| 4195 5854 18 18 18 18 18 18 310 308 114 310 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Fast and scalable bitmaps. * * Copyright (C) 2016 Facebook * Copyright (C) 2013-2014 Jens Axboe */ #ifndef __LINUX_SCALE_BITMAP_H #define __LINUX_SCALE_BITMAP_H #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/cache.h> #include <linux/list.h> #include <linux/log2.h> #include <linux/minmax.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/smp.h> #include <linux/types.h> #include <linux/wait.h> struct seq_file; /** * struct sbitmap_word - Word in a &struct sbitmap. */ struct sbitmap_word { /** * @word: word holding free bits */ unsigned long word; /** * @cleared: word holding cleared bits */ unsigned long cleared ____cacheline_aligned_in_smp; /** * @swap_lock: serializes simultaneous updates of ->word and ->cleared */ raw_spinlock_t swap_lock; } ____cacheline_aligned_in_smp; /** * struct sbitmap - Scalable bitmap. * * A &struct sbitmap is spread over multiple cachelines to avoid ping-pong. This * trades off higher memory usage for better scalability. */ struct sbitmap { /** * @depth: Number of bits used in the whole bitmap. */ unsigned int depth; /** * @shift: log2(number of bits used per word) */ unsigned int shift; /** * @map_nr: Number of words (cachelines) being used for the bitmap. */ unsigned int map_nr; /** * @round_robin: Allocate bits in strict round-robin order. */ bool round_robin; /** * @map: Allocated bitmap. */ struct sbitmap_word *map; /* * @alloc_hint: Cache of last successfully allocated or freed bit. * * This is per-cpu, which allows multiple users to stick to different * cachelines until the map is exhausted. */ unsigned int __percpu *alloc_hint; }; #define SBQ_WAIT_QUEUES 8 #define SBQ_WAKE_BATCH 8 /** * struct sbq_wait_state - Wait queue in a &struct sbitmap_queue. */ struct sbq_wait_state { /** * @wait: Wait queue. */ wait_queue_head_t wait; } ____cacheline_aligned_in_smp; /** * struct sbitmap_queue - Scalable bitmap with the added ability to wait on free * bits. * * A &struct sbitmap_queue uses multiple wait queues and rolling wakeups to * avoid contention on the wait queue spinlock. This ensures that we don't hit a * scalability wall when we run out of free bits and have to start putting tasks * to sleep. */ struct sbitmap_queue { /** * @sb: Scalable bitmap. */ struct sbitmap sb; /** * @wake_batch: Number of bits which must be freed before we wake up any * waiters. */ unsigned int wake_batch; /** * @wake_index: Next wait queue in @ws to wake up. */ atomic_t wake_index; /** * @ws: Wait queues. */ struct sbq_wait_state *ws; /* * @ws_active: count of currently active ws waitqueues */ atomic_t ws_active; /** * @min_shallow_depth: The minimum shallow depth which may be passed to * sbitmap_queue_get_shallow() */ unsigned int min_shallow_depth; /** * @completion_cnt: Number of bits cleared passed to the * wakeup function. */ atomic_t completion_cnt; /** * @wakeup_cnt: Number of thread wake ups issued. */ atomic_t wakeup_cnt; }; /** * sbitmap_init_node() - Initialize a &struct sbitmap on a specific memory node. * @sb: Bitmap to initialize. * @depth: Number of bits to allocate. * @shift: Use 2^@shift bits per word in the bitmap; if a negative number if * given, a good default is chosen. * @flags: Allocation flags. * @node: Memory node to allocate on. * @round_robin: If true, be stricter about allocation order; always allocate * starting from the last allocated bit. This is less efficient * than the default behavior (false). * @alloc_hint: If true, apply percpu hint for where to start searching for * a free bit. * * Return: Zero on success or negative errno on failure. */ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, gfp_t flags, int node, bool round_robin, bool alloc_hint); /* sbitmap internal helper */ static inline unsigned int __map_depth(const struct sbitmap *sb, int index) { if (index == sb->map_nr - 1) return sb->depth - (index << sb->shift); return 1U << sb->shift; } /** * sbitmap_free() - Free memory used by a &struct sbitmap. * @sb: Bitmap to free. */ static inline void sbitmap_free(struct sbitmap *sb) { free_percpu(sb->alloc_hint); kvfree(sb->map); sb->map = NULL; } /** * sbitmap_resize() - Resize a &struct sbitmap. * @sb: Bitmap to resize. * @depth: New number of bits to resize to. * * Doesn't reallocate anything. It's up to the caller to ensure that the new * depth doesn't exceed the depth that the sb was initialized with. */ void sbitmap_resize(struct sbitmap *sb, unsigned int depth); /** * sbitmap_get() - Try to allocate a free bit from a &struct sbitmap. * @sb: Bitmap to allocate from. * * This operation provides acquire barrier semantics if it succeeds. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ int sbitmap_get(struct sbitmap *sb); /** * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap, * limiting the depth used from each word. * @sb: Bitmap to allocate from. * @shallow_depth: The maximum number of bits to allocate from a single word. * * This rather specific operation allows for having multiple users with * different allocation limits. E.g., there can be a high-priority class that * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow() * with a @shallow_depth of (1 << (@sb->shift - 1)). Then, the low-priority * class can only allocate half of the total bits in the bitmap, preventing it * from starving out the high-priority class. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth); /** * sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap. * @sb: Bitmap to check. * * Return: true if any bit in the bitmap is set, false otherwise. */ bool sbitmap_any_bit_set(const struct sbitmap *sb); #define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift) #define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U)) typedef bool (*sb_for_each_fn)(struct sbitmap *, unsigned int, void *); /** * __sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap. * @start: Where to start the iteration. * @sb: Bitmap to iterate over. * @fn: Callback. Should return true to continue or false to break early. * @data: Pointer to pass to callback. * * This is inline even though it's non-trivial so that the function calls to the * callback will hopefully get optimized away. */ static inline void __sbitmap_for_each_set(struct sbitmap *sb, unsigned int start, sb_for_each_fn fn, void *data) { unsigned int index; unsigned int nr; unsigned int scanned = 0; if (start >= sb->depth) start = 0; index = SB_NR_TO_INDEX(sb, start); nr = SB_NR_TO_BIT(sb, start); while (scanned < sb->depth) { unsigned long word; unsigned int depth = min_t(unsigned int, __map_depth(sb, index) - nr, sb->depth - scanned); scanned += depth; word = sb->map[index].word & ~sb->map[index].cleared; if (!word) goto next; /* * On the first iteration of the outer loop, we need to add the * bit offset back to the size of the word for find_next_bit(). * On all other iterations, nr is zero, so this is a noop. */ depth += nr; while (1) { nr = find_next_bit(&word, depth, nr); if (nr >= depth) break; if (!fn(sb, (index << sb->shift) + nr, data)) return; nr++; } next: nr = 0; if (++index >= sb->map_nr) index = 0; } } /** * sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap. * @sb: Bitmap to iterate over. * @fn: Callback. Should return true to continue or false to break early. * @data: Pointer to pass to callback. */ static inline void sbitmap_for_each_set(struct sbitmap *sb, sb_for_each_fn fn, void *data) { __sbitmap_for_each_set(sb, 0, fn, data); } static inline unsigned long *__sbitmap_word(struct sbitmap *sb, unsigned int bitnr) { return &sb->map[SB_NR_TO_INDEX(sb, bitnr)].word; } /* Helpers equivalent to the operations in asm/bitops.h and linux/bitmap.h */ static inline void sbitmap_set_bit(struct sbitmap *sb, unsigned int bitnr) { set_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); } static inline void sbitmap_clear_bit(struct sbitmap *sb, unsigned int bitnr) { clear_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); } /* * This one is special, since it doesn't actually clear the bit, rather it * sets the corresponding bit in the ->cleared mask instead. Paired with * the caller doing sbitmap_deferred_clear() if a given index is full, which * will clear the previously freed entries in the corresponding ->word. */ static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int bitnr) { unsigned long *addr = &sb->map[SB_NR_TO_INDEX(sb, bitnr)].cleared; set_bit(SB_NR_TO_BIT(sb, bitnr), addr); } /* * Pair of sbitmap_get, and this one applies both cleared bit and * allocation hint. */ static inline void sbitmap_put(struct sbitmap *sb, unsigned int bitnr) { sbitmap_deferred_clear_bit(sb, bitnr); if (likely(sb->alloc_hint && !sb->round_robin && bitnr < sb->depth)) *raw_cpu_ptr(sb->alloc_hint) = bitnr; } static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr) { return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); } static inline int sbitmap_calculate_shift(unsigned int depth) { int shift = ilog2(BITS_PER_LONG); /* * If the bitmap is small, shrink the number of bits per word so * we spread over a few cachelines, at least. If less than 4 * bits, just forget about it, it's not going to work optimally * anyway. */ if (depth >= 4) { while ((4U << shift) > depth) shift--; } return shift; } /** * sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file. * @sb: Bitmap to show. * @m: struct seq_file to write to. * * This is intended for debugging. The format may change at any time. */ void sbitmap_show(struct sbitmap *sb, struct seq_file *m); /** * sbitmap_weight() - Return how many set and not cleared bits in a &struct * sbitmap. * @sb: Bitmap to check. * * Return: How many set and not cleared bits set */ unsigned int sbitmap_weight(const struct sbitmap *sb); /** * sbitmap_bitmap_show() - Write a hex dump of a &struct sbitmap to a &struct * seq_file. * @sb: Bitmap to show. * @m: struct seq_file to write to. * * This is intended for debugging. The output isn't guaranteed to be internally * consistent. */ void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m); /** * sbitmap_queue_init_node() - Initialize a &struct sbitmap_queue on a specific * memory node. * @sbq: Bitmap queue to initialize. * @depth: See sbitmap_init_node(). * @shift: See sbitmap_init_node(). * @round_robin: See sbitmap_get(). * @flags: Allocation flags. * @node: Memory node to allocate on. * * Return: Zero on success or negative errno on failure. */ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, int shift, bool round_robin, gfp_t flags, int node); /** * sbitmap_queue_free() - Free memory used by a &struct sbitmap_queue. * * @sbq: Bitmap queue to free. */ static inline void sbitmap_queue_free(struct sbitmap_queue *sbq) { kfree(sbq->ws); sbitmap_free(&sbq->sb); } /** * sbitmap_queue_recalculate_wake_batch() - Recalculate wake batch * @sbq: Bitmap queue to recalculate wake batch. * @users: Number of shares. * * Like sbitmap_queue_update_wake_batch(), this will calculate wake batch * by depth. This interface is for HCTX shared tags or queue shared tags. */ void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq, unsigned int users); /** * sbitmap_queue_resize() - Resize a &struct sbitmap_queue. * @sbq: Bitmap queue to resize. * @depth: New number of bits to resize to. * * Like sbitmap_resize(), this doesn't reallocate anything. It has to do * some extra work on the &struct sbitmap_queue, so it's not safe to just * resize the underlying &struct sbitmap. */ void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth); /** * __sbitmap_queue_get() - Try to allocate a free bit from a &struct * sbitmap_queue with preemption already disabled. * @sbq: Bitmap queue to allocate from. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ int __sbitmap_queue_get(struct sbitmap_queue *sbq); /** * __sbitmap_queue_get_batch() - Try to allocate a batch of free bits * @sbq: Bitmap queue to allocate from. * @nr_tags: number of tags requested * @offset: offset to add to returned bits * * Return: Mask of allocated tags, 0 if none are found. Each tag allocated is * a bit in the mask returned, and the caller must add @offset to the value to * get the absolute tag value. */ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, unsigned int *offset); /** * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct * sbitmap_queue, limiting the depth used from each word, with preemption * already disabled. * @sbq: Bitmap queue to allocate from. * @shallow_depth: The maximum number of bits to allocate from a single word. * See sbitmap_get_shallow(). * * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after * initializing @sbq. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, unsigned int shallow_depth); /** * sbitmap_queue_get() - Try to allocate a free bit from a &struct * sbitmap_queue. * @sbq: Bitmap queue to allocate from. * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to * sbitmap_queue_clear()). * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq, unsigned int *cpu) { int nr; *cpu = get_cpu(); nr = __sbitmap_queue_get(sbq); put_cpu(); return nr; } /** * sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the * minimum shallow depth that will be used. * @sbq: Bitmap queue in question. * @min_shallow_depth: The minimum shallow depth that will be passed to * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow(). * * sbitmap_queue_clear() batches wakeups as an optimization. The batch size * depends on the depth of the bitmap. Since the shallow allocation functions * effectively operate with a different depth, the shallow depth must be taken * into account when calculating the batch size. This function must be called * with the minimum shallow depth that will be used. Failure to do so can result * in missed wakeups. */ void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq, unsigned int min_shallow_depth); /** * sbitmap_queue_clear() - Free an allocated bit and wake up waiters on a * &struct sbitmap_queue. * @sbq: Bitmap to free from. * @nr: Bit number to free. * @cpu: CPU the bit was allocated on. */ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, unsigned int cpu); /** * sbitmap_queue_clear_batch() - Free a batch of allocated bits * &struct sbitmap_queue. * @sbq: Bitmap to free from. * @offset: offset for each tag in array * @tags: array of tags * @nr_tags: number of tags in array */ void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset, int *tags, int nr_tags); static inline int sbq_index_inc(int index) { return (index + 1) & (SBQ_WAIT_QUEUES - 1); } static inline void sbq_index_atomic_inc(atomic_t *index) { int old = atomic_read(index); int new = sbq_index_inc(old); atomic_cmpxchg(index, old, new); } /** * sbq_wait_ptr() - Get the next wait queue to use for a &struct * sbitmap_queue. * @sbq: Bitmap queue to wait on. * @wait_index: A counter per "user" of @sbq. */ static inline struct sbq_wait_state *sbq_wait_ptr(struct sbitmap_queue *sbq, atomic_t *wait_index) { struct sbq_wait_state *ws; ws = &sbq->ws[atomic_read(wait_index)]; sbq_index_atomic_inc(wait_index); return ws; } /** * sbitmap_queue_wake_all() - Wake up everything waiting on a &struct * sbitmap_queue. * @sbq: Bitmap queue to wake up. */ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq); /** * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue * on a &struct sbitmap_queue. * @sbq: Bitmap queue to wake up. * @nr: Number of bits cleared. */ void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr); /** * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct * seq_file. * @sbq: Bitmap queue to show. * @m: struct seq_file to write to. * * This is intended for debugging. The format may change at any time. */ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m); struct sbq_wait { struct sbitmap_queue *sbq; /* if set, sbq_wait is accounted */ struct wait_queue_entry wait; }; #define DEFINE_SBQ_WAIT(name) \ struct sbq_wait name = { \ .sbq = NULL, \ .wait = { \ .private = current, \ .func = autoremove_wake_function, \ .entry = LIST_HEAD_INIT((name).wait.entry), \ } \ } /* * Wrapper around prepare_to_wait_exclusive(), which maintains some extra * internal state. */ void sbitmap_prepare_to_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, struct sbq_wait *sbq_wait, int state); /* * Must be paired with sbitmap_prepare_to_wait(). */ void sbitmap_finish_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, struct sbq_wait *sbq_wait); /* * Wrapper around add_wait_queue(), which maintains some extra internal state */ void sbitmap_add_wait_queue(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, struct sbq_wait *sbq_wait); /* * Must be paired with sbitmap_add_wait_queue() */ void sbitmap_del_wait_queue(struct sbq_wait *sbq_wait); #endif /* __LINUX_SCALE_BITMAP_H */ |
| 272 245 244 245 4 241 245 1 2 165 171 171 171 170 73 73 73 73 151 151 151 138 27 1 151 151 1 151 1 78 78 77 5 78 78 15 70 27 3 2 2 2 2 376 375 376 376 30 30 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/list_bl.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/mbcache.h> /* * Mbcache is a simple key-value store. Keys need not be unique, however * key-value pairs are expected to be unique (we use this fact in * mb_cache_entry_delete_or_get()). * * Ext2 and ext4 use this cache for deduplication of extended attribute blocks. * Ext4 also uses it for deduplication of xattr values stored in inodes. * They use hash of data as a key and provide a value that may represent a * block or inode number. That's why keys need not be unique (hash of different * data may be the same). However user provided value always uniquely * identifies a cache entry. * * We provide functions for creation and removal of entries, search by key, * and a special "delete entry with given key-value pair" operation. Fixed * size hash table is used for fast key lookups. */ struct mb_cache { /* Hash table of entries */ struct hlist_bl_head *c_hash; /* log2 of hash table size */ int c_bucket_bits; /* Maximum entries in cache to avoid degrading hash too much */ unsigned long c_max_entries; /* Protects c_list, c_entry_count */ spinlock_t c_list_lock; struct list_head c_list; /* Number of entries in cache */ unsigned long c_entry_count; struct shrinker *c_shrink; /* Work for shrinking when the cache has too many entries */ struct work_struct c_shrink_work; }; static struct kmem_cache *mb_entry_cache; static unsigned long mb_cache_shrink(struct mb_cache *cache, unsigned long nr_to_scan); static inline struct hlist_bl_head *mb_cache_entry_head(struct mb_cache *cache, u32 key) { return &cache->c_hash[hash_32(key, cache->c_bucket_bits)]; } /* * Number of entries to reclaim synchronously when there are too many entries * in cache */ #define SYNC_SHRINK_BATCH 64 /* * mb_cache_entry_create - create entry in cache * @cache - cache where the entry should be created * @mask - gfp mask with which the entry should be allocated * @key - key of the entry * @value - value of the entry * @reusable - is the entry reusable by others? * * Creates entry in @cache with key @key and value @value. The function returns * -EBUSY if entry with the same key and value already exists in cache. * Otherwise 0 is returned. */ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, u64 value, bool reusable) { struct mb_cache_entry *entry, *dup; struct hlist_bl_node *dup_node; struct hlist_bl_head *head; /* Schedule background reclaim if there are too many entries */ if (cache->c_entry_count >= cache->c_max_entries) schedule_work(&cache->c_shrink_work); /* Do some sync reclaim if background reclaim cannot keep up */ if (cache->c_entry_count >= 2*cache->c_max_entries) mb_cache_shrink(cache, SYNC_SHRINK_BATCH); entry = kmem_cache_alloc(mb_entry_cache, mask); if (!entry) return -ENOMEM; INIT_LIST_HEAD(&entry->e_list); /* * We create entry with two references. One reference is kept by the * hash table, the other reference is used to protect us from * mb_cache_entry_delete_or_get() until the entry is fully setup. This * avoids nesting of cache->c_list_lock into hash table bit locks which * is problematic for RT. */ atomic_set(&entry->e_refcnt, 2); entry->e_key = key; entry->e_value = value; entry->e_flags = 0; if (reusable) set_bit(MBE_REUSABLE_B, &entry->e_flags); head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) { if (dup->e_key == key && dup->e_value == value) { hlist_bl_unlock(head); kmem_cache_free(mb_entry_cache, entry); return -EBUSY; } } hlist_bl_add_head(&entry->e_hash_list, head); hlist_bl_unlock(head); spin_lock(&cache->c_list_lock); list_add_tail(&entry->e_list, &cache->c_list); cache->c_entry_count++; spin_unlock(&cache->c_list_lock); mb_cache_entry_put(cache, entry); return 0; } EXPORT_SYMBOL(mb_cache_entry_create); void __mb_cache_entry_free(struct mb_cache *cache, struct mb_cache_entry *entry) { struct hlist_bl_head *head; head = mb_cache_entry_head(cache, entry->e_key); hlist_bl_lock(head); hlist_bl_del(&entry->e_hash_list); hlist_bl_unlock(head); kmem_cache_free(mb_entry_cache, entry); } EXPORT_SYMBOL(__mb_cache_entry_free); /* * mb_cache_entry_wait_unused - wait to be the last user of the entry * * @entry - entry to work on * * Wait to be the last user of the entry. */ void mb_cache_entry_wait_unused(struct mb_cache_entry *entry) { wait_var_event(&entry->e_refcnt, atomic_read(&entry->e_refcnt) <= 2); } EXPORT_SYMBOL(mb_cache_entry_wait_unused); static struct mb_cache_entry *__entry_find(struct mb_cache *cache, struct mb_cache_entry *entry, u32 key) { struct mb_cache_entry *old_entry = entry; struct hlist_bl_node *node; struct hlist_bl_head *head; head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); if (entry && !hlist_bl_unhashed(&entry->e_hash_list)) node = entry->e_hash_list.next; else node = hlist_bl_first(head); while (node) { entry = hlist_bl_entry(node, struct mb_cache_entry, e_hash_list); if (entry->e_key == key && test_bit(MBE_REUSABLE_B, &entry->e_flags) && atomic_inc_not_zero(&entry->e_refcnt)) goto out; node = node->next; } entry = NULL; out: hlist_bl_unlock(head); if (old_entry) mb_cache_entry_put(cache, old_entry); return entry; } /* * mb_cache_entry_find_first - find the first reusable entry with the given key * @cache: cache where we should search * @key: key to look for * * Search in @cache for a reusable entry with key @key. Grabs reference to the * first reusable entry found and returns the entry. */ struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, u32 key) { return __entry_find(cache, NULL, key); } EXPORT_SYMBOL(mb_cache_entry_find_first); /* * mb_cache_entry_find_next - find next reusable entry with the same key * @cache: cache where we should search * @entry: entry to start search from * * Finds next reusable entry in the hash chain which has the same key as @entry. * If @entry is unhashed (which can happen when deletion of entry races with the * search), finds the first reusable entry in the hash chain. The function drops * reference to @entry and returns with a reference to the found entry. */ struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache, struct mb_cache_entry *entry) { return __entry_find(cache, entry, entry->e_key); } EXPORT_SYMBOL(mb_cache_entry_find_next); /* * mb_cache_entry_get - get a cache entry by value (and key) * @cache - cache we work with * @key - key * @value - value */ struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, u64 value) { struct hlist_bl_node *node; struct hlist_bl_head *head; struct mb_cache_entry *entry; head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(entry, node, head, e_hash_list) { if (entry->e_key == key && entry->e_value == value && atomic_inc_not_zero(&entry->e_refcnt)) goto out; } entry = NULL; out: hlist_bl_unlock(head); return entry; } EXPORT_SYMBOL(mb_cache_entry_get); /* mb_cache_entry_delete_or_get - remove a cache entry if it has no users * @cache - cache we work with * @key - key * @value - value * * Remove entry from cache @cache with key @key and value @value. The removal * happens only if the entry is unused. The function returns NULL in case the * entry was successfully removed or there's no entry in cache. Otherwise the * function grabs reference of the entry that we failed to delete because it * still has users and return it. */ struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache, u32 key, u64 value) { struct mb_cache_entry *entry; entry = mb_cache_entry_get(cache, key, value); if (!entry) return NULL; /* * Drop the ref we got from mb_cache_entry_get() and the initial hash * ref if we are the last user */ if (atomic_cmpxchg(&entry->e_refcnt, 2, 0) != 2) return entry; spin_lock(&cache->c_list_lock); if (!list_empty(&entry->e_list)) list_del_init(&entry->e_list); cache->c_entry_count--; spin_unlock(&cache->c_list_lock); __mb_cache_entry_free(cache, entry); return NULL; } EXPORT_SYMBOL(mb_cache_entry_delete_or_get); /* mb_cache_entry_touch - cache entry got used * @cache - cache the entry belongs to * @entry - entry that got used * * Marks entry as used to give hit higher chances of surviving in cache. */ void mb_cache_entry_touch(struct mb_cache *cache, struct mb_cache_entry *entry) { set_bit(MBE_REFERENCED_B, &entry->e_flags); } EXPORT_SYMBOL(mb_cache_entry_touch); static unsigned long mb_cache_count(struct shrinker *shrink, struct shrink_control *sc) { struct mb_cache *cache = shrink->private_data; return cache->c_entry_count; } /* Shrink number of entries in cache */ static unsigned long mb_cache_shrink(struct mb_cache *cache, unsigned long nr_to_scan) { struct mb_cache_entry *entry; unsigned long shrunk = 0; spin_lock(&cache->c_list_lock); while (nr_to_scan-- && !list_empty(&cache->c_list)) { entry = list_first_entry(&cache->c_list, struct mb_cache_entry, e_list); /* Drop initial hash reference if there is no user */ if (test_bit(MBE_REFERENCED_B, &entry->e_flags) || atomic_cmpxchg(&entry->e_refcnt, 1, 0) != 1) { clear_bit(MBE_REFERENCED_B, &entry->e_flags); list_move_tail(&entry->e_list, &cache->c_list); continue; } list_del_init(&entry->e_list); cache->c_entry_count--; spin_unlock(&cache->c_list_lock); __mb_cache_entry_free(cache, entry); shrunk++; cond_resched(); spin_lock(&cache->c_list_lock); } spin_unlock(&cache->c_list_lock); return shrunk; } static unsigned long mb_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { struct mb_cache *cache = shrink->private_data; return mb_cache_shrink(cache, sc->nr_to_scan); } /* We shrink 1/X of the cache when we have too many entries in it */ #define SHRINK_DIVISOR 16 static void mb_cache_shrink_worker(struct work_struct *work) { struct mb_cache *cache = container_of(work, struct mb_cache, c_shrink_work); mb_cache_shrink(cache, cache->c_max_entries / SHRINK_DIVISOR); } /* * mb_cache_create - create cache * @bucket_bits: log2 of the hash table size * * Create cache for keys with 2^bucket_bits hash entries. */ struct mb_cache *mb_cache_create(int bucket_bits) { struct mb_cache *cache; unsigned long bucket_count = 1UL << bucket_bits; unsigned long i; cache = kzalloc(sizeof(struct mb_cache), GFP_KERNEL); if (!cache) goto err_out; cache->c_bucket_bits = bucket_bits; cache->c_max_entries = bucket_count << 4; INIT_LIST_HEAD(&cache->c_list); spin_lock_init(&cache->c_list_lock); cache->c_hash = kmalloc_array(bucket_count, sizeof(struct hlist_bl_head), GFP_KERNEL); if (!cache->c_hash) { kfree(cache); goto err_out; } for (i = 0; i < bucket_count; i++) INIT_HLIST_BL_HEAD(&cache->c_hash[i]); cache->c_shrink = shrinker_alloc(0, "mbcache-shrinker"); if (!cache->c_shrink) { kfree(cache->c_hash); kfree(cache); goto err_out; } cache->c_shrink->count_objects = mb_cache_count; cache->c_shrink->scan_objects = mb_cache_scan; cache->c_shrink->private_data = cache; shrinker_register(cache->c_shrink); INIT_WORK(&cache->c_shrink_work, mb_cache_shrink_worker); return cache; err_out: return NULL; } EXPORT_SYMBOL(mb_cache_create); /* * mb_cache_destroy - destroy cache * @cache: the cache to destroy * * Free all entries in cache and cache itself. Caller must make sure nobody * (except shrinker) can reach @cache when calling this. */ void mb_cache_destroy(struct mb_cache *cache) { struct mb_cache_entry *entry, *next; shrinker_free(cache->c_shrink); /* * We don't bother with any locking. Cache must not be used at this * point. */ list_for_each_entry_safe(entry, next, &cache->c_list, e_list) { list_del(&entry->e_list); WARN_ON(atomic_read(&entry->e_refcnt) != 1); mb_cache_entry_put(cache, entry); } kfree(cache->c_hash); kfree(cache); } EXPORT_SYMBOL(mb_cache_destroy); static int __init mbcache_init(void) { mb_entry_cache = KMEM_CACHE(mb_cache_entry, SLAB_RECLAIM_ACCOUNT); if (!mb_entry_cache) return -ENOMEM; return 0; } static void __exit mbcache_exit(void) { kmem_cache_destroy(mb_entry_cache); } module_init(mbcache_init) module_exit(mbcache_exit) MODULE_AUTHOR("Jan Kara <jack@suse.cz>"); MODULE_DESCRIPTION("Meta block cache (for extended attributes)"); MODULE_LICENSE("GPL"); |
| 165 165 165 39 5 44 44 159 159 159 142 3 14 114 102 12 133 19 118 133 127 5 122 1 1 1 1 118 4 127 123 4 10 1 9 9 9 116 95 64 11 50 1 114 114 1 53 53 53 53 203 203 40 50 1 3 3 3 3 40 21 53 72 72 71 64 64 64 11 64 64 63 50 2 1 50 51 50 10 64 64 63 51 60 61 1 61 62 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 | // SPDX-License-Identifier: GPL-2.0-or-later /* * localalloc.c * * Node local data allocation * * Copyright (C) 2002, 2004 Oracle. All rights reserved. */ #include <linux/fs.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/bitops.h> #include <cluster/masklog.h> #include "ocfs2.h" #include "alloc.h" #include "blockcheck.h" #include "dlmglue.h" #include "inode.h" #include "journal.h" #include "localalloc.h" #include "suballoc.h" #include "super.h" #include "sysfile.h" #include "ocfs2_trace.h" #include "buffer_head_io.h" #define OCFS2_LOCAL_ALLOC(dinode) (&((dinode)->id2.i_lab)) static u32 ocfs2_local_alloc_count_bits(struct ocfs2_dinode *alloc); static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb, struct ocfs2_dinode *alloc, u32 *numbits, struct ocfs2_alloc_reservation *resv); static void ocfs2_clear_local_alloc(struct ocfs2_dinode *alloc); static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_dinode *alloc, struct inode *main_bm_inode, struct buffer_head *main_bm_bh); static int ocfs2_local_alloc_reserve_for_window(struct ocfs2_super *osb, struct ocfs2_alloc_context **ac, struct inode **bitmap_inode, struct buffer_head **bitmap_bh); static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_alloc_context *ac); static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb, struct inode *local_alloc_inode); /* * ocfs2_la_default_mb() - determine a default size, in megabytes of * the local alloc. * * Generally, we'd like to pick as large a local alloc as * possible. Performance on large workloads tends to scale * proportionally to la size. In addition to that, the reservations * code functions more efficiently as it can reserve more windows for * write. * * Some things work against us when trying to choose a large local alloc: * * - We need to ensure our sizing is picked to leave enough space in * group descriptors for other allocations (such as block groups, * etc). Picking default sizes which are a multiple of 4 could help * - block groups are allocated in 2mb and 4mb chunks. * * - Likewise, we don't want to starve other nodes of bits on small * file systems. This can easily be taken care of by limiting our * default to a reasonable size (256M) on larger cluster sizes. * * - Some file systems can't support very large sizes - 4k and 8k in * particular are limited to less than 128 and 256 megabytes respectively. * * The following reference table shows group descriptor and local * alloc maximums at various cluster sizes (4k blocksize) * * csize: 4K group: 126M la: 121M * csize: 8K group: 252M la: 243M * csize: 16K group: 504M la: 486M * csize: 32K group: 1008M la: 972M * csize: 64K group: 2016M la: 1944M * csize: 128K group: 4032M la: 3888M * csize: 256K group: 8064M la: 7776M * csize: 512K group: 16128M la: 15552M * csize: 1024K group: 32256M la: 31104M */ #define OCFS2_LA_MAX_DEFAULT_MB 256 #define OCFS2_LA_OLD_DEFAULT 8 unsigned int ocfs2_la_default_mb(struct ocfs2_super *osb) { unsigned int la_mb; unsigned int gd_mb; unsigned int la_max_mb; unsigned int megs_per_slot; struct super_block *sb = osb->sb; gd_mb = ocfs2_clusters_to_megabytes(osb->sb, 8 * ocfs2_group_bitmap_size(sb, 0, osb->s_feature_incompat)); /* * This takes care of files systems with very small group * descriptors - 512 byte blocksize at cluster sizes lower * than 16K and also 1k blocksize with 4k cluster size. */ if ((sb->s_blocksize == 512 && osb->s_clustersize <= 8192) || (sb->s_blocksize == 1024 && osb->s_clustersize == 4096)) return OCFS2_LA_OLD_DEFAULT; /* * Leave enough room for some block groups and make the final * value we work from a multiple of 4. */ gd_mb -= 16; gd_mb &= 0xFFFFFFFB; la_mb = gd_mb; /* * Keep window sizes down to a reasonable default */ if (la_mb > OCFS2_LA_MAX_DEFAULT_MB) { /* * Some clustersize / blocksize combinations will have * given us a larger than OCFS2_LA_MAX_DEFAULT_MB * default size, but get poor distribution when * limited to exactly 256 megabytes. * * As an example, 16K clustersize at 4K blocksize * gives us a cluster group size of 504M. Paring the * local alloc size down to 256 however, would give us * only one window and around 200MB left in the * cluster group. Instead, find the first size below * 256 which would give us an even distribution. * * Larger cluster group sizes actually work out pretty * well when pared to 256, so we don't have to do this * for any group that fits more than two * OCFS2_LA_MAX_DEFAULT_MB windows. */ if (gd_mb > (2 * OCFS2_LA_MAX_DEFAULT_MB)) la_mb = 256; else { unsigned int gd_mult = gd_mb; while (gd_mult > 256) gd_mult = gd_mult >> 1; la_mb = gd_mult; } } megs_per_slot = osb->osb_clusters_at_boot / osb->max_slots; megs_per_slot = ocfs2_clusters_to_megabytes(osb->sb, megs_per_slot); /* Too many nodes, too few disk clusters. */ if (megs_per_slot < la_mb) la_mb = megs_per_slot; /* We can't store more bits than we can in a block. */ la_max_mb = ocfs2_clusters_to_megabytes(osb->sb, ocfs2_local_alloc_size(sb) * 8); if (la_mb > la_max_mb) la_mb = la_max_mb; return la_mb; } void ocfs2_la_set_sizes(struct ocfs2_super *osb, int requested_mb) { struct super_block *sb = osb->sb; unsigned int la_default_mb = ocfs2_la_default_mb(osb); unsigned int la_max_mb; la_max_mb = ocfs2_clusters_to_megabytes(sb, ocfs2_local_alloc_size(sb) * 8); trace_ocfs2_la_set_sizes(requested_mb, la_max_mb, la_default_mb); if (requested_mb == -1) { /* No user request - use defaults */ osb->local_alloc_default_bits = ocfs2_megabytes_to_clusters(sb, la_default_mb); } else if (requested_mb > la_max_mb) { /* Request is too big, we give the maximum available */ osb->local_alloc_default_bits = ocfs2_megabytes_to_clusters(sb, la_max_mb); } else { osb->local_alloc_default_bits = ocfs2_megabytes_to_clusters(sb, requested_mb); } osb->local_alloc_bits = osb->local_alloc_default_bits; } static inline int ocfs2_la_state_enabled(struct ocfs2_super *osb) { return (osb->local_alloc_state == OCFS2_LA_THROTTLED || osb->local_alloc_state == OCFS2_LA_ENABLED); } void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb, unsigned int num_clusters) { if (num_clusters >= osb->local_alloc_default_bits) { spin_lock(&osb->osb_lock); if (osb->local_alloc_state == OCFS2_LA_DISABLED || osb->local_alloc_state == OCFS2_LA_THROTTLED) { cancel_delayed_work(&osb->la_enable_wq); osb->local_alloc_state = OCFS2_LA_ENABLED; } spin_unlock(&osb->osb_lock); } } void ocfs2_la_enable_worker(struct work_struct *work) { struct ocfs2_super *osb = container_of(work, struct ocfs2_super, la_enable_wq.work); spin_lock(&osb->osb_lock); osb->local_alloc_state = OCFS2_LA_ENABLED; spin_unlock(&osb->osb_lock); } /* * Tell us whether a given allocation should use the local alloc * file. Otherwise, it has to go to the main bitmap. * * This function does semi-dirty reads of local alloc size and state! * This is ok however, as the values are re-checked once under mutex. */ int ocfs2_alloc_should_use_local(struct ocfs2_super *osb, u64 bits) { int ret = 0; int la_bits; spin_lock(&osb->osb_lock); la_bits = osb->local_alloc_bits; if (!ocfs2_la_state_enabled(osb)) goto bail; /* la_bits should be at least twice the size (in clusters) of * a new block group. We want to be sure block group * allocations go through the local alloc, so allow an * allocation to take up to half the bitmap. */ if (bits > (la_bits / 2)) goto bail; ret = 1; bail: trace_ocfs2_alloc_should_use_local( (unsigned long long)bits, osb->local_alloc_state, la_bits, ret); spin_unlock(&osb->osb_lock); return ret; } int ocfs2_load_local_alloc(struct ocfs2_super *osb) { int status = 0; struct ocfs2_dinode *alloc = NULL; struct buffer_head *alloc_bh = NULL; u32 num_used; struct inode *inode = NULL; struct ocfs2_local_alloc *la; if (osb->local_alloc_bits == 0) goto bail; if (osb->local_alloc_bits >= osb->bitmap_cpg) { mlog(ML_NOTICE, "Requested local alloc window %d is larger " "than max possible %u. Using defaults.\n", osb->local_alloc_bits, (osb->bitmap_cpg - 1)); osb->local_alloc_bits = ocfs2_megabytes_to_clusters(osb->sb, ocfs2_la_default_mb(osb)); } /* read the alloc off disk */ inode = ocfs2_get_system_file_inode(osb, LOCAL_ALLOC_SYSTEM_INODE, osb->slot_num); if (!inode) { status = -EINVAL; mlog_errno(status); goto bail; } status = ocfs2_read_inode_block_full(inode, &alloc_bh, OCFS2_BH_IGNORE_CACHE); if (status < 0) { mlog_errno(status); goto bail; } alloc = (struct ocfs2_dinode *) alloc_bh->b_data; la = OCFS2_LOCAL_ALLOC(alloc); if (!(le32_to_cpu(alloc->i_flags) & (OCFS2_LOCAL_ALLOC_FL|OCFS2_BITMAP_FL))) { mlog(ML_ERROR, "Invalid local alloc inode, %llu\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); status = -EINVAL; goto bail; } if ((la->la_size == 0) || (le16_to_cpu(la->la_size) > ocfs2_local_alloc_size(inode->i_sb))) { mlog(ML_ERROR, "Local alloc size is invalid (la_size = %u)\n", le16_to_cpu(la->la_size)); status = -EINVAL; goto bail; } /* do a little verification. */ num_used = ocfs2_local_alloc_count_bits(alloc); /* hopefully the local alloc has always been recovered before * we load it. */ if (num_used || alloc->id1.bitmap1.i_used || alloc->id1.bitmap1.i_total || la->la_bm_off) { mlog(ML_ERROR, "inconsistent detected, clean journal with" " unrecovered local alloc, please run fsck.ocfs2!\n" "found = %u, set = %u, taken = %u, off = %u\n", num_used, le32_to_cpu(alloc->id1.bitmap1.i_used), le32_to_cpu(alloc->id1.bitmap1.i_total), le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off)); status = -EINVAL; goto bail; } osb->local_alloc_bh = alloc_bh; osb->local_alloc_state = OCFS2_LA_ENABLED; bail: if (status < 0) brelse(alloc_bh); iput(inode); trace_ocfs2_load_local_alloc(osb->local_alloc_bits); if (status) mlog_errno(status); return status; } /* * return any unused bits to the bitmap and write out a clean * local_alloc. * * local_alloc_bh is optional. If not passed, we will simply use the * one off osb. If you do pass it however, be warned that it *will* be * returned brelse'd and NULL'd out.*/ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb) { int status; handle_t *handle; struct inode *local_alloc_inode = NULL; struct buffer_head *bh = NULL; struct buffer_head *main_bm_bh = NULL; struct inode *main_bm_inode = NULL; struct ocfs2_dinode *alloc_copy = NULL; struct ocfs2_dinode *alloc = NULL; cancel_delayed_work(&osb->la_enable_wq); if (osb->ocfs2_wq) flush_workqueue(osb->ocfs2_wq); if (osb->local_alloc_state == OCFS2_LA_UNUSED) goto out; local_alloc_inode = ocfs2_get_system_file_inode(osb, LOCAL_ALLOC_SYSTEM_INODE, osb->slot_num); if (!local_alloc_inode) { status = -ENOENT; mlog_errno(status); goto out; } osb->local_alloc_state = OCFS2_LA_DISABLED; ocfs2_resmap_uninit(&osb->osb_la_resmap); main_bm_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE, OCFS2_INVALID_SLOT); if (!main_bm_inode) { status = -EINVAL; mlog_errno(status); goto out; } inode_lock(main_bm_inode); status = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 1); if (status < 0) { mlog_errno(status); goto out_mutex; } /* WINDOW_MOVE_CREDITS is a bit heavy... */ handle = ocfs2_start_trans(osb, OCFS2_WINDOW_MOVE_CREDITS); if (IS_ERR(handle)) { mlog_errno(PTR_ERR(handle)); handle = NULL; goto out_unlock; } bh = osb->local_alloc_bh; alloc = (struct ocfs2_dinode *) bh->b_data; alloc_copy = kmemdup(alloc, bh->b_size, GFP_NOFS); if (!alloc_copy) { status = -ENOMEM; goto out_commit; } status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto out_commit; } ocfs2_clear_local_alloc(alloc); ocfs2_journal_dirty(handle, bh); brelse(bh); osb->local_alloc_bh = NULL; osb->local_alloc_state = OCFS2_LA_UNUSED; status = ocfs2_sync_local_to_main(osb, handle, alloc_copy, main_bm_inode, main_bm_bh); if (status < 0) mlog_errno(status); out_commit: ocfs2_commit_trans(osb, handle); out_unlock: brelse(main_bm_bh); ocfs2_inode_unlock(main_bm_inode, 1); out_mutex: inode_unlock(main_bm_inode); iput(main_bm_inode); out: iput(local_alloc_inode); kfree(alloc_copy); } /* * We want to free the bitmap bits outside of any recovery context as * we'll need a cluster lock to do so, but we must clear the local * alloc before giving up the recovered nodes journal. To solve this, * we kmalloc a copy of the local alloc before it's change for the * caller to process with ocfs2_complete_local_alloc_recovery */ int ocfs2_begin_local_alloc_recovery(struct ocfs2_super *osb, int slot_num, struct ocfs2_dinode **alloc_copy) { int status = 0; struct buffer_head *alloc_bh = NULL; struct inode *inode = NULL; struct ocfs2_dinode *alloc; trace_ocfs2_begin_local_alloc_recovery(slot_num); *alloc_copy = NULL; inode = ocfs2_get_system_file_inode(osb, LOCAL_ALLOC_SYSTEM_INODE, slot_num); if (!inode) { status = -EINVAL; mlog_errno(status); goto bail; } inode_lock(inode); status = ocfs2_read_inode_block_full(inode, &alloc_bh, OCFS2_BH_IGNORE_CACHE); if (status < 0) { mlog_errno(status); goto bail; } *alloc_copy = kmalloc(alloc_bh->b_size, GFP_KERNEL); if (!(*alloc_copy)) { status = -ENOMEM; goto bail; } memcpy((*alloc_copy), alloc_bh->b_data, alloc_bh->b_size); alloc = (struct ocfs2_dinode *) alloc_bh->b_data; ocfs2_clear_local_alloc(alloc); ocfs2_compute_meta_ecc(osb->sb, alloc_bh->b_data, &alloc->i_check); status = ocfs2_write_block(osb, alloc_bh, INODE_CACHE(inode)); if (status < 0) mlog_errno(status); bail: if (status < 0) { kfree(*alloc_copy); *alloc_copy = NULL; } brelse(alloc_bh); if (inode) { inode_unlock(inode); iput(inode); } if (status) mlog_errno(status); return status; } /* * Step 2: By now, we've completed the journal recovery, we've stamped * a clean local alloc on disk and dropped the node out of the * recovery map. Dlm locks will no longer stall, so lets clear out the * main bitmap. */ int ocfs2_complete_local_alloc_recovery(struct ocfs2_super *osb, struct ocfs2_dinode *alloc) { int status; handle_t *handle; struct buffer_head *main_bm_bh = NULL; struct inode *main_bm_inode; main_bm_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE, OCFS2_INVALID_SLOT); if (!main_bm_inode) { status = -EINVAL; mlog_errno(status); goto out; } inode_lock(main_bm_inode); status = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 1); if (status < 0) { mlog_errno(status); goto out_mutex; } handle = ocfs2_start_trans(osb, OCFS2_WINDOW_MOVE_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto out_unlock; } /* we want the bitmap change to be recorded on disk asap */ handle->h_sync = 1; status = ocfs2_sync_local_to_main(osb, handle, alloc, main_bm_inode, main_bm_bh); if (status < 0) mlog_errno(status); ocfs2_commit_trans(osb, handle); out_unlock: ocfs2_inode_unlock(main_bm_inode, 1); out_mutex: inode_unlock(main_bm_inode); brelse(main_bm_bh); iput(main_bm_inode); out: if (!status) ocfs2_init_steal_slots(osb); if (status) mlog_errno(status); return status; } /* * make sure we've got at least bits_wanted contiguous bits in the * local alloc. You lose them when you drop i_rwsem. * * We will add ourselves to the transaction passed in, but may start * our own in order to shift windows. */ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb, u32 bits_wanted, struct ocfs2_alloc_context *ac) { int status; struct ocfs2_dinode *alloc; struct inode *local_alloc_inode; unsigned int free_bits; BUG_ON(!ac); local_alloc_inode = ocfs2_get_system_file_inode(osb, LOCAL_ALLOC_SYSTEM_INODE, osb->slot_num); if (!local_alloc_inode) { status = -ENOENT; mlog_errno(status); goto bail; } inode_lock(local_alloc_inode); /* * We must double check state and allocator bits because * another process may have changed them while holding i_rwsem. */ spin_lock(&osb->osb_lock); if (!ocfs2_la_state_enabled(osb) || (bits_wanted > osb->local_alloc_bits)) { spin_unlock(&osb->osb_lock); status = -ENOSPC; goto bail; } spin_unlock(&osb->osb_lock); alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; #ifdef CONFIG_OCFS2_DEBUG_FS if (le32_to_cpu(alloc->id1.bitmap1.i_used) != ocfs2_local_alloc_count_bits(alloc)) { status = ocfs2_error(osb->sb, "local alloc inode %llu says it has %u used bits, but a count shows %u\n", (unsigned long long)le64_to_cpu(alloc->i_blkno), le32_to_cpu(alloc->id1.bitmap1.i_used), ocfs2_local_alloc_count_bits(alloc)); goto bail; } #endif free_bits = le32_to_cpu(alloc->id1.bitmap1.i_total) - le32_to_cpu(alloc->id1.bitmap1.i_used); if (bits_wanted > free_bits) { /* uhoh, window change time. */ status = ocfs2_local_alloc_slide_window(osb, local_alloc_inode); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } /* * Under certain conditions, the window slide code * might have reduced the number of bits available or * disabled the local alloc entirely. Re-check * here and return -ENOSPC if necessary. */ status = -ENOSPC; if (!ocfs2_la_state_enabled(osb)) goto bail; free_bits = le32_to_cpu(alloc->id1.bitmap1.i_total) - le32_to_cpu(alloc->id1.bitmap1.i_used); if (bits_wanted > free_bits) goto bail; } ac->ac_inode = local_alloc_inode; /* We should never use localalloc from another slot */ ac->ac_alloc_slot = osb->slot_num; ac->ac_which = OCFS2_AC_USE_LOCAL; get_bh(osb->local_alloc_bh); ac->ac_bh = osb->local_alloc_bh; status = 0; bail: if (status < 0 && local_alloc_inode) { inode_unlock(local_alloc_inode); iput(local_alloc_inode); } trace_ocfs2_reserve_local_alloc_bits( (unsigned long long)ac->ac_max_block, bits_wanted, osb->slot_num, status); if (status) mlog_errno(status); return status; } int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_alloc_context *ac, u32 bits_wanted, u32 *bit_off, u32 *num_bits) { int status, start; struct inode *local_alloc_inode; void *bitmap; struct ocfs2_dinode *alloc; struct ocfs2_local_alloc *la; BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL); local_alloc_inode = ac->ac_inode; alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; la = OCFS2_LOCAL_ALLOC(alloc); start = ocfs2_local_alloc_find_clear_bits(osb, alloc, &bits_wanted, ac->ac_resv); if (start == -1) { /* TODO: Shouldn't we just BUG here? */ status = -ENOSPC; mlog_errno(status); goto bail; } bitmap = la->la_bitmap; *bit_off = le32_to_cpu(la->la_bm_off) + start; *num_bits = bits_wanted; status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), osb->local_alloc_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; } ocfs2_resmap_claimed_bits(&osb->osb_la_resmap, ac->ac_resv, start, bits_wanted); while(bits_wanted--) ocfs2_set_bit(start++, bitmap); le32_add_cpu(&alloc->id1.bitmap1.i_used, *num_bits); ocfs2_journal_dirty(handle, osb->local_alloc_bh); bail: if (status) mlog_errno(status); return status; } int ocfs2_free_local_alloc_bits(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_alloc_context *ac, u32 bit_off, u32 num_bits) { int status, start; u32 clear_bits; struct inode *local_alloc_inode; void *bitmap; struct ocfs2_dinode *alloc; struct ocfs2_local_alloc *la; BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL); local_alloc_inode = ac->ac_inode; alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; la = OCFS2_LOCAL_ALLOC(alloc); bitmap = la->la_bitmap; start = bit_off - le32_to_cpu(la->la_bm_off); clear_bits = num_bits; status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), osb->local_alloc_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; } while (clear_bits--) ocfs2_clear_bit(start++, bitmap); le32_add_cpu(&alloc->id1.bitmap1.i_used, -num_bits); ocfs2_journal_dirty(handle, osb->local_alloc_bh); bail: return status; } static u32 ocfs2_local_alloc_count_bits(struct ocfs2_dinode *alloc) { u32 count; struct ocfs2_local_alloc *la = OCFS2_LOCAL_ALLOC(alloc); count = memweight(la->la_bitmap, le16_to_cpu(la->la_size)); trace_ocfs2_local_alloc_count_bits(count); return count; } static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb, struct ocfs2_dinode *alloc, u32 *numbits, struct ocfs2_alloc_reservation *resv) { int numfound = 0, bitoff, left, startoff; int local_resv = 0; struct ocfs2_alloc_reservation r; void *bitmap = NULL; struct ocfs2_reservation_map *resmap = &osb->osb_la_resmap; if (!alloc->id1.bitmap1.i_total) { bitoff = -1; goto bail; } if (!resv) { local_resv = 1; ocfs2_resv_init_once(&r); ocfs2_resv_set_type(&r, OCFS2_RESV_FLAG_TMP); resv = &r; } numfound = *numbits; if (ocfs2_resmap_resv_bits(resmap, resv, &bitoff, &numfound) == 0) { if (numfound < *numbits) *numbits = numfound; goto bail; } /* * Code error. While reservations are enabled, local * allocation should _always_ go through them. */ BUG_ON(osb->osb_resv_level != 0); /* * Reservations are disabled. Handle this the old way. */ bitmap = OCFS2_LOCAL_ALLOC(alloc)->la_bitmap; numfound = bitoff = startoff = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); while ((bitoff = ocfs2_find_next_zero_bit(bitmap, left, startoff)) < left) { /* Ok, we found a zero bit... is it contig. or do we * start over?*/ if (bitoff == startoff) { /* we found a zero */ numfound++; startoff++; } else { /* got a zero after some ones */ numfound = 1; startoff = bitoff+1; } /* we got everything we needed */ if (numfound == *numbits) { /* mlog(0, "Found it all!\n"); */ break; } } trace_ocfs2_local_alloc_find_clear_bits_search_bitmap(bitoff, numfound); if (numfound == *numbits) bitoff = startoff - numfound; else bitoff = -1; bail: if (local_resv) ocfs2_resv_discard(resmap, resv); trace_ocfs2_local_alloc_find_clear_bits(*numbits, le32_to_cpu(alloc->id1.bitmap1.i_total), bitoff, numfound); return bitoff; } static void ocfs2_clear_local_alloc(struct ocfs2_dinode *alloc) { struct ocfs2_local_alloc *la = OCFS2_LOCAL_ALLOC(alloc); int i; alloc->id1.bitmap1.i_total = 0; alloc->id1.bitmap1.i_used = 0; la->la_bm_off = 0; for(i = 0; i < le16_to_cpu(la->la_size); i++) la->la_bitmap[i] = 0; } #if 0 /* turn this on and uncomment below to aid debugging window shifts. */ static void ocfs2_verify_zero_bits(unsigned long *bitmap, unsigned int start, unsigned int count) { unsigned int tmp = count; while(tmp--) { if (ocfs2_test_bit(start + tmp, bitmap)) { printk("ocfs2_verify_zero_bits: start = %u, count = " "%u\n", start, count); printk("ocfs2_verify_zero_bits: bit %u is set!", start + tmp); BUG(); } } } #endif /* * sync the local alloc to main bitmap. * * assumes you've already locked the main bitmap -- the bitmap inode * passed is used for caching. */ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_dinode *alloc, struct inode *main_bm_inode, struct buffer_head *main_bm_bh) { int status = 0; int bit_off, left, count, start; u64 la_start_blk; u64 blkno; void *bitmap; struct ocfs2_local_alloc *la = OCFS2_LOCAL_ALLOC(alloc); trace_ocfs2_sync_local_to_main( le32_to_cpu(alloc->id1.bitmap1.i_total), le32_to_cpu(alloc->id1.bitmap1.i_used)); if (!alloc->id1.bitmap1.i_total) { goto bail; } if (le32_to_cpu(alloc->id1.bitmap1.i_used) == le32_to_cpu(alloc->id1.bitmap1.i_total)) { goto bail; } la_start_blk = ocfs2_clusters_to_blocks(osb->sb, le32_to_cpu(la->la_bm_off)); bitmap = la->la_bitmap; start = count = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); while (1) { bit_off = ocfs2_find_next_zero_bit(bitmap, left, start); if ((bit_off < left) && (bit_off == start)) { count++; start++; continue; } if (count) { blkno = la_start_blk + ocfs2_clusters_to_blocks(osb->sb, start - count); trace_ocfs2_sync_local_to_main_free( count, start - count, (unsigned long long)la_start_blk, (unsigned long long)blkno); status = ocfs2_release_clusters(handle, main_bm_inode, main_bm_bh, blkno, count); if (status < 0) { mlog_errno(status); goto bail; } } if (bit_off >= left) break; count = 1; start = bit_off + 1; } bail: if (status) mlog_errno(status); return status; } enum ocfs2_la_event { OCFS2_LA_EVENT_SLIDE, /* Normal window slide. */ OCFS2_LA_EVENT_FRAGMENTED, /* The global bitmap has * enough bits theoretically * free, but a contiguous * allocation could not be * found. */ OCFS2_LA_EVENT_ENOSPC, /* Global bitmap doesn't have * enough bits free to satisfy * our request. */ }; #define OCFS2_LA_ENABLE_INTERVAL (30 * HZ) /* * Given an event, calculate the size of our next local alloc window. * * This should always be called under i_rwsem of the local alloc inode * so that local alloc disabling doesn't race with processes trying to * use the allocator. * * Returns the state which the local alloc was left in. This value can * be ignored by some paths. */ static int ocfs2_recalc_la_window(struct ocfs2_super *osb, enum ocfs2_la_event event) { unsigned int bits; int state; spin_lock(&osb->osb_lock); if (osb->local_alloc_state == OCFS2_LA_DISABLED) { WARN_ON_ONCE(osb->local_alloc_state == OCFS2_LA_DISABLED); goto out_unlock; } /* * ENOSPC and fragmentation are treated similarly for now. */ if (event == OCFS2_LA_EVENT_ENOSPC || event == OCFS2_LA_EVENT_FRAGMENTED) { /* * We ran out of contiguous space in the primary * bitmap. Drastically reduce the number of bits used * by local alloc until we have to disable it. */ bits = osb->local_alloc_bits >> 1; if (bits > ocfs2_megabytes_to_clusters(osb->sb, 1)) { /* * By setting state to THROTTLED, we'll keep * the number of local alloc bits used down * until an event occurs which would give us * reason to assume the bitmap situation might * have changed. */ osb->local_alloc_state = OCFS2_LA_THROTTLED; osb->local_alloc_bits = bits; } else { osb->local_alloc_state = OCFS2_LA_DISABLED; } queue_delayed_work(osb->ocfs2_wq, &osb->la_enable_wq, OCFS2_LA_ENABLE_INTERVAL); goto out_unlock; } /* * Don't increase the size of the local alloc window until we * know we might be able to fulfill the request. Otherwise, we * risk bouncing around the global bitmap during periods of * low space. */ if (osb->local_alloc_state != OCFS2_LA_THROTTLED) osb->local_alloc_bits = osb->local_alloc_default_bits; out_unlock: state = osb->local_alloc_state; spin_unlock(&osb->osb_lock); return state; } static int ocfs2_local_alloc_reserve_for_window(struct ocfs2_super *osb, struct ocfs2_alloc_context **ac, struct inode **bitmap_inode, struct buffer_head **bitmap_bh) { int status; *ac = kzalloc(sizeof(struct ocfs2_alloc_context), GFP_KERNEL); if (!(*ac)) { status = -ENOMEM; mlog_errno(status); goto bail; } retry_enospc: (*ac)->ac_bits_wanted = osb->local_alloc_bits; status = ocfs2_reserve_cluster_bitmap_bits(osb, *ac); if (status == -ENOSPC) { if (ocfs2_recalc_la_window(osb, OCFS2_LA_EVENT_ENOSPC) == OCFS2_LA_DISABLED) goto bail; ocfs2_free_ac_resource(*ac); memset(*ac, 0, sizeof(struct ocfs2_alloc_context)); goto retry_enospc; } if (status < 0) { mlog_errno(status); goto bail; } *bitmap_inode = (*ac)->ac_inode; igrab(*bitmap_inode); *bitmap_bh = (*ac)->ac_bh; get_bh(*bitmap_bh); status = 0; bail: if ((status < 0) && *ac) { ocfs2_free_alloc_context(*ac); *ac = NULL; } if (status) mlog_errno(status); return status; } /* * pass it the bitmap lock in lock_bh if you have it. */ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb, handle_t *handle, struct ocfs2_alloc_context *ac) { int status = 0; u32 cluster_off, cluster_count; struct ocfs2_dinode *alloc = NULL; struct ocfs2_local_alloc *la; alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; la = OCFS2_LOCAL_ALLOC(alloc); trace_ocfs2_local_alloc_new_window( le32_to_cpu(alloc->id1.bitmap1.i_total), osb->local_alloc_bits); /* Instruct the allocation code to try the most recently used * cluster group. We'll re-record the group used this pass * below. */ ac->ac_last_group = osb->la_last_gd; /* we used the generic suballoc reserve function, but we set * everything up nicely, so there's no reason why we can't use * the more specific cluster api to claim bits. */ status = ocfs2_claim_clusters(handle, ac, osb->local_alloc_bits, &cluster_off, &cluster_count); if (status == -ENOSPC) { retry_enospc: /* * Note: We could also try syncing the journal here to * allow use of any free bits which the current * transaction can't give us access to. --Mark */ if (ocfs2_recalc_la_window(osb, OCFS2_LA_EVENT_FRAGMENTED) == OCFS2_LA_DISABLED) goto bail; ac->ac_bits_wanted = osb->local_alloc_bits; status = ocfs2_claim_clusters(handle, ac, osb->local_alloc_bits, &cluster_off, &cluster_count); if (status == -ENOSPC) goto retry_enospc; /* * We only shrunk the *minimum* number of in our * request - it's entirely possible that the allocator * might give us more than we asked for. */ if (status == 0) { spin_lock(&osb->osb_lock); osb->local_alloc_bits = cluster_count; spin_unlock(&osb->osb_lock); } } if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } osb->la_last_gd = ac->ac_last_group; la->la_bm_off = cpu_to_le32(cluster_off); alloc->id1.bitmap1.i_total = cpu_to_le32(cluster_count); /* just in case... In the future when we find space ourselves, * we don't have to get all contiguous -- but we'll have to * set all previously used bits in bitmap and update * la_bits_set before setting the bits in the main bitmap. */ alloc->id1.bitmap1.i_used = 0; memset(OCFS2_LOCAL_ALLOC(alloc)->la_bitmap, 0, le16_to_cpu(la->la_size)); ocfs2_resmap_restart(&osb->osb_la_resmap, cluster_count, OCFS2_LOCAL_ALLOC(alloc)->la_bitmap); trace_ocfs2_local_alloc_new_window_result( le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off), le32_to_cpu(alloc->id1.bitmap1.i_total)); bail: if (status) mlog_errno(status); return status; } /* Note that we do *NOT* lock the local alloc inode here as * it's been locked already for us. */ static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb, struct inode *local_alloc_inode) { int status = 0; struct buffer_head *main_bm_bh = NULL; struct inode *main_bm_inode = NULL; handle_t *handle = NULL; struct ocfs2_dinode *alloc; struct ocfs2_dinode *alloc_copy = NULL; struct ocfs2_alloc_context *ac = NULL; ocfs2_recalc_la_window(osb, OCFS2_LA_EVENT_SLIDE); /* This will lock the main bitmap for us. */ status = ocfs2_local_alloc_reserve_for_window(osb, &ac, &main_bm_inode, &main_bm_bh); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } handle = ocfs2_start_trans(osb, OCFS2_WINDOW_MOVE_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto bail; } alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; /* We want to clear the local alloc before doing anything * else, so that if we error later during this operation, * local alloc shutdown won't try to double free main bitmap * bits. Make a copy so the sync function knows which bits to * free. */ alloc_copy = kmemdup(alloc, osb->local_alloc_bh->b_size, GFP_NOFS); if (!alloc_copy) { status = -ENOMEM; mlog_errno(status); goto bail; } status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), osb->local_alloc_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; } ocfs2_clear_local_alloc(alloc); ocfs2_journal_dirty(handle, osb->local_alloc_bh); status = ocfs2_sync_local_to_main(osb, handle, alloc_copy, main_bm_inode, main_bm_bh); if (status < 0) { mlog_errno(status); goto bail; } status = ocfs2_local_alloc_new_window(osb, handle, ac); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } atomic_inc(&osb->alloc_stats.moves); bail: if (handle) ocfs2_commit_trans(osb, handle); brelse(main_bm_bh); iput(main_bm_inode); kfree(alloc_copy); if (ac) ocfs2_free_alloc_context(ac); if (status) mlog_errno(status); return status; } |
| 3927 3923 4723 4723 | 1 2 3 4 5 6 7 8 9 10 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BACKING_DEV_DEFS_H #define __LINUX_BACKING_DEV_DEFS_H #include <linux/list.h> #include <linux/radix-tree.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/percpu_counter.h> #include <linux/percpu-refcount.h> #include <linux/flex_proportions.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/kref.h> #include <linux/refcount.h> struct page; struct device; struct dentry; /* * Bits in bdi_writeback.state */ enum wb_state { WB_registered, /* bdi_register() was done */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ WB_start_all, /* nr_pages == 0 (all) work pending */ }; enum wb_stat_item { WB_RECLAIMABLE, WB_WRITEBACK, WB_DIRTIED, WB_WRITTEN, NR_WB_STAT_ITEMS }; #define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) /* * why some writeback work was initiated */ enum wb_reason { WB_REASON_BACKGROUND, WB_REASON_VMSCAN, WB_REASON_SYNC, WB_REASON_PERIODIC, WB_REASON_LAPTOP_TIMER, WB_REASON_FS_FREE_SPACE, /* * There is no bdi forker thread any more and works are done * by emergency worker, however, this is TPs userland visible * and we'll be exposing exactly the same information, * so it has a mismatch name. */ WB_REASON_FORKER_THREAD, WB_REASON_FOREIGN_FLUSH, WB_REASON_MAX, }; struct wb_completion { atomic_t cnt; wait_queue_head_t *waitq; }; #define __WB_COMPLETION_INIT(_waitq) \ (struct wb_completion){ .cnt = ATOMIC_INIT(1), .waitq = (_waitq) } /* * If one wants to wait for one or more wb_writeback_works, each work's * ->done should be set to a wb_completion defined using the following * macro. Once all work items are issued with wb_queue_work(), the caller * can wait for the completion of all using wb_wait_for_completion(). Work * items which are waited upon aren't freed automatically on completion. */ #define WB_COMPLETION_INIT(bdi) __WB_COMPLETION_INIT(&(bdi)->wb_waitq) #define DEFINE_WB_COMPLETION(cmpl, bdi) \ struct wb_completion cmpl = WB_COMPLETION_INIT(bdi) /* * Each wb (bdi_writeback) can perform writeback operations, is measured * and throttled, independently. Without cgroup writeback, each bdi * (bdi_writeback) is served by its embedded bdi->wb. * * On the default hierarchy, blkcg implicitly enables memcg. This allows * using memcg's page ownership for attributing writeback IOs, and every * memcg - blkcg combination can be served by its own wb by assigning a * dedicated wb to each memcg, which enables isolation across different * cgroups and propagation of IO back pressure down from the IO layer upto * the tasks which are generating the dirty pages to be written back. * * A cgroup wb is indexed on its bdi by the ID of the associated memcg, * refcounted with the number of inodes attached to it, and pins the memcg * and the corresponding blkcg. As the corresponding blkcg for a memcg may * change as blkcg is disabled and enabled higher up in the hierarchy, a wb * is tested for blkcg after lookup and removed from index on mismatch so * that a new wb for the combination can be created. * * Each bdi_writeback that is not embedded into the backing_dev_info must hold * a reference to the parent backing_dev_info. See cgwb_create() for details. */ struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ unsigned long state; /* Always use atomic bitops on this */ unsigned long last_old_flush; /* last old data flush */ struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ struct list_head b_dirty_time; /* time stamps are dirty */ spinlock_t list_lock; /* protects the b_* lists */ atomic_t writeback_inodes; /* number of inodes under writeback */ struct percpu_counter stat[NR_WB_STAT_ITEMS]; unsigned long bw_time_stamp; /* last time write bw is updated */ unsigned long dirtied_stamp; unsigned long written_stamp; /* pages written at bw_time_stamp */ unsigned long write_bandwidth; /* the estimated write bandwidth */ unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */ /* * The base dirty throttle rate, re-calculated on every 200ms. * All the bdi tasks' dirty rate will be curbed under it. * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit * in small steps and is much more smooth/stable than the latter. */ unsigned long dirty_ratelimit; unsigned long balanced_dirty_ratelimit; struct fprop_local_percpu completions; int dirty_exceeded; enum wb_reason start_all_reason; spinlock_t work_lock; /* protects work_list & dwork scheduling */ struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ struct delayed_work bw_dwork; /* work item used for bandwidth estimate */ struct list_head bdi_node; /* anchored at bdi->wb_list */ #ifdef CONFIG_CGROUP_WRITEBACK struct percpu_ref refcnt; /* used only for !root wb's */ struct fprop_local_percpu memcg_completions; struct cgroup_subsys_state *memcg_css; /* the associated memcg */ struct cgroup_subsys_state *blkcg_css; /* and blkcg */ struct list_head memcg_node; /* anchored at memcg->cgwb_list */ struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ struct list_head b_attached; /* attached inodes, protected by list_lock */ struct list_head offline_node; /* anchored at offline_cgwbs */ union { struct work_struct release_work; struct rcu_head rcu; }; #endif }; struct backing_dev_info { u64 id; struct rb_node rb_node; /* keyed by ->id */ struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long io_pages; /* max allowed IO size */ struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ unsigned int min_ratio; unsigned int max_ratio, max_prop_frac; /* * Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are * any dirty wbs, which is depended upon by bdi_has_dirty(). */ atomic_long_t tot_write_bandwidth; /* * Jiffies when last process was dirty throttled on this bdi. Used by * blk-wbt. */ unsigned long last_bdp_sleep; struct bdi_writeback wb; /* the root writeback info for this bdi */ struct list_head wb_list; /* list of all wbs */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ #endif wait_queue_head_t wb_waitq; struct device *dev; char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; #endif }; struct wb_lock_cookie { bool locked; unsigned long flags; }; #ifdef CONFIG_CGROUP_WRITEBACK /** * wb_tryget - try to increment a wb's refcount * @wb: bdi_writeback to get */ static inline bool wb_tryget(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) return percpu_ref_tryget(&wb->refcnt); return true; } /** * wb_get - increment a wb's refcount * @wb: bdi_writeback to get */ static inline void wb_get(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) percpu_ref_get(&wb->refcnt); } /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put * @nr: number of references to put */ static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { if (WARN_ON_ONCE(!wb->bdi)) { /* * A driver bug might cause a file to be removed before bdi was * initialized. */ return; } if (wb != &wb->bdi->wb) percpu_ref_put_many(&wb->refcnt, nr); } /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put */ static inline void wb_put(struct bdi_writeback *wb) { wb_put_many(wb, 1); } /** * wb_dying - is a wb dying? * @wb: bdi_writeback of interest * * Returns whether @wb is unlinked and being drained. */ static inline bool wb_dying(struct bdi_writeback *wb) { return percpu_ref_is_dying(&wb->refcnt); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool wb_tryget(struct bdi_writeback *wb) { return true; } static inline void wb_get(struct bdi_writeback *wb) { } static inline void wb_put(struct bdi_writeback *wb) { } static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { } static inline bool wb_dying(struct bdi_writeback *wb) { return false; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* __LINUX_BACKING_DEV_DEFS_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * acpi.h - ACPI Interface * * Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> */ #ifndef _LINUX_ACPI_H #define _LINUX_ACPI_H #include <linux/errno.h> #include <linux/ioport.h> /* for struct resource */ #include <linux/resource_ext.h> #include <linux/device.h> #include <linux/mod_devicetable.h> #include <linux/property.h> #include <linux/uuid.h> #include <linux/node.h> struct irq_domain; struct irq_domain_ops; #ifndef _LINUX #define _LINUX #endif #include <acpi/acpi.h> #include <acpi/acpi_numa.h> #ifdef CONFIG_ACPI #include <linux/list.h> #include <linux/dynamic_debug.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/fw_table.h> #include <acpi/acpi_bus.h> #include <acpi/acpi_drivers.h> #include <acpi/acpi_io.h> #include <asm/acpi.h> #ifdef CONFIG_ACPI_TABLE_LIB #define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, "ACPI") #define __init_or_acpilib #define __initdata_or_acpilib #else #define EXPORT_SYMBOL_ACPI_LIB(x) #define __init_or_acpilib __init #define __initdata_or_acpilib __initdata #endif static inline acpi_handle acpi_device_handle(struct acpi_device *adev) { return adev ? adev->handle : NULL; } #define ACPI_COMPANION(dev) to_acpi_device_node((dev)->fwnode) #define ACPI_COMPANION_SET(dev, adev) set_primary_fwnode(dev, (adev) ? \ acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) #define ACPI_HANDLE_FWNODE(fwnode) \ acpi_device_handle(to_acpi_device_node(fwnode)) static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) { struct fwnode_handle *fwnode; fwnode = kzalloc(sizeof(struct fwnode_handle), GFP_KERNEL); if (!fwnode) return NULL; fwnode_init(fwnode, &acpi_static_fwnode_ops); return fwnode; } static inline void acpi_free_fwnode_static(struct fwnode_handle *fwnode) { if (WARN_ON(!is_acpi_static_node(fwnode))) return; kfree(fwnode); } static inline bool has_acpi_companion(struct device *dev) { return is_acpi_device_node(dev->fwnode); } static inline void acpi_preset_companion(struct device *dev, struct acpi_device *parent, u64 addr) { ACPI_COMPANION_SET(dev, acpi_find_child_device(parent, addr, false)); } static inline const char *acpi_dev_name(struct acpi_device *adev) { return dev_name(&adev->dev); } struct device *acpi_get_first_physical_node(struct acpi_device *adev); enum acpi_irq_model_id { ACPI_IRQ_MODEL_PIC = 0, ACPI_IRQ_MODEL_IOAPIC, ACPI_IRQ_MODEL_IOSAPIC, ACPI_IRQ_MODEL_PLATFORM, ACPI_IRQ_MODEL_GIC, ACPI_IRQ_MODEL_LPIC, ACPI_IRQ_MODEL_RINTC, ACPI_IRQ_MODEL_COUNT }; extern enum acpi_irq_model_id acpi_irq_model; enum acpi_interrupt_id { ACPI_INTERRUPT_PMI = 1, ACPI_INTERRUPT_INIT, ACPI_INTERRUPT_CPEI, ACPI_INTERRUPT_COUNT }; #define ACPI_SPACE_MEM 0 enum acpi_address_range_id { ACPI_ADDRESS_RANGE_MEMORY = 1, ACPI_ADDRESS_RANGE_RESERVED = 2, ACPI_ADDRESS_RANGE_ACPI = 3, ACPI_ADDRESS_RANGE_NVS = 4, ACPI_ADDRESS_RANGE_COUNT }; /* Table Handlers */ typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); /* Debugger support */ struct acpi_debugger_ops { int (*create_thread)(acpi_osd_exec_callback function, void *context); ssize_t (*write_log)(const char *msg); ssize_t (*read_cmd)(char *buffer, size_t length); int (*wait_command_ready)(bool single_step, char *buffer, size_t length); int (*notify_command_complete)(void); }; struct acpi_debugger { const struct acpi_debugger_ops *ops; struct module *owner; struct mutex lock; }; #ifdef CONFIG_ACPI_DEBUGGER int __init acpi_debugger_init(void); int acpi_register_debugger(struct module *owner, const struct acpi_debugger_ops *ops); void acpi_unregister_debugger(const struct acpi_debugger_ops *ops); int acpi_debugger_create_thread(acpi_osd_exec_callback function, void *context); ssize_t acpi_debugger_write_log(const char *msg); ssize_t acpi_debugger_read_cmd(char *buffer, size_t buffer_length); int acpi_debugger_wait_command_ready(void); int acpi_debugger_notify_command_complete(void); #else static inline int acpi_debugger_init(void) { return -ENODEV; } static inline int acpi_register_debugger(struct module *owner, const struct acpi_debugger_ops *ops) { return -ENODEV; } static inline void acpi_unregister_debugger(const struct acpi_debugger_ops *ops) { } static inline int acpi_debugger_create_thread(acpi_osd_exec_callback function, void *context) { return -ENODEV; } static inline int acpi_debugger_write_log(const char *msg) { return -ENODEV; } static inline int acpi_debugger_read_cmd(char *buffer, u32 buffer_length) { return -ENODEV; } static inline int acpi_debugger_wait_command_ready(void) { return -ENODEV; } static inline int acpi_debugger_notify_command_complete(void) { return -ENODEV; } #endif #define BAD_MADT_ENTRY(entry, end) ( \ (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ ((struct acpi_subtable_header *)entry)->length < sizeof(*entry)) void __iomem *__acpi_map_table(unsigned long phys, unsigned long size); void __acpi_unmap_table(void __iomem *map, unsigned long size); int early_acpi_boot_init(void); int acpi_boot_init (void); void acpi_boot_table_prepare (void); void acpi_boot_table_init (void); int acpi_mps_check (void); int acpi_numa_init (void); int acpi_locate_initial_tables (void); void acpi_reserve_initial_tables (void); void acpi_table_init_complete (void); int acpi_table_init (void); int acpi_table_parse(char *id, acpi_tbl_table_handler handler); int __init_or_acpilib acpi_table_parse_entries(char *id, unsigned long table_size, int entry_id, acpi_tbl_entry_handler handler, unsigned int max_entries); int __init_or_acpilib acpi_table_parse_entries_array(char *id, unsigned long table_size, struct acpi_subtable_proc *proc, int proc_num, unsigned int max_entries); int acpi_table_parse_madt(enum acpi_madt_type id, acpi_tbl_entry_handler handler, unsigned int max_entries); int __init_or_acpilib acpi_table_parse_cedt(enum acpi_cedt_type id, acpi_tbl_entry_handler_arg handler_arg, void *arg); int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); #if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); #else static inline void acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { } #endif void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); #if defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) void acpi_arch_dma_setup(struct device *dev); #else static inline void acpi_arch_dma_setup(struct device *dev) { } #endif #ifdef CONFIG_ARM64 void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa); #else static inline void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } #endif #ifdef CONFIG_RISCV void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa); #else static inline void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { } #endif #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t; #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1) #endif static inline bool invalid_logical_cpuid(u32 cpuid) { return (int)cpuid < 0; } static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) { return phys_id == PHYS_CPUID_INVALID; } int __init acpi_get_madt_revision(void); /* Validate the processor object's proc_id */ bool acpi_duplicate_processor_id(int proc_id); /* Processor _CTS control */ struct acpi_processor_power; #ifdef CONFIG_ACPI_PROCESSOR_CSTATE bool acpi_processor_claim_cst_control(void); int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, struct acpi_processor_power *info); #else static inline bool acpi_processor_claim_cst_control(void) { return false; } static inline int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, struct acpi_processor_power *info) { return -ENODEV; } #endif #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu); int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ acpi_handle acpi_get_processor_handle(int cpu); #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); #endif int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base); int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base); int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base); void acpi_irq_stats_init(void); extern u32 acpi_irq_handled; extern u32 acpi_irq_not_handled; extern unsigned int acpi_sci_irq; extern bool acpi_no_s5; #define INVALID_ACPI_IRQ ((unsigned)-1) static inline bool acpi_sci_irq_valid(void) { return acpi_sci_irq != INVALID_ACPI_IRQ; } extern int sbf_port; int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity); int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi); void acpi_set_irq_model(enum acpi_irq_model_id model, struct fwnode_handle *(*)(u32)); void acpi_set_gsi_to_irq_fallback(u32 (*)(u32)); struct irq_domain *acpi_irq_create_hierarchy(unsigned int flags, unsigned int size, struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data); #ifdef CONFIG_X86_IO_APIC extern int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #else static inline int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) { return -1; } #endif /* * This function undoes the effect of one call to acpi_register_gsi(). * If this matches the last registration, any IRQ resources for gsi * are freed. */ void acpi_unregister_gsi (u32 gsi); struct pci_dev; struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin); int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); bool acpi_isa_irq_available(int irq); #ifdef CONFIG_PCI void acpi_penalize_sci_irq(int irq, int trigger, int polarity); #else static inline void acpi_penalize_sci_irq(int irq, int trigger, int polarity) { } #endif void acpi_pci_irq_disable (struct pci_dev *dev); extern int ec_read(u8 addr, u8 *val); extern int ec_write(u8 addr, u8 val); extern int ec_transaction(u8 command, const u8 *wdata, unsigned wdata_len, u8 *rdata, unsigned rdata_len); extern acpi_handle ec_get_handle(void); extern bool acpi_is_pnp_device(struct acpi_device *); #if defined(CONFIG_ACPI_WMI) || defined(CONFIG_ACPI_WMI_MODULE) typedef void (*wmi_notify_handler) (union acpi_object *data, void *context); int wmi_instance_count(const char *guid); extern acpi_status wmi_evaluate_method(const char *guid, u8 instance, u32 method_id, const struct acpi_buffer *in, struct acpi_buffer *out); extern acpi_status wmi_query_block(const char *guid, u8 instance, struct acpi_buffer *out); extern acpi_status wmi_set_block(const char *guid, u8 instance, const struct acpi_buffer *in); extern acpi_status wmi_install_notify_handler(const char *guid, wmi_notify_handler handler, void *data); extern acpi_status wmi_remove_notify_handler(const char *guid); extern bool wmi_has_guid(const char *guid); extern char *wmi_get_acpi_device_uid(const char *guid); #endif /* CONFIG_ACPI_WMI */ #define ACPI_VIDEO_OUTPUT_SWITCHING 0x0001 #define ACPI_VIDEO_DEVICE_POSTING 0x0002 #define ACPI_VIDEO_ROM_AVAILABLE 0x0004 #define ACPI_VIDEO_BACKLIGHT 0x0008 #define ACPI_VIDEO_BACKLIGHT_FORCE_VENDOR 0x0010 #define ACPI_VIDEO_BACKLIGHT_FORCE_VIDEO 0x0020 #define ACPI_VIDEO_OUTPUT_SWITCHING_FORCE_VENDOR 0x0040 #define ACPI_VIDEO_OUTPUT_SWITCHING_FORCE_VIDEO 0x0080 #define ACPI_VIDEO_BACKLIGHT_DMI_VENDOR 0x0100 #define ACPI_VIDEO_BACKLIGHT_DMI_VIDEO 0x0200 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VENDOR 0x0400 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VIDEO 0x0800 extern char acpi_video_backlight_string[]; extern long acpi_is_video_device(acpi_handle handle); extern void acpi_osi_setup(char *str); extern bool acpi_osi_is_win8(void); #ifdef CONFIG_ACPI_THERMAL_LIB int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp); int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp); int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp); int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp); #endif #ifdef CONFIG_ACPI_HMAT int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord); #else static inline int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord) { return -EOPNOTSUPP; } #endif #ifdef CONFIG_ACPI_NUMA int acpi_map_pxm_to_node(int pxm); int acpi_get_node(acpi_handle handle); /** * pxm_to_online_node - Map proximity ID to online node * @pxm: ACPI proximity ID * * This is similar to pxm_to_node(), but always returns an online * node. When the mapped node from a given proximity ID is offline, it * looks up the node distance table and returns the nearest online node. * * ACPI device drivers, which are called after the NUMA initialization has * completed in the kernel, can call this interface to obtain their device * NUMA topology from ACPI tables. Such drivers do not have to deal with * offline nodes. A node may be offline when SRAT memory entry does not exist, * or NUMA is disabled, ex. "numa=off" on x86. */ static inline int pxm_to_online_node(int pxm) { int node = pxm_to_node(pxm); return numa_map_to_online_node(node); } #else static inline int pxm_to_online_node(int pxm) { return 0; } static inline int acpi_map_pxm_to_node(int pxm) { return 0; } static inline int acpi_get_node(acpi_handle handle) { return 0; } #endif extern int pnpacpi_disabled; #define PXM_INVAL (-1) bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_address_space(struct acpi_resource *ares, struct resource_win *win); bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, struct resource_win *win); unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable, u8 wake_capable); unsigned int acpi_dev_get_irq_type(int triggering, int polarity); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), void *preproc_data); int acpi_dev_get_dma_resources(struct acpi_device *adev, struct list_head *list); int acpi_dev_get_memory_resources(struct acpi_device *adev, struct list_head *list); int acpi_dev_filter_resource_type(struct acpi_resource *ares, unsigned long types); static inline int acpi_dev_filter_resource_type_cb(struct acpi_resource *ares, void *arg) { return acpi_dev_filter_resource_type(ares, (unsigned long)arg); } struct acpi_device *acpi_resource_consumer(struct resource *res); int acpi_check_resource_conflict(const struct resource *res); int acpi_check_region(resource_size_t start, resource_size_t n, const char *name); int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION extern int acpi_check_s4_hw_signature; #endif #ifdef CONFIG_PM_SLEEP void __init acpi_old_suspend_ordering(void); void __init acpi_nvs_nosave(void); void __init acpi_nvs_nosave_s3(void); void __init acpi_sleep_no_blacklist(void); #endif /* CONFIG_PM_SLEEP */ int acpi_register_wakeup_handler( int wake_irq, bool (*wakeup)(void *context), void *context); void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context); struct acpi_osc_context { char *uuid_str; /* UUID string */ int rev; struct acpi_buffer cap; /* list of DWORD capabilities */ struct acpi_buffer ret; /* free by caller if success */ }; acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); /* Number of _OSC capability DWORDS depends on bridge type */ #define OSC_PCI_CAPABILITY_DWORDS 3 #define OSC_CXL_CAPABILITY_DWORDS 5 /* Indexes into _OSC Capabilities Buffer (DWORDs 2 to 5 are device-specific) */ #define OSC_QUERY_DWORD 0 /* DWORD 1 */ #define OSC_SUPPORT_DWORD 1 /* DWORD 2 */ #define OSC_CONTROL_DWORD 2 /* DWORD 3 */ #define OSC_EXT_SUPPORT_DWORD 3 /* DWORD 4 */ #define OSC_EXT_CONTROL_DWORD 4 /* DWORD 5 */ /* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */ #define OSC_QUERY_ENABLE 0x00000001 /* input */ #define OSC_REQUEST_ERROR 0x00000002 /* return */ #define OSC_INVALID_UUID_ERROR 0x00000004 /* return */ #define OSC_INVALID_REVISION_ERROR 0x00000008 /* return */ #define OSC_CAPABILITIES_MASK_ERROR 0x00000010 /* return */ /* Platform-Wide Capabilities _OSC: Capabilities DWORD 2: Support Field */ #define OSC_SB_PAD_SUPPORT 0x00000001 #define OSC_SB_PPC_OST_SUPPORT 0x00000002 #define OSC_SB_PR3_SUPPORT 0x00000004 #define OSC_SB_HOTPLUG_OST_SUPPORT 0x00000008 #define OSC_SB_APEI_SUPPORT 0x00000010 #define OSC_SB_CPC_SUPPORT 0x00000020 #define OSC_SB_CPCV2_SUPPORT 0x00000040 #define OSC_SB_PCLPI_SUPPORT 0x00000080 #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_FAST_THERMAL_SAMPLING_SUPPORT 0x00000200 #define OSC_SB_OVER_16_PSTATES_SUPPORT 0x00000400 #define OSC_SB_GED_SUPPORT 0x00000800 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_IRQ_RESOURCE_SOURCE_SUPPORT 0x00002000 #define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00020000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 #define OSC_SB_BATTERY_CHARGE_LIMITING_SUPPORT 0x00080000 #define OSC_SB_PRM_SUPPORT 0x00200000 #define OSC_SB_FFH_OPR_SUPPORT 0x00400000 extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; extern bool osc_sb_cppc2_support_acked; extern bool osc_cpc_flexible_adr_space_confirmed; /* USB4 Capabilities */ #define OSC_USB_USB3_TUNNELING 0x00000001 #define OSC_USB_DP_TUNNELING 0x00000002 #define OSC_USB_PCIE_TUNNELING 0x00000004 #define OSC_USB_XDOMAIN 0x00000008 extern u32 osc_sb_native_usb4_control; /* PCI Host Bridge _OSC: Capabilities DWORD 2: Support Field */ #define OSC_PCI_EXT_CONFIG_SUPPORT 0x00000001 #define OSC_PCI_ASPM_SUPPORT 0x00000002 #define OSC_PCI_CLOCK_PM_SUPPORT 0x00000004 #define OSC_PCI_SEGMENT_GROUPS_SUPPORT 0x00000008 #define OSC_PCI_MSI_SUPPORT 0x00000010 #define OSC_PCI_EDR_SUPPORT 0x00000080 #define OSC_PCI_HPX_TYPE_3_SUPPORT 0x00000100 /* PCI Host Bridge _OSC: Capabilities DWORD 3: Control Field */ #define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL 0x00000001 #define OSC_PCI_SHPC_NATIVE_HP_CONTROL 0x00000002 #define OSC_PCI_EXPRESS_PME_CONTROL 0x00000004 #define OSC_PCI_EXPRESS_AER_CONTROL 0x00000008 #define OSC_PCI_EXPRESS_CAPABILITY_CONTROL 0x00000010 #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 /* CXL _OSC: Capabilities DWORD 4: Support Field */ #define OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT 0x00000001 #define OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT 0x00000002 #define OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT 0x00000004 #define OSC_CXL_NATIVE_HP_SUPPORT 0x00000008 /* CXL _OSC: Capabilities DWORD 5: Control Field */ #define OSC_CXL_ERROR_REPORTING_CONTROL 0x00000001 static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) { u32 *ret = context->ret.pointer; return ret[OSC_CONTROL_DWORD]; } static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) { u32 *ret = context->ret.pointer; return ret[OSC_EXT_CONTROL_DWORD]; } #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 #define ACPI_GSB_ACCESS_ATTRIB_BYTE 0x00000006 #define ACPI_GSB_ACCESS_ATTRIB_WORD 0x00000008 #define ACPI_GSB_ACCESS_ATTRIB_BLOCK 0x0000000A #define ACPI_GSB_ACCESS_ATTRIB_MULTIBYTE 0x0000000B #define ACPI_GSB_ACCESS_ATTRIB_WORD_CALL 0x0000000C #define ACPI_GSB_ACCESS_ATTRIB_BLOCK_CALL 0x0000000D #define ACPI_GSB_ACCESS_ATTRIB_RAW_BYTES 0x0000000E #define ACPI_GSB_ACCESS_ATTRIB_RAW_PROCESS 0x0000000F /* Enable _OST when all relevant hotplug operations are enabled */ #if defined(CONFIG_ACPI_HOTPLUG_CPU) && \ defined(CONFIG_ACPI_HOTPLUG_MEMORY) && \ defined(CONFIG_ACPI_CONTAINER) #define ACPI_HOTPLUG_OST #endif /* _OST Source Event Code (OSPM Action) */ #define ACPI_OST_EC_OSPM_SHUTDOWN 0x100 #define ACPI_OST_EC_OSPM_EJECT 0x103 #define ACPI_OST_EC_OSPM_INSERTION 0x200 /* _OST General Processing Status Code */ #define ACPI_OST_SC_SUCCESS 0x0 #define ACPI_OST_SC_NON_SPECIFIC_FAILURE 0x1 #define ACPI_OST_SC_UNRECOGNIZED_NOTIFY 0x2 /* _OST OS Shutdown Processing (0x100) Status Code */ #define ACPI_OST_SC_OS_SHUTDOWN_DENIED 0x80 #define ACPI_OST_SC_OS_SHUTDOWN_IN_PROGRESS 0x81 #define ACPI_OST_SC_OS_SHUTDOWN_COMPLETED 0x82 #define ACPI_OST_SC_OS_SHUTDOWN_NOT_SUPPORTED 0x83 /* _OST Ejection Request (0x3, 0x103) Status Code */ #define ACPI_OST_SC_EJECT_NOT_SUPPORTED 0x80 #define ACPI_OST_SC_DEVICE_IN_USE 0x81 #define ACPI_OST_SC_DEVICE_BUSY 0x82 #define ACPI_OST_SC_EJECT_DEPENDENCY_BUSY 0x83 #define ACPI_OST_SC_EJECT_IN_PROGRESS 0x84 /* _OST Insertion Request (0x200) Status Code */ #define ACPI_OST_SC_INSERT_IN_PROGRESS 0x80 #define ACPI_OST_SC_DRIVER_LOAD_FAILURE 0x81 #define ACPI_OST_SC_INSERT_NOT_SUPPORTED 0x82 enum acpi_predicate { all_versions, less_than_or_equal, equal, greater_than_or_equal, }; /* Table must be terminted by a NULL entry */ struct acpi_platform_list { char oem_id[ACPI_OEM_ID_SIZE+1]; char oem_table_id[ACPI_OEM_TABLE_ID_SIZE+1]; u32 oem_revision; char *table; enum acpi_predicate pred; char *reason; u32 data; }; int acpi_match_platform_list(const struct acpi_platform_list *plat); extern void acpi_early_init(void); extern void acpi_subsystem_init(void); extern int acpi_nvs_register(__u64 start, __u64 size); extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), void *data); const struct acpi_device_id *acpi_match_acpi_device(const struct acpi_device_id *ids, const struct acpi_device *adev); const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids, const struct device *dev); const void *acpi_device_get_match_data(const struct device *dev); extern bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv); int acpi_device_uevent_modalias(const struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); struct platform_device *acpi_create_platform_device(struct acpi_device *, const struct property_entry *); #define ACPI_PTR(_ptr) (_ptr) static inline void acpi_device_set_enumerated(struct acpi_device *adev) { adev->flags.visited = true; } static inline void acpi_device_clear_enumerated(struct acpi_device *adev) { adev->flags.visited = false; } enum acpi_reconfig_event { ACPI_RECONFIG_DEVICE_ADD = 0, ACPI_RECONFIG_DEVICE_REMOVE, }; int acpi_reconfig_notifier_register(struct notifier_block *nb); int acpi_reconfig_notifier_unregister(struct notifier_block *nb); #ifdef CONFIG_ACPI_GTDT int acpi_gtdt_init(struct acpi_table_header *table, int *platform_timer_count); int acpi_gtdt_map_ppi(int type); bool acpi_gtdt_c3stop(int type); int acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem, int *timer_count); #endif #ifndef ACPI_HAVE_ARCH_SET_ROOT_POINTER static inline void acpi_arch_set_root_pointer(u64 addr) { } #endif #ifndef ACPI_HAVE_ARCH_GET_ROOT_POINTER static inline u64 acpi_arch_get_root_pointer(void) { return 0; } #endif int acpi_get_local_u64_address(acpi_handle handle, u64 *addr); int acpi_get_local_address(acpi_handle handle, u32 *addr); const char *acpi_get_subsystem_id(acpi_handle handle); #else /* !CONFIG_ACPI */ #define acpi_disabled 1 #define ACPI_COMPANION(dev) (NULL) #define ACPI_COMPANION_SET(dev, adev) do { } while (0) #define ACPI_HANDLE(dev) (NULL) #define ACPI_HANDLE_FWNODE(fwnode) (NULL) /* Get rid of the -Wunused-variable for adev */ #define acpi_dev_uid_match(adev, uid2) (adev && false) #define acpi_dev_hid_uid_match(adev, hid2, uid2) (adev && false) struct fwnode_handle; static inline bool acpi_dev_found(const char *hid) { return false; } static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) { return false; } struct acpi_device; static inline int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer) { return -ENODEV; } static inline struct acpi_device * acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) { return NULL; } static inline bool acpi_reduced_hardware(void) { return false; } static inline void acpi_dev_put(struct acpi_device *adev) {} static inline bool is_acpi_node(const struct fwnode_handle *fwnode) { return false; } static inline bool is_acpi_device_node(const struct fwnode_handle *fwnode) { return false; } static inline struct acpi_device *to_acpi_device_node(const struct fwnode_handle *fwnode) { return NULL; } static inline bool is_acpi_data_node(const struct fwnode_handle *fwnode) { return false; } static inline struct acpi_data_node *to_acpi_data_node(const struct fwnode_handle *fwnode) { return NULL; } static inline bool acpi_data_node_match(const struct fwnode_handle *fwnode, const char *name) { return false; } static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev) { return NULL; } static inline acpi_handle acpi_device_handle(struct acpi_device *adev) { return NULL; } static inline bool has_acpi_companion(struct device *dev) { return false; } static inline void acpi_preset_companion(struct device *dev, struct acpi_device *parent, u64 addr) { } static inline const char *acpi_dev_name(struct acpi_device *adev) { return NULL; } static inline struct device *acpi_get_first_physical_node(struct acpi_device *adev) { return NULL; } static inline void acpi_early_init(void) { } static inline void acpi_subsystem_init(void) { } static inline int early_acpi_boot_init(void) { return 0; } static inline int acpi_boot_init(void) { return 0; } static inline void acpi_boot_table_prepare(void) { } static inline void acpi_boot_table_init(void) { } static inline int acpi_mps_check(void) { return 0; } static inline int acpi_check_resource_conflict(struct resource *res) { return 0; } static inline int acpi_check_region(resource_size_t start, resource_size_t n, const char *name) { return 0; } struct acpi_table_header; static inline int acpi_table_parse(char *id, int (*handler)(struct acpi_table_header *)) { return -ENODEV; } static inline int acpi_nvs_register(__u64 start, __u64 size) { return 0; } static inline int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), void *data) { return 0; } struct acpi_device_id; static inline const struct acpi_device_id *acpi_match_acpi_device( const struct acpi_device_id *ids, const struct acpi_device *adev) { return NULL; } static inline const struct acpi_device_id *acpi_match_device( const struct acpi_device_id *ids, const struct device *dev) { return NULL; } static inline const void *acpi_device_get_match_data(const struct device *dev) { return NULL; } static inline bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv) { return false; } static inline bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs) { return false; } static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4) { return NULL; } static inline union acpi_object *acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4, acpi_object_type type) { return NULL; } static inline int acpi_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { return -ENODEV; } static inline int acpi_device_modalias(struct device *dev, char *buf, int size) { return -ENODEV; } static inline struct platform_device * acpi_create_platform_device(struct acpi_device *adev, const struct property_entry *properties) { return NULL; } static inline bool acpi_dma_supported(const struct acpi_device *adev) { return false; } static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) { return DEV_DMA_NOT_SUPPORTED; } static inline int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map) { return -ENODEV; } static inline int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) { return 0; } static inline int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, const u32 *input_id) { return 0; } #define ACPI_PTR(_ptr) (NULL) static inline void acpi_device_set_enumerated(struct acpi_device *adev) { } static inline void acpi_device_clear_enumerated(struct acpi_device *adev) { } static inline int acpi_reconfig_notifier_register(struct notifier_block *nb) { return -EINVAL; } static inline int acpi_reconfig_notifier_unregister(struct notifier_block *nb) { return -EINVAL; } static inline struct acpi_device *acpi_resource_consumer(struct resource *res) { return NULL; } static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) { return -ENODEV; } static inline const char *acpi_get_subsystem_id(acpi_handle handle) { return ERR_PTR(-ENODEV); } static inline int acpi_register_wakeup_handler(int wake_irq, bool (*wakeup)(void *context), void *context) { return -ENXIO; } static inline void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context) { } struct acpi_osc_context; static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) { return 0; } static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) { return 0; } static inline bool acpi_sleep_state_supported(u8 sleep_state) { return false; } static inline acpi_handle acpi_get_processor_handle(int cpu) { return NULL; } #endif /* !CONFIG_ACPI */ extern void arch_post_acpi_subsys_init(void); #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_ioapic_add(acpi_handle root); #else static inline int acpi_ioapic_add(acpi_handle root) { return 0; } #endif #ifdef CONFIG_ACPI void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl)); acpi_status acpi_os_prepare_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control); void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, u32 val_a, u32 val_b)); acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); #if defined(CONFIG_SUSPEND) && defined(CONFIG_X86) struct acpi_s2idle_dev_ops { struct list_head list_node; void (*prepare)(void); void (*check)(void); void (*restore)(void); }; int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg); void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg); int acpi_get_lps0_constraint(struct acpi_device *adev); #else /* CONFIG_SUSPEND && CONFIG_X86 */ static inline int acpi_get_lps0_constraint(struct device *dev) { return ACPI_STATE_UNKNOWN; } #endif /* CONFIG_SUSPEND && CONFIG_X86 */ void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else #define acpi_os_set_prepare_sleep(func, pm1a_ctrl, pm1b_ctrl) do { } while (0) #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM) int acpi_dev_suspend(struct device *dev, bool wakeup); int acpi_dev_resume(struct device *dev); int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); bool acpi_storage_d3(struct device *dev); bool acpi_dev_state_d0(struct device *dev); #else static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) { return 0; } static inline bool acpi_storage_d3(struct device *dev) { return false; } static inline bool acpi_dev_state_d0(struct device *dev) { return true; } #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) int acpi_subsys_prepare(struct device *dev); void acpi_subsys_complete(struct device *dev); int acpi_subsys_suspend_late(struct device *dev); int acpi_subsys_suspend_noirq(struct device *dev); int acpi_subsys_suspend(struct device *dev); int acpi_subsys_freeze(struct device *dev); int acpi_subsys_poweroff(struct device *dev); int acpi_subsys_restore_early(struct device *dev); #else static inline int acpi_subsys_prepare(struct device *dev) { return 0; } static inline void acpi_subsys_complete(struct device *dev) {} static inline int acpi_subsys_suspend_late(struct device *dev) { return 0; } static inline int acpi_subsys_suspend_noirq(struct device *dev) { return 0; } static inline int acpi_subsys_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_freeze(struct device *dev) { return 0; } static inline int acpi_subsys_poweroff(struct device *dev) { return 0; } static inline int acpi_subsys_restore_early(struct device *dev) { return 0; } #endif #if defined(CONFIG_ACPI_EC) && defined(CONFIG_PM_SLEEP) void acpi_ec_mark_gpe_for_wake(void); void acpi_ec_set_gpe_wake_mask(u8 action); #else static inline void acpi_ec_mark_gpe_for_wake(void) {} static inline void acpi_ec_set_gpe_wake_mask(u8 action) {} #endif #ifdef CONFIG_ACPI char *acpi_handle_path(acpi_handle handle); __printf(3, 4) void acpi_handle_printk(const char *level, acpi_handle handle, const char *fmt, ...); void acpi_evaluation_failure_warn(acpi_handle handle, const char *name, acpi_status status); #else /* !CONFIG_ACPI */ static inline __printf(3, 4) void acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {} static inline void acpi_evaluation_failure_warn(acpi_handle handle, const char *name, acpi_status status) {} #endif /* !CONFIG_ACPI */ #if defined(CONFIG_ACPI) && defined(CONFIG_DYNAMIC_DEBUG) __printf(3, 4) void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const char *fmt, ...); #endif /* * acpi_handle_<level>: Print message with ACPI prefix and object path * * These interfaces acquire the global namespace mutex to obtain an object * path. In interrupt context, it shows the object path as <n/a>. */ #define acpi_handle_emerg(handle, fmt, ...) \ acpi_handle_printk(KERN_EMERG, handle, fmt, ##__VA_ARGS__) #define acpi_handle_alert(handle, fmt, ...) \ acpi_handle_printk(KERN_ALERT, handle, fmt, ##__VA_ARGS__) #define acpi_handle_crit(handle, fmt, ...) \ acpi_handle_printk(KERN_CRIT, handle, fmt, ##__VA_ARGS__) #define acpi_handle_err(handle, fmt, ...) \ acpi_handle_printk(KERN_ERR, handle, fmt, ##__VA_ARGS__) #define acpi_handle_warn(handle, fmt, ...) \ acpi_handle_printk(KERN_WARNING, handle, fmt, ##__VA_ARGS__) #define acpi_handle_notice(handle, fmt, ...) \ acpi_handle_printk(KERN_NOTICE, handle, fmt, ##__VA_ARGS__) #define acpi_handle_info(handle, fmt, ...) \ acpi_handle_printk(KERN_INFO, handle, fmt, ##__VA_ARGS__) #if defined(DEBUG) #define acpi_handle_debug(handle, fmt, ...) \ acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__) #else #if defined(CONFIG_DYNAMIC_DEBUG) #define acpi_handle_debug(handle, fmt, ...) \ _dynamic_func_call(fmt, __acpi_handle_debug, \ handle, pr_fmt(fmt), ##__VA_ARGS__) #else #define acpi_handle_debug(handle, fmt, ...) \ ({ \ if (0) \ acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__); \ 0; \ }) #endif #endif #if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB) bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) { return false; } static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) { return false; } static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable) { return -ENXIO; } #endif static inline int acpi_dev_gpio_irq_wake_get(struct acpi_device *adev, int index, bool *wake_capable) { return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, wake_capable); } static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *con_id, int index) { return acpi_dev_gpio_irq_wake_get_by(adev, con_id, index, NULL); } static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, NULL); } /* Device properties */ #ifdef CONFIG_ACPI int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj); int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct fwnode_reference_args *args); static inline int acpi_node_get_property_reference( const struct fwnode_handle *fwnode, const char *name, size_t index, struct fwnode_reference_args *args) { return __acpi_node_get_property_reference(fwnode, name, index, NR_FWNODE_REFERENCE_ARGS, args); } static inline bool acpi_dev_has_props(const struct acpi_device *adev) { return !list_empty(&adev->data.properties); } struct acpi_device_properties * acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, union acpi_object *properties); int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, struct acpi_probe_entry *); #define ACPI_TABLE_ID_LEN 5 /** * struct acpi_probe_entry - boot-time probing entry * @id: ACPI table name * @type: Optional subtable type to match * (if @id contains subtables) * @subtable_valid: Optional callback to check the validity of * the subtable * @probe_table: Callback to the driver being probed when table * match is successful * @probe_subtbl: Callback to the driver being probed when table and * subtable match (and optional callback is successful) * @driver_data: Sideband data provided back to the driver */ struct acpi_probe_entry { __u8 id[ACPI_TABLE_ID_LEN]; __u8 type; acpi_probe_entry_validate_subtbl subtable_valid; union { acpi_tbl_table_handler probe_table; acpi_tbl_entry_handler probe_subtbl; }; kernel_ulong_t driver_data; }; void arch_sort_irqchip_probe(struct acpi_probe_entry *ap_head, int nr); #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, \ valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ .probe_table = fn, \ .driver_data = data, \ } #define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id, \ subtable, valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ .probe_subtbl = fn, \ .driver_data = data, \ } #define ACPI_PROBE_TABLE(name) __##name##_acpi_probe_table #define ACPI_PROBE_TABLE_END(name) __##name##_acpi_probe_table_end int __acpi_probe_device_table(struct acpi_probe_entry *start, int nr); #define acpi_probe_device_table(t) \ ({ \ extern struct acpi_probe_entry ACPI_PROBE_TABLE(t), \ ACPI_PROBE_TABLE_END(t); \ __acpi_probe_device_table(&ACPI_PROBE_TABLE(t), \ (&ACPI_PROBE_TABLE_END(t) - \ &ACPI_PROBE_TABLE(t))); \ }) #else static inline int acpi_dev_get_property(struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj) { return -ENXIO; } static inline int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct fwnode_reference_args *args) { return -ENXIO; } static inline int acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, struct fwnode_reference_args *args) { return -ENXIO; } static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr) { return -ENXIO; } static inline struct fwnode_handle * acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { return NULL; } static inline struct fwnode_handle * acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { return ERR_PTR(-ENXIO); } static inline int acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle **remote, struct fwnode_handle **port, struct fwnode_handle **endpoint) { return -ENXIO; } #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \ static const void * __acpi_table_##name[] \ __attribute__((unused)) \ = { (void *) table_id, \ (void *) subtable, \ (void *) valid, \ (void *) fn, \ (void *) data } #define acpi_probe_device_table(t) ({ int __r = 0; __r;}) #endif #ifdef CONFIG_ACPI_TABLE_UPGRADE void acpi_table_upgrade(void); #else static inline void acpi_table_upgrade(void) { } #endif #if defined(CONFIG_ACPI) && defined(CONFIG_ACPI_WATCHDOG) extern bool acpi_has_watchdog(void); #else static inline bool acpi_has_watchdog(void) { return false; } #endif #ifdef CONFIG_ACPI_SPCR_TABLE extern bool qdf2400_e44_present; int acpi_parse_spcr(bool enable_earlycon, bool enable_console); #else static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console) { return 0; } #endif #if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI) int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res); #else static inline int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res) { return -EINVAL; } #endif #ifdef CONFIG_ACPI_LPIT int lpit_read_residency_count_address(u64 *address); #else static inline int lpit_read_residency_count_address(u64 *address) { return -EINVAL; } #endif #ifdef CONFIG_ACPI_PROCESSOR_IDLE #ifndef arch_get_idle_state_flags static inline unsigned int arch_get_idle_state_flags(u32 arch_flags) { return 0; } #endif #endif /* CONFIG_ACPI_PROCESSOR_IDLE */ #ifdef CONFIG_ACPI_PPTT int acpi_pptt_cpu_is_thread(unsigned int cpu); int find_acpi_cpu_topology(unsigned int cpu, int level); int find_acpi_cpu_topology_cluster(unsigned int cpu); int find_acpi_cpu_topology_package(unsigned int cpu); int find_acpi_cpu_topology_hetero_id(unsigned int cpu); #else static inline int acpi_pptt_cpu_is_thread(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology(unsigned int cpu, int level) { return -EINVAL; } static inline int find_acpi_cpu_topology_cluster(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology_package(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu) { return -EINVAL; } #endif void acpi_arch_init(void); #ifdef CONFIG_ACPI_PCC void acpi_init_pcc(void); #else static inline void acpi_init_pcc(void) { } #endif #ifdef CONFIG_ACPI_FFH void acpi_init_ffh(void); extern int acpi_ffh_address_space_arch_setup(void *handler_ctxt, void **region_ctxt); extern int acpi_ffh_address_space_arch_handler(acpi_integer *value, void *region_context); #else static inline void acpi_init_ffh(void) { } #endif #ifdef CONFIG_ACPI extern void acpi_device_notify(struct device *dev); extern void acpi_device_notify_remove(struct device *dev); #else static inline void acpi_device_notify(struct device *dev) { } static inline void acpi_device_notify_remove(struct device *dev) { } #endif static inline void acpi_use_parent_companion(struct device *dev) { ACPI_COMPANION_SET(dev, ACPI_COMPANION(dev->parent)); } #ifdef CONFIG_ACPI_HMAT int hmat_update_target_coordinates(int nid, struct access_coordinate *coord, enum access_coordinate_class access); #else static inline int hmat_update_target_coordinates(int nid, struct access_coordinate *coord, enum access_coordinate_class access) { return -EOPNOTSUPP; } #endif #ifdef CONFIG_ACPI_NUMA bool acpi_node_backed_by_real_pxm(int nid); #else static inline bool acpi_node_backed_by_real_pxm(int nid) { return false; } #endif #endif /*_LINUX_ACPI_H*/ |
| 2 5 445 2 2 2 2 1 1 1 1 441 355 441 442 442 441 442 442 440 336 354 346 48 199 155 5 5 445 445 2 444 443 440 21 445 355 356 10 357 5 354 354 10 444 445 445 | 1 2 3 4 5 6 7 8 9 10 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2007 Oracle. All rights reserved. * Copyright (C) 2022 Christoph Hellwig. */ #include <linux/bio.h> #include "bio.h" #include "ctree.h" #include "volumes.h" #include "raid56.h" #include "async-thread.h" #include "dev-replace.h" #include "zoned.h" #include "file-item.h" #include "raid-stripe-tree.h" static struct bio_set btrfs_bioset; static struct bio_set btrfs_clone_bioset; static struct bio_set btrfs_repair_bioset; static mempool_t btrfs_failed_bio_pool; struct btrfs_failed_bio { struct btrfs_bio *bbio; int num_copies; atomic_t repair_count; }; /* Is this a data path I/O that needs storage layer checksum and repair? */ static inline bool is_data_bbio(struct btrfs_bio *bbio) { return bbio->inode && is_data_inode(bbio->inode); } static bool bbio_has_ordered_extent(struct btrfs_bio *bbio) { return is_data_bbio(bbio) && btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE; } /* * Initialize a btrfs_bio structure. This skips the embedded bio itself as it * is already initialized by the block layer. */ void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info, btrfs_bio_end_io_t end_io, void *private) { memset(bbio, 0, offsetof(struct btrfs_bio, bio)); bbio->fs_info = fs_info; bbio->end_io = end_io; bbio->private = private; atomic_set(&bbio->pending_ios, 1); WRITE_ONCE(bbio->status, BLK_STS_OK); } /* * Allocate a btrfs_bio structure. The btrfs_bio is the main I/O container for * btrfs, and is used for all I/O submitted through btrfs_submit_bbio(). * * Just like the underlying bio_alloc_bioset it will not fail as it is backed by * a mempool. */ struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf, struct btrfs_fs_info *fs_info, btrfs_bio_end_io_t end_io, void *private) { struct btrfs_bio *bbio; struct bio *bio; bio = bio_alloc_bioset(NULL, nr_vecs, opf, GFP_NOFS, &btrfs_bioset); bbio = btrfs_bio(bio); btrfs_bio_init(bbio, fs_info, end_io, private); return bbio; } static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info, struct btrfs_bio *orig_bbio, u64 map_length) { struct btrfs_bio *bbio; struct bio *bio; bio = bio_split(&orig_bbio->bio, map_length >> SECTOR_SHIFT, GFP_NOFS, &btrfs_clone_bioset); if (IS_ERR(bio)) return ERR_CAST(bio); bbio = btrfs_bio(bio); btrfs_bio_init(bbio, fs_info, NULL, orig_bbio); bbio->inode = orig_bbio->inode; bbio->file_offset = orig_bbio->file_offset; orig_bbio->file_offset += map_length; if (bbio_has_ordered_extent(bbio)) { refcount_inc(&orig_bbio->ordered->refs); bbio->ordered = orig_bbio->ordered; } atomic_inc(&orig_bbio->pending_ios); return bbio; } void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status) { bbio->bio.bi_status = status; if (bbio->bio.bi_pool == &btrfs_clone_bioset) { struct btrfs_bio *orig_bbio = bbio->private; /* Free bio that was never submitted to the underlying device. */ if (bbio_has_ordered_extent(bbio)) btrfs_put_ordered_extent(bbio->ordered); bio_put(&bbio->bio); bbio = orig_bbio; } /* * At this point, bbio always points to the original btrfs_bio. Save * the first error in it. */ if (status != BLK_STS_OK) cmpxchg(&bbio->status, BLK_STS_OK, status); if (atomic_dec_and_test(&bbio->pending_ios)) { /* Load split bio's error which might be set above. */ if (status == BLK_STS_OK) bbio->bio.bi_status = READ_ONCE(bbio->status); if (bbio_has_ordered_extent(bbio)) { struct btrfs_ordered_extent *ordered = bbio->ordered; bbio->end_io(bbio); btrfs_put_ordered_extent(ordered); } else { bbio->end_io(bbio); } } } static int next_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror) { if (cur_mirror == fbio->num_copies) return cur_mirror + 1 - fbio->num_copies; return cur_mirror + 1; } static int prev_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror) { if (cur_mirror == 1) return fbio->num_copies; return cur_mirror - 1; } static void btrfs_repair_done(struct btrfs_failed_bio *fbio) { if (atomic_dec_and_test(&fbio->repair_count)) { btrfs_bio_end_io(fbio->bbio, fbio->bbio->bio.bi_status); mempool_free(fbio, &btrfs_failed_bio_pool); } } static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio, struct btrfs_device *dev) { struct btrfs_failed_bio *fbio = repair_bbio->private; struct btrfs_inode *inode = repair_bbio->inode; struct btrfs_fs_info *fs_info = inode->root->fs_info; struct bio_vec *bv = bio_first_bvec_all(&repair_bbio->bio); int mirror = repair_bbio->mirror_num; /* * We can only trigger this for data bio, which doesn't support larger * folios yet. */ ASSERT(folio_order(page_folio(bv->bv_page)) == 0); if (repair_bbio->bio.bi_status || !btrfs_data_csum_ok(repair_bbio, dev, 0, bv)) { bio_reset(&repair_bbio->bio, NULL, REQ_OP_READ); repair_bbio->bio.bi_iter = repair_bbio->saved_iter; mirror = next_repair_mirror(fbio, mirror); if (mirror == fbio->bbio->mirror_num) { btrfs_debug(fs_info, "no mirror left"); fbio->bbio->bio.bi_status = BLK_STS_IOERR; goto done; } btrfs_submit_bbio(repair_bbio, mirror); return; } do { mirror = prev_repair_mirror(fbio, mirror); btrfs_repair_io_failure(fs_info, btrfs_ino(inode), repair_bbio->file_offset, fs_info->sectorsize, repair_bbio->saved_iter.bi_sector << SECTOR_SHIFT, page_folio(bv->bv_page), bv->bv_offset, mirror); } while (mirror != fbio->bbio->mirror_num); done: btrfs_repair_done(fbio); bio_put(&repair_bbio->bio); } /* * Try to kick off a repair read to the next available mirror for a bad sector. * * This primarily tries to recover good data to serve the actual read request, * but also tries to write the good data back to the bad mirror(s) when a * read succeeded to restore the redundancy. */ static struct btrfs_failed_bio *repair_one_sector(struct btrfs_bio *failed_bbio, u32 bio_offset, struct bio_vec *bv, struct btrfs_failed_bio *fbio) { struct btrfs_inode *inode = failed_bbio->inode; struct btrfs_fs_info *fs_info = inode->root->fs_info; const u32 sectorsize = fs_info->sectorsize; const u64 logical = (failed_bbio->saved_iter.bi_sector << SECTOR_SHIFT); struct btrfs_bio *repair_bbio; struct bio *repair_bio; int num_copies; int mirror; btrfs_debug(fs_info, "repair read error: read error at %llu", failed_bbio->file_offset + bio_offset); num_copies = btrfs_num_copies(fs_info, logical, sectorsize); if (num_copies == 1) { btrfs_debug(fs_info, "no copy to repair from"); failed_bbio->bio.bi_status = BLK_STS_IOERR; return fbio; } if (!fbio) { fbio = mempool_alloc(&btrfs_failed_bio_pool, GFP_NOFS); fbio->bbio = failed_bbio; fbio->num_copies = num_copies; atomic_set(&fbio->repair_count, 1); } atomic_inc(&fbio->repair_count); repair_bio = bio_alloc_bioset(NULL, 1, REQ_OP_READ, GFP_NOFS, &btrfs_repair_bioset); repair_bio->bi_iter.bi_sector = failed_bbio->saved_iter.bi_sector; __bio_add_page(repair_bio, bv->bv_page, bv->bv_len, bv->bv_offset); repair_bbio = btrfs_bio(repair_bio); btrfs_bio_init(repair_bbio, fs_info, NULL, fbio); repair_bbio->inode = failed_bbio->inode; repair_bbio->file_offset = failed_bbio->file_offset + bio_offset; mirror = next_repair_mirror(fbio, failed_bbio->mirror_num); btrfs_debug(fs_info, "submitting repair read to mirror %d", mirror); btrfs_submit_bbio(repair_bbio, mirror); return fbio; } static void btrfs_check_read_bio(struct btrfs_bio *bbio, struct btrfs_device *dev) { struct btrfs_inode *inode = bbio->inode; struct btrfs_fs_info *fs_info = inode->root->fs_info; u32 sectorsize = fs_info->sectorsize; struct bvec_iter *iter = &bbio->saved_iter; blk_status_t status = bbio->bio.bi_status; struct btrfs_failed_bio *fbio = NULL; u32 offset = 0; /* Read-repair requires the inode field to be set by the submitter. */ ASSERT(inode); /* * Hand off repair bios to the repair code as there is no upper level * submitter for them. */ if (bbio->bio.bi_pool == &btrfs_repair_bioset) { btrfs_end_repair_bio(bbio, dev); return; } /* Clear the I/O error. A failed repair will reset it. */ bbio->bio.bi_status = BLK_STS_OK; while (iter->bi_size) { struct bio_vec bv = bio_iter_iovec(&bbio->bio, *iter); bv.bv_len = min(bv.bv_len, sectorsize); if (status || !btrfs_data_csum_ok(bbio, dev, offset, &bv)) fbio = repair_one_sector(bbio, offset, &bv, fbio); bio_advance_iter_single(&bbio->bio, iter, sectorsize); offset += sectorsize; } if (bbio->csum != bbio->csum_inline) kfree(bbio->csum); if (fbio) btrfs_repair_done(fbio); else btrfs_bio_end_io(bbio, bbio->bio.bi_status); } static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev) { if (!dev || !dev->bdev) return; if (bio->bi_status != BLK_STS_IOERR && bio->bi_status != BLK_STS_TARGET) return; if (btrfs_op(bio) == BTRFS_MAP_WRITE) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); else if (!(bio->bi_opf & REQ_RAHEAD)) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_READ_ERRS); if (bio->bi_opf & REQ_PREFLUSH) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_FLUSH_ERRS); } static struct workqueue_struct *btrfs_end_io_wq(struct btrfs_fs_info *fs_info, struct bio *bio) { if (bio->bi_opf & REQ_META) return fs_info->endio_meta_workers; return fs_info->endio_workers; } static void btrfs_end_bio_work(struct work_struct *work) { struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, end_io_work); /* Metadata reads are checked and repaired by the submitter. */ if (is_data_bbio(bbio)) btrfs_check_read_bio(bbio, bbio->bio.bi_private); else btrfs_bio_end_io(bbio, bbio->bio.bi_status); } static void btrfs_simple_end_io(struct bio *bio) { struct btrfs_bio *bbio = btrfs_bio(bio); struct btrfs_device *dev = bio->bi_private; struct btrfs_fs_info *fs_info = bbio->fs_info; btrfs_bio_counter_dec(fs_info); if (bio->bi_status) btrfs_log_dev_io_error(bio, dev); if (bio_op(bio) == REQ_OP_READ) { INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work); queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); } else { if (bio_is_zone_append(bio) && !bio->bi_status) btrfs_record_physical_zoned(bbio); btrfs_bio_end_io(bbio, bbio->bio.bi_status); } } static void btrfs_raid56_end_io(struct bio *bio) { struct btrfs_io_context *bioc = bio->bi_private; struct btrfs_bio *bbio = btrfs_bio(bio); btrfs_bio_counter_dec(bioc->fs_info); bbio->mirror_num = bioc->mirror_num; if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio)) btrfs_check_read_bio(bbio, NULL); else btrfs_bio_end_io(bbio, bbio->bio.bi_status); btrfs_put_bioc(bioc); } static void btrfs_orig_write_end_io(struct bio *bio) { struct btrfs_io_stripe *stripe = bio->bi_private; struct btrfs_io_context *bioc = stripe->bioc; struct btrfs_bio *bbio = btrfs_bio(bio); btrfs_bio_counter_dec(bioc->fs_info); if (bio->bi_status) { atomic_inc(&bioc->error); btrfs_log_dev_io_error(bio, stripe->dev); } /* * Only send an error to the higher layers if it is beyond the tolerance * threshold. */ if (atomic_read(&bioc->error) > bioc->max_errors) bio->bi_status = BLK_STS_IOERR; else bio->bi_status = BLK_STS_OK; if (bio_is_zone_append(bio) && !bio->bi_status) stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; btrfs_bio_end_io(bbio, bbio->bio.bi_status); btrfs_put_bioc(bioc); } static void btrfs_clone_write_end_io(struct bio *bio) { struct btrfs_io_stripe *stripe = bio->bi_private; if (bio->bi_status) { atomic_inc(&stripe->bioc->error); btrfs_log_dev_io_error(bio, stripe->dev); } else if (bio_is_zone_append(bio)) { stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; } /* Pass on control to the original bio this one was cloned from */ bio_endio(stripe->bioc->orig_bio); bio_put(bio); } static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio) { if (!dev || !dev->bdev || test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) || (btrfs_op(bio) == BTRFS_MAP_WRITE && !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))) { bio_io_error(bio); return; } bio_set_dev(bio, dev->bdev); /* * For zone append writing, bi_sector must point the beginning of the * zone */ if (bio_op(bio) == REQ_OP_ZONE_APPEND) { u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; u64 zone_start = round_down(physical, dev->fs_info->zone_size); ASSERT(btrfs_dev_is_sequential(dev, physical)); bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT; } btrfs_debug_in_rcu(dev->fs_info, "%s: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u", __func__, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector, (unsigned long)dev->bdev->bd_dev, btrfs_dev_name(dev), dev->devid, bio->bi_iter.bi_size); /* * Track reads if tracking is enabled; ignore I/O operations before the * filesystem is fully initialized. */ if (dev->fs_devices->collect_fs_stats && bio_op(bio) == REQ_OP_READ && dev->fs_info) percpu_counter_add(&dev->fs_info->stats_read_blocks, bio->bi_iter.bi_size >> dev->fs_info->sectorsize_bits); if (bio->bi_opf & REQ_BTRFS_CGROUP_PUNT) blkcg_punt_bio_submit(bio); else submit_bio(bio); } static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr) { struct bio *orig_bio = bioc->orig_bio, *bio; ASSERT(bio_op(orig_bio) != REQ_OP_READ); /* Reuse the bio embedded into the btrfs_bio for the last mirror */ if (dev_nr == bioc->num_stripes - 1) { bio = orig_bio; bio->bi_end_io = btrfs_orig_write_end_io; } else { bio = bio_alloc_clone(NULL, orig_bio, GFP_NOFS, &fs_bio_set); bio_inc_remaining(orig_bio); bio->bi_end_io = btrfs_clone_write_end_io; } bio->bi_private = &bioc->stripes[dev_nr]; bio->bi_iter.bi_sector = bioc->stripes[dev_nr].physical >> SECTOR_SHIFT; bioc->stripes[dev_nr].bioc = bioc; bioc->size = bio->bi_iter.bi_size; btrfs_submit_dev_bio(bioc->stripes[dev_nr].dev, bio); } static void btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc, struct btrfs_io_stripe *smap, int mirror_num) { if (!bioc) { /* Single mirror read/write fast path. */ btrfs_bio(bio)->mirror_num = mirror_num; bio->bi_iter.bi_sector = smap->physical >> SECTOR_SHIFT; if (bio_op(bio) != REQ_OP_READ) btrfs_bio(bio)->orig_physical = smap->physical; bio->bi_private = smap->dev; bio->bi_end_io = btrfs_simple_end_io; btrfs_submit_dev_bio(smap->dev, bio); } else if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) { /* Parity RAID write or read recovery. */ bio->bi_private = bioc; bio->bi_end_io = btrfs_raid56_end_io; if (bio_op(bio) == REQ_OP_READ) raid56_parity_recover(bio, bioc, mirror_num); else raid56_parity_write(bio, bioc); } else { /* Write to multiple mirrors. */ int total_devs = bioc->num_stripes; bioc->orig_bio = bio; for (int dev_nr = 0; dev_nr < total_devs; dev_nr++) btrfs_submit_mirrored_bio(bioc, dev_nr); } } static blk_status_t btrfs_bio_csum(struct btrfs_bio *bbio) { if (bbio->bio.bi_opf & REQ_META) return btree_csum_one_bio(bbio); return btrfs_csum_one_bio(bbio); } /* * Async submit bios are used to offload expensive checksumming onto the worker * threads. */ struct async_submit_bio { struct btrfs_bio *bbio; struct btrfs_io_context *bioc; struct btrfs_io_stripe smap; int mirror_num; struct btrfs_work work; }; /* * In order to insert checksums into the metadata in large chunks, we wait * until bio submission time. All the pages in the bio are checksummed and * sums are attached onto the ordered extent record. * * At IO completion time the csums attached on the ordered extent record are * inserted into the btree. */ static void run_one_async_start(struct btrfs_work *work) { struct async_submit_bio *async = container_of(work, struct async_submit_bio, work); blk_status_t ret; ret = btrfs_bio_csum(async->bbio); if (ret) async->bbio->bio.bi_status = ret; } /* * In order to insert checksums into the metadata in large chunks, we wait * until bio submission time. All the pages in the bio are checksummed and * sums are attached onto the ordered extent record. * * At IO completion time the csums attached on the ordered extent record are * inserted into the tree. * * If called with @do_free == true, then it will free the work struct. */ static void run_one_async_done(struct btrfs_work *work, bool do_free) { struct async_submit_bio *async = container_of(work, struct async_submit_bio, work); struct bio *bio = &async->bbio->bio; if (do_free) { kfree(container_of(work, struct async_submit_bio, work)); return; } /* If an error occurred we just want to clean up the bio and move on. */ if (bio->bi_status) { btrfs_bio_end_io(async->bbio, bio->bi_status); return; } /* * All of the bios that pass through here are from async helpers. * Use REQ_BTRFS_CGROUP_PUNT to issue them from the owning cgroup's * context. This changes nothing when cgroups aren't in use. */ bio->bi_opf |= REQ_BTRFS_CGROUP_PUNT; btrfs_submit_bio(bio, async->bioc, &async->smap, async->mirror_num); } static bool should_async_write(struct btrfs_bio *bbio) { bool auto_csum_mode = true; #ifdef CONFIG_BTRFS_EXPERIMENTAL struct btrfs_fs_devices *fs_devices = bbio->fs_info->fs_devices; enum btrfs_offload_csum_mode csum_mode = READ_ONCE(fs_devices->offload_csum_mode); if (csum_mode == BTRFS_OFFLOAD_CSUM_FORCE_OFF) return false; auto_csum_mode = (csum_mode == BTRFS_OFFLOAD_CSUM_AUTO); #endif /* Submit synchronously if the checksum implementation is fast. */ if (auto_csum_mode && test_bit(BTRFS_FS_CSUM_IMPL_FAST, &bbio->fs_info->flags)) return false; /* * Try to defer the submission to a workqueue to parallelize the * checksum calculation unless the I/O is issued synchronously. */ if (op_is_sync(bbio->bio.bi_opf)) return false; /* Zoned devices require I/O to be submitted in order. */ if ((bbio->bio.bi_opf & REQ_META) && btrfs_is_zoned(bbio->fs_info)) return false; return true; } /* * Submit bio to an async queue. * * Return true if the work has been successfully submitted, else false. */ static bool btrfs_wq_submit_bio(struct btrfs_bio *bbio, struct btrfs_io_context *bioc, struct btrfs_io_stripe *smap, int mirror_num) { struct btrfs_fs_info *fs_info = bbio->fs_info; struct async_submit_bio *async; async = kmalloc(sizeof(*async), GFP_NOFS); if (!async) return false; async->bbio = bbio; async->bioc = bioc; async->smap = *smap; async->mirror_num = mirror_num; btrfs_init_work(&async->work, run_one_async_start, run_one_async_done); btrfs_queue_work(fs_info->workers, &async->work); return true; } static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) { unsigned int nr_segs; int sector_offset; map_length = min(map_length, bbio->fs_info->max_zone_append_size); sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, &nr_segs, map_length); if (sector_offset) { /* * bio_split_rw_at() could split at a size smaller than our * sectorsize and thus cause unaligned I/Os. Fix that by * always rounding down to the nearest boundary. */ return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize); } return map_length; } static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) { struct btrfs_inode *inode = bbio->inode; struct btrfs_fs_info *fs_info = bbio->fs_info; struct bio *bio = &bbio->bio; u64 logical = bio->bi_iter.bi_sector << SECTOR_SHIFT; u64 length = bio->bi_iter.bi_size; u64 map_length = length; bool use_append = btrfs_use_zone_append(bbio); struct btrfs_io_context *bioc = NULL; struct btrfs_io_stripe smap; blk_status_t ret; int error; if (!bbio->inode || btrfs_is_data_reloc_root(inode->root)) smap.rst_search_commit_root = true; else smap.rst_search_commit_root = false; btrfs_bio_counter_inc_blocked(fs_info); error = btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length, &bioc, &smap, &mirror_num); if (error) { ret = errno_to_blk_status(error); btrfs_bio_counter_dec(fs_info); goto end_bbio; } map_length = min(map_length, length); if (use_append) map_length = btrfs_append_map_length(bbio, map_length); if (map_length < length) { struct btrfs_bio *split; split = btrfs_split_bio(fs_info, bbio, map_length); if (IS_ERR(split)) { ret = errno_to_blk_status(PTR_ERR(split)); btrfs_bio_counter_dec(fs_info); goto end_bbio; } bbio = split; bio = &bbio->bio; } /* * Save the iter for the end_io handler and preload the checksums for * data reads. */ if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio)) { bbio->saved_iter = bio->bi_iter; ret = btrfs_lookup_bio_sums(bbio); if (ret) goto fail; } if (btrfs_op(bio) == BTRFS_MAP_WRITE) { if (use_append) { bio->bi_opf &= ~REQ_OP_WRITE; bio->bi_opf |= REQ_OP_ZONE_APPEND; } if (is_data_bbio(bbio) && bioc && bioc->use_rst) { /* * No locking for the list update, as we only add to * the list in the I/O submission path, and list * iteration only happens in the completion path, which * can't happen until after the last submission. */ btrfs_get_bioc(bioc); list_add_tail(&bioc->rst_ordered_entry, &bbio->ordered->bioc_list); } /* * Csum items for reloc roots have already been cloned at this * point, so they are handled as part of the no-checksum case. */ if (inode && !(inode->flags & BTRFS_INODE_NODATASUM) && !test_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state) && !btrfs_is_data_reloc_root(inode->root)) { if (should_async_write(bbio) && btrfs_wq_submit_bio(bbio, bioc, &smap, mirror_num)) goto done; ret = btrfs_bio_csum(bbio); if (ret) goto fail; } else if (use_append || (btrfs_is_zoned(fs_info) && inode && inode->flags & BTRFS_INODE_NODATASUM)) { ret = btrfs_alloc_dummy_sum(bbio); if (ret) goto fail; } } btrfs_submit_bio(bio, bioc, &smap, mirror_num); done: return map_length == length; fail: btrfs_bio_counter_dec(fs_info); /* * We have split the original bbio, now we have to end both the current * @bbio and remaining one, as the remaining one will never be submitted. */ if (map_length < length) { struct btrfs_bio *remaining = bbio->private; ASSERT(bbio->bio.bi_pool == &btrfs_clone_bioset); ASSERT(remaining); btrfs_bio_end_io(remaining, ret); } end_bbio: btrfs_bio_end_io(bbio, ret); /* Do not submit another chunk */ return true; } void btrfs_submit_bbio(struct btrfs_bio *bbio, int mirror_num) { /* If bbio->inode is not populated, its file_offset must be 0. */ ASSERT(bbio->inode || bbio->file_offset == 0); while (!btrfs_submit_chunk(bbio, mirror_num)) ; } /* * Submit a repair write. * * This bypasses btrfs_submit_bbio() deliberately, as that writes all copies in a * RAID setup. Here we only want to write the one bad copy, so we do the * mapping ourselves and submit the bio directly. * * The I/O is issued synchronously to block the repair read completion from * freeing the bio. */ int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, u64 length, u64 logical, struct folio *folio, unsigned int folio_offset, int mirror_num) { struct btrfs_io_stripe smap = { 0 }; struct bio_vec bvec; struct bio bio; int ret = 0; ASSERT(!(fs_info->sb->s_flags & SB_RDONLY)); BUG_ON(!mirror_num); if (btrfs_repair_one_zone(fs_info, logical)) return 0; /* * Avoid races with device replace and make sure our bioc has devices * associated to its stripes that don't go away while we are doing the * read repair operation. */ btrfs_bio_counter_inc_blocked(fs_info); ret = btrfs_map_repair_block(fs_info, &smap, logical, length, mirror_num); if (ret < 0) goto out_counter_dec; if (!smap.dev->bdev || !test_bit(BTRFS_DEV_STATE_WRITEABLE, &smap.dev->dev_state)) { ret = -EIO; goto out_counter_dec; } bio_init(&bio, smap.dev->bdev, &bvec, 1, REQ_OP_WRITE | REQ_SYNC); bio.bi_iter.bi_sector = smap.physical >> SECTOR_SHIFT; ret = bio_add_folio(&bio, folio, length, folio_offset); ASSERT(ret); ret = submit_bio_wait(&bio); if (ret) { /* try to remap that extent elsewhere? */ btrfs_dev_stat_inc_and_print(smap.dev, BTRFS_DEV_STAT_WRITE_ERRS); goto out_bio_uninit; } btrfs_info_rl_in_rcu(fs_info, "read error corrected: ino %llu off %llu (dev %s sector %llu)", ino, start, btrfs_dev_name(smap.dev), smap.physical >> SECTOR_SHIFT); ret = 0; out_bio_uninit: bio_uninit(&bio); out_counter_dec: btrfs_bio_counter_dec(fs_info); return ret; } /* * Submit a btrfs_bio based repair write. * * If @dev_replace is true, the write would be submitted to dev-replace target. */ void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_replace) { struct btrfs_fs_info *fs_info = bbio->fs_info; u64 logical = bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT; u64 length = bbio->bio.bi_iter.bi_size; struct btrfs_io_stripe smap = { 0 }; int ret; ASSERT(fs_info); ASSERT(mirror_num > 0); ASSERT(btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE); ASSERT(!bbio->inode); btrfs_bio_counter_inc_blocked(fs_info); ret = btrfs_map_repair_block(fs_info, &smap, logical, length, mirror_num); if (ret < 0) goto fail; if (dev_replace) { ASSERT(smap.dev == fs_info->dev_replace.srcdev); smap.dev = fs_info->dev_replace.tgtdev; } btrfs_submit_bio(&bbio->bio, NULL, &smap, mirror_num); return; fail: btrfs_bio_counter_dec(fs_info); btrfs_bio_end_io(bbio, errno_to_blk_status(ret)); } int __init btrfs_bioset_init(void) { if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE, offsetof(struct btrfs_bio, bio), BIOSET_NEED_BVECS)) return -ENOMEM; if (bioset_init(&btrfs_clone_bioset, BIO_POOL_SIZE, offsetof(struct btrfs_bio, bio), 0)) goto out_free_bioset; if (bioset_init(&btrfs_repair_bioset, BIO_POOL_SIZE, offsetof(struct btrfs_bio, bio), BIOSET_NEED_BVECS)) goto out_free_clone_bioset; if (mempool_init_kmalloc_pool(&btrfs_failed_bio_pool, BIO_POOL_SIZE, sizeof(struct btrfs_failed_bio))) goto out_free_repair_bioset; return 0; out_free_repair_bioset: bioset_exit(&btrfs_repair_bioset); out_free_clone_bioset: bioset_exit(&btrfs_clone_bioset); out_free_bioset: bioset_exit(&btrfs_bioset); return -ENOMEM; } void __cold btrfs_bioset_exit(void) { mempool_exit(&btrfs_failed_bio_pool); bioset_exit(&btrfs_repair_bioset); bioset_exit(&btrfs_clone_bioset); bioset_exit(&btrfs_bioset); } |
| 11 16 2 124 123 | 1 2 3 4 5 6 7 8 9 10 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* delayacct.h - per-task delay accounting * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 */ #ifndef _LINUX_DELAYACCT_H #define _LINUX_DELAYACCT_H #include <uapi/linux/taskstats.h> #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { raw_spinlock_t lock; /* For each stat XXX, add following, aligned appropriately * * struct timespec XXX_start, XXX_end; * u64 XXX_delay; * u32 XXX_count; * * Atomicity of updates to XXX_delay, XXX_count protected by * single lock above (split into XXX_lock if contention is an issue). */ /* * XXX_count is incremented on every XXX operation, the delay * associated with the operation is added to XXX_delay. * XXX_delay contains the accumulated delay time in nanoseconds. */ u64 blkio_start; u64 blkio_delay_max; u64 blkio_delay_min; u64 blkio_delay; /* wait for sync block io completion */ u64 swapin_start; u64 swapin_delay_max; u64 swapin_delay_min; u64 swapin_delay; /* wait for swapin */ u32 blkio_count; /* total count of the number of sync block */ /* io operations performed */ u32 swapin_count; /* total count of swapin */ u64 freepages_start; u64 freepages_delay_max; u64 freepages_delay_min; u64 freepages_delay; /* wait for memory reclaim */ u64 thrashing_start; u64 thrashing_delay_max; u64 thrashing_delay_min; u64 thrashing_delay; /* wait for thrashing page */ u64 compact_start; u64 compact_delay_max; u64 compact_delay_min; u64 compact_delay; /* wait for memory compact */ u64 wpcopy_start; u64 wpcopy_delay_max; u64 wpcopy_delay_min; u64 wpcopy_delay; /* wait for write-protect copy */ u64 irq_delay_max; u64 irq_delay_min; u64 irq_delay; /* wait for IRQ/SOFTIRQ */ u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ u32 compact_count; /* total count of memory compact */ u32 wpcopy_count; /* total count of write-protect copy */ u32 irq_count; /* total count of IRQ/SOFTIRQ */ }; #endif #include <linux/sched.h> #include <linux/slab.h> #include <linux/jump_label.h> #ifdef CONFIG_TASK_DELAY_ACCT DECLARE_STATIC_KEY_FALSE(delayacct_key); extern int delayacct_on; /* Delay accounting turned on/off */ extern struct kmem_cache *delayacct_cache; extern void delayacct_init(void); extern void __delayacct_tsk_init(struct task_struct *); extern void __delayacct_tsk_exit(struct task_struct *); extern void __delayacct_blkio_start(void); extern void __delayacct_blkio_end(struct task_struct *); extern int delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); extern void __delayacct_thrashing_start(bool *in_thrashing); extern void __delayacct_thrashing_end(bool *in_thrashing); extern void __delayacct_swapin_start(void); extern void __delayacct_swapin_end(void); extern void __delayacct_compact_start(void); extern void __delayacct_compact_end(void); extern void __delayacct_wpcopy_start(void); extern void __delayacct_wpcopy_end(void); extern void __delayacct_irq(struct task_struct *task, u32 delta); static inline void delayacct_tsk_init(struct task_struct *tsk) { /* reinitialize in case parent's non-null pointer was dup'ed*/ tsk->delays = NULL; if (delayacct_on) __delayacct_tsk_init(tsk); } /* Free tsk->delays. Called from bad fork and __put_task_struct * where there's no risk of tsk->delays being accessed elsewhere */ static inline void delayacct_tsk_free(struct task_struct *tsk) { if (tsk->delays) kmem_cache_free(delayacct_cache, tsk->delays); tsk->delays = NULL; } static inline void delayacct_blkio_start(void) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) __delayacct_blkio_start(); } static inline void delayacct_blkio_end(struct task_struct *p) { if (!static_branch_unlikely(&delayacct_key)) return; if (p->delays) __delayacct_blkio_end(p); } static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) { if (tsk->delays) return __delayacct_blkio_ticks(tsk); return 0; } static inline void delayacct_freepages_start(void) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) __delayacct_freepages_start(); } static inline void delayacct_freepages_end(void) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) __delayacct_freepages_end(); } static inline void delayacct_thrashing_start(bool *in_thrashing) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) __delayacct_thrashing_start(in_thrashing); } static inline void delayacct_thrashing_end(bool *in_thrashing) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) __delayacct_thrashing_end(in_thrashing); } static inline void delayacct_swapin_start(void) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) __delayacct_swapin_start(); } static inline void delayacct_swapin_end(void) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) __delayacct_swapin_end(); } static inline void delayacct_compact_start(void) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) __delayacct_compact_start(); } static inline void delayacct_compact_end(void) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) __delayacct_compact_end(); } static inline void delayacct_wpcopy_start(void) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) __delayacct_wpcopy_start(); } static inline void delayacct_wpcopy_end(void) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) __delayacct_wpcopy_end(); } static inline void delayacct_irq(struct task_struct *task, u32 delta) { if (!static_branch_unlikely(&delayacct_key)) return; if (task->delays) __delayacct_irq(task, delta); } #else static inline void delayacct_init(void) {} static inline void delayacct_tsk_init(struct task_struct *tsk) {} static inline void delayacct_tsk_free(struct task_struct *tsk) {} static inline void delayacct_blkio_start(void) {} static inline void delayacct_blkio_end(struct task_struct *p) {} static inline int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) { return 0; } static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) { return 0; } static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { return 0; } static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} static inline void delayacct_thrashing_start(bool *in_thrashing) {} static inline void delayacct_thrashing_end(bool *in_thrashing) {} static inline void delayacct_swapin_start(void) {} static inline void delayacct_swapin_end(void) {} static inline void delayacct_compact_start(void) {} static inline void delayacct_compact_end(void) {} static inline void delayacct_wpcopy_start(void) {} static inline void delayacct_wpcopy_end(void) {} static inline void delayacct_irq(struct task_struct *task, u32 delta) {} #endif /* CONFIG_TASK_DELAY_ACCT */ #endif |
| 2 1 6 25 8 27 52 1885 1659 1807 249 17 130 16 146 4 131 249 248 248 1 5 4 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_SIGNAL_H #define _LINUX_SCHED_SIGNAL_H #include <linux/rculist.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/jobctl.h> #include <linux/sched/task.h> #include <linux/cred.h> #include <linux/refcount.h> #include <linux/pid.h> #include <linux/posix-timers.h> #include <linux/mm_types.h> #include <asm/ptrace.h> /* * Types defining task->signal and task->sighand and APIs using them: */ struct sighand_struct { spinlock_t siglock; refcount_t count; wait_queue_head_t signalfd_wqh; struct k_sigaction action[_NSIG]; }; /* * Per-process accounting stats: */ struct pacct_struct { int ac_flag; long ac_exitcode; unsigned long ac_mem; u64 ac_utime, ac_stime; unsigned long ac_minflt, ac_majflt; }; struct cpu_itimer { u64 expires; u64 incr; }; /* * This is the atomic variant of task_cputime, which can be used for * storing and updating task_cputime statistics without locking. */ struct task_cputime_atomic { atomic64_t utime; atomic64_t stime; atomic64_t sum_exec_runtime; }; #define INIT_CPUTIME_ATOMIC \ (struct task_cputime_atomic) { \ .utime = ATOMIC64_INIT(0), \ .stime = ATOMIC64_INIT(0), \ .sum_exec_runtime = ATOMIC64_INIT(0), \ } /** * struct thread_group_cputimer - thread group interval timer counts * @cputime_atomic: atomic thread group interval timers. * * This structure contains the version of task_cputime, above, that is * used for thread group CPU timer calculations. */ struct thread_group_cputimer { struct task_cputime_atomic cputime_atomic; }; struct multiprocess_signals { sigset_t signal; struct hlist_node node; }; struct core_thread { struct task_struct *task; struct core_thread *next; }; struct core_state { atomic_t nr_threads; struct core_thread dumper; struct completion startup; }; /* * NOTE! "signal_struct" does not have its own * locking, because a shared signal_struct always * implies a shared sighand_struct, so locking * sighand_struct is always a proper superset of * the locking of signal_struct. */ struct signal_struct { refcount_t sigcnt; atomic_t live; int nr_threads; int quick_threads; struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ /* current thread group signal load-balancing target: */ struct task_struct *curr_target; /* shared signal handling: */ struct sigpending shared_pending; /* For collecting multiprocess signals during fork */ struct hlist_head multiprocess; /* thread group exit support */ int group_exit_code; /* notify group_exec_task when notify_count is less or equal to 0 */ int notify_count; struct task_struct *group_exec_task; /* thread group stop support, overloads group_exit_code too */ int group_stop_count; unsigned int flags; /* see SIGNAL_* flags below */ struct core_state *core_state; /* coredumping support */ /* * PR_SET_CHILD_SUBREAPER marks a process, like a service * manager, to re-parent orphan (double-forking) child processes * to this process instead of 'init'. The service manager is * able to receive SIGCHLD signals and is able to investigate * the process until it calls wait(). All children of this * process will inherit a flag if they should look for a * child_subreaper process at exit. */ unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ unsigned int timer_create_restore_ids:1; atomic_t next_posix_timer_id; struct hlist_head posix_timers; struct hlist_head ignored_posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; ktime_t it_real_incr; /* * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these * values are defined to 0 and 1 respectively */ struct cpu_itimer it[2]; /* * Thread group totals for process CPU timers. * See thread_group_cputimer(), et al, for details. */ struct thread_group_cputimer cputimer; #endif /* Empty if CONFIG_POSIX_TIMERS=n */ struct posix_cputimers posix_cputimers; /* PID/PID hash table linkage. */ struct pid *pids[PIDTYPE_MAX]; #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif struct pid *tty_old_pgrp; /* boolean value for session group leader */ int leader; struct tty_struct *tty; /* NULL if no tty */ #ifdef CONFIG_SCHED_AUTOGROUP struct autogroup *autogroup; #endif /* * Cumulative resource counters for dead threads in the group, * and for reaped dead child processes forked by this group. * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ seqlock_t stats_lock; u64 utime, stime, cutime, cstime; u64 gtime; u64 cgtime; struct prev_cputime prev_cputime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; unsigned long maxrss, cmaxrss; struct task_io_accounting ioac; /* * Cumulative ns of schedule CPU time fo dead threads in the * group, not including a zombie group leader, (This only differs * from jiffies_to_ns(utime + stime) if sched_clock uses something * other than jiffies.) */ unsigned long long sum_sched_runtime; /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs * to get both rlim_cur and rlim_max atomically, and either one * alone is a single word that can safely be read normally. * getrlimit/setrlimit use task_lock(current->group_leader) to * protect this instead of the siglock, because they really * have no need to disable irqs. */ struct rlimit rlim[RLIM_NLIMITS]; #ifdef CONFIG_BSD_PROCESS_ACCT struct pacct_struct pacct; /* per-process accounting information */ #endif #ifdef CONFIG_TASKSTATS struct taskstats *stats; #endif #ifdef CONFIG_AUDIT unsigned audit_tty; struct tty_audit_buf *tty_audit_buf; #endif /* * Thread is the potential origin of an oom condition; kill first on * oom */ bool oom_flag_origin; short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ struct mm_struct *oom_mm; /* recorded mm when the thread group got * killed by the oom killer */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) * Deprecated do not use in new code. * Use exec_update_lock instead. */ struct rw_semaphore exec_update_lock; /* Held while task_struct is * being updated during exec, * and may have inconsistent * permissions. */ } __randomize_layout; /* * Bits in flags field of signal_struct. */ #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ /* * Pending notifications to parent. */ #define SIGNAL_CLD_STOPPED 0x00000010 #define SIGNAL_CLD_CONTINUED 0x00000020 #define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED) #define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ #define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ SIGNAL_STOP_CONTINUED) static inline void signal_set_stop_flags(struct signal_struct *sig, unsigned int flags) { WARN_ON(sig->flags & SIGNAL_GROUP_EXIT); sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type); static inline int kernel_dequeue_signal(void) { struct task_struct *task = current; kernel_siginfo_t __info; enum pid_type __type; int ret; spin_lock_irq(&task->sighand->siglock); ret = dequeue_signal(&task->blocked, &__info, &__type); spin_unlock_irq(&task->sighand->siglock); return ret; } static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); if (current->jobctl & JOBCTL_STOP_DEQUEUED) { current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); } spin_unlock_irq(¤t->sighand->siglock); schedule(); } int force_sig_fault_to_task(int sig, int code, void __user *addr, struct task_struct *t); int force_sig_fault(int sig, int code, void __user *addr); int send_sig_fault(int sig, int code, void __user *addr, struct task_struct *t); int force_sig_mceerr(int code, void __user *, short); int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); int send_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno, struct task_struct *t); int force_sig_seccomp(int syscall, int reason, bool force_coredump); extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig); extern int force_sig_info(struct kernel_siginfo *); extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp); extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid); extern int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, struct pid *, const struct cred *); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); extern void force_fatal_sig(int); extern void force_exit_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline void clear_notify_signal(void) { clear_thread_flag(TIF_NOTIFY_SIGNAL); smp_mb__after_atomic(); } /* * Returns 'true' if kick_process() is needed to force a transition from * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. */ static inline bool __set_notify_signal(struct task_struct *task) { return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && !wake_up_state(task, TASK_INTERRUPTIBLE); } /* * Called to break out of interruptible wait loops, and enter the * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { if (__set_notify_signal(task)) kick_process(task); } static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); return -ERESTARTNOINTR; } static inline int task_sigpending(struct task_struct *p) { return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } static inline int signal_pending(struct task_struct *p) { /* * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same * behavior in terms of ensuring that we break out of wait loops * so that notify signal callbacks can be processed. */ if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL))) return 1; return task_sigpending(p); } static inline int __fatal_signal_pending(struct task_struct *p) { return unlikely(sigismember(&p->pending.signal, SIGKILL)); } static inline int fatal_signal_pending(struct task_struct *p) { return task_sigpending(p) && __fatal_signal_pending(p); } static inline int signal_pending_state(unsigned int state, struct task_struct *p) { if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) return 0; if (!signal_pending(p)) return 0; return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); } /* * This should only be used in fault handlers to decide whether we * should stop the current fault routine to handle the signals * instead, especially with the case where we've got interrupted with * a VM_FAULT_RETRY. */ static inline bool fault_signal_pending(vm_fault_t fault_flags, struct pt_regs *regs) { return unlikely((fault_flags & VM_FAULT_RETRY) && (fatal_signal_pending(current) || (user_mode(regs) && signal_pending(current)))); } /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. * This is required every time the blocked sigset_t changes. * callers must hold sighand->siglock. */ extern void recalc_sigpending(void); extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); static inline void signal_wake_up(struct task_struct *t, bool fatal) { unsigned int state = 0; if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) { t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED); state = TASK_WAKEKILL | __TASK_TRACED; } signal_wake_up_state(t, state); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { unsigned int state = 0; if (resume) { t->jobctl &= ~JOBCTL_TRACED; state = __TASK_TRACED; } signal_wake_up_state(t, state); } void task_join_group_stop(struct task_struct *task); #ifdef TIF_RESTORE_SIGMASK /* * Legacy restore_sigmask accessors. These are inefficient on * SMP architectures because they require atomic operations. */ /** * set_restore_sigmask() - make sure saved_sigmask processing gets done * * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code * will run before returning to user mode, to process the flag. For * all callers, TIF_SIGPENDING is already set or it's no harm to set * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the * arch code will notice on return to user mode, in case those bits * are scarce. We set TIF_SIGPENDING here to ensure that the arch * signal code always gets run when TIF_RESTORE_SIGMASK is set. */ static inline void set_restore_sigmask(void) { set_thread_flag(TIF_RESTORE_SIGMASK); } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { clear_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline void clear_restore_sigmask(void) { clear_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return test_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline bool test_restore_sigmask(void) { return test_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_and_clear_restore_sigmask(void) { return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); } #else /* TIF_RESTORE_SIGMASK */ /* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */ static inline void set_restore_sigmask(void) { current->restore_sigmask = true; } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { task->restore_sigmask = false; } static inline void clear_restore_sigmask(void) { current->restore_sigmask = false; } static inline bool test_restore_sigmask(void) { return current->restore_sigmask; } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return task->restore_sigmask; } static inline bool test_and_clear_restore_sigmask(void) { if (!current->restore_sigmask) return false; current->restore_sigmask = false; return true; } #endif static inline void restore_saved_sigmask(void) { if (test_and_clear_restore_sigmask()) __set_current_blocked(¤t->saved_sigmask); } extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize); static inline void restore_saved_sigmask_unless(bool interrupted) { if (interrupted) WARN_ON(!signal_pending(current)); else restore_saved_sigmask(); } static inline sigset_t *sigmask_to_save(void) { sigset_t *res = ¤t->blocked; if (unlikely(test_restore_sigmask())) res = ¤t->saved_sigmask; return res; } static inline int kill_cad_pid(int sig, int priv) { return kill_pid(cad_pid, sig, priv); } /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) #define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) static inline int __on_sig_stack(unsigned long sp) { #ifdef CONFIG_STACK_GROWSUP return sp >= current->sas_ss_sp && sp - current->sas_ss_sp < current->sas_ss_size; #else return sp > current->sas_ss_sp && sp - current->sas_ss_sp <= current->sas_ss_size; #endif } /* * True if we are on the alternate signal stack. */ static inline int on_sig_stack(unsigned long sp) { /* * If the signal stack is SS_AUTODISARM then, by construction, we * can't be on the signal stack unless user code deliberately set * SS_AUTODISARM when we were already on it. * * This improves reliability: if user state gets corrupted such that * the stack pointer points very close to the end of the signal stack, * then this check will enable the signal to be handled anyway. */ if (current->sas_ss_flags & SS_AUTODISARM) return 0; return __on_sig_stack(sp); } static inline int sas_ss_flags(unsigned long sp) { if (!current->sas_ss_size) return SS_DISABLE; return on_sig_stack(sp) ? SS_ONSTACK : 0; } static inline void sas_ss_reset(struct task_struct *p) { p->sas_ss_sp = 0; p->sas_ss_size = 0; p->sas_ss_flags = SS_DISABLE; } static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) { if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) #ifdef CONFIG_STACK_GROWSUP return current->sas_ss_sp; #else return current->sas_ss_sp + current->sas_ss_size; #endif return sp; } extern void __cleanup_sighand(struct sighand_struct *); extern void flush_itimer_signals(void); #define tasklist_empty() \ list_empty(&init_task.tasks) #define next_task(p) \ list_entry_rcu((p)->tasks.next, struct task_struct, tasks) #define for_each_process(p) \ for (p = &init_task ; (p = next_task(p)) != &init_task ; ) extern bool current_is_single_threaded(void); /* * Without tasklist/siglock it is only rcu-safe if g can't exit/exec, * otherwise next_thread(t) will never reach g after list_del_rcu(g). */ #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) #define for_other_threads(p, t) \ for (t = p; (t = next_thread(t)) != p; ) #define __for_each_thread(signal, t) \ list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node, \ lockdep_is_held(&tasklist_lock)) #define for_each_thread(p, t) \ __for_each_thread((p)->signal, t) /* Careful: this is a double loop, 'break' won't work as expected. */ #define for_each_process_thread(p, t) \ for_each_process(p) for_each_thread(p, t) typedef int (*proc_visitor)(struct task_struct *p, void *data); void walk_process_tree(struct task_struct *top, proc_visitor, void *); static inline struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { struct pid *pid; if (type == PIDTYPE_PID) pid = task_pid(task); else pid = task->signal->pids[type]; return pid; } static inline struct pid *task_tgid(struct task_struct *task) { return task->signal->pids[PIDTYPE_TGID]; } /* * Without tasklist or RCU lock it is not safe to dereference * the result of task_pgrp/task_session even if task == current, * we can race with another thread doing sys_setsid/sys_setpgid. */ static inline struct pid *task_pgrp(struct task_struct *task) { return task->signal->pids[PIDTYPE_PGID]; } static inline struct pid *task_session(struct task_struct *task) { return task->signal->pids[PIDTYPE_SID]; } static inline int get_nr_threads(struct task_struct *task) { return task->signal->nr_threads; } static inline bool thread_group_leader(struct task_struct *p) { return p->exit_signal >= 0; } static inline bool same_thread_group(struct task_struct *p1, struct task_struct *p2) { return p1->signal == p2->signal; } /* * returns NULL if p is the last thread in the thread group */ static inline struct task_struct *__next_thread(struct task_struct *p) { return list_next_or_null_rcu(&p->signal->thread_head, &p->thread_node, struct task_struct, thread_node); } static inline struct task_struct *next_thread(struct task_struct *p) { return __next_thread(p) ?: p->group_leader; } static inline int thread_group_empty(struct task_struct *p) { return thread_group_leader(p) && list_is_last(&p->thread_node, &p->signal->thread_head); } #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) extern struct sighand_struct *__lock_task_sighand(struct task_struct *task, unsigned long *flags); static inline struct sighand_struct *lock_task_sighand(struct task_struct *task, unsigned long *flags) { struct sighand_struct *ret; ret = __lock_task_sighand(task, flags); (void)__cond_lock(&task->sighand->siglock, ret); return ret; } static inline void unlock_task_sighand(struct task_struct *task, unsigned long *flags) { spin_unlock_irqrestore(&task->sighand->siglock, *flags); } #ifdef CONFIG_LOCKDEP extern void lockdep_assert_task_sighand_held(struct task_struct *task); #else static inline void lockdep_assert_task_sighand_held(struct task_struct *task) { } #endif static inline unsigned long task_rlimit(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_cur); } static inline unsigned long task_rlimit_max(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_max); } static inline unsigned long rlimit(unsigned int limit) { return task_rlimit(current, limit); } static inline unsigned long rlimit_max(unsigned int limit) { return task_rlimit_max(current, limit); } #endif /* _LINUX_SCHED_SIGNAL_H */ |
| 1 11 1 10 11 11 1 1 1 1 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MIN_HEAP_H #define _LINUX_MIN_HEAP_H #include <linux/bug.h> #include <linux/string.h> #include <linux/types.h> /* * The Min Heap API provides utilities for managing min-heaps, a binary tree * structure where each node's value is less than or equal to its children's * values, ensuring the smallest element is at the root. * * Users should avoid directly calling functions prefixed with __min_heap_*(). * Instead, use the provided macro wrappers. * * For further details and examples, refer to Documentation/core-api/min_heap.rst. */ /** * Data structure to hold a min-heap. * @nr: Number of elements currently in the heap. * @size: Maximum number of elements that can be held in current storage. * @data: Pointer to the start of array holding the heap elements. * @preallocated: Start of the static preallocated array holding the heap elements. */ #define MIN_HEAP_PREALLOCATED(_type, _name, _nr) \ struct _name { \ size_t nr; \ size_t size; \ _type *data; \ _type preallocated[_nr]; \ } #define DEFINE_MIN_HEAP(_type, _name) MIN_HEAP_PREALLOCATED(_type, _name, 0) typedef DEFINE_MIN_HEAP(char, min_heap_char) min_heap_char; #define __minheap_cast(_heap) (typeof((_heap)->data[0]) *) #define __minheap_obj_size(_heap) sizeof((_heap)->data[0]) /** * struct min_heap_callbacks - Data/functions to customise the min_heap. * @less: Partial order function for this heap. * @swp: Swap elements function. */ struct min_heap_callbacks { bool (*less)(const void *lhs, const void *rhs, void *args); void (*swp)(void *lhs, void *rhs, void *args); }; /** * is_aligned - is this pointer & size okay for word-wide copying? * @base: pointer to data * @size: size of each element * @align: required alignment (typically 4 or 8) * * Returns true if elements can be copied using word loads and stores. * The size must be a multiple of the alignment, and the base address must * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. * * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)" * to "if ((a | b) & mask)", so we do that by hand. */ __attribute_const__ __always_inline static bool is_aligned(const void *base, size_t size, unsigned char align) { unsigned char lsbits = (unsigned char)size; (void)base; #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS lsbits |= (unsigned char)(uintptr_t)base; #endif return (lsbits & (align - 1)) == 0; } /** * swap_words_32 - swap two elements in 32-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 4) * * Exchange the two objects in memory. This exploits base+index addressing, * which basically all CPUs have, to minimize loop overhead computations. * * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the * bottom of the loop, even though the zero flag is still valid from the * subtract (since the intervening mov instructions don't alter the flags). * Gcc 8.1.0 doesn't have that problem. */ static __always_inline void swap_words_32(void *a, void *b, size_t n) { do { u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; } while (n); } /** * swap_words_64 - swap two elements in 64-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 8) * * Exchange the two objects in memory. This exploits base+index * addressing, which basically all CPUs have, to minimize loop overhead * computations. * * We'd like to use 64-bit loads if possible. If they're not, emulating * one requires base+index+4 addressing which x86 has but most other * processors do not. If CONFIG_64BIT, we definitely have 64-bit loads, * but it's possible to have 64-bit loads without 64-bit pointers (e.g. * x32 ABI). Are there any cases the kernel needs to worry about? */ static __always_inline void swap_words_64(void *a, void *b, size_t n) { do { #ifdef CONFIG_64BIT u64 t = *(u64 *)(a + (n -= 8)); *(u64 *)(a + n) = *(u64 *)(b + n); *(u64 *)(b + n) = t; #else /* Use two 32-bit transfers to avoid base+index+4 addressing */ u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; #endif } while (n); } /** * swap_bytes - swap two elements a byte at a time * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size * * This is the fallback if alignment doesn't allow using larger chunks. */ static __always_inline void swap_bytes(void *a, void *b, size_t n) { do { char t = ((char *)a)[--n]; ((char *)a)[n] = ((char *)b)[n]; ((char *)b)[n] = t; } while (n); } /* * The values are arbitrary as long as they can't be confused with * a pointer, but small integers make for the smallest compare * instructions. */ #define SWAP_WORDS_64 ((void (*)(void *, void *, void *))0) #define SWAP_WORDS_32 ((void (*)(void *, void *, void *))1) #define SWAP_BYTES ((void (*)(void *, void *, void *))2) /* * Selects the appropriate swap function based on the element size. */ static __always_inline void *select_swap_func(const void *base, size_t size) { if (is_aligned(base, size, 8)) return SWAP_WORDS_64; else if (is_aligned(base, size, 4)) return SWAP_WORDS_32; else return SWAP_BYTES; } static __always_inline void do_swap(void *a, void *b, size_t size, void (*swap_func)(void *lhs, void *rhs, void *args), void *priv) { if (swap_func == SWAP_WORDS_64) swap_words_64(a, b, size); else if (swap_func == SWAP_WORDS_32) swap_words_32(a, b, size); else if (swap_func == SWAP_BYTES) swap_bytes(a, b, size); else swap_func(a, b, priv); } /** * parent - given the offset of the child, find the offset of the parent. * @i: the offset of the heap element whose parent is sought. Non-zero. * @lsbit: a precomputed 1-bit mask, equal to "size & -size" * @size: size of each element * * In terms of array indexes, the parent of element j = @i/@size is simply * (j-1)/2. But when working in byte offsets, we can't use implicit * truncation of integer divides. * * Fortunately, we only need one bit of the quotient, not the full divide. * @size has a least significant bit. That bit will be clear if @i is * an even multiple of @size, and set if it's an odd multiple. * * Logically, we're doing "if (i & lsbit) i -= size;", but since the * branch is unpredictable, it's done with a bit of clever branch-free * code instead. */ __attribute_const__ __always_inline static size_t parent(size_t i, unsigned int lsbit, size_t size) { i -= size; i -= size & -(i & lsbit); return i / 2; } /* Initialize a min-heap. */ static __always_inline void __min_heap_init_inline(min_heap_char *heap, void *data, int size) { heap->nr = 0; heap->size = size; if (data) heap->data = data; else heap->data = heap->preallocated; } #define min_heap_init_inline(_heap, _data, _size) \ __min_heap_init_inline(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size) /* Get the minimum element from the heap. */ static __always_inline void *__min_heap_peek_inline(struct min_heap_char *heap) { return heap->nr ? heap->data : NULL; } #define min_heap_peek_inline(_heap) \ (__minheap_cast(_heap) \ __min_heap_peek_inline(container_of(&(_heap)->nr, min_heap_char, nr))) /* Check if the heap is full. */ static __always_inline bool __min_heap_full_inline(min_heap_char *heap) { return heap->nr == heap->size; } #define min_heap_full_inline(_heap) \ __min_heap_full_inline(container_of(&(_heap)->nr, min_heap_char, nr)) /* Sift the element at pos down the heap. */ static __always_inline void __min_heap_sift_down_inline(min_heap_char *heap, int pos, size_t elem_size, const struct min_heap_callbacks *func, void *args) { const unsigned long lsbit = elem_size & -elem_size; void *data = heap->data; void (*swp)(void *lhs, void *rhs, void *args) = func->swp; /* pre-scale counters for performance */ size_t a = pos * elem_size; size_t b, c, d; size_t n = heap->nr * elem_size; if (!swp) swp = select_swap_func(data, elem_size); /* Find the sift-down path all the way to the leaves. */ for (b = a; c = 2 * b + elem_size, (d = c + elem_size) < n;) b = func->less(data + c, data + d, args) ? c : d; /* Special case for the last leaf with no sibling. */ if (d == n) b = c; /* Backtrack to the correct location. */ while (b != a && func->less(data + a, data + b, args)) b = parent(b, lsbit, elem_size); /* Shift the element into its correct place. */ c = b; while (b != a) { b = parent(b, lsbit, elem_size); do_swap(data + b, data + c, elem_size, swp, args); } } #define min_heap_sift_down_inline(_heap, _pos, _func, _args) \ __min_heap_sift_down_inline(container_of(&(_heap)->nr, min_heap_char, nr), _pos, \ __minheap_obj_size(_heap), _func, _args) /* Sift up ith element from the heap, O(log2(nr)). */ static __always_inline void __min_heap_sift_up_inline(min_heap_char *heap, size_t elem_size, size_t idx, const struct min_heap_callbacks *func, void *args) { const unsigned long lsbit = elem_size & -elem_size; void *data = heap->data; void (*swp)(void *lhs, void *rhs, void *args) = func->swp; /* pre-scale counters for performance */ size_t a = idx * elem_size, b; if (!swp) swp = select_swap_func(data, elem_size); while (a) { b = parent(a, lsbit, elem_size); if (func->less(data + b, data + a, args)) break; do_swap(data + a, data + b, elem_size, swp, args); a = b; } } #define min_heap_sift_up_inline(_heap, _idx, _func, _args) \ __min_heap_sift_up_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _idx, _func, _args) /* Floyd's approach to heapification that is O(nr). */ static __always_inline void __min_heapify_all_inline(min_heap_char *heap, size_t elem_size, const struct min_heap_callbacks *func, void *args) { int i; for (i = heap->nr / 2 - 1; i >= 0; i--) __min_heap_sift_down_inline(heap, i, elem_size, func, args); } #define min_heapify_all_inline(_heap, _func, _args) \ __min_heapify_all_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _func, _args) /* Remove minimum element from the heap, O(log2(nr)). */ static __always_inline bool __min_heap_pop_inline(min_heap_char *heap, size_t elem_size, const struct min_heap_callbacks *func, void *args) { void *data = heap->data; if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap")) return false; /* Place last element at the root (position 0) and then sift down. */ heap->nr--; memcpy(data, data + (heap->nr * elem_size), elem_size); __min_heap_sift_down_inline(heap, 0, elem_size, func, args); return true; } #define min_heap_pop_inline(_heap, _func, _args) \ __min_heap_pop_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _func, _args) /* * Remove the minimum element and then push the given element. The * implementation performs 1 sift (O(log2(nr))) and is therefore more * efficient than a pop followed by a push that does 2. */ static __always_inline void __min_heap_pop_push_inline(min_heap_char *heap, const void *element, size_t elem_size, const struct min_heap_callbacks *func, void *args) { memcpy(heap->data, element, elem_size); __min_heap_sift_down_inline(heap, 0, elem_size, func, args); } #define min_heap_pop_push_inline(_heap, _element, _func, _args) \ __min_heap_pop_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ __minheap_obj_size(_heap), _func, _args) /* Push an element on to the heap, O(log2(nr)). */ static __always_inline bool __min_heap_push_inline(min_heap_char *heap, const void *element, size_t elem_size, const struct min_heap_callbacks *func, void *args) { void *data = heap->data; int pos; if (WARN_ONCE(heap->nr >= heap->size, "Pushing on a full heap")) return false; /* Place at the end of data. */ pos = heap->nr; memcpy(data + (pos * elem_size), element, elem_size); heap->nr++; /* Sift child at pos up. */ __min_heap_sift_up_inline(heap, elem_size, pos, func, args); return true; } #define min_heap_push_inline(_heap, _element, _func, _args) \ __min_heap_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ __minheap_obj_size(_heap), _func, _args) /* Remove ith element from the heap, O(log2(nr)). */ static __always_inline bool __min_heap_del_inline(min_heap_char *heap, size_t elem_size, size_t idx, const struct min_heap_callbacks *func, void *args) { void *data = heap->data; void (*swp)(void *lhs, void *rhs, void *args) = func->swp; if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap")) return false; if (!swp) swp = select_swap_func(data, elem_size); /* Place last element at the root (position 0) and then sift down. */ heap->nr--; if (idx == heap->nr) return true; do_swap(data + (idx * elem_size), data + (heap->nr * elem_size), elem_size, swp, args); __min_heap_sift_up_inline(heap, elem_size, idx, func, args); __min_heap_sift_down_inline(heap, idx, elem_size, func, args); return true; } #define min_heap_del_inline(_heap, _idx, _func, _args) \ __min_heap_del_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _idx, _func, _args) void __min_heap_init(min_heap_char *heap, void *data, int size); void *__min_heap_peek(struct min_heap_char *heap); bool __min_heap_full(min_heap_char *heap); void __min_heap_sift_down(min_heap_char *heap, int pos, size_t elem_size, const struct min_heap_callbacks *func, void *args); void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx, const struct min_heap_callbacks *func, void *args); void __min_heapify_all(min_heap_char *heap, size_t elem_size, const struct min_heap_callbacks *func, void *args); bool __min_heap_pop(min_heap_char *heap, size_t elem_size, const struct min_heap_callbacks *func, void *args); void __min_heap_pop_push(min_heap_char *heap, const void *element, size_t elem_size, const struct min_heap_callbacks *func, void *args); bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size, const struct min_heap_callbacks *func, void *args); bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx, const struct min_heap_callbacks *func, void *args); #define min_heap_init(_heap, _data, _size) \ __min_heap_init(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size) #define min_heap_peek(_heap) \ (__minheap_cast(_heap) __min_heap_peek(container_of(&(_heap)->nr, min_heap_char, nr))) #define min_heap_full(_heap) \ __min_heap_full(container_of(&(_heap)->nr, min_heap_char, nr)) #define min_heap_sift_down(_heap, _pos, _func, _args) \ __min_heap_sift_down(container_of(&(_heap)->nr, min_heap_char, nr), _pos, \ __minheap_obj_size(_heap), _func, _args) #define min_heap_sift_up(_heap, _idx, _func, _args) \ __min_heap_sift_up(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _idx, _func, _args) #define min_heapify_all(_heap, _func, _args) \ __min_heapify_all(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _func, _args) #define min_heap_pop(_heap, _func, _args) \ __min_heap_pop(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _func, _args) #define min_heap_pop_push(_heap, _element, _func, _args) \ __min_heap_pop_push(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ __minheap_obj_size(_heap), _func, _args) #define min_heap_push(_heap, _element, _func, _args) \ __min_heap_push(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ __minheap_obj_size(_heap), _func, _args) #define min_heap_del(_heap, _idx, _func, _args) \ __min_heap_del(container_of(&(_heap)->nr, min_heap_char, nr), \ __minheap_obj_size(_heap), _idx, _func, _args) #endif /* _LINUX_MIN_HEAP_H */ |
| 1 1 3 9 9 9 10 10 1 9 10 13 1 1 1 10 10 1 9 9 17 1 12 2 14 2 8 9 9 9 9 9 9 18 18 33 33 30 3 1 8 2 1 1 1 1 3 10 2 2 1 1 1 1 1 1 1 1 22 4 20 19 19 19 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2020, Microsoft Corporation. * * Author(s): Steve French <stfrench@microsoft.com> * David Howells <dhowells@redhat.com> */ /* #include <linux/module.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/magic.h> #include <linux/security.h> #include <net/net_namespace.h> #ifdef CONFIG_CIFS_DFS_UPCALL #include "dfs_cache.h" #endif */ #include <linux/ctype.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/parser.h> #include <linux/utsname.h> #include "cifsfs.h" #include "cifspdu.h" #include "cifsglob.h" #include "cifsproto.h" #include "cifs_unicode.h" #include "cifs_debug.h" #include "cifs_fs_sb.h" #include "ntlmssp.h" #include "nterr.h" #include "rfc1002pdu.h" #include "fs_context.h" DEFINE_MUTEX(cifs_mount_mutex); static const match_table_t cifs_smb_version_tokens = { { Smb_1, SMB1_VERSION_STRING }, { Smb_20, SMB20_VERSION_STRING}, { Smb_21, SMB21_VERSION_STRING }, { Smb_30, SMB30_VERSION_STRING }, { Smb_302, SMB302_VERSION_STRING }, { Smb_302, ALT_SMB302_VERSION_STRING }, { Smb_311, SMB311_VERSION_STRING }, { Smb_311, ALT_SMB311_VERSION_STRING }, { Smb_3any, SMB3ANY_VERSION_STRING }, { Smb_default, SMBDEFAULT_VERSION_STRING }, { Smb_version_err, NULL } }; static const match_table_t cifs_secflavor_tokens = { { Opt_sec_krb5, "krb5" }, { Opt_sec_krb5i, "krb5i" }, { Opt_sec_krb5p, "krb5p" }, { Opt_sec_ntlmsspi, "ntlmsspi" }, { Opt_sec_ntlmssp, "ntlmssp" }, { Opt_sec_ntlmv2, "nontlm" }, { Opt_sec_ntlmv2, "ntlmv2" }, { Opt_sec_ntlmv2i, "ntlmv2i" }, { Opt_sec_none, "none" }, { Opt_sec_err, NULL } }; static const match_table_t cifs_upcall_target = { { Opt_upcall_target_mount, "mount" }, { Opt_upcall_target_application, "app" }, { Opt_upcall_target_err, NULL } }; const struct fs_parameter_spec smb3_fs_parameters[] = { /* Mount options that take no arguments */ fsparam_flag_no("user_xattr", Opt_user_xattr), fsparam_flag_no("forceuid", Opt_forceuid), fsparam_flag_no("multichannel", Opt_multichannel), fsparam_flag_no("forcegid", Opt_forcegid), fsparam_flag("noblocksend", Opt_noblocksend), fsparam_flag("noautotune", Opt_noautotune), fsparam_flag("nolease", Opt_nolease), fsparam_flag_no("hard", Opt_hard), fsparam_flag_no("soft", Opt_soft), fsparam_flag_no("perm", Opt_perm), fsparam_flag("nodelete", Opt_nodelete), fsparam_flag_no("mapposix", Opt_mapposix), fsparam_flag("mapchars", Opt_mapchars), fsparam_flag("nomapchars", Opt_nomapchars), fsparam_flag_no("sfu", Opt_sfu), fsparam_flag("nodfs", Opt_nodfs), fsparam_flag_no("posixpaths", Opt_posixpaths), fsparam_flag_no("unix", Opt_unix), fsparam_flag_no("linux", Opt_unix), fsparam_flag_no("posix", Opt_unix), fsparam_flag("nocase", Opt_nocase), fsparam_flag("ignorecase", Opt_nocase), fsparam_flag_no("brl", Opt_brl), fsparam_flag_no("handlecache", Opt_handlecache), fsparam_flag("forcemandatorylock", Opt_forcemandatorylock), fsparam_flag("forcemand", Opt_forcemandatorylock), fsparam_flag("setuidfromacl", Opt_setuidfromacl), fsparam_flag("idsfromsid", Opt_setuidfromacl), fsparam_flag_no("setuids", Opt_setuids), fsparam_flag_no("dynperm", Opt_dynperm), fsparam_flag_no("intr", Opt_intr), fsparam_flag_no("strictsync", Opt_strictsync), fsparam_flag_no("serverino", Opt_serverino), fsparam_flag("rwpidforward", Opt_rwpidforward), fsparam_flag("cifsacl", Opt_cifsacl), fsparam_flag_no("acl", Opt_acl), fsparam_flag("locallease", Opt_locallease), fsparam_flag("sign", Opt_sign), fsparam_flag("ignore_signature", Opt_ignore_signature), fsparam_flag("signloosely", Opt_ignore_signature), fsparam_flag("seal", Opt_seal), fsparam_flag("noac", Opt_noac), fsparam_flag("fsc", Opt_fsc), fsparam_flag("mfsymlinks", Opt_mfsymlinks), fsparam_flag("multiuser", Opt_multiuser), fsparam_flag("sloppy", Opt_sloppy), fsparam_flag("nosharesock", Opt_nosharesock), fsparam_flag_no("persistenthandles", Opt_persistent), fsparam_flag_no("resilienthandles", Opt_resilient), fsparam_flag_no("tcpnodelay", Opt_tcp_nodelay), fsparam_flag("nosparse", Opt_nosparse), fsparam_flag("domainauto", Opt_domainauto), fsparam_flag("rdma", Opt_rdma), fsparam_flag("modesid", Opt_modesid), fsparam_flag("modefromsid", Opt_modesid), fsparam_flag("rootfs", Opt_rootfs), fsparam_flag("compress", Opt_compress), fsparam_flag("witness", Opt_witness), fsparam_flag_no("nativesocket", Opt_nativesocket), /* Mount options which take uid or gid */ fsparam_uid("backupuid", Opt_backupuid), fsparam_gid("backupgid", Opt_backupgid), fsparam_uid("uid", Opt_uid), fsparam_uid("cruid", Opt_cruid), fsparam_gid("gid", Opt_gid), /* Mount options which take numeric value */ fsparam_u32("file_mode", Opt_file_mode), fsparam_u32("dirmode", Opt_dirmode), fsparam_u32("dir_mode", Opt_dirmode), fsparam_u32("port", Opt_port), fsparam_u32("min_enc_offload", Opt_min_enc_offload), fsparam_u32("retrans", Opt_retrans), fsparam_u32("esize", Opt_min_enc_offload), fsparam_u32("bsize", Opt_blocksize), fsparam_u32("rasize", Opt_rasize), fsparam_u32("rsize", Opt_rsize), fsparam_u32("wsize", Opt_wsize), fsparam_u32("actimeo", Opt_actimeo), fsparam_u32("acdirmax", Opt_acdirmax), fsparam_u32("acregmax", Opt_acregmax), fsparam_u32("closetimeo", Opt_closetimeo), fsparam_u32("echo_interval", Opt_echo_interval), fsparam_u32("max_credits", Opt_max_credits), fsparam_u32("max_cached_dirs", Opt_max_cached_dirs), fsparam_u32("handletimeout", Opt_handletimeout), fsparam_u64("snapshot", Opt_snapshot), fsparam_u32("max_channels", Opt_max_channels), /* Mount options which take string value */ fsparam_string("source", Opt_source), fsparam_string("user", Opt_user), fsparam_string("username", Opt_user), fsparam_string("pass", Opt_pass), fsparam_string("password", Opt_pass), fsparam_string("pass2", Opt_pass2), fsparam_string("password2", Opt_pass2), fsparam_string("ip", Opt_ip), fsparam_string("addr", Opt_ip), fsparam_string("domain", Opt_domain), fsparam_string("dom", Opt_domain), fsparam_string("srcaddr", Opt_srcaddr), fsparam_string("iocharset", Opt_iocharset), fsparam_string("netbiosname", Opt_netbiosname), fsparam_string("servern", Opt_servern), fsparam_string("ver", Opt_ver), fsparam_string("vers", Opt_vers), fsparam_string("sec", Opt_sec), fsparam_string("cache", Opt_cache), fsparam_string("reparse", Opt_reparse), fsparam_string("upcall_target", Opt_upcalltarget), fsparam_string("symlink", Opt_symlink), fsparam_string("symlinkroot", Opt_symlinkroot), /* Arguments that should be ignored */ fsparam_flag("guest", Opt_ignore), fsparam_flag("noatime", Opt_ignore), fsparam_flag("relatime", Opt_ignore), fsparam_flag("_netdev", Opt_ignore), fsparam_flag_no("suid", Opt_ignore), fsparam_flag_no("exec", Opt_ignore), fsparam_flag_no("dev", Opt_ignore), fsparam_flag_no("mand", Opt_ignore), fsparam_flag_no("auto", Opt_ignore), fsparam_string("cred", Opt_ignore), fsparam_string("credentials", Opt_ignore), /* * UNC and prefixpath is now extracted from Opt_source * in the new mount API so we can just ignore them going forward. */ fsparam_string("unc", Opt_ignore), fsparam_string("prefixpath", Opt_ignore), {} }; static int cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_context *ctx) { substring_t args[MAX_OPT_ARGS]; /* * With mount options, the last one should win. Reset any existing * settings back to default. */ ctx->sectype = Unspecified; ctx->sign = false; switch (match_token(value, cifs_secflavor_tokens, args)) { case Opt_sec_krb5p: cifs_errorf(fc, "sec=krb5p is not supported. Use sec=krb5,seal instead\n"); return 1; case Opt_sec_krb5i: ctx->sign = true; fallthrough; case Opt_sec_krb5: ctx->sectype = Kerberos; break; case Opt_sec_ntlmsspi: ctx->sign = true; fallthrough; case Opt_sec_ntlmssp: ctx->sectype = RawNTLMSSP; break; case Opt_sec_ntlmv2i: ctx->sign = true; fallthrough; case Opt_sec_ntlmv2: ctx->sectype = NTLMv2; break; case Opt_sec_none: ctx->nullauth = 1; kfree(ctx->username); ctx->username = NULL; break; default: cifs_errorf(fc, "bad security option: %s\n", value); return 1; } return 0; } static int cifs_parse_upcall_target(struct fs_context *fc, char *value, struct smb3_fs_context *ctx) { substring_t args[MAX_OPT_ARGS]; ctx->upcall_target = UPTARGET_UNSPECIFIED; switch (match_token(value, cifs_upcall_target, args)) { case Opt_upcall_target_mount: ctx->upcall_target = UPTARGET_MOUNT; break; case Opt_upcall_target_application: ctx->upcall_target = UPTARGET_APP; break; default: cifs_errorf(fc, "bad upcall target: %s\n", value); return 1; } return 0; } static const match_table_t cifs_cacheflavor_tokens = { { Opt_cache_loose, "loose" }, { Opt_cache_strict, "strict" }, { Opt_cache_none, "none" }, { Opt_cache_ro, "ro" }, { Opt_cache_rw, "singleclient" }, { Opt_cache_err, NULL } }; static int cifs_parse_cache_flavor(struct fs_context *fc, char *value, struct smb3_fs_context *ctx) { substring_t args[MAX_OPT_ARGS]; switch (match_token(value, cifs_cacheflavor_tokens, args)) { case Opt_cache_loose: ctx->direct_io = false; ctx->strict_io = false; ctx->cache_ro = false; ctx->cache_rw = false; break; case Opt_cache_strict: ctx->direct_io = false; ctx->strict_io = true; ctx->cache_ro = false; ctx->cache_rw = false; break; case Opt_cache_none: ctx->direct_io = true; ctx->strict_io = false; ctx->cache_ro = false; ctx->cache_rw = false; break; case Opt_cache_ro: ctx->direct_io = false; ctx->strict_io = false; ctx->cache_ro = true; ctx->cache_rw = false; break; case Opt_cache_rw: ctx->direct_io = false; ctx->strict_io = false; ctx->cache_ro = false; ctx->cache_rw = true; break; default: cifs_errorf(fc, "bad cache= option: %s\n", value); return 1; } return 0; } static const match_table_t reparse_flavor_tokens = { { Opt_reparse_default, "default" }, { Opt_reparse_none, "none" }, { Opt_reparse_nfs, "nfs" }, { Opt_reparse_wsl, "wsl" }, { Opt_reparse_err, NULL }, }; static int parse_reparse_flavor(struct fs_context *fc, char *value, struct smb3_fs_context *ctx) { substring_t args[MAX_OPT_ARGS]; switch (match_token(value, reparse_flavor_tokens, args)) { case Opt_reparse_default: ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT; break; case Opt_reparse_none: ctx->reparse_type = CIFS_REPARSE_TYPE_NONE; break; case Opt_reparse_nfs: ctx->reparse_type = CIFS_REPARSE_TYPE_NFS; break; case Opt_reparse_wsl: ctx->reparse_type = CIFS_REPARSE_TYPE_WSL; break; default: cifs_errorf(fc, "bad reparse= option: %s\n", value); return 1; } return 0; } static const match_table_t symlink_flavor_tokens = { { Opt_symlink_default, "default" }, { Opt_symlink_none, "none" }, { Opt_symlink_native, "native" }, { Opt_symlink_unix, "unix" }, { Opt_symlink_mfsymlinks, "mfsymlinks" }, { Opt_symlink_sfu, "sfu" }, { Opt_symlink_nfs, "nfs" }, { Opt_symlink_wsl, "wsl" }, { Opt_symlink_err, NULL }, }; static int parse_symlink_flavor(struct fs_context *fc, char *value, struct smb3_fs_context *ctx) { substring_t args[MAX_OPT_ARGS]; switch (match_token(value, symlink_flavor_tokens, args)) { case Opt_symlink_default: ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT; break; case Opt_symlink_none: ctx->symlink_type = CIFS_SYMLINK_TYPE_NONE; break; case Opt_symlink_native: ctx->symlink_type = CIFS_SYMLINK_TYPE_NATIVE; break; case Opt_symlink_unix: ctx->symlink_type = CIFS_SYMLINK_TYPE_UNIX; break; case Opt_symlink_mfsymlinks: ctx->symlink_type = CIFS_SYMLINK_TYPE_MFSYMLINKS; break; case Opt_symlink_sfu: ctx->symlink_type = CIFS_SYMLINK_TYPE_SFU; break; case Opt_symlink_nfs: ctx->symlink_type = CIFS_SYMLINK_TYPE_NFS; break; case Opt_symlink_wsl: ctx->symlink_type = CIFS_SYMLINK_TYPE_WSL; break; default: cifs_errorf(fc, "bad symlink= option: %s\n", value); return 1; } return 0; } #define DUP_CTX_STR(field) \ do { \ if (ctx->field) { \ new_ctx->field = kstrdup(ctx->field, GFP_ATOMIC); \ if (new_ctx->field == NULL) { \ smb3_cleanup_fs_context_contents(new_ctx); \ return -ENOMEM; \ } \ } \ } while (0) int smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx) { memcpy(new_ctx, ctx, sizeof(*ctx)); new_ctx->prepath = NULL; new_ctx->nodename = NULL; new_ctx->username = NULL; new_ctx->password = NULL; new_ctx->password2 = NULL; new_ctx->server_hostname = NULL; new_ctx->domainname = NULL; new_ctx->UNC = NULL; new_ctx->source = NULL; new_ctx->iocharset = NULL; new_ctx->leaf_fullpath = NULL; new_ctx->dns_dom = NULL; new_ctx->symlinkroot = NULL; /* * Make sure to stay in sync with smb3_cleanup_fs_context_contents() */ DUP_CTX_STR(prepath); DUP_CTX_STR(username); DUP_CTX_STR(password); DUP_CTX_STR(password2); DUP_CTX_STR(server_hostname); DUP_CTX_STR(UNC); DUP_CTX_STR(source); DUP_CTX_STR(domainname); DUP_CTX_STR(nodename); DUP_CTX_STR(iocharset); DUP_CTX_STR(leaf_fullpath); DUP_CTX_STR(dns_dom); DUP_CTX_STR(symlinkroot); return 0; } static int cifs_parse_smb_version(struct fs_context *fc, char *value, struct smb3_fs_context *ctx, bool is_smb3) { substring_t args[MAX_OPT_ARGS]; switch (match_token(value, cifs_smb_version_tokens, args)) { #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY case Smb_1: if (disable_legacy_dialects) { cifs_errorf(fc, "mount with legacy dialect disabled\n"); return 1; } if (is_smb3) { cifs_errorf(fc, "vers=1.0 (cifs) not permitted when mounting with smb3\n"); return 1; } cifs_errorf(fc, "Use of the less secure dialect vers=1.0 is not recommended unless required for access to very old servers\n"); ctx->ops = &smb1_operations; ctx->vals = &smb1_values; break; case Smb_20: if (disable_legacy_dialects) { cifs_errorf(fc, "mount with legacy dialect disabled\n"); return 1; } if (is_smb3) { cifs_errorf(fc, "vers=2.0 not permitted when mounting with smb3\n"); return 1; } ctx->ops = &smb20_operations; ctx->vals = &smb20_values; break; #else case Smb_1: cifs_errorf(fc, "vers=1.0 (cifs) mount not permitted when legacy dialects disabled\n"); return 1; case Smb_20: cifs_errorf(fc, "vers=2.0 mount not permitted when legacy dialects disabled\n"); return 1; #endif /* CIFS_ALLOW_INSECURE_LEGACY */ case Smb_21: ctx->ops = &smb21_operations; ctx->vals = &smb21_values; break; case Smb_30: ctx->ops = &smb30_operations; ctx->vals = &smb30_values; break; case Smb_302: ctx->ops = &smb30_operations; /* currently identical with 3.0 */ ctx->vals = &smb302_values; break; case Smb_311: ctx->ops = &smb311_operations; ctx->vals = &smb311_values; break; case Smb_3any: ctx->ops = &smb30_operations; /* currently identical with 3.0 */ ctx->vals = &smb3any_values; break; case Smb_default: ctx->ops = &smb30_operations; ctx->vals = &smbdefault_values; break; default: cifs_errorf(fc, "Unknown vers= option specified: %s\n", value); return 1; } return 0; } int smb3_parse_opt(const char *options, const char *key, char **val) { int rc = -ENOENT; char *opts, *orig, *p; orig = opts = kstrdup(options, GFP_KERNEL); if (!opts) return -ENOMEM; while ((p = strsep(&opts, ","))) { char *nval; if (!*p) continue; if (strncasecmp(p, key, strlen(key))) continue; nval = strchr(p, '='); if (nval) { if (nval == p) continue; *nval++ = 0; *val = kstrdup(nval, GFP_KERNEL); rc = !*val ? -ENOMEM : 0; goto out; } } out: kfree(orig); return rc; } /* * Remove duplicate path delimiters. Windows is supposed to do that * but there are some bugs that prevent rename from working if there are * multiple delimiters. * * Return a sanitized duplicate of @path or NULL for empty prefix paths. * Otherwise, return ERR_PTR. * * @gfp indicates the GFP_* flags for kstrdup. * The caller is responsible for freeing the original. */ #define IS_DELIM(c) ((c) == '/' || (c) == '\\') char *cifs_sanitize_prepath(char *prepath, gfp_t gfp) { char *cursor1 = prepath, *cursor2 = prepath; char *s; /* skip all prepended delimiters */ while (IS_DELIM(*cursor1)) cursor1++; /* copy the first letter */ *cursor2 = *cursor1; /* copy the remainder... */ while (*(cursor1++)) { /* ... skipping all duplicated delimiters */ if (IS_DELIM(*cursor1) && IS_DELIM(*cursor2)) continue; *(++cursor2) = *cursor1; } /* if the last character is a delimiter, skip it */ if (IS_DELIM(*(cursor2 - 1))) cursor2--; *cursor2 = '\0'; if (!*prepath) return NULL; s = kstrdup(prepath, gfp); if (!s) return ERR_PTR(-ENOMEM); return s; } /* * Return full path based on the values of @ctx->{UNC,prepath}. * * It is assumed that both values were already parsed by smb3_parse_devname(). */ char *smb3_fs_context_fullpath(const struct smb3_fs_context *ctx, char dirsep) { size_t ulen, plen; char *s; ulen = strlen(ctx->UNC); plen = ctx->prepath ? strlen(ctx->prepath) + 1 : 0; s = kmalloc(ulen + plen + 1, GFP_KERNEL); if (!s) return ERR_PTR(-ENOMEM); memcpy(s, ctx->UNC, ulen); if (plen) { s[ulen] = dirsep; memcpy(s + ulen + 1, ctx->prepath, plen); } s[ulen + plen] = '\0'; convert_delimiter(s, dirsep); return s; } /* * Parse a devname into substrings and populate the ctx->UNC and ctx->prepath * fields with the result. Returns 0 on success and an error otherwise * (e.g. ENOMEM or EINVAL) */ int smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx) { char *pos; const char *delims = "/\\"; size_t len; int rc; if (unlikely(!devname || !*devname)) { cifs_dbg(VFS, "Device name not specified\n"); return -EINVAL; } /* make sure we have a valid UNC double delimiter prefix */ len = strspn(devname, delims); if (len != 2) return -EINVAL; /* find delimiter between host and sharename */ pos = strpbrk(devname + 2, delims); if (!pos) return -EINVAL; /* record the server hostname */ kfree(ctx->server_hostname); ctx->server_hostname = kstrndup(devname + 2, pos - devname - 2, GFP_KERNEL); if (!ctx->server_hostname) return -ENOMEM; /* skip past delimiter */ ++pos; /* now go until next delimiter or end of string */ len = strcspn(pos, delims); if (!len) return -EINVAL; /* move "pos" up to delimiter or NULL */ pos += len; kfree(ctx->UNC); ctx->UNC = kstrndup(devname, pos - devname, GFP_KERNEL); if (!ctx->UNC) return -ENOMEM; convert_delimiter(ctx->UNC, '\\'); /* skip any delimiter */ if (*pos == '/' || *pos == '\\') pos++; kfree(ctx->prepath); ctx->prepath = NULL; /* If pos is NULL then no prepath */ if (!*pos) return 0; ctx->prepath = cifs_sanitize_prepath(pos, GFP_KERNEL); if (IS_ERR(ctx->prepath)) { rc = PTR_ERR(ctx->prepath); ctx->prepath = NULL; return rc; } return 0; } static void smb3_fs_context_free(struct fs_context *fc); static int smb3_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param); static int smb3_fs_context_parse_monolithic(struct fs_context *fc, void *data); static int smb3_get_tree(struct fs_context *fc); static int smb3_reconfigure(struct fs_context *fc); static const struct fs_context_operations smb3_fs_context_ops = { .free = smb3_fs_context_free, .parse_param = smb3_fs_context_parse_param, .parse_monolithic = smb3_fs_context_parse_monolithic, .get_tree = smb3_get_tree, .reconfigure = smb3_reconfigure, }; /* * Parse a monolithic block of data from sys_mount(). * smb3_fs_context_parse_monolithic - Parse key[=val][,key[=val]]* mount data * @ctx: The superblock configuration to fill in. * @data: The data to parse * * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be * called from the ->monolithic_mount_data() fs_context operation. * * Returns 0 on success or the error returned by the ->parse_option() fs_context * operation on failure. */ static int smb3_fs_context_parse_monolithic(struct fs_context *fc, void *data) { char *options = data, *key; int ret = 0; if (!options) return 0; ret = security_sb_eat_lsm_opts(options, &fc->security); if (ret) return ret; /* BB Need to add support for sep= here TBD */ while ((key = strsep(&options, ",")) != NULL) { size_t len; char *value; if (*key == 0) break; /* Check if following character is the deliminator If yes, * we have encountered a double deliminator reset the NULL * character to the deliminator */ while (options && options[0] == ',') { len = strlen(key); strcpy(key + len, options); options = strchr(options, ','); if (options) *options++ = 0; } len = 0; value = strchr(key, '='); if (value) { if (value == key) continue; *value++ = 0; len = strlen(value); } ret = vfs_parse_fs_string(fc, key, value, len); if (ret < 0) break; } return ret; } /* * Validate the preparsed information in the config. */ static int smb3_fs_context_validate(struct fs_context *fc) { struct smb3_fs_context *ctx = smb3_fc2context(fc); if (ctx->rdma && ctx->vals->protocol_id < SMB30_PROT_ID) { cifs_errorf(fc, "SMB Direct requires Version >=3.0\n"); return -EOPNOTSUPP; } #ifndef CONFIG_KEYS /* Muliuser mounts require CONFIG_KEYS support */ if (ctx->multiuser) { cifs_errorf(fc, "Multiuser mounts require kernels with CONFIG_KEYS enabled\n"); return -1; } #endif if (ctx->got_version == false) pr_warn_once("No dialect specified on mount. Default has changed to a more secure dialect, SMB2.1 or later (e.g. SMB3.1.1), from CIFS (SMB1). To use the less secure SMB1 dialect to access old servers which do not support SMB3.1.1 (or even SMB3 or SMB2.1) specify vers=1.0 on mount.\n"); if (!ctx->UNC) { cifs_errorf(fc, "CIFS mount error: No usable UNC path provided in device string!\n"); return -1; } /* make sure UNC has a share name */ if (strlen(ctx->UNC) < 3 || !strchr(ctx->UNC + 3, '\\')) { cifs_errorf(fc, "Malformed UNC. Unable to find share name.\n"); return -ENOENT; } if (!ctx->got_ip) { int len; const char *slash; /* No ip= option specified? Try to get it from UNC */ /* Use the address part of the UNC. */ slash = strchr(&ctx->UNC[2], '\\'); len = slash - &ctx->UNC[2]; if (!cifs_convert_address((struct sockaddr *)&ctx->dstaddr, &ctx->UNC[2], len)) { pr_err("Unable to determine destination address\n"); return -EHOSTUNREACH; } } /* set the port that we got earlier */ cifs_set_port((struct sockaddr *)&ctx->dstaddr, ctx->port); if (ctx->uid_specified && !ctx->forceuid_specified) { ctx->override_uid = 1; pr_notice("enabling forceuid mount option implicitly because uid= option is specified\n"); } if (ctx->gid_specified && !ctx->forcegid_specified) { ctx->override_gid = 1; pr_notice("enabling forcegid mount option implicitly because gid= option is specified\n"); } if (ctx->override_uid && !ctx->uid_specified) { ctx->override_uid = 0; pr_notice("ignoring forceuid mount option specified with no uid= option\n"); } if (ctx->override_gid && !ctx->gid_specified) { ctx->override_gid = 0; pr_notice("ignoring forcegid mount option specified with no gid= option\n"); } return 0; } static int smb3_get_tree_common(struct fs_context *fc) { struct smb3_fs_context *ctx = smb3_fc2context(fc); struct dentry *root; int rc = 0; root = cifs_smb3_do_mount(fc->fs_type, 0, ctx); if (IS_ERR(root)) return PTR_ERR(root); fc->root = root; return rc; } /* * Create an SMB3 superblock from the parameters passed. */ static int smb3_get_tree(struct fs_context *fc) { int err = smb3_fs_context_validate(fc); int ret; if (err) return err; cifs_mount_lock(); ret = smb3_get_tree_common(fc); cifs_mount_unlock(); return ret; } static void smb3_fs_context_free(struct fs_context *fc) { struct smb3_fs_context *ctx = smb3_fc2context(fc); smb3_cleanup_fs_context(ctx); } /* * Compare the old and new proposed context during reconfigure * and check if the changes are compatible. */ static int smb3_verify_reconfigure_ctx(struct fs_context *fc, struct smb3_fs_context *new_ctx, struct smb3_fs_context *old_ctx, bool need_recon) { if (new_ctx->posix_paths != old_ctx->posix_paths) { cifs_errorf(fc, "can not change posixpaths during remount\n"); return -EINVAL; } if (new_ctx->sectype != old_ctx->sectype) { cifs_errorf(fc, "can not change sec during remount\n"); return -EINVAL; } if (new_ctx->multiuser != old_ctx->multiuser) { cifs_errorf(fc, "can not change multiuser during remount\n"); return -EINVAL; } if (new_ctx->UNC && (!old_ctx->UNC || strcmp(new_ctx->UNC, old_ctx->UNC))) { cifs_errorf(fc, "can not change UNC during remount\n"); return -EINVAL; } if (new_ctx->username && (!old_ctx->username || strcmp(new_ctx->username, old_ctx->username))) { cifs_errorf(fc, "can not change username during remount\n"); return -EINVAL; } if (new_ctx->password && (!old_ctx->password || strcmp(new_ctx->password, old_ctx->password))) { if (need_recon == false) { cifs_errorf(fc, "can not change password of active session during remount\n"); return -EINVAL; } else if (old_ctx->sectype == Kerberos) { cifs_errorf(fc, "can not change password for Kerberos via remount\n"); return -EINVAL; } } if (new_ctx->domainname && (!old_ctx->domainname || strcmp(new_ctx->domainname, old_ctx->domainname))) { cifs_errorf(fc, "can not change domainname during remount\n"); return -EINVAL; } if (strcmp(new_ctx->workstation_name, old_ctx->workstation_name)) { cifs_errorf(fc, "can not change workstation_name during remount\n"); return -EINVAL; } if (new_ctx->nodename && (!old_ctx->nodename || strcmp(new_ctx->nodename, old_ctx->nodename))) { cifs_errorf(fc, "can not change nodename during remount\n"); return -EINVAL; } if (new_ctx->iocharset && (!old_ctx->iocharset || strcmp(new_ctx->iocharset, old_ctx->iocharset))) { cifs_errorf(fc, "can not change iocharset during remount\n"); return -EINVAL; } return 0; } #define STEAL_STRING(cifs_sb, ctx, field) \ do { \ kfree(ctx->field); \ ctx->field = cifs_sb->ctx->field; \ cifs_sb->ctx->field = NULL; \ } while (0) #define STEAL_STRING_SENSITIVE(cifs_sb, ctx, field) \ do { \ kfree_sensitive(ctx->field); \ ctx->field = cifs_sb->ctx->field; \ cifs_sb->ctx->field = NULL; \ } while (0) int smb3_sync_session_ctx_passwords(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) { if (ses->password && cifs_sb->ctx->password && strcmp(ses->password, cifs_sb->ctx->password)) { kfree_sensitive(cifs_sb->ctx->password); cifs_sb->ctx->password = kstrdup(ses->password, GFP_KERNEL); if (!cifs_sb->ctx->password) return -ENOMEM; } if (ses->password2 && cifs_sb->ctx->password2 && strcmp(ses->password2, cifs_sb->ctx->password2)) { kfree_sensitive(cifs_sb->ctx->password2); cifs_sb->ctx->password2 = kstrdup(ses->password2, GFP_KERNEL); if (!cifs_sb->ctx->password2) { kfree_sensitive(cifs_sb->ctx->password); cifs_sb->ctx->password = NULL; return -ENOMEM; } } return 0; } static int smb3_reconfigure(struct fs_context *fc) { struct smb3_fs_context *ctx = smb3_fc2context(fc); struct dentry *root = fc->root; struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb); struct cifs_ses *ses = cifs_sb_master_tcon(cifs_sb)->ses; char *new_password = NULL, *new_password2 = NULL; bool need_recon = false; int rc; if (ses->expired_pwd) need_recon = true; rc = smb3_verify_reconfigure_ctx(fc, ctx, cifs_sb->ctx, need_recon); if (rc) return rc; /* * We can not change UNC/username/password/domainname/ * workstation_name/nodename/iocharset * during reconnect so ignore what we have in the new context and * just use what we already have in cifs_sb->ctx. */ STEAL_STRING(cifs_sb, ctx, UNC); STEAL_STRING(cifs_sb, ctx, source); STEAL_STRING(cifs_sb, ctx, username); if (need_recon == false) STEAL_STRING_SENSITIVE(cifs_sb, ctx, password); else { if (ctx->password) { new_password = kstrdup(ctx->password, GFP_KERNEL); if (!new_password) return -ENOMEM; } else STEAL_STRING_SENSITIVE(cifs_sb, ctx, password); } /* * if a new password2 has been specified, then reset it's value * inside the ses struct */ if (ctx->password2) { new_password2 = kstrdup(ctx->password2, GFP_KERNEL); if (!new_password2) { kfree_sensitive(new_password); return -ENOMEM; } } else STEAL_STRING_SENSITIVE(cifs_sb, ctx, password2); /* * we may update the passwords in the ses struct below. Make sure we do * not race with smb2_reconnect */ mutex_lock(&ses->session_mutex); /* * smb2_reconnect may swap password and password2 in case session setup * failed. First get ctx passwords in sync with ses passwords. It should * be okay to do this even if this function were to return an error at a * later stage */ rc = smb3_sync_session_ctx_passwords(cifs_sb, ses); if (rc) { mutex_unlock(&ses->session_mutex); return rc; } /* * now that allocations for passwords are done, commit them */ if (new_password) { kfree_sensitive(ses->password); ses->password = new_password; } if (new_password2) { kfree_sensitive(ses->password2); ses->password2 = new_password2; } mutex_unlock(&ses->session_mutex); STEAL_STRING(cifs_sb, ctx, domainname); STEAL_STRING(cifs_sb, ctx, nodename); STEAL_STRING(cifs_sb, ctx, iocharset); /* if rsize or wsize not passed in on remount, use previous values */ if (ctx->rsize == 0) ctx->rsize = cifs_sb->ctx->rsize; if (ctx->wsize == 0) ctx->wsize = cifs_sb->ctx->wsize; smb3_cleanup_fs_context_contents(cifs_sb->ctx); rc = smb3_fs_context_dup(cifs_sb->ctx, ctx); smb3_update_mnt_flags(cifs_sb); #ifdef CONFIG_CIFS_DFS_UPCALL if (!rc) rc = dfs_cache_remount_fs(cifs_sb); #endif return rc; } static int smb3_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; struct smb3_fs_context *ctx = smb3_fc2context(fc); int i, opt; bool is_smb3 = !strcmp(fc->fs_type->name, "smb3"); bool skip_parsing = false; cifs_dbg(FYI, "CIFS: parsing cifs mount option '%s'\n", param->key); /* * fs_parse can not handle string options with an empty value so * we will need special handling of them. */ if (param->type == fs_value_is_string && param->string[0] == 0) { if (!strcmp("pass", param->key) || !strcmp("password", param->key)) { skip_parsing = true; opt = Opt_pass; } else if (!strcmp("user", param->key) || !strcmp("username", param->key)) { skip_parsing = true; opt = Opt_user; } else if (!strcmp("pass2", param->key) || !strcmp("password2", param->key)) { skip_parsing = true; opt = Opt_pass2; } } if (!skip_parsing) { opt = fs_parse(fc, smb3_fs_parameters, param, &result); if (opt < 0) return ctx->sloppy ? 1 : opt; } switch (opt) { case Opt_compress: if (!IS_ENABLED(CONFIG_CIFS_COMPRESSION)) { cifs_errorf(fc, "CONFIG_CIFS_COMPRESSION kernel config option is unset\n"); goto cifs_parse_mount_err; } ctx->compress = true; cifs_dbg(VFS, "SMB3 compression support is experimental\n"); break; case Opt_nodfs: ctx->nodfs = 1; break; case Opt_hard: if (result.negated) { if (ctx->retry == 1) cifs_dbg(VFS, "conflicting hard vs. soft mount options\n"); ctx->retry = 0; } else ctx->retry = 1; break; case Opt_soft: if (result.negated) ctx->retry = 1; else { if (ctx->retry == 1) cifs_dbg(VFS, "conflicting hard vs soft mount options\n"); ctx->retry = 0; } break; case Opt_mapposix: if (result.negated) ctx->remap = false; else { ctx->remap = true; ctx->sfu_remap = false; /* disable SFU mapping */ } break; case Opt_mapchars: if (result.negated) ctx->sfu_remap = false; else { ctx->sfu_remap = true; ctx->remap = false; /* disable SFM (mapposix) mapping */ } break; case Opt_user_xattr: if (result.negated) ctx->no_xattr = 1; else ctx->no_xattr = 0; break; case Opt_forceuid: if (result.negated) ctx->override_uid = 0; else ctx->override_uid = 1; ctx->forceuid_specified = true; break; case Opt_forcegid: if (result.negated) ctx->override_gid = 0; else ctx->override_gid = 1; ctx->forcegid_specified = true; break; case Opt_perm: if (result.negated) ctx->noperm = 1; else ctx->noperm = 0; break; case Opt_dynperm: if (result.negated) ctx->dynperm = 0; else ctx->dynperm = 1; break; case Opt_sfu: if (result.negated) ctx->sfu_emul = 0; else ctx->sfu_emul = 1; break; case Opt_noblocksend: ctx->noblocksnd = 1; break; case Opt_noautotune: ctx->noautotune = 1; break; case Opt_nolease: ctx->no_lease = 1; break; case Opt_nosparse: ctx->no_sparse = 1; break; case Opt_nodelete: ctx->nodelete = 1; break; case Opt_multichannel: if (result.negated) { ctx->multichannel = false; ctx->max_channels = 1; } else { ctx->multichannel = true; /* if number of channels not specified, default to 2 */ if (ctx->max_channels < 2) ctx->max_channels = 2; } break; case Opt_uid: ctx->linux_uid = result.uid; ctx->uid_specified = true; break; case Opt_cruid: ctx->cred_uid = result.uid; ctx->cruid_specified = true; break; case Opt_backupuid: ctx->backupuid = result.uid; ctx->backupuid_specified = true; break; case Opt_backupgid: ctx->backupgid = result.gid; ctx->backupgid_specified = true; break; case Opt_gid: ctx->linux_gid = result.gid; ctx->gid_specified = true; break; case Opt_port: ctx->port = result.uint_32; break; case Opt_file_mode: ctx->file_mode = result.uint_32; break; case Opt_dirmode: ctx->dir_mode = result.uint_32; break; case Opt_min_enc_offload: ctx->min_offload = result.uint_32; break; case Opt_retrans: ctx->retrans = result.uint_32; break; case Opt_blocksize: /* * inode blocksize realistically should never need to be * less than 16K or greater than 16M and default is 1MB. * Note that small inode block sizes (e.g. 64K) can lead * to very poor performance of common tools like cp and scp */ if ((result.uint_32 < CIFS_MAX_MSGSIZE) || (result.uint_32 > (4 * SMB3_DEFAULT_IOSIZE))) { cifs_errorf(fc, "%s: Invalid blocksize\n", __func__); goto cifs_parse_mount_err; } ctx->bsize = result.uint_32; ctx->got_bsize = true; break; case Opt_rasize: /* * readahead size realistically should never need to be * less than 1M (CIFS_DEFAULT_IOSIZE) or greater than 32M * (perhaps an exception should be considered in the * for the case of a large number of channels * when multichannel is negotiated) since that would lead * to plenty of parallel I/O in flight to the server. * Note that smaller read ahead sizes would * hurt performance of common tools like cp and scp * which often trigger sequential i/o with read ahead */ if ((result.uint_32 > (8 * SMB3_DEFAULT_IOSIZE)) || (result.uint_32 < CIFS_DEFAULT_IOSIZE)) { cifs_errorf(fc, "%s: Invalid rasize %d vs. %d\n", __func__, result.uint_32, SMB3_DEFAULT_IOSIZE); goto cifs_parse_mount_err; } ctx->rasize = result.uint_32; break; case Opt_rsize: ctx->rsize = result.uint_32; ctx->got_rsize = true; break; case Opt_wsize: ctx->wsize = result.uint_32; ctx->got_wsize = true; if (ctx->wsize % PAGE_SIZE != 0) { ctx->wsize = round_down(ctx->wsize, PAGE_SIZE); if (ctx->wsize == 0) { ctx->wsize = PAGE_SIZE; cifs_dbg(VFS, "wsize too small, reset to minimum %ld\n", PAGE_SIZE); } else { cifs_dbg(VFS, "wsize rounded down to %d to multiple of PAGE_SIZE %ld\n", ctx->wsize, PAGE_SIZE); } } break; case Opt_acregmax: if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) { cifs_errorf(fc, "acregmax too large\n"); goto cifs_parse_mount_err; } ctx->acregmax = HZ * result.uint_32; break; case Opt_acdirmax: if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) { cifs_errorf(fc, "acdirmax too large\n"); goto cifs_parse_mount_err; } ctx->acdirmax = HZ * result.uint_32; break; case Opt_actimeo: if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) { cifs_errorf(fc, "timeout too large\n"); goto cifs_parse_mount_err; } if ((ctx->acdirmax != CIFS_DEF_ACTIMEO) || (ctx->acregmax != CIFS_DEF_ACTIMEO)) { cifs_errorf(fc, "actimeo ignored since acregmax or acdirmax specified\n"); break; } ctx->acdirmax = ctx->acregmax = HZ * result.uint_32; break; case Opt_closetimeo: if (result.uint_32 > SMB3_MAX_DCLOSETIMEO / HZ) { cifs_errorf(fc, "closetimeo too large\n"); goto cifs_parse_mount_err; } ctx->closetimeo = HZ * result.uint_32; break; case Opt_echo_interval: ctx->echo_interval = result.uint_32; break; case Opt_snapshot: ctx->snapshot_time = result.uint_64; break; case Opt_max_credits: if (result.uint_32 < 20 || result.uint_32 > 60000) { cifs_errorf(fc, "%s: Invalid max_credits value\n", __func__); goto cifs_parse_mount_err; } ctx->max_credits = result.uint_32; break; case Opt_max_channels: if (result.uint_32 < 1 || result.uint_32 > CIFS_MAX_CHANNELS) { cifs_errorf(fc, "%s: Invalid max_channels value, needs to be 1-%d\n", __func__, CIFS_MAX_CHANNELS); goto cifs_parse_mount_err; } ctx->max_channels = result.uint_32; /* If more than one channel requested ... they want multichan */ if (result.uint_32 > 1) ctx->multichannel = true; break; case Opt_max_cached_dirs: if (result.uint_32 < 1) { cifs_errorf(fc, "%s: Invalid max_cached_dirs, needs to be 1 or more\n", __func__); goto cifs_parse_mount_err; } ctx->max_cached_dirs = result.uint_32; break; case Opt_handletimeout: ctx->handle_timeout = result.uint_32; if (ctx->handle_timeout > SMB3_MAX_HANDLE_TIMEOUT) { cifs_errorf(fc, "Invalid handle cache timeout, longer than 16 minutes\n"); goto cifs_parse_mount_err; } break; case Opt_source: kfree(ctx->UNC); ctx->UNC = NULL; switch (smb3_parse_devname(param->string, ctx)) { case 0: break; case -ENOMEM: cifs_errorf(fc, "Unable to allocate memory for devname\n"); goto cifs_parse_mount_err; case -EINVAL: cifs_errorf(fc, "Malformed UNC in devname\n"); goto cifs_parse_mount_err; default: cifs_errorf(fc, "Unknown error parsing devname\n"); goto cifs_parse_mount_err; } ctx->source = smb3_fs_context_fullpath(ctx, '/'); if (IS_ERR(ctx->source)) { ctx->source = NULL; cifs_errorf(fc, "OOM when copying UNC string\n"); goto cifs_parse_mount_err; } fc->source = kstrdup(ctx->source, GFP_KERNEL); if (fc->source == NULL) { cifs_errorf(fc, "OOM when copying UNC string\n"); goto cifs_parse_mount_err; } break; case Opt_user: kfree(ctx->username); ctx->username = NULL; if (ctx->nullauth) break; if (strlen(param->string) == 0) { /* null user, ie. anonymous authentication */ ctx->nullauth = 1; break; } if (strnlen(param->string, CIFS_MAX_USERNAME_LEN) > CIFS_MAX_USERNAME_LEN) { pr_warn("username too long\n"); goto cifs_parse_mount_err; } ctx->username = kstrdup(param->string, GFP_KERNEL); if (ctx->username == NULL) { cifs_errorf(fc, "OOM when copying username string\n"); goto cifs_parse_mount_err; } break; case Opt_pass: kfree_sensitive(ctx->password); ctx->password = NULL; if (strlen(param->string) == 0) break; ctx->password = kstrdup(param->string, GFP_KERNEL); if (ctx->password == NULL) { cifs_errorf(fc, "OOM when copying password string\n"); goto cifs_parse_mount_err; } break; case Opt_pass2: kfree_sensitive(ctx->password2); ctx->password2 = NULL; if (strlen(param->string) == 0) break; ctx->password2 = kstrdup(param->string, GFP_KERNEL); if (ctx->password2 == NULL) { cifs_errorf(fc, "OOM when copying password2 string\n"); goto cifs_parse_mount_err; } break; case Opt_ip: if (strlen(param->string) == 0) { ctx->got_ip = false; break; } if (!cifs_convert_address((struct sockaddr *)&ctx->dstaddr, param->string, strlen(param->string))) { pr_err("bad ip= option (%s)\n", param->string); goto cifs_parse_mount_err; } ctx->got_ip = true; break; case Opt_domain: if (strnlen(param->string, CIFS_MAX_DOMAINNAME_LEN) == CIFS_MAX_DOMAINNAME_LEN) { pr_warn("domain name too long\n"); goto cifs_parse_mount_err; } kfree(ctx->domainname); ctx->domainname = kstrdup(param->string, GFP_KERNEL); if (ctx->domainname == NULL) { cifs_errorf(fc, "OOM when copying domainname string\n"); goto cifs_parse_mount_err; } cifs_dbg(FYI, "Domain name set\n"); break; case Opt_srcaddr: if (!cifs_convert_address( (struct sockaddr *)&ctx->srcaddr, param->string, strlen(param->string))) { pr_warn("Could not parse srcaddr: %s\n", param->string); goto cifs_parse_mount_err; } break; case Opt_iocharset: if (strnlen(param->string, 1024) >= 65) { pr_warn("iocharset name too long\n"); goto cifs_parse_mount_err; } if (strncasecmp(param->string, "default", 7) != 0) { kfree(ctx->iocharset); ctx->iocharset = kstrdup(param->string, GFP_KERNEL); if (ctx->iocharset == NULL) { cifs_errorf(fc, "OOM when copying iocharset string\n"); goto cifs_parse_mount_err; } } /* if iocharset not set then load_nls_default * is used by caller */ cifs_dbg(FYI, "iocharset set to %s\n", ctx->iocharset); break; case Opt_netbiosname: memset(ctx->source_rfc1001_name, 0x20, RFC1001_NAME_LEN); /* * FIXME: are there cases in which a comma can * be valid in workstation netbios name (and * need special handling)? */ for (i = 0; i < RFC1001_NAME_LEN; i++) { /* don't ucase netbiosname for user */ if (param->string[i] == 0) break; ctx->source_rfc1001_name[i] = param->string[i]; } /* The string has 16th byte zero still from * set at top of the function */ if (i == RFC1001_NAME_LEN && param->string[i] != 0) pr_warn("netbiosname longer than 15 truncated\n"); break; case Opt_servern: /* last byte, type, is 0x20 for servr type */ memset(ctx->target_rfc1001_name, 0x20, RFC1001_NAME_LEN_WITH_NULL); /* * BB are there cases in which a comma can be valid in this * workstation netbios name (and need special handling)? */ /* user or mount helper must uppercase the netbios name */ for (i = 0; i < 15; i++) { if (param->string[i] == 0) break; ctx->target_rfc1001_name[i] = param->string[i]; } /* The string has 16th byte zero still from set at top of function */ if (i == RFC1001_NAME_LEN && param->string[i] != 0) pr_warn("server netbiosname longer than 15 truncated\n"); break; case Opt_ver: /* version of mount userspace tools, not dialect */ /* If interface changes in mount.cifs bump to new ver */ if (strncasecmp(param->string, "1", 1) == 0) { if (strlen(param->string) > 1) { pr_warn("Bad mount helper ver=%s. Did you want SMB1 (CIFS) dialect and mean to type vers=1.0 instead?\n", param->string); goto cifs_parse_mount_err; } /* This is the default */ break; } /* For all other value, error */ pr_warn("Invalid mount helper version specified\n"); goto cifs_parse_mount_err; case Opt_vers: /* protocol version (dialect) */ if (cifs_parse_smb_version(fc, param->string, ctx, is_smb3) != 0) goto cifs_parse_mount_err; ctx->got_version = true; break; case Opt_sec: if (cifs_parse_security_flavors(fc, param->string, ctx) != 0) goto cifs_parse_mount_err; break; case Opt_upcalltarget: if (cifs_parse_upcall_target(fc, param->string, ctx) != 0) goto cifs_parse_mount_err; break; case Opt_cache: if (cifs_parse_cache_flavor(fc, param->string, ctx) != 0) goto cifs_parse_mount_err; break; case Opt_witness: #ifndef CONFIG_CIFS_SWN_UPCALL cifs_errorf(fc, "Witness support needs CONFIG_CIFS_SWN_UPCALL config option\n"); goto cifs_parse_mount_err; #endif ctx->witness = true; pr_warn_once("Witness protocol support is experimental\n"); break; case Opt_rootfs: #ifndef CONFIG_CIFS_ROOT cifs_dbg(VFS, "rootfs support requires CONFIG_CIFS_ROOT config option\n"); goto cifs_parse_mount_err; #endif ctx->rootfs = true; break; case Opt_posixpaths: if (result.negated) ctx->posix_paths = 0; else ctx->posix_paths = 1; break; case Opt_unix: if (result.negated) { if (ctx->linux_ext == 1) pr_warn_once("conflicting posix mount options specified\n"); ctx->linux_ext = 0; ctx->no_linux_ext = 1; } else { if (ctx->no_linux_ext == 1) pr_warn_once("conflicting posix mount options specified\n"); ctx->linux_ext = 1; ctx->no_linux_ext = 0; } break; case Opt_nocase: ctx->nocase = 1; break; case Opt_brl: if (result.negated) { /* * turn off mandatory locking in mode * if remote locking is turned off since the * local vfs will do advisory */ if (ctx->file_mode == (S_IALLUGO & ~(S_ISUID | S_IXGRP))) ctx->file_mode = S_IALLUGO; ctx->nobrl = 1; } else ctx->nobrl = 0; break; case Opt_handlecache: if (result.negated) ctx->nohandlecache = 1; else ctx->nohandlecache = 0; break; case Opt_forcemandatorylock: ctx->mand_lock = 1; break; case Opt_setuids: ctx->setuids = result.negated; break; case Opt_intr: ctx->intr = !result.negated; break; case Opt_setuidfromacl: ctx->setuidfromacl = 1; break; case Opt_strictsync: ctx->nostrictsync = result.negated; break; case Opt_serverino: ctx->server_ino = !result.negated; break; case Opt_rwpidforward: ctx->rwpidforward = 1; break; case Opt_modesid: ctx->mode_ace = 1; break; case Opt_cifsacl: ctx->cifs_acl = !result.negated; break; case Opt_acl: ctx->no_psx_acl = result.negated; break; case Opt_locallease: ctx->local_lease = 1; break; case Opt_sign: ctx->sign = true; break; case Opt_ignore_signature: ctx->sign = true; ctx->ignore_signature = true; break; case Opt_seal: /* we do not do the following in secFlags because seal * is a per tree connection (mount) not a per socket * or per-smb connection option in the protocol * vol->secFlg |= CIFSSEC_MUST_SEAL; */ ctx->seal = 1; break; case Opt_noac: pr_warn("Mount option noac not supported. Instead set /proc/fs/cifs/LookupCacheEnabled to 0\n"); break; case Opt_fsc: #ifndef CONFIG_CIFS_FSCACHE cifs_errorf(fc, "FS-Cache support needs CONFIG_CIFS_FSCACHE kernel config option set\n"); goto cifs_parse_mount_err; #endif ctx->fsc = true; break; case Opt_mfsymlinks: ctx->mfsymlinks = true; break; case Opt_multiuser: ctx->multiuser = true; break; case Opt_sloppy: ctx->sloppy = true; break; case Opt_nosharesock: ctx->nosharesock = true; break; case Opt_persistent: if (result.negated) { ctx->nopersistent = true; if (ctx->persistent) { cifs_errorf(fc, "persistenthandles mount options conflict\n"); goto cifs_parse_mount_err; } } else { ctx->persistent = true; if ((ctx->nopersistent) || (ctx->resilient)) { cifs_errorf(fc, "persistenthandles mount options conflict\n"); goto cifs_parse_mount_err; } } break; case Opt_resilient: if (result.negated) { ctx->resilient = false; /* already the default */ } else { ctx->resilient = true; if (ctx->persistent) { cifs_errorf(fc, "persistenthandles mount options conflict\n"); goto cifs_parse_mount_err; } } break; case Opt_tcp_nodelay: /* tcp nodelay should not usually be needed since we CORK/UNCORK the socket */ if (result.negated) ctx->sockopt_tcp_nodelay = false; else ctx->sockopt_tcp_nodelay = true; break; case Opt_domainauto: ctx->domainauto = true; break; case Opt_rdma: ctx->rdma = true; break; case Opt_reparse: if (parse_reparse_flavor(fc, param->string, ctx)) goto cifs_parse_mount_err; break; case Opt_nativesocket: ctx->nonativesocket = result.negated; break; case Opt_symlink: if (parse_symlink_flavor(fc, param->string, ctx)) goto cifs_parse_mount_err; break; case Opt_symlinkroot: if (param->string[0] != '/') { cifs_errorf(fc, "symlinkroot mount options must be absolute path\n"); goto cifs_parse_mount_err; } kfree(ctx->symlinkroot); ctx->symlinkroot = kstrdup(param->string, GFP_KERNEL); if (!ctx->symlinkroot) goto cifs_parse_mount_err; break; } /* case Opt_ignore: - is ignored as expected ... */ if (ctx->multiuser && ctx->upcall_target == UPTARGET_MOUNT) { cifs_errorf(fc, "multiuser mount option not supported with upcalltarget set as 'mount'\n"); goto cifs_parse_mount_err; } /* * By default resolve all native absolute symlinks relative to "/mnt/". * Same default has drvfs driver running in WSL for resolving SMB shares. */ if (!ctx->symlinkroot) ctx->symlinkroot = kstrdup("/mnt/", GFP_KERNEL); return 0; cifs_parse_mount_err: kfree_sensitive(ctx->password); ctx->password = NULL; kfree_sensitive(ctx->password2); ctx->password2 = NULL; return -EINVAL; } enum cifs_symlink_type get_cifs_symlink_type(struct cifs_sb_info *cifs_sb) { if (cifs_sb->ctx->symlink_type == CIFS_SYMLINK_TYPE_DEFAULT) { if (cifs_sb->ctx->mfsymlinks) return CIFS_SYMLINK_TYPE_MFSYMLINKS; else if (cifs_sb->ctx->sfu_emul) return CIFS_SYMLINK_TYPE_SFU; else if (cifs_sb->ctx->linux_ext && !cifs_sb->ctx->no_linux_ext) return CIFS_SYMLINK_TYPE_UNIX; else if (cifs_sb->ctx->reparse_type != CIFS_REPARSE_TYPE_NONE) return CIFS_SYMLINK_TYPE_NATIVE; else return CIFS_SYMLINK_TYPE_NONE; } else { return cifs_sb->ctx->symlink_type; } } int smb3_init_fs_context(struct fs_context *fc) { struct smb3_fs_context *ctx; char *nodename = utsname()->nodename; int i; ctx = kzalloc(sizeof(struct smb3_fs_context), GFP_KERNEL); if (unlikely(!ctx)) return -ENOMEM; strscpy(ctx->workstation_name, nodename, sizeof(ctx->workstation_name)); /* * does not have to be perfect mapping since field is * informational, only used for servers that do not support * port 445 and it can be overridden at mount time */ memset(ctx->source_rfc1001_name, 0x20, RFC1001_NAME_LEN); for (i = 0; i < strnlen(nodename, RFC1001_NAME_LEN); i++) ctx->source_rfc1001_name[i] = toupper(nodename[i]); ctx->source_rfc1001_name[RFC1001_NAME_LEN] = 0; /* * null target name indicates to use *SMBSERVR default called name * if we end up sending RFC1001 session initialize */ ctx->target_rfc1001_name[0] = 0; ctx->cred_uid = current_uid(); ctx->linux_uid = current_uid(); ctx->linux_gid = current_gid(); /* By default 4MB read ahead size, 1MB block size */ ctx->bsize = CIFS_DEFAULT_IOSIZE; /* can improve cp performance significantly */ ctx->rasize = 0; /* 0 = use default (ie negotiated rsize) for read ahead pages */ /* * default to SFM style remapping of seven reserved characters * unless user overrides it or we negotiate CIFS POSIX where * it is unnecessary. Can not simultaneously use more than one mapping * since then readdir could list files that open could not open */ ctx->remap = true; /* default to only allowing write access to owner of the mount */ ctx->dir_mode = ctx->file_mode = S_IRUGO | S_IXUGO | S_IWUSR; /* ctx->retry default is 0 (i.e. "soft" limited retry not hard retry) */ /* default is always to request posix paths. */ ctx->posix_paths = 1; /* default to using server inode numbers where available */ ctx->server_ino = 1; /* default is to use strict cifs caching semantics */ ctx->strict_io = true; ctx->acregmax = CIFS_DEF_ACTIMEO; ctx->acdirmax = CIFS_DEF_ACTIMEO; ctx->closetimeo = SMB3_DEF_DCLOSETIMEO; ctx->max_cached_dirs = MAX_CACHED_FIDS; /* Most clients set timeout to 0, allows server to use its default */ ctx->handle_timeout = 0; /* See MS-SMB2 spec section 2.2.14.2.12 */ /* offer SMB2.1 and later (SMB3 etc). Secure and widely accepted */ ctx->ops = &smb30_operations; ctx->vals = &smbdefault_values; ctx->echo_interval = SMB_ECHO_INTERVAL_DEFAULT; /* default to no multichannel (single server connection) */ ctx->multichannel = false; ctx->max_channels = 1; ctx->backupuid_specified = false; /* no backup intent for a user */ ctx->backupgid_specified = false; /* no backup intent for a group */ ctx->retrans = 1; ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT; ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT; ctx->nonativesocket = 0; /* * short int override_uid = -1; * short int override_gid = -1; * char *nodename = strdup(utsname()->nodename); * struct sockaddr *dstaddr = (struct sockaddr *)&vol->dstaddr; */ fc->fs_private = ctx; fc->ops = &smb3_fs_context_ops; return 0; } void smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx) { if (ctx == NULL) return; /* * Make sure this stays in sync with smb3_fs_context_dup() */ kfree(ctx->username); ctx->username = NULL; kfree_sensitive(ctx->password); ctx->password = NULL; kfree_sensitive(ctx->password2); ctx->password2 = NULL; kfree(ctx->server_hostname); ctx->server_hostname = NULL; kfree(ctx->UNC); ctx->UNC = NULL; kfree(ctx->source); ctx->source = NULL; kfree(ctx->domainname); ctx->domainname = NULL; kfree(ctx->nodename); ctx->nodename = NULL; kfree(ctx->iocharset); ctx->iocharset = NULL; kfree(ctx->prepath); ctx->prepath = NULL; kfree(ctx->leaf_fullpath); ctx->leaf_fullpath = NULL; kfree(ctx->dns_dom); ctx->dns_dom = NULL; kfree(ctx->symlinkroot); ctx->symlinkroot = NULL; } void smb3_cleanup_fs_context(struct smb3_fs_context *ctx) { if (!ctx) return; smb3_cleanup_fs_context_contents(ctx); kfree(ctx); } void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb) { struct smb3_fs_context *ctx = cifs_sb->ctx; if (ctx->nodfs) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_DFS; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_DFS; if (ctx->noperm) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_PERM; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_PERM; if (ctx->setuids) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SET_UID; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SET_UID; if (ctx->setuidfromacl) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UID_FROM_ACL; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_UID_FROM_ACL; if (ctx->server_ino) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SERVER_INUM; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM; if (ctx->remap) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SFM_CHR; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MAP_SFM_CHR; if (ctx->sfu_remap) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SPECIAL_CHR; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MAP_SPECIAL_CHR; if (ctx->no_xattr) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_XATTR; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_XATTR; if (ctx->sfu_emul) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UNX_EMUL; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_UNX_EMUL; if (ctx->nobrl) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_BRL; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_BRL; if (ctx->nohandlecache) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_HANDLE_CACHE; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_HANDLE_CACHE; if (ctx->nostrictsync) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOSSYNC; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NOSSYNC; if (ctx->mand_lock) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOPOSIXBRL; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NOPOSIXBRL; if (ctx->rwpidforward) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_RWPIDFORWARD; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_RWPIDFORWARD; if (ctx->mode_ace) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MODE_FROM_SID; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MODE_FROM_SID; if (ctx->cifs_acl) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_ACL; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_ACL; if (ctx->backupuid_specified) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPUID; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_BACKUPUID; if (ctx->backupgid_specified) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPGID; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_BACKUPGID; if (ctx->override_uid) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_UID; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_OVERR_UID; if (ctx->override_gid) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_GID; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_OVERR_GID; if (ctx->dynperm) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DYNPERM; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_DYNPERM; if (ctx->fsc) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_FSCACHE; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_FSCACHE; if (ctx->multiuser) cifs_sb->mnt_cifs_flags |= (CIFS_MOUNT_MULTIUSER | CIFS_MOUNT_NO_PERM); else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MULTIUSER; if (ctx->strict_io) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_STRICT_IO; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_STRICT_IO; if (ctx->direct_io) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DIRECT_IO; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_DIRECT_IO; if (ctx->mfsymlinks) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MF_SYMLINKS; else cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MF_SYMLINKS; if (ctx->mfsymlinks) { if (ctx->sfu_emul) { /* * Our SFU ("Services for Unix") emulation allows now * creating new and reading existing SFU symlinks. * Older Linux kernel versions were not able to neither * read existing nor create new SFU symlinks. But * creating and reading SFU style mknod and FIFOs was * supported for long time. When "mfsymlinks" and * "sfu" are both enabled at the same time, it allows * reading both types of symlinks, but will only create * them with mfsymlinks format. This allows better * Apple compatibility, compatibility with older Linux * kernel clients (probably better for Samba too) * while still recognizing old Windows style symlinks. */ cifs_dbg(VFS, "mount options mfsymlinks and sfu both enabled\n"); } } cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SHUTDOWN; return; } |
