state #define ireq_family req.__req_common.skc_family u16 snd_wscale : 4, rcv_wscale : 4, tstamp_ok : 1, sack_ok : 1, wscale_ok : 1, ecn_ok : 1, acked : 1, no_srccheck: 1, smc_ok : 1; u32 ir_mark; union { struct ip_options_rcu __rcu *ireq_opt; #if IS_ENABLED(CONFIG_IPV6) struct { struct ipv6_txoptions *ipv6_opt; struct sk_buff *pktopts; }; #endif }; }; static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) { return (struct inet_request_sock *)sk; } static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { u32 mark = READ_ONCE(sk->sk_mark); if (!mark && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)) return skb->mark; return mark; } static inline int inet_request_bound_dev_if(const struct sock *sk, struct sk_buff *skb) { int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); if (!bound_dev_if && READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept)) return l3mdev_master_ifindex_by_index(net, skb->skb_iif); #endif return bound_dev_if; } static inline int inet_sk_bound_l3mdev(const struct sock *sk) { #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); if (!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept)) return l3mdev_master_ifindex_by_index(net, sk->sk_bound_dev_if); #endif return 0; } static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if, int dif, int sdif) { if (!bound_dev_if) return !sdif || l3mdev_accept; return bound_dev_if == dif || bound_dev_if == sdif; } static inline bool inet_sk_bound_dev_eq(const struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept), bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); #endif } struct inet_cork { unsigned int flags; __be32 addr; struct ip_options *opt; unsigned int fragsize; int length; /* Total length of all frames */ struct dst_entry *dst; u8 tx_flags; __u8 ttl; __s16 tos; char priority; __u16 gso_size; u64 transmit_time; u32 mark; }; struct inet_cork_full { struct inet_cork base; struct flowi fl; }; struct ip_mc_socklist; struct ipv6_pinfo; struct rtable; /** struct inet_sock - representation of INET sockets * * @sk - ancestor class * @pinet6 - pointer to IPv6 control block * @inet_daddr - Foreign IPv4 addr * @inet_rcv_saddr - Bound local IPv4 addr * @inet_dport - Destination port * @inet_num - Local port * @inet_flags - various atomic flags * @inet_saddr - Sending source * @uc_ttl - Unicast TTL * @inet_sport - Source port * @inet_id - ID counter for DF pkts * @tos - TOS * @mc_ttl - Multicasting TTL * @uc_index - Unicast outgoing device index * @mc_index - Multicast device index * @mc_list - Group array * @cork - info to build ip hdr on each ip frag while socket is corked */ struct inet_sock { /* sk and pinet6 has to be the first two members of inet_sock */ struct sock sk; #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *pinet6; #endif /* Socket demultiplex comparisons on incoming packets. */ #define inet_daddr sk.__sk_common.skc_daddr #define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr #define inet_dport sk.__sk_common.skc_dport #define inet_num sk.__sk_common.skc_num unsigned long inet_flags; __be32 inet_saddr; __s16 uc_ttl; __be16 inet_sport; struct ip_options_rcu __rcu *inet_opt; atomic_t inet_id; __u8 tos; __u8 min_ttl; __u8 mc_ttl; __u8 pmtudisc; __u8 rcv_tos; __u8 convert_csum; int uc_index; int mc_index; __be32 mc_addr; u32 local_port_range; /* high << 16 | low */ struct ip_mc_socklist __rcu *mc_list; struct inet_cork_full cork; }; #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ enum { INET_FLAGS_PKTINFO = 0, INET_FLAGS_TTL = 1, INET_FLAGS_TOS = 2, INET_FLAGS_RECVOPTS = 3, INET_FLAGS_RETOPTS = 4, INET_FLAGS_PASSSEC = 5, INET_FLAGS_ORIGDSTADDR = 6, INET_FLAGS_CHECKSUM = 7, INET_FLAGS_RECVFRAGSIZE = 8, INET_FLAGS_RECVERR = 9, INET_FLAGS_RECVERR_RFC4884 = 10, INET_FLAGS_FREEBIND = 11, INET_FLAGS_HDRINCL = 12, INET_FLAGS_MC_LOOP = 13, INET_FLAGS_MC_ALL = 14, INET_FLAGS_TRANSPARENT = 15, INET_FLAGS_IS_ICSK = 16, INET_FLAGS_NODEFRAG = 17, INET_FLAGS_BIND_ADDRESS_NO_PORT = 18, INET_FLAGS_DEFER_CONNECT = 19, INET_FLAGS_MC6_LOOP = 20, INET_FLAGS_RECVERR6_RFC4884 = 21, INET_FLAGS_MC6_ALL = 22, INET_FLAGS_AUTOFLOWLABEL_SET = 23, INET_FLAGS_AUTOFLOWLABEL = 24, INET_FLAGS_DONTFRAG = 25, INET_FLAGS_RECVERR6 = 26, INET_FLAGS_REPFLOW = 27, INET_FLAGS_RTALERT_ISOLATE = 28, INET_FLAGS_SNDFLOW = 29, INET_FLAGS_RTALERT = 30, }; /* cmsg flags for inet */ #define IP_CMSG_PKTINFO BIT(INET_FLAGS_PKTINFO) #define IP_CMSG_TTL BIT(INET_FLAGS_TTL) #define IP_CMSG_TOS BIT(INET_FLAGS_TOS) #define IP_CMSG_RECVOPTS BIT(INET_FLAGS_RECVOPTS) #define IP_CMSG_RETOPTS BIT(INET_FLAGS_RETOPTS) #define IP_CMSG_PASSSEC BIT(INET_FLAGS_PASSSEC) #define IP_CMSG_ORIGDSTADDR BIT(INET_FLAGS_ORIGDSTADDR) #define IP_CMSG_CHECKSUM BIT(INET_FLAGS_CHECKSUM) #define IP_CMSG_RECVFRAGSIZE BIT(INET_FLAGS_RECVFRAGSIZE) #define IP_CMSG_ALL (IP_CMSG_PKTINFO | IP_CMSG_TTL | \ IP_CMSG_TOS | IP_CMSG_RECVOPTS | \ IP_CMSG_RETOPTS | IP_CMSG_PASSSEC | \ IP_CMSG_ORIGDSTADDR | IP_CMSG_CHECKSUM | \ IP_CMSG_RECVFRAGSIZE) static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet) { return READ_ONCE(inet->inet_flags) & IP_CMSG_ALL; } #define inet_test_bit(nr, sk) \ test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet_set_bit(nr, sk) \ set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet_clear_bit(nr, sk) \ clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet_assign_bit(nr, sk, val) \ assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val) /** * sk_to_full_sk - Access to a full socket * @sk: pointer to a socket * * SYNACK messages might be attached to request sockets. * Some places want to reach the listener in this case. */ static inline struct sock *sk_to_full_sk(struct sock *sk) { #ifdef CONFIG_INET if (sk && sk->sk_state == TCP_NEW_SYN_RECV) sk = inet_reqsk(sk)->rsk_listener; #endif return sk; } /* sk_to_full_sk() variant with a const argument */ static inline const struct sock *sk_const_to_full_sk(const struct sock *sk) { #ifdef CONFIG_INET if (sk && sk->sk_state == TCP_NEW_SYN_RECV) sk = ((const struct request_sock *)sk)->rsk_listener; #endif return sk; } static inline struct sock *skb_to_full_sk(const struct sk_buff *skb) { return sk_to_full_sk(skb->sk); } #define inet_sk(ptr) container_of_const(ptr, struct inet_sock, sk) static inline void __inet_sk_copy_descendant(struct sock *sk_to, const struct sock *sk_from, const int ancestor_size) { memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1, sk_from->sk_prot->obj_size - ancestor_size); } int inet_sk_rebuild_header(struct sock *sk); /** * inet_sk_state_load - read sk->sk_state for lockless contexts * @sk: socket pointer * * Paired with inet_sk_state_store(). Used in places we don't hold socket lock: * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... */ static inline int inet_sk_state_load(const struct sock *sk) { /* state change might impact lockless readers. */ return smp_load_acquire(&sk->sk_state); } /** * inet_sk_state_store - update sk->sk_state * @sk: socket pointer * @newstate: new state * * Paired with inet_sk_state_load(). Should be used in contexts where * state change might impact lockless readers. */ void inet_sk_state_store(struct sock *sk, int newstate); void inet_sk_set_state(struct sock *sk, int state); static inline unsigned int __inet_ehashfn(const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport, u32 initval) { return jhash_3words((__force __u32) laddr, (__force __u32) faddr, ((__u32) lport) << 16 | (__force __u32)fport, initval); } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener); static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { __u8 flags = 0; if (inet_test_bit(TRANSPARENT, sk) || inet_test_bit(HDRINCL, sk)) flags |= FLOWI_FLAG_ANYSRC; return flags; } static inline void inet_inc_convert_csum(struct sock *sk) { inet_sk(sk)->convert_csum++; } static inline void inet_dec_convert_csum(struct sock *sk) { if (inet_sk(sk)->convert_csum > 0) inet_sk(sk)->convert_csum--; } static inline bool inet_get_convert_csum(struct sock *sk) { return !!inet_sk(sk)->convert_csum; } static inline bool inet_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) || test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags); } static inline bool inet_addr_valid_or_nonlocal(struct net *net, struct inet_sock *inet, __be32 addr, int addr_type) { return inet_can_nonlocal_bind(net, inet) || addr == htonl(INADDR_ANY) || addr_type == RTN_LOCAL || addr_type == RTN_MULTICAST || addr_type == RTN_BROADCAST; } #endif /* _INET_SOCK_H */ |
| 15 63 15 17 19 48 49 49 49 49 47 49 49 81 81 82 1 83 81 81 82 83 81 83 58 63 62 61 63 61 1 1 1 6 5 2 5 6 50 49 48 60 61 62 61 61 28 61 1 1 61 60 57 61 58 59 29 63 59 61 62 63 61 62 63 2 2 61 62 63 41 20 15 15 15 15 15 15 14 4 14 40 15 58 60 63 64 62 62 63 1 60 61 59 59 58 60 60 60 59 3 3 3 3 2 2 2 2 2 2 2 2 2 2 2 19 19 19 19 19 8 19 19 8 19 19 19 19 19 17 17 19 18 19 17 17 17 18 19 2 2 2 19 19 19 19 19 19 19 17 18 19 3 3 3 1 1 3 3 3 1 3 3 2 2 2 1 2 2 2 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Keyring handling * * Copyright (C) 2004-2005, 2008, 2013 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/export.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/seq_file.h> #include <linux/err.h> #include <linux/user_namespace.h> #include <linux/nsproxy.h> #include <keys/keyring-type.h> #include <keys/user-type.h> #include <linux/assoc_array_priv.h> #include <linux/uaccess.h> #include <net/net_namespace.h> #include "internal.h" /* * When plumbing the depths of the key tree, this sets a hard limit * set on how deep we're willing to go. */ #define KEYRING_SEARCH_MAX_DEPTH 6 /* * We mark pointers we pass to the associative array with bit 1 set if * they're keyrings and clear otherwise. */ #define KEYRING_PTR_SUBTYPE 0x2UL static inline bool keyring_ptr_is_keyring(const struct assoc_array_ptr *x) { return (unsigned long)x & KEYRING_PTR_SUBTYPE; } static inline struct key *keyring_ptr_to_key(const struct assoc_array_ptr *x) { void *object = assoc_array_ptr_to_leaf(x); return (struct key *)((unsigned long)object & ~KEYRING_PTR_SUBTYPE); } static inline void *keyring_key_to_ptr(struct key *key) { if (key->type == &key_type_keyring) return (void *)((unsigned long)key | KEYRING_PTR_SUBTYPE); return key; } static DEFINE_RWLOCK(keyring_name_lock); /* * Clean up the bits of user_namespace that belong to us. */ void key_free_user_ns(struct user_namespace *ns) { write_lock(&keyring_name_lock); list_del_init(&ns->keyring_name_list); write_unlock(&keyring_name_lock); key_put(ns->user_keyring_register); #ifdef CONFIG_PERSISTENT_KEYRINGS key_put(ns->persistent_keyring_register); #endif } /* * The keyring key type definition. Keyrings are simply keys of this type and * can be treated as ordinary keys in addition to having their own special * operations. */ static int keyring_preparse(struct key_preparsed_payload *prep); static void keyring_free_preparse(struct key_preparsed_payload *prep); static int keyring_instantiate(struct key *keyring, struct key_preparsed_payload *prep); static void keyring_revoke(struct key *keyring); static void keyring_destroy(struct key *keyring); static void keyring_describe(const struct key *keyring, struct seq_file *m); static long keyring_read(const struct key *keyring, char *buffer, size_t buflen); struct key_type key_type_keyring = { .name = "keyring", .def_datalen = 0, .preparse = keyring_preparse, .free_preparse = keyring_free_preparse, .instantiate = keyring_instantiate, .revoke = keyring_revoke, .destroy = keyring_destroy, .describe = keyring_describe, .read = keyring_read, }; EXPORT_SYMBOL(key_type_keyring); /* * Semaphore to serialise link/link calls to prevent two link calls in parallel * introducing a cycle. */ static DEFINE_MUTEX(keyring_serialise_link_lock); /* * Publish the name of a keyring so that it can be found by name (if it has * one and it doesn't begin with a dot). */ static void keyring_publish_name(struct key *keyring) { struct user_namespace *ns = current_user_ns(); if (keyring->description && keyring->description[0] && keyring->description[0] != '.') { write_lock(&keyring_name_lock); list_add_tail(&keyring->name_link, &ns->keyring_name_list); write_unlock(&keyring_name_lock); } } /* * Preparse a keyring payload */ static int keyring_preparse(struct key_preparsed_payload *prep) { return prep->datalen != 0 ? -EINVAL : 0; } /* * Free a preparse of a user defined key payload */ static void keyring_free_preparse(struct key_preparsed_payload *prep) { } /* * Initialise a keyring. * * Returns 0 on success, -EINVAL if given any data. */ static int keyring_instantiate(struct key *keyring, struct key_preparsed_payload *prep) { assoc_array_init(&keyring->keys); /* make the keyring available by name if it has one */ keyring_publish_name(keyring); return 0; } /* * Multiply 64-bits by 32-bits to 96-bits and fold back to 64-bit. Ideally we'd * fold the carry back too, but that requires inline asm. */ static u64 mult_64x32_and_fold(u64 x, u32 y) { u64 hi = (u64)(u32)(x >> 32) * y; u64 lo = (u64)(u32)(x) * y; return lo + ((u64)(u32)hi << 32) + (u32)(hi >> 32); } /* * Hash a key type and description. */ static void hash_key_type_and_desc(struct keyring_index_key *index_key) { const unsigned level_shift = ASSOC_ARRAY_LEVEL_STEP; const unsigned long fan_mask = ASSOC_ARRAY_FAN_MASK; const char *description = index_key->description; unsigned long hash, type; u32 piece; u64 acc; int n, desc_len = index_key->desc_len; type = (unsigned long)index_key->type; acc = mult_64x32_and_fold(type, desc_len + 13); acc = mult_64x32_and_fold(acc, 9207); piece = (unsigned long)index_key->domain_tag; acc = mult_64x32_and_fold(acc, piece); acc = mult_64x32_and_fold(acc, 9207); for (;;) { n = desc_len; if (n <= 0) break; if (n > 4) n = 4; piece = 0; memcpy(&piece, description, n); description += n; desc_len -= n; acc = mult_64x32_and_fold(acc, piece); acc = mult_64x32_and_fold(acc, 9207); } /* Fold the hash down to 32 bits if need be. */ hash = acc; if (ASSOC_ARRAY_KEY_CHUNK_SIZE == 32) hash ^= acc >> 32; /* Squidge all the keyrings into a separate part of the tree to * ordinary keys by making sure the lowest level segment in the hash is * zero for keyrings and non-zero otherwise. */ if (index_key->type != &key_type_keyring && (hash & fan_mask) == 0) hash |= (hash >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - level_shift)) | 1; else if (index_key->type == &key_type_keyring && (hash & fan_mask) != 0) hash = (hash + (hash << level_shift)) & ~fan_mask; index_key->hash = hash; } /* * Finalise an index key to include a part of the description actually in the * index key, to set the domain tag and to calculate the hash. */ void key_set_index_key(struct keyring_index_key *index_key) { static struct key_tag default_domain_tag = { .usage = REFCOUNT_INIT(1), }; size_t n = min_t(size_t, index_key->desc_len, sizeof(index_key->desc)); memcpy(index_key->desc, index_key->description, n); if (!index_key->domain_tag) { if (index_key->type->flags & KEY_TYPE_NET_DOMAIN) index_key->domain_tag = current->nsproxy->net_ns->key_domain; else index_key->domain_tag = &default_domain_tag; } hash_key_type_and_desc(index_key); } /** * key_put_tag - Release a ref on a tag. * @tag: The tag to release. * * This releases a reference the given tag and returns true if that ref was the * last one. */ bool key_put_tag(struct key_tag *tag) { if (refcount_dec_and_test(&tag->usage)) { kfree_rcu(tag, rcu); return true; } return false; } /** * key_remove_domain - Kill off a key domain and gc its keys * @domain_tag: The domain tag to release. * * This marks a domain tag as being dead and releases a ref on it. If that * wasn't the last reference, the garbage collector is poked to try and delete * all keys that were in the domain. */ void key_remove_domain(struct key_tag *domain_tag) { domain_tag->removed = true; if (!key_put_tag(domain_tag)) key_schedule_gc_links(); } /* * Build the next index key chunk. * * We return it one word-sized chunk at a time. */ static unsigned long keyring_get_key_chunk(const void *data, int level) { const struct keyring_index_key *index_key = data; unsigned long chunk = 0; const u8 *d; int desc_len = index_key->desc_len, n = sizeof(chunk); level /= ASSOC_ARRAY_KEY_CHUNK_SIZE; switch (level) { case 0: return index_key->hash; case 1: return index_key->x; case 2: return (unsigned long)index_key->type; case 3: return (unsigned long)index_key->domain_tag; default: level -= 4; if (desc_len <= sizeof(index_key->desc)) return 0; d = index_key->description + sizeof(index_key->desc); d += level * sizeof(long); desc_len -= sizeof(index_key->desc); if (desc_len > n) desc_len = n; do { chunk <<= 8; chunk |= *d++; } while (--desc_len > 0); return chunk; } } static unsigned long keyring_get_object_key_chunk(const void *object, int level) { const struct key *key = keyring_ptr_to_key(object); return keyring_get_key_chunk(&key->index_key, level); } static bool keyring_compare_object(const void *object, const void *data) { const struct keyring_index_key *index_key = data; const struct key *key = keyring_ptr_to_key(object); return key->index_key.type == index_key->type && key->index_key.domain_tag == index_key->domain_tag && key->index_key.desc_len == index_key->desc_len && memcmp(key->index_key.description, index_key->description, index_key->desc_len) == 0; } /* * Compare the index keys of a pair of objects and determine the bit position * at which they differ - if they differ. */ static int keyring_diff_objects(const void *object, const void *data) { const struct key *key_a = keyring_ptr_to_key(object); const struct keyring_index_key *a = &key_a->index_key; const struct keyring_index_key *b = data; unsigned long seg_a, seg_b; int level, i; level = 0; seg_a = a->hash; seg_b = b->hash; if ((seg_a ^ seg_b) != 0) goto differ; level += ASSOC_ARRAY_KEY_CHUNK_SIZE / 8; /* The number of bits contributed by the hash is controlled by a * constant in the assoc_array headers. Everything else thereafter we * can deal with as being machine word-size dependent. */ seg_a = a->x; seg_b = b->x; if ((seg_a ^ seg_b) != 0) goto differ; level += sizeof(unsigned long); /* The next bit may not work on big endian */ seg_a = (unsigned long)a->type; seg_b = (unsigned long)b->type; if ((seg_a ^ seg_b) != 0) goto differ; level += sizeof(unsigned long); seg_a = (unsigned long)a->domain_tag; seg_b = (unsigned long)b->domain_tag; if ((seg_a ^ seg_b) != 0) goto differ; level += sizeof(unsigned long); i = sizeof(a->desc); if (a->desc_len <= i) goto same; for (; i < a->desc_len; i++) { seg_a = *(unsigned char *)(a->description + i); seg_b = *(unsigned char *)(b->description + i); if ((seg_a ^ seg_b) != 0) goto differ_plus_i; } same: return -1; differ_plus_i: level += i; differ: i = level * 8 + __ffs(seg_a ^ seg_b); return i; } /* * Free an object after stripping the keyring flag off of the pointer. */ static void keyring_free_object(void *object) { key_put(keyring_ptr_to_key(object)); } /* * Operations for keyring management by the index-tree routines. */ static const struct assoc_array_ops keyring_assoc_array_ops = { .get_key_chunk = keyring_get_key_chunk, .get_object_key_chunk = keyring_get_object_key_chunk, .compare_object = keyring_compare_object, .diff_objects = keyring_diff_objects, .free_object = keyring_free_object, }; /* * Clean up a keyring when it is destroyed. Unpublish its name if it had one * and dispose of its data. * * The garbage collector detects the final key_put(), removes the keyring from * the serial number tree and then does RCU synchronisation before coming here, * so we shouldn't need to worry about code poking around here with the RCU * readlock held by this time. */ static void keyring_destroy(struct key *keyring) { if (keyring->description) { write_lock(&keyring_name_lock); if (keyring->name_link.next != NULL && !list_empty(&keyring->name_link)) list_del(&keyring->name_link); write_unlock(&keyring_name_lock); } if (keyring->restrict_link) { struct key_restriction *keyres = keyring->restrict_link; key_put(keyres->key); kfree(keyres); } assoc_array_destroy(&keyring->keys, &keyring_assoc_array_ops); } /* * Describe a keyring for /proc. */ static void keyring_describe(const struct key *keyring, struct seq_file *m) { if (keyring->description) seq_puts(m, keyring->description); else seq_puts(m, "[anon]"); if (key_is_positive(keyring)) { if (keyring->keys.nr_leaves_on_tree != 0) seq_printf(m, ": %lu", keyring->keys.nr_leaves_on_tree); else seq_puts(m, ": empty"); } } struct keyring_read_iterator_context { size_t buflen; size_t count; key_serial_t *buffer; }; static int keyring_read_iterator(const void *object, void *data) { struct keyring_read_iterator_context *ctx = data; const struct key *key = keyring_ptr_to_key(object); kenter("{%s,%d},,{%zu/%zu}", key->type->name, key->serial, ctx->count, ctx->buflen); if (ctx->count >= ctx->buflen) return 1; *ctx->buffer++ = key->serial; ctx->count += sizeof(key->serial); return 0; } /* * Read a list of key IDs from the keyring's contents in binary form * * The keyring's semaphore is read-locked by the caller. This prevents someone * from modifying it under us - which could cause us to read key IDs multiple * times. */ static long keyring_read(const struct key *keyring, char *buffer, size_t buflen) { struct keyring_read_iterator_context ctx; long ret; kenter("{%d},,%zu", key_serial(keyring), buflen); if (buflen & (sizeof(key_serial_t) - 1)) return -EINVAL; /* Copy as many key IDs as fit into the buffer */ if (buffer && buflen) { ctx.buffer = (key_serial_t *)buffer; ctx.buflen = buflen; ctx.count = 0; ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx); if (ret < 0) { kleave(" = %ld [iterate]", ret); return ret; } } /* Return the size of the buffer needed */ ret = keyring->keys.nr_leaves_on_tree * sizeof(key_serial_t); if (ret <= buflen) kleave("= %ld [ok]", ret); else kleave("= %ld [buffer too small]", ret); return ret; } /* * Allocate a keyring and link into the destination keyring. */ struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link, struct key *dest) { struct key *keyring; int ret; keyring = key_alloc(&key_type_keyring, description, uid, gid, cred, perm, flags, restrict_link); if (!IS_ERR(keyring)) { ret = key_instantiate_and_link(keyring, NULL, 0, dest, NULL); if (ret < 0) { key_put(keyring); keyring = ERR_PTR(ret); } } return keyring; } EXPORT_SYMBOL(keyring_alloc); /** * restrict_link_reject - Give -EPERM to restrict link * @keyring: The keyring being added to. * @type: The type of key being added. * @payload: The payload of the key intended to be added. * @restriction_key: Keys providing additional data for evaluating restriction. * * Reject the addition of any links to a keyring. It can be overridden by * passing KEY_ALLOC_BYPASS_RESTRICTION to key_instantiate_and_link() when * adding a key to a keyring. * * This is meant to be stored in a key_restriction structure which is passed * in the restrict_link parameter to keyring_alloc(). */ int restrict_link_reject(struct key *keyring, const struct key_type *type, const union key_payload *payload, struct key *restriction_key) { return -EPERM; } /* * By default, we keys found by getting an exact match on their descriptions. */ bool key_default_cmp(const struct key *key, const struct key_match_data *match_data) { return strcmp(key->description, match_data->raw_data) == 0; } /* * Iteration function to consider each key found. */ static int keyring_search_iterator(const void *object, void *iterator_data) { struct keyring_search_context *ctx = iterator_data; const struct key *key = keyring_ptr_to_key(object); unsigned long kflags = READ_ONCE(key->flags); short state = READ_ONCE(key->state); kenter("{%d}", key->serial); /* ignore keys not of this type */ if (key->type != ctx->index_key.type) { kleave(" = 0 [!type]"); return 0; } /* skip invalidated, revoked and expired keys */ if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) { time64_t expiry = READ_ONCE(key->expiry); if (kflags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) { ctx->result = ERR_PTR(-EKEYREVOKED); kleave(" = %d [invrev]", ctx->skipped_ret); goto skipped; } if (expiry && ctx->now >= expiry) { if (!(ctx->flags & KEYRING_SEARCH_SKIP_EXPIRED)) ctx->result = ERR_PTR(-EKEYEXPIRED); kleave(" = %d [expire]", ctx->skipped_ret); goto skipped; } } /* keys that don't match */ if (!ctx->match_data.cmp(key, &ctx->match_data)) { kleave(" = 0 [!match]"); return 0; } /* key must have search permissions */ if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) && key_task_permission(make_key_ref(key, ctx->possessed), ctx->cred, KEY_NEED_SEARCH) < 0) { ctx->result = ERR_PTR(-EACCES); kleave(" = %d [!perm]", ctx->skipped_ret); goto skipped; } if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) { /* we set a different error code if we pass a negative key */ if (state < 0) { ctx->result = ERR_PTR(state); kleave(" = %d [neg]", ctx->skipped_ret); goto skipped; } } /* Found */ ctx->result = make_key_ref(key, ctx->possessed); kleave(" = 1 [found]"); return 1; skipped: return ctx->skipped_ret; } /* * Search inside a keyring for a key. We can search by walking to it * directly based on its index-key or we can iterate over the entire * tree looking for it, based on the match function. */ static int search_keyring(struct key *keyring, struct keyring_search_context *ctx) { if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_DIRECT) { const void *object; object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops, &ctx->index_key); return object ? ctx->iterator(object, ctx) : 0; } return assoc_array_iterate(&keyring->keys, ctx->iterator, ctx); } /* * Search a tree of keyrings that point to other keyrings up to the maximum * depth. */ static bool search_nested_keyrings(struct key *keyring, struct keyring_search_context *ctx) { struct { struct key *keyring; struct assoc_array_node *node; int slot; } stack[KEYRING_SEARCH_MAX_DEPTH]; struct assoc_array_shortcut *shortcut; struct assoc_array_node *node; struct assoc_array_ptr *ptr; struct key *key; int sp = 0, slot; kenter("{%d},{%s,%s}", keyring->serial, ctx->index_key.type->name, ctx->index_key.description); #define STATE_CHECKS (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_DO_STATE_CHECK) BUG_ON((ctx->flags & STATE_CHECKS) == 0 || (ctx->flags & STATE_CHECKS) == STATE_CHECKS); if (ctx->index_key.description) key_set_index_key(&ctx->index_key); /* Check to see if this top-level keyring is what we are looking for * and whether it is valid or not. */ if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_ITERATE || keyring_compare_object(keyring, &ctx->index_key)) { ctx->skipped_ret = 2; switch (ctx->iterator(keyring_key_to_ptr(keyring), ctx)) { case 1: goto found; case 2: return false; default: break; } } ctx->skipped_ret = 0; /* Start processing a new keyring */ descend_to_keyring: kdebug("descend to %d", keyring->serial); if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) goto not_this_keyring; /* Search through the keys in this keyring before its searching its * subtrees. */ if (search_keyring(keyring, ctx)) goto found; /* Then manually iterate through the keyrings nested in this one. * * Start from the root node of the index tree. Because of the way the * hash function has been set up, keyrings cluster on the leftmost * branch of the root node (root slot 0) or in the root node itself. * Non-keyrings avoid the leftmost branch of the root entirely (root * slots 1-15). */ if (!(ctx->flags & KEYRING_SEARCH_RECURSE)) goto not_this_keyring; ptr = READ_ONCE(keyring->keys.root); if (!ptr) goto not_this_keyring; if (assoc_array_ptr_is_shortcut(ptr)) { /* If the root is a shortcut, either the keyring only contains * keyring pointers (everything clusters behind root slot 0) or * doesn't contain any keyring pointers. */ shortcut = assoc_array_ptr_to_shortcut(ptr); if ((shortcut->index_key[0] & ASSOC_ARRAY_FAN_MASK) != 0) goto not_this_keyring; ptr = READ_ONCE(shortcut->next_node); node = assoc_array_ptr_to_node(ptr); goto begin_node; } node = assoc_array_ptr_to_node(ptr); ptr = node->slots[0]; if (!assoc_array_ptr_is_meta(ptr)) goto begin_node; descend_to_node: /* Descend to a more distal node in this keyring's content tree and go * through that. */ kdebug("descend"); if (assoc_array_ptr_is_shortcut(ptr)) { shortcut = assoc_array_ptr_to_shortcut(ptr); ptr = READ_ONCE(shortcut->next_node); BUG_ON(!assoc_array_ptr_is_node(ptr)); } node = assoc_array_ptr_to_node(ptr); begin_node: kdebug("begin_node"); slot = 0; ascend_to_node: /* Go through the slots in a node */ for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { ptr = READ_ONCE(node->slots[slot]); if (assoc_array_ptr_is_meta(ptr) && node->back_pointer) goto descend_to_node; if (!keyring_ptr_is_keyring(ptr)) continue; key = keyring_ptr_to_key(ptr); if (sp >= KEYRING_SEARCH_MAX_DEPTH) { if (ctx->flags & KEYRING_SEARCH_DETECT_TOO_DEEP) { ctx->result = ERR_PTR(-ELOOP); return false; } goto not_this_keyring; } /* Search a nested keyring */ if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) && key_task_permission(make_key_ref(key, ctx->possessed), ctx->cred, KEY_NEED_SEARCH) < 0) continue; /* stack the current position */ stack[sp].keyring = keyring; stack[sp].node = node; stack[sp].slot = slot; sp++; /* begin again with the new keyring */ keyring = key; goto descend_to_keyring; } /* We've dealt with all the slots in the current node, so now we need * to ascend to the parent and continue processing there. */ ptr = READ_ONCE(node->back_pointer); slot = node->parent_slot; if (ptr && assoc_array_ptr_is_shortcut(ptr)) { shortcut = assoc_array_ptr_to_shortcut(ptr); ptr = READ_ONCE(shortcut->back_pointer); slot = shortcut->parent_slot; } if (!ptr) goto not_this_keyring; node = assoc_array_ptr_to_node(ptr); slot++; /* If we've ascended to the root (zero backpointer), we must have just * finished processing the leftmost branch rather than the root slots - * so there can't be any more keyrings for us to find. */ if (node->back_pointer) { kdebug("ascend %d", slot); goto ascend_to_node; } /* The keyring we're looking at was disqualified or didn't contain a * matching key. */ not_this_keyring: kdebug("not_this_keyring %d", sp); if (sp <= 0) { kleave(" = false"); return false; } /* Resume the processing of a keyring higher up in the tree */ sp--; keyring = stack[sp].keyring; node = stack[sp].node; slot = stack[sp].slot + 1; kdebug("ascend to %d [%d]", keyring->serial, slot); goto ascend_to_node; /* We found a viable match */ found: key = key_ref_to_ptr(ctx->result); key_check(key); if (!(ctx->flags & KEYRING_SEARCH_NO_UPDATE_TIME)) { key->last_used_at = ctx->now; keyring->last_used_at = ctx->now; while (sp > 0) stack[--sp].keyring->last_used_at = ctx->now; } kleave(" = true"); return true; } /** * keyring_search_rcu - Search a keyring tree for a matching key under RCU * @keyring_ref: A pointer to the keyring with possession indicator. * @ctx: The keyring search context. * * Search the supplied keyring tree for a key that matches the criteria given. * The root keyring and any linked keyrings must grant Search permission to the * caller to be searchable and keys can only be found if they too grant Search * to the caller. The possession flag on the root keyring pointer controls use * of the possessor bits in permissions checking of the entire tree. In * addition, the LSM gets to forbid keyring searches and key matches. * * The search is performed as a breadth-then-depth search up to the prescribed * limit (KEYRING_SEARCH_MAX_DEPTH). The caller must hold the RCU read lock to * prevent keyrings from being destroyed or rearranged whilst they are being * searched. * * Keys are matched to the type provided and are then filtered by the match * function, which is given the description to use in any way it sees fit. The * match function may use any attributes of a key that it wishes to * determine the match. Normally the match function from the key type would be * used. * * RCU can be used to prevent the keyring key lists from disappearing without * the need to take lots of locks. * * Returns a pointer to the found key and increments the key usage count if * successful; -EAGAIN if no matching keys were found, or if expired or revoked * keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the * specified keyring wasn't a keyring. * * In the case of a successful return, the possession attribute from * @keyring_ref is propagated to the returned key reference. */ key_ref_t keyring_search_rcu(key_ref_t keyring_ref, struct keyring_search_context *ctx) { struct key *keyring; long err; ctx->iterator = keyring_search_iterator; ctx->possessed = is_key_possessed(keyring_ref); ctx->result = ERR_PTR(-EAGAIN); keyring = key_ref_to_ptr(keyring_ref); key_check(keyring); if (keyring->type != &key_type_keyring) return ERR_PTR(-ENOTDIR); if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM)) { err = key_task_permission(keyring_ref, ctx->cred, KEY_NEED_SEARCH); if (err < 0) return ERR_PTR(err); } ctx->now = ktime_get_real_seconds(); if (search_nested_keyrings(keyring, ctx)) __key_get(key_ref_to_ptr(ctx->result)); return ctx->result; } /** * keyring_search - Search the supplied keyring tree for a matching key * @keyring: The root of the keyring tree to be searched. * @type: The type of keyring we want to find. * @description: The name of the keyring we want to find. * @recurse: True to search the children of @keyring also * * As keyring_search_rcu() above, but using the current task's credentials and * type's default matching function and preferred search method. */ key_ref_t keyring_search(key_ref_t keyring, struct key_type *type, const char *description, bool recurse) { struct keyring_search_context ctx = { .index_key.type = type, .index_key.description = description, .index_key.desc_len = strlen(description), .cred = current_cred(), .match_data.cmp = key_default_cmp, .match_data.raw_data = description, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .flags = KEYRING_SEARCH_DO_STATE_CHECK, }; key_ref_t key; int ret; if (recurse) ctx.flags |= KEYRING_SEARCH_RECURSE; if (type->match_preparse) { ret = type->match_preparse(&ctx.match_data); if (ret < 0) return ERR_PTR(ret); } rcu_read_lock(); key = keyring_search_rcu(keyring, &ctx); rcu_read_unlock(); if (type->match_free) type->match_free(&ctx.match_data); return key; } EXPORT_SYMBOL(keyring_search); static struct key_restriction *keyring_restriction_alloc( key_restrict_link_func_t check) { struct key_restriction *keyres = kzalloc(sizeof(struct key_restriction), GFP_KERNEL); if (!keyres) return ERR_PTR(-ENOMEM); keyres->check = check; return keyres; } /* * Semaphore to serialise restriction setup to prevent reference count * cycles through restriction key pointers. */ static DECLARE_RWSEM(keyring_serialise_restrict_sem); /* * Check for restriction cycles that would prevent keyring garbage collection. * keyring_serialise_restrict_sem must be held. */ static bool keyring_detect_restriction_cycle(const struct key *dest_keyring, struct key_restriction *keyres) { while (keyres && keyres->key && keyres->key->type == &key_type_keyring) { if (keyres->key == dest_keyring) return true; keyres = keyres->key->restrict_link; } return false; } /** * keyring_restrict - Look up and apply a restriction to a keyring * @keyring_ref: The keyring to be restricted * @type: The key type that will provide the restriction checker. * @restriction: The restriction options to apply to the keyring * * Look up a keyring and apply a restriction to it. The restriction is managed * by the specific key type, but can be configured by the options specified in * the restriction string. */ int keyring_restrict(key_ref_t keyring_ref, const char *type, const char *restriction) { struct key *keyring; struct key_type *restrict_type = NULL; struct key_restriction *restrict_link; int ret = 0; keyring = key_ref_to_ptr(keyring_ref); key_check(keyring); if (keyring->type != &key_type_keyring) return -ENOTDIR; if (!type) { restrict_link = keyring_restriction_alloc(restrict_link_reject); } else { restrict_type = key_type_lookup(type); if (IS_ERR(restrict_type)) return PTR_ERR(restrict_type); if (!restrict_type->lookup_restriction) { ret = -ENOENT; goto error; } restrict_link = restrict_type->lookup_restriction(restriction); } if (IS_ERR(restrict_link)) { ret = PTR_ERR(restrict_link); goto error; } down_write(&keyring->sem); down_write(&keyring_serialise_restrict_sem); if (keyring->restrict_link) { ret = -EEXIST; } else if (keyring_detect_restriction_cycle(keyring, restrict_link)) { ret = -EDEADLK; } else { keyring->restrict_link = restrict_link; notify_key(keyring, NOTIFY_KEY_SETATTR, 0); } up_write(&keyring_serialise_restrict_sem); up_write(&keyring->sem); if (ret < 0) { key_put(restrict_link->key); kfree(restrict_link); } error: if (restrict_type) key_type_put(restrict_type); return ret; } EXPORT_SYMBOL(keyring_restrict); /* * Search the given keyring for a key that might be updated. * * The caller must guarantee that the keyring is a keyring and that the * permission is granted to modify the keyring as no check is made here. The * caller must also hold a lock on the keyring semaphore. * * Returns a pointer to the found key with usage count incremented if * successful and returns NULL if not found. Revoked and invalidated keys are * skipped over. * * If successful, the possession indicator is propagated from the keyring ref * to the returned key reference. */ key_ref_t find_key_to_update(key_ref_t keyring_ref, const struct keyring_index_key *index_key) { struct key *keyring, *key; const void *object; keyring = key_ref_to_ptr(keyring_ref); kenter("{%d},{%s,%s}", keyring->serial, index_key->type->name, index_key->description); object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops, index_key); if (object) goto found; kleave(" = NULL"); return NULL; found: key = keyring_ptr_to_key(object); if (key->flags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) { kleave(" = NULL [x]"); return NULL; } __key_get(key); kleave(" = {%d}", key->serial); return make_key_ref(key, is_key_possessed(keyring_ref)); } /* * Find a keyring with the specified name. * * Only keyrings that have nonzero refcount, are not revoked, and are owned by a * user in the current user namespace are considered. If @uid_keyring is %true, * the keyring additionally must have been allocated as a user or user session * keyring; otherwise, it must grant Search permission directly to the caller. * * Returns a pointer to the keyring with the keyring's refcount having being * incremented on success. -ENOKEY is returned if a key could not be found. */ struct key *find_keyring_by_name(const char *name, bool uid_keyring) { struct user_namespace *ns = current_user_ns(); struct key *keyring; if (!name) return ERR_PTR(-EINVAL); read_lock(&keyring_name_lock); /* Search this hash bucket for a keyring with a matching name that * grants Search permission and that hasn't been revoked */ list_for_each_entry(keyring, &ns->keyring_name_list, name_link) { if (!kuid_has_mapping(ns, keyring->user->uid)) continue; if (test_bit(KEY_FLAG_REVOKED, &keyring->flags)) continue; if (strcmp(keyring->description, name) != 0) continue; if (uid_keyring) { if (!test_bit(KEY_FLAG_UID_KEYRING, &keyring->flags)) continue; } else { if (key_permission(make_key_ref(keyring, 0), KEY_NEED_SEARCH) < 0) continue; } /* we've got a match but we might end up racing with * key_cleanup() if the keyring is currently 'dead' * (ie. it has a zero usage count) */ if (!refcount_inc_not_zero(&keyring->usage)) continue; keyring->last_used_at = ktime_get_real_seconds(); goto out; } keyring = ERR_PTR(-ENOKEY); out: read_unlock(&keyring_name_lock); return keyring; } static int keyring_detect_cycle_iterator(const void *object, void *iterator_data) { struct keyring_search_context *ctx = iterator_data; const struct key *key = keyring_ptr_to_key(object); kenter("{%d}", key->serial); /* We might get a keyring with matching index-key that is nonetheless a * different keyring. */ if (key != ctx->match_data.raw_data) return 0; ctx->result = ERR_PTR(-EDEADLK); return 1; } /* * See if a cycle will be created by inserting acyclic tree B in acyclic * tree A at the topmost level (ie: as a direct child of A). * * Since we are adding B to A at the top level, checking for cycles should just * be a matter of seeing if node A is somewhere in tree B. */ static int keyring_detect_cycle(struct key *A, struct key *B) { struct keyring_search_context ctx = { .index_key = A->index_key, .match_data.raw_data = A, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .iterator = keyring_detect_cycle_iterator, .flags = (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_NO_UPDATE_TIME | KEYRING_SEARCH_NO_CHECK_PERM | KEYRING_SEARCH_DETECT_TOO_DEEP | KEYRING_SEARCH_RECURSE), }; rcu_read_lock(); search_nested_keyrings(B, &ctx); rcu_read_unlock(); return PTR_ERR(ctx.result) == -EAGAIN ? 0 : PTR_ERR(ctx.result); } /* * Lock keyring for link. */ int __key_link_lock(struct key *keyring, const struct keyring_index_key *index_key) __acquires(&keyring->sem) __acquires(&keyring_serialise_link_lock) { if (keyring->type != &key_type_keyring) return -ENOTDIR; down_write(&keyring->sem); /* Serialise link/link calls to prevent parallel calls causing a cycle * when linking two keyring in opposite orders. */ if (index_key->type == &key_type_keyring) mutex_lock(&keyring_serialise_link_lock); return 0; } /* * Lock keyrings for move (link/unlink combination). */ int __key_move_lock(struct key *l_keyring, struct key *u_keyring, const struct keyring_index_key *index_key) __acquires(&l_keyring->sem) __acquires(&u_keyring->sem) __acquires(&keyring_serialise_link_lock) { if (l_keyring->type != &key_type_keyring || u_keyring->type != &key_type_keyring) return -ENOTDIR; /* We have to be very careful here to take the keyring locks in the * right order, lest we open ourselves to deadlocking against another * move operation. */ if (l_keyring < u_keyring) { down_write(&l_keyring->sem); down_write_nested(&u_keyring->sem, 1); } else { down_write(&u_keyring->sem); down_write_nested(&l_keyring->sem, 1); } /* Serialise link/link calls to prevent parallel calls causing a cycle * when linking two keyring in opposite orders. */ if (index_key->type == &key_type_keyring) mutex_lock(&keyring_serialise_link_lock); return 0; } /* * Preallocate memory so that a key can be linked into to a keyring. */ int __key_link_begin(struct key *keyring, const struct keyring_index_key *index_key, struct assoc_array_edit **_edit) { struct assoc_array_edit *edit; int ret; kenter("%d,%s,%s,", keyring->serial, index_key->type->name, index_key->description); BUG_ON(index_key->desc_len == 0); BUG_ON(*_edit != NULL); *_edit = NULL; ret = -EKEYREVOKED; if (test_bit(KEY_FLAG_REVOKED, &keyring->flags)) goto error; /* Create an edit script that will insert/replace the key in the * keyring tree. */ edit = assoc_array_insert(&keyring->keys, &keyring_assoc_array_ops, index_key, NULL); if (IS_ERR(edit)) { ret = PTR_ERR(edit); goto error; } /* If we're not replacing a link in-place then we're going to need some * extra quota. */ if (!edit->dead_leaf) { ret = key_payload_reserve(keyring, keyring->datalen + KEYQUOTA_LINK_BYTES); if (ret < 0) goto error_cancel; } *_edit = edit; kleave(" = 0"); return 0; error_cancel: assoc_array_cancel_edit(edit); error: kleave(" = %d", ret); return ret; } /* * Check already instantiated keys aren't going to be a problem. * * The caller must have called __key_link_begin(). Don't need to call this for * keys that were created since __key_link_begin() was called. */ int __key_link_check_live_key(struct key *keyring, struct key *key) { if (key->type == &key_type_keyring) /* check that we aren't going to create a cycle by linking one * keyring to another */ return keyring_detect_cycle(keyring, key); return 0; } /* * Link a key into to a keyring. * * Must be called with __key_link_begin() having being called. Discards any * already extant link to matching key if there is one, so that each keyring * holds at most one link to any given key of a particular type+description * combination. */ void __key_link(struct key *keyring, struct key *key, struct assoc_array_edit **_edit) { __key_get(key); assoc_array_insert_set_object(*_edit, keyring_key_to_ptr(key)); assoc_array_apply_edit(*_edit); *_edit = NULL; notify_key(keyring, NOTIFY_KEY_LINKED, key_serial(key)); } /* * Finish linking a key into to a keyring. * * Must be called with __key_link_begin() having being called. */ void __key_link_end(struct key *keyring, const struct keyring_index_key *index_key, struct assoc_array_edit *edit) __releases(&keyring->sem) __releases(&keyring_serialise_link_lock) { BUG_ON(index_key->type == NULL); kenter("%d,%s,", keyring->serial, index_key->type->name); if (edit) { if (!edit->dead_leaf) { key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES); } assoc_array_cancel_edit(edit); } up_write(&keyring->sem); if (index_key->type == &key_type_keyring) mutex_unlock(&keyring_serialise_link_lock); } /* * Check addition of keys to restricted keyrings. */ static int __key_link_check_restriction(struct key *keyring, struct key *key) { if (!keyring->restrict_link || !keyring->restrict_link->check) return 0; return keyring->restrict_link->check(keyring, key->type, &key->payload, keyring->restrict_link->key); } /** * key_link - Link a key to a keyring * @keyring: The keyring to make the link in. * @key: The key to link to. * * Make a link in a keyring to a key, such that the keyring holds a reference * on that key and the key can potentially be found by searching that keyring. * * This function will write-lock the keyring's semaphore and will consume some * of the user's key data quota to hold the link. * * Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring, * -EKEYREVOKED if the keyring has been revoked, -ENFILE if the keyring is * full, -EDQUOT if there is insufficient key data quota remaining to add * another link or -ENOMEM if there's insufficient memory. * * It is assumed that the caller has checked that it is permitted for a link to * be made (the keyring should have Write permission and the key Link * permission). */ int key_link(struct key *keyring, struct key *key) { struct assoc_array_edit *edit = NULL; int ret; kenter("{%d,%d}", keyring->serial, refcount_read(&keyring->usage)); key_check(keyring); key_check(key); ret = __key_link_lock(keyring, &key->index_key); if (ret < 0) goto error; ret = __key_link_begin(keyring, &key->index_key, &edit); if (ret < 0) goto error_end; kdebug("begun {%d,%d}", keyring->serial, refcount_read(&keyring->usage)); ret = __key_link_check_restriction(keyring, key); if (ret == 0) ret = __key_link_check_live_key(keyring, key); if (ret == 0) __key_link(keyring, key, &edit); error_end: __key_link_end(keyring, &key->index_key, edit); error: kleave(" = %d {%d,%d}", ret, keyring->serial, refcount_read(&keyring->usage)); return ret; } EXPORT_SYMBOL(key_link); /* * Lock a keyring for unlink. */ static int __key_unlink_lock(struct key *keyring) __acquires(&keyring->sem) { if (keyring->type != &key_type_keyring) return -ENOTDIR; down_write(&keyring->sem); return 0; } /* * Begin the process of unlinking a key from a keyring. */ static int __key_unlink_begin(struct key *keyring, struct key *key, struct assoc_array_edit **_edit) { struct assoc_array_edit *edit; BUG_ON(*_edit != NULL); edit = assoc_array_delete(&keyring->keys, &keyring_assoc_array_ops, &key->index_key); if (IS_ERR(edit)) return PTR_ERR(edit); if (!edit) return -ENOENT; *_edit = edit; return 0; } /* * Apply an unlink change. */ static void __key_unlink(struct key *keyring, struct key *key, struct assoc_array_edit **_edit) { assoc_array_apply_edit(*_edit); notify_key(keyring, NOTIFY_KEY_UNLINKED, key_serial(key)); *_edit = NULL; key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES); } /* * Finish unlinking a key from to a keyring. */ static void __key_unlink_end(struct key *keyring, struct key *key, struct assoc_array_edit *edit) __releases(&keyring->sem) { if (edit) assoc_array_cancel_edit(edit); up_write(&keyring->sem); } /** * key_unlink - Unlink the first link to a key from a keyring. * @keyring: The keyring to remove the link from. * @key: The key the link is to. * * Remove a link from a keyring to a key. * * This function will write-lock the keyring's semaphore. * * Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring, -ENOENT if * the key isn't linked to by the keyring or -ENOMEM if there's insufficient * memory. * * It is assumed that the caller has checked that it is permitted for a link to * be removed (the keyring should have Write permission; no permissions are * required on the key). */ int key_unlink(struct key *keyring, struct key *key) { struct assoc_array_edit *edit = NULL; int ret; key_check(keyring); key_check(key); ret = __key_unlink_lock(keyring); if (ret < 0) return ret; ret = __key_unlink_begin(keyring, key, &edit); if (ret == 0) __key_unlink(keyring, key, &edit); __key_unlink_end(keyring, key, edit); return ret; } EXPORT_SYMBOL(key_unlink); /** * key_move - Move a key from one keyring to another * @key: The key to move * @from_keyring: The keyring to remove the link from. * @to_keyring: The keyring to make the link in. * @flags: Qualifying flags, such as KEYCTL_MOVE_EXCL. * * Make a link in @to_keyring to a key, such that the keyring holds a reference * on that key and the key can potentially be found by searching that keyring * whilst simultaneously removing a link to the key from @from_keyring. * * This function will write-lock both keyring's semaphores and will consume * some of the user's key data quota to hold the link on @to_keyring. * * Returns 0 if successful, -ENOTDIR if either keyring isn't a keyring, * -EKEYREVOKED if either keyring has been revoked, -ENFILE if the second * keyring is full, -EDQUOT if there is insufficient key data quota remaining * to add another link or -ENOMEM if there's insufficient memory. If * KEYCTL_MOVE_EXCL is set, then -EEXIST will be returned if there's already a * matching key in @to_keyring. * * It is assumed that the caller has checked that it is permitted for a link to * be made (the keyring should have Write permission and the key Link * permission). */ int key_move(struct key *key, struct key *from_keyring, struct key *to_keyring, unsigned int flags) { struct assoc_array_edit *from_edit = NULL, *to_edit = NULL; int ret; kenter("%d,%d,%d", key->serial, from_keyring->serial, to_keyring->serial); if (from_keyring == to_keyring) return 0; key_check(key); key_check(from_keyring); key_check(to_keyring); ret = __key_move_lock(from_keyring, to_keyring, &key->index_key); if (ret < 0) goto out; ret = __key_unlink_begin(from_keyring, key, &from_edit); if (ret < 0) goto error; ret = __key_link_begin(to_keyring, &key->index_key, &to_edit); if (ret < 0) goto error; ret = -EEXIST; if (to_edit->dead_leaf && (flags & KEYCTL_MOVE_EXCL)) goto error; ret = __key_link_check_restriction(to_keyring, key); if (ret < 0) goto error; ret = __key_link_check_live_key(to_keyring, key); if (ret < 0) goto error; __key_unlink(from_keyring, key, &from_edit); __key_link(to_keyring, key, &to_edit); error: __key_link_end(to_keyring, &key->index_key, to_edit); __key_unlink_end(from_keyring, key, from_edit); out: kleave(" = %d", ret); return ret; } EXPORT_SYMBOL(key_move); /** * keyring_clear - Clear a keyring * @keyring: The keyring to clear. * * Clear the contents of the specified keyring. * * Returns 0 if successful or -ENOTDIR if the keyring isn't a keyring. */ int keyring_clear(struct key *keyring) { struct assoc_array_edit *edit; int ret; if (keyring->type != &key_type_keyring) return -ENOTDIR; down_write(&keyring->sem); edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops); if (IS_ERR(edit)) { ret = PTR_ERR(edit); } else { if (edit) assoc_array_apply_edit(edit); notify_key(keyring, NOTIFY_KEY_CLEARED, 0); key_payload_reserve(keyring, 0); ret = 0; } up_write(&keyring->sem); return ret; } EXPORT_SYMBOL(keyring_clear); /* * Dispose of the links from a revoked keyring. * * This is called with the key sem write-locked. */ static void keyring_revoke(struct key *keyring) { struct assoc_array_edit *edit; edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops); if (!IS_ERR(edit)) { if (edit) assoc_array_apply_edit(edit); key_payload_reserve(keyring, 0); } } static bool keyring_gc_select_iterator(void *object, void *iterator_data) { struct key *key = keyring_ptr_to_key(object); time64_t *limit = iterator_data; if (key_is_dead(key, *limit)) return false; key_get(key); return true; } static int keyring_gc_check_iterator(const void *object, void *iterator_data) { const struct key *key = keyring_ptr_to_key(object); time64_t *limit = iterator_data; key_check(key); return key_is_dead(key, *limit); } /* * Garbage collect pointers from a keyring. * * Not called with any locks held. The keyring's key struct will not be * deallocated under us as only our caller may deallocate it. */ void keyring_gc(struct key *keyring, time64_t limit) { int result; kenter("%x{%s}", keyring->serial, keyring->description ?: ""); if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) goto dont_gc; /* scan the keyring looking for dead keys */ rcu_read_lock(); result = assoc_array_iterate(&keyring->keys, keyring_gc_check_iterator, &limit); rcu_read_unlock(); if (result == true) goto do_gc; dont_gc: kleave(" [no gc]"); return; do_gc: down_write(&keyring->sem); assoc_array_gc(&keyring->keys, &keyring_assoc_array_ops, keyring_gc_select_iterator, &limit); up_write(&keyring->sem); kleave(" [gc]"); } /* * Garbage collect restriction pointers from a keyring. * * Keyring restrictions are associated with a key type, and must be cleaned * up if the key type is unregistered. The restriction is altered to always * reject additional keys so a keyring cannot be opened up by unregistering * a key type. * * Not called with any keyring locks held. The keyring's key struct will not * be deallocated under us as only our caller may deallocate it. * * The caller is required to hold key_types_sem and dead_type->sem. This is * fulfilled by key_gc_keytype() holding the locks on behalf of * key_garbage_collector(), which it invokes on a workqueue. */ void keyring_restriction_gc(struct key *keyring, struct key_type *dead_type) { struct key_restriction *keyres; kenter("%x{%s}", keyring->serial, keyring->description ?: ""); /* * keyring->restrict_link is only assigned at key allocation time * or with the key type locked, so the only values that could be * concurrently assigned to keyring->restrict_link are for key * types other than dead_type. Given this, it's ok to check * the key type before acquiring keyring->sem. */ if (!dead_type || !keyring->restrict_link || keyring->restrict_link->keytype != dead_type) { kleave(" [no restriction gc]"); return; } /* Lock the keyring to ensure that a link is not in progress */ down_write(&keyring->sem); keyres = keyring->restrict_link; keyres->check = restrict_link_reject; key_put(keyres->key); keyres->key = NULL; keyres->keytype = NULL; up_write(&keyring->sem); kleave(" [restriction gc]"); } |
| 372 371 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2013 Politecnico di Torino, Italy * TORSEC group -- https://security.polito.it * * Author: Roberto Sassu <roberto.sassu@polito.it> * * File: ima_template.c * Helpers to manage template descriptors. */ #include <linux/rculist.h> #include "ima.h" #include "ima_template_lib.h" enum header_fields { HDR_PCR, HDR_DIGEST, HDR_TEMPLATE_NAME, HDR_TEMPLATE_DATA, HDR__LAST }; static struct ima_template_desc builtin_templates[] = { {.name = IMA_TEMPLATE_IMA_NAME, .fmt = IMA_TEMPLATE_IMA_FMT}, {.name = "ima-ng", .fmt = "d-ng|n-ng"}, {.name = "ima-sig", .fmt = "d-ng|n-ng|sig"}, {.name = "ima-ngv2", .fmt = "d-ngv2|n-ng"}, {.name = "ima-sigv2", .fmt = "d-ngv2|n-ng|sig"}, {.name = "ima-buf", .fmt = "d-ng|n-ng|buf"}, {.name = "ima-modsig", .fmt = "d-ng|n-ng|sig|d-modsig|modsig"}, {.name = "evm-sig", .fmt = "d-ng|n-ng|evmsig|xattrnames|xattrlengths|xattrvalues|iuid|igid|imode"}, {.name = "", .fmt = ""}, /* placeholder for a custom format */ }; static LIST_HEAD(defined_templates); static DEFINE_SPINLOCK(template_list); static int template_setup_done; static const struct ima_template_field supported_fields[] = { {.field_id = "d", .field_init = ima_eventdigest_init, .field_show = ima_show_template_digest}, {.field_id = "n", .field_init = ima_eventname_init, .field_show = ima_show_template_string}, {.field_id = "d-ng", .field_init = ima_eventdigest_ng_init, .field_show = ima_show_template_digest_ng}, {.field_id = "d-ngv2", .field_init = ima_eventdigest_ngv2_init, .field_show = ima_show_template_digest_ngv2}, {.field_id = "n-ng", .field_init = ima_eventname_ng_init, .field_show = ima_show_template_string}, {.field_id = "sig", .field_init = ima_eventsig_init, .field_show = ima_show_template_sig}, {.field_id = "buf", .field_init = ima_eventbuf_init, .field_show = ima_show_template_buf}, {.field_id = "d-modsig", .field_init = ima_eventdigest_modsig_init, .field_show = ima_show_template_digest_ng}, {.field_id = "modsig", .field_init = ima_eventmodsig_init, .field_show = ima_show_template_sig}, {.field_id = "evmsig", .field_init = ima_eventevmsig_init, .field_show = ima_show_template_sig}, {.field_id = "iuid", .field_init = ima_eventinodeuid_init, .field_show = ima_show_template_uint}, {.field_id = "igid", .field_init = ima_eventinodegid_init, .field_show = ima_show_template_uint}, {.field_id = "imode", .field_init = ima_eventinodemode_init, .field_show = ima_show_template_uint}, {.field_id = "xattrnames", .field_init = ima_eventinodexattrnames_init, .field_show = ima_show_template_string}, {.field_id = "xattrlengths", .field_init = ima_eventinodexattrlengths_init, .field_show = ima_show_template_sig}, {.field_id = "xattrvalues", .field_init = ima_eventinodexattrvalues_init, .field_show = ima_show_template_sig}, }; /* * Used when restoring measurements carried over from a kexec. 'd' and 'n' don't * need to be accounted for since they shouldn't be defined in the same template * description as 'd-ng' and 'n-ng' respectively. */ #define MAX_TEMPLATE_NAME_LEN \ sizeof("d-ng|n-ng|evmsig|xattrnames|xattrlengths|xattrvalues|iuid|igid|imode") static struct ima_template_desc *ima_template; static struct ima_template_desc *ima_buf_template; /** * ima_template_has_modsig - Check whether template has modsig-related fields. * @ima_template: IMA template to check. * * Tells whether the given template has fields referencing a file's appended * signature. */ bool ima_template_has_modsig(const struct ima_template_desc *ima_template) { int i; for (i = 0; i < ima_template->num_fields; i++) if (!strcmp(ima_template->fields[i]->field_id, "modsig") || !strcmp(ima_template->fields[i]->field_id, "d-modsig")) return true; return false; } static int __init ima_template_setup(char *str) { struct ima_template_desc *template_desc; int template_len = strlen(str); if (template_setup_done) return 1; if (!ima_template) ima_init_template_list(); /* * Verify that a template with the supplied name exists. * If not, use CONFIG_IMA_DEFAULT_TEMPLATE. */ template_desc = lookup_template_desc(str); if (!template_desc) { pr_err("template %s not found, using %s\n", str, CONFIG_IMA_DEFAULT_TEMPLATE); return 1; } /* * Verify whether the current hash algorithm is supported * by the 'ima' template. */ if (template_len == 3 && strcmp(str, IMA_TEMPLATE_IMA_NAME) == 0 && ima_hash_algo != HASH_ALGO_SHA1 && ima_hash_algo != HASH_ALGO_MD5) { pr_err("template does not support hash alg\n"); return 1; } ima_template = template_desc; template_setup_done = 1; return 1; } __setup("ima_template=", ima_template_setup); static int __init ima_template_fmt_setup(char *str) { int num_templates = ARRAY_SIZE(builtin_templates); if (template_setup_done) return 1; if (template_desc_init_fields(str, NULL, NULL) < 0) { pr_err("format string '%s' not valid, using template %s\n", str, CONFIG_IMA_DEFAULT_TEMPLATE); return 1; } builtin_templates[num_templates - 1].fmt = str; ima_template = builtin_templates + num_templates - 1; template_setup_done = 1; return 1; } __setup("ima_template_fmt=", ima_template_fmt_setup); struct ima_template_desc *lookup_template_desc(const char *name) { struct ima_template_desc *template_desc; int found = 0; rcu_read_lock(); list_for_each_entry_rcu(template_desc, &defined_templates, list) { if ((strcmp(template_desc->name, name) == 0) || (strcmp(template_desc->fmt, name) == 0)) { found = 1; break; } } rcu_read_unlock(); return found ? template_desc : NULL; } static const struct ima_template_field * lookup_template_field(const char *field_id) { int i; for (i = 0; i < ARRAY_SIZE(supported_fields); i++) if (strncmp(supported_fields[i].field_id, field_id, IMA_TEMPLATE_FIELD_ID_MAX_LEN) == 0) return &supported_fields[i]; return NULL; } static int template_fmt_size(const char *template_fmt) { char c; int template_fmt_len = strlen(template_fmt); int i = 0, j = 0; while (i < template_fmt_len) { c = template_fmt[i]; if (c == '|') j++; i++; } return j + 1; } int template_desc_init_fields(const char *template_fmt, const struct ima_template_field ***fields, int *num_fields) { const char *template_fmt_ptr; const struct ima_template_field *found_fields[IMA_TEMPLATE_NUM_FIELDS_MAX]; int template_num_fields; int i, len; if (num_fields && *num_fields > 0) /* already initialized? */ return 0; template_num_fields = template_fmt_size(template_fmt); if (template_num_fields > IMA_TEMPLATE_NUM_FIELDS_MAX) { pr_err("format string '%s' contains too many fields\n", template_fmt); return -EINVAL; } for (i = 0, template_fmt_ptr = template_fmt; i < template_num_fields; i++, template_fmt_ptr += len + 1) { char tmp_field_id[IMA_TEMPLATE_FIELD_ID_MAX_LEN + 1]; len = strchrnul(template_fmt_ptr, '|') - template_fmt_ptr; if (len == 0 || len > IMA_TEMPLATE_FIELD_ID_MAX_LEN) { pr_err("Invalid field with length %d\n", len); return -EINVAL; } memcpy(tmp_field_id, template_fmt_ptr, len); tmp_field_id[len] = '\0'; found_fields[i] = lookup_template_field(tmp_field_id); if (!found_fields[i]) { pr_err("field '%s' not found\n", tmp_field_id); return -ENOENT; } } if (fields && num_fields) { *fields = kmalloc_array(i, sizeof(**fields), GFP_KERNEL); if (*fields == NULL) return -ENOMEM; memcpy(*fields, found_fields, i * sizeof(**fields)); *num_fields = i; } return 0; } void ima_init_template_list(void) { int i; if (!list_empty(&defined_templates)) return; spin_lock(&template_list); for (i = 0; i < ARRAY_SIZE(builtin_templates); i++) { list_add_tail_rcu(&builtin_templates[i].list, &defined_templates); } spin_unlock(&template_list); } struct ima_template_desc *ima_template_desc_current(void) { if (!ima_template) { ima_init_template_list(); ima_template = lookup_template_desc(CONFIG_IMA_DEFAULT_TEMPLATE); } return ima_template; } struct ima_template_desc *ima_template_desc_buf(void) { if (!ima_buf_template) { ima_init_template_list(); ima_buf_template = lookup_template_desc("ima-buf"); } return ima_buf_template; } int __init ima_init_template(void) { struct ima_template_desc *template = ima_template_desc_current(); int result; result = template_desc_init_fields(template->fmt, &(template->fields), &(template->num_fields)); if (result < 0) { pr_err("template %s init failed, result: %d\n", (strlen(template->name) ? template->name : template->fmt), result); return result; } template = ima_template_desc_buf(); if (!template) { pr_err("Failed to get ima-buf template\n"); return -EINVAL; } result = template_desc_init_fields(template->fmt, &(template->fields), &(template->num_fields)); if (result < 0) pr_err("template %s init failed, result: %d\n", (strlen(template->name) ? template->name : template->fmt), result); return result; } static struct ima_template_desc *restore_template_fmt(char *template_name) { struct ima_template_desc *template_desc = NULL; int ret; ret = template_desc_init_fields(template_name, NULL, NULL); if (ret < 0) { pr_err("attempting to initialize the template \"%s\" failed\n", template_name); goto out; } template_desc = kzalloc(sizeof(*template_desc), GFP_KERNEL); if (!template_desc) goto out; template_desc->name = ""; template_desc->fmt = kstrdup(template_name, GFP_KERNEL); if (!template_desc->fmt) { kfree(template_desc); template_desc = NULL; goto out; } spin_lock(&template_list); list_add_tail_rcu(&template_desc->list, &defined_templates); spin_unlock(&template_list); out: return template_desc; } static int ima_restore_template_data(struct ima_template_desc *template_desc, void *template_data, int template_data_size, struct ima_template_entry **entry) { struct tpm_digest *digests; int ret = 0; int i; *entry = kzalloc(struct_size(*entry, template_data, template_desc->num_fields), GFP_NOFS); if (!*entry) return -ENOMEM; digests = kcalloc(NR_BANKS(ima_tpm_chip) + ima_extra_slots, sizeof(*digests), GFP_NOFS); if (!digests) { kfree(*entry); return -ENOMEM; } (*entry)->digests = digests; ret = ima_parse_buf(template_data, template_data + template_data_size, NULL, template_desc->num_fields, (*entry)->template_data, NULL, NULL, ENFORCE_FIELDS | ENFORCE_BUFEND, "template data"); if (ret < 0) { kfree((*entry)->digests); kfree(*entry); return ret; } (*entry)->template_desc = template_desc; for (i = 0; i < template_desc->num_fields; i++) { struct ima_field_data *field_data = &(*entry)->template_data[i]; u8 *data = field_data->data; (*entry)->template_data[i].data = kzalloc(field_data->len + 1, GFP_KERNEL); if (!(*entry)->template_data[i].data) { ret = -ENOMEM; break; } memcpy((*entry)->template_data[i].data, data, field_data->len); (*entry)->template_data_len += sizeof(field_data->len); (*entry)->template_data_len += field_data->len; } if (ret < 0) { ima_free_template_entry(*entry); *entry = NULL; } return ret; } /* Restore the serialized binary measurement list without extending PCRs. */ int ima_restore_measurement_list(loff_t size, void *buf) { char template_name[MAX_TEMPLATE_NAME_LEN]; unsigned char zero[TPM_DIGEST_SIZE] = { 0 }; struct ima_kexec_hdr *khdr = buf; struct ima_field_data hdr[HDR__LAST] = { [HDR_PCR] = {.len = sizeof(u32)}, [HDR_DIGEST] = {.len = TPM_DIGEST_SIZE}, }; void *bufp = buf + sizeof(*khdr); void *bufendp; struct ima_template_entry *entry; struct ima_template_desc *template_desc; DECLARE_BITMAP(hdr_mask, HDR__LAST); unsigned long count = 0; int ret = 0; if (!buf || size < sizeof(*khdr)) return 0; if (ima_canonical_fmt) { khdr->version = le16_to_cpu((__force __le16)khdr->version); khdr->count = le64_to_cpu((__force __le64)khdr->count); khdr->buffer_size = le64_to_cpu((__force __le64)khdr->buffer_size); } if (khdr->version != 1) { pr_err("attempting to restore a incompatible measurement list"); return -EINVAL; } if (khdr->count > ULONG_MAX - 1) { pr_err("attempting to restore too many measurements"); return -EINVAL; } bitmap_zero(hdr_mask, HDR__LAST); bitmap_set(hdr_mask, HDR_PCR, 1); bitmap_set(hdr_mask, HDR_DIGEST, 1); /* * ima kexec buffer prefix: version, buffer size, count * v1 format: pcr, digest, template-name-len, template-name, * template-data-size, template-data */ bufendp = buf + khdr->buffer_size; while ((bufp < bufendp) && (count++ < khdr->count)) { int enforce_mask = ENFORCE_FIELDS; enforce_mask |= (count == khdr->count) ? ENFORCE_BUFEND : 0; ret = ima_parse_buf(bufp, bufendp, &bufp, HDR__LAST, hdr, NULL, hdr_mask, enforce_mask, "entry header"); if (ret < 0) break; if (hdr[HDR_TEMPLATE_NAME].len >= MAX_TEMPLATE_NAME_LEN) { pr_err("attempting to restore a template name that is too long\n"); ret = -EINVAL; break; } /* template name is not null terminated */ memcpy(template_name, hdr[HDR_TEMPLATE_NAME].data, hdr[HDR_TEMPLATE_NAME].len); template_name[hdr[HDR_TEMPLATE_NAME].len] = 0; if (strcmp(template_name, "ima") == 0) { pr_err("attempting to restore an unsupported template \"%s\" failed\n", template_name); ret = -EINVAL; break; } template_desc = lookup_template_desc(template_name); if (!template_desc) { template_desc = restore_template_fmt(template_name); if (!template_desc) break; } /* * Only the running system's template format is initialized * on boot. As needed, initialize the other template formats. */ ret = template_desc_init_fields(template_desc->fmt, &(template_desc->fields), &(template_desc->num_fields)); if (ret < 0) { pr_err("attempting to restore the template fmt \"%s\" failed\n", template_desc->fmt); ret = -EINVAL; break; } ret = ima_restore_template_data(template_desc, hdr[HDR_TEMPLATE_DATA].data, hdr[HDR_TEMPLATE_DATA].len, &entry); if (ret < 0) break; if (memcmp(hdr[HDR_DIGEST].data, zero, sizeof(zero))) { ret = ima_calc_field_array_hash( &entry->template_data[0], entry); if (ret < 0) { pr_err("cannot calculate template digest\n"); ret = -EINVAL; break; } } entry->pcr = !ima_canonical_fmt ? *(u32 *)(hdr[HDR_PCR].data) : le32_to_cpu(*(__le32 *)(hdr[HDR_PCR].data)); ret = ima_restore_measurement_entry(entry); if (ret < 0) break; } return ret; } |
| 66 55 67 66 65 34 32 32 31 48 67 32 7 25 30 35 3 31 32 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/mutex.h> #include <net/sock.h> #include "nf_internals.h" /* Sockopts only registered and called from user context, so net locking would be overkill. Also, [gs]etsockopt calls may sleep. */ static DEFINE_MUTEX(nf_sockopt_mutex); static LIST_HEAD(nf_sockopts); /* Do exclusive ranges overlap? */ static inline int overlap(int min1, int max1, int min2, int max2) { return max1 > min2 && min1 < max2; } /* Functions to register sockopt ranges (exclusive). */ int nf_register_sockopt(struct nf_sockopt_ops *reg) { struct nf_sockopt_ops *ops; int ret = 0; mutex_lock(&nf_sockopt_mutex); list_for_each_entry(ops, &nf_sockopts, list) { if (ops->pf == reg->pf && (overlap(ops->set_optmin, ops->set_optmax, reg->set_optmin, reg->set_optmax) || overlap(ops->get_optmin, ops->get_optmax, reg->get_optmin, reg->get_optmax))) { pr_debug("nf_sock overlap: %u-%u/%u-%u v %u-%u/%u-%u\n", ops->set_optmin, ops->set_optmax, ops->get_optmin, ops->get_optmax, reg->set_optmin, reg->set_optmax, reg->get_optmin, reg->get_optmax); ret = -EBUSY; goto out; } } list_add(®->list, &nf_sockopts); out: mutex_unlock(&nf_sockopt_mutex); return ret; } EXPORT_SYMBOL(nf_register_sockopt); void nf_unregister_sockopt(struct nf_sockopt_ops *reg) { mutex_lock(&nf_sockopt_mutex); list_del(®->list); mutex_unlock(&nf_sockopt_mutex); } EXPORT_SYMBOL(nf_unregister_sockopt); static struct nf_sockopt_ops *nf_sockopt_find(struct sock *sk, u_int8_t pf, int val, int get) { struct nf_sockopt_ops *ops; mutex_lock(&nf_sockopt_mutex); list_for_each_entry(ops, &nf_sockopts, list) { if (ops->pf == pf) { if (!try_module_get(ops->owner)) goto out_nosup; if (get) { if (val >= ops->get_optmin && val < ops->get_optmax) goto out; } else { if (val >= ops->set_optmin && val < ops->set_optmax) goto out; } module_put(ops->owner); } } out_nosup: ops = ERR_PTR(-ENOPROTOOPT); out: mutex_unlock(&nf_sockopt_mutex); return ops; } int nf_setsockopt(struct sock *sk, u_int8_t pf, int val, sockptr_t opt, unsigned int len) { struct nf_sockopt_ops *ops; int ret; ops = nf_sockopt_find(sk, pf, val, 0); if (IS_ERR(ops)) return PTR_ERR(ops); ret = ops->set(sk, val, opt, len); module_put(ops->owner); return ret; } EXPORT_SYMBOL(nf_setsockopt); int nf_getsockopt(struct sock *sk, u_int8_t pf, int val, char __user *opt, int *len) { struct nf_sockopt_ops *ops; int ret; ops = nf_sockopt_find(sk, pf, val, 1); if (IS_ERR(ops)) return PTR_ERR(ops); ret = ops->get(sk, val, opt, len); module_put(ops->owner); return ret; } EXPORT_SYMBOL(nf_getsockopt); |
| 8 10 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright 2019 Google LLC */ /* * Refer to Documentation/block/inline-encryption.rst for detailed explanation. */ #define pr_fmt(fmt) "blk-crypto: " fmt #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-crypto-profile.h> #include <linux/module.h> #include <linux/ratelimit.h> #include <linux/slab.h> #include "blk-crypto-internal.h" const struct blk_crypto_mode blk_crypto_modes[] = { [BLK_ENCRYPTION_MODE_AES_256_XTS] = { .name = "AES-256-XTS", .cipher_str = "xts(aes)", .keysize = 64, .ivsize = 16, }, [BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV] = { .name = "AES-128-CBC-ESSIV", .cipher_str = "essiv(cbc(aes),sha256)", .keysize = 16, .ivsize = 16, }, [BLK_ENCRYPTION_MODE_ADIANTUM] = { .name = "Adiantum", .cipher_str = "adiantum(xchacha12,aes)", .keysize = 32, .ivsize = 32, }, [BLK_ENCRYPTION_MODE_SM4_XTS] = { .name = "SM4-XTS", .cipher_str = "xts(sm4)", .keysize = 32, .ivsize = 16, }, }; /* * This number needs to be at least (the number of threads doing IO * concurrently) * (maximum recursive depth of a bio), so that we don't * deadlock on crypt_ctx allocations. The default is chosen to be the same * as the default number of post read contexts in both EXT4 and F2FS. */ static int num_prealloc_crypt_ctxs = 128; module_param(num_prealloc_crypt_ctxs, int, 0444); MODULE_PARM_DESC(num_prealloc_crypt_ctxs, "Number of bio crypto contexts to preallocate"); static struct kmem_cache *bio_crypt_ctx_cache; static mempool_t *bio_crypt_ctx_pool; static int __init bio_crypt_ctx_init(void) { size_t i; bio_crypt_ctx_cache = KMEM_CACHE(bio_crypt_ctx, 0); if (!bio_crypt_ctx_cache) goto out_no_mem; bio_crypt_ctx_pool = mempool_create_slab_pool(num_prealloc_crypt_ctxs, bio_crypt_ctx_cache); if (!bio_crypt_ctx_pool) goto out_no_mem; /* This is assumed in various places. */ BUILD_BUG_ON(BLK_ENCRYPTION_MODE_INVALID != 0); /* Sanity check that no algorithm exceeds the defined limits. */ for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++) { BUG_ON(blk_crypto_modes[i].keysize > BLK_CRYPTO_MAX_KEY_SIZE); BUG_ON(blk_crypto_modes[i].ivsize > BLK_CRYPTO_MAX_IV_SIZE); } return 0; out_no_mem: panic("Failed to allocate mem for bio crypt ctxs\n"); } subsys_initcall(bio_crypt_ctx_init); void bio_crypt_set_ctx(struct bio *bio, const struct blk_crypto_key *key, const u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], gfp_t gfp_mask) { struct bio_crypt_ctx *bc; /* * The caller must use a gfp_mask that contains __GFP_DIRECT_RECLAIM so * that the mempool_alloc() can't fail. */ WARN_ON_ONCE(!(gfp_mask & __GFP_DIRECT_RECLAIM)); bc = mempool_alloc(bio_crypt_ctx_pool, gfp_mask); bc->bc_key = key; memcpy(bc->bc_dun, dun, sizeof(bc->bc_dun)); bio->bi_crypt_context = bc; } void __bio_crypt_free_ctx(struct bio *bio) { mempool_free(bio->bi_crypt_context, bio_crypt_ctx_pool); bio->bi_crypt_context = NULL; } int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask) { dst->bi_crypt_context = mempool_alloc(bio_crypt_ctx_pool, gfp_mask); if (!dst->bi_crypt_context) return -ENOMEM; *dst->bi_crypt_context = *src->bi_crypt_context; return 0; } /* Increments @dun by @inc, treating @dun as a multi-limb integer. */ void bio_crypt_dun_increment(u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], unsigned int inc) { int i; for (i = 0; inc && i < BLK_CRYPTO_DUN_ARRAY_SIZE; i++) { dun[i] += inc; /* * If the addition in this limb overflowed, then we need to * carry 1 into the next limb. Else the carry is 0. */ if (dun[i] < inc) inc = 1; else inc = 0; } } void __bio_crypt_advance(struct bio *bio, unsigned int bytes) { struct bio_crypt_ctx *bc = bio->bi_crypt_context; bio_crypt_dun_increment(bc->bc_dun, bytes >> bc->bc_key->data_unit_size_bits); } /* * Returns true if @bc->bc_dun plus @bytes converted to data units is equal to * @next_dun, treating the DUNs as multi-limb integers. */ bool bio_crypt_dun_is_contiguous(const struct bio_crypt_ctx *bc, unsigned int bytes, const u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]) { int i; unsigned int carry = bytes >> bc->bc_key->data_unit_size_bits; for (i = 0; i < BLK_CRYPTO_DUN_ARRAY_SIZE; i++) { if (bc->bc_dun[i] + carry != next_dun[i]) return false; /* * If the addition in this limb overflowed, then we need to * carry 1 into the next limb. Else the carry is 0. */ if ((bc->bc_dun[i] + carry) < carry) carry = 1; else carry = 0; } /* If the DUN wrapped through 0, don't treat it as contiguous. */ return carry == 0; } /* * Checks that two bio crypt contexts are compatible - i.e. that * they are mergeable except for data_unit_num continuity. */ static bool bio_crypt_ctx_compatible(struct bio_crypt_ctx *bc1, struct bio_crypt_ctx *bc2) { if (!bc1) return !bc2; return bc2 && bc1->bc_key == bc2->bc_key; } bool bio_crypt_rq_ctx_compatible(struct request *rq, struct bio *bio) { return bio_crypt_ctx_compatible(rq->crypt_ctx, bio->bi_crypt_context); } /* * Checks that two bio crypt contexts are compatible, and also * that their data_unit_nums are continuous (and can hence be merged) * in the order @bc1 followed by @bc2. */ bool bio_crypt_ctx_mergeable(struct bio_crypt_ctx *bc1, unsigned int bc1_bytes, struct bio_crypt_ctx *bc2) { if (!bio_crypt_ctx_compatible(bc1, bc2)) return false; return !bc1 || bio_crypt_dun_is_contiguous(bc1, bc1_bytes, bc2->bc_dun); } /* Check that all I/O segments are data unit aligned. */ static bool bio_crypt_check_alignment(struct bio *bio) { const unsigned int data_unit_size = bio->bi_crypt_context->bc_key->crypto_cfg.data_unit_size; struct bvec_iter iter; struct bio_vec bv; bio_for_each_segment(bv, bio, iter) { if (!IS_ALIGNED(bv.bv_len | bv.bv_offset, data_unit_size)) return false; } return true; } blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq) { return blk_crypto_get_keyslot(rq->q->crypto_profile, rq->crypt_ctx->bc_key, &rq->crypt_keyslot); } void __blk_crypto_rq_put_keyslot(struct request *rq) { blk_crypto_put_keyslot(rq->crypt_keyslot); rq->crypt_keyslot = NULL; } void __blk_crypto_free_request(struct request *rq) { /* The keyslot, if one was needed, should have been released earlier. */ if (WARN_ON_ONCE(rq->crypt_keyslot)) __blk_crypto_rq_put_keyslot(rq); mempool_free(rq->crypt_ctx, bio_crypt_ctx_pool); rq->crypt_ctx = NULL; } /** * __blk_crypto_bio_prep - Prepare bio for inline encryption * * @bio_ptr: pointer to original bio pointer * * If the bio crypt context provided for the bio is supported by the underlying * device's inline encryption hardware, do nothing. * * Otherwise, try to perform en/decryption for this bio by falling back to the * kernel crypto API. When the crypto API fallback is used for encryption, * blk-crypto may choose to split the bio into 2 - the first one that will * continue to be processed and the second one that will be resubmitted via * submit_bio_noacct. A bounce bio will be allocated to encrypt the contents * of the aforementioned "first one", and *bio_ptr will be updated to this * bounce bio. * * Caller must ensure bio has bio_crypt_ctx. * * Return: true on success; false on error (and bio->bi_status will be set * appropriately, and bio_endio() will have been called so bio * submission should abort). */ bool __blk_crypto_bio_prep(struct bio **bio_ptr) { struct bio *bio = *bio_ptr; const struct blk_crypto_key *bc_key = bio->bi_crypt_context->bc_key; /* Error if bio has no data. */ if (WARN_ON_ONCE(!bio_has_data(bio))) { bio->bi_status = BLK_STS_IOERR; goto fail; } if (!bio_crypt_check_alignment(bio)) { bio->bi_status = BLK_STS_IOERR; goto fail; } /* * Success if device supports the encryption context, or if we succeeded * in falling back to the crypto API. */ if (blk_crypto_config_supported_natively(bio->bi_bdev, &bc_key->crypto_cfg)) return true; if (blk_crypto_fallback_bio_prep(bio_ptr)) return true; fail: bio_endio(*bio_ptr); return false; } int __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, gfp_t gfp_mask) { if (!rq->crypt_ctx) { rq->crypt_ctx = mempool_alloc(bio_crypt_ctx_pool, gfp_mask); if (!rq->crypt_ctx) return -ENOMEM; } *rq->crypt_ctx = *bio->bi_crypt_context; return 0; } /** * blk_crypto_init_key() - Prepare a key for use with blk-crypto * @blk_key: Pointer to the blk_crypto_key to initialize. * @raw_key: Pointer to the raw key. Must be the correct length for the chosen * @crypto_mode; see blk_crypto_modes[]. * @crypto_mode: identifier for the encryption algorithm to use * @dun_bytes: number of bytes that will be used to specify the DUN when this * key is used * @data_unit_size: the data unit size to use for en/decryption * * Return: 0 on success, -errno on failure. The caller is responsible for * zeroizing both blk_key and raw_key when done with them. */ int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, enum blk_crypto_mode_num crypto_mode, unsigned int dun_bytes, unsigned int data_unit_size) { const struct blk_crypto_mode *mode; memset(blk_key, 0, sizeof(*blk_key)); if (crypto_mode >= ARRAY_SIZE(blk_crypto_modes)) return -EINVAL; mode = &blk_crypto_modes[crypto_mode]; if (mode->keysize == 0) return -EINVAL; if (dun_bytes == 0 || dun_bytes > mode->ivsize) return -EINVAL; if (!is_power_of_2(data_unit_size)) return -EINVAL; blk_key->crypto_cfg.crypto_mode = crypto_mode; blk_key->crypto_cfg.dun_bytes = dun_bytes; blk_key->crypto_cfg.data_unit_size = data_unit_size; blk_key->data_unit_size_bits = ilog2(data_unit_size); blk_key->size = mode->keysize; memcpy(blk_key->raw, raw_key, mode->keysize); return 0; } bool blk_crypto_config_supported_natively(struct block_device *bdev, const struct blk_crypto_config *cfg) { return __blk_crypto_cfg_supported(bdev_get_queue(bdev)->crypto_profile, cfg); } /* * Check if bios with @cfg can be en/decrypted by blk-crypto (i.e. either the * block_device it's submitted to supports inline crypto, or the * blk-crypto-fallback is enabled and supports the cfg). */ bool blk_crypto_config_supported(struct block_device *bdev, const struct blk_crypto_config *cfg) { return IS_ENABLED(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) || blk_crypto_config_supported_natively(bdev, cfg); } /** * blk_crypto_start_using_key() - Start using a blk_crypto_key on a device * @bdev: block device to operate on * @key: A key to use on the device * * Upper layers must call this function to ensure that either the hardware * supports the key's crypto settings, or the crypto API fallback has transforms * for the needed mode allocated and ready to go. This function may allocate * an skcipher, and *should not* be called from the data path, since that might * cause a deadlock * * Return: 0 on success; -ENOPKG if the hardware doesn't support the key and * blk-crypto-fallback is either disabled or the needed algorithm * is disabled in the crypto API; or another -errno code. */ int blk_crypto_start_using_key(struct block_device *bdev, const struct blk_crypto_key *key) { if (blk_crypto_config_supported_natively(bdev, &key->crypto_cfg)) return 0; return blk_crypto_fallback_start_using_mode(key->crypto_cfg.crypto_mode); } /** * blk_crypto_evict_key() - Evict a blk_crypto_key from a block_device * @bdev: a block_device on which I/O using the key may have been done * @key: the key to evict * * For a given block_device, this function removes the given blk_crypto_key from * the keyslot management structures and evicts it from any underlying hardware * keyslot(s) or blk-crypto-fallback keyslot it may have been programmed into. * * Upper layers must call this before freeing the blk_crypto_key. It must be * called for every block_device the key may have been used on. The key must no * longer be in use by any I/O when this function is called. * * Context: May sleep. */ void blk_crypto_evict_key(struct block_device *bdev, const struct blk_crypto_key *key) { struct request_queue *q = bdev_get_queue(bdev); int err; if (blk_crypto_config_supported_natively(bdev, &key->crypto_cfg)) err = __blk_crypto_evict_key(q->crypto_profile, key); else err = blk_crypto_fallback_evict_key(key); /* * An error can only occur here if the key failed to be evicted from a * keyslot (due to a hardware or driver issue) or is allegedly still in * use by I/O (due to a kernel bug). Even in these cases, the key is * still unlinked from the keyslot management structures, and the caller * is allowed and expected to free it right away. There's nothing * callers can do to handle errors, so just log them and return void. */ if (err) pr_warn_ratelimited("%pg: error %d evicting key\n", bdev, err); } EXPORT_SYMBOL_GPL(blk_crypto_evict_key); |
| 5 4 4 1 4 4 4 4 4 4 4 4 4 4 4 4 4 1 1 1 1 1 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 1 1 1 1 1 1 1 1 1 1 1 1 1 1 5 5 5 5 5 5 5 4 4 4 4 4 4 4 4 4 4 4 1 1 1 1 1 1 1 1 1 5 7 4 4 4 4 4 5 4 1 5 5 5 5 5 5 5 4 5 4 5 5 5 4 5 5 5 5 5 5 5 5 5 5 4 4 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <net/switchdev.h> #include "br_private.h" #include "br_private_tunnel.h" static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid); static inline int br_vlan_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct net_bridge_vlan *vle = ptr; u16 vid = *(u16 *)arg->key; return vle->vid != vid; } static const struct rhashtable_params br_vlan_rht_params = { .head_offset = offsetof(struct net_bridge_vlan, vnode), .key_offset = offsetof(struct net_bridge_vlan, vid), .key_len = sizeof(u16), .nelem_hint = 3, .max_size = VLAN_N_VID, .obj_cmpfn = br_vlan_cmp, .automatic_shrinking = true, }; static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid) { return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params); } static void __vlan_add_pvid(struct net_bridge_vlan_group *vg, const struct net_bridge_vlan *v) { if (vg->pvid == v->vid) return; smp_wmb(); br_vlan_set_pvid_state(vg, v->state); vg->pvid = v->vid; } static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid) { if (vg->pvid != vid) return; smp_wmb(); vg->pvid = 0; } /* Update the BRIDGE_VLAN_INFO_PVID and BRIDGE_VLAN_INFO_UNTAGGED flags of @v. * If @commit is false, return just whether the BRIDGE_VLAN_INFO_PVID and * BRIDGE_VLAN_INFO_UNTAGGED bits of @flags would produce any change onto @v. */ static bool __vlan_flags_update(struct net_bridge_vlan *v, u16 flags, bool commit) { struct net_bridge_vlan_group *vg; bool change; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); else vg = nbp_vlan_group(v->port); /* check if anything would be changed on commit */ change = !!(flags & BRIDGE_VLAN_INFO_PVID) == !!(vg->pvid != v->vid) || ((flags ^ v->flags) & BRIDGE_VLAN_INFO_UNTAGGED); if (!commit) goto out; if (flags & BRIDGE_VLAN_INFO_PVID) __vlan_add_pvid(vg, v); else __vlan_delete_pvid(vg, v->vid); if (flags & BRIDGE_VLAN_INFO_UNTAGGED) v->flags |= BRIDGE_VLAN_INFO_UNTAGGED; else v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; out: return change; } static bool __vlan_flags_would_change(struct net_bridge_vlan *v, u16 flags) { return __vlan_flags_update(v, flags, false); } static void __vlan_flags_commit(struct net_bridge_vlan *v, u16 flags) { __vlan_flags_update(v, flags, true); } static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, struct net_bridge_vlan *v, u16 flags, struct netlink_ext_ack *extack) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q add. */ err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack); if (err == -EOPNOTSUPP) return vlan_vid_add(dev, br->vlan_proto, v->vid); v->priv_flags |= BR_VLFLAG_ADDED_BY_SWITCHDEV; return err; } static void __vlan_add_list(struct net_bridge_vlan *v) { struct net_bridge_vlan_group *vg; struct list_head *headp, *hpos; struct net_bridge_vlan *vent; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); else vg = nbp_vlan_group(v->port); headp = &vg->vlan_list; list_for_each_prev(hpos, headp) { vent = list_entry(hpos, struct net_bridge_vlan, vlist); if (v->vid >= vent->vid) break; } list_add_rcu(&v->vlist, hpos); } static void __vlan_del_list(struct net_bridge_vlan *v) { list_del_rcu(&v->vlist); } static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, const struct net_bridge_vlan *v) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q del. */ err = br_switchdev_port_vlan_del(dev, v->vid); if (!(v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV)) vlan_vid_del(dev, br->vlan_proto, v->vid); return err == -EOPNOTSUPP ? 0 : err; } /* Returns a master vlan, if it didn't exist it gets created. In all cases * a reference is taken to the master vlan before returning. */ static struct net_bridge_vlan * br_vlan_get_master(struct net_bridge *br, u16 vid, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *masterv; vg = br_vlan_group(br); masterv = br_vlan_find(vg, vid); if (!masterv) { bool changed; /* missing global ctx, create it now */ if (br_vlan_add(br, vid, 0, &changed, extack)) return NULL; masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) return NULL; refcount_set(&masterv->refcnt, 1); return masterv; } refcount_inc(&masterv->refcnt); return masterv; } static void br_master_vlan_rcu_free(struct rcu_head *rcu) { struct net_bridge_vlan *v; v = container_of(rcu, struct net_bridge_vlan, rcu); WARN_ON(!br_vlan_is_master(v)); free_percpu(v->stats); v->stats = NULL; kfree(v); } static void br_vlan_put_master(struct net_bridge_vlan *masterv) { struct net_bridge_vlan_group *vg; if (!br_vlan_is_master(masterv)) return; vg = br_vlan_group(masterv->br); if (refcount_dec_and_test(&masterv->refcnt)) { rhashtable_remove_fast(&vg->vlan_hash, &masterv->vnode, br_vlan_rht_params); __vlan_del_list(masterv); br_multicast_toggle_one_vlan(masterv, false); br_multicast_ctx_deinit(&masterv->br_mcast_ctx); call_rcu(&masterv->rcu, br_master_vlan_rcu_free); } } static void nbp_vlan_rcu_free(struct rcu_head *rcu) { struct net_bridge_vlan *v; v = container_of(rcu, struct net_bridge_vlan, rcu); WARN_ON(br_vlan_is_master(v)); /* if we had per-port stats configured then free them here */ if (v->priv_flags & BR_VLFLAG_PER_PORT_STATS) free_percpu(v->stats); v->stats = NULL; kfree(v); } static void br_vlan_init_state(struct net_bridge_vlan *v) { struct net_bridge *br; if (br_vlan_is_master(v)) br = v->br; else br = v->port->br; if (br_opt_get(br, BROPT_MST_ENABLED)) { br_mst_vlan_init_state(v); return; } v->state = BR_STATE_FORWARDING; v->msti = 0; } /* This is the shared VLAN add function which works for both ports and bridge * devices. There are four possible calls to this function in terms of the * vlan entry type: * 1. vlan is being added on a port (no master flags, global entry exists) * 2. vlan is being added on a bridge (both master and brentry flags) * 3. vlan is being added on a port, but a global entry didn't exist which * is being created right now (master flag set, brentry flag unset), the * global entry is used for global per-vlan features, but not for filtering * 4. same as 3 but with both master and brentry flags set so the entry * will be used for filtering in both the port and the bridge */ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, struct netlink_ext_ack *extack) { struct net_bridge_vlan *masterv = NULL; struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_device *dev; struct net_bridge *br; int err; if (br_vlan_is_master(v)) { br = v->br; dev = br->dev; vg = br_vlan_group(br); } else { p = v->port; br = p->br; dev = p->dev; vg = nbp_vlan_group(p); } if (p) { /* Add VLAN to the device filter if it is supported. * This ensures tagged traffic enters the bridge when * promiscuous mode is disabled by br_manage_promisc(). */ err = __vlan_vid_add(dev, br, v, flags, extack); if (err) goto out; /* need to work on the master vlan too */ if (flags & BRIDGE_VLAN_INFO_MASTER) { bool changed; err = br_vlan_add(br, v->vid, flags | BRIDGE_VLAN_INFO_BRENTRY, &changed, extack); if (err) goto out_filt; if (changed) br_vlan_notify(br, NULL, v->vid, 0, RTM_NEWVLAN); } masterv = br_vlan_get_master(br, v->vid, extack); if (!masterv) { err = -ENOMEM; goto out_filt; } v->brvlan = masterv; if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) { v->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!v->stats) { err = -ENOMEM; goto out_filt; } v->priv_flags |= BR_VLFLAG_PER_PORT_STATS; } else { v->stats = masterv->stats; } br_multicast_port_ctx_init(p, v, &v->port_mcast_ctx); } else { if (br_vlan_should_use(v)) { err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack); if (err && err != -EOPNOTSUPP) goto out; } br_multicast_ctx_init(br, v, &v->br_mcast_ctx); v->priv_flags |= BR_VLFLAG_GLOBAL_MCAST_ENABLED; } /* Add the dev mac and count the vlan only if it's usable */ if (br_vlan_should_use(v)) { err = br_fdb_add_local(br, p, dev->dev_addr, v->vid); if (err) { br_err(br, "failed insert local address into bridge forwarding table\n"); goto out_filt; } vg->num_vlans++; } /* set the state before publishing */ br_vlan_init_state(v); err = rhashtable_lookup_insert_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); if (err) goto out_fdb_insert; __vlan_add_list(v); __vlan_flags_commit(v, flags); br_multicast_toggle_one_vlan(v, true); if (p) nbp_vlan_set_vlan_dev_state(p, v->vid); out: return err; out_fdb_insert: if (br_vlan_should_use(v)) { br_fdb_find_delete_local(br, p, dev->dev_addr, v->vid); vg->num_vlans--; } out_filt: if (p) { __vlan_vid_del(dev, br, v); if (masterv) { if (v->stats && masterv->stats != v->stats) free_percpu(v->stats); v->stats = NULL; br_vlan_put_master(masterv); v->brvlan = NULL; } } else { br_switchdev_port_vlan_del(dev, v->vid); } goto out; } static int __vlan_del(struct net_bridge_vlan *v) { struct net_bridge_vlan *masterv = v; struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; int err = 0; if (br_vlan_is_master(v)) { vg = br_vlan_group(v->br); } else { p = v->port; vg = nbp_vlan_group(v->port); masterv = v->brvlan; } __vlan_delete_pvid(vg, v->vid); if (p) { err = __vlan_vid_del(p->dev, p->br, v); if (err) goto out; } else { err = br_switchdev_port_vlan_del(v->br->dev, v->vid); if (err && err != -EOPNOTSUPP) goto out; err = 0; } if (br_vlan_should_use(v)) { v->flags &= ~BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans--; } if (masterv != v) { vlan_tunnel_info_del(vg, v); rhashtable_remove_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); __vlan_del_list(v); nbp_vlan_set_vlan_dev_state(p, v->vid); br_multicast_toggle_one_vlan(v, false); br_multicast_port_ctx_deinit(&v->port_mcast_ctx); call_rcu(&v->rcu, nbp_vlan_rcu_free); } br_vlan_put_master(masterv); out: return err; } static void __vlan_group_free(struct net_bridge_vlan_group *vg) { WARN_ON(!list_empty(&vg->vlan_list)); rhashtable_destroy(&vg->vlan_hash); vlan_tunnel_deinit(vg); kfree(vg); } static void __vlan_flush(const struct net_bridge *br, const struct net_bridge_port *p, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *vlan, *tmp; u16 v_start = 0, v_end = 0; int err; __vlan_delete_pvid(vg, vg->pvid); list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) { /* take care of disjoint ranges */ if (!v_start) { v_start = vlan->vid; } else if (vlan->vid - v_end != 1) { /* found range end, notify and start next one */ br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); v_start = vlan->vid; } v_end = vlan->vid; err = __vlan_del(vlan); if (err) { br_err(br, "port %u(%s) failed to delete vlan %d: %pe\n", (unsigned int) p->port_no, p->dev->name, vlan->vid, ERR_PTR(err)); } } /* notify about the last/whole vlan range */ if (v_start) br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); } struct sk_buff *br_handle_vlan(struct net_bridge *br, const struct net_bridge_port *p, struct net_bridge_vlan_group *vg, struct sk_buff *skb) { struct pcpu_sw_netstats *stats; struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) goto out; /* At this point, we know that the frame was filtered and contains * a valid vlan id. If the vlan id has untagged flag set, * send untagged; otherwise, send tagged. */ br_vlan_get_tag(skb, &vid); v = br_vlan_find(vg, vid); /* Vlan entry must be configured at this point. The * only exception is the bridge is set in promisc mode and the * packet is destined for the bridge device. In this case * pass the packet as is. */ if (!v || !br_vlan_should_use(v)) { if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) { goto out; } else { kfree_skb(skb); return NULL; } } if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); u64_stats_add(&stats->tx_bytes, skb->len); u64_stats_inc(&stats->tx_packets); u64_stats_update_end(&stats->syncp); } /* If the skb will be sent using forwarding offload, the assumption is * that the switchdev will inject the packet into hardware together * with the bridge VLAN, so that it can be forwarded according to that * VLAN. The switchdev should deal with popping the VLAN header in * hardware on each egress port as appropriate. So only strip the VLAN * header if forwarding offload is not being used. */ if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED && !br_switchdev_frame_uses_tx_fwd_offload(skb)) __vlan_hwaccel_clear_tag(skb); if (p && (p->flags & BR_VLAN_TUNNEL) && br_handle_egress_vlan_tunnel(skb, v)) { kfree_skb(skb); return NULL; } out: return skb; } /* Called under RCU */ static bool __allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid, u8 *state, struct net_bridge_vlan **vlan) { struct pcpu_sw_netstats *stats; struct net_bridge_vlan *v; bool tagged; BR_INPUT_SKB_CB(skb)->vlan_filtered = true; /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have * HW accelerated vlan tag. */ if (unlikely(!skb_vlan_tag_present(skb) && skb->protocol == br->vlan_proto)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) return false; } if (!br_vlan_get_tag(skb, vid)) { /* Tagged frame */ if (skb->vlan_proto != br->vlan_proto) { /* Protocol-mismatch, empty out vlan_tci for new tag */ skb_push(skb, ETH_HLEN); skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (unlikely(!skb)) return false; skb_pull(skb, ETH_HLEN); skb_reset_mac_len(skb); *vid = 0; tagged = false; } else { tagged = true; } } else { /* Untagged frame */ tagged = false; } if (!*vid) { u16 pvid = br_get_pvid(vg); /* Frame had a tag with VID 0 or did not have a tag. * See if pvid is set on this port. That tells us which * vlan untagged or priority-tagged traffic belongs to. */ if (!pvid) goto drop; /* PVID is set on this port. Any untagged or priority-tagged * ingress frame is considered to belong to this vlan. */ *vid = pvid; if (likely(!tagged)) /* Untagged Frame. */ __vlan_hwaccel_put_tag(skb, br->vlan_proto, pvid); else /* Priority-tagged Frame. * At this point, we know that skb->vlan_tci VID * field was 0. * We update only VID field and preserve PCP field. */ skb->vlan_tci |= pvid; /* if snooping and stats are disabled we can avoid the lookup */ if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) && !br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_pvid_state(vg); if (!br_vlan_state_allowed(*state, true)) goto drop; } return true; } } v = br_vlan_find(vg, *vid); if (!v || !br_vlan_should_use(v)) goto drop; if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_state(v); if (!br_vlan_state_allowed(*state, true)) goto drop; } if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); u64_stats_add(&stats->rx_bytes, skb->len); u64_stats_inc(&stats->rx_packets); u64_stats_update_end(&stats->syncp); } *vlan = v; return true; drop: kfree_skb(skb); return false; } bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid, u8 *state, struct net_bridge_vlan **vlan) { /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ *vlan = NULL; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) { BR_INPUT_SKB_CB(skb)->vlan_filtered = false; return true; } return __allowed_ingress(br, vg, skb, vid, state, vlan); } /* Called under RCU. */ bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb) { const struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) return true; br_vlan_get_tag(skb, &vid); v = br_vlan_find(vg, vid); if (v && br_vlan_should_use(v) && br_vlan_state_allowed(br_vlan_get_state(v), false)) return true; return false; } /* Called under RCU */ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) { struct net_bridge_vlan_group *vg; struct net_bridge *br = p->br; struct net_bridge_vlan *v; /* If filtering was disabled at input, let it pass. */ if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return true; vg = nbp_vlan_group_rcu(p); if (!vg || !vg->num_vlans) return false; if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto) *vid = 0; if (!*vid) { *vid = br_get_pvid(vg); if (!*vid || !br_vlan_state_allowed(br_vlan_get_pvid_state(vg), true)) return false; return true; } v = br_vlan_find(vg, *vid); if (v && br_vlan_state_allowed(br_vlan_get_state(v), true)) return true; return false; } static int br_vlan_add_existing(struct net_bridge *br, struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u16 flags, bool *changed, struct netlink_ext_ack *extack) { bool would_change = __vlan_flags_would_change(vlan, flags); bool becomes_brentry = false; int err; if (!br_vlan_is_brentry(vlan)) { /* Trying to change flags of non-existent bridge vlan */ if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) return -EINVAL; becomes_brentry = true; } /* Master VLANs that aren't brentries weren't notified before, * time to notify them now. */ if (becomes_brentry || would_change) { err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags, would_change, extack); if (err && err != -EOPNOTSUPP) return err; } if (becomes_brentry) { /* It was only kept for port vlans, now make it real */ err = br_fdb_add_local(br, NULL, br->dev->dev_addr, vlan->vid); if (err) { br_err(br, "failed to insert local address into bridge forwarding table\n"); goto err_fdb_insert; } refcount_inc(&vlan->refcnt); vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans++; *changed = true; br_multicast_toggle_one_vlan(vlan, true); } __vlan_flags_commit(vlan, flags); if (would_change) *changed = true; return 0; err_fdb_insert: br_switchdev_port_vlan_del(br->dev, vlan->vid); return err; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. * changed must be true only if the vlan was created or updated */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; int ret; ASSERT_RTNL(); *changed = false; vg = br_vlan_group(br); vlan = br_vlan_find(vg, vid); if (vlan) return br_vlan_add_existing(br, vg, vlan, flags, changed, extack); vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); if (!vlan) return -ENOMEM; vlan->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!vlan->stats) { kfree(vlan); return -ENOMEM; } vlan->vid = vid; vlan->flags = flags | BRIDGE_VLAN_INFO_MASTER; vlan->flags &= ~BRIDGE_VLAN_INFO_PVID; vlan->br = br; if (flags & BRIDGE_VLAN_INFO_BRENTRY) refcount_set(&vlan->refcnt, 1); ret = __vlan_add(vlan, flags, extack); if (ret) { free_percpu(vlan->stats); kfree(vlan); } else { *changed = true; } return ret; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int br_vlan_delete(struct net_bridge *br, u16 vid) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; ASSERT_RTNL(); vg = br_vlan_group(br); v = br_vlan_find(vg, vid); if (!v || !br_vlan_is_brentry(v)) return -ENOENT; br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); br_fdb_delete_by_port(br, NULL, vid, 0); vlan_tunnel_info_del(vg, v); return __vlan_del(v); } void br_vlan_flush(struct net_bridge *br) { struct net_bridge_vlan_group *vg; ASSERT_RTNL(); vg = br_vlan_group(br); __vlan_flush(br, NULL, vg); RCU_INIT_POINTER(br->vlgrp, NULL); synchronize_net(); __vlan_group_free(vg); } struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid) { if (!vg) return NULL; return br_vlan_lookup(&vg->vlan_hash, vid); } /* Must be protected by RTNL. */ static void recalculate_group_addr(struct net_bridge *br) { if (br_opt_get(br, BROPT_GROUP_ADDR_SET)) return; spin_lock_bh(&br->lock); if (!br_opt_get(br, BROPT_VLAN_ENABLED) || br->vlan_proto == htons(ETH_P_8021Q)) { /* Bridge Group Address */ br->group_addr[5] = 0x00; } else { /* vlan_enabled && ETH_P_8021AD */ /* Provider Bridge Group Address */ br->group_addr[5] = 0x08; } spin_unlock_bh(&br->lock); } /* Must be protected by RTNL. */ void br_recalculate_fwd_mask(struct net_bridge *br) { if (!br_opt_get(br, BROPT_VLAN_ENABLED) || br->vlan_proto == htons(ETH_P_8021Q)) br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT; else /* vlan_enabled && ETH_P_8021AD */ br->group_fwd_mask_required = BR_GROUPFWD_8021AD & ~(1u << br->group_addr[5]); } int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_filtering = val, }; int err; if (br_opt_get(br, BROPT_VLAN_ENABLED) == !!val) return 0; br_opt_toggle(br, BROPT_VLAN_ENABLED, !!val); err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) { br_opt_toggle(br, BROPT_VLAN_ENABLED, !val); return err; } br_manage_promisc(br); recalculate_group_addr(br); br_recalculate_fwd_mask(br); if (!val && br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { br_info(br, "vlan filtering disabled, automatically disabling multicast vlan snooping\n"); br_multicast_toggle_vlan_snooping(br, false, NULL); } return 0; } bool br_vlan_enabled(const struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); return br_opt_get(br, BROPT_VLAN_ENABLED); } EXPORT_SYMBOL_GPL(br_vlan_enabled); int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto) { struct net_bridge *br = netdev_priv(dev); *p_proto = ntohs(br->vlan_proto); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_proto); int __br_vlan_set_proto(struct net_bridge *br, __be16 proto, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_protocol = ntohs(proto), }; int err = 0; struct net_bridge_port *p; struct net_bridge_vlan *vlan; struct net_bridge_vlan_group *vg; __be16 oldproto = br->vlan_proto; if (br->vlan_proto == proto) return 0; err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) return err; /* Add VLANs for the new proto to the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; err = vlan_vid_add(p->dev, proto, vlan->vid); if (err) goto err_filt; } } br->vlan_proto = proto; recalculate_group_addr(br); br_recalculate_fwd_mask(br); /* Delete VLANs for the old proto from the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, oldproto, vlan->vid); } } return 0; err_filt: attr.u.vlan_protocol = ntohs(oldproto); switchdev_port_attr_set(br->dev, &attr, NULL); list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, proto, vlan->vid); } list_for_each_entry_continue_reverse(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, proto, vlan->vid); } } return err; } int br_vlan_set_proto(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { if (!eth_type_vlan(htons(val))) return -EPROTONOSUPPORT; return __br_vlan_set_proto(br, htons(val), extack); } int br_vlan_set_stats(struct net_bridge *br, unsigned long val) { switch (val) { case 0: case 1: br_opt_toggle(br, BROPT_VLAN_STATS_ENABLED, !!val); break; default: return -EINVAL; } return 0; } int br_vlan_set_stats_per_port(struct net_bridge *br, unsigned long val) { struct net_bridge_port *p; /* allow to change the option if there are no port vlans configured */ list_for_each_entry(p, &br->port_list, list) { struct net_bridge_vlan_group *vg = nbp_vlan_group(p); if (vg->num_vlans) return -EBUSY; } switch (val) { case 0: case 1: br_opt_toggle(br, BROPT_VLAN_STATS_PER_PORT, !!val); break; default: return -EINVAL; } return 0; } static bool vlan_default_pvid(struct net_bridge_vlan_group *vg, u16 vid) { struct net_bridge_vlan *v; if (vid != vg->pvid) return false; v = br_vlan_lookup(&vg->vlan_hash, vid); if (v && br_vlan_should_use(v) && (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) return true; return false; } static void br_vlan_disable_default_pvid(struct net_bridge *br) { struct net_bridge_port *p; u16 pvid = br->default_pvid; /* Disable default_pvid on all ports where it is still * configured. */ if (vlan_default_pvid(br_vlan_group(br), pvid)) { if (!br_vlan_delete(br, pvid)) br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } list_for_each_entry(p, &br->port_list, list) { if (vlan_default_pvid(nbp_vlan_group(p), pvid) && !nbp_vlan_delete(p, pvid)) br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } br->default_pvid = 0; } int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid, struct netlink_ext_ack *extack) { const struct net_bridge_vlan *pvent; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; unsigned long *changed; bool vlchange; u16 old_pvid; int err = 0; if (!pvid) { br_vlan_disable_default_pvid(br); return 0; } changed = bitmap_zalloc(BR_MAX_PORTS, GFP_KERNEL); if (!changed) return -ENOMEM; old_pvid = br->default_pvid; /* Update default_pvid config only if we do not conflict with * user configuration. */ vg = br_vlan_group(br); pvent = br_vlan_find(vg, pvid); if ((!old_pvid || vlan_default_pvid(vg, old_pvid)) && (!pvent || !br_vlan_should_use(pvent))) { err = br_vlan_add(br, pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, extack); if (err) goto out; if (br_vlan_delete(br, old_pvid)) br_vlan_notify(br, NULL, old_pvid, 0, RTM_DELVLAN); br_vlan_notify(br, NULL, pvid, 0, RTM_NEWVLAN); __set_bit(0, changed); } list_for_each_entry(p, &br->port_list, list) { /* Update default_pvid config only if we do not conflict with * user configuration. */ vg = nbp_vlan_group(p); if ((old_pvid && !vlan_default_pvid(vg, old_pvid)) || br_vlan_find(vg, pvid)) continue; err = nbp_vlan_add(p, pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, extack); if (err) goto err_port; if (nbp_vlan_delete(p, old_pvid)) br_vlan_notify(br, p, old_pvid, 0, RTM_DELVLAN); br_vlan_notify(p->br, p, pvid, 0, RTM_NEWVLAN); __set_bit(p->port_no, changed); } br->default_pvid = pvid; out: bitmap_free(changed); return err; err_port: list_for_each_entry_continue_reverse(p, &br->port_list, list) { if (!test_bit(p->port_no, changed)) continue; if (old_pvid) { nbp_vlan_add(p, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, NULL); br_vlan_notify(p->br, p, old_pvid, 0, RTM_NEWVLAN); } nbp_vlan_delete(p, pvid); br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } if (test_bit(0, changed)) { if (old_pvid) { br_vlan_add(br, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, NULL); br_vlan_notify(br, NULL, old_pvid, 0, RTM_NEWVLAN); } br_vlan_delete(br, pvid); br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } goto out; } int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { u16 pvid = val; int err = 0; if (val >= VLAN_VID_MASK) return -EINVAL; if (pvid == br->default_pvid) goto out; /* Only allow default pvid change when filtering is disabled */ if (br_opt_get(br, BROPT_VLAN_ENABLED)) { pr_info_once("Please disable vlan filtering to change default_pvid\n"); err = -EPERM; goto out; } err = __br_vlan_set_default_pvid(br, pvid, extack); out: return err; } int br_vlan_init(struct net_bridge *br) { struct net_bridge_vlan_group *vg; int ret = -ENOMEM; vg = kzalloc(sizeof(*vg), GFP_KERNEL); if (!vg) goto out; ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; ret = vlan_tunnel_init(vg); if (ret) goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; rcu_assign_pointer(br->vlgrp, vg); out: return ret; err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: kfree(vg); goto out; } int nbp_vlan_init(struct net_bridge_port *p, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = p->br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_filtering = br_opt_get(p->br, BROPT_VLAN_ENABLED), }; struct net_bridge_vlan_group *vg; int ret = -ENOMEM; vg = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL); if (!vg) goto out; ret = switchdev_port_attr_set(p->dev, &attr, extack); if (ret && ret != -EOPNOTSUPP) goto err_vlan_enabled; ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; ret = vlan_tunnel_init(vg); if (ret) goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); rcu_assign_pointer(p->vlgrp, vg); if (p->br->default_pvid) { bool changed; ret = nbp_vlan_add(p, p->br->default_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &changed, extack); if (ret) goto err_vlan_add; br_vlan_notify(p->br, p, p->br->default_pvid, 0, RTM_NEWVLAN); } out: return ret; err_vlan_add: RCU_INIT_POINTER(p->vlgrp, NULL); synchronize_rcu(); vlan_tunnel_deinit(vg); err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: err_vlan_enabled: kfree(vg); goto out; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. * changed must be true only if the vlan was created or updated */ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, bool *changed, struct netlink_ext_ack *extack) { struct net_bridge_vlan *vlan; int ret; ASSERT_RTNL(); *changed = false; vlan = br_vlan_find(nbp_vlan_group(port), vid); if (vlan) { bool would_change = __vlan_flags_would_change(vlan, flags); if (would_change) { /* Pass the flags to the hardware bridge */ ret = br_switchdev_port_vlan_add(port->dev, vid, flags, true, extack); if (ret && ret != -EOPNOTSUPP) return ret; } __vlan_flags_commit(vlan, flags); *changed = would_change; return 0; } vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); if (!vlan) return -ENOMEM; vlan->vid = vid; vlan->port = port; ret = __vlan_add(vlan, flags, extack); if (ret) kfree(vlan); else *changed = true; return ret; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) { struct net_bridge_vlan *v; ASSERT_RTNL(); v = br_vlan_find(nbp_vlan_group(port), vid); if (!v) return -ENOENT; br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); br_fdb_delete_by_port(port->br, port, vid, 0); return __vlan_del(v); } void nbp_vlan_flush(struct net_bridge_port *port) { struct net_bridge_vlan_group *vg; ASSERT_RTNL(); vg = nbp_vlan_group(port); __vlan_flush(port->br, port, vg); RCU_INIT_POINTER(port->vlgrp, NULL); synchronize_net(); __vlan_group_free(vg); } void br_vlan_get_stats(const struct net_bridge_vlan *v, struct pcpu_sw_netstats *stats) { int i; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(i) { u64 rxpackets, rxbytes, txpackets, txbytes; struct pcpu_sw_netstats *cpu_stats; unsigned int start; cpu_stats = per_cpu_ptr(v->stats, i); do { start = u64_stats_fetch_begin(&cpu_stats->syncp); rxpackets = u64_stats_read(&cpu_stats->rx_packets); rxbytes = u64_stats_read(&cpu_stats->rx_bytes); txbytes = u64_stats_read(&cpu_stats->tx_bytes); txpackets = u64_stats_read(&cpu_stats->tx_packets); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->rx_packets, rxpackets); u64_stats_add(&stats->rx_bytes, rxbytes); u64_stats_add(&stats->tx_bytes, txbytes); u64_stats_add(&stats->tx_packets, txpackets); } } int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group(netdev_priv(dev)); else return -EINVAL; *p_pvid = br_get_pvid(vg); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid); int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p; p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group_rcu(netdev_priv(dev)); else return -EINVAL; *p_pvid = br_get_pvid(vg); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu); void br_vlan_fill_forward_path_pvid(struct net_bridge *br, struct net_device_path_ctx *ctx, struct net_device_path *path) { struct net_bridge_vlan_group *vg; int idx = ctx->num_vlans - 1; u16 vid; path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return; vg = br_vlan_group(br); if (idx >= 0 && ctx->vlan[idx].proto == br->vlan_proto) { vid = ctx->vlan[idx].id; } else { path->bridge.vlan_mode = DEV_PATH_BR_VLAN_TAG; vid = br_get_pvid(vg); } path->bridge.vlan_id = vid; path->bridge.vlan_proto = br->vlan_proto; } int br_vlan_fill_forward_path_mode(struct net_bridge *br, struct net_bridge_port *dst, struct net_device_path *path) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return 0; vg = nbp_vlan_group_rcu(dst); v = br_vlan_find(vg, path->bridge.vlan_id); if (!v || !br_vlan_should_use(v)) return -EINVAL; if (!(v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) return 0; if (path->bridge.vlan_mode == DEV_PATH_BR_VLAN_TAG) path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; else if (v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG_HW; else path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG; return 0; } int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group(netdev_priv(dev)); else return -EINVAL; v = br_vlan_find(vg, vid); if (!v) return -ENOENT; p_vinfo->vid = vid; p_vinfo->flags = v->flags; if (vid == br_get_pvid(vg)) p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_info); int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group_rcu(netdev_priv(dev)); else return -EINVAL; v = br_vlan_find(vg, vid); if (!v) return -ENOENT; p_vinfo->vid = vid; p_vinfo->flags = v->flags; if (vid == br_get_pvid(vg)) p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_info_rcu); static int br_vlan_is_bind_vlan_dev(const struct net_device *dev) { return is_vlan_dev(dev) && !!(vlan_dev_priv(dev)->flags & VLAN_FLAG_BRIDGE_BINDING); } static int br_vlan_is_bind_vlan_dev_fn(struct net_device *dev, __always_unused struct netdev_nested_priv *priv) { return br_vlan_is_bind_vlan_dev(dev); } static bool br_vlan_has_upper_bind_vlan_dev(struct net_device *dev) { int found; rcu_read_lock(); found = netdev_walk_all_upper_dev_rcu(dev, br_vlan_is_bind_vlan_dev_fn, NULL); rcu_read_unlock(); return !!found; } struct br_vlan_bind_walk_data { u16 vid; struct net_device *result; }; static int br_vlan_match_bind_vlan_dev_fn(struct net_device *dev, struct netdev_nested_priv *priv) { struct br_vlan_bind_walk_data *data = priv->data; int found = 0; if (br_vlan_is_bind_vlan_dev(dev) && vlan_dev_priv(dev)->vlan_id == data->vid) { data->result = dev; found = 1; } return found; } static struct net_device * br_vlan_get_upper_bind_vlan_dev(struct net_device *dev, u16 vid) { struct br_vlan_bind_walk_data data = { .vid = vid, }; struct netdev_nested_priv priv = { .data = (void *)&data, }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_match_bind_vlan_dev_fn, &priv); rcu_read_unlock(); return data.result; } static bool br_vlan_is_dev_up(const struct net_device *dev) { return !!(dev->flags & IFF_UP) && netif_oper_up(dev); } static void br_vlan_set_vlan_dev_state(const struct net_bridge *br, struct net_device *vlan_dev) { u16 vid = vlan_dev_priv(vlan_dev)->vlan_id; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; bool has_carrier = false; if (!netif_carrier_ok(br->dev)) { netif_carrier_off(vlan_dev); return; } list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); if (br_vlan_find(vg, vid) && br_vlan_is_dev_up(p->dev)) { has_carrier = true; break; } } if (has_carrier) netif_carrier_on(vlan_dev); else netif_carrier_off(vlan_dev); } static void br_vlan_set_all_vlan_dev_state(struct net_bridge_port *p) { struct net_bridge_vlan_group *vg = nbp_vlan_group(p); struct net_bridge_vlan *vlan; struct net_device *vlan_dev; list_for_each_entry(vlan, &vg->vlan_list, vlist) { vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev, vlan->vid); if (vlan_dev) { if (br_vlan_is_dev_up(p->dev)) { if (netif_carrier_ok(p->br->dev)) netif_carrier_on(vlan_dev); } else { br_vlan_set_vlan_dev_state(p->br, vlan_dev); } } } } static void br_vlan_upper_change(struct net_device *dev, struct net_device *upper_dev, bool linking) { struct net_bridge *br = netdev_priv(dev); if (!br_vlan_is_bind_vlan_dev(upper_dev)) return; if (linking) { br_vlan_set_vlan_dev_state(br, upper_dev); br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, true); } else { br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, br_vlan_has_upper_bind_vlan_dev(dev)); } } struct br_vlan_link_state_walk_data { struct net_bridge *br; }; static int br_vlan_link_state_change_fn(struct net_device *vlan_dev, struct netdev_nested_priv *priv) { struct br_vlan_link_state_walk_data *data = priv->data; if (br_vlan_is_bind_vlan_dev(vlan_dev)) br_vlan_set_vlan_dev_state(data->br, vlan_dev); return 0; } static void br_vlan_link_state_change(struct net_device *dev, struct net_bridge *br) { struct br_vlan_link_state_walk_data data = { .br = br }; struct netdev_nested_priv priv = { .data = (void *)&data, }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_link_state_change_fn, &priv); rcu_read_unlock(); } /* Must be protected by RTNL. */ static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid) { struct net_device *vlan_dev; if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING)) return; vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev, vid); if (vlan_dev) br_vlan_set_vlan_dev_state(p->br, vlan_dev); } /* Must be protected by RTNL. */ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_changeupper_info *info; struct net_bridge *br = netdev_priv(dev); int vlcmd = 0, ret = 0; bool changed = false; switch (event) { case NETDEV_REGISTER: ret = br_vlan_add(br, br->default_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); vlcmd = RTM_NEWVLAN; break; case NETDEV_UNREGISTER: changed = !br_vlan_delete(br, br->default_pvid); vlcmd = RTM_DELVLAN; break; case NETDEV_CHANGEUPPER: info = ptr; br_vlan_upper_change(dev, info->upper_dev, info->linking); break; case NETDEV_CHANGE: case NETDEV_UP: if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING)) break; br_vlan_link_state_change(dev, br); break; } if (changed) br_vlan_notify(br, NULL, br->default_pvid, 0, vlcmd); return ret; } /* Must be protected by RTNL. */ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event) { if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING)) return; switch (event) { case NETDEV_CHANGE: case NETDEV_DOWN: case NETDEV_UP: br_vlan_set_all_vlan_dev_state(p); break; } } static bool br_vlan_stats_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) { struct pcpu_sw_netstats stats; struct nlattr *nest; nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY_STATS); if (!nest) return false; br_vlan_get_stats(v, &stats); if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_BYTES, u64_stats_read(&stats.rx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_PACKETS, u64_stats_read(&stats.rx_packets), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_BYTES, u64_stats_read(&stats.tx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_PACKETS, u64_stats_read(&stats.tx_packets), BRIDGE_VLANDB_STATS_PAD)) goto out_err; nla_nest_end(skb, nest); return true; out_err: nla_nest_cancel(skb, nest); return false; } /* v_opts is used to dump the options which must be equal in the whole range */ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, const struct net_bridge_vlan *v_opts, const struct net_bridge_port *p, u16 flags, bool dump_stats) { struct bridge_vlan_info info; struct nlattr *nest; nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY); if (!nest) return false; memset(&info, 0, sizeof(info)); info.vid = vid; if (flags & BRIDGE_VLAN_INFO_UNTAGGED) info.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (flags & BRIDGE_VLAN_INFO_PVID) info.flags |= BRIDGE_VLAN_INFO_PVID; if (nla_put(skb, BRIDGE_VLANDB_ENTRY_INFO, sizeof(info), &info)) goto out_err; if (vid_range && vid < vid_range && !(flags & BRIDGE_VLAN_INFO_PVID) && nla_put_u16(skb, BRIDGE_VLANDB_ENTRY_RANGE, vid_range)) goto out_err; if (v_opts) { if (!br_vlan_opts_fill(skb, v_opts, p)) goto out_err; if (dump_stats && !br_vlan_stats_fill(skb, v_opts)) goto out_err; } nla_nest_end(skb, nest); return true; out_err: nla_nest_cancel(skb, nest); return false; } static size_t rtnl_vlan_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct br_vlan_msg)) + nla_total_size(0) /* BRIDGE_VLANDB_ENTRY */ + nla_total_size(sizeof(u16)) /* BRIDGE_VLANDB_ENTRY_RANGE */ + nla_total_size(sizeof(struct bridge_vlan_info)) /* BRIDGE_VLANDB_ENTRY_INFO */ + br_vlan_opts_nl_size(); /* bridge vlan options */ } void br_vlan_notify(const struct net_bridge *br, const struct net_bridge_port *p, u16 vid, u16 vid_range, int cmd) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v = NULL; struct br_vlan_msg *bvm; struct nlmsghdr *nlh; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; u16 flags = 0; int ifindex; /* right now notifications are done only with rtnl held */ ASSERT_RTNL(); if (p) { ifindex = p->dev->ifindex; vg = nbp_vlan_group(p); net = dev_net(p->dev); } else { ifindex = br->dev->ifindex; vg = br_vlan_group(br); net = dev_net(br->dev); } skb = nlmsg_new(rtnl_vlan_nlmsg_size(), GFP_KERNEL); if (!skb) goto out_err; err = -EMSGSIZE; nlh = nlmsg_put(skb, 0, 0, cmd, sizeof(*bvm), 0); if (!nlh) goto out_err; bvm = nlmsg_data(nlh); memset(bvm, 0, sizeof(*bvm)); bvm->family = AF_BRIDGE; bvm->ifindex = ifindex; switch (cmd) { case RTM_NEWVLAN: /* need to find the vlan due to flags/options */ v = br_vlan_find(vg, vid); if (!v || !br_vlan_should_use(v)) goto out_kfree; flags = v->flags; if (br_get_pvid(vg) == v->vid) flags |= BRIDGE_VLAN_INFO_PVID; break; case RTM_DELVLAN: break; default: goto out_kfree; } if (!br_vlan_fill_vids(skb, vid, vid_range, v, p, flags, false)) goto out_err; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_BRVLAN, NULL, GFP_KERNEL); return; out_err: rtnl_set_sk_err(net, RTNLGRP_BRVLAN, err); out_kfree: kfree_skb(skb); } /* check if v_curr can enter a range ending in range_end */ bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end) { return v_curr->vid - range_end->vid == 1 && range_end->flags == v_curr->flags && br_vlan_opts_eq_range(v_curr, range_end); } static int br_vlan_dump_dev(const struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb, u32 dump_flags) { struct net_bridge_vlan *v, *range_start = NULL, *range_end = NULL; bool dump_global = !!(dump_flags & BRIDGE_VLANDB_DUMPF_GLOBAL); bool dump_stats = !!(dump_flags & BRIDGE_VLANDB_DUMPF_STATS); struct net_bridge_vlan_group *vg; int idx = 0, s_idx = cb->args[1]; struct nlmsghdr *nlh = NULL; struct net_bridge_port *p; struct br_vlan_msg *bvm; struct net_bridge *br; int err = 0; u16 pvid; if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) return -EINVAL; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); p = NULL; } else { /* global options are dumped only for bridge devices */ if (dump_global) return 0; p = br_port_get_rcu(dev); if (WARN_ON(!p)) return -EINVAL; vg = nbp_vlan_group_rcu(p); br = p->br; } if (!vg) return 0; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWVLAN, sizeof(*bvm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; bvm = nlmsg_data(nlh); memset(bvm, 0, sizeof(*bvm)); bvm->family = PF_BRIDGE; bvm->ifindex = dev->ifindex; pvid = br_get_pvid(vg); /* idx must stay at range's beginning until it is filled in */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!dump_global && !br_vlan_should_use(v)) continue; if (idx < s_idx) { idx++; continue; } if (!range_start) { range_start = v; range_end = v; continue; } if (dump_global) { if (br_vlan_global_opts_can_enter_range(v, range_end)) goto update_end; if (!br_vlan_global_opts_fill(skb, range_start->vid, range_end->vid, range_start)) { err = -EMSGSIZE; break; } /* advance number of filled vlans */ idx += range_end->vid - range_start->vid + 1; range_start = v; } else if (dump_stats || v->vid == pvid || !br_vlan_can_enter_range(v, range_end)) { u16 vlan_flags = br_vlan_flags(range_start, pvid); if (!br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, p, vlan_flags, dump_stats)) { err = -EMSGSIZE; break; } /* advance number of filled vlans */ idx += range_end->vid - range_start->vid + 1; range_start = v; } update_end: range_end = v; } /* err will be 0 and range_start will be set in 3 cases here: * - first vlan (range_start == range_end) * - last vlan (range_start == range_end, not in range) * - last vlan range (range_start != range_end, in range) */ if (!err && range_start) { if (dump_global && !br_vlan_global_opts_fill(skb, range_start->vid, range_end->vid, range_start)) err = -EMSGSIZE; else if (!dump_global && !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, p, br_vlan_flags(range_start, pvid), dump_stats)) err = -EMSGSIZE; } cb->args[1] = err ? idx : 0; nlmsg_end(skb, nlh); return err; } static const struct nla_policy br_vlan_db_dump_pol[BRIDGE_VLANDB_DUMP_MAX + 1] = { [BRIDGE_VLANDB_DUMP_FLAGS] = { .type = NLA_U32 }, }; static int br_vlan_rtm_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *dtb[BRIDGE_VLANDB_DUMP_MAX + 1]; int idx = 0, err = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); struct br_vlan_msg *bvm; struct net_device *dev; u32 dump_flags = 0; err = nlmsg_parse(cb->nlh, sizeof(*bvm), dtb, BRIDGE_VLANDB_DUMP_MAX, br_vlan_db_dump_pol, cb->extack); if (err < 0) return err; bvm = nlmsg_data(cb->nlh); if (dtb[BRIDGE_VLANDB_DUMP_FLAGS]) dump_flags = nla_get_u32(dtb[BRIDGE_VLANDB_DUMP_FLAGS]); rcu_read_lock(); if (bvm->ifindex) { dev = dev_get_by_index_rcu(net, bvm->ifindex); if (!dev) { err = -ENODEV; goto out_err; } err = br_vlan_dump_dev(dev, skb, cb, dump_flags); /* if the dump completed without an error we return 0 here */ if (err != -EMSGSIZE) goto out_err; } else { for_each_netdev_rcu(net, dev) { if (idx < s_idx) goto skip; err = br_vlan_dump_dev(dev, skb, cb, dump_flags); if (err == -EMSGSIZE) break; skip: idx++; } } cb->args[0] = idx; rcu_read_unlock(); return skb->len; out_err: rcu_read_unlock(); return err; } static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = { [BRIDGE_VLANDB_ENTRY_INFO] = NLA_POLICY_EXACT_LEN(sizeof(struct bridge_vlan_info)), [BRIDGE_VLANDB_ENTRY_RANGE] = { .type = NLA_U16 }, [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, [BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS] = { .type = NLA_REJECT }, [BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, [BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1), }; static int br_vlan_rtm_process_one(struct net_device *dev, const struct nlattr *attr, int cmd, struct netlink_ext_ack *extack) { struct bridge_vlan_info *vinfo, vrange_end, *vinfo_last = NULL; struct nlattr *tb[BRIDGE_VLANDB_ENTRY_MAX + 1]; bool changed = false, skip_processing = false; struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; int err = 0, cmdmap = 0; struct net_bridge *br; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group(br); } else { p = br_port_get_rtnl(dev); if (WARN_ON(!p)) return -ENODEV; br = p->br; vg = nbp_vlan_group(p); } if (WARN_ON(!vg)) return -ENODEV; err = nla_parse_nested(tb, BRIDGE_VLANDB_ENTRY_MAX, attr, br_vlan_db_policy, extack); if (err) return err; if (!tb[BRIDGE_VLANDB_ENTRY_INFO]) { NL_SET_ERR_MSG_MOD(extack, "Missing vlan entry info"); return -EINVAL; } memset(&vrange_end, 0, sizeof(vrange_end)); vinfo = nla_data(tb[BRIDGE_VLANDB_ENTRY_INFO]); if (vinfo->flags & (BRIDGE_VLAN_INFO_RANGE_BEGIN | BRIDGE_VLAN_INFO_RANGE_END)) { NL_SET_ERR_MSG_MOD(extack, "Old-style vlan ranges are not allowed when using RTM vlan calls"); return -EINVAL; } if (!br_vlan_valid_id(vinfo->vid, extack)) return -EINVAL; if (tb[BRIDGE_VLANDB_ENTRY_RANGE]) { vrange_end.vid = nla_get_u16(tb[BRIDGE_VLANDB_ENTRY_RANGE]); /* validate user-provided flags without RANGE_BEGIN */ vrange_end.flags = BRIDGE_VLAN_INFO_RANGE_END | vinfo->flags; vinfo->flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN; /* vinfo_last is the range start, vinfo the range end */ vinfo_last = vinfo; vinfo = &vrange_end; if (!br_vlan_valid_id(vinfo->vid, extack) || !br_vlan_valid_range(vinfo, vinfo_last, extack)) return -EINVAL; } switch (cmd) { case RTM_NEWVLAN: cmdmap = RTM_SETLINK; skip_processing = !!(vinfo->flags & BRIDGE_VLAN_INFO_ONLY_OPTS); break; case RTM_DELVLAN: cmdmap = RTM_DELLINK; break; } if (!skip_processing) { struct bridge_vlan_info *tmp_last = vinfo_last; /* br_process_vlan_info may overwrite vinfo_last */ err = br_process_vlan_info(br, p, cmdmap, vinfo, &tmp_last, &changed, extack); /* notify first if anything changed */ if (changed) br_ifinfo_notify(cmdmap, br, p); if (err) return err; } /* deal with options */ if (cmd == RTM_NEWVLAN) { struct net_bridge_vlan *range_start, *range_end; if (vinfo_last) { range_start = br_vlan_find(vg, vinfo_last->vid); range_end = br_vlan_find(vg, vinfo->vid); } else { range_start = br_vlan_find(vg, vinfo->vid); range_end = range_start; } err = br_vlan_process_options(br, p, range_start, range_end, tb, extack); } return err; } static int br_vlan_rtm_process(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct br_vlan_msg *bvm; struct net_device *dev; struct nlattr *attr; int err, vlans = 0; int rem; /* this should validate the header and check for remaining bytes */ err = nlmsg_parse(nlh, sizeof(*bvm), NULL, BRIDGE_VLANDB_MAX, NULL, extack); if (err < 0) return err; bvm = nlmsg_data(nlh); dev = __dev_get_by_index(net, bvm->ifindex); if (!dev) return -ENODEV; if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) { NL_SET_ERR_MSG_MOD(extack, "The device is not a valid bridge or bridge port"); return -EINVAL; } nlmsg_for_each_attr(attr, nlh, sizeof(*bvm), rem) { switch (nla_type(attr)) { case BRIDGE_VLANDB_ENTRY: err = br_vlan_rtm_process_one(dev, attr, nlh->nlmsg_type, extack); break; case BRIDGE_VLANDB_GLOBAL_OPTIONS: err = br_vlan_rtm_process_global_options(dev, attr, nlh->nlmsg_type, extack); break; default: continue; } vlans++; if (err) break; } if (!vlans) { NL_SET_ERR_MSG_MOD(extack, "No vlans found to process"); err = -EINVAL; } return err; } void br_vlan_rtnl_init(void) { rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_GETVLAN, NULL, br_vlan_rtm_dump, 0); rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_NEWVLAN, br_vlan_rtm_process, NULL, 0); rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_DELVLAN, br_vlan_rtm_process, NULL, 0); } void br_vlan_rtnl_uninit(void) { rtnl_unregister(PF_BRIDGE, RTM_GETVLAN); rtnl_unregister(PF_BRIDGE, RTM_NEWVLAN); rtnl_unregister(PF_BRIDGE, RTM_DELVLAN); } |
| 270 9 11 8 494 1728 1173 1730 107 217 216 11 10 4 60 4934 4920 4991 4989 58 60 | 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 | // SPDX-License-Identifier: GPL-2.0 // Generated by scripts/atomic/gen-atomic-fallback.sh // DO NOT MODIFY THIS FILE DIRECTLY #ifndef _LINUX_ATOMIC_FALLBACK_H #define _LINUX_ATOMIC_FALLBACK_H #include <linux/compiler.h> #if defined(arch_xchg) #define raw_xchg arch_xchg #elif defined(arch_xchg_relaxed) #define raw_xchg(...) \ __atomic_op_fence(arch_xchg, __VA_ARGS__) #else extern void raw_xchg_not_implemented(void); #define raw_xchg(...) raw_xchg_not_implemented() #endif #if defined(arch_xchg_acquire) #define raw_xchg_acquire arch_xchg_acquire #elif defined(arch_xchg_relaxed) #define raw_xchg_acquire(...) \ __atomic_op_acquire(arch_xchg, __VA_ARGS__) #elif defined(arch_xchg) #define raw_xchg_acquire arch_xchg #else extern void raw_xchg_acquire_not_implemented(void); #define raw_xchg_acquire(...) raw_xchg_acquire_not_implemented() #endif #if defined(arch_xchg_release) #define raw_xchg_release arch_xchg_release #elif defined(arch_xchg_relaxed) #define raw_xchg_release(...) \ __atomic_op_release(arch_xchg, __VA_ARGS__) #elif defined(arch_xchg) #define raw_xchg_release arch_xchg #else extern void raw_xchg_release_not_implemented(void); #define raw_xchg_release(...) raw_xchg_release_not_implemented() #endif #if defined(arch_xchg_relaxed) #define raw_xchg_relaxed arch_xchg_relaxed #elif defined(arch_xchg) #define raw_xchg_relaxed arch_xchg #else extern void raw_xchg_relaxed_not_implemented(void); #define raw_xchg_relaxed(...) raw_xchg_relaxed_not_implemented() #endif #if defined(arch_cmpxchg) #define raw_cmpxchg arch_cmpxchg #elif defined(arch_cmpxchg_relaxed) #define raw_cmpxchg(...) \ __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) #else extern void raw_cmpxchg_not_implemented(void); #define raw_cmpxchg(...) raw_cmpxchg_not_implemented() #endif #if defined(arch_cmpxchg_acquire) #define raw_cmpxchg_acquire arch_cmpxchg_acquire #elif defined(arch_cmpxchg_relaxed) #define raw_cmpxchg_acquire(...) \ __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) #elif defined(arch_cmpxchg) #define raw_cmpxchg_acquire arch_cmpxchg #else extern void raw_cmpxchg_acquire_not_implemented(void); #define raw_cmpxchg_acquire(...) raw_cmpxchg_acquire_not_implemented() #endif #if defined(arch_cmpxchg_release) #define raw_cmpxchg_release arch_cmpxchg_release #elif defined(arch_cmpxchg_relaxed) #define raw_cmpxchg_release(...) \ __atomic_op_release(arch_cmpxchg, __VA_ARGS__) #elif defined(arch_cmpxchg) #define raw_cmpxchg_release arch_cmpxchg #else extern void raw_cmpxchg_release_not_implemented(void); #define raw_cmpxchg_release(...) raw_cmpxchg_release_not_implemented() #endif #if defined(arch_cmpxchg_relaxed) #define raw_cmpxchg_relaxed arch_cmpxchg_relaxed #elif defined(arch_cmpxchg) #define raw_cmpxchg_relaxed arch_cmpxchg #else extern void raw_cmpxchg_relaxed_not_implemented(void); #define raw_cmpxchg_relaxed(...) raw_cmpxchg_relaxed_not_implemented() #endif #if defined(arch_cmpxchg64) #define raw_cmpxchg64 arch_cmpxchg64 #elif defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64(...) \ __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) #else extern void raw_cmpxchg64_not_implemented(void); #define raw_cmpxchg64(...) raw_cmpxchg64_not_implemented() #endif #if defined(arch_cmpxchg64_acquire) #define raw_cmpxchg64_acquire arch_cmpxchg64_acquire #elif defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64_acquire(...) \ __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) #elif defined(arch_cmpxchg64) #define raw_cmpxchg64_acquire arch_cmpxchg64 #else extern void raw_cmpxchg64_acquire_not_implemented(void); #define raw_cmpxchg64_acquire(...) raw_cmpxchg64_acquire_not_implemented() #endif #if defined(arch_cmpxchg64_release) #define raw_cmpxchg64_release arch_cmpxchg64_release #elif defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64_release(...) \ __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) #elif defined(arch_cmpxchg64) #define raw_cmpxchg64_release arch_cmpxchg64 #else extern void raw_cmpxchg64_release_not_implemented(void); #define raw_cmpxchg64_release(...) raw_cmpxchg64_release_not_implemented() #endif #if defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64_relaxed arch_cmpxchg64_relaxed #elif defined(arch_cmpxchg64) #define raw_cmpxchg64_relaxed arch_cmpxchg64 #else extern void raw_cmpxchg64_relaxed_not_implemented(void); #define raw_cmpxchg64_relaxed(...) raw_cmpxchg64_relaxed_not_implemented() #endif #if defined(arch_cmpxchg128) #define raw_cmpxchg128 arch_cmpxchg128 #elif defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128(...) \ __atomic_op_fence(arch_cmpxchg128, __VA_ARGS__) #else extern void raw_cmpxchg128_not_implemented(void); #define raw_cmpxchg128(...) raw_cmpxchg128_not_implemented() #endif #if defined(arch_cmpxchg128_acquire) #define raw_cmpxchg128_acquire arch_cmpxchg128_acquire #elif defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128_acquire(...) \ __atomic_op_acquire(arch_cmpxchg128, __VA_ARGS__) #elif defined(arch_cmpxchg128) #define raw_cmpxchg128_acquire arch_cmpxchg128 #else extern void raw_cmpxchg128_acquire_not_implemented(void); #define raw_cmpxchg128_acquire(...) raw_cmpxchg128_acquire_not_implemented() #endif #if defined(arch_cmpxchg128_release) #define raw_cmpxchg128_release arch_cmpxchg128_release #elif defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128_release(...) \ __atomic_op_release(arch_cmpxchg128, __VA_ARGS__) #elif defined(arch_cmpxchg128) #define raw_cmpxchg128_release arch_cmpxchg128 #else extern void raw_cmpxchg128_release_not_implemented(void); #define raw_cmpxchg128_release(...) raw_cmpxchg128_release_not_implemented() #endif #if defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128_relaxed arch_cmpxchg128_relaxed #elif defined(arch_cmpxchg128) #define raw_cmpxchg128_relaxed arch_cmpxchg128 #else extern void raw_cmpxchg128_relaxed_not_implemented(void); #define raw_cmpxchg128_relaxed(...) raw_cmpxchg128_relaxed_not_implemented() #endif #if defined(arch_try_cmpxchg) #define raw_try_cmpxchg arch_try_cmpxchg #elif defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg(...) \ __atomic_op_fence(arch_try_cmpxchg, __VA_ARGS__) #else #define raw_try_cmpxchg(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg_acquire) #define raw_try_cmpxchg_acquire arch_try_cmpxchg_acquire #elif defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg_acquire(...) \ __atomic_op_acquire(arch_try_cmpxchg, __VA_ARGS__) #elif defined(arch_try_cmpxchg) #define raw_try_cmpxchg_acquire arch_try_cmpxchg #else #define raw_try_cmpxchg_acquire(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_acquire((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg_release) #define raw_try_cmpxchg_release arch_try_cmpxchg_release #elif defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg_release(...) \ __atomic_op_release(arch_try_cmpxchg, __VA_ARGS__) #elif defined(arch_try_cmpxchg) #define raw_try_cmpxchg_release arch_try_cmpxchg #else #define raw_try_cmpxchg_release(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_release((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg_relaxed arch_try_cmpxchg_relaxed #elif defined(arch_try_cmpxchg) #define raw_try_cmpxchg_relaxed arch_try_cmpxchg #else #define raw_try_cmpxchg_relaxed(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_relaxed((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64 arch_try_cmpxchg64 #elif defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64(...) \ __atomic_op_fence(arch_try_cmpxchg64, __VA_ARGS__) #else #define raw_try_cmpxchg64(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64_acquire) #define raw_try_cmpxchg64_acquire arch_try_cmpxchg64_acquire #elif defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64_acquire(...) \ __atomic_op_acquire(arch_try_cmpxchg64, __VA_ARGS__) #elif defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64_acquire arch_try_cmpxchg64 #else #define raw_try_cmpxchg64_acquire(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_acquire((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64_release) #define raw_try_cmpxchg64_release arch_try_cmpxchg64_release #elif defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64_release(...) \ __atomic_op_release(arch_try_cmpxchg64, __VA_ARGS__) #elif defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64_release arch_try_cmpxchg64 #else #define raw_try_cmpxchg64_release(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_release((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64_relaxed arch_try_cmpxchg64_relaxed #elif defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64_relaxed arch_try_cmpxchg64 #else #define raw_try_cmpxchg64_relaxed(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_relaxed((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128 arch_try_cmpxchg128 #elif defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128(...) \ __atomic_op_fence(arch_try_cmpxchg128, __VA_ARGS__) #else #define raw_try_cmpxchg128(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128_acquire) #define raw_try_cmpxchg128_acquire arch_try_cmpxchg128_acquire #elif defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128_acquire(...) \ __atomic_op_acquire(arch_try_cmpxchg128, __VA_ARGS__) #elif defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128_acquire arch_try_cmpxchg128 #else #define raw_try_cmpxchg128_acquire(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_acquire((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128_release) #define raw_try_cmpxchg128_release arch_try_cmpxchg128_release #elif defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128_release(...) \ __atomic_op_release(arch_try_cmpxchg128, __VA_ARGS__) #elif defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128_release arch_try_cmpxchg128 #else #define raw_try_cmpxchg128_release(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_release((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128_relaxed arch_try_cmpxchg128_relaxed #elif defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128_relaxed arch_try_cmpxchg128 #else #define raw_try_cmpxchg128_relaxed(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_relaxed((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_cmpxchg_local arch_cmpxchg_local #ifdef arch_try_cmpxchg_local #define raw_try_cmpxchg_local arch_try_cmpxchg_local #else #define raw_try_cmpxchg_local(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_local((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_cmpxchg64_local arch_cmpxchg64_local #ifdef arch_try_cmpxchg64_local #define raw_try_cmpxchg64_local arch_try_cmpxchg64_local #else #define raw_try_cmpxchg64_local(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_local((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_cmpxchg128_local arch_cmpxchg128_local #ifdef arch_try_cmpxchg128_local #define raw_try_cmpxchg128_local arch_try_cmpxchg128_local #else #define raw_try_cmpxchg128_local(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_local((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_sync_cmpxchg arch_sync_cmpxchg #ifdef arch_sync_try_cmpxchg #define raw_sync_try_cmpxchg arch_sync_try_cmpxchg #else #define raw_sync_try_cmpxchg(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_sync_cmpxchg((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif /** * raw_atomic_read() - atomic load with relaxed ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_read() elsewhere. * * Return: The value loaded from @v. */ static __always_inline int raw_atomic_read(const atomic_t *v) { return arch_atomic_read(v); } /** * raw_atomic_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with acquire ordering. * * Safe to use in noinstr code; prefer atomic_read_acquire() elsewhere. * * Return: The value loaded from @v. */ static __always_inline int raw_atomic_read_acquire(const atomic_t *v) { #if defined(arch_atomic_read_acquire) return arch_atomic_read_acquire(v); #else int ret; if (__native_word(atomic_t)) { ret = smp_load_acquire(&(v)->counter); } else { ret = raw_atomic_read(v); __atomic_acquire_fence(); } return ret; #endif } /** * raw_atomic_set() - atomic set with relaxed ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_set() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_set(atomic_t *v, int i) { arch_atomic_set(v, i); } /** * raw_atomic_set_release() - atomic set with release ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with release ordering. * * Safe to use in noinstr code; prefer atomic_set_release() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_set_release(atomic_t *v, int i) { #if defined(arch_atomic_set_release) arch_atomic_set_release(v, i); #else if (__native_word(atomic_t)) { smp_store_release(&(v)->counter, i); } else { __atomic_release_fence(); raw_atomic_set(v, i); } #endif } /** * raw_atomic_add() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_add() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_add(int i, atomic_t *v) { arch_atomic_add(i, v); } /** * raw_atomic_add_return() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_add_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return(int i, atomic_t *v) { #if defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #elif defined(arch_atomic_add_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_add_return" #endif } /** * raw_atomic_add_return_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_add_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return_acquire(int i, atomic_t *v) { #if defined(arch_atomic_add_return_acquire) return arch_atomic_add_return_acquire(i, v); #elif defined(arch_atomic_add_return_relaxed) int ret = arch_atomic_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #else #error "Unable to define raw_atomic_add_return_acquire" #endif } /** * raw_atomic_add_return_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_add_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return_release(int i, atomic_t *v) { #if defined(arch_atomic_add_return_release) return arch_atomic_add_return_release(i, v); #elif defined(arch_atomic_add_return_relaxed) __atomic_release_fence(); return arch_atomic_add_return_relaxed(i, v); #elif defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #else #error "Unable to define raw_atomic_add_return_release" #endif } /** * raw_atomic_add_return_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_add_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_add_return_relaxed) return arch_atomic_add_return_relaxed(i, v); #elif defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #else #error "Unable to define raw_atomic_add_return_relaxed" #endif } /** * raw_atomic_fetch_add() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #elif defined(arch_atomic_fetch_add_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_add" #endif } /** * raw_atomic_fetch_add_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add_acquire) return arch_atomic_fetch_add_acquire(i, v); #elif defined(arch_atomic_fetch_add_relaxed) int ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #else #error "Unable to define raw_atomic_fetch_add_acquire" #endif } /** * raw_atomic_fetch_add_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add_release) return arch_atomic_fetch_add_release(i, v); #elif defined(arch_atomic_fetch_add_relaxed) __atomic_release_fence(); return arch_atomic_fetch_add_relaxed(i, v); #elif defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #else #error "Unable to define raw_atomic_fetch_add_release" #endif } /** * raw_atomic_fetch_add_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add_relaxed) return arch_atomic_fetch_add_relaxed(i, v); #elif defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #else #error "Unable to define raw_atomic_fetch_add_relaxed" #endif } /** * raw_atomic_sub() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_sub() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_sub(int i, atomic_t *v) { arch_atomic_sub(i, v); } /** * raw_atomic_sub_return() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_sub_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return(int i, atomic_t *v) { #if defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #elif defined(arch_atomic_sub_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_sub_return" #endif } /** * raw_atomic_sub_return_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_sub_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return_acquire(int i, atomic_t *v) { #if defined(arch_atomic_sub_return_acquire) return arch_atomic_sub_return_acquire(i, v); #elif defined(arch_atomic_sub_return_relaxed) int ret = arch_atomic_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #else #error "Unable to define raw_atomic_sub_return_acquire" #endif } /** * raw_atomic_sub_return_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_sub_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return_release(int i, atomic_t *v) { #if defined(arch_atomic_sub_return_release) return arch_atomic_sub_return_release(i, v); #elif defined(arch_atomic_sub_return_relaxed) __atomic_release_fence(); return arch_atomic_sub_return_relaxed(i, v); #elif defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #else #error "Unable to define raw_atomic_sub_return_release" #endif } /** * raw_atomic_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_sub_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_sub_return_relaxed) return arch_atomic_sub_return_relaxed(i, v); #elif defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #else #error "Unable to define raw_atomic_sub_return_relaxed" #endif } /** * raw_atomic_fetch_sub() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #elif defined(arch_atomic_fetch_sub_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_sub" #endif } /** * raw_atomic_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub_acquire) return arch_atomic_fetch_sub_acquire(i, v); #elif defined(arch_atomic_fetch_sub_relaxed) int ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #else #error "Unable to define raw_atomic_fetch_sub_acquire" #endif } /** * raw_atomic_fetch_sub_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub_release) return arch_atomic_fetch_sub_release(i, v); #elif defined(arch_atomic_fetch_sub_relaxed) __atomic_release_fence(); return arch_atomic_fetch_sub_relaxed(i, v); #elif defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #else #error "Unable to define raw_atomic_fetch_sub_release" #endif } /** * raw_atomic_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub_relaxed) return arch_atomic_fetch_sub_relaxed(i, v); #elif defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #else #error "Unable to define raw_atomic_fetch_sub_relaxed" #endif } /** * raw_atomic_inc() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_inc() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_inc(atomic_t *v) { #if defined(arch_atomic_inc) arch_atomic_inc(v); #else raw_atomic_add(1, v); #endif } /** * raw_atomic_inc_return() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_inc_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return(atomic_t *v) { #if defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #elif defined(arch_atomic_inc_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_add_return(1, v); #endif } /** * raw_atomic_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_inc_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return_acquire(atomic_t *v) { #if defined(arch_atomic_inc_return_acquire) return arch_atomic_inc_return_acquire(v); #elif defined(arch_atomic_inc_return_relaxed) int ret = arch_atomic_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #else return raw_atomic_add_return_acquire(1, v); #endif } /** * raw_atomic_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_inc_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return_release(atomic_t *v) { #if defined(arch_atomic_inc_return_release) return arch_atomic_inc_return_release(v); #elif defined(arch_atomic_inc_return_relaxed) __atomic_release_fence(); return arch_atomic_inc_return_relaxed(v); #elif defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #else return raw_atomic_add_return_release(1, v); #endif } /** * raw_atomic_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_inc_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return_relaxed(atomic_t *v) { #if defined(arch_atomic_inc_return_relaxed) return arch_atomic_inc_return_relaxed(v); #elif defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #else return raw_atomic_add_return_relaxed(1, v); #endif } /** * raw_atomic_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc(atomic_t *v) { #if defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #elif defined(arch_atomic_fetch_inc_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_fetch_add(1, v); #endif } /** * raw_atomic_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc_acquire(atomic_t *v) { #if defined(arch_atomic_fetch_inc_acquire) return arch_atomic_fetch_inc_acquire(v); #elif defined(arch_atomic_fetch_inc_relaxed) int ret = arch_atomic_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #else return raw_atomic_fetch_add_acquire(1, v); #endif } /** * raw_atomic_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc_release(atomic_t *v) { #if defined(arch_atomic_fetch_inc_release) return arch_atomic_fetch_inc_release(v); #elif defined(arch_atomic_fetch_inc_relaxed) __atomic_release_fence(); return arch_atomic_fetch_inc_relaxed(v); #elif defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #else return raw_atomic_fetch_add_release(1, v); #endif } /** * raw_atomic_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc_relaxed(atomic_t *v) { #if defined(arch_atomic_fetch_inc_relaxed) return arch_atomic_fetch_inc_relaxed(v); #elif defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #else return raw_atomic_fetch_add_relaxed(1, v); #endif } /** * raw_atomic_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_dec() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_dec(atomic_t *v) { #if defined(arch_atomic_dec) arch_atomic_dec(v); #else raw_atomic_sub(1, v); #endif } /** * raw_atomic_dec_return() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_dec_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return(atomic_t *v) { #if defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #elif defined(arch_atomic_dec_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_sub_return(1, v); #endif } /** * raw_atomic_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_dec_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return_acquire(atomic_t *v) { #if defined(arch_atomic_dec_return_acquire) return arch_atomic_dec_return_acquire(v); #elif defined(arch_atomic_dec_return_relaxed) int ret = arch_atomic_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #else return raw_atomic_sub_return_acquire(1, v); #endif } /** * raw_atomic_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_dec_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return_release(atomic_t *v) { #if defined(arch_atomic_dec_return_release) return arch_atomic_dec_return_release(v); #elif defined(arch_atomic_dec_return_relaxed) __atomic_release_fence(); return arch_atomic_dec_return_relaxed(v); #elif defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #else return raw_atomic_sub_return_release(1, v); #endif } /** * raw_atomic_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_dec_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return_relaxed(atomic_t *v) { #if defined(arch_atomic_dec_return_relaxed) return arch_atomic_dec_return_relaxed(v); #elif defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #else return raw_atomic_sub_return_relaxed(1, v); #endif } /** * raw_atomic_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec(atomic_t *v) { #if defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #elif defined(arch_atomic_fetch_dec_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_fetch_sub(1, v); #endif } /** * raw_atomic_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec_acquire(atomic_t *v) { #if defined(arch_atomic_fetch_dec_acquire) return arch_atomic_fetch_dec_acquire(v); #elif defined(arch_atomic_fetch_dec_relaxed) int ret = arch_atomic_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #else return raw_atomic_fetch_sub_acquire(1, v); #endif } /** * raw_atomic_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec_release(atomic_t *v) { #if defined(arch_atomic_fetch_dec_release) return arch_atomic_fetch_dec_release(v); #elif defined(arch_atomic_fetch_dec_relaxed) __atomic_release_fence(); return arch_atomic_fetch_dec_relaxed(v); #elif defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #else return raw_atomic_fetch_sub_release(1, v); #endif } /** * raw_atomic_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec_relaxed(atomic_t *v) { #if defined(arch_atomic_fetch_dec_relaxed) return arch_atomic_fetch_dec_relaxed(v); #elif defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #else return raw_atomic_fetch_sub_relaxed(1, v); #endif } /** * raw_atomic_and() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_and() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_and(int i, atomic_t *v) { arch_atomic_and(i, v); } /** * raw_atomic_fetch_and() - atomic bitwise AND with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #elif defined(arch_atomic_fetch_and_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_and" #endif } /** * raw_atomic_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and_acquire) return arch_atomic_fetch_and_acquire(i, v); #elif defined(arch_atomic_fetch_and_relaxed) int ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #else #error "Unable to define raw_atomic_fetch_and_acquire" #endif } /** * raw_atomic_fetch_and_release() - atomic bitwise AND with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and_release) return arch_atomic_fetch_and_release(i, v); #elif defined(arch_atomic_fetch_and_relaxed) __atomic_release_fence(); return arch_atomic_fetch_and_relaxed(i, v); #elif defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #else #error "Unable to define raw_atomic_fetch_and_release" #endif } /** * raw_atomic_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and_relaxed) return arch_atomic_fetch_and_relaxed(i, v); #elif defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #else #error "Unable to define raw_atomic_fetch_and_relaxed" #endif } /** * raw_atomic_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_andnot() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_andnot(int i, atomic_t *v) { #if defined(arch_atomic_andnot) arch_atomic_andnot(i, v); #else raw_atomic_and(~i, v); #endif } /** * raw_atomic_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #elif defined(arch_atomic_fetch_andnot_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic_fetch_and(~i, v); #endif } /** * raw_atomic_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot_acquire) return arch_atomic_fetch_andnot_acquire(i, v); #elif defined(arch_atomic_fetch_andnot_relaxed) int ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #else return raw_atomic_fetch_and_acquire(~i, v); #endif } /** * raw_atomic_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot_release) return arch_atomic_fetch_andnot_release(i, v); #elif defined(arch_atomic_fetch_andnot_relaxed) __atomic_release_fence(); return arch_atomic_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #else return raw_atomic_fetch_and_release(~i, v); #endif } /** * raw_atomic_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot_relaxed) return arch_atomic_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #else return raw_atomic_fetch_and_relaxed(~i, v); #endif } /** * raw_atomic_or() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_or() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_or(int i, atomic_t *v) { arch_atomic_or(i, v); } /** * raw_atomic_fetch_or() - atomic bitwise OR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #elif defined(arch_atomic_fetch_or_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_or" #endif } /** * raw_atomic_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or_acquire) return arch_atomic_fetch_or_acquire(i, v); #elif defined(arch_atomic_fetch_or_relaxed) int ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #else #error "Unable to define raw_atomic_fetch_or_acquire" #endif } /** * raw_atomic_fetch_or_release() - atomic bitwise OR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or_release) return arch_atomic_fetch_or_release(i, v); #elif defined(arch_atomic_fetch_or_relaxed) __atomic_release_fence(); return arch_atomic_fetch_or_relaxed(i, v); #elif defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #else #error "Unable to define raw_atomic_fetch_or_release" #endif } /** * raw_atomic_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or_relaxed) return arch_atomic_fetch_or_relaxed(i, v); #elif defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #else #error "Unable to define raw_atomic_fetch_or_relaxed" #endif } /** * raw_atomic_xor() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_xor() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_xor(int i, atomic_t *v) { arch_atomic_xor(i, v); } /** * raw_atomic_fetch_xor() - atomic bitwise XOR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #elif defined(arch_atomic_fetch_xor_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_xor" #endif } /** * raw_atomic_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor_acquire) return arch_atomic_fetch_xor_acquire(i, v); #elif defined(arch_atomic_fetch_xor_relaxed) int ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #else #error "Unable to define raw_atomic_fetch_xor_acquire" #endif } /** * raw_atomic_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor_release) return arch_atomic_fetch_xor_release(i, v); #elif defined(arch_atomic_fetch_xor_relaxed) __atomic_release_fence(); return arch_atomic_fetch_xor_relaxed(i, v); #elif defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #else #error "Unable to define raw_atomic_fetch_xor_release" #endif } /** * raw_atomic_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor_relaxed) return arch_atomic_fetch_xor_relaxed(i, v); #elif defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #else #error "Unable to define raw_atomic_fetch_xor_relaxed" #endif } /** * raw_atomic_xchg() - atomic exchange with full ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with full ordering. * * Safe to use in noinstr code; prefer atomic_xchg() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg(atomic_t *v, int new) { #if defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #elif defined(arch_atomic_xchg_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_xchg_relaxed(v, new); __atomic_post_full_fence(); return ret; #else return raw_xchg(&v->counter, new); #endif } /** * raw_atomic_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with acquire ordering. * * Safe to use in noinstr code; prefer atomic_xchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg_acquire(atomic_t *v, int new) { #if defined(arch_atomic_xchg_acquire) return arch_atomic_xchg_acquire(v, new); #elif defined(arch_atomic_xchg_relaxed) int ret = arch_atomic_xchg_relaxed(v, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #else return raw_xchg_acquire(&v->counter, new); #endif } /** * raw_atomic_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with release ordering. * * Safe to use in noinstr code; prefer atomic_xchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg_release(atomic_t *v, int new) { #if defined(arch_atomic_xchg_release) return arch_atomic_xchg_release(v, new); #elif defined(arch_atomic_xchg_relaxed) __atomic_release_fence(); return arch_atomic_xchg_relaxed(v, new); #elif defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #else return raw_xchg_release(&v->counter, new); #endif } /** * raw_atomic_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_xchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg_relaxed(atomic_t *v, int new) { #if defined(arch_atomic_xchg_relaxed) return arch_atomic_xchg_relaxed(v, new); #elif defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #else return raw_xchg_relaxed(&v->counter, new); #endif } /** * raw_atomic_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #elif defined(arch_atomic_cmpxchg_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else return raw_cmpxchg(&v->counter, old, new); #endif } /** * raw_atomic_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg_acquire) return arch_atomic_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic_cmpxchg_relaxed) int ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #else return raw_cmpxchg_acquire(&v->counter, old, new); #endif } /** * raw_atomic_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg_release(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg_release) return arch_atomic_cmpxchg_release(v, old, new); #elif defined(arch_atomic_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #else return raw_cmpxchg_release(&v->counter, old, new); #endif } /** * raw_atomic_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg_relaxed) return arch_atomic_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #else return raw_cmpxchg_relaxed(&v->counter, old, new); #endif } /** * raw_atomic_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #elif defined(arch_atomic_try_cmpxchg_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else int r, o = *old; r = raw_atomic_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_acquire() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg_acquire) return arch_atomic_try_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic_try_cmpxchg_relaxed) bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #else int r, o = *old; r = raw_atomic_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_release() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg_release) return arch_atomic_try_cmpxchg_release(v, old, new); #elif defined(arch_atomic_try_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #else int r, o = *old; r = raw_atomic_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_relaxed() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg_relaxed) return arch_atomic_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #else int r, o = *old; r = raw_atomic_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_sub_and_test() - atomic subtract and test if zero with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_sub_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_sub_and_test(int i, atomic_t *v) { #if defined(arch_atomic_sub_and_test) return arch_atomic_sub_and_test(i, v); #else return raw_atomic_sub_return(i, v) == 0; #endif } /** * raw_atomic_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_dec_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_dec_and_test(atomic_t *v) { #if defined(arch_atomic_dec_and_test) return arch_atomic_dec_and_test(v); #else return raw_atomic_dec_return(v) == 0; #endif } /** * raw_atomic_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_inc_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_inc_and_test(atomic_t *v) { #if defined(arch_atomic_inc_and_test) return arch_atomic_inc_and_test(v); #else return raw_atomic_inc_return(v) == 0; #endif } /** * raw_atomic_add_negative() - atomic add and test if negative with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_add_negative() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative(int i, atomic_t *v) { #if defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #elif defined(arch_atomic_add_negative_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic_add_negative_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic_add_return(i, v) < 0; #endif } /** * raw_atomic_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_add_negative_acquire() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative_acquire(int i, atomic_t *v) { #if defined(arch_atomic_add_negative_acquire) return arch_atomic_add_negative_acquire(i, v); #elif defined(arch_atomic_add_negative_relaxed) bool ret = arch_atomic_add_negative_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #else return raw_atomic_add_return_acquire(i, v) < 0; #endif } /** * raw_atomic_add_negative_release() - atomic add and test if negative with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_add_negative_release() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative_release(int i, atomic_t *v) { #if defined(arch_atomic_add_negative_release) return arch_atomic_add_negative_release(i, v); #elif defined(arch_atomic_add_negative_relaxed) __atomic_release_fence(); return arch_atomic_add_negative_relaxed(i, v); #elif defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #else return raw_atomic_add_return_release(i, v) < 0; #endif } /** * raw_atomic_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_add_negative_relaxed() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_add_negative_relaxed) return arch_atomic_add_negative_relaxed(i, v); #elif defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #else return raw_atomic_add_return_relaxed(i, v) < 0; #endif } /** * raw_atomic_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_fetch_add_unless() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_unless(atomic_t *v, int a, int u) { #if defined(arch_atomic_fetch_add_unless) return arch_atomic_fetch_add_unless(v, a, u); #else int c = raw_atomic_read(v); do { if (unlikely(c == u)) break; } while (!raw_atomic_try_cmpxchg(v, &c, c + a)); return c; #endif } /** * raw_atomic_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_add_unless() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_add_unless(atomic_t *v, int a, int u) { #if defined(arch_atomic_add_unless) return arch_atomic_add_unless(v, a, u); #else return raw_atomic_fetch_add_unless(v, a, u) != u; #endif } /** * raw_atomic_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_inc_not_zero() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_inc_not_zero(atomic_t *v) { #if defined(arch_atomic_inc_not_zero) return arch_atomic_inc_not_zero(v); #else return raw_atomic_add_unless(v, 1, 0); #endif } /** * raw_atomic_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_inc_unless_negative() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_inc_unless_negative(atomic_t *v) { #if defined(arch_atomic_inc_unless_negative) return arch_atomic_inc_unless_negative(v); #else int c = raw_atomic_read(v); do { if (unlikely(c < 0)) return false; } while (!raw_atomic_try_cmpxchg(v, &c, c + 1)); return true; #endif } /** * raw_atomic_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_dec_unless_positive() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_dec_unless_positive(atomic_t *v) { #if defined(arch_atomic_dec_unless_positive) return arch_atomic_dec_unless_positive(v); #else int c = raw_atomic_read(v); do { if (unlikely(c > 0)) return false; } while (!raw_atomic_try_cmpxchg(v, &c, c - 1)); return true; #endif } /** * raw_atomic_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_dec_if_positive() elsewhere. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline int raw_atomic_dec_if_positive(atomic_t *v) { #if defined(arch_atomic_dec_if_positive) return arch_atomic_dec_if_positive(v); #else int dec, c = raw_atomic_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!raw_atomic_try_cmpxchg(v, &c, dec)); return dec; #endif } #ifdef CONFIG_GENERIC_ATOMIC64 #include <asm-generic/atomic64.h> #endif /** * raw_atomic64_read() - atomic load with relaxed ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_read() elsewhere. * * Return: The value loaded from @v. */ static __always_inline s64 raw_atomic64_read(const atomic64_t *v) { return arch_atomic64_read(v); } /** * raw_atomic64_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_read_acquire() elsewhere. * * Return: The value loaded from @v. */ static __always_inline s64 raw_atomic64_read_acquire(const atomic64_t *v) { #if defined(arch_atomic64_read_acquire) return arch_atomic64_read_acquire(v); #else s64 ret; if (__native_word(atomic64_t)) { ret = smp_load_acquire(&(v)->counter); } else { ret = raw_atomic64_read(v); __atomic_acquire_fence(); } return ret; #endif } /** * raw_atomic64_set() - atomic set with relaxed ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_set() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_set(atomic64_t *v, s64 i) { arch_atomic64_set(v, i); } /** * raw_atomic64_set_release() - atomic set with release ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with release ordering. * * Safe to use in noinstr code; prefer atomic64_set_release() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_set_release(atomic64_t *v, s64 i) { #if defined(arch_atomic64_set_release) arch_atomic64_set_release(v, i); #else if (__native_word(atomic64_t)) { smp_store_release(&(v)->counter, i); } else { __atomic_release_fence(); raw_atomic64_set(v, i); } #endif } /** * raw_atomic64_add() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_add() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_add(s64 i, atomic64_t *v) { arch_atomic64_add(i, v); } /** * raw_atomic64_add_return() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_add_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #elif defined(arch_atomic64_add_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_add_return" #endif } /** * raw_atomic64_add_return_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_add_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return_acquire) return arch_atomic64_add_return_acquire(i, v); #elif defined(arch_atomic64_add_return_relaxed) s64 ret = arch_atomic64_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #else #error "Unable to define raw_atomic64_add_return_acquire" #endif } /** * raw_atomic64_add_return_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_add_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return_release) return arch_atomic64_add_return_release(i, v); #elif defined(arch_atomic64_add_return_relaxed) __atomic_release_fence(); return arch_atomic64_add_return_relaxed(i, v); #elif defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #else #error "Unable to define raw_atomic64_add_return_release" #endif } /** * raw_atomic64_add_return_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_add_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return_relaxed) return arch_atomic64_add_return_relaxed(i, v); #elif defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #else #error "Unable to define raw_atomic64_add_return_relaxed" #endif } /** * raw_atomic64_fetch_add() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #elif defined(arch_atomic64_fetch_add_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_add" #endif } /** * raw_atomic64_fetch_add_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add_acquire) return arch_atomic64_fetch_add_acquire(i, v); #elif defined(arch_atomic64_fetch_add_relaxed) s64 ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #else #error "Unable to define raw_atomic64_fetch_add_acquire" #endif } /** * raw_atomic64_fetch_add_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add_release) return arch_atomic64_fetch_add_release(i, v); #elif defined(arch_atomic64_fetch_add_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_add_relaxed(i, v); #elif defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #else #error "Unable to define raw_atomic64_fetch_add_release" #endif } /** * raw_atomic64_fetch_add_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add_relaxed) return arch_atomic64_fetch_add_relaxed(i, v); #elif defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #else #error "Unable to define raw_atomic64_fetch_add_relaxed" #endif } /** * raw_atomic64_sub() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_sub() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_sub(s64 i, atomic64_t *v) { arch_atomic64_sub(i, v); } /** * raw_atomic64_sub_return() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #elif defined(arch_atomic64_sub_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_sub_return" #endif } /** * raw_atomic64_sub_return_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return_acquire) return arch_atomic64_sub_return_acquire(i, v); #elif defined(arch_atomic64_sub_return_relaxed) s64 ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #else #error "Unable to define raw_atomic64_sub_return_acquire" #endif } /** * raw_atomic64_sub_return_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return_release) return arch_atomic64_sub_return_release(i, v); #elif defined(arch_atomic64_sub_return_relaxed) __atomic_release_fence(); return arch_atomic64_sub_return_relaxed(i, v); #elif defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #else #error "Unable to define raw_atomic64_sub_return_release" #endif } /** * raw_atomic64_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return_relaxed) return arch_atomic64_sub_return_relaxed(i, v); #elif defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #else #error "Unable to define raw_atomic64_sub_return_relaxed" #endif } /** * raw_atomic64_fetch_sub() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #elif defined(arch_atomic64_fetch_sub_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_sub" #endif } /** * raw_atomic64_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub_acquire) return arch_atomic64_fetch_sub_acquire(i, v); #elif defined(arch_atomic64_fetch_sub_relaxed) s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #else #error "Unable to define raw_atomic64_fetch_sub_acquire" #endif } /** * raw_atomic64_fetch_sub_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub_release) return arch_atomic64_fetch_sub_release(i, v); #elif defined(arch_atomic64_fetch_sub_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_sub_relaxed(i, v); #elif defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #else #error "Unable to define raw_atomic64_fetch_sub_release" #endif } /** * raw_atomic64_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub_relaxed) return arch_atomic64_fetch_sub_relaxed(i, v); #elif defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #else #error "Unable to define raw_atomic64_fetch_sub_relaxed" #endif } /** * raw_atomic64_inc() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_inc() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_inc(atomic64_t *v) { #if defined(arch_atomic64_inc) arch_atomic64_inc(v); #else raw_atomic64_add(1, v); #endif } /** * raw_atomic64_inc_return() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return(atomic64_t *v) { #if defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #elif defined(arch_atomic64_inc_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_add_return(1, v); #endif } /** * raw_atomic64_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return_acquire(atomic64_t *v) { #if defined(arch_atomic64_inc_return_acquire) return arch_atomic64_inc_return_acquire(v); #elif defined(arch_atomic64_inc_return_relaxed) s64 ret = arch_atomic64_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #else return raw_atomic64_add_return_acquire(1, v); #endif } /** * raw_atomic64_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return_release(atomic64_t *v) { #if defined(arch_atomic64_inc_return_release) return arch_atomic64_inc_return_release(v); #elif defined(arch_atomic64_inc_return_relaxed) __atomic_release_fence(); return arch_atomic64_inc_return_relaxed(v); #elif defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #else return raw_atomic64_add_return_release(1, v); #endif } /** * raw_atomic64_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return_relaxed(atomic64_t *v) { #if defined(arch_atomic64_inc_return_relaxed) return arch_atomic64_inc_return_relaxed(v); #elif defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #else return raw_atomic64_add_return_relaxed(1, v); #endif } /** * raw_atomic64_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #elif defined(arch_atomic64_fetch_inc_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_fetch_add(1, v); #endif } /** * raw_atomic64_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc_acquire(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc_acquire) return arch_atomic64_fetch_inc_acquire(v); #elif defined(arch_atomic64_fetch_inc_relaxed) s64 ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #else return raw_atomic64_fetch_add_acquire(1, v); #endif } /** * raw_atomic64_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc_release(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc_release) return arch_atomic64_fetch_inc_release(v); #elif defined(arch_atomic64_fetch_inc_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_inc_relaxed(v); #elif defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #else return raw_atomic64_fetch_add_release(1, v); #endif } /** * raw_atomic64_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc_relaxed(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc_relaxed) return arch_atomic64_fetch_inc_relaxed(v); #elif defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #else return raw_atomic64_fetch_add_relaxed(1, v); #endif } /** * raw_atomic64_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_dec() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_dec(atomic64_t *v) { #if defined(arch_atomic64_dec) arch_atomic64_dec(v); #else raw_atomic64_sub(1, v); #endif } /** * raw_atomic64_dec_return() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return(atomic64_t *v) { #if defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #elif defined(arch_atomic64_dec_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_sub_return(1, v); #endif } /** * raw_atomic64_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return_acquire(atomic64_t *v) { #if defined(arch_atomic64_dec_return_acquire) return arch_atomic64_dec_return_acquire(v); #elif defined(arch_atomic64_dec_return_relaxed) s64 ret = arch_atomic64_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #else return raw_atomic64_sub_return_acquire(1, v); #endif } /** * raw_atomic64_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return_release(atomic64_t *v) { #if defined(arch_atomic64_dec_return_release) return arch_atomic64_dec_return_release(v); #elif defined(arch_atomic64_dec_return_relaxed) __atomic_release_fence(); return arch_atomic64_dec_return_relaxed(v); #elif defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #else return raw_atomic64_sub_return_release(1, v); #endif } /** * raw_atomic64_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return_relaxed(atomic64_t *v) { #if defined(arch_atomic64_dec_return_relaxed) return arch_atomic64_dec_return_relaxed(v); #elif defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #else return raw_atomic64_sub_return_relaxed(1, v); #endif } /** * raw_atomic64_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #elif defined(arch_atomic64_fetch_dec_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_fetch_sub(1, v); #endif } /** * raw_atomic64_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec_acquire(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec_acquire) return arch_atomic64_fetch_dec_acquire(v); #elif defined(arch_atomic64_fetch_dec_relaxed) s64 ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #else return raw_atomic64_fetch_sub_acquire(1, v); #endif } /** * raw_atomic64_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec_release(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec_release) return arch_atomic64_fetch_dec_release(v); #elif defined(arch_atomic64_fetch_dec_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_dec_relaxed(v); #elif defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #else return raw_atomic64_fetch_sub_release(1, v); #endif } /** * raw_atomic64_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec_relaxed(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec_relaxed) return arch_atomic64_fetch_dec_relaxed(v); #elif defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #else return raw_atomic64_fetch_sub_relaxed(1, v); #endif } /** * raw_atomic64_and() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_and() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_and(s64 i, atomic64_t *v) { arch_atomic64_and(i, v); } /** * raw_atomic64_fetch_and() - atomic bitwise AND with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #elif defined(arch_atomic64_fetch_and_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_and" #endif } /** * raw_atomic64_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and_acquire) return arch_atomic64_fetch_and_acquire(i, v); #elif defined(arch_atomic64_fetch_and_relaxed) s64 ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #else #error "Unable to define raw_atomic64_fetch_and_acquire" #endif } /** * raw_atomic64_fetch_and_release() - atomic bitwise AND with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and_release) return arch_atomic64_fetch_and_release(i, v); #elif defined(arch_atomic64_fetch_and_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_and_relaxed(i, v); #elif defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #else #error "Unable to define raw_atomic64_fetch_and_release" #endif } /** * raw_atomic64_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and_relaxed) return arch_atomic64_fetch_and_relaxed(i, v); #elif defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #else #error "Unable to define raw_atomic64_fetch_and_relaxed" #endif } /** * raw_atomic64_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_andnot() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_andnot(s64 i, atomic64_t *v) { #if defined(arch_atomic64_andnot) arch_atomic64_andnot(i, v); #else raw_atomic64_and(~i, v); #endif } /** * raw_atomic64_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #elif defined(arch_atomic64_fetch_andnot_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_fetch_and(~i, v); #endif } /** * raw_atomic64_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot_acquire) return arch_atomic64_fetch_andnot_acquire(i, v); #elif defined(arch_atomic64_fetch_andnot_relaxed) s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #else return raw_atomic64_fetch_and_acquire(~i, v); #endif } /** * raw_atomic64_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot_release) return arch_atomic64_fetch_andnot_release(i, v); #elif defined(arch_atomic64_fetch_andnot_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #else return raw_atomic64_fetch_and_release(~i, v); #endif } /** * raw_atomic64_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot_relaxed) return arch_atomic64_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #else return raw_atomic64_fetch_and_relaxed(~i, v); #endif } /** * raw_atomic64_or() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_or() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_or(s64 i, atomic64_t *v) { arch_atomic64_or(i, v); } /** * raw_atomic64_fetch_or() - atomic bitwise OR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #elif defined(arch_atomic64_fetch_or_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_or" #endif } /** * raw_atomic64_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or_acquire) return arch_atomic64_fetch_or_acquire(i, v); #elif defined(arch_atomic64_fetch_or_relaxed) s64 ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #else #error "Unable to define raw_atomic64_fetch_or_acquire" #endif } /** * raw_atomic64_fetch_or_release() - atomic bitwise OR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or_release) return arch_atomic64_fetch_or_release(i, v); #elif defined(arch_atomic64_fetch_or_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_or_relaxed(i, v); #elif defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #else #error "Unable to define raw_atomic64_fetch_or_release" #endif } /** * raw_atomic64_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or_relaxed) return arch_atomic64_fetch_or_relaxed(i, v); #elif defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #else #error "Unable to define raw_atomic64_fetch_or_relaxed" #endif } /** * raw_atomic64_xor() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_xor() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_xor(s64 i, atomic64_t *v) { arch_atomic64_xor(i, v); } /** * raw_atomic64_fetch_xor() - atomic bitwise XOR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #elif defined(arch_atomic64_fetch_xor_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_xor" #endif } /** * raw_atomic64_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor_acquire) return arch_atomic64_fetch_xor_acquire(i, v); #elif defined(arch_atomic64_fetch_xor_relaxed) s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #else #error "Unable to define raw_atomic64_fetch_xor_acquire" #endif } /** * raw_atomic64_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor_release) return arch_atomic64_fetch_xor_release(i, v); #elif defined(arch_atomic64_fetch_xor_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_xor_relaxed(i, v); #elif defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #else #error "Unable to define raw_atomic64_fetch_xor_release" #endif } /** * raw_atomic64_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor_relaxed) return arch_atomic64_fetch_xor_relaxed(i, v); #elif defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #else #error "Unable to define raw_atomic64_fetch_xor_relaxed" #endif } /** * raw_atomic64_xchg() - atomic exchange with full ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with full ordering. * * Safe to use in noinstr code; prefer atomic64_xchg() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #elif defined(arch_atomic64_xchg_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_xchg_relaxed(v, new); __atomic_post_full_fence(); return ret; #else return raw_xchg(&v->counter, new); #endif } /** * raw_atomic64_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_xchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg_acquire(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg_acquire) return arch_atomic64_xchg_acquire(v, new); #elif defined(arch_atomic64_xchg_relaxed) s64 ret = arch_atomic64_xchg_relaxed(v, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #else return raw_xchg_acquire(&v->counter, new); #endif } /** * raw_atomic64_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with release ordering. * * Safe to use in noinstr code; prefer atomic64_xchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg_release(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg_release) return arch_atomic64_xchg_release(v, new); #elif defined(arch_atomic64_xchg_relaxed) __atomic_release_fence(); return arch_atomic64_xchg_relaxed(v, new); #elif defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #else return raw_xchg_release(&v->counter, new); #endif } /** * raw_atomic64_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_xchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg_relaxed(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg_relaxed) return arch_atomic64_xchg_relaxed(v, new); #elif defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #else return raw_xchg_relaxed(&v->counter, new); #endif } /** * raw_atomic64_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #elif defined(arch_atomic64_cmpxchg_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else return raw_cmpxchg(&v->counter, old, new); #endif } /** * raw_atomic64_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg_acquire) return arch_atomic64_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic64_cmpxchg_relaxed) s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #else return raw_cmpxchg_acquire(&v->counter, old, new); #endif } /** * raw_atomic64_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg_release) return arch_atomic64_cmpxchg_release(v, old, new); #elif defined(arch_atomic64_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic64_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #else return raw_cmpxchg_release(&v->counter, old, new); #endif } /** * raw_atomic64_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg_relaxed) return arch_atomic64_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #else return raw_cmpxchg_relaxed(&v->counter, old, new); #endif } /** * raw_atomic64_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #elif defined(arch_atomic64_try_cmpxchg_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else s64 r, o = *old; r = raw_atomic64_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_acquire() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg_acquire) return arch_atomic64_try_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic64_try_cmpxchg_relaxed) bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #else s64 r, o = *old; r = raw_atomic64_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_release() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg_release) return arch_atomic64_try_cmpxchg_release(v, old, new); #elif defined(arch_atomic64_try_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic64_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #else s64 r, o = *old; r = raw_atomic64_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_relaxed() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg_relaxed) return arch_atomic64_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #else s64 r, o = *old; r = raw_atomic64_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_sub_and_test() - atomic subtract and test if zero with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_sub_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic64_sub_and_test(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_and_test) return arch_atomic64_sub_and_test(i, v); #else return raw_atomic64_sub_return(i, v) == 0; #endif } /** * raw_atomic64_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_dec_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic64_dec_and_test(atomic64_t *v) { #if defined(arch_atomic64_dec_and_test) return arch_atomic64_dec_and_test(v); #else return raw_atomic64_dec_return(v) == 0; #endif } /** * raw_atomic64_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_inc_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic64_inc_and_test(atomic64_t *v) { #if defined(arch_atomic64_inc_and_test) return arch_atomic64_inc_and_test(v); #else return raw_atomic64_inc_return(v) == 0; #endif } /** * raw_atomic64_add_negative() - atomic add and test if negative with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #elif defined(arch_atomic64_add_negative_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic64_add_negative_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_add_return(i, v) < 0; #endif } /** * raw_atomic64_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative_acquire() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative_acquire) return arch_atomic64_add_negative_acquire(i, v); #elif defined(arch_atomic64_add_negative_relaxed) bool ret = arch_atomic64_add_negative_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #else return raw_atomic64_add_return_acquire(i, v) < 0; #endif } /** * raw_atomic64_add_negative_release() - atomic add and test if negative with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative_release() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative_release) return arch_atomic64_add_negative_release(i, v); #elif defined(arch_atomic64_add_negative_relaxed) __atomic_release_fence(); return arch_atomic64_add_negative_relaxed(i, v); #elif defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #else return raw_atomic64_add_return_release(i, v) < 0; #endif } /** * raw_atomic64_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative_relaxed() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative_relaxed) return arch_atomic64_add_negative_relaxed(i, v); #elif defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #else return raw_atomic64_add_return_relaxed(i, v) < 0; #endif } /** * raw_atomic64_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_fetch_add_unless() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { #if defined(arch_atomic64_fetch_add_unless) return arch_atomic64_fetch_add_unless(v, a, u); #else s64 c = raw_atomic64_read(v); do { if (unlikely(c == u)) break; } while (!raw_atomic64_try_cmpxchg(v, &c, c + a)); return c; #endif } /** * raw_atomic64_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_add_unless() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { #if defined(arch_atomic64_add_unless) return arch_atomic64_add_unless(v, a, u); #else return raw_atomic64_fetch_add_unless(v, a, u) != u; #endif } /** * raw_atomic64_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic64_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_inc_not_zero() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_inc_not_zero(atomic64_t *v) { #if defined(arch_atomic64_inc_not_zero) return arch_atomic64_inc_not_zero(v); #else return raw_atomic64_add_unless(v, 1, 0); #endif } /** * raw_atomic64_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic64_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_inc_unless_negative() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_inc_unless_negative(atomic64_t *v) { #if defined(arch_atomic64_inc_unless_negative) return arch_atomic64_inc_unless_negative(v); #else s64 c = raw_atomic64_read(v); do { if (unlikely(c < 0)) return false; } while (!raw_atomic64_try_cmpxchg(v, &c, c + 1)); return true; #endif } /** * raw_atomic64_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic64_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_dec_unless_positive() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_dec_unless_positive(atomic64_t *v) { #if defined(arch_atomic64_dec_unless_positive) return arch_atomic64_dec_unless_positive(v); #else s64 c = raw_atomic64_read(v); do { if (unlikely(c > 0)) return false; } while (!raw_atomic64_try_cmpxchg(v, &c, c - 1)); return true; #endif } /** * raw_atomic64_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic64_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_dec_if_positive() elsewhere. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline s64 raw_atomic64_dec_if_positive(atomic64_t *v) { #if defined(arch_atomic64_dec_if_positive) return arch_atomic64_dec_if_positive(v); #else s64 dec, c = raw_atomic64_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!raw_atomic64_try_cmpxchg(v, &c, dec)); return dec; #endif } #endif /* _LINUX_ATOMIC_FALLBACK_H */ // b565db590afeeff0d7c9485ccbca5bb6e155749f |
| 2 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 | /* * af_llc.c - LLC User Interface SAPs * Description: * Functions in this module are implementation of socket based llc * communications for the Linux operating system. Support of llc class * one and class two is provided via SOCK_DGRAM and SOCK_STREAM * respectively. * * An llc2 connection is (mac + sap), only one llc2 sap connection * is allowed per mac. Though one sap may have multiple mac + sap * connections. * * Copyright (c) 2001 by Jay Schulist <jschlst@samba.org> * 2002-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <net/llc.h> #include <net/llc_sap.h> #include <net/llc_pdu.h> #include <net/llc_conn.h> #include <net/tcp_states.h> /* remember: uninitialized global data is zeroed because its in .bss */ static u16 llc_ui_sap_last_autoport = LLC_SAP_DYN_START; static u16 llc_ui_sap_link_no_max[256]; static struct sockaddr_llc llc_ui_addrnull; static const struct proto_ops llc_ui_ops; static bool llc_ui_wait_for_conn(struct sock *sk, long timeout); static int llc_ui_wait_for_disc(struct sock *sk, long timeout); static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout); #if 0 #define dprintk(args...) printk(KERN_DEBUG args) #else #define dprintk(args...) do {} while (0) #endif /* Maybe we'll add some more in the future. */ #define LLC_CMSG_PKTINFO 1 /** * llc_ui_next_link_no - return the next unused link number for a sap * @sap: Address of sap to get link number from. * * Return the next unused link number for a given sap. */ static inline u16 llc_ui_next_link_no(int sap) { return llc_ui_sap_link_no_max[sap]++; } /** * llc_proto_type - return eth protocol for ARP header type * @arphrd: ARP header type. * * Given an ARP header type return the corresponding ethernet protocol. */ static inline __be16 llc_proto_type(u16 arphrd) { return htons(ETH_P_802_2); } /** * llc_ui_addr_null - determines if a address structure is null * @addr: Address to test if null. */ static inline u8 llc_ui_addr_null(struct sockaddr_llc *addr) { return !memcmp(addr, &llc_ui_addrnull, sizeof(*addr)); } /** * llc_ui_header_len - return length of llc header based on operation * @sk: Socket which contains a valid llc socket type. * @addr: Complete sockaddr_llc structure received from the user. * * Provide the length of the llc header depending on what kind of * operation the user would like to perform and the type of socket. * Returns the correct llc header length. */ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) { u8 rc = LLC_PDU_LEN_U; if (addr->sllc_test) rc = LLC_PDU_LEN_U; else if (addr->sllc_xid) /* We need to expand header to sizeof(struct llc_xid_info) * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header * as XID PDU. In llc_ui_sendmsg() we reserved header size and then * filled all other space with user data. If we won't reserve this * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data */ rc = LLC_PDU_LEN_U_XID; else if (sk->sk_type == SOCK_STREAM) rc = LLC_PDU_LEN_I; return rc; } /** * llc_ui_send_data - send data via reliable llc2 connection * @sk: Connection the socket is using. * @skb: Data the user wishes to send. * @noblock: can we block waiting for data? * * Send data via reliable llc2 connection. * Returns 0 upon success, non-zero if action did not succeed. * * This function always consumes a reference to the skb. */ static int llc_ui_send_data(struct sock* sk, struct sk_buff *skb, int noblock) { struct llc_sock* llc = llc_sk(sk); if (unlikely(llc_data_accept_state(llc->state) || llc->remote_busy_flag || llc->p_flag)) { long timeout = sock_sndtimeo(sk, noblock); int rc; rc = llc_ui_wait_for_busy_core(sk, timeout); if (rc) { kfree_skb(skb); return rc; } } return llc_build_and_send_pkt(sk, skb); } static void llc_ui_sk_init(struct socket *sock, struct sock *sk) { sock_graft(sk, sock); sk->sk_type = sock->type; sock->ops = &llc_ui_ops; } static struct proto llc_proto = { .name = "LLC", .owner = THIS_MODULE, .obj_size = sizeof(struct llc_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, }; /** * llc_ui_create - alloc and init a new llc_ui socket * @net: network namespace (must be default network) * @sock: Socket to initialize and attach allocated sk to. * @protocol: Unused. * @kern: on behalf of kernel or userspace * * Allocate and initialize a new llc_ui socket, validate the user wants a * socket type we have available. * Returns 0 upon success, negative upon failure. */ static int llc_ui_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; int rc = -ESOCKTNOSUPPORT; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; if (likely(sock->type == SOCK_DGRAM || sock->type == SOCK_STREAM)) { rc = -ENOMEM; sk = llc_sk_alloc(net, PF_LLC, GFP_KERNEL, &llc_proto, kern); if (sk) { rc = 0; llc_ui_sk_init(sock, sk); } } return rc; } /** * llc_ui_release - shutdown socket * @sock: Socket to release. * * Shutdown and deallocate an existing socket. */ static int llc_ui_release(struct socket *sock) { struct sock *sk = sock->sk; struct llc_sock *llc; if (unlikely(sk == NULL)) goto out; sock_hold(sk); lock_sock(sk); llc = llc_sk(sk); dprintk("%s: closing local(%02X) remote(%02X)\n", __func__, llc->laddr.lsap, llc->daddr.lsap); if (!llc_send_disc(sk)) llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); if (!sock_flag(sk, SOCK_ZAPPED)) { struct llc_sap *sap = llc->sap; /* Hold this for release_sock(), so that llc_backlog_rcv() * could still use it. */ llc_sap_hold(sap); llc_sap_remove_socket(llc->sap, sk); release_sock(sk); llc_sap_put(sap); } else { release_sock(sk); } netdev_put(llc->dev, &llc->dev_tracker); sock_put(sk); sock_orphan(sk); sock->sk = NULL; llc_sk_free(sk); out: return 0; } /** * llc_ui_autoport - provide dynamically allocate SAP number * * Provide the caller with a dynamically allocated SAP number according * to the rules that are set in this function. Returns: 0, upon failure, * SAP number otherwise. */ static int llc_ui_autoport(void) { struct llc_sap *sap; int i, tries = 0; while (tries < LLC_SAP_DYN_TRIES) { for (i = llc_ui_sap_last_autoport; i < LLC_SAP_DYN_STOP; i += 2) { sap = llc_sap_find(i); if (!sap) { llc_ui_sap_last_autoport = i + 2; goto out; } llc_sap_put(sap); } llc_ui_sap_last_autoport = LLC_SAP_DYN_START; tries++; } i = 0; out: return i; } /** * llc_ui_autobind - automatically bind a socket to a sap * @sock: socket to bind * @addr: address to connect to * * Used by llc_ui_connect and llc_ui_sendmsg when the user hasn't * specifically used llc_ui_bind to bind to an specific address/sap * * Returns: 0 upon success, negative otherwise. */ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); struct net_device *dev = NULL; struct llc_sap *sap; int rc = -EINVAL; if (!sock_flag(sk, SOCK_ZAPPED)) goto out; if (!addr->sllc_arphrd) addr->sllc_arphrd = ARPHRD_ETHER; if (addr->sllc_arphrd != ARPHRD_ETHER) goto out; rc = -ENODEV; if (sk->sk_bound_dev_if) { dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); if (dev && addr->sllc_arphrd != dev->type) { dev_put(dev); dev = NULL; } } else dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd); if (!dev) goto out; rc = -EUSERS; llc->laddr.lsap = llc_ui_autoport(); if (!llc->laddr.lsap) goto out; rc = -EBUSY; /* some other network layer is using the sap */ sap = llc_sap_open(llc->laddr.lsap, NULL); if (!sap) goto out; /* Note: We do not expect errors from this point. */ llc->dev = dev; netdev_tracker_alloc(llc->dev, &llc->dev_tracker, GFP_KERNEL); dev = NULL; memcpy(llc->laddr.mac, llc->dev->dev_addr, IFHWADDRLEN); memcpy(&llc->addr, addr, sizeof(llc->addr)); /* assign new connection to its SAP */ llc_sap_add_socket(sap, sk); sock_reset_flag(sk, SOCK_ZAPPED); rc = 0; out: dev_put(dev); return rc; } /** * llc_ui_bind - bind a socket to a specific address. * @sock: Socket to bind an address to. * @uaddr: Address the user wants the socket bound to. * @addrlen: Length of the uaddr structure. * * Bind a socket to a specific address. For llc a user is able to bind to * a specific sap only or mac + sap. * If the user desires to bind to a specific mac + sap, it is possible to * have multiple sap connections via multiple macs. * Bind and autobind for that matter must enforce the correct sap usage * otherwise all hell will break loose. * Returns: 0 upon success, negative otherwise. */ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) { struct sockaddr_llc *addr = (struct sockaddr_llc *)uaddr; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); struct net_device *dev = NULL; struct llc_sap *sap; int rc = -EINVAL; lock_sock(sk); if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; if (!addr->sllc_arphrd) addr->sllc_arphrd = ARPHRD_ETHER; if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER)) goto out; dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); rc = -ENODEV; rcu_read_lock(); if (sk->sk_bound_dev_if) { dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); if (dev) { if (is_zero_ether_addr(addr->sllc_mac)) memcpy(addr->sllc_mac, dev->dev_addr, IFHWADDRLEN); if (addr->sllc_arphrd != dev->type || !ether_addr_equal(addr->sllc_mac, dev->dev_addr)) { rc = -EINVAL; dev = NULL; } } } else { dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd, addr->sllc_mac); } dev_hold(dev); rcu_read_unlock(); if (!dev) goto out; if (!addr->sllc_sap) { rc = -EUSERS; addr->sllc_sap = llc_ui_autoport(); if (!addr->sllc_sap) goto out; } sap = llc_sap_find(addr->sllc_sap); if (!sap) { sap = llc_sap_open(addr->sllc_sap, NULL); rc = -EBUSY; /* some other network layer is using the sap */ if (!sap) goto out; } else { struct llc_addr laddr, daddr; struct sock *ask; memset(&laddr, 0, sizeof(laddr)); memset(&daddr, 0, sizeof(daddr)); /* * FIXME: check if the address is multicast, * only SOCK_DGRAM can do this. */ memcpy(laddr.mac, addr->sllc_mac, IFHWADDRLEN); laddr.lsap = addr->sllc_sap; rc = -EADDRINUSE; /* mac + sap clash. */ ask = llc_lookup_established(sap, &daddr, &laddr, &init_net); if (ask) { sock_put(ask); goto out_put; } } /* Note: We do not expect errors from this point. */ llc->dev = dev; netdev_tracker_alloc(llc->dev, &llc->dev_tracker, GFP_KERNEL); dev = NULL; llc->laddr.lsap = addr->sllc_sap; memcpy(llc->laddr.mac, addr->sllc_mac, IFHWADDRLEN); memcpy(&llc->addr, addr, sizeof(llc->addr)); /* assign new connection to its SAP */ llc_sap_add_socket(sap, sk); sock_reset_flag(sk, SOCK_ZAPPED); rc = 0; out_put: llc_sap_put(sap); out: dev_put(dev); release_sock(sk); return rc; } /** * llc_ui_shutdown - shutdown a connect llc2 socket. * @sock: Socket to shutdown. * @how: What part of the socket to shutdown. * * Shutdown a connected llc2 socket. Currently this function only supports * shutting down both sends and receives (2), we could probably make this * function such that a user can shutdown only half the connection but not * right now. * Returns: 0 upon success, negative otherwise. */ static int llc_ui_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int rc = -ENOTCONN; lock_sock(sk); if (unlikely(sk->sk_state != TCP_ESTABLISHED)) goto out; rc = -EINVAL; if (how != 2) goto out; rc = llc_send_disc(sk); if (!rc) rc = llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); /* Wake up anyone sleeping in poll */ sk->sk_state_change(sk); out: release_sock(sk); return rc; } /** * llc_ui_connect - Connect to a remote llc2 mac + sap. * @sock: Socket which will be connected to the remote destination. * @uaddr: Remote and possibly the local address of the new connection. * @addrlen: Size of uaddr structure. * @flags: Operational flags specified by the user. * * Connect to a remote llc2 mac + sap. The caller must specify the * destination mac and address to connect to. If the user hasn't previously * called bind(2) with a smac the address of the first interface of the * specified arp type will be used. * This function will autobind if user did not previously call bind. * Returns: 0 upon success, negative otherwise. */ static int llc_ui_connect(struct socket *sock, struct sockaddr *uaddr, int addrlen, int flags) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); struct sockaddr_llc *addr = (struct sockaddr_llc *)uaddr; int rc = -EINVAL; lock_sock(sk); if (unlikely(addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; if (unlikely(addr->sllc_family != AF_LLC)) goto out; if (unlikely(sk->sk_type != SOCK_STREAM)) goto out; rc = -EALREADY; if (unlikely(sock->state == SS_CONNECTING)) goto out; /* bind connection to sap if user hasn't done it. */ if (sock_flag(sk, SOCK_ZAPPED)) { /* bind to sap with null dev, exclusive */ rc = llc_ui_autobind(sock, addr); if (rc) goto out; } llc->daddr.lsap = addr->sllc_sap; memcpy(llc->daddr.mac, addr->sllc_mac, IFHWADDRLEN); sock->state = SS_CONNECTING; sk->sk_state = TCP_SYN_SENT; llc->link = llc_ui_next_link_no(llc->sap->laddr.lsap); rc = llc_establish_connection(sk, llc->dev->dev_addr, addr->sllc_mac, addr->sllc_sap); if (rc) { dprintk("%s: llc_ui_send_conn failed :-(\n", __func__); sock->state = SS_UNCONNECTED; sk->sk_state = TCP_CLOSE; goto out; } if (sk->sk_state == TCP_SYN_SENT) { const long timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); if (!timeo || !llc_ui_wait_for_conn(sk, timeo)) goto out; rc = sock_intr_errno(timeo); if (signal_pending(current)) goto out; } if (sk->sk_state == TCP_CLOSE) goto sock_error; sock->state = SS_CONNECTED; rc = 0; out: release_sock(sk); return rc; sock_error: rc = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; goto out; } /** * llc_ui_listen - allow a normal socket to accept incoming connections * @sock: Socket to allow incoming connections on. * @backlog: Number of connections to queue. * * Allow a normal socket to accept incoming connections. * Returns 0 upon success, negative otherwise. */ static int llc_ui_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; int rc = -EINVAL; lock_sock(sk); if (unlikely(sock->state != SS_UNCONNECTED)) goto out; rc = -EOPNOTSUPP; if (unlikely(sk->sk_type != SOCK_STREAM)) goto out; rc = -EAGAIN; if (sock_flag(sk, SOCK_ZAPPED)) goto out; rc = 0; if (!(unsigned int)backlog) /* BSDism */ backlog = 1; sk->sk_max_ack_backlog = backlog; if (sk->sk_state != TCP_LISTEN) { sk->sk_ack_backlog = 0; sk->sk_state = TCP_LISTEN; } sk->sk_socket->flags |= __SO_ACCEPTCON; out: release_sock(sk); return rc; } static int llc_ui_wait_for_disc(struct sock *sk, long timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int rc = 0; add_wait_queue(sk_sleep(sk), &wait); while (1) { if (sk_wait_event(sk, &timeout, READ_ONCE(sk->sk_state) == TCP_CLOSE, &wait)) break; rc = -ERESTARTSYS; if (signal_pending(current)) break; rc = -EAGAIN; if (!timeout) break; rc = 0; } remove_wait_queue(sk_sleep(sk), &wait); return rc; } static bool llc_ui_wait_for_conn(struct sock *sk, long timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(sk_sleep(sk), &wait); while (1) { if (sk_wait_event(sk, &timeout, READ_ONCE(sk->sk_state) != TCP_SYN_SENT, &wait)) break; if (signal_pending(current) || !timeout) break; } remove_wait_queue(sk_sleep(sk), &wait); return timeout; } static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct llc_sock *llc = llc_sk(sk); int rc; add_wait_queue(sk_sleep(sk), &wait); while (1) { rc = 0; if (sk_wait_event(sk, &timeout, (READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN) || (!llc_data_accept_state(llc->state) && !llc->remote_busy_flag && !llc->p_flag), &wait)) break; rc = -ERESTARTSYS; if (signal_pending(current)) break; rc = -EAGAIN; if (!timeout) break; } remove_wait_queue(sk_sleep(sk), &wait); return rc; } static int llc_wait_data(struct sock *sk, long timeo) { int rc; while (1) { /* * POSIX 1003.1g mandates this order. */ rc = sock_error(sk); if (rc) break; rc = 0; if (sk->sk_shutdown & RCV_SHUTDOWN) break; rc = -EAGAIN; if (!timeo) break; rc = sock_intr_errno(timeo); if (signal_pending(current)) break; rc = 0; if (sk_wait_data(sk, &timeo, NULL)) break; } return rc; } static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(skb->sk); if (llc->cmsg_flags & LLC_CMSG_PKTINFO) { struct llc_pktinfo info; memset(&info, 0, sizeof(info)); info.lpi_ifindex = llc_sk(skb->sk)->dev->ifindex; llc_pdu_decode_dsap(skb, &info.lpi_sap); llc_pdu_decode_da(skb, info.lpi_mac); put_cmsg(msg, SOL_LLC, LLC_OPT_PKTINFO, sizeof(info), &info); } } /** * llc_ui_accept - accept a new incoming connection. * @sock: Socket which connections arrive on. * @newsock: Socket to move incoming connection to. * @arg: User specified arguments * * Accept a new incoming connection. * Returns 0 upon success, negative otherwise. */ static int llc_ui_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct sock *sk = sock->sk, *newsk; struct llc_sock *llc, *newllc; struct sk_buff *skb; int rc = -EOPNOTSUPP; dprintk("%s: accepting on %02X\n", __func__, llc_sk(sk)->laddr.lsap); lock_sock(sk); if (unlikely(sk->sk_type != SOCK_STREAM)) goto out; rc = -EINVAL; if (unlikely(sock->state != SS_UNCONNECTED || sk->sk_state != TCP_LISTEN)) goto out; /* wait for a connection to arrive. */ if (skb_queue_empty(&sk->sk_receive_queue)) { rc = llc_wait_data(sk, sk->sk_rcvtimeo); if (rc) goto out; } dprintk("%s: got a new connection on %02X\n", __func__, llc_sk(sk)->laddr.lsap); skb = skb_dequeue(&sk->sk_receive_queue); rc = -EINVAL; if (!skb->sk) goto frees; rc = 0; newsk = skb->sk; /* attach connection to a new socket. */ llc_ui_sk_init(newsock, newsk); sock_reset_flag(newsk, SOCK_ZAPPED); newsk->sk_state = TCP_ESTABLISHED; newsock->state = SS_CONNECTED; llc = llc_sk(sk); newllc = llc_sk(newsk); memcpy(&newllc->addr, &llc->addr, sizeof(newllc->addr)); newllc->link = llc_ui_next_link_no(newllc->laddr.lsap); /* put original socket back into a clean listen state. */ sk->sk_state = TCP_LISTEN; sk_acceptq_removed(sk); dprintk("%s: ok success on %02X, client on %02X\n", __func__, llc_sk(sk)->addr.sllc_sap, newllc->daddr.lsap); frees: kfree_skb(skb); out: release_sock(sk); return rc; } /** * llc_ui_recvmsg - copy received data to the socket user. * @sock: Socket to copy data from. * @msg: Various user space related information. * @len: Size of user buffer. * @flags: User specified flags. * * Copy received data to the socket user. * Returns non-negative upon success, negative otherwise. */ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { DECLARE_SOCKADDR(struct sockaddr_llc *, uaddr, msg->msg_name); const int nonblock = flags & MSG_DONTWAIT; struct sk_buff *skb = NULL; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); size_t copied = 0; u32 peek_seq = 0; u32 *seq, skb_len; unsigned long used; int target; /* Read at least this many bytes */ long timeo; lock_sock(sk); copied = -ENOTCONN; if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN)) goto out; timeo = sock_rcvtimeo(sk, nonblock); seq = &llc->copied_seq; if (flags & MSG_PEEK) { peek_seq = llc->copied_seq; seq = &peek_seq; } target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); copied = 0; do { u32 offset; /* * We need to check signals first, to get correct SIGURG * handling. FIXME: Need to check this doesn't impact 1003.1g * and move it down to the bottom of the loop */ if (signal_pending(current)) { if (copied) break; copied = timeo ? sock_intr_errno(timeo) : -EAGAIN; break; } /* Next get a buffer. */ skb = skb_peek(&sk->sk_receive_queue); if (skb) { offset = *seq; goto found_ok_skb; } /* Well, if we have backlog, try to process it now yet. */ if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { if (sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || !timeo || (flags & MSG_PEEK)) break; } else { if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { copied = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_CLOSE) { if (!sock_flag(sk, SOCK_DONE)) { /* * This occurs when user tries to read * from never connected socket. */ copied = -ENOTCONN; break; } break; } if (!timeo) { copied = -EAGAIN; break; } } if (copied >= target) { /* Do not sleep, just process backlog. */ release_sock(sk); lock_sock(sk); } else sk_wait_data(sk, &timeo, NULL); if ((flags & MSG_PEEK) && peek_seq != llc->copied_seq) { net_dbg_ratelimited("LLC(%s:%d): Application bug, race in MSG_PEEK\n", current->comm, task_pid_nr(current)); peek_seq = llc->copied_seq; } continue; found_ok_skb: skb_len = skb->len; /* Ok so how much can we use? */ used = skb->len - offset; if (len < used) used = len; if (!(flags & MSG_TRUNC)) { int rc = skb_copy_datagram_msg(skb, offset, msg, used); if (rc) { /* Exception. Bailout! */ if (!copied) copied = -EFAULT; break; } } *seq += used; copied += used; len -= used; /* For non stream protcols we get one packet per recvmsg call */ if (sk->sk_type != SOCK_STREAM) goto copy_uaddr; if (!(flags & MSG_PEEK)) { skb_unlink(skb, &sk->sk_receive_queue); kfree_skb(skb); *seq = 0; } /* Partial read */ if (used + offset < skb_len) continue; } while (len > 0); out: release_sock(sk); return copied; copy_uaddr: if (uaddr != NULL && skb != NULL) { memcpy(uaddr, llc_ui_skb_cb(skb), sizeof(*uaddr)); msg->msg_namelen = sizeof(*uaddr); } if (llc_sk(sk)->cmsg_flags) llc_cmsg_rcv(msg, skb); if (!(flags & MSG_PEEK)) { skb_unlink(skb, &sk->sk_receive_queue); kfree_skb(skb); *seq = 0; } goto out; } /** * llc_ui_sendmsg - Transmit data provided by the socket user. * @sock: Socket to transmit data from. * @msg: Various user related information. * @len: Length of data to transmit. * * Transmit data provided by the socket user. * Returns non-negative upon success, negative otherwise. */ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; int rc = -EINVAL, copied = 0, hdrlen, hh_len; struct sk_buff *skb = NULL; struct net_device *dev; size_t size = 0; dprintk("%s: sending from %02X to %02X\n", __func__, llc->laddr.lsap, llc->daddr.lsap); lock_sock(sk); if (addr) { if (msg->msg_namelen < sizeof(*addr)) goto out; } else { if (llc_ui_addr_null(&llc->addr)) goto out; addr = &llc->addr; } /* must bind connection to sap if user hasn't done it. */ if (sock_flag(sk, SOCK_ZAPPED)) { /* bind to sap with null dev, exclusive. */ rc = llc_ui_autobind(sock, addr); if (rc) goto out; } dev = llc->dev; hh_len = LL_RESERVED_SPACE(dev); hdrlen = llc_ui_header_len(sk, addr); size = hdrlen + len; size = min_t(size_t, size, READ_ONCE(dev->mtu)); copied = size - hdrlen; rc = -EINVAL; if (copied < 0) goto out; release_sock(sk); skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc); lock_sock(sk); if (!skb) goto out; if (sock_flag(sk, SOCK_ZAPPED) || llc->dev != dev || hdrlen != llc_ui_header_len(sk, addr) || hh_len != LL_RESERVED_SPACE(dev) || size > READ_ONCE(dev->mtu)) goto out; skb->dev = dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); skb_reserve(skb, hh_len + hdrlen); rc = memcpy_from_msg(skb_put(skb, copied), msg, copied); if (rc) goto out; if (sk->sk_type == SOCK_DGRAM || addr->sllc_ua) { llc_build_and_send_ui_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); skb = NULL; goto out; } if (addr->sllc_test) { llc_build_and_send_test_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); skb = NULL; goto out; } if (addr->sllc_xid) { llc_build_and_send_xid_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); skb = NULL; goto out; } rc = -ENOPROTOOPT; if (!(sk->sk_type == SOCK_STREAM && !addr->sllc_ua)) goto out; rc = llc_ui_send_data(sk, skb, noblock); skb = NULL; out: kfree_skb(skb); if (rc) dprintk("%s: failed sending from %02X to %02X: %d\n", __func__, llc->laddr.lsap, llc->daddr.lsap, rc); release_sock(sk); return rc ? : copied; } /** * llc_ui_getname - return the address info of a socket * @sock: Socket to get address of. * @uaddr: Address structure to return information. * @peer: Does user want local or remote address information. * * Return the address information of a socket. */ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_llc sllc; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); int rc = -EBADF; memset(&sllc, 0, sizeof(sllc)); lock_sock(sk); if (sock_flag(sk, SOCK_ZAPPED)) goto out; if (peer) { rc = -ENOTCONN; if (sk->sk_state != TCP_ESTABLISHED) goto out; if(llc->dev) sllc.sllc_arphrd = llc->dev->type; sllc.sllc_sap = llc->daddr.lsap; memcpy(&sllc.sllc_mac, &llc->daddr.mac, IFHWADDRLEN); } else { rc = -EINVAL; if (!llc->sap) goto out; sllc.sllc_sap = llc->sap->laddr.lsap; if (llc->dev) { sllc.sllc_arphrd = llc->dev->type; memcpy(&sllc.sllc_mac, llc->dev->dev_addr, IFHWADDRLEN); } } sllc.sllc_family = AF_LLC; memcpy(uaddr, &sllc, sizeof(sllc)); rc = sizeof(sllc); out: release_sock(sk); return rc; } /** * llc_ui_ioctl - io controls for PF_LLC * @sock: Socket to get/set info * @cmd: command * @arg: optional argument for cmd * * get/set info on llc sockets */ static int llc_ui_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -ENOIOCTLCMD; } /** * llc_ui_setsockopt - set various connection specific parameters. * @sock: Socket to set options on. * @level: Socket level user is requesting operations on. * @optname: Operation name. * @optval: User provided operation data. * @optlen: Length of optval. * * Set various connection specific parameters. */ static int llc_ui_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); unsigned int opt; int rc = -EINVAL; lock_sock(sk); if (unlikely(level != SOL_LLC || optlen != sizeof(int))) goto out; rc = copy_from_sockptr(&opt, optval, sizeof(opt)); if (rc) goto out; rc = -EINVAL; switch (optname) { case LLC_OPT_RETRY: if (opt > LLC_OPT_MAX_RETRY) goto out; llc->n2 = opt; break; case LLC_OPT_SIZE: if (opt > LLC_OPT_MAX_SIZE) goto out; llc->n1 = opt; break; case LLC_OPT_ACK_TMR_EXP: if (opt > LLC_OPT_MAX_ACK_TMR_EXP) goto out; llc->ack_timer.expire = opt * HZ; break; case LLC_OPT_P_TMR_EXP: if (opt > LLC_OPT_MAX_P_TMR_EXP) goto out; llc->pf_cycle_timer.expire = opt * HZ; break; case LLC_OPT_REJ_TMR_EXP: if (opt > LLC_OPT_MAX_REJ_TMR_EXP) goto out; llc->rej_sent_timer.expire = opt * HZ; break; case LLC_OPT_BUSY_TMR_EXP: if (opt > LLC_OPT_MAX_BUSY_TMR_EXP) goto out; llc->busy_state_timer.expire = opt * HZ; break; case LLC_OPT_TX_WIN: if (opt > LLC_OPT_MAX_WIN) goto out; llc->k = opt; break; case LLC_OPT_RX_WIN: if (opt > LLC_OPT_MAX_WIN) goto out; llc->rw = opt; break; case LLC_OPT_PKTINFO: if (opt) llc->cmsg_flags |= LLC_CMSG_PKTINFO; else llc->cmsg_flags &= ~LLC_CMSG_PKTINFO; break; default: rc = -ENOPROTOOPT; goto out; } rc = 0; out: release_sock(sk); return rc; } /** * llc_ui_getsockopt - get connection specific socket info * @sock: Socket to get information from. * @level: Socket level user is requesting operations on. * @optname: Operation name. * @optval: Variable to return operation data in. * @optlen: Length of optval. * * Get connection specific socket information. */ static int llc_ui_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); int val = 0, len = 0, rc = -EINVAL; lock_sock(sk); if (unlikely(level != SOL_LLC)) goto out; rc = get_user(len, optlen); if (rc) goto out; rc = -EINVAL; if (len != sizeof(int)) goto out; switch (optname) { case LLC_OPT_RETRY: val = llc->n2; break; case LLC_OPT_SIZE: val = llc->n1; break; case LLC_OPT_ACK_TMR_EXP: val = llc->ack_timer.expire / HZ; break; case LLC_OPT_P_TMR_EXP: val = llc->pf_cycle_timer.expire / HZ; break; case LLC_OPT_REJ_TMR_EXP: val = llc->rej_sent_timer.expire / HZ; break; case LLC_OPT_BUSY_TMR_EXP: val = llc->busy_state_timer.expire / HZ; break; case LLC_OPT_TX_WIN: val = llc->k; break; case LLC_OPT_RX_WIN: val = llc->rw; break; case LLC_OPT_PKTINFO: val = (llc->cmsg_flags & LLC_CMSG_PKTINFO) != 0; break; default: rc = -ENOPROTOOPT; goto out; } rc = 0; if (put_user(len, optlen) || copy_to_user(optval, &val, len)) rc = -EFAULT; out: release_sock(sk); return rc; } static const struct net_proto_family llc_ui_family_ops = { .family = PF_LLC, .create = llc_ui_create, .owner = THIS_MODULE, }; static const struct proto_ops llc_ui_ops = { .family = PF_LLC, .owner = THIS_MODULE, .release = llc_ui_release, .bind = llc_ui_bind, .connect = llc_ui_connect, .socketpair = sock_no_socketpair, .accept = llc_ui_accept, .getname = llc_ui_getname, .poll = datagram_poll, .ioctl = llc_ui_ioctl, .listen = llc_ui_listen, .shutdown = llc_ui_shutdown, .setsockopt = llc_ui_setsockopt, .getsockopt = llc_ui_getsockopt, .sendmsg = llc_ui_sendmsg, .recvmsg = llc_ui_recvmsg, .mmap = sock_no_mmap, }; static const char llc_proc_err_msg[] __initconst = KERN_CRIT "LLC: Unable to register the proc_fs entries\n"; static const char llc_sysctl_err_msg[] __initconst = KERN_CRIT "LLC: Unable to register the sysctl entries\n"; static const char llc_sock_err_msg[] __initconst = KERN_CRIT "LLC: Unable to register the network family\n"; static int __init llc2_init(void) { int rc = proto_register(&llc_proto, 0); if (rc != 0) goto out; llc_build_offset_table(); llc_station_init(); llc_ui_sap_last_autoport = LLC_SAP_DYN_START; rc = llc_proc_init(); if (rc != 0) { printk(llc_proc_err_msg); goto out_station; } rc = llc_sysctl_init(); if (rc) { printk(llc_sysctl_err_msg); goto out_proc; } rc = sock_register(&llc_ui_family_ops); if (rc) { printk(llc_sock_err_msg); goto out_sysctl; } llc_add_pack(LLC_DEST_SAP, llc_sap_handler); llc_add_pack(LLC_DEST_CONN, llc_conn_handler); out: return rc; out_sysctl: llc_sysctl_exit(); out_proc: llc_proc_exit(); out_station: llc_station_exit(); proto_unregister(&llc_proto); goto out; } static void __exit llc2_exit(void) { llc_station_exit(); llc_remove_pack(LLC_DEST_SAP); llc_remove_pack(LLC_DEST_CONN); sock_unregister(PF_LLC); llc_proc_exit(); llc_sysctl_exit(); proto_unregister(&llc_proto); } module_init(llc2_init); module_exit(llc2_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Procom 1997, Jay Schullist 2001, Arnaldo C. Melo 2001-2003"); MODULE_DESCRIPTION("IEEE 802.2 PF_LLC support"); MODULE_ALIAS_NETPROTO(PF_LLC); |
| 422 117 117 411 424 2 509 760 137 4 134 137 136 2 4 2 761 760 14 12 747 509 277 680 684 677 85 684 678 163 163 4 163 2 2 2 5 5 5 5 5 86 85 86 86 86 72 763 72 5 119 116 105 758 172 761 2 2 764 757 664 102 755 730 14 754 119 755 119 757 758 764 115 761 765 759 802 237 236 230 175 176 163 142 135 1306 1310 1311 1313 849 1320 1304 1298 1320 858 761 766 3 3 1 5 5 5 19 19 19 37 37 37 37 150 5 5 5 5 47 5 5 5 5 5 7 7 7 7 7 15 15 15 15 5 5 5 5 15 15 15 15 15 20 18 18 19 1 20 20 19 20 15 5 5 5 5 5 14 15 5 15 5 5 5 5 5 5 5 5 5 3 3 3 3 3 3 3 3 1336 1334 204 1259 19 19 1243 1337 833 1340 1338 391 390 390 391 191 913 913 314 911 5 1339 1341 1333 1303 1309 1300 165 1295 1299 434 1299 192 1304 1275 1274 196 195 196 1234 1123 1100 1214 1280 1231 1232 1237 1239 1235 1226 1236 15 15 15 14 93 93 93 497 501 403 379 378 379 500 396 389 368 394 412 415 416 134 92 93 91 416 9 9 14 16 14 2 2 370 369 370 366 286 284 285 286 298 300 300 299 299 299 298 300 299 300 300 300 298 300 298 299 299 298 298 299 300 22 1 365 283 286 286 168 168 168 201 286 81 170 5 203 13 2 13 2 13 14 14 14 13 14 14 14 14 14 5 9 9 1 14 14 14 14 13 14 14 14 14 14 14 14 14 14 14 14 14 6 14 14 14 14 30 30 165 165 164 163 150 165 27 27 16 16 16 16 16 27 5 5 5 5 5 4 4 4 4 13 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/dcache.c * * Complete reimplementation * (C) 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ /* * Notes on the allocation strategy: * * The dcache is a master of the icache - whenever a dcache entry * exists, the inode will always exist. "iput()" is done either when * the dcache entry is deleted or garbage collected. */ #include <linux/ratelimit.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/cache.h> #include <linux/export.h> #include <linux/security.h> #include <linux/seqlock.h> #include <linux/memblock.h> #include <linux/bit_spinlock.h> #include <linux/rculist_bl.h> #include <linux/list_lru.h> #include "internal.h" #include "mount.h" #include <asm/runtime-const.h> /* * Usage: * dcache->d_inode->i_lock protects: * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_roots bl list spinlock protects: * - the s_roots list (see __d_drop) * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags * - d_name * - d_lru * - d_count * - d_unhashed() * - d_parent and d_chilren * - childrens' d_sib and d_parent * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock * dentry->d_lock * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_roots lock * * If there is an ancestor relationship: * dentry->d_parent->...->d_parent->d_lock * ... * dentry->d_parent->d_lock * dentry->d_lock * * If no ancestor relationship: * arbitrary, since it's serialized on rename_lock */ int sysctl_vfs_cache_pressure __read_mostly = 100; EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __ro_after_init; const struct qstr empty_name = QSTR_INIT("", 0); EXPORT_SYMBOL(empty_name); const struct qstr slash_name = QSTR_INIT("/", 1); EXPORT_SYMBOL(slash_name); const struct qstr dotdot_name = QSTR_INIT("..", 2); EXPORT_SYMBOL(dotdot_name); /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try * to make this good - I've just made it work. * * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. * * Marking the variables "used" ensures that the compiler doesn't * optimize them away completely on architectures with runtime * constant infrastructure, this allows debuggers to see their * values. But updating these values has no effect on those arches. */ static unsigned int d_hash_shift __ro_after_init __used; static struct hlist_bl_head *dentry_hashtable __ro_after_init __used; static inline struct hlist_bl_head *d_hash(unsigned long hashlen) { return runtime_const_ptr(dentry_hashtable) + runtime_const_shift_right_32(hashlen, d_hash_shift); } #define IN_LOOKUP_SHIFT 10 static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT]; static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } struct dentry_stat_t { long nr_dentry; long nr_unused; long age_limit; /* age in seconds */ long want_pages; /* pages requested by system */ long nr_negative; /* # of unused negative dentries */ long dummy; /* Reserved for future use */ }; static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* Statistics gathering. */ static struct dentry_stat_t dentry_stat = { .age_limit = 45, }; /* * Here we resort to our own counters instead of using generic per-cpu counters * for consistency with what the vfs inode code does. We are expected to harvest * better code and performance by having our own specialized counters. * * Please note that the loop is done over all possible CPUs, not over all online * CPUs. The reason for this is that we don't want to play games with CPUs going * on and off. If one of them goes off, we will just keep their counters. * * glommer: See cffbc8a for details, and if you ever intend to change this, * please update all vfs counters to match. */ static long get_nr_dentry(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_unused, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_negative(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_negative, i); return sum < 0 ? 0 : sum; } static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table fs_dcache_sysctls[] = { { .procname = "dentry-state", .data = &dentry_stat, .maxlen = 6*sizeof(long), .mode = 0444, .proc_handler = proc_nr_dentry, }, }; static int __init init_fs_dcache_sysctls(void) { register_sysctl_init("fs", fs_dcache_sysctls); return 0; } fs_initcall(init_fs_dcache_sysctls); #endif /* * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> /* * NOTE! 'cs' and 'scount' come from a dentry, so it has a * aligned allocation for this particular component. We don't * strictly need the load_unaligned_zeropad() safety, but it * doesn't hurt either. * * In contrast, 'ct' and 'tcount' can be from a pathname, and do * need the careful unaligned handling. */ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { unsigned long a,b,mask; for (;;) { a = read_word_at_a_time(cs); b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) return 1; cs += sizeof(unsigned long); ct += sizeof(unsigned long); tcount -= sizeof(unsigned long); if (!tcount) return 0; } mask = bytemask_from_count(tcount); return unlikely(!!((a ^ b) & mask)); } #else static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { do { if (*cs != *ct) return 1; cs++; ct++; tcount--; } while (tcount); return 0; } #endif static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) { /* * Be careful about RCU walk racing with rename: * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The * RCU walk will check the sequence count eventually, * and catch it. And we won't overrun the buffer, * because we're reading the name pointer atomically, * and a dentry name is guaranteed to be properly * terminated with a NUL byte. * * End result: even if 'len' is wrong, we'll exit * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } struct external_name { union { atomic_t count; struct rcu_head head; } u; unsigned char name[]; }; static inline struct external_name *external_name(struct dentry *dentry) { return container_of(dentry->d_name.name, struct external_name, name[0]); } static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kmem_cache_free(dentry_cache, dentry); } static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) { return dentry->d_name.name != dentry->d_iname; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { spin_lock(&dentry->d_lock); name->name = dentry->d_name; if (unlikely(dname_external(dentry))) { atomic_inc(&external_name(dentry)->u.count); } else { memcpy(name->inline_name, dentry->d_iname, dentry->d_name.len + 1); name->name.name = name->inline_name; } spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { if (unlikely(name->name.name != name->inline_name)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->u.count))) kfree_rcu(p, u.head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) { unsigned flags; dentry->d_inode = inode; flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; flags |= type_flags; smp_store_release(&dentry->d_flags, flags); } static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; /* * The negative counter only tracks dentries on the LRU. Don't inc if * d_lru is on another list. */ if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) { WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); if (likely(atomic_dec_and_test(&p->u.count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } } /* if dentry was never visible to RCU, immediate free is OK */ if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. */ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_lock) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) fsnotify_inoderemove(inode); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else iput(inode); } /* * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry * is in use - which includes both the "real" per-superblock * LRU list _and_ the DCACHE_SHRINK_LIST use. * * The DCACHE_SHRINK_LIST bit is set whenever the dentry is * on the shrink list (ie not on the superblock LRU list). * * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * * The per-cpu "nr_dentry_negative" counters are only updated * when deleted from or added to the per-superblock LRU list, not * from/to the shrink list. That is to avoid an unneeded dec/inc * pair when moving from LRU to shrink list in select_collect(). * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ #define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x)) static void d_lru_add(struct dentry *dentry) { D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_lru_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_shrink_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); list_del_init(&dentry->d_lru); dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); this_cpu_dec(nr_dentry_unused); } static void d_shrink_add(struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, 0); list_add(&dentry->d_lru, list); dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); } /* * These can only be called under the global LRU lock, ie during the * callback for freeing the LRU list. "isolate" removes it from the * LRU lists entirely, while shrink_move moves it to the indicated * private list. */ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } static void ___d_drop(struct dentry *dentry) { struct hlist_bl_head *b; /* * Hashed dentries are normally on the dentry hashtable, * with the exception of those newly allocated by * d_obtain_root, which are always IS_ROOT: */ if (unlikely(IS_ROOT(dentry))) b = &dentry->d_sb->s_roots; else b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); hlist_bl_unlock(b); } void __d_drop(struct dentry *dentry) { if (!d_unhashed(dentry)) { ___d_drop(dentry); dentry->d_hash.pprev = NULL; write_seqcount_invalidate(&dentry->d_seq); } } EXPORT_SYMBOL(__d_drop); /** * d_drop - drop a dentry * @dentry: dentry to drop * * d_drop() unhashes the entry from the parent dentry hashes, so that it won't * be found through a VFS lookup any more. Note that this is different from * deleting the dentry - d_delete will try to mark the dentry negative if * possible, giving a successful _negative_ lookup, while d_drop will * just make the cache lookup fail. * * d_drop() is used mainly for stuff that wants to invalidate a dentry for some * reason (NFS timeouts or autofs deletes). * * __d_drop requires dentry->d_lock * * ___d_drop doesn't mark dentry as "unhashed" * (dentry->d_hash.pprev will be LIST_POISON2, not NULL). */ void d_drop(struct dentry *dentry) { spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_drop); static inline void dentry_unlist(struct dentry *dentry) { struct dentry *next; /* * Inform d_walk() and shrink_dentry_list() that we are no longer * attached to the dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; if (unlikely(hlist_unhashed(&dentry->d_sib))) return; __hlist_del(&dentry->d_sib); /* * Cursors can move around the list of children. While we'd been * a normal list member, it didn't matter - ->d_sib.next would've * been updated. However, from now on it won't be and for the * things like d_walk() it might end up with a nasty surprise. * Normally d_walk() doesn't care about cursors moving around - * ->d_lock on parent prevents that and since a cursor has no children * of its own, we get through it without ever unlocking the parent. * There is one exception, though - if we ascend from a child that * gets killed as soon as we unlock it, the next sibling is found * using the value left in its ->d_sib.next. And if _that_ * pointed to a cursor, and cursor got moved (e.g. by lseek()) * before d_walk() regains parent->d_lock, we'll end up skipping * everything the cursor had been moved past. * * Solution: make sure that the pointer left behind in ->d_sib.next * points to something that won't be moving around. I.e. skip the * cursors. */ while (dentry->d_sib.next) { next = hlist_entry(dentry->d_sib.next, struct dentry, d_sib); if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) break; dentry->d_sib.next = next->d_sib.next; } } static struct dentry *__dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; bool can_free = true; /* * The dentry is now unrecoverably dead to the world. */ lockref_mark_dead(&dentry->d_lockref); /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. */ if (dentry->d_flags & DCACHE_OP_PRUNE) dentry->d_op->d_prune(dentry); if (dentry->d_flags & DCACHE_LRU_LIST) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) d_lru_del(dentry); } /* if it was on the hash then remove it */ __d_drop(dentry); if (dentry->d_inode) dentry_unlink_inode(dentry); else spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); cond_resched(); /* now that it's negative, ->d_parent is stable */ if (!IS_ROOT(dentry)) { parent = dentry->d_parent; spin_lock(&parent->d_lock); } spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry_unlist(dentry); if (dentry->d_flags & DCACHE_SHRINK_LIST) can_free = false; spin_unlock(&dentry->d_lock); if (likely(can_free)) dentry_free(dentry); if (parent && --parent->d_lockref.count) { spin_unlock(&parent->d_lock); return NULL; } return parent; } /* * Lock a dentry for feeding it to __dentry_kill(). * Called under rcu_read_lock() and dentry->d_lock; the former * guarantees that nothing we access will be freed under us. * Note that dentry is *not* protected from concurrent dentry_kill(), * d_delete(), etc. * * Return false if dentry is busy. Otherwise, return true and have * that dentry's inode locked. */ static bool lock_for_kill(struct dentry *dentry) { struct inode *inode = dentry->d_inode; if (unlikely(dentry->d_lockref.count)) return false; if (!inode || likely(spin_trylock(&inode->i_lock))) return true; do { spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); if (likely(inode == dentry->d_inode)) break; spin_unlock(&inode->i_lock); inode = dentry->d_inode; } while (inode); if (likely(!dentry->d_lockref.count)) return true; if (inode) spin_unlock(&inode->i_lock); return false; } /* * Decide if dentry is worth retaining. Usually this is called with dentry * locked; if not locked, we are more limited and might not be able to tell * without a lock. False in this case means "punt to locked path and recheck". * * In case we aren't locked, these predicates are not "stable". However, it is * sufficient that at some point after we dropped the reference the dentry was * hashed and the flags had the proper value. Other dentry users may have * re-gotten a reference to the dentry and change that, but our work is done - * we can leave the dentry around with a zero refcount. */ static inline bool retain_dentry(struct dentry *dentry, bool locked) { unsigned int d_flags; smp_rmb(); d_flags = READ_ONCE(dentry->d_flags); // Unreachable? Nobody would be able to look it up, no point retaining if (unlikely(d_unhashed(dentry))) return false; // Same if it's disconnected if (unlikely(d_flags & DCACHE_DISCONNECTED)) return false; // ->d_delete() might tell us not to bother, but that requires // ->d_lock; can't decide without it if (unlikely(d_flags & DCACHE_OP_DELETE)) { if (!locked || dentry->d_op->d_delete(dentry)) return false; } // Explicitly told not to bother if (unlikely(d_flags & DCACHE_DONTCACHE)) return false; // At this point it looks like we ought to keep it. We also might // need to do something - put it on LRU if it wasn't there already // and mark it referenced if it was on LRU, but not marked yet. // Unfortunately, both actions require ->d_lock, so in lockless // case we'd have to punt rather than doing those. if (unlikely(!(d_flags & DCACHE_LRU_LIST))) { if (!locked) return false; d_lru_add(dentry); } else if (unlikely(!(d_flags & DCACHE_REFERENCED))) { if (!locked) return false; dentry->d_flags |= DCACHE_REFERENCED; } return true; } void d_mark_dontcache(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) { spin_lock(&de->d_lock); de->d_flags |= DCACHE_DONTCACHE; spin_unlock(&de->d_lock); } inode->i_state |= I_DONTCACHE; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_mark_dontcache); /* * Try to do a lockless dput(), and return whether that was successful. * * If unsuccessful, we return false, having already taken the dentry lock. * In that case refcount is guaranteed to be zero and we have already * decided that it's not worth keeping around. * * The caller needs to hold the RCU read lock, so that the dentry is * guaranteed to stay around even if the refcount goes down to zero! */ static inline bool fast_dput(struct dentry *dentry) { int ret; /* * try to decrement the lockref optimistically. */ ret = lockref_put_return(&dentry->d_lockref); /* * If the lockref_put_return() failed due to the lock being held * by somebody else, the fast path has failed. We will need to * get the lock, and then check the count again. */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } dentry->d_lockref.count--; goto locked; } /* * If we weren't the last ref, we're done. */ if (ret) return true; /* * Can we decide that decrement of refcount is all we needed without * taking the lock? There's a very common case when it's all we need - * dentry looks like it ought to be retained and there's nothing else * to do. */ if (retain_dentry(dentry, false)) return true; /* * Either not worth retaining or we can't tell without the lock. * Get the lock, then. We've already decremented the refcount to 0, * but we'll need to re-check the situation after getting the lock. */ spin_lock(&dentry->d_lock); /* * Did somebody else grab a reference to it in the meantime, and * we're no longer the last user after all? Alternatively, somebody * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ locked: if (dentry->d_lockref.count || retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return true; } return false; } /* * This is dput * * This is complicated by the fact that we do not want to put * dentries that are no longer on any hash chain on the unused * list: we'd much rather just get rid of them immediately. * * However, that implies that we have to traverse the dentry * tree upwards to the parents which might _also_ now be * scheduled for deletion (it may have been only waiting for * its last child to go away). * * This tail recursion is done by hand as we don't want to depend * on the compiler to always get this right (gcc generally doesn't). * Real recursion would eat up our stack space. */ /* * dput - release a dentry * @dentry: dentry to release * * Release a dentry. This will drop the usage count and if appropriate * call the dentry unlink method as well as removing it from the queues and * releasing its resources. If the parent dentries were scheduled for release * they too may now get deleted. */ void dput(struct dentry *dentry) { if (!dentry) return; might_sleep(); rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } while (lock_for_kill(dentry)) { rcu_read_unlock(); dentry = __dentry_kill(dentry); if (!dentry) return; if (retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return; } rcu_read_lock(); } rcu_read_unlock(); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(dput); static void to_shrink_list(struct dentry *dentry, struct list_head *list) __must_hold(&dentry->d_lock) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); d_shrink_add(dentry, list); } } void dput_to_list(struct dentry *dentry, struct list_head *list) { rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } rcu_read_unlock(); to_shrink_list(dentry, list); spin_unlock(&dentry->d_lock); } struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } repeat: /* * Don't need rcu_dereference because we re-check it was correct under * the lock. */ rcu_read_lock(); ret = dentry->d_parent; spin_lock(&ret->d_lock); if (unlikely(ret != dentry->d_parent)) { spin_unlock(&ret->d_lock); rcu_read_unlock(); goto repeat; } rcu_read_unlock(); BUG_ON(!ret->d_lockref.count); ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } EXPORT_SYMBOL(dget_parent); static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; if (hlist_empty(&inode->i_dentry)) return NULL; alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); lockref_get(&alias->d_lockref); return alias; } /** * d_find_any_alias - find any alias for a given inode * @inode: inode to find an alias for * * If any aliases exist for the given inode, take and return a * reference for one of them. If no aliases exist, return %NULL. */ struct dentry *d_find_any_alias(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); de = __d_find_any_alias(inode); spin_unlock(&inode->i_lock); return de; } EXPORT_SYMBOL(d_find_any_alias); static struct dentry *__d_find_alias(struct inode *inode) { struct dentry *alias; if (S_ISDIR(inode->i_mode)) return __d_find_any_alias(inode); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { dget_dlock(alias); spin_unlock(&alias->d_lock); return alias; } spin_unlock(&alias->d_lock); } return NULL; } /** * d_find_alias - grab a hashed alias of inode * @inode: inode in question * * If inode has a hashed alias, or is a directory and has any alias, * acquire the reference to alias and return it. Otherwise return NULL. * Notice that if inode is a directory there can be only one alias and * it can be unhashed only if it has no children, or if it is the root * of a filesystem, or if the directory was renamed and d_revalidate * was the first vfs operation to notice. * * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer * any other hashed alias over that one. */ struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); de = __d_find_alias(inode); spin_unlock(&inode->i_lock); } return de; } EXPORT_SYMBOL(d_find_alias); /* * Caller MUST be holding rcu_read_lock() and be guaranteed * that inode won't get freed until rcu_read_unlock(). */ struct dentry *d_find_alias_rcu(struct inode *inode) { struct hlist_head *l = &inode->i_dentry; struct dentry *de = NULL; spin_lock(&inode->i_lock); // ->i_dentry and ->i_rcu are colocated, but the latter won't be // used without having I_FREEING set, which means no aliases left if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) { if (S_ISDIR(inode->i_mode)) { de = hlist_entry(l->first, struct dentry, d_u.d_alias); } else { hlist_for_each_entry(de, l, d_u.d_alias) if (!d_unhashed(de)) break; } } spin_unlock(&inode->i_lock); return de; } /* * Try to kill dentries associated with this inode. * WARNING: you must own a reference to inode. */ void d_prune_aliases(struct inode *inode) { LIST_HEAD(dispose); struct dentry *dentry; spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) to_shrink_list(dentry, &dispose); spin_unlock(&dentry->d_lock); } spin_unlock(&inode->i_lock); shrink_dentry_list(&dispose); } EXPORT_SYMBOL(d_prune_aliases); static inline void shrink_kill(struct dentry *victim) { do { rcu_read_unlock(); victim = __dentry_kill(victim); rcu_read_lock(); } while (victim && lock_for_kill(victim)); rcu_read_unlock(); if (victim) spin_unlock(&victim->d_lock); } void shrink_dentry_list(struct list_head *list) { while (!list_empty(list)) { struct dentry *dentry; dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); rcu_read_lock(); if (!lock_for_kill(dentry)) { bool can_free; rcu_read_unlock(); d_shrink_del(dentry); can_free = dentry->d_flags & DCACHE_DENTRY_KILLED; spin_unlock(&dentry->d_lock); if (can_free) dentry_free(dentry); continue; } d_shrink_del(dentry); shrink_kill(dentry); } } static enum lru_status dentry_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; /* * Referenced dentries are still in use. If they have active * counts, just remove them from the LRU. Otherwise give them * another pass through the LRU. */ if (dentry->d_lockref.count) { d_lru_isolate(lru, dentry); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } if (dentry->d_flags & DCACHE_REFERENCED) { dentry->d_flags &= ~DCACHE_REFERENCED; spin_unlock(&dentry->d_lock); /* * The list move itself will be made by the common LRU code. At * this point, we've dropped the dentry->d_lock but keep the * lru lock. This is safe to do, since every list movement is * protected by the lru lock even if both locks are held. * * This is guaranteed by the fact that all LRU management * functions are intermediated by the LRU API calls like * list_lru_add_obj and list_lru_del_obj. List movement in this file * only ever occur through this functions or through callbacks * like this one, that are called from the LRU API. * * The only exceptions to this are functions like * shrink_dentry_list, and code that first checks for the * DCACHE_SHRINK_LIST flag. Those are guaranteed to be * operating only with stack provided lists after they are * properly isolated from the main list. It is thus, always a * local access. */ return LRU_ROTATE; } d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * prune_dcache_sb - shrink the dcache * @sb: superblock * @sc: shrink control, passed to list_lru_shrink_walk() * * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This * is done when we need more memory and called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(dispose); long freed; freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc, dentry_lru_isolate, &dispose); shrink_dentry_list(&dispose); return freed; } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock * * Shrink the dcache for the specified super block. This is used to free * the dcache before unmounting a file system. */ void shrink_dcache_sb(struct super_block *sb) { do { LIST_HEAD(dispose); list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); /** * enum d_walk_ret - action to talke during tree walk * @D_WALK_CONTINUE: contrinue walk * @D_WALK_QUIT: quit walk * @D_WALK_NORETRY: quit when retry is needed * @D_WALK_SKIP: skip this dentry and its children */ enum d_walk_ret { D_WALK_CONTINUE, D_WALK_QUIT, D_WALK_NORETRY, D_WALK_SKIP, }; /** * d_walk - walk the dentry tree * @parent: start of walk * @data: data passed to @enter() and @finish() * @enter: callback when first entering the dentry * * The @enter() callbacks are called with d_lock held. */ static void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent, *dentry; unsigned seq = 0; enum d_walk_ret ret; bool retry = true; again: read_seqbegin_or_lock(&rename_lock, &seq); this_parent = parent; spin_lock(&this_parent->d_lock); ret = enter(data, this_parent); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: case D_WALK_SKIP: goto out_unlock; case D_WALK_NORETRY: retry = false; break; } repeat: dentry = d_first_child(this_parent); resume: hlist_for_each_entry_from(dentry, d_sib) { if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: spin_unlock(&dentry->d_lock); goto out_unlock; case D_WALK_NORETRY: retry = false; break; case D_WALK_SKIP: spin_unlock(&dentry->d_lock); continue; } if (!hlist_empty(&dentry->d_children)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ rcu_read_lock(); ascend: if (this_parent != parent) { dentry = this_parent; this_parent = dentry->d_parent; spin_unlock(&dentry->d_lock); spin_lock(&this_parent->d_lock); /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; /* go into the first sibling still alive */ hlist_for_each_entry_continue(dentry, d_sib) { if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) { rcu_read_unlock(); goto resume; } } goto ascend; } if (need_seqretry(&rename_lock, seq)) goto rename_retry; rcu_read_unlock(); out_unlock: spin_unlock(&this_parent->d_lock); done_seqretry(&rename_lock, seq); return; rename_retry: spin_unlock(&this_parent->d_lock); rcu_read_unlock(); BUG_ON(seq & 1); if (!retry) return; seq = 1; goto again; } struct check_mount { struct vfsmount *mnt; unsigned int mounted; }; static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry) { struct check_mount *info = data; struct path path = { .mnt = info->mnt, .dentry = dentry }; if (likely(!d_mountpoint(dentry))) return D_WALK_CONTINUE; if (__path_is_mountpoint(&path)) { info->mounted = 1; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * path_has_submounts - check for mounts over a dentry in the * current namespace. * @parent: path to check. * * Return true if the parent or its subdirectories contain * a mount point in the current namespace. */ int path_has_submounts(const struct path *parent) { struct check_mount data = { .mnt = parent->mnt, .mounted = 0 }; read_seqlock_excl(&mount_lock); d_walk(parent->dentry, &data, path_check_mount); read_sequnlock_excl(&mount_lock); return data.mounted; } EXPORT_SYMBOL(path_has_submounts); /* * Called by mount code to set a mountpoint and check if the mountpoint is * reachable (e.g. NFS can unhash a directory dentry and then the complete * subtree can become unreachable). * * Only one of d_invalidate() and d_set_mounted() must succeed. For * this reason take rename_lock and d_lock on dentry and ancestors. */ int d_set_mounted(struct dentry *dentry) { struct dentry *p; int ret = -ENOENT; write_seqlock(&rename_lock); for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) { /* Need exclusion wrt. d_invalidate() */ spin_lock(&p->d_lock); if (unlikely(d_unhashed(p))) { spin_unlock(&p->d_lock); goto out; } spin_unlock(&p->d_lock); } spin_lock(&dentry->d_lock); if (!d_unlinked(dentry)) { ret = -EBUSY; if (!d_mountpoint(dentry)) { dentry->d_flags |= DCACHE_MOUNTED; ret = 0; } } spin_unlock(&dentry->d_lock); out: write_sequnlock(&rename_lock); return ret; } /* * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level * whenever the d_children list is non-empty and continue * searching. * * It returns zero iff there are no unused children, * otherwise it returns the number of children moved to * the end of the unused list. This may not be the total * number of unused children, because select_parent can * drop the lock and return early due to latency * constraints. */ struct select_data { struct dentry *start; union { long found; struct dentry *victim; }; struct list_head dispose; }; static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; } else if (!dentry->d_lockref.count) { to_shrink_list(dentry, &data->dispose); data->found++; } else if (dentry->d_lockref.count < 0) { data->found++; } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (!dentry->d_lockref.count) { if (dentry->d_flags & DCACHE_SHRINK_LIST) { rcu_read_lock(); data->victim = dentry; return D_WALK_QUIT; } to_shrink_list(dentry, &data->dispose); } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } /** * shrink_dcache_parent - prune dcache * @parent: parent of entries to prune * * Prune the dcache to remove unused children of the parent dentry. */ void shrink_dcache_parent(struct dentry *parent) { for (;;) { struct select_data data = {.start = parent}; INIT_LIST_HEAD(&data.dispose); d_walk(parent, &data, select_collect); if (!list_empty(&data.dispose)) { shrink_dentry_list(&data.dispose); continue; } cond_resched(); if (!data.found) break; data.victim = NULL; d_walk(parent, &data, select_collect2); if (data.victim) { spin_lock(&data.victim->d_lock); if (!lock_for_kill(data.victim)) { spin_unlock(&data.victim->d_lock); rcu_read_unlock(); } else { shrink_kill(data.victim); } } if (!list_empty(&data.dispose)) shrink_dentry_list(&data.dispose); } } EXPORT_SYMBOL(shrink_dcache_parent); static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { /* it has busy descendents; complain about those instead */ if (!hlist_empty(&dentry->d_children)) return D_WALK_CONTINUE; /* root with refcount 1 is fine */ if (dentry == _data && dentry->d_lockref.count == 1) return D_WALK_CONTINUE; WARN(1, "BUG: Dentry %p{i=%lx,n=%pd} " " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : 0UL, dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); return D_WALK_CONTINUE; } static void do_one_tree(struct dentry *dentry) { shrink_dcache_parent(dentry); d_walk(dentry, dentry, umount_check); d_drop(dentry); dput(dentry); } /* * destroy the dentries attached to a superblock on unmounting */ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; rwsem_assert_held_write(&sb->s_umount); dentry = sb->s_root; sb->s_root = NULL; do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_roots)) { dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash)); do_one_tree(dentry); } } static enum d_walk_ret find_submount(void *_data, struct dentry *dentry) { struct dentry **victim = _data; if (d_mountpoint(dentry)) { *victim = dget_dlock(dentry); return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * d_invalidate - detach submounts, prune dcache, and drop * @dentry: dentry to invalidate (aka detach, prune and drop) */ void d_invalidate(struct dentry *dentry) { bool had_submounts = false; spin_lock(&dentry->d_lock); if (d_unhashed(dentry)) { spin_unlock(&dentry->d_lock); return; } __d_drop(dentry); spin_unlock(&dentry->d_lock); /* Negative dentries can be dropped without further checks */ if (!dentry->d_inode) return; shrink_dcache_parent(dentry); for (;;) { struct dentry *victim = NULL; d_walk(dentry, &victim, find_submount); if (!victim) { if (had_submounts) shrink_dcache_parent(dentry); return; } had_submounts = true; detach_mounts(victim); dput(victim); } } EXPORT_SYMBOL(d_invalidate); /** * __d_alloc - allocate a dcache entry * @sb: filesystem it will belong to * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { struct dentry *dentry; char *dname; int err; dentry = kmem_cache_alloc_lru(dentry_cache, &sb->s_dentry_lru, GFP_KERNEL); if (!dentry) return NULL; /* * We guarantee that the inline name is always NUL-terminated. * This way the memcpy() done by the name switching in rename * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; dname = dentry->d_iname; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; } atomic_set(&p->u.count, 1); dname = p->name; } else { dname = dentry->d_iname; } dentry->d_name.len = name->len; dentry->d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ dentry->d_lockref.count = 1; dentry->d_flags = 0; spin_lock_init(&dentry->d_lock); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; dentry->d_sb = sb; dentry->d_op = NULL; dentry->d_fsdata = NULL; INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_HLIST_HEAD(&dentry->d_children); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_HLIST_NODE(&dentry->d_sib); d_set_d_op(dentry, dentry->d_sb->s_d_op); if (dentry->d_op && dentry->d_op->d_init) { err = dentry->d_op->d_init(dentry); if (err) { if (dname_external(dentry)) kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); return NULL; } } this_cpu_inc(nr_dentry); return dentry; } /** * d_alloc - allocate a dcache entry * @parent: parent of entry to allocate * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) { struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject * to concurrency here */ dentry->d_parent = dget_dlock(parent); hlist_add_head(&dentry->d_sib, &parent->d_children); spin_unlock(&parent->d_lock); return dentry; } EXPORT_SYMBOL(d_alloc); struct dentry *d_alloc_anon(struct super_block *sb) { return __d_alloc(sb, NULL); } EXPORT_SYMBOL(d_alloc_anon); struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; } /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock * @name: qstr of the name * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. * This is used for pipes, sockets et.al. - the stuff that should * never be anyone's children or parents. Unlike all other * dentries, these will not have RCU delay between dropping the * last reference and freeing them. * * The only user is alloc_file_pseudo() and that's what should * be considered a public interface. Don't use directly. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; struct dentry *dentry = __d_alloc(sb, name); if (likely(dentry)) { dentry->d_flags |= DCACHE_NORCU; if (!sb->s_d_op) d_set_d_op(dentry, &anon_ops); } return dentry; } struct dentry *d_alloc_name(struct dentry *parent, const char *name) { struct qstr q; q.name = name; q.hash_len = hashlen_string(parent, name); return d_alloc(parent, &q); } EXPORT_SYMBOL(d_alloc_name); void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) { WARN_ON_ONCE(dentry->d_op); WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH | DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | DCACHE_OP_REAL)); dentry->d_op = op; if (!op) return; if (op->d_hash) dentry->d_flags |= DCACHE_OP_HASH; if (op->d_compare) dentry->d_flags |= DCACHE_OP_COMPARE; if (op->d_revalidate) dentry->d_flags |= DCACHE_OP_REVALIDATE; if (op->d_weak_revalidate) dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE; if (op->d_delete) dentry->d_flags |= DCACHE_OP_DELETE; if (op->d_prune) dentry->d_flags |= DCACHE_OP_PRUNE; if (op->d_real) dentry->d_flags |= DCACHE_OP_REAL; } EXPORT_SYMBOL(d_set_d_op); static unsigned d_flags_for_inode(struct inode *inode) { unsigned add_flags = DCACHE_REGULAR_TYPE; if (!inode) return DCACHE_MISS_TYPE; if (S_ISDIR(inode->i_mode)) { add_flags = DCACHE_DIRECTORY_TYPE; if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) { if (unlikely(!inode->i_op->lookup)) add_flags = DCACHE_AUTODIR_TYPE; else inode->i_opflags |= IOP_LOOKUP; } goto type_determined; } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } inode->i_opflags |= IOP_NOFOLLOW; } if (unlikely(!S_ISREG(inode->i_mode))) add_flags = DCACHE_SPECIAL_TYPE; type_determined: if (unlikely(IS_AUTOMOUNT(inode))) add_flags |= DCACHE_NEED_AUTOMOUNT; return add_flags; } static void __d_instantiate(struct dentry *dentry, struct inode *inode) { unsigned add_flags = d_flags_for_inode(inode); WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); /* * The negative counter only tracks dentries on the LRU. Don't dec if * d_lru is on another list. */ if ((dentry->d_flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); spin_unlock(&dentry->d_lock); } /** * d_instantiate - fill in inode information for a dentry * @entry: dentry to complete * @inode: inode to attach to this dentry * * Fill in inode information in the entry. * * This turns negative dentries into productive full members * of society. * * NOTE! This assumes that the inode count has been incremented * (or otherwise set) by the caller to indicate that it is now * in use by the dcache. */ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_instantiate); /* * This should be equivalent to d_instantiate() + unlock_new_inode(), * with lockdep-related part of unlock_new_inode() done before * anything else. Use that instead of open-coding d_instantiate()/ * unlock_new_inode() combinations. */ void d_instantiate_new(struct dentry *entry, struct inode *inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); BUG_ON(!inode); lockdep_annotate_inode_mutex_key(inode); security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; /* * Pairs with the barrier in prepare_to_wait_event() to make sure * ___wait_var_event() either sees the bit cleared or * waitqueue_active() check in wake_up_var() sees the waiter. */ smp_mb(); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); struct dentry *d_make_root(struct inode *root_inode) { struct dentry *res = NULL; if (root_inode) { res = d_alloc_anon(root_inode->i_sb); if (res) d_instantiate(res, root_inode); else iput(root_inode); } return res; } EXPORT_SYMBOL(d_make_root); static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected) { struct super_block *sb; struct dentry *new, *res; if (!inode) return ERR_PTR(-ESTALE); if (IS_ERR(inode)) return ERR_CAST(inode); sb = inode->i_sb; res = d_find_any_alias(inode); /* existing alias? */ if (res) goto out; new = d_alloc_anon(sb); if (!new) { res = ERR_PTR(-ENOMEM); goto out; } security_d_instantiate(new, inode); spin_lock(&inode->i_lock); res = __d_find_any_alias(inode); /* recheck under lock */ if (likely(!res)) { /* still no alias, attach a disconnected dentry */ unsigned add_flags = d_flags_for_inode(inode); if (disconnected) add_flags |= DCACHE_DISCONNECTED; spin_lock(&new->d_lock); __d_set_inode_and_type(new, inode, add_flags); hlist_add_head(&new->d_u.d_alias, &inode->i_dentry); if (!disconnected) { hlist_bl_lock(&sb->s_roots); hlist_bl_add_head(&new->d_hash, &sb->s_roots); hlist_bl_unlock(&sb->s_roots); } spin_unlock(&new->d_lock); spin_unlock(&inode->i_lock); inode = NULL; /* consumed by new->d_inode */ res = new; } else { spin_unlock(&inode->i_lock); dput(new); } out: iput(inode); return res; } /** * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain a dentry for an inode resulting from NFS filehandle conversion or * similar open by handle operations. The returned dentry may be anonymous, * or may have a full name (if the inode was already in the cache). * * When called on a directory inode, we must ensure that the inode only ever * has one dentry. If a dentry is found, that is returned instead of * allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is released. * To make it easier to use in export operations a %NULL or IS_ERR inode may * be passed in and the error will be propagated to the return value, * with a %NULL @inode replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_alias(struct inode *inode) { return __d_obtain_alias(inode, true); } EXPORT_SYMBOL(d_obtain_alias); /** * d_obtain_root - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain an IS_ROOT dentry for the root of a filesystem. * * We must ensure that directory inodes only ever have one dentry. If a * dentry is found, that is returned instead of allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is * released. A %NULL or IS_ERR inode may be passed in and will be the * error will be propagate to the return value, with a %NULL @inode * replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_root(struct inode *inode) { return __d_obtain_alias(inode, false); } EXPORT_SYMBOL(d_obtain_root); /** * d_add_ci - lookup or allocate new dentry with case-exact name * @inode: the inode case-insensitive lookup has found * @dentry: the negative dentry that was passed to the parent's lookup func * @name: the case-exact name to be associated with the returned dentry * * This is to avoid filling the dcache with case-insensitive names to the * same inode, only the actual correct case is stored in the dcache for * case-insensitive filesystems. * * For a case-insensitive lookup match and if the case-exact dentry * already exists in the dcache, use it and return it. * * If no entry exists with the exact case name, allocate new dentry with * the exact case, and return the spliced entry. */ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, struct qstr *name) { struct dentry *found, *res; /* * First check if a dentry matching the name already exists, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); if (found) { iput(inode); return found; } if (d_in_lookup(dentry)) { found = d_alloc_parallel(dentry->d_parent, name, dentry->d_wait); if (IS_ERR(found) || !d_in_lookup(found)) { iput(inode); return found; } } else { found = d_alloc(dentry->d_parent, name); if (!found) { iput(inode); return ERR_PTR(-ENOMEM); } } res = d_splice_alias(inode, found); if (res) { d_lookup_done(found); dput(found); return res; } return found; } EXPORT_SYMBOL(d_add_ci); /** * d_same_name - compare dentry name with case-exact name * @parent: parent dentry * @dentry: the negative dentry that was passed to the parent's lookup func * @name: the case-exact name to be associated with the returned dentry * * Return: true if names are same, or false */ bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name) { if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { if (dentry->d_name.len != name->len) return false; return dentry_cmp(dentry, name->name, name->len) == 0; } return parent->d_op->d_compare(dentry, dentry->d_name.len, dentry->d_name.name, name) == 0; } EXPORT_SYMBOL_GPL(d_same_name); /* * This is __d_lookup_rcu() when the parent dentry has * DCACHE_OP_COMPARE, which makes things much nastier. */ static noinline struct dentry *__d_lookup_rcu_op_compare( const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { int tlen; const char *tname; unsigned seq; seqretry: seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; tlen = dentry->d_name.len; tname = dentry->d_name.name; /* we want a consistent (name,len) pair */ if (read_seqcount_retry(&dentry->d_seq, seq)) { cpu_relax(); goto seqretry; } if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry * @name: qstr of name we wish to find * @seqp: returns d_seq value at the point where the dentry was found * Returns: dentry, or NULL * * __d_lookup_rcu is the dcache lookup function for rcu-walk name * resolution (store-free path walking) design described in * Documentation/filesystems/path-lookup.txt. * * This is not to be used outside core vfs. * * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock * held, and rcu_read_lock held. The returned dentry must not be stored into * without taking d_lock and checking d_seq sequence count against @seq * returned here. * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. * * NOTE! The caller *has* to check the resulting dentry against the sequence * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; const unsigned char *str = name->name; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) return __d_lookup_rcu_op_compare(parent, name, seqp); /* * The hash list is protected using RCU. * * Carefully use d_seq when comparing a candidate dentry, to avoid * races with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. * * The caller must perform a seqcount check in order * to do anything useful with the returned dentry. * * NOTE! We do a "raw" seqcount_begin here. That means that * we don't wait for the sequence count to stabilize if it * is in the middle of a sequence change. If we do the slow * dentry compare, we will do seqretries until it is stable, * and if we end up with a successful lookup, we actually * want to exit RCU lookup anyway. * * Note that raw_seqcount_begin still *does* smp_rmb(), so * we are still guaranteed NUL-termination of ->d_name.name. */ seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash_len != hashlen) continue; if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * d_lookup - search for a dentry * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * d_lookup searches the children of the parent dentry for the name in * question. If the dentry is found its reference count is incremented and the * dentry is returned. The caller must use dput to free the entry when it has * finished using it. %NULL is returned if the dentry does not exist. */ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name) { struct dentry *dentry; unsigned seq; do { seq = read_seqbegin(&rename_lock); dentry = __d_lookup(parent, name); if (dentry) break; } while (read_seqretry(&rename_lock, seq)); return dentry; } EXPORT_SYMBOL(d_lookup); /** * __d_lookup - search for a dentry (racy) * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * __d_lookup is like d_lookup, however it may (rarely) return a * false-negative result due to unrelated rename activity. * * __d_lookup is slightly faster by avoiding rename_lock read seqlock, * however it must be used carefully, eg. with a following d_lookup in * the case of failure. * * __d_lookup callers must be commented. */ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) { unsigned int hash = name->hash; struct hlist_bl_head *b = d_hash(hash); struct hlist_bl_node *node; struct dentry *found = NULL; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Take d_lock when comparing a candidate dentry, to avoid races * with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { if (dentry->d_name.hash != hash) continue; spin_lock(&dentry->d_lock); if (dentry->d_parent != parent) goto next; if (d_unhashed(dentry)) goto next; if (!d_same_name(dentry, parent, name)) goto next; dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; next: spin_unlock(&dentry->d_lock); } rcu_read_unlock(); return found; } /** * d_hash_and_lookup - hash the qstr then search for a dentry * @dir: Directory to search in * @name: qstr of name we wish to find * * On lookup failure NULL is returned; on bad name - ERR_PTR(-error) */ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) { /* * Check for a fs-specific hash function. Note that we must * calculate the standard hash first, as the d_op->d_hash() * routine may choose to leave the hash value unchanged. */ name->hash = full_name_hash(dir, name->name, name->len); if (dir->d_flags & DCACHE_OP_HASH) { int err = dir->d_op->d_hash(dir, name); if (unlikely(err < 0)) return ERR_PTR(err); } return d_lookup(dir, name); } EXPORT_SYMBOL(d_hash_and_lookup); /* * When a file is deleted, we have two options: * - turn this dentry into a negative dentry * - unhash this dentry and free it. * * Usually, we want to just turn this into * a negative dentry, but if anybody else is * currently using the dentry or the inode * we can't do that and we fall back on removing * it from the hash queues and waiting for * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * * Turn the dentry into a negative dentry if possible, otherwise * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) { struct inode *inode = dentry->d_inode; spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); /* * Are we the only user? */ if (dentry->d_lockref.count == 1) { dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_delete); static void __d_rehash(struct dentry *entry) { struct hlist_bl_head *b = d_hash(entry->d_name.hash); hlist_bl_lock(b); hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } /** * d_rehash - add an entry back to the hash * @entry: dentry to add to the hash * * Adds a dentry to the hash according to its name. */ void d_rehash(struct dentry * entry) { spin_lock(&entry->d_lock); __d_rehash(entry); spin_unlock(&entry->d_lock); } EXPORT_SYMBOL(d_rehash); static inline unsigned start_dir_add(struct inode *dir) { preempt_disable_nested(); for (;;) { unsigned n = dir->i_dir_seq; if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) return n; cpu_relax(); } } static inline void end_dir_add(struct inode *dir, unsigned int n, wait_queue_head_t *d_wait) { smp_store_release(&dir->i_dir_seq, n + 2); preempt_enable_nested(); wake_up_all(d_wait); } static void d_wait_lookup(struct dentry *dentry) { if (d_in_lookup(dentry)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(dentry->d_wait, &wait); do { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&dentry->d_lock); schedule(); spin_lock(&dentry->d_lock); } while (d_in_lookup(dentry)); } } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, wait_queue_head_t *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); struct hlist_bl_node *node; struct dentry *new = d_alloc(parent, name); struct dentry *dentry; unsigned seq, r_seq, d_seq; if (unlikely(!new)) return ERR_PTR(-ENOMEM); retry: rcu_read_lock(); seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } if (read_seqcount_retry(&dentry->d_seq, d_seq)) { rcu_read_unlock(); dput(dentry); goto retry; } rcu_read_unlock(); dput(new); return dentry; } if (unlikely(read_seqretry(&rename_lock, r_seq))) { rcu_read_unlock(); goto retry; } if (unlikely(seq & 1)) { rcu_read_unlock(); goto retry; } hlist_bl_lock(b); if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; } /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), * any potential in-lookup matches are going to stay here until * we unlock the chain. All fields are stable in everything * we encounter. */ hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) { if (dentry->d_name.hash != hash) continue; if (dentry->d_parent != parent) continue; if (!d_same_name(dentry, parent, name)) continue; hlist_bl_unlock(b); /* now we can try to grab a reference */ if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } rcu_read_unlock(); /* * somebody is likely to be still doing lookup for it; * wait for them to finish */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* * it's not in-lookup anymore; in principle we should repeat * everything from dcache lookup, but it's likely to be what * d_lookup() would've found anyway. If it is, just return it; * otherwise we really have to repeat the whole thing. */ if (unlikely(dentry->d_name.hash != hash)) goto mismatch; if (unlikely(dentry->d_parent != parent)) goto mismatch; if (unlikely(d_unhashed(dentry))) goto mismatch; if (unlikely(!d_same_name(dentry, parent, name))) goto mismatch; /* OK, it *is* a hashed match; return it */ spin_unlock(&dentry->d_lock); dput(new); return dentry; } rcu_read_unlock(); /* we can't take ->d_lock here; it's OK, though. */ new->d_flags |= DCACHE_PAR_LOOKUP; new->d_wait = wq; hlist_bl_add_head(&new->d_u.d_in_lookup_hash, b); hlist_bl_unlock(b); return new; mismatch: spin_unlock(&dentry->d_lock); dput(dentry); goto retry; } EXPORT_SYMBOL(d_alloc_parallel); /* * - Unhash the dentry * - Retrieve and clear the waitqueue head in dentry * - Return the waitqueue head */ static wait_queue_head_t *__d_lookup_unhash(struct dentry *dentry) { wait_queue_head_t *d_wait; struct hlist_bl_head *b; lockdep_assert_held(&dentry->d_lock); b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash); hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); d_wait = dentry->d_wait; dentry->d_wait = NULL; hlist_bl_unlock(b); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_lru); return d_wait; } void __d_lookup_unhash_wake(struct dentry *dentry) { spin_lock(&dentry->d_lock); wake_up_all(__d_lookup_unhash(dentry)); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(__d_lookup_unhash_wake); /* inode->i_lock held if inode is non-NULL */ static inline void __d_add(struct dentry *dentry, struct inode *inode) { wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; spin_lock(&dentry->d_lock); if (unlikely(d_in_lookup(dentry))) { dir = dentry->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(dentry); } if (inode) { unsigned add_flags = d_flags_for_inode(inode); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); } __d_rehash(dentry); if (dir) end_dir_add(dir, n, d_wait); spin_unlock(&dentry->d_lock); if (inode) spin_unlock(&inode->i_lock); } /** * d_add - add dentry to hash queues * @entry: dentry to add * @inode: The inode to attach to this dentry * * This adds the entry to the hash queues and initializes @inode. * The entry was actually filled in earlier during d_alloc(). */ void d_add(struct dentry *entry, struct inode *inode) { if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); } __d_add(entry, inode); } EXPORT_SYMBOL(d_add); /** * d_exact_alias - find and hash an exact unhashed alias * @entry: dentry to add * @inode: The inode to go with this dentry * * If an unhashed dentry with the same name/parent and desired * inode already exists, hash and return it. Otherwise, return * NULL. * * Parent directory should be locked. */ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) { struct dentry *alias; unsigned int hash = entry->d_name.hash; spin_lock(&inode->i_lock); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or * parent changes, because the parent inode i_mutex is held. */ if (alias->d_name.hash != hash) continue; if (alias->d_parent != entry->d_parent) continue; if (!d_same_name(alias, entry->d_parent, &entry->d_name)) continue; spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { spin_unlock(&alias->d_lock); alias = NULL; } else { dget_dlock(alias); __d_rehash(alias); spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); return alias; } spin_unlock(&inode->i_lock); return NULL; } EXPORT_SYMBOL(d_exact_alias); static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { if (unlikely(dname_external(dentry))) { /* * Both external: swap the pointers */ swap(target->d_name.name, dentry->d_name.name); } else { /* * dentry:internal, target:external. Steal target's * storage and make target internal. */ memcpy(target->d_iname, dentry->d_name.name, dentry->d_name.len + 1); dentry->d_name.name = target->d_name.name; target->d_name.name = target->d_iname; } } else { if (unlikely(dname_external(dentry))) { /* * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); target->d_name.name = dentry->d_name.name; dentry->d_name.name = dentry->d_iname; } else { /* * Both are internal. */ unsigned int i; BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { swap(((long *) &dentry->d_iname)[i], ((long *) &target->d_iname)[i]); } } } swap(dentry->d_name.hash_len, target->d_name.hash_len); } static void copy_name(struct dentry *dentry, struct dentry *target) { struct external_name *old_name = NULL; if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { atomic_inc(&external_name(target)->u.count); dentry->d_name = target->d_name; } else { memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); dentry->d_name.name = dentry->d_iname; dentry->d_name.hash_len = target->d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->u.count))) kfree_rcu(old_name, u.head); } /* * __d_move - move a dentry * @dentry: entry to move * @target: new dentry * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. Caller must hold * rename_lock, the i_mutex of the source and target directories, * and the sb->s_vfs_rename_mutex if they differ. See lock_rename(). */ static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { struct dentry *old_parent, *p; wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; WARN_ON(!dentry->d_inode); if (WARN_ON(dentry == target)) return; BUG_ON(d_ancestor(target, dentry)); old_parent = dentry->d_parent; p = d_ancestor(old_parent, target); if (IS_ROOT(dentry)) { BUG_ON(p); spin_lock(&target->d_parent->d_lock); } else if (!p) { /* target is not a descendent of dentry->d_parent */ spin_lock(&target->d_parent->d_lock); spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED); } else { BUG_ON(p == dentry); spin_lock(&old_parent->d_lock); if (p != target) spin_lock_nested(&target->d_parent->d_lock, DENTRY_D_LOCK_NESTED); } spin_lock_nested(&dentry->d_lock, 2); spin_lock_nested(&target->d_lock, 3); if (unlikely(d_in_lookup(target))) { dir = target->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(target); } write_seqcount_begin(&dentry->d_seq); write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); /* unhash both */ if (!d_unhashed(dentry)) ___d_drop(dentry); if (!d_unhashed(target)) ___d_drop(target); /* ... and switch them in the tree */ dentry->d_parent = target->d_parent; if (!exchange) { copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; swap_names(dentry, target); if (!hlist_unhashed(&target->d_sib)) __hlist_del(&target->d_sib); hlist_add_head(&target->d_sib, &target->d_parent->d_children); __d_rehash(target); fsnotify_update_flags(target); } if (!hlist_unhashed(&dentry->d_sib)) __hlist_del(&dentry->d_sib); hlist_add_head(&dentry->d_sib, &dentry->d_parent->d_children); __d_rehash(dentry); fsnotify_update_flags(dentry); fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); if (dir) end_dir_add(dir, n, d_wait); if (dentry->d_parent != old_parent) spin_unlock(&dentry->d_parent->d_lock); if (dentry != old_parent) spin_unlock(&old_parent->d_lock); spin_unlock(&target->d_lock); spin_unlock(&dentry->d_lock); } /* * d_move - move a dentry * @dentry: entry to move * @target: new dentry * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. See the locking * requirements for __d_move. */ void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); /* * d_exchange - exchange two dentries * @dentry1: first dentry * @dentry2: second dentry */ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) { write_seqlock(&rename_lock); WARN_ON(!dentry1->d_inode); WARN_ON(!dentry2->d_inode); WARN_ON(IS_ROOT(dentry1)); WARN_ON(IS_ROOT(dentry2)); __d_move(dentry1, dentry2, true); write_sequnlock(&rename_lock); } /** * d_ancestor - search for an ancestor * @p1: ancestor dentry * @p2: child dentry * * Returns the ancestor dentry of p2 which is a child of p1, if p1 is * an ancestor of p2, else NULL. */ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) { struct dentry *p; for (p = p2; !IS_ROOT(p); p = p->d_parent) { if (p->d_parent == p1) return p; } return NULL; } /* * This helper attempts to cope with remotely renamed directories * * It assumes that the caller is already holding * dentry->d_parent->d_inode->i_mutex, and rename_lock * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... */ static int __d_unalias(struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL; struct rw_semaphore *m2 = NULL; int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; if (!inode_trylock_shared(alias->d_parent->d_inode)) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: __d_move(alias, dentry, false); ret = 0; out_err: if (m2) up_read(m2); if (m1) mutex_unlock(m1); return ret; } /** * d_splice_alias - splice a disconnected dentry into the tree if one exists * @inode: the inode which may have a disconnected dentry * @dentry: a negative dentry which we want to point to the inode. * * If inode is a directory and has an IS_ROOT alias, then d_move that in * place of the given dentry and return it, else simply d_add the inode * to the dentry and return NULL. * * If a non-IS_ROOT directory is found, the filesystem is corrupt, and * we should error out: directories can't have multiple aliases. * * This is needed in the lookup routine of any filesystem that is exportable * (via knfsd) so that we can build dcache paths to directories effectively. * * If a dentry was found and moved, then it is returned. Otherwise NULL * is returned. This matches the expected return value of ->lookup. * * Cluster filesystems may call this function with a negative, hashed dentry. * In that case, we know that the inode will be a regular file, and also this * will only occur during atomic_open. So we need to check for the dentry * being already hashed only in the final case. */ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) { if (IS_ERR(inode)) return ERR_CAST(inode); BUG_ON(!d_unhashed(dentry)); if (!inode) goto out; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); if (unlikely(new)) { /* The reference to new ensures it remains an alias */ spin_unlock(&inode->i_lock); write_seqlock(&rename_lock); if (unlikely(d_ancestor(new, dentry))) { write_sequnlock(&rename_lock); dput(new); new = ERR_PTR(-ELOOP); pr_warn_ratelimited( "VFS: Lookup of '%s' in %s %s" " would have caused loop\n", dentry->d_name.name, inode->i_sb->s_type->name, inode->i_sb->s_id); } else if (!IS_ROOT(new)) { struct dentry *old_parent = dget(new->d_parent); int err = __d_unalias(dentry, new); write_sequnlock(&rename_lock); if (err) { dput(new); new = ERR_PTR(err); } dput(old_parent); } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); } iput(inode); return new; } } out: __d_add(dentry, inode); return NULL; } EXPORT_SYMBOL(d_splice_alias); /* * Test whether new_dentry is a subdirectory of old_dentry. * * Trivially implemented using the dcache structure */ /** * is_subdir - is new dentry a subdirectory of old_dentry * @new_dentry: new dentry * @old_dentry: old dentry * * Returns true if new_dentry is a subdirectory of the parent (at any depth). * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { bool subdir; unsigned seq; if (new_dentry == old_dentry) return true; /* Access d_parent under rcu as d_move() may change it. */ rcu_read_lock(); seq = read_seqbegin(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); /* Try lockless once... */ if (read_seqretry(&rename_lock, seq)) { /* ...else acquire lock for progress even on deep chains. */ read_seqlock_excl(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); read_sequnlock_excl(&rename_lock); } rcu_read_unlock(); return subdir; } EXPORT_SYMBOL(is_subdir); static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry) { struct dentry *root = data; if (dentry != root) { if (d_unhashed(dentry) || !dentry->d_inode) return D_WALK_SKIP; if (!(dentry->d_flags & DCACHE_GENOCIDE)) { dentry->d_flags |= DCACHE_GENOCIDE; dentry->d_lockref.count--; } } return D_WALK_CONTINUE; } void d_genocide(struct dentry *parent) { d_walk(parent, parent, d_genocide_kill); } void d_mark_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; BUG_ON(dentry->d_name.name != dentry->d_iname || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry->d_name.len = sprintf(dentry->d_iname, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); } EXPORT_SYMBOL(d_mark_tmpfile); void d_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; inode_dec_link_count(inode); d_mark_tmpfile(file, inode); d_instantiate(dentry, inode); } EXPORT_SYMBOL(d_tmpfile); /* * Obtain inode number of the parent dentry. */ ino_t d_parent_ino(struct dentry *dentry) { struct dentry *parent; struct inode *iparent; unsigned seq; ino_t ret; scoped_guard(rcu) { seq = raw_seqcount_begin(&dentry->d_seq); parent = READ_ONCE(dentry->d_parent); iparent = d_inode_rcu(parent); if (likely(iparent)) { ret = iparent->i_ino; if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; } } spin_lock(&dentry->d_lock); ret = dentry->d_parent->d_inode->i_ino; spin_unlock(&dentry->d_lock); return ret; } EXPORT_SYMBOL(d_parent_ino); static __initdata unsigned long dhash_entries; static int __init set_dhash_entries(char *str) { if (!str) return 0; dhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_EARLY | HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } static void __init dcache_init(void) { /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature * of the dcache. */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT, d_iname); /* Hash may have been set up in dcache_init_early */ if (!hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } /* SLAB cache for __getname() consumers */ struct kmem_cache *names_cachep __ro_after_init; EXPORT_SYMBOL(names_cachep); void __init vfs_caches_init_early(void) { int i; for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); dcache_init_early(); inode_init_early(); } void __init vfs_caches_init(void) { names_cachep = kmem_cache_create_usercopy("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, 0, PATH_MAX, NULL); dcache_init(); inode_init(); files_init(); files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); } |