| 2 1 1 5 1 1 1 1 1 7 3 9 1 6 3 17 1 1 15 1 12 2 12 2 14 9 5 14 14 9 14 7 7 7 7 10 5 9 9 5 8 8 8 8 8 8 8 8 6 2 4 2 4 9 5 4 4 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_quota.h" #include "xfs_qm.h" #include "xfs_icache.h" int xfs_qm_scall_quotaoff( xfs_mount_t *mp, uint flags) { /* * No file system can have quotas enabled on disk but not in core. * Note that quota utilities (like quotaoff) _expect_ * errno == -EEXIST here. */ if ((mp->m_qflags & flags) == 0) return -EEXIST; /* * We do not support actually turning off quota accounting any more. * Just log a warning and ignore the accounting related flags. */ if (flags & XFS_ALL_QUOTA_ACCT) xfs_info(mp, "disabling of quota accounting not supported."); mutex_lock(&mp->m_quotainfo->qi_quotaofflock); mp->m_qflags &= ~(flags & XFS_ALL_QUOTA_ENFD); spin_lock(&mp->m_sb_lock); mp->m_sb.sb_qflags = mp->m_qflags; spin_unlock(&mp->m_sb_lock); mutex_unlock(&mp->m_quotainfo->qi_quotaofflock); /* XXX what to do if error ? Revert back to old vals incore ? */ return xfs_sync_sb(mp, false); } STATIC int xfs_qm_scall_trunc_qfile( struct xfs_mount *mp, xfs_dqtype_t type) { struct xfs_inode *ip; struct xfs_trans *tp; int error; error = xfs_qm_qino_load(mp, type, &ip); if (error == -ENOENT) return 0; if (error) return error; xfs_ilock(ip, XFS_IOLOCK_EXCL); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); if (error) { xfs_iunlock(ip, XFS_IOLOCK_EXCL); goto out_put; } xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); ip->i_disk_size = 0; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0); if (error) { xfs_trans_cancel(tp); goto out_unlock; } ASSERT(ip->i_df.if_nextents == 0); xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); error = xfs_trans_commit(tp); out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); out_put: xfs_irele(ip); return error; } int xfs_qm_scall_trunc_qfiles( xfs_mount_t *mp, uint flags) { int error = -EINVAL; if (!xfs_has_quota(mp) || flags == 0 || (flags & ~XFS_QMOPT_QUOTALL)) { xfs_debug(mp, "%s: flags=%x m_qflags=%x", __func__, flags, mp->m_qflags); return -EINVAL; } if (flags & XFS_QMOPT_UQUOTA) { error = xfs_qm_scall_trunc_qfile(mp, XFS_DQTYPE_USER); if (error) return error; } if (flags & XFS_QMOPT_GQUOTA) { error = xfs_qm_scall_trunc_qfile(mp, XFS_DQTYPE_GROUP); if (error) return error; } if (flags & XFS_QMOPT_PQUOTA) error = xfs_qm_scall_trunc_qfile(mp, XFS_DQTYPE_PROJ); return error; } /* * Switch on (a given) quota enforcement for a filesystem. This takes * effect immediately. * (Switching on quota accounting must be done at mount time.) */ int xfs_qm_scall_quotaon( xfs_mount_t *mp, uint flags) { int error; uint qf; /* * Switching on quota accounting must be done at mount time, * only consider quota enforcement stuff here. */ flags &= XFS_ALL_QUOTA_ENFD; if (flags == 0) { xfs_debug(mp, "%s: zero flags, m_qflags=%x", __func__, mp->m_qflags); return -EINVAL; } /* * Can't enforce without accounting. We check the superblock * qflags here instead of m_qflags because rootfs can have * quota acct on ondisk without m_qflags' knowing. */ if (((mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) == 0 && (flags & XFS_UQUOTA_ENFD)) || ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 && (flags & XFS_GQUOTA_ENFD)) || ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 && (flags & XFS_PQUOTA_ENFD))) { xfs_debug(mp, "%s: Can't enforce without acct, flags=%x sbflags=%x", __func__, flags, mp->m_sb.sb_qflags); return -EINVAL; } /* * If everything's up to-date incore, then don't waste time. */ if ((mp->m_qflags & flags) == flags) return -EEXIST; /* * Change sb_qflags on disk but not incore mp->qflags * if this is the root filesystem. */ spin_lock(&mp->m_sb_lock); qf = mp->m_sb.sb_qflags; mp->m_sb.sb_qflags = qf | flags; spin_unlock(&mp->m_sb_lock); /* * There's nothing to change if it's the same. */ if ((qf & flags) == flags) return -EEXIST; error = xfs_sync_sb(mp, false); if (error) return error; /* * If we aren't trying to switch on quota enforcement, we are done. */ if (((mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) != (mp->m_qflags & XFS_UQUOTA_ACCT)) || ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) != (mp->m_qflags & XFS_PQUOTA_ACCT)) || ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) != (mp->m_qflags & XFS_GQUOTA_ACCT))) return 0; if (!XFS_IS_QUOTA_ON(mp)) return -ESRCH; /* * Switch on quota enforcement in core. */ mutex_lock(&mp->m_quotainfo->qi_quotaofflock); mp->m_qflags |= (flags & XFS_ALL_QUOTA_ENFD); mutex_unlock(&mp->m_quotainfo->qi_quotaofflock); return 0; } #define XFS_QC_MASK (QC_LIMIT_MASK | QC_TIMER_MASK) /* * Adjust limits of this quota, and the defaults if passed in. Returns true * if the new limits made sense and were applied, false otherwise. */ static inline bool xfs_setqlim_limits( struct xfs_mount *mp, struct xfs_dquot_res *res, struct xfs_quota_limits *qlim, xfs_qcnt_t hard, xfs_qcnt_t soft, const char *tag) { /* The hard limit can't be less than the soft limit. */ if (hard != 0 && hard < soft) { xfs_debug(mp, "%shard %lld < %ssoft %lld", tag, hard, tag, soft); return false; } res->hardlimit = hard; res->softlimit = soft; if (qlim) { qlim->hard = hard; qlim->soft = soft; } return true; } static inline void xfs_setqlim_timer( struct xfs_mount *mp, struct xfs_dquot_res *res, struct xfs_quota_limits *qlim, s64 timer) { if (qlim) { /* Set the length of the default grace period. */ res->timer = xfs_dquot_set_grace_period(timer); qlim->time = res->timer; } else { /* Set the grace period expiration on a quota. */ res->timer = xfs_dquot_set_timeout(mp, timer); } } /* * Adjust quota limits, and start/stop timers accordingly. */ int xfs_qm_scall_setqlim( struct xfs_mount *mp, xfs_dqid_t id, xfs_dqtype_t type, struct qc_dqblk *newlim) { struct xfs_quotainfo *q = mp->m_quotainfo; struct xfs_dquot *dqp; struct xfs_trans *tp; struct xfs_def_quota *defq; struct xfs_dquot_res *res; struct xfs_quota_limits *qlim; int error; xfs_qcnt_t hard, soft; if (newlim->d_fieldmask & ~XFS_QC_MASK) return -EINVAL; if ((newlim->d_fieldmask & XFS_QC_MASK) == 0) return 0; /* * Get the dquot (locked) before we start, as we need to do a * transaction to allocate it if it doesn't exist. Once we have the * dquot, unlock it so we can start the next transaction safely. We hold * a reference to the dquot, so it's safe to do this unlock/lock without * it being reclaimed in the mean time. */ error = xfs_qm_dqget(mp, id, type, true, &dqp); if (error) { ASSERT(error != -ENOENT); return error; } defq = xfs_get_defquota(q, xfs_dquot_type(dqp)); xfs_dqunlock(dqp); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_setqlim, 0, 0, 0, &tp); if (error) goto out_rele; xfs_dqlock(dqp); xfs_trans_dqjoin(tp, dqp); /* * Update quota limits, warnings, and timers, and the defaults * if we're touching id == 0. * * Make sure that hardlimits are >= soft limits before changing. * * Update warnings counter(s) if requested. * * Timelimits for the super user set the relative time the other users * can be over quota for this file system. If it is zero a default is * used. Ditto for the default soft and hard limit values (already * done, above), and for warnings. * * For other IDs, userspace can bump out the grace period if over * the soft limit. */ /* Blocks on the data device. */ hard = (newlim->d_fieldmask & QC_SPC_HARD) ? (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_hardlimit) : dqp->q_blk.hardlimit; soft = (newlim->d_fieldmask & QC_SPC_SOFT) ? (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_softlimit) : dqp->q_blk.softlimit; res = &dqp->q_blk; qlim = id == 0 ? &defq->blk : NULL; if (xfs_setqlim_limits(mp, res, qlim, hard, soft, "blk")) xfs_dquot_set_prealloc_limits(dqp); if (newlim->d_fieldmask & QC_SPC_TIMER) xfs_setqlim_timer(mp, res, qlim, newlim->d_spc_timer); /* Blocks on the realtime device. */ hard = (newlim->d_fieldmask & QC_RT_SPC_HARD) ? (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_hardlimit) : dqp->q_rtb.hardlimit; soft = (newlim->d_fieldmask & QC_RT_SPC_SOFT) ? (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_softlimit) : dqp->q_rtb.softlimit; res = &dqp->q_rtb; qlim = id == 0 ? &defq->rtb : NULL; xfs_setqlim_limits(mp, res, qlim, hard, soft, "rtb"); if (newlim->d_fieldmask & QC_RT_SPC_TIMER) xfs_setqlim_timer(mp, res, qlim, newlim->d_rt_spc_timer); /* Inodes */ hard = (newlim->d_fieldmask & QC_INO_HARD) ? (xfs_qcnt_t) newlim->d_ino_hardlimit : dqp->q_ino.hardlimit; soft = (newlim->d_fieldmask & QC_INO_SOFT) ? (xfs_qcnt_t) newlim->d_ino_softlimit : dqp->q_ino.softlimit; res = &dqp->q_ino; qlim = id == 0 ? &defq->ino : NULL; xfs_setqlim_limits(mp, res, qlim, hard, soft, "ino"); if (newlim->d_fieldmask & QC_INO_TIMER) xfs_setqlim_timer(mp, res, qlim, newlim->d_ino_timer); if (id != 0) { /* * If the user is now over quota, start the timelimit. * The user will not be 'warned'. * Note that we keep the timers ticking, whether enforcement * is on or off. We don't really want to bother with iterating * over all ondisk dquots and turning the timers on/off. */ xfs_qm_adjust_dqtimers(dqp); } dqp->q_flags |= XFS_DQFLAG_DIRTY; xfs_trans_log_dquot(tp, dqp); error = xfs_trans_commit(tp); out_rele: xfs_qm_dqrele(dqp); return error; } /* Fill out the quota context. */ static void xfs_qm_scall_getquota_fill_qc( struct xfs_mount *mp, xfs_dqtype_t type, const struct xfs_dquot *dqp, struct qc_dqblk *dst) { memset(dst, 0, sizeof(*dst)); dst->d_spc_hardlimit = XFS_FSB_TO_B(mp, dqp->q_blk.hardlimit); dst->d_spc_softlimit = XFS_FSB_TO_B(mp, dqp->q_blk.softlimit); dst->d_ino_hardlimit = dqp->q_ino.hardlimit; dst->d_ino_softlimit = dqp->q_ino.softlimit; dst->d_space = XFS_FSB_TO_B(mp, dqp->q_blk.reserved); dst->d_ino_count = dqp->q_ino.reserved; dst->d_spc_timer = dqp->q_blk.timer; dst->d_ino_timer = dqp->q_ino.timer; dst->d_ino_warns = 0; dst->d_spc_warns = 0; dst->d_rt_spc_hardlimit = XFS_FSB_TO_B(mp, dqp->q_rtb.hardlimit); dst->d_rt_spc_softlimit = XFS_FSB_TO_B(mp, dqp->q_rtb.softlimit); dst->d_rt_space = XFS_FSB_TO_B(mp, dqp->q_rtb.reserved); dst->d_rt_spc_timer = dqp->q_rtb.timer; dst->d_rt_spc_warns = 0; /* * Internally, we don't reset all the timers when quota enforcement * gets turned off. No need to confuse the user level code, * so return zeroes in that case. */ if (!xfs_dquot_is_enforced(dqp)) { dst->d_spc_timer = 0; dst->d_ino_timer = 0; dst->d_rt_spc_timer = 0; } } /* Return the quota information for the dquot matching id. */ int xfs_qm_scall_getquota( struct xfs_mount *mp, xfs_dqid_t id, xfs_dqtype_t type, struct qc_dqblk *dst) { struct xfs_dquot *dqp; int error; /* * Expedite pending inodegc work at the start of a quota reporting * scan but don't block waiting for it to complete. */ if (id == 0) xfs_inodegc_push(mp); /* * Try to get the dquot. We don't want it allocated on disk, so don't * set doalloc. If it doesn't exist, we'll get ENOENT back. */ error = xfs_qm_dqget(mp, id, type, false, &dqp); if (error) return error; /* * If everything's NULL, this dquot doesn't quite exist as far as * our utility programs are concerned. */ if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) { error = -ENOENT; goto out_put; } xfs_qm_scall_getquota_fill_qc(mp, type, dqp, dst); out_put: xfs_qm_dqput(dqp); return error; } /* * Return the quota information for the first initialized dquot whose id * is at least as high as id. */ int xfs_qm_scall_getquota_next( struct xfs_mount *mp, xfs_dqid_t *id, xfs_dqtype_t type, struct qc_dqblk *dst) { struct xfs_dquot *dqp; int error; /* Flush inodegc work at the start of a quota reporting scan. */ if (*id == 0) xfs_inodegc_push(mp); error = xfs_qm_dqget_next(mp, *id, type, &dqp); if (error) return error; /* Fill in the ID we actually read from disk */ *id = dqp->q_id; xfs_qm_scall_getquota_fill_qc(mp, type, dqp, dst); xfs_qm_dqput(dqp); return error; } |
| 1 1 1 1 1 1 5 6 1 1 1 1 1 2 1 1 1 1 1 1 1 1 7 1 3 1 1 3 3 3 8 2 6 2 1 1 2 1 1 4 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 | // SPDX-License-Identifier: GPL-2.0-or-later /* * User-space I/O driver support for HID subsystem * Copyright (c) 2012 David Herrmann */ /* */ #include <linux/atomic.h> #include <linux/compat.h> #include <linux/cred.h> #include <linux/device.h> #include <linux/fs.h> #include <linux/hid.h> #include <linux/input.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/uhid.h> #include <linux/wait.h> #define UHID_NAME "uhid" #define UHID_BUFSIZE 32 struct uhid_device { struct mutex devlock; /* This flag tracks whether the HID device is usable for commands from * userspace. The flag is already set before hid_add_device(), which * runs in workqueue context, to allow hid_add_device() to communicate * with userspace. * However, if hid_add_device() fails, the flag is cleared without * holding devlock. * We guarantee that if @running changes from true to false while you're * holding @devlock, it's still fine to access @hid. */ bool running; __u8 *rd_data; uint rd_size; /* When this is NULL, userspace may use UHID_CREATE/UHID_CREATE2. */ struct hid_device *hid; struct uhid_event input_buf; wait_queue_head_t waitq; spinlock_t qlock; __u8 head; __u8 tail; struct uhid_event *outq[UHID_BUFSIZE]; /* blocking GET_REPORT support; state changes protected by qlock */ struct mutex report_lock; wait_queue_head_t report_wait; bool report_running; u32 report_id; u32 report_type; struct uhid_event report_buf; struct work_struct worker; }; static struct miscdevice uhid_misc; static void uhid_device_add_worker(struct work_struct *work) { struct uhid_device *uhid = container_of(work, struct uhid_device, worker); int ret; ret = hid_add_device(uhid->hid); if (ret) { hid_err(uhid->hid, "Cannot register HID device: error %d\n", ret); /* We used to call hid_destroy_device() here, but that's really * messy to get right because we have to coordinate with * concurrent writes from userspace that might be in the middle * of using uhid->hid. * Just leave uhid->hid as-is for now, and clean it up when * userspace tries to close or reinitialize the uhid instance. * * However, we do have to clear the ->running flag and do a * wakeup to make sure userspace knows that the device is gone. */ WRITE_ONCE(uhid->running, false); wake_up_interruptible(&uhid->report_wait); } } static void uhid_queue(struct uhid_device *uhid, struct uhid_event *ev) { __u8 newhead; newhead = (uhid->head + 1) % UHID_BUFSIZE; if (newhead != uhid->tail) { uhid->outq[uhid->head] = ev; uhid->head = newhead; wake_up_interruptible(&uhid->waitq); } else { hid_warn(uhid->hid, "Output queue is full\n"); kfree(ev); } } static int uhid_queue_event(struct uhid_device *uhid, __u32 event) { unsigned long flags; struct uhid_event *ev; ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) return -ENOMEM; ev->type = event; spin_lock_irqsave(&uhid->qlock, flags); uhid_queue(uhid, ev); spin_unlock_irqrestore(&uhid->qlock, flags); return 0; } static int uhid_hid_start(struct hid_device *hid) { struct uhid_device *uhid = hid->driver_data; struct uhid_event *ev; unsigned long flags; ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) return -ENOMEM; ev->type = UHID_START; if (hid->report_enum[HID_FEATURE_REPORT].numbered) ev->u.start.dev_flags |= UHID_DEV_NUMBERED_FEATURE_REPORTS; if (hid->report_enum[HID_OUTPUT_REPORT].numbered) ev->u.start.dev_flags |= UHID_DEV_NUMBERED_OUTPUT_REPORTS; if (hid->report_enum[HID_INPUT_REPORT].numbered) ev->u.start.dev_flags |= UHID_DEV_NUMBERED_INPUT_REPORTS; spin_lock_irqsave(&uhid->qlock, flags); uhid_queue(uhid, ev); spin_unlock_irqrestore(&uhid->qlock, flags); return 0; } static void uhid_hid_stop(struct hid_device *hid) { struct uhid_device *uhid = hid->driver_data; hid->claimed = 0; uhid_queue_event(uhid, UHID_STOP); } static int uhid_hid_open(struct hid_device *hid) { struct uhid_device *uhid = hid->driver_data; return uhid_queue_event(uhid, UHID_OPEN); } static void uhid_hid_close(struct hid_device *hid) { struct uhid_device *uhid = hid->driver_data; uhid_queue_event(uhid, UHID_CLOSE); } static int uhid_hid_parse(struct hid_device *hid) { struct uhid_device *uhid = hid->driver_data; return hid_parse_report(hid, uhid->rd_data, uhid->rd_size); } /* must be called with report_lock held */ static int __uhid_report_queue_and_wait(struct uhid_device *uhid, struct uhid_event *ev, __u32 *report_id) { unsigned long flags; int ret; spin_lock_irqsave(&uhid->qlock, flags); *report_id = ++uhid->report_id; uhid->report_type = ev->type + 1; uhid->report_running = true; uhid_queue(uhid, ev); spin_unlock_irqrestore(&uhid->qlock, flags); ret = wait_event_interruptible_timeout(uhid->report_wait, !uhid->report_running || !READ_ONCE(uhid->running), 5 * HZ); if (!ret || !READ_ONCE(uhid->running) || uhid->report_running) ret = -EIO; else if (ret < 0) ret = -ERESTARTSYS; else ret = 0; uhid->report_running = false; return ret; } static void uhid_report_wake_up(struct uhid_device *uhid, u32 id, const struct uhid_event *ev) { unsigned long flags; spin_lock_irqsave(&uhid->qlock, flags); /* id for old report; drop it silently */ if (uhid->report_type != ev->type || uhid->report_id != id) goto unlock; if (!uhid->report_running) goto unlock; memcpy(&uhid->report_buf, ev, sizeof(*ev)); uhid->report_running = false; wake_up_interruptible(&uhid->report_wait); unlock: spin_unlock_irqrestore(&uhid->qlock, flags); } static int uhid_hid_get_report(struct hid_device *hid, unsigned char rnum, u8 *buf, size_t count, u8 rtype) { struct uhid_device *uhid = hid->driver_data; struct uhid_get_report_reply_req *req; struct uhid_event *ev; int ret; if (!READ_ONCE(uhid->running)) return -EIO; ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) return -ENOMEM; ev->type = UHID_GET_REPORT; ev->u.get_report.rnum = rnum; ev->u.get_report.rtype = rtype; ret = mutex_lock_interruptible(&uhid->report_lock); if (ret) { kfree(ev); return ret; } /* this _always_ takes ownership of @ev */ ret = __uhid_report_queue_and_wait(uhid, ev, &ev->u.get_report.id); if (ret) goto unlock; req = &uhid->report_buf.u.get_report_reply; if (req->err) { ret = -EIO; } else { ret = min3(count, (size_t)req->size, (size_t)UHID_DATA_MAX); memcpy(buf, req->data, ret); } unlock: mutex_unlock(&uhid->report_lock); return ret; } static int uhid_hid_set_report(struct hid_device *hid, unsigned char rnum, const u8 *buf, size_t count, u8 rtype) { struct uhid_device *uhid = hid->driver_data; struct uhid_event *ev; int ret; if (!READ_ONCE(uhid->running) || count > UHID_DATA_MAX) return -EIO; ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) return -ENOMEM; ev->type = UHID_SET_REPORT; ev->u.set_report.rnum = rnum; ev->u.set_report.rtype = rtype; ev->u.set_report.size = count; memcpy(ev->u.set_report.data, buf, count); ret = mutex_lock_interruptible(&uhid->report_lock); if (ret) { kfree(ev); return ret; } /* this _always_ takes ownership of @ev */ ret = __uhid_report_queue_and_wait(uhid, ev, &ev->u.set_report.id); if (ret) goto unlock; if (uhid->report_buf.u.set_report_reply.err) ret = -EIO; else ret = count; unlock: mutex_unlock(&uhid->report_lock); return ret; } static int uhid_hid_raw_request(struct hid_device *hid, unsigned char reportnum, __u8 *buf, size_t len, unsigned char rtype, int reqtype) { u8 u_rtype; switch (rtype) { case HID_FEATURE_REPORT: u_rtype = UHID_FEATURE_REPORT; break; case HID_OUTPUT_REPORT: u_rtype = UHID_OUTPUT_REPORT; break; case HID_INPUT_REPORT: u_rtype = UHID_INPUT_REPORT; break; default: return -EINVAL; } switch (reqtype) { case HID_REQ_GET_REPORT: return uhid_hid_get_report(hid, reportnum, buf, len, u_rtype); case HID_REQ_SET_REPORT: return uhid_hid_set_report(hid, reportnum, buf, len, u_rtype); default: return -EIO; } } static int uhid_hid_output_raw(struct hid_device *hid, __u8 *buf, size_t count, unsigned char report_type) { struct uhid_device *uhid = hid->driver_data; __u8 rtype; unsigned long flags; struct uhid_event *ev; switch (report_type) { case HID_FEATURE_REPORT: rtype = UHID_FEATURE_REPORT; break; case HID_OUTPUT_REPORT: rtype = UHID_OUTPUT_REPORT; break; default: return -EINVAL; } if (count < 1 || count > UHID_DATA_MAX) return -EINVAL; ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) return -ENOMEM; ev->type = UHID_OUTPUT; ev->u.output.size = count; ev->u.output.rtype = rtype; memcpy(ev->u.output.data, buf, count); spin_lock_irqsave(&uhid->qlock, flags); uhid_queue(uhid, ev); spin_unlock_irqrestore(&uhid->qlock, flags); return count; } static int uhid_hid_output_report(struct hid_device *hid, __u8 *buf, size_t count) { return uhid_hid_output_raw(hid, buf, count, HID_OUTPUT_REPORT); } static const struct hid_ll_driver uhid_hid_driver = { .start = uhid_hid_start, .stop = uhid_hid_stop, .open = uhid_hid_open, .close = uhid_hid_close, .parse = uhid_hid_parse, .raw_request = uhid_hid_raw_request, .output_report = uhid_hid_output_report, .max_buffer_size = UHID_DATA_MAX, }; #ifdef CONFIG_COMPAT /* Apparently we haven't stepped on these rakes enough times yet. */ struct uhid_create_req_compat { __u8 name[128]; __u8 phys[64]; __u8 uniq[64]; compat_uptr_t rd_data; __u16 rd_size; __u16 bus; __u32 vendor; __u32 product; __u32 version; __u32 country; } __attribute__((__packed__)); static int uhid_event_from_user(const char __user *buffer, size_t len, struct uhid_event *event) { if (in_compat_syscall()) { u32 type; if (get_user(type, buffer)) return -EFAULT; if (type == UHID_CREATE) { /* * This is our messed up request with compat pointer. * It is largish (more than 256 bytes) so we better * allocate it from the heap. */ struct uhid_create_req_compat *compat; compat = kzalloc(sizeof(*compat), GFP_KERNEL); if (!compat) return -ENOMEM; buffer += sizeof(type); len -= sizeof(type); if (copy_from_user(compat, buffer, min(len, sizeof(*compat)))) { kfree(compat); return -EFAULT; } /* Shuffle the data over to proper structure */ event->type = type; memcpy(event->u.create.name, compat->name, sizeof(compat->name)); memcpy(event->u.create.phys, compat->phys, sizeof(compat->phys)); memcpy(event->u.create.uniq, compat->uniq, sizeof(compat->uniq)); event->u.create.rd_data = compat_ptr(compat->rd_data); event->u.create.rd_size = compat->rd_size; event->u.create.bus = compat->bus; event->u.create.vendor = compat->vendor; event->u.create.product = compat->product; event->u.create.version = compat->version; event->u.create.country = compat->country; kfree(compat); return 0; } /* All others can be copied directly */ } if (copy_from_user(event, buffer, min(len, sizeof(*event)))) return -EFAULT; return 0; } #else static int uhid_event_from_user(const char __user *buffer, size_t len, struct uhid_event *event) { if (copy_from_user(event, buffer, min(len, sizeof(*event)))) return -EFAULT; return 0; } #endif static int uhid_dev_create2(struct uhid_device *uhid, const struct uhid_event *ev) { struct hid_device *hid; size_t rd_size; void *rd_data; int ret; if (uhid->hid) return -EALREADY; rd_size = ev->u.create2.rd_size; if (rd_size <= 0 || rd_size > HID_MAX_DESCRIPTOR_SIZE) return -EINVAL; rd_data = kmemdup(ev->u.create2.rd_data, rd_size, GFP_KERNEL); if (!rd_data) return -ENOMEM; uhid->rd_size = rd_size; uhid->rd_data = rd_data; hid = hid_allocate_device(); if (IS_ERR(hid)) { ret = PTR_ERR(hid); goto err_free; } BUILD_BUG_ON(sizeof(hid->name) != sizeof(ev->u.create2.name)); strscpy(hid->name, ev->u.create2.name, sizeof(hid->name)); BUILD_BUG_ON(sizeof(hid->phys) != sizeof(ev->u.create2.phys)); strscpy(hid->phys, ev->u.create2.phys, sizeof(hid->phys)); BUILD_BUG_ON(sizeof(hid->uniq) != sizeof(ev->u.create2.uniq)); strscpy(hid->uniq, ev->u.create2.uniq, sizeof(hid->uniq)); hid->ll_driver = &uhid_hid_driver; hid->bus = ev->u.create2.bus; hid->vendor = ev->u.create2.vendor; hid->product = ev->u.create2.product; hid->version = ev->u.create2.version; hid->country = ev->u.create2.country; hid->driver_data = uhid; hid->dev.parent = uhid_misc.this_device; uhid->hid = hid; uhid->running = true; /* Adding of a HID device is done through a worker, to allow HID drivers * which use feature requests during .probe to work, without they would * be blocked on devlock, which is held by uhid_char_write. */ schedule_work(&uhid->worker); return 0; err_free: kfree(uhid->rd_data); uhid->rd_data = NULL; uhid->rd_size = 0; return ret; } static int uhid_dev_create(struct uhid_device *uhid, struct uhid_event *ev) { struct uhid_create_req orig; orig = ev->u.create; if (orig.rd_size <= 0 || orig.rd_size > HID_MAX_DESCRIPTOR_SIZE) return -EINVAL; if (copy_from_user(&ev->u.create2.rd_data, orig.rd_data, orig.rd_size)) return -EFAULT; memcpy(ev->u.create2.name, orig.name, sizeof(orig.name)); memcpy(ev->u.create2.phys, orig.phys, sizeof(orig.phys)); memcpy(ev->u.create2.uniq, orig.uniq, sizeof(orig.uniq)); ev->u.create2.rd_size = orig.rd_size; ev->u.create2.bus = orig.bus; ev->u.create2.vendor = orig.vendor; ev->u.create2.product = orig.product; ev->u.create2.version = orig.version; ev->u.create2.country = orig.country; return uhid_dev_create2(uhid, ev); } static int uhid_dev_destroy(struct uhid_device *uhid) { if (!uhid->hid) return -EINVAL; WRITE_ONCE(uhid->running, false); wake_up_interruptible(&uhid->report_wait); cancel_work_sync(&uhid->worker); hid_destroy_device(uhid->hid); uhid->hid = NULL; kfree(uhid->rd_data); return 0; } static int uhid_dev_input(struct uhid_device *uhid, struct uhid_event *ev) { if (!READ_ONCE(uhid->running)) return -EINVAL; hid_input_report(uhid->hid, HID_INPUT_REPORT, ev->u.input.data, min_t(size_t, ev->u.input.size, UHID_DATA_MAX), 0); return 0; } static int uhid_dev_input2(struct uhid_device *uhid, struct uhid_event *ev) { if (!READ_ONCE(uhid->running)) return -EINVAL; hid_input_report(uhid->hid, HID_INPUT_REPORT, ev->u.input2.data, min_t(size_t, ev->u.input2.size, UHID_DATA_MAX), 0); return 0; } static int uhid_dev_get_report_reply(struct uhid_device *uhid, struct uhid_event *ev) { if (!READ_ONCE(uhid->running)) return -EINVAL; uhid_report_wake_up(uhid, ev->u.get_report_reply.id, ev); return 0; } static int uhid_dev_set_report_reply(struct uhid_device *uhid, struct uhid_event *ev) { if (!READ_ONCE(uhid->running)) return -EINVAL; uhid_report_wake_up(uhid, ev->u.set_report_reply.id, ev); return 0; } static int uhid_char_open(struct inode *inode, struct file *file) { struct uhid_device *uhid; uhid = kzalloc(sizeof(*uhid), GFP_KERNEL); if (!uhid) return -ENOMEM; mutex_init(&uhid->devlock); mutex_init(&uhid->report_lock); spin_lock_init(&uhid->qlock); init_waitqueue_head(&uhid->waitq); init_waitqueue_head(&uhid->report_wait); uhid->running = false; INIT_WORK(&uhid->worker, uhid_device_add_worker); file->private_data = uhid; stream_open(inode, file); return 0; } static int uhid_char_release(struct inode *inode, struct file *file) { struct uhid_device *uhid = file->private_data; unsigned int i; uhid_dev_destroy(uhid); for (i = 0; i < UHID_BUFSIZE; ++i) kfree(uhid->outq[i]); kfree(uhid); return 0; } static ssize_t uhid_char_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct uhid_device *uhid = file->private_data; int ret; unsigned long flags; size_t len; /* they need at least the "type" member of uhid_event */ if (count < sizeof(__u32)) return -EINVAL; try_again: if (file->f_flags & O_NONBLOCK) { if (uhid->head == uhid->tail) return -EAGAIN; } else { ret = wait_event_interruptible(uhid->waitq, uhid->head != uhid->tail); if (ret) return ret; } ret = mutex_lock_interruptible(&uhid->devlock); if (ret) return ret; if (uhid->head == uhid->tail) { mutex_unlock(&uhid->devlock); goto try_again; } else { len = min(count, sizeof(**uhid->outq)); if (copy_to_user(buffer, uhid->outq[uhid->tail], len)) { ret = -EFAULT; } else { kfree(uhid->outq[uhid->tail]); uhid->outq[uhid->tail] = NULL; spin_lock_irqsave(&uhid->qlock, flags); uhid->tail = (uhid->tail + 1) % UHID_BUFSIZE; spin_unlock_irqrestore(&uhid->qlock, flags); } } mutex_unlock(&uhid->devlock); return ret ? ret : len; } static ssize_t uhid_char_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct uhid_device *uhid = file->private_data; int ret; size_t len; /* we need at least the "type" member of uhid_event */ if (count < sizeof(__u32)) return -EINVAL; ret = mutex_lock_interruptible(&uhid->devlock); if (ret) return ret; memset(&uhid->input_buf, 0, sizeof(uhid->input_buf)); len = min(count, sizeof(uhid->input_buf)); ret = uhid_event_from_user(buffer, len, &uhid->input_buf); if (ret) goto unlock; switch (uhid->input_buf.type) { case UHID_CREATE: /* * 'struct uhid_create_req' contains a __user pointer which is * copied from, so it's unsafe to allow this with elevated * privileges (e.g. from a setuid binary) or via kernel_write(). */ if (file->f_cred != current_cred()) { pr_err_once("UHID_CREATE from different security context by process %d (%s), this is not allowed.\n", task_tgid_vnr(current), current->comm); ret = -EACCES; goto unlock; } ret = uhid_dev_create(uhid, &uhid->input_buf); break; case UHID_CREATE2: ret = uhid_dev_create2(uhid, &uhid->input_buf); break; case UHID_DESTROY: ret = uhid_dev_destroy(uhid); break; case UHID_INPUT: ret = uhid_dev_input(uhid, &uhid->input_buf); break; case UHID_INPUT2: ret = uhid_dev_input2(uhid, &uhid->input_buf); break; case UHID_GET_REPORT_REPLY: ret = uhid_dev_get_report_reply(uhid, &uhid->input_buf); break; case UHID_SET_REPORT_REPLY: ret = uhid_dev_set_report_reply(uhid, &uhid->input_buf); break; default: ret = -EOPNOTSUPP; } unlock: mutex_unlock(&uhid->devlock); /* return "count" not "len" to not confuse the caller */ return ret ? ret : count; } static __poll_t uhid_char_poll(struct file *file, poll_table *wait) { struct uhid_device *uhid = file->private_data; __poll_t mask = EPOLLOUT | EPOLLWRNORM; /* uhid is always writable */ poll_wait(file, &uhid->waitq, wait); if (uhid->head != uhid->tail) mask |= EPOLLIN | EPOLLRDNORM; return mask; } static const struct file_operations uhid_fops = { .owner = THIS_MODULE, .open = uhid_char_open, .release = uhid_char_release, .read = uhid_char_read, .write = uhid_char_write, .poll = uhid_char_poll, }; static struct miscdevice uhid_misc = { .fops = &uhid_fops, .minor = UHID_MINOR, .name = UHID_NAME, }; module_misc_device(uhid_misc); MODULE_LICENSE("GPL"); MODULE_AUTHOR("David Herrmann <dh.herrmann@gmail.com>"); MODULE_DESCRIPTION("User-space I/O driver support for HID subsystem"); MODULE_ALIAS_MISCDEV(UHID_MINOR); MODULE_ALIAS("devname:" UHID_NAME); |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This is a module which is used for queueing packets and communicating with * userspace via nfnetlink. * * (C) 2005 by Harald Welte <laforge@netfilter.org> * (C) 2007 by Patrick McHardy <kaber@trash.net> * * Based on the old ipv4-only ip_queue.c: * (C) 2000-2002 James Morris <jmorris@intercode.com.au> * (C) 2003-2005 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/proc_fs.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_queue.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/list.h> #include <linux/cgroup-defs.h> #include <net/gso.h> #include <net/sock.h> #include <net/tcp_states.h> #include <net/netfilter/nf_queue.h> #include <net/netns/generic.h> #include <linux/atomic.h> #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) #include "../bridge/br_private.h" #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif #define NFQNL_QMAX_DEFAULT 1024 /* We're using struct nlattr which has 16bit nla_len. Note that nla_len * includes the header length. Thus, the maximum packet length that we * support is 65531 bytes. We send truncated packets if the specified length * is larger than that. Userspace can check for presence of NFQA_CAP_LEN * attribute to detect truncation. */ #define NFQNL_MAX_COPY_RANGE (0xffff - NLA_HDRLEN) struct nfqnl_instance { struct hlist_node hlist; /* global list of queues */ struct rcu_head rcu; u32 peer_portid; unsigned int queue_maxlen; unsigned int copy_range; unsigned int queue_dropped; unsigned int queue_user_dropped; u_int16_t queue_num; /* number of this queue */ u_int8_t copy_mode; u_int32_t flags; /* Set using NFQA_CFG_FLAGS */ /* * Following fields are dirtied for each queued packet, * keep them in same cache line if possible. */ spinlock_t lock ____cacheline_aligned_in_smp; unsigned int queue_total; unsigned int id_sequence; /* 'sequence' of pkt ids */ struct list_head queue_list; /* packets in queue */ }; typedef int (*nfqnl_cmpfn)(struct nf_queue_entry *, unsigned long); static unsigned int nfnl_queue_net_id __read_mostly; #define INSTANCE_BUCKETS 16 struct nfnl_queue_net { spinlock_t instances_lock; struct hlist_head instance_table[INSTANCE_BUCKETS]; }; static struct nfnl_queue_net *nfnl_queue_pernet(struct net *net) { return net_generic(net, nfnl_queue_net_id); } static inline u_int8_t instance_hashfn(u_int16_t queue_num) { return ((queue_num >> 8) ^ queue_num) % INSTANCE_BUCKETS; } static struct nfqnl_instance * instance_lookup(struct nfnl_queue_net *q, u_int16_t queue_num) { struct hlist_head *head; struct nfqnl_instance *inst; head = &q->instance_table[instance_hashfn(queue_num)]; hlist_for_each_entry_rcu(inst, head, hlist) { if (inst->queue_num == queue_num) return inst; } return NULL; } static struct nfqnl_instance * instance_create(struct nfnl_queue_net *q, u_int16_t queue_num, u32 portid) { struct nfqnl_instance *inst; unsigned int h; int err; spin_lock(&q->instances_lock); if (instance_lookup(q, queue_num)) { err = -EEXIST; goto out_unlock; } inst = kzalloc(sizeof(*inst), GFP_ATOMIC); if (!inst) { err = -ENOMEM; goto out_unlock; } inst->queue_num = queue_num; inst->peer_portid = portid; inst->queue_maxlen = NFQNL_QMAX_DEFAULT; inst->copy_range = NFQNL_MAX_COPY_RANGE; inst->copy_mode = NFQNL_COPY_NONE; spin_lock_init(&inst->lock); INIT_LIST_HEAD(&inst->queue_list); if (!try_module_get(THIS_MODULE)) { err = -EAGAIN; goto out_free; } h = instance_hashfn(queue_num); hlist_add_head_rcu(&inst->hlist, &q->instance_table[h]); spin_unlock(&q->instances_lock); return inst; out_free: kfree(inst); out_unlock: spin_unlock(&q->instances_lock); return ERR_PTR(err); } static void nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data); static void instance_destroy_rcu(struct rcu_head *head) { struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance, rcu); rcu_read_lock(); nfqnl_flush(inst, NULL, 0); rcu_read_unlock(); kfree(inst); module_put(THIS_MODULE); } static void __instance_destroy(struct nfqnl_instance *inst) { hlist_del_rcu(&inst->hlist); call_rcu(&inst->rcu, instance_destroy_rcu); } static void instance_destroy(struct nfnl_queue_net *q, struct nfqnl_instance *inst) { spin_lock(&q->instances_lock); __instance_destroy(inst); spin_unlock(&q->instances_lock); } static inline void __enqueue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry) { list_add_tail(&entry->list, &queue->queue_list); queue->queue_total++; } static void __dequeue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry) { list_del(&entry->list); queue->queue_total--; } static struct nf_queue_entry * find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) { struct nf_queue_entry *entry = NULL, *i; spin_lock_bh(&queue->lock); list_for_each_entry(i, &queue->queue_list, list) { if (i->id == id) { entry = i; break; } } if (entry) __dequeue_entry(queue, entry); spin_unlock_bh(&queue->lock); return entry; } static unsigned int nf_iterate(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *hooks, unsigned int *index) { const struct nf_hook_entry *hook; unsigned int verdict, i = *index; while (i < hooks->num_hook_entries) { hook = &hooks->hooks[i]; repeat: verdict = nf_hook_entry_hookfn(hook, skb, state); if (verdict != NF_ACCEPT) { *index = i; if (verdict != NF_REPEAT) return verdict; goto repeat; } i++; } *index = i; return NF_ACCEPT; } static struct nf_hook_entries *nf_hook_entries_head(const struct net *net, u8 pf, u8 hooknum) { switch (pf) { #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE case NFPROTO_BRIDGE: return rcu_dereference(net->nf.hooks_bridge[hooknum]); #endif case NFPROTO_IPV4: return rcu_dereference(net->nf.hooks_ipv4[hooknum]); case NFPROTO_IPV6: return rcu_dereference(net->nf.hooks_ipv6[hooknum]); default: WARN_ON_ONCE(1); return NULL; } return NULL; } static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) { #ifdef CONFIG_INET const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); if (entry->state.hook == NF_INET_LOCAL_OUT) { const struct iphdr *iph = ip_hdr(skb); if (!(iph->tos == rt_info->tos && skb->mark == rt_info->mark && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) return ip_route_me_harder(entry->state.net, entry->state.sk, skb, RTN_UNSPEC); } #endif return 0; } static int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry) { const struct nf_ipv6_ops *v6ops; int ret = 0; switch (entry->state.pf) { case AF_INET: ret = nf_ip_reroute(skb, entry); break; case AF_INET6: v6ops = rcu_dereference(nf_ipv6_ops); if (v6ops) ret = v6ops->reroute(skb, entry); break; } return ret; } /* caller must hold rcu read-side lock */ static void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_hook_entry *hook_entry; const struct nf_hook_entries *hooks; struct sk_buff *skb = entry->skb; const struct net *net; unsigned int i; int err; u8 pf; net = entry->state.net; pf = entry->state.pf; hooks = nf_hook_entries_head(net, pf, entry->state.hook); i = entry->hook_index; if (!hooks || i >= hooks->num_hook_entries) { kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP); nf_queue_entry_free(entry); return; } hook_entry = &hooks->hooks[i]; /* Continue traversal iff userspace said ok... */ if (verdict == NF_REPEAT) verdict = nf_hook_entry_hookfn(hook_entry, skb, &entry->state); if (verdict == NF_ACCEPT) { if (nf_reroute(skb, entry) < 0) verdict = NF_DROP; } if (verdict == NF_ACCEPT) { next_hook: ++i; verdict = nf_iterate(skb, &entry->state, hooks, &i); } switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: case NF_STOP: local_bh_disable(); entry->state.okfn(entry->state.net, entry->state.sk, skb); local_bh_enable(); break; case NF_QUEUE: err = nf_queue(skb, &entry->state, i, verdict); if (err == 1) goto next_hook; break; case NF_STOLEN: break; default: kfree_skb(skb); } nf_queue_entry_free(entry); } static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_ct_hook *ct_hook; if (verdict == NF_ACCEPT || verdict == NF_REPEAT || verdict == NF_STOP) { unsigned int ct_verdict = verdict; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ct_verdict = ct_hook->update(entry->state.net, entry->skb); rcu_read_unlock(); switch (ct_verdict & NF_VERDICT_MASK) { case NF_ACCEPT: /* follow userspace verdict, could be REPEAT */ break; case NF_STOLEN: nf_queue_entry_free(entry); return; default: verdict = ct_verdict & NF_VERDICT_MASK; break; } } nf_reinject(entry, verdict); } static void nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data) { struct nf_queue_entry *entry, *next; spin_lock_bh(&queue->lock); list_for_each_entry_safe(entry, next, &queue->queue_list, list) { if (!cmpfn || cmpfn(entry, data)) { list_del(&entry->list); queue->queue_total--; nfqnl_reinject(entry, NF_DROP); } } spin_unlock_bh(&queue->lock); } static int nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet, bool csum_verify) { __u32 flags = 0; if (packet->ip_summed == CHECKSUM_PARTIAL) flags = NFQA_SKB_CSUMNOTREADY; else if (csum_verify) flags = NFQA_SKB_CSUM_NOTVERIFIED; if (skb_is_gso(packet)) flags |= NFQA_SKB_GSO; return flags ? nla_put_be32(nlskb, NFQA_SKB_INFO, htonl(flags)) : 0; } static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk) { const struct cred *cred; if (!sk_fullsock(sk)) return 0; read_lock_bh(&sk->sk_callback_lock); if (sk->sk_socket && sk->sk_socket->file) { cred = sk->sk_socket->file->f_cred; if (nla_put_be32(skb, NFQA_UID, htonl(from_kuid_munged(&init_user_ns, cred->fsuid)))) goto nla_put_failure; if (nla_put_be32(skb, NFQA_GID, htonl(from_kgid_munged(&init_user_ns, cred->fsgid)))) goto nla_put_failure; } read_unlock_bh(&sk->sk_callback_lock); return 0; nla_put_failure: read_unlock_bh(&sk->sk_callback_lock); return -1; } static int nfqnl_put_sk_classid(struct sk_buff *skb, struct sock *sk) { #if IS_ENABLED(CONFIG_CGROUP_NET_CLASSID) if (sk && sk_fullsock(sk)) { u32 classid = sock_cgroup_classid(&sk->sk_cgrp_data); if (classid && nla_put_be32(skb, NFQA_CGROUP_CLASSID, htonl(classid))) return -1; } #endif return 0; } static int nfqnl_get_sk_secctx(struct sk_buff *skb, struct lsm_context *ctx) { int seclen = 0; #if IS_ENABLED(CONFIG_NETWORK_SECMARK) if (!skb || !sk_fullsock(skb->sk)) return 0; read_lock_bh(&skb->sk->sk_callback_lock); if (skb->secmark) seclen = security_secid_to_secctx(skb->secmark, ctx); read_unlock_bh(&skb->sk->sk_callback_lock); #endif return seclen; } static u32 nfqnl_get_bridge_size(struct nf_queue_entry *entry) { struct sk_buff *entskb = entry->skb; u32 nlalen = 0; if (entry->state.pf != PF_BRIDGE || !skb_mac_header_was_set(entskb)) return 0; if (skb_vlan_tag_present(entskb)) nlalen += nla_total_size(nla_total_size(sizeof(__be16)) + nla_total_size(sizeof(__be16))); if (entskb->network_header > entskb->mac_header) nlalen += nla_total_size((entskb->network_header - entskb->mac_header)); return nlalen; } static int nfqnl_put_bridge(struct nf_queue_entry *entry, struct sk_buff *skb) { struct sk_buff *entskb = entry->skb; if (entry->state.pf != PF_BRIDGE || !skb_mac_header_was_set(entskb)) return 0; if (skb_vlan_tag_present(entskb)) { struct nlattr *nest; nest = nla_nest_start(skb, NFQA_VLAN); if (!nest) goto nla_put_failure; if (nla_put_be16(skb, NFQA_VLAN_TCI, htons(entskb->vlan_tci)) || nla_put_be16(skb, NFQA_VLAN_PROTO, entskb->vlan_proto)) goto nla_put_failure; nla_nest_end(skb, nest); } if (entskb->mac_header < entskb->network_header) { int len = (int)(entskb->network_header - entskb->mac_header); if (nla_put(skb, NFQA_L2HDR, len, skb_mac_header(entskb))) goto nla_put_failure; } return 0; nla_put_failure: return -1; } static int nf_queue_checksum_help(struct sk_buff *entskb) { if (skb_csum_is_sctp(entskb)) return skb_crc32c_csum_help(entskb); return skb_checksum_help(entskb); } static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, __be32 **packet_id_ptr) { size_t size; size_t data_len = 0, cap_len = 0; unsigned int hlen = 0; struct sk_buff *skb; struct nlattr *nla; struct nfqnl_msg_packet_hdr *pmsg; struct nlmsghdr *nlh; struct sk_buff *entskb = entry->skb; struct net_device *indev; struct net_device *outdev; struct nf_conn *ct = NULL; enum ip_conntrack_info ctinfo = 0; const struct nfnl_ct_hook *nfnl_ct; bool csum_verify; struct lsm_context ctx = { NULL, 0, 0 }; int seclen = 0; ktime_t tstamp; size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfqnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #endif + nla_total_size(sizeof(u_int32_t)) /* mark */ + nla_total_size(sizeof(u_int32_t)) /* priority */ + nla_total_size(sizeof(struct nfqnl_msg_packet_hw)) + nla_total_size(sizeof(u_int32_t)) /* skbinfo */ #if IS_ENABLED(CONFIG_CGROUP_NET_CLASSID) + nla_total_size(sizeof(u_int32_t)) /* classid */ #endif + nla_total_size(sizeof(u_int32_t)); /* cap_len */ tstamp = skb_tstamp_cond(entskb, false); if (tstamp) size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp)); size += nfqnl_get_bridge_size(entry); if (entry->state.hook <= NF_INET_FORWARD || (entry->state.hook == NF_INET_POST_ROUTING && entskb->sk == NULL)) csum_verify = !skb_csum_unnecessary(entskb); else csum_verify = false; outdev = entry->state.out; switch ((enum nfqnl_config_mode)READ_ONCE(queue->copy_mode)) { case NFQNL_COPY_META: case NFQNL_COPY_NONE: break; case NFQNL_COPY_PACKET: if (!(queue->flags & NFQA_CFG_F_GSO) && entskb->ip_summed == CHECKSUM_PARTIAL && nf_queue_checksum_help(entskb)) return NULL; data_len = READ_ONCE(queue->copy_range); if (data_len > entskb->len) data_len = entskb->len; hlen = skb_zerocopy_headlen(entskb); hlen = min_t(unsigned int, hlen, data_len); size += sizeof(struct nlattr) + hlen; cap_len = entskb->len; break; } nfnl_ct = rcu_dereference(nfnl_ct_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (queue->flags & NFQA_CFG_F_CONNTRACK) { if (nfnl_ct != NULL) { ct = nf_ct_get(entskb, &ctinfo); if (ct != NULL) size += nfnl_ct->build_size(ct); } } #endif if (queue->flags & NFQA_CFG_F_UID_GID) { size += (nla_total_size(sizeof(u_int32_t)) /* uid */ + nla_total_size(sizeof(u_int32_t))); /* gid */ } if ((queue->flags & NFQA_CFG_F_SECCTX) && entskb->sk) { seclen = nfqnl_get_sk_secctx(entskb, &ctx); if (seclen < 0) return NULL; if (seclen) size += nla_total_size(seclen); } skb = alloc_skb(size, GFP_ATOMIC); if (!skb) { skb_tx_error(entskb); goto nlmsg_failure; } nlh = nfnl_msg_put(skb, 0, 0, nfnl_msg_type(NFNL_SUBSYS_QUEUE, NFQNL_MSG_PACKET), 0, entry->state.pf, NFNETLINK_V0, htons(queue->queue_num)); if (!nlh) { skb_tx_error(entskb); kfree_skb(skb); goto nlmsg_failure; } nla = __nla_reserve(skb, NFQA_PACKET_HDR, sizeof(*pmsg)); pmsg = nla_data(nla); pmsg->hw_protocol = entskb->protocol; pmsg->hook = entry->state.hook; *packet_id_ptr = &pmsg->packet_id; indev = entry->state.in; if (indev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; #else if (entry->state.pf == PF_BRIDGE) { /* Case 1: indev is physical input device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV, htonl(indev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by __nf_queue */ nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; } else { int physinif; /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; physinif = nf_bridge_get_physinif(entskb); if (physinif && nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV, htonl(physinif))) goto nla_put_failure; } #endif } if (outdev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; #else if (entry->state.pf == PF_BRIDGE) { /* Case 1: outdev is physical output device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV, htonl(outdev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by __nf_queue */ nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) goto nla_put_failure; } else { int physoutif; /* Case 2: outdev is bridge group, we need to look for * physical output device (when called from ipv4) */ if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; physoutif = nf_bridge_get_physoutif(entskb); if (physoutif && nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV, htonl(physoutif))) goto nla_put_failure; } #endif } if (entskb->mark && nla_put_be32(skb, NFQA_MARK, htonl(entskb->mark))) goto nla_put_failure; if (entskb->priority && nla_put_be32(skb, NFQA_PRIORITY, htonl(entskb->priority))) goto nla_put_failure; if (indev && entskb->dev && skb_mac_header_was_set(entskb) && skb_mac_header_len(entskb) != 0) { struct nfqnl_msg_packet_hw phw; int len; memset(&phw, 0, sizeof(phw)); len = dev_parse_header(entskb, phw.hw_addr); if (len) { phw.hw_addrlen = htons(len); if (nla_put(skb, NFQA_HWADDR, sizeof(phw), &phw)) goto nla_put_failure; } } if (nfqnl_put_bridge(entry, skb) < 0) goto nla_put_failure; if (entry->state.hook <= NF_INET_FORWARD && tstamp) { struct nfqnl_msg_packet_timestamp ts; struct timespec64 kts = ktime_to_timespec64(tstamp); ts.sec = cpu_to_be64(kts.tv_sec); ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC); if (nla_put(skb, NFQA_TIMESTAMP, sizeof(ts), &ts)) goto nla_put_failure; } if ((queue->flags & NFQA_CFG_F_UID_GID) && entskb->sk && nfqnl_put_sk_uidgid(skb, entskb->sk) < 0) goto nla_put_failure; if (nfqnl_put_sk_classid(skb, entskb->sk) < 0) goto nla_put_failure; if (seclen > 0 && nla_put(skb, NFQA_SECCTX, ctx.len, ctx.context)) goto nla_put_failure; if (ct && nfnl_ct->build(skb, ct, ctinfo, NFQA_CT, NFQA_CT_INFO) < 0) goto nla_put_failure; if (cap_len > data_len && nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len))) goto nla_put_failure; if (nfqnl_put_packet_info(skb, entskb, csum_verify)) goto nla_put_failure; if (data_len) { struct nlattr *nla; if (skb_tailroom(skb) < sizeof(*nla) + hlen) goto nla_put_failure; nla = skb_put(skb, sizeof(*nla)); nla->nla_type = NFQA_PAYLOAD; nla->nla_len = nla_attr_size(data_len); if (skb_zerocopy(skb, entskb, data_len, hlen)) goto nla_put_failure; } nlh->nlmsg_len = skb->len; if (seclen >= 0) security_release_secctx(&ctx); return skb; nla_put_failure: skb_tx_error(entskb); kfree_skb(skb); net_err_ratelimited("nf_queue: error creating packet message\n"); nlmsg_failure: if (seclen >= 0) security_release_secctx(&ctx); return NULL; } static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) static const unsigned long flags = IPS_CONFIRMED | IPS_DYING; struct nf_conn *ct = (void *)skb_nfct(entry->skb); unsigned long status; unsigned int use; if (!ct) return false; status = READ_ONCE(ct->status); if ((status & flags) == IPS_DYING) return true; if (status & IPS_CONFIRMED) return false; /* in some cases skb_clone() can occur after initial conntrack * pickup, but conntrack assumes exclusive skb->_nfct ownership for * unconfirmed entries. * * This happens for br_netfilter and with ip multicast routing. * We can't be solved with serialization here because one clone could * have been queued for local delivery. */ use = refcount_read(&ct->ct_general.use); if (likely(use == 1)) return false; /* Can't decrement further? Exclusive ownership. */ if (!refcount_dec_not_one(&ct->ct_general.use)) return false; skb_set_nfct(entry->skb, 0); /* No nf_ct_put(): we already decremented .use and it cannot * drop down to 0. */ return true; #endif return false; } static int __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry) { struct sk_buff *nskb; int err = -ENOBUFS; __be32 *packet_id_ptr; int failopen = 0; nskb = nfqnl_build_packet_message(net, queue, entry, &packet_id_ptr); if (nskb == NULL) { err = -ENOMEM; goto err_out; } spin_lock_bh(&queue->lock); if (nf_ct_drop_unconfirmed(entry)) goto err_out_free_nskb; if (queue->queue_total >= queue->queue_maxlen) { if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { failopen = 1; err = 0; } else { queue->queue_dropped++; net_warn_ratelimited("nf_queue: full at %d entries, dropping packets(s)\n", queue->queue_total); } goto err_out_free_nskb; } entry->id = ++queue->id_sequence; *packet_id_ptr = htonl(entry->id); /* nfnetlink_unicast will either free the nskb or add it to a socket */ err = nfnetlink_unicast(nskb, net, queue->peer_portid); if (err < 0) { if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { failopen = 1; err = 0; } else { queue->queue_user_dropped++; } goto err_out_unlock; } __enqueue_entry(queue, entry); spin_unlock_bh(&queue->lock); return 0; err_out_free_nskb: kfree_skb(nskb); err_out_unlock: spin_unlock_bh(&queue->lock); if (failopen) nfqnl_reinject(entry, NF_ACCEPT); err_out: return err; } static struct nf_queue_entry * nf_queue_entry_dup(struct nf_queue_entry *e) { struct nf_queue_entry *entry = kmemdup(e, e->size, GFP_ATOMIC); if (!entry) return NULL; if (nf_queue_entry_get_refs(entry)) return entry; kfree(entry); return NULL; } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* When called from bridge netfilter, skb->data must point to MAC header * before calling skb_gso_segment(). Else, original MAC header is lost * and segmented skbs will be sent to wrong destination. */ static void nf_bridge_adjust_skb_data(struct sk_buff *skb) { if (nf_bridge_info_get(skb)) __skb_push(skb, skb->network_header - skb->mac_header); } static void nf_bridge_adjust_segmented_data(struct sk_buff *skb) { if (nf_bridge_info_get(skb)) __skb_pull(skb, skb->network_header - skb->mac_header); } #else #define nf_bridge_adjust_skb_data(s) do {} while (0) #define nf_bridge_adjust_segmented_data(s) do {} while (0) #endif static int __nfqnl_enqueue_packet_gso(struct net *net, struct nfqnl_instance *queue, struct sk_buff *skb, struct nf_queue_entry *entry) { int ret = -ENOMEM; struct nf_queue_entry *entry_seg; nf_bridge_adjust_segmented_data(skb); if (skb->next == NULL) { /* last packet, no need to copy entry */ struct sk_buff *gso_skb = entry->skb; entry->skb = skb; ret = __nfqnl_enqueue_packet(net, queue, entry); if (ret) entry->skb = gso_skb; return ret; } skb_mark_not_on_list(skb); entry_seg = nf_queue_entry_dup(entry); if (entry_seg) { entry_seg->skb = skb; ret = __nfqnl_enqueue_packet(net, queue, entry_seg); if (ret) nf_queue_entry_free(entry_seg); } return ret; } static int nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) { unsigned int queued; struct nfqnl_instance *queue; struct sk_buff *skb, *segs, *nskb; int err = -ENOBUFS; struct net *net = entry->state.net; struct nfnl_queue_net *q = nfnl_queue_pernet(net); /* rcu_read_lock()ed by nf_hook_thresh */ queue = instance_lookup(q, queuenum); if (!queue) return -ESRCH; if (queue->copy_mode == NFQNL_COPY_NONE) return -EINVAL; skb = entry->skb; switch (entry->state.pf) { case NFPROTO_IPV4: skb->protocol = htons(ETH_P_IP); break; case NFPROTO_IPV6: skb->protocol = htons(ETH_P_IPV6); break; } if (!skb_is_gso(skb) || ((queue->flags & NFQA_CFG_F_GSO) && !skb_is_gso_sctp(skb))) return __nfqnl_enqueue_packet(net, queue, entry); nf_bridge_adjust_skb_data(skb); segs = skb_gso_segment(skb, 0); /* Does not use PTR_ERR to limit the number of error codes that can be * returned by nf_queue. For instance, callers rely on -ESRCH to * mean 'ignore this hook'. */ if (IS_ERR_OR_NULL(segs)) goto out_err; queued = 0; err = 0; skb_list_walk_safe(segs, segs, nskb) { if (err == 0) err = __nfqnl_enqueue_packet_gso(net, queue, segs, entry); if (err == 0) queued++; else kfree_skb(segs); } if (queued) { if (err) /* some segments are already queued */ nf_queue_entry_free(entry); kfree_skb(skb); return 0; } out_err: nf_bridge_adjust_segmented_data(skb); return err; } static int nfqnl_mangle(void *data, unsigned int data_len, struct nf_queue_entry *e, int diff) { struct sk_buff *nskb; if (diff < 0) { unsigned int min_len = skb_transport_offset(e->skb); if (data_len < min_len) return -EINVAL; if (pskb_trim(e->skb, data_len)) return -ENOMEM; } else if (diff > 0) { if (data_len > 0xFFFF) return -EINVAL; if (diff > skb_tailroom(e->skb)) { nskb = skb_copy_expand(e->skb, skb_headroom(e->skb), diff, GFP_ATOMIC); if (!nskb) return -ENOMEM; kfree_skb(e->skb); e->skb = nskb; } skb_put(e->skb, diff); } if (skb_ensure_writable(e->skb, data_len)) return -ENOMEM; skb_copy_to_linear_data(e->skb, data, data_len); e->skb->ip_summed = CHECKSUM_NONE; return 0; } static int nfqnl_set_mode(struct nfqnl_instance *queue, unsigned char mode, unsigned int range) { int status = 0; spin_lock_bh(&queue->lock); switch (mode) { case NFQNL_COPY_NONE: case NFQNL_COPY_META: queue->copy_mode = mode; queue->copy_range = 0; break; case NFQNL_COPY_PACKET: queue->copy_mode = mode; if (range == 0 || range > NFQNL_MAX_COPY_RANGE) queue->copy_range = NFQNL_MAX_COPY_RANGE; else queue->copy_range = range; break; default: status = -EINVAL; } spin_unlock_bh(&queue->lock); return status; } static int dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) int physinif, physoutif; physinif = nf_bridge_get_physinif(entry->skb); physoutif = nf_bridge_get_physoutif(entry->skb); if (physinif == ifindex || physoutif == ifindex) return 1; #endif if (entry->state.in) if (entry->state.in->ifindex == ifindex) return 1; if (entry->state.out) if (entry->state.out->ifindex == ifindex) return 1; return 0; } /* drop all packets with either indev or outdev == ifindex from all queue * instances */ static void nfqnl_dev_drop(struct net *net, int ifindex) { int i; struct nfnl_queue_net *q = nfnl_queue_pernet(net); rcu_read_lock(); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct nfqnl_instance *inst; struct hlist_head *head = &q->instance_table[i]; hlist_for_each_entry_rcu(inst, head, hlist) nfqnl_flush(inst, dev_cmp, ifindex); } rcu_read_unlock(); } static int nfqnl_rcv_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* Drop any packets associated with the downed device */ if (event == NETDEV_DOWN) nfqnl_dev_drop(dev_net(dev), dev->ifindex); return NOTIFY_DONE; } static struct notifier_block nfqnl_dev_notifier = { .notifier_call = nfqnl_rcv_dev_event, }; static void nfqnl_nf_hook_drop(struct net *net) { struct nfnl_queue_net *q = nfnl_queue_pernet(net); int i; /* This function is also called on net namespace error unwind, * when pernet_ops->init() failed and ->exit() functions of the * previous pernet_ops gets called. * * This may result in a call to nfqnl_nf_hook_drop() before * struct nfnl_queue_net was allocated. */ if (!q) return; for (i = 0; i < INSTANCE_BUCKETS; i++) { struct nfqnl_instance *inst; struct hlist_head *head = &q->instance_table[i]; hlist_for_each_entry_rcu(inst, head, hlist) nfqnl_flush(inst, NULL, 0); } } static int nfqnl_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netlink_notify *n = ptr; struct nfnl_queue_net *q = nfnl_queue_pernet(n->net); if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; /* destroy all instances for this portid */ spin_lock(&q->instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct hlist_node *t2; struct nfqnl_instance *inst; struct hlist_head *head = &q->instance_table[i]; hlist_for_each_entry_safe(inst, t2, head, hlist) { if (n->portid == inst->peer_portid) __instance_destroy(inst); } } spin_unlock(&q->instances_lock); } return NOTIFY_DONE; } static struct notifier_block nfqnl_rtnl_notifier = { .notifier_call = nfqnl_rcv_nl_event, }; static const struct nla_policy nfqa_vlan_policy[NFQA_VLAN_MAX + 1] = { [NFQA_VLAN_TCI] = { .type = NLA_U16}, [NFQA_VLAN_PROTO] = { .type = NLA_U16}, }; static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = { [NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) }, [NFQA_MARK] = { .type = NLA_U32 }, [NFQA_PAYLOAD] = { .type = NLA_UNSPEC }, [NFQA_CT] = { .type = NLA_UNSPEC }, [NFQA_EXP] = { .type = NLA_UNSPEC }, [NFQA_VLAN] = { .type = NLA_NESTED }, [NFQA_PRIORITY] = { .type = NLA_U32 }, }; static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { [NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) }, [NFQA_MARK] = { .type = NLA_U32 }, [NFQA_PRIORITY] = { .type = NLA_U32 }, }; static struct nfqnl_instance * verdict_instance_lookup(struct nfnl_queue_net *q, u16 queue_num, u32 nlportid) { struct nfqnl_instance *queue; queue = instance_lookup(q, queue_num); if (!queue) return ERR_PTR(-ENODEV); if (queue->peer_portid != nlportid) return ERR_PTR(-EPERM); return queue; } static struct nfqnl_msg_verdict_hdr* verdicthdr_get(const struct nlattr * const nfqa[]) { struct nfqnl_msg_verdict_hdr *vhdr; unsigned int verdict; if (!nfqa[NFQA_VERDICT_HDR]) return NULL; vhdr = nla_data(nfqa[NFQA_VERDICT_HDR]); verdict = ntohl(vhdr->verdict) & NF_VERDICT_MASK; if (verdict > NF_MAX_VERDICT || verdict == NF_STOLEN) return NULL; return vhdr; } static int nfq_id_after(unsigned int id, unsigned int max) { return (int)(id - max) > 0; } static int nfqnl_recv_verdict_batch(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); u16 queue_num = ntohs(info->nfmsg->res_id); struct nf_queue_entry *entry, *tmp; struct nfqnl_msg_verdict_hdr *vhdr; struct nfqnl_instance *queue; unsigned int verdict, maxid; LIST_HEAD(batch_list); queue = verdict_instance_lookup(q, queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); vhdr = verdicthdr_get(nfqa); if (!vhdr) return -EINVAL; verdict = ntohl(vhdr->verdict); maxid = ntohl(vhdr->id); spin_lock_bh(&queue->lock); list_for_each_entry_safe(entry, tmp, &queue->queue_list, list) { if (nfq_id_after(entry->id, maxid)) break; __dequeue_entry(queue, entry); list_add_tail(&entry->list, &batch_list); } spin_unlock_bh(&queue->lock); if (list_empty(&batch_list)) return -ENOENT; list_for_each_entry_safe(entry, tmp, &batch_list, list) { if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); if (nfqa[NFQA_PRIORITY]) entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY])); nfqnl_reinject(entry, verdict); } return 0; } static struct nf_conn *nfqnl_ct_parse(const struct nfnl_ct_hook *nfnl_ct, const struct nlmsghdr *nlh, const struct nlattr * const nfqa[], struct nf_queue_entry *entry, enum ip_conntrack_info *ctinfo) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct nf_conn *ct; ct = nf_ct_get(entry->skb, ctinfo); if (ct == NULL) return NULL; if (nfnl_ct->parse(nfqa[NFQA_CT], ct) < 0) return NULL; if (nfqa[NFQA_EXP]) nfnl_ct->attach_expect(nfqa[NFQA_EXP], ct, NETLINK_CB(entry->skb).portid, nlmsg_report(nlh)); return ct; #else return NULL; #endif } static int nfqa_parse_bridge(struct nf_queue_entry *entry, const struct nlattr * const nfqa[]) { if (nfqa[NFQA_VLAN]) { struct nlattr *tb[NFQA_VLAN_MAX + 1]; int err; err = nla_parse_nested_deprecated(tb, NFQA_VLAN_MAX, nfqa[NFQA_VLAN], nfqa_vlan_policy, NULL); if (err < 0) return err; if (!tb[NFQA_VLAN_TCI] || !tb[NFQA_VLAN_PROTO]) return -EINVAL; __vlan_hwaccel_put_tag(entry->skb, nla_get_be16(tb[NFQA_VLAN_PROTO]), ntohs(nla_get_be16(tb[NFQA_VLAN_TCI]))); } if (nfqa[NFQA_L2HDR]) { int mac_header_len = entry->skb->network_header - entry->skb->mac_header; if (mac_header_len != nla_len(nfqa[NFQA_L2HDR])) return -EINVAL; else if (mac_header_len > 0) memcpy(skb_mac_header(entry->skb), nla_data(nfqa[NFQA_L2HDR]), mac_header_len); } return 0; } static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); u_int16_t queue_num = ntohs(info->nfmsg->res_id); const struct nfnl_ct_hook *nfnl_ct; struct nfqnl_msg_verdict_hdr *vhdr; enum ip_conntrack_info ctinfo; struct nfqnl_instance *queue; struct nf_queue_entry *entry; struct nf_conn *ct = NULL; unsigned int verdict; int err; queue = verdict_instance_lookup(q, queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); vhdr = verdicthdr_get(nfqa); if (!vhdr) return -EINVAL; verdict = ntohl(vhdr->verdict); entry = find_dequeue_entry(queue, ntohl(vhdr->id)); if (entry == NULL) return -ENOENT; /* rcu lock already held from nfnl->call_rcu. */ nfnl_ct = rcu_dereference(nfnl_ct_hook); if (nfqa[NFQA_CT]) { if (nfnl_ct != NULL) ct = nfqnl_ct_parse(nfnl_ct, info->nlh, nfqa, entry, &ctinfo); } if (entry->state.pf == PF_BRIDGE) { err = nfqa_parse_bridge(entry, nfqa); if (err < 0) return err; } if (nfqa[NFQA_PAYLOAD]) { u16 payload_len = nla_len(nfqa[NFQA_PAYLOAD]); int diff = payload_len - entry->skb->len; if (nfqnl_mangle(nla_data(nfqa[NFQA_PAYLOAD]), payload_len, entry, diff) < 0) verdict = NF_DROP; if (ct && diff) nfnl_ct->seq_adjust(entry->skb, ct, ctinfo, diff); } if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); if (nfqa[NFQA_PRIORITY]) entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY])); nfqnl_reinject(entry, verdict); return 0; } static int nfqnl_recv_unsupp(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { return -ENOTSUPP; } static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = { [NFQA_CFG_CMD] = { .len = sizeof(struct nfqnl_msg_config_cmd) }, [NFQA_CFG_PARAMS] = { .len = sizeof(struct nfqnl_msg_config_params) }, [NFQA_CFG_QUEUE_MAXLEN] = { .type = NLA_U32 }, [NFQA_CFG_MASK] = { .type = NLA_U32 }, [NFQA_CFG_FLAGS] = { .type = NLA_U32 }, }; static const struct nf_queue_handler nfqh = { .outfn = nfqnl_enqueue_packet, .nf_hook_drop = nfqnl_nf_hook_drop, }; static int nfqnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); u_int16_t queue_num = ntohs(info->nfmsg->res_id); struct nfqnl_msg_config_cmd *cmd = NULL; struct nfqnl_instance *queue; __u32 flags = 0, mask = 0; int ret = 0; if (nfqa[NFQA_CFG_CMD]) { cmd = nla_data(nfqa[NFQA_CFG_CMD]); /* Obsolete commands without queue context */ switch (cmd->command) { case NFQNL_CFG_CMD_PF_BIND: return 0; case NFQNL_CFG_CMD_PF_UNBIND: return 0; } } /* Check if we support these flags in first place, dependencies should * be there too not to break atomicity. */ if (nfqa[NFQA_CFG_FLAGS]) { if (!nfqa[NFQA_CFG_MASK]) { /* A mask is needed to specify which flags are being * changed. */ return -EINVAL; } flags = ntohl(nla_get_be32(nfqa[NFQA_CFG_FLAGS])); mask = ntohl(nla_get_be32(nfqa[NFQA_CFG_MASK])); if (flags >= NFQA_CFG_F_MAX) return -EOPNOTSUPP; #if !IS_ENABLED(CONFIG_NETWORK_SECMARK) if (flags & mask & NFQA_CFG_F_SECCTX) return -EOPNOTSUPP; #endif if ((flags & mask & NFQA_CFG_F_CONNTRACK) && !rcu_access_pointer(nfnl_ct_hook)) { #ifdef CONFIG_MODULES nfnl_unlock(NFNL_SUBSYS_QUEUE); request_module("ip_conntrack_netlink"); nfnl_lock(NFNL_SUBSYS_QUEUE); if (rcu_access_pointer(nfnl_ct_hook)) return -EAGAIN; #endif return -EOPNOTSUPP; } } rcu_read_lock(); queue = instance_lookup(q, queue_num); if (queue && queue->peer_portid != NETLINK_CB(skb).portid) { ret = -EPERM; goto err_out_unlock; } if (cmd != NULL) { switch (cmd->command) { case NFQNL_CFG_CMD_BIND: if (queue) { ret = -EBUSY; goto err_out_unlock; } queue = instance_create(q, queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) { ret = PTR_ERR(queue); goto err_out_unlock; } break; case NFQNL_CFG_CMD_UNBIND: if (!queue) { ret = -ENODEV; goto err_out_unlock; } instance_destroy(q, queue); goto err_out_unlock; case NFQNL_CFG_CMD_PF_BIND: case NFQNL_CFG_CMD_PF_UNBIND: break; default: ret = -ENOTSUPP; goto err_out_unlock; } } if (!queue) { ret = -ENODEV; goto err_out_unlock; } if (nfqa[NFQA_CFG_PARAMS]) { struct nfqnl_msg_config_params *params = nla_data(nfqa[NFQA_CFG_PARAMS]); nfqnl_set_mode(queue, params->copy_mode, ntohl(params->copy_range)); } if (nfqa[NFQA_CFG_QUEUE_MAXLEN]) { __be32 *queue_maxlen = nla_data(nfqa[NFQA_CFG_QUEUE_MAXLEN]); spin_lock_bh(&queue->lock); queue->queue_maxlen = ntohl(*queue_maxlen); spin_unlock_bh(&queue->lock); } if (nfqa[NFQA_CFG_FLAGS]) { spin_lock_bh(&queue->lock); queue->flags &= ~mask; queue->flags |= flags & mask; spin_unlock_bh(&queue->lock); } err_out_unlock: rcu_read_unlock(); return ret; } static const struct nfnl_callback nfqnl_cb[NFQNL_MSG_MAX] = { [NFQNL_MSG_PACKET] = { .call = nfqnl_recv_unsupp, .type = NFNL_CB_RCU, .attr_count = NFQA_MAX, }, [NFQNL_MSG_VERDICT] = { .call = nfqnl_recv_verdict, .type = NFNL_CB_RCU, .attr_count = NFQA_MAX, .policy = nfqa_verdict_policy }, [NFQNL_MSG_CONFIG] = { .call = nfqnl_recv_config, .type = NFNL_CB_MUTEX, .attr_count = NFQA_CFG_MAX, .policy = nfqa_cfg_policy }, [NFQNL_MSG_VERDICT_BATCH] = { .call = nfqnl_recv_verdict_batch, .type = NFNL_CB_RCU, .attr_count = NFQA_MAX, .policy = nfqa_verdict_batch_policy }, }; static const struct nfnetlink_subsystem nfqnl_subsys = { .name = "nf_queue", .subsys_id = NFNL_SUBSYS_QUEUE, .cb_count = NFQNL_MSG_MAX, .cb = nfqnl_cb, }; #ifdef CONFIG_PROC_FS struct iter_state { struct seq_net_private p; unsigned int bucket; }; static struct hlist_node *get_first(struct seq_file *seq) { struct iter_state *st = seq->private; struct net *net; struct nfnl_queue_net *q; if (!st) return NULL; net = seq_file_net(seq); q = nfnl_queue_pernet(net); for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) { if (!hlist_empty(&q->instance_table[st->bucket])) return q->instance_table[st->bucket].first; } return NULL; } static struct hlist_node *get_next(struct seq_file *seq, struct hlist_node *h) { struct iter_state *st = seq->private; struct net *net = seq_file_net(seq); h = h->next; while (!h) { struct nfnl_queue_net *q; if (++st->bucket >= INSTANCE_BUCKETS) return NULL; q = nfnl_queue_pernet(net); h = q->instance_table[st->bucket].first; } return h; } static struct hlist_node *get_idx(struct seq_file *seq, loff_t pos) { struct hlist_node *head; head = get_first(seq); if (head) while (pos && (head = get_next(seq, head))) pos--; return pos ? NULL : head; } static void *seq_start(struct seq_file *s, loff_t *pos) __acquires(nfnl_queue_pernet(seq_file_net(s))->instances_lock) { spin_lock(&nfnl_queue_pernet(seq_file_net(s))->instances_lock); return get_idx(s, *pos); } static void *seq_next(struct seq_file *s, void *v, loff_t *pos) { (*pos)++; return get_next(s, v); } static void seq_stop(struct seq_file *s, void *v) __releases(nfnl_queue_pernet(seq_file_net(s))->instances_lock) { spin_unlock(&nfnl_queue_pernet(seq_file_net(s))->instances_lock); } static int seq_show(struct seq_file *s, void *v) { const struct nfqnl_instance *inst = v; seq_printf(s, "%5u %6u %5u %1u %5u %5u %5u %8u %2d\n", inst->queue_num, inst->peer_portid, inst->queue_total, inst->copy_mode, inst->copy_range, inst->queue_dropped, inst->queue_user_dropped, inst->id_sequence, 1); return 0; } static const struct seq_operations nfqnl_seq_ops = { .start = seq_start, .next = seq_next, .stop = seq_stop, .show = seq_show, }; #endif /* PROC_FS */ static int __net_init nfnl_queue_net_init(struct net *net) { unsigned int i; struct nfnl_queue_net *q = nfnl_queue_pernet(net); for (i = 0; i < INSTANCE_BUCKETS; i++) INIT_HLIST_HEAD(&q->instance_table[i]); spin_lock_init(&q->instances_lock); #ifdef CONFIG_PROC_FS if (!proc_create_net("nfnetlink_queue", 0440, net->nf.proc_netfilter, &nfqnl_seq_ops, sizeof(struct iter_state))) return -ENOMEM; #endif return 0; } static void __net_exit nfnl_queue_net_exit(struct net *net) { struct nfnl_queue_net *q = nfnl_queue_pernet(net); unsigned int i; #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_queue", net->nf.proc_netfilter); #endif for (i = 0; i < INSTANCE_BUCKETS; i++) WARN_ON_ONCE(!hlist_empty(&q->instance_table[i])); } static struct pernet_operations nfnl_queue_net_ops = { .init = nfnl_queue_net_init, .exit = nfnl_queue_net_exit, .id = &nfnl_queue_net_id, .size = sizeof(struct nfnl_queue_net), }; static int __init nfnetlink_queue_init(void) { int status; status = register_pernet_subsys(&nfnl_queue_net_ops); if (status < 0) { pr_err("failed to register pernet ops\n"); goto out; } netlink_register_notifier(&nfqnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfqnl_subsys); if (status < 0) { pr_err("failed to create netlink socket\n"); goto cleanup_netlink_notifier; } status = register_netdevice_notifier(&nfqnl_dev_notifier); if (status < 0) { pr_err("failed to register netdevice notifier\n"); goto cleanup_netlink_subsys; } nf_register_queue_handler(&nfqh); return status; cleanup_netlink_subsys: nfnetlink_subsys_unregister(&nfqnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfqnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_queue_net_ops); out: return status; } static void __exit nfnetlink_queue_fini(void) { nf_unregister_queue_handler(); unregister_netdevice_notifier(&nfqnl_dev_notifier); nfnetlink_subsys_unregister(&nfqnl_subsys); netlink_unregister_notifier(&nfqnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_queue_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ } MODULE_DESCRIPTION("netfilter packet queue handler"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_QUEUE); module_init(nfnetlink_queue_init); module_exit(nfnetlink_queue_fini); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2023 Isovalent */ #ifndef __NET_TCX_H #define __NET_TCX_H #include <linux/bpf.h> #include <linux/bpf_mprog.h> #include <net/sch_generic.h> struct mini_Qdisc; struct tcx_entry { struct mini_Qdisc __rcu *miniq; struct bpf_mprog_bundle bundle; u32 miniq_active; struct rcu_head rcu; }; struct tcx_link { struct bpf_link link; struct net_device *dev; u32 location; }; static inline void tcx_set_ingress(struct sk_buff *skb, bool ingress) { #ifdef CONFIG_NET_XGRESS skb->tc_at_ingress = ingress; #endif } #ifdef CONFIG_NET_XGRESS static inline struct tcx_entry *tcx_entry(struct bpf_mprog_entry *entry) { struct bpf_mprog_bundle *bundle = entry->parent; return container_of(bundle, struct tcx_entry, bundle); } static inline struct tcx_link *tcx_link(const struct bpf_link *link) { return container_of(link, struct tcx_link, link); } void tcx_inc(void); void tcx_dec(void); static inline void tcx_entry_sync(void) { /* bpf_mprog_entry got a/b swapped, therefore ensure that * there are no inflight users on the old one anymore. */ synchronize_rcu(); } static inline void tcx_entry_update(struct net_device *dev, struct bpf_mprog_entry *entry, bool ingress) { ASSERT_RTNL(); if (ingress) rcu_assign_pointer(dev->tcx_ingress, entry); else rcu_assign_pointer(dev->tcx_egress, entry); } static inline struct bpf_mprog_entry * tcx_entry_fetch(struct net_device *dev, bool ingress) { ASSERT_RTNL(); if (ingress) return rcu_dereference_rtnl(dev->tcx_ingress); else return rcu_dereference_rtnl(dev->tcx_egress); } static inline struct bpf_mprog_entry *tcx_entry_create_noprof(void) { struct tcx_entry *tcx = kzalloc_noprof(sizeof(*tcx), GFP_KERNEL); if (tcx) { bpf_mprog_bundle_init(&tcx->bundle); return &tcx->bundle.a; } return NULL; } #define tcx_entry_create(...) alloc_hooks(tcx_entry_create_noprof(__VA_ARGS__)) static inline void tcx_entry_free(struct bpf_mprog_entry *entry) { kfree_rcu(tcx_entry(entry), rcu); } static inline struct bpf_mprog_entry * tcx_entry_fetch_or_create(struct net_device *dev, bool ingress, bool *created) { struct bpf_mprog_entry *entry = tcx_entry_fetch(dev, ingress); *created = false; if (!entry) { entry = tcx_entry_create(); if (!entry) return NULL; *created = true; } return entry; } static inline void tcx_skeys_inc(bool ingress) { tcx_inc(); if (ingress) net_inc_ingress_queue(); else net_inc_egress_queue(); } static inline void tcx_skeys_dec(bool ingress) { if (ingress) net_dec_ingress_queue(); else net_dec_egress_queue(); tcx_dec(); } static inline void tcx_miniq_inc(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active++; } static inline void tcx_miniq_dec(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active--; } static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); return bpf_mprog_total(entry) || tcx_entry(entry)->miniq_active; } static inline enum tcx_action_base tcx_action_code(struct sk_buff *skb, int code) { switch (code) { case TCX_PASS: skb->tc_index = qdisc_skb_cb(skb)->tc_classid; fallthrough; case TCX_DROP: case TCX_REDIRECT: return code; case TCX_NEXT: default: return TCX_NEXT; } } #endif /* CONFIG_NET_XGRESS */ #if defined(CONFIG_NET_XGRESS) && defined(CONFIG_BPF_SYSCALL) int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); void tcx_uninstall(struct net_device *dev, bool ingress); int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); static inline void dev_tcx_uninstall(struct net_device *dev) { ASSERT_RTNL(); tcx_uninstall(dev, true); tcx_uninstall(dev, false); } #else static inline int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline void dev_tcx_uninstall(struct net_device *dev) { } #endif /* CONFIG_NET_XGRESS && CONFIG_BPF_SYSCALL */ #endif /* __NET_TCX_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 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 | /* 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 the Forwarding Information Base. * * Authors: A.N.Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #ifndef _NET_IP_FIB_H #define _NET_IP_FIB_H #include <net/flow.h> #include <linux/seq_file.h> #include <linux/rcupdate.h> #include <net/fib_notifier.h> #include <net/fib_rules.h> #include <net/inet_dscp.h> #include <net/inetpeer.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/refcount.h> #include <linux/ip.h> #include <linux/in_route.h> struct fib_config { u8 fc_dst_len; dscp_t fc_dscp; u8 fc_protocol; u8 fc_scope; u8 fc_type; u8 fc_gw_family; /* 2 bytes unused */ u32 fc_table; __be32 fc_dst; union { __be32 fc_gw4; struct in6_addr fc_gw6; }; int fc_oif; u32 fc_flags; u32 fc_priority; __be32 fc_prefsrc; u32 fc_nh_id; struct nlattr *fc_mx; struct rtnexthop *fc_mp; int fc_mx_len; int fc_mp_len; u32 fc_flow; u32 fc_nlflags; struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; }; struct fib_info; struct rtable; struct fib_nh_exception { struct fib_nh_exception __rcu *fnhe_next; int fnhe_genid; __be32 fnhe_daddr; u32 fnhe_pmtu; bool fnhe_mtu_locked; __be32 fnhe_gw; unsigned long fnhe_expires; struct rtable __rcu *fnhe_rth_input; struct rtable __rcu *fnhe_rth_output; unsigned long fnhe_stamp; struct rcu_head rcu; }; struct fnhe_hash_bucket { struct fib_nh_exception __rcu *chain; }; #define FNHE_HASH_SHIFT 11 #define FNHE_HASH_SIZE (1 << FNHE_HASH_SHIFT) #define FNHE_RECLAIM_DEPTH 5 struct fib_nh_common { struct net_device *nhc_dev; netdevice_tracker nhc_dev_tracker; int nhc_oif; unsigned char nhc_scope; u8 nhc_family; u8 nhc_gw_family; unsigned char nhc_flags; struct lwtunnel_state *nhc_lwtstate; union { __be32 ipv4; struct in6_addr ipv6; } nhc_gw; int nhc_weight; atomic_t nhc_upper_bound; /* v4 specific, but allows fib6_nh with v4 routes */ struct rtable __rcu * __percpu *nhc_pcpu_rth_output; struct rtable __rcu *nhc_rth_input; struct fnhe_hash_bucket __rcu *nhc_exceptions; }; struct fib_nh { struct fib_nh_common nh_common; struct hlist_node nh_hash; struct fib_info *nh_parent; #ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif __be32 nh_saddr; int nh_saddr_genid; #define fib_nh_family nh_common.nhc_family #define fib_nh_dev nh_common.nhc_dev #define fib_nh_dev_tracker nh_common.nhc_dev_tracker #define fib_nh_oif nh_common.nhc_oif #define fib_nh_flags nh_common.nhc_flags #define fib_nh_lws nh_common.nhc_lwtstate #define fib_nh_scope nh_common.nhc_scope #define fib_nh_gw_family nh_common.nhc_gw_family #define fib_nh_gw4 nh_common.nhc_gw.ipv4 #define fib_nh_gw6 nh_common.nhc_gw.ipv6 #define fib_nh_weight nh_common.nhc_weight #define fib_nh_upper_bound nh_common.nhc_upper_bound }; /* * This structure contains data shared by many of routes. */ struct nexthop; struct fib_info { struct hlist_node fib_hash; struct hlist_node fib_lhash; struct list_head nh_list; struct net *fib_net; refcount_t fib_treeref; refcount_t fib_clntref; unsigned int fib_flags; unsigned char fib_dead; unsigned char fib_protocol; unsigned char fib_scope; unsigned char fib_type; __be32 fib_prefsrc; u32 fib_tb_id; u32 fib_priority; struct dst_metrics *fib_metrics; #define fib_mtu fib_metrics->metrics[RTAX_MTU-1] #define fib_window fib_metrics->metrics[RTAX_WINDOW-1] #define fib_rtt fib_metrics->metrics[RTAX_RTT-1] #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; bool fib_nh_is_v6; bool nh_updated; bool pfsrc_removed; struct nexthop *nh; struct rcu_head rcu; struct fib_nh fib_nh[] __counted_by(fib_nhs); }; int __net_init fib4_semantics_init(struct net *net); void __net_exit fib4_semantics_exit(struct net *net); #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rule; #endif struct fib_table; struct fib_result { __be32 prefix; unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; u32 tclassid; dscp_t dscp; struct fib_nh_common *nhc; struct fib_info *fi; struct fib_table *table; struct hlist_head *fa_head; }; struct fib_result_nl { __be32 fl_addr; /* To be looked up*/ u32 fl_mark; unsigned char fl_tos; unsigned char fl_scope; unsigned char tb_id_in; unsigned char tb_id; /* Results */ unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; int err; }; #ifdef CONFIG_IP_MULTIPLE_TABLES #define FIB_TABLE_HASHSZ 256 #else #define FIB_TABLE_HASHSZ 2 #endif __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope); __be32 fib_result_prefsrc(struct net *net, struct fib_result *res); #define FIB_RES_NHC(res) ((res).nhc) #define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev) #define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif) struct fib_rt_info { struct fib_info *fi; u32 tb_id; __be32 dst; int dst_len; dscp_t dscp; u8 type; u8 offload:1, trap:1, offload_failed:1, unused:5; }; struct fib_entry_notifier_info { struct fib_notifier_info info; /* must be first */ u32 dst; int dst_len; struct fib_info *fi; dscp_t dscp; u8 type; u32 tb_id; }; struct fib_nh_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib_nh *fib_nh; }; int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int __net_init fib4_notifier_init(struct net *net); void __net_exit fib4_notifier_exit(struct net *net); void fib_info_notify_update(struct net *net, struct nl_info *info); int fib_notify(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); struct fib_table { struct hlist_node tb_hlist; u32 tb_id; int tb_num_default; struct rcu_head rcu; unsigned long *tb_data; unsigned long __data[]; }; struct fib_dump_filter { u32 table_id; /* filter_set is an optimization that an entry is set */ bool filter_set; bool dump_routes; bool dump_exceptions; bool rtnl_held; unsigned char protocol; unsigned char rt_type; unsigned int flags; struct net_device *dev; }; int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_delete(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter); int fib_table_flush(struct net *net, struct fib_table *table, bool flush_all); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); #ifndef CONFIG_IP_MULTIPLE_TABLES #define TABLE_LOCAL_INDEX (RT_TABLE_LOCAL & (FIB_TABLE_HASHSZ - 1)) #define TABLE_MAIN_INDEX (RT_TABLE_MAIN & (FIB_TABLE_HASHSZ - 1)) static inline struct fib_table *fib_get_table(struct net *net, u32 id) { struct hlist_node *tb_hlist; struct hlist_head *ptr; ptr = id == RT_TABLE_LOCAL ? &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] : &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]; tb_hlist = rcu_dereference_rtnl(hlist_first_rcu(ptr)); return hlist_entry(tb_hlist, struct fib_table, tb_hlist); } static inline struct fib_table *fib_new_table(struct net *net, u32 id) { return fib_get_table(net, id); } static inline int fib_lookup(struct net *net, const struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; rcu_read_lock(); tb = fib_get_table(net, RT_TABLE_MAIN); if (tb) err = fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF); if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } static inline bool fib4_has_custom_rules(const struct net *net) { return false; } static inline bool fib4_rule_default(const struct fib_rule *rule) { return true; } static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static inline unsigned int fib4_rules_seq_read(const struct net *net) { return 0; } static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { return false; } #else /* CONFIG_IP_MULTIPLE_TABLES */ int __net_init fib4_rules_init(struct net *net); void __net_exit fib4_rules_exit(struct net *net); struct fib_table *fib_new_table(struct net *net, u32 id); struct fib_table *fib_get_table(struct net *net, u32 id); int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags); static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; flags |= FIB_LOOKUP_NOREF; if (net->ipv4.fib_has_custom_rules) return __fib_lookup(net, flp, res, flags); rcu_read_lock(); res->tclassid = 0; tb = rcu_dereference_rtnl(net->ipv4.fib_main); if (tb) err = fib_table_lookup(tb, flp, res, flags); if (!err) goto out; tb = rcu_dereference_rtnl(net->ipv4.fib_default); if (tb) err = fib_table_lookup(tb, flp, res, flags); out: if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } static inline bool fib4_has_custom_rules(const struct net *net) { return net->ipv4.fib_has_custom_rules; } bool fib4_rule_default(const struct fib_rule *rule); int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); unsigned int fib4_rules_seq_read(const struct net *net); static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; if (!net->ipv4.fib_rules_require_fldissect) return false; memset(flkeys, 0, sizeof(*flkeys)); __skb_flow_dissect(net, skb, &flow_keys_dissector, flkeys, NULL, 0, 0, 0, flag); fl4->fl4_sport = flkeys->ports.src; fl4->fl4_dport = flkeys->ports.dst; fl4->flowi4_proto = flkeys->basic.ip_proto; return true; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ static inline bool fib_dscp_masked_match(dscp_t dscp, const struct flowi4 *fl4) { return dscp == inet_dsfield_to_dscp(RT_TOS(fl4->flowi4_tos)); } /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack); __be32 fib_compute_spec_dst(struct sk_buff *skb); bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); static inline enum skb_drop_reason fib_validate_source_reason(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, struct in_device *idev, u32 *itag) { int err = fib_validate_source(skb, src, dst, dscp, oif, dev, idev, itag); if (err < 0) return -err; return SKB_NOT_DROPPED_YET; } #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { return atomic_read(&net->ipv4.fib_num_tclassid_users); } #else static inline int fib_num_tclassid_users(struct net *net) { return 0; } #endif int fib_unmerge(struct net *net); static inline bool nhc_l3mdev_matches_dev(const struct fib_nh_common *nhc, const struct net_device *dev) { if (nhc->nhc_dev == dev || l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) return true; return false; } /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned char nh_flags); void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); /* Fields used for sysctl_fib_multipath_hash_fields. * Common to IPv4 and IPv6. * * Add new fields at the end. This is user API. */ #define FIB_MULTIPATH_HASH_FIELD_SRC_IP BIT(0) #define FIB_MULTIPATH_HASH_FIELD_DST_IP BIT(1) #define FIB_MULTIPATH_HASH_FIELD_IP_PROTO BIT(2) #define FIB_MULTIPATH_HASH_FIELD_FLOWLABEL BIT(3) #define FIB_MULTIPATH_HASH_FIELD_SRC_PORT BIT(4) #define FIB_MULTIPATH_HASH_FIELD_DST_PORT BIT(5) #define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP BIT(6) #define FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP BIT(7) #define FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO BIT(8) #define FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL BIT(9) #define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT BIT(10) #define FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT BIT(11) #define FIB_MULTIPATH_HASH_FIELD_OUTER_MASK \ (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_IP_PROTO | \ FIB_MULTIPATH_HASH_FIELD_FLOWLABEL | \ FIB_MULTIPATH_HASH_FIELD_SRC_PORT | \ FIB_MULTIPATH_HASH_FIELD_DST_PORT) #define FIB_MULTIPATH_HASH_FIELD_INNER_MASK \ (FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO | \ FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL | \ FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT | \ FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) #define FIB_MULTIPATH_HASH_FIELD_ALL_MASK \ (FIB_MULTIPATH_HASH_FIELD_OUTER_MASK | \ FIB_MULTIPATH_HASH_FIELD_INNER_MASK) #define FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK \ (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_IP_PROTO) #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); static void fib_multipath_hash_construct_key(siphash_key_t *key, u32 mp_seed) { u64 mp_seed_64 = mp_seed; key->key[0] = (mp_seed_64 << 32) | mp_seed_64; key->key[1] = key->key[0]; } static inline u32 fib_multipath_hash_from_keys(const struct net *net, struct flow_keys *keys) { siphash_aligned_key_t hash_key; u32 mp_seed; mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed; fib_multipath_hash_construct_key(&hash_key, mp_seed); return flow_hash_from_keys_seed(keys, &hash_key); } #else static inline u32 fib_multipath_hash_from_keys(const struct net *net, struct flow_keys *keys) { return flow_hash_from_keys(keys); } #endif int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, struct netlink_ext_ack *extack); void fib_select_multipath(struct fib_result *res, int hash); void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb); int fib_nh_init(struct net *net, struct fib_nh *fib_nh, struct fib_config *cfg, int nh_weight, struct netlink_ext_ack *extack); void fib_nh_release(struct net *net, struct fib_nh *fib_nh); int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc, struct nlattr *fc_encap, u16 fc_encap_type, void *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib_nh_common_release(struct fib_nh_common *nhc); /* Exported by fib_trie.c */ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri); void fib_trie_init(void); struct fib_table *fib_trie_table(u32 id, struct fib_table *alias); bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, const struct flowi4 *flp); static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { #ifdef CONFIG_IP_ROUTE_CLASSID struct fib_nh_common *nhc = res->nhc; #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); *itag = nh->nh_tclassid << 16; } else { *itag = 0; } #ifdef CONFIG_IP_MULTIPLE_TABLES rtag = res->tclassid; if (*itag == 0) *itag = (rtag<<16); *itag |= (rtag>>16); #endif #endif } void fib_flush(struct net *net); void free_fib_info(struct fib_info *fi); static inline void fib_info_hold(struct fib_info *fi) { refcount_inc(&fi->fib_clntref); } static inline void fib_info_put(struct fib_info *fi) { if (refcount_dec_and_test(&fi->fib_clntref)) free_fib_info(fi); } #ifdef CONFIG_PROC_FS int __net_init fib_proc_init(struct net *net); void __net_exit fib_proc_exit(struct net *net); #else static inline int fib_proc_init(struct net *net) { return 0; } static inline void fib_proc_exit(struct net *net) { } #endif u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr); int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb); int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh, u8 rt_family, unsigned char *flags, bool skip_oif); int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh, int nh_weight, u8 rt_family, u32 nh_tclassid); #endif /* _NET_FIB_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 | // SPDX-License-Identifier: GPL-2.0-only /* * VXLAN: Virtual eXtensible Local Area Network * * Copyright (c) 2012-2013 Vyatta Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/udp.h> #include <linux/igmp.h> #include <linux/if_ether.h> #include <linux/ethtool.h> #include <net/arp.h> #include <net/ndisc.h> #include <net/gro.h> #include <net/ipv6_stubs.h> #include <net/ip.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netdev_lock.h> #include <net/tun_proto.h> #include <net/vxlan.h> #include <net/nexthop.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_tunnel.h> #include <net/ip6_checksum.h> #endif #include "vxlan_private.h" #define VXLAN_VERSION "0.1" #define FDB_AGE_DEFAULT 300 /* 5 min */ #define FDB_AGE_INTERVAL (10 * HZ) /* rescan interval */ /* UDP port for VXLAN traffic. * The IANA assigned port is 4789, but the Linux default is 8472 * for compatibility with early adopters. */ static unsigned short vxlan_port __read_mostly = 8472; module_param_named(udp_port, vxlan_port, ushort, 0444); MODULE_PARM_DESC(udp_port, "Destination UDP port"); static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); unsigned int vxlan_net_id; const u8 all_zeros_mac[ETH_ALEN + 2]; static struct rtnl_link_ops vxlan_link_ops; static int vxlan_sock_add(struct vxlan_dev *vxlan); static void vxlan_vs_del_dev(struct vxlan_dev *vxlan); /* salt for hash table */ static u32 vxlan_salt __read_mostly; static inline bool vxlan_collect_metadata(struct vxlan_sock *vs) { return vs->flags & VXLAN_F_COLLECT_METADATA || ip_tunnel_collect_metadata(); } /* Find VXLAN socket based on network namespace, address family, UDP port, * enabled unshareable flags and socket device binding (see l3mdev with * non-default VRF). */ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family, __be16 port, u32 flags, int ifindex) { struct vxlan_sock *vs; flags &= VXLAN_F_RCV_FLAGS; hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) { if (inet_sk(vs->sock->sk)->inet_sport == port && vxlan_get_sk_family(vs) == family && vs->flags == flags && vs->sock->sk->sk_bound_dev_if == ifindex) return vs; } return NULL; } static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, int ifindex, __be32 vni, struct vxlan_vni_node **vninode) { struct vxlan_vni_node *vnode; struct vxlan_dev_node *node; /* For flow based devices, map all packets to VNI 0 */ if (vs->flags & VXLAN_F_COLLECT_METADATA && !(vs->flags & VXLAN_F_VNIFILTER)) vni = 0; hlist_for_each_entry_rcu(node, vni_head(vs, vni), hlist) { if (!node->vxlan) continue; vnode = NULL; if (node->vxlan->cfg.flags & VXLAN_F_VNIFILTER) { vnode = vxlan_vnifilter_lookup(node->vxlan, vni); if (!vnode) continue; } else if (node->vxlan->default_dst.remote_vni != vni) { continue; } if (IS_ENABLED(CONFIG_IPV6)) { const struct vxlan_config *cfg = &node->vxlan->cfg; if ((cfg->flags & VXLAN_F_IPV6_LINKLOCAL) && cfg->remote_ifindex != ifindex) continue; } if (vninode) *vninode = vnode; return node->vxlan; } return NULL; } /* Look up VNI in a per net namespace table */ static struct vxlan_dev *vxlan_find_vni(struct net *net, int ifindex, __be32 vni, sa_family_t family, __be16 port, u32 flags) { struct vxlan_sock *vs; vs = vxlan_find_sock(net, family, port, flags, ifindex); if (!vs) return NULL; return vxlan_vs_find_vni(vs, ifindex, vni, NULL); } /* Fill in neighbour message in skbuff. */ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, const struct vxlan_fdb *fdb, u32 portid, u32 seq, int type, unsigned int flags, const struct vxlan_rdst *rdst) { unsigned long now = jiffies; struct nda_cacheinfo ci; bool send_ip, send_eth; struct nlmsghdr *nlh; struct nexthop *nh; struct ndmsg *ndm; int nh_family; u32 nh_id; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; ndm = nlmsg_data(nlh); memset(ndm, 0, sizeof(*ndm)); send_eth = send_ip = true; rcu_read_lock(); nh = rcu_dereference(fdb->nh); if (nh) { nh_family = nexthop_get_family(nh); nh_id = nh->id; } rcu_read_unlock(); if (type == RTM_GETNEIGH) { if (rdst) { send_ip = !vxlan_addr_any(&rdst->remote_ip); ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET; } else if (nh) { ndm->ndm_family = nh_family; } send_eth = !is_zero_ether_addr(fdb->eth_addr); } else ndm->ndm_family = AF_BRIDGE; ndm->ndm_state = fdb->state; ndm->ndm_ifindex = vxlan->dev->ifindex; ndm->ndm_flags = fdb->flags; if (rdst && rdst->offloaded) ndm->ndm_flags |= NTF_OFFLOADED; ndm->ndm_type = RTN_UNICAST; if (!net_eq(dev_net(vxlan->dev), vxlan->net) && nla_put_s32(skb, NDA_LINK_NETNSID, peernet2id(dev_net(vxlan->dev), vxlan->net))) goto nla_put_failure; if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr)) goto nla_put_failure; if (nh) { if (nla_put_u32(skb, NDA_NH_ID, nh_id)) goto nla_put_failure; } else if (rdst) { if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip)) goto nla_put_failure; if (rdst->remote_port && rdst->remote_port != vxlan->cfg.dst_port && nla_put_be16(skb, NDA_PORT, rdst->remote_port)) goto nla_put_failure; if (rdst->remote_vni != vxlan->default_dst.remote_vni && nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni))) goto nla_put_failure; if (rdst->remote_ifindex && nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex)) goto nla_put_failure; } if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && fdb->vni && nla_put_u32(skb, NDA_SRC_VNI, be32_to_cpu(fdb->vni))) goto nla_put_failure; ci.ndm_used = jiffies_to_clock_t(now - READ_ONCE(fdb->used)); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - READ_ONCE(fdb->updated)); ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static inline size_t vxlan_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct in6_addr)) /* NDA_DST */ + nla_total_size(sizeof(__be16)) /* NDA_PORT */ + nla_total_size(sizeof(__be32)) /* NDA_VNI */ + nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */ + nla_total_size(sizeof(__s32)) /* NDA_LINK_NETNSID */ + nla_total_size(sizeof(struct nda_cacheinfo)); } static void __vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, int type) { struct net *net = dev_net(vxlan->dev); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(vxlan_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, rd); if (err < 0) { /* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan, const struct vxlan_fdb *fdb, const struct vxlan_rdst *rd, struct netlink_ext_ack *extack, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { fdb_info->info.dev = vxlan->dev; fdb_info->info.extack = extack; fdb_info->remote_ip = rd->remote_ip; fdb_info->remote_port = rd->remote_port; fdb_info->remote_vni = rd->remote_vni; fdb_info->remote_ifindex = rd->remote_ifindex; memcpy(fdb_info->eth_addr, fdb->eth_addr, ETH_ALEN); fdb_info->vni = fdb->vni; fdb_info->offloaded = rd->offloaded; fdb_info->added_by_user = fdb->flags & NTF_VXLAN_ADDED_BY_USER; } static int vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, bool adding, struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info info; enum switchdev_notifier_type notifier_type; int ret; if (WARN_ON(!rd)) return 0; notifier_type = adding ? SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE : SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE; vxlan_fdb_switchdev_notifier_info(vxlan, fdb, rd, NULL, &info); ret = call_switchdev_notifiers(notifier_type, vxlan->dev, &info.info, extack); return notifier_to_errno(ret); } static int vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, int type, bool swdev_notify, struct netlink_ext_ack *extack) { int err; if (swdev_notify && rd) { switch (type) { case RTM_NEWNEIGH: err = vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, true, extack); if (err) return err; break; case RTM_DELNEIGH: vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, false, extack); break; } } __vxlan_fdb_notify(vxlan, fdb, rd, type); return 0; } static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb f = { .state = NUD_STALE, }; struct vxlan_rdst remote = { .remote_ip = *ipa, /* goes to NDA_DST */ .remote_vni = cpu_to_be32(VXLAN_N_VID), }; vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN]) { struct vxlan_fdb f = { .state = NUD_STALE, }; struct vxlan_rdst remote = { }; memcpy(f.eth_addr, eth_addr, ETH_ALEN); vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } /* Hash Ethernet address */ static u32 eth_hash(const unsigned char *addr) { u64 value = get_unaligned((u64 *)addr); /* only want 6 bytes */ #ifdef __BIG_ENDIAN value >>= 16; #else value <<= 16; #endif return hash_64(value, FDB_HASH_BITS); } u32 eth_vni_hash(const unsigned char *addr, __be32 vni) { /* use 1 byte of OUI and 3 bytes of NIC */ u32 key = get_unaligned((u32 *)(addr + 2)); return jhash_2words(key, vni, vxlan_salt) & (FDB_HASH_SIZE - 1); } u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) return eth_vni_hash(mac, vni); else return eth_hash(mac); } /* Hash chain to use given mac address */ static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { return &vxlan->fdb_head[fdb_head_index(vxlan, mac, vni)]; } /* Look up Ethernet address in forwarding table */ static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { struct hlist_head *head = vxlan_fdb_head(vxlan, mac, vni); struct vxlan_fdb *f; hlist_for_each_entry_rcu(f, head, hlist) { if (ether_addr_equal(mac, f->eth_addr)) { if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { if (vni == f->vni) return f; } else { return f; } } } return NULL; } static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { struct vxlan_fdb *f; f = __vxlan_find_mac(vxlan, mac, vni); if (f) { unsigned long now = jiffies; if (READ_ONCE(f->used) != now) WRITE_ONCE(f->used, now); } return f; } /* caller should hold vxlan->hash_lock */ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex) { struct vxlan_rdst *rd; list_for_each_entry(rd, &f->remotes, list) { if (vxlan_addr_equal(&rd->remote_ip, ip) && rd->remote_port == port && rd->remote_vni == vni && rd->remote_ifindex == ifindex) return rd; } return NULL; } int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); u8 eth_addr[ETH_ALEN + 2] = { 0 }; struct vxlan_rdst *rdst; struct vxlan_fdb *f; int rc = 0; if (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)) return -EINVAL; ether_addr_copy(eth_addr, mac); rcu_read_lock(); f = __vxlan_find_mac(vxlan, eth_addr, vni); if (!f) { rc = -ENOENT; goto out; } rdst = first_remote_rcu(f); vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, NULL, fdb_info); out: rcu_read_unlock(); return rc; } EXPORT_SYMBOL_GPL(vxlan_fdb_find_uc); static int vxlan_fdb_notify_one(struct notifier_block *nb, const struct vxlan_dev *vxlan, const struct vxlan_fdb *f, const struct vxlan_rdst *rdst, struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info fdb_info; int rc; vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, extack, &fdb_info); rc = nb->notifier_call(nb, SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, &fdb_info); return notifier_to_errno(rc); } int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan; struct vxlan_rdst *rdst; struct vxlan_fdb *f; unsigned int h; int rc = 0; if (!netif_is_vxlan(dev)) return -EINVAL; vxlan = netdev_priv(dev); for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) { if (f->vni == vni) { list_for_each_entry(rdst, &f->remotes, list) { rc = vxlan_fdb_notify_one(nb, vxlan, f, rdst, extack); if (rc) goto unlock; } } } spin_unlock_bh(&vxlan->hash_lock[h]); } return 0; unlock: spin_unlock_bh(&vxlan->hash_lock[h]); return rc; } EXPORT_SYMBOL_GPL(vxlan_fdb_replay); void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni) { struct vxlan_dev *vxlan; struct vxlan_rdst *rdst; struct vxlan_fdb *f; unsigned int h; if (!netif_is_vxlan(dev)) return; vxlan = netdev_priv(dev); for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) if (f->vni == vni) list_for_each_entry(rdst, &f->remotes, list) rdst->offloaded = false; spin_unlock_bh(&vxlan->hash_lock[h]); } } EXPORT_SYMBOL_GPL(vxlan_fdb_clear_offload); /* Replace destination of unicast mac */ static int vxlan_fdb_replace(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex, struct vxlan_rdst *oldrd) { struct vxlan_rdst *rd; rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); if (rd) return 0; rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list); if (!rd) return 0; *oldrd = *rd; dst_cache_reset(&rd->dst_cache); rd->remote_ip = *ip; rd->remote_port = port; rd->remote_vni = vni; rd->remote_ifindex = ifindex; rd->offloaded = false; return 1; } /* Add/update destinations for multicast */ static int vxlan_fdb_append(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex, struct vxlan_rdst **rdp) { struct vxlan_rdst *rd; rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); if (rd) return 0; rd = kmalloc(sizeof(*rd), GFP_ATOMIC); if (rd == NULL) return -ENOMEM; if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) { kfree(rd); return -ENOMEM; } rd->remote_ip = *ip; rd->remote_port = port; rd->offloaded = false; rd->remote_vni = vni; rd->remote_ifindex = ifindex; list_add_tail_rcu(&rd->list, &f->remotes); *rdp = rd; return 1; } static bool vxlan_parse_gpe_proto(const struct vxlanhdr *hdr, __be16 *protocol) { const struct vxlanhdr_gpe *gpe = (const struct vxlanhdr_gpe *)hdr; /* Need to have Next Protocol set for interfaces in GPE mode. */ if (!gpe->np_applied) return false; /* "The initial version is 0. If a receiver does not support the * version indicated it MUST drop the packet. */ if (gpe->version != 0) return false; /* "When the O bit is set to 1, the packet is an OAM packet and OAM * processing MUST occur." However, we don't implement OAM * processing, thus drop the packet. */ if (gpe->oam_flag) return false; *protocol = tun_p_to_eth_p(gpe->next_protocol); if (!*protocol) return false; return true; } static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, unsigned int off, struct vxlanhdr *vh, size_t hdrlen, __be32 vni_field, struct gro_remcsum *grc, bool nopartial) { size_t start, offset; if (skb->remcsum_offload) return vh; if (!NAPI_GRO_CB(skb)->csum_valid) return NULL; start = vxlan_rco_start(vni_field); offset = start + vxlan_rco_offset(vni_field); vh = skb_gro_remcsum_process(skb, (void *)vh, off, hdrlen, start, offset, grc, nopartial); skb->remcsum_offload = 1; return vh; } static struct vxlanhdr *vxlan_gro_prepare_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb, struct gro_remcsum *grc) { struct sk_buff *p; struct vxlanhdr *vh, *vh2; unsigned int hlen, off_vx; struct vxlan_sock *vs = rcu_dereference_sk_user_data(sk); __be32 flags; skb_gro_remcsum_init(grc); off_vx = skb_gro_offset(skb); hlen = off_vx + sizeof(*vh); vh = skb_gro_header(skb, hlen, off_vx); if (unlikely(!vh)) return NULL; skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr)); flags = vh->vx_flags; if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr), vh->vx_vni, grc, !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL)); if (!vh) return NULL; } skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */ list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; vh2 = (struct vxlanhdr *)(p->data + off_vx); if (vh->vx_flags != vh2->vx_flags || vh->vx_vni != vh2->vx_vni) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } return vh; } static struct sk_buff *vxlan_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct gro_remcsum grc; int flush = 1; if (vxlan_gro_prepare_receive(sk, head, skb, &grc)) { pp = call_gro_receive(eth_gro_receive, head, skb); flush = 0; } skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static struct sk_buff *vxlan_gpe_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { const struct packet_offload *ptype; struct sk_buff *pp = NULL; struct gro_remcsum grc; struct vxlanhdr *vh; __be16 protocol; int flush = 1; vh = vxlan_gro_prepare_receive(sk, head, skb, &grc); if (vh) { if (!vxlan_parse_gpe_proto(vh, &protocol)) goto out; ptype = gro_find_receive_by_type(protocol); if (!ptype) goto out; pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; } out: skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { /* Sets 'skb->inner_mac_header' since we are always called with * 'skb->encapsulation' set. */ return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); } static int vxlan_gpe_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct vxlanhdr *vh = (struct vxlanhdr *)(skb->data + nhoff); const struct packet_offload *ptype; int err = -ENOSYS; __be16 protocol; if (!vxlan_parse_gpe_proto(vh, &protocol)) return err; ptype = gro_find_complete_by_type(protocol); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); return err; } static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, const u8 *mac, __u16 state, __be32 src_vni, __u16 ndm_flags) { struct vxlan_fdb *f; f = kmalloc(sizeof(*f), GFP_ATOMIC); if (!f) return NULL; f->state = state; f->flags = ndm_flags; f->updated = f->used = jiffies; f->vni = src_vni; f->nh = NULL; RCU_INIT_POINTER(f->vdev, vxlan); INIT_LIST_HEAD(&f->nh_list); INIT_LIST_HEAD(&f->remotes); memcpy(f->eth_addr, mac, ETH_ALEN); return f; } static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac, __be32 src_vni, struct vxlan_fdb *f) { ++vxlan->addrcnt; hlist_add_head_rcu(&f->hlist, vxlan_fdb_head(vxlan, mac, src_vni)); } static int vxlan_fdb_nh_update(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, u32 nhid, struct netlink_ext_ack *extack) { struct nexthop *old_nh = rtnl_dereference(fdb->nh); struct nexthop *nh; int err = -EINVAL; if (old_nh && old_nh->id == nhid) return 0; nh = nexthop_find_by_id(vxlan->net, nhid); if (!nh) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); goto err_inval; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); nh = NULL; goto err_inval; } if (!nexthop_is_fdb(nh)) { NL_SET_ERR_MSG(extack, "Nexthop is not a fdb nexthop"); goto err_inval; } if (!nexthop_is_multipath(nh)) { NL_SET_ERR_MSG(extack, "Nexthop is not a multipath group"); goto err_inval; } /* check nexthop group family */ switch (vxlan->default_dst.remote_ip.sa.sa_family) { case AF_INET: if (!nexthop_has_v4(nh)) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); goto err_inval; } break; case AF_INET6: if (nexthop_has_v4(nh)) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); goto err_inval; } } if (old_nh) { list_del_rcu(&fdb->nh_list); nexthop_put(old_nh); } rcu_assign_pointer(fdb->nh, nh); list_add_tail_rcu(&fdb->nh_list, &nh->fdb_list); return 1; err_inval: if (nh) nexthop_put(nh); return err; } int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, struct vxlan_fdb **fdb, struct netlink_ext_ack *extack) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int rc; if (vxlan->cfg.addrmax && vxlan->addrcnt >= vxlan->cfg.addrmax) return -ENOSPC; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags); if (!f) return -ENOMEM; if (nhid) rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); else rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) goto errout; *fdb = f; return 0; errout: kfree(f); return rc; } static void __vxlan_fdb_free(struct vxlan_fdb *f) { struct vxlan_rdst *rd, *nd; struct nexthop *nh; nh = rcu_dereference_raw(f->nh); if (nh) { rcu_assign_pointer(f->nh, NULL); rcu_assign_pointer(f->vdev, NULL); nexthop_put(nh); } list_for_each_entry_safe(rd, nd, &f->remotes, list) { dst_cache_destroy(&rd->dst_cache); kfree(rd); } kfree(f); } static void vxlan_fdb_free(struct rcu_head *head) { struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu); __vxlan_fdb_free(f); } static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, bool do_notify, bool swdev_notify) { struct vxlan_rdst *rd; netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr); --vxlan->addrcnt; if (do_notify) { if (rcu_access_pointer(f->nh)) vxlan_fdb_notify(vxlan, f, NULL, RTM_DELNEIGH, swdev_notify, NULL); else list_for_each_entry(rd, &f->remotes, list) vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); } hlist_del_rcu(&f->hlist); list_del_rcu(&f->nh_list); call_rcu(&f->rcu, vxlan_fdb_free); } static void vxlan_dst_free(struct rcu_head *head) { struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); dst_cache_destroy(&rd->dst_cache); kfree(rd); } static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 vni, __u32 ifindex, __u16 ndm_flags, struct vxlan_fdb *f, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_rdst *rd = NULL; struct vxlan_rdst oldrd; int notify = 0; int rc = 0; int err; if (nhid && !rcu_access_pointer(f->nh)) { NL_SET_ERR_MSG(extack, "Cannot replace an existing non nexthop fdb with a nexthop"); return -EOPNOTSUPP; } if (nhid && (flags & NLM_F_APPEND)) { NL_SET_ERR_MSG(extack, "Cannot append to a nexthop fdb"); return -EOPNOTSUPP; } /* Do not allow an externally learned entry to take over an entry added * by the user. */ if (!(fdb_flags & NTF_EXT_LEARNED) || !(f->flags & NTF_VXLAN_ADDED_BY_USER)) { if (f->state != state) { f->state = state; notify = 1; } if (f->flags != fdb_flags) { f->flags = fdb_flags; notify = 1; } } if ((flags & NLM_F_REPLACE)) { /* Only change unicasts */ if (!(is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { if (nhid) { rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); if (rc < 0) return rc; } else { rc = vxlan_fdb_replace(f, ip, port, vni, ifindex, &oldrd); } notify |= rc; } else { NL_SET_ERR_MSG(extack, "Cannot replace non-unicast fdb entries"); return -EOPNOTSUPP; } } if ((flags & NLM_F_APPEND) && (is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) return rc; notify |= rc; } if (ndm_flags & NTF_USE) WRITE_ONCE(f->updated, jiffies); if (notify) { if (rd == NULL) rd = first_remote_rtnl(f); WRITE_ONCE(f->updated, jiffies); err = vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH, swdev_notify, extack); if (err) goto err_notify; } return 0; err_notify: if (nhid) return err; if ((flags & NLM_F_REPLACE) && rc) *rd = oldrd; else if ((flags & NLM_F_APPEND) && rc) { list_del_rcu(&rd->list); call_rcu(&rd->rcu, vxlan_dst_free); } return err; } static int vxlan_fdb_update_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_fdb *f; int rc; /* Disallow replace to add a multicast entry */ if ((flags & NLM_F_REPLACE) && (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac))) return -EOPNOTSUPP; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni, vni, ifindex, fdb_flags, nhid, &f, extack); if (rc < 0) return rc; vxlan_fdb_insert(vxlan, mac, src_vni, f); rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, swdev_notify, extack); if (rc) goto err_notify; return 0; err_notify: vxlan_fdb_destroy(vxlan, f, false, false); return rc; } /* Add new entry to forwarding table -- assumes lock held */ int vxlan_fdb_update(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { struct vxlan_fdb *f; f = __vxlan_find_mac(vxlan, mac, src_vni); if (f) { if (flags & NLM_F_EXCL) { netdev_dbg(vxlan->dev, "lost race to create %pM\n", mac); return -EEXIST; } return vxlan_fdb_update_existing(vxlan, ip, state, flags, port, vni, ifindex, ndm_flags, f, nhid, swdev_notify, extack); } else { if (!(flags & NLM_F_CREATE)) return -ENOENT; return vxlan_fdb_update_create(vxlan, mac, ip, state, flags, port, src_vni, vni, ifindex, ndm_flags, nhid, swdev_notify, extack); } } static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, struct vxlan_rdst *rd, bool swdev_notify) { list_del_rcu(&rd->list); vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); call_rcu(&rd->rcu, vxlan_dst_free); } static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, union vxlan_addr *ip, __be16 *port, __be32 *src_vni, __be32 *vni, u32 *ifindex, u32 *nhid, struct netlink_ext_ack *extack) { struct net *net = dev_net(vxlan->dev); int err; if (tb[NDA_NH_ID] && (tb[NDA_DST] || tb[NDA_VNI] || tb[NDA_IFINDEX] || tb[NDA_PORT])) { NL_SET_ERR_MSG(extack, "DST, VNI, ifindex and port are mutually exclusive with NH_ID"); return -EINVAL; } if (tb[NDA_DST]) { err = vxlan_nla_get_addr(ip, tb[NDA_DST]); if (err) { NL_SET_ERR_MSG(extack, "Unsupported address family"); return err; } } else { union vxlan_addr *remote = &vxlan->default_dst.remote_ip; if (remote->sa.sa_family == AF_INET) { ip->sin.sin_addr.s_addr = htonl(INADDR_ANY); ip->sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { ip->sin6.sin6_addr = in6addr_any; ip->sa.sa_family = AF_INET6; #endif } } if (tb[NDA_PORT]) { if (nla_len(tb[NDA_PORT]) != sizeof(__be16)) { NL_SET_ERR_MSG(extack, "Invalid vxlan port"); return -EINVAL; } *port = nla_get_be16(tb[NDA_PORT]); } else { *port = vxlan->cfg.dst_port; } if (tb[NDA_VNI]) { if (nla_len(tb[NDA_VNI]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid vni"); return -EINVAL; } *vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); } else { *vni = vxlan->default_dst.remote_vni; } if (tb[NDA_SRC_VNI]) { if (nla_len(tb[NDA_SRC_VNI]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid src vni"); return -EINVAL; } *src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); } else { *src_vni = vxlan->default_dst.remote_vni; } if (tb[NDA_IFINDEX]) { struct net_device *tdev; if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid ifindex"); return -EINVAL; } *ifindex = nla_get_u32(tb[NDA_IFINDEX]); tdev = __dev_get_by_index(net, *ifindex); if (!tdev) { NL_SET_ERR_MSG(extack, "Device not found"); return -EADDRNOTAVAIL; } } else { *ifindex = 0; } *nhid = nla_get_u32_default(tb[NDA_NH_ID], 0); return 0; } /* Add static entry (via netlink) */ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags, bool *notified, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); /* struct net *net = dev_net(vxlan->dev); */ union vxlan_addr ip; __be16 port; __be32 src_vni, vni; u32 ifindex, nhid; u32 hash_index; int err; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) { pr_info("RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); return -EINVAL; } if (!tb || (!tb[NDA_DST] && !tb[NDA_NH_ID])) return -EINVAL; err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, &nhid, extack); if (err) return err; if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family) return -EAFNOSUPPORT; hash_index = fdb_head_index(vxlan, addr, src_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, port, src_vni, vni, ifindex, ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER, nhid, true, extack); spin_unlock_bh(&vxlan->hash_lock[hash_index]); if (!err) *notified = true; return err; } int __vxlan_fdb_delete(struct vxlan_dev *vxlan, const unsigned char *addr, union vxlan_addr ip, __be16 port, __be32 src_vni, __be32 vni, u32 ifindex, bool swdev_notify) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int err = -ENOENT; f = __vxlan_find_mac(vxlan, addr, src_vni); if (!f) return err; if (!vxlan_addr_any(&ip)) { rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex); if (!rd) goto out; } /* remove a destination if it's not the only one on the list, * otherwise destroy the fdb entry */ if (rd && !list_is_singular(&f->remotes)) { vxlan_fdb_dst_destroy(vxlan, f, rd, swdev_notify); goto out; } vxlan_fdb_destroy(vxlan, f, true, swdev_notify); out: return 0; } /* Delete entry (via netlink) */ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, bool *notified, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); union vxlan_addr ip; __be32 src_vni, vni; u32 ifindex, nhid; u32 hash_index; __be16 port; int err; err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, &nhid, extack); if (err) return err; hash_index = fdb_head_index(vxlan, addr, src_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); if (!err) *notified = true; return err; } /* Dump forwarding table */ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { struct ndo_fdb_dump_context *ctx = (void *)cb->ctx; struct vxlan_dev *vxlan = netdev_priv(dev); unsigned int h; int err = 0; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct vxlan_fdb *f; rcu_read_lock(); hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { struct vxlan_rdst *rd; if (rcu_access_pointer(f->nh)) { if (*idx < ctx->fdb_idx) goto skip_nh; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, NULL); if (err < 0) { rcu_read_unlock(); goto out; } skip_nh: *idx += 1; continue; } list_for_each_entry_rcu(rd, &f->remotes, list) { if (*idx < ctx->fdb_idx) goto skip; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); if (err < 0) { rcu_read_unlock(); goto out; } skip: *idx += 1; } } rcu_read_unlock(); } out: return err; } static int vxlan_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; __be32 vni; int err; if (tb[NDA_VNI]) vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); else vni = vxlan->default_dst.remote_vni; rcu_read_lock(); f = __vxlan_find_mac(vxlan, addr, vni); if (!f) { NL_SET_ERR_MSG(extack, "Fdb entry not found"); err = -ENOENT; goto errout; } err = vxlan_fdb_info(skb, vxlan, f, portid, seq, RTM_NEWNEIGH, 0, first_remote_rcu(f)); errout: rcu_read_unlock(); return err; } /* Watch incoming packets to learn mapping between Ethernet address * and Tunnel endpoint. */ static enum skb_drop_reason vxlan_snoop(struct net_device *dev, union vxlan_addr *src_ip, const u8 *src_mac, u32 src_ifindex, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; u32 ifindex = 0; /* Ignore packets from invalid src-address */ if (!is_valid_ether_addr(src_mac)) return SKB_DROP_REASON_MAC_INVALID_SOURCE; #if IS_ENABLED(CONFIG_IPV6) if (src_ip->sa.sa_family == AF_INET6 && (ipv6_addr_type(&src_ip->sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)) ifindex = src_ifindex; #endif f = __vxlan_find_mac(vxlan, src_mac, vni); if (likely(f)) { struct vxlan_rdst *rdst = first_remote_rcu(f); unsigned long now = jiffies; if (READ_ONCE(f->updated) != now) WRITE_ONCE(f->updated, now); if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) && rdst->remote_ifindex == ifindex)) return SKB_NOT_DROPPED_YET; /* Don't migrate static entries, drop packets */ if (f->state & (NUD_PERMANENT | NUD_NOARP)) return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; /* Don't override an fdb with nexthop with a learnt entry */ if (rcu_access_pointer(f->nh)) return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; if (net_ratelimit()) netdev_info(dev, "%pM migrated from %pIS to %pIS\n", src_mac, &rdst->remote_ip.sa, &src_ip->sa); rdst->remote_ip = *src_ip; vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL); } else { u32 hash_index = fdb_head_index(vxlan, src_mac, vni); /* learned new entry */ spin_lock(&vxlan->hash_lock[hash_index]); /* close off race between vxlan_flush and incoming packets */ if (netif_running(dev)) vxlan_fdb_update(vxlan, src_mac, src_ip, NUD_REACHABLE, NLM_F_EXCL|NLM_F_CREATE, vxlan->cfg.dst_port, vni, vxlan->default_dst.remote_vni, ifindex, NTF_SELF, 0, true, NULL); spin_unlock(&vxlan->hash_lock[hash_index]); } return SKB_NOT_DROPPED_YET; } static bool __vxlan_sock_release_prep(struct vxlan_sock *vs) { struct vxlan_net *vn; if (!vs) return false; if (!refcount_dec_and_test(&vs->refcnt)) return false; vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id); spin_lock(&vn->sock_lock); hlist_del_rcu(&vs->hlist); udp_tunnel_notify_del_rx_port(vs->sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); spin_unlock(&vn->sock_lock); return true; } static void vxlan_sock_release(struct vxlan_dev *vxlan) { struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock); #if IS_ENABLED(CONFIG_IPV6) struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock); RCU_INIT_POINTER(vxlan->vn6_sock, NULL); #endif RCU_INIT_POINTER(vxlan->vn4_sock, NULL); synchronize_net(); if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vs_del_vnigrp(vxlan); else vxlan_vs_del_dev(vxlan); if (__vxlan_sock_release_prep(sock4)) { udp_tunnel_sock_release(sock4->sock); kfree(sock4); } #if IS_ENABLED(CONFIG_IPV6) if (__vxlan_sock_release_prep(sock6)) { udp_tunnel_sock_release(sock6->sock); kfree(sock6); } #endif } static enum skb_drop_reason vxlan_remcsum(struct sk_buff *skb, u32 vxflags) { const struct vxlanhdr *vh = vxlan_hdr(skb); enum skb_drop_reason reason; size_t start, offset; if (!(vh->vx_flags & VXLAN_HF_RCO) || skb->remcsum_offload) return SKB_NOT_DROPPED_YET; start = vxlan_rco_start(vh->vx_vni); offset = start + vxlan_rco_offset(vh->vx_vni); reason = pskb_may_pull_reason(skb, offset + sizeof(u16)); if (reason) return reason; skb_remcsum_process(skb, (void *)(vxlan_hdr(skb) + 1), start, offset, !!(vxflags & VXLAN_F_REMCSUM_NOPARTIAL)); return SKB_NOT_DROPPED_YET; } static void vxlan_parse_gbp_hdr(struct sk_buff *skb, u32 vxflags, struct vxlan_metadata *md) { const struct vxlanhdr *vh = vxlan_hdr(skb); const struct vxlanhdr_gbp *gbp; struct metadata_dst *tun_dst; gbp = (const struct vxlanhdr_gbp *)vh; if (!(vh->vx_flags & VXLAN_HF_GBP)) return; md->gbp = ntohs(gbp->policy_id); tun_dst = (struct metadata_dst *)skb_dst(skb); if (tun_dst) { __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_dst->u.tun_info.key.tun_flags); tun_dst->u.tun_info.options_len = sizeof(*md); } if (gbp->dont_learn) md->gbp |= VXLAN_GBP_DONT_LEARN; if (gbp->policy_applied) md->gbp |= VXLAN_GBP_POLICY_APPLIED; /* In flow-based mode, GBP is carried in dst_metadata */ if (!(vxflags & VXLAN_F_COLLECT_METADATA)) skb->mark = md->gbp; } static enum skb_drop_reason vxlan_set_mac(struct vxlan_dev *vxlan, struct vxlan_sock *vs, struct sk_buff *skb, __be32 vni) { union vxlan_addr saddr; u32 ifindex = skb->dev->ifindex; skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, vxlan->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); /* Ignore packet loops (and multicast echo) */ if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) return SKB_DROP_REASON_LOCAL_MAC; /* Get address from the outer IP header */ if (vxlan_get_sk_family(vs) == AF_INET) { saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; saddr.sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { saddr.sin6.sin6_addr = ipv6_hdr(skb)->saddr; saddr.sa.sa_family = AF_INET6; #endif } if (!(vxlan->cfg.flags & VXLAN_F_LEARN)) return SKB_NOT_DROPPED_YET; return vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source, ifindex, vni); } static bool vxlan_ecn_decapsulate(struct vxlan_sock *vs, void *oiph, struct sk_buff *skb) { int err = 0; if (vxlan_get_sk_family(vs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); #endif if (unlikely(err) && log_ecn_error) { if (vxlan_get_sk_family(vs) == AF_INET) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); } return err <= 1; } static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) { struct vxlan_vni_node *vninode = NULL; const struct vxlanhdr *vh; struct vxlan_dev *vxlan; struct vxlan_sock *vs; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 protocol = htons(ETH_P_TEB); enum skb_drop_reason reason; bool raw_proto = false; void *oiph; __be32 vni = 0; int nh; /* Need UDP and VXLAN header to be present */ reason = pskb_may_pull_reason(skb, VXLAN_HLEN); if (reason) goto drop; vh = vxlan_hdr(skb); /* VNI flag always required to be set */ if (!(vh->vx_flags & VXLAN_HF_VNI)) { netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n", ntohl(vh->vx_flags), ntohl(vh->vx_vni)); reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; /* Return non vxlan pkt */ goto drop; } vs = rcu_dereference_sk_user_data(sk); if (!vs) goto drop; vni = vxlan_vni(vh->vx_vni); vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, &vninode); if (!vxlan) { reason = SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND; goto drop; } if (vh->vx_flags & vxlan->cfg.reserved_bits.vx_flags || vh->vx_vni & vxlan->cfg.reserved_bits.vx_vni) { /* If the header uses bits besides those enabled by the * netdevice configuration, treat this as a malformed packet. * This behavior diverges from VXLAN RFC (RFC7348) which * stipulates that bits in reserved in reserved fields are to be * ignored. The approach here maintains compatibility with * previous stack code, and also is more robust and provides a * little more security in adding extensions to VXLAN. */ reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; DEV_STATS_INC(vxlan->dev, rx_frame_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } if (vxlan->cfg.flags & VXLAN_F_GPE) { if (!vxlan_parse_gpe_proto(vh, &protocol)) goto drop; raw_proto = true; } if (__iptunnel_pull_header(skb, VXLAN_HLEN, protocol, raw_proto, !net_eq(vxlan->net, dev_net(vxlan->dev)))) { reason = SKB_DROP_REASON_NOMEM; goto drop; } if (vxlan->cfg.flags & VXLAN_F_REMCSUM_RX) { reason = vxlan_remcsum(skb, vxlan->cfg.flags); if (unlikely(reason)) goto drop; } if (vxlan_collect_metadata(vs)) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst; __set_bit(IP_TUNNEL_KEY_BIT, flags); tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), flags, key32_to_tunnel_id(vni), sizeof(*md)); if (!tun_dst) { reason = SKB_DROP_REASON_NOMEM; goto drop; } md = ip_tunnel_info_opts(&tun_dst->u.tun_info); skb_dst_set(skb, (struct dst_entry *)tun_dst); } else { memset(md, 0, sizeof(*md)); } if (vxlan->cfg.flags & VXLAN_F_GBP) vxlan_parse_gbp_hdr(skb, vxlan->cfg.flags, md); /* Note that GBP and GPE can never be active together. This is * ensured in vxlan_dev_configure. */ if (!raw_proto) { reason = vxlan_set_mac(vxlan, vs, skb, vni); if (reason) goto drop; } else { skb_reset_mac_header(skb); skb->dev = vxlan->dev; skb->pkt_type = PACKET_HOST; } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); reason = pskb_inet_may_pull_reason(skb); if (reason) { DEV_STATS_INC(vxlan->dev, rx_length_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (!vxlan_ecn_decapsulate(vs, oiph, skb)) { reason = SKB_DROP_REASON_IP_TUNNEL_ECN; DEV_STATS_INC(vxlan->dev, rx_frame_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } rcu_read_lock(); if (unlikely(!(vxlan->dev->flags & IFF_UP))) { rcu_read_unlock(); dev_dstats_rx_dropped(vxlan->dev); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_DROPS, 0); reason = SKB_DROP_REASON_DEV_READY; goto drop; } dev_dstats_rx_add(vxlan->dev, skb->len); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX, skb->len); gro_cells_receive(&vxlan->gro_cells, skb); rcu_read_unlock(); return 0; drop: reason = reason ?: SKB_DROP_REASON_NOT_SPECIFIED; /* Consume bad packet */ kfree_skb_reason(skb, reason); return 0; } static int vxlan_err_lookup(struct sock *sk, struct sk_buff *skb) { struct vxlan_dev *vxlan; struct vxlan_sock *vs; struct vxlanhdr *hdr; __be32 vni; if (!pskb_may_pull(skb, skb_transport_offset(skb) + VXLAN_HLEN)) return -EINVAL; hdr = vxlan_hdr(skb); if (!(hdr->vx_flags & VXLAN_HF_VNI)) return -EINVAL; vs = rcu_dereference_sk_user_data(sk); if (!vs) return -ENOENT; vni = vxlan_vni(hdr->vx_vni); vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, NULL); if (!vxlan) return -ENOENT; return 0; } static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct arphdr *parp; u8 *arpptr, *sha; __be32 sip, tip; struct neighbour *n; if (dev->flags & IFF_NOARP) goto out; if (!pskb_may_pull(skb, arp_hdr_len(dev))) { dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); goto out; } parp = arp_hdr(skb); if ((parp->ar_hrd != htons(ARPHRD_ETHER) && parp->ar_hrd != htons(ARPHRD_IEEE802)) || parp->ar_pro != htons(ETH_P_IP) || parp->ar_op != htons(ARPOP_REQUEST) || parp->ar_hln != dev->addr_len || parp->ar_pln != 4) goto out; arpptr = (u8 *)parp + sizeof(struct arphdr); sha = arpptr; arpptr += dev->addr_len; /* sha */ memcpy(&sip, arpptr, sizeof(sip)); arpptr += sizeof(sip); arpptr += dev->addr_len; /* tha */ memcpy(&tip, arpptr, sizeof(tip)); if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) goto out; n = neigh_lookup(&arp_tbl, &tip, dev); if (n) { struct vxlan_fdb *f; struct sk_buff *reply; if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } f = vxlan_find_mac(vxlan, n->ha, vni); if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { /* bridge-local neighbor */ neigh_release(n); goto out; } reply = arp_create(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, n->ha, sha); neigh_release(n); if (reply == NULL) goto out; skb_reset_mac_header(reply); __skb_pull(reply, skb_network_offset(reply)); reply->ip_summed = CHECKSUM_UNNECESSARY; reply->pkt_type = PACKET_HOST; if (netif_rx(reply) == NET_RX_DROP) { dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = tip, .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); } out: consume_skb(skb); return NETDEV_TX_OK; } #if IS_ENABLED(CONFIG_IPV6) static struct sk_buff *vxlan_na_create(struct sk_buff *request, struct neighbour *n, bool isrouter) { struct net_device *dev = request->dev; struct sk_buff *reply; struct nd_msg *ns, *na; struct ipv6hdr *pip6; u8 *daddr; int na_olen = 8; /* opt hdr + ETH_ALEN for target */ int ns_olen; int i, len; if (dev == NULL || !pskb_may_pull(request, request->len)) return NULL; len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + sizeof(*na) + na_olen + dev->needed_tailroom; reply = alloc_skb(len, GFP_ATOMIC); if (reply == NULL) return NULL; reply->protocol = htons(ETH_P_IPV6); reply->dev = dev; skb_reserve(reply, LL_RESERVED_SPACE(request->dev)); skb_push(reply, sizeof(struct ethhdr)); skb_reset_mac_header(reply); ns = (struct nd_msg *)(ipv6_hdr(request) + 1); daddr = eth_hdr(request)->h_source; ns_olen = request->len - skb_network_offset(request) - sizeof(struct ipv6hdr) - sizeof(*ns); for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) { if (!ns->opt[i + 1]) { kfree_skb(reply); return NULL; } if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { daddr = ns->opt + i + sizeof(struct nd_opt_hdr); break; } } /* Ethernet header */ ether_addr_copy(eth_hdr(reply)->h_dest, daddr); ether_addr_copy(eth_hdr(reply)->h_source, n->ha); eth_hdr(reply)->h_proto = htons(ETH_P_IPV6); reply->protocol = htons(ETH_P_IPV6); skb_pull(reply, sizeof(struct ethhdr)); skb_reset_network_header(reply); skb_put(reply, sizeof(struct ipv6hdr)); /* IPv6 header */ pip6 = ipv6_hdr(reply); memset(pip6, 0, sizeof(struct ipv6hdr)); pip6->version = 6; pip6->priority = ipv6_hdr(request)->priority; pip6->nexthdr = IPPROTO_ICMPV6; pip6->hop_limit = 255; pip6->daddr = ipv6_hdr(request)->saddr; pip6->saddr = *(struct in6_addr *)n->primary_key; skb_pull(reply, sizeof(struct ipv6hdr)); skb_reset_transport_header(reply); /* Neighbor Advertisement */ na = skb_put_zero(reply, sizeof(*na) + na_olen); na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; na->icmph.icmp6_router = isrouter; na->icmph.icmp6_override = 1; na->icmph.icmp6_solicited = 1; na->target = ns->target; ether_addr_copy(&na->opt[2], n->ha); na->opt[0] = ND_OPT_TARGET_LL_ADDR; na->opt[1] = na_olen >> 3; na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6, csum_partial(na, sizeof(*na)+na_olen, 0)); pip6->payload_len = htons(sizeof(*na)+na_olen); skb_push(reply, sizeof(struct ipv6hdr)); reply->ip_summed = CHECKSUM_UNNECESSARY; return reply; } static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); const struct in6_addr *daddr; const struct ipv6hdr *iphdr; struct inet6_dev *in6_dev; struct neighbour *n; struct nd_msg *msg; rcu_read_lock(); in6_dev = __in6_dev_get(dev); if (!in6_dev) goto out; iphdr = ipv6_hdr(skb); daddr = &iphdr->daddr; msg = (struct nd_msg *)(iphdr + 1); if (ipv6_addr_loopback(daddr) || ipv6_addr_is_multicast(&msg->target)) goto out; n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev); if (n) { struct vxlan_fdb *f; struct sk_buff *reply; if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } f = vxlan_find_mac(vxlan, n->ha, vni); if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { /* bridge-local neighbor */ neigh_release(n); goto out; } reply = vxlan_na_create(skb, n, !!(f ? f->flags & NTF_ROUTER : 0)); neigh_release(n); if (reply == NULL) goto out; if (netif_rx(reply) == NET_RX_DROP) { dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin6.sin6_addr = msg->target, .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); } out: rcu_read_unlock(); consume_skb(skb); return NETDEV_TX_OK; } #endif static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); struct neighbour *n; if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) return false; n = NULL; switch (ntohs(eth_hdr(skb)->h_proto)) { case ETH_P_IP: { struct iphdr *pip; if (!pskb_may_pull(skb, sizeof(struct iphdr))) return false; pip = ip_hdr(skb); n = neigh_lookup(&arp_tbl, &pip->daddr, dev); if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = pip->daddr, .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); return false; } break; } #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: { struct ipv6hdr *pip6; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return false; pip6 = ipv6_hdr(skb); n = neigh_lookup(ipv6_stub->nd_tbl, &pip6->daddr, dev); if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin6.sin6_addr = pip6->daddr, .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); return false; } break; } #endif default: return false; } if (n) { bool diff; diff = !ether_addr_equal(eth_hdr(skb)->h_dest, n->ha); if (diff) { memcpy(eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, dev->addr_len); memcpy(eth_hdr(skb)->h_dest, n->ha, dev->addr_len); } neigh_release(n); return diff; } return false; } static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, __be16 protocol) { struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)vxh; gpe->np_applied = 1; gpe->next_protocol = tun_p_from_eth_p(protocol); if (!gpe->next_protocol) return -EPFNOSUPPORT; return 0; } static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, int iphdr_len, __be32 vni, struct vxlan_metadata *md, u32 vxflags, bool udp_sum) { struct vxlanhdr *vxh; int min_headroom; int err; int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; __be16 inner_protocol = htons(ETH_P_TEB); if ((vxflags & VXLAN_F_REMCSUM_TX) && skb->ip_summed == CHECKSUM_PARTIAL) { int csum_start = skb_checksum_start_offset(skb); if (csum_start <= VXLAN_MAX_REMCSUM_START && !(csum_start & VXLAN_RCO_SHIFT_MASK) && (skb->csum_offset == offsetof(struct udphdr, check) || skb->csum_offset == offsetof(struct tcphdr, check))) type |= SKB_GSO_TUNNEL_REMCSUM; } min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + VXLAN_HLEN + iphdr_len; /* Need space for new headers (invalidates iph ptr) */ err = skb_cow_head(skb, min_headroom); if (unlikely(err)) return err; err = iptunnel_handle_offloads(skb, type); if (err) return err; vxh = __skb_push(skb, sizeof(*vxh)); vxh->vx_flags = VXLAN_HF_VNI; vxh->vx_vni = vxlan_vni_field(vni); if (type & SKB_GSO_TUNNEL_REMCSUM) { unsigned int start; start = skb_checksum_start_offset(skb) - sizeof(struct vxlanhdr); vxh->vx_vni |= vxlan_compute_rco(start, skb->csum_offset); vxh->vx_flags |= VXLAN_HF_RCO; if (!skb_is_gso(skb)) { skb->ip_summed = CHECKSUM_NONE; skb->encapsulation = 0; } } if (vxflags & VXLAN_F_GBP) vxlan_build_gbp_hdr(vxh, md); if (vxflags & VXLAN_F_GPE) { err = vxlan_build_gpe_hdr(vxh, skb->protocol); if (err < 0) return err; inner_protocol = skb->protocol; } skb_set_inner_protocol(skb, inner_protocol); return 0; } /* Bypass encapsulation if the destination is local */ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct vxlan_dev *dst_vxlan, __be32 vni, bool snoop) { union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; unsigned int len = skb->len; struct net_device *dev; skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; skb->dev = dst_vxlan->dev; __skb_pull(skb, skb_network_offset(skb)); if (remote_ip->sa.sa_family == AF_INET) { loopback.sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK); loopback.sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { loopback.sin6.sin6_addr = in6addr_loopback; loopback.sa.sa_family = AF_INET6; #endif } rcu_read_lock(); dev = skb->dev; if (unlikely(!(dev->flags & IFF_UP))) { kfree_skb_reason(skb, SKB_DROP_REASON_DEV_READY); goto drop; } if ((dst_vxlan->cfg.flags & VXLAN_F_LEARN) && snoop) vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); dev_dstats_tx_add(src_vxlan->dev, len); vxlan_vnifilter_count(src_vxlan, vni, NULL, VXLAN_VNI_STATS_TX, len); if (__netif_rx(skb) == NET_RX_SUCCESS) { dev_dstats_rx_add(dst_vxlan->dev, len); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX, len); } else { drop: dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } rcu_read_unlock(); } static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *vxlan, int addr_family, __be16 dst_port, int dst_ifindex, __be32 vni, struct dst_entry *dst, u32 rt_flags) { #if IS_ENABLED(CONFIG_IPV6) /* IPv6 rt-flags are checked against RTF_LOCAL, but the value of * RTF_LOCAL is equal to RTCF_LOCAL. So to keep code simple * we can use RTCF_LOCAL which works for ipv4 and ipv6 route entry. */ BUILD_BUG_ON(RTCF_LOCAL != RTF_LOCAL); #endif /* Bypass encapsulation if the destination is local */ if (rt_flags & RTCF_LOCAL && !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) && vxlan->cfg.flags & VXLAN_F_LOCALBYPASS) { struct vxlan_dev *dst_vxlan; dst_release(dst); dst_vxlan = vxlan_find_vni(vxlan->net, dst_ifindex, vni, addr_family, dst_port, vxlan->cfg.flags); if (!dst_vxlan) { DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND); return -ENOENT; } vxlan_encap_bypass(skb, vxlan, dst_vxlan, vni, true); return 1; } return 0; } void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, __be32 default_vni, struct vxlan_rdst *rdst, bool did_rsc) { struct dst_cache *dst_cache; struct ip_tunnel_info *info; struct ip_tunnel_key *pkey; struct ip_tunnel_key key; struct vxlan_dev *vxlan = netdev_priv(dev); const struct iphdr *old_iph; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; unsigned int pkt_len = skb->len; __be16 src_port = 0, dst_port; struct dst_entry *ndst = NULL; int addr_family; __u8 tos, ttl; int ifindex; int err; u32 flags = vxlan->cfg.flags; bool use_cache; bool udp_sum = false; bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev)); enum skb_drop_reason reason; bool no_eth_encap; __be32 vni = 0; no_eth_encap = flags & VXLAN_F_GPE && skb->protocol != htons(ETH_P_TEB); reason = skb_vlan_inet_prepare(skb, no_eth_encap); if (reason) goto drop; reason = SKB_DROP_REASON_NOT_SPECIFIED; old_iph = ip_hdr(skb); info = skb_tunnel_info(skb); use_cache = ip_tunnel_dst_cache_usable(skb, info); if (rdst) { memset(&key, 0, sizeof(key)); pkey = &key; if (vxlan_addr_any(&rdst->remote_ip)) { if (did_rsc) { /* short-circuited back to local bridge */ vxlan_encap_bypass(skb, vxlan, vxlan, default_vni, true); return; } goto drop; } addr_family = vxlan->cfg.saddr.sa.sa_family; dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; vni = (rdst->remote_vni) ? : default_vni; ifindex = rdst->remote_ifindex; if (addr_family == AF_INET) { key.u.ipv4.src = vxlan->cfg.saddr.sin.sin_addr.s_addr; key.u.ipv4.dst = rdst->remote_ip.sin.sin_addr.s_addr; } else { key.u.ipv6.src = vxlan->cfg.saddr.sin6.sin6_addr; key.u.ipv6.dst = rdst->remote_ip.sin6.sin6_addr; } dst_cache = &rdst->dst_cache; md->gbp = skb->mark; if (flags & VXLAN_F_TTL_INHERIT) { ttl = ip_tunnel_get_ttl(old_iph, skb); } else { ttl = vxlan->cfg.ttl; if (!ttl && vxlan_addr_multicast(&rdst->remote_ip)) ttl = 1; } tos = vxlan->cfg.tos; if (tos == 1) tos = ip_tunnel_get_dsfield(old_iph, skb); if (tos && !info) use_cache = false; if (addr_family == AF_INET) udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX); else udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX); #if IS_ENABLED(CONFIG_IPV6) switch (vxlan->cfg.label_policy) { case VXLAN_LABEL_FIXED: key.label = vxlan->cfg.label; break; case VXLAN_LABEL_INHERIT: key.label = ip_tunnel_get_flowlabel(old_iph, skb); break; default: DEBUG_NET_WARN_ON_ONCE(1); goto drop; } #endif } else { if (!info) { WARN_ONCE(1, "%s: Missing encapsulation instructions\n", dev->name); goto drop; } pkey = &info->key; addr_family = ip_tunnel_info_af(info); dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; dst_cache = &info->dst_cache; if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { if (info->options_len < sizeof(*md)) goto drop; md = ip_tunnel_info_opts(info); } ttl = info->key.ttl; tos = info->key.tos; udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); rcu_read_lock(); if (addr_family == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; __be16 df = 0; __be32 saddr; if (!ifindex) ifindex = sock4->sock->sk->sk_bound_dev_if; rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, ifindex, &saddr, pkey, src_port, dst_port, tos, use_cache ? dst_cache : NULL); if (IS_ERR(rt)) { err = PTR_ERR(rt); reason = SKB_DROP_REASON_IP_OUTNOROUTES; goto tx_error; } if (!info) { /* Bypass encapsulation if the destination is local */ err = encap_bypass_if_local(skb, dev, vxlan, AF_INET, dst_port, ifindex, vni, &rt->dst, rt->rt_flags); if (err) goto out_unlock; if (vxlan->cfg.df == VXLAN_DF_SET) { df = htons(IP_DF); } else if (vxlan->cfg.df == VXLAN_DF_INHERIT) { struct ethhdr *eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_IPV6 || (ntohs(eth->h_proto) == ETH_P_IP && old_iph->frag_off & htons(IP_DF))) df = htons(IP_DF); } } else if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags)) { df = htons(IP_DF); } ndst = &rt->dst; err = skb_tunnel_check_pmtu(skb, ndst, vxlan_headroom(flags & VXLAN_F_GPE), netif_is_any_bridge_port(dev)); if (err < 0) { goto tx_error; } else if (err) { if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) goto tx_error; unclone->key.u.ipv4.src = pkey->u.ipv4.dst; unclone->key.u.ipv4.dst = saddr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr), vni, md, flags, udp_sum); if (err < 0) { reason = SKB_DROP_REASON_NOMEM; goto tx_error; } udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, saddr, pkey->u.ipv4.dst, tos, ttl, df, src_port, dst_port, xnet, !udp_sum); #if IS_ENABLED(CONFIG_IPV6) } else { struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct in6_addr saddr; if (!ifindex) ifindex = sock6->sock->sk->sk_bound_dev_if; ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, ifindex, &saddr, pkey, src_port, dst_port, tos, use_cache ? dst_cache : NULL); if (IS_ERR(ndst)) { err = PTR_ERR(ndst); ndst = NULL; reason = SKB_DROP_REASON_IP_OUTNOROUTES; goto tx_error; } if (!info) { u32 rt6i_flags = dst_rt6_info(ndst)->rt6i_flags; err = encap_bypass_if_local(skb, dev, vxlan, AF_INET6, dst_port, ifindex, vni, ndst, rt6i_flags); if (err) goto out_unlock; } err = skb_tunnel_check_pmtu(skb, ndst, vxlan_headroom((flags & VXLAN_F_GPE) | VXLAN_F_IPV6), netif_is_any_bridge_port(dev)); if (err < 0) { goto tx_error; } else if (err) { if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) goto tx_error; unclone->key.u.ipv6.src = pkey->u.ipv6.dst; unclone->key.u.ipv6.dst = saddr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet); err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr), vni, md, flags, udp_sum); if (err < 0) { reason = SKB_DROP_REASON_NOMEM; goto tx_error; } udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev, &saddr, &pkey->u.ipv6.dst, tos, ttl, pkey->label, src_port, dst_port, !udp_sum); #endif } vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX, pkt_len); out_unlock: rcu_read_unlock(); return; drop: dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb_reason(skb, reason); return; tx_error: rcu_read_unlock(); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); dst_release(ndst); DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb_reason(skb, reason); } static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev, struct vxlan_fdb *f, __be32 vni, bool did_rsc) { struct vxlan_rdst nh_rdst; struct nexthop *nh; bool do_xmit; u32 hash; memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); hash = skb_get_hash(skb); rcu_read_lock(); nh = rcu_dereference(f->nh); if (!nh) { rcu_read_unlock(); goto drop; } do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); rcu_read_unlock(); if (likely(do_xmit)) vxlan_xmit_one(skb, dev, vni, &nh_rdst, did_rsc); else goto drop; return; drop: dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); } static netdev_tx_t vxlan_xmit_nhid(struct sk_buff *skb, struct net_device *dev, u32 nhid, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst nh_rdst; struct nexthop *nh; bool do_xmit; u32 hash; memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); hash = skb_get_hash(skb); rcu_read_lock(); nh = nexthop_find_by_id(dev_net(dev), nhid); if (unlikely(!nh || !nexthop_is_fdb(nh) || !nexthop_is_multipath(nh))) { rcu_read_unlock(); goto drop; } do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); rcu_read_unlock(); if (vxlan->cfg.saddr.sa.sa_family != nh_rdst.remote_ip.sa.sa_family) goto drop; if (likely(do_xmit)) vxlan_xmit_one(skb, dev, vni, &nh_rdst, false); else goto drop; return NETDEV_TX_OK; drop: dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); return NETDEV_TX_OK; } /* Transmit local packets over Vxlan * * Outer IP header inherits ECN and DF from inner header. * Outer UDP destination is the VXLAN assigned port. * source port is based on hash of flow */ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst, *fdst = NULL; const struct ip_tunnel_info *info; struct vxlan_fdb *f; struct ethhdr *eth; __be32 vni = 0; u32 nhid = 0; bool did_rsc; info = skb_tunnel_info(skb); skb_reset_mac_header(skb); if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { if (info && info->mode & IP_TUNNEL_INFO_BRIDGE && info->mode & IP_TUNNEL_INFO_TX) { vni = tunnel_id_to_key32(info->key.tun_id); nhid = info->key.nhid; } else { if (info && info->mode & IP_TUNNEL_INFO_TX) vxlan_xmit_one(skb, dev, vni, NULL, false); else kfree_skb_reason(skb, SKB_DROP_REASON_TUNNEL_TXINFO); return NETDEV_TX_OK; } } if (vxlan->cfg.flags & VXLAN_F_PROXY) { eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_ARP) return arp_reduce(dev, skb, vni); #if IS_ENABLED(CONFIG_IPV6) else if (ntohs(eth->h_proto) == ETH_P_IPV6 && pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)) && ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1); if (m->icmph.icmp6_code == 0 && m->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) return neigh_reduce(dev, skb, vni); } #endif } if (nhid) return vxlan_xmit_nhid(skb, dev, nhid, vni); if (vxlan->cfg.flags & VXLAN_F_MDB) { struct vxlan_mdb_entry *mdb_entry; rcu_read_lock(); mdb_entry = vxlan_mdb_entry_skb_get(vxlan, skb, vni); if (mdb_entry) { netdev_tx_t ret; ret = vxlan_mdb_xmit(vxlan, mdb_entry, skb); rcu_read_unlock(); return ret; } rcu_read_unlock(); } eth = eth_hdr(skb); f = vxlan_find_mac(vxlan, eth->h_dest, vni); did_rsc = false; if (f && (f->flags & NTF_ROUTER) && (vxlan->cfg.flags & VXLAN_F_RSC) && (ntohs(eth->h_proto) == ETH_P_IP || ntohs(eth->h_proto) == ETH_P_IPV6)) { did_rsc = route_shortcircuit(dev, skb); if (did_rsc) f = vxlan_find_mac(vxlan, eth->h_dest, vni); } if (f == NULL) { f = vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f == NULL) { if ((vxlan->cfg.flags & VXLAN_F_L2MISS) && !is_multicast_ether_addr(eth->h_dest)) vxlan_fdb_miss(vxlan, eth->h_dest); dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET); return NETDEV_TX_OK; } } if (rcu_access_pointer(f->nh)) { vxlan_xmit_nh(skb, dev, f, (vni ? : vxlan->default_dst.remote_vni), did_rsc); } else { list_for_each_entry_rcu(rdst, &f->remotes, list) { struct sk_buff *skb1; if (!fdst) { fdst = rdst; continue; } skb1 = skb_clone(skb, GFP_ATOMIC); if (skb1) vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc); } if (fdst) vxlan_xmit_one(skb, dev, vni, fdst, did_rsc); else kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET); } return NETDEV_TX_OK; } /* Walk the forwarding table and purge stale entries */ static void vxlan_cleanup(struct timer_list *t) { struct vxlan_dev *vxlan = from_timer(vxlan, t, age_timer); unsigned long next_timer = jiffies + FDB_AGE_INTERVAL; unsigned int h; if (!netif_running(vxlan->dev)) return; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n; spin_lock(&vxlan->hash_lock[h]); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); unsigned long timeout; if (f->state & (NUD_PERMANENT | NUD_NOARP)) continue; if (f->flags & NTF_EXT_LEARNED) continue; timeout = READ_ONCE(f->updated) + vxlan->cfg.age_interval * HZ; if (time_before_eq(timeout, jiffies)) { netdev_dbg(vxlan->dev, "garbage collect %pM\n", f->eth_addr); f->state = NUD_STALE; vxlan_fdb_destroy(vxlan, f, true, true); } else if (time_before(timeout, next_timer)) next_timer = timeout; } spin_unlock(&vxlan->hash_lock[h]); } mod_timer(&vxlan->age_timer, next_timer); } static void vxlan_vs_del_dev(struct vxlan_dev *vxlan) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); spin_lock(&vn->sock_lock); hlist_del_init_rcu(&vxlan->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&vxlan->hlist6.hlist); #endif spin_unlock(&vn->sock_lock); } static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan, struct vxlan_dev_node *node) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); __be32 vni = vxlan->default_dst.remote_vni; node->vxlan = vxlan; spin_lock(&vn->sock_lock); hlist_add_head_rcu(&node->hlist, vni_head(vs, vni)); spin_unlock(&vn->sock_lock); } /* Setup stats when device is created */ static int vxlan_init(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); int err; if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) { err = vxlan_vnigroup_init(vxlan); if (err) return err; } err = gro_cells_init(&vxlan->gro_cells, dev); if (err) goto err_vnigroup_uninit; err = vxlan_mdb_init(vxlan); if (err) goto err_gro_cells_destroy; netdev_lockdep_set_classes(dev); return 0; err_gro_cells_destroy: gro_cells_destroy(&vxlan->gro_cells); err_vnigroup_uninit: if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_uninit(vxlan); return err; } static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni) { struct vxlan_fdb *f; u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = __vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f) vxlan_fdb_destroy(vxlan, f, true, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); } static void vxlan_uninit(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); vxlan_mdb_fini(vxlan); if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_uninit(vxlan); gro_cells_destroy(&vxlan->gro_cells); vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni); } /* Start ageing timer and join group when device is brought up */ static int vxlan_open(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); int ret; ret = vxlan_sock_add(vxlan); if (ret < 0) return ret; ret = vxlan_multicast_join(vxlan); if (ret) { vxlan_sock_release(vxlan); return ret; } if (vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL); return ret; } struct vxlan_fdb_flush_desc { bool ignore_default_entry; unsigned long state; unsigned long state_mask; unsigned long flags; unsigned long flags_mask; __be32 src_vni; u32 nhid; __be32 vni; __be16 port; union vxlan_addr dst_ip; }; static bool vxlan_fdb_is_default_entry(const struct vxlan_fdb *f, const struct vxlan_dev *vxlan) { return is_zero_ether_addr(f->eth_addr) && f->vni == vxlan->cfg.vni; } static bool vxlan_fdb_nhid_matches(const struct vxlan_fdb *f, u32 nhid) { struct nexthop *nh = rtnl_dereference(f->nh); return nh && nh->id == nhid; } static bool vxlan_fdb_flush_matches(const struct vxlan_fdb *f, const struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc) { if (desc->state_mask && (f->state & desc->state_mask) != desc->state) return false; if (desc->flags_mask && (f->flags & desc->flags_mask) != desc->flags) return false; if (desc->ignore_default_entry && vxlan_fdb_is_default_entry(f, vxlan)) return false; if (desc->src_vni && f->vni != desc->src_vni) return false; if (desc->nhid && !vxlan_fdb_nhid_matches(f, desc->nhid)) return false; return true; } static bool vxlan_fdb_flush_should_match_remotes(const struct vxlan_fdb_flush_desc *desc) { return desc->vni || desc->port || desc->dst_ip.sa.sa_family; } static bool vxlan_fdb_flush_remote_matches(const struct vxlan_fdb_flush_desc *desc, const struct vxlan_rdst *rd) { if (desc->vni && rd->remote_vni != desc->vni) return false; if (desc->port && rd->remote_port != desc->port) return false; if (desc->dst_ip.sa.sa_family && !vxlan_addr_equal(&rd->remote_ip, &desc->dst_ip)) return false; return true; } static void vxlan_fdb_flush_match_remotes(struct vxlan_fdb *f, struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc, bool *p_destroy_fdb) { bool remotes_flushed = false; struct vxlan_rdst *rd, *tmp; list_for_each_entry_safe(rd, tmp, &f->remotes, list) { if (!vxlan_fdb_flush_remote_matches(desc, rd)) continue; vxlan_fdb_dst_destroy(vxlan, f, rd, true); remotes_flushed = true; } *p_destroy_fdb = remotes_flushed && list_empty(&f->remotes); } /* Purge the forwarding table */ static void vxlan_flush(struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc) { bool match_remotes = vxlan_fdb_flush_should_match_remotes(desc); unsigned int h; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n; spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); if (!vxlan_fdb_flush_matches(f, vxlan, desc)) continue; if (match_remotes) { bool destroy_fdb = false; vxlan_fdb_flush_match_remotes(f, vxlan, desc, &destroy_fdb); if (!destroy_fdb) continue; } vxlan_fdb_destroy(vxlan, f, true, true); } spin_unlock_bh(&vxlan->hash_lock[h]); } } static const struct nla_policy vxlan_del_bulk_policy[NDA_MAX + 1] = { [NDA_SRC_VNI] = { .type = NLA_U32 }, [NDA_NH_ID] = { .type = NLA_U32 }, [NDA_VNI] = { .type = NLA_U32 }, [NDA_PORT] = { .type = NLA_U16 }, [NDA_DST] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [NDA_NDM_STATE_MASK] = { .type = NLA_U16 }, [NDA_NDM_FLAGS_MASK] = { .type = NLA_U8 }, }; #define VXLAN_FDB_FLUSH_IGNORED_NDM_FLAGS (NTF_MASTER | NTF_SELF) #define VXLAN_FDB_FLUSH_ALLOWED_NDM_STATES (NUD_PERMANENT | NUD_NOARP) #define VXLAN_FDB_FLUSH_ALLOWED_NDM_FLAGS (NTF_EXT_LEARNED | NTF_OFFLOADED | \ NTF_ROUTER) static int vxlan_fdb_delete_bulk(struct nlmsghdr *nlh, struct net_device *dev, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = {}; struct ndmsg *ndm = nlmsg_data(nlh); struct nlattr *tb[NDA_MAX + 1]; u8 ndm_flags; int err; ndm_flags = ndm->ndm_flags & ~VXLAN_FDB_FLUSH_IGNORED_NDM_FLAGS; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, vxlan_del_bulk_policy, extack); if (err) return err; if (ndm_flags & ~VXLAN_FDB_FLUSH_ALLOWED_NDM_FLAGS) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm flag bits set"); return -EINVAL; } if (ndm->ndm_state & ~VXLAN_FDB_FLUSH_ALLOWED_NDM_STATES) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm state bits set"); return -EINVAL; } desc.state = ndm->ndm_state; desc.flags = ndm_flags; if (tb[NDA_NDM_STATE_MASK]) desc.state_mask = nla_get_u16(tb[NDA_NDM_STATE_MASK]); if (tb[NDA_NDM_FLAGS_MASK]) desc.flags_mask = nla_get_u8(tb[NDA_NDM_FLAGS_MASK]); if (tb[NDA_SRC_VNI]) desc.src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); if (tb[NDA_NH_ID]) desc.nhid = nla_get_u32(tb[NDA_NH_ID]); if (tb[NDA_VNI]) desc.vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); if (tb[NDA_PORT]) desc.port = nla_get_be16(tb[NDA_PORT]); if (tb[NDA_DST]) { union vxlan_addr ip; err = vxlan_nla_get_addr(&ip, tb[NDA_DST]); if (err) { NL_SET_ERR_MSG_ATTR(extack, tb[NDA_DST], "Unsupported address family"); return err; } desc.dst_ip = ip; } vxlan_flush(vxlan, &desc); return 0; } /* Cleanup timer and forwarding table on shutdown */ static int vxlan_stop(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = { /* Default entry is deleted at vxlan_uninit. */ .ignore_default_entry = true, .state = 0, .state_mask = NUD_PERMANENT | NUD_NOARP, }; vxlan_multicast_leave(vxlan); del_timer_sync(&vxlan->age_timer); vxlan_flush(vxlan, &desc); vxlan_sock_release(vxlan); return 0; } /* Stub, nothing needs to be done. */ static void vxlan_set_multicast_list(struct net_device *dev) { } static int vxlan_change_mtu(struct net_device *dev, int new_mtu) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); /* This check is different than dev->max_mtu, because it looks at * the lowerdev->mtu, rather than the static dev->max_mtu */ if (lowerdev) { int max_mtu = lowerdev->mtu - vxlan_headroom(vxlan->cfg.flags); if (new_mtu > max_mtu) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); struct ip_tunnel_info *info = skb_tunnel_info(skb); __be16 sport, dport; sport = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); dport = info->key.tp_dst ? : vxlan->cfg.dst_port; if (ip_tunnel_info_af(info) == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; if (!sock4) return -EIO; rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, 0, &info->key.u.ipv4.src, &info->key, sport, dport, info->key.tos, &info->dst_cache); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); } else { #if IS_ENABLED(CONFIG_IPV6) struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct dst_entry *ndst; if (!sock6) return -EIO; ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, 0, &info->key.u.ipv6.src, &info->key, sport, dport, info->key.tos, &info->dst_cache); if (IS_ERR(ndst)) return PTR_ERR(ndst); dst_release(ndst); #else /* !CONFIG_IPV6 */ return -EPFNOSUPPORT; #endif } info->key.tp_src = sport; info->key.tp_dst = dport; return 0; } static const struct net_device_ops vxlan_netdev_ether_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, .ndo_set_rx_mode = vxlan_set_multicast_list, .ndo_change_mtu = vxlan_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fdb_add = vxlan_fdb_add, .ndo_fdb_del = vxlan_fdb_delete, .ndo_fdb_del_bulk = vxlan_fdb_delete_bulk, .ndo_fdb_dump = vxlan_fdb_dump, .ndo_fdb_get = vxlan_fdb_get, .ndo_mdb_add = vxlan_mdb_add, .ndo_mdb_del = vxlan_mdb_del, .ndo_mdb_del_bulk = vxlan_mdb_del_bulk, .ndo_mdb_dump = vxlan_mdb_dump, .ndo_mdb_get = vxlan_mdb_get, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; static const struct net_device_ops vxlan_netdev_raw_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, .ndo_change_mtu = vxlan_change_mtu, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; /* Info for udev, that this is a virtual tunnel endpoint */ static const struct device_type vxlan_type = { .name = "vxlan", }; /* Calls the ndo_udp_tunnel_add of the caller in order to * supply the listening VXLAN udp ports. Callers are expected * to implement the ndo_udp_tunnel_add. */ static void vxlan_offload_rx_ports(struct net_device *dev, bool push) { struct vxlan_sock *vs; struct net *net = dev_net(dev); struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int i; spin_lock(&vn->sock_lock); for (i = 0; i < PORT_HASH_SIZE; ++i) { hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) { unsigned short type; if (vs->flags & VXLAN_F_GPE) type = UDP_TUNNEL_TYPE_VXLAN_GPE; else type = UDP_TUNNEL_TYPE_VXLAN; if (push) udp_tunnel_push_rx_port(dev, vs->sock, type); else udp_tunnel_drop_rx_port(dev, vs->sock, type); } } spin_unlock(&vn->sock_lock); } /* Initialize the device structure. */ static void vxlan_setup(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); unsigned int h; eth_hw_addr_random(dev); ether_setup(dev); dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &vxlan_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; dev->vlan_features = dev->features; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; netif_keep_dst(dev); dev->priv_flags |= IFF_NO_QUEUE; dev->change_proto_down = true; dev->lltx = true; /* MTU range: 68 - 65535 */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = ETH_MAX_MTU; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; INIT_LIST_HEAD(&vxlan->next); timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE); vxlan->dev = dev; for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_init(&vxlan->hash_lock[h]); INIT_HLIST_HEAD(&vxlan->fdb_head[h]); } } static void vxlan_ether_setup(struct net_device *dev) { dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->netdev_ops = &vxlan_netdev_ether_ops; } static void vxlan_raw_setup(struct net_device *dev) { dev->header_ops = NULL; dev->type = ARPHRD_NONE; dev->hard_header_len = 0; dev->addr_len = 0; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->netdev_ops = &vxlan_netdev_raw_ops; } static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_UNSPEC] = { .strict_start_type = IFLA_VXLAN_LOCALBYPASS }, [IFLA_VXLAN_ID] = { .type = NLA_U32 }, [IFLA_VXLAN_GROUP] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_LINK] = { .type = NLA_U32 }, [IFLA_VXLAN_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, [IFLA_VXLAN_LABEL] = { .type = NLA_U32 }, [IFLA_VXLAN_LEARNING] = { .type = NLA_U8 }, [IFLA_VXLAN_AGEING] = { .type = NLA_U32 }, [IFLA_VXLAN_LIMIT] = { .type = NLA_U32 }, [IFLA_VXLAN_PORT_RANGE] = { .len = sizeof(struct ifla_vxlan_port_range) }, [IFLA_VXLAN_PROXY] = { .type = NLA_U8 }, [IFLA_VXLAN_RSC] = { .type = NLA_U8 }, [IFLA_VXLAN_L2MISS] = { .type = NLA_U8 }, [IFLA_VXLAN_L3MISS] = { .type = NLA_U8 }, [IFLA_VXLAN_COLLECT_METADATA] = { .type = NLA_U8 }, [IFLA_VXLAN_PORT] = { .type = NLA_U16 }, [IFLA_VXLAN_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_VXLAN_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_GBP] = { .type = NLA_FLAG, }, [IFLA_VXLAN_GPE] = { .type = NLA_FLAG, }, [IFLA_VXLAN_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG }, [IFLA_VXLAN_TTL_INHERIT] = { .type = NLA_FLAG }, [IFLA_VXLAN_DF] = { .type = NLA_U8 }, [IFLA_VXLAN_VNIFILTER] = { .type = NLA_U8 }, [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_VXLAN_LABEL_POLICY] = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX), [IFLA_VXLAN_RESERVED_BITS] = NLA_POLICY_EXACT_LEN(sizeof(struct vxlanhdr)), }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided link layer address is not Ethernet"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided Ethernet address is not unicast"); return -EADDRNOTAVAIL; } } if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); if (mtu < ETH_MIN_MTU || mtu > ETH_MAX_MTU) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], "MTU must be between 68 and 65535"); return -EINVAL; } } if (!data) { NL_SET_ERR_MSG(extack, "Required attributes not provided to perform the operation"); return -EINVAL; } if (data[IFLA_VXLAN_ID]) { u32 id = nla_get_u32(data[IFLA_VXLAN_ID]); if (id >= VXLAN_N_VID) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_ID], "VXLAN ID must be lower than 16777216"); return -ERANGE; } } if (data[IFLA_VXLAN_PORT_RANGE]) { const struct ifla_vxlan_port_range *p = nla_data(data[IFLA_VXLAN_PORT_RANGE]); if (ntohs(p->high) < ntohs(p->low)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_PORT_RANGE], "Invalid source port range"); return -EINVAL; } } if (data[IFLA_VXLAN_DF]) { enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]); if (df < 0 || df > VXLAN_DF_MAX) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_DF], "Invalid DF attribute"); return -EINVAL; } } return 0; } static void vxlan_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->version, VXLAN_VERSION, sizeof(drvinfo->version)); strscpy(drvinfo->driver, "vxlan", sizeof(drvinfo->driver)); } static int vxlan_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); if (!lowerdev) { cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; cmd->base.speed = SPEED_UNKNOWN; return 0; } return __ethtool_get_link_ksettings(lowerdev, cmd); } static const struct ethtool_ops vxlan_ethtool_ops = { .get_drvinfo = vxlan_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = vxlan_get_link_ksettings, }; static struct socket *vxlan_create_sock(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { struct socket *sock; struct udp_port_cfg udp_conf; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6) { udp_conf.family = AF_INET6; udp_conf.use_udp6_rx_checksums = !(flags & VXLAN_F_UDP_ZERO_CSUM6_RX); udp_conf.ipv6_v6only = 1; } else { udp_conf.family = AF_INET; } udp_conf.local_udp_port = port; udp_conf.bind_ifindex = ifindex; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock; } /* Create new listen socket if needed */ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_sock *vs; struct socket *sock; unsigned int h; struct udp_tunnel_sock_cfg tunnel_cfg; vs = kzalloc(sizeof(*vs), GFP_KERNEL); if (!vs) return ERR_PTR(-ENOMEM); for (h = 0; h < VNI_HASH_SIZE; ++h) INIT_HLIST_HEAD(&vs->vni_list[h]); sock = vxlan_create_sock(net, ipv6, port, flags, ifindex); if (IS_ERR(sock)) { kfree(vs); return ERR_CAST(sock); } vs->sock = sock; refcount_set(&vs->refcnt, 1); vs->flags = (flags & VXLAN_F_RCV_FLAGS); spin_lock(&vn->sock_lock); hlist_add_head_rcu(&vs->hlist, vs_head(net, port)); udp_tunnel_notify_add_rx_port(sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); spin_unlock(&vn->sock_lock); /* Mark socket as an encapsulation socket. */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = vs; tunnel_cfg.encap_type = 1; tunnel_cfg.encap_rcv = vxlan_rcv; tunnel_cfg.encap_err_lookup = vxlan_err_lookup; tunnel_cfg.encap_destroy = NULL; if (vs->flags & VXLAN_F_GPE) { tunnel_cfg.gro_receive = vxlan_gpe_gro_receive; tunnel_cfg.gro_complete = vxlan_gpe_gro_complete; } else { tunnel_cfg.gro_receive = vxlan_gro_receive; tunnel_cfg.gro_complete = vxlan_gro_complete; } setup_udp_tunnel_sock(net, sock, &tunnel_cfg); return vs; } static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; struct vxlan_sock *vs = NULL; struct vxlan_dev_node *node; int l3mdev_index = 0; if (vxlan->cfg.remote_ifindex) l3mdev_index = l3mdev_master_upper_ifindex_by_index( vxlan->net, vxlan->cfg.remote_ifindex); if (!vxlan->cfg.no_share) { spin_lock(&vn->sock_lock); vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET, vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index); if (vs && !refcount_inc_not_zero(&vs->refcnt)) { spin_unlock(&vn->sock_lock); return -EBUSY; } spin_unlock(&vn->sock_lock); } if (!vs) vs = vxlan_socket_create(vxlan->net, ipv6, vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index); if (IS_ERR(vs)) return PTR_ERR(vs); #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { rcu_assign_pointer(vxlan->vn6_sock, vs); node = &vxlan->hlist6; } else #endif { rcu_assign_pointer(vxlan->vn4_sock, vs); node = &vxlan->hlist4; } if (metadata && (vxlan->cfg.flags & VXLAN_F_VNIFILTER)) vxlan_vs_add_vnigrp(vxlan, vs, ipv6); else vxlan_vs_add_dev(vs, vxlan, node); return 0; } static int vxlan_sock_add(struct vxlan_dev *vxlan) { bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; bool ipv6 = vxlan->cfg.flags & VXLAN_F_IPV6 || metadata; bool ipv4 = !ipv6 || metadata; int ret = 0; RCU_INIT_POINTER(vxlan->vn4_sock, NULL); #if IS_ENABLED(CONFIG_IPV6) RCU_INIT_POINTER(vxlan->vn6_sock, NULL); if (ipv6) { ret = __vxlan_sock_add(vxlan, true); if (ret < 0 && ret != -EAFNOSUPPORT) ipv4 = false; } #endif if (ipv4) ret = __vxlan_sock_add(vxlan, false); if (ret < 0) vxlan_sock_release(vxlan); return ret; } int vxlan_vni_in_use(struct net *src_net, struct vxlan_dev *vxlan, struct vxlan_config *conf, __be32 vni) { struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); struct vxlan_dev *tmp; list_for_each_entry(tmp, &vn->vxlan_list, next) { if (tmp == vxlan) continue; if (tmp->cfg.flags & VXLAN_F_VNIFILTER) { if (!vxlan_vnifilter_lookup(tmp, vni)) continue; } else if (tmp->cfg.vni != vni) { continue; } if (tmp->cfg.dst_port != conf->dst_port) continue; if ((tmp->cfg.flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6)) != (conf->flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6))) continue; if ((conf->flags & VXLAN_F_IPV6_LINKLOCAL) && tmp->cfg.remote_ifindex != conf->remote_ifindex) continue; return -EEXIST; } return 0; } static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf, struct net_device **lower, struct vxlan_dev *old, struct netlink_ext_ack *extack) { bool use_ipv6 = false; if (conf->flags & VXLAN_F_GPE) { /* For now, allow GPE only together with * COLLECT_METADATA. This can be relaxed later; in such * case, the other side of the PtP link will have to be * provided. */ if ((conf->flags & ~VXLAN_F_ALLOWED_GPE) || !(conf->flags & VXLAN_F_COLLECT_METADATA)) { NL_SET_ERR_MSG(extack, "VXLAN GPE does not support this combination of attributes"); return -EINVAL; } } if (!conf->remote_ip.sa.sa_family && !conf->saddr.sa.sa_family) { /* Unless IPv6 is explicitly requested, assume IPv4 */ conf->remote_ip.sa.sa_family = AF_INET; conf->saddr.sa.sa_family = AF_INET; } else if (!conf->remote_ip.sa.sa_family) { conf->remote_ip.sa.sa_family = conf->saddr.sa.sa_family; } else if (!conf->saddr.sa.sa_family) { conf->saddr.sa.sa_family = conf->remote_ip.sa.sa_family; } if (conf->saddr.sa.sa_family != conf->remote_ip.sa.sa_family) { NL_SET_ERR_MSG(extack, "Local and remote address must be from the same family"); return -EINVAL; } if (vxlan_addr_multicast(&conf->saddr)) { NL_SET_ERR_MSG(extack, "Local address cannot be multicast"); return -EINVAL; } if (conf->saddr.sa.sa_family == AF_INET6) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG(extack, "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } use_ipv6 = true; conf->flags |= VXLAN_F_IPV6; if (!(conf->flags & VXLAN_F_COLLECT_METADATA)) { int local_type = ipv6_addr_type(&conf->saddr.sin6.sin6_addr); int remote_type = ipv6_addr_type(&conf->remote_ip.sin6.sin6_addr); if (local_type & IPV6_ADDR_LINKLOCAL) { if (!(remote_type & IPV6_ADDR_LINKLOCAL) && (remote_type != IPV6_ADDR_ANY)) { NL_SET_ERR_MSG(extack, "Invalid combination of local and remote address scopes"); return -EINVAL; } conf->flags |= VXLAN_F_IPV6_LINKLOCAL; } else { if (remote_type == (IPV6_ADDR_UNICAST | IPV6_ADDR_LINKLOCAL)) { NL_SET_ERR_MSG(extack, "Invalid combination of local and remote address scopes"); return -EINVAL; } conf->flags &= ~VXLAN_F_IPV6_LINKLOCAL; } } } if (conf->label && !use_ipv6) { NL_SET_ERR_MSG(extack, "Label attribute only applies to IPv6 VXLAN devices"); return -EINVAL; } if (conf->label_policy && !use_ipv6) { NL_SET_ERR_MSG(extack, "Label policy only applies to IPv6 VXLAN devices"); return -EINVAL; } if (conf->remote_ifindex) { struct net_device *lowerdev; lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex); if (!lowerdev) { NL_SET_ERR_MSG(extack, "Invalid local interface, device not found"); return -ENODEV; } #if IS_ENABLED(CONFIG_IPV6) if (use_ipv6) { struct inet6_dev *idev = __in6_dev_get(lowerdev); if (idev && idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 support disabled by administrator"); return -EPERM; } } #endif *lower = lowerdev; } else { if (vxlan_addr_multicast(&conf->remote_ip)) { NL_SET_ERR_MSG(extack, "Local interface required for multicast remote destination"); return -EINVAL; } #if IS_ENABLED(CONFIG_IPV6) if (conf->flags & VXLAN_F_IPV6_LINKLOCAL) { NL_SET_ERR_MSG(extack, "Local interface required for link-local local/remote addresses"); return -EINVAL; } #endif *lower = NULL; } if (!conf->dst_port) { if (conf->flags & VXLAN_F_GPE) conf->dst_port = htons(IANA_VXLAN_GPE_UDP_PORT); else conf->dst_port = htons(vxlan_port); } if (!conf->age_interval) conf->age_interval = FDB_AGE_DEFAULT; if (vxlan_vni_in_use(src_net, old, conf, conf->vni)) { NL_SET_ERR_MSG(extack, "A VXLAN device with the specified VNI already exists"); return -EEXIST; } return 0; } static void vxlan_config_apply(struct net_device *dev, struct vxlan_config *conf, struct net_device *lowerdev, struct net *src_net, bool changelink) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; unsigned short needed_headroom = ETH_HLEN; int max_mtu = ETH_MAX_MTU; u32 flags = conf->flags; if (!changelink) { if (flags & VXLAN_F_GPE) vxlan_raw_setup(dev); else vxlan_ether_setup(dev); if (conf->mtu) dev->mtu = conf->mtu; vxlan->net = src_net; } dst->remote_vni = conf->vni; memcpy(&dst->remote_ip, &conf->remote_ip, sizeof(conf->remote_ip)); if (lowerdev) { dst->remote_ifindex = conf->remote_ifindex; netif_inherit_tso_max(dev, lowerdev); needed_headroom = lowerdev->hard_header_len; needed_headroom += lowerdev->needed_headroom; dev->needed_tailroom = lowerdev->needed_tailroom; max_mtu = lowerdev->mtu - vxlan_headroom(flags); if (max_mtu < ETH_MIN_MTU) max_mtu = ETH_MIN_MTU; if (!changelink && !conf->mtu) dev->mtu = max_mtu; } if (dev->mtu > max_mtu) dev->mtu = max_mtu; if (flags & VXLAN_F_COLLECT_METADATA) flags |= VXLAN_F_IPV6; needed_headroom += vxlan_headroom(flags); dev->needed_headroom = needed_headroom; memcpy(&vxlan->cfg, conf, sizeof(*conf)); } static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, struct vxlan_config *conf, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *lowerdev; int ret; ret = vxlan_config_validate(src_net, conf, &lowerdev, vxlan, extack); if (ret) return ret; vxlan_config_apply(dev, conf, lowerdev, src_net, false); return 0; } static int __vxlan_dev_create(struct net *net, struct net_device *dev, struct vxlan_config *conf, struct netlink_ext_ack *extack) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *remote_dev = NULL; struct vxlan_fdb *f = NULL; bool unregister = false; struct vxlan_rdst *dst; int err; dst = &vxlan->default_dst; err = vxlan_dev_configure(net, dev, conf, extack); if (err) return err; dev->ethtool_ops = &vxlan_ethtool_ops; /* create an fdb entry for a valid default destination */ if (!vxlan_addr_any(&dst->remote_ip)) { err = vxlan_fdb_create(vxlan, all_zeros_mac, &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, NTF_SELF, 0, &f, extack); if (err) return err; } err = register_netdevice(dev); if (err) goto errout; unregister = true; if (dst->remote_ifindex) { remote_dev = __dev_get_by_index(net, dst->remote_ifindex); if (!remote_dev) { err = -ENODEV; goto errout; } err = netdev_upper_dev_link(remote_dev, dev, extack); if (err) goto errout; } err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto unlink; if (f) { vxlan_fdb_insert(vxlan, all_zeros_mac, dst->remote_vni, f); /* notify default fdb entry */ err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, true, extack); if (err) { vxlan_fdb_destroy(vxlan, f, false, false); if (remote_dev) netdev_upper_dev_unlink(remote_dev, dev); goto unregister; } } list_add(&vxlan->next, &vn->vxlan_list); if (remote_dev) dst->remote_dev = remote_dev; return 0; unlink: if (remote_dev) netdev_upper_dev_unlink(remote_dev, dev); errout: /* unregister_netdevice() destroys the default FDB entry with deletion * notification. But the addition notification was not sent yet, so * destroy the entry by hand here. */ if (f) __vxlan_fdb_free(f); unregister: if (unregister) unregister_netdevice(dev); return err; } /* Set/clear flags based on attribute */ static int vxlan_nl2flag(struct vxlan_config *conf, struct nlattr *tb[], int attrtype, unsigned long mask, bool changelink, bool changelink_supported, struct netlink_ext_ack *extack) { unsigned long flags; if (!tb[attrtype]) return 0; if (changelink && !changelink_supported) { vxlan_flag_attr_error(attrtype, extack); return -EOPNOTSUPP; } if (vxlan_policy[attrtype].type == NLA_FLAG) flags = conf->flags | mask; else if (nla_get_u8(tb[attrtype])) flags = conf->flags | mask; else flags = conf->flags & ~mask; conf->flags = flags; return 0; } static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], struct net_device *dev, struct vxlan_config *conf, bool changelink, struct netlink_ext_ack *extack) { struct vxlanhdr used_bits = { .vx_flags = VXLAN_HF_VNI, .vx_vni = VXLAN_VNI_MASK, }; struct vxlan_dev *vxlan = netdev_priv(dev); int err = 0; memset(conf, 0, sizeof(*conf)); /* if changelink operation, start with old existing cfg */ if (changelink) memcpy(conf, &vxlan->cfg, sizeof(*conf)); if (data[IFLA_VXLAN_ID]) { __be32 vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); if (changelink && (vni != conf->vni)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID], "Cannot change VNI"); return -EOPNOTSUPP; } conf->vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); } if (data[IFLA_VXLAN_GROUP]) { if (changelink && (conf->remote_ip.sa.sa_family != AF_INET)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP], "New group address family does not match old group"); return -EOPNOTSUPP; } conf->remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]); conf->remote_ip.sa.sa_family = AF_INET; } else if (data[IFLA_VXLAN_GROUP6]) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } if (changelink && (conf->remote_ip.sa.sa_family != AF_INET6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "New group address family does not match old group"); return -EOPNOTSUPP; } conf->remote_ip.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_GROUP6]); conf->remote_ip.sa.sa_family = AF_INET6; } if (data[IFLA_VXLAN_LOCAL]) { if (changelink && (conf->saddr.sa.sa_family != AF_INET)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL], "New local address family does not match old"); return -EOPNOTSUPP; } conf->saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_LOCAL]); conf->saddr.sa.sa_family = AF_INET; } else if (data[IFLA_VXLAN_LOCAL6]) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } if (changelink && (conf->saddr.sa.sa_family != AF_INET6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "New local address family does not match old"); return -EOPNOTSUPP; } /* TODO: respect scope id */ conf->saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_LOCAL6]); conf->saddr.sa.sa_family = AF_INET6; } if (data[IFLA_VXLAN_LINK]) conf->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]); if (data[IFLA_VXLAN_TOS]) conf->tos = nla_get_u8(data[IFLA_VXLAN_TOS]); if (data[IFLA_VXLAN_TTL]) conf->ttl = nla_get_u8(data[IFLA_VXLAN_TTL]); if (data[IFLA_VXLAN_TTL_INHERIT]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_TTL_INHERIT, VXLAN_F_TTL_INHERIT, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_LABEL]) conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) & IPV6_FLOWLABEL_MASK; if (data[IFLA_VXLAN_LABEL_POLICY]) conf->label_policy = nla_get_u32(data[IFLA_VXLAN_LABEL_POLICY]); if (data[IFLA_VXLAN_LEARNING]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LEARNING, VXLAN_F_LEARN, changelink, true, extack); if (err) return err; } else if (!changelink) { /* default to learn on a new device */ conf->flags |= VXLAN_F_LEARN; } if (data[IFLA_VXLAN_AGEING]) conf->age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]); if (data[IFLA_VXLAN_PROXY]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_PROXY, VXLAN_F_PROXY, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_RSC]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_RSC, VXLAN_F_RSC, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_L2MISS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L2MISS, VXLAN_F_L2MISS, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_L3MISS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L3MISS, VXLAN_F_L3MISS, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_LIMIT]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LIMIT], "Cannot change limit"); return -EOPNOTSUPP; } conf->addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]); } if (data[IFLA_VXLAN_COLLECT_METADATA]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_COLLECT_METADATA, VXLAN_F_COLLECT_METADATA, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_PORT_RANGE]) { if (!changelink) { const struct ifla_vxlan_port_range *p = nla_data(data[IFLA_VXLAN_PORT_RANGE]); conf->port_min = ntohs(p->low); conf->port_max = ntohs(p->high); } else { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT_RANGE], "Cannot change port range"); return -EOPNOTSUPP; } } if (data[IFLA_VXLAN_PORT]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT], "Cannot change port"); return -EOPNOTSUPP; } conf->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); } if (data[IFLA_VXLAN_UDP_CSUM]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_UDP_CSUM], "Cannot change UDP_CSUM flag"); return -EOPNOTSUPP; } if (!nla_get_u8(data[IFLA_VXLAN_UDP_CSUM])) conf->flags |= VXLAN_F_UDP_ZERO_CSUM_TX; } if (data[IFLA_VXLAN_LOCALBYPASS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LOCALBYPASS, VXLAN_F_LOCALBYPASS, changelink, true, extack); if (err) return err; } else if (!changelink) { /* default to local bypass on a new device */ conf->flags |= VXLAN_F_LOCALBYPASS; } if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, VXLAN_F_UDP_ZERO_CSUM6_TX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, VXLAN_F_UDP_ZERO_CSUM6_RX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_TX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_TX, VXLAN_F_REMCSUM_TX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_RX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_RX, VXLAN_F_REMCSUM_RX, changelink, false, extack); if (err) return err; used_bits.vx_flags |= VXLAN_HF_RCO; used_bits.vx_vni |= ~VXLAN_VNI_MASK; } if (data[IFLA_VXLAN_GBP]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GBP, VXLAN_F_GBP, changelink, false, extack); if (err) return err; used_bits.vx_flags |= VXLAN_GBP_USED_BITS; } if (data[IFLA_VXLAN_GPE]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GPE, VXLAN_F_GPE, changelink, false, extack); if (err) return err; used_bits.vx_flags |= VXLAN_GPE_USED_BITS; } if (data[IFLA_VXLAN_RESERVED_BITS]) { struct vxlanhdr reserved_bits; if (changelink) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_RESERVED_BITS], "Cannot change reserved_bits"); return -EOPNOTSUPP; } nla_memcpy(&reserved_bits, data[IFLA_VXLAN_RESERVED_BITS], sizeof(reserved_bits)); if (used_bits.vx_flags & reserved_bits.vx_flags || used_bits.vx_vni & reserved_bits.vx_vni) { __be64 ub_be64, rb_be64; memcpy(&ub_be64, &used_bits, sizeof(ub_be64)); memcpy(&rb_be64, &reserved_bits, sizeof(rb_be64)); NL_SET_ERR_MSG_ATTR_FMT(extack, data[IFLA_VXLAN_RESERVED_BITS], "Used bits %#018llx cannot overlap reserved bits %#018llx", be64_to_cpu(ub_be64), be64_to_cpu(rb_be64)); return -EINVAL; } conf->reserved_bits = reserved_bits; } else { /* For backwards compatibility, only allow reserved fields to be * used by VXLAN extensions if explicitly requested. */ conf->reserved_bits = (struct vxlanhdr) { .vx_flags = ~used_bits.vx_flags, .vx_vni = ~used_bits.vx_vni, }; } if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_NOPARTIAL, VXLAN_F_REMCSUM_NOPARTIAL, changelink, false, extack); if (err) return err; } if (tb[IFLA_MTU]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], "Cannot change mtu"); return -EOPNOTSUPP; } conf->mtu = nla_get_u32(tb[IFLA_MTU]); } if (data[IFLA_VXLAN_DF]) conf->df = nla_get_u8(data[IFLA_VXLAN_DF]); if (data[IFLA_VXLAN_VNIFILTER]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_VNIFILTER, VXLAN_F_VNIFILTER, changelink, false, extack); if (err) return err; if ((conf->flags & VXLAN_F_VNIFILTER) && !(conf->flags & VXLAN_F_COLLECT_METADATA)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_VNIFILTER], "vxlan vnifilter only valid in collect metadata mode"); return -EINVAL; } } return 0; } static int vxlan_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct vxlan_config conf; int err; err = vxlan_nl2conf(tb, data, dev, &conf, false, extack); if (err) return err; return __vxlan_dev_create(link_net, dev, &conf, extack); } static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); bool rem_ip_changed, change_igmp; struct net_device *lowerdev; struct vxlan_config conf; struct vxlan_rdst *dst; int err; dst = &vxlan->default_dst; err = vxlan_nl2conf(tb, data, dev, &conf, true, extack); if (err) return err; err = vxlan_config_validate(vxlan->net, &conf, &lowerdev, vxlan, extack); if (err) return err; if (dst->remote_dev == lowerdev) lowerdev = NULL; err = netdev_adjacent_change_prepare(dst->remote_dev, lowerdev, dev, extack); if (err) return err; rem_ip_changed = !vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip); change_igmp = vxlan->dev->flags & IFF_UP && (rem_ip_changed || dst->remote_ifindex != conf.remote_ifindex); /* handle default dst entry */ if (rem_ip_changed) { u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); if (!vxlan_addr_any(&conf.remote_ip)) { err = vxlan_fdb_update(vxlan, all_zeros_mac, &conf.remote_ip, NUD_REACHABLE | NUD_PERMANENT, NLM_F_APPEND | NLM_F_CREATE, vxlan->cfg.dst_port, conf.vni, conf.vni, conf.remote_ifindex, NTF_SELF, 0, true, extack); if (err) { spin_unlock_bh(&vxlan->hash_lock[hash_index]); netdev_adjacent_change_abort(dst->remote_dev, lowerdev, dev); return err; } } if (!vxlan_addr_any(&dst->remote_ip)) __vxlan_fdb_delete(vxlan, all_zeros_mac, dst->remote_ip, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); /* If vni filtering device, also update fdb entries of * all vnis that were using default remote ip */ if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) { err = vxlan_vnilist_update_group(vxlan, &dst->remote_ip, &conf.remote_ip, extack); if (err) { netdev_adjacent_change_abort(dst->remote_dev, lowerdev, dev); return err; } } } if (change_igmp && vxlan_addr_multicast(&dst->remote_ip)) err = vxlan_multicast_leave(vxlan); if (conf.age_interval != vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies); netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev); if (lowerdev && lowerdev != dst->remote_dev) dst->remote_dev = lowerdev; vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true); if (!err && change_igmp && vxlan_addr_multicast(&dst->remote_ip)) err = vxlan_multicast_join(vxlan); return err; } static void vxlan_dellink(struct net_device *dev, struct list_head *head) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = { /* Default entry is deleted at vxlan_uninit. */ .ignore_default_entry = true, }; vxlan_flush(vxlan, &desc); list_del(&vxlan->next); unregister_netdevice_queue(dev, head); if (vxlan->default_dst.remote_dev) netdev_upper_dev_unlink(vxlan->default_dst.remote_dev, dev); } static size_t vxlan_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_ID */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_GROUP{6} */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL_INHERIT */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_DF */ nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LABEL_POLICY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_PROXY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_RSC */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L2MISS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L3MISS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_COLLECT_METADATA */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_AGEING */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LIMIT */ nla_total_size(sizeof(__be16)) + /* IFLA_VXLAN_PORT */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LOCALBYPASS */ /* IFLA_VXLAN_PORT_RANGE */ nla_total_size(sizeof(struct ifla_vxlan_port_range)) + nla_total_size(0) + /* IFLA_VXLAN_GBP */ nla_total_size(0) + /* IFLA_VXLAN_GPE */ nla_total_size(0) + /* IFLA_VXLAN_REMCSUM_NOPARTIAL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_VNIFILTER */ /* IFLA_VXLAN_RESERVED_BITS */ nla_total_size(sizeof(struct vxlanhdr)) + 0; } static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) { const struct vxlan_dev *vxlan = netdev_priv(dev); const struct vxlan_rdst *dst = &vxlan->default_dst; struct ifla_vxlan_port_range ports = { .low = htons(vxlan->cfg.port_min), .high = htons(vxlan->cfg.port_max), }; if (nla_put_u32(skb, IFLA_VXLAN_ID, be32_to_cpu(dst->remote_vni))) goto nla_put_failure; if (!vxlan_addr_any(&dst->remote_ip)) { if (dst->remote_ip.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, IFLA_VXLAN_GROUP, dst->remote_ip.sin.sin_addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, IFLA_VXLAN_GROUP6, &dst->remote_ip.sin6.sin6_addr)) goto nla_put_failure; #endif } } if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex)) goto nla_put_failure; if (!vxlan_addr_any(&vxlan->cfg.saddr)) { if (vxlan->cfg.saddr.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, IFLA_VXLAN_LOCAL, vxlan->cfg.saddr.sin.sin_addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, IFLA_VXLAN_LOCAL6, &vxlan->cfg.saddr.sin6.sin6_addr)) goto nla_put_failure; #endif } } if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) || nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT, !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) || nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) || nla_put_u32(skb, IFLA_VXLAN_LABEL_POLICY, vxlan->cfg.label_policy) || nla_put_u8(skb, IFLA_VXLAN_LEARNING, !!(vxlan->cfg.flags & VXLAN_F_LEARN)) || nla_put_u8(skb, IFLA_VXLAN_PROXY, !!(vxlan->cfg.flags & VXLAN_F_PROXY)) || nla_put_u8(skb, IFLA_VXLAN_RSC, !!(vxlan->cfg.flags & VXLAN_F_RSC)) || nla_put_u8(skb, IFLA_VXLAN_L2MISS, !!(vxlan->cfg.flags & VXLAN_F_L2MISS)) || nla_put_u8(skb, IFLA_VXLAN_L3MISS, !!(vxlan->cfg.flags & VXLAN_F_L3MISS)) || nla_put_u8(skb, IFLA_VXLAN_COLLECT_METADATA, !!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)) || nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->cfg.age_interval) || nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) || nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) || nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM, !(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_RX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_TX, !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_RX, !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_RX)) || nla_put_u8(skb, IFLA_VXLAN_LOCALBYPASS, !!(vxlan->cfg.flags & VXLAN_F_LOCALBYPASS))) goto nla_put_failure; if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_GBP && nla_put_flag(skb, IFLA_VXLAN_GBP)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_GPE && nla_put_flag(skb, IFLA_VXLAN_GPE)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_REMCSUM_NOPARTIAL && nla_put_flag(skb, IFLA_VXLAN_REMCSUM_NOPARTIAL)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_VNIFILTER && nla_put_u8(skb, IFLA_VXLAN_VNIFILTER, !!(vxlan->cfg.flags & VXLAN_F_VNIFILTER))) goto nla_put_failure; if (nla_put(skb, IFLA_VXLAN_RESERVED_BITS, sizeof(vxlan->cfg.reserved_bits), &vxlan->cfg.reserved_bits)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct net *vxlan_get_link_net(const struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); return READ_ONCE(vxlan->net); } static struct rtnl_link_ops vxlan_link_ops __read_mostly = { .kind = "vxlan", .maxtype = IFLA_VXLAN_MAX, .policy = vxlan_policy, .priv_size = sizeof(struct vxlan_dev), .setup = vxlan_setup, .validate = vxlan_validate, .newlink = vxlan_newlink, .changelink = vxlan_changelink, .dellink = vxlan_dellink, .get_size = vxlan_get_size, .fill_info = vxlan_fill_info, .get_link_net = vxlan_get_link_net, }; struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; int err; memset(&tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &vxlan_link_ops, tb, NULL); if (IS_ERR(dev)) return dev; err = __vxlan_dev_create(net, dev, conf, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); } err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) { LIST_HEAD(list_kill); vxlan_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } return dev; } EXPORT_SYMBOL_GPL(vxlan_dev_create); static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn, struct net_device *dev) { struct vxlan_dev *vxlan, *next; LIST_HEAD(list_kill); list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) { struct vxlan_rdst *dst = &vxlan->default_dst; /* In case we created vxlan device with carrier * and we loose the carrier due to module unload * we also need to remove vxlan device. In other * cases, it's not necessary and remote_ifindex * is 0 here, so no matches. */ if (dst->remote_ifindex == dev->ifindex) vxlan_dellink(vxlan->dev, &list_kill); } unregister_netdevice_many(&list_kill); } static int vxlan_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); if (event == NETDEV_UNREGISTER) vxlan_handle_lowerdev_unregister(vn, dev); else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO) vxlan_offload_rx_ports(dev, true); else if (event == NETDEV_UDP_TUNNEL_DROP_INFO) vxlan_offload_rx_ports(dev, false); return NOTIFY_DONE; } static struct notifier_block vxlan_notifier_block __read_mostly = { .notifier_call = vxlan_netdevice_event, }; static void vxlan_fdb_offloaded_set(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst; struct vxlan_fdb *f; u32 hash_index; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = __vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) goto out; rdst = vxlan_fdb_find_rdst(f, &fdb_info->remote_ip, fdb_info->remote_port, fdb_info->remote_vni, fdb_info->remote_ifindex); if (!rdst) goto out; rdst->offloaded = fdb_info->offloaded; out: spin_unlock_bh(&vxlan->hash_lock[hash_index]); } static int vxlan_fdb_external_learn_add(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct netlink_ext_ack *extack; u32 hash_index; int err; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); extack = switchdev_notifier_info_to_extack(&fdb_info->info); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = vxlan_fdb_update(vxlan, fdb_info->eth_addr, &fdb_info->remote_ip, NUD_REACHABLE, NLM_F_CREATE | NLM_F_REPLACE, fdb_info->remote_port, fdb_info->vni, fdb_info->remote_vni, fdb_info->remote_ifindex, NTF_USE | NTF_SELF | NTF_EXT_LEARNED, 0, false, extack); spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; } static int vxlan_fdb_external_learn_del(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; u32 hash_index; int err = 0; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = __vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) err = -ENOENT; else if (f->flags & NTF_EXT_LEARNED) err = __vxlan_fdb_delete(vxlan, fdb_info->eth_addr, fdb_info->remote_ip, fdb_info->remote_port, fdb_info->vni, fdb_info->remote_vni, fdb_info->remote_ifindex, false); spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; } static int vxlan_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct switchdev_notifier_vxlan_fdb_info *fdb_info; int err = 0; switch (event) { case SWITCHDEV_VXLAN_FDB_OFFLOADED: vxlan_fdb_offloaded_set(dev, ptr); break; case SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = vxlan_fdb_external_learn_add(dev, fdb_info); if (err) { err = notifier_from_errno(err); break; } fdb_info->offloaded = true; vxlan_fdb_offloaded_set(dev, fdb_info); break; case SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = vxlan_fdb_external_learn_del(dev, fdb_info); if (err) { err = notifier_from_errno(err); break; } fdb_info->offloaded = false; vxlan_fdb_offloaded_set(dev, fdb_info); break; } return err; } static struct notifier_block vxlan_switchdev_notifier_block __read_mostly = { .notifier_call = vxlan_switchdev_event, }; static void vxlan_fdb_nh_flush(struct nexthop *nh) { struct vxlan_fdb *fdb; struct vxlan_dev *vxlan; u32 hash_index; rcu_read_lock(); list_for_each_entry_rcu(fdb, &nh->fdb_list, nh_list) { vxlan = rcu_dereference(fdb->vdev); WARN_ON(!vxlan); hash_index = fdb_head_index(vxlan, fdb->eth_addr, vxlan->default_dst.remote_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); if (!hlist_unhashed(&fdb->hlist)) vxlan_fdb_destroy(vxlan, fdb, false, false); spin_unlock_bh(&vxlan->hash_lock[hash_index]); } rcu_read_unlock(); } static int vxlan_nexthop_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct nh_notifier_info *info = ptr; struct nexthop *nh; if (event != NEXTHOP_EVENT_DEL) return NOTIFY_DONE; nh = nexthop_find_by_id(info->net, info->id); if (!nh) return NOTIFY_DONE; vxlan_fdb_nh_flush(nh); return NOTIFY_DONE; } static __net_init int vxlan_init_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int h; INIT_LIST_HEAD(&vn->vxlan_list); spin_lock_init(&vn->sock_lock); vn->nexthop_notifier_block.notifier_call = vxlan_nexthop_event; for (h = 0; h < PORT_HASH_SIZE; ++h) INIT_HLIST_HEAD(&vn->sock_list[h]); return register_nexthop_notifier(net, &vn->nexthop_notifier_block, NULL); } static void __net_exit vxlan_destroy_tunnels(struct vxlan_net *vn, struct list_head *dev_to_kill) { struct vxlan_dev *vxlan, *next; list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) vxlan_dellink(vxlan->dev, dev_to_kill); } static void __net_exit vxlan_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); __unregister_nexthop_notifier(net, &vn->nexthop_notifier_block); vxlan_destroy_tunnels(vn, dev_to_kill); } } static void __net_exit vxlan_exit_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int h; for (h = 0; h < PORT_HASH_SIZE; ++h) WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h])); } static struct pernet_operations vxlan_net_ops = { .init = vxlan_init_net, .exit_batch_rtnl = vxlan_exit_batch_rtnl, .exit = vxlan_exit_net, .id = &vxlan_net_id, .size = sizeof(struct vxlan_net), }; static int __init vxlan_init_module(void) { int rc; get_random_bytes(&vxlan_salt, sizeof(vxlan_salt)); rc = register_pernet_subsys(&vxlan_net_ops); if (rc) goto out1; rc = register_netdevice_notifier(&vxlan_notifier_block); if (rc) goto out2; rc = register_switchdev_notifier(&vxlan_switchdev_notifier_block); if (rc) goto out3; rc = rtnl_link_register(&vxlan_link_ops); if (rc) goto out4; rc = vxlan_vnifilter_init(); if (rc) goto out5; return 0; out5: rtnl_link_unregister(&vxlan_link_ops); out4: unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); out3: unregister_netdevice_notifier(&vxlan_notifier_block); out2: unregister_pernet_subsys(&vxlan_net_ops); out1: return rc; } late_initcall(vxlan_init_module); static void __exit vxlan_cleanup_module(void) { vxlan_vnifilter_uninit(); rtnl_link_unregister(&vxlan_link_ops); unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); unregister_netdevice_notifier(&vxlan_notifier_block); unregister_pernet_subsys(&vxlan_net_ops); /* rcu_barrier() is called by netns */ } module_exit(vxlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(VXLAN_VERSION); MODULE_AUTHOR("Stephen Hemminger <stephen@networkplumber.org>"); MODULE_DESCRIPTION("Driver for VXLAN encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("vxlan"); |
| 3 1 1 1 2 2 2 5 3 2 1 6 3 1 2 2 2 5 5 1 3 1 3 1 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * CMOS/NV-RAM driver for Linux * * Copyright (C) 1997 Roman Hodek <Roman.Hodek@informatik.uni-erlangen.de> * idea by and with help from Richard Jelinek <rj@suse.de> * Portions copyright (c) 2001,2002 Sun Microsystems (thockin@sun.com) * * This driver allows you to access the contents of the non-volatile memory in * the mc146818rtc.h real-time clock. This chip is built into all PCs and into * many Atari machines. In the former it's called "CMOS-RAM", in the latter * "NVRAM" (NV stands for non-volatile). * * The data are supplied as a (seekable) character device, /dev/nvram. The * size of this file is dependent on the controller. The usual size is 114, * the number of freely available bytes in the memory (i.e., not used by the * RTC itself). * * Checksums over the NVRAM contents are managed by this driver. In case of a * bad checksum, reads and writes return -EIO. The checksum can be initialized * to a sane state either by ioctl(NVRAM_INIT) (clear whole NVRAM) or * ioctl(NVRAM_SETCKS) (doesn't change contents, just makes checksum valid * again; use with care!) * * 1.1 Cesar Barros: SMP locking fixes * added changelog * 1.2 Erik Gilling: Cobalt Networks support * Tim Hockin: general cleanup, Cobalt support * 1.3 Wim Van Sebroeck: convert PRINT_PROC to seq_file */ #define NVRAM_VERSION "1.3" #include <linux/module.h> #include <linux/nvram.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/miscdevice.h> #include <linux/ioport.h> #include <linux/fcntl.h> #include <linux/mc146818rtc.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/io.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/pagemap.h> #ifdef CONFIG_PPC #include <asm/nvram.h> #endif static DEFINE_MUTEX(nvram_mutex); static DEFINE_SPINLOCK(nvram_state_lock); static int nvram_open_cnt; /* #times opened */ static int nvram_open_mode; /* special open modes */ static ssize_t nvram_size; #define NVRAM_WRITE 1 /* opened for writing (exclusive) */ #define NVRAM_EXCL 2 /* opened with O_EXCL */ #ifdef CONFIG_X86 /* * These functions are provided to be called internally or by other parts of * the kernel. It's up to the caller to ensure correct checksum before reading * or after writing (needs to be done only once). * * It is worth noting that these functions all access bytes of general * purpose memory in the NVRAM - that is to say, they all add the * NVRAM_FIRST_BYTE offset. Pass them offsets into NVRAM as if you did not * know about the RTC cruft. */ #define NVRAM_BYTES (128 - NVRAM_FIRST_BYTE) /* Note that *all* calls to CMOS_READ and CMOS_WRITE must be done with * rtc_lock held. Due to the index-port/data-port design of the RTC, we * don't want two different things trying to get to it at once. (e.g. the * periodic 11 min sync from kernel/time/ntp.c vs. this driver.) */ static unsigned char __nvram_read_byte(int i) { return CMOS_READ(NVRAM_FIRST_BYTE + i); } static unsigned char pc_nvram_read_byte(int i) { unsigned long flags; unsigned char c; spin_lock_irqsave(&rtc_lock, flags); c = __nvram_read_byte(i); spin_unlock_irqrestore(&rtc_lock, flags); return c; } /* This races nicely with trying to read with checksum checking (nvram_read) */ static void __nvram_write_byte(unsigned char c, int i) { CMOS_WRITE(c, NVRAM_FIRST_BYTE + i); } static void pc_nvram_write_byte(unsigned char c, int i) { unsigned long flags; spin_lock_irqsave(&rtc_lock, flags); __nvram_write_byte(c, i); spin_unlock_irqrestore(&rtc_lock, flags); } /* On PCs, the checksum is built only over bytes 2..31 */ #define PC_CKS_RANGE_START 2 #define PC_CKS_RANGE_END 31 #define PC_CKS_LOC 32 static int __nvram_check_checksum(void) { int i; unsigned short sum = 0; unsigned short expect; for (i = PC_CKS_RANGE_START; i <= PC_CKS_RANGE_END; ++i) sum += __nvram_read_byte(i); expect = __nvram_read_byte(PC_CKS_LOC)<<8 | __nvram_read_byte(PC_CKS_LOC+1); return (sum & 0xffff) == expect; } static void __nvram_set_checksum(void) { int i; unsigned short sum = 0; for (i = PC_CKS_RANGE_START; i <= PC_CKS_RANGE_END; ++i) sum += __nvram_read_byte(i); __nvram_write_byte(sum >> 8, PC_CKS_LOC); __nvram_write_byte(sum & 0xff, PC_CKS_LOC + 1); } static long pc_nvram_set_checksum(void) { spin_lock_irq(&rtc_lock); __nvram_set_checksum(); spin_unlock_irq(&rtc_lock); return 0; } static long pc_nvram_initialize(void) { ssize_t i; spin_lock_irq(&rtc_lock); for (i = 0; i < NVRAM_BYTES; ++i) __nvram_write_byte(0, i); __nvram_set_checksum(); spin_unlock_irq(&rtc_lock); return 0; } static ssize_t pc_nvram_get_size(void) { return NVRAM_BYTES; } static ssize_t pc_nvram_read(char *buf, size_t count, loff_t *ppos) { char *p = buf; loff_t i; spin_lock_irq(&rtc_lock); if (!__nvram_check_checksum()) { spin_unlock_irq(&rtc_lock); return -EIO; } for (i = *ppos; count > 0 && i < NVRAM_BYTES; --count, ++i, ++p) *p = __nvram_read_byte(i); spin_unlock_irq(&rtc_lock); *ppos = i; return p - buf; } static ssize_t pc_nvram_write(char *buf, size_t count, loff_t *ppos) { char *p = buf; loff_t i; spin_lock_irq(&rtc_lock); if (!__nvram_check_checksum()) { spin_unlock_irq(&rtc_lock); return -EIO; } for (i = *ppos; count > 0 && i < NVRAM_BYTES; --count, ++i, ++p) __nvram_write_byte(*p, i); __nvram_set_checksum(); spin_unlock_irq(&rtc_lock); *ppos = i; return p - buf; } const struct nvram_ops arch_nvram_ops = { .read = pc_nvram_read, .write = pc_nvram_write, .read_byte = pc_nvram_read_byte, .write_byte = pc_nvram_write_byte, .get_size = pc_nvram_get_size, .set_checksum = pc_nvram_set_checksum, .initialize = pc_nvram_initialize, }; EXPORT_SYMBOL(arch_nvram_ops); #endif /* CONFIG_X86 */ /* * The are the file operation function for user access to /dev/nvram */ static loff_t nvram_misc_llseek(struct file *file, loff_t offset, int origin) { return generic_file_llseek_size(file, offset, origin, MAX_LFS_FILESIZE, nvram_size); } static ssize_t nvram_misc_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { char *tmp; ssize_t ret; if (*ppos >= nvram_size) return 0; count = min_t(size_t, count, nvram_size - *ppos); count = min_t(size_t, count, PAGE_SIZE); tmp = kmalloc(count, GFP_KERNEL); if (!tmp) return -ENOMEM; ret = nvram_read(tmp, count, ppos); if (ret <= 0) goto out; if (copy_to_user(buf, tmp, ret)) { *ppos -= ret; ret = -EFAULT; } out: kfree(tmp); return ret; } static ssize_t nvram_misc_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *tmp; ssize_t ret; if (*ppos >= nvram_size) return 0; count = min_t(size_t, count, nvram_size - *ppos); count = min_t(size_t, count, PAGE_SIZE); tmp = memdup_user(buf, count); if (IS_ERR(tmp)) return PTR_ERR(tmp); ret = nvram_write(tmp, count, ppos); kfree(tmp); return ret; } static long nvram_misc_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { long ret = -ENOTTY; switch (cmd) { #ifdef CONFIG_PPC case OBSOLETE_PMAC_NVRAM_GET_OFFSET: pr_warn("nvram: Using obsolete PMAC_NVRAM_GET_OFFSET ioctl\n"); fallthrough; case IOC_NVRAM_GET_OFFSET: ret = -EINVAL; #ifdef CONFIG_PPC_PMAC if (machine_is(powermac)) { int part, offset; if (copy_from_user(&part, (void __user *)arg, sizeof(part)) != 0) return -EFAULT; if (part < pmac_nvram_OF || part > pmac_nvram_NR) return -EINVAL; offset = pmac_get_partition(part); if (offset < 0) return -EINVAL; if (copy_to_user((void __user *)arg, &offset, sizeof(offset)) != 0) return -EFAULT; ret = 0; } #endif break; #ifdef CONFIG_PPC32 case IOC_NVRAM_SYNC: if (ppc_md.nvram_sync != NULL) { mutex_lock(&nvram_mutex); ppc_md.nvram_sync(); mutex_unlock(&nvram_mutex); } ret = 0; break; #endif #elif defined(CONFIG_X86) || defined(CONFIG_M68K) case NVRAM_INIT: /* initialize NVRAM contents and checksum */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (arch_nvram_ops.initialize != NULL) { mutex_lock(&nvram_mutex); ret = arch_nvram_ops.initialize(); mutex_unlock(&nvram_mutex); } break; case NVRAM_SETCKS: /* just set checksum, contents unchanged (maybe useful after * checksum garbaged somehow...) */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (arch_nvram_ops.set_checksum != NULL) { mutex_lock(&nvram_mutex); ret = arch_nvram_ops.set_checksum(); mutex_unlock(&nvram_mutex); } break; #endif /* CONFIG_X86 || CONFIG_M68K */ } return ret; } static int nvram_misc_open(struct inode *inode, struct file *file) { spin_lock(&nvram_state_lock); /* Prevent multiple readers/writers if desired. */ if ((nvram_open_cnt && (file->f_flags & O_EXCL)) || (nvram_open_mode & NVRAM_EXCL)) { spin_unlock(&nvram_state_lock); return -EBUSY; } #if defined(CONFIG_X86) || defined(CONFIG_M68K) /* Prevent multiple writers if the set_checksum ioctl is implemented. */ if ((arch_nvram_ops.set_checksum != NULL) && (file->f_mode & FMODE_WRITE) && (nvram_open_mode & NVRAM_WRITE)) { spin_unlock(&nvram_state_lock); return -EBUSY; } #endif if (file->f_flags & O_EXCL) nvram_open_mode |= NVRAM_EXCL; if (file->f_mode & FMODE_WRITE) nvram_open_mode |= NVRAM_WRITE; nvram_open_cnt++; spin_unlock(&nvram_state_lock); return 0; } static int nvram_misc_release(struct inode *inode, struct file *file) { spin_lock(&nvram_state_lock); nvram_open_cnt--; /* if only one instance is open, clear the EXCL bit */ if (nvram_open_mode & NVRAM_EXCL) nvram_open_mode &= ~NVRAM_EXCL; if (file->f_mode & FMODE_WRITE) nvram_open_mode &= ~NVRAM_WRITE; spin_unlock(&nvram_state_lock); return 0; } #if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) static const char * const floppy_types[] = { "none", "5.25'' 360k", "5.25'' 1.2M", "3.5'' 720k", "3.5'' 1.44M", "3.5'' 2.88M", "3.5'' 2.88M" }; static const char * const gfx_types[] = { "EGA, VGA, ... (with BIOS)", "CGA (40 cols)", "CGA (80 cols)", "monochrome", }; static void pc_nvram_proc_read(unsigned char *nvram, struct seq_file *seq, void *offset) { int checksum; int type; spin_lock_irq(&rtc_lock); checksum = __nvram_check_checksum(); spin_unlock_irq(&rtc_lock); seq_printf(seq, "Checksum status: %svalid\n", checksum ? "" : "not "); seq_printf(seq, "# floppies : %d\n", (nvram[6] & 1) ? (nvram[6] >> 6) + 1 : 0); seq_printf(seq, "Floppy 0 type : "); type = nvram[2] >> 4; if (type < ARRAY_SIZE(floppy_types)) seq_printf(seq, "%s\n", floppy_types[type]); else seq_printf(seq, "%d (unknown)\n", type); seq_printf(seq, "Floppy 1 type : "); type = nvram[2] & 0x0f; if (type < ARRAY_SIZE(floppy_types)) seq_printf(seq, "%s\n", floppy_types[type]); else seq_printf(seq, "%d (unknown)\n", type); seq_printf(seq, "HD 0 type : "); type = nvram[4] >> 4; if (type) seq_printf(seq, "%02x\n", type == 0x0f ? nvram[11] : type); else seq_printf(seq, "none\n"); seq_printf(seq, "HD 1 type : "); type = nvram[4] & 0x0f; if (type) seq_printf(seq, "%02x\n", type == 0x0f ? nvram[12] : type); else seq_printf(seq, "none\n"); seq_printf(seq, "HD type 48 data: %d/%d/%d C/H/S, precomp %d, lz %d\n", nvram[18] | (nvram[19] << 8), nvram[20], nvram[25], nvram[21] | (nvram[22] << 8), nvram[23] | (nvram[24] << 8)); seq_printf(seq, "HD type 49 data: %d/%d/%d C/H/S, precomp %d, lz %d\n", nvram[39] | (nvram[40] << 8), nvram[41], nvram[46], nvram[42] | (nvram[43] << 8), nvram[44] | (nvram[45] << 8)); seq_printf(seq, "DOS base memory: %d kB\n", nvram[7] | (nvram[8] << 8)); seq_printf(seq, "Extended memory: %d kB (configured), %d kB (tested)\n", nvram[9] | (nvram[10] << 8), nvram[34] | (nvram[35] << 8)); seq_printf(seq, "Gfx adapter : %s\n", gfx_types[(nvram[6] >> 4) & 3]); seq_printf(seq, "FPU : %sinstalled\n", (nvram[6] & 2) ? "" : "not "); return; } static int nvram_proc_read(struct seq_file *seq, void *offset) { unsigned char contents[NVRAM_BYTES]; int i = 0; spin_lock_irq(&rtc_lock); for (i = 0; i < NVRAM_BYTES; ++i) contents[i] = __nvram_read_byte(i); spin_unlock_irq(&rtc_lock); pc_nvram_proc_read(contents, seq, offset); return 0; } #endif /* CONFIG_X86 && CONFIG_PROC_FS */ static const struct file_operations nvram_misc_fops = { .owner = THIS_MODULE, .llseek = nvram_misc_llseek, .read = nvram_misc_read, .write = nvram_misc_write, .unlocked_ioctl = nvram_misc_ioctl, .open = nvram_misc_open, .release = nvram_misc_release, }; static struct miscdevice nvram_misc = { NVRAM_MINOR, "nvram", &nvram_misc_fops, }; static int __init nvram_module_init(void) { int ret; nvram_size = nvram_get_size(); if (nvram_size < 0) return nvram_size; ret = misc_register(&nvram_misc); if (ret) { pr_err("nvram: can't misc_register on minor=%d\n", NVRAM_MINOR); return ret; } #if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) if (!proc_create_single("driver/nvram", 0, NULL, nvram_proc_read)) { pr_err("nvram: can't create /proc/driver/nvram\n"); misc_deregister(&nvram_misc); return -ENOMEM; } #endif pr_info("Non-volatile memory driver v" NVRAM_VERSION "\n"); return 0; } static void __exit nvram_module_exit(void) { #if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) remove_proc_entry("driver/nvram", NULL); #endif misc_deregister(&nvram_misc); } module_init(nvram_module_init); module_exit(nvram_module_exit); MODULE_DESCRIPTION("CMOS/NV-RAM driver for Linux"); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(NVRAM_MINOR); MODULE_ALIAS("devname:nvram"); |
| 7 8 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 | /* * videobuf2-vmalloc.c - vmalloc memory allocator for videobuf2 * * Copyright (C) 2010 Samsung Electronics * * Author: Pawel Osciak <pawel@osciak.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation. */ #include <linux/io.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/refcount.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <media/videobuf2-v4l2.h> #include <media/videobuf2-vmalloc.h> #include <media/videobuf2-memops.h> struct vb2_vmalloc_buf { void *vaddr; struct frame_vector *vec; enum dma_data_direction dma_dir; unsigned long size; refcount_t refcount; struct vb2_vmarea_handler handler; struct dma_buf *dbuf; }; static void vb2_vmalloc_put(void *buf_priv); static void *vb2_vmalloc_alloc(struct vb2_buffer *vb, struct device *dev, unsigned long size) { struct vb2_vmalloc_buf *buf; buf = kzalloc(sizeof(*buf), GFP_KERNEL | vb->vb2_queue->gfp_flags); if (!buf) return ERR_PTR(-ENOMEM); buf->size = size; buf->vaddr = vmalloc_user(buf->size); if (!buf->vaddr) { pr_debug("vmalloc of size %ld failed\n", buf->size); kfree(buf); return ERR_PTR(-ENOMEM); } buf->dma_dir = vb->vb2_queue->dma_dir; buf->handler.refcount = &buf->refcount; buf->handler.put = vb2_vmalloc_put; buf->handler.arg = buf; refcount_set(&buf->refcount, 1); return buf; } static void vb2_vmalloc_put(void *buf_priv) { struct vb2_vmalloc_buf *buf = buf_priv; if (refcount_dec_and_test(&buf->refcount)) { vfree(buf->vaddr); kfree(buf); } } static void *vb2_vmalloc_get_userptr(struct vb2_buffer *vb, struct device *dev, unsigned long vaddr, unsigned long size) { struct vb2_vmalloc_buf *buf; struct frame_vector *vec; int n_pages, offset, i; int ret = -ENOMEM; buf = kzalloc(sizeof(*buf), GFP_KERNEL); if (!buf) return ERR_PTR(-ENOMEM); buf->dma_dir = vb->vb2_queue->dma_dir; offset = vaddr & ~PAGE_MASK; buf->size = size; vec = vb2_create_framevec(vaddr, size, buf->dma_dir == DMA_FROM_DEVICE || buf->dma_dir == DMA_BIDIRECTIONAL); if (IS_ERR(vec)) { ret = PTR_ERR(vec); goto fail_pfnvec_create; } buf->vec = vec; n_pages = frame_vector_count(vec); if (frame_vector_to_pages(vec) < 0) { unsigned long *nums = frame_vector_pfns(vec); /* * We cannot get page pointers for these pfns. Check memory is * physically contiguous and use direct mapping. */ for (i = 1; i < n_pages; i++) if (nums[i-1] + 1 != nums[i]) goto fail_map; buf->vaddr = (__force void *) ioremap(__pfn_to_phys(nums[0]), size + offset); } else { buf->vaddr = vm_map_ram(frame_vector_pages(vec), n_pages, -1); } if (!buf->vaddr) goto fail_map; buf->vaddr += offset; return buf; fail_map: vb2_destroy_framevec(vec); fail_pfnvec_create: kfree(buf); return ERR_PTR(ret); } static void vb2_vmalloc_put_userptr(void *buf_priv) { struct vb2_vmalloc_buf *buf = buf_priv; unsigned long vaddr = (unsigned long)buf->vaddr & PAGE_MASK; unsigned int i; struct page **pages; unsigned int n_pages; if (!buf->vec->is_pfns) { n_pages = frame_vector_count(buf->vec); if (vaddr) vm_unmap_ram((void *)vaddr, n_pages); if (buf->dma_dir == DMA_FROM_DEVICE || buf->dma_dir == DMA_BIDIRECTIONAL) { pages = frame_vector_pages(buf->vec); if (!WARN_ON_ONCE(IS_ERR(pages))) for (i = 0; i < n_pages; i++) set_page_dirty_lock(pages[i]); } } else { iounmap((__force void __iomem *)buf->vaddr); } vb2_destroy_framevec(buf->vec); kfree(buf); } static void *vb2_vmalloc_vaddr(struct vb2_buffer *vb, void *buf_priv) { struct vb2_vmalloc_buf *buf = buf_priv; if (!buf->vaddr) { pr_err("Address of an unallocated plane requested or cannot map user pointer\n"); return NULL; } return buf->vaddr; } static unsigned int vb2_vmalloc_num_users(void *buf_priv) { struct vb2_vmalloc_buf *buf = buf_priv; return refcount_read(&buf->refcount); } static int vb2_vmalloc_mmap(void *buf_priv, struct vm_area_struct *vma) { struct vb2_vmalloc_buf *buf = buf_priv; int ret; if (!buf) { pr_err("No memory to map\n"); return -EINVAL; } ret = remap_vmalloc_range(vma, buf->vaddr, 0); if (ret) { pr_err("Remapping vmalloc memory, error: %d\n", ret); return ret; } /* * Make sure that vm_areas for 2 buffers won't be merged together */ vm_flags_set(vma, VM_DONTEXPAND); /* * Use common vm_area operations to track buffer refcount. */ vma->vm_private_data = &buf->handler; vma->vm_ops = &vb2_common_vm_ops; vma->vm_ops->open(vma); return 0; } #ifdef CONFIG_HAS_DMA /*********************************************/ /* DMABUF ops for exporters */ /*********************************************/ struct vb2_vmalloc_attachment { struct sg_table sgt; enum dma_data_direction dma_dir; }; static int vb2_vmalloc_dmabuf_ops_attach(struct dma_buf *dbuf, struct dma_buf_attachment *dbuf_attach) { struct vb2_vmalloc_attachment *attach; struct vb2_vmalloc_buf *buf = dbuf->priv; int num_pages = PAGE_ALIGN(buf->size) / PAGE_SIZE; struct sg_table *sgt; struct scatterlist *sg; void *vaddr = buf->vaddr; int ret; int i; attach = kzalloc(sizeof(*attach), GFP_KERNEL); if (!attach) return -ENOMEM; sgt = &attach->sgt; ret = sg_alloc_table(sgt, num_pages, GFP_KERNEL); if (ret) { kfree(attach); return ret; } for_each_sgtable_sg(sgt, sg, i) { struct page *page = vmalloc_to_page(vaddr); if (!page) { sg_free_table(sgt); kfree(attach); return -ENOMEM; } sg_set_page(sg, page, PAGE_SIZE, 0); vaddr += PAGE_SIZE; } attach->dma_dir = DMA_NONE; dbuf_attach->priv = attach; return 0; } static void vb2_vmalloc_dmabuf_ops_detach(struct dma_buf *dbuf, struct dma_buf_attachment *db_attach) { struct vb2_vmalloc_attachment *attach = db_attach->priv; struct sg_table *sgt; if (!attach) return; sgt = &attach->sgt; /* release the scatterlist cache */ if (attach->dma_dir != DMA_NONE) dma_unmap_sgtable(db_attach->dev, sgt, attach->dma_dir, 0); sg_free_table(sgt); kfree(attach); db_attach->priv = NULL; } static struct sg_table *vb2_vmalloc_dmabuf_ops_map( struct dma_buf_attachment *db_attach, enum dma_data_direction dma_dir) { struct vb2_vmalloc_attachment *attach = db_attach->priv; struct sg_table *sgt; sgt = &attach->sgt; /* return previously mapped sg table */ if (attach->dma_dir == dma_dir) return sgt; /* release any previous cache */ if (attach->dma_dir != DMA_NONE) { dma_unmap_sgtable(db_attach->dev, sgt, attach->dma_dir, 0); attach->dma_dir = DMA_NONE; } /* mapping to the client with new direction */ if (dma_map_sgtable(db_attach->dev, sgt, dma_dir, 0)) { pr_err("failed to map scatterlist\n"); return ERR_PTR(-EIO); } attach->dma_dir = dma_dir; return sgt; } static void vb2_vmalloc_dmabuf_ops_unmap(struct dma_buf_attachment *db_attach, struct sg_table *sgt, enum dma_data_direction dma_dir) { /* nothing to be done here */ } static void vb2_vmalloc_dmabuf_ops_release(struct dma_buf *dbuf) { /* drop reference obtained in vb2_vmalloc_get_dmabuf */ vb2_vmalloc_put(dbuf->priv); } static int vb2_vmalloc_dmabuf_ops_vmap(struct dma_buf *dbuf, struct iosys_map *map) { struct vb2_vmalloc_buf *buf = dbuf->priv; iosys_map_set_vaddr(map, buf->vaddr); return 0; } static int vb2_vmalloc_dmabuf_ops_mmap(struct dma_buf *dbuf, struct vm_area_struct *vma) { return vb2_vmalloc_mmap(dbuf->priv, vma); } static const struct dma_buf_ops vb2_vmalloc_dmabuf_ops = { .attach = vb2_vmalloc_dmabuf_ops_attach, .detach = vb2_vmalloc_dmabuf_ops_detach, .map_dma_buf = vb2_vmalloc_dmabuf_ops_map, .unmap_dma_buf = vb2_vmalloc_dmabuf_ops_unmap, .vmap = vb2_vmalloc_dmabuf_ops_vmap, .mmap = vb2_vmalloc_dmabuf_ops_mmap, .release = vb2_vmalloc_dmabuf_ops_release, }; static struct dma_buf *vb2_vmalloc_get_dmabuf(struct vb2_buffer *vb, void *buf_priv, unsigned long flags) { struct vb2_vmalloc_buf *buf = buf_priv; struct dma_buf *dbuf; DEFINE_DMA_BUF_EXPORT_INFO(exp_info); exp_info.ops = &vb2_vmalloc_dmabuf_ops; exp_info.size = buf->size; exp_info.flags = flags; exp_info.priv = buf; if (WARN_ON(!buf->vaddr)) return NULL; dbuf = dma_buf_export(&exp_info); if (IS_ERR(dbuf)) return NULL; /* dmabuf keeps reference to vb2 buffer */ refcount_inc(&buf->refcount); return dbuf; } #endif /* CONFIG_HAS_DMA */ /*********************************************/ /* callbacks for DMABUF buffers */ /*********************************************/ static int vb2_vmalloc_map_dmabuf(void *mem_priv) { struct vb2_vmalloc_buf *buf = mem_priv; struct iosys_map map; int ret; ret = dma_buf_vmap_unlocked(buf->dbuf, &map); if (ret) return -EFAULT; buf->vaddr = map.vaddr; return 0; } static void vb2_vmalloc_unmap_dmabuf(void *mem_priv) { struct vb2_vmalloc_buf *buf = mem_priv; struct iosys_map map = IOSYS_MAP_INIT_VADDR(buf->vaddr); dma_buf_vunmap_unlocked(buf->dbuf, &map); buf->vaddr = NULL; } static void vb2_vmalloc_detach_dmabuf(void *mem_priv) { struct vb2_vmalloc_buf *buf = mem_priv; struct iosys_map map = IOSYS_MAP_INIT_VADDR(buf->vaddr); if (buf->vaddr) dma_buf_vunmap_unlocked(buf->dbuf, &map); kfree(buf); } static void *vb2_vmalloc_attach_dmabuf(struct vb2_buffer *vb, struct device *dev, struct dma_buf *dbuf, unsigned long size) { struct vb2_vmalloc_buf *buf; if (dbuf->size < size) return ERR_PTR(-EFAULT); buf = kzalloc(sizeof(*buf), GFP_KERNEL); if (!buf) return ERR_PTR(-ENOMEM); buf->dbuf = dbuf; buf->dma_dir = vb->vb2_queue->dma_dir; buf->size = size; return buf; } const struct vb2_mem_ops vb2_vmalloc_memops = { .alloc = vb2_vmalloc_alloc, .put = vb2_vmalloc_put, .get_userptr = vb2_vmalloc_get_userptr, .put_userptr = vb2_vmalloc_put_userptr, #ifdef CONFIG_HAS_DMA .get_dmabuf = vb2_vmalloc_get_dmabuf, #endif .map_dmabuf = vb2_vmalloc_map_dmabuf, .unmap_dmabuf = vb2_vmalloc_unmap_dmabuf, .attach_dmabuf = vb2_vmalloc_attach_dmabuf, .detach_dmabuf = vb2_vmalloc_detach_dmabuf, .vaddr = vb2_vmalloc_vaddr, .mmap = vb2_vmalloc_mmap, .num_users = vb2_vmalloc_num_users, }; EXPORT_SYMBOL_GPL(vb2_vmalloc_memops); MODULE_DESCRIPTION("vmalloc memory handling routines for videobuf2"); MODULE_AUTHOR("Pawel Osciak <pawel@osciak.com>"); MODULE_LICENSE("GPL"); MODULE_IMPORT_NS("DMA_BUF"); |
| 447 288 | 1 2 3 4 5 6 7 8 9 10 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM vmalloc #if !defined(_TRACE_VMALLOC_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_VMALLOC_H #include <linux/tracepoint.h> /** * alloc_vmap_area - called when a new vmap allocation occurs * @addr: an allocated address * @size: a requested size * @align: a requested alignment * @vstart: a requested start range * @vend: a requested end range * @failed: an allocation failed or not * * This event is used for a debug purpose, it can give an extra * information for a developer about how often it occurs and which * parameters are passed for further validation. */ TRACE_EVENT(alloc_vmap_area, TP_PROTO(unsigned long addr, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int failed), TP_ARGS(addr, size, align, vstart, vend, failed), TP_STRUCT__entry( __field(unsigned long, addr) __field(unsigned long, size) __field(unsigned long, align) __field(unsigned long, vstart) __field(unsigned long, vend) __field(int, failed) ), TP_fast_assign( __entry->addr = addr; __entry->size = size; __entry->align = align; __entry->vstart = vstart; __entry->vend = vend; __entry->failed = failed; ), TP_printk("va_start: %lu size=%lu align=%lu vstart=0x%lx vend=0x%lx failed=%d", __entry->addr, __entry->size, __entry->align, __entry->vstart, __entry->vend, __entry->failed) ); /** * purge_vmap_area_lazy - called when vmap areas were lazily freed * @start: purging start address * @end: purging end address * @npurged: numbed of purged vmap areas * * This event is used for a debug purpose. It gives some * indication about start:end range and how many objects * are released. */ TRACE_EVENT(purge_vmap_area_lazy, TP_PROTO(unsigned long start, unsigned long end, unsigned int npurged), TP_ARGS(start, end, npurged), TP_STRUCT__entry( __field(unsigned long, start) __field(unsigned long, end) __field(unsigned int, npurged) ), TP_fast_assign( __entry->start = start; __entry->end = end; __entry->npurged = npurged; ), TP_printk("start=0x%lx end=0x%lx num_purged=%u", __entry->start, __entry->end, __entry->npurged) ); /** * free_vmap_area_noflush - called when a vmap area is freed * @va_start: a start address of VA * @nr_lazy: number of current lazy pages * @nr_lazy_max: number of maximum lazy pages * * This event is used for a debug purpose. It gives some * indication about a VA that is released, number of current * outstanding areas and a maximum allowed threshold before * dropping all of them. */ TRACE_EVENT(free_vmap_area_noflush, TP_PROTO(unsigned long va_start, unsigned long nr_lazy, unsigned long nr_lazy_max), TP_ARGS(va_start, nr_lazy, nr_lazy_max), TP_STRUCT__entry( __field(unsigned long, va_start) __field(unsigned long, nr_lazy) __field(unsigned long, nr_lazy_max) ), TP_fast_assign( __entry->va_start = va_start; __entry->nr_lazy = nr_lazy; __entry->nr_lazy_max = nr_lazy_max; ), TP_printk("va_start=0x%lx nr_lazy=%lu nr_lazy_max=%lu", __entry->va_start, __entry->nr_lazy, __entry->nr_lazy_max) ); #endif /* _TRACE_VMALLOC_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 2 3 3 1 2 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 3 2 1 1 21 3 2 1 3 1 1 3 2 8 185 185 | 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 | // SPDX-License-Identifier: GPL-2.0 #ifndef NO_BCACHEFS_CHARDEV #include "bcachefs.h" #include "bcachefs_ioctl.h" #include "buckets.h" #include "chardev.h" #include "disk_accounting.h" #include "fsck.h" #include "journal.h" #include "move.h" #include "recovery_passes.h" #include "replicas.h" #include "sb-counters.h" #include "super-io.h" #include "thread_with_file.h" #include <linux/cdev.h> #include <linux/device.h> #include <linux/fs.h> #include <linux/ioctl.h> #include <linux/major.h> #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/uaccess.h> /* returns with ref on ca->ref */ static struct bch_dev *bch2_device_lookup(struct bch_fs *c, u64 dev, unsigned flags) { struct bch_dev *ca; if (flags & BCH_BY_INDEX) { if (dev >= c->sb.nr_devices) return ERR_PTR(-EINVAL); ca = bch2_dev_tryget_noerror(c, dev); if (!ca) return ERR_PTR(-EINVAL); } else { char *path; path = strndup_user((const char __user *) (unsigned long) dev, PATH_MAX); if (IS_ERR(path)) return ERR_CAST(path); ca = bch2_dev_lookup(c, path); kfree(path); } return ca; } #if 0 static long bch2_ioctl_assemble(struct bch_ioctl_assemble __user *user_arg) { struct bch_ioctl_assemble arg; struct bch_fs *c; u64 *user_devs = NULL; char **devs = NULL; unsigned i; int ret = -EFAULT; if (copy_from_user(&arg, user_arg, sizeof(arg))) return -EFAULT; if (arg.flags || arg.pad) return -EINVAL; user_devs = kmalloc_array(arg.nr_devs, sizeof(u64), GFP_KERNEL); if (!user_devs) return -ENOMEM; devs = kcalloc(arg.nr_devs, sizeof(char *), GFP_KERNEL); if (copy_from_user(user_devs, user_arg->devs, sizeof(u64) * arg.nr_devs)) goto err; for (i = 0; i < arg.nr_devs; i++) { devs[i] = strndup_user((const char __user *)(unsigned long) user_devs[i], PATH_MAX); ret= PTR_ERR_OR_ZERO(devs[i]); if (ret) goto err; } c = bch2_fs_open(devs, arg.nr_devs, bch2_opts_empty()); ret = PTR_ERR_OR_ZERO(c); if (!ret) closure_put(&c->cl); err: if (devs) for (i = 0; i < arg.nr_devs; i++) kfree(devs[i]); kfree(devs); return ret; } static long bch2_ioctl_incremental(struct bch_ioctl_incremental __user *user_arg) { struct bch_ioctl_incremental arg; const char *err; char *path; if (copy_from_user(&arg, user_arg, sizeof(arg))) return -EFAULT; if (arg.flags || arg.pad) return -EINVAL; path = strndup_user((const char __user *)(unsigned long) arg.dev, PATH_MAX); ret = PTR_ERR_OR_ZERO(path); if (ret) return ret; err = bch2_fs_open_incremental(path); kfree(path); if (err) { pr_err("Could not register bcachefs devices: %s", err); return -EINVAL; } return 0; } #endif static long bch2_global_ioctl(unsigned cmd, void __user *arg) { long ret; switch (cmd) { #if 0 case BCH_IOCTL_ASSEMBLE: return bch2_ioctl_assemble(arg); case BCH_IOCTL_INCREMENTAL: return bch2_ioctl_incremental(arg); #endif case BCH_IOCTL_FSCK_OFFLINE: { ret = bch2_ioctl_fsck_offline(arg); break; } default: ret = -ENOTTY; break; } if (ret < 0) ret = bch2_err_class(ret); return ret; } static long bch2_ioctl_query_uuid(struct bch_fs *c, struct bch_ioctl_query_uuid __user *user_arg) { return copy_to_user_errcode(&user_arg->uuid, &c->sb.user_uuid, sizeof(c->sb.user_uuid)); } #if 0 static long bch2_ioctl_start(struct bch_fs *c, struct bch_ioctl_start arg) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (arg.flags || arg.pad) return -EINVAL; return bch2_fs_start(c); } static long bch2_ioctl_stop(struct bch_fs *c) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; bch2_fs_stop(c); return 0; } #endif static long bch2_ioctl_disk_add(struct bch_fs *c, struct bch_ioctl_disk arg) { char *path; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (arg.flags || arg.pad) return -EINVAL; path = strndup_user((const char __user *)(unsigned long) arg.dev, PATH_MAX); ret = PTR_ERR_OR_ZERO(path); if (ret) return ret; ret = bch2_dev_add(c, path); if (!IS_ERR(path)) kfree(path); return ret; } static long bch2_ioctl_disk_remove(struct bch_fs *c, struct bch_ioctl_disk arg) { struct bch_dev *ca; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if ((arg.flags & ~(BCH_FORCE_IF_DATA_LOST| BCH_FORCE_IF_METADATA_LOST| BCH_FORCE_IF_DEGRADED| BCH_BY_INDEX)) || arg.pad) return -EINVAL; ca = bch2_device_lookup(c, arg.dev, arg.flags); if (IS_ERR(ca)) return PTR_ERR(ca); return bch2_dev_remove(c, ca, arg.flags); } static long bch2_ioctl_disk_online(struct bch_fs *c, struct bch_ioctl_disk arg) { char *path; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (arg.flags || arg.pad) return -EINVAL; path = strndup_user((const char __user *)(unsigned long) arg.dev, PATH_MAX); ret = PTR_ERR_OR_ZERO(path); if (ret) return ret; ret = bch2_dev_online(c, path); kfree(path); return ret; } static long bch2_ioctl_disk_offline(struct bch_fs *c, struct bch_ioctl_disk arg) { struct bch_dev *ca; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if ((arg.flags & ~(BCH_FORCE_IF_DATA_LOST| BCH_FORCE_IF_METADATA_LOST| BCH_FORCE_IF_DEGRADED| BCH_BY_INDEX)) || arg.pad) return -EINVAL; ca = bch2_device_lookup(c, arg.dev, arg.flags); if (IS_ERR(ca)) return PTR_ERR(ca); ret = bch2_dev_offline(c, ca, arg.flags); bch2_dev_put(ca); return ret; } static long bch2_ioctl_disk_set_state(struct bch_fs *c, struct bch_ioctl_disk_set_state arg) { struct bch_dev *ca; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if ((arg.flags & ~(BCH_FORCE_IF_DATA_LOST| BCH_FORCE_IF_METADATA_LOST| BCH_FORCE_IF_DEGRADED| BCH_BY_INDEX)) || arg.pad[0] || arg.pad[1] || arg.pad[2] || arg.new_state >= BCH_MEMBER_STATE_NR) return -EINVAL; ca = bch2_device_lookup(c, arg.dev, arg.flags); if (IS_ERR(ca)) return PTR_ERR(ca); ret = bch2_dev_set_state(c, ca, arg.new_state, arg.flags); if (ret) bch_err(c, "Error setting device state: %s", bch2_err_str(ret)); bch2_dev_put(ca); return ret; } struct bch_data_ctx { struct thread_with_file thr; struct bch_fs *c; struct bch_ioctl_data arg; struct bch_move_stats stats; }; static int bch2_data_thread(void *arg) { struct bch_data_ctx *ctx = container_of(arg, struct bch_data_ctx, thr); ctx->thr.ret = bch2_data_job(ctx->c, &ctx->stats, ctx->arg); if (ctx->thr.ret == -BCH_ERR_device_offline) ctx->stats.ret = BCH_IOCTL_DATA_EVENT_RET_device_offline; else { ctx->stats.ret = BCH_IOCTL_DATA_EVENT_RET_done; ctx->stats.data_type = (int) DATA_PROGRESS_DATA_TYPE_done; } return 0; } static int bch2_data_job_release(struct inode *inode, struct file *file) { struct bch_data_ctx *ctx = container_of(file->private_data, struct bch_data_ctx, thr); bch2_thread_with_file_exit(&ctx->thr); kfree(ctx); return 0; } static ssize_t bch2_data_job_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { struct bch_data_ctx *ctx = container_of(file->private_data, struct bch_data_ctx, thr); struct bch_fs *c = ctx->c; struct bch_ioctl_data_event e = { .type = BCH_DATA_EVENT_PROGRESS, .ret = ctx->stats.ret, .p.data_type = ctx->stats.data_type, .p.btree_id = ctx->stats.pos.btree, .p.pos = ctx->stats.pos.pos, .p.sectors_done = atomic64_read(&ctx->stats.sectors_seen), .p.sectors_error_corrected = atomic64_read(&ctx->stats.sectors_error_corrected), .p.sectors_error_uncorrected = atomic64_read(&ctx->stats.sectors_error_uncorrected), }; if (ctx->arg.op == BCH_DATA_OP_scrub) { struct bch_dev *ca = bch2_dev_tryget(c, ctx->arg.scrub.dev); if (ca) { struct bch_dev_usage u; bch2_dev_usage_read_fast(ca, &u); for (unsigned i = BCH_DATA_btree; i < ARRAY_SIZE(u.d); i++) if (ctx->arg.scrub.data_types & BIT(i)) e.p.sectors_total += u.d[i].sectors; bch2_dev_put(ca); } } else { e.p.sectors_total = bch2_fs_usage_read_short(c).used; } if (len < sizeof(e)) return -EINVAL; return copy_to_user_errcode(buf, &e, sizeof(e)) ?: sizeof(e); } static const struct file_operations bcachefs_data_ops = { .release = bch2_data_job_release, .read = bch2_data_job_read, }; static long bch2_ioctl_data(struct bch_fs *c, struct bch_ioctl_data arg) { struct bch_data_ctx *ctx; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (arg.op >= BCH_DATA_OP_NR || arg.flags) return -EINVAL; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->c = c; ctx->arg = arg; ret = bch2_run_thread_with_file(&ctx->thr, &bcachefs_data_ops, bch2_data_thread); if (ret < 0) kfree(ctx); return ret; } static long bch2_ioctl_fs_usage(struct bch_fs *c, struct bch_ioctl_fs_usage __user *user_arg) { struct bch_ioctl_fs_usage arg = {}; darray_char replicas = {}; u32 replica_entries_bytes; int ret = 0; if (!test_bit(BCH_FS_started, &c->flags)) return -EINVAL; if (get_user(replica_entries_bytes, &user_arg->replica_entries_bytes)) return -EFAULT; ret = bch2_fs_replicas_usage_read(c, &replicas) ?: (replica_entries_bytes < replicas.nr ? -ERANGE : 0) ?: copy_to_user_errcode(&user_arg->replicas, replicas.data, replicas.nr); if (ret) goto err; struct bch_fs_usage_short u = bch2_fs_usage_read_short(c); arg.capacity = c->capacity; arg.used = u.used; arg.online_reserved = percpu_u64_get(c->online_reserved); arg.replica_entries_bytes = replicas.nr; for (unsigned i = 0; i < BCH_REPLICAS_MAX; i++) { struct disk_accounting_pos k = { .type = BCH_DISK_ACCOUNTING_persistent_reserved, .persistent_reserved.nr_replicas = i, }; bch2_accounting_mem_read(c, disk_accounting_pos_to_bpos(&k), &arg.persistent_reserved[i], 1); } ret = copy_to_user_errcode(user_arg, &arg, sizeof(arg)); err: darray_exit(&replicas); return ret; } static long bch2_ioctl_query_accounting(struct bch_fs *c, struct bch_ioctl_query_accounting __user *user_arg) { struct bch_ioctl_query_accounting arg; darray_char accounting = {}; int ret = 0; if (!test_bit(BCH_FS_started, &c->flags)) return -EINVAL; ret = copy_from_user_errcode(&arg, user_arg, sizeof(arg)) ?: bch2_fs_accounting_read(c, &accounting, arg.accounting_types_mask) ?: (arg.accounting_u64s * sizeof(u64) < accounting.nr ? -ERANGE : 0) ?: copy_to_user_errcode(&user_arg->accounting, accounting.data, accounting.nr); if (ret) goto err; arg.capacity = c->capacity; arg.used = bch2_fs_usage_read_short(c).used; arg.online_reserved = percpu_u64_get(c->online_reserved); arg.accounting_u64s = accounting.nr / sizeof(u64); ret = copy_to_user_errcode(user_arg, &arg, sizeof(arg)); err: darray_exit(&accounting); return ret; } /* obsolete, didn't allow for new data types: */ static long bch2_ioctl_dev_usage(struct bch_fs *c, struct bch_ioctl_dev_usage __user *user_arg) { struct bch_ioctl_dev_usage arg; struct bch_dev_usage src; struct bch_dev *ca; unsigned i; if (!test_bit(BCH_FS_started, &c->flags)) return -EINVAL; if (copy_from_user(&arg, user_arg, sizeof(arg))) return -EFAULT; if ((arg.flags & ~BCH_BY_INDEX) || arg.pad[0] || arg.pad[1] || arg.pad[2]) return -EINVAL; ca = bch2_device_lookup(c, arg.dev, arg.flags); if (IS_ERR(ca)) return PTR_ERR(ca); src = bch2_dev_usage_read(ca); arg.state = ca->mi.state; arg.bucket_size = ca->mi.bucket_size; arg.nr_buckets = ca->mi.nbuckets - ca->mi.first_bucket; for (i = 0; i < ARRAY_SIZE(arg.d); i++) { arg.d[i].buckets = src.d[i].buckets; arg.d[i].sectors = src.d[i].sectors; arg.d[i].fragmented = src.d[i].fragmented; } bch2_dev_put(ca); return copy_to_user_errcode(user_arg, &arg, sizeof(arg)); } static long bch2_ioctl_dev_usage_v2(struct bch_fs *c, struct bch_ioctl_dev_usage_v2 __user *user_arg) { struct bch_ioctl_dev_usage_v2 arg; struct bch_dev_usage src; struct bch_dev *ca; int ret = 0; if (!test_bit(BCH_FS_started, &c->flags)) return -EINVAL; if (copy_from_user(&arg, user_arg, sizeof(arg))) return -EFAULT; if ((arg.flags & ~BCH_BY_INDEX) || arg.pad[0] || arg.pad[1] || arg.pad[2]) return -EINVAL; ca = bch2_device_lookup(c, arg.dev, arg.flags); if (IS_ERR(ca)) return PTR_ERR(ca); src = bch2_dev_usage_read(ca); arg.state = ca->mi.state; arg.bucket_size = ca->mi.bucket_size; arg.nr_data_types = min(arg.nr_data_types, BCH_DATA_NR); arg.nr_buckets = ca->mi.nbuckets - ca->mi.first_bucket; ret = copy_to_user_errcode(user_arg, &arg, sizeof(arg)); if (ret) goto err; for (unsigned i = 0; i < arg.nr_data_types; i++) { struct bch_ioctl_dev_usage_type t = { .buckets = src.d[i].buckets, .sectors = src.d[i].sectors, .fragmented = src.d[i].fragmented, }; ret = copy_to_user_errcode(&user_arg->d[i], &t, sizeof(t)); if (ret) goto err; } err: bch2_dev_put(ca); return ret; } static long bch2_ioctl_read_super(struct bch_fs *c, struct bch_ioctl_read_super arg) { struct bch_dev *ca = NULL; struct bch_sb *sb; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if ((arg.flags & ~(BCH_BY_INDEX|BCH_READ_DEV)) || arg.pad) return -EINVAL; mutex_lock(&c->sb_lock); if (arg.flags & BCH_READ_DEV) { ca = bch2_device_lookup(c, arg.dev, arg.flags); ret = PTR_ERR_OR_ZERO(ca); if (ret) goto err_unlock; sb = ca->disk_sb.sb; } else { sb = c->disk_sb.sb; } if (vstruct_bytes(sb) > arg.size) { ret = -ERANGE; goto err; } ret = copy_to_user_errcode((void __user *)(unsigned long)arg.sb, sb, vstruct_bytes(sb)); err: bch2_dev_put(ca); err_unlock: mutex_unlock(&c->sb_lock); return ret; } static long bch2_ioctl_disk_get_idx(struct bch_fs *c, struct bch_ioctl_disk_get_idx arg) { dev_t dev = huge_decode_dev(arg.dev); if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!dev) return -EINVAL; for_each_online_member(c, ca) if (ca->dev == dev) { percpu_ref_put(&ca->io_ref); return ca->dev_idx; } return -BCH_ERR_ENOENT_dev_idx_not_found; } static long bch2_ioctl_disk_resize(struct bch_fs *c, struct bch_ioctl_disk_resize arg) { struct bch_dev *ca; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if ((arg.flags & ~BCH_BY_INDEX) || arg.pad) return -EINVAL; ca = bch2_device_lookup(c, arg.dev, arg.flags); if (IS_ERR(ca)) return PTR_ERR(ca); ret = bch2_dev_resize(c, ca, arg.nbuckets); bch2_dev_put(ca); return ret; } static long bch2_ioctl_disk_resize_journal(struct bch_fs *c, struct bch_ioctl_disk_resize_journal arg) { struct bch_dev *ca; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if ((arg.flags & ~BCH_BY_INDEX) || arg.pad) return -EINVAL; if (arg.nbuckets > U32_MAX) return -EINVAL; ca = bch2_device_lookup(c, arg.dev, arg.flags); if (IS_ERR(ca)) return PTR_ERR(ca); ret = bch2_set_nr_journal_buckets(c, ca, arg.nbuckets); bch2_dev_put(ca); return ret; } #define BCH_IOCTL(_name, _argtype) \ do { \ _argtype i; \ \ if (copy_from_user(&i, arg, sizeof(i))) \ return -EFAULT; \ ret = bch2_ioctl_##_name(c, i); \ goto out; \ } while (0) long bch2_fs_ioctl(struct bch_fs *c, unsigned cmd, void __user *arg) { long ret; switch (cmd) { case BCH_IOCTL_QUERY_UUID: return bch2_ioctl_query_uuid(c, arg); case BCH_IOCTL_FS_USAGE: return bch2_ioctl_fs_usage(c, arg); case BCH_IOCTL_DEV_USAGE: return bch2_ioctl_dev_usage(c, arg); case BCH_IOCTL_DEV_USAGE_V2: return bch2_ioctl_dev_usage_v2(c, arg); #if 0 case BCH_IOCTL_START: BCH_IOCTL(start, struct bch_ioctl_start); case BCH_IOCTL_STOP: return bch2_ioctl_stop(c); #endif case BCH_IOCTL_READ_SUPER: BCH_IOCTL(read_super, struct bch_ioctl_read_super); case BCH_IOCTL_DISK_GET_IDX: BCH_IOCTL(disk_get_idx, struct bch_ioctl_disk_get_idx); } if (!test_bit(BCH_FS_started, &c->flags)) return -EINVAL; switch (cmd) { case BCH_IOCTL_DISK_ADD: BCH_IOCTL(disk_add, struct bch_ioctl_disk); case BCH_IOCTL_DISK_REMOVE: BCH_IOCTL(disk_remove, struct bch_ioctl_disk); case BCH_IOCTL_DISK_ONLINE: BCH_IOCTL(disk_online, struct bch_ioctl_disk); case BCH_IOCTL_DISK_OFFLINE: BCH_IOCTL(disk_offline, struct bch_ioctl_disk); case BCH_IOCTL_DISK_SET_STATE: BCH_IOCTL(disk_set_state, struct bch_ioctl_disk_set_state); case BCH_IOCTL_DATA: BCH_IOCTL(data, struct bch_ioctl_data); case BCH_IOCTL_DISK_RESIZE: BCH_IOCTL(disk_resize, struct bch_ioctl_disk_resize); case BCH_IOCTL_DISK_RESIZE_JOURNAL: BCH_IOCTL(disk_resize_journal, struct bch_ioctl_disk_resize_journal); case BCH_IOCTL_FSCK_ONLINE: BCH_IOCTL(fsck_online, struct bch_ioctl_fsck_online); case BCH_IOCTL_QUERY_ACCOUNTING: return bch2_ioctl_query_accounting(c, arg); case BCH_IOCTL_QUERY_COUNTERS: return bch2_ioctl_query_counters(c, arg); default: return -ENOTTY; } out: if (ret < 0) ret = bch2_err_class(ret); return ret; } static DEFINE_IDR(bch_chardev_minor); static long bch2_chardev_ioctl(struct file *filp, unsigned cmd, unsigned long v) { unsigned minor = iminor(file_inode(filp)); struct bch_fs *c = minor < U8_MAX ? idr_find(&bch_chardev_minor, minor) : NULL; void __user *arg = (void __user *) v; return c ? bch2_fs_ioctl(c, cmd, arg) : bch2_global_ioctl(cmd, arg); } static const struct file_operations bch_chardev_fops = { .owner = THIS_MODULE, .unlocked_ioctl = bch2_chardev_ioctl, .open = nonseekable_open, }; static int bch_chardev_major; static const struct class bch_chardev_class = { .name = "bcachefs", }; static struct device *bch_chardev; void bch2_fs_chardev_exit(struct bch_fs *c) { if (!IS_ERR_OR_NULL(c->chardev)) device_unregister(c->chardev); if (c->minor >= 0) idr_remove(&bch_chardev_minor, c->minor); } int bch2_fs_chardev_init(struct bch_fs *c) { c->minor = idr_alloc(&bch_chardev_minor, c, 0, 0, GFP_KERNEL); if (c->minor < 0) return c->minor; c->chardev = device_create(&bch_chardev_class, NULL, MKDEV(bch_chardev_major, c->minor), c, "bcachefs%u-ctl", c->minor); if (IS_ERR(c->chardev)) return PTR_ERR(c->chardev); return 0; } void bch2_chardev_exit(void) { device_destroy(&bch_chardev_class, MKDEV(bch_chardev_major, U8_MAX)); class_unregister(&bch_chardev_class); if (bch_chardev_major > 0) unregister_chrdev(bch_chardev_major, "bcachefs"); } int __init bch2_chardev_init(void) { int ret; bch_chardev_major = register_chrdev(0, "bcachefs-ctl", &bch_chardev_fops); if (bch_chardev_major < 0) return bch_chardev_major; ret = class_register(&bch_chardev_class); if (ret) goto major_out; bch_chardev = device_create(&bch_chardev_class, NULL, MKDEV(bch_chardev_major, U8_MAX), NULL, "bcachefs-ctl"); if (IS_ERR(bch_chardev)) { ret = PTR_ERR(bch_chardev); goto class_out; } return 0; class_out: class_unregister(&bch_chardev_class); major_out: unregister_chrdev(bch_chardev_major, "bcachefs-ctl"); return ret; } #endif /* NO_BCACHEFS_CHARDEV */ |
| 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 | // SPDX-License-Identifier: GPL-2.0 /* * Framework for userspace DMA-BUF allocations * * Copyright (C) 2011 Google, Inc. * Copyright (C) 2019 Linaro Ltd. */ #include <linux/cdev.h> #include <linux/device.h> #include <linux/dma-buf.h> #include <linux/dma-heap.h> #include <linux/err.h> #include <linux/list.h> #include <linux/nospec.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/xarray.h> #include <uapi/linux/dma-heap.h> #define DEVNAME "dma_heap" #define NUM_HEAP_MINORS 128 /** * struct dma_heap - represents a dmabuf heap in the system * @name: used for debugging/device-node name * @ops: ops struct for this heap * @priv: private data for this heap * @heap_devt: heap device node * @list: list head connecting to list of heaps * @heap_cdev: heap char device * * Represents a heap of memory from which buffers can be made. */ struct dma_heap { const char *name; const struct dma_heap_ops *ops; void *priv; dev_t heap_devt; struct list_head list; struct cdev heap_cdev; }; static LIST_HEAD(heap_list); static DEFINE_MUTEX(heap_list_lock); static dev_t dma_heap_devt; static struct class *dma_heap_class; static DEFINE_XARRAY_ALLOC(dma_heap_minors); static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, u32 fd_flags, u64 heap_flags) { struct dma_buf *dmabuf; int fd; /* * Allocations from all heaps have to begin * and end on page boundaries. */ len = PAGE_ALIGN(len); if (!len) return -EINVAL; dmabuf = heap->ops->allocate(heap, len, fd_flags, heap_flags); if (IS_ERR(dmabuf)) return PTR_ERR(dmabuf); fd = dma_buf_fd(dmabuf, fd_flags); if (fd < 0) { dma_buf_put(dmabuf); /* just return, as put will call release and that will free */ } return fd; } static int dma_heap_open(struct inode *inode, struct file *file) { struct dma_heap *heap; heap = xa_load(&dma_heap_minors, iminor(inode)); if (!heap) { pr_err("dma_heap: minor %d unknown.\n", iminor(inode)); return -ENODEV; } /* instance data as context */ file->private_data = heap; nonseekable_open(inode, file); return 0; } static long dma_heap_ioctl_allocate(struct file *file, void *data) { struct dma_heap_allocation_data *heap_allocation = data; struct dma_heap *heap = file->private_data; int fd; if (heap_allocation->fd) return -EINVAL; if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS) return -EINVAL; if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS) return -EINVAL; fd = dma_heap_buffer_alloc(heap, heap_allocation->len, heap_allocation->fd_flags, heap_allocation->heap_flags); if (fd < 0) return fd; heap_allocation->fd = fd; return 0; } static unsigned int dma_heap_ioctl_cmds[] = { DMA_HEAP_IOCTL_ALLOC, }; static long dma_heap_ioctl(struct file *file, unsigned int ucmd, unsigned long arg) { char stack_kdata[128]; char *kdata = stack_kdata; unsigned int kcmd; unsigned int in_size, out_size, drv_size, ksize; int nr = _IOC_NR(ucmd); int ret = 0; if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds)) return -EINVAL; nr = array_index_nospec(nr, ARRAY_SIZE(dma_heap_ioctl_cmds)); /* Get the kernel ioctl cmd that matches */ kcmd = dma_heap_ioctl_cmds[nr]; /* Figure out the delta between user cmd size and kernel cmd size */ drv_size = _IOC_SIZE(kcmd); out_size = _IOC_SIZE(ucmd); in_size = out_size; if ((ucmd & kcmd & IOC_IN) == 0) in_size = 0; if ((ucmd & kcmd & IOC_OUT) == 0) out_size = 0; ksize = max(max(in_size, out_size), drv_size); /* If necessary, allocate buffer for ioctl argument */ if (ksize > sizeof(stack_kdata)) { kdata = kmalloc(ksize, GFP_KERNEL); if (!kdata) return -ENOMEM; } if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) { ret = -EFAULT; goto err; } /* zero out any difference between the kernel/user structure size */ if (ksize > in_size) memset(kdata + in_size, 0, ksize - in_size); switch (kcmd) { case DMA_HEAP_IOCTL_ALLOC: ret = dma_heap_ioctl_allocate(file, kdata); break; default: ret = -ENOTTY; goto err; } if (copy_to_user((void __user *)arg, kdata, out_size) != 0) ret = -EFAULT; err: if (kdata != stack_kdata) kfree(kdata); return ret; } static const struct file_operations dma_heap_fops = { .owner = THIS_MODULE, .open = dma_heap_open, .unlocked_ioctl = dma_heap_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = dma_heap_ioctl, #endif }; /** * dma_heap_get_drvdata - get per-heap driver data * @heap: DMA-Heap to retrieve private data for * * Returns: * The per-heap data for the heap. */ void *dma_heap_get_drvdata(struct dma_heap *heap) { return heap->priv; } /** * dma_heap_get_name - get heap name * @heap: DMA-Heap to retrieve the name of * * Returns: * The char* for the heap name. */ const char *dma_heap_get_name(struct dma_heap *heap) { return heap->name; } /** * dma_heap_add - adds a heap to dmabuf heaps * @exp_info: information needed to register this heap */ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) { struct dma_heap *heap, *h, *err_ret; struct device *dev_ret; unsigned int minor; int ret; if (!exp_info->name || !strcmp(exp_info->name, "")) { pr_err("dma_heap: Cannot add heap without a name\n"); return ERR_PTR(-EINVAL); } if (!exp_info->ops || !exp_info->ops->allocate) { pr_err("dma_heap: Cannot add heap with invalid ops struct\n"); return ERR_PTR(-EINVAL); } heap = kzalloc(sizeof(*heap), GFP_KERNEL); if (!heap) return ERR_PTR(-ENOMEM); heap->name = exp_info->name; heap->ops = exp_info->ops; heap->priv = exp_info->priv; /* Find unused minor number */ ret = xa_alloc(&dma_heap_minors, &minor, heap, XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL); if (ret < 0) { pr_err("dma_heap: Unable to get minor number for heap\n"); err_ret = ERR_PTR(ret); goto err0; } /* Create device */ heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), minor); cdev_init(&heap->heap_cdev, &dma_heap_fops); ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1); if (ret < 0) { pr_err("dma_heap: Unable to add char device\n"); err_ret = ERR_PTR(ret); goto err1; } dev_ret = device_create(dma_heap_class, NULL, heap->heap_devt, NULL, heap->name); if (IS_ERR(dev_ret)) { pr_err("dma_heap: Unable to create device\n"); err_ret = ERR_CAST(dev_ret); goto err2; } mutex_lock(&heap_list_lock); /* check the name is unique */ list_for_each_entry(h, &heap_list, list) { if (!strcmp(h->name, exp_info->name)) { mutex_unlock(&heap_list_lock); pr_err("dma_heap: Already registered heap named %s\n", exp_info->name); err_ret = ERR_PTR(-EINVAL); goto err3; } } /* Add heap to the list */ list_add(&heap->list, &heap_list); mutex_unlock(&heap_list_lock); return heap; err3: device_destroy(dma_heap_class, heap->heap_devt); err2: cdev_del(&heap->heap_cdev); err1: xa_erase(&dma_heap_minors, minor); err0: kfree(heap); return err_ret; } static char *dma_heap_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "dma_heap/%s", dev_name(dev)); } static int dma_heap_init(void) { int ret; ret = alloc_chrdev_region(&dma_heap_devt, 0, NUM_HEAP_MINORS, DEVNAME); if (ret) return ret; dma_heap_class = class_create(DEVNAME); if (IS_ERR(dma_heap_class)) { unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS); return PTR_ERR(dma_heap_class); } dma_heap_class->devnode = dma_heap_devnode; return 0; } subsys_initcall(dma_heap_init); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/etherdevice.h> #include <linux/if_macvlan.h> #include <linux/if_tap.h> #include <linux/if_vlan.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched/signal.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <linux/virtio_net.h> #include <linux/skb_array.h> struct macvtap_dev { struct macvlan_dev vlan; struct tap_dev tap; }; /* * Variables for dealing with macvtaps device numbers. */ static dev_t macvtap_major; static const void *macvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); return dev_net(dev); } static struct class macvtap_class = { .name = "macvtap", .ns_type = &net_ns_type_operations, .namespace = macvtap_net_namespace, }; static struct cdev macvtap_cdev; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static void macvtap_count_tx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_dropped); } static void macvtap_count_rx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; macvlan_count_rx(vlan, 0, 0, 0); } static void macvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; vlan->set_features = features; netdev_update_features(vlan->dev); } static int macvtap_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct macvtap_dev *vlantap = netdev_priv(dev); int err; INIT_LIST_HEAD(&vlantap->tap.queue_list); /* Since macvlan supports all offloads by default, make * tap support all offloads also. */ vlantap->tap.tap_features = TUN_OFFLOADS; /* Register callbacks for rx/tx drops accounting and updating * net_device features */ vlantap->tap.count_tx_dropped = macvtap_count_tx_dropped; vlantap->tap.count_rx_dropped = macvtap_count_rx_dropped; vlantap->tap.update_features = macvtap_update_features; err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); if (err) return err; /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ err = macvlan_common_newlink(dev, params, extack); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return 0; } static void macvtap_dellink(struct net_device *dev, struct list_head *head) { struct macvtap_dev *vlantap = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlantap->tap); macvlan_dellink(dev, head); } static void macvtap_setup(struct net_device *dev) { macvlan_common_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; } static struct net *macvtap_link_net(const struct net_device *dev) { return dev_net(macvlan_dev_real_dev(dev)); } static struct rtnl_link_ops macvtap_link_ops __read_mostly = { .kind = "macvtap", .setup = macvtap_setup, .newlink = macvtap_newlink, .dellink = macvtap_dellink, .get_link_net = macvtap_link_net, .priv_size = sizeof(struct macvtap_dev), }; static int macvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &macvtap_link_ops) return NOTIFY_DONE; snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); vlantap = netdev_priv(dev); switch (event) { case NETDEV_REGISTER: /* Create the device node here after the network device has * been registered but before register_netdevice has * finished running. */ err = tap_get_minor(macvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); classdev = device_create(&macvtap_class, &dev->dev, devt, dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(macvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); } err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, tap_name); if (err) return notifier_from_errno(err); break; case NETDEV_UNREGISTER: /* vlan->minor == 0 if NETDEV_REGISTER above failed */ if (vlantap->tap.minor == 0) break; sysfs_remove_link(&dev->dev.kobj, tap_name); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); device_destroy(&macvtap_class, devt); tap_free_minor(macvtap_major, &vlantap->tap); break; case NETDEV_CHANGE_TX_QUEUE_LEN: if (tap_queue_resize(&vlantap->tap)) return NOTIFY_BAD; break; } return NOTIFY_DONE; } static struct notifier_block macvtap_notifier_block __read_mostly = { .notifier_call = macvtap_device_event, }; static int __init macvtap_init(void) { int err; err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap", THIS_MODULE); if (err) goto out1; err = class_register(&macvtap_class); if (err) goto out2; err = register_netdevice_notifier(&macvtap_notifier_block); if (err) goto out3; err = macvlan_link_register(&macvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&macvtap_notifier_block); out3: class_unregister(&macvtap_class); out2: tap_destroy_cdev(macvtap_major, &macvtap_cdev); out1: return err; } module_init(macvtap_init); static void __exit macvtap_exit(void) { rtnl_link_unregister(&macvtap_link_ops); unregister_netdevice_notifier(&macvtap_notifier_block); class_unregister(&macvtap_class); tap_destroy_cdev(macvtap_major, &macvtap_cdev); } module_exit(macvtap_exit); MODULE_ALIAS_RTNL_LINK("macvtap"); MODULE_DESCRIPTION("MAC-VLAN based tap driver"); MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>"); MODULE_LICENSE("GPL"); |
| 49 393 77 391 393 14 392 393 393 393 10 30 30 31 31 31 31 31 31 31 31 31 393 393 31 386 31 393 393 31 31 392 393 388 31 30 74 45 393 392 392 392 392 393 79 17 74 74 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Scatterlist Cryptographic API. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2002 David S. Miller (davem@redhat.com) * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au> * * Portions derived from Cryptoapi, by Alexander Kjeldaas <astor@fast.no> * and Nettle, by Niels Möller. */ #include <linux/err.h> #include <linux/errno.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/module.h> #include <linux/param.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/completion.h> #include "internal.h" LIST_HEAD(crypto_alg_list); EXPORT_SYMBOL_GPL(crypto_alg_list); DECLARE_RWSEM(crypto_alg_sem); EXPORT_SYMBOL_GPL(crypto_alg_sem); BLOCKING_NOTIFIER_HEAD(crypto_chain); EXPORT_SYMBOL_GPL(crypto_chain); #if IS_BUILTIN(CONFIG_CRYPTO_ALGAPI) && \ !IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) DEFINE_STATIC_KEY_FALSE(__crypto_boot_test_finished); #endif static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg); static struct crypto_alg *crypto_alg_lookup(const char *name, u32 type, u32 mask); struct crypto_alg *crypto_mod_get(struct crypto_alg *alg) { return try_module_get(alg->cra_module) ? crypto_alg_get(alg) : NULL; } EXPORT_SYMBOL_GPL(crypto_mod_get); void crypto_mod_put(struct crypto_alg *alg) { struct module *module = alg->cra_module; crypto_alg_put(alg); module_put(module); } EXPORT_SYMBOL_GPL(crypto_mod_put); static struct crypto_alg *__crypto_alg_lookup(const char *name, u32 type, u32 mask) { struct crypto_alg *q, *alg = NULL; int best = -2; list_for_each_entry(q, &crypto_alg_list, cra_list) { int exact, fuzzy; if (crypto_is_moribund(q)) continue; if ((q->cra_flags ^ type) & mask) continue; exact = !strcmp(q->cra_driver_name, name); fuzzy = !strcmp(q->cra_name, name); if (!exact && !(fuzzy && q->cra_priority > best)) continue; if (unlikely(!crypto_mod_get(q))) continue; best = q->cra_priority; if (alg) crypto_mod_put(alg); alg = q; if (exact) break; } return alg; } static void crypto_larval_destroy(struct crypto_alg *alg) { struct crypto_larval *larval = (void *)alg; BUG_ON(!crypto_is_larval(alg)); if (!IS_ERR_OR_NULL(larval->adult)) crypto_mod_put(larval->adult); kfree(larval); } struct crypto_larval *crypto_larval_alloc(const char *name, u32 type, u32 mask) { struct crypto_larval *larval; larval = kzalloc(sizeof(*larval), GFP_KERNEL); if (!larval) return ERR_PTR(-ENOMEM); type &= ~CRYPTO_ALG_TYPE_MASK | (mask ?: CRYPTO_ALG_TYPE_MASK); larval->mask = mask; larval->alg.cra_flags = CRYPTO_ALG_LARVAL | type; larval->alg.cra_priority = -1; larval->alg.cra_destroy = crypto_larval_destroy; strscpy(larval->alg.cra_name, name, CRYPTO_MAX_ALG_NAME); init_completion(&larval->completion); return larval; } EXPORT_SYMBOL_GPL(crypto_larval_alloc); static struct crypto_alg *crypto_larval_add(const char *name, u32 type, u32 mask) { struct crypto_alg *alg; struct crypto_larval *larval; larval = crypto_larval_alloc(name, type, mask); if (IS_ERR(larval)) return ERR_CAST(larval); refcount_set(&larval->alg.cra_refcnt, 2); down_write(&crypto_alg_sem); alg = __crypto_alg_lookup(name, type, mask); if (!alg) { alg = &larval->alg; list_add(&alg->cra_list, &crypto_alg_list); } up_write(&crypto_alg_sem); if (alg != &larval->alg) { kfree(larval); if (crypto_is_larval(alg)) alg = crypto_larval_wait(alg); } return alg; } static void crypto_larval_kill(struct crypto_larval *larval) { bool unlinked; down_write(&crypto_alg_sem); unlinked = list_empty(&larval->alg.cra_list); if (!unlinked) list_del_init(&larval->alg.cra_list); up_write(&crypto_alg_sem); if (unlinked) return; complete_all(&larval->completion); crypto_alg_put(&larval->alg); } void crypto_schedule_test(struct crypto_larval *larval) { int err; err = crypto_probing_notify(CRYPTO_MSG_ALG_REGISTER, larval->adult); WARN_ON_ONCE(err != NOTIFY_STOP); } EXPORT_SYMBOL_GPL(crypto_schedule_test); static void crypto_start_test(struct crypto_larval *larval) { if (!crypto_is_test_larval(larval)) return; if (larval->test_started) return; down_write(&crypto_alg_sem); if (larval->test_started) { up_write(&crypto_alg_sem); return; } larval->test_started = true; up_write(&crypto_alg_sem); crypto_schedule_test(larval); } static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg) { struct crypto_larval *larval; long time_left; again: larval = container_of(alg, struct crypto_larval, alg); if (!crypto_boot_test_finished()) crypto_start_test(larval); time_left = wait_for_completion_killable_timeout( &larval->completion, 60 * HZ); alg = larval->adult; if (time_left < 0) alg = ERR_PTR(-EINTR); else if (!time_left) { if (crypto_is_test_larval(larval)) crypto_larval_kill(larval); alg = ERR_PTR(-ETIMEDOUT); } else if (!alg) { u32 type; u32 mask; alg = &larval->alg; type = alg->cra_flags & ~(CRYPTO_ALG_LARVAL | CRYPTO_ALG_DEAD); mask = larval->mask; alg = crypto_alg_lookup(alg->cra_name, type, mask) ?: ERR_PTR(-EAGAIN); } else if (IS_ERR(alg)) ; else if (crypto_is_test_larval(larval) && !(alg->cra_flags & CRYPTO_ALG_TESTED)) alg = ERR_PTR(-EAGAIN); else if (alg->cra_flags & CRYPTO_ALG_FIPS_INTERNAL) alg = ERR_PTR(-EAGAIN); else if (!crypto_mod_get(alg)) alg = ERR_PTR(-EAGAIN); crypto_mod_put(&larval->alg); if (!IS_ERR(alg) && crypto_is_larval(alg)) goto again; return alg; } static struct crypto_alg *crypto_alg_lookup(const char *name, u32 type, u32 mask) { const u32 fips = CRYPTO_ALG_FIPS_INTERNAL; struct crypto_alg *alg; u32 test = 0; if (!((type | mask) & CRYPTO_ALG_TESTED)) test |= CRYPTO_ALG_TESTED; down_read(&crypto_alg_sem); alg = __crypto_alg_lookup(name, (type | test) & ~fips, (mask | test) & ~fips); if (alg) { if (((type | mask) ^ fips) & fips) mask |= fips; mask &= fips; if (!crypto_is_larval(alg) && ((type ^ alg->cra_flags) & mask)) { /* Algorithm is disallowed in FIPS mode. */ crypto_mod_put(alg); alg = ERR_PTR(-ENOENT); } } else if (test) { alg = __crypto_alg_lookup(name, type, mask); if (alg && !crypto_is_larval(alg)) { /* Test failed */ crypto_mod_put(alg); alg = ERR_PTR(-ELIBBAD); } } up_read(&crypto_alg_sem); return alg; } static struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask) { struct crypto_alg *alg; if (!name) return ERR_PTR(-ENOENT); type &= ~(CRYPTO_ALG_LARVAL | CRYPTO_ALG_DEAD); mask &= ~(CRYPTO_ALG_LARVAL | CRYPTO_ALG_DEAD); alg = crypto_alg_lookup(name, type, mask); if (!alg && !(mask & CRYPTO_NOLOAD)) { request_module("crypto-%s", name); if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask & CRYPTO_ALG_NEED_FALLBACK)) request_module("crypto-%s-all", name); alg = crypto_alg_lookup(name, type, mask); } if (!IS_ERR_OR_NULL(alg) && crypto_is_larval(alg)) alg = crypto_larval_wait(alg); else if (alg) ; else if (!(mask & CRYPTO_ALG_TESTED)) alg = crypto_larval_add(name, type, mask); else alg = ERR_PTR(-ENOENT); return alg; } int crypto_probing_notify(unsigned long val, void *v) { int ok; ok = blocking_notifier_call_chain(&crypto_chain, val, v); if (ok == NOTIFY_DONE) { request_module("cryptomgr"); ok = blocking_notifier_call_chain(&crypto_chain, val, v); } return ok; } EXPORT_SYMBOL_GPL(crypto_probing_notify); struct crypto_alg *crypto_alg_mod_lookup(const char *name, u32 type, u32 mask) { struct crypto_alg *alg; struct crypto_alg *larval; int ok; /* * If the internal flag is set for a cipher, require a caller to * invoke the cipher with the internal flag to use that cipher. * Also, if a caller wants to allocate a cipher that may or may * not be an internal cipher, use type | CRYPTO_ALG_INTERNAL and * !(mask & CRYPTO_ALG_INTERNAL). */ if (!((type | mask) & CRYPTO_ALG_INTERNAL)) mask |= CRYPTO_ALG_INTERNAL; larval = crypto_larval_lookup(name, type, mask); if (IS_ERR(larval) || !crypto_is_larval(larval)) return larval; ok = crypto_probing_notify(CRYPTO_MSG_ALG_REQUEST, larval); if (ok == NOTIFY_STOP) alg = crypto_larval_wait(larval); else { crypto_mod_put(larval); alg = ERR_PTR(-ENOENT); } crypto_larval_kill(container_of(larval, struct crypto_larval, alg)); return alg; } EXPORT_SYMBOL_GPL(crypto_alg_mod_lookup); static void crypto_exit_ops(struct crypto_tfm *tfm) { const struct crypto_type *type = tfm->__crt_alg->cra_type; if (type && tfm->exit) tfm->exit(tfm); } static unsigned int crypto_ctxsize(struct crypto_alg *alg, u32 type, u32 mask) { const struct crypto_type *type_obj = alg->cra_type; unsigned int len; len = alg->cra_alignmask & ~(crypto_tfm_ctx_alignment() - 1); if (type_obj) return len + type_obj->ctxsize(alg, type, mask); switch (alg->cra_flags & CRYPTO_ALG_TYPE_MASK) { default: BUG(); case CRYPTO_ALG_TYPE_CIPHER: len += crypto_cipher_ctxsize(alg); break; case CRYPTO_ALG_TYPE_COMPRESS: len += crypto_compress_ctxsize(alg); break; } return len; } void crypto_shoot_alg(struct crypto_alg *alg) { down_write(&crypto_alg_sem); alg->cra_flags |= CRYPTO_ALG_DYING; up_write(&crypto_alg_sem); } EXPORT_SYMBOL_GPL(crypto_shoot_alg); struct crypto_tfm *__crypto_alloc_tfmgfp(struct crypto_alg *alg, u32 type, u32 mask, gfp_t gfp) { struct crypto_tfm *tfm; unsigned int tfm_size; int err = -ENOMEM; tfm_size = sizeof(*tfm) + crypto_ctxsize(alg, type, mask); tfm = kzalloc(tfm_size, gfp); if (tfm == NULL) goto out_err; tfm->__crt_alg = alg; refcount_set(&tfm->refcnt, 1); if (!tfm->exit && alg->cra_init && (err = alg->cra_init(tfm))) goto cra_init_failed; goto out; cra_init_failed: crypto_exit_ops(tfm); if (err == -EAGAIN) crypto_shoot_alg(alg); kfree(tfm); out_err: tfm = ERR_PTR(err); out: return tfm; } EXPORT_SYMBOL_GPL(__crypto_alloc_tfmgfp); struct crypto_tfm *__crypto_alloc_tfm(struct crypto_alg *alg, u32 type, u32 mask) { return __crypto_alloc_tfmgfp(alg, type, mask, GFP_KERNEL); } EXPORT_SYMBOL_GPL(__crypto_alloc_tfm); /* * crypto_alloc_base - Locate algorithm and allocate transform * @alg_name: Name of algorithm * @type: Type of algorithm * @mask: Mask for type comparison * * This function should not be used by new algorithm types. * Please use crypto_alloc_tfm instead. * * crypto_alloc_base() will first attempt to locate an already loaded * algorithm. If that fails and the kernel supports dynamically loadable * modules, it will then attempt to load a module of the same name or * alias. If that fails it will send a query to any loaded crypto manager * to construct an algorithm on the fly. A refcount is grabbed on the * algorithm which is then associated with the new transform. * * The returned transform is of a non-determinate type. Most people * should use one of the more specific allocation functions such as * crypto_alloc_skcipher(). * * In case of error the return value is an error pointer. */ struct crypto_tfm *crypto_alloc_base(const char *alg_name, u32 type, u32 mask) { struct crypto_tfm *tfm; int err; for (;;) { struct crypto_alg *alg; alg = crypto_alg_mod_lookup(alg_name, type, mask); if (IS_ERR(alg)) { err = PTR_ERR(alg); goto err; } tfm = __crypto_alloc_tfm(alg, type, mask); if (!IS_ERR(tfm)) return tfm; crypto_mod_put(alg); err = PTR_ERR(tfm); err: if (err != -EAGAIN) break; if (fatal_signal_pending(current)) { err = -EINTR; break; } } return ERR_PTR(err); } EXPORT_SYMBOL_GPL(crypto_alloc_base); static void *crypto_alloc_tfmmem(struct crypto_alg *alg, const struct crypto_type *frontend, int node, gfp_t gfp) { struct crypto_tfm *tfm; unsigned int tfmsize; unsigned int total; char *mem; tfmsize = frontend->tfmsize; total = tfmsize + sizeof(*tfm) + frontend->extsize(alg); mem = kzalloc_node(total, gfp, node); if (mem == NULL) return ERR_PTR(-ENOMEM); tfm = (struct crypto_tfm *)(mem + tfmsize); tfm->__crt_alg = alg; tfm->node = node; refcount_set(&tfm->refcnt, 1); return mem; } void *crypto_create_tfm_node(struct crypto_alg *alg, const struct crypto_type *frontend, int node) { struct crypto_tfm *tfm; char *mem; int err; mem = crypto_alloc_tfmmem(alg, frontend, node, GFP_KERNEL); if (IS_ERR(mem)) goto out; tfm = (struct crypto_tfm *)(mem + frontend->tfmsize); err = frontend->init_tfm(tfm); if (err) goto out_free_tfm; if (!tfm->exit && alg->cra_init && (err = alg->cra_init(tfm))) goto cra_init_failed; goto out; cra_init_failed: crypto_exit_ops(tfm); out_free_tfm: if (err == -EAGAIN) crypto_shoot_alg(alg); kfree(mem); mem = ERR_PTR(err); out: return mem; } EXPORT_SYMBOL_GPL(crypto_create_tfm_node); void *crypto_clone_tfm(const struct crypto_type *frontend, struct crypto_tfm *otfm) { struct crypto_alg *alg = otfm->__crt_alg; struct crypto_tfm *tfm; char *mem; mem = ERR_PTR(-ESTALE); if (unlikely(!crypto_mod_get(alg))) goto out; mem = crypto_alloc_tfmmem(alg, frontend, otfm->node, GFP_ATOMIC); if (IS_ERR(mem)) { crypto_mod_put(alg); goto out; } tfm = (struct crypto_tfm *)(mem + frontend->tfmsize); tfm->crt_flags = otfm->crt_flags; tfm->exit = otfm->exit; out: return mem; } EXPORT_SYMBOL_GPL(crypto_clone_tfm); struct crypto_alg *crypto_find_alg(const char *alg_name, const struct crypto_type *frontend, u32 type, u32 mask) { if (frontend) { type &= frontend->maskclear; mask &= frontend->maskclear; type |= frontend->type; mask |= frontend->maskset; } return crypto_alg_mod_lookup(alg_name, type, mask); } EXPORT_SYMBOL_GPL(crypto_find_alg); /* * crypto_alloc_tfm_node - Locate algorithm and allocate transform * @alg_name: Name of algorithm * @frontend: Frontend algorithm type * @type: Type of algorithm * @mask: Mask for type comparison * @node: NUMA node in which users desire to put requests, if node is * NUMA_NO_NODE, it means users have no special requirement. * * crypto_alloc_tfm() will first attempt to locate an already loaded * algorithm. If that fails and the kernel supports dynamically loadable * modules, it will then attempt to load a module of the same name or * alias. If that fails it will send a query to any loaded crypto manager * to construct an algorithm on the fly. A refcount is grabbed on the * algorithm which is then associated with the new transform. * * The returned transform is of a non-determinate type. Most people * should use one of the more specific allocation functions such as * crypto_alloc_skcipher(). * * In case of error the return value is an error pointer. */ void *crypto_alloc_tfm_node(const char *alg_name, const struct crypto_type *frontend, u32 type, u32 mask, int node) { void *tfm; int err; for (;;) { struct crypto_alg *alg; alg = crypto_find_alg(alg_name, frontend, type, mask); if (IS_ERR(alg)) { err = PTR_ERR(alg); goto err; } tfm = crypto_create_tfm_node(alg, frontend, node); if (!IS_ERR(tfm)) return tfm; crypto_mod_put(alg); err = PTR_ERR(tfm); err: if (err != -EAGAIN) break; if (fatal_signal_pending(current)) { err = -EINTR; break; } } return ERR_PTR(err); } EXPORT_SYMBOL_GPL(crypto_alloc_tfm_node); /* * crypto_destroy_tfm - Free crypto transform * @mem: Start of tfm slab * @tfm: Transform to free * * This function frees up the transform and any associated resources, * then drops the refcount on the associated algorithm. */ void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm) { struct crypto_alg *alg; if (IS_ERR_OR_NULL(mem)) return; if (!refcount_dec_and_test(&tfm->refcnt)) return; alg = tfm->__crt_alg; if (!tfm->exit && alg->cra_exit) alg->cra_exit(tfm); crypto_exit_ops(tfm); crypto_mod_put(alg); kfree_sensitive(mem); } EXPORT_SYMBOL_GPL(crypto_destroy_tfm); int crypto_has_alg(const char *name, u32 type, u32 mask) { int ret = 0; struct crypto_alg *alg = crypto_alg_mod_lookup(name, type, mask); if (!IS_ERR(alg)) { crypto_mod_put(alg); ret = 1; } return ret; } EXPORT_SYMBOL_GPL(crypto_has_alg); void crypto_req_done(void *data, int err) { struct crypto_wait *wait = data; if (err == -EINPROGRESS) return; wait->err = err; complete(&wait->completion); } EXPORT_SYMBOL_GPL(crypto_req_done); MODULE_DESCRIPTION("Cryptographic core API"); MODULE_LICENSE("GPL"); |
| 4 4 1 1 4 4 3 4 4 4 4 4 4 4 4 4 4 1 1 1 1 1 1 1 1 1 1 1 1 11 4 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 10 10 10 9 10 9 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 2 2 2 2 2 4 2 1 1 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 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Timers abstract layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/delay.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/mutex.h> #include <linux/device.h> #include <linux/module.h> #include <linux/string.h> #include <linux/sched/signal.h> #include <linux/anon_inodes.h> #include <linux/idr.h> #include <sound/core.h> #include <sound/timer.h> #include <sound/control.h> #include <sound/info.h> #include <sound/minors.h> #include <sound/initval.h> #include <linux/kmod.h> /* internal flags */ #define SNDRV_TIMER_IFLG_PAUSED 0x00010000 #define SNDRV_TIMER_IFLG_DEAD 0x00020000 #if IS_ENABLED(CONFIG_SND_HRTIMER) #define DEFAULT_TIMER_LIMIT 4 #else #define DEFAULT_TIMER_LIMIT 1 #endif static int timer_limit = DEFAULT_TIMER_LIMIT; static int timer_tstamp_monotonic = 1; MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>, Takashi Iwai <tiwai@suse.de>"); MODULE_DESCRIPTION("ALSA timer interface"); MODULE_LICENSE("GPL"); module_param(timer_limit, int, 0444); MODULE_PARM_DESC(timer_limit, "Maximum global timers in system."); module_param(timer_tstamp_monotonic, int, 0444); MODULE_PARM_DESC(timer_tstamp_monotonic, "Use posix monotonic clock source for timestamps (default)."); MODULE_ALIAS_CHARDEV(CONFIG_SND_MAJOR, SNDRV_MINOR_TIMER); MODULE_ALIAS("devname:snd/timer"); enum timer_tread_format { TREAD_FORMAT_NONE = 0, TREAD_FORMAT_TIME64, TREAD_FORMAT_TIME32, }; struct snd_timer_tread32 { int event; s32 tstamp_sec; s32 tstamp_nsec; unsigned int val; }; struct snd_timer_tread64 { int event; u8 pad1[4]; s64 tstamp_sec; s64 tstamp_nsec; unsigned int val; u8 pad2[4]; }; struct snd_timer_user { struct snd_timer_instance *timeri; int tread; /* enhanced read with timestamps and events */ unsigned long ticks; unsigned long overrun; int qhead; int qtail; int qused; int queue_size; bool disconnected; struct snd_timer_read *queue; struct snd_timer_tread64 *tqueue; spinlock_t qlock; unsigned long last_resolution; unsigned int filter; struct timespec64 tstamp; /* trigger tstamp */ wait_queue_head_t qchange_sleep; struct snd_fasync *fasync; struct mutex ioctl_lock; }; struct snd_timer_status32 { s32 tstamp_sec; /* Timestamp - last update */ s32 tstamp_nsec; unsigned int resolution; /* current period resolution in ns */ unsigned int lost; /* counter of master tick lost */ unsigned int overrun; /* count of read queue overruns */ unsigned int queue; /* used queue size */ unsigned char reserved[64]; /* reserved */ }; #define SNDRV_TIMER_IOCTL_STATUS32 _IOR('T', 0x14, struct snd_timer_status32) struct snd_timer_status64 { s64 tstamp_sec; /* Timestamp - last update */ s64 tstamp_nsec; unsigned int resolution; /* current period resolution in ns */ unsigned int lost; /* counter of master tick lost */ unsigned int overrun; /* count of read queue overruns */ unsigned int queue; /* used queue size */ unsigned char reserved[64]; /* reserved */ }; #ifdef CONFIG_SND_UTIMER #define SNDRV_UTIMERS_MAX_COUNT 128 /* Internal data structure for keeping the state of the userspace-driven timer */ struct snd_utimer { char *name; struct snd_timer *timer; unsigned int id; }; #endif #define SNDRV_TIMER_IOCTL_STATUS64 _IOR('T', 0x14, struct snd_timer_status64) /* list of timers */ static LIST_HEAD(snd_timer_list); /* list of slave instances */ static LIST_HEAD(snd_timer_slave_list); /* lock for slave active lists */ static DEFINE_SPINLOCK(slave_active_lock); #define MAX_SLAVE_INSTANCES 1000 static int num_slaves; static DEFINE_MUTEX(register_mutex); static int snd_timer_free(struct snd_timer *timer); static int snd_timer_dev_free(struct snd_device *device); static int snd_timer_dev_register(struct snd_device *device); static int snd_timer_dev_disconnect(struct snd_device *device); static void snd_timer_reschedule(struct snd_timer * timer, unsigned long ticks_left); /* * create a timer instance with the given owner string. */ struct snd_timer_instance *snd_timer_instance_new(const char *owner) { struct snd_timer_instance *timeri; timeri = kzalloc(sizeof(*timeri), GFP_KERNEL); if (timeri == NULL) return NULL; timeri->owner = kstrdup(owner, GFP_KERNEL); if (! timeri->owner) { kfree(timeri); return NULL; } INIT_LIST_HEAD(&timeri->open_list); INIT_LIST_HEAD(&timeri->active_list); INIT_LIST_HEAD(&timeri->ack_list); INIT_LIST_HEAD(&timeri->slave_list_head); INIT_LIST_HEAD(&timeri->slave_active_head); return timeri; } EXPORT_SYMBOL(snd_timer_instance_new); void snd_timer_instance_free(struct snd_timer_instance *timeri) { if (timeri) { if (timeri->private_free) timeri->private_free(timeri); kfree(timeri->owner); kfree(timeri); } } EXPORT_SYMBOL(snd_timer_instance_free); /* * find a timer instance from the given timer id */ static struct snd_timer *snd_timer_find(struct snd_timer_id *tid) { struct snd_timer *timer; list_for_each_entry(timer, &snd_timer_list, device_list) { if (timer->tmr_class != tid->dev_class) continue; if ((timer->tmr_class == SNDRV_TIMER_CLASS_CARD || timer->tmr_class == SNDRV_TIMER_CLASS_PCM) && (timer->card == NULL || timer->card->number != tid->card)) continue; if (timer->tmr_device != tid->device) continue; if (timer->tmr_subdevice != tid->subdevice) continue; return timer; } return NULL; } #ifdef CONFIG_MODULES static void snd_timer_request(struct snd_timer_id *tid) { switch (tid->dev_class) { case SNDRV_TIMER_CLASS_GLOBAL: if (tid->device < timer_limit) request_module("snd-timer-%i", tid->device); break; case SNDRV_TIMER_CLASS_CARD: case SNDRV_TIMER_CLASS_PCM: if (tid->card < snd_ecards_limit) request_module("snd-card-%i", tid->card); break; default: break; } } #endif /* move the slave if it belongs to the master; return 1 if match */ static int check_matching_master_slave(struct snd_timer_instance *master, struct snd_timer_instance *slave) { if (slave->slave_class != master->slave_class || slave->slave_id != master->slave_id) return 0; if (master->timer->num_instances >= master->timer->max_instances) return -EBUSY; list_move_tail(&slave->open_list, &master->slave_list_head); master->timer->num_instances++; guard(spinlock_irq)(&slave_active_lock); guard(spinlock)(&master->timer->lock); slave->master = master; slave->timer = master->timer; if (slave->flags & SNDRV_TIMER_IFLG_RUNNING) list_add_tail(&slave->active_list, &master->slave_active_head); return 1; } /* * look for a master instance matching with the slave id of the given slave. * when found, relink the open_link of the slave. * * call this with register_mutex down. */ static int snd_timer_check_slave(struct snd_timer_instance *slave) { struct snd_timer *timer; struct snd_timer_instance *master; int err = 0; /* FIXME: it's really dumb to look up all entries.. */ list_for_each_entry(timer, &snd_timer_list, device_list) { list_for_each_entry(master, &timer->open_list_head, open_list) { err = check_matching_master_slave(master, slave); if (err != 0) /* match found or error */ goto out; } } out: return err < 0 ? err : 0; } /* * look for slave instances matching with the slave id of the given master. * when found, relink the open_link of slaves. * * call this with register_mutex down. */ static int snd_timer_check_master(struct snd_timer_instance *master) { struct snd_timer_instance *slave, *tmp; int err = 0; /* check all pending slaves */ list_for_each_entry_safe(slave, tmp, &snd_timer_slave_list, open_list) { err = check_matching_master_slave(master, slave); if (err < 0) break; } return err < 0 ? err : 0; } static void snd_timer_close_locked(struct snd_timer_instance *timeri, struct device **card_devp_to_put); /* * open a timer instance * when opening a master, the slave id must be here given. */ int snd_timer_open(struct snd_timer_instance *timeri, struct snd_timer_id *tid, unsigned int slave_id) { struct snd_timer *timer; struct device *card_dev_to_put = NULL; int err; mutex_lock(®ister_mutex); if (tid->dev_class == SNDRV_TIMER_CLASS_SLAVE) { /* open a slave instance */ if (tid->dev_sclass <= SNDRV_TIMER_SCLASS_NONE || tid->dev_sclass > SNDRV_TIMER_SCLASS_OSS_SEQUENCER) { pr_debug("ALSA: timer: invalid slave class %i\n", tid->dev_sclass); err = -EINVAL; goto unlock; } if (num_slaves >= MAX_SLAVE_INSTANCES) { err = -EBUSY; goto unlock; } timeri->slave_class = tid->dev_sclass; timeri->slave_id = tid->device; timeri->flags |= SNDRV_TIMER_IFLG_SLAVE; list_add_tail(&timeri->open_list, &snd_timer_slave_list); num_slaves++; err = snd_timer_check_slave(timeri); goto list_added; } /* open a master instance */ timer = snd_timer_find(tid); #ifdef CONFIG_MODULES if (!timer) { mutex_unlock(®ister_mutex); snd_timer_request(tid); mutex_lock(®ister_mutex); timer = snd_timer_find(tid); } #endif if (!timer) { err = -ENODEV; goto unlock; } if (!list_empty(&timer->open_list_head)) { struct snd_timer_instance *t = list_entry(timer->open_list_head.next, struct snd_timer_instance, open_list); if (t->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) { err = -EBUSY; goto unlock; } } if (timer->num_instances >= timer->max_instances) { err = -EBUSY; goto unlock; } if (!try_module_get(timer->module)) { err = -EBUSY; goto unlock; } /* take a card refcount for safe disconnection */ if (timer->card) { get_device(&timer->card->card_dev); card_dev_to_put = &timer->card->card_dev; } if (list_empty(&timer->open_list_head) && timer->hw.open) { err = timer->hw.open(timer); if (err) { module_put(timer->module); goto unlock; } } timeri->timer = timer; timeri->slave_class = tid->dev_sclass; timeri->slave_id = slave_id; list_add_tail(&timeri->open_list, &timer->open_list_head); timer->num_instances++; err = snd_timer_check_master(timeri); list_added: if (err < 0) snd_timer_close_locked(timeri, &card_dev_to_put); unlock: mutex_unlock(®ister_mutex); /* put_device() is called after unlock for avoiding deadlock */ if (err < 0 && card_dev_to_put) put_device(card_dev_to_put); return err; } EXPORT_SYMBOL(snd_timer_open); /* remove slave links, called from snd_timer_close_locked() below */ static void remove_slave_links(struct snd_timer_instance *timeri, struct snd_timer *timer) { struct snd_timer_instance *slave, *tmp; guard(spinlock_irq)(&slave_active_lock); guard(spinlock)(&timer->lock); timeri->timer = NULL; list_for_each_entry_safe(slave, tmp, &timeri->slave_list_head, open_list) { list_move_tail(&slave->open_list, &snd_timer_slave_list); timer->num_instances--; slave->master = NULL; slave->timer = NULL; list_del_init(&slave->ack_list); list_del_init(&slave->active_list); } } /* * close a timer instance * call this with register_mutex down. */ static void snd_timer_close_locked(struct snd_timer_instance *timeri, struct device **card_devp_to_put) { struct snd_timer *timer = timeri->timer; if (timer) { guard(spinlock_irq)(&timer->lock); timeri->flags |= SNDRV_TIMER_IFLG_DEAD; } if (!list_empty(&timeri->open_list)) { list_del_init(&timeri->open_list); if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) num_slaves--; } /* force to stop the timer */ snd_timer_stop(timeri); if (timer) { timer->num_instances--; /* wait, until the active callback is finished */ spin_lock_irq(&timer->lock); while (timeri->flags & SNDRV_TIMER_IFLG_CALLBACK) { spin_unlock_irq(&timer->lock); udelay(10); spin_lock_irq(&timer->lock); } spin_unlock_irq(&timer->lock); remove_slave_links(timeri, timer); /* slave doesn't need to release timer resources below */ if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) timer = NULL; } if (timer) { if (list_empty(&timer->open_list_head) && timer->hw.close) timer->hw.close(timer); /* release a card refcount for safe disconnection */ if (timer->card) *card_devp_to_put = &timer->card->card_dev; module_put(timer->module); } } /* * close a timer instance */ void snd_timer_close(struct snd_timer_instance *timeri) { struct device *card_dev_to_put = NULL; if (snd_BUG_ON(!timeri)) return; scoped_guard(mutex, ®ister_mutex) snd_timer_close_locked(timeri, &card_dev_to_put); /* put_device() is called after unlock for avoiding deadlock */ if (card_dev_to_put) put_device(card_dev_to_put); } EXPORT_SYMBOL(snd_timer_close); static unsigned long snd_timer_hw_resolution(struct snd_timer *timer) { if (timer->hw.c_resolution) return timer->hw.c_resolution(timer); else return timer->hw.resolution; } unsigned long snd_timer_resolution(struct snd_timer_instance *timeri) { struct snd_timer * timer; unsigned long ret = 0; if (timeri == NULL) return 0; timer = timeri->timer; if (timer) { guard(spinlock_irqsave)(&timer->lock); ret = snd_timer_hw_resolution(timer); } return ret; } EXPORT_SYMBOL(snd_timer_resolution); static void snd_timer_notify1(struct snd_timer_instance *ti, int event) { struct snd_timer *timer = ti->timer; unsigned long resolution = 0; struct snd_timer_instance *ts; struct timespec64 tstamp; if (timer_tstamp_monotonic) ktime_get_ts64(&tstamp); else ktime_get_real_ts64(&tstamp); if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_START || event > SNDRV_TIMER_EVENT_PAUSE)) return; if (timer && (event == SNDRV_TIMER_EVENT_START || event == SNDRV_TIMER_EVENT_CONTINUE)) resolution = snd_timer_hw_resolution(timer); if (ti->ccallback) ti->ccallback(ti, event, &tstamp, resolution); if (ti->flags & SNDRV_TIMER_IFLG_SLAVE) return; if (timer == NULL) return; if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) return; event += 10; /* convert to SNDRV_TIMER_EVENT_MXXX */ list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) ts->ccallback(ts, event, &tstamp, resolution); } /* start/continue a master timer */ static int snd_timer_start1(struct snd_timer_instance *timeri, bool start, unsigned long ticks) { struct snd_timer *timer; int result; timer = timeri->timer; if (!timer) return -EINVAL; guard(spinlock_irqsave)(&timer->lock); if (timeri->flags & SNDRV_TIMER_IFLG_DEAD) return -EINVAL; if (timer->card && timer->card->shutdown) return -ENODEV; if (timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START)) return -EBUSY; /* check the actual time for the start tick; * bail out as error if it's way too low (< 100us) */ if (start && !(timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) { if ((u64)snd_timer_hw_resolution(timer) * ticks < 100000) return -EINVAL; } if (start) timeri->ticks = timeri->cticks = ticks; else if (!timeri->cticks) timeri->cticks = 1; timeri->pticks = 0; list_move_tail(&timeri->active_list, &timer->active_list_head); if (timer->running) { if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) goto __start_now; timer->flags |= SNDRV_TIMER_FLG_RESCHED; timeri->flags |= SNDRV_TIMER_IFLG_START; result = 1; /* delayed start */ } else { if (start) timer->sticks = ticks; timer->hw.start(timer); __start_now: timer->running++; timeri->flags |= SNDRV_TIMER_IFLG_RUNNING; result = 0; } snd_timer_notify1(timeri, start ? SNDRV_TIMER_EVENT_START : SNDRV_TIMER_EVENT_CONTINUE); return result; } /* start/continue a slave timer */ static int snd_timer_start_slave(struct snd_timer_instance *timeri, bool start) { guard(spinlock_irqsave)(&slave_active_lock); if (timeri->flags & SNDRV_TIMER_IFLG_DEAD) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_RUNNING) return -EBUSY; timeri->flags |= SNDRV_TIMER_IFLG_RUNNING; if (timeri->master && timeri->timer) { guard(spinlock)(&timeri->timer->lock); list_add_tail(&timeri->active_list, &timeri->master->slave_active_head); snd_timer_notify1(timeri, start ? SNDRV_TIMER_EVENT_START : SNDRV_TIMER_EVENT_CONTINUE); } return 1; /* delayed start */ } /* stop/pause a master timer */ static int snd_timer_stop1(struct snd_timer_instance *timeri, bool stop) { struct snd_timer *timer; timer = timeri->timer; if (!timer) return -EINVAL; guard(spinlock_irqsave)(&timer->lock); list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); if (!(timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START))) return -EBUSY; if (timer->card && timer->card->shutdown) return 0; if (stop) { timeri->cticks = timeri->ticks; timeri->pticks = 0; } if ((timeri->flags & SNDRV_TIMER_IFLG_RUNNING) && !(--timer->running)) { timer->hw.stop(timer); if (timer->flags & SNDRV_TIMER_FLG_RESCHED) { timer->flags &= ~SNDRV_TIMER_FLG_RESCHED; snd_timer_reschedule(timer, 0); if (timer->flags & SNDRV_TIMER_FLG_CHANGE) { timer->flags &= ~SNDRV_TIMER_FLG_CHANGE; timer->hw.start(timer); } } } timeri->flags &= ~(SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START); if (stop) timeri->flags &= ~SNDRV_TIMER_IFLG_PAUSED; else timeri->flags |= SNDRV_TIMER_IFLG_PAUSED; snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP : SNDRV_TIMER_EVENT_PAUSE); return 0; } /* stop/pause a slave timer */ static int snd_timer_stop_slave(struct snd_timer_instance *timeri, bool stop) { bool running; guard(spinlock_irqsave)(&slave_active_lock); running = timeri->flags & SNDRV_TIMER_IFLG_RUNNING; timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; if (timeri->timer) { guard(spinlock)(&timeri->timer->lock); list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); if (running) snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP : SNDRV_TIMER_EVENT_PAUSE); } return running ? 0 : -EBUSY; } /* * start the timer instance */ int snd_timer_start(struct snd_timer_instance *timeri, unsigned int ticks) { if (timeri == NULL || ticks < 1) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_start_slave(timeri, true); else return snd_timer_start1(timeri, true, ticks); } EXPORT_SYMBOL(snd_timer_start); /* * stop the timer instance. * * do not call this from the timer callback! */ int snd_timer_stop(struct snd_timer_instance *timeri) { if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_stop_slave(timeri, true); else return snd_timer_stop1(timeri, true); } EXPORT_SYMBOL(snd_timer_stop); /* * start again.. the tick is kept. */ int snd_timer_continue(struct snd_timer_instance *timeri) { /* timer can continue only after pause */ if (!(timeri->flags & SNDRV_TIMER_IFLG_PAUSED)) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_start_slave(timeri, false); else return snd_timer_start1(timeri, false, 0); } EXPORT_SYMBOL(snd_timer_continue); /* * pause.. remember the ticks left */ int snd_timer_pause(struct snd_timer_instance * timeri) { if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_stop_slave(timeri, false); else return snd_timer_stop1(timeri, false); } EXPORT_SYMBOL(snd_timer_pause); /* * reschedule the timer * * start pending instances and check the scheduling ticks. * when the scheduling ticks is changed set CHANGE flag to reprogram the timer. */ static void snd_timer_reschedule(struct snd_timer * timer, unsigned long ticks_left) { struct snd_timer_instance *ti; unsigned long ticks = ~0UL; list_for_each_entry(ti, &timer->active_list_head, active_list) { if (ti->flags & SNDRV_TIMER_IFLG_START) { ti->flags &= ~SNDRV_TIMER_IFLG_START; ti->flags |= SNDRV_TIMER_IFLG_RUNNING; timer->running++; } if (ti->flags & SNDRV_TIMER_IFLG_RUNNING) { if (ticks > ti->cticks) ticks = ti->cticks; } } if (ticks == ~0UL) { timer->flags &= ~SNDRV_TIMER_FLG_RESCHED; return; } if (ticks > timer->hw.ticks) ticks = timer->hw.ticks; if (ticks_left != ticks) timer->flags |= SNDRV_TIMER_FLG_CHANGE; timer->sticks = ticks; } /* call callbacks in timer ack list */ static void snd_timer_process_callbacks(struct snd_timer *timer, struct list_head *head) { struct snd_timer_instance *ti; unsigned long resolution, ticks; while (!list_empty(head)) { ti = list_first_entry(head, struct snd_timer_instance, ack_list); /* remove from ack_list and make empty */ list_del_init(&ti->ack_list); if (!(ti->flags & SNDRV_TIMER_IFLG_DEAD)) { ticks = ti->pticks; ti->pticks = 0; resolution = ti->resolution; ti->flags |= SNDRV_TIMER_IFLG_CALLBACK; spin_unlock(&timer->lock); if (ti->callback) ti->callback(ti, resolution, ticks); spin_lock(&timer->lock); ti->flags &= ~SNDRV_TIMER_IFLG_CALLBACK; } } } /* clear pending instances from ack list */ static void snd_timer_clear_callbacks(struct snd_timer *timer, struct list_head *head) { guard(spinlock_irqsave)(&timer->lock); while (!list_empty(head)) list_del_init(head->next); } /* * timer work * */ static void snd_timer_work(struct work_struct *work) { struct snd_timer *timer = container_of(work, struct snd_timer, task_work); if (timer->card && timer->card->shutdown) { snd_timer_clear_callbacks(timer, &timer->sack_list_head); return; } guard(spinlock_irqsave)(&timer->lock); snd_timer_process_callbacks(timer, &timer->sack_list_head); } /* * timer interrupt * * ticks_left is usually equal to timer->sticks. * */ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left) { struct snd_timer_instance *ti, *ts, *tmp; unsigned long resolution; struct list_head *ack_list_head; if (timer == NULL) return; if (timer->card && timer->card->shutdown) { snd_timer_clear_callbacks(timer, &timer->ack_list_head); return; } guard(spinlock_irqsave)(&timer->lock); /* remember the current resolution */ resolution = snd_timer_hw_resolution(timer); /* loop for all active instances * Here we cannot use list_for_each_entry because the active_list of a * processed instance is relinked to done_list_head before the callback * is called. */ list_for_each_entry_safe(ti, tmp, &timer->active_list_head, active_list) { if (ti->flags & SNDRV_TIMER_IFLG_DEAD) continue; if (!(ti->flags & SNDRV_TIMER_IFLG_RUNNING)) continue; ti->pticks += ticks_left; ti->resolution = resolution; if (ti->cticks < ticks_left) ti->cticks = 0; else ti->cticks -= ticks_left; if (ti->cticks) /* not expired */ continue; if (ti->flags & SNDRV_TIMER_IFLG_AUTO) { ti->cticks = ti->ticks; } else { ti->flags &= ~SNDRV_TIMER_IFLG_RUNNING; --timer->running; list_del_init(&ti->active_list); } if ((timer->hw.flags & SNDRV_TIMER_HW_WORK) || (ti->flags & SNDRV_TIMER_IFLG_FAST)) ack_list_head = &timer->ack_list_head; else ack_list_head = &timer->sack_list_head; if (list_empty(&ti->ack_list)) list_add_tail(&ti->ack_list, ack_list_head); list_for_each_entry(ts, &ti->slave_active_head, active_list) { ts->pticks = ti->pticks; ts->resolution = resolution; if (list_empty(&ts->ack_list)) list_add_tail(&ts->ack_list, ack_list_head); } } if (timer->flags & SNDRV_TIMER_FLG_RESCHED) snd_timer_reschedule(timer, timer->sticks); if (timer->running) { if (timer->hw.flags & SNDRV_TIMER_HW_STOP) { timer->hw.stop(timer); timer->flags |= SNDRV_TIMER_FLG_CHANGE; } if (!(timer->hw.flags & SNDRV_TIMER_HW_AUTO) || (timer->flags & SNDRV_TIMER_FLG_CHANGE)) { /* restart timer */ timer->flags &= ~SNDRV_TIMER_FLG_CHANGE; timer->hw.start(timer); } } else { timer->hw.stop(timer); } /* now process all fast callbacks */ snd_timer_process_callbacks(timer, &timer->ack_list_head); /* do we have any slow callbacks? */ if (!list_empty(&timer->sack_list_head)) queue_work(system_highpri_wq, &timer->task_work); } EXPORT_SYMBOL(snd_timer_interrupt); /* */ int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid, struct snd_timer **rtimer) { struct snd_timer *timer; int err; static const struct snd_device_ops ops = { .dev_free = snd_timer_dev_free, .dev_register = snd_timer_dev_register, .dev_disconnect = snd_timer_dev_disconnect, }; if (snd_BUG_ON(!tid)) return -EINVAL; if (tid->dev_class == SNDRV_TIMER_CLASS_CARD || tid->dev_class == SNDRV_TIMER_CLASS_PCM) { if (WARN_ON(!card)) return -EINVAL; } if (rtimer) *rtimer = NULL; timer = kzalloc(sizeof(*timer), GFP_KERNEL); if (!timer) return -ENOMEM; timer->tmr_class = tid->dev_class; timer->card = card; timer->tmr_device = tid->device; timer->tmr_subdevice = tid->subdevice; if (id) strscpy(timer->id, id, sizeof(timer->id)); timer->sticks = 1; INIT_LIST_HEAD(&timer->device_list); INIT_LIST_HEAD(&timer->open_list_head); INIT_LIST_HEAD(&timer->active_list_head); INIT_LIST_HEAD(&timer->ack_list_head); INIT_LIST_HEAD(&timer->sack_list_head); spin_lock_init(&timer->lock); INIT_WORK(&timer->task_work, snd_timer_work); timer->max_instances = 1000; /* default limit per timer */ if (card != NULL) { timer->module = card->module; err = snd_device_new(card, SNDRV_DEV_TIMER, timer, &ops); if (err < 0) { snd_timer_free(timer); return err; } } if (rtimer) *rtimer = timer; return 0; } EXPORT_SYMBOL(snd_timer_new); static int snd_timer_free(struct snd_timer *timer) { if (!timer) return 0; guard(mutex)(®ister_mutex); if (! list_empty(&timer->open_list_head)) { struct list_head *p, *n; struct snd_timer_instance *ti; pr_warn("ALSA: timer %p is busy?\n", timer); list_for_each_safe(p, n, &timer->open_list_head) { list_del_init(p); ti = list_entry(p, struct snd_timer_instance, open_list); ti->timer = NULL; } } list_del(&timer->device_list); if (timer->private_free) timer->private_free(timer); kfree(timer); return 0; } static int snd_timer_dev_free(struct snd_device *device) { struct snd_timer *timer = device->device_data; return snd_timer_free(timer); } static int snd_timer_dev_register(struct snd_device *dev) { struct snd_timer *timer = dev->device_data; struct snd_timer *timer1; if (snd_BUG_ON(!timer || !timer->hw.start || !timer->hw.stop)) return -ENXIO; if (!(timer->hw.flags & SNDRV_TIMER_HW_SLAVE) && !timer->hw.resolution && timer->hw.c_resolution == NULL) return -EINVAL; guard(mutex)(®ister_mutex); list_for_each_entry(timer1, &snd_timer_list, device_list) { if (timer1->tmr_class > timer->tmr_class) break; if (timer1->tmr_class < timer->tmr_class) continue; if (timer1->card && timer->card) { if (timer1->card->number > timer->card->number) break; if (timer1->card->number < timer->card->number) continue; } if (timer1->tmr_device > timer->tmr_device) break; if (timer1->tmr_device < timer->tmr_device) continue; if (timer1->tmr_subdevice > timer->tmr_subdevice) break; if (timer1->tmr_subdevice < timer->tmr_subdevice) continue; /* conflicts.. */ return -EBUSY; } list_add_tail(&timer->device_list, &timer1->device_list); return 0; } static int snd_timer_dev_disconnect(struct snd_device *device) { struct snd_timer *timer = device->device_data; struct snd_timer_instance *ti; guard(mutex)(®ister_mutex); list_del_init(&timer->device_list); /* wake up pending sleepers */ list_for_each_entry(ti, &timer->open_list_head, open_list) { if (ti->disconnect) ti->disconnect(ti); } return 0; } void snd_timer_notify(struct snd_timer *timer, int event, struct timespec64 *tstamp) { unsigned long resolution = 0; struct snd_timer_instance *ti, *ts; if (timer->card && timer->card->shutdown) return; if (! (timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) return; if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_MSTART || event > SNDRV_TIMER_EVENT_MRESUME)) return; guard(spinlock_irqsave)(&timer->lock); if (event == SNDRV_TIMER_EVENT_MSTART || event == SNDRV_TIMER_EVENT_MCONTINUE || event == SNDRV_TIMER_EVENT_MRESUME) resolution = snd_timer_hw_resolution(timer); list_for_each_entry(ti, &timer->active_list_head, active_list) { if (ti->ccallback) ti->ccallback(ti, event, tstamp, resolution); list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) ts->ccallback(ts, event, tstamp, resolution); } } EXPORT_SYMBOL(snd_timer_notify); /* * exported functions for global timers */ int snd_timer_global_new(char *id, int device, struct snd_timer **rtimer) { struct snd_timer_id tid; tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL; tid.dev_sclass = SNDRV_TIMER_SCLASS_NONE; tid.card = -1; tid.device = device; tid.subdevice = 0; return snd_timer_new(NULL, id, &tid, rtimer); } EXPORT_SYMBOL(snd_timer_global_new); int snd_timer_global_free(struct snd_timer *timer) { return snd_timer_free(timer); } EXPORT_SYMBOL(snd_timer_global_free); int snd_timer_global_register(struct snd_timer *timer) { struct snd_device dev; memset(&dev, 0, sizeof(dev)); dev.device_data = timer; return snd_timer_dev_register(&dev); } EXPORT_SYMBOL(snd_timer_global_register); /* * System timer */ struct snd_timer_system_private { struct timer_list tlist; struct snd_timer *snd_timer; unsigned long last_expires; unsigned long last_jiffies; unsigned long correction; }; static void snd_timer_s_function(struct timer_list *t) { struct snd_timer_system_private *priv = from_timer(priv, t, tlist); struct snd_timer *timer = priv->snd_timer; unsigned long jiff = jiffies; if (time_after(jiff, priv->last_expires)) priv->correction += (long)jiff - (long)priv->last_expires; snd_timer_interrupt(timer, (long)jiff - (long)priv->last_jiffies); } static int snd_timer_s_start(struct snd_timer * timer) { struct snd_timer_system_private *priv; unsigned long njiff; priv = (struct snd_timer_system_private *) timer->private_data; njiff = (priv->last_jiffies = jiffies); if (priv->correction > timer->sticks - 1) { priv->correction -= timer->sticks - 1; njiff++; } else { njiff += timer->sticks - priv->correction; priv->correction = 0; } priv->last_expires = njiff; mod_timer(&priv->tlist, njiff); return 0; } static int snd_timer_s_stop(struct snd_timer * timer) { struct snd_timer_system_private *priv; unsigned long jiff; priv = (struct snd_timer_system_private *) timer->private_data; del_timer(&priv->tlist); jiff = jiffies; if (time_before(jiff, priv->last_expires)) timer->sticks = priv->last_expires - jiff; else timer->sticks = 1; priv->correction = 0; return 0; } static int snd_timer_s_close(struct snd_timer *timer) { struct snd_timer_system_private *priv; priv = (struct snd_timer_system_private *)timer->private_data; del_timer_sync(&priv->tlist); return 0; } static const struct snd_timer_hardware snd_timer_system = { .flags = SNDRV_TIMER_HW_FIRST | SNDRV_TIMER_HW_WORK, .resolution = NSEC_PER_SEC / HZ, .ticks = 10000000L, .close = snd_timer_s_close, .start = snd_timer_s_start, .stop = snd_timer_s_stop }; static void snd_timer_free_system(struct snd_timer *timer) { kfree(timer->private_data); } static int snd_timer_register_system(void) { struct snd_timer *timer; struct snd_timer_system_private *priv; int err; err = snd_timer_global_new("system", SNDRV_TIMER_GLOBAL_SYSTEM, &timer); if (err < 0) return err; strcpy(timer->name, "system timer"); timer->hw = snd_timer_system; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (priv == NULL) { snd_timer_free(timer); return -ENOMEM; } priv->snd_timer = timer; timer_setup(&priv->tlist, snd_timer_s_function, 0); timer->private_data = priv; timer->private_free = snd_timer_free_system; return snd_timer_global_register(timer); } #ifdef CONFIG_SND_PROC_FS /* * Info interface */ static void snd_timer_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_timer *timer; struct snd_timer_instance *ti; unsigned long resolution; guard(mutex)(®ister_mutex); list_for_each_entry(timer, &snd_timer_list, device_list) { if (timer->card && timer->card->shutdown) continue; switch (timer->tmr_class) { case SNDRV_TIMER_CLASS_GLOBAL: snd_iprintf(buffer, "G%i: ", timer->tmr_device); break; case SNDRV_TIMER_CLASS_CARD: snd_iprintf(buffer, "C%i-%i: ", timer->card->number, timer->tmr_device); break; case SNDRV_TIMER_CLASS_PCM: snd_iprintf(buffer, "P%i-%i-%i: ", timer->card->number, timer->tmr_device, timer->tmr_subdevice); break; default: snd_iprintf(buffer, "?%i-%i-%i-%i: ", timer->tmr_class, timer->card ? timer->card->number : -1, timer->tmr_device, timer->tmr_subdevice); } snd_iprintf(buffer, "%s :", timer->name); scoped_guard(spinlock_irq, &timer->lock) resolution = snd_timer_hw_resolution(timer); if (resolution) snd_iprintf(buffer, " %lu.%03luus (%lu ticks)", resolution / 1000, resolution % 1000, timer->hw.ticks); if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) snd_iprintf(buffer, " SLAVE"); snd_iprintf(buffer, "\n"); list_for_each_entry(ti, &timer->open_list_head, open_list) snd_iprintf(buffer, " Client %s : %s\n", ti->owner ? ti->owner : "unknown", (ti->flags & (SNDRV_TIMER_IFLG_START | SNDRV_TIMER_IFLG_RUNNING)) ? "running" : "stopped"); } } static struct snd_info_entry *snd_timer_proc_entry; static void __init snd_timer_proc_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "timers", NULL); if (entry != NULL) { entry->c.text.read = snd_timer_proc_read; if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); entry = NULL; } } snd_timer_proc_entry = entry; } static void __exit snd_timer_proc_done(void) { snd_info_free_entry(snd_timer_proc_entry); } #else /* !CONFIG_SND_PROC_FS */ #define snd_timer_proc_init() #define snd_timer_proc_done() #endif /* * USER SPACE interface */ static void snd_timer_user_interrupt(struct snd_timer_instance *timeri, unsigned long resolution, unsigned long ticks) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_read *r; int prev; guard(spinlock)(&tu->qlock); if (tu->qused > 0) { prev = tu->qtail == 0 ? tu->queue_size - 1 : tu->qtail - 1; r = &tu->queue[prev]; if (r->resolution == resolution) { r->ticks += ticks; goto __wake; } } if (tu->qused >= tu->queue_size) { tu->overrun++; } else { r = &tu->queue[tu->qtail++]; tu->qtail %= tu->queue_size; r->resolution = resolution; r->ticks = ticks; tu->qused++; } __wake: snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static void snd_timer_user_append_to_tqueue(struct snd_timer_user *tu, struct snd_timer_tread64 *tread) { if (tu->qused >= tu->queue_size) { tu->overrun++; } else { memcpy(&tu->tqueue[tu->qtail++], tread, sizeof(*tread)); tu->qtail %= tu->queue_size; tu->qused++; } } static void snd_timer_user_ccallback(struct snd_timer_instance *timeri, int event, struct timespec64 *tstamp, unsigned long resolution) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_tread64 r1; if (event >= SNDRV_TIMER_EVENT_START && event <= SNDRV_TIMER_EVENT_PAUSE) tu->tstamp = *tstamp; if ((tu->filter & (1 << event)) == 0 || !tu->tread) return; memset(&r1, 0, sizeof(r1)); r1.event = event; r1.tstamp_sec = tstamp->tv_sec; r1.tstamp_nsec = tstamp->tv_nsec; r1.val = resolution; scoped_guard(spinlock_irqsave, &tu->qlock) snd_timer_user_append_to_tqueue(tu, &r1); snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static void snd_timer_user_disconnect(struct snd_timer_instance *timeri) { struct snd_timer_user *tu = timeri->callback_data; tu->disconnected = true; wake_up(&tu->qchange_sleep); } static void snd_timer_user_tinterrupt(struct snd_timer_instance *timeri, unsigned long resolution, unsigned long ticks) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_tread64 *r, r1; struct timespec64 tstamp; int prev, append = 0; memset(&r1, 0, sizeof(r1)); memset(&tstamp, 0, sizeof(tstamp)); scoped_guard(spinlock, &tu->qlock) { if ((tu->filter & ((1 << SNDRV_TIMER_EVENT_RESOLUTION) | (1 << SNDRV_TIMER_EVENT_TICK))) == 0) return; if (tu->last_resolution != resolution || ticks > 0) { if (timer_tstamp_monotonic) ktime_get_ts64(&tstamp); else ktime_get_real_ts64(&tstamp); } if ((tu->filter & (1 << SNDRV_TIMER_EVENT_RESOLUTION)) && tu->last_resolution != resolution) { r1.event = SNDRV_TIMER_EVENT_RESOLUTION; r1.tstamp_sec = tstamp.tv_sec; r1.tstamp_nsec = tstamp.tv_nsec; r1.val = resolution; snd_timer_user_append_to_tqueue(tu, &r1); tu->last_resolution = resolution; append++; } if ((tu->filter & (1 << SNDRV_TIMER_EVENT_TICK)) == 0) break; if (ticks == 0) break; if (tu->qused > 0) { prev = tu->qtail == 0 ? tu->queue_size - 1 : tu->qtail - 1; r = &tu->tqueue[prev]; if (r->event == SNDRV_TIMER_EVENT_TICK) { r->tstamp_sec = tstamp.tv_sec; r->tstamp_nsec = tstamp.tv_nsec; r->val += ticks; append++; break; } } r1.event = SNDRV_TIMER_EVENT_TICK; r1.tstamp_sec = tstamp.tv_sec; r1.tstamp_nsec = tstamp.tv_nsec; r1.val = ticks; snd_timer_user_append_to_tqueue(tu, &r1); append++; } if (append == 0) return; snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static int realloc_user_queue(struct snd_timer_user *tu, int size) { struct snd_timer_read *queue = NULL; struct snd_timer_tread64 *tqueue = NULL; if (tu->tread) { tqueue = kcalloc(size, sizeof(*tqueue), GFP_KERNEL); if (!tqueue) return -ENOMEM; } else { queue = kcalloc(size, sizeof(*queue), GFP_KERNEL); if (!queue) return -ENOMEM; } guard(spinlock_irq)(&tu->qlock); kfree(tu->queue); kfree(tu->tqueue); tu->queue_size = size; tu->queue = queue; tu->tqueue = tqueue; tu->qhead = tu->qtail = tu->qused = 0; return 0; } static int snd_timer_user_open(struct inode *inode, struct file *file) { struct snd_timer_user *tu; int err; err = stream_open(inode, file); if (err < 0) return err; tu = kzalloc(sizeof(*tu), GFP_KERNEL); if (tu == NULL) return -ENOMEM; spin_lock_init(&tu->qlock); init_waitqueue_head(&tu->qchange_sleep); mutex_init(&tu->ioctl_lock); tu->ticks = 1; if (realloc_user_queue(tu, 128) < 0) { kfree(tu); return -ENOMEM; } file->private_data = tu; return 0; } static int snd_timer_user_release(struct inode *inode, struct file *file) { struct snd_timer_user *tu; if (file->private_data) { tu = file->private_data; file->private_data = NULL; scoped_guard(mutex, &tu->ioctl_lock) { if (tu->timeri) { snd_timer_close(tu->timeri); snd_timer_instance_free(tu->timeri); } } snd_fasync_free(tu->fasync); kfree(tu->queue); kfree(tu->tqueue); kfree(tu); } return 0; } static void snd_timer_user_zero_id(struct snd_timer_id *id) { id->dev_class = SNDRV_TIMER_CLASS_NONE; id->dev_sclass = SNDRV_TIMER_SCLASS_NONE; id->card = -1; id->device = -1; id->subdevice = -1; } static void snd_timer_user_copy_id(struct snd_timer_id *id, struct snd_timer *timer) { id->dev_class = timer->tmr_class; id->dev_sclass = SNDRV_TIMER_SCLASS_NONE; id->card = timer->card ? timer->card->number : -1; id->device = timer->tmr_device; id->subdevice = timer->tmr_subdevice; } static void get_next_device(struct snd_timer_id *id) { struct snd_timer *timer; struct list_head *p; if (id->dev_class < 0) { /* first item */ if (list_empty(&snd_timer_list)) snd_timer_user_zero_id(id); else { timer = list_entry(snd_timer_list.next, struct snd_timer, device_list); snd_timer_user_copy_id(id, timer); } } else { switch (id->dev_class) { case SNDRV_TIMER_CLASS_GLOBAL: id->device = id->device < 0 ? 0 : id->device + 1; list_for_each(p, &snd_timer_list) { timer = list_entry(p, struct snd_timer, device_list); if (timer->tmr_class > SNDRV_TIMER_CLASS_GLOBAL) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_device >= id->device) { snd_timer_user_copy_id(id, timer); break; } } if (p == &snd_timer_list) snd_timer_user_zero_id(id); break; case SNDRV_TIMER_CLASS_CARD: case SNDRV_TIMER_CLASS_PCM: if (id->card < 0) { id->card = 0; } else { if (id->device < 0) { id->device = 0; } else { if (id->subdevice < 0) id->subdevice = 0; else if (id->subdevice < INT_MAX) id->subdevice++; } } list_for_each(p, &snd_timer_list) { timer = list_entry(p, struct snd_timer, device_list); if (timer->tmr_class > id->dev_class) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_class < id->dev_class) continue; if (timer->card->number > id->card) { snd_timer_user_copy_id(id, timer); break; } if (timer->card->number < id->card) continue; if (timer->tmr_device > id->device) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_device < id->device) continue; if (timer->tmr_subdevice > id->subdevice) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_subdevice < id->subdevice) continue; snd_timer_user_copy_id(id, timer); break; } if (p == &snd_timer_list) snd_timer_user_zero_id(id); break; default: snd_timer_user_zero_id(id); } } } static int snd_timer_user_next_device(struct snd_timer_id __user *_tid) { struct snd_timer_id id; if (copy_from_user(&id, _tid, sizeof(id))) return -EFAULT; scoped_guard(mutex, ®ister_mutex) get_next_device(&id); if (copy_to_user(_tid, &id, sizeof(*_tid))) return -EFAULT; return 0; } static int snd_timer_user_ginfo(struct file *file, struct snd_timer_ginfo __user *_ginfo) { struct snd_timer_ginfo *ginfo __free(kfree) = NULL; struct snd_timer_id tid; struct snd_timer *t; struct list_head *p; ginfo = memdup_user(_ginfo, sizeof(*ginfo)); if (IS_ERR(ginfo)) return PTR_ERR(ginfo); tid = ginfo->tid; memset(ginfo, 0, sizeof(*ginfo)); ginfo->tid = tid; scoped_guard(mutex, ®ister_mutex) { t = snd_timer_find(&tid); if (!t) return -ENODEV; ginfo->card = t->card ? t->card->number : -1; if (t->hw.flags & SNDRV_TIMER_HW_SLAVE) ginfo->flags |= SNDRV_TIMER_FLG_SLAVE; strscpy(ginfo->id, t->id, sizeof(ginfo->id)); strscpy(ginfo->name, t->name, sizeof(ginfo->name)); scoped_guard(spinlock_irq, &t->lock) ginfo->resolution = snd_timer_hw_resolution(t); if (t->hw.resolution_min > 0) { ginfo->resolution_min = t->hw.resolution_min; ginfo->resolution_max = t->hw.resolution_max; } list_for_each(p, &t->open_list_head) { ginfo->clients++; } } if (copy_to_user(_ginfo, ginfo, sizeof(*ginfo))) return -EFAULT; return 0; } static int timer_set_gparams(struct snd_timer_gparams *gparams) { struct snd_timer *t; guard(mutex)(®ister_mutex); t = snd_timer_find(&gparams->tid); if (!t) return -ENODEV; if (!list_empty(&t->open_list_head)) return -EBUSY; if (!t->hw.set_period) return -ENOSYS; return t->hw.set_period(t, gparams->period_num, gparams->period_den); } static int snd_timer_user_gparams(struct file *file, struct snd_timer_gparams __user *_gparams) { struct snd_timer_gparams gparams; if (copy_from_user(&gparams, _gparams, sizeof(gparams))) return -EFAULT; return timer_set_gparams(&gparams); } static int snd_timer_user_gstatus(struct file *file, struct snd_timer_gstatus __user *_gstatus) { struct snd_timer_gstatus gstatus; struct snd_timer_id tid; struct snd_timer *t; if (copy_from_user(&gstatus, _gstatus, sizeof(gstatus))) return -EFAULT; tid = gstatus.tid; memset(&gstatus, 0, sizeof(gstatus)); gstatus.tid = tid; scoped_guard(mutex, ®ister_mutex) { t = snd_timer_find(&tid); if (t != NULL) { guard(spinlock_irq)(&t->lock); gstatus.resolution = snd_timer_hw_resolution(t); if (t->hw.precise_resolution) { t->hw.precise_resolution(t, &gstatus.resolution_num, &gstatus.resolution_den); } else { gstatus.resolution_num = gstatus.resolution; gstatus.resolution_den = 1000000000uL; } } else { return -ENODEV; } } if (copy_to_user(_gstatus, &gstatus, sizeof(gstatus))) return -EFAULT; return 0; } static int snd_timer_user_tselect(struct file *file, struct snd_timer_select __user *_tselect) { struct snd_timer_user *tu; struct snd_timer_select tselect; char str[32]; int err = 0; tu = file->private_data; if (tu->timeri) { snd_timer_close(tu->timeri); snd_timer_instance_free(tu->timeri); tu->timeri = NULL; } if (copy_from_user(&tselect, _tselect, sizeof(tselect))) { err = -EFAULT; goto __err; } sprintf(str, "application %i", current->pid); if (tselect.id.dev_class != SNDRV_TIMER_CLASS_SLAVE) tselect.id.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION; tu->timeri = snd_timer_instance_new(str); if (!tu->timeri) { err = -ENOMEM; goto __err; } tu->timeri->flags |= SNDRV_TIMER_IFLG_FAST; tu->timeri->callback = tu->tread ? snd_timer_user_tinterrupt : snd_timer_user_interrupt; tu->timeri->ccallback = snd_timer_user_ccallback; tu->timeri->callback_data = (void *)tu; tu->timeri->disconnect = snd_timer_user_disconnect; err = snd_timer_open(tu->timeri, &tselect.id, current->pid); if (err < 0) { snd_timer_instance_free(tu->timeri); tu->timeri = NULL; } __err: return err; } static int snd_timer_user_info(struct file *file, struct snd_timer_info __user *_info) { struct snd_timer_user *tu; struct snd_timer_info *info __free(kfree) = NULL; struct snd_timer *t; tu = file->private_data; if (!tu->timeri) return -EBADFD; t = tu->timeri->timer; if (!t) return -EBADFD; info = kzalloc(sizeof(*info), GFP_KERNEL); if (! info) return -ENOMEM; info->card = t->card ? t->card->number : -1; if (t->hw.flags & SNDRV_TIMER_HW_SLAVE) info->flags |= SNDRV_TIMER_FLG_SLAVE; strscpy(info->id, t->id, sizeof(info->id)); strscpy(info->name, t->name, sizeof(info->name)); scoped_guard(spinlock_irq, &t->lock) info->resolution = snd_timer_hw_resolution(t); if (copy_to_user(_info, info, sizeof(*_info))) return -EFAULT; return 0; } static int snd_timer_user_params(struct file *file, struct snd_timer_params __user *_params) { struct snd_timer_user *tu; struct snd_timer_params params; struct snd_timer *t; int err; tu = file->private_data; if (!tu->timeri) return -EBADFD; t = tu->timeri->timer; if (!t) return -EBADFD; if (copy_from_user(¶ms, _params, sizeof(params))) return -EFAULT; if (!(t->hw.flags & SNDRV_TIMER_HW_SLAVE)) { u64 resolution; if (params.ticks < 1) { err = -EINVAL; goto _end; } /* Don't allow resolution less than 1ms */ resolution = snd_timer_resolution(tu->timeri); resolution *= params.ticks; if (resolution < 1000000) { err = -EINVAL; goto _end; } } if (params.queue_size > 0 && (params.queue_size < 32 || params.queue_size > 1024)) { err = -EINVAL; goto _end; } if (params.filter & ~((1<<SNDRV_TIMER_EVENT_RESOLUTION)| (1<<SNDRV_TIMER_EVENT_TICK)| (1<<SNDRV_TIMER_EVENT_START)| (1<<SNDRV_TIMER_EVENT_STOP)| (1<<SNDRV_TIMER_EVENT_CONTINUE)| (1<<SNDRV_TIMER_EVENT_PAUSE)| (1<<SNDRV_TIMER_EVENT_SUSPEND)| (1<<SNDRV_TIMER_EVENT_RESUME)| (1<<SNDRV_TIMER_EVENT_MSTART)| (1<<SNDRV_TIMER_EVENT_MSTOP)| (1<<SNDRV_TIMER_EVENT_MCONTINUE)| (1<<SNDRV_TIMER_EVENT_MPAUSE)| (1<<SNDRV_TIMER_EVENT_MSUSPEND)| (1<<SNDRV_TIMER_EVENT_MRESUME))) { err = -EINVAL; goto _end; } snd_timer_stop(tu->timeri); scoped_guard(spinlock_irq, &t->lock) { tu->timeri->flags &= ~(SNDRV_TIMER_IFLG_AUTO| SNDRV_TIMER_IFLG_EXCLUSIVE| SNDRV_TIMER_IFLG_EARLY_EVENT); if (params.flags & SNDRV_TIMER_PSFLG_AUTO) tu->timeri->flags |= SNDRV_TIMER_IFLG_AUTO; if (params.flags & SNDRV_TIMER_PSFLG_EXCLUSIVE) tu->timeri->flags |= SNDRV_TIMER_IFLG_EXCLUSIVE; if (params.flags & SNDRV_TIMER_PSFLG_EARLY_EVENT) tu->timeri->flags |= SNDRV_TIMER_IFLG_EARLY_EVENT; } if (params.queue_size > 0 && (unsigned int)tu->queue_size != params.queue_size) { err = realloc_user_queue(tu, params.queue_size); if (err < 0) goto _end; } scoped_guard(spinlock_irq, &tu->qlock) { tu->qhead = tu->qtail = tu->qused = 0; if (tu->timeri->flags & SNDRV_TIMER_IFLG_EARLY_EVENT) { if (tu->tread) { struct snd_timer_tread64 tread; memset(&tread, 0, sizeof(tread)); tread.event = SNDRV_TIMER_EVENT_EARLY; tread.tstamp_sec = 0; tread.tstamp_nsec = 0; tread.val = 0; snd_timer_user_append_to_tqueue(tu, &tread); } else { struct snd_timer_read *r = &tu->queue[0]; r->resolution = 0; r->ticks = 0; tu->qused++; tu->qtail++; } } tu->filter = params.filter; tu->ticks = params.ticks; } err = 0; _end: if (copy_to_user(_params, ¶ms, sizeof(params))) return -EFAULT; return err; } static int snd_timer_user_status32(struct file *file, struct snd_timer_status32 __user *_status) { struct snd_timer_user *tu; struct snd_timer_status32 status; tu = file->private_data; if (!tu->timeri) return -EBADFD; memset(&status, 0, sizeof(status)); status.tstamp_sec = tu->tstamp.tv_sec; status.tstamp_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; scoped_guard(spinlock_irq, &tu->qlock) status.queue = tu->qused; if (copy_to_user(_status, &status, sizeof(status))) return -EFAULT; return 0; } static int snd_timer_user_status64(struct file *file, struct snd_timer_status64 __user *_status) { struct snd_timer_user *tu; struct snd_timer_status64 status; tu = file->private_data; if (!tu->timeri) return -EBADFD; memset(&status, 0, sizeof(status)); status.tstamp_sec = tu->tstamp.tv_sec; status.tstamp_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; scoped_guard(spinlock_irq, &tu->qlock) status.queue = tu->qused; if (copy_to_user(_status, &status, sizeof(status))) return -EFAULT; return 0; } static int snd_timer_user_start(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; snd_timer_stop(tu->timeri); tu->timeri->lost = 0; tu->last_resolution = 0; err = snd_timer_start(tu->timeri, tu->ticks); if (err < 0) return err; return 0; } static int snd_timer_user_stop(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; err = snd_timer_stop(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_continue(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; /* start timer instead of continue if it's not used before */ if (!(tu->timeri->flags & SNDRV_TIMER_IFLG_PAUSED)) return snd_timer_user_start(file); tu->timeri->lost = 0; err = snd_timer_continue(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_pause(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; err = snd_timer_pause(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_tread(void __user *argp, struct snd_timer_user *tu, unsigned int cmd, bool compat) { int __user *p = argp; int xarg, old_tread; if (tu->timeri) /* too late */ return -EBUSY; if (get_user(xarg, p)) return -EFAULT; old_tread = tu->tread; if (!xarg) tu->tread = TREAD_FORMAT_NONE; else if (cmd == SNDRV_TIMER_IOCTL_TREAD64 || (IS_ENABLED(CONFIG_64BIT) && !compat)) tu->tread = TREAD_FORMAT_TIME64; else tu->tread = TREAD_FORMAT_TIME32; if (tu->tread != old_tread && realloc_user_queue(tu, tu->queue_size) < 0) { tu->tread = old_tread; return -ENOMEM; } return 0; } enum { SNDRV_TIMER_IOCTL_START_OLD = _IO('T', 0x20), SNDRV_TIMER_IOCTL_STOP_OLD = _IO('T', 0x21), SNDRV_TIMER_IOCTL_CONTINUE_OLD = _IO('T', 0x22), SNDRV_TIMER_IOCTL_PAUSE_OLD = _IO('T', 0x23), }; #ifdef CONFIG_SND_UTIMER /* * Since userspace-driven timers are passed to userspace, we need to have an identifier * which will allow us to use them (basically, the subdevice number of udriven timer). */ static DEFINE_IDA(snd_utimer_ids); static void snd_utimer_put_id(struct snd_utimer *utimer) { int timer_id = utimer->id; snd_BUG_ON(timer_id < 0 || timer_id >= SNDRV_UTIMERS_MAX_COUNT); ida_free(&snd_utimer_ids, timer_id); } static int snd_utimer_take_id(void) { return ida_alloc_max(&snd_utimer_ids, SNDRV_UTIMERS_MAX_COUNT - 1, GFP_KERNEL); } static void snd_utimer_free(struct snd_utimer *utimer) { snd_timer_free(utimer->timer); snd_utimer_put_id(utimer); kfree(utimer->name); kfree(utimer); } static int snd_utimer_release(struct inode *inode, struct file *file) { struct snd_utimer *utimer = (struct snd_utimer *)file->private_data; snd_utimer_free(utimer); return 0; } static int snd_utimer_trigger(struct file *file) { struct snd_utimer *utimer = (struct snd_utimer *)file->private_data; snd_timer_interrupt(utimer->timer, utimer->timer->sticks); return 0; } static long snd_utimer_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { switch (ioctl) { case SNDRV_TIMER_IOCTL_TRIGGER: return snd_utimer_trigger(file); } return -ENOTTY; } static const struct file_operations snd_utimer_fops = { .llseek = noop_llseek, .release = snd_utimer_release, .unlocked_ioctl = snd_utimer_ioctl, }; static int snd_utimer_start(struct snd_timer *t) { return 0; } static int snd_utimer_stop(struct snd_timer *t) { return 0; } static int snd_utimer_open(struct snd_timer *t) { return 0; } static int snd_utimer_close(struct snd_timer *t) { return 0; } static const struct snd_timer_hardware timer_hw = { .flags = SNDRV_TIMER_HW_AUTO | SNDRV_TIMER_HW_WORK, .open = snd_utimer_open, .close = snd_utimer_close, .start = snd_utimer_start, .stop = snd_utimer_stop, }; static int snd_utimer_create(struct snd_timer_uinfo *utimer_info, struct snd_utimer **r_utimer) { struct snd_utimer *utimer; struct snd_timer *timer; struct snd_timer_id tid; int utimer_id; int err = 0; if (!utimer_info || utimer_info->resolution == 0) return -EINVAL; utimer = kzalloc(sizeof(*utimer), GFP_KERNEL); if (!utimer) return -ENOMEM; /* We hold the ioctl lock here so we won't get a race condition when allocating id */ utimer_id = snd_utimer_take_id(); if (utimer_id < 0) { err = utimer_id; goto err_take_id; } utimer->name = kasprintf(GFP_KERNEL, "snd-utimer%d", utimer_id); if (!utimer->name) { err = -ENOMEM; goto err_get_name; } utimer->id = utimer_id; tid.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION; tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL; tid.card = -1; tid.device = SNDRV_TIMER_GLOBAL_UDRIVEN; tid.subdevice = utimer_id; err = snd_timer_new(NULL, utimer->name, &tid, &timer); if (err < 0) { pr_err("Can't create userspace-driven timer\n"); goto err_timer_new; } timer->module = THIS_MODULE; timer->hw = timer_hw; timer->hw.resolution = utimer_info->resolution; timer->hw.ticks = 1; timer->max_instances = MAX_SLAVE_INSTANCES; utimer->timer = timer; err = snd_timer_global_register(timer); if (err < 0) { pr_err("Can't register a userspace-driven timer\n"); goto err_timer_reg; } *r_utimer = utimer; return 0; err_timer_reg: snd_timer_free(timer); err_timer_new: kfree(utimer->name); err_get_name: snd_utimer_put_id(utimer); err_take_id: kfree(utimer); return err; } static int snd_utimer_ioctl_create(struct file *file, struct snd_timer_uinfo __user *_utimer_info) { struct snd_utimer *utimer; struct snd_timer_uinfo *utimer_info __free(kfree) = NULL; int err, timer_fd; utimer_info = memdup_user(_utimer_info, sizeof(*utimer_info)); if (IS_ERR(utimer_info)) return PTR_ERR(utimer_info); err = snd_utimer_create(utimer_info, &utimer); if (err < 0) return err; utimer_info->id = utimer->id; timer_fd = anon_inode_getfd(utimer->name, &snd_utimer_fops, utimer, O_RDWR | O_CLOEXEC); if (timer_fd < 0) { snd_utimer_free(utimer); return timer_fd; } utimer_info->fd = timer_fd; err = copy_to_user(_utimer_info, utimer_info, sizeof(*utimer_info)); if (err) { /* * "Leak" the fd, as there is nothing we can do about it. * It might have been closed already since anon_inode_getfd * makes it available for userspace. * * We have to rely on the process exit path to do any * necessary cleanup (e.g. releasing the file). */ return -EFAULT; } return 0; } #else static int snd_utimer_ioctl_create(struct file *file, struct snd_timer_uinfo __user *_utimer_info) { return -ENOTTY; } #endif static long __snd_timer_user_ioctl(struct file *file, unsigned int cmd, unsigned long arg, bool compat) { struct snd_timer_user *tu; void __user *argp = (void __user *)arg; int __user *p = argp; tu = file->private_data; switch (cmd) { case SNDRV_TIMER_IOCTL_PVERSION: return put_user(SNDRV_TIMER_VERSION, p) ? -EFAULT : 0; case SNDRV_TIMER_IOCTL_NEXT_DEVICE: return snd_timer_user_next_device(argp); case SNDRV_TIMER_IOCTL_TREAD_OLD: case SNDRV_TIMER_IOCTL_TREAD64: return snd_timer_user_tread(argp, tu, cmd, compat); case SNDRV_TIMER_IOCTL_GINFO: return snd_timer_user_ginfo(file, argp); case SNDRV_TIMER_IOCTL_GPARAMS: return snd_timer_user_gparams(file, argp); case SNDRV_TIMER_IOCTL_GSTATUS: return snd_timer_user_gstatus(file, argp); case SNDRV_TIMER_IOCTL_SELECT: return snd_timer_user_tselect(file, argp); case SNDRV_TIMER_IOCTL_INFO: return snd_timer_user_info(file, argp); case SNDRV_TIMER_IOCTL_PARAMS: return snd_timer_user_params(file, argp); case SNDRV_TIMER_IOCTL_STATUS32: return snd_timer_user_status32(file, argp); case SNDRV_TIMER_IOCTL_STATUS64: return snd_timer_user_status64(file, argp); case SNDRV_TIMER_IOCTL_START: case SNDRV_TIMER_IOCTL_START_OLD: return snd_timer_user_start(file); case SNDRV_TIMER_IOCTL_STOP: case SNDRV_TIMER_IOCTL_STOP_OLD: return snd_timer_user_stop(file); case SNDRV_TIMER_IOCTL_CONTINUE: case SNDRV_TIMER_IOCTL_CONTINUE_OLD: return snd_timer_user_continue(file); case SNDRV_TIMER_IOCTL_PAUSE: case SNDRV_TIMER_IOCTL_PAUSE_OLD: return snd_timer_user_pause(file); case SNDRV_TIMER_IOCTL_CREATE: return snd_utimer_ioctl_create(file, argp); } return -ENOTTY; } static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct snd_timer_user *tu = file->private_data; guard(mutex)(&tu->ioctl_lock); return __snd_timer_user_ioctl(file, cmd, arg, false); } static int snd_timer_user_fasync(int fd, struct file * file, int on) { struct snd_timer_user *tu; tu = file->private_data; return snd_fasync_helper(fd, file, on, &tu->fasync); } static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, size_t count, loff_t *offset) { struct snd_timer_tread64 *tread; struct snd_timer_tread32 tread32; struct snd_timer_user *tu; long result = 0, unit; int qhead; int err = 0; tu = file->private_data; switch (tu->tread) { case TREAD_FORMAT_TIME64: unit = sizeof(struct snd_timer_tread64); break; case TREAD_FORMAT_TIME32: unit = sizeof(struct snd_timer_tread32); break; case TREAD_FORMAT_NONE: unit = sizeof(struct snd_timer_read); break; default: WARN_ONCE(1, "Corrupt snd_timer_user\n"); return -ENOTSUPP; } mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); while ((long)count - result >= unit) { while (!tu->qused) { wait_queue_entry_t wait; if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) { err = -EAGAIN; goto _error; } set_current_state(TASK_INTERRUPTIBLE); init_waitqueue_entry(&wait, current); add_wait_queue(&tu->qchange_sleep, &wait); spin_unlock_irq(&tu->qlock); mutex_unlock(&tu->ioctl_lock); schedule(); mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); remove_wait_queue(&tu->qchange_sleep, &wait); if (tu->disconnected) { err = -ENODEV; goto _error; } if (signal_pending(current)) { err = -ERESTARTSYS; goto _error; } } qhead = tu->qhead++; tu->qhead %= tu->queue_size; tu->qused--; spin_unlock_irq(&tu->qlock); tread = &tu->tqueue[qhead]; switch (tu->tread) { case TREAD_FORMAT_TIME64: if (copy_to_user(buffer, tread, sizeof(struct snd_timer_tread64))) err = -EFAULT; break; case TREAD_FORMAT_TIME32: memset(&tread32, 0, sizeof(tread32)); tread32 = (struct snd_timer_tread32) { .event = tread->event, .tstamp_sec = tread->tstamp_sec, .tstamp_nsec = tread->tstamp_nsec, .val = tread->val, }; if (copy_to_user(buffer, &tread32, sizeof(tread32))) err = -EFAULT; break; case TREAD_FORMAT_NONE: if (copy_to_user(buffer, &tu->queue[qhead], sizeof(struct snd_timer_read))) err = -EFAULT; break; default: err = -ENOTSUPP; break; } spin_lock_irq(&tu->qlock); if (err < 0) goto _error; result += unit; buffer += unit; } _error: spin_unlock_irq(&tu->qlock); mutex_unlock(&tu->ioctl_lock); return result > 0 ? result : err; } static __poll_t snd_timer_user_poll(struct file *file, poll_table * wait) { __poll_t mask; struct snd_timer_user *tu; tu = file->private_data; poll_wait(file, &tu->qchange_sleep, wait); mask = 0; guard(spinlock_irq)(&tu->qlock); if (tu->qused) mask |= EPOLLIN | EPOLLRDNORM; if (tu->disconnected) mask |= EPOLLERR; return mask; } #ifdef CONFIG_COMPAT #include "timer_compat.c" #else #define snd_timer_user_ioctl_compat NULL #endif static const struct file_operations snd_timer_f_ops = { .owner = THIS_MODULE, .read = snd_timer_user_read, .open = snd_timer_user_open, .release = snd_timer_user_release, .poll = snd_timer_user_poll, .unlocked_ioctl = snd_timer_user_ioctl, .compat_ioctl = snd_timer_user_ioctl_compat, .fasync = snd_timer_user_fasync, }; /* unregister the system timer */ static void snd_timer_free_all(void) { struct snd_timer *timer, *n; list_for_each_entry_safe(timer, n, &snd_timer_list, device_list) snd_timer_free(timer); } static struct device *timer_dev; /* * ENTRY functions */ static int __init alsa_timer_init(void) { int err; err = snd_device_alloc(&timer_dev, NULL); if (err < 0) return err; dev_set_name(timer_dev, "timer"); #ifdef SNDRV_OSS_INFO_DEV_TIMERS snd_oss_info_register(SNDRV_OSS_INFO_DEV_TIMERS, SNDRV_CARDS - 1, "system timer"); #endif err = snd_timer_register_system(); if (err < 0) { pr_err("ALSA: unable to register system timer (%i)\n", err); goto put_timer; } err = snd_register_device(SNDRV_DEVICE_TYPE_TIMER, NULL, 0, &snd_timer_f_ops, NULL, timer_dev); if (err < 0) { pr_err("ALSA: unable to register timer device (%i)\n", err); snd_timer_free_all(); goto put_timer; } snd_timer_proc_init(); return 0; put_timer: put_device(timer_dev); return err; } static void __exit alsa_timer_exit(void) { snd_unregister_device(timer_dev); snd_timer_free_all(); put_device(timer_dev); snd_timer_proc_done(); #ifdef SNDRV_OSS_INFO_DEV_TIMERS snd_oss_info_unregister(SNDRV_OSS_INFO_DEV_TIMERS, SNDRV_CARDS - 1); #endif } module_init(alsa_timer_init) module_exit(alsa_timer_exit) |
| 265 357 | 1 2 3 4 5 6 7 8 9 10 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #ifndef __XFS_LINUX__ #define __XFS_LINUX__ #include <linux/types.h> #include <linux/uuid.h> /* * Kernel specific type declarations for XFS */ typedef __s64 xfs_off_t; /* <file offset> type */ typedef unsigned long long xfs_ino_t; /* <inode> type */ typedef __s64 xfs_daddr_t; /* <disk address> type */ typedef __u32 xfs_dev_t; typedef __u32 xfs_nlink_t; #include "xfs_types.h" #include <linux/semaphore.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/crc32c.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/file.h> #include <linux/filelock.h> #include <linux/swap.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/bitops.h> #include <linux/major.h> #include <linux/pagemap.h> #include <linux/vfs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/list.h> #include <linux/proc_fs.h> #include <linux/sort.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/delay.h> #include <linux/log2.h> #include <linux/rwsem.h> #include <linux/spinlock.h> #include <linux/random.h> #include <linux/ctype.h> #include <linux/writeback.h> #include <linux/capability.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/list_sort.h> #include <linux/ratelimit.h> #include <linux/rhashtable.h> #include <linux/xattr.h> #include <linux/mnt_idmapping.h> #include <linux/debugfs.h> #include <asm/page.h> #include <asm/div64.h> #include <asm/param.h> #include <linux/uaccess.h> #include <asm/byteorder.h> #include <linux/unaligned.h> #include "xfs_fs.h" #include "xfs_stats.h" #include "xfs_sysctl.h" #include "xfs_iops.h" #include "xfs_aops.h" #include "xfs_super.h" #include "xfs_cksum.h" #include "xfs_buf.h" #include "xfs_message.h" #include "xfs_drain.h" #include "xfs_hooks.h" #ifdef __BIG_ENDIAN #define XFS_NATIVE_HOST 1 #else #undef XFS_NATIVE_HOST #endif #define irix_sgid_inherit xfs_params.sgid_inherit.val #define irix_symlink_mode xfs_params.symlink_mode.val #define xfs_panic_mask xfs_params.panic_mask.val #define xfs_error_level xfs_params.error_level.val #define xfs_syncd_centisecs xfs_params.syncd_timer.val #define xfs_stats_clear xfs_params.stats_clear.val #define xfs_inherit_sync xfs_params.inherit_sync.val #define xfs_inherit_nodump xfs_params.inherit_nodump.val #define xfs_inherit_noatime xfs_params.inherit_noatim.val #define xfs_inherit_nosymlinks xfs_params.inherit_nosym.val #define xfs_rotorstep xfs_params.rotorstep.val #define xfs_inherit_nodefrag xfs_params.inherit_nodfrg.val #define xfs_fstrm_centisecs xfs_params.fstrm_timer.val #define xfs_blockgc_secs xfs_params.blockgc_timer.val #define current_cpu() (raw_smp_processor_id()) #define current_set_flags_nested(sp, f) \ (*(sp) = current->flags, current->flags |= (f)) #define current_restore_flags_nested(sp, f) \ (current->flags = ((current->flags & ~(f)) | (*(sp) & (f)))) #define NBBY 8 /* number of bits per byte */ /* * Size of block device i/o is parameterized here. * Currently the system supports page-sized i/o. */ #define BLKDEV_IOSHIFT PAGE_SHIFT #define BLKDEV_IOSIZE (1<<BLKDEV_IOSHIFT) /* number of BB's per block device block */ #define BLKDEV_BB BTOBB(BLKDEV_IOSIZE) #define ENOATTR ENODATA /* Attribute not found */ #define EWRONGFS EINVAL /* Mount with wrong filesystem type */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define __return_address __builtin_return_address(0) /* * Return the address of a label. Use barrier() so that the optimizer * won't reorder code to refactor the error jumpouts into a single * return, which throws off the reported address. */ #define __this_address ({ __label__ __here; __here: barrier(); &&__here; }) #define howmany(x, y) (((x)+((y)-1))/(y)) static inline void delay(long ticks) { schedule_timeout_uninterruptible(ticks); } /* * XFS wrapper structure for sysfs support. It depends on external data * structures and is embedded in various internal data structures to implement * the XFS sysfs object heirarchy. Define it here for broad access throughout * the codebase. */ struct xfs_kobj { struct kobject kobject; struct completion complete; }; struct xstats { struct xfsstats __percpu *xs_stats; struct xfs_kobj xs_kobj; }; extern struct xstats xfsstats; static inline dev_t xfs_to_linux_dev_t(xfs_dev_t dev) { return MKDEV(sysv_major(dev) & 0x1ff, sysv_minor(dev)); } static inline xfs_dev_t linux_to_xfs_dev_t(dev_t dev) { return sysv_encode_dev(dev); } /* * Various platform dependent calls that don't fit anywhere else */ #define xfs_sort(a,n,s,fn) sort(a,n,s,fn,NULL) #define xfs_stack_trace() dump_stack() static inline uint64_t rounddown_64(uint64_t x, uint32_t y) { do_div(x, y); return x * y; } static inline uint64_t roundup_64(uint64_t x, uint32_t y) { x += y - 1; do_div(x, y); return x * y; } static inline uint64_t howmany_64(uint64_t x, uint32_t y) { x += y - 1; do_div(x, y); return x; } static inline bool isaligned_64(uint64_t x, uint32_t y) { return do_div(x, y) == 0; } /* If @b is a power of 2, return log2(b). Else return -1. */ static inline int8_t log2_if_power2(unsigned long b) { return is_power_of_2(b) ? ilog2(b) : -1; } /* If @b is a power of 2, return a mask of the lower bits, else return zero. */ static inline unsigned long long mask64_if_power2(unsigned long b) { return is_power_of_2(b) ? b - 1 : 0; } int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count, char *data, enum req_op op); #define ASSERT_ALWAYS(expr) \ (likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__)) #ifdef DEBUG #define ASSERT(expr) \ (likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__)) #else /* !DEBUG */ #ifdef XFS_WARN #define ASSERT(expr) \ (likely(expr) ? (void)0 : asswarn(NULL, #expr, __FILE__, __LINE__)) #else /* !DEBUG && !XFS_WARN */ #define ASSERT(expr) ((void)0) #endif /* XFS_WARN */ #endif /* DEBUG */ #define XFS_IS_CORRUPT(mp, expr) \ (unlikely(expr) ? xfs_corruption_error(#expr, XFS_ERRLEVEL_LOW, (mp), \ NULL, 0, __FILE__, __LINE__, \ __this_address), \ true : false) #define STATIC static noinline #ifdef CONFIG_XFS_RT /* * make sure we ignore the inode flag if the filesystem doesn't have a * configured realtime device. */ #define XFS_IS_REALTIME_INODE(ip) \ (((ip)->i_diflags & XFS_DIFLAG_REALTIME) && \ (ip)->i_mount->m_rtdev_targp) #define XFS_IS_REALTIME_MOUNT(mp) ((mp)->m_rtdev_targp ? 1 : 0) #else #define XFS_IS_REALTIME_INODE(ip) (0) #define XFS_IS_REALTIME_MOUNT(mp) (0) #endif /* * Starting in Linux 4.15, the %p (raw pointer value) printk modifier * prints a hashed version of the pointer to avoid leaking kernel * pointers into dmesg. If we're trying to debug the kernel we want the * raw values, so override this behavior as best we can. */ #ifdef DEBUG # define PTR_FMT "%px" #else # define PTR_FMT "%p" #endif /* * Helper for IO routines to grab backing pages from allocated kernel memory. */ static inline struct page * kmem_to_page(void *addr) { if (is_vmalloc_addr(addr)) return vmalloc_to_page(addr); return virt_to_page(addr); } #endif /* __XFS_LINUX__ */ |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/sys.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/export.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/utsname.h> #include <linux/mman.h> #include <linux/reboot.h> #include <linux/prctl.h> #include <linux/highuid.h> #include <linux/fs.h> #include <linux/kmod.h> #include <linux/ksm.h> #include <linux/perf_event.h> #include <linux/resource.h> #include <linux/kernel.h> #include <linux/workqueue.h> #include <linux/capability.h> #include <linux/device.h> #include <linux/key.h> #include <linux/times.h> #include <linux/posix-timers.h> #include <linux/security.h> #include <linux/random.h> #include <linux/suspend.h> #include <linux/tty.h> #include <linux/signal.h> #include <linux/cn_proc.h> #include <linux/getcpu.h> #include <linux/task_io_accounting_ops.h> #include <linux/seccomp.h> #include <linux/cpu.h> #include <linux/personality.h> #include <linux/ptrace.h> #include <linux/fs_struct.h> #include <linux/file.h> #include <linux/mount.h> #include <linux/gfp.h> #include <linux/syscore_ops.h> #include <linux/version.h> #include <linux/ctype.h> #include <linux/syscall_user_dispatch.h> #include <linux/compat.h> #include <linux/syscalls.h> #include <linux/kprobes.h> #include <linux/user_namespace.h> #include <linux/time_namespace.h> #include <linux/binfmts.h> #include <linux/sched.h> #include <linux/sched/autogroup.h> #include <linux/sched/loadavg.h> #include <linux/sched/stat.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/sched/cputime.h> #include <linux/rcupdate.h> #include <linux/uidgid.h> #include <linux/cred.h> #include <linux/nospec.h> #include <linux/kmsg_dump.h> /* Move somewhere else to avoid recompiling? */ #include <generated/utsrelease.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/unistd.h> #include <trace/events/task.h> #include "uid16.h" #ifndef SET_UNALIGN_CTL # define SET_UNALIGN_CTL(a, b) (-EINVAL) #endif #ifndef GET_UNALIGN_CTL # define GET_UNALIGN_CTL(a, b) (-EINVAL) #endif #ifndef SET_FPEMU_CTL # define SET_FPEMU_CTL(a, b) (-EINVAL) #endif #ifndef GET_FPEMU_CTL # define GET_FPEMU_CTL(a, b) (-EINVAL) #endif #ifndef SET_FPEXC_CTL # define SET_FPEXC_CTL(a, b) (-EINVAL) #endif #ifndef GET_FPEXC_CTL # define GET_FPEXC_CTL(a, b) (-EINVAL) #endif #ifndef GET_ENDIAN # define GET_ENDIAN(a, b) (-EINVAL) #endif #ifndef SET_ENDIAN # define SET_ENDIAN(a, b) (-EINVAL) #endif #ifndef GET_TSC_CTL # define GET_TSC_CTL(a) (-EINVAL) #endif #ifndef SET_TSC_CTL # define SET_TSC_CTL(a) (-EINVAL) #endif #ifndef GET_FP_MODE # define GET_FP_MODE(a) (-EINVAL) #endif #ifndef SET_FP_MODE # define SET_FP_MODE(a,b) (-EINVAL) #endif #ifndef SVE_SET_VL # define SVE_SET_VL(a) (-EINVAL) #endif #ifndef SVE_GET_VL # define SVE_GET_VL() (-EINVAL) #endif #ifndef SME_SET_VL # define SME_SET_VL(a) (-EINVAL) #endif #ifndef SME_GET_VL # define SME_GET_VL() (-EINVAL) #endif #ifndef PAC_RESET_KEYS # define PAC_RESET_KEYS(a, b) (-EINVAL) #endif #ifndef PAC_SET_ENABLED_KEYS # define PAC_SET_ENABLED_KEYS(a, b, c) (-EINVAL) #endif #ifndef PAC_GET_ENABLED_KEYS # define PAC_GET_ENABLED_KEYS(a) (-EINVAL) #endif #ifndef SET_TAGGED_ADDR_CTRL # define SET_TAGGED_ADDR_CTRL(a) (-EINVAL) #endif #ifndef GET_TAGGED_ADDR_CTRL # define GET_TAGGED_ADDR_CTRL() (-EINVAL) #endif #ifndef RISCV_V_SET_CONTROL # define RISCV_V_SET_CONTROL(a) (-EINVAL) #endif #ifndef RISCV_V_GET_CONTROL # define RISCV_V_GET_CONTROL() (-EINVAL) #endif #ifndef RISCV_SET_ICACHE_FLUSH_CTX # define RISCV_SET_ICACHE_FLUSH_CTX(a, b) (-EINVAL) #endif #ifndef PPC_GET_DEXCR_ASPECT # define PPC_GET_DEXCR_ASPECT(a, b) (-EINVAL) #endif #ifndef PPC_SET_DEXCR_ASPECT # define PPC_SET_DEXCR_ASPECT(a, b, c) (-EINVAL) #endif /* * this is where the system-wide overflow UID and GID are defined, for * architectures that now have 32-bit UID/GID but didn't in the past */ int overflowuid = DEFAULT_OVERFLOWUID; int overflowgid = DEFAULT_OVERFLOWGID; EXPORT_SYMBOL(overflowuid); EXPORT_SYMBOL(overflowgid); /* * the same as above, but for filesystems which can only store a 16-bit * UID and GID. as such, this is needed on all architectures */ int fs_overflowuid = DEFAULT_FS_OVERFLOWUID; int fs_overflowgid = DEFAULT_FS_OVERFLOWGID; EXPORT_SYMBOL(fs_overflowuid); EXPORT_SYMBOL(fs_overflowgid); /* * Returns true if current's euid is same as p's uid or euid, * or has CAP_SYS_NICE to p's user_ns. * * Called with rcu_read_lock, creds are safe */ static bool set_one_prio_perm(struct task_struct *p) { const struct cred *cred = current_cred(), *pcred = __task_cred(p); if (uid_eq(pcred->uid, cred->euid) || uid_eq(pcred->euid, cred->euid)) return true; if (ns_capable(pcred->user_ns, CAP_SYS_NICE)) return true; return false; } /* * set the priority of a task * - the caller must hold the RCU read lock */ static int set_one_prio(struct task_struct *p, int niceval, int error) { int no_nice; if (!set_one_prio_perm(p)) { error = -EPERM; goto out; } if (niceval < task_nice(p) && !can_nice(p, niceval)) { error = -EACCES; goto out; } no_nice = security_task_setnice(p, niceval); if (no_nice) { error = no_nice; goto out; } if (error == -ESRCH) error = 0; set_user_nice(p, niceval); out: return error; } SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) { struct task_struct *g, *p; struct user_struct *user; const struct cred *cred = current_cred(); int error = -EINVAL; struct pid *pgrp; kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) goto out; /* normalize: avoid signed division (rounding problems) */ error = -ESRCH; if (niceval < MIN_NICE) niceval = MIN_NICE; if (niceval > MAX_NICE) niceval = MAX_NICE; rcu_read_lock(); switch (which) { case PRIO_PROCESS: if (who) p = find_task_by_vpid(who); else p = current; if (p) error = set_one_prio(p, niceval, error); break; case PRIO_PGRP: if (who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { error = set_one_prio(p, niceval, error); } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); read_unlock(&tasklist_lock); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) uid = cred->uid; else if (!uid_eq(uid, cred->uid)) { user = find_user(uid); if (!user) goto out_unlock; /* No processes for this user */ } for_each_process_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) error = set_one_prio(p, niceval, error); } if (!uid_eq(uid, cred->uid)) free_uid(user); /* For find_user() */ break; } out_unlock: rcu_read_unlock(); out: return error; } /* * Ugh. To avoid negative return values, "getpriority()" will * not return the normal nice-value, but a negated value that * has been offset by 20 (ie it returns 40..1 instead of -20..19) * to stay compatible. */ SYSCALL_DEFINE2(getpriority, int, which, int, who) { struct task_struct *g, *p; struct user_struct *user; const struct cred *cred = current_cred(); long niceval, retval = -ESRCH; struct pid *pgrp; kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) return -EINVAL; rcu_read_lock(); switch (which) { case PRIO_PROCESS: if (who) p = find_task_by_vpid(who); else p = current; if (p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } break; case PRIO_PGRP: if (who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); read_unlock(&tasklist_lock); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) uid = cred->uid; else if (!uid_eq(uid, cred->uid)) { user = find_user(uid); if (!user) goto out_unlock; /* No processes for this user */ } for_each_process_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } } if (!uid_eq(uid, cred->uid)) free_uid(user); /* for find_user() */ break; } out_unlock: rcu_read_unlock(); return retval; } /* * Unprivileged users may change the real gid to the effective gid * or vice versa. (BSD-style) * * If you set the real gid at all, or set the effective gid to a value not * equal to the real gid, then the saved gid is set to the new effective gid. * * This makes it possible for a setgid program to completely drop its * privileges, which is often a useful assertion to make when you are doing * a security audit over a program. * * The general idea is that a program which uses just setregid() will be * 100% compatible with BSD. A program which uses just setgid() will be * 100% compatible with POSIX with saved IDs. * * SMP: There are not races, the GIDs are checked only by filesystem * operations (as far as semantic preservation is concerned). */ #ifdef CONFIG_MULTIUSER long __sys_setregid(gid_t rgid, gid_t egid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t krgid, kegid; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); if ((rgid != (gid_t) -1) && !gid_valid(krgid)) return -EINVAL; if ((egid != (gid_t) -1) && !gid_valid(kegid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (rgid != (gid_t) -1) { if (gid_eq(old->gid, krgid) || gid_eq(old->egid, krgid) || ns_capable_setid(old->user_ns, CAP_SETGID)) new->gid = krgid; else goto error; } if (egid != (gid_t) -1) { if (gid_eq(old->gid, kegid) || gid_eq(old->egid, kegid) || gid_eq(old->sgid, kegid) || ns_capable_setid(old->user_ns, CAP_SETGID)) new->egid = kegid; else goto error; } if (rgid != (gid_t) -1 || (egid != (gid_t) -1 && !gid_eq(kegid, old->gid))) new->sgid = new->egid; new->fsgid = new->egid; retval = security_task_fix_setgid(new, old, LSM_SETID_RE); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) { return __sys_setregid(rgid, egid); } /* * setgid() is implemented like SysV w/ SAVED_IDS * * SMP: Same implicit races as above. */ long __sys_setgid(gid_t gid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t kgid; kgid = make_kgid(ns, gid); if (!gid_valid(kgid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ns_capable_setid(old->user_ns, CAP_SETGID)) new->gid = new->egid = new->sgid = new->fsgid = kgid; else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid)) new->egid = new->fsgid = kgid; else goto error; retval = security_task_fix_setgid(new, old, LSM_SETID_ID); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE1(setgid, gid_t, gid) { return __sys_setgid(gid); } /* * change the user struct in a credentials set to match the new UID */ static int set_user(struct cred *new) { struct user_struct *new_user; new_user = alloc_uid(new->uid); if (!new_user) return -EAGAIN; free_uid(new->user); new->user = new_user; return 0; } static void flag_nproc_exceeded(struct cred *new) { if (new->ucounts == current_ucounts()) return; /* * We don't fail in case of NPROC limit excess here because too many * poorly written programs don't check set*uid() return code, assuming * it never fails if called by root. We may still enforce NPROC limit * for programs doing set*uid()+execve() by harmlessly deferring the * failure to the execve() stage. */ if (is_rlimit_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) && new->user != INIT_USER) current->flags |= PF_NPROC_EXCEEDED; else current->flags &= ~PF_NPROC_EXCEEDED; } /* * Unprivileged users may change the real uid to the effective uid * or vice versa. (BSD-style) * * If you set the real uid at all, or set the effective uid to a value not * equal to the real uid, then the saved uid is set to the new effective uid. * * This makes it possible for a setuid program to completely drop its * privileges, which is often a useful assertion to make when you are doing * a security audit over a program. * * The general idea is that a program which uses just setreuid() will be * 100% compatible with BSD. A program which uses just setuid() will be * 100% compatible with POSIX with saved IDs. */ long __sys_setreuid(uid_t ruid, uid_t euid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kruid, keuid; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); if ((ruid != (uid_t) -1) && !uid_valid(kruid)) return -EINVAL; if ((euid != (uid_t) -1) && !uid_valid(keuid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ruid != (uid_t) -1) { new->uid = kruid; if (!uid_eq(old->uid, kruid) && !uid_eq(old->euid, kruid) && !ns_capable_setid(old->user_ns, CAP_SETUID)) goto error; } if (euid != (uid_t) -1) { new->euid = keuid; if (!uid_eq(old->uid, keuid) && !uid_eq(old->euid, keuid) && !uid_eq(old->suid, keuid) && !ns_capable_setid(old->user_ns, CAP_SETUID)) goto error; } if (!uid_eq(new->uid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } if (ruid != (uid_t) -1 || (euid != (uid_t) -1 && !uid_eq(keuid, old->uid))) new->suid = new->euid; new->fsuid = new->euid; retval = security_task_fix_setuid(new, old, LSM_SETID_RE); if (retval < 0) goto error; retval = set_cred_ucounts(new); if (retval < 0) goto error; flag_nproc_exceeded(new); return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) { return __sys_setreuid(ruid, euid); } /* * setuid() is implemented like SysV with SAVED_IDS * * Note that SAVED_ID's is deficient in that a setuid root program * like sendmail, for example, cannot set its uid to be a normal * user and then switch back, because if you're root, setuid() sets * the saved uid too. If you don't like this, blame the bright people * in the POSIX committee and/or USG. Note that the BSD-style setreuid() * will allow a root program to temporarily drop privileges and be able to * regain them by swapping the real and effective uid. */ long __sys_setuid(uid_t uid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kuid; kuid = make_kuid(ns, uid); if (!uid_valid(kuid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ns_capable_setid(old->user_ns, CAP_SETUID)) { new->suid = new->uid = kuid; if (!uid_eq(kuid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } } else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) { goto error; } new->fsuid = new->euid = kuid; retval = security_task_fix_setuid(new, old, LSM_SETID_ID); if (retval < 0) goto error; retval = set_cred_ucounts(new); if (retval < 0) goto error; flag_nproc_exceeded(new); return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE1(setuid, uid_t, uid) { return __sys_setuid(uid); } /* * This function implements a generic ability to update ruid, euid, * and suid. This allows you to implement the 4.4 compatible seteuid(). */ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kruid, keuid, ksuid; bool ruid_new, euid_new, suid_new; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); ksuid = make_kuid(ns, suid); if ((ruid != (uid_t) -1) && !uid_valid(kruid)) return -EINVAL; if ((euid != (uid_t) -1) && !uid_valid(keuid)) return -EINVAL; if ((suid != (uid_t) -1) && !uid_valid(ksuid)) return -EINVAL; old = current_cred(); /* check for no-op */ if ((ruid == (uid_t) -1 || uid_eq(kruid, old->uid)) && (euid == (uid_t) -1 || (uid_eq(keuid, old->euid) && uid_eq(keuid, old->fsuid))) && (suid == (uid_t) -1 || uid_eq(ksuid, old->suid))) return 0; ruid_new = ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid); euid_new = euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid); suid_new = suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid); if ((ruid_new || euid_new || suid_new) && !ns_capable_setid(old->user_ns, CAP_SETUID)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (ruid != (uid_t) -1) { new->uid = kruid; if (!uid_eq(kruid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } } if (euid != (uid_t) -1) new->euid = keuid; if (suid != (uid_t) -1) new->suid = ksuid; new->fsuid = new->euid; retval = security_task_fix_setuid(new, old, LSM_SETID_RES); if (retval < 0) goto error; retval = set_cred_ucounts(new); if (retval < 0) goto error; flag_nproc_exceeded(new); return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) { return __sys_setresuid(ruid, euid, suid); } SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp) { const struct cred *cred = current_cred(); int retval; uid_t ruid, euid, suid; ruid = from_kuid_munged(cred->user_ns, cred->uid); euid = from_kuid_munged(cred->user_ns, cred->euid); suid = from_kuid_munged(cred->user_ns, cred->suid); retval = put_user(ruid, ruidp); if (!retval) { retval = put_user(euid, euidp); if (!retval) return put_user(suid, suidp); } return retval; } /* * Same as above, but for rgid, egid, sgid. */ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t krgid, kegid, ksgid; bool rgid_new, egid_new, sgid_new; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); ksgid = make_kgid(ns, sgid); if ((rgid != (gid_t) -1) && !gid_valid(krgid)) return -EINVAL; if ((egid != (gid_t) -1) && !gid_valid(kegid)) return -EINVAL; if ((sgid != (gid_t) -1) && !gid_valid(ksgid)) return -EINVAL; old = current_cred(); /* check for no-op */ if ((rgid == (gid_t) -1 || gid_eq(krgid, old->gid)) && (egid == (gid_t) -1 || (gid_eq(kegid, old->egid) && gid_eq(kegid, old->fsgid))) && (sgid == (gid_t) -1 || gid_eq(ksgid, old->sgid))) return 0; rgid_new = rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid); egid_new = egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid); sgid_new = sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid); if ((rgid_new || egid_new || sgid_new) && !ns_capable_setid(old->user_ns, CAP_SETGID)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (rgid != (gid_t) -1) new->gid = krgid; if (egid != (gid_t) -1) new->egid = kegid; if (sgid != (gid_t) -1) new->sgid = ksgid; new->fsgid = new->egid; retval = security_task_fix_setgid(new, old, LSM_SETID_RES); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) { return __sys_setresgid(rgid, egid, sgid); } SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp) { const struct cred *cred = current_cred(); int retval; gid_t rgid, egid, sgid; rgid = from_kgid_munged(cred->user_ns, cred->gid); egid = from_kgid_munged(cred->user_ns, cred->egid); sgid = from_kgid_munged(cred->user_ns, cred->sgid); retval = put_user(rgid, rgidp); if (!retval) { retval = put_user(egid, egidp); if (!retval) retval = put_user(sgid, sgidp); } return retval; } /* * "setfsuid()" sets the fsuid - the uid used for filesystem checks. This * is used for "access()" and for the NFS daemon (letting nfsd stay at * whatever uid it wants to). It normally shadows "euid", except when * explicitly set by setfsuid() or for access.. */ long __sys_setfsuid(uid_t uid) { const struct cred *old; struct cred *new; uid_t old_fsuid; kuid_t kuid; old = current_cred(); old_fsuid = from_kuid_munged(old->user_ns, old->fsuid); kuid = make_kuid(old->user_ns, uid); if (!uid_valid(kuid)) return old_fsuid; new = prepare_creds(); if (!new) return old_fsuid; if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) || uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) || ns_capable_setid(old->user_ns, CAP_SETUID)) { if (!uid_eq(kuid, old->fsuid)) { new->fsuid = kuid; if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) goto change_okay; } } abort_creds(new); return old_fsuid; change_okay: commit_creds(new); return old_fsuid; } SYSCALL_DEFINE1(setfsuid, uid_t, uid) { return __sys_setfsuid(uid); } /* * Samma på svenska.. */ long __sys_setfsgid(gid_t gid) { const struct cred *old; struct cred *new; gid_t old_fsgid; kgid_t kgid; old = current_cred(); old_fsgid = from_kgid_munged(old->user_ns, old->fsgid); kgid = make_kgid(old->user_ns, gid); if (!gid_valid(kgid)) return old_fsgid; new = prepare_creds(); if (!new) return old_fsgid; if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) || gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) || ns_capable_setid(old->user_ns, CAP_SETGID)) { if (!gid_eq(kgid, old->fsgid)) { new->fsgid = kgid; if (security_task_fix_setgid(new,old,LSM_SETID_FS) == 0) goto change_okay; } } abort_creds(new); return old_fsgid; change_okay: commit_creds(new); return old_fsgid; } SYSCALL_DEFINE1(setfsgid, gid_t, gid) { return __sys_setfsgid(gid); } #endif /* CONFIG_MULTIUSER */ /** * sys_getpid - return the thread group id of the current process * * Note, despite the name, this returns the tgid not the pid. The tgid and * the pid are identical unless CLONE_THREAD was specified on clone() in * which case the tgid is the same in all threads of the same group. * * This is SMP safe as current->tgid does not change. */ SYSCALL_DEFINE0(getpid) { return task_tgid_vnr(current); } /* Thread ID - the internal kernel "pid" */ SYSCALL_DEFINE0(gettid) { return task_pid_vnr(current); } /* * Accessing ->real_parent is not SMP-safe, it could * change from under us. However, we can use a stale * value of ->real_parent under rcu_read_lock(), see * release_task()->call_rcu(delayed_put_task_struct). */ SYSCALL_DEFINE0(getppid) { int pid; rcu_read_lock(); pid = task_tgid_vnr(rcu_dereference(current->real_parent)); rcu_read_unlock(); return pid; } SYSCALL_DEFINE0(getuid) { /* Only we change this so SMP safe */ return from_kuid_munged(current_user_ns(), current_uid()); } SYSCALL_DEFINE0(geteuid) { /* Only we change this so SMP safe */ return from_kuid_munged(current_user_ns(), current_euid()); } SYSCALL_DEFINE0(getgid) { /* Only we change this so SMP safe */ return from_kgid_munged(current_user_ns(), current_gid()); } SYSCALL_DEFINE0(getegid) { /* Only we change this so SMP safe */ return from_kgid_munged(current_user_ns(), current_egid()); } static void do_sys_times(struct tms *tms) { u64 tgutime, tgstime, cutime, cstime; thread_group_cputime_adjusted(current, &tgutime, &tgstime); cutime = current->signal->cutime; cstime = current->signal->cstime; tms->tms_utime = nsec_to_clock_t(tgutime); tms->tms_stime = nsec_to_clock_t(tgstime); tms->tms_cutime = nsec_to_clock_t(cutime); tms->tms_cstime = nsec_to_clock_t(cstime); } SYSCALL_DEFINE1(times, struct tms __user *, tbuf) { if (tbuf) { struct tms tmp; do_sys_times(&tmp); if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } force_successful_syscall_return(); return (long) jiffies_64_to_clock_t(get_jiffies_64()); } #ifdef CONFIG_COMPAT static compat_clock_t clock_t_to_compat_clock_t(clock_t x) { return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); } COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf) { if (tbuf) { struct tms tms; struct compat_tms tmp; do_sys_times(&tms); /* Convert our struct tms to the compat version. */ tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); if (copy_to_user(tbuf, &tmp, sizeof(tmp))) return -EFAULT; } force_successful_syscall_return(); return compat_jiffies_to_clock_t(jiffies); } #endif /* * This needs some heavy checking ... * I just haven't the stomach for it. I also don't fully * understand sessions/pgrp etc. Let somebody who does explain it. * * OK, I think I have the protection semantics right.... this is really * only important on a multi-user system anyway, to make sure one user * can't send a signal to a process owned by another. -TYT, 12/12/91 * * !PF_FORKNOEXEC check to conform completely to POSIX. */ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) { struct task_struct *p; struct task_struct *group_leader = current->group_leader; struct pid *pids[PIDTYPE_MAX] = { 0 }; struct pid *pgrp; int err; if (!pid) pid = task_pid_vnr(group_leader); if (!pgid) pgid = pid; if (pgid < 0) return -EINVAL; rcu_read_lock(); /* From this point forward we keep holding onto the tasklist lock * so that our parent does not change from under us. -DaveM */ write_lock_irq(&tasklist_lock); err = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; err = -EINVAL; if (!thread_group_leader(p)) goto out; if (same_thread_group(p->real_parent, group_leader)) { err = -EPERM; if (task_session(p) != task_session(group_leader)) goto out; err = -EACCES; if (!(p->flags & PF_FORKNOEXEC)) goto out; } else { err = -ESRCH; if (p != group_leader) goto out; } err = -EPERM; if (p->signal->leader) goto out; pgrp = task_pid(p); if (pgid != pid) { struct task_struct *g; pgrp = find_vpid(pgid); g = pid_task(pgrp, PIDTYPE_PGID); if (!g || task_session(g) != task_session(group_leader)) goto out; } err = security_task_setpgid(p, pgid); if (err) goto out; if (task_pgrp(p) != pgrp) change_pid(pids, p, PIDTYPE_PGID, pgrp); err = 0; out: /* All paths lead to here, thus we are safe. -DaveM */ write_unlock_irq(&tasklist_lock); rcu_read_unlock(); free_pids(pids); return err; } static int do_getpgid(pid_t pid) { struct task_struct *p; struct pid *grp; int retval; rcu_read_lock(); if (!pid) grp = task_pgrp(current); else { retval = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; grp = task_pgrp(p); if (!grp) goto out; retval = security_task_getpgid(p); if (retval) goto out; } retval = pid_vnr(grp); out: rcu_read_unlock(); return retval; } SYSCALL_DEFINE1(getpgid, pid_t, pid) { return do_getpgid(pid); } #ifdef __ARCH_WANT_SYS_GETPGRP SYSCALL_DEFINE0(getpgrp) { return do_getpgid(0); } #endif SYSCALL_DEFINE1(getsid, pid_t, pid) { struct task_struct *p; struct pid *sid; int retval; rcu_read_lock(); if (!pid) sid = task_session(current); else { retval = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; sid = task_session(p); if (!sid) goto out; retval = security_task_getsid(p); if (retval) goto out; } retval = pid_vnr(sid); out: rcu_read_unlock(); return retval; } static void set_special_pids(struct pid **pids, struct pid *pid) { struct task_struct *curr = current->group_leader; if (task_session(curr) != pid) change_pid(pids, curr, PIDTYPE_SID, pid); if (task_pgrp(curr) != pid) change_pid(pids, curr, PIDTYPE_PGID, pid); } int ksys_setsid(void) { struct task_struct *group_leader = current->group_leader; struct pid *sid = task_pid(group_leader); struct pid *pids[PIDTYPE_MAX] = { 0 }; pid_t session = pid_vnr(sid); int err = -EPERM; write_lock_irq(&tasklist_lock); /* Fail if I am already a session leader */ if (group_leader->signal->leader) goto out; /* Fail if a process group id already exists that equals the * proposed session id. */ if (pid_task(sid, PIDTYPE_PGID)) goto out; group_leader->signal->leader = 1; set_special_pids(pids, sid); proc_clear_tty(group_leader); err = session; out: write_unlock_irq(&tasklist_lock); free_pids(pids); if (err > 0) { proc_sid_connector(group_leader); sched_autogroup_create_attach(group_leader); } return err; } SYSCALL_DEFINE0(setsid) { return ksys_setsid(); } DECLARE_RWSEM(uts_sem); #ifdef COMPAT_UTS_MACHINE #define override_architecture(name) \ (personality(current->personality) == PER_LINUX32 && \ copy_to_user(name->machine, COMPAT_UTS_MACHINE, \ sizeof(COMPAT_UTS_MACHINE))) #else #define override_architecture(name) 0 #endif /* * Work around broken programs that cannot handle "Linux 3.0". * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40 * And we map 4.x and later versions to 2.6.60+x, so 4.0/5.0/6.0/... would be * 2.6.60. */ static int override_release(char __user *release, size_t len) { int ret = 0; if (current->personality & UNAME26) { const char *rest = UTS_RELEASE; char buf[65] = { 0 }; int ndots = 0; unsigned v; size_t copy; while (*rest) { if (*rest == '.' && ++ndots >= 3) break; if (!isdigit(*rest) && *rest != '.') break; rest++; } v = LINUX_VERSION_PATCHLEVEL + 60; copy = clamp_t(size_t, len, 1, sizeof(buf)); copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); ret = copy_to_user(release, buf, copy + 1); } return ret; } SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) { struct new_utsname tmp; down_read(&uts_sem); memcpy(&tmp, utsname(), sizeof(tmp)); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; if (override_architecture(name)) return -EFAULT; return 0; } #ifdef __ARCH_WANT_SYS_OLD_UNAME /* * Old cruft */ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) { struct old_utsname tmp; if (!name) return -EFAULT; down_read(&uts_sem); memcpy(&tmp, utsname(), sizeof(tmp)); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; if (override_architecture(name)) return -EFAULT; return 0; } SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { struct oldold_utsname tmp; if (!name) return -EFAULT; memset(&tmp, 0, sizeof(tmp)); down_read(&uts_sem); memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN); memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN); memcpy(&tmp.release, &utsname()->release, __OLD_UTS_LEN); memcpy(&tmp.version, &utsname()->version, __OLD_UTS_LEN); memcpy(&tmp.machine, &utsname()->machine, __OLD_UTS_LEN); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_architecture(name)) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; return 0; } #endif SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) { int errno; char tmp[__NEW_UTS_LEN]; if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { struct new_utsname *u; add_device_randomness(tmp, len); down_write(&uts_sem); u = utsname(); memcpy(u->nodename, tmp, len); memset(u->nodename + len, 0, sizeof(u->nodename) - len); errno = 0; uts_proc_notify(UTS_PROC_HOSTNAME); up_write(&uts_sem); } return errno; } #ifdef __ARCH_WANT_SYS_GETHOSTNAME SYSCALL_DEFINE2(gethostname, char __user *, name, int, len) { int i; struct new_utsname *u; char tmp[__NEW_UTS_LEN + 1]; if (len < 0) return -EINVAL; down_read(&uts_sem); u = utsname(); i = 1 + strlen(u->nodename); if (i > len) i = len; memcpy(tmp, u->nodename, i); up_read(&uts_sem); if (copy_to_user(name, tmp, i)) return -EFAULT; return 0; } #endif /* * Only setdomainname; getdomainname can be implemented by calling * uname() */ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) { int errno; char tmp[__NEW_UTS_LEN]; if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { struct new_utsname *u; add_device_randomness(tmp, len); down_write(&uts_sem); u = utsname(); memcpy(u->domainname, tmp, len); memset(u->domainname + len, 0, sizeof(u->domainname) - len); errno = 0; uts_proc_notify(UTS_PROC_DOMAINNAME); up_write(&uts_sem); } return errno; } /* make sure you are allowed to change @tsk limits before calling this */ static int do_prlimit(struct task_struct *tsk, unsigned int resource, struct rlimit *new_rlim, struct rlimit *old_rlim) { struct rlimit *rlim; int retval = 0; if (resource >= RLIM_NLIMITS) return -EINVAL; resource = array_index_nospec(resource, RLIM_NLIMITS); if (new_rlim) { if (new_rlim->rlim_cur > new_rlim->rlim_max) return -EINVAL; if (resource == RLIMIT_NOFILE && new_rlim->rlim_max > sysctl_nr_open) return -EPERM; } /* Holding a refcount on tsk protects tsk->signal from disappearing. */ rlim = tsk->signal->rlim + resource; task_lock(tsk->group_leader); if (new_rlim) { /* * Keep the capable check against init_user_ns until cgroups can * contain all limits. */ if (new_rlim->rlim_max > rlim->rlim_max && !capable(CAP_SYS_RESOURCE)) retval = -EPERM; if (!retval) retval = security_task_setrlimit(tsk, resource, new_rlim); } if (!retval) { if (old_rlim) *old_rlim = *rlim; if (new_rlim) *rlim = *new_rlim; } task_unlock(tsk->group_leader); /* * RLIMIT_CPU handling. Arm the posix CPU timer if the limit is not * infinite. In case of RLIM_INFINITY the posix CPU timer code * ignores the rlimit. */ if (!retval && new_rlim && resource == RLIMIT_CPU && new_rlim->rlim_cur != RLIM_INFINITY && IS_ENABLED(CONFIG_POSIX_TIMERS)) { /* * update_rlimit_cpu can fail if the task is exiting, but there * may be other tasks in the thread group that are not exiting, * and they need their cpu timers adjusted. * * The group_leader is the last task to be released, so if we * cannot update_rlimit_cpu on it, then the entire process is * exiting and we do not need to update at all. */ update_rlimit_cpu(tsk->group_leader, new_rlim->rlim_cur); } return retval; } SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit value; int ret; ret = do_prlimit(current, resource, NULL, &value); if (!ret) ret = copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0; return ret; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; struct compat_rlimit r32; if (copy_from_user(&r32, rlim, sizeof(struct compat_rlimit))) return -EFAULT; if (r32.rlim_cur == COMPAT_RLIM_INFINITY) r.rlim_cur = RLIM_INFINITY; else r.rlim_cur = r32.rlim_cur; if (r32.rlim_max == COMPAT_RLIM_INFINITY) r.rlim_max = RLIM_INFINITY; else r.rlim_max = r32.rlim_max; return do_prlimit(current, resource, &r, NULL); } COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; int ret; ret = do_prlimit(current, resource, NULL, &r); if (!ret) { struct compat_rlimit r32; if (r.rlim_cur > COMPAT_RLIM_INFINITY) r32.rlim_cur = COMPAT_RLIM_INFINITY; else r32.rlim_cur = r.rlim_cur; if (r.rlim_max > COMPAT_RLIM_INFINITY) r32.rlim_max = COMPAT_RLIM_INFINITY; else r32.rlim_max = r.rlim_max; if (copy_to_user(rlim, &r32, sizeof(struct compat_rlimit))) return -EFAULT; } return ret; } #endif #ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT /* * Back compatibility for getrlimit. Needed for some apps. */ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit x; if (resource >= RLIM_NLIMITS) return -EINVAL; resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); x = current->signal->rlim[resource]; task_unlock(current->group_leader); if (x.rlim_cur > 0x7FFFFFFF) x.rlim_cur = 0x7FFFFFFF; if (x.rlim_max > 0x7FFFFFFF) x.rlim_max = 0x7FFFFFFF; return copy_to_user(rlim, &x, sizeof(x)) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; if (resource >= RLIM_NLIMITS) return -EINVAL; resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); r = current->signal->rlim[resource]; task_unlock(current->group_leader); if (r.rlim_cur > 0x7FFFFFFF) r.rlim_cur = 0x7FFFFFFF; if (r.rlim_max > 0x7FFFFFFF) r.rlim_max = 0x7FFFFFFF; if (put_user(r.rlim_cur, &rlim->rlim_cur) || put_user(r.rlim_max, &rlim->rlim_max)) return -EFAULT; return 0; } #endif #endif static inline bool rlim64_is_infinity(__u64 rlim64) { #if BITS_PER_LONG < 64 return rlim64 >= ULONG_MAX; #else return rlim64 == RLIM64_INFINITY; #endif } static void rlim_to_rlim64(const struct rlimit *rlim, struct rlimit64 *rlim64) { if (rlim->rlim_cur == RLIM_INFINITY) rlim64->rlim_cur = RLIM64_INFINITY; else rlim64->rlim_cur = rlim->rlim_cur; if (rlim->rlim_max == RLIM_INFINITY) rlim64->rlim_max = RLIM64_INFINITY; else rlim64->rlim_max = rlim->rlim_max; } static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim) { if (rlim64_is_infinity(rlim64->rlim_cur)) rlim->rlim_cur = RLIM_INFINITY; else rlim->rlim_cur = (unsigned long)rlim64->rlim_cur; if (rlim64_is_infinity(rlim64->rlim_max)) rlim->rlim_max = RLIM_INFINITY; else rlim->rlim_max = (unsigned long)rlim64->rlim_max; } /* rcu lock must be held */ static int check_prlimit_permission(struct task_struct *task, unsigned int flags) { const struct cred *cred = current_cred(), *tcred; bool id_match; if (current == task) return 0; tcred = __task_cred(task); id_match = (uid_eq(cred->uid, tcred->euid) && uid_eq(cred->uid, tcred->suid) && uid_eq(cred->uid, tcred->uid) && gid_eq(cred->gid, tcred->egid) && gid_eq(cred->gid, tcred->sgid) && gid_eq(cred->gid, tcred->gid)); if (!id_match && !ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) return -EPERM; return security_task_prlimit(cred, tcred, flags); } SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim) { struct rlimit64 old64, new64; struct rlimit old, new; struct task_struct *tsk; unsigned int checkflags = 0; int ret; if (old_rlim) checkflags |= LSM_PRLIMIT_READ; if (new_rlim) { if (copy_from_user(&new64, new_rlim, sizeof(new64))) return -EFAULT; rlim64_to_rlim(&new64, &new); checkflags |= LSM_PRLIMIT_WRITE; } rcu_read_lock(); tsk = pid ? find_task_by_vpid(pid) : current; if (!tsk) { rcu_read_unlock(); return -ESRCH; } ret = check_prlimit_permission(tsk, checkflags); if (ret) { rcu_read_unlock(); return ret; } get_task_struct(tsk); rcu_read_unlock(); ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL, old_rlim ? &old : NULL); if (!ret && old_rlim) { rlim_to_rlim64(&old, &old64); if (copy_to_user(old_rlim, &old64, sizeof(old64))) ret = -EFAULT; } put_task_struct(tsk); return ret; } SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit new_rlim; if (copy_from_user(&new_rlim, rlim, sizeof(*rlim))) return -EFAULT; return do_prlimit(current, resource, &new_rlim, NULL); } /* * It would make sense to put struct rusage in the task_struct, * except that would make the task_struct be *really big*. After * task_struct gets moved into malloc'ed memory, it would * make sense to do this. It will make moving the rest of the information * a lot simpler! (Which we're not doing right now because we're not * measuring them yet). * * When sampling multiple threads for RUSAGE_SELF, under SMP we might have * races with threads incrementing their own counters. But since word * reads are atomic, we either get new values or old values and we don't * care which for the sums. We always take the siglock to protect reading * the c* fields from p->signal from races with exit.c updating those * fields when reaping, so a sample either gets all the additions of a * given child after it's reaped, or none so this sample is before reaping. * * Locking: * We need to take the siglock for CHILDEREN, SELF and BOTH * for the cases current multithreaded, non-current single threaded * non-current multithreaded. Thread traversal is now safe with * the siglock held. * Strictly speaking, we donot need to take the siglock if we are current and * single threaded, as no one else can take our signal_struct away, no one * else can reap the children to update signal->c* counters, and no one else * can race with the signal-> fields. If we do not take any lock, the * signal-> fields could be read out of order while another thread was just * exiting. So we should place a read memory barrier when we avoid the lock. * On the writer side, write memory barrier is implied in __exit_signal * as __exit_signal releases the siglock spinlock after updating the signal-> * fields. But we don't do this yet to keep things simple. * */ static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) { r->ru_nvcsw += t->nvcsw; r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; r->ru_majflt += t->maj_flt; r->ru_inblock += task_io_get_inblock(t); r->ru_oublock += task_io_get_oublock(t); } void getrusage(struct task_struct *p, int who, struct rusage *r) { struct task_struct *t; unsigned long flags; u64 tgutime, tgstime, utime, stime; unsigned long maxrss; struct mm_struct *mm; struct signal_struct *sig = p->signal; unsigned int seq = 0; retry: memset(r, 0, sizeof(*r)); utime = stime = 0; maxrss = 0; if (who == RUSAGE_THREAD) { task_cputime_adjusted(current, &utime, &stime); accumulate_thread_rusage(p, r); maxrss = sig->maxrss; goto out_thread; } flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); switch (who) { case RUSAGE_BOTH: case RUSAGE_CHILDREN: utime = sig->cutime; stime = sig->cstime; r->ru_nvcsw = sig->cnvcsw; r->ru_nivcsw = sig->cnivcsw; r->ru_minflt = sig->cmin_flt; r->ru_majflt = sig->cmaj_flt; r->ru_inblock = sig->cinblock; r->ru_oublock = sig->coublock; maxrss = sig->cmaxrss; if (who == RUSAGE_CHILDREN) break; fallthrough; case RUSAGE_SELF: r->ru_nvcsw += sig->nvcsw; r->ru_nivcsw += sig->nivcsw; r->ru_minflt += sig->min_flt; r->ru_majflt += sig->maj_flt; r->ru_inblock += sig->inblock; r->ru_oublock += sig->oublock; if (maxrss < sig->maxrss) maxrss = sig->maxrss; rcu_read_lock(); __for_each_thread(sig, t) accumulate_thread_rusage(t, r); rcu_read_unlock(); break; default: BUG(); } if (need_seqretry(&sig->stats_lock, seq)) { seq = 1; goto retry; } done_seqretry_irqrestore(&sig->stats_lock, seq, flags); if (who == RUSAGE_CHILDREN) goto out_children; thread_group_cputime_adjusted(p, &tgutime, &tgstime); utime += tgutime; stime += tgstime; out_thread: mm = get_task_mm(p); if (mm) { setmax_mm_hiwater_rss(&maxrss, mm); mmput(mm); } out_children: r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ r->ru_utime = ns_to_kernel_old_timeval(utime); r->ru_stime = ns_to_kernel_old_timeval(stime); } SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) { struct rusage r; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) return -EINVAL; getrusage(current, who, &r); return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(getrusage, int, who, struct compat_rusage __user *, ru) { struct rusage r; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) return -EINVAL; getrusage(current, who, &r); return put_compat_rusage(&r, ru); } #endif SYSCALL_DEFINE1(umask, int, mask) { mask = xchg(¤t->fs->umask, mask & S_IRWXUGO); return mask; } static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) { CLASS(fd, exe)(fd); struct inode *inode; int err; if (fd_empty(exe)) return -EBADF; inode = file_inode(fd_file(exe)); /* * Because the original mm->exe_file points to executable file, make * sure that this one is executable as well, to avoid breaking an * overall picture. */ if (!S_ISREG(inode->i_mode) || path_noexec(&fd_file(exe)->f_path)) return -EACCES; err = file_permission(fd_file(exe), MAY_EXEC); if (err) return err; return replace_mm_exe_file(mm, fd_file(exe)); } /* * Check arithmetic relations of passed addresses. * * WARNING: we don't require any capability here so be very careful * in what is allowed for modification from userspace. */ static int validate_prctl_map_addr(struct prctl_mm_map *prctl_map) { unsigned long mmap_max_addr = TASK_SIZE; int error = -EINVAL, i; static const unsigned char offsets[] = { offsetof(struct prctl_mm_map, start_code), offsetof(struct prctl_mm_map, end_code), offsetof(struct prctl_mm_map, start_data), offsetof(struct prctl_mm_map, end_data), offsetof(struct prctl_mm_map, start_brk), offsetof(struct prctl_mm_map, brk), offsetof(struct prctl_mm_map, start_stack), offsetof(struct prctl_mm_map, arg_start), offsetof(struct prctl_mm_map, arg_end), offsetof(struct prctl_mm_map, env_start), offsetof(struct prctl_mm_map, env_end), }; /* * Make sure the members are not somewhere outside * of allowed address space. */ for (i = 0; i < ARRAY_SIZE(offsets); i++) { u64 val = *(u64 *)((char *)prctl_map + offsets[i]); if ((unsigned long)val >= mmap_max_addr || (unsigned long)val < mmap_min_addr) goto out; } /* * Make sure the pairs are ordered. */ #define __prctl_check_order(__m1, __op, __m2) \ ((unsigned long)prctl_map->__m1 __op \ (unsigned long)prctl_map->__m2) ? 0 : -EINVAL error = __prctl_check_order(start_code, <, end_code); error |= __prctl_check_order(start_data,<=, end_data); error |= __prctl_check_order(start_brk, <=, brk); error |= __prctl_check_order(arg_start, <=, arg_end); error |= __prctl_check_order(env_start, <=, env_end); if (error) goto out; #undef __prctl_check_order error = -EINVAL; /* * Neither we should allow to override limits if they set. */ if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk, prctl_map->start_brk, prctl_map->end_data, prctl_map->start_data)) goto out; error = 0; out: return error; } #ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size) { struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, }; unsigned long user_auxv[AT_VECTOR_SIZE]; struct mm_struct *mm = current->mm; int error; BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); BUILD_BUG_ON(sizeof(struct prctl_mm_map) > 256); if (opt == PR_SET_MM_MAP_SIZE) return put_user((unsigned int)sizeof(prctl_map), (unsigned int __user *)addr); if (data_size != sizeof(prctl_map)) return -EINVAL; if (copy_from_user(&prctl_map, addr, sizeof(prctl_map))) return -EFAULT; error = validate_prctl_map_addr(&prctl_map); if (error) return error; if (prctl_map.auxv_size) { /* * Someone is trying to cheat the auxv vector. */ if (!prctl_map.auxv || prctl_map.auxv_size > sizeof(mm->saved_auxv)) return -EINVAL; memset(user_auxv, 0, sizeof(user_auxv)); if (copy_from_user(user_auxv, (const void __user *)prctl_map.auxv, prctl_map.auxv_size)) return -EFAULT; /* Last entry must be AT_NULL as specification requires */ user_auxv[AT_VECTOR_SIZE - 2] = AT_NULL; user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL; } if (prctl_map.exe_fd != (u32)-1) { /* * Check if the current user is checkpoint/restore capable. * At the time of this writing, it checks for CAP_SYS_ADMIN * or CAP_CHECKPOINT_RESTORE. * Note that a user with access to ptrace can masquerade an * arbitrary program as any executable, even setuid ones. * This may have implications in the tomoyo subsystem. */ if (!checkpoint_restore_ns_capable(current_user_ns())) return -EPERM; error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd); if (error) return error; } /* * arg_lock protects concurrent updates but we still need mmap_lock for * read to exclude races with sys_brk. */ mmap_read_lock(mm); /* * We don't validate if these members are pointing to * real present VMAs because application may have correspond * VMAs already unmapped and kernel uses these members for statistics * output in procfs mostly, except * * - @start_brk/@brk which are used in do_brk_flags but kernel lookups * for VMAs when updating these members so anything wrong written * here cause kernel to swear at userspace program but won't lead * to any problem in kernel itself */ spin_lock(&mm->arg_lock); mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; mm->end_data = prctl_map.end_data; mm->start_brk = prctl_map.start_brk; mm->brk = prctl_map.brk; mm->start_stack = prctl_map.start_stack; mm->arg_start = prctl_map.arg_start; mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; spin_unlock(&mm->arg_lock); /* * Note this update of @saved_auxv is lockless thus * if someone reads this member in procfs while we're * updating -- it may get partly updated results. It's * known and acceptable trade off: we leave it as is to * not introduce additional locks here making the kernel * more complex. */ if (prctl_map.auxv_size) memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); mmap_read_unlock(mm); return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr, unsigned long len) { /* * This doesn't move the auxiliary vector itself since it's pinned to * mm_struct, but it permits filling the vector with new values. It's * up to the caller to provide sane values here, otherwise userspace * tools which use this vector might be unhappy. */ unsigned long user_auxv[AT_VECTOR_SIZE] = {}; if (len > sizeof(user_auxv)) return -EINVAL; if (copy_from_user(user_auxv, (const void __user *)addr, len)) return -EFAULT; /* Make sure the last entry is always AT_NULL */ user_auxv[AT_VECTOR_SIZE - 2] = 0; user_auxv[AT_VECTOR_SIZE - 1] = 0; BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); task_lock(current); memcpy(mm->saved_auxv, user_auxv, len); task_unlock(current); return 0; } static int prctl_set_mm(int opt, unsigned long addr, unsigned long arg4, unsigned long arg5) { struct mm_struct *mm = current->mm; struct prctl_mm_map prctl_map = { .auxv = NULL, .auxv_size = 0, .exe_fd = -1, }; struct vm_area_struct *vma; int error; if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV && opt != PR_SET_MM_MAP && opt != PR_SET_MM_MAP_SIZE))) return -EINVAL; #ifdef CONFIG_CHECKPOINT_RESTORE if (opt == PR_SET_MM_MAP || opt == PR_SET_MM_MAP_SIZE) return prctl_set_mm_map(opt, (const void __user *)addr, arg4); #endif if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (opt == PR_SET_MM_EXE_FILE) return prctl_set_mm_exe_file(mm, (unsigned int)addr); if (opt == PR_SET_MM_AUXV) return prctl_set_auxv(mm, addr, arg4); if (addr >= TASK_SIZE || addr < mmap_min_addr) return -EINVAL; error = -EINVAL; /* * arg_lock protects concurrent updates of arg boundaries, we need * mmap_lock for a) concurrent sys_brk, b) finding VMA for addr * validation. */ mmap_read_lock(mm); vma = find_vma(mm, addr); spin_lock(&mm->arg_lock); prctl_map.start_code = mm->start_code; prctl_map.end_code = mm->end_code; prctl_map.start_data = mm->start_data; prctl_map.end_data = mm->end_data; prctl_map.start_brk = mm->start_brk; prctl_map.brk = mm->brk; prctl_map.start_stack = mm->start_stack; prctl_map.arg_start = mm->arg_start; prctl_map.arg_end = mm->arg_end; prctl_map.env_start = mm->env_start; prctl_map.env_end = mm->env_end; switch (opt) { case PR_SET_MM_START_CODE: prctl_map.start_code = addr; break; case PR_SET_MM_END_CODE: prctl_map.end_code = addr; break; case PR_SET_MM_START_DATA: prctl_map.start_data = addr; break; case PR_SET_MM_END_DATA: prctl_map.end_data = addr; break; case PR_SET_MM_START_STACK: prctl_map.start_stack = addr; break; case PR_SET_MM_START_BRK: prctl_map.start_brk = addr; break; case PR_SET_MM_BRK: prctl_map.brk = addr; break; case PR_SET_MM_ARG_START: prctl_map.arg_start = addr; break; case PR_SET_MM_ARG_END: prctl_map.arg_end = addr; break; case PR_SET_MM_ENV_START: prctl_map.env_start = addr; break; case PR_SET_MM_ENV_END: prctl_map.env_end = addr; break; default: goto out; } error = validate_prctl_map_addr(&prctl_map); if (error) goto out; switch (opt) { /* * If command line arguments and environment * are placed somewhere else on stack, we can * set them up here, ARG_START/END to setup * command line arguments and ENV_START/END * for environment. */ case PR_SET_MM_START_STACK: case PR_SET_MM_ARG_START: case PR_SET_MM_ARG_END: case PR_SET_MM_ENV_START: case PR_SET_MM_ENV_END: if (!vma) { error = -EFAULT; goto out; } } mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; mm->end_data = prctl_map.end_data; mm->start_brk = prctl_map.start_brk; mm->brk = prctl_map.brk; mm->start_stack = prctl_map.start_stack; mm->arg_start = prctl_map.arg_start; mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; error = 0; out: spin_unlock(&mm->arg_lock); mmap_read_unlock(mm); return error; } #ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr) { return put_user(me->clear_child_tid, tid_addr); } #else static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr) { return -EINVAL; } #endif static int propagate_has_child_subreaper(struct task_struct *p, void *data) { /* * If task has has_child_subreaper - all its descendants * already have these flag too and new descendants will * inherit it on fork, skip them. * * If we've found child_reaper - skip descendants in * it's subtree as they will never get out pidns. */ if (p->signal->has_child_subreaper || is_child_reaper(task_pid(p))) return 0; p->signal->has_child_subreaper = 1; return 1; } int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which) { return -EINVAL; } int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, unsigned long ctrl) { return -EINVAL; } int __weak arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status) { return -EINVAL; } int __weak arch_set_shadow_stack_status(struct task_struct *t, unsigned long status) { return -EINVAL; } int __weak arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status) { return -EINVAL; } #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE) #ifdef CONFIG_ANON_VMA_NAME #define ANON_VMA_NAME_MAX_LEN 80 #define ANON_VMA_NAME_INVALID_CHARS "\\`$[]" static inline bool is_valid_name_char(char ch) { /* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */ return ch > 0x1f && ch < 0x7f && !strchr(ANON_VMA_NAME_INVALID_CHARS, ch); } static int prctl_set_vma(unsigned long opt, unsigned long addr, unsigned long size, unsigned long arg) { struct mm_struct *mm = current->mm; const char __user *uname; struct anon_vma_name *anon_name = NULL; int error; switch (opt) { case PR_SET_VMA_ANON_NAME: uname = (const char __user *)arg; if (uname) { char *name, *pch; name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); if (IS_ERR(name)) return PTR_ERR(name); for (pch = name; *pch != '\0'; pch++) { if (!is_valid_name_char(*pch)) { kfree(name); return -EINVAL; } } /* anon_vma has its own copy */ anon_name = anon_vma_name_alloc(name); kfree(name); if (!anon_name) return -ENOMEM; } mmap_write_lock(mm); error = madvise_set_anon_name(mm, addr, size, anon_name); mmap_write_unlock(mm); anon_vma_name_put(anon_name); break; default: error = -EINVAL; } return error; } #else /* CONFIG_ANON_VMA_NAME */ static int prctl_set_vma(unsigned long opt, unsigned long start, unsigned long size, unsigned long arg) { return -EINVAL; } #endif /* CONFIG_ANON_VMA_NAME */ static inline unsigned long get_current_mdwe(void) { unsigned long ret = 0; if (test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) ret |= PR_MDWE_REFUSE_EXEC_GAIN; if (test_bit(MMF_HAS_MDWE_NO_INHERIT, ¤t->mm->flags)) ret |= PR_MDWE_NO_INHERIT; return ret; } static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, unsigned long arg4, unsigned long arg5) { unsigned long current_bits; if (arg3 || arg4 || arg5) return -EINVAL; if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT)) return -EINVAL; /* NO_INHERIT only makes sense with REFUSE_EXEC_GAIN */ if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN)) return -EINVAL; /* * EOPNOTSUPP might be more appropriate here in principle, but * existing userspace depends on EINVAL specifically. */ if (!arch_memory_deny_write_exec_supported()) return -EINVAL; current_bits = get_current_mdwe(); if (current_bits && current_bits != bits) return -EPERM; /* Cannot unset the flags */ if (bits & PR_MDWE_NO_INHERIT) set_bit(MMF_HAS_MDWE_NO_INHERIT, ¤t->mm->flags); if (bits & PR_MDWE_REFUSE_EXEC_GAIN) set_bit(MMF_HAS_MDWE, ¤t->mm->flags); return 0; } static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { if (arg2 || arg3 || arg4 || arg5) return -EINVAL; return get_current_mdwe(); } static int prctl_get_auxv(void __user *addr, unsigned long len) { struct mm_struct *mm = current->mm; unsigned long size = min_t(unsigned long, sizeof(mm->saved_auxv), len); if (size && copy_to_user(addr, mm->saved_auxv, size)) return -EFAULT; return sizeof(mm->saved_auxv); } SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { struct task_struct *me = current; unsigned char comm[sizeof(me->comm)]; long error; error = security_task_prctl(option, arg2, arg3, arg4, arg5); if (error != -ENOSYS) return error; error = 0; switch (option) { case PR_SET_PDEATHSIG: if (!valid_signal(arg2)) { error = -EINVAL; break; } me->pdeath_signal = arg2; break; case PR_GET_PDEATHSIG: error = put_user(me->pdeath_signal, (int __user *)arg2); break; case PR_GET_DUMPABLE: error = get_dumpable(me->mm); break; case PR_SET_DUMPABLE: if (arg2 != SUID_DUMP_DISABLE && arg2 != SUID_DUMP_USER) { error = -EINVAL; break; } set_dumpable(me->mm, arg2); break; case PR_SET_UNALIGN: error = SET_UNALIGN_CTL(me, arg2); break; case PR_GET_UNALIGN: error = GET_UNALIGN_CTL(me, arg2); break; case PR_SET_FPEMU: error = SET_FPEMU_CTL(me, arg2); break; case PR_GET_FPEMU: error = GET_FPEMU_CTL(me, arg2); break; case PR_SET_FPEXC: error = SET_FPEXC_CTL(me, arg2); break; case PR_GET_FPEXC: error = GET_FPEXC_CTL(me, arg2); break; case PR_GET_TIMING: error = PR_TIMING_STATISTICAL; break; case PR_SET_TIMING: if (arg2 != PR_TIMING_STATISTICAL) error = -EINVAL; break; case PR_SET_NAME: comm[sizeof(me->comm) - 1] = 0; if (strncpy_from_user(comm, (char __user *)arg2, sizeof(me->comm) - 1) < 0) return -EFAULT; set_task_comm(me, comm); proc_comm_connector(me); break; case PR_GET_NAME: get_task_comm(comm, me); if (copy_to_user((char __user *)arg2, comm, sizeof(comm))) return -EFAULT; break; case PR_GET_ENDIAN: error = GET_ENDIAN(me, arg2); break; case PR_SET_ENDIAN: error = SET_ENDIAN(me, arg2); break; case PR_GET_SECCOMP: error = prctl_get_seccomp(); break; case PR_SET_SECCOMP: error = prctl_set_seccomp(arg2, (char __user *)arg3); break; case PR_GET_TSC: error = GET_TSC_CTL(arg2); break; case PR_SET_TSC: error = SET_TSC_CTL(arg2); break; case PR_TASK_PERF_EVENTS_DISABLE: error = perf_event_task_disable(); break; case PR_TASK_PERF_EVENTS_ENABLE: error = perf_event_task_enable(); break; case PR_GET_TIMERSLACK: if (current->timer_slack_ns > ULONG_MAX) error = ULONG_MAX; else error = current->timer_slack_ns; break; case PR_SET_TIMERSLACK: if (rt_or_dl_task_policy(current)) break; if (arg2 <= 0) current->timer_slack_ns = current->default_timer_slack_ns; else current->timer_slack_ns = arg2; break; case PR_MCE_KILL: if (arg4 | arg5) return -EINVAL; switch (arg2) { case PR_MCE_KILL_CLEAR: if (arg3 != 0) return -EINVAL; current->flags &= ~PF_MCE_PROCESS; break; case PR_MCE_KILL_SET: current->flags |= PF_MCE_PROCESS; if (arg3 == PR_MCE_KILL_EARLY) current->flags |= PF_MCE_EARLY; else if (arg3 == PR_MCE_KILL_LATE) current->flags &= ~PF_MCE_EARLY; else if (arg3 == PR_MCE_KILL_DEFAULT) current->flags &= ~(PF_MCE_EARLY|PF_MCE_PROCESS); else return -EINVAL; break; default: return -EINVAL; } break; case PR_MCE_KILL_GET: if (arg2 | arg3 | arg4 | arg5) return -EINVAL; if (current->flags & PF_MCE_PROCESS) error = (current->flags & PF_MCE_EARLY) ? PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE; else error = PR_MCE_KILL_DEFAULT; break; case PR_SET_MM: error = prctl_set_mm(arg2, arg3, arg4, arg5); break; case PR_GET_TID_ADDRESS: error = prctl_get_tid_address(me, (int __user * __user *)arg2); break; case PR_SET_CHILD_SUBREAPER: me->signal->is_child_subreaper = !!arg2; if (!arg2) break; walk_process_tree(me, propagate_has_child_subreaper, NULL); break; case PR_GET_CHILD_SUBREAPER: error = put_user(me->signal->is_child_subreaper, (int __user *)arg2); break; case PR_SET_NO_NEW_PRIVS: if (arg2 != 1 || arg3 || arg4 || arg5) return -EINVAL; task_set_no_new_privs(current); break; case PR_GET_NO_NEW_PRIVS: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; return task_no_new_privs(current) ? 1 : 0; case PR_GET_THP_DISABLE: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = !!test_bit(MMF_DISABLE_THP, &me->mm->flags); break; case PR_SET_THP_DISABLE: if (arg3 || arg4 || arg5) return -EINVAL; if (mmap_write_lock_killable(me->mm)) return -EINTR; if (arg2) set_bit(MMF_DISABLE_THP, &me->mm->flags); else clear_bit(MMF_DISABLE_THP, &me->mm->flags); mmap_write_unlock(me->mm); break; case PR_MPX_ENABLE_MANAGEMENT: case PR_MPX_DISABLE_MANAGEMENT: /* No longer implemented: */ return -EINVAL; case PR_SET_FP_MODE: error = SET_FP_MODE(me, arg2); break; case PR_GET_FP_MODE: error = GET_FP_MODE(me); break; case PR_SVE_SET_VL: error = SVE_SET_VL(arg2); break; case PR_SVE_GET_VL: error = SVE_GET_VL(); break; case PR_SME_SET_VL: error = SME_SET_VL(arg2); break; case PR_SME_GET_VL: error = SME_GET_VL(); break; case PR_GET_SPECULATION_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; error = arch_prctl_spec_ctrl_get(me, arg2); break; case PR_SET_SPECULATION_CTRL: if (arg4 || arg5) return -EINVAL; error = arch_prctl_spec_ctrl_set(me, arg2, arg3); break; case PR_PAC_RESET_KEYS: if (arg3 || arg4 || arg5) return -EINVAL; error = PAC_RESET_KEYS(me, arg2); break; case PR_PAC_SET_ENABLED_KEYS: if (arg4 || arg5) return -EINVAL; error = PAC_SET_ENABLED_KEYS(me, arg2, arg3); break; case PR_PAC_GET_ENABLED_KEYS: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = PAC_GET_ENABLED_KEYS(me); break; case PR_SET_TAGGED_ADDR_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; error = SET_TAGGED_ADDR_CTRL(arg2); break; case PR_GET_TAGGED_ADDR_CTRL: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = GET_TAGGED_ADDR_CTRL(); break; case PR_SET_IO_FLUSHER: if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (arg3 || arg4 || arg5) return -EINVAL; if (arg2 == 1) current->flags |= PR_IO_FLUSHER; else if (!arg2) current->flags &= ~PR_IO_FLUSHER; else return -EINVAL; break; case PR_GET_IO_FLUSHER: if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER; break; case PR_SET_SYSCALL_USER_DISPATCH: error = set_syscall_user_dispatch(arg2, arg3, arg4, (char __user *) arg5); break; #ifdef CONFIG_SCHED_CORE case PR_SCHED_CORE: error = sched_core_share_pid(arg2, arg3, arg4, arg5); break; #endif case PR_SET_MDWE: error = prctl_set_mdwe(arg2, arg3, arg4, arg5); break; case PR_GET_MDWE: error = prctl_get_mdwe(arg2, arg3, arg4, arg5); break; case PR_PPC_GET_DEXCR: if (arg3 || arg4 || arg5) return -EINVAL; error = PPC_GET_DEXCR_ASPECT(me, arg2); break; case PR_PPC_SET_DEXCR: if (arg4 || arg5) return -EINVAL; error = PPC_SET_DEXCR_ASPECT(me, arg2, arg3); break; case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; case PR_GET_AUXV: if (arg4 || arg5) return -EINVAL; error = prctl_get_auxv((void __user *)arg2, arg3); break; #ifdef CONFIG_KSM case PR_SET_MEMORY_MERGE: if (arg3 || arg4 || arg5) return -EINVAL; if (mmap_write_lock_killable(me->mm)) return -EINTR; if (arg2) error = ksm_enable_merge_any(me->mm); else error = ksm_disable_merge_any(me->mm); mmap_write_unlock(me->mm); break; case PR_GET_MEMORY_MERGE: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = !!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags); break; #endif case PR_RISCV_V_SET_CONTROL: error = RISCV_V_SET_CONTROL(arg2); break; case PR_RISCV_V_GET_CONTROL: error = RISCV_V_GET_CONTROL(); break; case PR_RISCV_SET_ICACHE_FLUSH_CTX: error = RISCV_SET_ICACHE_FLUSH_CTX(arg2, arg3); break; case PR_GET_SHADOW_STACK_STATUS: if (arg3 || arg4 || arg5) return -EINVAL; error = arch_get_shadow_stack_status(me, (unsigned long __user *) arg2); break; case PR_SET_SHADOW_STACK_STATUS: if (arg3 || arg4 || arg5) return -EINVAL; error = arch_set_shadow_stack_status(me, arg2); break; case PR_LOCK_SHADOW_STACK_STATUS: if (arg3 || arg4 || arg5) return -EINVAL; error = arch_lock_shadow_stack_status(me, arg2); break; case PR_TIMER_CREATE_RESTORE_IDS: if (arg3 || arg4 || arg5) return -EINVAL; error = posixtimer_create_prctl(arg2); break; default: trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5); error = -EINVAL; break; } return error; } SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, struct getcpu_cache __user *, unused) { int err = 0; int cpu = raw_smp_processor_id(); if (cpup) err |= put_user(cpu, cpup); if (nodep) err |= put_user(cpu_to_node(cpu), nodep); return err ? -EFAULT : 0; } /** * do_sysinfo - fill in sysinfo struct * @info: pointer to buffer to fill */ static int do_sysinfo(struct sysinfo *info) { unsigned long mem_total, sav_total; unsigned int mem_unit, bitcount; struct timespec64 tp; memset(info, 0, sizeof(struct sysinfo)); ktime_get_boottime_ts64(&tp); timens_add_boottime(&tp); info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); info->procs = nr_threads; si_meminfo(info); si_swapinfo(info); /* * If the sum of all the available memory (i.e. ram + swap) * is less than can be stored in a 32 bit unsigned long then * we can be binary compatible with 2.2.x kernels. If not, * well, in that case 2.2.x was broken anyways... * * -Erik Andersen <andersee@debian.org> */ mem_total = info->totalram + info->totalswap; if (mem_total < info->totalram || mem_total < info->totalswap) goto out; bitcount = 0; mem_unit = info->mem_unit; while (mem_unit > 1) { bitcount++; mem_unit >>= 1; sav_total = mem_total; mem_total <<= 1; if (mem_total < sav_total) goto out; } /* * If mem_total did not overflow, multiply all memory values by * info->mem_unit and set it to 1. This leaves things compatible * with 2.2.x, and also retains compatibility with earlier 2.4.x * kernels... */ info->mem_unit = 1; info->totalram <<= bitcount; info->freeram <<= bitcount; info->sharedram <<= bitcount; info->bufferram <<= bitcount; info->totalswap <<= bitcount; info->freeswap <<= bitcount; info->totalhigh <<= bitcount; info->freehigh <<= bitcount; out: return 0; } SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info) { struct sysinfo val; do_sysinfo(&val); if (copy_to_user(info, &val, sizeof(struct sysinfo))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT struct compat_sysinfo { s32 uptime; u32 loads[3]; u32 totalram; u32 freeram; u32 sharedram; u32 bufferram; u32 totalswap; u32 freeswap; u16 procs; u16 pad; u32 totalhigh; u32 freehigh; u32 mem_unit; char _f[20-2*sizeof(u32)-sizeof(int)]; }; COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info) { struct sysinfo s; struct compat_sysinfo s_32; do_sysinfo(&s); /* Check to see if any memory value is too large for 32-bit and scale * down if needed */ if (upper_32_bits(s.totalram) || upper_32_bits(s.totalswap)) { int bitcount = 0; while (s.mem_unit < PAGE_SIZE) { s.mem_unit <<= 1; bitcount++; } s.totalram >>= bitcount; s.freeram >>= bitcount; s.sharedram >>= bitcount; s.bufferram >>= bitcount; s.totalswap >>= bitcount; s.freeswap >>= bitcount; s.totalhigh >>= bitcount; s.freehigh >>= bitcount; } memset(&s_32, 0, sizeof(s_32)); s_32.uptime = s.uptime; s_32.loads[0] = s.loads[0]; s_32.loads[1] = s.loads[1]; s_32.loads[2] = s.loads[2]; s_32.totalram = s.totalram; s_32.freeram = s.freeram; s_32.sharedram = s.sharedram; s_32.bufferram = s.bufferram; s_32.totalswap = s.totalswap; s_32.freeswap = s.freeswap; s_32.procs = s.procs; s_32.totalhigh = s.totalhigh; s_32.freehigh = s.freehigh; s_32.mem_unit = s.mem_unit; if (copy_to_user(info, &s_32, sizeof(s_32))) return -EFAULT; return 0; } #endif /* CONFIG_COMPAT */ |