| 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 2007 Patrick McHardy <kaber@trash.net> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/gen_stats.h> #include <linux/jhash.h> #include <linux/rtnetlink.h> #include <linux/random.h> #include <linux/slab.h> #include <net/gen_stats.h> #include <net/netlink.h> #include <net/netns/generic.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_RATEEST.h> #include <net/netfilter/xt_rateest.h> #define RATEEST_HSIZE 16 struct xt_rateest_net { struct mutex hash_lock; struct hlist_head hash[RATEEST_HSIZE]; }; static unsigned int xt_rateest_id; static unsigned int jhash_rnd __read_mostly; static unsigned int xt_rateest_hash(const char *name) { return jhash(name, sizeof_field(struct xt_rateest, name), jhash_rnd) & (RATEEST_HSIZE - 1); } static void xt_rateest_hash_insert(struct xt_rateest_net *xn, struct xt_rateest *est) { unsigned int h; h = xt_rateest_hash(est->name); hlist_add_head(&est->list, &xn->hash[h]); } static struct xt_rateest *__xt_rateest_lookup(struct xt_rateest_net *xn, const char *name) { struct xt_rateest *est; unsigned int h; h = xt_rateest_hash(name); hlist_for_each_entry(est, &xn->hash[h], list) { if (strcmp(est->name, name) == 0) { est->refcnt++; return est; } } return NULL; } struct xt_rateest *xt_rateest_lookup(struct net *net, const char *name) { struct xt_rateest_net *xn = net_generic(net, xt_rateest_id); struct xt_rateest *est; mutex_lock(&xn->hash_lock); est = __xt_rateest_lookup(xn, name); mutex_unlock(&xn->hash_lock); return est; } EXPORT_SYMBOL_GPL(xt_rateest_lookup); void xt_rateest_put(struct net *net, struct xt_rateest *est) { struct xt_rateest_net *xn = net_generic(net, xt_rateest_id); mutex_lock(&xn->hash_lock); if (--est->refcnt == 0) { hlist_del(&est->list); gen_kill_estimator(&est->rate_est); /* * gen_estimator est_timer() might access est->lock or bstats, * wait a RCU grace period before freeing 'est' */ kfree_rcu(est, rcu); } mutex_unlock(&xn->hash_lock); } EXPORT_SYMBOL_GPL(xt_rateest_put); static unsigned int xt_rateest_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_rateest_target_info *info = par->targinfo; struct gnet_stats_basic_sync *stats = &info->est->bstats; spin_lock_bh(&info->est->lock); u64_stats_add(&stats->bytes, skb->len); u64_stats_inc(&stats->packets); spin_unlock_bh(&info->est->lock); return XT_CONTINUE; } static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) { struct xt_rateest_net *xn = net_generic(par->net, xt_rateest_id); struct xt_rateest_target_info *info = par->targinfo; struct xt_rateest *est; struct { struct nlattr opt; struct gnet_estimator est; } cfg; int ret; if (strnlen(info->name, sizeof(est->name)) >= sizeof(est->name)) return -ENAMETOOLONG; net_get_random_once(&jhash_rnd, sizeof(jhash_rnd)); mutex_lock(&xn->hash_lock); est = __xt_rateest_lookup(xn, info->name); if (est) { mutex_unlock(&xn->hash_lock); /* * If estimator parameters are specified, they must match the * existing estimator. */ if ((!info->interval && !info->ewma_log) || (info->interval != est->params.interval || info->ewma_log != est->params.ewma_log)) { xt_rateest_put(par->net, est); return -EINVAL; } info->est = est; return 0; } ret = -ENOMEM; est = kzalloc(sizeof(*est), GFP_KERNEL); if (!est) goto err1; gnet_stats_basic_sync_init(&est->bstats); strscpy(est->name, info->name, sizeof(est->name)); spin_lock_init(&est->lock); est->refcnt = 1; est->params.interval = info->interval; est->params.ewma_log = info->ewma_log; cfg.opt.nla_len = nla_attr_size(sizeof(cfg.est)); cfg.opt.nla_type = TCA_STATS_RATE_EST; cfg.est.interval = info->interval; cfg.est.ewma_log = info->ewma_log; ret = gen_new_estimator(&est->bstats, NULL, &est->rate_est, &est->lock, NULL, &cfg.opt); if (ret < 0) goto err2; info->est = est; xt_rateest_hash_insert(xn, est); mutex_unlock(&xn->hash_lock); return 0; err2: kfree(est); err1: mutex_unlock(&xn->hash_lock); return ret; } static void xt_rateest_tg_destroy(const struct xt_tgdtor_param *par) { struct xt_rateest_target_info *info = par->targinfo; xt_rateest_put(par->net, info->est); } static struct xt_target xt_rateest_tg_reg __read_mostly = { .name = "RATEEST", .revision = 0, .family = NFPROTO_UNSPEC, .target = xt_rateest_tg, .checkentry = xt_rateest_tg_checkentry, .destroy = xt_rateest_tg_destroy, .targetsize = sizeof(struct xt_rateest_target_info), .usersize = offsetof(struct xt_rateest_target_info, est), .me = THIS_MODULE, }; static __net_init int xt_rateest_net_init(struct net *net) { struct xt_rateest_net *xn = net_generic(net, xt_rateest_id); int i; mutex_init(&xn->hash_lock); for (i = 0; i < ARRAY_SIZE(xn->hash); i++) INIT_HLIST_HEAD(&xn->hash[i]); return 0; } static struct pernet_operations xt_rateest_net_ops = { .init = xt_rateest_net_init, .id = &xt_rateest_id, .size = sizeof(struct xt_rateest_net), }; static int __init xt_rateest_tg_init(void) { int err = register_pernet_subsys(&xt_rateest_net_ops); if (err) return err; return xt_register_target(&xt_rateest_tg_reg); } static void __exit xt_rateest_tg_fini(void) { xt_unregister_target(&xt_rateest_tg_reg); unregister_pernet_subsys(&xt_rateest_net_ops); } MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Xtables: packet rate estimator"); MODULE_ALIAS("ipt_RATEEST"); MODULE_ALIAS("ip6t_RATEEST"); module_init(xt_rateest_tg_init); module_exit(xt_rateest_tg_fini); |
| 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_simple.c Simple example of an action * * Authors: Jamal Hadi Salim (2005-8) */ #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> #include <linux/tc_act/tc_defact.h> #include <net/tc_act/tc_defact.h> static struct tc_action_ops act_simp_ops; #define SIMP_MAX_DATA 32 TC_INDIRECT_SCOPE int tcf_simp_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_defact *d = to_defact(a); spin_lock(&d->tcf_lock); tcf_lastuse_update(&d->tcf_tm); bstats_update(&d->tcf_bstats, skb); /* print policy string followed by _ then packet count * Example if this was the 3rd packet and the string was "hello" * then it would look like "hello_3" (without quotes) */ pr_info("simple: %s_%llu\n", (char *)d->tcfd_defdata, u64_stats_read(&d->tcf_bstats.packets)); spin_unlock(&d->tcf_lock); return d->tcf_action; } static void tcf_simp_release(struct tc_action *a) { struct tcf_defact *d = to_defact(a); kfree(d->tcfd_defdata); } static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata) { d->tcfd_defdata = kzalloc(SIMP_MAX_DATA, GFP_KERNEL); if (unlikely(!d->tcfd_defdata)) return -ENOMEM; nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); return 0; } static int reset_policy(struct tc_action *a, const struct nlattr *defdata, struct tc_defact *p, struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tcf_chain *goto_ch = NULL; struct tcf_defact *d; int err; err = tcf_action_check_ctrlact(p->action, tp, &goto_ch, extack); if (err < 0) return err; d = to_defact(a); spin_lock_bh(&d->tcf_lock); goto_ch = tcf_action_set_ctrlact(a, p->action, goto_ch); memset(d->tcfd_defdata, 0, SIMP_MAX_DATA); nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); spin_unlock_bh(&d->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); return 0; } static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { [TCA_DEF_PARMS] = { .len = sizeof(struct tc_defact) }, [TCA_DEF_DATA] = { .type = NLA_STRING, .len = SIMP_MAX_DATA }, }; static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_simp_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_DEF_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_defact *parm; struct tcf_defact *d; bool exists = false; int ret = 0, err; u32 index; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_DEF_MAX, nla, simple_policy, NULL); if (err < 0) return err; if (tb[TCA_DEF_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_DEF_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (tb[TCA_DEF_DATA] == NULL) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_simp_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } d = to_defact(*a); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; err = alloc_defdata(d, tb[TCA_DEF_DATA]); if (err < 0) goto put_chain; tcf_action_set_ctrlact(*a, parm->action, goto_ch); ret = ACT_P_CREATED; } else { if (!(flags & TCA_ACT_FLAGS_REPLACE)) { err = -EEXIST; goto release_idr; } err = reset_policy(*a, tb[TCA_DEF_DATA], parm, tp, extack); if (err) goto release_idr; } return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_defact *d = to_defact(a); struct tc_defact opt = { .index = d->tcf_index, .refcnt = refcount_read(&d->tcf_refcnt) - ref, .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&d->tcf_lock); opt.action = d->tcf_action; if (nla_put(skb, TCA_DEF_PARMS, sizeof(opt), &opt) || nla_put_string(skb, TCA_DEF_DATA, d->tcfd_defdata)) goto nla_put_failure; tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_DEF_TM, sizeof(t), &t, TCA_DEF_PAD)) goto nla_put_failure; spin_unlock_bh(&d->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&d->tcf_lock); nlmsg_trim(skb, b); return -1; } static struct tc_action_ops act_simp_ops = { .kind = "simple", .id = TCA_ID_SIMP, .owner = THIS_MODULE, .act = tcf_simp_act, .dump = tcf_simp_dump, .cleanup = tcf_simp_release, .init = tcf_simp_init, .size = sizeof(struct tcf_defact), }; MODULE_ALIAS_NET_ACT("simple"); static __net_init int simp_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_simp_ops.net_id); return tc_action_net_init(net, tn, &act_simp_ops); } static void __net_exit simp_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_simp_ops.net_id); } static struct pernet_operations simp_net_ops = { .init = simp_init_net, .exit_batch = simp_exit_net, .id = &act_simp_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2005)"); MODULE_DESCRIPTION("Simple example action"); MODULE_LICENSE("GPL"); static int __init simp_init_module(void) { int ret = tcf_register_action(&act_simp_ops, &simp_net_ops); if (!ret) pr_info("Simple TC action Loaded\n"); return ret; } static void __exit simp_cleanup_module(void) { tcf_unregister_action(&act_simp_ops, &simp_net_ops); } module_init(simp_init_module); module_exit(simp_cleanup_module); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM vsyscall #if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define __VSYSCALL_TRACE_H #include <linux/tracepoint.h> TRACE_EVENT(emulate_vsyscall, TP_PROTO(int nr), TP_ARGS(nr), TP_STRUCT__entry(__field(int, nr)), TP_fast_assign( __entry->nr = nr; ), TP_printk("nr = %d", __entry->nr) ); #endif #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/ #define TRACE_INCLUDE_FILE vsyscall_trace #include <trace/define_trace.h> |
| 40 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 | // SPDX-License-Identifier: GPL-2.0-only /* * * Authors: * (C) 2015 Pengutronix, Alexander Aring <aar@pengutronix.de> */ #include <linux/if_arp.h> #include <linux/module.h> #include <net/6lowpan.h> #include <net/addrconf.h> #include "6lowpan_i.h" int lowpan_register_netdevice(struct net_device *dev, enum lowpan_lltypes lltype) { int i, ret; switch (lltype) { case LOWPAN_LLTYPE_IEEE802154: dev->addr_len = EUI64_ADDR_LEN; break; case LOWPAN_LLTYPE_BTLE: dev->addr_len = ETH_ALEN; break; } dev->type = ARPHRD_6LOWPAN; dev->mtu = IPV6_MIN_MTU; lowpan_dev(dev)->lltype = lltype; spin_lock_init(&lowpan_dev(dev)->ctx.lock); for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) lowpan_dev(dev)->ctx.table[i].id = i; dev->ndisc_ops = &lowpan_ndisc_ops; ret = register_netdevice(dev); if (ret < 0) return ret; lowpan_dev_debugfs_init(dev); return ret; } EXPORT_SYMBOL(lowpan_register_netdevice); int lowpan_register_netdev(struct net_device *dev, enum lowpan_lltypes lltype) { int ret; rtnl_lock(); ret = lowpan_register_netdevice(dev, lltype); rtnl_unlock(); return ret; } EXPORT_SYMBOL(lowpan_register_netdev); void lowpan_unregister_netdevice(struct net_device *dev) { unregister_netdevice(dev); lowpan_dev_debugfs_exit(dev); } EXPORT_SYMBOL(lowpan_unregister_netdevice); void lowpan_unregister_netdev(struct net_device *dev) { rtnl_lock(); lowpan_unregister_netdevice(dev); rtnl_unlock(); } EXPORT_SYMBOL(lowpan_unregister_netdev); int addrconf_ifid_802154_6lowpan(u8 *eui, struct net_device *dev) { struct wpan_dev *wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr; /* Set short_addr autoconfiguration if short_addr is present only */ if (!lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr)) return -1; /* For either address format, all zero addresses MUST NOT be used */ if (wpan_dev->pan_id == cpu_to_le16(0x0000) && wpan_dev->short_addr == cpu_to_le16(0x0000)) return -1; /* Alternatively, if no PAN ID is known, 16 zero bits may be used */ if (wpan_dev->pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST)) memset(eui, 0, 2); else ieee802154_le16_to_be16(eui, &wpan_dev->pan_id); /* The "Universal/Local" (U/L) bit shall be set to zero */ eui[0] &= ~2; eui[2] = 0; eui[3] = 0xFF; eui[4] = 0xFE; eui[5] = 0; ieee802154_le16_to_be16(&eui[6], &wpan_dev->short_addr); return 0; } static int lowpan_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev; struct in6_addr addr; int i; if (dev->type != ARPHRD_6LOWPAN) return NOTIFY_DONE; idev = __in6_dev_get(dev); if (!idev) return NOTIFY_DONE; switch (event) { case NETDEV_UP: case NETDEV_CHANGE: /* (802.15.4 6LoWPAN short address slaac handling */ if (lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154) && addrconf_ifid_802154_6lowpan(addr.s6_addr + 8, dev) == 0) { __ipv6_addr_set_half(&addr.s6_addr32[0], htonl(0xFE800000), 0); addrconf_add_linklocal(idev, &addr, 0); } break; case NETDEV_DOWN: for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) clear_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE, &lowpan_dev(dev)->ctx.table[i].flags); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block lowpan_notifier = { .notifier_call = lowpan_event, }; static int __init lowpan_module_init(void) { int ret; lowpan_debugfs_init(); ret = register_netdevice_notifier(&lowpan_notifier); if (ret < 0) { lowpan_debugfs_exit(); return ret; } request_module_nowait("nhc_dest"); request_module_nowait("nhc_fragment"); request_module_nowait("nhc_hop"); request_module_nowait("nhc_ipv6"); request_module_nowait("nhc_mobility"); request_module_nowait("nhc_routing"); request_module_nowait("nhc_udp"); return 0; } static void __exit lowpan_module_exit(void) { lowpan_debugfs_exit(); unregister_netdevice_notifier(&lowpan_notifier); } module_init(lowpan_module_init); module_exit(lowpan_module_exit); MODULE_DESCRIPTION("IPv6 over Low-Power Wireless Personal Area Network core module"); MODULE_LICENSE("GPL"); |
| 16 10 10 9 16 179 179 179 190 190 190 9 9 9 9 9 8 8 9 9 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007 Jens Axboe <jens.axboe@oracle.com> * * Scatterlist handling helpers. */ #include <linux/export.h> #include <linux/slab.h> #include <linux/scatterlist.h> #include <linux/highmem.h> #include <linux/kmemleak.h> #include <linux/bvec.h> #include <linux/uio.h> #include <linux/folio_queue.h> /** * sg_next - return the next scatterlist entry in a list * @sg: The current sg entry * * Description: * Usually the next entry will be @sg@ + 1, but if this sg element is part * of a chained scatterlist, it could jump to the start of a new * scatterlist array. * **/ struct scatterlist *sg_next(struct scatterlist *sg) { if (sg_is_last(sg)) return NULL; sg++; if (unlikely(sg_is_chain(sg))) sg = sg_chain_ptr(sg); return sg; } EXPORT_SYMBOL(sg_next); /** * sg_nents - return total count of entries in scatterlist * @sg: The scatterlist * * Description: * Allows to know how many entries are in sg, taking into account * chaining as well * **/ int sg_nents(struct scatterlist *sg) { int nents; for (nents = 0; sg; sg = sg_next(sg)) nents++; return nents; } EXPORT_SYMBOL(sg_nents); /** * sg_nents_for_len - return total count of entries in scatterlist * needed to satisfy the supplied length * @sg: The scatterlist * @len: The total required length * * Description: * Determines the number of entries in sg that are required to meet * the supplied length, taking into account chaining as well * * Returns: * the number of sg entries needed, negative error on failure * **/ int sg_nents_for_len(struct scatterlist *sg, u64 len) { int nents; u64 total; if (!len) return 0; for (nents = 0, total = 0; sg; sg = sg_next(sg)) { nents++; total += sg->length; if (total >= len) return nents; } return -EINVAL; } EXPORT_SYMBOL(sg_nents_for_len); /** * sg_last - return the last scatterlist entry in a list * @sgl: First entry in the scatterlist * @nents: Number of entries in the scatterlist * * Description: * Should only be used casually, it (currently) scans the entire list * to get the last entry. * * Note that the @sgl@ pointer passed in need not be the first one, * the important bit is that @nents@ denotes the number of entries that * exist from @sgl@. * **/ struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents) { struct scatterlist *sg, *ret = NULL; unsigned int i; for_each_sg(sgl, sg, nents, i) ret = sg; BUG_ON(!sg_is_last(ret)); return ret; } EXPORT_SYMBOL(sg_last); /** * sg_init_table - Initialize SG table * @sgl: The SG table * @nents: Number of entries in table * * Notes: * If this is part of a chained sg table, sg_mark_end() should be * used only on the last table part. * **/ void sg_init_table(struct scatterlist *sgl, unsigned int nents) { memset(sgl, 0, sizeof(*sgl) * nents); sg_init_marker(sgl, nents); } EXPORT_SYMBOL(sg_init_table); /** * sg_init_one - Initialize a single entry sg list * @sg: SG entry * @buf: Virtual address for IO * @buflen: IO length * **/ void sg_init_one(struct scatterlist *sg, const void *buf, unsigned int buflen) { sg_init_table(sg, 1); sg_set_buf(sg, buf, buflen); } EXPORT_SYMBOL(sg_init_one); /* * The default behaviour of sg_alloc_table() is to use these kmalloc/kfree * helpers. */ static struct scatterlist *sg_kmalloc(unsigned int nents, gfp_t gfp_mask) { if (nents == SG_MAX_SINGLE_ALLOC) { /* * Kmemleak doesn't track page allocations as they are not * commonly used (in a raw form) for kernel data structures. * As we chain together a list of pages and then a normal * kmalloc (tracked by kmemleak), in order to for that last * allocation not to become decoupled (and thus a * false-positive) we need to inform kmemleak of all the * intermediate allocations. */ void *ptr = (void *) __get_free_page(gfp_mask); kmemleak_alloc(ptr, PAGE_SIZE, 1, gfp_mask); return ptr; } else return kmalloc_array(nents, sizeof(struct scatterlist), gfp_mask); } static void sg_kfree(struct scatterlist *sg, unsigned int nents) { if (nents == SG_MAX_SINGLE_ALLOC) { kmemleak_free(sg); free_page((unsigned long) sg); } else kfree(sg); } /** * __sg_free_table - Free a previously mapped sg table * @table: The sg table header to use * @max_ents: The maximum number of entries per single scatterlist * @nents_first_chunk: Number of entries int the (preallocated) first * scatterlist chunk, 0 means no such preallocated first chunk * @free_fn: Free function * @num_ents: Number of entries in the table * * Description: * Free an sg table previously allocated and setup with * __sg_alloc_table(). The @max_ents value must be identical to * that previously used with __sg_alloc_table(). * **/ void __sg_free_table(struct sg_table *table, unsigned int max_ents, unsigned int nents_first_chunk, sg_free_fn *free_fn, unsigned int num_ents) { struct scatterlist *sgl, *next; unsigned curr_max_ents = nents_first_chunk ?: max_ents; if (unlikely(!table->sgl)) return; sgl = table->sgl; while (num_ents) { unsigned int alloc_size = num_ents; unsigned int sg_size; /* * If we have more than max_ents segments left, * then assign 'next' to the sg table after the current one. * sg_size is then one less than alloc size, since the last * element is the chain pointer. */ if (alloc_size > curr_max_ents) { next = sg_chain_ptr(&sgl[curr_max_ents - 1]); alloc_size = curr_max_ents; sg_size = alloc_size - 1; } else { sg_size = alloc_size; next = NULL; } num_ents -= sg_size; if (nents_first_chunk) nents_first_chunk = 0; else free_fn(sgl, alloc_size); sgl = next; curr_max_ents = max_ents; } table->sgl = NULL; } EXPORT_SYMBOL(__sg_free_table); /** * sg_free_append_table - Free a previously allocated append sg table. * @table: The mapped sg append table header * **/ void sg_free_append_table(struct sg_append_table *table) { __sg_free_table(&table->sgt, SG_MAX_SINGLE_ALLOC, 0, sg_kfree, table->total_nents); } EXPORT_SYMBOL(sg_free_append_table); /** * sg_free_table - Free a previously allocated sg table * @table: The mapped sg table header * **/ void sg_free_table(struct sg_table *table) { __sg_free_table(table, SG_MAX_SINGLE_ALLOC, 0, sg_kfree, table->orig_nents); } EXPORT_SYMBOL(sg_free_table); /** * __sg_alloc_table - Allocate and initialize an sg table with given allocator * @table: The sg table header to use * @nents: Number of entries in sg list * @max_ents: The maximum number of entries the allocator returns per call * @first_chunk: first SGL if preallocated (may be %NULL) * @nents_first_chunk: Number of entries in the (preallocated) first * scatterlist chunk, 0 means no such preallocated chunk provided by user * @gfp_mask: GFP allocation mask * @alloc_fn: Allocator to use * * Description: * This function returns a @table @nents long. The allocator is * defined to return scatterlist chunks of maximum size @max_ents. * Thus if @nents is bigger than @max_ents, the scatterlists will be * chained in units of @max_ents. * * Notes: * If this function returns non-0 (eg failure), the caller must call * __sg_free_table() to cleanup any leftover allocations. * **/ int __sg_alloc_table(struct sg_table *table, unsigned int nents, unsigned int max_ents, struct scatterlist *first_chunk, unsigned int nents_first_chunk, gfp_t gfp_mask, sg_alloc_fn *alloc_fn) { struct scatterlist *sg, *prv; unsigned int left; unsigned curr_max_ents = nents_first_chunk ?: max_ents; unsigned prv_max_ents; memset(table, 0, sizeof(*table)); if (nents == 0) return -EINVAL; #ifdef CONFIG_ARCH_NO_SG_CHAIN if (WARN_ON_ONCE(nents > max_ents)) return -EINVAL; #endif left = nents; prv = NULL; do { unsigned int sg_size, alloc_size = left; if (alloc_size > curr_max_ents) { alloc_size = curr_max_ents; sg_size = alloc_size - 1; } else sg_size = alloc_size; left -= sg_size; if (first_chunk) { sg = first_chunk; first_chunk = NULL; } else { sg = alloc_fn(alloc_size, gfp_mask); } if (unlikely(!sg)) { /* * Adjust entry count to reflect that the last * entry of the previous table won't be used for * linkage. Without this, sg_kfree() may get * confused. */ if (prv) table->nents = ++table->orig_nents; return -ENOMEM; } sg_init_table(sg, alloc_size); table->nents = table->orig_nents += sg_size; /* * If this is the first mapping, assign the sg table header. * If this is not the first mapping, chain previous part. */ if (prv) sg_chain(prv, prv_max_ents, sg); else table->sgl = sg; /* * If no more entries after this one, mark the end */ if (!left) sg_mark_end(&sg[sg_size - 1]); prv = sg; prv_max_ents = curr_max_ents; curr_max_ents = max_ents; } while (left); return 0; } EXPORT_SYMBOL(__sg_alloc_table); /** * sg_alloc_table - Allocate and initialize an sg table * @table: The sg table header to use * @nents: Number of entries in sg list * @gfp_mask: GFP allocation mask * * Description: * Allocate and initialize an sg table. If @nents@ is larger than * SG_MAX_SINGLE_ALLOC a chained sg table will be setup. * **/ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask) { int ret; ret = __sg_alloc_table(table, nents, SG_MAX_SINGLE_ALLOC, NULL, 0, gfp_mask, sg_kmalloc); if (unlikely(ret)) sg_free_table(table); return ret; } EXPORT_SYMBOL(sg_alloc_table); static struct scatterlist *get_next_sg(struct sg_append_table *table, struct scatterlist *cur, unsigned long needed_sges, gfp_t gfp_mask) { struct scatterlist *new_sg, *next_sg; unsigned int alloc_size; if (cur) { next_sg = sg_next(cur); /* Check if last entry should be keeped for chainning */ if (!sg_is_last(next_sg) || needed_sges == 1) return next_sg; } alloc_size = min_t(unsigned long, needed_sges, SG_MAX_SINGLE_ALLOC); new_sg = sg_kmalloc(alloc_size, gfp_mask); if (!new_sg) return ERR_PTR(-ENOMEM); sg_init_table(new_sg, alloc_size); if (cur) { table->total_nents += alloc_size - 1; __sg_chain(next_sg, new_sg); } else { table->sgt.sgl = new_sg; table->total_nents = alloc_size; } return new_sg; } static bool pages_are_mergeable(struct page *a, struct page *b) { if (page_to_pfn(a) != page_to_pfn(b) + 1) return false; if (!zone_device_pages_have_same_pgmap(a, b)) return false; return true; } /** * sg_alloc_append_table_from_pages - Allocate and initialize an append sg * table from an array of pages * @sgt_append: The sg append table to use * @pages: Pointer to an array of page pointers * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) * @max_segment: Maximum size of a scatterlist element in bytes * @left_pages: Left pages caller have to set after this call * @gfp_mask: GFP allocation mask * * Description: * In the first call it allocate and initialize an sg table from a list of * pages, else reuse the scatterlist from sgt_append. Contiguous ranges of * the pages are squashed into a single scatterlist entry up to the maximum * size specified in @max_segment. A user may provide an offset at a start * and a size of valid data in a buffer specified by the page array. The * returned sg table is released by sg_free_append_table * * Returns: * 0 on success, negative error on failure * * Notes: * If this function returns non-0 (eg failure), the caller must call * sg_free_append_table() to cleanup any leftover allocations. * * In the fist call, sgt_append must by initialized. */ int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, unsigned int left_pages, gfp_t gfp_mask) { unsigned int chunks, cur_page, seg_len, i, prv_len = 0; unsigned int added_nents = 0; struct scatterlist *s = sgt_append->prv; struct page *last_pg; /* * The algorithm below requires max_segment to be aligned to PAGE_SIZE * otherwise it can overshoot. */ max_segment = ALIGN_DOWN(max_segment, PAGE_SIZE); if (WARN_ON(max_segment < PAGE_SIZE)) return -EINVAL; if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && sgt_append->prv) return -EOPNOTSUPP; if (sgt_append->prv) { unsigned long next_pfn = (page_to_phys(sg_page(sgt_append->prv)) + sgt_append->prv->offset + sgt_append->prv->length) / PAGE_SIZE; if (WARN_ON(offset)) return -EINVAL; /* Merge contiguous pages into the last SG */ prv_len = sgt_append->prv->length; if (page_to_pfn(pages[0]) == next_pfn) { last_pg = pfn_to_page(next_pfn - 1); while (n_pages && pages_are_mergeable(pages[0], last_pg)) { if (sgt_append->prv->length + PAGE_SIZE > max_segment) break; sgt_append->prv->length += PAGE_SIZE; last_pg = pages[0]; pages++; n_pages--; } if (!n_pages) goto out; } } /* compute number of contiguous chunks */ chunks = 1; seg_len = 0; for (i = 1; i < n_pages; i++) { seg_len += PAGE_SIZE; if (seg_len >= max_segment || !pages_are_mergeable(pages[i], pages[i - 1])) { chunks++; seg_len = 0; } } /* merging chunks and putting them into the scatterlist */ cur_page = 0; for (i = 0; i < chunks; i++) { unsigned int j, chunk_size; /* look for the end of the current chunk */ seg_len = 0; for (j = cur_page + 1; j < n_pages; j++) { seg_len += PAGE_SIZE; if (seg_len >= max_segment || !pages_are_mergeable(pages[j], pages[j - 1])) break; } /* Pass how many chunks might be left */ s = get_next_sg(sgt_append, s, chunks - i + left_pages, gfp_mask); if (IS_ERR(s)) { /* * Adjust entry length to be as before function was * called. */ if (sgt_append->prv) sgt_append->prv->length = prv_len; return PTR_ERR(s); } chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset; sg_set_page(s, pages[cur_page], min_t(unsigned long, size, chunk_size), offset); added_nents++; size -= chunk_size; offset = 0; cur_page = j; } sgt_append->sgt.nents += added_nents; sgt_append->sgt.orig_nents = sgt_append->sgt.nents; sgt_append->prv = s; out: if (!left_pages) sg_mark_end(s); return 0; } EXPORT_SYMBOL(sg_alloc_append_table_from_pages); /** * sg_alloc_table_from_pages_segment - Allocate and initialize an sg table from * an array of pages and given maximum * segment. * @sgt: The sg table header to use * @pages: Pointer to an array of page pointers * @n_pages: Number of pages in the pages array * @offset: Offset from start of the first page to the start of a buffer * @size: Number of valid bytes in the buffer (after offset) * @max_segment: Maximum size of a scatterlist element in bytes * @gfp_mask: GFP allocation mask * * Description: * Allocate and initialize an sg table from a list of pages. Contiguous * ranges of the pages are squashed into a single scatterlist node up to the * maximum size specified in @max_segment. A user may provide an offset at a * start and a size of valid data in a buffer specified by the page array. * * The returned sg table is released by sg_free_table. * * Returns: * 0 on success, negative error on failure */ int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages, unsigned int n_pages, unsigned int offset, unsigned long size, unsigned int max_segment, gfp_t gfp_mask) { struct sg_append_table append = {}; int err; err = sg_alloc_append_table_from_pages(&append, pages, n_pages, offset, size, max_segment, 0, gfp_mask); if (err) { sg_free_append_table(&append); return err; } memcpy(sgt, &append.sgt, sizeof(*sgt)); WARN_ON(append.total_nents != sgt->orig_nents); return 0; } EXPORT_SYMBOL(sg_alloc_table_from_pages_segment); #ifdef CONFIG_SGL_ALLOC /** * sgl_alloc_order - allocate a scatterlist and its pages * @length: Length in bytes of the scatterlist. Must be at least one * @order: Second argument for alloc_pages() * @chainable: Whether or not to allocate an extra element in the scatterlist * for scatterlist chaining purposes * @gfp: Memory allocation flags * @nent_p: [out] Number of entries in the scatterlist that have pages * * Returns: A pointer to an initialized scatterlist or %NULL upon failure. */ struct scatterlist *sgl_alloc_order(unsigned long long length, unsigned int order, bool chainable, gfp_t gfp, unsigned int *nent_p) { struct scatterlist *sgl, *sg; struct page *page; unsigned int nent, nalloc; u32 elem_len; nent = round_up(length, PAGE_SIZE << order) >> (PAGE_SHIFT + order); /* Check for integer overflow */ if (length > (nent << (PAGE_SHIFT + order))) return NULL; nalloc = nent; if (chainable) { /* Check for integer overflow */ if (nalloc + 1 < nalloc) return NULL; nalloc++; } sgl = kmalloc_array(nalloc, sizeof(struct scatterlist), gfp & ~GFP_DMA); if (!sgl) return NULL; sg_init_table(sgl, nalloc); sg = sgl; while (length) { elem_len = min_t(u64, length, PAGE_SIZE << order); page = alloc_pages(gfp, order); if (!page) { sgl_free_order(sgl, order); return NULL; } sg_set_page(sg, page, elem_len, 0); length -= elem_len; sg = sg_next(sg); } WARN_ONCE(length, "length = %lld\n", length); if (nent_p) *nent_p = nent; return sgl; } EXPORT_SYMBOL(sgl_alloc_order); /** * sgl_alloc - allocate a scatterlist and its pages * @length: Length in bytes of the scatterlist * @gfp: Memory allocation flags * @nent_p: [out] Number of entries in the scatterlist * * Returns: A pointer to an initialized scatterlist or %NULL upon failure. */ struct scatterlist *sgl_alloc(unsigned long long length, gfp_t gfp, unsigned int *nent_p) { return sgl_alloc_order(length, 0, false, gfp, nent_p); } EXPORT_SYMBOL(sgl_alloc); /** * sgl_free_n_order - free a scatterlist and its pages * @sgl: Scatterlist with one or more elements * @nents: Maximum number of elements to free * @order: Second argument for __free_pages() * * Notes: * - If several scatterlists have been chained and each chain element is * freed separately then it's essential to set nents correctly to avoid that a * page would get freed twice. * - All pages in a chained scatterlist can be freed at once by setting @nents * to a high number. */ void sgl_free_n_order(struct scatterlist *sgl, int nents, int order) { struct scatterlist *sg; struct page *page; int i; for_each_sg(sgl, sg, nents, i) { if (!sg) break; page = sg_page(sg); if (page) __free_pages(page, order); } kfree(sgl); } EXPORT_SYMBOL(sgl_free_n_order); /** * sgl_free_order - free a scatterlist and its pages * @sgl: Scatterlist with one or more elements * @order: Second argument for __free_pages() */ void sgl_free_order(struct scatterlist *sgl, int order) { sgl_free_n_order(sgl, INT_MAX, order); } EXPORT_SYMBOL(sgl_free_order); /** * sgl_free - free a scatterlist and its pages * @sgl: Scatterlist with one or more elements */ void sgl_free(struct scatterlist *sgl) { sgl_free_order(sgl, 0); } EXPORT_SYMBOL(sgl_free); #endif /* CONFIG_SGL_ALLOC */ void __sg_page_iter_start(struct sg_page_iter *piter, struct scatterlist *sglist, unsigned int nents, unsigned long pgoffset) { piter->__pg_advance = 0; piter->__nents = nents; piter->sg = sglist; piter->sg_pgoffset = pgoffset; } EXPORT_SYMBOL(__sg_page_iter_start); static int sg_page_count(struct scatterlist *sg) { return PAGE_ALIGN(sg->offset + sg->length) >> PAGE_SHIFT; } bool __sg_page_iter_next(struct sg_page_iter *piter) { if (!piter->__nents || !piter->sg) return false; piter->sg_pgoffset += piter->__pg_advance; piter->__pg_advance = 1; while (piter->sg_pgoffset >= sg_page_count(piter->sg)) { piter->sg_pgoffset -= sg_page_count(piter->sg); piter->sg = sg_next(piter->sg); if (!--piter->__nents || !piter->sg) return false; } return true; } EXPORT_SYMBOL(__sg_page_iter_next); static int sg_dma_page_count(struct scatterlist *sg) { return PAGE_ALIGN(sg->offset + sg_dma_len(sg)) >> PAGE_SHIFT; } bool __sg_page_iter_dma_next(struct sg_dma_page_iter *dma_iter) { struct sg_page_iter *piter = &dma_iter->base; if (!piter->__nents || !piter->sg) return false; piter->sg_pgoffset += piter->__pg_advance; piter->__pg_advance = 1; while (piter->sg_pgoffset >= sg_dma_page_count(piter->sg)) { piter->sg_pgoffset -= sg_dma_page_count(piter->sg); piter->sg = sg_next(piter->sg); if (!--piter->__nents || !piter->sg) return false; } return true; } EXPORT_SYMBOL(__sg_page_iter_dma_next); /** * sg_miter_start - start mapping iteration over a sg list * @miter: sg mapping iter to be started * @sgl: sg list to iterate over * @nents: number of sg entries * @flags: sg iterator flags * * Description: * Starts mapping iterator @miter. * * Context: * Don't care. */ void sg_miter_start(struct sg_mapping_iter *miter, struct scatterlist *sgl, unsigned int nents, unsigned int flags) { memset(miter, 0, sizeof(struct sg_mapping_iter)); __sg_page_iter_start(&miter->piter, sgl, nents, 0); WARN_ON(!(flags & (SG_MITER_TO_SG | SG_MITER_FROM_SG))); miter->__flags = flags; } EXPORT_SYMBOL(sg_miter_start); static bool sg_miter_get_next_page(struct sg_mapping_iter *miter) { if (!miter->__remaining) { struct scatterlist *sg; if (!__sg_page_iter_next(&miter->piter)) return false; sg = miter->piter.sg; miter->__offset = miter->piter.sg_pgoffset ? 0 : sg->offset; miter->piter.sg_pgoffset += miter->__offset >> PAGE_SHIFT; miter->__offset &= PAGE_SIZE - 1; miter->__remaining = sg->offset + sg->length - (miter->piter.sg_pgoffset << PAGE_SHIFT) - miter->__offset; miter->__remaining = min_t(unsigned long, miter->__remaining, PAGE_SIZE - miter->__offset); } return true; } /** * sg_miter_skip - reposition mapping iterator * @miter: sg mapping iter to be skipped * @offset: number of bytes to plus the current location * * Description: * Sets the offset of @miter to its current location plus @offset bytes. * If mapping iterator @miter has been proceeded by sg_miter_next(), this * stops @miter. * * Context: * Don't care. * * Returns: * true if @miter contains the valid mapping. false if end of sg * list is reached. */ bool sg_miter_skip(struct sg_mapping_iter *miter, off_t offset) { sg_miter_stop(miter); while (offset) { off_t consumed; if (!sg_miter_get_next_page(miter)) return false; consumed = min_t(off_t, offset, miter->__remaining); miter->__offset += consumed; miter->__remaining -= consumed; offset -= consumed; } return true; } EXPORT_SYMBOL(sg_miter_skip); /** * sg_miter_next - proceed mapping iterator to the next mapping * @miter: sg mapping iter to proceed * * Description: * Proceeds @miter to the next mapping. @miter should have been started * using sg_miter_start(). On successful return, @miter->page, * @miter->addr and @miter->length point to the current mapping. * * Context: * May sleep if !SG_MITER_ATOMIC. * * Returns: * true if @miter contains the next mapping. false if end of sg * list is reached. */ bool sg_miter_next(struct sg_mapping_iter *miter) { sg_miter_stop(miter); /* * Get to the next page if necessary. * __remaining, __offset is adjusted by sg_miter_stop */ if (!sg_miter_get_next_page(miter)) return false; miter->page = sg_page_iter_page(&miter->piter); miter->consumed = miter->length = miter->__remaining; if (miter->__flags & SG_MITER_ATOMIC) miter->addr = kmap_atomic(miter->page) + miter->__offset; else miter->addr = kmap(miter->page) + miter->__offset; return true; } EXPORT_SYMBOL(sg_miter_next); /** * sg_miter_stop - stop mapping iteration * @miter: sg mapping iter to be stopped * * Description: * Stops mapping iterator @miter. @miter should have been started * using sg_miter_start(). A stopped iteration can be resumed by * calling sg_miter_next() on it. This is useful when resources (kmap) * need to be released during iteration. * * Context: * Don't care otherwise. */ void sg_miter_stop(struct sg_mapping_iter *miter) { WARN_ON(miter->consumed > miter->length); /* drop resources from the last iteration */ if (miter->addr) { miter->__offset += miter->consumed; miter->__remaining -= miter->consumed; if (miter->__flags & SG_MITER_TO_SG) flush_dcache_page(miter->page); if (miter->__flags & SG_MITER_ATOMIC) { WARN_ON_ONCE(!pagefault_disabled()); kunmap_atomic(miter->addr); } else kunmap(miter->page); miter->page = NULL; miter->addr = NULL; miter->length = 0; miter->consumed = 0; } } EXPORT_SYMBOL(sg_miter_stop); /** * sg_copy_buffer - Copy data between a linear buffer and an SG list * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy from * @buflen: The number of bytes to copy * @skip: Number of bytes to skip before copying * @to_buffer: transfer direction (true == from an sg list to a * buffer, false == from a buffer to an sg list) * * Returns the number of copied bytes. * **/ size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip, bool to_buffer) { unsigned int offset = 0; struct sg_mapping_iter miter; unsigned int sg_flags = SG_MITER_ATOMIC; if (to_buffer) sg_flags |= SG_MITER_FROM_SG; else sg_flags |= SG_MITER_TO_SG; sg_miter_start(&miter, sgl, nents, sg_flags); if (!sg_miter_skip(&miter, skip)) return 0; while ((offset < buflen) && sg_miter_next(&miter)) { unsigned int len; len = min(miter.length, buflen - offset); if (to_buffer) memcpy(buf + offset, miter.addr, len); else memcpy(miter.addr, buf + offset, len); offset += len; } sg_miter_stop(&miter); return offset; } EXPORT_SYMBOL(sg_copy_buffer); /** * sg_copy_from_buffer - Copy from a linear buffer to an SG list * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy from * @buflen: The number of bytes to copy * * Returns the number of copied bytes. * **/ size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents, const void *buf, size_t buflen) { return sg_copy_buffer(sgl, nents, (void *)buf, buflen, 0, false); } EXPORT_SYMBOL(sg_copy_from_buffer); /** * sg_copy_to_buffer - Copy from an SG list to a linear buffer * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy to * @buflen: The number of bytes to copy * * Returns the number of copied bytes. * **/ size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen) { return sg_copy_buffer(sgl, nents, buf, buflen, 0, true); } EXPORT_SYMBOL(sg_copy_to_buffer); /** * sg_pcopy_from_buffer - Copy from a linear buffer to an SG list * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy from * @buflen: The number of bytes to copy * @skip: Number of bytes to skip before copying * * Returns the number of copied bytes. * **/ size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents, const void *buf, size_t buflen, off_t skip) { return sg_copy_buffer(sgl, nents, (void *)buf, buflen, skip, false); } EXPORT_SYMBOL(sg_pcopy_from_buffer); /** * sg_pcopy_to_buffer - Copy from an SG list to a linear buffer * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy to * @buflen: The number of bytes to copy * @skip: Number of bytes to skip before copying * * Returns the number of copied bytes. * **/ size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip) { return sg_copy_buffer(sgl, nents, buf, buflen, skip, true); } EXPORT_SYMBOL(sg_pcopy_to_buffer); /** * sg_zero_buffer - Zero-out a part of a SG list * @sgl: The SG list * @nents: Number of SG entries * @buflen: The number of bytes to zero out * @skip: Number of bytes to skip before zeroing * * Returns the number of bytes zeroed. **/ size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents, size_t buflen, off_t skip) { unsigned int offset = 0; struct sg_mapping_iter miter; unsigned int sg_flags = SG_MITER_ATOMIC | SG_MITER_TO_SG; sg_miter_start(&miter, sgl, nents, sg_flags); if (!sg_miter_skip(&miter, skip)) return false; while (offset < buflen && sg_miter_next(&miter)) { unsigned int len; len = min(miter.length, buflen - offset); memset(miter.addr, 0, len); offset += len; } sg_miter_stop(&miter); return offset; } EXPORT_SYMBOL(sg_zero_buffer); /* * Extract and pin a list of up to sg_max pages from UBUF- or IOVEC-class * iterators, and add them to the scatterlist. */ static ssize_t extract_user_to_sg(struct iov_iter *iter, ssize_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { struct scatterlist *sg = sgtable->sgl + sgtable->nents; struct page **pages; unsigned int npages; ssize_t ret = 0, res; size_t len, off; /* We decant the page list into the tail of the scatterlist */ pages = (void *)sgtable->sgl + array_size(sg_max, sizeof(struct scatterlist)); pages -= sg_max; do { res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max, extraction_flags, &off); if (res <= 0) goto failed; len = res; maxsize -= len; ret += len; npages = DIV_ROUND_UP(off + len, PAGE_SIZE); sg_max -= npages; for (; npages > 0; npages--) { struct page *page = *pages; size_t seg = min_t(size_t, PAGE_SIZE - off, len); *pages++ = NULL; sg_set_page(sg, page, seg, off); sgtable->nents++; sg++; len -= seg; off = 0; } } while (maxsize > 0 && sg_max > 0); return ret; failed: while (sgtable->nents > sgtable->orig_nents) unpin_user_page(sg_page(&sgtable->sgl[--sgtable->nents])); return res; } /* * Extract up to sg_max pages from a BVEC-type iterator and add them to the * scatterlist. The pages are not pinned. */ static ssize_t extract_bvec_to_sg(struct iov_iter *iter, ssize_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { const struct bio_vec *bv = iter->bvec; struct scatterlist *sg = sgtable->sgl + sgtable->nents; unsigned long start = iter->iov_offset; unsigned int i; ssize_t ret = 0; for (i = 0; i < iter->nr_segs; i++) { size_t off, len; len = bv[i].bv_len; if (start >= len) { start -= len; continue; } len = min_t(size_t, maxsize, len - start); off = bv[i].bv_offset + start; sg_set_page(sg, bv[i].bv_page, len, off); sgtable->nents++; sg++; sg_max--; ret += len; maxsize -= len; if (maxsize <= 0 || sg_max == 0) break; start = 0; } if (ret > 0) iov_iter_advance(iter, ret); return ret; } /* * Extract up to sg_max pages from a KVEC-type iterator and add them to the * scatterlist. This can deal with vmalloc'd buffers as well as kmalloc'd or * static buffers. The pages are not pinned. */ static ssize_t extract_kvec_to_sg(struct iov_iter *iter, ssize_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { const struct kvec *kv = iter->kvec; struct scatterlist *sg = sgtable->sgl + sgtable->nents; unsigned long start = iter->iov_offset; unsigned int i; ssize_t ret = 0; for (i = 0; i < iter->nr_segs; i++) { struct page *page; unsigned long kaddr; size_t off, len, seg; len = kv[i].iov_len; if (start >= len) { start -= len; continue; } kaddr = (unsigned long)kv[i].iov_base + start; off = kaddr & ~PAGE_MASK; len = min_t(size_t, maxsize, len - start); kaddr &= PAGE_MASK; maxsize -= len; ret += len; do { seg = min_t(size_t, len, PAGE_SIZE - off); if (is_vmalloc_or_module_addr((void *)kaddr)) page = vmalloc_to_page((void *)kaddr); else page = virt_to_page((void *)kaddr); sg_set_page(sg, page, len, off); sgtable->nents++; sg++; sg_max--; len -= seg; kaddr += PAGE_SIZE; off = 0; } while (len > 0 && sg_max > 0); if (maxsize <= 0 || sg_max == 0) break; start = 0; } if (ret > 0) iov_iter_advance(iter, ret); return ret; } /* * Extract up to sg_max folios from an FOLIOQ-type iterator and add them to * the scatterlist. The pages are not pinned. */ static ssize_t extract_folioq_to_sg(struct iov_iter *iter, ssize_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { const struct folio_queue *folioq = iter->folioq; struct scatterlist *sg = sgtable->sgl + sgtable->nents; unsigned int slot = iter->folioq_slot; ssize_t ret = 0; size_t offset = iter->iov_offset; BUG_ON(!folioq); if (slot >= folioq_nr_slots(folioq)) { folioq = folioq->next; if (WARN_ON_ONCE(!folioq)) return 0; slot = 0; } do { struct folio *folio = folioq_folio(folioq, slot); size_t fsize = folioq_folio_size(folioq, slot); if (offset < fsize) { size_t part = umin(maxsize - ret, fsize - offset); sg_set_page(sg, folio_page(folio, 0), part, offset); sgtable->nents++; sg++; sg_max--; offset += part; ret += part; } if (offset >= fsize) { offset = 0; slot++; if (slot >= folioq_nr_slots(folioq)) { if (!folioq->next) { WARN_ON_ONCE(ret < iter->count); break; } folioq = folioq->next; slot = 0; } } } while (sg_max > 0 && ret < maxsize); iter->folioq = folioq; iter->folioq_slot = slot; iter->iov_offset = offset; iter->count -= ret; return ret; } /* * Extract up to sg_max folios from an XARRAY-type iterator and add them to * the scatterlist. The pages are not pinned. */ static ssize_t extract_xarray_to_sg(struct iov_iter *iter, ssize_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { struct scatterlist *sg = sgtable->sgl + sgtable->nents; struct xarray *xa = iter->xarray; struct folio *folio; loff_t start = iter->xarray_start + iter->iov_offset; pgoff_t index = start / PAGE_SIZE; ssize_t ret = 0; size_t offset, len; XA_STATE(xas, xa, index); rcu_read_lock(); xas_for_each(&xas, folio, ULONG_MAX) { if (xas_retry(&xas, folio)) continue; if (WARN_ON(xa_is_value(folio))) break; if (WARN_ON(folio_test_hugetlb(folio))) break; offset = offset_in_folio(folio, start); len = min_t(size_t, maxsize, folio_size(folio) - offset); sg_set_page(sg, folio_page(folio, 0), len, offset); sgtable->nents++; sg++; sg_max--; maxsize -= len; ret += len; if (maxsize <= 0 || sg_max == 0) break; } rcu_read_unlock(); if (ret > 0) iov_iter_advance(iter, ret); return ret; } /** * extract_iter_to_sg - Extract pages from an iterator and add to an sglist * @iter: The iterator to extract from * @maxsize: The amount of iterator to copy * @sgtable: The scatterlist table to fill in * @sg_max: Maximum number of elements in @sgtable that may be filled * @extraction_flags: Flags to qualify the request * * Extract the page fragments from the given amount of the source iterator and * add them to a scatterlist that refers to all of those bits, to a maximum * addition of @sg_max elements. * * The pages referred to by UBUF- and IOVEC-type iterators are extracted and * pinned; BVEC-, KVEC-, FOLIOQ- and XARRAY-type are extracted but aren't * pinned; DISCARD-type is not supported. * * No end mark is placed on the scatterlist; that's left to the caller. * * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA * be allowed on the pages extracted. * * If successful, @sgtable->nents is updated to include the number of elements * added and the number of bytes added is returned. @sgtable->orig_nents is * left unaltered. * * The iov_iter_extract_mode() function should be used to query how cleanup * should be performed. */ ssize_t extract_iter_to_sg(struct iov_iter *iter, size_t maxsize, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags) { if (maxsize == 0) return 0; switch (iov_iter_type(iter)) { case ITER_UBUF: case ITER_IOVEC: return extract_user_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); case ITER_BVEC: return extract_bvec_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); case ITER_KVEC: return extract_kvec_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); case ITER_FOLIOQ: return extract_folioq_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); case ITER_XARRAY: return extract_xarray_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); default: pr_err("%s(%u) unsupported\n", __func__, iov_iter_type(iter)); WARN_ON_ONCE(1); return -EIO; } } EXPORT_SYMBOL_GPL(extract_iter_to_sg); |
| 2 2 6 6 1 9 2 9 2 8 9 9 1 9 3 1 1 3 3 3 3 3 3 3 3 3 3 3 3 1 1 1 1 1 3 3 3 3 3 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 3 3 3 3 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 | // SPDX-License-Identifier: GPL-2.0 #include <linux/jhash.h> #include <linux/netfilter.h> #include <linux/rcupdate.h> #include <linux/rhashtable.h> #include <linux/vmalloc.h> #include <net/genetlink.h> #include <net/netns/generic.h> #include <uapi/linux/genetlink.h> #include "ila.h" struct ila_xlat_params { struct ila_params ip; int ifindex; }; struct ila_map { struct ila_xlat_params xp; struct rhash_head node; struct ila_map __rcu *next; struct rcu_head rcu; }; #define MAX_LOCKS 1024 #define LOCKS_PER_CPU 10 static int alloc_ila_locks(struct ila_net *ilan) { return alloc_bucket_spinlocks(&ilan->xlat.locks, &ilan->xlat.locks_mask, MAX_LOCKS, LOCKS_PER_CPU, GFP_KERNEL); } static u32 hashrnd __read_mostly; static __always_inline void __ila_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); } static inline u32 ila_locator_hash(struct ila_locator loc) { u32 *v = (u32 *)loc.v32; __ila_hash_secret_init(); return jhash_2words(v[0], v[1], hashrnd); } static inline spinlock_t *ila_get_lock(struct ila_net *ilan, struct ila_locator loc) { return &ilan->xlat.locks[ila_locator_hash(loc) & ilan->xlat.locks_mask]; } static inline int ila_cmp_wildcards(struct ila_map *ila, struct ila_addr *iaddr, int ifindex) { return (ila->xp.ifindex && ila->xp.ifindex != ifindex); } static inline int ila_cmp_params(struct ila_map *ila, struct ila_xlat_params *xp) { return (ila->xp.ifindex != xp->ifindex); } static int ila_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) { const struct ila_map *ila = obj; return (ila->xp.ip.locator_match.v64 != *(__be64 *)arg->key); } static inline int ila_order(struct ila_map *ila) { int score = 0; if (ila->xp.ifindex) score += 1 << 1; return score; } static const struct rhashtable_params rht_params = { .nelem_hint = 1024, .head_offset = offsetof(struct ila_map, node), .key_offset = offsetof(struct ila_map, xp.ip.locator_match), .key_len = sizeof(u64), /* identifier */ .max_size = 1048576, .min_size = 256, .automatic_shrinking = true, .obj_cmpfn = ila_cmpfn, }; static int parse_nl_config(struct genl_info *info, struct ila_xlat_params *xp) { memset(xp, 0, sizeof(*xp)); if (info->attrs[ILA_ATTR_LOCATOR]) xp->ip.locator.v64 = (__force __be64)nla_get_u64( info->attrs[ILA_ATTR_LOCATOR]); if (info->attrs[ILA_ATTR_LOCATOR_MATCH]) xp->ip.locator_match.v64 = (__force __be64)nla_get_u64( info->attrs[ILA_ATTR_LOCATOR_MATCH]); if (info->attrs[ILA_ATTR_CSUM_MODE]) xp->ip.csum_mode = nla_get_u8(info->attrs[ILA_ATTR_CSUM_MODE]); else xp->ip.csum_mode = ILA_CSUM_NO_ACTION; if (info->attrs[ILA_ATTR_IDENT_TYPE]) xp->ip.ident_type = nla_get_u8( info->attrs[ILA_ATTR_IDENT_TYPE]); else xp->ip.ident_type = ILA_ATYPE_USE_FORMAT; if (info->attrs[ILA_ATTR_IFINDEX]) xp->ifindex = nla_get_s32(info->attrs[ILA_ATTR_IFINDEX]); return 0; } /* Must be called with rcu readlock */ static inline struct ila_map *ila_lookup_wildcards(struct ila_addr *iaddr, int ifindex, struct ila_net *ilan) { struct ila_map *ila; ila = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &iaddr->loc, rht_params); while (ila) { if (!ila_cmp_wildcards(ila, iaddr, ifindex)) return ila; ila = rcu_access_pointer(ila->next); } return NULL; } /* Must be called with rcu readlock */ static inline struct ila_map *ila_lookup_by_params(struct ila_xlat_params *xp, struct ila_net *ilan) { struct ila_map *ila; ila = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &xp->ip.locator_match, rht_params); while (ila) { if (!ila_cmp_params(ila, xp)) return ila; ila = rcu_access_pointer(ila->next); } return NULL; } static inline void ila_release(struct ila_map *ila) { kfree_rcu(ila, rcu); } static void ila_free_node(struct ila_map *ila) { struct ila_map *next; /* Assume rcu_readlock held */ while (ila) { next = rcu_access_pointer(ila->next); ila_release(ila); ila = next; } } static void ila_free_cb(void *ptr, void *arg) { ila_free_node((struct ila_map *)ptr); } static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila); static unsigned int ila_nf_input(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { ila_xlat_addr(skb, false); return NF_ACCEPT; } static const struct nf_hook_ops ila_nf_hook_ops[] = { { .hook = ila_nf_input, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = -1, }, }; static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) { struct ila_net *ilan = net_generic(net, ila_net_id); struct ila_map *ila, *head; spinlock_t *lock = ila_get_lock(ilan, xp->ip.locator_match); int err = 0, order; if (!ilan->xlat.hooks_registered) { /* We defer registering net hooks in the namespace until the * first mapping is added. */ err = nf_register_net_hooks(net, ila_nf_hook_ops, ARRAY_SIZE(ila_nf_hook_ops)); if (err) return err; ilan->xlat.hooks_registered = true; } ila = kzalloc(sizeof(*ila), GFP_KERNEL); if (!ila) return -ENOMEM; ila_init_saved_csum(&xp->ip); ila->xp = *xp; order = ila_order(ila); spin_lock(lock); head = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &xp->ip.locator_match, rht_params); if (!head) { /* New entry for the rhash_table */ err = rhashtable_lookup_insert_fast(&ilan->xlat.rhash_table, &ila->node, rht_params); } else { struct ila_map *tila = head, *prev = NULL; do { if (!ila_cmp_params(tila, xp)) { err = -EEXIST; goto out; } if (order > ila_order(tila)) break; prev = tila; tila = rcu_dereference_protected(tila->next, lockdep_is_held(lock)); } while (tila); if (prev) { /* Insert in sub list of head */ RCU_INIT_POINTER(ila->next, tila); rcu_assign_pointer(prev->next, ila); } else { /* Make this ila new head */ RCU_INIT_POINTER(ila->next, head); err = rhashtable_replace_fast(&ilan->xlat.rhash_table, &head->node, &ila->node, rht_params); if (err) goto out; } } out: spin_unlock(lock); if (err) kfree(ila); return err; } static int ila_del_mapping(struct net *net, struct ila_xlat_params *xp) { struct ila_net *ilan = net_generic(net, ila_net_id); struct ila_map *ila, *head, *prev; spinlock_t *lock = ila_get_lock(ilan, xp->ip.locator_match); int err = -ENOENT; spin_lock(lock); head = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &xp->ip.locator_match, rht_params); ila = head; prev = NULL; while (ila) { if (ila_cmp_params(ila, xp)) { prev = ila; ila = rcu_dereference_protected(ila->next, lockdep_is_held(lock)); continue; } err = 0; if (prev) { /* Not head, just delete from list */ rcu_assign_pointer(prev->next, ila->next); } else { /* It is the head. If there is something in the * sublist we need to make a new head. */ head = rcu_dereference_protected(ila->next, lockdep_is_held(lock)); if (head) { /* Put first entry in the sublist into the * table */ err = rhashtable_replace_fast( &ilan->xlat.rhash_table, &ila->node, &head->node, rht_params); if (err) goto out; } else { /* Entry no longer used */ err = rhashtable_remove_fast( &ilan->xlat.rhash_table, &ila->node, rht_params); } } ila_release(ila); break; } out: spin_unlock(lock); return err; } int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct ila_xlat_params p; int err; err = parse_nl_config(info, &p); if (err) return err; return ila_add_mapping(net, &p); } int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct ila_xlat_params xp; int err; err = parse_nl_config(info, &xp); if (err) return err; ila_del_mapping(net, &xp); return 0; } static inline spinlock_t *lock_from_ila_map(struct ila_net *ilan, struct ila_map *ila) { return ila_get_lock(ilan, ila->xp.ip.locator_match); } int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct ila_net *ilan = net_generic(net, ila_net_id); struct rhashtable_iter iter; struct ila_map *ila; spinlock_t *lock; int ret = 0; rhashtable_walk_enter(&ilan->xlat.rhash_table, &iter); rhashtable_walk_start(&iter); for (;;) { ila = rhashtable_walk_next(&iter); if (IS_ERR(ila)) { if (PTR_ERR(ila) == -EAGAIN) continue; ret = PTR_ERR(ila); goto done; } else if (!ila) { break; } lock = lock_from_ila_map(ilan, ila); spin_lock(lock); ret = rhashtable_remove_fast(&ilan->xlat.rhash_table, &ila->node, rht_params); if (!ret) ila_free_node(ila); spin_unlock(lock); if (ret) break; } done: rhashtable_walk_stop(&iter); rhashtable_walk_exit(&iter); return ret; } static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg) { if (nla_put_u64_64bit(msg, ILA_ATTR_LOCATOR, (__force u64)ila->xp.ip.locator.v64, ILA_ATTR_PAD) || nla_put_u64_64bit(msg, ILA_ATTR_LOCATOR_MATCH, (__force u64)ila->xp.ip.locator_match.v64, ILA_ATTR_PAD) || nla_put_s32(msg, ILA_ATTR_IFINDEX, ila->xp.ifindex) || nla_put_u8(msg, ILA_ATTR_CSUM_MODE, ila->xp.ip.csum_mode) || nla_put_u8(msg, ILA_ATTR_IDENT_TYPE, ila->xp.ip.ident_type)) return -1; return 0; } static int ila_dump_info(struct ila_map *ila, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &ila_nl_family, flags, cmd); if (!hdr) return -ENOMEM; if (ila_fill_info(ila, skb) < 0) goto nla_put_failure; genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct ila_net *ilan = net_generic(net, ila_net_id); struct sk_buff *msg; struct ila_xlat_params xp; struct ila_map *ila; int ret; ret = parse_nl_config(info, &xp); if (ret) return ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; rcu_read_lock(); ret = -ESRCH; ila = ila_lookup_by_params(&xp, ilan); if (ila) { ret = ila_dump_info(ila, info->snd_portid, info->snd_seq, 0, msg, info->genlhdr->cmd); } rcu_read_unlock(); if (ret < 0) goto out_free; return genlmsg_reply(msg, info); out_free: nlmsg_free(msg); return ret; } struct ila_dump_iter { struct rhashtable_iter rhiter; int skip; }; int ila_xlat_nl_dump_start(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct ila_net *ilan = net_generic(net, ila_net_id); struct ila_dump_iter *iter; iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return -ENOMEM; rhashtable_walk_enter(&ilan->xlat.rhash_table, &iter->rhiter); iter->skip = 0; cb->args[0] = (long)iter; return 0; } int ila_xlat_nl_dump_done(struct netlink_callback *cb) { struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0]; rhashtable_walk_exit(&iter->rhiter); kfree(iter); return 0; } int ila_xlat_nl_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0]; struct rhashtable_iter *rhiter = &iter->rhiter; int skip = iter->skip; struct ila_map *ila; int ret; rhashtable_walk_start(rhiter); /* Get first entry */ ila = rhashtable_walk_peek(rhiter); if (ila && !IS_ERR(ila) && skip) { /* Skip over visited entries */ while (ila && skip) { /* Skip over any ila entries in this list that we * have already dumped. */ ila = rcu_access_pointer(ila->next); skip--; } } skip = 0; for (;;) { if (IS_ERR(ila)) { ret = PTR_ERR(ila); if (ret == -EAGAIN) { /* Table has changed and iter has reset. Return * -EAGAIN to the application even if we have * written data to the skb. The application * needs to deal with this. */ goto out_ret; } else { break; } } else if (!ila) { ret = 0; break; } while (ila) { ret = ila_dump_info(ila, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, ILA_CMD_GET); if (ret) goto out; skip++; ila = rcu_access_pointer(ila->next); } skip = 0; ila = rhashtable_walk_next(rhiter); } out: iter->skip = skip; ret = (skb->len ? : ret); out_ret: rhashtable_walk_stop(rhiter); return ret; } int ila_xlat_init_net(struct net *net) { struct ila_net *ilan = net_generic(net, ila_net_id); int err; err = alloc_ila_locks(ilan); if (err) return err; err = rhashtable_init(&ilan->xlat.rhash_table, &rht_params); if (err) { free_bucket_spinlocks(ilan->xlat.locks); return err; } return 0; } void ila_xlat_pre_exit_net(struct net *net) { struct ila_net *ilan = net_generic(net, ila_net_id); if (ilan->xlat.hooks_registered) nf_unregister_net_hooks(net, ila_nf_hook_ops, ARRAY_SIZE(ila_nf_hook_ops)); } void ila_xlat_exit_net(struct net *net) { struct ila_net *ilan = net_generic(net, ila_net_id); rhashtable_free_and_destroy(&ilan->xlat.rhash_table, ila_free_cb, NULL); free_bucket_spinlocks(ilan->xlat.locks); } static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) { struct ila_map *ila; struct ipv6hdr *ip6h = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); struct ila_net *ilan = net_generic(net, ila_net_id); struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); /* Assumes skb contains a valid IPv6 header that is pulled */ /* No check here that ILA type in the mapping matches what is in the * address. We assume that whatever sender gaves us can be translated. * The checksum mode however is relevant. */ rcu_read_lock(); ila = ila_lookup_wildcards(iaddr, skb->dev->ifindex, ilan); if (ila) ila_update_ipv6_locator(skb, &ila->xp.ip, sir2ila); rcu_read_unlock(); return 0; } |
| 20 20 20 20 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 | // SPDX-License-Identifier: GPL-2.0-or-later /* 6LoWPAN fragment reassembly * * Authors: * Alexander Aring <aar@pengutronix.de> * * Based on: net/ipv6/reassembly.c */ #define pr_fmt(fmt) "6LoWPAN: " fmt #include <linux/net.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/jhash.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/export.h> #include <net/ieee802154_netdev.h> #include <net/6lowpan.h> #include <net/ipv6_frag.h> #include <net/inet_frag.h> #include <net/ip.h> #include "6lowpan_i.h" static const char lowpan_frags_cache_name[] = "lowpan-frags"; static struct inet_frags lowpan_frags; static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev, struct net_device *ldev); static void lowpan_frag_init(struct inet_frag_queue *q, const void *a) { const struct frag_lowpan_compare_key *key = a; BUILD_BUG_ON(sizeof(*key) > sizeof(q->key)); memcpy(&q->key, key, sizeof(*key)); } static void lowpan_frag_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; fq = container_of(frag, struct frag_queue, q); spin_lock(&fq->q.lock); if (fq->q.flags & INET_FRAG_COMPLETE) goto out; inet_frag_kill(&fq->q); out: spin_unlock(&fq->q.lock); inet_frag_put(&fq->q); } static inline struct lowpan_frag_queue * fq_find(struct net *net, const struct lowpan_802154_cb *cb, const struct ieee802154_addr *src, const struct ieee802154_addr *dst) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); struct frag_lowpan_compare_key key = {}; struct inet_frag_queue *q; key.tag = cb->d_tag; key.d_size = cb->d_size; key.src = *src; key.dst = *dst; q = inet_frag_find(ieee802154_lowpan->fqdir, &key); if (!q) return NULL; return container_of(q, struct lowpan_frag_queue, q); } static int lowpan_frag_queue(struct lowpan_frag_queue *fq, struct sk_buff *skb, u8 frag_type) { struct sk_buff *prev_tail; struct net_device *ldev; int end, offset, err; /* inet_frag_queue_* functions use skb->cb; see struct ipfrag_skb_cb * in inet_fragment.c */ BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(struct inet_skb_parm)); BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(struct inet6_skb_parm)); if (fq->q.flags & INET_FRAG_COMPLETE) goto err; offset = lowpan_802154_cb(skb)->d_offset << 3; end = lowpan_802154_cb(skb)->d_size; /* Is this the final fragment? */ if (offset + skb->len == end) { /* If we already have some bits beyond end * or have different end, the segment is corrupted. */ if (end < fq->q.len || ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) goto err; fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ if (fq->q.flags & INET_FRAG_LAST_IN) goto err; fq->q.len = end; } } ldev = skb->dev; if (ldev) skb->dev = NULL; barrier(); prev_tail = fq->q.fragments_tail; err = inet_frag_queue_insert(&fq->q, skb, offset, end); if (err) goto err; fq->q.stamp = skb->tstamp; fq->q.tstamp_type = skb->tstamp_type; if (frag_type == LOWPAN_DISPATCH_FRAG1) fq->q.flags |= INET_FRAG_FIRST_IN; fq->q.meat += skb->len; add_frag_mem_limit(fq->q.fqdir, skb->truesize); if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { int res; unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; res = lowpan_frag_reasm(fq, skb, prev_tail, ldev); skb->_skb_refdst = orefdst; return res; } skb_dst_drop(skb); return -1; err: kfree_skb(skb); return -1; } /* Check if this packet is complete. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *ldev) { void *reasm_data; inet_frag_kill(&fq->q); reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); if (!reasm_data) goto out_oom; inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); skb->dev = ldev; skb->tstamp = fq->q.stamp; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; fq->q.last_run_head = NULL; return 1; out_oom: net_dbg_ratelimited("lowpan_frag_reasm: no memory for reassembly\n"); return -1; } static int lowpan_frag_rx_handlers_result(struct sk_buff *skb, lowpan_rx_result res) { switch (res) { case RX_QUEUED: return NET_RX_SUCCESS; case RX_CONTINUE: /* nobody cared about this packet */ net_warn_ratelimited("%s: received unknown dispatch\n", __func__); fallthrough; default: /* all others failure */ return NET_RX_DROP; } } static lowpan_rx_result lowpan_frag_rx_h_iphc(struct sk_buff *skb) { int ret; if (!lowpan_is_iphc(*skb_network_header(skb))) return RX_CONTINUE; ret = lowpan_iphc_decompress(skb); if (ret < 0) return RX_DROP; return RX_QUEUED; } static int lowpan_invoke_frag_rx_handlers(struct sk_buff *skb) { lowpan_rx_result res; #define CALL_RXH(rxh) \ do { \ res = rxh(skb); \ if (res != RX_CONTINUE) \ goto rxh_next; \ } while (0) /* likely at first */ CALL_RXH(lowpan_frag_rx_h_iphc); CALL_RXH(lowpan_rx_h_ipv6); rxh_next: return lowpan_frag_rx_handlers_result(skb, res); #undef CALL_RXH } #define LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK 0x07 #define LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT 8 static int lowpan_get_cb(struct sk_buff *skb, u8 frag_type, struct lowpan_802154_cb *cb) { bool fail; u8 high = 0, low = 0; __be16 d_tag = 0; fail = lowpan_fetch_skb(skb, &high, 1); fail |= lowpan_fetch_skb(skb, &low, 1); /* remove the dispatch value and use first three bits as high value * for the datagram size */ cb->d_size = (high & LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK) << LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT | low; fail |= lowpan_fetch_skb(skb, &d_tag, 2); cb->d_tag = ntohs(d_tag); if (frag_type == LOWPAN_DISPATCH_FRAGN) { fail |= lowpan_fetch_skb(skb, &cb->d_offset, 1); } else { skb_reset_network_header(skb); cb->d_offset = 0; /* check if datagram_size has ipv6hdr on FRAG1 */ fail |= cb->d_size < sizeof(struct ipv6hdr); /* check if we can dereference the dispatch value */ fail |= !skb->len; } if (unlikely(fail)) return -EIO; return 0; } int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type) { struct lowpan_frag_queue *fq; struct net *net = dev_net(skb->dev); struct lowpan_802154_cb *cb = lowpan_802154_cb(skb); struct ieee802154_hdr hdr = {}; int err; if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) goto err; err = lowpan_get_cb(skb, frag_type, cb); if (err < 0) goto err; if (frag_type == LOWPAN_DISPATCH_FRAG1) { err = lowpan_invoke_frag_rx_handlers(skb); if (err == NET_RX_DROP) goto err; } if (cb->d_size > IPV6_MIN_MTU) { net_warn_ratelimited("lowpan_frag_rcv: datagram size exceeds MTU\n"); goto err; } fq = fq_find(net, cb, &hdr.source, &hdr.dest); if (fq != NULL) { int ret; spin_lock(&fq->q.lock); ret = lowpan_frag_queue(fq, skb, frag_type); spin_unlock(&fq->q.lock); inet_frag_put(&fq->q); return ret; } err: kfree_skb(skb); return -1; } #ifdef CONFIG_SYSCTL static struct ctl_table lowpan_frags_ns_ctl_table[] = { { .procname = "6lowpanfrag_high_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "6lowpanfrag_low_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "6lowpanfrag_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, }; /* secret interval has been deprecated */ static int lowpan_frags_secret_interval_unused; static struct ctl_table lowpan_frags_ctl_table[] = { { .procname = "6lowpanfrag_secret_interval", .data = &lowpan_frags_secret_interval_unused, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, }; static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); size_t table_size = ARRAY_SIZE(lowpan_frags_ns_ctl_table); table = lowpan_frags_ns_ctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(lowpan_frags_ns_ctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) table_size = 0; } table[0].data = &ieee802154_lowpan->fqdir->high_thresh; table[0].extra1 = &ieee802154_lowpan->fqdir->low_thresh; table[1].data = &ieee802154_lowpan->fqdir->low_thresh; table[1].extra2 = &ieee802154_lowpan->fqdir->high_thresh; table[2].data = &ieee802154_lowpan->fqdir->timeout; hdr = register_net_sysctl_sz(net, "net/ieee802154/6lowpan", table, table_size); if (hdr == NULL) goto err_reg; ieee802154_lowpan->sysctl.frags_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void __net_exit lowpan_frags_ns_sysctl_unregister(struct net *net) { const struct ctl_table *table; struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); table = ieee802154_lowpan->sysctl.frags_hdr->ctl_table_arg; unregister_net_sysctl_table(ieee802154_lowpan->sysctl.frags_hdr); if (!net_eq(net, &init_net)) kfree(table); } static struct ctl_table_header *lowpan_ctl_header; static int __init lowpan_frags_sysctl_register(void) { lowpan_ctl_header = register_net_sysctl(&init_net, "net/ieee802154/6lowpan", lowpan_frags_ctl_table); return lowpan_ctl_header == NULL ? -ENOMEM : 0; } static void lowpan_frags_sysctl_unregister(void) { unregister_net_sysctl_table(lowpan_ctl_header); } #else static inline int lowpan_frags_ns_sysctl_register(struct net *net) { return 0; } static inline void lowpan_frags_ns_sysctl_unregister(struct net *net) { } static inline int __init lowpan_frags_sysctl_register(void) { return 0; } static inline void lowpan_frags_sysctl_unregister(void) { } #endif static int __net_init lowpan_frags_init_net(struct net *net) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); int res; res = fqdir_init(&ieee802154_lowpan->fqdir, &lowpan_frags, net); if (res < 0) return res; ieee802154_lowpan->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; ieee802154_lowpan->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; ieee802154_lowpan->fqdir->timeout = IPV6_FRAG_TIMEOUT; res = lowpan_frags_ns_sysctl_register(net); if (res < 0) fqdir_exit(ieee802154_lowpan->fqdir); return res; } static void __net_exit lowpan_frags_pre_exit_net(struct net *net) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); fqdir_pre_exit(ieee802154_lowpan->fqdir); } static void __net_exit lowpan_frags_exit_net(struct net *net) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); lowpan_frags_ns_sysctl_unregister(net); fqdir_exit(ieee802154_lowpan->fqdir); } static struct pernet_operations lowpan_frags_ops = { .init = lowpan_frags_init_net, .pre_exit = lowpan_frags_pre_exit_net, .exit = lowpan_frags_exit_net, }; static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed) { return jhash2(data, sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed); } static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed) { const struct inet_frag_queue *fq = data; return jhash2((const u32 *)&fq->key, sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed); } static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) { const struct frag_lowpan_compare_key *key = arg->key; const struct inet_frag_queue *fq = ptr; return !!memcmp(&fq->key, key, sizeof(*key)); } static const struct rhashtable_params lowpan_rhash_params = { .head_offset = offsetof(struct inet_frag_queue, node), .hashfn = lowpan_key_hashfn, .obj_hashfn = lowpan_obj_hashfn, .obj_cmpfn = lowpan_obj_cmpfn, .automatic_shrinking = true, }; int __init lowpan_net_frag_init(void) { int ret; lowpan_frags.constructor = lowpan_frag_init; lowpan_frags.destructor = NULL; lowpan_frags.qsize = sizeof(struct frag_queue); lowpan_frags.frag_expire = lowpan_frag_expire; lowpan_frags.frags_cache_name = lowpan_frags_cache_name; lowpan_frags.rhash_params = lowpan_rhash_params; ret = inet_frags_init(&lowpan_frags); if (ret) goto out; ret = lowpan_frags_sysctl_register(); if (ret) goto err_sysctl; ret = register_pernet_subsys(&lowpan_frags_ops); if (ret) goto err_pernet; out: return ret; err_pernet: lowpan_frags_sysctl_unregister(); err_sysctl: inet_frags_fini(&lowpan_frags); return ret; } void lowpan_net_frag_exit(void) { lowpan_frags_sysctl_unregister(); unregister_pernet_subsys(&lowpan_frags_ops); inet_frags_fini(&lowpan_frags); } |
| 6 2 3 6 6 5 4 3 3 3 3 2 3 2 2 2 2 1 1 1 1 6 6 6 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 8 18 17 17 16 17 17 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * kexec.c - kexec system call core code. * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/btf.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/kexec.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/highmem.h> #include <linux/syscalls.h> #include <linux/reboot.h> #include <linux/ioport.h> #include <linux/hardirq.h> #include <linux/elf.h> #include <linux/elfcore.h> #include <linux/utsname.h> #include <linux/numa.h> #include <linux/suspend.h> #include <linux/device.h> #include <linux/freezer.h> #include <linux/panic_notifier.h> #include <linux/pm.h> #include <linux/cpu.h> #include <linux/uaccess.h> #include <linux/io.h> #include <linux/console.h> #include <linux/vmalloc.h> #include <linux/swap.h> #include <linux/syscore_ops.h> #include <linux/compiler.h> #include <linux/hugetlb.h> #include <linux/objtool.h> #include <linux/kmsg_dump.h> #include <asm/page.h> #include <asm/sections.h> #include <crypto/hash.h> #include "kexec_internal.h" atomic_t __kexec_lock = ATOMIC_INIT(0); /* Flag to indicate we are going to kexec a new kernel */ bool kexec_in_progress = false; bool kexec_file_dbg_print; /* * When kexec transitions to the new kernel there is a one-to-one * mapping between physical and virtual addresses. On processors * where you can disable the MMU this is trivial, and easy. For * others it is still a simple predictable page table to setup. * * In that environment kexec copies the new kernel to its final * resting place. This means I can only support memory whose * physical address can fit in an unsigned long. In particular * addresses where (pfn << PAGE_SHIFT) > ULONG_MAX cannot be handled. * If the assembly stub has more restrictive requirements * KEXEC_SOURCE_MEMORY_LIMIT and KEXEC_DEST_MEMORY_LIMIT can be * defined more restrictively in <asm/kexec.h>. * * The code for the transition from the current kernel to the * new kernel is placed in the control_code_buffer, whose size * is given by KEXEC_CONTROL_PAGE_SIZE. In the best case only a single * page of memory is necessary, but some architectures require more. * Because this memory must be identity mapped in the transition from * virtual to physical addresses it must live in the range * 0 - TASK_SIZE, as only the user space mappings are arbitrarily * modifiable. * * The assembly stub in the control code buffer is passed a linked list * of descriptor pages detailing the source pages of the new kernel, * and the destination addresses of those source pages. As this data * structure is not used in the context of the current OS, it must * be self-contained. * * The code has been made to work with highmem pages and will use a * destination page in its final resting place (if it happens * to allocate it). The end product of this is that most of the * physical address space, and most of RAM can be used. * * Future directions include: * - allocating a page table with the control code buffer identity * mapped, to simplify machine_kexec and make kexec_on_panic more * reliable. */ /* * KIMAGE_NO_DEST is an impossible destination address..., for * allocating pages whose destination address we do not care about. */ #define KIMAGE_NO_DEST (-1UL) #define PAGE_COUNT(x) (((x) + PAGE_SIZE - 1) >> PAGE_SHIFT) static struct page *kimage_alloc_page(struct kimage *image, gfp_t gfp_mask, unsigned long dest); int sanity_check_segment_list(struct kimage *image) { int i; unsigned long nr_segments = image->nr_segments; unsigned long total_pages = 0; unsigned long nr_pages = totalram_pages(); /* * Verify we have good destination addresses. The caller is * responsible for making certain we don't attempt to load * the new image into invalid or reserved areas of RAM. This * just verifies it is an address we can use. * * Since the kernel does everything in page size chunks ensure * the destination addresses are page aligned. Too many * special cases crop of when we don't do this. The most * insidious is getting overlapping destination addresses * simply because addresses are changed to page size * granularity. */ for (i = 0; i < nr_segments; i++) { unsigned long mstart, mend; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz; if (mstart > mend) return -EADDRNOTAVAIL; if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK)) return -EADDRNOTAVAIL; if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT) return -EADDRNOTAVAIL; } /* Verify our destination addresses do not overlap. * If we alloed overlapping destination addresses * through very weird things can happen with no * easy explanation as one segment stops on another. */ for (i = 0; i < nr_segments; i++) { unsigned long mstart, mend; unsigned long j; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz; for (j = 0; j < i; j++) { unsigned long pstart, pend; pstart = image->segment[j].mem; pend = pstart + image->segment[j].memsz; /* Do the segments overlap ? */ if ((mend > pstart) && (mstart < pend)) return -EINVAL; } } /* Ensure our buffer sizes are strictly less than * our memory sizes. This should always be the case, * and it is easier to check up front than to be surprised * later on. */ for (i = 0; i < nr_segments; i++) { if (image->segment[i].bufsz > image->segment[i].memsz) return -EINVAL; } /* * Verify that no more than half of memory will be consumed. If the * request from userspace is too large, a large amount of time will be * wasted allocating pages, which can cause a soft lockup. */ for (i = 0; i < nr_segments; i++) { if (PAGE_COUNT(image->segment[i].memsz) > nr_pages / 2) return -EINVAL; total_pages += PAGE_COUNT(image->segment[i].memsz); } if (total_pages > nr_pages / 2) return -EINVAL; #ifdef CONFIG_CRASH_DUMP /* * Verify we have good destination addresses. Normally * the caller is responsible for making certain we don't * attempt to load the new image into invalid or reserved * areas of RAM. But crash kernels are preloaded into a * reserved area of ram. We must ensure the addresses * are in the reserved area otherwise preloading the * kernel could corrupt things. */ if (image->type == KEXEC_TYPE_CRASH) { for (i = 0; i < nr_segments; i++) { unsigned long mstart, mend; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz - 1; /* Ensure we are within the crash kernel limits */ if ((mstart < phys_to_boot_phys(crashk_res.start)) || (mend > phys_to_boot_phys(crashk_res.end))) return -EADDRNOTAVAIL; } } #endif return 0; } struct kimage *do_kimage_alloc_init(void) { struct kimage *image; /* Allocate a controlling structure */ image = kzalloc(sizeof(*image), GFP_KERNEL); if (!image) return NULL; image->head = 0; image->entry = &image->head; image->last_entry = &image->head; image->control_page = ~0; /* By default this does not apply */ image->type = KEXEC_TYPE_DEFAULT; /* Initialize the list of control pages */ INIT_LIST_HEAD(&image->control_pages); /* Initialize the list of destination pages */ INIT_LIST_HEAD(&image->dest_pages); /* Initialize the list of unusable pages */ INIT_LIST_HEAD(&image->unusable_pages); #ifdef CONFIG_CRASH_HOTPLUG image->hp_action = KEXEC_CRASH_HP_NONE; image->elfcorehdr_index = -1; image->elfcorehdr_updated = false; #endif return image; } int kimage_is_destination_range(struct kimage *image, unsigned long start, unsigned long end) { unsigned long i; for (i = 0; i < image->nr_segments; i++) { unsigned long mstart, mend; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz - 1; if ((end >= mstart) && (start <= mend)) return 1; } return 0; } static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order) { struct page *pages; if (fatal_signal_pending(current)) return NULL; pages = alloc_pages(gfp_mask & ~__GFP_ZERO, order); if (pages) { unsigned int count, i; pages->mapping = NULL; set_page_private(pages, order); count = 1 << order; for (i = 0; i < count; i++) SetPageReserved(pages + i); arch_kexec_post_alloc_pages(page_address(pages), count, gfp_mask); if (gfp_mask & __GFP_ZERO) for (i = 0; i < count; i++) clear_highpage(pages + i); } return pages; } static void kimage_free_pages(struct page *page) { unsigned int order, count, i; order = page_private(page); count = 1 << order; arch_kexec_pre_free_pages(page_address(page), count); for (i = 0; i < count; i++) ClearPageReserved(page + i); __free_pages(page, order); } void kimage_free_page_list(struct list_head *list) { struct page *page, *next; list_for_each_entry_safe(page, next, list, lru) { list_del(&page->lru); kimage_free_pages(page); } } static struct page *kimage_alloc_normal_control_pages(struct kimage *image, unsigned int order) { /* Control pages are special, they are the intermediaries * that are needed while we copy the rest of the pages * to their final resting place. As such they must * not conflict with either the destination addresses * or memory the kernel is already using. * * The only case where we really need more than one of * these are for architectures where we cannot disable * the MMU and must instead generate an identity mapped * page table for all of the memory. * * At worst this runs in O(N) of the image size. */ struct list_head extra_pages; struct page *pages; unsigned int count; count = 1 << order; INIT_LIST_HEAD(&extra_pages); /* Loop while I can allocate a page and the page allocated * is a destination page. */ do { unsigned long pfn, epfn, addr, eaddr; pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order); if (!pages) break; pfn = page_to_boot_pfn(pages); epfn = pfn + count; addr = pfn << PAGE_SHIFT; eaddr = (epfn << PAGE_SHIFT) - 1; if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) || kimage_is_destination_range(image, addr, eaddr)) { list_add(&pages->lru, &extra_pages); pages = NULL; } } while (!pages); if (pages) { /* Remember the allocated page... */ list_add(&pages->lru, &image->control_pages); /* Because the page is already in it's destination * location we will never allocate another page at * that address. Therefore kimage_alloc_pages * will not return it (again) and we don't need * to give it an entry in image->segment[]. */ } /* Deal with the destination pages I have inadvertently allocated. * * Ideally I would convert multi-page allocations into single * page allocations, and add everything to image->dest_pages. * * For now it is simpler to just free the pages. */ kimage_free_page_list(&extra_pages); return pages; } #ifdef CONFIG_CRASH_DUMP static struct page *kimage_alloc_crash_control_pages(struct kimage *image, unsigned int order) { /* Control pages are special, they are the intermediaries * that are needed while we copy the rest of the pages * to their final resting place. As such they must * not conflict with either the destination addresses * or memory the kernel is already using. * * Control pages are also the only pags we must allocate * when loading a crash kernel. All of the other pages * are specified by the segments and we just memcpy * into them directly. * * The only case where we really need more than one of * these are for architectures where we cannot disable * the MMU and must instead generate an identity mapped * page table for all of the memory. * * Given the low demand this implements a very simple * allocator that finds the first hole of the appropriate * size in the reserved memory region, and allocates all * of the memory up to and including the hole. */ unsigned long hole_start, hole_end, size; struct page *pages; pages = NULL; size = (1 << order) << PAGE_SHIFT; hole_start = ALIGN(image->control_page, size); hole_end = hole_start + size - 1; while (hole_end <= crashk_res.end) { unsigned long i; cond_resched(); if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT) break; /* See if I overlap any of the segments */ for (i = 0; i < image->nr_segments; i++) { unsigned long mstart, mend; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz - 1; if ((hole_end >= mstart) && (hole_start <= mend)) { /* Advance the hole to the end of the segment */ hole_start = ALIGN(mend, size); hole_end = hole_start + size - 1; break; } } /* If I don't overlap any segments I have found my hole! */ if (i == image->nr_segments) { pages = pfn_to_page(hole_start >> PAGE_SHIFT); image->control_page = hole_end + 1; break; } } /* Ensure that these pages are decrypted if SME is enabled. */ if (pages) arch_kexec_post_alloc_pages(page_address(pages), 1 << order, 0); return pages; } #endif struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order) { struct page *pages = NULL; switch (image->type) { case KEXEC_TYPE_DEFAULT: pages = kimage_alloc_normal_control_pages(image, order); break; #ifdef CONFIG_CRASH_DUMP case KEXEC_TYPE_CRASH: pages = kimage_alloc_crash_control_pages(image, order); break; #endif } return pages; } static int kimage_add_entry(struct kimage *image, kimage_entry_t entry) { if (*image->entry != 0) image->entry++; if (image->entry == image->last_entry) { kimage_entry_t *ind_page; struct page *page; page = kimage_alloc_page(image, GFP_KERNEL, KIMAGE_NO_DEST); if (!page) return -ENOMEM; ind_page = page_address(page); *image->entry = virt_to_boot_phys(ind_page) | IND_INDIRECTION; image->entry = ind_page; image->last_entry = ind_page + ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1); } *image->entry = entry; image->entry++; *image->entry = 0; return 0; } static int kimage_set_destination(struct kimage *image, unsigned long destination) { destination &= PAGE_MASK; return kimage_add_entry(image, destination | IND_DESTINATION); } static int kimage_add_page(struct kimage *image, unsigned long page) { page &= PAGE_MASK; return kimage_add_entry(image, page | IND_SOURCE); } static void kimage_free_extra_pages(struct kimage *image) { /* Walk through and free any extra destination pages I may have */ kimage_free_page_list(&image->dest_pages); /* Walk through and free any unusable pages I have cached */ kimage_free_page_list(&image->unusable_pages); } void kimage_terminate(struct kimage *image) { if (*image->entry != 0) image->entry++; *image->entry = IND_DONE; } #define for_each_kimage_entry(image, ptr, entry) \ for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \ ptr = (entry & IND_INDIRECTION) ? \ boot_phys_to_virt((entry & PAGE_MASK)) : ptr + 1) static void kimage_free_entry(kimage_entry_t entry) { struct page *page; page = boot_pfn_to_page(entry >> PAGE_SHIFT); kimage_free_pages(page); } void kimage_free(struct kimage *image) { kimage_entry_t *ptr, entry; kimage_entry_t ind = 0; if (!image) return; #ifdef CONFIG_CRASH_DUMP if (image->vmcoreinfo_data_copy) { crash_update_vmcoreinfo_safecopy(NULL); vunmap(image->vmcoreinfo_data_copy); } #endif kimage_free_extra_pages(image); for_each_kimage_entry(image, ptr, entry) { if (entry & IND_INDIRECTION) { /* Free the previous indirection page */ if (ind & IND_INDIRECTION) kimage_free_entry(ind); /* Save this indirection page until we are * done with it. */ ind = entry; } else if (entry & IND_SOURCE) kimage_free_entry(entry); } /* Free the final indirection page */ if (ind & IND_INDIRECTION) kimage_free_entry(ind); /* Handle any machine specific cleanup */ machine_kexec_cleanup(image); /* Free the kexec control pages... */ kimage_free_page_list(&image->control_pages); /* * Free up any temporary buffers allocated. This might hit if * error occurred much later after buffer allocation. */ if (image->file_mode) kimage_file_post_load_cleanup(image); kfree(image); } static kimage_entry_t *kimage_dst_used(struct kimage *image, unsigned long page) { kimage_entry_t *ptr, entry; unsigned long destination = 0; for_each_kimage_entry(image, ptr, entry) { if (entry & IND_DESTINATION) destination = entry & PAGE_MASK; else if (entry & IND_SOURCE) { if (page == destination) return ptr; destination += PAGE_SIZE; } } return NULL; } static struct page *kimage_alloc_page(struct kimage *image, gfp_t gfp_mask, unsigned long destination) { /* * Here we implement safeguards to ensure that a source page * is not copied to its destination page before the data on * the destination page is no longer useful. * * To do this we maintain the invariant that a source page is * either its own destination page, or it is not a * destination page at all. * * That is slightly stronger than required, but the proof * that no problems will not occur is trivial, and the * implementation is simply to verify. * * When allocating all pages normally this algorithm will run * in O(N) time, but in the worst case it will run in O(N^2) * time. If the runtime is a problem the data structures can * be fixed. */ struct page *page; unsigned long addr; /* * Walk through the list of destination pages, and see if I * have a match. */ list_for_each_entry(page, &image->dest_pages, lru) { addr = page_to_boot_pfn(page) << PAGE_SHIFT; if (addr == destination) { list_del(&page->lru); return page; } } page = NULL; while (1) { kimage_entry_t *old; /* Allocate a page, if we run out of memory give up */ page = kimage_alloc_pages(gfp_mask, 0); if (!page) return NULL; /* If the page cannot be used file it away */ if (page_to_boot_pfn(page) > (KEXEC_SOURCE_MEMORY_LIMIT >> PAGE_SHIFT)) { list_add(&page->lru, &image->unusable_pages); continue; } addr = page_to_boot_pfn(page) << PAGE_SHIFT; /* If it is the destination page we want use it */ if (addr == destination) break; /* If the page is not a destination page use it */ if (!kimage_is_destination_range(image, addr, addr + PAGE_SIZE - 1)) break; /* * I know that the page is someones destination page. * See if there is already a source page for this * destination page. And if so swap the source pages. */ old = kimage_dst_used(image, addr); if (old) { /* If so move it */ unsigned long old_addr; struct page *old_page; old_addr = *old & PAGE_MASK; old_page = boot_pfn_to_page(old_addr >> PAGE_SHIFT); copy_highpage(page, old_page); *old = addr | (*old & ~PAGE_MASK); /* The old page I have found cannot be a * destination page, so return it if it's * gfp_flags honor the ones passed in. */ if (!(gfp_mask & __GFP_HIGHMEM) && PageHighMem(old_page)) { kimage_free_pages(old_page); continue; } page = old_page; break; } /* Place the page on the destination list, to be used later */ list_add(&page->lru, &image->dest_pages); } return page; } static int kimage_load_normal_segment(struct kimage *image, struct kexec_segment *segment) { unsigned long maddr; size_t ubytes, mbytes; int result; unsigned char __user *buf = NULL; unsigned char *kbuf = NULL; if (image->file_mode) kbuf = segment->kbuf; else buf = segment->buf; ubytes = segment->bufsz; mbytes = segment->memsz; maddr = segment->mem; result = kimage_set_destination(image, maddr); if (result < 0) goto out; while (mbytes) { struct page *page; char *ptr; size_t uchunk, mchunk; page = kimage_alloc_page(image, GFP_HIGHUSER, maddr); if (!page) { result = -ENOMEM; goto out; } result = kimage_add_page(image, page_to_boot_pfn(page) << PAGE_SHIFT); if (result < 0) goto out; ptr = kmap_local_page(page); /* Start with a clear page */ clear_page(ptr); ptr += maddr & ~PAGE_MASK; mchunk = min_t(size_t, mbytes, PAGE_SIZE - (maddr & ~PAGE_MASK)); uchunk = min(ubytes, mchunk); if (uchunk) { /* For file based kexec, source pages are in kernel memory */ if (image->file_mode) memcpy(ptr, kbuf, uchunk); else result = copy_from_user(ptr, buf, uchunk); ubytes -= uchunk; if (image->file_mode) kbuf += uchunk; else buf += uchunk; } kunmap_local(ptr); if (result) { result = -EFAULT; goto out; } maddr += mchunk; mbytes -= mchunk; cond_resched(); } out: return result; } #ifdef CONFIG_CRASH_DUMP static int kimage_load_crash_segment(struct kimage *image, struct kexec_segment *segment) { /* For crash dumps kernels we simply copy the data from * user space to it's destination. * We do things a page at a time for the sake of kmap. */ unsigned long maddr; size_t ubytes, mbytes; int result; unsigned char __user *buf = NULL; unsigned char *kbuf = NULL; result = 0; if (image->file_mode) kbuf = segment->kbuf; else buf = segment->buf; ubytes = segment->bufsz; mbytes = segment->memsz; maddr = segment->mem; while (mbytes) { struct page *page; char *ptr; size_t uchunk, mchunk; page = boot_pfn_to_page(maddr >> PAGE_SHIFT); if (!page) { result = -ENOMEM; goto out; } arch_kexec_post_alloc_pages(page_address(page), 1, 0); ptr = kmap_local_page(page); ptr += maddr & ~PAGE_MASK; mchunk = min_t(size_t, mbytes, PAGE_SIZE - (maddr & ~PAGE_MASK)); uchunk = min(ubytes, mchunk); if (mchunk > uchunk) { /* Zero the trailing part of the page */ memset(ptr + uchunk, 0, mchunk - uchunk); } if (uchunk) { /* For file based kexec, source pages are in kernel memory */ if (image->file_mode) memcpy(ptr, kbuf, uchunk); else result = copy_from_user(ptr, buf, uchunk); ubytes -= uchunk; if (image->file_mode) kbuf += uchunk; else buf += uchunk; } kexec_flush_icache_page(page); kunmap_local(ptr); arch_kexec_pre_free_pages(page_address(page), 1); if (result) { result = -EFAULT; goto out; } maddr += mchunk; mbytes -= mchunk; cond_resched(); } out: return result; } #endif int kimage_load_segment(struct kimage *image, struct kexec_segment *segment) { int result = -ENOMEM; switch (image->type) { case KEXEC_TYPE_DEFAULT: result = kimage_load_normal_segment(image, segment); break; #ifdef CONFIG_CRASH_DUMP case KEXEC_TYPE_CRASH: result = kimage_load_crash_segment(image, segment); break; #endif } return result; } struct kexec_load_limit { /* Mutex protects the limit count. */ struct mutex mutex; int limit; }; static struct kexec_load_limit load_limit_reboot = { .mutex = __MUTEX_INITIALIZER(load_limit_reboot.mutex), .limit = -1, }; static struct kexec_load_limit load_limit_panic = { .mutex = __MUTEX_INITIALIZER(load_limit_panic.mutex), .limit = -1, }; struct kimage *kexec_image; struct kimage *kexec_crash_image; static int kexec_load_disabled; #ifdef CONFIG_SYSCTL static int kexec_limit_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct kexec_load_limit *limit = table->data; int val; struct ctl_table tmp = { .data = &val, .maxlen = sizeof(val), .mode = table->mode, }; int ret; if (write) { ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (ret) return ret; if (val < 0) return -EINVAL; mutex_lock(&limit->mutex); if (limit->limit != -1 && val >= limit->limit) ret = -EINVAL; else limit->limit = val; mutex_unlock(&limit->mutex); return ret; } mutex_lock(&limit->mutex); val = limit->limit; mutex_unlock(&limit->mutex); return proc_dointvec(&tmp, write, buffer, lenp, ppos); } static struct ctl_table kexec_core_sysctls[] = { { .procname = "kexec_load_disabled", .data = &kexec_load_disabled, .maxlen = sizeof(int), .mode = 0644, /* only handle a transition from default "0" to "1" */ .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_ONE, }, { .procname = "kexec_load_limit_panic", .data = &load_limit_panic, .mode = 0644, .proc_handler = kexec_limit_handler, }, { .procname = "kexec_load_limit_reboot", .data = &load_limit_reboot, .mode = 0644, .proc_handler = kexec_limit_handler, }, }; static int __init kexec_core_sysctl_init(void) { register_sysctl_init("kernel", kexec_core_sysctls); return 0; } late_initcall(kexec_core_sysctl_init); #endif bool kexec_load_permitted(int kexec_image_type) { struct kexec_load_limit *limit; /* * Only the superuser can use the kexec syscall and if it has not * been disabled. */ if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) return false; /* Check limit counter and decrease it.*/ limit = (kexec_image_type == KEXEC_TYPE_CRASH) ? &load_limit_panic : &load_limit_reboot; mutex_lock(&limit->mutex); if (!limit->limit) { mutex_unlock(&limit->mutex); return false; } if (limit->limit != -1) limit->limit--; mutex_unlock(&limit->mutex); return true; } /* * Move into place and start executing a preloaded standalone * executable. If nothing was preloaded return an error. */ int kernel_kexec(void) { int error = 0; if (!kexec_trylock()) return -EBUSY; if (!kexec_image) { error = -EINVAL; goto Unlock; } #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { pm_prepare_console(); error = freeze_processes(); if (error) { error = -EBUSY; goto Restore_console; } suspend_console(); error = dpm_suspend_start(PMSG_FREEZE); if (error) goto Resume_console; /* At this point, dpm_suspend_start() has been called, * but *not* dpm_suspend_end(). We *must* call * dpm_suspend_end() now. Otherwise, drivers for * some devices (e.g. interrupt controllers) become * desynchronized with the actual state of the * hardware at resume time, and evil weirdness ensues. */ error = dpm_suspend_end(PMSG_FREEZE); if (error) goto Resume_devices; error = suspend_disable_secondary_cpus(); if (error) goto Enable_cpus; local_irq_disable(); error = syscore_suspend(); if (error) goto Enable_irqs; } else #endif { kexec_in_progress = true; kernel_restart_prepare("kexec reboot"); migrate_to_reboot_cpu(); syscore_shutdown(); /* * migrate_to_reboot_cpu() disables CPU hotplug assuming that * no further code needs to use CPU hotplug (which is true in * the reboot case). However, the kexec path depends on using * CPU hotplug again; so re-enable it here. */ cpu_hotplug_enable(); pr_notice("Starting new kernel\n"); machine_shutdown(); } kmsg_dump(KMSG_DUMP_SHUTDOWN); machine_kexec(kexec_image); #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { syscore_resume(); Enable_irqs: local_irq_enable(); Enable_cpus: suspend_enable_secondary_cpus(); dpm_resume_start(PMSG_RESTORE); Resume_devices: dpm_resume_end(PMSG_RESTORE); Resume_console: resume_console(); thaw_processes(); Restore_console: pm_restore_console(); } #endif Unlock: kexec_unlock(); return error; } |
| 6 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 | /* 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 */ |
| 116 139 204 203 203 204 204 204 204 139 203 137 116 138 138 138 138 137 138 16 32 32 32 16 2 16 16 32 32 8 8 7 8 2 8 14 14 14 14 19 19 9 9 9 10 10 10 10 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 | /* * * Copyright IBM Corporation, 2012 * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> * * Cgroup v2 * Copyright (C) 2019 Red Hat, Inc. * Author: Giuseppe Scrivano <gscrivan@redhat.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2.1 of the GNU Lesser General Public License * as published by the Free Software Foundation. * * This program is distributed in the hope that it would be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. * */ #include <linux/cgroup.h> #include <linux/page_counter.h> #include <linux/slab.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val)) #define MEMFILE_IDX(val) (((val) >> 16) & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) /* Use t->m[0] to encode the offset */ #define MEMFILE_OFFSET(t, m0) (((offsetof(t, m0) << 16) | sizeof_field(t, m0))) #define MEMFILE_OFFSET0(val) (((val) >> 16) & 0xffff) #define MEMFILE_FIELD_SIZE(val) ((val) & 0xffff) #define DFL_TMPL_SIZE ARRAY_SIZE(hugetlb_dfl_tmpl) #define LEGACY_TMPL_SIZE ARRAY_SIZE(hugetlb_legacy_tmpl) static struct hugetlb_cgroup *root_h_cgroup __read_mostly; static struct cftype *dfl_files; static struct cftype *legacy_files; static inline struct page_counter * __hugetlb_cgroup_counter_from_cgroup(struct hugetlb_cgroup *h_cg, int idx, bool rsvd) { if (rsvd) return &h_cg->rsvd_hugepage[idx]; return &h_cg->hugepage[idx]; } static inline struct page_counter * hugetlb_cgroup_counter_from_cgroup(struct hugetlb_cgroup *h_cg, int idx) { return __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, false); } static inline struct page_counter * hugetlb_cgroup_counter_from_cgroup_rsvd(struct hugetlb_cgroup *h_cg, int idx) { return __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, true); } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) { return s ? container_of(s, struct hugetlb_cgroup, css) : NULL; } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task) { return hugetlb_cgroup_from_css(task_css(task, hugetlb_cgrp_id)); } static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) { return (h_cg == root_h_cgroup); } static inline struct hugetlb_cgroup * parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg) { return hugetlb_cgroup_from_css(h_cg->css.parent); } static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) { struct hstate *h; for_each_hstate(h) { if (page_counter_read( hugetlb_cgroup_counter_from_cgroup(h_cg, hstate_index(h)))) return true; } return false; } static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, struct hugetlb_cgroup *parent_h_cgroup) { int idx; for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) { struct page_counter *fault_parent = NULL; struct page_counter *rsvd_parent = NULL; unsigned long limit; int ret; if (parent_h_cgroup) { fault_parent = hugetlb_cgroup_counter_from_cgroup( parent_h_cgroup, idx); rsvd_parent = hugetlb_cgroup_counter_from_cgroup_rsvd( parent_h_cgroup, idx); } page_counter_init(hugetlb_cgroup_counter_from_cgroup(h_cgroup, idx), fault_parent, false); page_counter_init( hugetlb_cgroup_counter_from_cgroup_rsvd(h_cgroup, idx), rsvd_parent, false); limit = round_down(PAGE_COUNTER_MAX, pages_per_huge_page(&hstates[idx])); ret = page_counter_set_max( hugetlb_cgroup_counter_from_cgroup(h_cgroup, idx), limit); VM_BUG_ON(ret); ret = page_counter_set_max( hugetlb_cgroup_counter_from_cgroup_rsvd(h_cgroup, idx), limit); VM_BUG_ON(ret); } } static void hugetlb_cgroup_free(struct hugetlb_cgroup *h_cgroup) { int node; for_each_node(node) kfree(h_cgroup->nodeinfo[node]); kfree(h_cgroup); } static struct cgroup_subsys_state * hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css); struct hugetlb_cgroup *h_cgroup; int node; h_cgroup = kzalloc(struct_size(h_cgroup, nodeinfo, nr_node_ids), GFP_KERNEL); if (!h_cgroup) return ERR_PTR(-ENOMEM); if (!parent_h_cgroup) root_h_cgroup = h_cgroup; /* * TODO: this routine can waste much memory for nodes which will * never be onlined. It's better to use memory hotplug callback * function. */ for_each_node(node) { /* Set node_to_alloc to NUMA_NO_NODE for offline nodes. */ int node_to_alloc = node_state(node, N_NORMAL_MEMORY) ? node : NUMA_NO_NODE; h_cgroup->nodeinfo[node] = kzalloc_node(sizeof(struct hugetlb_cgroup_per_node), GFP_KERNEL, node_to_alloc); if (!h_cgroup->nodeinfo[node]) goto fail_alloc_nodeinfo; } hugetlb_cgroup_init(h_cgroup, parent_h_cgroup); return &h_cgroup->css; fail_alloc_nodeinfo: hugetlb_cgroup_free(h_cgroup); return ERR_PTR(-ENOMEM); } static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css) { hugetlb_cgroup_free(hugetlb_cgroup_from_css(css)); } /* * Should be called with hugetlb_lock held. * Since we are holding hugetlb_lock, pages cannot get moved from * active list or uncharged from the cgroup, So no need to get * page reference and test for page active here. This function * cannot fail. */ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg, struct page *page) { unsigned int nr_pages; struct page_counter *counter; struct hugetlb_cgroup *page_hcg; struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg); struct folio *folio = page_folio(page); page_hcg = hugetlb_cgroup_from_folio(folio); /* * We can have pages in active list without any cgroup * ie, hugepage with less than 3 pages. We can safely * ignore those pages. */ if (!page_hcg || page_hcg != h_cg) goto out; nr_pages = compound_nr(page); if (!parent) { parent = root_h_cgroup; /* root has no limit */ page_counter_charge(&parent->hugepage[idx], nr_pages); } counter = &h_cg->hugepage[idx]; /* Take the pages off the local counter */ page_counter_cancel(counter, nr_pages); set_hugetlb_cgroup(folio, parent); out: return; } /* * Force the hugetlb cgroup to empty the hugetlb resources by moving them to * the parent cgroup. */ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) { struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); struct hstate *h; struct page *page; do { for_each_hstate(h) { spin_lock_irq(&hugetlb_lock); list_for_each_entry(page, &h->hugepage_activelist, lru) hugetlb_cgroup_move_parent(hstate_index(h), h_cg, page); spin_unlock_irq(&hugetlb_lock); } cond_resched(); } while (hugetlb_cgroup_have_usage(h_cg)); } static inline void hugetlb_event(struct hugetlb_cgroup *hugetlb, int idx, enum hugetlb_memory_event event) { atomic_long_inc(&hugetlb->events_local[idx][event]); cgroup_file_notify(&hugetlb->events_local_file[idx]); do { atomic_long_inc(&hugetlb->events[idx][event]); cgroup_file_notify(&hugetlb->events_file[idx]); } while ((hugetlb = parent_hugetlb_cgroup(hugetlb)) && !hugetlb_cgroup_is_root(hugetlb)); } static int __hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr, bool rsvd) { int ret = 0; struct page_counter *counter; struct hugetlb_cgroup *h_cg = NULL; if (hugetlb_cgroup_disabled()) goto done; again: rcu_read_lock(); h_cg = hugetlb_cgroup_from_task(current); if (!css_tryget(&h_cg->css)) { rcu_read_unlock(); goto again; } rcu_read_unlock(); if (!page_counter_try_charge( __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), nr_pages, &counter)) { ret = -ENOMEM; hugetlb_event(h_cg, idx, HUGETLB_MAX); css_put(&h_cg->css); goto done; } /* Reservations take a reference to the css because they do not get * reparented. */ if (!rsvd) css_put(&h_cg->css); done: *ptr = h_cg; return ret; } int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { return __hugetlb_cgroup_charge_cgroup(idx, nr_pages, ptr, false); } int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { return __hugetlb_cgroup_charge_cgroup(idx, nr_pages, ptr, true); } /* Should be called with hugetlb_lock held */ static void __hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio, bool rsvd) { if (hugetlb_cgroup_disabled() || !h_cg) return; lockdep_assert_held(&hugetlb_lock); __set_hugetlb_cgroup(folio, h_cg, rsvd); if (!rsvd) { unsigned long usage = h_cg->nodeinfo[folio_nid(folio)]->usage[idx]; /* * This write is not atomic due to fetching usage and writing * to it, but that's fine because we call this with * hugetlb_lock held anyway. */ WRITE_ONCE(h_cg->nodeinfo[folio_nid(folio)]->usage[idx], usage + nr_pages); } } void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio) { __hugetlb_cgroup_commit_charge(idx, nr_pages, h_cg, folio, false); } void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio) { __hugetlb_cgroup_commit_charge(idx, nr_pages, h_cg, folio, true); } /* * Should be called with hugetlb_lock held */ static void __hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, struct folio *folio, bool rsvd) { struct hugetlb_cgroup *h_cg; if (hugetlb_cgroup_disabled()) return; lockdep_assert_held(&hugetlb_lock); h_cg = __hugetlb_cgroup_from_folio(folio, rsvd); if (unlikely(!h_cg)) return; __set_hugetlb_cgroup(folio, NULL, rsvd); page_counter_uncharge(__hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), nr_pages); if (rsvd) css_put(&h_cg->css); else { unsigned long usage = h_cg->nodeinfo[folio_nid(folio)]->usage[idx]; /* * This write is not atomic due to fetching usage and writing * to it, but that's fine because we call this with * hugetlb_lock held anyway. */ WRITE_ONCE(h_cg->nodeinfo[folio_nid(folio)]->usage[idx], usage - nr_pages); } } void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, struct folio *folio) { __hugetlb_cgroup_uncharge_folio(idx, nr_pages, folio, false); } void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, struct folio *folio) { __hugetlb_cgroup_uncharge_folio(idx, nr_pages, folio, true); } static void __hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, bool rsvd) { if (hugetlb_cgroup_disabled() || !h_cg) return; page_counter_uncharge(__hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), nr_pages); if (rsvd) css_put(&h_cg->css); } void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg) { __hugetlb_cgroup_uncharge_cgroup(idx, nr_pages, h_cg, false); } void hugetlb_cgroup_uncharge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg) { __hugetlb_cgroup_uncharge_cgroup(idx, nr_pages, h_cg, true); } void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start, unsigned long end) { if (hugetlb_cgroup_disabled() || !resv || !resv->reservation_counter || !resv->css) return; page_counter_uncharge(resv->reservation_counter, (end - start) * resv->pages_per_hpage); css_put(resv->css); } void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, unsigned long nr_pages, bool region_del) { if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages) return; if (rg->reservation_counter && resv->pages_per_hpage && !resv->reservation_counter) { page_counter_uncharge(rg->reservation_counter, nr_pages * resv->pages_per_hpage); /* * Only do css_put(rg->css) when we delete the entire region * because one file_region must hold exactly one css reference. */ if (region_del) css_put(rg->css); } } enum { RES_USAGE, RES_RSVD_USAGE, RES_LIMIT, RES_RSVD_LIMIT, RES_MAX_USAGE, RES_RSVD_MAX_USAGE, RES_FAILCNT, RES_RSVD_FAILCNT, }; static int hugetlb_cgroup_read_numa_stat(struct seq_file *seq, void *dummy) { int nid; struct cftype *cft = seq_cft(seq); int idx = MEMFILE_IDX(cft->private); bool legacy = !cgroup_subsys_on_dfl(hugetlb_cgrp_subsys); struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq)); struct cgroup_subsys_state *css; unsigned long usage; if (legacy) { /* Add up usage across all nodes for the non-hierarchical total. */ usage = 0; for_each_node_state(nid, N_MEMORY) usage += READ_ONCE(h_cg->nodeinfo[nid]->usage[idx]); seq_printf(seq, "total=%lu", usage * PAGE_SIZE); /* Simply print the per-node usage for the non-hierarchical total. */ for_each_node_state(nid, N_MEMORY) seq_printf(seq, " N%d=%lu", nid, READ_ONCE(h_cg->nodeinfo[nid]->usage[idx]) * PAGE_SIZE); seq_putc(seq, '\n'); } /* * The hierarchical total is pretty much the value recorded by the * counter, so use that. */ seq_printf(seq, "%stotal=%lu", legacy ? "hierarchical_" : "", page_counter_read(&h_cg->hugepage[idx]) * PAGE_SIZE); /* * For each node, transverse the css tree to obtain the hierarchical * node usage. */ for_each_node_state(nid, N_MEMORY) { usage = 0; rcu_read_lock(); css_for_each_descendant_pre(css, &h_cg->css) { usage += READ_ONCE(hugetlb_cgroup_from_css(css) ->nodeinfo[nid] ->usage[idx]); } rcu_read_unlock(); seq_printf(seq, " N%d=%lu", nid, usage * PAGE_SIZE); } seq_putc(seq, '\n'); return 0; } static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { struct page_counter *counter; struct page_counter *rsvd_counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)]; rsvd_counter = &h_cg->rsvd_hugepage[MEMFILE_IDX(cft->private)]; switch (MEMFILE_ATTR(cft->private)) { case RES_USAGE: return (u64)page_counter_read(counter) * PAGE_SIZE; case RES_RSVD_USAGE: return (u64)page_counter_read(rsvd_counter) * PAGE_SIZE; case RES_LIMIT: return (u64)counter->max * PAGE_SIZE; case RES_RSVD_LIMIT: return (u64)rsvd_counter->max * PAGE_SIZE; case RES_MAX_USAGE: return (u64)counter->watermark * PAGE_SIZE; case RES_RSVD_MAX_USAGE: return (u64)rsvd_counter->watermark * PAGE_SIZE; case RES_FAILCNT: return counter->failcnt; case RES_RSVD_FAILCNT: return rsvd_counter->failcnt; default: BUG(); } } static int hugetlb_cgroup_read_u64_max(struct seq_file *seq, void *v) { int idx; u64 val; struct cftype *cft = seq_cft(seq); unsigned long limit; struct page_counter *counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq)); idx = MEMFILE_IDX(cft->private); counter = &h_cg->hugepage[idx]; limit = round_down(PAGE_COUNTER_MAX, pages_per_huge_page(&hstates[idx])); switch (MEMFILE_ATTR(cft->private)) { case RES_RSVD_USAGE: counter = &h_cg->rsvd_hugepage[idx]; fallthrough; case RES_USAGE: val = (u64)page_counter_read(counter); seq_printf(seq, "%llu\n", val * PAGE_SIZE); break; case RES_RSVD_LIMIT: counter = &h_cg->rsvd_hugepage[idx]; fallthrough; case RES_LIMIT: val = (u64)counter->max; if (val == limit) seq_puts(seq, "max\n"); else seq_printf(seq, "%llu\n", val * PAGE_SIZE); break; default: BUG(); } return 0; } static DEFINE_MUTEX(hugetlb_limit_mutex); static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, const char *max) { int ret, idx; unsigned long nr_pages; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); bool rsvd = false; if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */ return -EINVAL; buf = strstrip(buf); ret = page_counter_memparse(buf, max, &nr_pages); if (ret) return ret; idx = MEMFILE_IDX(of_cft(of)->private); nr_pages = round_down(nr_pages, pages_per_huge_page(&hstates[idx])); switch (MEMFILE_ATTR(of_cft(of)->private)) { case RES_RSVD_LIMIT: rsvd = true; fallthrough; case RES_LIMIT: mutex_lock(&hugetlb_limit_mutex); ret = page_counter_set_max( __hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), nr_pages); mutex_unlock(&hugetlb_limit_mutex); break; default: ret = -EINVAL; break; } return ret ?: nbytes; } static ssize_t hugetlb_cgroup_write_legacy(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return hugetlb_cgroup_write(of, buf, nbytes, off, "-1"); } static ssize_t hugetlb_cgroup_write_dfl(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return hugetlb_cgroup_write(of, buf, nbytes, off, "max"); } static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { int ret = 0; struct page_counter *counter, *rsvd_counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)]; rsvd_counter = &h_cg->rsvd_hugepage[MEMFILE_IDX(of_cft(of)->private)]; switch (MEMFILE_ATTR(of_cft(of)->private)) { case RES_MAX_USAGE: page_counter_reset_watermark(counter); break; case RES_RSVD_MAX_USAGE: page_counter_reset_watermark(rsvd_counter); break; case RES_FAILCNT: counter->failcnt = 0; break; case RES_RSVD_FAILCNT: rsvd_counter->failcnt = 0; break; default: ret = -EINVAL; break; } return ret ?: nbytes; } static char *mem_fmt(char *buf, int size, unsigned long hsize) { if (hsize >= SZ_1G) snprintf(buf, size, "%luGB", hsize / SZ_1G); else if (hsize >= SZ_1M) snprintf(buf, size, "%luMB", hsize / SZ_1M); else snprintf(buf, size, "%luKB", hsize / SZ_1K); return buf; } static int __hugetlb_events_show(struct seq_file *seq, bool local) { int idx; long max; struct cftype *cft = seq_cft(seq); struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq)); idx = MEMFILE_IDX(cft->private); if (local) max = atomic_long_read(&h_cg->events_local[idx][HUGETLB_MAX]); else max = atomic_long_read(&h_cg->events[idx][HUGETLB_MAX]); seq_printf(seq, "max %lu\n", max); return 0; } static int hugetlb_events_show(struct seq_file *seq, void *v) { return __hugetlb_events_show(seq, false); } static int hugetlb_events_local_show(struct seq_file *seq, void *v) { return __hugetlb_events_show(seq, true); } static struct cftype hugetlb_dfl_tmpl[] = { { .name = "max", .private = RES_LIMIT, .seq_show = hugetlb_cgroup_read_u64_max, .write = hugetlb_cgroup_write_dfl, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "rsvd.max", .private = RES_RSVD_LIMIT, .seq_show = hugetlb_cgroup_read_u64_max, .write = hugetlb_cgroup_write_dfl, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "current", .private = RES_USAGE, .seq_show = hugetlb_cgroup_read_u64_max, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "rsvd.current", .private = RES_RSVD_USAGE, .seq_show = hugetlb_cgroup_read_u64_max, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "events", .seq_show = hugetlb_events_show, .file_offset = MEMFILE_OFFSET(struct hugetlb_cgroup, events_file[0]), .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "events.local", .seq_show = hugetlb_events_local_show, .file_offset = MEMFILE_OFFSET(struct hugetlb_cgroup, events_local_file[0]), .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "numa_stat", .seq_show = hugetlb_cgroup_read_numa_stat, .flags = CFTYPE_NOT_ON_ROOT, }, /* don't need terminator here */ }; static struct cftype hugetlb_legacy_tmpl[] = { { .name = "limit_in_bytes", .private = RES_LIMIT, .read_u64 = hugetlb_cgroup_read_u64, .write = hugetlb_cgroup_write_legacy, }, { .name = "rsvd.limit_in_bytes", .private = RES_RSVD_LIMIT, .read_u64 = hugetlb_cgroup_read_u64, .write = hugetlb_cgroup_write_legacy, }, { .name = "usage_in_bytes", .private = RES_USAGE, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "rsvd.usage_in_bytes", .private = RES_RSVD_USAGE, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "max_usage_in_bytes", .private = RES_MAX_USAGE, .write = hugetlb_cgroup_reset, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "rsvd.max_usage_in_bytes", .private = RES_RSVD_MAX_USAGE, .write = hugetlb_cgroup_reset, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "failcnt", .private = RES_FAILCNT, .write = hugetlb_cgroup_reset, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "rsvd.failcnt", .private = RES_RSVD_FAILCNT, .write = hugetlb_cgroup_reset, .read_u64 = hugetlb_cgroup_read_u64, }, { .name = "numa_stat", .seq_show = hugetlb_cgroup_read_numa_stat, }, /* don't need terminator here */ }; static void __init hugetlb_cgroup_cfttypes_init(struct hstate *h, struct cftype *cft, struct cftype *tmpl, int tmpl_size) { char buf[32]; int i, idx = hstate_index(h); /* format the size */ mem_fmt(buf, sizeof(buf), huge_page_size(h)); for (i = 0; i < tmpl_size; cft++, tmpl++, i++) { *cft = *tmpl; /* rebuild the name */ snprintf(cft->name, MAX_CFTYPE_NAME, "%s.%s", buf, tmpl->name); /* rebuild the private */ cft->private = MEMFILE_PRIVATE(idx, tmpl->private); /* rebuild the file_offset */ if (tmpl->file_offset) { unsigned int offset = tmpl->file_offset; cft->file_offset = MEMFILE_OFFSET0(offset) + MEMFILE_FIELD_SIZE(offset) * idx; } lockdep_register_key(&cft->lockdep_key); } } static void __init __hugetlb_cgroup_file_dfl_init(struct hstate *h) { int idx = hstate_index(h); hugetlb_cgroup_cfttypes_init(h, dfl_files + idx * DFL_TMPL_SIZE, hugetlb_dfl_tmpl, DFL_TMPL_SIZE); } static void __init __hugetlb_cgroup_file_legacy_init(struct hstate *h) { int idx = hstate_index(h); hugetlb_cgroup_cfttypes_init(h, legacy_files + idx * LEGACY_TMPL_SIZE, hugetlb_legacy_tmpl, LEGACY_TMPL_SIZE); } static void __init __hugetlb_cgroup_file_init(struct hstate *h) { __hugetlb_cgroup_file_dfl_init(h); __hugetlb_cgroup_file_legacy_init(h); } static void __init __hugetlb_cgroup_file_pre_init(void) { int cft_count; cft_count = hugetlb_max_hstate * DFL_TMPL_SIZE + 1; /* add terminator */ dfl_files = kcalloc(cft_count, sizeof(struct cftype), GFP_KERNEL); BUG_ON(!dfl_files); cft_count = hugetlb_max_hstate * LEGACY_TMPL_SIZE + 1; /* add terminator */ legacy_files = kcalloc(cft_count, sizeof(struct cftype), GFP_KERNEL); BUG_ON(!legacy_files); } static void __init __hugetlb_cgroup_file_post_init(void) { WARN_ON(cgroup_add_dfl_cftypes(&hugetlb_cgrp_subsys, dfl_files)); WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys, legacy_files)); } void __init hugetlb_cgroup_file_init(void) { struct hstate *h; __hugetlb_cgroup_file_pre_init(); for_each_hstate(h) __hugetlb_cgroup_file_init(h); __hugetlb_cgroup_file_post_init(); } /* * hugetlb_lock will make sure a parallel cgroup rmdir won't happen * when we migrate hugepages */ void hugetlb_cgroup_migrate(struct folio *old_folio, struct folio *new_folio) { struct hugetlb_cgroup *h_cg; struct hugetlb_cgroup *h_cg_rsvd; struct hstate *h = folio_hstate(old_folio); if (hugetlb_cgroup_disabled()) return; spin_lock_irq(&hugetlb_lock); h_cg = hugetlb_cgroup_from_folio(old_folio); h_cg_rsvd = hugetlb_cgroup_from_folio_rsvd(old_folio); set_hugetlb_cgroup(old_folio, NULL); set_hugetlb_cgroup_rsvd(old_folio, NULL); /* move the h_cg details to new cgroup */ set_hugetlb_cgroup(new_folio, h_cg); set_hugetlb_cgroup_rsvd(new_folio, h_cg_rsvd); list_move(&new_folio->lru, &h->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); return; } static struct cftype hugetlb_files[] = { {} /* terminate */ }; struct cgroup_subsys hugetlb_cgrp_subsys = { .css_alloc = hugetlb_cgroup_css_alloc, .css_offline = hugetlb_cgroup_css_offline, .css_free = hugetlb_cgroup_css_free, .dfl_cftypes = hugetlb_files, .legacy_cftypes = hugetlb_files, }; |
| 39 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 | // SPDX-License-Identifier: GPL-2.0-or-later /* * G8BPQ compatible "AX.25 via ethernet" driver release 004 * * This code REQUIRES 2.0.0 or higher/ NET3.029 * * This is a "pseudo" network driver to allow AX.25 over Ethernet * using G8BPQ encapsulation. It has been extracted from the protocol * implementation because * * - things got unreadable within the protocol stack * - to cure the protocol stack from "feature-ism" * - a protocol implementation shouldn't need to know on * which hardware it is running * - user-level programs like the AX.25 utilities shouldn't * need to know about the hardware. * - IP over ethernet encapsulated AX.25 was impossible * - rxecho.c did not work * - to have room for extensions * - it just deserves to "live" as an own driver * * This driver can use any ethernet destination address, and can be * limited to accept frames from one dedicated ethernet card only. * * Note that the driver sets up the BPQ devices automagically on * startup or (if started before the "insmod" of an ethernet device) * on "ifconfig up". It hopefully will remove the BPQ on "rmmod"ing * the ethernet device (in fact: as soon as another ethernet or bpq * device gets "ifconfig"ured). * * I have heard that several people are thinking of experiments * with highspeed packet radio using existing ethernet cards. * Well, this driver is prepared for this purpose, just add * your tx key control and a txdelay / tailtime algorithm, * probably some buffering, and /voila/... * * History * BPQ 001 Joerg(DL1BKE) Extracted BPQ code from AX.25 * protocol stack and added my own * yet existing patches * BPQ 002 Joerg(DL1BKE) Scan network device list on * startup. * BPQ 003 Joerg(DL1BKE) Ethernet destination address * and accepted source address * can be configured by an ioctl() * call. * Fixed to match Linux networking * changes - 2.1.15. * BPQ 004 Joerg(DL1BKE) Fixed to not lock up on ifconfig. */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/net.h> #include <linux/slab.h> #include <net/ax25.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/uaccess.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/stat.h> #include <linux/module.h> #include <linux/init.h> #include <linux/rtnetlink.h> #include <net/ip.h> #include <net/arp.h> #include <net/net_namespace.h> #include <linux/bpqether.h> static const char banner[] __initconst = KERN_INFO \ "AX.25: bpqether driver version 004\n"; static int bpq_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); static int bpq_device_event(struct notifier_block *, unsigned long, void *); static struct packet_type bpq_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_BPQ), .func = bpq_rcv, }; static struct notifier_block bpq_dev_notifier = { .notifier_call = bpq_device_event, }; struct bpqdev { struct list_head bpq_list; /* list of bpq devices chain */ struct net_device *ethdev; /* link to ethernet device */ struct net_device *axdev; /* bpq device (bpq#) */ char dest_addr[6]; /* ether destination address */ char acpt_addr[6]; /* accept ether frames from this address only */ }; static LIST_HEAD(bpq_devices); /* * bpqether network devices are paired with ethernet devices below them, so * form a special "super class" of normal ethernet devices; split their locks * off into a separate class since they always nest. */ static struct lock_class_key bpq_netdev_xmit_lock_key; static struct lock_class_key bpq_netdev_addr_lock_key; static void bpq_set_lockdep_class_one(struct net_device *dev, struct netdev_queue *txq, void *_unused) { lockdep_set_class(&txq->_xmit_lock, &bpq_netdev_xmit_lock_key); } static void bpq_set_lockdep_class(struct net_device *dev) { lockdep_set_class(&dev->addr_list_lock, &bpq_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, bpq_set_lockdep_class_one, NULL); } /* ------------------------------------------------------------------------ */ /* * Get the ethernet device for a BPQ device */ static inline struct net_device *bpq_get_ether_dev(struct net_device *dev) { struct bpqdev *bpq = netdev_priv(dev); return bpq ? bpq->ethdev : NULL; } /* * Get the BPQ device for the ethernet device */ static inline struct net_device *bpq_get_ax25_dev(struct net_device *dev) { struct bpqdev *bpq; list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list, lockdep_rtnl_is_held()) { if (bpq->ethdev == dev) return bpq->axdev; } return NULL; } static inline int dev_is_ethdev(struct net_device *dev) { return dev->type == ARPHRD_ETHER && strncmp(dev->name, "dummy", 5); } /* ------------------------------------------------------------------------ */ /* * Receive an AX.25 frame via an ethernet interface. */ static int bpq_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { int len; char * ptr; struct ethhdr *eth; struct bpqdev *bpq; if (!net_eq(dev_net(dev), &init_net)) goto drop; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) return NET_RX_DROP; if (!pskb_may_pull(skb, sizeof(struct ethhdr))) goto drop; rcu_read_lock(); dev = bpq_get_ax25_dev(dev); if (dev == NULL || !netif_running(dev)) goto drop_unlock; /* * if we want to accept frames from just one ethernet device * we check the source address of the sender. */ bpq = netdev_priv(dev); eth = eth_hdr(skb); if (!(bpq->acpt_addr[0] & 0x01) && !ether_addr_equal(eth->h_source, bpq->acpt_addr)) goto drop_unlock; if (skb_cow(skb, sizeof(struct ethhdr))) goto drop_unlock; len = skb->data[0] + skb->data[1] * 256 - 5; skb_pull(skb, 2); /* Remove the length bytes */ skb_trim(skb, len); /* Set the length of the data */ dev->stats.rx_packets++; dev->stats.rx_bytes += len; ptr = skb_push(skb, 1); *ptr = 0; skb->protocol = ax25_type_trans(skb, dev); netif_rx(skb); unlock: rcu_read_unlock(); return 0; drop_unlock: kfree_skb(skb); goto unlock; drop: kfree_skb(skb); return 0; } /* * Send an AX.25 frame via an ethernet interface */ static netdev_tx_t bpq_xmit(struct sk_buff *skb, struct net_device *dev) { unsigned char *ptr; struct bpqdev *bpq; struct net_device *orig_dev; int size; if (skb->protocol == htons(ETH_P_IP)) return ax25_ip_xmit(skb); /* * Just to be *really* sure not to send anything if the interface * is down, the ethernet device may have gone. */ if (!netif_running(dev)) { kfree_skb(skb); return NETDEV_TX_OK; } skb_pull(skb, 1); /* Drop KISS byte */ size = skb->len; /* * We're about to mess with the skb which may still shared with the * generic networking code so unshare and ensure it's got enough * space for the BPQ headers. */ if (skb_cow(skb, AX25_BPQ_HEADER_LEN)) { if (net_ratelimit()) pr_err("bpqether: out of memory\n"); kfree_skb(skb); return NETDEV_TX_OK; } ptr = skb_push(skb, 2); /* Make space for length */ *ptr++ = (size + 5) % 256; *ptr++ = (size + 5) / 256; bpq = netdev_priv(dev); orig_dev = dev; if ((dev = bpq_get_ether_dev(dev)) == NULL) { orig_dev->stats.tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; } skb->protocol = ax25_type_trans(skb, dev); skb_reset_network_header(skb); dev_hard_header(skb, dev, ETH_P_BPQ, bpq->dest_addr, NULL, 0); dev->stats.tx_packets++; dev->stats.tx_bytes+=skb->len; dev_queue_xmit(skb); netif_wake_queue(dev); return NETDEV_TX_OK; } /* * Set AX.25 callsign */ static int bpq_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = (struct sockaddr *)addr; dev_addr_set(dev, sa->sa_data); return 0; } /* Ioctl commands * * SIOCSBPQETHOPT reserved for enhancements * SIOCSBPQETHADDR set the destination and accepted * source ethernet address (broadcast * or multicast: accept all) */ static int bpq_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { struct bpq_ethaddr __user *ethaddr = data; struct bpqdev *bpq = netdev_priv(dev); struct bpq_req req; if (!capable(CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case SIOCSBPQETHOPT: if (copy_from_user(&req, data, sizeof(struct bpq_req))) return -EFAULT; switch (req.cmd) { case SIOCGBPQETHPARAM: case SIOCSBPQETHPARAM: default: return -EINVAL; } break; case SIOCSBPQETHADDR: if (copy_from_user(bpq->dest_addr, ethaddr->destination, ETH_ALEN)) return -EFAULT; if (copy_from_user(bpq->acpt_addr, ethaddr->accept, ETH_ALEN)) return -EFAULT; break; default: return -EINVAL; } return 0; } /* * open/close a device */ static int bpq_open(struct net_device *dev) { netif_start_queue(dev); return 0; } static int bpq_close(struct net_device *dev) { netif_stop_queue(dev); return 0; } /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS /* * Proc filesystem */ static void *bpq_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { int i = 1; struct bpqdev *bpqdev; rcu_read_lock(); if (*pos == 0) return SEQ_START_TOKEN; list_for_each_entry_rcu(bpqdev, &bpq_devices, bpq_list) { if (i == *pos) return bpqdev; } return NULL; } static void *bpq_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct list_head *p; struct bpqdev *bpqdev = v; ++*pos; if (v == SEQ_START_TOKEN) p = rcu_dereference(list_next_rcu(&bpq_devices)); else p = rcu_dereference(list_next_rcu(&bpqdev->bpq_list)); return (p == &bpq_devices) ? NULL : list_entry(p, struct bpqdev, bpq_list); } static void bpq_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int bpq_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "dev ether destination accept from\n"); else { const struct bpqdev *bpqdev = v; seq_printf(seq, "%-5s %-10s %pM ", bpqdev->axdev->name, bpqdev->ethdev->name, bpqdev->dest_addr); if (is_multicast_ether_addr(bpqdev->acpt_addr)) seq_printf(seq, "*\n"); else seq_printf(seq, "%pM\n", bpqdev->acpt_addr); } return 0; } static const struct seq_operations bpq_seqops = { .start = bpq_seq_start, .next = bpq_seq_next, .stop = bpq_seq_stop, .show = bpq_seq_show, }; #endif /* ------------------------------------------------------------------------ */ static const struct net_device_ops bpq_netdev_ops = { .ndo_open = bpq_open, .ndo_stop = bpq_close, .ndo_start_xmit = bpq_xmit, .ndo_set_mac_address = bpq_set_mac_address, .ndo_siocdevprivate = bpq_siocdevprivate, }; static void bpq_setup(struct net_device *dev) { dev->netdev_ops = &bpq_netdev_ops; dev->needs_free_netdev = true; dev->flags = 0; dev->lltx = true; /* Allow recursion */ #if IS_ENABLED(CONFIG_AX25) dev->header_ops = &ax25_header_ops; #endif dev->type = ARPHRD_AX25; dev->hard_header_len = AX25_MAX_HEADER_LEN + AX25_BPQ_HEADER_LEN; dev->mtu = AX25_DEF_PACLEN; dev->addr_len = AX25_ADDR_LEN; memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); dev_addr_set(dev, (u8 *)&ax25_defaddr); } /* * Setup a new device. */ static int bpq_new_device(struct net_device *edev) { int err; struct net_device *ndev; struct bpqdev *bpq; ndev = alloc_netdev(sizeof(struct bpqdev), "bpq%d", NET_NAME_UNKNOWN, bpq_setup); if (!ndev) return -ENOMEM; bpq = netdev_priv(ndev); dev_hold(edev); bpq->ethdev = edev; bpq->axdev = ndev; eth_broadcast_addr(bpq->dest_addr); eth_broadcast_addr(bpq->acpt_addr); err = register_netdevice(ndev); if (err) goto error; bpq_set_lockdep_class(ndev); /* List protected by RTNL */ list_add_rcu(&bpq->bpq_list, &bpq_devices); return 0; error: dev_put(edev); free_netdev(ndev); return err; } static void bpq_free_device(struct net_device *ndev) { struct bpqdev *bpq = netdev_priv(ndev); dev_put(bpq->ethdev); list_del_rcu(&bpq->bpq_list); unregister_netdevice(ndev); } /* * Handle device status changes. */ static int bpq_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; if (!dev_is_ethdev(dev) && !bpq_get_ax25_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: /* new ethernet device -> new BPQ interface */ if (bpq_get_ax25_dev(dev) == NULL) bpq_new_device(dev); break; case NETDEV_DOWN: /* ethernet device closed -> close BPQ interface */ if ((dev = bpq_get_ax25_dev(dev)) != NULL) dev_close(dev); break; case NETDEV_UNREGISTER: /* ethernet device removed -> free BPQ interface */ if ((dev = bpq_get_ax25_dev(dev)) != NULL) bpq_free_device(dev); break; default: break; } return NOTIFY_DONE; } /* ------------------------------------------------------------------------ */ /* * Initialize driver. To be called from af_ax25 if not compiled as a * module */ static int __init bpq_init_driver(void) { #ifdef CONFIG_PROC_FS if (!proc_create_seq("bpqether", 0444, init_net.proc_net, &bpq_seqops)) { printk(KERN_ERR "bpq: cannot create /proc/net/bpqether entry.\n"); return -ENOENT; } #endif /* CONFIG_PROC_FS */ dev_add_pack(&bpq_packet_type); register_netdevice_notifier(&bpq_dev_notifier); printk(banner); return 0; } static void __exit bpq_cleanup_driver(void) { struct bpqdev *bpq; dev_remove_pack(&bpq_packet_type); unregister_netdevice_notifier(&bpq_dev_notifier); remove_proc_entry("bpqether", init_net.proc_net); rtnl_lock(); while (!list_empty(&bpq_devices)) { bpq = list_entry(bpq_devices.next, struct bpqdev, bpq_list); bpq_free_device(bpq->axdev); } rtnl_unlock(); } MODULE_AUTHOR("Joerg Reuter DL1BKE <jreuter@yaina.de>"); MODULE_DESCRIPTION("Transmit and receive AX.25 packets over Ethernet"); MODULE_LICENSE("GPL"); module_init(bpq_init_driver); module_exit(bpq_cleanup_driver); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_LEGACY_H #define __X86_KERNEL_FPU_LEGACY_H #include <asm/fpu/types.h> extern unsigned int mxcsr_feature_mask; static inline void ldmxcsr(u32 mxcsr) { asm volatile("ldmxcsr %0" :: "m" (mxcsr)); } /* * Returns 0 on success or the trap number when the operation raises an * exception. */ #define user_insn(insn, output, input...) \ ({ \ int err; \ \ might_fault(); \ \ asm volatile(ASM_STAC "\n" \ "1: " #insn "\n" \ "2: " ASM_CLAC "\n" \ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \ : [err] "=a" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn_err(insn, output, input...) \ ({ \ int err; \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[err]) \ : [err] "=r" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn(insn, output, input...) \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FPU_RESTORE) \ : output : input) static inline int fnsave_to_user_sigframe(struct fregs_state __user *fx) { return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); } static inline int fxsave_to_user_sigframe(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); else return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); } static inline void fxrstor(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int fxrstor_safe(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int fxrstor_from_user_sigframe(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void frstor(struct fregs_state *fx) { kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int frstor_safe(struct fregs_state *fx) { return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int frstor_from_user_sigframe(struct fregs_state __user *fx) { return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void fxsave(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx)); else asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx)); } #endif |
| 5 5 5 5 5 5 13 12 13 13 12 12 12 11 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 10 10 54 49 1 2 33 67 53 1 54 54 54 54 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/anon_inodes.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/magic.h> #include <linux/mount.h> #include <linux/pid.h> #include <linux/pidfs.h> #include <linux/pid_namespace.h> #include <linux/poll.h> #include <linux/proc_fs.h> #include <linux/proc_ns.h> #include <linux/pseudo_fs.h> #include <linux/ptrace.h> #include <linux/seq_file.h> #include <uapi/linux/pidfd.h> #include <linux/ipc_namespace.h> #include <linux/time_namespace.h> #include <linux/utsname.h> #include <net/net_namespace.h> #include "internal.h" #include "mount.h" #ifdef CONFIG_PROC_FS /** * pidfd_show_fdinfo - print information about a pidfd * @m: proc fdinfo file * @f: file referencing a pidfd * * Pid: * This function will print the pid that a given pidfd refers to in the * pid namespace of the procfs instance. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its pid. This is * similar to calling getppid() on a process whose parent is outside of * its pid namespace. * * NSpid: * If pid namespaces are supported then this function will also print * the pid of a given pidfd refers to for all descendant pid namespaces * starting from the current pid namespace of the instance, i.e. the * Pid field and the first entry in the NSpid field will be identical. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its first NSpid * entry and no others will be shown. * Note that this differs from the Pid and NSpid fields in * /proc/<pid>/status where Pid and NSpid are always shown relative to * the pid namespace of the procfs instance. The difference becomes * obvious when sending around a pidfd between pid namespaces from a * different branch of the tree, i.e. where no ancestral relation is * present between the pid namespaces: * - create two new pid namespaces ns1 and ns2 in the initial pid * namespace (also take care to create new mount namespaces in the * new pid namespace and mount procfs) * - create a process with a pidfd in ns1 * - send pidfd from ns1 to ns2 * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid * have exactly one entry, which is 0 */ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) { struct pid *pid = pidfd_pid(f); struct pid_namespace *ns; pid_t nr = -1; if (likely(pid_has_task(pid, PIDTYPE_PID))) { ns = proc_pid_ns(file_inode(m->file)->i_sb); nr = pid_nr_ns(pid, ns); } seq_put_decimal_ll(m, "Pid:\t", nr); #ifdef CONFIG_PID_NS seq_put_decimal_ll(m, "\nNSpid:\t", nr); if (nr > 0) { int i; /* If nr is non-zero it means that 'pid' is valid and that * ns, i.e. the pid namespace associated with the procfs * instance, is in the pid namespace hierarchy of pid. * Start at one below the already printed level. */ for (i = ns->level + 1; i <= pid->level; i++) seq_put_decimal_ll(m, "\t", pid->numbers[i].nr); } #endif seq_putc(m, '\n'); } #endif /* * Poll support for process exit notification. */ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct pid *pid = pidfd_pid(file); bool thread = file->f_flags & PIDFD_THREAD; struct task_struct *task; __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); /* * Depending on PIDFD_THREAD, inform pollers when the thread * or the whole thread-group exits. */ guard(rcu)(); task = pid_task(pid, PIDTYPE_PID); if (!task) poll_flags = EPOLLIN | EPOLLRDNORM | EPOLLHUP; else if (task->exit_state && (thread || thread_group_empty(task))) poll_flags = EPOLLIN | EPOLLRDNORM; return poll_flags; } static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct task_struct *task __free(put_task) = NULL; struct nsproxy *nsp __free(put_nsproxy) = NULL; struct pid *pid = pidfd_pid(file); struct ns_common *ns_common = NULL; struct pid_namespace *pid_ns; if (arg) return -EINVAL; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; scoped_guard(task_lock, task) { nsp = task->nsproxy; if (nsp) get_nsproxy(nsp); } if (!nsp) return -ESRCH; /* just pretend it didn't exist */ /* * We're trying to open a file descriptor to the namespace so perform a * filesystem cred ptrace check. Also, we mirror nsfs behavior. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) return -EACCES; switch (cmd) { /* Namespaces that hang of nsproxy. */ case PIDFD_GET_CGROUP_NAMESPACE: if (IS_ENABLED(CONFIG_CGROUPS)) { get_cgroup_ns(nsp->cgroup_ns); ns_common = to_ns_common(nsp->cgroup_ns); } break; case PIDFD_GET_IPC_NAMESPACE: if (IS_ENABLED(CONFIG_IPC_NS)) { get_ipc_ns(nsp->ipc_ns); ns_common = to_ns_common(nsp->ipc_ns); } break; case PIDFD_GET_MNT_NAMESPACE: get_mnt_ns(nsp->mnt_ns); ns_common = to_ns_common(nsp->mnt_ns); break; case PIDFD_GET_NET_NAMESPACE: if (IS_ENABLED(CONFIG_NET_NS)) { ns_common = to_ns_common(nsp->net_ns); get_net_ns(ns_common); } break; case PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE: if (IS_ENABLED(CONFIG_PID_NS)) { get_pid_ns(nsp->pid_ns_for_children); ns_common = to_ns_common(nsp->pid_ns_for_children); } break; case PIDFD_GET_TIME_NAMESPACE: if (IS_ENABLED(CONFIG_TIME_NS)) { get_time_ns(nsp->time_ns); ns_common = to_ns_common(nsp->time_ns); } break; case PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE: if (IS_ENABLED(CONFIG_TIME_NS)) { get_time_ns(nsp->time_ns_for_children); ns_common = to_ns_common(nsp->time_ns_for_children); } break; case PIDFD_GET_UTS_NAMESPACE: if (IS_ENABLED(CONFIG_UTS_NS)) { get_uts_ns(nsp->uts_ns); ns_common = to_ns_common(nsp->uts_ns); } break; /* Namespaces that don't hang of nsproxy. */ case PIDFD_GET_USER_NAMESPACE: if (IS_ENABLED(CONFIG_USER_NS)) { rcu_read_lock(); ns_common = to_ns_common(get_user_ns(task_cred_xxx(task, user_ns))); rcu_read_unlock(); } break; case PIDFD_GET_PID_NAMESPACE: if (IS_ENABLED(CONFIG_PID_NS)) { rcu_read_lock(); pid_ns = task_active_pid_ns(task); if (pid_ns) ns_common = to_ns_common(get_pid_ns(pid_ns)); rcu_read_unlock(); } break; default: return -ENOIOCTLCMD; } if (!ns_common) return -EOPNOTSUPP; /* open_namespace() unconditionally consumes the reference */ return open_namespace(ns_common); } static const struct file_operations pidfs_file_operations = { .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif .unlocked_ioctl = pidfd_ioctl, .compat_ioctl = compat_ptr_ioctl, }; struct pid *pidfd_pid(const struct file *file) { if (file->f_op != &pidfs_file_operations) return ERR_PTR(-EBADF); return file_inode(file)->i_private; } static struct vfsmount *pidfs_mnt __ro_after_init; #if BITS_PER_LONG == 32 /* * Provide a fallback mechanism for 32-bit systems so processes remain * reliably comparable by inode number even on those systems. */ static DEFINE_IDA(pidfd_inum_ida); static int pidfs_inum(struct pid *pid, unsigned long *ino) { int ret; ret = ida_alloc_range(&pidfd_inum_ida, RESERVED_PIDS + 1, UINT_MAX, GFP_ATOMIC); if (ret < 0) return -ENOSPC; *ino = ret; return 0; } static inline void pidfs_free_inum(unsigned long ino) { if (ino > 0) ida_free(&pidfd_inum_ida, ino); } #else static inline int pidfs_inum(struct pid *pid, unsigned long *ino) { *ino = pid->ino; return 0; } #define pidfs_free_inum(ino) ((void)(ino)) #endif /* * The vfs falls back to simple_setattr() if i_op->setattr() isn't * implemented. Let's reject it completely until we have a clean * permission concept for pidfds. */ static int pidfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EOPNOTSUPP; } /* * User space expects pidfs inodes to have no file type in st_mode. * * In particular, 'lsof' has this legacy logic: * * type = s->st_mode & S_IFMT; * switch (type) { * ... * case 0: * if (!strcmp(p, "anon_inode")) * Lf->ntype = Ntype = N_ANON_INODE; * * to detect our old anon_inode logic. * * Rather than mess with our internal sane inode data, just fix it * up here in getattr() by masking off the format bits. */ static int pidfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->mode &= ~S_IFMT; return 0; } static const struct inode_operations pidfs_inode_operations = { .getattr = pidfs_getattr, .setattr = pidfs_setattr, }; static void pidfs_evict_inode(struct inode *inode) { struct pid *pid = inode->i_private; clear_inode(inode); put_pid(pid); pidfs_free_inum(inode->i_ino); } static const struct super_operations pidfs_sops = { .drop_inode = generic_delete_inode, .evict_inode = pidfs_evict_inode, .statfs = simple_statfs, }; /* * 'lsof' has knowledge of out historical anon_inode use, and expects * the pidfs dentry name to start with 'anon_inode'. */ static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "anon_inode:[pidfd]"); } static const struct dentry_operations pidfs_dentry_operations = { .d_delete = always_delete_dentry, .d_dname = pidfs_dname, .d_prune = stashed_dentry_prune, }; static int pidfs_init_inode(struct inode *inode, void *data) { inode->i_private = data; inode->i_flags |= S_PRIVATE; inode->i_mode |= S_IRWXU; inode->i_op = &pidfs_inode_operations; inode->i_fop = &pidfs_file_operations; /* * Inode numbering for pidfs start at RESERVED_PIDS + 1. This * avoids collisions with the root inode which is 1 for pseudo * filesystems. */ return pidfs_inum(data, &inode->i_ino); } static void pidfs_put_data(void *data) { struct pid *pid = data; put_pid(pid); } static const struct stashed_operations pidfs_stashed_ops = { .init_inode = pidfs_init_inode, .put_data = pidfs_put_data, }; static int pidfs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx; ctx = init_pseudo(fc, PID_FS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &pidfs_sops; ctx->dops = &pidfs_dentry_operations; fc->s_fs_info = (void *)&pidfs_stashed_ops; return 0; } static struct file_system_type pidfs_type = { .name = "pidfs", .init_fs_context = pidfs_init_fs_context, .kill_sb = kill_anon_super, }; struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags) { struct file *pidfd_file; struct path path; int ret; ret = path_from_stashed(&pid->stashed, pidfs_mnt, get_pid(pid), &path); if (ret < 0) return ERR_PTR(ret); pidfd_file = dentry_open(&path, flags, current_cred()); path_put(&path); return pidfd_file; } void __init pidfs_init(void) { pidfs_mnt = kern_mount(&pidfs_type); if (IS_ERR(pidfs_mnt)) panic("Failed to mount pidfs pseudo filesystem"); } |
| 20 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Patrick McHardy <kaber@trash.net> */ #include <linux/module.h> #include <linux/skbuff.h> #include <asm/unaligned.h> #include <net/tcp.h> #include <net/netns/generic.h> #include <linux/proc_fs.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter/nf_synproxy.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_synproxy.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_synproxy.h> unsigned int synproxy_net_id; EXPORT_SYMBOL_GPL(synproxy_net_id); bool synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, const struct tcphdr *th, struct synproxy_options *opts) { int length = (th->doff * 4) - sizeof(*th); u8 buf[40], *ptr; if (unlikely(length < 0)) return false; ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); if (ptr == NULL) return false; opts->options = 0; while (length > 0) { int opcode = *ptr++; int opsize; switch (opcode) { case TCPOPT_EOL: return true; case TCPOPT_NOP: length--; continue; default: if (length < 2) return true; opsize = *ptr++; if (opsize < 2) return true; if (opsize > length) return true; switch (opcode) { case TCPOPT_MSS: if (opsize == TCPOLEN_MSS) { opts->mss_option = get_unaligned_be16(ptr); opts->options |= NF_SYNPROXY_OPT_MSS; } break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW) { opts->wscale = *ptr; if (opts->wscale > TCP_MAX_WSCALE) opts->wscale = TCP_MAX_WSCALE; opts->options |= NF_SYNPROXY_OPT_WSCALE; } break; case TCPOPT_TIMESTAMP: if (opsize == TCPOLEN_TIMESTAMP) { opts->tsval = get_unaligned_be32(ptr); opts->tsecr = get_unaligned_be32(ptr + 4); opts->options |= NF_SYNPROXY_OPT_TIMESTAMP; } break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM) opts->options |= NF_SYNPROXY_OPT_SACK_PERM; break; } ptr += opsize - 2; length -= opsize; } } return true; } EXPORT_SYMBOL_GPL(synproxy_parse_options); static unsigned int synproxy_options_size(const struct synproxy_options *opts) { unsigned int size = 0; if (opts->options & NF_SYNPROXY_OPT_MSS) size += TCPOLEN_MSS_ALIGNED; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) size += TCPOLEN_TSTAMP_ALIGNED; else if (opts->options & NF_SYNPROXY_OPT_SACK_PERM) size += TCPOLEN_SACKPERM_ALIGNED; if (opts->options & NF_SYNPROXY_OPT_WSCALE) size += TCPOLEN_WSCALE_ALIGNED; return size; } static void synproxy_build_options(struct tcphdr *th, const struct synproxy_options *opts) { __be32 *ptr = (__be32 *)(th + 1); u8 options = opts->options; if (options & NF_SYNPROXY_OPT_MSS) *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | opts->mss_option); if (options & NF_SYNPROXY_OPT_TIMESTAMP) { if (options & NF_SYNPROXY_OPT_SACK_PERM) *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); else *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); *ptr++ = htonl(opts->tsval); *ptr++ = htonl(opts->tsecr); } else if (options & NF_SYNPROXY_OPT_SACK_PERM) *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); if (options & NF_SYNPROXY_OPT_WSCALE) *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | opts->wscale); } void synproxy_init_timestamp_cookie(const struct nf_synproxy_info *info, struct synproxy_options *opts) { opts->tsecr = opts->tsval; opts->tsval = tcp_clock_ms() & ~0x3f; if (opts->options & NF_SYNPROXY_OPT_WSCALE) { opts->tsval |= opts->wscale; opts->wscale = info->wscale; } else opts->tsval |= 0xf; if (opts->options & NF_SYNPROXY_OPT_SACK_PERM) opts->tsval |= 1 << 4; if (opts->options & NF_SYNPROXY_OPT_ECN) opts->tsval |= 1 << 5; } EXPORT_SYMBOL_GPL(synproxy_init_timestamp_cookie); static void synproxy_check_timestamp_cookie(struct synproxy_options *opts) { opts->wscale = opts->tsecr & 0xf; if (opts->wscale != 0xf) opts->options |= NF_SYNPROXY_OPT_WSCALE; opts->options |= opts->tsecr & (1 << 4) ? NF_SYNPROXY_OPT_SACK_PERM : 0; opts->options |= opts->tsecr & (1 << 5) ? NF_SYNPROXY_OPT_ECN : 0; } static unsigned int synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff, struct tcphdr *th, struct nf_conn *ct, enum ip_conntrack_info ctinfo, const struct nf_conn_synproxy *synproxy) { unsigned int optoff, optend; __be32 *ptr, old; if (synproxy->tsoff == 0) return 1; optoff = protoff + sizeof(struct tcphdr); optend = protoff + th->doff * 4; if (skb_ensure_writable(skb, optend)) return 0; while (optoff < optend) { unsigned char *op = skb->data + optoff; switch (op[0]) { case TCPOPT_EOL: return 1; case TCPOPT_NOP: optoff++; continue; default: if (optoff + 1 == optend || optoff + op[1] > optend || op[1] < 2) return 0; if (op[0] == TCPOPT_TIMESTAMP && op[1] == TCPOLEN_TIMESTAMP) { if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) { ptr = (__be32 *)&op[2]; old = *ptr; *ptr = htonl(ntohl(*ptr) - synproxy->tsoff); } else { ptr = (__be32 *)&op[6]; old = *ptr; *ptr = htonl(ntohl(*ptr) + synproxy->tsoff); } inet_proto_csum_replace4(&th->check, skb, old, *ptr, false); return 1; } optoff += op[1]; } } return 1; } #ifdef CONFIG_PROC_FS static void *synproxy_cpu_seq_start(struct seq_file *seq, loff_t *pos) { struct synproxy_net *snet = synproxy_pernet(seq_file_net(seq)); int cpu; if (*pos == 0) return SEQ_START_TOKEN; for (cpu = *pos - 1; cpu < nr_cpu_ids; cpu++) { if (!cpu_possible(cpu)) continue; *pos = cpu + 1; return per_cpu_ptr(snet->stats, cpu); } return NULL; } static void *synproxy_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct synproxy_net *snet = synproxy_pernet(seq_file_net(seq)); int cpu; for (cpu = *pos; cpu < nr_cpu_ids; cpu++) { if (!cpu_possible(cpu)) continue; *pos = cpu + 1; return per_cpu_ptr(snet->stats, cpu); } (*pos)++; return NULL; } static void synproxy_cpu_seq_stop(struct seq_file *seq, void *v) { return; } static int synproxy_cpu_seq_show(struct seq_file *seq, void *v) { struct synproxy_stats *stats = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, "entries\t\tsyn_received\t" "cookie_invalid\tcookie_valid\t" "cookie_retrans\tconn_reopened\n"); return 0; } seq_printf(seq, "%08x\t%08x\t%08x\t%08x\t%08x\t%08x\n", 0, stats->syn_received, stats->cookie_invalid, stats->cookie_valid, stats->cookie_retrans, stats->conn_reopened); return 0; } static const struct seq_operations synproxy_cpu_seq_ops = { .start = synproxy_cpu_seq_start, .next = synproxy_cpu_seq_next, .stop = synproxy_cpu_seq_stop, .show = synproxy_cpu_seq_show, }; static int __net_init synproxy_proc_init(struct net *net) { if (!proc_create_net("synproxy", 0444, net->proc_net_stat, &synproxy_cpu_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } static void __net_exit synproxy_proc_exit(struct net *net) { remove_proc_entry("synproxy", net->proc_net_stat); } #else static int __net_init synproxy_proc_init(struct net *net) { return 0; } static void __net_exit synproxy_proc_exit(struct net *net) { return; } #endif /* CONFIG_PROC_FS */ static int __net_init synproxy_net_init(struct net *net) { struct synproxy_net *snet = synproxy_pernet(net); struct nf_conn *ct; int err = -ENOMEM; ct = nf_ct_tmpl_alloc(net, &nf_ct_zone_dflt, GFP_KERNEL); if (!ct) goto err1; if (!nfct_seqadj_ext_add(ct)) goto err2; if (!nfct_synproxy_ext_add(ct)) goto err2; __set_bit(IPS_CONFIRMED_BIT, &ct->status); snet->tmpl = ct; snet->stats = alloc_percpu(struct synproxy_stats); if (snet->stats == NULL) goto err2; err = synproxy_proc_init(net); if (err < 0) goto err3; return 0; err3: free_percpu(snet->stats); err2: nf_ct_tmpl_free(ct); err1: return err; } static void __net_exit synproxy_net_exit(struct net *net) { struct synproxy_net *snet = synproxy_pernet(net); nf_ct_put(snet->tmpl); synproxy_proc_exit(net); free_percpu(snet->stats); } static struct pernet_operations synproxy_net_ops = { .init = synproxy_net_init, .exit = synproxy_net_exit, .id = &synproxy_net_id, .size = sizeof(struct synproxy_net), }; static int __init synproxy_core_init(void) { return register_pernet_subsys(&synproxy_net_ops); } static void __exit synproxy_core_exit(void) { unregister_pernet_subsys(&synproxy_net_ops); } module_init(synproxy_core_init); module_exit(synproxy_core_exit); static struct iphdr * synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct iphdr *iph; skb_reset_network_header(skb); iph = skb_put(skb, sizeof(*iph)); iph->version = 4; iph->ihl = sizeof(*iph) / 4; iph->tos = 0; iph->id = 0; iph->frag_off = htons(IP_DF); iph->ttl = READ_ONCE(net->ipv4.sysctl_ip_default_ttl); iph->protocol = IPPROTO_TCP; iph->check = 0; iph->saddr = saddr; iph->daddr = daddr; return iph; } static void synproxy_send_tcp(struct net *net, const struct sk_buff *skb, struct sk_buff *nskb, struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo, struct iphdr *niph, struct tcphdr *nth, unsigned int tcp_hdr_size) { nth->check = ~tcp_v4_check(tcp_hdr_size, niph->saddr, niph->daddr, 0); nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (unsigned char *)nth - nskb->head; nskb->csum_offset = offsetof(struct tcphdr, check); skb_dst_set_noref(nskb, skb_dst(skb)); nskb->protocol = htons(ETH_P_IP); if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC)) goto free_nskb; if (nfct) { nf_ct_set(nskb, (struct nf_conn *)nfct, ctinfo); nf_conntrack_get(nfct); } ip_local_out(net, nskb->sk, nskb); return; free_nskb: kfree_skb(nskb); } void synproxy_send_client_synack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { struct sk_buff *nskb; struct iphdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; u16 mss = opts->mss_encode; iph = ip_hdr(skb); tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, GFP_ATOMIC); if (!nskb) return; skb_reserve(nskb, MAX_TCP_HEADER); niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr); skb_reset_transport_header(nskb); nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(__cookie_v4_init_sequence(iph, th, &mss)); nth->ack_seq = htonl(ntohl(th->seq) + 1); tcp_flag_word(nth) = TCP_FLAG_SYN | TCP_FLAG_ACK; if (opts->options & NF_SYNPROXY_OPT_ECN) tcp_flag_word(nth) |= TCP_FLAG_ECE; nth->doff = tcp_hdr_size / 4; nth->window = 0; nth->check = 0; nth->urg_ptr = 0; synproxy_build_options(nth, opts); synproxy_send_tcp(net, skb, nskb, skb_nfct(skb), IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } EXPORT_SYMBOL_GPL(synproxy_send_client_synack); static void synproxy_send_server_syn(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts, u32 recv_seq) { struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *nskb; struct iphdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; iph = ip_hdr(skb); tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, GFP_ATOMIC); if (!nskb) return; skb_reserve(nskb, MAX_TCP_HEADER); niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr); skb_reset_transport_header(nskb); nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(recv_seq - 1); /* ack_seq is used to relay our ISN to the synproxy hook to initialize * sequence number translation once a connection tracking entry exists. */ nth->ack_seq = htonl(ntohl(th->ack_seq) - 1); tcp_flag_word(nth) = TCP_FLAG_SYN; if (opts->options & NF_SYNPROXY_OPT_ECN) tcp_flag_word(nth) |= TCP_FLAG_ECE | TCP_FLAG_CWR; nth->doff = tcp_hdr_size / 4; nth->window = th->window; nth->check = 0; nth->urg_ptr = 0; synproxy_build_options(nth, opts); synproxy_send_tcp(net, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, niph, nth, tcp_hdr_size); } static void synproxy_send_server_ack(struct net *net, const struct ip_ct_tcp *state, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { struct sk_buff *nskb; struct iphdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; iph = ip_hdr(skb); tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, GFP_ATOMIC); if (!nskb) return; skb_reserve(nskb, MAX_TCP_HEADER); niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr); skb_reset_transport_header(nskb); nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(ntohl(th->ack_seq)); nth->ack_seq = htonl(ntohl(th->seq) + 1); tcp_flag_word(nth) = TCP_FLAG_ACK; nth->doff = tcp_hdr_size / 4; nth->window = htons(state->seen[IP_CT_DIR_ORIGINAL].td_maxwin); nth->check = 0; nth->urg_ptr = 0; synproxy_build_options(nth, opts); synproxy_send_tcp(net, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); } static void synproxy_send_client_ack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { struct sk_buff *nskb; struct iphdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; iph = ip_hdr(skb); tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, GFP_ATOMIC); if (!nskb) return; skb_reserve(nskb, MAX_TCP_HEADER); niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr); skb_reset_transport_header(nskb); nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(ntohl(th->seq) + 1); nth->ack_seq = th->ack_seq; tcp_flag_word(nth) = TCP_FLAG_ACK; nth->doff = tcp_hdr_size / 4; nth->window = htons(ntohs(th->window) >> opts->wscale); nth->check = 0; nth->urg_ptr = 0; synproxy_build_options(nth, opts); synproxy_send_tcp(net, skb, nskb, skb_nfct(skb), IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } bool synproxy_recv_client_ack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq) { struct synproxy_net *snet = synproxy_pernet(net); int mss; mss = __cookie_v4_check(ip_hdr(skb), th); if (mss == 0) { this_cpu_inc(snet->stats->cookie_invalid); return false; } this_cpu_inc(snet->stats->cookie_valid); opts->mss_option = mss; opts->options |= NF_SYNPROXY_OPT_MSS; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) synproxy_check_timestamp_cookie(opts); synproxy_send_server_syn(net, skb, th, opts, recv_seq); return true; } EXPORT_SYMBOL_GPL(synproxy_recv_client_ack); unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs) { struct net *net = nhs->net; struct synproxy_net *snet = synproxy_pernet(net); enum ip_conntrack_info ctinfo; struct nf_conn *ct; struct nf_conn_synproxy *synproxy; struct synproxy_options opts = {}; const struct ip_ct_tcp *state; struct tcphdr *th, _th; unsigned int thoff; ct = nf_ct_get(skb, &ctinfo); if (!ct) return NF_ACCEPT; synproxy = nfct_synproxy(ct); if (!synproxy) return NF_ACCEPT; if (nf_is_loopback_packet(skb) || ip_hdr(skb)->protocol != IPPROTO_TCP) return NF_ACCEPT; thoff = ip_hdrlen(skb); th = skb_header_pointer(skb, thoff, sizeof(_th), &_th); if (!th) return NF_DROP; state = &ct->proto.tcp; switch (state->state) { case TCP_CONNTRACK_CLOSE: if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq) + 1); break; } if (!th->syn || th->ack || CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) break; /* Reopened connection - reset the sequence number and timestamp * adjustments, they will get initialized once the connection is * reestablished. */ nf_ct_seqadj_init(ct, ctinfo, 0); synproxy->tsoff = 0; this_cpu_inc(snet->stats->conn_reopened); fallthrough; case TCP_CONNTRACK_SYN_SENT: if (!synproxy_parse_options(skb, thoff, th, &opts)) return NF_DROP; if (!th->syn && th->ack && CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { /* Keep-Alives are sent with SEG.SEQ = SND.NXT-1, * therefore we need to add 1 to make the SYN sequence * number match the one of first SYN. */ if (synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq) + 1)) { this_cpu_inc(snet->stats->cookie_retrans); consume_skb(skb); return NF_STOLEN; } else { return NF_DROP; } } synproxy->isn = ntohl(th->ack_seq); if (opts.options & NF_SYNPROXY_OPT_TIMESTAMP) synproxy->its = opts.tsecr; nf_conntrack_event_cache(IPCT_SYNPROXY, ct); break; case TCP_CONNTRACK_SYN_RECV: if (!th->syn || !th->ack) break; if (!synproxy_parse_options(skb, thoff, th, &opts)) return NF_DROP; if (opts.options & NF_SYNPROXY_OPT_TIMESTAMP) { synproxy->tsoff = opts.tsval - synproxy->its; nf_conntrack_event_cache(IPCT_SYNPROXY, ct); } opts.options &= ~(NF_SYNPROXY_OPT_MSS | NF_SYNPROXY_OPT_WSCALE | NF_SYNPROXY_OPT_SACK_PERM); swap(opts.tsval, opts.tsecr); synproxy_send_server_ack(net, state, skb, th, &opts); nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq)); nf_conntrack_event_cache(IPCT_SEQADJ, ct); swap(opts.tsval, opts.tsecr); synproxy_send_client_ack(net, skb, th, &opts); consume_skb(skb); return NF_STOLEN; default: break; } synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy); return NF_ACCEPT; } EXPORT_SYMBOL_GPL(ipv4_synproxy_hook); static const struct nf_hook_ops ipv4_synproxy_ops[] = { { .hook = ipv4_synproxy_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, }, { .hook = ipv4_synproxy_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, }, }; int nf_synproxy_ipv4_init(struct synproxy_net *snet, struct net *net) { int err; if (snet->hook_ref4 == 0) { err = nf_register_net_hooks(net, ipv4_synproxy_ops, ARRAY_SIZE(ipv4_synproxy_ops)); if (err) return err; } snet->hook_ref4++; return 0; } EXPORT_SYMBOL_GPL(nf_synproxy_ipv4_init); void nf_synproxy_ipv4_fini(struct synproxy_net *snet, struct net *net) { snet->hook_ref4--; if (snet->hook_ref4 == 0) nf_unregister_net_hooks(net, ipv4_synproxy_ops, ARRAY_SIZE(ipv4_synproxy_ops)); } EXPORT_SYMBOL_GPL(nf_synproxy_ipv4_fini); #if IS_ENABLED(CONFIG_IPV6) static struct ipv6hdr * synproxy_build_ip_ipv6(struct net *net, struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr) { struct ipv6hdr *iph; skb_reset_network_header(skb); iph = skb_put(skb, sizeof(*iph)); ip6_flow_hdr(iph, 0, 0); iph->hop_limit = READ_ONCE(net->ipv6.devconf_all->hop_limit); iph->nexthdr = IPPROTO_TCP; iph->saddr = *saddr; iph->daddr = *daddr; return iph; } static void synproxy_send_tcp_ipv6(struct net *net, const struct sk_buff *skb, struct sk_buff *nskb, struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo, struct ipv6hdr *niph, struct tcphdr *nth, unsigned int tcp_hdr_size) { struct dst_entry *dst; struct flowi6 fl6; int err; nth->check = ~tcp_v6_check(tcp_hdr_size, &niph->saddr, &niph->daddr, 0); nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (unsigned char *)nth - nskb->head; nskb->csum_offset = offsetof(struct tcphdr, check); memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; fl6.saddr = niph->saddr; fl6.daddr = niph->daddr; fl6.fl6_sport = nth->source; fl6.fl6_dport = nth->dest; security_skb_classify_flow((struct sk_buff *)skb, flowi6_to_flowi_common(&fl6)); err = nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false); if (err) { goto free_nskb; } dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) goto free_nskb; skb_dst_set(nskb, dst); if (nfct) { nf_ct_set(nskb, (struct nf_conn *)nfct, ctinfo); nf_conntrack_get(nfct); } ip6_local_out(net, nskb->sk, nskb); return; free_nskb: kfree_skb(nskb); } void synproxy_send_client_synack_ipv6(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { struct sk_buff *nskb; struct ipv6hdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; u16 mss = opts->mss_encode; iph = ipv6_hdr(skb); tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, GFP_ATOMIC); if (!nskb) return; skb_reserve(nskb, MAX_TCP_HEADER); niph = synproxy_build_ip_ipv6(net, nskb, &iph->daddr, &iph->saddr); skb_reset_transport_header(nskb); nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(nf_ipv6_cookie_init_sequence(iph, th, &mss)); nth->ack_seq = htonl(ntohl(th->seq) + 1); tcp_flag_word(nth) = TCP_FLAG_SYN | TCP_FLAG_ACK; if (opts->options & NF_SYNPROXY_OPT_ECN) tcp_flag_word(nth) |= TCP_FLAG_ECE; nth->doff = tcp_hdr_size / 4; nth->window = 0; nth->check = 0; nth->urg_ptr = 0; synproxy_build_options(nth, opts); synproxy_send_tcp_ipv6(net, skb, nskb, skb_nfct(skb), IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } EXPORT_SYMBOL_GPL(synproxy_send_client_synack_ipv6); static void synproxy_send_server_syn_ipv6(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts, u32 recv_seq) { struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *nskb; struct ipv6hdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; iph = ipv6_hdr(skb); tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, GFP_ATOMIC); if (!nskb) return; skb_reserve(nskb, MAX_TCP_HEADER); niph = synproxy_build_ip_ipv6(net, nskb, &iph->saddr, &iph->daddr); skb_reset_transport_header(nskb); nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(recv_seq - 1); /* ack_seq is used to relay our ISN to the synproxy hook to initialize * sequence number translation once a connection tracking entry exists. */ nth->ack_seq = htonl(ntohl(th->ack_seq) - 1); tcp_flag_word(nth) = TCP_FLAG_SYN; if (opts->options & NF_SYNPROXY_OPT_ECN) tcp_flag_word(nth) |= TCP_FLAG_ECE | TCP_FLAG_CWR; nth->doff = tcp_hdr_size / 4; nth->window = th->window; nth->check = 0; nth->urg_ptr = 0; synproxy_build_options(nth, opts); synproxy_send_tcp_ipv6(net, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, niph, nth, tcp_hdr_size); } static void synproxy_send_server_ack_ipv6(struct net *net, const struct ip_ct_tcp *state, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { struct sk_buff *nskb; struct ipv6hdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; iph = ipv6_hdr(skb); tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, GFP_ATOMIC); if (!nskb) return; skb_reserve(nskb, MAX_TCP_HEADER); niph = synproxy_build_ip_ipv6(net, nskb, &iph->daddr, &iph->saddr); skb_reset_transport_header(nskb); nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(ntohl(th->ack_seq)); nth->ack_seq = htonl(ntohl(th->seq) + 1); tcp_flag_word(nth) = TCP_FLAG_ACK; nth->doff = tcp_hdr_size / 4; nth->window = htons(state->seen[IP_CT_DIR_ORIGINAL].td_maxwin); nth->check = 0; nth->urg_ptr = 0; synproxy_build_options(nth, opts); synproxy_send_tcp_ipv6(net, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); } static void synproxy_send_client_ack_ipv6(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { struct sk_buff *nskb; struct ipv6hdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; iph = ipv6_hdr(skb); tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, GFP_ATOMIC); if (!nskb) return; skb_reserve(nskb, MAX_TCP_HEADER); niph = synproxy_build_ip_ipv6(net, nskb, &iph->saddr, &iph->daddr); skb_reset_transport_header(nskb); nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(ntohl(th->seq) + 1); nth->ack_seq = th->ack_seq; tcp_flag_word(nth) = TCP_FLAG_ACK; nth->doff = tcp_hdr_size / 4; nth->window = htons(ntohs(th->window) >> opts->wscale); nth->check = 0; nth->urg_ptr = 0; synproxy_build_options(nth, opts); synproxy_send_tcp_ipv6(net, skb, nskb, skb_nfct(skb), IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } bool synproxy_recv_client_ack_ipv6(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq) { struct synproxy_net *snet = synproxy_pernet(net); int mss; mss = nf_cookie_v6_check(ipv6_hdr(skb), th); if (mss == 0) { this_cpu_inc(snet->stats->cookie_invalid); return false; } this_cpu_inc(snet->stats->cookie_valid); opts->mss_option = mss; opts->options |= NF_SYNPROXY_OPT_MSS; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) synproxy_check_timestamp_cookie(opts); synproxy_send_server_syn_ipv6(net, skb, th, opts, recv_seq); return true; } EXPORT_SYMBOL_GPL(synproxy_recv_client_ack_ipv6); unsigned int ipv6_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs) { struct net *net = nhs->net; struct synproxy_net *snet = synproxy_pernet(net); enum ip_conntrack_info ctinfo; struct nf_conn *ct; struct nf_conn_synproxy *synproxy; struct synproxy_options opts = {}; const struct ip_ct_tcp *state; struct tcphdr *th, _th; __be16 frag_off; u8 nexthdr; int thoff; ct = nf_ct_get(skb, &ctinfo); if (!ct) return NF_ACCEPT; synproxy = nfct_synproxy(ct); if (!synproxy) return NF_ACCEPT; if (nf_is_loopback_packet(skb)) return NF_ACCEPT; nexthdr = ipv6_hdr(skb)->nexthdr; thoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (thoff < 0 || nexthdr != IPPROTO_TCP) return NF_ACCEPT; th = skb_header_pointer(skb, thoff, sizeof(_th), &_th); if (!th) return NF_DROP; state = &ct->proto.tcp; switch (state->state) { case TCP_CONNTRACK_CLOSE: if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq) + 1); break; } if (!th->syn || th->ack || CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) break; /* Reopened connection - reset the sequence number and timestamp * adjustments, they will get initialized once the connection is * reestablished. */ nf_ct_seqadj_init(ct, ctinfo, 0); synproxy->tsoff = 0; this_cpu_inc(snet->stats->conn_reopened); fallthrough; case TCP_CONNTRACK_SYN_SENT: if (!synproxy_parse_options(skb, thoff, th, &opts)) return NF_DROP; if (!th->syn && th->ack && CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { /* Keep-Alives are sent with SEG.SEQ = SND.NXT-1, * therefore we need to add 1 to make the SYN sequence * number match the one of first SYN. */ if (synproxy_recv_client_ack_ipv6(net, skb, th, &opts, ntohl(th->seq) + 1)) { this_cpu_inc(snet->stats->cookie_retrans); consume_skb(skb); return NF_STOLEN; } else { return NF_DROP; } } synproxy->isn = ntohl(th->ack_seq); if (opts.options & NF_SYNPROXY_OPT_TIMESTAMP) synproxy->its = opts.tsecr; nf_conntrack_event_cache(IPCT_SYNPROXY, ct); break; case TCP_CONNTRACK_SYN_RECV: if (!th->syn || !th->ack) break; if (!synproxy_parse_options(skb, thoff, th, &opts)) return NF_DROP; if (opts.options & NF_SYNPROXY_OPT_TIMESTAMP) { synproxy->tsoff = opts.tsval - synproxy->its; nf_conntrack_event_cache(IPCT_SYNPROXY, ct); } opts.options &= ~(NF_SYNPROXY_OPT_MSS | NF_SYNPROXY_OPT_WSCALE | NF_SYNPROXY_OPT_SACK_PERM); swap(opts.tsval, opts.tsecr); synproxy_send_server_ack_ipv6(net, state, skb, th, &opts); nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq)); nf_conntrack_event_cache(IPCT_SEQADJ, ct); swap(opts.tsval, opts.tsecr); synproxy_send_client_ack_ipv6(net, skb, th, &opts); consume_skb(skb); return NF_STOLEN; default: break; } synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy); return NF_ACCEPT; } EXPORT_SYMBOL_GPL(ipv6_synproxy_hook); static const struct nf_hook_ops ipv6_synproxy_ops[] = { { .hook = ipv6_synproxy_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, }, { .hook = ipv6_synproxy_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, }, }; int nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net) { int err; if (snet->hook_ref6 == 0) { err = nf_register_net_hooks(net, ipv6_synproxy_ops, ARRAY_SIZE(ipv6_synproxy_ops)); if (err) return err; } snet->hook_ref6++; return 0; } EXPORT_SYMBOL_GPL(nf_synproxy_ipv6_init); void nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net) { snet->hook_ref6--; if (snet->hook_ref6 == 0) nf_unregister_net_hooks(net, ipv6_synproxy_ops, ARRAY_SIZE(ipv6_synproxy_ops)); } EXPORT_SYMBOL_GPL(nf_synproxy_ipv6_fini); #endif /* CONFIG_IPV6 */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("nftables SYNPROXY expression support"); |
| 100 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_UNALIGNED_H #define __ASM_GENERIC_UNALIGNED_H /* * This is the most generic implementation of unaligned accesses * and should work almost anywhere. */ #include <linux/unaligned/packed_struct.h> #include <asm/byteorder.h> #include <vdso/unaligned.h> #define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) #define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr)) static inline u16 get_unaligned_le16(const void *p) { return le16_to_cpu(__get_unaligned_t(__le16, p)); } static inline u32 get_unaligned_le32(const void *p) { return le32_to_cpu(__get_unaligned_t(__le32, p)); } static inline u64 get_unaligned_le64(const void *p) { return le64_to_cpu(__get_unaligned_t(__le64, p)); } static inline void put_unaligned_le16(u16 val, void *p) { __put_unaligned_t(__le16, cpu_to_le16(val), p); } static inline void put_unaligned_le32(u32 val, void *p) { __put_unaligned_t(__le32, cpu_to_le32(val), p); } static inline void put_unaligned_le64(u64 val, void *p) { __put_unaligned_t(__le64, cpu_to_le64(val), p); } static inline u16 get_unaligned_be16(const void *p) { return be16_to_cpu(__get_unaligned_t(__be16, p)); } static inline u32 get_unaligned_be32(const void *p) { return be32_to_cpu(__get_unaligned_t(__be32, p)); } static inline u64 get_unaligned_be64(const void *p) { return be64_to_cpu(__get_unaligned_t(__be64, p)); } static inline void put_unaligned_be16(u16 val, void *p) { __put_unaligned_t(__be16, cpu_to_be16(val), p); } static inline void put_unaligned_be32(u32 val, void *p) { __put_unaligned_t(__be32, cpu_to_be32(val), p); } static inline void put_unaligned_be64(u64 val, void *p) { __put_unaligned_t(__be64, cpu_to_be64(val), p); } static inline u32 __get_unaligned_be24(const u8 *p) { return p[0] << 16 | p[1] << 8 | p[2]; } static inline u32 get_unaligned_be24(const void *p) { return __get_unaligned_be24(p); } static inline u32 __get_unaligned_le24(const u8 *p) { return p[0] | p[1] << 8 | p[2] << 16; } static inline u32 get_unaligned_le24(const void *p) { return __get_unaligned_le24(p); } static inline void __put_unaligned_be24(const u32 val, u8 *p) { *p++ = (val >> 16) & 0xff; *p++ = (val >> 8) & 0xff; *p++ = val & 0xff; } static inline void put_unaligned_be24(const u32 val, void *p) { __put_unaligned_be24(val, p); } static inline void __put_unaligned_le24(const u32 val, u8 *p) { *p++ = val & 0xff; *p++ = (val >> 8) & 0xff; *p++ = (val >> 16) & 0xff; } static inline void put_unaligned_le24(const u32 val, void *p) { __put_unaligned_le24(val, p); } static inline void __put_unaligned_be48(const u64 val, u8 *p) { *p++ = (val >> 40) & 0xff; *p++ = (val >> 32) & 0xff; *p++ = (val >> 24) & 0xff; *p++ = (val >> 16) & 0xff; *p++ = (val >> 8) & 0xff; *p++ = val & 0xff; } static inline void put_unaligned_be48(const u64 val, void *p) { __put_unaligned_be48(val, p); } static inline u64 __get_unaligned_be48(const u8 *p) { return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | p[3] << 16 | p[4] << 8 | p[5]; } static inline u64 get_unaligned_be48(const void *p) { return __get_unaligned_be48(p); } #endif /* __ASM_GENERIC_UNALIGNED_H */ |
| 9 9 9 9 9 9 9 9 9 9 9 9 8 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/block_validity.c * * Copyright (C) 2009 * Theodore Ts'o (tytso@mit.edu) * * Track which blocks in the filesystem are metadata blocks that * should never be used as data blocks by files or directories. */ #include <linux/time.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/quotaops.h> #include <linux/buffer_head.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/blkdev.h> #include <linux/slab.h> #include "ext4.h" struct ext4_system_zone { struct rb_node node; ext4_fsblk_t start_blk; unsigned int count; u32 ino; }; static struct kmem_cache *ext4_system_zone_cachep; int __init ext4_init_system_zone(void) { ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone, 0); if (ext4_system_zone_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_system_zone(void) { rcu_barrier(); kmem_cache_destroy(ext4_system_zone_cachep); } static inline int can_merge(struct ext4_system_zone *entry1, struct ext4_system_zone *entry2) { if ((entry1->start_blk + entry1->count) == entry2->start_blk && entry1->ino == entry2->ino) return 1; return 0; } static void release_system_zone(struct ext4_system_blocks *system_blks) { struct ext4_system_zone *entry, *n; rbtree_postorder_for_each_entry_safe(entry, n, &system_blks->root, node) kmem_cache_free(ext4_system_zone_cachep, entry); } /* * Mark a range of blocks as belonging to the "system zone" --- that * is, filesystem metadata blocks which should never be used by * inodes. */ static int add_system_zone(struct ext4_system_blocks *system_blks, ext4_fsblk_t start_blk, unsigned int count, u32 ino) { struct ext4_system_zone *new_entry, *entry; struct rb_node **n = &system_blks->root.rb_node, *node; struct rb_node *parent = NULL, *new_node; while (*n) { parent = *n; entry = rb_entry(parent, struct ext4_system_zone, node); if (start_blk < entry->start_blk) n = &(*n)->rb_left; else if (start_blk >= (entry->start_blk + entry->count)) n = &(*n)->rb_right; else /* Unexpected overlap of system zones. */ return -EFSCORRUPTED; } new_entry = kmem_cache_alloc(ext4_system_zone_cachep, GFP_KERNEL); if (!new_entry) return -ENOMEM; new_entry->start_blk = start_blk; new_entry->count = count; new_entry->ino = ino; new_node = &new_entry->node; rb_link_node(new_node, parent, n); rb_insert_color(new_node, &system_blks->root); /* Can we merge to the left? */ node = rb_prev(new_node); if (node) { entry = rb_entry(node, struct ext4_system_zone, node); if (can_merge(entry, new_entry)) { new_entry->start_blk = entry->start_blk; new_entry->count += entry->count; rb_erase(node, &system_blks->root); kmem_cache_free(ext4_system_zone_cachep, entry); } } /* Can we merge to the right? */ node = rb_next(new_node); if (node) { entry = rb_entry(node, struct ext4_system_zone, node); if (can_merge(new_entry, entry)) { new_entry->count += entry->count; rb_erase(node, &system_blks->root); kmem_cache_free(ext4_system_zone_cachep, entry); } } return 0; } static void debug_print_tree(struct ext4_sb_info *sbi) { struct rb_node *node; struct ext4_system_zone *entry; struct ext4_system_blocks *system_blks; int first = 1; printk(KERN_INFO "System zones: "); rcu_read_lock(); system_blks = rcu_dereference(sbi->s_system_blks); node = rb_first(&system_blks->root); while (node) { entry = rb_entry(node, struct ext4_system_zone, node); printk(KERN_CONT "%s%llu-%llu", first ? "" : ", ", entry->start_blk, entry->start_blk + entry->count - 1); first = 0; node = rb_next(node); } rcu_read_unlock(); printk(KERN_CONT "\n"); } static int ext4_protect_reserved_inode(struct super_block *sb, struct ext4_system_blocks *system_blks, u32 ino) { struct inode *inode; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_map_blocks map; u32 i = 0, num; int err = 0, n; if ((ino < EXT4_ROOT_INO) || (ino > le32_to_cpu(sbi->s_es->s_inodes_count))) return -EINVAL; inode = ext4_iget(sb, ino, EXT4_IGET_SPECIAL); if (IS_ERR(inode)) return PTR_ERR(inode); num = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; while (i < num) { cond_resched(); map.m_lblk = i; map.m_len = num - i; n = ext4_map_blocks(NULL, inode, &map, 0); if (n < 0) { err = n; break; } if (n == 0) { i++; } else { err = add_system_zone(system_blks, map.m_pblk, n, ino); if (err < 0) { if (err == -EFSCORRUPTED) { EXT4_ERROR_INODE_ERR(inode, -err, "blocks %llu-%llu from inode overlap system zone", map.m_pblk, map.m_pblk + map.m_len - 1); } break; } i += n; } } iput(inode); return err; } static void ext4_destroy_system_zone(struct rcu_head *rcu) { struct ext4_system_blocks *system_blks; system_blks = container_of(rcu, struct ext4_system_blocks, rcu); release_system_zone(system_blks); kfree(system_blks); } /* * Build system zone rbtree which is used for block validity checking. * * The update of system_blks pointer in this function is protected by * sb->s_umount semaphore. However we have to be careful as we can be * racing with ext4_inode_block_valid() calls reading system_blks rbtree * protected only by RCU. That's why we first build the rbtree and then * swap it in place. */ int ext4_setup_system_zone(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_system_blocks *system_blks; struct ext4_group_desc *gdp; ext4_group_t i; int ret; system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL); if (!system_blks) return -ENOMEM; for (i=0; i < ngroups; i++) { unsigned int meta_blks = ext4_num_base_meta_blocks(sb, i); cond_resched(); if (meta_blks != 0) { ret = add_system_zone(system_blks, ext4_group_first_block_no(sb, i), meta_blks, 0); if (ret) goto err; } gdp = ext4_get_group_desc(sb, i, NULL); ret = add_system_zone(system_blks, ext4_block_bitmap(sb, gdp), 1, 0); if (ret) goto err; ret = add_system_zone(system_blks, ext4_inode_bitmap(sb, gdp), 1, 0); if (ret) goto err; ret = add_system_zone(system_blks, ext4_inode_table(sb, gdp), sbi->s_itb_per_group, 0); if (ret) goto err; } if (ext4_has_feature_journal(sb) && sbi->s_es->s_journal_inum) { ret = ext4_protect_reserved_inode(sb, system_blks, le32_to_cpu(sbi->s_es->s_journal_inum)); if (ret) goto err; } /* * System blks rbtree complete, announce it once to prevent racing * with ext4_inode_block_valid() accessing the rbtree at the same * time. */ rcu_assign_pointer(sbi->s_system_blks, system_blks); if (test_opt(sb, DEBUG)) debug_print_tree(sbi); return 0; err: release_system_zone(system_blks); kfree(system_blks); return ret; } /* * Called when the filesystem is unmounted or when remounting it with * noblock_validity specified. * * The update of system_blks pointer in this function is protected by * sb->s_umount semaphore. However we have to be careful as we can be * racing with ext4_inode_block_valid() calls reading system_blks rbtree * protected only by RCU. So we first clear the system_blks pointer and * then free the rbtree only after RCU grace period expires. */ void ext4_release_system_zone(struct super_block *sb) { struct ext4_system_blocks *system_blks; system_blks = rcu_dereference_protected(EXT4_SB(sb)->s_system_blks, lockdep_is_held(&sb->s_umount)); rcu_assign_pointer(EXT4_SB(sb)->s_system_blks, NULL); if (system_blks) call_rcu(&system_blks->rcu, ext4_destroy_system_zone); } int ext4_sb_block_valid(struct super_block *sb, struct inode *inode, ext4_fsblk_t start_blk, unsigned int count) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_system_blocks *system_blks; struct ext4_system_zone *entry; struct rb_node *n; int ret = 1; if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || (start_blk + count < start_blk) || (start_blk + count > ext4_blocks_count(sbi->s_es))) return 0; /* * Lock the system zone to prevent it being released concurrently * when doing a remount which inverse current "[no]block_validity" * mount option. */ rcu_read_lock(); system_blks = rcu_dereference(sbi->s_system_blks); if (system_blks == NULL) goto out_rcu; n = system_blks->root.rb_node; while (n) { entry = rb_entry(n, struct ext4_system_zone, node); if (start_blk + count - 1 < entry->start_blk) n = n->rb_left; else if (start_blk >= (entry->start_blk + entry->count)) n = n->rb_right; else { ret = 0; if (inode) ret = (entry->ino == inode->i_ino); break; } } out_rcu: rcu_read_unlock(); return ret; } /* * Returns 1 if the passed-in block region (start_blk, * start_blk+count) is valid; 0 if some part of the block region * overlaps with some other filesystem metadata blocks. */ int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, unsigned int count) { return ext4_sb_block_valid(inode->i_sb, inode, start_blk, count); } int ext4_check_blockref(const char *function, unsigned int line, struct inode *inode, __le32 *p, unsigned int max) { __le32 *bref = p; unsigned int blk; if (ext4_has_feature_journal(inode->i_sb) && (inode->i_ino == le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) return 0; while (bref < p+max) { blk = le32_to_cpu(*bref++); if (blk && unlikely(!ext4_inode_block_valid(inode, blk, 1))) { ext4_error_inode(inode, function, line, blk, "invalid block"); return -EFSCORRUPTED; } } return 0; } |
| 139 6 895 590 410 915 915 333 333 3041 180 336 673 43 170 170 170 45 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 | /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_MAPLE_TREE_H #define _LINUX_MAPLE_TREE_H /* * Maple Tree - An RCU-safe adaptive tree for storing ranges * Copyright (c) 2018-2022 Oracle * Authors: Liam R. Howlett <Liam.Howlett@Oracle.com> * Matthew Wilcox <willy@infradead.org> */ #include <linux/kernel.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> /* #define CONFIG_MAPLE_RCU_DISABLED */ /* * Allocated nodes are mutable until they have been inserted into the tree, * at which time they cannot change their type until they have been removed * from the tree and an RCU grace period has passed. * * Removed nodes have their ->parent set to point to themselves. RCU readers * check ->parent before relying on the value that they loaded from the * slots array. This lets us reuse the slots array for the RCU head. * * Nodes in the tree point to their parent unless bit 0 is set. */ #if defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) /* 64bit sizes */ #define MAPLE_NODE_SLOTS 31 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 16 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 10 /* 240 bytes */ #define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 1) #else /* 32bit sizes */ #define MAPLE_NODE_SLOTS 63 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 32 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 21 /* 240 bytes */ #define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 2) #endif /* defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) */ #define MAPLE_NODE_MASK 255UL /* * The node->parent of the root node has bit 0 set and the rest of the pointer * is a pointer to the tree itself. No more bits are available in this pointer * (on m68k, the data structure may only be 2-byte aligned). * * Internal non-root nodes can only have maple_range_* nodes as parents. The * parent pointer is 256B aligned like all other tree nodes. When storing a 32 * or 64 bit values, the offset can fit into 4 bits. The 16 bit values need an * extra bit to store the offset. This extra bit comes from a reuse of the last * bit in the node type. This is possible by using bit 1 to indicate if bit 2 * is part of the type or the slot. * * Once the type is decided, the decision of an allocation range type or a * range type is done by examining the immutable tree flag for the * MT_FLAGS_ALLOC_RANGE flag. * * Node types: * 0x??1 = Root * 0x?00 = 16 bit nodes * 0x010 = 32 bit nodes * 0x110 = 64 bit nodes * * Slot size and location in the parent pointer: * type : slot location * 0x??1 : Root * 0x?00 : 16 bit values, type in 0-1, slot in 2-6 * 0x010 : 32 bit values, type in 0-2, slot in 3-6 * 0x110 : 64 bit values, type in 0-2, slot in 3-6 */ /* * This metadata is used to optimize the gap updating code and in reverse * searching for gaps or any other code that needs to find the end of the data. */ struct maple_metadata { unsigned char end; unsigned char gap; }; /* * Leaf nodes do not store pointers to nodes, they store user data. Users may * store almost any bit pattern. As noted above, the optimisation of storing an * entry at 0 in the root pointer cannot be done for data which have the bottom * two bits set to '10'. We also reserve values with the bottom two bits set to * '10' which are below 4096 (ie 2, 6, 10 .. 4094) for internal use. Some APIs * return errnos as a negative errno shifted right by two bits and the bottom * two bits set to '10', and while choosing to store these values in the array * is not an error, it may lead to confusion if you're testing for an error with * mas_is_err(). * * Non-leaf nodes store the type of the node pointed to (enum maple_type in bits * 3-6), bit 2 is reserved. That leaves bits 0-1 unused for now. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to * indicate that the tree is specifying ranges, Pivots may appear in the * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. */ struct maple_range_64 { struct maple_pnode *parent; unsigned long pivot[MAPLE_RANGE64_SLOTS - 1]; union { void __rcu *slot[MAPLE_RANGE64_SLOTS]; struct { void __rcu *pad[MAPLE_RANGE64_SLOTS - 1]; struct maple_metadata meta; }; }; }; /* * At tree creation time, the user can specify that they're willing to trade off * storing fewer entries in a tree in return for storing more information in * each node. * * The maple tree supports recording the largest range of NULL entries available * in this node, also called gaps. This optimises the tree for allocating a * range. */ struct maple_arange_64 { struct maple_pnode *parent; unsigned long pivot[MAPLE_ARANGE64_SLOTS - 1]; void __rcu *slot[MAPLE_ARANGE64_SLOTS]; unsigned long gap[MAPLE_ARANGE64_SLOTS]; struct maple_metadata meta; }; struct maple_alloc { unsigned long total; unsigned char node_count; unsigned int request_count; struct maple_alloc *slot[MAPLE_ALLOC_SLOTS]; }; struct maple_topiary { struct maple_pnode *parent; struct maple_enode *next; /* Overlaps the pivot */ }; enum maple_type { maple_dense, maple_leaf_64, maple_range_64, maple_arange_64, }; enum store_type { wr_invalid, wr_new_root, wr_store_root, wr_exact_fit, wr_spanning_store, wr_split_store, wr_rebalance, wr_append, wr_node_store, wr_slot_store, }; /** * DOC: Maple tree flags * * * MT_FLAGS_ALLOC_RANGE - Track gaps in this tree * * MT_FLAGS_USE_RCU - Operate in RCU mode * * MT_FLAGS_HEIGHT_OFFSET - The position of the tree height in the flags * * MT_FLAGS_HEIGHT_MASK - The mask for the maple tree height value * * MT_FLAGS_LOCK_MASK - How the mt_lock is used * * MT_FLAGS_LOCK_IRQ - Acquired irq-safe * * MT_FLAGS_LOCK_BH - Acquired bh-safe * * MT_FLAGS_LOCK_EXTERN - mt_lock is not used * * MAPLE_HEIGHT_MAX The largest height that can be stored */ #define MT_FLAGS_ALLOC_RANGE 0x01 #define MT_FLAGS_USE_RCU 0x02 #define MT_FLAGS_HEIGHT_OFFSET 0x02 #define MT_FLAGS_HEIGHT_MASK 0x7C #define MT_FLAGS_LOCK_MASK 0x300 #define MT_FLAGS_LOCK_IRQ 0x100 #define MT_FLAGS_LOCK_BH 0x200 #define MT_FLAGS_LOCK_EXTERN 0x300 #define MT_FLAGS_ALLOC_WRAPPED 0x0800 #define MAPLE_HEIGHT_MAX 31 #define MAPLE_NODE_TYPE_MASK 0x0F #define MAPLE_NODE_TYPE_SHIFT 0x03 #define MAPLE_RESERVED_RANGE 4096 #ifdef CONFIG_LOCKDEP typedef struct lockdep_map *lockdep_map_p; #define mt_lock_is_held(mt) \ (!(mt)->ma_external_lock || lock_is_held((mt)->ma_external_lock)) #define mt_write_lock_is_held(mt) \ (!(mt)->ma_external_lock || \ lock_is_held_type((mt)->ma_external_lock, 0)) #define mt_set_external_lock(mt, lock) \ (mt)->ma_external_lock = &(lock)->dep_map #define mt_on_stack(mt) (mt).ma_external_lock = NULL #else typedef struct { /* nothing */ } lockdep_map_p; #define mt_lock_is_held(mt) 1 #define mt_write_lock_is_held(mt) 1 #define mt_set_external_lock(mt, lock) do { } while (0) #define mt_on_stack(mt) do { } while (0) #endif /* * If the tree contains a single entry at index 0, it is usually stored in * tree->ma_root. To optimise for the page cache, an entry which ends in '00', * '01' or '11' is stored in the root, but an entry which ends in '10' will be * stored in a node. Bits 3-6 are used to store enum maple_type. * * The flags are used both to store some immutable information about this tree * (set at tree creation time) and dynamic information set under the spinlock. * * Another use of flags are to indicate global states of the tree. This is the * case with the MAPLE_USE_RCU flag, which indicates the tree is currently in * RCU mode. This mode was added to allow the tree to reuse nodes instead of * re-allocating and RCU freeing nodes when there is a single user. */ struct maple_tree { union { spinlock_t ma_lock; lockdep_map_p ma_external_lock; }; unsigned int ma_flags; void __rcu *ma_root; }; /** * MTREE_INIT() - Initialize a maple tree * @name: The maple tree name * @__flags: The maple tree flags * */ #define MTREE_INIT(name, __flags) { \ .ma_lock = __SPIN_LOCK_UNLOCKED((name).ma_lock), \ .ma_flags = __flags, \ .ma_root = NULL, \ } /** * MTREE_INIT_EXT() - Initialize a maple tree with an external lock. * @name: The tree name * @__flags: The maple tree flags * @__lock: The external lock */ #ifdef CONFIG_LOCKDEP #define MTREE_INIT_EXT(name, __flags, __lock) { \ .ma_external_lock = &(__lock).dep_map, \ .ma_flags = (__flags), \ .ma_root = NULL, \ } #else #define MTREE_INIT_EXT(name, __flags, __lock) MTREE_INIT(name, __flags) #endif #define DEFINE_MTREE(name) \ struct maple_tree name = MTREE_INIT(name, 0) #define mtree_lock(mt) spin_lock((&(mt)->ma_lock)) #define mtree_lock_nested(mas, subclass) \ spin_lock_nested((&(mt)->ma_lock), subclass) #define mtree_unlock(mt) spin_unlock((&(mt)->ma_lock)) /* * The Maple Tree squeezes various bits in at various points which aren't * necessarily obvious. Usually, this is done by observing that pointers are * N-byte aligned and thus the bottom log_2(N) bits are available for use. We * don't use the high bits of pointers to store additional information because * we don't know what bits are unused on any given architecture. * * Nodes are 256 bytes in size and are also aligned to 256 bytes, giving us 8 * low bits for our own purposes. Nodes are currently of 4 types: * 1. Single pointer (Range is 0-0) * 2. Non-leaf Allocation Range nodes * 3. Non-leaf Range nodes * 4. Leaf Range nodes All nodes consist of a number of node slots, * pivots, and a parent pointer. */ struct maple_node { union { struct { struct maple_pnode *parent; void __rcu *slot[MAPLE_NODE_SLOTS]; }; struct { void *pad; struct rcu_head rcu; struct maple_enode *piv_parent; unsigned char parent_slot; enum maple_type type; unsigned char slot_len; unsigned int ma_flags; }; struct maple_range_64 mr64; struct maple_arange_64 ma64; struct maple_alloc alloc; }; }; /* * More complicated stores can cause two nodes to become one or three and * potentially alter the height of the tree. Either half of the tree may need * to be rebalanced against the other. The ma_topiary struct is used to track * which nodes have been 'cut' from the tree so that the change can be done * safely at a later date. This is done to support RCU. */ struct ma_topiary { struct maple_enode *head; struct maple_enode *tail; struct maple_tree *mtree; }; void *mtree_load(struct maple_tree *mt, unsigned long index); int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp); int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp); int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); int mtree_store_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp); int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp); void *mtree_erase(struct maple_tree *mt, unsigned long index); int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp); int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp); void mtree_destroy(struct maple_tree *mt); void __mt_destroy(struct maple_tree *mt); /** * mtree_empty() - Determine if a tree has any present entries. * @mt: Maple Tree. * * Context: Any context. * Return: %true if the tree contains only NULL pointers. */ static inline bool mtree_empty(const struct maple_tree *mt) { return mt->ma_root == NULL; } /* Advanced API */ /* * Maple State Status * ma_active means the maple state is pointing to a node and offset and can * continue operating on the tree. * ma_start means we have not searched the tree. * ma_root means we have searched the tree and the entry we found lives in * the root of the tree (ie it has index 0, length 1 and is the only entry in * the tree). * ma_none means we have searched the tree and there is no node in the * tree for this entry. For example, we searched for index 1 in an empty * tree. Or we have a tree which points to a full leaf node and we * searched for an entry which is larger than can be contained in that * leaf node. * ma_pause means the data within the maple state may be stale, restart the * operation * ma_overflow means the search has reached the upper limit of the search * ma_underflow means the search has reached the lower limit of the search * ma_error means there was an error, check the node for the error number. */ enum maple_status { ma_active, ma_start, ma_root, ma_none, ma_pause, ma_overflow, ma_underflow, ma_error, }; /* * The maple state is defined in the struct ma_state and is used to keep track * of information during operations, and even between operations when using the * advanced API. * * If state->node has bit 0 set then it references a tree location which is not * a node (eg the root). If bit 1 is set, the rest of the bits are a negative * errno. Bit 2 (the 'unallocated slots' bit) is clear. Bits 3-6 indicate the * node type. * * state->alloc either has a request number of nodes or an allocated node. If * stat->alloc has a requested number of nodes, the first bit will be set (0x1) * and the remaining bits are the value. If state->alloc is a node, then the * node will be of type maple_alloc. maple_alloc has MAPLE_NODE_SLOTS - 1 for * storing more allocated nodes, a total number of nodes allocated, and the * node_count in this node. node_count is the number of allocated nodes in this * node. The scaling beyond MAPLE_NODE_SLOTS - 1 is handled by storing further * nodes into state->alloc->slot[0]'s node. Nodes are taken from state->alloc * by removing a node from the state->alloc node until state->alloc->node_count * is 1, when state->alloc is returned and the state->alloc->slot[0] is promoted * to state->alloc. Nodes are pushed onto state->alloc by putting the current * state->alloc into the pushed node's slot[0]. * * The state also contains the implied min/max of the state->node, the depth of * this search, and the offset. The implied min/max are either from the parent * node or are 0-oo for the root node. The depth is incremented or decremented * every time a node is walked down or up. The offset is the slot/pivot of * interest in the node - either for reading or writing. * * When returning a value the maple state index and last respectively contain * the start and end of the range for the entry. Ranges are inclusive in the * Maple Tree. * * The status of the state is used to determine how the next action should treat * the state. For instance, if the status is ma_start then the next action * should start at the root of the tree and walk down. If the status is * ma_pause then the node may be stale data and should be discarded. If the * status is ma_overflow, then the last action hit the upper limit. * */ struct ma_state { struct maple_tree *tree; /* The tree we're operating in */ unsigned long index; /* The index we're operating on - range start */ unsigned long last; /* The last index we're operating on - range end */ struct maple_enode *node; /* The node containing this entry */ unsigned long min; /* The minimum index of this node - implied pivot min */ unsigned long max; /* The maximum index of this node - implied pivot max */ struct maple_alloc *alloc; /* Allocated nodes for this operation */ enum maple_status status; /* The status of the state (active, start, none, etc) */ unsigned char depth; /* depth of tree descent during write */ unsigned char offset; unsigned char mas_flags; unsigned char end; /* The end of the node */ enum store_type store_type; /* The type of store needed for this operation */ }; struct ma_wr_state { struct ma_state *mas; struct maple_node *node; /* Decoded mas->node */ unsigned long r_min; /* range min */ unsigned long r_max; /* range max */ enum maple_type type; /* mas->node type */ unsigned char offset_end; /* The offset where the write ends */ unsigned long *pivots; /* mas->node->pivots pointer */ unsigned long end_piv; /* The pivot at the offset end */ void __rcu **slots; /* mas->node->slots pointer */ void *entry; /* The entry to write */ void *content; /* The existing entry that is being overwritten */ }; #define mas_lock(mas) spin_lock(&((mas)->tree->ma_lock)) #define mas_lock_nested(mas, subclass) \ spin_lock_nested(&((mas)->tree->ma_lock), subclass) #define mas_unlock(mas) spin_unlock(&((mas)->tree->ma_lock)) /* * Special values for ma_state.node. * MA_ERROR represents an errno. After dropping the lock and attempting * to resolve the error, the walk would have to be restarted from the * top of the tree as the tree may have been modified. */ #define MA_ERROR(err) \ ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) #define MA_STATE(name, mt, first, end) \ struct ma_state name = { \ .tree = mt, \ .index = first, \ .last = end, \ .node = NULL, \ .status = ma_start, \ .min = 0, \ .max = ULONG_MAX, \ .alloc = NULL, \ .mas_flags = 0, \ .store_type = wr_invalid, \ } #define MA_WR_STATE(name, ma_state, wr_entry) \ struct ma_wr_state name = { \ .mas = ma_state, \ .content = NULL, \ .entry = wr_entry, \ } #define MA_TOPIARY(name, tree) \ struct ma_topiary name = { \ .head = NULL, \ .tail = NULL, \ .mtree = tree, \ } void *mas_walk(struct ma_state *mas); void *mas_store(struct ma_state *mas, void *entry); void *mas_erase(struct ma_state *mas); int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp); void mas_store_prealloc(struct ma_state *mas, void *entry); void *mas_find(struct ma_state *mas, unsigned long max); void *mas_find_range(struct ma_state *mas, unsigned long max); void *mas_find_rev(struct ma_state *mas, unsigned long min); void *mas_find_range_rev(struct ma_state *mas, unsigned long max); int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp); bool mas_nomem(struct ma_state *mas, gfp_t gfp); void mas_pause(struct ma_state *mas); void maple_tree_init(void); void mas_destroy(struct ma_state *mas); int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries); void *mas_prev(struct ma_state *mas, unsigned long min); void *mas_prev_range(struct ma_state *mas, unsigned long max); void *mas_next(struct ma_state *mas, unsigned long max); void *mas_next_range(struct ma_state *mas, unsigned long max); int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size); /* * This finds an empty area from the highest address to the lowest. * AKA "Topdown" version, */ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size); static inline void mas_init(struct ma_state *mas, struct maple_tree *tree, unsigned long addr) { memset(mas, 0, sizeof(struct ma_state)); mas->tree = tree; mas->index = mas->last = addr; mas->max = ULONG_MAX; mas->status = ma_start; mas->node = NULL; } static inline bool mas_is_active(struct ma_state *mas) { return mas->status == ma_active; } static inline bool mas_is_err(struct ma_state *mas) { return mas->status == ma_error; } /** * mas_reset() - Reset a Maple Tree operation state. * @mas: Maple Tree operation state. * * Resets the error or walk state of the @mas so future walks of the * array will start from the root. Use this if you have dropped the * lock and want to reuse the ma_state. * * Context: Any context. */ static __always_inline void mas_reset(struct ma_state *mas) { mas->status = ma_start; mas->node = NULL; } /** * mas_for_each() - Iterate over a range of the maple tree. * @__mas: Maple Tree operation state (maple_state) * @__entry: Entry retrieved from the tree * @__max: maximum index to retrieve from the tree * * When returned, mas->index and mas->last will hold the entire range for the * entry. * * Note: may return the zero entry. */ #define mas_for_each(__mas, __entry, __max) \ while (((__entry) = mas_find((__mas), (__max))) != NULL) #ifdef CONFIG_DEBUG_MAPLE_TREE enum mt_dump_format { mt_dump_dec, mt_dump_hex, }; extern atomic_t maple_tree_tests_run; extern atomic_t maple_tree_tests_passed; void mt_dump(const struct maple_tree *mt, enum mt_dump_format format); void mas_dump(const struct ma_state *mas); void mas_wr_dump(const struct ma_wr_state *wr_mas); void mt_validate(struct maple_tree *mt); void mt_cache_shrink(void); #define MT_BUG_ON(__tree, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mt_dump(__tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MAS_BUG_ON(__mas, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_dump(__mas); \ mt_dump((__mas)->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MAS_WR_BUG_ON(__wrmas, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_wr_dump(__wrmas); \ mas_dump((__wrmas)->mas); \ mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MT_WARN_ON(__tree, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mt_dump(__tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #define MAS_WARN_ON(__mas, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_dump(__mas); \ mt_dump((__mas)->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #define MAS_WR_WARN_ON(__wrmas, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_wr_dump(__wrmas); \ mas_dump((__wrmas)->mas); \ mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #else #define MT_BUG_ON(__tree, __x) BUG_ON(__x) #define MAS_BUG_ON(__mas, __x) BUG_ON(__x) #define MAS_WR_BUG_ON(__mas, __x) BUG_ON(__x) #define MT_WARN_ON(__tree, __x) WARN_ON(__x) #define MAS_WARN_ON(__mas, __x) WARN_ON(__x) #define MAS_WR_WARN_ON(__mas, __x) WARN_ON(__x) #endif /* CONFIG_DEBUG_MAPLE_TREE */ /** * __mas_set_range() - Set up Maple Tree operation state to a sub-range of the * current location. * @mas: Maple Tree operation state. * @start: New start of range in the Maple Tree. * @last: New end of range in the Maple Tree. * * set the internal maple state values to a sub-range. * Please use mas_set_range() if you do not know where you are in the tree. */ static inline void __mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) { /* Ensure the range starts within the current slot */ MAS_WARN_ON(mas, mas_is_active(mas) && (mas->index > start || mas->last < start)); mas->index = start; mas->last = last; } /** * mas_set_range() - Set up Maple Tree operation state for a different index. * @mas: Maple Tree operation state. * @start: New start of range in the Maple Tree. * @last: New end of range in the Maple Tree. * * Move the operation state to refer to a different range. This will * have the effect of starting a walk from the top; see mas_next() * to move to an adjacent index. */ static inline void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) { mas_reset(mas); __mas_set_range(mas, start, last); } /** * mas_set() - Set up Maple Tree operation state for a different index. * @mas: Maple Tree operation state. * @index: New index into the Maple Tree. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see mas_next() * to move to an adjacent index. */ static inline void mas_set(struct ma_state *mas, unsigned long index) { mas_set_range(mas, index, index); } static inline bool mt_external_lock(const struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_LOCK_MASK) == MT_FLAGS_LOCK_EXTERN; } /** * mt_init_flags() - Initialise an empty maple tree with flags. * @mt: Maple Tree * @flags: maple tree flags. * * If you need to initialise a Maple Tree with special flags (eg, an * allocation tree), use this function. * * Context: Any context. */ static inline void mt_init_flags(struct maple_tree *mt, unsigned int flags) { mt->ma_flags = flags; if (!mt_external_lock(mt)) spin_lock_init(&mt->ma_lock); rcu_assign_pointer(mt->ma_root, NULL); } /** * mt_init() - Initialise an empty maple tree. * @mt: Maple Tree * * An empty Maple Tree. * * Context: Any context. */ static inline void mt_init(struct maple_tree *mt) { mt_init_flags(mt, 0); } static inline bool mt_in_rcu(struct maple_tree *mt) { #ifdef CONFIG_MAPLE_RCU_DISABLED return false; #endif return mt->ma_flags & MT_FLAGS_USE_RCU; } /** * mt_clear_in_rcu() - Switch the tree to non-RCU mode. * @mt: The Maple Tree */ static inline void mt_clear_in_rcu(struct maple_tree *mt) { if (!mt_in_rcu(mt)) return; if (mt_external_lock(mt)) { WARN_ON(!mt_lock_is_held(mt)); mt->ma_flags &= ~MT_FLAGS_USE_RCU; } else { mtree_lock(mt); mt->ma_flags &= ~MT_FLAGS_USE_RCU; mtree_unlock(mt); } } /** * mt_set_in_rcu() - Switch the tree to RCU safe mode. * @mt: The Maple Tree */ static inline void mt_set_in_rcu(struct maple_tree *mt) { if (mt_in_rcu(mt)) return; if (mt_external_lock(mt)) { WARN_ON(!mt_lock_is_held(mt)); mt->ma_flags |= MT_FLAGS_USE_RCU; } else { mtree_lock(mt); mt->ma_flags |= MT_FLAGS_USE_RCU; mtree_unlock(mt); } } static inline unsigned int mt_height(const struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET; } void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max); void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max); void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min); void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max); /** * mt_for_each - Iterate over each entry starting at index until max. * @__tree: The Maple Tree * @__entry: The current entry * @__index: The index to start the search from. Subsequently used as iterator. * @__max: The maximum limit for @index * * This iterator skips all entries, which resolve to a NULL pointer, * e.g. entries which has been reserved with XA_ZERO_ENTRY. */ #define mt_for_each(__tree, __entry, __index, __max) \ for (__entry = mt_find(__tree, &(__index), __max); \ __entry; __entry = mt_find_after(__tree, &(__index), __max)) #endif /*_LINUX_MAPLE_TREE_H */ |
| 2 2 2 2 2 21 2 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 | // SPDX-License-Identifier: GPL-2.0 #include <linux/debugfs.h> #include "netdevsim.h" #define NSIM_DEV_HWSTATS_TRAFFIC_MS 100 static struct list_head * nsim_dev_hwstats_get_list_head(struct nsim_dev_hwstats *hwstats, enum netdev_offload_xstats_type type) { switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return &hwstats->l3_list; } WARN_ON_ONCE(1); return NULL; } static void nsim_dev_hwstats_traffic_bump(struct nsim_dev_hwstats *hwstats, enum netdev_offload_xstats_type type) { struct nsim_dev_hwstats_netdev *hwsdev; struct list_head *hwsdev_list; hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type); if (WARN_ON(!hwsdev_list)) return; list_for_each_entry(hwsdev, hwsdev_list, list) { if (hwsdev->enabled) { hwsdev->stats.rx_packets += 1; hwsdev->stats.tx_packets += 2; hwsdev->stats.rx_bytes += 100; hwsdev->stats.tx_bytes += 300; } } } static void nsim_dev_hwstats_traffic_work(struct work_struct *work) { struct nsim_dev_hwstats *hwstats; hwstats = container_of(work, struct nsim_dev_hwstats, traffic_dw.work); mutex_lock(&hwstats->hwsdev_list_lock); nsim_dev_hwstats_traffic_bump(hwstats, NETDEV_OFFLOAD_XSTATS_TYPE_L3); mutex_unlock(&hwstats->hwsdev_list_lock); schedule_delayed_work(&hwstats->traffic_dw, msecs_to_jiffies(NSIM_DEV_HWSTATS_TRAFFIC_MS)); } static struct nsim_dev_hwstats_netdev * nsim_dev_hwslist_find_hwsdev(struct list_head *hwsdev_list, int ifindex) { struct nsim_dev_hwstats_netdev *hwsdev; list_for_each_entry(hwsdev, hwsdev_list, list) { if (hwsdev->netdev->ifindex == ifindex) return hwsdev; } return NULL; } static int nsim_dev_hwsdev_enable(struct nsim_dev_hwstats_netdev *hwsdev, struct netlink_ext_ack *extack) { if (hwsdev->fail_enable) { hwsdev->fail_enable = false; NL_SET_ERR_MSG_MOD(extack, "Stats enablement set to fail"); return -ECANCELED; } hwsdev->enabled = true; return 0; } static void nsim_dev_hwsdev_disable(struct nsim_dev_hwstats_netdev *hwsdev) { hwsdev->enabled = false; memset(&hwsdev->stats, 0, sizeof(hwsdev->stats)); } static int nsim_dev_hwsdev_report_delta(struct nsim_dev_hwstats_netdev *hwsdev, struct netdev_notifier_offload_xstats_info *info) { netdev_offload_xstats_report_delta(info->report_delta, &hwsdev->stats); memset(&hwsdev->stats, 0, sizeof(hwsdev->stats)); return 0; } static void nsim_dev_hwsdev_report_used(struct nsim_dev_hwstats_netdev *hwsdev, struct netdev_notifier_offload_xstats_info *info) { if (hwsdev->enabled) netdev_offload_xstats_report_used(info->report_used); } static int nsim_dev_hwstats_event_off_xstats(struct nsim_dev_hwstats *hwstats, struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_offload_xstats_info *info; struct nsim_dev_hwstats_netdev *hwsdev; struct list_head *hwsdev_list; int err = 0; info = ptr; hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, info->type); if (!hwsdev_list) return 0; mutex_lock(&hwstats->hwsdev_list_lock); hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, dev->ifindex); if (!hwsdev) goto out; switch (event) { case NETDEV_OFFLOAD_XSTATS_ENABLE: err = nsim_dev_hwsdev_enable(hwsdev, info->info.extack); break; case NETDEV_OFFLOAD_XSTATS_DISABLE: nsim_dev_hwsdev_disable(hwsdev); break; case NETDEV_OFFLOAD_XSTATS_REPORT_USED: nsim_dev_hwsdev_report_used(hwsdev, info); break; case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA: err = nsim_dev_hwsdev_report_delta(hwsdev, info); break; } out: mutex_unlock(&hwstats->hwsdev_list_lock); return err; } static void nsim_dev_hwsdev_fini(struct nsim_dev_hwstats_netdev *hwsdev) { dev_put(hwsdev->netdev); kfree(hwsdev); } static void __nsim_dev_hwstats_event_unregister(struct nsim_dev_hwstats *hwstats, struct net_device *dev, enum netdev_offload_xstats_type type) { struct nsim_dev_hwstats_netdev *hwsdev; struct list_head *hwsdev_list; hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type); if (WARN_ON(!hwsdev_list)) return; hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, dev->ifindex); if (!hwsdev) return; list_del(&hwsdev->list); nsim_dev_hwsdev_fini(hwsdev); } static void nsim_dev_hwstats_event_unregister(struct nsim_dev_hwstats *hwstats, struct net_device *dev) { mutex_lock(&hwstats->hwsdev_list_lock); __nsim_dev_hwstats_event_unregister(hwstats, dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3); mutex_unlock(&hwstats->hwsdev_list_lock); } static int nsim_dev_hwstats_event(struct nsim_dev_hwstats *hwstats, struct net_device *dev, unsigned long event, void *ptr) { switch (event) { case NETDEV_OFFLOAD_XSTATS_ENABLE: case NETDEV_OFFLOAD_XSTATS_DISABLE: case NETDEV_OFFLOAD_XSTATS_REPORT_USED: case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA: return nsim_dev_hwstats_event_off_xstats(hwstats, dev, event, ptr); case NETDEV_UNREGISTER: nsim_dev_hwstats_event_unregister(hwstats, dev); break; } return 0; } static int nsim_dev_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nsim_dev_hwstats *hwstats; int err = 0; hwstats = container_of(nb, struct nsim_dev_hwstats, netdevice_nb); err = nsim_dev_hwstats_event(hwstats, dev, event, ptr); if (err) return notifier_from_errno(err); return NOTIFY_OK; } static int nsim_dev_hwstats_enable_ifindex(struct nsim_dev_hwstats *hwstats, int ifindex, enum netdev_offload_xstats_type type, struct list_head *hwsdev_list) { struct nsim_dev_hwstats_netdev *hwsdev; struct nsim_dev *nsim_dev; struct net_device *netdev; bool notify = false; struct net *net; int err = 0; nsim_dev = container_of(hwstats, struct nsim_dev, hwstats); net = nsim_dev_net(nsim_dev); rtnl_lock(); mutex_lock(&hwstats->hwsdev_list_lock); hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex); if (hwsdev) goto out_unlock_list; netdev = dev_get_by_index(net, ifindex); if (!netdev) { err = -ENODEV; goto out_unlock_list; } hwsdev = kzalloc(sizeof(*hwsdev), GFP_KERNEL); if (!hwsdev) { err = -ENOMEM; goto out_put_netdev; } hwsdev->netdev = netdev; list_add_tail(&hwsdev->list, hwsdev_list); mutex_unlock(&hwstats->hwsdev_list_lock); if (netdev_offload_xstats_enabled(netdev, type)) { nsim_dev_hwsdev_enable(hwsdev, NULL); notify = true; } if (notify) rtnl_offload_xstats_notify(netdev); rtnl_unlock(); return err; out_put_netdev: dev_put(netdev); out_unlock_list: mutex_unlock(&hwstats->hwsdev_list_lock); rtnl_unlock(); return err; } static int nsim_dev_hwstats_disable_ifindex(struct nsim_dev_hwstats *hwstats, int ifindex, enum netdev_offload_xstats_type type, struct list_head *hwsdev_list) { struct nsim_dev_hwstats_netdev *hwsdev; int err = 0; rtnl_lock(); mutex_lock(&hwstats->hwsdev_list_lock); hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex); if (hwsdev) list_del(&hwsdev->list); mutex_unlock(&hwstats->hwsdev_list_lock); if (!hwsdev) { err = -ENOENT; goto unlock_out; } if (netdev_offload_xstats_enabled(hwsdev->netdev, type)) { netdev_offload_xstats_push_delta(hwsdev->netdev, type, &hwsdev->stats); rtnl_offload_xstats_notify(hwsdev->netdev); } nsim_dev_hwsdev_fini(hwsdev); unlock_out: rtnl_unlock(); return err; } static int nsim_dev_hwstats_fail_ifindex(struct nsim_dev_hwstats *hwstats, int ifindex, enum netdev_offload_xstats_type type, struct list_head *hwsdev_list) { struct nsim_dev_hwstats_netdev *hwsdev; int err = 0; mutex_lock(&hwstats->hwsdev_list_lock); hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex); if (!hwsdev) { err = -ENOENT; goto err_hwsdev_list_unlock; } hwsdev->fail_enable = true; err_hwsdev_list_unlock: mutex_unlock(&hwstats->hwsdev_list_lock); return err; } enum nsim_dev_hwstats_do { NSIM_DEV_HWSTATS_DO_DISABLE, NSIM_DEV_HWSTATS_DO_ENABLE, NSIM_DEV_HWSTATS_DO_FAIL, }; struct nsim_dev_hwstats_fops { const struct file_operations fops; enum nsim_dev_hwstats_do action; enum netdev_offload_xstats_type type; }; static ssize_t nsim_dev_hwstats_do_write(struct file *file, const char __user *data, size_t count, loff_t *ppos) { struct nsim_dev_hwstats *hwstats = file->private_data; struct nsim_dev_hwstats_fops *hwsfops; struct list_head *hwsdev_list; int ifindex; int err; hwsfops = container_of(debugfs_real_fops(file), struct nsim_dev_hwstats_fops, fops); err = kstrtoint_from_user(data, count, 0, &ifindex); if (err) return err; hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, hwsfops->type); if (WARN_ON(!hwsdev_list)) return -EINVAL; switch (hwsfops->action) { case NSIM_DEV_HWSTATS_DO_DISABLE: err = nsim_dev_hwstats_disable_ifindex(hwstats, ifindex, hwsfops->type, hwsdev_list); break; case NSIM_DEV_HWSTATS_DO_ENABLE: err = nsim_dev_hwstats_enable_ifindex(hwstats, ifindex, hwsfops->type, hwsdev_list); break; case NSIM_DEV_HWSTATS_DO_FAIL: err = nsim_dev_hwstats_fail_ifindex(hwstats, ifindex, hwsfops->type, hwsdev_list); break; } if (err) return err; return count; } #define NSIM_DEV_HWSTATS_FOPS(ACTION, TYPE) \ { \ .fops = { \ .open = simple_open, \ .write = nsim_dev_hwstats_do_write, \ .llseek = generic_file_llseek, \ .owner = THIS_MODULE, \ }, \ .action = ACTION, \ .type = TYPE, \ } static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_disable_fops = NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_DISABLE, NETDEV_OFFLOAD_XSTATS_TYPE_L3); static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_enable_fops = NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_ENABLE, NETDEV_OFFLOAD_XSTATS_TYPE_L3); static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_fail_fops = NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_FAIL, NETDEV_OFFLOAD_XSTATS_TYPE_L3); #undef NSIM_DEV_HWSTATS_FOPS int nsim_dev_hwstats_init(struct nsim_dev *nsim_dev) { struct nsim_dev_hwstats *hwstats = &nsim_dev->hwstats; struct net *net = nsim_dev_net(nsim_dev); int err; mutex_init(&hwstats->hwsdev_list_lock); INIT_LIST_HEAD(&hwstats->l3_list); hwstats->netdevice_nb.notifier_call = nsim_dev_netdevice_event; err = register_netdevice_notifier_net(net, &hwstats->netdevice_nb); if (err) goto err_mutex_destroy; hwstats->ddir = debugfs_create_dir("hwstats", nsim_dev->ddir); if (IS_ERR(hwstats->ddir)) { err = PTR_ERR(hwstats->ddir); goto err_unregister_notifier; } hwstats->l3_ddir = debugfs_create_dir("l3", hwstats->ddir); if (IS_ERR(hwstats->l3_ddir)) { err = PTR_ERR(hwstats->l3_ddir); goto err_remove_hwstats_recursive; } debugfs_create_file("enable_ifindex", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_enable_fops.fops); debugfs_create_file("disable_ifindex", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_disable_fops.fops); debugfs_create_file("fail_next_enable", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_fail_fops.fops); INIT_DELAYED_WORK(&hwstats->traffic_dw, &nsim_dev_hwstats_traffic_work); schedule_delayed_work(&hwstats->traffic_dw, msecs_to_jiffies(NSIM_DEV_HWSTATS_TRAFFIC_MS)); return 0; err_remove_hwstats_recursive: debugfs_remove_recursive(hwstats->ddir); err_unregister_notifier: unregister_netdevice_notifier_net(net, &hwstats->netdevice_nb); err_mutex_destroy: mutex_destroy(&hwstats->hwsdev_list_lock); return err; } static void nsim_dev_hwsdev_list_wipe(struct nsim_dev_hwstats *hwstats, enum netdev_offload_xstats_type type) { struct nsim_dev_hwstats_netdev *hwsdev, *tmp; struct list_head *hwsdev_list; hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type); if (WARN_ON(!hwsdev_list)) return; mutex_lock(&hwstats->hwsdev_list_lock); list_for_each_entry_safe(hwsdev, tmp, hwsdev_list, list) { list_del(&hwsdev->list); nsim_dev_hwsdev_fini(hwsdev); } mutex_unlock(&hwstats->hwsdev_list_lock); } void nsim_dev_hwstats_exit(struct nsim_dev *nsim_dev) { struct nsim_dev_hwstats *hwstats = &nsim_dev->hwstats; struct net *net = nsim_dev_net(nsim_dev); cancel_delayed_work_sync(&hwstats->traffic_dw); debugfs_remove_recursive(hwstats->ddir); unregister_netdevice_notifier_net(net, &hwstats->netdevice_nb); nsim_dev_hwsdev_list_wipe(hwstats, NETDEV_OFFLOAD_XSTATS_TYPE_L3); mutex_destroy(&hwstats->hwsdev_list_lock); } |
| 4 4 4 2 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 | /* * Copyright (c) 2007, 2020 Oracle and/or its affiliates. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/dma-mapping.h> /* for DMA_*_DEVICE */ #include "rds.h" /* * XXX * - build with sparse * - should we detect duplicate keys on a socket? hmm. * - an rdma is an mlock, apply rlimit? */ /* * get the number of pages by looking at the page indices that the start and * end addresses fall in. * * Returns 0 if the vec is invalid. It is invalid if the number of bytes * causes the address to wrap or overflows an unsigned int. This comes * from being stored in the 'length' member of 'struct scatterlist'. */ static unsigned int rds_pages_in_vec(struct rds_iovec *vec) { if ((vec->addr + vec->bytes <= vec->addr) || (vec->bytes > (u64)UINT_MAX)) return 0; return ((vec->addr + vec->bytes + PAGE_SIZE - 1) >> PAGE_SHIFT) - (vec->addr >> PAGE_SHIFT); } static struct rds_mr *rds_mr_tree_walk(struct rb_root *root, u64 key, struct rds_mr *insert) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct rds_mr *mr; while (*p) { parent = *p; mr = rb_entry(parent, struct rds_mr, r_rb_node); if (key < mr->r_key) p = &(*p)->rb_left; else if (key > mr->r_key) p = &(*p)->rb_right; else return mr; } if (insert) { rb_link_node(&insert->r_rb_node, parent, p); rb_insert_color(&insert->r_rb_node, root); kref_get(&insert->r_kref); } return NULL; } /* * Destroy the transport-specific part of a MR. */ static void rds_destroy_mr(struct rds_mr *mr) { struct rds_sock *rs = mr->r_sock; void *trans_private = NULL; unsigned long flags; rdsdebug("RDS: destroy mr key is %x refcnt %u\n", mr->r_key, kref_read(&mr->r_kref)); spin_lock_irqsave(&rs->rs_rdma_lock, flags); if (!RB_EMPTY_NODE(&mr->r_rb_node)) rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); trans_private = mr->r_trans_private; mr->r_trans_private = NULL; spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (trans_private) mr->r_trans->free_mr(trans_private, mr->r_invalidate); } void __rds_put_mr_final(struct kref *kref) { struct rds_mr *mr = container_of(kref, struct rds_mr, r_kref); rds_destroy_mr(mr); kfree(mr); } /* * By the time this is called we can't have any more ioctls called on * the socket so we don't need to worry about racing with others. */ void rds_rdma_drop_keys(struct rds_sock *rs) { struct rds_mr *mr; struct rb_node *node; unsigned long flags; /* Release any MRs associated with this socket */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); while ((node = rb_first(&rs->rs_rdma_keys))) { mr = rb_entry(node, struct rds_mr, r_rb_node); if (mr->r_trans == rs->rs_transport) mr->r_invalidate = 0; rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); kref_put(&mr->r_kref, __rds_put_mr_final); spin_lock_irqsave(&rs->rs_rdma_lock, flags); } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (rs->rs_transport && rs->rs_transport->flush_mrs) rs->rs_transport->flush_mrs(); } /* * Helper function to pin user pages. */ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, struct page **pages, int write) { unsigned int gup_flags = FOLL_LONGTERM; int ret; if (write) gup_flags |= FOLL_WRITE; ret = pin_user_pages_fast(user_addr, nr_pages, gup_flags, pages); if (ret >= 0 && ret < nr_pages) { unpin_user_pages(pages, ret); ret = -EFAULT; } return ret; } static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, u64 *cookie_ret, struct rds_mr **mr_ret, struct rds_conn_path *cp) { struct rds_mr *mr = NULL, *found; struct scatterlist *sg = NULL; unsigned int nr_pages; struct page **pages = NULL; void *trans_private; unsigned long flags; rds_rdma_cookie_t cookie; unsigned int nents = 0; int need_odp = 0; long i; int ret; if (ipv6_addr_any(&rs->rs_bound_addr) || !rs->rs_transport) { ret = -ENOTCONN; /* XXX not a great errno */ goto out; } if (!rs->rs_transport->get_mr) { ret = -EOPNOTSUPP; goto out; } /* If the combination of the addr and size requested for this memory * region causes an integer overflow, return error. */ if (((args->vec.addr + args->vec.bytes) < args->vec.addr) || PAGE_ALIGN(args->vec.addr + args->vec.bytes) < (args->vec.addr + args->vec.bytes)) { ret = -EINVAL; goto out; } if (!can_do_mlock()) { ret = -EPERM; goto out; } nr_pages = rds_pages_in_vec(&args->vec); if (nr_pages == 0) { ret = -EINVAL; goto out; } /* Restrict the size of mr irrespective of underlying transport * To account for unaligned mr regions, subtract one from nr_pages */ if ((nr_pages - 1) > (RDS_MAX_MSG_SIZE >> PAGE_SHIFT)) { ret = -EMSGSIZE; goto out; } rdsdebug("RDS: get_mr addr %llx len %llu nr_pages %u\n", args->vec.addr, args->vec.bytes, nr_pages); /* XXX clamp nr_pages to limit the size of this alloc? */ pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; goto out; } mr = kzalloc(sizeof(struct rds_mr), GFP_KERNEL); if (!mr) { ret = -ENOMEM; goto out; } kref_init(&mr->r_kref); RB_CLEAR_NODE(&mr->r_rb_node); mr->r_trans = rs->rs_transport; mr->r_sock = rs; if (args->flags & RDS_RDMA_USE_ONCE) mr->r_use_once = 1; if (args->flags & RDS_RDMA_INVALIDATE) mr->r_invalidate = 1; if (args->flags & RDS_RDMA_READWRITE) mr->r_write = 1; /* * Pin the pages that make up the user buffer and transfer the page * pointers to the mr's sg array. We check to see if we've mapped * the whole region after transferring the partial page references * to the sg array so that we can have one page ref cleanup path. * * For now we have no flag that tells us whether the mapping is * r/o or r/w. We need to assume r/w, or we'll do a lot of RDMA to * the zero page. */ ret = rds_pin_pages(args->vec.addr, nr_pages, pages, 1); if (ret == -EOPNOTSUPP) { need_odp = 1; } else if (ret <= 0) { goto out; } else { nents = ret; sg = kmalloc_array(nents, sizeof(*sg), GFP_KERNEL); if (!sg) { ret = -ENOMEM; goto out; } WARN_ON(!nents); sg_init_table(sg, nents); /* Stick all pages into the scatterlist */ for (i = 0 ; i < nents; i++) sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0); rdsdebug("RDS: trans_private nents is %u\n", nents); } /* Obtain a transport specific MR. If this succeeds, the * s/g list is now owned by the MR. * Note that dma_map() implies that pending writes are * flushed to RAM, so no dma_sync is needed here. */ trans_private = rs->rs_transport->get_mr( sg, nents, rs, &mr->r_key, cp ? cp->cp_conn : NULL, args->vec.addr, args->vec.bytes, need_odp ? ODP_ZEROBASED : ODP_NOT_NEEDED); if (IS_ERR(trans_private)) { /* In ODP case, we don't GUP pages, so don't need * to release anything. */ if (!need_odp) { unpin_user_pages(pages, nr_pages); kfree(sg); } ret = PTR_ERR(trans_private); /* Trigger connection so that its ready for the next retry */ if (ret == -ENODEV && cp) rds_conn_connect_if_down(cp->cp_conn); goto out; } mr->r_trans_private = trans_private; rdsdebug("RDS: get_mr put_user key is %x cookie_addr %p\n", mr->r_key, (void *)(unsigned long) args->cookie_addr); /* The user may pass us an unaligned address, but we can only * map page aligned regions. So we keep the offset, and build * a 64bit cookie containing <R_Key, offset> and pass that * around. */ if (need_odp) cookie = rds_rdma_make_cookie(mr->r_key, 0); else cookie = rds_rdma_make_cookie(mr->r_key, args->vec.addr & ~PAGE_MASK); if (cookie_ret) *cookie_ret = cookie; if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long)args->cookie_addr)) { if (!need_odp) { unpin_user_pages(pages, nr_pages); kfree(sg); } ret = -EFAULT; goto out; } /* Inserting the new MR into the rbtree bumps its * reference count. */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); found = rds_mr_tree_walk(&rs->rs_rdma_keys, mr->r_key, mr); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); BUG_ON(found && found != mr); rdsdebug("RDS: get_mr key is %x\n", mr->r_key); if (mr_ret) { kref_get(&mr->r_kref); *mr_ret = mr; } ret = 0; out: kfree(pages); if (mr) kref_put(&mr->r_kref, __rds_put_mr_final); return ret; } int rds_get_mr(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_get_mr_args args; if (optlen != sizeof(struct rds_get_mr_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_get_mr_args))) return -EFAULT; return __rds_rdma_map(rs, &args, NULL, NULL, NULL); } int rds_get_mr_for_dest(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_get_mr_for_dest_args args; struct rds_get_mr_args new_args; if (optlen != sizeof(struct rds_get_mr_for_dest_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_get_mr_for_dest_args))) return -EFAULT; /* * Initially, just behave like get_mr(). * TODO: Implement get_mr as wrapper around this * and deprecate it. */ new_args.vec = args.vec; new_args.cookie_addr = args.cookie_addr; new_args.flags = args.flags; return __rds_rdma_map(rs, &new_args, NULL, NULL, NULL); } /* * Free the MR indicated by the given R_Key */ int rds_free_mr(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_free_mr_args args; struct rds_mr *mr; unsigned long flags; if (optlen != sizeof(struct rds_free_mr_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_free_mr_args))) return -EFAULT; /* Special case - a null cookie means flush all unused MRs */ if (args.cookie == 0) { if (!rs->rs_transport || !rs->rs_transport->flush_mrs) return -EINVAL; rs->rs_transport->flush_mrs(); return 0; } /* Look up the MR given its R_key and remove it from the rbtree * so nobody else finds it. * This should also prevent races with rds_rdma_unuse. */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, rds_rdma_cookie_key(args.cookie), NULL); if (mr) { rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); if (args.flags & RDS_RDMA_INVALIDATE) mr->r_invalidate = 1; } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (!mr) return -EINVAL; kref_put(&mr->r_kref, __rds_put_mr_final); return 0; } /* * This is called when we receive an extension header that * tells us this MR was used. It allows us to implement * use_once semantics */ void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force) { struct rds_mr *mr; unsigned long flags; int zot_me = 0; spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, r_key, NULL); if (!mr) { pr_debug("rds: trying to unuse MR with unknown r_key %u!\n", r_key); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); return; } /* Get a reference so that the MR won't go away before calling * sync_mr() below. */ kref_get(&mr->r_kref); /* If it is going to be freed, remove it from the tree now so * that no other thread can find it and free it. */ if (mr->r_use_once || force) { rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); zot_me = 1; } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); /* May have to issue a dma_sync on this memory region. * Note we could avoid this if the operation was a RDMA READ, * but at this point we can't tell. */ if (mr->r_trans->sync_mr) mr->r_trans->sync_mr(mr->r_trans_private, DMA_FROM_DEVICE); /* Release the reference held above. */ kref_put(&mr->r_kref, __rds_put_mr_final); /* If the MR was marked as invalidate, this will * trigger an async flush. */ if (zot_me) kref_put(&mr->r_kref, __rds_put_mr_final); } void rds_rdma_free_op(struct rm_rdma_op *ro) { unsigned int i; if (ro->op_odp_mr) { kref_put(&ro->op_odp_mr->r_kref, __rds_put_mr_final); } else { for (i = 0; i < ro->op_nents; i++) { struct page *page = sg_page(&ro->op_sg[i]); /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ unpin_user_pages_dirty_lock(&page, 1, !ro->op_write); } } kfree(ro->op_notifier); ro->op_notifier = NULL; ro->op_active = 0; ro->op_odp_mr = NULL; } void rds_atomic_free_op(struct rm_atomic_op *ao) { struct page *page = sg_page(ao->op_sg); /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ unpin_user_pages_dirty_lock(&page, 1, true); kfree(ao->op_notifier); ao->op_notifier = NULL; ao->op_active = 0; } /* * Count the number of pages needed to describe an incoming iovec array. */ static int rds_rdma_pages(struct rds_iovec iov[], int nr_iovecs) { int tot_pages = 0; unsigned int nr_pages; unsigned int i; /* figure out the number of pages in the vector */ for (i = 0; i < nr_iovecs; i++) { nr_pages = rds_pages_in_vec(&iov[i]); if (nr_pages == 0) return -EINVAL; tot_pages += nr_pages; /* * nr_pages for one entry is limited to (UINT_MAX>>PAGE_SHIFT)+1, * so tot_pages cannot overflow without first going negative. */ if (tot_pages < 0) return -EINVAL; } return tot_pages; } int rds_rdma_extra_size(struct rds_rdma_args *args, struct rds_iov_vector *iov) { struct rds_iovec *vec; struct rds_iovec __user *local_vec; int tot_pages = 0; unsigned int nr_pages; unsigned int i; local_vec = (struct rds_iovec __user *)(unsigned long) args->local_vec_addr; if (args->nr_local == 0) return -EINVAL; if (args->nr_local > UIO_MAXIOV) return -EMSGSIZE; iov->iov = kcalloc(args->nr_local, sizeof(struct rds_iovec), GFP_KERNEL); if (!iov->iov) return -ENOMEM; vec = &iov->iov[0]; if (copy_from_user(vec, local_vec, args->nr_local * sizeof(struct rds_iovec))) return -EFAULT; iov->len = args->nr_local; /* figure out the number of pages in the vector */ for (i = 0; i < args->nr_local; i++, vec++) { nr_pages = rds_pages_in_vec(vec); if (nr_pages == 0) return -EINVAL; tot_pages += nr_pages; /* * nr_pages for one entry is limited to (UINT_MAX>>PAGE_SHIFT)+1, * so tot_pages cannot overflow without first going negative. */ if (tot_pages < 0) return -EINVAL; } return tot_pages * sizeof(struct scatterlist); } /* * The application asks for a RDMA transfer. * Extract all arguments and set up the rdma_op */ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg, struct rds_iov_vector *vec) { struct rds_rdma_args *args; struct rm_rdma_op *op = &rm->rdma; int nr_pages; unsigned int nr_bytes; struct page **pages = NULL; struct rds_iovec *iovs; unsigned int i, j; int ret = 0; bool odp_supported = true; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args)) || rm->rdma.op_active) return -EINVAL; args = CMSG_DATA(cmsg); if (ipv6_addr_any(&rs->rs_bound_addr)) { ret = -ENOTCONN; /* XXX not a great errno */ goto out_ret; } if (args->nr_local > UIO_MAXIOV) { ret = -EMSGSIZE; goto out_ret; } if (vec->len != args->nr_local) { ret = -EINVAL; goto out_ret; } /* odp-mr is not supported for multiple requests within one message */ if (args->nr_local != 1) odp_supported = false; iovs = vec->iov; nr_pages = rds_rdma_pages(iovs, args->nr_local); if (nr_pages < 0) { ret = -EINVAL; goto out_ret; } pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; goto out_ret; } op->op_write = !!(args->flags & RDS_RDMA_READWRITE); op->op_fence = !!(args->flags & RDS_RDMA_FENCE); op->op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME); op->op_silent = !!(args->flags & RDS_RDMA_SILENT); op->op_active = 1; op->op_recverr = rs->rs_recverr; op->op_odp_mr = NULL; WARN_ON(!nr_pages); op->op_sg = rds_message_alloc_sgs(rm, nr_pages); if (IS_ERR(op->op_sg)) { ret = PTR_ERR(op->op_sg); goto out_pages; } if (op->op_notify || op->op_recverr) { /* We allocate an uninitialized notifier here, because * we don't want to do that in the completion handler. We * would have to use GFP_ATOMIC there, and don't want to deal * with failed allocations. */ op->op_notifier = kmalloc(sizeof(struct rds_notifier), GFP_KERNEL); if (!op->op_notifier) { ret = -ENOMEM; goto out_pages; } op->op_notifier->n_user_token = args->user_token; op->op_notifier->n_status = RDS_RDMA_SUCCESS; } /* The cookie contains the R_Key of the remote memory region, and * optionally an offset into it. This is how we implement RDMA into * unaligned memory. * When setting up the RDMA, we need to add that offset to the * destination address (which is really an offset into the MR) * FIXME: We may want to move this into ib_rdma.c */ op->op_rkey = rds_rdma_cookie_key(args->cookie); op->op_remote_addr = args->remote_vec.addr + rds_rdma_cookie_offset(args->cookie); nr_bytes = 0; rdsdebug("RDS: rdma prepare nr_local %llu rva %llx rkey %x\n", (unsigned long long)args->nr_local, (unsigned long long)args->remote_vec.addr, op->op_rkey); for (i = 0; i < args->nr_local; i++) { struct rds_iovec *iov = &iovs[i]; /* don't need to check, rds_rdma_pages() verified nr will be +nonzero */ unsigned int nr = rds_pages_in_vec(iov); rs->rs_user_addr = iov->addr; rs->rs_user_bytes = iov->bytes; /* If it's a WRITE operation, we want to pin the pages for reading. * If it's a READ operation, we need to pin the pages for writing. */ ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); if ((!odp_supported && ret <= 0) || (odp_supported && ret <= 0 && ret != -EOPNOTSUPP)) goto out_pages; if (ret == -EOPNOTSUPP) { struct rds_mr *local_odp_mr; if (!rs->rs_transport->get_mr) { ret = -EOPNOTSUPP; goto out_pages; } local_odp_mr = kzalloc(sizeof(*local_odp_mr), GFP_KERNEL); if (!local_odp_mr) { ret = -ENOMEM; goto out_pages; } RB_CLEAR_NODE(&local_odp_mr->r_rb_node); kref_init(&local_odp_mr->r_kref); local_odp_mr->r_trans = rs->rs_transport; local_odp_mr->r_sock = rs; local_odp_mr->r_trans_private = rs->rs_transport->get_mr( NULL, 0, rs, &local_odp_mr->r_key, NULL, iov->addr, iov->bytes, ODP_VIRTUAL); if (IS_ERR(local_odp_mr->r_trans_private)) { ret = PTR_ERR(local_odp_mr->r_trans_private); rdsdebug("get_mr ret %d %p\"", ret, local_odp_mr->r_trans_private); kfree(local_odp_mr); ret = -EOPNOTSUPP; goto out_pages; } rdsdebug("Need odp; local_odp_mr %p trans_private %p\n", local_odp_mr, local_odp_mr->r_trans_private); op->op_odp_mr = local_odp_mr; op->op_odp_addr = iov->addr; } rdsdebug("RDS: nr_bytes %u nr %u iov->bytes %llu iov->addr %llx\n", nr_bytes, nr, iov->bytes, iov->addr); nr_bytes += iov->bytes; for (j = 0; j < nr; j++) { unsigned int offset = iov->addr & ~PAGE_MASK; struct scatterlist *sg; sg = &op->op_sg[op->op_nents + j]; sg_set_page(sg, pages[j], min_t(unsigned int, iov->bytes, PAGE_SIZE - offset), offset); sg_dma_len(sg) = sg->length; rdsdebug("RDS: sg->offset %x sg->len %x iov->addr %llx iov->bytes %llu\n", sg->offset, sg->length, iov->addr, iov->bytes); iov->addr += sg->length; iov->bytes -= sg->length; } op->op_nents += nr; } if (nr_bytes > args->remote_vec.bytes) { rdsdebug("RDS nr_bytes %u remote_bytes %u do not match\n", nr_bytes, (unsigned int) args->remote_vec.bytes); ret = -EINVAL; goto out_pages; } op->op_bytes = nr_bytes; ret = 0; out_pages: kfree(pages); out_ret: if (ret) rds_rdma_free_op(op); else rds_stats_inc(s_send_rdma); return ret; } /* * The application wants us to pass an RDMA destination (aka MR) * to the remote */ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { unsigned long flags; struct rds_mr *mr; u32 r_key; int err = 0; if (cmsg->cmsg_len < CMSG_LEN(sizeof(rds_rdma_cookie_t)) || rm->m_rdma_cookie != 0) return -EINVAL; memcpy(&rm->m_rdma_cookie, CMSG_DATA(cmsg), sizeof(rm->m_rdma_cookie)); /* We are reusing a previously mapped MR here. Most likely, the * application has written to the buffer, so we need to explicitly * flush those writes to RAM. Otherwise the HCA may not see them * when doing a DMA from that buffer. */ r_key = rds_rdma_cookie_key(rm->m_rdma_cookie); spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, r_key, NULL); if (!mr) err = -EINVAL; /* invalid r_key */ else kref_get(&mr->r_kref); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (mr) { mr->r_trans->sync_mr(mr->r_trans_private, DMA_TO_DEVICE); rm->rdma.op_rdma_mr = mr; } return err; } /* * The application passes us an address range it wants to enable RDMA * to/from. We map the area, and save the <R_Key,offset> pair * in rm->m_rdma_cookie. This causes it to be sent along to the peer * in an extension header. */ int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_get_mr_args)) || rm->m_rdma_cookie != 0) return -EINVAL; return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->rdma.op_rdma_mr, rm->m_conn_path); } /* * Fill in rds_message for an atomic request. */ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { struct page *page = NULL; struct rds_atomic_args *args; int ret = 0; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_atomic_args)) || rm->atomic.op_active) return -EINVAL; args = CMSG_DATA(cmsg); /* Nonmasked & masked cmsg ops converted to masked hw ops */ switch (cmsg->cmsg_type) { case RDS_CMSG_ATOMIC_FADD: rm->atomic.op_type = RDS_ATOMIC_TYPE_FADD; rm->atomic.op_m_fadd.add = args->fadd.add; rm->atomic.op_m_fadd.nocarry_mask = 0; break; case RDS_CMSG_MASKED_ATOMIC_FADD: rm->atomic.op_type = RDS_ATOMIC_TYPE_FADD; rm->atomic.op_m_fadd.add = args->m_fadd.add; rm->atomic.op_m_fadd.nocarry_mask = args->m_fadd.nocarry_mask; break; case RDS_CMSG_ATOMIC_CSWP: rm->atomic.op_type = RDS_ATOMIC_TYPE_CSWP; rm->atomic.op_m_cswp.compare = args->cswp.compare; rm->atomic.op_m_cswp.swap = args->cswp.swap; rm->atomic.op_m_cswp.compare_mask = ~0; rm->atomic.op_m_cswp.swap_mask = ~0; break; case RDS_CMSG_MASKED_ATOMIC_CSWP: rm->atomic.op_type = RDS_ATOMIC_TYPE_CSWP; rm->atomic.op_m_cswp.compare = args->m_cswp.compare; rm->atomic.op_m_cswp.swap = args->m_cswp.swap; rm->atomic.op_m_cswp.compare_mask = args->m_cswp.compare_mask; rm->atomic.op_m_cswp.swap_mask = args->m_cswp.swap_mask; break; default: BUG(); /* should never happen */ } rm->atomic.op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME); rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT); rm->atomic.op_active = 1; rm->atomic.op_recverr = rs->rs_recverr; rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1); if (IS_ERR(rm->atomic.op_sg)) { ret = PTR_ERR(rm->atomic.op_sg); goto err; } /* verify 8 byte-aligned */ if (args->local_addr & 0x7) { ret = -EFAULT; goto err; } ret = rds_pin_pages(args->local_addr, 1, &page, 1); if (ret != 1) goto err; ret = 0; sg_set_page(rm->atomic.op_sg, page, 8, offset_in_page(args->local_addr)); if (rm->atomic.op_notify || rm->atomic.op_recverr) { /* We allocate an uninitialized notifier here, because * we don't want to do that in the completion handler. We * would have to use GFP_ATOMIC there, and don't want to deal * with failed allocations. */ rm->atomic.op_notifier = kmalloc(sizeof(*rm->atomic.op_notifier), GFP_KERNEL); if (!rm->atomic.op_notifier) { ret = -ENOMEM; goto err; } rm->atomic.op_notifier->n_user_token = args->user_token; rm->atomic.op_notifier->n_status = RDS_RDMA_SUCCESS; } rm->atomic.op_rkey = rds_rdma_cookie_key(args->cookie); rm->atomic.op_remote_addr = args->remote_addr + rds_rdma_cookie_offset(args->cookie); return ret; err: if (page) unpin_user_page(page); rm->atomic.op_active = 0; kfree(rm->atomic.op_notifier); return ret; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* include/net/dsfield.h - Manipulation of the Differentiated Services field */ /* Written 1998-2000 by Werner Almesberger, EPFL ICA */ #ifndef __NET_DSFIELD_H #define __NET_DSFIELD_H #include <linux/types.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <asm/byteorder.h> static inline __u8 ipv4_get_dsfield(const struct iphdr *iph) { return iph->tos; } static inline __u8 ipv6_get_dsfield(const struct ipv6hdr *ipv6h) { return ntohs(*(__force const __be16 *)ipv6h) >> 4; } static inline void ipv4_change_dsfield(struct iphdr *iph,__u8 mask, __u8 value) { __u32 check = ntohs((__force __be16)iph->check); __u8 dsfield; dsfield = (iph->tos & mask) | value; check += iph->tos; if ((check+1) >> 16) check = (check+1) & 0xffff; check -= dsfield; check += check >> 16; /* adjust carry */ iph->check = (__force __sum16)htons(check); iph->tos = dsfield; } static inline void ipv6_change_dsfield(struct ipv6hdr *ipv6h,__u8 mask, __u8 value) { __be16 *p = (__force __be16 *)ipv6h; *p = (*p & htons((((u16)mask << 4) | 0xf00f))) | htons((u16)value << 4); } #endif |
| 4 1 4 1 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_UIDGID_H #define _LINUX_UIDGID_H /* * A set of types for the internal kernel types representing uids and gids. * * The types defined in this header allow distinguishing which uids and gids in * the kernel are values used by userspace and which uid and gid values are * the internal kernel values. With the addition of user namespaces the values * can be different. Using the type system makes it possible for the compiler * to detect when we overlook these differences. * */ #include <linux/uidgid_types.h> #include <linux/highuid.h> struct user_namespace; extern struct user_namespace init_user_ns; struct uid_gid_map; #define KUIDT_INIT(value) (kuid_t){ value } #define KGIDT_INIT(value) (kgid_t){ value } #ifdef CONFIG_MULTIUSER static inline uid_t __kuid_val(kuid_t uid) { return uid.val; } static inline gid_t __kgid_val(kgid_t gid) { return gid.val; } #else static inline uid_t __kuid_val(kuid_t uid) { return 0; } static inline gid_t __kgid_val(kgid_t gid) { return 0; } #endif #define GLOBAL_ROOT_UID KUIDT_INIT(0) #define GLOBAL_ROOT_GID KGIDT_INIT(0) #define INVALID_UID KUIDT_INIT(-1) #define INVALID_GID KGIDT_INIT(-1) static inline bool uid_eq(kuid_t left, kuid_t right) { return __kuid_val(left) == __kuid_val(right); } static inline bool gid_eq(kgid_t left, kgid_t right) { return __kgid_val(left) == __kgid_val(right); } static inline bool uid_gt(kuid_t left, kuid_t right) { return __kuid_val(left) > __kuid_val(right); } static inline bool gid_gt(kgid_t left, kgid_t right) { return __kgid_val(left) > __kgid_val(right); } static inline bool uid_gte(kuid_t left, kuid_t right) { return __kuid_val(left) >= __kuid_val(right); } static inline bool gid_gte(kgid_t left, kgid_t right) { return __kgid_val(left) >= __kgid_val(right); } static inline bool uid_lt(kuid_t left, kuid_t right) { return __kuid_val(left) < __kuid_val(right); } static inline bool gid_lt(kgid_t left, kgid_t right) { return __kgid_val(left) < __kgid_val(right); } static inline bool uid_lte(kuid_t left, kuid_t right) { return __kuid_val(left) <= __kuid_val(right); } static inline bool gid_lte(kgid_t left, kgid_t right) { return __kgid_val(left) <= __kgid_val(right); } static inline bool uid_valid(kuid_t uid) { return __kuid_val(uid) != (uid_t) -1; } static inline bool gid_valid(kgid_t gid) { return __kgid_val(gid) != (gid_t) -1; } #ifdef CONFIG_USER_NS extern kuid_t make_kuid(struct user_namespace *from, uid_t uid); extern kgid_t make_kgid(struct user_namespace *from, gid_t gid); extern uid_t from_kuid(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid(struct user_namespace *to, kgid_t gid); extern uid_t from_kuid_munged(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid_munged(struct user_namespace *to, kgid_t gid); static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return from_kuid(ns, uid) != (uid_t) -1; } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return from_kgid(ns, gid) != (gid_t) -1; } u32 map_id_down(struct uid_gid_map *map, u32 id); u32 map_id_up(struct uid_gid_map *map, u32 id); #else static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid) { return KUIDT_INIT(uid); } static inline kgid_t make_kgid(struct user_namespace *from, gid_t gid) { return KGIDT_INIT(gid); } static inline uid_t from_kuid(struct user_namespace *to, kuid_t kuid) { return __kuid_val(kuid); } static inline gid_t from_kgid(struct user_namespace *to, kgid_t kgid) { return __kgid_val(kgid); } static inline uid_t from_kuid_munged(struct user_namespace *to, kuid_t kuid) { uid_t uid = from_kuid(to, kuid); if (uid == (uid_t)-1) uid = overflowuid; return uid; } static inline gid_t from_kgid_munged(struct user_namespace *to, kgid_t kgid) { gid_t gid = from_kgid(to, kgid); if (gid == (gid_t)-1) gid = overflowgid; return gid; } static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return uid_valid(uid); } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return gid_valid(gid); } static inline u32 map_id_down(struct uid_gid_map *map, u32 id) { return id; } static inline u32 map_id_up(struct uid_gid_map *map, u32 id) { return id; } #endif /* CONFIG_USER_NS */ #endif /* _LINUX_UIDGID_H */ |
| 216 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/dsa.h - Driver for Distributed Switch Architecture switch chips * Copyright (c) 2008-2009 Marvell Semiconductor */ #ifndef __LINUX_NET_DSA_H #define __LINUX_NET_DSA_H #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/platform_data/dsa.h> #include <linux/phylink.h> #include <net/devlink.h> #include <net/switchdev.h> struct dsa_8021q_context; struct tc_action; #define DSA_TAG_PROTO_NONE_VALUE 0 #define DSA_TAG_PROTO_BRCM_VALUE 1 #define DSA_TAG_PROTO_BRCM_PREPEND_VALUE 2 #define DSA_TAG_PROTO_DSA_VALUE 3 #define DSA_TAG_PROTO_EDSA_VALUE 4 #define DSA_TAG_PROTO_GSWIP_VALUE 5 #define DSA_TAG_PROTO_KSZ9477_VALUE 6 #define DSA_TAG_PROTO_KSZ9893_VALUE 7 #define DSA_TAG_PROTO_LAN9303_VALUE 8 #define DSA_TAG_PROTO_MTK_VALUE 9 #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 #define DSA_TAG_PROTO_8021Q_VALUE 12 #define DSA_TAG_PROTO_SJA1105_VALUE 13 #define DSA_TAG_PROTO_KSZ8795_VALUE 14 #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 #define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 #define DSA_TAG_PROTO_LAN937X_VALUE 27 #define DSA_TAG_PROTO_VSC73XX_8021Q_VALUE 28 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE, DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE, DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE, DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE, DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE, DSA_TAG_PROTO_GSWIP = DSA_TAG_PROTO_GSWIP_VALUE, DSA_TAG_PROTO_KSZ9477 = DSA_TAG_PROTO_KSZ9477_VALUE, DSA_TAG_PROTO_KSZ9893 = DSA_TAG_PROTO_KSZ9893_VALUE, DSA_TAG_PROTO_LAN9303 = DSA_TAG_PROTO_LAN9303_VALUE, DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, DSA_TAG_PROTO_VSC73XX_8021Q = DSA_TAG_PROTO_VSC73XX_8021Q_VALUE, }; struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); int (*connect)(struct dsa_switch *ds); void (*disconnect)(struct dsa_switch *ds); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC * address, in which case the DSA conduit would drop packets on ingress * if what it understands out of the destination MAC address is not in * its RX filter. */ bool promisc_on_conduit; }; struct dsa_lag { struct net_device *dev; unsigned int id; struct mutex fdb_lock; struct list_head fdbs; refcount_t refcount; }; struct dsa_switch_tree { struct list_head list; /* List of switch ports */ struct list_head ports; /* Notifier chain for switch-wide events */ struct raw_notifier_head nh; /* Tree identifier */ unsigned int index; /* Number of switches attached to this tree */ struct kref refcount; /* Maps offloaded LAG netdevs to a zero-based linear ID for * drivers that need it. */ struct dsa_lag **lags; /* Tagging protocol operations */ const struct dsa_device_ops *tag_ops; /* Default tagging protocol preferred by the switches in this * tree. */ enum dsa_tag_protocol default_proto; /* Has this tree been applied to the hardware? */ bool setup; /* * Configuration data for the platform device that owns * this dsa switch tree instance. */ struct dsa_platform_data *pd; /* List of DSA links composing the routing table */ struct list_head rtable; /* Length of "lags" array */ unsigned int lags_len; /* Track the largest switch index within a tree */ unsigned int last_switch; }; /* LAG IDs are one-based, the dst->lags array is zero-based */ #define dsa_lags_foreach_id(_id, _dst) \ for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++) \ if ((_dst)->lags[(_id) - 1]) #define dsa_lag_foreach_port(_dp, _dst, _lag) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_offloads_lag((_dp), (_lag))) #define dsa_hsr_foreach_port(_dp, _ds, _hsr) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr)) static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst, unsigned int id) { /* DSA LAG IDs are one-based, dst->lags is zero-based */ return dst->lags[id - 1]; } static inline int dsa_lag_id(struct dsa_switch_tree *dst, struct net_device *lag_dev) { unsigned int id; dsa_lags_foreach_id(id, dst) { struct dsa_lag *lag = dsa_lag_by_id(dst, id); if (lag->dev == lag_dev) return lag->id; } return -ENODEV; } /* TC matchall action types */ enum dsa_port_mall_action_type { DSA_PORT_MALL_MIRROR, DSA_PORT_MALL_POLICER, }; /* TC mirroring entry */ struct dsa_mall_mirror_tc_entry { u8 to_local_port; bool ingress; }; /* TC port policer entry */ struct dsa_mall_policer_tc_entry { u32 burst; u64 rate_bytes_per_sec; }; /* TC matchall entry */ struct dsa_mall_tc_entry { struct list_head list; unsigned long cookie; enum dsa_port_mall_action_type type; union { struct dsa_mall_mirror_tc_entry mirror; struct dsa_mall_policer_tc_entry policer; }; }; struct dsa_bridge { struct net_device *dev; unsigned int num; bool tx_fwd_offload; refcount_t refcount; }; struct dsa_port { /* A CPU port is physically connected to a conduit device. A user port * exposes a network device to user-space, called 'user' here. */ union { struct net_device *conduit; struct net_device *user; }; /* Copy of the tagging protocol operations, for quicker access * in the data path. Valid only for the CPU ports. */ const struct dsa_device_ops *tag_ops; /* Copies for faster access in conduit receive hot path */ struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); struct dsa_switch *ds; unsigned int index; enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU, DSA_PORT_TYPE_DSA, DSA_PORT_TYPE_USER, } type; const char *name; struct dsa_port *cpu_dp; u8 mac[ETH_ALEN]; u8 stp_state; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u8 vlan_filtering:1; /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ u8 learning:1; u8 lag_tx_enabled:1; /* conduit state bits, valid only on CPU ports */ u8 conduit_admin_up:1; u8 conduit_oper_up:1; /* Valid only on user ports */ u8 cpu_port_in_lag:1; u8 setup:1; struct device_node *dn; unsigned int ageing_time; struct dsa_bridge *bridge; struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; struct dsa_lag *lag; struct net_device *hsr_dev; struct list_head list; /* * Original copy of the conduit netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; /* List of MAC addresses that must be forwarded on this port. * These are only valid on CPU ports and DSA links. */ struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; struct mutex vlans_lock; union { /* List of VLANs that CPU and DSA ports are members of. * Access to this is serialized by the sleepable @vlans_lock. */ struct list_head vlans; /* List of VLANs that user ports are members of. * Access to this is serialized by netif_addr_lock_bh(). */ struct list_head user_vlans; }; }; static inline struct dsa_port * dsa_phylink_to_port(struct phylink_config *config) { return container_of(config, struct dsa_port, pl_config); } /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, * so keep it stupid at the moment and list them all. */ struct dsa_link { struct dsa_port *dp; struct dsa_port *link_dp; struct list_head list; }; enum dsa_db_type { DSA_DB_PORT, DSA_DB_LAG, DSA_DB_BRIDGE, }; struct dsa_db { enum dsa_db_type type; union { const struct dsa_port *dp; struct dsa_lag lag; struct dsa_bridge bridge; }; }; struct dsa_mac_addr { unsigned char addr[ETH_ALEN]; u16 vid; refcount_t refcount; struct list_head list; struct dsa_db db; }; struct dsa_vlan { u16 vid; refcount_t refcount; struct list_head list; }; struct dsa_switch { struct device *dev; /* * Parent switch tree, and switch index. */ struct dsa_switch_tree *dst; unsigned int index; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u32 setup:1; /* Disallow bridge core from requesting different VLAN awareness * settings on ports if not hardware-supported */ u32 vlan_filtering_is_global:1; /* Keep VLAN filtering enabled on ports not offloading any upper */ u32 needs_standalone_vlan_filtering:1; /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges * that have vlan_filtering=0. All drivers should ideally set this (and * then the option would get removed), but it is unknown whether this * would break things or not. */ u32 configure_vlan_while_not_filtering:1; /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. * DEPRECATED: Do NOT set this field in new drivers. Instead look at * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. * Useful if the switch cannot preserve the VLAN tag as seen on the * wire for user port ingress, and chooses to send all frames as * VLAN-tagged to the CPU, including those which were originally * untagged. */ u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. */ u32 assisted_learning_on_cpu_port:1; /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ u32 vlan_filtering:1; /* For switches that only have the MRU configurable. To ensure the * configured MTU is not exceeded, normalization of MRU on all bridged * interfaces is needed. */ u32 mtu_enforcement_ingress:1; /* Drivers that isolate the FDBs of multiple bridges must set this * to true to receive the bridge as an argument in .port_fdb_{add,del} * and .port_mdb_{add,del}. Otherwise, the bridge.num will always be * passed as zero. */ u32 fdb_isolation:1; /* Drivers that have global DSCP mapping settings must set this to * true to automatically apply the settings to all ports. */ u32 dscp_prio_mapping_is_global:1; /* Listener for switch fabric events */ struct notifier_block nb; /* * Give the switch driver somewhere to hang its private data * structure. */ void *priv; void *tagger_data; /* * Configuration data for this switch. */ struct dsa_chip_data *cd; /* * The switch operations. */ const struct dsa_switch_ops *ops; /* * Allow a DSA switch driver to override the phylink MAC ops */ const struct phylink_mac_ops *phylink_mac_ops; /* * User mii_bus and devices for the individual ports. */ u32 phys_mii_mask; struct mii_bus *user_mii_bus; /* Ageing Time limits in msecs */ unsigned int ageing_time_min; unsigned int ageing_time_max; /* Storage for drivers using tag_8021q */ struct dsa_8021q_context *tag_8021q_ctx; /* devlink used to represent this switch device */ struct devlink *devlink; /* Number of switch port queues */ unsigned int num_tx_queues; /* Drivers that benefit from having an ID associated with each * offloaded LAG should set this to the maximum number of * supported IDs. DSA will then maintain a mapping of _at * least_ these many IDs, accessible to drivers via * dsa_lag_id(). */ unsigned int num_lag_ids; /* Drivers that support bridge forwarding offload or FDB isolation * should set this to the maximum number of bridges spanning the same * switch tree (or all trees, in the case of cross-tree bridging * support) that can be offloaded. */ unsigned int max_num_bridges; unsigned int num_ports; }; static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) { struct dsa_switch_tree *dst = ds->dst; struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dp->ds == ds && dp->index == p) return dp; return NULL; } static inline bool dsa_port_is_dsa(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_port_is_cpu(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_port_is_user(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_USER; } static inline bool dsa_port_is_unused(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_port_conduit_is_operational(struct dsa_port *dp) { return dsa_port_is_cpu(dp) && dp->conduit_admin_up && dp->conduit_oper_up; } static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; } #define dsa_tree_for_each_user_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \ list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_cpu_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_port(_dp, _ds) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_available_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (!dsa_port_is_unused((_dp))) #define dsa_switch_for_each_user_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_user_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_cpu_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; u32 mask = 0; dsa_switch_for_each_user_port(dp, ds) mask |= BIT(dp->index); return mask; } static inline u32 dsa_cpu_ports(struct dsa_switch *ds) { struct dsa_port *cpu_dp; u32 mask = 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) mask |= BIT(cpu_dp->index); return mask; } /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { struct dsa_switch_tree *dst = ds->dst; struct dsa_link *dl; list_for_each_entry(dl, &dst->rtable, list) if (dl->dp->ds == ds && dl->link_dp->ds->index == device) return dl->dp->index; return ds->num_ports; } /* Return the local port used to reach an arbitrary switch port */ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device, int port) { if (device == ds->index) return port; else return dsa_routing_port(ds, device); } /* Return the local port used to reach the dedicated CPU port */ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) { const struct dsa_port *dp = dsa_to_port(ds, port); const struct dsa_port *cpu_dp = dp->cpu_dp; if (!cpu_dp) return port; return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } /* Return true if this is the local port used to reach the CPU port */ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) { if (dsa_is_unused_port(ds, port)) return false; return port == dsa_upstream_port(ds, port); } /* Return true if this is a DSA port leading away from the CPU */ static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) { return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); } /* Return the local port used to reach the CPU port */ static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) { struct dsa_port *dp; dsa_switch_for_each_available_port(dp, ds) { return dsa_upstream_port(ds, dp->index); } return ds->num_ports; } /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. */ static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds, struct dsa_switch *downstream_ds) { int routing_port; if (upstream_ds == downstream_ds) return true; routing_port = dsa_routing_port(downstream_ds, upstream_ds->index); return dsa_is_upstream_port(downstream_ds, routing_port); } static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) { const struct dsa_switch *ds = dp->ds; if (ds->vlan_filtering_is_global) return ds->vlan_filtering; else return dp->vlan_filtering; } static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp) { return dp->lag ? dp->lag->id : 0; } static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp) { return dp->lag ? dp->lag->dev : NULL; } static inline bool dsa_port_offloads_lag(struct dsa_port *dp, const struct dsa_lag *lag) { return dsa_port_lag_dev_get(dp) == lag->dev; } static inline struct net_device *dsa_port_to_conduit(const struct dsa_port *dp) { if (dp->cpu_port_in_lag) return dsa_port_lag_dev_get(dp->cpu_dp); return dp->cpu_dp->conduit; } static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { if (!dp->bridge) return NULL; if (dp->lag) return dp->lag->dev; else if (dp->hsr_dev) return dp->hsr_dev; return dp->user; } static inline struct net_device * dsa_port_bridge_dev_get(const struct dsa_port *dp) { return dp->bridge ? dp->bridge->dev : NULL; } static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) { return dp->bridge ? dp->bridge->num : 0; } static inline bool dsa_port_bridge_same(const struct dsa_port *a, const struct dsa_port *b) { struct net_device *br_a = dsa_port_bridge_dev_get(a); struct net_device *br_b = dsa_port_bridge_dev_get(b); /* Standalone ports are not in the same bridge with one another */ return (!br_a || !br_b) ? false : (br_a == br_b); } static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, const struct net_device *dev) { return dsa_port_to_bridge_port(dp) == dev; } static inline bool dsa_port_offloads_bridge_dev(struct dsa_port *dp, const struct net_device *bridge_dev) { /* DSA ports connected to a bridge, and event was emitted * for the bridge. */ return dsa_port_bridge_dev_get(dp) == bridge_dev; } static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, const struct dsa_bridge *bridge) { return dsa_port_bridge_dev_get(dp) == bridge->dev; } /* Returns true if any port of this tree offloads the given net_device */ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, const struct net_device *dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_port(dp, dev)) return true; return false; } /* Returns true if any port of this tree offloads the given bridge */ static inline bool dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, const struct net_device *bridge_dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_dev(dp, bridge_dev)) return true; return false; } static inline bool dsa_port_tree_same(const struct dsa_port *a, const struct dsa_port *b) { return a->ds->dst == b->ds->dst; } typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { /* * Tagging protocol helpers called for the CPU ports and DSA links. * @get_tag_protocol retrieves the initial tagging protocol and is * mandatory. Switches which can operate using multiple tagging * protocols should implement @change_tag_protocol and report in * @get_tag_protocol the tagger in current use. */ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver * in current use. The switch driver can provide handlers for certain * types of packets for switch management. */ int (*connect_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); int (*port_change_conduit)(struct dsa_switch *ds, int port, struct net_device *conduit, struct netlink_ext_ack *extack); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); /* Per-port initialization and destruction methods. Mandatory if the * driver registers devlink port regions, optional otherwise. */ int (*port_setup)(struct dsa_switch *ds, int port); void (*port_teardown)(struct dsa_switch *ds, int port); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* * Access to the switch's PHY registers. */ int (*phy_read)(struct dsa_switch *ds, int port, int regnum); int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); /* * PHYLINK integration */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds, int port, phy_interface_t iface); void (*phylink_mac_config)(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state); void (*phylink_mac_link_down)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); void (*phylink_mac_link_up)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, struct phy_device *phydev, int speed, int duplex, bool tx_pause, bool rx_pause); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* * Port statistics counters. */ void (*get_strings)(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_phy_stats *phy_stats); void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_mac_stats *mac_stats); void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, struct ethtool_pause_stats *pause_stats); void (*self_test)(struct dsa_switch *ds, int port, struct ethtool_test *etest, u64 *data); /* * ethtool Wake-on-LAN */ void (*get_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); int (*set_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); /* * ethtool timestamp info */ int (*get_ts_info)(struct dsa_switch *ds, int port, struct kernel_ethtool_ts_info *ts); /* * ethtool MAC merge layer */ int (*get_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_state *state); int (*set_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack); void (*get_mm_stats)(struct dsa_switch *ds, int port, struct ethtool_mm_stats *stats); /* * DCB ops */ int (*port_get_default_prio)(struct dsa_switch *ds, int port); int (*port_set_default_prio)(struct dsa_switch *ds, int port, u8 prio); int (*port_get_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp); int (*port_add_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_set_apptrust)(struct dsa_switch *ds, int port, const u8 *sel, int nsel); int (*port_get_apptrust)(struct dsa_switch *ds, int port, u8 *sel, int *nsel); /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); int (*resume)(struct dsa_switch *ds); /* * Port enable/disable */ int (*port_enable)(struct dsa_switch *ds, int port, struct phy_device *phy); void (*port_disable)(struct dsa_switch *ds, int port); /* * Notification for MAC address changes on user ports. Drivers can * currently only veto operations. They should not use the method to * program the hardware, since the operation is not rolled back in case * of other errors. */ int (*port_set_mac_address)(struct dsa_switch *ds, int port, const unsigned char *addr); /* * Compatibility between device trees defining multiple CPU ports and * drivers which are not OK to use by default the numerically smallest * CPU port of a switch for its local ports. This can return NULL, * meaning "don't know/don't care". */ struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds); /* * Port's MAC EEE settings */ int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); int (*get_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); int (*get_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); int (*set_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); /* * Register access. */ int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); /* * Upper device tracking. */ int (*port_prechangeupper)(struct dsa_switch *ds, int port, struct netdev_notifier_changeupper_info *info); /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, struct netlink_ext_ack *extack); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); int (*port_mst_state_set)(struct dsa_switch *ds, int port, const struct switchdev_mst_state *state); void (*port_fast_age)(struct dsa_switch *ds, int port); int (*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid); int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); void (*port_set_host_flood)(struct dsa_switch *ds, int port, bool uc, bool mc); /* * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack); int (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); int (*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge, const struct switchdev_vlan_msti *msti); /* * Forwarding database */ int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); /* * Multicast database */ int (*port_mdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* * RXNFC */ int (*get_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc, u32 *rule_locs); int (*set_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc); /* * TC integration */ int (*cls_flower_add)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_del)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_stats)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*port_mirror_add)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress, struct netlink_ext_ack *extack); void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, struct dsa_mall_policer_tc_entry *policer); void (*port_policer_del)(struct dsa_switch *ds, int port); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); /* * Cross-chip operations */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge, struct netlink_ext_ack *extack); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag); /* * PTP functionality */ int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, struct ifreq *ifr); int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, struct ifreq *ifr); void (*port_txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_info_get)(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack); int (*devlink_sb_pool_get)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info); int (*devlink_sb_pool_set)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type, struct netlink_ext_ack *extack); int (*devlink_sb_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_threshold); int (*devlink_sb_port_pool_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_tc_pool_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 *p_pool_index, u32 *p_threshold); int (*devlink_sb_tc_pool_bind_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_occ_snapshot)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_max_clear)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_cur, u32 *p_max); int (*devlink_sb_occ_tc_port_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); /* * MTU change functionality. Switches can also adjust their MRU through * this method. By MTU, one understands the SDU (L2 payload) length. * If the switch needs to account for the DSA tag on the CPU port, this * method needs to do so privately. */ int (*port_change_mtu)(struct dsa_switch *ds, int port, int new_mtu); int (*port_max_mtu)(struct dsa_switch *ds, int port); /* * LAG integration */ int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*port_lag_leave)(struct dsa_switch *ds, int port, struct dsa_lag lag); /* * HSR integration */ int (*port_hsr_join)(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int (*port_hsr_leave)(struct dsa_switch *ds, int port, struct net_device *hsr); /* * MRP integration */ int (*port_mrp_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_add_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); /* * tag_8021q operations */ int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); /* * DSA conduit tracking operations */ void (*conduit_state_change)(struct dsa_switch *ds, const struct net_device *conduit, bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \ dsa_devlink_param_get, dsa_devlink_param_set, NULL) int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int dsa_devlink_params_register(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); void dsa_devlink_params_unregister(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); int dsa_devlink_resource_register(struct dsa_switch *ds, const char *resource_name, u64 resource_size, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); void dsa_devlink_resources_unregister(struct dsa_switch *ds); void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, u64 resource_id, devlink_resource_occ_get_t *occ_get, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); struct devlink_region * dsa_devlink_region_create(struct dsa_switch *ds, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); struct devlink_region * dsa_devlink_port_region_create(struct dsa_switch *ds, int port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size); void dsa_devlink_region_destroy(struct devlink_region *region); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; }; static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) { struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port) { struct devlink *dl = port->devlink; struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline int dsa_devlink_port_to_port(struct devlink_port *port) { return port->index; } struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; }; bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(const struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } /* All DSA tags that push the EtherType to the right (basically all except tail * tags, which don't break dissection) can be treated the same from the * perspective of the flow dissector. * * We need to return: * - offset: the (B - A) difference between: * A. the position of the real EtherType and * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes * after the normal EtherType was supposed to be) * The offset in bytes is exactly equal to the tagger overhead (and half of * that, in __be16 shorts). * * - proto: the value of the real EtherType. */ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; #endif } void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); void dsa_flush_workqueue(void); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); #else static inline int dsa_switch_suspend(struct dsa_switch *ds) { return 0; } static inline int dsa_switch_resume(struct dsa_switch *ds) { return 0; } #endif /* CONFIG_PM_SLEEP */ #if IS_ENABLED(CONFIG_NET_DSA) bool dsa_user_dev_check(const struct net_device *dev); #else static inline bool dsa_user_dev_check(const struct net_device *dev) { return false; } #endif netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); #endif |
| 4 40 41 39 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 | // SPDX-License-Identifier: GPL-2.0-only /* * CAIF Interface registration. * Copyright (C) ST-Ericsson AB 2010 * Author: Sjur Brendeland * * Borrowed heavily from file: pn_dev.c. Thanks to Remi Denis-Courmont * and Sakari Ailus <sakari.ailus@nokia.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ #include <linux/kernel.h> #include <linux/if_arp.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/mutex.h> #include <linux/module.h> #include <linux/spinlock.h> #include <net/netns/generic.h> #include <net/net_namespace.h> #include <net/pkt_sched.h> #include <net/caif/caif_device.h> #include <net/caif/caif_layer.h> #include <net/caif/caif_dev.h> #include <net/caif/cfpkt.h> #include <net/caif/cfcnfg.h> #include <net/caif/cfserl.h> MODULE_DESCRIPTION("ST-Ericsson CAIF modem protocol support"); MODULE_LICENSE("GPL"); /* Used for local tracking of the CAIF net devices */ struct caif_device_entry { struct cflayer layer; struct list_head list; struct net_device *netdev; int __percpu *pcpu_refcnt; spinlock_t flow_lock; struct sk_buff *xoff_skb; void (*xoff_skb_dtor)(struct sk_buff *skb); bool xoff; }; struct caif_device_entry_list { struct list_head list; /* Protects simulanous deletes in list */ struct mutex lock; }; struct caif_net { struct cfcnfg *cfg; struct caif_device_entry_list caifdevs; }; static unsigned int caif_net_id; static int q_high = 50; /* Percent */ struct cfcnfg *get_cfcnfg(struct net *net) { struct caif_net *caifn; caifn = net_generic(net, caif_net_id); return caifn->cfg; } EXPORT_SYMBOL(get_cfcnfg); static struct caif_device_entry_list *caif_device_list(struct net *net) { struct caif_net *caifn; caifn = net_generic(net, caif_net_id); return &caifn->caifdevs; } static void caifd_put(struct caif_device_entry *e) { this_cpu_dec(*e->pcpu_refcnt); } static void caifd_hold(struct caif_device_entry *e) { this_cpu_inc(*e->pcpu_refcnt); } static int caifd_refcnt_read(struct caif_device_entry *e) { int i, refcnt = 0; for_each_possible_cpu(i) refcnt += *per_cpu_ptr(e->pcpu_refcnt, i); return refcnt; } /* Allocate new CAIF device. */ static struct caif_device_entry *caif_device_alloc(struct net_device *dev) { struct caif_device_entry *caifd; caifd = kzalloc(sizeof(*caifd), GFP_KERNEL); if (!caifd) return NULL; caifd->pcpu_refcnt = alloc_percpu(int); if (!caifd->pcpu_refcnt) { kfree(caifd); return NULL; } caifd->netdev = dev; dev_hold(dev); return caifd; } static struct caif_device_entry *caif_get(struct net_device *dev) { struct caif_device_entry_list *caifdevs = caif_device_list(dev_net(dev)); struct caif_device_entry *caifd; list_for_each_entry_rcu(caifd, &caifdevs->list, list, lockdep_rtnl_is_held()) { if (caifd->netdev == dev) return caifd; } return NULL; } static void caif_flow_cb(struct sk_buff *skb) { struct caif_device_entry *caifd; void (*dtor)(struct sk_buff *skb) = NULL; bool send_xoff; WARN_ON(skb->dev == NULL); rcu_read_lock(); caifd = caif_get(skb->dev); WARN_ON(caifd == NULL); if (!caifd) { rcu_read_unlock(); return; } caifd_hold(caifd); rcu_read_unlock(); spin_lock_bh(&caifd->flow_lock); send_xoff = caifd->xoff; caifd->xoff = false; dtor = caifd->xoff_skb_dtor; if (WARN_ON(caifd->xoff_skb != skb)) skb = NULL; caifd->xoff_skb = NULL; caifd->xoff_skb_dtor = NULL; spin_unlock_bh(&caifd->flow_lock); if (dtor && skb) dtor(skb); if (send_xoff) caifd->layer.up-> ctrlcmd(caifd->layer.up, _CAIF_CTRLCMD_PHYIF_FLOW_ON_IND, caifd->layer.id); caifd_put(caifd); } static int transmit(struct cflayer *layer, struct cfpkt *pkt) { int err, high = 0, qlen = 0; struct caif_device_entry *caifd = container_of(layer, struct caif_device_entry, layer); struct sk_buff *skb; struct netdev_queue *txq; rcu_read_lock_bh(); skb = cfpkt_tonative(pkt); skb->dev = caifd->netdev; skb_reset_network_header(skb); skb->protocol = htons(ETH_P_CAIF); /* Check if we need to handle xoff */ if (likely(caifd->netdev->priv_flags & IFF_NO_QUEUE)) goto noxoff; if (unlikely(caifd->xoff)) goto noxoff; if (likely(!netif_queue_stopped(caifd->netdev))) { struct Qdisc *sch; /* If we run with a TX queue, check if the queue is too long*/ txq = netdev_get_tx_queue(skb->dev, 0); sch = rcu_dereference_bh(txq->qdisc); if (likely(qdisc_is_empty(sch))) goto noxoff; /* can check for explicit qdisc len value only !NOLOCK, * always set flow off otherwise */ high = (caifd->netdev->tx_queue_len * q_high) / 100; if (!(sch->flags & TCQ_F_NOLOCK) && likely(sch->q.qlen < high)) goto noxoff; } /* Hold lock while accessing xoff */ spin_lock_bh(&caifd->flow_lock); if (caifd->xoff) { spin_unlock_bh(&caifd->flow_lock); goto noxoff; } /* * Handle flow off, we do this by temporary hi-jacking this * skb's destructor function, and replace it with our own * flow-on callback. The callback will set flow-on and call * the original destructor. */ pr_debug("queue has stopped(%d) or is full (%d > %d)\n", netif_queue_stopped(caifd->netdev), qlen, high); caifd->xoff = true; caifd->xoff_skb = skb; caifd->xoff_skb_dtor = skb->destructor; skb->destructor = caif_flow_cb; spin_unlock_bh(&caifd->flow_lock); caifd->layer.up->ctrlcmd(caifd->layer.up, _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND, caifd->layer.id); noxoff: rcu_read_unlock_bh(); err = dev_queue_xmit(skb); if (err > 0) err = -EIO; return err; } /* * Stuff received packets into the CAIF stack. * On error, returns non-zero and releases the skb. */ static int receive(struct sk_buff *skb, struct net_device *dev, struct packet_type *pkttype, struct net_device *orig_dev) { struct cfpkt *pkt; struct caif_device_entry *caifd; int err; pkt = cfpkt_fromnative(CAIF_DIR_IN, skb); rcu_read_lock(); caifd = caif_get(dev); if (!caifd || !caifd->layer.up || !caifd->layer.up->receive || !netif_oper_up(caifd->netdev)) { rcu_read_unlock(); kfree_skb(skb); return NET_RX_DROP; } /* Hold reference to netdevice while using CAIF stack */ caifd_hold(caifd); rcu_read_unlock(); err = caifd->layer.up->receive(caifd->layer.up, pkt); /* For -EILSEQ the packet is not freed so free it now */ if (err == -EILSEQ) cfpkt_destroy(pkt); /* Release reference to stack upwards */ caifd_put(caifd); if (err != 0) err = NET_RX_DROP; return err; } static struct packet_type caif_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_CAIF), .func = receive, }; static void dev_flowctrl(struct net_device *dev, int on) { struct caif_device_entry *caifd; rcu_read_lock(); caifd = caif_get(dev); if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) { rcu_read_unlock(); return; } caifd_hold(caifd); rcu_read_unlock(); caifd->layer.up->ctrlcmd(caifd->layer.up, on ? _CAIF_CTRLCMD_PHYIF_FLOW_ON_IND : _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND, caifd->layer.id); caifd_put(caifd); } int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, struct cflayer *link_support, int head_room, struct cflayer **layer, int (**rcv_func)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *)) { struct caif_device_entry *caifd; enum cfcnfg_phy_preference pref; struct cfcnfg *cfg = get_cfcnfg(dev_net(dev)); struct caif_device_entry_list *caifdevs; int res; caifdevs = caif_device_list(dev_net(dev)); caifd = caif_device_alloc(dev); if (!caifd) return -ENOMEM; *layer = &caifd->layer; spin_lock_init(&caifd->flow_lock); switch (caifdev->link_select) { case CAIF_LINK_HIGH_BANDW: pref = CFPHYPREF_HIGH_BW; break; case CAIF_LINK_LOW_LATENCY: pref = CFPHYPREF_LOW_LAT; break; default: pref = CFPHYPREF_HIGH_BW; break; } mutex_lock(&caifdevs->lock); list_add_rcu(&caifd->list, &caifdevs->list); strscpy(caifd->layer.name, dev->name, sizeof(caifd->layer.name)); caifd->layer.transmit = transmit; res = cfcnfg_add_phy_layer(cfg, dev, &caifd->layer, pref, link_support, caifdev->use_fcs, head_room); mutex_unlock(&caifdevs->lock); if (rcv_func) *rcv_func = receive; return res; } EXPORT_SYMBOL(caif_enroll_dev); /* notify Caif of device events */ static int caif_device_notify(struct notifier_block *me, unsigned long what, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct caif_device_entry *caifd = NULL; struct caif_dev_common *caifdev; struct cfcnfg *cfg; struct cflayer *layer, *link_support; int head_room = 0; struct caif_device_entry_list *caifdevs; int res; cfg = get_cfcnfg(dev_net(dev)); caifdevs = caif_device_list(dev_net(dev)); caifd = caif_get(dev); if (caifd == NULL && dev->type != ARPHRD_CAIF) return 0; switch (what) { case NETDEV_REGISTER: if (caifd != NULL) break; caifdev = netdev_priv(dev); link_support = NULL; if (caifdev->use_frag) { head_room = 1; link_support = cfserl_create(dev->ifindex, caifdev->use_stx); if (!link_support) { pr_warn("Out of memory\n"); break; } } res = caif_enroll_dev(dev, caifdev, link_support, head_room, &layer, NULL); if (res) cfserl_release(link_support); caifdev->flowctrl = dev_flowctrl; break; case NETDEV_UP: rcu_read_lock(); caifd = caif_get(dev); if (caifd == NULL) { rcu_read_unlock(); break; } caifd->xoff = false; cfcnfg_set_phy_state(cfg, &caifd->layer, true); rcu_read_unlock(); break; case NETDEV_DOWN: rcu_read_lock(); caifd = caif_get(dev); if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) { rcu_read_unlock(); return -EINVAL; } cfcnfg_set_phy_state(cfg, &caifd->layer, false); caifd_hold(caifd); rcu_read_unlock(); caifd->layer.up->ctrlcmd(caifd->layer.up, _CAIF_CTRLCMD_PHYIF_DOWN_IND, caifd->layer.id); spin_lock_bh(&caifd->flow_lock); /* * Replace our xoff-destructor with original destructor. * We trust that skb->destructor *always* is called before * the skb reference is invalid. The hijacked SKB destructor * takes the flow_lock so manipulating the skb->destructor here * should be safe. */ if (caifd->xoff_skb_dtor != NULL && caifd->xoff_skb != NULL) caifd->xoff_skb->destructor = caifd->xoff_skb_dtor; caifd->xoff = false; caifd->xoff_skb_dtor = NULL; caifd->xoff_skb = NULL; spin_unlock_bh(&caifd->flow_lock); caifd_put(caifd); break; case NETDEV_UNREGISTER: mutex_lock(&caifdevs->lock); caifd = caif_get(dev); if (caifd == NULL) { mutex_unlock(&caifdevs->lock); break; } list_del_rcu(&caifd->list); /* * NETDEV_UNREGISTER is called repeatedly until all reference * counts for the net-device are released. If references to * caifd is taken, simply ignore NETDEV_UNREGISTER and wait for * the next call to NETDEV_UNREGISTER. * * If any packets are in flight down the CAIF Stack, * cfcnfg_del_phy_layer will return nonzero. * If no packets are in flight, the CAIF Stack associated * with the net-device un-registering is freed. */ if (caifd_refcnt_read(caifd) != 0 || cfcnfg_del_phy_layer(cfg, &caifd->layer) != 0) { pr_info("Wait for device inuse\n"); /* Enrole device if CAIF Stack is still in use */ list_add_rcu(&caifd->list, &caifdevs->list); mutex_unlock(&caifdevs->lock); break; } synchronize_rcu(); dev_put(caifd->netdev); free_percpu(caifd->pcpu_refcnt); kfree(caifd); mutex_unlock(&caifdevs->lock); break; } return 0; } static struct notifier_block caif_device_notifier = { .notifier_call = caif_device_notify, .priority = 0, }; /* Per-namespace Caif devices handling */ static int caif_init_net(struct net *net) { struct caif_net *caifn = net_generic(net, caif_net_id); INIT_LIST_HEAD(&caifn->caifdevs.list); mutex_init(&caifn->caifdevs.lock); caifn->cfg = cfcnfg_create(); if (!caifn->cfg) return -ENOMEM; return 0; } static void caif_exit_net(struct net *net) { struct caif_device_entry *caifd, *tmp; struct caif_device_entry_list *caifdevs = caif_device_list(net); struct cfcnfg *cfg = get_cfcnfg(net); rtnl_lock(); mutex_lock(&caifdevs->lock); list_for_each_entry_safe(caifd, tmp, &caifdevs->list, list) { int i = 0; list_del_rcu(&caifd->list); cfcnfg_set_phy_state(cfg, &caifd->layer, false); while (i < 10 && (caifd_refcnt_read(caifd) != 0 || cfcnfg_del_phy_layer(cfg, &caifd->layer) != 0)) { pr_info("Wait for device inuse\n"); msleep(250); i++; } synchronize_rcu(); dev_put(caifd->netdev); free_percpu(caifd->pcpu_refcnt); kfree(caifd); } cfcnfg_remove(cfg); mutex_unlock(&caifdevs->lock); rtnl_unlock(); } static struct pernet_operations caif_net_ops = { .init = caif_init_net, .exit = caif_exit_net, .id = &caif_net_id, .size = sizeof(struct caif_net), }; /* Initialize Caif devices list */ static int __init caif_device_init(void) { int result; result = register_pernet_subsys(&caif_net_ops); if (result) return result; register_netdevice_notifier(&caif_device_notifier); dev_add_pack(&caif_packet_type); return result; } static void __exit caif_device_exit(void) { unregister_netdevice_notifier(&caif_device_notifier); dev_remove_pack(&caif_packet_type); unregister_pernet_subsys(&caif_net_ops); } module_init(caif_device_init); module_exit(caif_device_exit); |