| 823 973 950 189 994 996 974 975 994 996 949 189 | 1 2 3 4 5 6 7 8 9 10 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 | /* * Cryptographic API. * * Glue code for the SHA256 Secure Hash Algorithm assembler implementations * using SSSE3, AVX, AVX2, and SHA-NI instructions. * * This file is based on sha256_generic.c * * Copyright (C) 2013 Intel Corporation. * * Author: * Tim Chen <tim.c.chen@linux.intel.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free * Software Foundation; either version 2 of the License, or (at your option) * any later version. * * 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. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> #include <crypto/sha2.h> #include <crypto/sha256_base.h> #include <linux/string.h> #include <asm/cpu_device_id.h> #include <asm/simd.h> asmlinkage void sha256_transform_ssse3(struct sha256_state *state, const u8 *data, int blocks); static const struct x86_cpu_id module_cpu_ids[] = { #ifdef CONFIG_AS_SHA256_NI X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL), #endif X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids); static int _sha256_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha256_block_fn *sha256_xform) { struct sha256_state *sctx = shash_desc_ctx(desc); if (!crypto_simd_usable() || (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE) return crypto_sha256_update(desc, data, len); /* * Make sure struct sha256_state begins directly with the SHA256 * 256-bit internal state, as this is what the asm functions expect. */ BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0); kernel_fpu_begin(); sha256_base_do_update(desc, data, len, sha256_xform); kernel_fpu_end(); return 0; } static int sha256_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out, sha256_block_fn *sha256_xform) { if (!crypto_simd_usable()) return crypto_sha256_finup(desc, data, len, out); kernel_fpu_begin(); if (len) sha256_base_do_update(desc, data, len, sha256_xform); sha256_base_do_finalize(desc, sha256_xform); kernel_fpu_end(); return sha256_base_finish(desc, out); } static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_transform_ssse3); } static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_transform_ssse3); } /* Add padding and return the message digest. */ static int sha256_ssse3_final(struct shash_desc *desc, u8 *out) { return sha256_ssse3_finup(desc, NULL, 0, out); } static int sha256_ssse3_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_ssse3_finup(desc, data, len, out); } static struct shash_alg sha256_ssse3_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_ssse3_update, .final = sha256_ssse3_final, .finup = sha256_ssse3_finup, .digest = sha256_ssse3_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-ssse3", .cra_priority = 150, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_ssse3_update, .final = sha256_ssse3_final, .finup = sha256_ssse3_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-ssse3", .cra_priority = 150, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static int register_sha256_ssse3(void) { if (boot_cpu_has(X86_FEATURE_SSSE3)) return crypto_register_shashes(sha256_ssse3_algs, ARRAY_SIZE(sha256_ssse3_algs)); return 0; } static void unregister_sha256_ssse3(void) { if (boot_cpu_has(X86_FEATURE_SSSE3)) crypto_unregister_shashes(sha256_ssse3_algs, ARRAY_SIZE(sha256_ssse3_algs)); } asmlinkage void sha256_transform_avx(struct sha256_state *state, const u8 *data, int blocks); static int sha256_avx_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_transform_avx); } static int sha256_avx_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_transform_avx); } static int sha256_avx_final(struct shash_desc *desc, u8 *out) { return sha256_avx_finup(desc, NULL, 0, out); } static int sha256_avx_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_avx_finup(desc, data, len, out); } static struct shash_alg sha256_avx_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_avx_update, .final = sha256_avx_final, .finup = sha256_avx_finup, .digest = sha256_avx_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-avx", .cra_priority = 160, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_avx_update, .final = sha256_avx_final, .finup = sha256_avx_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-avx", .cra_priority = 160, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static bool avx_usable(void) { if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { if (boot_cpu_has(X86_FEATURE_AVX)) pr_info("AVX detected but unusable.\n"); return false; } return true; } static int register_sha256_avx(void) { if (avx_usable()) return crypto_register_shashes(sha256_avx_algs, ARRAY_SIZE(sha256_avx_algs)); return 0; } static void unregister_sha256_avx(void) { if (avx_usable()) crypto_unregister_shashes(sha256_avx_algs, ARRAY_SIZE(sha256_avx_algs)); } asmlinkage void sha256_transform_rorx(struct sha256_state *state, const u8 *data, int blocks); static int sha256_avx2_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_transform_rorx); } static int sha256_avx2_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_transform_rorx); } static int sha256_avx2_final(struct shash_desc *desc, u8 *out) { return sha256_avx2_finup(desc, NULL, 0, out); } static int sha256_avx2_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_avx2_finup(desc, data, len, out); } static struct shash_alg sha256_avx2_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_avx2_update, .final = sha256_avx2_final, .finup = sha256_avx2_finup, .digest = sha256_avx2_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-avx2", .cra_priority = 170, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_avx2_update, .final = sha256_avx2_final, .finup = sha256_avx2_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-avx2", .cra_priority = 170, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static bool avx2_usable(void) { if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI2)) return true; return false; } static int register_sha256_avx2(void) { if (avx2_usable()) return crypto_register_shashes(sha256_avx2_algs, ARRAY_SIZE(sha256_avx2_algs)); return 0; } static void unregister_sha256_avx2(void) { if (avx2_usable()) crypto_unregister_shashes(sha256_avx2_algs, ARRAY_SIZE(sha256_avx2_algs)); } #ifdef CONFIG_AS_SHA256_NI asmlinkage void sha256_ni_transform(struct sha256_state *digest, const u8 *data, int rounds); static int sha256_ni_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_ni_transform); } static int sha256_ni_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_ni_transform); } static int sha256_ni_final(struct shash_desc *desc, u8 *out) { return sha256_ni_finup(desc, NULL, 0, out); } static int sha256_ni_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_ni_finup(desc, data, len, out); } static struct shash_alg sha256_ni_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_ni_update, .final = sha256_ni_final, .finup = sha256_ni_finup, .digest = sha256_ni_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-ni", .cra_priority = 250, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_ni_update, .final = sha256_ni_final, .finup = sha256_ni_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-ni", .cra_priority = 250, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static int register_sha256_ni(void) { if (boot_cpu_has(X86_FEATURE_SHA_NI)) return crypto_register_shashes(sha256_ni_algs, ARRAY_SIZE(sha256_ni_algs)); return 0; } static void unregister_sha256_ni(void) { if (boot_cpu_has(X86_FEATURE_SHA_NI)) crypto_unregister_shashes(sha256_ni_algs, ARRAY_SIZE(sha256_ni_algs)); } #else static inline int register_sha256_ni(void) { return 0; } static inline void unregister_sha256_ni(void) { } #endif static int __init sha256_ssse3_mod_init(void) { if (!x86_match_cpu(module_cpu_ids)) return -ENODEV; if (register_sha256_ssse3()) goto fail; if (register_sha256_avx()) { unregister_sha256_ssse3(); goto fail; } if (register_sha256_avx2()) { unregister_sha256_avx(); unregister_sha256_ssse3(); goto fail; } if (register_sha256_ni()) { unregister_sha256_avx2(); unregister_sha256_avx(); unregister_sha256_ssse3(); goto fail; } return 0; fail: return -ENODEV; } static void __exit sha256_ssse3_mod_fini(void) { unregister_sha256_ni(); unregister_sha256_avx2(); unregister_sha256_avx(); unregister_sha256_ssse3(); } module_init(sha256_ssse3_mod_init); module_exit(sha256_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated"); MODULE_ALIAS_CRYPTO("sha256"); MODULE_ALIAS_CRYPTO("sha256-ssse3"); MODULE_ALIAS_CRYPTO("sha256-avx"); MODULE_ALIAS_CRYPTO("sha256-avx2"); MODULE_ALIAS_CRYPTO("sha224"); MODULE_ALIAS_CRYPTO("sha224-ssse3"); MODULE_ALIAS_CRYPTO("sha224-avx"); MODULE_ALIAS_CRYPTO("sha224-avx2"); #ifdef CONFIG_AS_SHA256_NI MODULE_ALIAS_CRYPTO("sha256-ni"); MODULE_ALIAS_CRYPTO("sha224-ni"); #endif |
| 10 8 10 10 10 64 64 64 64 64 64 62 63 62 63 62 62 1 63 63 63 62 | 1 2 3 4 5 6 7 8 9 10 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 | /* * xxHash - Extremely Fast Hash algorithm * Copyright (C) 2012-2016, Yann Collet. * * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) * * 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. * * 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. * * This program is free software; you can redistribute it and/or modify it under * the terms of the GNU General Public License version 2 as published by the * Free Software Foundation. This program is dual-licensed; you may select * either version 2 of the GNU General Public License ("GPL") or BSD license * ("BSD"). * * You can contact the author at: * - xxHash homepage: https://cyan4973.github.io/xxHash/ * - xxHash source repository: https://github.com/Cyan4973/xxHash */ #include <linux/unaligned.h> #include <linux/errno.h> #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/string.h> #include <linux/xxhash.h> /*-************************************* * Macros **************************************/ #define xxh_rotl32(x, r) ((x << r) | (x >> (32 - r))) #define xxh_rotl64(x, r) ((x << r) | (x >> (64 - r))) #ifdef __LITTLE_ENDIAN # define XXH_CPU_LITTLE_ENDIAN 1 #else # define XXH_CPU_LITTLE_ENDIAN 0 #endif /*-************************************* * Constants **************************************/ static const uint32_t PRIME32_1 = 2654435761U; static const uint32_t PRIME32_2 = 2246822519U; static const uint32_t PRIME32_3 = 3266489917U; static const uint32_t PRIME32_4 = 668265263U; static const uint32_t PRIME32_5 = 374761393U; static const uint64_t PRIME64_1 = 11400714785074694791ULL; static const uint64_t PRIME64_2 = 14029467366897019727ULL; static const uint64_t PRIME64_3 = 1609587929392839161ULL; static const uint64_t PRIME64_4 = 9650029242287828579ULL; static const uint64_t PRIME64_5 = 2870177450012600261ULL; /*-************************** * Utils ***************************/ void xxh32_copy_state(struct xxh32_state *dst, const struct xxh32_state *src) { memcpy(dst, src, sizeof(*dst)); } EXPORT_SYMBOL(xxh32_copy_state); void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state *src) { memcpy(dst, src, sizeof(*dst)); } EXPORT_SYMBOL(xxh64_copy_state); /*-*************************** * Simple Hash Functions ****************************/ static uint32_t xxh32_round(uint32_t seed, const uint32_t input) { seed += input * PRIME32_2; seed = xxh_rotl32(seed, 13); seed *= PRIME32_1; return seed; } uint32_t xxh32(const void *input, const size_t len, const uint32_t seed) { const uint8_t *p = (const uint8_t *)input; const uint8_t *b_end = p + len; uint32_t h32; if (len >= 16) { const uint8_t *const limit = b_end - 16; uint32_t v1 = seed + PRIME32_1 + PRIME32_2; uint32_t v2 = seed + PRIME32_2; uint32_t v3 = seed + 0; uint32_t v4 = seed - PRIME32_1; do { v1 = xxh32_round(v1, get_unaligned_le32(p)); p += 4; v2 = xxh32_round(v2, get_unaligned_le32(p)); p += 4; v3 = xxh32_round(v3, get_unaligned_le32(p)); p += 4; v4 = xxh32_round(v4, get_unaligned_le32(p)); p += 4; } while (p <= limit); h32 = xxh_rotl32(v1, 1) + xxh_rotl32(v2, 7) + xxh_rotl32(v3, 12) + xxh_rotl32(v4, 18); } else { h32 = seed + PRIME32_5; } h32 += (uint32_t)len; while (p + 4 <= b_end) { h32 += get_unaligned_le32(p) * PRIME32_3; h32 = xxh_rotl32(h32, 17) * PRIME32_4; p += 4; } while (p < b_end) { h32 += (*p) * PRIME32_5; h32 = xxh_rotl32(h32, 11) * PRIME32_1; p++; } h32 ^= h32 >> 15; h32 *= PRIME32_2; h32 ^= h32 >> 13; h32 *= PRIME32_3; h32 ^= h32 >> 16; return h32; } EXPORT_SYMBOL(xxh32); static uint64_t xxh64_round(uint64_t acc, const uint64_t input) { acc += input * PRIME64_2; acc = xxh_rotl64(acc, 31); acc *= PRIME64_1; return acc; } static uint64_t xxh64_merge_round(uint64_t acc, uint64_t val) { val = xxh64_round(0, val); acc ^= val; acc = acc * PRIME64_1 + PRIME64_4; return acc; } uint64_t xxh64(const void *input, const size_t len, const uint64_t seed) { const uint8_t *p = (const uint8_t *)input; const uint8_t *const b_end = p + len; uint64_t h64; if (len >= 32) { const uint8_t *const limit = b_end - 32; uint64_t v1 = seed + PRIME64_1 + PRIME64_2; uint64_t v2 = seed + PRIME64_2; uint64_t v3 = seed + 0; uint64_t v4 = seed - PRIME64_1; do { v1 = xxh64_round(v1, get_unaligned_le64(p)); p += 8; v2 = xxh64_round(v2, get_unaligned_le64(p)); p += 8; v3 = xxh64_round(v3, get_unaligned_le64(p)); p += 8; v4 = xxh64_round(v4, get_unaligned_le64(p)); p += 8; } while (p <= limit); h64 = xxh_rotl64(v1, 1) + xxh_rotl64(v2, 7) + xxh_rotl64(v3, 12) + xxh_rotl64(v4, 18); h64 = xxh64_merge_round(h64, v1); h64 = xxh64_merge_round(h64, v2); h64 = xxh64_merge_round(h64, v3); h64 = xxh64_merge_round(h64, v4); } else { h64 = seed + PRIME64_5; } h64 += (uint64_t)len; while (p + 8 <= b_end) { const uint64_t k1 = xxh64_round(0, get_unaligned_le64(p)); h64 ^= k1; h64 = xxh_rotl64(h64, 27) * PRIME64_1 + PRIME64_4; p += 8; } if (p + 4 <= b_end) { h64 ^= (uint64_t)(get_unaligned_le32(p)) * PRIME64_1; h64 = xxh_rotl64(h64, 23) * PRIME64_2 + PRIME64_3; p += 4; } while (p < b_end) { h64 ^= (*p) * PRIME64_5; h64 = xxh_rotl64(h64, 11) * PRIME64_1; p++; } h64 ^= h64 >> 33; h64 *= PRIME64_2; h64 ^= h64 >> 29; h64 *= PRIME64_3; h64 ^= h64 >> 32; return h64; } EXPORT_SYMBOL(xxh64); /*-************************************************** * Advanced Hash Functions ***************************************************/ void xxh32_reset(struct xxh32_state *statePtr, const uint32_t seed) { /* use a local state for memcpy() to avoid strict-aliasing warnings */ struct xxh32_state state; memset(&state, 0, sizeof(state)); state.v1 = seed + PRIME32_1 + PRIME32_2; state.v2 = seed + PRIME32_2; state.v3 = seed + 0; state.v4 = seed - PRIME32_1; memcpy(statePtr, &state, sizeof(state)); } EXPORT_SYMBOL(xxh32_reset); void xxh64_reset(struct xxh64_state *statePtr, const uint64_t seed) { /* use a local state for memcpy() to avoid strict-aliasing warnings */ struct xxh64_state state; memset(&state, 0, sizeof(state)); state.v1 = seed + PRIME64_1 + PRIME64_2; state.v2 = seed + PRIME64_2; state.v3 = seed + 0; state.v4 = seed - PRIME64_1; memcpy(statePtr, &state, sizeof(state)); } EXPORT_SYMBOL(xxh64_reset); int xxh32_update(struct xxh32_state *state, const void *input, const size_t len) { const uint8_t *p = (const uint8_t *)input; const uint8_t *const b_end = p + len; if (input == NULL) return -EINVAL; state->total_len_32 += (uint32_t)len; state->large_len |= (len >= 16) | (state->total_len_32 >= 16); if (state->memsize + len < 16) { /* fill in tmp buffer */ memcpy((uint8_t *)(state->mem32) + state->memsize, input, len); state->memsize += (uint32_t)len; return 0; } if (state->memsize) { /* some data left from previous update */ const uint32_t *p32 = state->mem32; memcpy((uint8_t *)(state->mem32) + state->memsize, input, 16 - state->memsize); state->v1 = xxh32_round(state->v1, get_unaligned_le32(p32)); p32++; state->v2 = xxh32_round(state->v2, get_unaligned_le32(p32)); p32++; state->v3 = xxh32_round(state->v3, get_unaligned_le32(p32)); p32++; state->v4 = xxh32_round(state->v4, get_unaligned_le32(p32)); p32++; p += 16-state->memsize; state->memsize = 0; } if (p <= b_end - 16) { const uint8_t *const limit = b_end - 16; uint32_t v1 = state->v1; uint32_t v2 = state->v2; uint32_t v3 = state->v3; uint32_t v4 = state->v4; do { v1 = xxh32_round(v1, get_unaligned_le32(p)); p += 4; v2 = xxh32_round(v2, get_unaligned_le32(p)); p += 4; v3 = xxh32_round(v3, get_unaligned_le32(p)); p += 4; v4 = xxh32_round(v4, get_unaligned_le32(p)); p += 4; } while (p <= limit); state->v1 = v1; state->v2 = v2; state->v3 = v3; state->v4 = v4; } if (p < b_end) { memcpy(state->mem32, p, (size_t)(b_end-p)); state->memsize = (uint32_t)(b_end-p); } return 0; } EXPORT_SYMBOL(xxh32_update); uint32_t xxh32_digest(const struct xxh32_state *state) { const uint8_t *p = (const uint8_t *)state->mem32; const uint8_t *const b_end = (const uint8_t *)(state->mem32) + state->memsize; uint32_t h32; if (state->large_len) { h32 = xxh_rotl32(state->v1, 1) + xxh_rotl32(state->v2, 7) + xxh_rotl32(state->v3, 12) + xxh_rotl32(state->v4, 18); } else { h32 = state->v3 /* == seed */ + PRIME32_5; } h32 += state->total_len_32; while (p + 4 <= b_end) { h32 += get_unaligned_le32(p) * PRIME32_3; h32 = xxh_rotl32(h32, 17) * PRIME32_4; p += 4; } while (p < b_end) { h32 += (*p) * PRIME32_5; h32 = xxh_rotl32(h32, 11) * PRIME32_1; p++; } h32 ^= h32 >> 15; h32 *= PRIME32_2; h32 ^= h32 >> 13; h32 *= PRIME32_3; h32 ^= h32 >> 16; return h32; } EXPORT_SYMBOL(xxh32_digest); int xxh64_update(struct xxh64_state *state, const void *input, const size_t len) { const uint8_t *p = (const uint8_t *)input; const uint8_t *const b_end = p + len; if (input == NULL) return -EINVAL; state->total_len += len; if (state->memsize + len < 32) { /* fill in tmp buffer */ memcpy(((uint8_t *)state->mem64) + state->memsize, input, len); state->memsize += (uint32_t)len; return 0; } if (state->memsize) { /* tmp buffer is full */ uint64_t *p64 = state->mem64; memcpy(((uint8_t *)p64) + state->memsize, input, 32 - state->memsize); state->v1 = xxh64_round(state->v1, get_unaligned_le64(p64)); p64++; state->v2 = xxh64_round(state->v2, get_unaligned_le64(p64)); p64++; state->v3 = xxh64_round(state->v3, get_unaligned_le64(p64)); p64++; state->v4 = xxh64_round(state->v4, get_unaligned_le64(p64)); p += 32 - state->memsize; state->memsize = 0; } if (p + 32 <= b_end) { const uint8_t *const limit = b_end - 32; uint64_t v1 = state->v1; uint64_t v2 = state->v2; uint64_t v3 = state->v3; uint64_t v4 = state->v4; do { v1 = xxh64_round(v1, get_unaligned_le64(p)); p += 8; v2 = xxh64_round(v2, get_unaligned_le64(p)); p += 8; v3 = xxh64_round(v3, get_unaligned_le64(p)); p += 8; v4 = xxh64_round(v4, get_unaligned_le64(p)); p += 8; } while (p <= limit); state->v1 = v1; state->v2 = v2; state->v3 = v3; state->v4 = v4; } if (p < b_end) { memcpy(state->mem64, p, (size_t)(b_end-p)); state->memsize = (uint32_t)(b_end - p); } return 0; } EXPORT_SYMBOL(xxh64_update); uint64_t xxh64_digest(const struct xxh64_state *state) { const uint8_t *p = (const uint8_t *)state->mem64; const uint8_t *const b_end = (const uint8_t *)state->mem64 + state->memsize; uint64_t h64; if (state->total_len >= 32) { const uint64_t v1 = state->v1; const uint64_t v2 = state->v2; const uint64_t v3 = state->v3; const uint64_t v4 = state->v4; h64 = xxh_rotl64(v1, 1) + xxh_rotl64(v2, 7) + xxh_rotl64(v3, 12) + xxh_rotl64(v4, 18); h64 = xxh64_merge_round(h64, v1); h64 = xxh64_merge_round(h64, v2); h64 = xxh64_merge_round(h64, v3); h64 = xxh64_merge_round(h64, v4); } else { h64 = state->v3 + PRIME64_5; } h64 += (uint64_t)state->total_len; while (p + 8 <= b_end) { const uint64_t k1 = xxh64_round(0, get_unaligned_le64(p)); h64 ^= k1; h64 = xxh_rotl64(h64, 27) * PRIME64_1 + PRIME64_4; p += 8; } if (p + 4 <= b_end) { h64 ^= (uint64_t)(get_unaligned_le32(p)) * PRIME64_1; h64 = xxh_rotl64(h64, 23) * PRIME64_2 + PRIME64_3; p += 4; } while (p < b_end) { h64 ^= (*p) * PRIME64_5; h64 = xxh_rotl64(h64, 11) * PRIME64_1; p++; } h64 ^= h64 >> 33; h64 *= PRIME64_2; h64 ^= h64 >> 29; h64 *= PRIME64_3; h64 ^= h64 >> 32; return h64; } EXPORT_SYMBOL(xxh64_digest); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("xxHash"); |
| 44 17 1 1 10 10 10 1 1 125 82 60 116 10 9 1 8 2 4 6 2 8 6 4 7 3 6 4 3 4 3 7 3 6 4 3 2 4 1 195 195 85 85 31 17 19 20 16 19 21 37 28 24 15 5 1 6 5 2 58 70 1 1 1 1 1 1 1 1 73 72 1 73 73 1 1 59 12 59 12 71 71 71 71 70 1 69 3 79 71 4 3 18 79 21 78 1 79 34 26 1 60 58 3 80 11 89 80 11 6 88 88 23 23 53 | 1 2 3 4 5 6 7 8 9 10 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2012-2013 Samsung Electronics Co., Ltd. */ #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/module.h> #include <linux/init.h> #include <linux/time.h> #include <linux/mount.h> #include <linux/cred.h> #include <linux/statfs.h> #include <linux/seq_file.h> #include <linux/blkdev.h> #include <linux/fs_struct.h> #include <linux/iversion.h> #include <linux/nls.h> #include <linux/buffer_head.h> #include <linux/magic.h> #include "exfat_raw.h" #include "exfat_fs.h" static char exfat_default_iocharset[] = CONFIG_EXFAT_DEFAULT_IOCHARSET; static struct kmem_cache *exfat_inode_cachep; static void exfat_free_iocharset(struct exfat_sb_info *sbi) { if (sbi->options.iocharset != exfat_default_iocharset) kfree(sbi->options.iocharset); } static void exfat_put_super(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); mutex_lock(&sbi->s_lock); exfat_free_bitmap(sbi); brelse(sbi->boot_bh); mutex_unlock(&sbi->s_lock); } static int exfat_sync_fs(struct super_block *sb, int wait) { struct exfat_sb_info *sbi = EXFAT_SB(sb); int err = 0; if (unlikely(exfat_forced_shutdown(sb))) return 0; if (!wait) return 0; /* If there are some dirty buffers in the bdev inode */ mutex_lock(&sbi->s_lock); sync_blockdev(sb->s_bdev); if (exfat_clear_volume_dirty(sb)) err = -EIO; mutex_unlock(&sbi->s_lock); return err; } static int exfat_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); unsigned long long id = huge_encode_dev(sb->s_bdev->bd_dev); if (sbi->used_clusters == EXFAT_CLUSTERS_UNTRACKED) { mutex_lock(&sbi->s_lock); if (exfat_count_used_clusters(sb, &sbi->used_clusters)) { mutex_unlock(&sbi->s_lock); return -EIO; } mutex_unlock(&sbi->s_lock); } buf->f_type = sb->s_magic; buf->f_bsize = sbi->cluster_size; buf->f_blocks = sbi->num_clusters - 2; /* clu 0 & 1 */ buf->f_bfree = buf->f_blocks - sbi->used_clusters; buf->f_bavail = buf->f_bfree; buf->f_fsid = u64_to_fsid(id); /* Unicode utf16 255 characters */ buf->f_namelen = EXFAT_MAX_FILE_LEN * NLS_MAX_CHARSET_SIZE; return 0; } static int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flags) { struct exfat_sb_info *sbi = EXFAT_SB(sb); struct boot_sector *p_boot = (struct boot_sector *)sbi->boot_bh->b_data; /* retain persistent-flags */ new_flags |= sbi->vol_flags_persistent; /* flags are not changed */ if (sbi->vol_flags == new_flags) return 0; sbi->vol_flags = new_flags; /* skip updating volume dirty flag, * if this volume has been mounted with read-only */ if (sb_rdonly(sb)) return 0; p_boot->vol_flags = cpu_to_le16(new_flags); set_buffer_uptodate(sbi->boot_bh); mark_buffer_dirty(sbi->boot_bh); __sync_dirty_buffer(sbi->boot_bh, REQ_SYNC | REQ_FUA | REQ_PREFLUSH); return 0; } int exfat_set_volume_dirty(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); return exfat_set_vol_flags(sb, sbi->vol_flags | VOLUME_DIRTY); } int exfat_clear_volume_dirty(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); return exfat_set_vol_flags(sb, sbi->vol_flags & ~VOLUME_DIRTY); } static int exfat_show_options(struct seq_file *m, struct dentry *root) { struct super_block *sb = root->d_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_mount_options *opts = &sbi->options; /* Show partition info */ if (!uid_eq(opts->fs_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, opts->fs_uid)); if (!gid_eq(opts->fs_gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, opts->fs_gid)); seq_printf(m, ",fmask=%04o,dmask=%04o", opts->fs_fmask, opts->fs_dmask); if (opts->allow_utime) seq_printf(m, ",allow_utime=%04o", opts->allow_utime); if (opts->utf8) seq_puts(m, ",iocharset=utf8"); else if (sbi->nls_io) seq_printf(m, ",iocharset=%s", sbi->nls_io->charset); if (opts->errors == EXFAT_ERRORS_CONT) seq_puts(m, ",errors=continue"); else if (opts->errors == EXFAT_ERRORS_PANIC) seq_puts(m, ",errors=panic"); else seq_puts(m, ",errors=remount-ro"); if (opts->discard) seq_puts(m, ",discard"); if (opts->keep_last_dots) seq_puts(m, ",keep_last_dots"); if (opts->sys_tz) seq_puts(m, ",sys_tz"); else if (opts->time_offset) seq_printf(m, ",time_offset=%d", opts->time_offset); if (opts->zero_size_dir) seq_puts(m, ",zero_size_dir"); return 0; } int exfat_force_shutdown(struct super_block *sb, u32 flags) { int ret; struct exfat_sb_info *sbi = sb->s_fs_info; struct exfat_mount_options *opts = &sbi->options; if (exfat_forced_shutdown(sb)) return 0; switch (flags) { case EXFAT_GOING_DOWN_DEFAULT: case EXFAT_GOING_DOWN_FULLSYNC: ret = bdev_freeze(sb->s_bdev); if (ret) return ret; bdev_thaw(sb->s_bdev); set_bit(EXFAT_FLAGS_SHUTDOWN, &sbi->s_exfat_flags); break; case EXFAT_GOING_DOWN_NOSYNC: set_bit(EXFAT_FLAGS_SHUTDOWN, &sbi->s_exfat_flags); break; default: return -EINVAL; } if (opts->discard) opts->discard = 0; return 0; } static void exfat_shutdown(struct super_block *sb) { exfat_force_shutdown(sb, EXFAT_GOING_DOWN_NOSYNC); } static struct inode *exfat_alloc_inode(struct super_block *sb) { struct exfat_inode_info *ei; ei = alloc_inode_sb(sb, exfat_inode_cachep, GFP_NOFS); if (!ei) return NULL; init_rwsem(&ei->truncate_lock); return &ei->vfs_inode; } static void exfat_free_inode(struct inode *inode) { kmem_cache_free(exfat_inode_cachep, EXFAT_I(inode)); } static const struct super_operations exfat_sops = { .alloc_inode = exfat_alloc_inode, .free_inode = exfat_free_inode, .write_inode = exfat_write_inode, .evict_inode = exfat_evict_inode, .put_super = exfat_put_super, .sync_fs = exfat_sync_fs, .statfs = exfat_statfs, .show_options = exfat_show_options, .shutdown = exfat_shutdown, }; enum { Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_allow_utime, Opt_charset, Opt_errors, Opt_discard, Opt_keep_last_dots, Opt_sys_tz, Opt_time_offset, Opt_zero_size_dir, /* Deprecated options */ Opt_utf8, Opt_debug, Opt_namecase, Opt_codepage, }; static const struct constant_table exfat_param_enums[] = { { "continue", EXFAT_ERRORS_CONT }, { "panic", EXFAT_ERRORS_PANIC }, { "remount-ro", EXFAT_ERRORS_RO }, {} }; static const struct fs_parameter_spec exfat_parameters[] = { fsparam_uid("uid", Opt_uid), fsparam_gid("gid", Opt_gid), fsparam_u32oct("umask", Opt_umask), fsparam_u32oct("dmask", Opt_dmask), fsparam_u32oct("fmask", Opt_fmask), fsparam_u32oct("allow_utime", Opt_allow_utime), fsparam_string("iocharset", Opt_charset), fsparam_enum("errors", Opt_errors, exfat_param_enums), fsparam_flag("discard", Opt_discard), fsparam_flag("keep_last_dots", Opt_keep_last_dots), fsparam_flag("sys_tz", Opt_sys_tz), fsparam_s32("time_offset", Opt_time_offset), fsparam_flag("zero_size_dir", Opt_zero_size_dir), __fsparam(NULL, "utf8", Opt_utf8, fs_param_deprecated, NULL), __fsparam(NULL, "debug", Opt_debug, fs_param_deprecated, NULL), __fsparam(fs_param_is_u32, "namecase", Opt_namecase, fs_param_deprecated, NULL), __fsparam(fs_param_is_u32, "codepage", Opt_codepage, fs_param_deprecated, NULL), {} }; static int exfat_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct exfat_sb_info *sbi = fc->s_fs_info; struct exfat_mount_options *opts = &sbi->options; struct fs_parse_result result; int opt; opt = fs_parse(fc, exfat_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_uid: opts->fs_uid = result.uid; break; case Opt_gid: opts->fs_gid = result.gid; break; case Opt_umask: opts->fs_fmask = result.uint_32; opts->fs_dmask = result.uint_32; break; case Opt_dmask: opts->fs_dmask = result.uint_32; break; case Opt_fmask: opts->fs_fmask = result.uint_32; break; case Opt_allow_utime: opts->allow_utime = result.uint_32 & 0022; break; case Opt_charset: exfat_free_iocharset(sbi); opts->iocharset = param->string; param->string = NULL; break; case Opt_errors: opts->errors = result.uint_32; break; case Opt_discard: opts->discard = 1; break; case Opt_keep_last_dots: opts->keep_last_dots = 1; break; case Opt_sys_tz: opts->sys_tz = 1; break; case Opt_time_offset: /* * Make the limit 24 just in case someone invents something * unusual. */ if (result.int_32 < -24 * 60 || result.int_32 > 24 * 60) return -EINVAL; opts->time_offset = result.int_32; break; case Opt_zero_size_dir: opts->zero_size_dir = true; break; case Opt_utf8: case Opt_debug: case Opt_namecase: case Opt_codepage: break; default: return -EINVAL; } return 0; } static void exfat_hash_init(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); int i; spin_lock_init(&sbi->inode_hash_lock); for (i = 0; i < EXFAT_HASH_SIZE; i++) INIT_HLIST_HEAD(&sbi->inode_hashtable[i]); } static int exfat_read_root(struct inode *inode) { struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); struct exfat_chain cdir; int num_subdirs, num_clu = 0; exfat_chain_set(&ei->dir, sbi->root_dir, 0, ALLOC_FAT_CHAIN); ei->entry = -1; ei->start_clu = sbi->root_dir; ei->flags = ALLOC_FAT_CHAIN; ei->type = TYPE_DIR; ei->version = 0; ei->hint_bmap.off = EXFAT_EOF_CLUSTER; ei->hint_stat.eidx = 0; ei->hint_stat.clu = sbi->root_dir; ei->hint_femp.eidx = EXFAT_HINT_NONE; exfat_chain_set(&cdir, sbi->root_dir, 0, ALLOC_FAT_CHAIN); if (exfat_count_num_clusters(sb, &cdir, &num_clu)) return -EIO; i_size_write(inode, num_clu << sbi->cluster_size_bits); num_subdirs = exfat_count_dir_entries(sb, &cdir); if (num_subdirs < 0) return -EIO; set_nlink(inode, num_subdirs + EXFAT_MIN_SUBDIR); inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); inode->i_generation = 0; inode->i_mode = exfat_make_mode(sbi, EXFAT_ATTR_SUBDIR, 0777); inode->i_op = &exfat_dir_inode_operations; inode->i_fop = &exfat_dir_operations; inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> 9; ei->i_pos = ((loff_t)sbi->root_dir << 32) | 0xffffffff; exfat_save_attr(inode, EXFAT_ATTR_SUBDIR); ei->i_crtime = simple_inode_init_ts(inode); exfat_truncate_inode_atime(inode); return 0; } static int exfat_calibrate_blocksize(struct super_block *sb, int logical_sect) { struct exfat_sb_info *sbi = EXFAT_SB(sb); if (!is_power_of_2(logical_sect)) { exfat_err(sb, "bogus logical sector size %u", logical_sect); return -EIO; } if (logical_sect < sb->s_blocksize) { exfat_err(sb, "logical sector size too small for device (logical sector size = %u)", logical_sect); return -EIO; } if (logical_sect > sb->s_blocksize) { brelse(sbi->boot_bh); sbi->boot_bh = NULL; if (!sb_set_blocksize(sb, logical_sect)) { exfat_err(sb, "unable to set blocksize %u", logical_sect); return -EIO; } sbi->boot_bh = sb_bread(sb, 0); if (!sbi->boot_bh) { exfat_err(sb, "unable to read boot sector (logical sector size = %lu)", sb->s_blocksize); return -EIO; } } return 0; } static int exfat_read_boot_sector(struct super_block *sb) { struct boot_sector *p_boot; struct exfat_sb_info *sbi = EXFAT_SB(sb); /* set block size to read super block */ sb_min_blocksize(sb, 512); /* read boot sector */ sbi->boot_bh = sb_bread(sb, 0); if (!sbi->boot_bh) { exfat_err(sb, "unable to read boot sector"); return -EIO; } p_boot = (struct boot_sector *)sbi->boot_bh->b_data; /* check the validity of BOOT */ if (le16_to_cpu((p_boot->signature)) != BOOT_SIGNATURE) { exfat_err(sb, "invalid boot record signature"); return -EINVAL; } if (memcmp(p_boot->fs_name, STR_EXFAT, BOOTSEC_FS_NAME_LEN)) { exfat_err(sb, "invalid fs_name"); /* fs_name may unprintable */ return -EINVAL; } /* * must_be_zero field must be filled with zero to prevent mounting * from FAT volume. */ if (memchr_inv(p_boot->must_be_zero, 0, sizeof(p_boot->must_be_zero))) return -EINVAL; if (p_boot->num_fats != 1 && p_boot->num_fats != 2) { exfat_err(sb, "bogus number of FAT structure"); return -EINVAL; } /* * sect_size_bits could be at least 9 and at most 12. */ if (p_boot->sect_size_bits < EXFAT_MIN_SECT_SIZE_BITS || p_boot->sect_size_bits > EXFAT_MAX_SECT_SIZE_BITS) { exfat_err(sb, "bogus sector size bits : %u", p_boot->sect_size_bits); return -EINVAL; } /* * sect_per_clus_bits could be at least 0 and at most 25 - sect_size_bits. */ if (p_boot->sect_per_clus_bits > EXFAT_MAX_SECT_PER_CLUS_BITS(p_boot)) { exfat_err(sb, "bogus sectors bits per cluster : %u", p_boot->sect_per_clus_bits); return -EINVAL; } sbi->sect_per_clus = 1 << p_boot->sect_per_clus_bits; sbi->sect_per_clus_bits = p_boot->sect_per_clus_bits; sbi->cluster_size_bits = p_boot->sect_per_clus_bits + p_boot->sect_size_bits; sbi->cluster_size = 1 << sbi->cluster_size_bits; sbi->num_FAT_sectors = le32_to_cpu(p_boot->fat_length); sbi->FAT1_start_sector = le32_to_cpu(p_boot->fat_offset); sbi->FAT2_start_sector = le32_to_cpu(p_boot->fat_offset); if (p_boot->num_fats == 2) sbi->FAT2_start_sector += sbi->num_FAT_sectors; sbi->data_start_sector = le32_to_cpu(p_boot->clu_offset); sbi->num_sectors = le64_to_cpu(p_boot->vol_length); /* because the cluster index starts with 2 */ sbi->num_clusters = le32_to_cpu(p_boot->clu_count) + EXFAT_RESERVED_CLUSTERS; sbi->root_dir = le32_to_cpu(p_boot->root_cluster); sbi->dentries_per_clu = 1 << (sbi->cluster_size_bits - DENTRY_SIZE_BITS); sbi->vol_flags = le16_to_cpu(p_boot->vol_flags); sbi->vol_flags_persistent = sbi->vol_flags & (VOLUME_DIRTY | MEDIA_FAILURE); sbi->clu_srch_ptr = EXFAT_FIRST_CLUSTER; sbi->used_clusters = EXFAT_CLUSTERS_UNTRACKED; /* check consistencies */ if ((u64)sbi->num_FAT_sectors << p_boot->sect_size_bits < (u64)sbi->num_clusters * 4) { exfat_err(sb, "bogus fat length"); return -EINVAL; } if (sbi->data_start_sector < (u64)sbi->FAT1_start_sector + (u64)sbi->num_FAT_sectors * p_boot->num_fats) { exfat_err(sb, "bogus data start sector"); return -EINVAL; } if (sbi->vol_flags & VOLUME_DIRTY) exfat_warn(sb, "Volume was not properly unmounted. Some data may be corrupt. Please run fsck."); if (sbi->vol_flags & MEDIA_FAILURE) exfat_warn(sb, "Medium has reported failures. Some data may be lost."); /* exFAT file size is limited by a disk volume size */ sb->s_maxbytes = (u64)(sbi->num_clusters - EXFAT_RESERVED_CLUSTERS) << sbi->cluster_size_bits; /* check logical sector size */ if (exfat_calibrate_blocksize(sb, 1 << p_boot->sect_size_bits)) return -EIO; return 0; } static int exfat_verify_boot_region(struct super_block *sb) { struct buffer_head *bh = NULL; u32 chksum = 0; __le32 *p_sig, *p_chksum; int sn, i; /* read boot sector sub-regions */ for (sn = 0; sn < 11; sn++) { bh = sb_bread(sb, sn); if (!bh) return -EIO; if (sn != 0 && sn <= 8) { /* extended boot sector sub-regions */ p_sig = (__le32 *)&bh->b_data[sb->s_blocksize - 4]; if (le32_to_cpu(*p_sig) != EXBOOT_SIGNATURE) exfat_warn(sb, "Invalid exboot-signature(sector = %d): 0x%08x", sn, le32_to_cpu(*p_sig)); } chksum = exfat_calc_chksum32(bh->b_data, sb->s_blocksize, chksum, sn ? CS_DEFAULT : CS_BOOT_SECTOR); brelse(bh); } /* boot checksum sub-regions */ bh = sb_bread(sb, sn); if (!bh) return -EIO; for (i = 0; i < sb->s_blocksize; i += sizeof(u32)) { p_chksum = (__le32 *)&bh->b_data[i]; if (le32_to_cpu(*p_chksum) != chksum) { exfat_err(sb, "Invalid boot checksum (boot checksum : 0x%08x, checksum : 0x%08x)", le32_to_cpu(*p_chksum), chksum); brelse(bh); return -EINVAL; } } brelse(bh); return 0; } /* mount the file system volume */ static int __exfat_fill_super(struct super_block *sb) { int ret; struct exfat_sb_info *sbi = EXFAT_SB(sb); ret = exfat_read_boot_sector(sb); if (ret) { exfat_err(sb, "failed to read boot sector"); goto free_bh; } ret = exfat_verify_boot_region(sb); if (ret) { exfat_err(sb, "invalid boot region"); goto free_bh; } ret = exfat_create_upcase_table(sb); if (ret) { exfat_err(sb, "failed to load upcase table"); goto free_bh; } ret = exfat_load_bitmap(sb); if (ret) { exfat_err(sb, "failed to load alloc-bitmap"); goto free_bh; } ret = exfat_count_used_clusters(sb, &sbi->used_clusters); if (ret) { exfat_err(sb, "failed to scan clusters"); goto free_alloc_bitmap; } return 0; free_alloc_bitmap: exfat_free_bitmap(sbi); free_bh: brelse(sbi->boot_bh); return ret; } static int exfat_fill_super(struct super_block *sb, struct fs_context *fc) { struct exfat_sb_info *sbi = sb->s_fs_info; struct exfat_mount_options *opts = &sbi->options; struct inode *root_inode; int err; if (opts->allow_utime == (unsigned short)-1) opts->allow_utime = ~opts->fs_dmask & 0022; if (opts->discard && !bdev_max_discard_sectors(sb->s_bdev)) { exfat_warn(sb, "mounting with \"discard\" option, but the device does not support discard"); opts->discard = 0; } sb->s_flags |= SB_NODIRATIME; sb->s_magic = EXFAT_SUPER_MAGIC; sb->s_op = &exfat_sops; sb->s_time_gran = 10 * NSEC_PER_MSEC; sb->s_time_min = EXFAT_MIN_TIMESTAMP_SECS; sb->s_time_max = EXFAT_MAX_TIMESTAMP_SECS; err = __exfat_fill_super(sb); if (err) { exfat_err(sb, "failed to recognize exfat type"); goto check_nls_io; } /* set up enough so that it can read an inode */ exfat_hash_init(sb); if (!strcmp(sbi->options.iocharset, "utf8")) opts->utf8 = 1; else { sbi->nls_io = load_nls(sbi->options.iocharset); if (!sbi->nls_io) { exfat_err(sb, "IO charset %s not found", sbi->options.iocharset); err = -EINVAL; goto free_table; } } if (sbi->options.utf8) sb->s_d_op = &exfat_utf8_dentry_ops; else sb->s_d_op = &exfat_dentry_ops; root_inode = new_inode(sb); if (!root_inode) { exfat_err(sb, "failed to allocate root inode"); err = -ENOMEM; goto free_table; } root_inode->i_ino = EXFAT_ROOT_INO; inode_set_iversion(root_inode, 1); err = exfat_read_root(root_inode); if (err) { exfat_err(sb, "failed to initialize root inode"); goto put_inode; } exfat_hash_inode(root_inode, EXFAT_I(root_inode)->i_pos); insert_inode_hash(root_inode); sb->s_root = d_make_root(root_inode); if (!sb->s_root) { exfat_err(sb, "failed to get the root dentry"); err = -ENOMEM; goto free_table; } return 0; put_inode: iput(root_inode); sb->s_root = NULL; free_table: exfat_free_bitmap(sbi); brelse(sbi->boot_bh); check_nls_io: return err; } static int exfat_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, exfat_fill_super); } static void exfat_free_sbi(struct exfat_sb_info *sbi) { exfat_free_iocharset(sbi); kfree(sbi); } static void exfat_free(struct fs_context *fc) { struct exfat_sb_info *sbi = fc->s_fs_info; if (sbi) exfat_free_sbi(sbi); } static int exfat_reconfigure(struct fs_context *fc) { fc->sb_flags |= SB_NODIRATIME; /* volume flag will be updated in exfat_sync_fs */ sync_filesystem(fc->root->d_sb); return 0; } static const struct fs_context_operations exfat_context_ops = { .parse_param = exfat_parse_param, .get_tree = exfat_get_tree, .free = exfat_free, .reconfigure = exfat_reconfigure, }; static int exfat_init_fs_context(struct fs_context *fc) { struct exfat_sb_info *sbi; sbi = kzalloc(sizeof(struct exfat_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; mutex_init(&sbi->s_lock); mutex_init(&sbi->bitmap_lock); ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); sbi->options.fs_uid = current_uid(); sbi->options.fs_gid = current_gid(); sbi->options.fs_fmask = current->fs->umask; sbi->options.fs_dmask = current->fs->umask; sbi->options.allow_utime = -1; sbi->options.iocharset = exfat_default_iocharset; sbi->options.errors = EXFAT_ERRORS_RO; fc->s_fs_info = sbi; fc->ops = &exfat_context_ops; return 0; } static void delayed_free(struct rcu_head *p) { struct exfat_sb_info *sbi = container_of(p, struct exfat_sb_info, rcu); unload_nls(sbi->nls_io); exfat_free_upcase_table(sbi); exfat_free_sbi(sbi); } static void exfat_kill_sb(struct super_block *sb) { struct exfat_sb_info *sbi = sb->s_fs_info; kill_block_super(sb); if (sbi) call_rcu(&sbi->rcu, delayed_free); } static struct file_system_type exfat_fs_type = { .owner = THIS_MODULE, .name = "exfat", .init_fs_context = exfat_init_fs_context, .parameters = exfat_parameters, .kill_sb = exfat_kill_sb, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; static void exfat_inode_init_once(void *foo) { struct exfat_inode_info *ei = (struct exfat_inode_info *)foo; spin_lock_init(&ei->cache_lru_lock); ei->nr_caches = 0; ei->cache_valid_id = EXFAT_CACHE_VALID + 1; INIT_LIST_HEAD(&ei->cache_lru); INIT_HLIST_NODE(&ei->i_hash_fat); inode_init_once(&ei->vfs_inode); } static int __init init_exfat_fs(void) { int err; err = exfat_cache_init(); if (err) return err; exfat_inode_cachep = kmem_cache_create("exfat_inode_cache", sizeof(struct exfat_inode_info), 0, SLAB_RECLAIM_ACCOUNT, exfat_inode_init_once); if (!exfat_inode_cachep) { err = -ENOMEM; goto shutdown_cache; } err = register_filesystem(&exfat_fs_type); if (err) goto destroy_cache; return 0; destroy_cache: kmem_cache_destroy(exfat_inode_cachep); shutdown_cache: exfat_cache_shutdown(); return err; } static void __exit exit_exfat_fs(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(exfat_inode_cachep); unregister_filesystem(&exfat_fs_type); exfat_cache_shutdown(); } module_init(init_exfat_fs); module_exit(exit_exfat_fs); MODULE_ALIAS_FS("exfat"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("exFAT filesystem support"); MODULE_AUTHOR("Samsung Electronics Co., Ltd."); |
| 1320 1319 | 1 2 3 4 5 6 7 8 9 10 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; } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 | // SPDX-License-Identifier: GPL-2.0-only /* * Monitoring code for network dropped packet alerts * * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> #include <linux/if_arp.h> #include <linux/inetdevice.h> #include <linux/inet.h> #include <linux/interrupt.h> #include <linux/netpoll.h> #include <linux/sched.h> #include <linux/delay.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/netlink.h> #include <linux/net_dropmon.h> #include <linux/bitfield.h> #include <linux/percpu.h> #include <linux/timer.h> #include <linux/bitops.h> #include <linux/slab.h> #include <linux/module.h> #include <net/genetlink.h> #include <net/netevent.h> #include <net/flow_offload.h> #include <net/dropreason.h> #include <net/devlink.h> #include <trace/events/skb.h> #include <trace/events/napi.h> #include <trace/events/devlink.h> #include <linux/unaligned.h> #define TRACE_ON 1 #define TRACE_OFF 0 /* * Globals, our netlink socket pointer * and the work handle that will send up * netlink alerts */ static int trace_state = TRACE_OFF; static bool monitor_hw; /* net_dm_mutex * * An overall lock guarding every operation coming from userspace. */ static DEFINE_MUTEX(net_dm_mutex); struct net_dm_stats { u64_stats_t dropped; struct u64_stats_sync syncp; }; #define NET_DM_MAX_HW_TRAP_NAME_LEN 40 struct net_dm_hw_entry { char trap_name[NET_DM_MAX_HW_TRAP_NAME_LEN]; u32 count; }; struct net_dm_hw_entries { u32 num_entries; struct net_dm_hw_entry entries[]; }; struct per_cpu_dm_data { raw_spinlock_t lock; /* Protects 'skb', 'hw_entries' and * 'send_timer' */ union { struct sk_buff *skb; struct net_dm_hw_entries *hw_entries; }; struct sk_buff_head drop_queue; struct work_struct dm_alert_work; struct timer_list send_timer; struct net_dm_stats stats; }; struct dm_hw_stat_delta { unsigned long last_rx; unsigned long last_drop_val; struct rcu_head rcu; }; static struct genl_family net_drop_monitor_family; static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_hw_cpu_data); static int dm_hit_limit = 64; static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static enum net_dm_alert_mode net_dm_alert_mode = NET_DM_ALERT_MODE_SUMMARY; static u32 net_dm_trunc_len; static u32 net_dm_queue_len = 1000; struct net_dm_alert_ops { void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason, struct sock *rx_sk); void (*napi_poll_probe)(void *ignore, struct napi_struct *napi, int work, int budget); void (*work_item_func)(struct work_struct *work); void (*hw_work_item_func)(struct work_struct *work); void (*hw_trap_probe)(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata); }; struct net_dm_skb_cb { union { struct devlink_trap_metadata *hw_metadata; void *pc; }; enum skb_drop_reason reason; }; #define NET_DM_SKB_CB(__skb) ((struct net_dm_skb_cb *)&((__skb)->cb[0])) static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; struct net_dm_alert_msg *msg; struct nlattr *nla; struct sk_buff *skb; unsigned long flags; void *msg_header; al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); al += sizeof(struct nlattr); skb = genlmsg_new(al, GFP_KERNEL); if (!skb) goto err; msg_header = genlmsg_put(skb, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_ALERT); if (!msg_header) { nlmsg_free(skb); skb = NULL; goto err; } nla = nla_reserve(skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg)); if (!nla) { nlmsg_free(skb); skb = NULL; goto err; } msg = nla_data(nla); memset(msg, 0, al); goto out; err: mod_timer(&data->send_timer, jiffies + HZ / 10); out: raw_spin_lock_irqsave(&data->lock, flags); swap(data->skb, skb); raw_spin_unlock_irqrestore(&data->lock, flags); if (skb) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data; struct genlmsghdr *gnlh = (struct genlmsghdr *)nlmsg_data(nlh); genlmsg_end(skb, genlmsg_data(gnlh)); } return skb; } static const struct genl_multicast_group dropmon_mcgrps[] = { { .name = "events", .flags = GENL_MCAST_CAP_SYS_ADMIN, }, }; static void send_dm_alert(struct work_struct *work) { struct sk_buff *skb; struct per_cpu_dm_data *data; data = container_of(work, struct per_cpu_dm_data, dm_alert_work); skb = reset_per_cpu_data(data); if (skb) genlmsg_multicast(&net_drop_monitor_family, skb, 0, 0, GFP_KERNEL); } /* * This is the timer function to delay the sending of an alert * in the event that more drops will arrive during the * hysteresis period. */ static void sched_send_work(struct timer_list *t) { struct per_cpu_dm_data *data = from_timer(data, t, send_timer); schedule_work(&data->dm_alert_work); } static void trace_drop_common(struct sk_buff *skb, void *location) { struct net_dm_alert_msg *msg; struct net_dm_drop_point *point; struct nlmsghdr *nlh; struct nlattr *nla; int i; struct sk_buff *dskb; struct per_cpu_dm_data *data; unsigned long flags; local_irq_save(flags); data = this_cpu_ptr(&dm_cpu_data); raw_spin_lock(&data->lock); dskb = data->skb; if (!dskb) goto out; nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); point = msg->points; for (i = 0; i < msg->entries; i++) { if (!memcmp(&location, &point->pc, sizeof(void *))) { point->count++; goto out; } point++; } if (msg->entries == dm_hit_limit) goto out; /* * We need to create a new entry */ __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); memcpy(point->pc, &location, sizeof(void *)); point->count = 1; msg->entries++; if (!timer_pending(&data->send_timer)) { data->send_timer.expires = jiffies + dm_delay * HZ; add_timer(&data->send_timer); } out: raw_spin_unlock_irqrestore(&data->lock, flags); } static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason, struct sock *rx_sk) { trace_drop_common(skb, location); } static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi, int work, int budget) { struct net_device *dev = napi->dev; struct dm_hw_stat_delta *stat; /* * Don't check napi structures with no associated device */ if (!dev) return; rcu_read_lock(); stat = rcu_dereference(dev->dm_private); if (stat) { /* * only add a note to our monitor buffer if: * 1) its after the last_rx delta * 2) our rx_dropped count has gone up */ if (time_after(jiffies, stat->last_rx + dm_hw_check_delta) && (dev->stats.rx_dropped != stat->last_drop_val)) { trace_drop_common(NULL, NULL); stat->last_drop_val = dev->stats.rx_dropped; stat->last_rx = jiffies; } } rcu_read_unlock(); } static struct net_dm_hw_entries * net_dm_hw_reset_per_cpu_data(struct per_cpu_dm_data *hw_data) { struct net_dm_hw_entries *hw_entries; unsigned long flags; hw_entries = kzalloc(struct_size(hw_entries, entries, dm_hit_limit), GFP_KERNEL); if (!hw_entries) { /* If the memory allocation failed, we try to perform another * allocation in 1/10 second. Otherwise, the probe function * will constantly bail out. */ mod_timer(&hw_data->send_timer, jiffies + HZ / 10); } raw_spin_lock_irqsave(&hw_data->lock, flags); swap(hw_data->hw_entries, hw_entries); raw_spin_unlock_irqrestore(&hw_data->lock, flags); return hw_entries; } static int net_dm_hw_entry_put(struct sk_buff *msg, const struct net_dm_hw_entry *hw_entry) { struct nlattr *attr; attr = nla_nest_start(msg, NET_DM_ATTR_HW_ENTRY); if (!attr) return -EMSGSIZE; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_NAME, hw_entry->trap_name)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_HW_TRAP_COUNT, hw_entry->count)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_hw_entries_put(struct sk_buff *msg, const struct net_dm_hw_entries *hw_entries) { struct nlattr *attr; int i; attr = nla_nest_start(msg, NET_DM_ATTR_HW_ENTRIES); if (!attr) return -EMSGSIZE; for (i = 0; i < hw_entries->num_entries; i++) { int rc; rc = net_dm_hw_entry_put(msg, &hw_entries->entries[i]); if (rc) goto nla_put_failure; } nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_hw_summary_report_fill(struct sk_buff *msg, const struct net_dm_hw_entries *hw_entries) { struct net_dm_alert_msg anc_hdr = { 0 }; void *hdr; int rc; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_ALERT); if (!hdr) return -EMSGSIZE; /* We need to put the ancillary header in order not to break user * space. */ if (nla_put(msg, NLA_UNSPEC, sizeof(anc_hdr), &anc_hdr)) goto nla_put_failure; rc = net_dm_hw_entries_put(msg, hw_entries); if (rc) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void net_dm_hw_summary_work(struct work_struct *work) { struct net_dm_hw_entries *hw_entries; struct per_cpu_dm_data *hw_data; struct sk_buff *msg; int rc; hw_data = container_of(work, struct per_cpu_dm_data, dm_alert_work); hw_entries = net_dm_hw_reset_per_cpu_data(hw_data); if (!hw_entries) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out; rc = net_dm_hw_summary_report_fill(msg, hw_entries); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: kfree(hw_entries); } static void net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata) { struct net_dm_hw_entries *hw_entries; struct net_dm_hw_entry *hw_entry; struct per_cpu_dm_data *hw_data; unsigned long flags; int i; if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) return; hw_data = this_cpu_ptr(&dm_hw_cpu_data); raw_spin_lock_irqsave(&hw_data->lock, flags); hw_entries = hw_data->hw_entries; if (!hw_entries) goto out; for (i = 0; i < hw_entries->num_entries; i++) { hw_entry = &hw_entries->entries[i]; if (!strncmp(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1)) { hw_entry->count++; goto out; } } if (WARN_ON_ONCE(hw_entries->num_entries == dm_hit_limit)) goto out; hw_entry = &hw_entries->entries[hw_entries->num_entries]; strscpy(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1); hw_entry->count = 1; hw_entries->num_entries++; if (!timer_pending(&hw_data->send_timer)) { hw_data->send_timer.expires = jiffies + dm_delay * HZ; add_timer(&hw_data->send_timer); } out: raw_spin_unlock_irqrestore(&hw_data->lock, flags); } static const struct net_dm_alert_ops net_dm_alert_summary_ops = { .kfree_skb_probe = trace_kfree_skb_hit, .napi_poll_probe = trace_napi_poll_hit, .work_item_func = send_dm_alert, .hw_work_item_func = net_dm_hw_summary_work, .hw_trap_probe = net_dm_hw_trap_summary_probe, }; static void net_dm_packet_trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason, struct sock *rx_sk) { ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *data; struct net_dm_skb_cb *cb; struct sk_buff *nskb; unsigned long flags; if (!skb_mac_header_was_set(skb)) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; cb = NET_DM_SKB_CB(nskb); cb->reason = reason; cb->pc = location; /* Override the timestamp because we care about the time when the * packet was dropped. */ nskb->tstamp = tstamp; data = this_cpu_ptr(&dm_cpu_data); spin_lock_irqsave(&data->drop_queue.lock, flags); if (skb_queue_len(&data->drop_queue) < net_dm_queue_len) __skb_queue_tail(&data->drop_queue, nskb); else goto unlock_free; spin_unlock_irqrestore(&data->drop_queue.lock, flags); schedule_work(&data->dm_alert_work); return; unlock_free: spin_unlock_irqrestore(&data->drop_queue.lock, flags); u64_stats_update_begin(&data->stats.syncp); u64_stats_inc(&data->stats.dropped); u64_stats_update_end(&data->stats.syncp); consume_skb(nskb); } static void net_dm_packet_trace_napi_poll_hit(void *ignore, struct napi_struct *napi, int work, int budget) { } static size_t net_dm_in_port_size(void) { /* NET_DM_ATTR_IN_PORT nest */ return nla_total_size(0) + /* NET_DM_ATTR_PORT_NETDEV_IFINDEX */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PORT_NETDEV_NAME */ nla_total_size(IFNAMSIZ + 1); } #define NET_DM_MAX_SYMBOL_LEN 40 #define NET_DM_MAX_REASON_LEN 50 static size_t net_dm_packet_report_size(size_t payload_len) { size_t size; size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); return NLMSG_ALIGN(size) + /* NET_DM_ATTR_ORIGIN */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_PC */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_SYMBOL */ nla_total_size(NET_DM_MAX_SYMBOL_LEN + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + /* NET_DM_ATTR_TIMESTAMP */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_REASON */ nla_total_size(NET_DM_MAX_REASON_LEN + 1) + /* NET_DM_ATTR_PAYLOAD */ nla_total_size(payload_len); } static int net_dm_packet_report_in_port_put(struct sk_buff *msg, int ifindex, const char *name) { struct nlattr *attr; attr = nla_nest_start(msg, NET_DM_ATTR_IN_PORT); if (!attr) return -EMSGSIZE; if (ifindex && nla_put_u32(msg, NET_DM_ATTR_PORT_NETDEV_IFINDEX, ifindex)) goto nla_put_failure; if (name && nla_put_string(msg, NET_DM_ATTR_PORT_NETDEV_NAME, name)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, size_t payload_len) { struct net_dm_skb_cb *cb = NET_DM_SKB_CB(skb); const struct drop_reason_list *list = NULL; unsigned int subsys, subsys_reason; char buf[NET_DM_MAX_SYMBOL_LEN]; struct nlattr *attr; void *hdr; int rc; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_PACKET_ALERT); if (!hdr) return -EMSGSIZE; if (nla_put_u16(msg, NET_DM_ATTR_ORIGIN, NET_DM_ORIGIN_SW)) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_PC, (u64)(uintptr_t)cb->pc, NET_DM_ATTR_PAD)) goto nla_put_failure; rcu_read_lock(); subsys = u32_get_bits(cb->reason, SKB_DROP_REASON_SUBSYS_MASK); if (subsys < SKB_DROP_REASON_SUBSYS_NUM) list = rcu_dereference(drop_reasons_by_subsys[subsys]); subsys_reason = cb->reason & ~SKB_DROP_REASON_SUBSYS_MASK; if (!list || subsys_reason >= list->n_reasons || !list->reasons[subsys_reason] || strlen(list->reasons[subsys_reason]) > NET_DM_MAX_REASON_LEN) { list = rcu_dereference(drop_reasons_by_subsys[SKB_DROP_REASON_SUBSYS_CORE]); subsys_reason = SKB_DROP_REASON_NOT_SPECIFIED; } if (nla_put_string(msg, NET_DM_ATTR_REASON, list->reasons[subsys_reason])) { rcu_read_unlock(); goto nla_put_failure; } rcu_read_unlock(); snprintf(buf, sizeof(buf), "%pS", cb->pc); if (nla_put_string(msg, NET_DM_ATTR_SYMBOL, buf)) goto nla_put_failure; rc = net_dm_packet_report_in_port_put(msg, skb->skb_iif, NULL); if (rc) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_TIMESTAMP, ktime_to_ns(skb->tstamp), NET_DM_ATTR_PAD)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) goto nla_put_failure; if (!payload_len) goto out; if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) goto nla_put_failure; attr = skb_put(msg, nla_total_size(payload_len)); attr->nla_type = NET_DM_ATTR_PAYLOAD; attr->nla_len = nla_attr_size(payload_len); if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) goto nla_put_failure; out: genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } #define NET_DM_MAX_PACKET_SIZE (0xffff - NLA_HDRLEN - NLA_ALIGNTO) static void net_dm_packet_report(struct sk_buff *skb) { struct sk_buff *msg; size_t payload_len; int rc; /* Make sure we start copying the packet from the MAC header */ if (skb->data > skb_mac_header(skb)) skb_push(skb, skb->data - skb_mac_header(skb)); else skb_pull(skb, skb_mac_header(skb) - skb->data); /* Ensure packet fits inside a single netlink attribute */ payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); if (net_dm_trunc_len) payload_len = min_t(size_t, net_dm_trunc_len, payload_len); msg = nlmsg_new(net_dm_packet_report_size(payload_len), GFP_KERNEL); if (!msg) goto out; rc = net_dm_packet_report_fill(msg, skb, payload_len); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: consume_skb(skb); } static void net_dm_packet_work(struct work_struct *work) { struct per_cpu_dm_data *data; struct sk_buff_head list; struct sk_buff *skb; unsigned long flags; data = container_of(work, struct per_cpu_dm_data, dm_alert_work); __skb_queue_head_init(&list); spin_lock_irqsave(&data->drop_queue.lock, flags); skb_queue_splice_tail_init(&data->drop_queue, &list); spin_unlock_irqrestore(&data->drop_queue.lock, flags); while ((skb = __skb_dequeue(&list))) net_dm_packet_report(skb); } static size_t net_dm_flow_action_cookie_size(const struct devlink_trap_metadata *hw_metadata) { return hw_metadata->fa_cookie ? nla_total_size(hw_metadata->fa_cookie->cookie_len) : 0; } static size_t net_dm_hw_packet_report_size(size_t payload_len, const struct devlink_trap_metadata *hw_metadata) { size_t size; size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); return NLMSG_ALIGN(size) + /* NET_DM_ATTR_ORIGIN */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_HW_TRAP_GROUP_NAME */ nla_total_size(strlen(hw_metadata->trap_group_name) + 1) + /* NET_DM_ATTR_HW_TRAP_NAME */ nla_total_size(strlen(hw_metadata->trap_name) + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + /* NET_DM_ATTR_FLOW_ACTION_COOKIE */ net_dm_flow_action_cookie_size(hw_metadata) + /* NET_DM_ATTR_TIMESTAMP */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_PAYLOAD */ nla_total_size(payload_len); } static int net_dm_hw_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, size_t payload_len) { struct devlink_trap_metadata *hw_metadata; struct nlattr *attr; void *hdr; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_PACKET_ALERT); if (!hdr) return -EMSGSIZE; if (nla_put_u16(msg, NET_DM_ATTR_ORIGIN, NET_DM_ORIGIN_HW)) goto nla_put_failure; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_GROUP_NAME, hw_metadata->trap_group_name)) goto nla_put_failure; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_NAME, hw_metadata->trap_name)) goto nla_put_failure; if (hw_metadata->input_dev) { struct net_device *dev = hw_metadata->input_dev; int rc; rc = net_dm_packet_report_in_port_put(msg, dev->ifindex, dev->name); if (rc) goto nla_put_failure; } if (hw_metadata->fa_cookie && nla_put(msg, NET_DM_ATTR_FLOW_ACTION_COOKIE, hw_metadata->fa_cookie->cookie_len, hw_metadata->fa_cookie->cookie)) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_TIMESTAMP, ktime_to_ns(skb->tstamp), NET_DM_ATTR_PAD)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) goto nla_put_failure; if (!payload_len) goto out; if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) goto nla_put_failure; attr = skb_put(msg, nla_total_size(payload_len)); attr->nla_type = NET_DM_ATTR_PAYLOAD; attr->nla_len = nla_attr_size(payload_len); if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) goto nla_put_failure; out: genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static struct devlink_trap_metadata * net_dm_hw_metadata_copy(const struct devlink_trap_metadata *metadata) { const struct flow_action_cookie *fa_cookie; struct devlink_trap_metadata *hw_metadata; const char *trap_group_name; const char *trap_name; hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC); if (!hw_metadata) return NULL; trap_group_name = kstrdup(metadata->trap_group_name, GFP_ATOMIC); if (!trap_group_name) goto free_hw_metadata; hw_metadata->trap_group_name = trap_group_name; trap_name = kstrdup(metadata->trap_name, GFP_ATOMIC); if (!trap_name) goto free_trap_group; hw_metadata->trap_name = trap_name; if (metadata->fa_cookie) { size_t cookie_size = sizeof(*fa_cookie) + metadata->fa_cookie->cookie_len; fa_cookie = kmemdup(metadata->fa_cookie, cookie_size, GFP_ATOMIC); if (!fa_cookie) goto free_trap_name; hw_metadata->fa_cookie = fa_cookie; } hw_metadata->input_dev = metadata->input_dev; netdev_hold(hw_metadata->input_dev, &hw_metadata->dev_tracker, GFP_ATOMIC); return hw_metadata; free_trap_name: kfree(trap_name); free_trap_group: kfree(trap_group_name); free_hw_metadata: kfree(hw_metadata); return NULL; } static void net_dm_hw_metadata_free(struct devlink_trap_metadata *hw_metadata) { netdev_put(hw_metadata->input_dev, &hw_metadata->dev_tracker); kfree(hw_metadata->fa_cookie); kfree(hw_metadata->trap_name); kfree(hw_metadata->trap_group_name); kfree(hw_metadata); } static void net_dm_hw_packet_report(struct sk_buff *skb) { struct devlink_trap_metadata *hw_metadata; struct sk_buff *msg; size_t payload_len; int rc; if (skb->data > skb_mac_header(skb)) skb_push(skb, skb->data - skb_mac_header(skb)); else skb_pull(skb, skb_mac_header(skb) - skb->data); payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); if (net_dm_trunc_len) payload_len = min_t(size_t, net_dm_trunc_len, payload_len); hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; msg = nlmsg_new(net_dm_hw_packet_report_size(payload_len, hw_metadata), GFP_KERNEL); if (!msg) goto out; rc = net_dm_hw_packet_report_fill(msg, skb, payload_len); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: net_dm_hw_metadata_free(NET_DM_SKB_CB(skb)->hw_metadata); consume_skb(skb); } static void net_dm_hw_packet_work(struct work_struct *work) { struct per_cpu_dm_data *hw_data; struct sk_buff_head list; struct sk_buff *skb; unsigned long flags; hw_data = container_of(work, struct per_cpu_dm_data, dm_alert_work); __skb_queue_head_init(&list); spin_lock_irqsave(&hw_data->drop_queue.lock, flags); skb_queue_splice_tail_init(&hw_data->drop_queue, &list); spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); while ((skb = __skb_dequeue(&list))) net_dm_hw_packet_report(skb); } static void net_dm_hw_trap_packet_probe(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata) { struct devlink_trap_metadata *n_hw_metadata; ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *hw_data; struct sk_buff *nskb; unsigned long flags; if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) return; if (!skb_mac_header_was_set(skb)) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; n_hw_metadata = net_dm_hw_metadata_copy(metadata); if (!n_hw_metadata) goto free; NET_DM_SKB_CB(nskb)->hw_metadata = n_hw_metadata; nskb->tstamp = tstamp; hw_data = this_cpu_ptr(&dm_hw_cpu_data); spin_lock_irqsave(&hw_data->drop_queue.lock, flags); if (skb_queue_len(&hw_data->drop_queue) < net_dm_queue_len) __skb_queue_tail(&hw_data->drop_queue, nskb); else goto unlock_free; spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); schedule_work(&hw_data->dm_alert_work); return; unlock_free: spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); u64_stats_update_begin(&hw_data->stats.syncp); u64_stats_inc(&hw_data->stats.dropped); u64_stats_update_end(&hw_data->stats.syncp); net_dm_hw_metadata_free(n_hw_metadata); free: consume_skb(nskb); } static const struct net_dm_alert_ops net_dm_alert_packet_ops = { .kfree_skb_probe = net_dm_packet_trace_kfree_skb_hit, .napi_poll_probe = net_dm_packet_trace_napi_poll_hit, .work_item_func = net_dm_packet_work, .hw_work_item_func = net_dm_hw_packet_work, .hw_trap_probe = net_dm_hw_trap_packet_probe, }; static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = { [NET_DM_ALERT_MODE_SUMMARY] = &net_dm_alert_summary_ops, [NET_DM_ALERT_MODE_PACKET] = &net_dm_alert_packet_ops, }; #if IS_ENABLED(CONFIG_NET_DEVLINK) static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) { return register_trace_devlink_trap_report(ops->hw_trap_probe, NULL); } static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) { unregister_trace_devlink_trap_report(ops->hw_trap_probe, NULL); tracepoint_synchronize_unregister(); } #else static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) { return -EOPNOTSUPP; } static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) { } #endif static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu, rc; if (monitor_hw) { NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already enabled"); return -EAGAIN; } ops = net_dm_alert_ops_arr[net_dm_alert_mode]; if (!try_module_get(THIS_MODULE)) { NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); return -ENODEV; } for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct net_dm_hw_entries *hw_entries; INIT_WORK(&hw_data->dm_alert_work, ops->hw_work_item_func); timer_setup(&hw_data->send_timer, sched_send_work, 0); hw_entries = net_dm_hw_reset_per_cpu_data(hw_data); kfree(hw_entries); } rc = net_dm_hw_probe_register(ops); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to devlink_trap_probe() tracepoint"); goto err_module_put; } monitor_hw = true; return 0; err_module_put: for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct sk_buff *skb; del_timer_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { struct devlink_trap_metadata *hw_metadata; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; net_dm_hw_metadata_free(hw_metadata); consume_skb(skb); } } module_put(THIS_MODULE); return rc; } static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu; if (!monitor_hw) { NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already disabled"); return; } ops = net_dm_alert_ops_arr[net_dm_alert_mode]; monitor_hw = false; net_dm_hw_probe_unregister(ops); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct sk_buff *skb; del_timer_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { struct devlink_trap_metadata *hw_metadata; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; net_dm_hw_metadata_free(hw_metadata); consume_skb(skb); } } module_put(THIS_MODULE); } static int net_dm_trace_on_set(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu, rc; ops = net_dm_alert_ops_arr[net_dm_alert_mode]; if (!try_module_get(THIS_MODULE)) { NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); return -ENODEV; } for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; INIT_WORK(&data->dm_alert_work, ops->work_item_func); timer_setup(&data->send_timer, sched_send_work, 0); /* Allocate a new per-CPU skb for the summary alert message and * free the old one which might contain stale data from * previous tracing. */ skb = reset_per_cpu_data(data); consume_skb(skb); } rc = register_trace_kfree_skb(ops->kfree_skb_probe, NULL); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to kfree_skb() tracepoint"); goto err_module_put; } rc = register_trace_napi_poll(ops->napi_poll_probe, NULL); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to napi_poll() tracepoint"); goto err_unregister_trace; } return 0; err_unregister_trace: unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); err_module_put: for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; del_timer_sync(&data->send_timer); cancel_work_sync(&data->dm_alert_work); while ((skb = __skb_dequeue(&data->drop_queue))) consume_skb(skb); } module_put(THIS_MODULE); return rc; } static void net_dm_trace_off_set(void) { const struct net_dm_alert_ops *ops; int cpu; ops = net_dm_alert_ops_arr[net_dm_alert_mode]; unregister_trace_napi_poll(ops->napi_poll_probe, NULL); unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); tracepoint_synchronize_unregister(); /* Make sure we do not send notifications to user space after request * to stop tracing returns. */ for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; del_timer_sync(&data->send_timer); cancel_work_sync(&data->dm_alert_work); while ((skb = __skb_dequeue(&data->drop_queue))) consume_skb(skb); } module_put(THIS_MODULE); } static int set_all_monitor_traces(int state, struct netlink_ext_ack *extack) { int rc = 0; if (state == trace_state) { NL_SET_ERR_MSG_MOD(extack, "Trace state already set to requested state"); return -EAGAIN; } switch (state) { case TRACE_ON: rc = net_dm_trace_on_set(extack); break; case TRACE_OFF: net_dm_trace_off_set(); break; default: rc = 1; break; } if (!rc) trace_state = state; else rc = -EINPROGRESS; return rc; } static bool net_dm_is_monitoring(void) { return trace_state == TRACE_ON || monitor_hw; } static int net_dm_alert_mode_get_from_info(struct genl_info *info, enum net_dm_alert_mode *p_alert_mode) { u8 val; val = nla_get_u8(info->attrs[NET_DM_ATTR_ALERT_MODE]); switch (val) { case NET_DM_ALERT_MODE_SUMMARY: case NET_DM_ALERT_MODE_PACKET: *p_alert_mode = val; break; default: return -EINVAL; } return 0; } static int net_dm_alert_mode_set(struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; enum net_dm_alert_mode alert_mode; int rc; if (!info->attrs[NET_DM_ATTR_ALERT_MODE]) return 0; rc = net_dm_alert_mode_get_from_info(info, &alert_mode); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Invalid alert mode"); return -EINVAL; } net_dm_alert_mode = alert_mode; return 0; } static void net_dm_trunc_len_set(struct genl_info *info) { if (!info->attrs[NET_DM_ATTR_TRUNC_LEN]) return; net_dm_trunc_len = nla_get_u32(info->attrs[NET_DM_ATTR_TRUNC_LEN]); } static void net_dm_queue_len_set(struct genl_info *info) { if (!info->attrs[NET_DM_ATTR_QUEUE_LEN]) return; net_dm_queue_len = nla_get_u32(info->attrs[NET_DM_ATTR_QUEUE_LEN]); } static int net_dm_cmd_config(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; int rc; if (net_dm_is_monitoring()) { NL_SET_ERR_MSG_MOD(extack, "Cannot configure drop monitor during monitoring"); return -EBUSY; } rc = net_dm_alert_mode_set(info); if (rc) return rc; net_dm_trunc_len_set(info); net_dm_queue_len_set(info); return 0; } static int net_dm_monitor_start(bool set_sw, bool set_hw, struct netlink_ext_ack *extack) { bool sw_set = false; int rc; if (set_sw) { rc = set_all_monitor_traces(TRACE_ON, extack); if (rc) return rc; sw_set = true; } if (set_hw) { rc = net_dm_hw_monitor_start(extack); if (rc) goto err_monitor_hw; } return 0; err_monitor_hw: if (sw_set) set_all_monitor_traces(TRACE_OFF, extack); return rc; } static void net_dm_monitor_stop(bool set_sw, bool set_hw, struct netlink_ext_ack *extack) { if (set_hw) net_dm_hw_monitor_stop(extack); if (set_sw) set_all_monitor_traces(TRACE_OFF, extack); } static int net_dm_cmd_trace(struct sk_buff *skb, struct genl_info *info) { bool set_sw = !!info->attrs[NET_DM_ATTR_SW_DROPS]; bool set_hw = !!info->attrs[NET_DM_ATTR_HW_DROPS]; struct netlink_ext_ack *extack = info->extack; /* To maintain backward compatibility, we start / stop monitoring of * software drops if no flag is specified. */ if (!set_sw && !set_hw) set_sw = true; switch (info->genlhdr->cmd) { case NET_DM_CMD_START: return net_dm_monitor_start(set_sw, set_hw, extack); case NET_DM_CMD_STOP: net_dm_monitor_stop(set_sw, set_hw, extack); return 0; } return -EOPNOTSUPP; } static int net_dm_config_fill(struct sk_buff *msg, struct genl_info *info) { void *hdr; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &net_drop_monitor_family, 0, NET_DM_CMD_CONFIG_NEW); if (!hdr) return -EMSGSIZE; if (nla_put_u8(msg, NET_DM_ATTR_ALERT_MODE, net_dm_alert_mode)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_TRUNC_LEN, net_dm_trunc_len)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_QUEUE_LEN, net_dm_queue_len)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int net_dm_cmd_config_get(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; int rc; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; rc = net_dm_config_fill(msg, info); if (rc) goto free_msg; return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); return rc; } static void net_dm_stats_read(struct net_dm_stats *stats) { int cpu; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct net_dm_stats *cpu_stats = &data->stats; unsigned int start; u64 dropped; do { start = u64_stats_fetch_begin(&cpu_stats->syncp); dropped = u64_stats_read(&cpu_stats->dropped); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->dropped, dropped); } } static int net_dm_stats_put(struct sk_buff *msg) { struct net_dm_stats stats; struct nlattr *attr; net_dm_stats_read(&stats); attr = nla_nest_start(msg, NET_DM_ATTR_STATS); if (!attr) return -EMSGSIZE; if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, u64_stats_read(&stats.dropped), NET_DM_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static void net_dm_hw_stats_read(struct net_dm_stats *stats) { int cpu; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct net_dm_stats *cpu_stats = &hw_data->stats; unsigned int start; u64 dropped; do { start = u64_stats_fetch_begin(&cpu_stats->syncp); dropped = u64_stats_read(&cpu_stats->dropped); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->dropped, dropped); } } static int net_dm_hw_stats_put(struct sk_buff *msg) { struct net_dm_stats stats; struct nlattr *attr; net_dm_hw_stats_read(&stats); attr = nla_nest_start(msg, NET_DM_ATTR_HW_STATS); if (!attr) return -EMSGSIZE; if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, u64_stats_read(&stats.dropped), NET_DM_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_stats_fill(struct sk_buff *msg, struct genl_info *info) { void *hdr; int rc; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &net_drop_monitor_family, 0, NET_DM_CMD_STATS_NEW); if (!hdr) return -EMSGSIZE; rc = net_dm_stats_put(msg); if (rc) goto nla_put_failure; rc = net_dm_hw_stats_put(msg); if (rc) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int net_dm_cmd_stats_get(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; int rc; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; rc = net_dm_stats_fill(msg, info); if (rc) goto free_msg; return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); return rc; } static int dropmon_net_event(struct notifier_block *ev_block, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dm_hw_stat_delta *stat; switch (event) { case NETDEV_REGISTER: if (WARN_ON_ONCE(rtnl_dereference(dev->dm_private))) break; stat = kzalloc(sizeof(*stat), GFP_KERNEL); if (!stat) break; stat->last_rx = jiffies; rcu_assign_pointer(dev->dm_private, stat); break; case NETDEV_UNREGISTER: stat = rtnl_dereference(dev->dm_private); if (stat) { rcu_assign_pointer(dev->dm_private, NULL); kfree_rcu(stat, rcu); } break; } return NOTIFY_DONE; } static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = { [NET_DM_ATTR_UNSPEC] = { .strict_start_type = NET_DM_ATTR_UNSPEC + 1 }, [NET_DM_ATTR_ALERT_MODE] = { .type = NLA_U8 }, [NET_DM_ATTR_TRUNC_LEN] = { .type = NLA_U32 }, [NET_DM_ATTR_QUEUE_LEN] = { .type = NLA_U32 }, [NET_DM_ATTR_SW_DROPS] = {. type = NLA_FLAG }, [NET_DM_ATTR_HW_DROPS] = {. type = NLA_FLAG }, }; static const struct genl_small_ops dropmon_ops[] = { { .cmd = NET_DM_CMD_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_config, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_START, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_STOP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_CONFIG_GET, .doit = net_dm_cmd_config_get, }, { .cmd = NET_DM_CMD_STATS_GET, .doit = net_dm_cmd_stats_get, }, }; static int net_dm_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_lock(&net_dm_mutex); return 0; } static void net_dm_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_unlock(&net_dm_mutex); } static struct genl_family net_drop_monitor_family __ro_after_init = { .hdrsize = 0, .name = "NET_DM", .version = 2, .maxattr = NET_DM_ATTR_MAX, .policy = net_dm_nl_policy, .pre_doit = net_dm_nl_pre_doit, .post_doit = net_dm_nl_post_doit, .module = THIS_MODULE, .small_ops = dropmon_ops, .n_small_ops = ARRAY_SIZE(dropmon_ops), .resv_start_op = NET_DM_CMD_STATS_GET + 1, .mcgrps = dropmon_mcgrps, .n_mcgrps = ARRAY_SIZE(dropmon_mcgrps), }; static struct notifier_block dropmon_net_notifier = { .notifier_call = dropmon_net_event }; static void __net_dm_cpu_data_init(struct per_cpu_dm_data *data) { raw_spin_lock_init(&data->lock); skb_queue_head_init(&data->drop_queue); u64_stats_init(&data->stats.syncp); } static void __net_dm_cpu_data_fini(struct per_cpu_dm_data *data) { WARN_ON(!skb_queue_empty(&data->drop_queue)); } static void net_dm_cpu_data_init(int cpu) { struct per_cpu_dm_data *data; data = &per_cpu(dm_cpu_data, cpu); __net_dm_cpu_data_init(data); } static void net_dm_cpu_data_fini(int cpu) { struct per_cpu_dm_data *data; data = &per_cpu(dm_cpu_data, cpu); /* At this point, we should have exclusive access * to this struct and can free the skb inside it. */ consume_skb(data->skb); __net_dm_cpu_data_fini(data); } static void net_dm_hw_cpu_data_init(int cpu) { struct per_cpu_dm_data *hw_data; hw_data = &per_cpu(dm_hw_cpu_data, cpu); __net_dm_cpu_data_init(hw_data); } static void net_dm_hw_cpu_data_fini(int cpu) { struct per_cpu_dm_data *hw_data; hw_data = &per_cpu(dm_hw_cpu_data, cpu); kfree(hw_data->hw_entries); __net_dm_cpu_data_fini(hw_data); } static int __init init_net_drop_monitor(void) { int cpu, rc; pr_info("Initializing network drop monitor service\n"); if (sizeof(void *) > 8) { pr_err("Unable to store program counters on this arch, Drop monitor failed\n"); return -ENOSPC; } for_each_possible_cpu(cpu) { net_dm_cpu_data_init(cpu); net_dm_hw_cpu_data_init(cpu); } rc = register_netdevice_notifier(&dropmon_net_notifier); if (rc < 0) { pr_crit("Failed to register netdevice notifier\n"); return rc; } rc = genl_register_family(&net_drop_monitor_family); if (rc) { pr_err("Could not create drop monitor netlink family\n"); goto out_unreg; } WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = 0; goto out; out_unreg: WARN_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); out: return rc; } static void exit_net_drop_monitor(void) { int cpu; /* * Because of the module_get/put we do in the trace state change path * we are guaranteed not to have any current users when we get here */ BUG_ON(genl_unregister_family(&net_drop_monitor_family)); BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); for_each_possible_cpu(cpu) { net_dm_hw_cpu_data_fini(cpu); net_dm_cpu_data_fini(cpu); } } module_init(init_net_drop_monitor); module_exit(exit_net_drop_monitor); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>"); MODULE_ALIAS_GENL_FAMILY("NET_DM"); MODULE_DESCRIPTION("Monitoring code for network dropped packet alerts"); |
| 27 278 | 1 2 3 4 5 6 7 8 9 10 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * inode.h * * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. */ #ifndef OCFS2_INODE_H #define OCFS2_INODE_H #include "extent_map.h" /* OCFS2 Inode Private Data */ struct ocfs2_inode_info { u64 ip_blkno; struct ocfs2_lock_res ip_rw_lockres; struct ocfs2_lock_res ip_inode_lockres; struct ocfs2_lock_res ip_open_lockres; /* protects allocation changes on this inode. */ struct rw_semaphore ip_alloc_sem; /* protects extended attribute changes on this inode */ struct rw_semaphore ip_xattr_sem; /* These fields are protected by ip_lock */ spinlock_t ip_lock; u32 ip_open_count; struct list_head ip_io_markers; u32 ip_clusters; u16 ip_dyn_features; struct mutex ip_io_mutex; u32 ip_flags; /* see below */ u32 ip_attr; /* inode attributes */ /* Record unwritten extents during direct io. */ struct list_head ip_unwritten_list; /* protected by recovery_lock. */ struct inode *ip_next_orphan; struct ocfs2_caching_info ip_metadata_cache; struct ocfs2_extent_map ip_extent_map; struct inode vfs_inode; struct jbd2_inode ip_jinode; u32 ip_dir_start_lookup; /* Only valid if the inode is the dir. */ u32 ip_last_used_slot; u64 ip_last_used_group; u32 ip_dir_lock_gen; struct ocfs2_alloc_reservation ip_la_data_resv; /* * Transactions that contain inode's metadata needed to complete * fsync and fdatasync, respectively. */ tid_t i_sync_tid; tid_t i_datasync_tid; struct dquot __rcu *i_dquot[MAXQUOTAS]; }; /* * Flags for the ip_flags field */ /* System file inodes */ #define OCFS2_INODE_SYSTEM_FILE 0x00000001 #define OCFS2_INODE_JOURNAL 0x00000002 #define OCFS2_INODE_BITMAP 0x00000004 /* This inode has been wiped from disk */ #define OCFS2_INODE_DELETED 0x00000008 /* Has the inode been orphaned on another node? * * This hints to ocfs2_drop_inode that it should clear i_nlink before * continuing. * * We *only* set this on unlink vote from another node. If the inode * was locally orphaned, then we're sure of the state and don't need * to twiddle i_nlink later - it's either zero or not depending on * whether our unlink succeeded. Otherwise we got this from a node * whose intention was to orphan the inode, however he may have * crashed, failed etc, so we let ocfs2_drop_inode zero the value and * rely on ocfs2_delete_inode to sort things out under the proper * cluster locks. */ #define OCFS2_INODE_MAYBE_ORPHANED 0x00000010 /* Does someone have the file open O_DIRECT */ #define OCFS2_INODE_OPEN_DIRECT 0x00000020 /* Tell the inode wipe code it's not in orphan dir */ #define OCFS2_INODE_SKIP_ORPHAN_DIR 0x00000040 /* Entry in orphan dir with 'dio-' prefix */ #define OCFS2_INODE_DIO_ORPHAN_ENTRY 0x00000080 static inline struct ocfs2_inode_info *OCFS2_I(struct inode *inode) { return container_of(inode, struct ocfs2_inode_info, vfs_inode); } #define INODE_JOURNAL(i) (OCFS2_I(i)->ip_flags & OCFS2_INODE_JOURNAL) #define SET_INODE_JOURNAL(i) (OCFS2_I(i)->ip_flags |= OCFS2_INODE_JOURNAL) extern const struct address_space_operations ocfs2_aops; extern const struct ocfs2_caching_operations ocfs2_inode_caching_ops; static inline struct ocfs2_caching_info *INODE_CACHE(struct inode *inode) { return &OCFS2_I(inode)->ip_metadata_cache; } void ocfs2_evict_inode(struct inode *inode); int ocfs2_drop_inode(struct inode *inode); /* Flags for ocfs2_iget() */ #define OCFS2_FI_FLAG_SYSFILE 0x1 #define OCFS2_FI_FLAG_ORPHAN_RECOVERY 0x2 #define OCFS2_FI_FLAG_FILECHECK_CHK 0x4 #define OCFS2_FI_FLAG_FILECHECK_FIX 0x8 struct inode *ocfs2_ilookup(struct super_block *sb, u64 feoff); struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 feoff, unsigned flags, int sysfile_type); int ocfs2_inode_revalidate(struct dentry *dentry); void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, int create_ino); void ocfs2_sync_blockdev(struct super_block *sb); void ocfs2_refresh_inode(struct inode *inode, struct ocfs2_dinode *fe); int ocfs2_mark_inode_dirty(handle_t *handle, struct inode *inode, struct buffer_head *bh); void ocfs2_set_inode_flags(struct inode *inode); void ocfs2_get_inode_flags(struct ocfs2_inode_info *oi); static inline blkcnt_t ocfs2_inode_sector_count(struct inode *inode) { int c_to_s_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits - 9; return (blkcnt_t)OCFS2_I(inode)->ip_clusters << c_to_s_bits; } /* Validate that a bh contains a valid inode */ int ocfs2_validate_inode_block(struct super_block *sb, struct buffer_head *bh); /* * Read an inode block into *bh. If *bh is NULL, a bh will be allocated. * This is a cached read. The inode will be validated with * ocfs2_validate_inode_block(). */ int ocfs2_read_inode_block(struct inode *inode, struct buffer_head **bh); /* The same, but can be passed OCFS2_BH_* flags */ int ocfs2_read_inode_block_full(struct inode *inode, struct buffer_head **bh, int flags); static inline struct ocfs2_inode_info *cache_info_to_inode(struct ocfs2_caching_info *ci) { return container_of(ci, struct ocfs2_inode_info, ip_metadata_cache); } /* Does this inode have the reflink flag set? */ static inline bool ocfs2_is_refcount_inode(struct inode *inode) { return (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL); } #endif /* OCFS2_INODE_H */ |
| 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 | // SPDX-License-Identifier: GPL-2.0 /* * buffered writeback throttling. loosely based on CoDel. We can't drop * packets for IO scheduling, so the logic is something like this: * * - Monitor latencies in a defined window of time. * - If the minimum latency in the above window exceeds some target, increment * scaling step and scale down queue depth by a factor of 2x. The monitoring * window is then shrunk to 100 / sqrt(scaling step + 1). * - For any window where we don't have solid data on what the latencies * look like, retain status quo. * - If latencies look good, decrement scaling step. * - If we're only doing writes, allow the scaling step to go negative. This * will temporarily boost write performance, snapping back to a stable * scaling step of 0 if reads show up or the heavy writers finish. Unlike * positive scaling steps where we shrink the monitoring window, a negative * scaling step retains the default step==0 window size. * * Copyright (C) 2016 Jens Axboe * */ #include <linux/kernel.h> #include <linux/blk_types.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/swap.h> #include "blk-stat.h" #include "blk-wbt.h" #include "blk-rq-qos.h" #include "elevator.h" #include "blk.h" #define CREATE_TRACE_POINTS #include <trace/events/wbt.h> enum wbt_flags { WBT_TRACKED = 1, /* write, tracked for throttling */ WBT_READ = 2, /* read */ WBT_SWAP = 4, /* write, from swap_writepage() */ WBT_DISCARD = 8, /* discard */ WBT_NR_BITS = 4, /* number of bits */ }; enum { WBT_RWQ_BG = 0, WBT_RWQ_SWAP, WBT_RWQ_DISCARD, WBT_NUM_RWQ, }; /* * If current state is WBT_STATE_ON/OFF_DEFAULT, it can be covered to any other * state, if current state is WBT_STATE_ON/OFF_MANUAL, it can only be covered * to WBT_STATE_OFF/ON_MANUAL. */ enum { WBT_STATE_ON_DEFAULT = 1, /* on by default */ WBT_STATE_ON_MANUAL = 2, /* on manually by sysfs */ WBT_STATE_OFF_DEFAULT = 3, /* off by default */ WBT_STATE_OFF_MANUAL = 4, /* off manually by sysfs */ }; struct rq_wb { /* * Settings that govern how we throttle */ unsigned int wb_background; /* background writeback */ unsigned int wb_normal; /* normal writeback */ short enable_state; /* WBT_STATE_* */ /* * Number of consecutive periods where we don't have enough * information to make a firm scale up/down decision. */ unsigned int unknown_cnt; u64 win_nsec; /* default window size */ u64 cur_win_nsec; /* current window size */ struct blk_stat_callback *cb; u64 sync_issue; void *sync_cookie; unsigned long last_issue; /* last non-throttled issue */ unsigned long last_comp; /* last non-throttled comp */ unsigned long min_lat_nsec; struct rq_qos rqos; struct rq_wait rq_wait[WBT_NUM_RWQ]; struct rq_depth rq_depth; }; static inline struct rq_wb *RQWB(struct rq_qos *rqos) { return container_of(rqos, struct rq_wb, rqos); } static inline void wbt_clear_state(struct request *rq) { rq->wbt_flags = 0; } static inline enum wbt_flags wbt_flags(struct request *rq) { return rq->wbt_flags; } static inline bool wbt_is_tracked(struct request *rq) { return rq->wbt_flags & WBT_TRACKED; } static inline bool wbt_is_read(struct request *rq) { return rq->wbt_flags & WBT_READ; } enum { /* * Default setting, we'll scale up (to 75% of QD max) or down (min 1) * from here depending on device stats */ RWB_DEF_DEPTH = 16, /* * 100msec window */ RWB_WINDOW_NSEC = 100 * 1000 * 1000ULL, /* * Disregard stats, if we don't meet this minimum */ RWB_MIN_WRITE_SAMPLES = 3, /* * If we have this number of consecutive windows without enough * information to scale up or down, slowly return to center state * (step == 0). */ RWB_UNKNOWN_BUMP = 5, }; static inline bool rwb_enabled(struct rq_wb *rwb) { return rwb && rwb->enable_state != WBT_STATE_OFF_DEFAULT && rwb->enable_state != WBT_STATE_OFF_MANUAL; } static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) { if (rwb_enabled(rwb)) { const unsigned long cur = jiffies; if (cur != *var) *var = cur; } } /* * If a task was rate throttled in balance_dirty_pages() within the last * second or so, use that to indicate a higher cleaning rate. */ static bool wb_recent_wait(struct rq_wb *rwb) { struct backing_dev_info *bdi = rwb->rqos.disk->bdi; return time_before(jiffies, bdi->last_bdp_sleep + HZ); } static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, enum wbt_flags wb_acct) { if (wb_acct & WBT_SWAP) return &rwb->rq_wait[WBT_RWQ_SWAP]; else if (wb_acct & WBT_DISCARD) return &rwb->rq_wait[WBT_RWQ_DISCARD]; return &rwb->rq_wait[WBT_RWQ_BG]; } static void rwb_wake_all(struct rq_wb *rwb) { int i; for (i = 0; i < WBT_NUM_RWQ; i++) { struct rq_wait *rqw = &rwb->rq_wait[i]; if (wq_has_sleeper(&rqw->wait)) wake_up_all(&rqw->wait); } } static void wbt_rqw_done(struct rq_wb *rwb, struct rq_wait *rqw, enum wbt_flags wb_acct) { int inflight, limit; inflight = atomic_dec_return(&rqw->inflight); /* * For discards, our limit is always the background. For writes, if * the device does write back caching, drop further down before we * wake people up. */ if (wb_acct & WBT_DISCARD) limit = rwb->wb_background; else if (blk_queue_write_cache(rwb->rqos.disk->queue) && !wb_recent_wait(rwb)) limit = 0; else limit = rwb->wb_normal; /* * Don't wake anyone up if we are above the normal limit. */ if (inflight && inflight >= limit) return; if (wq_has_sleeper(&rqw->wait)) { int diff = limit - inflight; if (!inflight || diff >= rwb->wb_background / 2) wake_up_all(&rqw->wait); } } static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct) { struct rq_wb *rwb = RQWB(rqos); struct rq_wait *rqw; if (!(wb_acct & WBT_TRACKED)) return; rqw = get_rq_wait(rwb, wb_acct); wbt_rqw_done(rwb, rqw, wb_acct); } /* * Called on completion of a request. Note that it's also called when * a request is merged, when the request gets freed. */ static void wbt_done(struct rq_qos *rqos, struct request *rq) { struct rq_wb *rwb = RQWB(rqos); if (!wbt_is_tracked(rq)) { if (rwb->sync_cookie == rq) { rwb->sync_issue = 0; rwb->sync_cookie = NULL; } if (wbt_is_read(rq)) wb_timestamp(rwb, &rwb->last_comp); } else { WARN_ON_ONCE(rq == rwb->sync_cookie); __wbt_done(rqos, wbt_flags(rq)); } wbt_clear_state(rq); } static inline bool stat_sample_valid(struct blk_rq_stat *stat) { /* * We need at least one read sample, and a minimum of * RWB_MIN_WRITE_SAMPLES. We require some write samples to know * that it's writes impacting us, and not just some sole read on * a device that is in a lower power state. */ return (stat[READ].nr_samples >= 1 && stat[WRITE].nr_samples >= RWB_MIN_WRITE_SAMPLES); } static u64 rwb_sync_issue_lat(struct rq_wb *rwb) { u64 issue = READ_ONCE(rwb->sync_issue); if (!issue || !rwb->sync_cookie) return 0; return blk_time_get_ns() - issue; } static inline unsigned int wbt_inflight(struct rq_wb *rwb) { unsigned int i, ret = 0; for (i = 0; i < WBT_NUM_RWQ; i++) ret += atomic_read(&rwb->rq_wait[i].inflight); return ret; } enum { LAT_OK = 1, LAT_UNKNOWN, LAT_UNKNOWN_WRITES, LAT_EXCEEDED, }; static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) { struct backing_dev_info *bdi = rwb->rqos.disk->bdi; struct rq_depth *rqd = &rwb->rq_depth; u64 thislat; /* * If our stored sync issue exceeds the window size, or it * exceeds our min target AND we haven't logged any entries, * flag the latency as exceeded. wbt works off completion latencies, * but for a flooded device, a single sync IO can take a long time * to complete after being issued. If this time exceeds our * monitoring window AND we didn't see any other completions in that * window, then count that sync IO as a violation of the latency. */ thislat = rwb_sync_issue_lat(rwb); if (thislat > rwb->cur_win_nsec || (thislat > rwb->min_lat_nsec && !stat[READ].nr_samples)) { trace_wbt_lat(bdi, thislat); return LAT_EXCEEDED; } /* * No read/write mix, if stat isn't valid */ if (!stat_sample_valid(stat)) { /* * If we had writes in this stat window and the window is * current, we're only doing writes. If a task recently * waited or still has writes in flights, consider us doing * just writes as well. */ if (stat[WRITE].nr_samples || wb_recent_wait(rwb) || wbt_inflight(rwb)) return LAT_UNKNOWN_WRITES; return LAT_UNKNOWN; } /* * If the 'min' latency exceeds our target, step down. */ if (stat[READ].min > rwb->min_lat_nsec) { trace_wbt_lat(bdi, stat[READ].min); trace_wbt_stat(bdi, stat); return LAT_EXCEEDED; } if (rqd->scale_step) trace_wbt_stat(bdi, stat); return LAT_OK; } static void rwb_trace_step(struct rq_wb *rwb, const char *msg) { struct backing_dev_info *bdi = rwb->rqos.disk->bdi; struct rq_depth *rqd = &rwb->rq_depth; trace_wbt_step(bdi, msg, rqd->scale_step, rwb->cur_win_nsec, rwb->wb_background, rwb->wb_normal, rqd->max_depth); } static void calc_wb_limits(struct rq_wb *rwb) { if (rwb->min_lat_nsec == 0) { rwb->wb_normal = rwb->wb_background = 0; } else if (rwb->rq_depth.max_depth <= 2) { rwb->wb_normal = rwb->rq_depth.max_depth; rwb->wb_background = 1; } else { rwb->wb_normal = (rwb->rq_depth.max_depth + 1) / 2; rwb->wb_background = (rwb->rq_depth.max_depth + 3) / 4; } } static void scale_up(struct rq_wb *rwb) { if (!rq_depth_scale_up(&rwb->rq_depth)) return; calc_wb_limits(rwb); rwb->unknown_cnt = 0; rwb_wake_all(rwb); rwb_trace_step(rwb, tracepoint_string("scale up")); } static void scale_down(struct rq_wb *rwb, bool hard_throttle) { if (!rq_depth_scale_down(&rwb->rq_depth, hard_throttle)) return; calc_wb_limits(rwb); rwb->unknown_cnt = 0; rwb_trace_step(rwb, tracepoint_string("scale down")); } static void rwb_arm_timer(struct rq_wb *rwb) { struct rq_depth *rqd = &rwb->rq_depth; if (rqd->scale_step > 0) { /* * We should speed this up, using some variant of a fast * integer inverse square root calculation. Since we only do * this for every window expiration, it's not a huge deal, * though. */ rwb->cur_win_nsec = div_u64(rwb->win_nsec << 4, int_sqrt((rqd->scale_step + 1) << 8)); } else { /* * For step < 0, we don't want to increase/decrease the * window size. */ rwb->cur_win_nsec = rwb->win_nsec; } blk_stat_activate_nsecs(rwb->cb, rwb->cur_win_nsec); } static void wb_timer_fn(struct blk_stat_callback *cb) { struct rq_wb *rwb = cb->data; struct rq_depth *rqd = &rwb->rq_depth; unsigned int inflight = wbt_inflight(rwb); int status; if (!rwb->rqos.disk) return; status = latency_exceeded(rwb, cb->stat); trace_wbt_timer(rwb->rqos.disk->bdi, status, rqd->scale_step, inflight); /* * If we exceeded the latency target, step down. If we did not, * step one level up. If we don't know enough to say either exceeded * or ok, then don't do anything. */ switch (status) { case LAT_EXCEEDED: scale_down(rwb, true); break; case LAT_OK: scale_up(rwb); break; case LAT_UNKNOWN_WRITES: /* * We don't have a valid read/write sample, but we do have * writes going on. Allow step to go negative, to increase * write performance. */ scale_up(rwb); break; case LAT_UNKNOWN: if (++rwb->unknown_cnt < RWB_UNKNOWN_BUMP) break; /* * We get here when previously scaled reduced depth, and we * currently don't have a valid read/write sample. For that * case, slowly return to center state (step == 0). */ if (rqd->scale_step > 0) scale_up(rwb); else if (rqd->scale_step < 0) scale_down(rwb, false); break; default: break; } /* * Re-arm timer, if we have IO in flight */ if (rqd->scale_step || inflight) rwb_arm_timer(rwb); } static void wbt_update_limits(struct rq_wb *rwb) { struct rq_depth *rqd = &rwb->rq_depth; rqd->scale_step = 0; rqd->scaled_max = false; rq_depth_calc_max_depth(rqd); calc_wb_limits(rwb); rwb_wake_all(rwb); } bool wbt_disabled(struct request_queue *q) { struct rq_qos *rqos = wbt_rq_qos(q); return !rqos || !rwb_enabled(RQWB(rqos)); } u64 wbt_get_min_lat(struct request_queue *q) { struct rq_qos *rqos = wbt_rq_qos(q); if (!rqos) return 0; return RQWB(rqos)->min_lat_nsec; } void wbt_set_min_lat(struct request_queue *q, u64 val) { struct rq_qos *rqos = wbt_rq_qos(q); if (!rqos) return; RQWB(rqos)->min_lat_nsec = val; if (val) RQWB(rqos)->enable_state = WBT_STATE_ON_MANUAL; else RQWB(rqos)->enable_state = WBT_STATE_OFF_MANUAL; wbt_update_limits(RQWB(rqos)); } static bool close_io(struct rq_wb *rwb) { const unsigned long now = jiffies; return time_before(now, rwb->last_issue + HZ / 10) || time_before(now, rwb->last_comp + HZ / 10); } #define REQ_HIPRIO (REQ_SYNC | REQ_META | REQ_PRIO | REQ_SWAP) static inline unsigned int get_limit(struct rq_wb *rwb, blk_opf_t opf) { unsigned int limit; if ((opf & REQ_OP_MASK) == REQ_OP_DISCARD) return rwb->wb_background; /* * At this point we know it's a buffered write. If this is * swap trying to free memory, or REQ_SYNC is set, then * it's WB_SYNC_ALL writeback, and we'll use the max limit for * that. If the write is marked as a background write, then use * the idle limit, or go to normal if we haven't had competing * IO for a bit. */ if ((opf & REQ_HIPRIO) || wb_recent_wait(rwb)) limit = rwb->rq_depth.max_depth; else if ((opf & REQ_BACKGROUND) || close_io(rwb)) { /* * If less than 100ms since we completed unrelated IO, * limit us to half the depth for background writeback. */ limit = rwb->wb_background; } else limit = rwb->wb_normal; return limit; } struct wbt_wait_data { struct rq_wb *rwb; enum wbt_flags wb_acct; blk_opf_t opf; }; static bool wbt_inflight_cb(struct rq_wait *rqw, void *private_data) { struct wbt_wait_data *data = private_data; return rq_wait_inc_below(rqw, get_limit(data->rwb, data->opf)); } static void wbt_cleanup_cb(struct rq_wait *rqw, void *private_data) { struct wbt_wait_data *data = private_data; wbt_rqw_done(data->rwb, rqw, data->wb_acct); } /* * Block if we will exceed our limit, or if we are currently waiting for * the timer to kick off queuing again. */ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct, blk_opf_t opf) { struct rq_wait *rqw = get_rq_wait(rwb, wb_acct); struct wbt_wait_data data = { .rwb = rwb, .wb_acct = wb_acct, .opf = opf, }; rq_qos_wait(rqw, &data, wbt_inflight_cb, wbt_cleanup_cb); } static inline bool wbt_should_throttle(struct bio *bio) { switch (bio_op(bio)) { case REQ_OP_WRITE: /* * Don't throttle WRITE_ODIRECT */ if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) == (REQ_SYNC | REQ_IDLE)) return false; fallthrough; case REQ_OP_DISCARD: return true; default: return false; } } static enum wbt_flags bio_to_wbt_flags(struct rq_wb *rwb, struct bio *bio) { enum wbt_flags flags = 0; if (!rwb_enabled(rwb)) return 0; if (bio_op(bio) == REQ_OP_READ) { flags = WBT_READ; } else if (wbt_should_throttle(bio)) { if (bio->bi_opf & REQ_SWAP) flags |= WBT_SWAP; if (bio_op(bio) == REQ_OP_DISCARD) flags |= WBT_DISCARD; flags |= WBT_TRACKED; } return flags; } static void wbt_cleanup(struct rq_qos *rqos, struct bio *bio) { struct rq_wb *rwb = RQWB(rqos); enum wbt_flags flags = bio_to_wbt_flags(rwb, bio); __wbt_done(rqos, flags); } /* May sleep, if we have exceeded the writeback limits. */ static void wbt_wait(struct rq_qos *rqos, struct bio *bio) { struct rq_wb *rwb = RQWB(rqos); enum wbt_flags flags; flags = bio_to_wbt_flags(rwb, bio); if (!(flags & WBT_TRACKED)) { if (flags & WBT_READ) wb_timestamp(rwb, &rwb->last_issue); return; } __wbt_wait(rwb, flags, bio->bi_opf); if (!blk_stat_is_active(rwb->cb)) rwb_arm_timer(rwb); } static void wbt_track(struct rq_qos *rqos, struct request *rq, struct bio *bio) { struct rq_wb *rwb = RQWB(rqos); rq->wbt_flags |= bio_to_wbt_flags(rwb, bio); } static void wbt_issue(struct rq_qos *rqos, struct request *rq) { struct rq_wb *rwb = RQWB(rqos); if (!rwb_enabled(rwb)) return; /* * Track sync issue, in case it takes a long time to complete. Allows us * to react quicker, if a sync IO takes a long time to complete. Note * that this is just a hint. The request can go away when it completes, * so it's important we never dereference it. We only use the address to * compare with, which is why we store the sync_issue time locally. */ if (wbt_is_read(rq) && !rwb->sync_issue) { rwb->sync_cookie = rq; rwb->sync_issue = rq->io_start_time_ns; } } static void wbt_requeue(struct rq_qos *rqos, struct request *rq) { struct rq_wb *rwb = RQWB(rqos); if (!rwb_enabled(rwb)) return; if (rq == rwb->sync_cookie) { rwb->sync_issue = 0; rwb->sync_cookie = NULL; } } /* * Enable wbt if defaults are configured that way */ void wbt_enable_default(struct gendisk *disk) { struct request_queue *q = disk->queue; struct rq_qos *rqos; bool enable = IS_ENABLED(CONFIG_BLK_WBT_MQ); if (q->elevator && test_bit(ELEVATOR_FLAG_DISABLE_WBT, &q->elevator->flags)) enable = false; /* Throttling already enabled? */ rqos = wbt_rq_qos(q); if (rqos) { if (enable && RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT) RQWB(rqos)->enable_state = WBT_STATE_ON_DEFAULT; return; } /* Queue not registered? Maybe shutting down... */ if (!blk_queue_registered(q)) return; if (queue_is_mq(q) && enable) wbt_init(disk); } EXPORT_SYMBOL_GPL(wbt_enable_default); u64 wbt_default_latency_nsec(struct request_queue *q) { /* * We default to 2msec for non-rotational storage, and 75msec * for rotational storage. */ if (blk_queue_nonrot(q)) return 2000000ULL; else return 75000000ULL; } static int wbt_data_dir(const struct request *rq) { const enum req_op op = req_op(rq); if (op == REQ_OP_READ) return READ; else if (op_is_write(op)) return WRITE; /* don't account */ return -1; } static void wbt_queue_depth_changed(struct rq_qos *rqos) { RQWB(rqos)->rq_depth.queue_depth = blk_queue_depth(rqos->disk->queue); wbt_update_limits(RQWB(rqos)); } static void wbt_exit(struct rq_qos *rqos) { struct rq_wb *rwb = RQWB(rqos); blk_stat_remove_callback(rqos->disk->queue, rwb->cb); blk_stat_free_callback(rwb->cb); kfree(rwb); } /* * Disable wbt, if enabled by default. */ void wbt_disable_default(struct gendisk *disk) { struct rq_qos *rqos = wbt_rq_qos(disk->queue); struct rq_wb *rwb; if (!rqos) return; rwb = RQWB(rqos); if (rwb->enable_state == WBT_STATE_ON_DEFAULT) { blk_stat_deactivate(rwb->cb); rwb->enable_state = WBT_STATE_OFF_DEFAULT; } } EXPORT_SYMBOL_GPL(wbt_disable_default); #ifdef CONFIG_BLK_DEBUG_FS static int wbt_curr_win_nsec_show(void *data, struct seq_file *m) { struct rq_qos *rqos = data; struct rq_wb *rwb = RQWB(rqos); seq_printf(m, "%llu\n", rwb->cur_win_nsec); return 0; } static int wbt_enabled_show(void *data, struct seq_file *m) { struct rq_qos *rqos = data; struct rq_wb *rwb = RQWB(rqos); seq_printf(m, "%d\n", rwb->enable_state); return 0; } static int wbt_id_show(void *data, struct seq_file *m) { struct rq_qos *rqos = data; seq_printf(m, "%u\n", rqos->id); return 0; } static int wbt_inflight_show(void *data, struct seq_file *m) { struct rq_qos *rqos = data; struct rq_wb *rwb = RQWB(rqos); int i; for (i = 0; i < WBT_NUM_RWQ; i++) seq_printf(m, "%d: inflight %d\n", i, atomic_read(&rwb->rq_wait[i].inflight)); return 0; } static int wbt_min_lat_nsec_show(void *data, struct seq_file *m) { struct rq_qos *rqos = data; struct rq_wb *rwb = RQWB(rqos); seq_printf(m, "%lu\n", rwb->min_lat_nsec); return 0; } static int wbt_unknown_cnt_show(void *data, struct seq_file *m) { struct rq_qos *rqos = data; struct rq_wb *rwb = RQWB(rqos); seq_printf(m, "%u\n", rwb->unknown_cnt); return 0; } static int wbt_normal_show(void *data, struct seq_file *m) { struct rq_qos *rqos = data; struct rq_wb *rwb = RQWB(rqos); seq_printf(m, "%u\n", rwb->wb_normal); return 0; } static int wbt_background_show(void *data, struct seq_file *m) { struct rq_qos *rqos = data; struct rq_wb *rwb = RQWB(rqos); seq_printf(m, "%u\n", rwb->wb_background); return 0; } static const struct blk_mq_debugfs_attr wbt_debugfs_attrs[] = { {"curr_win_nsec", 0400, wbt_curr_win_nsec_show}, {"enabled", 0400, wbt_enabled_show}, {"id", 0400, wbt_id_show}, {"inflight", 0400, wbt_inflight_show}, {"min_lat_nsec", 0400, wbt_min_lat_nsec_show}, {"unknown_cnt", 0400, wbt_unknown_cnt_show}, {"wb_normal", 0400, wbt_normal_show}, {"wb_background", 0400, wbt_background_show}, {}, }; #endif static const struct rq_qos_ops wbt_rqos_ops = { .throttle = wbt_wait, .issue = wbt_issue, .track = wbt_track, .requeue = wbt_requeue, .done = wbt_done, .cleanup = wbt_cleanup, .queue_depth_changed = wbt_queue_depth_changed, .exit = wbt_exit, #ifdef CONFIG_BLK_DEBUG_FS .debugfs_attrs = wbt_debugfs_attrs, #endif }; int wbt_init(struct gendisk *disk) { struct request_queue *q = disk->queue; struct rq_wb *rwb; int i; int ret; rwb = kzalloc(sizeof(*rwb), GFP_KERNEL); if (!rwb) return -ENOMEM; rwb->cb = blk_stat_alloc_callback(wb_timer_fn, wbt_data_dir, 2, rwb); if (!rwb->cb) { kfree(rwb); return -ENOMEM; } for (i = 0; i < WBT_NUM_RWQ; i++) rq_wait_init(&rwb->rq_wait[i]); rwb->last_comp = rwb->last_issue = jiffies; rwb->win_nsec = RWB_WINDOW_NSEC; rwb->enable_state = WBT_STATE_ON_DEFAULT; rwb->rq_depth.default_depth = RWB_DEF_DEPTH; rwb->min_lat_nsec = wbt_default_latency_nsec(q); rwb->rq_depth.queue_depth = blk_queue_depth(q); wbt_update_limits(rwb); /* * Assign rwb and add the stats callback. */ mutex_lock(&q->rq_qos_mutex); ret = rq_qos_add(&rwb->rqos, disk, RQ_QOS_WBT, &wbt_rqos_ops); mutex_unlock(&q->rq_qos_mutex); if (ret) goto err_free; blk_stat_add_callback(q, rwb->cb); return 0; err_free: blk_stat_free_callback(rwb->cb); kfree(rwb); return ret; } |
| 491 490 489 589 585 592 590 592 31 32 589 592 430 428 431 431 431 488 4 489 488 174 203 431 429 591 591 326 14 14 14 14 14 14 14 14 13 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2008 Oracle. All rights reserved. */ #include <linux/sched.h> #include <linux/pagemap.h> #include <linux/spinlock.h> #include <linux/page-flags.h> #include <asm/bug.h> #include <trace/events/btrfs.h> #include "ctree.h" #include "extent_io.h" #include "locking.h" /* * Lockdep class keys for extent_buffer->lock's in this root. For a given * eb, the lockdep key is determined by the btrfs_root it belongs to and * the level the eb occupies in the tree. * * Different roots are used for different purposes and may nest inside each * other and they require separate keysets. As lockdep keys should be * static, assign keysets according to the purpose of the root as indicated * by btrfs_root->root_key.objectid. This ensures that all special purpose * roots have separate keysets. * * Lock-nesting across peer nodes is always done with the immediate parent * node locked thus preventing deadlock. As lockdep doesn't know this, use * subclass to avoid triggering lockdep warning in such cases. * * The key is set by the readpage_end_io_hook after the buffer has passed * csum validation but before the pages are unlocked. It is also set by * btrfs_init_new_buffer on freshly allocated blocks. * * We also add a check to make sure the highest level of the tree is the * same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this code * needs update as well. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC #if BTRFS_MAX_LEVEL != 8 #error #endif #define DEFINE_LEVEL(stem, level) \ .names[level] = "btrfs-" stem "-0" #level, #define DEFINE_NAME(stem) \ DEFINE_LEVEL(stem, 0) \ DEFINE_LEVEL(stem, 1) \ DEFINE_LEVEL(stem, 2) \ DEFINE_LEVEL(stem, 3) \ DEFINE_LEVEL(stem, 4) \ DEFINE_LEVEL(stem, 5) \ DEFINE_LEVEL(stem, 6) \ DEFINE_LEVEL(stem, 7) static struct btrfs_lockdep_keyset { u64 id; /* root objectid */ /* Longest entry: btrfs-block-group-00 */ char names[BTRFS_MAX_LEVEL][24]; struct lock_class_key keys[BTRFS_MAX_LEVEL]; } btrfs_lockdep_keysets[] = { { .id = BTRFS_ROOT_TREE_OBJECTID, DEFINE_NAME("root") }, { .id = BTRFS_EXTENT_TREE_OBJECTID, DEFINE_NAME("extent") }, { .id = BTRFS_CHUNK_TREE_OBJECTID, DEFINE_NAME("chunk") }, { .id = BTRFS_DEV_TREE_OBJECTID, DEFINE_NAME("dev") }, { .id = BTRFS_CSUM_TREE_OBJECTID, DEFINE_NAME("csum") }, { .id = BTRFS_QUOTA_TREE_OBJECTID, DEFINE_NAME("quota") }, { .id = BTRFS_TREE_LOG_OBJECTID, DEFINE_NAME("log") }, { .id = BTRFS_TREE_RELOC_OBJECTID, DEFINE_NAME("treloc") }, { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, DEFINE_NAME("dreloc") }, { .id = BTRFS_UUID_TREE_OBJECTID, DEFINE_NAME("uuid") }, { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, DEFINE_NAME("free-space") }, { .id = BTRFS_BLOCK_GROUP_TREE_OBJECTID, DEFINE_NAME("block-group") }, { .id = BTRFS_RAID_STRIPE_TREE_OBJECTID, DEFINE_NAME("raid-stripe") }, { .id = 0, DEFINE_NAME("tree") }, }; #undef DEFINE_LEVEL #undef DEFINE_NAME void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level) { struct btrfs_lockdep_keyset *ks; ASSERT(level < ARRAY_SIZE(ks->keys)); /* Find the matching keyset, id 0 is the default entry */ for (ks = btrfs_lockdep_keysets; ks->id; ks++) if (ks->id == objectid) break; lockdep_set_class_and_name(&eb->lock, &ks->keys[level], ks->names[level]); } void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb) { if (test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state)) btrfs_set_buffer_lockdep_class(btrfs_root_id(root), eb, btrfs_header_level(eb)); } #endif #ifdef CONFIG_BTRFS_DEBUG static void btrfs_set_eb_lock_owner(struct extent_buffer *eb, pid_t owner) { eb->lock_owner = owner; } #else static void btrfs_set_eb_lock_owner(struct extent_buffer *eb, pid_t owner) { } #endif /* * Extent buffer locking * ===================== * * We use a rw_semaphore for tree locking, and the semantics are exactly the * same: * * - reader/writer exclusion * - writer/writer exclusion * - reader/reader sharing * - try-lock semantics for readers and writers * * The rwsem implementation does opportunistic spinning which reduces number of * times the locking task needs to sleep. */ /* * btrfs_tree_read_lock_nested - lock extent buffer for read * @eb: the eb to be locked * @nest: the nesting level to be used for lockdep * * This takes the read lock on the extent buffer, using the specified nesting * level for lockdep purposes. */ void btrfs_tree_read_lock_nested(struct extent_buffer *eb, enum btrfs_lock_nesting nest) { u64 start_ns = 0; if (trace_btrfs_tree_read_lock_enabled()) start_ns = ktime_get_ns(); down_read_nested(&eb->lock, nest); trace_btrfs_tree_read_lock(eb, start_ns); } /* * Try-lock for read. * * Return 1 if the rwlock has been taken, 0 otherwise */ int btrfs_try_tree_read_lock(struct extent_buffer *eb) { if (down_read_trylock(&eb->lock)) { trace_btrfs_try_tree_read_lock(eb); return 1; } return 0; } /* * Release read lock. */ void btrfs_tree_read_unlock(struct extent_buffer *eb) { trace_btrfs_tree_read_unlock(eb); up_read(&eb->lock); } /* * Lock eb for write. * * @eb: the eb to lock * @nest: the nesting to use for the lock * * Returns with the eb->lock write locked. */ void btrfs_tree_lock_nested(struct extent_buffer *eb, enum btrfs_lock_nesting nest) __acquires(&eb->lock) { u64 start_ns = 0; if (trace_btrfs_tree_lock_enabled()) start_ns = ktime_get_ns(); down_write_nested(&eb->lock, nest); btrfs_set_eb_lock_owner(eb, current->pid); trace_btrfs_tree_lock(eb, start_ns); } /* * Release the write lock. */ void btrfs_tree_unlock(struct extent_buffer *eb) { trace_btrfs_tree_unlock(eb); btrfs_set_eb_lock_owner(eb, 0); up_write(&eb->lock); } /* * This releases any locks held in the path starting at level and going all the * way up to the root. * * btrfs_search_slot will keep the lock held on higher nodes in a few corner * cases, such as COW of the block at slot zero in the node. This ignores * those rules, and it should only be called when there are no more updates to * be done higher up in the tree. */ void btrfs_unlock_up_safe(struct btrfs_path *path, int level) { int i; if (path->keep_locks) return; for (i = level; i < BTRFS_MAX_LEVEL; i++) { if (!path->nodes[i]) continue; if (!path->locks[i]) continue; btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]); path->locks[i] = 0; } } /* * Loop around taking references on and locking the root node of the tree until * we end up with a lock on the root node. * * Return: root extent buffer with write lock held */ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root) { struct extent_buffer *eb; while (1) { eb = btrfs_root_node(root); btrfs_maybe_reset_lockdep_class(root, eb); btrfs_tree_lock(eb); if (eb == root->node) break; btrfs_tree_unlock(eb); free_extent_buffer(eb); } return eb; } /* * Loop around taking references on and locking the root node of the tree until * we end up with a lock on the root node. * * Return: root extent buffer with read lock held */ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root) { struct extent_buffer *eb; while (1) { eb = btrfs_root_node(root); btrfs_maybe_reset_lockdep_class(root, eb); btrfs_tree_read_lock(eb); if (eb == root->node) break; btrfs_tree_read_unlock(eb); free_extent_buffer(eb); } return eb; } /* * Loop around taking references on and locking the root node of the tree in * nowait mode until we end up with a lock on the root node or returning to * avoid blocking. * * Return: root extent buffer with read lock held or -EAGAIN. */ struct extent_buffer *btrfs_try_read_lock_root_node(struct btrfs_root *root) { struct extent_buffer *eb; while (1) { eb = btrfs_root_node(root); if (!btrfs_try_tree_read_lock(eb)) { free_extent_buffer(eb); return ERR_PTR(-EAGAIN); } if (eb == root->node) break; btrfs_tree_read_unlock(eb); free_extent_buffer(eb); } return eb; } /* * DREW locks * ========== * * DREW stands for double-reader-writer-exclusion lock. It's used in situation * where you want to provide A-B exclusion but not AA or BB. * * Currently implementation gives more priority to reader. If a reader and a * writer both race to acquire their respective sides of the lock the writer * would yield its lock as soon as it detects a concurrent reader. Additionally * if there are pending readers no new writers would be allowed to come in and * acquire the lock. */ void btrfs_drew_lock_init(struct btrfs_drew_lock *lock) { atomic_set(&lock->readers, 0); atomic_set(&lock->writers, 0); init_waitqueue_head(&lock->pending_readers); init_waitqueue_head(&lock->pending_writers); } /* Return true if acquisition is successful, false otherwise */ bool btrfs_drew_try_write_lock(struct btrfs_drew_lock *lock) { if (atomic_read(&lock->readers)) return false; atomic_inc(&lock->writers); /* Ensure writers count is updated before we check for pending readers */ smp_mb__after_atomic(); if (atomic_read(&lock->readers)) { btrfs_drew_write_unlock(lock); return false; } return true; } void btrfs_drew_write_lock(struct btrfs_drew_lock *lock) { while (true) { if (btrfs_drew_try_write_lock(lock)) return; wait_event(lock->pending_writers, !atomic_read(&lock->readers)); } } void btrfs_drew_write_unlock(struct btrfs_drew_lock *lock) { /* * atomic_dec_and_test() implies a full barrier, so woken up readers are * guaranteed to see the decrement. */ if (atomic_dec_and_test(&lock->writers)) wake_up(&lock->pending_readers); } void btrfs_drew_read_lock(struct btrfs_drew_lock *lock) { atomic_inc(&lock->readers); /* * Ensure the pending reader count is perceieved BEFORE this reader * goes to sleep in case of active writers. This guarantees new writers * won't be allowed and that the current reader will be woken up when * the last active writer finishes its jobs. */ smp_mb__after_atomic(); wait_event(lock->pending_readers, atomic_read(&lock->writers) == 0); } void btrfs_drew_read_unlock(struct btrfs_drew_lock *lock) { /* * atomic_dec_and_test implies a full barrier, so woken up writers * are guaranteed to see the decrement */ if (atomic_dec_and_test(&lock->readers)) wake_up(&lock->pending_writers); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * This file is part of the Linux kernel. * * Copyright (c) 2011-2014, Intel Corporation * Authors: Fenghua Yu <fenghua.yu@intel.com>, * H. Peter Anvin <hpa@linux.intel.com> */ #ifndef ASM_X86_ARCHRANDOM_H #define ASM_X86_ARCHRANDOM_H #include <asm/processor.h> #include <asm/cpufeature.h> #define RDRAND_RETRY_LOOPS 10 /* Unconditional execution of RDRAND and RDSEED */ static inline bool __must_check rdrand_long(unsigned long *v) { bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { asm volatile("rdrand %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); if (ok) return true; } while (--retry); return false; } static inline bool __must_check rdseed_long(unsigned long *v) { bool ok; asm volatile("rdseed %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); return ok; } /* * These are the generic interfaces; they must not be declared if the * stubs in <linux/random.h> are to be invoked. */ static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs) { return max_longs && static_cpu_has(X86_FEATURE_RDRAND) && rdrand_long(v) ? 1 : 0; } static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs) { return max_longs && static_cpu_has(X86_FEATURE_RDSEED) && rdseed_long(v) ? 1 : 0; } #ifndef CONFIG_UML void x86_init_rdrand(struct cpuinfo_x86 *c); #endif #endif /* ASM_X86_ARCHRANDOM_H */ |
| 1 2 2 2 1 1 1 1 2 2 1 1 1 1 2 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 | // SPDX-License-Identifier: GPL-2.0-only /* * Pluggable TCP congestion control support and newReno * congestion control. * Based on ideas from I/O scheduler support and Web100. * * Copyright (C) 2005 Stephen Hemminger <shemminger@osdl.org> */ #define pr_fmt(fmt) "TCP: " fmt #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> #include <linux/list.h> #include <linux/gfp.h> #include <linux/jhash.h> #include <net/tcp.h> #include <trace/events/tcp.h> static DEFINE_SPINLOCK(tcp_cong_list_lock); static LIST_HEAD(tcp_cong_list); /* Simple linear search, don't expect many entries! */ struct tcp_congestion_ops *tcp_ca_find(const char *name) { struct tcp_congestion_ops *e; list_for_each_entry_rcu(e, &tcp_cong_list, list) { if (strcmp(e->name, name) == 0) return e; } return NULL; } void tcp_set_ca_state(struct sock *sk, const u8 ca_state) { struct inet_connection_sock *icsk = inet_csk(sk); trace_tcp_cong_state_set(sk, ca_state); if (icsk->icsk_ca_ops->set_state) icsk->icsk_ca_ops->set_state(sk, ca_state); icsk->icsk_ca_state = ca_state; } /* Must be called with rcu lock held */ static struct tcp_congestion_ops *tcp_ca_find_autoload(const char *name) { struct tcp_congestion_ops *ca = tcp_ca_find(name); #ifdef CONFIG_MODULES if (!ca && capable(CAP_NET_ADMIN)) { rcu_read_unlock(); request_module("tcp_%s", name); rcu_read_lock(); ca = tcp_ca_find(name); } #endif return ca; } /* Simple linear search, not much in here. */ struct tcp_congestion_ops *tcp_ca_find_key(u32 key) { struct tcp_congestion_ops *e; list_for_each_entry_rcu(e, &tcp_cong_list, list) { if (e->key == key) return e; } return NULL; } int tcp_validate_congestion_control(struct tcp_congestion_ops *ca) { /* all algorithms must implement these */ if (!ca->ssthresh || !ca->undo_cwnd || !(ca->cong_avoid || ca->cong_control)) { pr_err("%s does not implement required ops\n", ca->name); return -EINVAL; } return 0; } /* Attach new congestion control algorithm to the list * of available options. */ int tcp_register_congestion_control(struct tcp_congestion_ops *ca) { int ret; ret = tcp_validate_congestion_control(ca); if (ret) return ret; ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); spin_lock(&tcp_cong_list_lock); if (ca->key == TCP_CA_UNSPEC || tcp_ca_find_key(ca->key)) { pr_notice("%s already registered or non-unique key\n", ca->name); ret = -EEXIST; } else { list_add_tail_rcu(&ca->list, &tcp_cong_list); pr_debug("%s registered\n", ca->name); } spin_unlock(&tcp_cong_list_lock); return ret; } EXPORT_SYMBOL_GPL(tcp_register_congestion_control); /* * Remove congestion control algorithm, called from * the module's remove function. Module ref counts are used * to ensure that this can't be done till all sockets using * that method are closed. */ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca) { spin_lock(&tcp_cong_list_lock); list_del_rcu(&ca->list); spin_unlock(&tcp_cong_list_lock); /* Wait for outstanding readers to complete before the * module gets removed entirely. * * A try_module_get() should fail by now as our module is * in "going" state since no refs are held anymore and * module_exit() handler being called. */ synchronize_rcu(); } EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); /* Replace a registered old ca with a new one. * * The new ca must have the same name as the old one, that has been * registered. */ int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_congestion_ops *old_ca) { struct tcp_congestion_ops *existing; int ret = 0; ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); spin_lock(&tcp_cong_list_lock); existing = tcp_ca_find_key(old_ca->key); if (ca->key == TCP_CA_UNSPEC || !existing || strcmp(existing->name, ca->name)) { pr_notice("%s not registered or non-unique key\n", ca->name); ret = -EINVAL; } else if (existing != old_ca) { pr_notice("invalid old congestion control algorithm to replace\n"); ret = -EINVAL; } else { /* Add the new one before removing the old one to keep * one implementation available all the time. */ list_add_tail_rcu(&ca->list, &tcp_cong_list); list_del_rcu(&existing->list); pr_debug("%s updated\n", ca->name); } spin_unlock(&tcp_cong_list_lock); /* Wait for outstanding readers to complete before the * module or struct_ops gets removed entirely. */ if (!ret) synchronize_rcu(); return ret; } u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca) { const struct tcp_congestion_ops *ca; u32 key = TCP_CA_UNSPEC; might_sleep(); rcu_read_lock(); ca = tcp_ca_find_autoload(name); if (ca) { key = ca->key; *ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN; } rcu_read_unlock(); return key; } char *tcp_ca_get_name_by_key(u32 key, char *buffer) { const struct tcp_congestion_ops *ca; char *ret = NULL; rcu_read_lock(); ca = tcp_ca_find_key(key); if (ca) { strscpy(buffer, ca->name, TCP_CA_NAME_MAX); ret = buffer; } rcu_read_unlock(); return ret; } /* Assign choice of congestion control. */ void tcp_assign_congestion_control(struct sock *sk) { struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; rcu_read_lock(); ca = rcu_dereference(net->ipv4.tcp_congestion_control); if (unlikely(!bpf_try_module_get(ca, ca->owner))) ca = &tcp_reno; icsk->icsk_ca_ops = ca; rcu_read_unlock(); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) INET_ECN_xmit(sk); else INET_ECN_dontxmit(sk); } void tcp_init_congestion_control(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_sk(sk)->prior_ssthresh = 0; if (icsk->icsk_ca_ops->init) icsk->icsk_ca_ops->init(sk); if (tcp_ca_needs_ecn(sk)) INET_ECN_xmit(sk); else INET_ECN_dontxmit(sk); icsk->icsk_ca_initialized = 1; } static void tcp_reinit_congestion_control(struct sock *sk, const struct tcp_congestion_ops *ca) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_cleanup_congestion_control(sk); icsk->icsk_ca_ops = ca; icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) INET_ECN_xmit(sk); else INET_ECN_dontxmit(sk); if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } /* Manage refcounts on socket close. */ void tcp_cleanup_congestion_control(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); icsk->icsk_ca_initialized = 0; bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); } /* Used by sysctl to change default congestion control */ int tcp_set_default_congestion_control(struct net *net, const char *name) { struct tcp_congestion_ops *ca; const struct tcp_congestion_ops *prev; int ret; rcu_read_lock(); ca = tcp_ca_find_autoload(name); if (!ca) { ret = -ENOENT; } else if (!bpf_try_module_get(ca, ca->owner)) { ret = -EBUSY; } else if (!net_eq(net, &init_net) && !(ca->flags & TCP_CONG_NON_RESTRICTED)) { /* Only init netns can set default to a restricted algorithm */ ret = -EPERM; } else { prev = xchg(&net->ipv4.tcp_congestion_control, ca); if (prev) bpf_module_put(prev, prev->owner); ca->flags |= TCP_CONG_NON_RESTRICTED; ret = 0; } rcu_read_unlock(); return ret; } /* Set default value from kernel configuration at bootup */ static int __init tcp_congestion_default(void) { return tcp_set_default_congestion_control(&init_net, CONFIG_DEFAULT_TCP_CONG); } late_initcall(tcp_congestion_default); /* Build string with list of available congestion control values */ void tcp_get_available_congestion_control(char *buf, size_t maxlen) { struct tcp_congestion_ops *ca; size_t offs = 0; rcu_read_lock(); list_for_each_entry_rcu(ca, &tcp_cong_list, list) { offs += snprintf(buf + offs, maxlen - offs, "%s%s", offs == 0 ? "" : " ", ca->name); if (WARN_ON_ONCE(offs >= maxlen)) break; } rcu_read_unlock(); } /* Get current default congestion control */ void tcp_get_default_congestion_control(struct net *net, char *name) { const struct tcp_congestion_ops *ca; rcu_read_lock(); ca = rcu_dereference(net->ipv4.tcp_congestion_control); strscpy(name, ca->name, TCP_CA_NAME_MAX); rcu_read_unlock(); } /* Built list of non-restricted congestion control values */ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen) { struct tcp_congestion_ops *ca; size_t offs = 0; *buf = '\0'; rcu_read_lock(); list_for_each_entry_rcu(ca, &tcp_cong_list, list) { if (!(ca->flags & TCP_CONG_NON_RESTRICTED)) continue; offs += snprintf(buf + offs, maxlen - offs, "%s%s", offs == 0 ? "" : " ", ca->name); if (WARN_ON_ONCE(offs >= maxlen)) break; } rcu_read_unlock(); } /* Change list of non-restricted congestion control */ int tcp_set_allowed_congestion_control(char *val) { struct tcp_congestion_ops *ca; char *saved_clone, *clone, *name; int ret = 0; saved_clone = clone = kstrdup(val, GFP_USER); if (!clone) return -ENOMEM; spin_lock(&tcp_cong_list_lock); /* pass 1 check for bad entries */ while ((name = strsep(&clone, " ")) && *name) { ca = tcp_ca_find(name); if (!ca) { ret = -ENOENT; goto out; } } /* pass 2 clear old values */ list_for_each_entry_rcu(ca, &tcp_cong_list, list) ca->flags &= ~TCP_CONG_NON_RESTRICTED; /* pass 3 mark as allowed */ while ((name = strsep(&val, " ")) && *name) { ca = tcp_ca_find(name); WARN_ON(!ca); if (ca) ca->flags |= TCP_CONG_NON_RESTRICTED; } out: spin_unlock(&tcp_cong_list_lock); kfree(saved_clone); return ret; } /* Change congestion control for socket. If load is false, then it is the * responsibility of the caller to call tcp_init_congestion_control or * tcp_reinit_congestion_control (if the current congestion control was * already initialized. */ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool cap_net_admin) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; int err = 0; if (icsk->icsk_ca_dst_locked) return -EPERM; rcu_read_lock(); if (!load) ca = tcp_ca_find(name); else ca = tcp_ca_find_autoload(name); /* No change asking for existing value */ if (ca == icsk->icsk_ca_ops) { icsk->icsk_ca_setsockopt = 1; goto out; } if (!ca) err = -ENOENT; else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) err = -EPERM; else if (!bpf_try_module_get(ca, ca->owner)) err = -EBUSY; else tcp_reinit_congestion_control(sk, ca); out: rcu_read_unlock(); return err; } /* Slow start is used when congestion window is no greater than the slow start * threshold. We base on RFC2581 and also handle stretch ACKs properly. * We do not implement RFC3465 Appropriate Byte Counting (ABC) per se but * something better;) a packet is only considered (s)acked in its entirety to * defend the ACK attacks described in the RFC. Slow start processes a stretch * ACK of degree N as if N acks of degree 1 are received back to back except * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and * returns the leftover acks to adjust cwnd in congestion avoidance mode. */ __bpf_kfunc u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) { u32 cwnd = min(tcp_snd_cwnd(tp) + acked, tp->snd_ssthresh); acked -= cwnd - tcp_snd_cwnd(tp); tcp_snd_cwnd_set(tp, min(cwnd, tp->snd_cwnd_clamp)); return acked; } EXPORT_SYMBOL_GPL(tcp_slow_start); /* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w), * for every packet that was ACKed. */ __bpf_kfunc void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) { /* If credits accumulated at a higher w, apply them gently now. */ if (tp->snd_cwnd_cnt >= w) { tp->snd_cwnd_cnt = 0; tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + 1); } tp->snd_cwnd_cnt += acked; if (tp->snd_cwnd_cnt >= w) { u32 delta = tp->snd_cwnd_cnt / w; tp->snd_cwnd_cnt -= delta * w; tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + delta); } tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp), tp->snd_cwnd_clamp)); } EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai); /* * TCP Reno congestion control * This is special case used for fallback as well. */ /* This is Jacobson's slow start and congestion avoidance. * SIGCOMM '88, p. 328. */ __bpf_kfunc void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); if (!tcp_is_cwnd_limited(sk)) return; /* In "safe" area, increase. */ if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; } /* In dangerous area, increase slowly. */ tcp_cong_avoid_ai(tp, tcp_snd_cwnd(tp), acked); } EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid); /* Slow start threshold is half the congestion window (min 2) */ __bpf_kfunc u32 tcp_reno_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return max(tcp_snd_cwnd(tp) >> 1U, 2U); } EXPORT_SYMBOL_GPL(tcp_reno_ssthresh); __bpf_kfunc u32 tcp_reno_undo_cwnd(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return max(tcp_snd_cwnd(tp), tp->prior_cwnd); } EXPORT_SYMBOL_GPL(tcp_reno_undo_cwnd); struct tcp_congestion_ops tcp_reno = { .flags = TCP_CONG_NON_RESTRICTED, .name = "reno", .owner = THIS_MODULE, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, .undo_cwnd = tcp_reno_undo_cwnd, }; |
| 2 2 2 2 4 4 2 4 2 3 3 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 | /* * Created: Fri Jan 19 10:48:35 2001 by faith@acm.org * * Copyright 2001 VA Linux Systems, Inc., Sunnyvale, California. * All Rights Reserved. * * Author Rickard E. (Rik) Faith <faith@valinux.com> * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice (including the next * paragraph) shall be included in all copies or substantial portions of the * Software. * * 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 * PRECISION INSIGHT AND/OR ITS SUPPLIERS 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/bitops.h> #include <linux/cgroup_dmem.h> #include <linux/debugfs.h> #include <linux/fs.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/slab.h> #include <linux/sprintf.h> #include <linux/srcu.h> #include <linux/xarray.h> #include <drm/drm_accel.h> #include <drm/drm_cache.h> #include <drm/drm_client_event.h> #include <drm/drm_color_mgmt.h> #include <drm/drm_drv.h> #include <drm/drm_file.h> #include <drm/drm_managed.h> #include <drm/drm_mode_object.h> #include <drm/drm_panic.h> #include <drm/drm_print.h> #include <drm/drm_privacy_screen_machine.h> #include "drm_crtc_internal.h" #include "drm_internal.h" MODULE_AUTHOR("Gareth Hughes, Leif Delgass, José Fonseca, Jon Smirl"); MODULE_DESCRIPTION("DRM shared core routines"); MODULE_LICENSE("GPL and additional rights"); DEFINE_XARRAY_ALLOC(drm_minors_xa); /* * If the drm core fails to init for whatever reason, * we should prevent any drivers from registering with it. * It's best to check this at drm_dev_init(), as some drivers * prefer to embed struct drm_device into their own device * structure and call drm_dev_init() themselves. */ static bool drm_core_init_complete; static struct dentry *drm_debugfs_root; DEFINE_STATIC_SRCU(drm_unplug_srcu); /* * DRM Minors * A DRM device can provide several char-dev interfaces on the DRM-Major. Each * of them is represented by a drm_minor object. Depending on the capabilities * of the device-driver, different interfaces are registered. * * Minors can be accessed via dev->$minor_name. This pointer is either * NULL or a valid drm_minor pointer and stays valid as long as the device is * valid. This means, DRM minors have the same life-time as the underlying * device. However, this doesn't mean that the minor is active. Minors are * registered and unregistered dynamically according to device-state. */ static struct xarray *drm_minor_get_xa(enum drm_minor_type type) { if (type == DRM_MINOR_PRIMARY || type == DRM_MINOR_RENDER) return &drm_minors_xa; #if IS_ENABLED(CONFIG_DRM_ACCEL) else if (type == DRM_MINOR_ACCEL) return &accel_minors_xa; #endif else return ERR_PTR(-EOPNOTSUPP); } static struct drm_minor **drm_minor_get_slot(struct drm_device *dev, enum drm_minor_type type) { switch (type) { case DRM_MINOR_PRIMARY: return &dev->primary; case DRM_MINOR_RENDER: return &dev->render; case DRM_MINOR_ACCEL: return &dev->accel; default: BUG(); } } static void drm_minor_alloc_release(struct drm_device *dev, void *data) { struct drm_minor *minor = data; WARN_ON(dev != minor->dev); put_device(minor->kdev); xa_erase(drm_minor_get_xa(minor->type), minor->index); } /* * DRM used to support 64 devices, for backwards compatibility we need to maintain the * minor allocation scheme where minors 0-63 are primary nodes, 64-127 are control nodes, * and 128-191 are render nodes. * After reaching the limit, we're allocating minors dynamically - first-come, first-serve. * Accel nodes are using a distinct major, so the minors are allocated in continuous 0-MAX * range. */ #define DRM_MINOR_LIMIT(t) ({ \ typeof(t) _t = (t); \ _t == DRM_MINOR_ACCEL ? XA_LIMIT(0, ACCEL_MAX_MINORS) : XA_LIMIT(64 * _t, 64 * _t + 63); \ }) #define DRM_EXTENDED_MINOR_LIMIT XA_LIMIT(192, (1 << MINORBITS) - 1) static int drm_minor_alloc(struct drm_device *dev, enum drm_minor_type type) { struct drm_minor *minor; int r; minor = drmm_kzalloc(dev, sizeof(*minor), GFP_KERNEL); if (!minor) return -ENOMEM; minor->type = type; minor->dev = dev; r = xa_alloc(drm_minor_get_xa(type), &minor->index, NULL, DRM_MINOR_LIMIT(type), GFP_KERNEL); if (r == -EBUSY && (type == DRM_MINOR_PRIMARY || type == DRM_MINOR_RENDER)) r = xa_alloc(&drm_minors_xa, &minor->index, NULL, DRM_EXTENDED_MINOR_LIMIT, GFP_KERNEL); if (r < 0) return r; r = drmm_add_action_or_reset(dev, drm_minor_alloc_release, minor); if (r) return r; minor->kdev = drm_sysfs_minor_alloc(minor); if (IS_ERR(minor->kdev)) return PTR_ERR(minor->kdev); *drm_minor_get_slot(dev, type) = minor; return 0; } static int drm_minor_register(struct drm_device *dev, enum drm_minor_type type) { struct drm_minor *minor; void *entry; int ret; DRM_DEBUG("\n"); minor = *drm_minor_get_slot(dev, type); if (!minor) return 0; if (minor->type != DRM_MINOR_ACCEL) { ret = drm_debugfs_register(minor, minor->index, drm_debugfs_root); if (ret) { DRM_ERROR("DRM: Failed to initialize /sys/kernel/debug/dri.\n"); goto err_debugfs; } } ret = device_add(minor->kdev); if (ret) goto err_debugfs; /* replace NULL with @minor so lookups will succeed from now on */ entry = xa_store(drm_minor_get_xa(type), minor->index, minor, GFP_KERNEL); if (xa_is_err(entry)) { ret = xa_err(entry); goto err_debugfs; } WARN_ON(entry); DRM_DEBUG("new minor registered %d\n", minor->index); return 0; err_debugfs: drm_debugfs_unregister(minor); return ret; } static void drm_minor_unregister(struct drm_device *dev, enum drm_minor_type type) { struct drm_minor *minor; minor = *drm_minor_get_slot(dev, type); if (!minor || !device_is_registered(minor->kdev)) return; /* replace @minor with NULL so lookups will fail from now on */ xa_store(drm_minor_get_xa(type), minor->index, NULL, GFP_KERNEL); device_del(minor->kdev); dev_set_drvdata(minor->kdev, NULL); /* safety belt */ drm_debugfs_unregister(minor); } /* * Looks up the given minor-ID and returns the respective DRM-minor object. The * refence-count of the underlying device is increased so you must release this * object with drm_minor_release(). * * As long as you hold this minor, it is guaranteed that the object and the * minor->dev pointer will stay valid! However, the device may get unplugged and * unregistered while you hold the minor. */ struct drm_minor *drm_minor_acquire(struct xarray *minor_xa, unsigned int minor_id) { struct drm_minor *minor; xa_lock(minor_xa); minor = xa_load(minor_xa, minor_id); if (minor) drm_dev_get(minor->dev); xa_unlock(minor_xa); if (!minor) { return ERR_PTR(-ENODEV); } else if (drm_dev_is_unplugged(minor->dev)) { drm_dev_put(minor->dev); return ERR_PTR(-ENODEV); } return minor; } void drm_minor_release(struct drm_minor *minor) { drm_dev_put(minor->dev); } /** * DOC: driver instance overview * * A device instance for a drm driver is represented by &struct drm_device. This * is allocated and initialized with devm_drm_dev_alloc(), usually from * bus-specific ->probe() callbacks implemented by the driver. The driver then * needs to initialize all the various subsystems for the drm device like memory * management, vblank handling, modesetting support and initial output * configuration plus obviously initialize all the corresponding hardware bits. * Finally when everything is up and running and ready for userspace the device * instance can be published using drm_dev_register(). * * There is also deprecated support for initializing device instances using * bus-specific helpers and the &drm_driver.load callback. But due to * backwards-compatibility needs the device instance have to be published too * early, which requires unpretty global locking to make safe and is therefore * only support for existing drivers not yet converted to the new scheme. * * When cleaning up a device instance everything needs to be done in reverse: * First unpublish the device instance with drm_dev_unregister(). Then clean up * any other resources allocated at device initialization and drop the driver's * reference to &drm_device using drm_dev_put(). * * Note that any allocation or resource which is visible to userspace must be * released only when the final drm_dev_put() is called, and not when the * driver is unbound from the underlying physical struct &device. Best to use * &drm_device managed resources with drmm_add_action(), drmm_kmalloc() and * related functions. * * devres managed resources like devm_kmalloc() can only be used for resources * directly related to the underlying hardware device, and only used in code * paths fully protected by drm_dev_enter() and drm_dev_exit(). * * Display driver example * ~~~~~~~~~~~~~~~~~~~~~~ * * The following example shows a typical structure of a DRM display driver. * The example focus on the probe() function and the other functions that is * almost always present and serves as a demonstration of devm_drm_dev_alloc(). * * .. code-block:: c * * struct driver_device { * struct drm_device drm; * void *userspace_facing; * struct clk *pclk; * }; * * static const struct drm_driver driver_drm_driver = { * [...] * }; * * static int driver_probe(struct platform_device *pdev) * { * struct driver_device *priv; * struct drm_device *drm; * int ret; * * priv = devm_drm_dev_alloc(&pdev->dev, &driver_drm_driver, * struct driver_device, drm); * if (IS_ERR(priv)) * return PTR_ERR(priv); * drm = &priv->drm; * * ret = drmm_mode_config_init(drm); * if (ret) * return ret; * * priv->userspace_facing = drmm_kzalloc(..., GFP_KERNEL); * if (!priv->userspace_facing) * return -ENOMEM; * * priv->pclk = devm_clk_get(dev, "PCLK"); * if (IS_ERR(priv->pclk)) * return PTR_ERR(priv->pclk); * * // Further setup, display pipeline etc * * platform_set_drvdata(pdev, drm); * * drm_mode_config_reset(drm); * * ret = drm_dev_register(drm); * if (ret) * return ret; * * drm_fbdev_{...}_setup(drm, 32); * * return 0; * } * * // This function is called before the devm_ resources are released * static int driver_remove(struct platform_device *pdev) * { * struct drm_device *drm = platform_get_drvdata(pdev); * * drm_dev_unregister(drm); * drm_atomic_helper_shutdown(drm) * * return 0; * } * * // This function is called on kernel restart and shutdown * static void driver_shutdown(struct platform_device *pdev) * { * drm_atomic_helper_shutdown(platform_get_drvdata(pdev)); * } * * static int __maybe_unused driver_pm_suspend(struct device *dev) * { * return drm_mode_config_helper_suspend(dev_get_drvdata(dev)); * } * * static int __maybe_unused driver_pm_resume(struct device *dev) * { * drm_mode_config_helper_resume(dev_get_drvdata(dev)); * * return 0; * } * * static const struct dev_pm_ops driver_pm_ops = { * SET_SYSTEM_SLEEP_PM_OPS(driver_pm_suspend, driver_pm_resume) * }; * * static struct platform_driver driver_driver = { * .driver = { * [...] * .pm = &driver_pm_ops, * }, * .probe = driver_probe, * .remove = driver_remove, * .shutdown = driver_shutdown, * }; * module_platform_driver(driver_driver); * * Drivers that want to support device unplugging (USB, DT overlay unload) should * use drm_dev_unplug() instead of drm_dev_unregister(). The driver must protect * regions that is accessing device resources to prevent use after they're * released. This is done using drm_dev_enter() and drm_dev_exit(). There is one * shortcoming however, drm_dev_unplug() marks the drm_device as unplugged before * drm_atomic_helper_shutdown() is called. This means that if the disable code * paths are protected, they will not run on regular driver module unload, * possibly leaving the hardware enabled. */ /** * drm_put_dev - Unregister and release a DRM device * @dev: DRM device * * Called at module unload time or when a PCI device is unplugged. * * Cleans up all DRM device, calling drm_lastclose(). * * Note: Use of this function is deprecated. It will eventually go away * completely. Please use drm_dev_unregister() and drm_dev_put() explicitly * instead to make sure that the device isn't userspace accessible any more * while teardown is in progress, ensuring that userspace can't access an * inconsistent state. */ void drm_put_dev(struct drm_device *dev) { DRM_DEBUG("\n"); if (!dev) { DRM_ERROR("cleanup called no dev\n"); return; } drm_dev_unregister(dev); drm_dev_put(dev); } EXPORT_SYMBOL(drm_put_dev); /** * drm_dev_enter - Enter device critical section * @dev: DRM device * @idx: Pointer to index that will be passed to the matching drm_dev_exit() * * This function marks and protects the beginning of a section that should not * be entered after the device has been unplugged. The section end is marked * with drm_dev_exit(). Calls to this function can be nested. * * Returns: * True if it is OK to enter the section, false otherwise. */ bool drm_dev_enter(struct drm_device *dev, int *idx) { *idx = srcu_read_lock(&drm_unplug_srcu); if (dev->unplugged) { srcu_read_unlock(&drm_unplug_srcu, *idx); return false; } return true; } EXPORT_SYMBOL(drm_dev_enter); /** * drm_dev_exit - Exit device critical section * @idx: index returned from drm_dev_enter() * * This function marks the end of a section that should not be entered after * the device has been unplugged. */ void drm_dev_exit(int idx) { srcu_read_unlock(&drm_unplug_srcu, idx); } EXPORT_SYMBOL(drm_dev_exit); /** * drm_dev_unplug - unplug a DRM device * @dev: DRM device * * This unplugs a hotpluggable DRM device, which makes it inaccessible to * userspace operations. Entry-points can use drm_dev_enter() and * drm_dev_exit() to protect device resources in a race free manner. This * essentially unregisters the device like drm_dev_unregister(), but can be * called while there are still open users of @dev. */ void drm_dev_unplug(struct drm_device *dev) { /* * After synchronizing any critical read section is guaranteed to see * the new value of ->unplugged, and any critical section which might * still have seen the old value of ->unplugged is guaranteed to have * finished. */ dev->unplugged = true; synchronize_srcu(&drm_unplug_srcu); drm_dev_unregister(dev); /* Clear all CPU mappings pointing to this device */ unmap_mapping_range(dev->anon_inode->i_mapping, 0, 0, 1); } EXPORT_SYMBOL(drm_dev_unplug); /* * Available recovery methods for wedged device. To be sent along with device * wedged uevent. */ static const char *drm_get_wedge_recovery(unsigned int opt) { switch (BIT(opt)) { case DRM_WEDGE_RECOVERY_NONE: return "none"; case DRM_WEDGE_RECOVERY_REBIND: return "rebind"; case DRM_WEDGE_RECOVERY_BUS_RESET: return "bus-reset"; default: return NULL; } } /** * drm_dev_wedged_event - generate a device wedged uevent * @dev: DRM device * @method: method(s) to be used for recovery * * This generates a device wedged uevent for the DRM device specified by @dev. * Recovery @method\(s) of choice will be sent in the uevent environment as * ``WEDGED=<method1>[,..,<methodN>]`` in order of less to more side-effects. * If caller is unsure about recovery or @method is unknown (0), * ``WEDGED=unknown`` will be sent instead. * * Refer to "Device Wedging" chapter in Documentation/gpu/drm-uapi.rst for more * details. * * Returns: 0 on success, negative error code otherwise. */ int drm_dev_wedged_event(struct drm_device *dev, unsigned long method) { const char *recovery = NULL; unsigned int len, opt; /* Event string length up to 28+ characters with available methods */ char event_string[32]; char *envp[] = { event_string, NULL }; len = scnprintf(event_string, sizeof(event_string), "%s", "WEDGED="); for_each_set_bit(opt, &method, BITS_PER_TYPE(method)) { recovery = drm_get_wedge_recovery(opt); if (drm_WARN_ONCE(dev, !recovery, "invalid recovery method %u\n", opt)) break; len += scnprintf(event_string + len, sizeof(event_string), "%s,", recovery); } if (recovery) /* Get rid of trailing comma */ event_string[len - 1] = '\0'; else /* Caller is unsure about recovery, do the best we can at this point. */ snprintf(event_string, sizeof(event_string), "%s", "WEDGED=unknown"); drm_info(dev, "device wedged, %s\n", method == DRM_WEDGE_RECOVERY_NONE ? "but recovered through reset" : "needs recovery"); return kobject_uevent_env(&dev->primary->kdev->kobj, KOBJ_CHANGE, envp); } EXPORT_SYMBOL(drm_dev_wedged_event); /* * DRM internal mount * We want to be able to allocate our own "struct address_space" to control * memory-mappings in VRAM (or stolen RAM, ...). However, core MM does not allow * stand-alone address_space objects, so we need an underlying inode. As there * is no way to allocate an independent inode easily, we need a fake internal * VFS mount-point. * * The drm_fs_inode_new() function allocates a new inode, drm_fs_inode_free() * frees it again. You are allowed to use iget() and iput() to get references to * the inode. But each drm_fs_inode_new() call must be paired with exactly one * drm_fs_inode_free() call (which does not have to be the last iput()). * We use drm_fs_inode_*() to manage our internal VFS mount-point and share it * between multiple inode-users. You could, technically, call * iget() + drm_fs_inode_free() directly after alloc and sometime later do an * iput(), but this way you'd end up with a new vfsmount for each inode. */ static int drm_fs_cnt; static struct vfsmount *drm_fs_mnt; static int drm_fs_init_fs_context(struct fs_context *fc) { return init_pseudo(fc, 0x010203ff) ? 0 : -ENOMEM; } static struct file_system_type drm_fs_type = { .name = "drm", .owner = THIS_MODULE, .init_fs_context = drm_fs_init_fs_context, .kill_sb = kill_anon_super, }; static struct inode *drm_fs_inode_new(void) { struct inode *inode; int r; r = simple_pin_fs(&drm_fs_type, &drm_fs_mnt, &drm_fs_cnt); if (r < 0) { DRM_ERROR("Cannot mount pseudo fs: %d\n", r); return ERR_PTR(r); } inode = alloc_anon_inode(drm_fs_mnt->mnt_sb); if (IS_ERR(inode)) simple_release_fs(&drm_fs_mnt, &drm_fs_cnt); return inode; } static void drm_fs_inode_free(struct inode *inode) { if (inode) { iput(inode); simple_release_fs(&drm_fs_mnt, &drm_fs_cnt); } } /** * DOC: component helper usage recommendations * * DRM drivers that drive hardware where a logical device consists of a pile of * independent hardware blocks are recommended to use the :ref:`component helper * library<component>`. For consistency and better options for code reuse the * following guidelines apply: * * - The entire device initialization procedure should be run from the * &component_master_ops.master_bind callback, starting with * devm_drm_dev_alloc(), then binding all components with * component_bind_all() and finishing with drm_dev_register(). * * - The opaque pointer passed to all components through component_bind_all() * should point at &struct drm_device of the device instance, not some driver * specific private structure. * * - The component helper fills the niche where further standardization of * interfaces is not practical. When there already is, or will be, a * standardized interface like &drm_bridge or &drm_panel, providing its own * functions to find such components at driver load time, like * drm_of_find_panel_or_bridge(), then the component helper should not be * used. */ static void drm_dev_init_release(struct drm_device *dev, void *res) { drm_fs_inode_free(dev->anon_inode); put_device(dev->dev); /* Prevent use-after-free in drm_managed_release when debugging is * enabled. Slightly awkward, but can't really be helped. */ dev->dev = NULL; mutex_destroy(&dev->master_mutex); mutex_destroy(&dev->clientlist_mutex); mutex_destroy(&dev->filelist_mutex); mutex_destroy(&dev->struct_mutex); } static int drm_dev_init(struct drm_device *dev, const struct drm_driver *driver, struct device *parent) { struct inode *inode; int ret; if (!drm_core_init_complete) { DRM_ERROR("DRM core is not initialized\n"); return -ENODEV; } if (WARN_ON(!parent)) return -EINVAL; kref_init(&dev->ref); dev->dev = get_device(parent); dev->driver = driver; INIT_LIST_HEAD(&dev->managed.resources); spin_lock_init(&dev->managed.lock); /* no per-device feature limits by default */ dev->driver_features = ~0u; if (drm_core_check_feature(dev, DRIVER_COMPUTE_ACCEL) && (drm_core_check_feature(dev, DRIVER_RENDER) || drm_core_check_feature(dev, DRIVER_MODESET))) { DRM_ERROR("DRM driver can't be both a compute acceleration and graphics driver\n"); return -EINVAL; } INIT_LIST_HEAD(&dev->filelist); INIT_LIST_HEAD(&dev->filelist_internal); INIT_LIST_HEAD(&dev->clientlist); INIT_LIST_HEAD(&dev->vblank_event_list); spin_lock_init(&dev->event_lock); mutex_init(&dev->struct_mutex); mutex_init(&dev->filelist_mutex); mutex_init(&dev->clientlist_mutex); mutex_init(&dev->master_mutex); raw_spin_lock_init(&dev->mode_config.panic_lock); ret = drmm_add_action_or_reset(dev, drm_dev_init_release, NULL); if (ret) return ret; inode = drm_fs_inode_new(); if (IS_ERR(inode)) { ret = PTR_ERR(inode); DRM_ERROR("Cannot allocate anonymous inode: %d\n", ret); goto err; } dev->anon_inode = inode; if (drm_core_check_feature(dev, DRIVER_COMPUTE_ACCEL)) { ret = drm_minor_alloc(dev, DRM_MINOR_ACCEL); if (ret) goto err; } else { if (drm_core_check_feature(dev, DRIVER_RENDER)) { ret = drm_minor_alloc(dev, DRM_MINOR_RENDER); if (ret) goto err; } ret = drm_minor_alloc(dev, DRM_MINOR_PRIMARY); if (ret) goto err; } if (drm_core_check_feature(dev, DRIVER_GEM)) { ret = drm_gem_init(dev); if (ret) { DRM_ERROR("Cannot initialize graphics execution manager (GEM)\n"); goto err; } } dev->unique = drmm_kstrdup(dev, dev_name(parent), GFP_KERNEL); if (!dev->unique) { ret = -ENOMEM; goto err; } if (drm_core_check_feature(dev, DRIVER_COMPUTE_ACCEL)) accel_debugfs_init(dev); else drm_debugfs_dev_init(dev, drm_debugfs_root); return 0; err: drm_managed_release(dev); return ret; } static void devm_drm_dev_init_release(void *data) { drm_dev_put(data); } static int devm_drm_dev_init(struct device *parent, struct drm_device *dev, const struct drm_driver *driver) { int ret; ret = drm_dev_init(dev, driver, parent); if (ret) return ret; return devm_add_action_or_reset(parent, devm_drm_dev_init_release, dev); } void *__devm_drm_dev_alloc(struct device *parent, const struct drm_driver *driver, size_t size, size_t offset) { void *container; struct drm_device *drm; int ret; container = kzalloc(size, GFP_KERNEL); if (!container) return ERR_PTR(-ENOMEM); drm = container + offset; ret = devm_drm_dev_init(parent, drm, driver); if (ret) { kfree(container); return ERR_PTR(ret); } drmm_add_final_kfree(drm, container); return container; } EXPORT_SYMBOL(__devm_drm_dev_alloc); /** * drm_dev_alloc - Allocate new DRM device * @driver: DRM driver to allocate device for * @parent: Parent device object * * This is the deprecated version of devm_drm_dev_alloc(), which does not support * subclassing through embedding the struct &drm_device in a driver private * structure, and which does not support automatic cleanup through devres. * * RETURNS: * Pointer to new DRM device, or ERR_PTR on failure. */ struct drm_device *drm_dev_alloc(const struct drm_driver *driver, struct device *parent) { struct drm_device *dev; int ret; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return ERR_PTR(-ENOMEM); ret = drm_dev_init(dev, driver, parent); if (ret) { kfree(dev); return ERR_PTR(ret); } drmm_add_final_kfree(dev, dev); return dev; } EXPORT_SYMBOL(drm_dev_alloc); static void drm_dev_release(struct kref *ref) { struct drm_device *dev = container_of(ref, struct drm_device, ref); /* Just in case register/unregister was never called */ drm_debugfs_dev_fini(dev); if (dev->driver->release) dev->driver->release(dev); drm_managed_release(dev); kfree(dev->managed.final_kfree); } /** * drm_dev_get - Take reference of a DRM device * @dev: device to take reference of or NULL * * This increases the ref-count of @dev by one. You *must* already own a * reference when calling this. Use drm_dev_put() to drop this reference * again. * * This function never fails. However, this function does not provide *any* * guarantee whether the device is alive or running. It only provides a * reference to the object and the memory associated with it. */ void drm_dev_get(struct drm_device *dev) { if (dev) kref_get(&dev->ref); } EXPORT_SYMBOL(drm_dev_get); /** * drm_dev_put - Drop reference of a DRM device * @dev: device to drop reference of or NULL * * This decreases the ref-count of @dev by one. The device is destroyed if the * ref-count drops to zero. */ void drm_dev_put(struct drm_device *dev) { if (dev) kref_put(&dev->ref, drm_dev_release); } EXPORT_SYMBOL(drm_dev_put); static void drmm_cg_unregister_region(struct drm_device *dev, void *arg) { dmem_cgroup_unregister_region(arg); } /** * drmm_cgroup_register_region - Register a region of a DRM device to cgroups * @dev: device for region * @region_name: Region name for registering * @size: Size of region in bytes * * This decreases the ref-count of @dev by one. The device is destroyed if the * ref-count drops to zero. */ struct dmem_cgroup_region *drmm_cgroup_register_region(struct drm_device *dev, const char *region_name, u64 size) { struct dmem_cgroup_region *region; int ret; region = dmem_cgroup_register_region(size, "drm/%s/%s", dev->unique, region_name); if (IS_ERR_OR_NULL(region)) return region; ret = drmm_add_action_or_reset(dev, drmm_cg_unregister_region, region); if (ret) return ERR_PTR(ret); return region; } EXPORT_SYMBOL_GPL(drmm_cgroup_register_region); static int create_compat_control_link(struct drm_device *dev) { struct drm_minor *minor; char *name; int ret; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return 0; minor = *drm_minor_get_slot(dev, DRM_MINOR_PRIMARY); if (!minor) return 0; /* * Some existing userspace out there uses the existing of the controlD* * sysfs files to figure out whether it's a modeset driver. It only does * readdir, hence a symlink is sufficient (and the least confusing * option). Otherwise controlD* is entirely unused. * * Old controlD chardev have been allocated in the range * 64-127. */ name = kasprintf(GFP_KERNEL, "controlD%d", minor->index + 64); if (!name) return -ENOMEM; ret = sysfs_create_link(minor->kdev->kobj.parent, &minor->kdev->kobj, name); kfree(name); return ret; } static void remove_compat_control_link(struct drm_device *dev) { struct drm_minor *minor; char *name; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return; minor = *drm_minor_get_slot(dev, DRM_MINOR_PRIMARY); if (!minor) return; name = kasprintf(GFP_KERNEL, "controlD%d", minor->index + 64); if (!name) return; sysfs_remove_link(minor->kdev->kobj.parent, name); kfree(name); } /** * drm_dev_register - Register DRM device * @dev: Device to register * @flags: Flags passed to the driver's .load() function * * Register the DRM device @dev with the system, advertise device to user-space * and start normal device operation. @dev must be initialized via drm_dev_init() * previously. * * Never call this twice on any device! * * NOTE: To ensure backward compatibility with existing drivers method this * function calls the &drm_driver.load method after registering the device * nodes, creating race conditions. Usage of the &drm_driver.load methods is * therefore deprecated, drivers must perform all initialization before calling * drm_dev_register(). * * RETURNS: * 0 on success, negative error code on failure. */ int drm_dev_register(struct drm_device *dev, unsigned long flags) { const struct drm_driver *driver = dev->driver; int ret; if (!driver->load) drm_mode_config_validate(dev); WARN_ON(!dev->managed.final_kfree); if (drm_dev_needs_global_mutex(dev)) mutex_lock(&drm_global_mutex); if (drm_core_check_feature(dev, DRIVER_COMPUTE_ACCEL)) accel_debugfs_register(dev); else drm_debugfs_dev_register(dev); ret = drm_minor_register(dev, DRM_MINOR_RENDER); if (ret) goto err_minors; ret = drm_minor_register(dev, DRM_MINOR_PRIMARY); if (ret) goto err_minors; ret = drm_minor_register(dev, DRM_MINOR_ACCEL); if (ret) goto err_minors; ret = create_compat_control_link(dev); if (ret) goto err_minors; dev->registered = true; if (driver->load) { ret = driver->load(dev, flags); if (ret) goto err_minors; } if (drm_core_check_feature(dev, DRIVER_MODESET)) { ret = drm_modeset_register_all(dev); if (ret) goto err_unload; } drm_panic_register(dev); DRM_INFO("Initialized %s %d.%d.%d for %s on minor %d\n", driver->name, driver->major, driver->minor, driver->patchlevel, dev->dev ? dev_name(dev->dev) : "virtual device", dev->primary ? dev->primary->index : dev->accel->index); goto out_unlock; err_unload: if (dev->driver->unload) dev->driver->unload(dev); err_minors: remove_compat_control_link(dev); drm_minor_unregister(dev, DRM_MINOR_ACCEL); drm_minor_unregister(dev, DRM_MINOR_PRIMARY); drm_minor_unregister(dev, DRM_MINOR_RENDER); out_unlock: if (drm_dev_needs_global_mutex(dev)) mutex_unlock(&drm_global_mutex); return ret; } EXPORT_SYMBOL(drm_dev_register); /** * drm_dev_unregister - Unregister DRM device * @dev: Device to unregister * * Unregister the DRM device from the system. This does the reverse of * drm_dev_register() but does not deallocate the device. The caller must call * drm_dev_put() to drop their final reference, unless it is managed with devres * (as devices allocated with devm_drm_dev_alloc() are), in which case there is * already an unwind action registered. * * A special form of unregistering for hotpluggable devices is drm_dev_unplug(), * which can be called while there are still open users of @dev. * * This should be called first in the device teardown code to make sure * userspace can't access the device instance any more. */ void drm_dev_unregister(struct drm_device *dev) { dev->registered = false; drm_panic_unregister(dev); drm_client_dev_unregister(dev); if (drm_core_check_feature(dev, DRIVER_MODESET)) drm_modeset_unregister_all(dev); if (dev->driver->unload) dev->driver->unload(dev); remove_compat_control_link(dev); drm_minor_unregister(dev, DRM_MINOR_ACCEL); drm_minor_unregister(dev, DRM_MINOR_PRIMARY); drm_minor_unregister(dev, DRM_MINOR_RENDER); drm_debugfs_dev_fini(dev); } EXPORT_SYMBOL(drm_dev_unregister); /* * DRM Core * The DRM core module initializes all global DRM objects and makes them * available to drivers. Once setup, drivers can probe their respective * devices. * Currently, core management includes: * - The "DRM-Global" key/value database * - Global ID management for connectors * - DRM major number allocation * - DRM minor management * - DRM sysfs class * - DRM debugfs root * * Furthermore, the DRM core provides dynamic char-dev lookups. For each * interface registered on a DRM device, you can request minor numbers from DRM * core. DRM core takes care of major-number management and char-dev * registration. A stub ->open() callback forwards any open() requests to the * registered minor. */ static int drm_stub_open(struct inode *inode, struct file *filp) { const struct file_operations *new_fops; struct drm_minor *minor; int err; DRM_DEBUG("\n"); minor = drm_minor_acquire(&drm_minors_xa, iminor(inode)); if (IS_ERR(minor)) return PTR_ERR(minor); new_fops = fops_get(minor->dev->driver->fops); if (!new_fops) { err = -ENODEV; goto out; } replace_fops(filp, new_fops); if (filp->f_op->open) err = filp->f_op->open(inode, filp); else err = 0; out: drm_minor_release(minor); return err; } static const struct file_operations drm_stub_fops = { .owner = THIS_MODULE, .open = drm_stub_open, .llseek = noop_llseek, }; static void drm_core_exit(void) { drm_privacy_screen_lookup_exit(); drm_panic_exit(); accel_core_exit(); unregister_chrdev(DRM_MAJOR, "drm"); debugfs_remove(drm_debugfs_root); drm_sysfs_destroy(); WARN_ON(!xa_empty(&drm_minors_xa)); drm_connector_ida_destroy(); } static int __init drm_core_init(void) { int ret; drm_connector_ida_init(); drm_memcpy_init_early(); ret = drm_sysfs_init(); if (ret < 0) { DRM_ERROR("Cannot create DRM class: %d\n", ret); goto error; } drm_debugfs_root = debugfs_create_dir("dri", NULL); ret = register_chrdev(DRM_MAJOR, "drm", &drm_stub_fops); if (ret < 0) goto error; ret = accel_core_init(); if (ret < 0) goto error; drm_panic_init(); drm_privacy_screen_lookup_init(); drm_core_init_complete = true; DRM_DEBUG("Initialized\n"); return 0; error: drm_core_exit(); return ret; } module_init(drm_core_init); module_exit(drm_core_exit); |