| 246 170 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_COREDUMP_H #define _LINUX_SCHED_COREDUMP_H #include <linux/mm_types.h> #define SUID_DUMP_DISABLE 0 /* No setuid dumping */ #define SUID_DUMP_USER 1 /* Dump as user of process */ #define SUID_DUMP_ROOT 2 /* Dump as root */ /* mm flags */ /* for SUID_DUMP_* above */ #define MMF_DUMPABLE_BITS 2 #define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) extern void set_dumpable(struct mm_struct *mm, int value); /* * This returns the actual value of the suid_dumpable flag. For things * that are using this for checking for privilege transitions, it must * test against SUID_DUMP_USER rather than treating it as a boolean * value. */ static inline int __get_dumpable(unsigned long mm_flags) { return mm_flags & MMF_DUMPABLE_MASK; } static inline int get_dumpable(struct mm_struct *mm) { return __get_dumpable(mm->flags); } /* coredump filter bits */ #define MMF_DUMP_ANON_PRIVATE 2 #define MMF_DUMP_ANON_SHARED 3 #define MMF_DUMP_MAPPED_PRIVATE 4 #define MMF_DUMP_MAPPED_SHARED 5 #define MMF_DUMP_ELF_HEADERS 6 #define MMF_DUMP_HUGETLB_PRIVATE 7 #define MMF_DUMP_HUGETLB_SHARED 8 #define MMF_DUMP_DAX_PRIVATE 9 #define MMF_DUMP_DAX_SHARED 10 #define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS #define MMF_DUMP_FILTER_BITS 9 #define MMF_DUMP_FILTER_MASK \ (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) #define MMF_DUMP_FILTER_DEFAULT \ ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) #ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS # define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) #else # define MMF_DUMP_MASK_DEFAULT_ELF 0 #endif /* leave room for more dump flags */ #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ #define MMF_VM_HUGEPAGE 17 /* set when mm is available for khugepaged */ /* * This one-shot flag is dropped due to necessity of changing exe once again * on NFS restore */ //#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ #define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ #define MMF_MULTIPROCESS 26 /* mm is shared between processes */ /* * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either * replaced in the future by mm.pinned_vm when it becomes stable, or grow into * a counter on its own. We're aggresive on this bit for now: even if the * pinned pages were unpinned later on, we'll still keep this bit set for the * lifecycle of this mm, just for simplicity. */ #define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ #define MMF_HAS_MDWE 28 #define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE) #define MMF_HAS_MDWE_NO_INHERIT 29 #define MMF_VM_MERGE_ANY 30 #define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) #define MMF_TOPDOWN 31 /* mm searches top down by default */ #define MMF_TOPDOWN_MASK (1 << MMF_TOPDOWN) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK) static inline unsigned long mmf_init_flags(unsigned long flags) { if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) flags &= ~((1UL << MMF_HAS_MDWE) | (1UL << MMF_HAS_MDWE_NO_INHERIT)); return flags & MMF_INIT_MASK; } #endif /* _LINUX_SCHED_COREDUMP_H */ |
| 13 13 13 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PACKET_INTERNAL_H__ #define __PACKET_INTERNAL_H__ #include <linux/refcount.h> struct packet_mclist { struct packet_mclist *next; int ifindex; int count; unsigned short type; unsigned short alen; unsigned char addr[MAX_ADDR_LEN]; }; /* kbdq - kernel block descriptor queue */ struct tpacket_kbdq_core { struct pgv *pkbdq; unsigned int feature_req_word; unsigned int hdrlen; unsigned char reset_pending_on_curr_blk; unsigned char delete_blk_timer; unsigned short kactive_blk_num; unsigned short blk_sizeof_priv; /* last_kactive_blk_num: * trick to see if user-space has caught up * in order to avoid refreshing timer when every single pkt arrives. */ unsigned short last_kactive_blk_num; char *pkblk_start; char *pkblk_end; int kblk_size; unsigned int max_frame_len; unsigned int knum_blocks; uint64_t knxt_seq_num; char *prev; char *nxt_offset; struct sk_buff *skb; rwlock_t blk_fill_in_prog_lock; /* Default is set to 8ms */ #define DEFAULT_PRB_RETIRE_TOV (8) unsigned short retire_blk_tov; unsigned short version; unsigned long tov_in_jiffies; /* timer to retire an outstanding block */ struct timer_list retire_blk_timer; }; struct pgv { char *buffer; }; struct packet_ring_buffer { struct pgv *pg_vec; unsigned int head; unsigned int frames_per_block; unsigned int frame_size; unsigned int frame_max; unsigned int pg_vec_order; unsigned int pg_vec_pages; unsigned int pg_vec_len; unsigned int __percpu *pending_refcnt; union { unsigned long *rx_owner_map; struct tpacket_kbdq_core prb_bdqc; }; }; extern struct mutex fanout_mutex; #define PACKET_FANOUT_MAX (1 << 16) struct packet_fanout { possible_net_t net; unsigned int num_members; u32 max_num_members; u16 id; u8 type; u8 flags; union { atomic_t rr_cur; struct bpf_prog __rcu *bpf_prog; }; struct list_head list; spinlock_t lock; refcount_t sk_ref; struct packet_type prot_hook ____cacheline_aligned_in_smp; struct sock __rcu *arr[] __counted_by(max_num_members); }; struct packet_rollover { int sock; atomic_long_t num; atomic_long_t num_huge; atomic_long_t num_failed; #define ROLLOVER_HLEN (L1_CACHE_BYTES / sizeof(u32)) u32 history[ROLLOVER_HLEN] ____cacheline_aligned; } ____cacheline_aligned_in_smp; struct packet_sock { /* struct sock has to be the first member of packet_sock */ struct sock sk; struct packet_fanout *fanout; union tpacket_stats_u stats; struct packet_ring_buffer rx_ring; struct packet_ring_buffer tx_ring; int copy_thresh; spinlock_t bind_lock; struct mutex pg_vec_lock; unsigned long flags; int ifindex; /* bound device */ u8 vnet_hdr_sz; __be16 num; struct packet_rollover *rollover; struct packet_mclist *mclist; atomic_long_t mapped; enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; unsigned int tp_tstamp; struct completion skb_completion; struct net_device __rcu *cached_dev; struct packet_type prot_hook ____cacheline_aligned_in_smp; atomic_t tp_drops ____cacheline_aligned_in_smp; }; #define pkt_sk(ptr) container_of_const(ptr, struct packet_sock, sk) enum packet_sock_flags { PACKET_SOCK_ORIGDEV, PACKET_SOCK_AUXDATA, PACKET_SOCK_TX_HAS_OFF, PACKET_SOCK_TP_LOSS, PACKET_SOCK_RUNNING, PACKET_SOCK_PRESSURE, PACKET_SOCK_QDISC_BYPASS, }; static inline void packet_sock_flag_set(struct packet_sock *po, enum packet_sock_flags flag, bool val) { if (val) set_bit(flag, &po->flags); else clear_bit(flag, &po->flags); } static inline bool packet_sock_flag(const struct packet_sock *po, enum packet_sock_flags flag) { return test_bit(flag, &po->flags); } #endif |
| 24 24 24 24 24 24 24 2 2 9 40 40 40 24 2 9 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018, Intel Corporation. */ /* A common module to handle registrations and notifications for paravirtual * drivers to enable accelerated datapath and support VF live migration. * * The notifier and event handling code is based on netvsc driver. */ #include <linux/module.h> #include <linux/etherdevice.h> #include <uapi/linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/if_vlan.h> #include <net/failover.h> static LIST_HEAD(failover_list); static DEFINE_SPINLOCK(failover_lock); static struct net_device *failover_get_bymac(u8 *mac, struct failover_ops **ops) { struct net_device *failover_dev; struct failover *failover; spin_lock(&failover_lock); list_for_each_entry(failover, &failover_list, list) { failover_dev = rtnl_dereference(failover->failover_dev); if (ether_addr_equal(failover_dev->perm_addr, mac)) { *ops = rtnl_dereference(failover->ops); spin_unlock(&failover_lock); return failover_dev; } } spin_unlock(&failover_lock); return NULL; } /** * failover_slave_register - Register a slave netdev * * @slave_dev: slave netdev that is being registered * * Registers a slave device to a failover instance. Only ethernet devices * are supported. */ static int failover_slave_register(struct net_device *slave_dev) { struct netdev_lag_upper_info lag_upper_info; struct net_device *failover_dev; struct failover_ops *fops; int err; if (slave_dev->type != ARPHRD_ETHER) goto done; ASSERT_RTNL(); failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); if (!failover_dev) goto done; if (fops && fops->slave_pre_register && fops->slave_pre_register(slave_dev, failover_dev)) goto done; err = netdev_rx_handler_register(slave_dev, fops->slave_handle_frame, failover_dev); if (err) { netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n", err); goto done; } lag_upper_info.tx_type = NETDEV_LAG_TX_TYPE_ACTIVEBACKUP; err = netdev_master_upper_dev_link(slave_dev, failover_dev, NULL, &lag_upper_info, NULL); if (err) { netdev_err(slave_dev, "can not set failover device %s (err = %d)\n", failover_dev->name, err); goto err_upper_link; } slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_NO_ADDRCONF); if (fops && fops->slave_register && !fops->slave_register(slave_dev, failover_dev)) return NOTIFY_OK; netdev_upper_dev_unlink(slave_dev, failover_dev); slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_NO_ADDRCONF); err_upper_link: netdev_rx_handler_unregister(slave_dev); done: return NOTIFY_DONE; } /** * failover_slave_unregister - Unregister a slave netdev * * @slave_dev: slave netdev that is being unregistered * * Unregisters a slave device from a failover instance. */ int failover_slave_unregister(struct net_device *slave_dev) { struct net_device *failover_dev; struct failover_ops *fops; if (!netif_is_failover_slave(slave_dev)) goto done; ASSERT_RTNL(); failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); if (!failover_dev) goto done; if (fops && fops->slave_pre_unregister && fops->slave_pre_unregister(slave_dev, failover_dev)) goto done; netdev_rx_handler_unregister(slave_dev); netdev_upper_dev_unlink(slave_dev, failover_dev); slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_NO_ADDRCONF); if (fops && fops->slave_unregister && !fops->slave_unregister(slave_dev, failover_dev)) return NOTIFY_OK; done: return NOTIFY_DONE; } EXPORT_SYMBOL_GPL(failover_slave_unregister); static int failover_slave_link_change(struct net_device *slave_dev) { struct net_device *failover_dev; struct failover_ops *fops; if (!netif_is_failover_slave(slave_dev)) goto done; ASSERT_RTNL(); failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); if (!failover_dev) goto done; if (!netif_running(failover_dev)) goto done; if (fops && fops->slave_link_change && !fops->slave_link_change(slave_dev, failover_dev)) return NOTIFY_OK; done: return NOTIFY_DONE; } static int failover_slave_name_change(struct net_device *slave_dev) { struct net_device *failover_dev; struct failover_ops *fops; if (!netif_is_failover_slave(slave_dev)) goto done; ASSERT_RTNL(); failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); if (!failover_dev) goto done; if (!netif_running(failover_dev)) goto done; if (fops && fops->slave_name_change && !fops->slave_name_change(slave_dev, failover_dev)) return NOTIFY_OK; done: return NOTIFY_DONE; } static int failover_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); /* Skip parent events */ if (netif_is_failover(event_dev)) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: return failover_slave_register(event_dev); case NETDEV_UNREGISTER: return failover_slave_unregister(event_dev); case NETDEV_UP: case NETDEV_DOWN: case NETDEV_CHANGE: return failover_slave_link_change(event_dev); case NETDEV_CHANGENAME: return failover_slave_name_change(event_dev); default: return NOTIFY_DONE; } } static struct notifier_block failover_notifier = { .notifier_call = failover_event, }; static void failover_existing_slave_register(struct net_device *failover_dev) { struct net *net = dev_net(failover_dev); struct net_device *dev; rtnl_lock(); for_each_netdev(net, dev) { if (netif_is_failover(dev)) continue; if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr)) failover_slave_register(dev); } rtnl_unlock(); } /** * failover_register - Register a failover instance * * @dev: failover netdev * @ops: failover ops * * Allocate and register a failover instance for a failover netdev. ops * provides handlers for slave device register/unregister/link change/ * name change events. * * Return: pointer to failover instance */ struct failover *failover_register(struct net_device *dev, struct failover_ops *ops) { struct failover *failover; if (dev->type != ARPHRD_ETHER) return ERR_PTR(-EINVAL); failover = kzalloc(sizeof(*failover), GFP_KERNEL); if (!failover) return ERR_PTR(-ENOMEM); rcu_assign_pointer(failover->ops, ops); netdev_hold(dev, &failover->dev_tracker, GFP_KERNEL); dev->priv_flags |= IFF_FAILOVER; rcu_assign_pointer(failover->failover_dev, dev); spin_lock(&failover_lock); list_add_tail(&failover->list, &failover_list); spin_unlock(&failover_lock); netdev_info(dev, "failover master:%s registered\n", dev->name); failover_existing_slave_register(dev); return failover; } EXPORT_SYMBOL_GPL(failover_register); /** * failover_unregister - Unregister a failover instance * * @failover: pointer to failover instance * * Unregisters and frees a failover instance. */ void failover_unregister(struct failover *failover) { struct net_device *failover_dev; failover_dev = rcu_dereference(failover->failover_dev); netdev_info(failover_dev, "failover master:%s unregistered\n", failover_dev->name); failover_dev->priv_flags &= ~IFF_FAILOVER; netdev_put(failover_dev, &failover->dev_tracker); spin_lock(&failover_lock); list_del(&failover->list); spin_unlock(&failover_lock); kfree(failover); } EXPORT_SYMBOL_GPL(failover_unregister); static __init int failover_init(void) { register_netdevice_notifier(&failover_notifier); return 0; } module_init(failover_init); static __exit void failover_exit(void) { unregister_netdevice_notifier(&failover_notifier); } module_exit(failover_exit); MODULE_DESCRIPTION("Generic failover infrastructure/interface"); MODULE_LICENSE("GPL v2"); |
| 20 20 20 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 fragment reassembly for connection tracking * * Copyright (C)2004 USAGI/WIDE Project * * Author: * Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> * * Based on: net/ipv6/reassembly.c */ #define pr_fmt(fmt) "IPv6-nf: " fmt #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/ipv6.h> #include <linux/slab.h> #include <net/ipv6_frag.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> #include <linux/sysctl.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/kernel.h> #include <linux/module.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/netns/generic.h> static const char nf_frags_cache_name[] = "nf-frags"; static unsigned int nf_frag_pernet_id __read_mostly; static struct inet_frags nf_frags; static struct nft_ct_frag6_pernet *nf_frag_pernet(struct net *net) { return net_generic(net, nf_frag_pernet_id); } #ifdef CONFIG_SYSCTL static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_frag6_low_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "nf_conntrack_frag6_high_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; static int nf_ct_frag6_sysctl_register(struct net *net) { struct nft_ct_frag6_pernet *nf_frag; struct ctl_table *table; struct ctl_table_header *hdr; table = nf_ct_frag6_sysctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(nf_ct_frag6_sysctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; } nf_frag = nf_frag_pernet(net); table[0].data = &nf_frag->fqdir->timeout; table[1].data = &nf_frag->fqdir->low_thresh; table[1].extra2 = &nf_frag->fqdir->high_thresh; table[2].data = &nf_frag->fqdir->high_thresh; table[2].extra1 = &nf_frag->fqdir->low_thresh; hdr = register_net_sysctl_sz(net, "net/netfilter", table, ARRAY_SIZE(nf_ct_frag6_sysctl_table)); if (hdr == NULL) goto err_reg; nf_frag->nf_frag_frags_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); const struct ctl_table *table; table = nf_frag->nf_frag_frags_hdr->ctl_table_arg; unregister_net_sysctl_table(nf_frag->nf_frag_frags_hdr); if (!net_eq(net, &init_net)) kfree(table); } #else static int nf_ct_frag6_sysctl_register(struct net *net) { return 0; } static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) { } #endif static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev); static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) { return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); } static void nf_ct_frag6_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; fq = container_of(frag, struct frag_queue, q); ip6frag_expire_frag_queue(fq->q.fqdir->net, fq); } /* Creation primitives. */ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, const struct ipv6hdr *hdr, int iif) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); struct frag_v6_compare_key key = { .id = id, .saddr = hdr->saddr, .daddr = hdr->daddr, .user = user, .iif = iif, }; struct inet_frag_queue *q; if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL))) key.iif = 0; q = inet_frag_find(nf_frag->fqdir, &key); if (!q) return NULL; return container_of(q, struct frag_queue, q); } static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, const struct frag_hdr *fhdr, int nhoff) { unsigned int payload_len; struct net_device *dev; struct sk_buff *prev; int offset, end, err; u8 ecn; if (fq->q.flags & INET_FRAG_COMPLETE) { pr_debug("Already completed\n"); goto err; } payload_len = ntohs(ipv6_hdr(skb)->payload_len); offset = ntohs(fhdr->frag_off) & ~0x7; end = offset + (payload_len - ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { pr_debug("offset is too large.\n"); return -EINVAL; } ecn = ip6_frag_ecn(ipv6_hdr(skb)); if (skb->ip_summed == CHECKSUM_COMPLETE) { const unsigned char *nh = skb_network_header(skb); skb->csum = csum_sub(skb->csum, csum_partial(nh, (u8 *)(fhdr + 1) - nh, 0)); } /* Is this the final fragment? */ if (!(fhdr->frag_off & htons(IP6_MF))) { /* If we already have some bits beyond end * or have different end, the segment is corrupted. */ if (end < fq->q.len || ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) { pr_debug("already received last fragment\n"); goto err; } fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { /* Check if the fragment is rounded to 8 bytes. * Required by the RFC. */ if (end & 0x7) { /* RFC2460 says always send parameter problem in * this case. -DaveM */ pr_debug("end of fragment not rounded to 8 bytes.\n"); inet_frag_kill(&fq->q); return -EPROTO; } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ if (fq->q.flags & INET_FRAG_LAST_IN) { pr_debug("last packet already reached.\n"); goto err; } fq->q.len = end; } } if (end == offset) goto err; /* Point into the IP datagram 'data' part. */ if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) { pr_debug("queue: message is too short.\n"); goto err; } if (pskb_trim_rcsum(skb, end - offset)) { pr_debug("Can't trim\n"); goto err; } /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier(); prev = fq->q.fragments_tail; err = inet_frag_queue_insert(&fq->q, skb, offset, end); if (err) { if (err == IPFRAG_DUP) { /* No error for duplicates, pretend they got queued. */ kfree_skb_reason(skb, SKB_DROP_REASON_DUP_FRAG); return -EINPROGRESS; } goto insert_error; } if (dev) fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; fq->q.tstamp_type = skb->tstamp_type; fq->q.meat += skb->len; fq->ecn |= ecn; if (payload_len > fq->q.max_size) fq->q.max_size = payload_len; add_frag_mem_limit(fq->q.fqdir, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. */ if (offset == 0) { fq->nhoffset = nhoff; fq->q.flags |= INET_FRAG_FIRST_IN; } if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; err = nf_ct_frag6_reasm(fq, skb, prev, dev); skb->_skb_refdst = orefdst; /* After queue has assumed skb ownership, only 0 or * -EINPROGRESS must be returned. */ return err ? -EINPROGRESS : 0; } skb_dst_drop(skb); skb_orphan(skb); return -EINPROGRESS; insert_error: inet_frag_kill(&fq->q); err: skb_dst_drop(skb); return -EINVAL; } /* * Check if this packet is complete. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev) { void *reasm_data; int payload_len; u8 ecn; inet_frag_kill(&fq->q); ecn = ip_frag_ecn_table[fq->ecn]; if (unlikely(ecn == 0xff)) goto err; reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); if (!reasm_data) goto err; payload_len = -skb_network_offset(skb) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr); if (payload_len > IPV6_MAXPLEN) { net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", payload_len); goto err; } /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0]; memmove(skb->head + sizeof(struct frag_hdr), skb->head, (skb->data - skb->head) - sizeof(struct frag_hdr)); skb->mac_header += sizeof(struct frag_hdr); skb->network_header += sizeof(struct frag_hdr); skb_reset_transport_header(skb); inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); skb->ignore_df = 1; skb->dev = dev; ipv6_hdr(skb)->payload_len = htons(payload_len); ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; /* Yes, and fold redundant checksum back. 8) */ if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_partial(skb_network_header(skb), skb_network_header_len(skb), skb->csum); fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; fq->q.last_run_head = NULL; return 0; err: inet_frag_kill(&fq->q); return -EINVAL; } /* * find the header just before Fragment Header. * * if success return 0 and set ... * (*prevhdrp): the value of "Next Header Field" in the header * just before Fragment Header. * (*prevhoff): the offset of "Next Header Field" in the header * just before Fragment Header. * (*fhoff) : the offset of Fragment Header. * * Based on ipv6_skip_hdr() in net/ipv6/exthdr.c * */ static int find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) { u8 nexthdr = ipv6_hdr(skb)->nexthdr; const int netoff = skb_network_offset(skb); u8 prev_nhoff = netoff + offsetof(struct ipv6hdr, nexthdr); int start = netoff + sizeof(struct ipv6hdr); int len = skb->len - start; u8 prevhdr = NEXTHDR_IPV6; while (nexthdr != NEXTHDR_FRAGMENT) { struct ipv6_opt_hdr hdr; int hdrlen; if (!ipv6_ext_hdr(nexthdr)) { return -1; } if (nexthdr == NEXTHDR_NONE) { pr_debug("next header is none\n"); return -1; } if (len < (int)sizeof(struct ipv6_opt_hdr)) { pr_debug("too short\n"); return -1; } if (skb_copy_bits(skb, start, &hdr, sizeof(hdr))) BUG(); if (nexthdr == NEXTHDR_AUTH) hdrlen = ipv6_authlen(&hdr); else hdrlen = ipv6_optlen(&hdr); prevhdr = nexthdr; prev_nhoff = start; nexthdr = hdr.nexthdr; len -= hdrlen; start += hdrlen; } if (len < 0) return -1; *prevhdrp = prevhdr; *prevhoff = prev_nhoff; *fhoff = start; return 0; } int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { u16 savethdr = skb->transport_header; u8 nexthdr = NEXTHDR_FRAGMENT; int fhoff, nhoff, ret; struct frag_hdr *fhdr; struct frag_queue *fq; struct ipv6hdr *hdr; u8 prevhdr; /* Jumbo payload inhibits frag. header */ if (ipv6_hdr(skb)->payload_len == 0) { pr_debug("payload len = 0\n"); return 0; } if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) return 0; /* Discard the first fragment if it does not include all headers * RFC 8200, Section 4.5 */ if (ipv6frag_thdr_truncated(skb, fhoff, &nexthdr)) { pr_debug("Drop incomplete fragment\n"); return 0; } if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) return -ENOMEM; skb_set_transport_header(skb, fhoff); hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); fq = fq_find(net, fhdr->identification, user, hdr, skb->dev ? skb->dev->ifindex : 0); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); return -ENOMEM; } spin_lock_bh(&fq->q.lock); ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff); if (ret == -EPROTO) { skb->transport_header = savethdr; ret = 0; } spin_unlock_bh(&fq->q.lock); inet_frag_put(&fq->q); return ret; } EXPORT_SYMBOL_GPL(nf_ct_frag6_gather); static int nf_ct_net_init(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); int res; res = fqdir_init(&nf_frag->fqdir, &nf_frags, net); if (res < 0) return res; nf_frag->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; nf_frag->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; nf_frag->fqdir->timeout = IPV6_FRAG_TIMEOUT; res = nf_ct_frag6_sysctl_register(net); if (res < 0) fqdir_exit(nf_frag->fqdir); return res; } static void nf_ct_net_pre_exit(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); fqdir_pre_exit(nf_frag->fqdir); } static void nf_ct_net_exit(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); nf_ct_frags6_sysctl_unregister(net); fqdir_exit(nf_frag->fqdir); } static struct pernet_operations nf_ct_net_ops = { .init = nf_ct_net_init, .pre_exit = nf_ct_net_pre_exit, .exit = nf_ct_net_exit, .id = &nf_frag_pernet_id, .size = sizeof(struct nft_ct_frag6_pernet), }; static const struct rhashtable_params nfct_rhash_params = { .head_offset = offsetof(struct inet_frag_queue, node), .hashfn = ip6frag_key_hashfn, .obj_hashfn = ip6frag_obj_hashfn, .obj_cmpfn = ip6frag_obj_cmpfn, .automatic_shrinking = true, }; int nf_ct_frag6_init(void) { int ret = 0; nf_frags.constructor = ip6frag_init; nf_frags.destructor = NULL; nf_frags.qsize = sizeof(struct frag_queue); nf_frags.frag_expire = nf_ct_frag6_expire; nf_frags.frags_cache_name = nf_frags_cache_name; nf_frags.rhash_params = nfct_rhash_params; ret = inet_frags_init(&nf_frags); if (ret) goto out; ret = register_pernet_subsys(&nf_ct_net_ops); if (ret) inet_frags_fini(&nf_frags); out: return ret; } void nf_ct_frag6_cleanup(void) { unregister_pernet_subsys(&nf_ct_net_ops); inet_frags_fini(&nf_frags); } |
| 2079 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Landlock LSM - Filesystem management and hooks * * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI */ #ifndef _SECURITY_LANDLOCK_FS_H #define _SECURITY_LANDLOCK_FS_H #include <linux/fs.h> #include <linux/init.h> #include <linux/rcupdate.h> #include "ruleset.h" #include "setup.h" /** * struct landlock_inode_security - Inode security blob * * Enable to reference a &struct landlock_object tied to an inode (i.e. * underlying object). */ struct landlock_inode_security { /** * @object: Weak pointer to an allocated object. All assignments of a * new object are protected by the underlying inode->i_lock. However, * atomically disassociating @object from the inode is only protected * by @object->lock, from the time @object's usage refcount drops to * zero to the time this pointer is nulled out (cf. release_inode() and * hook_sb_delete()). Indeed, such disassociation doesn't require * inode->i_lock thanks to the careful rcu_access_pointer() check * performed by get_inode_object(). */ struct landlock_object __rcu *object; }; /** * struct landlock_file_security - File security blob * * This information is populated when opening a file in hook_file_open, and * tracks the relevant Landlock access rights that were available at the time * of opening the file. Other LSM hooks use these rights in order to authorize * operations on already opened files. */ struct landlock_file_security { /** * @allowed_access: Access rights that were available at the time of * opening the file. This is not necessarily the full set of access * rights available at that time, but it's the necessary subset as * needed to authorize later operations on the open file. */ access_mask_t allowed_access; /** * @fown_domain: Domain of the task that set the PID that may receive a * signal e.g., SIGURG when writing MSG_OOB to the related socket. * This pointer is protected by the related file->f_owner->lock, as for * fown_struct's members: pid, uid, and euid. */ struct landlock_ruleset *fown_domain; }; /** * struct landlock_superblock_security - Superblock security blob * * Enable hook_sb_delete() to wait for concurrent calls to release_inode(). */ struct landlock_superblock_security { /** * @inode_refs: Number of pending inodes (from this superblock) that * are being released by release_inode(). * Cf. struct super_block->s_fsnotify_inode_refs . */ atomic_long_t inode_refs; }; static inline struct landlock_file_security * landlock_file(const struct file *const file) { return file->f_security + landlock_blob_sizes.lbs_file; } static inline struct landlock_inode_security * landlock_inode(const struct inode *const inode) { return inode->i_security + landlock_blob_sizes.lbs_inode; } static inline struct landlock_superblock_security * landlock_superblock(const struct super_block *const superblock) { return superblock->s_security + landlock_blob_sizes.lbs_superblock; } __init void landlock_add_fs_hooks(void); int landlock_append_fs_rule(struct landlock_ruleset *const ruleset, const struct path *const path, access_mask_t access_hierarchy); #endif /* _SECURITY_LANDLOCK_FS_H */ |
| 219 214 13 165 180 167 166 13 13 62 61 63 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 13 242 5 243 243 244 245 243 243 244 21 141 242 221 222 222 221 153 102 167 165 165 166 222 167 101 203 179 179 224 223 166 167 20 53 2 185 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic helpers for smp ipi calls * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/gfp.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/sched.h> #include <linux/sched/idle.h> #include <linux/hypervisor.h> #include <linux/sched/clock.h> #include <linux/nmi.h> #include <linux/sched/debug.h> #include <linux/jump_label.h> #include <linux/string_choices.h> #include <trace/events/ipi.h> #define CREATE_TRACE_POINTS #include <trace/events/csd.h> #undef CREATE_TRACE_POINTS #include "smpboot.h" #include "sched/smp.h" #define CSD_TYPE(_csd) ((_csd)->node.u_flags & CSD_FLAG_TYPE_MASK) struct call_function_data { call_single_data_t __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); static DEFINE_PER_CPU(atomic_t, trigger_backtrace) = ATOMIC_INIT(1); static void __flush_smp_call_function_queue(bool warn_cpu_offline); int smpcfd_prepare_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return -ENOMEM; if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, cpu_to_node(cpu))) { free_cpumask_var(cfd->cpumask); return -ENOMEM; } cfd->csd = alloc_percpu(call_single_data_t); if (!cfd->csd) { free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; } return 0; } int smpcfd_dead_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); free_percpu(cfd->csd); return 0; } int smpcfd_dying_cpu(unsigned int cpu) { /* * The IPIs for the smp-call-function callbacks queued by other * CPUs might arrive late, either due to hardware latencies or * because this CPU disabled interrupts (inside stop-machine) * before the IPIs were sent. So flush out any pending callbacks * explicitly (without waiting for the IPIs to arrive), to * ensure that the outgoing CPU doesn't go offline with work * still pending. */ __flush_smp_call_function_queue(false); irq_work_run(); return 0; } void __init call_function_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(call_single_queue, i)); smpcfd_prepare_cpu(smp_processor_id()); } static __always_inline void send_call_function_single_ipi(int cpu) { if (call_function_single_prep_ipi(cpu)) { trace_ipi_send_cpu(cpu, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_single_ipi(cpu); } } static __always_inline void send_call_function_ipi_mask(struct cpumask *mask) { trace_ipi_send_cpumask(mask, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_ipi_mask(mask); } static __always_inline void csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd) { trace_csd_function_entry(func, csd); func(info); trace_csd_function_exit(func, csd); } #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled); /* * Parse the csdlock_debug= kernel boot parameter. * * If you need to restore the old "ext" value that once provided * additional debugging information, reapply the following commits: * * de7b09ef658d ("locking/csd_lock: Prepare more CSD lock debugging") * a5aabace5fb8 ("locking/csd_lock: Add more data to CSD lock debugging") */ static int __init csdlock_debug(char *str) { int ret; unsigned int val = 0; ret = get_option(&str, &val); if (ret) { if (val) static_branch_enable(&csdlock_debug_enabled); else static_branch_disable(&csdlock_debug_enabled); } return 1; } __setup("csdlock_debug=", csdlock_debug); static DEFINE_PER_CPU(call_single_data_t *, cur_csd); static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */ module_param(csd_lock_timeout, ulong, 0444); static int panic_on_ipistall; /* CSD panic timeout in milliseconds, 300000 for five minutes. */ module_param(panic_on_ipistall, int, 0444); static atomic_t csd_bug_count = ATOMIC_INIT(0); /* Record current CSD work for current CPU, NULL to erase. */ static void __csd_lock_record(call_single_data_t *csd) { if (!csd) { smp_mb(); /* NULL cur_csd after unlock. */ __this_cpu_write(cur_csd, NULL); return; } __this_cpu_write(cur_csd_func, csd->func); __this_cpu_write(cur_csd_info, csd->info); smp_wmb(); /* func and info before csd. */ __this_cpu_write(cur_csd, csd); smp_mb(); /* Update cur_csd before function call. */ /* Or before unlock, as the case may be. */ } static __always_inline void csd_lock_record(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) __csd_lock_record(csd); } static int csd_lock_wait_getcpu(call_single_data_t *csd) { unsigned int csd_type; csd_type = CSD_TYPE(csd); if (csd_type == CSD_TYPE_ASYNC || csd_type == CSD_TYPE_SYNC) return csd->node.dst; /* Other CSD_TYPE_ values might not have ->dst. */ return -1; } static atomic_t n_csd_lock_stuck; /** * csd_lock_is_stuck - Has a CSD-lock acquisition been stuck too long? * * Returns @true if a CSD-lock acquisition is stuck and has been stuck * long enough for a "non-responsive CSD lock" message to be printed. */ bool csd_lock_is_stuck(void) { return !!atomic_read(&n_csd_lock_stuck); } /* * Complain if too much time spent waiting. Note that only * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, * so waiting on other types gets much less information. */ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id, unsigned long *nmessages) { int cpu = -1; int cpux; bool firsttime; u64 ts2, ts_delta; call_single_data_t *cpu_cur_csd; unsigned int flags = READ_ONCE(csd->node.u_flags); unsigned long long csd_lock_timeout_ns = csd_lock_timeout * NSEC_PER_MSEC; if (!(flags & CSD_FLAG_LOCK)) { if (!unlikely(*bug_id)) return true; cpu = csd_lock_wait_getcpu(csd); pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n", *bug_id, raw_smp_processor_id(), cpu); atomic_dec(&n_csd_lock_stuck); return true; } ts2 = sched_clock(); /* How long since we last checked for a stuck CSD lock.*/ ts_delta = ts2 - *ts1; if (likely(ts_delta <= csd_lock_timeout_ns * (*nmessages + 1) * (!*nmessages ? 1 : (ilog2(num_online_cpus()) / 2 + 1)) || csd_lock_timeout_ns == 0)) return false; if (ts0 > ts2) { /* Our own sched_clock went backward; don't blame another CPU. */ ts_delta = ts0 - ts2; pr_alert("sched_clock on CPU %d went backward by %llu ns\n", raw_smp_processor_id(), ts_delta); *ts1 = ts2; return false; } firsttime = !*bug_id; if (firsttime) *bug_id = atomic_inc_return(&csd_bug_count); cpu = csd_lock_wait_getcpu(csd); if (WARN_ONCE(cpu < 0 || cpu >= nr_cpu_ids, "%s: cpu = %d\n", __func__, cpu)) cpux = 0; else cpux = cpu; cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */ /* How long since this CSD lock was stuck. */ ts_delta = ts2 - ts0; pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %lld ns for CPU#%02d %pS(%ps).\n", firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), (s64)ts_delta, cpu, csd->func, csd->info); (*nmessages)++; if (firsttime) atomic_inc(&n_csd_lock_stuck); /* * If the CSD lock is still stuck after 5 minutes, it is unlikely * to become unstuck. Use a signed comparison to avoid triggering * on underflows when the TSC is out of sync between sockets. */ BUG_ON(panic_on_ipistall > 0 && (s64)ts_delta > ((s64)panic_on_ipistall * NSEC_PER_MSEC)); if (cpu_cur_csd && csd != cpu_cur_csd) { pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n", *bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)), READ_ONCE(per_cpu(cur_csd_info, cpux))); } else { pr_alert("\tcsd: CSD lock (#%d) %s.\n", *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request"); } if (cpu >= 0) { if (atomic_cmpxchg_acquire(&per_cpu(trigger_backtrace, cpu), 1, 0)) dump_cpu_task(cpu); if (!cpu_cur_csd) { pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu); arch_send_call_function_single_ipi(cpu); } } if (firsttime) dump_stack(); *ts1 = ts2; return false; } /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources * * For non-synchronous ipi calls the csd can still be in use by the * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ static void __csd_lock_wait(call_single_data_t *csd) { unsigned long nmessages = 0; int bug_id = 0; u64 ts0, ts1; ts1 = ts0 = sched_clock(); for (;;) { if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id, &nmessages)) break; cpu_relax(); } smp_acquire__after_ctrl_dep(); } static __always_inline void csd_lock_wait(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) { __csd_lock_wait(csd); return; } smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #else static void csd_lock_record(call_single_data_t *csd) { } static __always_inline void csd_lock_wait(call_single_data_t *csd) { smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #endif static __always_inline void csd_lock(call_single_data_t *csd) { csd_lock_wait(csd); csd->node.u_flags |= CSD_FLAG_LOCK; /* * prevent CPU from reordering the above assignment * to ->flags with any subsequent assignments to other * fields of the specified call_single_data_t structure: */ smp_wmb(); } static __always_inline void csd_unlock(call_single_data_t *csd) { WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: */ smp_store_release(&csd->node.u_flags, 0); } static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); void __smp_call_single_queue(int cpu, struct llist_node *node) { /* * We have to check the type of the CSD before queueing it, because * once queued it can have its flags cleared by * flush_smp_call_function_queue() * even if we haven't sent the smp_call IPI yet (e.g. the stopper * executes migration_cpu_stop() on the remote CPU). */ if (trace_csd_queue_cpu_enabled()) { call_single_data_t *csd; smp_call_func_t func; csd = container_of(node, call_single_data_t, node.llist); func = CSD_TYPE(csd) == CSD_TYPE_TTWU ? sched_ttwu_pending : csd->func; trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); } /* * The list addition should be visible to the target CPU when it pops * the head of the list to pull the entry off it in the IPI handler * because of normal cache coherency rules implied by the underlying * llist ops. * * If IPIs can go out of order to the cache coherency protocol * in an architecture, sufficient synchronisation should be added * to arch code to make it appear to obey cache coherency WRT * locking and barrier primitives. Generic code isn't really * equipped to do the right thing... */ if (llist_add(node, &per_cpu(call_single_queue, cpu))) send_call_function_single_ipi(cpu); } /* * Insert a previously allocated call_single_data_t element * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ static int generic_exec_single(int cpu, call_single_data_t *csd) { if (cpu == smp_processor_id()) { smp_call_func_t func = csd->func; void *info = csd->info; unsigned long flags; /* * We can unlock early even for the synchronous on-stack case, * since we're doing this from the same CPU.. */ csd_lock_record(csd); csd_unlock(csd); local_irq_save(flags); csd_do_func(func, info, NULL); csd_lock_record(NULL); local_irq_restore(flags); return 0; } if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) { csd_unlock(csd); return -ENXIO; } __smp_call_single_queue(cpu, &csd->node.llist); return 0; } /** * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks * * Invoked by arch to handle an IPI for call function single. * Must be called with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { __flush_smp_call_function_queue(true); } /** * __flush_smp_call_function_queue - Flush pending smp-call-function callbacks * * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an * offline CPU. Skip this check if set to 'false'. * * Flush any pending smp-call-function callbacks queued on this CPU. This is * invoked by the generic IPI handler, as well as by a CPU about to go offline, * to ensure that all pending IPI callbacks are run before it goes completely * offline. * * Loop through the call_single_queue and run all the queued callbacks. * Must be called with interrupts disabled. */ static void __flush_smp_call_function_queue(bool warn_cpu_offline) { call_single_data_t *csd, *csd_next; struct llist_node *entry, *prev; struct llist_head *head; static bool warned; atomic_t *tbt; lockdep_assert_irqs_disabled(); /* Allow waiters to send backtrace NMI from here onwards */ tbt = this_cpu_ptr(&trigger_backtrace); atomic_set_release(tbt, 1); head = this_cpu_ptr(&call_single_queue); entry = llist_del_all(head); entry = llist_reverse_order(entry); /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); /* * We don't have to use the _safe() variant here * because we are not invoking the IPI handlers yet. */ llist_for_each_entry(csd, entry, node.llist) { switch (CSD_TYPE(csd)) { case CSD_TYPE_ASYNC: case CSD_TYPE_SYNC: case CSD_TYPE_IRQ_WORK: pr_warn("IPI callback %pS sent to offline CPU\n", csd->func); break; case CSD_TYPE_TTWU: pr_warn("IPI task-wakeup sent to offline CPU\n"); break; default: pr_warn("IPI callback, unknown type %d, sent to offline CPU\n", CSD_TYPE(csd)); break; } } } /* * First; run all SYNC callbacks, people are waiting for us. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { /* Do we wait until *after* callback? */ if (CSD_TYPE(csd) == CSD_TYPE_SYNC) { smp_call_func_t func = csd->func; void *info = csd->info; if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } csd_lock_record(csd); csd_do_func(func, info, csd); csd_unlock(csd); csd_lock_record(NULL); } else { prev = &csd->node.llist; } } if (!entry) return; /* * Second; run all !SYNC callbacks. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { int type = CSD_TYPE(csd); if (type != CSD_TYPE_TTWU) { if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } if (type == CSD_TYPE_ASYNC) { smp_call_func_t func = csd->func; void *info = csd->info; csd_lock_record(csd); csd_unlock(csd); csd_do_func(func, info, csd); csd_lock_record(NULL); } else if (type == CSD_TYPE_IRQ_WORK) { irq_work_single(csd); } } else { prev = &csd->node.llist; } } /* * Third; only CSD_TYPE_TTWU is left, issue those. */ if (entry) { csd = llist_entry(entry, typeof(*csd), node.llist); csd_do_func(sched_ttwu_pending, entry, csd); } } /** * flush_smp_call_function_queue - Flush pending smp-call-function callbacks * from task context (idle, migration thread) * * When TIF_POLLING_NRFLAG is supported and a CPU is in idle and has it * set, then remote CPUs can avoid sending IPIs and wake the idle CPU by * setting TIF_NEED_RESCHED. The idle task on the woken up CPU has to * handle queued SMP function calls before scheduling. * * The migration thread has to ensure that an eventually pending wakeup has * been handled before it migrates a task. */ void flush_smp_call_function_queue(void) { unsigned int was_pending; unsigned long flags; if (llist_empty(this_cpu_ptr(&call_single_queue))) return; local_irq_save(flags); /* Get the already pending soft interrupts for RT enabled kernels */ was_pending = local_softirq_pending(); __flush_smp_call_function_queue(true); if (local_softirq_pending()) do_softirq_post_smp_call_flush(was_pending); local_irq_restore(flags); } /* * smp_call_function_single - Run a function on a specific CPU * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed on other CPUs. * * Returns 0 on success, else a negative status code. */ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, int wait) { call_single_data_t *csd; call_single_data_t csd_stack = { .node = { .u_flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC, }, }; int this_cpu; int err; /* * prevent preemption and reschedule on another processor, * as well as CPU removal */ this_cpu = get_cpu(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); csd = &csd_stack; if (!wait) { csd = this_cpu_ptr(&csd_data); csd_lock(csd); } csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif err = generic_exec_single(cpu, csd); if (wait) csd_lock_wait(csd); put_cpu(); return err; } EXPORT_SYMBOL(smp_call_function_single); /** * smp_call_function_single_async() - Run an asynchronous function on a * specific CPU. * @cpu: The CPU to run on. * @csd: Pre-allocated and setup data structure * * Like smp_call_function_single(), but the call is asynchonous and * can thus be done from contexts with disabled interrupts. * * The caller passes his own pre-allocated data structure * (ie: embedded in an object) and is responsible for synchronizing it * such that the IPIs performed on the @csd are strictly serialized. * * If the function is called with one csd which has not yet been * processed by previous call to smp_call_function_single_async(), the * function will return immediately with -EBUSY showing that the csd * object is still in progress. * * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. * * Return: %0 on success or negative errno value on error */ int smp_call_function_single_async(int cpu, call_single_data_t *csd) { int err = 0; preempt_disable(); if (csd->node.u_flags & CSD_FLAG_LOCK) { err = -EBUSY; goto out; } csd->node.u_flags = CSD_FLAG_LOCK; smp_wmb(); err = generic_exec_single(cpu, csd); out: preempt_enable(); return err; } EXPORT_SYMBOL_GPL(smp_call_function_single_async); /* * smp_call_function_any - Run a function on any of the given cpus * @mask: The mask of cpus it can run on. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed. * * Returns 0 on success, else a negative status code (if no cpus were online). * * Selection preference: * 1) current cpu if in @mask * 2) any cpu of current node if in @mask * 3) any other online cpu in @mask */ int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { unsigned int cpu; const struct cpumask *nodemask; int ret; /* Try for same CPU (cheapest) */ cpu = get_cpu(); if (cpumask_test_cpu(cpu, mask)) goto call; /* Try for same node. */ nodemask = cpumask_of_node(cpu_to_node(cpu)); for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids; cpu = cpumask_next_and(cpu, nodemask, mask)) { if (cpu_online(cpu)) goto call; } /* Any online will do: smp_call_function_single handles nr_cpu_ids. */ cpu = cpumask_any_and(mask, cpu_online_mask); call: ret = smp_call_function_single(cpu, func, info, wait); put_cpu(); return ret; } EXPORT_SYMBOL_GPL(smp_call_function_any); /* * Flags to be used as scf_flags argument of smp_call_function_many_cond(). * * %SCF_WAIT: Wait until function execution is completed * %SCF_RUN_LOCAL: Run also locally if local cpu is set in cpumask */ #define SCF_WAIT (1U << 0) #define SCF_RUN_LOCAL (1U << 1) static void smp_call_function_many_cond(const struct cpumask *mask, smp_call_func_t func, void *info, unsigned int scf_flags, smp_cond_func_t cond_func) { int cpu, last_cpu, this_cpu = smp_processor_id(); struct call_function_data *cfd; bool wait = scf_flags & SCF_WAIT; int nr_cpus = 0; bool run_remote = false; bool run_local = false; lockdep_assert_preemption_disabled(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ if (cpu_online(this_cpu) && !oops_in_progress && !early_boot_irqs_disabled) lockdep_assert_irqs_enabled(); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); /* Check if we need local execution. */ if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask)) run_local = true; /* Check if we need remote execution, i.e., any CPU excluding this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); if (cpu < nr_cpu_ids) run_remote = true; if (run_remote) { cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); __cpumask_clear_cpu(this_cpu, cfd->cpumask); cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); if (cond_func && !cond_func(cpu, info)) { __cpumask_clear_cpu(cpu, cfd->cpumask); continue; } csd_lock(csd); if (wait) csd->node.u_flags |= CSD_TYPE_SYNC; csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) { __cpumask_set_cpu(cpu, cfd->cpumask_ipi); nr_cpus++; last_cpu = cpu; } } /* * Choose the most efficient way to send an IPI. Note that the * number of CPUs might be zero due to concurrent changes to the * provided mask. */ if (nr_cpus == 1) send_call_function_single_ipi(last_cpu); else if (likely(nr_cpus > 1)) send_call_function_ipi_mask(cfd->cpumask_ipi); } if (run_local && (!cond_func || cond_func(this_cpu, info))) { unsigned long flags; local_irq_save(flags); csd_do_func(func, info, NULL); local_irq_restore(flags); } if (run_remote && wait) { for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd; csd = per_cpu_ptr(cfd->csd, cpu); csd_lock_wait(csd); } } } /** * smp_call_function_many(): Run a function on a set of CPUs. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: Bitmask that controls the operation. If %SCF_WAIT is set, wait * (atomically) until function has completed on other CPUs. If * %SCF_RUN_LOCAL is set, the function will also be run locally * if the local CPU is set in the @cpumask. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. Preemption * must be disabled when calling this function. */ void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { smp_call_function_many_cond(mask, func, info, wait * SCF_WAIT, NULL); } EXPORT_SYMBOL(smp_call_function_many); /** * smp_call_function(): Run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * Returns 0. * * If @wait is true, then returns once @func has returned; otherwise * it returns just before the target cpu calls @func. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ void smp_call_function(smp_call_func_t func, void *info, int wait) { preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); } EXPORT_SYMBOL(smp_call_function); /* Setup configured maximum number of CPUs to activate */ unsigned int setup_max_cpus = NR_CPUS; EXPORT_SYMBOL(setup_max_cpus); /* * Setup routine for controlling SMP activation * * Command-line option of "nosmp" or "maxcpus=0" will disable SMP * activation entirely (the MPS table probe still happens, though). * * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer * greater than 0, limits the maximum number of CPUs activated in * SMP mode to <NUM>. */ void __weak __init arch_disable_smp_support(void) { } static int __init nosmp(char *str) { setup_max_cpus = 0; arch_disable_smp_support(); return 0; } early_param("nosmp", nosmp); /* this is hard limit */ static int __init nrcpus(char *str) { int nr_cpus; if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids) set_nr_cpu_ids(nr_cpus); return 0; } early_param("nr_cpus", nrcpus); static int __init maxcpus(char *str) { get_option(&str, &setup_max_cpus); if (setup_max_cpus == 0) arch_disable_smp_support(); return 0; } early_param("maxcpus", maxcpus); #if (NR_CPUS > 1) && !defined(CONFIG_FORCE_NR_CPUS) /* Setup number of possible processor ids */ unsigned int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); #endif /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ void __init setup_nr_cpu_ids(void) { set_nr_cpu_ids(find_last_bit(cpumask_bits(cpu_possible_mask), NR_CPUS) + 1); } /* Called by boot processor to activate the rest. */ void __init smp_init(void) { int num_nodes, num_cpus; idle_threads_init(); cpuhp_threads_init(); pr_info("Bringing up secondary CPUs ...\n"); bringup_nonboot_cpus(setup_max_cpus); num_nodes = num_online_nodes(); num_cpus = num_online_cpus(); pr_info("Brought up %d node%s, %d CPU%s\n", num_nodes, str_plural(num_nodes), num_cpus, str_plural(num_cpus)); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } /* * on_each_cpu_cond(): Call a function on each processor for which * the supplied function cond_func returns true, optionally waiting * for all the required CPUs to finish. This may include the local * processor. * @cond_func: A callback function that is passed a cpu id and * the info parameter. The function is called * with preemption disabled. The function should * return a blooean value indicating whether to IPI * the specified CPU. * @func: The function to run on all applicable CPUs. * This must be fast and non-blocking. * @info: An arbitrary pointer to pass to both functions. * @wait: If true, wait (atomically) until function has * completed on other CPUs. * * Preemption is disabled to protect against CPUs going offline but not online. * CPUs going online during the call will not be seen or sent an IPI. * * You must not call this function with disabled interrupts or * from a hardware interrupt handler or from a bottom half handler. */ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask) { unsigned int scf_flags = SCF_RUN_LOCAL; if (wait) scf_flags |= SCF_WAIT; preempt_disable(); smp_call_function_many_cond(mask, func, info, scf_flags, cond_func); preempt_enable(); } EXPORT_SYMBOL(on_each_cpu_cond_mask); static void do_nothing(void *unused) { } /** * kick_all_cpus_sync - Force all cpus out of idle * * Used to synchronize the update of pm_idle function pointer. It's * called after the pointer is updated and returns after the dummy * callback function has been executed on all cpus. The execution of * the function can only happen on the remote cpus after they have * left the idle function which had been called via pm_idle function * pointer. So it's guaranteed that nothing uses the previous pointer * anymore. */ void kick_all_cpus_sync(void) { /* Make sure the change is visible before we kick the cpus */ smp_mb(); smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(kick_all_cpus_sync); /** * wake_up_all_idle_cpus - break all cpus out of idle * wake_up_all_idle_cpus try to break all cpus which is in idle state even * including idle polling cpus, for non-idle cpus, we will do nothing * for them. */ void wake_up_all_idle_cpus(void) { int cpu; for_each_possible_cpu(cpu) { preempt_disable(); if (cpu != smp_processor_id() && cpu_online(cpu)) wake_up_if_idle(cpu); preempt_enable(); } } EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus); /** * struct smp_call_on_cpu_struct - Call a function on a specific CPU * @work: &work_struct * @done: &completion to signal * @func: function to call * @data: function's data argument * @ret: return value from @func * @cpu: target CPU (%-1 for any CPU) * * Used to call a function on a specific cpu and wait for it to return. * Optionally make sure the call is done on a specified physical cpu via vcpu * pinning in order to support virtualized environments. */ struct smp_call_on_cpu_struct { struct work_struct work; struct completion done; int (*func)(void *); void *data; int ret; int cpu; }; static void smp_call_on_cpu_callback(struct work_struct *work) { struct smp_call_on_cpu_struct *sscs; sscs = container_of(work, struct smp_call_on_cpu_struct, work); if (sscs->cpu >= 0) hypervisor_pin_vcpu(sscs->cpu); sscs->ret = sscs->func(sscs->data); if (sscs->cpu >= 0) hypervisor_pin_vcpu(-1); complete(&sscs->done); } int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys) { struct smp_call_on_cpu_struct sscs = { .done = COMPLETION_INITIALIZER_ONSTACK(sscs.done), .func = func, .data = par, .cpu = phys ? cpu : -1, }; INIT_WORK_ONSTACK(&sscs.work, smp_call_on_cpu_callback); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; queue_work_on(cpu, system_wq, &sscs.work); wait_for_completion(&sscs.done); destroy_work_on_stack(&sscs.work); return sscs.ret; } EXPORT_SYMBOL_GPL(smp_call_on_cpu); |
| 5 4 4 4 4 4 4 4 4 4 4 26 26 1 1 1 3 2 2 1 1 1 1 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 4 3 3 1 2 2 1 2 3 2 2 2 2 5 4 3 2 2 2 2 1 2 5 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 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 5 1 5 3 2 3 2 3 2 2 4 41 24 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/rtnetlink.h> #include <net/busy_poll.h> #include <net/net_namespace.h> #include <net/netdev_queues.h> #include <net/netdev_rx_queue.h> #include <net/sock.h> #include <net/xdp.h> #include <net/xdp_sock.h> #include "dev.h" #include "devmem.h" #include "netdev-genl-gen.h" struct netdev_nl_dump_ctx { unsigned long ifindex; unsigned int rxq_idx; unsigned int txq_idx; unsigned int napi_id; }; static struct netdev_nl_dump_ctx *netdev_dump_ctx(struct netlink_callback *cb) { NL_ASSERT_DUMP_CTX_FITS(struct netdev_nl_dump_ctx); return (struct netdev_nl_dump_ctx *)cb->ctx; } static int netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info) { u64 xsk_features = 0; u64 xdp_rx_meta = 0; void *hdr; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; #define XDP_METADATA_KFUNC(_, flag, __, xmo) \ if (netdev->xdp_metadata_ops && netdev->xdp_metadata_ops->xmo) \ xdp_rx_meta |= flag; XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC if (netdev->xsk_tx_metadata_ops) { if (netdev->xsk_tx_metadata_ops->tmo_fill_timestamp) xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP; if (netdev->xsk_tx_metadata_ops->tmo_request_checksum) xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM; } if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES, netdev->xdp_features, NETDEV_A_DEV_PAD) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, xdp_rx_meta, NETDEV_A_DEV_PAD) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES, xsk_features, NETDEV_A_DEV_PAD)) goto err_cancel_msg; if (netdev->xdp_features & NETDEV_XDP_ACT_XSK_ZEROCOPY) { if (nla_put_u32(rsp, NETDEV_A_DEV_XDP_ZC_MAX_SEGS, netdev->xdp_zc_max_segs)) goto err_cancel_msg; } genlmsg_end(rsp, hdr); return 0; err_cancel_msg: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } static void netdev_genl_dev_notify(struct net_device *netdev, int cmd) { struct genl_info info; struct sk_buff *ntf; if (!genl_has_listeners(&netdev_nl_family, dev_net(netdev), NETDEV_NLGRP_MGMT)) return; genl_info_init_ntf(&info, &netdev_nl_family, cmd); ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!ntf) return; if (netdev_nl_dev_fill(netdev, ntf, &info)) { nlmsg_free(ntf); return; } genlmsg_multicast_netns(&netdev_nl_family, dev_net(netdev), ntf, 0, NETDEV_NLGRP_MGMT, GFP_KERNEL); } int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info) { struct net_device *netdev; struct sk_buff *rsp; u32 ifindex; int err; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX)) return -EINVAL; ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) return -ENOMEM; rtnl_lock(); netdev = __dev_get_by_index(genl_info_net(info), ifindex); if (netdev) err = netdev_nl_dev_fill(netdev, rsp, info); else err = -ENODEV; rtnl_unlock(); if (err) goto err_free_msg; return genlmsg_reply(rsp, info); err_free_msg: nlmsg_free(rsp); return err; } int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; int err = 0; rtnl_lock(); for_each_netdev_dump(net, netdev, ctx->ifindex) { err = netdev_nl_dev_fill(netdev, skb, genl_info_dump(cb)); if (err < 0) break; } rtnl_unlock(); return err; } static int netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, const struct genl_info *info) { void *hdr; pid_t pid; if (WARN_ON_ONCE(!napi->dev)) return -EINVAL; if (!(napi->dev->flags & IFF_UP)) return 0; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; if (napi->napi_id >= MIN_NAPI_ID && nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id)) goto nla_put_failure; if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex)) goto nla_put_failure; if (napi->irq >= 0 && nla_put_u32(rsp, NETDEV_A_NAPI_IRQ, napi->irq)) goto nla_put_failure; if (napi->thread) { pid = task_pid_nr(napi->thread); if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid)) goto nla_put_failure; } genlmsg_end(rsp, hdr); return 0; nla_put_failure: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) { struct napi_struct *napi; struct sk_buff *rsp; u32 napi_id; int err; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_NAPI_ID)) return -EINVAL; napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]); rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) return -ENOMEM; rtnl_lock(); napi = napi_by_id(napi_id); if (napi) { err = netdev_nl_napi_fill_one(rsp, napi, info); } else { NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_NAPI_ID]); err = -ENOENT; } rtnl_unlock(); if (err) goto err_free_msg; return genlmsg_reply(rsp, info); err_free_msg: nlmsg_free(rsp); return err; } static int netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info, struct netdev_nl_dump_ctx *ctx) { struct napi_struct *napi; int err = 0; if (!(netdev->flags & IFF_UP)) return err; list_for_each_entry(napi, &netdev->napi_list, dev_list) { if (ctx->napi_id && napi->napi_id >= ctx->napi_id) continue; err = netdev_nl_napi_fill_one(rsp, napi, info); if (err) return err; ctx->napi_id = napi->napi_id; } return err; } int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); const struct genl_info *info = genl_info_dump(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; u32 ifindex = 0; int err = 0; if (info->attrs[NETDEV_A_NAPI_IFINDEX]) ifindex = nla_get_u32(info->attrs[NETDEV_A_NAPI_IFINDEX]); rtnl_lock(); if (ifindex) { netdev = __dev_get_by_index(net, ifindex); if (netdev) err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); else err = -ENODEV; } else { for_each_netdev_dump(net, netdev, ctx->ifindex) { err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); if (err < 0) break; ctx->napi_id = 0; } } rtnl_unlock(); return err; } static int netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { struct net_devmem_dmabuf_binding *binding; struct netdev_rx_queue *rxq; struct netdev_queue *txq; void *hdr; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; if (nla_put_u32(rsp, NETDEV_A_QUEUE_ID, q_idx) || nla_put_u32(rsp, NETDEV_A_QUEUE_TYPE, q_type) || nla_put_u32(rsp, NETDEV_A_QUEUE_IFINDEX, netdev->ifindex)) goto nla_put_failure; switch (q_type) { case NETDEV_QUEUE_TYPE_RX: rxq = __netif_get_rx_queue(netdev, q_idx); if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID, rxq->napi->napi_id)) goto nla_put_failure; binding = rxq->mp_params.mp_priv; if (binding && nla_put_u32(rsp, NETDEV_A_QUEUE_DMABUF, binding->id)) goto nla_put_failure; break; case NETDEV_QUEUE_TYPE_TX: txq = netdev_get_tx_queue(netdev, q_idx); if (txq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID, txq->napi->napi_id)) goto nla_put_failure; } genlmsg_end(rsp, hdr); return 0; nla_put_failure: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } static int netdev_nl_queue_validate(struct net_device *netdev, u32 q_id, u32 q_type) { switch (q_type) { case NETDEV_QUEUE_TYPE_RX: if (q_id >= netdev->real_num_rx_queues) return -EINVAL; return 0; case NETDEV_QUEUE_TYPE_TX: if (q_id >= netdev->real_num_tx_queues) return -EINVAL; } return 0; } static int netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { int err = 0; if (!(netdev->flags & IFF_UP)) return err; err = netdev_nl_queue_validate(netdev, q_idx, q_type); if (err) return err; return netdev_nl_queue_fill_one(rsp, netdev, q_idx, q_type, info); } int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info) { u32 q_id, q_type, ifindex; struct net_device *netdev; struct sk_buff *rsp; int err; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_ID) || GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_TYPE) || GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_IFINDEX)) return -EINVAL; q_id = nla_get_u32(info->attrs[NETDEV_A_QUEUE_ID]); q_type = nla_get_u32(info->attrs[NETDEV_A_QUEUE_TYPE]); ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]); rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) return -ENOMEM; rtnl_lock(); netdev = __dev_get_by_index(genl_info_net(info), ifindex); if (netdev) err = netdev_nl_queue_fill(rsp, netdev, q_id, q_type, info); else err = -ENODEV; rtnl_unlock(); if (err) goto err_free_msg; return genlmsg_reply(rsp, info); err_free_msg: nlmsg_free(rsp); return err; } static int netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info, struct netdev_nl_dump_ctx *ctx) { int err = 0; int i; if (!(netdev->flags & IFF_UP)) return err; for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) { err = netdev_nl_queue_fill_one(rsp, netdev, i, NETDEV_QUEUE_TYPE_RX, info); if (err) return err; ctx->rxq_idx = i++; } for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) { err = netdev_nl_queue_fill_one(rsp, netdev, i, NETDEV_QUEUE_TYPE_TX, info); if (err) return err; ctx->txq_idx = i++; } return err; } int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); const struct genl_info *info = genl_info_dump(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; u32 ifindex = 0; int err = 0; if (info->attrs[NETDEV_A_QUEUE_IFINDEX]) ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]); rtnl_lock(); if (ifindex) { netdev = __dev_get_by_index(net, ifindex); if (netdev) err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); else err = -ENODEV; } else { for_each_netdev_dump(net, netdev, ctx->ifindex) { err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); if (err < 0) break; ctx->rxq_idx = 0; ctx->txq_idx = 0; } } rtnl_unlock(); return err; } #define NETDEV_STAT_NOT_SET (~0ULL) static void netdev_nl_stats_add(void *_sum, const void *_add, size_t size) { const u64 *add = _add; u64 *sum = _sum; while (size) { if (*add != NETDEV_STAT_NOT_SET && *sum != NETDEV_STAT_NOT_SET) *sum += *add; sum++; add++; size -= 8; } } static int netdev_stat_put(struct sk_buff *rsp, unsigned int attr_id, u64 value) { if (value == NETDEV_STAT_NOT_SET) return 0; return nla_put_uint(rsp, attr_id, value); } static int netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx) { if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROPS, rx->hw_drops) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, rx->hw_drop_overruns) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, rx->csum_unnecessary) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_NONE, rx->csum_none) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_BAD, rx->csum_bad) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_PACKETS, rx->hw_gro_packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_BYTES, rx->hw_gro_bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS, rx->hw_gro_wire_packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES, rx->hw_gro_wire_bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS, rx->hw_drop_ratelimits)) return -EMSGSIZE; return 0; } static int netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx) { if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROPS, tx->hw_drops) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_ERRORS, tx->hw_drop_errors) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_CSUM_NONE, tx->csum_none) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_NEEDS_CSUM, tx->needs_csum) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_PACKETS, tx->hw_gso_packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_BYTES, tx->hw_gso_bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, tx->hw_gso_wire_packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, tx->hw_gso_wire_bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, tx->hw_drop_ratelimits) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_STOP, tx->stop) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_WAKE, tx->wake)) return -EMSGSIZE; return 0; } static int netdev_nl_stats_queue(struct net_device *netdev, struct sk_buff *rsp, u32 q_type, int i, const struct genl_info *info) { const struct netdev_stat_ops *ops = netdev->stat_ops; struct netdev_queue_stats_rx rx; struct netdev_queue_stats_tx tx; void *hdr; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex) || nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_TYPE, q_type) || nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_ID, i)) goto nla_put_failure; switch (q_type) { case NETDEV_QUEUE_TYPE_RX: memset(&rx, 0xff, sizeof(rx)); ops->get_queue_stats_rx(netdev, i, &rx); if (!memchr_inv(&rx, 0xff, sizeof(rx))) goto nla_cancel; if (netdev_nl_stats_write_rx(rsp, &rx)) goto nla_put_failure; break; case NETDEV_QUEUE_TYPE_TX: memset(&tx, 0xff, sizeof(tx)); ops->get_queue_stats_tx(netdev, i, &tx); if (!memchr_inv(&tx, 0xff, sizeof(tx))) goto nla_cancel; if (netdev_nl_stats_write_tx(rsp, &tx)) goto nla_put_failure; break; } genlmsg_end(rsp, hdr); return 0; nla_cancel: genlmsg_cancel(rsp, hdr); return 0; nla_put_failure: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } static int netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info, struct netdev_nl_dump_ctx *ctx) { const struct netdev_stat_ops *ops = netdev->stat_ops; int i, err; if (!(netdev->flags & IFF_UP)) return 0; i = ctx->rxq_idx; while (ops->get_queue_stats_rx && i < netdev->real_num_rx_queues) { err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_RX, i, info); if (err) return err; ctx->rxq_idx = i++; } i = ctx->txq_idx; while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_TX, i, info); if (err) return err; ctx->txq_idx = i++; } ctx->rxq_idx = 0; ctx->txq_idx = 0; return 0; } static int netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info) { struct netdev_queue_stats_rx rx_sum, rx; struct netdev_queue_stats_tx tx_sum, tx; const struct netdev_stat_ops *ops; void *hdr; int i; ops = netdev->stat_ops; /* Netdev can't guarantee any complete counters */ if (!ops->get_base_stats) return 0; memset(&rx_sum, 0xff, sizeof(rx_sum)); memset(&tx_sum, 0xff, sizeof(tx_sum)); ops->get_base_stats(netdev, &rx_sum, &tx_sum); /* The op was there, but nothing reported, don't bother */ if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) && !memchr_inv(&tx_sum, 0xff, sizeof(tx_sum))) return 0; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex)) goto nla_put_failure; for (i = 0; i < netdev->real_num_rx_queues; i++) { memset(&rx, 0xff, sizeof(rx)); if (ops->get_queue_stats_rx) ops->get_queue_stats_rx(netdev, i, &rx); netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx)); } for (i = 0; i < netdev->real_num_tx_queues; i++) { memset(&tx, 0xff, sizeof(tx)); if (ops->get_queue_stats_tx) ops->get_queue_stats_tx(netdev, i, &tx); netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx)); } if (netdev_nl_stats_write_rx(rsp, &rx_sum) || netdev_nl_stats_write_tx(rsp, &tx_sum)) goto nla_put_failure; genlmsg_end(rsp, hdr); return 0; nla_put_failure: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } static int netdev_nl_qstats_get_dump_one(struct net_device *netdev, unsigned int scope, struct sk_buff *skb, const struct genl_info *info, struct netdev_nl_dump_ctx *ctx) { if (!netdev->stat_ops) return 0; switch (scope) { case 0: return netdev_nl_stats_by_netdev(netdev, skb, info); case NETDEV_QSTATS_SCOPE_QUEUE: return netdev_nl_stats_by_queue(netdev, skb, info, ctx); } return -EINVAL; /* Should not happen, per netlink policy */ } int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); const struct genl_info *info = genl_info_dump(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; unsigned int ifindex; unsigned int scope; int err = 0; scope = 0; if (info->attrs[NETDEV_A_QSTATS_SCOPE]) scope = nla_get_uint(info->attrs[NETDEV_A_QSTATS_SCOPE]); ifindex = 0; if (info->attrs[NETDEV_A_QSTATS_IFINDEX]) ifindex = nla_get_u32(info->attrs[NETDEV_A_QSTATS_IFINDEX]); rtnl_lock(); if (ifindex) { netdev = __dev_get_by_index(net, ifindex); if (netdev && netdev->stat_ops) { err = netdev_nl_qstats_get_dump_one(netdev, scope, skb, info, ctx); } else { NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_QSTATS_IFINDEX]); err = netdev ? -EOPNOTSUPP : -ENODEV; } } else { for_each_netdev_dump(net, netdev, ctx->ifindex) { err = netdev_nl_qstats_get_dump_one(netdev, scope, skb, info, ctx); if (err < 0) break; } } rtnl_unlock(); return err; } int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[ARRAY_SIZE(netdev_queue_id_nl_policy)]; struct net_devmem_dmabuf_binding *binding; struct list_head *sock_binding_list; u32 ifindex, dmabuf_fd, rxq_idx; struct net_device *netdev; struct sk_buff *rsp; struct nlattr *attr; int rem, err = 0; void *hdr; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX) || GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_FD) || GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_QUEUES)) return -EINVAL; ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]); sock_binding_list = genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk); if (IS_ERR(sock_binding_list)) return PTR_ERR(sock_binding_list); rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) return -ENOMEM; hdr = genlmsg_iput(rsp, info); if (!hdr) { err = -EMSGSIZE; goto err_genlmsg_free; } rtnl_lock(); netdev = __dev_get_by_index(genl_info_net(info), ifindex); if (!netdev || !netif_device_present(netdev)) { err = -ENODEV; goto err_unlock; } if (dev_xdp_prog_count(netdev)) { NL_SET_ERR_MSG(info->extack, "unable to bind dmabuf to device with XDP program attached"); err = -EEXIST; goto err_unlock; } binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack); if (IS_ERR(binding)) { err = PTR_ERR(binding); goto err_unlock; } nla_for_each_attr_type(attr, NETDEV_A_DMABUF_QUEUES, genlmsg_data(info->genlhdr), genlmsg_len(info->genlhdr), rem) { err = nla_parse_nested( tb, ARRAY_SIZE(netdev_queue_id_nl_policy) - 1, attr, netdev_queue_id_nl_policy, info->extack); if (err < 0) goto err_unbind; if (NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_ID) || NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_TYPE)) { err = -EINVAL; goto err_unbind; } if (nla_get_u32(tb[NETDEV_A_QUEUE_TYPE]) != NETDEV_QUEUE_TYPE_RX) { NL_SET_BAD_ATTR(info->extack, tb[NETDEV_A_QUEUE_TYPE]); err = -EINVAL; goto err_unbind; } rxq_idx = nla_get_u32(tb[NETDEV_A_QUEUE_ID]); err = net_devmem_bind_dmabuf_to_queue(netdev, rxq_idx, binding, info->extack); if (err) goto err_unbind; } list_add(&binding->list, sock_binding_list); nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id); genlmsg_end(rsp, hdr); err = genlmsg_reply(rsp, info); if (err) goto err_unbind; rtnl_unlock(); return 0; err_unbind: net_devmem_unbind_dmabuf(binding); err_unlock: rtnl_unlock(); err_genlmsg_free: nlmsg_free(rsp); return err; } void netdev_nl_sock_priv_init(struct list_head *priv) { INIT_LIST_HEAD(priv); } void netdev_nl_sock_priv_destroy(struct list_head *priv) { struct net_devmem_dmabuf_binding *binding; struct net_devmem_dmabuf_binding *temp; list_for_each_entry_safe(binding, temp, priv, list) { rtnl_lock(); net_devmem_unbind_dmabuf(binding); rtnl_unlock(); } } static int netdev_genl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_REGISTER: netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_ADD_NTF); break; case NETDEV_UNREGISTER: netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_DEL_NTF); break; case NETDEV_XDP_FEAT_CHANGE: netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_CHANGE_NTF); break; } return NOTIFY_OK; } static struct notifier_block netdev_genl_nb = { .notifier_call = netdev_genl_netdevice_event, }; static int __init netdev_genl_init(void) { int err; err = register_netdevice_notifier(&netdev_genl_nb); if (err) return err; err = genl_register_family(&netdev_nl_family); if (err) goto err_unreg_ntf; return 0; err_unreg_ntf: unregister_netdevice_notifier(&netdev_genl_nb); return err; } subsys_initcall(netdev_genl_init); |
| 53 53 52 53 53 51 52 52 49 51 53 52 52 53 53 53 17 16 10 18 18 17 18 18 16 18 18 18 18 18 18 50 49 50 50 50 52 52 51 51 50 52 51 36 33 3 52 50 49 50 50 50 50 50 49 48 48 53 2 54 48 18 12 12 7 7 7 7 7 7 7 7 7 7 7 7 50 50 53 53 53 52 50 48 49 18 18 18 18 18 18 53 53 52 52 53 49 51 18 18 18 18 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001 Intel Corp. * Copyright (c) 2001 La Monte H.P. Yarroll * * This file is part of the SCTP kernel implementation * * This module provides the abstraction for an SCTP association. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@us.ibm.com> * Xingang Guo <xingang.guo@intel.com> * Hui Huang <hui.huang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Daisy Chang <daisyc@us.ibm.com> * Ryan Layer <rmlayer@us.ibm.com> * Kevin Gao <kevin.gao@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/fcntl.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/in.h> #include <net/ipv6.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> /* Forward declarations for internal functions. */ static void sctp_select_active_and_retran_path(struct sctp_association *asoc); static void sctp_assoc_bh_rcv(struct work_struct *work); static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc); static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc); /* 1st Level Abstractions. */ /* Initialize a new association from provided memory. */ static struct sctp_association *sctp_association_init( struct sctp_association *asoc, const struct sctp_endpoint *ep, const struct sock *sk, enum sctp_scope scope, gfp_t gfp) { struct sctp_sock *sp; struct sctp_paramhdr *p; int i; /* Retrieve the SCTP per socket area. */ sp = sctp_sk((struct sock *)sk); /* Discarding const is appropriate here. */ asoc->ep = (struct sctp_endpoint *)ep; asoc->base.sk = (struct sock *)sk; asoc->base.net = sock_net(sk); sctp_endpoint_hold(asoc->ep); sock_hold(asoc->base.sk); /* Initialize the common base substructure. */ asoc->base.type = SCTP_EP_TYPE_ASSOCIATION; /* Initialize the object handling fields. */ refcount_set(&asoc->base.refcnt, 1); /* Initialize the bind addr area. */ sctp_bind_addr_init(&asoc->base.bind_addr, ep->base.bind_addr.port); asoc->state = SCTP_STATE_CLOSED; asoc->cookie_life = ms_to_ktime(sp->assocparams.sasoc_cookie_life); asoc->user_frag = sp->user_frag; /* Set the association max_retrans and RTO values from the * socket values. */ asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt; asoc->pf_retrans = sp->pf_retrans; asoc->ps_retrans = sp->ps_retrans; asoc->pf_expose = sp->pf_expose; asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial); asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max); asoc->rto_min = msecs_to_jiffies(sp->rtoinfo.srto_min); /* Initialize the association's heartbeat interval based on the * sock configured value. */ asoc->hbinterval = msecs_to_jiffies(sp->hbinterval); asoc->probe_interval = msecs_to_jiffies(sp->probe_interval); asoc->encap_port = sp->encap_port; /* Initialize path max retrans value. */ asoc->pathmaxrxt = sp->pathmaxrxt; asoc->flowlabel = sp->flowlabel; asoc->dscp = sp->dscp; /* Set association default SACK delay */ asoc->sackdelay = msecs_to_jiffies(sp->sackdelay); asoc->sackfreq = sp->sackfreq; /* Set the association default flags controlling * Heartbeat, SACK delay, and Path MTU Discovery. */ asoc->param_flags = sp->param_flags; /* Initialize the maximum number of new data packets that can be sent * in a burst. */ asoc->max_burst = sp->max_burst; asoc->subscribe = sp->subscribe; /* initialize association timers */ asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE] = asoc->rto_initial; asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT] = asoc->rto_initial; asoc->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = asoc->rto_initial; /* sctpimpguide Section 2.12.2 * If the 'T5-shutdown-guard' timer is used, it SHOULD be set to the * recommended value of 5 times 'RTO.Max'. */ asoc->timeouts[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD] = 5 * asoc->rto_max; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) timer_setup(&asoc->timers[i], sctp_timer_events[i], 0); /* Pull default initialization values from the sock options. * Note: This assumes that the values have already been * validated in the sock. */ asoc->c.sinit_max_instreams = sp->initmsg.sinit_max_instreams; asoc->c.sinit_num_ostreams = sp->initmsg.sinit_num_ostreams; asoc->max_init_attempts = sp->initmsg.sinit_max_attempts; asoc->max_init_timeo = msecs_to_jiffies(sp->initmsg.sinit_max_init_timeo); /* Set the local window size for receive. * This is also the rcvbuf space per association. * RFC 6 - A SCTP receiver MUST be able to receive a minimum of * 1500 bytes in one SCTP packet. */ if ((sk->sk_rcvbuf/2) < SCTP_DEFAULT_MINWINDOW) asoc->rwnd = SCTP_DEFAULT_MINWINDOW; else asoc->rwnd = sk->sk_rcvbuf/2; asoc->a_rwnd = asoc->rwnd; /* Use my own max window until I learn something better. */ asoc->peer.rwnd = SCTP_DEFAULT_MAXWINDOW; /* Initialize the receive memory counter */ atomic_set(&asoc->rmem_alloc, 0); init_waitqueue_head(&asoc->wait); asoc->c.my_vtag = sctp_generate_tag(ep); asoc->c.my_port = ep->base.bind_addr.port; asoc->c.initial_tsn = sctp_generate_tsn(ep); asoc->next_tsn = asoc->c.initial_tsn; asoc->ctsn_ack_point = asoc->next_tsn - 1; asoc->adv_peer_ack_point = asoc->ctsn_ack_point; asoc->highest_sacked = asoc->ctsn_ack_point; asoc->last_cwr_tsn = asoc->ctsn_ack_point; /* ADDIP Section 4.1 Asconf Chunk Procedures * * When an endpoint has an ASCONF signaled change to be sent to the * remote endpoint it should do the following: * ... * A2) a serial number should be assigned to the chunk. The serial * number SHOULD be a monotonically increasing number. The serial * numbers SHOULD be initialized at the start of the * association to the same value as the initial TSN. */ asoc->addip_serial = asoc->c.initial_tsn; asoc->strreset_outseq = asoc->c.initial_tsn; INIT_LIST_HEAD(&asoc->addip_chunk_list); INIT_LIST_HEAD(&asoc->asconf_ack_list); /* Make an empty list of remote transport addresses. */ INIT_LIST_HEAD(&asoc->peer.transport_addr_list); /* RFC 2960 5.1 Normal Establishment of an Association * * After the reception of the first data chunk in an * association the endpoint must immediately respond with a * sack to acknowledge the data chunk. Subsequent * acknowledgements should be done as described in Section * 6.2. * * [We implement this by telling a new association that it * already received one packet.] */ asoc->peer.sack_needed = 1; asoc->peer.sack_generation = 1; /* Create an input queue. */ sctp_inq_init(&asoc->base.inqueue); sctp_inq_set_th_handler(&asoc->base.inqueue, sctp_assoc_bh_rcv); /* Create an output queue. */ sctp_outq_init(asoc, &asoc->outqueue); sctp_ulpq_init(&asoc->ulpq, asoc); if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp)) goto stream_free; /* Initialize default path MTU. */ asoc->pathmtu = sp->pathmtu; sctp_assoc_update_frag_point(asoc); /* Assume that peer would support both address types unless we are * told otherwise. */ asoc->peer.ipv4_address = 1; if (asoc->base.sk->sk_family == PF_INET6) asoc->peer.ipv6_address = 1; INIT_LIST_HEAD(&asoc->asocs); asoc->default_stream = sp->default_stream; asoc->default_ppid = sp->default_ppid; asoc->default_flags = sp->default_flags; asoc->default_context = sp->default_context; asoc->default_timetolive = sp->default_timetolive; asoc->default_rcv_context = sp->default_rcv_context; /* AUTH related initializations */ INIT_LIST_HEAD(&asoc->endpoint_shared_keys); if (sctp_auth_asoc_copy_shkeys(ep, asoc, gfp)) goto stream_free; asoc->active_key_id = ep->active_key_id; asoc->strreset_enable = ep->strreset_enable; /* Save the hmacs and chunks list into this association */ if (ep->auth_hmacs_list) memcpy(asoc->c.auth_hmacs, ep->auth_hmacs_list, ntohs(ep->auth_hmacs_list->param_hdr.length)); if (ep->auth_chunk_list) memcpy(asoc->c.auth_chunks, ep->auth_chunk_list, ntohs(ep->auth_chunk_list->param_hdr.length)); /* Get the AUTH random number for this association */ p = (struct sctp_paramhdr *)asoc->c.auth_random; p->type = SCTP_PARAM_RANDOM; p->length = htons(sizeof(*p) + SCTP_AUTH_RANDOM_LENGTH); get_random_bytes(p+1, SCTP_AUTH_RANDOM_LENGTH); return asoc; stream_free: sctp_stream_free(&asoc->stream); sock_put(asoc->base.sk); sctp_endpoint_put(asoc->ep); return NULL; } /* Allocate and initialize a new association */ struct sctp_association *sctp_association_new(const struct sctp_endpoint *ep, const struct sock *sk, enum sctp_scope scope, gfp_t gfp) { struct sctp_association *asoc; asoc = kzalloc(sizeof(*asoc), gfp); if (!asoc) goto fail; if (!sctp_association_init(asoc, ep, sk, scope, gfp)) goto fail_init; SCTP_DBG_OBJCNT_INC(assoc); pr_debug("Created asoc %p\n", asoc); return asoc; fail_init: kfree(asoc); fail: return NULL; } /* Free this association if possible. There may still be users, so * the actual deallocation may be delayed. */ void sctp_association_free(struct sctp_association *asoc) { struct sock *sk = asoc->base.sk; struct sctp_transport *transport; struct list_head *pos, *temp; int i; /* Only real associations count against the endpoint, so * don't bother for if this is a temporary association. */ if (!list_empty(&asoc->asocs)) { list_del(&asoc->asocs); /* Decrement the backlog value for a TCP-style listening * socket. */ if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING)) sk_acceptq_removed(sk); } /* Mark as dead, so other users can know this structure is * going away. */ asoc->base.dead = true; /* Dispose of any data lying around in the outqueue. */ sctp_outq_free(&asoc->outqueue); /* Dispose of any pending messages for the upper layer. */ sctp_ulpq_free(&asoc->ulpq); /* Dispose of any pending chunks on the inqueue. */ sctp_inq_free(&asoc->base.inqueue); sctp_tsnmap_free(&asoc->peer.tsn_map); /* Free stream information. */ sctp_stream_free(&asoc->stream); if (asoc->strreset_chunk) sctp_chunk_free(asoc->strreset_chunk); /* Clean up the bound address list. */ sctp_bind_addr_free(&asoc->base.bind_addr); /* Do we need to go through all of our timers and * delete them? To be safe we will try to delete all, but we * should be able to go through and make a guess based * on our state. */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) { if (del_timer(&asoc->timers[i])) sctp_association_put(asoc); } /* Free peer's cached cookie. */ kfree(asoc->peer.cookie); kfree(asoc->peer.peer_random); kfree(asoc->peer.peer_chunks); kfree(asoc->peer.peer_hmacs); /* Release the transport structures. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); list_del_rcu(pos); sctp_unhash_transport(transport); sctp_transport_free(transport); } asoc->peer.transport_count = 0; sctp_asconf_queue_teardown(asoc); /* Free pending address space being deleted */ kfree(asoc->asconf_addr_del_pending); /* AUTH - Free the endpoint shared keys */ sctp_auth_destroy_keys(&asoc->endpoint_shared_keys); /* AUTH - Free the association shared key */ sctp_auth_key_put(asoc->asoc_shared_key); sctp_association_put(asoc); } /* Cleanup and free up an association. */ static void sctp_association_destroy(struct sctp_association *asoc) { if (unlikely(!asoc->base.dead)) { WARN(1, "Attempt to destroy undead association %p!\n", asoc); return; } sctp_endpoint_put(asoc->ep); sock_put(asoc->base.sk); if (asoc->assoc_id != 0) { spin_lock_bh(&sctp_assocs_id_lock); idr_remove(&sctp_assocs_id, asoc->assoc_id); spin_unlock_bh(&sctp_assocs_id_lock); } WARN_ON(atomic_read(&asoc->rmem_alloc)); kfree_rcu(asoc, rcu); SCTP_DBG_OBJCNT_DEC(assoc); } /* Change the primary destination address for the peer. */ void sctp_assoc_set_primary(struct sctp_association *asoc, struct sctp_transport *transport) { int changeover = 0; /* it's a changeover only if we already have a primary path * that we are changing */ if (asoc->peer.primary_path != NULL && asoc->peer.primary_path != transport) changeover = 1 ; asoc->peer.primary_path = transport; sctp_ulpevent_notify_peer_addr_change(transport, SCTP_ADDR_MADE_PRIM, 0); /* Set a default msg_name for events. */ memcpy(&asoc->peer.primary_addr, &transport->ipaddr, sizeof(union sctp_addr)); /* If the primary path is changing, assume that the * user wants to use this new path. */ if ((transport->state == SCTP_ACTIVE) || (transport->state == SCTP_UNKNOWN)) asoc->peer.active_path = transport; /* * SFR-CACC algorithm: * Upon the receipt of a request to change the primary * destination address, on the data structure for the new * primary destination, the sender MUST do the following: * * 1) If CHANGEOVER_ACTIVE is set, then there was a switch * to this destination address earlier. The sender MUST set * CYCLING_CHANGEOVER to indicate that this switch is a * double switch to the same destination address. * * Really, only bother is we have data queued or outstanding on * the association. */ if (!asoc->outqueue.outstanding_bytes && !asoc->outqueue.out_qlen) return; if (transport->cacc.changeover_active) transport->cacc.cycling_changeover = changeover; /* 2) The sender MUST set CHANGEOVER_ACTIVE to indicate that * a changeover has occurred. */ transport->cacc.changeover_active = changeover; /* 3) The sender MUST store the next TSN to be sent in * next_tsn_at_change. */ transport->cacc.next_tsn_at_change = asoc->next_tsn; } /* Remove a transport from an association. */ void sctp_assoc_rm_peer(struct sctp_association *asoc, struct sctp_transport *peer) { struct sctp_transport *transport; struct list_head *pos; struct sctp_chunk *ch; pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc, &peer->ipaddr.sa); /* If we are to remove the current retran_path, update it * to the next peer before removing this peer from the list. */ if (asoc->peer.retran_path == peer) sctp_assoc_update_retran_path(asoc); /* Remove this peer from the list. */ list_del_rcu(&peer->transports); /* Remove this peer from the transport hashtable */ sctp_unhash_transport(peer); /* Get the first transport of asoc. */ pos = asoc->peer.transport_addr_list.next; transport = list_entry(pos, struct sctp_transport, transports); /* Update any entries that match the peer to be deleted. */ if (asoc->peer.primary_path == peer) sctp_assoc_set_primary(asoc, transport); if (asoc->peer.active_path == peer) asoc->peer.active_path = transport; if (asoc->peer.retran_path == peer) asoc->peer.retran_path = transport; if (asoc->peer.last_data_from == peer) asoc->peer.last_data_from = transport; if (asoc->strreset_chunk && asoc->strreset_chunk->transport == peer) { asoc->strreset_chunk->transport = transport; sctp_transport_reset_reconf_timer(transport); } /* If we remove the transport an INIT was last sent to, set it to * NULL. Combined with the update of the retran path above, this * will cause the next INIT to be sent to the next available * transport, maintaining the cycle. */ if (asoc->init_last_sent_to == peer) asoc->init_last_sent_to = NULL; /* If we remove the transport an SHUTDOWN was last sent to, set it * to NULL. Combined with the update of the retran path above, this * will cause the next SHUTDOWN to be sent to the next available * transport, maintaining the cycle. */ if (asoc->shutdown_last_sent_to == peer) asoc->shutdown_last_sent_to = NULL; /* If we remove the transport an ASCONF was last sent to, set it to * NULL. */ if (asoc->addip_last_asconf && asoc->addip_last_asconf->transport == peer) asoc->addip_last_asconf->transport = NULL; /* If we have something on the transmitted list, we have to * save it off. The best place is the active path. */ if (!list_empty(&peer->transmitted)) { struct sctp_transport *active = asoc->peer.active_path; /* Reset the transport of each chunk on this list */ list_for_each_entry(ch, &peer->transmitted, transmitted_list) { ch->transport = NULL; ch->rtt_in_progress = 0; } list_splice_tail_init(&peer->transmitted, &active->transmitted); /* Start a T3 timer here in case it wasn't running so * that these migrated packets have a chance to get * retransmitted. */ if (!timer_pending(&active->T3_rtx_timer)) if (!mod_timer(&active->T3_rtx_timer, jiffies + active->rto)) sctp_transport_hold(active); } list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) if (ch->transport == peer) ch->transport = NULL; asoc->peer.transport_count--; sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_REMOVED, 0); sctp_transport_free(peer); } /* Add a transport address to an association. */ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, const union sctp_addr *addr, const gfp_t gfp, const int peer_state) { struct sctp_transport *peer; struct sctp_sock *sp; unsigned short port; sp = sctp_sk(asoc->base.sk); /* AF_INET and AF_INET6 share common port field. */ port = ntohs(addr->v4.sin_port); pr_debug("%s: association:%p addr:%pISpc state:%d\n", __func__, asoc, &addr->sa, peer_state); /* Set the port if it has not been set yet. */ if (0 == asoc->peer.port) asoc->peer.port = port; /* Check to see if this is a duplicate. */ peer = sctp_assoc_lookup_paddr(asoc, addr); if (peer) { /* An UNKNOWN state is only set on transports added by * user in sctp_connectx() call. Such transports should be * considered CONFIRMED per RFC 4960, Section 5.4. */ if (peer->state == SCTP_UNKNOWN) { peer->state = SCTP_ACTIVE; } return peer; } peer = sctp_transport_new(asoc->base.net, addr, gfp); if (!peer) return NULL; sctp_transport_set_owner(peer, asoc); /* Initialize the peer's heartbeat interval based on the * association configured value. */ peer->hbinterval = asoc->hbinterval; peer->probe_interval = asoc->probe_interval; peer->encap_port = asoc->encap_port; /* Set the path max_retrans. */ peer->pathmaxrxt = asoc->pathmaxrxt; /* And the partial failure retrans threshold */ peer->pf_retrans = asoc->pf_retrans; /* And the primary path switchover retrans threshold */ peer->ps_retrans = asoc->ps_retrans; /* Initialize the peer's SACK delay timeout based on the * association configured value. */ peer->sackdelay = asoc->sackdelay; peer->sackfreq = asoc->sackfreq; if (addr->sa.sa_family == AF_INET6) { __be32 info = addr->v6.sin6_flowinfo; if (info) { peer->flowlabel = ntohl(info & IPV6_FLOWLABEL_MASK); peer->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } else { peer->flowlabel = asoc->flowlabel; } } peer->dscp = asoc->dscp; /* Enable/disable heartbeat, SACK delay, and path MTU discovery * based on association setting. */ peer->param_flags = asoc->param_flags; /* Initialize the pmtu of the transport. */ sctp_transport_route(peer, NULL, sp); /* If this is the first transport addr on this association, * initialize the association PMTU to the peer's PMTU. * If not and the current association PMTU is higher than the new * peer's PMTU, reset the association PMTU to the new peer's PMTU. */ sctp_assoc_set_pmtu(asoc, asoc->pathmtu ? min_t(int, peer->pathmtu, asoc->pathmtu) : peer->pathmtu); peer->pmtu_pending = 0; /* The asoc->peer.port might not be meaningful yet, but * initialize the packet structure anyway. */ sctp_packet_init(&peer->packet, peer, asoc->base.bind_addr.port, asoc->peer.port); /* 7.2.1 Slow-Start * * o The initial cwnd before DATA transmission or after a sufficiently * long idle period MUST be set to * min(4*MTU, max(2*MTU, 4380 bytes)) * * o The initial value of ssthresh MAY be arbitrarily high * (for example, implementations MAY use the size of the * receiver advertised window). */ peer->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); /* At this point, we may not have the receiver's advertised window, * so initialize ssthresh to the default value and it will be set * later when we process the INIT. */ peer->ssthresh = SCTP_DEFAULT_MAXWINDOW; peer->partial_bytes_acked = 0; peer->flight_size = 0; peer->burst_limited = 0; /* Set the transport's RTO.initial value */ peer->rto = asoc->rto_initial; sctp_max_rto(asoc, peer); /* Set the peer's active state. */ peer->state = peer_state; /* Add this peer into the transport hashtable */ if (sctp_hash_transport(peer)) { sctp_transport_free(peer); return NULL; } sctp_transport_pl_reset(peer); /* Attach the remote transport to our asoc. */ list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list); asoc->peer.transport_count++; sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_ADDED, 0); /* If we do not yet have a primary path, set one. */ if (!asoc->peer.primary_path) { sctp_assoc_set_primary(asoc, peer); asoc->peer.retran_path = peer; } if (asoc->peer.active_path == asoc->peer.retran_path && peer->state != SCTP_UNCONFIRMED) { asoc->peer.retran_path = peer; } return peer; } /* Delete a transport address from an association. */ void sctp_assoc_del_peer(struct sctp_association *asoc, const union sctp_addr *addr) { struct list_head *pos; struct list_head *temp; struct sctp_transport *transport; list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); if (sctp_cmp_addr_exact(addr, &transport->ipaddr)) { /* Do book keeping for removing the peer and free it. */ sctp_assoc_rm_peer(asoc, transport); break; } } } /* Lookup a transport by address. */ struct sctp_transport *sctp_assoc_lookup_paddr( const struct sctp_association *asoc, const union sctp_addr *address) { struct sctp_transport *t; /* Cycle through all transports searching for a peer address. */ list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (sctp_cmp_addr_exact(address, &t->ipaddr)) return t; } return NULL; } /* Remove all transports except a give one */ void sctp_assoc_del_nonprimary_peers(struct sctp_association *asoc, struct sctp_transport *primary) { struct sctp_transport *temp; struct sctp_transport *t; list_for_each_entry_safe(t, temp, &asoc->peer.transport_addr_list, transports) { /* if the current transport is not the primary one, delete it */ if (t != primary) sctp_assoc_rm_peer(asoc, t); } } /* Engage in transport control operations. * Mark the transport up or down and send a notification to the user. * Select and update the new active and retran paths. */ void sctp_assoc_control_transport(struct sctp_association *asoc, struct sctp_transport *transport, enum sctp_transport_cmd command, sctp_sn_error_t error) { int spc_state = SCTP_ADDR_AVAILABLE; bool ulp_notify = true; /* Record the transition on the transport. */ switch (command) { case SCTP_TRANSPORT_UP: /* If we are moving from UNCONFIRMED state due * to heartbeat success, report the SCTP_ADDR_CONFIRMED * state to the user, otherwise report SCTP_ADDR_AVAILABLE. */ if (transport->state == SCTP_PF && asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE) ulp_notify = false; else if (transport->state == SCTP_UNCONFIRMED && error == SCTP_HEARTBEAT_SUCCESS) spc_state = SCTP_ADDR_CONFIRMED; transport->state = SCTP_ACTIVE; sctp_transport_pl_reset(transport); break; case SCTP_TRANSPORT_DOWN: /* If the transport was never confirmed, do not transition it * to inactive state. Also, release the cached route since * there may be a better route next time. */ if (transport->state != SCTP_UNCONFIRMED) { transport->state = SCTP_INACTIVE; sctp_transport_pl_reset(transport); spc_state = SCTP_ADDR_UNREACHABLE; } else { sctp_transport_dst_release(transport); ulp_notify = false; } break; case SCTP_TRANSPORT_PF: transport->state = SCTP_PF; if (asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE) ulp_notify = false; else spc_state = SCTP_ADDR_POTENTIALLY_FAILED; break; default: return; } /* Generate and send a SCTP_PEER_ADDR_CHANGE notification * to the user. */ if (ulp_notify) sctp_ulpevent_notify_peer_addr_change(transport, spc_state, error); /* Select new active and retran paths. */ sctp_select_active_and_retran_path(asoc); } /* Hold a reference to an association. */ void sctp_association_hold(struct sctp_association *asoc) { refcount_inc(&asoc->base.refcnt); } /* Release a reference to an association and cleanup * if there are no more references. */ void sctp_association_put(struct sctp_association *asoc) { if (refcount_dec_and_test(&asoc->base.refcnt)) sctp_association_destroy(asoc); } /* Allocate the next TSN, Transmission Sequence Number, for the given * association. */ __u32 sctp_association_get_next_tsn(struct sctp_association *asoc) { /* From Section 1.6 Serial Number Arithmetic: * Transmission Sequence Numbers wrap around when they reach * 2**32 - 1. That is, the next TSN a DATA chunk MUST use * after transmitting TSN = 2*32 - 1 is TSN = 0. */ __u32 retval = asoc->next_tsn; asoc->next_tsn++; asoc->unack_data++; return retval; } /* Compare two addresses to see if they match. Wildcard addresses * only match themselves. */ int sctp_cmp_addr_exact(const union sctp_addr *ss1, const union sctp_addr *ss2) { struct sctp_af *af; af = sctp_get_af_specific(ss1->sa.sa_family); if (unlikely(!af)) return 0; return af->cmp_addr(ss1, ss2); } /* Return an ecne chunk to get prepended to a packet. * Note: We are sly and return a shared, prealloced chunk. FIXME: * No we don't, but we could/should. */ struct sctp_chunk *sctp_get_ecne_prepend(struct sctp_association *asoc) { if (!asoc->need_ecne) return NULL; /* Send ECNE if needed. * Not being able to allocate a chunk here is not deadly. */ return sctp_make_ecne(asoc, asoc->last_ecne_tsn); } /* * Find which transport this TSN was sent on. */ struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *asoc, __u32 tsn) { struct sctp_transport *active; struct sctp_transport *match; struct sctp_transport *transport; struct sctp_chunk *chunk; __be32 key = htonl(tsn); match = NULL; /* * FIXME: In general, find a more efficient data structure for * searching. */ /* * The general strategy is to search each transport's transmitted * list. Return which transport this TSN lives on. * * Let's be hopeful and check the active_path first. * Another optimization would be to know if there is only one * outbound path and not have to look for the TSN at all. * */ active = asoc->peer.active_path; list_for_each_entry(chunk, &active->transmitted, transmitted_list) { if (key == chunk->subh.data_hdr->tsn) { match = active; goto out; } } /* If not found, go search all the other transports. */ list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { if (transport == active) continue; list_for_each_entry(chunk, &transport->transmitted, transmitted_list) { if (key == chunk->subh.data_hdr->tsn) { match = transport; goto out; } } } out: return match; } /* Do delayed input processing. This is scheduled by sctp_rcv(). */ static void sctp_assoc_bh_rcv(struct work_struct *work) { struct sctp_association *asoc = container_of(work, struct sctp_association, base.inqueue.immediate); struct net *net = asoc->base.net; union sctp_subtype subtype; struct sctp_endpoint *ep; struct sctp_chunk *chunk; struct sctp_inq *inqueue; int first_time = 1; /* is this the first time through the loop */ int error = 0; int state; /* The association should be held so we should be safe. */ ep = asoc->ep; inqueue = &asoc->base.inqueue; sctp_association_hold(asoc); while (NULL != (chunk = sctp_inq_pop(inqueue))) { state = asoc->state; subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type); /* If the first chunk in the packet is AUTH, do special * processing specified in Section 6.3 of SCTP-AUTH spec */ if (first_time && subtype.chunk == SCTP_CID_AUTH) { struct sctp_chunkhdr *next_hdr; next_hdr = sctp_inq_peek(inqueue); if (!next_hdr) goto normal; /* If the next chunk is COOKIE-ECHO, skip the AUTH * chunk while saving a pointer to it so we can do * Authentication later (during cookie-echo * processing). */ if (next_hdr->type == SCTP_CID_COOKIE_ECHO) { chunk->auth_chunk = skb_clone(chunk->skb, GFP_ATOMIC); chunk->auth = 1; continue; } } normal: /* SCTP-AUTH, Section 6.3: * The receiver has a list of chunk types which it expects * to be received only after an AUTH-chunk. This list has * been sent to the peer during the association setup. It * MUST silently discard these chunks if they are not placed * after an AUTH chunk in the packet. */ if (sctp_auth_recv_cid(subtype.chunk, asoc) && !chunk->auth) continue; /* Remember where the last DATA chunk came from so we * know where to send the SACK. */ if (sctp_chunk_is_data(chunk)) asoc->peer.last_data_from = chunk->transport; else { SCTP_INC_STATS(net, SCTP_MIB_INCTRLCHUNKS); asoc->stats.ictrlchunks++; if (chunk->chunk_hdr->type == SCTP_CID_SACK) asoc->stats.isacks++; } if (chunk->transport) chunk->transport->last_time_heard = ktime_get(); /* Run through the state machine. */ error = sctp_do_sm(net, SCTP_EVENT_T_CHUNK, subtype, state, ep, asoc, chunk, GFP_ATOMIC); /* Check to see if the association is freed in response to * the incoming chunk. If so, get out of the while loop. */ if (asoc->base.dead) break; /* If there is an error on chunk, discard this packet. */ if (error && chunk) chunk->pdiscard = 1; if (first_time) first_time = 0; } sctp_association_put(asoc); } /* This routine moves an association from its old sk to a new sk. */ void sctp_assoc_migrate(struct sctp_association *assoc, struct sock *newsk) { struct sctp_sock *newsp = sctp_sk(newsk); struct sock *oldsk = assoc->base.sk; /* Delete the association from the old endpoint's list of * associations. */ list_del_init(&assoc->asocs); /* Decrement the backlog value for a TCP-style socket. */ if (sctp_style(oldsk, TCP)) sk_acceptq_removed(oldsk); /* Release references to the old endpoint and the sock. */ sctp_endpoint_put(assoc->ep); sock_put(assoc->base.sk); /* Get a reference to the new endpoint. */ assoc->ep = newsp->ep; sctp_endpoint_hold(assoc->ep); /* Get a reference to the new sock. */ assoc->base.sk = newsk; sock_hold(assoc->base.sk); /* Add the association to the new endpoint's list of associations. */ sctp_endpoint_add_asoc(newsp->ep, assoc); } /* Update an association (possibly from unexpected COOKIE-ECHO processing). */ int sctp_assoc_update(struct sctp_association *asoc, struct sctp_association *new) { struct sctp_transport *trans; struct list_head *pos, *temp; /* Copy in new parameters of peer. */ asoc->c = new->c; asoc->peer.rwnd = new->peer.rwnd; asoc->peer.sack_needed = new->peer.sack_needed; asoc->peer.auth_capable = new->peer.auth_capable; asoc->peer.i = new->peer.i; if (!sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, asoc->peer.i.initial_tsn, GFP_ATOMIC)) return -ENOMEM; /* Remove any peer addresses not present in the new association. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { trans = list_entry(pos, struct sctp_transport, transports); if (!sctp_assoc_lookup_paddr(new, &trans->ipaddr)) { sctp_assoc_rm_peer(asoc, trans); continue; } if (asoc->state >= SCTP_STATE_ESTABLISHED) sctp_transport_reset(trans); } /* If the case is A (association restart), use * initial_tsn as next_tsn. If the case is B, use * current next_tsn in case data sent to peer * has been discarded and needs retransmission. */ if (asoc->state >= SCTP_STATE_ESTABLISHED) { asoc->next_tsn = new->next_tsn; asoc->ctsn_ack_point = new->ctsn_ack_point; asoc->adv_peer_ack_point = new->adv_peer_ack_point; /* Reinitialize SSN for both local streams * and peer's streams. */ sctp_stream_clear(&asoc->stream); /* Flush the ULP reassembly and ordered queue. * Any data there will now be stale and will * cause problems. */ sctp_ulpq_flush(&asoc->ulpq); /* reset the overall association error count so * that the restarted association doesn't get torn * down on the next retransmission timer. */ asoc->overall_error_count = 0; } else { /* Add any peer addresses from the new association. */ list_for_each_entry(trans, &new->peer.transport_addr_list, transports) if (!sctp_assoc_add_peer(asoc, &trans->ipaddr, GFP_ATOMIC, trans->state)) return -ENOMEM; asoc->ctsn_ack_point = asoc->next_tsn - 1; asoc->adv_peer_ack_point = asoc->ctsn_ack_point; if (sctp_state(asoc, COOKIE_WAIT)) sctp_stream_update(&asoc->stream, &new->stream); /* get a new assoc id if we don't have one yet. */ if (sctp_assoc_set_id(asoc, GFP_ATOMIC)) return -ENOMEM; } /* SCTP-AUTH: Save the peer parameters from the new associations * and also move the association shared keys over */ kfree(asoc->peer.peer_random); asoc->peer.peer_random = new->peer.peer_random; new->peer.peer_random = NULL; kfree(asoc->peer.peer_chunks); asoc->peer.peer_chunks = new->peer.peer_chunks; new->peer.peer_chunks = NULL; kfree(asoc->peer.peer_hmacs); asoc->peer.peer_hmacs = new->peer.peer_hmacs; new->peer.peer_hmacs = NULL; return sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); } /* Update the retran path for sending a retransmitted packet. * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints: * * When there is outbound data to send and the primary path * becomes inactive (e.g., due to failures), or where the * SCTP user explicitly requests to send data to an * inactive destination transport address, before reporting * an error to its ULP, the SCTP endpoint should try to send * the data to an alternate active destination transport * address if one exists. * * When retransmitting data that timed out, if the endpoint * is multihomed, it should consider each source-destination * address pair in its retransmission selection policy. * When retransmitting timed-out data, the endpoint should * attempt to pick the most divergent source-destination * pair from the original source-destination pair to which * the packet was transmitted. * * Note: Rules for picking the most divergent source-destination * pair are an implementation decision and are not specified * within this document. * * Our basic strategy is to round-robin transports in priorities * according to sctp_trans_score() e.g., if no such * transport with state SCTP_ACTIVE exists, round-robin through * SCTP_UNKNOWN, etc. You get the picture. */ static u8 sctp_trans_score(const struct sctp_transport *trans) { switch (trans->state) { case SCTP_ACTIVE: return 3; /* best case */ case SCTP_UNKNOWN: return 2; case SCTP_PF: return 1; default: /* case SCTP_INACTIVE */ return 0; /* worst case */ } } static struct sctp_transport *sctp_trans_elect_tie(struct sctp_transport *trans1, struct sctp_transport *trans2) { if (trans1->error_count > trans2->error_count) { return trans2; } else if (trans1->error_count == trans2->error_count && ktime_after(trans2->last_time_heard, trans1->last_time_heard)) { return trans2; } else { return trans1; } } static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr, struct sctp_transport *best) { u8 score_curr, score_best; if (best == NULL || curr == best) return curr; score_curr = sctp_trans_score(curr); score_best = sctp_trans_score(best); /* First, try a score-based selection if both transport states * differ. If we're in a tie, lets try to make a more clever * decision here based on error counts and last time heard. */ if (score_curr > score_best) return curr; else if (score_curr == score_best) return sctp_trans_elect_tie(best, curr); else return best; } void sctp_assoc_update_retran_path(struct sctp_association *asoc) { struct sctp_transport *trans = asoc->peer.retran_path; struct sctp_transport *trans_next = NULL; /* We're done as we only have the one and only path. */ if (asoc->peer.transport_count == 1) return; /* If active_path and retran_path are the same and active, * then this is the only active path. Use it. */ if (asoc->peer.active_path == asoc->peer.retran_path && asoc->peer.active_path->state == SCTP_ACTIVE) return; /* Iterate from retran_path's successor back to retran_path. */ for (trans = list_next_entry(trans, transports); 1; trans = list_next_entry(trans, transports)) { /* Manually skip the head element. */ if (&trans->transports == &asoc->peer.transport_addr_list) continue; if (trans->state == SCTP_UNCONFIRMED) continue; trans_next = sctp_trans_elect_best(trans, trans_next); /* Active is good enough for immediate return. */ if (trans_next->state == SCTP_ACTIVE) break; /* We've reached the end, time to update path. */ if (trans == asoc->peer.retran_path) break; } asoc->peer.retran_path = trans_next; pr_debug("%s: association:%p updated new path to addr:%pISpc\n", __func__, asoc, &asoc->peer.retran_path->ipaddr.sa); } static void sctp_select_active_and_retran_path(struct sctp_association *asoc) { struct sctp_transport *trans, *trans_pri = NULL, *trans_sec = NULL; struct sctp_transport *trans_pf = NULL; /* Look for the two most recently used active transports. */ list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { /* Skip uninteresting transports. */ if (trans->state == SCTP_INACTIVE || trans->state == SCTP_UNCONFIRMED) continue; /* Keep track of the best PF transport from our * list in case we don't find an active one. */ if (trans->state == SCTP_PF) { trans_pf = sctp_trans_elect_best(trans, trans_pf); continue; } /* For active transports, pick the most recent ones. */ if (trans_pri == NULL || ktime_after(trans->last_time_heard, trans_pri->last_time_heard)) { trans_sec = trans_pri; trans_pri = trans; } else if (trans_sec == NULL || ktime_after(trans->last_time_heard, trans_sec->last_time_heard)) { trans_sec = trans; } } /* RFC 2960 6.4 Multi-Homed SCTP Endpoints * * By default, an endpoint should always transmit to the primary * path, unless the SCTP user explicitly specifies the * destination transport address (and possibly source transport * address) to use. [If the primary is active but not most recent, * bump the most recently used transport.] */ if ((asoc->peer.primary_path->state == SCTP_ACTIVE || asoc->peer.primary_path->state == SCTP_UNKNOWN) && asoc->peer.primary_path != trans_pri) { trans_sec = trans_pri; trans_pri = asoc->peer.primary_path; } /* We did not find anything useful for a possible retransmission * path; either primary path that we found is the same as * the current one, or we didn't generally find an active one. */ if (trans_sec == NULL) trans_sec = trans_pri; /* If we failed to find a usable transport, just camp on the * active or pick a PF iff it's the better choice. */ if (trans_pri == NULL) { trans_pri = sctp_trans_elect_best(asoc->peer.active_path, trans_pf); trans_sec = trans_pri; } /* Set the active and retran transports. */ asoc->peer.active_path = trans_pri; asoc->peer.retran_path = trans_sec; } struct sctp_transport * sctp_assoc_choose_alter_transport(struct sctp_association *asoc, struct sctp_transport *last_sent_to) { /* If this is the first time packet is sent, use the active path, * else use the retran path. If the last packet was sent over the * retran path, update the retran path and use it. */ if (last_sent_to == NULL) { return asoc->peer.active_path; } else { if (last_sent_to == asoc->peer.retran_path) sctp_assoc_update_retran_path(asoc); return asoc->peer.retran_path; } } void sctp_assoc_update_frag_point(struct sctp_association *asoc) { int frag = sctp_mtu_payload(sctp_sk(asoc->base.sk), asoc->pathmtu, sctp_datachk_len(&asoc->stream)); if (asoc->user_frag) frag = min_t(int, frag, asoc->user_frag); frag = min_t(int, frag, SCTP_MAX_CHUNK_LEN - sctp_datachk_len(&asoc->stream)); asoc->frag_point = SCTP_TRUNC4(frag); } void sctp_assoc_set_pmtu(struct sctp_association *asoc, __u32 pmtu) { if (asoc->pathmtu != pmtu) { asoc->pathmtu = pmtu; sctp_assoc_update_frag_point(asoc); } pr_debug("%s: asoc:%p, pmtu:%d, frag_point:%d\n", __func__, asoc, asoc->pathmtu, asoc->frag_point); } /* Update the association's pmtu and frag_point by going through all the * transports. This routine is called when a transport's PMTU has changed. */ void sctp_assoc_sync_pmtu(struct sctp_association *asoc) { struct sctp_transport *t; __u32 pmtu = 0; if (!asoc) return; /* Get the lowest pmtu of all the transports. */ list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (t->pmtu_pending && t->dst) { sctp_transport_update_pmtu(t, atomic_read(&t->mtu_info)); t->pmtu_pending = 0; } if (!pmtu || (t->pathmtu < pmtu)) pmtu = t->pathmtu; } sctp_assoc_set_pmtu(asoc, pmtu); } /* Should we send a SACK to update our peer? */ static inline bool sctp_peer_needs_update(struct sctp_association *asoc) { struct net *net = asoc->base.net; switch (asoc->state) { case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_RECEIVED: case SCTP_STATE_SHUTDOWN_SENT: if ((asoc->rwnd > asoc->a_rwnd) && ((asoc->rwnd - asoc->a_rwnd) >= max_t(__u32, (asoc->base.sk->sk_rcvbuf >> net->sctp.rwnd_upd_shift), asoc->pathmtu))) return true; break; default: break; } return false; } /* Increase asoc's rwnd by len and send any window update SACK if needed. */ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) { struct sctp_chunk *sack; struct timer_list *timer; if (asoc->rwnd_over) { if (asoc->rwnd_over >= len) { asoc->rwnd_over -= len; } else { asoc->rwnd += (len - asoc->rwnd_over); asoc->rwnd_over = 0; } } else { asoc->rwnd += len; } /* If we had window pressure, start recovering it * once our rwnd had reached the accumulated pressure * threshold. The idea is to recover slowly, but up * to the initial advertised window. */ if (asoc->rwnd_press) { int change = min(asoc->pathmtu, asoc->rwnd_press); asoc->rwnd += change; asoc->rwnd_press -= change; } pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n", __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, asoc->a_rwnd); /* Send a window update SACK if the rwnd has increased by at least the * minimum of the association's PMTU and half of the receive buffer. * The algorithm used is similar to the one described in * Section 4.2.3.3 of RFC 1122. */ if (sctp_peer_needs_update(asoc)) { asoc->a_rwnd = asoc->rwnd; pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u " "a_rwnd:%u\n", __func__, asoc, asoc->rwnd, asoc->a_rwnd); sack = sctp_make_sack(asoc); if (!sack) return; asoc->peer.sack_needed = 0; sctp_outq_tail(&asoc->outqueue, sack, GFP_ATOMIC); /* Stop the SACK timer. */ timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK]; if (del_timer(timer)) sctp_association_put(asoc); } } /* Decrease asoc's rwnd by len. */ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) { int rx_count; int over = 0; if (unlikely(!asoc->rwnd || asoc->rwnd_over)) pr_debug("%s: association:%p has asoc->rwnd:%u, " "asoc->rwnd_over:%u!\n", __func__, asoc, asoc->rwnd, asoc->rwnd_over); if (asoc->ep->rcvbuf_policy) rx_count = atomic_read(&asoc->rmem_alloc); else rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); /* If we've reached or overflowed our receive buffer, announce * a 0 rwnd if rwnd would still be positive. Store the * potential pressure overflow so that the window can be restored * back to original value. */ if (rx_count >= asoc->base.sk->sk_rcvbuf) over = 1; if (asoc->rwnd >= len) { asoc->rwnd -= len; if (over) { asoc->rwnd_press += asoc->rwnd; asoc->rwnd = 0; } } else { asoc->rwnd_over += len - asoc->rwnd; asoc->rwnd = 0; } pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n", __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, asoc->rwnd_press); } /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. */ int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, enum sctp_scope scope, gfp_t gfp) { struct sock *sk = asoc->base.sk; int flags; /* Use scoping rules to determine the subset of addresses from * the endpoint. */ flags = (PF_INET6 == sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; if (!inet_v6_ipv6only(sk)) flags |= SCTP_ADDR4_ALLOWED; if (asoc->peer.ipv4_address) flags |= SCTP_ADDR4_PEERSUPP; if (asoc->peer.ipv6_address) flags |= SCTP_ADDR6_PEERSUPP; return sctp_bind_addr_copy(asoc->base.net, &asoc->base.bind_addr, &asoc->ep->base.bind_addr, scope, gfp, flags); } /* Build the association's bind address list from the cookie. */ int sctp_assoc_set_bind_addr_from_cookie(struct sctp_association *asoc, struct sctp_cookie *cookie, gfp_t gfp) { struct sctp_init_chunk *peer_init = (struct sctp_init_chunk *)(cookie + 1); int var_size2 = ntohs(peer_init->chunk_hdr.length); int var_size3 = cookie->raw_addr_list_len; __u8 *raw = (__u8 *)peer_init + var_size2; return sctp_raw_to_bind_addrs(&asoc->base.bind_addr, raw, var_size3, asoc->ep->base.bind_addr.port, gfp); } /* Lookup laddr in the bind address list of an association. */ int sctp_assoc_lookup_laddr(struct sctp_association *asoc, const union sctp_addr *laddr) { int found = 0; if ((asoc->base.bind_addr.port == ntohs(laddr->v4.sin_port)) && sctp_bind_addr_match(&asoc->base.bind_addr, laddr, sctp_sk(asoc->base.sk))) found = 1; return found; } /* Set an association id for a given association */ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp) { bool preload = gfpflags_allow_blocking(gfp); int ret; /* If the id is already assigned, keep it. */ if (asoc->assoc_id) return 0; if (preload) idr_preload(gfp); spin_lock_bh(&sctp_assocs_id_lock); /* 0, 1, 2 are used as SCTP_FUTURE_ASSOC, SCTP_CURRENT_ASSOC and * SCTP_ALL_ASSOC, so an available id must be > SCTP_ALL_ASSOC. */ ret = idr_alloc_cyclic(&sctp_assocs_id, asoc, SCTP_ALL_ASSOC + 1, 0, GFP_NOWAIT); spin_unlock_bh(&sctp_assocs_id_lock); if (preload) idr_preload_end(); if (ret < 0) return ret; asoc->assoc_id = (sctp_assoc_t)ret; return 0; } /* Free the ASCONF queue */ static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc) { struct sctp_chunk *asconf; struct sctp_chunk *tmp; list_for_each_entry_safe(asconf, tmp, &asoc->addip_chunk_list, list) { list_del_init(&asconf->list); sctp_chunk_free(asconf); } } /* Free asconf_ack cache */ static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc) { struct sctp_chunk *ack; struct sctp_chunk *tmp; list_for_each_entry_safe(ack, tmp, &asoc->asconf_ack_list, transmitted_list) { list_del_init(&ack->transmitted_list); sctp_chunk_free(ack); } } /* Clean up the ASCONF_ACK queue */ void sctp_assoc_clean_asconf_ack_cache(const struct sctp_association *asoc) { struct sctp_chunk *ack; struct sctp_chunk *tmp; /* We can remove all the entries from the queue up to * the "Peer-Sequence-Number". */ list_for_each_entry_safe(ack, tmp, &asoc->asconf_ack_list, transmitted_list) { if (ack->subh.addip_hdr->serial == htonl(asoc->peer.addip_serial)) break; list_del_init(&ack->transmitted_list); sctp_chunk_free(ack); } } /* Find the ASCONF_ACK whose serial number matches ASCONF */ struct sctp_chunk *sctp_assoc_lookup_asconf_ack( const struct sctp_association *asoc, __be32 serial) { struct sctp_chunk *ack; /* Walk through the list of cached ASCONF-ACKs and find the * ack chunk whose serial number matches that of the request. */ list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) { if (sctp_chunk_pending(ack)) continue; if (ack->subh.addip_hdr->serial == serial) { sctp_chunk_hold(ack); return ack; } } return NULL; } void sctp_asconf_queue_teardown(struct sctp_association *asoc) { /* Free any cached ASCONF_ACK chunk. */ sctp_assoc_free_asconf_acks(asoc); /* Free the ASCONF queue. */ sctp_assoc_free_asconf_queue(asoc); /* Free any cached ASCONF chunk. */ if (asoc->addip_last_asconf) sctp_chunk_free(asoc->addip_last_asconf); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/fsnotify_backend.h> #include <linux/inotify.h> #include <linux/slab.h> /* struct kmem_cache */ struct inotify_event_info { struct fsnotify_event fse; u32 mask; int wd; u32 sync_cookie; int name_len; char name[]; }; struct inotify_inode_mark { struct fsnotify_mark fsn_mark; int wd; }; static inline struct inotify_event_info *INOTIFY_E(struct fsnotify_event *fse) { return container_of(fse, struct inotify_event_info, fse); } /* * INOTIFY_USER_FLAGS represents all of the mask bits that we expose to * userspace. There is at least one bit (FS_EVENT_ON_CHILD) which is * used only internally to the kernel. */ #define INOTIFY_USER_MASK (IN_ALL_EVENTS) static inline __u32 inotify_mark_user_mask(struct fsnotify_mark *fsn_mark) { __u32 mask = fsn_mark->mask & INOTIFY_USER_MASK; if (fsn_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) mask |= IN_EXCL_UNLINK; if (fsn_mark->flags & FSNOTIFY_MARK_FLAG_IN_ONESHOT) mask |= IN_ONESHOT; return mask; } extern void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark, struct fsnotify_group *group); extern int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie); extern const struct fsnotify_ops inotify_fsnotify_ops; extern struct kmem_cache *inotify_inode_mark_cachep; #ifdef CONFIG_INOTIFY_USER static inline void dec_inotify_instances(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_INOTIFY_INSTANCES); } static inline struct ucounts *inc_inotify_watches(struct ucounts *ucounts) { return inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_INOTIFY_WATCHES); } static inline void dec_inotify_watches(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_INOTIFY_WATCHES); } #endif |
| 64 95 99 73 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM migrate #if !defined(_TRACE_MIGRATE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MIGRATE_H #include <linux/tracepoint.h> #define MIGRATE_MODE \ EM( MIGRATE_ASYNC, "MIGRATE_ASYNC") \ EM( MIGRATE_SYNC_LIGHT, "MIGRATE_SYNC_LIGHT") \ EMe(MIGRATE_SYNC, "MIGRATE_SYNC") #define MIGRATE_REASON \ EM( MR_COMPACTION, "compaction") \ EM( MR_MEMORY_FAILURE, "memory_failure") \ EM( MR_MEMORY_HOTPLUG, "memory_hotplug") \ EM( MR_SYSCALL, "syscall_or_cpuset") \ EM( MR_MEMPOLICY_MBIND, "mempolicy_mbind") \ EM( MR_NUMA_MISPLACED, "numa_misplaced") \ EM( MR_CONTIG_RANGE, "contig_range") \ EM( MR_LONGTERM_PIN, "longterm_pin") \ EM( MR_DEMOTION, "demotion") \ EMe(MR_DAMON, "damon") /* * First define the enums in the above macros to be exported to userspace * via TRACE_DEFINE_ENUM(). */ #undef EM #undef EMe #define EM(a, b) TRACE_DEFINE_ENUM(a); #define EMe(a, b) TRACE_DEFINE_ENUM(a); MIGRATE_MODE MIGRATE_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a, b) {a, b}, #define EMe(a, b) {a, b} TRACE_EVENT(mm_migrate_pages, TP_PROTO(unsigned long succeeded, unsigned long failed, unsigned long thp_succeeded, unsigned long thp_failed, unsigned long thp_split, unsigned long large_folio_split, enum migrate_mode mode, int reason), TP_ARGS(succeeded, failed, thp_succeeded, thp_failed, thp_split, large_folio_split, mode, reason), TP_STRUCT__entry( __field( unsigned long, succeeded) __field( unsigned long, failed) __field( unsigned long, thp_succeeded) __field( unsigned long, thp_failed) __field( unsigned long, thp_split) __field( unsigned long, large_folio_split) __field( enum migrate_mode, mode) __field( int, reason) ), TP_fast_assign( __entry->succeeded = succeeded; __entry->failed = failed; __entry->thp_succeeded = thp_succeeded; __entry->thp_failed = thp_failed; __entry->thp_split = thp_split; __entry->large_folio_split = large_folio_split; __entry->mode = mode; __entry->reason = reason; ), TP_printk("nr_succeeded=%lu nr_failed=%lu nr_thp_succeeded=%lu nr_thp_failed=%lu nr_thp_split=%lu nr_split=%lu mode=%s reason=%s", __entry->succeeded, __entry->failed, __entry->thp_succeeded, __entry->thp_failed, __entry->thp_split, __entry->large_folio_split, __print_symbolic(__entry->mode, MIGRATE_MODE), __print_symbolic(__entry->reason, MIGRATE_REASON)) ); TRACE_EVENT(mm_migrate_pages_start, TP_PROTO(enum migrate_mode mode, int reason), TP_ARGS(mode, reason), TP_STRUCT__entry( __field(enum migrate_mode, mode) __field(int, reason) ), TP_fast_assign( __entry->mode = mode; __entry->reason = reason; ), TP_printk("mode=%s reason=%s", __print_symbolic(__entry->mode, MIGRATE_MODE), __print_symbolic(__entry->reason, MIGRATE_REASON)) ); DECLARE_EVENT_CLASS(migration_pte, TP_PROTO(unsigned long addr, unsigned long pte, int order), TP_ARGS(addr, pte, order), TP_STRUCT__entry( __field(unsigned long, addr) __field(unsigned long, pte) __field(int, order) ), TP_fast_assign( __entry->addr = addr; __entry->pte = pte; __entry->order = order; ), TP_printk("addr=%lx, pte=%lx order=%d", __entry->addr, __entry->pte, __entry->order) ); DEFINE_EVENT(migration_pte, set_migration_pte, TP_PROTO(unsigned long addr, unsigned long pte, int order), TP_ARGS(addr, pte, order) ); DEFINE_EVENT(migration_pte, remove_migration_pte, TP_PROTO(unsigned long addr, unsigned long pte, int order), TP_ARGS(addr, pte, order) ); #endif /* _TRACE_MIGRATE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 4 4 4 25 25 21 21 21 21 24 24 4 4 4 1 4 4 4 4 1 1 4 4 4 4 8 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 2 2 2 2 2 4 6 6 6 6 6 6 6 6 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 6 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3: Implementation of the ICMP protocol layer. * * Alan Cox, <alan@lxorguk.ukuu.org.uk> * * Some of the function names and the icmp unreach table for this * module were derived from [icmp.c 1.0.11 06/02/93] by * Ross Biro, Fred N. van Kempen, Mark Evans, Alan Cox, Gerhard Koerting. * Other than that this module is a complete rewrite. * * Fixes: * Clemens Fruhwirth : introduce global icmp rate limiting * with icmp type masking ability instead * of broken per type icmp timeouts. * Mike Shaver : RFC1122 checks. * Alan Cox : Multicast ping reply as self. * Alan Cox : Fix atomicity lockup in ip_build_xmit * call. * Alan Cox : Added 216,128 byte paths to the MTU * code. * Martin Mares : RFC1812 checks. * Martin Mares : Can be configured to follow redirects * if acting as a router _without_ a * routing protocol (RFC 1812). * Martin Mares : Echo requests may be configured to * be ignored (RFC 1812). * Martin Mares : Limitation of ICMP error message * transmit rate (RFC 1812). * Martin Mares : TOS and Precedence set correctly * (RFC 1812). * Martin Mares : Now copying as much data from the * original packet as we can without * exceeding 576 bytes (RFC 1812). * Willy Konynenberg : Transparent proxying support. * Keith Owens : RFC1191 correction for 4.2BSD based * path MTU bug. * Thomas Quinot : ICMP Dest Unreach codes up to 15 are * valid (RFC 1812). * Andi Kleen : Check all packet lengths properly * and moved all kfree_skb() up to * icmp_rcv. * Andi Kleen : Move the rate limit bookkeeping * into the dest entry and use a token * bucket filter (thanks to ANK). Make * the rates sysctl configurable. * Yu Tianli : Fixed two ugly bugs in icmp_send * - IP option length was accounted wrongly * - ICMP header length was not accounted * at all. * Tristan Greaves : Added sysctl option to ignore bogus * broadcast responses from broken routers. * * To Fix: * * - Should use skb_pull() instead of all the manual checking. * This would also greatly simply some upper layer error handlers. --AK */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/string.h> #include <linux/netfilter_ipv4.h> #include <linux/slab.h> #include <net/snmp.h> #include <net/ip.h> #include <net/route.h> #include <net/protocol.h> #include <net/icmp.h> #include <net/tcp.h> #include <net/udp.h> #include <net/raw.h> #include <net/ping.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/init.h> #include <linux/uaccess.h> #include <net/checksum.h> #include <net/xfrm.h> #include <net/inet_common.h> #include <net/ip_fib.h> #include <net/l3mdev.h> #include <net/addrconf.h> #include <net/inet_dscp.h> #define CREATE_TRACE_POINTS #include <trace/events/icmp.h> /* * Build xmit assembly blocks */ struct icmp_bxm { struct sk_buff *skb; int offset; int data_len; struct { struct icmphdr icmph; __be32 times[3]; } data; int head_len; struct ip_options_data replyopts; }; /* An array of errno for error messages from dest unreach. */ /* RFC 1122: 3.2.2.1 States that NET_UNREACH, HOST_UNREACH and SR_FAILED MUST be considered 'transient errs'. */ const struct icmp_err icmp_err_convert[] = { { .errno = ENETUNREACH, /* ICMP_NET_UNREACH */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_UNREACH */ .fatal = 0, }, { .errno = ENOPROTOOPT /* ICMP_PROT_UNREACH */, .fatal = 1, }, { .errno = ECONNREFUSED, /* ICMP_PORT_UNREACH */ .fatal = 1, }, { .errno = EMSGSIZE, /* ICMP_FRAG_NEEDED */ .fatal = 0, }, { .errno = EOPNOTSUPP, /* ICMP_SR_FAILED */ .fatal = 0, }, { .errno = ENETUNREACH, /* ICMP_NET_UNKNOWN */ .fatal = 1, }, { .errno = EHOSTDOWN, /* ICMP_HOST_UNKNOWN */ .fatal = 1, }, { .errno = ENONET, /* ICMP_HOST_ISOLATED */ .fatal = 1, }, { .errno = ENETUNREACH, /* ICMP_NET_ANO */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_ANO */ .fatal = 1, }, { .errno = ENETUNREACH, /* ICMP_NET_UNR_TOS */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_UNR_TOS */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_PKT_FILTERED */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_PREC_VIOLATION */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_PREC_CUTOFF */ .fatal = 1, }, }; EXPORT_SYMBOL(icmp_err_convert); /* * ICMP control array. This specifies what to do with each ICMP. */ struct icmp_control { enum skb_drop_reason (*handler)(struct sk_buff *skb); short error; /* This ICMP is classed as an error message */ }; static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; static DEFINE_PER_CPU(struct sock *, ipv4_icmp_sk); /* Called with BH disabled */ static inline struct sock *icmp_xmit_lock(struct net *net) { struct sock *sk; sk = this_cpu_read(ipv4_icmp_sk); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path signals a * dst_link_failure() for an outgoing ICMP packet. */ return NULL; } sock_net_set(sk, net); return sk; } static inline void icmp_xmit_unlock(struct sock *sk) { sock_net_set(sk, &init_net); spin_unlock(&sk->sk_lock.slock); } /** * icmp_global_allow - Are we allowed to send one more ICMP message ? * @net: network namespace * * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec. * Returns false if we reached the limit and can not send another packet. * Works in tandem with icmp_global_consume(). */ bool icmp_global_allow(struct net *net) { u32 delta, now, oldstamp; int incr, new, old; /* Note: many cpus could find this condition true. * Then later icmp_global_consume() could consume more credits, * this is an acceptable race. */ if (atomic_read(&net->ipv4.icmp_global_credit) > 0) return true; now = jiffies; oldstamp = READ_ONCE(net->ipv4.icmp_global_stamp); delta = min_t(u32, now - oldstamp, HZ); if (delta < HZ / 50) return false; incr = READ_ONCE(net->ipv4.sysctl_icmp_msgs_per_sec) * delta / HZ; if (!incr) return false; if (cmpxchg(&net->ipv4.icmp_global_stamp, oldstamp, now) == oldstamp) { old = atomic_read(&net->ipv4.icmp_global_credit); do { new = min(old + incr, READ_ONCE(net->ipv4.sysctl_icmp_msgs_burst)); } while (!atomic_try_cmpxchg(&net->ipv4.icmp_global_credit, &old, new)); } return true; } EXPORT_SYMBOL(icmp_global_allow); void icmp_global_consume(struct net *net) { int credits = get_random_u32_below(3); /* Note: this might make icmp_global.credit negative. */ if (credits) atomic_sub(credits, &net->ipv4.icmp_global_credit); } EXPORT_SYMBOL(icmp_global_consume); static bool icmpv4_mask_allow(struct net *net, int type, int code) { if (type > NR_ICMP_TYPES) return true; /* Don't limit PMTU discovery. */ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) return true; /* Limit if icmp type is enabled in ratemask. */ if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask))) return true; return false; } static bool icmpv4_global_allow(struct net *net, int type, int code, bool *apply_ratelimit) { if (icmpv4_mask_allow(net, type, code)) return true; if (icmp_global_allow(net)) { *apply_ratelimit = true; return true; } __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL); return false; } /* * Send an ICMP frame. */ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, struct flowi4 *fl4, int type, int code, bool apply_ratelimit) { struct dst_entry *dst = &rt->dst; struct inet_peer *peer; bool rc = true; int vif; if (!apply_ratelimit) return true; /* No rate limit on loopback */ if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) goto out; vif = l3mdev_master_ifindex(dst->dev); peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1); rc = inet_peer_xrlim_allow(peer, READ_ONCE(net->ipv4.sysctl_icmp_ratelimit)); if (peer) inet_putpeer(peer); out: if (!rc) __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST); else icmp_global_consume(net); return rc; } /* * Maintain the counters used in the SNMP statistics for outgoing ICMP */ void icmp_out_count(struct net *net, unsigned char type) { ICMPMSGOUT_INC_STATS(net, type); ICMP_INC_STATS(net, ICMP_MIB_OUTMSGS); } /* * Checksum each fragment, and on the first include the headers and final * checksum. */ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct icmp_bxm *icmp_param = from; __wsum csum; csum = skb_copy_and_csum_bits(icmp_param->skb, icmp_param->offset + offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); if (icmp_pointers[icmp_param->data.icmph.type].error) nf_ct_attach(skb, icmp_param->skb); return 0; } static void icmp_push_reply(struct sock *sk, struct icmp_bxm *icmp_param, struct flowi4 *fl4, struct ipcm_cookie *ipc, struct rtable **rt) { struct sk_buff *skb; if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param, icmp_param->data_len+icmp_param->head_len, icmp_param->head_len, ipc, rt, MSG_DONTWAIT) < 0) { __ICMP_INC_STATS(sock_net(sk), ICMP_MIB_OUTERRORS); ip_flush_pending_frames(sk); } else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) { struct icmphdr *icmph = icmp_hdr(skb); __wsum csum; struct sk_buff *skb1; csum = csum_partial_copy_nocheck((void *)&icmp_param->data, (char *)icmph, icmp_param->head_len); skb_queue_walk(&sk->sk_write_queue, skb1) { csum = csum_add(csum, skb1->csum); } icmph->checksum = csum_fold(csum); skb->ip_summed = CHECKSUM_NONE; ip_push_pending_frames(sk, fl4); } } /* * Driving logic for building and sending ICMP messages. */ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) { struct ipcm_cookie ipc; struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->dst.dev); bool apply_ratelimit = false; struct flowi4 fl4; struct sock *sk; struct inet_sock *inet; __be32 daddr, saddr; u32 mark = IP4_REPLY_MARK(net, skb->mark); int type = icmp_param->data.icmph.type; int code = icmp_param->data.icmph.code; if (ip_options_echo(net, &icmp_param->replyopts.opt.opt, skb)) return; /* Needed by both icmpv4_global_allow and icmp_xmit_lock */ local_bh_disable(); /* is global icmp_msgs_per_sec exhausted ? */ if (!icmpv4_global_allow(net, type, code, &apply_ratelimit)) goto out_bh_enable; sk = icmp_xmit_lock(net); if (!sk) goto out_bh_enable; inet = inet_sk(sk); icmp_param->data.icmph.checksum = 0; ipcm_init(&ipc); inet->tos = ip_hdr(skb)->tos; ipc.sockc.mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); if (icmp_param->replyopts.opt.opt.optlen) { ipc.opt = &icmp_param->replyopts.opt; if (ipc.opt->opt.srr) daddr = icmp_param->replyopts.opt.opt.faddr; } memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_mark = mark; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK; fl4.flowi4_proto = IPPROTO_ICMP; fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) goto out_unlock; if (icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit)) icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt); ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); out_bh_enable: local_bh_enable(); } /* * The device used for looking up which routing table to use for sending an ICMP * error is preferably the source whenever it is set, which should ensure the * icmp error can be sent to the source host, else lookup using the routing * table of the destination device, else use the main routing table (index 0). */ static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb) { struct net_device *route_lookup_dev = NULL; if (skb->dev) route_lookup_dev = skb->dev; else if (skb_dst(skb)) route_lookup_dev = skb_dst(skb)->dev; return route_lookup_dev; } static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, const struct iphdr *iph, __be32 saddr, u8 tos, u32 mark, int type, int code, struct icmp_bxm *param) { struct net_device *route_lookup_dev; struct dst_entry *dst, *dst2; struct rtable *rt, *rt2; struct flowi4 fl4_dec; int err; memset(fl4, 0, sizeof(*fl4)); fl4->daddr = (param->replyopts.opt.opt.srr ? param->replyopts.opt.opt.faddr : iph->saddr); fl4->saddr = saddr; fl4->flowi4_mark = mark; fl4->flowi4_uid = sock_net_uid(net, NULL); fl4->flowi4_tos = tos & INET_DSCP_MASK; fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; route_lookup_dev = icmp_get_route_lookup_dev(skb_in); fl4->flowi4_oif = l3mdev_master_ifindex(route_lookup_dev); security_skb_classify_flow(skb_in, flowi4_to_flowi_common(fl4)); rt = ip_route_output_key_hash(net, fl4, skb_in); if (IS_ERR(rt)) return rt; /* No need to clone since we're just using its address. */ rt2 = rt; dst = xfrm_lookup(net, &rt->dst, flowi4_to_flowi(fl4), NULL, 0); rt = dst_rtable(dst); if (!IS_ERR(dst)) { if (rt != rt2) return rt; } else if (PTR_ERR(dst) == -EPERM) { rt = NULL; } else { return rt; } err = xfrm_decode_session_reverse(net, skb_in, flowi4_to_flowi(&fl4_dec), AF_INET); if (err) goto relookup_failed; if (inet_addr_type_dev_table(net, route_lookup_dev, fl4_dec.saddr) == RTN_LOCAL) { rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) err = PTR_ERR(rt2); } else { struct flowi4 fl4_2 = {}; unsigned long orefdst; fl4_2.daddr = fl4_dec.saddr; rt2 = ip_route_output_key(net, &fl4_2); if (IS_ERR(rt2)) { err = PTR_ERR(rt2); goto relookup_failed; } /* Ugh! */ orefdst = skb_in->_skb_refdst; /* save old refdst */ skb_dst_set(skb_in, NULL); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, tos, rt2->dst.dev); dst_release(&rt2->dst); rt2 = skb_rtable(skb_in); skb_in->_skb_refdst = orefdst; /* restore old refdst */ } if (err) goto relookup_failed; dst2 = xfrm_lookup(net, &rt2->dst, flowi4_to_flowi(&fl4_dec), NULL, XFRM_LOOKUP_ICMP); rt2 = dst_rtable(dst2); if (!IS_ERR(dst2)) { dst_release(&rt->dst); memcpy(fl4, &fl4_dec, sizeof(*fl4)); rt = rt2; } else if (PTR_ERR(dst2) == -EPERM) { if (rt) dst_release(&rt->dst); return rt2; } else { err = PTR_ERR(dst2); goto relookup_failed; } return rt; relookup_failed: if (rt) return rt; return ERR_PTR(err); } /* * Send an ICMP message in response to a situation * * RFC 1122: 3.2.2 MUST send at least the IP header and 8 bytes of header. * MAY send more (we do). * MUST NOT change this header information. * MUST NOT reply to a multicast/broadcast IP address. * MUST NOT reply to a multicast/broadcast MAC address. * MUST reply to only the first fragment. */ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, const struct ip_options *opt) { struct iphdr *iph; int room; struct icmp_bxm icmp_param; struct rtable *rt = skb_rtable(skb_in); bool apply_ratelimit = false; struct ipcm_cookie ipc; struct flowi4 fl4; __be32 saddr; u8 tos; u32 mark; struct net *net; struct sock *sk; if (!rt) goto out; if (rt->dst.dev) net = dev_net(rt->dst.dev); else if (skb_in->dev) net = dev_net(skb_in->dev); else goto out; /* * Find the original header. It is expected to be valid, of course. * Check this, icmp_send is called from the most obscure devices * sometimes. */ iph = ip_hdr(skb_in); if ((u8 *)iph < skb_in->head || (skb_network_header(skb_in) + sizeof(*iph)) > skb_tail_pointer(skb_in)) goto out; /* * No replies to physical multicast/broadcast */ if (skb_in->pkt_type != PACKET_HOST) goto out; /* * Now check at the protocol level */ if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto out; /* * Only reply to fragment 0. We byte re-order the constant * mask for efficiency. */ if (iph->frag_off & htons(IP_OFFSET)) goto out; /* * If we send an ICMP error to an ICMP error a mess would result.. */ if (icmp_pointers[type].error) { /* * We are an error, check if we are replying to an * ICMP error */ if (iph->protocol == IPPROTO_ICMP) { u8 _inner_type, *itp; itp = skb_header_pointer(skb_in, skb_network_header(skb_in) + (iph->ihl << 2) + offsetof(struct icmphdr, type) - skb_in->data, sizeof(_inner_type), &_inner_type); if (!itp) goto out; /* * Assume any unknown ICMP type is an error. This * isn't specified by the RFC, but think about it.. */ if (*itp > NR_ICMP_TYPES || icmp_pointers[*itp].error) goto out; } } /* Needed by both icmpv4_global_allow and icmp_xmit_lock */ local_bh_disable(); /* Check global sysctl_icmp_msgs_per_sec ratelimit, unless * incoming dev is loopback. If outgoing dev change to not be * loopback, then peer ratelimit still work (in icmpv4_xrlim_allow) */ if (!(skb_in->dev && (skb_in->dev->flags&IFF_LOOPBACK)) && !icmpv4_global_allow(net, type, code, &apply_ratelimit)) goto out_bh_enable; sk = icmp_xmit_lock(net); if (!sk) goto out_bh_enable; /* * Construct source address and options. */ saddr = iph->daddr; if (!(rt->rt_flags & RTCF_LOCAL)) { struct net_device *dev = NULL; rcu_read_lock(); if (rt_is_input_route(rt) && READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)) dev = dev_get_by_index_rcu(net, inet_iif(skb_in)); if (dev) saddr = inet_select_addr(dev, iph->saddr, RT_SCOPE_LINK); else saddr = 0; rcu_read_unlock(); } tos = icmp_pointers[type].error ? (RT_TOS(iph->tos) | IPTOS_PREC_INTERNETCONTROL) : iph->tos; mark = IP4_REPLY_MARK(net, skb_in->mark); if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt)) goto out_unlock; /* * Prepare data for ICMP header. */ icmp_param.data.icmph.type = type; icmp_param.data.icmph.code = code; icmp_param.data.icmph.un.gateway = info; icmp_param.data.icmph.checksum = 0; icmp_param.skb = skb_in; icmp_param.offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; ipcm_init(&ipc); ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts.opt; ipc.sockc.mark = mark; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark, type, code, &icmp_param); if (IS_ERR(rt)) goto out_unlock; /* peer icmp_ratelimit */ if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit)) goto ende; /* RFC says return as much as we can without exceeding 576 bytes. */ room = dst_mtu(&rt->dst); if (room > 576) room = 576; room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen; room -= sizeof(struct icmphdr); /* Guard against tiny mtu. We need to include at least one * IP network header for this message to make any sense. */ if (room <= (int)sizeof(struct iphdr)) goto ende; icmp_param.data_len = skb_in->len - icmp_param.offset; if (icmp_param.data_len > room) icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); /* if we don't have a source address at this point, fall back to the * dummy address instead of sending out a packet with a source address * of 0.0.0.0 */ if (!fl4.saddr) fl4.saddr = htonl(INADDR_DUMMY); trace_icmp_send(skb_in, type, code); icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); out_bh_enable: local_bh_enable(); out:; } EXPORT_SYMBOL(__icmp_send); #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_conntrack.h> void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct sk_buff *cloned_skb = NULL; struct ip_options opts = { 0 }; enum ip_conntrack_info ctinfo; struct nf_conn *ct; __be32 orig_ip; ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { __icmp_send(skb_in, type, code, info, &opts); return; } if (skb_shared(skb_in)) skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC); if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head || (skb_network_header(skb_in) + sizeof(struct iphdr)) > skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in, skb_network_offset(skb_in) + sizeof(struct iphdr)))) goto out; orig_ip = ip_hdr(skb_in)->saddr; ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; __icmp_send(skb_in, type, code, info, &opts); ip_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); } EXPORT_SYMBOL(icmp_ndo_send); #endif static void icmp_socket_deliver(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; const struct net_protocol *ipprot; int protocol = iph->protocol; /* Checkin full IP header plus 8 bytes of protocol to * avoid additional coding at protocol handlers. */ if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) { __ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS); return; } raw_icmp_error(skb, protocol, info); ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, info); } static bool icmp_tag_validation(int proto) { bool ok; rcu_read_lock(); ok = rcu_dereference(inet_protos[proto])->icmp_strict_tag_validation; rcu_read_unlock(); return ok; } /* * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEEDED, ICMP_QUENCH, and * ICMP_PARAMETERPROB. */ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb) { enum skb_drop_reason reason = SKB_NOT_DROPPED_YET; const struct iphdr *iph; struct icmphdr *icmph; struct net *net; u32 info = 0; net = dev_net(skb_dst(skb)->dev); /* * Incomplete header ? * Only checks for the IP header, there should be an * additional check for longer headers in upper levels. */ if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out_err; icmph = icmp_hdr(skb); iph = (const struct iphdr *)skb->data; if (iph->ihl < 5) { /* Mangled header, drop. */ reason = SKB_DROP_REASON_IP_INHDR; goto out_err; } switch (icmph->type) { case ICMP_DEST_UNREACH: switch (icmph->code & 15) { case ICMP_NET_UNREACH: case ICMP_HOST_UNREACH: case ICMP_PROT_UNREACH: case ICMP_PORT_UNREACH: break; case ICMP_FRAG_NEEDED: /* for documentation of the ip_no_pmtu_disc * values please see * Documentation/networking/ip-sysctl.rst */ switch (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) { default: net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n", &iph->daddr); break; case 2: goto out; case 3: if (!icmp_tag_validation(iph->protocol)) goto out; fallthrough; case 0: info = ntohs(icmph->un.frag.mtu); } break; case ICMP_SR_FAILED: net_dbg_ratelimited("%pI4: Source Route Failed\n", &iph->daddr); break; default: break; } if (icmph->code > NR_ICMP_UNREACH) goto out; break; case ICMP_PARAMETERPROB: info = ntohl(icmph->un.gateway) >> 24; break; case ICMP_TIME_EXCEEDED: __ICMP_INC_STATS(net, ICMP_MIB_INTIMEEXCDS); if (icmph->code == ICMP_EXC_FRAGTIME) goto out; break; } /* * Throw it at our lower layers * * RFC 1122: 3.2.2 MUST extract the protocol ID from the passed * header. * RFC 1122: 3.2.2.1 MUST pass ICMP unreach messages to the * transport layer. * RFC 1122: 3.2.2.2 MUST pass ICMP time expired messages to * transport layer. */ /* * Check the other end isn't violating RFC 1122. Some routers send * bogus responses to broadcast frames. If you see this message * first check your netmask matches at both ends, if it does then * get the other vendor to fix their kit. */ if (!READ_ONCE(net->ipv4.sysctl_icmp_ignore_bogus_error_responses) && inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) { net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n", &ip_hdr(skb)->saddr, icmph->type, icmph->code, &iph->daddr, skb->dev->name); goto out; } icmp_socket_deliver(skb, info); out: return reason; out_err: __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return reason ?: SKB_DROP_REASON_NOT_SPECIFIED; } /* * Handle ICMP_REDIRECT. */ static enum skb_drop_reason icmp_redirect(struct sk_buff *skb) { if (skb->len < sizeof(struct iphdr)) { __ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS); return SKB_DROP_REASON_PKT_TOO_SMALL; } if (!pskb_may_pull(skb, sizeof(struct iphdr))) { /* there aught to be a stat */ return SKB_DROP_REASON_NOMEM; } icmp_socket_deliver(skb, ntohl(icmp_hdr(skb)->un.gateway)); return SKB_NOT_DROPPED_YET; } /* * Handle ICMP_ECHO ("ping") and ICMP_EXT_ECHO ("PROBE") requests. * * RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo * requests. * RFC 1122: 3.2.2.6 Data received in the ICMP_ECHO request MUST be * included in the reply. * RFC 1812: 4.3.3.6 SHOULD have a config option for silently ignoring * echo requests, MUST have default=NOT. * RFC 8335: 8 MUST have a config option to enable/disable ICMP * Extended Echo Functionality, MUST be disabled by default * See also WRT handling of options once they are done and working. */ static enum skb_drop_reason icmp_echo(struct sk_buff *skb) { struct icmp_bxm icmp_param; struct net *net; net = dev_net(skb_dst(skb)->dev); /* should there be an ICMP stat for ignored echos? */ if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all)) return SKB_NOT_DROPPED_YET; icmp_param.data.icmph = *icmp_hdr(skb); icmp_param.skb = skb; icmp_param.offset = 0; icmp_param.data_len = skb->len; icmp_param.head_len = sizeof(struct icmphdr); if (icmp_param.data.icmph.type == ICMP_ECHO) icmp_param.data.icmph.type = ICMP_ECHOREPLY; else if (!icmp_build_probe(skb, &icmp_param.data.icmph)) return SKB_NOT_DROPPED_YET; icmp_reply(&icmp_param, skb); return SKB_NOT_DROPPED_YET; } /* Helper for icmp_echo and icmpv6_echo_reply. * Searches for net_device that matches PROBE interface identifier * and builds PROBE reply message in icmphdr. * * Returns false if PROBE responses are disabled via sysctl */ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) { struct icmp_ext_hdr *ext_hdr, _ext_hdr; struct icmp_ext_echo_iio *iio, _iio; struct net *net = dev_net(skb->dev); struct inet6_dev *in6_dev; struct in_device *in_dev; struct net_device *dev; char buff[IFNAMSIZ]; u16 ident_len; u8 status; if (!READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe)) return false; /* We currently only support probing interfaces on the proxy node * Check to ensure L-bit is set */ if (!(ntohs(icmphdr->un.echo.sequence) & 1)) return false; /* Clear status bits in reply message */ icmphdr->un.echo.sequence &= htons(0xFF00); if (icmphdr->type == ICMP_EXT_ECHO) icmphdr->type = ICMP_EXT_ECHOREPLY; else icmphdr->type = ICMPV6_EXT_ECHO_REPLY; ext_hdr = skb_header_pointer(skb, 0, sizeof(_ext_hdr), &_ext_hdr); /* Size of iio is class_type dependent. * Only check header here and assign length based on ctype in the switch statement */ iio = skb_header_pointer(skb, sizeof(_ext_hdr), sizeof(iio->extobj_hdr), &_iio); if (!ext_hdr || !iio) goto send_mal_query; if (ntohs(iio->extobj_hdr.length) <= sizeof(iio->extobj_hdr) || ntohs(iio->extobj_hdr.length) > sizeof(_iio)) goto send_mal_query; ident_len = ntohs(iio->extobj_hdr.length) - sizeof(iio->extobj_hdr); iio = skb_header_pointer(skb, sizeof(_ext_hdr), sizeof(iio->extobj_hdr) + ident_len, &_iio); if (!iio) goto send_mal_query; status = 0; dev = NULL; switch (iio->extobj_hdr.class_type) { case ICMP_EXT_ECHO_CTYPE_NAME: if (ident_len >= IFNAMSIZ) goto send_mal_query; memset(buff, 0, sizeof(buff)); memcpy(buff, &iio->ident.name, ident_len); dev = dev_get_by_name(net, buff); break; case ICMP_EXT_ECHO_CTYPE_INDEX: if (ident_len != sizeof(iio->ident.ifindex)) goto send_mal_query; dev = dev_get_by_index(net, ntohl(iio->ident.ifindex)); break; case ICMP_EXT_ECHO_CTYPE_ADDR: if (ident_len < sizeof(iio->ident.addr.ctype3_hdr) || ident_len != sizeof(iio->ident.addr.ctype3_hdr) + iio->ident.addr.ctype3_hdr.addrlen) goto send_mal_query; switch (ntohs(iio->ident.addr.ctype3_hdr.afi)) { case ICMP_AFI_IP: if (iio->ident.addr.ctype3_hdr.addrlen != sizeof(struct in_addr)) goto send_mal_query; dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr); break; #if IS_ENABLED(CONFIG_IPV6) case ICMP_AFI_IP6: if (iio->ident.addr.ctype3_hdr.addrlen != sizeof(struct in6_addr)) goto send_mal_query; dev = ipv6_stub->ipv6_dev_find(net, &iio->ident.addr.ip_addr.ipv6_addr, dev); dev_hold(dev); break; #endif default: goto send_mal_query; } break; default: goto send_mal_query; } if (!dev) { icmphdr->code = ICMP_EXT_CODE_NO_IF; return true; } /* Fill bits in reply message */ if (dev->flags & IFF_UP) status |= ICMP_EXT_ECHOREPLY_ACTIVE; in_dev = __in_dev_get_rcu(dev); if (in_dev && rcu_access_pointer(in_dev->ifa_list)) status |= ICMP_EXT_ECHOREPLY_IPV4; in6_dev = __in6_dev_get(dev); if (in6_dev && !list_empty(&in6_dev->addr_list)) status |= ICMP_EXT_ECHOREPLY_IPV6; dev_put(dev); icmphdr->un.echo.sequence |= htons(status); return true; send_mal_query: icmphdr->code = ICMP_EXT_CODE_MAL_QUERY; return true; } EXPORT_SYMBOL_GPL(icmp_build_probe); /* * Handle ICMP Timestamp requests. * RFC 1122: 3.2.2.8 MAY implement ICMP timestamp requests. * SHOULD be in the kernel for minimum random latency. * MUST be accurate to a few minutes. * MUST be updated at least at 15Hz. */ static enum skb_drop_reason icmp_timestamp(struct sk_buff *skb) { struct icmp_bxm icmp_param; /* * Too short. */ if (skb->len < 4) goto out_err; /* * Fill in the current time as ms since midnight UT: */ icmp_param.data.times[1] = inet_current_timestamp(); icmp_param.data.times[2] = icmp_param.data.times[1]; BUG_ON(skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4)); icmp_param.data.icmph = *icmp_hdr(skb); icmp_param.data.icmph.type = ICMP_TIMESTAMPREPLY; icmp_param.data.icmph.code = 0; icmp_param.skb = skb; icmp_param.offset = 0; icmp_param.data_len = 0; icmp_param.head_len = sizeof(struct icmphdr) + 12; icmp_reply(&icmp_param, skb); return SKB_NOT_DROPPED_YET; out_err: __ICMP_INC_STATS(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS); return SKB_DROP_REASON_PKT_TOO_SMALL; } static enum skb_drop_reason icmp_discard(struct sk_buff *skb) { /* pretend it was a success */ return SKB_NOT_DROPPED_YET; } /* * Deal with incoming ICMP packets. */ int icmp_rcv(struct sk_buff *skb) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->dst.dev); struct icmphdr *icmph; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { struct sec_path *sp = skb_sec_path(skb); int nh; if (!(sp && sp->xvec[sp->len - 1]->props.flags & XFRM_STATE_ICMP)) { reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; } if (!pskb_may_pull(skb, sizeof(*icmph) + sizeof(struct iphdr))) goto drop; nh = skb_network_offset(skb); skb_set_network_header(skb, sizeof(*icmph)); if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN, skb)) { reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; } skb_set_network_header(skb, nh); } __ICMP_INC_STATS(net, ICMP_MIB_INMSGS); if (skb_checksum_simple_validate(skb)) goto csum_error; if (!pskb_pull(skb, sizeof(*icmph))) goto error; icmph = icmp_hdr(skb); ICMPMSGIN_INC_STATS(net, icmph->type); /* Check for ICMP Extended Echo (PROBE) messages */ if (icmph->type == ICMP_EXT_ECHO) { /* We can't use icmp_pointers[].handler() because it is an array of * size NR_ICMP_TYPES + 1 (19 elements) and PROBE has code 42. */ reason = icmp_echo(skb); goto reason_check; } if (icmph->type == ICMP_EXT_ECHOREPLY) { reason = ping_rcv(skb); goto reason_check; } /* * 18 is the highest 'known' ICMP type. Anything else is a mystery * * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently * discarded. */ if (icmph->type > NR_ICMP_TYPES) { reason = SKB_DROP_REASON_UNHANDLED_PROTO; goto error; } /* * Parse the ICMP message */ if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { /* * RFC 1122: 3.2.2.6 An ICMP_ECHO to broadcast MAY be * silently ignored (we let user decide with a sysctl). * RFC 1122: 3.2.2.8 An ICMP_TIMESTAMP MAY be silently * discarded if to broadcast/multicast. */ if ((icmph->type == ICMP_ECHO || icmph->type == ICMP_TIMESTAMP) && READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_broadcasts)) { reason = SKB_DROP_REASON_INVALID_PROTO; goto error; } if (icmph->type != ICMP_ECHO && icmph->type != ICMP_TIMESTAMP && icmph->type != ICMP_ADDRESS && icmph->type != ICMP_ADDRESSREPLY) { reason = SKB_DROP_REASON_INVALID_PROTO; goto error; } } reason = icmp_pointers[icmph->type].handler(skb); reason_check: if (!reason) { consume_skb(skb); return NET_RX_SUCCESS; } drop: kfree_skb_reason(skb, reason); return NET_RX_DROP; csum_error: reason = SKB_DROP_REASON_ICMP_CSUM; __ICMP_INC_STATS(net, ICMP_MIB_CSUMERRORS); error: __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); goto drop; } static bool ip_icmp_error_rfc4884_validate(const struct sk_buff *skb, int off) { struct icmp_extobj_hdr *objh, _objh; struct icmp_ext_hdr *exth, _exth; u16 olen; exth = skb_header_pointer(skb, off, sizeof(_exth), &_exth); if (!exth) return false; if (exth->version != 2) return true; if (exth->checksum && csum_fold(skb_checksum(skb, off, skb->len - off, 0))) return false; off += sizeof(_exth); while (off < skb->len) { objh = skb_header_pointer(skb, off, sizeof(_objh), &_objh); if (!objh) return false; olen = ntohs(objh->length); if (olen < sizeof(_objh)) return false; off += olen; if (off > skb->len) return false; } return true; } void ip_icmp_error_rfc4884(const struct sk_buff *skb, struct sock_ee_data_rfc4884 *out, int thlen, int off) { int hlen; /* original datagram headers: end of icmph to payload (skb->data) */ hlen = -skb_transport_offset(skb) - thlen; /* per rfc 4884: minimal datagram length of 128 bytes */ if (off < 128 || off < hlen) return; /* kernel has stripped headers: return payload offset in bytes */ off -= hlen; if (off + sizeof(struct icmp_ext_hdr) > skb->len) return; out->len = off; if (!ip_icmp_error_rfc4884_validate(skb, off)) out->flags |= SO_EE_RFC4884_FLAG_INVALID; } EXPORT_SYMBOL_GPL(ip_icmp_error_rfc4884); int icmp_err(struct sk_buff *skb, u32 info) { struct iphdr *iph = (struct iphdr *)skb->data; int offset = iph->ihl<<2; struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset); int type = icmp_hdr(skb)->type; int code = icmp_hdr(skb)->code; struct net *net = dev_net(skb->dev); /* * Use ping_err to handle all icmp errors except those * triggered by ICMP_ECHOREPLY which sent from kernel. */ if (icmph->type != ICMP_ECHOREPLY) { ping_err(skb, offset, info); return 0; } if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ICMP); else if (type == ICMP_REDIRECT) ipv4_redirect(skb, net, 0, IPPROTO_ICMP); return 0; } /* * This table is the definition of how we handle ICMP. */ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = { [ICMP_ECHOREPLY] = { .handler = ping_rcv, }, [1] = { .handler = icmp_discard, .error = 1, }, [2] = { .handler = icmp_discard, .error = 1, }, [ICMP_DEST_UNREACH] = { .handler = icmp_unreach, .error = 1, }, [ICMP_SOURCE_QUENCH] = { .handler = icmp_unreach, .error = 1, }, [ICMP_REDIRECT] = { .handler = icmp_redirect, .error = 1, }, [6] = { .handler = icmp_discard, .error = 1, }, [7] = { .handler = icmp_discard, .error = 1, }, [ICMP_ECHO] = { .handler = icmp_echo, }, [9] = { .handler = icmp_discard, .error = 1, }, [10] = { .handler = icmp_discard, .error = 1, }, [ICMP_TIME_EXCEEDED] = { .handler = icmp_unreach, .error = 1, }, [ICMP_PARAMETERPROB] = { .handler = icmp_unreach, .error = 1, }, [ICMP_TIMESTAMP] = { .handler = icmp_timestamp, }, [ICMP_TIMESTAMPREPLY] = { .handler = icmp_discard, }, [ICMP_INFO_REQUEST] = { .handler = icmp_discard, }, [ICMP_INFO_REPLY] = { .handler = icmp_discard, }, [ICMP_ADDRESS] = { .handler = icmp_discard, }, [ICMP_ADDRESSREPLY] = { .handler = icmp_discard, }, }; static int __net_init icmp_sk_init(struct net *net) { /* Control parameters for ECHO replies. */ net->ipv4.sysctl_icmp_echo_ignore_all = 0; net->ipv4.sysctl_icmp_echo_enable_probe = 0; net->ipv4.sysctl_icmp_echo_ignore_broadcasts = 1; /* Control parameter - ignore bogus broadcast responses? */ net->ipv4.sysctl_icmp_ignore_bogus_error_responses = 1; /* * Configurable global rate limit. * * ratelimit defines tokens/packet consumed for dst->rate_token * bucket ratemask defines which icmp types are ratelimited by * setting it's bit position. * * default: * dest unreachable (3), source quench (4), * time exceeded (11), parameter problem (12) */ net->ipv4.sysctl_icmp_ratelimit = 1 * HZ; net->ipv4.sysctl_icmp_ratemask = 0x1818; net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; net->ipv4.sysctl_icmp_msgs_per_sec = 1000; net->ipv4.sysctl_icmp_msgs_burst = 50; return 0; } static struct pernet_operations __net_initdata icmp_sk_ops = { .init = icmp_sk_init, }; int __init icmp_init(void) { int err, i; for_each_possible_cpu(i) { struct sock *sk; err = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, IPPROTO_ICMP, &init_net); if (err < 0) return err; per_cpu(ipv4_icmp_sk, i) = sk; /* Enough space for 2 64K ICMP packets, including * sk_buff/skb_shared_info struct overhead. */ sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); /* * Speedup sock_wfree() */ sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT; } return register_pernet_subsys(&icmp_sk_ops); } |