| 1 1 1 1 1 1 1 1 1 17 17 17 10 6 17 6 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 10 4 6 6 5 6 2 2 2 2 2 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * TUN - Universal TUN/TAP device driver. * Copyright (C) 1999-2002 Maxim Krasnyansky <maxk@qualcomm.com> * * $Id: tun.c,v 1.15 2002/03/01 02:44:24 maxk Exp $ */ /* * Changes: * * Mike Kershaw <dragorn@kismetwireless.net> 2005/08/14 * Add TUNSETLINK ioctl to set the link encapsulation * * Mark Smith <markzzzsmith@yahoo.com.au> * Use eth_random_addr() for tap MAC address. * * Harald Roelle <harald.roelle@ifi.lmu.de> 2004/04/20 * Fixes in packet dropping, queue length setting and queue wakeup. * Increased default tx queue length. * Added ethtool API. * Minor cleanups * * Daniel Podlejski <underley@underley.eu.org> * Modifications for 2.3.99-pre5 kernel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "tun" #define DRV_VERSION "1.6" #define DRV_DESCRIPTION "Universal TUN/TAP device driver" #define DRV_COPYRIGHT "(C) 1999-2004 Max Krasnyansky <maxk@qualcomm.com>" #include <linux/module.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/major.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/fcntl.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/miscdevice.h> #include <linux/ethtool.h> #include <linux/rtnetlink.h> #include <linux/compat.h> #include <linux/if.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/if_tun.h> #include <linux/if_vlan.h> #include <linux/crc32.h> #include <linux/math.h> #include <linux/nsproxy.h> #include <linux/virtio_net.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <net/xdp.h> #include <net/ip_tunnels.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/skb_array.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/mutex.h> #include <linux/ieee802154.h> #include <uapi/linux/if_ltalk.h> #include <uapi/linux/if_fddi.h> #include <uapi/linux/if_hippi.h> #include <uapi/linux/if_fc.h> #include <net/ax25.h> #include <net/rose.h> #include <net/6lowpan.h> #include <net/rps.h> #include <linux/uaccess.h> #include <linux/proc_fs.h> #include "tun_vnet.h" static void tun_default_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd); #define TUN_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) /* TUN device flags */ /* IFF_ATTACH_QUEUE is never stored in device flags, * overload it to mean fasync when stored there. */ #define TUN_FASYNC IFF_ATTACH_QUEUE #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \ IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS) #define GOODCOPY_LEN 128 #define FLT_EXACT_COUNT 8 struct tap_filter { unsigned int count; /* Number of addrs. Zero means disabled */ u32 mask[2]; /* Mask of the hashed addrs */ unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN]; }; /* MAX_TAP_QUEUES 256 is chosen to allow rx/tx queues to be equal * to max number of VCPUs in guest. */ #define MAX_TAP_QUEUES 256 #define MAX_TAP_FLOWS 4096 #define TUN_FLOW_EXPIRE (3 * HZ) /* A tun_file connects an open character device to a tuntap netdevice. It * also contains all socket related structures (except sock_fprog and tap_filter) * to serve as one transmit queue for tuntap device. The sock_fprog and * tap_filter were kept in tun_struct since they were used for filtering for the * netdevice not for a specific queue (at least I didn't see the requirement for * this). * * RCU usage: * The tun_file and tun_struct are loosely coupled, the pointer from one to the * other can only be read while rcu_read_lock or rtnl_lock is held. */ struct tun_file { struct sock sk; struct socket socket; struct tun_struct __rcu *tun; struct fasync_struct *fasync; /* only used for fasnyc */ unsigned int flags; union { u16 queue_index; unsigned int ifindex; }; struct napi_struct napi; bool napi_enabled; bool napi_frags_enabled; struct mutex napi_mutex; /* Protects access to the above napi */ struct list_head next; struct tun_struct *detached; struct ptr_ring tx_ring; struct xdp_rxq_info xdp_rxq; }; struct tun_page { struct page *page; int count; }; struct tun_flow_entry { struct hlist_node hash_link; struct rcu_head rcu; struct tun_struct *tun; u32 rxhash; u32 rps_rxhash; int queue_index; unsigned long updated ____cacheline_aligned_in_smp; }; #define TUN_NUM_FLOW_ENTRIES 1024 #define TUN_MASK_FLOW_ENTRIES (TUN_NUM_FLOW_ENTRIES - 1) struct tun_prog { struct rcu_head rcu; struct bpf_prog *prog; }; /* Since the socket were moved to tun_file, to preserve the behavior of persist * device, socket filter, sndbuf and vnet header size were restore when the * file were attached to a persist device. */ struct tun_struct { struct tun_file __rcu *tfiles[MAX_TAP_QUEUES]; unsigned int numqueues; unsigned int flags; kuid_t owner; kgid_t group; struct net_device *dev; netdev_features_t set_features; #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4) int align; int vnet_hdr_sz; int sndbuf; struct tap_filter txflt; struct sock_fprog fprog; /* protected by rtnl lock */ bool filter_attached; u32 msg_enable; spinlock_t lock; struct hlist_head flows[TUN_NUM_FLOW_ENTRIES]; struct timer_list flow_gc_timer; unsigned long ageing_time; unsigned int numdisabled; struct list_head disabled; void *security; u32 flow_count; u32 rx_batched; atomic_long_t rx_frame_errors; struct bpf_prog __rcu *xdp_prog; struct tun_prog __rcu *steering_prog; struct tun_prog __rcu *filter_prog; struct ethtool_link_ksettings link_ksettings; /* init args */ struct file *file; struct ifreq *ifr; }; struct veth { __be16 h_vlan_proto; __be16 h_vlan_TCI; }; static void tun_flow_init(struct tun_struct *tun); static void tun_flow_uninit(struct tun_struct *tun); static int tun_napi_receive(struct napi_struct *napi, int budget) { struct tun_file *tfile = container_of(napi, struct tun_file, napi); struct sk_buff_head *queue = &tfile->sk.sk_write_queue; struct sk_buff_head process_queue; struct sk_buff *skb; int received = 0; __skb_queue_head_init(&process_queue); spin_lock(&queue->lock); skb_queue_splice_tail_init(queue, &process_queue); spin_unlock(&queue->lock); while (received < budget && (skb = __skb_dequeue(&process_queue))) { napi_gro_receive(napi, skb); ++received; } if (!skb_queue_empty(&process_queue)) { spin_lock(&queue->lock); skb_queue_splice(&process_queue, queue); spin_unlock(&queue->lock); } return received; } static int tun_napi_poll(struct napi_struct *napi, int budget) { unsigned int received; received = tun_napi_receive(napi, budget); if (received < budget) napi_complete_done(napi, received); return received; } static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, bool napi_en, bool napi_frags) { tfile->napi_enabled = napi_en; tfile->napi_frags_enabled = napi_en && napi_frags; if (napi_en) { netif_napi_add_tx(tun->dev, &tfile->napi, tun_napi_poll); napi_enable(&tfile->napi); } } static void tun_napi_enable(struct tun_file *tfile) { if (tfile->napi_enabled) napi_enable(&tfile->napi); } static void tun_napi_disable(struct tun_file *tfile) { if (tfile->napi_enabled) napi_disable(&tfile->napi); } static void tun_napi_del(struct tun_file *tfile) { if (tfile->napi_enabled) netif_napi_del(&tfile->napi); } static bool tun_napi_frags_enabled(const struct tun_file *tfile) { return tfile->napi_frags_enabled; } static inline u32 tun_hashfn(u32 rxhash) { return rxhash & TUN_MASK_FLOW_ENTRIES; } static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash) { struct tun_flow_entry *e; hlist_for_each_entry_rcu(e, head, hash_link) { if (e->rxhash == rxhash) return e; } return NULL; } static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun, struct hlist_head *head, u32 rxhash, u16 queue_index) { struct tun_flow_entry *e = kmalloc(sizeof(*e), GFP_ATOMIC); if (e) { netif_info(tun, tx_queued, tun->dev, "create flow: hash %u index %u\n", rxhash, queue_index); e->updated = jiffies; e->rxhash = rxhash; e->rps_rxhash = 0; e->queue_index = queue_index; e->tun = tun; hlist_add_head_rcu(&e->hash_link, head); ++tun->flow_count; } return e; } static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e) { netif_info(tun, tx_queued, tun->dev, "delete flow: hash %u index %u\n", e->rxhash, e->queue_index); hlist_del_rcu(&e->hash_link); kfree_rcu(e, rcu); --tun->flow_count; } static void tun_flow_flush(struct tun_struct *tun) { int i; spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) tun_flow_delete(tun, e); } spin_unlock_bh(&tun->lock); } static void tun_flow_delete_by_queue(struct tun_struct *tun, u16 queue_index) { int i; spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { if (e->queue_index == queue_index) tun_flow_delete(tun, e); } } spin_unlock_bh(&tun->lock); } static void tun_flow_cleanup(struct timer_list *t) { struct tun_struct *tun = from_timer(tun, t, flow_gc_timer); unsigned long delay = tun->ageing_time; unsigned long next_timer = jiffies + delay; unsigned long count = 0; int i; spin_lock(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { unsigned long this_timer; this_timer = e->updated + delay; if (time_before_eq(this_timer, jiffies)) { tun_flow_delete(tun, e); continue; } count++; if (time_before(this_timer, next_timer)) next_timer = this_timer; } } if (count) mod_timer(&tun->flow_gc_timer, round_jiffies_up(next_timer)); spin_unlock(&tun->lock); } static void tun_flow_update(struct tun_struct *tun, u32 rxhash, struct tun_file *tfile) { struct hlist_head *head; struct tun_flow_entry *e; unsigned long delay = tun->ageing_time; u16 queue_index = tfile->queue_index; head = &tun->flows[tun_hashfn(rxhash)]; rcu_read_lock(); e = tun_flow_find(head, rxhash); if (likely(e)) { /* TODO: keep queueing to old queue until it's empty? */ if (READ_ONCE(e->queue_index) != queue_index) WRITE_ONCE(e->queue_index, queue_index); if (e->updated != jiffies) e->updated = jiffies; sock_rps_record_flow_hash(e->rps_rxhash); } else { spin_lock_bh(&tun->lock); if (!tun_flow_find(head, rxhash) && tun->flow_count < MAX_TAP_FLOWS) tun_flow_create(tun, head, rxhash, queue_index); if (!timer_pending(&tun->flow_gc_timer)) mod_timer(&tun->flow_gc_timer, round_jiffies_up(jiffies + delay)); spin_unlock_bh(&tun->lock); } rcu_read_unlock(); } /* Save the hash received in the stack receive path and update the * flow_hash table accordingly. */ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) { if (unlikely(e->rps_rxhash != hash)) e->rps_rxhash = hash; } /* We try to identify a flow through its rxhash. The reason that * we do not check rxq no. is because some cards(e.g 82599), chooses * the rxq based on the txq where the last packet of the flow comes. As * the userspace application move between processors, we may get a * different rxq no. here. */ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb) { struct tun_flow_entry *e; u32 txq, numqueues; numqueues = READ_ONCE(tun->numqueues); txq = __skb_get_hash_symmetric(skb); e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq); if (e) { tun_flow_save_rps_rxhash(e, txq); txq = e->queue_index; } else { txq = reciprocal_scale(txq, numqueues); } return txq; } static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb) { struct tun_prog *prog; u32 numqueues; u16 ret = 0; numqueues = READ_ONCE(tun->numqueues); if (!numqueues) return 0; prog = rcu_dereference(tun->steering_prog); if (prog) ret = bpf_prog_run_clear_cb(prog->prog, skb); return ret % numqueues; } static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { struct tun_struct *tun = netdev_priv(dev); u16 ret; rcu_read_lock(); if (rcu_dereference(tun->steering_prog)) ret = tun_ebpf_select_queue(tun, skb); else ret = tun_automq_select_queue(tun, skb); rcu_read_unlock(); return ret; } static inline bool tun_not_capable(struct tun_struct *tun) { const struct cred *cred = current_cred(); struct net *net = dev_net(tun->dev); return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) || (gid_valid(tun->group) && !in_egroup_p(tun->group))) && !ns_capable(net->user_ns, CAP_NET_ADMIN); } static void tun_set_real_num_queues(struct tun_struct *tun) { netif_set_real_num_tx_queues(tun->dev, tun->numqueues); netif_set_real_num_rx_queues(tun->dev, tun->numqueues); } static void tun_disable_queue(struct tun_struct *tun, struct tun_file *tfile) { tfile->detached = tun; list_add_tail(&tfile->next, &tun->disabled); ++tun->numdisabled; } static struct tun_struct *tun_enable_queue(struct tun_file *tfile) { struct tun_struct *tun = tfile->detached; tfile->detached = NULL; list_del_init(&tfile->next); --tun->numdisabled; return tun; } void tun_ptr_free(void *ptr) { if (!ptr) return; if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); xdp_return_frame(xdpf); } else { __skb_array_destroy_skb(ptr); } } EXPORT_SYMBOL_GPL(tun_ptr_free); static void tun_queue_purge(struct tun_file *tfile) { void *ptr; while ((ptr = ptr_ring_consume(&tfile->tx_ring)) != NULL) tun_ptr_free(ptr); skb_queue_purge(&tfile->sk.sk_write_queue); skb_queue_purge(&tfile->sk.sk_error_queue); } static void __tun_detach(struct tun_file *tfile, bool clean) { struct tun_file *ntfile; struct tun_struct *tun; tun = rtnl_dereference(tfile->tun); if (tun && clean) { if (!tfile->detached) tun_napi_disable(tfile); tun_napi_del(tfile); } if (tun && !tfile->detached) { u16 index = tfile->queue_index; BUG_ON(index >= tun->numqueues); rcu_assign_pointer(tun->tfiles[index], tun->tfiles[tun->numqueues - 1]); ntfile = rtnl_dereference(tun->tfiles[index]); ntfile->queue_index = index; ntfile->xdp_rxq.queue_index = index; rcu_assign_pointer(tun->tfiles[tun->numqueues - 1], NULL); --tun->numqueues; if (clean) { RCU_INIT_POINTER(tfile->tun, NULL); sock_put(&tfile->sk); } else { tun_disable_queue(tun, tfile); tun_napi_disable(tfile); } synchronize_net(); tun_flow_delete_by_queue(tun, tun->numqueues + 1); /* Drop read queue */ tun_queue_purge(tfile); tun_set_real_num_queues(tun); } else if (tfile->detached && clean) { tun = tun_enable_queue(tfile); sock_put(&tfile->sk); } if (clean) { if (tun && tun->numqueues == 0 && tun->numdisabled == 0) { netif_carrier_off(tun->dev); if (!(tun->flags & IFF_PERSIST) && tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); } if (tun) xdp_rxq_info_unreg(&tfile->xdp_rxq); ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free); } } static void tun_detach(struct tun_file *tfile, bool clean) { struct tun_struct *tun; struct net_device *dev; rtnl_lock(); tun = rtnl_dereference(tfile->tun); dev = tun ? tun->dev : NULL; __tun_detach(tfile, clean); if (dev) netdev_state_change(dev); rtnl_unlock(); if (clean) sock_put(&tfile->sk); } static void tun_detach_all(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile, *tmp; int i, n = tun->numqueues; for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); BUG_ON(!tfile); tun_napi_disable(tfile); tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); --tun->numqueues; } list_for_each_entry(tfile, &tun->disabled, next) { tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); } BUG_ON(tun->numqueues != 0); synchronize_net(); for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); tun_napi_del(tfile); /* Drop read queue */ tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { tun_napi_del(tfile); tun_enable_queue(tfile); tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } BUG_ON(tun->numdisabled != 0); if (tun->flags & IFF_PERSIST) module_put(THIS_MODULE); } static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter, bool napi, bool napi_frags, bool publish_tun) { struct tun_file *tfile = file->private_data; struct net_device *dev = tun->dev; int err; err = security_tun_dev_attach(tfile->socket.sk, tun->security); if (err < 0) goto out; err = -EINVAL; if (rtnl_dereference(tfile->tun) && !tfile->detached) goto out; err = -EBUSY; if (!(tun->flags & IFF_MULTI_QUEUE) && tun->numqueues == 1) goto out; err = -E2BIG; if (!tfile->detached && tun->numqueues + tun->numdisabled == MAX_TAP_QUEUES) goto out; err = 0; /* Re-attach the filter to persist device */ if (!skip_filter && (tun->filter_attached == true)) { lock_sock(tfile->socket.sk); err = sk_attach_filter(&tun->fprog, tfile->socket.sk); release_sock(tfile->socket.sk); if (!err) goto out; } if (!tfile->detached && ptr_ring_resize(&tfile->tx_ring, dev->tx_queue_len, GFP_KERNEL, tun_ptr_free)) { err = -ENOMEM; goto out; } tfile->queue_index = tun->numqueues; tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN; if (tfile->detached) { /* Re-attach detached tfile, updating XDP queue_index */ WARN_ON(!xdp_rxq_info_is_reg(&tfile->xdp_rxq)); if (tfile->xdp_rxq.queue_index != tfile->queue_index) tfile->xdp_rxq.queue_index = tfile->queue_index; } else { /* Setup XDP RX-queue info, for new tfile getting attached */ err = xdp_rxq_info_reg(&tfile->xdp_rxq, tun->dev, tfile->queue_index, 0); if (err < 0) goto out; err = xdp_rxq_info_reg_mem_model(&tfile->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err < 0) { xdp_rxq_info_unreg(&tfile->xdp_rxq); goto out; } err = 0; } if (tfile->detached) { tun_enable_queue(tfile); tun_napi_enable(tfile); } else { sock_hold(&tfile->sk); tun_napi_init(tun, tfile, napi, napi_frags); } if (rtnl_dereference(tun->xdp_prog)) sock_set_flag(&tfile->sk, SOCK_XDP); /* device is allowed to go away first, so no need to hold extra * refcnt. */ /* Publish tfile->tun and tun->tfiles only after we've fully * initialized tfile; otherwise we risk using half-initialized * object. */ if (publish_tun) rcu_assign_pointer(tfile->tun, tun); rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); tun->numqueues++; tun_set_real_num_queues(tun); out: return err; } static struct tun_struct *tun_get(struct tun_file *tfile) { struct tun_struct *tun; rcu_read_lock(); tun = rcu_dereference(tfile->tun); if (tun) dev_hold(tun->dev); rcu_read_unlock(); return tun; } static void tun_put(struct tun_struct *tun) { dev_put(tun->dev); } /* TAP filtering */ static void addr_hash_set(u32 *mask, const u8 *addr) { int n = ether_crc(ETH_ALEN, addr) >> 26; mask[n >> 5] |= (1 << (n & 31)); } static unsigned int addr_hash_test(const u32 *mask, const u8 *addr) { int n = ether_crc(ETH_ALEN, addr) >> 26; return mask[n >> 5] & (1 << (n & 31)); } static int update_filter(struct tap_filter *filter, void __user *arg) { struct { u8 u[ETH_ALEN]; } *addr; struct tun_filter uf; int err, alen, n, nexact; if (copy_from_user(&uf, arg, sizeof(uf))) return -EFAULT; if (!uf.count) { /* Disabled */ filter->count = 0; return 0; } alen = ETH_ALEN * uf.count; addr = memdup_user(arg + sizeof(uf), alen); if (IS_ERR(addr)) return PTR_ERR(addr); /* The filter is updated without holding any locks. Which is * perfectly safe. We disable it first and in the worst * case we'll accept a few undesired packets. */ filter->count = 0; wmb(); /* Use first set of addresses as an exact filter */ for (n = 0; n < uf.count && n < FLT_EXACT_COUNT; n++) memcpy(filter->addr[n], addr[n].u, ETH_ALEN); nexact = n; /* Remaining multicast addresses are hashed, * unicast will leave the filter disabled. */ memset(filter->mask, 0, sizeof(filter->mask)); for (; n < uf.count; n++) { if (!is_multicast_ether_addr(addr[n].u)) { err = 0; /* no filter */ goto free_addr; } addr_hash_set(filter->mask, addr[n].u); } /* For ALLMULTI just set the mask to all ones. * This overrides the mask populated above. */ if ((uf.flags & TUN_FLT_ALLMULTI)) memset(filter->mask, ~0, sizeof(filter->mask)); /* Now enable the filter */ wmb(); filter->count = nexact; /* Return the number of exact filters */ err = nexact; free_addr: kfree(addr); return err; } /* Returns: 0 - drop, !=0 - accept */ static int run_filter(struct tap_filter *filter, const struct sk_buff *skb) { /* Cannot use eth_hdr(skb) here because skb_mac_hdr() is incorrect * at this point. */ struct ethhdr *eh = (struct ethhdr *) skb->data; int i; /* Exact match */ for (i = 0; i < filter->count; i++) if (ether_addr_equal(eh->h_dest, filter->addr[i])) return 1; /* Inexact match (multicast only) */ if (is_multicast_ether_addr(eh->h_dest)) return addr_hash_test(filter->mask, eh->h_dest); return 0; } /* * Checks whether the packet is accepted or not. * Returns: 0 - drop, !=0 - accept */ static int check_filter(struct tap_filter *filter, const struct sk_buff *skb) { if (!filter->count) return 1; return run_filter(filter, skb); } /* Network device part of the driver */ static const struct ethtool_ops tun_ethtool_ops; static int tun_net_init(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); struct ifreq *ifr = tun->ifr; int err; spin_lock_init(&tun->lock); err = security_tun_dev_alloc_security(&tun->security); if (err < 0) return err; tun_flow_init(tun); dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->features = dev->hw_features; dev->vlan_features = dev->features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); dev->lltx = true; tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); INIT_LIST_HEAD(&tun->disabled); err = tun_attach(tun, tun->file, false, ifr->ifr_flags & IFF_NAPI, ifr->ifr_flags & IFF_NAPI_FRAGS, false); if (err < 0) { tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); return err; } return 0; } /* Net device detach from fd. */ static void tun_net_uninit(struct net_device *dev) { tun_detach_all(dev); } /* Net device open. */ static int tun_net_open(struct net_device *dev) { netif_tx_start_all_queues(dev); return 0; } /* Net device close. */ static int tun_net_close(struct net_device *dev) { netif_tx_stop_all_queues(dev); return 0; } /* Net device start xmit */ static void tun_automq_xmit(struct tun_struct *tun, struct sk_buff *skb) { #ifdef CONFIG_RPS if (tun->numqueues == 1 && static_branch_unlikely(&rps_needed)) { /* Select queue was not called for the skbuff, so we extract the * RPS hash and save it into the flow_table here. */ struct tun_flow_entry *e; __u32 rxhash; rxhash = __skb_get_hash_symmetric(skb); e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)], rxhash); if (e) tun_flow_save_rps_rxhash(e, rxhash); } #endif } static unsigned int run_ebpf_filter(struct tun_struct *tun, struct sk_buff *skb, int len) { struct tun_prog *prog = rcu_dereference(tun->filter_prog); if (prog) len = bpf_prog_run_clear_cb(prog->prog, skb); return len; } /* Net device start xmit */ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); enum skb_drop_reason drop_reason; int txq = skb->queue_mapping; struct netdev_queue *queue; struct tun_file *tfile; int len = skb->len; rcu_read_lock(); tfile = rcu_dereference(tun->tfiles[txq]); /* Drop packet if interface is not attached */ if (!tfile) { drop_reason = SKB_DROP_REASON_DEV_READY; goto drop; } if (!rcu_dereference(tun->steering_prog)) tun_automq_xmit(tun, skb); netif_info(tun, tx_queued, tun->dev, "%s %d\n", __func__, skb->len); /* Drop if the filter does not like it. * This is a noop if the filter is disabled. * Filter can be enabled only for the TAP devices. */ if (!check_filter(&tun->txflt, skb)) { drop_reason = SKB_DROP_REASON_TAP_TXFILTER; goto drop; } if (tfile->socket.sk->sk_filter && sk_filter(tfile->socket.sk, skb)) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto drop; } len = run_ebpf_filter(tun, skb, len); if (len == 0) { drop_reason = SKB_DROP_REASON_TAP_FILTER; goto drop; } if (pskb_trim(skb, len)) { drop_reason = SKB_DROP_REASON_NOMEM; goto drop; } if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) { drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT; goto drop; } skb_tx_timestamp(skb); /* Orphan the skb - required as we might hang on to it * for indefinite time. */ skb_orphan(skb); nf_reset_ct(skb); if (ptr_ring_produce(&tfile->tx_ring, skb)) { drop_reason = SKB_DROP_REASON_FULL_RING; goto drop; } /* dev->lltx requires to do our own update of trans_start */ queue = netdev_get_tx_queue(dev, txq); txq_trans_cond_update(queue); /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); tfile->socket.sk->sk_data_ready(tfile->socket.sk); rcu_read_unlock(); return NETDEV_TX_OK; drop: dev_core_stats_tx_dropped_inc(dev); skb_tx_error(skb); kfree_skb_reason(skb, drop_reason); rcu_read_unlock(); return NET_XMIT_DROP; } static void tun_net_mclist(struct net_device *dev) { /* * This callback is supposed to deal with mc filter in * _rx_ path and has nothing to do with the _tx_ path. * In rx path we always accept everything userspace gives us. */ } static netdev_features_t tun_net_fix_features(struct net_device *dev, netdev_features_t features) { struct tun_struct *tun = netdev_priv(dev); return (features & tun->set_features) | (features & ~TUN_USER_FEATURES); } static void tun_set_headroom(struct net_device *dev, int new_hr) { struct tun_struct *tun = netdev_priv(dev); if (new_hr < NET_SKB_PAD) new_hr = NET_SKB_PAD; tun->align = new_hr; } static void tun_net_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct tun_struct *tun = netdev_priv(dev); dev_get_tstats64(dev, stats); stats->rx_frame_errors += (unsigned long)atomic_long_read(&tun->rx_frame_errors); } static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile; struct bpf_prog *old_prog; int i; old_prog = rtnl_dereference(tun->xdp_prog); rcu_assign_pointer(tun->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); if (prog) sock_set_flag(&tfile->sk, SOCK_XDP); else sock_reset_flag(&tfile->sk, SOCK_XDP); } list_for_each_entry(tfile, &tun->disabled, next) { if (prog) sock_set_flag(&tfile->sk, SOCK_XDP); else sock_reset_flag(&tfile->sk, SOCK_XDP); } return 0; } static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return tun_xdp_set(dev, xdp->prog, xdp->extack); default: return -EINVAL; } } static int tun_net_change_carrier(struct net_device *dev, bool new_carrier) { if (new_carrier) { struct tun_struct *tun = netdev_priv(dev); if (!tun->numqueues) return -EPERM; netif_carrier_on(dev); } else { netif_carrier_off(dev); } return 0; } static const struct net_device_ops tun_netdev_ops = { .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, .ndo_fix_features = tun_net_fix_features, .ndo_select_queue = tun_select_queue, .ndo_set_rx_headroom = tun_set_headroom, .ndo_get_stats64 = tun_net_get_stats64, .ndo_change_carrier = tun_net_change_carrier, }; static void __tun_xdp_flush_tfile(struct tun_file *tfile) { /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); tfile->socket.sk->sk_data_ready(tfile->socket.sk); } static int tun_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile; u32 numqueues; int nxmit = 0; int i; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; rcu_read_lock(); resample: numqueues = READ_ONCE(tun->numqueues); if (!numqueues) { rcu_read_unlock(); return -ENXIO; /* Caller will free/return all frames */ } tfile = rcu_dereference(tun->tfiles[smp_processor_id() % numqueues]); if (unlikely(!tfile)) goto resample; spin_lock(&tfile->tx_ring.producer_lock); for (i = 0; i < n; i++) { struct xdp_frame *xdp = frames[i]; /* Encode the XDP flag into lowest bit for consumer to differ * XDP buffer from sk_buff. */ void *frame = tun_xdp_to_ptr(xdp); if (__ptr_ring_produce(&tfile->tx_ring, frame)) { dev_core_stats_tx_dropped_inc(dev); break; } nxmit++; } spin_unlock(&tfile->tx_ring.producer_lock); if (flags & XDP_XMIT_FLUSH) __tun_xdp_flush_tfile(tfile); rcu_read_unlock(); return nxmit; } static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp) { struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp); int nxmit; if (unlikely(!frame)) return -EOVERFLOW; nxmit = tun_xdp_xmit(dev, 1, &frame, XDP_XMIT_FLUSH); if (!nxmit) xdp_return_frame_rx_napi(frame); return nxmit; } static const struct net_device_ops tap_netdev_ops = { .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, .ndo_fix_features = tun_net_fix_features, .ndo_set_rx_mode = tun_net_mclist, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_select_queue = tun_select_queue, .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = tun_set_headroom, .ndo_bpf = tun_xdp, .ndo_xdp_xmit = tun_xdp_xmit, .ndo_change_carrier = tun_net_change_carrier, }; static void tun_flow_init(struct tun_struct *tun) { int i; for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) INIT_HLIST_HEAD(&tun->flows[i]); tun->ageing_time = TUN_FLOW_EXPIRE; timer_setup(&tun->flow_gc_timer, tun_flow_cleanup, 0); mod_timer(&tun->flow_gc_timer, round_jiffies_up(jiffies + tun->ageing_time)); } static void tun_flow_uninit(struct tun_struct *tun) { del_timer_sync(&tun->flow_gc_timer); tun_flow_flush(tun); } #define MIN_MTU 68 #define MAX_MTU 65535 /* Initialize net device. */ static void tun_net_initialize(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: dev->netdev_ops = &tun_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; /* Point-to-Point TUN Device */ dev->hard_header_len = 0; dev->addr_len = 0; dev->mtu = 1500; /* Zero header length */ dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; break; case IFF_TAP: dev->netdev_ops = &tap_netdev_ops; /* Ethernet TAP Device */ ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; eth_hw_addr_random(dev); /* Currently tun does not support XDP, only tap does. */ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_NDO_XMIT; break; } dev->min_mtu = MIN_MTU; dev->max_mtu = MAX_MTU - dev->hard_header_len; } static bool tun_sock_writeable(struct tun_struct *tun, struct tun_file *tfile) { struct sock *sk = tfile->socket.sk; return (tun->dev->flags & IFF_UP) && sock_writeable(sk); } /* Character device part */ /* Poll */ static __poll_t tun_chr_poll(struct file *file, poll_table *wait) { struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); struct sock *sk; __poll_t mask = 0; if (!tun) return EPOLLERR; sk = tfile->socket.sk; poll_wait(file, sk_sleep(sk), wait); if (!ptr_ring_empty(&tfile->tx_ring)) mask |= EPOLLIN | EPOLLRDNORM; /* Make sure SOCKWQ_ASYNC_NOSPACE is set if not writable to * guarantee EPOLLOUT to be raised by either here or * tun_sock_write_space(). Then process could get notification * after it writes to a down device and meets -EIO. */ if (tun_sock_writeable(tun, tfile) || (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && tun_sock_writeable(tun, tfile))) mask |= EPOLLOUT | EPOLLWRNORM; if (tun->dev->reg_state != NETREG_REGISTERED) mask = EPOLLERR; tun_put(tun); return mask; } static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, size_t len, const struct iov_iter *it) { struct sk_buff *skb; size_t linear; int err; int i; if (it->nr_segs > MAX_SKB_FRAGS + 1 || len > (ETH_MAX_MTU - NET_SKB_PAD - NET_IP_ALIGN)) return ERR_PTR(-EMSGSIZE); local_bh_disable(); skb = napi_get_frags(&tfile->napi); local_bh_enable(); if (!skb) return ERR_PTR(-ENOMEM); linear = iov_iter_single_seg_count(it); err = __skb_grow(skb, linear); if (err) goto free; skb->len = len; skb->data_len = len - linear; skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { const struct iovec *iov = iter_iov(it) + i; size_t fragsz = iov->iov_len; struct page *page; void *frag; if (fragsz == 0 || fragsz > PAGE_SIZE) { err = -EINVAL; goto free; } frag = netdev_alloc_frag(fragsz); if (!frag) { err = -ENOMEM; goto free; } page = virt_to_head_page(frag); skb_fill_page_desc(skb, i - 1, page, frag - page_address(page), fragsz); } return skb; free: /* frees skb and all frags allocated with napi_alloc_frag() */ napi_free_frags(&tfile->napi); return ERR_PTR(err); } /* prepad is the amount to reserve at front. len is length after that. * linear is a hint as to how much to copy (usually headers). */ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile, size_t prepad, size_t len, size_t linear, int noblock) { struct sock *sk = tfile->socket.sk; struct sk_buff *skb; int err; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE) linear = len; if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER); skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, &err, PAGE_ALLOC_COSTLY_ORDER); if (!skb) return ERR_PTR(err); skb_reserve(skb, prepad); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile, struct sk_buff *skb, int more) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; struct sk_buff_head process_queue; u32 rx_batched = tun->rx_batched; bool rcv = false; if (!rx_batched || (!more && skb_queue_empty(queue))) { local_bh_disable(); skb_record_rx_queue(skb, tfile->queue_index); netif_receive_skb(skb); local_bh_enable(); return; } spin_lock(&queue->lock); if (!more || skb_queue_len(queue) == rx_batched) { __skb_queue_head_init(&process_queue); skb_queue_splice_tail_init(queue, &process_queue); rcv = true; } else { __skb_queue_tail(queue, skb); } spin_unlock(&queue->lock); if (rcv) { struct sk_buff *nskb; local_bh_disable(); while ((nskb = __skb_dequeue(&process_queue))) { skb_record_rx_queue(nskb, tfile->queue_index); netif_receive_skb(nskb); } skb_record_rx_queue(skb, tfile->queue_index); netif_receive_skb(skb); local_bh_enable(); } } static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, int len, int noblock, bool zerocopy) { if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) return false; if (tfile->socket.sk->sk_sndbuf != INT_MAX) return false; if (!noblock) return false; if (zerocopy) return false; if (SKB_DATA_ALIGN(len + TUN_RX_PAD + XDP_PACKET_HEADROOM) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return false; return true; } static struct sk_buff *__tun_build_skb(struct tun_file *tfile, struct page_frag *alloc_frag, char *buf, int buflen, int len, int pad, int metasize) { struct sk_buff *skb = build_skb(buf, buflen); if (!skb) return ERR_PTR(-ENOMEM); skb_reserve(skb, pad); skb_put(skb, len); if (metasize) skb_metadata_set(skb, metasize); skb_set_owner_w(skb, tfile->socket.sk); get_page(alloc_frag->page); alloc_frag->offset += buflen; return skb; } static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog, struct xdp_buff *xdp, u32 act) { int err; switch (act) { case XDP_REDIRECT: err = xdp_do_redirect(tun->dev, xdp, xdp_prog); if (err) { dev_core_stats_rx_dropped_inc(tun->dev); return err; } dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_TX: err = tun_xdp_tx(tun->dev, xdp); if (err < 0) { dev_core_stats_rx_dropped_inc(tun->dev); return err; } dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_PASS: break; default: bpf_warn_invalid_xdp_action(tun->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(tun->dev, xdp_prog, act); fallthrough; case XDP_DROP: dev_core_stats_rx_dropped_inc(tun->dev); break; } return act; } static struct sk_buff *tun_build_skb(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *from, struct virtio_net_hdr *hdr, int len, int *skb_xdp) { struct page_frag *alloc_frag = ¤t->task_frag; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct bpf_prog *xdp_prog; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); char *buf; size_t copied; int pad = TUN_RX_PAD; int metasize = 0; int err = 0; rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) pad += XDP_PACKET_HEADROOM; buflen += SKB_DATA_ALIGN(len + pad); rcu_read_unlock(); alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL))) return ERR_PTR(-ENOMEM); buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; copied = copy_page_from_iter(alloc_frag->page, alloc_frag->offset + pad, len, from); if (copied != len) return ERR_PTR(-EFAULT); /* There's a small window that XDP may be set after the check * of xdp_prog above, this should be rare and for simplicity * we do XDP on skb in case the headroom is not enough. */ if (hdr->gso_type || !xdp_prog) { *skb_xdp = 1; return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad, metasize); } *skb_xdp = 0; local_bh_disable(); rcu_read_lock(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { struct xdp_buff xdp; u32 act; xdp_init_buff(&xdp, buflen, &tfile->xdp_rxq); xdp_prepare_buff(&xdp, buf, pad, len, true); act = bpf_prog_run_xdp(xdp_prog, &xdp); if (act == XDP_REDIRECT || act == XDP_TX) { get_page(alloc_frag->page); alloc_frag->offset += buflen; } err = tun_xdp_act(tun, xdp_prog, &xdp, act); if (err < 0) { if (act == XDP_REDIRECT || act == XDP_TX) put_page(alloc_frag->page); goto out; } if (err == XDP_REDIRECT) xdp_do_flush(); if (err != XDP_PASS) goto out; pad = xdp.data - xdp.data_hard_start; len = xdp.data_end - xdp.data; /* It is known that the xdp_buff was prepared with metadata * support, so the metasize will never be negative. */ metasize = xdp.data - xdp.data_meta; } bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad, metasize); out: bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); return NULL; } /* Get packet from user space buffer */ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, void *msg_control, struct iov_iter *from, int noblock, bool more) { struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) }; struct sk_buff *skb; size_t total_len = iov_iter_count(from); size_t len = total_len, align = tun->align, linear; struct virtio_net_hdr gso = { 0 }; int good_linear; int copylen; int hdr_len = 0; bool zerocopy = false; int err; u32 rxhash = 0; int skb_xdp = 1; bool frags = tun_napi_frags_enabled(tfile); enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (!(tun->flags & IFF_NO_PI)) { if (len < sizeof(pi)) return -EINVAL; len -= sizeof(pi); if (!copy_from_iter_full(&pi, sizeof(pi), from)) return -EFAULT; } if (tun->flags & IFF_VNET_HDR) { int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); hdr_len = tun_vnet_hdr_get(vnet_hdr_sz, tun->flags, from, &gso); if (hdr_len < 0) return hdr_len; len -= vnet_hdr_sz; } if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) { align += NET_IP_ALIGN; if (unlikely(len < ETH_HLEN || (hdr_len && hdr_len < ETH_HLEN))) return -EINVAL; } good_linear = SKB_MAX_HEAD(align); if (msg_control) { struct iov_iter i = *from; /* There are 256 bytes to be copied in skb, so there is * enough room for skb expand head in case it is used. * The rest of the buffer is mapped from userspace. */ copylen = min(hdr_len ? hdr_len : GOODCOPY_LEN, good_linear); linear = copylen; iov_iter_advance(&i, copylen); if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS) zerocopy = true; } if (!frags && tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) { /* For the packet that is not easy to be processed * (e.g gso or jumbo packet), we will do it at after * skb was created with generic XDP routine. */ skb = tun_build_skb(tun, tfile, from, &gso, len, &skb_xdp); err = PTR_ERR_OR_ZERO(skb); if (err) goto drop; if (!skb) return total_len; } else { if (!zerocopy) { copylen = len; linear = min(hdr_len, good_linear); } if (frags) { mutex_lock(&tfile->napi_mutex); skb = tun_napi_alloc_frags(tfile, copylen, from); /* tun_napi_alloc_frags() enforces a layout for the skb. * If zerocopy is enabled, then this layout will be * overwritten by zerocopy_sg_from_iter(). */ zerocopy = false; } else { if (!linear) linear = min_t(size_t, good_linear, copylen); skb = tun_alloc_skb(tfile, align, copylen, linear, noblock); } err = PTR_ERR_OR_ZERO(skb); if (err) goto drop; if (zerocopy) err = zerocopy_sg_from_iter(skb, from); else err = skb_copy_datagram_from_iter(skb, 0, from, len); if (err) { err = -EFAULT; drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT; goto drop; } } if (tun_vnet_hdr_to_skb(tun->flags, skb, &gso)) { atomic_long_inc(&tun->rx_frame_errors); err = -EINVAL; goto free_skb; } switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: if (tun->flags & IFF_NO_PI) { u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0; switch (ip_version) { case 4: pi.proto = htons(ETH_P_IP); break; case 6: pi.proto = htons(ETH_P_IPV6); break; default: err = -EINVAL; goto drop; } } skb_reset_mac_header(skb); skb->protocol = pi.proto; skb->dev = tun->dev; break; case IFF_TAP: if (frags && !pskb_may_pull(skb, ETH_HLEN)) { err = -ENOMEM; drop_reason = SKB_DROP_REASON_HDR_TRUNC; goto drop; } skb->protocol = eth_type_trans(skb, tun->dev); break; } /* copy skb_ubuf_info for callback when skb has no error */ if (zerocopy) { skb_zcopy_init(skb, msg_control); } else if (msg_control) { struct ubuf_info *uarg = msg_control; uarg->ops->complete(NULL, uarg, false); } skb_reset_network_header(skb); skb_probe_transport_header(skb); skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { struct bpf_prog *xdp_prog; int ret; local_bh_disable(); rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { rcu_read_unlock(); local_bh_enable(); goto unlock_frags; } } rcu_read_unlock(); local_bh_enable(); } /* Compute the costly rx hash only if needed for flow updates. * We may get a very small possibility of OOO during switching, not * worth to optimize. */ if (!rcu_access_pointer(tun->steering_prog) && tun->numqueues > 1 && !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); rcu_read_lock(); if (unlikely(!(tun->dev->flags & IFF_UP))) { err = -EIO; rcu_read_unlock(); drop_reason = SKB_DROP_REASON_DEV_READY; goto drop; } if (frags) { u32 headlen; /* Exercise flow dissector code path. */ skb_push(skb, ETH_HLEN); headlen = eth_get_headlen(tun->dev, skb->data, skb_headlen(skb)); if (unlikely(headlen > skb_headlen(skb))) { WARN_ON_ONCE(1); err = -ENOMEM; dev_core_stats_rx_dropped_inc(tun->dev); napi_busy: napi_free_frags(&tfile->napi); rcu_read_unlock(); mutex_unlock(&tfile->napi_mutex); return err; } if (likely(napi_schedule_prep(&tfile->napi))) { local_bh_disable(); napi_gro_frags(&tfile->napi); napi_complete(&tfile->napi); local_bh_enable(); } else { err = -EBUSY; goto napi_busy; } mutex_unlock(&tfile->napi_mutex); } else if (tfile->napi_enabled) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; int queue_len; spin_lock_bh(&queue->lock); if (unlikely(tfile->detached)) { spin_unlock_bh(&queue->lock); rcu_read_unlock(); err = -EBUSY; goto free_skb; } __skb_queue_tail(queue, skb); queue_len = skb_queue_len(queue); spin_unlock(&queue->lock); if (!more || queue_len > NAPI_POLL_WEIGHT) napi_schedule(&tfile->napi); local_bh_enable(); } else if (!IS_ENABLED(CONFIG_4KSTACKS)) { tun_rx_batched(tun, tfile, skb, more); } else { netif_rx(skb); } rcu_read_unlock(); preempt_disable(); dev_sw_netstats_rx_add(tun->dev, len); preempt_enable(); if (rxhash) tun_flow_update(tun, rxhash, tfile); return total_len; drop: if (err != -EAGAIN) dev_core_stats_rx_dropped_inc(tun->dev); free_skb: if (!IS_ERR_OR_NULL(skb)) kfree_skb_reason(skb, drop_reason); unlock_frags: if (frags) { tfile->napi.skb = NULL; mutex_unlock(&tfile->napi_mutex); } return err ?: total_len; } static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t result; int noblock = 0; if (!tun) return -EBADFD; if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) noblock = 1; result = tun_get_user(tun, tfile, NULL, from, noblock, false); tun_put(tun); return result; } static ssize_t tun_put_user_xdp(struct tun_struct *tun, struct tun_file *tfile, struct xdp_frame *xdp_frame, struct iov_iter *iter) { int vnet_hdr_sz = 0; size_t size = xdp_frame->len; ssize_t ret; if (tun->flags & IFF_VNET_HDR) { struct virtio_net_hdr gso = { 0 }; vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso); if (ret) return ret; } ret = copy_to_iter(xdp_frame->data, size, iter) + vnet_hdr_sz; preempt_disable(); dev_sw_netstats_tx_add(tun->dev, 1, ret); preempt_enable(); return ret; } /* Put packet to the user space buffer */ static ssize_t tun_put_user(struct tun_struct *tun, struct tun_file *tfile, struct sk_buff *skb, struct iov_iter *iter) { struct tun_pi pi = { 0, skb->protocol }; ssize_t total; int vlan_offset = 0; int vlan_hlen = 0; int vnet_hdr_sz = 0; int ret; if (skb_vlan_tag_present(skb)) vlan_hlen = VLAN_HLEN; if (tun->flags & IFF_VNET_HDR) vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); total = skb->len + vlan_hlen + vnet_hdr_sz; if (!(tun->flags & IFF_NO_PI)) { if (iov_iter_count(iter) < sizeof(pi)) return -EINVAL; total += sizeof(pi); if (iov_iter_count(iter) < total) { /* Packet will be striped */ pi.flags |= TUN_PKT_STRIP; } if (copy_to_iter(&pi, sizeof(pi), iter) != sizeof(pi)) return -EFAULT; } if (vnet_hdr_sz) { struct virtio_net_hdr gso; ret = tun_vnet_hdr_from_skb(tun->flags, tun->dev, skb, &gso); if (ret) return ret; ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso); if (ret) return ret; } if (vlan_hlen) { int ret; struct veth veth; veth.h_vlan_proto = skb->vlan_proto; veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto); ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset); if (ret || !iov_iter_count(iter)) goto done; ret = copy_to_iter(&veth, sizeof(veth), iter); if (ret != sizeof(veth) || !iov_iter_count(iter)) goto done; } skb_copy_datagram_iter(skb, vlan_offset, iter, skb->len - vlan_offset); done: /* caller is in process context, */ preempt_disable(); dev_sw_netstats_tx_add(tun->dev, 1, skb->len + vlan_hlen); preempt_enable(); return total; } static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err) { DECLARE_WAITQUEUE(wait, current); void *ptr = NULL; int error = 0; ptr = ptr_ring_consume(&tfile->tx_ring); if (ptr) goto out; if (noblock) { error = -EAGAIN; goto out; } add_wait_queue(&tfile->socket.wq.wait, &wait); while (1) { set_current_state(TASK_INTERRUPTIBLE); ptr = ptr_ring_consume(&tfile->tx_ring); if (ptr) break; if (signal_pending(current)) { error = -ERESTARTSYS; break; } if (tfile->socket.sk->sk_shutdown & RCV_SHUTDOWN) { error = -EFAULT; break; } schedule(); } __set_current_state(TASK_RUNNING); remove_wait_queue(&tfile->socket.wq.wait, &wait); out: *err = error; return ptr; } static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *to, int noblock, void *ptr) { ssize_t ret; int err; if (!iov_iter_count(to)) { tun_ptr_free(ptr); return 0; } if (!ptr) { /* Read frames from ring */ ptr = tun_ring_recv(tfile, noblock, &err); if (!ptr) return err; } if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); ret = tun_put_user_xdp(tun, tfile, xdpf, to); xdp_return_frame(xdpf); } else { struct sk_buff *skb = ptr; ret = tun_put_user(tun, tfile, skb, to); if (unlikely(ret < 0)) kfree_skb(skb); else consume_skb(skb); } return ret; } static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t len = iov_iter_count(to), ret; int noblock = 0; if (!tun) return -EBADFD; if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) noblock = 1; ret = tun_do_read(tun, tfile, to, noblock, NULL); ret = min_t(ssize_t, ret, len); if (ret > 0) iocb->ki_pos = ret; tun_put(tun); return ret; } static void tun_prog_free(struct rcu_head *rcu) { struct tun_prog *prog = container_of(rcu, struct tun_prog, rcu); bpf_prog_destroy(prog->prog); kfree(prog); } static int __tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, struct bpf_prog *prog) { struct tun_prog *old, *new = NULL; if (prog) { new = kmalloc(sizeof(*new), GFP_KERNEL); if (!new) return -ENOMEM; new->prog = prog; } spin_lock_bh(&tun->lock); old = rcu_dereference_protected(*prog_p, lockdep_is_held(&tun->lock)); rcu_assign_pointer(*prog_p, new); spin_unlock_bh(&tun->lock); if (old) call_rcu(&old->rcu, tun_prog_free); return 0; } static void tun_free_netdev(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); BUG_ON(!(list_empty(&tun->disabled))); tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); __tun_set_ebpf(tun, &tun->steering_prog, NULL); __tun_set_ebpf(tun, &tun->filter_prog, NULL); } static void tun_setup(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); tun->owner = INVALID_UID; tun->group = INVALID_GID; tun_default_link_ksettings(dev, &tun->link_ksettings); dev->ethtool_ops = &tun_ethtool_ops; dev->needs_free_netdev = true; dev->priv_destructor = tun_free_netdev; /* We prefer our own queue length */ dev->tx_queue_len = TUN_READQ_SIZE; } /* Trivial set of netlink ops to allow deleting tun or tap * device with netlink. */ static int tun_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "tun/tap creation via rtnetlink is not supported."); return -EOPNOTSUPP; } static size_t tun_get_size(const struct net_device *dev) { BUILD_BUG_ON(sizeof(u32) != sizeof(uid_t)); BUILD_BUG_ON(sizeof(u32) != sizeof(gid_t)); return nla_total_size(sizeof(uid_t)) + /* OWNER */ nla_total_size(sizeof(gid_t)) + /* GROUP */ nla_total_size(sizeof(u8)) + /* TYPE */ nla_total_size(sizeof(u8)) + /* PI */ nla_total_size(sizeof(u8)) + /* VNET_HDR */ nla_total_size(sizeof(u8)) + /* PERSIST */ nla_total_size(sizeof(u8)) + /* MULTI_QUEUE */ nla_total_size(sizeof(u32)) + /* NUM_QUEUES */ nla_total_size(sizeof(u32)) + /* NUM_DISABLED_QUEUES */ 0; } static int tun_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); if (nla_put_u8(skb, IFLA_TUN_TYPE, tun->flags & TUN_TYPE_MASK)) goto nla_put_failure; if (uid_valid(tun->owner) && nla_put_u32(skb, IFLA_TUN_OWNER, from_kuid_munged(current_user_ns(), tun->owner))) goto nla_put_failure; if (gid_valid(tun->group) && nla_put_u32(skb, IFLA_TUN_GROUP, from_kgid_munged(current_user_ns(), tun->group))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_PI, !(tun->flags & IFF_NO_PI))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_VNET_HDR, !!(tun->flags & IFF_VNET_HDR))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_PERSIST, !!(tun->flags & IFF_PERSIST))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_MULTI_QUEUE, !!(tun->flags & IFF_MULTI_QUEUE))) goto nla_put_failure; if (tun->flags & IFF_MULTI_QUEUE) { if (nla_put_u32(skb, IFLA_TUN_NUM_QUEUES, tun->numqueues)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_TUN_NUM_DISABLED_QUEUES, tun->numdisabled)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops tun_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct tun_struct), .setup = tun_setup, .validate = tun_validate, .get_size = tun_get_size, .fill_info = tun_fill_info, }; static void tun_sock_write_space(struct sock *sk) { struct tun_file *tfile; wait_queue_head_t *wqueue; if (!sock_writeable(sk)) return; if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; wqueue = sk_sleep(sk); if (wqueue && waitqueue_active(wqueue)) wake_up_interruptible_sync_poll(wqueue, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); tfile = container_of(sk, struct tun_file, sk); kill_fasync(&tfile->fasync, SIGIO, POLL_OUT); } static void tun_put_page(struct tun_page *tpage) { if (tpage->page) __page_frag_cache_drain(tpage->page, tpage->count); } static int tun_xdp_one(struct tun_struct *tun, struct tun_file *tfile, struct xdp_buff *xdp, int *flush, struct tun_page *tpage) { unsigned int datasize = xdp->data_end - xdp->data; struct tun_xdp_hdr *hdr = xdp->data_hard_start; struct virtio_net_hdr *gso = &hdr->gso; struct bpf_prog *xdp_prog; struct sk_buff *skb = NULL; struct sk_buff_head *queue; u32 rxhash = 0, act; int buflen = hdr->buflen; int metasize = 0; int ret = 0; bool skb_xdp = false; struct page *page; if (unlikely(datasize < ETH_HLEN)) return -EINVAL; xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { if (gso->gso_type) { skb_xdp = true; goto build; } xdp_init_buff(xdp, buflen, &tfile->xdp_rxq); act = bpf_prog_run_xdp(xdp_prog, xdp); ret = tun_xdp_act(tun, xdp_prog, xdp, act); if (ret < 0) { put_page(virt_to_head_page(xdp->data)); return ret; } switch (ret) { case XDP_REDIRECT: *flush = true; fallthrough; case XDP_TX: return 0; case XDP_PASS: break; default: page = virt_to_head_page(xdp->data); if (tpage->page == page) { ++tpage->count; } else { tun_put_page(tpage); tpage->page = page; tpage->count = 1; } return 0; } } build: skb = build_skb(xdp->data_hard_start, buflen); if (!skb) { ret = -ENOMEM; goto out; } skb_reserve(skb, xdp->data - xdp->data_hard_start); skb_put(skb, xdp->data_end - xdp->data); /* The externally provided xdp_buff may have no metadata support, which * is marked by xdp->data_meta being xdp->data + 1. This will lead to a * metasize of -1 and is the reason why the condition checks for > 0. */ metasize = xdp->data - xdp->data_meta; if (metasize > 0) skb_metadata_set(skb, metasize); if (tun_vnet_hdr_to_skb(tun->flags, skb, gso)) { atomic_long_inc(&tun->rx_frame_errors); kfree_skb(skb); ret = -EINVAL; goto out; } skb->protocol = eth_type_trans(skb, tun->dev); skb_reset_network_header(skb); skb_probe_transport_header(skb); skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { ret = 0; goto out; } } if (!rcu_dereference(tun->steering_prog) && tun->numqueues > 1 && !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); if (tfile->napi_enabled) { queue = &tfile->sk.sk_write_queue; spin_lock(&queue->lock); if (unlikely(tfile->detached)) { spin_unlock(&queue->lock); kfree_skb(skb); return -EBUSY; } __skb_queue_tail(queue, skb); spin_unlock(&queue->lock); ret = 1; } else { netif_receive_skb(skb); ret = 0; } /* No need to disable preemption here since this function is * always called with bh disabled */ dev_sw_netstats_rx_add(tun->dev, datasize); if (rxhash) tun_flow_update(tun, rxhash, tfile); out: return ret; } static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { int ret, i; struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); struct tun_msg_ctl *ctl = m->msg_control; struct xdp_buff *xdp; if (!tun) return -EBADFD; if (m->msg_controllen == sizeof(struct tun_msg_ctl) && ctl && ctl->type == TUN_MSG_PTR) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct tun_page tpage; int n = ctl->num; int flush = 0, queued = 0; memset(&tpage, 0, sizeof(tpage)); local_bh_disable(); rcu_read_lock(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); for (i = 0; i < n; i++) { xdp = &((struct xdp_buff *)ctl->ptr)[i]; ret = tun_xdp_one(tun, tfile, xdp, &flush, &tpage); if (ret > 0) queued += ret; } if (flush) xdp_do_flush(); if (tfile->napi_enabled && queued > 0) napi_schedule(&tfile->napi); bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); tun_put_page(&tpage); ret = total_len; goto out; } ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter, m->msg_flags & MSG_DONTWAIT, m->msg_flags & MSG_MORE); out: tun_put(tun); return ret; } static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len, int flags) { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); void *ptr = m->msg_control; int ret; if (!tun) { ret = -EBADFD; goto out_free; } if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) { ret = -EINVAL; goto out_put_tun; } if (flags & MSG_ERRQUEUE) { ret = sock_recv_errqueue(sock->sk, m, total_len, SOL_PACKET, TUN_TX_TIMESTAMP); goto out; } ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, ptr); if (ret > (ssize_t)total_len) { m->msg_flags |= MSG_TRUNC; ret = flags & MSG_TRUNC ? ret : total_len; } out: tun_put(tun); return ret; out_put_tun: tun_put(tun); out_free: tun_ptr_free(ptr); return ret; } static int tun_ptr_peek_len(void *ptr) { if (likely(ptr)) { if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); return xdpf->len; } return __skb_array_len_with_tag(ptr); } else { return 0; } } static int tun_peek_len(struct socket *sock) { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun; int ret = 0; tun = tun_get(tfile); if (!tun) return 0; ret = PTR_RING_PEEK_CALL(&tfile->tx_ring, tun_ptr_peek_len); tun_put(tun); return ret; } /* Ops structure to mimic raw sockets with tun */ static const struct proto_ops tun_socket_ops = { .peek_len = tun_peek_len, .sendmsg = tun_sendmsg, .recvmsg = tun_recvmsg, }; static struct proto tun_proto = { .name = "tun", .owner = THIS_MODULE, .obj_size = sizeof(struct tun_file), }; static int tun_flags(struct tun_struct *tun) { return tun->flags & (TUN_FEATURES | IFF_PERSIST | IFF_TUN | IFF_TAP); } static ssize_t tun_flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return sysfs_emit(buf, "0x%x\n", tun_flags(tun)); } static ssize_t owner_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return uid_valid(tun->owner)? sysfs_emit(buf, "%u\n", from_kuid_munged(current_user_ns(), tun->owner)) : sysfs_emit(buf, "-1\n"); } static ssize_t group_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return gid_valid(tun->group) ? sysfs_emit(buf, "%u\n", from_kgid_munged(current_user_ns(), tun->group)) : sysfs_emit(buf, "-1\n"); } static DEVICE_ATTR_RO(tun_flags); static DEVICE_ATTR_RO(owner); static DEVICE_ATTR_RO(group); static struct attribute *tun_dev_attrs[] = { &dev_attr_tun_flags.attr, &dev_attr_owner.attr, &dev_attr_group.attr, NULL }; static const struct attribute_group tun_attr_group = { .attrs = tun_dev_attrs }; static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) { struct tun_struct *tun; struct tun_file *tfile = file->private_data; struct net_device *dev; int err; if (tfile->detached) return -EINVAL; if ((ifr->ifr_flags & IFF_NAPI_FRAGS)) { if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!(ifr->ifr_flags & IFF_NAPI) || (ifr->ifr_flags & TUN_TYPE_MASK) != IFF_TAP) return -EINVAL; } dev = __dev_get_by_name(net, ifr->ifr_name); if (dev) { if (ifr->ifr_flags & IFF_TUN_EXCL) return -EBUSY; if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops) tun = netdev_priv(dev); else if ((ifr->ifr_flags & IFF_TAP) && dev->netdev_ops == &tap_netdev_ops) tun = netdev_priv(dev); else return -EINVAL; if (!!(ifr->ifr_flags & IFF_MULTI_QUEUE) != !!(tun->flags & IFF_MULTI_QUEUE)) return -EINVAL; if (tun_not_capable(tun)) return -EPERM; err = security_tun_dev_open(tun->security); if (err < 0) return err; err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER, ifr->ifr_flags & IFF_NAPI, ifr->ifr_flags & IFF_NAPI_FRAGS, true); if (err < 0) return err; if (tun->flags & IFF_MULTI_QUEUE && (tun->numqueues + tun->numdisabled > 1)) { /* One or more queue has already been attached, no need * to initialize the device again. */ netdev_state_change(dev); return 0; } tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); netdev_state_change(dev); } else { char *name; unsigned long flags = 0; int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; err = security_tun_dev_create(); if (err < 0) return err; /* Set dev type */ if (ifr->ifr_flags & IFF_TUN) { /* TUN device */ flags |= IFF_TUN; name = "tun%d"; } else if (ifr->ifr_flags & IFF_TAP) { /* TAP device */ flags |= IFF_TAP; name = "tap%d"; } else return -EINVAL; if (*ifr->ifr_name) name = ifr->ifr_name; dev = alloc_netdev_mqs(sizeof(struct tun_struct), name, NET_NAME_UNKNOWN, tun_setup, queues, queues); if (!dev) return -ENOMEM; dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; dev->ifindex = tfile->ifindex; dev->sysfs_groups[0] = &tun_attr_group; tun = netdev_priv(dev); tun->dev = dev; tun->flags = flags; tun->txflt.count = 0; tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr); tun->align = NET_SKB_PAD; tun->filter_attached = false; tun->sndbuf = tfile->socket.sk->sk_sndbuf; tun->rx_batched = 0; RCU_INIT_POINTER(tun->steering_prog, NULL); tun->ifr = ifr; tun->file = file; tun_net_initialize(dev); err = register_netdevice(tun->dev); if (err < 0) { free_netdev(dev); return err; } /* free_netdev() won't check refcnt, to avoid race * with dev_put() we need publish tun after registration. */ rcu_assign_pointer(tfile->tun, tun); } if (ifr->ifr_flags & IFF_NO_CARRIER) netif_carrier_off(tun->dev); else netif_carrier_on(tun->dev); /* Make sure persistent devices do not get stuck in * xoff state. */ if (netif_running(tun->dev)) netif_tx_wake_all_queues(tun->dev); strcpy(ifr->ifr_name, tun->dev->name); return 0; } static void tun_get_iff(struct tun_struct *tun, struct ifreq *ifr) { strcpy(ifr->ifr_name, tun->dev->name); ifr->ifr_flags = tun_flags(tun); } /* This is like a cut-down ethtool ops, except done via tun fd so no * privs required. */ static int set_offload(struct tun_struct *tun, unsigned long arg) { netdev_features_t features = 0; if (arg & TUN_F_CSUM) { features |= NETIF_F_HW_CSUM; arg &= ~TUN_F_CSUM; if (arg & (TUN_F_TSO4|TUN_F_TSO6)) { if (arg & TUN_F_TSO_ECN) { features |= NETIF_F_TSO_ECN; arg &= ~TUN_F_TSO_ECN; } if (arg & TUN_F_TSO4) features |= NETIF_F_TSO; if (arg & TUN_F_TSO6) features |= NETIF_F_TSO6; arg &= ~(TUN_F_TSO4|TUN_F_TSO6); } arg &= ~TUN_F_UFO; /* TODO: for now USO4 and USO6 should work simultaneously */ if (arg & TUN_F_USO4 && arg & TUN_F_USO6) { features |= NETIF_F_GSO_UDP_L4; arg &= ~(TUN_F_USO4 | TUN_F_USO6); } } /* This gives the user a way to test for new features in future by * trying to set them. */ if (arg) return -EINVAL; tun->set_features = features; tun->dev->wanted_features &= ~TUN_USER_FEATURES; tun->dev->wanted_features |= features; netdev_update_features(tun->dev); return 0; } static void tun_detach_filter(struct tun_struct *tun, int n) { int i; struct tun_file *tfile; for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); lock_sock(tfile->socket.sk); sk_detach_filter(tfile->socket.sk); release_sock(tfile->socket.sk); } tun->filter_attached = false; } static int tun_attach_filter(struct tun_struct *tun) { int i, ret = 0; struct tun_file *tfile; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); lock_sock(tfile->socket.sk); ret = sk_attach_filter(&tun->fprog, tfile->socket.sk); release_sock(tfile->socket.sk); if (ret) { tun_detach_filter(tun, i); return ret; } } tun->filter_attached = true; return ret; } static void tun_set_sndbuf(struct tun_struct *tun) { struct tun_file *tfile; int i; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); tfile->socket.sk->sk_sndbuf = tun->sndbuf; } } static int tun_set_queue(struct file *file, struct ifreq *ifr) { struct tun_file *tfile = file->private_data; struct tun_struct *tun; int ret = 0; rtnl_lock(); if (ifr->ifr_flags & IFF_ATTACH_QUEUE) { tun = tfile->detached; if (!tun) { ret = -EINVAL; goto unlock; } ret = security_tun_dev_attach_queue(tun->security); if (ret < 0) goto unlock; ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI, tun->flags & IFF_NAPI_FRAGS, true); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached) ret = -EINVAL; else __tun_detach(tfile, false); } else ret = -EINVAL; if (ret >= 0) netdev_state_change(tun->dev); unlock: rtnl_unlock(); return ret; } static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, void __user *data) { struct bpf_prog *prog; int fd; if (copy_from_user(&fd, data, sizeof(fd))) return -EFAULT; if (fd == -1) { prog = NULL; } else { prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(prog)) return PTR_ERR(prog); } return __tun_set_ebpf(tun, prog_p, prog); } /* Return correct value for tun->dev->addr_len based on tun->dev->type. */ static unsigned char tun_get_addr_len(unsigned short type) { switch (type) { case ARPHRD_IP6GRE: case ARPHRD_TUNNEL6: return sizeof(struct in6_addr); case ARPHRD_IPGRE: case ARPHRD_TUNNEL: case ARPHRD_SIT: return 4; case ARPHRD_ETHER: return ETH_ALEN; case ARPHRD_IEEE802154: case ARPHRD_IEEE802154_MONITOR: return IEEE802154_EXTENDED_ADDR_LEN; case ARPHRD_PHONET_PIPE: case ARPHRD_PPP: case ARPHRD_NONE: return 0; case ARPHRD_6LOWPAN: return EUI64_ADDR_LEN; case ARPHRD_FDDI: return FDDI_K_ALEN; case ARPHRD_HIPPI: return HIPPI_ALEN; case ARPHRD_IEEE802: return FC_ALEN; case ARPHRD_ROSE: return ROSE_ADDR_LEN; case ARPHRD_NETROM: return AX25_ADDR_LEN; case ARPHRD_LOCALTLK: return LTALK_ALEN; default: return 0; } } static long __tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg, int ifreq_len) { struct tun_file *tfile = file->private_data; struct net *net = sock_net(&tfile->sk); struct tun_struct *tun; void __user* argp = (void __user*)arg; unsigned int carrier; struct ifreq ifr; kuid_t owner; kgid_t group; int ifindex; int sndbuf; int ret; bool do_notify = false; if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || (_IOC_TYPE(cmd) == SOCK_IOC_TYPE && cmd != SIOCGSKNS)) { if (copy_from_user(&ifr, argp, ifreq_len)) return -EFAULT; } else { memset(&ifr, 0, sizeof(ifr)); } if (cmd == TUNGETFEATURES) { /* Currently this just means: "what IFF flags are valid?". * This is needed because we never checked for invalid flags on * TUNSETIFF. */ return put_user(IFF_TUN | IFF_TAP | IFF_NO_CARRIER | TUN_FEATURES, (unsigned int __user*)argp); } else if (cmd == TUNSETQUEUE) { return tun_set_queue(file, &ifr); } else if (cmd == SIOCGSKNS) { if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; return open_related_ns(&net->ns, get_net_ns); } rtnl_lock(); tun = tun_get(tfile); if (cmd == TUNSETIFF) { ret = -EEXIST; if (tun) goto unlock; ifr.ifr_name[IFNAMSIZ-1] = '\0'; ret = tun_set_iff(net, file, &ifr); if (ret) goto unlock; if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; goto unlock; } if (cmd == TUNSETIFINDEX) { ret = -EPERM; if (tun) goto unlock; ret = -EFAULT; if (copy_from_user(&ifindex, argp, sizeof(ifindex))) goto unlock; ret = -EINVAL; if (ifindex < 0) goto unlock; ret = 0; tfile->ifindex = ifindex; goto unlock; } ret = -EBADFD; if (!tun) goto unlock; netif_info(tun, drv, tun->dev, "tun_chr_ioctl cmd %u\n", cmd); net = dev_net(tun->dev); ret = 0; switch (cmd) { case TUNGETIFF: tun_get_iff(tun, &ifr); if (tfile->detached) ifr.ifr_flags |= IFF_DETACH_QUEUE; if (!tfile->socket.sk->sk_filter) ifr.ifr_flags |= IFF_NOFILTER; if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; case TUNSETNOCSUM: /* Disable/Enable checksum */ /* [unimplemented] */ netif_info(tun, drv, tun->dev, "ignored: set checksum %s\n", arg ? "disabled" : "enabled"); break; case TUNSETPERSIST: /* Disable/Enable persist mode. Keep an extra reference to the * module to prevent the module being unprobed. */ if (arg && !(tun->flags & IFF_PERSIST)) { tun->flags |= IFF_PERSIST; __module_get(THIS_MODULE); do_notify = true; } if (!arg && (tun->flags & IFF_PERSIST)) { tun->flags &= ~IFF_PERSIST; module_put(THIS_MODULE); do_notify = true; } netif_info(tun, drv, tun->dev, "persist %s\n", arg ? "enabled" : "disabled"); break; case TUNSETOWNER: /* Set owner of the device */ owner = make_kuid(current_user_ns(), arg); if (!uid_valid(owner)) { ret = -EINVAL; break; } tun->owner = owner; do_notify = true; netif_info(tun, drv, tun->dev, "owner set to %u\n", from_kuid(&init_user_ns, tun->owner)); break; case TUNSETGROUP: /* Set group of the device */ group = make_kgid(current_user_ns(), arg); if (!gid_valid(group)) { ret = -EINVAL; break; } tun->group = group; do_notify = true; netif_info(tun, drv, tun->dev, "group set to %u\n", from_kgid(&init_user_ns, tun->group)); break; case TUNSETLINK: /* Only allow setting the type when the interface is down */ if (tun->dev->flags & IFF_UP) { netif_info(tun, drv, tun->dev, "Linktype set failed because interface is up\n"); ret = -EBUSY; } else { ret = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, tun->dev); ret = notifier_to_errno(ret); if (ret) { netif_info(tun, drv, tun->dev, "Refused to change device type\n"); break; } tun->dev->type = (int) arg; tun->dev->addr_len = tun_get_addr_len(tun->dev->type); netif_info(tun, drv, tun->dev, "linktype set to %d\n", tun->dev->type); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, tun->dev); } break; case TUNSETDEBUG: tun->msg_enable = (u32)arg; break; case TUNSETOFFLOAD: ret = set_offload(tun, arg); break; case TUNSETTXFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = update_filter(&tun->txflt, (void __user *)arg); break; case SIOCGIFHWADDR: /* Get hw address */ dev_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name); if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; case SIOCSIFHWADDR: /* Set hw address */ ret = dev_set_mac_address_user(tun->dev, &ifr.ifr_hwaddr, NULL); break; case TUNGETSNDBUF: sndbuf = tfile->socket.sk->sk_sndbuf; if (copy_to_user(argp, &sndbuf, sizeof(sndbuf))) ret = -EFAULT; break; case TUNSETSNDBUF: if (copy_from_user(&sndbuf, argp, sizeof(sndbuf))) { ret = -EFAULT; break; } if (sndbuf <= 0) { ret = -EINVAL; break; } tun->sndbuf = sndbuf; tun_set_sndbuf(tun); break; case TUNATTACHFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = -EFAULT; if (copy_from_user(&tun->fprog, argp, sizeof(tun->fprog))) break; ret = tun_attach_filter(tun); break; case TUNDETACHFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = 0; tun_detach_filter(tun, tun->numqueues); break; case TUNGETFILTER: ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = -EFAULT; if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog))) break; ret = 0; break; case TUNSETSTEERINGEBPF: ret = tun_set_ebpf(tun, &tun->steering_prog, argp); break; case TUNSETFILTEREBPF: ret = tun_set_ebpf(tun, &tun->filter_prog, argp); break; case TUNSETCARRIER: ret = -EFAULT; if (copy_from_user(&carrier, argp, sizeof(carrier))) goto unlock; ret = tun_net_change_carrier(tun->dev, (bool)carrier); break; case TUNGETDEVNETNS: ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto unlock; ret = open_related_ns(&net->ns, get_net_ns); break; default: ret = tun_vnet_ioctl(&tun->vnet_hdr_sz, &tun->flags, cmd, argp); break; } if (do_notify) netdev_state_change(tun->dev); unlock: rtnl_unlock(); if (tun) tun_put(tun); return ret; } static long tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return __tun_chr_ioctl(file, cmd, arg, sizeof (struct ifreq)); } #ifdef CONFIG_COMPAT static long tun_chr_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { switch (cmd) { case TUNSETIFF: case TUNGETIFF: case TUNSETTXFILTER: case TUNGETSNDBUF: case TUNSETSNDBUF: case SIOCGIFHWADDR: case SIOCSIFHWADDR: arg = (unsigned long)compat_ptr(arg); break; default: arg = (compat_ulong_t)arg; break; } /* * compat_ifreq is shorter than ifreq, so we must not access beyond * the end of that structure. All fields that are used in this * driver are compatible though, we don't need to convert the * contents. */ return __tun_chr_ioctl(file, cmd, arg, sizeof(struct compat_ifreq)); } #endif /* CONFIG_COMPAT */ static int tun_chr_fasync(int fd, struct file *file, int on) { struct tun_file *tfile = file->private_data; int ret; if (on) { ret = file_f_owner_allocate(file); if (ret) goto out; } if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0) goto out; if (on) { __f_setown(file, task_pid(current), PIDTYPE_TGID, 0); tfile->flags |= TUN_FASYNC; } else tfile->flags &= ~TUN_FASYNC; ret = 0; out: return ret; } static int tun_chr_open(struct inode *inode, struct file * file) { struct net *net = current->nsproxy->net_ns; struct tun_file *tfile; tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL, &tun_proto, 0); if (!tfile) return -ENOMEM; if (ptr_ring_init(&tfile->tx_ring, 0, GFP_KERNEL)) { sk_free(&tfile->sk); return -ENOMEM; } mutex_init(&tfile->napi_mutex); RCU_INIT_POINTER(tfile->tun, NULL); tfile->flags = 0; tfile->ifindex = 0; init_waitqueue_head(&tfile->socket.wq.wait); tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; sock_init_data_uid(&tfile->socket, &tfile->sk, current_fsuid()); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; file->private_data = tfile; INIT_LIST_HEAD(&tfile->next); sock_set_flag(&tfile->sk, SOCK_ZEROCOPY); /* tun groks IOCB_NOWAIT just fine, mark it as such */ file->f_mode |= FMODE_NOWAIT; return 0; } static int tun_chr_close(struct inode *inode, struct file *file) { struct tun_file *tfile = file->private_data; tun_detach(tfile, true); return 0; } #ifdef CONFIG_PROC_FS static void tun_chr_show_fdinfo(struct seq_file *m, struct file *file) { struct tun_file *tfile = file->private_data; struct tun_struct *tun; struct ifreq ifr; memset(&ifr, 0, sizeof(ifr)); rtnl_lock(); tun = tun_get(tfile); if (tun) tun_get_iff(tun, &ifr); rtnl_unlock(); if (tun) tun_put(tun); seq_printf(m, "iff:\t%s\n", ifr.ifr_name); } #endif static const struct file_operations tun_fops = { .owner = THIS_MODULE, .read_iter = tun_chr_read_iter, .write_iter = tun_chr_write_iter, .poll = tun_chr_poll, .unlocked_ioctl = tun_chr_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = tun_chr_compat_ioctl, #endif .open = tun_chr_open, .release = tun_chr_close, .fasync = tun_chr_fasync, #ifdef CONFIG_PROC_FS .show_fdinfo = tun_chr_show_fdinfo, #endif }; static struct miscdevice tun_miscdev = { .minor = TUN_MINOR, .name = "tun", .nodename = "net/tun", .fops = &tun_fops, }; /* ethtool interface */ static void tun_default_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { ethtool_link_ksettings_zero_link_mode(cmd, supported); ethtool_link_ksettings_zero_link_mode(cmd, advertising); cmd->base.speed = SPEED_10000; cmd->base.duplex = DUPLEX_FULL; cmd->base.port = PORT_TP; cmd->base.phy_address = 0; cmd->base.autoneg = AUTONEG_DISABLE; } static int tun_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct tun_struct *tun = netdev_priv(dev); memcpy(cmd, &tun->link_ksettings, sizeof(*cmd)); return 0; } static int tun_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct tun_struct *tun = netdev_priv(dev); memcpy(&tun->link_ksettings, cmd, sizeof(*cmd)); return 0; } static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct tun_struct *tun = netdev_priv(dev); strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->version, DRV_VERSION, sizeof(info->version)); switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: strscpy(info->bus_info, "tun", sizeof(info->bus_info)); break; case IFF_TAP: strscpy(info->bus_info, "tap", sizeof(info->bus_info)); break; } } static u32 tun_get_msglevel(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); return tun->msg_enable; } static void tun_set_msglevel(struct net_device *dev, u32 value) { struct tun_struct *tun = netdev_priv(dev); tun->msg_enable = value; } static int tun_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); ec->rx_max_coalesced_frames = tun->rx_batched; return 0; } static int tun_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); if (ec->rx_max_coalesced_frames > NAPI_POLL_WEIGHT) tun->rx_batched = NAPI_POLL_WEIGHT; else tun->rx_batched = ec->rx_max_coalesced_frames; return 0; } static void tun_get_channels(struct net_device *dev, struct ethtool_channels *channels) { struct tun_struct *tun = netdev_priv(dev); channels->combined_count = tun->numqueues; channels->max_combined = tun->flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1; } static const struct ethtool_ops tun_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_RX_MAX_FRAMES, .get_drvinfo = tun_get_drvinfo, .get_msglevel = tun_get_msglevel, .set_msglevel = tun_set_msglevel, .get_link = ethtool_op_get_link, .get_channels = tun_get_channels, .get_ts_info = ethtool_op_get_ts_info, .get_coalesce = tun_get_coalesce, .set_coalesce = tun_set_coalesce, .get_link_ksettings = tun_get_link_ksettings, .set_link_ksettings = tun_set_link_ksettings, }; static int tun_queue_resize(struct tun_struct *tun) { struct net_device *dev = tun->dev; struct tun_file *tfile; struct ptr_ring **rings; int n = tun->numqueues + tun->numdisabled; int ret, i; rings = kmalloc_array(n, sizeof(*rings), GFP_KERNEL); if (!rings) return -ENOMEM; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); rings[i] = &tfile->tx_ring; } list_for_each_entry(tfile, &tun->disabled, next) rings[i++] = &tfile->tx_ring; ret = ptr_ring_resize_multiple_bh(rings, n, dev->tx_queue_len, GFP_KERNEL, tun_ptr_free); kfree(rings); return ret; } static int tun_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tun_struct *tun = netdev_priv(dev); int i; if (dev->rtnl_link_ops != &tun_link_ops) return NOTIFY_DONE; switch (event) { case NETDEV_CHANGE_TX_QUEUE_LEN: if (tun_queue_resize(tun)) return NOTIFY_BAD; break; case NETDEV_UP: for (i = 0; i < tun->numqueues; i++) { struct tun_file *tfile; tfile = rtnl_dereference(tun->tfiles[i]); tfile->socket.sk->sk_write_space(tfile->socket.sk); } break; default: break; } return NOTIFY_DONE; } static struct notifier_block tun_notifier_block __read_mostly = { .notifier_call = tun_device_event, }; static int __init tun_init(void) { int ret = 0; pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION); ret = rtnl_link_register(&tun_link_ops); if (ret) { pr_err("Can't register link_ops\n"); goto err_linkops; } ret = misc_register(&tun_miscdev); if (ret) { pr_err("Can't register misc device %d\n", TUN_MINOR); goto err_misc; } ret = register_netdevice_notifier(&tun_notifier_block); if (ret) { pr_err("Can't register netdevice notifier\n"); goto err_notifier; } return 0; err_notifier: misc_deregister(&tun_miscdev); err_misc: rtnl_link_unregister(&tun_link_ops); err_linkops: return ret; } static void __exit tun_cleanup(void) { misc_deregister(&tun_miscdev); rtnl_link_unregister(&tun_link_ops); unregister_netdevice_notifier(&tun_notifier_block); } /* Get an underlying socket object from tun file. Returns error unless file is * attached to a device. The returned object works like a packet socket, it * can be used for sock_sendmsg/sock_recvmsg. The caller is responsible for * holding a reference to the file for as long as the socket is in use. */ struct socket *tun_get_socket(struct file *file) { struct tun_file *tfile; if (file->f_op != &tun_fops) return ERR_PTR(-EINVAL); tfile = file->private_data; if (!tfile) return ERR_PTR(-EBADFD); return &tfile->socket; } EXPORT_SYMBOL_GPL(tun_get_socket); struct ptr_ring *tun_get_tx_ring(struct file *file) { struct tun_file *tfile; if (file->f_op != &tun_fops) return ERR_PTR(-EINVAL); tfile = file->private_data; if (!tfile) return ERR_PTR(-EBADFD); return &tfile->tx_ring; } EXPORT_SYMBOL_GPL(tun_get_tx_ring); module_init(tun_init); module_exit(tun_cleanup); MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR(DRV_COPYRIGHT); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(TUN_MINOR); MODULE_ALIAS("devname:net/tun"); |
| 106 62 62 61 61 62 59 15 143 144 141 3 64 64 64 64 63 4 4 90 78 63 2 31 106 106 103 15 29 87 106 94 106 12 105 94 12 10 10 10 106 107 106 1 106 106 106 106 107 107 186 186 64 57 1 1 63 32 63 156 100 23 2 133 2 2 1 5 28 28 8 5 4 9 5 4 5 4 8 7 4 4 4 7 8 8 8 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 80 80 75 5 5 5 5 5 182 183 183 183 183 90 185 172 5 8 185 172 172 5 8 90 90 185 | 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * bcachefs journalling code, for btree insertions * * Copyright 2012 Google, Inc. */ #include "bcachefs.h" #include "alloc_foreground.h" #include "bkey_methods.h" #include "btree_gc.h" #include "btree_update.h" #include "btree_write_buffer.h" #include "buckets.h" #include "error.h" #include "journal.h" #include "journal_io.h" #include "journal_reclaim.h" #include "journal_sb.h" #include "journal_seq_blacklist.h" #include "trace.h" static inline bool journal_seq_unwritten(struct journal *j, u64 seq) { return seq > j->seq_ondisk; } static bool __journal_entry_is_open(union journal_res_state state) { return state.cur_entry_offset < JOURNAL_ENTRY_CLOSED_VAL; } static inline unsigned nr_unwritten_journal_entries(struct journal *j) { return atomic64_read(&j->seq) - j->seq_ondisk; } static bool journal_entry_is_open(struct journal *j) { return __journal_entry_is_open(j->reservations); } static void bch2_journal_buf_to_text(struct printbuf *out, struct journal *j, u64 seq) { union journal_res_state s = READ_ONCE(j->reservations); unsigned i = seq & JOURNAL_BUF_MASK; struct journal_buf *buf = j->buf + i; prt_printf(out, "seq:\t%llu\n", seq); printbuf_indent_add(out, 2); if (!buf->write_started) prt_printf(out, "refcount:\t%u\n", journal_state_count(s, i & JOURNAL_STATE_BUF_MASK)); struct closure *cl = &buf->io; int r = atomic_read(&cl->remaining); prt_printf(out, "io:\t%pS r %i\n", cl->fn, r & CLOSURE_REMAINING_MASK); if (buf->data) { prt_printf(out, "size:\t"); prt_human_readable_u64(out, vstruct_bytes(buf->data)); prt_newline(out); } prt_printf(out, "expires:\t"); prt_printf(out, "%li jiffies\n", buf->expires - jiffies); prt_printf(out, "flags:\t"); if (buf->noflush) prt_str(out, "noflush "); if (buf->must_flush) prt_str(out, "must_flush "); if (buf->separate_flush) prt_str(out, "separate_flush "); if (buf->need_flush_to_write_buffer) prt_str(out, "need_flush_to_write_buffer "); if (buf->write_started) prt_str(out, "write_started "); if (buf->write_allocated) prt_str(out, "write_allocated "); if (buf->write_done) prt_str(out, "write_done"); prt_newline(out); printbuf_indent_sub(out, 2); } static void bch2_journal_bufs_to_text(struct printbuf *out, struct journal *j) { lockdep_assert_held(&j->lock); out->atomic++; if (!out->nr_tabstops) printbuf_tabstop_push(out, 24); for (u64 seq = journal_last_unwritten_seq(j); seq <= journal_cur_seq(j); seq++) bch2_journal_buf_to_text(out, j, seq); prt_printf(out, "last buf %s\n", journal_entry_is_open(j) ? "open" : "closed"); --out->atomic; } static inline struct journal_buf * journal_seq_to_buf(struct journal *j, u64 seq) { struct journal_buf *buf = NULL; EBUG_ON(seq > journal_cur_seq(j)); if (journal_seq_unwritten(j, seq)) buf = j->buf + (seq & JOURNAL_BUF_MASK); return buf; } static void journal_pin_list_init(struct journal_entry_pin_list *p, int count) { for (unsigned i = 0; i < ARRAY_SIZE(p->unflushed); i++) INIT_LIST_HEAD(&p->unflushed[i]); for (unsigned i = 0; i < ARRAY_SIZE(p->flushed); i++) INIT_LIST_HEAD(&p->flushed[i]); atomic_set(&p->count, count); p->devs.nr = 0; } /* * Detect stuck journal conditions and trigger shutdown. Technically the journal * can end up stuck for a variety of reasons, such as a blocked I/O, journal * reservation lockup, etc. Since this is a fatal error with potentially * unpredictable characteristics, we want to be fairly conservative before we * decide to shut things down. * * Consider the journal stuck when it appears full with no ability to commit * btree transactions, to discard journal buckets, nor acquire priority * (reserved watermark) reservation. */ static inline bool journal_error_check_stuck(struct journal *j, int error, unsigned flags) { struct bch_fs *c = container_of(j, struct bch_fs, journal); bool stuck = false; struct printbuf buf = PRINTBUF; if (!(error == -BCH_ERR_journal_full || error == -BCH_ERR_journal_pin_full) || nr_unwritten_journal_entries(j) || (flags & BCH_WATERMARK_MASK) != BCH_WATERMARK_reclaim) return stuck; spin_lock(&j->lock); if (j->can_discard) { spin_unlock(&j->lock); return stuck; } stuck = true; /* * The journal shutdown path will set ->err_seq, but do it here first to * serialize against concurrent failures and avoid duplicate error * reports. */ if (j->err_seq) { spin_unlock(&j->lock); return stuck; } j->err_seq = journal_cur_seq(j); spin_unlock(&j->lock); bch_err(c, "Journal stuck! Hava a pre-reservation but journal full (error %s)", bch2_err_str(error)); bch2_journal_debug_to_text(&buf, j); bch_err(c, "%s", buf.buf); printbuf_reset(&buf); bch2_journal_pins_to_text(&buf, j); bch_err(c, "Journal pins:\n%s", buf.buf); printbuf_exit(&buf); bch2_fatal_error(c); dump_stack(); return stuck; } void bch2_journal_do_writes(struct journal *j) { for (u64 seq = journal_last_unwritten_seq(j); seq <= journal_cur_seq(j); seq++) { unsigned idx = seq & JOURNAL_BUF_MASK; struct journal_buf *w = j->buf + idx; if (w->write_started && !w->write_allocated) break; if (w->write_started) continue; if (!journal_state_seq_count(j, j->reservations, seq)) { j->seq_write_started = seq; w->write_started = true; closure_call(&w->io, bch2_journal_write, j->wq, NULL); } break; } } /* * Final processing when the last reference of a journal buffer has been * dropped. Drop the pin list reference acquired at journal entry open and write * the buffer, if requested. */ void bch2_journal_buf_put_final(struct journal *j, u64 seq) { lockdep_assert_held(&j->lock); if (__bch2_journal_pin_put(j, seq)) bch2_journal_reclaim_fast(j); bch2_journal_do_writes(j); /* * for __bch2_next_write_buffer_flush_journal_buf(), when quiescing an * open journal entry */ wake_up(&j->wait); } /* * Returns true if journal entry is now closed: * * We don't close a journal_buf until the next journal_buf is finished writing, * and can be opened again - this also initializes the next journal_buf: */ static void __journal_entry_close(struct journal *j, unsigned closed_val, bool trace) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct journal_buf *buf = journal_cur_buf(j); union journal_res_state old, new; unsigned sectors; BUG_ON(closed_val != JOURNAL_ENTRY_CLOSED_VAL && closed_val != JOURNAL_ENTRY_ERROR_VAL); lockdep_assert_held(&j->lock); old.v = atomic64_read(&j->reservations.counter); do { new.v = old.v; new.cur_entry_offset = closed_val; if (old.cur_entry_offset == JOURNAL_ENTRY_ERROR_VAL || old.cur_entry_offset == new.cur_entry_offset) return; } while (!atomic64_try_cmpxchg(&j->reservations.counter, &old.v, new.v)); if (!__journal_entry_is_open(old)) return; if (old.cur_entry_offset == JOURNAL_ENTRY_BLOCKED_VAL) old.cur_entry_offset = j->cur_entry_offset_if_blocked; /* Close out old buffer: */ buf->data->u64s = cpu_to_le32(old.cur_entry_offset); if (trace_journal_entry_close_enabled() && trace) { struct printbuf pbuf = PRINTBUF; pbuf.atomic++; prt_str(&pbuf, "entry size: "); prt_human_readable_u64(&pbuf, vstruct_bytes(buf->data)); prt_newline(&pbuf); bch2_prt_task_backtrace(&pbuf, current, 1, GFP_NOWAIT); trace_journal_entry_close(c, pbuf.buf); printbuf_exit(&pbuf); } sectors = vstruct_blocks_plus(buf->data, c->block_bits, buf->u64s_reserved) << c->block_bits; BUG_ON(sectors > buf->sectors); buf->sectors = sectors; /* * We have to set last_seq here, _before_ opening a new journal entry: * * A threads may replace an old pin with a new pin on their current * journal reservation - the expectation being that the journal will * contain either what the old pin protected or what the new pin * protects. * * After the old pin is dropped journal_last_seq() won't include the old * pin, so we can only write the updated last_seq on the entry that * contains whatever the new pin protects. * * Restated, we can _not_ update last_seq for a given entry if there * could be a newer entry open with reservations/pins that have been * taken against it. * * Hence, we want update/set last_seq on the current journal entry right * before we open a new one: */ buf->last_seq = journal_last_seq(j); buf->data->last_seq = cpu_to_le64(buf->last_seq); BUG_ON(buf->last_seq > le64_to_cpu(buf->data->seq)); cancel_delayed_work(&j->write_work); bch2_journal_space_available(j); __bch2_journal_buf_put(j, le64_to_cpu(buf->data->seq)); } void bch2_journal_halt(struct journal *j) { spin_lock(&j->lock); __journal_entry_close(j, JOURNAL_ENTRY_ERROR_VAL, true); if (!j->err_seq) j->err_seq = journal_cur_seq(j); journal_wake(j); spin_unlock(&j->lock); } void bch2_journal_halt_locked(struct journal *j) { lockdep_assert_held(&j->lock); __journal_entry_close(j, JOURNAL_ENTRY_ERROR_VAL, true); if (!j->err_seq) j->err_seq = journal_cur_seq(j); journal_wake(j); } static bool journal_entry_want_write(struct journal *j) { bool ret = !journal_entry_is_open(j) || journal_cur_seq(j) == journal_last_unwritten_seq(j); /* Don't close it yet if we already have a write in flight: */ if (ret) __journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true); else if (nr_unwritten_journal_entries(j)) { struct journal_buf *buf = journal_cur_buf(j); if (!buf->flush_time) { buf->flush_time = local_clock() ?: 1; buf->expires = jiffies; } } return ret; } bool bch2_journal_entry_close(struct journal *j) { bool ret; spin_lock(&j->lock); ret = journal_entry_want_write(j); spin_unlock(&j->lock); return ret; } /* * should _only_ called from journal_res_get() - when we actually want a * journal reservation - journal entry is open means journal is dirty: */ static int journal_entry_open(struct journal *j) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct journal_buf *buf = j->buf + ((journal_cur_seq(j) + 1) & JOURNAL_BUF_MASK); union journal_res_state old, new; int u64s; lockdep_assert_held(&j->lock); BUG_ON(journal_entry_is_open(j)); BUG_ON(BCH_SB_CLEAN(c->disk_sb.sb)); if (j->blocked) return -BCH_ERR_journal_blocked; if (j->cur_entry_error) return j->cur_entry_error; int ret = bch2_journal_error(j); if (unlikely(ret)) return ret; if (!fifo_free(&j->pin)) return -BCH_ERR_journal_pin_full; if (nr_unwritten_journal_entries(j) == ARRAY_SIZE(j->buf)) return -BCH_ERR_journal_max_in_flight; if (atomic64_read(&j->seq) - j->seq_write_started == JOURNAL_STATE_BUF_NR) return -BCH_ERR_journal_max_open; if (journal_cur_seq(j) >= JOURNAL_SEQ_MAX) { bch_err(c, "cannot start: journal seq overflow"); if (bch2_fs_emergency_read_only_locked(c)) bch_err(c, "fatal error - emergency read only"); return -BCH_ERR_journal_shutdown; } if (!j->free_buf && !buf->data) return -BCH_ERR_journal_buf_enomem; /* will retry after write completion frees up a buf */ BUG_ON(!j->cur_entry_sectors); if (!buf->data) { swap(buf->data, j->free_buf); swap(buf->buf_size, j->free_buf_size); } buf->expires = (journal_cur_seq(j) == j->flushed_seq_ondisk ? jiffies : j->last_flush_write) + msecs_to_jiffies(c->opts.journal_flush_delay); buf->u64s_reserved = j->entry_u64s_reserved; buf->disk_sectors = j->cur_entry_sectors; buf->sectors = min(buf->disk_sectors, buf->buf_size >> 9); u64s = (int) (buf->sectors << 9) / sizeof(u64) - journal_entry_overhead(j); u64s = clamp_t(int, u64s, 0, JOURNAL_ENTRY_CLOSED_VAL - 1); if (u64s <= (ssize_t) j->early_journal_entries.nr) return -BCH_ERR_journal_full; if (fifo_empty(&j->pin) && j->reclaim_thread) wake_up_process(j->reclaim_thread); /* * The fifo_push() needs to happen at the same time as j->seq is * incremented for journal_last_seq() to be calculated correctly */ atomic64_inc(&j->seq); journal_pin_list_init(fifo_push_ref(&j->pin), 1); BUG_ON(j->pin.back - 1 != atomic64_read(&j->seq)); BUG_ON(j->buf + (journal_cur_seq(j) & JOURNAL_BUF_MASK) != buf); bkey_extent_init(&buf->key); buf->noflush = false; buf->must_flush = false; buf->separate_flush = false; buf->flush_time = 0; buf->need_flush_to_write_buffer = true; buf->write_started = false; buf->write_allocated = false; buf->write_done = false; memset(buf->data, 0, sizeof(*buf->data)); buf->data->seq = cpu_to_le64(journal_cur_seq(j)); buf->data->u64s = 0; if (j->early_journal_entries.nr) { memcpy(buf->data->_data, j->early_journal_entries.data, j->early_journal_entries.nr * sizeof(u64)); le32_add_cpu(&buf->data->u64s, j->early_journal_entries.nr); } /* * Must be set before marking the journal entry as open: */ j->cur_entry_u64s = u64s; old.v = atomic64_read(&j->reservations.counter); do { new.v = old.v; BUG_ON(old.cur_entry_offset == JOURNAL_ENTRY_ERROR_VAL); new.idx++; BUG_ON(journal_state_count(new, new.idx)); BUG_ON(new.idx != (journal_cur_seq(j) & JOURNAL_STATE_BUF_MASK)); journal_state_inc(&new); /* Handle any already added entries */ new.cur_entry_offset = le32_to_cpu(buf->data->u64s); } while (!atomic64_try_cmpxchg(&j->reservations.counter, &old.v, new.v)); if (nr_unwritten_journal_entries(j) == 1) mod_delayed_work(j->wq, &j->write_work, msecs_to_jiffies(c->opts.journal_flush_delay)); journal_wake(j); if (j->early_journal_entries.nr) darray_exit(&j->early_journal_entries); return 0; } static bool journal_quiesced(struct journal *j) { bool ret = atomic64_read(&j->seq) == j->seq_ondisk; if (!ret) bch2_journal_entry_close(j); return ret; } static void journal_quiesce(struct journal *j) { wait_event(j->wait, journal_quiesced(j)); } static void journal_write_work(struct work_struct *work) { struct journal *j = container_of(work, struct journal, write_work.work); spin_lock(&j->lock); if (__journal_entry_is_open(j->reservations)) { long delta = journal_cur_buf(j)->expires - jiffies; if (delta > 0) mod_delayed_work(j->wq, &j->write_work, delta); else __journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true); } spin_unlock(&j->lock); } static void journal_buf_prealloc(struct journal *j) { if (j->free_buf && j->free_buf_size >= j->buf_size_want) return; unsigned buf_size = j->buf_size_want; spin_unlock(&j->lock); void *buf = kvmalloc(buf_size, GFP_NOFS); spin_lock(&j->lock); if (buf && (!j->free_buf || buf_size > j->free_buf_size)) { swap(buf, j->free_buf); swap(buf_size, j->free_buf_size); } if (unlikely(buf)) { spin_unlock(&j->lock); /* kvfree can sleep */ kvfree(buf); spin_lock(&j->lock); } } static int __journal_res_get(struct journal *j, struct journal_res *res, unsigned flags) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct journal_buf *buf; bool can_discard; int ret; retry: if (journal_res_get_fast(j, res, flags)) return 0; ret = bch2_journal_error(j); if (unlikely(ret)) return ret; if (j->blocked) return -BCH_ERR_journal_blocked; if ((flags & BCH_WATERMARK_MASK) < j->watermark) { ret = -BCH_ERR_journal_full; can_discard = j->can_discard; goto out; } if (nr_unwritten_journal_entries(j) == ARRAY_SIZE(j->buf) && !journal_entry_is_open(j)) { ret = -BCH_ERR_journal_max_in_flight; goto out; } spin_lock(&j->lock); journal_buf_prealloc(j); /* * Recheck after taking the lock, so we don't race with another thread * that just did journal_entry_open() and call bch2_journal_entry_close() * unnecessarily */ if (journal_res_get_fast(j, res, flags)) { ret = 0; goto unlock; } /* * If we couldn't get a reservation because the current buf filled up, * and we had room for a bigger entry on disk, signal that we want to * realloc the journal bufs: */ buf = journal_cur_buf(j); if (journal_entry_is_open(j) && buf->buf_size >> 9 < buf->disk_sectors && buf->buf_size < JOURNAL_ENTRY_SIZE_MAX) j->buf_size_want = max(j->buf_size_want, buf->buf_size << 1); __journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, false); ret = journal_entry_open(j) ?: -BCH_ERR_journal_retry_open; unlock: can_discard = j->can_discard; spin_unlock(&j->lock); out: if (likely(!ret)) return 0; if (ret == -BCH_ERR_journal_retry_open) goto retry; if (journal_error_check_stuck(j, ret, flags)) ret = -BCH_ERR_journal_stuck; if (ret == -BCH_ERR_journal_max_in_flight && track_event_change(&c->times[BCH_TIME_blocked_journal_max_in_flight], true) && trace_journal_entry_full_enabled()) { struct printbuf buf = PRINTBUF; bch2_printbuf_make_room(&buf, 4096); spin_lock(&j->lock); prt_printf(&buf, "seq %llu\n", journal_cur_seq(j)); bch2_journal_bufs_to_text(&buf, j); spin_unlock(&j->lock); trace_journal_entry_full(c, buf.buf); printbuf_exit(&buf); count_event(c, journal_entry_full); } if (ret == -BCH_ERR_journal_max_open && track_event_change(&c->times[BCH_TIME_blocked_journal_max_open], true) && trace_journal_entry_full_enabled()) { struct printbuf buf = PRINTBUF; bch2_printbuf_make_room(&buf, 4096); spin_lock(&j->lock); prt_printf(&buf, "seq %llu\n", journal_cur_seq(j)); bch2_journal_bufs_to_text(&buf, j); spin_unlock(&j->lock); trace_journal_entry_full(c, buf.buf); printbuf_exit(&buf); count_event(c, journal_entry_full); } /* * Journal is full - can't rely on reclaim from work item due to * freezing: */ if ((ret == -BCH_ERR_journal_full || ret == -BCH_ERR_journal_pin_full) && !(flags & JOURNAL_RES_GET_NONBLOCK)) { if (can_discard) { bch2_journal_do_discards(j); goto retry; } if (mutex_trylock(&j->reclaim_lock)) { bch2_journal_reclaim(j); mutex_unlock(&j->reclaim_lock); } } return ret; } static unsigned max_dev_latency(struct bch_fs *c) { u64 nsecs = 0; for_each_rw_member(c, ca) nsecs = max(nsecs, ca->io_latency[WRITE].stats.max_duration); return nsecs_to_jiffies(nsecs); } /* * Essentially the entry function to the journaling code. When bcachefs is doing * a btree insert, it calls this function to get the current journal write. * Journal write is the structure used set up journal writes. The calling * function will then add its keys to the structure, queuing them for the next * write. * * To ensure forward progress, the current task must not be holding any * btree node write locks. */ int bch2_journal_res_get_slowpath(struct journal *j, struct journal_res *res, unsigned flags, struct btree_trans *trans) { int ret; if (closure_wait_event_timeout(&j->async_wait, !bch2_err_matches(ret = __journal_res_get(j, res, flags), BCH_ERR_operation_blocked) || (flags & JOURNAL_RES_GET_NONBLOCK), HZ)) return ret; if (trans) bch2_trans_unlock_long(trans); struct bch_fs *c = container_of(j, struct bch_fs, journal); int remaining_wait = max(max_dev_latency(c) * 2, HZ * 10); remaining_wait = max(0, remaining_wait - HZ); if (closure_wait_event_timeout(&j->async_wait, !bch2_err_matches(ret = __journal_res_get(j, res, flags), BCH_ERR_operation_blocked) || (flags & JOURNAL_RES_GET_NONBLOCK), remaining_wait)) return ret; struct printbuf buf = PRINTBUF; bch2_journal_debug_to_text(&buf, j); bch_err(c, "Journal stuck? Waited for 10 seconds...\n%s", buf.buf); printbuf_exit(&buf); closure_wait_event(&j->async_wait, !bch2_err_matches(ret = __journal_res_get(j, res, flags), BCH_ERR_operation_blocked) || (flags & JOURNAL_RES_GET_NONBLOCK)); return ret; } /* journal_entry_res: */ void bch2_journal_entry_res_resize(struct journal *j, struct journal_entry_res *res, unsigned new_u64s) { union journal_res_state state; int d = new_u64s - res->u64s; spin_lock(&j->lock); j->entry_u64s_reserved += d; if (d <= 0) goto out; j->cur_entry_u64s = max_t(int, 0, j->cur_entry_u64s - d); state = READ_ONCE(j->reservations); if (state.cur_entry_offset < JOURNAL_ENTRY_CLOSED_VAL && state.cur_entry_offset > j->cur_entry_u64s) { j->cur_entry_u64s += d; /* * Not enough room in current journal entry, have to flush it: */ __journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true); } else { journal_cur_buf(j)->u64s_reserved += d; } out: spin_unlock(&j->lock); res->u64s += d; } /* journal flushing: */ /** * bch2_journal_flush_seq_async - wait for a journal entry to be written * @j: journal object * @seq: seq to flush * @parent: closure object to wait with * Returns: 1 if @seq has already been flushed, 0 if @seq is being flushed, * -BCH_ERR_journal_flush_err if @seq will never be flushed * * Like bch2_journal_wait_on_seq, except that it triggers a write immediately if * necessary */ int bch2_journal_flush_seq_async(struct journal *j, u64 seq, struct closure *parent) { struct journal_buf *buf; int ret = 0; if (seq <= j->flushed_seq_ondisk) return 1; spin_lock(&j->lock); if (WARN_ONCE(seq > journal_cur_seq(j), "requested to flush journal seq %llu, but currently at %llu", seq, journal_cur_seq(j))) goto out; /* Recheck under lock: */ if (j->err_seq && seq >= j->err_seq) { ret = -BCH_ERR_journal_flush_err; goto out; } if (seq <= j->flushed_seq_ondisk) { ret = 1; goto out; } /* if seq was written, but not flushed - flush a newer one instead */ seq = max(seq, journal_last_unwritten_seq(j)); recheck_need_open: if (seq > journal_cur_seq(j)) { struct journal_res res = { 0 }; if (journal_entry_is_open(j)) __journal_entry_close(j, JOURNAL_ENTRY_CLOSED_VAL, true); spin_unlock(&j->lock); /* * We're called from bch2_journal_flush_seq() -> wait_event(); * but this might block. We won't usually block, so we won't * livelock: */ sched_annotate_sleep(); ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0, NULL); if (ret) return ret; seq = res.seq; buf = journal_seq_to_buf(j, seq); buf->must_flush = true; if (!buf->flush_time) { buf->flush_time = local_clock() ?: 1; buf->expires = jiffies; } if (parent && !closure_wait(&buf->wait, parent)) BUG(); bch2_journal_res_put(j, &res); spin_lock(&j->lock); goto want_write; } /* * if write was kicked off without a flush, or if we promised it * wouldn't be a flush, flush the next sequence number instead */ buf = journal_seq_to_buf(j, seq); if (buf->noflush) { seq++; goto recheck_need_open; } buf->must_flush = true; j->flushing_seq = max(j->flushing_seq, seq); if (parent && !closure_wait(&buf->wait, parent)) BUG(); want_write: if (seq == journal_cur_seq(j)) journal_entry_want_write(j); out: spin_unlock(&j->lock); return ret; } int bch2_journal_flush_seq(struct journal *j, u64 seq, unsigned task_state) { u64 start_time = local_clock(); int ret, ret2; /* * Don't update time_stats when @seq is already flushed: */ if (seq <= j->flushed_seq_ondisk) return 0; ret = wait_event_state(j->wait, (ret2 = bch2_journal_flush_seq_async(j, seq, NULL)), task_state); if (!ret) bch2_time_stats_update(j->flush_seq_time, start_time); return ret ?: ret2 < 0 ? ret2 : 0; } /* * bch2_journal_flush_async - if there is an open journal entry, or a journal * still being written, write it and wait for the write to complete */ void bch2_journal_flush_async(struct journal *j, struct closure *parent) { bch2_journal_flush_seq_async(j, atomic64_read(&j->seq), parent); } int bch2_journal_flush(struct journal *j) { return bch2_journal_flush_seq(j, atomic64_read(&j->seq), TASK_UNINTERRUPTIBLE); } /* * bch2_journal_noflush_seq - ask the journal not to issue any flushes in the * range [start, end) * @seq */ bool bch2_journal_noflush_seq(struct journal *j, u64 start, u64 end) { struct bch_fs *c = container_of(j, struct bch_fs, journal); u64 unwritten_seq; bool ret = false; if (!(c->sb.features & (1ULL << BCH_FEATURE_journal_no_flush))) return false; if (c->journal.flushed_seq_ondisk >= start) return false; spin_lock(&j->lock); if (c->journal.flushed_seq_ondisk >= start) goto out; for (unwritten_seq = journal_last_unwritten_seq(j); unwritten_seq < end; unwritten_seq++) { struct journal_buf *buf = journal_seq_to_buf(j, unwritten_seq); /* journal flush already in flight, or flush requseted */ if (buf->must_flush) goto out; buf->noflush = true; } ret = true; out: spin_unlock(&j->lock); return ret; } static int __bch2_journal_meta(struct journal *j) { struct journal_res res = {}; int ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0, NULL); if (ret) return ret; struct journal_buf *buf = j->buf + (res.seq & JOURNAL_BUF_MASK); buf->must_flush = true; if (!buf->flush_time) { buf->flush_time = local_clock() ?: 1; buf->expires = jiffies; } bch2_journal_res_put(j, &res); return bch2_journal_flush_seq(j, res.seq, TASK_UNINTERRUPTIBLE); } int bch2_journal_meta(struct journal *j) { struct bch_fs *c = container_of(j, struct bch_fs, journal); if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_journal)) return -BCH_ERR_erofs_no_writes; int ret = __bch2_journal_meta(j); bch2_write_ref_put(c, BCH_WRITE_REF_journal); return ret; } /* block/unlock the journal: */ void bch2_journal_unblock(struct journal *j) { spin_lock(&j->lock); if (!--j->blocked && j->cur_entry_offset_if_blocked < JOURNAL_ENTRY_CLOSED_VAL && j->reservations.cur_entry_offset == JOURNAL_ENTRY_BLOCKED_VAL) { union journal_res_state old, new; old.v = atomic64_read(&j->reservations.counter); do { new.v = old.v; new.cur_entry_offset = j->cur_entry_offset_if_blocked; } while (!atomic64_try_cmpxchg(&j->reservations.counter, &old.v, new.v)); } spin_unlock(&j->lock); journal_wake(j); } static void __bch2_journal_block(struct journal *j) { if (!j->blocked++) { union journal_res_state old, new; old.v = atomic64_read(&j->reservations.counter); do { j->cur_entry_offset_if_blocked = old.cur_entry_offset; if (j->cur_entry_offset_if_blocked >= JOURNAL_ENTRY_CLOSED_VAL) break; new.v = old.v; new.cur_entry_offset = JOURNAL_ENTRY_BLOCKED_VAL; } while (!atomic64_try_cmpxchg(&j->reservations.counter, &old.v, new.v)); if (old.cur_entry_offset < JOURNAL_ENTRY_BLOCKED_VAL) journal_cur_buf(j)->data->u64s = cpu_to_le32(old.cur_entry_offset); } } void bch2_journal_block(struct journal *j) { spin_lock(&j->lock); __bch2_journal_block(j); spin_unlock(&j->lock); journal_quiesce(j); } static struct journal_buf *__bch2_next_write_buffer_flush_journal_buf(struct journal *j, u64 max_seq, bool *blocked) { struct journal_buf *ret = NULL; /* We're inside wait_event(), but using mutex_lock(: */ sched_annotate_sleep(); mutex_lock(&j->buf_lock); spin_lock(&j->lock); max_seq = min(max_seq, journal_cur_seq(j)); for (u64 seq = journal_last_unwritten_seq(j); seq <= max_seq; seq++) { unsigned idx = seq & JOURNAL_BUF_MASK; struct journal_buf *buf = j->buf + idx; if (buf->need_flush_to_write_buffer) { union journal_res_state s; s.v = atomic64_read_acquire(&j->reservations.counter); unsigned open = seq == journal_cur_seq(j) && __journal_entry_is_open(s); if (open && !*blocked) { __bch2_journal_block(j); *blocked = true; } ret = journal_state_count(s, idx & JOURNAL_STATE_BUF_MASK) > open ? ERR_PTR(-EAGAIN) : buf; break; } } spin_unlock(&j->lock); if (IS_ERR_OR_NULL(ret)) mutex_unlock(&j->buf_lock); return ret; } struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j, u64 max_seq, bool *blocked) { struct journal_buf *ret; *blocked = false; wait_event(j->wait, (ret = __bch2_next_write_buffer_flush_journal_buf(j, max_seq, blocked)) != ERR_PTR(-EAGAIN)); if (IS_ERR_OR_NULL(ret) && *blocked) bch2_journal_unblock(j); return ret; } /* allocate journal on a device: */ static int bch2_set_nr_journal_buckets_iter(struct bch_dev *ca, unsigned nr, bool new_fs, struct closure *cl) { struct bch_fs *c = ca->fs; struct journal_device *ja = &ca->journal; u64 *new_bucket_seq = NULL, *new_buckets = NULL; struct open_bucket **ob = NULL; long *bu = NULL; unsigned i, pos, nr_got = 0, nr_want = nr - ja->nr; int ret = 0; BUG_ON(nr <= ja->nr); bu = kcalloc(nr_want, sizeof(*bu), GFP_KERNEL); ob = kcalloc(nr_want, sizeof(*ob), GFP_KERNEL); new_buckets = kcalloc(nr, sizeof(u64), GFP_KERNEL); new_bucket_seq = kcalloc(nr, sizeof(u64), GFP_KERNEL); if (!bu || !ob || !new_buckets || !new_bucket_seq) { ret = -BCH_ERR_ENOMEM_set_nr_journal_buckets; goto err_free; } for (nr_got = 0; nr_got < nr_want; nr_got++) { enum bch_watermark watermark = new_fs ? BCH_WATERMARK_btree : BCH_WATERMARK_normal; ob[nr_got] = bch2_bucket_alloc(c, ca, watermark, BCH_DATA_journal, cl); ret = PTR_ERR_OR_ZERO(ob[nr_got]); if (ret) break; if (!new_fs) { ret = bch2_trans_run(c, bch2_trans_mark_metadata_bucket(trans, ca, ob[nr_got]->bucket, BCH_DATA_journal, ca->mi.bucket_size, BTREE_TRIGGER_transactional)); if (ret) { bch2_open_bucket_put(c, ob[nr_got]); bch_err_msg(c, ret, "marking new journal buckets"); break; } } bu[nr_got] = ob[nr_got]->bucket; } if (!nr_got) goto err_free; /* Don't return an error if we successfully allocated some buckets: */ ret = 0; if (c) { bch2_journal_flush_all_pins(&c->journal); bch2_journal_block(&c->journal); mutex_lock(&c->sb_lock); } memcpy(new_buckets, ja->buckets, ja->nr * sizeof(u64)); memcpy(new_bucket_seq, ja->bucket_seq, ja->nr * sizeof(u64)); BUG_ON(ja->discard_idx > ja->nr); pos = ja->discard_idx ?: ja->nr; memmove(new_buckets + pos + nr_got, new_buckets + pos, sizeof(new_buckets[0]) * (ja->nr - pos)); memmove(new_bucket_seq + pos + nr_got, new_bucket_seq + pos, sizeof(new_bucket_seq[0]) * (ja->nr - pos)); for (i = 0; i < nr_got; i++) { new_buckets[pos + i] = bu[i]; new_bucket_seq[pos + i] = 0; } nr = ja->nr + nr_got; ret = bch2_journal_buckets_to_sb(c, ca, new_buckets, nr); if (ret) goto err_unblock; bch2_write_super(c); /* Commit: */ if (c) spin_lock(&c->journal.lock); swap(new_buckets, ja->buckets); swap(new_bucket_seq, ja->bucket_seq); ja->nr = nr; if (pos <= ja->discard_idx) ja->discard_idx = (ja->discard_idx + nr_got) % ja->nr; if (pos <= ja->dirty_idx_ondisk) ja->dirty_idx_ondisk = (ja->dirty_idx_ondisk + nr_got) % ja->nr; if (pos <= ja->dirty_idx) ja->dirty_idx = (ja->dirty_idx + nr_got) % ja->nr; if (pos <= ja->cur_idx) ja->cur_idx = (ja->cur_idx + nr_got) % ja->nr; if (c) spin_unlock(&c->journal.lock); err_unblock: if (c) { bch2_journal_unblock(&c->journal); mutex_unlock(&c->sb_lock); } if (ret && !new_fs) for (i = 0; i < nr_got; i++) bch2_trans_run(c, bch2_trans_mark_metadata_bucket(trans, ca, bu[i], BCH_DATA_free, 0, BTREE_TRIGGER_transactional)); err_free: for (i = 0; i < nr_got; i++) bch2_open_bucket_put(c, ob[i]); kfree(new_bucket_seq); kfree(new_buckets); kfree(ob); kfree(bu); return ret; } static int bch2_set_nr_journal_buckets_loop(struct bch_fs *c, struct bch_dev *ca, unsigned nr, bool new_fs) { struct journal_device *ja = &ca->journal; int ret = 0; struct closure cl; closure_init_stack(&cl); /* don't handle reducing nr of buckets yet: */ if (nr < ja->nr) return 0; while (!ret && ja->nr < nr) { struct disk_reservation disk_res = { 0, 0, 0 }; /* * note: journal buckets aren't really counted as _sectors_ used yet, so * we don't need the disk reservation to avoid the BUG_ON() in buckets.c * when space used goes up without a reservation - but we do need the * reservation to ensure we'll actually be able to allocate: * * XXX: that's not right, disk reservations only ensure a * filesystem-wide allocation will succeed, this is a device * specific allocation - we can hang here: */ if (!new_fs) { ret = bch2_disk_reservation_get(c, &disk_res, bucket_to_sector(ca, nr - ja->nr), 1, 0); if (ret) break; } ret = bch2_set_nr_journal_buckets_iter(ca, nr, new_fs, &cl); if (ret == -BCH_ERR_bucket_alloc_blocked || ret == -BCH_ERR_open_buckets_empty) ret = 0; /* wait and retry */ bch2_disk_reservation_put(c, &disk_res); closure_sync(&cl); } return ret; } /* * Allocate more journal space at runtime - not currently making use if it, but * the code works: */ int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca, unsigned nr) { down_write(&c->state_lock); int ret = bch2_set_nr_journal_buckets_loop(c, ca, nr, false); up_write(&c->state_lock); bch_err_fn(c, ret); return ret; } int bch2_dev_journal_alloc(struct bch_dev *ca, bool new_fs) { unsigned nr; int ret; if (dynamic_fault("bcachefs:add:journal_alloc")) { ret = -BCH_ERR_ENOMEM_set_nr_journal_buckets; goto err; } /* 1/128th of the device by default: */ nr = ca->mi.nbuckets >> 7; /* * clamp journal size to 8192 buckets or 8GB (in sectors), whichever * is smaller: */ nr = clamp_t(unsigned, nr, BCH_JOURNAL_BUCKETS_MIN, min(1 << 13, (1 << 24) / ca->mi.bucket_size)); ret = bch2_set_nr_journal_buckets_loop(ca->fs, ca, nr, new_fs); err: bch_err_fn(ca, ret); return ret; } int bch2_fs_journal_alloc(struct bch_fs *c) { for_each_online_member(c, ca) { if (ca->journal.nr) continue; int ret = bch2_dev_journal_alloc(ca, true); if (ret) { percpu_ref_put(&ca->io_ref); return ret; } } return 0; } /* startup/shutdown: */ static bool bch2_journal_writing_to_device(struct journal *j, unsigned dev_idx) { bool ret = false; u64 seq; spin_lock(&j->lock); for (seq = journal_last_unwritten_seq(j); seq <= journal_cur_seq(j) && !ret; seq++) { struct journal_buf *buf = journal_seq_to_buf(j, seq); if (bch2_bkey_has_device_c(bkey_i_to_s_c(&buf->key), dev_idx)) ret = true; } spin_unlock(&j->lock); return ret; } void bch2_dev_journal_stop(struct journal *j, struct bch_dev *ca) { wait_event(j->wait, !bch2_journal_writing_to_device(j, ca->dev_idx)); } void bch2_fs_journal_stop(struct journal *j) { if (!test_bit(JOURNAL_running, &j->flags)) return; bch2_journal_reclaim_stop(j); bch2_journal_flush_all_pins(j); wait_event(j->wait, bch2_journal_entry_close(j)); /* * Always write a new journal entry, to make sure the clock hands are up * to date (and match the superblock) */ __bch2_journal_meta(j); journal_quiesce(j); cancel_delayed_work_sync(&j->write_work); WARN(!bch2_journal_error(j) && test_bit(JOURNAL_replay_done, &j->flags) && j->last_empty_seq != journal_cur_seq(j), "journal shutdown error: cur seq %llu but last empty seq %llu", journal_cur_seq(j), j->last_empty_seq); if (!bch2_journal_error(j)) clear_bit(JOURNAL_running, &j->flags); } int bch2_fs_journal_start(struct journal *j, u64 cur_seq) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct journal_entry_pin_list *p; struct journal_replay *i, **_i; struct genradix_iter iter; bool had_entries = false; u64 last_seq = cur_seq, nr, seq; if (cur_seq >= JOURNAL_SEQ_MAX) { bch_err(c, "cannot start: journal seq overflow"); return -EINVAL; } genradix_for_each_reverse(&c->journal_entries, iter, _i) { i = *_i; if (journal_replay_ignore(i)) continue; last_seq = le64_to_cpu(i->j.last_seq); break; } nr = cur_seq - last_seq; if (nr + 1 > j->pin.size) { free_fifo(&j->pin); init_fifo(&j->pin, roundup_pow_of_two(nr + 1), GFP_KERNEL); if (!j->pin.data) { bch_err(c, "error reallocating journal fifo (%llu open entries)", nr); return -BCH_ERR_ENOMEM_journal_pin_fifo; } } j->replay_journal_seq = last_seq; j->replay_journal_seq_end = cur_seq; j->last_seq_ondisk = last_seq; j->flushed_seq_ondisk = cur_seq - 1; j->seq_write_started = cur_seq - 1; j->seq_ondisk = cur_seq - 1; j->pin.front = last_seq; j->pin.back = cur_seq; atomic64_set(&j->seq, cur_seq - 1); fifo_for_each_entry_ptr(p, &j->pin, seq) journal_pin_list_init(p, 1); genradix_for_each(&c->journal_entries, iter, _i) { i = *_i; if (journal_replay_ignore(i)) continue; seq = le64_to_cpu(i->j.seq); BUG_ON(seq >= cur_seq); if (seq < last_seq) continue; if (journal_entry_empty(&i->j)) j->last_empty_seq = le64_to_cpu(i->j.seq); p = journal_seq_pin(j, seq); p->devs.nr = 0; darray_for_each(i->ptrs, ptr) bch2_dev_list_add_dev(&p->devs, ptr->dev); had_entries = true; } if (!had_entries) j->last_empty_seq = cur_seq - 1; /* to match j->seq */ spin_lock(&j->lock); set_bit(JOURNAL_running, &j->flags); j->last_flush_write = jiffies; j->reservations.idx = journal_cur_seq(j); c->last_bucket_seq_cleanup = journal_cur_seq(j); bch2_journal_space_available(j); spin_unlock(&j->lock); return bch2_journal_reclaim_start(j); } /* init/exit: */ void bch2_dev_journal_exit(struct bch_dev *ca) { struct journal_device *ja = &ca->journal; for (unsigned i = 0; i < ARRAY_SIZE(ja->bio); i++) { kfree(ja->bio[i]); ja->bio[i] = NULL; } kfree(ja->buckets); kfree(ja->bucket_seq); ja->buckets = NULL; ja->bucket_seq = NULL; } int bch2_dev_journal_init(struct bch_dev *ca, struct bch_sb *sb) { struct journal_device *ja = &ca->journal; struct bch_sb_field_journal *journal_buckets = bch2_sb_field_get(sb, journal); struct bch_sb_field_journal_v2 *journal_buckets_v2 = bch2_sb_field_get(sb, journal_v2); ja->nr = 0; if (journal_buckets_v2) { unsigned nr = bch2_sb_field_journal_v2_nr_entries(journal_buckets_v2); for (unsigned i = 0; i < nr; i++) ja->nr += le64_to_cpu(journal_buckets_v2->d[i].nr); } else if (journal_buckets) { ja->nr = bch2_nr_journal_buckets(journal_buckets); } ja->bucket_seq = kcalloc(ja->nr, sizeof(u64), GFP_KERNEL); if (!ja->bucket_seq) return -BCH_ERR_ENOMEM_dev_journal_init; unsigned nr_bvecs = DIV_ROUND_UP(JOURNAL_ENTRY_SIZE_MAX, PAGE_SIZE); for (unsigned i = 0; i < ARRAY_SIZE(ja->bio); i++) { ja->bio[i] = kzalloc(struct_size(ja->bio[i], bio.bi_inline_vecs, nr_bvecs), GFP_KERNEL); if (!ja->bio[i]) return -BCH_ERR_ENOMEM_dev_journal_init; ja->bio[i]->ca = ca; ja->bio[i]->buf_idx = i; bio_init(&ja->bio[i]->bio, NULL, ja->bio[i]->bio.bi_inline_vecs, nr_bvecs, 0); } ja->buckets = kcalloc(ja->nr, sizeof(u64), GFP_KERNEL); if (!ja->buckets) return -BCH_ERR_ENOMEM_dev_journal_init; if (journal_buckets_v2) { unsigned nr = bch2_sb_field_journal_v2_nr_entries(journal_buckets_v2); unsigned dst = 0; for (unsigned i = 0; i < nr; i++) for (unsigned j = 0; j < le64_to_cpu(journal_buckets_v2->d[i].nr); j++) ja->buckets[dst++] = le64_to_cpu(journal_buckets_v2->d[i].start) + j; } else if (journal_buckets) { for (unsigned i = 0; i < ja->nr; i++) ja->buckets[i] = le64_to_cpu(journal_buckets->buckets[i]); } return 0; } void bch2_fs_journal_exit(struct journal *j) { if (j->wq) destroy_workqueue(j->wq); darray_exit(&j->early_journal_entries); for (unsigned i = 0; i < ARRAY_SIZE(j->buf); i++) kvfree(j->buf[i].data); kvfree(j->free_buf); free_fifo(&j->pin); } int bch2_fs_journal_init(struct journal *j) { static struct lock_class_key res_key; mutex_init(&j->buf_lock); spin_lock_init(&j->lock); spin_lock_init(&j->err_lock); init_waitqueue_head(&j->wait); INIT_DELAYED_WORK(&j->write_work, journal_write_work); init_waitqueue_head(&j->reclaim_wait); init_waitqueue_head(&j->pin_flush_wait); mutex_init(&j->reclaim_lock); mutex_init(&j->discard_lock); lockdep_init_map(&j->res_map, "journal res", &res_key, 0); atomic64_set(&j->reservations.counter, ((union journal_res_state) { .cur_entry_offset = JOURNAL_ENTRY_CLOSED_VAL }).v); if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL))) return -BCH_ERR_ENOMEM_journal_pin_fifo; j->free_buf_size = j->buf_size_want = JOURNAL_ENTRY_SIZE_MIN; j->free_buf = kvmalloc(j->free_buf_size, GFP_KERNEL); if (!j->free_buf) return -BCH_ERR_ENOMEM_journal_buf; for (unsigned i = 0; i < ARRAY_SIZE(j->buf); i++) j->buf[i].idx = i; j->pin.front = j->pin.back = 1; j->wq = alloc_workqueue("bcachefs_journal", WQ_HIGHPRI|WQ_FREEZABLE|WQ_UNBOUND|WQ_MEM_RECLAIM, 512); if (!j->wq) return -BCH_ERR_ENOMEM_fs_other_alloc; return 0; } /* debug: */ static const char * const bch2_journal_flags_strs[] = { #define x(n) #n, JOURNAL_FLAGS() #undef x NULL }; void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) { struct bch_fs *c = container_of(j, struct bch_fs, journal); union journal_res_state s; unsigned long now = jiffies; u64 nr_writes = j->nr_flush_writes + j->nr_noflush_writes; printbuf_tabstops_reset(out); printbuf_tabstop_push(out, 28); out->atomic++; rcu_read_lock(); s = READ_ONCE(j->reservations); prt_printf(out, "flags:\t"); prt_bitflags(out, bch2_journal_flags_strs, j->flags); prt_newline(out); prt_printf(out, "dirty journal entries:\t%llu/%llu\n", fifo_used(&j->pin), j->pin.size); prt_printf(out, "seq:\t%llu\n", journal_cur_seq(j)); prt_printf(out, "seq_ondisk:\t%llu\n", j->seq_ondisk); prt_printf(out, "last_seq:\t%llu\n", journal_last_seq(j)); prt_printf(out, "last_seq_ondisk:\t%llu\n", j->last_seq_ondisk); prt_printf(out, "flushed_seq_ondisk:\t%llu\n", j->flushed_seq_ondisk); prt_printf(out, "watermark:\t%s\n", bch2_watermarks[j->watermark]); prt_printf(out, "each entry reserved:\t%u\n", j->entry_u64s_reserved); prt_printf(out, "nr flush writes:\t%llu\n", j->nr_flush_writes); prt_printf(out, "nr noflush writes:\t%llu\n", j->nr_noflush_writes); prt_printf(out, "average write size:\t"); prt_human_readable_u64(out, nr_writes ? div64_u64(j->entry_bytes_written, nr_writes) : 0); prt_newline(out); prt_printf(out, "free buf:\t%u\n", j->free_buf ? j->free_buf_size : 0); prt_printf(out, "nr direct reclaim:\t%llu\n", j->nr_direct_reclaim); prt_printf(out, "nr background reclaim:\t%llu\n", j->nr_background_reclaim); prt_printf(out, "reclaim kicked:\t%u\n", j->reclaim_kicked); prt_printf(out, "reclaim runs in:\t%u ms\n", time_after(j->next_reclaim, now) ? jiffies_to_msecs(j->next_reclaim - jiffies) : 0); prt_printf(out, "blocked:\t%u\n", j->blocked); prt_printf(out, "current entry sectors:\t%u\n", j->cur_entry_sectors); prt_printf(out, "current entry error:\t%s\n", bch2_err_str(j->cur_entry_error)); prt_printf(out, "current entry:\t"); switch (s.cur_entry_offset) { case JOURNAL_ENTRY_ERROR_VAL: prt_printf(out, "error\n"); break; case JOURNAL_ENTRY_CLOSED_VAL: prt_printf(out, "closed\n"); break; case JOURNAL_ENTRY_BLOCKED_VAL: prt_printf(out, "blocked\n"); break; default: prt_printf(out, "%u/%u\n", s.cur_entry_offset, j->cur_entry_u64s); break; } prt_printf(out, "unwritten entries:\n"); bch2_journal_bufs_to_text(out, j); prt_printf(out, "space:\n"); printbuf_indent_add(out, 2); prt_printf(out, "discarded\t%u:%u\n", j->space[journal_space_discarded].next_entry, j->space[journal_space_discarded].total); prt_printf(out, "clean ondisk\t%u:%u\n", j->space[journal_space_clean_ondisk].next_entry, j->space[journal_space_clean_ondisk].total); prt_printf(out, "clean\t%u:%u\n", j->space[journal_space_clean].next_entry, j->space[journal_space_clean].total); prt_printf(out, "total\t%u:%u\n", j->space[journal_space_total].next_entry, j->space[journal_space_total].total); printbuf_indent_sub(out, 2); for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) { if (!ca->mi.durability) continue; struct journal_device *ja = &ca->journal; if (!test_bit(ca->dev_idx, c->rw_devs[BCH_DATA_journal].d)) continue; if (!ja->nr) continue; prt_printf(out, "dev %u:\n", ca->dev_idx); prt_printf(out, "durability %u:\n", ca->mi.durability); printbuf_indent_add(out, 2); prt_printf(out, "nr\t%u\n", ja->nr); prt_printf(out, "bucket size\t%u\n", ca->mi.bucket_size); prt_printf(out, "available\t%u:%u\n", bch2_journal_dev_buckets_available(j, ja, journal_space_discarded), ja->sectors_free); prt_printf(out, "discard_idx\t%u\n", ja->discard_idx); prt_printf(out, "dirty_ondisk\t%u (seq %llu)\n",ja->dirty_idx_ondisk, ja->bucket_seq[ja->dirty_idx_ondisk]); prt_printf(out, "dirty_idx\t%u (seq %llu)\n", ja->dirty_idx, ja->bucket_seq[ja->dirty_idx]); prt_printf(out, "cur_idx\t%u (seq %llu)\n", ja->cur_idx, ja->bucket_seq[ja->cur_idx]); printbuf_indent_sub(out, 2); } prt_printf(out, "replicas want %u need %u\n", c->opts.metadata_replicas, c->opts.metadata_replicas_required); rcu_read_unlock(); --out->atomic; } void bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) { spin_lock(&j->lock); __bch2_journal_debug_to_text(out, j); spin_unlock(&j->lock); } |
| 1 1 1 1 1 1 1 1 1 1 31 31 22 22 22 20 21 21 22 21 11 11 11 11 11 3 3 14 3 11 14 14 14 14 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Generic associative array implementation. * * See Documentation/core-api/assoc_array.rst for information. * * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ //#define DEBUG #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/assoc_array_priv.h> /* * Iterate over an associative array. The caller must hold the RCU read lock * or better. */ static int assoc_array_subtree_iterate(const struct assoc_array_ptr *root, const struct assoc_array_ptr *stop, int (*iterator)(const void *leaf, void *iterator_data), void *iterator_data) { const struct assoc_array_shortcut *shortcut; const struct assoc_array_node *node; const struct assoc_array_ptr *cursor, *ptr, *parent; unsigned long has_meta; int slot, ret; cursor = root; begin_node: if (assoc_array_ptr_is_shortcut(cursor)) { /* Descend through a shortcut */ shortcut = assoc_array_ptr_to_shortcut(cursor); cursor = READ_ONCE(shortcut->next_node); /* Address dependency. */ } node = assoc_array_ptr_to_node(cursor); slot = 0; /* We perform two passes of each node. * * The first pass does all the leaves in this node. This means we * don't miss any leaves if the node is split up by insertion whilst * we're iterating over the branches rooted here (we may, however, see * some leaves twice). */ has_meta = 0; for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */ has_meta |= (unsigned long)ptr; if (ptr && assoc_array_ptr_is_leaf(ptr)) { /* We need a barrier between the read of the pointer, * which is supplied by the above READ_ONCE(). */ /* Invoke the callback */ ret = iterator(assoc_array_ptr_to_leaf(ptr), iterator_data); if (ret) return ret; } } /* The second pass attends to all the metadata pointers. If we follow * one of these we may find that we don't come back here, but rather go * back to a replacement node with the leaves in a different layout. * * We are guaranteed to make progress, however, as the slot number for * a particular portion of the key space cannot change - and we * continue at the back pointer + 1. */ if (!(has_meta & ASSOC_ARRAY_PTR_META_TYPE)) goto finished_node; slot = 0; continue_node: node = assoc_array_ptr_to_node(cursor); for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */ if (assoc_array_ptr_is_meta(ptr)) { cursor = ptr; goto begin_node; } } finished_node: /* Move up to the parent (may need to skip back over a shortcut) */ parent = READ_ONCE(node->back_pointer); /* Address dependency. */ slot = node->parent_slot; if (parent == stop) return 0; if (assoc_array_ptr_is_shortcut(parent)) { shortcut = assoc_array_ptr_to_shortcut(parent); cursor = parent; parent = READ_ONCE(shortcut->back_pointer); /* Address dependency. */ slot = shortcut->parent_slot; if (parent == stop) return 0; } /* Ascend to next slot in parent node */ cursor = parent; slot++; goto continue_node; } /** * assoc_array_iterate - Pass all objects in the array to a callback * @array: The array to iterate over. * @iterator: The callback function. * @iterator_data: Private data for the callback function. * * Iterate over all the objects in an associative array. Each one will be * presented to the iterator function. * * If the array is being modified concurrently with the iteration then it is * possible that some objects in the array will be passed to the iterator * callback more than once - though every object should be passed at least * once. If this is undesirable then the caller must lock against modification * for the duration of this function. * * The function will return 0 if no objects were in the array or else it will * return the result of the last iterator function called. Iteration stops * immediately if any call to the iteration function results in a non-zero * return. * * The caller should hold the RCU read lock or better if concurrent * modification is possible. */ int assoc_array_iterate(const struct assoc_array *array, int (*iterator)(const void *object, void *iterator_data), void *iterator_data) { struct assoc_array_ptr *root = READ_ONCE(array->root); /* Address dependency. */ if (!root) return 0; return assoc_array_subtree_iterate(root, NULL, iterator, iterator_data); } enum assoc_array_walk_status { assoc_array_walk_tree_empty, assoc_array_walk_found_terminal_node, assoc_array_walk_found_wrong_shortcut, }; struct assoc_array_walk_result { struct { struct assoc_array_node *node; /* Node in which leaf might be found */ int level; int slot; } terminal_node; struct { struct assoc_array_shortcut *shortcut; int level; int sc_level; unsigned long sc_segments; unsigned long dissimilarity; } wrong_shortcut; }; /* * Navigate through the internal tree looking for the closest node to the key. */ static enum assoc_array_walk_status assoc_array_walk(const struct assoc_array *array, const struct assoc_array_ops *ops, const void *index_key, struct assoc_array_walk_result *result) { struct assoc_array_shortcut *shortcut; struct assoc_array_node *node; struct assoc_array_ptr *cursor, *ptr; unsigned long sc_segments, dissimilarity; unsigned long segments; int level, sc_level, next_sc_level; int slot; pr_devel("-->%s()\n", __func__); cursor = READ_ONCE(array->root); /* Address dependency. */ if (!cursor) return assoc_array_walk_tree_empty; level = 0; /* Use segments from the key for the new leaf to navigate through the * internal tree, skipping through nodes and shortcuts that are on * route to the destination. Eventually we'll come to a slot that is * either empty or contains a leaf at which point we've found a node in * which the leaf we're looking for might be found or into which it * should be inserted. */ jumped: segments = ops->get_key_chunk(index_key, level); pr_devel("segments[%d]: %lx\n", level, segments); if (assoc_array_ptr_is_shortcut(cursor)) goto follow_shortcut; consider_node: node = assoc_array_ptr_to_node(cursor); slot = segments >> (level & ASSOC_ARRAY_KEY_CHUNK_MASK); slot &= ASSOC_ARRAY_FAN_MASK; ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */ pr_devel("consider slot %x [ix=%d type=%lu]\n", slot, level, (unsigned long)ptr & 3); if (!assoc_array_ptr_is_meta(ptr)) { /* The node doesn't have a node/shortcut pointer in the slot * corresponding to the index key that we have to follow. */ result->terminal_node.node = node; result->terminal_node.level = level; result->terminal_node.slot = slot; pr_devel("<--%s() = terminal_node\n", __func__); return assoc_array_walk_found_terminal_node; } if (assoc_array_ptr_is_node(ptr)) { /* There is a pointer to a node in the slot corresponding to * this index key segment, so we need to follow it. */ cursor = ptr; level += ASSOC_ARRAY_LEVEL_STEP; if ((level & ASSOC_ARRAY_KEY_CHUNK_MASK) != 0) goto consider_node; goto jumped; } /* There is a shortcut in the slot corresponding to the index key * segment. We follow the shortcut if its partial index key matches * this leaf's. Otherwise we need to split the shortcut. */ cursor = ptr; follow_shortcut: shortcut = assoc_array_ptr_to_shortcut(cursor); pr_devel("shortcut to %d\n", shortcut->skip_to_level); sc_level = level + ASSOC_ARRAY_LEVEL_STEP; BUG_ON(sc_level > shortcut->skip_to_level); do { /* Check the leaf against the shortcut's index key a word at a * time, trimming the final word (the shortcut stores the index * key completely from the root to the shortcut's target). */ if ((sc_level & ASSOC_ARRAY_KEY_CHUNK_MASK) == 0) segments = ops->get_key_chunk(index_key, sc_level); sc_segments = shortcut->index_key[sc_level >> ASSOC_ARRAY_KEY_CHUNK_SHIFT]; dissimilarity = segments ^ sc_segments; if (round_up(sc_level, ASSOC_ARRAY_KEY_CHUNK_SIZE) > shortcut->skip_to_level) { /* Trim segments that are beyond the shortcut */ int shift = shortcut->skip_to_level & ASSOC_ARRAY_KEY_CHUNK_MASK; dissimilarity &= ~(ULONG_MAX << shift); next_sc_level = shortcut->skip_to_level; } else { next_sc_level = sc_level + ASSOC_ARRAY_KEY_CHUNK_SIZE; next_sc_level = round_down(next_sc_level, ASSOC_ARRAY_KEY_CHUNK_SIZE); } if (dissimilarity != 0) { /* This shortcut points elsewhere */ result->wrong_shortcut.shortcut = shortcut; result->wrong_shortcut.level = level; result->wrong_shortcut.sc_level = sc_level; result->wrong_shortcut.sc_segments = sc_segments; result->wrong_shortcut.dissimilarity = dissimilarity; return assoc_array_walk_found_wrong_shortcut; } sc_level = next_sc_level; } while (sc_level < shortcut->skip_to_level); /* The shortcut matches the leaf's index to this point. */ cursor = READ_ONCE(shortcut->next_node); /* Address dependency. */ if (((level ^ sc_level) & ~ASSOC_ARRAY_KEY_CHUNK_MASK) != 0) { level = sc_level; goto jumped; } else { level = sc_level; goto consider_node; } } /** * assoc_array_find - Find an object by index key * @array: The associative array to search. * @ops: The operations to use. * @index_key: The key to the object. * * Find an object in an associative array by walking through the internal tree * to the node that should contain the object and then searching the leaves * there. NULL is returned if the requested object was not found in the array. * * The caller must hold the RCU read lock or better. */ void *assoc_array_find(const struct assoc_array *array, const struct assoc_array_ops *ops, const void *index_key) { struct assoc_array_walk_result result; const struct assoc_array_node *node; const struct assoc_array_ptr *ptr; const void *leaf; int slot; if (assoc_array_walk(array, ops, index_key, &result) != assoc_array_walk_found_terminal_node) return NULL; node = result.terminal_node.node; /* If the target key is available to us, it's has to be pointed to by * the terminal node. */ for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) { ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */ if (ptr && assoc_array_ptr_is_leaf(ptr)) { /* We need a barrier between the read of the pointer * and dereferencing the pointer - but only if we are * actually going to dereference it. */ leaf = assoc_array_ptr_to_leaf(ptr); if (ops->compare_object(leaf, index_key)) return (void *)leaf; } } return NULL; } /* * Destructively iterate over an associative array. The caller must prevent * other simultaneous accesses. */ static void assoc_array_destroy_subtree(struct assoc_array_ptr *root, const struct assoc_array_ops *ops) { struct assoc_array_shortcut *shortcut; struct assoc_array_node *node; struct assoc_array_ptr *cursor, *parent = NULL; int slot = -1; pr_devel("-->%s()\n", __func__); cursor = root; if (!cursor) { pr_devel("empty\n"); return; } move_to_meta: if (assoc_array_ptr_is_shortcut(cursor)) { /* Descend through a shortcut */ pr_devel("[%d] shortcut\n", slot); BUG_ON(!assoc_array_ptr_is_shortcut(cursor)); shortcut = assoc_array_ptr_to_shortcut(cursor); BUG_ON(shortcut->back_pointer != parent); BUG_ON(slot != -1 && shortcut->parent_slot != slot); parent = cursor; cursor = shortcut->next_node; slot = -1; BUG_ON(!assoc_array_ptr_is_node(cursor)); } pr_devel("[%d] node\n", slot); node = assoc_array_ptr_to_node(cursor); BUG_ON(node->back_pointer != parent); BUG_ON(slot != -1 && node->parent_slot != slot); slot = 0; continue_node: pr_devel("Node %p [back=%p]\n", node, node->back_pointer); for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { struct assoc_array_ptr *ptr = node->slots[slot]; if (!ptr) continue; if (assoc_array_ptr_is_meta(ptr)) { parent = cursor; cursor = ptr; goto move_to_meta; } if (ops) { pr_devel("[%d] free leaf\n", slot); ops->free_object(assoc_array_ptr_to_leaf(ptr)); } } parent = node->back_pointer; slot = node->parent_slot; pr_devel("free node\n"); kfree(node); if (!parent) return; /* Done */ /* Move back up to the parent (may need to free a shortcut on * the way up) */ if (assoc_array_ptr_is_shortcut(parent)) { shortcut = assoc_array_ptr_to_shortcut(parent); BUG_ON(shortcut->next_node != cursor); cursor = parent; parent = shortcut->back_pointer; slot = shortcut->parent_slot; pr_devel("free shortcut\n"); kfree(shortcut); if (!parent) return; BUG_ON(!assoc_array_ptr_is_node(parent)); } /* Ascend to next slot in parent node */ pr_devel("ascend to %p[%d]\n", parent, slot); cursor = parent; node = assoc_array_ptr_to_node(cursor); slot++; goto continue_node; } /** * assoc_array_destroy - Destroy an associative array * @array: The array to destroy. * @ops: The operations to use. * * Discard all metadata and free all objects in an associative array. The * array will be empty and ready to use again upon completion. This function * cannot fail. * * The caller must prevent all other accesses whilst this takes place as no * attempt is made to adjust pointers gracefully to permit RCU readlock-holding * accesses to continue. On the other hand, no memory allocation is required. */ void assoc_array_destroy(struct assoc_array *array, const struct assoc_array_ops *ops) { assoc_array_destroy_subtree(array->root, ops); array->root = NULL; } /* * Handle insertion into an empty tree. */ static bool assoc_array_insert_in_empty_tree(struct assoc_array_edit *edit) { struct assoc_array_node *new_n0; pr_devel("-->%s()\n", __func__); new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL); if (!new_n0) return false; edit->new_meta[0] = assoc_array_node_to_ptr(new_n0); edit->leaf_p = &new_n0->slots[0]; edit->adjust_count_on = new_n0; edit->set[0].ptr = &edit->array->root; edit->set[0].to = assoc_array_node_to_ptr(new_n0); pr_devel("<--%s() = ok [no root]\n", __func__); return true; } /* * Handle insertion into a terminal node. */ static bool assoc_array_insert_into_terminal_node(struct assoc_array_edit *edit, const struct assoc_array_ops *ops, const void *index_key, struct assoc_array_walk_result *result) { struct assoc_array_shortcut *shortcut, *new_s0; struct assoc_array_node *node, *new_n0, *new_n1, *side; struct assoc_array_ptr *ptr; unsigned long dissimilarity, base_seg, blank; size_t keylen; bool have_meta; int level, diff; int slot, next_slot, free_slot, i, j; node = result->terminal_node.node; level = result->terminal_node.level; edit->segment_cache[ASSOC_ARRAY_FAN_OUT] = result->terminal_node.slot; pr_devel("-->%s()\n", __func__); /* We arrived at a node which doesn't have an onward node or shortcut * pointer that we have to follow. This means that (a) the leaf we * want must go here (either by insertion or replacement) or (b) we * need to split this node and insert in one of the fragments. */ free_slot = -1; /* Firstly, we have to check the leaves in this node to see if there's * a matching one we should replace in place. */ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) { ptr = node->slots[i]; if (!ptr) { free_slot = i; continue; } if (assoc_array_ptr_is_leaf(ptr) && ops->compare_object(assoc_array_ptr_to_leaf(ptr), index_key)) { pr_devel("replace in slot %d\n", i); edit->leaf_p = &node->slots[i]; edit->dead_leaf = node->slots[i]; pr_devel("<--%s() = ok [replace]\n", __func__); return true; } } /* If there is a free slot in this node then we can just insert the * leaf here. */ if (free_slot >= 0) { pr_devel("insert in free slot %d\n", free_slot); edit->leaf_p = &node->slots[free_slot]; edit->adjust_count_on = node; pr_devel("<--%s() = ok [insert]\n", __func__); return true; } /* The node has no spare slots - so we're either going to have to split * it or insert another node before it. * * Whatever, we're going to need at least two new nodes - so allocate * those now. We may also need a new shortcut, but we deal with that * when we need it. */ new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL); if (!new_n0) return false; edit->new_meta[0] = assoc_array_node_to_ptr(new_n0); new_n1 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL); if (!new_n1) return false; edit->new_meta[1] = assoc_array_node_to_ptr(new_n1); /* We need to find out how similar the leaves are. */ pr_devel("no spare slots\n"); have_meta = false; for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) { ptr = node->slots[i]; if (assoc_array_ptr_is_meta(ptr)) { edit->segment_cache[i] = 0xff; have_meta = true; continue; } base_seg = ops->get_object_key_chunk( assoc_array_ptr_to_leaf(ptr), level); base_seg >>= level & ASSOC_ARRAY_KEY_CHUNK_MASK; edit->segment_cache[i] = base_seg & ASSOC_ARRAY_FAN_MASK; } if (have_meta) { pr_devel("have meta\n"); goto split_node; } /* The node contains only leaves */ dissimilarity = 0; base_seg = edit->segment_cache[0]; for (i = 1; i < ASSOC_ARRAY_FAN_OUT; i++) dissimilarity |= edit->segment_cache[i] ^ base_seg; pr_devel("only leaves; dissimilarity=%lx\n", dissimilarity); if ((dissimilarity & ASSOC_ARRAY_FAN_MASK) == 0) { /* The old leaves all cluster in the same slot. We will need * to insert a shortcut if the new node wants to cluster with them. */ if ((edit->segment_cache[ASSOC_ARRAY_FAN_OUT] ^ base_seg) == 0) goto all_leaves_cluster_together; /* Otherwise all the old leaves cluster in the same slot, but * the new leaf wants to go into a different slot - so we * create a new node (n0) to hold the new leaf and a pointer to * a new node (n1) holding all the old leaves. * * This can be done by falling through to the node splitting * path. */ pr_devel("present leaves cluster but not new leaf\n"); } split_node: pr_devel("split node\n"); /* We need to split the current node. The node must contain anything * from a single leaf (in the one leaf case, this leaf will cluster * with the new leaf) and the rest meta-pointers, to all leaves, some * of which may cluster. * * It won't contain the case in which all the current leaves plus the * new leaves want to cluster in the same slot. * * We need to expel at least two leaves out of a set consisting of the * leaves in the node and the new leaf. The current meta pointers can * just be copied as they shouldn't cluster with any of the leaves. * * We need a new node (n0) to replace the current one and a new node to * take the expelled nodes (n1). */ edit->set[0].to = assoc_array_node_to_ptr(new_n0); new_n0->back_pointer = node->back_pointer; new_n0->parent_slot = node->parent_slot; new_n1->back_pointer = assoc_array_node_to_ptr(new_n0); new_n1->parent_slot = -1; /* Need to calculate this */ do_split_node: pr_devel("do_split_node\n"); new_n0->nr_leaves_on_branch = node->nr_leaves_on_branch; new_n1->nr_leaves_on_branch = 0; /* Begin by finding two matching leaves. There have to be at least two * that match - even if there are meta pointers - because any leaf that * would match a slot with a meta pointer in it must be somewhere * behind that meta pointer and cannot be here. Further, given N * remaining leaf slots, we now have N+1 leaves to go in them. */ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) { slot = edit->segment_cache[i]; if (slot != 0xff) for (j = i + 1; j < ASSOC_ARRAY_FAN_OUT + 1; j++) if (edit->segment_cache[j] == slot) goto found_slot_for_multiple_occupancy; } found_slot_for_multiple_occupancy: pr_devel("same slot: %x %x [%02x]\n", i, j, slot); BUG_ON(i >= ASSOC_ARRAY_FAN_OUT); BUG_ON(j >= ASSOC_ARRAY_FAN_OUT + 1); BUG_ON(slot >= ASSOC_ARRAY_FAN_OUT); new_n1->parent_slot = slot; /* Metadata pointers cannot change slot */ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) if (assoc_array_ptr_is_meta(node->slots[i])) new_n0->slots[i] = node->slots[i]; else new_n0->slots[i] = NULL; BUG_ON(new_n0->slots[slot] != NULL); new_n0->slots[slot] = assoc_array_node_to_ptr(new_n1); /* Filter the leaf pointers between the new nodes */ free_slot = -1; next_slot = 0; for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) { if (assoc_array_ptr_is_meta(node->slots[i])) continue; if (edit->segment_cache[i] == slot) { new_n1->slots[next_slot++] = node->slots[i]; new_n1->nr_leaves_on_branch++; } else { do { free_slot++; } while (new_n0->slots[free_slot] != NULL); new_n0->slots[free_slot] = node->slots[i]; } } pr_devel("filtered: f=%x n=%x\n", free_slot, next_slot); if (edit->segment_cache[ASSOC_ARRAY_FAN_OUT] != slot) { do { free_slot++; } while (new_n0->slots[free_slot] != NULL); edit->leaf_p = &new_n0->slots[free_slot]; edit->adjust_count_on = new_n0; } else { edit->leaf_p = &new_n1->slots[next_slot++]; edit->adjust_count_on = new_n1; } BUG_ON(next_slot <= 1); edit->set_backpointers_to = assoc_array_node_to_ptr(new_n0); for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) { if (edit->segment_cache[i] == 0xff) { ptr = node->slots[i]; BUG_ON(assoc_array_ptr_is_leaf(ptr)); if (assoc_array_ptr_is_node(ptr)) { side = assoc_array_ptr_to_node(ptr); edit->set_backpointers[i] = &side->back_pointer; } else { shortcut = assoc_array_ptr_to_shortcut(ptr); edit->set_backpointers[i] = &shortcut->back_pointer; } } } ptr = node->back_pointer; if (!ptr) edit->set[0].ptr = &edit->array->root; else if (assoc_array_ptr_is_node(ptr)) edit->set[0].ptr = &assoc_array_ptr_to_node(ptr)->slots[node->parent_slot]; else edit->set[0].ptr = &assoc_array_ptr_to_shortcut(ptr)->next_node; edit->excised_meta[0] = assoc_array_node_to_ptr(node); pr_devel("<--%s() = ok [split node]\n", __func__); return true; all_leaves_cluster_together: /* All the leaves, new and old, want to cluster together in this node * in the same slot, so we have to replace this node with a shortcut to * skip over the identical parts of the key and then place a pair of * nodes, one inside the other, at the end of the shortcut and * distribute the keys between them. * * Firstly we need to work out where the leaves start diverging as a * bit position into their keys so that we know how big the shortcut * needs to be. * * We only need to make a single pass of N of the N+1 leaves because if * any keys differ between themselves at bit X then at least one of * them must also differ with the base key at bit X or before. */ pr_devel("all leaves cluster together\n"); diff = INT_MAX; for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) { int x = ops->diff_objects(assoc_array_ptr_to_leaf(node->slots[i]), index_key); if (x < diff) { BUG_ON(x < 0); diff = x; } } BUG_ON(diff == INT_MAX); BUG_ON(diff < level + ASSOC_ARRAY_LEVEL_STEP); keylen = round_up(diff, ASSOC_ARRAY_KEY_CHUNK_SIZE); keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT; new_s0 = kzalloc(struct_size(new_s0, index_key, keylen), GFP_KERNEL); if (!new_s0) return false; edit->new_meta[2] = assoc_array_shortcut_to_ptr(new_s0); edit->set[0].to = assoc_array_shortcut_to_ptr(new_s0); new_s0->back_pointer = node->back_pointer; new_s0->parent_slot = node->parent_slot; new_s0->next_node = assoc_array_node_to_ptr(new_n0); new_n0->back_pointer = assoc_array_shortcut_to_ptr(new_s0); new_n0->parent_slot = 0; new_n1->back_pointer = assoc_array_node_to_ptr(new_n0); new_n1->parent_slot = -1; /* Need to calculate this */ new_s0->skip_to_level = level = diff & ~ASSOC_ARRAY_LEVEL_STEP_MASK; pr_devel("skip_to_level = %d [diff %d]\n", level, diff); BUG_ON(level <= 0); for (i = 0; i < keylen; i++) new_s0->index_key[i] = ops->get_key_chunk(index_key, i * ASSOC_ARRAY_KEY_CHUNK_SIZE); if (level & ASSOC_ARRAY_KEY_CHUNK_MASK) { blank = ULONG_MAX << (level & ASSOC_ARRAY_KEY_CHUNK_MASK); pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, level, blank); new_s0->index_key[keylen - 1] &= ~blank; } /* This now reduces to a node splitting exercise for which we'll need * to regenerate the disparity table. */ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) { ptr = node->slots[i]; base_seg = ops->get_object_key_chunk(assoc_array_ptr_to_leaf(ptr), level); base_seg >>= level & ASSOC_ARRAY_KEY_CHUNK_MASK; edit->segment_cache[i] = base_seg & ASSOC_ARRAY_FAN_MASK; } base_seg = ops->get_key_chunk(index_key, level); base_seg >>= level & ASSOC_ARRAY_KEY_CHUNK_MASK; edit->segment_cache[ASSOC_ARRAY_FAN_OUT] = base_seg & ASSOC_ARRAY_FAN_MASK; goto do_split_node; } /* * Handle insertion into the middle of a shortcut. */ static bool assoc_array_insert_mid_shortcut(struct assoc_array_edit *edit, const struct assoc_array_ops *ops, struct assoc_array_walk_result *result) { struct assoc_array_shortcut *shortcut, *new_s0, *new_s1; struct assoc_array_node *node, *new_n0, *side; unsigned long sc_segments, dissimilarity, blank; size_t keylen; int level, sc_level, diff; int sc_slot; shortcut = result->wrong_shortcut.shortcut; level = result->wrong_shortcut.level; sc_level = result->wrong_shortcut.sc_level; sc_segments = result->wrong_shortcut.sc_segments; dissimilarity = result->wrong_shortcut.dissimilarity; pr_devel("-->%s(ix=%d dis=%lx scix=%d)\n", __func__, level, dissimilarity, sc_level); /* We need to split a shortcut and insert a node between the two * pieces. Zero-length pieces will be dispensed with entirely. * * First of all, we need to find out in which level the first * difference was. */ diff = __ffs(dissimilarity); diff &= ~ASSOC_ARRAY_LEVEL_STEP_MASK; diff += sc_level & ~ASSOC_ARRAY_KEY_CHUNK_MASK; pr_devel("diff=%d\n", diff); if (!shortcut->back_pointer) { edit->set[0].ptr = &edit->array->root; } else if (assoc_array_ptr_is_node(shortcut->back_pointer)) { node = assoc_array_ptr_to_node(shortcut->back_pointer); edit->set[0].ptr = &node->slots[shortcut->parent_slot]; } else { BUG(); } edit->excised_meta[0] = assoc_array_shortcut_to_ptr(shortcut); /* Create a new node now since we're going to need it anyway */ new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL); if (!new_n0) return false; edit->new_meta[0] = assoc_array_node_to_ptr(new_n0); edit->adjust_count_on = new_n0; /* Insert a new shortcut before the new node if this segment isn't of * zero length - otherwise we just connect the new node directly to the * parent. */ level += ASSOC_ARRAY_LEVEL_STEP; if (diff > level) { pr_devel("pre-shortcut %d...%d\n", level, diff); keylen = round_up(diff, ASSOC_ARRAY_KEY_CHUNK_SIZE); keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT; new_s0 = kzalloc(struct_size(new_s0, index_key, keylen), GFP_KERNEL); if (!new_s0) return false; edit->new_meta[1] = assoc_array_shortcut_to_ptr(new_s0); edit->set[0].to = assoc_array_shortcut_to_ptr(new_s0); new_s0->back_pointer = shortcut->back_pointer; new_s0->parent_slot = shortcut->parent_slot; new_s0->next_node = assoc_array_node_to_ptr(new_n0); new_s0->skip_to_level = diff; new_n0->back_pointer = assoc_array_shortcut_to_ptr(new_s0); new_n0->parent_slot = 0; memcpy(new_s0->index_key, shortcut->index_key, flex_array_size(new_s0, index_key, keylen)); blank = ULONG_MAX << (diff & ASSOC_ARRAY_KEY_CHUNK_MASK); pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, diff, blank); new_s0->index_key[keylen - 1] &= ~blank; } else { pr_devel("no pre-shortcut\n"); edit->set[0].to = assoc_array_node_to_ptr(new_n0); new_n0->back_pointer = shortcut->back_pointer; new_n0->parent_slot = shortcut->parent_slot; } side = assoc_array_ptr_to_node(shortcut->next_node); new_n0->nr_leaves_on_branch = side->nr_leaves_on_branch; /* We need to know which slot in the new node is going to take a * metadata pointer. */ sc_slot = sc_segments >> (diff & ASSOC_ARRAY_KEY_CHUNK_MASK); sc_slot &= ASSOC_ARRAY_FAN_MASK; pr_devel("new slot %lx >> %d -> %d\n", sc_segments, diff & ASSOC_ARRAY_KEY_CHUNK_MASK, sc_slot); /* Determine whether we need to follow the new node with a replacement * for the current shortcut. We could in theory reuse the current * shortcut if its parent slot number doesn't change - but that's a * 1-in-16 chance so not worth expending the code upon. */ level = diff + ASSOC_ARRAY_LEVEL_STEP; if (level < shortcut->skip_to_level) { pr_devel("post-shortcut %d...%d\n", level, shortcut->skip_to_level); keylen = round_up(shortcut->skip_to_level, ASSOC_ARRAY_KEY_CHUNK_SIZE); keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT; new_s1 = kzalloc(struct_size(new_s1, index_key, keylen), GFP_KERNEL); if (!new_s1) return false; edit->new_meta[2] = assoc_array_shortcut_to_ptr(new_s1); new_s1->back_pointer = assoc_array_node_to_ptr(new_n0); new_s1->parent_slot = sc_slot; new_s1->next_node = shortcut->next_node; new_s1->skip_to_level = shortcut->skip_to_level; new_n0->slots[sc_slot] = assoc_array_shortcut_to_ptr(new_s1); memcpy(new_s1->index_key, shortcut->index_key, flex_array_size(new_s1, index_key, keylen)); edit->set[1].ptr = &side->back_pointer; edit->set[1].to = assoc_array_shortcut_to_ptr(new_s1); } else { pr_devel("no post-shortcut\n"); /* We don't have to replace the pointed-to node as long as we * use memory barriers to make sure the parent slot number is * changed before the back pointer (the parent slot number is * irrelevant to the old parent shortcut). */ new_n0->slots[sc_slot] = shortcut->next_node; edit->set_parent_slot[0].p = &side->parent_slot; edit->set_parent_slot[0].to = sc_slot; edit->set[1].ptr = &side->back_pointer; edit->set[1].to = assoc_array_node_to_ptr(new_n0); } /* Install the new leaf in a spare slot in the new node. */ if (sc_slot == 0) edit->leaf_p = &new_n0->slots[1]; else edit->leaf_p = &new_n0->slots[0]; pr_devel("<--%s() = ok [split shortcut]\n", __func__); return true; } /** * assoc_array_insert - Script insertion of an object into an associative array * @array: The array to insert into. * @ops: The operations to use. * @index_key: The key to insert at. * @object: The object to insert. * * Precalculate and preallocate a script for the insertion or replacement of an * object in an associative array. This results in an edit script that can * either be applied or cancelled. * * The function returns a pointer to an edit script or -ENOMEM. * * The caller should lock against other modifications and must continue to hold * the lock until assoc_array_apply_edit() has been called. * * Accesses to the tree may take place concurrently with this function, * provided they hold the RCU read lock. */ struct assoc_array_edit *assoc_array_insert(struct assoc_array *array, const struct assoc_array_ops *ops, const void *index_key, void *object) { struct assoc_array_walk_result result; struct assoc_array_edit *edit; pr_devel("-->%s()\n", __func__); /* The leaf pointer we're given must not have the bottom bit set as we * use those for type-marking the pointer. NULL pointers are also not * allowed as they indicate an empty slot but we have to allow them * here as they can be updated later. */ BUG_ON(assoc_array_ptr_is_meta(object)); edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL); if (!edit) return ERR_PTR(-ENOMEM); edit->array = array; edit->ops = ops; edit->leaf = assoc_array_leaf_to_ptr(object); edit->adjust_count_by = 1; switch (assoc_array_walk(array, ops, index_key, &result)) { case assoc_array_walk_tree_empty: /* Allocate a root node if there isn't one yet */ if (!assoc_array_insert_in_empty_tree(edit)) goto enomem; return edit; case assoc_array_walk_found_terminal_node: /* We found a node that doesn't have a node/shortcut pointer in * the slot corresponding to the index key that we have to * follow. */ if (!assoc_array_insert_into_terminal_node(edit, ops, index_key, &result)) goto enomem; return edit; case assoc_array_walk_found_wrong_shortcut: /* We found a shortcut that didn't match our key in a slot we * needed to follow. */ if (!assoc_array_insert_mid_shortcut(edit, ops, &result)) goto enomem; return edit; } enomem: /* Clean up after an out of memory error */ pr_devel("enomem\n"); assoc_array_cancel_edit(edit); return ERR_PTR(-ENOMEM); } /** * assoc_array_insert_set_object - Set the new object pointer in an edit script * @edit: The edit script to modify. * @object: The object pointer to set. * * Change the object to be inserted in an edit script. The object pointed to * by the old object is not freed. This must be done prior to applying the * script. */ void assoc_array_insert_set_object(struct assoc_array_edit *edit, void *object) { BUG_ON(!object); edit->leaf = assoc_array_leaf_to_ptr(object); } struct assoc_array_delete_collapse_context { struct assoc_array_node *node; const void *skip_leaf; int slot; }; /* * Subtree collapse to node iterator. */ static int assoc_array_delete_collapse_iterator(const void *leaf, void *iterator_data) { struct assoc_array_delete_collapse_context *collapse = iterator_data; if (leaf == collapse->skip_leaf) return 0; BUG_ON(collapse->slot >= ASSOC_ARRAY_FAN_OUT); collapse->node->slots[collapse->slot++] = assoc_array_leaf_to_ptr(leaf); return 0; } /** * assoc_array_delete - Script deletion of an object from an associative array * @array: The array to search. * @ops: The operations to use. * @index_key: The key to the object. * * Precalculate and preallocate a script for the deletion of an object from an * associative array. This results in an edit script that can either be * applied or cancelled. * * The function returns a pointer to an edit script if the object was found, * NULL if the object was not found or -ENOMEM. * * The caller should lock against other modifications and must continue to hold * the lock until assoc_array_apply_edit() has been called. * * Accesses to the tree may take place concurrently with this function, * provided they hold the RCU read lock. */ struct assoc_array_edit *assoc_array_delete(struct assoc_array *array, const struct assoc_array_ops *ops, const void *index_key) { struct assoc_array_delete_collapse_context collapse; struct assoc_array_walk_result result; struct assoc_array_node *node, *new_n0; struct assoc_array_edit *edit; struct assoc_array_ptr *ptr; bool has_meta; int slot, i; pr_devel("-->%s()\n", __func__); edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL); if (!edit) return ERR_PTR(-ENOMEM); edit->array = array; edit->ops = ops; edit->adjust_count_by = -1; switch (assoc_array_walk(array, ops, index_key, &result)) { case assoc_array_walk_found_terminal_node: /* We found a node that should contain the leaf we've been * asked to remove - *if* it's in the tree. */ pr_devel("terminal_node\n"); node = result.terminal_node.node; for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) { ptr = node->slots[slot]; if (ptr && assoc_array_ptr_is_leaf(ptr) && ops->compare_object(assoc_array_ptr_to_leaf(ptr), index_key)) goto found_leaf; } fallthrough; case assoc_array_walk_tree_empty: case assoc_array_walk_found_wrong_shortcut: default: assoc_array_cancel_edit(edit); pr_devel("not found\n"); return NULL; } found_leaf: BUG_ON(array->nr_leaves_on_tree <= 0); /* In the simplest form of deletion we just clear the slot and release * the leaf after a suitable interval. */ edit->dead_leaf = node->slots[slot]; edit->set[0].ptr = &node->slots[slot]; edit->set[0].to = NULL; edit->adjust_count_on = node; /* If that concludes erasure of the last leaf, then delete the entire * internal array. */ if (array->nr_leaves_on_tree == 1) { edit->set[1].ptr = &array->root; edit->set[1].to = NULL; edit->adjust_count_on = NULL; edit->excised_subtree = array->root; pr_devel("all gone\n"); return edit; } /* However, we'd also like to clear up some metadata blocks if we * possibly can. * * We go for a simple algorithm of: if this node has FAN_OUT or fewer * leaves in it, then attempt to collapse it - and attempt to * recursively collapse up the tree. * * We could also try and collapse in partially filled subtrees to take * up space in this node. */ if (node->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT + 1) { struct assoc_array_node *parent, *grandparent; struct assoc_array_ptr *ptr; /* First of all, we need to know if this node has metadata so * that we don't try collapsing if all the leaves are already * here. */ has_meta = false; for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) { ptr = node->slots[i]; if (assoc_array_ptr_is_meta(ptr)) { has_meta = true; break; } } pr_devel("leaves: %ld [m=%d]\n", node->nr_leaves_on_branch - 1, has_meta); /* Look further up the tree to see if we can collapse this node * into a more proximal node too. */ parent = node; collapse_up: pr_devel("collapse subtree: %ld\n", parent->nr_leaves_on_branch); ptr = parent->back_pointer; if (!ptr) goto do_collapse; if (assoc_array_ptr_is_shortcut(ptr)) { struct assoc_array_shortcut *s = assoc_array_ptr_to_shortcut(ptr); ptr = s->back_pointer; if (!ptr) goto do_collapse; } grandparent = assoc_array_ptr_to_node(ptr); if (grandparent->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT + 1) { parent = grandparent; goto collapse_up; } do_collapse: /* There's no point collapsing if the original node has no meta * pointers to discard and if we didn't merge into one of that * node's ancestry. */ if (has_meta || parent != node) { node = parent; /* Create a new node to collapse into */ new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL); if (!new_n0) goto enomem; edit->new_meta[0] = assoc_array_node_to_ptr(new_n0); new_n0->back_pointer = node->back_pointer; new_n0->parent_slot = node->parent_slot; new_n0->nr_leaves_on_branch = node->nr_leaves_on_branch; edit->adjust_count_on = new_n0; collapse.node = new_n0; collapse.skip_leaf = assoc_array_ptr_to_leaf(edit->dead_leaf); collapse.slot = 0; assoc_array_subtree_iterate(assoc_array_node_to_ptr(node), node->back_pointer, assoc_array_delete_collapse_iterator, &collapse); pr_devel("collapsed %d,%lu\n", collapse.slot, new_n0->nr_leaves_on_branch); BUG_ON(collapse.slot != new_n0->nr_leaves_on_branch - 1); if (!node->back_pointer) { edit->set[1].ptr = &array->root; } else if (assoc_array_ptr_is_leaf(node->back_pointer)) { BUG(); } else if (assoc_array_ptr_is_node(node->back_pointer)) { struct assoc_array_node *p = assoc_array_ptr_to_node(node->back_pointer); edit->set[1].ptr = &p->slots[node->parent_slot]; } else if (assoc_array_ptr_is_shortcut(node->back_pointer)) { struct assoc_array_shortcut *s = assoc_array_ptr_to_shortcut(node->back_pointer); edit->set[1].ptr = &s->next_node; } edit->set[1].to = assoc_array_node_to_ptr(new_n0); edit->excised_subtree = assoc_array_node_to_ptr(node); } } return edit; enomem: /* Clean up after an out of memory error */ pr_devel("enomem\n"); assoc_array_cancel_edit(edit); return ERR_PTR(-ENOMEM); } /** * assoc_array_clear - Script deletion of all objects from an associative array * @array: The array to clear. * @ops: The operations to use. * * Precalculate and preallocate a script for the deletion of all the objects * from an associative array. This results in an edit script that can either * be applied or cancelled. * * The function returns a pointer to an edit script if there are objects to be * deleted, NULL if there are no objects in the array or -ENOMEM. * * The caller should lock against other modifications and must continue to hold * the lock until assoc_array_apply_edit() has been called. * * Accesses to the tree may take place concurrently with this function, * provided they hold the RCU read lock. */ struct assoc_array_edit *assoc_array_clear(struct assoc_array *array, const struct assoc_array_ops *ops) { struct assoc_array_edit *edit; pr_devel("-->%s()\n", __func__); if (!array->root) return NULL; edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL); if (!edit) return ERR_PTR(-ENOMEM); edit->array = array; edit->ops = ops; edit->set[1].ptr = &array->root; edit->set[1].to = NULL; edit->excised_subtree = array->root; edit->ops_for_excised_subtree = ops; pr_devel("all gone\n"); return edit; } /* * Handle the deferred destruction after an applied edit. */ static void assoc_array_rcu_cleanup(struct rcu_head *head) { struct assoc_array_edit *edit = container_of(head, struct assoc_array_edit, rcu); int i; pr_devel("-->%s()\n", __func__); if (edit->dead_leaf) edit->ops->free_object(assoc_array_ptr_to_leaf(edit->dead_leaf)); for (i = 0; i < ARRAY_SIZE(edit->excised_meta); i++) if (edit->excised_meta[i]) kfree(assoc_array_ptr_to_node(edit->excised_meta[i])); if (edit->excised_subtree) { BUG_ON(assoc_array_ptr_is_leaf(edit->excised_subtree)); if (assoc_array_ptr_is_node(edit->excised_subtree)) { struct assoc_array_node *n = assoc_array_ptr_to_node(edit->excised_subtree); n->back_pointer = NULL; } else { struct assoc_array_shortcut *s = assoc_array_ptr_to_shortcut(edit->excised_subtree); s->back_pointer = NULL; } assoc_array_destroy_subtree(edit->excised_subtree, edit->ops_for_excised_subtree); } kfree(edit); } /** * assoc_array_apply_edit - Apply an edit script to an associative array * @edit: The script to apply. * * Apply an edit script to an associative array to effect an insertion, * deletion or clearance. As the edit script includes preallocated memory, * this is guaranteed not to fail. * * The edit script, dead objects and dead metadata will be scheduled for * destruction after an RCU grace period to permit those doing read-only * accesses on the array to continue to do so under the RCU read lock whilst * the edit is taking place. */ void assoc_array_apply_edit(struct assoc_array_edit *edit) { struct assoc_array_shortcut *shortcut; struct assoc_array_node *node; struct assoc_array_ptr *ptr; int i; pr_devel("-->%s()\n", __func__); smp_wmb(); if (edit->leaf_p) *edit->leaf_p = edit->leaf; smp_wmb(); for (i = 0; i < ARRAY_SIZE(edit->set_parent_slot); i++) if (edit->set_parent_slot[i].p) *edit->set_parent_slot[i].p = edit->set_parent_slot[i].to; smp_wmb(); for (i = 0; i < ARRAY_SIZE(edit->set_backpointers); i++) if (edit->set_backpointers[i]) *edit->set_backpointers[i] = edit->set_backpointers_to; smp_wmb(); for (i = 0; i < ARRAY_SIZE(edit->set); i++) if (edit->set[i].ptr) *edit->set[i].ptr = edit->set[i].to; if (edit->array->root == NULL) { edit->array->nr_leaves_on_tree = 0; } else if (edit->adjust_count_on) { node = edit->adjust_count_on; for (;;) { node->nr_leaves_on_branch += edit->adjust_count_by; ptr = node->back_pointer; if (!ptr) break; if (assoc_array_ptr_is_shortcut(ptr)) { shortcut = assoc_array_ptr_to_shortcut(ptr); ptr = shortcut->back_pointer; if (!ptr) break; } BUG_ON(!assoc_array_ptr_is_node(ptr)); node = assoc_array_ptr_to_node(ptr); } edit->array->nr_leaves_on_tree += edit->adjust_count_by; } call_rcu(&edit->rcu, assoc_array_rcu_cleanup); } /** * assoc_array_cancel_edit - Discard an edit script. * @edit: The script to discard. * * Free an edit script and all the preallocated data it holds without making * any changes to the associative array it was intended for. * * NOTE! In the case of an insertion script, this does _not_ release the leaf * that was to be inserted. That is left to the caller. */ void assoc_array_cancel_edit(struct assoc_array_edit *edit) { struct assoc_array_ptr *ptr; int i; pr_devel("-->%s()\n", __func__); /* Clean up after an out of memory error */ for (i = 0; i < ARRAY_SIZE(edit->new_meta); i++) { ptr = edit->new_meta[i]; if (ptr) { if (assoc_array_ptr_is_node(ptr)) kfree(assoc_array_ptr_to_node(ptr)); else kfree(assoc_array_ptr_to_shortcut(ptr)); } } kfree(edit); } /** * assoc_array_gc - Garbage collect an associative array. * @array: The array to clean. * @ops: The operations to use. * @iterator: A callback function to pass judgement on each object. * @iterator_data: Private data for the callback function. * * Collect garbage from an associative array and pack down the internal tree to * save memory. * * The iterator function is asked to pass judgement upon each object in the * array. If it returns false, the object is discard and if it returns true, * the object is kept. If it returns true, it must increment the object's * usage count (or whatever it needs to do to retain it) before returning. * * This function returns 0 if successful or -ENOMEM if out of memory. In the * latter case, the array is not changed. * * The caller should lock against other modifications and must continue to hold * the lock until assoc_array_apply_edit() has been called. * * Accesses to the tree may take place concurrently with this function, * provided they hold the RCU read lock. */ int assoc_array_gc(struct assoc_array *array, const struct assoc_array_ops *ops, bool (*iterator)(void *object, void *iterator_data), void *iterator_data) { struct assoc_array_shortcut *shortcut, *new_s; struct assoc_array_node *node, *new_n; struct assoc_array_edit *edit; struct assoc_array_ptr *cursor, *ptr; struct assoc_array_ptr *new_root, *new_parent, **new_ptr_pp; unsigned long nr_leaves_on_tree; bool retained; int keylen, slot, nr_free, next_slot, i; pr_devel("-->%s()\n", __func__); if (!array->root) return 0; edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL); if (!edit) return -ENOMEM; edit->array = array; edit->ops = ops; edit->ops_for_excised_subtree = ops; edit->set[0].ptr = &array->root; edit->excised_subtree = array->root; new_root = new_parent = NULL; new_ptr_pp = &new_root; cursor = array->root; descend: /* If this point is a shortcut, then we need to duplicate it and * advance the target cursor. */ if (assoc_array_ptr_is_shortcut(cursor)) { shortcut = assoc_array_ptr_to_shortcut(cursor); keylen = round_up(shortcut->skip_to_level, ASSOC_ARRAY_KEY_CHUNK_SIZE); keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT; new_s = kmalloc(struct_size(new_s, index_key, keylen), GFP_KERNEL); if (!new_s) goto enomem; pr_devel("dup shortcut %p -> %p\n", shortcut, new_s); memcpy(new_s, shortcut, struct_size(new_s, index_key, keylen)); new_s->back_pointer = new_parent; new_s->parent_slot = shortcut->parent_slot; *new_ptr_pp = new_parent = assoc_array_shortcut_to_ptr(new_s); new_ptr_pp = &new_s->next_node; cursor = shortcut->next_node; } /* Duplicate the node at this position */ node = assoc_array_ptr_to_node(cursor); new_n = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL); if (!new_n) goto enomem; pr_devel("dup node %p -> %p\n", node, new_n); new_n->back_pointer = new_parent; new_n->parent_slot = node->parent_slot; *new_ptr_pp = new_parent = assoc_array_node_to_ptr(new_n); new_ptr_pp = NULL; slot = 0; continue_node: /* Filter across any leaves and gc any subtrees */ for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { ptr = node->slots[slot]; if (!ptr) continue; if (assoc_array_ptr_is_leaf(ptr)) { if (iterator(assoc_array_ptr_to_leaf(ptr), iterator_data)) /* The iterator will have done any reference * counting on the object for us. */ new_n->slots[slot] = ptr; continue; } new_ptr_pp = &new_n->slots[slot]; cursor = ptr; goto descend; } retry_compress: pr_devel("-- compress node %p --\n", new_n); /* Count up the number of empty slots in this node and work out the * subtree leaf count. */ new_n->nr_leaves_on_branch = 0; nr_free = 0; for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) { ptr = new_n->slots[slot]; if (!ptr) nr_free++; else if (assoc_array_ptr_is_leaf(ptr)) new_n->nr_leaves_on_branch++; } pr_devel("free=%d, leaves=%lu\n", nr_free, new_n->nr_leaves_on_branch); /* See what we can fold in */ retained = false; next_slot = 0; for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) { struct assoc_array_shortcut *s; struct assoc_array_node *child; ptr = new_n->slots[slot]; if (!ptr || assoc_array_ptr_is_leaf(ptr)) continue; s = NULL; if (assoc_array_ptr_is_shortcut(ptr)) { s = assoc_array_ptr_to_shortcut(ptr); ptr = s->next_node; } child = assoc_array_ptr_to_node(ptr); new_n->nr_leaves_on_branch += child->nr_leaves_on_branch; if (child->nr_leaves_on_branch <= nr_free + 1) { /* Fold the child node into this one */ pr_devel("[%d] fold node %lu/%d [nx %d]\n", slot, child->nr_leaves_on_branch, nr_free + 1, next_slot); /* We would already have reaped an intervening shortcut * on the way back up the tree. */ BUG_ON(s); new_n->slots[slot] = NULL; nr_free++; if (slot < next_slot) next_slot = slot; for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) { struct assoc_array_ptr *p = child->slots[i]; if (!p) continue; BUG_ON(assoc_array_ptr_is_meta(p)); while (new_n->slots[next_slot]) next_slot++; BUG_ON(next_slot >= ASSOC_ARRAY_FAN_OUT); new_n->slots[next_slot++] = p; nr_free--; } kfree(child); } else { pr_devel("[%d] retain node %lu/%d [nx %d]\n", slot, child->nr_leaves_on_branch, nr_free + 1, next_slot); retained = true; } } if (retained && new_n->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT) { pr_devel("internal nodes remain despite enough space, retrying\n"); goto retry_compress; } pr_devel("after: %lu\n", new_n->nr_leaves_on_branch); nr_leaves_on_tree = new_n->nr_leaves_on_branch; /* Excise this node if it is singly occupied by a shortcut */ if (nr_free == ASSOC_ARRAY_FAN_OUT - 1) { for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) if ((ptr = new_n->slots[slot])) break; if (assoc_array_ptr_is_meta(ptr) && assoc_array_ptr_is_shortcut(ptr)) { pr_devel("excise node %p with 1 shortcut\n", new_n); new_s = assoc_array_ptr_to_shortcut(ptr); new_parent = new_n->back_pointer; slot = new_n->parent_slot; kfree(new_n); if (!new_parent) { new_s->back_pointer = NULL; new_s->parent_slot = 0; new_root = ptr; goto gc_complete; } if (assoc_array_ptr_is_shortcut(new_parent)) { /* We can discard any preceding shortcut also */ struct assoc_array_shortcut *s = assoc_array_ptr_to_shortcut(new_parent); pr_devel("excise preceding shortcut\n"); new_parent = new_s->back_pointer = s->back_pointer; slot = new_s->parent_slot = s->parent_slot; kfree(s); if (!new_parent) { new_s->back_pointer = NULL; new_s->parent_slot = 0; new_root = ptr; goto gc_complete; } } new_s->back_pointer = new_parent; new_s->parent_slot = slot; new_n = assoc_array_ptr_to_node(new_parent); new_n->slots[slot] = ptr; goto ascend_old_tree; } } /* Excise any shortcuts we might encounter that point to nodes that * only contain leaves. */ ptr = new_n->back_pointer; if (!ptr) goto gc_complete; if (assoc_array_ptr_is_shortcut(ptr)) { new_s = assoc_array_ptr_to_shortcut(ptr); new_parent = new_s->back_pointer; slot = new_s->parent_slot; if (new_n->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT) { struct assoc_array_node *n; pr_devel("excise shortcut\n"); new_n->back_pointer = new_parent; new_n->parent_slot = slot; kfree(new_s); if (!new_parent) { new_root = assoc_array_node_to_ptr(new_n); goto gc_complete; } n = assoc_array_ptr_to_node(new_parent); n->slots[slot] = assoc_array_node_to_ptr(new_n); } } else { new_parent = ptr; } new_n = assoc_array_ptr_to_node(new_parent); ascend_old_tree: ptr = node->back_pointer; if (assoc_array_ptr_is_shortcut(ptr)) { shortcut = assoc_array_ptr_to_shortcut(ptr); slot = shortcut->parent_slot; cursor = shortcut->back_pointer; if (!cursor) goto gc_complete; } else { slot = node->parent_slot; cursor = ptr; } BUG_ON(!cursor); node = assoc_array_ptr_to_node(cursor); slot++; goto continue_node; gc_complete: edit->set[0].to = new_root; assoc_array_apply_edit(edit); array->nr_leaves_on_tree = nr_leaves_on_tree; return 0; enomem: pr_devel("enomem\n"); assoc_array_destroy_subtree(new_root, edit->ops); kfree(edit); return -ENOMEM; } |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/affs/bitmap.c * * (c) 1996 Hans-Joachim Widmaier * * bitmap.c contains the code that handles all bitmap related stuff - * block allocation, deallocation, calculation of free space. */ #include <linux/slab.h> #include "affs.h" u32 affs_count_free_blocks(struct super_block *sb) { struct affs_bm_info *bm; u32 free; int i; pr_debug("%s()\n", __func__); if (sb_rdonly(sb)) return 0; mutex_lock(&AFFS_SB(sb)->s_bmlock); bm = AFFS_SB(sb)->s_bitmap; free = 0; for (i = AFFS_SB(sb)->s_bmap_count; i > 0; bm++, i--) free += bm->bm_free; mutex_unlock(&AFFS_SB(sb)->s_bmlock); return free; } void affs_free_block(struct super_block *sb, u32 block) { struct affs_sb_info *sbi = AFFS_SB(sb); struct affs_bm_info *bm; struct buffer_head *bh; u32 blk, bmap, bit, mask, tmp; __be32 *data; pr_debug("%s(%u)\n", __func__, block); if (block > sbi->s_partition_size) goto err_range; blk = block - sbi->s_reserved; bmap = blk / sbi->s_bmap_bits; bit = blk % sbi->s_bmap_bits; bm = &sbi->s_bitmap[bmap]; mutex_lock(&sbi->s_bmlock); bh = sbi->s_bmap_bh; if (sbi->s_last_bmap != bmap) { affs_brelse(bh); bh = affs_bread(sb, bm->bm_key); if (!bh) goto err_bh_read; sbi->s_bmap_bh = bh; sbi->s_last_bmap = bmap; } mask = 1 << (bit & 31); data = (__be32 *)bh->b_data + bit / 32 + 1; /* mark block free */ tmp = be32_to_cpu(*data); if (tmp & mask) goto err_free; *data = cpu_to_be32(tmp | mask); /* fix checksum */ tmp = be32_to_cpu(*(__be32 *)bh->b_data); *(__be32 *)bh->b_data = cpu_to_be32(tmp - mask); mark_buffer_dirty(bh); affs_mark_sb_dirty(sb); bm->bm_free++; mutex_unlock(&sbi->s_bmlock); return; err_free: affs_warning(sb,"affs_free_block","Trying to free block %u which is already free", block); mutex_unlock(&sbi->s_bmlock); return; err_bh_read: affs_error(sb,"affs_free_block","Cannot read bitmap block %u", bm->bm_key); sbi->s_bmap_bh = NULL; sbi->s_last_bmap = ~0; mutex_unlock(&sbi->s_bmlock); return; err_range: affs_error(sb, "affs_free_block","Block %u outside partition", block); } /* * Allocate a block in the given allocation zone. * Since we have to byte-swap the bitmap on little-endian * machines, this is rather expensive. Therefore we will * preallocate up to 16 blocks from the same word, if * possible. We are not doing preallocations in the * header zone, though. */ u32 affs_alloc_block(struct inode *inode, u32 goal) { struct super_block *sb; struct affs_sb_info *sbi; struct affs_bm_info *bm; struct buffer_head *bh; __be32 *data, *enddata; u32 blk, bmap, bit, mask, mask2, tmp; int i; sb = inode->i_sb; sbi = AFFS_SB(sb); pr_debug("balloc(inode=%lu,goal=%u): ", inode->i_ino, goal); if (AFFS_I(inode)->i_pa_cnt) { pr_debug("%d\n", AFFS_I(inode)->i_lastalloc+1); AFFS_I(inode)->i_pa_cnt--; return ++AFFS_I(inode)->i_lastalloc; } if (!goal || goal > sbi->s_partition_size) { if (goal) affs_warning(sb, "affs_balloc", "invalid goal %d", goal); //if (!AFFS_I(inode)->i_last_block) // affs_warning(sb, "affs_balloc", "no last alloc block"); goal = sbi->s_reserved; } blk = goal - sbi->s_reserved; bmap = blk / sbi->s_bmap_bits; bm = &sbi->s_bitmap[bmap]; mutex_lock(&sbi->s_bmlock); if (bm->bm_free) goto find_bmap_bit; find_bmap: /* search for the next bmap buffer with free bits */ i = sbi->s_bmap_count; do { if (--i < 0) goto err_full; bmap++; bm++; if (bmap < sbi->s_bmap_count) continue; /* restart search at zero */ bmap = 0; bm = sbi->s_bitmap; } while (!bm->bm_free); blk = bmap * sbi->s_bmap_bits; find_bmap_bit: bh = sbi->s_bmap_bh; if (sbi->s_last_bmap != bmap) { affs_brelse(bh); bh = affs_bread(sb, bm->bm_key); if (!bh) goto err_bh_read; sbi->s_bmap_bh = bh; sbi->s_last_bmap = bmap; } /* find an unused block in this bitmap block */ bit = blk % sbi->s_bmap_bits; data = (__be32 *)bh->b_data + bit / 32 + 1; enddata = (__be32 *)((u8 *)bh->b_data + sb->s_blocksize); mask = ~0UL << (bit & 31); blk &= ~31UL; tmp = be32_to_cpu(*data); if (tmp & mask) goto find_bit; /* scan the rest of the buffer */ do { blk += 32; if (++data >= enddata) /* didn't find something, can only happen * if scan didn't start at 0, try next bmap */ goto find_bmap; } while (!*data); tmp = be32_to_cpu(*data); mask = ~0; find_bit: /* finally look for a free bit in the word */ bit = ffs(tmp & mask) - 1; blk += bit + sbi->s_reserved; mask2 = mask = 1 << (bit & 31); AFFS_I(inode)->i_lastalloc = blk; /* prealloc as much as possible within this word */ while ((mask2 <<= 1)) { if (!(tmp & mask2)) break; AFFS_I(inode)->i_pa_cnt++; mask |= mask2; } bm->bm_free -= AFFS_I(inode)->i_pa_cnt + 1; *data = cpu_to_be32(tmp & ~mask); /* fix checksum */ tmp = be32_to_cpu(*(__be32 *)bh->b_data); *(__be32 *)bh->b_data = cpu_to_be32(tmp + mask); mark_buffer_dirty(bh); affs_mark_sb_dirty(sb); mutex_unlock(&sbi->s_bmlock); pr_debug("%d\n", blk); return blk; err_bh_read: affs_error(sb,"affs_read_block","Cannot read bitmap block %u", bm->bm_key); sbi->s_bmap_bh = NULL; sbi->s_last_bmap = ~0; err_full: mutex_unlock(&sbi->s_bmlock); pr_debug("failed\n"); return 0; } int affs_init_bitmap(struct super_block *sb, int *flags) { struct affs_bm_info *bm; struct buffer_head *bmap_bh = NULL, *bh = NULL; __be32 *bmap_blk; u32 size, blk, end, offset, mask; int i, res = 0; struct affs_sb_info *sbi = AFFS_SB(sb); if (*flags & SB_RDONLY) return 0; if (!AFFS_ROOT_TAIL(sb, sbi->s_root_bh)->bm_flag) { pr_notice("Bitmap invalid - mounting %s read only\n", sb->s_id); *flags |= SB_RDONLY; return 0; } sbi->s_last_bmap = ~0; sbi->s_bmap_bh = NULL; sbi->s_bmap_bits = sb->s_blocksize * 8 - 32; sbi->s_bmap_count = (sbi->s_partition_size - sbi->s_reserved + sbi->s_bmap_bits - 1) / sbi->s_bmap_bits; size = sbi->s_bmap_count * sizeof(*bm); bm = sbi->s_bitmap = kzalloc(size, GFP_KERNEL); if (!sbi->s_bitmap) { pr_err("Bitmap allocation failed\n"); return -ENOMEM; } bmap_blk = (__be32 *)sbi->s_root_bh->b_data; blk = sb->s_blocksize / 4 - 49; end = blk + 25; for (i = sbi->s_bmap_count; i > 0; bm++, i--) { affs_brelse(bh); bm->bm_key = be32_to_cpu(bmap_blk[blk]); bh = affs_bread(sb, bm->bm_key); if (!bh) { pr_err("Cannot read bitmap\n"); res = -EIO; goto out; } if (affs_checksum_block(sb, bh)) { pr_warn("Bitmap %u invalid - mounting %s read only.\n", bm->bm_key, sb->s_id); *flags |= SB_RDONLY; goto out; } pr_debug("read bitmap block %d: %d\n", blk, bm->bm_key); bm->bm_free = memweight(bh->b_data + 4, sb->s_blocksize - 4); /* Don't try read the extension if this is the last block, * but we also need the right bm pointer below */ if (++blk < end || i == 1) continue; if (bmap_bh) affs_brelse(bmap_bh); bmap_bh = affs_bread(sb, be32_to_cpu(bmap_blk[blk])); if (!bmap_bh) { pr_err("Cannot read bitmap extension\n"); res = -EIO; goto out; } bmap_blk = (__be32 *)bmap_bh->b_data; blk = 0; end = sb->s_blocksize / 4 - 1; } offset = (sbi->s_partition_size - sbi->s_reserved) % sbi->s_bmap_bits; mask = ~(0xFFFFFFFFU << (offset & 31)); pr_debug("last word: %d %d %d\n", offset, offset / 32 + 1, mask); offset = offset / 32 + 1; if (mask) { u32 old, new; /* Mark unused bits in the last word as allocated */ old = be32_to_cpu(((__be32 *)bh->b_data)[offset]); new = old & mask; //if (old != new) { ((__be32 *)bh->b_data)[offset] = cpu_to_be32(new); /* fix checksum */ //new -= old; //old = be32_to_cpu(*(__be32 *)bh->b_data); //*(__be32 *)bh->b_data = cpu_to_be32(old - new); //mark_buffer_dirty(bh); //} /* correct offset for the bitmap count below */ //offset++; } while (++offset < sb->s_blocksize / 4) ((__be32 *)bh->b_data)[offset] = 0; ((__be32 *)bh->b_data)[0] = 0; ((__be32 *)bh->b_data)[0] = cpu_to_be32(-affs_checksum_block(sb, bh)); mark_buffer_dirty(bh); /* recalculate bitmap count for last block */ bm--; bm->bm_free = memweight(bh->b_data + 4, sb->s_blocksize - 4); out: affs_brelse(bh); affs_brelse(bmap_bh); return res; } void affs_free_bitmap(struct super_block *sb) { struct affs_sb_info *sbi = AFFS_SB(sb); if (!sbi->s_bitmap) return; affs_brelse(sbi->s_bmap_bh); sbi->s_bmap_bh = NULL; sbi->s_last_bmap = ~0; kfree(sbi->s_bitmap); sbi->s_bitmap = NULL; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CPUSET_H #define _LINUX_CPUSET_H /* * cpuset interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/sched/topology.h> #include <linux/sched/task.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/jump_label.h> #ifdef CONFIG_CPUSETS /* * Static branch rewrites can happen in an arbitrary order for a given * key. In code paths where we need to loop with read_mems_allowed_begin() and * read_mems_allowed_retry() to get a consistent view of mems_allowed, we need * to ensure that begin() always gets rewritten before retry() in the * disabled -> enabled transition. If not, then if local irqs are disabled * around the loop, we can deadlock since retry() would always be * comparing the latest value of the mems_allowed seqcount against 0 as * begin() still would see cpusets_enabled() as false. The enabled -> disabled * transition should happen in reverse order for the same reasons (want to stop * looking at real value of mems_allowed.sequence in retry() first). */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; extern struct static_key_false cpusets_insane_config_key; static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); } static inline void cpuset_inc(void) { static_branch_inc_cpuslocked(&cpusets_pre_enable_key); static_branch_inc_cpuslocked(&cpusets_enabled_key); } static inline void cpuset_dec(void) { static_branch_dec_cpuslocked(&cpusets_enabled_key); static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } /* * This will get enabled whenever a cpuset configuration is considered * unsupportable in general. E.g. movable only node which cannot satisfy * any non movable allocations (see update_nodemask). Page allocator * needs to make additional checks for those configurations and this * check is meant to guard those checks without any overhead for sane * configurations. */ static inline bool cpusets_insane_config(void) { return static_branch_unlikely(&cpusets_insane_config_key); } extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void inc_dl_tasks_cs(struct task_struct *task); extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern bool cpuset_cpu_is_isolated(int cpu); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); extern bool cpuset_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return cpuset_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { if (cpusets_enabled()) return __cpuset_zone_allowed(z, gfp_mask); return true; } extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2); #ifdef CONFIG_CPUSETS_V1 #define cpuset_memory_pressure_bump() \ do { \ if (cpuset_memory_pressure_enabled) \ __cpuset_memory_pressure_bump(); \ } while (0) extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); #else static inline void cpuset_memory_pressure_bump(void) { } #endif extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); extern int cpuset_mem_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { return task_spread_page(current); } extern bool current_cpuset_is_being_rebound(void); extern void dl_rebuild_rd_accounting(void); extern void rebuild_sched_domains(void); extern void cpuset_print_current_mems_allowed(void); extern void cpuset_reset_sched_domains(void); /* * read_mems_allowed_begin is required when making decisions involving * mems_allowed such as during page allocation. mems_allowed can be updated in * parallel and depending on the new value an operation can fail potentially * causing process failure. A retry loop with read_mems_allowed_begin and * read_mems_allowed_retry prevents these artificial failures. */ static inline unsigned int read_mems_allowed_begin(void) { if (!static_branch_unlikely(&cpusets_pre_enable_key)) return 0; return read_seqcount_begin(¤t->mems_allowed_seq); } /* * If this returns true, the operation that took place after * read_mems_allowed_begin may have failed artificially due to a concurrent * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ static inline bool read_mems_allowed_retry(unsigned int seq) { if (!static_branch_unlikely(&cpusets_enabled_key)) return false; return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) { unsigned long flags; task_lock(current); local_irq_save(flags); write_seqcount_begin(¤t->mems_allowed_seq); current->mems_allowed = nodemask; write_seqcount_end(¤t->mems_allowed_seq); local_irq_restore(flags); task_unlock(current); } #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } static inline bool cpusets_insane_config(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} static inline void cpuset_force_rebuild(void) { } static inline void cpuset_update_active_cpus(void) { partition_sched_domains(1, NULL, NULL); } static inline void inc_dl_tasks_cs(struct task_struct *task) { } static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } static inline void cpuset_unlock(void) { } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { cpumask_copy(mask, task_cpu_possible_mask(p)); } static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p) { return false; } static inline bool cpuset_cpu_is_isolated(int cpu) { return false; } static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; } #define cpuset_current_mems_allowed (node_states[N_MEMORY]) static inline void cpuset_init_current_mems_allowed(void) {} static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return 1; } static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return 1; } static inline void cpuset_memory_pressure_bump(void) {} static inline void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { } static inline int cpuset_mem_spread_node(void) { return 0; } static inline int cpuset_do_page_mem_spread(void) { return 0; } static inline bool current_cpuset_is_being_rebound(void) { return false; } static inline void dl_rebuild_rd_accounting(void) { } static inline void rebuild_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_reset_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_print_current_mems_allowed(void) { } static inline void set_mems_allowed(nodemask_t nodemask) { } static inline unsigned int read_mems_allowed_begin(void) { return 0; } static inline bool read_mems_allowed_retry(unsigned int seq) { return false; } #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ |
| 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 2 3 4 5 6 7 8 9 10 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) International Business Machines Corp., 2006 * * Authors: Artem Bityutskiy (Битюцкий Артём), Thomas Gleixner */ /* * UBI wear-leveling sub-system. * * This sub-system is responsible for wear-leveling. It works in terms of * physical eraseblocks and erase counters and knows nothing about logical * eraseblocks, volumes, etc. From this sub-system's perspective all physical * eraseblocks are of two types - used and free. Used physical eraseblocks are * those that were "get" by the 'ubi_wl_get_peb()' function, and free physical * eraseblocks are those that were put by the 'ubi_wl_put_peb()' function. * * Physical eraseblocks returned by 'ubi_wl_get_peb()' have only erase counter * header. The rest of the physical eraseblock contains only %0xFF bytes. * * When physical eraseblocks are returned to the WL sub-system by means of the * 'ubi_wl_put_peb()' function, they are scheduled for erasure. The erasure is * done asynchronously in context of the per-UBI device background thread, * which is also managed by the WL sub-system. * * The wear-leveling is ensured by means of moving the contents of used * physical eraseblocks with low erase counter to free physical eraseblocks * with high erase counter. * * If the WL sub-system fails to erase a physical eraseblock, it marks it as * bad. * * This sub-system is also responsible for scrubbing. If a bit-flip is detected * in a physical eraseblock, it has to be moved. Technically this is the same * as moving it for wear-leveling reasons. * * As it was said, for the UBI sub-system all physical eraseblocks are either * "free" or "used". Free eraseblock are kept in the @wl->free RB-tree, while * used eraseblocks are kept in @wl->used, @wl->erroneous, or @wl->scrub * RB-trees, as well as (temporarily) in the @wl->pq queue. * * When the WL sub-system returns a physical eraseblock, the physical * eraseblock is protected from being moved for some "time". For this reason, * the physical eraseblock is not directly moved from the @wl->free tree to the * @wl->used tree. There is a protection queue in between where this * physical eraseblock is temporarily stored (@wl->pq). * * All this protection stuff is needed because: * o we don't want to move physical eraseblocks just after we have given them * to the user; instead, we first want to let users fill them up with data; * * o there is a chance that the user will put the physical eraseblock very * soon, so it makes sense not to move it for some time, but wait. * * Physical eraseblocks stay protected only for limited time. But the "time" is * measured in erase cycles in this case. This is implemented with help of the * protection queue. Eraseblocks are put to the tail of this queue when they * are returned by the 'ubi_wl_get_peb()', and eraseblocks are removed from the * head of the queue on each erase operation (for any eraseblock). So the * length of the queue defines how may (global) erase cycles PEBs are protected. * * To put it differently, each physical eraseblock has 2 main states: free and * used. The former state corresponds to the @wl->free tree. The latter state * is split up on several sub-states: * o the WL movement is allowed (@wl->used tree); * o the WL movement is disallowed (@wl->erroneous) because the PEB is * erroneous - e.g., there was a read error; * o the WL movement is temporarily prohibited (@wl->pq queue); * o scrubbing is needed (@wl->scrub tree). * * Depending on the sub-state, wear-leveling entries of the used physical * eraseblocks may be kept in one of those structures. * * Note, in this implementation, we keep a small in-RAM object for each physical * eraseblock. This is surely not a scalable solution. But it appears to be good * enough for moderately large flashes and it is simple. In future, one may * re-work this sub-system and make it more scalable. * * At the moment this sub-system does not utilize the sequence number, which * was introduced relatively recently. But it would be wise to do this because * the sequence number of a logical eraseblock characterizes how old is it. For * example, when we move a PEB with low erase counter, and we need to pick the * target PEB, we pick a PEB with the highest EC if our PEB is "old" and we * pick target PEB with an average EC if our PEB is not very "old". This is a * room for future re-works of the WL sub-system. */ #include <linux/slab.h> #include <linux/crc32.h> #include <linux/freezer.h> #include <linux/kthread.h> #include "ubi.h" #include "wl.h" /* Number of physical eraseblocks reserved for wear-leveling purposes */ #define WL_RESERVED_PEBS 1 /* * Maximum difference between two erase counters. If this threshold is * exceeded, the WL sub-system starts moving data from used physical * eraseblocks with low erase counter to free physical eraseblocks with high * erase counter. */ #define UBI_WL_THRESHOLD CONFIG_MTD_UBI_WL_THRESHOLD /* * When a physical eraseblock is moved, the WL sub-system has to pick the target * physical eraseblock to move to. The simplest way would be just to pick the * one with the highest erase counter. But in certain workloads this could lead * to an unlimited wear of one or few physical eraseblock. Indeed, imagine a * situation when the picked physical eraseblock is constantly erased after the * data is written to it. So, we have a constant which limits the highest erase * counter of the free physical eraseblock to pick. Namely, the WL sub-system * does not pick eraseblocks with erase counter greater than the lowest erase * counter plus %WL_FREE_MAX_DIFF. */ #define WL_FREE_MAX_DIFF (2*UBI_WL_THRESHOLD) /* * Maximum number of consecutive background thread failures which is enough to * switch to read-only mode. */ #define WL_MAX_FAILURES 32 static int self_check_ec(struct ubi_device *ubi, int pnum, int ec); static int self_check_in_wl_tree(const struct ubi_device *ubi, struct ubi_wl_entry *e, struct rb_root *root); static int self_check_in_pq(const struct ubi_device *ubi, struct ubi_wl_entry *e); /** * wl_tree_add - add a wear-leveling entry to a WL RB-tree. * @e: the wear-leveling entry to add * @root: the root of the tree * * Note, we use (erase counter, physical eraseblock number) pairs as keys in * the @ubi->used and @ubi->free RB-trees. */ static void wl_tree_add(struct ubi_wl_entry *e, struct rb_root *root) { struct rb_node **p, *parent = NULL; p = &root->rb_node; while (*p) { struct ubi_wl_entry *e1; parent = *p; e1 = rb_entry(parent, struct ubi_wl_entry, u.rb); if (e->ec < e1->ec) p = &(*p)->rb_left; else if (e->ec > e1->ec) p = &(*p)->rb_right; else { ubi_assert(e->pnum != e1->pnum); if (e->pnum < e1->pnum) p = &(*p)->rb_left; else p = &(*p)->rb_right; } } rb_link_node(&e->u.rb, parent, p); rb_insert_color(&e->u.rb, root); } /** * wl_entry_destroy - destroy a wear-leveling entry. * @ubi: UBI device description object * @e: the wear-leveling entry to add * * This function destroys a wear leveling entry and removes * the reference from the lookup table. */ static void wl_entry_destroy(struct ubi_device *ubi, struct ubi_wl_entry *e) { ubi->lookuptbl[e->pnum] = NULL; kmem_cache_free(ubi_wl_entry_slab, e); } /** * do_work - do one pending work. * @ubi: UBI device description object * @executed: whether there is one work is executed * * This function returns zero in case of success and a negative error code in * case of failure. If @executed is not NULL and there is one work executed, * @executed is set as %1, otherwise @executed is set as %0. */ static int do_work(struct ubi_device *ubi, int *executed) { int err; struct ubi_work *wrk; cond_resched(); /* * @ubi->work_sem is used to synchronize with the workers. Workers take * it in read mode, so many of them may be doing works at a time. But * the queue flush code has to be sure the whole queue of works is * done, and it takes the mutex in write mode. */ down_read(&ubi->work_sem); spin_lock(&ubi->wl_lock); if (list_empty(&ubi->works)) { spin_unlock(&ubi->wl_lock); up_read(&ubi->work_sem); if (executed) *executed = 0; return 0; } if (executed) *executed = 1; wrk = list_entry(ubi->works.next, struct ubi_work, list); list_del(&wrk->list); ubi->works_count -= 1; ubi_assert(ubi->works_count >= 0); spin_unlock(&ubi->wl_lock); /* * Call the worker function. Do not touch the work structure * after this call as it will have been freed or reused by that * time by the worker function. */ err = wrk->func(ubi, wrk, 0); if (err) ubi_err(ubi, "work failed with error code %d", err); up_read(&ubi->work_sem); return err; } /** * in_wl_tree - check if wear-leveling entry is present in a WL RB-tree. * @e: the wear-leveling entry to check * @root: the root of the tree * * This function returns non-zero if @e is in the @root RB-tree and zero if it * is not. */ static int in_wl_tree(struct ubi_wl_entry *e, struct rb_root *root) { struct rb_node *p; p = root->rb_node; while (p) { struct ubi_wl_entry *e1; e1 = rb_entry(p, struct ubi_wl_entry, u.rb); if (e->pnum == e1->pnum) { ubi_assert(e == e1); return 1; } if (e->ec < e1->ec) p = p->rb_left; else if (e->ec > e1->ec) p = p->rb_right; else { ubi_assert(e->pnum != e1->pnum); if (e->pnum < e1->pnum) p = p->rb_left; else p = p->rb_right; } } return 0; } /** * in_pq - check if a wear-leveling entry is present in the protection queue. * @ubi: UBI device description object * @e: the wear-leveling entry to check * * This function returns non-zero if @e is in the protection queue and zero * if it is not. */ static inline int in_pq(const struct ubi_device *ubi, struct ubi_wl_entry *e) { struct ubi_wl_entry *p; int i; for (i = 0; i < UBI_PROT_QUEUE_LEN; ++i) list_for_each_entry(p, &ubi->pq[i], u.list) if (p == e) return 1; return 0; } /** * prot_queue_add - add physical eraseblock to the protection queue. * @ubi: UBI device description object * @e: the physical eraseblock to add * * This function adds @e to the tail of the protection queue @ubi->pq, where * @e will stay for %UBI_PROT_QUEUE_LEN erase operations and will be * temporarily protected from the wear-leveling worker. Note, @wl->lock has to * be locked. */ static void prot_queue_add(struct ubi_device *ubi, struct ubi_wl_entry *e) { int pq_tail = ubi->pq_head - 1; if (pq_tail < 0) pq_tail = UBI_PROT_QUEUE_LEN - 1; ubi_assert(pq_tail >= 0 && pq_tail < UBI_PROT_QUEUE_LEN); list_add_tail(&e->u.list, &ubi->pq[pq_tail]); dbg_wl("added PEB %d EC %d to the protection queue", e->pnum, e->ec); } /** * find_wl_entry - find wear-leveling entry closest to certain erase counter. * @ubi: UBI device description object * @root: the RB-tree where to look for * @diff: maximum possible difference from the smallest erase counter * @pick_max: pick PEB even its erase counter beyonds 'min_ec + @diff' * * This function looks for a wear leveling entry with erase counter closest to * min + @diff, where min is the smallest erase counter. */ static struct ubi_wl_entry *find_wl_entry(struct ubi_device *ubi, struct rb_root *root, int diff, int pick_max) { struct rb_node *p; struct ubi_wl_entry *e; int max; e = rb_entry(rb_first(root), struct ubi_wl_entry, u.rb); max = e->ec + diff; p = root->rb_node; while (p) { struct ubi_wl_entry *e1; e1 = rb_entry(p, struct ubi_wl_entry, u.rb); if (e1->ec >= max) { if (pick_max) e = e1; p = p->rb_left; } else { p = p->rb_right; e = e1; } } return e; } /** * find_mean_wl_entry - find wear-leveling entry with medium erase counter. * @ubi: UBI device description object * @root: the RB-tree where to look for * * This function looks for a wear leveling entry with medium erase counter, * but not greater or equivalent than the lowest erase counter plus * %WL_FREE_MAX_DIFF/2. */ static struct ubi_wl_entry *find_mean_wl_entry(struct ubi_device *ubi, struct rb_root *root) { struct ubi_wl_entry *e, *first, *last; first = rb_entry(rb_first(root), struct ubi_wl_entry, u.rb); last = rb_entry(rb_last(root), struct ubi_wl_entry, u.rb); if (last->ec - first->ec < WL_FREE_MAX_DIFF) { e = rb_entry(root->rb_node, struct ubi_wl_entry, u.rb); /* * If no fastmap has been written and fm_anchor is not * reserved and this WL entry can be used as anchor PEB * hold it back and return the second best WL entry such * that fastmap can use the anchor PEB later. */ e = may_reserve_for_fm(ubi, e, root); } else e = find_wl_entry(ubi, root, WL_FREE_MAX_DIFF/2, 0); return e; } /** * wl_get_wle - get a mean wl entry to be used by ubi_wl_get_peb() or * refill_wl_user_pool(). * @ubi: UBI device description object * * This function returns a wear leveling entry in case of success and * NULL in case of failure. */ static struct ubi_wl_entry *wl_get_wle(struct ubi_device *ubi) { struct ubi_wl_entry *e; e = find_mean_wl_entry(ubi, &ubi->free); if (!e) { ubi_err(ubi, "no free eraseblocks"); return NULL; } self_check_in_wl_tree(ubi, e, &ubi->free); /* * Move the physical eraseblock to the protection queue where it will * be protected from being moved for some time. */ rb_erase(&e->u.rb, &ubi->free); ubi->free_count--; dbg_wl("PEB %d EC %d", e->pnum, e->ec); return e; } /** * prot_queue_del - remove a physical eraseblock from the protection queue. * @ubi: UBI device description object * @pnum: the physical eraseblock to remove * * This function deletes PEB @pnum from the protection queue and returns zero * in case of success and %-ENODEV if the PEB was not found. */ static int prot_queue_del(struct ubi_device *ubi, int pnum) { struct ubi_wl_entry *e; e = ubi->lookuptbl[pnum]; if (!e) return -ENODEV; if (self_check_in_pq(ubi, e)) return -ENODEV; list_del(&e->u.list); dbg_wl("deleted PEB %d from the protection queue", e->pnum); return 0; } /** * ubi_sync_erase - synchronously erase a physical eraseblock. * @ubi: UBI device description object * @e: the physical eraseblock to erase * @torture: if the physical eraseblock has to be tortured * * This function returns zero in case of success and a negative error code in * case of failure. */ int ubi_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, int torture) { int err; struct ubi_ec_hdr *ec_hdr; unsigned long long ec = e->ec; dbg_wl("erase PEB %d, old EC %llu", e->pnum, ec); err = self_check_ec(ubi, e->pnum, e->ec); if (err) return -EINVAL; ec_hdr = kzalloc(ubi->ec_hdr_alsize, GFP_NOFS); if (!ec_hdr) return -ENOMEM; err = ubi_io_sync_erase(ubi, e->pnum, torture); if (err < 0) goto out_free; ec += err; if (ec > UBI_MAX_ERASECOUNTER) { /* * Erase counter overflow. Upgrade UBI and use 64-bit * erase counters internally. */ ubi_err(ubi, "erase counter overflow at PEB %d, EC %llu", e->pnum, ec); err = -EINVAL; goto out_free; } dbg_wl("erased PEB %d, new EC %llu", e->pnum, ec); ec_hdr->ec = cpu_to_be64(ec); err = ubi_io_write_ec_hdr(ubi, e->pnum, ec_hdr); if (err) goto out_free; e->ec = ec; spin_lock(&ubi->wl_lock); if (e->ec > ubi->max_ec) ubi->max_ec = e->ec; spin_unlock(&ubi->wl_lock); out_free: kfree(ec_hdr); return err; } /** * serve_prot_queue - check if it is time to stop protecting PEBs. * @ubi: UBI device description object * * This function is called after each erase operation and removes PEBs from the * tail of the protection queue. These PEBs have been protected for long enough * and should be moved to the used tree. */ static void serve_prot_queue(struct ubi_device *ubi) { struct ubi_wl_entry *e, *tmp; int count; /* * There may be several protected physical eraseblock to remove, * process them all. */ repeat: count = 0; spin_lock(&ubi->wl_lock); list_for_each_entry_safe(e, tmp, &ubi->pq[ubi->pq_head], u.list) { dbg_wl("PEB %d EC %d protection over, move to used tree", e->pnum, e->ec); list_del(&e->u.list); wl_tree_add(e, &ubi->used); if (count++ > 32) { /* * Let's be nice and avoid holding the spinlock for * too long. */ spin_unlock(&ubi->wl_lock); cond_resched(); goto repeat; } } ubi->pq_head += 1; if (ubi->pq_head == UBI_PROT_QUEUE_LEN) ubi->pq_head = 0; ubi_assert(ubi->pq_head >= 0 && ubi->pq_head < UBI_PROT_QUEUE_LEN); spin_unlock(&ubi->wl_lock); } /** * __schedule_ubi_work - schedule a work. * @ubi: UBI device description object * @wrk: the work to schedule * * This function adds a work defined by @wrk to the tail of the pending works * list. Can only be used if ubi->work_sem is already held in read mode! */ static void __schedule_ubi_work(struct ubi_device *ubi, struct ubi_work *wrk) { spin_lock(&ubi->wl_lock); list_add_tail(&wrk->list, &ubi->works); ubi_assert(ubi->works_count >= 0); ubi->works_count += 1; if (ubi->thread_enabled && !ubi_dbg_is_bgt_disabled(ubi)) wake_up_process(ubi->bgt_thread); spin_unlock(&ubi->wl_lock); } /** * schedule_ubi_work - schedule a work. * @ubi: UBI device description object * @wrk: the work to schedule * * This function adds a work defined by @wrk to the tail of the pending works * list. */ static void schedule_ubi_work(struct ubi_device *ubi, struct ubi_work *wrk) { down_read(&ubi->work_sem); __schedule_ubi_work(ubi, wrk); up_read(&ubi->work_sem); } static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, int shutdown); /** * schedule_erase - schedule an erase work. * @ubi: UBI device description object * @e: the WL entry of the physical eraseblock to erase * @vol_id: the volume ID that last used this PEB * @lnum: the last used logical eraseblock number for the PEB * @torture: if the physical eraseblock has to be tortured * @nested: denotes whether the work_sem is already held * * This function returns zero in case of success and a %-ENOMEM in case of * failure. */ static int schedule_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, int vol_id, int lnum, int torture, bool nested) { struct ubi_work *wl_wrk; ubi_assert(e); dbg_wl("schedule erasure of PEB %d, EC %d, torture %d", e->pnum, e->ec, torture); wl_wrk = kmalloc(sizeof(struct ubi_work), GFP_NOFS); if (!wl_wrk) return -ENOMEM; wl_wrk->func = &erase_worker; wl_wrk->e = e; wl_wrk->vol_id = vol_id; wl_wrk->lnum = lnum; wl_wrk->torture = torture; if (nested) __schedule_ubi_work(ubi, wl_wrk); else schedule_ubi_work(ubi, wl_wrk); return 0; } static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk); /** * do_sync_erase - run the erase worker synchronously. * @ubi: UBI device description object * @e: the WL entry of the physical eraseblock to erase * @vol_id: the volume ID that last used this PEB * @lnum: the last used logical eraseblock number for the PEB * @torture: if the physical eraseblock has to be tortured * */ static int do_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, int vol_id, int lnum, int torture) { struct ubi_work wl_wrk; dbg_wl("sync erase of PEB %i", e->pnum); wl_wrk.e = e; wl_wrk.vol_id = vol_id; wl_wrk.lnum = lnum; wl_wrk.torture = torture; return __erase_worker(ubi, &wl_wrk); } static int ensure_wear_leveling(struct ubi_device *ubi, int nested); /** * wear_leveling_worker - wear-leveling worker function. * @ubi: UBI device description object * @wrk: the work object * @shutdown: non-zero if the worker has to free memory and exit * because the WL-subsystem is shutting down * * This function copies a more worn out physical eraseblock to a less worn out * one. Returns zero in case of success and a negative error code in case of * failure. */ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, int shutdown) { int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0; int erase = 0, keep = 0, vol_id = -1, lnum = -1; struct ubi_wl_entry *e1, *e2; struct ubi_vid_io_buf *vidb; struct ubi_vid_hdr *vid_hdr; int dst_leb_clean = 0; kfree(wrk); if (shutdown) return 0; vidb = ubi_alloc_vid_buf(ubi, GFP_NOFS); if (!vidb) return -ENOMEM; vid_hdr = ubi_get_vid_hdr(vidb); down_read(&ubi->fm_eba_sem); mutex_lock(&ubi->move_mutex); spin_lock(&ubi->wl_lock); ubi_assert(!ubi->move_from && !ubi->move_to); ubi_assert(!ubi->move_to_put); #ifdef CONFIG_MTD_UBI_FASTMAP if (!next_peb_for_wl(ubi, true) || #else if (!ubi->free.rb_node || #endif (!ubi->used.rb_node && !ubi->scrub.rb_node)) { /* * No free physical eraseblocks? Well, they must be waiting in * the queue to be erased. Cancel movement - it will be * triggered again when a free physical eraseblock appears. * * No used physical eraseblocks? They must be temporarily * protected from being moved. They will be moved to the * @ubi->used tree later and the wear-leveling will be * triggered again. */ dbg_wl("cancel WL, a list is empty: free %d, used %d", !ubi->free.rb_node, !ubi->used.rb_node); goto out_cancel; } #ifdef CONFIG_MTD_UBI_FASTMAP e1 = find_anchor_wl_entry(&ubi->used); if (e1 && ubi->fm_anchor && (ubi->fm_anchor->ec - e1->ec >= UBI_WL_THRESHOLD)) { ubi->fm_do_produce_anchor = 1; /* * fm_anchor is no longer considered a good anchor. * NULL assignment also prevents multiple wear level checks * of this PEB. */ wl_tree_add(ubi->fm_anchor, &ubi->free); ubi->fm_anchor = NULL; ubi->free_count++; } if (ubi->fm_do_produce_anchor) { if (!e1) goto out_cancel; e2 = get_peb_for_wl(ubi); if (!e2) goto out_cancel; self_check_in_wl_tree(ubi, e1, &ubi->used); rb_erase(&e1->u.rb, &ubi->used); dbg_wl("anchor-move PEB %d to PEB %d", e1->pnum, e2->pnum); ubi->fm_do_produce_anchor = 0; } else if (!ubi->scrub.rb_node) { #else if (!ubi->scrub.rb_node) { #endif /* * Now pick the least worn-out used physical eraseblock and a * highly worn-out free physical eraseblock. If the erase * counters differ much enough, start wear-leveling. */ e1 = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, u.rb); e2 = get_peb_for_wl(ubi); if (!e2) goto out_cancel; if (!(e2->ec - e1->ec >= UBI_WL_THRESHOLD)) { dbg_wl("no WL needed: min used EC %d, max free EC %d", e1->ec, e2->ec); /* Give the unused PEB back */ wl_tree_add(e2, &ubi->free); ubi->free_count++; goto out_cancel; } self_check_in_wl_tree(ubi, e1, &ubi->used); rb_erase(&e1->u.rb, &ubi->used); dbg_wl("move PEB %d EC %d to PEB %d EC %d", e1->pnum, e1->ec, e2->pnum, e2->ec); } else { /* Perform scrubbing */ scrubbing = 1; e1 = rb_entry(rb_first(&ubi->scrub), struct ubi_wl_entry, u.rb); e2 = get_peb_for_wl(ubi); if (!e2) goto out_cancel; self_check_in_wl_tree(ubi, e1, &ubi->scrub); rb_erase(&e1->u.rb, &ubi->scrub); dbg_wl("scrub PEB %d to PEB %d", e1->pnum, e2->pnum); } ubi->move_from = e1; ubi->move_to = e2; spin_unlock(&ubi->wl_lock); /* * Now we are going to copy physical eraseblock @e1->pnum to @e2->pnum. * We so far do not know which logical eraseblock our physical * eraseblock (@e1) belongs to. We have to read the volume identifier * header first. * * Note, we are protected from this PEB being unmapped and erased. The * 'ubi_wl_put_peb()' would wait for moving to be finished if the PEB * which is being moved was unmapped. */ err = ubi_io_read_vid_hdr(ubi, e1->pnum, vidb, 0); if (err && err != UBI_IO_BITFLIPS) { dst_leb_clean = 1; if (err == UBI_IO_FF) { /* * We are trying to move PEB without a VID header. UBI * always write VID headers shortly after the PEB was * given, so we have a situation when it has not yet * had a chance to write it, because it was preempted. * So add this PEB to the protection queue so far, * because presumably more data will be written there * (including the missing VID header), and then we'll * move it. */ dbg_wl("PEB %d has no VID header", e1->pnum); protect = 1; goto out_not_moved; } else if (err == UBI_IO_FF_BITFLIPS) { /* * The same situation as %UBI_IO_FF, but bit-flips were * detected. It is better to schedule this PEB for * scrubbing. */ dbg_wl("PEB %d has no VID header but has bit-flips", e1->pnum); scrubbing = 1; goto out_not_moved; } else if (ubi->fast_attach && err == UBI_IO_BAD_HDR_EBADMSG) { /* * While a full scan would detect interrupted erasures * at attach time we can face them here when attached from * Fastmap. */ dbg_wl("PEB %d has ECC errors, maybe from an interrupted erasure", e1->pnum); erase = 1; goto out_not_moved; } ubi_err(ubi, "error %d while reading VID header from PEB %d", err, e1->pnum); goto out_error; } vol_id = be32_to_cpu(vid_hdr->vol_id); lnum = be32_to_cpu(vid_hdr->lnum); err = ubi_eba_copy_leb(ubi, e1->pnum, e2->pnum, vidb); if (err) { if (err == MOVE_CANCEL_RACE) { /* * The LEB has not been moved because the volume is * being deleted or the PEB has been put meanwhile. We * should prevent this PEB from being selected for * wear-leveling movement again, so put it to the * protection queue. */ protect = 1; dst_leb_clean = 1; goto out_not_moved; } if (err == MOVE_RETRY) { /* * For source PEB: * 1. The scrubbing is set for scrub type PEB, it will * be put back into ubi->scrub list. * 2. Non-scrub type PEB will be put back into ubi->used * list. */ keep = 1; dst_leb_clean = 1; goto out_not_moved; } if (err == MOVE_TARGET_BITFLIPS || err == MOVE_TARGET_WR_ERR || err == MOVE_TARGET_RD_ERR) { /* * Target PEB had bit-flips or write error - torture it. */ torture = 1; keep = 1; goto out_not_moved; } if (err == MOVE_SOURCE_RD_ERR) { /* * An error happened while reading the source PEB. Do * not switch to R/O mode in this case, and give the * upper layers a possibility to recover from this, * e.g. by unmapping corresponding LEB. Instead, just * put this PEB to the @ubi->erroneous list to prevent * UBI from trying to move it over and over again. */ if (ubi->erroneous_peb_count > ubi->max_erroneous) { ubi_err(ubi, "too many erroneous eraseblocks (%d)", ubi->erroneous_peb_count); goto out_error; } dst_leb_clean = 1; erroneous = 1; goto out_not_moved; } if (err < 0) goto out_error; ubi_assert(0); } /* The PEB has been successfully moved */ if (scrubbing) ubi_msg(ubi, "scrubbed PEB %d (LEB %d:%d), data moved to PEB %d", e1->pnum, vol_id, lnum, e2->pnum); ubi_free_vid_buf(vidb); spin_lock(&ubi->wl_lock); if (!ubi->move_to_put) { wl_tree_add(e2, &ubi->used); e2 = NULL; } ubi->move_from = ubi->move_to = NULL; ubi->move_to_put = ubi->wl_scheduled = 0; spin_unlock(&ubi->wl_lock); err = do_sync_erase(ubi, e1, vol_id, lnum, 0); if (err) { if (e2) { spin_lock(&ubi->wl_lock); wl_entry_destroy(ubi, e2); spin_unlock(&ubi->wl_lock); } goto out_ro; } if (e2) { /* * Well, the target PEB was put meanwhile, schedule it for * erasure. */ dbg_wl("PEB %d (LEB %d:%d) was put meanwhile, erase", e2->pnum, vol_id, lnum); err = do_sync_erase(ubi, e2, vol_id, lnum, 0); if (err) goto out_ro; } dbg_wl("done"); mutex_unlock(&ubi->move_mutex); up_read(&ubi->fm_eba_sem); return 0; /* * For some reasons the LEB was not moved, might be an error, might be * something else. @e1 was not changed, so return it back. @e2 might * have been changed, schedule it for erasure. */ out_not_moved: if (vol_id != -1) dbg_wl("cancel moving PEB %d (LEB %d:%d) to PEB %d (%d)", e1->pnum, vol_id, lnum, e2->pnum, err); else dbg_wl("cancel moving PEB %d to PEB %d (%d)", e1->pnum, e2->pnum, err); spin_lock(&ubi->wl_lock); if (protect) prot_queue_add(ubi, e1); else if (erroneous) { wl_tree_add(e1, &ubi->erroneous); ubi->erroneous_peb_count += 1; } else if (scrubbing) wl_tree_add(e1, &ubi->scrub); else if (keep) wl_tree_add(e1, &ubi->used); if (dst_leb_clean) { wl_tree_add(e2, &ubi->free); ubi->free_count++; } ubi_assert(!ubi->move_to_put); ubi->move_from = ubi->move_to = NULL; ubi->wl_scheduled = 0; spin_unlock(&ubi->wl_lock); ubi_free_vid_buf(vidb); if (dst_leb_clean) { ensure_wear_leveling(ubi, 1); } else { err = do_sync_erase(ubi, e2, vol_id, lnum, torture); if (err) goto out_ro; } if (erase) { err = do_sync_erase(ubi, e1, vol_id, lnum, 1); if (err) goto out_ro; } mutex_unlock(&ubi->move_mutex); up_read(&ubi->fm_eba_sem); return 0; out_error: if (vol_id != -1) ubi_err(ubi, "error %d while moving PEB %d to PEB %d", err, e1->pnum, e2->pnum); else ubi_err(ubi, "error %d while moving PEB %d (LEB %d:%d) to PEB %d", err, e1->pnum, vol_id, lnum, e2->pnum); spin_lock(&ubi->wl_lock); ubi->move_from = ubi->move_to = NULL; ubi->move_to_put = ubi->wl_scheduled = 0; wl_entry_destroy(ubi, e1); wl_entry_destroy(ubi, e2); spin_unlock(&ubi->wl_lock); ubi_free_vid_buf(vidb); out_ro: ubi_ro_mode(ubi); mutex_unlock(&ubi->move_mutex); up_read(&ubi->fm_eba_sem); ubi_assert(err != 0); return err < 0 ? err : -EIO; out_cancel: ubi->wl_scheduled = 0; spin_unlock(&ubi->wl_lock); mutex_unlock(&ubi->move_mutex); up_read(&ubi->fm_eba_sem); ubi_free_vid_buf(vidb); return 0; } /** * ensure_wear_leveling - schedule wear-leveling if it is needed. * @ubi: UBI device description object * @nested: set to non-zero if this function is called from UBI worker * * This function checks if it is time to start wear-leveling and schedules it * if yes. This function returns zero in case of success and a negative error * code in case of failure. */ static int ensure_wear_leveling(struct ubi_device *ubi, int nested) { int err = 0; struct ubi_work *wrk; spin_lock(&ubi->wl_lock); if (ubi->wl_scheduled) /* Wear-leveling is already in the work queue */ goto out_unlock; /* * If the ubi->scrub tree is not empty, scrubbing is needed, and the * WL worker has to be scheduled anyway. */ if (!ubi->scrub.rb_node) { #ifdef CONFIG_MTD_UBI_FASTMAP if (!need_wear_leveling(ubi)) goto out_unlock; #else struct ubi_wl_entry *e1; struct ubi_wl_entry *e2; if (!ubi->used.rb_node || !ubi->free.rb_node) /* No physical eraseblocks - no deal */ goto out_unlock; /* * We schedule wear-leveling only if the difference between the * lowest erase counter of used physical eraseblocks and a high * erase counter of free physical eraseblocks is greater than * %UBI_WL_THRESHOLD. */ e1 = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, u.rb); e2 = find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF, 0); if (!(e2->ec - e1->ec >= UBI_WL_THRESHOLD)) goto out_unlock; #endif dbg_wl("schedule wear-leveling"); } else dbg_wl("schedule scrubbing"); ubi->wl_scheduled = 1; spin_unlock(&ubi->wl_lock); wrk = kmalloc(sizeof(struct ubi_work), GFP_NOFS); if (!wrk) { err = -ENOMEM; goto out_cancel; } wrk->func = &wear_leveling_worker; if (nested) __schedule_ubi_work(ubi, wrk); else schedule_ubi_work(ubi, wrk); return err; out_cancel: spin_lock(&ubi->wl_lock); ubi->wl_scheduled = 0; out_unlock: spin_unlock(&ubi->wl_lock); return err; } /** * __erase_worker - physical eraseblock erase worker function. * @ubi: UBI device description object * @wl_wrk: the work object * * This function erases a physical eraseblock and perform torture testing if * needed. It also takes care about marking the physical eraseblock bad if * needed. Returns zero in case of success and a negative error code in case of * failure. */ static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk) { struct ubi_wl_entry *e = wl_wrk->e; int pnum = e->pnum; int vol_id = wl_wrk->vol_id; int lnum = wl_wrk->lnum; int err, available_consumed = 0; dbg_wl("erase PEB %d EC %d LEB %d:%d", pnum, e->ec, wl_wrk->vol_id, wl_wrk->lnum); err = ubi_sync_erase(ubi, e, wl_wrk->torture); if (!err) { spin_lock(&ubi->wl_lock); if (!ubi->fm_disabled && !ubi->fm_anchor && e->pnum < UBI_FM_MAX_START) { /* * Abort anchor production, if needed it will be * enabled again in the wear leveling started below. */ ubi->fm_anchor = e; ubi->fm_do_produce_anchor = 0; } else { wl_tree_add(e, &ubi->free); ubi->free_count++; } spin_unlock(&ubi->wl_lock); /* * One more erase operation has happened, take care about * protected physical eraseblocks. */ serve_prot_queue(ubi); /* And take care about wear-leveling */ err = ensure_wear_leveling(ubi, 1); return err; } ubi_err(ubi, "failed to erase PEB %d, error %d", pnum, err); if (err == -EINTR || err == -ENOMEM || err == -EAGAIN || err == -EBUSY) { int err1; /* Re-schedule the LEB for erasure */ err1 = schedule_erase(ubi, e, vol_id, lnum, 0, true); if (err1) { spin_lock(&ubi->wl_lock); wl_entry_destroy(ubi, e); spin_unlock(&ubi->wl_lock); err = err1; goto out_ro; } return err; } spin_lock(&ubi->wl_lock); wl_entry_destroy(ubi, e); spin_unlock(&ubi->wl_lock); if (err != -EIO) /* * If this is not %-EIO, we have no idea what to do. Scheduling * this physical eraseblock for erasure again would cause * errors again and again. Well, lets switch to R/O mode. */ goto out_ro; /* It is %-EIO, the PEB went bad */ if (!ubi->bad_allowed) { ubi_err(ubi, "bad physical eraseblock %d detected", pnum); goto out_ro; } spin_lock(&ubi->volumes_lock); if (ubi->beb_rsvd_pebs == 0) { if (ubi->avail_pebs == 0) { spin_unlock(&ubi->volumes_lock); ubi_err(ubi, "no reserved/available physical eraseblocks"); goto out_ro; } ubi->avail_pebs -= 1; available_consumed = 1; } spin_unlock(&ubi->volumes_lock); ubi_msg(ubi, "mark PEB %d as bad", pnum); err = ubi_io_mark_bad(ubi, pnum); if (err) goto out_ro; spin_lock(&ubi->volumes_lock); if (ubi->beb_rsvd_pebs > 0) { if (available_consumed) { /* * The amount of reserved PEBs increased since we last * checked. */ ubi->avail_pebs += 1; available_consumed = 0; } ubi->beb_rsvd_pebs -= 1; } ubi->bad_peb_count += 1; ubi->good_peb_count -= 1; ubi_calculate_reserved(ubi); if (available_consumed) ubi_warn(ubi, "no PEBs in the reserved pool, used an available PEB"); else if (ubi->beb_rsvd_pebs) ubi_msg(ubi, "%d PEBs left in the reserve", ubi->beb_rsvd_pebs); else ubi_warn(ubi, "last PEB from the reserve was used"); spin_unlock(&ubi->volumes_lock); return err; out_ro: if (available_consumed) { spin_lock(&ubi->volumes_lock); ubi->avail_pebs += 1; spin_unlock(&ubi->volumes_lock); } ubi_ro_mode(ubi); return err; } static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, int shutdown) { int ret; if (shutdown) { struct ubi_wl_entry *e = wl_wrk->e; dbg_wl("cancel erasure of PEB %d EC %d", e->pnum, e->ec); kfree(wl_wrk); wl_entry_destroy(ubi, e); return 0; } ret = __erase_worker(ubi, wl_wrk); kfree(wl_wrk); return ret; } /** * ubi_wl_put_peb - return a PEB to the wear-leveling sub-system. * @ubi: UBI device description object * @vol_id: the volume ID that last used this PEB * @lnum: the last used logical eraseblock number for the PEB * @pnum: physical eraseblock to return * @torture: if this physical eraseblock has to be tortured * * This function is called to return physical eraseblock @pnum to the pool of * free physical eraseblocks. The @torture flag has to be set if an I/O error * occurred to this @pnum and it has to be tested. This function returns zero * in case of success, and a negative error code in case of failure. */ int ubi_wl_put_peb(struct ubi_device *ubi, int vol_id, int lnum, int pnum, int torture) { int err; struct ubi_wl_entry *e; dbg_wl("PEB %d", pnum); ubi_assert(pnum >= 0); ubi_assert(pnum < ubi->peb_count); down_read(&ubi->fm_protect); retry: spin_lock(&ubi->wl_lock); e = ubi->lookuptbl[pnum]; if (!e) { /* * This wl entry has been removed for some errors by other * process (eg. wear leveling worker), corresponding process * (except __erase_worker, which cannot concurrent with * ubi_wl_put_peb) will set ubi ro_mode at the same time, * just ignore this wl entry. */ spin_unlock(&ubi->wl_lock); up_read(&ubi->fm_protect); return 0; } if (e == ubi->move_from) { /* * User is putting the physical eraseblock which was selected to * be moved. It will be scheduled for erasure in the * wear-leveling worker. */ dbg_wl("PEB %d is being moved, wait", pnum); spin_unlock(&ubi->wl_lock); /* Wait for the WL worker by taking the @ubi->move_mutex */ mutex_lock(&ubi->move_mutex); mutex_unlock(&ubi->move_mutex); goto retry; } else if (e == ubi->move_to) { /* * User is putting the physical eraseblock which was selected * as the target the data is moved to. It may happen if the EBA * sub-system already re-mapped the LEB in 'ubi_eba_copy_leb()' * but the WL sub-system has not put the PEB to the "used" tree * yet, but it is about to do this. So we just set a flag which * will tell the WL worker that the PEB is not needed anymore * and should be scheduled for erasure. */ dbg_wl("PEB %d is the target of data moving", pnum); ubi_assert(!ubi->move_to_put); ubi->move_to_put = 1; spin_unlock(&ubi->wl_lock); up_read(&ubi->fm_protect); return 0; } else { if (in_wl_tree(e, &ubi->used)) { self_check_in_wl_tree(ubi, e, &ubi->used); rb_erase(&e->u.rb, &ubi->used); } else if (in_wl_tree(e, &ubi->scrub)) { self_check_in_wl_tree(ubi, e, &ubi->scrub); rb_erase(&e->u.rb, &ubi->scrub); } else if (in_wl_tree(e, &ubi->erroneous)) { self_check_in_wl_tree(ubi, e, &ubi->erroneous); rb_erase(&e->u.rb, &ubi->erroneous); ubi->erroneous_peb_count -= 1; ubi_assert(ubi->erroneous_peb_count >= 0); /* Erroneous PEBs should be tortured */ torture = 1; } else { err = prot_queue_del(ubi, e->pnum); if (err) { ubi_err(ubi, "PEB %d not found", pnum); ubi_ro_mode(ubi); spin_unlock(&ubi->wl_lock); up_read(&ubi->fm_protect); return err; } } } spin_unlock(&ubi->wl_lock); err = schedule_erase(ubi, e, vol_id, lnum, torture, false); if (err) { spin_lock(&ubi->wl_lock); wl_tree_add(e, &ubi->used); spin_unlock(&ubi->wl_lock); } up_read(&ubi->fm_protect); return err; } /** * ubi_wl_scrub_peb - schedule a physical eraseblock for scrubbing. * @ubi: UBI device description object * @pnum: the physical eraseblock to schedule * * If a bit-flip in a physical eraseblock is detected, this physical eraseblock * needs scrubbing. This function schedules a physical eraseblock for * scrubbing which is done in background. This function returns zero in case of * success and a negative error code in case of failure. */ int ubi_wl_scrub_peb(struct ubi_device *ubi, int pnum) { struct ubi_wl_entry *e; ubi_msg(ubi, "schedule PEB %d for scrubbing", pnum); retry: spin_lock(&ubi->wl_lock); e = ubi->lookuptbl[pnum]; if (e == ubi->move_from || in_wl_tree(e, &ubi->scrub) || in_wl_tree(e, &ubi->erroneous)) { spin_unlock(&ubi->wl_lock); return 0; } if (e == ubi->move_to) { /* * This physical eraseblock was used to move data to. The data * was moved but the PEB was not yet inserted to the proper * tree. We should just wait a little and let the WL worker * proceed. */ spin_unlock(&ubi->wl_lock); dbg_wl("the PEB %d is not in proper tree, retry", pnum); yield(); goto retry; } if (in_wl_tree(e, &ubi->used)) { self_check_in_wl_tree(ubi, e, &ubi->used); rb_erase(&e->u.rb, &ubi->used); } else { int err; err = prot_queue_del(ubi, e->pnum); if (err) { ubi_err(ubi, "PEB %d not found", pnum); ubi_ro_mode(ubi); spin_unlock(&ubi->wl_lock); return err; } } wl_tree_add(e, &ubi->scrub); spin_unlock(&ubi->wl_lock); /* * Technically scrubbing is the same as wear-leveling, so it is done * by the WL worker. */ return ensure_wear_leveling(ubi, 0); } /** * ubi_wl_flush - flush all pending works. * @ubi: UBI device description object * @vol_id: the volume id to flush for * @lnum: the logical eraseblock number to flush for * * This function executes all pending works for a particular volume id / * logical eraseblock number pair. If either value is set to %UBI_ALL, then it * acts as a wildcard for all of the corresponding volume numbers or logical * eraseblock numbers. It returns zero in case of success and a negative error * code in case of failure. */ int ubi_wl_flush(struct ubi_device *ubi, int vol_id, int lnum) { int err = 0; int found = 1; /* * Erase while the pending works queue is not empty, but not more than * the number of currently pending works. */ dbg_wl("flush pending work for LEB %d:%d (%d pending works)", vol_id, lnum, ubi->works_count); while (found) { struct ubi_work *wrk, *tmp; found = 0; down_read(&ubi->work_sem); spin_lock(&ubi->wl_lock); list_for_each_entry_safe(wrk, tmp, &ubi->works, list) { if ((vol_id == UBI_ALL || wrk->vol_id == vol_id) && (lnum == UBI_ALL || wrk->lnum == lnum)) { list_del(&wrk->list); ubi->works_count -= 1; ubi_assert(ubi->works_count >= 0); spin_unlock(&ubi->wl_lock); err = wrk->func(ubi, wrk, 0); if (err) { up_read(&ubi->work_sem); return err; } spin_lock(&ubi->wl_lock); found = 1; break; } } spin_unlock(&ubi->wl_lock); up_read(&ubi->work_sem); } /* * Make sure all the works which have been done in parallel are * finished. */ down_write(&ubi->work_sem); up_write(&ubi->work_sem); return err; } static bool scrub_possible(struct ubi_device *ubi, struct ubi_wl_entry *e) { if (in_wl_tree(e, &ubi->scrub)) return false; else if (in_wl_tree(e, &ubi->erroneous)) return false; else if (ubi->move_from == e) return false; else if (ubi->move_to == e) return false; return true; } /** * ubi_bitflip_check - Check an eraseblock for bitflips and scrub it if needed. * @ubi: UBI device description object * @pnum: the physical eraseblock to schedule * @force: don't read the block, assume bitflips happened and take action. * * This function reads the given eraseblock and checks if bitflips occured. * In case of bitflips, the eraseblock is scheduled for scrubbing. * If scrubbing is forced with @force, the eraseblock is not read, * but scheduled for scrubbing right away. * * Returns: * %EINVAL, PEB is out of range * %ENOENT, PEB is no longer used by UBI * %EBUSY, PEB cannot be checked now or a check is currently running on it * %EAGAIN, bit flips happened but scrubbing is currently not possible * %EUCLEAN, bit flips happened and PEB is scheduled for scrubbing * %0, no bit flips detected */ int ubi_bitflip_check(struct ubi_device *ubi, int pnum, int force) { int err = 0; struct ubi_wl_entry *e; if (pnum < 0 || pnum >= ubi->peb_count) { err = -EINVAL; goto out; } /* * Pause all parallel work, otherwise it can happen that the * erase worker frees a wl entry under us. */ down_write(&ubi->work_sem); /* * Make sure that the wl entry does not change state while * inspecting it. */ spin_lock(&ubi->wl_lock); e = ubi->lookuptbl[pnum]; if (!e) { spin_unlock(&ubi->wl_lock); err = -ENOENT; goto out_resume; } /* * Does it make sense to check this PEB? */ if (!scrub_possible(ubi, e)) { spin_unlock(&ubi->wl_lock); err = -EBUSY; goto out_resume; } spin_unlock(&ubi->wl_lock); if (!force) { mutex_lock(&ubi->buf_mutex); err = ubi_io_read(ubi, ubi->peb_buf, pnum, 0, ubi->peb_size); mutex_unlock(&ubi->buf_mutex); } if (force || err == UBI_IO_BITFLIPS) { /* * Okay, bit flip happened, let's figure out what we can do. */ spin_lock(&ubi->wl_lock); /* * Recheck. We released wl_lock, UBI might have killed the * wl entry under us. */ e = ubi->lookuptbl[pnum]; if (!e) { spin_unlock(&ubi->wl_lock); err = -ENOENT; goto out_resume; } /* * Need to re-check state */ if (!scrub_possible(ubi, e)) { spin_unlock(&ubi->wl_lock); err = -EBUSY; goto out_resume; } if (in_pq(ubi, e)) { prot_queue_del(ubi, e->pnum); wl_tree_add(e, &ubi->scrub); spin_unlock(&ubi->wl_lock); err = ensure_wear_leveling(ubi, 1); } else if (in_wl_tree(e, &ubi->used)) { rb_erase(&e->u.rb, &ubi->used); wl_tree_add(e, &ubi->scrub); spin_unlock(&ubi->wl_lock); err = ensure_wear_leveling(ubi, 1); } else if (in_wl_tree(e, &ubi->free)) { rb_erase(&e->u.rb, &ubi->free); ubi->free_count--; spin_unlock(&ubi->wl_lock); /* * This PEB is empty we can schedule it for * erasure right away. No wear leveling needed. */ err = schedule_erase(ubi, e, UBI_UNKNOWN, UBI_UNKNOWN, force ? 0 : 1, true); } else { spin_unlock(&ubi->wl_lock); err = -EAGAIN; } if (!err && !force) err = -EUCLEAN; } else { err = 0; } out_resume: up_write(&ubi->work_sem); out: return err; } /** * tree_destroy - destroy an RB-tree. * @ubi: UBI device description object * @root: the root of the tree to destroy */ static void tree_destroy(struct ubi_device *ubi, struct rb_root *root) { struct rb_node *rb; struct ubi_wl_entry *e; rb = root->rb_node; while (rb) { if (rb->rb_left) rb = rb->rb_left; else if (rb->rb_right) rb = rb->rb_right; else { e = rb_entry(rb, struct ubi_wl_entry, u.rb); rb = rb_parent(rb); if (rb) { if (rb->rb_left == &e->u.rb) rb->rb_left = NULL; else rb->rb_right = NULL; } wl_entry_destroy(ubi, e); } } } /** * ubi_thread - UBI background thread. * @u: the UBI device description object pointer */ int ubi_thread(void *u) { int failures = 0; struct ubi_device *ubi = u; ubi_msg(ubi, "background thread \"%s\" started, PID %d", ubi->bgt_name, task_pid_nr(current)); set_freezable(); for (;;) { int err; if (kthread_should_stop()) break; if (try_to_freeze()) continue; spin_lock(&ubi->wl_lock); if (list_empty(&ubi->works) || ubi->ro_mode || !ubi->thread_enabled || ubi_dbg_is_bgt_disabled(ubi)) { set_current_state(TASK_INTERRUPTIBLE); spin_unlock(&ubi->wl_lock); /* * Check kthread_should_stop() after we set the task * state to guarantee that we either see the stop bit * and exit or the task state is reset to runnable such * that it's not scheduled out indefinitely and detects * the stop bit at kthread_should_stop(). */ if (kthread_should_stop()) { set_current_state(TASK_RUNNING); break; } schedule(); continue; } spin_unlock(&ubi->wl_lock); err = do_work(ubi, NULL); if (err) { ubi_err(ubi, "%s: work failed with error code %d", ubi->bgt_name, err); if (failures++ > WL_MAX_FAILURES) { /* * Too many failures, disable the thread and * switch to read-only mode. */ ubi_msg(ubi, "%s: %d consecutive failures", ubi->bgt_name, WL_MAX_FAILURES); ubi_ro_mode(ubi); ubi->thread_enabled = 0; continue; } } else failures = 0; cond_resched(); } dbg_wl("background thread \"%s\" is killed", ubi->bgt_name); ubi->thread_enabled = 0; return 0; } /** * shutdown_work - shutdown all pending works. * @ubi: UBI device description object */ static void shutdown_work(struct ubi_device *ubi) { while (!list_empty(&ubi->works)) { struct ubi_work *wrk; wrk = list_entry(ubi->works.next, struct ubi_work, list); list_del(&wrk->list); wrk->func(ubi, wrk, 1); ubi->works_count -= 1; ubi_assert(ubi->works_count >= 0); } } /** * erase_aeb - erase a PEB given in UBI attach info PEB * @ubi: UBI device description object * @aeb: UBI attach info PEB * @sync: If true, erase synchronously. Otherwise schedule for erasure */ static int erase_aeb(struct ubi_device *ubi, struct ubi_ainf_peb *aeb, bool sync) { struct ubi_wl_entry *e; int err; e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL); if (!e) return -ENOMEM; e->pnum = aeb->pnum; e->ec = aeb->ec; ubi->lookuptbl[e->pnum] = e; if (sync) { err = ubi_sync_erase(ubi, e, false); if (err) goto out_free; wl_tree_add(e, &ubi->free); ubi->free_count++; } else { err = schedule_erase(ubi, e, aeb->vol_id, aeb->lnum, 0, false); if (err) goto out_free; } return 0; out_free: wl_entry_destroy(ubi, e); return err; } /** * ubi_wl_init - initialize the WL sub-system using attaching information. * @ubi: UBI device description object * @ai: attaching information * * This function returns zero in case of success, and a negative error code in * case of failure. */ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai) { int err, i, reserved_pebs, found_pebs = 0; struct rb_node *rb1, *rb2; struct ubi_ainf_volume *av; struct ubi_ainf_peb *aeb, *tmp; struct ubi_wl_entry *e; ubi->used = ubi->erroneous = ubi->free = ubi->scrub = RB_ROOT; spin_lock_init(&ubi->wl_lock); mutex_init(&ubi->move_mutex); init_rwsem(&ubi->work_sem); ubi->max_ec = ai->max_ec; INIT_LIST_HEAD(&ubi->works); sprintf(ubi->bgt_name, UBI_BGT_NAME_PATTERN, ubi->ubi_num); err = -ENOMEM; ubi->lookuptbl = kcalloc(ubi->peb_count, sizeof(void *), GFP_KERNEL); if (!ubi->lookuptbl) return err; for (i = 0; i < UBI_PROT_QUEUE_LEN; i++) INIT_LIST_HEAD(&ubi->pq[i]); ubi->pq_head = 0; ubi->free_count = 0; list_for_each_entry_safe(aeb, tmp, &ai->erase, u.list) { cond_resched(); err = erase_aeb(ubi, aeb, false); if (err) goto out_free; found_pebs++; } list_for_each_entry(aeb, &ai->free, u.list) { cond_resched(); e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL); if (!e) { err = -ENOMEM; goto out_free; } e->pnum = aeb->pnum; e->ec = aeb->ec; ubi_assert(e->ec >= 0); wl_tree_add(e, &ubi->free); ubi->free_count++; ubi->lookuptbl[e->pnum] = e; found_pebs++; } ubi_rb_for_each_entry(rb1, av, &ai->volumes, rb) { ubi_rb_for_each_entry(rb2, aeb, &av->root, u.rb) { cond_resched(); e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL); if (!e) { err = -ENOMEM; goto out_free; } e->pnum = aeb->pnum; e->ec = aeb->ec; ubi->lookuptbl[e->pnum] = e; if (!aeb->scrub) { dbg_wl("add PEB %d EC %d to the used tree", e->pnum, e->ec); wl_tree_add(e, &ubi->used); } else { dbg_wl("add PEB %d EC %d to the scrub tree", e->pnum, e->ec); wl_tree_add(e, &ubi->scrub); } found_pebs++; } } list_for_each_entry(aeb, &ai->fastmap, u.list) { cond_resched(); e = ubi_find_fm_block(ubi, aeb->pnum); if (e) { ubi_assert(!ubi->lookuptbl[e->pnum]); ubi->lookuptbl[e->pnum] = e; } else { bool sync = false; /* * Usually old Fastmap PEBs are scheduled for erasure * and we don't have to care about them but if we face * an power cut before scheduling them we need to * take care of them here. */ if (ubi->lookuptbl[aeb->pnum]) continue; /* * The fastmap update code might not find a free PEB for * writing the fastmap anchor to and then reuses the * current fastmap anchor PEB. When this PEB gets erased * and a power cut happens before it is written again we * must make sure that the fastmap attach code doesn't * find any outdated fastmap anchors, hence we erase the * outdated fastmap anchor PEBs synchronously here. */ if (aeb->vol_id == UBI_FM_SB_VOLUME_ID) sync = true; err = erase_aeb(ubi, aeb, sync); if (err) goto out_free; } found_pebs++; } dbg_wl("found %i PEBs", found_pebs); ubi_assert(ubi->good_peb_count == found_pebs); reserved_pebs = WL_RESERVED_PEBS; ubi_fastmap_init(ubi, &reserved_pebs); if (ubi->avail_pebs < reserved_pebs) { ubi_err(ubi, "no enough physical eraseblocks (%d, need %d)", ubi->avail_pebs, reserved_pebs); if (ubi->corr_peb_count) ubi_err(ubi, "%d PEBs are corrupted and not used", ubi->corr_peb_count); err = -ENOSPC; goto out_free; } ubi->avail_pebs -= reserved_pebs; ubi->rsvd_pebs += reserved_pebs; /* Schedule wear-leveling if needed */ err = ensure_wear_leveling(ubi, 0); if (err) goto out_free; #ifdef CONFIG_MTD_UBI_FASTMAP if (!ubi->ro_mode && !ubi->fm_disabled) ubi_ensure_anchor_pebs(ubi); #endif return 0; out_free: shutdown_work(ubi); tree_destroy(ubi, &ubi->used); tree_destroy(ubi, &ubi->free); tree_destroy(ubi, &ubi->scrub); kfree(ubi->lookuptbl); return err; } /** * protection_queue_destroy - destroy the protection queue. * @ubi: UBI device description object */ static void protection_queue_destroy(struct ubi_device *ubi) { int i; struct ubi_wl_entry *e, *tmp; for (i = 0; i < UBI_PROT_QUEUE_LEN; ++i) { list_for_each_entry_safe(e, tmp, &ubi->pq[i], u.list) { list_del(&e->u.list); wl_entry_destroy(ubi, e); } } } /** * ubi_wl_close - close the wear-leveling sub-system. * @ubi: UBI device description object */ void ubi_wl_close(struct ubi_device *ubi) { dbg_wl("close the WL sub-system"); ubi_fastmap_close(ubi); shutdown_work(ubi); protection_queue_destroy(ubi); tree_destroy(ubi, &ubi->used); tree_destroy(ubi, &ubi->erroneous); tree_destroy(ubi, &ubi->free); tree_destroy(ubi, &ubi->scrub); kfree(ubi->lookuptbl); } /** * self_check_ec - make sure that the erase counter of a PEB is correct. * @ubi: UBI device description object * @pnum: the physical eraseblock number to check * @ec: the erase counter to check * * This function returns zero if the erase counter of physical eraseblock @pnum * is equivalent to @ec, and a negative error code if not or if an error * occurred. */ static int self_check_ec(struct ubi_device *ubi, int pnum, int ec) { int err; long long read_ec; struct ubi_ec_hdr *ec_hdr; if (!ubi_dbg_chk_gen(ubi)) return 0; ec_hdr = kzalloc(ubi->ec_hdr_alsize, GFP_NOFS); if (!ec_hdr) return -ENOMEM; err = ubi_io_read_ec_hdr(ubi, pnum, ec_hdr, 0); if (err && err != UBI_IO_BITFLIPS) { /* The header does not have to exist */ err = 0; goto out_free; } read_ec = be64_to_cpu(ec_hdr->ec); if (ec != read_ec && read_ec - ec > 1) { ubi_err(ubi, "self-check failed for PEB %d", pnum); ubi_err(ubi, "read EC is %lld, should be %d", read_ec, ec); dump_stack(); err = 1; } else err = 0; out_free: kfree(ec_hdr); return err; } /** * self_check_in_wl_tree - check that wear-leveling entry is in WL RB-tree. * @ubi: UBI device description object * @e: the wear-leveling entry to check * @root: the root of the tree * * This function returns zero if @e is in the @root RB-tree and %-EINVAL if it * is not. */ static int self_check_in_wl_tree(const struct ubi_device *ubi, struct ubi_wl_entry *e, struct rb_root *root) { if (!ubi_dbg_chk_gen(ubi)) return 0; if (in_wl_tree(e, root)) return 0; ubi_err(ubi, "self-check failed for PEB %d, EC %d, RB-tree %p ", e->pnum, e->ec, root); dump_stack(); return -EINVAL; } /** * self_check_in_pq - check if wear-leveling entry is in the protection * queue. * @ubi: UBI device description object * @e: the wear-leveling entry to check * * This function returns zero if @e is in @ubi->pq and %-EINVAL if it is not. */ static int self_check_in_pq(const struct ubi_device *ubi, struct ubi_wl_entry *e) { if (!ubi_dbg_chk_gen(ubi)) return 0; if (in_pq(ubi, e)) return 0; ubi_err(ubi, "self-check failed for PEB %d, EC %d, Protect queue", e->pnum, e->ec); dump_stack(); return -EINVAL; } #ifndef CONFIG_MTD_UBI_FASTMAP static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi) { struct ubi_wl_entry *e; e = find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF, 0); self_check_in_wl_tree(ubi, e, &ubi->free); ubi->free_count--; ubi_assert(ubi->free_count >= 0); rb_erase(&e->u.rb, &ubi->free); return e; } /** * produce_free_peb - produce a free physical eraseblock. * @ubi: UBI device description object * * This function tries to make a free PEB by means of synchronous execution of * pending works. This may be needed if, for example the background thread is * disabled. Returns zero in case of success and a negative error code in case * of failure. */ static int produce_free_peb(struct ubi_device *ubi) { int err; while (!ubi->free.rb_node && ubi->works_count) { spin_unlock(&ubi->wl_lock); dbg_wl("do one work synchronously"); err = do_work(ubi, NULL); spin_lock(&ubi->wl_lock); if (err) return err; } return 0; } /** * ubi_wl_get_peb - get a physical eraseblock. * @ubi: UBI device description object * * This function returns a physical eraseblock in case of success and a * negative error code in case of failure. * Returns with ubi->fm_eba_sem held in read mode! */ int ubi_wl_get_peb(struct ubi_device *ubi) { int err; struct ubi_wl_entry *e; retry: down_read(&ubi->fm_eba_sem); spin_lock(&ubi->wl_lock); if (!ubi->free.rb_node) { if (ubi->works_count == 0) { ubi_err(ubi, "no free eraseblocks"); ubi_assert(list_empty(&ubi->works)); spin_unlock(&ubi->wl_lock); return -ENOSPC; } err = produce_free_peb(ubi); if (err < 0) { spin_unlock(&ubi->wl_lock); return err; } spin_unlock(&ubi->wl_lock); up_read(&ubi->fm_eba_sem); goto retry; } e = wl_get_wle(ubi); prot_queue_add(ubi, e); spin_unlock(&ubi->wl_lock); err = ubi_self_check_all_ff(ubi, e->pnum, ubi->vid_hdr_aloffset, ubi->peb_size - ubi->vid_hdr_aloffset); if (err) { ubi_err(ubi, "new PEB %d does not contain all 0xFF bytes", e->pnum); return err; } return e->pnum; } #else #include "fastmap-wl.c" #endif |
| 2 1 2 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Sync File validation framework * * Copyright (C) 2012 Google, Inc. */ #include <linux/file.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/sync_file.h> #include "sync_debug.h" #define CREATE_TRACE_POINTS #include "sync_trace.h" /* * SW SYNC validation framework * * A sync object driver that uses a 32bit counter to coordinate * synchronization. Useful when there is no hardware primitive backing * the synchronization. * * To start the framework just open: * * <debugfs>/sync/sw_sync * * That will create a sync timeline, all fences created under this timeline * file descriptor will belong to the this timeline. * * The 'sw_sync' file can be opened many times as to create different * timelines. * * Fences can be created with SW_SYNC_IOC_CREATE_FENCE ioctl with struct * sw_sync_create_fence_data as parameter. * * To increment the timeline counter, SW_SYNC_IOC_INC ioctl should be used * with the increment as u32. This will update the last signaled value * from the timeline and signal any fence that has a seqno smaller or equal * to it. * * struct sw_sync_create_fence_data * @value: the seqno to initialise the fence with * @name: the name of the new sync point * @fence: return the fd of the new sync_file with the created fence */ struct sw_sync_create_fence_data { __u32 value; char name[32]; __s32 fence; /* fd of new fence */ }; /** * struct sw_sync_get_deadline - get the deadline hint of a sw_sync fence * @deadline_ns: absolute time of the deadline * @pad: must be zero * @fence_fd: the sw_sync fence fd (in) * * Return the earliest deadline set on the fence. The timebase for the * deadline is CLOCK_MONOTONIC (same as vblank). If there is no deadline * set on the fence, this ioctl will return -ENOENT. */ struct sw_sync_get_deadline { __u64 deadline_ns; __u32 pad; __s32 fence_fd; }; #define SW_SYNC_IOC_MAGIC 'W' #define SW_SYNC_IOC_CREATE_FENCE _IOWR(SW_SYNC_IOC_MAGIC, 0,\ struct sw_sync_create_fence_data) #define SW_SYNC_IOC_INC _IOW(SW_SYNC_IOC_MAGIC, 1, __u32) #define SW_SYNC_GET_DEADLINE _IOWR(SW_SYNC_IOC_MAGIC, 2, \ struct sw_sync_get_deadline) #define SW_SYNC_HAS_DEADLINE_BIT DMA_FENCE_FLAG_USER_BITS static const struct dma_fence_ops timeline_fence_ops; static inline struct sync_pt *dma_fence_to_sync_pt(struct dma_fence *fence) { if (fence->ops != &timeline_fence_ops) return NULL; return container_of(fence, struct sync_pt, base); } /** * sync_timeline_create() - creates a sync object * @name: sync_timeline name * * Creates a new sync_timeline. Returns the sync_timeline object or NULL in * case of error. */ static struct sync_timeline *sync_timeline_create(const char *name) { struct sync_timeline *obj; obj = kzalloc(sizeof(*obj), GFP_KERNEL); if (!obj) return NULL; kref_init(&obj->kref); obj->context = dma_fence_context_alloc(1); strscpy(obj->name, name, sizeof(obj->name)); obj->pt_tree = RB_ROOT; INIT_LIST_HEAD(&obj->pt_list); spin_lock_init(&obj->lock); sync_timeline_debug_add(obj); return obj; } static void sync_timeline_free(struct kref *kref) { struct sync_timeline *obj = container_of(kref, struct sync_timeline, kref); sync_timeline_debug_remove(obj); kfree(obj); } static void sync_timeline_get(struct sync_timeline *obj) { kref_get(&obj->kref); } static void sync_timeline_put(struct sync_timeline *obj) { kref_put(&obj->kref, sync_timeline_free); } static const char *timeline_fence_get_driver_name(struct dma_fence *fence) { return "sw_sync"; } static const char *timeline_fence_get_timeline_name(struct dma_fence *fence) { struct sync_timeline *parent = dma_fence_parent(fence); return parent->name; } static void timeline_fence_release(struct dma_fence *fence) { struct sync_pt *pt = dma_fence_to_sync_pt(fence); struct sync_timeline *parent = dma_fence_parent(fence); unsigned long flags; spin_lock_irqsave(fence->lock, flags); if (!list_empty(&pt->link)) { list_del(&pt->link); rb_erase(&pt->node, &parent->pt_tree); } spin_unlock_irqrestore(fence->lock, flags); sync_timeline_put(parent); dma_fence_free(fence); } static bool timeline_fence_signaled(struct dma_fence *fence) { struct sync_timeline *parent = dma_fence_parent(fence); return !__dma_fence_is_later(fence->seqno, parent->value, fence->ops); } static void timeline_fence_value_str(struct dma_fence *fence, char *str, int size) { snprintf(str, size, "%lld", fence->seqno); } static void timeline_fence_timeline_value_str(struct dma_fence *fence, char *str, int size) { struct sync_timeline *parent = dma_fence_parent(fence); snprintf(str, size, "%d", parent->value); } static void timeline_fence_set_deadline(struct dma_fence *fence, ktime_t deadline) { struct sync_pt *pt = dma_fence_to_sync_pt(fence); unsigned long flags; spin_lock_irqsave(fence->lock, flags); if (test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) { if (ktime_before(deadline, pt->deadline)) pt->deadline = deadline; } else { pt->deadline = deadline; __set_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags); } spin_unlock_irqrestore(fence->lock, flags); } static const struct dma_fence_ops timeline_fence_ops = { .get_driver_name = timeline_fence_get_driver_name, .get_timeline_name = timeline_fence_get_timeline_name, .signaled = timeline_fence_signaled, .release = timeline_fence_release, .fence_value_str = timeline_fence_value_str, .timeline_value_str = timeline_fence_timeline_value_str, .set_deadline = timeline_fence_set_deadline, }; /** * sync_timeline_signal() - signal a status change on a sync_timeline * @obj: sync_timeline to signal * @inc: num to increment on timeline->value * * A sync implementation should call this any time one of it's fences * has signaled or has an error condition. */ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) { LIST_HEAD(signalled); struct sync_pt *pt, *next; trace_sync_timeline(obj); spin_lock_irq(&obj->lock); obj->value += inc; list_for_each_entry_safe(pt, next, &obj->pt_list, link) { if (!timeline_fence_signaled(&pt->base)) break; dma_fence_get(&pt->base); list_move_tail(&pt->link, &signalled); rb_erase(&pt->node, &obj->pt_tree); dma_fence_signal_locked(&pt->base); } spin_unlock_irq(&obj->lock); list_for_each_entry_safe(pt, next, &signalled, link) { list_del_init(&pt->link); dma_fence_put(&pt->base); } } /** * sync_pt_create() - creates a sync pt * @obj: parent sync_timeline * @value: value of the fence * * Creates a new sync_pt (fence) as a child of @parent. @size bytes will be * allocated allowing for implementation specific data to be kept after * the generic sync_timeline struct. Returns the sync_pt object or * NULL in case of error. */ static struct sync_pt *sync_pt_create(struct sync_timeline *obj, unsigned int value) { struct sync_pt *pt; pt = kzalloc(sizeof(*pt), GFP_KERNEL); if (!pt) return NULL; sync_timeline_get(obj); dma_fence_init(&pt->base, &timeline_fence_ops, &obj->lock, obj->context, value); INIT_LIST_HEAD(&pt->link); spin_lock_irq(&obj->lock); if (!dma_fence_is_signaled_locked(&pt->base)) { struct rb_node **p = &obj->pt_tree.rb_node; struct rb_node *parent = NULL; while (*p) { struct sync_pt *other; int cmp; parent = *p; other = rb_entry(parent, typeof(*pt), node); cmp = value - other->base.seqno; if (cmp > 0) { p = &parent->rb_right; } else if (cmp < 0) { p = &parent->rb_left; } else { if (dma_fence_get_rcu(&other->base)) { sync_timeline_put(obj); kfree(pt); pt = other; goto unlock; } p = &parent->rb_left; } } rb_link_node(&pt->node, parent, p); rb_insert_color(&pt->node, &obj->pt_tree); parent = rb_next(&pt->node); list_add_tail(&pt->link, parent ? &rb_entry(parent, typeof(*pt), node)->link : &obj->pt_list); } unlock: spin_unlock_irq(&obj->lock); return pt; } /* * *WARNING* * * improper use of this can result in deadlocking kernel drivers from userspace. */ /* opening sw_sync create a new sync obj */ static int sw_sync_debugfs_open(struct inode *inode, struct file *file) { struct sync_timeline *obj; char task_comm[TASK_COMM_LEN]; get_task_comm(task_comm, current); obj = sync_timeline_create(task_comm); if (!obj) return -ENOMEM; file->private_data = obj; return 0; } static int sw_sync_debugfs_release(struct inode *inode, struct file *file) { struct sync_timeline *obj = file->private_data; struct sync_pt *pt, *next; spin_lock_irq(&obj->lock); list_for_each_entry_safe(pt, next, &obj->pt_list, link) { dma_fence_set_error(&pt->base, -ENOENT); dma_fence_signal_locked(&pt->base); } spin_unlock_irq(&obj->lock); sync_timeline_put(obj); return 0; } static long sw_sync_ioctl_create_fence(struct sync_timeline *obj, unsigned long arg) { int fd = get_unused_fd_flags(O_CLOEXEC); int err; struct sync_pt *pt; struct sync_file *sync_file; struct sw_sync_create_fence_data data; if (fd < 0) return fd; if (copy_from_user(&data, (void __user *)arg, sizeof(data))) { err = -EFAULT; goto err; } pt = sync_pt_create(obj, data.value); if (!pt) { err = -ENOMEM; goto err; } sync_file = sync_file_create(&pt->base); dma_fence_put(&pt->base); if (!sync_file) { err = -ENOMEM; goto err; } data.fence = fd; if (copy_to_user((void __user *)arg, &data, sizeof(data))) { fput(sync_file->file); err = -EFAULT; goto err; } fd_install(fd, sync_file->file); return 0; err: put_unused_fd(fd); return err; } static long sw_sync_ioctl_inc(struct sync_timeline *obj, unsigned long arg) { u32 value; if (copy_from_user(&value, (void __user *)arg, sizeof(value))) return -EFAULT; while (value > INT_MAX) { sync_timeline_signal(obj, INT_MAX); value -= INT_MAX; } sync_timeline_signal(obj, value); return 0; } static int sw_sync_ioctl_get_deadline(struct sync_timeline *obj, unsigned long arg) { struct sw_sync_get_deadline data; struct dma_fence *fence; unsigned long flags; struct sync_pt *pt; int ret = 0; if (copy_from_user(&data, (void __user *)arg, sizeof(data))) return -EFAULT; if (data.deadline_ns || data.pad) return -EINVAL; fence = sync_file_get_fence(data.fence_fd); if (!fence) return -EINVAL; pt = dma_fence_to_sync_pt(fence); if (!pt) return -EINVAL; spin_lock_irqsave(fence->lock, flags); if (test_bit(SW_SYNC_HAS_DEADLINE_BIT, &fence->flags)) { data.deadline_ns = ktime_to_ns(pt->deadline); } else { ret = -ENOENT; } spin_unlock_irqrestore(fence->lock, flags); dma_fence_put(fence); if (ret) return ret; if (copy_to_user((void __user *)arg, &data, sizeof(data))) return -EFAULT; return 0; } static long sw_sync_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct sync_timeline *obj = file->private_data; switch (cmd) { case SW_SYNC_IOC_CREATE_FENCE: return sw_sync_ioctl_create_fence(obj, arg); case SW_SYNC_IOC_INC: return sw_sync_ioctl_inc(obj, arg); case SW_SYNC_GET_DEADLINE: return sw_sync_ioctl_get_deadline(obj, arg); default: return -ENOTTY; } } const struct file_operations sw_sync_debugfs_fops = { .open = sw_sync_debugfs_open, .release = sw_sync_debugfs_release, .unlocked_ioctl = sw_sync_ioctl, .compat_ioctl = compat_ptr_ioctl, }; |
| 163 121 2 94 91 3 10 5 77 1 1 4 73 1 2 2 1 1 41 1 70 23 60 4 25 1 1 30 7 24 31 8 22 17 29 3 24 30 1 18 12 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 | /* * linux/fs/hfs/dir.c * * Copyright (C) 1995-1997 Paul H. Hargrove * (C) 2003 Ardis Technologies <roman@ardistech.com> * This file may be distributed under the terms of the GNU General Public License. * * This file contains directory-related functions independent of which * scheme is being used to represent forks. * * Based on the minix file system code, (C) 1991, 1992 by Linus Torvalds */ #include "hfs_fs.h" #include "btree.h" /* * hfs_lookup() */ static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { hfs_cat_rec rec; struct hfs_find_data fd; struct inode *inode = NULL; int res; res = hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd); if (res) return ERR_PTR(res); hfs_cat_build_key(dir->i_sb, fd.search_key, dir->i_ino, &dentry->d_name); res = hfs_brec_read(&fd, &rec, sizeof(rec)); if (res) { if (res != -ENOENT) inode = ERR_PTR(res); } else { inode = hfs_iget(dir->i_sb, &fd.search_key->cat, &rec); if (!inode) inode = ERR_PTR(-EACCES); } hfs_find_exit(&fd); return d_splice_alias(inode, dentry); } /* * hfs_readdir */ static int hfs_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; int len, err; char strbuf[HFS_MAX_NAMELEN]; union hfs_cat_rec entry; struct hfs_find_data fd; struct hfs_readdir_data *rd; u16 type; if (ctx->pos >= inode->i_size) return 0; err = hfs_find_init(HFS_SB(sb)->cat_tree, &fd); if (err) return err; hfs_cat_build_key(sb, fd.search_key, inode->i_ino, NULL); err = hfs_brec_find(&fd); if (err) goto out; if (ctx->pos == 0) { /* This is completely artificial... */ if (!dir_emit_dot(file, ctx)) goto out; ctx->pos = 1; } if (ctx->pos == 1) { if (fd.entrylength > sizeof(entry) || fd.entrylength < 0) { err = -EIO; goto out; } hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); if (entry.type != HFS_CDR_THD) { pr_err("bad catalog folder thread\n"); err = -EIO; goto out; } //if (fd.entrylength < HFS_MIN_THREAD_SZ) { // pr_err("truncated catalog thread\n"); // err = -EIO; // goto out; //} if (!dir_emit(ctx, "..", 2, be32_to_cpu(entry.thread.ParID), DT_DIR)) goto out; ctx->pos = 2; } if (ctx->pos >= inode->i_size) goto out; err = hfs_brec_goto(&fd, ctx->pos - 1); if (err) goto out; for (;;) { if (be32_to_cpu(fd.key->cat.ParID) != inode->i_ino) { pr_err("walked past end of dir\n"); err = -EIO; goto out; } if (fd.entrylength > sizeof(entry) || fd.entrylength < 0) { err = -EIO; goto out; } hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); type = entry.type; len = hfs_mac2asc(sb, strbuf, &fd.key->cat.CName); if (type == HFS_CDR_DIR) { if (fd.entrylength < sizeof(struct hfs_cat_dir)) { pr_err("small dir entry\n"); err = -EIO; goto out; } if (!dir_emit(ctx, strbuf, len, be32_to_cpu(entry.dir.DirID), DT_DIR)) break; } else if (type == HFS_CDR_FIL) { if (fd.entrylength < sizeof(struct hfs_cat_file)) { pr_err("small file entry\n"); err = -EIO; goto out; } if (!dir_emit(ctx, strbuf, len, be32_to_cpu(entry.file.FlNum), DT_REG)) break; } else { pr_err("bad catalog entry type %d\n", type); err = -EIO; goto out; } ctx->pos++; if (ctx->pos >= inode->i_size) goto out; err = hfs_brec_goto(&fd, 1); if (err) goto out; } rd = file->private_data; if (!rd) { rd = kmalloc(sizeof(struct hfs_readdir_data), GFP_KERNEL); if (!rd) { err = -ENOMEM; goto out; } file->private_data = rd; rd->file = file; spin_lock(&HFS_I(inode)->open_dir_lock); list_add(&rd->list, &HFS_I(inode)->open_dir_list); spin_unlock(&HFS_I(inode)->open_dir_lock); } /* * Can be done after the list insertion; exclusion with * hfs_delete_cat() is provided by directory lock. */ memcpy(&rd->key, &fd.key->cat, sizeof(struct hfs_cat_key)); out: hfs_find_exit(&fd); return err; } static int hfs_dir_release(struct inode *inode, struct file *file) { struct hfs_readdir_data *rd = file->private_data; if (rd) { spin_lock(&HFS_I(inode)->open_dir_lock); list_del(&rd->list); spin_unlock(&HFS_I(inode)->open_dir_lock); kfree(rd); } return 0; } /* * hfs_create() * * This is the create() entry in the inode_operations structure for * regular HFS directories. The purpose is to create a new file in * a directory and return a corresponding inode, given the inode for * the directory and the name (and its length) of the new file. */ static int hfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; int res; inode = hfs_new_inode(dir, &dentry->d_name, mode); if (!inode) return -ENOMEM; res = hfs_cat_create(inode->i_ino, dir, &dentry->d_name, inode); if (res) { clear_nlink(inode); hfs_delete_inode(inode); iput(inode); return res; } d_instantiate(dentry, inode); mark_inode_dirty(inode); return 0; } /* * hfs_mkdir() * * This is the mkdir() entry in the inode_operations structure for * regular HFS directories. The purpose is to create a new directory * in a directory, given the inode for the parent directory and the * name (and its length) of the new directory. */ static struct dentry *hfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; int res; inode = hfs_new_inode(dir, &dentry->d_name, S_IFDIR | mode); if (!inode) return ERR_PTR(-ENOMEM); res = hfs_cat_create(inode->i_ino, dir, &dentry->d_name, inode); if (res) { clear_nlink(inode); hfs_delete_inode(inode); iput(inode); return ERR_PTR(res); } d_instantiate(dentry, inode); mark_inode_dirty(inode); return NULL; } /* * hfs_remove() * * This serves as both unlink() and rmdir() in the inode_operations * structure for regular HFS directories. The purpose is to delete * an existing child, given the inode for the parent directory and * the name (and its length) of the existing directory. * * HFS does not have hardlinks, so both rmdir and unlink set the * link count to 0. The only difference is the emptiness check. */ static int hfs_remove(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); int res; if (S_ISDIR(inode->i_mode) && inode->i_size != 2) return -ENOTEMPTY; res = hfs_cat_delete(inode->i_ino, dir, &dentry->d_name); if (res) return res; clear_nlink(inode); inode_set_ctime_current(inode); hfs_delete_inode(inode); mark_inode_dirty(inode); return 0; } /* * hfs_rename() * * This is the rename() entry in the inode_operations structure for * regular HFS directories. The purpose is to rename an existing * file or directory, given the inode for the current directory and * the name (and its length) of the existing file/directory and the * inode for the new directory and the name (and its length) of the * new file/directory. * XXX: how do you handle must_be dir? */ static int hfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { int res; if (flags & ~RENAME_NOREPLACE) return -EINVAL; /* Unlink destination if it already exists */ if (d_really_is_positive(new_dentry)) { res = hfs_remove(new_dir, new_dentry); if (res) return res; } res = hfs_cat_move(d_inode(old_dentry)->i_ino, old_dir, &old_dentry->d_name, new_dir, &new_dentry->d_name); if (!res) hfs_cat_build_key(old_dir->i_sb, (btree_key *)&HFS_I(d_inode(old_dentry))->cat_key, new_dir->i_ino, &new_dentry->d_name); return res; } const struct file_operations hfs_dir_operations = { .read = generic_read_dir, .iterate_shared = hfs_readdir, .llseek = generic_file_llseek, .release = hfs_dir_release, }; const struct inode_operations hfs_dir_inode_operations = { .create = hfs_create, .lookup = hfs_lookup, .unlink = hfs_remove, .mkdir = hfs_mkdir, .rmdir = hfs_remove, .rename = hfs_rename, .setattr = hfs_inode_setattr, }; |
| 118 26 99 118 118 118 117 118 198 198 5 5 198 100 100 100 100 100 100 100 5 95 100 100 6 100 100 100 100 100 100 178 100 100 100 100 100 101 101 101 100 100 100 1 100 100 100 6 100 8 8 8 8 8 100 100 100 98 100 100 99 5 100 99 100 100 99 5 5 5 5 5 5 100 100 101 101 101 101 101 1 100 88 100 1 1 100 7 7 202 203 202 100 100 100 100 100 100 99 100 100 100 100 100 100 100 100 100 100 100 100 100 100 101 101 8 100 44 44 44 44 29 29 28 29 73 73 81 81 89 90 90 106 106 177 178 178 178 178 178 178 25 26 4 3 3 3 3 3 90 90 89 90 89 186 185 | 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 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "alloc_foreground.h" #include "bkey_buf.h" #include "bkey_methods.h" #include "btree_cache.h" #include "btree_gc.h" #include "btree_journal_iter.h" #include "btree_update.h" #include "btree_update_interior.h" #include "btree_io.h" #include "btree_iter.h" #include "btree_locking.h" #include "buckets.h" #include "clock.h" #include "error.h" #include "extents.h" #include "io_write.h" #include "journal.h" #include "journal_reclaim.h" #include "keylist.h" #include "recovery_passes.h" #include "replicas.h" #include "sb-members.h" #include "super-io.h" #include "trace.h" #include <linux/random.h> static const char * const bch2_btree_update_modes[] = { #define x(t) #t, BTREE_UPDATE_MODES() #undef x NULL }; static int bch2_btree_insert_node(struct btree_update *, struct btree_trans *, btree_path_idx_t, struct btree *, struct keylist *); static void bch2_btree_update_add_new_node(struct btree_update *, struct btree *); /* * Verify that child nodes correctly span parent node's range: */ int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b) { struct bch_fs *c = trans->c; struct bpos node_min = b->key.k.type == KEY_TYPE_btree_ptr_v2 ? bkey_i_to_btree_ptr_v2(&b->key)->v.min_key : b->data->min_key; struct btree_and_journal_iter iter; struct bkey_s_c k; struct printbuf buf = PRINTBUF; struct bkey_buf prev; int ret = 0; BUG_ON(b->key.k.type == KEY_TYPE_btree_ptr_v2 && !bpos_eq(bkey_i_to_btree_ptr_v2(&b->key)->v.min_key, b->data->min_key)); bch2_bkey_buf_init(&prev); bkey_init(&prev.k->k); bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); if (b == btree_node_root(c, b)) { if (!bpos_eq(b->data->min_key, POS_MIN)) { printbuf_reset(&buf); bch2_bpos_to_text(&buf, b->data->min_key); log_fsck_err(trans, btree_root_bad_min_key, "btree root with incorrect min_key: %s", buf.buf); goto topology_repair; } if (!bpos_eq(b->data->max_key, SPOS_MAX)) { printbuf_reset(&buf); bch2_bpos_to_text(&buf, b->data->max_key); log_fsck_err(trans, btree_root_bad_max_key, "btree root with incorrect max_key: %s", buf.buf); goto topology_repair; } } if (!b->c.level) goto out; while ((k = bch2_btree_and_journal_iter_peek(&iter)).k) { if (k.k->type != KEY_TYPE_btree_ptr_v2) goto out; struct bkey_s_c_btree_ptr_v2 bp = bkey_s_c_to_btree_ptr_v2(k); struct bpos expected_min = bkey_deleted(&prev.k->k) ? node_min : bpos_successor(prev.k->k.p); if (!bpos_eq(expected_min, bp.v->min_key)) { bch2_topology_error(c); printbuf_reset(&buf); prt_str(&buf, "end of prev node doesn't match start of next node\n in "); bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); prt_str(&buf, " node "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, "\n prev "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k)); prt_str(&buf, "\n next "); bch2_bkey_val_to_text(&buf, c, k); log_fsck_err(trans, btree_node_topology_bad_min_key, "%s", buf.buf); goto topology_repair; } bch2_bkey_buf_reassemble(&prev, c, k); bch2_btree_and_journal_iter_advance(&iter); } if (bkey_deleted(&prev.k->k)) { bch2_topology_error(c); printbuf_reset(&buf); prt_str(&buf, "empty interior node\n in "); bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); prt_str(&buf, " node "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); log_fsck_err(trans, btree_node_topology_empty_interior_node, "%s", buf.buf); goto topology_repair; } else if (!bpos_eq(prev.k->k.p, b->key.k.p)) { bch2_topology_error(c); printbuf_reset(&buf); prt_str(&buf, "last child node doesn't end at end of parent node\n in "); bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); prt_str(&buf, " node "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, "\n last key "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k)); log_fsck_err(trans, btree_node_topology_bad_max_key, "%s", buf.buf); goto topology_repair; } out: fsck_err: bch2_btree_and_journal_iter_exit(&iter); bch2_bkey_buf_exit(&prev, c); printbuf_exit(&buf); return ret; topology_repair: ret = bch2_topology_error(c); goto out; } /* Calculate ideal packed bkey format for new btree nodes: */ static void __bch2_btree_calc_format(struct bkey_format_state *s, struct btree *b) { struct bkey_packed *k; struct bkey uk; for_each_bset(b, t) bset_tree_for_each_key(b, t, k) if (!bkey_deleted(k)) { uk = bkey_unpack_key(b, k); bch2_bkey_format_add_key(s, &uk); } } static struct bkey_format bch2_btree_calc_format(struct btree *b) { struct bkey_format_state s; bch2_bkey_format_init(&s); bch2_bkey_format_add_pos(&s, b->data->min_key); bch2_bkey_format_add_pos(&s, b->data->max_key); __bch2_btree_calc_format(&s, b); return bch2_bkey_format_done(&s); } static size_t btree_node_u64s_with_format(struct btree_nr_keys nr, struct bkey_format *old_f, struct bkey_format *new_f) { /* stupid integer promotion rules */ ssize_t delta = (((int) new_f->key_u64s - old_f->key_u64s) * (int) nr.packed_keys) + (((int) new_f->key_u64s - BKEY_U64s) * (int) nr.unpacked_keys); BUG_ON(delta + nr.live_u64s < 0); return nr.live_u64s + delta; } /** * bch2_btree_node_format_fits - check if we could rewrite node with a new format * * @c: filesystem handle * @b: btree node to rewrite * @nr: number of keys for new node (i.e. b->nr) * @new_f: bkey format to translate keys to * * Returns: true if all re-packed keys will be able to fit in a new node. * * Assumes all keys will successfully pack with the new format. */ static bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *b, struct btree_nr_keys nr, struct bkey_format *new_f) { size_t u64s = btree_node_u64s_with_format(nr, &b->format, new_f); return __vstruct_bytes(struct btree_node, u64s) < btree_buf_bytes(b); } /* Btree node freeing/allocation: */ static void __btree_node_free(struct btree_trans *trans, struct btree *b) { struct bch_fs *c = trans->c; trace_and_count(c, btree_node_free, trans, b); BUG_ON(btree_node_write_blocked(b)); BUG_ON(btree_node_dirty(b)); BUG_ON(btree_node_need_write(b)); BUG_ON(b == btree_node_root(c, b)); BUG_ON(b->ob.nr); BUG_ON(!list_empty(&b->write_blocked)); BUG_ON(b->will_make_reachable); clear_btree_node_noevict(b); } static void bch2_btree_node_free_inmem(struct btree_trans *trans, struct btree_path *path, struct btree *b) { struct bch_fs *c = trans->c; bch2_btree_node_lock_write_nofail(trans, path, &b->c); __btree_node_free(trans, b); mutex_lock(&c->btree_cache.lock); bch2_btree_node_hash_remove(&c->btree_cache, b); mutex_unlock(&c->btree_cache.lock); six_unlock_write(&b->c.lock); mark_btree_node_locked_noreset(path, b->c.level, BTREE_NODE_INTENT_LOCKED); bch2_trans_node_drop(trans, b); } static void bch2_btree_node_free_never_used(struct btree_update *as, struct btree_trans *trans, struct btree *b) { struct bch_fs *c = as->c; struct prealloc_nodes *p = &as->prealloc_nodes[b->c.lock.readers != NULL]; BUG_ON(!list_empty(&b->write_blocked)); BUG_ON(b->will_make_reachable != (1UL|(unsigned long) as)); b->will_make_reachable = 0; closure_put(&as->cl); clear_btree_node_will_make_reachable(b); clear_btree_node_accessed(b); clear_btree_node_dirty_acct(c, b); clear_btree_node_need_write(b); mutex_lock(&c->btree_cache.lock); __bch2_btree_node_hash_remove(&c->btree_cache, b); mutex_unlock(&c->btree_cache.lock); BUG_ON(p->nr >= ARRAY_SIZE(p->b)); p->b[p->nr++] = b; six_unlock_intent(&b->c.lock); bch2_trans_node_drop(trans, b); } static struct btree *__bch2_btree_node_alloc(struct btree_trans *trans, struct disk_reservation *res, struct closure *cl, bool interior_node, unsigned flags) { struct bch_fs *c = trans->c; struct write_point *wp; struct btree *b; BKEY_PADDED_ONSTACK(k, BKEY_BTREE_PTR_VAL_U64s_MAX) tmp; struct open_buckets obs = { .nr = 0 }; struct bch_devs_list devs_have = (struct bch_devs_list) { 0 }; enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; unsigned nr_reserve = watermark < BCH_WATERMARK_reclaim ? BTREE_NODE_RESERVE : 0; int ret; b = bch2_btree_node_mem_alloc(trans, interior_node); if (IS_ERR(b)) return b; BUG_ON(b->ob.nr); mutex_lock(&c->btree_reserve_cache_lock); if (c->btree_reserve_cache_nr > nr_reserve) { struct btree_alloc *a = &c->btree_reserve_cache[--c->btree_reserve_cache_nr]; obs = a->ob; bkey_copy(&tmp.k, &a->k); mutex_unlock(&c->btree_reserve_cache_lock); goto out; } mutex_unlock(&c->btree_reserve_cache_lock); retry: ret = bch2_alloc_sectors_start_trans(trans, c->opts.metadata_target ?: c->opts.foreground_target, 0, writepoint_ptr(&c->btree_write_point), &devs_have, res->nr_replicas, min(res->nr_replicas, c->opts.metadata_replicas_required), watermark, 0, cl, &wp); if (unlikely(ret)) goto err; if (wp->sectors_free < btree_sectors(c)) { struct open_bucket *ob; unsigned i; open_bucket_for_each(c, &wp->ptrs, ob, i) if (ob->sectors_free < btree_sectors(c)) ob->sectors_free = 0; bch2_alloc_sectors_done(c, wp); goto retry; } bkey_btree_ptr_v2_init(&tmp.k); bch2_alloc_sectors_append_ptrs(c, wp, &tmp.k, btree_sectors(c), false); bch2_open_bucket_get(c, wp, &obs); bch2_alloc_sectors_done(c, wp); out: bkey_copy(&b->key, &tmp.k); b->ob = obs; six_unlock_write(&b->c.lock); six_unlock_intent(&b->c.lock); return b; err: bch2_btree_node_to_freelist(c, b); return ERR_PTR(ret); } static struct btree *bch2_btree_node_alloc(struct btree_update *as, struct btree_trans *trans, unsigned level) { struct bch_fs *c = as->c; struct btree *b; struct prealloc_nodes *p = &as->prealloc_nodes[!!level]; int ret; BUG_ON(level >= BTREE_MAX_DEPTH); BUG_ON(!p->nr); b = p->b[--p->nr]; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_intent); btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_write); set_btree_node_accessed(b); set_btree_node_dirty_acct(c, b); set_btree_node_need_write(b); bch2_bset_init_first(b, &b->data->keys); b->c.level = level; b->c.btree_id = as->btree_id; b->version_ondisk = c->sb.version; memset(&b->nr, 0, sizeof(b->nr)); b->data->magic = cpu_to_le64(bset_magic(c)); memset(&b->data->_ptr, 0, sizeof(b->data->_ptr)); b->data->flags = 0; SET_BTREE_NODE_ID(b->data, as->btree_id); SET_BTREE_NODE_LEVEL(b->data, level); if (b->key.k.type == KEY_TYPE_btree_ptr_v2) { struct bkey_i_btree_ptr_v2 *bp = bkey_i_to_btree_ptr_v2(&b->key); bp->v.mem_ptr = 0; bp->v.seq = b->data->keys.seq; bp->v.sectors_written = 0; } SET_BTREE_NODE_NEW_EXTENT_OVERWRITE(b->data, true); bch2_btree_build_aux_trees(b); ret = bch2_btree_node_hash_insert(&c->btree_cache, b, level, as->btree_id); BUG_ON(ret); trace_and_count(c, btree_node_alloc, trans, b); bch2_increment_clock(c, btree_sectors(c), WRITE); return b; } static void btree_set_min(struct btree *b, struct bpos pos) { if (b->key.k.type == KEY_TYPE_btree_ptr_v2) bkey_i_to_btree_ptr_v2(&b->key)->v.min_key = pos; b->data->min_key = pos; } static void btree_set_max(struct btree *b, struct bpos pos) { b->key.k.p = pos; b->data->max_key = pos; } static struct btree *bch2_btree_node_alloc_replacement(struct btree_update *as, struct btree_trans *trans, struct btree *b) { struct btree *n = bch2_btree_node_alloc(as, trans, b->c.level); struct bkey_format format = bch2_btree_calc_format(b); /* * The keys might expand with the new format - if they wouldn't fit in * the btree node anymore, use the old format for now: */ if (!bch2_btree_node_format_fits(as->c, b, b->nr, &format)) format = b->format; SET_BTREE_NODE_SEQ(n->data, BTREE_NODE_SEQ(b->data) + 1); btree_set_min(n, b->data->min_key); btree_set_max(n, b->data->max_key); n->data->format = format; btree_node_set_format(n, format); bch2_btree_sort_into(as->c, n, b); btree_node_reset_sib_u64s(n); return n; } static struct btree *__btree_root_alloc(struct btree_update *as, struct btree_trans *trans, unsigned level) { struct btree *b = bch2_btree_node_alloc(as, trans, level); btree_set_min(b, POS_MIN); btree_set_max(b, SPOS_MAX); b->data->format = bch2_btree_calc_format(b); btree_node_set_format(b, b->data->format); bch2_btree_build_aux_trees(b); return b; } static void bch2_btree_reserve_put(struct btree_update *as, struct btree_trans *trans) { struct bch_fs *c = as->c; struct prealloc_nodes *p; for (p = as->prealloc_nodes; p < as->prealloc_nodes + ARRAY_SIZE(as->prealloc_nodes); p++) { while (p->nr) { struct btree *b = p->b[--p->nr]; mutex_lock(&c->btree_reserve_cache_lock); if (c->btree_reserve_cache_nr < ARRAY_SIZE(c->btree_reserve_cache)) { struct btree_alloc *a = &c->btree_reserve_cache[c->btree_reserve_cache_nr++]; a->ob = b->ob; b->ob.nr = 0; bkey_copy(&a->k, &b->key); } else { bch2_open_buckets_put(c, &b->ob); } mutex_unlock(&c->btree_reserve_cache_lock); btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_intent); btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_write); __btree_node_free(trans, b); bch2_btree_node_to_freelist(c, b); } } } static int bch2_btree_reserve_get(struct btree_trans *trans, struct btree_update *as, unsigned nr_nodes[2], unsigned flags, struct closure *cl) { struct btree *b; unsigned interior; int ret = 0; BUG_ON(nr_nodes[0] + nr_nodes[1] > BTREE_RESERVE_MAX); /* * Protects reaping from the btree node cache and using the btree node * open bucket reserve: */ ret = bch2_btree_cache_cannibalize_lock(trans, cl); if (ret) return ret; for (interior = 0; interior < 2; interior++) { struct prealloc_nodes *p = as->prealloc_nodes + interior; while (p->nr < nr_nodes[interior]) { b = __bch2_btree_node_alloc(trans, &as->disk_res, cl, interior, flags); if (IS_ERR(b)) { ret = PTR_ERR(b); goto err; } p->b[p->nr++] = b; } } err: bch2_btree_cache_cannibalize_unlock(trans); return ret; } /* Asynchronous interior node update machinery */ static void bch2_btree_update_free(struct btree_update *as, struct btree_trans *trans) { struct bch_fs *c = as->c; if (as->took_gc_lock) up_read(&c->gc_lock); as->took_gc_lock = false; bch2_journal_pin_drop(&c->journal, &as->journal); bch2_journal_pin_flush(&c->journal, &as->journal); bch2_disk_reservation_put(c, &as->disk_res); bch2_btree_reserve_put(as, trans); bch2_time_stats_update(&c->times[BCH_TIME_btree_interior_update_total], as->start_time); mutex_lock(&c->btree_interior_update_lock); list_del(&as->unwritten_list); list_del(&as->list); closure_debug_destroy(&as->cl); mempool_free(as, &c->btree_interior_update_pool); /* * Have to do the wakeup with btree_interior_update_lock still held, * since being on btree_interior_update_list is our ref on @c: */ closure_wake_up(&c->btree_interior_update_wait); mutex_unlock(&c->btree_interior_update_lock); } static void btree_update_add_key(struct btree_update *as, struct keylist *keys, struct btree *b) { struct bkey_i *k = &b->key; BUG_ON(bch2_keylist_u64s(keys) + k->k.u64s > ARRAY_SIZE(as->_old_keys)); bkey_copy(keys->top, k); bkey_i_to_btree_ptr_v2(keys->top)->v.mem_ptr = b->c.level + 1; bch2_keylist_push(keys); } static bool btree_update_new_nodes_marked_sb(struct btree_update *as) { for_each_keylist_key(&as->new_keys, k) if (!bch2_dev_btree_bitmap_marked(as->c, bkey_i_to_s_c(k))) return false; return true; } static void btree_update_new_nodes_mark_sb(struct btree_update *as) { struct bch_fs *c = as->c; mutex_lock(&c->sb_lock); for_each_keylist_key(&as->new_keys, k) bch2_dev_btree_bitmap_mark(c, bkey_i_to_s_c(k)); bch2_write_super(c); mutex_unlock(&c->sb_lock); } /* * The transactional part of an interior btree node update, where we journal the * update we did to the interior node and update alloc info: */ static int btree_update_nodes_written_trans(struct btree_trans *trans, struct btree_update *as) { struct jset_entry *e = bch2_trans_jset_entry_alloc(trans, as->journal_u64s); int ret = PTR_ERR_OR_ZERO(e); if (ret) return ret; memcpy(e, as->journal_entries, as->journal_u64s * sizeof(u64)); trans->journal_pin = &as->journal; for_each_keylist_key(&as->old_keys, k) { unsigned level = bkey_i_to_btree_ptr_v2(k)->v.mem_ptr; ret = bch2_key_trigger_old(trans, as->btree_id, level, bkey_i_to_s_c(k), BTREE_TRIGGER_transactional); if (ret) return ret; } for_each_keylist_key(&as->new_keys, k) { unsigned level = bkey_i_to_btree_ptr_v2(k)->v.mem_ptr; ret = bch2_key_trigger_new(trans, as->btree_id, level, bkey_i_to_s(k), BTREE_TRIGGER_transactional); if (ret) return ret; } return 0; } /* If the node has been reused, we might be reading uninitialized memory - that's fine: */ static noinline __no_kmsan_checks bool btree_node_seq_matches(struct btree *b, __le64 seq) { struct btree_node *b_data = READ_ONCE(b->data); return (b_data ? b_data->keys.seq : 0) == seq; } static void btree_update_nodes_written(struct btree_update *as) { struct bch_fs *c = as->c; struct btree *b; struct btree_trans *trans = bch2_trans_get(c); u64 journal_seq = 0; unsigned i; int ret; /* * If we're already in an error state, it might be because a btree node * was never written, and we might be trying to free that same btree * node here, but it won't have been marked as allocated and we'll see * spurious disk usage inconsistencies in the transactional part below * if we don't skip it: */ ret = bch2_journal_error(&c->journal); if (ret) goto err; if (!btree_update_new_nodes_marked_sb(as)) btree_update_new_nodes_mark_sb(as); /* * Wait for any in flight writes to finish before we free the old nodes * on disk: */ for (i = 0; i < as->nr_old_nodes; i++) { b = as->old_nodes[i]; if (btree_node_seq_matches(b, as->old_nodes_seq[i])) wait_on_bit_io(&b->flags, BTREE_NODE_write_in_flight_inner, TASK_UNINTERRUPTIBLE); } /* * We did an update to a parent node where the pointers we added pointed * to child nodes that weren't written yet: now, the child nodes have * been written so we can write out the update to the interior node. */ /* * We can't call into journal reclaim here: we'd block on the journal * reclaim lock, but we may need to release the open buckets we have * pinned in order for other btree updates to make forward progress, and * journal reclaim does btree updates when flushing bkey_cached entries, * which may require allocations as well. */ ret = commit_do(trans, &as->disk_res, &journal_seq, BCH_WATERMARK_interior_updates| BCH_TRANS_COMMIT_no_enospc| BCH_TRANS_COMMIT_no_check_rw| BCH_TRANS_COMMIT_journal_reclaim, btree_update_nodes_written_trans(trans, as)); bch2_trans_unlock(trans); bch2_fs_fatal_err_on(ret && !bch2_journal_error(&c->journal), c, "%s", bch2_err_str(ret)); err: /* * Ensure transaction is unlocked before using btree_node_lock_nopath() * (the use of which is always suspect, we need to work on removing this * in the future) * * It should be, but bch2_path_get_unlocked_mut() -> bch2_path_get() * calls bch2_path_upgrade(), before we call path_make_mut(), so we may * rarely end up with a locked path besides the one we have here: */ bch2_trans_unlock(trans); bch2_trans_begin(trans); /* * We have to be careful because another thread might be getting ready * to free as->b and calling btree_update_reparent() on us - we'll * recheck under btree_update_lock below: */ b = READ_ONCE(as->b); if (b) { /* * @b is the node we did the final insert into: * * On failure to get a journal reservation, we still have to * unblock the write and allow most of the write path to happen * so that shutdown works, but the i->journal_seq mechanism * won't work to prevent the btree write from being visible (we * didn't get a journal sequence number) - instead * __bch2_btree_node_write() doesn't do the actual write if * we're in journal error state: */ btree_path_idx_t path_idx = bch2_path_get_unlocked_mut(trans, as->btree_id, b->c.level, b->key.k.p); struct btree_path *path = trans->paths + path_idx; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_intent); mark_btree_node_locked(trans, path, b->c.level, BTREE_NODE_INTENT_LOCKED); path->l[b->c.level].lock_seq = six_lock_seq(&b->c.lock); path->l[b->c.level].b = b; bch2_btree_node_lock_write_nofail(trans, path, &b->c); mutex_lock(&c->btree_interior_update_lock); list_del(&as->write_blocked_list); if (list_empty(&b->write_blocked)) clear_btree_node_write_blocked(b); /* * Node might have been freed, recheck under * btree_interior_update_lock: */ if (as->b == b) { BUG_ON(!b->c.level); BUG_ON(!btree_node_dirty(b)); if (!ret) { struct bset *last = btree_bset_last(b); last->journal_seq = cpu_to_le64( max(journal_seq, le64_to_cpu(last->journal_seq))); bch2_btree_add_journal_pin(c, b, journal_seq); } else { /* * If we didn't get a journal sequence number we * can't write this btree node, because recovery * won't know to ignore this write: */ set_btree_node_never_write(b); } } mutex_unlock(&c->btree_interior_update_lock); mark_btree_node_locked_noreset(path, b->c.level, BTREE_NODE_INTENT_LOCKED); six_unlock_write(&b->c.lock); btree_node_write_if_need(trans, b, SIX_LOCK_intent); btree_node_unlock(trans, path, b->c.level); bch2_path_put(trans, path_idx, true); } bch2_journal_pin_drop(&c->journal, &as->journal); mutex_lock(&c->btree_interior_update_lock); for (i = 0; i < as->nr_new_nodes; i++) { b = as->new_nodes[i]; BUG_ON(b->will_make_reachable != (unsigned long) as); b->will_make_reachable = 0; clear_btree_node_will_make_reachable(b); } mutex_unlock(&c->btree_interior_update_lock); for (i = 0; i < as->nr_new_nodes; i++) { b = as->new_nodes[i]; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read); btree_node_write_if_need(trans, b, SIX_LOCK_read); six_unlock_read(&b->c.lock); } for (i = 0; i < as->nr_open_buckets; i++) bch2_open_bucket_put(c, c->open_buckets + as->open_buckets[i]); bch2_btree_update_free(as, trans); bch2_trans_put(trans); } static void btree_interior_update_work(struct work_struct *work) { struct bch_fs *c = container_of(work, struct bch_fs, btree_interior_update_work); struct btree_update *as; while (1) { mutex_lock(&c->btree_interior_update_lock); as = list_first_entry_or_null(&c->btree_interior_updates_unwritten, struct btree_update, unwritten_list); if (as && !as->nodes_written) as = NULL; mutex_unlock(&c->btree_interior_update_lock); if (!as) break; btree_update_nodes_written(as); } } static CLOSURE_CALLBACK(btree_update_set_nodes_written) { closure_type(as, struct btree_update, cl); struct bch_fs *c = as->c; mutex_lock(&c->btree_interior_update_lock); as->nodes_written = true; mutex_unlock(&c->btree_interior_update_lock); queue_work(c->btree_interior_update_worker, &c->btree_interior_update_work); } /* * We're updating @b with pointers to nodes that haven't finished writing yet: * block @b from being written until @as completes */ static void btree_update_updated_node(struct btree_update *as, struct btree *b) { struct bch_fs *c = as->c; BUG_ON(as->mode != BTREE_UPDATE_none); BUG_ON(as->update_level_end < b->c.level); BUG_ON(!btree_node_dirty(b)); BUG_ON(!b->c.level); mutex_lock(&c->btree_interior_update_lock); list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten); as->mode = BTREE_UPDATE_node; as->b = b; as->update_level_end = b->c.level; set_btree_node_write_blocked(b); list_add(&as->write_blocked_list, &b->write_blocked); mutex_unlock(&c->btree_interior_update_lock); } static int bch2_update_reparent_journal_pin_flush(struct journal *j, struct journal_entry_pin *_pin, u64 seq) { return 0; } static void btree_update_reparent(struct btree_update *as, struct btree_update *child) { struct bch_fs *c = as->c; lockdep_assert_held(&c->btree_interior_update_lock); child->b = NULL; child->mode = BTREE_UPDATE_update; bch2_journal_pin_copy(&c->journal, &as->journal, &child->journal, bch2_update_reparent_journal_pin_flush); } static void btree_update_updated_root(struct btree_update *as, struct btree *b) { struct bkey_i *insert = &b->key; struct bch_fs *c = as->c; BUG_ON(as->mode != BTREE_UPDATE_none); BUG_ON(as->journal_u64s + jset_u64s(insert->k.u64s) > ARRAY_SIZE(as->journal_entries)); as->journal_u64s += journal_entry_set((void *) &as->journal_entries[as->journal_u64s], BCH_JSET_ENTRY_btree_root, b->c.btree_id, b->c.level, insert, insert->k.u64s); mutex_lock(&c->btree_interior_update_lock); list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten); as->mode = BTREE_UPDATE_root; mutex_unlock(&c->btree_interior_update_lock); } /* * bch2_btree_update_add_new_node: * * This causes @as to wait on @b to be written, before it gets to * bch2_btree_update_nodes_written * * Additionally, it sets b->will_make_reachable to prevent any additional writes * to @b from happening besides the first until @b is reachable on disk * * And it adds @b to the list of @as's new nodes, so that we can update sector * counts in bch2_btree_update_nodes_written: */ static void bch2_btree_update_add_new_node(struct btree_update *as, struct btree *b) { struct bch_fs *c = as->c; closure_get(&as->cl); mutex_lock(&c->btree_interior_update_lock); BUG_ON(as->nr_new_nodes >= ARRAY_SIZE(as->new_nodes)); BUG_ON(b->will_make_reachable); as->new_nodes[as->nr_new_nodes++] = b; b->will_make_reachable = 1UL|(unsigned long) as; set_btree_node_will_make_reachable(b); mutex_unlock(&c->btree_interior_update_lock); btree_update_add_key(as, &as->new_keys, b); if (b->key.k.type == KEY_TYPE_btree_ptr_v2) { unsigned bytes = vstruct_end(&b->data->keys) - (void *) b->data; unsigned sectors = round_up(bytes, block_bytes(c)) >> 9; bkey_i_to_btree_ptr_v2(&b->key)->v.sectors_written = cpu_to_le16(sectors); } } /* * returns true if @b was a new node */ static void btree_update_drop_new_node(struct bch_fs *c, struct btree *b) { struct btree_update *as; unsigned long v; unsigned i; mutex_lock(&c->btree_interior_update_lock); /* * When b->will_make_reachable != 0, it owns a ref on as->cl that's * dropped when it gets written by bch2_btree_complete_write - the * xchg() is for synchronization with bch2_btree_complete_write: */ v = xchg(&b->will_make_reachable, 0); clear_btree_node_will_make_reachable(b); as = (struct btree_update *) (v & ~1UL); if (!as) { mutex_unlock(&c->btree_interior_update_lock); return; } for (i = 0; i < as->nr_new_nodes; i++) if (as->new_nodes[i] == b) goto found; BUG(); found: array_remove_item(as->new_nodes, as->nr_new_nodes, i); mutex_unlock(&c->btree_interior_update_lock); if (v & 1) closure_put(&as->cl); } static void bch2_btree_update_get_open_buckets(struct btree_update *as, struct btree *b) { while (b->ob.nr) as->open_buckets[as->nr_open_buckets++] = b->ob.v[--b->ob.nr]; } static int bch2_btree_update_will_free_node_journal_pin_flush(struct journal *j, struct journal_entry_pin *_pin, u64 seq) { return 0; } /* * @b is being split/rewritten: it may have pointers to not-yet-written btree * nodes and thus outstanding btree_updates - redirect @b's * btree_updates to point to this btree_update: */ static void bch2_btree_interior_update_will_free_node(struct btree_update *as, struct btree *b) { struct bch_fs *c = as->c; struct btree_update *p, *n; struct btree_write *w; set_btree_node_dying(b); if (btree_node_fake(b)) return; mutex_lock(&c->btree_interior_update_lock); /* * Does this node have any btree_update operations preventing * it from being written? * * If so, redirect them to point to this btree_update: we can * write out our new nodes, but we won't make them visible until those * operations complete */ list_for_each_entry_safe(p, n, &b->write_blocked, write_blocked_list) { list_del_init(&p->write_blocked_list); btree_update_reparent(as, p); /* * for flush_held_btree_writes() waiting on updates to flush or * nodes to be writeable: */ closure_wake_up(&c->btree_interior_update_wait); } clear_btree_node_dirty_acct(c, b); clear_btree_node_need_write(b); clear_btree_node_write_blocked(b); /* * Does this node have unwritten data that has a pin on the journal? * * If so, transfer that pin to the btree_update operation - * note that if we're freeing multiple nodes, we only need to keep the * oldest pin of any of the nodes we're freeing. We'll release the pin * when the new nodes are persistent and reachable on disk: */ w = btree_current_write(b); bch2_journal_pin_copy(&c->journal, &as->journal, &w->journal, bch2_btree_update_will_free_node_journal_pin_flush); bch2_journal_pin_drop(&c->journal, &w->journal); w = btree_prev_write(b); bch2_journal_pin_copy(&c->journal, &as->journal, &w->journal, bch2_btree_update_will_free_node_journal_pin_flush); bch2_journal_pin_drop(&c->journal, &w->journal); mutex_unlock(&c->btree_interior_update_lock); /* * Is this a node that isn't reachable on disk yet? * * Nodes that aren't reachable yet have writes blocked until they're * reachable - now that we've cancelled any pending writes and moved * things waiting on that write to wait on this update, we can drop this * node from the list of nodes that the other update is making * reachable, prior to freeing it: */ btree_update_drop_new_node(c, b); btree_update_add_key(as, &as->old_keys, b); as->old_nodes[as->nr_old_nodes] = b; as->old_nodes_seq[as->nr_old_nodes] = b->data->keys.seq; as->nr_old_nodes++; } static void bch2_btree_update_done(struct btree_update *as, struct btree_trans *trans) { struct bch_fs *c = as->c; u64 start_time = as->start_time; BUG_ON(as->mode == BTREE_UPDATE_none); if (as->took_gc_lock) up_read(&as->c->gc_lock); as->took_gc_lock = false; bch2_btree_reserve_put(as, trans); continue_at(&as->cl, btree_update_set_nodes_written, as->c->btree_interior_update_worker); bch2_time_stats_update(&c->times[BCH_TIME_btree_interior_update_foreground], start_time); } static struct btree_update * bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, unsigned level_start, bool split, unsigned flags) { struct bch_fs *c = trans->c; struct btree_update *as; u64 start_time = local_clock(); int disk_res_flags = (flags & BCH_TRANS_COMMIT_no_enospc) ? BCH_DISK_RESERVATION_NOFAIL : 0; unsigned nr_nodes[2] = { 0, 0 }; unsigned level_end = level_start; enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; int ret = 0; u32 restart_count = trans->restart_count; BUG_ON(!path->should_be_locked); if (watermark == BCH_WATERMARK_copygc) watermark = BCH_WATERMARK_btree_copygc; if (watermark < BCH_WATERMARK_btree) watermark = BCH_WATERMARK_btree; flags &= ~BCH_WATERMARK_MASK; flags |= watermark; if (watermark < BCH_WATERMARK_reclaim && test_bit(JOURNAL_space_low, &c->journal.flags)) { if (flags & BCH_TRANS_COMMIT_journal_reclaim) return ERR_PTR(-BCH_ERR_journal_reclaim_would_deadlock); ret = drop_locks_do(trans, ({ wait_event(c->journal.wait, !test_bit(JOURNAL_space_low, &c->journal.flags)); 0; })); if (ret) return ERR_PTR(ret); } while (1) { nr_nodes[!!level_end] += 1 + split; level_end++; ret = bch2_btree_path_upgrade(trans, path, level_end + 1); if (ret) return ERR_PTR(ret); if (!btree_path_node(path, level_end)) { /* Allocating new root? */ nr_nodes[1] += split; level_end = BTREE_MAX_DEPTH; break; } /* * Always check for space for two keys, even if we won't have to * split at prior level - it might have been a merge instead: */ if (bch2_btree_node_insert_fits(path->l[level_end].b, BKEY_BTREE_PTR_U64s_MAX * 2)) break; split = path->l[level_end].b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c); } if (!down_read_trylock(&c->gc_lock)) { ret = drop_locks_do(trans, (down_read(&c->gc_lock), 0)); if (ret) { up_read(&c->gc_lock); return ERR_PTR(ret); } } as = mempool_alloc(&c->btree_interior_update_pool, GFP_NOFS); memset(as, 0, sizeof(*as)); closure_init(&as->cl, NULL); as->c = c; as->start_time = start_time; as->ip_started = _RET_IP_; as->mode = BTREE_UPDATE_none; as->flags = flags; as->took_gc_lock = true; as->btree_id = path->btree_id; as->update_level_start = level_start; as->update_level_end = level_end; INIT_LIST_HEAD(&as->list); INIT_LIST_HEAD(&as->unwritten_list); INIT_LIST_HEAD(&as->write_blocked_list); bch2_keylist_init(&as->old_keys, as->_old_keys); bch2_keylist_init(&as->new_keys, as->_new_keys); bch2_keylist_init(&as->parent_keys, as->inline_keys); mutex_lock(&c->btree_interior_update_lock); list_add_tail(&as->list, &c->btree_interior_update_list); mutex_unlock(&c->btree_interior_update_lock); /* * We don't want to allocate if we're in an error state, that can cause * deadlock on emergency shutdown due to open buckets getting stuck in * the btree_reserve_cache after allocator shutdown has cleared it out. * This check needs to come after adding us to the btree_interior_update * list but before calling bch2_btree_reserve_get, to synchronize with * __bch2_fs_read_only(). */ ret = bch2_journal_error(&c->journal); if (ret) goto err; ret = bch2_disk_reservation_get(c, &as->disk_res, (nr_nodes[0] + nr_nodes[1]) * btree_sectors(c), c->opts.metadata_replicas, disk_res_flags); if (ret) goto err; ret = bch2_btree_reserve_get(trans, as, nr_nodes, flags, NULL); if (bch2_err_matches(ret, ENOSPC) || bch2_err_matches(ret, ENOMEM)) { struct closure cl; /* * XXX: this should probably be a separate BTREE_INSERT_NONBLOCK * flag */ if (bch2_err_matches(ret, ENOSPC) && (flags & BCH_TRANS_COMMIT_journal_reclaim) && watermark < BCH_WATERMARK_reclaim) { ret = -BCH_ERR_journal_reclaim_would_deadlock; goto err; } closure_init_stack(&cl); do { ret = bch2_btree_reserve_get(trans, as, nr_nodes, flags, &cl); bch2_trans_unlock(trans); bch2_wait_on_allocator(c, &cl); } while (bch2_err_matches(ret, BCH_ERR_operation_blocked)); } if (ret) { trace_and_count(c, btree_reserve_get_fail, trans->fn, _RET_IP_, nr_nodes[0] + nr_nodes[1], ret); goto err; } ret = bch2_trans_relock(trans); if (ret) goto err; bch2_trans_verify_not_restarted(trans, restart_count); return as; err: bch2_btree_update_free(as, trans); if (!bch2_err_matches(ret, ENOSPC) && !bch2_err_matches(ret, EROFS) && ret != -BCH_ERR_journal_reclaim_would_deadlock) bch_err_fn_ratelimited(c, ret); return ERR_PTR(ret); } /* Btree root updates: */ static void bch2_btree_set_root_inmem(struct bch_fs *c, struct btree *b) { /* Root nodes cannot be reaped */ mutex_lock(&c->btree_cache.lock); list_del_init(&b->list); mutex_unlock(&c->btree_cache.lock); mutex_lock(&c->btree_root_lock); bch2_btree_id_root(c, b->c.btree_id)->b = b; mutex_unlock(&c->btree_root_lock); bch2_recalc_btree_reserve(c); } static int bch2_btree_set_root(struct btree_update *as, struct btree_trans *trans, struct btree_path *path, struct btree *b, bool nofail) { struct bch_fs *c = as->c; trace_and_count(c, btree_node_set_root, trans, b); struct btree *old = btree_node_root(c, b); /* * Ensure no one is using the old root while we switch to the * new root: */ if (nofail) { bch2_btree_node_lock_write_nofail(trans, path, &old->c); } else { int ret = bch2_btree_node_lock_write(trans, path, &old->c); if (ret) return ret; } bch2_btree_set_root_inmem(c, b); btree_update_updated_root(as, b); /* * Unlock old root after new root is visible: * * The new root isn't persistent, but that's ok: we still have * an intent lock on the new root, and any updates that would * depend on the new root would have to update the new root. */ bch2_btree_node_unlock_write(trans, path, old); return 0; } /* Interior node updates: */ static void bch2_insert_fixup_btree_ptr(struct btree_update *as, struct btree_trans *trans, struct btree_path *path, struct btree *b, struct btree_node_iter *node_iter, struct bkey_i *insert) { struct bch_fs *c = as->c; struct bkey_packed *k; struct printbuf buf = PRINTBUF; unsigned long old, new; BUG_ON(insert->k.type == KEY_TYPE_btree_ptr_v2 && !btree_ptr_sectors_written(bkey_i_to_s_c(insert))); if (unlikely(!test_bit(JOURNAL_replay_done, &c->journal.flags))) bch2_journal_key_overwritten(c, b->c.btree_id, b->c.level, insert->k.p); struct bkey_validate_context from = (struct bkey_validate_context) { .from = BKEY_VALIDATE_btree_node, .level = b->c.level, .btree = b->c.btree_id, .flags = BCH_VALIDATE_commit, }; if (bch2_bkey_validate(c, bkey_i_to_s_c(insert), from) ?: bch2_bkey_in_btree_node(c, b, bkey_i_to_s_c(insert), from)) { bch2_fs_inconsistent(c, "%s: inserting invalid bkey", __func__); dump_stack(); } BUG_ON(as->journal_u64s + jset_u64s(insert->k.u64s) > ARRAY_SIZE(as->journal_entries)); as->journal_u64s += journal_entry_set((void *) &as->journal_entries[as->journal_u64s], BCH_JSET_ENTRY_btree_keys, b->c.btree_id, b->c.level, insert, insert->k.u64s); while ((k = bch2_btree_node_iter_peek_all(node_iter, b)) && bkey_iter_pos_cmp(b, k, &insert->k.p) < 0) bch2_btree_node_iter_advance(node_iter, b); bch2_btree_bset_insert_key(trans, path, b, node_iter, insert); set_btree_node_dirty_acct(c, b); old = READ_ONCE(b->flags); do { new = old; new &= ~BTREE_WRITE_TYPE_MASK; new |= BTREE_WRITE_interior; new |= 1 << BTREE_NODE_need_write; } while (!try_cmpxchg(&b->flags, &old, new)); printbuf_exit(&buf); } static void bch2_btree_insert_keys_interior(struct btree_update *as, struct btree_trans *trans, struct btree_path *path, struct btree *b, struct btree_node_iter node_iter, struct keylist *keys) { struct bkey_i *insert = bch2_keylist_front(keys); struct bkey_packed *k; BUG_ON(btree_node_type(b) != BKEY_TYPE_btree); while ((k = bch2_btree_node_iter_prev_all(&node_iter, b)) && (bkey_cmp_left_packed(b, k, &insert->k.p) >= 0)) ; for (; insert != keys->top && bpos_le(insert->k.p, b->key.k.p); insert = bkey_next(insert)) bch2_insert_fixup_btree_ptr(as, trans, path, b, &node_iter, insert); if (bch2_btree_node_check_topology(trans, b)) { struct printbuf buf = PRINTBUF; for (struct bkey_i *k = keys->keys; k != insert; k = bkey_next(k)) { bch2_bkey_val_to_text(&buf, trans->c, bkey_i_to_s_c(k)); prt_newline(&buf); } panic("%s(): check_topology error: inserted keys\n%s", __func__, buf.buf); } memmove_u64s_down(keys->keys, insert, keys->top_p - insert->_data); keys->top_p -= insert->_data - keys->keys_p; } static bool key_deleted_in_insert(struct keylist *insert_keys, struct bpos pos) { if (insert_keys) for_each_keylist_key(insert_keys, k) if (bkey_deleted(&k->k) && bpos_eq(k->k.p, pos)) return true; return false; } /* * Move keys from n1 (original replacement node, now lower node) to n2 (higher * node) */ static void __btree_split_node(struct btree_update *as, struct btree_trans *trans, struct btree *b, struct btree *n[2], struct keylist *insert_keys) { struct bkey_packed *k; struct bpos n1_pos = POS_MIN; struct btree_node_iter iter; struct bset *bsets[2]; struct bkey_format_state format[2]; struct bkey_packed *out[2]; struct bkey uk; unsigned u64s, n1_u64s = (b->nr.live_u64s * 3) / 5; struct { unsigned nr_keys, val_u64s; } nr_keys[2]; int i; memset(&nr_keys, 0, sizeof(nr_keys)); for (i = 0; i < 2; i++) { BUG_ON(n[i]->nsets != 1); bsets[i] = btree_bset_first(n[i]); out[i] = bsets[i]->start; SET_BTREE_NODE_SEQ(n[i]->data, BTREE_NODE_SEQ(b->data) + 1); bch2_bkey_format_init(&format[i]); } u64s = 0; for_each_btree_node_key(b, k, &iter) { if (bkey_deleted(k)) continue; uk = bkey_unpack_key(b, k); if (b->c.level && u64s < n1_u64s && u64s + k->u64s >= n1_u64s && (bch2_key_deleted_in_journal(trans, b->c.btree_id, b->c.level, uk.p) || key_deleted_in_insert(insert_keys, uk.p))) n1_u64s += k->u64s; i = u64s >= n1_u64s; u64s += k->u64s; if (!i) n1_pos = uk.p; bch2_bkey_format_add_key(&format[i], &uk); nr_keys[i].nr_keys++; nr_keys[i].val_u64s += bkeyp_val_u64s(&b->format, k); } btree_set_min(n[0], b->data->min_key); btree_set_max(n[0], n1_pos); btree_set_min(n[1], bpos_successor(n1_pos)); btree_set_max(n[1], b->data->max_key); for (i = 0; i < 2; i++) { bch2_bkey_format_add_pos(&format[i], n[i]->data->min_key); bch2_bkey_format_add_pos(&format[i], n[i]->data->max_key); n[i]->data->format = bch2_bkey_format_done(&format[i]); unsigned u64s = nr_keys[i].nr_keys * n[i]->data->format.key_u64s + nr_keys[i].val_u64s; if (__vstruct_bytes(struct btree_node, u64s) > btree_buf_bytes(b)) n[i]->data->format = b->format; btree_node_set_format(n[i], n[i]->data->format); } u64s = 0; for_each_btree_node_key(b, k, &iter) { if (bkey_deleted(k)) continue; i = u64s >= n1_u64s; u64s += k->u64s; if (bch2_bkey_transform(&n[i]->format, out[i], bkey_packed(k) ? &b->format: &bch2_bkey_format_current, k)) out[i]->format = KEY_FORMAT_LOCAL_BTREE; else bch2_bkey_unpack(b, (void *) out[i], k); out[i]->needs_whiteout = false; btree_keys_account_key_add(&n[i]->nr, 0, out[i]); out[i] = bkey_p_next(out[i]); } for (i = 0; i < 2; i++) { bsets[i]->u64s = cpu_to_le16((u64 *) out[i] - bsets[i]->_data); BUG_ON(!bsets[i]->u64s); set_btree_bset_end(n[i], n[i]->set); btree_node_reset_sib_u64s(n[i]); bch2_verify_btree_nr_keys(n[i]); BUG_ON(bch2_btree_node_check_topology(trans, n[i])); } } /* * For updates to interior nodes, we've got to do the insert before we split * because the stuff we're inserting has to be inserted atomically. Post split, * the keys might have to go in different nodes and the split would no longer be * atomic. * * Worse, if the insert is from btree node coalescing, if we do the insert after * we do the split (and pick the pivot) - the pivot we pick might be between * nodes that were coalesced, and thus in the middle of a child node post * coalescing: */ static void btree_split_insert_keys(struct btree_update *as, struct btree_trans *trans, btree_path_idx_t path_idx, struct btree *b, struct keylist *keys) { struct btree_path *path = trans->paths + path_idx; if (!bch2_keylist_empty(keys) && bpos_le(bch2_keylist_front(keys)->k.p, b->data->max_key)) { struct btree_node_iter node_iter; bch2_btree_node_iter_init(&node_iter, b, &bch2_keylist_front(keys)->k.p); bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys); } } static int btree_split(struct btree_update *as, struct btree_trans *trans, btree_path_idx_t path, struct btree *b, struct keylist *keys) { struct bch_fs *c = as->c; struct btree *parent = btree_node_parent(trans->paths + path, b); struct btree *n1, *n2 = NULL, *n3 = NULL; btree_path_idx_t path1 = 0, path2 = 0; u64 start_time = local_clock(); int ret = 0; bch2_verify_btree_nr_keys(b); BUG_ON(!parent && (b != btree_node_root(c, b))); BUG_ON(parent && !btree_node_intent_locked(trans->paths + path, b->c.level + 1)); ret = bch2_btree_node_check_topology(trans, b); if (ret) return ret; if (b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c)) { struct btree *n[2]; trace_and_count(c, btree_node_split, trans, b); n[0] = n1 = bch2_btree_node_alloc(as, trans, b->c.level); n[1] = n2 = bch2_btree_node_alloc(as, trans, b->c.level); __btree_split_node(as, trans, b, n, keys); if (keys) { btree_split_insert_keys(as, trans, path, n1, keys); btree_split_insert_keys(as, trans, path, n2, keys); BUG_ON(!bch2_keylist_empty(keys)); } bch2_btree_build_aux_trees(n2); bch2_btree_build_aux_trees(n1); bch2_btree_update_add_new_node(as, n1); bch2_btree_update_add_new_node(as, n2); six_unlock_write(&n2->c.lock); six_unlock_write(&n1->c.lock); path1 = bch2_path_get_unlocked_mut(trans, as->btree_id, n1->c.level, n1->key.k.p); six_lock_increment(&n1->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + path1, n1->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + path1, n1); path2 = bch2_path_get_unlocked_mut(trans, as->btree_id, n2->c.level, n2->key.k.p); six_lock_increment(&n2->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + path2, n2->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + path2, n2); /* * Note that on recursive parent_keys == keys, so we * can't start adding new keys to parent_keys before emptying it * out (which we did with btree_split_insert_keys() above) */ bch2_keylist_add(&as->parent_keys, &n1->key); bch2_keylist_add(&as->parent_keys, &n2->key); if (!parent) { /* Depth increases, make a new root */ n3 = __btree_root_alloc(as, trans, b->c.level + 1); bch2_btree_update_add_new_node(as, n3); six_unlock_write(&n3->c.lock); trans->paths[path2].locks_want++; BUG_ON(btree_node_locked(trans->paths + path2, n3->c.level)); six_lock_increment(&n3->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + path2, n3->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + path2, n3); n3->sib_u64s[0] = U16_MAX; n3->sib_u64s[1] = U16_MAX; btree_split_insert_keys(as, trans, path, n3, &as->parent_keys); } } else { trace_and_count(c, btree_node_compact, trans, b); n1 = bch2_btree_node_alloc_replacement(as, trans, b); if (keys) { btree_split_insert_keys(as, trans, path, n1, keys); BUG_ON(!bch2_keylist_empty(keys)); } bch2_btree_build_aux_trees(n1); bch2_btree_update_add_new_node(as, n1); six_unlock_write(&n1->c.lock); path1 = bch2_path_get_unlocked_mut(trans, as->btree_id, n1->c.level, n1->key.k.p); six_lock_increment(&n1->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + path1, n1->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + path1, n1); if (parent) bch2_keylist_add(&as->parent_keys, &n1->key); } /* New nodes all written, now make them visible: */ if (parent) { /* Split a non root node */ ret = bch2_btree_insert_node(as, trans, path, parent, &as->parent_keys); } else if (n3) { ret = bch2_btree_set_root(as, trans, trans->paths + path, n3, false); } else { /* Root filled up but didn't need to be split */ ret = bch2_btree_set_root(as, trans, trans->paths + path, n1, false); } if (ret) goto err; bch2_btree_interior_update_will_free_node(as, b); if (n3) { bch2_btree_update_get_open_buckets(as, n3); bch2_btree_node_write_trans(trans, n3, SIX_LOCK_intent, 0); } if (n2) { bch2_btree_update_get_open_buckets(as, n2); bch2_btree_node_write_trans(trans, n2, SIX_LOCK_intent, 0); } bch2_btree_update_get_open_buckets(as, n1); bch2_btree_node_write_trans(trans, n1, SIX_LOCK_intent, 0); /* * The old node must be freed (in memory) _before_ unlocking the new * nodes - else another thread could re-acquire a read lock on the old * node after another thread has locked and updated the new node, thus * seeing stale data: */ bch2_btree_node_free_inmem(trans, trans->paths + path, b); if (n3) bch2_trans_node_add(trans, trans->paths + path, n3); if (n2) bch2_trans_node_add(trans, trans->paths + path2, n2); bch2_trans_node_add(trans, trans->paths + path1, n1); if (n3) six_unlock_intent(&n3->c.lock); if (n2) six_unlock_intent(&n2->c.lock); six_unlock_intent(&n1->c.lock); out: if (path2) { __bch2_btree_path_unlock(trans, trans->paths + path2); bch2_path_put(trans, path2, true); } if (path1) { __bch2_btree_path_unlock(trans, trans->paths + path1); bch2_path_put(trans, path1, true); } bch2_trans_verify_locks(trans); bch2_time_stats_update(&c->times[n2 ? BCH_TIME_btree_node_split : BCH_TIME_btree_node_compact], start_time); return ret; err: if (n3) bch2_btree_node_free_never_used(as, trans, n3); if (n2) bch2_btree_node_free_never_used(as, trans, n2); bch2_btree_node_free_never_used(as, trans, n1); goto out; } /** * bch2_btree_insert_node - insert bkeys into a given btree node * * @as: btree_update object * @trans: btree_trans object * @path_idx: path that points to current node * @b: node to insert keys into * @keys: list of keys to insert * * Returns: 0 on success, typically transaction restart error on failure * * Inserts as many keys as it can into a given btree node, splitting it if full. * If a split occurred, this function will return early. This can only happen * for leaf nodes -- inserts into interior nodes have to be atomic. */ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *trans, btree_path_idx_t path_idx, struct btree *b, struct keylist *keys) { struct bch_fs *c = as->c; struct btree_path *path = trans->paths + path_idx, *linked; unsigned i; int old_u64s = le16_to_cpu(btree_bset_last(b)->u64s); int old_live_u64s = b->nr.live_u64s; int live_u64s_added, u64s_added; int ret; lockdep_assert_held(&c->gc_lock); BUG_ON(!btree_node_intent_locked(path, b->c.level)); BUG_ON(!b->c.level); BUG_ON(!as || as->b); bch2_verify_keylist_sorted(keys); ret = bch2_btree_node_lock_write(trans, path, &b->c); if (ret) return ret; bch2_btree_node_prep_for_write(trans, path, b); if (!bch2_btree_node_insert_fits(b, bch2_keylist_u64s(keys))) { bch2_btree_node_unlock_write(trans, path, b); goto split; } ret = bch2_btree_node_check_topology(trans, b); if (ret) { bch2_btree_node_unlock_write(trans, path, b); return ret; } bch2_btree_insert_keys_interior(as, trans, path, b, path->l[b->c.level].iter, keys); trans_for_each_path_with_node(trans, b, linked, i) bch2_btree_node_iter_peek(&linked->l[b->c.level].iter, b); bch2_trans_verify_paths(trans); live_u64s_added = (int) b->nr.live_u64s - old_live_u64s; u64s_added = (int) le16_to_cpu(btree_bset_last(b)->u64s) - old_u64s; if (b->sib_u64s[0] != U16_MAX && live_u64s_added < 0) b->sib_u64s[0] = max(0, (int) b->sib_u64s[0] + live_u64s_added); if (b->sib_u64s[1] != U16_MAX && live_u64s_added < 0) b->sib_u64s[1] = max(0, (int) b->sib_u64s[1] + live_u64s_added); if (u64s_added > live_u64s_added && bch2_maybe_compact_whiteouts(c, b)) bch2_trans_node_reinit_iter(trans, b); btree_update_updated_node(as, b); bch2_btree_node_unlock_write(trans, path, b); return 0; split: /* * We could attempt to avoid the transaction restart, by calling * bch2_btree_path_upgrade() and allocating more nodes: */ if (b->c.level >= as->update_level_end) { trace_and_count(c, trans_restart_split_race, trans, _THIS_IP_, b); return btree_trans_restart(trans, BCH_ERR_transaction_restart_split_race); } return btree_split(as, trans, path_idx, b, keys); } int bch2_btree_split_leaf(struct btree_trans *trans, btree_path_idx_t path, unsigned flags) { /* btree_split & merge may both cause paths array to be reallocated */ struct btree *b = path_l(trans->paths + path)->b; struct btree_update *as; unsigned l; int ret = 0; as = bch2_btree_update_start(trans, trans->paths + path, trans->paths[path].level, true, flags); if (IS_ERR(as)) return PTR_ERR(as); ret = btree_split(as, trans, path, b, NULL); if (ret) { bch2_btree_update_free(as, trans); return ret; } bch2_btree_update_done(as, trans); for (l = trans->paths[path].level + 1; btree_node_intent_locked(&trans->paths[path], l) && !ret; l++) ret = bch2_foreground_maybe_merge(trans, path, l, flags); return ret; } static void __btree_increase_depth(struct btree_update *as, struct btree_trans *trans, btree_path_idx_t path_idx) { struct bch_fs *c = as->c; struct btree_path *path = trans->paths + path_idx; struct btree *n, *b = bch2_btree_id_root(c, path->btree_id)->b; BUG_ON(!btree_node_locked(path, b->c.level)); n = __btree_root_alloc(as, trans, b->c.level + 1); bch2_btree_update_add_new_node(as, n); six_unlock_write(&n->c.lock); path->locks_want++; BUG_ON(btree_node_locked(path, n->c.level)); six_lock_increment(&n->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, path, n->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, path, n); n->sib_u64s[0] = U16_MAX; n->sib_u64s[1] = U16_MAX; bch2_keylist_add(&as->parent_keys, &b->key); btree_split_insert_keys(as, trans, path_idx, n, &as->parent_keys); int ret = bch2_btree_set_root(as, trans, path, n, true); BUG_ON(ret); bch2_btree_update_get_open_buckets(as, n); bch2_btree_node_write_trans(trans, n, SIX_LOCK_intent, 0); bch2_trans_node_add(trans, path, n); six_unlock_intent(&n->c.lock); mutex_lock(&c->btree_cache.lock); list_add_tail(&b->list, &c->btree_cache.live[btree_node_pinned(b)].list); mutex_unlock(&c->btree_cache.lock); bch2_trans_verify_locks(trans); } int bch2_btree_increase_depth(struct btree_trans *trans, btree_path_idx_t path, unsigned flags) { struct bch_fs *c = trans->c; struct btree *b = bch2_btree_id_root(c, trans->paths[path].btree_id)->b; if (btree_node_fake(b)) return bch2_btree_split_leaf(trans, path, flags); struct btree_update *as = bch2_btree_update_start(trans, trans->paths + path, b->c.level, true, flags); if (IS_ERR(as)) return PTR_ERR(as); __btree_increase_depth(as, trans, path); bch2_btree_update_done(as, trans); return 0; } int __bch2_foreground_maybe_merge(struct btree_trans *trans, btree_path_idx_t path, unsigned level, unsigned flags, enum btree_node_sibling sib) { struct bch_fs *c = trans->c; struct btree_update *as; struct bkey_format_state new_s; struct bkey_format new_f; struct bkey_i delete; struct btree *b, *m, *n, *prev, *next, *parent; struct bpos sib_pos; size_t sib_u64s; enum btree_id btree = trans->paths[path].btree_id; btree_path_idx_t sib_path = 0, new_path = 0; u64 start_time = local_clock(); int ret = 0; bch2_trans_verify_not_unlocked_or_in_restart(trans); BUG_ON(!trans->paths[path].should_be_locked); BUG_ON(!btree_node_locked(&trans->paths[path], level)); /* * Work around a deadlock caused by the btree write buffer not doing * merges and leaving tons of merges for us to do - we really don't need * to be doing merges at all from the interior update path, and if the * interior update path is generating too many new interior updates we * deadlock: */ if ((flags & BCH_WATERMARK_MASK) == BCH_WATERMARK_interior_updates) return 0; if ((flags & BCH_WATERMARK_MASK) <= BCH_WATERMARK_reclaim) { flags &= ~BCH_WATERMARK_MASK; flags |= BCH_WATERMARK_btree; flags |= BCH_TRANS_COMMIT_journal_reclaim; } b = trans->paths[path].l[level].b; if ((sib == btree_prev_sib && bpos_eq(b->data->min_key, POS_MIN)) || (sib == btree_next_sib && bpos_eq(b->data->max_key, SPOS_MAX))) { b->sib_u64s[sib] = U16_MAX; return 0; } sib_pos = sib == btree_prev_sib ? bpos_predecessor(b->data->min_key) : bpos_successor(b->data->max_key); sib_path = bch2_path_get(trans, btree, sib_pos, U8_MAX, level, BTREE_ITER_intent, _THIS_IP_); ret = bch2_btree_path_traverse(trans, sib_path, false); if (ret) goto err; btree_path_set_should_be_locked(trans, trans->paths + sib_path); m = trans->paths[sib_path].l[level].b; if (btree_node_parent(trans->paths + path, b) != btree_node_parent(trans->paths + sib_path, m)) { b->sib_u64s[sib] = U16_MAX; goto out; } if (sib == btree_prev_sib) { prev = m; next = b; } else { prev = b; next = m; } if (!bpos_eq(bpos_successor(prev->data->max_key), next->data->min_key)) { struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF; bch2_bpos_to_text(&buf1, prev->data->max_key); bch2_bpos_to_text(&buf2, next->data->min_key); bch_err(c, "%s(): btree topology error:\n" " prev ends at %s\n" " next starts at %s", __func__, buf1.buf, buf2.buf); printbuf_exit(&buf1); printbuf_exit(&buf2); ret = bch2_topology_error(c); goto err; } bch2_bkey_format_init(&new_s); bch2_bkey_format_add_pos(&new_s, prev->data->min_key); __bch2_btree_calc_format(&new_s, prev); __bch2_btree_calc_format(&new_s, next); bch2_bkey_format_add_pos(&new_s, next->data->max_key); new_f = bch2_bkey_format_done(&new_s); sib_u64s = btree_node_u64s_with_format(b->nr, &b->format, &new_f) + btree_node_u64s_with_format(m->nr, &m->format, &new_f); if (sib_u64s > BTREE_FOREGROUND_MERGE_HYSTERESIS(c)) { sib_u64s -= BTREE_FOREGROUND_MERGE_HYSTERESIS(c); sib_u64s /= 2; sib_u64s += BTREE_FOREGROUND_MERGE_HYSTERESIS(c); } sib_u64s = min(sib_u64s, btree_max_u64s(c)); sib_u64s = min(sib_u64s, (size_t) U16_MAX - 1); b->sib_u64s[sib] = sib_u64s; if (b->sib_u64s[sib] > c->btree_foreground_merge_threshold) goto out; parent = btree_node_parent(trans->paths + path, b); as = bch2_btree_update_start(trans, trans->paths + path, level, false, BCH_TRANS_COMMIT_no_enospc|flags); ret = PTR_ERR_OR_ZERO(as); if (ret) goto err; trace_and_count(c, btree_node_merge, trans, b); n = bch2_btree_node_alloc(as, trans, b->c.level); SET_BTREE_NODE_SEQ(n->data, max(BTREE_NODE_SEQ(b->data), BTREE_NODE_SEQ(m->data)) + 1); btree_set_min(n, prev->data->min_key); btree_set_max(n, next->data->max_key); n->data->format = new_f; btree_node_set_format(n, new_f); bch2_btree_sort_into(c, n, prev); bch2_btree_sort_into(c, n, next); bch2_btree_build_aux_trees(n); bch2_btree_update_add_new_node(as, n); six_unlock_write(&n->c.lock); new_path = bch2_path_get_unlocked_mut(trans, btree, n->c.level, n->key.k.p); six_lock_increment(&n->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + new_path, n->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + new_path, n); bkey_init(&delete.k); delete.k.p = prev->key.k.p; bch2_keylist_add(&as->parent_keys, &delete); bch2_keylist_add(&as->parent_keys, &n->key); bch2_trans_verify_paths(trans); ret = bch2_btree_insert_node(as, trans, path, parent, &as->parent_keys); if (ret) goto err_free_update; bch2_btree_interior_update_will_free_node(as, b); bch2_btree_interior_update_will_free_node(as, m); bch2_trans_verify_paths(trans); bch2_btree_update_get_open_buckets(as, n); bch2_btree_node_write_trans(trans, n, SIX_LOCK_intent, 0); bch2_btree_node_free_inmem(trans, trans->paths + path, b); bch2_btree_node_free_inmem(trans, trans->paths + sib_path, m); bch2_trans_node_add(trans, trans->paths + path, n); bch2_trans_verify_paths(trans); six_unlock_intent(&n->c.lock); bch2_btree_update_done(as, trans); bch2_time_stats_update(&c->times[BCH_TIME_btree_node_merge], start_time); out: err: if (new_path) bch2_path_put(trans, new_path, true); bch2_path_put(trans, sib_path, true); bch2_trans_verify_locks(trans); if (ret == -BCH_ERR_journal_reclaim_would_deadlock) ret = 0; if (!ret) ret = bch2_trans_relock(trans); return ret; err_free_update: bch2_btree_node_free_never_used(as, trans, n); bch2_btree_update_free(as, trans); goto out; } static int get_iter_to_node(struct btree_trans *trans, struct btree_iter *iter, struct btree *b) { bch2_trans_node_iter_init(trans, iter, b->c.btree_id, b->key.k.p, BTREE_MAX_DEPTH, b->c.level, BTREE_ITER_intent); int ret = bch2_btree_iter_traverse(iter); if (ret) goto err; /* has node been freed? */ if (btree_iter_path(trans, iter)->l[b->c.level].b != b) { /* node has been freed: */ BUG_ON(!btree_node_dying(b)); ret = -BCH_ERR_btree_node_dying; goto err; } BUG_ON(!btree_node_hashed(b)); return 0; err: bch2_trans_iter_exit(trans, iter); return ret; } int bch2_btree_node_rewrite(struct btree_trans *trans, struct btree_iter *iter, struct btree *b, unsigned flags) { struct bch_fs *c = trans->c; struct btree *n, *parent; struct btree_update *as; btree_path_idx_t new_path = 0; int ret; flags |= BCH_TRANS_COMMIT_no_enospc; struct btree_path *path = btree_iter_path(trans, iter); parent = btree_node_parent(path, b); as = bch2_btree_update_start(trans, path, b->c.level, false, flags); ret = PTR_ERR_OR_ZERO(as); if (ret) goto out; n = bch2_btree_node_alloc_replacement(as, trans, b); bch2_btree_build_aux_trees(n); bch2_btree_update_add_new_node(as, n); six_unlock_write(&n->c.lock); new_path = bch2_path_get_unlocked_mut(trans, iter->btree_id, n->c.level, n->key.k.p); six_lock_increment(&n->c.lock, SIX_LOCK_intent); mark_btree_node_locked(trans, trans->paths + new_path, n->c.level, BTREE_NODE_INTENT_LOCKED); bch2_btree_path_level_init(trans, trans->paths + new_path, n); trace_and_count(c, btree_node_rewrite, trans, b); if (parent) { bch2_keylist_add(&as->parent_keys, &n->key); ret = bch2_btree_insert_node(as, trans, iter->path, parent, &as->parent_keys); } else { ret = bch2_btree_set_root(as, trans, btree_iter_path(trans, iter), n, false); } if (ret) goto err; bch2_btree_interior_update_will_free_node(as, b); bch2_btree_update_get_open_buckets(as, n); bch2_btree_node_write_trans(trans, n, SIX_LOCK_intent, 0); bch2_btree_node_free_inmem(trans, btree_iter_path(trans, iter), b); bch2_trans_node_add(trans, trans->paths + iter->path, n); six_unlock_intent(&n->c.lock); bch2_btree_update_done(as, trans); out: if (new_path) bch2_path_put(trans, new_path, true); bch2_trans_downgrade(trans); return ret; err: bch2_btree_node_free_never_used(as, trans, n); bch2_btree_update_free(as, trans); goto out; } static int bch2_btree_node_rewrite_key(struct btree_trans *trans, enum btree_id btree, unsigned level, struct bkey_i *k, unsigned flags) { struct btree_iter iter; bch2_trans_node_iter_init(trans, &iter, btree, k->k.p, BTREE_MAX_DEPTH, level, 0); struct btree *b = bch2_btree_iter_peek_node(&iter); int ret = PTR_ERR_OR_ZERO(b); if (ret) goto out; bool found = b && btree_ptr_hash_val(&b->key) == btree_ptr_hash_val(k); ret = found ? bch2_btree_node_rewrite(trans, &iter, b, flags) : -ENOENT; out: bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_btree_node_rewrite_pos(struct btree_trans *trans, enum btree_id btree, unsigned level, struct bpos pos, unsigned flags) { BUG_ON(!level); /* Traverse one depth lower to get a pointer to the node itself: */ struct btree_iter iter; bch2_trans_node_iter_init(trans, &iter, btree, pos, 0, level - 1, 0); struct btree *b = bch2_btree_iter_peek_node(&iter); int ret = PTR_ERR_OR_ZERO(b); if (ret) goto err; ret = bch2_btree_node_rewrite(trans, &iter, b, flags); err: bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_btree_node_rewrite_key_get_iter(struct btree_trans *trans, struct btree *b, unsigned flags) { struct btree_iter iter; int ret = get_iter_to_node(trans, &iter, b); if (ret) return ret == -BCH_ERR_btree_node_dying ? 0 : ret; ret = bch2_btree_node_rewrite(trans, &iter, b, flags); bch2_trans_iter_exit(trans, &iter); return ret; } struct async_btree_rewrite { struct bch_fs *c; struct work_struct work; struct list_head list; enum btree_id btree_id; unsigned level; struct bkey_buf key; }; static void async_btree_node_rewrite_work(struct work_struct *work) { struct async_btree_rewrite *a = container_of(work, struct async_btree_rewrite, work); struct bch_fs *c = a->c; int ret = bch2_trans_do(c, bch2_btree_node_rewrite_key(trans, a->btree_id, a->level, a->key.k, 0)); if (ret != -ENOENT) bch_err_fn_ratelimited(c, ret); spin_lock(&c->btree_node_rewrites_lock); list_del(&a->list); spin_unlock(&c->btree_node_rewrites_lock); closure_wake_up(&c->btree_node_rewrites_wait); bch2_bkey_buf_exit(&a->key, c); bch2_write_ref_put(c, BCH_WRITE_REF_node_rewrite); kfree(a); } void bch2_btree_node_rewrite_async(struct bch_fs *c, struct btree *b) { struct async_btree_rewrite *a = kmalloc(sizeof(*a), GFP_NOFS); if (!a) return; a->c = c; a->btree_id = b->c.btree_id; a->level = b->c.level; INIT_WORK(&a->work, async_btree_node_rewrite_work); bch2_bkey_buf_init(&a->key); bch2_bkey_buf_copy(&a->key, c, &b->key); bool now = false, pending = false; spin_lock(&c->btree_node_rewrites_lock); if (c->curr_recovery_pass > BCH_RECOVERY_PASS_journal_replay && bch2_write_ref_tryget(c, BCH_WRITE_REF_node_rewrite)) { list_add(&a->list, &c->btree_node_rewrites); now = true; } else if (!test_bit(BCH_FS_may_go_rw, &c->flags)) { list_add(&a->list, &c->btree_node_rewrites_pending); pending = true; } spin_unlock(&c->btree_node_rewrites_lock); if (now) { queue_work(c->btree_node_rewrite_worker, &a->work); } else if (pending) { /* bch2_do_pending_node_rewrites will execute */ } else { bch2_bkey_buf_exit(&a->key, c); kfree(a); } } void bch2_async_btree_node_rewrites_flush(struct bch_fs *c) { closure_wait_event(&c->btree_node_rewrites_wait, list_empty(&c->btree_node_rewrites)); } void bch2_do_pending_node_rewrites(struct bch_fs *c) { while (1) { spin_lock(&c->btree_node_rewrites_lock); struct async_btree_rewrite *a = list_pop_entry(&c->btree_node_rewrites_pending, struct async_btree_rewrite, list); if (a) list_add(&a->list, &c->btree_node_rewrites); spin_unlock(&c->btree_node_rewrites_lock); if (!a) break; bch2_write_ref_get(c, BCH_WRITE_REF_node_rewrite); queue_work(c->btree_node_rewrite_worker, &a->work); } } void bch2_free_pending_node_rewrites(struct bch_fs *c) { while (1) { spin_lock(&c->btree_node_rewrites_lock); struct async_btree_rewrite *a = list_pop_entry(&c->btree_node_rewrites_pending, struct async_btree_rewrite, list); spin_unlock(&c->btree_node_rewrites_lock); if (!a) break; bch2_bkey_buf_exit(&a->key, c); kfree(a); } } static int __bch2_btree_node_update_key(struct btree_trans *trans, struct btree_iter *iter, struct btree *b, struct btree *new_hash, struct bkey_i *new_key, unsigned commit_flags, bool skip_triggers) { struct bch_fs *c = trans->c; struct btree_iter iter2 = { NULL }; struct btree *parent; int ret; if (!skip_triggers) { ret = bch2_key_trigger_old(trans, b->c.btree_id, b->c.level + 1, bkey_i_to_s_c(&b->key), BTREE_TRIGGER_transactional) ?: bch2_key_trigger_new(trans, b->c.btree_id, b->c.level + 1, bkey_i_to_s(new_key), BTREE_TRIGGER_transactional); if (ret) return ret; } if (new_hash) { bkey_copy(&new_hash->key, new_key); ret = bch2_btree_node_hash_insert(&c->btree_cache, new_hash, b->c.level, b->c.btree_id); BUG_ON(ret); } parent = btree_node_parent(btree_iter_path(trans, iter), b); if (parent) { bch2_trans_copy_iter(&iter2, iter); iter2.path = bch2_btree_path_make_mut(trans, iter2.path, iter2.flags & BTREE_ITER_intent, _THIS_IP_); struct btree_path *path2 = btree_iter_path(trans, &iter2); BUG_ON(path2->level != b->c.level); BUG_ON(!bpos_eq(path2->pos, new_key->k.p)); btree_path_set_level_up(trans, path2); trans->paths_sorted = false; ret = bch2_btree_iter_traverse(&iter2) ?: bch2_trans_update(trans, &iter2, new_key, BTREE_TRIGGER_norun); if (ret) goto err; } else { BUG_ON(btree_node_root(c, b) != b); struct jset_entry *e = bch2_trans_jset_entry_alloc(trans, jset_u64s(new_key->k.u64s)); ret = PTR_ERR_OR_ZERO(e); if (ret) return ret; journal_entry_set(e, BCH_JSET_ENTRY_btree_root, b->c.btree_id, b->c.level, new_key, new_key->k.u64s); } ret = bch2_trans_commit(trans, NULL, NULL, commit_flags); if (ret) goto err; bch2_btree_node_lock_write_nofail(trans, btree_iter_path(trans, iter), &b->c); if (new_hash) { mutex_lock(&c->btree_cache.lock); bch2_btree_node_hash_remove(&c->btree_cache, new_hash); __bch2_btree_node_hash_remove(&c->btree_cache, b); bkey_copy(&b->key, new_key); ret = __bch2_btree_node_hash_insert(&c->btree_cache, b); BUG_ON(ret); mutex_unlock(&c->btree_cache.lock); } else { bkey_copy(&b->key, new_key); } bch2_btree_node_unlock_write(trans, btree_iter_path(trans, iter), b); out: bch2_trans_iter_exit(trans, &iter2); return ret; err: if (new_hash) { mutex_lock(&c->btree_cache.lock); bch2_btree_node_hash_remove(&c->btree_cache, b); mutex_unlock(&c->btree_cache.lock); } goto out; } int bch2_btree_node_update_key(struct btree_trans *trans, struct btree_iter *iter, struct btree *b, struct bkey_i *new_key, unsigned commit_flags, bool skip_triggers) { struct bch_fs *c = trans->c; struct btree *new_hash = NULL; struct btree_path *path = btree_iter_path(trans, iter); struct closure cl; int ret = 0; ret = bch2_btree_path_upgrade(trans, path, b->c.level + 1); if (ret) return ret; closure_init_stack(&cl); /* * check btree_ptr_hash_val() after @b is locked by * btree_iter_traverse(): */ if (btree_ptr_hash_val(new_key) != b->hash_val) { ret = bch2_btree_cache_cannibalize_lock(trans, &cl); if (ret) { ret = drop_locks_do(trans, (closure_sync(&cl), 0)); if (ret) return ret; } new_hash = bch2_btree_node_mem_alloc(trans, false); ret = PTR_ERR_OR_ZERO(new_hash); if (ret) goto err; } path->intent_ref++; ret = __bch2_btree_node_update_key(trans, iter, b, new_hash, new_key, commit_flags, skip_triggers); --path->intent_ref; if (new_hash) bch2_btree_node_to_freelist(c, new_hash); err: closure_sync(&cl); bch2_btree_cache_cannibalize_unlock(trans); return ret; } int bch2_btree_node_update_key_get_iter(struct btree_trans *trans, struct btree *b, struct bkey_i *new_key, unsigned commit_flags, bool skip_triggers) { struct btree_iter iter; int ret = get_iter_to_node(trans, &iter, b); if (ret) return ret == -BCH_ERR_btree_node_dying ? 0 : ret; bch2_bkey_drop_ptrs(bkey_i_to_s(new_key), ptr, !bch2_bkey_has_device(bkey_i_to_s(&b->key), ptr->dev)); ret = bch2_btree_node_update_key(trans, &iter, b, new_key, commit_flags, skip_triggers); bch2_trans_iter_exit(trans, &iter); return ret; } /* Init code: */ /* * Only for filesystem bringup, when first reading the btree roots or allocating * btree roots when initializing a new filesystem: */ void bch2_btree_set_root_for_read(struct bch_fs *c, struct btree *b) { BUG_ON(btree_node_root(c, b)); bch2_btree_set_root_inmem(c, b); } int bch2_btree_root_alloc_fake_trans(struct btree_trans *trans, enum btree_id id, unsigned level) { struct bch_fs *c = trans->c; struct closure cl; struct btree *b; int ret; closure_init_stack(&cl); do { ret = bch2_btree_cache_cannibalize_lock(trans, &cl); closure_sync(&cl); } while (ret); b = bch2_btree_node_mem_alloc(trans, false); bch2_btree_cache_cannibalize_unlock(trans); ret = PTR_ERR_OR_ZERO(b); if (ret) return ret; set_btree_node_fake(b); set_btree_node_need_rewrite(b); b->c.level = level; b->c.btree_id = id; bkey_btree_ptr_init(&b->key); b->key.k.p = SPOS_MAX; *((u64 *) bkey_i_to_btree_ptr(&b->key)->v.start) = U64_MAX - id; bch2_bset_init_first(b, &b->data->keys); bch2_btree_build_aux_trees(b); b->data->flags = 0; btree_set_min(b, POS_MIN); btree_set_max(b, SPOS_MAX); b->data->format = bch2_btree_calc_format(b); btree_node_set_format(b, b->data->format); ret = bch2_btree_node_hash_insert(&c->btree_cache, b, b->c.level, b->c.btree_id); BUG_ON(ret); bch2_btree_set_root_inmem(c, b); six_unlock_write(&b->c.lock); six_unlock_intent(&b->c.lock); return 0; } void bch2_btree_root_alloc_fake(struct bch_fs *c, enum btree_id id, unsigned level) { bch2_trans_run(c, lockrestart_do(trans, bch2_btree_root_alloc_fake_trans(trans, id, level))); } static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update *as) { prt_printf(out, "%ps: ", (void *) as->ip_started); bch2_trans_commit_flags_to_text(out, as->flags); prt_str(out, " "); bch2_btree_id_to_text(out, as->btree_id); prt_printf(out, " l=%u-%u mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n", as->update_level_start, as->update_level_end, bch2_btree_update_modes[as->mode], as->nodes_written, closure_nr_remaining(&as->cl), as->journal.seq); } void bch2_btree_updates_to_text(struct printbuf *out, struct bch_fs *c) { struct btree_update *as; mutex_lock(&c->btree_interior_update_lock); list_for_each_entry(as, &c->btree_interior_update_list, list) bch2_btree_update_to_text(out, as); mutex_unlock(&c->btree_interior_update_lock); } static bool bch2_btree_interior_updates_pending(struct bch_fs *c) { bool ret; mutex_lock(&c->btree_interior_update_lock); ret = !list_empty(&c->btree_interior_update_list); mutex_unlock(&c->btree_interior_update_lock); return ret; } bool bch2_btree_interior_updates_flush(struct bch_fs *c) { bool ret = bch2_btree_interior_updates_pending(c); if (ret) closure_wait_event(&c->btree_interior_update_wait, !bch2_btree_interior_updates_pending(c)); return ret; } void bch2_journal_entry_to_btree_root(struct bch_fs *c, struct jset_entry *entry) { struct btree_root *r = bch2_btree_id_root(c, entry->btree_id); mutex_lock(&c->btree_root_lock); r->level = entry->level; r->alive = true; bkey_copy(&r->key, (struct bkey_i *) entry->start); mutex_unlock(&c->btree_root_lock); } struct jset_entry * bch2_btree_roots_to_journal_entries(struct bch_fs *c, struct jset_entry *end, unsigned long skip) { unsigned i; mutex_lock(&c->btree_root_lock); for (i = 0; i < btree_id_nr_alive(c); i++) { struct btree_root *r = bch2_btree_id_root(c, i); if (r->alive && !test_bit(i, &skip)) { journal_entry_set(end, BCH_JSET_ENTRY_btree_root, i, r->level, &r->key, r->key.k.u64s); end = vstruct_next(end); } } mutex_unlock(&c->btree_root_lock); return end; } static void bch2_btree_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct btree_alloc *a) { printbuf_indent_add(out, 2); bch2_bkey_val_to_text(out, c, bkey_i_to_s_c(&a->k)); prt_newline(out); struct open_bucket *ob; unsigned i; open_bucket_for_each(c, &a->ob, ob, i) bch2_open_bucket_to_text(out, c, ob); printbuf_indent_sub(out, 2); } void bch2_btree_reserve_cache_to_text(struct printbuf *out, struct bch_fs *c) { for (unsigned i = 0; i < c->btree_reserve_cache_nr; i++) bch2_btree_alloc_to_text(out, c, &c->btree_reserve_cache[i]); } void bch2_fs_btree_interior_update_exit(struct bch_fs *c) { WARN_ON(!list_empty(&c->btree_node_rewrites)); WARN_ON(!list_empty(&c->btree_node_rewrites_pending)); if (c->btree_node_rewrite_worker) destroy_workqueue(c->btree_node_rewrite_worker); if (c->btree_interior_update_worker) destroy_workqueue(c->btree_interior_update_worker); mempool_exit(&c->btree_interior_update_pool); } void bch2_fs_btree_interior_update_init_early(struct bch_fs *c) { mutex_init(&c->btree_reserve_cache_lock); INIT_LIST_HEAD(&c->btree_interior_update_list); INIT_LIST_HEAD(&c->btree_interior_updates_unwritten); mutex_init(&c->btree_interior_update_lock); INIT_WORK(&c->btree_interior_update_work, btree_interior_update_work); INIT_LIST_HEAD(&c->btree_node_rewrites); INIT_LIST_HEAD(&c->btree_node_rewrites_pending); spin_lock_init(&c->btree_node_rewrites_lock); } int bch2_fs_btree_interior_update_init(struct bch_fs *c) { c->btree_interior_update_worker = alloc_workqueue("btree_update", WQ_UNBOUND|WQ_MEM_RECLAIM, 8); if (!c->btree_interior_update_worker) return -BCH_ERR_ENOMEM_btree_interior_update_worker_init; c->btree_node_rewrite_worker = alloc_ordered_workqueue("btree_node_rewrite", WQ_UNBOUND); if (!c->btree_node_rewrite_worker) return -BCH_ERR_ENOMEM_btree_interior_update_worker_init; if (mempool_init_kmalloc_pool(&c->btree_interior_update_pool, 1, sizeof(struct btree_update))) return -BCH_ERR_ENOMEM_btree_interior_update_pool_init; return 0; } |
| 111 111 110 108 108 108 3 228 1 206 227 24 25 23 25 13 21 81 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "btree_update_interior.h" #include "buckets.h" #include "error.h" #include "journal_io.h" #include "replicas.h" #include "sb-clean.h" #include "super-io.h" /* * BCH_SB_FIELD_clean: * * Btree roots, and a few other things, are recovered from the journal after an * unclean shutdown - but after a clean shutdown, to avoid having to read the * journal, we can store them in the superblock. * * bch_sb_field_clean simply contains a list of journal entries, stored exactly * as they would be in the journal: */ int bch2_sb_clean_validate_late(struct bch_fs *c, struct bch_sb_field_clean *clean, int write) { struct bkey_validate_context from = { .flags = write, .from = BKEY_VALIDATE_superblock, }; struct jset_entry *entry; int ret; for (entry = clean->start; entry < (struct jset_entry *) vstruct_end(&clean->field); entry = vstruct_next(entry)) { if (vstruct_end(entry) > vstruct_end(&clean->field)) { bch_err(c, "journal entry (u64s %u) overran end of superblock clean section (u64s %u) by %zu", le16_to_cpu(entry->u64s), le32_to_cpu(clean->field.u64s), (u64 *) vstruct_end(entry) - (u64 *) vstruct_end(&clean->field)); bch2_sb_error_count(c, BCH_FSCK_ERR_sb_clean_entry_overrun); return -BCH_ERR_fsck_repair_unimplemented; } ret = bch2_journal_entry_validate(c, NULL, entry, le16_to_cpu(c->disk_sb.sb->version), BCH_SB_BIG_ENDIAN(c->disk_sb.sb), from); if (ret) return ret; } return 0; } static struct bkey_i *btree_root_find(struct bch_fs *c, struct bch_sb_field_clean *clean, struct jset *j, enum btree_id id, unsigned *level) { struct bkey_i *k; struct jset_entry *entry, *start, *end; if (clean) { start = clean->start; end = vstruct_end(&clean->field); } else { start = j->start; end = vstruct_last(j); } for (entry = start; entry < end; entry = vstruct_next(entry)) if (entry->type == BCH_JSET_ENTRY_btree_root && entry->btree_id == id) goto found; return NULL; found: if (!entry->u64s) return ERR_PTR(-EINVAL); k = entry->start; *level = entry->level; return k; } int bch2_verify_superblock_clean(struct bch_fs *c, struct bch_sb_field_clean **cleanp, struct jset *j) { unsigned i; struct bch_sb_field_clean *clean = *cleanp; struct printbuf buf1 = PRINTBUF; struct printbuf buf2 = PRINTBUF; int ret = 0; if (mustfix_fsck_err_on(j->seq != clean->journal_seq, c, sb_clean_journal_seq_mismatch, "superblock journal seq (%llu) doesn't match journal (%llu) after clean shutdown", le64_to_cpu(clean->journal_seq), le64_to_cpu(j->seq))) { kfree(clean); *cleanp = NULL; return 0; } for (i = 0; i < BTREE_ID_NR; i++) { struct bkey_i *k1, *k2; unsigned l1 = 0, l2 = 0; k1 = btree_root_find(c, clean, NULL, i, &l1); k2 = btree_root_find(c, NULL, j, i, &l2); if (!k1 && !k2) continue; printbuf_reset(&buf1); printbuf_reset(&buf2); if (k1) bch2_bkey_val_to_text(&buf1, c, bkey_i_to_s_c(k1)); else prt_printf(&buf1, "(none)"); if (k2) bch2_bkey_val_to_text(&buf2, c, bkey_i_to_s_c(k2)); else prt_printf(&buf2, "(none)"); mustfix_fsck_err_on(!k1 || !k2 || IS_ERR(k1) || IS_ERR(k2) || k1->k.u64s != k2->k.u64s || memcmp(k1, k2, bkey_bytes(&k1->k)) || l1 != l2, c, sb_clean_btree_root_mismatch, "superblock btree root %u doesn't match journal after clean shutdown\n" "sb: l=%u %s\n" "journal: l=%u %s\n", i, l1, buf1.buf, l2, buf2.buf); } fsck_err: printbuf_exit(&buf2); printbuf_exit(&buf1); return ret; } struct bch_sb_field_clean *bch2_read_superblock_clean(struct bch_fs *c) { struct bch_sb_field_clean *clean, *sb_clean; int ret; mutex_lock(&c->sb_lock); sb_clean = bch2_sb_field_get(c->disk_sb.sb, clean); if (fsck_err_on(!sb_clean, c, sb_clean_missing, "superblock marked clean but clean section not present")) { SET_BCH_SB_CLEAN(c->disk_sb.sb, false); c->sb.clean = false; mutex_unlock(&c->sb_lock); return ERR_PTR(-BCH_ERR_invalid_sb_clean); } clean = kmemdup(sb_clean, vstruct_bytes(&sb_clean->field), GFP_KERNEL); if (!clean) { mutex_unlock(&c->sb_lock); return ERR_PTR(-BCH_ERR_ENOMEM_read_superblock_clean); } ret = bch2_sb_clean_validate_late(c, clean, READ); if (ret) { kfree(clean); mutex_unlock(&c->sb_lock); return ERR_PTR(ret); } mutex_unlock(&c->sb_lock); return clean; fsck_err: mutex_unlock(&c->sb_lock); return ERR_PTR(ret); } void bch2_journal_super_entries_add_common(struct bch_fs *c, struct jset_entry **end, u64 journal_seq) { { struct jset_entry_usage *u = container_of(jset_entry_init(end, sizeof(*u)), struct jset_entry_usage, entry); u->entry.type = BCH_JSET_ENTRY_usage; u->entry.btree_id = BCH_FS_USAGE_key_version; u->v = cpu_to_le64(atomic64_read(&c->key_version)); } for (unsigned i = 0; i < 2; i++) { struct jset_entry_clock *clock = container_of(jset_entry_init(end, sizeof(*clock)), struct jset_entry_clock, entry); clock->entry.type = BCH_JSET_ENTRY_clock; clock->rw = i; clock->time = cpu_to_le64(atomic64_read(&c->io_clock[i].now)); } } static int bch2_sb_clean_validate(struct bch_sb *sb, struct bch_sb_field *f, enum bch_validate_flags flags, struct printbuf *err) { struct bch_sb_field_clean *clean = field_to_type(f, clean); if (vstruct_bytes(&clean->field) < sizeof(*clean)) { prt_printf(err, "wrong size (got %zu should be %zu)", vstruct_bytes(&clean->field), sizeof(*clean)); return -BCH_ERR_invalid_sb_clean; } for (struct jset_entry *entry = clean->start; entry != vstruct_end(&clean->field); entry = vstruct_next(entry)) { if ((void *) vstruct_next(entry) > vstruct_end(&clean->field)) { prt_str(err, "entry type "); bch2_prt_jset_entry_type(err, entry->type); prt_str(err, " overruns end of section"); return -BCH_ERR_invalid_sb_clean; } } return 0; } static void bch2_sb_clean_to_text(struct printbuf *out, struct bch_sb *sb, struct bch_sb_field *f) { struct bch_sb_field_clean *clean = field_to_type(f, clean); struct jset_entry *entry; prt_printf(out, "flags: %x\n", le32_to_cpu(clean->flags)); prt_printf(out, "journal_seq: %llu\n", le64_to_cpu(clean->journal_seq)); for (entry = clean->start; entry != vstruct_end(&clean->field); entry = vstruct_next(entry)) { if ((void *) vstruct_next(entry) > vstruct_end(&clean->field)) break; if (entry->type == BCH_JSET_ENTRY_btree_keys && !entry->u64s) continue; bch2_journal_entry_to_text(out, NULL, entry); prt_newline(out); } } const struct bch_sb_field_ops bch_sb_field_ops_clean = { .validate = bch2_sb_clean_validate, .to_text = bch2_sb_clean_to_text, }; int bch2_fs_mark_dirty(struct bch_fs *c) { int ret; /* * Unconditionally write superblock, to verify it hasn't changed before * we go rw: */ mutex_lock(&c->sb_lock); SET_BCH_SB_CLEAN(c->disk_sb.sb, false); c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALWAYS); ret = bch2_write_super(c); mutex_unlock(&c->sb_lock); return ret; } void bch2_fs_mark_clean(struct bch_fs *c) { struct bch_sb_field_clean *sb_clean; struct jset_entry *entry; unsigned u64s; int ret; mutex_lock(&c->sb_lock); if (BCH_SB_CLEAN(c->disk_sb.sb)) goto out; SET_BCH_SB_CLEAN(c->disk_sb.sb, true); c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_alloc_info); c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_alloc_metadata); c->disk_sb.sb->features[0] &= cpu_to_le64(~(1ULL << BCH_FEATURE_extents_above_btree_updates)); c->disk_sb.sb->features[0] &= cpu_to_le64(~(1ULL << BCH_FEATURE_btree_updates_journalled)); u64s = sizeof(*sb_clean) / sizeof(u64) + c->journal.entry_u64s_reserved; sb_clean = bch2_sb_field_resize(&c->disk_sb, clean, u64s); if (!sb_clean) { bch_err(c, "error resizing superblock while setting filesystem clean"); goto out; } sb_clean->flags = 0; sb_clean->journal_seq = cpu_to_le64(atomic64_read(&c->journal.seq)); /* Trying to catch outstanding bug: */ BUG_ON(le64_to_cpu(sb_clean->journal_seq) > S64_MAX); entry = sb_clean->start; bch2_journal_super_entries_add_common(c, &entry, 0); entry = bch2_btree_roots_to_journal_entries(c, entry, 0); BUG_ON((void *) entry > vstruct_end(&sb_clean->field)); memset(entry, 0, vstruct_end(&sb_clean->field) - (void *) entry); /* * this should be in the write path, and we should be validating every * superblock section: */ ret = bch2_sb_clean_validate_late(c, sb_clean, WRITE); if (ret) { bch_err(c, "error writing marking filesystem clean: validate error"); goto out; } bch2_journal_pos_from_member_info_set(c); bch2_write_super(c); out: mutex_unlock(&c->sb_lock); } |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Packet matching code. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> * Copyright (c) 2006-2010 Patrick McHardy <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/capability.h> #include <linux/in.h> #include <linux/skbuff.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> #include <linux/poison.h> #include <net/ipv6.h> #include <net/compat.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/err.h> #include <linux/cpumask.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_log.h> #include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv6 packet filter"); void *ip6t_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(ip6t, IP6T); } EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool ip6_packet_match(const struct sk_buff *skb, const char *indev, const char *outdev, const struct ip6t_ip6 *ip6info, unsigned int *protoff, u16 *fragoff, bool *hotdrop) { unsigned long ret; const struct ipv6hdr *ipv6 = ipv6_hdr(skb); if (NF_INVF(ip6info, IP6T_INV_SRCIP, ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk, &ip6info->src)) || NF_INVF(ip6info, IP6T_INV_DSTIP, ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, &ip6info->dst))) return false; ret = ifname_compare_aligned(indev, ip6info->iniface, ip6info->iniface_mask); if (NF_INVF(ip6info, IP6T_INV_VIA_IN, ret != 0)) return false; ret = ifname_compare_aligned(outdev, ip6info->outiface, ip6info->outiface_mask); if (NF_INVF(ip6info, IP6T_INV_VIA_OUT, ret != 0)) return false; /* ... might want to do something with class and flowlabel here ... */ /* look for the desired protocol header */ if (ip6info->flags & IP6T_F_PROTO) { int protohdr; unsigned short _frag_off; protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off, NULL); if (protohdr < 0) { if (_frag_off == 0) *hotdrop = true; return false; } *fragoff = _frag_off; if (ip6info->proto == protohdr) { if (ip6info->invflags & IP6T_INV_PROTO) return false; return true; } /* We need match for the '-p all', too! */ if ((ip6info->proto != 0) && !(ip6info->invflags & IP6T_INV_PROTO)) return false; } return true; } /* should be ip6 safe */ static bool ip6_checkentry(const struct ip6t_ip6 *ipv6) { if (ipv6->flags & ~IP6T_F_MASK) return false; if (ipv6->invflags & ~IP6T_INV_MASK) return false; return true; } static unsigned int ip6t_error(struct sk_buff *skb, const struct xt_action_param *par) { net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } static inline struct ip6t_entry * get_entry(const void *base, unsigned int offset) { return (struct ip6t_entry *)(base + offset); } /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ static inline bool unconditional(const struct ip6t_entry *e) { static const struct ip6t_ip6 uncond; return e->target_offset == sizeof(struct ip6t_entry) && memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0; } static inline const struct xt_entry_target * ip6t_get_target_c(const struct ip6t_entry *e) { return ip6t_get_target((struct ip6t_entry *)e); } #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* This cries for unification! */ static const char *const hooknames[] = { [NF_INET_PRE_ROUTING] = "PREROUTING", [NF_INET_LOCAL_IN] = "INPUT", [NF_INET_FORWARD] = "FORWARD", [NF_INET_LOCAL_OUT] = "OUTPUT", [NF_INET_POST_ROUTING] = "POSTROUTING", }; enum nf_ip_trace_comments { NF_IP6_TRACE_COMMENT_RULE, NF_IP6_TRACE_COMMENT_RETURN, NF_IP6_TRACE_COMMENT_POLICY, }; static const char *const comments[] = { [NF_IP6_TRACE_COMMENT_RULE] = "rule", [NF_IP6_TRACE_COMMENT_RETURN] = "return", [NF_IP6_TRACE_COMMENT_POLICY] = "policy", }; static const struct nf_loginfo trace_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { .level = LOGLEVEL_WARNING, .logflags = NF_LOG_DEFAULT_MASK, }, }, }; /* Mildly perf critical (only if packet tracing is on) */ static inline int get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { const struct xt_standard_target *t = (void *)ip6t_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; } else if (s == e) { (*rulenum)++; if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP6_TRACE_COMMENT_POLICY] : comments[NF_IP6_TRACE_COMMENT_RETURN]; } return 1; } else (*rulenum)++; return 0; } static void trace_packet(struct net *net, const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, const char *tablename, const struct xt_table_info *private, const struct ip6t_entry *e) { const struct ip6t_entry *root; const char *hookname, *chainname, *comment; const struct ip6t_entry *iter; unsigned int rulenum = 0; root = get_entry(private->entries, private->hook_entry[hook]); hookname = chainname = hooknames[hook]; comment = comments[NF_IP6_TRACE_COMMENT_RULE]; xt_entry_foreach(iter, root, private->size - private->hook_entry[hook]) if (get_chainname_rulenum(iter, e, hookname, &chainname, &comment, &rulenum) != 0) break; nf_log_trace(net, AF_INET6, hook, skb, in, out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", tablename, chainname, comment, rulenum); } #endif static inline struct ip6t_entry * ip6t_next_entry(const struct ip6t_entry *entry) { return (void *)entry + entry->next_offset; } /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ip6t_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; const void *table_base; struct ip6t_entry *e, **jumpstack; unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ stackidx = 0; indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as * if it was a normal packet. All other fragments are treated * normally, except that they will NEVER match rules that ask * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ acpar.fragoff = 0; acpar.hotdrop = false; acpar.state = state; WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; /* Switch to alternate jumpstack if we're being invoked via TEE. * TEE issues XT_CONTINUE verdict on original skb so we must not * clobber the jumpstack. * * For recursion via REJECT or SYNPROXY the stack will be clobbered * but it is no problem since absolute verdict is issued by these. */ if (static_key_false(&xt_tee_enabled)) jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); e = get_entry(table_base, private->hook_entry[hook]); do { const struct xt_entry_target *t; const struct xt_entry_match *ematch; struct xt_counters *counter; WARN_ON(!e); acpar.thoff = 0; if (!ip6_packet_match(skb, indev, outdev, &e->ipv6, &acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) { no_match: e = ip6t_next_entry(e); continue; } xt_ematch_foreach(ematch, e) { acpar.match = ematch->u.kernel.match; acpar.matchinfo = ematch->data; if (!acpar.match->match(skb, &acpar)) goto no_match; } counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, skb->len, 1); t = ip6t_get_target_c(e); WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) trace_packet(state->net, skb, hook, state->in, state->out, table->name, private, e); #endif /* Standard target? */ if (!t->u.kernel.target->target) { int v; v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { verdict = (unsigned int)(-v) - 1; break; } if (stackidx == 0) e = get_entry(table_base, private->underflow[hook]); else e = ip6t_next_entry(jumpstack[--stackidx]); continue; } if (table_base + v != ip6t_next_entry(e) && !(e->ipv6.flags & IP6T_F_GOTO)) { if (unlikely(stackidx >= private->stacksize)) { verdict = NF_DROP; break; } jumpstack[stackidx++] = e; } e = get_entry(table_base, v); continue; } acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); if (verdict == XT_CONTINUE) e = ip6t_next_entry(e); else /* Verdict */ break; } while (!acpar.hotdrop); xt_write_recseq_end(addend); local_bh_enable(); if (acpar.hotdrop) return NF_DROP; else return verdict; } /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0, unsigned int *offsets) { unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset to 0 as we leave), and comefrom to save source hook bitmask */ for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; struct ip6t_entry *e = entry0 + pos; if (!(valid_hooks & (1 << hook))) continue; /* Set initial back pointer. */ e->counters.pcnt = pos; for (;;) { const struct xt_standard_target *t = (void *)ip6t_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) return 0; e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && t->verdict < 0) || visited) { unsigned int oldpos, size; /* Return: backtrack through the last big jump. */ do { e->comefrom ^= (1<<NF_INET_NUMHOOKS); oldpos = pos; pos = e->counters.pcnt; e->counters.pcnt = 0; /* We're at the start. */ if (pos == oldpos) goto next; e = entry0 + pos; } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; e->counters.pcnt = pos; pos += size; } else { int newpos = t->verdict; if (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; if (newpos >= newinfo->size) return 0; } e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; } } next: ; } return 1; } static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; par.net = net; par.match = m->u.kernel.match; par.matchinfo = m->data; par.family = NFPROTO_IPV6; if (par.match->destroy != NULL) par.match->destroy(&par); module_put(par.match->me); } static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ip6t_ip6 *ipv6 = par->entryinfo; par->match = m->u.kernel.match; par->matchinfo = m->data; return xt_check_match(par, m->u.match_size - sizeof(*m), ipv6->proto, ipv6->invflags & IP6T_INV_PROTO); } static int find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; ret = check_match(m, par); if (ret) goto err; return 0; err: module_put(m->u.kernel.match->me); return ret; } static int check_target(struct ip6t_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = ip6t_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, .targinfo = t->data, .hook_mask = e->comefrom, .family = NFPROTO_IPV6, }; return xt_check_target(&par, t->u.target_size - sizeof(*t), e->ipv6.proto, e->ipv6.invflags & IP6T_INV_PROTO); } static int find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; if (!xt_percpu_counter_alloc(alloc_state, &e->counters)) return -ENOMEM; j = 0; memset(&mtpar, 0, sizeof(mtpar)); mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ipv6; mtpar.hook_mask = e->comefrom; mtpar.family = NFPROTO_IPV6; xt_ematch_foreach(ematch, e) { ret = find_check_match(ematch, &mtpar); if (ret != 0) goto cleanup_matches; ++j; } t = ip6t_get_target(e); target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto cleanup_matches; } t->u.kernel.target = target; ret = check_target(e, net, name); if (ret) goto err; return 0; err: module_put(t->u.kernel.target->me); cleanup_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; cleanup_match(ematch, net); } xt_percpu_counter_free(&e->counters); return ret; } static bool check_underflow(const struct ip6t_entry *e) { const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(e)) return false; t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } static int check_entry_size_and_hooks(struct ip6t_entry *e, struct xt_table_info *newinfo, const unsigned char *base, const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks) { unsigned int h; int err; if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || (unsigned char *)e + sizeof(struct ip6t_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct ip6t_entry) + sizeof(struct xt_entry_target)) return -EINVAL; if (!ip6_checkentry(&e->ipv6)) return -EINVAL; err = xt_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (err) return err; /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) return -EINVAL; newinfo->underflow[h] = underflows[h]; } } /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; return 0; } static void cleanup_entry(struct ip6t_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) cleanup_match(ematch, net); t = ip6t_get_target(e); par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_IPV6; if (par.target->destroy != NULL) par.target->destroy(&par); module_put(par.target->me); xt_percpu_counter_free(&e->counters); } /* Checks and translates the user-supplied table segment (held in newinfo) */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ip6t_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; struct ip6t_entry *iter; unsigned int *offsets; unsigned int i; int ret = 0; newinfo->size = repl->size; newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = 0xFFFFFFFF; newinfo->underflow[i] = 0xFFFFFFFF; } offsets = xt_alloc_entry_offsets(newinfo->number); if (!offsets) return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { ret = check_entry_size_and_hooks(iter, newinfo, entry0, entry0 + repl->size, repl->hook_entry, repl->underflow, repl->valid_hooks); if (ret != 0) goto out_free; if (i < repl->num_entries) offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ip6t_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } ret = -EINVAL; if (i != repl->num_entries) goto out_free; ret = xt_check_table_hooks(newinfo, repl->valid_hooks); if (ret) goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; goto out_free; } kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; ++i; } if (ret != 0) { xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; cleanup_entry(iter, net); } return ret; } return ret; out_free: kvfree(offsets); return ret; } static void get_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ip6t_entry *iter; unsigned int cpu; unsigned int i; for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; u64 bcnt, pcnt; unsigned int start; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); do { start = read_seqcount_begin(s); bcnt = tmp->bcnt; pcnt = tmp->pcnt; } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; cond_resched(); } } } static void get_old_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ip6t_entry *iter; unsigned int cpu, i; for_each_possible_cpu(cpu) { i = 0; xt_entry_foreach(iter, t->entries, t->size) { const struct xt_counters *tmp; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); ++i; } cond_resched(); } } static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); get_counters(private, counters); return counters; } static int copy_entries_to_user(unsigned int total_size, const struct xt_table *table, void __user *userptr) { unsigned int off, num; const struct ip6t_entry *e; struct xt_counters *counters; const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); loc_cpu_entry = private->entries; /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; const struct xt_entry_match *m; const struct xt_entry_target *t; e = loc_cpu_entry + off; if (copy_to_user(userptr + off, e, sizeof(*e))) { ret = -EFAULT; goto free_counters; } if (copy_to_user(userptr + off + offsetof(struct ip6t_entry, counters), &counters[num], sizeof(counters[num])) != 0) { ret = -EFAULT; goto free_counters; } for (i = sizeof(struct ip6t_entry); i < e->target_offset; i += m->u.match_size) { m = (void *)e + i; if (xt_match_to_user(m, userptr + off + i)) { ret = -EFAULT; goto free_counters; } } t = ip6t_get_target_c(e); if (xt_target_to_user(t, userptr + off + e->target_offset)) { ret = -EFAULT; goto free_counters; } } free_counters: vfree(counters); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; if (v > 0) v += xt_compat_calc_jump(AF_INET6, v); memcpy(dst, &v, sizeof(v)); } static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; if (cv > 0) cv -= xt_compat_calc_jump(AF_INET6, cv); return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } static int compat_calc_entry(const struct ip6t_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - base; xt_ematch_foreach(ematch, e) off += xt_compat_match_offset(ematch->u.kernel.match); t = ip6t_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); if (ret) return ret; for (i = 0; i < NF_INET_NUMHOOKS; i++) { if (info->hook_entry[i] && (e < (struct ip6t_entry *)(base + info->hook_entry[i]))) newinfo->hook_entry[i] -= off; if (info->underflow[i] && (e < (struct ip6t_entry *)(base + info->underflow[i]))) newinfo->underflow[i] -= off; } return 0; } static int compat_table_info(const struct xt_table_info *info, struct xt_table_info *newinfo) { struct ip6t_entry *iter; const void *loc_cpu_entry; int ret; if (!newinfo || !info) return -EINVAL; /* we dont care about newinfo->entries */ memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; ret = xt_compat_init_offsets(AF_INET6, info->number); if (ret) return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) return ret; } return 0; } #endif static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; if (*len != sizeof(struct ip6t_getinfo)) return -EINVAL; if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_lock(AF_INET6); #endif t = xt_request_find_table_lock(net, AF_INET6, name); if (!IS_ERR(t)) { struct ip6t_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct xt_table_info tmp; if (in_compat_syscall()) { ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET6); private = &tmp; } #endif memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); memcpy(info.underflow, private->underflow, sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; strcpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; xt_table_unlock(t); module_put(t->me); } else ret = PTR_ERR(t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_unlock(AF_INET6); #endif return ret; } static int get_entries(struct net *net, struct ip6t_get_entries __user *uptr, const int *len) { int ret; struct ip6t_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct ip6t_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); else ret = -EAGAIN; module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); return ret; } static int __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, unsigned int num_counters, void __user *counters_ptr) { int ret; struct xt_table *t; struct xt_table_info *oldinfo; struct xt_counters *counters; struct ip6t_entry *iter; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; } t = xt_request_find_table_lock(net, AF_INET6, name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free_newinfo_counters_untrans; } /* You lied! */ if (valid_hooks != t->valid_hooks) { ret = -EINVAL; goto put_module; } oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); if (!oldinfo) goto put_module; /* Update module usage count based on number of rules */ if ((oldinfo->number > oldinfo->initial_entries) || (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); if ((oldinfo->number > oldinfo->initial_entries) && (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); xt_table_unlock(t); get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) { /* Silent error, can't fail, new table is already in place */ net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); } vfree(counters); return 0; put_module: module_put(t->me); xt_table_unlock(t); free_newinfo_counters_untrans: vfree(counters); out: return ret; } static int do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ip6t_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, tmp.counters); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) { unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct ip6t_entry *iter; unsigned int addend; paddc = xt_copy_counters(arg, len, &tmp); if (IS_ERR(paddc)) return PTR_ERR(paddc); t = xt_find_table_lock(net, AF_INET6, tmp.name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free; } local_bh_disable(); private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; addend = xt_write_recseq_begin(); xt_entry_foreach(iter, private->entries, private->size) { struct xt_counters *tmp; tmp = xt_get_this_cpu_counter(&iter->counters); ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt); ++i; } xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: vfree(paddc); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_ip6t_replace { char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; compat_uptr_t counters; /* struct xt_counters * */ struct compat_ip6t_entry entries[]; }; static int compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { struct xt_entry_target *t; struct compat_ip6t_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; const struct xt_entry_match *ematch; int ret = 0; origsize = *size; ce = *dstptr; if (copy_to_user(ce, e, sizeof(struct ip6t_entry)) != 0 || copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])) != 0) return -EFAULT; *dstptr += sizeof(struct compat_ip6t_entry); *size -= sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); xt_ematch_foreach(ematch, e) { ret = xt_compat_match_to_user(ematch, dstptr, size); if (ret != 0) return ret; } target_offset = e->target_offset - (origsize - *size); t = ip6t_get_target(e); ret = xt_compat_target_to_user(t, dstptr, size); if (ret) return ret; next_offset = e->next_offset - (origsize - *size); if (put_user(target_offset, &ce->target_offset) != 0 || put_user(next_offset, &ce->next_offset) != 0) return -EFAULT; return 0; } static int compat_find_calc_match(struct xt_entry_match *m, const struct ip6t_ip6 *ipv6, int *size) { struct xt_match *match; match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; *size += xt_compat_match_offset(match); return 0; } static void compat_release_entry(struct compat_ip6t_entry *e) { struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) module_put(ematch->u.kernel.match->me); t = compat_ip6t_get_target(e); module_put(t->u.kernel.target->me); } static int check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, const unsigned char *limit) { struct xt_entry_match *ematch; struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; int ret, off; if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct compat_ip6t_entry) + sizeof(struct compat_xt_entry_target)) return -EINVAL; if (!ip6_checkentry(&e->ipv6)) return -EINVAL; ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (ret) return ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { ret = compat_find_calc_match(ematch, &e->ipv6, &off); if (ret != 0) goto release_matches; ++j; } t = compat_ip6t_get_target(e); target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto release_matches; } t->u.kernel.target = target; off += xt_compat_target_offset(target); *size += off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); if (ret) goto out; return 0; out: module_put(t->u.kernel.target->me); release_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; module_put(ematch->u.kernel.match->me); } return ret; } static void compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct ip6t_entry *de; unsigned int origsize; int h; struct xt_entry_match *ematch; origsize = *size; de = *dstptr; memcpy(de, e, sizeof(struct ip6t_entry)); memcpy(&de->counters, &e->counters, sizeof(e->counters)); *dstptr += sizeof(struct ip6t_entry); *size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); xt_ematch_foreach(ematch, e) xt_compat_match_from_user(ematch, dstptr, size); de->target_offset = e->target_offset - (origsize - *size); t = compat_ip6t_get_target(e); xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); for (h = 0; h < NF_INET_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } } static int translate_compat_table(struct net *net, struct xt_table_info **pinfo, void **pentry0, const struct compat_ip6t_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_ip6t_entry *iter0; struct ip6t_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; size = compatr->size; info->number = compatr->num_entries; j = 0; xt_compat_lock(AF_INET6); ret = xt_compat_init_offsets(AF_INET6, compatr->num_entries); if (ret) goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; if (j != compatr->num_entries) goto out_unlock; ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; memset(newinfo->entries, 0, size); newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; size = compatr->size; xt_entry_foreach(iter0, entry0, compatr->size) compat_copy_entry_from_user(iter0, &pos, &size, newinfo, entry1); /* all module references in entry0 are now gone. */ xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); memcpy(&repl, compatr, sizeof(*compatr)); for (i = 0; i < NF_INET_NUMHOOKS; i++) { repl.hook_entry[i] = newinfo->hook_entry[i]; repl.underflow[i] = newinfo->underflow[i]; } repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); return 0; free_newinfo: xt_free_table_info(newinfo); return ret; out_unlock: xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; } static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct compat_ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ip6t_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, compat_ptr(tmp.counters)); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } struct compat_ip6t_get_entries { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ip6t_entry entrytable[]; }; static int compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; unsigned int i = 0; struct ip6t_entry *iter; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); pos = userptr; size = total_size; xt_entry_foreach(iter, private->entries, total_size) { ret = compat_copy_entry_to_user(iter, &pos, &size, counters, i++); if (ret != 0) break; } vfree(counters); return ret; } static int compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, int *len) { int ret; struct compat_ip6t_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct compat_ip6t_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) ret = compat_copy_entries_to_user(private->size, t, uptr->entrytable); else if (!ret) ret = -EAGAIN; xt_compat_flush_offsets(AF_INET6); module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); xt_compat_unlock(AF_INET6); return ret; } #endif static int do_ip6t_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IP6T_SO_SET_REPLACE: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_do_replace(sock_net(sk), arg, len); else #endif ret = do_replace(sock_net(sk), arg, len); break; case IP6T_SO_SET_ADD_COUNTERS: ret = do_add_counters(sock_net(sk), arg, len); break; default: ret = -EINVAL; } return ret; } static int do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IP6T_SO_GET_INFO: ret = get_info(sock_net(sk), user, len); break; case IP6T_SO_GET_ENTRIES: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_get_entries(sock_net(sk), user, len); else #endif ret = get_entries(sock_net(sk), user, len); break; case IP6T_SO_GET_REVISION_MATCH: case IP6T_SO_GET_REVISION_TARGET: { struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { ret = -EINVAL; break; } if (copy_from_user(&rev, user, sizeof(rev)) != 0) { ret = -EFAULT; break; } rev.name[sizeof(rev.name)-1] = 0; if (cmd == IP6T_SO_GET_REVISION_TARGET) target = 1; else target = 0; try_then_request_module(xt_find_revision(AF_INET6, rev.name, rev.revision, target, &ret), "ip6t_%s", rev.name); break; } default: ret = -EINVAL; } return ret; } static void __ip6t_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; struct module *table_owner = table->me; struct ip6t_entry *iter; private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); } int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *template_ops) { struct nf_hook_ops *ops; unsigned int num_ops; int ret, i; struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) { xt_free_table_info(newinfo); return ret; } new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ip6t_entry *iter; xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } if (!template_ops) return 0; num_ops = hweight32(table->valid_hooks); if (num_ops == 0) { ret = -EINVAL; goto out_free; } ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; } for (i = 0; i < num_ops; i++) ops[i].priv = new_table; new_table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); if (ret != 0) goto out_free; return ret; out_free: __ip6t_unregister_table(net, new_table); return ret; } void ip6t_unregister_table_pre_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); if (table) nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ip6t_unregister_table_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); if (table) __ip6t_unregister_table(net, table); } /* The built-in targets: standard (NULL) and error. */ static struct xt_target ip6t_builtin_tg[] __read_mostly = { { .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV6, #ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, .compat_to_user = compat_standard_to_user, #endif }, { .name = XT_ERROR_TARGET, .target = ip6t_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV6, }, }; static struct nf_sockopt_ops ip6t_sockopts = { .pf = PF_INET6, .set_optmin = IP6T_BASE_CTL, .set_optmax = IP6T_SO_SET_MAX+1, .set = do_ip6t_set_ctl, .get_optmin = IP6T_BASE_CTL, .get_optmax = IP6T_SO_GET_MAX+1, .get = do_ip6t_get_ctl, .owner = THIS_MODULE, }; static int __net_init ip6_tables_net_init(struct net *net) { return xt_proto_init(net, NFPROTO_IPV6); } static void __net_exit ip6_tables_net_exit(struct net *net) { xt_proto_fini(net, NFPROTO_IPV6); } static struct pernet_operations ip6_tables_net_ops = { .init = ip6_tables_net_init, .exit = ip6_tables_net_exit, }; static int __init ip6_tables_init(void) { int ret; ret = register_pernet_subsys(&ip6_tables_net_ops); if (ret < 0) goto err1; /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); if (ret < 0) goto err2; /* Register setsockopt */ ret = nf_register_sockopt(&ip6t_sockopts); if (ret < 0) goto err4; return 0; err4: xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); err2: unregister_pernet_subsys(&ip6_tables_net_ops); err1: return ret; } static void __exit ip6_tables_fini(void) { nf_unregister_sockopt(&ip6t_sockopts); xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); unregister_pernet_subsys(&ip6_tables_net_ops); } EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table_pre_exit); EXPORT_SYMBOL(ip6t_unregister_table_exit); EXPORT_SYMBOL(ip6t_do_table); module_init(ip6_tables_init); module_exit(ip6_tables_fini); |
| 12 156 53 135 10 3 38 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2002 * Portions Copyright (C) Christoph Hellwig, 2001-2002 */ #ifndef _H_JFS_METAPAGE #define _H_JFS_METAPAGE #include <linux/pagemap.h> struct metapage { /* Common logsyncblk prefix (see jfs_logmgr.h) */ u16 xflag; u16 unused; lid_t lid; int lsn; struct list_head synclist; /* End of logsyncblk prefix */ unsigned long flag; /* See Below */ unsigned long count; /* Reference count */ void *data; /* Data pointer */ sector_t index; /* block address of page */ wait_queue_head_t wait; /* implementation */ struct folio *folio; struct super_block *sb; unsigned int logical_size; /* Journal management */ int clsn; int nohomeok; struct jfs_log *log; }; /* metapage flag */ #define META_locked 0 #define META_dirty 2 #define META_sync 3 #define META_discard 4 #define META_forcewrite 5 #define META_io 6 #define mark_metapage_dirty(mp) set_bit(META_dirty, &(mp)->flag) /* function prototypes */ extern int metapage_init(void); extern void metapage_exit(void); extern struct metapage *__get_metapage(struct inode *inode, unsigned long lblock, unsigned int size, int absolute, unsigned long new); #define read_metapage(inode, lblock, size, absolute)\ __get_metapage(inode, lblock, size, absolute, false) #define get_metapage(inode, lblock, size, absolute)\ __get_metapage(inode, lblock, size, absolute, true) extern void release_metapage(struct metapage *); extern void grab_metapage(struct metapage *); extern void force_metapage(struct metapage *); /* * hold_metapage and put_metapage are used in conjunction. The page lock * is not dropped between the two, so no other threads can get or release * the metapage */ extern void hold_metapage(struct metapage *); extern void put_metapage(struct metapage *); static inline void write_metapage(struct metapage *mp) { set_bit(META_dirty, &mp->flag); release_metapage(mp); } static inline void flush_metapage(struct metapage *mp) { set_bit(META_sync, &mp->flag); write_metapage(mp); } static inline void discard_metapage(struct metapage *mp) { clear_bit(META_dirty, &mp->flag); set_bit(META_discard, &mp->flag); release_metapage(mp); } static inline void metapage_nohomeok(struct metapage *mp) { struct folio *folio = mp->folio; folio_lock(folio); if (!mp->nohomeok++) { mark_metapage_dirty(mp); folio_get(folio); folio_wait_writeback(folio); } folio_unlock(folio); } /* * This serializes access to mp->lsn when metapages are added to logsynclist * without setting nohomeok. i.e. updating imap & dmap */ static inline void metapage_wait_for_io(struct metapage *mp) { if (test_bit(META_io, &mp->flag)) folio_wait_writeback(mp->folio); } /* * This is called when already holding the metapage */ static inline void _metapage_homeok(struct metapage *mp) { if (!--mp->nohomeok) folio_put(mp->folio); } static inline void metapage_homeok(struct metapage *mp) { hold_metapage(mp); _metapage_homeok(mp); put_metapage(mp); } extern const struct address_space_operations jfs_metapage_aops; /* * This routines invalidate all pages for an extent. */ extern void __invalidate_metapages(struct inode *, s64, int); #define invalidate_pxd_metapages(ip, pxd) \ __invalidate_metapages((ip), addressPXD(&(pxd)), lengthPXD(&(pxd))) #define invalidate_dxd_metapages(ip, dxd) \ __invalidate_metapages((ip), addressDXD(&(dxd)), lengthDXD(&(dxd))) #define invalidate_xad_metapages(ip, xad) \ __invalidate_metapages((ip), addressXAD(&(xad)), lengthXAD(&(xad))) #endif /* _H_JFS_METAPAGE */ |
| 166 89 68 89 89 | 1 2 3 4 5 6 7 8 9 10 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfsplus/xattr_trusted.c * * Vyacheslav Dubeyko <slava@dubeyko.com> * * Handler for storing security labels as extended attributes. */ #include <linux/security.h> #include <linux/nls.h> #include "hfsplus_fs.h" #include "xattr.h" static int hfsplus_security_getxattr(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *buffer, size_t size) { return hfsplus_getxattr(inode, name, buffer, size, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); } static int hfsplus_security_setxattr(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) { return hfsplus_setxattr(inode, name, buffer, size, flags, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); } static int hfsplus_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { const struct xattr *xattr; char *xattr_name; int err = 0; xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, GFP_KERNEL); if (!xattr_name) return -ENOMEM; for (xattr = xattr_array; xattr->name != NULL; xattr++) { if (!strcmp(xattr->name, "")) continue; strcpy(xattr_name, XATTR_SECURITY_PREFIX); strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, xattr->name); memset(xattr_name + XATTR_SECURITY_PREFIX_LEN + strlen(xattr->name), 0, 1); err = __hfsplus_setxattr(inode, xattr_name, xattr->value, xattr->value_len, 0); if (err) break; } kfree(xattr_name); return err; } int hfsplus_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr) { return security_inode_init_security(inode, dir, qstr, &hfsplus_initxattrs, NULL); } const struct xattr_handler hfsplus_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .get = hfsplus_security_getxattr, .set = hfsplus_security_setxattr, }; |
| 11 11 11 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 | /* * linux/fs/nls/mac-celtic.c * * Charset macceltic translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ /* * COPYRIGHT AND PERMISSION NOTICE * * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under * the Terms of Use in http://www.unicode.org/copyright.html. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of the Unicode data files and any associated documentation (the "Data * Files") or Unicode software and any associated documentation (the * "Software") to deal in the Data Files or Software without restriction, * including without limitation the rights to use, copy, modify, merge, * publish, distribute, and/or sell copies of the Data Files or Software, and * to permit persons to whom the Data Files or Software are furnished to do * so, provided that (a) the above copyright notice(s) and this permission * notice appear with all copies of the Data Files or Software, (b) both the * above copyright notice(s) and this permission notice appear in associated * documentation, and (c) there is clear notice in each modified Data File or * in the Software as well as in the documentation associated with the Data * File(s) or Software that the data or software has been modified. * * THE DATA FILES AND SOFTWARE ARE 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 OF * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR * PERFORMANCE OF THE DATA FILES OR SOFTWARE. * * Except as contained in this notice, the name of a copyright holder shall * not be used in advertising or otherwise to promote the sale, use or other * dealings in these Data Files or Software without prior written * authorization of the copyright holder. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00 */ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10 */ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20 */ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30 */ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40 */ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50 */ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60 */ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70 */ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80 */ 0x00c4, 0x00c5, 0x00c7, 0x00c9, 0x00d1, 0x00d6, 0x00dc, 0x00e1, 0x00e0, 0x00e2, 0x00e4, 0x00e3, 0x00e5, 0x00e7, 0x00e9, 0x00e8, /* 0x90 */ 0x00ea, 0x00eb, 0x00ed, 0x00ec, 0x00ee, 0x00ef, 0x00f1, 0x00f3, 0x00f2, 0x00f4, 0x00f6, 0x00f5, 0x00fa, 0x00f9, 0x00fb, 0x00fc, /* 0xa0 */ 0x2020, 0x00b0, 0x00a2, 0x00a3, 0x00a7, 0x2022, 0x00b6, 0x00df, 0x00ae, 0x00a9, 0x2122, 0x00b4, 0x00a8, 0x2260, 0x00c6, 0x00d8, /* 0xb0 */ 0x221e, 0x00b1, 0x2264, 0x2265, 0x00a5, 0x00b5, 0x2202, 0x2211, 0x220f, 0x03c0, 0x222b, 0x00aa, 0x00ba, 0x03a9, 0x00e6, 0x00f8, /* 0xc0 */ 0x00bf, 0x00a1, 0x00ac, 0x221a, 0x0192, 0x2248, 0x2206, 0x00ab, 0x00bb, 0x2026, 0x00a0, 0x00c0, 0x00c3, 0x00d5, 0x0152, 0x0153, /* 0xd0 */ 0x2013, 0x2014, 0x201c, 0x201d, 0x2018, 0x2019, 0x00f7, 0x25ca, 0x00ff, 0x0178, 0x2044, 0x20ac, 0x2039, 0x203a, 0x0176, 0x0177, /* 0xe0 */ 0x2021, 0x00b7, 0x1ef2, 0x1ef3, 0x2030, 0x00c2, 0x00ca, 0x00c1, 0x00cb, 0x00c8, 0x00cd, 0x00ce, 0x00cf, 0x00cc, 0x00d3, 0x00d4, /* 0xf0 */ 0x2663, 0x00d2, 0x00da, 0x00db, 0x00d9, 0x0131, 0x00dd, 0x00fd, 0x0174, 0x0175, 0x1e84, 0x1e85, 0x1e80, 0x1e81, 0x1e82, 0x1e83, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xca, 0xc1, 0xa2, 0xa3, 0x00, 0xb4, 0x00, 0xa4, /* 0xa0-0xa7 */ 0xac, 0xa9, 0xbb, 0xc7, 0xc2, 0x00, 0xa8, 0x00, /* 0xa8-0xaf */ 0xa1, 0xb1, 0x00, 0x00, 0xab, 0xb5, 0xa6, 0xe1, /* 0xb0-0xb7 */ 0x00, 0x00, 0xbc, 0xc8, 0x00, 0x00, 0x00, 0xc0, /* 0xb8-0xbf */ 0xcb, 0xe7, 0xe5, 0xcc, 0x80, 0x81, 0xae, 0x82, /* 0xc0-0xc7 */ 0xe9, 0x83, 0xe6, 0xe8, 0xed, 0xea, 0xeb, 0xec, /* 0xc8-0xcf */ 0x00, 0x84, 0xf1, 0xee, 0xef, 0xcd, 0x85, 0x00, /* 0xd0-0xd7 */ 0xaf, 0xf4, 0xf2, 0xf3, 0x86, 0xf6, 0x00, 0xa7, /* 0xd8-0xdf */ 0x88, 0x87, 0x89, 0x8b, 0x8a, 0x8c, 0xbe, 0x8d, /* 0xe0-0xe7 */ 0x8f, 0x8e, 0x90, 0x91, 0x93, 0x92, 0x94, 0x95, /* 0xe8-0xef */ 0x00, 0x96, 0x98, 0x97, 0x99, 0x9b, 0x9a, 0xd6, /* 0xf0-0xf7 */ 0xbf, 0x9d, 0x9c, 0x9e, 0x9f, 0xf7, 0x00, 0xd8, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0xce, 0xcf, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0xf8, 0xf9, 0xde, 0xdf, /* 0x70-0x77 */ 0xd9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page03[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0xbd, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0xb9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page1e[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xfc, 0xfd, 0xfe, 0xff, 0xfa, 0xfb, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0xe2, 0xe3, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd4, 0xd5, 0x00, 0x00, 0xd2, 0xd3, 0x00, 0x00, /* 0x18-0x1f */ 0xa0, 0xe0, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0xe4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0xdc, 0xdd, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0xdb, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page21[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0xb6, 0x00, 0x00, 0x00, 0xc6, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb8, /* 0x08-0x0f */ 0x00, 0xb7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0xb0, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0xba, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0xc5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page25[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0xd7, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page26[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0xf0, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, NULL, page03, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page1e, NULL, page20, page21, page22, NULL, NULL, page25, page26, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x00-0x07 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x08-0x0f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x10-0x17 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x18-0x1f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x20-0x27 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x28-0x2f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x30-0x37 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x38-0x3f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x40-0x47 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x48-0x4f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x50-0x57 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x58-0x5f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x60-0x67 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x68-0x6f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x70-0x77 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x78-0x7f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x80-0x87 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x88-0x8f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x90-0x97 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x98-0x9f */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xa0-0xa7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xa8-0xaf */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xb0-0xb7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xb8-0xbf */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xc0-0xc7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xc8-0xcf */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xd0-0xd7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xd8-0xdf */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xe0-0xe7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xe8-0xef */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xf0-0xf7 */ 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "macceltic", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_macceltic(void) { return register_nls(&table); } static void __exit exit_nls_macceltic(void) { unregister_nls(&table); } module_init(init_nls_macceltic) module_exit(exit_nls_macceltic) MODULE_DESCRIPTION("NLS Codepage macceltic"); MODULE_LICENSE("Dual BSD/GPL"); |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cred.h> #include <linux/device.h> #include <linux/dma-buf.h> #include <linux/dma-resv.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/memfd.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/shmem_fs.h> #include <linux/hugetlb.h> #include <linux/slab.h> #include <linux/udmabuf.h> #include <linux/vmalloc.h> #include <linux/iosys-map.h> static int list_limit = 1024; module_param(list_limit, int, 0644); MODULE_PARM_DESC(list_limit, "udmabuf_create_list->count limit. Default is 1024."); static int size_limit_mb = 64; module_param(size_limit_mb, int, 0644); MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default is 64."); struct udmabuf { pgoff_t pagecount; struct folio **folios; /** * Unlike folios, pinned_folios is only used for unpin. * So, nr_pinned is not the same to pagecount, the pinned_folios * only set each folio which already pinned when udmabuf_create. * Note that, since a folio may be pinned multiple times, each folio * can be added to pinned_folios multiple times, depending on how many * times the folio has been pinned when create. */ pgoff_t nr_pinned; struct folio **pinned_folios; struct sg_table *sg; struct miscdevice *device; pgoff_t *offsets; }; static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct udmabuf *ubuf = vma->vm_private_data; pgoff_t pgoff = vmf->pgoff; unsigned long addr, pfn; vm_fault_t ret; if (pgoff >= ubuf->pagecount) return VM_FAULT_SIGBUS; pfn = folio_pfn(ubuf->folios[pgoff]); pfn += ubuf->offsets[pgoff] >> PAGE_SHIFT; ret = vmf_insert_pfn(vma, vmf->address, pfn); if (ret & VM_FAULT_ERROR) return ret; /* pre fault */ pgoff = vma->vm_pgoff; addr = vma->vm_start; for (; addr < vma->vm_end; pgoff++, addr += PAGE_SIZE) { if (addr == vmf->address) continue; if (WARN_ON(pgoff >= ubuf->pagecount)) break; pfn = folio_pfn(ubuf->folios[pgoff]); pfn += ubuf->offsets[pgoff] >> PAGE_SHIFT; /** * If the below vmf_insert_pfn() fails, we do not return an * error here during this pre-fault step. However, an error * will be returned if the failure occurs when the addr is * truly accessed. */ if (vmf_insert_pfn(vma, addr, pfn) & VM_FAULT_ERROR) break; } return ret; } static const struct vm_operations_struct udmabuf_vm_ops = { .fault = udmabuf_vm_fault, }; static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma) { struct udmabuf *ubuf = buf->priv; if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0) return -EINVAL; vma->vm_ops = &udmabuf_vm_ops; vma->vm_private_data = ubuf; vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); return 0; } static int vmap_udmabuf(struct dma_buf *buf, struct iosys_map *map) { struct udmabuf *ubuf = buf->priv; unsigned long *pfns; void *vaddr; pgoff_t pg; dma_resv_assert_held(buf->resv); /** * HVO may free tail pages, so just use pfn to map each folio * into vmalloc area. */ pfns = kvmalloc_array(ubuf->pagecount, sizeof(*pfns), GFP_KERNEL); if (!pfns) return -ENOMEM; for (pg = 0; pg < ubuf->pagecount; pg++) { unsigned long pfn = folio_pfn(ubuf->folios[pg]); pfn += ubuf->offsets[pg] >> PAGE_SHIFT; pfns[pg] = pfn; } vaddr = vmap_pfn(pfns, ubuf->pagecount, PAGE_KERNEL); kvfree(pfns); if (!vaddr) return -EINVAL; iosys_map_set_vaddr(map, vaddr); return 0; } static void vunmap_udmabuf(struct dma_buf *buf, struct iosys_map *map) { struct udmabuf *ubuf = buf->priv; dma_resv_assert_held(buf->resv); vm_unmap_ram(map->vaddr, ubuf->pagecount); } static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf, enum dma_data_direction direction) { struct udmabuf *ubuf = buf->priv; struct sg_table *sg; struct scatterlist *sgl; unsigned int i = 0; int ret; sg = kzalloc(sizeof(*sg), GFP_KERNEL); if (!sg) return ERR_PTR(-ENOMEM); ret = sg_alloc_table(sg, ubuf->pagecount, GFP_KERNEL); if (ret < 0) goto err_alloc; for_each_sg(sg->sgl, sgl, ubuf->pagecount, i) sg_set_folio(sgl, ubuf->folios[i], PAGE_SIZE, ubuf->offsets[i]); ret = dma_map_sgtable(dev, sg, direction, 0); if (ret < 0) goto err_map; return sg; err_map: sg_free_table(sg); err_alloc: kfree(sg); return ERR_PTR(ret); } static void put_sg_table(struct device *dev, struct sg_table *sg, enum dma_data_direction direction) { dma_unmap_sgtable(dev, sg, direction, 0); sg_free_table(sg); kfree(sg); } static struct sg_table *map_udmabuf(struct dma_buf_attachment *at, enum dma_data_direction direction) { return get_sg_table(at->dev, at->dmabuf, direction); } static void unmap_udmabuf(struct dma_buf_attachment *at, struct sg_table *sg, enum dma_data_direction direction) { return put_sg_table(at->dev, sg, direction); } static void unpin_all_folios(struct udmabuf *ubuf) { pgoff_t i; for (i = 0; i < ubuf->nr_pinned; ++i) unpin_folio(ubuf->pinned_folios[i]); kvfree(ubuf->pinned_folios); } static __always_inline int init_udmabuf(struct udmabuf *ubuf, pgoff_t pgcnt) { ubuf->folios = kvmalloc_array(pgcnt, sizeof(*ubuf->folios), GFP_KERNEL); if (!ubuf->folios) return -ENOMEM; ubuf->offsets = kvcalloc(pgcnt, sizeof(*ubuf->offsets), GFP_KERNEL); if (!ubuf->offsets) return -ENOMEM; ubuf->pinned_folios = kvmalloc_array(pgcnt, sizeof(*ubuf->pinned_folios), GFP_KERNEL); if (!ubuf->pinned_folios) return -ENOMEM; return 0; } static __always_inline void deinit_udmabuf(struct udmabuf *ubuf) { unpin_all_folios(ubuf); kvfree(ubuf->offsets); kvfree(ubuf->folios); } static void release_udmabuf(struct dma_buf *buf) { struct udmabuf *ubuf = buf->priv; struct device *dev = ubuf->device->this_device; if (ubuf->sg) put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL); deinit_udmabuf(ubuf); kfree(ubuf); } static int begin_cpu_udmabuf(struct dma_buf *buf, enum dma_data_direction direction) { struct udmabuf *ubuf = buf->priv; struct device *dev = ubuf->device->this_device; int ret = 0; if (!ubuf->sg) { ubuf->sg = get_sg_table(dev, buf, direction); if (IS_ERR(ubuf->sg)) { ret = PTR_ERR(ubuf->sg); ubuf->sg = NULL; } } else { dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents, direction); } return ret; } static int end_cpu_udmabuf(struct dma_buf *buf, enum dma_data_direction direction) { struct udmabuf *ubuf = buf->priv; struct device *dev = ubuf->device->this_device; if (!ubuf->sg) return -EINVAL; dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction); return 0; } static const struct dma_buf_ops udmabuf_ops = { .cache_sgt_mapping = true, .map_dma_buf = map_udmabuf, .unmap_dma_buf = unmap_udmabuf, .release = release_udmabuf, .mmap = mmap_udmabuf, .vmap = vmap_udmabuf, .vunmap = vunmap_udmabuf, .begin_cpu_access = begin_cpu_udmabuf, .end_cpu_access = end_cpu_udmabuf, }; #define SEALS_WANTED (F_SEAL_SHRINK) #define SEALS_DENIED (F_SEAL_WRITE|F_SEAL_FUTURE_WRITE) static int check_memfd_seals(struct file *memfd) { int seals; if (!shmem_file(memfd) && !is_file_hugepages(memfd)) return -EBADFD; seals = memfd_fcntl(memfd, F_GET_SEALS, 0); if (seals == -EINVAL) return -EBADFD; if ((seals & SEALS_WANTED) != SEALS_WANTED || (seals & SEALS_DENIED) != 0) return -EINVAL; return 0; } static struct dma_buf *export_udmabuf(struct udmabuf *ubuf, struct miscdevice *device) { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); ubuf->device = device; exp_info.ops = &udmabuf_ops; exp_info.size = ubuf->pagecount << PAGE_SHIFT; exp_info.priv = ubuf; exp_info.flags = O_RDWR; return dma_buf_export(&exp_info); } static long udmabuf_pin_folios(struct udmabuf *ubuf, struct file *memfd, loff_t start, loff_t size, struct folio **folios) { pgoff_t nr_pinned = ubuf->nr_pinned; pgoff_t upgcnt = ubuf->pagecount; u32 cur_folio, cur_pgcnt; pgoff_t pgoff, pgcnt; long nr_folios; loff_t end; pgcnt = size >> PAGE_SHIFT; end = start + (pgcnt << PAGE_SHIFT) - 1; nr_folios = memfd_pin_folios(memfd, start, end, folios, pgcnt, &pgoff); if (nr_folios <= 0) return nr_folios ? nr_folios : -EINVAL; cur_pgcnt = 0; for (cur_folio = 0; cur_folio < nr_folios; ++cur_folio) { pgoff_t subpgoff = pgoff; size_t fsize = folio_size(folios[cur_folio]); ubuf->pinned_folios[nr_pinned++] = folios[cur_folio]; for (; subpgoff < fsize; subpgoff += PAGE_SIZE) { ubuf->folios[upgcnt] = folios[cur_folio]; ubuf->offsets[upgcnt] = subpgoff; ++upgcnt; if (++cur_pgcnt >= pgcnt) goto end; } /** * In a given range, only the first subpage of the first folio * has an offset, that is returned by memfd_pin_folios(). * The first subpages of other folios (in the range) have an * offset of 0. */ pgoff = 0; } end: ubuf->pagecount = upgcnt; ubuf->nr_pinned = nr_pinned; return 0; } static long udmabuf_create(struct miscdevice *device, struct udmabuf_create_list *head, struct udmabuf_create_item *list) { unsigned long max_nr_folios = 0; struct folio **folios = NULL; pgoff_t pgcnt = 0, pglimit; struct udmabuf *ubuf; struct dma_buf *dmabuf; long ret = -EINVAL; u32 i, flags; ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL); if (!ubuf) return -ENOMEM; pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT; for (i = 0; i < head->count; i++) { pgoff_t subpgcnt; if (!PAGE_ALIGNED(list[i].offset)) goto err_noinit; if (!PAGE_ALIGNED(list[i].size)) goto err_noinit; subpgcnt = list[i].size >> PAGE_SHIFT; pgcnt += subpgcnt; if (pgcnt > pglimit) goto err_noinit; max_nr_folios = max_t(unsigned long, subpgcnt, max_nr_folios); } if (!pgcnt) goto err_noinit; ret = init_udmabuf(ubuf, pgcnt); if (ret) goto err; folios = kvmalloc_array(max_nr_folios, sizeof(*folios), GFP_KERNEL); if (!folios) { ret = -ENOMEM; goto err; } for (i = 0; i < head->count; i++) { struct file *memfd = fget(list[i].memfd); if (!memfd) { ret = -EBADFD; goto err; } /* * Take the inode lock to protect against concurrent * memfd_add_seals(), which takes this lock in write mode. */ inode_lock_shared(file_inode(memfd)); ret = check_memfd_seals(memfd); if (ret) goto out_unlock; ret = udmabuf_pin_folios(ubuf, memfd, list[i].offset, list[i].size, folios); out_unlock: inode_unlock_shared(file_inode(memfd)); fput(memfd); if (ret) goto err; } flags = head->flags & UDMABUF_FLAGS_CLOEXEC ? O_CLOEXEC : 0; dmabuf = export_udmabuf(ubuf, device); if (IS_ERR(dmabuf)) { ret = PTR_ERR(dmabuf); goto err; } /* * Ownership of ubuf is held by the dmabuf from here. * If the following dma_buf_fd() fails, dma_buf_put() cleans up both the * dmabuf and the ubuf (through udmabuf_ops.release). */ ret = dma_buf_fd(dmabuf, flags); if (ret < 0) dma_buf_put(dmabuf); kvfree(folios); return ret; err: deinit_udmabuf(ubuf); err_noinit: kfree(ubuf); kvfree(folios); return ret; } static long udmabuf_ioctl_create(struct file *filp, unsigned long arg) { struct udmabuf_create create; struct udmabuf_create_list head; struct udmabuf_create_item list; if (copy_from_user(&create, (void __user *)arg, sizeof(create))) return -EFAULT; head.flags = create.flags; head.count = 1; list.memfd = create.memfd; list.offset = create.offset; list.size = create.size; return udmabuf_create(filp->private_data, &head, &list); } static long udmabuf_ioctl_create_list(struct file *filp, unsigned long arg) { struct udmabuf_create_list head; struct udmabuf_create_item *list; int ret = -EINVAL; u32 lsize; if (copy_from_user(&head, (void __user *)arg, sizeof(head))) return -EFAULT; if (head.count > list_limit) return -EINVAL; lsize = sizeof(struct udmabuf_create_item) * head.count; list = memdup_user((void __user *)(arg + sizeof(head)), lsize); if (IS_ERR(list)) return PTR_ERR(list); ret = udmabuf_create(filp->private_data, &head, list); kfree(list); return ret; } static long udmabuf_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { long ret; switch (ioctl) { case UDMABUF_CREATE: ret = udmabuf_ioctl_create(filp, arg); break; case UDMABUF_CREATE_LIST: ret = udmabuf_ioctl_create_list(filp, arg); break; default: ret = -ENOTTY; break; } return ret; } static const struct file_operations udmabuf_fops = { .owner = THIS_MODULE, .unlocked_ioctl = udmabuf_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = udmabuf_ioctl, #endif }; static struct miscdevice udmabuf_misc = { .minor = MISC_DYNAMIC_MINOR, .name = "udmabuf", .fops = &udmabuf_fops, }; static int __init udmabuf_dev_init(void) { int ret; ret = misc_register(&udmabuf_misc); if (ret < 0) { pr_err("Could not initialize udmabuf device\n"); return ret; } ret = dma_coerce_mask_and_coherent(udmabuf_misc.this_device, DMA_BIT_MASK(64)); if (ret < 0) { pr_err("Could not setup DMA mask for udmabuf device\n"); misc_deregister(&udmabuf_misc); return ret; } return 0; } static void __exit udmabuf_dev_exit(void) { misc_deregister(&udmabuf_misc); } module_init(udmabuf_dev_init) module_exit(udmabuf_dev_exit) MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>"); |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/types.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/sysctl.h> #include <linux/net.h> #include <linux/module.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/mpls.h> #include <linux/netconf.h> #include <linux/nospec.h> #include <linux/vmalloc.h> #include <linux/percpu.h> #include <net/gso.h> #include <net/ip.h> #include <net/dst.h> #include <net/sock.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/netevent.h> #include <net/ip_tunnels.h> #include <net/netns/generic.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #endif #include <net/ipv6_stubs.h> #include <net/rtnh.h> #include "internal.h" /* max memory we will use for mpls_route */ #define MAX_MPLS_ROUTE_MEM 4096 /* Maximum number of labels to look ahead at when selecting a path of * a multipath route */ #define MAX_MP_SELECT_LABELS 4 #define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1) static int label_limit = (1 << 20) - 1; static int ttl_max = 255; #if IS_ENABLED(CONFIG_NET_IP_TUNNEL) static size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e) { return sizeof(struct mpls_shim_hdr); } static const struct ip_tunnel_encap_ops mpls_iptun_ops = { .encap_hlen = ipgre_mpls_encap_hlen, }; static int ipgre_tunnel_encap_add_mpls_ops(void) { return ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); } static void ipgre_tunnel_encap_del_mpls_ops(void) { ip_tunnel_encap_del_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); } #else static int ipgre_tunnel_encap_add_mpls_ops(void) { return 0; } static void ipgre_tunnel_encap_del_mpls_ops(void) { } #endif static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, unsigned int nlm_flags); static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index) { struct mpls_route *rt = NULL; if (index < net->mpls.platform_labels) { struct mpls_route __rcu **platform_label = rcu_dereference(net->mpls.platform_label); rt = rcu_dereference(platform_label[index]); } return rt; } bool mpls_output_possible(const struct net_device *dev) { return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev); } EXPORT_SYMBOL_GPL(mpls_output_possible); static u8 *__mpls_nh_via(struct mpls_route *rt, struct mpls_nh *nh) { return (u8 *)nh + rt->rt_via_offset; } static const u8 *mpls_nh_via(const struct mpls_route *rt, const struct mpls_nh *nh) { return __mpls_nh_via((struct mpls_route *)rt, (struct mpls_nh *)nh); } static unsigned int mpls_nh_header_size(const struct mpls_nh *nh) { /* The size of the layer 2.5 labels to be added for this route */ return nh->nh_labels * sizeof(struct mpls_shim_hdr); } unsigned int mpls_dev_mtu(const struct net_device *dev) { /* The amount of data the layer 2 frame can hold */ return dev->mtu; } EXPORT_SYMBOL_GPL(mpls_dev_mtu); bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) return false; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; } EXPORT_SYMBOL_GPL(mpls_pkt_too_big); void mpls_stats_inc_outucastpkts(struct net_device *dev, const struct sk_buff *skb) { struct mpls_dev *mdev; if (skb->protocol == htons(ETH_P_MPLS_UC)) { mdev = mpls_dev_get(dev); if (mdev) MPLS_INC_STATS_LEN(mdev, skb->len, tx_packets, tx_bytes); } else if (skb->protocol == htons(ETH_P_IP)) { IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6)) { struct inet6_dev *in6dev = __in6_dev_get(dev); if (in6dev) IP6_UPD_PO_STATS(dev_net(dev), in6dev, IPSTATS_MIB_OUT, skb->len); #endif } } EXPORT_SYMBOL_GPL(mpls_stats_inc_outucastpkts); static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb) { struct mpls_entry_decoded dec; unsigned int mpls_hdr_len = 0; struct mpls_shim_hdr *hdr; bool eli_seen = false; int label_index; u32 hash = 0; for (label_index = 0; label_index < MAX_MP_SELECT_LABELS; label_index++) { mpls_hdr_len += sizeof(*hdr); if (!pskb_may_pull(skb, mpls_hdr_len)) break; /* Read and decode the current label */ hdr = mpls_hdr(skb) + label_index; dec = mpls_entry_decode(hdr); /* RFC6790 - reserved labels MUST NOT be used as keys * for the load-balancing function */ if (likely(dec.label >= MPLS_LABEL_FIRST_UNRESERVED)) { hash = jhash_1word(dec.label, hash); /* The entropy label follows the entropy label * indicator, so this means that the entropy * label was just added to the hash - no need to * go any deeper either in the label stack or in the * payload */ if (eli_seen) break; } else if (dec.label == MPLS_LABEL_ENTROPY) { eli_seen = true; } if (!dec.bos) continue; /* found bottom label; does skb have room for a header? */ if (pskb_may_pull(skb, mpls_hdr_len + sizeof(struct iphdr))) { const struct iphdr *v4hdr; v4hdr = (const struct iphdr *)(hdr + 1); if (v4hdr->version == 4) { hash = jhash_3words(ntohl(v4hdr->saddr), ntohl(v4hdr->daddr), v4hdr->protocol, hash); } else if (v4hdr->version == 6 && pskb_may_pull(skb, mpls_hdr_len + sizeof(struct ipv6hdr))) { const struct ipv6hdr *v6hdr; v6hdr = (const struct ipv6hdr *)(hdr + 1); hash = __ipv6_addr_jhash(&v6hdr->saddr, hash); hash = __ipv6_addr_jhash(&v6hdr->daddr, hash); hash = jhash_1word(v6hdr->nexthdr, hash); } } break; } return hash; } static struct mpls_nh *mpls_get_nexthop(struct mpls_route *rt, u8 index) { return (struct mpls_nh *)((u8 *)rt->rt_nh + index * rt->rt_nh_size); } /* number of alive nexthops (rt->rt_nhn_alive) and the flags for * a next hop (nh->nh_flags) are modified by netdev event handlers. * Since those fields can change at any moment, use READ_ONCE to * access both. */ static const struct mpls_nh *mpls_select_multipath(struct mpls_route *rt, struct sk_buff *skb) { u32 hash = 0; int nh_index = 0; int n = 0; u8 alive; /* No need to look further into packet if there's only * one path */ if (rt->rt_nhn == 1) return rt->rt_nh; alive = READ_ONCE(rt->rt_nhn_alive); if (alive == 0) return NULL; hash = mpls_multipath_hash(rt, skb); nh_index = hash % alive; if (alive == rt->rt_nhn) goto out; for_nexthops(rt) { unsigned int nh_flags = READ_ONCE(nh->nh_flags); if (nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) continue; if (n == nh_index) return nh; n++; } endfor_nexthops(rt); out: return mpls_get_nexthop(rt, nh_index); } static bool mpls_egress(struct net *net, struct mpls_route *rt, struct sk_buff *skb, struct mpls_entry_decoded dec) { enum mpls_payload_type payload_type; bool success = false; /* The IPv4 code below accesses through the IPv4 header * checksum, which is 12 bytes into the packet. * The IPv6 code below accesses through the IPv6 hop limit * which is 8 bytes into the packet. * * For all supported cases there should always be at least 12 * bytes of packet data present. The IPv4 header is 20 bytes * without options and the IPv6 header is always 40 bytes * long. */ if (!pskb_may_pull(skb, 12)) return false; payload_type = rt->rt_payload_type; if (payload_type == MPT_UNSPEC) payload_type = ip_hdr(skb)->version; switch (payload_type) { case MPT_IPV4: { struct iphdr *hdr4 = ip_hdr(skb); u8 new_ttl; skb->protocol = htons(ETH_P_IP); /* If propagating TTL, take the decremented TTL from * the incoming MPLS header, otherwise decrement the * TTL, but only if not 0 to avoid underflow. */ if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && net->mpls.ip_ttl_propagate)) new_ttl = dec.ttl; else new_ttl = hdr4->ttl ? hdr4->ttl - 1 : 0; csum_replace2(&hdr4->check, htons(hdr4->ttl << 8), htons(new_ttl << 8)); hdr4->ttl = new_ttl; success = true; break; } case MPT_IPV6: { struct ipv6hdr *hdr6 = ipv6_hdr(skb); skb->protocol = htons(ETH_P_IPV6); /* If propagating TTL, take the decremented TTL from * the incoming MPLS header, otherwise decrement the * hop limit, but only if not 0 to avoid underflow. */ if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && net->mpls.ip_ttl_propagate)) hdr6->hop_limit = dec.ttl; else if (hdr6->hop_limit) hdr6->hop_limit = hdr6->hop_limit - 1; success = true; break; } case MPT_UNSPEC: /* Should have decided which protocol it is by now */ break; } return success; } static int mpls_forward(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct net *net = dev_net(dev); struct mpls_shim_hdr *hdr; const struct mpls_nh *nh; struct mpls_route *rt; struct mpls_entry_decoded dec; struct net_device *out_dev; struct mpls_dev *out_mdev; struct mpls_dev *mdev; unsigned int hh_len; unsigned int new_header_size; unsigned int mtu; int err; /* Careful this entire function runs inside of an rcu critical section */ mdev = mpls_dev_get(dev); if (!mdev) goto drop; MPLS_INC_STATS_LEN(mdev, skb->len, rx_packets, rx_bytes); if (!mdev->input_enabled) { MPLS_INC_STATS(mdev, rx_dropped); goto drop; } if (skb->pkt_type != PACKET_HOST) goto err; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) goto err; if (!pskb_may_pull(skb, sizeof(*hdr))) goto err; skb_dst_drop(skb); /* Read and decode the label */ hdr = mpls_hdr(skb); dec = mpls_entry_decode(hdr); rt = mpls_route_input_rcu(net, dec.label); if (!rt) { MPLS_INC_STATS(mdev, rx_noroute); goto drop; } nh = mpls_select_multipath(rt, skb); if (!nh) goto err; /* Pop the label */ skb_pull(skb, sizeof(*hdr)); skb_reset_network_header(skb); skb_orphan(skb); if (skb_warn_if_lro(skb)) goto err; skb_forward_csum(skb); /* Verify ttl is valid */ if (dec.ttl <= 1) goto err; /* Find the output device */ out_dev = nh->nh_dev; if (!mpls_output_possible(out_dev)) goto tx_err; /* Verify the destination can hold the packet */ new_header_size = mpls_nh_header_size(nh); mtu = mpls_dev_mtu(out_dev); if (mpls_pkt_too_big(skb, mtu - new_header_size)) goto tx_err; hh_len = LL_RESERVED_SPACE(out_dev); if (!out_dev->header_ops) hh_len = 0; /* Ensure there is enough space for the headers in the skb */ if (skb_cow(skb, hh_len + new_header_size)) goto tx_err; skb->dev = out_dev; skb->protocol = htons(ETH_P_MPLS_UC); dec.ttl -= 1; if (unlikely(!new_header_size && dec.bos)) { /* Penultimate hop popping */ if (!mpls_egress(dev_net(out_dev), rt, skb, dec)) goto err; } else { bool bos; int i; skb_push(skb, new_header_size); skb_reset_network_header(skb); /* Push the new labels */ hdr = mpls_hdr(skb); bos = dec.bos; for (i = nh->nh_labels - 1; i >= 0; i--) { hdr[i] = mpls_entry_encode(nh->nh_label[i], dec.ttl, 0, bos); bos = false; } } mpls_stats_inc_outucastpkts(out_dev, skb); /* If via wasn't specified then send out using device address */ if (nh->nh_via_table == MPLS_NEIGH_TABLE_UNSPEC) err = neigh_xmit(NEIGH_LINK_TABLE, out_dev, out_dev->dev_addr, skb); else err = neigh_xmit(nh->nh_via_table, out_dev, mpls_nh_via(rt, nh), skb); if (err) net_dbg_ratelimited("%s: packet transmission failed: %d\n", __func__, err); return 0; tx_err: out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL; if (out_mdev) MPLS_INC_STATS(out_mdev, tx_errors); goto drop; err: MPLS_INC_STATS(mdev, rx_errors); drop: kfree_skb(skb); return NET_RX_DROP; } static struct packet_type mpls_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_MPLS_UC), .func = mpls_forward, }; static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { [RTA_DST] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_TTL_PROPAGATE] = { .type = NLA_U8 }, }; struct mpls_route_config { u32 rc_protocol; u32 rc_ifindex; u8 rc_via_table; u8 rc_via_alen; u8 rc_via[MAX_VIA_ALEN]; u32 rc_label; u8 rc_ttl_propagate; u8 rc_output_labels; u32 rc_output_label[MAX_NEW_LABELS]; u32 rc_nlflags; enum mpls_payload_type rc_payload_type; struct nl_info rc_nlinfo; struct rtnexthop *rc_mp; int rc_mp_len; }; /* all nexthops within a route have the same size based on max * number of labels and max via length for a hop */ static struct mpls_route *mpls_rt_alloc(u8 num_nh, u8 max_alen, u8 max_labels) { u8 nh_size = MPLS_NH_SIZE(max_labels, max_alen); struct mpls_route *rt; size_t size; size = sizeof(*rt) + num_nh * nh_size; if (size > MAX_MPLS_ROUTE_MEM) return ERR_PTR(-EINVAL); rt = kzalloc(size, GFP_KERNEL); if (!rt) return ERR_PTR(-ENOMEM); rt->rt_nhn = num_nh; rt->rt_nhn_alive = num_nh; rt->rt_nh_size = nh_size; rt->rt_via_offset = MPLS_NH_VIA_OFF(max_labels); return rt; } static void mpls_rt_free(struct mpls_route *rt) { if (rt) kfree_rcu(rt, rt_rcu); } static void mpls_notify_route(struct net *net, unsigned index, struct mpls_route *old, struct mpls_route *new, const struct nl_info *info) { struct nlmsghdr *nlh = info ? info->nlh : NULL; unsigned portid = info ? info->portid : 0; int event = new ? RTM_NEWROUTE : RTM_DELROUTE; struct mpls_route *rt = new ? new : old; unsigned nlm_flags = (old && new) ? NLM_F_REPLACE : 0; /* Ignore reserved labels for now */ if (rt && (index >= MPLS_LABEL_FIRST_UNRESERVED)) rtmsg_lfib(event, index, rt, nlh, net, portid, nlm_flags); } static void mpls_route_update(struct net *net, unsigned index, struct mpls_route *new, const struct nl_info *info) { struct mpls_route __rcu **platform_label; struct mpls_route *rt; ASSERT_RTNL(); platform_label = rtnl_dereference(net->mpls.platform_label); rt = rtnl_dereference(platform_label[index]); rcu_assign_pointer(platform_label[index], new); mpls_notify_route(net, index, rt, new, info); /* If we removed a route free it now */ mpls_rt_free(rt); } static unsigned find_free_label(struct net *net) { struct mpls_route __rcu **platform_label; size_t platform_labels; unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; for (index = MPLS_LABEL_FIRST_UNRESERVED; index < platform_labels; index++) { if (!rtnl_dereference(platform_label[index])) return index; } return LABEL_NOT_SPECIFIED; } #if IS_ENABLED(CONFIG_INET) static struct net_device *inet_fib_lookup_dev(struct net *net, const void *addr) { struct net_device *dev; struct rtable *rt; struct in_addr daddr; memcpy(&daddr, addr, sizeof(struct in_addr)); rt = ip_route_output(net, daddr.s_addr, 0, 0, 0, RT_SCOPE_UNIVERSE); if (IS_ERR(rt)) return ERR_CAST(rt); dev = rt->dst.dev; dev_hold(dev); ip_rt_put(rt); return dev; } #else static struct net_device *inet_fib_lookup_dev(struct net *net, const void *addr) { return ERR_PTR(-EAFNOSUPPORT); } #endif #if IS_ENABLED(CONFIG_IPV6) static struct net_device *inet6_fib_lookup_dev(struct net *net, const void *addr) { struct net_device *dev; struct dst_entry *dst; struct flowi6 fl6; if (!ipv6_stub) return ERR_PTR(-EAFNOSUPPORT); memset(&fl6, 0, sizeof(fl6)); memcpy(&fl6.daddr, addr, sizeof(struct in6_addr)); dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst)) return ERR_CAST(dst); dev = dst->dev; dev_hold(dev); dst_release(dst); return dev; } #else static struct net_device *inet6_fib_lookup_dev(struct net *net, const void *addr) { return ERR_PTR(-EAFNOSUPPORT); } #endif static struct net_device *find_outdev(struct net *net, struct mpls_route *rt, struct mpls_nh *nh, int oif) { struct net_device *dev = NULL; if (!oif) { switch (nh->nh_via_table) { case NEIGH_ARP_TABLE: dev = inet_fib_lookup_dev(net, mpls_nh_via(rt, nh)); break; case NEIGH_ND_TABLE: dev = inet6_fib_lookup_dev(net, mpls_nh_via(rt, nh)); break; case NEIGH_LINK_TABLE: break; } } else { dev = dev_get_by_index(net, oif); } if (!dev) return ERR_PTR(-ENODEV); if (IS_ERR(dev)) return dev; /* The caller is holding rtnl anyways, so release the dev reference */ dev_put(dev); return dev; } static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt, struct mpls_nh *nh, int oif) { struct net_device *dev = NULL; int err = -ENODEV; dev = find_outdev(net, rt, nh, oif); if (IS_ERR(dev)) { err = PTR_ERR(dev); dev = NULL; goto errout; } /* Ensure this is a supported device */ err = -EINVAL; if (!mpls_dev_get(dev)) goto errout; if ((nh->nh_via_table == NEIGH_LINK_TABLE) && (dev->addr_len != nh->nh_via_alen)) goto errout; nh->nh_dev = dev; if (!(dev->flags & IFF_UP)) { nh->nh_flags |= RTNH_F_DEAD; } else { unsigned int flags; flags = dev_get_flags(dev); if (!(flags & (IFF_RUNNING | IFF_LOWER_UP))) nh->nh_flags |= RTNH_F_LINKDOWN; } return 0; errout: return err; } static int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table, u8 via_addr[], struct netlink_ext_ack *extack) { struct rtvia *via = nla_data(nla); int err = -EINVAL; int alen; if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid attribute length for RTA_VIA"); goto errout; } alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); if (alen > MAX_VIA_ALEN) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid address length for RTA_VIA"); goto errout; } /* Validate the address family */ switch (via->rtvia_family) { case AF_PACKET: *via_table = NEIGH_LINK_TABLE; break; case AF_INET: *via_table = NEIGH_ARP_TABLE; if (alen != 4) goto errout; break; case AF_INET6: *via_table = NEIGH_ND_TABLE; if (alen != 16) goto errout; break; default: /* Unsupported address family */ goto errout; } memcpy(via_addr, via->rtvia_addr, alen); *via_alen = alen; err = 0; errout: return err; } static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg, struct mpls_route *rt) { struct net *net = cfg->rc_nlinfo.nl_net; struct mpls_nh *nh = rt->rt_nh; int err; int i; if (!nh) return -ENOMEM; nh->nh_labels = cfg->rc_output_labels; for (i = 0; i < nh->nh_labels; i++) nh->nh_label[i] = cfg->rc_output_label[i]; nh->nh_via_table = cfg->rc_via_table; memcpy(__mpls_nh_via(rt, nh), cfg->rc_via, cfg->rc_via_alen); nh->nh_via_alen = cfg->rc_via_alen; err = mpls_nh_assign_dev(net, rt, nh, cfg->rc_ifindex); if (err) goto errout; if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) rt->rt_nhn_alive--; return 0; errout: return err; } static int mpls_nh_build(struct net *net, struct mpls_route *rt, struct mpls_nh *nh, int oif, struct nlattr *via, struct nlattr *newdst, u8 max_labels, struct netlink_ext_ack *extack) { int err = -ENOMEM; if (!nh) goto errout; if (newdst) { err = nla_get_labels(newdst, max_labels, &nh->nh_labels, nh->nh_label, extack); if (err) goto errout; } if (via) { err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table, __mpls_nh_via(rt, nh), extack); if (err) goto errout; } else { nh->nh_via_table = MPLS_NEIGH_TABLE_UNSPEC; } err = mpls_nh_assign_dev(net, rt, nh, oif); if (err) goto errout; return 0; errout: return err; } static u8 mpls_count_nexthops(struct rtnexthop *rtnh, int len, u8 cfg_via_alen, u8 *max_via_alen, u8 *max_labels) { int remaining = len; u8 nhs = 0; *max_via_alen = 0; *max_labels = 0; while (rtnh_ok(rtnh, remaining)) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); int attrlen; u8 n_labels = 0; attrlen = rtnh_attrlen(rtnh); nla = nla_find(attrs, attrlen, RTA_VIA); if (nla && nla_len(nla) >= offsetof(struct rtvia, rtvia_addr)) { int via_alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); if (via_alen <= MAX_VIA_ALEN) *max_via_alen = max_t(u16, *max_via_alen, via_alen); } nla = nla_find(attrs, attrlen, RTA_NEWDST); if (nla && nla_get_labels(nla, MAX_NEW_LABELS, &n_labels, NULL, NULL) != 0) return 0; *max_labels = max_t(u8, *max_labels, n_labels); /* number of nexthops is tracked by a u8. * Check for overflow. */ if (nhs == 255) return 0; nhs++; rtnh = rtnh_next(rtnh, &remaining); } /* leftover implies invalid nexthop configuration, discard it */ return remaining > 0 ? 0 : nhs; } static int mpls_nh_build_multi(struct mpls_route_config *cfg, struct mpls_route *rt, u8 max_labels, struct netlink_ext_ack *extack) { struct rtnexthop *rtnh = cfg->rc_mp; struct nlattr *nla_via, *nla_newdst; int remaining = cfg->rc_mp_len; int err = 0; u8 nhs = 0; change_nexthops(rt) { int attrlen; nla_via = NULL; nla_newdst = NULL; err = -EINVAL; if (!rtnh_ok(rtnh, remaining)) goto errout; /* neither weighted multipath nor any flags * are supported */ if (rtnh->rtnh_hops || rtnh->rtnh_flags) goto errout; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *attrs = rtnh_attrs(rtnh); nla_via = nla_find(attrs, attrlen, RTA_VIA); nla_newdst = nla_find(attrs, attrlen, RTA_NEWDST); } err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh, rtnh->rtnh_ifindex, nla_via, nla_newdst, max_labels, extack); if (err) goto errout; if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) rt->rt_nhn_alive--; rtnh = rtnh_next(rtnh, &remaining); nhs++; } endfor_nexthops(rt); rt->rt_nhn = nhs; return 0; errout: return err; } static bool mpls_label_ok(struct net *net, unsigned int *index, struct netlink_ext_ack *extack) { bool is_ok = true; /* Reserved labels may not be set */ if (*index < MPLS_LABEL_FIRST_UNRESERVED) { NL_SET_ERR_MSG(extack, "Invalid label - must be MPLS_LABEL_FIRST_UNRESERVED or higher"); is_ok = false; } /* The full 20 bit range may not be supported. */ if (is_ok && *index >= net->mpls.platform_labels) { NL_SET_ERR_MSG(extack, "Label >= configured maximum in platform_labels"); is_ok = false; } *index = array_index_nospec(*index, net->mpls.platform_labels); return is_ok; } static int mpls_route_add(struct mpls_route_config *cfg, struct netlink_ext_ack *extack) { struct mpls_route __rcu **platform_label; struct net *net = cfg->rc_nlinfo.nl_net; struct mpls_route *rt, *old; int err = -EINVAL; u8 max_via_alen; unsigned index; u8 max_labels; u8 nhs; index = cfg->rc_label; /* If a label was not specified during insert pick one */ if ((index == LABEL_NOT_SPECIFIED) && (cfg->rc_nlflags & NLM_F_CREATE)) { index = find_free_label(net); } if (!mpls_label_ok(net, &index, extack)) goto errout; /* Append makes no sense with mpls */ err = -EOPNOTSUPP; if (cfg->rc_nlflags & NLM_F_APPEND) { NL_SET_ERR_MSG(extack, "MPLS does not support route append"); goto errout; } err = -EEXIST; platform_label = rtnl_dereference(net->mpls.platform_label); old = rtnl_dereference(platform_label[index]); if ((cfg->rc_nlflags & NLM_F_EXCL) && old) goto errout; err = -EEXIST; if (!(cfg->rc_nlflags & NLM_F_REPLACE) && old) goto errout; err = -ENOENT; if (!(cfg->rc_nlflags & NLM_F_CREATE) && !old) goto errout; err = -EINVAL; if (cfg->rc_mp) { nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len, cfg->rc_via_alen, &max_via_alen, &max_labels); } else { max_via_alen = cfg->rc_via_alen; max_labels = cfg->rc_output_labels; nhs = 1; } if (nhs == 0) { NL_SET_ERR_MSG(extack, "Route does not contain a nexthop"); goto errout; } rt = mpls_rt_alloc(nhs, max_via_alen, max_labels); if (IS_ERR(rt)) { err = PTR_ERR(rt); goto errout; } rt->rt_protocol = cfg->rc_protocol; rt->rt_payload_type = cfg->rc_payload_type; rt->rt_ttl_propagate = cfg->rc_ttl_propagate; if (cfg->rc_mp) err = mpls_nh_build_multi(cfg, rt, max_labels, extack); else err = mpls_nh_build_from_cfg(cfg, rt); if (err) goto freert; mpls_route_update(net, index, rt, &cfg->rc_nlinfo); return 0; freert: mpls_rt_free(rt); errout: return err; } static int mpls_route_del(struct mpls_route_config *cfg, struct netlink_ext_ack *extack) { struct net *net = cfg->rc_nlinfo.nl_net; unsigned index; int err = -EINVAL; index = cfg->rc_label; if (!mpls_label_ok(net, &index, extack)) goto errout; mpls_route_update(net, index, NULL, &cfg->rc_nlinfo); err = 0; errout: return err; } static void mpls_get_stats(struct mpls_dev *mdev, struct mpls_link_stats *stats) { struct mpls_pcpu_stats *p; int i; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(i) { struct mpls_link_stats local; unsigned int start; p = per_cpu_ptr(mdev->stats, i); do { start = u64_stats_fetch_begin(&p->syncp); local = p->stats; } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += local.rx_packets; stats->rx_bytes += local.rx_bytes; stats->tx_packets += local.tx_packets; stats->tx_bytes += local.tx_bytes; stats->rx_errors += local.rx_errors; stats->tx_errors += local.tx_errors; stats->rx_dropped += local.rx_dropped; stats->tx_dropped += local.tx_dropped; stats->rx_noroute += local.rx_noroute; } } static int mpls_fill_stats_af(struct sk_buff *skb, const struct net_device *dev) { struct mpls_link_stats *stats; struct mpls_dev *mdev; struct nlattr *nla; mdev = mpls_dev_get(dev); if (!mdev) return -ENODATA; nla = nla_reserve_64bit(skb, MPLS_STATS_LINK, sizeof(struct mpls_link_stats), MPLS_STATS_UNSPEC); if (!nla) return -EMSGSIZE; stats = nla_data(nla); mpls_get_stats(mdev, stats); return 0; } static size_t mpls_get_stats_af_size(const struct net_device *dev) { struct mpls_dev *mdev; mdev = mpls_dev_get(dev); if (!mdev) return 0; return nla_total_size_64bit(sizeof(struct mpls_link_stats)); } static int mpls_netconf_fill_devconf(struct sk_buff *skb, struct mpls_dev *mdev, u32 portid, u32 seq, int event, unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; bool all = false; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); if (!nlh) return -EMSGSIZE; if (type == NETCONFA_ALL) all = true; ncm = nlmsg_data(nlh); ncm->ncm_family = AF_MPLS; if (nla_put_s32(skb, NETCONFA_IFINDEX, mdev->dev->ifindex) < 0) goto nla_put_failure; if ((all || type == NETCONFA_INPUT) && nla_put_s32(skb, NETCONFA_INPUT, READ_ONCE(mdev->input_enabled)) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int mpls_netconf_msgsize_devconf(int type) { int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + nla_total_size(4); /* NETCONFA_IFINDEX */ bool all = false; if (type == NETCONFA_ALL) all = true; if (all || type == NETCONFA_INPUT) size += nla_total_size(4); return size; } static void mpls_netconf_notify_devconf(struct net *net, int event, int type, struct mpls_dev *mdev) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(mpls_netconf_msgsize_devconf(type), GFP_KERNEL); if (!skb) goto errout; err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_MPLS_NETCONF, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err); } static const struct nla_policy devconf_mpls_policy[NETCONFA_MAX + 1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, }; static int mpls_netconf_valid_get_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_mpls_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_mpls_policy, extack); if (err) return err; for (i = 0; i <= NETCONFA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETCONFA_IFINDEX: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in netconf get request"); return -EINVAL; } } return 0; } static int mpls_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX + 1]; struct net_device *dev; struct mpls_dev *mdev; struct sk_buff *skb; int ifindex; int err; err = mpls_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); dev = __dev_get_by_index(net, ifindex); if (!dev) goto errout; mdev = mpls_dev_get(dev); if (!mdev) goto errout; err = -ENOBUFS; skb = nlmsg_new(mpls_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; err = mpls_netconf_fill_devconf(skb, mdev, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, 0, NETCONFA_ALL); if (err < 0) { /* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; } static int mpls_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct { unsigned long ifindex; } *ctx = (void *)cb->ctx; struct net_device *dev; struct mpls_dev *mdev; int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; struct netconfmsg *ncm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ncm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid data after header in netconf dump request"); return -EINVAL; } } rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->ifindex) { mdev = mpls_dev_get(dev); if (!mdev) continue; err = mpls_netconf_fill_devconf(skb, mdev, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) break; } rcu_read_unlock(); return err; } #define MPLS_PERDEV_SYSCTL_OFFSET(field) \ (&((struct mpls_dev *)0)->field) static int mpls_conf_proc(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int oval = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) { struct mpls_dev *mdev = ctl->extra1; int i = (int *)ctl->data - (int *)mdev; struct net *net = ctl->extra2; int val = *(int *)ctl->data; if (i == offsetof(struct mpls_dev, input_enabled) && val != oval) { mpls_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_INPUT, mdev); } } return ret; } static const struct ctl_table mpls_dev_table[] = { { .procname = "input", .maxlen = sizeof(int), .mode = 0644, .proc_handler = mpls_conf_proc, .data = MPLS_PERDEV_SYSCTL_OFFSET(input_enabled), }, }; static int mpls_dev_sysctl_register(struct net_device *dev, struct mpls_dev *mdev) { char path[sizeof("net/mpls/conf/") + IFNAMSIZ]; size_t table_size = ARRAY_SIZE(mpls_dev_table); struct net *net = dev_net(dev); struct ctl_table *table; int i; table = kmemdup(&mpls_dev_table, sizeof(mpls_dev_table), GFP_KERNEL); if (!table) goto out; /* Table data contains only offsets relative to the base of * the mdev at this point, so make them absolute. */ for (i = 0; i < table_size; i++) { table[i].data = (char *)mdev + (uintptr_t)table[i].data; table[i].extra1 = mdev; table[i].extra2 = net; } snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name); mdev->sysctl = register_net_sysctl_sz(net, path, table, table_size); if (!mdev->sysctl) goto free; mpls_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, mdev); return 0; free: kfree(table); out: mdev->sysctl = NULL; return -ENOBUFS; } static void mpls_dev_sysctl_unregister(struct net_device *dev, struct mpls_dev *mdev) { struct net *net = dev_net(dev); const struct ctl_table *table; if (!mdev->sysctl) return; table = mdev->sysctl->ctl_table_arg; unregister_net_sysctl_table(mdev->sysctl); kfree(table); mpls_netconf_notify_devconf(net, RTM_DELNETCONF, 0, mdev); } static struct mpls_dev *mpls_add_dev(struct net_device *dev) { struct mpls_dev *mdev; int err = -ENOMEM; int i; ASSERT_RTNL(); mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) return ERR_PTR(err); mdev->stats = alloc_percpu(struct mpls_pcpu_stats); if (!mdev->stats) goto free; for_each_possible_cpu(i) { struct mpls_pcpu_stats *mpls_stats; mpls_stats = per_cpu_ptr(mdev->stats, i); u64_stats_init(&mpls_stats->syncp); } mdev->dev = dev; err = mpls_dev_sysctl_register(dev, mdev); if (err) goto free; rcu_assign_pointer(dev->mpls_ptr, mdev); return mdev; free: free_percpu(mdev->stats); kfree(mdev); return ERR_PTR(err); } static void mpls_dev_destroy_rcu(struct rcu_head *head) { struct mpls_dev *mdev = container_of(head, struct mpls_dev, rcu); free_percpu(mdev->stats); kfree(mdev); } static int mpls_ifdown(struct net_device *dev, int event) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); bool nh_del = false; u8 alive = 0; if (!rt) continue; if (event == NETDEV_UNREGISTER) { u8 deleted = 0; for_nexthops(rt) { if (!nh->nh_dev || nh->nh_dev == dev) deleted++; if (nh->nh_dev == dev) nh_del = true; } endfor_nexthops(rt); /* if there are no more nexthops, delete the route */ if (deleted == rt->rt_nhn) { mpls_route_update(net, index, NULL, NULL); continue; } if (nh_del) { size_t size = sizeof(*rt) + rt->rt_nhn * rt->rt_nh_size; struct mpls_route *orig = rt; rt = kmemdup(orig, size, GFP_KERNEL); if (!rt) return -ENOMEM; } } change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; if (nh->nh_dev != dev) goto next; switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: nh_flags |= RTNH_F_DEAD; fallthrough; case NETDEV_CHANGE: nh_flags |= RTNH_F_LINKDOWN; break; } if (event == NETDEV_UNREGISTER) nh->nh_dev = NULL; if (nh->nh_flags != nh_flags) WRITE_ONCE(nh->nh_flags, nh_flags); next: if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))) alive++; } endfor_nexthops(rt); WRITE_ONCE(rt->rt_nhn_alive, alive); if (nh_del) mpls_route_update(net, index, rt, NULL); } return 0; } static void mpls_ifup(struct net_device *dev, unsigned int flags) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); unsigned index; u8 alive; platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); if (!rt) continue; alive = 0; change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; if (!(nh_flags & flags)) { alive++; continue; } if (nh->nh_dev != dev) continue; alive++; nh_flags &= ~flags; WRITE_ONCE(nh->nh_flags, nh_flags); } endfor_nexthops(rt); WRITE_ONCE(rt->rt_nhn_alive, alive); } } static int mpls_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct mpls_dev *mdev; unsigned int flags; int err; if (event == NETDEV_REGISTER) { mdev = mpls_add_dev(dev); if (IS_ERR(mdev)) return notifier_from_errno(PTR_ERR(mdev)); return NOTIFY_OK; } mdev = mpls_dev_get(dev); if (!mdev) return NOTIFY_OK; switch (event) { case NETDEV_DOWN: err = mpls_ifdown(dev, event); if (err) return notifier_from_errno(err); break; case NETDEV_UP: flags = dev_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); else mpls_ifup(dev, RTNH_F_DEAD); break; case NETDEV_CHANGE: flags = dev_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) { mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); } else { err = mpls_ifdown(dev, event); if (err) return notifier_from_errno(err); } break; case NETDEV_UNREGISTER: err = mpls_ifdown(dev, event); if (err) return notifier_from_errno(err); mdev = mpls_dev_get(dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); RCU_INIT_POINTER(dev->mpls_ptr, NULL); call_rcu(&mdev->rcu, mpls_dev_destroy_rcu); } break; case NETDEV_CHANGENAME: mdev = mpls_dev_get(dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); err = mpls_dev_sysctl_register(dev, mdev); if (err) return notifier_from_errno(err); } break; } return NOTIFY_OK; } static struct notifier_block mpls_dev_notifier = { .notifier_call = mpls_dev_notify, }; static int nla_put_via(struct sk_buff *skb, u8 table, const void *addr, int alen) { static const int table_to_family[NEIGH_NR_TABLES + 1] = { AF_INET, AF_INET6, AF_PACKET, }; struct nlattr *nla; struct rtvia *via; int family = AF_UNSPEC; nla = nla_reserve(skb, RTA_VIA, alen + 2); if (!nla) return -EMSGSIZE; if (table <= NEIGH_NR_TABLES) family = table_to_family[table]; via = nla_data(nla); via->rtvia_family = family; memcpy(via->rtvia_addr, addr, alen); return 0; } int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, const u32 label[]) { struct nlattr *nla; struct mpls_shim_hdr *nla_label; bool bos; int i; nla = nla_reserve(skb, attrtype, labels*4); if (!nla) return -EMSGSIZE; nla_label = nla_data(nla); bos = true; for (i = labels - 1; i >= 0; i--) { nla_label[i] = mpls_entry_encode(label[i], 0, 0, bos); bos = false; } return 0; } EXPORT_SYMBOL_GPL(nla_put_labels); int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels, u32 label[], struct netlink_ext_ack *extack) { unsigned len = nla_len(nla); struct mpls_shim_hdr *nla_label; u8 nla_labels; bool bos; int i; /* len needs to be an even multiple of 4 (the label size). Number * of labels is a u8 so check for overflow. */ if (len & 3 || len / 4 > 255) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid length for labels attribute"); return -EINVAL; } /* Limit the number of new labels allowed */ nla_labels = len/4; if (nla_labels > max_labels) { NL_SET_ERR_MSG(extack, "Too many labels"); return -EINVAL; } /* when label == NULL, caller wants number of labels */ if (!label) goto out; nla_label = nla_data(nla); bos = true; for (i = nla_labels - 1; i >= 0; i--, bos = false) { struct mpls_entry_decoded dec; dec = mpls_entry_decode(nla_label + i); /* Ensure the bottom of stack flag is properly set * and ttl and tc are both clear. */ if (dec.ttl) { NL_SET_ERR_MSG_ATTR(extack, nla, "TTL in label must be 0"); return -EINVAL; } if (dec.tc) { NL_SET_ERR_MSG_ATTR(extack, nla, "Traffic class in label must be 0"); return -EINVAL; } if (dec.bos != bos) { NL_SET_BAD_ATTR(extack, nla); if (bos) { NL_SET_ERR_MSG(extack, "BOS bit must be set in first label"); } else { NL_SET_ERR_MSG(extack, "BOS bit can only be set in first label"); } return -EINVAL; } switch (dec.label) { case MPLS_LABEL_IMPLNULL: /* RFC3032: This is a label that an LSR may * assign and distribute, but which never * actually appears in the encapsulation. */ NL_SET_ERR_MSG_ATTR(extack, nla, "Implicit NULL Label (3) can not be used in encapsulation"); return -EINVAL; } label[i] = dec.label; } out: *labels = nla_labels; return 0; } EXPORT_SYMBOL_GPL(nla_get_labels); static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, struct mpls_route_config *cfg, struct netlink_ext_ack *extack) { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; int index; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); if (rtm->rtm_family != AF_MPLS) { NL_SET_ERR_MSG(extack, "Invalid address family in rtmsg"); goto errout; } if (rtm->rtm_dst_len != 20) { NL_SET_ERR_MSG(extack, "rtm_dst_len must be 20 for MPLS"); goto errout; } if (rtm->rtm_src_len != 0) { NL_SET_ERR_MSG(extack, "rtm_src_len must be 0 for MPLS"); goto errout; } if (rtm->rtm_tos != 0) { NL_SET_ERR_MSG(extack, "rtm_tos must be 0 for MPLS"); goto errout; } if (rtm->rtm_table != RT_TABLE_MAIN) { NL_SET_ERR_MSG(extack, "MPLS only supports the main route table"); goto errout; } /* Any value is acceptable for rtm_protocol */ /* As mpls uses destination specific addresses * (or source specific address in the case of multicast) * all addresses have universal scope. */ if (rtm->rtm_scope != RT_SCOPE_UNIVERSE) { NL_SET_ERR_MSG(extack, "Invalid route scope - MPLS only supports UNIVERSE"); goto errout; } if (rtm->rtm_type != RTN_UNICAST) { NL_SET_ERR_MSG(extack, "Invalid route type - MPLS only supports UNICAST"); goto errout; } if (rtm->rtm_flags != 0) { NL_SET_ERR_MSG(extack, "rtm_flags must be 0 for MPLS"); goto errout; } cfg->rc_label = LABEL_NOT_SPECIFIED; cfg->rc_protocol = rtm->rtm_protocol; cfg->rc_via_table = MPLS_NEIGH_TABLE_UNSPEC; cfg->rc_ttl_propagate = MPLS_TTL_PROP_DEFAULT; cfg->rc_nlflags = nlh->nlmsg_flags; cfg->rc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->rc_nlinfo.nlh = nlh; cfg->rc_nlinfo.nl_net = sock_net(skb->sk); for (index = 0; index <= RTA_MAX; index++) { struct nlattr *nla = tb[index]; if (!nla) continue; switch (index) { case RTA_OIF: cfg->rc_ifindex = nla_get_u32(nla); break; case RTA_NEWDST: if (nla_get_labels(nla, MAX_NEW_LABELS, &cfg->rc_output_labels, cfg->rc_output_label, extack)) goto errout; break; case RTA_DST: { u8 label_count; if (nla_get_labels(nla, 1, &label_count, &cfg->rc_label, extack)) goto errout; if (!mpls_label_ok(cfg->rc_nlinfo.nl_net, &cfg->rc_label, extack)) goto errout; break; } case RTA_GATEWAY: NL_SET_ERR_MSG(extack, "MPLS does not support RTA_GATEWAY attribute"); goto errout; case RTA_VIA: { if (nla_get_via(nla, &cfg->rc_via_alen, &cfg->rc_via_table, cfg->rc_via, extack)) goto errout; break; } case RTA_MULTIPATH: { cfg->rc_mp = nla_data(nla); cfg->rc_mp_len = nla_len(nla); break; } case RTA_TTL_PROPAGATE: { u8 ttl_propagate = nla_get_u8(nla); if (ttl_propagate > 1) { NL_SET_ERR_MSG_ATTR(extack, nla, "RTA_TTL_PROPAGATE can only be 0 or 1"); goto errout; } cfg->rc_ttl_propagate = ttl_propagate ? MPLS_TTL_PROP_ENABLED : MPLS_TTL_PROP_DISABLED; break; } default: NL_SET_ERR_MSG_ATTR(extack, nla, "Unknown attribute"); /* Unsupported attribute */ goto errout; } } err = 0; errout: return err; } static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct mpls_route_config *cfg; int err; cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); if (!cfg) return -ENOMEM; err = rtm_to_route_config(skb, nlh, cfg, extack); if (err < 0) goto out; err = mpls_route_del(cfg, extack); out: kfree(cfg); return err; } static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct mpls_route_config *cfg; int err; cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); if (!cfg) return -ENOMEM; err = rtm_to_route_config(skb, nlh, cfg, extack); if (err < 0) goto out; err = mpls_route_add(cfg, extack); out: kfree(cfg); return err; } static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, u32 label, struct mpls_route *rt, int flags) { struct net_device *dev; struct nlmsghdr *nlh; struct rtmsg *rtm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = AF_MPLS; rtm->rtm_dst_len = 20; rtm->rtm_src_len = 0; rtm->rtm_tos = 0; rtm->rtm_table = RT_TABLE_MAIN; rtm->rtm_protocol = rt->rt_protocol; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_type = RTN_UNICAST; rtm->rtm_flags = 0; if (nla_put_labels(skb, RTA_DST, 1, &label)) goto nla_put_failure; if (rt->rt_ttl_propagate != MPLS_TTL_PROP_DEFAULT) { bool ttl_propagate = rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED; if (nla_put_u8(skb, RTA_TTL_PROPAGATE, ttl_propagate)) goto nla_put_failure; } if (rt->rt_nhn == 1) { const struct mpls_nh *nh = rt->rt_nh; if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, nh->nh_label)) goto nla_put_failure; if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; dev = nh->nh_dev; if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; if (nh->nh_flags & RTNH_F_LINKDOWN) rtm->rtm_flags |= RTNH_F_LINKDOWN; if (nh->nh_flags & RTNH_F_DEAD) rtm->rtm_flags |= RTNH_F_DEAD; } else { struct rtnexthop *rtnh; struct nlattr *mp; u8 linkdown = 0; u8 dead = 0; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; for_nexthops(rt) { dev = nh->nh_dev; if (!dev) continue; rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); if (!rtnh) goto nla_put_failure; rtnh->rtnh_ifindex = dev->ifindex; if (nh->nh_flags & RTNH_F_LINKDOWN) { rtnh->rtnh_flags |= RTNH_F_LINKDOWN; linkdown++; } if (nh->nh_flags & RTNH_F_DEAD) { rtnh->rtnh_flags |= RTNH_F_DEAD; dead++; } if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, nh->nh_label)) goto nla_put_failure; if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh; } endfor_nexthops(rt); if (linkdown == rt->rt_nhn) rtm->rtm_flags |= RTNH_F_LINKDOWN; if (dead == rt->rt_nhn) rtm->rtm_flags |= RTNH_F_DEAD; nla_nest_end(skb, mp); } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } #if IS_ENABLED(CONFIG_INET) static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb) { return ip_valid_fib_dump_req(net, nlh, filter, cb); } #else static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[RTA_MAX + 1]; struct rtmsg *rtm; int err, i; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for FIB dump request"); return -EINVAL; } rtm = nlmsg_data(nlh); if (rtm->rtm_dst_len || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for FIB dump request"); return -EINVAL; } if (rtm->rtm_protocol) { filter->protocol = rtm->rtm_protocol; filter->filter_set = 1; cb->answer_flags = NLM_F_DUMP_FILTERED; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); if (err < 0) return err; for (i = 0; i <= RTA_MAX; ++i) { int ifindex; if (i == RTA_OIF) { ifindex = nla_get_u32(tb[i]); filter->dev = __dev_get_by_index(net, ifindex); if (!filter->dev) return -ENODEV; filter->filter_set = 1; } else if (tb[i]) { NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in dump request"); return -EINVAL; } } return 0; } #endif static bool mpls_rt_uses_dev(struct mpls_route *rt, const struct net_device *dev) { if (rt->rt_nhn == 1) { struct mpls_nh *nh = rt->rt_nh; if (nh->nh_dev == dev) return true; } else { for_nexthops(rt) { if (nh->nh_dev == dev) return true; } endfor_nexthops(rt); } return false; } static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct mpls_route __rcu **platform_label; struct fib_dump_filter filter = { .rtnl_held = true, }; unsigned int flags = NLM_F_MULTI; size_t platform_labels; unsigned int index; ASSERT_RTNL(); if (cb->strict_check) { int err; err = mpls_valid_fib_dump_req(net, nlh, &filter, cb); if (err < 0) return err; /* for MPLS, there is only 1 table with fixed type and flags. * If either are set in the filter then return nothing. */ if ((filter.table_id && filter.table_id != RT_TABLE_MAIN) || (filter.rt_type && filter.rt_type != RTN_UNICAST) || filter.flags) return skb->len; } index = cb->args[0]; if (index < MPLS_LABEL_FIRST_UNRESERVED) index = MPLS_LABEL_FIRST_UNRESERVED; platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; if (filter.filter_set) flags |= NLM_F_DUMP_FILTERED; for (; index < platform_labels; index++) { struct mpls_route *rt; rt = rtnl_dereference(platform_label[index]); if (!rt) continue; if ((filter.dev && !mpls_rt_uses_dev(rt, filter.dev)) || (filter.protocol && rt->rt_protocol != filter.protocol)) continue; if (mpls_dump_route(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, index, rt, flags) < 0) break; } cb->args[0] = index; return skb->len; } static inline size_t lfib_nlmsg_size(struct mpls_route *rt) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_DST */ + nla_total_size(1); /* RTA_TTL_PROPAGATE */ if (rt->rt_nhn == 1) { struct mpls_nh *nh = rt->rt_nh; if (nh->nh_dev) payload += nla_total_size(4); /* RTA_OIF */ if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) /* RTA_VIA */ payload += nla_total_size(2 + nh->nh_via_alen); if (nh->nh_labels) /* RTA_NEWDST */ payload += nla_total_size(nh->nh_labels * 4); } else { /* each nexthop is packed in an attribute */ size_t nhsize = 0; for_nexthops(rt) { if (!nh->nh_dev) continue; nhsize += nla_total_size(sizeof(struct rtnexthop)); /* RTA_VIA */ if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) nhsize += nla_total_size(2 + nh->nh_via_alen); if (nh->nh_labels) nhsize += nla_total_size(nh->nh_labels * 4); } endfor_nexthops(rt); /* nested attribute */ payload += nla_total_size(nhsize); } return payload; } static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, unsigned int nlm_flags) { struct sk_buff *skb; u32 seq = nlh ? nlh->nlmsg_seq : 0; int err = -ENOBUFS; skb = nlmsg_new(lfib_nlmsg_size(rt), GFP_KERNEL); if (skb == NULL) goto errout; err = mpls_dump_route(skb, portid, seq, event, label, rt, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in lfib_nlmsg_size */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, portid, RTNLGRP_MPLS_ROUTE, nlh, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); } static int mpls_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for get route request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_dst_len && rtm->rtm_dst_len != 20) || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get route request"); return -EINVAL; } if (rtm->rtm_flags & ~RTM_F_FIB_MATCH) { NL_SET_ERR_MSG_MOD(extack, "Invalid flags for get route request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); if (err) return err; if ((tb[RTA_DST] || tb[RTA_NEWDST]) && !rtm->rtm_dst_len) { NL_SET_ERR_MSG_MOD(extack, "rtm_dst_len must be 20 for MPLS"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_DST: case RTA_NEWDST: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request"); return -EINVAL; } } return 0; } static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); u32 portid = NETLINK_CB(in_skb).portid; u32 in_label = LABEL_NOT_SPECIFIED; struct nlattr *tb[RTA_MAX + 1]; u32 labels[MAX_NEW_LABELS]; struct mpls_shim_hdr *hdr; unsigned int hdr_size = 0; const struct mpls_nh *nh; struct net_device *dev; struct mpls_route *rt; struct rtmsg *rtm, *r; struct nlmsghdr *nlh; struct sk_buff *skb; u8 n_labels; int err; err = mpls_valid_getroute_req(in_skb, in_nlh, tb, extack); if (err < 0) goto errout; rtm = nlmsg_data(in_nlh); if (tb[RTA_DST]) { u8 label_count; if (nla_get_labels(tb[RTA_DST], 1, &label_count, &in_label, extack)) { err = -EINVAL; goto errout; } if (!mpls_label_ok(net, &in_label, extack)) { err = -EINVAL; goto errout; } } rt = mpls_route_input_rcu(net, in_label); if (!rt) { err = -ENETUNREACH; goto errout; } if (rtm->rtm_flags & RTM_F_FIB_MATCH) { skb = nlmsg_new(lfib_nlmsg_size(rt), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout; } err = mpls_dump_route(skb, portid, in_nlh->nlmsg_seq, RTM_NEWROUTE, in_label, rt, 0); if (err < 0) { /* -EMSGSIZE implies BUG in lfib_nlmsg_size */ WARN_ON(err == -EMSGSIZE); goto errout_free; } return rtnl_unicast(skb, net, portid); } if (tb[RTA_NEWDST]) { if (nla_get_labels(tb[RTA_NEWDST], MAX_NEW_LABELS, &n_labels, labels, extack) != 0) { err = -EINVAL; goto errout; } hdr_size = n_labels * sizeof(struct mpls_shim_hdr); } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout; } skb->protocol = htons(ETH_P_MPLS_UC); if (hdr_size) { bool bos; int i; if (skb_cow(skb, hdr_size)) { err = -ENOBUFS; goto errout_free; } skb_reserve(skb, hdr_size); skb_push(skb, hdr_size); skb_reset_network_header(skb); /* Push new labels */ hdr = mpls_hdr(skb); bos = true; for (i = n_labels - 1; i >= 0; i--) { hdr[i] = mpls_entry_encode(labels[i], 1, 0, bos); bos = false; } } nh = mpls_select_multipath(rt, skb); if (!nh) { err = -ENETUNREACH; goto errout_free; } if (hdr_size) { skb_pull(skb, hdr_size); skb_reset_network_header(skb); } nlh = nlmsg_put(skb, portid, in_nlh->nlmsg_seq, RTM_NEWROUTE, sizeof(*r), 0); if (!nlh) { err = -EMSGSIZE; goto errout_free; } r = nlmsg_data(nlh); r->rtm_family = AF_MPLS; r->rtm_dst_len = 20; r->rtm_src_len = 0; r->rtm_table = RT_TABLE_MAIN; r->rtm_type = RTN_UNICAST; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = rt->rt_protocol; r->rtm_flags = 0; if (nla_put_labels(skb, RTA_DST, 1, &in_label)) goto nla_put_failure; if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, nh->nh_label)) goto nla_put_failure; if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; dev = nh->nh_dev; if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; nlmsg_end(skb, nlh); err = rtnl_unicast(skb, net, portid); errout: return err; nla_put_failure: nlmsg_cancel(skb, nlh); err = -EMSGSIZE; errout_free: kfree_skb(skb); return err; } static int resize_platform_label_table(struct net *net, size_t limit) { size_t size = sizeof(struct mpls_route *) * limit; size_t old_limit; size_t cp_size; struct mpls_route __rcu **labels = NULL, **old; struct mpls_route *rt0 = NULL, *rt2 = NULL; unsigned index; if (size) { labels = kvzalloc(size, GFP_KERNEL); if (!labels) goto nolabels; } /* In case the predefined labels need to be populated */ if (limit > MPLS_LABEL_IPV4NULL) { struct net_device *lo = net->loopback_dev; rt0 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt0)) goto nort0; rt0->rt_nh->nh_dev = lo; rt0->rt_protocol = RTPROT_KERNEL; rt0->rt_payload_type = MPT_IPV4; rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt0->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt0->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt0, rt0->rt_nh), lo->dev_addr, lo->addr_len); } if (limit > MPLS_LABEL_IPV6NULL) { struct net_device *lo = net->loopback_dev; rt2 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt2)) goto nort2; rt2->rt_nh->nh_dev = lo; rt2->rt_protocol = RTPROT_KERNEL; rt2->rt_payload_type = MPT_IPV6; rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt2->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt2->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt2, rt2->rt_nh), lo->dev_addr, lo->addr_len); } rtnl_lock(); /* Remember the original table */ old = rtnl_dereference(net->mpls.platform_label); old_limit = net->mpls.platform_labels; /* Free any labels beyond the new table */ for (index = limit; index < old_limit; index++) mpls_route_update(net, index, NULL, NULL); /* Copy over the old labels */ cp_size = size; if (old_limit < limit) cp_size = old_limit * sizeof(struct mpls_route *); memcpy(labels, old, cp_size); /* If needed set the predefined labels */ if ((old_limit <= MPLS_LABEL_IPV6NULL) && (limit > MPLS_LABEL_IPV6NULL)) { RCU_INIT_POINTER(labels[MPLS_LABEL_IPV6NULL], rt2); rt2 = NULL; } if ((old_limit <= MPLS_LABEL_IPV4NULL) && (limit > MPLS_LABEL_IPV4NULL)) { RCU_INIT_POINTER(labels[MPLS_LABEL_IPV4NULL], rt0); rt0 = NULL; } /* Update the global pointers */ net->mpls.platform_labels = limit; rcu_assign_pointer(net->mpls.platform_label, labels); rtnl_unlock(); mpls_rt_free(rt2); mpls_rt_free(rt0); if (old) { synchronize_rcu(); kvfree(old); } return 0; nort2: mpls_rt_free(rt0); nort0: kvfree(labels); nolabels: return -ENOMEM; } static int mpls_platform_labels(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = table->data; int platform_labels = net->mpls.platform_labels; int ret; struct ctl_table tmp = { .procname = table->procname, .data = &platform_labels, .maxlen = sizeof(int), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = &label_limit, }; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) ret = resize_platform_label_table(net, platform_labels); return ret; } #define MPLS_NS_SYSCTL_OFFSET(field) \ (&((struct net *)0)->field) static const struct ctl_table mpls_table[] = { { .procname = "platform_labels", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = mpls_platform_labels, }, { .procname = "ip_ttl_propagate", .data = MPLS_NS_SYSCTL_OFFSET(mpls.ip_ttl_propagate), .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "default_ttl", .data = MPLS_NS_SYSCTL_OFFSET(mpls.default_ttl), .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &ttl_max, }, }; static int mpls_net_init(struct net *net) { size_t table_size = ARRAY_SIZE(mpls_table); struct ctl_table *table; int i; net->mpls.platform_labels = 0; net->mpls.platform_label = NULL; net->mpls.ip_ttl_propagate = 1; net->mpls.default_ttl = 255; table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL); if (table == NULL) return -ENOMEM; /* Table data contains only offsets relative to the base of * the mdev at this point, so make them absolute. */ for (i = 0; i < table_size; i++) table[i].data = (char *)net + (uintptr_t)table[i].data; net->mpls.ctl = register_net_sysctl_sz(net, "net/mpls", table, table_size); if (net->mpls.ctl == NULL) { kfree(table); return -ENOMEM; } return 0; } static void mpls_net_exit(struct net *net) { struct mpls_route __rcu **platform_label; size_t platform_labels; const struct ctl_table *table; unsigned int index; table = net->mpls.ctl->ctl_table_arg; unregister_net_sysctl_table(net->mpls.ctl); kfree(table); /* An rcu grace period has passed since there was a device in * the network namespace (and thus the last in flight packet) * left this network namespace. This is because * unregister_netdevice_many and netdev_run_todo has completed * for each network device that was in this network namespace. * * As such no additional rcu synchronization is necessary when * freeing the platform_label table. */ rtnl_lock(); platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; for (index = 0; index < platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); RCU_INIT_POINTER(platform_label[index], NULL); mpls_notify_route(net, index, rt, NULL, NULL); mpls_rt_free(rt); } rtnl_unlock(); kvfree(platform_label); } static struct pernet_operations mpls_net_ops = { .init = mpls_net_init, .exit = mpls_net_exit, }; static struct rtnl_af_ops mpls_af_ops __read_mostly = { .family = AF_MPLS, .fill_stats_af = mpls_fill_stats_af, .get_stats_af_size = mpls_get_stats_af_size, }; static const struct rtnl_msg_handler mpls_rtnl_msg_handlers[] __initdata_or_module = { {THIS_MODULE, PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, 0}, {THIS_MODULE, PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, 0}, {THIS_MODULE, PF_MPLS, RTM_GETROUTE, mpls_getroute, mpls_dump_routes, 0}, {THIS_MODULE, PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, mpls_netconf_dump_devconf, RTNL_FLAG_DUMP_UNLOCKED}, }; static int __init mpls_init(void) { int err; BUILD_BUG_ON(sizeof(struct mpls_shim_hdr) != 4); err = register_pernet_subsys(&mpls_net_ops); if (err) goto out; err = register_netdevice_notifier(&mpls_dev_notifier); if (err) goto out_unregister_pernet; dev_add_pack(&mpls_packet_type); err = rtnl_af_register(&mpls_af_ops); if (err) goto out_unregister_dev_type; err = rtnl_register_many(mpls_rtnl_msg_handlers); if (err) goto out_unregister_rtnl_af; err = ipgre_tunnel_encap_add_mpls_ops(); if (err) { pr_err("Can't add mpls over gre tunnel ops\n"); goto out_unregister_rtnl; } err = 0; out: return err; out_unregister_rtnl: rtnl_unregister_many(mpls_rtnl_msg_handlers); out_unregister_rtnl_af: rtnl_af_unregister(&mpls_af_ops); out_unregister_dev_type: dev_remove_pack(&mpls_packet_type); out_unregister_pernet: unregister_pernet_subsys(&mpls_net_ops); goto out; } module_init(mpls_init); static void __exit mpls_exit(void) { rtnl_unregister_all(PF_MPLS); rtnl_af_unregister(&mpls_af_ops); dev_remove_pack(&mpls_packet_type); unregister_netdevice_notifier(&mpls_dev_notifier); unregister_pernet_subsys(&mpls_net_ops); ipgre_tunnel_encap_del_mpls_ops(); } module_exit(mpls_exit); MODULE_DESCRIPTION("MultiProtocol Label Switching"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS_NETPROTO(PF_MPLS); |