| 2 2 10 10 10 22 22 22 3 3 21 22 21 3 3 22 22 21 10 10 15 12 3 22 22 1 1 1 3 3 3 3 3 3 3 3 3 3 22 22 10 10 10 10 10 10 22 22 22 10 10 10 10 10 10 10 10 11 11 11 10 10 10 9 9 9 3 3 3 3 3 3 3 3 3 3 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2001 Jens Axboe <axboe@kernel.dk> */ #include <linux/mm.h> #include <linux/swap.h> #include <linux/bio-integrity.h> #include <linux/blkdev.h> #include <linux/uio.h> #include <linux/iocontext.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/mempool.h> #include <linux/workqueue.h> #include <linux/cgroup.h> #include <linux/highmem.h> #include <linux/blk-crypto.h> #include <linux/xarray.h> #include <trace/events/block.h> #include "blk.h" #include "blk-rq-qos.h" #include "blk-cgroup.h" #define ALLOC_CACHE_THRESHOLD 16 #define ALLOC_CACHE_MAX 256 struct bio_alloc_cache { struct bio *free_list; struct bio *free_list_irq; unsigned int nr; unsigned int nr_irq; }; static struct biovec_slab { int nr_vecs; char *name; struct kmem_cache *slab; } bvec_slabs[] __read_mostly = { { .nr_vecs = 16, .name = "biovec-16" }, { .nr_vecs = 64, .name = "biovec-64" }, { .nr_vecs = 128, .name = "biovec-128" }, { .nr_vecs = BIO_MAX_VECS, .name = "biovec-max" }, }; static struct biovec_slab *biovec_slab(unsigned short nr_vecs) { switch (nr_vecs) { /* smaller bios use inline vecs */ case 5 ... 16: return &bvec_slabs[0]; case 17 ... 64: return &bvec_slabs[1]; case 65 ... 128: return &bvec_slabs[2]; case 129 ... BIO_MAX_VECS: return &bvec_slabs[3]; default: BUG(); return NULL; } } /* * fs_bio_set is the bio_set containing bio and iovec memory pools used by * IO code that does not need private memory pools. */ struct bio_set fs_bio_set; EXPORT_SYMBOL(fs_bio_set); /* * Our slab pool management */ struct bio_slab { struct kmem_cache *slab; unsigned int slab_ref; unsigned int slab_size; char name[8]; }; static DEFINE_MUTEX(bio_slab_lock); static DEFINE_XARRAY(bio_slabs); static struct bio_slab *create_bio_slab(unsigned int size) { struct bio_slab *bslab = kzalloc(sizeof(*bslab), GFP_KERNEL); if (!bslab) return NULL; snprintf(bslab->name, sizeof(bslab->name), "bio-%d", size); bslab->slab = kmem_cache_create(bslab->name, size, ARCH_KMALLOC_MINALIGN, SLAB_HWCACHE_ALIGN | SLAB_TYPESAFE_BY_RCU, NULL); if (!bslab->slab) goto fail_alloc_slab; bslab->slab_ref = 1; bslab->slab_size = size; if (!xa_err(xa_store(&bio_slabs, size, bslab, GFP_KERNEL))) return bslab; kmem_cache_destroy(bslab->slab); fail_alloc_slab: kfree(bslab); return NULL; } static inline unsigned int bs_bio_slab_size(struct bio_set *bs) { return bs->front_pad + sizeof(struct bio) + bs->back_pad; } static struct kmem_cache *bio_find_or_create_slab(struct bio_set *bs) { unsigned int size = bs_bio_slab_size(bs); struct bio_slab *bslab; mutex_lock(&bio_slab_lock); bslab = xa_load(&bio_slabs, size); if (bslab) bslab->slab_ref++; else bslab = create_bio_slab(size); mutex_unlock(&bio_slab_lock); if (bslab) return bslab->slab; return NULL; } static void bio_put_slab(struct bio_set *bs) { struct bio_slab *bslab = NULL; unsigned int slab_size = bs_bio_slab_size(bs); mutex_lock(&bio_slab_lock); bslab = xa_load(&bio_slabs, slab_size); if (WARN(!bslab, KERN_ERR "bio: unable to find slab!\n")) goto out; WARN_ON_ONCE(bslab->slab != bs->bio_slab); WARN_ON(!bslab->slab_ref); if (--bslab->slab_ref) goto out; xa_erase(&bio_slabs, slab_size); kmem_cache_destroy(bslab->slab); kfree(bslab); out: mutex_unlock(&bio_slab_lock); } void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs) { BUG_ON(nr_vecs > BIO_MAX_VECS); if (nr_vecs == BIO_MAX_VECS) mempool_free(bv, pool); else if (nr_vecs > BIO_INLINE_VECS) kmem_cache_free(biovec_slab(nr_vecs)->slab, bv); } /* * Make the first allocation restricted and don't dump info on allocation * failures, since we'll fall back to the mempool in case of failure. */ static inline gfp_t bvec_alloc_gfp(gfp_t gfp) { return (gfp & ~(__GFP_DIRECT_RECLAIM | __GFP_IO)) | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; } struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs, gfp_t gfp_mask) { struct biovec_slab *bvs = biovec_slab(*nr_vecs); if (WARN_ON_ONCE(!bvs)) return NULL; /* * Upgrade the nr_vecs request to take full advantage of the allocation. * We also rely on this in the bvec_free path. */ *nr_vecs = bvs->nr_vecs; /* * Try a slab allocation first for all smaller allocations. If that * fails and __GFP_DIRECT_RECLAIM is set retry with the mempool. * The mempool is sized to handle up to BIO_MAX_VECS entries. */ if (*nr_vecs < BIO_MAX_VECS) { struct bio_vec *bvl; bvl = kmem_cache_alloc(bvs->slab, bvec_alloc_gfp(gfp_mask)); if (likely(bvl) || !(gfp_mask & __GFP_DIRECT_RECLAIM)) return bvl; *nr_vecs = BIO_MAX_VECS; } return mempool_alloc(pool, gfp_mask); } void bio_uninit(struct bio *bio) { #ifdef CONFIG_BLK_CGROUP if (bio->bi_blkg) { blkg_put(bio->bi_blkg); bio->bi_blkg = NULL; } #endif if (bio_integrity(bio)) bio_integrity_free(bio); bio_crypt_free_ctx(bio); } EXPORT_SYMBOL(bio_uninit); static void bio_free(struct bio *bio) { struct bio_set *bs = bio->bi_pool; void *p = bio; WARN_ON_ONCE(!bs); bio_uninit(bio); bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs); mempool_free(p - bs->front_pad, &bs->bio_pool); } /* * Users of this function have their own bio allocation. Subsequently, * they must remember to pair any call to bio_init() with bio_uninit() * when IO has completed, or when the bio is released. */ void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, unsigned short max_vecs, blk_opf_t opf) { bio->bi_next = NULL; bio->bi_bdev = bdev; bio->bi_opf = opf; bio->bi_flags = 0; bio->bi_ioprio = 0; bio->bi_write_hint = 0; bio->bi_status = 0; bio->bi_iter.bi_sector = 0; bio->bi_iter.bi_size = 0; bio->bi_iter.bi_idx = 0; bio->bi_iter.bi_bvec_done = 0; bio->bi_end_io = NULL; bio->bi_private = NULL; #ifdef CONFIG_BLK_CGROUP bio->bi_blkg = NULL; bio->bi_issue.value = 0; if (bdev) bio_associate_blkg(bio); #ifdef CONFIG_BLK_CGROUP_IOCOST bio->bi_iocost_cost = 0; #endif #endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION bio->bi_crypt_context = NULL; #endif #ifdef CONFIG_BLK_DEV_INTEGRITY bio->bi_integrity = NULL; #endif bio->bi_vcnt = 0; atomic_set(&bio->__bi_remaining, 1); atomic_set(&bio->__bi_cnt, 1); bio->bi_cookie = BLK_QC_T_NONE; bio->bi_max_vecs = max_vecs; bio->bi_io_vec = table; bio->bi_pool = NULL; } EXPORT_SYMBOL(bio_init); /** * bio_reset - reinitialize a bio * @bio: bio to reset * @bdev: block device to use the bio for * @opf: operation and flags for bio * * Description: * After calling bio_reset(), @bio will be in the same state as a freshly * allocated bio returned bio bio_alloc_bioset() - the only fields that are * preserved are the ones that are initialized by bio_alloc_bioset(). See * comment in struct bio. */ void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf) { bio_uninit(bio); memset(bio, 0, BIO_RESET_BYTES); atomic_set(&bio->__bi_remaining, 1); bio->bi_bdev = bdev; if (bio->bi_bdev) bio_associate_blkg(bio); bio->bi_opf = opf; } EXPORT_SYMBOL(bio_reset); static struct bio *__bio_chain_endio(struct bio *bio) { struct bio *parent = bio->bi_private; if (bio->bi_status && !parent->bi_status) parent->bi_status = bio->bi_status; bio_put(bio); return parent; } static void bio_chain_endio(struct bio *bio) { bio_endio(__bio_chain_endio(bio)); } /** * bio_chain - chain bio completions * @bio: the target bio * @parent: the parent bio of @bio * * The caller won't have a bi_end_io called when @bio completes - instead, * @parent's bi_end_io won't be called until both @parent and @bio have * completed; the chained bio will also be freed when it completes. * * The caller must not set bi_private or bi_end_io in @bio. */ void bio_chain(struct bio *bio, struct bio *parent) { BUG_ON(bio->bi_private || bio->bi_end_io); bio->bi_private = parent; bio->bi_end_io = bio_chain_endio; bio_inc_remaining(parent); } EXPORT_SYMBOL(bio_chain); /** * bio_chain_and_submit - submit a bio after chaining it to another one * @prev: bio to chain and submit * @new: bio to chain to * * If @prev is non-NULL, chain it to @new and submit it. * * Return: @new. */ struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new) { if (prev) { bio_chain(prev, new); submit_bio(prev); } return new; } struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, blk_opf_t opf, gfp_t gfp) { return bio_chain_and_submit(bio, bio_alloc(bdev, nr_pages, opf, gfp)); } EXPORT_SYMBOL_GPL(blk_next_bio); static void bio_alloc_rescue(struct work_struct *work) { struct bio_set *bs = container_of(work, struct bio_set, rescue_work); struct bio *bio; while (1) { spin_lock(&bs->rescue_lock); bio = bio_list_pop(&bs->rescue_list); spin_unlock(&bs->rescue_lock); if (!bio) break; submit_bio_noacct(bio); } } static void punt_bios_to_rescuer(struct bio_set *bs) { struct bio_list punt, nopunt; struct bio *bio; if (WARN_ON_ONCE(!bs->rescue_workqueue)) return; /* * In order to guarantee forward progress we must punt only bios that * were allocated from this bio_set; otherwise, if there was a bio on * there for a stacking driver higher up in the stack, processing it * could require allocating bios from this bio_set, and doing that from * our own rescuer would be bad. * * Since bio lists are singly linked, pop them all instead of trying to * remove from the middle of the list: */ bio_list_init(&punt); bio_list_init(&nopunt); while ((bio = bio_list_pop(¤t->bio_list[0]))) bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio); current->bio_list[0] = nopunt; bio_list_init(&nopunt); while ((bio = bio_list_pop(¤t->bio_list[1]))) bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio); current->bio_list[1] = nopunt; spin_lock(&bs->rescue_lock); bio_list_merge(&bs->rescue_list, &punt); spin_unlock(&bs->rescue_lock); queue_work(bs->rescue_workqueue, &bs->rescue_work); } static void bio_alloc_irq_cache_splice(struct bio_alloc_cache *cache) { unsigned long flags; /* cache->free_list must be empty */ if (WARN_ON_ONCE(cache->free_list)) return; local_irq_save(flags); cache->free_list = cache->free_list_irq; cache->free_list_irq = NULL; cache->nr += cache->nr_irq; cache->nr_irq = 0; local_irq_restore(flags); } static struct bio *bio_alloc_percpu_cache(struct block_device *bdev, unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp, struct bio_set *bs) { struct bio_alloc_cache *cache; struct bio *bio; cache = per_cpu_ptr(bs->cache, get_cpu()); if (!cache->free_list) { if (READ_ONCE(cache->nr_irq) >= ALLOC_CACHE_THRESHOLD) bio_alloc_irq_cache_splice(cache); if (!cache->free_list) { put_cpu(); return NULL; } } bio = cache->free_list; cache->free_list = bio->bi_next; cache->nr--; put_cpu(); bio_init(bio, bdev, nr_vecs ? bio->bi_inline_vecs : NULL, nr_vecs, opf); bio->bi_pool = bs; return bio; } /** * bio_alloc_bioset - allocate a bio for I/O * @bdev: block device to allocate the bio for (can be %NULL) * @nr_vecs: number of bvecs to pre-allocate * @opf: operation and flags for bio * @gfp_mask: the GFP_* mask given to the slab allocator * @bs: the bio_set to allocate from. * * Allocate a bio from the mempools in @bs. * * If %__GFP_DIRECT_RECLAIM is set then bio_alloc will always be able to * allocate a bio. This is due to the mempool guarantees. To make this work, * callers must never allocate more than 1 bio at a time from the general pool. * Callers that need to allocate more than 1 bio must always submit the * previously allocated bio for IO before attempting to allocate a new one. * Failure to do so can cause deadlocks under memory pressure. * * Note that when running under submit_bio_noacct() (i.e. any block driver), * bios are not submitted until after you return - see the code in * submit_bio_noacct() that converts recursion into iteration, to prevent * stack overflows. * * This would normally mean allocating multiple bios under submit_bio_noacct() * would be susceptible to deadlocks, but we have * deadlock avoidance code that resubmits any blocked bios from a rescuer * thread. * * However, we do not guarantee forward progress for allocations from other * mempools. Doing multiple allocations from the same mempool under * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad * for per bio allocations. * * Returns: Pointer to new bio on success, NULL on failure. */ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp_mask, struct bio_set *bs) { gfp_t saved_gfp = gfp_mask; struct bio *bio; void *p; /* should not use nobvec bioset for nr_vecs > 0 */ if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_vecs > 0)) return NULL; if (opf & REQ_ALLOC_CACHE) { if (bs->cache && nr_vecs <= BIO_INLINE_VECS) { bio = bio_alloc_percpu_cache(bdev, nr_vecs, opf, gfp_mask, bs); if (bio) return bio; /* * No cached bio available, bio returned below marked with * REQ_ALLOC_CACHE to particpate in per-cpu alloc cache. */ } else { opf &= ~REQ_ALLOC_CACHE; } } /* * submit_bio_noacct() converts recursion to iteration; this means if * we're running beneath it, any bios we allocate and submit will not be * submitted (and thus freed) until after we return. * * This exposes us to a potential deadlock if we allocate multiple bios * from the same bio_set() while running underneath submit_bio_noacct(). * If we were to allocate multiple bios (say a stacking block driver * that was splitting bios), we would deadlock if we exhausted the * mempool's reserve. * * We solve this, and guarantee forward progress, with a rescuer * workqueue per bio_set. If we go to allocate and there are bios on * current->bio_list, we first try the allocation without * __GFP_DIRECT_RECLAIM; if that fails, we punt those bios we would be * blocking to the rescuer workqueue before we retry with the original * gfp_flags. */ if (current->bio_list && (!bio_list_empty(¤t->bio_list[0]) || !bio_list_empty(¤t->bio_list[1])) && bs->rescue_workqueue) gfp_mask &= ~__GFP_DIRECT_RECLAIM; p = mempool_alloc(&bs->bio_pool, gfp_mask); if (!p && gfp_mask != saved_gfp) { punt_bios_to_rescuer(bs); gfp_mask = saved_gfp; p = mempool_alloc(&bs->bio_pool, gfp_mask); } if (unlikely(!p)) return NULL; if (!mempool_is_saturated(&bs->bio_pool)) opf &= ~REQ_ALLOC_CACHE; bio = p + bs->front_pad; if (nr_vecs > BIO_INLINE_VECS) { struct bio_vec *bvl = NULL; bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask); if (!bvl && gfp_mask != saved_gfp) { punt_bios_to_rescuer(bs); gfp_mask = saved_gfp; bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask); } if (unlikely(!bvl)) goto err_free; bio_init(bio, bdev, bvl, nr_vecs, opf); } else if (nr_vecs) { bio_init(bio, bdev, bio->bi_inline_vecs, BIO_INLINE_VECS, opf); } else { bio_init(bio, bdev, NULL, 0, opf); } bio->bi_pool = bs; return bio; err_free: mempool_free(p, &bs->bio_pool); return NULL; } EXPORT_SYMBOL(bio_alloc_bioset); /** * bio_kmalloc - kmalloc a bio * @nr_vecs: number of bio_vecs to allocate * @gfp_mask: the GFP_* mask given to the slab allocator * * Use kmalloc to allocate a bio (including bvecs). The bio must be initialized * using bio_init() before use. To free a bio returned from this function use * kfree() after calling bio_uninit(). A bio returned from this function can * be reused by calling bio_uninit() before calling bio_init() again. * * Note that unlike bio_alloc() or bio_alloc_bioset() allocations from this * function are not backed by a mempool can fail. Do not use this function * for allocations in the file system I/O path. * * Returns: Pointer to new bio on success, NULL on failure. */ struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask) { struct bio *bio; if (nr_vecs > UIO_MAXIOV) return NULL; return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask); } EXPORT_SYMBOL(bio_kmalloc); void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start) { struct bio_vec bv; struct bvec_iter iter; __bio_for_each_segment(bv, bio, iter, start) memzero_bvec(&bv); } EXPORT_SYMBOL(zero_fill_bio_iter); /** * bio_truncate - truncate the bio to small size of @new_size * @bio: the bio to be truncated * @new_size: new size for truncating the bio * * Description: * Truncate the bio to new size of @new_size. If bio_op(bio) is * REQ_OP_READ, zero the truncated part. This function should only * be used for handling corner cases, such as bio eod. */ static void bio_truncate(struct bio *bio, unsigned new_size) { struct bio_vec bv; struct bvec_iter iter; unsigned int done = 0; bool truncated = false; if (new_size >= bio->bi_iter.bi_size) return; if (bio_op(bio) != REQ_OP_READ) goto exit; bio_for_each_segment(bv, bio, iter) { if (done + bv.bv_len > new_size) { unsigned offset; if (!truncated) offset = new_size - done; else offset = 0; zero_user(bv.bv_page, bv.bv_offset + offset, bv.bv_len - offset); truncated = true; } done += bv.bv_len; } exit: /* * Don't touch bvec table here and make it really immutable, since * fs bio user has to retrieve all pages via bio_for_each_segment_all * in its .end_bio() callback. * * It is enough to truncate bio by updating .bi_size since we can make * correct bvec with the updated .bi_size for drivers. */ bio->bi_iter.bi_size = new_size; } /** * guard_bio_eod - truncate a BIO to fit the block device * @bio: bio to truncate * * This allows us to do IO even on the odd last sectors of a device, even if the * block size is some multiple of the physical sector size. * * We'll just truncate the bio to the size of the device, and clear the end of * the buffer head manually. Truly out-of-range accesses will turn into actual * I/O errors, this only handles the "we need to be able to do I/O at the final * sector" case. */ void guard_bio_eod(struct bio *bio) { sector_t maxsector = bdev_nr_sectors(bio->bi_bdev); if (!maxsector) return; /* * If the *whole* IO is past the end of the device, * let it through, and the IO layer will turn it into * an EIO. */ if (unlikely(bio->bi_iter.bi_sector >= maxsector)) return; maxsector -= bio->bi_iter.bi_sector; if (likely((bio->bi_iter.bi_size >> 9) <= maxsector)) return; bio_truncate(bio, maxsector << 9); } static int __bio_alloc_cache_prune(struct bio_alloc_cache *cache, unsigned int nr) { unsigned int i = 0; struct bio *bio; while ((bio = cache->free_list) != NULL) { cache->free_list = bio->bi_next; cache->nr--; bio_free(bio); if (++i == nr) break; } return i; } static void bio_alloc_cache_prune(struct bio_alloc_cache *cache, unsigned int nr) { nr -= __bio_alloc_cache_prune(cache, nr); if (!READ_ONCE(cache->free_list)) { bio_alloc_irq_cache_splice(cache); __bio_alloc_cache_prune(cache, nr); } } static int bio_cpu_dead(unsigned int cpu, struct hlist_node *node) { struct bio_set *bs; bs = hlist_entry_safe(node, struct bio_set, cpuhp_dead); if (bs->cache) { struct bio_alloc_cache *cache = per_cpu_ptr(bs->cache, cpu); bio_alloc_cache_prune(cache, -1U); } return 0; } static void bio_alloc_cache_destroy(struct bio_set *bs) { int cpu; if (!bs->cache) return; cpuhp_state_remove_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead); for_each_possible_cpu(cpu) { struct bio_alloc_cache *cache; cache = per_cpu_ptr(bs->cache, cpu); bio_alloc_cache_prune(cache, -1U); } free_percpu(bs->cache); bs->cache = NULL; } static inline void bio_put_percpu_cache(struct bio *bio) { struct bio_alloc_cache *cache; cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu()); if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX) goto out_free; if (in_task()) { bio_uninit(bio); bio->bi_next = cache->free_list; /* Not necessary but helps not to iopoll already freed bios */ bio->bi_bdev = NULL; cache->free_list = bio; cache->nr++; } else if (in_hardirq()) { lockdep_assert_irqs_disabled(); bio_uninit(bio); bio->bi_next = cache->free_list_irq; cache->free_list_irq = bio; cache->nr_irq++; } else { goto out_free; } put_cpu(); return; out_free: put_cpu(); bio_free(bio); } /** * bio_put - release a reference to a bio * @bio: bio to release reference to * * Description: * Put a reference to a &struct bio, either one you have gotten with * bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it. **/ void bio_put(struct bio *bio) { if (unlikely(bio_flagged(bio, BIO_REFFED))) { BUG_ON(!atomic_read(&bio->__bi_cnt)); if (!atomic_dec_and_test(&bio->__bi_cnt)) return; } if (bio->bi_opf & REQ_ALLOC_CACHE) bio_put_percpu_cache(bio); else bio_free(bio); } EXPORT_SYMBOL(bio_put); static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) { bio_set_flag(bio, BIO_CLONED); bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter = bio_src->bi_iter; if (bio->bi_bdev) { if (bio->bi_bdev == bio_src->bi_bdev && bio_flagged(bio_src, BIO_REMAPPED)) bio_set_flag(bio, BIO_REMAPPED); bio_clone_blkg_association(bio, bio_src); } if (bio_crypt_clone(bio, bio_src, gfp) < 0) return -ENOMEM; if (bio_integrity(bio_src) && bio_integrity_clone(bio, bio_src, gfp) < 0) return -ENOMEM; return 0; } /** * bio_alloc_clone - clone a bio that shares the original bio's biovec * @bdev: block_device to clone onto * @bio_src: bio to clone from * @gfp: allocation priority * @bs: bio_set to allocate from * * Allocate a new bio that is a clone of @bio_src. The caller owns the returned * bio, but not the actual data it points to. * * The caller must ensure that the return bio is not freed before @bio_src. */ struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, gfp_t gfp, struct bio_set *bs) { struct bio *bio; bio = bio_alloc_bioset(bdev, 0, bio_src->bi_opf, gfp, bs); if (!bio) return NULL; if (__bio_clone(bio, bio_src, gfp) < 0) { bio_put(bio); return NULL; } bio->bi_io_vec = bio_src->bi_io_vec; return bio; } EXPORT_SYMBOL(bio_alloc_clone); /** * bio_init_clone - clone a bio that shares the original bio's biovec * @bdev: block_device to clone onto * @bio: bio to clone into * @bio_src: bio to clone from * @gfp: allocation priority * * Initialize a new bio in caller provided memory that is a clone of @bio_src. * The caller owns the returned bio, but not the actual data it points to. * * The caller must ensure that @bio_src is not freed before @bio. */ int bio_init_clone(struct block_device *bdev, struct bio *bio, struct bio *bio_src, gfp_t gfp) { int ret; bio_init(bio, bdev, bio_src->bi_io_vec, 0, bio_src->bi_opf); ret = __bio_clone(bio, bio_src, gfp); if (ret) bio_uninit(bio); return ret; } EXPORT_SYMBOL(bio_init_clone); /** * bio_full - check if the bio is full * @bio: bio to check * @len: length of one segment to be added * * Return true if @bio is full and one segment with @len bytes can't be * added to the bio, otherwise return false */ static inline bool bio_full(struct bio *bio, unsigned len) { if (bio->bi_vcnt >= bio->bi_max_vecs) return true; if (bio->bi_iter.bi_size > UINT_MAX - len) return true; return false; } static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page, unsigned int len, unsigned int off, bool *same_page) { size_t bv_end = bv->bv_offset + bv->bv_len; phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1; phys_addr_t page_addr = page_to_phys(page); if (vec_end_addr + 1 != page_addr + off) return false; if (xen_domain() && !xen_biovec_phys_mergeable(bv, page)) return false; if (!zone_device_pages_have_same_pgmap(bv->bv_page, page)) return false; *same_page = ((vec_end_addr & PAGE_MASK) == ((page_addr + off) & PAGE_MASK)); if (!*same_page) { if (IS_ENABLED(CONFIG_KMSAN)) return false; if (bv->bv_page + bv_end / PAGE_SIZE != page + off / PAGE_SIZE) return false; } bv->bv_len += len; return true; } /* * Try to merge a page into a segment, while obeying the hardware segment * size limit. This is not for normal read/write bios, but for passthrough * or Zone Append operations that we can't split. */ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, struct page *page, unsigned len, unsigned offset, bool *same_page) { unsigned long mask = queue_segment_boundary(q); phys_addr_t addr1 = bvec_phys(bv); phys_addr_t addr2 = page_to_phys(page) + offset + len - 1; if ((addr1 | mask) != (addr2 | mask)) return false; if (len > queue_max_segment_size(q) - bv->bv_len) return false; return bvec_try_merge_page(bv, page, len, offset, same_page); } /** * bio_add_hw_page - attempt to add a page to a bio with hw constraints * @q: the target queue * @bio: destination bio * @page: page to add * @len: vec entry length * @offset: vec entry offset * @max_sectors: maximum number of sectors that can be added * @same_page: return if the segment has been merged inside the same page * * Add a page to a bio while respecting the hardware max_sectors, max_segment * and gap limitations. */ int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page) { unsigned int max_size = max_sectors << SECTOR_SHIFT; if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return 0; len = min3(len, max_size, queue_max_segment_size(q)); if (len > max_size - bio->bi_iter.bi_size) return 0; if (bio->bi_vcnt > 0) { struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; if (bvec_try_merge_hw_page(q, bv, page, len, offset, same_page)) { bio->bi_iter.bi_size += len; return len; } if (bio->bi_vcnt >= min(bio->bi_max_vecs, queue_max_segments(q))) return 0; /* * If the queue doesn't support SG gaps and adding this segment * would create a gap, disallow it. */ if (bvec_gap_to_prev(&q->limits, bv, offset)) return 0; } bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, offset); bio->bi_vcnt++; bio->bi_iter.bi_size += len; return len; } /** * bio_add_hw_folio - attempt to add a folio to a bio with hw constraints * @q: the target queue * @bio: destination bio * @folio: folio to add * @len: vec entry length * @offset: vec entry offset in the folio * @max_sectors: maximum number of sectors that can be added * @same_page: return if the segment has been merged inside the same folio * * Add a folio to a bio while respecting the hardware max_sectors, max_segment * and gap limitations. */ int bio_add_hw_folio(struct request_queue *q, struct bio *bio, struct folio *folio, size_t len, size_t offset, unsigned int max_sectors, bool *same_page) { if (len > UINT_MAX || offset > UINT_MAX) return 0; return bio_add_hw_page(q, bio, folio_page(folio, 0), len, offset, max_sectors, same_page); } /** * bio_add_pc_page - attempt to add page to passthrough bio * @q: the target queue * @bio: destination bio * @page: page to add * @len: vec entry length * @offset: vec entry offset * * Attempt to add a page to the bio_vec maplist. This can fail for a * number of reasons, such as the bio being full or target block device * limitations. The target block device must allow bio's up to PAGE_SIZE, * so it is always possible to add a single page to an empty bio. * * This should only be used by passthrough bios. */ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { bool same_page = false; return bio_add_hw_page(q, bio, page, len, offset, queue_max_hw_sectors(q), &same_page); } EXPORT_SYMBOL(bio_add_pc_page); /** * bio_add_zone_append_page - attempt to add page to zone-append bio * @bio: destination bio * @page: page to add * @len: vec entry length * @offset: vec entry offset * * Attempt to add a page to the bio_vec maplist of a bio that will be submitted * for a zone-append request. This can fail for a number of reasons, such as the * bio being full or the target block device is not a zoned block device or * other limitations of the target block device. The target block device must * allow bio's up to PAGE_SIZE, so it is always possible to add a single page * to an empty bio. * * Returns: number of bytes added to the bio, or 0 in case of a failure. */ int bio_add_zone_append_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); bool same_page = false; if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_ZONE_APPEND)) return 0; if (WARN_ON_ONCE(!bdev_is_zoned(bio->bi_bdev))) return 0; return bio_add_hw_page(q, bio, page, len, offset, queue_max_zone_append_sectors(q), &same_page); } EXPORT_SYMBOL_GPL(bio_add_zone_append_page); /** * __bio_add_page - add page(s) to a bio in a new segment * @bio: destination bio * @page: start page to add * @len: length of the data to add, may cross pages * @off: offset of the data relative to @page, may cross pages * * Add the data at @page + @off to @bio as a new bvec. The caller must ensure * that @bio has space for another bvec. */ void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); WARN_ON_ONCE(bio_full(bio, len)); bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, off); bio->bi_iter.bi_size += len; bio->bi_vcnt++; } EXPORT_SYMBOL_GPL(__bio_add_page); /** * bio_add_page - attempt to add page(s) to bio * @bio: destination bio * @page: start page to add * @len: vec entry length, may cross pages * @offset: vec entry offset relative to @page, may cross pages * * Attempt to add page(s) to the bio_vec maplist. This will only fail * if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio. */ int bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { bool same_page = false; if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return 0; if (bio->bi_iter.bi_size > UINT_MAX - len) return 0; if (bio->bi_vcnt > 0 && bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1], page, len, offset, &same_page)) { bio->bi_iter.bi_size += len; return len; } if (bio->bi_vcnt >= bio->bi_max_vecs) return 0; __bio_add_page(bio, page, len, offset); return len; } EXPORT_SYMBOL(bio_add_page); void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, size_t off) { WARN_ON_ONCE(len > UINT_MAX); WARN_ON_ONCE(off > UINT_MAX); __bio_add_page(bio, &folio->page, len, off); } EXPORT_SYMBOL_GPL(bio_add_folio_nofail); /** * bio_add_folio - Attempt to add part of a folio to a bio. * @bio: BIO to add to. * @folio: Folio to add. * @len: How many bytes from the folio to add. * @off: First byte in this folio to add. * * Filesystems that use folios can call this function instead of calling * bio_add_page() for each page in the folio. If @off is bigger than * PAGE_SIZE, this function can create a bio_vec that starts in a page * after the bv_page. BIOs do not support folios that are 4GiB or larger. * * Return: Whether the addition was successful. */ bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len, size_t off) { if (len > UINT_MAX || off > UINT_MAX) return false; return bio_add_page(bio, &folio->page, len, off) > 0; } EXPORT_SYMBOL(bio_add_folio); void __bio_release_pages(struct bio *bio, bool mark_dirty) { struct folio_iter fi; bio_for_each_folio_all(fi, bio) { size_t nr_pages; if (mark_dirty) { folio_lock(fi.folio); folio_mark_dirty(fi.folio); folio_unlock(fi.folio); } nr_pages = (fi.offset + fi.length - 1) / PAGE_SIZE - fi.offset / PAGE_SIZE + 1; unpin_user_folio(fi.folio, nr_pages); } } EXPORT_SYMBOL_GPL(__bio_release_pages); void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) { size_t size = iov_iter_count(iter); WARN_ON_ONCE(bio->bi_max_vecs); if (bio_op(bio) == REQ_OP_ZONE_APPEND) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); size_t max_sectors = queue_max_zone_append_sectors(q); size = min(size, max_sectors << SECTOR_SHIFT); } bio->bi_vcnt = iter->nr_segs; bio->bi_io_vec = (struct bio_vec *)iter->bvec; bio->bi_iter.bi_bvec_done = iter->iov_offset; bio->bi_iter.bi_size = size; bio_set_flag(bio, BIO_CLONED); } static int bio_iov_add_folio(struct bio *bio, struct folio *folio, size_t len, size_t offset) { bool same_page = false; if (WARN_ON_ONCE(bio->bi_iter.bi_size > UINT_MAX - len)) return -EIO; if (bio->bi_vcnt > 0 && bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1], folio_page(folio, 0), len, offset, &same_page)) { bio->bi_iter.bi_size += len; if (same_page && bio_flagged(bio, BIO_PAGE_PINNED)) unpin_user_folio(folio, 1); return 0; } bio_add_folio_nofail(bio, folio, len, offset); return 0; } static int bio_iov_add_zone_append_folio(struct bio *bio, struct folio *folio, size_t len, size_t offset) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); bool same_page = false; if (bio_add_hw_folio(q, bio, folio, len, offset, queue_max_zone_append_sectors(q), &same_page) != len) return -EINVAL; if (same_page && bio_flagged(bio, BIO_PAGE_PINNED)) unpin_user_folio(folio, 1); return 0; } static unsigned int get_contig_folio_len(unsigned int *num_pages, struct page **pages, unsigned int i, struct folio *folio, size_t left, size_t offset) { size_t bytes = left; size_t contig_sz = min_t(size_t, PAGE_SIZE - offset, bytes); unsigned int j; /* * We might COW a single page in the middle of * a large folio, so we have to check that all * pages belong to the same folio. */ bytes -= contig_sz; for (j = i + 1; j < i + *num_pages; j++) { size_t next = min_t(size_t, PAGE_SIZE, bytes); if (page_folio(pages[j]) != folio || pages[j] != pages[j - 1] + 1) { break; } contig_sz += next; bytes -= next; } *num_pages = j - i; return contig_sz; } #define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *)) /** * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be mapped * * Extracts pages from *iter and appends them to @bio's bvec array. The pages * will have to be cleaned up in the way indicated by the BIO_PAGE_PINNED flag. * For a multi-segment *iter, this function only adds pages from the next * non-empty segment of the iov iterator. */ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { iov_iter_extraction_t extraction_flags = 0; unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; ssize_t size; unsigned int num_pages, i = 0; size_t offset, folio_offset, left, len; int ret = 0; /* * Move page array up in the allocated memory for the bio vecs as far as * possible so that we can start filling biovecs from the beginning * without overwriting the temporary page array. */ BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2); pages += entries_left * (PAGE_PTRS_PER_BVEC - 1); if (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue)) extraction_flags |= ITER_ALLOW_P2PDMA; /* * Each segment in the iov is required to be a block size multiple. * However, we may not be able to get the entire segment if it spans * more pages than bi_max_vecs allows, so we have to ALIGN_DOWN the * result to ensure the bio's total size is correct. The remainder of * the iov data will be picked up in the next bio iteration. */ size = iov_iter_extract_pages(iter, &pages, UINT_MAX - bio->bi_iter.bi_size, nr_pages, extraction_flags, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE); if (bio->bi_bdev) { size_t trim = size & (bdev_logical_block_size(bio->bi_bdev) - 1); iov_iter_revert(iter, trim); size -= trim; } if (unlikely(!size)) { ret = -EFAULT; goto out; } for (left = size, i = 0; left > 0; left -= len, i += num_pages) { struct page *page = pages[i]; struct folio *folio = page_folio(page); folio_offset = ((size_t)folio_page_idx(folio, page) << PAGE_SHIFT) + offset; len = min(folio_size(folio) - folio_offset, left); num_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE); if (num_pages > 1) len = get_contig_folio_len(&num_pages, pages, i, folio, left, offset); if (bio_op(bio) == REQ_OP_ZONE_APPEND) { ret = bio_iov_add_zone_append_folio(bio, folio, len, folio_offset); if (ret) break; } else bio_iov_add_folio(bio, folio, len, folio_offset); offset = 0; } iov_iter_revert(iter, left); out: while (i < nr_pages) bio_release_page(bio, pages[i++]); return ret; } /** * bio_iov_iter_get_pages - add user or kernel pages to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be added * * This takes either an iterator pointing to user memory, or one pointing to * kernel pages (BVEC iterator). If we're adding user pages, we pin them and * map them into the kernel. On IO completion, the caller should put those * pages. For bvec based iterators bio_iov_iter_get_pages() uses the provided * bvecs rather than copying them. Hence anyone issuing kiocb based IO needs * to ensure the bvecs and pages stay referenced until the submitted I/O is * completed by a call to ->ki_complete() or returns with an error other than * -EIOCBQUEUED. The caller needs to check if the bio is flagged BIO_NO_PAGE_REF * on IO completion. If it isn't, then pages should be released. * * The function tries, but does not guarantee, to pin as many pages as * fit into the bio, or are requested in @iter, whatever is smaller. If * MM encounters an error pinning the requested pages, it stops. Error * is returned only if 0 pages could be pinned. */ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { int ret = 0; if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return -EIO; if (iov_iter_is_bvec(iter)) { bio_iov_bvec_set(bio, iter); iov_iter_advance(iter, bio->bi_iter.bi_size); return 0; } if (iov_iter_extract_will_pin(iter)) bio_set_flag(bio, BIO_PAGE_PINNED); do { ret = __bio_iov_iter_get_pages(bio, iter); } while (!ret && iov_iter_count(iter) && !bio_full(bio, 0)); return bio->bi_vcnt ? 0 : ret; } EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); static void submit_bio_wait_endio(struct bio *bio) { complete(bio->bi_private); } /** * submit_bio_wait - submit a bio, and wait until it completes * @bio: The &struct bio which describes the I/O * * Simple wrapper around submit_bio(). Returns 0 on success, or the error from * bio_endio() on failure. * * WARNING: Unlike to how submit_bio() is usually used, this function does not * result in bio reference to be consumed. The caller must drop the reference * on his own. */ int submit_bio_wait(struct bio *bio) { DECLARE_COMPLETION_ONSTACK_MAP(done, bio->bi_bdev->bd_disk->lockdep_map); bio->bi_private = &done; bio->bi_end_io = submit_bio_wait_endio; bio->bi_opf |= REQ_SYNC; submit_bio(bio); blk_wait_io(&done); return blk_status_to_errno(bio->bi_status); } EXPORT_SYMBOL(submit_bio_wait); static void bio_wait_end_io(struct bio *bio) { complete(bio->bi_private); bio_put(bio); } /* * bio_await_chain - ends @bio and waits for every chained bio to complete */ void bio_await_chain(struct bio *bio) { DECLARE_COMPLETION_ONSTACK_MAP(done, bio->bi_bdev->bd_disk->lockdep_map); bio->bi_private = &done; bio->bi_end_io = bio_wait_end_io; bio_endio(bio); blk_wait_io(&done); } void __bio_advance(struct bio *bio, unsigned bytes) { if (bio_integrity(bio)) bio_integrity_advance(bio, bytes); bio_crypt_advance(bio, bytes); bio_advance_iter(bio, &bio->bi_iter, bytes); } EXPORT_SYMBOL(__bio_advance); void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter) { while (src_iter->bi_size && dst_iter->bi_size) { struct bio_vec src_bv = bio_iter_iovec(src, *src_iter); struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter); unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len); void *src_buf = bvec_kmap_local(&src_bv); void *dst_buf = bvec_kmap_local(&dst_bv); memcpy(dst_buf, src_buf, bytes); kunmap_local(dst_buf); kunmap_local(src_buf); bio_advance_iter_single(src, src_iter, bytes); bio_advance_iter_single(dst, dst_iter, bytes); } } EXPORT_SYMBOL(bio_copy_data_iter); /** * bio_copy_data - copy contents of data buffers from one bio to another * @src: source bio * @dst: destination bio * * Stops when it reaches the end of either @src or @dst - that is, copies * min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios). */ void bio_copy_data(struct bio *dst, struct bio *src) { struct bvec_iter src_iter = src->bi_iter; struct bvec_iter dst_iter = dst->bi_iter; bio_copy_data_iter(dst, &dst_iter, src, &src_iter); } EXPORT_SYMBOL(bio_copy_data); void bio_free_pages(struct bio *bio) { struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) __free_page(bvec->bv_page); } EXPORT_SYMBOL(bio_free_pages); /* * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions * for performing direct-IO in BIOs. * * The problem is that we cannot run folio_mark_dirty() from interrupt context * because the required locks are not interrupt-safe. So what we can do is to * mark the pages dirty _before_ performing IO. And in interrupt context, * check that the pages are still dirty. If so, fine. If not, redirty them * in process context. * * Note that this code is very hard to test under normal circumstances because * direct-io pins the pages with get_user_pages(). This makes * is_page_cache_freeable return false, and the VM will not clean the pages. * But other code (eg, flusher threads) could clean the pages if they are mapped * pagecache. * * Simply disabling the call to bio_set_pages_dirty() is a good way to test the * deferred bio dirtying paths. */ /* * bio_set_pages_dirty() will mark all the bio's pages as dirty. */ void bio_set_pages_dirty(struct bio *bio) { struct folio_iter fi; bio_for_each_folio_all(fi, bio) { folio_lock(fi.folio); folio_mark_dirty(fi.folio); folio_unlock(fi.folio); } } EXPORT_SYMBOL_GPL(bio_set_pages_dirty); /* * bio_check_pages_dirty() will check that all the BIO's pages are still dirty. * If they are, then fine. If, however, some pages are clean then they must * have been written out during the direct-IO read. So we take another ref on * the BIO and re-dirty the pages in process context. * * It is expected that bio_check_pages_dirty() will wholly own the BIO from * here on. It will unpin each page and will run one bio_put() against the * BIO. */ static void bio_dirty_fn(struct work_struct *work); static DECLARE_WORK(bio_dirty_work, bio_dirty_fn); static DEFINE_SPINLOCK(bio_dirty_lock); static struct bio *bio_dirty_list; /* * This runs in process context */ static void bio_dirty_fn(struct work_struct *work) { struct bio *bio, *next; spin_lock_irq(&bio_dirty_lock); next = bio_dirty_list; bio_dirty_list = NULL; spin_unlock_irq(&bio_dirty_lock); while ((bio = next) != NULL) { next = bio->bi_private; bio_release_pages(bio, true); bio_put(bio); } } void bio_check_pages_dirty(struct bio *bio) { struct folio_iter fi; unsigned long flags; bio_for_each_folio_all(fi, bio) { if (!folio_test_dirty(fi.folio)) goto defer; } bio_release_pages(bio, false); bio_put(bio); return; defer: spin_lock_irqsave(&bio_dirty_lock, flags); bio->bi_private = bio_dirty_list; bio_dirty_list = bio; spin_unlock_irqrestore(&bio_dirty_lock, flags); schedule_work(&bio_dirty_work); } EXPORT_SYMBOL_GPL(bio_check_pages_dirty); static inline bool bio_remaining_done(struct bio *bio) { /* * If we're not chaining, then ->__bi_remaining is always 1 and * we always end io on the first invocation. */ if (!bio_flagged(bio, BIO_CHAIN)) return true; BUG_ON(atomic_read(&bio->__bi_remaining) <= 0); if (atomic_dec_and_test(&bio->__bi_remaining)) { bio_clear_flag(bio, BIO_CHAIN); return true; } return false; } /** * bio_endio - end I/O on a bio * @bio: bio * * Description: * bio_endio() will end I/O on the whole bio. bio_endio() is the preferred * way to end I/O on a bio. No one should call bi_end_io() directly on a * bio unless they own it and thus know that it has an end_io function. * * bio_endio() can be called several times on a bio that has been chained * using bio_chain(). The ->bi_end_io() function will only be called the * last time. **/ void bio_endio(struct bio *bio) { again: if (!bio_remaining_done(bio)) return; if (!bio_integrity_endio(bio)) return; blk_zone_bio_endio(bio); rq_qos_done_bio(bio); if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) { trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio); bio_clear_flag(bio, BIO_TRACE_COMPLETION); } /* * Need to have a real endio function for chained bios, otherwise * various corner cases will break (like stacking block devices that * save/restore bi_end_io) - however, we want to avoid unbounded * recursion and blowing the stack. Tail call optimization would * handle this, but compiling with frame pointers also disables * gcc's sibling call optimization. */ if (bio->bi_end_io == bio_chain_endio) { bio = __bio_chain_endio(bio); goto again; } #ifdef CONFIG_BLK_CGROUP /* * Release cgroup info. We shouldn't have to do this here, but quite * a few callers of bio_init fail to call bio_uninit, so we cover up * for that here at least for now. */ if (bio->bi_blkg) { blkg_put(bio->bi_blkg); bio->bi_blkg = NULL; } #endif if (bio->bi_end_io) bio->bi_end_io(bio); } EXPORT_SYMBOL(bio_endio); /** * bio_split - split a bio * @bio: bio to split * @sectors: number of sectors to split from the front of @bio * @gfp: gfp mask * @bs: bio set to allocate from * * Allocates and returns a new bio which represents @sectors from the start of * @bio, and updates @bio to represent the remaining sectors. * * Unless this is a discard request the newly allocated bio will point * to @bio's bi_io_vec. It is the caller's responsibility to ensure that * neither @bio nor @bs are freed before the split bio. */ struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs) { struct bio *split; BUG_ON(sectors <= 0); BUG_ON(sectors >= bio_sectors(bio)); /* Zone append commands cannot be split */ if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND)) return NULL; split = bio_alloc_clone(bio->bi_bdev, bio, gfp, bs); if (!split) return NULL; split->bi_iter.bi_size = sectors << 9; if (bio_integrity(split)) bio_integrity_trim(split); bio_advance(bio, split->bi_iter.bi_size); if (bio_flagged(bio, BIO_TRACE_COMPLETION)) bio_set_flag(split, BIO_TRACE_COMPLETION); return split; } EXPORT_SYMBOL(bio_split); /** * bio_trim - trim a bio * @bio: bio to trim * @offset: number of sectors to trim from the front of @bio * @size: size we want to trim @bio to, in sectors * * This function is typically used for bios that are cloned and submitted * to the underlying device in parts. */ void bio_trim(struct bio *bio, sector_t offset, sector_t size) { if (WARN_ON_ONCE(offset > BIO_MAX_SECTORS || size > BIO_MAX_SECTORS || offset + size > bio_sectors(bio))) return; size <<= 9; if (offset == 0 && size == bio->bi_iter.bi_size) return; bio_advance(bio, offset << 9); bio->bi_iter.bi_size = size; if (bio_integrity(bio)) bio_integrity_trim(bio); } EXPORT_SYMBOL_GPL(bio_trim); /* * create memory pools for biovec's in a bio_set. * use the global biovec slabs created for general use. */ int biovec_init_pool(mempool_t *pool, int pool_entries) { struct biovec_slab *bp = bvec_slabs + ARRAY_SIZE(bvec_slabs) - 1; return mempool_init_slab_pool(pool, pool_entries, bp->slab); } /* * bioset_exit - exit a bioset initialized with bioset_init() * * May be called on a zeroed but uninitialized bioset (i.e. allocated with * kzalloc()). */ void bioset_exit(struct bio_set *bs) { bio_alloc_cache_destroy(bs); if (bs->rescue_workqueue) destroy_workqueue(bs->rescue_workqueue); bs->rescue_workqueue = NULL; mempool_exit(&bs->bio_pool); mempool_exit(&bs->bvec_pool); bioset_integrity_free(bs); if (bs->bio_slab) bio_put_slab(bs); bs->bio_slab = NULL; } EXPORT_SYMBOL(bioset_exit); /** * bioset_init - Initialize a bio_set * @bs: pool to initialize * @pool_size: Number of bio and bio_vecs to cache in the mempool * @front_pad: Number of bytes to allocate in front of the returned bio * @flags: Flags to modify behavior, currently %BIOSET_NEED_BVECS * and %BIOSET_NEED_RESCUER * * Description: * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller * to ask for a number of bytes to be allocated in front of the bio. * Front pad allocation is useful for embedding the bio inside * another structure, to avoid allocating extra data to go with the bio. * Note that the bio must be embedded at the END of that structure always, * or things will break badly. * If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated * for allocating iovecs. This pool is not needed e.g. for bio_init_clone(). * If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used * to dispatch queued requests when the mempool runs out of space. * */ int bioset_init(struct bio_set *bs, unsigned int pool_size, unsigned int front_pad, int flags) { bs->front_pad = front_pad; if (flags & BIOSET_NEED_BVECS) bs->back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec); else bs->back_pad = 0; spin_lock_init(&bs->rescue_lock); bio_list_init(&bs->rescue_list); INIT_WORK(&bs->rescue_work, bio_alloc_rescue); bs->bio_slab = bio_find_or_create_slab(bs); if (!bs->bio_slab) return -ENOMEM; if (mempool_init_slab_pool(&bs->bio_pool, pool_size, bs->bio_slab)) goto bad; if ((flags & BIOSET_NEED_BVECS) && biovec_init_pool(&bs->bvec_pool, pool_size)) goto bad; if (flags & BIOSET_NEED_RESCUER) { bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0); if (!bs->rescue_workqueue) goto bad; } if (flags & BIOSET_PERCPU_CACHE) { bs->cache = alloc_percpu(struct bio_alloc_cache); if (!bs->cache) goto bad; cpuhp_state_add_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead); } return 0; bad: bioset_exit(bs); return -ENOMEM; } EXPORT_SYMBOL(bioset_init); static int __init init_bio(void) { int i; BUILD_BUG_ON(BIO_FLAG_LAST > 8 * sizeof_field(struct bio, bi_flags)); bio_integrity_init(); for (i = 0; i < ARRAY_SIZE(bvec_slabs); i++) { struct biovec_slab *bvs = bvec_slabs + i; bvs->slab = kmem_cache_create(bvs->name, bvs->nr_vecs * sizeof(struct bio_vec), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); } cpuhp_setup_state_multi(CPUHP_BIO_DEAD, "block/bio:dead", NULL, bio_cpu_dead); if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS | BIOSET_PERCPU_CACHE)) panic("bio: can't allocate bios\n"); if (bioset_integrity_create(&fs_bio_set, BIO_POOL_SIZE)) panic("bio: can't create integrity pool\n"); return 0; } subsys_initcall(init_bio); |
| 697 21 772 695 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H #include <linux/mm.h> #include <linux/percpu_counter.h> #include <linux/atomic.h> #include <uapi/linux/mman.h> /* * Arrange for legacy / undefined architecture specific flags to be * ignored by mmap handling code. */ #ifndef MAP_32BIT #define MAP_32BIT 0 #endif #ifndef MAP_ABOVE4G #define MAP_ABOVE4G 0 #endif #ifndef MAP_HUGE_2MB #define MAP_HUGE_2MB 0 #endif #ifndef MAP_HUGE_1GB #define MAP_HUGE_1GB 0 #endif #ifndef MAP_UNINITIALIZED #define MAP_UNINITIALIZED 0 #endif #ifndef MAP_SYNC #define MAP_SYNC 0 #endif /* * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. * * MAP_EXECUTABLE and MAP_DENYWRITE are completely ignored throughout the * kernel. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ | MAP_FIXED \ | MAP_ANONYMOUS \ | MAP_DENYWRITE \ | MAP_EXECUTABLE \ | MAP_UNINITIALIZED \ | MAP_GROWSDOWN \ | MAP_LOCKED \ | MAP_NORESERVE \ | MAP_POPULATE \ | MAP_NONBLOCK \ | MAP_STACK \ | MAP_HUGETLB \ | MAP_32BIT \ | MAP_ABOVE4G \ | MAP_HUGE_2MB \ | MAP_HUGE_1GB) extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; extern struct percpu_counter vm_committed_as; #ifdef CONFIG_SMP extern s32 vm_committed_as_batch; extern void mm_compute_batch(int overcommit_policy); #else #define vm_committed_as_batch 0 static inline void mm_compute_batch(int overcommit_policy) { } #endif unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) { vm_acct_memory(-pages); } /* * Allow architectures to handle additional protection and flag bits. The * overriding macros must be defined in the arch-specific asm/mman.h file. */ #ifndef arch_calc_vm_prot_bits #define arch_calc_vm_prot_bits(prot, pkey) 0 #endif #ifndef arch_calc_vm_flag_bits #define arch_calc_vm_flag_bits(flags) 0 #endif #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have * already been masked out. * * Returns true if the prot flags are valid */ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) { return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0; } #define arch_validate_prot arch_validate_prot #endif #ifndef arch_validate_flags /* * This is called from mmap() and mprotect() with the updated vma->vm_flags. * * Returns true if the VM_* flags are valid. */ static inline bool arch_validate_flags(unsigned long flags) { return true; } #define arch_validate_flags arch_validate_flags #endif /* * Optimisation macro. It is equivalent to: * (x & bit1) ? bit2 : 0 * but this version is faster. * ("bit1" and "bit2" must be single bits) */ #define _calc_vm_trans(x, bit1, bit2) \ ((!(bit1) || !(bit2)) ? 0 : \ ((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \ : ((x) & (bit1)) / ((bit1) / (bit2)))) /* * Combine the mmap "prot" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { return _calc_vm_trans(prot, PROT_READ, VM_READ ) | _calc_vm_trans(prot, PROT_WRITE, VM_WRITE) | _calc_vm_trans(prot, PROT_EXEC, VM_EXEC) | arch_calc_vm_prot_bits(prot, pkey); } /* * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_flag_bits(unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | arch_calc_vm_flag_bits(flags); } unsigned long vm_commit_limit(void); #ifndef arch_memory_deny_write_exec_supported static inline bool arch_memory_deny_write_exec_supported(void) { return true; } #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported #endif /* * Denies creating a writable executable mapping or gaining executable permissions. * * This denies the following: * * a) mmap(PROT_WRITE | PROT_EXEC) * * b) mmap(PROT_WRITE) * mprotect(PROT_EXEC) * * c) mmap(PROT_WRITE) * mprotect(PROT_READ) * mprotect(PROT_EXEC) * * But allows the following: * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) */ static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) return true; if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) return true; return false; } #endif /* _LINUX_MMAN_H */ |
| 379 7 7 6 5 6 6 6 5 5 6 7 7 7 7 7 5 6 5 6 6 7 5 4 4 5 4 5 4 2 2 2 8 7 6 6 5 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/readahead.c - address_space-level file readahead. * * Copyright (C) 2002, Linus Torvalds * * 09Apr2002 Andrew Morton * Initial version. */ /** * DOC: Readahead Overview * * Readahead is used to read content into the page cache before it is * explicitly requested by the application. Readahead only ever * attempts to read folios that are not yet in the page cache. If a * folio is present but not up-to-date, readahead will not try to read * it. In that case a simple ->read_folio() will be requested. * * Readahead is triggered when an application read request (whether a * system call or a page fault) finds that the requested folio is not in * the page cache, or that it is in the page cache and has the * readahead flag set. This flag indicates that the folio was read * as part of a previous readahead request and now that it has been * accessed, it is time for the next readahead. * * Each readahead request is partly synchronous read, and partly async * readahead. This is reflected in the struct file_ra_state which * contains ->size being the total number of pages, and ->async_size * which is the number of pages in the async section. The readahead * flag will be set on the first folio in this async section to trigger * a subsequent readahead. Once a series of sequential reads has been * established, there should be no need for a synchronous component and * all readahead request will be fully asynchronous. * * When either of the triggers causes a readahead, three numbers need * to be determined: the start of the region to read, the size of the * region, and the size of the async tail. * * The start of the region is simply the first page address at or after * the accessed address, which is not currently populated in the page * cache. This is found with a simple search in the page cache. * * The size of the async tail is determined by subtracting the size that * was explicitly requested from the determined request size, unless * this would be less than zero - then zero is used. NOTE THIS * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED * PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY. * * The size of the region is normally determined from the size of the * previous readahead which loaded the preceding pages. This may be * discovered from the struct file_ra_state for simple sequential reads, * or from examining the state of the page cache when multiple * sequential reads are interleaved. Specifically: where the readahead * was triggered by the readahead flag, the size of the previous * readahead is assumed to be the number of pages from the triggering * page to the start of the new readahead. In these cases, the size of * the previous readahead is scaled, often doubled, for the new * readahead, though see get_next_ra_size() for details. * * If the size of the previous read cannot be determined, the number of * preceding pages in the page cache is used to estimate the size of * a previous read. This estimate could easily be misled by random * reads being coincidentally adjacent, so it is ignored unless it is * larger than the current request, and it is not scaled up, unless it * is at the start of file. * * In general readahead is accelerated at the start of the file, as * reads from there are often sequential. There are other minor * adjustments to the readahead size in various special cases and these * are best discovered by reading the code. * * The above calculation, based on the previous readahead size, * determines the size of the readahead, to which any requested read * size may be added. * * Readahead requests are sent to the filesystem using the ->readahead() * address space operation, for which mpage_readahead() is a canonical * implementation. ->readahead() should normally initiate reads on all * folios, but may fail to read any or all folios without causing an I/O * error. The page cache reading code will issue a ->read_folio() request * for any folio which ->readahead() did not read, and only an error * from this will be final. * * ->readahead() will generally call readahead_folio() repeatedly to get * each folio from those prepared for readahead. It may fail to read a * folio by: * * * not calling readahead_folio() sufficiently many times, effectively * ignoring some folios, as might be appropriate if the path to * storage is congested. * * * failing to actually submit a read request for a given folio, * possibly due to insufficient resources, or * * * getting an error during subsequent processing of a request. * * In the last two cases, the folio should be unlocked by the filesystem * to indicate that the read attempt has failed. In the first case the * folio will be unlocked by the VFS. * * Those folios not in the final ``async_size`` of the request should be * considered to be important and ->readahead() should not fail them due * to congestion or temporary resource unavailability, but should wait * for necessary resources (e.g. memory or indexing information) to * become available. Folios in the final ``async_size`` may be * considered less urgent and failure to read them is more acceptable. * In this case it is best to use filemap_remove_folio() to remove the * folios from the page cache as is automatically done for folios that * were not fetched with readahead_folio(). This will allow a * subsequent synchronous readahead request to try them again. If they * are left in the page cache, then they will be read individually using * ->read_folio() which may be less efficient. */ #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/pagemap.h> #include <linux/psi.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include <linux/sched/mm.h> #include "internal.h" /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. */ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; struct folio *folio; struct blk_plug plug; if (!readahead_count(rac)) return; if (unlikely(rac->_workingset)) psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { aops->readahead(rac); /* * Clean up the remaining folios. The sizes in ->ra * may be used to size the next readahead, so make sure * they accurately reflect what happened. */ while ((folio = readahead_folio(rac)) != NULL) { unsigned long nr = folio_nr_pages(folio); folio_get(folio); rac->ra->size -= nr; if (rac->ra->async_size >= nr) { rac->ra->async_size -= nr; filemap_remove_folio(folio); } folio_unlock(folio); folio_put(folio); } } else { while ((folio = readahead_folio(rac)) != NULL) aops->read_folio(rac->file, folio); } blk_finish_plug(&plug); if (unlikely(rac->_workingset)) psi_memstall_leave(&rac->_pflags); rac->_workingset = false; BUG_ON(readahead_count(rac)); } /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. * @nr_to_read: The number of pages to read. * @lookahead_size: Where to start the next readahead. * * This function is for filesystems to call when they want to start * readahead beyond a file's stated i_size. This is almost certainly * not the function you want to call. Use page_cache_async_readahead() * or page_cache_sync_readahead() instead. * * Context: File is referenced by caller. Mutexes may be held by caller. * May sleep, but will not reenter filesystem to reclaim memory. */ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long ra_folio_index, index = readahead_index(ractl); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long mark, i = 0; unsigned int min_nrpages = mapping_min_folio_nrpages(mapping); /* * Partway through the readahead operation, we will have added * locked pages to the page cache, but will not yet have submitted * them for I/O. Adding another page may need to allocate memory, * which can trigger memory reclaim. Telling the VM we're in * the middle of a filesystem operation will cause it to not * touch file-backed pages, preventing a deadlock. Most (all?) * filesystems already specify __GFP_NOFS in their mapping's * gfp_mask, but let's be explicit here. */ unsigned int nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); index = mapping_align_index(mapping, index); /* * As iterator `i` is aligned to min_nrpages, round_up the * difference between nr_to_read and lookahead_size to mark the * index that only has lookahead or "async_region" to set the * readahead flag. */ ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size, min_nrpages); mark = ra_folio_index - index; nr_to_read += readahead_index(ractl) - index; ractl->_index = index; /* * Preallocate as many pages as we will need. */ while (i < nr_to_read) { struct folio *folio = xa_load(&mapping->i_pages, index + i); int ret; if (folio && !xa_is_value(folio)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the * next batch. This page may be the one we would * have intended to mark as Readahead, but we don't * have a stable reference to this page, and it's * not worth getting one just for that. */ read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } folio = filemap_alloc_folio(gfp_mask, mapping_min_folio_order(mapping)); if (!folio) break; ret = filemap_add_folio(mapping, folio, index + i, gfp_mask); if (ret < 0) { folio_put(folio); if (ret == -ENOMEM) break; read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } if (i == mark) folio_set_readahead(folio); ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages += min_nrpages; i += min_nrpages; } /* * Now start the IO. We ignore I/O errors - if the folio is not * uptodate then the caller will launch read_folio again, and * will then handle the error. */ read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); /* * do_page_cache_ra() actually reads a chunk of disk. It allocates * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. */ static void do_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct inode *inode = ractl->mapping->host; unsigned long index = readahead_index(ractl); loff_t isize = i_size_read(inode); pgoff_t end_index; /* The last page we want to read */ if (isize == 0) return; end_index = (isize - 1) >> PAGE_SHIFT; if (index > end_index) return; /* Don't read past the page containing the last byte of the file */ if (nr_to_read > end_index - index) nr_to_read = end_index - index + 1; page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size); } /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much * memory at once. */ void force_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages; if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead)) return; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min_t(unsigned long, nr_to_read, max_pages); while (nr_to_read) { unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; do_page_cache_ra(ractl, this_chunk, 0); nr_to_read -= this_chunk; } } /* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { unsigned long newsize = roundup_pow_of_two(size); if (newsize <= max / 32) newsize = newsize * 4; else if (newsize <= max / 4) newsize = newsize * 2; else newsize = max; return newsize; } /* * Get the previous window size, ramp it up, and * return it as the new window size. */ static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { unsigned long cur = ra->size; if (cur < max / 16) return 4 * cur; if (cur <= max / 2) return 2 * cur; return max; } /* * On-demand readahead design. * * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * * |<----- async_size ---------| * |------------------- size -------------------->| * |==================#===========================| * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; * Instead, submit an asynchronous readahead I/O as soon as there are * only async_size pages left in the readahead window. Normally async_size * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as * sequential ones. * * There is a special-case: if the first page which the application tries to * read happens to be the first page of the file, it is assumed that a linear * read is about to happen and the window is immediately set to the initial size * based on I/O request size and the max_readahead. * * The code ramps up the readahead size aggressively at first, but slow down as * it approaches max_readhead. */ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { int err; struct folio *folio = filemap_alloc_folio(gfp, order); if (!folio) return -ENOMEM; mark = round_down(mark, 1UL << order); if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) { folio_put(folio); return err; } ractl->_nr_pages += 1UL << order; ractl->_workingset |= folio_test_workingset(folio); return 0; } void page_cache_ra_order(struct readahead_control *ractl, struct file_ra_state *ra, unsigned int new_order) { struct address_space *mapping = ractl->mapping; pgoff_t start = readahead_index(ractl); pgoff_t index = start; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); unsigned int min_ra_size = max(4, mapping_min_folio_nrpages(mapping)); /* * Fallback when size < min_nrpages as each folio should be * at least min_nrpages anyway. */ if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size) goto fallback; limit = min(limit, index + ra->size - 1); if (new_order < mapping_max_folio_order(mapping)) new_order += 2; new_order = min(mapping_max_folio_order(mapping), new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); new_order = max(new_order, min_order); /* See comment in page_cache_ra_unbounded() */ nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); /* * If the new_order is greater than min_order and index is * already aligned to new_order, then this will be noop as index * aligned to new_order should also be aligned to min_order. */ ractl->_index = mapping_align_index(mapping, index); index = readahead_index(ractl); while (index <= limit) { unsigned int order = new_order; /* Align with smaller pages if needed */ if (index & ((1UL << order) - 1)) order = __ffs(index); /* Don't allocate pages past EOF */ while (order > min_order && index + (1UL << order) - 1 > limit) order--; err = ra_alloc_folio(ractl, index, mark, order, gfp); if (err) break; index += 1UL << order; } read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have * left some gaps. Let the regular readahead code take care of this * situation. */ if (!err) return; fallback: do_page_cache_ra(ractl, ra->size - (index - start), ra->async_size); } static unsigned long ractl_max_pages(struct readahead_control *ractl, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); unsigned long max_pages = ractl->ra->ra_pages; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ if (req_size > max_pages && bdi->io_pages > max_pages) max_pages = min(req_size, bdi->io_pages); return max_pages; } void page_cache_sync_ra(struct readahead_control *ractl, unsigned long req_count) { pgoff_t index = readahead_index(ractl); bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); struct file_ra_state *ra = ractl->ra; unsigned long max_pages, contig_count; pgoff_t prev_index, miss; /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced * readahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ if (!ra->ra_pages || blk_cgroup_congested()) { if (!ractl->file) return; req_count = 1; do_forced_ra = true; } /* be dumb */ if (do_forced_ra) { force_page_cache_ra(ractl, req_count); return; } max_pages = ractl_max_pages(ractl, req_count); prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; /* * A start of file, oversized read, or sequential cache miss: * trivial case: (index - prev_index) == 1 * unaligned reads: (index - prev_index) == 0 */ if (!index || req_count > max_pages || index - prev_index <= 1UL) { ra->start = index; ra->size = get_init_ra_size(req_count, max_pages); ra->async_size = ra->size > req_count ? ra->size - req_count : ra->size >> 1; goto readit; } /* * Query the page cache and look for the traces(cached history pages) * that a sequential stream would leave behind. */ rcu_read_lock(); miss = page_cache_prev_miss(ractl->mapping, index - 1, max_pages); rcu_read_unlock(); contig_count = index - miss - 1; /* * Standalone, small random read. Read as is, and do not pollute the * readahead state. */ if (contig_count <= req_count) { do_page_cache_ra(ractl, req_count, 0); return; } /* * File cached from the beginning: * it is a strong indication of long-run stream (or whole-file-read) */ if (miss == ULONG_MAX) contig_count *= 2; ra->start = index; ra->size = min(contig_count + req_count, max_pages); ra->async_size = 1; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, 0); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, struct folio *folio, unsigned long req_count) { unsigned long max_pages; struct file_ra_state *ra = ractl->ra; pgoff_t index = readahead_index(ractl); pgoff_t expected, start; unsigned int order = folio_order(folio); /* no readahead */ if (!ra->ra_pages) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ if (folio_test_writeback(folio)) return; folio_clear_readahead(folio); if (blk_cgroup_congested()) return; max_pages = ractl_max_pages(ractl, req_count); /* * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ expected = round_down(ra->start + ra->size - ra->async_size, 1UL << order); if (index == expected) { ra->start += ra->size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; goto readit; } /* * Hit a marked folio without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ rcu_read_lock(); start = page_cache_next_miss(ractl->mapping, index + 1, max_pages); rcu_read_unlock(); if (!start || start - index > max_pages) return; ra->start = start; ra->size = start - index; /* old async_size */ ra->size += req_count; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, order); } EXPORT_SYMBOL_GPL(page_cache_async_ra); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { ssize_t ret; struct fd f; ret = -EBADF; f = fdget(fd); if (!fd_file(f) || !(fd_file(f)->f_mode & FMODE_READ)) goto out; /* * The readahead() syscall is intended to run only on files * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ ret = -EINVAL; if (!fd_file(f)->f_mapping || !fd_file(f)->f_mapping->a_ops || (!S_ISREG(file_inode(fd_file(f))->i_mode) && !S_ISBLK(file_inode(fd_file(f))->i_mode))) goto out; ret = vfs_fadvise(fd_file(f), offset, count, POSIX_FADV_WILLNEED); out: fdput(f); return ret; } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD) COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count) { return ksys_readahead(fd, compat_arg_u64_glue(offset), count); } #endif /** * readahead_expand - Expand a readahead request * @ractl: The request to be expanded * @new_start: The revised start * @new_len: The revised size of the request * * Attempt to expand a readahead request outwards from the current size to the * specified size by inserting locked pages before and after the current window * to increase the size to the new window. This may involve the insertion of * THPs, in which case the window may get expanded even beyond what was * requested. * * The algorithm will stop if it encounters a conflicting page already in the * pagecache and leave a smaller expansion than requested. * * The caller must check for this by examining the revised @ractl object for a * different expansion than was requested. */ void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; pgoff_t new_index, new_nr_pages; gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long min_nrpages = mapping_min_folio_nrpages(mapping); unsigned int min_order = mapping_min_folio_order(mapping); new_index = new_start / PAGE_SIZE; /* * Readahead code should have aligned the ractl->_index to * min_nrpages before calling readahead aops. */ VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages)); /* Expand the leading edge downwards */ while (ractl->_index > new_index) { unsigned long index = ractl->_index - 1; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = filemap_alloc_folio(gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; ractl->_index = folio->index; } new_len += new_start - readahead_pos(ractl); new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE); /* Expand the trailing edge upwards */ while (ractl->_nr_pages < new_nr_pages) { unsigned long index = ractl->_index + ractl->_nr_pages; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = filemap_alloc_folio(gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; if (ra) { ra->size += min_nrpages; ra->async_size += min_nrpages; } } } EXPORT_SYMBOL(readahead_expand); |
| 10 116 7 147 165 78 189 42 40 87 87 152 2 2 402 785 163 1211 920 587 197 36 14 1 4 4 4 211 168 626 660 1758 121 1136 1 702 56 13 29 794 47 3 101 27 394 395 149 150 453 406 453 406 307 228 228 208 467 228 467 228 834 582 338 233 834 582 338 31 253 697 628 139 103 118 284 462 173 4 98 7 7 100 130 9 23 8 8 223 266 58 5 750 822 1 1083 17 43 1270 30 1273 21 11 10 9 5 8 1 1 7 3 7 1 1 7 36 70 59 5 31 27 13 7 13 12 29 21 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_H #define _LINUX_FS_H #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> #include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> #include <linux/shrinker.h> #include <linux/migrate_mode.h> #include <linux/uidgid.h> #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> #include <linux/fs_types.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <linux/mount.h> #include <linux/cred.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> #include <linux/maple_tree.h> #include <linux/rw_hint.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> struct backing_dev_info; struct bdi_writeback; struct bio; struct io_comp_batch; struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; struct kiocb; struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; struct fscrypt_inode_info; struct fscrypt_operations; struct fsverity_info; struct fsverity_operations; struct fsnotify_mark_connector; struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; struct fileattr; struct iomap_ops; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; typedef __kernel_rwf_t rwf_t; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 #define MAY_READ 0x00000004 #define MAY_APPEND 0x00000008 #define MAY_ACCESS 0x00000010 #define MAY_OPEN 0x00000020 #define MAY_CHDIR 0x00000040 /* called from RCU mode, don't block */ #define MAY_NOT_BLOCK 0x00000080 /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ #define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ #define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ #define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ #define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ #define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ #define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) /* File supports atomic writes */ #define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) /* FMODE_* bit 8 */ /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ #define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. * * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ #define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) /* FMODE_* bit 13 */ /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ #define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ #define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) #define FMODE_OPENED ((__force fmode_t)(1 << 19)) #define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ #define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) #define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) /* FMODE_* bit 24 */ /* File is embedded in backing_file object */ #define FMODE_BACKING ((__force fmode_t)(1 << 25)) /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ #define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * Attribute flags. These should be or-ed together to figure out what * has been changed! */ #define ATTR_MODE (1 << 0) #define ATTR_UID (1 << 1) #define ATTR_GID (1 << 2) #define ATTR_SIZE (1 << 3) #define ATTR_ATIME (1 << 4) #define ATTR_MTIME (1 << 5) #define ATTR_CTIME (1 << 6) #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) #define ATTR_KILL_PRIV (1 << 14) #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) #define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */ /* * Whiteout is represented by a char device. The following constants define the * mode and device number to use. */ #define WHITEOUT_MODE 0 #define WHITEOUT_DEV 0 /* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. * Also, in this manner, a Filesystem can look at only the values it cares * about. Basically, these are the attributes that the VFS layer can * request to change from the FS layer. * * Derek Atkins <warlord@MIT.EDU> 94-10-20 */ struct iattr { unsigned int ia_valid; umode_t ia_mode; /* * The two anonymous unions wrap structures with the same member. * * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which * are a dedicated type requiring the filesystem to use the dedicated * helpers. Other filesystem can continue to use ia_{g,u}id until they * have been ported. * * They always contain the same value. In other words FS_ALLOW_IDMAP * pass down the same value on idmapped mounts as they would on regular * mounts. */ union { kuid_t ia_uid; vfsuid_t ia_vfsuid; }; union { kgid_t ia_gid; vfsgid_t ia_vfsgid; }; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to * implement an ftruncate() like method. NOTE: filesystem should * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL). */ struct file *ia_file; }; /* * Includes for diskquotas. */ #include <linux/quota.h> /* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ #define FILESYSTEM_MAX_STACK_DEPTH 2 /** * enum positive_aop_returns - aop return codes with specific semantics * * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has * completed, that the page is still locked, and * should be considered active. The VM uses this hint * to return the page to the active list -- it won't * be a candidate for writeback again in the near * future. Other callers must be careful to unlock * the page if they get this return. Returned by * writepage(); * * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has * unlocked it and the page might have been truncated. * The caller should back up to acquiring a new page and * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a * page to allow for functions that return the number of bytes operated on in a * given page. */ enum positive_aop_returns { AOP_WRITEPAGE_ACTIVATE = 0x80000, AOP_TRUNCATED_PAGE = 0x80001, }; /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; struct readahead_control; /* Match RWF_* bits to IOCB bits */ #define IOCB_HIPRI (__force int) RWF_HIPRI #define IOCB_DSYNC (__force int) RWF_DSYNC #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND #define IOCB_ATOMIC (__force int) RWF_ATOMIC /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) #define IOCB_DIRECT (1 << 17) #define IOCB_WRITE (1 << 18) /* iocb->ki_waitq is valid */ #define IOCB_WAITQ (1 << 19) #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) /* * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the * iocb completion can be passed back to the owner for execution from a safe * context rather than needing to be punted through a workqueue. If this * flag is set, the bio completion handling may set iocb->dio_complete to a * handler function and iocb->private to context information for that handler. * The issuer should call the handler with that context information from task * context to complete the processing of the iocb. Note that while this * provides a task context for the dio_complete() callback, it should only be * used on the completion side for non-IO generating completions. It's fine to * call blocking functions from this callback, but they should not wait for * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) /* kiocb is a read or write operation submitted by fs/aio.c. */ #define IOCB_AIO_RW (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ { IOCB_HIPRI, "HIPRI" }, \ { IOCB_DSYNC, "DSYNC" }, \ { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ { IOCB_ATOMIC, "ATOMIC"}, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ { IOCB_DIO_CALLER_COMP, "CALLER_COMP" } struct kiocb { struct file *ki_filp; loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ union { /* * Only used for async buffered reads, where it denotes the * page waitqueue associated with completing the read. Valid * IFF IOCB_WAITQ is set. */ struct wait_page_queue *ki_waitq; /* * Can be used for O_DIRECT IO, where the completion handling * is punted back to the issuer of the IO. May only be set * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer * must then check for presence of this handler when ki_complete * is invoked. The data passed in to this handler must be * assigned to ->private when dio_complete is assigned. */ ssize_t (*dio_complete)(void *data); }; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); /* Mark a folio dirty. Return true if this dirtied it */ bool (*dirty_folio)(struct address_space *, struct folio *); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); void (*free_folio)(struct folio *folio); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a folio to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ int (*migrate_folio)(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_folio)(struct address_space *, struct folio *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. * @invalidate_lock: Guards coherency between page cache contents and * file offset->disk block mappings in the filesystem during invalidates. * It is also used to block modification of page cache contents through * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. * @i_private_lock: For use by the owner of the address_space. * @i_private_list: For use by the owner of the address_space. * @i_private_data: For use by the owner of the address_space. */ struct address_space { struct inode *host; struct xarray i_pages; struct rw_semaphore invalidate_lock; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS /* number of thp, only for non-shmem files */ atomic_t nr_thps; #endif struct rb_root_cached i_mmap; unsigned long nrpages; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; spinlock_t i_private_lock; struct list_head i_private_list; struct rw_semaphore i_mmap_rwsem; void * i_private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 #define PAGECACHE_TAG_WRITEBACK XA_MARK_1 #define PAGECACHE_TAG_TOWRITE XA_MARK_2 /* * Returns true if any of the pages in the mapping are marked with the tag. */ static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } static inline void i_mmap_lock_write(struct address_space *mapping) { down_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_write(struct address_space *mapping) { return down_write_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_write(struct address_space *mapping) { up_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_read(struct address_space *mapping) { return down_read_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_read(struct address_space *mapping) { up_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_locked(struct address_space *mapping) { lockdep_assert_held(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_write_locked(struct address_space *mapping) { lockdep_assert_held_write(&mapping->i_mmap_rwsem); } /* * Might pages of this file be mapped into userspace? */ static inline int mapping_mapped(struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* * Might pages of this file have been modified in userspace? * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ static inline int mapping_writably_mapped(struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } static inline int mapping_map_writable(struct address_space *mapping) { return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? 0 : -EPERM; } static inline void mapping_unmap_writable(struct address_space *mapping) { atomic_dec(&mapping->i_mmap_writable); } static inline int mapping_deny_writable(struct address_space *mapping) { return atomic_dec_unless_positive(&mapping->i_mmap_writable) ? 0 : -EBUSY; } static inline void mapping_allow_writable(struct address_space *mapping) { atomic_inc(&mapping->i_mmap_writable); } /* * Use sequence counter to get consistent i_size on 32-bit processors. */ #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __NEED_I_SIZE_ORDERED #define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount) #else #define i_size_ordered_init(inode) do { } while (0) #endif struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) /* * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to * cache the ACL. This also means that ->get_inode_acl() can be called in RCU * mode with the LOOKUP_RCU flag. */ #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) { return (void *)task + 1; } static inline bool is_uncached_acl(struct posix_acl *acl) { return (long)acl & 1; } #define IOP_FASTPERM 0x0001 #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' */ struct inode { umode_t i_mode; unsigned short i_opflags; kuid_t i_uid; kgid_t i_gid; unsigned int i_flags; #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif const struct inode_operations *i_op; struct super_block *i_sb; struct address_space *i_mapping; #ifdef CONFIG_SECURITY void *i_security; #endif /* Stat data, not accessed from path walking */ unsigned long i_ino; /* * Filesystems may only read i_nlink directly. They shall use the * following functions for modification: * * (set|clear|inc|drop)_nlink * inode_(inc|dec)_link_count */ union { const unsigned int i_nlink; unsigned int __i_nlink; }; dev_t i_rdev; loff_t i_size; time64_t i_atime_sec; time64_t i_mtime_sec; time64_t i_ctime_sec; u32 i_atime_nsec; u32 i_mtime_nsec; u32 i_ctime_nsec; u32 i_generation; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif /* Misc */ u32 i_state; /* 32-bit hole */ struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_io_list; /* backing dev IO list */ #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *i_wb; /* the associated cgroup wb */ /* foreign inode detection, see wbc_detach_inode() */ int i_wb_frn_winner; u16 i_wb_frn_avg_time; u16 i_wb_frn_history; #endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; atomic64_t i_version; atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) atomic_t i_readcount; /* struct files open RO */ #endif union { const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ void (*free_inode)(struct inode *); }; struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; union { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; }; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ /* 32-bit hole reserved for expanding i_fsnotify_mask */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_inode_info *i_crypt_info; #endif #ifdef CONFIG_FS_VERITY struct fsverity_info *i_verity_info; #endif void *i_private; /* fs or device private pointer */ } __randomize_layout; /* * Get bit address from inode->i_state to use with wait_var_event() * infrastructre. */ #define inode_state_wait_address(inode, bit) ((char *)&(inode)->i_state + (bit)) struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, struct inode *inode, u32 bit); static inline void inode_wake_up_bit(struct inode *inode, u32 bit) { /* Caller is responsible for correct memory barriers. */ wake_up_var(inode_state_wait_address(inode, bit)); } struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) { return (1 << node->i_blkbits); } static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); } /* * __mark_inode_dirty expects inodes to be hashed. Since we don't * want special inodes in the fileset inode space, we make them * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ static inline void inode_fake_hash(struct inode *inode) { hlist_add_fake(&inode->i_hash); } /* * inode->i_mutex nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent * 2: child/target * 3: xattr * 4: second non-directory * 5: second parent (when locking independent directories in rename) * * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, I_MUTEX_NONDIR2, I_MUTEX_PARENT2, }; static inline void inode_lock(struct inode *inode) { down_write(&inode->i_rwsem); } static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); } static inline void inode_lock_shared(struct inode *inode) { down_read(&inode->i_rwsem); } static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); } static inline int inode_trylock(struct inode *inode) { return down_write_trylock(&inode->i_rwsem); } static inline int inode_trylock_shared(struct inode *inode) { return down_read_trylock(&inode->i_rwsem); } static inline int inode_is_locked(struct inode *inode) { return rwsem_is_locked(&inode->i_rwsem); } static inline void inode_lock_nested(struct inode *inode, unsigned subclass) { down_write_nested(&inode->i_rwsem, subclass); } static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass) { down_read_nested(&inode->i_rwsem, subclass); } static inline void filemap_invalidate_lock(struct address_space *mapping) { down_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock(struct address_space *mapping) { up_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_lock_shared(struct address_space *mapping) { down_read(&mapping->invalidate_lock); } static inline int filemap_invalidate_trylock_shared( struct address_space *mapping) { return down_read_trylock(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock_shared( struct address_space *mapping) { up_read(&mapping->invalidate_lock); } void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2); void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2); /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic * with respect to the local cpu (unlike with preempt disabled), * but they don't need to be atomic with respect to other cpus like in * true SMP (so they need either to either locally disable irq around * the read or for example on x86 they can be still implemented as a * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; unsigned int seq; do { seq = read_seqcount_begin(&inode->i_size_seqcount); i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); i_size = inode->i_size; preempt_enable(); return i_size; #else /* Pairs with smp_store_release() in i_size_write() */ return smp_load_acquire(&inode->i_size); #endif } /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else /* * Pairs with smp_load_acquire() in i_size_read() to ensure * changes related to inode size (such as page contents) are * visible before we see the changed inode size. */ smp_store_release(&inode->i_size, i_size); #endif } static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } struct fown_struct { struct file *file; /* backpointer for security modules */ rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ kuid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; /** * struct file_ra_state - Track a file's readahead state. * @start: Where the most recent readahead started. * @size: Number of pages read in the most recent readahead. * @async_size: Numer of pages that were/are not needed immediately * and so were/are genuinely "ahead". Start next readahead when * the first of these pages is accessed. * @ra_pages: Maximum size of a readahead request, copied from the bdi. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. * * When this structure is passed to ->readahead(), the "most recent" * readahead means the current readahead. */ struct file_ra_state { pgoff_t start; unsigned int size; unsigned int async_size; unsigned int ra_pages; unsigned int mmap_miss; loff_t prev_pos; }; /* * Check if @index falls in the readahead windows. */ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) { return (index >= ra->start && index < ra->start + ra->size); } /** * struct file - Represents a file * @f_count: reference count * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. * @f_mode: FMODE_* flags often used in hotpaths * @f_op: file operations * @f_mapping: Contents of a cacheable, mappable object. * @private_data: filesystem or driver specific data * @f_inode: cached inode * @f_flags: file flags * @f_iocb_flags: iocb flags * @f_cred: stashed credentials of creator/opener * @f_path: path of the file * @f_pos_lock: lock protecting file position * @f_pipe: specific to pipes * @f_pos: file position * @f_security: LSM security context of this file * @f_owner: file owner * @f_wb_err: writeback error * @f_sb_err: per sb writeback errors * @f_ep: link of all epoll hooks for this file * @f_task_work: task work entry point * @f_llist: work queue entrypoint * @f_ra: file's readahead state * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) */ struct file { atomic_long_t f_count; spinlock_t f_lock; fmode_t f_mode; const struct file_operations *f_op; struct address_space *f_mapping; void *private_data; struct inode *f_inode; unsigned int f_flags; unsigned int f_iocb_flags; const struct cred *f_cred; /* --- cacheline 1 boundary (64 bytes) --- */ struct path f_path; union { /* regular files (with FMODE_ATOMIC_POS) and directories */ struct mutex f_pos_lock; /* pipes */ u64 f_pipe; }; loff_t f_pos; #ifdef CONFIG_SECURITY void *f_security; #endif /* --- cacheline 2 boundary (128 bytes) --- */ struct fown_struct *f_owner; errseq_t f_wb_err; errseq_t f_sb_err; #ifdef CONFIG_EPOLL struct hlist_head *f_ep; #endif union { struct callback_head f_task_work; struct llist_node f_llist; struct file_ra_state f_ra; freeptr_t f_freeptr; }; /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { long prior = atomic_long_fetch_inc_relaxed(&f->f_count); WARN_ONCE(!prior, "struct file::f_count incremented from zero; use-after-free condition present!\n"); return f; } struct file *get_file_rcu(struct file __rcu **f); struct file *get_file_active(struct file **f); #define file_count(x) atomic_long_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 #define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; struct file_lease; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define OFFSET_MAX type_max(loff_t) #define OFFT_OFFSET_MAX type_max(off_t) #endif int file_f_owner_allocate(struct file *file); static inline struct fown_struct *file_f_owner(const struct file *file) { return READ_ONCE(file->f_owner); } extern void send_sigio(struct fown_struct *fown, int fd, int band); static inline struct inode *file_inode(const struct file *f) { return f->f_inode; } /* * file_dentry() is a relic from the days that overlayfs was using files with a * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs. * In those days, file_dentry() was needed to get the underlying fs dentry that * matches f_inode. * Files with "fake" path should not exist nowadays, so use an assertion to make * sure that file_dentry() was not papering over filesystem bugs. */ static inline struct dentry *file_dentry(const struct file *file) { struct dentry *dentry = file->f_path.dentry; WARN_ON_ONCE(d_inode(dentry) != file_inode(file)); return dentry; } struct fasync_struct { rwlock_t fa_lock; int magic; int fa_fd; struct fasync_struct *fa_next; /* singly linked list */ struct file *fa_file; struct rcu_head fa_rcu; }; #define FASYNC_MAGIC 0x4601 /* SMP safe fasync helpers: */ extern int fasync_helper(int, struct file *, int, struct fasync_struct **); extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); extern int fasync_remove_entry(struct file *, struct fasync_struct **); extern struct fasync_struct *fasync_alloc(void); extern void fasync_free(struct fasync_struct *); /* can be called from interrupts */ extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, int who, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct file *file); /* * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ #define SB_RDONLY BIT(0) /* Mount read-only */ #define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ #define SB_NODEV BIT(2) /* Disallow access to device special files */ #define SB_NOEXEC BIT(3) /* Disallow program execution */ #define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ #define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ #define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ #define SB_NOATIME BIT(10) /* Do not update access times. */ #define SB_NODIRATIME BIT(11) /* Do not update directory access times */ #define SB_SILENT BIT(15) #define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ #define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ #define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ #define SB_I_VERSION BIT(23) /* Update inode I_version field */ #define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ #define SB_DEAD BIT(21) #define SB_DYING BIT(24) #define SB_SUBMOUNT BIT(26) #define SB_FORCE BIT(27) #define SB_NOSEC BIT(28) #define SB_BORN BIT(29) #define SB_ACTIVE BIT(30) #define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) #define sb_has_strict_encoding(sb) \ (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) /* * Umount options */ #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ #define MNT_EXPIRE 0x00000004 /* Mark for expiry */ #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ /* sb->s_iflags */ #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ #define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 #define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ #define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop * internal threads if needed) */ SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ }; #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) struct sb_writers { unsigned short frozen; /* Is sb frozen? */ int freeze_kcount; /* How many kernel freeze requests? */ int freeze_ucount; /* How many userspace freeze requests? */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; const struct dquot_operations *dq_op; const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; int s_count; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; #endif const struct xattr_handler * const *s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif #if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ struct file *s_bdev_file; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; unsigned int s_quota_types; /* Bitmask of supported quota types */ struct quota_info s_dquot; /* Diskquota specific options */ struct sb_writers s_writers; /* * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and * s_fsnotify_info together for cache efficiency. They are frequently * accessed and rarely modified. */ void *s_fs_info; /* Filesystem private info */ /* Granularity of c/m/atime in ns (cannot be worse than a second) */ u32 s_time_gran; /* Time limits for c/m/atime in seconds */ time64_t s_time_min; time64_t s_time_max; #ifdef CONFIG_FSNOTIFY u32 s_fsnotify_mask; struct fsnotify_sb_info *s_fsnotify_info; #endif /* * q: why are s_id and s_sysfs_name not the same? both are human * readable strings that identify the filesystem * a: s_id is allowed to change at runtime; it's used in log messages, * and we want to when a device starts out as single device (s_id is dev * name) but then a device is hot added and we have to switch to * identifying it by UUID * but s_sysfs_name is a handle for programmatic access, and can't * change at runtime */ char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ char s_sysfs_name[UUID_STRING_LEN + 1]; unsigned int s_max_links; /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ struct mutex s_vfs_rename_mutex; /* Kludge */ /* * Filesystem subtype. If non-empty the filesystem type field * in /proc/mounts will be "type.subtype" */ const char *s_subtype; const struct dentry_operations *s_d_op; /* default d_op for dentries */ struct shrinker *s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; /* Read-only state of the superblock is being changed */ int s_readonly_remount; /* per-sb errseq_t for reporting writeback errors via syncfs */ errseq_t s_wb_err; /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; /* * Owning user namespace and default context in which to * interpret filesystem uids, gids, quotas, device nodes, * xattrs and security labels. */ struct user_namespace *s_user_ns; /* * The list_lru structure is essentially just a pointer to a table * of per-node lru lists, each of which has its own spinlock. * There is no need to put them into separate cachelines. */ struct list_lru s_dentry_lru; struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; struct mutex s_sync_lock; /* sync serialisation lock */ /* * Indicates how deep in a filesystem stack this SB is */ int s_stack_depth; /* s_inode_list_lock protects s_inodes */ spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; struct list_head s_inodes; /* all inodes */ spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ } __randomize_layout; static inline struct user_namespace *i_user_ns(const struct inode *inode) { return inode->i_sb->s_user_ns; } /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored * in the filesystem. */ static inline uid_t i_uid_read(const struct inode *inode) { return from_kuid(i_user_ns(inode), inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { return from_kgid(i_user_ns(inode), inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { inode->i_uid = make_kuid(i_user_ns(inode), uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { inode->i_gid = make_kgid(i_user_ns(inode), gid); } /** * i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: whe inode's i_uid mapped down according to @idmap. * If the inode's i_uid has no mapping INVALID_VFSUID is returned. */ static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid); } /** * i_uid_needs_update - check whether inode's i_uid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_uid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_uid field needs to be updated, false if not. */ static inline bool i_uid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_UID) && !vfsuid_eq(attr->ia_vfsuid, i_uid_into_vfsuid(idmap, inode))); } /** * i_uid_update - update @inode's i_uid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_uid field translating the vfsuid of any idmapped * mount into the filesystem kuid. */ static inline void i_uid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_UID) inode->i_uid = from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid); } /** * i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: the inode's i_gid mapped down according to @idmap. * If the inode's i_gid has no mapping INVALID_VFSGID is returned. */ static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid); } /** * i_gid_needs_update - check whether inode's i_gid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_gid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_gid field needs to be updated, false if not. */ static inline bool i_gid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_GID) && !vfsgid_eq(attr->ia_vfsgid, i_gid_into_vfsgid(idmap, inode))); } /** * i_gid_update - update @inode's i_gid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_gid field translating the vfsgid of any idmapped * mount into the filesystem kgid. */ static inline void i_gid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_GID) inode->i_gid = from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid); } /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_uid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsuid according to @idmap. */ static inline void inode_fsuid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode)); } /** * inode_fsgid_set - initialize inode's i_gid field with callers fsgid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_gid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsgid according to @idmap. */ static inline void inode_fsgid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode)); } /** * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped * @sb: the superblock we want a mapping in * @idmap: idmap of the relevant mount * * Check whether the caller's fsuid and fsgid have a valid mapping in the * s_user_ns of the superblock @sb. If the caller is on an idmapped mount map * the caller's fsuid and fsgid according to the @idmap first. * * Return: true if fsuid and fsgid is mapped, false if not. */ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct mnt_idmap *idmap) { struct user_namespace *fs_userns = sb->s_user_ns; kuid_t kuid; kgid_t kgid; kuid = mapped_fsuid(idmap, fs_userns); if (!uid_valid(kuid)) return false; kgid = mapped_fsgid(idmap, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && kgid_has_mapping(fs_userns, kgid); } struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); static inline time64_t inode_get_atime_sec(const struct inode *inode) { return inode->i_atime_sec; } static inline long inode_get_atime_nsec(const struct inode *inode) { return inode->i_atime_nsec; } static inline struct timespec64 inode_get_atime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode), .tv_nsec = inode_get_atime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_atime_sec = ts.tv_sec; inode->i_atime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_atime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_atime_to_ts(inode, ts); } static inline time64_t inode_get_mtime_sec(const struct inode *inode) { return inode->i_mtime_sec; } static inline long inode_get_mtime_nsec(const struct inode *inode) { return inode->i_mtime_nsec; } static inline struct timespec64 inode_get_mtime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode), .tv_nsec = inode_get_mtime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_mtime_sec = ts.tv_sec; inode->i_mtime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_mtime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_mtime_to_ts(inode, ts); } static inline time64_t inode_get_ctime_sec(const struct inode *inode) { return inode->i_ctime_sec; } static inline long inode_get_ctime_nsec(const struct inode *inode) { return inode->i_ctime_nsec; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode), .tv_nsec = inode_get_ctime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_ctime_sec = ts.tv_sec; inode->i_ctime_nsec = ts.tv_nsec; return ts; } /** * inode_set_ctime - set the ctime in the inode * @inode: inode in which to set the ctime * @sec: tv_sec value to set * @nsec: tv_nsec value to set * * Set the ctime in @inode to { @sec, @nsec } */ static inline struct timespec64 inode_set_ctime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_ctime_to_ts(inode, ts); } struct timespec64 simple_inode_init_ts(struct inode *inode); /* * Snapshotting support. */ /* * These are internal functions, please use sb_start_{write,pagefault,intwrite} * instead. */ static inline void __sb_end_write(struct super_block *sb, int level) { percpu_up_read(sb->s_writers.rw_sem + level-1); } static inline void __sb_start_write(struct super_block *sb, int level) { percpu_down_read(sb->s_writers.rw_sem + level - 1); } static inline bool __sb_start_write_trylock(struct super_block *sb, int level) { return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); } #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], _THIS_IP_) /** * __sb_write_started - check if sb freeze level is held * @sb: the super we write to * @level: the freeze level * * * > 0 - sb freeze level is held * * 0 - sb freeze level is not held * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN */ static inline int __sb_write_started(const struct super_block *sb, int level) { return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); } /** * sb_write_started - check if SB_FREEZE_WRITE is held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE); } /** * sb_write_not_started - check if SB_FREEZE_WRITE is not held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_not_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; } /** * file_write_started - check if SB_FREEZE_WRITE is held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_started(file_inode(file)->i_sb); } /** * file_write_not_started - check if SB_FREEZE_WRITE is not held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_not_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_not_started(file_inode(file)->i_sb); } /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to * * Decrement number of writers to the filesystem. Wake up possible waiters * wanting to freeze the filesystem. */ static inline void sb_end_write(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_WRITE); } /** * sb_end_pagefault - drop write access to a superblock from a page fault * @sb: the super we wrote to * * Decrement number of processes handling write page fault to the filesystem. * Wake up possible waiters wanting to freeze the filesystem. */ static inline void sb_end_pagefault(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_end_intwrite - drop write access to a superblock for internal fs purposes * @sb: the super we wrote to * * Decrement fs-internal number of writers to the filesystem. Wake up possible * waiters wanting to freeze the filesystem. */ static inline void sb_end_intwrite(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_FS); } /** * sb_start_write - get write access to a superblock * @sb: the super we write to * * When a process wants to write data or metadata to a file system (i.e. dirty * a page or an inode), it should embed the operation in a sb_start_write() - * sb_end_write() pair to get exclusion against file system freezing. This * function increments number of writers preventing freezing. If the file * system is already frozen, the function waits until the file system is * thawed. * * Since freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. Generally, * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write * -> i_mutex (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_WRITE); } static inline bool sb_start_write_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** * sb_start_pagefault - get write access to a superblock from a page fault * @sb: the super we write to * * When a process starts handling write page fault, it should embed the * operation into sb_start_pagefault() - sb_end_pagefault() pair to get * exclusion against file system freezing. This is needed since the page fault * is going to dirty a page. This function increments number of running page * faults preventing freezing. If the file system is already frozen, the * function waits until the file system is thawed. * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_start_intwrite - get write access to a superblock for internal fs purposes * @sb: the super we write to * * This is the third level of protection against filesystem freezing. It is * free for use by a filesystem. The only requirement is that it must rank * below sb_start_pagefault. * * For example filesystem can call sb_start_intwrite() when starting a * transaction which somewhat eases handling of freezing for internal sources * of filesystem changes (internal fs threads, discarding preallocation on file * close, etc.). */ static inline void sb_start_intwrite(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_FS); } static inline bool sb_start_intwrite_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_FS); } bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); int vfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int vfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *); int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); /** * struct renamedata - contains all information required for renaming * @old_mnt_idmap: idmap of the old mount the inode was found from * @old_dir: parent of source * @old_dentry: source * @new_mnt_idmap: idmap of the new mount the inode was found from * @new_dir: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { struct mnt_idmap *old_mnt_idmap; struct inode *old_dir; struct dentry *old_dentry; struct mnt_idmap *new_mnt_idmap; struct inode *new_dir; struct dentry *new_dentry; struct inode **delegated_inode; unsigned int flags; } __randomize_layout; int vfs_rename(struct renamedata *); static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); } struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred); struct file *kernel_file_open(const struct path *path, int flags, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #else #define compat_ptr_ioctl NULL #endif /* * VFS file helper functions. */ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. * Return 'true' to keep going and 'false' if there are no more entries. */ struct dir_context; typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { filldir_t actor; loff_t pos; }; /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. * * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) * NOMMU_MAP_READ: Can be mapped for reading * NOMMU_MAP_WRITE: Can be mapped for writing * NOMMU_MAP_EXEC: Can be mapped for execution */ #define NOMMU_MAP_COPY 0x00000001 #define NOMMU_MAP_DIRECT 0x00000008 #define NOMMU_MAP_READ VM_MAYREAD #define NOMMU_MAP_WRITE VM_MAYWRITE #define NOMMU_MAP_EXEC VM_MAYEXEC #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) /* * These flags control the behavior of the remap_file_range function pointer. * If it is called with len == 0 that means "remap to end of source file". * See Documentation/filesystems/vfs.rst for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) #define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of * the behavior of the remap operation. The changes must be made by the * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) /* * These flags control the behavior of vfs_copy_file_range(). * They are not available to the user via syscall. * * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops */ #define COPY_FILE_SPLICE (1 << 0) struct iov_iter; struct io_uring_cmd; struct offset_ctx; typedef unsigned int __bitwise fop_flags_t; struct file_operations { struct module *owner; fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, unsigned int flags); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); void (*splice_eof)(struct file *file); int (*setlease)(struct file *, int, struct file_lease **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, unsigned int poll_flags); } __randomize_layout; /* Supports async buffered reads */ #define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) /* Supports async buffered writes */ #define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) /* Supports synchronous page faults for mappings */ #define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) /* Supports non-exclusive O_DIRECT writes from multiple threads */ #define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) /* Contains huge pages */ #define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) /* Treat loff_t as unsigned (e.g., /dev/mem) */ #define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); #define WRAP_DIR_ITER(x) \ static int shared_##x(struct file *file , struct dir_context *ctx) \ { return wrap_directory_iterator(file, ctx, x); } struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct mnt_idmap *, struct inode *, int); struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *, int); int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { return file->f_op->mmap(file, vma); } extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write); int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *dax_read_ops); int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); /** * enum freeze_holder - holder of the freeze * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed * * Indicate who the owner of the freeze or thaw request is and whether * the freeze needs to be exclusive or can nest. * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the * same holder aren't allowed. It is however allowed to hold a single * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at * the same time. This is relied upon by some filesystems during online * repair or similar. */ enum freeze_holder { FREEZE_HOLDER_KERNEL = (1U << 0), FREEZE_HOLDER_USERSPACE = (1U << 1), FREEZE_MAY_NEST = (1U << 2), }; struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); void (*free_inode)(struct inode *); void (*dirty_inode) (struct inode *, int flags); int (*write_inode) (struct inode *, struct writeback_control *wbc); int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); int (*freeze_super) (struct super_block *, enum freeze_holder who); int (*freeze_fs) (struct super_block *); int (*thaw_super) (struct super_block *, enum freeze_holder who); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot __rcu **(*get_dquots)(struct inode *); #endif long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); void (*shutdown)(struct super_block *sb); }; /* * Inode flags - they have no relation to superblock flags now */ #define S_SYNC (1 << 0) /* Writes are synced at once */ #define S_NOATIME (1 << 1) /* Do not update access times */ #define S_APPEND (1 << 2) /* Append-only file */ #define S_IMMUTABLE (1 << 3) /* Immutable file */ #define S_DEAD (1 << 4) /* removed, but still open directory */ #define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ #define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ #define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ #define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE (1 << 9) /* Inode is fs-internal */ #define S_IMA (1 << 10) /* Inode has an associated IMA struct */ #define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ #define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX #define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else #define S_DAX 0 /* Make all the DAX code disappear */ #endif #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ #define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system * flags just means all the inodes inherit those flags by default. It might be * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their * i_flags updated. Hence, i_flags no longer inherit the superblock mount * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) #define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) #define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) #ifdef CONFIG_FS_POSIX_ACL #define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #else #define IS_POSIXACL(inode) 0 #endif #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) #ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #else #define IS_SWAPFILE(inode) ((void)(inode), 0U) #endif #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) #define IS_VERITY(inode) ((inode)->i_flags & S_VERITY) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) { return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode)); } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = filp->f_iocb_flags, .ki_ioprio = get_current_ioprio(), }; } static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; } /* * Inode state bits. Protected by inode->i_lock * * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. * * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at * various stages of removing an inode. * * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on * fdatasync() (unless I_DIRTY_DATASYNC is also set). * Timestamp updates are the usual cause. * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only * e.g. the timestamps have changed. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. * I_DIRTY_TIME The inode itself has dirty timestamps, and the * lazytime mount option is enabled. We keep track of this * separately from I_DIRTY_SYNC in order to implement * lazytime. This gets cleared if I_DIRTY_INODE * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already * in place because writeback might already be in progress * and we don't want to lose the time update * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and * wait for I_NEW to be released before returning. * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can * also cause waiting on I_NEW, without I_NEW actually * being set. find_inode() uses this to prevent returning * nearly-dead inodes. * I_WILL_FREE Must be set when calling write_inode_now() if i_count * is zero. I_FREEING must be set when I_WILL_FREE is * cleared. * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. * I_CLEAR Added by clear_inode(). In this state the inode is * clean and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for * the inode to be completely released, then create it * anew. Other functions will just ignore such inodes, * if appropriate. I_NEW is used for waiting. * * I_SYNC Writeback of inode is running. The bit is set during * data writeback, and cleared with a wakeup on the bit * address once it is done. The bit is also used to pin * the inode in memory for flusher thread. * * I_REFERENCED Marks the inode as recently references on the LRU list. * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See * inode_switch_wbs_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * * I_CREATING New object's inode in the middle of setting up. * * I_DONTCACHE Evict inode as soon as it is not used anymore. * * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding * i_count. * * Q: What is the difference between I_WILL_FREE and I_FREEING? * * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait * upon. There's one free address left. */ #define __I_NEW 0 #define I_NEW (1 << __I_NEW) #define __I_SYNC 1 #define I_SYNC (1 << __I_SYNC) #define __I_LRU_ISOLATING 2 #define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_SYNC (1 << 3) #define I_DIRTY_DATASYNC (1 << 4) #define I_DIRTY_PAGES (1 << 5) #define I_WILL_FREE (1 << 6) #define I_FREEING (1 << 7) #define I_CLEAR (1 << 8) #define I_REFERENCED (1 << 9) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) #define I_WB_SWITCH (1 << 12) #define I_OVL_INUSE (1 << 13) #define I_CREATING (1 << 14) #define I_DONTCACHE (1 << 15) #define I_SYNC_QUEUED (1 << 16) #define I_PINNING_NETFS_WB (1 << 17) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY); } static inline void mark_inode_dirty_sync(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY_SYNC); } /* * Returns true if the given inode itself only has dirty timestamps (its pages * may still be dirty) and isn't currently being allocated or freed. * Filesystems should call this if when writing an inode when lazytime is * enabled, they want to opportunistically write the timestamps of other inodes * located very nearby on-disk, e.g. in the same inode block. This returns true * if the given inode is in need of such an opportunistic update. Requires * i_lock, or at least later re-checking under i_lock. */ static inline bool inode_is_dirtytime_only(struct inode *inode) { return (inode->i_state & (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; } extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); extern void set_nlink(struct inode *inode, unsigned int nlink); static inline void inode_inc_link_count(struct inode *inode) { inc_nlink(inode); mark_inode_dirty(inode); } static inline void inode_dec_link_count(struct inode *inode) { drop_nlink(inode); mark_inode_dirty(inode); } enum file_time_flags { S_ATIME = 1, S_MTIME = 2, S_CTIME = 4, S_VERSION = 8, }; extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); int inode_update_time(struct inode *inode, int flags); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) touch_atime(&file->f_path); } extern int file_modified(struct file *file); int kiocb_modified(struct kiocb *iocb); int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { const char *name; int fs_flags; #define FS_REQUIRES_DEV 1 #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct hlist_head fs_supers; struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; struct lock_class_key s_vfs_rename_key; struct lock_class_key s_writers_key[SB_FREEZE_LEVELS]; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); int set_anon_super_fc(struct super_block *s, struct fs_context *fc); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); struct super_block *sget_dev(struct fs_context *fc, dev_t dev); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) ({ \ const struct file_operations *_fops = (fops); \ (((_fops) && try_module_get((_fops)->owner) ? (_fops) : NULL)); \ }) #define fops_put(fops) ({ \ const struct file_operations *_fops = (fops); \ if (_fops) \ module_put((_fops)->owner); \ }) /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies * should be sufficient to pin the caller down as well. */ #define replace_fops(f, fops) \ do { \ struct file *__file = (f); \ fops_put(__file->f_op); \ BUG_ON(!(__file->f_op = (fops))); \ } while(0) extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); int freeze_super(struct super_block *super, enum freeze_holder who); int thaw_super(struct super_block *super, enum freeze_holder who); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len) { if (WARN_ON(len > sizeof(sb->s_uuid))) len = sizeof(sb->s_uuid); sb->s_uuid_len = len; memcpy(&sb->s_uuid, uuid, len); } /* set sb sysfs name based on sb->s_bdev */ static inline void super_set_sysfs_name_bdev(struct super_block *sb) { snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev); } /* set sb sysfs name based on sb->s_uuid */ static inline void super_set_sysfs_name_uuid(struct super_block *sb) { WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid)); snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b); } /* set sb sysfs name based on sb->s_id */ static inline void super_set_sysfs_name_id(struct super_block *sb) { strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name)); } /* try to use something standard before you use this */ __printf(2, 3) static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...) { va_list args; va_start(args, fmt); vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args); va_end(args); } extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); int inode_update_timestamps(struct inode *inode, int flags); int generic_update_time(struct inode *, int); /* /sys/fs */ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) /* fs/open.c */ struct audit_names; struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ atomic_t refcnt; struct audit_names *aname; const char iname[]; }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); static inline struct mnt_idmap *file_mnt_idmap(const struct file *file) { return mnt_idmap(file->f_path.mnt); } /** * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check * * If @mnt has an non @nop_mnt_idmap attached to it then @mnt is mapped. * * Return: true if mount is mapped, false if not. */ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) { return mnt_idmap(mnt) != &nop_mnt_idmap; } extern long vfs_truncate(const struct path *, loff_t); int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(const struct path *, const char *, int, umode_t); static inline struct file *file_open_root_mnt(struct vfsmount *mnt, const char *name, int flags, umode_t mode) { return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, name, flags, mode); } struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); struct path *backing_file_user_path(struct file *f); /* * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file * stored in ->vm_file is a backing file whose f_inode is on the underlying * filesystem. When the mapped file path and inode number are displayed to * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the * path and inode number to display to the user, which is the path of the fd * that user has requested to map and the inode number that would be returned * by fstat() on that same fd. */ /* Get the path to display in /proc/<pid>/maps */ static inline const struct path *file_user_path(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return backing_file_user_path(f); return &f->f_path; } /* Get the inode whose inode number to display in /proc/<pid>/maps */ static inline const struct inode *file_user_inode(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return d_inode(backing_file_user_path(f)->dentry); return file_inode(f); } static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); } extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); extern void putname(struct filename *name); extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); /* Helper for the simple case when original dentry is used */ static inline int finish_open_simple(struct file *file, int error) { if (error) return error; return finish_open(file, file->f_path.dentry, NULL); } /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) extern struct super_block *blockdev_superblock; static inline bool sb_is_blkdev_sb(struct super_block *sb) { return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 /* Marks the top and bottom of the second segment of free char majors */ #define CHRDEV_MAJOR_DYN_EXT_START 511 #define CHRDEV_MAJOR_DYN_EXT_END 384 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name, const struct file_operations *fops); extern void __unregister_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name); extern void unregister_chrdev_region(dev_t, unsigned); extern void chrdev_show(struct seq_file *,off_t); static inline int register_chrdev(unsigned int major, const char *name, const struct file_operations *fops) { return __register_chrdev(major, 0, 256, name, fops); } static inline void unregister_chrdev(unsigned int major, const char *name) { __unregister_chrdev(major, 0, 256, name); } extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); static inline int file_write_and_wait(struct file *file) { return file_write_and_wait_range(file, 0, LLONG_MAX); } extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags); static inline bool iocb_is_dsync(const struct kiocb *iocb) { return (iocb->ki_flags & IOCB_DSYNC) || IS_SYNC(iocb->ki_filp->f_mapping->host); } /* * Sync the bytes written if this was a synchronous write. Expect ki_pos * to already be updated for the write, and will return either the amount * of bytes passed in, or an error if syncing the file failed. */ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) { if (iocb_is_dsync(iocb)) { int ret = vfs_fsync_range(iocb->ki_filp, iocb->ki_pos - count, iocb->ki_pos - 1, (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; } return count; } extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK extern int bmap(struct inode *inode, sector_t *block); #else static inline int bmap(struct inode *inode, sector_t *block) { return -EINVAL; } #endif int notify_change(struct mnt_idmap *, struct dentry *, struct iattr *, struct inode **); int inode_permission(struct mnt_idmap *, struct inode *, int); int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) { return inode_permission(file_mnt_idmap(file), file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { return inode_permission(mnt_idmap(path->mnt), d_inode(path->dentry), mask); } int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) { return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) { return (inode->i_mode ^ mode) & S_IFMT; } /** * file_start_write - get write access to a superblock for regular file io * @file: the file we want to write to * * This is a variant of sb_start_write() which is a noop on non-regualr file. * Should be matched with a call to file_end_write(). */ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_start_write_trylock(file_inode(file)->i_sb); } /** * file_end_write - drop write access to a superblock of a regular file * @file: the file we wrote to * * Should be matched with a call to file_start_write(). */ static inline void file_end_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_end_write(file_inode(file)->i_sb); } /** * kiocb_start_write - get write access to a superblock for async file io * @iocb: the io context we want to submit the write with * * This is a variant of sb_start_write() for async io submission. * Should be matched with a call to kiocb_end_write(). */ static inline void kiocb_start_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); sb_start_write(inode->i_sb); /* * Fool lockdep by telling it the lock got released so that it * doesn't complain about the held lock when we return to userspace. */ __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); } /** * kiocb_end_write - drop write access to a superblock after async file io * @iocb: the io context we sumbitted the write with * * Should be matched with a call to kiocb_start_write(). */ static inline void kiocb_end_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); /* * Tell lockdep we inherited freeze protection from submission thread. */ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); sb_end_write(inode->i_sb); } /* * This is used for regular files where some users -- especially the * currently executed binary in a process, previously handled via * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap * read-write shared) accesses. * * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. * deny_write_access() denies write access to a file. * allow_write_access() re-enables write access to a file. * * The i_writecount field of an inode can have the following values: * 0: no write access, no denied write access * < 0: (-i_writecount) users that denied write access to the file. * > 0: (i_writecount) users that have write access to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to * use {get,deny}_write_access() - these functions check the sign and refuse * to do the change if sign is wrong. */ static inline int get_write_access(struct inode *inode) { return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline int deny_write_access(struct file *file) { struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); } static inline void allow_write_access(struct file *file) { if (file) atomic_inc(&file_inode(file)->i_writecount); } static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; } #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) static inline void i_readcount_dec(struct inode *inode) { BUG_ON(atomic_dec_return(&inode->i_readcount) < 0); } static inline void i_readcount_inc(struct inode *inode) { atomic_inc(&inode->i_readcount); } #else static inline void i_readcount_dec(struct inode *inode) { return; } static inline void i_readcount_inc(struct inode *inode) { return; } #endif extern int do_pipe_flags(int *, int); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); extern char *file_path(struct file *, char *, int); /** * is_dot_dotdot - returns true only if @name is "." or ".." * @name: file name to check * @len: length of file name, in bytes */ static inline bool is_dot_dotdot(const char *name, size_t len) { return len && unlikely(name[0] == '.') && (len == 1 || (len == 2 && name[1] == '.')); } #include <linux/err.h> /* needed for stackable file system support */ extern loff_t default_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern int generic_delete_inode(struct inode *inode); static inline int generic_drop_inode(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); struct inode *iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); struct inode *iget5_locked_rcu(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); extern struct inode *find_inode_nowait(struct super_block *, unsigned long, int (*match)(struct inode *, unsigned long, void *), void *data); extern struct inode *find_inode_rcu(struct super_block *, unsigned long, int (*)(struct inode *, void *), void *); extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void lockdep_annotate_inode_mutex_key(struct inode *inode); #else static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); void dump_mapping(const struct address_space *); /* * Userspace may rely on the inode number being non-zero. For example, glibc * simply ignores files with zero i_ino in unlink() and other places. * * As an additional complication, if userspace was compiled with * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the * lower 32 bits, so we need to check that those aren't zero explicitly. With * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but * better safe than sorry. */ static inline bool is_zero_ino(ino_t ino) { return (u32)ino == 0; } /* * inode->i_lock must be held */ static inline void __iget(struct inode *inode) { atomic_inc(&inode->i_count); } extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs_flags(struct file *file, unsigned int flags); extern int file_remove_privs(struct file *); int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set * up the inode reclaim context correctly. */ #define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp) extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } extern void __remove_inode_hash(struct inode *); static inline void remove_inode_hash(struct inode *inode) { if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } extern void inode_sb_list_add(struct inode *inode); extern void inode_add_lru(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, ssize_t direct_written, ssize_t buffered_written); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter); ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/splice.c */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); ssize_t copy_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, u64 *cookie); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, loff_t file_offset); enum { /* need locking between buffered and direct access */ DIO_LOCKING = 0x01, /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, }; ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct iov_iter *iter, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif bool inode_dio_finished(const struct inode *inode); void inode_dio_wait(struct inode *inode); void inode_dio_wait_interruptible(struct inode *inode); /** * inode_dio_begin - signal start of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_begin(struct inode *inode) { atomic_inc(&inode->i_dio_count); } /** * inode_dio_end - signal finish of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) wake_up_var(&inode->i_dio_count); } extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, unsigned int unit_min, unsigned int unit_max); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); static inline loff_t __inode_get_bytes(struct inode *inode) { return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; } loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags); int vfs_fstat(int fd, struct kstat *stat); static inline int vfs_stat(const char __user *filename, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, filename, stat, 0); } static inline int vfs_lstat(const char __user *name, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); } extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); extern int simple_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern int simple_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); extern int simple_nosetlease(struct file *, int, struct file_lease **, void **); extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; extern void make_empty_dir_inode(struct inode *inode); extern bool is_empty_dir_inode(struct inode *inode); struct tree_descr { const char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); struct offset_ctx { struct maple_tree mt; unsigned long next_offset; }; void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); int simple_offset_empty(struct dentry *dentry); int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); void simple_offset_destroy(struct offset_ctx *octx); extern const struct file_operations simple_offset_dir_operations; extern int __generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); extern void generic_set_sb_d_ops(struct super_block *sb); extern int generic_ci_match(const struct inode *parent, const struct qstr *name, const struct qstr *folded_name, const u8 *de_name, u32 de_name_len); static inline bool sb_has_encoding(const struct super_block *sb) { #if IS_ENABLED(CONFIG_UNICODE) return !!sb->s_encoding; #else return false; #endif } int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); void setattr_copy(struct mnt_idmap *, struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); static inline bool vma_is_dax(const struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) { struct inode *inode; if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file) return false; if (!vma_is_dax(vma)) return false; inode = file_inode(vma->vm_file); if (S_ISCHR(inode->i_mode)) return false; /* device-dax */ return true; } static inline int iocb_flags(struct file *file) { int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if (file->f_flags & O_DSYNC) res |= IOCB_DSYNC; if (file->f_flags & __O_SYNC) res |= IOCB_SYNC; return res; } static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, int rw_type) { int kiocb_flags = 0; /* make sure there's no overlap between RWF and private IOCB flags */ BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); if (!flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND))) return -EINVAL; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; } if (flags & RWF_ATOMIC) { if (rw_type != WRITE) return -EOPNOTSUPP; if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) return -EOPNOTSUPP; } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) { if (IS_APPEND(file_inode(ki->ki_filp))) return -EPERM; ki->ki_flags &= ~IOCB_APPEND; } ki->ki_flags |= kiocb_flags; return 0; } /* Transaction based IO helpers */ /* * An argresp is stored in an allocated page and holds the * size of the argument or response, along with its content */ struct simple_transaction_argresp { ssize_t size; char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) char *simple_transaction_get(struct file *file, const char __user *buf, size_t size); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos); int simple_transaction_release(struct inode *inode, struct file *file); void simple_transaction_set(struct file *file, size_t n); /* * simple attribute files * * These attributes behave similar to those in sysfs: * * Writing to an attribute immediately sets a value, an open file can be * written to multiple times. * * Reading from an attribute creates a buffer from the value that might get * read with multiple read calls. When the attribute has been read * completely, no further read calls are possible until the file is opened * again. * * All attributes contain a text representation of a numeric value * that are accessed with the get() and set() functions. */ #define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ .write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \ .llseek = generic_file_llseek, \ } #define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) #define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) { /* don't do anything, just let the compiler check the arguments; */ } int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt); int simple_attr_release(struct inode *inode, struct file *file); ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) #define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ (flag & __FMODE_NONOTIFY))) static inline bool is_sxid(umode_t mode) { return mode & (S_ISUID | S_ISGID); } static inline int check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; return __check_sticky(idmap, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) { if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } static inline bool is_root_inode(struct inode *inode) { return inode == inode->i_sb->s_root->d_inode; } static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { return ctx->actor(ctx, name, namelen, ctx->pos, ino, type); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, file->f_path.dentry->d_inode->i_ino, DT_DIR); } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, d_parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) return false; ctx->pos = 1; } if (ctx->pos == 1) { if (!dir_emit_dotdot(file, ctx)) return false; ctx->pos = 2; } return true; } static inline bool dir_relax(struct inode *inode) { inode_unlock(inode); inode_lock(inode); return !IS_DEADDIR(inode); } static inline bool dir_relax_shared(struct inode *inode) { inode_unlock_shared(inode); inode_lock_shared(inode); return !IS_DEADDIR(inode); } extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); /* mm/fadvise.c */ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice); extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); static inline bool vfs_empty_path(int dfd, const char __user *path) { char c; if (dfd < 0) return false; /* We now allow NULL to be used for empty path. */ if (!path) return true; if (unlikely(get_user(c, path))) return false; return !c; } bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos); #endif /* _LINUX_FS_H */ |