| 32 181 180 181 126 55 121 143 62 62 53 15 181 167 13 188 189 142 83 91 3 143 51 142 35 142 143 143 11 10 188 143 142 187 189 40 27 1 18 142 141 38 121 116 37 5 41 118 5 38 56 19 18 45 6 6 6 6 2 6 6 3 6 6 29 3 29 29 15 25 15 15 29 10 20 20 73 8 61 1 3 4 61 3 58 6 6 8 70 69 70 61 9 6 3 1 1 59 59 59 1 58 64 6 6 8 9 9 6 3 3 9 34 3 31 30 2 5 31 30 1 28 9 9 9 6 6 6 6 6 6 70 70 6 12 102 102 102 1 4 65 65 65 65 65 26 116 116 116 72 72 7 8 60 71 58 59 59 116 116 8 108 115 8 108 60 60 60 59 59 59 12 12 8 4 4 7 5 1 6 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 * Portions Copyright (C) Christoph Hellwig, 2001-2002 */ /* * jfs_logmgr.c: log manager * * for related information, see transaction manager (jfs_txnmgr.c), and * recovery manager (jfs_logredo.c). * * note: for detail, RTFS. * * log buffer manager: * special purpose buffer manager supporting log i/o requirements. * per log serial pageout of logpage * queuing i/o requests and redrive i/o at iodone * maintain current logpage buffer * no caching since append only * appropriate jfs buffer cache buffers as needed * * group commit: * transactions which wrote COMMIT records in the same in-memory * log page during the pageout of previous/current log page(s) are * committed together by the pageout of the page. * * TBD lazy commit: * transactions are committed asynchronously when the log page * containing it COMMIT is paged out when it becomes full; * * serialization: * . a per log lock serialize log write. * . a per log lock serialize group commit. * . a per log lock serialize log open/close; * * TBD log integrity: * careful-write (ping-pong) of last logpage to recover from crash * in overwrite. * detection of split (out-of-order) write of physical sectors * of last logpage via timestamp at end of each sector * with its mirror data array at trailer). * * alternatives: * lsn - 64-bit monotonically increasing integer vs * 32-bit lspn and page eor. */ #include <linux/fs.h> #include <linux/blkdev.h> #include <linux/interrupt.h> #include <linux/completion.h> #include <linux/kthread.h> #include <linux/buffer_head.h> /* for sync_blockdev() */ #include <linux/bio.h> #include <linux/freezer.h> #include <linux/export.h> #include <linux/delay.h> #include <linux/mutex.h> #include <linux/seq_file.h> #include <linux/slab.h> #include "jfs_incore.h" #include "jfs_filsys.h" #include "jfs_metapage.h" #include "jfs_superblock.h" #include "jfs_txnmgr.h" #include "jfs_debug.h" /* * lbuf's ready to be redriven. Protected by log_redrive_lock (jfsIO thread) */ static struct lbuf *log_redrive_list; static DEFINE_SPINLOCK(log_redrive_lock); /* * log read/write serialization (per log) */ #define LOG_LOCK_INIT(log) mutex_init(&(log)->loglock) #define LOG_LOCK(log) mutex_lock(&((log)->loglock)) #define LOG_UNLOCK(log) mutex_unlock(&((log)->loglock)) /* * log group commit serialization (per log) */ #define LOGGC_LOCK_INIT(log) spin_lock_init(&(log)->gclock) #define LOGGC_LOCK(log) spin_lock_irq(&(log)->gclock) #define LOGGC_UNLOCK(log) spin_unlock_irq(&(log)->gclock) #define LOGGC_WAKEUP(tblk) wake_up_all(&(tblk)->gcwait) /* * log sync serialization (per log) */ #define LOGSYNC_DELTA(logsize) min((logsize)/8, 128*LOGPSIZE) #define LOGSYNC_BARRIER(logsize) ((logsize)/4) /* #define LOGSYNC_DELTA(logsize) min((logsize)/4, 256*LOGPSIZE) #define LOGSYNC_BARRIER(logsize) ((logsize)/2) */ /* * log buffer cache synchronization */ static DEFINE_SPINLOCK(jfsLCacheLock); #define LCACHE_LOCK(flags) spin_lock_irqsave(&jfsLCacheLock, flags) #define LCACHE_UNLOCK(flags) spin_unlock_irqrestore(&jfsLCacheLock, flags) /* * See __SLEEP_COND in jfs_locks.h */ #define LCACHE_SLEEP_COND(wq, cond, flags) \ do { \ if (cond) \ break; \ __SLEEP_COND(wq, cond, LCACHE_LOCK(flags), LCACHE_UNLOCK(flags)); \ } while (0) #define LCACHE_WAKEUP(event) wake_up(event) /* * lbuf buffer cache (lCache) control */ /* log buffer manager pageout control (cumulative, inclusive) */ #define lbmREAD 0x0001 #define lbmWRITE 0x0002 /* enqueue at tail of write queue; * init pageout if at head of queue; */ #define lbmRELEASE 0x0004 /* remove from write queue * at completion of pageout; * do not free/recycle it yet: * caller will free it; */ #define lbmSYNC 0x0008 /* do not return to freelist * when removed from write queue; */ #define lbmFREE 0x0010 /* return to freelist * at completion of pageout; * the buffer may be recycled; */ #define lbmDONE 0x0020 #define lbmERROR 0x0040 #define lbmGC 0x0080 /* lbmIODone to perform post-GC processing * of log page */ #define lbmDIRECT 0x0100 /* * Global list of active external journals */ static LIST_HEAD(jfs_external_logs); static struct jfs_log *dummy_log; static DEFINE_MUTEX(jfs_log_mutex); /* * forward references */ static int lmWriteRecord(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, struct tlock * tlck); static int lmNextPage(struct jfs_log * log); static int lmLogFileSystem(struct jfs_log * log, struct jfs_sb_info *sbi, int activate); static int open_inline_log(struct super_block *sb); static int open_dummy_log(struct super_block *sb); static int lbmLogInit(struct jfs_log * log); static void lbmLogShutdown(struct jfs_log * log); static struct lbuf *lbmAllocate(struct jfs_log * log, int); static void lbmFree(struct lbuf * bp); static void lbmfree(struct lbuf * bp); static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp); static void lbmWrite(struct jfs_log * log, struct lbuf * bp, int flag, int cant_block); static void lbmDirectWrite(struct jfs_log * log, struct lbuf * bp, int flag); static int lbmIOWait(struct lbuf * bp, int flag); static bio_end_io_t lbmIODone; static void lbmStartIO(struct lbuf * bp); static void lmGCwrite(struct jfs_log * log, int cant_block); static int lmLogSync(struct jfs_log * log, int hard_sync); /* * statistics */ #ifdef CONFIG_JFS_STATISTICS static struct lmStat { uint commit; /* # of commit */ uint pagedone; /* # of page written */ uint submitted; /* # of pages submitted */ uint full_page; /* # of full pages submitted */ uint partial_page; /* # of partial pages submitted */ } lmStat; #endif static void write_special_inodes(struct jfs_log *log, int (*writer)(struct address_space *)) { struct jfs_sb_info *sbi; list_for_each_entry(sbi, &log->sb_list, log_list) { writer(sbi->ipbmap->i_mapping); writer(sbi->ipimap->i_mapping); writer(sbi->direct_inode->i_mapping); } } /* * NAME: lmLog() * * FUNCTION: write a log record; * * PARAMETER: * * RETURN: lsn - offset to the next log record to write (end-of-log); * -1 - error; * * note: todo: log error handler */ int lmLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, struct tlock * tlck) { int lsn; int diffp, difft; struct metapage *mp = NULL; unsigned long flags; jfs_info("lmLog: log:0x%p tblk:0x%p, lrd:0x%p tlck:0x%p", log, tblk, lrd, tlck); LOG_LOCK(log); /* log by (out-of-transaction) JFS ? */ if (tblk == NULL) goto writeRecord; /* log from page ? */ if (tlck == NULL || tlck->type & tlckBTROOT || (mp = tlck->mp) == NULL) goto writeRecord; /* * initialize/update page/transaction recovery lsn */ lsn = log->lsn; LOGSYNC_LOCK(log, flags); /* * initialize page lsn if first log write of the page */ if (mp->lsn == 0) { mp->log = log; mp->lsn = lsn; log->count++; /* insert page at tail of logsynclist */ list_add_tail(&mp->synclist, &log->synclist); } /* * initialize/update lsn of tblock of the page * * transaction inherits oldest lsn of pages associated * with allocation/deallocation of resources (their * log records are used to reconstruct allocation map * at recovery time: inode for inode allocation map, * B+-tree index of extent descriptors for block * allocation map); * allocation map pages inherit transaction lsn at * commit time to allow forwarding log syncpt past log * records associated with allocation/deallocation of * resources only after persistent map of these map pages * have been updated and propagated to home. */ /* * initialize transaction lsn: */ if (tblk->lsn == 0) { /* inherit lsn of its first page logged */ tblk->lsn = mp->lsn; log->count++; /* insert tblock after the page on logsynclist */ list_add(&tblk->synclist, &mp->synclist); } /* * update transaction lsn: */ else { /* inherit oldest/smallest lsn of page */ logdiff(diffp, mp->lsn, log); logdiff(difft, tblk->lsn, log); if (diffp < difft) { /* update tblock lsn with page lsn */ tblk->lsn = mp->lsn; /* move tblock after page on logsynclist */ list_move(&tblk->synclist, &mp->synclist); } } LOGSYNC_UNLOCK(log, flags); /* * write the log record */ writeRecord: lsn = lmWriteRecord(log, tblk, lrd, tlck); /* * forward log syncpt if log reached next syncpt trigger */ logdiff(diffp, lsn, log); if (diffp >= log->nextsync) lsn = lmLogSync(log, 0); /* update end-of-log lsn */ log->lsn = lsn; LOG_UNLOCK(log); /* return end-of-log address */ return lsn; } /* * NAME: lmWriteRecord() * * FUNCTION: move the log record to current log page * * PARAMETER: cd - commit descriptor * * RETURN: end-of-log address * * serialization: LOG_LOCK() held on entry/exit */ static int lmWriteRecord(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, struct tlock * tlck) { int lsn = 0; /* end-of-log address */ struct lbuf *bp; /* dst log page buffer */ struct logpage *lp; /* dst log page */ caddr_t dst; /* destination address in log page */ int dstoffset; /* end-of-log offset in log page */ int freespace; /* free space in log page */ caddr_t p; /* src meta-data page */ caddr_t src; int srclen; int nbytes; /* number of bytes to move */ int i; int len; struct linelock *linelock; struct lv *lv; struct lvd *lvd; int l2linesize; len = 0; /* retrieve destination log page to write */ bp = (struct lbuf *) log->bp; lp = (struct logpage *) bp->l_ldata; dstoffset = log->eor; /* any log data to write ? */ if (tlck == NULL) goto moveLrd; /* * move log record data */ /* retrieve source meta-data page to log */ if (tlck->flag & tlckPAGELOCK) { p = (caddr_t) (tlck->mp->data); linelock = (struct linelock *) & tlck->lock; } /* retrieve source in-memory inode to log */ else if (tlck->flag & tlckINODELOCK) { if (tlck->type & tlckDTREE) p = (caddr_t) &JFS_IP(tlck->ip)->i_dtroot; else p = (caddr_t) &JFS_IP(tlck->ip)->i_xtroot; linelock = (struct linelock *) & tlck->lock; } else { jfs_err("lmWriteRecord: UFO tlck:0x%p", tlck); return 0; /* Probably should trap */ } l2linesize = linelock->l2linesize; moveData: ASSERT(linelock->index <= linelock->maxcnt); lv = linelock->lv; for (i = 0; i < linelock->index; i++, lv++) { if (lv->length == 0) continue; /* is page full ? */ if (dstoffset >= LOGPSIZE - LOGPTLRSIZE) { /* page become full: move on to next page */ lmNextPage(log); bp = log->bp; lp = (struct logpage *) bp->l_ldata; dstoffset = LOGPHDRSIZE; } /* * move log vector data */ src = (u8 *) p + (lv->offset << l2linesize); srclen = lv->length << l2linesize; len += srclen; while (srclen > 0) { freespace = (LOGPSIZE - LOGPTLRSIZE) - dstoffset; nbytes = min(freespace, srclen); dst = (caddr_t) lp + dstoffset; memcpy(dst, src, nbytes); dstoffset += nbytes; /* is page not full ? */ if (dstoffset < LOGPSIZE - LOGPTLRSIZE) break; /* page become full: move on to next page */ lmNextPage(log); bp = (struct lbuf *) log->bp; lp = (struct logpage *) bp->l_ldata; dstoffset = LOGPHDRSIZE; srclen -= nbytes; src += nbytes; } /* * move log vector descriptor */ len += 4; lvd = (struct lvd *) ((caddr_t) lp + dstoffset); lvd->offset = cpu_to_le16(lv->offset); lvd->length = cpu_to_le16(lv->length); dstoffset += 4; jfs_info("lmWriteRecord: lv offset:%d length:%d", lv->offset, lv->length); } if ((i = linelock->next)) { linelock = (struct linelock *) lid_to_tlock(i); goto moveData; } /* * move log record descriptor */ moveLrd: lrd->length = cpu_to_le16(len); src = (caddr_t) lrd; srclen = LOGRDSIZE; while (srclen > 0) { freespace = (LOGPSIZE - LOGPTLRSIZE) - dstoffset; nbytes = min(freespace, srclen); dst = (caddr_t) lp + dstoffset; memcpy(dst, src, nbytes); dstoffset += nbytes; srclen -= nbytes; /* are there more to move than freespace of page ? */ if (srclen) goto pageFull; /* * end of log record descriptor */ /* update last log record eor */ log->eor = dstoffset; bp->l_eor = dstoffset; lsn = (log->page << L2LOGPSIZE) + dstoffset; if (lrd->type & cpu_to_le16(LOG_COMMIT)) { tblk->clsn = lsn; jfs_info("wr: tclsn:0x%x, beor:0x%x", tblk->clsn, bp->l_eor); INCREMENT(lmStat.commit); /* # of commit */ /* * enqueue tblock for group commit: * * enqueue tblock of non-trivial/synchronous COMMIT * at tail of group commit queue * (trivial/asynchronous COMMITs are ignored by * group commit.) */ LOGGC_LOCK(log); /* init tblock gc state */ tblk->flag = tblkGC_QUEUE; tblk->bp = log->bp; tblk->pn = log->page; tblk->eor = log->eor; /* enqueue transaction to commit queue */ list_add_tail(&tblk->cqueue, &log->cqueue); LOGGC_UNLOCK(log); } jfs_info("lmWriteRecord: lrd:0x%04x bp:0x%p pn:%d eor:0x%x", le16_to_cpu(lrd->type), log->bp, log->page, dstoffset); /* page not full ? */ if (dstoffset < LOGPSIZE - LOGPTLRSIZE) return lsn; pageFull: /* page become full: move on to next page */ lmNextPage(log); bp = (struct lbuf *) log->bp; lp = (struct logpage *) bp->l_ldata; dstoffset = LOGPHDRSIZE; src += nbytes; } return lsn; } /* * NAME: lmNextPage() * * FUNCTION: write current page and allocate next page. * * PARAMETER: log * * RETURN: 0 * * serialization: LOG_LOCK() held on entry/exit */ static int lmNextPage(struct jfs_log * log) { struct logpage *lp; int lspn; /* log sequence page number */ int pn; /* current page number */ struct lbuf *bp; struct lbuf *nextbp; struct tblock *tblk; /* get current log page number and log sequence page number */ pn = log->page; bp = log->bp; lp = (struct logpage *) bp->l_ldata; lspn = le32_to_cpu(lp->h.page); LOGGC_LOCK(log); /* * write or queue the full page at the tail of write queue */ /* get the tail tblk on commit queue */ if (list_empty(&log->cqueue)) tblk = NULL; else tblk = list_entry(log->cqueue.prev, struct tblock, cqueue); /* every tblk who has COMMIT record on the current page, * and has not been committed, must be on commit queue * since tblk is queued at commit queueu at the time * of writing its COMMIT record on the page before * page becomes full (even though the tblk thread * who wrote COMMIT record may have been suspended * currently); */ /* is page bound with outstanding tail tblk ? */ if (tblk && tblk->pn == pn) { /* mark tblk for end-of-page */ tblk->flag |= tblkGC_EOP; if (log->cflag & logGC_PAGEOUT) { /* if page is not already on write queue, * just enqueue (no lbmWRITE to prevent redrive) * buffer to wqueue to ensure correct serial order * of the pages since log pages will be added * continuously */ if (bp->l_wqnext == NULL) lbmWrite(log, bp, 0, 0); } else { /* * No current GC leader, initiate group commit */ log->cflag |= logGC_PAGEOUT; lmGCwrite(log, 0); } } /* page is not bound with outstanding tblk: * init write or mark it to be redriven (lbmWRITE) */ else { /* finalize the page */ bp->l_ceor = bp->l_eor; lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_ceor); lbmWrite(log, bp, lbmWRITE | lbmRELEASE | lbmFREE, 0); } LOGGC_UNLOCK(log); /* * allocate/initialize next page */ /* if log wraps, the first data page of log is 2 * (0 never used, 1 is superblock). */ log->page = (pn == log->size - 1) ? 2 : pn + 1; log->eor = LOGPHDRSIZE; /* ? valid page empty/full at logRedo() */ /* allocate/initialize next log page buffer */ nextbp = lbmAllocate(log, log->page); nextbp->l_eor = log->eor; log->bp = nextbp; /* initialize next log page */ lp = (struct logpage *) nextbp->l_ldata; lp->h.page = lp->t.page = cpu_to_le32(lspn + 1); lp->h.eor = lp->t.eor = cpu_to_le16(LOGPHDRSIZE); return 0; } /* * NAME: lmGroupCommit() * * FUNCTION: group commit * initiate pageout of the pages with COMMIT in the order of * page number - redrive pageout of the page at the head of * pageout queue until full page has been written. * * RETURN: * * NOTE: * LOGGC_LOCK serializes log group commit queue, and * transaction blocks on the commit queue. * N.B. LOG_LOCK is NOT held during lmGroupCommit(). */ int lmGroupCommit(struct jfs_log * log, struct tblock * tblk) { int rc = 0; LOGGC_LOCK(log); /* group committed already ? */ if (tblk->flag & tblkGC_COMMITTED) { if (tblk->flag & tblkGC_ERROR) rc = -EIO; LOGGC_UNLOCK(log); return rc; } jfs_info("lmGroup Commit: tblk = 0x%p, gcrtc = %d", tblk, log->gcrtc); if (tblk->xflag & COMMIT_LAZY) tblk->flag |= tblkGC_LAZY; if ((!(log->cflag & logGC_PAGEOUT)) && (!list_empty(&log->cqueue)) && (!(tblk->xflag & COMMIT_LAZY) || test_bit(log_FLUSH, &log->flag) || jfs_tlocks_low)) { /* * No pageout in progress * * start group commit as its group leader. */ log->cflag |= logGC_PAGEOUT; lmGCwrite(log, 0); } if (tblk->xflag & COMMIT_LAZY) { /* * Lazy transactions can leave now */ LOGGC_UNLOCK(log); return 0; } /* lmGCwrite gives up LOGGC_LOCK, check again */ if (tblk->flag & tblkGC_COMMITTED) { if (tblk->flag & tblkGC_ERROR) rc = -EIO; LOGGC_UNLOCK(log); return rc; } /* upcount transaction waiting for completion */ log->gcrtc++; tblk->flag |= tblkGC_READY; __SLEEP_COND(tblk->gcwait, (tblk->flag & tblkGC_COMMITTED), LOGGC_LOCK(log), LOGGC_UNLOCK(log)); /* removed from commit queue */ if (tblk->flag & tblkGC_ERROR) rc = -EIO; LOGGC_UNLOCK(log); return rc; } /* * NAME: lmGCwrite() * * FUNCTION: group commit write * initiate write of log page, building a group of all transactions * with commit records on that page. * * RETURN: None * * NOTE: * LOGGC_LOCK must be held by caller. * N.B. LOG_LOCK is NOT held during lmGroupCommit(). */ static void lmGCwrite(struct jfs_log * log, int cant_write) { struct lbuf *bp; struct logpage *lp; int gcpn; /* group commit page number */ struct tblock *tblk; struct tblock *xtblk = NULL; /* * build the commit group of a log page * * scan commit queue and make a commit group of all * transactions with COMMIT records on the same log page. */ /* get the head tblk on the commit queue */ gcpn = list_entry(log->cqueue.next, struct tblock, cqueue)->pn; list_for_each_entry(tblk, &log->cqueue, cqueue) { if (tblk->pn != gcpn) break; xtblk = tblk; /* state transition: (QUEUE, READY) -> COMMIT */ tblk->flag |= tblkGC_COMMIT; } tblk = xtblk; /* last tblk of the page */ /* * pageout to commit transactions on the log page. */ bp = (struct lbuf *) tblk->bp; lp = (struct logpage *) bp->l_ldata; /* is page already full ? */ if (tblk->flag & tblkGC_EOP) { /* mark page to free at end of group commit of the page */ tblk->flag &= ~tblkGC_EOP; tblk->flag |= tblkGC_FREE; bp->l_ceor = bp->l_eor; lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_ceor); lbmWrite(log, bp, lbmWRITE | lbmRELEASE | lbmGC, cant_write); INCREMENT(lmStat.full_page); } /* page is not yet full */ else { bp->l_ceor = tblk->eor; /* ? bp->l_ceor = bp->l_eor; */ lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_ceor); lbmWrite(log, bp, lbmWRITE | lbmGC, cant_write); INCREMENT(lmStat.partial_page); } } /* * NAME: lmPostGC() * * FUNCTION: group commit post-processing * Processes transactions after their commit records have been written * to disk, redriving log I/O if necessary. * * RETURN: None * * NOTE: * This routine is called a interrupt time by lbmIODone */ static void lmPostGC(struct lbuf * bp) { unsigned long flags; struct jfs_log *log = bp->l_log; struct logpage *lp; struct tblock *tblk, *temp; //LOGGC_LOCK(log); spin_lock_irqsave(&log->gclock, flags); /* * current pageout of group commit completed. * * remove/wakeup transactions from commit queue who were * group committed with the current log page */ list_for_each_entry_safe(tblk, temp, &log->cqueue, cqueue) { if (!(tblk->flag & tblkGC_COMMIT)) break; /* if transaction was marked GC_COMMIT then * it has been shipped in the current pageout * and made it to disk - it is committed. */ if (bp->l_flag & lbmERROR) tblk->flag |= tblkGC_ERROR; /* remove it from the commit queue */ list_del(&tblk->cqueue); tblk->flag &= ~tblkGC_QUEUE; if (tblk == log->flush_tblk) { /* we can stop flushing the log now */ clear_bit(log_FLUSH, &log->flag); log->flush_tblk = NULL; } jfs_info("lmPostGC: tblk = 0x%p, flag = 0x%x", tblk, tblk->flag); if (!(tblk->xflag & COMMIT_FORCE)) /* * Hand tblk over to lazy commit thread */ txLazyUnlock(tblk); else { /* state transition: COMMIT -> COMMITTED */ tblk->flag |= tblkGC_COMMITTED; if (tblk->flag & tblkGC_READY) log->gcrtc--; LOGGC_WAKEUP(tblk); } /* was page full before pageout ? * (and this is the last tblk bound with the page) */ if (tblk->flag & tblkGC_FREE) lbmFree(bp); /* did page become full after pageout ? * (and this is the last tblk bound with the page) */ else if (tblk->flag & tblkGC_EOP) { /* finalize the page */ lp = (struct logpage *) bp->l_ldata; bp->l_ceor = bp->l_eor; lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_eor); jfs_info("lmPostGC: calling lbmWrite"); lbmWrite(log, bp, lbmWRITE | lbmRELEASE | lbmFREE, 1); } } /* are there any transactions who have entered lnGroupCommit() * (whose COMMITs are after that of the last log page written. * They are waiting for new group commit (above at (SLEEP 1)) * or lazy transactions are on a full (queued) log page, * select the latest ready transaction as new group leader and * wake her up to lead her group. */ if ((!list_empty(&log->cqueue)) && ((log->gcrtc > 0) || (tblk->bp->l_wqnext != NULL) || test_bit(log_FLUSH, &log->flag) || jfs_tlocks_low)) /* * Call lmGCwrite with new group leader */ lmGCwrite(log, 1); /* no transaction are ready yet (transactions are only just * queued (GC_QUEUE) and not entered for group commit yet). * the first transaction entering group commit * will elect herself as new group leader. */ else log->cflag &= ~logGC_PAGEOUT; //LOGGC_UNLOCK(log); spin_unlock_irqrestore(&log->gclock, flags); return; } /* * NAME: lmLogSync() * * FUNCTION: write log SYNCPT record for specified log * if new sync address is available * (normally the case if sync() is executed by back-ground * process). * calculate new value of i_nextsync which determines when * this code is called again. * * PARAMETERS: log - log structure * hard_sync - 1 to force all metadata to be written * * RETURN: 0 * * serialization: LOG_LOCK() held on entry/exit */ static int lmLogSync(struct jfs_log * log, int hard_sync) { int logsize; int written; /* written since last syncpt */ int free; /* free space left available */ int delta; /* additional delta to write normally */ int more; /* additional write granted */ struct lrd lrd; int lsn; struct logsyncblk *lp; unsigned long flags; /* push dirty metapages out to disk */ if (hard_sync) write_special_inodes(log, filemap_fdatawrite); else write_special_inodes(log, filemap_flush); /* * forward syncpt */ /* if last sync is same as last syncpt, * invoke sync point forward processing to update sync. */ if (log->sync == log->syncpt) { LOGSYNC_LOCK(log, flags); if (list_empty(&log->synclist)) log->sync = log->lsn; else { lp = list_entry(log->synclist.next, struct logsyncblk, synclist); log->sync = lp->lsn; } LOGSYNC_UNLOCK(log, flags); } /* if sync is different from last syncpt, * write a SYNCPT record with syncpt = sync. * reset syncpt = sync */ if (log->sync != log->syncpt) { lrd.logtid = 0; lrd.backchain = 0; lrd.type = cpu_to_le16(LOG_SYNCPT); lrd.length = 0; lrd.log.syncpt.sync = cpu_to_le32(log->sync); lsn = lmWriteRecord(log, NULL, &lrd, NULL); log->syncpt = log->sync; } else lsn = log->lsn; /* * setup next syncpt trigger (SWAG) */ logsize = log->logsize; logdiff(written, lsn, log); free = logsize - written; delta = LOGSYNC_DELTA(logsize); more = min(free / 2, delta); if (more < 2 * LOGPSIZE) { jfs_warn("\n ... Log Wrap ... Log Wrap ... Log Wrap ...\n"); /* * log wrapping * * option 1 - panic ? No.! * option 2 - shutdown file systems * associated with log ? * option 3 - extend log ? * option 4 - second chance * * mark log wrapped, and continue. * when all active transactions are completed, * mark log valid for recovery. * if crashed during invalid state, log state * implies invalid log, forcing fsck(). */ /* mark log state log wrap in log superblock */ /* log->state = LOGWRAP; */ /* reset sync point computation */ log->syncpt = log->sync = lsn; log->nextsync = delta; } else /* next syncpt trigger = written + more */ log->nextsync = written + more; /* if number of bytes written from last sync point is more * than 1/4 of the log size, stop new transactions from * starting until all current transactions are completed * by setting syncbarrier flag. */ if (!test_bit(log_SYNCBARRIER, &log->flag) && (written > LOGSYNC_BARRIER(logsize)) && log->active) { set_bit(log_SYNCBARRIER, &log->flag); jfs_info("log barrier on: lsn=0x%x syncpt=0x%x", lsn, log->syncpt); /* * We may have to initiate group commit */ jfs_flush_journal(log, 0); } return lsn; } /* * NAME: jfs_syncpt * * FUNCTION: write log SYNCPT record for specified log * * PARAMETERS: log - log structure * hard_sync - set to 1 to force metadata to be written */ void jfs_syncpt(struct jfs_log *log, int hard_sync) { LOG_LOCK(log); if (!test_bit(log_QUIESCE, &log->flag)) lmLogSync(log, hard_sync); LOG_UNLOCK(log); } /* * NAME: lmLogOpen() * * FUNCTION: open the log on first open; * insert filesystem in the active list of the log. * * PARAMETER: ipmnt - file system mount inode * iplog - log inode (out) * * RETURN: * * serialization: */ int lmLogOpen(struct super_block *sb) { int rc; struct file *bdev_file; struct jfs_log *log; struct jfs_sb_info *sbi = JFS_SBI(sb); if (sbi->flag & JFS_NOINTEGRITY) return open_dummy_log(sb); if (sbi->mntflag & JFS_INLINELOG) return open_inline_log(sb); mutex_lock(&jfs_log_mutex); list_for_each_entry(log, &jfs_external_logs, journal_list) { if (file_bdev(log->bdev_file)->bd_dev == sbi->logdev) { if (!uuid_equal(&log->uuid, &sbi->loguuid)) { jfs_warn("wrong uuid on JFS journal"); mutex_unlock(&jfs_log_mutex); return -EINVAL; } /* * add file system to log active file system list */ if ((rc = lmLogFileSystem(log, sbi, 1))) { mutex_unlock(&jfs_log_mutex); return rc; } goto journal_found; } } if (!(log = kzalloc(sizeof(struct jfs_log), GFP_KERNEL))) { mutex_unlock(&jfs_log_mutex); return -ENOMEM; } INIT_LIST_HEAD(&log->sb_list); init_waitqueue_head(&log->syncwait); /* * external log as separate logical volume * * file systems to log may have n-to-1 relationship; */ bdev_file = bdev_file_open_by_dev(sbi->logdev, BLK_OPEN_READ | BLK_OPEN_WRITE, log, NULL); if (IS_ERR(bdev_file)) { rc = PTR_ERR(bdev_file); goto free; } log->bdev_file = bdev_file; uuid_copy(&log->uuid, &sbi->loguuid); /* * initialize log: */ if ((rc = lmLogInit(log))) goto close; list_add(&log->journal_list, &jfs_external_logs); /* * add file system to log active file system list */ if ((rc = lmLogFileSystem(log, sbi, 1))) goto shutdown; journal_found: LOG_LOCK(log); list_add(&sbi->log_list, &log->sb_list); sbi->log = log; LOG_UNLOCK(log); mutex_unlock(&jfs_log_mutex); return 0; /* * unwind on error */ shutdown: /* unwind lbmLogInit() */ list_del(&log->journal_list); lbmLogShutdown(log); close: /* close external log device */ bdev_fput(bdev_file); free: /* free log descriptor */ mutex_unlock(&jfs_log_mutex); kfree(log); jfs_warn("lmLogOpen: exit(%d)", rc); return rc; } static int open_inline_log(struct super_block *sb) { struct jfs_log *log; int rc; if (!(log = kzalloc(sizeof(struct jfs_log), GFP_KERNEL))) return -ENOMEM; INIT_LIST_HEAD(&log->sb_list); init_waitqueue_head(&log->syncwait); set_bit(log_INLINELOG, &log->flag); log->bdev_file = sb->s_bdev_file; log->base = addressPXD(&JFS_SBI(sb)->logpxd); log->size = lengthPXD(&JFS_SBI(sb)->logpxd) >> (L2LOGPSIZE - sb->s_blocksize_bits); log->l2bsize = sb->s_blocksize_bits; ASSERT(L2LOGPSIZE >= sb->s_blocksize_bits); /* * initialize log. */ if ((rc = lmLogInit(log))) { kfree(log); jfs_warn("lmLogOpen: exit(%d)", rc); return rc; } list_add(&JFS_SBI(sb)->log_list, &log->sb_list); JFS_SBI(sb)->log = log; return rc; } static int open_dummy_log(struct super_block *sb) { int rc; mutex_lock(&jfs_log_mutex); if (!dummy_log) { dummy_log = kzalloc(sizeof(struct jfs_log), GFP_KERNEL); if (!dummy_log) { mutex_unlock(&jfs_log_mutex); return -ENOMEM; } INIT_LIST_HEAD(&dummy_log->sb_list); init_waitqueue_head(&dummy_log->syncwait); dummy_log->no_integrity = 1; /* Make up some stuff */ dummy_log->base = 0; dummy_log->size = 1024; rc = lmLogInit(dummy_log); if (rc) { kfree(dummy_log); dummy_log = NULL; mutex_unlock(&jfs_log_mutex); return rc; } } LOG_LOCK(dummy_log); list_add(&JFS_SBI(sb)->log_list, &dummy_log->sb_list); JFS_SBI(sb)->log = dummy_log; LOG_UNLOCK(dummy_log); mutex_unlock(&jfs_log_mutex); return 0; } /* * NAME: lmLogInit() * * FUNCTION: log initialization at first log open. * * logredo() (or logformat()) should have been run previously. * initialize the log from log superblock. * set the log state in the superblock to LOGMOUNT and * write SYNCPT log record. * * PARAMETER: log - log structure * * RETURN: 0 - if ok * -EINVAL - bad log magic number or superblock dirty * error returned from logwait() * * serialization: single first open thread */ int lmLogInit(struct jfs_log * log) { int rc = 0; struct lrd lrd; struct logsuper *logsuper; struct lbuf *bpsuper; struct lbuf *bp; struct logpage *lp; int lsn = 0; jfs_info("lmLogInit: log:0x%p", log); /* initialize the group commit serialization lock */ LOGGC_LOCK_INIT(log); /* allocate/initialize the log write serialization lock */ LOG_LOCK_INIT(log); LOGSYNC_LOCK_INIT(log); INIT_LIST_HEAD(&log->synclist); INIT_LIST_HEAD(&log->cqueue); log->flush_tblk = NULL; log->count = 0; /* * initialize log i/o */ if ((rc = lbmLogInit(log))) return rc; if (!test_bit(log_INLINELOG, &log->flag)) log->l2bsize = L2LOGPSIZE; /* check for disabled journaling to disk */ if (log->no_integrity) { /* * Journal pages will still be filled. When the time comes * to actually do the I/O, the write is not done, and the * endio routine is called directly. */ bp = lbmAllocate(log , 0); log->bp = bp; bp->l_pn = bp->l_eor = 0; } else { /* * validate log superblock */ if ((rc = lbmRead(log, 1, &bpsuper))) goto errout10; logsuper = (struct logsuper *) bpsuper->l_ldata; if (logsuper->magic != cpu_to_le32(LOGMAGIC)) { jfs_warn("*** Log Format Error ! ***"); rc = -EINVAL; goto errout20; } /* logredo() should have been run successfully. */ if (logsuper->state != cpu_to_le32(LOGREDONE)) { jfs_warn("*** Log Is Dirty ! ***"); rc = -EINVAL; goto errout20; } /* initialize log from log superblock */ if (test_bit(log_INLINELOG,&log->flag)) { if (log->size != le32_to_cpu(logsuper->size)) { rc = -EINVAL; goto errout20; } jfs_info("lmLogInit: inline log:0x%p base:0x%Lx size:0x%x", log, (unsigned long long)log->base, log->size); } else { if (!uuid_equal(&logsuper->uuid, &log->uuid)) { jfs_warn("wrong uuid on JFS log device"); rc = -EINVAL; goto errout20; } log->size = le32_to_cpu(logsuper->size); log->l2bsize = le32_to_cpu(logsuper->l2bsize); jfs_info("lmLogInit: external log:0x%p base:0x%Lx size:0x%x", log, (unsigned long long)log->base, log->size); } log->page = le32_to_cpu(logsuper->end) / LOGPSIZE; log->eor = le32_to_cpu(logsuper->end) - (LOGPSIZE * log->page); /* * initialize for log append write mode */ /* establish current/end-of-log page/buffer */ if ((rc = lbmRead(log, log->page, &bp))) goto errout20; lp = (struct logpage *) bp->l_ldata; jfs_info("lmLogInit: lsn:0x%x page:%d eor:%d:%d", le32_to_cpu(logsuper->end), log->page, log->eor, le16_to_cpu(lp->h.eor)); log->bp = bp; bp->l_pn = log->page; bp->l_eor = log->eor; /* if current page is full, move on to next page */ if (log->eor >= LOGPSIZE - LOGPTLRSIZE) lmNextPage(log); /* * initialize log syncpoint */ /* * write the first SYNCPT record with syncpoint = 0 * (i.e., log redo up to HERE !); * remove current page from lbm write queue at end of pageout * (to write log superblock update), but do not release to * freelist; */ lrd.logtid = 0; lrd.backchain = 0; lrd.type = cpu_to_le16(LOG_SYNCPT); lrd.length = 0; lrd.log.syncpt.sync = 0; lsn = lmWriteRecord(log, NULL, &lrd, NULL); bp = log->bp; bp->l_ceor = bp->l_eor; lp = (struct logpage *) bp->l_ldata; lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_eor); lbmWrite(log, bp, lbmWRITE | lbmSYNC, 0); if ((rc = lbmIOWait(bp, 0))) goto errout30; /* * update/write superblock */ logsuper->state = cpu_to_le32(LOGMOUNT); log->serial = le32_to_cpu(logsuper->serial) + 1; logsuper->serial = cpu_to_le32(log->serial); lbmDirectWrite(log, bpsuper, lbmWRITE | lbmRELEASE | lbmSYNC); if ((rc = lbmIOWait(bpsuper, lbmFREE))) goto errout30; } /* initialize logsync parameters */ log->logsize = (log->size - 2) << L2LOGPSIZE; log->lsn = lsn; log->syncpt = lsn; log->sync = log->syncpt; log->nextsync = LOGSYNC_DELTA(log->logsize); jfs_info("lmLogInit: lsn:0x%x syncpt:0x%x sync:0x%x", log->lsn, log->syncpt, log->sync); /* * initialize for lazy/group commit */ log->clsn = lsn; return 0; /* * unwind on error */ errout30: /* release log page */ log->wqueue = NULL; bp->l_wqnext = NULL; lbmFree(bp); errout20: /* release log superblock */ lbmFree(bpsuper); errout10: /* unwind lbmLogInit() */ lbmLogShutdown(log); jfs_warn("lmLogInit: exit(%d)", rc); return rc; } /* * NAME: lmLogClose() * * FUNCTION: remove file system <ipmnt> from active list of log <iplog> * and close it on last close. * * PARAMETER: sb - superblock * * RETURN: errors from subroutines * * serialization: */ int lmLogClose(struct super_block *sb) { struct jfs_sb_info *sbi = JFS_SBI(sb); struct jfs_log *log = sbi->log; struct file *bdev_file; int rc = 0; jfs_info("lmLogClose: log:0x%p", log); mutex_lock(&jfs_log_mutex); LOG_LOCK(log); list_del(&sbi->log_list); LOG_UNLOCK(log); sbi->log = NULL; /* * We need to make sure all of the "written" metapages * actually make it to disk */ sync_blockdev(sb->s_bdev); if (test_bit(log_INLINELOG, &log->flag)) { /* * in-line log in host file system */ rc = lmLogShutdown(log); kfree(log); goto out; } if (!log->no_integrity) lmLogFileSystem(log, sbi, 0); if (!list_empty(&log->sb_list)) goto out; /* * TODO: ensure that the dummy_log is in a state to allow * lbmLogShutdown to deallocate all the buffers and call * kfree against dummy_log. For now, leave dummy_log & its * buffers in memory, and resuse if another no-integrity mount * is requested. */ if (log->no_integrity) goto out; /* * external log as separate logical volume */ list_del(&log->journal_list); bdev_file = log->bdev_file; rc = lmLogShutdown(log); bdev_fput(bdev_file); kfree(log); out: mutex_unlock(&jfs_log_mutex); jfs_info("lmLogClose: exit(%d)", rc); return rc; } /* * NAME: jfs_flush_journal() * * FUNCTION: initiate write of any outstanding transactions to the journal * and optionally wait until they are all written to disk * * wait == 0 flush until latest txn is committed, don't wait * wait == 1 flush until latest txn is committed, wait * wait > 1 flush until all txn's are complete, wait */ void jfs_flush_journal(struct jfs_log *log, int wait) { int i; struct tblock *target = NULL; /* jfs_write_inode may call us during read-only mount */ if (!log) return; jfs_info("jfs_flush_journal: log:0x%p wait=%d", log, wait); LOGGC_LOCK(log); if (!list_empty(&log->cqueue)) { /* * This ensures that we will keep writing to the journal as long * as there are unwritten commit records */ target = list_entry(log->cqueue.prev, struct tblock, cqueue); if (test_bit(log_FLUSH, &log->flag)) { /* * We're already flushing. * if flush_tblk is NULL, we are flushing everything, * so leave it that way. Otherwise, update it to the * latest transaction */ if (log->flush_tblk) log->flush_tblk = target; } else { /* Only flush until latest transaction is committed */ log->flush_tblk = target; set_bit(log_FLUSH, &log->flag); /* * Initiate I/O on outstanding transactions */ if (!(log->cflag & logGC_PAGEOUT)) { log->cflag |= logGC_PAGEOUT; lmGCwrite(log, 0); } } } if ((wait > 1) || test_bit(log_SYNCBARRIER, &log->flag)) { /* Flush until all activity complete */ set_bit(log_FLUSH, &log->flag); log->flush_tblk = NULL; } if (wait && target && !(target->flag & tblkGC_COMMITTED)) { DECLARE_WAITQUEUE(__wait, current); add_wait_queue(&target->gcwait, &__wait); set_current_state(TASK_UNINTERRUPTIBLE); LOGGC_UNLOCK(log); schedule(); LOGGC_LOCK(log); remove_wait_queue(&target->gcwait, &__wait); } LOGGC_UNLOCK(log); if (wait < 2) return; write_special_inodes(log, filemap_fdatawrite); /* * If there was recent activity, we may need to wait * for the lazycommit thread to catch up */ if ((!list_empty(&log->cqueue)) || !list_empty(&log->synclist)) { for (i = 0; i < 200; i++) { /* Too much? */ msleep(250); write_special_inodes(log, filemap_fdatawrite); if (list_empty(&log->cqueue) && list_empty(&log->synclist)) break; } } assert(list_empty(&log->cqueue)); #ifdef CONFIG_JFS_DEBUG if (!list_empty(&log->synclist)) { struct logsyncblk *lp; printk(KERN_ERR "jfs_flush_journal: synclist not empty\n"); list_for_each_entry(lp, &log->synclist, synclist) { if (lp->xflag & COMMIT_PAGE) { struct metapage *mp = (struct metapage *)lp; print_hex_dump(KERN_ERR, "metapage: ", DUMP_PREFIX_ADDRESS, 16, 4, mp, sizeof(struct metapage), 0); print_hex_dump(KERN_ERR, "page: ", DUMP_PREFIX_ADDRESS, 16, sizeof(long), mp->folio, sizeof(struct page), 0); } else print_hex_dump(KERN_ERR, "tblock:", DUMP_PREFIX_ADDRESS, 16, 4, lp, sizeof(struct tblock), 0); } } #else WARN_ON(!list_empty(&log->synclist)); #endif clear_bit(log_FLUSH, &log->flag); } /* * NAME: lmLogShutdown() * * FUNCTION: log shutdown at last LogClose(). * * write log syncpt record. * update super block to set redone flag to 0. * * PARAMETER: log - log inode * * RETURN: 0 - success * * serialization: single last close thread */ int lmLogShutdown(struct jfs_log * log) { int rc; struct lrd lrd; int lsn; struct logsuper *logsuper; struct lbuf *bpsuper; struct lbuf *bp; struct logpage *lp; jfs_info("lmLogShutdown: log:0x%p", log); jfs_flush_journal(log, 2); /* * write the last SYNCPT record with syncpoint = 0 * (i.e., log redo up to HERE !) */ lrd.logtid = 0; lrd.backchain = 0; lrd.type = cpu_to_le16(LOG_SYNCPT); lrd.length = 0; lrd.log.syncpt.sync = 0; lsn = lmWriteRecord(log, NULL, &lrd, NULL); bp = log->bp; lp = (struct logpage *) bp->l_ldata; lp->h.eor = lp->t.eor = cpu_to_le16(bp->l_eor); lbmWrite(log, log->bp, lbmWRITE | lbmRELEASE | lbmSYNC, 0); lbmIOWait(log->bp, lbmFREE); log->bp = NULL; /* * synchronous update log superblock * mark log state as shutdown cleanly * (i.e., Log does not need to be replayed). */ if ((rc = lbmRead(log, 1, &bpsuper))) goto out; logsuper = (struct logsuper *) bpsuper->l_ldata; logsuper->state = cpu_to_le32(LOGREDONE); logsuper->end = cpu_to_le32(lsn); lbmDirectWrite(log, bpsuper, lbmWRITE | lbmRELEASE | lbmSYNC); rc = lbmIOWait(bpsuper, lbmFREE); jfs_info("lmLogShutdown: lsn:0x%x page:%d eor:%d", lsn, log->page, log->eor); out: /* * shutdown per log i/o */ lbmLogShutdown(log); if (rc) { jfs_warn("lmLogShutdown: exit(%d)", rc); } return rc; } /* * NAME: lmLogFileSystem() * * FUNCTION: insert (<activate> = true)/remove (<activate> = false) * file system into/from log active file system list. * * PARAMETE: log - pointer to logs inode. * fsdev - kdev_t of filesystem. * serial - pointer to returned log serial number * activate - insert/remove device from active list. * * RETURN: 0 - success * errors returned by vms_iowait(). */ static int lmLogFileSystem(struct jfs_log * log, struct jfs_sb_info *sbi, int activate) { int rc = 0; int i; struct logsuper *logsuper; struct lbuf *bpsuper; uuid_t *uuid = &sbi->uuid; /* * insert/remove file system device to log active file system list. */ if ((rc = lbmRead(log, 1, &bpsuper))) return rc; logsuper = (struct logsuper *) bpsuper->l_ldata; if (activate) { for (i = 0; i < MAX_ACTIVE; i++) if (uuid_is_null(&logsuper->active[i].uuid)) { uuid_copy(&logsuper->active[i].uuid, uuid); sbi->aggregate = i; break; } if (i == MAX_ACTIVE) { jfs_warn("Too many file systems sharing journal!"); lbmFree(bpsuper); return -EMFILE; /* Is there a better rc? */ } } else { for (i = 0; i < MAX_ACTIVE; i++) if (uuid_equal(&logsuper->active[i].uuid, uuid)) { uuid_copy(&logsuper->active[i].uuid, &uuid_null); break; } if (i == MAX_ACTIVE) { jfs_warn("Somebody stomped on the journal!"); lbmFree(bpsuper); return -EIO; } } /* * synchronous write log superblock: * * write sidestream bypassing write queue: * at file system mount, log super block is updated for * activation of the file system before any log record * (MOUNT record) of the file system, and at file system * unmount, all meta data for the file system has been * flushed before log super block is updated for deactivation * of the file system. */ lbmDirectWrite(log, bpsuper, lbmWRITE | lbmRELEASE | lbmSYNC); rc = lbmIOWait(bpsuper, lbmFREE); return rc; } /* * log buffer manager (lbm) * ------------------------ * * special purpose buffer manager supporting log i/o requirements. * * per log write queue: * log pageout occurs in serial order by fifo write queue and * restricting to a single i/o in pregress at any one time. * a circular singly-linked list * (log->wrqueue points to the tail, and buffers are linked via * bp->wrqueue field), and * maintains log page in pageout ot waiting for pageout in serial pageout. */ /* * lbmLogInit() * * initialize per log I/O setup at lmLogInit() */ static int lbmLogInit(struct jfs_log * log) { /* log inode */ int i; struct lbuf *lbuf; jfs_info("lbmLogInit: log:0x%p", log); /* initialize current buffer cursor */ log->bp = NULL; /* initialize log device write queue */ log->wqueue = NULL; /* * Each log has its own buffer pages allocated to it. These are * not managed by the page cache. This ensures that a transaction * writing to the log does not block trying to allocate a page from * the page cache (for the log). This would be bad, since page * allocation waits on the kswapd thread that may be committing inodes * which would cause log activity. Was that clear? I'm trying to * avoid deadlock here. */ init_waitqueue_head(&log->free_wait); log->lbuf_free = NULL; for (i = 0; i < LOGPAGES;) { char *buffer; uint offset; struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) goto error; buffer = page_address(page); for (offset = 0; offset < PAGE_SIZE; offset += LOGPSIZE) { lbuf = kmalloc(sizeof(struct lbuf), GFP_KERNEL); if (lbuf == NULL) { if (offset == 0) __free_page(page); goto error; } if (offset) /* we already have one reference */ get_page(page); lbuf->l_offset = offset; lbuf->l_ldata = buffer + offset; lbuf->l_page = page; lbuf->l_log = log; init_waitqueue_head(&lbuf->l_ioevent); lbuf->l_freelist = log->lbuf_free; log->lbuf_free = lbuf; i++; } } return (0); error: lbmLogShutdown(log); return -ENOMEM; } /* * lbmLogShutdown() * * finalize per log I/O setup at lmLogShutdown() */ static void lbmLogShutdown(struct jfs_log * log) { struct lbuf *lbuf; jfs_info("lbmLogShutdown: log:0x%p", log); lbuf = log->lbuf_free; while (lbuf) { struct lbuf *next = lbuf->l_freelist; __free_page(lbuf->l_page); kfree(lbuf); lbuf = next; } } /* * lbmAllocate() * * allocate an empty log buffer */ static struct lbuf *lbmAllocate(struct jfs_log * log, int pn) { struct lbuf *bp; unsigned long flags; /* * recycle from log buffer freelist if any */ LCACHE_LOCK(flags); LCACHE_SLEEP_COND(log->free_wait, (bp = log->lbuf_free), flags); log->lbuf_free = bp->l_freelist; LCACHE_UNLOCK(flags); bp->l_flag = 0; bp->l_wqnext = NULL; bp->l_freelist = NULL; bp->l_pn = pn; bp->l_blkno = log->base + (pn << (L2LOGPSIZE - log->l2bsize)); bp->l_ceor = 0; return bp; } /* * lbmFree() * * release a log buffer to freelist */ static void lbmFree(struct lbuf * bp) { unsigned long flags; LCACHE_LOCK(flags); lbmfree(bp); LCACHE_UNLOCK(flags); } static void lbmfree(struct lbuf * bp) { struct jfs_log *log = bp->l_log; assert(bp->l_wqnext == NULL); /* * return the buffer to head of freelist */ bp->l_freelist = log->lbuf_free; log->lbuf_free = bp; wake_up(&log->free_wait); return; } /* * NAME: lbmRedrive * * FUNCTION: add a log buffer to the log redrive list * * PARAMETER: * bp - log buffer * * NOTES: * Takes log_redrive_lock. */ static inline void lbmRedrive(struct lbuf *bp) { unsigned long flags; spin_lock_irqsave(&log_redrive_lock, flags); bp->l_redrive_next = log_redrive_list; log_redrive_list = bp; spin_unlock_irqrestore(&log_redrive_lock, flags); wake_up_process(jfsIOthread); } /* * lbmRead() */ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp) { struct bio *bio; struct lbuf *bp; /* * allocate a log buffer */ *bpp = bp = lbmAllocate(log, pn); jfs_info("lbmRead: bp:0x%p pn:0x%x", bp, pn); bp->l_flag |= lbmREAD; bio = bio_alloc(file_bdev(log->bdev_file), 1, REQ_OP_READ, GFP_NOFS); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); bio->bi_end_io = lbmIODone; bio->bi_private = bp; /*check if journaling to disk has been disabled*/ if (log->no_integrity) { bio->bi_iter.bi_size = 0; lbmIODone(bio); } else { submit_bio(bio); } wait_event(bp->l_ioevent, (bp->l_flag != lbmREAD)); return 0; } /* * lbmWrite() * * buffer at head of pageout queue stays after completion of * partial-page pageout and redriven by explicit initiation of * pageout by caller until full-page pageout is completed and * released. * * device driver i/o done redrives pageout of new buffer at * head of pageout queue when current buffer at head of pageout * queue is released at the completion of its full-page pageout. * * LOGGC_LOCK() serializes lbmWrite() by lmNextPage() and lmGroupCommit(). * LCACHE_LOCK() serializes xflag between lbmWrite() and lbmIODone() */ static void lbmWrite(struct jfs_log * log, struct lbuf * bp, int flag, int cant_block) { struct lbuf *tail; unsigned long flags; jfs_info("lbmWrite: bp:0x%p flag:0x%x pn:0x%x", bp, flag, bp->l_pn); /* map the logical block address to physical block address */ bp->l_blkno = log->base + (bp->l_pn << (L2LOGPSIZE - log->l2bsize)); LCACHE_LOCK(flags); /* disable+lock */ /* * initialize buffer for device driver */ bp->l_flag = flag; /* * insert bp at tail of write queue associated with log * * (request is either for bp already/currently at head of queue * or new bp to be inserted at tail) */ tail = log->wqueue; /* is buffer not already on write queue ? */ if (bp->l_wqnext == NULL) { /* insert at tail of wqueue */ if (tail == NULL) { log->wqueue = bp; bp->l_wqnext = bp; } else { log->wqueue = bp; bp->l_wqnext = tail->l_wqnext; tail->l_wqnext = bp; } tail = bp; } /* is buffer at head of wqueue and for write ? */ if ((bp != tail->l_wqnext) || !(flag & lbmWRITE)) { LCACHE_UNLOCK(flags); /* unlock+enable */ return; } LCACHE_UNLOCK(flags); /* unlock+enable */ if (cant_block) lbmRedrive(bp); else if (flag & lbmSYNC) lbmStartIO(bp); else { LOGGC_UNLOCK(log); lbmStartIO(bp); LOGGC_LOCK(log); } } /* * lbmDirectWrite() * * initiate pageout bypassing write queue for sidestream * (e.g., log superblock) write; */ static void lbmDirectWrite(struct jfs_log * log, struct lbuf * bp, int flag) { jfs_info("lbmDirectWrite: bp:0x%p flag:0x%x pn:0x%x", bp, flag, bp->l_pn); /* * initialize buffer for device driver */ bp->l_flag = flag | lbmDIRECT; /* map the logical block address to physical block address */ bp->l_blkno = log->base + (bp->l_pn << (L2LOGPSIZE - log->l2bsize)); /* * initiate pageout of the page */ lbmStartIO(bp); } /* * NAME: lbmStartIO() * * FUNCTION: Interface to DD strategy routine * * RETURN: none * * serialization: LCACHE_LOCK() is NOT held during log i/o; */ static void lbmStartIO(struct lbuf * bp) { struct bio *bio; struct jfs_log *log = bp->l_log; struct block_device *bdev = NULL; jfs_info("lbmStartIO"); if (!log->no_integrity) bdev = file_bdev(log->bdev_file); bio = bio_alloc(bdev, 1, REQ_OP_WRITE | REQ_SYNC, GFP_NOFS); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); bio->bi_end_io = lbmIODone; bio->bi_private = bp; /* check if journaling to disk has been disabled */ if (log->no_integrity) { bio->bi_iter.bi_size = 0; lbmIODone(bio); } else { submit_bio(bio); INCREMENT(lmStat.submitted); } } /* * lbmIOWait() */ static int lbmIOWait(struct lbuf * bp, int flag) { unsigned long flags; int rc = 0; jfs_info("lbmIOWait1: bp:0x%p flag:0x%x:0x%x", bp, bp->l_flag, flag); LCACHE_LOCK(flags); /* disable+lock */ LCACHE_SLEEP_COND(bp->l_ioevent, (bp->l_flag & lbmDONE), flags); rc = (bp->l_flag & lbmERROR) ? -EIO : 0; if (flag & lbmFREE) lbmfree(bp); LCACHE_UNLOCK(flags); /* unlock+enable */ jfs_info("lbmIOWait2: bp:0x%p flag:0x%x:0x%x", bp, bp->l_flag, flag); return rc; } /* * lbmIODone() * * executed at INTIODONE level */ static void lbmIODone(struct bio *bio) { struct lbuf *bp = bio->bi_private; struct lbuf *nextbp, *tail; struct jfs_log *log; unsigned long flags; /* * get back jfs buffer bound to the i/o buffer */ jfs_info("lbmIODone: bp:0x%p flag:0x%x", bp, bp->l_flag); LCACHE_LOCK(flags); /* disable+lock */ bp->l_flag |= lbmDONE; if (bio->bi_status) { bp->l_flag |= lbmERROR; jfs_err("lbmIODone: I/O error in JFS log"); } bio_put(bio); /* * pagein completion */ if (bp->l_flag & lbmREAD) { bp->l_flag &= ~lbmREAD; LCACHE_UNLOCK(flags); /* unlock+enable */ /* wakeup I/O initiator */ LCACHE_WAKEUP(&bp->l_ioevent); return; } /* * pageout completion * * the bp at the head of write queue has completed pageout. * * if single-commit/full-page pageout, remove the current buffer * from head of pageout queue, and redrive pageout with * the new buffer at head of pageout queue; * otherwise, the partial-page pageout buffer stays at * the head of pageout queue to be redriven for pageout * by lmGroupCommit() until full-page pageout is completed. */ bp->l_flag &= ~lbmWRITE; INCREMENT(lmStat.pagedone); /* update committed lsn */ log = bp->l_log; log->clsn = (bp->l_pn << L2LOGPSIZE) + bp->l_ceor; if (bp->l_flag & lbmDIRECT) { LCACHE_WAKEUP(&bp->l_ioevent); LCACHE_UNLOCK(flags); return; } tail = log->wqueue; /* single element queue */ if (bp == tail) { /* remove head buffer of full-page pageout * from log device write queue */ if (bp->l_flag & lbmRELEASE) { log->wqueue = NULL; bp->l_wqnext = NULL; } } /* multi element queue */ else { /* remove head buffer of full-page pageout * from log device write queue */ if (bp->l_flag & lbmRELEASE) { nextbp = tail->l_wqnext = bp->l_wqnext; bp->l_wqnext = NULL; /* * redrive pageout of next page at head of write queue: * redrive next page without any bound tblk * (i.e., page w/o any COMMIT records), or * first page of new group commit which has been * queued after current page (subsequent pageout * is performed synchronously, except page without * any COMMITs) by lmGroupCommit() as indicated * by lbmWRITE flag; */ if (nextbp->l_flag & lbmWRITE) { /* * We can't do the I/O at interrupt time. * The jfsIO thread can do it */ lbmRedrive(nextbp); } } } /* * synchronous pageout: * * buffer has not necessarily been removed from write queue * (e.g., synchronous write of partial-page with COMMIT): * leave buffer for i/o initiator to dispose */ if (bp->l_flag & lbmSYNC) { LCACHE_UNLOCK(flags); /* unlock+enable */ /* wakeup I/O initiator */ LCACHE_WAKEUP(&bp->l_ioevent); } /* * Group Commit pageout: */ else if (bp->l_flag & lbmGC) { LCACHE_UNLOCK(flags); lmPostGC(bp); } /* * asynchronous pageout: * * buffer must have been removed from write queue: * insert buffer at head of freelist where it can be recycled */ else { assert(bp->l_flag & lbmRELEASE); assert(bp->l_flag & lbmFREE); lbmfree(bp); LCACHE_UNLOCK(flags); /* unlock+enable */ } } int jfsIOWait(void *arg) { struct lbuf *bp; do { spin_lock_irq(&log_redrive_lock); while ((bp = log_redrive_list)) { log_redrive_list = bp->l_redrive_next; bp->l_redrive_next = NULL; spin_unlock_irq(&log_redrive_lock); lbmStartIO(bp); spin_lock_irq(&log_redrive_lock); } if (freezing(current)) { spin_unlock_irq(&log_redrive_lock); try_to_freeze(); } else { set_current_state(TASK_INTERRUPTIBLE); spin_unlock_irq(&log_redrive_lock); schedule(); } } while (!kthread_should_stop()); jfs_info("jfsIOWait being killed!"); return 0; } /* * NAME: lmLogFormat()/jfs_logform() * * FUNCTION: format file system log * * PARAMETERS: * log - volume log * logAddress - start address of log space in FS block * logSize - length of log space in FS block; * * RETURN: 0 - success * -EIO - i/o error * * XXX: We're synchronously writing one page at a time. This needs to * be improved by writing multiple pages at once. */ int lmLogFormat(struct jfs_log *log, s64 logAddress, int logSize) { int rc = -EIO; struct jfs_sb_info *sbi; struct logsuper *logsuper; struct logpage *lp; int lspn; /* log sequence page number */ struct lrd *lrd_ptr; int npages = 0; struct lbuf *bp; jfs_info("lmLogFormat: logAddress:%Ld logSize:%d", (long long)logAddress, logSize); sbi = list_entry(log->sb_list.next, struct jfs_sb_info, log_list); /* allocate a log buffer */ bp = lbmAllocate(log, 1); npages = logSize >> sbi->l2nbperpage; /* * log space: * * page 0 - reserved; * page 1 - log superblock; * page 2 - log data page: A SYNC log record is written * into this page at logform time; * pages 3-N - log data page: set to empty log data pages; */ /* * init log superblock: log page 1 */ logsuper = (struct logsuper *) bp->l_ldata; logsuper->magic = cpu_to_le32(LOGMAGIC); logsuper->version = cpu_to_le32(LOGVERSION); logsuper->state = cpu_to_le32(LOGREDONE); logsuper->flag = cpu_to_le32(sbi->mntflag); /* ? */ logsuper->size = cpu_to_le32(npages); logsuper->bsize = cpu_to_le32(sbi->bsize); logsuper->l2bsize = cpu_to_le32(sbi->l2bsize); logsuper->end = cpu_to_le32(2 * LOGPSIZE + LOGPHDRSIZE + LOGRDSIZE); bp->l_flag = lbmWRITE | lbmSYNC | lbmDIRECT; bp->l_blkno = logAddress + sbi->nbperpage; lbmStartIO(bp); if ((rc = lbmIOWait(bp, 0))) goto exit; /* * init pages 2 to npages-1 as log data pages: * * log page sequence number (lpsn) initialization: * * pn: 0 1 2 3 n-1 * +-----+-----+=====+=====+===.....===+=====+ * lspn: N-1 0 1 N-2 * <--- N page circular file ----> * * the N (= npages-2) data pages of the log is maintained as * a circular file for the log records; * lpsn grows by 1 monotonically as each log page is written * to the circular file of the log; * and setLogpage() will not reset the page number even if * the eor is equal to LOGPHDRSIZE. In order for binary search * still work in find log end process, we have to simulate the * log wrap situation at the log format time. * The 1st log page written will have the highest lpsn. Then * the succeeding log pages will have ascending order of * the lspn starting from 0, ... (N-2) */ lp = (struct logpage *) bp->l_ldata; /* * initialize 1st log page to be written: lpsn = N - 1, * write a SYNCPT log record is written to this page */ lp->h.page = lp->t.page = cpu_to_le32(npages - 3); lp->h.eor = lp->t.eor = cpu_to_le16(LOGPHDRSIZE + LOGRDSIZE); lrd_ptr = (struct lrd *) &lp->data; lrd_ptr->logtid = 0; lrd_ptr->backchain = 0; lrd_ptr->type = cpu_to_le16(LOG_SYNCPT); lrd_ptr->length = 0; lrd_ptr->log.syncpt.sync = 0; bp->l_blkno += sbi->nbperpage; bp->l_flag = lbmWRITE | lbmSYNC | lbmDIRECT; lbmStartIO(bp); if ((rc = lbmIOWait(bp, 0))) goto exit; /* * initialize succeeding log pages: lpsn = 0, 1, ..., (N-2) */ for (lspn = 0; lspn < npages - 3; lspn++) { lp->h.page = lp->t.page = cpu_to_le32(lspn); lp->h.eor = lp->t.eor = cpu_to_le16(LOGPHDRSIZE); bp->l_blkno += sbi->nbperpage; bp->l_flag = lbmWRITE | lbmSYNC | lbmDIRECT; lbmStartIO(bp); if ((rc = lbmIOWait(bp, 0))) goto exit; } rc = 0; exit: /* * finalize log */ /* release the buffer */ lbmFree(bp); return rc; } #ifdef CONFIG_JFS_STATISTICS int jfs_lmstats_proc_show(struct seq_file *m, void *v) { seq_printf(m, "JFS Logmgr stats\n" "================\n" "commits = %d\n" "writes submitted = %d\n" "writes completed = %d\n" "full pages submitted = %d\n" "partial pages submitted = %d\n", lmStat.commit, lmStat.submitted, lmStat.pagedone, lmStat.full_page, lmStat.partial_page); return 0; } #endif /* CONFIG_JFS_STATISTICS */ |
| 7 1 6 9 9 11 11 6 5 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Modified by Fred N. van Kempen, 01/29/93, to add line disciplines * which can be dynamically activated and de-activated by the line * discipline handling modules (like SLIP). */ #include <linux/bits.h> #include <linux/types.h> #include <linux/termios.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/tty.h> #include <linux/fcntl.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/bitops.h> #include <linux/mutex.h> #include <linux/compat.h> #include <linux/termios_internal.h> #include "tty.h" #include <asm/io.h> #include <linux/uaccess.h> #undef DEBUG /* * Internal flag options for termios setting behavior */ #define TERMIOS_FLUSH BIT(0) #define TERMIOS_WAIT BIT(1) #define TERMIOS_TERMIO BIT(2) #define TERMIOS_OLD BIT(3) /** * tty_chars_in_buffer - characters pending * @tty: terminal * * Returns: the number of bytes of data in the device private output queue. If * no private method is supplied there is assumed to be no queue on the device. */ unsigned int tty_chars_in_buffer(struct tty_struct *tty) { if (tty->ops->chars_in_buffer) return tty->ops->chars_in_buffer(tty); return 0; } EXPORT_SYMBOL(tty_chars_in_buffer); /** * tty_write_room - write queue space * @tty: terminal * * Returns: the number of bytes that can be queued to this device at the present * time. The result should be treated as a guarantee and the driver cannot * offer a value it later shrinks by more than the number of bytes written. If * no method is provided, 2K is always returned and data may be lost as there * will be no flow control. */ unsigned int tty_write_room(struct tty_struct *tty) { if (tty->ops->write_room) return tty->ops->write_room(tty); return 2048; } EXPORT_SYMBOL(tty_write_room); /** * tty_driver_flush_buffer - discard internal buffer * @tty: terminal * * Discard the internal output buffer for this device. If no method is provided, * then either the buffer cannot be hardware flushed or there is no buffer * driver side. */ void tty_driver_flush_buffer(struct tty_struct *tty) { if (tty->ops->flush_buffer) tty->ops->flush_buffer(tty); } EXPORT_SYMBOL(tty_driver_flush_buffer); /** * tty_unthrottle - flow control * @tty: terminal * * Indicate that a @tty may continue transmitting data down the stack. Takes * the &tty_struct->termios_rwsem to protect against parallel * throttle/unthrottle and also to ensure the driver can consistently reference * its own termios data at this point when implementing software flow control. * * Drivers should however remember that the stack can issue a throttle, then * change flow control method, then unthrottle. */ void tty_unthrottle(struct tty_struct *tty) { down_write(&tty->termios_rwsem); if (test_and_clear_bit(TTY_THROTTLED, &tty->flags) && tty->ops->unthrottle) tty->ops->unthrottle(tty); tty->flow_change = TTY_FLOW_NO_CHANGE; up_write(&tty->termios_rwsem); } EXPORT_SYMBOL(tty_unthrottle); /** * tty_throttle_safe - flow control * @tty: terminal * * Indicate that a @tty should stop transmitting data down the stack. * tty_throttle_safe() will only attempt throttle if @tty->flow_change is * %TTY_THROTTLE_SAFE. Prevents an accidental throttle due to race conditions * when throttling is conditional on factors evaluated prior to throttling. * * Returns: %true if @tty is throttled (or was already throttled) */ bool tty_throttle_safe(struct tty_struct *tty) { bool ret = true; mutex_lock(&tty->throttle_mutex); if (!tty_throttled(tty)) { if (tty->flow_change != TTY_THROTTLE_SAFE) ret = false; else { set_bit(TTY_THROTTLED, &tty->flags); if (tty->ops->throttle) tty->ops->throttle(tty); } } mutex_unlock(&tty->throttle_mutex); return ret; } /** * tty_unthrottle_safe - flow control * @tty: terminal * * Similar to tty_unthrottle() but will only attempt unthrottle if * @tty->flow_change is %TTY_UNTHROTTLE_SAFE. Prevents an accidental unthrottle * due to race conditions when unthrottling is conditional on factors evaluated * prior to unthrottling. * * Returns: %true if @tty is unthrottled (or was already unthrottled) */ bool tty_unthrottle_safe(struct tty_struct *tty) { bool ret = true; mutex_lock(&tty->throttle_mutex); if (tty_throttled(tty)) { if (tty->flow_change != TTY_UNTHROTTLE_SAFE) ret = false; else { clear_bit(TTY_THROTTLED, &tty->flags); if (tty->ops->unthrottle) tty->ops->unthrottle(tty); } } mutex_unlock(&tty->throttle_mutex); return ret; } /** * tty_wait_until_sent - wait for I/O to finish * @tty: tty we are waiting for * @timeout: how long we will wait * * Wait for characters pending in a tty driver to hit the wire, or for a * timeout to occur (eg due to flow control). * * Locking: none */ void tty_wait_until_sent(struct tty_struct *tty, long timeout) { if (!timeout) timeout = MAX_SCHEDULE_TIMEOUT; timeout = wait_event_interruptible_timeout(tty->write_wait, !tty_chars_in_buffer(tty), timeout); if (timeout <= 0) return; if (timeout == MAX_SCHEDULE_TIMEOUT) timeout = 0; if (tty->ops->wait_until_sent) tty->ops->wait_until_sent(tty, timeout); } EXPORT_SYMBOL(tty_wait_until_sent); /* * Termios Helper Methods */ static void unset_locked_termios(struct tty_struct *tty, const struct ktermios *old) { struct ktermios *termios = &tty->termios; struct ktermios *locked = &tty->termios_locked; int i; #define NOSET_MASK(x, y, z) (x = ((x) & ~(z)) | ((y) & (z))) NOSET_MASK(termios->c_iflag, old->c_iflag, locked->c_iflag); NOSET_MASK(termios->c_oflag, old->c_oflag, locked->c_oflag); NOSET_MASK(termios->c_cflag, old->c_cflag, locked->c_cflag); NOSET_MASK(termios->c_lflag, old->c_lflag, locked->c_lflag); termios->c_line = locked->c_line ? old->c_line : termios->c_line; for (i = 0; i < NCCS; i++) termios->c_cc[i] = locked->c_cc[i] ? old->c_cc[i] : termios->c_cc[i]; /* FIXME: What should we do for i/ospeed */ } /** * tty_termios_copy_hw - copy hardware settings * @new: new termios * @old: old termios * * Propagate the hardware specific terminal setting bits from the @old termios * structure to the @new one. This is used in cases where the hardware does not * support reconfiguration or as a helper in some cases where only minimal * reconfiguration is supported. */ void tty_termios_copy_hw(struct ktermios *new, const struct ktermios *old) { /* The bits a dumb device handles in software. Smart devices need to always provide a set_termios method */ new->c_cflag &= HUPCL | CREAD | CLOCAL; new->c_cflag |= old->c_cflag & ~(HUPCL | CREAD | CLOCAL); new->c_ispeed = old->c_ispeed; new->c_ospeed = old->c_ospeed; } EXPORT_SYMBOL(tty_termios_copy_hw); /** * tty_termios_hw_change - check for setting change * @a: termios * @b: termios to compare * * Check if any of the bits that affect a dumb device have changed between the * two termios structures, or a speed change is needed. * * Returns: %true if change is needed */ bool tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b) { if (a->c_ispeed != b->c_ispeed || a->c_ospeed != b->c_ospeed) return true; if ((a->c_cflag ^ b->c_cflag) & ~(HUPCL | CREAD | CLOCAL)) return true; return false; } EXPORT_SYMBOL(tty_termios_hw_change); /** * tty_get_char_size - get size of a character * @cflag: termios cflag value * * Returns: size (in bits) of a character depending on @cflag's %CSIZE setting */ unsigned char tty_get_char_size(unsigned int cflag) { switch (cflag & CSIZE) { case CS5: return 5; case CS6: return 6; case CS7: return 7; case CS8: default: return 8; } } EXPORT_SYMBOL_GPL(tty_get_char_size); /** * tty_get_frame_size - get size of a frame * @cflag: termios cflag value * * Get the size (in bits) of a frame depending on @cflag's %CSIZE, %CSTOPB, and * %PARENB setting. The result is a sum of character size, start and stop bits * -- one bit each -- second stop bit (if set), and parity bit (if set). * * Returns: size (in bits) of a frame depending on @cflag's setting. */ unsigned char tty_get_frame_size(unsigned int cflag) { unsigned char bits = 2 + tty_get_char_size(cflag); if (cflag & CSTOPB) bits++; if (cflag & PARENB) bits++; if (cflag & ADDRB) bits++; return bits; } EXPORT_SYMBOL_GPL(tty_get_frame_size); /** * tty_set_termios - update termios values * @tty: tty to update * @new_termios: desired new value * * Perform updates to the termios values set on this @tty. A master pty's * termios should never be set. * * Locking: &tty_struct->termios_rwsem */ int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) { struct ktermios old_termios; struct tty_ldisc *ld; WARN_ON(tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER); /* * Perform the actual termios internal changes under lock. */ /* FIXME: we need to decide on some locking/ordering semantics for the set_termios notification eventually */ down_write(&tty->termios_rwsem); old_termios = tty->termios; tty->termios = *new_termios; unset_locked_termios(tty, &old_termios); /* Reset any ADDRB changes, ADDRB is changed through ->rs485_config() */ tty->termios.c_cflag ^= (tty->termios.c_cflag ^ old_termios.c_cflag) & ADDRB; if (tty->ops->set_termios) tty->ops->set_termios(tty, &old_termios); else tty_termios_copy_hw(&tty->termios, &old_termios); ld = tty_ldisc_ref(tty); if (ld != NULL) { if (ld->ops->set_termios) ld->ops->set_termios(tty, &old_termios); tty_ldisc_deref(ld); } up_write(&tty->termios_rwsem); return 0; } EXPORT_SYMBOL_GPL(tty_set_termios); /* * Translate a "termio" structure into a "termios". Ugh. */ __weak int user_termio_to_kernel_termios(struct ktermios *termios, struct termio __user *termio) { struct termio v; if (copy_from_user(&v, termio, sizeof(struct termio))) return -EFAULT; termios->c_iflag = (0xffff0000 & termios->c_iflag) | v.c_iflag; termios->c_oflag = (0xffff0000 & termios->c_oflag) | v.c_oflag; termios->c_cflag = (0xffff0000 & termios->c_cflag) | v.c_cflag; termios->c_lflag = (0xffff0000 & termios->c_lflag) | v.c_lflag; termios->c_line = (0xffff0000 & termios->c_lflag) | v.c_line; memcpy(termios->c_cc, v.c_cc, NCC); return 0; } /* * Translate a "termios" structure into a "termio". Ugh. */ __weak int kernel_termios_to_user_termio(struct termio __user *termio, struct ktermios *termios) { struct termio v; memset(&v, 0, sizeof(struct termio)); v.c_iflag = termios->c_iflag; v.c_oflag = termios->c_oflag; v.c_cflag = termios->c_cflag; v.c_lflag = termios->c_lflag; v.c_line = termios->c_line; memcpy(v.c_cc, termios->c_cc, NCC); return copy_to_user(termio, &v, sizeof(struct termio)); } #ifdef TCGETS2 __weak int user_termios_to_kernel_termios(struct ktermios *k, struct termios2 __user *u) { return copy_from_user(k, u, sizeof(struct termios2)); } __weak int kernel_termios_to_user_termios(struct termios2 __user *u, struct ktermios *k) { return copy_to_user(u, k, sizeof(struct termios2)); } __weak int user_termios_to_kernel_termios_1(struct ktermios *k, struct termios __user *u) { return copy_from_user(k, u, sizeof(struct termios)); } __weak int kernel_termios_to_user_termios_1(struct termios __user *u, struct ktermios *k) { return copy_to_user(u, k, sizeof(struct termios)); } #else __weak int user_termios_to_kernel_termios(struct ktermios *k, struct termios __user *u) { return copy_from_user(k, u, sizeof(struct termios)); } __weak int kernel_termios_to_user_termios(struct termios __user *u, struct ktermios *k) { return copy_to_user(u, k, sizeof(struct termios)); } #endif /* TCGETS2 */ /** * set_termios - set termios values for a tty * @tty: terminal device * @arg: user data * @opt: option information * * Helper function to prepare termios data and run necessary other functions * before using tty_set_termios() to do the actual changes. * * Locking: called functions take &tty_struct->ldisc_sem and * &tty_struct->termios_rwsem locks * * Returns: 0 on success, an error otherwise */ static int set_termios(struct tty_struct *tty, void __user *arg, int opt) { struct ktermios tmp_termios; struct tty_ldisc *ld; int retval = tty_check_change(tty); if (retval) return retval; down_read(&tty->termios_rwsem); tmp_termios = tty->termios; up_read(&tty->termios_rwsem); if (opt & TERMIOS_TERMIO) { if (user_termio_to_kernel_termios(&tmp_termios, (struct termio __user *)arg)) return -EFAULT; #ifdef TCGETS2 } else if (opt & TERMIOS_OLD) { if (user_termios_to_kernel_termios_1(&tmp_termios, (struct termios __user *)arg)) return -EFAULT; } else { if (user_termios_to_kernel_termios(&tmp_termios, (struct termios2 __user *)arg)) return -EFAULT; } #else } else if (user_termios_to_kernel_termios(&tmp_termios, (struct termios __user *)arg)) return -EFAULT; #endif /* If old style Bfoo values are used then load c_ispeed/c_ospeed * with the real speed so its unconditionally usable */ tmp_termios.c_ispeed = tty_termios_input_baud_rate(&tmp_termios); tmp_termios.c_ospeed = tty_termios_baud_rate(&tmp_termios); if (opt & (TERMIOS_FLUSH|TERMIOS_WAIT)) { retry_write_wait: retval = wait_event_interruptible(tty->write_wait, !tty_chars_in_buffer(tty)); if (retval < 0) return retval; if (tty_write_lock(tty, false) < 0) goto retry_write_wait; /* Racing writer? */ if (tty_chars_in_buffer(tty)) { tty_write_unlock(tty); goto retry_write_wait; } ld = tty_ldisc_ref(tty); if (ld != NULL) { if ((opt & TERMIOS_FLUSH) && ld->ops->flush_buffer) ld->ops->flush_buffer(tty); tty_ldisc_deref(ld); } if ((opt & TERMIOS_WAIT) && tty->ops->wait_until_sent) { tty->ops->wait_until_sent(tty, 0); if (signal_pending(current)) { tty_write_unlock(tty); return -ERESTARTSYS; } } tty_set_termios(tty, &tmp_termios); tty_write_unlock(tty); } else { tty_set_termios(tty, &tmp_termios); } /* FIXME: Arguably if tmp_termios == tty->termios AND the actual requested termios was not tmp_termios then we may want to return an error as no user requested change has succeeded */ return 0; } static void copy_termios(struct tty_struct *tty, struct ktermios *kterm) { down_read(&tty->termios_rwsem); *kterm = tty->termios; up_read(&tty->termios_rwsem); } static void copy_termios_locked(struct tty_struct *tty, struct ktermios *kterm) { down_read(&tty->termios_rwsem); *kterm = tty->termios_locked; up_read(&tty->termios_rwsem); } static int get_termio(struct tty_struct *tty, struct termio __user *termio) { struct ktermios kterm; copy_termios(tty, &kterm); if (kernel_termios_to_user_termio(termio, &kterm)) return -EFAULT; return 0; } #ifdef TIOCGETP /* * These are deprecated, but there is limited support.. * * The "sg_flags" translation is a joke.. */ static int get_sgflags(struct tty_struct *tty) { int flags = 0; if (!L_ICANON(tty)) { if (L_ISIG(tty)) flags |= 0x02; /* cbreak */ else flags |= 0x20; /* raw */ } if (L_ECHO(tty)) flags |= 0x08; /* echo */ if (O_OPOST(tty)) if (O_ONLCR(tty)) flags |= 0x10; /* crmod */ return flags; } static int get_sgttyb(struct tty_struct *tty, struct sgttyb __user *sgttyb) { struct sgttyb tmp; down_read(&tty->termios_rwsem); tmp.sg_ispeed = tty->termios.c_ispeed; tmp.sg_ospeed = tty->termios.c_ospeed; tmp.sg_erase = tty->termios.c_cc[VERASE]; tmp.sg_kill = tty->termios.c_cc[VKILL]; tmp.sg_flags = get_sgflags(tty); up_read(&tty->termios_rwsem); return copy_to_user(sgttyb, &tmp, sizeof(tmp)) ? -EFAULT : 0; } static void set_sgflags(struct ktermios *termios, int flags) { termios->c_iflag = ICRNL | IXON; termios->c_oflag = 0; termios->c_lflag = ISIG | ICANON; if (flags & 0x02) { /* cbreak */ termios->c_iflag = 0; termios->c_lflag &= ~ICANON; } if (flags & 0x08) { /* echo */ termios->c_lflag |= ECHO | ECHOE | ECHOK | ECHOCTL | ECHOKE | IEXTEN; } if (flags & 0x10) { /* crmod */ termios->c_oflag |= OPOST | ONLCR; } if (flags & 0x20) { /* raw */ termios->c_iflag = 0; termios->c_lflag &= ~(ISIG | ICANON); } if (!(termios->c_lflag & ICANON)) { termios->c_cc[VMIN] = 1; termios->c_cc[VTIME] = 0; } } /** * set_sgttyb - set legacy terminal values * @tty: tty structure * @sgttyb: pointer to old style terminal structure * * Updates a terminal from the legacy BSD style terminal information structure. * * Locking: &tty_struct->termios_rwsem * * Returns: 0 on success, an error otherwise */ static int set_sgttyb(struct tty_struct *tty, struct sgttyb __user *sgttyb) { int retval; struct sgttyb tmp; struct ktermios termios; retval = tty_check_change(tty); if (retval) return retval; if (copy_from_user(&tmp, sgttyb, sizeof(tmp))) return -EFAULT; down_write(&tty->termios_rwsem); termios = tty->termios; termios.c_cc[VERASE] = tmp.sg_erase; termios.c_cc[VKILL] = tmp.sg_kill; set_sgflags(&termios, tmp.sg_flags); /* Try and encode into Bfoo format */ tty_termios_encode_baud_rate(&termios, termios.c_ispeed, termios.c_ospeed); up_write(&tty->termios_rwsem); tty_set_termios(tty, &termios); return 0; } #endif #ifdef TIOCGETC static int get_tchars(struct tty_struct *tty, struct tchars __user *tchars) { struct tchars tmp; down_read(&tty->termios_rwsem); tmp.t_intrc = tty->termios.c_cc[VINTR]; tmp.t_quitc = tty->termios.c_cc[VQUIT]; tmp.t_startc = tty->termios.c_cc[VSTART]; tmp.t_stopc = tty->termios.c_cc[VSTOP]; tmp.t_eofc = tty->termios.c_cc[VEOF]; tmp.t_brkc = tty->termios.c_cc[VEOL2]; /* what is brkc anyway? */ up_read(&tty->termios_rwsem); return copy_to_user(tchars, &tmp, sizeof(tmp)) ? -EFAULT : 0; } static int set_tchars(struct tty_struct *tty, struct tchars __user *tchars) { struct tchars tmp; if (copy_from_user(&tmp, tchars, sizeof(tmp))) return -EFAULT; down_write(&tty->termios_rwsem); tty->termios.c_cc[VINTR] = tmp.t_intrc; tty->termios.c_cc[VQUIT] = tmp.t_quitc; tty->termios.c_cc[VSTART] = tmp.t_startc; tty->termios.c_cc[VSTOP] = tmp.t_stopc; tty->termios.c_cc[VEOF] = tmp.t_eofc; tty->termios.c_cc[VEOL2] = tmp.t_brkc; /* what is brkc anyway? */ up_write(&tty->termios_rwsem); return 0; } #endif #ifdef TIOCGLTC static int get_ltchars(struct tty_struct *tty, struct ltchars __user *ltchars) { struct ltchars tmp; down_read(&tty->termios_rwsem); tmp.t_suspc = tty->termios.c_cc[VSUSP]; /* what is dsuspc anyway? */ tmp.t_dsuspc = tty->termios.c_cc[VSUSP]; tmp.t_rprntc = tty->termios.c_cc[VREPRINT]; /* what is flushc anyway? */ tmp.t_flushc = tty->termios.c_cc[VEOL2]; tmp.t_werasc = tty->termios.c_cc[VWERASE]; tmp.t_lnextc = tty->termios.c_cc[VLNEXT]; up_read(&tty->termios_rwsem); return copy_to_user(ltchars, &tmp, sizeof(tmp)) ? -EFAULT : 0; } static int set_ltchars(struct tty_struct *tty, struct ltchars __user *ltchars) { struct ltchars tmp; if (copy_from_user(&tmp, ltchars, sizeof(tmp))) return -EFAULT; down_write(&tty->termios_rwsem); tty->termios.c_cc[VSUSP] = tmp.t_suspc; /* what is dsuspc anyway? */ tty->termios.c_cc[VEOL2] = tmp.t_dsuspc; tty->termios.c_cc[VREPRINT] = tmp.t_rprntc; /* what is flushc anyway? */ tty->termios.c_cc[VEOL2] = tmp.t_flushc; tty->termios.c_cc[VWERASE] = tmp.t_werasc; tty->termios.c_cc[VLNEXT] = tmp.t_lnextc; up_write(&tty->termios_rwsem); return 0; } #endif /** * tty_change_softcar - carrier change ioctl helper * @tty: tty to update * @enable: enable/disable %CLOCAL * * Perform a change to the %CLOCAL state and call into the driver layer to make * it visible. * * Locking: &tty_struct->termios_rwsem. * * Returns: 0 on success, an error otherwise */ static int tty_change_softcar(struct tty_struct *tty, bool enable) { int ret = 0; struct ktermios old; tcflag_t bit = enable ? CLOCAL : 0; down_write(&tty->termios_rwsem); old = tty->termios; tty->termios.c_cflag &= ~CLOCAL; tty->termios.c_cflag |= bit; if (tty->ops->set_termios) tty->ops->set_termios(tty, &old); if (C_CLOCAL(tty) != bit) ret = -EINVAL; up_write(&tty->termios_rwsem); return ret; } /** * tty_mode_ioctl - mode related ioctls * @tty: tty for the ioctl * @cmd: command * @arg: ioctl argument * * Perform non-line discipline specific mode control ioctls. This is designed * to be called by line disciplines to ensure they provide consistent mode * setting. */ int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct tty_struct *real_tty; void __user *p = (void __user *)arg; int ret = 0; struct ktermios kterm; if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER) real_tty = tty->link; else real_tty = tty; switch (cmd) { #ifdef TIOCGETP case TIOCGETP: return get_sgttyb(real_tty, (struct sgttyb __user *) arg); case TIOCSETP: case TIOCSETN: return set_sgttyb(real_tty, (struct sgttyb __user *) arg); #endif #ifdef TIOCGETC case TIOCGETC: return get_tchars(real_tty, p); case TIOCSETC: return set_tchars(real_tty, p); #endif #ifdef TIOCGLTC case TIOCGLTC: return get_ltchars(real_tty, p); case TIOCSLTC: return set_ltchars(real_tty, p); #endif case TCSETSF: return set_termios(real_tty, p, TERMIOS_FLUSH | TERMIOS_WAIT | TERMIOS_OLD); case TCSETSW: return set_termios(real_tty, p, TERMIOS_WAIT | TERMIOS_OLD); case TCSETS: return set_termios(real_tty, p, TERMIOS_OLD); #ifndef TCGETS2 case TCGETS: copy_termios(real_tty, &kterm); if (kernel_termios_to_user_termios((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; #else case TCGETS: copy_termios(real_tty, &kterm); if (kernel_termios_to_user_termios_1((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; case TCGETS2: copy_termios(real_tty, &kterm); if (kernel_termios_to_user_termios((struct termios2 __user *)arg, &kterm)) ret = -EFAULT; return ret; case TCSETSF2: return set_termios(real_tty, p, TERMIOS_FLUSH | TERMIOS_WAIT); case TCSETSW2: return set_termios(real_tty, p, TERMIOS_WAIT); case TCSETS2: return set_termios(real_tty, p, 0); #endif case TCGETA: return get_termio(real_tty, p); case TCSETAF: return set_termios(real_tty, p, TERMIOS_FLUSH | TERMIOS_WAIT | TERMIOS_TERMIO); case TCSETAW: return set_termios(real_tty, p, TERMIOS_WAIT | TERMIOS_TERMIO); case TCSETA: return set_termios(real_tty, p, TERMIOS_TERMIO); #ifndef TCGETS2 case TIOCGLCKTRMIOS: copy_termios_locked(real_tty, &kterm); if (kernel_termios_to_user_termios((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; case TIOCSLCKTRMIOS: if (!checkpoint_restore_ns_capable(&init_user_ns)) return -EPERM; copy_termios_locked(real_tty, &kterm); if (user_termios_to_kernel_termios(&kterm, (struct termios __user *) arg)) return -EFAULT; down_write(&real_tty->termios_rwsem); real_tty->termios_locked = kterm; up_write(&real_tty->termios_rwsem); return 0; #else case TIOCGLCKTRMIOS: copy_termios_locked(real_tty, &kterm); if (kernel_termios_to_user_termios_1((struct termios __user *)arg, &kterm)) ret = -EFAULT; return ret; case TIOCSLCKTRMIOS: if (!checkpoint_restore_ns_capable(&init_user_ns)) return -EPERM; copy_termios_locked(real_tty, &kterm); if (user_termios_to_kernel_termios_1(&kterm, (struct termios __user *) arg)) return -EFAULT; down_write(&real_tty->termios_rwsem); real_tty->termios_locked = kterm; up_write(&real_tty->termios_rwsem); return ret; #endif #ifdef TCGETX case TCGETX: case TCSETX: case TCSETXW: case TCSETXF: return -ENOTTY; #endif case TIOCGSOFTCAR: copy_termios(real_tty, &kterm); ret = put_user((kterm.c_cflag & CLOCAL) ? 1 : 0, (int __user *)arg); return ret; case TIOCSSOFTCAR: if (get_user(arg, (unsigned int __user *) arg)) return -EFAULT; return tty_change_softcar(real_tty, arg); default: return -ENOIOCTLCMD; } } EXPORT_SYMBOL_GPL(tty_mode_ioctl); /* Caller guarantees ldisc reference is held */ static int __tty_perform_flush(struct tty_struct *tty, unsigned long arg) { struct tty_ldisc *ld = tty->ldisc; switch (arg) { case TCIFLUSH: if (ld && ld->ops->flush_buffer) { ld->ops->flush_buffer(tty); tty_unthrottle(tty); } break; case TCIOFLUSH: if (ld && ld->ops->flush_buffer) { ld->ops->flush_buffer(tty); tty_unthrottle(tty); } fallthrough; case TCOFLUSH: tty_driver_flush_buffer(tty); break; default: return -EINVAL; } return 0; } int tty_perform_flush(struct tty_struct *tty, unsigned long arg) { struct tty_ldisc *ld; int retval = tty_check_change(tty); if (retval) return retval; ld = tty_ldisc_ref_wait(tty); retval = __tty_perform_flush(tty, arg); if (ld) tty_ldisc_deref(ld); return retval; } EXPORT_SYMBOL_GPL(tty_perform_flush); int n_tty_ioctl_helper(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { int retval; switch (cmd) { case TCXONC: retval = tty_check_change(tty); if (retval) return retval; switch (arg) { case TCOOFF: spin_lock_irq(&tty->flow.lock); if (!tty->flow.tco_stopped) { tty->flow.tco_stopped = true; __stop_tty(tty); } spin_unlock_irq(&tty->flow.lock); break; case TCOON: spin_lock_irq(&tty->flow.lock); if (tty->flow.tco_stopped) { tty->flow.tco_stopped = false; __start_tty(tty); } spin_unlock_irq(&tty->flow.lock); break; case TCIOFF: if (STOP_CHAR(tty) != __DISABLED_CHAR) retval = tty_send_xchar(tty, STOP_CHAR(tty)); break; case TCION: if (START_CHAR(tty) != __DISABLED_CHAR) retval = tty_send_xchar(tty, START_CHAR(tty)); break; default: return -EINVAL; } return retval; case TCFLSH: retval = tty_check_change(tty); if (retval) return retval; return __tty_perform_flush(tty, arg); default: /* Try the mode commands */ return tty_mode_ioctl(tty, cmd, arg); } } EXPORT_SYMBOL(n_tty_ioctl_helper); |
| 6 6 6 6 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 | // SPDX-License-Identifier: GPL-2.0-or-later /* AFS cell alias detection * * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/slab.h> #include <linux/sched.h> #include <linux/namei.h> #include <keys/rxrpc-type.h> #include "internal.h" /* * Sample a volume. */ static struct afs_volume *afs_sample_volume(struct afs_cell *cell, struct key *key, const char *name, unsigned int namelen) { struct afs_volume *volume; struct afs_fs_context fc = { .type = 0, /* Explicitly leave it to the VLDB */ .volnamesz = namelen, .volname = name, .net = cell->net, .cell = cell, .key = key, /* This might need to be something */ }; volume = afs_create_volume(&fc); _leave(" = %p", volume); return volume; } /* * Compare the address lists of a pair of fileservers. */ static int afs_compare_fs_alists(const struct afs_server *server_a, const struct afs_server *server_b) { const struct afs_addr_list *la, *lb; int a = 0, b = 0, addr_matches = 0; la = rcu_dereference(server_a->endpoint_state)->addresses; lb = rcu_dereference(server_b->endpoint_state)->addresses; while (a < la->nr_addrs && b < lb->nr_addrs) { unsigned long pa = (unsigned long)la->addrs[a].peer; unsigned long pb = (unsigned long)lb->addrs[b].peer; long diff = pa - pb; if (diff < 0) { a++; } else if (diff > 0) { b++; } else { addr_matches++; a++; b++; } } return addr_matches; } /* * Compare the fileserver lists of two volumes. The server lists are sorted in * order of ascending UUID. */ static int afs_compare_volume_slists(const struct afs_volume *vol_a, const struct afs_volume *vol_b) { const struct afs_server_list *la, *lb; int i, a = 0, b = 0, uuid_matches = 0, addr_matches = 0; la = rcu_dereference(vol_a->servers); lb = rcu_dereference(vol_b->servers); for (i = 0; i < AFS_MAXTYPES; i++) if (vol_a->vids[i] != vol_b->vids[i]) return 0; while (a < la->nr_servers && b < lb->nr_servers) { const struct afs_server *server_a = la->servers[a].server; const struct afs_server *server_b = lb->servers[b].server; int diff = memcmp(&server_a->uuid, &server_b->uuid, sizeof(uuid_t)); if (diff < 0) { a++; } else if (diff > 0) { b++; } else { uuid_matches++; addr_matches += afs_compare_fs_alists(server_a, server_b); a++; b++; } } _leave(" = %d [um %d]", addr_matches, uuid_matches); return addr_matches; } /* * Compare root.cell volumes. */ static int afs_compare_cell_roots(struct afs_cell *cell) { struct afs_cell *p; _enter(""); rcu_read_lock(); hlist_for_each_entry_rcu(p, &cell->net->proc_cells, proc_link) { if (p == cell || p->alias_of) continue; if (!p->root_volume) continue; /* Ignore cells that don't have a root.cell volume. */ if (afs_compare_volume_slists(cell->root_volume, p->root_volume) != 0) goto is_alias; } rcu_read_unlock(); _leave(" = 0"); return 0; is_alias: rcu_read_unlock(); cell->alias_of = afs_use_cell(p, afs_cell_trace_use_alias); return 1; } /* * Query the new cell for a volume from a cell we're already using. */ static int afs_query_for_alias_one(struct afs_cell *cell, struct key *key, struct afs_cell *p) { struct afs_volume *volume, *pvol = NULL; int ret; /* Arbitrarily pick a volume from the list. */ read_seqlock_excl(&p->volume_lock); if (!RB_EMPTY_ROOT(&p->volumes)) pvol = afs_get_volume(rb_entry(p->volumes.rb_node, struct afs_volume, cell_node), afs_volume_trace_get_query_alias); read_sequnlock_excl(&p->volume_lock); if (!pvol) return 0; _enter("%s:%s", cell->name, pvol->name); /* And see if it's in the new cell. */ volume = afs_sample_volume(cell, key, pvol->name, pvol->name_len); if (IS_ERR(volume)) { afs_put_volume(pvol, afs_volume_trace_put_query_alias); if (PTR_ERR(volume) != -ENOMEDIUM) return PTR_ERR(volume); /* That volume is not in the new cell, so not an alias */ return 0; } /* The new cell has a like-named volume also - compare volume ID, * server and address lists. */ ret = 0; if (pvol->vid == volume->vid) { rcu_read_lock(); if (afs_compare_volume_slists(volume, pvol)) ret = 1; rcu_read_unlock(); } afs_put_volume(volume, afs_volume_trace_put_query_alias); afs_put_volume(pvol, afs_volume_trace_put_query_alias); return ret; } /* * Query the new cell for volumes we know exist in cells we're already using. */ static int afs_query_for_alias(struct afs_cell *cell, struct key *key) { struct afs_cell *p; _enter("%s", cell->name); if (mutex_lock_interruptible(&cell->net->proc_cells_lock) < 0) return -ERESTARTSYS; hlist_for_each_entry(p, &cell->net->proc_cells, proc_link) { if (p == cell || p->alias_of) continue; if (RB_EMPTY_ROOT(&p->volumes)) continue; if (p->root_volume) continue; /* Ignore cells that have a root.cell volume. */ afs_use_cell(p, afs_cell_trace_use_check_alias); mutex_unlock(&cell->net->proc_cells_lock); if (afs_query_for_alias_one(cell, key, p) != 0) goto is_alias; if (mutex_lock_interruptible(&cell->net->proc_cells_lock) < 0) { afs_unuse_cell(p, afs_cell_trace_unuse_check_alias); return -ERESTARTSYS; } afs_unuse_cell(p, afs_cell_trace_unuse_check_alias); } mutex_unlock(&cell->net->proc_cells_lock); _leave(" = 0"); return 0; is_alias: cell->alias_of = p; /* Transfer our ref */ return 1; } /* * Look up a VLDB record for a volume. */ static char *afs_vl_get_cell_name(struct afs_cell *cell, struct key *key) { struct afs_vl_cursor vc; char *cell_name = ERR_PTR(-EDESTADDRREQ); bool skipped = false, not_skipped = false; int ret; if (!afs_begin_vlserver_operation(&vc, cell, key)) return ERR_PTR(-ERESTARTSYS); while (afs_select_vlserver(&vc)) { if (!test_bit(AFS_VLSERVER_FL_IS_YFS, &vc.server->flags)) { vc.call_error = -EOPNOTSUPP; skipped = true; continue; } not_skipped = true; cell_name = afs_yfsvl_get_cell_name(&vc); } ret = afs_end_vlserver_operation(&vc); if (skipped && !not_skipped) ret = -EOPNOTSUPP; return ret < 0 ? ERR_PTR(ret) : cell_name; } static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) { struct afs_cell *master; size_t name_len; char *cell_name; cell_name = afs_vl_get_cell_name(cell, key); if (IS_ERR(cell_name)) return PTR_ERR(cell_name); if (strcmp(cell_name, cell->name) == 0) { kfree(cell_name); return 0; } name_len = strlen(cell_name); if (!name_len || name_len > AFS_MAXCELLNAME) master = ERR_PTR(-EOPNOTSUPP); else master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, false, afs_cell_trace_use_lookup_canonical); kfree(cell_name); if (IS_ERR(master)) return PTR_ERR(master); cell->alias_of = master; /* Transfer our ref */ return 1; } static int afs_do_cell_detect_alias(struct afs_cell *cell, struct key *key) { struct afs_volume *root_volume; int ret; _enter("%s", cell->name); ret = yfs_check_canonical_cell_name(cell, key); if (ret != -EOPNOTSUPP) return ret; /* Try and get the root.cell volume for comparison with other cells */ root_volume = afs_sample_volume(cell, key, "root.cell", 9); if (!IS_ERR(root_volume)) { cell->root_volume = root_volume; return afs_compare_cell_roots(cell); } if (PTR_ERR(root_volume) != -ENOMEDIUM) return PTR_ERR(root_volume); /* Okay, this cell doesn't have an root.cell volume. We need to * locate some other random volume and use that to check. */ return afs_query_for_alias(cell, key); } /* * Check to see if a new cell is an alias of a cell we already have. At this * point we have the cell's volume server list. * * Returns 0 if we didn't detect an alias, 1 if we found an alias and an error * if we had problems gathering the data required. In the case the we did * detect an alias, cell->alias_of is set to point to the assumed master. */ int afs_cell_detect_alias(struct afs_cell *cell, struct key *key) { struct afs_net *net = cell->net; int ret; if (mutex_lock_interruptible(&net->cells_alias_lock) < 0) return -ERESTARTSYS; if (test_bit(AFS_CELL_FL_CHECK_ALIAS, &cell->flags)) { ret = afs_do_cell_detect_alias(cell, key); if (ret >= 0) clear_bit_unlock(AFS_CELL_FL_CHECK_ALIAS, &cell->flags); } else { ret = cell->alias_of ? 1 : 0; } mutex_unlock(&net->cells_alias_lock); if (ret == 1) pr_notice("kAFS: Cell %s is an alias of %s\n", cell->name, cell->alias_of->name); return ret; } |
| 73 21 84 | 1 2 3 4 5 6 7 8 9 10 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Unified UUID/GUID definition * * Copyright (C) 2009, 2016 Intel Corp. * Huang Ying <ying.huang@intel.com> */ #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/uuid.h> #include <linux/random.h> const guid_t guid_null; EXPORT_SYMBOL(guid_null); const uuid_t uuid_null; EXPORT_SYMBOL(uuid_null); const u8 guid_index[16] = {3,2,1,0,5,4,7,6,8,9,10,11,12,13,14,15}; const u8 uuid_index[16] = {0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15}; /** * generate_random_uuid - generate a random UUID * @uuid: where to put the generated UUID * * Random UUID interface * * Used to create a Boot ID or a filesystem UUID/GUID, but can be * useful for other kernel drivers. */ void generate_random_uuid(unsigned char uuid[16]) { get_random_bytes(uuid, 16); /* Set UUID version to 4 --- truly random generation */ uuid[6] = (uuid[6] & 0x0F) | 0x40; /* Set the UUID variant to DCE */ uuid[8] = (uuid[8] & 0x3F) | 0x80; } EXPORT_SYMBOL(generate_random_uuid); void generate_random_guid(unsigned char guid[16]) { get_random_bytes(guid, 16); /* Set GUID version to 4 --- truly random generation */ guid[7] = (guid[7] & 0x0F) | 0x40; /* Set the GUID variant to DCE */ guid[8] = (guid[8] & 0x3F) | 0x80; } EXPORT_SYMBOL(generate_random_guid); static void __uuid_gen_common(__u8 b[16]) { get_random_bytes(b, 16); /* reversion 0b10 */ b[8] = (b[8] & 0x3F) | 0x80; } void guid_gen(guid_t *lu) { __uuid_gen_common(lu->b); /* version 4 : random generation */ lu->b[7] = (lu->b[7] & 0x0F) | 0x40; } EXPORT_SYMBOL_GPL(guid_gen); void uuid_gen(uuid_t *bu) { __uuid_gen_common(bu->b); /* version 4 : random generation */ bu->b[6] = (bu->b[6] & 0x0F) | 0x40; } EXPORT_SYMBOL_GPL(uuid_gen); /** * uuid_is_valid - checks if a UUID string is valid * @uuid: UUID string to check * * Description: * It checks if the UUID string is following the format: * xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx * * where x is a hex digit. * * Return: true if input is valid UUID string. */ bool uuid_is_valid(const char *uuid) { unsigned int i; for (i = 0; i < UUID_STRING_LEN; i++) { if (i == 8 || i == 13 || i == 18 || i == 23) { if (uuid[i] != '-') return false; } else if (!isxdigit(uuid[i])) { return false; } } return true; } EXPORT_SYMBOL(uuid_is_valid); static int __uuid_parse(const char *uuid, __u8 b[16], const u8 ei[16]) { static const u8 si[16] = {0,2,4,6,9,11,14,16,19,21,24,26,28,30,32,34}; unsigned int i; if (!uuid_is_valid(uuid)) return -EINVAL; for (i = 0; i < 16; i++) { int hi = hex_to_bin(uuid[si[i] + 0]); int lo = hex_to_bin(uuid[si[i] + 1]); b[ei[i]] = (hi << 4) | lo; } return 0; } int guid_parse(const char *uuid, guid_t *u) { return __uuid_parse(uuid, u->b, guid_index); } EXPORT_SYMBOL(guid_parse); int uuid_parse(const char *uuid, uuid_t *u) { return __uuid_parse(uuid, u->b, uuid_index); } EXPORT_SYMBOL(uuid_parse); |
| 10 10 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * cn_proc.c - process events connector * * Copyright (C) Matt Helsley, IBM Corp. 2005 * Based on cn_fork.c by Guillaume Thouvenin <guillaume.thouvenin@bull.net> * Original copyright notice follows: * Copyright (C) 2005 BULL SA. */ #include <linux/kernel.h> #include <linux/ktime.h> #include <linux/init.h> #include <linux/connector.h> #include <linux/gfp.h> #include <linux/ptrace.h> #include <linux/atomic.h> #include <linux/pid_namespace.h> #include <linux/cn_proc.h> #include <linux/local_lock.h> /* * Size of a cn_msg followed by a proc_event structure. Since the * sizeof struct cn_msg is a multiple of 4 bytes, but not 8 bytes, we * add one 4-byte word to the size here, and then start the actual * cn_msg structure 4 bytes into the stack buffer. The result is that * the immediately following proc_event structure is aligned to 8 bytes. */ #define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event) + 4) /* See comment above; we test our assumption about sizeof struct cn_msg here. */ static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer) { BUILD_BUG_ON(sizeof(struct cn_msg) != 20); return (struct cn_msg *)(buffer + 4); } static atomic_t proc_event_num_listeners = ATOMIC_INIT(0); static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC }; /* local_event.count is used as the sequence number of the netlink message */ struct local_event { local_lock_t lock; __u32 count; }; static DEFINE_PER_CPU(struct local_event, local_event) = { .lock = INIT_LOCAL_LOCK(lock), }; static int cn_filter(struct sock *dsk, struct sk_buff *skb, void *data) { __u32 what, exit_code, *ptr; enum proc_cn_mcast_op mc_op; uintptr_t val; if (!dsk || !dsk->sk_user_data || !data) return 0; ptr = (__u32 *)data; what = *ptr++; exit_code = *ptr; val = ((struct proc_input *)(dsk->sk_user_data))->event_type; mc_op = ((struct proc_input *)(dsk->sk_user_data))->mcast_op; if (mc_op == PROC_CN_MCAST_IGNORE) return 1; if ((__u32)val == PROC_EVENT_ALL) return 0; /* * Drop packet if we have to report only non-zero exit status * (PROC_EVENT_NONZERO_EXIT) and exit status is 0 */ if (((__u32)val & PROC_EVENT_NONZERO_EXIT) && (what == PROC_EVENT_EXIT)) { if (exit_code) return 0; } if ((__u32)val & what) return 0; return 1; } static inline void send_msg(struct cn_msg *msg) { __u32 filter_data[2]; local_lock(&local_event.lock); msg->seq = __this_cpu_inc_return(local_event.count) - 1; ((struct proc_event *)msg->data)->cpu = smp_processor_id(); /* * local_lock() disables preemption during send to ensure the messages * are ordered according to their sequence numbers. * * If cn_netlink_send() fails, the data is not sent. */ filter_data[0] = ((struct proc_event *)msg->data)->what; if (filter_data[0] == PROC_EVENT_EXIT) { filter_data[1] = ((struct proc_event *)msg->data)->event_data.exit.exit_code; } else { filter_data[1] = 0; } cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, cn_filter, (void *)filter_data); local_unlock(&local_event.lock); } void proc_fork_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); struct task_struct *parent; if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_FORK; rcu_read_lock(); parent = rcu_dereference(task->real_parent); ev->event_data.fork.parent_pid = parent->pid; ev->event_data.fork.parent_tgid = parent->tgid; rcu_read_unlock(); ev->event_data.fork.child_pid = task->pid; ev->event_data.fork.child_tgid = task->tgid; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_exec_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXEC; ev->event_data.exec.process_pid = task->pid; ev->event_data.exec.process_tgid = task->tgid; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_id_connector(struct task_struct *task, int which_id) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); const struct cred *cred; if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->what = which_id; ev->event_data.id.process_pid = task->pid; ev->event_data.id.process_tgid = task->tgid; rcu_read_lock(); cred = __task_cred(task); if (which_id == PROC_EVENT_UID) { ev->event_data.id.r.ruid = from_kuid_munged(&init_user_ns, cred->uid); ev->event_data.id.e.euid = from_kuid_munged(&init_user_ns, cred->euid); } else if (which_id == PROC_EVENT_GID) { ev->event_data.id.r.rgid = from_kgid_munged(&init_user_ns, cred->gid); ev->event_data.id.e.egid = from_kgid_munged(&init_user_ns, cred->egid); } else { rcu_read_unlock(); return; } rcu_read_unlock(); ev->timestamp_ns = ktime_get_ns(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_sid_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_SID; ev->event_data.sid.process_pid = task->pid; ev->event_data.sid.process_tgid = task->tgid; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_ptrace_connector(struct task_struct *task, int ptrace_id) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_PTRACE; ev->event_data.ptrace.process_pid = task->pid; ev->event_data.ptrace.process_tgid = task->tgid; if (ptrace_id == PTRACE_ATTACH) { ev->event_data.ptrace.tracer_pid = current->pid; ev->event_data.ptrace.tracer_tgid = current->tgid; } else if (ptrace_id == PTRACE_DETACH) { ev->event_data.ptrace.tracer_pid = 0; ev->event_data.ptrace.tracer_tgid = 0; } else return; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_comm_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COMM; ev->event_data.comm.process_pid = task->pid; ev->event_data.comm.process_tgid = task->tgid; get_task_comm(ev->event_data.comm.comm, task); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_coredump_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; struct task_struct *parent; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COREDUMP; ev->event_data.coredump.process_pid = task->pid; ev->event_data.coredump.process_tgid = task->tgid; rcu_read_lock(); if (pid_alive(task)) { parent = rcu_dereference(task->real_parent); ev->event_data.coredump.parent_pid = parent->pid; ev->event_data.coredump.parent_tgid = parent->tgid; } rcu_read_unlock(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_exit_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; struct task_struct *parent; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXIT; ev->event_data.exit.process_pid = task->pid; ev->event_data.exit.process_tgid = task->tgid; ev->event_data.exit.exit_code = task->exit_code; ev->event_data.exit.exit_signal = task->exit_signal; rcu_read_lock(); if (pid_alive(task)) { parent = rcu_dereference(task->real_parent); ev->event_data.exit.parent_pid = parent->pid; ev->event_data.exit.parent_tgid = parent->tgid; } rcu_read_unlock(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } /* * Send an acknowledgement message to userspace * * Use 0 for success, EFOO otherwise. * Note: this is the negative of conventional kernel error * values because it's not being returned via syscall return * mechanisms. */ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); msg->seq = rcvd_seq; ev->timestamp_ns = ktime_get_ns(); ev->cpu = -1; ev->what = PROC_EVENT_NONE; ev->event_data.ack.err = err; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = rcvd_ack + 1; msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } /** * cn_proc_mcast_ctl * @msg: message sent from userspace via the connector * @nsp: NETLINK_CB of the client's socket buffer */ static void cn_proc_mcast_ctl(struct cn_msg *msg, struct netlink_skb_parms *nsp) { enum proc_cn_mcast_op mc_op = 0, prev_mc_op = 0; struct proc_input *pinput = NULL; enum proc_cn_event ev_type = 0; int err = 0, initial = 0; struct sock *sk = NULL; /* * Events are reported with respect to the initial pid * and user namespaces so ignore requestors from * other namespaces. */ if ((current_user_ns() != &init_user_ns) || !task_is_in_init_pid_ns(current)) return; if (msg->len == sizeof(*pinput)) { pinput = (struct proc_input *)msg->data; mc_op = pinput->mcast_op; ev_type = pinput->event_type; } else if (msg->len == sizeof(mc_op)) { mc_op = *((enum proc_cn_mcast_op *)msg->data); ev_type = PROC_EVENT_ALL; } else { return; } ev_type = valid_event((enum proc_cn_event)ev_type); if (ev_type == PROC_EVENT_NONE) ev_type = PROC_EVENT_ALL; if (nsp->sk) { sk = nsp->sk; if (sk->sk_user_data == NULL) { sk->sk_user_data = kzalloc(sizeof(struct proc_input), GFP_KERNEL); if (sk->sk_user_data == NULL) { err = ENOMEM; goto out; } initial = 1; } else { prev_mc_op = ((struct proc_input *)(sk->sk_user_data))->mcast_op; } ((struct proc_input *)(sk->sk_user_data))->event_type = ev_type; ((struct proc_input *)(sk->sk_user_data))->mcast_op = mc_op; } switch (mc_op) { case PROC_CN_MCAST_LISTEN: if (initial || (prev_mc_op != PROC_CN_MCAST_LISTEN)) atomic_inc(&proc_event_num_listeners); break; case PROC_CN_MCAST_IGNORE: if (!initial && (prev_mc_op != PROC_CN_MCAST_IGNORE)) atomic_dec(&proc_event_num_listeners); ((struct proc_input *)(sk->sk_user_data))->event_type = PROC_EVENT_NONE; break; default: err = EINVAL; break; } out: cn_proc_ack(err, msg->seq, msg->ack); } /* * cn_proc_init - initialization entry point * * Adds the connector callback to the connector driver. */ static int __init cn_proc_init(void) { int err = cn_add_callback(&cn_proc_event_id, "cn_proc", &cn_proc_mcast_ctl); if (err) { pr_warn("cn_proc failed to register\n"); return err; } return 0; } device_initcall(cn_proc_init); |
| 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * A virtual codec example device. * * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved. * * This is a virtual codec device driver for testing the codec framework. * It simulates a device that uses memory buffers for both source and * destination and encodes or decodes the data. */ #include <linux/module.h> #include <linux/delay.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/platform_device.h> #include <media/v4l2-mem2mem.h> #include <media/v4l2-device.h> #include <media/v4l2-ioctl.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-event.h> #include <media/videobuf2-vmalloc.h> #include "codec-v4l2-fwht.h" MODULE_DESCRIPTION("Virtual codec device"); MODULE_AUTHOR("Hans Verkuil <hansverk@cisco.com>"); MODULE_LICENSE("GPL v2"); static bool multiplanar; module_param(multiplanar, bool, 0444); MODULE_PARM_DESC(multiplanar, " use multi-planar API instead of single-planar API"); static unsigned int debug; module_param(debug, uint, 0644); MODULE_PARM_DESC(debug, " activates debug info"); #define VICODEC_NAME "vicodec" #define MAX_WIDTH 4096U #define MIN_WIDTH 640U #define MAX_HEIGHT 2160U #define MIN_HEIGHT 360U /* Recommended number of buffers for the stateful codecs */ #define VICODEC_REC_BUFS 2 #define dprintk(dev, fmt, arg...) \ v4l2_dbg(1, debug, &dev->v4l2_dev, "%s: " fmt, __func__, ## arg) struct pixfmt_info { u32 id; unsigned int bytesperline_mult; unsigned int sizeimage_mult; unsigned int sizeimage_div; unsigned int luma_step; unsigned int chroma_step; /* Chroma plane subsampling */ unsigned int width_div; unsigned int height_div; }; static const struct v4l2_fwht_pixfmt_info pixfmt_fwht = { V4L2_PIX_FMT_FWHT, 0, 3, 1, 1, 1, 1, 1, 0, 1 }; static const struct v4l2_fwht_pixfmt_info pixfmt_stateless_fwht = { V4L2_PIX_FMT_FWHT_STATELESS, 0, 3, 1, 1, 1, 1, 1, 0, 1 }; static void vicodec_dev_release(struct device *dev) { } static struct platform_device vicodec_pdev = { .name = VICODEC_NAME, .dev.release = vicodec_dev_release, }; /* Per-queue, driver-specific private data */ struct vicodec_q_data { unsigned int coded_width; unsigned int coded_height; unsigned int visible_width; unsigned int visible_height; unsigned int sizeimage; unsigned int vb2_sizeimage; unsigned int sequence; const struct v4l2_fwht_pixfmt_info *info; }; enum { V4L2_M2M_SRC = 0, V4L2_M2M_DST = 1, }; struct vicodec_dev_instance { struct video_device vfd; struct mutex mutex; spinlock_t lock; struct v4l2_m2m_dev *m2m_dev; }; struct vicodec_dev { struct v4l2_device v4l2_dev; struct vicodec_dev_instance stateful_enc; struct vicodec_dev_instance stateful_dec; struct vicodec_dev_instance stateless_dec; #ifdef CONFIG_MEDIA_CONTROLLER struct media_device mdev; #endif }; struct vicodec_ctx { struct v4l2_fh fh; struct vicodec_dev *dev; bool is_enc; bool is_stateless; spinlock_t *lock; struct v4l2_ctrl_handler hdl; /* Source and destination queue data */ struct vicodec_q_data q_data[2]; struct v4l2_fwht_state state; u32 cur_buf_offset; u32 comp_max_size; u32 comp_size; u32 header_size; u32 comp_magic_cnt; bool comp_has_frame; bool comp_has_next_frame; bool first_source_change_sent; bool source_changed; }; static const struct v4l2_event vicodec_eos_event = { .type = V4L2_EVENT_EOS }; static inline struct vicodec_ctx *file2ctx(struct file *file) { return container_of(file->private_data, struct vicodec_ctx, fh); } static struct vicodec_q_data *get_q_data(struct vicodec_ctx *ctx, enum v4l2_buf_type type) { switch (type) { case V4L2_BUF_TYPE_VIDEO_OUTPUT: case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: return &ctx->q_data[V4L2_M2M_SRC]; case V4L2_BUF_TYPE_VIDEO_CAPTURE: case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: return &ctx->q_data[V4L2_M2M_DST]; default: break; } return NULL; } static void copy_cap_to_ref(const u8 *cap, const struct v4l2_fwht_pixfmt_info *info, struct v4l2_fwht_state *state) { int plane_idx; u8 *p_ref = state->ref_frame.buf; unsigned int cap_stride = state->stride; unsigned int ref_stride = state->ref_stride; for (plane_idx = 0; plane_idx < info->planes_num; plane_idx++) { int i; unsigned int h_div = (plane_idx == 1 || plane_idx == 2) ? info->height_div : 1; const u8 *row_cap = cap; u8 *row_ref = p_ref; if (info->planes_num == 3 && plane_idx == 1) { cap_stride /= 2; ref_stride /= 2; } if (plane_idx == 1 && (info->id == V4L2_PIX_FMT_NV24 || info->id == V4L2_PIX_FMT_NV42)) { cap_stride *= 2; ref_stride *= 2; } for (i = 0; i < state->visible_height / h_div; i++) { memcpy(row_ref, row_cap, ref_stride); row_ref += ref_stride; row_cap += cap_stride; } cap += cap_stride * (state->coded_height / h_div); p_ref += ref_stride * (state->coded_height / h_div); } } static bool validate_by_version(unsigned int flags, unsigned int version) { if (!version || version > V4L2_FWHT_VERSION) return false; if (version >= 2) { unsigned int components_num = 1 + ((flags & V4L2_FWHT_FL_COMPONENTS_NUM_MSK) >> V4L2_FWHT_FL_COMPONENTS_NUM_OFFSET); unsigned int pixenc = flags & V4L2_FWHT_FL_PIXENC_MSK; if (components_num == 0 || components_num > 4 || !pixenc) return false; } return true; } static bool validate_stateless_params_flags(const struct v4l2_ctrl_fwht_params *params, const struct v4l2_fwht_pixfmt_info *cur_info) { unsigned int width_div = (params->flags & V4L2_FWHT_FL_CHROMA_FULL_WIDTH) ? 1 : 2; unsigned int height_div = (params->flags & V4L2_FWHT_FL_CHROMA_FULL_HEIGHT) ? 1 : 2; unsigned int components_num = 3; unsigned int pixenc = 0; if (params->version < 3) return false; components_num = 1 + ((params->flags & V4L2_FWHT_FL_COMPONENTS_NUM_MSK) >> V4L2_FWHT_FL_COMPONENTS_NUM_OFFSET); pixenc = (params->flags & V4L2_FWHT_FL_PIXENC_MSK); if (v4l2_fwht_validate_fmt(cur_info, width_div, height_div, components_num, pixenc)) return true; return false; } static void update_state_from_header(struct vicodec_ctx *ctx) { const struct fwht_cframe_hdr *p_hdr = &ctx->state.header; ctx->state.visible_width = ntohl(p_hdr->width); ctx->state.visible_height = ntohl(p_hdr->height); ctx->state.colorspace = ntohl(p_hdr->colorspace); ctx->state.xfer_func = ntohl(p_hdr->xfer_func); ctx->state.ycbcr_enc = ntohl(p_hdr->ycbcr_enc); ctx->state.quantization = ntohl(p_hdr->quantization); } static int device_process(struct vicodec_ctx *ctx, struct vb2_v4l2_buffer *src_vb, struct vb2_v4l2_buffer *dst_vb) { struct vicodec_dev *dev = ctx->dev; struct v4l2_fwht_state *state = &ctx->state; u8 *p_src, *p_dst; int ret = 0; if (ctx->is_enc || ctx->is_stateless) p_src = vb2_plane_vaddr(&src_vb->vb2_buf, 0); else p_src = state->compressed_frame; if (ctx->is_stateless) { struct media_request *src_req = src_vb->vb2_buf.req_obj.req; ret = v4l2_ctrl_request_setup(src_req, &ctx->hdl); if (ret) return ret; update_state_from_header(ctx); ctx->state.header.size = htonl(vb2_get_plane_payload(&src_vb->vb2_buf, 0)); /* * set the reference buffer from the reference timestamp * only if this is a P-frame */ if (!(ntohl(ctx->state.header.flags) & V4L2_FWHT_FL_I_FRAME)) { struct vb2_buffer *ref_vb2_buf; struct vb2_queue *vq_cap = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); ref_vb2_buf = vb2_find_buffer(vq_cap, ctx->state.ref_frame_ts); if (!ref_vb2_buf) return -EINVAL; if (ref_vb2_buf->state == VB2_BUF_STATE_ERROR) ret = -EINVAL; ctx->state.ref_frame.buf = vb2_plane_vaddr(ref_vb2_buf, 0); } else { ctx->state.ref_frame.buf = NULL; } } p_dst = vb2_plane_vaddr(&dst_vb->vb2_buf, 0); if (!p_src || !p_dst) { v4l2_err(&dev->v4l2_dev, "Acquiring kernel pointers to buffers failed\n"); return -EFAULT; } if (ctx->is_enc) { struct vicodec_q_data *q_src; int comp_sz_or_errcode; q_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT); state->info = q_src->info; comp_sz_or_errcode = v4l2_fwht_encode(state, p_src, p_dst); if (comp_sz_or_errcode < 0) return comp_sz_or_errcode; vb2_set_plane_payload(&dst_vb->vb2_buf, 0, comp_sz_or_errcode); } else { struct vicodec_q_data *q_dst; unsigned int comp_frame_size = ntohl(ctx->state.header.size); q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); if (comp_frame_size > ctx->comp_max_size) return -EINVAL; state->info = q_dst->info; ret = v4l2_fwht_decode(state, p_src, p_dst); if (ret < 0) return ret; if (!ctx->is_stateless) copy_cap_to_ref(p_dst, ctx->state.info, &ctx->state); vb2_set_plane_payload(&dst_vb->vb2_buf, 0, q_dst->sizeimage); if (ntohl(ctx->state.header.flags) & V4L2_FWHT_FL_I_FRAME) dst_vb->flags |= V4L2_BUF_FLAG_KEYFRAME; else dst_vb->flags |= V4L2_BUF_FLAG_PFRAME; } return ret; } /* * mem2mem callbacks */ static enum vb2_buffer_state get_next_header(struct vicodec_ctx *ctx, u8 **pp, u32 sz) { static const u8 magic[] = { 0x4f, 0x4f, 0x4f, 0x4f, 0xff, 0xff, 0xff, 0xff }; u8 *p = *pp; u32 state; u8 *header = (u8 *)&ctx->state.header; state = VB2_BUF_STATE_DONE; if (!ctx->header_size) { state = VB2_BUF_STATE_ERROR; for (; p < *pp + sz; p++) { u32 copy; p = memchr(p, magic[ctx->comp_magic_cnt], *pp + sz - p); if (!p) { ctx->comp_magic_cnt = 0; p = *pp + sz; break; } copy = sizeof(magic) - ctx->comp_magic_cnt; if (*pp + sz - p < copy) copy = *pp + sz - p; memcpy(header + ctx->comp_magic_cnt, p, copy); ctx->comp_magic_cnt += copy; if (!memcmp(header, magic, ctx->comp_magic_cnt)) { p += copy; state = VB2_BUF_STATE_DONE; break; } ctx->comp_magic_cnt = 0; } if (ctx->comp_magic_cnt < sizeof(magic)) { *pp = p; return state; } ctx->header_size = sizeof(magic); } if (ctx->header_size < sizeof(struct fwht_cframe_hdr)) { u32 copy = sizeof(struct fwht_cframe_hdr) - ctx->header_size; if (*pp + sz - p < copy) copy = *pp + sz - p; memcpy(header + ctx->header_size, p, copy); p += copy; ctx->header_size += copy; } *pp = p; return state; } /* device_run() - prepares and starts the device */ static void device_run(void *priv) { struct vicodec_ctx *ctx = priv; struct vicodec_dev *dev = ctx->dev; struct vb2_v4l2_buffer *src_buf, *dst_buf; struct vicodec_q_data *q_src, *q_dst; u32 state; struct media_request *src_req; src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx); dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx); src_req = src_buf->vb2_buf.req_obj.req; q_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT); q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); state = VB2_BUF_STATE_DONE; if (device_process(ctx, src_buf, dst_buf)) state = VB2_BUF_STATE_ERROR; else dst_buf->sequence = q_dst->sequence++; dst_buf->flags &= ~V4L2_BUF_FLAG_LAST; v4l2_m2m_buf_copy_metadata(src_buf, dst_buf, false); spin_lock(ctx->lock); if (!ctx->comp_has_next_frame && v4l2_m2m_is_last_draining_src_buf(ctx->fh.m2m_ctx, src_buf)) { dst_buf->flags |= V4L2_BUF_FLAG_LAST; v4l2_event_queue_fh(&ctx->fh, &vicodec_eos_event); v4l2_m2m_mark_stopped(ctx->fh.m2m_ctx); } if (ctx->is_enc || ctx->is_stateless) { src_buf->sequence = q_src->sequence++; src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx); v4l2_m2m_buf_done(src_buf, state); } else if (vb2_get_plane_payload(&src_buf->vb2_buf, 0) == ctx->cur_buf_offset) { src_buf->sequence = q_src->sequence++; src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx); v4l2_m2m_buf_done(src_buf, state); ctx->cur_buf_offset = 0; ctx->comp_has_next_frame = false; } v4l2_m2m_buf_done(dst_buf, state); ctx->comp_size = 0; ctx->header_size = 0; ctx->comp_magic_cnt = 0; ctx->comp_has_frame = false; spin_unlock(ctx->lock); if (ctx->is_stateless && src_req) v4l2_ctrl_request_complete(src_req, &ctx->hdl); if (ctx->is_enc) v4l2_m2m_job_finish(dev->stateful_enc.m2m_dev, ctx->fh.m2m_ctx); else if (ctx->is_stateless) v4l2_m2m_job_finish(dev->stateless_dec.m2m_dev, ctx->fh.m2m_ctx); else v4l2_m2m_job_finish(dev->stateful_dec.m2m_dev, ctx->fh.m2m_ctx); } static void job_remove_src_buf(struct vicodec_ctx *ctx, u32 state) { struct vb2_v4l2_buffer *src_buf; struct vicodec_q_data *q_src; q_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT); spin_lock(ctx->lock); src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx); src_buf->sequence = q_src->sequence++; v4l2_m2m_buf_done(src_buf, state); ctx->cur_buf_offset = 0; spin_unlock(ctx->lock); } static const struct v4l2_fwht_pixfmt_info * info_from_header(const struct fwht_cframe_hdr *p_hdr) { unsigned int flags = ntohl(p_hdr->flags); unsigned int width_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_WIDTH) ? 1 : 2; unsigned int height_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_HEIGHT) ? 1 : 2; unsigned int components_num = 3; unsigned int pixenc = 0; unsigned int version = ntohl(p_hdr->version); if (version >= 2) { components_num = 1 + ((flags & V4L2_FWHT_FL_COMPONENTS_NUM_MSK) >> V4L2_FWHT_FL_COMPONENTS_NUM_OFFSET); pixenc = (flags & V4L2_FWHT_FL_PIXENC_MSK); } return v4l2_fwht_find_nth_fmt(width_div, height_div, components_num, pixenc, 0); } static bool is_header_valid(const struct fwht_cframe_hdr *p_hdr) { const struct v4l2_fwht_pixfmt_info *info; unsigned int w = ntohl(p_hdr->width); unsigned int h = ntohl(p_hdr->height); unsigned int version = ntohl(p_hdr->version); unsigned int flags = ntohl(p_hdr->flags); if (w < MIN_WIDTH || w > MAX_WIDTH || h < MIN_HEIGHT || h > MAX_HEIGHT) return false; if (!validate_by_version(flags, version)) return false; info = info_from_header(p_hdr); if (!info) return false; return true; } static void update_capture_data_from_header(struct vicodec_ctx *ctx) { struct vicodec_q_data *q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); const struct fwht_cframe_hdr *p_hdr = &ctx->state.header; const struct v4l2_fwht_pixfmt_info *info = info_from_header(p_hdr); unsigned int flags = ntohl(p_hdr->flags); unsigned int hdr_width_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_WIDTH) ? 1 : 2; unsigned int hdr_height_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_HEIGHT) ? 1 : 2; /* * This function should not be used by a stateless codec since * it changes values in q_data that are not request specific */ WARN_ON(ctx->is_stateless); q_dst->info = info; q_dst->visible_width = ntohl(p_hdr->width); q_dst->visible_height = ntohl(p_hdr->height); q_dst->coded_width = vic_round_dim(q_dst->visible_width, hdr_width_div); q_dst->coded_height = vic_round_dim(q_dst->visible_height, hdr_height_div); q_dst->sizeimage = q_dst->coded_width * q_dst->coded_height * q_dst->info->sizeimage_mult / q_dst->info->sizeimage_div; ctx->state.colorspace = ntohl(p_hdr->colorspace); ctx->state.xfer_func = ntohl(p_hdr->xfer_func); ctx->state.ycbcr_enc = ntohl(p_hdr->ycbcr_enc); ctx->state.quantization = ntohl(p_hdr->quantization); } static void set_last_buffer(struct vb2_v4l2_buffer *dst_buf, const struct vb2_v4l2_buffer *src_buf, struct vicodec_ctx *ctx) { struct vicodec_q_data *q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); vb2_set_plane_payload(&dst_buf->vb2_buf, 0, 0); dst_buf->sequence = q_dst->sequence++; v4l2_m2m_buf_copy_metadata(src_buf, dst_buf, !ctx->is_enc); dst_buf->flags |= V4L2_BUF_FLAG_LAST; v4l2_m2m_buf_done(dst_buf, VB2_BUF_STATE_DONE); } static int job_ready(void *priv) { static const u8 magic[] = { 0x4f, 0x4f, 0x4f, 0x4f, 0xff, 0xff, 0xff, 0xff }; struct vicodec_ctx *ctx = priv; struct vb2_v4l2_buffer *src_buf; u8 *p_src; u8 *p; u32 sz; u32 state; struct vicodec_q_data *q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); unsigned int flags; unsigned int hdr_width_div; unsigned int hdr_height_div; unsigned int max_to_copy; unsigned int comp_frame_size; if (ctx->source_changed) return 0; if (ctx->is_stateless || ctx->is_enc || ctx->comp_has_frame) return 1; restart: ctx->comp_has_next_frame = false; src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx); if (!src_buf) return 0; p_src = vb2_plane_vaddr(&src_buf->vb2_buf, 0); sz = vb2_get_plane_payload(&src_buf->vb2_buf, 0); p = p_src + ctx->cur_buf_offset; state = VB2_BUF_STATE_DONE; if (ctx->header_size < sizeof(struct fwht_cframe_hdr)) { state = get_next_header(ctx, &p, p_src + sz - p); if (ctx->header_size < sizeof(struct fwht_cframe_hdr)) { if (v4l2_m2m_is_last_draining_src_buf(ctx->fh.m2m_ctx, src_buf)) return 1; job_remove_src_buf(ctx, state); goto restart; } } comp_frame_size = ntohl(ctx->state.header.size); /* * The current scanned frame might be the first frame of a new * resolution so its size might be larger than ctx->comp_max_size. * In that case it is copied up to the current buffer capacity and * the copy will continue after allocating new large enough buffer * when restreaming */ max_to_copy = min(comp_frame_size, ctx->comp_max_size); if (ctx->comp_size < max_to_copy) { u32 copy = max_to_copy - ctx->comp_size; if (copy > p_src + sz - p) copy = p_src + sz - p; memcpy(ctx->state.compressed_frame + ctx->comp_size, p, copy); p += copy; ctx->comp_size += copy; if (ctx->comp_size < max_to_copy) { if (v4l2_m2m_is_last_draining_src_buf(ctx->fh.m2m_ctx, src_buf)) return 1; job_remove_src_buf(ctx, state); goto restart; } } ctx->cur_buf_offset = p - p_src; if (ctx->comp_size == comp_frame_size) ctx->comp_has_frame = true; ctx->comp_has_next_frame = false; if (ctx->comp_has_frame && sz - ctx->cur_buf_offset >= sizeof(struct fwht_cframe_hdr)) { struct fwht_cframe_hdr *p_hdr = (struct fwht_cframe_hdr *)p; u32 frame_size = ntohl(p_hdr->size); u32 remaining = sz - ctx->cur_buf_offset - sizeof(*p_hdr); if (!memcmp(p, magic, sizeof(magic))) ctx->comp_has_next_frame = remaining >= frame_size; } /* * if the header is invalid the device_run will just drop the frame * with an error */ if (!is_header_valid(&ctx->state.header) && ctx->comp_has_frame) return 1; flags = ntohl(ctx->state.header.flags); hdr_width_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_WIDTH) ? 1 : 2; hdr_height_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_HEIGHT) ? 1 : 2; if (ntohl(ctx->state.header.width) != q_dst->visible_width || ntohl(ctx->state.header.height) != q_dst->visible_height || !q_dst->info || hdr_width_div != q_dst->info->width_div || hdr_height_div != q_dst->info->height_div) { static const struct v4l2_event rs_event = { .type = V4L2_EVENT_SOURCE_CHANGE, .u.src_change.changes = V4L2_EVENT_SRC_CH_RESOLUTION, }; struct vb2_v4l2_buffer *dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx); update_capture_data_from_header(ctx); v4l2_event_queue_fh(&ctx->fh, &rs_event); set_last_buffer(dst_buf, src_buf, ctx); ctx->source_changed = true; return 0; } return 1; } /* * video ioctls */ static const struct v4l2_fwht_pixfmt_info *find_fmt(u32 fmt) { const struct v4l2_fwht_pixfmt_info *info = v4l2_fwht_find_pixfmt(fmt); if (!info) info = v4l2_fwht_get_pixfmt(0); return info; } static int vidioc_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { strscpy(cap->driver, VICODEC_NAME, sizeof(cap->driver)); strscpy(cap->card, VICODEC_NAME, sizeof(cap->card)); snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", VICODEC_NAME); return 0; } static int enum_fmt(struct v4l2_fmtdesc *f, struct vicodec_ctx *ctx, bool is_out) { bool is_uncomp = (ctx->is_enc && is_out) || (!ctx->is_enc && !is_out); if (V4L2_TYPE_IS_MULTIPLANAR(f->type) && !multiplanar) return -EINVAL; if (!V4L2_TYPE_IS_MULTIPLANAR(f->type) && multiplanar) return -EINVAL; if (is_uncomp) { const struct v4l2_fwht_pixfmt_info *info = get_q_data(ctx, f->type)->info; if (ctx->is_enc || !vb2_is_streaming(&ctx->fh.m2m_ctx->cap_q_ctx.q)) info = v4l2_fwht_get_pixfmt(f->index); else info = v4l2_fwht_find_nth_fmt(info->width_div, info->height_div, info->components_num, info->pixenc, f->index); if (!info) return -EINVAL; f->pixelformat = info->id; } else { if (f->index) return -EINVAL; f->pixelformat = ctx->is_stateless ? V4L2_PIX_FMT_FWHT_STATELESS : V4L2_PIX_FMT_FWHT; if (!ctx->is_enc && !ctx->is_stateless) f->flags = V4L2_FMT_FLAG_DYN_RESOLUTION | V4L2_FMT_FLAG_CONTINUOUS_BYTESTREAM; } return 0; } static int vidioc_enum_fmt_vid_cap(struct file *file, void *priv, struct v4l2_fmtdesc *f) { struct vicodec_ctx *ctx = file2ctx(file); return enum_fmt(f, ctx, false); } static int vidioc_enum_fmt_vid_out(struct file *file, void *priv, struct v4l2_fmtdesc *f) { struct vicodec_ctx *ctx = file2ctx(file); return enum_fmt(f, ctx, true); } static int vidioc_g_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f) { struct vb2_queue *vq; struct vicodec_q_data *q_data; struct v4l2_pix_format_mplane *pix_mp; struct v4l2_pix_format *pix; const struct v4l2_fwht_pixfmt_info *info; vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type); if (!vq) return -EINVAL; q_data = get_q_data(ctx, f->type); info = q_data->info; switch (f->type) { case V4L2_BUF_TYPE_VIDEO_CAPTURE: case V4L2_BUF_TYPE_VIDEO_OUTPUT: if (multiplanar) return -EINVAL; pix = &f->fmt.pix; pix->width = q_data->coded_width; pix->height = q_data->coded_height; pix->field = V4L2_FIELD_NONE; pix->pixelformat = info->id; pix->bytesperline = q_data->coded_width * info->bytesperline_mult; pix->sizeimage = q_data->sizeimage; pix->colorspace = ctx->state.colorspace; pix->xfer_func = ctx->state.xfer_func; pix->ycbcr_enc = ctx->state.ycbcr_enc; pix->quantization = ctx->state.quantization; break; case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: if (!multiplanar) return -EINVAL; pix_mp = &f->fmt.pix_mp; pix_mp->width = q_data->coded_width; pix_mp->height = q_data->coded_height; pix_mp->field = V4L2_FIELD_NONE; pix_mp->pixelformat = info->id; pix_mp->num_planes = 1; pix_mp->plane_fmt[0].bytesperline = q_data->coded_width * info->bytesperline_mult; pix_mp->plane_fmt[0].sizeimage = q_data->sizeimage; pix_mp->colorspace = ctx->state.colorspace; pix_mp->xfer_func = ctx->state.xfer_func; pix_mp->ycbcr_enc = ctx->state.ycbcr_enc; pix_mp->quantization = ctx->state.quantization; break; default: return -EINVAL; } return 0; } static int vidioc_g_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f) { return vidioc_g_fmt(file2ctx(file), f); } static int vidioc_g_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { return vidioc_g_fmt(file2ctx(file), f); } static int vidioc_try_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f) { struct v4l2_pix_format_mplane *pix_mp; struct v4l2_pix_format *pix; struct v4l2_plane_pix_format *plane; const struct v4l2_fwht_pixfmt_info *info = ctx->is_stateless ? &pixfmt_stateless_fwht : &pixfmt_fwht; switch (f->type) { case V4L2_BUF_TYPE_VIDEO_CAPTURE: case V4L2_BUF_TYPE_VIDEO_OUTPUT: pix = &f->fmt.pix; if (pix->pixelformat != V4L2_PIX_FMT_FWHT && pix->pixelformat != V4L2_PIX_FMT_FWHT_STATELESS) info = find_fmt(pix->pixelformat); pix->width = clamp(pix->width, MIN_WIDTH, MAX_WIDTH); pix->width = vic_round_dim(pix->width, info->width_div); pix->height = clamp(pix->height, MIN_HEIGHT, MAX_HEIGHT); pix->height = vic_round_dim(pix->height, info->height_div); pix->field = V4L2_FIELD_NONE; pix->bytesperline = pix->width * info->bytesperline_mult; pix->sizeimage = pix->width * pix->height * info->sizeimage_mult / info->sizeimage_div; if (pix->pixelformat == V4L2_PIX_FMT_FWHT) pix->sizeimage += sizeof(struct fwht_cframe_hdr); break; case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: pix_mp = &f->fmt.pix_mp; plane = pix_mp->plane_fmt; if (pix_mp->pixelformat != V4L2_PIX_FMT_FWHT && pix_mp->pixelformat != V4L2_PIX_FMT_FWHT_STATELESS) info = find_fmt(pix_mp->pixelformat); pix_mp->num_planes = 1; pix_mp->width = clamp(pix_mp->width, MIN_WIDTH, MAX_WIDTH); pix_mp->width = vic_round_dim(pix_mp->width, info->width_div); pix_mp->height = clamp(pix_mp->height, MIN_HEIGHT, MAX_HEIGHT); pix_mp->height = vic_round_dim(pix_mp->height, info->height_div); pix_mp->field = V4L2_FIELD_NONE; plane->bytesperline = pix_mp->width * info->bytesperline_mult; plane->sizeimage = pix_mp->width * pix_mp->height * info->sizeimage_mult / info->sizeimage_div; if (pix_mp->pixelformat == V4L2_PIX_FMT_FWHT) plane->sizeimage += sizeof(struct fwht_cframe_hdr); break; default: return -EINVAL; } return 0; } static int vidioc_try_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { struct vicodec_ctx *ctx = file2ctx(file); struct v4l2_pix_format_mplane *pix_mp; struct v4l2_pix_format *pix; switch (f->type) { case V4L2_BUF_TYPE_VIDEO_CAPTURE: if (multiplanar) return -EINVAL; pix = &f->fmt.pix; pix->pixelformat = ctx->is_enc ? V4L2_PIX_FMT_FWHT : find_fmt(f->fmt.pix.pixelformat)->id; pix->colorspace = ctx->state.colorspace; pix->xfer_func = ctx->state.xfer_func; pix->ycbcr_enc = ctx->state.ycbcr_enc; pix->quantization = ctx->state.quantization; break; case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: if (!multiplanar) return -EINVAL; pix_mp = &f->fmt.pix_mp; pix_mp->pixelformat = ctx->is_enc ? V4L2_PIX_FMT_FWHT : find_fmt(pix_mp->pixelformat)->id; pix_mp->colorspace = ctx->state.colorspace; pix_mp->xfer_func = ctx->state.xfer_func; pix_mp->ycbcr_enc = ctx->state.ycbcr_enc; pix_mp->quantization = ctx->state.quantization; break; default: return -EINVAL; } return vidioc_try_fmt(ctx, f); } static int vidioc_try_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f) { struct vicodec_ctx *ctx = file2ctx(file); struct v4l2_pix_format_mplane *pix_mp; struct v4l2_pix_format *pix; switch (f->type) { case V4L2_BUF_TYPE_VIDEO_OUTPUT: if (multiplanar) return -EINVAL; pix = &f->fmt.pix; if (ctx->is_enc) pix->pixelformat = find_fmt(pix->pixelformat)->id; else if (ctx->is_stateless) pix->pixelformat = V4L2_PIX_FMT_FWHT_STATELESS; else pix->pixelformat = V4L2_PIX_FMT_FWHT; if (!pix->colorspace) pix->colorspace = V4L2_COLORSPACE_REC709; break; case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: if (!multiplanar) return -EINVAL; pix_mp = &f->fmt.pix_mp; if (ctx->is_enc) pix_mp->pixelformat = find_fmt(pix_mp->pixelformat)->id; else if (ctx->is_stateless) pix_mp->pixelformat = V4L2_PIX_FMT_FWHT_STATELESS; else pix_mp->pixelformat = V4L2_PIX_FMT_FWHT; if (!pix_mp->colorspace) pix_mp->colorspace = V4L2_COLORSPACE_REC709; break; default: return -EINVAL; } return vidioc_try_fmt(ctx, f); } static int vidioc_s_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f) { struct vicodec_q_data *q_data; struct vb2_queue *vq; bool fmt_changed = true; struct v4l2_pix_format_mplane *pix_mp; struct v4l2_pix_format *pix; vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type); if (!vq) return -EINVAL; q_data = get_q_data(ctx, f->type); if (!q_data) return -EINVAL; switch (f->type) { case V4L2_BUF_TYPE_VIDEO_CAPTURE: case V4L2_BUF_TYPE_VIDEO_OUTPUT: pix = &f->fmt.pix; if (ctx->is_enc && V4L2_TYPE_IS_OUTPUT(f->type)) fmt_changed = !q_data->info || q_data->info->id != pix->pixelformat || q_data->coded_width != pix->width || q_data->coded_height != pix->height; if (vb2_is_busy(vq) && fmt_changed) return -EBUSY; if (pix->pixelformat == V4L2_PIX_FMT_FWHT) q_data->info = &pixfmt_fwht; else if (pix->pixelformat == V4L2_PIX_FMT_FWHT_STATELESS) q_data->info = &pixfmt_stateless_fwht; else q_data->info = find_fmt(pix->pixelformat); q_data->coded_width = pix->width; q_data->coded_height = pix->height; q_data->sizeimage = pix->sizeimage; break; case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: pix_mp = &f->fmt.pix_mp; if (ctx->is_enc && V4L2_TYPE_IS_OUTPUT(f->type)) fmt_changed = !q_data->info || q_data->info->id != pix_mp->pixelformat || q_data->coded_width != pix_mp->width || q_data->coded_height != pix_mp->height; if (vb2_is_busy(vq) && fmt_changed) return -EBUSY; if (pix_mp->pixelformat == V4L2_PIX_FMT_FWHT) q_data->info = &pixfmt_fwht; else if (pix_mp->pixelformat == V4L2_PIX_FMT_FWHT_STATELESS) q_data->info = &pixfmt_stateless_fwht; else q_data->info = find_fmt(pix_mp->pixelformat); q_data->coded_width = pix_mp->width; q_data->coded_height = pix_mp->height; q_data->sizeimage = pix_mp->plane_fmt[0].sizeimage; break; default: return -EINVAL; } dprintk(ctx->dev, "Setting format for type %d, coded wxh: %dx%d, fourcc: 0x%08x\n", f->type, q_data->coded_width, q_data->coded_height, q_data->info->id); return 0; } static int vidioc_s_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { int ret; ret = vidioc_try_fmt_vid_cap(file, priv, f); if (ret) return ret; return vidioc_s_fmt(file2ctx(file), f); } static int vidioc_s_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f) { struct vicodec_ctx *ctx = file2ctx(file); struct vicodec_q_data *q_data; struct vicodec_q_data *q_data_cap; struct v4l2_pix_format *pix; struct v4l2_pix_format_mplane *pix_mp; u32 coded_w = 0, coded_h = 0; unsigned int size = 0; int ret; q_data = get_q_data(ctx, f->type); q_data_cap = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); ret = vidioc_try_fmt_vid_out(file, priv, f); if (ret) return ret; if (ctx->is_enc) { struct vb2_queue *vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type); struct vb2_queue *vq_cap = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); const struct v4l2_fwht_pixfmt_info *info = ctx->is_stateless ? &pixfmt_stateless_fwht : &pixfmt_fwht; if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) { coded_w = f->fmt.pix.width; coded_h = f->fmt.pix.height; } else { coded_w = f->fmt.pix_mp.width; coded_h = f->fmt.pix_mp.height; } if (vb2_is_busy(vq) && (coded_w != q_data->coded_width || coded_h != q_data->coded_height)) return -EBUSY; size = coded_w * coded_h * info->sizeimage_mult / info->sizeimage_div; if (!ctx->is_stateless) size += sizeof(struct fwht_cframe_hdr); if (vb2_is_busy(vq_cap) && size > q_data_cap->sizeimage) return -EBUSY; } ret = vidioc_s_fmt(file2ctx(file), f); if (!ret) { if (ctx->is_enc) { q_data->visible_width = coded_w; q_data->visible_height = coded_h; q_data_cap->coded_width = coded_w; q_data_cap->coded_height = coded_h; q_data_cap->sizeimage = size; } switch (f->type) { case V4L2_BUF_TYPE_VIDEO_OUTPUT: pix = &f->fmt.pix; ctx->state.colorspace = pix->colorspace; ctx->state.xfer_func = pix->xfer_func; ctx->state.ycbcr_enc = pix->ycbcr_enc; ctx->state.quantization = pix->quantization; break; case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: pix_mp = &f->fmt.pix_mp; ctx->state.colorspace = pix_mp->colorspace; ctx->state.xfer_func = pix_mp->xfer_func; ctx->state.ycbcr_enc = pix_mp->ycbcr_enc; ctx->state.quantization = pix_mp->quantization; break; default: break; } } return ret; } static int vidioc_g_selection(struct file *file, void *priv, struct v4l2_selection *s) { struct vicodec_ctx *ctx = file2ctx(file); struct vicodec_q_data *q_data; q_data = get_q_data(ctx, s->type); if (!q_data) return -EINVAL; /* * encoder supports only cropping on the OUTPUT buffer * decoder supports only composing on the CAPTURE buffer */ if (ctx->is_enc && s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) { switch (s->target) { case V4L2_SEL_TGT_CROP: s->r.left = 0; s->r.top = 0; s->r.width = q_data->visible_width; s->r.height = q_data->visible_height; return 0; case V4L2_SEL_TGT_CROP_DEFAULT: case V4L2_SEL_TGT_CROP_BOUNDS: s->r.left = 0; s->r.top = 0; s->r.width = q_data->coded_width; s->r.height = q_data->coded_height; return 0; } } else if (!ctx->is_enc && s->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) { switch (s->target) { case V4L2_SEL_TGT_COMPOSE: s->r.left = 0; s->r.top = 0; s->r.width = q_data->visible_width; s->r.height = q_data->visible_height; return 0; case V4L2_SEL_TGT_COMPOSE_DEFAULT: case V4L2_SEL_TGT_COMPOSE_BOUNDS: s->r.left = 0; s->r.top = 0; s->r.width = q_data->coded_width; s->r.height = q_data->coded_height; return 0; } } return -EINVAL; } static int vidioc_s_selection(struct file *file, void *priv, struct v4l2_selection *s) { struct vicodec_ctx *ctx = file2ctx(file); struct vicodec_q_data *q_data; if (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT) return -EINVAL; q_data = get_q_data(ctx, s->type); if (!q_data) return -EINVAL; if (!ctx->is_enc || s->target != V4L2_SEL_TGT_CROP) return -EINVAL; s->r.left = 0; s->r.top = 0; q_data->visible_width = clamp(s->r.width, MIN_WIDTH, q_data->coded_width); s->r.width = q_data->visible_width; q_data->visible_height = clamp(s->r.height, MIN_HEIGHT, q_data->coded_height); s->r.height = q_data->visible_height; return 0; } static int vicodec_encoder_cmd(struct file *file, void *fh, struct v4l2_encoder_cmd *ec) { struct vicodec_ctx *ctx = file2ctx(file); int ret; ret = v4l2_m2m_ioctl_try_encoder_cmd(file, fh, ec); if (ret < 0) return ret; if (!vb2_is_streaming(&ctx->fh.m2m_ctx->out_q_ctx.q)) return 0; ret = v4l2_m2m_ioctl_encoder_cmd(file, fh, ec); if (ret < 0) return ret; if (ec->cmd == V4L2_ENC_CMD_STOP && v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) v4l2_event_queue_fh(&ctx->fh, &vicodec_eos_event); if (ec->cmd == V4L2_ENC_CMD_START && v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) vb2_clear_last_buffer_dequeued(&ctx->fh.m2m_ctx->cap_q_ctx.q); return 0; } static int vicodec_decoder_cmd(struct file *file, void *fh, struct v4l2_decoder_cmd *dc) { struct vicodec_ctx *ctx = file2ctx(file); int ret; /* * This ioctl should not be used with a stateless codec that doesn't * support holding buffers and the associated flush command. */ WARN_ON(ctx->is_stateless); ret = v4l2_m2m_ioctl_try_decoder_cmd(file, fh, dc); if (ret < 0) return ret; if (!vb2_is_streaming(&ctx->fh.m2m_ctx->out_q_ctx.q)) return 0; ret = v4l2_m2m_ioctl_decoder_cmd(file, fh, dc); if (ret < 0) return ret; if (dc->cmd == V4L2_DEC_CMD_STOP && v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) v4l2_event_queue_fh(&ctx->fh, &vicodec_eos_event); if (dc->cmd == V4L2_DEC_CMD_START && v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) vb2_clear_last_buffer_dequeued(&ctx->fh.m2m_ctx->cap_q_ctx.q); return 0; } static int vicodec_enum_framesizes(struct file *file, void *fh, struct v4l2_frmsizeenum *fsize) { switch (fsize->pixel_format) { case V4L2_PIX_FMT_FWHT_STATELESS: break; case V4L2_PIX_FMT_FWHT: break; default: if (find_fmt(fsize->pixel_format)->id == fsize->pixel_format) break; return -EINVAL; } if (fsize->index) return -EINVAL; fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE; fsize->stepwise.min_width = MIN_WIDTH; fsize->stepwise.max_width = MAX_WIDTH; fsize->stepwise.step_width = 8; fsize->stepwise.min_height = MIN_HEIGHT; fsize->stepwise.max_height = MAX_HEIGHT; fsize->stepwise.step_height = 8; return 0; } static int vicodec_subscribe_event(struct v4l2_fh *fh, const struct v4l2_event_subscription *sub) { struct vicodec_ctx *ctx = container_of(fh, struct vicodec_ctx, fh); switch (sub->type) { case V4L2_EVENT_SOURCE_CHANGE: if (ctx->is_enc) return -EINVAL; fallthrough; case V4L2_EVENT_EOS: if (ctx->is_stateless) return -EINVAL; return v4l2_event_subscribe(fh, sub, 0, NULL); default: return v4l2_ctrl_subscribe_event(fh, sub); } } static const struct v4l2_ioctl_ops vicodec_ioctl_ops = { .vidioc_querycap = vidioc_querycap, .vidioc_enum_fmt_vid_cap = vidioc_enum_fmt_vid_cap, .vidioc_g_fmt_vid_cap = vidioc_g_fmt_vid_cap, .vidioc_try_fmt_vid_cap = vidioc_try_fmt_vid_cap, .vidioc_s_fmt_vid_cap = vidioc_s_fmt_vid_cap, .vidioc_g_fmt_vid_cap_mplane = vidioc_g_fmt_vid_cap, .vidioc_try_fmt_vid_cap_mplane = vidioc_try_fmt_vid_cap, .vidioc_s_fmt_vid_cap_mplane = vidioc_s_fmt_vid_cap, .vidioc_enum_fmt_vid_out = vidioc_enum_fmt_vid_out, .vidioc_g_fmt_vid_out = vidioc_g_fmt_vid_out, .vidioc_try_fmt_vid_out = vidioc_try_fmt_vid_out, .vidioc_s_fmt_vid_out = vidioc_s_fmt_vid_out, .vidioc_g_fmt_vid_out_mplane = vidioc_g_fmt_vid_out, .vidioc_try_fmt_vid_out_mplane = vidioc_try_fmt_vid_out, .vidioc_s_fmt_vid_out_mplane = vidioc_s_fmt_vid_out, .vidioc_reqbufs = v4l2_m2m_ioctl_reqbufs, .vidioc_querybuf = v4l2_m2m_ioctl_querybuf, .vidioc_qbuf = v4l2_m2m_ioctl_qbuf, .vidioc_dqbuf = v4l2_m2m_ioctl_dqbuf, .vidioc_prepare_buf = v4l2_m2m_ioctl_prepare_buf, .vidioc_create_bufs = v4l2_m2m_ioctl_create_bufs, .vidioc_expbuf = v4l2_m2m_ioctl_expbuf, .vidioc_remove_bufs = v4l2_m2m_ioctl_remove_bufs, .vidioc_streamon = v4l2_m2m_ioctl_streamon, .vidioc_streamoff = v4l2_m2m_ioctl_streamoff, .vidioc_g_selection = vidioc_g_selection, .vidioc_s_selection = vidioc_s_selection, .vidioc_try_encoder_cmd = v4l2_m2m_ioctl_try_encoder_cmd, .vidioc_encoder_cmd = vicodec_encoder_cmd, .vidioc_try_decoder_cmd = v4l2_m2m_ioctl_try_decoder_cmd, .vidioc_decoder_cmd = vicodec_decoder_cmd, .vidioc_enum_framesizes = vicodec_enum_framesizes, .vidioc_subscribe_event = vicodec_subscribe_event, .vidioc_unsubscribe_event = v4l2_event_unsubscribe, }; /* * Queue operations */ static int vicodec_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[]) { struct vicodec_ctx *ctx = vb2_get_drv_priv(vq); struct vicodec_q_data *q_data = get_q_data(ctx, vq->type); unsigned int size = q_data->sizeimage; if (*nplanes) return sizes[0] < size ? -EINVAL : 0; *nplanes = 1; sizes[0] = size; q_data->vb2_sizeimage = size; return 0; } static int vicodec_buf_out_validate(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); vbuf->field = V4L2_FIELD_NONE; return 0; } static int vicodec_buf_prepare(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct vicodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue); struct vicodec_q_data *q_data; dprintk(ctx->dev, "type: %d\n", vb->vb2_queue->type); q_data = get_q_data(ctx, vb->vb2_queue->type); if (V4L2_TYPE_IS_OUTPUT(vb->vb2_queue->type)) { if (vbuf->field == V4L2_FIELD_ANY) vbuf->field = V4L2_FIELD_NONE; if (vbuf->field != V4L2_FIELD_NONE) { dprintk(ctx->dev, "%s field isn't supported\n", __func__); return -EINVAL; } } if (vb2_plane_size(vb, 0) < q_data->vb2_sizeimage) { dprintk(ctx->dev, "%s data will not fit into plane (%lu < %lu)\n", __func__, vb2_plane_size(vb, 0), (long)q_data->vb2_sizeimage); return -EINVAL; } return 0; } static void vicodec_buf_queue(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct vicodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue); unsigned int sz = vb2_get_plane_payload(&vbuf->vb2_buf, 0); u8 *p_src = vb2_plane_vaddr(&vbuf->vb2_buf, 0); u8 *p = p_src; struct vb2_queue *vq_out = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT); struct vb2_queue *vq_cap = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); bool header_valid = false; static const struct v4l2_event rs_event = { .type = V4L2_EVENT_SOURCE_CHANGE, .u.src_change.changes = V4L2_EVENT_SRC_CH_RESOLUTION, }; if (V4L2_TYPE_IS_CAPTURE(vb->vb2_queue->type) && vb2_is_streaming(vb->vb2_queue) && v4l2_m2m_dst_buf_is_last(ctx->fh.m2m_ctx)) { unsigned int i; for (i = 0; i < vb->num_planes; i++) vb2_set_plane_payload(vb, i, 0); vbuf->field = V4L2_FIELD_NONE; vbuf->sequence = get_q_data(ctx, vb->vb2_queue->type)->sequence++; v4l2_m2m_last_buffer_done(ctx->fh.m2m_ctx, vbuf); v4l2_event_queue_fh(&ctx->fh, &vicodec_eos_event); return; } /* buf_queue handles only the first source change event */ if (ctx->first_source_change_sent) { v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf); return; } /* * if both queues are streaming, the source change event is * handled in job_ready */ if (vb2_is_streaming(vq_cap) && vb2_is_streaming(vq_out)) { v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf); return; } /* * source change event is relevant only for the stateful decoder * in the compressed stream */ if (ctx->is_stateless || ctx->is_enc || V4L2_TYPE_IS_CAPTURE(vb->vb2_queue->type)) { v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf); return; } do { enum vb2_buffer_state state = get_next_header(ctx, &p, p_src + sz - p); if (ctx->header_size < sizeof(struct fwht_cframe_hdr)) { v4l2_m2m_buf_done(vbuf, state); return; } header_valid = is_header_valid(&ctx->state.header); /* * p points right after the end of the header in the * buffer. If the header is invalid we set p to point * to the next byte after the start of the header */ if (!header_valid) { p = p - sizeof(struct fwht_cframe_hdr) + 1; if (p < p_src) p = p_src; ctx->header_size = 0; ctx->comp_magic_cnt = 0; } } while (!header_valid); ctx->cur_buf_offset = p - p_src; update_capture_data_from_header(ctx); ctx->first_source_change_sent = true; v4l2_event_queue_fh(&ctx->fh, &rs_event); v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf); } static void vicodec_return_bufs(struct vb2_queue *q, u32 state) { struct vicodec_ctx *ctx = vb2_get_drv_priv(q); struct vb2_v4l2_buffer *vbuf; for (;;) { if (V4L2_TYPE_IS_OUTPUT(q->type)) vbuf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx); else vbuf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx); if (vbuf == NULL) return; v4l2_ctrl_request_complete(vbuf->vb2_buf.req_obj.req, &ctx->hdl); spin_lock(ctx->lock); v4l2_m2m_buf_done(vbuf, state); spin_unlock(ctx->lock); } } static unsigned int total_frame_size(struct vicodec_q_data *q_data) { unsigned int size; unsigned int chroma_div; if (!q_data->info) { WARN_ON(1); return 0; } size = q_data->coded_width * q_data->coded_height; chroma_div = q_data->info->width_div * q_data->info->height_div; if (q_data->info->components_num == 4) return 2 * size + 2 * (size / chroma_div); else if (q_data->info->components_num == 3) return size + 2 * (size / chroma_div); return size; } static int vicodec_start_streaming(struct vb2_queue *q, unsigned int count) { struct vicodec_ctx *ctx = vb2_get_drv_priv(q); struct vicodec_q_data *q_data = get_q_data(ctx, q->type); struct v4l2_fwht_state *state = &ctx->state; const struct v4l2_fwht_pixfmt_info *info = q_data->info; unsigned int size = q_data->coded_width * q_data->coded_height; unsigned int chroma_div; unsigned int total_planes_size; u8 *new_comp_frame = NULL; chroma_div = info->width_div * info->height_div; q_data->sequence = 0; v4l2_m2m_update_start_streaming_state(ctx->fh.m2m_ctx, q); state->gop_cnt = 0; if ((V4L2_TYPE_IS_OUTPUT(q->type) && !ctx->is_enc) || (V4L2_TYPE_IS_CAPTURE(q->type) && ctx->is_enc)) return 0; if (info->id == V4L2_PIX_FMT_FWHT || info->id == V4L2_PIX_FMT_FWHT_STATELESS) { vicodec_return_bufs(q, VB2_BUF_STATE_QUEUED); return -EINVAL; } total_planes_size = total_frame_size(q_data); ctx->comp_max_size = total_planes_size; state->visible_width = q_data->visible_width; state->visible_height = q_data->visible_height; state->coded_width = q_data->coded_width; state->coded_height = q_data->coded_height; state->stride = q_data->coded_width * info->bytesperline_mult; if (ctx->is_stateless) { state->ref_stride = state->stride; return 0; } state->ref_stride = q_data->coded_width * info->luma_alpha_step; state->ref_frame.buf = kvmalloc(total_planes_size, GFP_KERNEL); state->ref_frame.luma = state->ref_frame.buf; new_comp_frame = kvmalloc(ctx->comp_max_size, GFP_KERNEL); if (!state->ref_frame.luma || !new_comp_frame) { kvfree(state->ref_frame.luma); kvfree(new_comp_frame); vicodec_return_bufs(q, VB2_BUF_STATE_QUEUED); return -ENOMEM; } /* * if state->compressed_frame was already allocated then * it contain data of the first frame of the new resolution */ if (state->compressed_frame) { if (ctx->comp_size > ctx->comp_max_size) ctx->comp_size = ctx->comp_max_size; memcpy(new_comp_frame, state->compressed_frame, ctx->comp_size); } kvfree(state->compressed_frame); state->compressed_frame = new_comp_frame; if (info->components_num < 3) { state->ref_frame.cb = NULL; state->ref_frame.cr = NULL; state->ref_frame.alpha = NULL; return 0; } state->ref_frame.cb = state->ref_frame.luma + size; state->ref_frame.cr = state->ref_frame.cb + size / chroma_div; if (info->components_num == 4) state->ref_frame.alpha = state->ref_frame.cr + size / chroma_div; else state->ref_frame.alpha = NULL; return 0; } static void vicodec_stop_streaming(struct vb2_queue *q) { struct vicodec_ctx *ctx = vb2_get_drv_priv(q); vicodec_return_bufs(q, VB2_BUF_STATE_ERROR); v4l2_m2m_update_stop_streaming_state(ctx->fh.m2m_ctx, q); if (V4L2_TYPE_IS_OUTPUT(q->type) && v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) v4l2_event_queue_fh(&ctx->fh, &vicodec_eos_event); if (!ctx->is_enc && V4L2_TYPE_IS_OUTPUT(q->type)) ctx->first_source_change_sent = false; if ((!V4L2_TYPE_IS_OUTPUT(q->type) && !ctx->is_enc) || (V4L2_TYPE_IS_OUTPUT(q->type) && ctx->is_enc)) { if (!ctx->is_stateless) kvfree(ctx->state.ref_frame.buf); ctx->state.ref_frame.buf = NULL; ctx->state.ref_frame.luma = NULL; ctx->comp_max_size = 0; ctx->source_changed = false; } if (V4L2_TYPE_IS_OUTPUT(q->type) && !ctx->is_enc) { ctx->cur_buf_offset = 0; ctx->comp_size = 0; ctx->header_size = 0; ctx->comp_magic_cnt = 0; ctx->comp_has_frame = false; ctx->comp_has_next_frame = false; } } static void vicodec_buf_request_complete(struct vb2_buffer *vb) { struct vicodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue); v4l2_ctrl_request_complete(vb->req_obj.req, &ctx->hdl); } static const struct vb2_ops vicodec_qops = { .queue_setup = vicodec_queue_setup, .buf_out_validate = vicodec_buf_out_validate, .buf_prepare = vicodec_buf_prepare, .buf_queue = vicodec_buf_queue, .buf_request_complete = vicodec_buf_request_complete, .start_streaming = vicodec_start_streaming, .stop_streaming = vicodec_stop_streaming, }; static int queue_init(void *priv, struct vb2_queue *src_vq, struct vb2_queue *dst_vq) { struct vicodec_ctx *ctx = priv; int ret; src_vq->type = (multiplanar ? V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE : V4L2_BUF_TYPE_VIDEO_OUTPUT); src_vq->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF; src_vq->drv_priv = ctx; src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer); src_vq->ops = &vicodec_qops; src_vq->mem_ops = &vb2_vmalloc_memops; src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY; if (ctx->is_enc) { src_vq->lock = &ctx->dev->stateful_enc.mutex; src_vq->min_reqbufs_allocation = VICODEC_REC_BUFS; } else if (ctx->is_stateless) { src_vq->lock = &ctx->dev->stateless_dec.mutex; } else { src_vq->lock = &ctx->dev->stateful_dec.mutex; } src_vq->supports_requests = ctx->is_stateless; src_vq->requires_requests = ctx->is_stateless; ret = vb2_queue_init(src_vq); if (ret) return ret; dst_vq->type = (multiplanar ? V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE : V4L2_BUF_TYPE_VIDEO_CAPTURE); dst_vq->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF; dst_vq->max_num_buffers = 64; dst_vq->drv_priv = ctx; dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer); dst_vq->ops = &vicodec_qops; dst_vq->mem_ops = &vb2_vmalloc_memops; dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY; dst_vq->lock = src_vq->lock; if (!ctx->is_stateless && !ctx->is_enc) dst_vq->min_reqbufs_allocation = VICODEC_REC_BUFS; return vb2_queue_init(dst_vq); } static int vicodec_try_ctrl(struct v4l2_ctrl *ctrl) { struct vicodec_ctx *ctx = container_of(ctrl->handler, struct vicodec_ctx, hdl); const struct v4l2_ctrl_fwht_params *params; struct vicodec_q_data *q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); switch (ctrl->id) { case V4L2_CID_STATELESS_FWHT_PARAMS: if (!q_dst->info) return -EINVAL; params = ctrl->p_new.p_fwht_params; if (params->width > q_dst->coded_width || params->width < MIN_WIDTH || params->height > q_dst->coded_height || params->height < MIN_HEIGHT) return -EINVAL; if (!validate_by_version(params->flags, params->version)) return -EINVAL; if (!validate_stateless_params_flags(params, q_dst->info)) return -EINVAL; return 0; default: return 0; } return 0; } static void update_header_from_stateless_params(struct vicodec_ctx *ctx, const struct v4l2_ctrl_fwht_params *params) { struct fwht_cframe_hdr *p_hdr = &ctx->state.header; p_hdr->magic1 = FWHT_MAGIC1; p_hdr->magic2 = FWHT_MAGIC2; p_hdr->version = htonl(params->version); p_hdr->width = htonl(params->width); p_hdr->height = htonl(params->height); p_hdr->flags = htonl(params->flags); p_hdr->colorspace = htonl(params->colorspace); p_hdr->xfer_func = htonl(params->xfer_func); p_hdr->ycbcr_enc = htonl(params->ycbcr_enc); p_hdr->quantization = htonl(params->quantization); } static int vicodec_s_ctrl(struct v4l2_ctrl *ctrl) { struct vicodec_ctx *ctx = container_of(ctrl->handler, struct vicodec_ctx, hdl); const struct v4l2_ctrl_fwht_params *params; switch (ctrl->id) { case V4L2_CID_MPEG_VIDEO_GOP_SIZE: ctx->state.gop_size = ctrl->val; return 0; case V4L2_CID_FWHT_I_FRAME_QP: ctx->state.i_frame_qp = ctrl->val; return 0; case V4L2_CID_FWHT_P_FRAME_QP: ctx->state.p_frame_qp = ctrl->val; return 0; case V4L2_CID_STATELESS_FWHT_PARAMS: params = ctrl->p_new.p_fwht_params; update_header_from_stateless_params(ctx, params); ctx->state.ref_frame_ts = params->backward_ref_ts; return 0; } return -EINVAL; } static const struct v4l2_ctrl_ops vicodec_ctrl_ops = { .s_ctrl = vicodec_s_ctrl, .try_ctrl = vicodec_try_ctrl, }; static const struct v4l2_ctrl_config vicodec_ctrl_stateless_state = { .ops = &vicodec_ctrl_ops, .id = V4L2_CID_STATELESS_FWHT_PARAMS, .elem_size = sizeof(struct v4l2_ctrl_fwht_params), }; /* * File operations */ static int vicodec_open(struct file *file) { const struct v4l2_fwht_pixfmt_info *info = v4l2_fwht_get_pixfmt(0); struct video_device *vfd = video_devdata(file); struct vicodec_dev *dev = video_drvdata(file); struct vicodec_ctx *ctx = NULL; struct v4l2_ctrl_handler *hdl; unsigned int raw_size; unsigned int comp_size; int rc = 0; if (mutex_lock_interruptible(vfd->lock)) return -ERESTARTSYS; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) { rc = -ENOMEM; goto open_unlock; } if (vfd == &dev->stateful_enc.vfd) ctx->is_enc = true; else if (vfd == &dev->stateless_dec.vfd) ctx->is_stateless = true; v4l2_fh_init(&ctx->fh, video_devdata(file)); file->private_data = &ctx->fh; ctx->dev = dev; hdl = &ctx->hdl; v4l2_ctrl_handler_init(hdl, 5); v4l2_ctrl_new_std(hdl, &vicodec_ctrl_ops, V4L2_CID_MPEG_VIDEO_GOP_SIZE, 1, 16, 1, 10); v4l2_ctrl_new_std(hdl, &vicodec_ctrl_ops, V4L2_CID_FWHT_I_FRAME_QP, 1, 31, 1, 20); v4l2_ctrl_new_std(hdl, &vicodec_ctrl_ops, V4L2_CID_FWHT_P_FRAME_QP, 1, 31, 1, 20); if (ctx->is_stateless) v4l2_ctrl_new_custom(hdl, &vicodec_ctrl_stateless_state, NULL); else v4l2_ctrl_new_std(hdl, &vicodec_ctrl_ops, ctx->is_enc ? V4L2_CID_MIN_BUFFERS_FOR_OUTPUT : V4L2_CID_MIN_BUFFERS_FOR_CAPTURE, VICODEC_REC_BUFS, VICODEC_REC_BUFS, 1, VICODEC_REC_BUFS); if (hdl->error) { rc = hdl->error; v4l2_ctrl_handler_free(hdl); kfree(ctx); goto open_unlock; } ctx->fh.ctrl_handler = hdl; v4l2_ctrl_handler_setup(hdl); if (ctx->is_enc) ctx->q_data[V4L2_M2M_SRC].info = info; else if (ctx->is_stateless) ctx->q_data[V4L2_M2M_SRC].info = &pixfmt_stateless_fwht; else ctx->q_data[V4L2_M2M_SRC].info = &pixfmt_fwht; ctx->q_data[V4L2_M2M_SRC].coded_width = 1280; ctx->q_data[V4L2_M2M_SRC].coded_height = 720; ctx->q_data[V4L2_M2M_SRC].visible_width = 1280; ctx->q_data[V4L2_M2M_SRC].visible_height = 720; raw_size = 1280 * 720 * info->sizeimage_mult / info->sizeimage_div; comp_size = 1280 * 720 * pixfmt_fwht.sizeimage_mult / pixfmt_fwht.sizeimage_div; if (ctx->is_enc) ctx->q_data[V4L2_M2M_SRC].sizeimage = raw_size; else if (ctx->is_stateless) ctx->q_data[V4L2_M2M_SRC].sizeimage = comp_size; else ctx->q_data[V4L2_M2M_SRC].sizeimage = comp_size + sizeof(struct fwht_cframe_hdr); ctx->q_data[V4L2_M2M_DST] = ctx->q_data[V4L2_M2M_SRC]; if (ctx->is_enc) { ctx->q_data[V4L2_M2M_DST].info = &pixfmt_fwht; ctx->q_data[V4L2_M2M_DST].sizeimage = comp_size + sizeof(struct fwht_cframe_hdr); } else { ctx->q_data[V4L2_M2M_DST].info = info; ctx->q_data[V4L2_M2M_DST].sizeimage = raw_size; } ctx->state.colorspace = V4L2_COLORSPACE_REC709; if (ctx->is_enc) { ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->stateful_enc.m2m_dev, ctx, &queue_init); ctx->lock = &dev->stateful_enc.lock; } else if (ctx->is_stateless) { ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->stateless_dec.m2m_dev, ctx, &queue_init); ctx->lock = &dev->stateless_dec.lock; } else { ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->stateful_dec.m2m_dev, ctx, &queue_init); ctx->lock = &dev->stateful_dec.lock; } if (IS_ERR(ctx->fh.m2m_ctx)) { rc = PTR_ERR(ctx->fh.m2m_ctx); v4l2_ctrl_handler_free(hdl); v4l2_fh_exit(&ctx->fh); kfree(ctx); goto open_unlock; } v4l2_fh_add(&ctx->fh); open_unlock: mutex_unlock(vfd->lock); return rc; } static int vicodec_release(struct file *file) { struct video_device *vfd = video_devdata(file); struct vicodec_ctx *ctx = file2ctx(file); mutex_lock(vfd->lock); v4l2_m2m_ctx_release(ctx->fh.m2m_ctx); mutex_unlock(vfd->lock); v4l2_fh_del(&ctx->fh); v4l2_fh_exit(&ctx->fh); v4l2_ctrl_handler_free(&ctx->hdl); kvfree(ctx->state.compressed_frame); kfree(ctx); return 0; } static int vicodec_request_validate(struct media_request *req) { struct media_request_object *obj; struct v4l2_ctrl_handler *parent_hdl, *hdl; struct vicodec_ctx *ctx = NULL; struct v4l2_ctrl *ctrl; unsigned int count; list_for_each_entry(obj, &req->objects, list) { struct vb2_buffer *vb; if (vb2_request_object_is_buffer(obj)) { vb = container_of(obj, struct vb2_buffer, req_obj); ctx = vb2_get_drv_priv(vb->vb2_queue); break; } } if (!ctx) { pr_err("No buffer was provided with the request\n"); return -ENOENT; } count = vb2_request_buffer_cnt(req); if (!count) { v4l2_info(&ctx->dev->v4l2_dev, "No buffer was provided with the request\n"); return -ENOENT; } else if (count > 1) { v4l2_info(&ctx->dev->v4l2_dev, "More than one buffer was provided with the request\n"); return -EINVAL; } parent_hdl = &ctx->hdl; hdl = v4l2_ctrl_request_hdl_find(req, parent_hdl); if (!hdl) { v4l2_info(&ctx->dev->v4l2_dev, "Missing codec control\n"); return -ENOENT; } ctrl = v4l2_ctrl_request_hdl_ctrl_find(hdl, vicodec_ctrl_stateless_state.id); v4l2_ctrl_request_hdl_put(hdl); if (!ctrl) { v4l2_info(&ctx->dev->v4l2_dev, "Missing required codec control\n"); return -ENOENT; } return vb2_request_validate(req); } static const struct v4l2_file_operations vicodec_fops = { .owner = THIS_MODULE, .open = vicodec_open, .release = vicodec_release, .poll = v4l2_m2m_fop_poll, .unlocked_ioctl = video_ioctl2, .mmap = v4l2_m2m_fop_mmap, }; static const struct video_device vicodec_videodev = { .name = VICODEC_NAME, .vfl_dir = VFL_DIR_M2M, .fops = &vicodec_fops, .ioctl_ops = &vicodec_ioctl_ops, .minor = -1, .release = video_device_release_empty, }; static const struct media_device_ops vicodec_m2m_media_ops = { .req_validate = vicodec_request_validate, .req_queue = v4l2_m2m_request_queue, }; static const struct v4l2_m2m_ops m2m_ops = { .device_run = device_run, .job_ready = job_ready, }; static int register_instance(struct vicodec_dev *dev, struct vicodec_dev_instance *dev_instance, const char *name, bool is_enc, bool is_stateless) { struct video_device *vfd; int ret; spin_lock_init(&dev_instance->lock); mutex_init(&dev_instance->mutex); dev_instance->m2m_dev = v4l2_m2m_init(&m2m_ops); if (IS_ERR(dev_instance->m2m_dev)) { v4l2_err(&dev->v4l2_dev, "Failed to init vicodec enc device\n"); return PTR_ERR(dev_instance->m2m_dev); } dev_instance->vfd = vicodec_videodev; vfd = &dev_instance->vfd; vfd->lock = &dev_instance->mutex; vfd->v4l2_dev = &dev->v4l2_dev; strscpy(vfd->name, name, sizeof(vfd->name)); vfd->device_caps = V4L2_CAP_STREAMING | (multiplanar ? V4L2_CAP_VIDEO_M2M_MPLANE : V4L2_CAP_VIDEO_M2M); if (is_enc || is_stateless) { v4l2_disable_ioctl(vfd, VIDIOC_DECODER_CMD); v4l2_disable_ioctl(vfd, VIDIOC_TRY_DECODER_CMD); } if (!is_enc) { v4l2_disable_ioctl(vfd, VIDIOC_ENCODER_CMD); v4l2_disable_ioctl(vfd, VIDIOC_TRY_ENCODER_CMD); } video_set_drvdata(vfd, dev); ret = video_register_device(vfd, VFL_TYPE_VIDEO, 0); if (ret) { v4l2_err(&dev->v4l2_dev, "Failed to register video device '%s'\n", name); v4l2_m2m_release(dev_instance->m2m_dev); return ret; } v4l2_info(&dev->v4l2_dev, "Device '%s' registered as /dev/video%d\n", name, vfd->num); return 0; } static void vicodec_v4l2_dev_release(struct v4l2_device *v4l2_dev) { struct vicodec_dev *dev = container_of(v4l2_dev, struct vicodec_dev, v4l2_dev); v4l2_device_unregister(&dev->v4l2_dev); v4l2_m2m_release(dev->stateful_enc.m2m_dev); v4l2_m2m_release(dev->stateful_dec.m2m_dev); v4l2_m2m_release(dev->stateless_dec.m2m_dev); #ifdef CONFIG_MEDIA_CONTROLLER media_device_cleanup(&dev->mdev); #endif kfree(dev); } static int vicodec_probe(struct platform_device *pdev) { struct vicodec_dev *dev; int ret; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return -ENOMEM; ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev); if (ret) goto free_dev; dev->v4l2_dev.release = vicodec_v4l2_dev_release; #ifdef CONFIG_MEDIA_CONTROLLER dev->mdev.dev = &pdev->dev; strscpy(dev->mdev.model, "vicodec", sizeof(dev->mdev.model)); strscpy(dev->mdev.bus_info, "platform:vicodec", sizeof(dev->mdev.bus_info)); media_device_init(&dev->mdev); dev->mdev.ops = &vicodec_m2m_media_ops; dev->v4l2_dev.mdev = &dev->mdev; #endif platform_set_drvdata(pdev, dev); ret = register_instance(dev, &dev->stateful_enc, "stateful-encoder", true, false); if (ret) goto unreg_dev; ret = register_instance(dev, &dev->stateful_dec, "stateful-decoder", false, false); if (ret) goto unreg_sf_enc; ret = register_instance(dev, &dev->stateless_dec, "stateless-decoder", false, true); if (ret) goto unreg_sf_dec; #ifdef CONFIG_MEDIA_CONTROLLER ret = v4l2_m2m_register_media_controller(dev->stateful_enc.m2m_dev, &dev->stateful_enc.vfd, MEDIA_ENT_F_PROC_VIDEO_ENCODER); if (ret) { v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller for enc\n"); goto unreg_m2m; } ret = v4l2_m2m_register_media_controller(dev->stateful_dec.m2m_dev, &dev->stateful_dec.vfd, MEDIA_ENT_F_PROC_VIDEO_DECODER); if (ret) { v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller for dec\n"); goto unreg_m2m_sf_enc_mc; } ret = v4l2_m2m_register_media_controller(dev->stateless_dec.m2m_dev, &dev->stateless_dec.vfd, MEDIA_ENT_F_PROC_VIDEO_DECODER); if (ret) { v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller for stateless dec\n"); goto unreg_m2m_sf_dec_mc; } ret = media_device_register(&dev->mdev); if (ret) { v4l2_err(&dev->v4l2_dev, "Failed to register mem2mem media device\n"); goto unreg_m2m_sl_dec_mc; } #endif return 0; #ifdef CONFIG_MEDIA_CONTROLLER unreg_m2m_sl_dec_mc: v4l2_m2m_unregister_media_controller(dev->stateless_dec.m2m_dev); unreg_m2m_sf_dec_mc: v4l2_m2m_unregister_media_controller(dev->stateful_dec.m2m_dev); unreg_m2m_sf_enc_mc: v4l2_m2m_unregister_media_controller(dev->stateful_enc.m2m_dev); unreg_m2m: video_unregister_device(&dev->stateless_dec.vfd); v4l2_m2m_release(dev->stateless_dec.m2m_dev); #endif unreg_sf_dec: video_unregister_device(&dev->stateful_dec.vfd); v4l2_m2m_release(dev->stateful_dec.m2m_dev); unreg_sf_enc: video_unregister_device(&dev->stateful_enc.vfd); v4l2_m2m_release(dev->stateful_enc.m2m_dev); unreg_dev: v4l2_device_unregister(&dev->v4l2_dev); free_dev: kfree(dev); return ret; } static void vicodec_remove(struct platform_device *pdev) { struct vicodec_dev *dev = platform_get_drvdata(pdev); v4l2_info(&dev->v4l2_dev, "Removing " VICODEC_NAME); #ifdef CONFIG_MEDIA_CONTROLLER media_device_unregister(&dev->mdev); v4l2_m2m_unregister_media_controller(dev->stateful_enc.m2m_dev); v4l2_m2m_unregister_media_controller(dev->stateful_dec.m2m_dev); v4l2_m2m_unregister_media_controller(dev->stateless_dec.m2m_dev); #endif video_unregister_device(&dev->stateful_enc.vfd); video_unregister_device(&dev->stateful_dec.vfd); video_unregister_device(&dev->stateless_dec.vfd); v4l2_device_put(&dev->v4l2_dev); } static struct platform_driver vicodec_pdrv = { .probe = vicodec_probe, .remove = vicodec_remove, .driver = { .name = VICODEC_NAME, }, }; static void __exit vicodec_exit(void) { platform_driver_unregister(&vicodec_pdrv); platform_device_unregister(&vicodec_pdev); } static int __init vicodec_init(void) { int ret; ret = platform_device_register(&vicodec_pdev); if (ret) return ret; ret = platform_driver_register(&vicodec_pdrv); if (ret) platform_device_unregister(&vicodec_pdev); return ret; } module_init(vicodec_init); module_exit(vicodec_exit); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2007-2012 Nicira, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/if_arp.h> #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/kernel.h> #include <linux/llc.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/openvswitch.h> #include <linux/export.h> #include <net/ip_tunnels.h> #include <net/rtnetlink.h> #include "datapath.h" #include "vport.h" #include "vport-internal_dev.h" #include "vport-netdev.h" static struct vport_ops ovs_netdev_vport_ops; /* Must be called with rcu_read_lock. */ static void netdev_port_receive(struct sk_buff *skb) { struct vport *vport; vport = ovs_netdev_get_vport(skb->dev); if (unlikely(!vport)) goto error; if (unlikely(skb_warn_if_lro(skb))) goto error; /* Make our own copy of the packet. Otherwise we will mangle the * packet for anyone who came before us (e.g. tcpdump via AF_PACKET). */ skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) return; if (skb->dev->type == ARPHRD_ETHER) skb_push_rcsum(skb, ETH_HLEN); ovs_vport_receive(vport, skb, skb_tunnel_info(skb)); return; error: kfree_skb(skb); } /* Called with rcu_read_lock and bottom-halves disabled. */ static rx_handler_result_t netdev_frame_hook(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; netdev_port_receive(skb); return RX_HANDLER_CONSUMED; } static struct net_device *get_dpdev(const struct datapath *dp) { struct vport *local; local = ovs_vport_ovsl(dp, OVSP_LOCAL); return local->dev; } struct vport *ovs_netdev_link(struct vport *vport, const char *name) { int err; vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), name); if (!vport->dev) { err = -ENODEV; goto error_free_vport; } /* Ensure that the device exists and that the provided * name is not one of its aliases. */ if (strcmp(name, ovs_vport_name(vport))) { err = -ENODEV; goto error_put; } netdev_tracker_alloc(vport->dev, &vport->dev_tracker, GFP_KERNEL); if (vport->dev->flags & IFF_LOOPBACK || (vport->dev->type != ARPHRD_ETHER && vport->dev->type != ARPHRD_NONE) || ovs_is_internal_dev(vport->dev)) { err = -EINVAL; goto error_put; } rtnl_lock(); err = netdev_master_upper_dev_link(vport->dev, get_dpdev(vport->dp), NULL, NULL, NULL); if (err) goto error_unlock; err = netdev_rx_handler_register(vport->dev, netdev_frame_hook, vport); if (err) goto error_master_upper_dev_unlink; dev_disable_lro(vport->dev); dev_set_promiscuity(vport->dev, 1); vport->dev->priv_flags |= IFF_OVS_DATAPATH; rtnl_unlock(); return vport; error_master_upper_dev_unlink: netdev_upper_dev_unlink(vport->dev, get_dpdev(vport->dp)); error_unlock: rtnl_unlock(); error_put: netdev_put(vport->dev, &vport->dev_tracker); error_free_vport: ovs_vport_free(vport); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(ovs_netdev_link); static struct vport *netdev_create(const struct vport_parms *parms) { struct vport *vport; vport = ovs_vport_alloc(0, &ovs_netdev_vport_ops, parms); if (IS_ERR(vport)) return vport; return ovs_netdev_link(vport, parms->name); } static void vport_netdev_free(struct rcu_head *rcu) { struct vport *vport = container_of(rcu, struct vport, rcu); netdev_put(vport->dev, &vport->dev_tracker); ovs_vport_free(vport); } void ovs_netdev_detach_dev(struct vport *vport) { ASSERT_RTNL(); vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; netdev_rx_handler_unregister(vport->dev); netdev_upper_dev_unlink(vport->dev, netdev_master_upper_dev_get(vport->dev)); dev_set_promiscuity(vport->dev, -1); } static void netdev_destroy(struct vport *vport) { rtnl_lock(); if (netif_is_ovs_port(vport->dev)) ovs_netdev_detach_dev(vport); rtnl_unlock(); call_rcu(&vport->rcu, vport_netdev_free); } void ovs_netdev_tunnel_destroy(struct vport *vport) { rtnl_lock(); if (netif_is_ovs_port(vport->dev)) ovs_netdev_detach_dev(vport); /* We can be invoked by both explicit vport deletion and * underlying netdev deregistration; delete the link only * if it's not already shutting down. */ if (vport->dev->reg_state == NETREG_REGISTERED) rtnl_delete_link(vport->dev, 0, NULL); netdev_put(vport->dev, &vport->dev_tracker); vport->dev = NULL; rtnl_unlock(); call_rcu(&vport->rcu, vport_netdev_free); } EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy); /* Returns null if this device is not attached to a datapath. */ struct vport *ovs_netdev_get_vport(struct net_device *dev) { if (likely(netif_is_ovs_port(dev))) return (struct vport *) rcu_dereference_rtnl(dev->rx_handler_data); else return NULL; } static struct vport_ops ovs_netdev_vport_ops = { .type = OVS_VPORT_TYPE_NETDEV, .create = netdev_create, .destroy = netdev_destroy, .send = dev_queue_xmit, }; int __init ovs_netdev_init(void) { return ovs_vport_ops_register(&ovs_netdev_vport_ops); } void ovs_netdev_exit(void) { ovs_vport_ops_unregister(&ovs_netdev_vport_ops); } |
| 2 1 1 13 1 1 2 2 2 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar * Copyright (C) 2005-2006, Thomas Gleixner, Russell King * * This file contains the interrupt descriptor management code. Detailed * information is available in Documentation/core-api/genericirq.rst * */ #include <linux/irq.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/maple_tree.h> #include <linux/irqdomain.h> #include <linux/sysfs.h> #include <linux/string_choices.h> #include "internals.h" /* * lockdep: we want to handle all irq_desc locks as a single lock-class: */ static struct lock_class_key irq_desc_lock_class; #if defined(CONFIG_SMP) static int __init irq_affinity_setup(char *str) { alloc_bootmem_cpumask_var(&irq_default_affinity); cpulist_parse(str, irq_default_affinity); /* * Set at least the boot cpu. We don't want to end up with * bugreports caused by random commandline masks */ cpumask_set_cpu(smp_processor_id(), irq_default_affinity); return 1; } __setup("irqaffinity=", irq_affinity_setup); static void __init init_irq_default_affinity(void) { if (!cpumask_available(irq_default_affinity)) zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); if (cpumask_empty(irq_default_affinity)) cpumask_setall(irq_default_affinity); } #else static void __init init_irq_default_affinity(void) { } #endif #ifdef CONFIG_SMP static int alloc_masks(struct irq_desc *desc, int node) { if (!zalloc_cpumask_var_node(&desc->irq_common_data.affinity, GFP_KERNEL, node)) return -ENOMEM; #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK if (!zalloc_cpumask_var_node(&desc->irq_common_data.effective_affinity, GFP_KERNEL, node)) { free_cpumask_var(desc->irq_common_data.affinity); return -ENOMEM; } #endif #ifdef CONFIG_GENERIC_PENDING_IRQ if (!zalloc_cpumask_var_node(&desc->pending_mask, GFP_KERNEL, node)) { #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK free_cpumask_var(desc->irq_common_data.effective_affinity); #endif free_cpumask_var(desc->irq_common_data.affinity); return -ENOMEM; } #endif return 0; } static void desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { if (!affinity) affinity = irq_default_affinity; cpumask_copy(desc->irq_common_data.affinity, affinity); #ifdef CONFIG_GENERIC_PENDING_IRQ cpumask_clear(desc->pending_mask); #endif #ifdef CONFIG_NUMA desc->irq_common_data.node = node; #endif } static void free_masks(struct irq_desc *desc) { #ifdef CONFIG_GENERIC_PENDING_IRQ free_cpumask_var(desc->pending_mask); #endif free_cpumask_var(desc->irq_common_data.affinity); #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK free_cpumask_var(desc->irq_common_data.effective_affinity); #endif } #else static inline int alloc_masks(struct irq_desc *desc, int node) { return 0; } static inline void desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { } static inline void free_masks(struct irq_desc *desc) { } #endif static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, const struct cpumask *affinity, struct module *owner) { int cpu; desc->irq_common_data.handler_data = NULL; desc->irq_common_data.msi_desc = NULL; desc->irq_data.common = &desc->irq_common_data; desc->irq_data.irq = irq; desc->irq_data.chip = &no_irq_chip; desc->irq_data.chip_data = NULL; irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS); irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); desc->handle_irq = handle_bad_irq; desc->depth = 1; desc->irq_count = 0; desc->irqs_unhandled = 0; desc->tot_count = 0; desc->name = NULL; desc->owner = owner; for_each_possible_cpu(cpu) *per_cpu_ptr(desc->kstat_irqs, cpu) = (struct irqstat) { }; desc_smp_init(desc, node, affinity); } static unsigned int nr_irqs = NR_IRQS; /** * irq_get_nr_irqs() - Number of interrupts supported by the system. */ unsigned int irq_get_nr_irqs(void) { return nr_irqs; } EXPORT_SYMBOL_GPL(irq_get_nr_irqs); /** * irq_set_nr_irqs() - Set the number of interrupts supported by the system. * @nr: New number of interrupts. * * Return: @nr. */ unsigned int irq_set_nr_irqs(unsigned int nr) { nr_irqs = nr; return nr; } EXPORT_SYMBOL_GPL(irq_set_nr_irqs); static DEFINE_MUTEX(sparse_irq_lock); static struct maple_tree sparse_irqs = MTREE_INIT_EXT(sparse_irqs, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | MT_FLAGS_USE_RCU, sparse_irq_lock); static int irq_find_free_area(unsigned int from, unsigned int cnt) { MA_STATE(mas, &sparse_irqs, 0, 0); if (mas_empty_area(&mas, from, MAX_SPARSE_IRQS, cnt)) return -ENOSPC; return mas.index; } static unsigned int irq_find_at_or_after(unsigned int offset) { unsigned long index = offset; struct irq_desc *desc; guard(rcu)(); desc = mt_find(&sparse_irqs, &index, nr_irqs); return desc ? irq_desc_get_irq(desc) : nr_irqs; } static void irq_insert_desc(unsigned int irq, struct irq_desc *desc) { MA_STATE(mas, &sparse_irqs, irq, irq); WARN_ON(mas_store_gfp(&mas, desc, GFP_KERNEL) != 0); } static void delete_irq_desc(unsigned int irq) { MA_STATE(mas, &sparse_irqs, irq, irq); mas_erase(&mas); } #ifdef CONFIG_SPARSE_IRQ static const struct kobj_type irq_kobj_type; #endif static int init_desc(struct irq_desc *desc, int irq, int node, unsigned int flags, const struct cpumask *affinity, struct module *owner) { desc->kstat_irqs = alloc_percpu(struct irqstat); if (!desc->kstat_irqs) return -ENOMEM; if (alloc_masks(desc, node)) { free_percpu(desc->kstat_irqs); return -ENOMEM; } raw_spin_lock_init(&desc->lock); lockdep_set_class(&desc->lock, &irq_desc_lock_class); mutex_init(&desc->request_mutex); init_waitqueue_head(&desc->wait_for_threads); desc_set_defaults(irq, desc, node, affinity, owner); irqd_set(&desc->irq_data, flags); irq_resend_init(desc); #ifdef CONFIG_SPARSE_IRQ kobject_init(&desc->kobj, &irq_kobj_type); init_rcu_head(&desc->rcu); #endif return 0; } #ifdef CONFIG_SPARSE_IRQ static void irq_kobj_release(struct kobject *kobj); #ifdef CONFIG_SYSFS static struct kobject *irq_kobj_base; #define IRQ_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) static ssize_t per_cpu_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; char *p = ""; int cpu; for_each_possible_cpu(cpu) { unsigned int c = irq_desc_kstat_cpu(desc, cpu); ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%u", p, c); p = ","; } ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n"); return ret; } IRQ_ATTR_RO(per_cpu_count); static ssize_t chip_name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); if (desc->irq_data.chip && desc->irq_data.chip->name) { ret = scnprintf(buf, PAGE_SIZE, "%s\n", desc->irq_data.chip->name); } raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(chip_name); static ssize_t hwirq_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); if (desc->irq_data.domain) ret = sprintf(buf, "%lu\n", desc->irq_data.hwirq); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(hwirq); static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); ret = sprintf(buf, "%s\n", irqd_is_level_type(&desc->irq_data) ? "level" : "edge"); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(type); static ssize_t wakeup_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); ret = sprintf(buf, "%s\n", str_enabled_disabled(irqd_is_wakeup_set(&desc->irq_data))); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(wakeup); static ssize_t name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); if (desc->name) ret = scnprintf(buf, PAGE_SIZE, "%s\n", desc->name); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(name); static ssize_t actions_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); struct irqaction *action; ssize_t ret = 0; char *p = ""; raw_spin_lock_irq(&desc->lock); for_each_action_of_desc(desc, action) { ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s", p, action->name); p = ","; } raw_spin_unlock_irq(&desc->lock); if (ret) ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n"); return ret; } IRQ_ATTR_RO(actions); static struct attribute *irq_attrs[] = { &per_cpu_count_attr.attr, &chip_name_attr.attr, &hwirq_attr.attr, &type_attr.attr, &wakeup_attr.attr, &name_attr.attr, &actions_attr.attr, NULL }; ATTRIBUTE_GROUPS(irq); static const struct kobj_type irq_kobj_type = { .release = irq_kobj_release, .sysfs_ops = &kobj_sysfs_ops, .default_groups = irq_groups, }; static void irq_sysfs_add(int irq, struct irq_desc *desc) { if (irq_kobj_base) { /* * Continue even in case of failure as this is nothing * crucial and failures in the late irq_sysfs_init() * cannot be rolled back. */ if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq)) pr_warn("Failed to add kobject for irq %d\n", irq); else desc->istate |= IRQS_SYSFS; } } static void irq_sysfs_del(struct irq_desc *desc) { /* * Only invoke kobject_del() when kobject_add() was successfully * invoked for the descriptor. This covers both early boot, where * sysfs is not initialized yet, and the case of a failed * kobject_add() invocation. */ if (desc->istate & IRQS_SYSFS) kobject_del(&desc->kobj); } static int __init irq_sysfs_init(void) { struct irq_desc *desc; int irq; /* Prevent concurrent irq alloc/free */ irq_lock_sparse(); irq_kobj_base = kobject_create_and_add("irq", kernel_kobj); if (!irq_kobj_base) { irq_unlock_sparse(); return -ENOMEM; } /* Add the already allocated interrupts */ for_each_irq_desc(irq, desc) irq_sysfs_add(irq, desc); irq_unlock_sparse(); return 0; } postcore_initcall(irq_sysfs_init); #else /* !CONFIG_SYSFS */ static const struct kobj_type irq_kobj_type = { .release = irq_kobj_release, }; static void irq_sysfs_add(int irq, struct irq_desc *desc) {} static void irq_sysfs_del(struct irq_desc *desc) {} #endif /* CONFIG_SYSFS */ struct irq_desc *irq_to_desc(unsigned int irq) { return mtree_load(&sparse_irqs, irq); } #ifdef CONFIG_KVM_BOOK3S_64_HV_MODULE EXPORT_SYMBOL_GPL(irq_to_desc); #endif void irq_lock_sparse(void) { mutex_lock(&sparse_irq_lock); } void irq_unlock_sparse(void) { mutex_unlock(&sparse_irq_lock); } static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, const struct cpumask *affinity, struct module *owner) { struct irq_desc *desc; int ret; desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node); if (!desc) return NULL; ret = init_desc(desc, irq, node, flags, affinity, owner); if (unlikely(ret)) { kfree(desc); return NULL; } return desc; } static void irq_kobj_release(struct kobject *kobj) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); free_masks(desc); free_percpu(desc->kstat_irqs); kfree(desc); } static void delayed_free_desc(struct rcu_head *rhp) { struct irq_desc *desc = container_of(rhp, struct irq_desc, rcu); kobject_put(&desc->kobj); } static void free_desc(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); irq_remove_debugfs_entry(desc); unregister_irq_proc(irq, desc); /* * sparse_irq_lock protects also show_interrupts() and * kstat_irq_usr(). Once we deleted the descriptor from the * sparse tree we can free it. Access in proc will fail to * lookup the descriptor. * * The sysfs entry must be serialized against a concurrent * irq_sysfs_init() as well. */ irq_sysfs_del(desc); delete_irq_desc(irq); /* * We free the descriptor, masks and stat fields via RCU. That * allows demultiplex interrupts to do rcu based management of * the child interrupts. * This also allows us to use rcu in kstat_irqs_usr(). */ call_rcu(&desc->rcu, delayed_free_desc); } static int alloc_descs(unsigned int start, unsigned int cnt, int node, const struct irq_affinity_desc *affinity, struct module *owner) { struct irq_desc *desc; int i; /* Validate affinity mask(s) */ if (affinity) { for (i = 0; i < cnt; i++) { if (cpumask_empty(&affinity[i].mask)) return -EINVAL; } } for (i = 0; i < cnt; i++) { const struct cpumask *mask = NULL; unsigned int flags = 0; if (affinity) { if (affinity->is_managed) { flags = IRQD_AFFINITY_MANAGED | IRQD_MANAGED_SHUTDOWN; } flags |= IRQD_AFFINITY_SET; mask = &affinity->mask; node = cpu_to_node(cpumask_first(mask)); affinity++; } desc = alloc_desc(start + i, node, flags, mask, owner); if (!desc) goto err; irq_insert_desc(start + i, desc); irq_sysfs_add(start + i, desc); irq_add_debugfs_entry(start + i, desc); } return start; err: for (i--; i >= 0; i--) free_desc(start + i); return -ENOMEM; } static int irq_expand_nr_irqs(unsigned int nr) { if (nr > MAX_SPARSE_IRQS) return -ENOMEM; nr_irqs = nr; return 0; } int __init early_irq_init(void) { int i, initcnt, node = first_online_node; struct irq_desc *desc; init_irq_default_affinity(); /* Let arch update nr_irqs and return the nr of preallocated irqs */ initcnt = arch_probe_nr_irqs(); printk(KERN_INFO "NR_IRQS: %d, nr_irqs: %d, preallocated irqs: %d\n", NR_IRQS, nr_irqs, initcnt); if (WARN_ON(nr_irqs > MAX_SPARSE_IRQS)) nr_irqs = MAX_SPARSE_IRQS; if (WARN_ON(initcnt > MAX_SPARSE_IRQS)) initcnt = MAX_SPARSE_IRQS; if (initcnt > nr_irqs) nr_irqs = initcnt; for (i = 0; i < initcnt; i++) { desc = alloc_desc(i, node, 0, NULL, NULL); irq_insert_desc(i, desc); } return arch_early_irq_init(); } #else /* !CONFIG_SPARSE_IRQ */ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { [0 ... NR_IRQS-1] = { .handle_irq = handle_bad_irq, .depth = 1, .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock), } }; int __init early_irq_init(void) { int count, i, node = first_online_node; int ret; init_irq_default_affinity(); printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS); count = ARRAY_SIZE(irq_desc); for (i = 0; i < count; i++) { ret = init_desc(irq_desc + i, i, node, 0, NULL, NULL); if (unlikely(ret)) goto __free_desc_res; } return arch_early_irq_init(); __free_desc_res: while (--i >= 0) { free_masks(irq_desc + i); free_percpu(irq_desc[i].kstat_irqs); } return ret; } struct irq_desc *irq_to_desc(unsigned int irq) { return (irq < NR_IRQS) ? irq_desc + irq : NULL; } EXPORT_SYMBOL(irq_to_desc); static void free_desc(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; raw_spin_lock_irqsave(&desc->lock, flags); desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL); raw_spin_unlock_irqrestore(&desc->lock, flags); delete_irq_desc(irq); } static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, const struct irq_affinity_desc *affinity, struct module *owner) { u32 i; for (i = 0; i < cnt; i++) { struct irq_desc *desc = irq_to_desc(start + i); desc->owner = owner; irq_insert_desc(start + i, desc); } return start; } static int irq_expand_nr_irqs(unsigned int nr) { return -ENOMEM; } void irq_mark_irq(unsigned int irq) { mutex_lock(&sparse_irq_lock); irq_insert_desc(irq, irq_desc + irq); mutex_unlock(&sparse_irq_lock); } #ifdef CONFIG_GENERIC_IRQ_LEGACY void irq_init_desc(unsigned int irq) { free_desc(irq); } #endif #endif /* !CONFIG_SPARSE_IRQ */ int handle_irq_desc(struct irq_desc *desc) { struct irq_data *data; if (!desc) return -EINVAL; data = irq_desc_get_irq_data(desc); if (WARN_ON_ONCE(!in_hardirq() && irqd_is_handle_enforce_irqctx(data))) return -EPERM; generic_handle_irq_desc(desc); return 0; } /** * generic_handle_irq - Invoke the handler for a particular irq * @irq: The irq number to handle * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an IRQ context with irq regs * initialized. */ int generic_handle_irq(unsigned int irq) { return handle_irq_desc(irq_to_desc(irq)); } EXPORT_SYMBOL_GPL(generic_handle_irq); /** * generic_handle_irq_safe - Invoke the handler for a particular irq from any * context. * @irq: The irq number to handle * * Returns: 0 on success, a negative value on error. * * This function can be called from any context (IRQ or process context). It * will report an error if not invoked from IRQ context and the irq has been * marked to enforce IRQ-context only. */ int generic_handle_irq_safe(unsigned int irq) { unsigned long flags; int ret; local_irq_save(flags); ret = handle_irq_desc(irq_to_desc(irq)); local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(generic_handle_irq_safe); #ifdef CONFIG_IRQ_DOMAIN /** * generic_handle_domain_irq - Invoke the handler for a HW irq belonging * to a domain. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an IRQ context with irq regs * initialized. */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq) { return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } EXPORT_SYMBOL_GPL(generic_handle_domain_irq); /** * generic_handle_irq_safe - Invoke the handler for a HW irq belonging * to a domain from any context. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, a negative value on error. * * This function can be called from any context (IRQ or process * context). If the interrupt is marked as 'enforce IRQ-context only' then * the function must be invoked from hard interrupt context. */ int generic_handle_domain_irq_safe(struct irq_domain *domain, unsigned int hwirq) { unsigned long flags; int ret; local_irq_save(flags); ret = handle_irq_desc(irq_resolve_mapping(domain, hwirq)); local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(generic_handle_domain_irq_safe); /** * generic_handle_domain_nmi - Invoke the handler for a HW nmi belonging * to a domain. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an NMI context with irq regs * initialized. **/ int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq) { WARN_ON_ONCE(!in_nmi()); return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } #endif /* Dynamic interrupt handling */ /** * irq_free_descs - free irq descriptors * @from: Start of descriptor range * @cnt: Number of consecutive irqs to free */ void irq_free_descs(unsigned int from, unsigned int cnt) { int i; if (from >= nr_irqs || (from + cnt) > nr_irqs) return; mutex_lock(&sparse_irq_lock); for (i = 0; i < cnt; i++) free_desc(from + i); mutex_unlock(&sparse_irq_lock); } EXPORT_SYMBOL_GPL(irq_free_descs); /** * __irq_alloc_descs - allocate and initialize a range of irq descriptors * @irq: Allocate for specific irq number if irq >= 0 * @from: Start the search from this irq number * @cnt: Number of consecutive irqs to allocate. * @node: Preferred node on which the irq descriptor should be allocated * @owner: Owning module (can be NULL) * @affinity: Optional pointer to an affinity mask array of size @cnt which * hints where the irq descriptors should be allocated and which * default affinities to use * * Returns the first irq number or error code */ int __ref __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, struct module *owner, const struct irq_affinity_desc *affinity) { int start, ret; if (!cnt) return -EINVAL; if (irq >= 0) { if (from > irq) return -EINVAL; from = irq; } else { /* * For interrupts which are freely allocated the * architecture can force a lower bound to the @from * argument. x86 uses this to exclude the GSI space. */ from = arch_dynirq_lower_bound(from); } mutex_lock(&sparse_irq_lock); start = irq_find_free_area(from, cnt); ret = -EEXIST; if (irq >=0 && start != irq) goto unlock; if (start + cnt > nr_irqs) { ret = irq_expand_nr_irqs(start + cnt); if (ret) goto unlock; } ret = alloc_descs(start, cnt, node, affinity, owner); unlock: mutex_unlock(&sparse_irq_lock); return ret; } EXPORT_SYMBOL_GPL(__irq_alloc_descs); /** * irq_get_next_irq - get next allocated irq number * @offset: where to start the search * * Returns next irq number after offset or nr_irqs if none is found. */ unsigned int irq_get_next_irq(unsigned int offset) { return irq_find_at_or_after(offset); } struct irq_desc * __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, unsigned int check) { struct irq_desc *desc = irq_to_desc(irq); if (desc) { if (check & _IRQ_DESC_CHECK) { if ((check & _IRQ_DESC_PERCPU) && !irq_settings_is_per_cpu_devid(desc)) return NULL; if (!(check & _IRQ_DESC_PERCPU) && irq_settings_is_per_cpu_devid(desc)) return NULL; } if (bus) chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, *flags); } return desc; } void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus) __releases(&desc->lock) { raw_spin_unlock_irqrestore(&desc->lock, flags); if (bus) chip_bus_sync_unlock(desc); } int irq_set_percpu_devid_partition(unsigned int irq, const struct cpumask *affinity) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || desc->percpu_enabled) return -EINVAL; desc->percpu_enabled = kzalloc(sizeof(*desc->percpu_enabled), GFP_KERNEL); if (!desc->percpu_enabled) return -ENOMEM; desc->percpu_affinity = affinity ? : cpu_possible_mask; irq_set_percpu_devid_flags(irq); return 0; } int irq_set_percpu_devid(unsigned int irq) { return irq_set_percpu_devid_partition(irq, NULL); } int irq_get_percpu_devid_partition(unsigned int irq, struct cpumask *affinity) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !desc->percpu_enabled) return -EINVAL; if (affinity) cpumask_copy(affinity, desc->percpu_affinity); return 0; } EXPORT_SYMBOL_GPL(irq_get_percpu_devid_partition); void kstat_incr_irq_this_cpu(unsigned int irq) { kstat_incr_irqs_this_cpu(irq_to_desc(irq)); } /** * kstat_irqs_cpu - Get the statistics for an interrupt on a cpu * @irq: The interrupt number * @cpu: The cpu number * * Returns the sum of interrupt counts on @cpu since boot for * @irq. The caller must ensure that the interrupt is not removed * concurrently. */ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { struct irq_desc *desc = irq_to_desc(irq); return desc && desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; } static unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask) { unsigned int sum = 0; int cpu; if (!irq_settings_is_per_cpu_devid(desc) && !irq_settings_is_per_cpu(desc) && !irq_is_nmi(desc)) return data_race(desc->tot_count); for_each_cpu(cpu, cpumask) sum += data_race(per_cpu(desc->kstat_irqs->cnt, cpu)); return sum; } static unsigned int kstat_irqs(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !desc->kstat_irqs) return 0; return kstat_irqs_desc(desc, cpu_possible_mask); } #ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT void kstat_snapshot_irqs(void) { struct irq_desc *desc; unsigned int irq; for_each_irq_desc(irq, desc) { if (!desc->kstat_irqs) continue; this_cpu_write(desc->kstat_irqs->ref, this_cpu_read(desc->kstat_irqs->cnt)); } } unsigned int kstat_get_irq_since_snapshot(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !desc->kstat_irqs) return 0; return this_cpu_read(desc->kstat_irqs->cnt) - this_cpu_read(desc->kstat_irqs->ref); } #endif /** * kstat_irqs_usr - Get the statistics for an interrupt from thread context * @irq: The interrupt number * * Returns the sum of interrupt counts on all cpus since boot for @irq. * * It uses rcu to protect the access since a concurrent removal of an * interrupt descriptor is observing an rcu grace period before * delayed_free_desc()/irq_kobj_release(). */ unsigned int kstat_irqs_usr(unsigned int irq) { unsigned int sum; rcu_read_lock(); sum = kstat_irqs(irq); rcu_read_unlock(); return sum; } #ifdef CONFIG_LOCKDEP void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class, struct lock_class_key *request_class) { struct irq_desc *desc = irq_to_desc(irq); if (desc) { lockdep_set_class(&desc->lock, lock_class); lockdep_set_class(&desc->request_mutex, request_class); } } EXPORT_SYMBOL_GPL(__irq_set_lockdep_class); #endif |
| 5138 89 89 55 7967 7961 7976 | 1 2 3 4 5 6 7 8 9 10 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/export.h> #include <linux/fault-inject-usercopy.h> #include <linux/kasan-checks.h> #include <linux/thread_info.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/mm.h> #include <asm/byteorder.h> #include <asm/word-at-a-time.h> #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS #define IS_UNALIGNED(src, dst) 0 #else #define IS_UNALIGNED(src, dst) \ (((long) dst | (long) src) & (sizeof(long) - 1)) #endif /* * Do a strncpy, return length of string without final '\0'. * 'count' is the user-supplied count (return 'count' if we * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ static __always_inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; while (max >= sizeof(unsigned long)) { unsigned long c, data, mask; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); /* * Note that we mask out the bytes following the NUL. This is * important to do because string oblivious code may read past * the NUL. For those routines, we don't want to give them * potentially random bytes after the NUL in `src`. * * One example of such code is BPF map keys. BPF treats map keys * as an opaque set of bytes. Without the post-NUL mask, any BPF * maps keyed by strings returned from strncpy_from_user() may * have multiple entries for semantically identical strings. */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); mask = zero_bytemask(data); *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } *(unsigned long *)(dst+res) = c; res += sizeof(unsigned long); max -= sizeof(unsigned long); } byte_at_a_time: while (max) { char c; unsafe_get_user(c,src+res, efault); dst[res] = c; if (!c) return res; res++; max--; } /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, that's ok - we got as much as the user asked for. */ if (res >= count) return res; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's an EFAULT. */ efault: return -EFAULT; } /** * strncpy_from_user: - Copy a NUL terminated string from userspace. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @src: Source address, in user space. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from userspace to kernel space. * * On success, returns the length of the string (not including the trailing * NUL). * * If access to userspace fails, returns -EFAULT (some data may have been * copied). * * If @count is smaller than the length of the string, copies @count bytes * and returns @count. */ long strncpy_from_user(char *dst, const char __user *src, long count) { unsigned long max_addr, src_addr; might_fault(); if (should_fail_usercopy()) return -EFAULT; if (unlikely(count <= 0)) return 0; kasan_check_write(dst, count); check_object_size(dst, count, false); if (can_do_masked_user_access()) { long retval; src = masked_user_access_begin(src); retval = do_strncpy_from_user(dst, src, count, count); user_read_access_end(); return retval; } max_addr = TASK_SIZE_MAX; src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; if (user_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_read_access_end(); return retval; } } return -EFAULT; } EXPORT_SYMBOL(strncpy_from_user); |
| 21 6 22 6 22 21 | 1 2 3 4 5 6 7 8 9 10 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Key permission checking * * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/export.h> #include <linux/security.h> #include "internal.h" /** * key_task_permission - Check a key can be used * @key_ref: The key to check. * @cred: The credentials to use. * @need_perm: The permission required. * * Check to see whether permission is granted to use a key in the desired way, * but permit the security modules to override. * * The caller must hold either a ref on cred or must hold the RCU readlock. * * Returns 0 if successful, -EACCES if access is denied based on the * permissions bits or the LSM check. */ int key_task_permission(const key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { struct key *key; key_perm_t kperm, mask; int ret; switch (need_perm) { default: WARN_ON(1); return -EACCES; case KEY_NEED_UNLINK: case KEY_SYSADMIN_OVERRIDE: case KEY_AUTHTOKEN_OVERRIDE: case KEY_DEFER_PERM_CHECK: goto lsm; case KEY_NEED_VIEW: mask = KEY_OTH_VIEW; break; case KEY_NEED_READ: mask = KEY_OTH_READ; break; case KEY_NEED_WRITE: mask = KEY_OTH_WRITE; break; case KEY_NEED_SEARCH: mask = KEY_OTH_SEARCH; break; case KEY_NEED_LINK: mask = KEY_OTH_LINK; break; case KEY_NEED_SETATTR: mask = KEY_OTH_SETATTR; break; } key = key_ref_to_ptr(key_ref); /* use the second 8-bits of permissions for keys the caller owns */ if (uid_eq(key->uid, cred->fsuid)) { kperm = key->perm >> 16; goto use_these_perms; } /* use the third 8-bits of permissions for keys the caller has a group * membership in common with */ if (gid_valid(key->gid) && key->perm & KEY_GRP_ALL) { if (gid_eq(key->gid, cred->fsgid)) { kperm = key->perm >> 8; goto use_these_perms; } ret = groups_search(cred->group_info, key->gid); if (ret) { kperm = key->perm >> 8; goto use_these_perms; } } /* otherwise use the least-significant 8-bits */ kperm = key->perm; use_these_perms: /* use the top 8-bits of permissions for keys the caller possesses * - possessor permissions are additive with other permissions */ if (is_key_possessed(key_ref)) kperm |= key->perm >> 24; if ((kperm & mask) != mask) return -EACCES; /* let LSM be the final arbiter */ lsm: return security_key_permission(key_ref, cred, need_perm); } EXPORT_SYMBOL(key_task_permission); /** * key_validate - Validate a key. * @key: The key to be validated. * * Check that a key is valid, returning 0 if the key is okay, -ENOKEY if the * key is invalidated, -EKEYREVOKED if the key's type has been removed or if * the key has been revoked or -EKEYEXPIRED if the key has expired. */ int key_validate(const struct key *key) { unsigned long flags = READ_ONCE(key->flags); time64_t expiry = READ_ONCE(key->expiry); if (flags & (1 << KEY_FLAG_INVALIDATED)) return -ENOKEY; /* check it's still accessible */ if (flags & ((1 << KEY_FLAG_REVOKED) | (1 << KEY_FLAG_DEAD))) return -EKEYREVOKED; /* check it hasn't expired */ if (expiry) { if (ktime_get_real_seconds() >= expiry) return -EKEYEXPIRED; } return 0; } EXPORT_SYMBOL(key_validate); |
| 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 | // 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) */ |
| 5 3 1 2 5 5 5 2 6 1 5 2 43 43 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * * export.c */ /* * This file implements code to make Squashfs filesystems exportable (NFS etc.) * * The export code uses an inode lookup table to map inode numbers passed in * filehandles to an inode location on disk. This table is stored compressed * into metadata blocks. A second index table is used to locate these. This * second index table for speed of access (and because it is small) is read at * mount time and cached in memory. * * The inode lookup table is used only by the export code, inode disk * locations are directly encoded in directories, enabling direct access * without an intermediate lookup for all operations except the export ops. */ #include <linux/fs.h> #include <linux/vfs.h> #include <linux/dcache.h> #include <linux/exportfs.h> #include <linux/slab.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs_fs_i.h" #include "squashfs.h" /* * Look-up inode number (ino) in table, returning the inode location. */ static long long squashfs_inode_lookup(struct super_block *sb, int ino_num) { struct squashfs_sb_info *msblk = sb->s_fs_info; int blk = SQUASHFS_LOOKUP_BLOCK(ino_num - 1); int offset = SQUASHFS_LOOKUP_BLOCK_OFFSET(ino_num - 1); u64 start; __le64 ino; int err; TRACE("Entered squashfs_inode_lookup, inode_number = %d\n", ino_num); if (ino_num == 0 || (ino_num - 1) >= msblk->inodes) return -EINVAL; start = le64_to_cpu(msblk->inode_lookup_table[blk]); err = squashfs_read_metadata(sb, &ino, &start, &offset, sizeof(ino)); if (err < 0) return err; TRACE("squashfs_inode_lookup, inode = 0x%llx\n", (u64) le64_to_cpu(ino)); return le64_to_cpu(ino); } static struct dentry *squashfs_export_iget(struct super_block *sb, unsigned int ino_num) { long long ino; struct dentry *dentry = ERR_PTR(-ENOENT); TRACE("Entered squashfs_export_iget\n"); ino = squashfs_inode_lookup(sb, ino_num); if (ino >= 0) dentry = d_obtain_alias(squashfs_iget(sb, ino, ino_num)); return dentry; } static struct dentry *squashfs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { if ((fh_type != FILEID_INO32_GEN && fh_type != FILEID_INO32_GEN_PARENT) || fh_len < 2) return NULL; return squashfs_export_iget(sb, fid->i32.ino); } static struct dentry *squashfs_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { if (fh_type != FILEID_INO32_GEN_PARENT || fh_len < 4) return NULL; return squashfs_export_iget(sb, fid->i32.parent_ino); } static struct dentry *squashfs_get_parent(struct dentry *child) { struct inode *inode = d_inode(child); unsigned int parent_ino = squashfs_i(inode)->parent; return squashfs_export_iget(inode->i_sb, parent_ino); } /* * Read uncompressed inode lookup table indexes off disk into memory */ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb, u64 lookup_table_start, u64 next_table, unsigned int inodes) { unsigned int length = SQUASHFS_LOOKUP_BLOCK_BYTES(inodes); unsigned int indexes = SQUASHFS_LOOKUP_BLOCKS(inodes); int n; __le64 *table; u64 start, end; TRACE("In read_inode_lookup_table, length %d\n", length); /* Sanity check values */ /* there should always be at least one inode */ if (inodes == 0) return ERR_PTR(-EINVAL); /* * The computed size of the lookup table (length bytes) should exactly * match the table start and end points */ if (length != (next_table - lookup_table_start)) return ERR_PTR(-EINVAL); table = squashfs_read_table(sb, lookup_table_start, length); if (IS_ERR(table)) return table; /* * table0], table[1], ... table[indexes - 1] store the locations * of the compressed inode lookup blocks. Each entry should be * less than the next (i.e. table[0] < table[1]), and the difference * between them should be SQUASHFS_METADATA_SIZE or less. * table[indexes - 1] should be less than lookup_table_start, and * again the difference should be SQUASHFS_METADATA_SIZE or less */ for (n = 0; n < (indexes - 1); n++) { start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]); if (start >= end || (end - start) > (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } } start = le64_to_cpu(table[indexes - 1]); if (start >= lookup_table_start || (lookup_table_start - start) > (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } return table; } const struct export_operations squashfs_export_ops = { .encode_fh = generic_encode_ino32_fh, .fh_to_dentry = squashfs_fh_to_dentry, .fh_to_parent = squashfs_fh_to_parent, .get_parent = squashfs_get_parent }; |