| 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * The NFSD open file cache. * * (c) 2015 - Jeff Layton <jeff.layton@primarydata.com> * * An nfsd_file object is a per-file collection of open state that binds * together: * - a struct file * * - a user credential * - a network namespace * - a read-ahead context * - monitoring for writeback errors * * nfsd_file objects are reference-counted. Consumers acquire a new * object via the nfsd_file_acquire API. They manage their interest in * the acquired object, and hence the object's reference count, via * nfsd_file_get and nfsd_file_put. There are two varieties of nfsd_file * object: * * * non-garbage-collected: When a consumer wants to precisely control * the lifetime of a file's open state, it acquires a non-garbage- * collected nfsd_file. The final nfsd_file_put releases the open * state immediately. * * * garbage-collected: When a consumer does not control the lifetime * of open state, it acquires a garbage-collected nfsd_file. The * final nfsd_file_put allows the open state to linger for a period * during which it may be re-used. */ #include <linux/hash.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/pagemap.h> #include <linux/sched.h> #include <linux/list_lru.h> #include <linux/fsnotify_backend.h> #include <linux/fsnotify.h> #include <linux/seq_file.h> #include <linux/rhashtable.h> #include "vfs.h" #include "nfsd.h" #include "nfsfh.h" #include "netns.h" #include "filecache.h" #include "trace.h" #define NFSD_LAUNDRETTE_DELAY (2 * HZ) #define NFSD_FILE_CACHE_UP (0) /* We only care about NFSD_MAY_READ/WRITE for this cache */ #define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE|NFSD_MAY_LOCALIO) static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits); static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions); static DEFINE_PER_CPU(unsigned long, nfsd_file_allocations); static DEFINE_PER_CPU(unsigned long, nfsd_file_releases); static DEFINE_PER_CPU(unsigned long, nfsd_file_total_age); static DEFINE_PER_CPU(unsigned long, nfsd_file_evictions); struct nfsd_fcache_disposal { spinlock_t lock; struct list_head freeme; }; static struct kmem_cache *nfsd_file_slab; static struct kmem_cache *nfsd_file_mark_slab; static struct list_lru nfsd_file_lru; static unsigned long nfsd_file_flags; static struct fsnotify_group *nfsd_file_fsnotify_group; static struct delayed_work nfsd_filecache_laundrette; static struct rhltable nfsd_file_rhltable ____cacheline_aligned_in_smp; static bool nfsd_match_cred(const struct cred *c1, const struct cred *c2) { int i; if (!uid_eq(c1->fsuid, c2->fsuid)) return false; if (!gid_eq(c1->fsgid, c2->fsgid)) return false; if (c1->group_info == NULL || c2->group_info == NULL) return c1->group_info == c2->group_info; if (c1->group_info->ngroups != c2->group_info->ngroups) return false; for (i = 0; i < c1->group_info->ngroups; i++) { if (!gid_eq(c1->group_info->gid[i], c2->group_info->gid[i])) return false; } return true; } static const struct rhashtable_params nfsd_file_rhash_params = { .key_len = sizeof_field(struct nfsd_file, nf_inode), .key_offset = offsetof(struct nfsd_file, nf_inode), .head_offset = offsetof(struct nfsd_file, nf_rlist), /* * Start with a single page hash table to reduce resizing churn * on light workloads. */ .min_size = 256, .automatic_shrinking = true, }; static void nfsd_file_schedule_laundrette(void) { if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags)) queue_delayed_work(system_unbound_wq, &nfsd_filecache_laundrette, NFSD_LAUNDRETTE_DELAY); } static void nfsd_file_slab_free(struct rcu_head *rcu) { struct nfsd_file *nf = container_of(rcu, struct nfsd_file, nf_rcu); put_cred(nf->nf_cred); kmem_cache_free(nfsd_file_slab, nf); } static void nfsd_file_mark_free(struct fsnotify_mark *mark) { struct nfsd_file_mark *nfm = container_of(mark, struct nfsd_file_mark, nfm_mark); kmem_cache_free(nfsd_file_mark_slab, nfm); } static struct nfsd_file_mark * nfsd_file_mark_get(struct nfsd_file_mark *nfm) { if (!refcount_inc_not_zero(&nfm->nfm_ref)) return NULL; return nfm; } static void nfsd_file_mark_put(struct nfsd_file_mark *nfm) { if (refcount_dec_and_test(&nfm->nfm_ref)) { fsnotify_destroy_mark(&nfm->nfm_mark, nfsd_file_fsnotify_group); fsnotify_put_mark(&nfm->nfm_mark); } } static struct nfsd_file_mark * nfsd_file_mark_find_or_create(struct inode *inode) { int err; struct fsnotify_mark *mark; struct nfsd_file_mark *nfm = NULL, *new; do { fsnotify_group_lock(nfsd_file_fsnotify_group); mark = fsnotify_find_inode_mark(inode, nfsd_file_fsnotify_group); if (mark) { nfm = nfsd_file_mark_get(container_of(mark, struct nfsd_file_mark, nfm_mark)); fsnotify_group_unlock(nfsd_file_fsnotify_group); if (nfm) { fsnotify_put_mark(mark); break; } /* Avoid soft lockup race with nfsd_file_mark_put() */ fsnotify_destroy_mark(mark, nfsd_file_fsnotify_group); fsnotify_put_mark(mark); } else { fsnotify_group_unlock(nfsd_file_fsnotify_group); } /* allocate a new nfm */ new = kmem_cache_alloc(nfsd_file_mark_slab, GFP_KERNEL); if (!new) return NULL; fsnotify_init_mark(&new->nfm_mark, nfsd_file_fsnotify_group); new->nfm_mark.mask = FS_ATTRIB|FS_DELETE_SELF; refcount_set(&new->nfm_ref, 1); err = fsnotify_add_inode_mark(&new->nfm_mark, inode, 0); /* * If the add was successful, then return the object. * Otherwise, we need to put the reference we hold on the * nfm_mark. The fsnotify code will take a reference and put * it on failure, so we can't just free it directly. It's also * not safe to call fsnotify_destroy_mark on it as the * mark->group will be NULL. Thus, we can't let the nfm_ref * counter drive the destruction at this point. */ if (likely(!err)) nfm = new; else fsnotify_put_mark(&new->nfm_mark); } while (unlikely(err == -EEXIST)); return nfm; } static struct nfsd_file * nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need, bool want_gc) { struct nfsd_file *nf; nf = kmem_cache_alloc(nfsd_file_slab, GFP_KERNEL); if (unlikely(!nf)) return NULL; this_cpu_inc(nfsd_file_allocations); INIT_LIST_HEAD(&nf->nf_lru); INIT_LIST_HEAD(&nf->nf_gc); nf->nf_birthtime = ktime_get(); nf->nf_file = NULL; nf->nf_cred = get_current_cred(); nf->nf_net = net; nf->nf_flags = want_gc ? BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING) | BIT(NFSD_FILE_GC) : BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING); nf->nf_inode = inode; refcount_set(&nf->nf_ref, 1); nf->nf_may = need; nf->nf_mark = NULL; return nf; } /** * nfsd_file_check_write_error - check for writeback errors on a file * @nf: nfsd_file to check for writeback errors * * Check whether a nfsd_file has an unseen error. Reset the write * verifier if so. */ static void nfsd_file_check_write_error(struct nfsd_file *nf) { struct file *file = nf->nf_file; if ((file->f_mode & FMODE_WRITE) && filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err))) nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); } static void nfsd_file_hash_remove(struct nfsd_file *nf) { trace_nfsd_file_unhash(nf); rhltable_remove(&nfsd_file_rhltable, &nf->nf_rlist, nfsd_file_rhash_params); } static bool nfsd_file_unhash(struct nfsd_file *nf) { if (test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { nfsd_file_hash_remove(nf); return true; } return false; } static void nfsd_file_free(struct nfsd_file *nf) { s64 age = ktime_to_ms(ktime_sub(ktime_get(), nf->nf_birthtime)); trace_nfsd_file_free(nf); this_cpu_inc(nfsd_file_releases); this_cpu_add(nfsd_file_total_age, age); nfsd_file_unhash(nf); if (nf->nf_mark) nfsd_file_mark_put(nf->nf_mark); if (nf->nf_file) { nfsd_file_check_write_error(nf); nfsd_filp_close(nf->nf_file); } /* * If this item is still linked via nf_lru, that's a bug. * WARN and leak it to preserve system stability. */ if (WARN_ON_ONCE(!list_empty(&nf->nf_lru))) return; call_rcu(&nf->nf_rcu, nfsd_file_slab_free); } static bool nfsd_file_check_writeback(struct nfsd_file *nf) { struct file *file = nf->nf_file; struct address_space *mapping; /* File not open for write? */ if (!(file->f_mode & FMODE_WRITE)) return false; /* * Some filesystems (e.g. NFS) flush all dirty data on close. * On others, there is no need to wait for writeback. */ if (!(file_inode(file)->i_sb->s_export_op->flags & EXPORT_OP_FLUSH_ON_CLOSE)) return false; mapping = file->f_mapping; return mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) || mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); } static bool nfsd_file_lru_add(struct nfsd_file *nf) { set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); if (list_lru_add_obj(&nfsd_file_lru, &nf->nf_lru)) { trace_nfsd_file_lru_add(nf); return true; } return false; } static bool nfsd_file_lru_remove(struct nfsd_file *nf) { if (list_lru_del_obj(&nfsd_file_lru, &nf->nf_lru)) { trace_nfsd_file_lru_del(nf); return true; } return false; } struct nfsd_file * nfsd_file_get(struct nfsd_file *nf) { if (nf && refcount_inc_not_zero(&nf->nf_ref)) return nf; return NULL; } /** * nfsd_file_put - put the reference to a nfsd_file * @nf: nfsd_file of which to put the reference * * Put a reference to a nfsd_file. In the non-GC case, we just put the * reference immediately. In the GC case, if the reference would be * the last one, the put it on the LRU instead to be cleaned up later. */ void nfsd_file_put(struct nfsd_file *nf) { might_sleep(); trace_nfsd_file_put(nf); if (test_bit(NFSD_FILE_GC, &nf->nf_flags) && test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { /* * If this is the last reference (nf_ref == 1), then try to * transfer it to the LRU. */ if (refcount_dec_not_one(&nf->nf_ref)) return; /* Try to add it to the LRU. If that fails, decrement. */ if (nfsd_file_lru_add(nf)) { /* If it's still hashed, we're done */ if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { nfsd_file_schedule_laundrette(); return; } /* * We're racing with unhashing, so try to remove it from * the LRU. If removal fails, then someone else already * has our reference. */ if (!nfsd_file_lru_remove(nf)) return; } } if (refcount_dec_and_test(&nf->nf_ref)) nfsd_file_free(nf); } /** * nfsd_file_put_local - put the reference to nfsd_file and local nfsd_serv * @nf: nfsd_file of which to put the references * * First put the reference of the nfsd_file and then put the * reference to the associated nn->nfsd_serv. */ void nfsd_file_put_local(struct nfsd_file *nf) { struct net *net = nf->nf_net; nfsd_file_put(nf); nfsd_serv_put(net); } /** * nfsd_file_file - get the backing file of an nfsd_file * @nf: nfsd_file of which to access the backing file. * * Return backing file for @nf. */ struct file * nfsd_file_file(struct nfsd_file *nf) { return nf->nf_file; } static void nfsd_file_dispose_list(struct list_head *dispose) { struct nfsd_file *nf; while (!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_gc); list_del_init(&nf->nf_gc); nfsd_file_free(nf); } } /** * nfsd_file_dispose_list_delayed - move list of dead files to net's freeme list * @dispose: list of nfsd_files to be disposed * * Transfers each file to the "freeme" list for its nfsd_net, to eventually * be disposed of by the per-net garbage collector. */ static void nfsd_file_dispose_list_delayed(struct list_head *dispose) { while(!list_empty(dispose)) { struct nfsd_file *nf = list_first_entry(dispose, struct nfsd_file, nf_gc); struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id); struct nfsd_fcache_disposal *l = nn->fcache_disposal; spin_lock(&l->lock); list_move_tail(&nf->nf_gc, &l->freeme); spin_unlock(&l->lock); svc_wake_up(nn->nfsd_serv); } } /** * nfsd_file_net_dispose - deal with nfsd_files waiting to be disposed. * @nn: nfsd_net in which to find files to be disposed. * * When files held open for nfsv3 are removed from the filecache, whether * due to memory pressure or garbage collection, they are queued to * a per-net-ns queue. This function completes the disposal, either * directly or by waking another nfsd thread to help with the work. */ void nfsd_file_net_dispose(struct nfsd_net *nn) { struct nfsd_fcache_disposal *l = nn->fcache_disposal; if (!list_empty(&l->freeme)) { LIST_HEAD(dispose); int i; spin_lock(&l->lock); for (i = 0; i < 8 && !list_empty(&l->freeme); i++) list_move(l->freeme.next, &dispose); spin_unlock(&l->lock); if (!list_empty(&l->freeme)) /* Wake up another thread to share the work * *before* doing any actual disposing. */ svc_wake_up(nn->nfsd_serv); nfsd_file_dispose_list(&dispose); } } /** * nfsd_file_lru_cb - Examine an entry on the LRU list * @item: LRU entry to examine * @lru: controlling LRU * @lock: LRU list lock (unused) * @arg: dispose list * * Return values: * %LRU_REMOVED: @item was removed from the LRU * %LRU_ROTATE: @item is to be moved to the LRU tail * %LRU_SKIP: @item cannot be evicted */ static enum lru_status nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, spinlock_t *lock, void *arg) __releases(lock) __acquires(lock) { struct list_head *head = arg; struct nfsd_file *nf = list_entry(item, struct nfsd_file, nf_lru); /* We should only be dealing with GC entries here */ WARN_ON_ONCE(!test_bit(NFSD_FILE_GC, &nf->nf_flags)); /* * Don't throw out files that are still undergoing I/O or * that have uncleared errors pending. */ if (nfsd_file_check_writeback(nf)) { trace_nfsd_file_gc_writeback(nf); return LRU_SKIP; } /* If it was recently added to the list, skip it */ if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags)) { trace_nfsd_file_gc_referenced(nf); return LRU_ROTATE; } /* * Put the reference held on behalf of the LRU. If it wasn't the last * one, then just remove it from the LRU and ignore it. */ if (!refcount_dec_and_test(&nf->nf_ref)) { trace_nfsd_file_gc_in_use(nf); list_lru_isolate(lru, &nf->nf_lru); return LRU_REMOVED; } /* Refcount went to zero. Unhash it and queue it to the dispose list */ nfsd_file_unhash(nf); list_lru_isolate(lru, &nf->nf_lru); list_add(&nf->nf_gc, head); this_cpu_inc(nfsd_file_evictions); trace_nfsd_file_gc_disposed(nf); return LRU_REMOVED; } static void nfsd_file_gc(void) { LIST_HEAD(dispose); unsigned long ret; ret = list_lru_walk(&nfsd_file_lru, nfsd_file_lru_cb, &dispose, list_lru_count(&nfsd_file_lru)); trace_nfsd_file_gc_removed(ret, list_lru_count(&nfsd_file_lru)); nfsd_file_dispose_list_delayed(&dispose); } static void nfsd_file_gc_worker(struct work_struct *work) { nfsd_file_gc(); if (list_lru_count(&nfsd_file_lru)) nfsd_file_schedule_laundrette(); } static unsigned long nfsd_file_lru_count(struct shrinker *s, struct shrink_control *sc) { return list_lru_count(&nfsd_file_lru); } static unsigned long nfsd_file_lru_scan(struct shrinker *s, struct shrink_control *sc) { LIST_HEAD(dispose); unsigned long ret; ret = list_lru_shrink_walk(&nfsd_file_lru, sc, nfsd_file_lru_cb, &dispose); trace_nfsd_file_shrinker_removed(ret, list_lru_count(&nfsd_file_lru)); nfsd_file_dispose_list_delayed(&dispose); return ret; } static struct shrinker *nfsd_file_shrinker; /** * nfsd_file_cond_queue - conditionally unhash and queue a nfsd_file * @nf: nfsd_file to attempt to queue * @dispose: private list to queue successfully-put objects * * Unhash an nfsd_file, try to get a reference to it, and then put that * reference. If it's the last reference, queue it to the dispose list. */ static void nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) __must_hold(RCU) { int decrement = 1; /* If we raced with someone else unhashing, ignore it */ if (!nfsd_file_unhash(nf)) return; /* If we can't get a reference, ignore it */ if (!nfsd_file_get(nf)) return; /* Extra decrement if we remove from the LRU */ if (nfsd_file_lru_remove(nf)) ++decrement; /* If refcount goes to 0, then put on the dispose list */ if (refcount_sub_and_test(decrement, &nf->nf_ref)) { list_add(&nf->nf_gc, dispose); trace_nfsd_file_closing(nf); } } /** * nfsd_file_queue_for_close: try to close out any open nfsd_files for an inode * @inode: inode on which to close out nfsd_files * @dispose: list on which to gather nfsd_files to close out * * An nfsd_file represents a struct file being held open on behalf of nfsd. * An open file however can block other activity (such as leases), or cause * undesirable behavior (e.g. spurious silly-renames when reexporting NFS). * * This function is intended to find open nfsd_files when this sort of * conflicting access occurs and then attempt to close those files out. * * Populates the dispose list with entries that have already had their * refcounts go to zero. The actual free of an nfsd_file can be expensive, * so we leave it up to the caller whether it wants to wait or not. */ static void nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose) { struct rhlist_head *tmp, *list; struct nfsd_file *nf; rcu_read_lock(); list = rhltable_lookup(&nfsd_file_rhltable, &inode, nfsd_file_rhash_params); rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { if (!test_bit(NFSD_FILE_GC, &nf->nf_flags)) continue; nfsd_file_cond_queue(nf, dispose); } rcu_read_unlock(); } /** * nfsd_file_close_inode - attempt a delayed close of a nfsd_file * @inode: inode of the file to attempt to remove * * Close out any open nfsd_files that can be reaped for @inode. The * actual freeing is deferred to the dispose_list_delayed infrastructure. * * This is used by the fsnotify callbacks and setlease notifier. */ static void nfsd_file_close_inode(struct inode *inode) { LIST_HEAD(dispose); nfsd_file_queue_for_close(inode, &dispose); nfsd_file_dispose_list_delayed(&dispose); } /** * nfsd_file_close_inode_sync - attempt to forcibly close a nfsd_file * @inode: inode of the file to attempt to remove * * Close out any open nfsd_files that can be reaped for @inode. The * nfsd_files are closed out synchronously. * * This is called from nfsd_rename and nfsd_unlink to avoid silly-renames * when reexporting NFS. */ void nfsd_file_close_inode_sync(struct inode *inode) { struct nfsd_file *nf; LIST_HEAD(dispose); trace_nfsd_file_close(inode); nfsd_file_queue_for_close(inode, &dispose); while (!list_empty(&dispose)) { nf = list_first_entry(&dispose, struct nfsd_file, nf_gc); list_del_init(&nf->nf_gc); nfsd_file_free(nf); } } static int nfsd_file_lease_notifier_call(struct notifier_block *nb, unsigned long arg, void *data) { struct file_lease *fl = data; /* Only close files for F_SETLEASE leases */ if (fl->c.flc_flags & FL_LEASE) nfsd_file_close_inode(file_inode(fl->c.flc_file)); return 0; } static struct notifier_block nfsd_file_lease_notifier = { .notifier_call = nfsd_file_lease_notifier_call, }; static int nfsd_file_fsnotify_handle_event(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { if (WARN_ON_ONCE(!inode)) return 0; trace_nfsd_file_fsnotify_handle_event(inode, mask); /* Should be no marks on non-regular files */ if (!S_ISREG(inode->i_mode)) { WARN_ON_ONCE(1); return 0; } /* don't close files if this was not the last link */ if (mask & FS_ATTRIB) { if (inode->i_nlink) return 0; } nfsd_file_close_inode(inode); return 0; } static const struct fsnotify_ops nfsd_file_fsnotify_ops = { .handle_inode_event = nfsd_file_fsnotify_handle_event, .free_mark = nfsd_file_mark_free, }; int nfsd_file_cache_init(void) { int ret; lockdep_assert_held(&nfsd_mutex); if (test_and_set_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) return 0; ret = rhltable_init(&nfsd_file_rhltable, &nfsd_file_rhash_params); if (ret) return ret; ret = -ENOMEM; nfsd_file_slab = KMEM_CACHE(nfsd_file, 0); if (!nfsd_file_slab) { pr_err("nfsd: unable to create nfsd_file_slab\n"); goto out_err; } nfsd_file_mark_slab = KMEM_CACHE(nfsd_file_mark, 0); if (!nfsd_file_mark_slab) { pr_err("nfsd: unable to create nfsd_file_mark_slab\n"); goto out_err; } ret = list_lru_init(&nfsd_file_lru); if (ret) { pr_err("nfsd: failed to init nfsd_file_lru: %d\n", ret); goto out_err; } nfsd_file_shrinker = shrinker_alloc(0, "nfsd-filecache"); if (!nfsd_file_shrinker) { ret = -ENOMEM; pr_err("nfsd: failed to allocate nfsd_file_shrinker\n"); goto out_lru; } nfsd_file_shrinker->count_objects = nfsd_file_lru_count; nfsd_file_shrinker->scan_objects = nfsd_file_lru_scan; nfsd_file_shrinker->seeks = 1; shrinker_register(nfsd_file_shrinker); ret = lease_register_notifier(&nfsd_file_lease_notifier); if (ret) { pr_err("nfsd: unable to register lease notifier: %d\n", ret); goto out_shrinker; } nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops, FSNOTIFY_GROUP_NOFS); if (IS_ERR(nfsd_file_fsnotify_group)) { pr_err("nfsd: unable to create fsnotify group: %ld\n", PTR_ERR(nfsd_file_fsnotify_group)); ret = PTR_ERR(nfsd_file_fsnotify_group); nfsd_file_fsnotify_group = NULL; goto out_notifier; } INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker); out: return ret; out_notifier: lease_unregister_notifier(&nfsd_file_lease_notifier); out_shrinker: shrinker_free(nfsd_file_shrinker); out_lru: list_lru_destroy(&nfsd_file_lru); out_err: kmem_cache_destroy(nfsd_file_slab); nfsd_file_slab = NULL; kmem_cache_destroy(nfsd_file_mark_slab); nfsd_file_mark_slab = NULL; rhltable_destroy(&nfsd_file_rhltable); goto out; } /** * __nfsd_file_cache_purge: clean out the cache for shutdown * @net: net-namespace to shut down the cache (may be NULL) * * Walk the nfsd_file cache and close out any that match @net. If @net is NULL, * then close out everything. Called when an nfsd instance is being shut down, * and when the exports table is flushed. */ static void __nfsd_file_cache_purge(struct net *net) { struct rhashtable_iter iter; struct nfsd_file *nf; LIST_HEAD(dispose); rhltable_walk_enter(&nfsd_file_rhltable, &iter); do { rhashtable_walk_start(&iter); nf = rhashtable_walk_next(&iter); while (!IS_ERR_OR_NULL(nf)) { if (!net || nf->nf_net == net) nfsd_file_cond_queue(nf, &dispose); nf = rhashtable_walk_next(&iter); } rhashtable_walk_stop(&iter); } while (nf == ERR_PTR(-EAGAIN)); rhashtable_walk_exit(&iter); nfsd_file_dispose_list(&dispose); } static struct nfsd_fcache_disposal * nfsd_alloc_fcache_disposal(void) { struct nfsd_fcache_disposal *l; l = kmalloc(sizeof(*l), GFP_KERNEL); if (!l) return NULL; spin_lock_init(&l->lock); INIT_LIST_HEAD(&l->freeme); return l; } static void nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l) { nfsd_file_dispose_list(&l->freeme); kfree(l); } static void nfsd_free_fcache_disposal_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct nfsd_fcache_disposal *l = nn->fcache_disposal; nfsd_free_fcache_disposal(l); } int nfsd_file_cache_start_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); nn->fcache_disposal = nfsd_alloc_fcache_disposal(); return nn->fcache_disposal ? 0 : -ENOMEM; } /** * nfsd_file_cache_purge - Remove all cache items associated with @net * @net: target net namespace * */ void nfsd_file_cache_purge(struct net *net) { lockdep_assert_held(&nfsd_mutex); if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) __nfsd_file_cache_purge(net); } void nfsd_file_cache_shutdown_net(struct net *net) { nfsd_file_cache_purge(net); nfsd_free_fcache_disposal_net(net); } void nfsd_file_cache_shutdown(void) { int i; lockdep_assert_held(&nfsd_mutex); if (test_and_clear_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0) return; lease_unregister_notifier(&nfsd_file_lease_notifier); shrinker_free(nfsd_file_shrinker); /* * make sure all callers of nfsd_file_lru_cb are done before * calling nfsd_file_cache_purge */ cancel_delayed_work_sync(&nfsd_filecache_laundrette); __nfsd_file_cache_purge(NULL); list_lru_destroy(&nfsd_file_lru); rcu_barrier(); fsnotify_put_group(nfsd_file_fsnotify_group); nfsd_file_fsnotify_group = NULL; kmem_cache_destroy(nfsd_file_slab); nfsd_file_slab = NULL; fsnotify_wait_marks_destroyed(); kmem_cache_destroy(nfsd_file_mark_slab); nfsd_file_mark_slab = NULL; rhltable_destroy(&nfsd_file_rhltable); for_each_possible_cpu(i) { per_cpu(nfsd_file_cache_hits, i) = 0; per_cpu(nfsd_file_acquisitions, i) = 0; per_cpu(nfsd_file_allocations, i) = 0; per_cpu(nfsd_file_releases, i) = 0; per_cpu(nfsd_file_total_age, i) = 0; per_cpu(nfsd_file_evictions, i) = 0; } } static struct nfsd_file * nfsd_file_lookup_locked(const struct net *net, const struct cred *cred, struct inode *inode, unsigned char need, bool want_gc) { struct rhlist_head *tmp, *list; struct nfsd_file *nf; list = rhltable_lookup(&nfsd_file_rhltable, &inode, nfsd_file_rhash_params); rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { if (nf->nf_may != need) continue; if (nf->nf_net != net) continue; if (!nfsd_match_cred(nf->nf_cred, cred)) continue; if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != want_gc) continue; if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) continue; if (!nfsd_file_get(nf)) continue; return nf; } return NULL; } /** * nfsd_file_is_cached - are there any cached open files for this inode? * @inode: inode to check * * The lookup matches inodes in all net namespaces and is atomic wrt * nfsd_file_acquire(). * * Return values: * %true: filecache contains at least one file matching this inode * %false: filecache contains no files matching this inode */ bool nfsd_file_is_cached(struct inode *inode) { struct rhlist_head *tmp, *list; struct nfsd_file *nf; bool ret = false; rcu_read_lock(); list = rhltable_lookup(&nfsd_file_rhltable, &inode, nfsd_file_rhash_params); rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) if (test_bit(NFSD_FILE_GC, &nf->nf_flags)) { ret = true; break; } rcu_read_unlock(); trace_nfsd_file_is_cached(inode, (int)ret); return ret; } static __be32 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, struct svc_cred *cred, struct auth_domain *client, struct svc_fh *fhp, unsigned int may_flags, struct file *file, struct nfsd_file **pnf, bool want_gc) { unsigned char need = may_flags & NFSD_FILE_MAY_MASK; struct nfsd_file *new, *nf; bool stale_retry = true; bool open_retry = true; struct inode *inode; __be32 status; int ret; retry: if (rqstp) { status = fh_verify(rqstp, fhp, S_IFREG, may_flags|NFSD_MAY_OWNER_OVERRIDE); } else { status = fh_verify_local(net, cred, client, fhp, S_IFREG, may_flags|NFSD_MAY_OWNER_OVERRIDE); } if (status != nfs_ok) return status; inode = d_inode(fhp->fh_dentry); rcu_read_lock(); nf = nfsd_file_lookup_locked(net, current_cred(), inode, need, want_gc); rcu_read_unlock(); if (nf) { /* * If the nf is on the LRU then it holds an extra reference * that must be put if it's removed. It had better not be * the last one however, since we should hold another. */ if (nfsd_file_lru_remove(nf)) WARN_ON_ONCE(refcount_dec_and_test(&nf->nf_ref)); goto wait_for_construction; } new = nfsd_file_alloc(net, inode, need, want_gc); if (!new) { status = nfserr_jukebox; goto out; } rcu_read_lock(); spin_lock(&inode->i_lock); nf = nfsd_file_lookup_locked(net, current_cred(), inode, need, want_gc); if (unlikely(nf)) { spin_unlock(&inode->i_lock); rcu_read_unlock(); nfsd_file_free(new); goto wait_for_construction; } nf = new; ret = rhltable_insert(&nfsd_file_rhltable, &nf->nf_rlist, nfsd_file_rhash_params); spin_unlock(&inode->i_lock); rcu_read_unlock(); if (likely(ret == 0)) goto open_file; trace_nfsd_file_insert_err(rqstp, inode, may_flags, ret); status = nfserr_jukebox; goto construction_err; wait_for_construction: wait_on_bit(&nf->nf_flags, NFSD_FILE_PENDING, TASK_UNINTERRUPTIBLE); /* Did construction of this file fail? */ if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { trace_nfsd_file_cons_err(rqstp, inode, may_flags, nf); if (!open_retry) { status = nfserr_jukebox; goto construction_err; } nfsd_file_put(nf); open_retry = false; fh_put(fhp); goto retry; } this_cpu_inc(nfsd_file_cache_hits); status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags)); if (status != nfs_ok) { nfsd_file_put(nf); nf = NULL; } out: if (status == nfs_ok) { this_cpu_inc(nfsd_file_acquisitions); nfsd_file_check_write_error(nf); *pnf = nf; } trace_nfsd_file_acquire(rqstp, inode, may_flags, nf, status); return status; open_file: trace_nfsd_file_alloc(nf); nf->nf_mark = nfsd_file_mark_find_or_create(inode); if (nf->nf_mark) { if (file) { get_file(file); nf->nf_file = file; status = nfs_ok; trace_nfsd_file_opened(nf, status); } else { ret = nfsd_open_verified(rqstp, fhp, may_flags, &nf->nf_file); if (ret == -EOPENSTALE && stale_retry) { stale_retry = false; nfsd_file_unhash(nf); clear_and_wake_up_bit(NFSD_FILE_PENDING, &nf->nf_flags); if (refcount_dec_and_test(&nf->nf_ref)) nfsd_file_free(nf); nf = NULL; fh_put(fhp); goto retry; } status = nfserrno(ret); trace_nfsd_file_open(nf, status); } } else status = nfserr_jukebox; /* * If construction failed, or we raced with a call to unlink() * then unhash. */ if (status != nfs_ok || inode->i_nlink == 0) nfsd_file_unhash(nf); clear_and_wake_up_bit(NFSD_FILE_PENDING, &nf->nf_flags); if (status == nfs_ok) goto out; construction_err: if (refcount_dec_and_test(&nf->nf_ref)) nfsd_file_free(nf); nf = NULL; goto out; } /** * nfsd_file_acquire_gc - Get a struct nfsd_file with an open file * @rqstp: the RPC transaction being executed * @fhp: the NFS filehandle of the file to be opened * @may_flags: NFSD_MAY_ settings for the file * @pnf: OUT: new or found "struct nfsd_file" object * * The nfsd_file object returned by this API is reference-counted * and garbage-collected. The object is retained for a few * seconds after the final nfsd_file_put() in case the caller * wants to re-use it. * * Return values: * %nfs_ok - @pnf points to an nfsd_file with its reference * count boosted. * * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, fhp, may_flags, NULL, pnf, true); } /** * nfsd_file_acquire - Get a struct nfsd_file with an open file * @rqstp: the RPC transaction being executed * @fhp: the NFS filehandle of the file to be opened * @may_flags: NFSD_MAY_ settings for the file * @pnf: OUT: new or found "struct nfsd_file" object * * The nfsd_file_object returned by this API is reference-counted * but not garbage-collected. The object is unhashed after the * final nfsd_file_put(). * * Return values: * %nfs_ok - @pnf points to an nfsd_file with its reference * count boosted. * * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, fhp, may_flags, NULL, pnf, false); } /** * nfsd_file_acquire_local - Get a struct nfsd_file with an open file for localio * @net: The network namespace in which to perform a lookup * @cred: the user credential with which to validate access * @client: the auth_domain for LOCALIO lookup * @fhp: the NFS filehandle of the file to be opened * @may_flags: NFSD_MAY_ settings for the file * @pnf: OUT: new or found "struct nfsd_file" object * * This file lookup interface provide access to a file given the * filehandle and credential. No connection-based authorisation * is performed and in that way it is quite different to other * file access mediated by nfsd. It allows a kernel module such as the NFS * client to reach across network and filesystem namespaces to access * a file. The security implications of this should be carefully * considered before use. * * The nfsd_file object returned by this API is reference-counted * and garbage-collected. The object is retained for a few * seconds after the final nfsd_file_put() in case the caller * wants to re-use it. * * Return values: * %nfs_ok - @pnf points to an nfsd_file with its reference * count boosted. * * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire_local(struct net *net, struct svc_cred *cred, struct auth_domain *client, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { /* * Save creds before calling nfsd_file_do_acquire() (which calls * nfsd_setuser). Important because caller (LOCALIO) is from * client context. */ const struct cred *save_cred = get_current_cred(); __be32 beres; beres = nfsd_file_do_acquire(NULL, net, cred, client, fhp, may_flags, NULL, pnf, true); revert_creds(save_cred); return beres; } /** * nfsd_file_acquire_opened - Get a struct nfsd_file using existing open file * @rqstp: the RPC transaction being executed * @fhp: the NFS filehandle of the file just created * @may_flags: NFSD_MAY_ settings for the file * @file: cached, already-open file (may be NULL) * @pnf: OUT: new or found "struct nfsd_file" object * * Acquire a nfsd_file object that is not GC'ed. If one doesn't already exist, * and @file is non-NULL, use it to instantiate a new nfsd_file instead of * opening a new one. * * Return values: * %nfs_ok - @pnf points to an nfsd_file with its reference * count boosted. * * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct file *file, struct nfsd_file **pnf) { return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL, fhp, may_flags, file, pnf, false); } /* * Note that fields may be added, removed or reordered in the future. Programs * scraping this file for info should test the labels to ensure they're * getting the correct field. */ int nfsd_file_cache_stats_show(struct seq_file *m, void *v) { unsigned long allocations = 0, releases = 0, evictions = 0; unsigned long hits = 0, acquisitions = 0; unsigned int i, count = 0, buckets = 0; unsigned long lru = 0, total_age = 0; /* Serialize with server shutdown */ mutex_lock(&nfsd_mutex); if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) { struct bucket_table *tbl; struct rhashtable *ht; lru = list_lru_count(&nfsd_file_lru); rcu_read_lock(); ht = &nfsd_file_rhltable.ht; count = atomic_read(&ht->nelems); tbl = rht_dereference_rcu(ht->tbl, ht); buckets = tbl->size; rcu_read_unlock(); } mutex_unlock(&nfsd_mutex); for_each_possible_cpu(i) { hits += per_cpu(nfsd_file_cache_hits, i); acquisitions += per_cpu(nfsd_file_acquisitions, i); allocations += per_cpu(nfsd_file_allocations, i); releases += per_cpu(nfsd_file_releases, i); total_age += per_cpu(nfsd_file_total_age, i); evictions += per_cpu(nfsd_file_evictions, i); } seq_printf(m, "total inodes: %u\n", count); seq_printf(m, "hash buckets: %u\n", buckets); seq_printf(m, "lru entries: %lu\n", lru); seq_printf(m, "cache hits: %lu\n", hits); seq_printf(m, "acquisitions: %lu\n", acquisitions); seq_printf(m, "allocations: %lu\n", allocations); seq_printf(m, "releases: %lu\n", releases); seq_printf(m, "evictions: %lu\n", evictions); if (releases) seq_printf(m, "mean age (ms): %ld\n", total_age / releases); else seq_printf(m, "mean age (ms): -\n"); return 0; } |
| 4 4 4 4 4 4 4 4 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 | // SPDX-License-Identifier: GPL-2.0 /* * XFRM compat layer * Author: Dmitry Safonov <dima@arista.com> * Based on code and translator idea by: Florian Westphal <fw@strlen.de> */ #include <linux/compat.h> #include <linux/nospec.h> #include <linux/xfrm.h> #include <net/xfrm.h> struct compat_xfrm_lifetime_cfg { compat_u64 soft_byte_limit, hard_byte_limit; compat_u64 soft_packet_limit, hard_packet_limit; compat_u64 soft_add_expires_seconds, hard_add_expires_seconds; compat_u64 soft_use_expires_seconds, hard_use_expires_seconds; }; /* same size on 32bit, but only 4 byte alignment required */ struct compat_xfrm_lifetime_cur { compat_u64 bytes, packets, add_time, use_time; }; /* same size on 32bit, but only 4 byte alignment required */ struct compat_xfrm_userpolicy_info { struct xfrm_selector sel; struct compat_xfrm_lifetime_cfg lft; struct compat_xfrm_lifetime_cur curlft; __u32 priority, index; u8 dir, action, flags, share; /* 4 bytes additional padding on 64bit */ }; struct compat_xfrm_usersa_info { struct xfrm_selector sel; struct xfrm_id id; xfrm_address_t saddr; struct compat_xfrm_lifetime_cfg lft; struct compat_xfrm_lifetime_cur curlft; struct xfrm_stats stats; __u32 seq, reqid; u16 family; u8 mode, replay_window, flags; /* 4 bytes additional padding on 64bit */ }; struct compat_xfrm_user_acquire { struct xfrm_id id; xfrm_address_t saddr; struct xfrm_selector sel; struct compat_xfrm_userpolicy_info policy; /* 4 bytes additional padding on 64bit */ __u32 aalgos, ealgos, calgos, seq; }; struct compat_xfrm_userspi_info { struct compat_xfrm_usersa_info info; /* 4 bytes additional padding on 64bit */ __u32 min, max; }; struct compat_xfrm_user_expire { struct compat_xfrm_usersa_info state; /* 8 bytes additional padding on 64bit */ u8 hard; }; struct compat_xfrm_user_polexpire { struct compat_xfrm_userpolicy_info pol; /* 8 bytes additional padding on 64bit */ u8 hard; }; #define XMSGSIZE(type) sizeof(struct type) static const int compat_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info), [XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info), [XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userspi_info), [XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_acquire), [XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_expire), [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info), [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info), [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_polexpire), [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush), [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0, [XFRM_MSG_NEWAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), [XFRM_MSG_GETAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), [XFRM_MSG_REPORT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report), [XFRM_MSG_MIGRATE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_NEWSADINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_GETSADINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_MAPPING - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping) }; static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_UNSPEC] = { .strict_start_type = XFRMA_SA_DIR }, [XFRMA_SA] = { .len = XMSGSIZE(compat_xfrm_usersa_info)}, [XFRMA_POLICY] = { .len = XMSGSIZE(compat_xfrm_userpolicy_info)}, [XFRMA_LASTUSED] = { .type = NLA_U64}, [XFRMA_ALG_AUTH_TRUNC] = { .len = sizeof(struct xfrm_algo_auth)}, [XFRMA_ALG_AEAD] = { .len = sizeof(struct xfrm_algo_aead) }, [XFRMA_ALG_AUTH] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ALG_CRYPT] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) }, [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, [XFRMA_ETIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SRCADDR] = { .len = sizeof(xfrm_address_t) }, [XFRMA_COADDR] = { .len = sizeof(xfrm_address_t) }, [XFRMA_POLICY_TYPE] = { .len = sizeof(struct xfrm_userpolicy_type)}, [XFRMA_MIGRATE] = { .len = sizeof(struct xfrm_user_migrate) }, [XFRMA_KMADDRESS] = { .len = sizeof(struct xfrm_user_kmaddress) }, [XFRMA_MARK] = { .len = sizeof(struct xfrm_mark) }, [XFRMA_TFCPAD] = { .type = NLA_U32 }, [XFRMA_REPLAY_ESN_VAL] = { .len = sizeof(struct xfrm_replay_state_esn) }, [XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 }, [XFRMA_PROTO] = { .type = NLA_U8 }, [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, [XFRMA_SET_MARK] = { .type = NLA_U32 }, [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), [XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 }, }; static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src, u16 type) { int payload = compat_msg_min[type]; int src_len = xfrm_msg_min[type]; struct nlmsghdr *nlh_dst; /* Compat messages are shorter or equal to native (+padding) */ if (WARN_ON_ONCE(src_len < payload)) return ERR_PTR(-EMSGSIZE); nlh_dst = nlmsg_put(skb, nlh_src->nlmsg_pid, nlh_src->nlmsg_seq, nlh_src->nlmsg_type, payload, nlh_src->nlmsg_flags); if (!nlh_dst) return ERR_PTR(-EMSGSIZE); memset(nlmsg_data(nlh_dst), 0, payload); switch (nlh_src->nlmsg_type) { /* Compat message has the same layout as native */ case XFRM_MSG_DELSA: case XFRM_MSG_DELPOLICY: case XFRM_MSG_FLUSHSA: case XFRM_MSG_FLUSHPOLICY: case XFRM_MSG_NEWAE: case XFRM_MSG_REPORT: case XFRM_MSG_MIGRATE: case XFRM_MSG_NEWSADINFO: case XFRM_MSG_NEWSPDINFO: case XFRM_MSG_MAPPING: WARN_ON_ONCE(src_len != payload); memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), src_len); break; /* 4 byte alignment for trailing u64 on native, but not on compat */ case XFRM_MSG_NEWSA: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_UPDSA: case XFRM_MSG_UPDPOLICY: WARN_ON_ONCE(src_len != payload + 4); memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), payload); break; case XFRM_MSG_EXPIRE: { const struct xfrm_user_expire *src_ue = nlmsg_data(nlh_src); struct compat_xfrm_user_expire *dst_ue = nlmsg_data(nlh_dst); /* compat_xfrm_user_expire has 4-byte smaller state */ memcpy(dst_ue, src_ue, sizeof(dst_ue->state)); dst_ue->hard = src_ue->hard; break; } case XFRM_MSG_ACQUIRE: { const struct xfrm_user_acquire *src_ua = nlmsg_data(nlh_src); struct compat_xfrm_user_acquire *dst_ua = nlmsg_data(nlh_dst); memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos)); dst_ua->aalgos = src_ua->aalgos; dst_ua->ealgos = src_ua->ealgos; dst_ua->calgos = src_ua->calgos; dst_ua->seq = src_ua->seq; break; } case XFRM_MSG_POLEXPIRE: { const struct xfrm_user_polexpire *src_upe = nlmsg_data(nlh_src); struct compat_xfrm_user_polexpire *dst_upe = nlmsg_data(nlh_dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_upe, src_upe, sizeof(dst_upe->pol)); dst_upe->hard = src_upe->hard; break; } case XFRM_MSG_ALLOCSPI: { const struct xfrm_userspi_info *src_usi = nlmsg_data(nlh_src); struct compat_xfrm_userspi_info *dst_usi = nlmsg_data(nlh_dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_usi, src_usi, sizeof(src_usi->info)); dst_usi->min = src_usi->min; dst_usi->max = src_usi->max; break; } /* Not being sent by kernel */ case XFRM_MSG_GETSA: case XFRM_MSG_GETPOLICY: case XFRM_MSG_GETAE: case XFRM_MSG_GETSADINFO: case XFRM_MSG_GETSPDINFO: default: pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type); return ERR_PTR(-EOPNOTSUPP); } return nlh_dst; } static int xfrm_nla_cpy(struct sk_buff *dst, const struct nlattr *src, int len) { return nla_put(dst, src->nla_type, len, nla_data(src)); } static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) { switch (src->nla_type) { case XFRMA_PAD: /* Ignore */ return 0; case XFRMA_UNSPEC: case XFRMA_ALG_AUTH: case XFRMA_ALG_CRYPT: case XFRMA_ALG_COMP: case XFRMA_ENCAP: case XFRMA_TMPL: return xfrm_nla_cpy(dst, src, nla_len(src)); case XFRMA_SA: return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_usersa_info)); case XFRMA_POLICY: return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_userpolicy_info)); case XFRMA_SEC_CTX: return xfrm_nla_cpy(dst, src, nla_len(src)); case XFRMA_LTIME_VAL: return nla_put_64bit(dst, src->nla_type, nla_len(src), nla_data(src), XFRMA_PAD); case XFRMA_REPLAY_VAL: case XFRMA_REPLAY_THRESH: case XFRMA_ETIMER_THRESH: case XFRMA_SRCADDR: case XFRMA_COADDR: return xfrm_nla_cpy(dst, src, nla_len(src)); case XFRMA_LASTUSED: return nla_put_64bit(dst, src->nla_type, nla_len(src), nla_data(src), XFRMA_PAD); case XFRMA_POLICY_TYPE: case XFRMA_MIGRATE: case XFRMA_ALG_AEAD: case XFRMA_KMADDRESS: case XFRMA_ALG_AUTH_TRUNC: case XFRMA_MARK: case XFRMA_TFCPAD: case XFRMA_REPLAY_ESN_VAL: case XFRMA_SA_EXTRA_FLAGS: case XFRMA_PROTO: case XFRMA_ADDRESS_FILTER: case XFRMA_OFFLOAD_DEV: case XFRMA_SET_MARK: case XFRMA_SET_MARK_MASK: case XFRMA_IF_ID: case XFRMA_MTIMER_THRESH: case XFRMA_SA_DIR: case XFRMA_NAT_KEEPALIVE_INTERVAL: return xfrm_nla_cpy(dst, src, nla_len(src)); default: BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL); pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } } /* Take kernel-built (64bit layout) and create 32bit layout for userspace */ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) { u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE; const struct nlattr *nla, *attrs; struct nlmsghdr *nlh_dst; int len, remaining; nlh_dst = xfrm_nlmsg_put_compat(dst, nlh_src, type); if (IS_ERR(nlh_dst)) return PTR_ERR(nlh_dst); attrs = nlmsg_attrdata(nlh_src, xfrm_msg_min[type]); len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]); nla_for_each_attr(nla, attrs, len, remaining) { int err; switch (nlh_src->nlmsg_type) { case XFRM_MSG_NEWSPDINFO: err = xfrm_nla_cpy(dst, nla, nla_len(nla)); break; default: err = xfrm_xlate64_attr(dst, nla); break; } if (err) return err; } nlmsg_end(dst, nlh_dst); return 0; } static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src) { u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE; struct sk_buff *new = NULL; int err; if (type >= ARRAY_SIZE(xfrm_msg_min)) { pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type); return -EOPNOTSUPP; } if (skb_shinfo(skb)->frag_list == NULL) { new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC); if (!new) return -ENOMEM; skb_shinfo(skb)->frag_list = new; } err = xfrm_xlate64(skb_shinfo(skb)->frag_list, nlh_src); if (err) { if (new) { kfree_skb(new); skb_shinfo(skb)->frag_list = NULL; } return err; } return 0; } /* Calculates len of translated 64-bit message. */ static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src, struct nlattr *attrs[XFRMA_MAX + 1], int maxtype) { size_t len = nlmsg_len(src); switch (src->nlmsg_type) { case XFRM_MSG_NEWSA: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_ALLOCSPI: case XFRM_MSG_ACQUIRE: case XFRM_MSG_UPDPOLICY: case XFRM_MSG_UPDSA: len += 4; break; case XFRM_MSG_EXPIRE: case XFRM_MSG_POLEXPIRE: len += 8; break; case XFRM_MSG_NEWSPDINFO: /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ return len; default: break; } /* Unexpected for anything, but XFRM_MSG_NEWSPDINFO, please * correct both 64=>32-bit and 32=>64-bit translators to copy * new attributes. */ if (WARN_ON_ONCE(maxtype)) return len; if (attrs[XFRMA_SA]) len += 4; if (attrs[XFRMA_POLICY]) len += 4; /* XXX: some attrs may need to be realigned * if !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */ return len; } static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src, size_t size, int copy_len, int payload) { struct nlmsghdr *nlmsg = dst; struct nlattr *nla; /* xfrm_user_rcv_msg_compat() relies on fact that 32-bit messages * have the same len or shorted than 64-bit ones. * 32-bit translation that is bigger than 64-bit original is unexpected. */ if (WARN_ON_ONCE(copy_len > payload)) copy_len = payload; if (size - *pos < nla_attr_size(payload)) return -ENOBUFS; nla = dst + *pos; memcpy(nla, src, nla_attr_size(copy_len)); nla->nla_len = nla_attr_size(payload); *pos += nla_attr_size(copy_len); nlmsg->nlmsg_len += nla->nla_len; memset(dst + *pos, 0, payload - copy_len); *pos += payload - copy_len; return 0; } static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, size_t *pos, size_t size, struct netlink_ext_ack *extack) { int type = nla_type(nla); u16 pol_len32, pol_len64; int err; if (type > XFRMA_MAX) { BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL); NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } type = array_index_nospec(type, XFRMA_MAX + 1); if (nla_len(nla) < compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; } pol_len32 = compat_policy[type].len; pol_len64 = xfrma_policy[type].len; /* XFRMA_SA and XFRMA_POLICY - need to know how-to translate */ if (pol_len32 != pol_len64) { if (nla_len(nla) != compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; } err = xfrm_attr_cpy32(dst, pos, nla, size, pol_len32, pol_len64); if (err) return err; } return xfrm_attr_cpy32(dst, pos, nla, size, nla_len(nla), nla_len(nla)); } static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src, struct nlattr *attrs[XFRMA_MAX+1], size_t size, u8 type, int maxtype, struct netlink_ext_ack *extack) { size_t pos; int i; memcpy(dst, src, NLMSG_HDRLEN); dst->nlmsg_len = NLMSG_HDRLEN + xfrm_msg_min[type]; memset(nlmsg_data(dst), 0, xfrm_msg_min[type]); switch (src->nlmsg_type) { /* Compat message has the same layout as native */ case XFRM_MSG_DELSA: case XFRM_MSG_GETSA: case XFRM_MSG_DELPOLICY: case XFRM_MSG_GETPOLICY: case XFRM_MSG_FLUSHSA: case XFRM_MSG_FLUSHPOLICY: case XFRM_MSG_NEWAE: case XFRM_MSG_GETAE: case XFRM_MSG_REPORT: case XFRM_MSG_MIGRATE: case XFRM_MSG_NEWSADINFO: case XFRM_MSG_GETSADINFO: case XFRM_MSG_NEWSPDINFO: case XFRM_MSG_GETSPDINFO: case XFRM_MSG_MAPPING: memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]); break; /* 4 byte alignment for trailing u64 on native, but not on compat */ case XFRM_MSG_NEWSA: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_UPDSA: case XFRM_MSG_UPDPOLICY: memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]); break; case XFRM_MSG_EXPIRE: { const struct compat_xfrm_user_expire *src_ue = nlmsg_data(src); struct xfrm_user_expire *dst_ue = nlmsg_data(dst); /* compat_xfrm_user_expire has 4-byte smaller state */ memcpy(dst_ue, src_ue, sizeof(src_ue->state)); dst_ue->hard = src_ue->hard; break; } case XFRM_MSG_ACQUIRE: { const struct compat_xfrm_user_acquire *src_ua = nlmsg_data(src); struct xfrm_user_acquire *dst_ua = nlmsg_data(dst); memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos)); dst_ua->aalgos = src_ua->aalgos; dst_ua->ealgos = src_ua->ealgos; dst_ua->calgos = src_ua->calgos; dst_ua->seq = src_ua->seq; break; } case XFRM_MSG_POLEXPIRE: { const struct compat_xfrm_user_polexpire *src_upe = nlmsg_data(src); struct xfrm_user_polexpire *dst_upe = nlmsg_data(dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_upe, src_upe, sizeof(src_upe->pol)); dst_upe->hard = src_upe->hard; break; } case XFRM_MSG_ALLOCSPI: { const struct compat_xfrm_userspi_info *src_usi = nlmsg_data(src); struct xfrm_userspi_info *dst_usi = nlmsg_data(dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_usi, src_usi, sizeof(src_usi->info)); dst_usi->min = src_usi->min; dst_usi->max = src_usi->max; break; } default: NL_SET_ERR_MSG(extack, "Unsupported message type"); return -EOPNOTSUPP; } pos = dst->nlmsg_len; if (maxtype) { /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ WARN_ON_ONCE(src->nlmsg_type != XFRM_MSG_NEWSPDINFO); for (i = 1; i <= maxtype; i++) { int err; if (!attrs[i]) continue; /* just copy - no need for translation */ err = xfrm_attr_cpy32(dst, &pos, attrs[i], size, nla_len(attrs[i]), nla_len(attrs[i])); if (err) return err; } return 0; } for (i = 1; i < XFRMA_MAX + 1; i++) { int err; if (i == XFRMA_PAD) continue; if (!attrs[i]) continue; err = xfrm_xlate32_attr(dst, attrs[i], &pos, size, extack); if (err) return err; } return 0; } static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { /* netlink_rcv_skb() checks if a message has full (struct nlmsghdr) */ u16 type = h32->nlmsg_type - XFRM_MSG_BASE; struct nlattr *attrs[XFRMA_MAX+1]; struct nlmsghdr *h64; size_t len; int err; BUILD_BUG_ON(ARRAY_SIZE(xfrm_msg_min) != ARRAY_SIZE(compat_msg_min)); if (type >= ARRAY_SIZE(xfrm_msg_min)) return ERR_PTR(-EINVAL); /* Don't call parse: the message might have only nlmsg header */ if ((h32->nlmsg_type == XFRM_MSG_GETSA || h32->nlmsg_type == XFRM_MSG_GETPOLICY) && (h32->nlmsg_flags & NLM_F_DUMP)) return NULL; err = nlmsg_parse_deprecated(h32, compat_msg_min[type], attrs, maxtype ? : XFRMA_MAX, policy ? : compat_policy, extack); if (err < 0) return ERR_PTR(err); len = xfrm_user_rcv_calculate_len64(h32, attrs, maxtype); /* The message doesn't need translation */ if (len == nlmsg_len(h32)) return NULL; len += NLMSG_HDRLEN; h64 = kvmalloc(len, GFP_KERNEL); if (!h64) return ERR_PTR(-ENOMEM); err = xfrm_xlate32(h64, h32, attrs, len, type, maxtype, extack); if (err < 0) { kvfree(h64); return ERR_PTR(err); } return h64; } static int xfrm_user_policy_compat(u8 **pdata32, int optlen) { struct compat_xfrm_userpolicy_info *p = (void *)*pdata32; u8 *src_templates, *dst_templates; u8 *data64; if (optlen < sizeof(*p)) return -EINVAL; data64 = kmalloc_track_caller(optlen + 4, GFP_USER | __GFP_NOWARN); if (!data64) return -ENOMEM; memcpy(data64, *pdata32, sizeof(*p)); memset(data64 + sizeof(*p), 0, 4); src_templates = *pdata32 + sizeof(*p); dst_templates = data64 + sizeof(*p) + 4; memcpy(dst_templates, src_templates, optlen - sizeof(*p)); kfree(*pdata32); *pdata32 = data64; return 0; } static struct xfrm_translator xfrm_translator = { .owner = THIS_MODULE, .alloc_compat = xfrm_alloc_compat, .rcv_msg_compat = xfrm_user_rcv_msg_compat, .xlate_user_policy_sockptr = xfrm_user_policy_compat, }; static int __init xfrm_compat_init(void) { return xfrm_register_translator(&xfrm_translator); } static void __exit xfrm_compat_exit(void) { xfrm_unregister_translator(&xfrm_translator); } module_init(xfrm_compat_init); module_exit(xfrm_compat_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Dmitry Safonov"); MODULE_DESCRIPTION("XFRM 32-bit compatibility layer"); |
| 1 1 3 3 9 8 8 7 6 5 4 4 1 3 1 9 10 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Crypto operations using stored keys * * Copyright (c) 2016, Intel Corporation */ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/scatterlist.h> #include <linux/crypto.h> #include <crypto/hash.h> #include <crypto/kpp.h> #include <crypto/dh.h> #include <crypto/kdf_sp800108.h> #include <keys/user-type.h> #include "internal.h" static ssize_t dh_data_from_key(key_serial_t keyid, const void **data) { struct key *key; key_ref_t key_ref; long status; ssize_t ret; key_ref = lookup_user_key(keyid, 0, KEY_NEED_READ); if (IS_ERR(key_ref)) { ret = -ENOKEY; goto error; } key = key_ref_to_ptr(key_ref); ret = -EOPNOTSUPP; if (key->type == &key_type_user) { down_read(&key->sem); status = key_validate(key); if (status == 0) { const struct user_key_payload *payload; uint8_t *duplicate; payload = user_key_payload_locked(key); duplicate = kmemdup(payload->data, payload->datalen, GFP_KERNEL); if (duplicate) { *data = duplicate; ret = payload->datalen; } else { ret = -ENOMEM; } } up_read(&key->sem); } key_put(key); error: return ret; } static void dh_free_data(struct dh *dh) { kfree_sensitive(dh->key); kfree_sensitive(dh->p); kfree_sensitive(dh->g); } static int kdf_alloc(struct crypto_shash **hash, char *hashname) { struct crypto_shash *tfm; /* allocate synchronous hash */ tfm = crypto_alloc_shash(hashname, 0, 0); if (IS_ERR(tfm)) { pr_info("could not allocate digest TFM handle %s\n", hashname); return PTR_ERR(tfm); } if (crypto_shash_digestsize(tfm) == 0) { crypto_free_shash(tfm); return -EINVAL; } *hash = tfm; return 0; } static void kdf_dealloc(struct crypto_shash *hash) { if (hash) crypto_free_shash(hash); } static int keyctl_dh_compute_kdf(struct crypto_shash *hash, char __user *buffer, size_t buflen, uint8_t *kbuf, size_t kbuflen) { struct kvec kbuf_iov = { .iov_base = kbuf, .iov_len = kbuflen }; uint8_t *outbuf = NULL; int ret; size_t outbuf_len = roundup(buflen, crypto_shash_digestsize(hash)); outbuf = kmalloc(outbuf_len, GFP_KERNEL); if (!outbuf) { ret = -ENOMEM; goto err; } ret = crypto_kdf108_ctr_generate(hash, &kbuf_iov, 1, outbuf, outbuf_len); if (ret) goto err; ret = buflen; if (copy_to_user(buffer, outbuf, buflen) != 0) ret = -EFAULT; err: kfree_sensitive(outbuf); return ret; } long __keyctl_dh_compute(struct keyctl_dh_params __user *params, char __user *buffer, size_t buflen, struct keyctl_kdf_params *kdfcopy) { long ret; ssize_t dlen; int secretlen; int outlen; struct keyctl_dh_params pcopy; struct dh dh_inputs; struct scatterlist outsg; DECLARE_CRYPTO_WAIT(compl); struct crypto_kpp *tfm; struct kpp_request *req; uint8_t *secret; uint8_t *outbuf; struct crypto_shash *hash = NULL; if (!params || (!buffer && buflen)) { ret = -EINVAL; goto out1; } if (copy_from_user(&pcopy, params, sizeof(pcopy)) != 0) { ret = -EFAULT; goto out1; } if (kdfcopy) { char *hashname; if (memchr_inv(kdfcopy->__spare, 0, sizeof(kdfcopy->__spare))) { ret = -EINVAL; goto out1; } if (buflen > KEYCTL_KDF_MAX_OUTPUT_LEN || kdfcopy->otherinfolen > KEYCTL_KDF_MAX_OI_LEN) { ret = -EMSGSIZE; goto out1; } /* get KDF name string */ hashname = strndup_user(kdfcopy->hashname, CRYPTO_MAX_ALG_NAME); if (IS_ERR(hashname)) { ret = PTR_ERR(hashname); goto out1; } /* allocate KDF from the kernel crypto API */ ret = kdf_alloc(&hash, hashname); kfree(hashname); if (ret) goto out1; } memset(&dh_inputs, 0, sizeof(dh_inputs)); dlen = dh_data_from_key(pcopy.prime, &dh_inputs.p); if (dlen < 0) { ret = dlen; goto out1; } dh_inputs.p_size = dlen; dlen = dh_data_from_key(pcopy.base, &dh_inputs.g); if (dlen < 0) { ret = dlen; goto out2; } dh_inputs.g_size = dlen; dlen = dh_data_from_key(pcopy.private, &dh_inputs.key); if (dlen < 0) { ret = dlen; goto out2; } dh_inputs.key_size = dlen; secretlen = crypto_dh_key_len(&dh_inputs); secret = kmalloc(secretlen, GFP_KERNEL); if (!secret) { ret = -ENOMEM; goto out2; } ret = crypto_dh_encode_key(secret, secretlen, &dh_inputs); if (ret) goto out3; tfm = crypto_alloc_kpp("dh", 0, 0); if (IS_ERR(tfm)) { ret = PTR_ERR(tfm); goto out3; } ret = crypto_kpp_set_secret(tfm, secret, secretlen); if (ret) goto out4; outlen = crypto_kpp_maxsize(tfm); if (!kdfcopy) { /* * When not using a KDF, buflen 0 is used to read the * required buffer length */ if (buflen == 0) { ret = outlen; goto out4; } else if (outlen > buflen) { ret = -EOVERFLOW; goto out4; } } outbuf = kzalloc(kdfcopy ? (outlen + kdfcopy->otherinfolen) : outlen, GFP_KERNEL); if (!outbuf) { ret = -ENOMEM; goto out4; } sg_init_one(&outsg, outbuf, outlen); req = kpp_request_alloc(tfm, GFP_KERNEL); if (!req) { ret = -ENOMEM; goto out5; } kpp_request_set_input(req, NULL, 0); kpp_request_set_output(req, &outsg, outlen); kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &compl); /* * For DH, generate_public_key and generate_shared_secret are * the same calculation */ ret = crypto_kpp_generate_public_key(req); ret = crypto_wait_req(ret, &compl); if (ret) goto out6; if (kdfcopy) { /* * Concatenate SP800-56A otherinfo past DH shared secret -- the * input to the KDF is (DH shared secret || otherinfo) */ if (copy_from_user(outbuf + req->dst_len, kdfcopy->otherinfo, kdfcopy->otherinfolen) != 0) { ret = -EFAULT; goto out6; } ret = keyctl_dh_compute_kdf(hash, buffer, buflen, outbuf, req->dst_len + kdfcopy->otherinfolen); } else if (copy_to_user(buffer, outbuf, req->dst_len) == 0) { ret = req->dst_len; } else { ret = -EFAULT; } out6: kpp_request_free(req); out5: kfree_sensitive(outbuf); out4: crypto_free_kpp(tfm); out3: kfree_sensitive(secret); out2: dh_free_data(&dh_inputs); out1: kdf_dealloc(hash); return ret; } long keyctl_dh_compute(struct keyctl_dh_params __user *params, char __user *buffer, size_t buflen, struct keyctl_kdf_params __user *kdf) { struct keyctl_kdf_params kdfcopy; if (!kdf) return __keyctl_dh_compute(params, buffer, buflen, NULL); if (copy_from_user(&kdfcopy, kdf, sizeof(kdfcopy)) != 0) return -EFAULT; return __keyctl_dh_compute(params, buffer, buflen, &kdfcopy); } |
| 3345 3341 3336 3325 3332 3333 3324 929 934 3157 3154 925 946 3182 1437 1445 3181 3158 1444 1435 1424 1428 1433 1429 1445 1433 1445 3155 3183 3153 3157 3184 68 68 53 54 53 54 69 69 68 69 69 69 69 69 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/debugfs.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/memblock.h> #include <linux/stacktrace.h> #include <linux/page_owner.h> #include <linux/jump_label.h> #include <linux/migrate.h> #include <linux/stackdepot.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> #include <linux/sched/clock.h> #include "internal.h" /* * TODO: teach PAGE_OWNER_STACK_DEPTH (__dump_page_owner and save_stack) * to use off stack temporal storage */ #define PAGE_OWNER_STACK_DEPTH (16) struct page_owner { unsigned short order; short last_migrate_reason; gfp_t gfp_mask; depot_stack_handle_t handle; depot_stack_handle_t free_handle; u64 ts_nsec; u64 free_ts_nsec; char comm[TASK_COMM_LEN]; pid_t pid; pid_t tgid; pid_t free_pid; pid_t free_tgid; }; struct stack { struct stack_record *stack_record; struct stack *next; }; static struct stack dummy_stack; static struct stack failure_stack; static struct stack *stack_list; static DEFINE_SPINLOCK(stack_list_lock); static bool page_owner_enabled __initdata; DEFINE_STATIC_KEY_FALSE(page_owner_inited); static depot_stack_handle_t dummy_handle; static depot_stack_handle_t failure_handle; static depot_stack_handle_t early_handle; static void init_early_allocated_pages(void); static inline void set_current_in_page_owner(void) { /* * Avoid recursion. * * We might need to allocate more memory from page_owner code, so make * sure to signal it in order to avoid recursion. */ current->in_page_owner = 1; } static inline void unset_current_in_page_owner(void) { current->in_page_owner = 0; } static int __init early_page_owner_param(char *buf) { int ret = kstrtobool(buf, &page_owner_enabled); if (page_owner_enabled) stack_depot_request_early_init(); return ret; } early_param("page_owner", early_page_owner_param); static __init bool need_page_owner(void) { return page_owner_enabled; } static __always_inline depot_stack_handle_t create_dummy_stack(void) { unsigned long entries[4]; unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); return stack_depot_save(entries, nr_entries, GFP_KERNEL); } static noinline void register_dummy_stack(void) { dummy_handle = create_dummy_stack(); } static noinline void register_failure_stack(void) { failure_handle = create_dummy_stack(); } static noinline void register_early_stack(void) { early_handle = create_dummy_stack(); } static __init void init_page_owner(void) { if (!page_owner_enabled) return; register_dummy_stack(); register_failure_stack(); register_early_stack(); init_early_allocated_pages(); /* Initialize dummy and failure stacks and link them to stack_list */ dummy_stack.stack_record = __stack_depot_get_stack_record(dummy_handle); failure_stack.stack_record = __stack_depot_get_stack_record(failure_handle); if (dummy_stack.stack_record) refcount_set(&dummy_stack.stack_record->count, 1); if (failure_stack.stack_record) refcount_set(&failure_stack.stack_record->count, 1); dummy_stack.next = &failure_stack; stack_list = &dummy_stack; static_branch_enable(&page_owner_inited); } struct page_ext_operations page_owner_ops = { .size = sizeof(struct page_owner), .need = need_page_owner, .init = init_page_owner, .need_shared_flags = true, }; static inline struct page_owner *get_page_owner(struct page_ext *page_ext) { return page_ext_data(page_ext, &page_owner_ops); } static noinline depot_stack_handle_t save_stack(gfp_t flags) { unsigned long entries[PAGE_OWNER_STACK_DEPTH]; depot_stack_handle_t handle; unsigned int nr_entries; if (current->in_page_owner) return dummy_handle; set_current_in_page_owner(); nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2); handle = stack_depot_save(entries, nr_entries, flags); if (!handle) handle = failure_handle; unset_current_in_page_owner(); return handle; } static void add_stack_record_to_list(struct stack_record *stack_record, gfp_t gfp_mask) { unsigned long flags; struct stack *stack; set_current_in_page_owner(); stack = kmalloc(sizeof(*stack), gfp_nested_mask(gfp_mask)); if (!stack) { unset_current_in_page_owner(); return; } unset_current_in_page_owner(); stack->stack_record = stack_record; stack->next = NULL; spin_lock_irqsave(&stack_list_lock, flags); stack->next = stack_list; /* * This pairs with smp_load_acquire() from function * stack_start(). This guarantees that stack_start() * will see an updated stack_list before starting to * traverse the list. */ smp_store_release(&stack_list, stack); spin_unlock_irqrestore(&stack_list_lock, flags); } static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask, int nr_base_pages) { struct stack_record *stack_record = __stack_depot_get_stack_record(handle); if (!stack_record) return; /* * New stack_record's that do not use STACK_DEPOT_FLAG_GET start * with REFCOUNT_SATURATED to catch spurious increments of their * refcount. * Since we do not use STACK_DEPOT_FLAG_GET API, let us * set a refcount of 1 ourselves. */ if (refcount_read(&stack_record->count) == REFCOUNT_SATURATED) { int old = REFCOUNT_SATURATED; if (atomic_try_cmpxchg_relaxed(&stack_record->count.refs, &old, 1)) /* Add the new stack_record to our list */ add_stack_record_to_list(stack_record, gfp_mask); } refcount_add(nr_base_pages, &stack_record->count); } static void dec_stack_record_count(depot_stack_handle_t handle, int nr_base_pages) { struct stack_record *stack_record = __stack_depot_get_stack_record(handle); if (!stack_record) return; if (refcount_sub_and_test(nr_base_pages, &stack_record->count)) pr_warn("%s: refcount went to 0 for %u handle\n", __func__, handle); } static inline void __update_page_owner_handle(struct page_ext *page_ext, depot_stack_handle_t handle, unsigned short order, gfp_t gfp_mask, short last_migrate_reason, u64 ts_nsec, pid_t pid, pid_t tgid, char *comm) { int i; struct page_owner *page_owner; for (i = 0; i < (1 << order); i++) { page_owner = get_page_owner(page_ext); page_owner->handle = handle; page_owner->order = order; page_owner->gfp_mask = gfp_mask; page_owner->last_migrate_reason = last_migrate_reason; page_owner->pid = pid; page_owner->tgid = tgid; page_owner->ts_nsec = ts_nsec; strscpy(page_owner->comm, comm, sizeof(page_owner->comm)); __set_bit(PAGE_EXT_OWNER, &page_ext->flags); __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); page_ext = page_ext_next(page_ext); } } static inline void __update_page_owner_free_handle(struct page_ext *page_ext, depot_stack_handle_t handle, unsigned short order, pid_t pid, pid_t tgid, u64 free_ts_nsec) { int i; struct page_owner *page_owner; for (i = 0; i < (1 << order); i++) { page_owner = get_page_owner(page_ext); /* Only __reset_page_owner() wants to clear the bit */ if (handle) { __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); page_owner->free_handle = handle; } page_owner->free_ts_nsec = free_ts_nsec; page_owner->free_pid = current->pid; page_owner->free_tgid = current->tgid; page_ext = page_ext_next(page_ext); } } void __reset_page_owner(struct page *page, unsigned short order) { struct page_ext *page_ext; depot_stack_handle_t handle; depot_stack_handle_t alloc_handle; struct page_owner *page_owner; u64 free_ts_nsec = local_clock(); page_ext = page_ext_get(page); if (unlikely(!page_ext)) return; page_owner = get_page_owner(page_ext); alloc_handle = page_owner->handle; handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); __update_page_owner_free_handle(page_ext, handle, order, current->pid, current->tgid, free_ts_nsec); page_ext_put(page_ext); if (alloc_handle != early_handle) /* * early_handle is being set as a handle for all those * early allocated pages. See init_pages_in_zone(). * Since their refcount is not being incremented because * the machinery is not ready yet, we cannot decrement * their refcount either. */ dec_stack_record_count(alloc_handle, 1 << order); } noinline void __set_page_owner(struct page *page, unsigned short order, gfp_t gfp_mask) { struct page_ext *page_ext; u64 ts_nsec = local_clock(); depot_stack_handle_t handle; handle = save_stack(gfp_mask); page_ext = page_ext_get(page); if (unlikely(!page_ext)) return; __update_page_owner_handle(page_ext, handle, order, gfp_mask, -1, ts_nsec, current->pid, current->tgid, current->comm); page_ext_put(page_ext); inc_stack_record_count(handle, gfp_mask, 1 << order); } void __set_page_owner_migrate_reason(struct page *page, int reason) { struct page_ext *page_ext = page_ext_get(page); struct page_owner *page_owner; if (unlikely(!page_ext)) return; page_owner = get_page_owner(page_ext); page_owner->last_migrate_reason = reason; page_ext_put(page_ext); } void __split_page_owner(struct page *page, int old_order, int new_order) { int i; struct page_ext *page_ext = page_ext_get(page); struct page_owner *page_owner; if (unlikely(!page_ext)) return; for (i = 0; i < (1 << old_order); i++) { page_owner = get_page_owner(page_ext); page_owner->order = new_order; page_ext = page_ext_next(page_ext); } page_ext_put(page_ext); } void __folio_copy_owner(struct folio *newfolio, struct folio *old) { int i; struct page_ext *old_ext; struct page_ext *new_ext; struct page_owner *old_page_owner; struct page_owner *new_page_owner; depot_stack_handle_t migrate_handle; old_ext = page_ext_get(&old->page); if (unlikely(!old_ext)) return; new_ext = page_ext_get(&newfolio->page); if (unlikely(!new_ext)) { page_ext_put(old_ext); return; } old_page_owner = get_page_owner(old_ext); new_page_owner = get_page_owner(new_ext); migrate_handle = new_page_owner->handle; __update_page_owner_handle(new_ext, old_page_owner->handle, old_page_owner->order, old_page_owner->gfp_mask, old_page_owner->last_migrate_reason, old_page_owner->ts_nsec, old_page_owner->pid, old_page_owner->tgid, old_page_owner->comm); /* * Do not proactively clear PAGE_EXT_OWNER{_ALLOCATED} bits as the folio * will be freed after migration. Keep them until then as they may be * useful. */ __update_page_owner_free_handle(new_ext, 0, old_page_owner->order, old_page_owner->free_pid, old_page_owner->free_tgid, old_page_owner->free_ts_nsec); /* * We linked the original stack to the new folio, we need to do the same * for the new one and the old folio otherwise there will be an imbalance * when subtracting those pages from the stack. */ for (i = 0; i < (1 << new_page_owner->order); i++) { old_page_owner->handle = migrate_handle; old_ext = page_ext_next(old_ext); old_page_owner = get_page_owner(old_ext); } page_ext_put(new_ext); page_ext_put(old_ext); } void pagetypeinfo_showmixedcount_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { struct page *page; struct page_ext *page_ext; struct page_owner *page_owner; unsigned long pfn, block_end_pfn; unsigned long end_pfn = zone_end_pfn(zone); unsigned long count[MIGRATE_TYPES] = { 0, }; int pageblock_mt, page_mt; int i; /* Scan block by block. First and last block may be incomplete */ pfn = zone->zone_start_pfn; /* * Walk the zone in pageblock_nr_pages steps. If a page block spans * a zone boundary, it will be double counted between zones. This does * not matter as the mixed block count will still be correct */ for (; pfn < end_pfn; ) { page = pfn_to_online_page(pfn); if (!page) { pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); continue; } block_end_pfn = pageblock_end_pfn(pfn); block_end_pfn = min(block_end_pfn, end_pfn); pageblock_mt = get_pageblock_migratetype(page); for (; pfn < block_end_pfn; pfn++) { /* The pageblock is online, no need to recheck. */ page = pfn_to_page(pfn); if (page_zone(page) != zone) continue; if (PageBuddy(page)) { unsigned long freepage_order; freepage_order = buddy_order_unsafe(page); if (freepage_order <= MAX_PAGE_ORDER) pfn += (1UL << freepage_order) - 1; continue; } if (PageReserved(page)) continue; page_ext = page_ext_get(page); if (unlikely(!page_ext)) continue; if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) goto ext_put_continue; page_owner = get_page_owner(page_ext); page_mt = gfp_migratetype(page_owner->gfp_mask); if (pageblock_mt != page_mt) { if (is_migrate_cma(pageblock_mt)) count[MIGRATE_MOVABLE]++; else count[pageblock_mt]++; pfn = block_end_pfn; page_ext_put(page_ext); break; } pfn += (1UL << page_owner->order) - 1; ext_put_continue: page_ext_put(page_ext); } } /* Print counts */ seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); for (i = 0; i < MIGRATE_TYPES; i++) seq_printf(m, "%12lu ", count[i]); seq_putc(m, '\n'); } /* * Looking for memcg information and print it out */ static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret, struct page *page) { #ifdef CONFIG_MEMCG unsigned long memcg_data; struct mem_cgroup *memcg; bool online; char name[80]; rcu_read_lock(); memcg_data = READ_ONCE(page->memcg_data); if (!memcg_data) goto out_unlock; if (memcg_data & MEMCG_DATA_OBJEXTS) ret += scnprintf(kbuf + ret, count - ret, "Slab cache page\n"); memcg = page_memcg_check(page); if (!memcg) goto out_unlock; online = (memcg->css.flags & CSS_ONLINE); cgroup_name(memcg->css.cgroup, name, sizeof(name)); ret += scnprintf(kbuf + ret, count - ret, "Charged %sto %smemcg %s\n", PageMemcgKmem(page) ? "(via objcg) " : "", online ? "" : "offline ", name); out_unlock: rcu_read_unlock(); #endif /* CONFIG_MEMCG */ return ret; } static ssize_t print_page_owner(char __user *buf, size_t count, unsigned long pfn, struct page *page, struct page_owner *page_owner, depot_stack_handle_t handle) { int ret, pageblock_mt, page_mt; char *kbuf; count = min_t(size_t, count, PAGE_SIZE); kbuf = kmalloc(count, GFP_KERNEL); if (!kbuf) return -ENOMEM; ret = scnprintf(kbuf, count, "Page allocated via order %u, mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu ns\n", page_owner->order, page_owner->gfp_mask, &page_owner->gfp_mask, page_owner->pid, page_owner->tgid, page_owner->comm, page_owner->ts_nsec); /* Print information relevant to grouping pages by mobility */ pageblock_mt = get_pageblock_migratetype(page); page_mt = gfp_migratetype(page_owner->gfp_mask); ret += scnprintf(kbuf + ret, count - ret, "PFN 0x%lx type %s Block %lu type %s Flags %pGp\n", pfn, migratetype_names[page_mt], pfn >> pageblock_order, migratetype_names[pageblock_mt], &page->flags); ret += stack_depot_snprint(handle, kbuf + ret, count - ret, 0); if (ret >= count) goto err; if (page_owner->last_migrate_reason != -1) { ret += scnprintf(kbuf + ret, count - ret, "Page has been migrated, last migrate reason: %s\n", migrate_reason_names[page_owner->last_migrate_reason]); } ret = print_page_owner_memcg(kbuf, count, ret, page); ret += snprintf(kbuf + ret, count - ret, "\n"); if (ret >= count) goto err; if (copy_to_user(buf, kbuf, ret)) ret = -EFAULT; kfree(kbuf); return ret; err: kfree(kbuf); return -ENOMEM; } void __dump_page_owner(const struct page *page) { struct page_ext *page_ext = page_ext_get((void *)page); struct page_owner *page_owner; depot_stack_handle_t handle; gfp_t gfp_mask; int mt; if (unlikely(!page_ext)) { pr_alert("There is not page extension available.\n"); return; } page_owner = get_page_owner(page_ext); gfp_mask = page_owner->gfp_mask; mt = gfp_migratetype(gfp_mask); if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) { pr_alert("page_owner info is not present (never set?)\n"); page_ext_put(page_ext); return; } if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) pr_alert("page_owner tracks the page as allocated\n"); else pr_alert("page_owner tracks the page as freed\n"); pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu, free_ts %llu\n", page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask, page_owner->pid, page_owner->tgid, page_owner->comm, page_owner->ts_nsec, page_owner->free_ts_nsec); handle = READ_ONCE(page_owner->handle); if (!handle) pr_alert("page_owner allocation stack trace missing\n"); else stack_depot_print(handle); handle = READ_ONCE(page_owner->free_handle); if (!handle) { pr_alert("page_owner free stack trace missing\n"); } else { pr_alert("page last free pid %d tgid %d stack trace:\n", page_owner->free_pid, page_owner->free_tgid); stack_depot_print(handle); } if (page_owner->last_migrate_reason != -1) pr_alert("page has been migrated, last migrate reason: %s\n", migrate_reason_names[page_owner->last_migrate_reason]); page_ext_put(page_ext); } static ssize_t read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) { unsigned long pfn; struct page *page; struct page_ext *page_ext; struct page_owner *page_owner; depot_stack_handle_t handle; if (!static_branch_unlikely(&page_owner_inited)) return -EINVAL; page = NULL; if (*ppos == 0) pfn = min_low_pfn; else pfn = *ppos; /* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */ while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) pfn++; /* Find an allocated page */ for (; pfn < max_pfn; pfn++) { /* * This temporary page_owner is required so * that we can avoid the context switches while holding * the rcu lock and copying the page owner information to * user through copy_to_user() or GFP_KERNEL allocations. */ struct page_owner page_owner_tmp; /* * If the new page is in a new MAX_ORDER_NR_PAGES area, * validate the area as existing, skip it if not */ if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) { pfn += MAX_ORDER_NR_PAGES - 1; continue; } page = pfn_to_page(pfn); if (PageBuddy(page)) { unsigned long freepage_order = buddy_order_unsafe(page); if (freepage_order <= MAX_PAGE_ORDER) pfn += (1UL << freepage_order) - 1; continue; } page_ext = page_ext_get(page); if (unlikely(!page_ext)) continue; /* * Some pages could be missed by concurrent allocation or free, * because we don't hold the zone lock. */ if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) goto ext_put_continue; /* * Although we do have the info about past allocation of free * pages, it's not relevant for current memory usage. */ if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) goto ext_put_continue; page_owner = get_page_owner(page_ext); /* * Don't print "tail" pages of high-order allocations as that * would inflate the stats. */ if (!IS_ALIGNED(pfn, 1 << page_owner->order)) goto ext_put_continue; /* * Access to page_ext->handle isn't synchronous so we should * be careful to access it. */ handle = READ_ONCE(page_owner->handle); if (!handle) goto ext_put_continue; /* Record the next PFN to read in the file offset */ *ppos = pfn + 1; page_owner_tmp = *page_owner; page_ext_put(page_ext); return print_page_owner(buf, count, pfn, page, &page_owner_tmp, handle); ext_put_continue: page_ext_put(page_ext); } return 0; } static loff_t lseek_page_owner(struct file *file, loff_t offset, int orig) { switch (orig) { case SEEK_SET: file->f_pos = offset; break; case SEEK_CUR: file->f_pos += offset; break; default: return -EINVAL; } return file->f_pos; } static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) { unsigned long pfn = zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(zone); unsigned long count = 0; /* * Walk the zone in pageblock_nr_pages steps. If a page block spans * a zone boundary, it will be double counted between zones. This does * not matter as the mixed block count will still be correct */ for (; pfn < end_pfn; ) { unsigned long block_end_pfn; if (!pfn_valid(pfn)) { pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); continue; } block_end_pfn = pageblock_end_pfn(pfn); block_end_pfn = min(block_end_pfn, end_pfn); for (; pfn < block_end_pfn; pfn++) { struct page *page = pfn_to_page(pfn); struct page_ext *page_ext; if (page_zone(page) != zone) continue; /* * To avoid having to grab zone->lock, be a little * careful when reading buddy page order. The only * danger is that we skip too much and potentially miss * some early allocated pages, which is better than * heavy lock contention. */ if (PageBuddy(page)) { unsigned long order = buddy_order_unsafe(page); if (order > 0 && order <= MAX_PAGE_ORDER) pfn += (1UL << order) - 1; continue; } if (PageReserved(page)) continue; page_ext = page_ext_get(page); if (unlikely(!page_ext)) continue; /* Maybe overlapping zone */ if (test_bit(PAGE_EXT_OWNER, &page_ext->flags)) goto ext_put_continue; /* Found early allocated page */ __update_page_owner_handle(page_ext, early_handle, 0, 0, -1, local_clock(), current->pid, current->tgid, current->comm); count++; ext_put_continue: page_ext_put(page_ext); } cond_resched(); } pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n", pgdat->node_id, zone->name, count); } static void init_zones_in_node(pg_data_t *pgdat) { struct zone *zone; struct zone *node_zones = pgdat->node_zones; for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { if (!populated_zone(zone)) continue; init_pages_in_zone(pgdat, zone); } } static void init_early_allocated_pages(void) { pg_data_t *pgdat; for_each_online_pgdat(pgdat) init_zones_in_node(pgdat); } static const struct file_operations proc_page_owner_operations = { .read = read_page_owner, .llseek = lseek_page_owner, }; static void *stack_start(struct seq_file *m, loff_t *ppos) { struct stack *stack; if (*ppos == -1UL) return NULL; if (!*ppos) { /* * This pairs with smp_store_release() from function * add_stack_record_to_list(), so we get a consistent * value of stack_list. */ stack = smp_load_acquire(&stack_list); m->private = stack; } else { stack = m->private; } return stack; } static void *stack_next(struct seq_file *m, void *v, loff_t *ppos) { struct stack *stack = v; stack = stack->next; *ppos = stack ? *ppos + 1 : -1UL; m->private = stack; return stack; } static unsigned long page_owner_pages_threshold; static int stack_print(struct seq_file *m, void *v) { int i, nr_base_pages; struct stack *stack = v; unsigned long *entries; unsigned long nr_entries; struct stack_record *stack_record = stack->stack_record; if (!stack->stack_record) return 0; nr_entries = stack_record->size; entries = stack_record->entries; nr_base_pages = refcount_read(&stack_record->count) - 1; if (nr_base_pages < 1 || nr_base_pages < page_owner_pages_threshold) return 0; for (i = 0; i < nr_entries; i++) seq_printf(m, " %pS\n", (void *)entries[i]); seq_printf(m, "nr_base_pages: %d\n\n", nr_base_pages); return 0; } static void stack_stop(struct seq_file *m, void *v) { } static const struct seq_operations page_owner_stack_op = { .start = stack_start, .next = stack_next, .stop = stack_stop, .show = stack_print }; static int page_owner_stack_open(struct inode *inode, struct file *file) { return seq_open_private(file, &page_owner_stack_op, 0); } static const struct file_operations page_owner_stack_operations = { .open = page_owner_stack_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; static int page_owner_threshold_get(void *data, u64 *val) { *val = READ_ONCE(page_owner_pages_threshold); return 0; } static int page_owner_threshold_set(void *data, u64 val) { WRITE_ONCE(page_owner_pages_threshold, val); return 0; } DEFINE_SIMPLE_ATTRIBUTE(proc_page_owner_threshold, &page_owner_threshold_get, &page_owner_threshold_set, "%llu"); static int __init pageowner_init(void) { struct dentry *dir; if (!static_branch_unlikely(&page_owner_inited)) { pr_info("page_owner is disabled\n"); return 0; } debugfs_create_file("page_owner", 0400, NULL, NULL, &proc_page_owner_operations); dir = debugfs_create_dir("page_owner_stacks", NULL); debugfs_create_file("show_stacks", 0400, dir, NULL, &page_owner_stack_operations); debugfs_create_file("count_threshold", 0600, dir, NULL, &proc_page_owner_threshold); return 0; } late_initcall(pageowner_init) |
| 7 7 7 7 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Contiguous Memory Allocator * * Copyright (c) 2010-2011 by Samsung Electronics. * Copyright IBM Corporation, 2013 * Copyright LG Electronics Inc., 2014 * Written by: * Marek Szyprowski <m.szyprowski@samsung.com> * Michal Nazarewicz <mina86@mina86.com> * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> * Joonsoo Kim <iamjoonsoo.kim@lge.com> */ #define pr_fmt(fmt) "cma: " fmt #define CREATE_TRACE_POINTS #include <linux/memblock.h> #include <linux/err.h> #include <linux/mm.h> #include <linux/sizes.h> #include <linux/slab.h> #include <linux/log2.h> #include <linux/cma.h> #include <linux/highmem.h> #include <linux/io.h> #include <linux/kmemleak.h> #include <trace/events/cma.h> #include "internal.h" #include "cma.h" struct cma cma_areas[MAX_CMA_AREAS]; unsigned cma_area_count; static DEFINE_MUTEX(cma_mutex); phys_addr_t cma_get_base(const struct cma *cma) { return PFN_PHYS(cma->base_pfn); } unsigned long cma_get_size(const struct cma *cma) { return cma->count << PAGE_SHIFT; } const char *cma_get_name(const struct cma *cma) { return cma->name; } static unsigned long cma_bitmap_aligned_mask(const struct cma *cma, unsigned int align_order) { if (align_order <= cma->order_per_bit) return 0; return (1UL << (align_order - cma->order_per_bit)) - 1; } /* * Find the offset of the base PFN from the specified align_order. * The value returned is represented in order_per_bits. */ static unsigned long cma_bitmap_aligned_offset(const struct cma *cma, unsigned int align_order) { return (cma->base_pfn & ((1UL << align_order) - 1)) >> cma->order_per_bit; } static unsigned long cma_bitmap_pages_to_bits(const struct cma *cma, unsigned long pages) { return ALIGN(pages, 1UL << cma->order_per_bit) >> cma->order_per_bit; } static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, unsigned long count) { unsigned long bitmap_no, bitmap_count; unsigned long flags; bitmap_no = (pfn - cma->base_pfn) >> cma->order_per_bit; bitmap_count = cma_bitmap_pages_to_bits(cma, count); spin_lock_irqsave(&cma->lock, flags); bitmap_clear(cma->bitmap, bitmap_no, bitmap_count); spin_unlock_irqrestore(&cma->lock, flags); } static void __init cma_activate_area(struct cma *cma) { unsigned long base_pfn = cma->base_pfn, pfn; struct zone *zone; cma->bitmap = bitmap_zalloc(cma_bitmap_maxno(cma), GFP_KERNEL); if (!cma->bitmap) goto out_error; /* * alloc_contig_range() requires the pfn range specified to be in the * same zone. Simplify by forcing the entire CMA resv range to be in the * same zone. */ WARN_ON_ONCE(!pfn_valid(base_pfn)); zone = page_zone(pfn_to_page(base_pfn)); for (pfn = base_pfn + 1; pfn < base_pfn + cma->count; pfn++) { WARN_ON_ONCE(!pfn_valid(pfn)); if (page_zone(pfn_to_page(pfn)) != zone) goto not_in_zone; } for (pfn = base_pfn; pfn < base_pfn + cma->count; pfn += pageblock_nr_pages) init_cma_reserved_pageblock(pfn_to_page(pfn)); spin_lock_init(&cma->lock); #ifdef CONFIG_CMA_DEBUGFS INIT_HLIST_HEAD(&cma->mem_head); spin_lock_init(&cma->mem_head_lock); #endif return; not_in_zone: bitmap_free(cma->bitmap); out_error: /* Expose all pages to the buddy, they are useless for CMA. */ if (!cma->reserve_pages_on_error) { for (pfn = base_pfn; pfn < base_pfn + cma->count; pfn++) free_reserved_page(pfn_to_page(pfn)); } totalcma_pages -= cma->count; cma->count = 0; pr_err("CMA area %s could not be activated\n", cma->name); return; } static int __init cma_init_reserved_areas(void) { int i; for (i = 0; i < cma_area_count; i++) cma_activate_area(&cma_areas[i]); return 0; } core_initcall(cma_init_reserved_areas); void __init cma_reserve_pages_on_error(struct cma *cma) { cma->reserve_pages_on_error = true; } /** * cma_init_reserved_mem() - create custom contiguous area from reserved memory * @base: Base address of the reserved area * @size: Size of the reserved area (in bytes), * @order_per_bit: Order of pages represented by one bit on bitmap. * @name: The name of the area. If this parameter is NULL, the name of * the area will be set to "cmaN", where N is a running counter of * used areas. * @res_cma: Pointer to store the created cma region. * * This function creates custom contiguous area from already reserved memory. */ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, unsigned int order_per_bit, const char *name, struct cma **res_cma) { struct cma *cma; /* Sanity checks */ if (cma_area_count == ARRAY_SIZE(cma_areas)) { pr_err("Not enough slots for CMA reserved regions!\n"); return -ENOSPC; } if (!size || !memblock_is_region_reserved(base, size)) return -EINVAL; /* ensure minimal alignment required by mm core */ if (!IS_ALIGNED(base | size, CMA_MIN_ALIGNMENT_BYTES)) return -EINVAL; /* * Each reserved area must be initialised later, when more kernel * subsystems (like slab allocator) are available. */ cma = &cma_areas[cma_area_count]; if (name) snprintf(cma->name, CMA_MAX_NAME, name); else snprintf(cma->name, CMA_MAX_NAME, "cma%d\n", cma_area_count); cma->base_pfn = PFN_DOWN(base); cma->count = size >> PAGE_SHIFT; cma->order_per_bit = order_per_bit; *res_cma = cma; cma_area_count++; totalcma_pages += cma->count; return 0; } /** * cma_declare_contiguous_nid() - reserve custom contiguous area * @base: Base address of the reserved area optional, use 0 for any * @size: Size of the reserved area (in bytes), * @limit: End address of the reserved memory (optional, 0 for any). * @alignment: Alignment for the CMA area, should be power of 2 or zero * @order_per_bit: Order of pages represented by one bit on bitmap. * @fixed: hint about where to place the reserved area * @name: The name of the area. See function cma_init_reserved_mem() * @res_cma: Pointer to store the created cma region. * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * This function reserves memory from early allocator. It should be * called by arch specific code once the early allocator (memblock or bootmem) * has been activated and all other subsystems have already allocated/reserved * memory. This function allows to create custom reserved areas. * * If @fixed is true, reserve contiguous area at exactly @base. If false, * reserve in range from @base to @limit. */ int __init cma_declare_contiguous_nid(phys_addr_t base, phys_addr_t size, phys_addr_t limit, phys_addr_t alignment, unsigned int order_per_bit, bool fixed, const char *name, struct cma **res_cma, int nid) { phys_addr_t memblock_end = memblock_end_of_DRAM(); phys_addr_t highmem_start; int ret; /* * We can't use __pa(high_memory) directly, since high_memory * isn't a valid direct map VA, and DEBUG_VIRTUAL will (validly) * complain. Find the boundary by adding one to the last valid * address. */ highmem_start = __pa(high_memory - 1) + 1; pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n", __func__, &size, &base, &limit, &alignment); if (cma_area_count == ARRAY_SIZE(cma_areas)) { pr_err("Not enough slots for CMA reserved regions!\n"); return -ENOSPC; } if (!size) return -EINVAL; if (alignment && !is_power_of_2(alignment)) return -EINVAL; if (!IS_ENABLED(CONFIG_NUMA)) nid = NUMA_NO_NODE; /* Sanitise input arguments. */ alignment = max_t(phys_addr_t, alignment, CMA_MIN_ALIGNMENT_BYTES); if (fixed && base & (alignment - 1)) { ret = -EINVAL; pr_err("Region at %pa must be aligned to %pa bytes\n", &base, &alignment); goto err; } base = ALIGN(base, alignment); size = ALIGN(size, alignment); limit &= ~(alignment - 1); if (!base) fixed = false; /* size should be aligned with order_per_bit */ if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit)) return -EINVAL; /* * If allocating at a fixed base the request region must not cross the * low/high memory boundary. */ if (fixed && base < highmem_start && base + size > highmem_start) { ret = -EINVAL; pr_err("Region at %pa defined on low/high memory boundary (%pa)\n", &base, &highmem_start); goto err; } /* * If the limit is unspecified or above the memblock end, its effective * value will be the memblock end. Set it explicitly to simplify further * checks. */ if (limit == 0 || limit > memblock_end) limit = memblock_end; if (base + size > limit) { ret = -EINVAL; pr_err("Size (%pa) of region at %pa exceeds limit (%pa)\n", &size, &base, &limit); goto err; } /* Reserve memory */ if (fixed) { if (memblock_is_region_reserved(base, size) || memblock_reserve(base, size) < 0) { ret = -EBUSY; goto err; } } else { phys_addr_t addr = 0; /* * If there is enough memory, try a bottom-up allocation first. * It will place the new cma area close to the start of the node * and guarantee that the compaction is moving pages out of the * cma area and not into it. * Avoid using first 4GB to not interfere with constrained zones * like DMA/DMA32. */ #ifdef CONFIG_PHYS_ADDR_T_64BIT if (!memblock_bottom_up() && memblock_end >= SZ_4G + size) { memblock_set_bottom_up(true); addr = memblock_alloc_range_nid(size, alignment, SZ_4G, limit, nid, true); memblock_set_bottom_up(false); } #endif /* * All pages in the reserved area must come from the same zone. * If the requested region crosses the low/high memory boundary, * try allocating from high memory first and fall back to low * memory in case of failure. */ if (!addr && base < highmem_start && limit > highmem_start) { addr = memblock_alloc_range_nid(size, alignment, highmem_start, limit, nid, true); limit = highmem_start; } if (!addr) { addr = memblock_alloc_range_nid(size, alignment, base, limit, nid, true); if (!addr) { ret = -ENOMEM; goto err; } } /* * kmemleak scans/reads tracked objects for pointers to other * objects but this address isn't mapped and accessible */ kmemleak_ignore_phys(addr); base = addr; } ret = cma_init_reserved_mem(base, size, order_per_bit, name, res_cma); if (ret) goto free_mem; pr_info("Reserved %ld MiB at %pa on node %d\n", (unsigned long)size / SZ_1M, &base, nid); return 0; free_mem: memblock_phys_free(base, size); err: pr_err("Failed to reserve %ld MiB on node %d\n", (unsigned long)size / SZ_1M, nid); return ret; } static void cma_debug_show_areas(struct cma *cma) { unsigned long next_zero_bit, next_set_bit, nr_zero; unsigned long start = 0; unsigned long nr_part, nr_total = 0; unsigned long nbits = cma_bitmap_maxno(cma); spin_lock_irq(&cma->lock); pr_info("number of available pages: "); for (;;) { next_zero_bit = find_next_zero_bit(cma->bitmap, nbits, start); if (next_zero_bit >= nbits) break; next_set_bit = find_next_bit(cma->bitmap, nbits, next_zero_bit); nr_zero = next_set_bit - next_zero_bit; nr_part = nr_zero << cma->order_per_bit; pr_cont("%s%lu@%lu", nr_total ? "+" : "", nr_part, next_zero_bit); nr_total += nr_part; start = next_zero_bit + nr_zero; } pr_cont("=> %lu free of %lu total pages\n", nr_total, cma->count); spin_unlock_irq(&cma->lock); } static struct page *__cma_alloc(struct cma *cma, unsigned long count, unsigned int align, gfp_t gfp) { unsigned long mask, offset; unsigned long pfn = -1; unsigned long start = 0; unsigned long bitmap_maxno, bitmap_no, bitmap_count; unsigned long i; struct page *page = NULL; int ret = -ENOMEM; const char *name = cma ? cma->name : NULL; trace_cma_alloc_start(name, count, align); if (!cma || !cma->count || !cma->bitmap) return page; pr_debug("%s(cma %p, name: %s, count %lu, align %d)\n", __func__, (void *)cma, cma->name, count, align); if (!count) return page; mask = cma_bitmap_aligned_mask(cma, align); offset = cma_bitmap_aligned_offset(cma, align); bitmap_maxno = cma_bitmap_maxno(cma); bitmap_count = cma_bitmap_pages_to_bits(cma, count); if (bitmap_count > bitmap_maxno) return page; for (;;) { spin_lock_irq(&cma->lock); bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap, bitmap_maxno, start, bitmap_count, mask, offset); if (bitmap_no >= bitmap_maxno) { spin_unlock_irq(&cma->lock); break; } bitmap_set(cma->bitmap, bitmap_no, bitmap_count); /* * It's safe to drop the lock here. We've marked this region for * our exclusive use. If the migration fails we will take the * lock again and unmark it. */ spin_unlock_irq(&cma->lock); pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit); mutex_lock(&cma_mutex); ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, gfp); mutex_unlock(&cma_mutex); if (ret == 0) { page = pfn_to_page(pfn); break; } cma_clear_bitmap(cma, pfn, count); if (ret != -EBUSY) break; pr_debug("%s(): memory range at pfn 0x%lx %p is busy, retrying\n", __func__, pfn, pfn_to_page(pfn)); trace_cma_alloc_busy_retry(cma->name, pfn, pfn_to_page(pfn), count, align); /* try again with a bit different memory target */ start = bitmap_no + mask + 1; } /* * CMA can allocate multiple page blocks, which results in different * blocks being marked with different tags. Reset the tags to ignore * those page blocks. */ if (page) { for (i = 0; i < count; i++) page_kasan_tag_reset(nth_page(page, i)); } if (ret && !(gfp & __GFP_NOWARN)) { pr_err_ratelimited("%s: %s: alloc failed, req-size: %lu pages, ret: %d\n", __func__, cma->name, count, ret); cma_debug_show_areas(cma); } pr_debug("%s(): returned %p\n", __func__, page); trace_cma_alloc_finish(name, pfn, page, count, align, ret); if (page) { count_vm_event(CMA_ALLOC_SUCCESS); cma_sysfs_account_success_pages(cma, count); } else { count_vm_event(CMA_ALLOC_FAIL); cma_sysfs_account_fail_pages(cma, count); } return page; } /** * cma_alloc() - allocate pages from contiguous area * @cma: Contiguous memory region for which the allocation is performed. * @count: Requested number of pages. * @align: Requested alignment of pages (in PAGE_SIZE order). * @no_warn: Avoid printing message about failed allocation * * This function allocates part of contiguous memory on specific * contiguous memory area. */ struct page *cma_alloc(struct cma *cma, unsigned long count, unsigned int align, bool no_warn) { return __cma_alloc(cma, count, align, GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0)); } struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp) { struct page *page; if (WARN_ON(!order || !(gfp & __GFP_COMP))) return NULL; page = __cma_alloc(cma, 1 << order, order, gfp); return page ? page_folio(page) : NULL; } bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned long count) { unsigned long pfn; if (!cma || !pages) return false; pfn = page_to_pfn(pages); if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) { pr_debug("%s(page %p, count %lu)\n", __func__, (void *)pages, count); return false; } return true; } /** * cma_release() - release allocated pages * @cma: Contiguous memory region for which the allocation is performed. * @pages: Allocated pages. * @count: Number of allocated pages. * * This function releases memory allocated by cma_alloc(). * It returns false when provided pages do not belong to contiguous area and * true otherwise. */ bool cma_release(struct cma *cma, const struct page *pages, unsigned long count) { unsigned long pfn; if (!cma_pages_valid(cma, pages, count)) return false; pr_debug("%s(page %p, count %lu)\n", __func__, (void *)pages, count); pfn = page_to_pfn(pages); VM_BUG_ON(pfn + count > cma->base_pfn + cma->count); free_contig_range(pfn, count); cma_clear_bitmap(cma, pfn, count); cma_sysfs_account_release_pages(cma, count); trace_cma_release(cma->name, pfn, pages, count); return true; } bool cma_free_folio(struct cma *cma, const struct folio *folio) { if (WARN_ON(!folio_test_large(folio))) return false; return cma_release(cma, &folio->page, folio_nr_pages(folio)); } int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data) { int i; for (i = 0; i < cma_area_count; i++) { int ret = it(&cma_areas[i], data); if (ret) return ret; } return 0; } |
| 190 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 | // SPDX-License-Identifier: GPL-2.0 /* * High memory handling common code and variables. * * (C) 1999 Andrea Arcangeli, SuSE GmbH, andrea@suse.de * Gerhard Wichert, Siemens AG, Gerhard.Wichert@pdb.siemens.de * * * Redesigned the x86 32-bit VM architecture to deal with * 64-bit physical space. With current x86 CPUs this * means up to 64 Gigabytes physical RAM. * * Rewrote high memory support to move the page cache into * high memory. Implemented permanent (schedulable) kmaps * based on Linus' idea. * * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com> */ #include <linux/mm.h> #include <linux/export.h> #include <linux/swap.h> #include <linux/bio.h> #include <linux/pagemap.h> #include <linux/mempool.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/highmem.h> #include <linux/kgdb.h> #include <asm/tlbflush.h> #include <linux/vmalloc.h> #ifdef CONFIG_KMAP_LOCAL static inline int kmap_local_calc_idx(int idx) { return idx + KM_MAX_IDX * smp_processor_id(); } #ifndef arch_kmap_local_map_idx #define arch_kmap_local_map_idx(idx, pfn) kmap_local_calc_idx(idx) #endif #endif /* CONFIG_KMAP_LOCAL */ /* * Virtual_count is not a pure "count". * 0 means that it is not mapped, and has not been mapped * since a TLB flush - it is usable. * 1 means that there are no users, but it has been mapped * since the last TLB flush - so we can't use it. * n means that there are (n-1) current users of it. */ #ifdef CONFIG_HIGHMEM /* * Architecture with aliasing data cache may define the following family of * helper functions in its asm/highmem.h to control cache color of virtual * addresses where physical memory pages are mapped by kmap. */ #ifndef get_pkmap_color /* * Determine color of virtual address where the page should be mapped. */ static inline unsigned int get_pkmap_color(struct page *page) { return 0; } #define get_pkmap_color get_pkmap_color /* * Get next index for mapping inside PKMAP region for page with given color. */ static inline unsigned int get_next_pkmap_nr(unsigned int color) { static unsigned int last_pkmap_nr; last_pkmap_nr = (last_pkmap_nr + 1) & LAST_PKMAP_MASK; return last_pkmap_nr; } /* * Determine if page index inside PKMAP region (pkmap_nr) of given color * has wrapped around PKMAP region end. When this happens an attempt to * flush all unused PKMAP slots is made. */ static inline int no_more_pkmaps(unsigned int pkmap_nr, unsigned int color) { return pkmap_nr == 0; } /* * Get the number of PKMAP entries of the given color. If no free slot is * found after checking that many entries, kmap will sleep waiting for * someone to call kunmap and free PKMAP slot. */ static inline int get_pkmap_entries_count(unsigned int color) { return LAST_PKMAP; } /* * Get head of a wait queue for PKMAP entries of the given color. * Wait queues for different mapping colors should be independent to avoid * unnecessary wakeups caused by freeing of slots of other colors. */ static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color) { static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait); return &pkmap_map_wait; } #endif unsigned long __nr_free_highpages(void) { unsigned long pages = 0; struct zone *zone; for_each_populated_zone(zone) { if (is_highmem(zone)) pages += zone_page_state(zone, NR_FREE_PAGES); } return pages; } unsigned long __totalhigh_pages(void) { unsigned long pages = 0; struct zone *zone; for_each_populated_zone(zone) { if (is_highmem(zone)) pages += zone_managed_pages(zone); } return pages; } EXPORT_SYMBOL(__totalhigh_pages); static int pkmap_count[LAST_PKMAP]; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock); pte_t *pkmap_page_table; /* * Most architectures have no use for kmap_high_get(), so let's abstract * the disabling of IRQ out of the locking in that case to save on a * potential useless overhead. */ #ifdef ARCH_NEEDS_KMAP_HIGH_GET #define lock_kmap() spin_lock_irq(&kmap_lock) #define unlock_kmap() spin_unlock_irq(&kmap_lock) #define lock_kmap_any(flags) spin_lock_irqsave(&kmap_lock, flags) #define unlock_kmap_any(flags) spin_unlock_irqrestore(&kmap_lock, flags) #else #define lock_kmap() spin_lock(&kmap_lock) #define unlock_kmap() spin_unlock(&kmap_lock) #define lock_kmap_any(flags) \ do { spin_lock(&kmap_lock); (void)(flags); } while (0) #define unlock_kmap_any(flags) \ do { spin_unlock(&kmap_lock); (void)(flags); } while (0) #endif struct page *__kmap_to_page(void *vaddr) { unsigned long base = (unsigned long) vaddr & PAGE_MASK; struct kmap_ctrl *kctrl = ¤t->kmap_ctrl; unsigned long addr = (unsigned long)vaddr; int i; /* kmap() mappings */ if (WARN_ON_ONCE(addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP))) return pte_page(ptep_get(&pkmap_page_table[PKMAP_NR(addr)])); /* kmap_local_page() mappings */ if (WARN_ON_ONCE(base >= __fix_to_virt(FIX_KMAP_END) && base < __fix_to_virt(FIX_KMAP_BEGIN))) { for (i = 0; i < kctrl->idx; i++) { unsigned long base_addr; int idx; idx = arch_kmap_local_map_idx(i, pte_pfn(pteval)); base_addr = __fix_to_virt(FIX_KMAP_BEGIN + idx); if (base_addr == base) return pte_page(kctrl->pteval[i]); } } return virt_to_page(vaddr); } EXPORT_SYMBOL(__kmap_to_page); static void flush_all_zero_pkmaps(void) { int i; int need_flush = 0; flush_cache_kmaps(); for (i = 0; i < LAST_PKMAP; i++) { struct page *page; pte_t ptent; /* * zero means we don't have anything to do, * >1 means that it is still in use. Only * a count of 1 means that it is free but * needs to be unmapped */ if (pkmap_count[i] != 1) continue; pkmap_count[i] = 0; /* sanity check */ ptent = ptep_get(&pkmap_page_table[i]); BUG_ON(pte_none(ptent)); /* * Don't need an atomic fetch-and-clear op here; * no-one has the page mapped, and cannot get at * its virtual address (and hence PTE) without first * getting the kmap_lock (which is held here). * So no dangers, even with speculative execution. */ page = pte_page(ptent); pte_clear(&init_mm, PKMAP_ADDR(i), &pkmap_page_table[i]); set_page_address(page, NULL); need_flush = 1; } if (need_flush) flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP)); } void __kmap_flush_unused(void) { lock_kmap(); flush_all_zero_pkmaps(); unlock_kmap(); } static inline unsigned long map_new_virtual(struct page *page) { unsigned long vaddr; int count; unsigned int last_pkmap_nr; unsigned int color = get_pkmap_color(page); start: count = get_pkmap_entries_count(color); /* Find an empty entry */ for (;;) { last_pkmap_nr = get_next_pkmap_nr(color); if (no_more_pkmaps(last_pkmap_nr, color)) { flush_all_zero_pkmaps(); count = get_pkmap_entries_count(color); } if (!pkmap_count[last_pkmap_nr]) break; /* Found a usable entry */ if (--count) continue; /* * Sleep for somebody else to unmap their entries */ { DECLARE_WAITQUEUE(wait, current); wait_queue_head_t *pkmap_map_wait = get_pkmap_wait_queue_head(color); __set_current_state(TASK_UNINTERRUPTIBLE); add_wait_queue(pkmap_map_wait, &wait); unlock_kmap(); schedule(); remove_wait_queue(pkmap_map_wait, &wait); lock_kmap(); /* Somebody else might have mapped it while we slept */ if (page_address(page)) return (unsigned long)page_address(page); /* Re-start */ goto start; } } vaddr = PKMAP_ADDR(last_pkmap_nr); set_pte_at(&init_mm, vaddr, &(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot)); pkmap_count[last_pkmap_nr] = 1; set_page_address(page, (void *)vaddr); return vaddr; } /** * kmap_high - map a highmem page into memory * @page: &struct page to map * * Returns the page's virtual memory address. * * We cannot call this from interrupts, as it may block. */ void *kmap_high(struct page *page) { unsigned long vaddr; /* * For highmem pages, we can't trust "virtual" until * after we have the lock. */ lock_kmap(); vaddr = (unsigned long)page_address(page); if (!vaddr) vaddr = map_new_virtual(page); pkmap_count[PKMAP_NR(vaddr)]++; BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2); unlock_kmap(); return (void *) vaddr; } EXPORT_SYMBOL(kmap_high); #ifdef ARCH_NEEDS_KMAP_HIGH_GET /** * kmap_high_get - pin a highmem page into memory * @page: &struct page to pin * * Returns the page's current virtual memory address, or NULL if no mapping * exists. If and only if a non null address is returned then a * matching call to kunmap_high() is necessary. * * This can be called from any context. */ void *kmap_high_get(struct page *page) { unsigned long vaddr, flags; lock_kmap_any(flags); vaddr = (unsigned long)page_address(page); if (vaddr) { BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 1); pkmap_count[PKMAP_NR(vaddr)]++; } unlock_kmap_any(flags); return (void *) vaddr; } #endif /** * kunmap_high - unmap a highmem page into memory * @page: &struct page to unmap * * If ARCH_NEEDS_KMAP_HIGH_GET is not defined then this may be called * only from user context. */ void kunmap_high(struct page *page) { unsigned long vaddr; unsigned long nr; unsigned long flags; int need_wakeup; unsigned int color = get_pkmap_color(page); wait_queue_head_t *pkmap_map_wait; lock_kmap_any(flags); vaddr = (unsigned long)page_address(page); BUG_ON(!vaddr); nr = PKMAP_NR(vaddr); /* * A count must never go down to zero * without a TLB flush! */ need_wakeup = 0; switch (--pkmap_count[nr]) { case 0: BUG(); case 1: /* * Avoid an unnecessary wake_up() function call. * The common case is pkmap_count[] == 1, but * no waiters. * The tasks queued in the wait-queue are guarded * by both the lock in the wait-queue-head and by * the kmap_lock. As the kmap_lock is held here, * no need for the wait-queue-head's lock. Simply * test if the queue is empty. */ pkmap_map_wait = get_pkmap_wait_queue_head(color); need_wakeup = waitqueue_active(pkmap_map_wait); } unlock_kmap_any(flags); /* do wake-up, if needed, race-free outside of the spin lock */ if (need_wakeup) wake_up(pkmap_map_wait); } EXPORT_SYMBOL(kunmap_high); void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); if (start1 >= end1) start1 = end1 = 0; if (start2 >= end2) start2 = end2 = 0; for (i = 0; i < compound_nr(page); i++) { void *kaddr = NULL; if (start1 >= PAGE_SIZE) { start1 -= PAGE_SIZE; end1 -= PAGE_SIZE; } else { unsigned this_end = min_t(unsigned, end1, PAGE_SIZE); if (end1 > start1) { kaddr = kmap_local_page(page + i); memset(kaddr + start1, 0, this_end - start1); } end1 -= this_end; start1 = 0; } if (start2 >= PAGE_SIZE) { start2 -= PAGE_SIZE; end2 -= PAGE_SIZE; } else { unsigned this_end = min_t(unsigned, end2, PAGE_SIZE); if (end2 > start2) { if (!kaddr) kaddr = kmap_local_page(page + i); memset(kaddr + start2, 0, this_end - start2); } end2 -= this_end; start2 = 0; } if (kaddr) { kunmap_local(kaddr); flush_dcache_page(page + i); } if (!end1 && !end2) break; } BUG_ON((start1 | start2 | end1 | end2) != 0); } EXPORT_SYMBOL(zero_user_segments); #endif /* CONFIG_HIGHMEM */ #ifdef CONFIG_KMAP_LOCAL #include <asm/kmap_size.h> /* * With DEBUG_KMAP_LOCAL the stack depth is doubled and every second * slot is unused which acts as a guard page */ #ifdef CONFIG_DEBUG_KMAP_LOCAL # define KM_INCR 2 #else # define KM_INCR 1 #endif static inline int kmap_local_idx_push(void) { WARN_ON_ONCE(in_hardirq() && !irqs_disabled()); current->kmap_ctrl.idx += KM_INCR; BUG_ON(current->kmap_ctrl.idx >= KM_MAX_IDX); return current->kmap_ctrl.idx - 1; } static inline int kmap_local_idx(void) { return current->kmap_ctrl.idx - 1; } static inline void kmap_local_idx_pop(void) { current->kmap_ctrl.idx -= KM_INCR; BUG_ON(current->kmap_ctrl.idx < 0); } #ifndef arch_kmap_local_post_map # define arch_kmap_local_post_map(vaddr, pteval) do { } while (0) #endif #ifndef arch_kmap_local_pre_unmap # define arch_kmap_local_pre_unmap(vaddr) do { } while (0) #endif #ifndef arch_kmap_local_post_unmap # define arch_kmap_local_post_unmap(vaddr) do { } while (0) #endif #ifndef arch_kmap_local_unmap_idx #define arch_kmap_local_unmap_idx(idx, vaddr) kmap_local_calc_idx(idx) #endif #ifndef arch_kmap_local_high_get static inline void *arch_kmap_local_high_get(struct page *page) { return NULL; } #endif #ifndef arch_kmap_local_set_pte #define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) \ set_pte_at(mm, vaddr, ptep, ptev) #endif /* Unmap a local mapping which was obtained by kmap_high_get() */ static inline bool kmap_high_unmap_local(unsigned long vaddr) { #ifdef ARCH_NEEDS_KMAP_HIGH_GET if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) { kunmap_high(pte_page(ptep_get(&pkmap_page_table[PKMAP_NR(vaddr)]))); return true; } #endif return false; } static pte_t *__kmap_pte; static pte_t *kmap_get_pte(unsigned long vaddr, int idx) { if (IS_ENABLED(CONFIG_KMAP_LOCAL_NON_LINEAR_PTE_ARRAY)) /* * Set by the arch if __kmap_pte[-idx] does not produce * the correct entry. */ return virt_to_kpte(vaddr); if (!__kmap_pte) __kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN)); return &__kmap_pte[-idx]; } void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot) { pte_t pteval, *kmap_pte; unsigned long vaddr; int idx; /* * Disable migration so resulting virtual address is stable * across preemption. */ migrate_disable(); preempt_disable(); idx = arch_kmap_local_map_idx(kmap_local_idx_push(), pfn); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); kmap_pte = kmap_get_pte(vaddr, idx); BUG_ON(!pte_none(ptep_get(kmap_pte))); pteval = pfn_pte(pfn, prot); arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte, pteval); arch_kmap_local_post_map(vaddr, pteval); current->kmap_ctrl.pteval[kmap_local_idx()] = pteval; preempt_enable(); return (void *)vaddr; } EXPORT_SYMBOL_GPL(__kmap_local_pfn_prot); void *__kmap_local_page_prot(struct page *page, pgprot_t prot) { void *kmap; /* * To broaden the usage of the actual kmap_local() machinery always map * pages when debugging is enabled and the architecture has no problems * with alias mappings. */ if (!IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) && !PageHighMem(page)) return page_address(page); /* Try kmap_high_get() if architecture has it enabled */ kmap = arch_kmap_local_high_get(page); if (kmap) return kmap; return __kmap_local_pfn_prot(page_to_pfn(page), prot); } EXPORT_SYMBOL(__kmap_local_page_prot); void kunmap_local_indexed(const void *vaddr) { unsigned long addr = (unsigned long) vaddr & PAGE_MASK; pte_t *kmap_pte; int idx; if (addr < __fix_to_virt(FIX_KMAP_END) || addr > __fix_to_virt(FIX_KMAP_BEGIN)) { if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP)) { /* This _should_ never happen! See above. */ WARN_ON_ONCE(1); return; } /* * Handle mappings which were obtained by kmap_high_get() * first as the virtual address of such mappings is below * PAGE_OFFSET. Warn for all other addresses which are in * the user space part of the virtual address space. */ if (!kmap_high_unmap_local(addr)) WARN_ON_ONCE(addr < PAGE_OFFSET); return; } preempt_disable(); idx = arch_kmap_local_unmap_idx(kmap_local_idx(), addr); WARN_ON_ONCE(addr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); kmap_pte = kmap_get_pte(addr, idx); arch_kmap_local_pre_unmap(addr); pte_clear(&init_mm, addr, kmap_pte); arch_kmap_local_post_unmap(addr); current->kmap_ctrl.pteval[kmap_local_idx()] = __pte(0); kmap_local_idx_pop(); preempt_enable(); migrate_enable(); } EXPORT_SYMBOL(kunmap_local_indexed); /* * Invoked before switch_to(). This is safe even when during or after * clearing the maps an interrupt which needs a kmap_local happens because * the task::kmap_ctrl.idx is not modified by the unmapping code so a * nested kmap_local will use the next unused index and restore the index * on unmap. The already cleared kmaps of the outgoing task are irrelevant * because the interrupt context does not know about them. The same applies * when scheduling back in for an interrupt which happens before the * restore is complete. */ void __kmap_local_sched_out(void) { struct task_struct *tsk = current; pte_t *kmap_pte; int i; /* Clear kmaps */ for (i = 0; i < tsk->kmap_ctrl.idx; i++) { pte_t pteval = tsk->kmap_ctrl.pteval[i]; unsigned long addr; int idx; /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) continue; /* * This is a horrible hack for XTENSA to calculate the * coloured PTE index. Uses the PFN encoded into the pteval * and the map index calculation because the actual mapped * virtual address is not stored in task::kmap_ctrl. * For any sane architecture this is optimized out. */ idx = arch_kmap_local_map_idx(i, pte_pfn(pteval)); addr = __fix_to_virt(FIX_KMAP_BEGIN + idx); kmap_pte = kmap_get_pte(addr, idx); arch_kmap_local_pre_unmap(addr); pte_clear(&init_mm, addr, kmap_pte); arch_kmap_local_post_unmap(addr); } } void __kmap_local_sched_in(void) { struct task_struct *tsk = current; pte_t *kmap_pte; int i; /* Restore kmaps */ for (i = 0; i < tsk->kmap_ctrl.idx; i++) { pte_t pteval = tsk->kmap_ctrl.pteval[i]; unsigned long addr; int idx; /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) continue; /* See comment in __kmap_local_sched_out() */ idx = arch_kmap_local_map_idx(i, pte_pfn(pteval)); addr = __fix_to_virt(FIX_KMAP_BEGIN + idx); kmap_pte = kmap_get_pte(addr, idx); set_pte_at(&init_mm, addr, kmap_pte, pteval); arch_kmap_local_post_map(addr, pteval); } } void kmap_local_fork(struct task_struct *tsk) { if (WARN_ON_ONCE(tsk->kmap_ctrl.idx)) memset(&tsk->kmap_ctrl, 0, sizeof(tsk->kmap_ctrl)); } #endif #if defined(HASHED_PAGE_VIRTUAL) #define PA_HASH_ORDER 7 /* * Describes one page->virtual association */ struct page_address_map { struct page *page; void *virtual; struct list_head list; }; static struct page_address_map page_address_maps[LAST_PKMAP]; /* * Hash table bucket */ static struct page_address_slot { struct list_head lh; /* List of page_address_maps */ spinlock_t lock; /* Protect this bucket's list */ } ____cacheline_aligned_in_smp page_address_htable[1<<PA_HASH_ORDER]; static struct page_address_slot *page_slot(const struct page *page) { return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)]; } /** * page_address - get the mapped virtual address of a page * @page: &struct page to get the virtual address of * * Returns the page's virtual address. */ void *page_address(const struct page *page) { unsigned long flags; void *ret; struct page_address_slot *pas; if (!PageHighMem(page)) return lowmem_page_address(page); pas = page_slot(page); ret = NULL; spin_lock_irqsave(&pas->lock, flags); if (!list_empty(&pas->lh)) { struct page_address_map *pam; list_for_each_entry(pam, &pas->lh, list) { if (pam->page == page) { ret = pam->virtual; break; } } } spin_unlock_irqrestore(&pas->lock, flags); return ret; } EXPORT_SYMBOL(page_address); /** * set_page_address - set a page's virtual address * @page: &struct page to set * @virtual: virtual address to use */ void set_page_address(struct page *page, void *virtual) { unsigned long flags; struct page_address_slot *pas; struct page_address_map *pam; BUG_ON(!PageHighMem(page)); pas = page_slot(page); if (virtual) { /* Add */ pam = &page_address_maps[PKMAP_NR((unsigned long)virtual)]; pam->page = page; pam->virtual = virtual; spin_lock_irqsave(&pas->lock, flags); list_add_tail(&pam->list, &pas->lh); spin_unlock_irqrestore(&pas->lock, flags); } else { /* Remove */ spin_lock_irqsave(&pas->lock, flags); list_for_each_entry(pam, &pas->lh, list) { if (pam->page == page) { list_del(&pam->list); break; } } spin_unlock_irqrestore(&pas->lock, flags); } } void __init page_address_init(void) { int i; for (i = 0; i < ARRAY_SIZE(page_address_htable); i++) { INIT_LIST_HEAD(&page_address_htable[i].lh); spin_lock_init(&page_address_htable[i].lock); } } #endif /* defined(HASHED_PAGE_VIRTUAL) */ |
| 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 | /* * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/in.h> #include <linux/if.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/if_arp.h> #include <linux/delay.h> #include <linux/slab.h> #include <linux/module.h> #include <net/addrconf.h> #include "rds_single_path.h" #include "rds.h" #include "ib.h" #include "ib_mr.h" static unsigned int rds_ib_mr_1m_pool_size = RDS_MR_1M_POOL_SIZE; static unsigned int rds_ib_mr_8k_pool_size = RDS_MR_8K_POOL_SIZE; unsigned int rds_ib_retry_count = RDS_IB_DEFAULT_RETRY_COUNT; static atomic_t rds_ib_unloading; module_param(rds_ib_mr_1m_pool_size, int, 0444); MODULE_PARM_DESC(rds_ib_mr_1m_pool_size, " Max number of 1M mr per HCA"); module_param(rds_ib_mr_8k_pool_size, int, 0444); MODULE_PARM_DESC(rds_ib_mr_8k_pool_size, " Max number of 8K mr per HCA"); module_param(rds_ib_retry_count, int, 0444); MODULE_PARM_DESC(rds_ib_retry_count, " Number of hw retries before reporting an error"); /* * we have a clumsy combination of RCU and a rwsem protecting this list * because it is used both in the get_mr fast path and while blocking in * the FMR flushing path. */ DECLARE_RWSEM(rds_ib_devices_lock); struct list_head rds_ib_devices; /* NOTE: if also grabbing ibdev lock, grab this first */ DEFINE_SPINLOCK(ib_nodev_conns_lock); LIST_HEAD(ib_nodev_conns); static void rds_ib_nodev_connect(void) { struct rds_ib_connection *ic; spin_lock(&ib_nodev_conns_lock); list_for_each_entry(ic, &ib_nodev_conns, ib_node) rds_conn_connect_if_down(ic->conn); spin_unlock(&ib_nodev_conns_lock); } static void rds_ib_dev_shutdown(struct rds_ib_device *rds_ibdev) { struct rds_ib_connection *ic; unsigned long flags; spin_lock_irqsave(&rds_ibdev->spinlock, flags); list_for_each_entry(ic, &rds_ibdev->conn_list, ib_node) rds_conn_path_drop(&ic->conn->c_path[0], true); spin_unlock_irqrestore(&rds_ibdev->spinlock, flags); } /* * rds_ib_destroy_mr_pool() blocks on a few things and mrs drop references * from interrupt context so we push freing off into a work struct in krdsd. */ static void rds_ib_dev_free(struct work_struct *work) { struct rds_ib_ipaddr *i_ipaddr, *i_next; struct rds_ib_device *rds_ibdev = container_of(work, struct rds_ib_device, free_work); if (rds_ibdev->mr_8k_pool) rds_ib_destroy_mr_pool(rds_ibdev->mr_8k_pool); if (rds_ibdev->mr_1m_pool) rds_ib_destroy_mr_pool(rds_ibdev->mr_1m_pool); if (rds_ibdev->pd) ib_dealloc_pd(rds_ibdev->pd); list_for_each_entry_safe(i_ipaddr, i_next, &rds_ibdev->ipaddr_list, list) { list_del(&i_ipaddr->list); kfree(i_ipaddr); } kfree(rds_ibdev->vector_load); kfree(rds_ibdev); } void rds_ib_dev_put(struct rds_ib_device *rds_ibdev) { BUG_ON(refcount_read(&rds_ibdev->refcount) == 0); if (refcount_dec_and_test(&rds_ibdev->refcount)) queue_work(rds_wq, &rds_ibdev->free_work); } static int rds_ib_add_one(struct ib_device *device) { struct rds_ib_device *rds_ibdev; int ret; /* Only handle IB (no iWARP) devices */ if (device->node_type != RDMA_NODE_IB_CA) return -EOPNOTSUPP; /* Device must support FRWR */ if (!(device->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS)) return -EOPNOTSUPP; rds_ibdev = kzalloc_node(sizeof(struct rds_ib_device), GFP_KERNEL, ibdev_to_node(device)); if (!rds_ibdev) return -ENOMEM; spin_lock_init(&rds_ibdev->spinlock); refcount_set(&rds_ibdev->refcount, 1); INIT_WORK(&rds_ibdev->free_work, rds_ib_dev_free); INIT_LIST_HEAD(&rds_ibdev->ipaddr_list); INIT_LIST_HEAD(&rds_ibdev->conn_list); rds_ibdev->max_wrs = device->attrs.max_qp_wr; rds_ibdev->max_sge = min(device->attrs.max_send_sge, RDS_IB_MAX_SGE); rds_ibdev->odp_capable = !!(device->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING) && !!(device->attrs.odp_caps.per_transport_caps.rc_odp_caps & IB_ODP_SUPPORT_WRITE) && !!(device->attrs.odp_caps.per_transport_caps.rc_odp_caps & IB_ODP_SUPPORT_READ); rds_ibdev->max_1m_mrs = device->attrs.max_mr ? min_t(unsigned int, (device->attrs.max_mr / 2), rds_ib_mr_1m_pool_size) : rds_ib_mr_1m_pool_size; rds_ibdev->max_8k_mrs = device->attrs.max_mr ? min_t(unsigned int, ((device->attrs.max_mr / 2) * RDS_MR_8K_SCALE), rds_ib_mr_8k_pool_size) : rds_ib_mr_8k_pool_size; rds_ibdev->max_initiator_depth = device->attrs.max_qp_init_rd_atom; rds_ibdev->max_responder_resources = device->attrs.max_qp_rd_atom; rds_ibdev->vector_load = kcalloc(device->num_comp_vectors, sizeof(int), GFP_KERNEL); if (!rds_ibdev->vector_load) { pr_err("RDS/IB: %s failed to allocate vector memory\n", __func__); ret = -ENOMEM; goto put_dev; } rds_ibdev->dev = device; rds_ibdev->pd = ib_alloc_pd(device, 0); if (IS_ERR(rds_ibdev->pd)) { ret = PTR_ERR(rds_ibdev->pd); rds_ibdev->pd = NULL; goto put_dev; } rds_ibdev->mr_1m_pool = rds_ib_create_mr_pool(rds_ibdev, RDS_IB_MR_1M_POOL); if (IS_ERR(rds_ibdev->mr_1m_pool)) { ret = PTR_ERR(rds_ibdev->mr_1m_pool); rds_ibdev->mr_1m_pool = NULL; goto put_dev; } rds_ibdev->mr_8k_pool = rds_ib_create_mr_pool(rds_ibdev, RDS_IB_MR_8K_POOL); if (IS_ERR(rds_ibdev->mr_8k_pool)) { ret = PTR_ERR(rds_ibdev->mr_8k_pool); rds_ibdev->mr_8k_pool = NULL; goto put_dev; } rdsdebug("RDS/IB: max_mr = %d, max_wrs = %d, max_sge = %d, max_1m_mrs = %d, max_8k_mrs = %d\n", device->attrs.max_mr, rds_ibdev->max_wrs, rds_ibdev->max_sge, rds_ibdev->max_1m_mrs, rds_ibdev->max_8k_mrs); pr_info("RDS/IB: %s: added\n", device->name); down_write(&rds_ib_devices_lock); list_add_tail_rcu(&rds_ibdev->list, &rds_ib_devices); up_write(&rds_ib_devices_lock); refcount_inc(&rds_ibdev->refcount); ib_set_client_data(device, &rds_ib_client, rds_ibdev); rds_ib_nodev_connect(); return 0; put_dev: rds_ib_dev_put(rds_ibdev); return ret; } /* * New connections use this to find the device to associate with the * connection. It's not in the fast path so we're not concerned about the * performance of the IB call. (As of this writing, it uses an interrupt * blocking spinlock to serialize walking a per-device list of all registered * clients.) * * RCU is used to handle incoming connections racing with device teardown. * Rather than use a lock to serialize removal from the client_data and * getting a new reference, we use an RCU grace period. The destruction * path removes the device from client_data and then waits for all RCU * readers to finish. * * A new connection can get NULL from this if its arriving on a * device that is in the process of being removed. */ struct rds_ib_device *rds_ib_get_client_data(struct ib_device *device) { struct rds_ib_device *rds_ibdev; rcu_read_lock(); rds_ibdev = ib_get_client_data(device, &rds_ib_client); if (rds_ibdev) refcount_inc(&rds_ibdev->refcount); rcu_read_unlock(); return rds_ibdev; } /* * The IB stack is letting us know that a device is going away. This can * happen if the underlying HCA driver is removed or if PCI hotplug is removing * the pci function, for example. * * This can be called at any time and can be racing with any other RDS path. */ static void rds_ib_remove_one(struct ib_device *device, void *client_data) { struct rds_ib_device *rds_ibdev = client_data; rds_ib_dev_shutdown(rds_ibdev); /* stop connection attempts from getting a reference to this device. */ ib_set_client_data(device, &rds_ib_client, NULL); down_write(&rds_ib_devices_lock); list_del_rcu(&rds_ibdev->list); up_write(&rds_ib_devices_lock); /* * This synchronize rcu is waiting for readers of both the ib * client data and the devices list to finish before we drop * both of those references. */ synchronize_rcu(); rds_ib_dev_put(rds_ibdev); rds_ib_dev_put(rds_ibdev); } struct ib_client rds_ib_client = { .name = "rds_ib", .add = rds_ib_add_one, .remove = rds_ib_remove_one }; static int rds_ib_conn_info_visitor(struct rds_connection *conn, void *buffer) { struct rds_info_rdma_connection *iinfo = buffer; struct rds_ib_connection *ic = conn->c_transport_data; /* We will only ever look at IB transports */ if (conn->c_trans != &rds_ib_transport) return 0; if (conn->c_isv6) return 0; iinfo->src_addr = conn->c_laddr.s6_addr32[3]; iinfo->dst_addr = conn->c_faddr.s6_addr32[3]; if (ic) { iinfo->tos = conn->c_tos; iinfo->sl = ic->i_sl; } memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid)); memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid)); if (rds_conn_state(conn) == RDS_CONN_UP) { struct rds_ib_device *rds_ibdev; rdma_read_gids(ic->i_cm_id, (union ib_gid *)&iinfo->src_gid, (union ib_gid *)&iinfo->dst_gid); rds_ibdev = ic->rds_ibdev; iinfo->max_send_wr = ic->i_send_ring.w_nr; iinfo->max_recv_wr = ic->i_recv_ring.w_nr; iinfo->max_send_sge = rds_ibdev->max_sge; rds_ib_get_mr_info(rds_ibdev, iinfo); iinfo->cache_allocs = atomic_read(&ic->i_cache_allocs); } return 1; } #if IS_ENABLED(CONFIG_IPV6) /* IPv6 version of rds_ib_conn_info_visitor(). */ static int rds6_ib_conn_info_visitor(struct rds_connection *conn, void *buffer) { struct rds6_info_rdma_connection *iinfo6 = buffer; struct rds_ib_connection *ic = conn->c_transport_data; /* We will only ever look at IB transports */ if (conn->c_trans != &rds_ib_transport) return 0; iinfo6->src_addr = conn->c_laddr; iinfo6->dst_addr = conn->c_faddr; if (ic) { iinfo6->tos = conn->c_tos; iinfo6->sl = ic->i_sl; } memset(&iinfo6->src_gid, 0, sizeof(iinfo6->src_gid)); memset(&iinfo6->dst_gid, 0, sizeof(iinfo6->dst_gid)); if (rds_conn_state(conn) == RDS_CONN_UP) { struct rds_ib_device *rds_ibdev; rdma_read_gids(ic->i_cm_id, (union ib_gid *)&iinfo6->src_gid, (union ib_gid *)&iinfo6->dst_gid); rds_ibdev = ic->rds_ibdev; iinfo6->max_send_wr = ic->i_send_ring.w_nr; iinfo6->max_recv_wr = ic->i_recv_ring.w_nr; iinfo6->max_send_sge = rds_ibdev->max_sge; rds6_ib_get_mr_info(rds_ibdev, iinfo6); iinfo6->cache_allocs = atomic_read(&ic->i_cache_allocs); } return 1; } #endif static void rds_ib_ic_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { u64 buffer[(sizeof(struct rds_info_rdma_connection) + 7) / 8]; rds_for_each_conn_info(sock, len, iter, lens, rds_ib_conn_info_visitor, buffer, sizeof(struct rds_info_rdma_connection)); } #if IS_ENABLED(CONFIG_IPV6) /* IPv6 version of rds_ib_ic_info(). */ static void rds6_ib_ic_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { u64 buffer[(sizeof(struct rds6_info_rdma_connection) + 7) / 8]; rds_for_each_conn_info(sock, len, iter, lens, rds6_ib_conn_info_visitor, buffer, sizeof(struct rds6_info_rdma_connection)); } #endif /* * Early RDS/IB was built to only bind to an address if there is an IPoIB * device with that address set. * * If it were me, I'd advocate for something more flexible. Sending and * receiving should be device-agnostic. Transports would try and maintain * connections between peers who have messages queued. Userspace would be * allowed to influence which paths have priority. We could call userspace * asserting this policy "routing". */ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr, __u32 scope_id) { int ret; struct rdma_cm_id *cm_id; #if IS_ENABLED(CONFIG_IPV6) struct sockaddr_in6 sin6; #endif struct sockaddr_in sin; struct sockaddr *sa; bool isv4; isv4 = ipv6_addr_v4mapped(addr); /* Create a CMA ID and try to bind it. This catches both * IB and iWARP capable NICs. */ cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, NULL, RDMA_PS_TCP, IB_QPT_RC); if (IS_ERR(cm_id)) return PTR_ERR(cm_id); if (isv4) { memset(&sin, 0, sizeof(sin)); sin.sin_family = AF_INET; sin.sin_addr.s_addr = addr->s6_addr32[3]; sa = (struct sockaddr *)&sin; } else { #if IS_ENABLED(CONFIG_IPV6) memset(&sin6, 0, sizeof(sin6)); sin6.sin6_family = AF_INET6; sin6.sin6_addr = *addr; sin6.sin6_scope_id = scope_id; sa = (struct sockaddr *)&sin6; /* XXX Do a special IPv6 link local address check here. The * reason is that rdma_bind_addr() always succeeds with IPv6 * link local address regardless it is indeed configured in a * system. */ if (ipv6_addr_type(addr) & IPV6_ADDR_LINKLOCAL) { struct net_device *dev; if (scope_id == 0) { ret = -EADDRNOTAVAIL; goto out; } /* Use init_net for now as RDS is not network * name space aware. */ dev = dev_get_by_index(&init_net, scope_id); if (!dev) { ret = -EADDRNOTAVAIL; goto out; } if (!ipv6_chk_addr(&init_net, addr, dev, 1)) { dev_put(dev); ret = -EADDRNOTAVAIL; goto out; } dev_put(dev); } #else ret = -EADDRNOTAVAIL; goto out; #endif } /* rdma_bind_addr will only succeed for IB & iWARP devices */ ret = rdma_bind_addr(cm_id, sa); /* due to this, we will claim to support iWARP devices unless we check node_type. */ if (ret || !cm_id->device || cm_id->device->node_type != RDMA_NODE_IB_CA) ret = -EADDRNOTAVAIL; rdsdebug("addr %pI6c%%%u ret %d node type %d\n", addr, scope_id, ret, cm_id->device ? cm_id->device->node_type : -1); out: rdma_destroy_id(cm_id); return ret; } static void rds_ib_unregister_client(void) { ib_unregister_client(&rds_ib_client); /* wait for rds_ib_dev_free() to complete */ flush_workqueue(rds_wq); } static void rds_ib_set_unloading(void) { atomic_set(&rds_ib_unloading, 1); } static bool rds_ib_is_unloading(struct rds_connection *conn) { struct rds_conn_path *cp = &conn->c_path[0]; return (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags) || atomic_read(&rds_ib_unloading) != 0); } void rds_ib_exit(void) { rds_ib_set_unloading(); synchronize_rcu(); rds_info_deregister_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info); #if IS_ENABLED(CONFIG_IPV6) rds_info_deregister_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info); #endif rds_ib_unregister_client(); rds_ib_destroy_nodev_conns(); rds_ib_sysctl_exit(); rds_ib_recv_exit(); rds_trans_unregister(&rds_ib_transport); rds_ib_mr_exit(); } static u8 rds_ib_get_tos_map(u8 tos) { /* 1:1 user to transport map for RDMA transport. * In future, if custom map is desired, hook can export * user configurable map. */ return tos; } struct rds_transport rds_ib_transport = { .laddr_check = rds_ib_laddr_check, .xmit_path_complete = rds_ib_xmit_path_complete, .xmit = rds_ib_xmit, .xmit_rdma = rds_ib_xmit_rdma, .xmit_atomic = rds_ib_xmit_atomic, .recv_path = rds_ib_recv_path, .conn_alloc = rds_ib_conn_alloc, .conn_free = rds_ib_conn_free, .conn_path_connect = rds_ib_conn_path_connect, .conn_path_shutdown = rds_ib_conn_path_shutdown, .inc_copy_to_user = rds_ib_inc_copy_to_user, .inc_free = rds_ib_inc_free, .cm_initiate_connect = rds_ib_cm_initiate_connect, .cm_handle_connect = rds_ib_cm_handle_connect, .cm_connect_complete = rds_ib_cm_connect_complete, .stats_info_copy = rds_ib_stats_info_copy, .exit = rds_ib_exit, .get_mr = rds_ib_get_mr, .sync_mr = rds_ib_sync_mr, .free_mr = rds_ib_free_mr, .flush_mrs = rds_ib_flush_mrs, .get_tos_map = rds_ib_get_tos_map, .t_owner = THIS_MODULE, .t_name = "infiniband", .t_unloading = rds_ib_is_unloading, .t_type = RDS_TRANS_IB }; int rds_ib_init(void) { int ret; INIT_LIST_HEAD(&rds_ib_devices); ret = rds_ib_mr_init(); if (ret) goto out; ret = ib_register_client(&rds_ib_client); if (ret) goto out_mr_exit; ret = rds_ib_sysctl_init(); if (ret) goto out_ibreg; ret = rds_ib_recv_init(); if (ret) goto out_sysctl; rds_trans_register(&rds_ib_transport); rds_info_register_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info); #if IS_ENABLED(CONFIG_IPV6) rds_info_register_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info); #endif goto out; out_sysctl: rds_ib_sysctl_exit(); out_ibreg: rds_ib_unregister_client(); out_mr_exit: rds_ib_mr_exit(); out: return ret; } MODULE_LICENSE("GPL"); |
| 26 25 26 26 26 26 26 26 5 5 5 5 5 5 5 5 4 6 6 5 5 4 4 5 3 6 6 6 4 4 4 4 4 48 28 4 26 26 26 25 26 2 25 24 24 24 24 6 5 6 5 1 2 26 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/dev_addr_lists.c - Functions for handling net device lists * Copyright (c) 2010 Jiri Pirko <jpirko@redhat.com> * * This file contains functions for working with unicast, multicast and device * addresses lists. */ #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/export.h> #include <linux/list.h> #include "dev.h" /* * General list handling functions */ static int __hw_addr_insert(struct netdev_hw_addr_list *list, struct netdev_hw_addr *new, int addr_len) { struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; while (*ins_point) { int diff; ha = rb_entry(*ins_point, struct netdev_hw_addr, node); diff = memcmp(new->addr, ha->addr, addr_len); if (diff == 0) diff = memcmp(&new->type, &ha->type, sizeof(new->type)); parent = *ins_point; if (diff < 0) ins_point = &parent->rb_left; else if (diff > 0) ins_point = &parent->rb_right; else return -EEXIST; } rb_link_node_rcu(&new->node, parent, ins_point); rb_insert_color(&new->node, &list->tree); return 0; } static struct netdev_hw_addr* __hw_addr_create(const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha; int alloc_size; alloc_size = sizeof(*ha); if (alloc_size < L1_CACHE_BYTES) alloc_size = L1_CACHE_BYTES; ha = kmalloc(alloc_size, GFP_ATOMIC); if (!ha) return NULL; memcpy(ha->addr, addr, addr_len); ha->type = addr_type; ha->refcount = 1; ha->global_use = global; ha->synced = sync ? 1 : 0; ha->sync_cnt = 0; return ha; } static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync, int sync_count, bool exclusive) { struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; if (addr_len > MAX_ADDR_LEN) return -EINVAL; while (*ins_point) { int diff; ha = rb_entry(*ins_point, struct netdev_hw_addr, node); diff = memcmp(addr, ha->addr, addr_len); if (diff == 0) diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); parent = *ins_point; if (diff < 0) { ins_point = &parent->rb_left; } else if (diff > 0) { ins_point = &parent->rb_right; } else { if (exclusive) return -EEXIST; if (global) { /* check if addr is already used as global */ if (ha->global_use) return 0; else ha->global_use = true; } if (sync) { if (ha->synced && sync_count) return -EEXIST; else ha->synced++; } ha->refcount++; return 0; } } ha = __hw_addr_create(addr, addr_len, addr_type, global, sync); if (!ha) return -ENOMEM; rb_link_node(&ha->node, parent, ins_point); rb_insert_color(&ha->node, &list->tree); list_add_tail_rcu(&ha->list, &list->list); list->count++; return 0; } static int __hw_addr_add(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, 0, false); } static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, struct netdev_hw_addr *ha, bool global, bool sync) { if (global && !ha->global_use) return -ENOENT; if (sync && !ha->synced) return -ENOENT; if (global) ha->global_use = false; if (sync) ha->synced--; if (--ha->refcount) return 0; rb_erase(&ha->node, &list->tree); list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); list->count--; return 0; } static struct netdev_hw_addr *__hw_addr_lookup(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { struct rb_node *node; node = list->tree.rb_node; while (node) { struct netdev_hw_addr *ha = rb_entry(node, struct netdev_hw_addr, node); int diff = memcmp(addr, ha->addr, addr_len); if (diff == 0 && addr_type) diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); if (diff < 0) node = node->rb_left; else if (diff > 0) node = node->rb_right; else return ha; } return NULL; } static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha = __hw_addr_lookup(list, addr, addr_len, addr_type); if (!ha) return -ENOENT; return __hw_addr_del_entry(list, ha, global, sync); } static int __hw_addr_del(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { return __hw_addr_del_ex(list, addr, addr_len, addr_type, false, false); } static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr *ha, int addr_len) { int err; err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, false, true, ha->sync_cnt, false); if (err && err != -EEXIST) return err; if (!err) { ha->sync_cnt++; ha->refcount++; } return 0; } static void __hw_addr_unsync_one(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, struct netdev_hw_addr *ha, int addr_len) { int err; err = __hw_addr_del_ex(to_list, ha->addr, addr_len, ha->type, false, true); if (err) return; ha->sync_cnt--; /* address on from list is not marked synced */ __hw_addr_del_entry(from_list, ha, false, false); } static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (ha->sync_cnt == ha->refcount) { __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } else { err = __hw_addr_sync_one(to_list, ha, addr_len); if (err) break; } } return err; } /* This function only works where there is a strict 1-1 relationship * between source and destination of they synch. If you ever need to * sync addresses to more then 1 destination, you need to use * __hw_addr_sync_multiple(). */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (!ha->sync_cnt) { err = __hw_addr_sync_one(to_list, ha, addr_len); if (err) break; } else if (ha->refcount == 1) __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } return err; } EXPORT_SYMBOL(__hw_addr_sync); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (ha->sync_cnt) __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } } EXPORT_SYMBOL(__hw_addr_unsync); /** * __hw_addr_sync_dev - Synchronize device's multicast list * @list: address list to synchronize * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed * * This function is intended to be called from the ndo_set_rx_mode * function of devices that require explicit address add/remove * notifications. The unsync function may be NULL in which case * the addresses requiring removal will simply be removed without * any notification to the device. **/ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)) { struct netdev_hw_addr *ha, *tmp; int err; /* first go through and flush out any stale entries */ list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt || ha->refcount != 1) continue; /* if unsync is defined and fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr)) continue; ha->sync_cnt--; __hw_addr_del_entry(list, ha, false, false); } /* go through and sync new entries to the list */ list_for_each_entry_safe(ha, tmp, &list->list, list) { if (ha->sync_cnt) continue; err = sync(dev, ha->addr); if (err) return err; ha->sync_cnt++; ha->refcount++; } return 0; } EXPORT_SYMBOL(__hw_addr_sync_dev); /** * __hw_addr_ref_sync_dev - Synchronize device's multicast address list taking * into account references * @list: address list to synchronize * @dev: device to sync * @sync: function to call if address or reference on it should be added * @unsync: function to call if address or some reference on it should removed * * This function is intended to be called from the ndo_set_rx_mode * function of devices that require explicit address or references on it * add/remove notifications. The unsync function may be NULL in which case * the addresses or references on it requiring removal will simply be * removed without any notification to the device. That is responsibility of * the driver to identify and distribute address or references on it between * internal address tables. **/ int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *, int), int (*unsync)(struct net_device *, const unsigned char *, int)) { struct netdev_hw_addr *ha, *tmp; int err, ref_cnt; /* first go through and flush out any unsynced/stale entries */ list_for_each_entry_safe(ha, tmp, &list->list, list) { /* sync if address is not used */ if ((ha->sync_cnt << 1) <= ha->refcount) continue; /* if fails defer unsyncing address */ ref_cnt = ha->refcount - ha->sync_cnt; if (unsync && unsync(dev, ha->addr, ref_cnt)) continue; ha->refcount = (ref_cnt << 1) + 1; ha->sync_cnt = ref_cnt; __hw_addr_del_entry(list, ha, false, false); } /* go through and sync updated/new entries to the list */ list_for_each_entry_safe(ha, tmp, &list->list, list) { /* sync if address added or reused */ if ((ha->sync_cnt << 1) >= ha->refcount) continue; ref_cnt = ha->refcount - ha->sync_cnt; err = sync(dev, ha->addr, ref_cnt); if (err) return err; ha->refcount = ref_cnt << 1; ha->sync_cnt = ref_cnt; } return 0; } EXPORT_SYMBOL(__hw_addr_ref_sync_dev); /** * __hw_addr_ref_unsync_dev - Remove synchronized addresses and references on * it from device * @list: address list to remove synchronized addresses (references on it) from * @dev: device to sync * @unsync: function to call if address and references on it should be removed * * Remove all addresses that were added to the device by * __hw_addr_ref_sync_dev(). This function is intended to be called from the * ndo_stop or ndo_open functions on devices that require explicit address (or * references on it) add/remove notifications. If the unsync function pointer * is NULL then this function can be used to just reset the sync_cnt for the * addresses in the list. **/ void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *, int)) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt) continue; /* if fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr, ha->sync_cnt)) continue; ha->refcount -= ha->sync_cnt - 1; ha->sync_cnt = 0; __hw_addr_del_entry(list, ha, false, false); } } EXPORT_SYMBOL(__hw_addr_ref_unsync_dev); /** * __hw_addr_unsync_dev - Remove synchronized addresses from device * @list: address list to remove synchronized addresses from * @dev: device to sync * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by __hw_addr_sync_dev(). * This function is intended to be called from the ndo_stop or ndo_open * functions on devices that require explicit address add/remove * notifications. If the unsync function pointer is NULL then this function * can be used to just reset the sync_cnt for the addresses in the list. **/ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt) continue; /* if unsync is defined and fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr)) continue; ha->sync_cnt--; __hw_addr_del_entry(list, ha, false, false); } } EXPORT_SYMBOL(__hw_addr_unsync_dev); static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; list->tree = RB_ROOT; list_for_each_entry_safe(ha, tmp, &list->list, list) { list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); } list->count = 0; } void __hw_addr_init(struct netdev_hw_addr_list *list) { INIT_LIST_HEAD(&list->list); list->count = 0; list->tree = RB_ROOT; } EXPORT_SYMBOL(__hw_addr_init); /* * Device addresses handling functions */ /* Check that netdev->dev_addr is not written to directly as this would * break the rbtree layout. All changes should go thru dev_addr_set() and co. * Remove this check in mid-2024. */ void dev_addr_check(struct net_device *dev) { if (!memcmp(dev->dev_addr, dev->dev_addr_shadow, MAX_ADDR_LEN)) return; netdev_warn(dev, "Current addr: %*ph\n", MAX_ADDR_LEN, dev->dev_addr); netdev_warn(dev, "Expected addr: %*ph\n", MAX_ADDR_LEN, dev->dev_addr_shadow); netdev_WARN(dev, "Incorrect netdev->dev_addr\n"); } /** * dev_addr_flush - Flush device address list * @dev: device * * Flush device address list and reset ->dev_addr. * * The caller must hold the rtnl_mutex. */ void dev_addr_flush(struct net_device *dev) { /* rtnl_mutex must be held here */ dev_addr_check(dev); __hw_addr_flush(&dev->dev_addrs); dev->dev_addr = NULL; } /** * dev_addr_init - Init device address list * @dev: device * * Init device address list and create the first element, * used by ->dev_addr. * * The caller must hold the rtnl_mutex. */ int dev_addr_init(struct net_device *dev) { unsigned char addr[MAX_ADDR_LEN]; struct netdev_hw_addr *ha; int err; /* rtnl_mutex must be held here */ __hw_addr_init(&dev->dev_addrs); memset(addr, 0, sizeof(addr)); err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr), NETDEV_HW_ADDR_T_LAN); if (!err) { /* * Get the first (previously created) address from the list * and set dev_addr pointer to this location. */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); dev->dev_addr = ha->addr; } return err; } void dev_addr_mod(struct net_device *dev, unsigned int offset, const void *addr, size_t len) { struct netdev_hw_addr *ha; dev_addr_check(dev); ha = container_of(dev->dev_addr, struct netdev_hw_addr, addr[0]); rb_erase(&ha->node, &dev->dev_addrs.tree); memcpy(&ha->addr[offset], addr, len); memcpy(&dev->dev_addr_shadow[offset], addr, len); WARN_ON(__hw_addr_insert(&dev->dev_addrs, ha, dev->addr_len)); } EXPORT_SYMBOL(dev_addr_mod); /** * dev_addr_add - Add a device address * @dev: device * @addr: address to add * @addr_type: address type * * Add a device address to the device or increase the reference count if * it already exists. * * The caller must hold the rtnl_mutex. */ int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; ASSERT_RTNL(); err = dev_pre_changeaddr_notify(dev, addr, NULL); if (err) return err; err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } EXPORT_SYMBOL(dev_addr_add); /** * dev_addr_del - Release a device address. * @dev: device * @addr: address to delete * @addr_type: address type * * Release reference to a device address and remove it from the device * if the reference count drops to zero. * * The caller must hold the rtnl_mutex. */ int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; struct netdev_hw_addr *ha; ASSERT_RTNL(); /* * We can not remove the first address from the list because * dev->dev_addr points to that. */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); if (!memcmp(ha->addr, addr, dev->addr_len) && ha->type == addr_type && ha->refcount == 1) return -ENOENT; err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } EXPORT_SYMBOL(dev_addr_del); /* * Unicast list handling functions */ /** * dev_uc_add_excl - Add a global secondary unicast address * @dev: device * @addr: address to add */ int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST, true, false, 0, true); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_add_excl); /** * dev_uc_add - Add a secondary unicast address * @dev: device * @addr: address to add * * Add a secondary unicast address to the device or increase * the reference count if it already exists. */ int dev_uc_add(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_add); /** * dev_uc_del - Release secondary unicast address. * @dev: device * @addr: address to delete * * Release reference to a secondary unicast address and remove it * from the device if the reference count drops to zero. */ int dev_uc_del(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_del(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_del); /** * dev_uc_sync - Synchronize device's unicast list to another device * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. This function assumes that * addresses will only ever be synced to the @to devices and no other. */ int dev_uc_sync(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync); /** * dev_uc_sync_multiple - Synchronize device's unicast list to another * device, but allow for multiple calls to sync to multiple devices. * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have been deleted from the source. The source device * must be locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. It allows for a single source * device to be synced to multiple destination devices. */ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync_multiple); /** * dev_uc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device * * Remove all addresses that were added to the destination device by * dev_uc_sync(). This function is intended to be called from the * dev->stop function of layered software devices. */ void dev_uc_unsync(struct net_device *to, struct net_device *from) { if (to->addr_len != from->addr_len) return; /* netif_addr_lock_bh() uses lockdep subclass 0, this is okay for two * reasons: * 1) This is always called without any addr_list_lock, so as the * outermost one here, it must be 0. * 2) This is called by some callers after unlinking the upper device, * so the dev->lower_level becomes 1 again. * Therefore, the subclass for 'from' is 0, for 'to' is either 1 or * larger. */ netif_addr_lock_bh(from); netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_uc_unsync); /** * dev_uc_flush - Flush unicast addresses * @dev: device * * Flush unicast addresses. */ void dev_uc_flush(struct net_device *dev) { netif_addr_lock_bh(dev); __hw_addr_flush(&dev->uc); netif_addr_unlock_bh(dev); } EXPORT_SYMBOL(dev_uc_flush); /** * dev_uc_init - Init unicast address list * @dev: device * * Init unicast address list. */ void dev_uc_init(struct net_device *dev) { __hw_addr_init(&dev->uc); } EXPORT_SYMBOL(dev_uc_init); /* * Multicast list handling functions */ /** * dev_mc_add_excl - Add a global secondary multicast address * @dev: device * @addr: address to add */ int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, true, false, 0, true); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_mc_add_excl); static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, global, false, 0, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } /** * dev_mc_add - Add a multicast address * @dev: device * @addr: address to add * * Add a multicast address to the device or increase * the reference count if it already exists. */ int dev_mc_add(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, false); } EXPORT_SYMBOL(dev_mc_add); /** * dev_mc_add_global - Add a global multicast address * @dev: device * @addr: address to add * * Add a global multicast address to the device. */ int dev_mc_add_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, true); } EXPORT_SYMBOL(dev_mc_add_global); static int __dev_mc_del(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, global, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } /** * dev_mc_del - Delete a multicast address. * @dev: device * @addr: address to delete * * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ int dev_mc_del(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, false); } EXPORT_SYMBOL(dev_mc_del); /** * dev_mc_del_global - Delete a global multicast address. * @dev: device * @addr: address to delete * * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ int dev_mc_del_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, true); } EXPORT_SYMBOL(dev_mc_del_global); /** * dev_mc_sync - Synchronize device's multicast list to another device * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the ndo_set_rx_mode * function of layered software devices. */ int dev_mc_sync(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync); /** * dev_mc_sync_multiple - Synchronize device's multicast list to another * device, but allow for multiple calls to sync to multiple devices. * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the ndo_set_rx_mode * function of layered software devices. It allows for a single * source device to be synced to multiple destination devices. */ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync_multiple); /** * dev_mc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device * * Remove all addresses that were added to the destination device by * dev_mc_sync(). This function is intended to be called from the * dev->stop function of layered software devices. */ void dev_mc_unsync(struct net_device *to, struct net_device *from) { if (to->addr_len != from->addr_len) return; /* See the above comments inside dev_uc_unsync(). */ netif_addr_lock_bh(from); netif_addr_lock(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_mc_unsync); /** * dev_mc_flush - Flush multicast addresses * @dev: device * * Flush multicast addresses. */ void dev_mc_flush(struct net_device *dev) { netif_addr_lock_bh(dev); __hw_addr_flush(&dev->mc); netif_addr_unlock_bh(dev); } EXPORT_SYMBOL(dev_mc_flush); /** * dev_mc_init - Init multicast address list * @dev: device * * Init multicast address list. */ void dev_mc_init(struct net_device *dev) { __hw_addr_init(&dev->mc); } EXPORT_SYMBOL(dev_mc_init); |
| 1580 22 1583 10 3 3 1572 10 10 10 10 10 10 10 10 10 10 10 10 10 9 8 10 8 8 10 10 10 10 10 9 10 10 22 8 8 8 8 8 8 8 8 2 2 2 2 2 2 911 909 22 22 22 22 10 22 13 22 22 10 22 22 22 22 22 22 22 3 3 22 22 22 22 1571 1571 1565 1569 1566 1570 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Common Block IO controller cgroup interface * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> * * For policy-specific per-blkcg data: * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it> * Arianna Avanzini <avanzini.arianna@gmail.com> */ #include <linux/ioprio.h> #include <linux/kdev_t.h> #include <linux/module.h> #include <linux/sched/signal.h> #include <linux/err.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/slab.h> #include <linux/delay.h> #include <linux/atomic.h> #include <linux/ctype.h> #include <linux/resume_user_mode.h> #include <linux/psi.h> #include <linux/part_stat.h> #include "blk.h" #include "blk-cgroup.h" #include "blk-ioprio.h" #include "blk-throttle.h" static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu); /* * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation. * blkcg_pol_register_mutex nests outside of it and synchronizes entire * policy [un]register operations including cgroup file additions / * removals. Putting cgroup file registration outside blkcg_pol_mutex * allows grabbing it from cgroup callbacks. */ static DEFINE_MUTEX(blkcg_pol_register_mutex); static DEFINE_MUTEX(blkcg_pol_mutex); struct blkcg blkcg_root; EXPORT_SYMBOL_GPL(blkcg_root); struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css; EXPORT_SYMBOL_GPL(blkcg_root_css); static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ bool blkcg_debug_stats = false; static DEFINE_RAW_SPINLOCK(blkg_stat_lock); #define BLKG_DESTROY_BATCH_SIZE 64 /* * Lockless lists for tracking IO stats update * * New IO stats are stored in the percpu iostat_cpu within blkcg_gq (blkg). * There are multiple blkg's (one for each block device) attached to each * blkcg. The rstat code keeps track of which cpu has IO stats updated, * but it doesn't know which blkg has the updated stats. If there are many * block devices in a system, the cost of iterating all the blkg's to flush * out the IO stats can be high. To reduce such overhead, a set of percpu * lockless lists (lhead) per blkcg are used to track the set of recently * updated iostat_cpu's since the last flush. An iostat_cpu will be put * onto the lockless list on the update side [blk_cgroup_bio_start()] if * not there yet and then removed when being flushed [blkcg_rstat_flush()]. * References to blkg are gotten and then put back in the process to * protect against blkg removal. * * Return: 0 if successful or -ENOMEM if allocation fails. */ static int init_blkcg_llists(struct blkcg *blkcg) { int cpu; blkcg->lhead = alloc_percpu_gfp(struct llist_head, GFP_KERNEL); if (!blkcg->lhead) return -ENOMEM; for_each_possible_cpu(cpu) init_llist_head(per_cpu_ptr(blkcg->lhead, cpu)); return 0; } /** * blkcg_css - find the current css * * Find the css associated with either the kthread or the current task. * This may return a dying css, so it is up to the caller to use tryget logic * to confirm it is alive and well. */ static struct cgroup_subsys_state *blkcg_css(void) { struct cgroup_subsys_state *css; css = kthread_blkcg(); if (css) return css; return task_css(current, io_cgrp_id); } static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) { return pol && test_bit(pol->plid, q->blkcg_pols); } static void blkg_free_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, free_work); struct request_queue *q = blkg->q; int i; /* * pd_free_fn() can also be called from blkcg_deactivate_policy(), * in order to make sure pd_free_fn() is called in order, the deletion * of the list blkg->q_node is delayed to here from blkg_destroy(), and * blkcg_mutex is used to synchronize blkg_free_workfn() and * blkcg_deactivate_policy(). */ mutex_lock(&q->blkcg_mutex); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); if (blkg->parent) blkg_put(blkg->parent); spin_lock_irq(&q->queue_lock); list_del_init(&blkg->q_node); spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); blk_put_queue(q); free_percpu(blkg->iostat_cpu); percpu_ref_exit(&blkg->refcnt); kfree(blkg); } /** * blkg_free - free a blkg * @blkg: blkg to free * * Free @blkg which may be partially allocated. */ static void blkg_free(struct blkcg_gq *blkg) { if (!blkg) return; /* * Both ->pd_free_fn() and request queue's release handler may * sleep, so free us by scheduling one work func */ INIT_WORK(&blkg->free_work, blkg_free_workfn); schedule_work(&blkg->free_work); } static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); struct blkcg *blkcg = blkg->blkcg; int cpu; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO WARN_ON(!bio_list_empty(&blkg->async_bios)); #endif /* * Flush all the non-empty percpu lockless lists before releasing * us, given these stat belongs to us. * * blkg_stat_lock is for serializing blkg stat update */ for_each_possible_cpu(cpu) __blkcg_rstat_flush(blkcg, cpu); /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); blkg_free(blkg); } /* * A group is RCU protected, but having an rcu lock does not mean that one * can access all the fields of blkg and assume these are valid. For * example, don't try to follow throtl_data and request queue links. * * Having a reference to blkg under an rcu allows accesses to only values * local to groups like group stats and group rate limits. */ static void blkg_release(struct percpu_ref *ref) { struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); call_rcu(&blkg->rcu_head, __blkg_release); } #ifdef CONFIG_BLK_CGROUP_PUNT_BIO static struct workqueue_struct *blkcg_punt_bio_wq; static void blkg_async_bio_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, async_bio_work); struct bio_list bios = BIO_EMPTY_LIST; struct bio *bio; struct blk_plug plug; bool need_plug = false; /* as long as there are pending bios, @blkg can't go away */ spin_lock(&blkg->async_bio_lock); bio_list_merge_init(&bios, &blkg->async_bios); spin_unlock(&blkg->async_bio_lock); /* start plug only when bio_list contains at least 2 bios */ if (bios.head && bios.head->bi_next) { need_plug = true; blk_start_plug(&plug); } while ((bio = bio_list_pop(&bios))) submit_bio(bio); if (need_plug) blk_finish_plug(&plug); } /* * When a shared kthread issues a bio for a cgroup, doing so synchronously can * lead to priority inversions as the kthread can be trapped waiting for that * cgroup. Use this helper instead of submit_bio to punt the actual issuing to * a dedicated per-blkcg work item to avoid such priority inversions. */ void blkcg_punt_bio_submit(struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; if (blkg->parent) { spin_lock(&blkg->async_bio_lock); bio_list_add(&blkg->async_bios, bio); spin_unlock(&blkg->async_bio_lock); queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work); } else { /* never bounce for the root cgroup */ submit_bio(bio); } } EXPORT_SYMBOL_GPL(blkcg_punt_bio_submit); static int __init blkcg_punt_bio_init(void) { blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND | WQ_SYSFS, 0); if (!blkcg_punt_bio_wq) return -ENOMEM; return 0; } subsys_initcall(blkcg_punt_bio_init); #endif /* CONFIG_BLK_CGROUP_PUNT_BIO */ /** * bio_blkcg_css - return the blkcg CSS associated with a bio * @bio: target bio * * This returns the CSS for the blkcg associated with a bio, or %NULL if not * associated. Callers are expected to either handle %NULL or know association * has been done prior to calling this. */ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { if (!bio || !bio->bi_blkg) return NULL; return &bio->bi_blkg->blkcg->css; } EXPORT_SYMBOL_GPL(bio_blkcg_css); /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest * * Return the parent blkcg of @blkcg. Can be called anytime. */ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) { return css_to_blkcg(blkcg->css.parent); } /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with * @disk: gendisk the new blkg is associated with * @gfp_mask: allocation mask to use * * Allocate a new blkg associating @blkcg and @disk. */ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, gfp_t gfp_mask) { struct blkcg_gq *blkg; int i, cpu; /* alloc and init base part */ blkg = kzalloc_node(sizeof(*blkg), gfp_mask, disk->queue->node); if (!blkg) return NULL; if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) goto out_free_blkg; blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask); if (!blkg->iostat_cpu) goto out_exit_refcnt; if (!blk_get_queue(disk->queue)) goto out_free_iostat; blkg->q = disk->queue; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; blkg->iostat.blkg = blkg; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); #endif u64_stats_init(&blkg->iostat.sync); for_each_possible_cpu(cpu) { u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync); per_cpu_ptr(blkg->iostat_cpu, cpu)->blkg = blkg; } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; if (!blkcg_policy_enabled(disk->queue, pol)) continue; /* alloc per-policy data and attach it to blkg */ pd = pol->pd_alloc_fn(disk, blkcg, gfp_mask); if (!pd) goto out_free_pds; blkg->pd[i] = pd; pd->blkg = blkg; pd->plid = i; pd->online = false; } return blkg; out_free_pds: while (--i >= 0) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); blk_put_queue(disk->queue); out_free_iostat: free_percpu(blkg->iostat_cpu); out_exit_refcnt: percpu_ref_exit(&blkg->refcnt); out_free_blkg: kfree(blkg); return NULL; } /* * If @new_blkg is %NULL, this function tries to allocate a new one as * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return. */ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, struct blkcg_gq *new_blkg) { struct blkcg_gq *blkg; int i, ret; lockdep_assert_held(&disk->queue->queue_lock); /* request_queue is dying, do not create/recreate a blkg */ if (blk_queue_dying(disk->queue)) { ret = -ENODEV; goto err_free_blkg; } /* blkg holds a reference to blkcg */ if (!css_tryget_online(&blkcg->css)) { ret = -ENODEV; goto err_free_blkg; } /* allocate */ if (!new_blkg) { new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto err_put_css; } } blkg = new_blkg; /* link parent */ if (blkcg_parent(blkcg)) { blkg->parent = blkg_lookup(blkcg_parent(blkcg), disk->queue); if (WARN_ON_ONCE(!blkg->parent)) { ret = -ENODEV; goto err_put_css; } blkg_get(blkg->parent); } /* invoke per-policy init */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_init_fn) pol->pd_init_fn(blkg->pd[i]); } /* insert */ spin_lock(&blkcg->lock); ret = radix_tree_insert(&blkcg->blkg_tree, disk->queue->id, blkg); if (likely(!ret)) { hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list); list_add(&blkg->q_node, &disk->queue->blkg_list); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i]) { if (pol->pd_online_fn) pol->pd_online_fn(blkg->pd[i]); blkg->pd[i]->online = true; } } } blkg->online = true; spin_unlock(&blkcg->lock); if (!ret) return blkg; /* @blkg failed fully initialized, use the usual release path */ blkg_put(blkg); return ERR_PTR(ret); err_put_css: css_put(&blkcg->css); err_free_blkg: if (new_blkg) blkg_free(new_blkg); return ERR_PTR(ret); } /** * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @disk: gendisk of interest * * Lookup blkg for the @blkcg - @disk pair. If it doesn't exist, try to * create one. blkg creation is performed recursively from blkcg_root such * that all non-root blkg's have access to the parent blkg. This function * should be called under RCU read lock and takes @disk->queue->queue_lock. * * Returns the blkg or the closest blkg if blkg_create() fails as it walks * down from root. */ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; unsigned long flags; WARN_ON_ONCE(!rcu_read_lock_held()); blkg = blkg_lookup(blkcg, q); if (blkg) return blkg; spin_lock_irqsave(&q->queue_lock, flags); blkg = blkg_lookup(blkcg, q); if (blkg) { if (blkcg != &blkcg_root && blkg != rcu_dereference(blkcg->blkg_hint)) rcu_assign_pointer(blkcg->blkg_hint, blkg); goto found; } /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. Returns the closest * blkg to the intended blkg should blkg_create() fail. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent = blkcg_parent(blkcg); struct blkcg_gq *ret_blkg = q->root_blkg; while (parent) { blkg = blkg_lookup(parent, q); if (blkg) { /* remember closest blkg */ ret_blkg = blkg; break; } pos = parent; parent = blkcg_parent(parent); } blkg = blkg_create(pos, disk, NULL); if (IS_ERR(blkg)) { blkg = ret_blkg; break; } if (pos == blkcg) break; } found: spin_unlock_irqrestore(&q->queue_lock, flags); return blkg; } static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; int i; lockdep_assert_held(&blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); /* * blkg stays on the queue list until blkg_free_workfn(), see details in * blkg_free_workfn(), hence this function can be called from * blkcg_destroy_blkgs() first and again from blkg_destroy_all() before * blkg_free_workfn(). */ if (hlist_unhashed(&blkg->blkcg_node)) return; for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && blkg->pd[i]->online) { blkg->pd[i]->online = false; if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[i]); } } blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); hlist_del_init_rcu(&blkg->blkcg_node); /* * Both setting lookup hint to and clearing it from @blkg are done * under queue_lock. If it's not pointing to @blkg now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(blkcg->blkg_hint) == blkg) rcu_assign_pointer(blkcg->blkg_hint, NULL); /* * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ percpu_ref_kill(&blkg->refcnt); } static void blkg_destroy_all(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; int count = BLKG_DESTROY_BATCH_SIZE; int i; restart: spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; if (hlist_unhashed(&blkg->blkcg_node)) continue; spin_lock(&blkcg->lock); blkg_destroy(blkg); spin_unlock(&blkcg->lock); /* * in order to avoid holding the spin lock for too long, release * it when a batch of blkgs are destroyed. */ if (!(--count)) { count = BLKG_DESTROY_BATCH_SIZE; spin_unlock_irq(&q->queue_lock); cond_resched(); goto restart; } } /* * Mark policy deactivated since policy offline has been done, and * the free is scheduled, so future blkcg_deactivate_policy() can * be bypassed */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (pol) __clear_bit(pol->plid, q->blkcg_pols); } q->root_blkg = NULL; spin_unlock_irq(&q->queue_lock); } static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] = src->bytes[i]; dst->ios[i] = src->ios[i]; } } static void __blkg_clear_stat(struct blkg_iostat_set *bis) { struct blkg_iostat cur = {0}; unsigned long flags; flags = u64_stats_update_begin_irqsave(&bis->sync); blkg_iostat_set(&bis->cur, &cur); blkg_iostat_set(&bis->last, &cur); u64_stats_update_end_irqrestore(&bis->sync, flags); } static void blkg_clear_stat(struct blkcg_gq *blkg) { int cpu; for_each_possible_cpu(cpu) { struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu); __blkg_clear_stat(s); } __blkg_clear_stat(&blkg->iostat); } static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; int i; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); /* * Note that stat reset is racy - it doesn't synchronize against * stat updates. This is a debug feature which shouldn't exist * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { blkg_clear_stat(blkg); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_reset_stats_fn) pol->pd_reset_stats_fn(blkg->pd[i]); } } spin_unlock_irq(&blkcg->lock); mutex_unlock(&blkcg_pol_mutex); return 0; } const char *blkg_dev_name(struct blkcg_gq *blkg) { if (!blkg->q->disk) return NULL; return bdi_dev_name(blkg->q->disk->bdi); } /** * blkcg_print_blkgs - helper for printing per-blkg data * @sf: seq_file to print to * @blkcg: blkcg of interest * @prfill: fill function to print out a blkg * @pol: policy in question * @data: data to be passed to @prfill * @show_total: to print out sum of prfill return values or not * * This function invokes @prfill on each blkg of @blkcg if pd for the * policy specified by @pol exists. @prfill is invoked with @sf, the * policy data and @data and the matching queue lock held. If @show_total * is %true, the sum of the return values from @prfill is printed with * "Total" label at the end. * * This is to be used to construct print functions for * cftype->read_seq_string method. */ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total) { struct blkcg_gq *blkg; u64 total = 0; rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); if (blkcg_policy_enabled(blkg->q, pol)) total += prfill(sf, blkg->pd[pol->plid], data); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); if (show_total) seq_printf(sf, "Total %llu\n", (unsigned long long)total); } EXPORT_SYMBOL_GPL(blkcg_print_blkgs); /** * __blkg_prfill_u64 - prfill helper for a single u64 value * @sf: seq_file to print to * @pd: policy private data of interest * @v: value to print * * Print @v to @sf for the device associated with @pd. */ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) { const char *dname = blkg_dev_name(pd->blkg); if (!dname) return 0; seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v); return v; } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); /** * blkg_conf_init - initialize a blkg_conf_ctx * @ctx: blkg_conf_ctx to initialize * @input: input string * * Initialize @ctx which can be used to parse blkg config input string @input. * Once initialized, @ctx can be used with blkg_conf_open_bdev() and * blkg_conf_prep(), and must be cleaned up with blkg_conf_exit(). */ void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input) { *ctx = (struct blkg_conf_ctx){ .input = input }; } EXPORT_SYMBOL_GPL(blkg_conf_init); /** * blkg_conf_open_bdev - parse and open bdev for per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse the device node prefix part, MAJ:MIN, of per-blkg config update from * @ctx->input and get and store the matching bdev in @ctx->bdev. @ctx->body is * set to point past the device node prefix. * * This function may be called multiple times on @ctx and the extra calls become * NOOPs. blkg_conf_prep() implicitly calls this function. Use this function * explicitly if bdev access is needed without resolving the blkcg / policy part * of @ctx->input. Returns -errno on error. */ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx) { char *input = ctx->input; unsigned int major, minor; struct block_device *bdev; int key_len; if (ctx->bdev) return 0; if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2) return -EINVAL; input += key_len; if (!isspace(*input)) return -EINVAL; input = skip_spaces(input); bdev = blkdev_get_no_open(MKDEV(major, minor)); if (!bdev) return -ENODEV; if (bdev_is_partition(bdev)) { blkdev_put_no_open(bdev); return -ENODEV; } mutex_lock(&bdev->bd_queue->rq_qos_mutex); if (!disk_live(bdev->bd_disk)) { blkdev_put_no_open(bdev); mutex_unlock(&bdev->bd_queue->rq_qos_mutex); return -ENODEV; } ctx->body = input; ctx->bdev = bdev; return 0; } /** * blkg_conf_prep - parse and prepare for per-blkg config update * @blkcg: target block cgroup * @pol: target policy * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse per-blkg config update from @ctx->input and initialize @ctx * accordingly. On success, @ctx->body points to the part of @ctx->input * following MAJ:MIN, @ctx->bdev points to the target block device and * @ctx->blkg to the blkg being configured. * * blkg_conf_open_bdev() may be called on @ctx beforehand. On success, this * function returns with queue lock held and must be followed by * blkg_conf_exit(). */ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct blkg_conf_ctx *ctx) __acquires(&bdev->bd_queue->queue_lock) { struct gendisk *disk; struct request_queue *q; struct blkcg_gq *blkg; int ret; ret = blkg_conf_open_bdev(ctx); if (ret) return ret; disk = ctx->bdev->bd_disk; q = disk->queue; /* * blkcg_deactivate_policy() requires queue to be frozen, we can grab * q_usage_counter to prevent concurrent with blkcg_deactivate_policy(). */ ret = blk_queue_enter(q, 0); if (ret) goto fail; spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { ret = -EOPNOTSUPP; goto fail_unlock; } blkg = blkg_lookup(blkcg, q); if (blkg) goto success; /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent; struct blkcg_gq *new_blkg; parent = blkcg_parent(blkcg); while (parent && !blkg_lookup(parent, q)) { pos = parent; parent = blkcg_parent(parent); } /* Drop locks to do new blkg allocation with GFP_KERNEL. */ spin_unlock_irq(&q->queue_lock); new_blkg = blkg_alloc(pos, disk, GFP_KERNEL); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto fail_exit_queue; } if (radix_tree_preload(GFP_KERNEL)) { blkg_free(new_blkg); ret = -ENOMEM; goto fail_exit_queue; } spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { blkg_free(new_blkg); ret = -EOPNOTSUPP; goto fail_preloaded; } blkg = blkg_lookup(pos, q); if (blkg) { blkg_free(new_blkg); } else { blkg = blkg_create(pos, disk, new_blkg); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); goto fail_preloaded; } } radix_tree_preload_end(); if (pos == blkcg) goto success; } success: blk_queue_exit(q); ctx->blkg = blkg; return 0; fail_preloaded: radix_tree_preload_end(); fail_unlock: spin_unlock_irq(&q->queue_lock); fail_exit_queue: blk_queue_exit(q); fail: /* * If queue was bypassing, we should retry. Do so after a * short msleep(). It isn't strictly necessary but queue * can be bypassing for some time and it's always nice to * avoid busy looping. */ if (ret == -EBUSY) { msleep(10); ret = restart_syscall(); } return ret; } EXPORT_SYMBOL_GPL(blkg_conf_prep); /** * blkg_conf_exit - clean up per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Clean up after per-blkg config update. This function must be called on all * blkg_conf_ctx's initialized with blkg_conf_init(). */ void blkg_conf_exit(struct blkg_conf_ctx *ctx) __releases(&ctx->bdev->bd_queue->queue_lock) __releases(&ctx->bdev->bd_queue->rq_qos_mutex) { if (ctx->blkg) { spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock); ctx->blkg = NULL; } if (ctx->bdev) { mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); blkdev_put_no_open(ctx->bdev); ctx->body = NULL; ctx->bdev = NULL; } } EXPORT_SYMBOL_GPL(blkg_conf_exit); static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] += src->bytes[i]; dst->ios[i] += src->ios[i]; } } static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] -= src->bytes[i]; dst->ios[i] -= src->ios[i]; } } static void blkcg_iostat_update(struct blkcg_gq *blkg, struct blkg_iostat *cur, struct blkg_iostat *last) { struct blkg_iostat delta; unsigned long flags; /* propagate percpu delta to global */ flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&delta, cur); blkg_iostat_sub(&delta, last); blkg_iostat_add(&blkg->iostat.cur, &delta); blkg_iostat_add(last, &delta); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) { struct llist_head *lhead = per_cpu_ptr(blkcg->lhead, cpu); struct llist_node *lnode; struct blkg_iostat_set *bisc, *next_bisc; unsigned long flags; rcu_read_lock(); lnode = llist_del_all(lhead); if (!lnode) goto out; /* * For covering concurrent parent blkg update from blkg_release(). * * When flushing from cgroup, cgroup_rstat_lock is always held, so * this lock won't cause contention most of time. */ raw_spin_lock_irqsave(&blkg_stat_lock, flags); /* * Iterate only the iostat_cpu's queued in the lockless list. */ llist_for_each_entry_safe(bisc, next_bisc, lnode, lnode) { struct blkcg_gq *blkg = bisc->blkg; struct blkcg_gq *parent = blkg->parent; struct blkg_iostat cur; unsigned int seq; /* * Order assignment of `next_bisc` from `bisc->lnode.next` in * llist_for_each_entry_safe and clearing `bisc->lqueued` for * avoiding to assign `next_bisc` with new next pointer added * in blk_cgroup_bio_start() in case of re-ordering. * * The pair barrier is implied in llist_add() in blk_cgroup_bio_start(). */ smp_mb(); WRITE_ONCE(bisc->lqueued, false); if (bisc == &blkg->iostat) goto propagate_up; /* propagate up to parent only */ /* fetch the current per-cpu values */ do { seq = u64_stats_fetch_begin(&bisc->sync); blkg_iostat_set(&cur, &bisc->cur); } while (u64_stats_fetch_retry(&bisc->sync, seq)); blkcg_iostat_update(blkg, &cur, &bisc->last); propagate_up: /* propagate global delta to parent (unless that's root) */ if (parent && parent->parent) { blkcg_iostat_update(parent, &blkg->iostat.cur, &blkg->iostat.last); /* * Queue parent->iostat to its blkcg's lockless * list to propagate up to the grandparent if the * iostat hasn't been queued yet. */ if (!parent->iostat.lqueued) { struct llist_head *plhead; plhead = per_cpu_ptr(parent->blkcg->lhead, cpu); llist_add(&parent->iostat.lnode, plhead); parent->iostat.lqueued = true; } } } raw_spin_unlock_irqrestore(&blkg_stat_lock, flags); out: rcu_read_unlock(); } static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) { /* Root-level stats are sourced from system-wide IO stats */ if (cgroup_parent(css->cgroup)) __blkcg_rstat_flush(css_to_blkcg(css), cpu); } /* * We source root cgroup stats from the system-wide stats to avoid * tracking the same information twice and incurring overhead when no * cgroups are defined. For that reason, cgroup_rstat_flush in * blkcg_print_stat does not actually fill out the iostat in the root * cgroup's blkcg_gq. * * However, we would like to re-use the printing code between the root and * non-root cgroups to the extent possible. For that reason, we simulate * flushing the root cgroup's stats by explicitly filling in the iostat * with disk level statistics. */ static void blkcg_fill_root_iostats(void) { struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct block_device *bdev = dev_to_bdev(dev); struct blkcg_gq *blkg = bdev->bd_disk->queue->root_blkg; struct blkg_iostat tmp; int cpu; unsigned long flags; memset(&tmp, 0, sizeof(tmp)); for_each_possible_cpu(cpu) { struct disk_stats *cpu_dkstats; cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu); tmp.ios[BLKG_IOSTAT_READ] += cpu_dkstats->ios[STAT_READ]; tmp.ios[BLKG_IOSTAT_WRITE] += cpu_dkstats->ios[STAT_WRITE]; tmp.ios[BLKG_IOSTAT_DISCARD] += cpu_dkstats->ios[STAT_DISCARD]; // convert sectors to bytes tmp.bytes[BLKG_IOSTAT_READ] += cpu_dkstats->sectors[STAT_READ] << 9; tmp.bytes[BLKG_IOSTAT_WRITE] += cpu_dkstats->sectors[STAT_WRITE] << 9; tmp.bytes[BLKG_IOSTAT_DISCARD] += cpu_dkstats->sectors[STAT_DISCARD] << 9; } flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&blkg->iostat.cur, &tmp); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } } static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) { struct blkg_iostat_set *bis = &blkg->iostat; u64 rbytes, wbytes, rios, wios, dbytes, dios; const char *dname; unsigned seq; int i; if (!blkg->online) return; dname = blkg_dev_name(blkg); if (!dname) return; seq_printf(s, "%s ", dname); do { seq = u64_stats_fetch_begin(&bis->sync); rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; rios = bis->cur.ios[BLKG_IOSTAT_READ]; wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", rbytes, wbytes, rios, wios, dbytes, dios); } if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { seq_printf(s, " use_delay=%d delay_nsec=%llu", atomic_read(&blkg->use_delay), atomic64_read(&blkg->delay_nsec)); } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (!blkg->pd[i] || !pol->pd_stat_fn) continue; pol->pd_stat_fn(blkg->pd[i], s); } seq_puts(s, "\n"); } static int blkcg_print_stat(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; if (!seq_css(sf)->parent) blkcg_fill_root_iostats(); else cgroup_rstat_flush(blkcg->css.cgroup); rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); blkcg_print_one_stat(blkg, sf); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); return 0; } static struct cftype blkcg_files[] = { { .name = "stat", .seq_show = blkcg_print_stat, }, { } /* terminate */ }; static struct cftype blkcg_legacy_files[] = { { .name = "reset_stats", .write_u64 = blkcg_reset_stats, }, { } /* terminate */ }; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css) { return &css_to_blkcg(css)->cgwb_list; } #endif /* * blkcg destruction is a three-stage process. * * 1. Destruction starts. The blkcg_css_offline() callback is invoked * which offlines writeback. Here we tie the next stage of blkg destruction * to the completion of writeback associated with the blkcg. This lets us * avoid punting potentially large amounts of outstanding writeback to root * while maintaining any ongoing policies. The next stage is triggered when * the nr_cgwbs count goes to zero. * * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called * and handles the destruction of blkgs. Here the css reference held by * the blkg is put back eventually allowing blkcg_css_free() to be called. * This work may occur in cgwb_release_workfn() on the cgwb_release * workqueue. Any submitted ios that fail to get the blkg ref will be * punted to the root_blkg. * * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. * This finally frees the blkcg. */ /** * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * * blkgs should be removed while holding both q and blkcg locks. As blkcg lock * is nested inside q lock, this function performs reverse double lock dancing. * Destroying the blkgs releases the reference held on the blkcg's css allowing * blkcg_css_free to eventually be called. * * This is the blkcg counterpart of ioc_release_fn(). */ static void blkcg_destroy_blkgs(struct blkcg *blkcg) { might_sleep(); spin_lock_irq(&blkcg->lock); while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (need_resched() || !spin_trylock(&q->queue_lock)) { /* * Given that the system can accumulate a huge number * of blkgs in pathological cases, check to see if we * need to rescheduling to avoid softlockup. */ spin_unlock_irq(&blkcg->lock); cond_resched(); spin_lock_irq(&blkcg->lock); continue; } blkg_destroy(blkg); spin_unlock(&q->queue_lock); } spin_unlock_irq(&blkcg->lock); } /** * blkcg_pin_online - pin online state * @blkcg_css: blkcg of interest * * While pinned, a blkcg is kept online. This is primarily used to * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline * while an associated cgwb is still active. */ void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css) { refcount_inc(&css_to_blkcg(blkcg_css)->online_pin); } /** * blkcg_unpin_online - unpin online state * @blkcg_css: blkcg of interest * * This is primarily used to impedance-match blkg and cgwb lifetimes so * that blkg doesn't go offline while an associated cgwb is still active. * When this count goes to zero, all active cgwbs have finished so the * blkcg can continue destruction by calling blkcg_destroy_blkgs(). */ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) { struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { if (!refcount_dec_and_test(&blkcg->online_pin)) break; blkcg_destroy_blkgs(blkcg); blkcg = blkcg_parent(blkcg); } while (blkcg); } /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * * This function is called when @css is about to go away. Here the cgwbs are * offlined first and only once writeback associated with the blkcg has * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { /* this prevents anyone from attaching or migrating to this blkcg */ wb_blkcg_offline(css); /* put the base online pin allowing step 2 to be triggered */ blkcg_unpin_online(css); } static void blkcg_css_free(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); int i; mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); mutex_unlock(&blkcg_pol_mutex); free_percpu(blkcg->lhead); kfree(blkcg); } static struct cgroup_subsys_state * blkcg_css_alloc(struct cgroup_subsys_state *parent_css) { struct blkcg *blkcg; int i; mutex_lock(&blkcg_pol_mutex); if (!parent_css) { blkcg = &blkcg_root; } else { blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL); if (!blkcg) goto unlock; } if (init_blkcg_llists(blkcg)) goto free_blkcg; for (i = 0; i < BLKCG_MAX_POLS ; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkcg_policy_data *cpd; /* * If the policy hasn't been attached yet, wait for it * to be attached before doing anything else. Otherwise, * check if the policy requires any specific per-cgroup * data: if it does, allocate and initialize it. */ if (!pol || !pol->cpd_alloc_fn) continue; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto free_pd_blkcg; blkcg->cpd[i] = cpd; cpd->blkcg = blkcg; cpd->plid = i; } spin_lock_init(&blkcg->lock); refcount_set(&blkcg->online_pin, 1); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN); INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); mutex_unlock(&blkcg_pol_mutex); return &blkcg->css; free_pd_blkcg: for (i--; i >= 0; i--) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); free_percpu(blkcg->lhead); free_blkcg: if (blkcg != &blkcg_root) kfree(blkcg); unlock: mutex_unlock(&blkcg_pol_mutex); return ERR_PTR(-ENOMEM); } static int blkcg_css_online(struct cgroup_subsys_state *css) { struct blkcg *parent = blkcg_parent(css_to_blkcg(css)); /* * blkcg_pin_online() is used to delay blkcg offline so that blkgs * don't go offline while cgwbs are still active on them. Pin the * parent so that offline always happens towards the root. */ if (parent) blkcg_pin_online(&parent->css); return 0; } void blkg_init_queue(struct request_queue *q) { INIT_LIST_HEAD(&q->blkg_list); mutex_init(&q->blkcg_mutex); } int blkcg_init_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *new_blkg, *blkg; bool preloaded; new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) return -ENOMEM; preloaded = !radix_tree_preload(GFP_KERNEL); /* Make sure the root blkg exists. */ /* spin_lock_irq can serve as RCU read-side critical section. */ spin_lock_irq(&q->queue_lock); blkg = blkg_create(&blkcg_root, disk, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); return 0; err_unlock: spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); return PTR_ERR(blkg); } void blkcg_exit_disk(struct gendisk *disk) { blkg_destroy_all(disk); blk_throtl_exit(disk); } static void blkcg_exit(struct task_struct *tsk) { if (tsk->throttle_disk) put_disk(tsk->throttle_disk); tsk->throttle_disk = NULL; } struct cgroup_subsys io_cgrp_subsys = { .css_alloc = blkcg_css_alloc, .css_online = blkcg_css_online, .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, .css_rstat_flush = blkcg_rstat_flush, .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, .legacy_name = "blkio", .exit = blkcg_exit, #ifdef CONFIG_MEMCG /* * This ensures that, if available, memcg is automatically enabled * together on the default hierarchy so that the owner cgroup can * be retrieved from writeback pages. */ .depends_on = 1 << memory_cgrp_id, #endif }; EXPORT_SYMBOL_GPL(io_cgrp_subsys); /** * blkcg_activate_policy - activate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to activate * * Activate @pol on @disk. Requires %GFP_KERNEL context. @disk goes through * bypass mode to populate its blkgs with policy_data for @pol. * * Activation happens with @disk bypassed, so nobody would be accessing blkgs * from IO path. Update of each blkg is protected by both queue and blkcg * locks so that holding either lock and testing blkcg_policy_enabled() is * always enough for dereferencing policy data. * * The caller is responsible for synchronizing [de]activations and policy * [un]registerations. Returns 0 on success, -errno on failure. */ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkg_policy_data *pd_prealloc = NULL; struct blkcg_gq *blkg, *pinned_blkg = NULL; int ret; if (blkcg_policy_enabled(q, pol)) return 0; /* * Policy is allowed to be registered without pd_alloc_fn/pd_free_fn, * for example, ioprio. Such policy will work on blkcg level, not disk * level, and don't need to be activated. */ if (WARN_ON_ONCE(!pol->pd_alloc_fn || !pol->pd_free_fn)) return -EINVAL; if (queue_is_mq(q)) blk_mq_freeze_queue(q); retry: spin_lock_irq(&q->queue_lock); /* blkg_list is pushed at the head, reverse walk to initialize parents first */ list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) { struct blkg_policy_data *pd; if (blkg->pd[pol->plid]) continue; /* If prealloc matches, use it; otherwise try GFP_NOWAIT */ if (blkg == pinned_blkg) { pd = pd_prealloc; pd_prealloc = NULL; } else { pd = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_NOWAIT | __GFP_NOWARN); } if (!pd) { /* * GFP_NOWAIT failed. Free the existing one and * prealloc for @blkg w/ GFP_KERNEL. */ if (pinned_blkg) blkg_put(pinned_blkg); blkg_get(blkg); pinned_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); pd_prealloc = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_KERNEL); if (pd_prealloc) goto retry; else goto enomem; } spin_lock(&blkg->blkcg->lock); pd->blkg = blkg; pd->plid = pol->plid; blkg->pd[pol->plid] = pd; if (pol->pd_init_fn) pol->pd_init_fn(pd); if (pol->pd_online_fn) pol->pd_online_fn(pd); pd->online = true; spin_unlock(&blkg->blkcg->lock); } __set_bit(pol->plid, q->blkcg_pols); ret = 0; spin_unlock_irq(&q->queue_lock); out: if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); if (pinned_blkg) blkg_put(pinned_blkg); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); return ret; enomem: /* alloc failed, take down everything */ spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; struct blkg_policy_data *pd; spin_lock(&blkcg->lock); pd = blkg->pd[pol->plid]; if (pd) { if (pd->online && pol->pd_offline_fn) pol->pd_offline_fn(pd); pd->online = false; pol->pd_free_fn(pd); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); ret = -ENOMEM; goto out; } EXPORT_SYMBOL_GPL(blkcg_activate_policy); /** * blkcg_deactivate_policy - deactivate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to deactivate * * Deactivate @pol on @disk. Follows the same synchronization rules as * blkcg_activate_policy(). */ void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) blk_mq_freeze_queue(q); mutex_lock(&q->blkcg_mutex); spin_lock_irq(&q->queue_lock); __clear_bit(pol->plid, q->blkcg_pols); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { if (blkg->pd[pol->plid]->online && pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); static void blkcg_free_all_cpd(struct blkcg_policy *pol) { struct blkcg *blkcg; list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); blkcg->cpd[pol->plid] = NULL; } } } /** * blkcg_policy_register - register a blkcg policy * @pol: blkcg policy to register * * Register @pol with blkcg core. Might sleep and @pol may be modified on * successful registration. Returns 0 on success and -errno on failure. */ int blkcg_policy_register(struct blkcg_policy *pol) { struct blkcg *blkcg; int i, ret; mutex_lock(&blkcg_pol_register_mutex); mutex_lock(&blkcg_pol_mutex); /* find an empty slot */ ret = -ENOSPC; for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; if (i >= BLKCG_MAX_POLS) { pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; } /* * Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy * without pd_alloc_fn/pd_free_fn can't be activated. */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || (!pol->pd_alloc_fn ^ !pol->pd_free_fn)) goto err_unlock; /* register @pol */ pol->plid = i; blkcg_policy[pol->plid] = pol; /* allocate and install cpd's */ if (pol->cpd_alloc_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { struct blkcg_policy_data *cpd; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto err_free_cpds; blkcg->cpd[pol->plid] = cpd; cpd->blkcg = blkcg; cpd->plid = pol->plid; } } mutex_unlock(&blkcg_pol_mutex); /* everything is in place, add intf files for the new policy */ if (pol->dfl_cftypes) WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); if (pol->legacy_cftypes) WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys, pol->legacy_cftypes)); mutex_unlock(&blkcg_pol_register_mutex); return 0; err_free_cpds: if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; err_unlock: mutex_unlock(&blkcg_pol_mutex); mutex_unlock(&blkcg_pol_register_mutex); return ret; } EXPORT_SYMBOL_GPL(blkcg_policy_register); /** * blkcg_policy_unregister - unregister a blkcg policy * @pol: blkcg policy to unregister * * Undo blkcg_policy_register(@pol). Might sleep. */ void blkcg_policy_unregister(struct blkcg_policy *pol) { mutex_lock(&blkcg_pol_register_mutex); if (WARN_ON(blkcg_policy[pol->plid] != pol)) goto out_unlock; /* kill the intf files first */ if (pol->dfl_cftypes) cgroup_rm_cftypes(pol->dfl_cftypes); if (pol->legacy_cftypes) cgroup_rm_cftypes(pol->legacy_cftypes); /* remove cpds and unregister */ mutex_lock(&blkcg_pol_mutex); if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; mutex_unlock(&blkcg_pol_mutex); out_unlock: mutex_unlock(&blkcg_pol_register_mutex); } EXPORT_SYMBOL_GPL(blkcg_policy_unregister); /* * Scale the accumulated delay based on how long it has been since we updated * the delay. We only call this when we are adding delay, in case it's been a * while since we added delay, and when we are checking to see if we need to * delay a task, to account for any delays that may have occurred. */ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now) { u64 old = atomic64_read(&blkg->delay_start); /* negative use_delay means no scaling, see blkcg_set_delay() */ if (atomic_read(&blkg->use_delay) < 0) return; /* * We only want to scale down every second. The idea here is that we * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain * time window. We only want to throttle tasks for recent delay that * has occurred, in 1 second time windows since that's the maximum * things can be throttled. We save the current delay window in * blkg->last_delay so we know what amount is still left to be charged * to the blkg from this point onward. blkg->last_use keeps track of * the use_delay counter. The idea is if we're unthrottling the blkg we * are ok with whatever is happening now, and we can take away more of * the accumulated delay as we've already throttled enough that * everybody is happy with their IO latencies. */ if (time_before64(old + NSEC_PER_SEC, now) && atomic64_try_cmpxchg(&blkg->delay_start, &old, now)) { u64 cur = atomic64_read(&blkg->delay_nsec); u64 sub = min_t(u64, blkg->last_delay, now - old); int cur_use = atomic_read(&blkg->use_delay); /* * We've been unthrottled, subtract a larger chunk of our * accumulated delay. */ if (cur_use < blkg->last_use) sub = max_t(u64, sub, blkg->last_delay >> 1); /* * This shouldn't happen, but handle it anyway. Our delay_nsec * should only ever be growing except here where we subtract out * min(last_delay, 1 second), but lord knows bugs happen and I'd * rather not end up with negative numbers. */ if (unlikely(cur < sub)) { atomic64_set(&blkg->delay_nsec, 0); blkg->last_delay = 0; } else { atomic64_sub(sub, &blkg->delay_nsec); blkg->last_delay = cur - sub; } blkg->last_use = cur_use; } } /* * This is called when we want to actually walk up the hierarchy and check to * see if we need to throttle, and then actually throttle if there is some * accumulated delay. This should only be called upon return to user space so * we're not holding some lock that would induce a priority inversion. */ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) { unsigned long pflags; bool clamp; u64 now = blk_time_get_ns(); u64 exp; u64 delay_nsec = 0; int tok; while (blkg->parent) { int use_delay = atomic_read(&blkg->use_delay); if (use_delay) { u64 this_delay; blkcg_scale_delay(blkg, now); this_delay = atomic64_read(&blkg->delay_nsec); if (this_delay > delay_nsec) { delay_nsec = this_delay; clamp = use_delay > 0; } } blkg = blkg->parent; } if (!delay_nsec) return; /* * Let's not sleep for all eternity if we've amassed a huge delay. * Swapping or metadata IO can accumulate 10's of seconds worth of * delay, and we want userspace to be able to do _something_ so cap the * delays at 0.25s. If there's 10's of seconds worth of delay then the * tasks will be delayed for 0.25 second for every syscall. If * blkcg_set_delay() was used as indicated by negative use_delay, the * caller is responsible for regulating the range. */ if (clamp) delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC); if (use_memdelay) psi_memstall_enter(&pflags); exp = ktime_add_ns(now, delay_nsec); tok = io_schedule_prepare(); do { __set_current_state(TASK_KILLABLE); if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS)) break; } while (!fatal_signal_pending(current)); io_schedule_finish(tok); if (use_memdelay) psi_memstall_leave(&pflags); } /** * blkcg_maybe_throttle_current - throttle the current task if it has been marked * * This is only called if we've been marked with set_notify_resume(). Obviously * we can be set_notify_resume() for reasons other than blkcg throttling, so we * check to see if current->throttle_disk is set and if not this doesn't do * anything. This should only ever be called by the resume code, it's not meant * to be called by people willy-nilly as it will actually do the work to * throttle the task if it is setup for throttling. */ void blkcg_maybe_throttle_current(void) { struct gendisk *disk = current->throttle_disk; struct blkcg *blkcg; struct blkcg_gq *blkg; bool use_memdelay = current->use_memdelay; if (!disk) return; current->throttle_disk = NULL; current->use_memdelay = false; rcu_read_lock(); blkcg = css_to_blkcg(blkcg_css()); if (!blkcg) goto out; blkg = blkg_lookup(blkcg, disk->queue); if (!blkg) goto out; if (!blkg_tryget(blkg)) goto out; rcu_read_unlock(); blkcg_maybe_throttle_blkg(blkg, use_memdelay); blkg_put(blkg); put_disk(disk); return; out: rcu_read_unlock(); } /** * blkcg_schedule_throttle - this task needs to check for throttling * @disk: disk to throttle * @use_memdelay: do we charge this to memory delay for PSI * * This is called by the IO controller when we know there's delay accumulated * for the blkg for this task. We do not pass the blkg because there are places * we call this that may not have that information, the swapping code for * instance will only have a block_device at that point. This set's the * notify_resume for the task to check and see if it requires throttling before * returning to user space. * * We will only schedule once per syscall. You can call this over and over * again and it will only do the check once upon return to user space, and only * throttle once. If the task needs to be throttled again it'll need to be * re-set at the next time we see the task. */ void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay) { if (unlikely(current->flags & PF_KTHREAD)) return; if (current->throttle_disk != disk) { if (test_bit(GD_DEAD, &disk->state)) return; get_device(disk_to_dev(disk)); if (current->throttle_disk) put_disk(current->throttle_disk); current->throttle_disk = disk; } if (use_memdelay) current->use_memdelay = use_memdelay; set_notify_resume(current); } /** * blkcg_add_delay - add delay to this blkg * @blkg: blkg of interest * @now: the current time in nanoseconds * @delta: how many nanoseconds of delay to add * * Charge @delta to the blkg's current delay accumulation. This is used to * throttle tasks if an IO controller thinks we need more throttling. */ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) return; blkcg_scale_delay(blkg, now); atomic64_add(delta, &blkg->delay_nsec); } /** * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @bio: target bio * @css: target css * * As the failure mode here is to walk up the blkg tree, this ensure that the * blkg->parent pointers are always valid. This returns the blkg that it ended * up taking a reference on or %NULL if no reference was taken. */ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio, struct cgroup_subsys_state *css) { struct blkcg_gq *blkg, *ret_blkg = NULL; rcu_read_lock(); blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_bdev->bd_disk); while (blkg) { if (blkg_tryget(blkg)) { ret_blkg = blkg; break; } blkg = blkg->parent; } rcu_read_unlock(); return ret_blkg; } /** * bio_associate_blkg_from_css - associate a bio with a specified css * @bio: target bio * @css: target css * * Associate @bio with the blkg found by combining the css's blkg and the * request_queue of the @bio. An association failure is handled by walking up * the blkg tree. Therefore, the blkg associated can be anything between @blkg * and q->root_blkg. This situation only happens when a cgroup is dying and * then the remaining bios will spill to the closest alive blkg. * * A reference will be taken on the blkg and will be released when @bio is * freed. */ void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { if (bio->bi_blkg) blkg_put(bio->bi_blkg); if (css && css->parent) { bio->bi_blkg = blkg_tryget_closest(bio, css); } else { blkg_get(bdev_get_queue(bio->bi_bdev)->root_blkg); bio->bi_blkg = bdev_get_queue(bio->bi_bdev)->root_blkg; } } EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); /** * bio_associate_blkg - associate a bio with a blkg * @bio: target bio * * Associate @bio with the blkg found from the bio's css and request_queue. * If one is not found, bio_lookup_blkg() creates the blkg. If a blkg is * already associated, the css is reused and association redone as the * request_queue may have changed. */ void bio_associate_blkg(struct bio *bio) { struct cgroup_subsys_state *css; if (blk_op_is_passthrough(bio->bi_opf)) return; rcu_read_lock(); if (bio->bi_blkg) css = bio_blkcg_css(bio); else css = blkcg_css(); bio_associate_blkg_from_css(bio, css); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(bio_associate_blkg); /** * bio_clone_blkg_association - clone blkg association from src to dst bio * @dst: destination bio * @src: source bio */ void bio_clone_blkg_association(struct bio *dst, struct bio *src) { if (src->bi_blkg) bio_associate_blkg_from_css(dst, bio_blkcg_css(src)); } EXPORT_SYMBOL_GPL(bio_clone_blkg_association); static int blk_cgroup_io_type(struct bio *bio) { if (op_is_discard(bio->bi_opf)) return BLKG_IOSTAT_DISCARD; if (op_is_write(bio->bi_opf)) return BLKG_IOSTAT_WRITE; return BLKG_IOSTAT_READ; } void blk_cgroup_bio_start(struct bio *bio) { struct blkcg *blkcg = bio->bi_blkg->blkcg; int rwd = blk_cgroup_io_type(bio), cpu; struct blkg_iostat_set *bis; unsigned long flags; if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) return; /* Root-level stats are sourced from system-wide IO stats */ if (!cgroup_parent(blkcg->css.cgroup)) return; cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); flags = u64_stats_update_begin_irqsave(&bis->sync); /* * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split * bio and we would have already accounted for the size of the bio. */ if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { bio_set_flag(bio, BIO_CGROUP_ACCT); bis->cur.bytes[rwd] += bio->bi_iter.bi_size; } bis->cur.ios[rwd]++; /* * If the iostat_cpu isn't in a lockless list, put it into the * list to indicate that a stat update is pending. */ if (!READ_ONCE(bis->lqueued)) { struct llist_head *lhead = this_cpu_ptr(blkcg->lhead); llist_add(&bis->lnode, lhead); WRITE_ONCE(bis->lqueued, true); } u64_stats_update_end_irqrestore(&bis->sync, flags); cgroup_rstat_updated(blkcg->css.cgroup, cpu); put_cpu(); } bool blk_cgroup_congested(void) { struct blkcg *blkcg; bool ret = false; rcu_read_lock(); for (blkcg = css_to_blkcg(blkcg_css()); blkcg; blkcg = blkcg_parent(blkcg)) { if (atomic_read(&blkcg->congestion_count)) { ret = true; break; } } rcu_read_unlock(); return ret; } module_param(blkcg_debug_stats, bool, 0644); MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not"); |
| 8 1 8 2 2 3 3 3 8 9 5 4 3 4 4 4 4 4 5 4 1 2 2 9 6 6 6 6 6 1 5 5 4 2 5 5 5 5 2 3 3 3 3 3 5 5 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 11 11 11 9 9 9 2 2 2 2 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * * Authors: * Alexander Aring <aar@pengutronix.de> * * Based on: net/wireless/nl80211.c */ #include <linux/rtnetlink.h> #include <net/cfg802154.h> #include <net/genetlink.h> #include <net/mac802154.h> #include <net/netlink.h> #include <net/nl802154.h> #include <net/sock.h> #include "nl802154.h" #include "rdev-ops.h" #include "core.h" /* the netlink family */ static struct genl_family nl802154_fam; /* multicast groups */ enum nl802154_multicast_groups { NL802154_MCGRP_CONFIG, NL802154_MCGRP_SCAN, }; static const struct genl_multicast_group nl802154_mcgrps[] = { [NL802154_MCGRP_CONFIG] = { .name = "config", }, [NL802154_MCGRP_SCAN] = { .name = "scan", }, }; /* returns ERR_PTR values */ static struct wpan_dev * __cfg802154_wpan_dev_from_attrs(struct net *netns, struct nlattr **attrs) { struct cfg802154_registered_device *rdev; struct wpan_dev *result = NULL; bool have_ifidx = attrs[NL802154_ATTR_IFINDEX]; bool have_wpan_dev_id = attrs[NL802154_ATTR_WPAN_DEV]; u64 wpan_dev_id; int wpan_phy_idx = -1; int ifidx = -1; ASSERT_RTNL(); if (!have_ifidx && !have_wpan_dev_id) return ERR_PTR(-EINVAL); if (have_ifidx) ifidx = nla_get_u32(attrs[NL802154_ATTR_IFINDEX]); if (have_wpan_dev_id) { wpan_dev_id = nla_get_u64(attrs[NL802154_ATTR_WPAN_DEV]); wpan_phy_idx = wpan_dev_id >> 32; } list_for_each_entry(rdev, &cfg802154_rdev_list, list) { struct wpan_dev *wpan_dev; if (wpan_phy_net(&rdev->wpan_phy) != netns) continue; if (have_wpan_dev_id && rdev->wpan_phy_idx != wpan_phy_idx) continue; list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) { if (have_ifidx && wpan_dev->netdev && wpan_dev->netdev->ifindex == ifidx) { result = wpan_dev; break; } if (have_wpan_dev_id && wpan_dev->identifier == (u32)wpan_dev_id) { result = wpan_dev; break; } } if (result) break; } if (result) return result; return ERR_PTR(-ENODEV); } static struct cfg802154_registered_device * __cfg802154_rdev_from_attrs(struct net *netns, struct nlattr **attrs) { struct cfg802154_registered_device *rdev = NULL, *tmp; struct net_device *netdev; ASSERT_RTNL(); if (!attrs[NL802154_ATTR_WPAN_PHY] && !attrs[NL802154_ATTR_IFINDEX] && !attrs[NL802154_ATTR_WPAN_DEV]) return ERR_PTR(-EINVAL); if (attrs[NL802154_ATTR_WPAN_PHY]) rdev = cfg802154_rdev_by_wpan_phy_idx( nla_get_u32(attrs[NL802154_ATTR_WPAN_PHY])); if (attrs[NL802154_ATTR_WPAN_DEV]) { u64 wpan_dev_id = nla_get_u64(attrs[NL802154_ATTR_WPAN_DEV]); struct wpan_dev *wpan_dev; bool found = false; tmp = cfg802154_rdev_by_wpan_phy_idx(wpan_dev_id >> 32); if (tmp) { /* make sure wpan_dev exists */ list_for_each_entry(wpan_dev, &tmp->wpan_dev_list, list) { if (wpan_dev->identifier != (u32)wpan_dev_id) continue; found = true; break; } if (!found) tmp = NULL; if (rdev && tmp != rdev) return ERR_PTR(-EINVAL); rdev = tmp; } } if (attrs[NL802154_ATTR_IFINDEX]) { int ifindex = nla_get_u32(attrs[NL802154_ATTR_IFINDEX]); netdev = __dev_get_by_index(netns, ifindex); if (netdev) { if (netdev->ieee802154_ptr) tmp = wpan_phy_to_rdev( netdev->ieee802154_ptr->wpan_phy); else tmp = NULL; /* not wireless device -- return error */ if (!tmp) return ERR_PTR(-EINVAL); /* mismatch -- return error */ if (rdev && tmp != rdev) return ERR_PTR(-EINVAL); rdev = tmp; } } if (!rdev) return ERR_PTR(-ENODEV); if (netns != wpan_phy_net(&rdev->wpan_phy)) return ERR_PTR(-ENODEV); return rdev; } /* This function returns a pointer to the driver * that the genl_info item that is passed refers to. * * The result of this can be a PTR_ERR and hence must * be checked with IS_ERR() for errors. */ static struct cfg802154_registered_device * cfg802154_get_dev_from_info(struct net *netns, struct genl_info *info) { return __cfg802154_rdev_from_attrs(netns, info->attrs); } /* policy for the attributes */ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = { [NL802154_ATTR_WPAN_PHY] = { .type = NLA_U32 }, [NL802154_ATTR_WPAN_PHY_NAME] = { .type = NLA_NUL_STRING, .len = 20-1 }, [NL802154_ATTR_IFINDEX] = { .type = NLA_U32 }, [NL802154_ATTR_IFTYPE] = { .type = NLA_U32 }, [NL802154_ATTR_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ-1 }, [NL802154_ATTR_WPAN_DEV] = { .type = NLA_U64 }, [NL802154_ATTR_PAGE] = NLA_POLICY_MAX(NLA_U8, IEEE802154_MAX_PAGE), [NL802154_ATTR_CHANNEL] = NLA_POLICY_MAX(NLA_U8, IEEE802154_MAX_CHANNEL), [NL802154_ATTR_TX_POWER] = { .type = NLA_S32, }, [NL802154_ATTR_CCA_MODE] = { .type = NLA_U32, }, [NL802154_ATTR_CCA_OPT] = { .type = NLA_U32, }, [NL802154_ATTR_CCA_ED_LEVEL] = { .type = NLA_S32, }, [NL802154_ATTR_SUPPORTED_CHANNEL] = { .type = NLA_U32, }, [NL802154_ATTR_PAN_ID] = { .type = NLA_U16, }, [NL802154_ATTR_EXTENDED_ADDR] = { .type = NLA_U64 }, [NL802154_ATTR_SHORT_ADDR] = { .type = NLA_U16, }, [NL802154_ATTR_MIN_BE] = { .type = NLA_U8, }, [NL802154_ATTR_MAX_BE] = { .type = NLA_U8, }, [NL802154_ATTR_MAX_CSMA_BACKOFFS] = { .type = NLA_U8, }, [NL802154_ATTR_MAX_FRAME_RETRIES] = { .type = NLA_S8, }, [NL802154_ATTR_LBT_MODE] = { .type = NLA_U8, }, [NL802154_ATTR_WPAN_PHY_CAPS] = { .type = NLA_NESTED }, [NL802154_ATTR_SUPPORTED_COMMANDS] = { .type = NLA_NESTED }, [NL802154_ATTR_ACKREQ_DEFAULT] = { .type = NLA_U8 }, [NL802154_ATTR_PID] = { .type = NLA_U32 }, [NL802154_ATTR_NETNS_FD] = { .type = NLA_U32 }, [NL802154_ATTR_COORDINATOR] = { .type = NLA_NESTED }, [NL802154_ATTR_SCAN_TYPE] = NLA_POLICY_RANGE(NLA_U8, NL802154_SCAN_ED, NL802154_SCAN_RIT_PASSIVE), [NL802154_ATTR_SCAN_CHANNELS] = NLA_POLICY_MASK(NLA_U32, GENMASK(IEEE802154_MAX_CHANNEL, 0)), [NL802154_ATTR_SCAN_PREAMBLE_CODES] = { .type = NLA_REJECT }, [NL802154_ATTR_SCAN_MEAN_PRF] = { .type = NLA_REJECT }, [NL802154_ATTR_SCAN_DURATION] = NLA_POLICY_MAX(NLA_U8, IEEE802154_MAX_SCAN_DURATION), [NL802154_ATTR_SCAN_DONE_REASON] = NLA_POLICY_RANGE(NLA_U8, NL802154_SCAN_DONE_REASON_FINISHED, NL802154_SCAN_DONE_REASON_ABORTED), [NL802154_ATTR_BEACON_INTERVAL] = NLA_POLICY_MAX(NLA_U8, IEEE802154_ACTIVE_SCAN_DURATION), [NL802154_ATTR_MAX_ASSOCIATIONS] = { .type = NLA_U32 }, [NL802154_ATTR_PEER] = { .type = NLA_NESTED }, #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL [NL802154_ATTR_SEC_ENABLED] = { .type = NLA_U8, }, [NL802154_ATTR_SEC_OUT_LEVEL] = { .type = NLA_U32, }, [NL802154_ATTR_SEC_OUT_KEY_ID] = { .type = NLA_NESTED, }, [NL802154_ATTR_SEC_FRAME_COUNTER] = { .type = NLA_U32 }, [NL802154_ATTR_SEC_LEVEL] = { .type = NLA_NESTED }, [NL802154_ATTR_SEC_DEVICE] = { .type = NLA_NESTED }, [NL802154_ATTR_SEC_DEVKEY] = { .type = NLA_NESTED }, [NL802154_ATTR_SEC_KEY] = { .type = NLA_NESTED }, #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ }; static int nl802154_prepare_wpan_dev_dump(struct sk_buff *skb, struct netlink_callback *cb, struct cfg802154_registered_device **rdev, struct wpan_dev **wpan_dev) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); int err; rtnl_lock(); if (!cb->args[0]) { *wpan_dev = __cfg802154_wpan_dev_from_attrs(sock_net(skb->sk), info->info.attrs); if (IS_ERR(*wpan_dev)) { err = PTR_ERR(*wpan_dev); goto out_unlock; } *rdev = wpan_phy_to_rdev((*wpan_dev)->wpan_phy); /* 0 is the first index - add 1 to parse only once */ cb->args[0] = (*rdev)->wpan_phy_idx + 1; cb->args[1] = (*wpan_dev)->identifier; } else { /* subtract the 1 again here */ struct wpan_phy *wpan_phy = wpan_phy_idx_to_wpan_phy(cb->args[0] - 1); struct wpan_dev *tmp; if (!wpan_phy) { err = -ENODEV; goto out_unlock; } *rdev = wpan_phy_to_rdev(wpan_phy); *wpan_dev = NULL; list_for_each_entry(tmp, &(*rdev)->wpan_dev_list, list) { if (tmp->identifier == cb->args[1]) { *wpan_dev = tmp; break; } } if (!*wpan_dev) { err = -ENODEV; goto out_unlock; } } return 0; out_unlock: rtnl_unlock(); return err; } static void nl802154_finish_wpan_dev_dump(struct cfg802154_registered_device *rdev) { rtnl_unlock(); } /* message building helper */ static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq, int flags, u8 cmd) { /* since there is no private header just add the generic one */ return genlmsg_put(skb, portid, seq, &nl802154_fam, flags, cmd); } static int nl802154_put_flags(struct sk_buff *msg, int attr, u32 mask) { struct nlattr *nl_flags = nla_nest_start_noflag(msg, attr); int i; if (!nl_flags) return -ENOBUFS; i = 0; while (mask) { if ((mask & 1) && nla_put_flag(msg, i)) return -ENOBUFS; mask >>= 1; i++; } nla_nest_end(msg, nl_flags); return 0; } static int nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev, struct sk_buff *msg) { struct nlattr *nl_page; unsigned long page; nl_page = nla_nest_start_noflag(msg, NL802154_ATTR_CHANNELS_SUPPORTED); if (!nl_page) return -ENOBUFS; for (page = 0; page <= IEEE802154_MAX_PAGE; page++) { if (nla_put_u32(msg, NL802154_ATTR_SUPPORTED_CHANNEL, rdev->wpan_phy.supported.channels[page])) return -ENOBUFS; } nla_nest_end(msg, nl_page); return 0; } static int nl802154_put_capabilities(struct sk_buff *msg, struct cfg802154_registered_device *rdev) { const struct wpan_phy_supported *caps = &rdev->wpan_phy.supported; struct nlattr *nl_caps, *nl_channels; int i; nl_caps = nla_nest_start_noflag(msg, NL802154_ATTR_WPAN_PHY_CAPS); if (!nl_caps) return -ENOBUFS; nl_channels = nla_nest_start_noflag(msg, NL802154_CAP_ATTR_CHANNELS); if (!nl_channels) return -ENOBUFS; for (i = 0; i <= IEEE802154_MAX_PAGE; i++) { if (caps->channels[i]) { if (nl802154_put_flags(msg, i, caps->channels[i])) return -ENOBUFS; } } nla_nest_end(msg, nl_channels); if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) { struct nlattr *nl_ed_lvls; nl_ed_lvls = nla_nest_start_noflag(msg, NL802154_CAP_ATTR_CCA_ED_LEVELS); if (!nl_ed_lvls) return -ENOBUFS; for (i = 0; i < caps->cca_ed_levels_size; i++) { if (nla_put_s32(msg, i, caps->cca_ed_levels[i])) return -ENOBUFS; } nla_nest_end(msg, nl_ed_lvls); } if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) { struct nlattr *nl_tx_pwrs; nl_tx_pwrs = nla_nest_start_noflag(msg, NL802154_CAP_ATTR_TX_POWERS); if (!nl_tx_pwrs) return -ENOBUFS; for (i = 0; i < caps->tx_powers_size; i++) { if (nla_put_s32(msg, i, caps->tx_powers[i])) return -ENOBUFS; } nla_nest_end(msg, nl_tx_pwrs); } if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) { if (nl802154_put_flags(msg, NL802154_CAP_ATTR_CCA_MODES, caps->cca_modes) || nl802154_put_flags(msg, NL802154_CAP_ATTR_CCA_OPTS, caps->cca_opts)) return -ENOBUFS; } if (nla_put_u8(msg, NL802154_CAP_ATTR_MIN_MINBE, caps->min_minbe) || nla_put_u8(msg, NL802154_CAP_ATTR_MAX_MINBE, caps->max_minbe) || nla_put_u8(msg, NL802154_CAP_ATTR_MIN_MAXBE, caps->min_maxbe) || nla_put_u8(msg, NL802154_CAP_ATTR_MAX_MAXBE, caps->max_maxbe) || nla_put_u8(msg, NL802154_CAP_ATTR_MIN_CSMA_BACKOFFS, caps->min_csma_backoffs) || nla_put_u8(msg, NL802154_CAP_ATTR_MAX_CSMA_BACKOFFS, caps->max_csma_backoffs) || nla_put_s8(msg, NL802154_CAP_ATTR_MIN_FRAME_RETRIES, caps->min_frame_retries) || nla_put_s8(msg, NL802154_CAP_ATTR_MAX_FRAME_RETRIES, caps->max_frame_retries) || nl802154_put_flags(msg, NL802154_CAP_ATTR_IFTYPES, caps->iftypes) || nla_put_u32(msg, NL802154_CAP_ATTR_LBT, caps->lbt)) return -ENOBUFS; nla_nest_end(msg, nl_caps); return 0; } static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev, enum nl802154_commands cmd, struct sk_buff *msg, u32 portid, u32 seq, int flags) { struct nlattr *nl_cmds; void *hdr; int i; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_WPAN_PHY, rdev->wpan_phy_idx) || nla_put_string(msg, NL802154_ATTR_WPAN_PHY_NAME, wpan_phy_name(&rdev->wpan_phy)) || nla_put_u32(msg, NL802154_ATTR_GENERATION, cfg802154_rdev_list_generation)) goto nla_put_failure; if (cmd != NL802154_CMD_NEW_WPAN_PHY) goto finish; /* DUMP PHY PIB */ /* current channel settings */ if (nla_put_u8(msg, NL802154_ATTR_PAGE, rdev->wpan_phy.current_page) || nla_put_u8(msg, NL802154_ATTR_CHANNEL, rdev->wpan_phy.current_channel)) goto nla_put_failure; /* TODO remove this behaviour, we still keep support it for a while * so users can change the behaviour to the new one. */ if (nl802154_send_wpan_phy_channels(rdev, msg)) goto nla_put_failure; /* cca mode */ if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) { if (nla_put_u32(msg, NL802154_ATTR_CCA_MODE, rdev->wpan_phy.cca.mode)) goto nla_put_failure; if (rdev->wpan_phy.cca.mode == NL802154_CCA_ENERGY_CARRIER) { if (nla_put_u32(msg, NL802154_ATTR_CCA_OPT, rdev->wpan_phy.cca.opt)) goto nla_put_failure; } } if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) { if (nla_put_s32(msg, NL802154_ATTR_TX_POWER, rdev->wpan_phy.transmit_power)) goto nla_put_failure; } if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) { if (nla_put_s32(msg, NL802154_ATTR_CCA_ED_LEVEL, rdev->wpan_phy.cca_ed_level)) goto nla_put_failure; } if (nl802154_put_capabilities(msg, rdev)) goto nla_put_failure; nl_cmds = nla_nest_start_noflag(msg, NL802154_ATTR_SUPPORTED_COMMANDS); if (!nl_cmds) goto nla_put_failure; i = 0; #define CMD(op, n) \ do { \ if (rdev->ops->op) { \ i++; \ if (nla_put_u32(msg, i, NL802154_CMD_ ## n)) \ goto nla_put_failure; \ } \ } while (0) CMD(add_virtual_intf, NEW_INTERFACE); CMD(del_virtual_intf, DEL_INTERFACE); CMD(set_channel, SET_CHANNEL); CMD(set_pan_id, SET_PAN_ID); CMD(set_short_addr, SET_SHORT_ADDR); CMD(set_backoff_exponent, SET_BACKOFF_EXPONENT); CMD(set_max_csma_backoffs, SET_MAX_CSMA_BACKOFFS); CMD(set_max_frame_retries, SET_MAX_FRAME_RETRIES); CMD(set_lbt_mode, SET_LBT_MODE); CMD(set_ackreq_default, SET_ACKREQ_DEFAULT); if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) CMD(set_tx_power, SET_TX_POWER); if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) CMD(set_cca_ed_level, SET_CCA_ED_LEVEL); if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE) CMD(set_cca_mode, SET_CCA_MODE); #undef CMD nla_nest_end(msg, nl_cmds); finish: genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } struct nl802154_dump_wpan_phy_state { s64 filter_wpan_phy; long start; }; static int nl802154_dump_wpan_phy_parse(struct sk_buff *skb, struct netlink_callback *cb, struct nl802154_dump_wpan_phy_state *state) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct nlattr **tb = info->info.attrs; if (tb[NL802154_ATTR_WPAN_PHY]) state->filter_wpan_phy = nla_get_u32(tb[NL802154_ATTR_WPAN_PHY]); if (tb[NL802154_ATTR_WPAN_DEV]) state->filter_wpan_phy = nla_get_u64(tb[NL802154_ATTR_WPAN_DEV]) >> 32; if (tb[NL802154_ATTR_IFINDEX]) { struct net_device *netdev; struct cfg802154_registered_device *rdev; int ifidx = nla_get_u32(tb[NL802154_ATTR_IFINDEX]); netdev = __dev_get_by_index(&init_net, ifidx); if (!netdev) return -ENODEV; if (netdev->ieee802154_ptr) { rdev = wpan_phy_to_rdev( netdev->ieee802154_ptr->wpan_phy); state->filter_wpan_phy = rdev->wpan_phy_idx; } } return 0; } static int nl802154_dump_wpan_phy(struct sk_buff *skb, struct netlink_callback *cb) { int idx = 0, ret; struct nl802154_dump_wpan_phy_state *state = (void *)cb->args[0]; struct cfg802154_registered_device *rdev; rtnl_lock(); if (!state) { state = kzalloc(sizeof(*state), GFP_KERNEL); if (!state) { rtnl_unlock(); return -ENOMEM; } state->filter_wpan_phy = -1; ret = nl802154_dump_wpan_phy_parse(skb, cb, state); if (ret) { kfree(state); rtnl_unlock(); return ret; } cb->args[0] = (long)state; } list_for_each_entry(rdev, &cfg802154_rdev_list, list) { if (!net_eq(wpan_phy_net(&rdev->wpan_phy), sock_net(skb->sk))) continue; if (++idx <= state->start) continue; if (state->filter_wpan_phy != -1 && state->filter_wpan_phy != rdev->wpan_phy_idx) continue; /* attempt to fit multiple wpan_phy data chunks into the skb */ ret = nl802154_send_wpan_phy(rdev, NL802154_CMD_NEW_WPAN_PHY, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); if (ret < 0) { if ((ret == -ENOBUFS || ret == -EMSGSIZE) && !skb->len && cb->min_dump_alloc < 4096) { cb->min_dump_alloc = 4096; rtnl_unlock(); return 1; } idx--; break; } break; } rtnl_unlock(); state->start = idx; return skb->len; } static int nl802154_dump_wpan_phy_done(struct netlink_callback *cb) { kfree((void *)cb->args[0]); return 0; } static int nl802154_get_wpan_phy(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; struct cfg802154_registered_device *rdev = info->user_ptr[0]; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; if (nl802154_send_wpan_phy(rdev, NL802154_CMD_NEW_WPAN_PHY, msg, info->snd_portid, info->snd_seq, 0) < 0) { nlmsg_free(msg); return -ENOBUFS; } return genlmsg_reply(msg, info); } static inline u64 wpan_dev_id(struct wpan_dev *wpan_dev) { return (u64)wpan_dev->identifier | ((u64)wpan_phy_to_rdev(wpan_dev->wpan_phy)->wpan_phy_idx << 32); } #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL #include <net/ieee802154_netdev.h> static int ieee802154_llsec_send_key_id(struct sk_buff *msg, const struct ieee802154_llsec_key_id *desc) { struct nlattr *nl_dev_addr; if (nla_put_u32(msg, NL802154_KEY_ID_ATTR_MODE, desc->mode)) return -ENOBUFS; switch (desc->mode) { case NL802154_KEY_ID_MODE_IMPLICIT: nl_dev_addr = nla_nest_start_noflag(msg, NL802154_KEY_ID_ATTR_IMPLICIT); if (!nl_dev_addr) return -ENOBUFS; if (nla_put_le16(msg, NL802154_DEV_ADDR_ATTR_PAN_ID, desc->device_addr.pan_id) || nla_put_u32(msg, NL802154_DEV_ADDR_ATTR_MODE, desc->device_addr.mode)) return -ENOBUFS; switch (desc->device_addr.mode) { case NL802154_DEV_ADDR_SHORT: if (nla_put_le16(msg, NL802154_DEV_ADDR_ATTR_SHORT, desc->device_addr.short_addr)) return -ENOBUFS; break; case NL802154_DEV_ADDR_EXTENDED: if (nla_put_le64(msg, NL802154_DEV_ADDR_ATTR_EXTENDED, desc->device_addr.extended_addr, NL802154_DEV_ADDR_ATTR_PAD)) return -ENOBUFS; break; default: /* userspace should handle unknown */ break; } nla_nest_end(msg, nl_dev_addr); break; case NL802154_KEY_ID_MODE_INDEX: break; case NL802154_KEY_ID_MODE_INDEX_SHORT: /* TODO renmae short_source? */ if (nla_put_le32(msg, NL802154_KEY_ID_ATTR_SOURCE_SHORT, desc->short_source)) return -ENOBUFS; break; case NL802154_KEY_ID_MODE_INDEX_EXTENDED: if (nla_put_le64(msg, NL802154_KEY_ID_ATTR_SOURCE_EXTENDED, desc->extended_source, NL802154_KEY_ID_ATTR_PAD)) return -ENOBUFS; break; default: /* userspace should handle unknown */ break; } /* TODO key_id to key_idx ? Check naming */ if (desc->mode != NL802154_KEY_ID_MODE_IMPLICIT) { if (nla_put_u8(msg, NL802154_KEY_ID_ATTR_INDEX, desc->id)) return -ENOBUFS; } return 0; } static int nl802154_get_llsec_params(struct sk_buff *msg, struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev) { struct nlattr *nl_key_id; struct ieee802154_llsec_params params; int ret; ret = rdev_get_llsec_params(rdev, wpan_dev, ¶ms); if (ret < 0) return ret; if (nla_put_u8(msg, NL802154_ATTR_SEC_ENABLED, params.enabled) || nla_put_u32(msg, NL802154_ATTR_SEC_OUT_LEVEL, params.out_level) || nla_put_be32(msg, NL802154_ATTR_SEC_FRAME_COUNTER, params.frame_counter)) return -ENOBUFS; nl_key_id = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_OUT_KEY_ID); if (!nl_key_id) return -ENOBUFS; ret = ieee802154_llsec_send_key_id(msg, ¶ms.out_key); if (ret < 0) return ret; nla_nest_end(msg, nl_key_id); return 0; } #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ static int nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev) { struct net_device *dev = wpan_dev->netdev; void *hdr; hdr = nl802154hdr_put(msg, portid, seq, flags, NL802154_CMD_NEW_INTERFACE); if (!hdr) return -1; if (dev && (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex) || nla_put_string(msg, NL802154_ATTR_IFNAME, dev->name))) goto nla_put_failure; if (nla_put_u32(msg, NL802154_ATTR_WPAN_PHY, rdev->wpan_phy_idx) || nla_put_u32(msg, NL802154_ATTR_IFTYPE, wpan_dev->iftype) || nla_put_u64_64bit(msg, NL802154_ATTR_WPAN_DEV, wpan_dev_id(wpan_dev), NL802154_ATTR_PAD) || nla_put_u32(msg, NL802154_ATTR_GENERATION, rdev->devlist_generation ^ (cfg802154_rdev_list_generation << 2))) goto nla_put_failure; /* address settings */ if (nla_put_le64(msg, NL802154_ATTR_EXTENDED_ADDR, wpan_dev->extended_addr, NL802154_ATTR_PAD) || nla_put_le16(msg, NL802154_ATTR_SHORT_ADDR, wpan_dev->short_addr) || nla_put_le16(msg, NL802154_ATTR_PAN_ID, wpan_dev->pan_id)) goto nla_put_failure; /* ARET handling */ if (nla_put_s8(msg, NL802154_ATTR_MAX_FRAME_RETRIES, wpan_dev->frame_retries) || nla_put_u8(msg, NL802154_ATTR_MAX_BE, wpan_dev->max_be) || nla_put_u8(msg, NL802154_ATTR_MAX_CSMA_BACKOFFS, wpan_dev->csma_retries) || nla_put_u8(msg, NL802154_ATTR_MIN_BE, wpan_dev->min_be)) goto nla_put_failure; /* listen before transmit */ if (nla_put_u8(msg, NL802154_ATTR_LBT_MODE, wpan_dev->lbt)) goto nla_put_failure; /* ackreq default behaviour */ if (nla_put_u8(msg, NL802154_ATTR_ACKREQ_DEFAULT, wpan_dev->ackreq)) goto nla_put_failure; #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) goto out; if (nl802154_get_llsec_params(msg, rdev, wpan_dev) < 0) goto nla_put_failure; out: #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_dump_interface(struct sk_buff *skb, struct netlink_callback *cb) { int wp_idx = 0; int if_idx = 0; int wp_start = cb->args[0]; int if_start = cb->args[1]; struct cfg802154_registered_device *rdev; struct wpan_dev *wpan_dev; rtnl_lock(); list_for_each_entry(rdev, &cfg802154_rdev_list, list) { if (!net_eq(wpan_phy_net(&rdev->wpan_phy), sock_net(skb->sk))) continue; if (wp_idx < wp_start) { wp_idx++; continue; } if_idx = 0; list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) { if (if_idx < if_start) { if_idx++; continue; } if (nl802154_send_iface(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev) < 0) { goto out; } if_idx++; } wp_idx++; } out: rtnl_unlock(); cb->args[0] = wp_idx; cb->args[1] = if_idx; return skb->len; } static int nl802154_get_interface(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct wpan_dev *wdev = info->user_ptr[1]; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; if (nl802154_send_iface(msg, info->snd_portid, info->snd_seq, 0, rdev, wdev) < 0) { nlmsg_free(msg); return -ENOBUFS; } return genlmsg_reply(msg, info); } static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; enum nl802154_iftype type = NL802154_IFTYPE_UNSPEC; __le64 extended_addr = cpu_to_le64(0x0000000000000000ULL); /* TODO avoid failing a new interface * creation due to pending removal? */ if (!info->attrs[NL802154_ATTR_IFNAME]) return -EINVAL; if (info->attrs[NL802154_ATTR_IFTYPE]) { type = nla_get_u32(info->attrs[NL802154_ATTR_IFTYPE]); if (type > NL802154_IFTYPE_MAX || !(rdev->wpan_phy.supported.iftypes & BIT(type))) return -EINVAL; } if (info->attrs[NL802154_ATTR_EXTENDED_ADDR]) extended_addr = nla_get_le64(info->attrs[NL802154_ATTR_EXTENDED_ADDR]); if (!rdev->ops->add_virtual_intf) return -EOPNOTSUPP; return rdev_add_virtual_intf(rdev, nla_data(info->attrs[NL802154_ATTR_IFNAME]), NET_NAME_USER, type, extended_addr); } static int nl802154_del_interface(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct wpan_dev *wpan_dev = info->user_ptr[1]; if (!rdev->ops->del_virtual_intf) return -EOPNOTSUPP; /* If we remove a wpan device without a netdev then clear * user_ptr[1] so that nl802154_post_doit won't dereference it * to check if it needs to do dev_put(). Otherwise it crashes * since the wpan_dev has been freed, unlike with a netdev where * we need the dev_put() for the netdev to really be freed. */ if (!wpan_dev->netdev) info->user_ptr[1] = NULL; return rdev_del_virtual_intf(rdev, wpan_dev); } static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; u8 channel, page; if (!info->attrs[NL802154_ATTR_PAGE] || !info->attrs[NL802154_ATTR_CHANNEL]) return -EINVAL; page = nla_get_u8(info->attrs[NL802154_ATTR_PAGE]); channel = nla_get_u8(info->attrs[NL802154_ATTR_CHANNEL]); /* check 802.15.4 constraints */ if (!ieee802154_chan_is_valid(&rdev->wpan_phy, page, channel)) return -EINVAL; return rdev_set_channel(rdev, page, channel); } static int nl802154_set_cca_mode(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct wpan_phy_cca cca; if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_MODE)) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_CCA_MODE]) return -EINVAL; cca.mode = nla_get_u32(info->attrs[NL802154_ATTR_CCA_MODE]); /* checking 802.15.4 constraints */ if (cca.mode < NL802154_CCA_ENERGY || cca.mode > NL802154_CCA_ATTR_MAX || !(rdev->wpan_phy.supported.cca_modes & BIT(cca.mode))) return -EINVAL; if (cca.mode == NL802154_CCA_ENERGY_CARRIER) { if (!info->attrs[NL802154_ATTR_CCA_OPT]) return -EINVAL; cca.opt = nla_get_u32(info->attrs[NL802154_ATTR_CCA_OPT]); if (cca.opt > NL802154_CCA_OPT_ATTR_MAX || !(rdev->wpan_phy.supported.cca_opts & BIT(cca.opt))) return -EINVAL; } return rdev_set_cca_mode(rdev, &cca); } static int nl802154_set_cca_ed_level(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; s32 ed_level; int i; if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL)) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_CCA_ED_LEVEL]) return -EINVAL; ed_level = nla_get_s32(info->attrs[NL802154_ATTR_CCA_ED_LEVEL]); for (i = 0; i < rdev->wpan_phy.supported.cca_ed_levels_size; i++) { if (ed_level == rdev->wpan_phy.supported.cca_ed_levels[i]) return rdev_set_cca_ed_level(rdev, ed_level); } return -EINVAL; } static int nl802154_set_tx_power(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; s32 power; int i; if (!(rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER)) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_TX_POWER]) return -EINVAL; power = nla_get_s32(info->attrs[NL802154_ATTR_TX_POWER]); for (i = 0; i < rdev->wpan_phy.supported.tx_powers_size; i++) { if (power == rdev->wpan_phy.supported.tx_powers[i]) return rdev_set_tx_power(rdev, power); } return -EINVAL; } static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; __le16 pan_id; /* conflict here while tx/rx calls */ if (netif_running(dev)) return -EBUSY; if (wpan_dev->lowpan_dev) { if (netif_running(wpan_dev->lowpan_dev)) return -EBUSY; } /* don't change address fields on monitor */ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR || !info->attrs[NL802154_ATTR_PAN_ID]) return -EINVAL; pan_id = nla_get_le16(info->attrs[NL802154_ATTR_PAN_ID]); /* Only allow changing the PAN ID when the device has no more * associations ongoing to avoid confusing peers. */ if (cfg802154_device_is_associated(wpan_dev)) { NL_SET_ERR_MSG(info->extack, "Existing associations, changing PAN ID forbidden"); return -EINVAL; } return rdev_set_pan_id(rdev, wpan_dev, pan_id); } static int nl802154_set_short_addr(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; __le16 short_addr; /* conflict here while tx/rx calls */ if (netif_running(dev)) return -EBUSY; if (wpan_dev->lowpan_dev) { if (netif_running(wpan_dev->lowpan_dev)) return -EBUSY; } /* don't change address fields on monitor */ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR || !info->attrs[NL802154_ATTR_SHORT_ADDR]) return -EINVAL; short_addr = nla_get_le16(info->attrs[NL802154_ATTR_SHORT_ADDR]); /* The short address only has a meaning when part of a PAN, after a * proper association procedure. However, we want to still offer the * possibility to create static networks so changing the short address * is only allowed when not already associated to other devices with * the official handshake. */ if (cfg802154_device_is_associated(wpan_dev)) { NL_SET_ERR_MSG(info->extack, "Existing associations, changing short address forbidden"); return -EINVAL; } return rdev_set_short_addr(rdev, wpan_dev, short_addr); } static int nl802154_set_backoff_exponent(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; u8 min_be, max_be; /* should be set on netif open inside phy settings */ if (netif_running(dev)) return -EBUSY; if (!info->attrs[NL802154_ATTR_MIN_BE] || !info->attrs[NL802154_ATTR_MAX_BE]) return -EINVAL; min_be = nla_get_u8(info->attrs[NL802154_ATTR_MIN_BE]); max_be = nla_get_u8(info->attrs[NL802154_ATTR_MAX_BE]); /* check 802.15.4 constraints */ if (min_be < rdev->wpan_phy.supported.min_minbe || min_be > rdev->wpan_phy.supported.max_minbe || max_be < rdev->wpan_phy.supported.min_maxbe || max_be > rdev->wpan_phy.supported.max_maxbe || min_be > max_be) return -EINVAL; return rdev_set_backoff_exponent(rdev, wpan_dev, min_be, max_be); } static int nl802154_set_max_csma_backoffs(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; u8 max_csma_backoffs; /* conflict here while other running iface settings */ if (netif_running(dev)) return -EBUSY; if (!info->attrs[NL802154_ATTR_MAX_CSMA_BACKOFFS]) return -EINVAL; max_csma_backoffs = nla_get_u8( info->attrs[NL802154_ATTR_MAX_CSMA_BACKOFFS]); /* check 802.15.4 constraints */ if (max_csma_backoffs < rdev->wpan_phy.supported.min_csma_backoffs || max_csma_backoffs > rdev->wpan_phy.supported.max_csma_backoffs) return -EINVAL; return rdev_set_max_csma_backoffs(rdev, wpan_dev, max_csma_backoffs); } static int nl802154_set_max_frame_retries(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; s8 max_frame_retries; if (netif_running(dev)) return -EBUSY; if (!info->attrs[NL802154_ATTR_MAX_FRAME_RETRIES]) return -EINVAL; max_frame_retries = nla_get_s8( info->attrs[NL802154_ATTR_MAX_FRAME_RETRIES]); /* check 802.15.4 constraints */ if (max_frame_retries < rdev->wpan_phy.supported.min_frame_retries || max_frame_retries > rdev->wpan_phy.supported.max_frame_retries) return -EINVAL; return rdev_set_max_frame_retries(rdev, wpan_dev, max_frame_retries); } static int nl802154_set_lbt_mode(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; int mode; if (netif_running(dev)) return -EBUSY; if (!info->attrs[NL802154_ATTR_LBT_MODE]) return -EINVAL; mode = nla_get_u8(info->attrs[NL802154_ATTR_LBT_MODE]); if (mode != 0 && mode != 1) return -EINVAL; if (!wpan_phy_supported_bool(mode, rdev->wpan_phy.supported.lbt)) return -EINVAL; return rdev_set_lbt_mode(rdev, wpan_dev, mode); } static int nl802154_set_ackreq_default(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; int ackreq; if (netif_running(dev)) return -EBUSY; if (!info->attrs[NL802154_ATTR_ACKREQ_DEFAULT]) return -EINVAL; ackreq = nla_get_u8(info->attrs[NL802154_ATTR_ACKREQ_DEFAULT]); if (ackreq != 0 && ackreq != 1) return -EINVAL; return rdev_set_ackreq_default(rdev, wpan_dev, ackreq); } static int nl802154_wpan_phy_netns(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net *net; int err; if (info->attrs[NL802154_ATTR_PID]) { u32 pid = nla_get_u32(info->attrs[NL802154_ATTR_PID]); net = get_net_ns_by_pid(pid); } else if (info->attrs[NL802154_ATTR_NETNS_FD]) { u32 fd = nla_get_u32(info->attrs[NL802154_ATTR_NETNS_FD]); net = get_net_ns_by_fd(fd); } else { return -EINVAL; } if (IS_ERR(net)) return PTR_ERR(net); err = 0; /* check if anything to do */ if (!net_eq(wpan_phy_net(&rdev->wpan_phy), net)) err = cfg802154_switch_netns(rdev, net); put_net(net); return err; } static int nl802154_prep_scan_event_msg(struct sk_buff *msg, struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, u32 portid, u32 seq, int flags, u8 cmd, struct ieee802154_coord_desc *desc) { struct nlattr *nla; void *hdr; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_WPAN_PHY, rdev->wpan_phy_idx)) goto nla_put_failure; if (wpan_dev->netdev && nla_put_u32(msg, NL802154_ATTR_IFINDEX, wpan_dev->netdev->ifindex)) goto nla_put_failure; if (nla_put_u64_64bit(msg, NL802154_ATTR_WPAN_DEV, wpan_dev_id(wpan_dev), NL802154_ATTR_PAD)) goto nla_put_failure; nla = nla_nest_start_noflag(msg, NL802154_ATTR_COORDINATOR); if (!nla) goto nla_put_failure; if (nla_put(msg, NL802154_COORD_PANID, IEEE802154_PAN_ID_LEN, &desc->addr.pan_id)) goto nla_put_failure; if (desc->addr.mode == IEEE802154_ADDR_SHORT) { if (nla_put(msg, NL802154_COORD_ADDR, IEEE802154_SHORT_ADDR_LEN, &desc->addr.short_addr)) goto nla_put_failure; } else { if (nla_put(msg, NL802154_COORD_ADDR, IEEE802154_EXTENDED_ADDR_LEN, &desc->addr.extended_addr)) goto nla_put_failure; } if (nla_put_u8(msg, NL802154_COORD_CHANNEL, desc->channel)) goto nla_put_failure; if (nla_put_u8(msg, NL802154_COORD_PAGE, desc->page)) goto nla_put_failure; if (nla_put_u16(msg, NL802154_COORD_SUPERFRAME_SPEC, desc->superframe_spec)) goto nla_put_failure; if (nla_put_u8(msg, NL802154_COORD_LINK_QUALITY, desc->link_quality)) goto nla_put_failure; if (desc->gts_permit && nla_put_flag(msg, NL802154_COORD_GTS_PERMIT)) goto nla_put_failure; /* TODO: NL802154_COORD_PAYLOAD_DATA if any */ nla_nest_end(msg, nla); genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } int nl802154_scan_event(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, struct ieee802154_coord_desc *desc) { struct cfg802154_registered_device *rdev = wpan_phy_to_rdev(wpan_phy); struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; ret = nl802154_prep_scan_event_msg(msg, rdev, wpan_dev, 0, 0, 0, NL802154_CMD_SCAN_EVENT, desc); if (ret < 0) { nlmsg_free(msg); return ret; } return genlmsg_multicast_netns(&nl802154_fam, wpan_phy_net(wpan_phy), msg, 0, NL802154_MCGRP_SCAN, GFP_ATOMIC); } EXPORT_SYMBOL_GPL(nl802154_scan_event); static int nl802154_trigger_scan(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct wpan_phy *wpan_phy = &rdev->wpan_phy; struct cfg802154_scan_request *request; u8 type; int err; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { NL_SET_ERR_MSG(info->extack, "Monitors are not allowed to perform scans"); return -EOPNOTSUPP; } if (!info->attrs[NL802154_ATTR_SCAN_TYPE]) { NL_SET_ERR_MSG(info->extack, "Malformed request, missing scan type"); return -EINVAL; } if (wpan_phy->flags & WPAN_PHY_FLAG_DATAGRAMS_ONLY) { NL_SET_ERR_MSG(info->extack, "PHY only supports datagrams"); return -EOPNOTSUPP; } request = kzalloc(sizeof(*request), GFP_KERNEL); if (!request) return -ENOMEM; request->wpan_dev = wpan_dev; request->wpan_phy = wpan_phy; type = nla_get_u8(info->attrs[NL802154_ATTR_SCAN_TYPE]); switch (type) { case NL802154_SCAN_ACTIVE: case NL802154_SCAN_PASSIVE: request->type = type; break; default: NL_SET_ERR_MSG_FMT(info->extack, "Unsupported scan type: %d", type); err = -EINVAL; goto free_request; } /* Use current page by default */ if (info->attrs[NL802154_ATTR_PAGE]) request->page = nla_get_u8(info->attrs[NL802154_ATTR_PAGE]); else request->page = wpan_phy->current_page; /* Scan all supported channels by default */ if (info->attrs[NL802154_ATTR_SCAN_CHANNELS]) request->channels = nla_get_u32(info->attrs[NL802154_ATTR_SCAN_CHANNELS]); else request->channels = wpan_phy->supported.channels[request->page]; /* Use maximum duration order by default */ if (info->attrs[NL802154_ATTR_SCAN_DURATION]) request->duration = nla_get_u8(info->attrs[NL802154_ATTR_SCAN_DURATION]); else request->duration = IEEE802154_MAX_SCAN_DURATION; err = rdev_trigger_scan(rdev, request); if (err) { pr_err("Failure starting scanning (%d)\n", err); goto free_request; } return 0; free_request: kfree(request); return err; } static int nl802154_prep_scan_msg(struct sk_buff *msg, struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, u32 portid, u32 seq, int flags, u8 cmd, u8 arg) { void *hdr; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_WPAN_PHY, rdev->wpan_phy_idx)) goto nla_put_failure; if (wpan_dev->netdev && nla_put_u32(msg, NL802154_ATTR_IFINDEX, wpan_dev->netdev->ifindex)) goto nla_put_failure; if (nla_put_u64_64bit(msg, NL802154_ATTR_WPAN_DEV, wpan_dev_id(wpan_dev), NL802154_ATTR_PAD)) goto nla_put_failure; if (cmd == NL802154_CMD_SCAN_DONE && nla_put_u8(msg, NL802154_ATTR_SCAN_DONE_REASON, arg)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_send_scan_msg(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, u8 cmd, u8 arg) { struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = nl802154_prep_scan_msg(msg, rdev, wpan_dev, 0, 0, 0, cmd, arg); if (ret < 0) { nlmsg_free(msg); return ret; } return genlmsg_multicast_netns(&nl802154_fam, wpan_phy_net(&rdev->wpan_phy), msg, 0, NL802154_MCGRP_SCAN, GFP_KERNEL); } int nl802154_scan_started(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev) { struct cfg802154_registered_device *rdev = wpan_phy_to_rdev(wpan_phy); int err; /* Ignore errors when there are no listeners */ err = nl802154_send_scan_msg(rdev, wpan_dev, NL802154_CMD_TRIGGER_SCAN, 0); if (err == -ESRCH) err = 0; return err; } EXPORT_SYMBOL_GPL(nl802154_scan_started); int nl802154_scan_done(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, enum nl802154_scan_done_reasons reason) { struct cfg802154_registered_device *rdev = wpan_phy_to_rdev(wpan_phy); int err; /* Ignore errors when there are no listeners */ err = nl802154_send_scan_msg(rdev, wpan_dev, NL802154_CMD_SCAN_DONE, reason); if (err == -ESRCH) err = 0; return err; } EXPORT_SYMBOL_GPL(nl802154_scan_done); static int nl802154_abort_scan(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; /* Resources are released in the notification helper above */ return rdev_abort_scan(rdev, wpan_dev); } static int nl802154_send_beacons(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct wpan_phy *wpan_phy = &rdev->wpan_phy; struct cfg802154_beacon_request *request; int err; if (wpan_dev->iftype != NL802154_IFTYPE_COORD) { NL_SET_ERR_MSG(info->extack, "Only coordinators can send beacons"); return -EOPNOTSUPP; } if (wpan_dev->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) { NL_SET_ERR_MSG(info->extack, "Device is not part of any PAN"); return -EPERM; } if (wpan_phy->flags & WPAN_PHY_FLAG_DATAGRAMS_ONLY) { NL_SET_ERR_MSG(info->extack, "PHY only supports datagrams"); return -EOPNOTSUPP; } request = kzalloc(sizeof(*request), GFP_KERNEL); if (!request) return -ENOMEM; request->wpan_dev = wpan_dev; request->wpan_phy = wpan_phy; /* Use maximum duration order by default */ if (info->attrs[NL802154_ATTR_BEACON_INTERVAL]) request->interval = nla_get_u8(info->attrs[NL802154_ATTR_BEACON_INTERVAL]); else request->interval = IEEE802154_MAX_SCAN_DURATION; err = rdev_send_beacons(rdev, request); if (err) { pr_err("Failure starting sending beacons (%d)\n", err); goto free_request; } return 0; free_request: kfree(request); return err; } void nl802154_beaconing_done(struct wpan_dev *wpan_dev) { /* NOP */ } EXPORT_SYMBOL_GPL(nl802154_beaconing_done); static int nl802154_stop_beacons(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; /* Resources are released in the notification helper above */ return rdev_stop_beacons(rdev, wpan_dev); } static int nl802154_associate(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev; struct wpan_phy *wpan_phy; struct ieee802154_addr coord; int err; wpan_dev = dev->ieee802154_ptr; wpan_phy = &rdev->wpan_phy; if (wpan_phy->flags & WPAN_PHY_FLAG_DATAGRAMS_ONLY) { NL_SET_ERR_MSG(info->extack, "PHY only supports datagrams"); return -EOPNOTSUPP; } if (!info->attrs[NL802154_ATTR_PAN_ID] || !info->attrs[NL802154_ATTR_EXTENDED_ADDR]) return -EINVAL; coord.pan_id = nla_get_le16(info->attrs[NL802154_ATTR_PAN_ID]); coord.mode = IEEE802154_ADDR_LONG; coord.extended_addr = nla_get_le64(info->attrs[NL802154_ATTR_EXTENDED_ADDR]); mutex_lock(&wpan_dev->association_lock); err = rdev_associate(rdev, wpan_dev, &coord); mutex_unlock(&wpan_dev->association_lock); if (err) pr_err("Association with PAN ID 0x%x failed (%d)\n", le16_to_cpu(coord.pan_id), err); return err; } static int nl802154_disassociate(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct wpan_phy *wpan_phy = &rdev->wpan_phy; struct ieee802154_addr target; if (wpan_phy->flags & WPAN_PHY_FLAG_DATAGRAMS_ONLY) { NL_SET_ERR_MSG(info->extack, "PHY only supports datagrams"); return -EOPNOTSUPP; } target.pan_id = wpan_dev->pan_id; if (info->attrs[NL802154_ATTR_EXTENDED_ADDR]) { target.mode = IEEE802154_ADDR_LONG; target.extended_addr = nla_get_le64(info->attrs[NL802154_ATTR_EXTENDED_ADDR]); } else if (info->attrs[NL802154_ATTR_SHORT_ADDR]) { target.mode = IEEE802154_ADDR_SHORT; target.short_addr = nla_get_le16(info->attrs[NL802154_ATTR_SHORT_ADDR]); } else { NL_SET_ERR_MSG(info->extack, "Device address is missing"); return -EINVAL; } mutex_lock(&wpan_dev->association_lock); rdev_disassociate(rdev, wpan_dev, &target); mutex_unlock(&wpan_dev->association_lock); return 0; } static int nl802154_set_max_associations(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; unsigned int max_assoc; if (!info->attrs[NL802154_ATTR_MAX_ASSOCIATIONS]) { NL_SET_ERR_MSG(info->extack, "No maximum number of association given"); return -EINVAL; } max_assoc = nla_get_u32(info->attrs[NL802154_ATTR_MAX_ASSOCIATIONS]); mutex_lock(&wpan_dev->association_lock); cfg802154_set_max_associations(wpan_dev, max_assoc); mutex_unlock(&wpan_dev->association_lock); return 0; } static int nl802154_send_peer_info(struct sk_buff *msg, struct netlink_callback *cb, u32 seq, int flags, struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, struct ieee802154_pan_device *peer, enum nl802154_peer_type type) { struct nlattr *nla; void *hdr; ASSERT_RTNL(); hdr = nl802154hdr_put(msg, NETLINK_CB(cb->skb).portid, seq, flags, NL802154_CMD_LIST_ASSOCIATIONS); if (!hdr) return -ENOBUFS; genl_dump_check_consistent(cb, hdr); nla = nla_nest_start_noflag(msg, NL802154_ATTR_PEER); if (!nla) goto nla_put_failure; if (nla_put_u8(msg, NL802154_DEV_ADDR_ATTR_PEER_TYPE, type)) goto nla_put_failure; if (nla_put_u8(msg, NL802154_DEV_ADDR_ATTR_MODE, peer->mode)) goto nla_put_failure; if (nla_put(msg, NL802154_DEV_ADDR_ATTR_SHORT, IEEE802154_SHORT_ADDR_LEN, &peer->short_addr)) goto nla_put_failure; if (nla_put(msg, NL802154_DEV_ADDR_ATTR_EXTENDED, IEEE802154_EXTENDED_ADDR_LEN, &peer->extended_addr)) goto nla_put_failure; nla_nest_end(msg, nla); genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_list_associations(struct sk_buff *skb, struct netlink_callback *cb) { struct cfg802154_registered_device *rdev; struct ieee802154_pan_device *child; struct wpan_dev *wpan_dev; int err; err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); if (err) return err; mutex_lock(&wpan_dev->association_lock); if (cb->args[2]) goto out; if (wpan_dev->parent) { err = nl802154_send_peer_info(skb, cb, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev, wpan_dev->parent, NL802154_PEER_TYPE_PARENT); if (err < 0) goto out_err; } list_for_each_entry(child, &wpan_dev->children, node) { err = nl802154_send_peer_info(skb, cb, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev, child, NL802154_PEER_TYPE_CHILD); if (err < 0) goto out_err; } cb->args[2] = 1; out: err = skb->len; out_err: mutex_unlock(&wpan_dev->association_lock); nl802154_finish_wpan_dev_dump(rdev); return err; } #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL static const struct nla_policy nl802154_dev_addr_policy[NL802154_DEV_ADDR_ATTR_MAX + 1] = { [NL802154_DEV_ADDR_ATTR_PAN_ID] = { .type = NLA_U16 }, [NL802154_DEV_ADDR_ATTR_MODE] = { .type = NLA_U32 }, [NL802154_DEV_ADDR_ATTR_SHORT] = { .type = NLA_U16 }, [NL802154_DEV_ADDR_ATTR_EXTENDED] = { .type = NLA_U64 }, }; static int ieee802154_llsec_parse_dev_addr(struct nlattr *nla, struct ieee802154_addr *addr) { struct nlattr *attrs[NL802154_DEV_ADDR_ATTR_MAX + 1]; if (!nla || nla_parse_nested_deprecated(attrs, NL802154_DEV_ADDR_ATTR_MAX, nla, nl802154_dev_addr_policy, NULL)) return -EINVAL; if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] || !attrs[NL802154_DEV_ADDR_ATTR_MODE]) return -EINVAL; addr->pan_id = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_PAN_ID]); addr->mode = nla_get_u32(attrs[NL802154_DEV_ADDR_ATTR_MODE]); switch (addr->mode) { case NL802154_DEV_ADDR_SHORT: if (!attrs[NL802154_DEV_ADDR_ATTR_SHORT]) return -EINVAL; addr->short_addr = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_SHORT]); break; case NL802154_DEV_ADDR_EXTENDED: if (!attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]) return -EINVAL; addr->extended_addr = nla_get_le64(attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]); break; default: return -EINVAL; } return 0; } static const struct nla_policy nl802154_key_id_policy[NL802154_KEY_ID_ATTR_MAX + 1] = { [NL802154_KEY_ID_ATTR_MODE] = { .type = NLA_U32 }, [NL802154_KEY_ID_ATTR_INDEX] = { .type = NLA_U8 }, [NL802154_KEY_ID_ATTR_IMPLICIT] = { .type = NLA_NESTED }, [NL802154_KEY_ID_ATTR_SOURCE_SHORT] = { .type = NLA_U32 }, [NL802154_KEY_ID_ATTR_SOURCE_EXTENDED] = { .type = NLA_U64 }, }; static int ieee802154_llsec_parse_key_id(struct nlattr *nla, struct ieee802154_llsec_key_id *desc) { struct nlattr *attrs[NL802154_KEY_ID_ATTR_MAX + 1]; if (!nla || nla_parse_nested_deprecated(attrs, NL802154_KEY_ID_ATTR_MAX, nla, nl802154_key_id_policy, NULL)) return -EINVAL; if (!attrs[NL802154_KEY_ID_ATTR_MODE]) return -EINVAL; desc->mode = nla_get_u32(attrs[NL802154_KEY_ID_ATTR_MODE]); switch (desc->mode) { case NL802154_KEY_ID_MODE_IMPLICIT: if (!attrs[NL802154_KEY_ID_ATTR_IMPLICIT]) return -EINVAL; if (ieee802154_llsec_parse_dev_addr(attrs[NL802154_KEY_ID_ATTR_IMPLICIT], &desc->device_addr) < 0) return -EINVAL; break; case NL802154_KEY_ID_MODE_INDEX: break; case NL802154_KEY_ID_MODE_INDEX_SHORT: if (!attrs[NL802154_KEY_ID_ATTR_SOURCE_SHORT]) return -EINVAL; desc->short_source = nla_get_le32(attrs[NL802154_KEY_ID_ATTR_SOURCE_SHORT]); break; case NL802154_KEY_ID_MODE_INDEX_EXTENDED: if (!attrs[NL802154_KEY_ID_ATTR_SOURCE_EXTENDED]) return -EINVAL; desc->extended_source = nla_get_le64(attrs[NL802154_KEY_ID_ATTR_SOURCE_EXTENDED]); break; default: return -EINVAL; } if (desc->mode != NL802154_KEY_ID_MODE_IMPLICIT) { if (!attrs[NL802154_KEY_ID_ATTR_INDEX]) return -EINVAL; /* TODO change id to idx */ desc->id = nla_get_u8(attrs[NL802154_KEY_ID_ATTR_INDEX]); } return 0; } static int nl802154_set_llsec_params(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_params params; u32 changed = 0; int ret; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (info->attrs[NL802154_ATTR_SEC_ENABLED]) { u8 enabled; enabled = nla_get_u8(info->attrs[NL802154_ATTR_SEC_ENABLED]); if (enabled != 0 && enabled != 1) return -EINVAL; params.enabled = nla_get_u8(info->attrs[NL802154_ATTR_SEC_ENABLED]); changed |= IEEE802154_LLSEC_PARAM_ENABLED; } if (info->attrs[NL802154_ATTR_SEC_OUT_KEY_ID]) { ret = ieee802154_llsec_parse_key_id(info->attrs[NL802154_ATTR_SEC_OUT_KEY_ID], ¶ms.out_key); if (ret < 0) return ret; changed |= IEEE802154_LLSEC_PARAM_OUT_KEY; } if (info->attrs[NL802154_ATTR_SEC_OUT_LEVEL]) { params.out_level = nla_get_u32(info->attrs[NL802154_ATTR_SEC_OUT_LEVEL]); if (params.out_level > NL802154_SECLEVEL_MAX) return -EINVAL; changed |= IEEE802154_LLSEC_PARAM_OUT_LEVEL; } if (info->attrs[NL802154_ATTR_SEC_FRAME_COUNTER]) { params.frame_counter = nla_get_be32(info->attrs[NL802154_ATTR_SEC_FRAME_COUNTER]); changed |= IEEE802154_LLSEC_PARAM_FRAME_COUNTER; } return rdev_set_llsec_params(rdev, wpan_dev, ¶ms, changed); } static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid, u32 seq, int flags, struct cfg802154_registered_device *rdev, struct net_device *dev, const struct ieee802154_llsec_key_entry *key) { void *hdr; u32 commands[NL802154_CMD_FRAME_NR_IDS / 32]; struct nlattr *nl_key, *nl_key_id; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; nl_key = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_KEY); if (!nl_key) goto nla_put_failure; nl_key_id = nla_nest_start_noflag(msg, NL802154_KEY_ATTR_ID); if (!nl_key_id) goto nla_put_failure; if (ieee802154_llsec_send_key_id(msg, &key->id) < 0) goto nla_put_failure; nla_nest_end(msg, nl_key_id); if (nla_put_u8(msg, NL802154_KEY_ATTR_USAGE_FRAMES, key->key->frame_types)) goto nla_put_failure; if (key->key->frame_types & BIT(NL802154_FRAME_CMD)) { /* TODO for each nested */ memset(commands, 0, sizeof(commands)); commands[7] = key->key->cmd_frame_ids; if (nla_put(msg, NL802154_KEY_ATTR_USAGE_CMDS, sizeof(commands), commands)) goto nla_put_failure; } if (nla_put(msg, NL802154_KEY_ATTR_BYTES, NL802154_KEY_SIZE, key->key->key)) goto nla_put_failure; nla_nest_end(msg, nl_key); genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_dump_llsec_key(struct sk_buff *skb, struct netlink_callback *cb) { struct cfg802154_registered_device *rdev = NULL; struct ieee802154_llsec_key_entry *key; struct ieee802154_llsec_table *table; struct wpan_dev *wpan_dev; int err; err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); if (err) return err; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { err = skb->len; goto out_err; } if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; } rdev_lock_llsec_table(rdev, wpan_dev); rdev_get_llsec_table(rdev, wpan_dev, &table); /* TODO make it like station dump */ if (cb->args[2]) goto out; list_for_each_entry(key, &table->keys, list) { if (nl802154_send_key(skb, NL802154_CMD_NEW_SEC_KEY, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev->netdev, key) < 0) { /* TODO */ err = -EIO; rdev_unlock_llsec_table(rdev, wpan_dev); goto out_err; } } cb->args[2] = 1; out: rdev_unlock_llsec_table(rdev, wpan_dev); err = skb->len; out_err: nl802154_finish_wpan_dev_dump(rdev); return err; } static const struct nla_policy nl802154_key_policy[NL802154_KEY_ATTR_MAX + 1] = { [NL802154_KEY_ATTR_ID] = { NLA_NESTED }, /* TODO handle it as for_each_nested and NLA_FLAG? */ [NL802154_KEY_ATTR_USAGE_FRAMES] = { NLA_U8 }, /* TODO handle it as for_each_nested, not static array? */ [NL802154_KEY_ATTR_USAGE_CMDS] = { .len = NL802154_CMD_FRAME_NR_IDS / 8 }, [NL802154_KEY_ATTR_BYTES] = { .len = NL802154_KEY_SIZE }, }; static int nl802154_add_llsec_key(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1]; struct ieee802154_llsec_key key = { }; struct ieee802154_llsec_key_id id = { }; u32 commands[NL802154_CMD_FRAME_NR_IDS / 32] = { }; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_SEC_KEY] || nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack)) return -EINVAL; if (!attrs[NL802154_KEY_ATTR_USAGE_FRAMES] || !attrs[NL802154_KEY_ATTR_BYTES]) return -EINVAL; if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0) return -ENOBUFS; key.frame_types = nla_get_u8(attrs[NL802154_KEY_ATTR_USAGE_FRAMES]); if (key.frame_types > BIT(NL802154_FRAME_MAX) || ((key.frame_types & BIT(NL802154_FRAME_CMD)) && !attrs[NL802154_KEY_ATTR_USAGE_CMDS])) return -EINVAL; if (attrs[NL802154_KEY_ATTR_USAGE_CMDS]) { /* TODO for each nested */ nla_memcpy(commands, attrs[NL802154_KEY_ATTR_USAGE_CMDS], NL802154_CMD_FRAME_NR_IDS / 8); /* TODO understand the -EINVAL logic here? last condition */ if (commands[0] || commands[1] || commands[2] || commands[3] || commands[4] || commands[5] || commands[6] || commands[7] > BIT(NL802154_CMD_FRAME_MAX)) return -EINVAL; key.cmd_frame_ids = commands[7]; } else { key.cmd_frame_ids = 0; } nla_memcpy(key.key, attrs[NL802154_KEY_ATTR_BYTES], NL802154_KEY_SIZE); if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0) return -ENOBUFS; return rdev_add_llsec_key(rdev, wpan_dev, &id, &key); } static int nl802154_del_llsec_key(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1]; struct ieee802154_llsec_key_id id; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_SEC_KEY] || nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack)) return -EINVAL; if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0) return -ENOBUFS; return rdev_del_llsec_key(rdev, wpan_dev, &id); } static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid, u32 seq, int flags, struct cfg802154_registered_device *rdev, struct net_device *dev, const struct ieee802154_llsec_device *dev_desc) { void *hdr; struct nlattr *nl_device; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; nl_device = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_DEVICE); if (!nl_device) goto nla_put_failure; if (nla_put_u32(msg, NL802154_DEV_ATTR_FRAME_COUNTER, dev_desc->frame_counter) || nla_put_le16(msg, NL802154_DEV_ATTR_PAN_ID, dev_desc->pan_id) || nla_put_le16(msg, NL802154_DEV_ATTR_SHORT_ADDR, dev_desc->short_addr) || nla_put_le64(msg, NL802154_DEV_ATTR_EXTENDED_ADDR, dev_desc->hwaddr, NL802154_DEV_ATTR_PAD) || nla_put_u8(msg, NL802154_DEV_ATTR_SECLEVEL_EXEMPT, dev_desc->seclevel_exempt) || nla_put_u32(msg, NL802154_DEV_ATTR_KEY_MODE, dev_desc->key_mode)) goto nla_put_failure; nla_nest_end(msg, nl_device); genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_dump_llsec_dev(struct sk_buff *skb, struct netlink_callback *cb) { struct cfg802154_registered_device *rdev = NULL; struct ieee802154_llsec_device *dev; struct ieee802154_llsec_table *table; struct wpan_dev *wpan_dev; int err; err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); if (err) return err; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { err = skb->len; goto out_err; } if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; } rdev_lock_llsec_table(rdev, wpan_dev); rdev_get_llsec_table(rdev, wpan_dev, &table); /* TODO make it like station dump */ if (cb->args[2]) goto out; list_for_each_entry(dev, &table->devices, list) { if (nl802154_send_device(skb, NL802154_CMD_NEW_SEC_LEVEL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev->netdev, dev) < 0) { /* TODO */ err = -EIO; rdev_unlock_llsec_table(rdev, wpan_dev); goto out_err; } } cb->args[2] = 1; out: rdev_unlock_llsec_table(rdev, wpan_dev); err = skb->len; out_err: nl802154_finish_wpan_dev_dump(rdev); return err; } static const struct nla_policy nl802154_dev_policy[NL802154_DEV_ATTR_MAX + 1] = { [NL802154_DEV_ATTR_FRAME_COUNTER] = { NLA_U32 }, [NL802154_DEV_ATTR_PAN_ID] = { .type = NLA_U16 }, [NL802154_DEV_ATTR_SHORT_ADDR] = { .type = NLA_U16 }, [NL802154_DEV_ATTR_EXTENDED_ADDR] = { .type = NLA_U64 }, [NL802154_DEV_ATTR_SECLEVEL_EXEMPT] = { NLA_U8 }, [NL802154_DEV_ATTR_KEY_MODE] = { NLA_U32 }, }; static int ieee802154_llsec_parse_device(struct nlattr *nla, struct ieee802154_llsec_device *dev) { struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1]; if (!nla || nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, nla, nl802154_dev_policy, NULL)) return -EINVAL; memset(dev, 0, sizeof(*dev)); if (!attrs[NL802154_DEV_ATTR_FRAME_COUNTER] || !attrs[NL802154_DEV_ATTR_PAN_ID] || !attrs[NL802154_DEV_ATTR_SHORT_ADDR] || !attrs[NL802154_DEV_ATTR_EXTENDED_ADDR] || !attrs[NL802154_DEV_ATTR_SECLEVEL_EXEMPT] || !attrs[NL802154_DEV_ATTR_KEY_MODE]) return -EINVAL; /* TODO be32 */ dev->frame_counter = nla_get_u32(attrs[NL802154_DEV_ATTR_FRAME_COUNTER]); dev->pan_id = nla_get_le16(attrs[NL802154_DEV_ATTR_PAN_ID]); dev->short_addr = nla_get_le16(attrs[NL802154_DEV_ATTR_SHORT_ADDR]); /* TODO rename hwaddr to extended_addr */ dev->hwaddr = nla_get_le64(attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]); dev->seclevel_exempt = nla_get_u8(attrs[NL802154_DEV_ATTR_SECLEVEL_EXEMPT]); dev->key_mode = nla_get_u32(attrs[NL802154_DEV_ATTR_KEY_MODE]); if (dev->key_mode > NL802154_DEVKEY_MAX || (dev->seclevel_exempt != 0 && dev->seclevel_exempt != 1)) return -EINVAL; return 0; } static int nl802154_add_llsec_dev(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_device dev_desc; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (ieee802154_llsec_parse_device(info->attrs[NL802154_ATTR_SEC_DEVICE], &dev_desc) < 0) return -EINVAL; return rdev_add_device(rdev, wpan_dev, &dev_desc); } static int nl802154_del_llsec_dev(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1]; __le64 extended_addr; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_SEC_DEVICE] || nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVICE], nl802154_dev_policy, info->extack)) return -EINVAL; if (!attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]) return -EINVAL; extended_addr = nla_get_le64(attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]); return rdev_del_device(rdev, wpan_dev, extended_addr); } static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid, u32 seq, int flags, struct cfg802154_registered_device *rdev, struct net_device *dev, __le64 extended_addr, const struct ieee802154_llsec_device_key *devkey) { void *hdr; struct nlattr *nl_devkey, *nl_key_id; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; nl_devkey = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_DEVKEY); if (!nl_devkey) goto nla_put_failure; if (nla_put_le64(msg, NL802154_DEVKEY_ATTR_EXTENDED_ADDR, extended_addr, NL802154_DEVKEY_ATTR_PAD) || nla_put_u32(msg, NL802154_DEVKEY_ATTR_FRAME_COUNTER, devkey->frame_counter)) goto nla_put_failure; nl_key_id = nla_nest_start_noflag(msg, NL802154_DEVKEY_ATTR_ID); if (!nl_key_id) goto nla_put_failure; if (ieee802154_llsec_send_key_id(msg, &devkey->key_id) < 0) goto nla_put_failure; nla_nest_end(msg, nl_key_id); nla_nest_end(msg, nl_devkey); genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_dump_llsec_devkey(struct sk_buff *skb, struct netlink_callback *cb) { struct cfg802154_registered_device *rdev = NULL; struct ieee802154_llsec_device_key *kpos; struct ieee802154_llsec_device *dpos; struct ieee802154_llsec_table *table; struct wpan_dev *wpan_dev; int err; err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); if (err) return err; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { err = skb->len; goto out_err; } if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; } rdev_lock_llsec_table(rdev, wpan_dev); rdev_get_llsec_table(rdev, wpan_dev, &table); /* TODO make it like station dump */ if (cb->args[2]) goto out; /* TODO look if remove devkey and do some nested attribute */ list_for_each_entry(dpos, &table->devices, list) { list_for_each_entry(kpos, &dpos->keys, list) { if (nl802154_send_devkey(skb, NL802154_CMD_NEW_SEC_LEVEL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev->netdev, dpos->hwaddr, kpos) < 0) { /* TODO */ err = -EIO; rdev_unlock_llsec_table(rdev, wpan_dev); goto out_err; } } } cb->args[2] = 1; out: rdev_unlock_llsec_table(rdev, wpan_dev); err = skb->len; out_err: nl802154_finish_wpan_dev_dump(rdev); return err; } static const struct nla_policy nl802154_devkey_policy[NL802154_DEVKEY_ATTR_MAX + 1] = { [NL802154_DEVKEY_ATTR_FRAME_COUNTER] = { NLA_U32 }, [NL802154_DEVKEY_ATTR_EXTENDED_ADDR] = { NLA_U64 }, [NL802154_DEVKEY_ATTR_ID] = { NLA_NESTED }, }; static int nl802154_add_llsec_devkey(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct nlattr *attrs[NL802154_DEVKEY_ATTR_MAX + 1]; struct ieee802154_llsec_device_key key; __le64 extended_addr; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] || nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack) < 0) return -EINVAL; if (!attrs[NL802154_DEVKEY_ATTR_FRAME_COUNTER] || !attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]) return -EINVAL; /* TODO change key.id ? */ if (ieee802154_llsec_parse_key_id(attrs[NL802154_DEVKEY_ATTR_ID], &key.key_id) < 0) return -ENOBUFS; /* TODO be32 */ key.frame_counter = nla_get_u32(attrs[NL802154_DEVKEY_ATTR_FRAME_COUNTER]); /* TODO change naming hwaddr -> extended_addr * check unique identifier short+pan OR extended_addr */ extended_addr = nla_get_le64(attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]); return rdev_add_devkey(rdev, wpan_dev, extended_addr, &key); } static int nl802154_del_llsec_devkey(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct nlattr *attrs[NL802154_DEVKEY_ATTR_MAX + 1]; struct ieee802154_llsec_device_key key; __le64 extended_addr; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] || nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack)) return -EINVAL; if (!attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]) return -EINVAL; /* TODO change key.id ? */ if (ieee802154_llsec_parse_key_id(attrs[NL802154_DEVKEY_ATTR_ID], &key.key_id) < 0) return -ENOBUFS; /* TODO change naming hwaddr -> extended_addr * check unique identifier short+pan OR extended_addr */ extended_addr = nla_get_le64(attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]); return rdev_del_devkey(rdev, wpan_dev, extended_addr, &key); } static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid, u32 seq, int flags, struct cfg802154_registered_device *rdev, struct net_device *dev, const struct ieee802154_llsec_seclevel *sl) { void *hdr; struct nlattr *nl_seclevel; hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; nl_seclevel = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_LEVEL); if (!nl_seclevel) goto nla_put_failure; if (nla_put_u32(msg, NL802154_SECLEVEL_ATTR_FRAME, sl->frame_type) || nla_put_u32(msg, NL802154_SECLEVEL_ATTR_LEVELS, sl->sec_levels) || nla_put_u8(msg, NL802154_SECLEVEL_ATTR_DEV_OVERRIDE, sl->device_override)) goto nla_put_failure; if (sl->frame_type == NL802154_FRAME_CMD) { if (nla_put_u32(msg, NL802154_SECLEVEL_ATTR_CMD_FRAME, sl->cmd_frame_id)) goto nla_put_failure; } nla_nest_end(msg, nl_seclevel); genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nl802154_dump_llsec_seclevel(struct sk_buff *skb, struct netlink_callback *cb) { struct cfg802154_registered_device *rdev = NULL; struct ieee802154_llsec_seclevel *sl; struct ieee802154_llsec_table *table; struct wpan_dev *wpan_dev; int err; err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev); if (err) return err; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { err = skb->len; goto out_err; } if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; } rdev_lock_llsec_table(rdev, wpan_dev); rdev_get_llsec_table(rdev, wpan_dev, &table); /* TODO make it like station dump */ if (cb->args[2]) goto out; list_for_each_entry(sl, &table->security_levels, list) { if (nl802154_send_seclevel(skb, NL802154_CMD_NEW_SEC_LEVEL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wpan_dev->netdev, sl) < 0) { /* TODO */ err = -EIO; rdev_unlock_llsec_table(rdev, wpan_dev); goto out_err; } } cb->args[2] = 1; out: rdev_unlock_llsec_table(rdev, wpan_dev); err = skb->len; out_err: nl802154_finish_wpan_dev_dump(rdev); return err; } static const struct nla_policy nl802154_seclevel_policy[NL802154_SECLEVEL_ATTR_MAX + 1] = { [NL802154_SECLEVEL_ATTR_LEVELS] = { .type = NLA_U8 }, [NL802154_SECLEVEL_ATTR_FRAME] = { .type = NLA_U32 }, [NL802154_SECLEVEL_ATTR_CMD_FRAME] = { .type = NLA_U32 }, [NL802154_SECLEVEL_ATTR_DEV_OVERRIDE] = { .type = NLA_U8 }, }; static int llsec_parse_seclevel(struct nlattr *nla, struct ieee802154_llsec_seclevel *sl) { struct nlattr *attrs[NL802154_SECLEVEL_ATTR_MAX + 1]; if (!nla || nla_parse_nested_deprecated(attrs, NL802154_SECLEVEL_ATTR_MAX, nla, nl802154_seclevel_policy, NULL)) return -EINVAL; memset(sl, 0, sizeof(*sl)); if (!attrs[NL802154_SECLEVEL_ATTR_LEVELS] || !attrs[NL802154_SECLEVEL_ATTR_FRAME] || !attrs[NL802154_SECLEVEL_ATTR_DEV_OVERRIDE]) return -EINVAL; sl->sec_levels = nla_get_u8(attrs[NL802154_SECLEVEL_ATTR_LEVELS]); sl->frame_type = nla_get_u32(attrs[NL802154_SECLEVEL_ATTR_FRAME]); sl->device_override = nla_get_u8(attrs[NL802154_SECLEVEL_ATTR_DEV_OVERRIDE]); if (sl->frame_type > NL802154_FRAME_MAX || (sl->device_override != 0 && sl->device_override != 1)) return -EINVAL; if (sl->frame_type == NL802154_FRAME_CMD) { if (!attrs[NL802154_SECLEVEL_ATTR_CMD_FRAME]) return -EINVAL; sl->cmd_frame_id = nla_get_u32(attrs[NL802154_SECLEVEL_ATTR_CMD_FRAME]); if (sl->cmd_frame_id > NL802154_CMD_FRAME_MAX) return -EINVAL; } return 0; } static int nl802154_add_llsec_seclevel(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_seclevel sl; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], &sl) < 0) return -EINVAL; return rdev_add_seclevel(rdev, wpan_dev, &sl); } static int nl802154_del_llsec_seclevel(struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_seclevel sl; if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; if (llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], &sl) < 0) return -EINVAL; return rdev_del_seclevel(rdev, wpan_dev, &sl); } #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ #define NL802154_FLAG_NEED_WPAN_PHY 0x01 #define NL802154_FLAG_NEED_NETDEV 0x02 #define NL802154_FLAG_NEED_RTNL 0x04 #define NL802154_FLAG_CHECK_NETDEV_UP 0x08 #define NL802154_FLAG_NEED_WPAN_DEV 0x10 static int nl802154_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev; struct wpan_dev *wpan_dev; struct net_device *dev; bool rtnl = ops->internal_flags & NL802154_FLAG_NEED_RTNL; if (rtnl) rtnl_lock(); if (ops->internal_flags & NL802154_FLAG_NEED_WPAN_PHY) { rdev = cfg802154_get_dev_from_info(genl_info_net(info), info); if (IS_ERR(rdev)) { if (rtnl) rtnl_unlock(); return PTR_ERR(rdev); } info->user_ptr[0] = rdev; } else if (ops->internal_flags & NL802154_FLAG_NEED_NETDEV || ops->internal_flags & NL802154_FLAG_NEED_WPAN_DEV) { ASSERT_RTNL(); wpan_dev = __cfg802154_wpan_dev_from_attrs(genl_info_net(info), info->attrs); if (IS_ERR(wpan_dev)) { if (rtnl) rtnl_unlock(); return PTR_ERR(wpan_dev); } dev = wpan_dev->netdev; rdev = wpan_phy_to_rdev(wpan_dev->wpan_phy); if (ops->internal_flags & NL802154_FLAG_NEED_NETDEV) { if (!dev) { if (rtnl) rtnl_unlock(); return -EINVAL; } info->user_ptr[1] = dev; } else { info->user_ptr[1] = wpan_dev; } if (dev) { if (ops->internal_flags & NL802154_FLAG_CHECK_NETDEV_UP && !netif_running(dev)) { if (rtnl) rtnl_unlock(); return -ENETDOWN; } dev_hold(dev); } info->user_ptr[0] = rdev; } return 0; } static void nl802154_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { if (info->user_ptr[1]) { if (ops->internal_flags & NL802154_FLAG_NEED_WPAN_DEV) { struct wpan_dev *wpan_dev = info->user_ptr[1]; dev_put(wpan_dev->netdev); } else { dev_put(info->user_ptr[1]); } } if (ops->internal_flags & NL802154_FLAG_NEED_RTNL) rtnl_unlock(); } static const struct genl_ops nl802154_ops[] = { { .cmd = NL802154_CMD_GET_WPAN_PHY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, .doit = nl802154_get_wpan_phy, .dumpit = nl802154_dump_wpan_phy, .done = nl802154_dump_wpan_phy_done, /* can be retrieved by unprivileged users */ .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_GET_INTERFACE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_get_interface, .dumpit = nl802154_dump_interface, /* can be retrieved by unprivileged users */ .internal_flags = NL802154_FLAG_NEED_WPAN_DEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_NEW_INTERFACE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_new_interface, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_DEL_INTERFACE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_del_interface, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_DEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_CHANNEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_channel, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_CCA_MODE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_cca_mode, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_CCA_ED_LEVEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_cca_ed_level, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_TX_POWER, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_tx_power, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_WPAN_PHY_NETNS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_wpan_phy_netns, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_WPAN_PHY | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_PAN_ID, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_pan_id, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_SHORT_ADDR, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_short_addr, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_BACKOFF_EXPONENT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_backoff_exponent, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_MAX_CSMA_BACKOFFS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_max_csma_backoffs, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_MAX_FRAME_RETRIES, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_max_frame_retries, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_LBT_MODE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_lbt_mode, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_ACKREQ_DEFAULT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_ackreq_default, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_TRIGGER_SCAN, .doit = nl802154_trigger_scan, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_CHECK_NETDEV_UP | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_ABORT_SCAN, .doit = nl802154_abort_scan, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_CHECK_NETDEV_UP | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SEND_BEACONS, .doit = nl802154_send_beacons, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_CHECK_NETDEV_UP | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_STOP_BEACONS, .doit = nl802154_stop_beacons, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_CHECK_NETDEV_UP | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_ASSOCIATE, .doit = nl802154_associate, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_CHECK_NETDEV_UP | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_DISASSOCIATE, .doit = nl802154_disassociate, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_CHECK_NETDEV_UP | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_SET_MAX_ASSOCIATIONS, .doit = nl802154_set_max_associations, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_LIST_ASSOCIATIONS, .dumpit = nl802154_list_associations, /* can be retrieved by unprivileged users */ }, #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL { .cmd = NL802154_CMD_SET_SEC_PARAMS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_set_llsec_params, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_GET_SEC_KEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, /* TODO .doit by matching key id? */ .dumpit = nl802154_dump_llsec_key, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_NEW_SEC_KEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_add_llsec_key, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_DEL_SEC_KEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_del_llsec_key, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, /* TODO unique identifier must short+pan OR extended_addr */ { .cmd = NL802154_CMD_GET_SEC_DEV, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, /* TODO .doit by matching extended_addr? */ .dumpit = nl802154_dump_llsec_dev, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_NEW_SEC_DEV, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_add_llsec_dev, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_DEL_SEC_DEV, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_del_llsec_dev, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, /* TODO remove complete devkey, put it as nested? */ { .cmd = NL802154_CMD_GET_SEC_DEVKEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, /* TODO doit by matching ??? */ .dumpit = nl802154_dump_llsec_devkey, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_NEW_SEC_DEVKEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_add_llsec_devkey, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_DEL_SEC_DEVKEY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_del_llsec_devkey, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_GET_SEC_LEVEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, /* TODO .doit by matching frame_type? */ .dumpit = nl802154_dump_llsec_seclevel, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_NEW_SEC_LEVEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl802154_add_llsec_seclevel, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, { .cmd = NL802154_CMD_DEL_SEC_LEVEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* TODO match frame_type only? */ .doit = nl802154_del_llsec_seclevel, .flags = GENL_ADMIN_PERM, .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ }; static struct genl_family nl802154_fam __ro_after_init = { .name = NL802154_GENL_NAME, /* have users key off the name instead */ .hdrsize = 0, /* no private header */ .version = 1, /* no particular meaning now */ .maxattr = NL802154_ATTR_MAX, .policy = nl802154_policy, .netnsok = true, .pre_doit = nl802154_pre_doit, .post_doit = nl802154_post_doit, .module = THIS_MODULE, .ops = nl802154_ops, .n_ops = ARRAY_SIZE(nl802154_ops), .resv_start_op = NL802154_CMD_DEL_SEC_LEVEL + 1, .mcgrps = nl802154_mcgrps, .n_mcgrps = ARRAY_SIZE(nl802154_mcgrps), }; /* initialisation/exit functions */ int __init nl802154_init(void) { return genl_register_family(&nl802154_fam); } void nl802154_exit(void) { genl_unregister_family(&nl802154_fam); } |