| 131 | 1 2 3 4 5 6 7 8 9 10 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * xpress_decompress.c - A decompressor for the XPRESS compression format * (Huffman variant), which can be used in "System Compressed" files. This is * based on the code from wimlib. * * Copyright (C) 2015 Eric Biggers */ #include "decompress_common.h" #include "lib.h" #define XPRESS_NUM_SYMBOLS 512 #define XPRESS_MAX_CODEWORD_LEN 15 #define XPRESS_MIN_MATCH_LEN 3 /* This value is chosen for fast decompression. */ #define XPRESS_TABLEBITS 12 /* Reusable heap-allocated memory for XPRESS decompression */ struct xpress_decompressor { /* The Huffman decoding table */ u16 decode_table[(1 << XPRESS_TABLEBITS) + 2 * XPRESS_NUM_SYMBOLS]; /* An array that maps symbols to codeword lengths */ u8 lens[XPRESS_NUM_SYMBOLS]; /* Temporary space for make_huffman_decode_table() */ u16 working_space[2 * (1 + XPRESS_MAX_CODEWORD_LEN) + XPRESS_NUM_SYMBOLS]; }; /* * xpress_allocate_decompressor - Allocate an XPRESS decompressor * * Return the pointer to the decompressor on success, or return NULL and set * errno on failure. */ struct xpress_decompressor *xpress_allocate_decompressor(void) { return kmalloc(sizeof(struct xpress_decompressor), GFP_NOFS); } /* * xpress_decompress - Decompress a buffer of XPRESS-compressed data * * @decompressor: A decompressor that was allocated with * xpress_allocate_decompressor() * @compressed_data: The buffer of data to decompress * @compressed_size: Number of bytes of compressed data * @uncompressed_data: The buffer in which to store the decompressed data * @uncompressed_size: The number of bytes the data decompresses into * * Return 0 on success, or return -1 and set errno on failure. */ int xpress_decompress(struct xpress_decompressor *decompressor, const void *compressed_data, size_t compressed_size, void *uncompressed_data, size_t uncompressed_size) { struct xpress_decompressor *d = decompressor; const u8 * const in_begin = compressed_data; u8 * const out_begin = uncompressed_data; u8 *out_next = out_begin; u8 * const out_end = out_begin + uncompressed_size; struct input_bitstream is; u32 i; /* Read the Huffman codeword lengths. */ if (compressed_size < XPRESS_NUM_SYMBOLS / 2) goto invalid; for (i = 0; i < XPRESS_NUM_SYMBOLS / 2; i++) { d->lens[i*2 + 0] = in_begin[i] & 0xF; d->lens[i*2 + 1] = in_begin[i] >> 4; } /* Build a decoding table for the Huffman code. */ if (make_huffman_decode_table(d->decode_table, XPRESS_NUM_SYMBOLS, XPRESS_TABLEBITS, d->lens, XPRESS_MAX_CODEWORD_LEN, d->working_space)) goto invalid; /* Decode the matches and literals. */ init_input_bitstream(&is, in_begin + XPRESS_NUM_SYMBOLS / 2, compressed_size - XPRESS_NUM_SYMBOLS / 2); while (out_next != out_end) { u32 sym; u32 log2_offset; u32 length; u32 offset; sym = read_huffsym(&is, d->decode_table, XPRESS_TABLEBITS, XPRESS_MAX_CODEWORD_LEN); if (sym < 256) { /* Literal */ *out_next++ = sym; } else { /* Match */ length = sym & 0xf; log2_offset = (sym >> 4) & 0xf; bitstream_ensure_bits(&is, 16); offset = ((u32)1 << log2_offset) | bitstream_pop_bits(&is, log2_offset); if (length == 0xf) { length += bitstream_read_byte(&is); if (length == 0xf + 0xff) length = bitstream_read_u16(&is); } length += XPRESS_MIN_MATCH_LEN; if (offset > (size_t)(out_next - out_begin)) goto invalid; if (length > (size_t)(out_end - out_next)) goto invalid; out_next = lz_copy(out_next, length, offset, out_end, XPRESS_MIN_MATCH_LEN); } } return 0; invalid: return -1; } /* * xpress_free_decompressor - Free an XPRESS decompressor * * @decompressor: A decompressor that was allocated with * xpress_allocate_decompressor(), or NULL. */ void xpress_free_decompressor(struct xpress_decompressor *decompressor) { kfree(decompressor); } |
| 1 2 3 4 5 6 7 8 9 10 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 | // SPDX-License-Identifier: GPL-2.0 #ifndef IORING_CANCEL_H #define IORING_CANCEL_H #include <linux/io_uring_types.h> struct io_cancel_data { struct io_ring_ctx *ctx; union { u64 data; struct file *file; }; u8 opcode; u32 flags; int seq; }; int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags); int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, unsigned int issue_flags); int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg); bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd); bool io_cancel_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx, struct hlist_head *list, bool cancel_all, bool (*cancel)(struct io_kiocb *)); int io_cancel_remove(struct io_ring_ctx *ctx, struct io_cancel_data *cd, unsigned int issue_flags, struct hlist_head *list, bool (*cancel)(struct io_kiocb *)); static inline bool io_cancel_match_sequence(struct io_kiocb *req, int sequence) { if (req->cancel_seq_set && sequence == req->work.cancel_seq) return true; req->cancel_seq_set = true; req->work.cancel_seq = sequence; return false; } #endif |
| 3 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 | // SPDX-License-Identifier: GPL-2.0-or-later /* mountpoint management * * Copyright (C) 2002 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/gfp.h> #include <linux/fs_context.h> #include "internal.h" static struct dentry *afs_mntpt_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); static int afs_mntpt_open(struct inode *inode, struct file *file); static void afs_mntpt_expiry_timed_out(struct work_struct *work); const struct file_operations afs_mntpt_file_operations = { .open = afs_mntpt_open, .llseek = noop_llseek, }; const struct inode_operations afs_mntpt_inode_operations = { .lookup = afs_mntpt_lookup, .readlink = afs_readlink, .getattr = afs_getattr, }; const struct inode_operations afs_autocell_inode_operations = { .getattr = afs_getattr, }; static LIST_HEAD(afs_vfsmounts); static DECLARE_DELAYED_WORK(afs_mntpt_expiry_timer, afs_mntpt_expiry_timed_out); static unsigned long afs_mntpt_expiry_timeout = 10 * 60; static const char afs_root_volume[] = "root.cell"; /* * no valid lookup procedure on this sort of dir */ static struct dentry *afs_mntpt_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { _enter("%p,%p{%pd2}", dir, dentry, dentry); return ERR_PTR(-EREMOTE); } /* * no valid open procedure on this sort of dir */ static int afs_mntpt_open(struct inode *inode, struct file *file) { _enter("%p,%p{%pD2}", inode, file, file); return -EREMOTE; } /* * Set the parameters for the proposed superblock. */ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) { struct afs_fs_context *ctx = fc->fs_private; struct afs_super_info *src_as = AFS_FS_S(mntpt->d_sb); struct afs_vnode *vnode = AFS_FS_I(d_inode(mntpt)); struct afs_cell *cell; const char *p; int ret; if (fc->net_ns != src_as->net_ns) { put_net(fc->net_ns); fc->net_ns = get_net(src_as->net_ns); } if (src_as->volume && src_as->volume->type == AFSVL_RWVOL) { ctx->type = AFSVL_RWVOL; ctx->force = true; } if (ctx->cell) { afs_unuse_cell(ctx->cell, afs_cell_trace_unuse_mntpt); ctx->cell = NULL; } if (test_bit(AFS_VNODE_PSEUDODIR, &vnode->flags)) { /* if the directory is a pseudo directory, use the d_name */ unsigned size = mntpt->d_name.len; if (size < 2) return -ENOENT; p = mntpt->d_name.name; if (mntpt->d_name.name[0] == '.') { size--; p++; ctx->type = AFSVL_RWVOL; ctx->force = true; } if (size > AFS_MAXCELLNAME) return -ENAMETOOLONG; cell = afs_lookup_cell(ctx->net, p, size, NULL, false, afs_cell_trace_use_lookup_mntpt); if (IS_ERR(cell)) { pr_err("kAFS: unable to lookup cell '%pd'\n", mntpt); return PTR_ERR(cell); } ctx->cell = cell; ctx->volname = afs_root_volume; ctx->volnamesz = sizeof(afs_root_volume) - 1; } else { /* read the contents of the AFS special symlink */ DEFINE_DELAYED_CALL(cleanup); const char *content; loff_t size = i_size_read(d_inode(mntpt)); if (src_as->cell) ctx->cell = afs_use_cell(src_as->cell, afs_cell_trace_use_mntpt); if (size < 2 || size > PAGE_SIZE - 1) return -EINVAL; content = afs_get_link(mntpt, d_inode(mntpt), &cleanup); if (IS_ERR(content)) { do_delayed_call(&cleanup); return PTR_ERR(content); } ret = -EINVAL; if (content[size - 1] == '.') ret = vfs_parse_fs_string(fc, "source", content, size - 1); do_delayed_call(&cleanup); if (ret < 0) return ret; /* Don't cross a backup volume mountpoint from a backup volume */ if (src_as->volume && src_as->volume->type == AFSVL_BACKVOL && ctx->type == AFSVL_BACKVOL) return -ENODEV; } return 0; } /* * create a vfsmount to be automounted */ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) { struct fs_context *fc; struct vfsmount *mnt; int ret; BUG_ON(!d_inode(mntpt)); fc = fs_context_for_submount(&afs_fs_type, mntpt); if (IS_ERR(fc)) return ERR_CAST(fc); ret = afs_mntpt_set_params(fc, mntpt); if (!ret) mnt = fc_mount(fc); else mnt = ERR_PTR(ret); put_fs_context(fc); return mnt; } /* * handle an automount point */ struct vfsmount *afs_d_automount(struct path *path) { struct vfsmount *newmnt; _enter("{%pd}", path->dentry); newmnt = afs_mntpt_do_automount(path->dentry); if (IS_ERR(newmnt)) return newmnt; mntget(newmnt); /* prevent immediate expiration */ mnt_set_expiry(newmnt, &afs_vfsmounts); queue_delayed_work(afs_wq, &afs_mntpt_expiry_timer, afs_mntpt_expiry_timeout * HZ); _leave(" = %p", newmnt); return newmnt; } /* * handle mountpoint expiry timer going off */ static void afs_mntpt_expiry_timed_out(struct work_struct *work) { _enter(""); if (!list_empty(&afs_vfsmounts)) { mark_mounts_for_expiry(&afs_vfsmounts); queue_delayed_work(afs_wq, &afs_mntpt_expiry_timer, afs_mntpt_expiry_timeout * HZ); } _leave(""); } /* * kill the AFS mountpoint timer if it's still running */ void afs_mntpt_kill_timer(void) { _enter(""); ASSERT(list_empty(&afs_vfsmounts)); cancel_delayed_work_sync(&afs_mntpt_expiry_timer); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * mac80211 <-> driver interface * * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH * Copyright (C) 2018 - 2025 Intel Corporation */ #ifndef MAC80211_H #define MAC80211_H #include <linux/bug.h> #include <linux/kernel.h> #include <linux/if_ether.h> #include <linux/skbuff.h> #include <linux/ieee80211.h> #include <linux/lockdep.h> #include <net/cfg80211.h> #include <net/codel.h> #include <net/ieee80211_radiotap.h> #include <linux/unaligned.h> /** * DOC: Introduction * * mac80211 is the Linux stack for 802.11 hardware that implements * only partial functionality in hard- or firmware. This document * defines the interface between mac80211 and low-level hardware * drivers. */ /** * DOC: Calling mac80211 from interrupts * * Only ieee80211_tx_status_irqsafe() and ieee80211_rx_irqsafe() can be * called in hardware interrupt context. The low-level driver must not call any * other functions in hardware interrupt context. If there is a need for such * call, the low-level driver should first ACK the interrupt and perform the * IEEE 802.11 code call after this, e.g. from a scheduled workqueue or even * tasklet function. * * NOTE: If the driver opts to use the _irqsafe() functions, it may not also * use the non-IRQ-safe functions! */ /** * DOC: Warning * * If you're reading this document and not the header file itself, it will * be incomplete because not all documentation has been converted yet. */ /** * DOC: Frame format * * As a general rule, when frames are passed between mac80211 and the driver, * they start with the IEEE 802.11 header and include the same octets that are * sent over the air except for the FCS which should be calculated by the * hardware. * * There are, however, various exceptions to this rule for advanced features: * * The first exception is for hardware encryption and decryption offload * where the IV/ICV may or may not be generated in hardware. * * Secondly, when the hardware handles fragmentation, the frame handed to * the driver from mac80211 is the MSDU, not the MPDU. */ /** * DOC: mac80211 workqueue * * mac80211 provides its own workqueue for drivers and internal mac80211 use. * The workqueue is a single threaded workqueue and can only be accessed by * helpers for sanity checking. Drivers must ensure all work added onto the * mac80211 workqueue should be cancelled on the driver stop() callback. * * mac80211 will flush the workqueue upon interface removal and during * suspend. * * All work performed on the mac80211 workqueue must not acquire the RTNL lock. * */ /** * DOC: mac80211 software tx queueing * * mac80211 uses an intermediate queueing implementation, designed to allow the * driver to keep hardware queues short and to provide some fairness between * different stations/interfaces. * * Drivers must provide the .wake_tx_queue driver operation by either * linking it to ieee80211_handle_wake_tx_queue() or implementing a custom * handler. * * Intermediate queues (struct ieee80211_txq) are kept per-sta per-tid, with * another per-sta for non-data/non-mgmt and bufferable management frames, and * a single per-vif queue for multicast data frames. * * The driver is expected to initialize its private per-queue data for stations * and interfaces in the .add_interface and .sta_add ops. * * The driver can't access the internal TX queues (iTXQs) directly. * Whenever mac80211 adds a new frame to a queue, it calls the .wake_tx_queue * driver op. * Drivers implementing a custom .wake_tx_queue op can get them by calling * ieee80211_tx_dequeue(). Drivers using ieee80211_handle_wake_tx_queue() will * simply get the individual frames pushed via the .tx driver operation. * * Drivers can optionally delegate responsibility for scheduling queues to * mac80211, to take advantage of airtime fairness accounting. In this case, to * obtain the next queue to pull frames from, the driver calls * ieee80211_next_txq(). The driver is then expected to return the txq using * ieee80211_return_txq(). * * For AP powersave TIM handling, the driver only needs to indicate if it has * buffered packets in the driver specific data structures by calling * ieee80211_sta_set_buffered(). For frames buffered in the ieee80211_txq * struct, mac80211 sets the appropriate TIM PVB bits and calls * .release_buffered_frames(). * In that callback the driver is therefore expected to release its own * buffered frames and afterwards also frames from the ieee80211_txq (obtained * via the usual ieee80211_tx_dequeue). */ /** * DOC: HW timestamping * * Timing Measurement and Fine Timing Measurement require accurate timestamps * of the action frames TX/RX and their respective acks. * * To report hardware timestamps for Timing Measurement or Fine Timing * Measurement frame RX, the low level driver should set the SKB's hwtstamp * field to the frame RX timestamp and report the ack TX timestamp in the * ieee80211_rx_status struct. * * Similarly, to report hardware timestamps for Timing Measurement or Fine * Timing Measurement frame TX, the driver should set the SKB's hwtstamp field * to the frame TX timestamp and report the ack RX timestamp in the * ieee80211_tx_status struct. */ struct device; /** * enum ieee80211_max_queues - maximum number of queues * * @IEEE80211_MAX_QUEUES: Maximum number of regular device queues. * @IEEE80211_MAX_QUEUE_MAP: bitmap with maximum queues set */ enum ieee80211_max_queues { IEEE80211_MAX_QUEUES = 16, IEEE80211_MAX_QUEUE_MAP = BIT(IEEE80211_MAX_QUEUES) - 1, }; #define IEEE80211_INVAL_HW_QUEUE 0xff /** * enum ieee80211_ac_numbers - AC numbers as used in mac80211 * @IEEE80211_AC_VO: voice * @IEEE80211_AC_VI: video * @IEEE80211_AC_BE: best effort * @IEEE80211_AC_BK: background */ enum ieee80211_ac_numbers { IEEE80211_AC_VO = 0, IEEE80211_AC_VI = 1, IEEE80211_AC_BE = 2, IEEE80211_AC_BK = 3, }; /** * struct ieee80211_tx_queue_params - transmit queue configuration * * The information provided in this structure is required for QoS * transmit queue configuration. Cf. IEEE 802.11 7.3.2.29. * * @aifs: arbitration interframe space [0..255] * @cw_min: minimum contention window [a value of the form * 2^n-1 in the range 1..32767] * @cw_max: maximum contention window [like @cw_min] * @txop: maximum burst time in units of 32 usecs, 0 meaning disabled * @acm: is mandatory admission control required for the access category * @uapsd: is U-APSD mode enabled for the queue * @mu_edca: is the MU EDCA configured * @mu_edca_param_rec: MU EDCA Parameter Record for HE */ struct ieee80211_tx_queue_params { u16 txop; u16 cw_min; u16 cw_max; u8 aifs; bool acm; bool uapsd; bool mu_edca; struct ieee80211_he_mu_edca_param_ac_rec mu_edca_param_rec; }; struct ieee80211_low_level_stats { unsigned int dot11ACKFailureCount; unsigned int dot11RTSFailureCount; unsigned int dot11FCSErrorCount; unsigned int dot11RTSSuccessCount; }; /** * enum ieee80211_chanctx_change - change flag for channel context * @IEEE80211_CHANCTX_CHANGE_WIDTH: The channel width changed * @IEEE80211_CHANCTX_CHANGE_RX_CHAINS: The number of RX chains changed * @IEEE80211_CHANCTX_CHANGE_RADAR: radar detection flag changed * @IEEE80211_CHANCTX_CHANGE_CHANNEL: switched to another operating channel, * this is used only with channel switching with CSA * @IEEE80211_CHANCTX_CHANGE_MIN_DEF: The min chandef changed * @IEEE80211_CHANCTX_CHANGE_AP: The AP channel definition changed, so (wider * bandwidth) OFDMA settings need to be changed * @IEEE80211_CHANCTX_CHANGE_PUNCTURING: The punctured channel(s) bitmap * was changed. */ enum ieee80211_chanctx_change { IEEE80211_CHANCTX_CHANGE_WIDTH = BIT(0), IEEE80211_CHANCTX_CHANGE_RX_CHAINS = BIT(1), IEEE80211_CHANCTX_CHANGE_RADAR = BIT(2), IEEE80211_CHANCTX_CHANGE_CHANNEL = BIT(3), IEEE80211_CHANCTX_CHANGE_MIN_DEF = BIT(4), IEEE80211_CHANCTX_CHANGE_AP = BIT(5), IEEE80211_CHANCTX_CHANGE_PUNCTURING = BIT(6), }; /** * struct ieee80211_chan_req - A channel "request" * @oper: channel definition to use for operation * @ap: the channel definition of the AP, if any * (otherwise the chan member is %NULL) */ struct ieee80211_chan_req { struct cfg80211_chan_def oper; struct cfg80211_chan_def ap; }; /** * struct ieee80211_chanctx_conf - channel context that vifs may be tuned to * * This is the driver-visible part. The ieee80211_chanctx * that contains it is visible in mac80211 only. * * @def: the channel definition * @min_def: the minimum channel definition currently required. * @ap: the channel definition the AP actually is operating as, * for use with (wider bandwidth) OFDMA * @radio_idx: index of the wiphy radio used used for this channel * @rx_chains_static: The number of RX chains that must always be * active on the channel to receive MIMO transmissions * @rx_chains_dynamic: The number of RX chains that must be enabled * after RTS/CTS handshake to receive SMPS MIMO transmissions; * this will always be >= @rx_chains_static. * @radar_enabled: whether radar detection is enabled on this channel. * @drv_priv: data area for driver use, will always be aligned to * sizeof(void *), size is determined in hw information. */ struct ieee80211_chanctx_conf { struct cfg80211_chan_def def; struct cfg80211_chan_def min_def; struct cfg80211_chan_def ap; int radio_idx; u8 rx_chains_static, rx_chains_dynamic; bool radar_enabled; u8 drv_priv[] __aligned(sizeof(void *)); }; /** * enum ieee80211_chanctx_switch_mode - channel context switch mode * @CHANCTX_SWMODE_REASSIGN_VIF: Both old and new contexts already * exist (and will continue to exist), but the virtual interface * needs to be switched from one to the other. * @CHANCTX_SWMODE_SWAP_CONTEXTS: The old context exists but will stop * to exist with this call, the new context doesn't exist but * will be active after this call, the virtual interface switches * from the old to the new (note that the driver may of course * implement this as an on-the-fly chandef switch of the existing * hardware context, but the mac80211 pointer for the old context * will cease to exist and only the new one will later be used * for changes/removal.) */ enum ieee80211_chanctx_switch_mode { CHANCTX_SWMODE_REASSIGN_VIF, CHANCTX_SWMODE_SWAP_CONTEXTS, }; /** * struct ieee80211_vif_chanctx_switch - vif chanctx switch information * * This is structure is used to pass information about a vif that * needs to switch from one chanctx to another. The * &ieee80211_chanctx_switch_mode defines how the switch should be * done. * * @vif: the vif that should be switched from old_ctx to new_ctx * @link_conf: the link conf that's switching * @old_ctx: the old context to which the vif was assigned * @new_ctx: the new context to which the vif must be assigned */ struct ieee80211_vif_chanctx_switch { struct ieee80211_vif *vif; struct ieee80211_bss_conf *link_conf; struct ieee80211_chanctx_conf *old_ctx; struct ieee80211_chanctx_conf *new_ctx; }; /** * enum ieee80211_bss_change - BSS change notification flags * * These flags are used with the bss_info_changed(), link_info_changed() * and vif_cfg_changed() callbacks to indicate which parameter(s) changed. * * @BSS_CHANGED_ASSOC: association status changed (associated/disassociated), * also implies a change in the AID. * @BSS_CHANGED_ERP_CTS_PROT: CTS protection changed * @BSS_CHANGED_ERP_PREAMBLE: preamble changed * @BSS_CHANGED_ERP_SLOT: slot timing changed * @BSS_CHANGED_HT: 802.11n parameters changed * @BSS_CHANGED_BASIC_RATES: Basic rateset changed * @BSS_CHANGED_BEACON_INT: Beacon interval changed * @BSS_CHANGED_BSSID: BSSID changed, for whatever * reason (IBSS and managed mode) * @BSS_CHANGED_BEACON: Beacon data changed, retrieve * new beacon (beaconing modes) * @BSS_CHANGED_BEACON_ENABLED: Beaconing should be * enabled/disabled (beaconing modes) * @BSS_CHANGED_CQM: Connection quality monitor config changed * @BSS_CHANGED_IBSS: IBSS join status changed * @BSS_CHANGED_ARP_FILTER: Hardware ARP filter address list or state changed. * @BSS_CHANGED_QOS: QoS for this association was enabled/disabled. Note * that it is only ever disabled for station mode. * @BSS_CHANGED_IDLE: Idle changed for this BSS/interface. * @BSS_CHANGED_SSID: SSID changed for this BSS (AP and IBSS mode) * @BSS_CHANGED_AP_PROBE_RESP: Probe Response changed for this BSS (AP mode) * @BSS_CHANGED_PS: PS changed for this BSS (STA mode) * @BSS_CHANGED_TXPOWER: TX power setting changed for this interface * @BSS_CHANGED_P2P_PS: P2P powersave settings (CTWindow, opportunistic PS) * changed * @BSS_CHANGED_BEACON_INFO: Data from the AP's beacon became available: * currently dtim_period only is under consideration. * @BSS_CHANGED_BANDWIDTH: The bandwidth used by this interface changed, * note that this is only called when it changes after the channel * context had been assigned. * @BSS_CHANGED_OCB: OCB join status changed * @BSS_CHANGED_MU_GROUPS: VHT MU-MIMO group id or user position changed * @BSS_CHANGED_KEEP_ALIVE: keep alive options (idle period or protected * keep alive) changed. * @BSS_CHANGED_MCAST_RATE: Multicast Rate setting changed for this interface * @BSS_CHANGED_FTM_RESPONDER: fine timing measurement request responder * functionality changed for this BSS (AP mode). * @BSS_CHANGED_TWT: TWT status changed * @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed. * @BSS_CHANGED_HE_BSS_COLOR: BSS Color has changed * @BSS_CHANGED_FILS_DISCOVERY: FILS discovery status changed. * @BSS_CHANGED_UNSOL_BCAST_PROBE_RESP: Unsolicited broadcast probe response * status changed. * @BSS_CHANGED_MLD_VALID_LINKS: MLD valid links status changed. * @BSS_CHANGED_MLD_TTLM: negotiated TID to link mapping was changed * @BSS_CHANGED_TPE: transmit power envelope changed */ enum ieee80211_bss_change { BSS_CHANGED_ASSOC = 1<<0, BSS_CHANGED_ERP_CTS_PROT = 1<<1, BSS_CHANGED_ERP_PREAMBLE = 1<<2, BSS_CHANGED_ERP_SLOT = 1<<3, BSS_CHANGED_HT = 1<<4, BSS_CHANGED_BASIC_RATES = 1<<5, BSS_CHANGED_BEACON_INT = 1<<6, BSS_CHANGED_BSSID = 1<<7, BSS_CHANGED_BEACON = 1<<8, BSS_CHANGED_BEACON_ENABLED = 1<<9, BSS_CHANGED_CQM = 1<<10, BSS_CHANGED_IBSS = 1<<11, BSS_CHANGED_ARP_FILTER = 1<<12, BSS_CHANGED_QOS = 1<<13, BSS_CHANGED_IDLE = 1<<14, BSS_CHANGED_SSID = 1<<15, BSS_CHANGED_AP_PROBE_RESP = 1<<16, BSS_CHANGED_PS = 1<<17, BSS_CHANGED_TXPOWER = 1<<18, BSS_CHANGED_P2P_PS = 1<<19, BSS_CHANGED_BEACON_INFO = 1<<20, BSS_CHANGED_BANDWIDTH = 1<<21, BSS_CHANGED_OCB = 1<<22, BSS_CHANGED_MU_GROUPS = 1<<23, BSS_CHANGED_KEEP_ALIVE = 1<<24, BSS_CHANGED_MCAST_RATE = 1<<25, BSS_CHANGED_FTM_RESPONDER = 1<<26, BSS_CHANGED_TWT = 1<<27, BSS_CHANGED_HE_OBSS_PD = 1<<28, BSS_CHANGED_HE_BSS_COLOR = 1<<29, BSS_CHANGED_FILS_DISCOVERY = 1<<30, BSS_CHANGED_UNSOL_BCAST_PROBE_RESP = BIT_ULL(31), BSS_CHANGED_MLD_VALID_LINKS = BIT_ULL(33), BSS_CHANGED_MLD_TTLM = BIT_ULL(34), BSS_CHANGED_TPE = BIT_ULL(35), /* when adding here, make sure to change ieee80211_reconfig */ }; /* * The maximum number of IPv4 addresses listed for ARP filtering. If the number * of addresses for an interface increase beyond this value, hardware ARP * filtering will be disabled. */ #define IEEE80211_BSS_ARP_ADDR_LIST_LEN 4 /** * enum ieee80211_event_type - event to be notified to the low level driver * @RSSI_EVENT: AP's rssi crossed the a threshold set by the driver. * @MLME_EVENT: event related to MLME * @BAR_RX_EVENT: a BAR was received * @BA_FRAME_TIMEOUT: Frames were released from the reordering buffer because * they timed out. This won't be called for each frame released, but only * once each time the timeout triggers. */ enum ieee80211_event_type { RSSI_EVENT, MLME_EVENT, BAR_RX_EVENT, BA_FRAME_TIMEOUT, }; /** * enum ieee80211_rssi_event_data - relevant when event type is %RSSI_EVENT * @RSSI_EVENT_HIGH: AP's rssi went below the threshold set by the driver. * @RSSI_EVENT_LOW: AP's rssi went above the threshold set by the driver. */ enum ieee80211_rssi_event_data { RSSI_EVENT_HIGH, RSSI_EVENT_LOW, }; /** * struct ieee80211_rssi_event - data attached to an %RSSI_EVENT * @data: See &enum ieee80211_rssi_event_data */ struct ieee80211_rssi_event { enum ieee80211_rssi_event_data data; }; /** * enum ieee80211_mlme_event_data - relevant when event type is %MLME_EVENT * @AUTH_EVENT: the MLME operation is authentication * @ASSOC_EVENT: the MLME operation is association * @DEAUTH_RX_EVENT: deauth received.. * @DEAUTH_TX_EVENT: deauth sent. */ enum ieee80211_mlme_event_data { AUTH_EVENT, ASSOC_EVENT, DEAUTH_RX_EVENT, DEAUTH_TX_EVENT, }; /** * enum ieee80211_mlme_event_status - relevant when event type is %MLME_EVENT * @MLME_SUCCESS: the MLME operation completed successfully. * @MLME_DENIED: the MLME operation was denied by the peer. * @MLME_TIMEOUT: the MLME operation timed out. */ enum ieee80211_mlme_event_status { MLME_SUCCESS, MLME_DENIED, MLME_TIMEOUT, }; /** * struct ieee80211_mlme_event - data attached to an %MLME_EVENT * @data: See &enum ieee80211_mlme_event_data * @status: See &enum ieee80211_mlme_event_status * @reason: the reason code if applicable */ struct ieee80211_mlme_event { enum ieee80211_mlme_event_data data; enum ieee80211_mlme_event_status status; u16 reason; }; /** * struct ieee80211_ba_event - data attached for BlockAck related events * @sta: pointer to the &ieee80211_sta to which this event relates * @tid: the tid * @ssn: the starting sequence number (for %BAR_RX_EVENT) */ struct ieee80211_ba_event { struct ieee80211_sta *sta; u16 tid; u16 ssn; }; /** * struct ieee80211_event - event to be sent to the driver * @type: The event itself. See &enum ieee80211_event_type. * @u.rssi: relevant if &type is %RSSI_EVENT * @u.mlme: relevant if &type is %AUTH_EVENT * @u.ba: relevant if &type is %BAR_RX_EVENT or %BA_FRAME_TIMEOUT * @u:union holding the fields above */ struct ieee80211_event { enum ieee80211_event_type type; union { struct ieee80211_rssi_event rssi; struct ieee80211_mlme_event mlme; struct ieee80211_ba_event ba; } u; }; /** * struct ieee80211_mu_group_data - STA's VHT MU-MIMO group data * * This structure describes the group id data of VHT MU-MIMO * * @membership: 64 bits array - a bit is set if station is member of the group * @position: 2 bits per group id indicating the position in the group */ struct ieee80211_mu_group_data { u8 membership[WLAN_MEMBERSHIP_LEN]; u8 position[WLAN_USER_POSITION_LEN]; }; /** * struct ieee80211_ftm_responder_params - FTM responder parameters * * @lci: LCI subelement content * @civicloc: CIVIC location subelement content * @lci_len: LCI data length * @civicloc_len: Civic data length */ struct ieee80211_ftm_responder_params { const u8 *lci; const u8 *civicloc; size_t lci_len; size_t civicloc_len; }; /** * struct ieee80211_fils_discovery - FILS discovery parameters from * IEEE Std 802.11ai-2016, Annex C.3 MIB detail. * * @min_interval: Minimum packet interval in TUs (0 - 10000) * @max_interval: Maximum packet interval in TUs (0 - 10000) */ struct ieee80211_fils_discovery { u32 min_interval; u32 max_interval; }; #define IEEE80211_TPE_EIRP_ENTRIES_320MHZ 5 struct ieee80211_parsed_tpe_eirp { bool valid; s8 power[IEEE80211_TPE_EIRP_ENTRIES_320MHZ]; u8 count; }; #define IEEE80211_TPE_PSD_ENTRIES_320MHZ 16 struct ieee80211_parsed_tpe_psd { bool valid; s8 power[IEEE80211_TPE_PSD_ENTRIES_320MHZ]; u8 count, n; }; /** * struct ieee80211_parsed_tpe - parsed transmit power envelope information * @max_local: maximum local EIRP, one value for 20, 40, 80, 160, 320 MHz each * (indexed by TX power category) * @max_reg_client: maximum regulatory client EIRP, one value for 20, 40, 80, * 160, 320 MHz each * (indexed by TX power category) * @psd_local: maximum local power spectral density, one value for each 20 MHz * subchannel per bss_conf's chanreq.oper * (indexed by TX power category) * @psd_reg_client: maximum regulatory power spectral density, one value for * each 20 MHz subchannel per bss_conf's chanreq.oper * (indexed by TX power category) */ struct ieee80211_parsed_tpe { struct ieee80211_parsed_tpe_eirp max_local[2], max_reg_client[2]; struct ieee80211_parsed_tpe_psd psd_local[2], psd_reg_client[2]; }; /** * struct ieee80211_bss_conf - holds the BSS's changing parameters * * This structure keeps information about a BSS (and an association * to that BSS) that can change during the lifetime of the BSS. * * @vif: reference to owning VIF * @bss: the cfg80211 bss descriptor. Valid only for a station, and only * when associated. Note: This contains information which is not * necessarily authenticated. For example, information coming from probe * responses. * @addr: (link) address used locally * @link_id: link ID, or 0 for non-MLO * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE * @uora_exists: is the UORA element advertised by AP * @uora_ocw_range: UORA element's OCW Range field * @frame_time_rts_th: HE duration RTS threshold, in units of 32us * @he_support: does this BSS support HE * @twt_requester: does this BSS support TWT requester (relevant for managed * mode only, set if the AP advertises TWT responder role) * @twt_responder: does this BSS support TWT requester (relevant for managed * mode only, set if the AP advertises TWT responder role) * @twt_protected: does this BSS support protected TWT frames * @twt_broadcast: does this BSS support broadcast TWT * @use_cts_prot: use CTS protection * @use_short_preamble: use 802.11b short preamble * @use_short_slot: use short slot time (only relevant for ERP) * @dtim_period: num of beacons before the next DTIM, for beaconing, * valid in station mode only if after the driver was notified * with the %BSS_CHANGED_BEACON_INFO flag, will be non-zero then. * @sync_tsf: last beacon's/probe response's TSF timestamp (could be old * as it may have been received during scanning long ago). If the * HW flag %IEEE80211_HW_TIMING_BEACON_ONLY is set, then this can * only come from a beacon, but might not become valid until after * association when a beacon is received (which is notified with the * %BSS_CHANGED_DTIM flag.). See also sync_dtim_count important notice. * @sync_device_ts: the device timestamp corresponding to the sync_tsf, * the driver/device can use this to calculate synchronisation * (see @sync_tsf). See also sync_dtim_count important notice. * @sync_dtim_count: Only valid when %IEEE80211_HW_TIMING_BEACON_ONLY * is requested, see @sync_tsf/@sync_device_ts. * IMPORTANT: These three sync_* parameters would possibly be out of sync * by the time the driver will use them. The synchronized view is currently * guaranteed only in certain callbacks. * Note also that this is not used with MLD associations, mac80211 doesn't * know how to track beacons for all of the links for this. * @beacon_int: beacon interval * @assoc_capability: capabilities taken from assoc resp * @basic_rates: bitmap of basic rates, each bit stands for an * index into the rate table configured by the driver in * the current band. * @beacon_rate: associated AP's beacon TX rate * @mcast_rate: per-band multicast rate index + 1 (0: disabled) * @bssid: The BSSID for this BSS * @enable_beacon: whether beaconing should be enabled or not * @chanreq: Channel request for this BSS -- the hardware might be * configured a higher bandwidth than this BSS uses, for example. * @mu_group: VHT MU-MIMO group membership data * @ht_operation_mode: HT operation mode like in &struct ieee80211_ht_operation. * This field is only valid when the channel is a wide HT/VHT channel. * Note that with TDLS this can be the case (channel is HT, protection must * be used from this field) even when the BSS association isn't using HT. * @cqm_rssi_thold: Connection quality monitor RSSI threshold, a zero value * implies disabled. As with the cfg80211 callback, a change here should * cause an event to be sent indicating where the current value is in * relation to the newly configured threshold. * @cqm_rssi_low: Connection quality monitor RSSI lower threshold, a zero value * implies disabled. This is an alternative mechanism to the single * threshold event and can't be enabled simultaneously with it. * @cqm_rssi_high: Connection quality monitor RSSI upper threshold. * @cqm_rssi_hyst: Connection quality monitor RSSI hysteresis * @qos: This is a QoS-enabled BSS. * @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode. * @txpower: TX power in dBm. INT_MIN means not configured. * @txpower_type: TX power adjustment used to control per packet Transmit * Power Control (TPC) in lower driver for the current vif. In particular * TPC is enabled if value passed in %txpower_type is * NL80211_TX_POWER_LIMITED (allow using less than specified from * userspace), whereas TPC is disabled if %txpower_type is set to * NL80211_TX_POWER_FIXED (use value configured from userspace) * @p2p_noa_attr: P2P NoA attribute for P2P powersave * @allow_p2p_go_ps: indication for AP or P2P GO interface, whether it's allowed * to use P2P PS mechanism or not. AP/P2P GO is not allowed to use P2P PS * if it has associated clients without P2P PS support. * @max_idle_period: the time period during which the station can refrain from * transmitting frames to its associated AP without being disassociated. * In units of 1000 TUs. Zero value indicates that the AP did not include * a (valid) BSS Max Idle Period Element. * @protected_keep_alive: if set, indicates that the station should send an RSN * protected frame to the AP to reset the idle timer at the AP for the * station. * @ftm_responder: whether to enable or disable fine timing measurement FTM * responder functionality. * @ftmr_params: configurable lci/civic parameter when enabling FTM responder. * @nontransmitted: this BSS is a nontransmitted BSS profile * @transmitter_bssid: the address of transmitter AP * @bssid_index: index inside the multiple BSSID set * @bssid_indicator: 2^bssid_indicator is the maximum number of APs in set * @ema_ap: AP supports enhancements of discovery and advertisement of * nontransmitted BSSIDs * @profile_periodicity: the least number of beacon frames need to be received * in order to discover all the nontransmitted BSSIDs in the set. * @he_oper: HE operation information of the BSS (AP/Mesh) or of the AP we are * connected to (STA) * @he_obss_pd: OBSS Packet Detection parameters. * @he_bss_color: BSS coloring settings, if BSS supports HE * @fils_discovery: FILS discovery configuration * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response * interval. * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed * to driver when rate control is offloaded to firmware. * @power_type: power type of BSS for 6 GHz * @tpe: transmit power envelope information * @pwr_reduction: power constraint of BSS. * @eht_support: does this BSS support EHT * @epcs_support: does this BSS support EPCS * @csa_active: marks whether a channel switch is going on. * @mu_mimo_owner: indicates interface owns MU-MIMO capability * @chanctx_conf: The channel context this interface is assigned to, or %NULL * when it is not assigned. This pointer is RCU-protected due to the TX * path needing to access it; even though the netdev carrier will always * be off when it is %NULL there can still be races and packets could be * processed after it switches back to %NULL. * @color_change_active: marks whether a color change is ongoing. * @color_change_color: the bss color that will be used after the change. * @ht_ldpc: in AP mode, indicates interface has HT LDPC capability. * @vht_ldpc: in AP mode, indicates interface has VHT LDPC capability. * @he_ldpc: in AP mode, indicates interface has HE LDPC capability. * @vht_su_beamformer: in AP mode, does this BSS support operation as an VHT SU * beamformer * @vht_su_beamformee: in AP mode, does this BSS support operation as an VHT SU * beamformee * @vht_mu_beamformer: in AP mode, does this BSS support operation as an VHT MU * beamformer * @vht_mu_beamformee: in AP mode, does this BSS support operation as an VHT MU * beamformee * @he_su_beamformer: in AP-mode, does this BSS support operation as an HE SU * beamformer * @he_su_beamformee: in AP-mode, does this BSS support operation as an HE SU * beamformee * @he_mu_beamformer: in AP-mode, does this BSS support operation as an HE MU * beamformer * @he_full_ul_mumimo: does this BSS support the reception (AP) or transmission * (non-AP STA) of an HE TB PPDU on an RU that spans the entire PPDU * bandwidth * @eht_su_beamformer: in AP-mode, does this BSS enable operation as an EHT SU * beamformer * @eht_su_beamformee: in AP-mode, does this BSS enable operation as an EHT SU * beamformee * @eht_mu_beamformer: in AP-mode, does this BSS enable operation as an EHT MU * beamformer * @eht_80mhz_full_bw_ul_mumimo: in AP-mode, does this BSS support the * reception of an EHT TB PPDU on an RU that spans the entire PPDU * bandwidth * @bss_param_ch_cnt: in BSS-mode, the BSS params change count. This * information is the latest known value. It can come from this link's * beacon or from a beacon sent by another link. * @bss_param_ch_cnt_link_id: in BSS-mode, the link_id to which the beacon * that updated &bss_param_ch_cnt belongs. E.g. if link 1 doesn't hear * its beacons, and link 2 sent a beacon with an RNR element that updated * link 1's BSS params change count, then, link 1's * bss_param_ch_cnt_link_id will be 2. That means that link 1 knows that * link 2 was the link that updated its bss_param_ch_cnt value. * In case link 1 hears its beacon again, bss_param_ch_cnt_link_id will * be updated to 1, even if bss_param_ch_cnt didn't change. This allows * the link to know that it heard the latest value from its own beacon * (as opposed to hearing its value from another link's beacon). */ struct ieee80211_bss_conf { struct ieee80211_vif *vif; struct cfg80211_bss *bss; const u8 *bssid; unsigned int link_id; u8 addr[ETH_ALEN] __aligned(2); u8 htc_trig_based_pkt_ext; bool uora_exists; u8 uora_ocw_range; u16 frame_time_rts_th; bool he_support; bool twt_requester; bool twt_responder; bool twt_protected; bool twt_broadcast; /* erp related data */ bool use_cts_prot; bool use_short_preamble; bool use_short_slot; bool enable_beacon; u8 dtim_period; u16 beacon_int; u16 assoc_capability; u64 sync_tsf; u32 sync_device_ts; u8 sync_dtim_count; u32 basic_rates; struct ieee80211_rate *beacon_rate; int mcast_rate[NUM_NL80211_BANDS]; u16 ht_operation_mode; s32 cqm_rssi_thold; u32 cqm_rssi_hyst; s32 cqm_rssi_low; s32 cqm_rssi_high; struct ieee80211_chan_req chanreq; struct ieee80211_mu_group_data mu_group; bool qos; bool hidden_ssid; int txpower; enum nl80211_tx_power_setting txpower_type; struct ieee80211_p2p_noa_attr p2p_noa_attr; bool allow_p2p_go_ps; u16 max_idle_period; bool protected_keep_alive; bool ftm_responder; struct ieee80211_ftm_responder_params *ftmr_params; /* Multiple BSSID data */ bool nontransmitted; u8 transmitter_bssid[ETH_ALEN]; u8 bssid_index; u8 bssid_indicator; bool ema_ap; u8 profile_periodicity; struct { u32 params; u16 nss_set; } he_oper; struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_he_bss_color he_bss_color; struct ieee80211_fils_discovery fils_discovery; u32 unsol_bcast_probe_resp_interval; struct cfg80211_bitrate_mask beacon_tx_rate; enum ieee80211_ap_reg_power power_type; struct ieee80211_parsed_tpe tpe; u8 pwr_reduction; bool eht_support; bool epcs_support; bool csa_active; bool mu_mimo_owner; struct ieee80211_chanctx_conf __rcu *chanctx_conf; bool color_change_active; u8 color_change_color; bool ht_ldpc; bool vht_ldpc; bool he_ldpc; bool vht_su_beamformer; bool vht_su_beamformee; bool vht_mu_beamformer; bool vht_mu_beamformee; bool he_su_beamformer; bool he_su_beamformee; bool he_mu_beamformer; bool he_full_ul_mumimo; bool eht_su_beamformer; bool eht_su_beamformee; bool eht_mu_beamformer; bool eht_80mhz_full_bw_ul_mumimo; u8 bss_param_ch_cnt; u8 bss_param_ch_cnt_link_id; }; /** * enum mac80211_tx_info_flags - flags to describe transmission information/status * * These flags are used with the @flags member of &ieee80211_tx_info. * * @IEEE80211_TX_CTL_REQ_TX_STATUS: require TX status callback for this frame. * @IEEE80211_TX_CTL_ASSIGN_SEQ: The driver has to assign a sequence * number to this frame, taking care of not overwriting the fragment * number and increasing the sequence number only when the * IEEE80211_TX_CTL_FIRST_FRAGMENT flag is set. mac80211 will properly * assign sequence numbers to QoS-data frames but cannot do so correctly * for non-QoS-data and management frames because beacons need them from * that counter as well and mac80211 cannot guarantee proper sequencing. * If this flag is set, the driver should instruct the hardware to * assign a sequence number to the frame or assign one itself. Cf. IEEE * 802.11-2007 7.1.3.4.1 paragraph 3. This flag will always be set for * beacons and always be clear for frames without a sequence number field. * @IEEE80211_TX_CTL_NO_ACK: tell the low level not to wait for an ack * @IEEE80211_TX_CTL_CLEAR_PS_FILT: clear powersave filter for destination * station * @IEEE80211_TX_CTL_FIRST_FRAGMENT: this is a first fragment of the frame * @IEEE80211_TX_CTL_SEND_AFTER_DTIM: send this frame after DTIM beacon * @IEEE80211_TX_CTL_AMPDU: this frame should be sent as part of an A-MPDU * @IEEE80211_TX_CTL_INJECTED: Frame was injected, internal to mac80211. * @IEEE80211_TX_STAT_TX_FILTERED: The frame was not transmitted * because the destination STA was in powersave mode. Note that to * avoid race conditions, the filter must be set by the hardware or * firmware upon receiving a frame that indicates that the station * went to sleep (must be done on device to filter frames already on * the queue) and may only be unset after mac80211 gives the OK for * that by setting the IEEE80211_TX_CTL_CLEAR_PS_FILT (see above), * since only then is it guaranteed that no more frames are in the * hardware queue. * @IEEE80211_TX_STAT_ACK: Frame was acknowledged * @IEEE80211_TX_STAT_AMPDU: The frame was aggregated, so status * is for the whole aggregation. * @IEEE80211_TX_STAT_AMPDU_NO_BACK: no block ack was returned, * so consider using block ack request (BAR). * @IEEE80211_TX_CTL_RATE_CTRL_PROBE: internal to mac80211, can be * set by rate control algorithms to indicate probe rate, will * be cleared for fragmented frames (except on the last fragment) * @IEEE80211_TX_INTFL_OFFCHAN_TX_OK: Internal to mac80211. Used to indicate * that a frame can be transmitted while the queues are stopped for * off-channel operation. * @IEEE80211_TX_CTL_HW_80211_ENCAP: This frame uses hardware encapsulation * (header conversion) * @IEEE80211_TX_INTFL_RETRIED: completely internal to mac80211, * used to indicate that a frame was already retried due to PS * @IEEE80211_TX_INTFL_DONT_ENCRYPT: completely internal to mac80211, * used to indicate frame should not be encrypted * @IEEE80211_TX_CTL_NO_PS_BUFFER: This frame is a response to a poll * frame (PS-Poll or uAPSD) or a non-bufferable MMPDU and must * be sent although the station is in powersave mode. * @IEEE80211_TX_CTL_MORE_FRAMES: More frames will be passed to the * transmit function after the current frame, this can be used * by drivers to kick the DMA queue only if unset or when the * queue gets full. * @IEEE80211_TX_INTFL_RETRANSMISSION: This frame is being retransmitted * after TX status because the destination was asleep, it must not * be modified again (no seqno assignment, crypto, etc.) * @IEEE80211_TX_INTFL_MLME_CONN_TX: This frame was transmitted by the MLME * code for connection establishment, this indicates that its status * should kick the MLME state machine. * @IEEE80211_TX_INTFL_NL80211_FRAME_TX: Frame was requested through nl80211 * MLME command (internal to mac80211 to figure out whether to send TX * status to user space) * @IEEE80211_TX_CTL_LDPC: tells the driver to use LDPC for this frame * @IEEE80211_TX_CTL_STBC: Enables Space-Time Block Coding (STBC) for this * frame and selects the maximum number of streams that it can use. * @IEEE80211_TX_CTL_TX_OFFCHAN: Marks this packet to be transmitted on * the off-channel channel when a remain-on-channel offload is done * in hardware -- normal packets still flow and are expected to be * handled properly by the device. * @IEEE80211_TX_INTFL_TKIP_MIC_FAILURE: Marks this packet to be used for TKIP * testing. It will be sent out with incorrect Michael MIC key to allow * TKIP countermeasures to be tested. * @IEEE80211_TX_CTL_NO_CCK_RATE: This frame will be sent at non CCK rate. * This flag is actually used for management frame especially for P2P * frames not being sent at CCK rate in 2GHz band. * @IEEE80211_TX_STATUS_EOSP: This packet marks the end of service period, * when its status is reported the service period ends. For frames in * an SP that mac80211 transmits, it is already set; for driver frames * the driver may set this flag. It is also used to do the same for * PS-Poll responses. * @IEEE80211_TX_CTL_USE_MINRATE: This frame will be sent at lowest rate. * This flag is used to send nullfunc frame at minimum rate when * the nullfunc is used for connection monitoring purpose. * @IEEE80211_TX_CTL_DONTFRAG: Don't fragment this packet even if it * would be fragmented by size (this is optional, only used for * monitor injection). * @IEEE80211_TX_STAT_NOACK_TRANSMITTED: A frame that was marked with * IEEE80211_TX_CTL_NO_ACK has been successfully transmitted without * any errors (like issues specific to the driver/HW). * This flag must not be set for frames that don't request no-ack * behaviour with IEEE80211_TX_CTL_NO_ACK. * * Note: If you have to add new flags to the enumeration, then don't * forget to update %IEEE80211_TX_TEMPORARY_FLAGS when necessary. */ enum mac80211_tx_info_flags { IEEE80211_TX_CTL_REQ_TX_STATUS = BIT(0), IEEE80211_TX_CTL_ASSIGN_SEQ = BIT(1), IEEE80211_TX_CTL_NO_ACK = BIT(2), IEEE80211_TX_CTL_CLEAR_PS_FILT = BIT(3), IEEE80211_TX_CTL_FIRST_FRAGMENT = BIT(4), IEEE80211_TX_CTL_SEND_AFTER_DTIM = BIT(5), IEEE80211_TX_CTL_AMPDU = BIT(6), IEEE80211_TX_CTL_INJECTED = BIT(7), IEEE80211_TX_STAT_TX_FILTERED = BIT(8), IEEE80211_TX_STAT_ACK = BIT(9), IEEE80211_TX_STAT_AMPDU = BIT(10), IEEE80211_TX_STAT_AMPDU_NO_BACK = BIT(11), IEEE80211_TX_CTL_RATE_CTRL_PROBE = BIT(12), IEEE80211_TX_INTFL_OFFCHAN_TX_OK = BIT(13), IEEE80211_TX_CTL_HW_80211_ENCAP = BIT(14), IEEE80211_TX_INTFL_RETRIED = BIT(15), IEEE80211_TX_INTFL_DONT_ENCRYPT = BIT(16), IEEE80211_TX_CTL_NO_PS_BUFFER = BIT(17), IEEE80211_TX_CTL_MORE_FRAMES = BIT(18), IEEE80211_TX_INTFL_RETRANSMISSION = BIT(19), IEEE80211_TX_INTFL_MLME_CONN_TX = BIT(20), IEEE80211_TX_INTFL_NL80211_FRAME_TX = BIT(21), IEEE80211_TX_CTL_LDPC = BIT(22), IEEE80211_TX_CTL_STBC = BIT(23) | BIT(24), IEEE80211_TX_CTL_TX_OFFCHAN = BIT(25), IEEE80211_TX_INTFL_TKIP_MIC_FAILURE = BIT(26), IEEE80211_TX_CTL_NO_CCK_RATE = BIT(27), IEEE80211_TX_STATUS_EOSP = BIT(28), IEEE80211_TX_CTL_USE_MINRATE = BIT(29), IEEE80211_TX_CTL_DONTFRAG = BIT(30), IEEE80211_TX_STAT_NOACK_TRANSMITTED = BIT(31), }; #define IEEE80211_TX_CTL_STBC_SHIFT 23 #define IEEE80211_TX_RC_S1G_MCS IEEE80211_TX_RC_VHT_MCS /** * enum mac80211_tx_control_flags - flags to describe transmit control * * @IEEE80211_TX_CTRL_PORT_CTRL_PROTO: this frame is a port control * protocol frame (e.g. EAP) * @IEEE80211_TX_CTRL_PS_RESPONSE: This frame is a response to a poll * frame (PS-Poll or uAPSD). * @IEEE80211_TX_CTRL_RATE_INJECT: This frame is injected with rate information * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame * @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path * @IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP: This frame skips mesh path lookup * @IEEE80211_TX_INTCFL_NEED_TXPROCESSING: completely internal to mac80211, * used to indicate that a pending frame requires TX processing before * it can be sent out. * @IEEE80211_TX_CTRL_NO_SEQNO: Do not overwrite the sequence number that * has already been assigned to this frame. * @IEEE80211_TX_CTRL_DONT_REORDER: This frame should not be reordered * relative to other frames that have this flag set, independent * of their QoS TID or other priority field values. * @IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX: first MLO TX, used mostly internally * for sequence number assignment * @IEEE80211_TX_CTRL_DONT_USE_RATE_MASK: Don't use rate mask for this frame * which is transmitted due to scanning or offchannel TX, not in normal * operation on the interface. * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this * frame should be transmitted on the specific link. This really is * only relevant for frames that do not have data present, and is * also not used for 802.3 format frames. Note that even if the frame * is on a specific link, address translation might still apply if * it's intended for an MLD. * * These flags are used in tx_info->control.flags. */ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_PORT_CTRL_PROTO = BIT(0), IEEE80211_TX_CTRL_PS_RESPONSE = BIT(1), IEEE80211_TX_CTRL_RATE_INJECT = BIT(2), IEEE80211_TX_CTRL_AMSDU = BIT(3), IEEE80211_TX_CTRL_FAST_XMIT = BIT(4), IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP = BIT(5), IEEE80211_TX_INTCFL_NEED_TXPROCESSING = BIT(6), IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX = BIT(9), IEEE80211_TX_CTRL_DONT_USE_RATE_MASK = BIT(10), IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000, }; #define IEEE80211_LINK_UNSPECIFIED 0xf #define IEEE80211_TX_CTRL_MLO_LINK_UNSPEC \ u32_encode_bits(IEEE80211_LINK_UNSPECIFIED, \ IEEE80211_TX_CTRL_MLO_LINK) /** * enum mac80211_tx_status_flags - flags to describe transmit status * * @IEEE80211_TX_STATUS_ACK_SIGNAL_VALID: ACK signal is valid * * These flags are used in tx_info->status.flags. */ enum mac80211_tx_status_flags { IEEE80211_TX_STATUS_ACK_SIGNAL_VALID = BIT(0), }; /* * This definition is used as a mask to clear all temporary flags, which are * set by the tx handlers for each transmission attempt by the mac80211 stack. */ #define IEEE80211_TX_TEMPORARY_FLAGS (IEEE80211_TX_CTL_NO_ACK | \ IEEE80211_TX_CTL_CLEAR_PS_FILT | IEEE80211_TX_CTL_FIRST_FRAGMENT | \ IEEE80211_TX_CTL_SEND_AFTER_DTIM | IEEE80211_TX_CTL_AMPDU | \ IEEE80211_TX_STAT_TX_FILTERED | IEEE80211_TX_STAT_ACK | \ IEEE80211_TX_STAT_AMPDU | IEEE80211_TX_STAT_AMPDU_NO_BACK | \ IEEE80211_TX_CTL_RATE_CTRL_PROBE | IEEE80211_TX_CTL_NO_PS_BUFFER | \ IEEE80211_TX_CTL_MORE_FRAMES | IEEE80211_TX_CTL_LDPC | \ IEEE80211_TX_CTL_STBC | IEEE80211_TX_STATUS_EOSP) /** * enum mac80211_rate_control_flags - per-rate flags set by the * Rate Control algorithm. * * These flags are set by the Rate control algorithm for each rate during tx, * in the @flags member of struct ieee80211_tx_rate. * * @IEEE80211_TX_RC_USE_RTS_CTS: Use RTS/CTS exchange for this rate. * @IEEE80211_TX_RC_USE_CTS_PROTECT: CTS-to-self protection is required. * This is set if the current BSS requires ERP protection. * @IEEE80211_TX_RC_USE_SHORT_PREAMBLE: Use short preamble. * @IEEE80211_TX_RC_MCS: HT rate. * @IEEE80211_TX_RC_VHT_MCS: VHT MCS rate, in this case the idx field is split * into a higher 4 bits (Nss) and lower 4 bits (MCS number) * @IEEE80211_TX_RC_GREEN_FIELD: Indicates whether this rate should be used in * Greenfield mode. * @IEEE80211_TX_RC_40_MHZ_WIDTH: Indicates if the Channel Width should be 40 MHz. * @IEEE80211_TX_RC_80_MHZ_WIDTH: Indicates 80 MHz transmission * @IEEE80211_TX_RC_160_MHZ_WIDTH: Indicates 160 MHz transmission * (80+80 isn't supported yet) * @IEEE80211_TX_RC_DUP_DATA: The frame should be transmitted on both of the * adjacent 20 MHz channels, if the current channel type is * NL80211_CHAN_HT40MINUS or NL80211_CHAN_HT40PLUS. * @IEEE80211_TX_RC_SHORT_GI: Short Guard interval should be used for this rate. */ enum mac80211_rate_control_flags { IEEE80211_TX_RC_USE_RTS_CTS = BIT(0), IEEE80211_TX_RC_USE_CTS_PROTECT = BIT(1), IEEE80211_TX_RC_USE_SHORT_PREAMBLE = BIT(2), /* rate index is an HT/VHT MCS instead of an index */ IEEE80211_TX_RC_MCS = BIT(3), IEEE80211_TX_RC_GREEN_FIELD = BIT(4), IEEE80211_TX_RC_40_MHZ_WIDTH = BIT(5), IEEE80211_TX_RC_DUP_DATA = BIT(6), IEEE80211_TX_RC_SHORT_GI = BIT(7), IEEE80211_TX_RC_VHT_MCS = BIT(8), IEEE80211_TX_RC_80_MHZ_WIDTH = BIT(9), IEEE80211_TX_RC_160_MHZ_WIDTH = BIT(10), }; /* there are 40 bytes if you don't need the rateset to be kept */ #define IEEE80211_TX_INFO_DRIVER_DATA_SIZE 40 /* if you do need the rateset, then you have less space */ #define IEEE80211_TX_INFO_RATE_DRIVER_DATA_SIZE 24 /* maximum number of rate stages */ #define IEEE80211_TX_MAX_RATES 4 /* maximum number of rate table entries */ #define IEEE80211_TX_RATE_TABLE_SIZE 4 /** * struct ieee80211_tx_rate - rate selection/status * * @idx: rate index to attempt to send with * @flags: rate control flags (&enum mac80211_rate_control_flags) * @count: number of tries in this rate before going to the next rate * * A value of -1 for @idx indicates an invalid rate and, if used * in an array of retry rates, that no more rates should be tried. * * When used for transmit status reporting, the driver should * always report the rate along with the flags it used. * * &struct ieee80211_tx_info contains an array of these structs * in the control information, and it will be filled by the rate * control algorithm according to what should be sent. For example, * if this array contains, in the format { <idx>, <count> } the * information:: * * { 3, 2 }, { 2, 2 }, { 1, 4 }, { -1, 0 }, { -1, 0 } * * then this means that the frame should be transmitted * up to twice at rate 3, up to twice at rate 2, and up to four * times at rate 1 if it doesn't get acknowledged. Say it gets * acknowledged by the peer after the fifth attempt, the status * information should then contain:: * * { 3, 2 }, { 2, 2 }, { 1, 1 }, { -1, 0 } ... * * since it was transmitted twice at rate 3, twice at rate 2 * and once at rate 1 after which we received an acknowledgement. */ struct ieee80211_tx_rate { s8 idx; u16 count:5, flags:11; } __packed; #define IEEE80211_MAX_TX_RETRY 31 static inline bool ieee80211_rate_valid(struct ieee80211_tx_rate *rate) { return rate->idx >= 0 && rate->count > 0; } static inline void ieee80211_rate_set_vht(struct ieee80211_tx_rate *rate, u8 mcs, u8 nss) { WARN_ON(mcs & ~0xF); WARN_ON((nss - 1) & ~0x7); rate->idx = ((nss - 1) << 4) | mcs; } static inline u8 ieee80211_rate_get_vht_mcs(const struct ieee80211_tx_rate *rate) { return rate->idx & 0xF; } static inline u8 ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) { return (rate->idx >> 4) + 1; } /** * struct ieee80211_tx_info - skb transmit information * * This structure is placed in skb->cb for three uses: * (1) mac80211 TX control - mac80211 tells the driver what to do * (2) driver internal use (if applicable) * (3) TX status information - driver tells mac80211 what happened * * @flags: transmit info flags, defined above * @band: the band to transmit on (use e.g. for checking for races), * not valid if the interface is an MLD since we won't know which * link the frame will be transmitted on * @hw_queue: HW queue to put the frame on, skb_get_queue_mapping() gives the AC * @status_data: internal data for TX status handling, assigned privately, * see also &enum ieee80211_status_data for the internal documentation * @status_data_idr: indicates status data is IDR allocated ID for ack frame * @tx_time_est: TX time estimate in units of 4us, used internally * @control: union part for control data * @control.rates: TX rates array to try * @control.rts_cts_rate_idx: rate for RTS or CTS * @control.use_rts: use RTS * @control.use_cts_prot: use RTS/CTS * @control.short_preamble: use short preamble (CCK only) * @control.skip_table: skip externally configured rate table * @control.jiffies: timestamp for expiry on powersave clients * @control.vif: virtual interface (may be NULL) * @control.hw_key: key to encrypt with (may be NULL) * @control.flags: control flags, see &enum mac80211_tx_control_flags * @control.enqueue_time: enqueue time (for iTXQs) * @driver_rates: alias to @control.rates to reserve space * @pad: padding * @rate_driver_data: driver use area if driver needs @control.rates * @status: union part for status data * @status.rates: attempted rates * @status.ack_signal: ACK signal * @status.ampdu_ack_len: AMPDU ack length * @status.ampdu_len: AMPDU length * @status.antenna: (legacy, kept only for iwlegacy) * @status.tx_time: airtime consumed for transmission; note this is only * used for WMM AC, not for airtime fairness * @status.flags: status flags, see &enum mac80211_tx_status_flags * @status.status_driver_data: driver use area * @ack: union part for pure ACK data * @ack.cookie: cookie for the ACK * @driver_data: array of driver_data pointers */ struct ieee80211_tx_info { /* common information */ u32 flags; u32 band:3, status_data_idr:1, status_data:13, hw_queue:4, tx_time_est:10; /* 1 free bit */ union { struct { union { /* rate control */ struct { struct ieee80211_tx_rate rates[ IEEE80211_TX_MAX_RATES]; s8 rts_cts_rate_idx; u8 use_rts:1; u8 use_cts_prot:1; u8 short_preamble:1; u8 skip_table:1; /* for injection only (bitmap) */ u8 antennas:2; /* 14 bits free */ }; /* only needed before rate control */ unsigned long jiffies; }; /* NB: vif can be NULL for injected frames */ struct ieee80211_vif *vif; struct ieee80211_key_conf *hw_key; u32 flags; codel_time_t enqueue_time; } control; struct { u64 cookie; } ack; struct { struct ieee80211_tx_rate rates[IEEE80211_TX_MAX_RATES]; s32 ack_signal; u8 ampdu_ack_len; u8 ampdu_len; u8 antenna; u8 pad; u16 tx_time; u8 flags; u8 pad2; void *status_driver_data[16 / sizeof(void *)]; } status; struct { struct ieee80211_tx_rate driver_rates[ IEEE80211_TX_MAX_RATES]; u8 pad[4]; void *rate_driver_data[ IEEE80211_TX_INFO_RATE_DRIVER_DATA_SIZE / sizeof(void *)]; }; void *driver_data[ IEEE80211_TX_INFO_DRIVER_DATA_SIZE / sizeof(void *)]; }; }; static inline u16 ieee80211_info_set_tx_time_est(struct ieee80211_tx_info *info, u16 tx_time_est) { /* We only have 10 bits in tx_time_est, so store airtime * in increments of 4us and clamp the maximum to 2**12-1 */ info->tx_time_est = min_t(u16, tx_time_est, 4095) >> 2; return info->tx_time_est << 2; } static inline u16 ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info) { return info->tx_time_est << 2; } /*** * struct ieee80211_rate_status - mrr stage for status path * * This struct is used in struct ieee80211_tx_status to provide drivers a * dynamic way to report about used rates and power levels per packet. * * @rate_idx The actual used rate. * @try_count How often the rate was tried. * @tx_power_idx An idx into the ieee80211_hw->tx_power_levels list of the * corresponding wifi hardware. The idx shall point to the power level * that was used when sending the packet. */ struct ieee80211_rate_status { struct rate_info rate_idx; u8 try_count; u8 tx_power_idx; }; /** * struct ieee80211_tx_status - extended tx status info for rate control * * @sta: Station that the packet was transmitted for * @info: Basic tx status information * @skb: Packet skb (can be NULL if not provided by the driver) * @rates: Mrr stages that were used when sending the packet * @n_rates: Number of mrr stages (count of instances for @rates) * @free_list: list where processed skbs are stored to be free'd by the driver * @ack_hwtstamp: Hardware timestamp of the received ack in nanoseconds * Only needed for Timing measurement and Fine timing measurement action * frames. Only reported by devices that have timestamping enabled. */ struct ieee80211_tx_status { struct ieee80211_sta *sta; struct ieee80211_tx_info *info; struct sk_buff *skb; struct ieee80211_rate_status *rates; ktime_t ack_hwtstamp; u8 n_rates; struct list_head *free_list; }; /** * struct ieee80211_scan_ies - descriptors for different blocks of IEs * * This structure is used to point to different blocks of IEs in HW scan * and scheduled scan. These blocks contain the IEs passed by userspace * and the ones generated by mac80211. * * @ies: pointers to band specific IEs. * @len: lengths of band_specific IEs. * @common_ies: IEs for all bands (especially vendor specific ones) * @common_ie_len: length of the common_ies */ struct ieee80211_scan_ies { const u8 *ies[NUM_NL80211_BANDS]; size_t len[NUM_NL80211_BANDS]; const u8 *common_ies; size_t common_ie_len; }; static inline struct ieee80211_tx_info *IEEE80211_SKB_CB(struct sk_buff *skb) { return (struct ieee80211_tx_info *)skb->cb; } static inline struct ieee80211_rx_status *IEEE80211_SKB_RXCB(struct sk_buff *skb) { return (struct ieee80211_rx_status *)skb->cb; } /** * ieee80211_tx_info_clear_status - clear TX status * * @info: The &struct ieee80211_tx_info to be cleared. * * When the driver passes an skb back to mac80211, it must report * a number of things in TX status. This function clears everything * in the TX status but the rate control information (it does clear * the count since you need to fill that in anyway). * * NOTE: While the rates array is kept intact, this will wipe all of the * driver_data fields in info, so it's up to the driver to restore * any fields it needs after calling this helper. */ static inline void ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) { int i; BUILD_BUG_ON(offsetof(struct ieee80211_tx_info, status.rates) != offsetof(struct ieee80211_tx_info, control.rates)); BUILD_BUG_ON(offsetof(struct ieee80211_tx_info, status.rates) != offsetof(struct ieee80211_tx_info, driver_rates)); BUILD_BUG_ON(offsetof(struct ieee80211_tx_info, status.rates) != 8); /* clear the rate counts */ for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) info->status.rates[i].count = 0; memset_after(&info->status, 0, rates); } /** * enum mac80211_rx_flags - receive flags * * These flags are used with the @flag member of &struct ieee80211_rx_status. * @RX_FLAG_MMIC_ERROR: Michael MIC error was reported on this frame. * Use together with %RX_FLAG_MMIC_STRIPPED. * @RX_FLAG_DECRYPTED: This frame was decrypted in hardware. * @RX_FLAG_MMIC_STRIPPED: the Michael MIC is stripped off this frame, * verification has been done by the hardware. * @RX_FLAG_IV_STRIPPED: The IV and ICV are stripped from this frame. * If this flag is set, the stack cannot do any replay detection * hence the driver or hardware will have to do that. * @RX_FLAG_PN_VALIDATED: Currently only valid for CCMP/GCMP frames, this * flag indicates that the PN was verified for replay protection. * Note that this flag is also currently only supported when a frame * is also decrypted (ie. @RX_FLAG_DECRYPTED must be set) * @RX_FLAG_DUP_VALIDATED: The driver should set this flag if it did * de-duplication by itself. * @RX_FLAG_FAILED_FCS_CRC: Set this flag if the FCS check failed on * the frame. * @RX_FLAG_FAILED_PLCP_CRC: Set this flag if the PCLP check failed on * the frame. * @RX_FLAG_MACTIME: The timestamp passed in the RX status (@mactime * field) is valid if this field is non-zero, and the position * where the timestamp was sampled depends on the value. * @RX_FLAG_MACTIME_START: The timestamp passed in the RX status (@mactime * field) is valid and contains the time the first symbol of the MPDU * was received. This is useful in monitor mode and for proper IBSS * merging. * @RX_FLAG_MACTIME_END: The timestamp passed in the RX status (@mactime * field) is valid and contains the time the last symbol of the MPDU * (including FCS) was received. * @RX_FLAG_MACTIME_PLCP_START: The timestamp passed in the RX status (@mactime * field) is valid and contains the time the SYNC preamble was received. * @RX_FLAG_MACTIME_IS_RTAP_TS64: The timestamp passed in the RX status @mactime * is only for use in the radiotap timestamp header, not otherwise a valid * @mactime value. Note this is a separate flag so that we continue to see * %RX_FLAG_MACTIME as unset. Also note that in this case the timestamp is * reported to be 64 bits wide, not just 32. * @RX_FLAG_NO_SIGNAL_VAL: The signal strength value is not present. * Valid only for data frames (mainly A-MPDU) * @RX_FLAG_AMPDU_DETAILS: A-MPDU details are known, in particular the reference * number (@ampdu_reference) must be populated and be a distinct number for * each A-MPDU * @RX_FLAG_AMPDU_LAST_KNOWN: last subframe is known, should be set on all * subframes of a single A-MPDU * @RX_FLAG_AMPDU_IS_LAST: this subframe is the last subframe of the A-MPDU * @RX_FLAG_AMPDU_DELIM_CRC_ERROR: A delimiter CRC error has been detected * on this subframe * @RX_FLAG_MIC_STRIPPED: The mic was stripped of this packet. Decryption was * done by the hardware * @RX_FLAG_ONLY_MONITOR: Report frame only to monitor interfaces without * processing it in any regular way. * This is useful if drivers offload some frames but still want to report * them for sniffing purposes. * @RX_FLAG_SKIP_MONITOR: Process and report frame to all interfaces except * monitor interfaces. * This is useful if drivers offload some frames but still want to report * them for sniffing purposes. * @RX_FLAG_AMSDU_MORE: Some drivers may prefer to report separate A-MSDU * subframes instead of a one huge frame for performance reasons. * All, but the last MSDU from an A-MSDU should have this flag set. E.g. * if an A-MSDU has 3 frames, the first 2 must have the flag set, while * the 3rd (last) one must not have this flag set. The flag is used to * deal with retransmission/duplication recovery properly since A-MSDU * subframes share the same sequence number. Reported subframes can be * either regular MSDU or singly A-MSDUs. Subframes must not be * interleaved with other frames. * @RX_FLAG_RADIOTAP_TLV_AT_END: This frame contains radiotap TLVs in the * skb->data (before the 802.11 header). * If used, the SKB's mac_header pointer must be set to point * to the 802.11 header after the TLVs, and any padding added after TLV * data to align to 4 must be cleared by the driver putting the TLVs * in the skb. * @RX_FLAG_ALLOW_SAME_PN: Allow the same PN as same packet before. * This is used for AMSDU subframes which can have the same PN as * the first subframe. * @RX_FLAG_ICV_STRIPPED: The ICV is stripped from this frame. CRC checking must * be done in the hardware. * @RX_FLAG_AMPDU_EOF_BIT: Value of the EOF bit in the A-MPDU delimiter for this * frame * @RX_FLAG_AMPDU_EOF_BIT_KNOWN: The EOF value is known * @RX_FLAG_RADIOTAP_HE: HE radiotap data is present * (&struct ieee80211_radiotap_he, mac80211 will fill in * * - DATA3_DATA_MCS * - DATA3_DATA_DCM * - DATA3_CODING * - DATA5_GI * - DATA5_DATA_BW_RU_ALLOC * - DATA6_NSTS * - DATA3_STBC * * from the RX info data, so leave those zeroed when building this data) * @RX_FLAG_RADIOTAP_HE_MU: HE MU radiotap data is present * (&struct ieee80211_radiotap_he_mu) * @RX_FLAG_RADIOTAP_LSIG: L-SIG radiotap data is present * @RX_FLAG_NO_PSDU: use the frame only for radiotap reporting, with * the "0-length PSDU" field included there. The value for it is * in &struct ieee80211_rx_status. Note that if this value isn't * known the frame shouldn't be reported. * @RX_FLAG_8023: the frame has an 802.3 header (decap offload performed by * hardware or driver) */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), RX_FLAG_DECRYPTED = BIT(1), RX_FLAG_ONLY_MONITOR = BIT(2), RX_FLAG_MMIC_STRIPPED = BIT(3), RX_FLAG_IV_STRIPPED = BIT(4), RX_FLAG_FAILED_FCS_CRC = BIT(5), RX_FLAG_FAILED_PLCP_CRC = BIT(6), RX_FLAG_MACTIME_IS_RTAP_TS64 = BIT(7), RX_FLAG_NO_SIGNAL_VAL = BIT(8), RX_FLAG_AMPDU_DETAILS = BIT(9), RX_FLAG_PN_VALIDATED = BIT(10), RX_FLAG_DUP_VALIDATED = BIT(11), RX_FLAG_AMPDU_LAST_KNOWN = BIT(12), RX_FLAG_AMPDU_IS_LAST = BIT(13), RX_FLAG_AMPDU_DELIM_CRC_ERROR = BIT(14), /* one free bit at 15 */ RX_FLAG_MACTIME = BIT(16) | BIT(17), RX_FLAG_MACTIME_PLCP_START = 1 << 16, RX_FLAG_MACTIME_START = 2 << 16, RX_FLAG_MACTIME_END = 3 << 16, RX_FLAG_SKIP_MONITOR = BIT(18), RX_FLAG_AMSDU_MORE = BIT(19), RX_FLAG_RADIOTAP_TLV_AT_END = BIT(20), RX_FLAG_MIC_STRIPPED = BIT(21), RX_FLAG_ALLOW_SAME_PN = BIT(22), RX_FLAG_ICV_STRIPPED = BIT(23), RX_FLAG_AMPDU_EOF_BIT = BIT(24), RX_FLAG_AMPDU_EOF_BIT_KNOWN = BIT(25), RX_FLAG_RADIOTAP_HE = BIT(26), RX_FLAG_RADIOTAP_HE_MU = BIT(27), RX_FLAG_RADIOTAP_LSIG = BIT(28), RX_FLAG_NO_PSDU = BIT(29), RX_FLAG_8023 = BIT(30), }; /** * enum mac80211_rx_encoding_flags - MCS & bandwidth flags * * @RX_ENC_FLAG_SHORTPRE: Short preamble was used for this frame * @RX_ENC_FLAG_SHORT_GI: Short guard interval was used * @RX_ENC_FLAG_HT_GF: This frame was received in a HT-greenfield transmission, * if the driver fills this value it should add * %IEEE80211_RADIOTAP_MCS_HAVE_FMT * to @hw.radiotap_mcs_details to advertise that fact. * @RX_ENC_FLAG_LDPC: LDPC was used * @RX_ENC_FLAG_STBC_MASK: STBC 2 bit bitmask. 1 - Nss=1, 2 - Nss=2, 3 - Nss=3 * @RX_ENC_FLAG_BF: packet was beamformed */ enum mac80211_rx_encoding_flags { RX_ENC_FLAG_SHORTPRE = BIT(0), RX_ENC_FLAG_SHORT_GI = BIT(2), RX_ENC_FLAG_HT_GF = BIT(3), RX_ENC_FLAG_STBC_MASK = BIT(4) | BIT(5), RX_ENC_FLAG_LDPC = BIT(6), RX_ENC_FLAG_BF = BIT(7), }; #define RX_ENC_FLAG_STBC_SHIFT 4 enum mac80211_rx_encoding { RX_ENC_LEGACY = 0, RX_ENC_HT, RX_ENC_VHT, RX_ENC_HE, RX_ENC_EHT, }; /** * struct ieee80211_rx_status - receive status * * The low-level driver should provide this information (the subset * supported by hardware) to the 802.11 code with each received * frame, in the skb's control buffer (cb). * * @mactime: value in microseconds of the 64-bit Time Synchronization Function * (TSF) timer when the first data symbol (MPDU) arrived at the hardware. * @boottime_ns: CLOCK_BOOTTIME timestamp the frame was received at, this is * needed only for beacons and probe responses that update the scan cache. * @ack_tx_hwtstamp: Hardware timestamp for the ack TX in nanoseconds. Only * needed for Timing measurement and Fine timing measurement action frames. * Only reported by devices that have timestamping enabled. * @device_timestamp: arbitrary timestamp for the device, mac80211 doesn't use * it but can store it and pass it back to the driver for synchronisation * @band: the active band when this frame was received * @freq: frequency the radio was tuned to when receiving this frame, in MHz * This field must be set for management frames, but isn't strictly needed * for data (other) frames - for those it only affects radiotap reporting. * @freq_offset: @freq has a positive offset of 500Khz. * @signal: signal strength when receiving this frame, either in dBm, in dB or * unspecified depending on the hardware capabilities flags * @IEEE80211_HW_SIGNAL_* * @chains: bitmask of receive chains for which separate signal strength * values were filled. * @chain_signal: per-chain signal strength, in dBm (unlike @signal, doesn't * support dB or unspecified units) * @antenna: antenna used * @rate_idx: index of data rate into band's supported rates or MCS index if * HT or VHT is used (%RX_FLAG_HT/%RX_FLAG_VHT) * @nss: number of streams (VHT, HE and EHT only) * @flag: %RX_FLAG_\* * @encoding: &enum mac80211_rx_encoding * @bw: &enum rate_info_bw * @enc_flags: uses bits from &enum mac80211_rx_encoding_flags * @he_ru: HE RU, from &enum nl80211_he_ru_alloc * @he_gi: HE GI, from &enum nl80211_he_gi * @he_dcm: HE DCM value * @eht: EHT specific rate information * @eht.ru: EHT RU, from &enum nl80211_eht_ru_alloc * @eht.gi: EHT GI, from &enum nl80211_eht_gi * @rx_flags: internal RX flags for mac80211 * @ampdu_reference: A-MPDU reference number, must be a different value for * each A-MPDU but the same for each subframe within one A-MPDU * @zero_length_psdu_type: radiotap type of the 0-length PSDU * @link_valid: if the link which is identified by @link_id is valid. This flag * is set only when connection is MLO. * @link_id: id of the link used to receive the packet. This is used along with * @link_valid. */ struct ieee80211_rx_status { u64 mactime; union { u64 boottime_ns; ktime_t ack_tx_hwtstamp; }; u32 device_timestamp; u32 ampdu_reference; u32 flag; u16 freq: 13, freq_offset: 1; u8 enc_flags; u8 encoding:3, bw:4; union { struct { u8 he_ru:3; u8 he_gi:2; u8 he_dcm:1; }; struct { u8 ru:4; u8 gi:2; } eht; }; u8 rate_idx; u8 nss; u8 rx_flags; u8 band; u8 antenna; s8 signal; u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; u8 zero_length_psdu_type; u8 link_valid:1, link_id:4; }; static inline u32 ieee80211_rx_status_to_khz(struct ieee80211_rx_status *rx_status) { return MHZ_TO_KHZ(rx_status->freq) + (rx_status->freq_offset ? 500 : 0); } /** * enum ieee80211_conf_flags - configuration flags * * Flags to define PHY configuration options * * @IEEE80211_CONF_MONITOR: there's a monitor interface present -- use this * to determine for example whether to calculate timestamps for packets * or not, do not use instead of filter flags! * @IEEE80211_CONF_PS: Enable 802.11 power save mode (managed mode only). * This is the power save mode defined by IEEE 802.11-2007 section 11.2, * meaning that the hardware still wakes up for beacons, is able to * transmit frames and receive the possible acknowledgment frames. * Not to be confused with hardware specific wakeup/sleep states, * driver is responsible for that. See the section "Powersave support" * for more. * @IEEE80211_CONF_IDLE: The device is running, but idle; if the flag is set * the driver should be prepared to handle configuration requests but * may turn the device off as much as possible. Typically, this flag will * be set when an interface is set UP but not associated or scanning, but * it can also be unset in that case when monitor interfaces are active. * @IEEE80211_CONF_OFFCHANNEL: The device is currently not on its main * operating channel. */ enum ieee80211_conf_flags { IEEE80211_CONF_MONITOR = (1<<0), IEEE80211_CONF_PS = (1<<1), IEEE80211_CONF_IDLE = (1<<2), IEEE80211_CONF_OFFCHANNEL = (1<<3), }; /** * enum ieee80211_conf_changed - denotes which configuration changed * * @IEEE80211_CONF_CHANGE_LISTEN_INTERVAL: the listen interval changed * @IEEE80211_CONF_CHANGE_MONITOR: the monitor flag changed * @IEEE80211_CONF_CHANGE_PS: the PS flag or dynamic PS timeout changed * @IEEE80211_CONF_CHANGE_POWER: the TX power changed * @IEEE80211_CONF_CHANGE_CHANNEL: the channel/channel_type changed * @IEEE80211_CONF_CHANGE_RETRY_LIMITS: retry limits changed * @IEEE80211_CONF_CHANGE_IDLE: Idle flag changed * @IEEE80211_CONF_CHANGE_SMPS: Spatial multiplexing powersave mode changed * Note that this is only valid if channel contexts are not used, * otherwise each channel context has the number of chains listed. */ enum ieee80211_conf_changed { IEEE80211_CONF_CHANGE_SMPS = BIT(1), IEEE80211_CONF_CHANGE_LISTEN_INTERVAL = BIT(2), IEEE80211_CONF_CHANGE_MONITOR = BIT(3), IEEE80211_CONF_CHANGE_PS = BIT(4), IEEE80211_CONF_CHANGE_POWER = BIT(5), IEEE80211_CONF_CHANGE_CHANNEL = BIT(6), IEEE80211_CONF_CHANGE_RETRY_LIMITS = BIT(7), IEEE80211_CONF_CHANGE_IDLE = BIT(8), }; /** * enum ieee80211_smps_mode - spatial multiplexing power save mode * * @IEEE80211_SMPS_AUTOMATIC: automatic * @IEEE80211_SMPS_OFF: off * @IEEE80211_SMPS_STATIC: static * @IEEE80211_SMPS_DYNAMIC: dynamic * @IEEE80211_SMPS_NUM_MODES: internal, don't use */ enum ieee80211_smps_mode { IEEE80211_SMPS_AUTOMATIC, IEEE80211_SMPS_OFF, IEEE80211_SMPS_STATIC, IEEE80211_SMPS_DYNAMIC, /* keep last */ IEEE80211_SMPS_NUM_MODES, }; /** * struct ieee80211_conf - configuration of the device * * This struct indicates how the driver shall configure the hardware. * * @flags: configuration flags defined above * * @listen_interval: listen interval in units of beacon interval * @ps_dtim_period: The DTIM period of the AP we're connected to, for use * in power saving. Power saving will not be enabled until a beacon * has been received and the DTIM period is known. * @dynamic_ps_timeout: The dynamic powersave timeout (in ms), see the * powersave documentation below. This variable is valid only when * the CONF_PS flag is set. * * @power_level: requested transmit power (in dBm), backward compatibility * value only that is set to the minimum of all interfaces * * @chandef: the channel definition to tune to * @radar_enabled: whether radar detection is enabled * * @long_frame_max_tx_count: Maximum number of transmissions for a "long" frame * (a frame not RTS protected), called "dot11LongRetryLimit" in 802.11, * but actually means the number of transmissions not the number of retries * @short_frame_max_tx_count: Maximum number of transmissions for a "short" * frame, called "dot11ShortRetryLimit" in 802.11, but actually means the * number of transmissions not the number of retries * * @smps_mode: spatial multiplexing powersave mode; note that * %IEEE80211_SMPS_STATIC is used when the device is not * configured for an HT channel. * Note that this is only valid if channel contexts are not used, * otherwise each channel context has the number of chains listed. */ struct ieee80211_conf { u32 flags; int power_level, dynamic_ps_timeout; u16 listen_interval; u8 ps_dtim_period; u8 long_frame_max_tx_count, short_frame_max_tx_count; struct cfg80211_chan_def chandef; bool radar_enabled; enum ieee80211_smps_mode smps_mode; }; /** * struct ieee80211_channel_switch - holds the channel switch data * * The information provided in this structure is required for channel switch * operation. * * @timestamp: value in microseconds of the 64-bit Time Synchronization * Function (TSF) timer when the frame containing the channel switch * announcement was received. This is simply the rx.mactime parameter * the driver passed into mac80211. * @device_timestamp: arbitrary timestamp for the device, this is the * rx.device_timestamp parameter the driver passed to mac80211. * @block_tx: Indicates whether transmission must be blocked before the * scheduled channel switch, as indicated by the AP. * @chandef: the new channel to switch to * @count: the number of TBTT's until the channel switch event * @delay: maximum delay between the time the AP transmitted the last beacon in * current channel and the expected time of the first beacon in the new * channel, expressed in TU. * @link_id: the link ID of the link doing the channel switch, 0 for non-MLO */ struct ieee80211_channel_switch { u64 timestamp; u32 device_timestamp; bool block_tx; struct cfg80211_chan_def chandef; u8 count; u8 link_id; u32 delay; }; /** * enum ieee80211_vif_flags - virtual interface flags * * @IEEE80211_VIF_BEACON_FILTER: the device performs beacon filtering * on this virtual interface to avoid unnecessary CPU wakeups * @IEEE80211_VIF_SUPPORTS_CQM_RSSI: the device can do connection quality * monitoring on this virtual interface -- i.e. it can monitor * connection quality related parameters, such as the RSSI level and * provide notifications if configured trigger levels are reached. * @IEEE80211_VIF_SUPPORTS_UAPSD: The device can do U-APSD for this * interface. This flag should be set during interface addition, * but may be set/cleared as late as authentication to an AP. It is * only valid for managed/station mode interfaces. * @IEEE80211_VIF_GET_NOA_UPDATE: request to handle NOA attributes * and send P2P_PS notification to the driver if NOA changed, even * this is not pure P2P vif. * @IEEE80211_VIF_EML_ACTIVE: The driver indicates that EML operation is * enabled for the interface. * @IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW: Ignore wider bandwidth OFDMA * operation on this interface and request a channel context without * the AP definition. Use this e.g. because the device is able to * handle OFDMA (downlink and trigger for uplink) on a per-AP basis. * @IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC: indicates that the AP sta should * be removed only after setting the vif as unassociated, and not the * opposite. Only relevant for STA vifs. */ enum ieee80211_vif_flags { IEEE80211_VIF_BEACON_FILTER = BIT(0), IEEE80211_VIF_SUPPORTS_CQM_RSSI = BIT(1), IEEE80211_VIF_SUPPORTS_UAPSD = BIT(2), IEEE80211_VIF_GET_NOA_UPDATE = BIT(3), IEEE80211_VIF_EML_ACTIVE = BIT(4), IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW = BIT(5), IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC = BIT(6), }; /** * enum ieee80211_offload_flags - virtual interface offload flags * * @IEEE80211_OFFLOAD_ENCAP_ENABLED: tx encapsulation offload is enabled * The driver supports sending frames passed as 802.3 frames by mac80211. * It must also support sending 802.11 packets for the same interface. * @IEEE80211_OFFLOAD_ENCAP_4ADDR: support 4-address mode encapsulation offload * @IEEE80211_OFFLOAD_DECAP_ENABLED: rx encapsulation offload is enabled * The driver supports passing received 802.11 frames as 802.3 frames to * mac80211. */ enum ieee80211_offload_flags { IEEE80211_OFFLOAD_ENCAP_ENABLED = BIT(0), IEEE80211_OFFLOAD_ENCAP_4ADDR = BIT(1), IEEE80211_OFFLOAD_DECAP_ENABLED = BIT(2), }; /** * struct ieee80211_vif_cfg - interface configuration * @assoc: association status * @ibss_joined: indicates whether this station is part of an IBSS or not * @ibss_creator: indicates if a new IBSS network is being created * @ps: power-save mode (STA only). This flag is NOT affected by * offchannel/dynamic_ps operations. * @aid: association ID number, valid only when @assoc is true * @eml_cap: EML capabilities as described in P802.11be_D4.1 Figure 9-1001j. * @eml_med_sync_delay: Medium Synchronization delay as described in * P802.11be_D4.1 Figure 9-1001i. * @mld_capa_op: MLD Capabilities and Operations per P802.11be_D4.1 * Figure 9-1001k * @arp_addr_list: List of IPv4 addresses for hardware ARP filtering. The * may filter ARP queries targeted for other addresses than listed here. * The driver must allow ARP queries targeted for all address listed here * to pass through. An empty list implies no ARP queries need to pass. * @arp_addr_cnt: Number of addresses currently on the list. Note that this * may be larger than %IEEE80211_BSS_ARP_ADDR_LIST_LEN (the arp_addr_list * array size), it's up to the driver what to do in that case. * @ssid: The SSID of the current vif. Valid in AP and IBSS mode. * @ssid_len: Length of SSID given in @ssid. * @s1g: BSS is S1G BSS (affects Association Request format). * @idle: This interface is idle. There's also a global idle flag in the * hardware config which may be more appropriate depending on what * your driver/device needs to do. * @ap_addr: AP MLD address, or BSSID for non-MLO connections * (station mode only) */ struct ieee80211_vif_cfg { /* association related data */ bool assoc, ibss_joined; bool ibss_creator; bool ps; u16 aid; u16 eml_cap; u16 eml_med_sync_delay; u16 mld_capa_op; __be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; int arp_addr_cnt; u8 ssid[IEEE80211_MAX_SSID_LEN]; size_t ssid_len; bool s1g; bool idle; u8 ap_addr[ETH_ALEN] __aligned(2); }; #define IEEE80211_TTLM_NUM_TIDS 8 /** * struct ieee80211_neg_ttlm - negotiated TID to link map info * * @downlink: bitmap of active links per TID for downlink, or 0 if mapping for * this TID is not included. * @uplink: bitmap of active links per TID for uplink, or 0 if mapping for this * TID is not included. * @valid: info is valid or not. */ struct ieee80211_neg_ttlm { u16 downlink[IEEE80211_TTLM_NUM_TIDS]; u16 uplink[IEEE80211_TTLM_NUM_TIDS]; bool valid; }; /** * enum ieee80211_neg_ttlm_res - return value for negotiated TTLM handling * @NEG_TTLM_RES_ACCEPT: accept the request * @NEG_TTLM_RES_REJECT: reject the request * @NEG_TTLM_RES_SUGGEST_PREFERRED: reject and suggest a new mapping */ enum ieee80211_neg_ttlm_res { NEG_TTLM_RES_ACCEPT, NEG_TTLM_RES_REJECT, NEG_TTLM_RES_SUGGEST_PREFERRED }; /** * struct ieee80211_vif - per-interface data * * Data in this structure is continually present for driver * use during the life of a virtual interface. * * @type: type of this virtual interface * @cfg: vif configuration, see &struct ieee80211_vif_cfg * @bss_conf: BSS configuration for this interface, either our own * or the BSS we're associated to * @link_conf: in case of MLD, the per-link BSS configuration, * indexed by link ID * @valid_links: bitmap of valid links, or 0 for non-MLO. * @active_links: The bitmap of active links, or 0 for non-MLO. * The driver shouldn't change this directly, but use the * API calls meant for that purpose. * @dormant_links: subset of the valid links that are disabled/suspended * due to advertised or negotiated TTLM respectively. * 0 for non-MLO. * @suspended_links: subset of dormant_links representing links that are * suspended due to negotiated TTLM, and could be activated in the * future by tearing down the TTLM negotiation. * 0 for non-MLO. * @neg_ttlm: negotiated TID to link mapping info. * see &struct ieee80211_neg_ttlm. * @addr: address of this interface * @addr_valid: indicates if the address is actively used. Set to false for * passive monitor interfaces, true in all other cases. * @p2p: indicates whether this AP or STA interface is a p2p * interface, i.e. a GO or p2p-sta respectively * @netdev_features: tx netdev features supported by the hardware for this * vif. mac80211 initializes this to hw->netdev_features, and the driver * can mask out specific tx features. mac80211 will handle software fixup * for masked offloads (GSO, CSUM) * @driver_flags: flags/capabilities the driver has for this interface, * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed * at runtime, mac80211 will never touch this field * @offload_flags: hardware offload capabilities/flags for this interface. * These are initialized by mac80211 before calling .add_interface, * .change_interface or .update_vif_offload and updated by the driver * within these ops, based on supported features or runtime change * restrictions. * @hw_queue: hardware queue for each AC * @cab_queue: content-after-beacon (DTIM beacon really) queue, AP mode only * @debugfs_dir: debugfs dentry, can be used by drivers to create own per * interface debug files. Note that it will be NULL for the virtual * monitor interface (if that is requested.) * @probe_req_reg: probe requests should be reported to mac80211 for this * interface. * @rx_mcast_action_reg: multicast Action frames should be reported to mac80211 * for this interface. * @drv_priv: data area for driver use, will always be aligned to * sizeof(void \*). * @txq: the multicast data TX queue * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see * &enum ieee80211_offload_flags. * @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled. */ struct ieee80211_vif { enum nl80211_iftype type; struct ieee80211_vif_cfg cfg; struct ieee80211_bss_conf bss_conf; struct ieee80211_bss_conf __rcu *link_conf[IEEE80211_MLD_MAX_NUM_LINKS]; u16 valid_links, active_links, dormant_links, suspended_links; struct ieee80211_neg_ttlm neg_ttlm; u8 addr[ETH_ALEN] __aligned(2); bool addr_valid; bool p2p; u8 cab_queue; u8 hw_queue[IEEE80211_NUM_ACS]; struct ieee80211_txq *txq; netdev_features_t netdev_features; u32 driver_flags; u32 offload_flags; #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *debugfs_dir; #endif bool probe_req_reg; bool rx_mcast_action_reg; struct ieee80211_vif *mbssid_tx_vif; /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; /** * ieee80211_vif_usable_links - Return the usable links for the vif * @vif: the vif for which the usable links are requested * Return: the usable link bitmap */ static inline u16 ieee80211_vif_usable_links(const struct ieee80211_vif *vif) { return vif->valid_links & ~vif->dormant_links; } /** * ieee80211_vif_is_mld - Returns true iff the vif is an MLD one * @vif: the vif * Return: %true if the vif is an MLD, %false otherwise. */ static inline bool ieee80211_vif_is_mld(const struct ieee80211_vif *vif) { /* valid_links != 0 indicates this vif is an MLD */ return vif->valid_links != 0; } /** * ieee80211_vif_link_active - check if a given link is active * @vif: the vif * @link_id: the link ID to check * Return: %true if the vif is an MLD and the link is active, or if * the vif is not an MLD and the link ID is 0; %false otherwise. */ static inline bool ieee80211_vif_link_active(const struct ieee80211_vif *vif, unsigned int link_id) { if (!ieee80211_vif_is_mld(vif)) return link_id == 0; return vif->active_links & BIT(link_id); } #define for_each_vif_active_link(vif, link, link_id) \ for (link_id = 0; link_id < ARRAY_SIZE((vif)->link_conf); link_id++) \ if ((!(vif)->active_links || \ (vif)->active_links & BIT(link_id)) && \ (link = link_conf_dereference_check(vif, link_id))) static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif) { #ifdef CONFIG_MAC80211_MESH return vif->type == NL80211_IFTYPE_MESH_POINT; #endif return false; } /** * wdev_to_ieee80211_vif - return a vif struct from a wdev * @wdev: the wdev to get the vif for * * This can be used by mac80211 drivers with direct cfg80211 APIs * (like the vendor commands) that get a wdev. * * Return: pointer to the wdev, or %NULL if the given wdev isn't * associated with a vif that the driver knows about (e.g. monitor * or AP_VLAN interfaces.) */ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev); /** * ieee80211_vif_to_wdev - return a wdev struct from a vif * @vif: the vif to get the wdev for * * This can be used by mac80211 drivers with direct cfg80211 APIs * (like the vendor commands) that needs to get the wdev for a vif. * This can also be useful to get the netdev associated to a vif. * * Return: pointer to the wdev */ struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif); static inline bool lockdep_vif_wiphy_mutex_held(struct ieee80211_vif *vif) { return lockdep_is_held(&ieee80211_vif_to_wdev(vif)->wiphy->mtx); } #define link_conf_dereference_protected(vif, link_id) \ rcu_dereference_protected((vif)->link_conf[link_id], \ lockdep_vif_wiphy_mutex_held(vif)) #define link_conf_dereference_check(vif, link_id) \ rcu_dereference_check((vif)->link_conf[link_id], \ lockdep_vif_wiphy_mutex_held(vif)) /** * enum ieee80211_key_flags - key flags * * These flags are used for communication about keys between the driver * and mac80211, with the @flags parameter of &struct ieee80211_key_conf. * * @IEEE80211_KEY_FLAG_GENERATE_IV: This flag should be set by the * driver to indicate that it requires IV generation for this * particular key. Setting this flag does not necessarily mean that SKBs * will have sufficient tailroom for ICV or MIC. * @IEEE80211_KEY_FLAG_GENERATE_MMIC: This flag should be set by * the driver for a TKIP key if it requires Michael MIC * generation in software. * @IEEE80211_KEY_FLAG_PAIRWISE: Set by mac80211, this flag indicates * that the key is pairwise rather then a shared key. * @IEEE80211_KEY_FLAG_SW_MGMT_TX: This flag should be set by the driver for a * CCMP/GCMP key if it requires CCMP/GCMP encryption of management frames * (MFP) to be done in software. * @IEEE80211_KEY_FLAG_PUT_IV_SPACE: This flag should be set by the driver * if space should be prepared for the IV, but the IV * itself should not be generated. Do not set together with * @IEEE80211_KEY_FLAG_GENERATE_IV on the same key. Setting this flag does * not necessarily mean that SKBs will have sufficient tailroom for ICV or * MIC. * @IEEE80211_KEY_FLAG_RX_MGMT: This key will be used to decrypt received * management frames. The flag can help drivers that have a hardware * crypto implementation that doesn't deal with management frames * properly by allowing them to not upload the keys to hardware and * fall back to software crypto. Note that this flag deals only with * RX, if your crypto engine can't deal with TX you can also set the * %IEEE80211_KEY_FLAG_SW_MGMT_TX flag to encrypt such frames in SW. * @IEEE80211_KEY_FLAG_GENERATE_IV_MGMT: This flag should be set by the * driver for a CCMP/GCMP key to indicate that is requires IV generation * only for management frames (MFP). * @IEEE80211_KEY_FLAG_RESERVE_TAILROOM: This flag should be set by the * driver for a key to indicate that sufficient tailroom must always * be reserved for ICV or MIC, even when HW encryption is enabled. * @IEEE80211_KEY_FLAG_PUT_MIC_SPACE: This flag should be set by the driver for * a TKIP key if it only requires MIC space. Do not set together with * @IEEE80211_KEY_FLAG_GENERATE_MMIC on the same key. * @IEEE80211_KEY_FLAG_NO_AUTO_TX: Key needs explicit Tx activation. * @IEEE80211_KEY_FLAG_GENERATE_MMIE: This flag should be set by the driver * for a AES_CMAC or a AES_GMAC key to indicate that it requires sequence * number generation only * @IEEE80211_KEY_FLAG_SPP_AMSDU: SPP A-MSDUs can be used with this key * (set by mac80211 from the sta->spp_amsdu flag) */ enum ieee80211_key_flags { IEEE80211_KEY_FLAG_GENERATE_IV_MGMT = BIT(0), IEEE80211_KEY_FLAG_GENERATE_IV = BIT(1), IEEE80211_KEY_FLAG_GENERATE_MMIC = BIT(2), IEEE80211_KEY_FLAG_PAIRWISE = BIT(3), IEEE80211_KEY_FLAG_SW_MGMT_TX = BIT(4), IEEE80211_KEY_FLAG_PUT_IV_SPACE = BIT(5), IEEE80211_KEY_FLAG_RX_MGMT = BIT(6), IEEE80211_KEY_FLAG_RESERVE_TAILROOM = BIT(7), IEEE80211_KEY_FLAG_PUT_MIC_SPACE = BIT(8), IEEE80211_KEY_FLAG_NO_AUTO_TX = BIT(9), IEEE80211_KEY_FLAG_GENERATE_MMIE = BIT(10), IEEE80211_KEY_FLAG_SPP_AMSDU = BIT(11), }; /** * struct ieee80211_key_conf - key information * * This key information is given by mac80211 to the driver by * the set_key() callback in &struct ieee80211_ops. * * @hw_key_idx: To be set by the driver, this is the key index the driver * wants to be given when a frame is transmitted and needs to be * encrypted in hardware. * @cipher: The key's cipher suite selector. * @tx_pn: PN used for TX keys, may be used by the driver as well if it * needs to do software PN assignment by itself (e.g. due to TSO) * @flags: key flags, see &enum ieee80211_key_flags. * @keyidx: the key index (0-7) * @keylen: key material length * @key: key material. For ALG_TKIP the key is encoded as a 256-bit (32 byte) * data block: * - Temporal Encryption Key (128 bits) * - Temporal Authenticator Tx MIC Key (64 bits) * - Temporal Authenticator Rx MIC Key (64 bits) * @icv_len: The ICV length for this key type * @iv_len: The IV length for this key type * @link_id: the link ID, 0 for non-MLO, or -1 for pairwise keys */ struct ieee80211_key_conf { atomic64_t tx_pn; u32 cipher; u8 icv_len; u8 iv_len; u8 hw_key_idx; s8 keyidx; u16 flags; s8 link_id; u8 keylen; u8 key[]; }; #define IEEE80211_MAX_PN_LEN 16 #define TKIP_PN_TO_IV16(pn) ((u16)(pn & 0xffff)) #define TKIP_PN_TO_IV32(pn) ((u32)((pn >> 16) & 0xffffffff)) /** * struct ieee80211_key_seq - key sequence counter * * @tkip: TKIP data, containing IV32 and IV16 in host byte order * @ccmp: PN data, most significant byte first (big endian, * reverse order than in packet) * @aes_cmac: PN data, most significant byte first (big endian, * reverse order than in packet) * @aes_gmac: PN data, most significant byte first (big endian, * reverse order than in packet) * @gcmp: PN data, most significant byte first (big endian, * reverse order than in packet) * @hw: data for HW-only (e.g. cipher scheme) keys */ struct ieee80211_key_seq { union { struct { u32 iv32; u16 iv16; } tkip; struct { u8 pn[6]; } ccmp; struct { u8 pn[6]; } aes_cmac; struct { u8 pn[6]; } aes_gmac; struct { u8 pn[6]; } gcmp; struct { u8 seq[IEEE80211_MAX_PN_LEN]; u8 seq_len; } hw; }; }; /** * enum set_key_cmd - key command * * Used with the set_key() callback in &struct ieee80211_ops, this * indicates whether a key is being removed or added. * * @SET_KEY: a key is set * @DISABLE_KEY: a key must be disabled */ enum set_key_cmd { SET_KEY, DISABLE_KEY, }; /** * enum ieee80211_sta_state - station state * * @IEEE80211_STA_NOTEXIST: station doesn't exist at all, * this is a special state for add/remove transitions * @IEEE80211_STA_NONE: station exists without special state * @IEEE80211_STA_AUTH: station is authenticated * @IEEE80211_STA_ASSOC: station is associated * @IEEE80211_STA_AUTHORIZED: station is authorized (802.1X) */ enum ieee80211_sta_state { /* NOTE: These need to be ordered correctly! */ IEEE80211_STA_NOTEXIST, IEEE80211_STA_NONE, IEEE80211_STA_AUTH, IEEE80211_STA_ASSOC, IEEE80211_STA_AUTHORIZED, }; /** * enum ieee80211_sta_rx_bandwidth - station RX bandwidth * @IEEE80211_STA_RX_BW_20: station can only receive 20 MHz * @IEEE80211_STA_RX_BW_40: station can receive up to 40 MHz * @IEEE80211_STA_RX_BW_80: station can receive up to 80 MHz * @IEEE80211_STA_RX_BW_160: station can receive up to 160 MHz * (including 80+80 MHz) * @IEEE80211_STA_RX_BW_320: station can receive up to 320 MHz * * Implementation note: 20 must be zero to be initialized * correctly, the values must be sorted. */ enum ieee80211_sta_rx_bandwidth { IEEE80211_STA_RX_BW_20 = 0, IEEE80211_STA_RX_BW_40, IEEE80211_STA_RX_BW_80, IEEE80211_STA_RX_BW_160, IEEE80211_STA_RX_BW_320, }; #define IEEE80211_STA_RX_BW_MAX IEEE80211_STA_RX_BW_320 /** * struct ieee80211_sta_rates - station rate selection table * * @rcu_head: RCU head used for freeing the table on update * @rate: transmit rates/flags to be used by default. * Overriding entries per-packet is possible by using cb tx control. */ struct ieee80211_sta_rates { struct rcu_head rcu_head; struct { s8 idx; u8 count; u8 count_cts; u8 count_rts; u16 flags; } rate[IEEE80211_TX_RATE_TABLE_SIZE]; }; /** * struct ieee80211_sta_txpwr - station txpower configuration * * Used to configure txpower for station. * * @power: indicates the tx power, in dBm, to be used when sending data frames * to the STA. * @type: In particular if TPC %type is NL80211_TX_POWER_LIMITED then tx power * will be less than or equal to specified from userspace, whereas if TPC * %type is NL80211_TX_POWER_AUTOMATIC then it indicates default tx power. * NL80211_TX_POWER_FIXED is not a valid configuration option for * per peer TPC. */ struct ieee80211_sta_txpwr { s16 power; enum nl80211_tx_power_setting type; }; /** * struct ieee80211_sta_aggregates - info that is aggregated from active links * * Used for any per-link data that needs to be aggregated and updated in the * main &struct ieee80211_sta when updated or the active links change. * * @max_amsdu_len: indicates the maximal length of an A-MSDU in bytes. * This field is always valid for packets with a VHT preamble. * For packets with a HT preamble, additional limits apply: * * * If the skb is transmitted as part of a BA agreement, the * A-MSDU maximal size is min(max_amsdu_len, 4065) bytes. * * If the skb is not part of a BA agreement, the A-MSDU maximal * size is min(max_amsdu_len, 7935) bytes. * * Both additional HT limits must be enforced by the low level * driver. This is defined by the spec (IEEE 802.11-2012 section * 8.3.2.2 NOTE 2). * @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control. * @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID */ struct ieee80211_sta_aggregates { u16 max_amsdu_len; u16 max_rc_amsdu_len; u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS]; }; /** * struct ieee80211_link_sta - station Link specific info * All link specific info for a STA link for a non MLD STA(single) * or a MLD STA(multiple entries) are stored here. * * @sta: reference to owning STA * @addr: MAC address of the Link STA. For non-MLO STA this is same as the addr * in ieee80211_sta. For MLO Link STA this addr can be same or different * from addr in ieee80211_sta (representing MLD STA addr) * @link_id: the link ID for this link STA (0 for deflink) * @smps_mode: current SMPS mode (off, static or dynamic) * @supp_rates: Bitmap of supported rates * @ht_cap: HT capabilities of this STA; restricted to our own capabilities * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities * @he_cap: HE capabilities of this STA * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities * @eht_cap: EHT capabilities of this STA * @agg: per-link data for multi-link aggregation * @bandwidth: current bandwidth the station can receive with * @rx_nss: in HT/VHT, the maximum number of spatial streams the * station can receive at the moment, changed by operating mode * notifications and capabilities. The value is only valid after * the station moves to associated state. * @txpwr: the station tx power configuration * */ struct ieee80211_link_sta { struct ieee80211_sta *sta; u8 addr[ETH_ALEN]; u8 link_id; enum ieee80211_smps_mode smps_mode; u32 supp_rates[NUM_NL80211_BANDS]; struct ieee80211_sta_ht_cap ht_cap; struct ieee80211_sta_vht_cap vht_cap; struct ieee80211_sta_he_cap he_cap; struct ieee80211_he_6ghz_capa he_6ghz_capa; struct ieee80211_sta_eht_cap eht_cap; struct ieee80211_sta_aggregates agg; u8 rx_nss; enum ieee80211_sta_rx_bandwidth bandwidth; struct ieee80211_sta_txpwr txpwr; }; /** * struct ieee80211_sta - station table entry * * A station table entry represents a station we are possibly * communicating with. Since stations are RCU-managed in * mac80211, any ieee80211_sta pointer you get access to must * either be protected by rcu_read_lock() explicitly or implicitly, * or you must take good care to not use such a pointer after a * call to your sta_remove callback that removed it. * This also represents the MLD STA in case of MLO association * and holds pointers to various link STA's * * @addr: MAC address * @aid: AID we assigned to the station if we're an AP * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU * that this station is allowed to transmit to us. * Can be modified by driver. * @wme: indicates whether the STA supports QoS/WME (if local devices does, * otherwise always false) * @drv_priv: data area for driver use, will always be aligned to * sizeof(void \*), size is determined in hw information. * @uapsd_queues: bitmap of queues configured for uapsd. Only valid * if wme is supported. The bits order is like in * IEEE80211_WMM_IE_STA_QOSINFO_AC_*. * @max_sp: max Service Period. Only valid if wme is supported. * @rates: rate control selection table * @tdls: indicates whether the STA is a TDLS peer * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only * valid if the STA is a TDLS peer in the first place. * @mfp: indicates whether the STA uses management frame protection or not. * @mlo: indicates whether the STA is MLO station. * @max_amsdu_subframes: indicates the maximal number of MSDUs in a single * A-MSDU. Taken from the Extended Capabilities element. 0 means * unlimited. * @cur: currently valid data as aggregated from the active links * For non MLO STA it will point to the deflink data. For MLO STA * ieee80211_sta_recalc_aggregates() must be called to update it. * @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not. * @txq: per-TID data TX queues; note that the last entry (%IEEE80211_NUM_TIDS) * is used for non-data frames * @deflink: This holds the default link STA information, for non MLO STA all link * specific STA information is accessed through @deflink or through * link[0] which points to address of @deflink. For MLO Link STA * the first added link STA will point to deflink. * @link: reference to Link Sta entries. For Non MLO STA, except 1st link, * i.e link[0] all links would be assigned to NULL by default and * would access link information via @deflink or link[0]. For MLO * STA, first link STA being added will point its link pointer to * @deflink address and remaining would be allocated and the address * would be assigned to link[link_id] where link_id is the id assigned * by the AP. * @valid_links: bitmap of valid links, or 0 for non-MLO * @spp_amsdu: indicates whether the STA uses SPP A-MSDU or not. */ struct ieee80211_sta { u8 addr[ETH_ALEN] __aligned(2); u16 aid; u16 max_rx_aggregation_subframes; bool wme; u8 uapsd_queues; u8 max_sp; struct ieee80211_sta_rates __rcu *rates; bool tdls; bool tdls_initiator; bool mfp; bool mlo; bool spp_amsdu; u8 max_amsdu_subframes; struct ieee80211_sta_aggregates *cur; bool support_p2p_ps; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; u16 valid_links; struct ieee80211_link_sta deflink; struct ieee80211_link_sta __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS]; /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; #ifdef CONFIG_LOCKDEP bool lockdep_sta_mutex_held(struct ieee80211_sta *pubsta); #else static inline bool lockdep_sta_mutex_held(struct ieee80211_sta *pubsta) { return true; } #endif #define link_sta_dereference_protected(sta, link_id) \ rcu_dereference_protected((sta)->link[link_id], \ lockdep_sta_mutex_held(sta)) #define link_sta_dereference_check(sta, link_id) \ rcu_dereference_check((sta)->link[link_id], \ lockdep_sta_mutex_held(sta)) #define for_each_sta_active_link(vif, sta, link_sta, link_id) \ for (link_id = 0; link_id < ARRAY_SIZE((sta)->link); link_id++) \ if ((!(vif)->active_links || \ (vif)->active_links & BIT(link_id)) && \ ((link_sta) = link_sta_dereference_check(sta, link_id))) /** * enum sta_notify_cmd - sta notify command * * Used with the sta_notify() callback in &struct ieee80211_ops, this * indicates if an associated station made a power state transition. * * @STA_NOTIFY_SLEEP: a station is now sleeping * @STA_NOTIFY_AWAKE: a sleeping station woke up */ enum sta_notify_cmd { STA_NOTIFY_SLEEP, STA_NOTIFY_AWAKE, }; /** * struct ieee80211_tx_control - TX control data * * @sta: station table entry, this sta pointer may be NULL and * it is not allowed to copy the pointer, due to RCU. */ struct ieee80211_tx_control { struct ieee80211_sta *sta; }; /** * struct ieee80211_txq - Software intermediate tx queue * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @sta: station table entry, %NULL for per-vif queue * @tid: the TID for this queue (unused for per-vif queue), * %IEEE80211_NUM_TIDS for non-data (if enabled) * @ac: the AC for this queue * @drv_priv: driver private area, sized by hw->txq_data_size * * The driver can obtain packets from this queue by calling * ieee80211_tx_dequeue(). */ struct ieee80211_txq { struct ieee80211_vif *vif; struct ieee80211_sta *sta; u8 tid; u8 ac; /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; /** * enum ieee80211_hw_flags - hardware flags * * These flags are used to indicate hardware capabilities to * the stack. Generally, flags here should have their meaning * done in a way that the simplest hardware doesn't need setting * any particular flags. There are some exceptions to this rule, * however, so you are advised to review these flags carefully. * * @IEEE80211_HW_HAS_RATE_CONTROL: * The hardware or firmware includes rate control, and cannot be * controlled by the stack. As such, no rate control algorithm * should be instantiated, and the TX rate reported to userspace * will be taken from the TX status instead of the rate control * algorithm. * Note that this requires that the driver implement a number of * callbacks so it has the correct information, it needs to have * the @set_rts_threshold callback and must look at the BSS config * @use_cts_prot for G/N protection, @use_short_slot for slot * timing in 2.4 GHz and @use_short_preamble for preambles for * CCK frames. * * @IEEE80211_HW_RX_INCLUDES_FCS: * Indicates that received frames passed to the stack include * the FCS at the end. * * @IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING: * Some wireless LAN chipsets buffer broadcast/multicast frames * for power saving stations in the hardware/firmware and others * rely on the host system for such buffering. This option is used * to configure the IEEE 802.11 upper layer to buffer broadcast and * multicast frames when there are power saving stations so that * the driver can fetch them with ieee80211_get_buffered_bc(). * * @IEEE80211_HW_SIGNAL_UNSPEC: * Hardware can provide signal values but we don't know its units. We * expect values between 0 and @max_signal. * If possible please provide dB or dBm instead. * * @IEEE80211_HW_SIGNAL_DBM: * Hardware gives signal values in dBm, decibel difference from * one milliwatt. This is the preferred method since it is standardized * between different devices. @max_signal does not need to be set. * * @IEEE80211_HW_SPECTRUM_MGMT: * Hardware supports spectrum management defined in 802.11h * Measurement, Channel Switch, Quieting, TPC * * @IEEE80211_HW_AMPDU_AGGREGATION: * Hardware supports 11n A-MPDU aggregation. * * @IEEE80211_HW_SUPPORTS_PS: * Hardware has power save support (i.e. can go to sleep). * * @IEEE80211_HW_PS_NULLFUNC_STACK: * Hardware requires nullfunc frame handling in stack, implies * stack support for dynamic PS. * * @IEEE80211_HW_SUPPORTS_DYNAMIC_PS: * Hardware has support for dynamic PS. * * @IEEE80211_HW_MFP_CAPABLE: * Hardware supports management frame protection (MFP, IEEE 802.11w). * * @IEEE80211_HW_REPORTS_TX_ACK_STATUS: * Hardware can provide ack status reports of Tx frames to * the stack. * * @IEEE80211_HW_CONNECTION_MONITOR: * The hardware performs its own connection monitoring, including * periodic keep-alives to the AP and probing the AP on beacon loss. * * @IEEE80211_HW_NEED_DTIM_BEFORE_ASSOC: * This device needs to get data from beacon before association (i.e. * dtim_period). * * @IEEE80211_HW_SUPPORTS_PER_STA_GTK: The device's crypto engine supports * per-station GTKs as used by IBSS RSN or during fast transition. If * the device doesn't support per-station GTKs, but can be asked not * to decrypt group addressed frames, then IBSS RSN support is still * possible but software crypto will be used. Advertise the wiphy flag * only in that case. * * @IEEE80211_HW_AP_LINK_PS: When operating in AP mode the device * autonomously manages the PS status of connected stations. When * this flag is set mac80211 will not trigger PS mode for connected * stations based on the PM bit of incoming frames. * Use ieee80211_start_ps()/ieee8021_end_ps() to manually configure * the PS mode of connected stations. * * @IEEE80211_HW_TX_AMPDU_SETUP_IN_HW: The device handles TX A-MPDU session * setup strictly in HW. mac80211 should not attempt to do this in * software. * * @IEEE80211_HW_WANT_MONITOR_VIF: The driver would like to be informed of * a virtual monitor interface when monitor interfaces are the only * active interfaces. * * @IEEE80211_HW_NO_VIRTUAL_MONITOR: The driver would like to be informed * of any monitor interface, as well as their configured channel. * This is useful for supporting multiple monitor interfaces on different * channels. * * @IEEE80211_HW_NO_AUTO_VIF: The driver would like for no wlanX to * be created. It is expected user-space will create vifs as * desired (and thus have them named as desired). * * @IEEE80211_HW_SW_CRYPTO_CONTROL: The driver wants to control which of the * crypto algorithms can be done in software - so don't automatically * try to fall back to it if hardware crypto fails, but do so only if * the driver returns 1. This also forces the driver to advertise its * supported cipher suites. * * @IEEE80211_HW_SUPPORT_FAST_XMIT: The driver/hardware supports fast-xmit, * this currently requires only the ability to calculate the duration * for frames. * * @IEEE80211_HW_QUEUE_CONTROL: The driver wants to control per-interface * queue mapping in order to use different queues (not just one per AC) * for different virtual interfaces. See the doc section on HW queue * control for more details. * * @IEEE80211_HW_SUPPORTS_RC_TABLE: The driver supports using a rate * selection table provided by the rate control algorithm. * * @IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF: Use the P2P Device address for any * P2P Interface. This will be honoured even if more than one interface * is supported. * * @IEEE80211_HW_TIMING_BEACON_ONLY: Use sync timing from beacon frames * only, to allow getting TBTT of a DTIM beacon. * * @IEEE80211_HW_SUPPORTS_HT_CCK_RATES: Hardware supports mixing HT/CCK rates * and can cope with CCK rates in an aggregation session (e.g. by not * using aggregation for such frames.) * * @IEEE80211_HW_CHANCTX_STA_CSA: Support 802.11h based channel-switch (CSA) * for a single active channel while using channel contexts. When support * is not enabled the default action is to disconnect when getting the * CSA frame. * * @IEEE80211_HW_SUPPORTS_CLONED_SKBS: The driver will never modify the payload * or tailroom of TX skbs without copying them first. * * @IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS: The HW supports scanning on all bands * in one command, mac80211 doesn't have to run separate scans per band. * * @IEEE80211_HW_TDLS_WIDER_BW: The device/driver supports wider bandwidth * than then BSS bandwidth for a TDLS link on the base channel. * * @IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU: The driver supports receiving A-MSDUs * within A-MPDU. * * @IEEE80211_HW_BEACON_TX_STATUS: The device/driver provides TX status * for sent beacons. * * @IEEE80211_HW_NEEDS_UNIQUE_STA_ADDR: Hardware (or driver) requires that each * station has a unique address, i.e. each station entry can be identified * by just its MAC address; this prevents, for example, the same station * from connecting to two virtual AP interfaces at the same time. * * @IEEE80211_HW_SUPPORTS_REORDERING_BUFFER: Hardware (or driver) manages the * reordering buffer internally, guaranteeing mac80211 receives frames in * order and does not need to manage its own reorder buffer or BA session * timeout. * * @IEEE80211_HW_USES_RSS: The device uses RSS and thus requires parallel RX, * which implies using per-CPU station statistics. * * @IEEE80211_HW_TX_AMSDU: Hardware (or driver) supports software aggregated * A-MSDU frames. Requires software tx queueing and fast-xmit support. * When not using minstrel/minstrel_ht rate control, the driver must * limit the maximum A-MSDU size based on the current tx rate by setting * max_rc_amsdu_len in struct ieee80211_sta. * * @IEEE80211_HW_TX_FRAG_LIST: Hardware (or driver) supports sending frag_list * skbs, needed for zero-copy software A-MSDU. * * @IEEE80211_HW_REPORTS_LOW_ACK: The driver (or firmware) reports low ack event * by ieee80211_report_low_ack() based on its own algorithm. For such * drivers, mac80211 packet loss mechanism will not be triggered and driver * is completely depending on firmware event for station kickout. * * @IEEE80211_HW_SUPPORTS_TX_FRAG: Hardware does fragmentation by itself. * The stack will not do fragmentation. * The callback for @set_frag_threshold should be set as well. * * @IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA: Hardware supports buffer STA on * TDLS links. * * @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't * support QoS NDP for AP probing - that's most likely a driver bug. * * @IEEE80211_HW_BUFF_MMPDU_TXQ: use the TXQ for bufferable MMPDUs, this of * course requires the driver to use TXQs to start with. * * @IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW: (Hardware) rate control supports VHT * extended NSS BW (dot11VHTExtendedNSSBWCapable). This flag will be set if * the selected rate control algorithm sets %RATE_CTRL_CAPA_VHT_EXT_NSS_BW * but if the rate control is built-in then it must be set by the driver. * See also the documentation for that flag. * * @IEEE80211_HW_STA_MMPDU_TXQ: use the extra non-TID per-station TXQ for all * MMPDUs on station interfaces. This of course requires the driver to use * TXQs to start with. * * @IEEE80211_HW_TX_STATUS_NO_AMPDU_LEN: Driver does not report accurate A-MPDU * length in tx status information * * @IEEE80211_HW_SUPPORTS_MULTI_BSSID: Hardware supports multi BSSID * * @IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID: Hardware supports multi BSSID * only for HE APs. Applies if @IEEE80211_HW_SUPPORTS_MULTI_BSSID is set. * * @IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT: The card and driver is only * aggregating MPDUs with the same keyid, allowing mac80211 to keep Tx * A-MPDU sessions active while rekeying with Extended Key ID. * * @IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD: Hardware supports tx encapsulation * offload * * @IEEE80211_HW_SUPPORTS_RX_DECAP_OFFLOAD: Hardware supports rx decapsulation * offload * * @IEEE80211_HW_SUPPORTS_CONC_MON_RX_DECAP: Hardware supports concurrent rx * decapsulation offload and passing raw 802.11 frames for monitor iface. * If this is supported, the driver must pass both 802.3 frames for real * usage and 802.11 frames with %RX_FLAG_ONLY_MONITOR set for monitor to * the stack. * * @IEEE80211_HW_DETECTS_COLOR_COLLISION: HW/driver has support for BSS color * collision detection and doesn't need it in software. * * @IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX: Hardware/driver handles transmitting * multicast frames on all links, mac80211 should not do that. * * @IEEE80211_HW_DISALLOW_PUNCTURING: HW requires disabling puncturing in EHT * and connecting with a lower bandwidth instead * @IEEE80211_HW_DISALLOW_PUNCTURING_5GHZ: HW requires disabling puncturing in * EHT in 5 GHz and connecting with a lower bandwidth instead * * @IEEE80211_HW_HANDLES_QUIET_CSA: HW/driver handles quieting for CSA, so * no need to stop queues. This really should be set by a driver that * implements MLO, so operation can continue on other links when one * link is switching. * * @IEEE80211_HW_STRICT: strictly enforce certain things mandated by the spec * but otherwise ignored/worked around for interoperability. This is a * HW flag so drivers can opt in according to their own control, e.g. in * testing. * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { IEEE80211_HW_HAS_RATE_CONTROL, IEEE80211_HW_RX_INCLUDES_FCS, IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING, IEEE80211_HW_SIGNAL_UNSPEC, IEEE80211_HW_SIGNAL_DBM, IEEE80211_HW_NEED_DTIM_BEFORE_ASSOC, IEEE80211_HW_SPECTRUM_MGMT, IEEE80211_HW_AMPDU_AGGREGATION, IEEE80211_HW_SUPPORTS_PS, IEEE80211_HW_PS_NULLFUNC_STACK, IEEE80211_HW_SUPPORTS_DYNAMIC_PS, IEEE80211_HW_MFP_CAPABLE, IEEE80211_HW_WANT_MONITOR_VIF, IEEE80211_HW_NO_VIRTUAL_MONITOR, IEEE80211_HW_NO_AUTO_VIF, IEEE80211_HW_SW_CRYPTO_CONTROL, IEEE80211_HW_SUPPORT_FAST_XMIT, IEEE80211_HW_REPORTS_TX_ACK_STATUS, IEEE80211_HW_CONNECTION_MONITOR, IEEE80211_HW_QUEUE_CONTROL, IEEE80211_HW_SUPPORTS_PER_STA_GTK, IEEE80211_HW_AP_LINK_PS, IEEE80211_HW_TX_AMPDU_SETUP_IN_HW, IEEE80211_HW_SUPPORTS_RC_TABLE, IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF, IEEE80211_HW_TIMING_BEACON_ONLY, IEEE80211_HW_SUPPORTS_HT_CCK_RATES, IEEE80211_HW_CHANCTX_STA_CSA, IEEE80211_HW_SUPPORTS_CLONED_SKBS, IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS, IEEE80211_HW_TDLS_WIDER_BW, IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU, IEEE80211_HW_BEACON_TX_STATUS, IEEE80211_HW_NEEDS_UNIQUE_STA_ADDR, IEEE80211_HW_SUPPORTS_REORDERING_BUFFER, IEEE80211_HW_USES_RSS, IEEE80211_HW_TX_AMSDU, IEEE80211_HW_TX_FRAG_LIST, IEEE80211_HW_REPORTS_LOW_ACK, IEEE80211_HW_SUPPORTS_TX_FRAG, IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA, IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP, IEEE80211_HW_BUFF_MMPDU_TXQ, IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW, IEEE80211_HW_STA_MMPDU_TXQ, IEEE80211_HW_TX_STATUS_NO_AMPDU_LEN, IEEE80211_HW_SUPPORTS_MULTI_BSSID, IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID, IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT, IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD, IEEE80211_HW_SUPPORTS_RX_DECAP_OFFLOAD, IEEE80211_HW_SUPPORTS_CONC_MON_RX_DECAP, IEEE80211_HW_DETECTS_COLOR_COLLISION, IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX, IEEE80211_HW_DISALLOW_PUNCTURING, IEEE80211_HW_DISALLOW_PUNCTURING_5GHZ, IEEE80211_HW_HANDLES_QUIET_CSA, IEEE80211_HW_STRICT, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS }; /** * struct ieee80211_hw - hardware information and state * * This structure contains the configuration and hardware * information for an 802.11 PHY. * * @wiphy: This points to the &struct wiphy allocated for this * 802.11 PHY. You must fill in the @perm_addr and @dev * members of this structure using SET_IEEE80211_DEV() * and SET_IEEE80211_PERM_ADDR(). Additionally, all supported * bands (with channels, bitrates) are registered here. * * @conf: &struct ieee80211_conf, device configuration, don't use. * * @priv: pointer to private area that was allocated for driver use * along with this structure. * * @flags: hardware flags, see &enum ieee80211_hw_flags. * * @extra_tx_headroom: headroom to reserve in each transmit skb * for use by the driver (e.g. for transmit headers.) * * @extra_beacon_tailroom: tailroom to reserve in each beacon tx skb. * Can be used by drivers to add extra IEs. * * @max_signal: Maximum value for signal (rssi) in RX information, used * only when @IEEE80211_HW_SIGNAL_UNSPEC or @IEEE80211_HW_SIGNAL_DB * * @max_listen_interval: max listen interval in units of beacon interval * that HW supports * * @queues: number of available hardware transmit queues for * data packets. WMM/QoS requires at least four, these * queues need to have configurable access parameters. * * @rate_control_algorithm: rate control algorithm for this hardware. * If unset (NULL), the default algorithm will be used. Must be * set before calling ieee80211_register_hw(). * * @vif_data_size: size (in bytes) of the drv_priv data area * within &struct ieee80211_vif. * @sta_data_size: size (in bytes) of the drv_priv data area * within &struct ieee80211_sta. * @chanctx_data_size: size (in bytes) of the drv_priv data area * within &struct ieee80211_chanctx_conf. * @txq_data_size: size (in bytes) of the drv_priv data area * within @struct ieee80211_txq. * * @max_rates: maximum number of alternate rate retry stages the hw * can handle. * @max_report_rates: maximum number of alternate rate retry stages * the hw can report back. * @max_rate_tries: maximum number of tries for each stage * * @max_rx_aggregation_subframes: maximum buffer size (number of * sub-frames) to be used for A-MPDU block ack receiver * aggregation. * This is only relevant if the device has restrictions on the * number of subframes, if it relies on mac80211 to do reordering * it shouldn't be set. * * @max_tx_aggregation_subframes: maximum number of subframes in an * aggregate an HT/HE device will transmit. In HT AddBA we'll * advertise a constant value of 64 as some older APs crash if * the window size is smaller (an example is LinkSys WRT120N * with FW v1.0.07 build 002 Jun 18 2012). * For AddBA to HE capable peers this value will be used. * * @max_tx_fragments: maximum number of tx buffers per (A)-MSDU, sum * of 1 + skb_shinfo(skb)->nr_frags for each skb in the frag_list. * * @offchannel_tx_hw_queue: HW queue ID to use for offchannel TX * (if %IEEE80211_HW_QUEUE_CONTROL is set) * * @radiotap_mcs_details: lists which MCS information can the HW * reports, by default it is set to _MCS, _GI and _BW but doesn't * include _FMT. Use %IEEE80211_RADIOTAP_MCS_HAVE_\* values, only * adding _BW is supported today. * * @radiotap_vht_details: lists which VHT MCS information the HW reports, * the default is _GI | _BANDWIDTH. * Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values. * * @radiotap_timestamp: Information for the radiotap timestamp field; if the * @units_pos member is set to a non-negative value then the timestamp * field will be added and populated from the &struct ieee80211_rx_status * device_timestamp. * @radiotap_timestamp.units_pos: Must be set to a combination of a * IEEE80211_RADIOTAP_TIMESTAMP_UNIT_* and a * IEEE80211_RADIOTAP_TIMESTAMP_SPOS_* value. * @radiotap_timestamp.accuracy: If non-negative, fills the accuracy in the * radiotap field and the accuracy known flag will be set. * * @netdev_features: netdev features to be set in each netdev created * from this HW. Note that not all features are usable with mac80211, * other features will be rejected during HW registration. * * @uapsd_queues: This bitmap is included in (re)association frame to indicate * for each access category if it is uAPSD trigger-enabled and delivery- * enabled. Use IEEE80211_WMM_IE_STA_QOSINFO_AC_* to set this bitmap. * Each bit corresponds to different AC. Value '1' in specific bit means * that corresponding AC is both trigger- and delivery-enabled. '0' means * neither enabled. * * @uapsd_max_sp_len: maximum number of total buffered frames the WMM AP may * deliver to a WMM STA during any Service Period triggered by the WMM STA. * Use IEEE80211_WMM_IE_STA_QOSINFO_SP_* for correct values. * * @max_nan_de_entries: maximum number of NAN DE functions supported by the * device. * * @tx_sk_pacing_shift: Pacing shift to set on TCP sockets when frames from * them are encountered. The default should typically not be changed, * unless the driver has good reasons for needing more buffers. * * @weight_multiplier: Driver specific airtime weight multiplier used while * refilling deficit of each TXQ. * * @max_mtu: the max mtu could be set. * * @tx_power_levels: a list of power levels supported by the wifi hardware. * The power levels can be specified either as integer or fractions. * The power level at idx 0 shall be the maximum positive power level. * * @max_txpwr_levels_idx: the maximum valid idx of 'tx_power_levels' list. */ struct ieee80211_hw { struct ieee80211_conf conf; struct wiphy *wiphy; const char *rate_control_algorithm; void *priv; unsigned long flags[BITS_TO_LONGS(NUM_IEEE80211_HW_FLAGS)]; unsigned int extra_tx_headroom; unsigned int extra_beacon_tailroom; int vif_data_size; int sta_data_size; int chanctx_data_size; int txq_data_size; u16 queues; u16 max_listen_interval; s8 max_signal; u8 max_rates; u8 max_report_rates; u8 max_rate_tries; u16 max_rx_aggregation_subframes; u16 max_tx_aggregation_subframes; u8 max_tx_fragments; u8 offchannel_tx_hw_queue; u8 radiotap_mcs_details; u16 radiotap_vht_details; struct { int units_pos; s16 accuracy; } radiotap_timestamp; netdev_features_t netdev_features; u8 uapsd_queues; u8 uapsd_max_sp_len; u8 max_nan_de_entries; u8 tx_sk_pacing_shift; u8 weight_multiplier; u32 max_mtu; const s8 *tx_power_levels; u8 max_txpwr_levels_idx; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, enum ieee80211_hw_flags flg) { return test_bit(flg, hw->flags); } #define ieee80211_hw_check(hw, flg) _ieee80211_hw_check(hw, IEEE80211_HW_##flg) static inline void _ieee80211_hw_set(struct ieee80211_hw *hw, enum ieee80211_hw_flags flg) { return __set_bit(flg, hw->flags); } #define ieee80211_hw_set(hw, flg) _ieee80211_hw_set(hw, IEEE80211_HW_##flg) /** * struct ieee80211_scan_request - hw scan request * * @ies: pointers different parts of IEs (in req.ie) * @req: cfg80211 request. */ struct ieee80211_scan_request { struct ieee80211_scan_ies ies; /* Keep last */ struct cfg80211_scan_request req; }; /** * struct ieee80211_tdls_ch_sw_params - TDLS channel switch parameters * * @sta: peer this TDLS channel-switch request/response came from * @chandef: channel referenced in a TDLS channel-switch request * @action_code: see &enum ieee80211_tdls_actioncode * @status: channel-switch response status * @timestamp: time at which the frame was received * @switch_time: switch-timing parameter received in the frame * @switch_timeout: switch-timing parameter received in the frame * @tmpl_skb: TDLS switch-channel response template * @ch_sw_tm_ie: offset of the channel-switch timing IE inside @tmpl_skb */ struct ieee80211_tdls_ch_sw_params { struct ieee80211_sta *sta; struct cfg80211_chan_def *chandef; u8 action_code; u32 status; u32 timestamp; u16 switch_time; u16 switch_timeout; struct sk_buff *tmpl_skb; u32 ch_sw_tm_ie; }; /** * wiphy_to_ieee80211_hw - return a mac80211 driver hw struct from a wiphy * * @wiphy: the &struct wiphy which we want to query * * mac80211 drivers can use this to get to their respective * &struct ieee80211_hw. Drivers wishing to get to their own private * structure can then access it via hw->priv. Note that mac802111 drivers should * not use wiphy_priv() to try to get their private driver structure as this * is already used internally by mac80211. * * Return: The mac80211 driver hw struct of @wiphy. */ struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy); /** * SET_IEEE80211_DEV - set device for 802.11 hardware * * @hw: the &struct ieee80211_hw to set the device for * @dev: the &struct device of this 802.11 device */ static inline void SET_IEEE80211_DEV(struct ieee80211_hw *hw, struct device *dev) { set_wiphy_dev(hw->wiphy, dev); } /** * SET_IEEE80211_PERM_ADDR - set the permanent MAC address for 802.11 hardware * * @hw: the &struct ieee80211_hw to set the MAC address for * @addr: the address to set */ static inline void SET_IEEE80211_PERM_ADDR(struct ieee80211_hw *hw, const u8 *addr) { memcpy(hw->wiphy->perm_addr, addr, ETH_ALEN); } static inline struct ieee80211_rate * ieee80211_get_tx_rate(const struct ieee80211_hw *hw, const struct ieee80211_tx_info *c) { if (WARN_ON_ONCE(c->control.rates[0].idx < 0)) return NULL; return &hw->wiphy->bands[c->band]->bitrates[c->control.rates[0].idx]; } static inline struct ieee80211_rate * ieee80211_get_rts_cts_rate(const struct ieee80211_hw *hw, const struct ieee80211_tx_info *c) { if (c->control.rts_cts_rate_idx < 0) return NULL; return &hw->wiphy->bands[c->band]->bitrates[c->control.rts_cts_rate_idx]; } static inline struct ieee80211_rate * ieee80211_get_alt_retry_rate(const struct ieee80211_hw *hw, const struct ieee80211_tx_info *c, int idx) { if (c->control.rates[idx + 1].idx < 0) return NULL; return &hw->wiphy->bands[c->band]->bitrates[c->control.rates[idx + 1].idx]; } /** * ieee80211_free_txskb - free TX skb * @hw: the hardware * @skb: the skb * * Free a transmit skb. Use this function when some failure * to transmit happened and thus status cannot be reported. */ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); /** * ieee80211_purge_tx_queue - purge TX skb queue * @hw: the hardware * @skbs: the skbs * * Free a set of transmit skbs. Use this function when device is going to stop * but some transmit skbs without TX status are still queued. * This function does not take the list lock and the caller must hold the * relevant locks to use it. */ void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, struct sk_buff_head *skbs); /** * DOC: Hardware crypto acceleration * * mac80211 is capable of taking advantage of many hardware * acceleration designs for encryption and decryption operations. * * The set_key() callback in the &struct ieee80211_ops for a given * device is called to enable hardware acceleration of encryption and * decryption. The callback takes a @sta parameter that will be NULL * for default keys or keys used for transmission only, or point to * the station information for the peer for individual keys. * Multiple transmission keys with the same key index may be used when * VLANs are configured for an access point. * * When transmitting, the TX control data will use the @hw_key_idx * selected by the driver by modifying the &struct ieee80211_key_conf * pointed to by the @key parameter to the set_key() function. * * The set_key() call for the %SET_KEY command should return 0 if * the key is now in use, -%EOPNOTSUPP or -%ENOSPC if it couldn't be * added; if you return 0 then hw_key_idx must be assigned to the * hardware key index. You are free to use the full u8 range. * * Note that in the case that the @IEEE80211_HW_SW_CRYPTO_CONTROL flag is * set, mac80211 will not automatically fall back to software crypto if * enabling hardware crypto failed. The set_key() call may also return the * value 1 to permit this specific key/algorithm to be done in software. * * When the cmd is %DISABLE_KEY then it must succeed. * * Note that it is permissible to not decrypt a frame even if a key * for it has been uploaded to hardware. The stack will not make any * decision based on whether a key has been uploaded or not but rather * based on the receive flags. * * The &struct ieee80211_key_conf structure pointed to by the @key * parameter is guaranteed to be valid until another call to set_key() * removes it, but it can only be used as a cookie to differentiate * keys. * * In TKIP some HW need to be provided a phase 1 key, for RX decryption * acceleration (i.e. iwlwifi). Those drivers should provide update_tkip_key * handler. * The update_tkip_key() call updates the driver with the new phase 1 key. * This happens every time the iv16 wraps around (every 65536 packets). The * set_key() call will happen only once for each key (unless the AP did * rekeying); it will not include a valid phase 1 key. The valid phase 1 key is * provided by update_tkip_key only. The trigger that makes mac80211 call this * handler is software decryption with wrap around of iv16. * * The set_default_unicast_key() call updates the default WEP key index * configured to the hardware for WEP encryption type. This is required * for devices that support offload of data packets (e.g. ARP responses). * * Mac80211 drivers should set the @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0 flag * when they are able to replace in-use PTK keys according to the following * requirements: * 1) They do not hand over frames decrypted with the old key to mac80211 once the call to set_key() with command %DISABLE_KEY has been completed, 2) either drop or continue to use the old key for any outgoing frames queued at the time of the key deletion (including re-transmits), 3) never send out a frame queued prior to the set_key() %SET_KEY command encrypted with the new key when also needing @IEEE80211_KEY_FLAG_GENERATE_IV and 4) never send out a frame unencrypted when it should be encrypted. Mac80211 will not queue any new frames for a deleted key to the driver. */ /** * DOC: Powersave support * * mac80211 has support for various powersave implementations. * * First, it can support hardware that handles all powersaving by itself; * such hardware should simply set the %IEEE80211_HW_SUPPORTS_PS hardware * flag. In that case, it will be told about the desired powersave mode * with the %IEEE80211_CONF_PS flag depending on the association status. * The hardware must take care of sending nullfunc frames when necessary, * i.e. when entering and leaving powersave mode. The hardware is required * to look at the AID in beacons and signal to the AP that it woke up when * it finds traffic directed to it. * * %IEEE80211_CONF_PS flag enabled means that the powersave mode defined in * IEEE 802.11-2007 section 11.2 is enabled. This is not to be confused * with hardware wakeup and sleep states. Driver is responsible for waking * up the hardware before issuing commands to the hardware and putting it * back to sleep at appropriate times. * * When PS is enabled, hardware needs to wakeup for beacons and receive the * buffered multicast/broadcast frames after the beacon. Also it must be * possible to send frames and receive the acknowledment frame. * * Other hardware designs cannot send nullfunc frames by themselves and also * need software support for parsing the TIM bitmap. This is also supported * by mac80211 by combining the %IEEE80211_HW_SUPPORTS_PS and * %IEEE80211_HW_PS_NULLFUNC_STACK flags. The hardware is of course still * required to pass up beacons. The hardware is still required to handle * waking up for multicast traffic; if it cannot the driver must handle that * as best as it can; mac80211 is too slow to do that. * * Dynamic powersave is an extension to normal powersave in which the * hardware stays awake for a user-specified period of time after sending a * frame so that reply frames need not be buffered and therefore delayed to * the next wakeup. It's a compromise of getting good enough latency when * there's data traffic and still saving significantly power in idle * periods. * * Dynamic powersave is simply supported by mac80211 enabling and disabling * PS based on traffic. Driver needs to only set %IEEE80211_HW_SUPPORTS_PS * flag and mac80211 will handle everything automatically. Additionally, * hardware having support for the dynamic PS feature may set the * %IEEE80211_HW_SUPPORTS_DYNAMIC_PS flag to indicate that it can support * dynamic PS mode itself. The driver needs to look at the * @dynamic_ps_timeout hardware configuration value and use it that value * whenever %IEEE80211_CONF_PS is set. In this case mac80211 will disable * dynamic PS feature in stack and will just keep %IEEE80211_CONF_PS * enabled whenever user has enabled powersave. * * Driver informs U-APSD client support by enabling * %IEEE80211_VIF_SUPPORTS_UAPSD flag. The mode is configured through the * uapsd parameter in conf_tx() operation. Hardware needs to send the QoS * Nullfunc frames and stay awake until the service period has ended. To * utilize U-APSD, dynamic powersave is disabled for voip AC and all frames * from that AC are transmitted with powersave enabled. * * Note: U-APSD client mode is not yet supported with * %IEEE80211_HW_PS_NULLFUNC_STACK. */ /** * DOC: Beacon filter support * * Some hardware have beacon filter support to reduce host cpu wakeups * which will reduce system power consumption. It usually works so that * the firmware creates a checksum of the beacon but omits all constantly * changing elements (TSF, TIM etc). Whenever the checksum changes the * beacon is forwarded to the host, otherwise it will be just dropped. That * way the host will only receive beacons where some relevant information * (for example ERP protection or WMM settings) have changed. * * Beacon filter support is advertised with the %IEEE80211_VIF_BEACON_FILTER * interface capability. The driver needs to enable beacon filter support * whenever power save is enabled, that is %IEEE80211_CONF_PS is set. When * power save is enabled, the stack will not check for beacon loss and the * driver needs to notify about loss of beacons with ieee80211_beacon_loss(). * * The time (or number of beacons missed) until the firmware notifies the * driver of a beacon loss event (which in turn causes the driver to call * ieee80211_beacon_loss()) should be configurable and will be controlled * by mac80211 and the roaming algorithm in the future. * * Since there may be constantly changing information elements that nothing * in the software stack cares about, we will, in the future, have mac80211 * tell the driver which information elements are interesting in the sense * that we want to see changes in them. This will include * * - a list of information element IDs * - a list of OUIs for the vendor information element * * Ideally, the hardware would filter out any beacons without changes in the * requested elements, but if it cannot support that it may, at the expense * of some efficiency, filter out only a subset. For example, if the device * doesn't support checking for OUIs it should pass up all changes in all * vendor information elements. * * Note that change, for the sake of simplification, also includes information * elements appearing or disappearing from the beacon. * * Some hardware supports an "ignore list" instead. Just make sure nothing * that was requested is on the ignore list, and include commonly changing * information element IDs in the ignore list, for example 11 (BSS load) and * the various vendor-assigned IEs with unknown contents (128, 129, 133-136, * 149, 150, 155, 156, 173, 176, 178, 179, 219); for forward compatibility * it could also include some currently unused IDs. * * * In addition to these capabilities, hardware should support notifying the * host of changes in the beacon RSSI. This is relevant to implement roaming * when no traffic is flowing (when traffic is flowing we see the RSSI of * the received data packets). This can consist of notifying the host when * the RSSI changes significantly or when it drops below or rises above * configurable thresholds. In the future these thresholds will also be * configured by mac80211 (which gets them from userspace) to implement * them as the roaming algorithm requires. * * If the hardware cannot implement this, the driver should ask it to * periodically pass beacon frames to the host so that software can do the * signal strength threshold checking. */ /** * DOC: Spatial multiplexing power save * * SMPS (Spatial multiplexing power save) is a mechanism to conserve * power in an 802.11n implementation. For details on the mechanism * and rationale, please refer to 802.11 (as amended by 802.11n-2009) * "11.2.3 SM power save". * * The mac80211 implementation is capable of sending action frames * to update the AP about the station's SMPS mode, and will instruct * the driver to enter the specific mode. It will also announce the * requested SMPS mode during the association handshake. Hardware * support for this feature is required, and can be indicated by * hardware flags. * * The default mode will be "automatic", which nl80211/cfg80211 * defines to be dynamic SMPS in (regular) powersave, and SMPS * turned off otherwise. * * To support this feature, the driver must set the appropriate * hardware support flags, and handle the SMPS flag to the config() * operation. It will then with this mechanism be instructed to * enter the requested SMPS mode while associated to an HT AP. */ /** * DOC: Frame filtering * * mac80211 requires to see many management frames for proper * operation, and users may want to see many more frames when * in monitor mode. However, for best CPU usage and power consumption, * having as few frames as possible percolate through the stack is * desirable. Hence, the hardware should filter as much as possible. * * To achieve this, mac80211 uses filter flags (see below) to tell * the driver's configure_filter() function which frames should be * passed to mac80211 and which should be filtered out. * * Before configure_filter() is invoked, the prepare_multicast() * callback is invoked with the parameters @mc_count and @mc_list * for the combined multicast address list of all virtual interfaces. * It's use is optional, and it returns a u64 that is passed to * configure_filter(). Additionally, configure_filter() has the * arguments @changed_flags telling which flags were changed and * @total_flags with the new flag states. * * If your device has no multicast address filters your driver will * need to check both the %FIF_ALLMULTI flag and the @mc_count * parameter to see whether multicast frames should be accepted * or dropped. * * All unsupported flags in @total_flags must be cleared. * Hardware does not support a flag if it is incapable of _passing_ * the frame to the stack. Otherwise the driver must ignore * the flag, but not clear it. * You must _only_ clear the flag (announce no support for the * flag to mac80211) if you are not able to pass the packet type * to the stack (so the hardware always filters it). * So for example, you should clear @FIF_CONTROL, if your hardware * always filters control frames. If your hardware always passes * control frames to the kernel and is incapable of filtering them, * you do _not_ clear the @FIF_CONTROL flag. * This rule applies to all other FIF flags as well. */ /** * DOC: AP support for powersaving clients * * In order to implement AP and P2P GO modes, mac80211 has support for * client powersaving, both "legacy" PS (PS-Poll/null data) and uAPSD. * There currently is no support for sAPSD. * * There is one assumption that mac80211 makes, namely that a client * will not poll with PS-Poll and trigger with uAPSD at the same time. * Both are supported, and both can be used by the same client, but * they can't be used concurrently by the same client. This simplifies * the driver code. * * The first thing to keep in mind is that there is a flag for complete * driver implementation: %IEEE80211_HW_AP_LINK_PS. If this flag is set, * mac80211 expects the driver to handle most of the state machine for * powersaving clients and will ignore the PM bit in incoming frames. * Drivers then use ieee80211_sta_ps_transition() to inform mac80211 of * stations' powersave transitions. In this mode, mac80211 also doesn't * handle PS-Poll/uAPSD. * * In the mode without %IEEE80211_HW_AP_LINK_PS, mac80211 will check the * PM bit in incoming frames for client powersave transitions. When a * station goes to sleep, we will stop transmitting to it. There is, * however, a race condition: a station might go to sleep while there is * data buffered on hardware queues. If the device has support for this * it will reject frames, and the driver should give the frames back to * mac80211 with the %IEEE80211_TX_STAT_TX_FILTERED flag set which will * cause mac80211 to retry the frame when the station wakes up. The * driver is also notified of powersave transitions by calling its * @sta_notify callback. * * When the station is asleep, it has three choices: it can wake up, * it can PS-Poll, or it can possibly start a uAPSD service period. * Waking up is implemented by simply transmitting all buffered (and * filtered) frames to the station. This is the easiest case. When * the station sends a PS-Poll or a uAPSD trigger frame, mac80211 * will inform the driver of this with the @allow_buffered_frames * callback; this callback is optional. mac80211 will then transmit * the frames as usual and set the %IEEE80211_TX_CTL_NO_PS_BUFFER * on each frame. The last frame in the service period (or the only * response to a PS-Poll) also has %IEEE80211_TX_STATUS_EOSP set to * indicate that it ends the service period; as this frame must have * TX status report it also sets %IEEE80211_TX_CTL_REQ_TX_STATUS. * When TX status is reported for this frame, the service period is * marked has having ended and a new one can be started by the peer. * * Additionally, non-bufferable MMPDUs can also be transmitted by * mac80211 with the %IEEE80211_TX_CTL_NO_PS_BUFFER set in them. * * Another race condition can happen on some devices like iwlwifi * when there are frames queued for the station and it wakes up * or polls; the frames that are already queued could end up being * transmitted first instead, causing reordering and/or wrong * processing of the EOSP. The cause is that allowing frames to be * transmitted to a certain station is out-of-band communication to * the device. To allow this problem to be solved, the driver can * call ieee80211_sta_block_awake() if frames are buffered when it * is notified that the station went to sleep. When all these frames * have been filtered (see above), it must call the function again * to indicate that the station is no longer blocked. * * If the driver buffers frames in the driver for aggregation in any * way, it must use the ieee80211_sta_set_buffered() call when it is * notified of the station going to sleep to inform mac80211 of any * TIDs that have frames buffered. Note that when a station wakes up * this information is reset (hence the requirement to call it when * informed of the station going to sleep). Then, when a service * period starts for any reason, @release_buffered_frames is called * with the number of frames to be released and which TIDs they are * to come from. In this case, the driver is responsible for setting * the EOSP (for uAPSD) and MORE_DATA bits in the released frames. * To help the @more_data parameter is passed to tell the driver if * there is more data on other TIDs -- the TIDs to release frames * from are ignored since mac80211 doesn't know how many frames the * buffers for those TIDs contain. * * If the driver also implement GO mode, where absence periods may * shorten service periods (or abort PS-Poll responses), it must * filter those response frames except in the case of frames that * are buffered in the driver -- those must remain buffered to avoid * reordering. Because it is possible that no frames are released * in this case, the driver must call ieee80211_sta_eosp() * to indicate to mac80211 that the service period ended anyway. * * Finally, if frames from multiple TIDs are released from mac80211 * but the driver might reorder them, it must clear & set the flags * appropriately (only the last frame may have %IEEE80211_TX_STATUS_EOSP) * and also take care of the EOSP and MORE_DATA bits in the frame. * The driver may also use ieee80211_sta_eosp() in this case. * * Note that if the driver ever buffers frames other than QoS-data * frames, it must take care to never send a non-QoS-data frame as * the last frame in a service period, adding a QoS-nulldata frame * after a non-QoS-data frame if needed. */ /** * DOC: HW queue control * * Before HW queue control was introduced, mac80211 only had a single static * assignment of per-interface AC software queues to hardware queues. This * was problematic for a few reasons: * 1) off-channel transmissions might get stuck behind other frames * 2) multiple virtual interfaces couldn't be handled correctly * 3) after-DTIM frames could get stuck behind other frames * * To solve this, hardware typically uses multiple different queues for all * the different usages, and this needs to be propagated into mac80211 so it * won't have the same problem with the software queues. * * Therefore, mac80211 now offers the %IEEE80211_HW_QUEUE_CONTROL capability * flag that tells it that the driver implements its own queue control. To do * so, the driver will set up the various queues in each &struct ieee80211_vif * and the offchannel queue in &struct ieee80211_hw. In response, mac80211 will * use those queue IDs in the hw_queue field of &struct ieee80211_tx_info and * if necessary will queue the frame on the right software queue that mirrors * the hardware queue. * Additionally, the driver has to then use these HW queue IDs for the queue * management functions (ieee80211_stop_queue() et al.) * * The driver is free to set up the queue mappings as needed; multiple virtual * interfaces may map to the same hardware queues if needed. The setup has to * happen during add_interface or change_interface callbacks. For example, a * driver supporting station+station and station+AP modes might decide to have * 10 hardware queues to handle different scenarios: * * 4 AC HW queues for 1st vif: 0, 1, 2, 3 * 4 AC HW queues for 2nd vif: 4, 5, 6, 7 * after-DTIM queue for AP: 8 * off-channel queue: 9 * * It would then set up the hardware like this: * hw.offchannel_tx_hw_queue = 9 * * and the first virtual interface that is added as follows: * vif.hw_queue[IEEE80211_AC_VO] = 0 * vif.hw_queue[IEEE80211_AC_VI] = 1 * vif.hw_queue[IEEE80211_AC_BE] = 2 * vif.hw_queue[IEEE80211_AC_BK] = 3 * vif.cab_queue = 8 // if AP mode, otherwise %IEEE80211_INVAL_HW_QUEUE * and the second virtual interface with 4-7. * * If queue 6 gets full, for example, mac80211 would only stop the second * virtual interface's BE queue since virtual interface queues are per AC. * * Note that the vif.cab_queue value should be set to %IEEE80211_INVAL_HW_QUEUE * whenever the queue is not used (i.e. the interface is not in AP mode) if the * queue could potentially be shared since mac80211 will look at cab_queue when * a queue is stopped/woken even if the interface is not in AP mode. */ /** * enum ieee80211_filter_flags - hardware filter flags * * These flags determine what the filter in hardware should be * programmed to let through and what should not be passed to the * stack. It is always safe to pass more frames than requested, * but this has negative impact on power consumption. * * @FIF_ALLMULTI: pass all multicast frames, this is used if requested * by the user or if the hardware is not capable of filtering by * multicast address. * * @FIF_FCSFAIL: pass frames with failed FCS (but you need to set the * %RX_FLAG_FAILED_FCS_CRC for them) * * @FIF_PLCPFAIL: pass frames with failed PLCP CRC (but you need to set * the %RX_FLAG_FAILED_PLCP_CRC for them * * @FIF_BCN_PRBRESP_PROMISC: This flag is set during scanning to indicate * to the hardware that it should not filter beacons or probe responses * by BSSID. Filtering them can greatly reduce the amount of processing * mac80211 needs to do and the amount of CPU wakeups, so you should * honour this flag if possible. * * @FIF_CONTROL: pass control frames (except for PS Poll) addressed to this * station * * @FIF_OTHER_BSS: pass frames destined to other BSSes * * @FIF_PSPOLL: pass PS Poll frames * * @FIF_PROBE_REQ: pass probe request frames * * @FIF_MCAST_ACTION: pass multicast Action frames */ enum ieee80211_filter_flags { FIF_ALLMULTI = 1<<1, FIF_FCSFAIL = 1<<2, FIF_PLCPFAIL = 1<<3, FIF_BCN_PRBRESP_PROMISC = 1<<4, FIF_CONTROL = 1<<5, FIF_OTHER_BSS = 1<<6, FIF_PSPOLL = 1<<7, FIF_PROBE_REQ = 1<<8, FIF_MCAST_ACTION = 1<<9, }; /** * enum ieee80211_ampdu_mlme_action - A-MPDU actions * * These flags are used with the ampdu_action() callback in * &struct ieee80211_ops to indicate which action is needed. * * Note that drivers MUST be able to deal with a TX aggregation * session being stopped even before they OK'ed starting it by * calling ieee80211_start_tx_ba_cb_irqsafe, because the peer * might receive the addBA frame and send a delBA right away! * * @IEEE80211_AMPDU_RX_START: start RX aggregation * @IEEE80211_AMPDU_RX_STOP: stop RX aggregation * @IEEE80211_AMPDU_TX_START: start TX aggregation, the driver must either * call ieee80211_start_tx_ba_cb_irqsafe() or * call ieee80211_start_tx_ba_cb_irqsafe() with status * %IEEE80211_AMPDU_TX_START_DELAY_ADDBA to delay addba after * ieee80211_start_tx_ba_cb_irqsafe is called, or just return the special * status %IEEE80211_AMPDU_TX_START_IMMEDIATE. * @IEEE80211_AMPDU_TX_OPERATIONAL: TX aggregation has become operational * @IEEE80211_AMPDU_TX_STOP_CONT: stop TX aggregation but continue transmitting * queued packets, now unaggregated. After all packets are transmitted the * driver has to call ieee80211_stop_tx_ba_cb_irqsafe(). * @IEEE80211_AMPDU_TX_STOP_FLUSH: stop TX aggregation and flush all packets, * called when the station is removed. There's no need or reason to call * ieee80211_stop_tx_ba_cb_irqsafe() in this case as mac80211 assumes the * session is gone and removes the station. * @IEEE80211_AMPDU_TX_STOP_FLUSH_CONT: called when TX aggregation is stopped * but the driver hasn't called ieee80211_stop_tx_ba_cb_irqsafe() yet and * now the connection is dropped and the station will be removed. Drivers * should clean up and drop remaining packets when this is called. */ enum ieee80211_ampdu_mlme_action { IEEE80211_AMPDU_RX_START, IEEE80211_AMPDU_RX_STOP, IEEE80211_AMPDU_TX_START, IEEE80211_AMPDU_TX_STOP_CONT, IEEE80211_AMPDU_TX_STOP_FLUSH, IEEE80211_AMPDU_TX_STOP_FLUSH_CONT, IEEE80211_AMPDU_TX_OPERATIONAL, }; #define IEEE80211_AMPDU_TX_START_IMMEDIATE 1 #define IEEE80211_AMPDU_TX_START_DELAY_ADDBA 2 /** * struct ieee80211_ampdu_params - AMPDU action parameters * * @action: the ampdu action, value from %ieee80211_ampdu_mlme_action. * @sta: peer of this AMPDU session * @tid: tid of the BA session * @ssn: start sequence number of the session. TX/RX_STOP can pass 0. When * action is set to %IEEE80211_AMPDU_RX_START the driver passes back the * actual ssn value used to start the session and writes the value here. * @buf_size: reorder buffer size (number of subframes). Valid only when the * action is set to %IEEE80211_AMPDU_RX_START or * %IEEE80211_AMPDU_TX_OPERATIONAL * @amsdu: indicates the peer's ability to receive A-MSDU within A-MPDU. * valid when the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL * @timeout: BA session timeout. Valid only when the action is set to * %IEEE80211_AMPDU_RX_START */ struct ieee80211_ampdu_params { enum ieee80211_ampdu_mlme_action action; struct ieee80211_sta *sta; u16 tid; u16 ssn; u16 buf_size; bool amsdu; u16 timeout; }; /** * enum ieee80211_frame_release_type - frame release reason * @IEEE80211_FRAME_RELEASE_PSPOLL: frame released for PS-Poll * @IEEE80211_FRAME_RELEASE_UAPSD: frame(s) released due to * frame received on trigger-enabled AC */ enum ieee80211_frame_release_type { IEEE80211_FRAME_RELEASE_PSPOLL, IEEE80211_FRAME_RELEASE_UAPSD, }; /** * enum ieee80211_rate_control_changed - flags to indicate what changed * * @IEEE80211_RC_BW_CHANGED: The bandwidth that can be used to transmit * to this station changed. The actual bandwidth is in the station * information -- for HT20/40 the IEEE80211_HT_CAP_SUP_WIDTH_20_40 * flag changes, for HT and VHT the bandwidth field changes. * @IEEE80211_RC_SMPS_CHANGED: The SMPS state of the station changed. * @IEEE80211_RC_SUPP_RATES_CHANGED: The supported rate set of this peer * changed (in IBSS mode) due to discovering more information about * the peer. * @IEEE80211_RC_NSS_CHANGED: N_SS (number of spatial streams) was changed * by the peer */ enum ieee80211_rate_control_changed { IEEE80211_RC_BW_CHANGED = BIT(0), IEEE80211_RC_SMPS_CHANGED = BIT(1), IEEE80211_RC_SUPP_RATES_CHANGED = BIT(2), IEEE80211_RC_NSS_CHANGED = BIT(3), }; /** * enum ieee80211_roc_type - remain on channel type * * With the support for multi channel contexts and multi channel operations, * remain on channel operations might be limited/deferred/aborted by other * flows/operations which have higher priority (and vice versa). * Specifying the ROC type can be used by devices to prioritize the ROC * operations compared to other operations/flows. * * @IEEE80211_ROC_TYPE_NORMAL: There are no special requirements for this ROC. * @IEEE80211_ROC_TYPE_MGMT_TX: The remain on channel request is required * for sending management frames offchannel. */ enum ieee80211_roc_type { IEEE80211_ROC_TYPE_NORMAL = 0, IEEE80211_ROC_TYPE_MGMT_TX, }; /** * enum ieee80211_reconfig_type - reconfig type * * This enum is used by the reconfig_complete() callback to indicate what * reconfiguration type was completed. * * @IEEE80211_RECONFIG_TYPE_RESTART: hw restart type * (also due to resume() callback returning 1) * @IEEE80211_RECONFIG_TYPE_SUSPEND: suspend type (regardless * of wowlan configuration) */ enum ieee80211_reconfig_type { IEEE80211_RECONFIG_TYPE_RESTART, IEEE80211_RECONFIG_TYPE_SUSPEND, }; /** * struct ieee80211_prep_tx_info - prepare TX information * @duration: if non-zero, hint about the required duration, * only used with the mgd_prepare_tx() method. * @subtype: frame subtype (auth, (re)assoc, deauth, disassoc) * @success: whether the frame exchange was successful, only * used with the mgd_complete_tx() method, and then only * valid for auth and (re)assoc. * @was_assoc: set if this call is due to deauth/disassoc * while just having been associated * @link_id: the link id on which the frame will be TX'ed. * 0 for a non-MLO connection. */ struct ieee80211_prep_tx_info { u16 duration; u16 subtype; u8 success:1, was_assoc:1; int link_id; }; /** * struct ieee80211_ops - callbacks from mac80211 to the driver * * This structure contains various callbacks that the driver may * handle or, in some cases, must handle, for example to configure * the hardware to a new channel or to transmit a frame. * * @tx: Handler that 802.11 module calls for each transmitted frame. * skb contains the buffer starting from the IEEE 802.11 header. * The low-level driver should send the frame out based on * configuration in the TX control data. This handler should, * preferably, never fail and stop queues appropriately. * Must be atomic. * * @start: Called before the first netdevice attached to the hardware * is enabled. This should turn on the hardware and must turn on * frame reception (for possibly enabled monitor interfaces.) * Returns negative error codes, these may be seen in userspace, * or zero. * When the device is started it should not have a MAC address * to avoid acknowledging frames before a non-monitor device * is added. * Must be implemented and can sleep. * * @stop: Called after last netdevice attached to the hardware * is disabled. This should turn off the hardware (at least * it must turn off frame reception.) * May be called right after add_interface if that rejects * an interface. If you added any work onto the mac80211 workqueue * you should ensure to cancel it on this callback. * Must be implemented and can sleep. * * @suspend: Suspend the device; mac80211 itself will quiesce before and * stop transmitting and doing any other configuration, and then * ask the device to suspend. This is only invoked when WoWLAN is * configured, otherwise the device is deconfigured completely and * reconfigured at resume time. * The driver may also impose special conditions under which it * wants to use the "normal" suspend (deconfigure), say if it only * supports WoWLAN when the device is associated. In this case, it * must return 1 from this function. * * @resume: If WoWLAN was configured, this indicates that mac80211 is * now resuming its operation, after this the device must be fully * functional again. If this returns an error, the only way out is * to also unregister the device. If it returns 1, then mac80211 * will also go through the regular complete restart on resume. * * @set_wakeup: Enable or disable wakeup when WoWLAN configuration is * modified. The reason is that device_set_wakeup_enable() is * supposed to be called when the configuration changes, not only * in suspend(). * * @add_interface: Called when a netdevice attached to the hardware is * enabled. Because it is not called for monitor mode devices, @start * and @stop must be implemented. * The driver should perform any initialization it needs before * the device can be enabled. The initial configuration for the * interface is given in the conf parameter. * The callback may refuse to add an interface by returning a * negative error code (which will be seen in userspace.) * Must be implemented and can sleep. * * @change_interface: Called when a netdevice changes type. This callback * is optional, but only if it is supported can interface types be * switched while the interface is UP. The callback may sleep. * Note that while an interface is being switched, it will not be * found by the interface iteration callbacks. * * @remove_interface: Notifies a driver that an interface is going down. * The @stop callback is called after this if it is the last interface * and no monitor interfaces are present. * When all interfaces are removed, the MAC address in the hardware * must be cleared so the device no longer acknowledges packets, * the mac_addr member of the conf structure is, however, set to the * MAC address of the device going away. * Hence, this callback must be implemented. It can sleep. * * @config: Handler for configuration requests. IEEE 802.11 code calls this * function to change hardware configuration, e.g., channel. * This function should never fail but returns a negative error code * if it does. The callback can sleep. * * @bss_info_changed: Handler for configuration requests related to BSS * parameters that may vary during BSS's lifespan, and may affect low * level driver (e.g. assoc/disassoc status, erp parameters). * This function should not be used if no BSS has been set, unless * for association indication. The @changed parameter indicates which * of the bss parameters has changed when a call is made. The callback * can sleep. * Note: this callback is called if @vif_cfg_changed or @link_info_changed * are not implemented. * * @vif_cfg_changed: Handler for configuration requests related to interface * (MLD) parameters from &struct ieee80211_vif_cfg that vary during the * lifetime of the interface (e.g. assoc status, IP addresses, etc.) * The @changed parameter indicates which value changed. * The callback can sleep. * * @link_info_changed: Handler for configuration requests related to link * parameters from &struct ieee80211_bss_conf that are related to an * individual link. e.g. legacy/HT/VHT/... rate information. * The @changed parameter indicates which value changed, and the @link_id * parameter indicates the link ID. Note that the @link_id will be 0 for * non-MLO connections. * The callback can sleep. * * @prepare_multicast: Prepare for multicast filter configuration. * This callback is optional, and its return value is passed * to configure_filter(). This callback must be atomic. * * @configure_filter: Configure the device's RX filter. * See the section "Frame filtering" for more information. * This callback must be implemented and can sleep. * * @config_iface_filter: Configure the interface's RX filter. * This callback is optional and is used to configure which frames * should be passed to mac80211. The filter_flags is the combination * of FIF_* flags. The changed_flags is a bit mask that indicates * which flags are changed. * This callback can sleep. * * @set_tim: Set TIM bit. mac80211 calls this function when a TIM bit * must be set or cleared for a given STA. Must be atomic. * * @set_key: See the section "Hardware crypto acceleration" * This callback is only called between add_interface and * remove_interface calls, i.e. while the given virtual interface * is enabled. * Returns a negative error code if the key can't be added. * The callback can sleep. * * @update_tkip_key: See the section "Hardware crypto acceleration" * This callback will be called in the context of Rx. Called for drivers * which set IEEE80211_KEY_FLAG_TKIP_REQ_RX_P1_KEY. * The callback must be atomic. * * @set_rekey_data: If the device supports GTK rekeying, for example while the * host is suspended, it can assign this callback to retrieve the data * necessary to do GTK rekeying, this is the KEK, KCK and replay counter. * After rekeying was done it should (for example during resume) notify * userspace of the new replay counter using ieee80211_gtk_rekey_notify(). * * @set_default_unicast_key: Set the default (unicast) key index, useful for * WEP when the device sends data packets autonomously, e.g. for ARP * offloading. The index can be 0-3, or -1 for unsetting it. * * @hw_scan: Ask the hardware to service the scan request, no need to start * the scan state machine in stack. The scan must honour the channel * configuration done by the regulatory agent in the wiphy's * registered bands. The hardware (or the driver) needs to make sure * that power save is disabled. * The @req ie/ie_len members are rewritten by mac80211 to contain the * entire IEs after the SSID, so that drivers need not look at these * at all but just send them after the SSID -- mac80211 includes the * (extended) supported rates and HT information (where applicable). * When the scan finishes, ieee80211_scan_completed() must be called; * note that it also must be called when the scan cannot finish due to * any error unless this callback returned a negative error code. * This callback is also allowed to return the special return value 1, * this indicates that hardware scan isn't desirable right now and a * software scan should be done instead. A driver wishing to use this * capability must ensure its (hardware) scan capabilities aren't * advertised as more capable than mac80211's software scan is. * The callback can sleep. * * @cancel_hw_scan: Ask the low-level tp cancel the active hw scan. * The driver should ask the hardware to cancel the scan (if possible), * but the scan will be completed only after the driver will call * ieee80211_scan_completed(). * This callback is needed for wowlan, to prevent enqueueing a new * scan_work after the low-level driver was already suspended. * The callback can sleep. * * @sched_scan_start: Ask the hardware to start scanning repeatedly at * specific intervals. The driver must call the * ieee80211_sched_scan_results() function whenever it finds results. * This process will continue until sched_scan_stop is called. * * @sched_scan_stop: Tell the hardware to stop an ongoing scheduled scan. * In this case, ieee80211_sched_scan_stopped() must not be called. * * @sw_scan_start: Notifier function that is called just before a software scan * is started. Can be NULL, if the driver doesn't need this notification. * The mac_addr parameter allows supporting NL80211_SCAN_FLAG_RANDOM_ADDR, * the driver may set the NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR flag if it * can use this parameter. The callback can sleep. * * @sw_scan_complete: Notifier function that is called just after a * software scan finished. Can be NULL, if the driver doesn't need * this notification. * The callback can sleep. * * @get_stats: Return low-level statistics. * Returns zero if statistics are available. * The callback can sleep. * * @get_key_seq: If your device implements encryption in hardware and does * IV/PN assignment then this callback should be provided to read the * IV/PN for the given key from hardware. * The callback must be atomic. * * @set_frag_threshold: Configuration of fragmentation threshold. Assign this * if the device does fragmentation by itself. Note that to prevent the * stack from doing fragmentation IEEE80211_HW_SUPPORTS_TX_FRAG * should be set as well. * The callback can sleep. * * @set_rts_threshold: Configuration of RTS threshold (if device needs it) * The callback can sleep. * * @sta_add: Notifies low level driver about addition of an associated station, * AP, IBSS/WDS/mesh peer etc. This callback can sleep. * * @sta_remove: Notifies low level driver about removal of an associated * station, AP, IBSS/WDS/mesh peer etc. Note that after the callback * returns it isn't safe to use the pointer, not even RCU protected; * no RCU grace period is guaranteed between returning here and freeing * the station. See @sta_pre_rcu_remove if needed. * This callback can sleep. * * @vif_add_debugfs: Drivers can use this callback to add a debugfs vif * directory with its files. This callback should be within a * CONFIG_MAC80211_DEBUGFS conditional. This callback can sleep. * * @link_add_debugfs: Drivers can use this callback to add debugfs files * when a link is added to a mac80211 vif. This callback should be within * a CONFIG_MAC80211_DEBUGFS conditional. This callback can sleep. * For non-MLO the callback will be called once for the default bss_conf * with the vif's directory rather than a separate subdirectory. * * @sta_add_debugfs: Drivers can use this callback to add debugfs files * when a station is added to mac80211's station list. This callback * should be within a CONFIG_MAC80211_DEBUGFS conditional. This * callback can sleep. * * @link_sta_add_debugfs: Drivers can use this callback to add debugfs files * when a link is added to a mac80211 station. This callback * should be within a CONFIG_MAC80211_DEBUGFS conditional. This * callback can sleep. * For non-MLO the callback will be called once for the deflink with the * station's directory rather than a separate subdirectory. * * @sta_notify: Notifies low level driver about power state transition of an * associated station, AP, IBSS/WDS/mesh peer etc. For a VIF operating * in AP mode, this callback will not be called when the flag * %IEEE80211_HW_AP_LINK_PS is set. Must be atomic. * * @sta_set_txpwr: Configure the station tx power. This callback set the tx * power for the station. * This callback can sleep. * * @sta_state: Notifies low level driver about state transition of a * station (which can be the AP, a client, IBSS/WDS/mesh peer etc.) * This callback is mutually exclusive with @sta_add/@sta_remove. * It must not fail for down transitions but may fail for transitions * up the list of states. Also note that after the callback returns it * isn't safe to use the pointer, not even RCU protected - no RCU grace * period is guaranteed between returning here and freeing the station. * See @sta_pre_rcu_remove if needed. * The callback can sleep. * * @sta_pre_rcu_remove: Notify driver about station removal before RCU * synchronisation. This is useful if a driver needs to have station * pointers protected using RCU, it can then use this call to clear * the pointers instead of waiting for an RCU grace period to elapse * in @sta_state. * The callback can sleep. * * @link_sta_rc_update: Notifies the driver of changes to the bitrates that can * be used to transmit to the station. The changes are advertised with bits * from &enum ieee80211_rate_control_changed and the values are reflected * in the station data. This callback should only be used when the driver * uses hardware rate control (%IEEE80211_HW_HAS_RATE_CONTROL) since * otherwise the rate control algorithm is notified directly. * Must be atomic. * @sta_rate_tbl_update: Notifies the driver that the rate table changed. This * is only used if the configured rate control algorithm actually uses * the new rate table API, and is therefore optional. Must be atomic. * * @sta_statistics: Get statistics for this station. For example with beacon * filtering, the statistics kept by mac80211 might not be accurate, so * let the driver pre-fill the statistics. The driver can fill most of * the values (indicating which by setting the filled bitmap), but not * all of them make sense - see the source for which ones are possible. * Statistics that the driver doesn't fill will be filled by mac80211. * The callback can sleep. * * @conf_tx: Configure TX queue parameters (EDCF (aifs, cw_min, cw_max), * bursting) for a hardware TX queue. * Returns a negative error code on failure. * The callback can sleep. * * @get_tsf: Get the current TSF timer value from firmware/hardware. Currently, * this is only used for IBSS mode BSSID merging and debugging. Is not a * required function. * The callback can sleep. * * @set_tsf: Set the TSF timer to the specified value in the firmware/hardware. * Currently, this is only used for IBSS mode debugging. Is not a * required function. * The callback can sleep. * * @offset_tsf: Offset the TSF timer by the specified value in the * firmware/hardware. Preferred to set_tsf as it avoids delay between * calling set_tsf() and hardware getting programmed, which will show up * as TSF delay. Is not a required function. * The callback can sleep. * * @reset_tsf: Reset the TSF timer and allow firmware/hardware to synchronize * with other STAs in the IBSS. This is only used in IBSS mode. This * function is optional if the firmware/hardware takes full care of * TSF synchronization. * The callback can sleep. * * @tx_last_beacon: Determine whether the last IBSS beacon was sent by us. * This is needed only for IBSS mode and the result of this function is * used to determine whether to reply to Probe Requests. * Returns non-zero if this device sent the last beacon. * The callback can sleep. * * @get_survey: Return per-channel survey information * * @rfkill_poll: Poll rfkill hardware state. If you need this, you also * need to set wiphy->rfkill_poll to %true before registration, * and need to call wiphy_rfkill_set_hw_state() in the callback. * The callback can sleep. * * @set_coverage_class: Set slot time for given coverage class as specified * in IEEE 802.11-2007 section 17.3.8.6 and modify ACK timeout * accordingly; coverage class equals to -1 to enable ACK timeout * estimation algorithm (dynack). To disable dynack set valid value for * coverage class. This callback is not required and may sleep. * * @testmode_cmd: Implement a cfg80211 test mode command. The passed @vif may * be %NULL. The callback can sleep. * @testmode_dump: Implement a cfg80211 test mode dump. The callback can sleep. * * @flush: Flush all pending frames from the hardware queue, making sure * that the hardware queues are empty. The @queues parameter is a bitmap * of queues to flush, which is useful if different virtual interfaces * use different hardware queues; it may also indicate all queues. * If the parameter @drop is set to %true, pending frames may be dropped. * Note that vif can be NULL. * The callback can sleep. * * @flush_sta: Flush or drop all pending frames from the hardware queue(s) for * the given station, as it's about to be removed. * The callback can sleep. * * @channel_switch: Drivers that need (or want) to offload the channel * switch operation for CSAs received from the AP may implement this * callback. They must then call ieee80211_chswitch_done() to indicate * completion of the channel switch. * * @set_antenna: Set antenna configuration (tx_ant, rx_ant) on the device. * Parameters are bitmaps of allowed antennas to use for TX/RX. Drivers may * reject TX/RX mask combinations they cannot support by returning -EINVAL * (also see nl80211.h @NL80211_ATTR_WIPHY_ANTENNA_TX). * * @get_antenna: Get current antenna configuration from device (tx_ant, rx_ant). * * @remain_on_channel: Starts an off-channel period on the given channel, must * call back to ieee80211_ready_on_channel() when on that channel. Note * that normal channel traffic is not stopped as this is intended for hw * offload. Frames to transmit on the off-channel channel are transmitted * normally except for the %IEEE80211_TX_CTL_TX_OFFCHAN flag. When the * duration (which will always be non-zero) expires, the driver must call * ieee80211_remain_on_channel_expired(). * Note that this callback may be called while the device is in IDLE and * must be accepted in this case. * This callback may sleep. * @cancel_remain_on_channel: Requests that an ongoing off-channel period is * aborted before it expires. This callback may sleep. * * @set_ringparam: Set tx and rx ring sizes. * * @get_ringparam: Get tx and rx ring current and maximum sizes. * * @tx_frames_pending: Check if there is any pending frame in the hardware * queues before entering power save. * * @set_bitrate_mask: Set a mask of rates to be used for rate control selection * when transmitting a frame. Currently only legacy rates are handled. * The callback can sleep. * @event_callback: Notify driver about any event in mac80211. See * &enum ieee80211_event_type for the different types. * The callback must be atomic. * * @release_buffered_frames: Release buffered frames according to the given * parameters. In the case where the driver buffers some frames for * sleeping stations mac80211 will use this callback to tell the driver * to release some frames, either for PS-poll or uAPSD. * Note that if the @more_data parameter is %false the driver must check * if there are more frames on the given TIDs, and if there are more than * the frames being released then it must still set the more-data bit in * the frame. If the @more_data parameter is %true, then of course the * more-data bit must always be set. * The @tids parameter tells the driver which TIDs to release frames * from, for PS-poll it will always have only a single bit set. * In the case this is used for a PS-poll initiated release, the * @num_frames parameter will always be 1 so code can be shared. In * this case the driver must also set %IEEE80211_TX_STATUS_EOSP flag * on the TX status (and must report TX status) so that the PS-poll * period is properly ended. This is used to avoid sending multiple * responses for a retried PS-poll frame. * In the case this is used for uAPSD, the @num_frames parameter may be * bigger than one, but the driver may send fewer frames (it must send * at least one, however). In this case it is also responsible for * setting the EOSP flag in the QoS header of the frames. Also, when the * service period ends, the driver must set %IEEE80211_TX_STATUS_EOSP * on the last frame in the SP. Alternatively, it may call the function * ieee80211_sta_eosp() to inform mac80211 of the end of the SP. * This callback must be atomic. * @allow_buffered_frames: Prepare device to allow the given number of frames * to go out to the given station. The frames will be sent by mac80211 * via the usual TX path after this call. The TX information for frames * released will also have the %IEEE80211_TX_CTL_NO_PS_BUFFER flag set * and the last one will also have %IEEE80211_TX_STATUS_EOSP set. In case * frames from multiple TIDs are released and the driver might reorder * them between the TIDs, it must set the %IEEE80211_TX_STATUS_EOSP flag * on the last frame and clear it on all others and also handle the EOSP * bit in the QoS header correctly. Alternatively, it can also call the * ieee80211_sta_eosp() function. * The @tids parameter is a bitmap and tells the driver which TIDs the * frames will be on; it will at most have two bits set. * This callback must be atomic. * * @get_et_sset_count: Ethtool API to get string-set count. * Note that the wiphy mutex is not held for this callback since it's * expected to return a static value. * * @get_et_stats: Ethtool API to get a set of u64 stats. * * @get_et_strings: Ethtool API to get a set of strings to describe stats * and perhaps other supported types of ethtool data-sets. * Note that the wiphy mutex is not held for this callback since it's * expected to return a static value. * * @mgd_prepare_tx: Prepare for transmitting a management frame for association * before associated. In multi-channel scenarios, a virtual interface is * bound to a channel before it is associated, but as it isn't associated * yet it need not necessarily be given airtime, in particular since any * transmission to a P2P GO needs to be synchronized against the GO's * powersave state. mac80211 will call this function before transmitting a * management frame prior to transmitting that frame to allow the driver * to give it channel time for the transmission, to get a response and be * able to synchronize with the GO. * The callback will be called before each transmission and upon return * mac80211 will transmit the frame right away. * Additional information is passed in the &struct ieee80211_prep_tx_info * data. If duration there is greater than zero, mac80211 hints to the * driver the duration for which the operation is requested. * The callback is optional and can (should!) sleep. * @mgd_complete_tx: Notify the driver that the response frame for a previously * transmitted frame announced with @mgd_prepare_tx was received, the data * is filled similarly to @mgd_prepare_tx though the duration is not used. * * @mgd_protect_tdls_discover: Protect a TDLS discovery session. After sending * a TDLS discovery-request, we expect a reply to arrive on the AP's * channel. We must stay on the channel (no PSM, scan, etc.), since a TDLS * setup-response is a direct packet not buffered by the AP. * mac80211 will call this function just before the transmission of a TDLS * discovery-request. The recommended period of protection is at least * 2 * (DTIM period). * The callback is optional and can sleep. * * @add_chanctx: Notifies device driver about new channel context creation. * This callback may sleep. * @remove_chanctx: Notifies device driver about channel context destruction. * This callback may sleep. * @change_chanctx: Notifies device driver about channel context changes that * may happen when combining different virtual interfaces on the same * channel context with different settings * This callback may sleep. * @assign_vif_chanctx: Notifies device driver about channel context being bound * to vif. Possible use is for hw queue remapping. * This callback may sleep. * @unassign_vif_chanctx: Notifies device driver about channel context being * unbound from vif. * This callback may sleep. * @switch_vif_chanctx: switch a number of vifs from one chanctx to * another, as specified in the list of * @ieee80211_vif_chanctx_switch passed to the driver, according * to the mode defined in &ieee80211_chanctx_switch_mode. * This callback may sleep. * * @start_ap: Start operation on the AP interface, this is called after all the * information in bss_conf is set and beacon can be retrieved. A channel * context is bound before this is called. Note that if the driver uses * software scan or ROC, this (and @stop_ap) isn't called when the AP is * just "paused" for scanning/ROC, which is indicated by the beacon being * disabled/enabled via @bss_info_changed. * @stop_ap: Stop operation on the AP interface. * * @reconfig_complete: Called after a call to ieee80211_restart_hw() and * during resume, when the reconfiguration has completed. * This can help the driver implement the reconfiguration step (and * indicate mac80211 is ready to receive frames). * This callback may sleep. * * @ipv6_addr_change: IPv6 address assignment on the given interface changed. * Currently, this is only called for managed or P2P client interfaces. * This callback is optional; it must not sleep. * * @channel_switch_beacon: Starts a channel switch to a new channel. * Beacons are modified to include CSA or ECSA IEs before calling this * function. The corresponding count fields in these IEs must be * decremented, and when they reach 1 the driver must call * ieee80211_csa_finish(). Drivers which use ieee80211_beacon_get() * get the csa counter decremented by mac80211, but must check if it is * 1 using ieee80211_beacon_counter_is_complete() after the beacon has been * transmitted and then call ieee80211_csa_finish(). * If the CSA count starts as zero or 1, this function will not be called, * since there won't be any time to beacon before the switch anyway. * @pre_channel_switch: This is an optional callback that is called * before a channel switch procedure is started (ie. when a STA * gets a CSA or a userspace initiated channel-switch), allowing * the driver to prepare for the channel switch. * @post_channel_switch: This is an optional callback that is called * after a channel switch procedure is completed, allowing the * driver to go back to a normal configuration. * @abort_channel_switch: This is an optional callback that is called * when channel switch procedure was aborted, allowing the * driver to go back to a normal configuration. * @channel_switch_rx_beacon: This is an optional callback that is called * when channel switch procedure is in progress and additional beacon with * CSA IE was received, allowing driver to track changes in count. * @join_ibss: Join an IBSS (on an IBSS interface); this is called after all * information in bss_conf is set up and the beacon can be retrieved. A * channel context is bound before this is called. * @leave_ibss: Leave the IBSS again. * * @get_expected_throughput: extract the expected throughput towards the * specified station. The returned value is expressed in Kbps. It returns 0 * if the RC algorithm does not have proper data to provide. * * @get_txpower: get current maximum tx power (in dBm) based on configuration * and hardware limits. * * @tdls_channel_switch: Start channel-switching with a TDLS peer. The driver * is responsible for continually initiating channel-switching operations * and returning to the base channel for communication with the AP. The * driver receives a channel-switch request template and the location of * the switch-timing IE within the template as part of the invocation. * The template is valid only within the call, and the driver can * optionally copy the skb for further re-use. * @tdls_cancel_channel_switch: Stop channel-switching with a TDLS peer. Both * peers must be on the base channel when the call completes. * @tdls_recv_channel_switch: a TDLS channel-switch related frame (request or * response) has been received from a remote peer. The driver gets * parameters parsed from the incoming frame and may use them to continue * an ongoing channel-switch operation. In addition, a channel-switch * response template is provided, together with the location of the * switch-timing IE within the template. The skb can only be used within * the function call. * * @wake_tx_queue: Called when new packets have been added to the queue. * @sync_rx_queues: Process all pending frames in RSS queues. This is a * synchronization which is needed in case driver has in its RSS queues * pending frames that were received prior to the control path action * currently taken (e.g. disassociation) but are not processed yet. * * @start_nan: join an existing NAN cluster, or create a new one. * @stop_nan: leave the NAN cluster. * @nan_change_conf: change NAN configuration. The data in cfg80211_nan_conf * contains full new configuration and changes specify which parameters * are changed with respect to the last NAN config. * The driver gets both full configuration and the changed parameters since * some devices may need the full configuration while others need only the * changed parameters. * @add_nan_func: Add a NAN function. Returns 0 on success. The data in * cfg80211_nan_func must not be referenced outside the scope of * this call. * @del_nan_func: Remove a NAN function. The driver must call * ieee80211_nan_func_terminated() with * NL80211_NAN_FUNC_TERM_REASON_USER_REQUEST reason code upon removal. * @can_aggregate_in_amsdu: Called in order to determine if HW supports * aggregating two specific frames in the same A-MSDU. The relation * between the skbs should be symmetric and transitive. Note that while * skb is always a real frame, head may or may not be an A-MSDU. * @get_ftm_responder_stats: Retrieve FTM responder statistics, if available. * Statistics should be cumulative, currently no way to reset is provided. * * @start_pmsr: start peer measurement (e.g. FTM) (this call can sleep) * @abort_pmsr: abort peer measurement (this call can sleep) * @set_tid_config: Apply TID specific configurations. This callback may sleep. * @reset_tid_config: Reset TID specific configuration for the peer. * This callback may sleep. * @update_vif_offload: Update virtual interface offload flags * This callback may sleep. * @sta_set_4addr: Called to notify the driver when a station starts/stops using * 4-address mode * @set_sar_specs: Update the SAR (TX power) settings. * @sta_set_decap_offload: Called to notify the driver when a station is allowed * to use rx decapsulation offload * @add_twt_setup: Update hw with TWT agreement parameters received from the peer. * This callback allows the hw to check if requested parameters * are supported and if there is enough room for a new agreement. * The hw is expected to set agreement result in the req_type field of * twt structure. * @twt_teardown_request: Update the hw with TWT teardown request received * from the peer. * @set_radar_background: Configure dedicated offchannel chain available for * radar/CAC detection on some hw. This chain can't be used to transmit * or receive frames and it is bounded to a running wdev. * Background radar/CAC detection allows to avoid the CAC downtime * switching to a different channel during CAC detection on the selected * radar channel. * The caller is expected to set chandef pointer to NULL in order to * disable background CAC/radar detection. * @net_fill_forward_path: Called from .ndo_fill_forward_path in order to * resolve a path for hardware flow offloading * @can_activate_links: Checks if a specific active_links bitmap is * supported by the driver. * @change_vif_links: Change the valid links on an interface, note that while * removing the old link information is still valid (link_conf pointer), * but may immediately disappear after the function returns. The old or * new links bitmaps may be 0 if going from/to a non-MLO situation. * The @old array contains pointers to the old bss_conf structures * that were already removed, in case they're needed. * This callback can sleep. * @change_sta_links: Change the valid links of a station, similar to * @change_vif_links. This callback can sleep. * Note that a sta can also be inserted or removed with valid links, * i.e. passed to @sta_add/@sta_state with sta->valid_links not zero. * In fact, cannot change from having valid_links and not having them. * @set_hw_timestamp: Enable/disable HW timestamping of TM/FTM frames. This is * not restored at HW reset by mac80211 so drivers need to take care of * that. * @net_setup_tc: Called from .ndo_setup_tc in order to prepare hardware * flow offloading for flows originating from the vif. * Note that the driver must not assume that the vif driver_data is valid * at this point, since the callback can be called during netdev teardown. * @can_neg_ttlm: for managed interface, requests the driver to determine * if the requested TID-To-Link mapping can be accepted or not. * If it's not accepted the driver may suggest a preferred mapping and * modify @ttlm parameter with the suggested TID-to-Link mapping. * @prep_add_interface: prepare for interface addition. This can be used by * drivers to prepare for the addition of a new interface, e.g., allocate * the needed resources etc. This callback doesn't guarantee that an * interface with the specified type would be added, and thus drivers that * implement this callback need to handle such cases. The type is the full * &enum nl80211_iftype. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct sk_buff *skb); int (*start)(struct ieee80211_hw *hw); void (*stop)(struct ieee80211_hw *hw, bool suspend); #ifdef CONFIG_PM int (*suspend)(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan); int (*resume)(struct ieee80211_hw *hw); void (*set_wakeup)(struct ieee80211_hw *hw, bool enabled); #endif int (*add_interface)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*change_interface)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum nl80211_iftype new_type, bool p2p); void (*remove_interface)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*config)(struct ieee80211_hw *hw, u32 changed); void (*bss_info_changed)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *info, u64 changed); void (*vif_cfg_changed)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u64 changed); void (*link_info_changed)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *info, u64 changed); int (*start_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf); void (*stop_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf); u64 (*prepare_multicast)(struct ieee80211_hw *hw, struct netdev_hw_addr_list *mc_list); void (*configure_filter)(struct ieee80211_hw *hw, unsigned int changed_flags, unsigned int *total_flags, u64 multicast); void (*config_iface_filter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int filter_flags, unsigned int changed_flags); int (*set_tim)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, bool set); int (*set_key)(struct ieee80211_hw *hw, enum set_key_cmd cmd, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key); void (*update_tkip_key)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_key_conf *conf, struct ieee80211_sta *sta, u32 iv32, u16 *phase1key); void (*set_rekey_data)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_gtk_rekey_data *data); void (*set_default_unicast_key)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int idx); int (*hw_scan)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_scan_request *req); void (*cancel_hw_scan)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*sched_scan_start)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_sched_scan_request *req, struct ieee80211_scan_ies *ies); int (*sched_scan_stop)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*sw_scan_start)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const u8 *mac_addr); void (*sw_scan_complete)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*get_stats)(struct ieee80211_hw *hw, struct ieee80211_low_level_stats *stats); void (*get_key_seq)(struct ieee80211_hw *hw, struct ieee80211_key_conf *key, struct ieee80211_key_seq *seq); int (*set_frag_threshold)(struct ieee80211_hw *hw, u32 value); int (*set_rts_threshold)(struct ieee80211_hw *hw, u32 value); int (*sta_add)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); int (*sta_remove)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); #ifdef CONFIG_MAC80211_DEBUGFS void (*vif_add_debugfs)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*link_add_debugfs)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf, struct dentry *dir); void (*sta_add_debugfs)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct dentry *dir); void (*link_sta_add_debugfs)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_link_sta *link_sta, struct dentry *dir); #endif void (*sta_notify)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum sta_notify_cmd, struct ieee80211_sta *sta); int (*sta_set_txpwr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); int (*sta_state)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, enum ieee80211_sta_state old_state, enum ieee80211_sta_state new_state); void (*sta_pre_rcu_remove)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void (*link_sta_rc_update)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_link_sta *link_sta, u32 changed); void (*sta_rate_tbl_update)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void (*sta_statistics)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct station_info *sinfo); int (*conf_tx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int link_id, u16 ac, const struct ieee80211_tx_queue_params *params); u64 (*get_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*set_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u64 tsf); void (*offset_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, s64 offset); void (*reset_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*tx_last_beacon)(struct ieee80211_hw *hw); /** * @ampdu_action: * Perform a certain A-MPDU action. * The RA/TID combination determines the destination and TID we want * the ampdu action to be performed for. The action is defined through * ieee80211_ampdu_mlme_action. * When the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL the driver * may neither send aggregates containing more subframes than @buf_size * nor send aggregates in a way that lost frames would exceed the * buffer size. If just limiting the aggregate size, this would be * possible with a buf_size of 8: * * - ``TX: 1.....7`` * - ``RX: 2....7`` (lost frame #1) * - ``TX: 8..1...`` * * which is invalid since #1 was now re-transmitted well past the * buffer size of 8. Correct ways to retransmit #1 would be: * * - ``TX: 1 or`` * - ``TX: 18 or`` * - ``TX: 81`` * * Even ``189`` would be wrong since 1 could be lost again. * * Returns a negative error code on failure. The driver may return * %IEEE80211_AMPDU_TX_START_IMMEDIATE for %IEEE80211_AMPDU_TX_START * if the session can start immediately. * * The callback can sleep. */ int (*ampdu_action)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params); int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); void (*set_coverage_class)(struct ieee80211_hw *hw, s16 coverage_class); #ifdef CONFIG_NL80211_TESTMODE int (*testmode_cmd)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void *data, int len); int (*testmode_dump)(struct ieee80211_hw *hw, struct sk_buff *skb, struct netlink_callback *cb, void *data, int len); #endif void (*flush)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u32 queues, bool drop); void (*flush_sta)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void (*channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel_switch *ch_switch); int (*set_antenna)(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant); int (*get_antenna)(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant); int (*remain_on_channel)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel *chan, int duration, enum ieee80211_roc_type type); int (*cancel_remain_on_channel)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*set_ringparam)(struct ieee80211_hw *hw, u32 tx, u32 rx); void (*get_ringparam)(struct ieee80211_hw *hw, u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max); bool (*tx_frames_pending)(struct ieee80211_hw *hw); int (*set_bitrate_mask)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const struct cfg80211_bitrate_mask *mask); void (*event_callback)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const struct ieee80211_event *event); void (*allow_buffered_frames)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u16 tids, int num_frames, enum ieee80211_frame_release_type reason, bool more_data); void (*release_buffered_frames)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u16 tids, int num_frames, enum ieee80211_frame_release_type reason, bool more_data); int (*get_et_sset_count)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int sset); void (*get_et_stats)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ethtool_stats *stats, u64 *data); void (*get_et_strings)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u32 sset, u8 *data); void (*mgd_prepare_tx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_prep_tx_info *info); void (*mgd_complete_tx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_prep_tx_info *info); void (*mgd_protect_tdls_discover)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int link_id); int (*add_chanctx)(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx); void (*remove_chanctx)(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx); void (*change_chanctx)(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx, u32 changed); int (*assign_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf, struct ieee80211_chanctx_conf *ctx); void (*unassign_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf, struct ieee80211_chanctx_conf *ctx); int (*switch_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif_chanctx_switch *vifs, int n_vifs, enum ieee80211_chanctx_switch_mode mode); void (*reconfig_complete)(struct ieee80211_hw *hw, enum ieee80211_reconfig_type reconfig_type); #if IS_ENABLED(CONFIG_IPV6) void (*ipv6_addr_change)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct inet6_dev *idev); #endif void (*channel_switch_beacon)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_chan_def *chandef); int (*pre_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel_switch *ch_switch); int (*post_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf); void (*abort_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf); void (*channel_switch_rx_beacon)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel_switch *ch_switch); int (*join_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*leave_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); u32 (*get_expected_throughput)(struct ieee80211_hw *hw, struct ieee80211_sta *sta); int (*get_txpower)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int link_id, int *dbm); int (*tdls_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, u8 oper_class, struct cfg80211_chan_def *chandef, struct sk_buff *tmpl_skb, u32 ch_sw_tm_ie); void (*tdls_cancel_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void (*tdls_recv_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_tdls_ch_sw_params *params); void (*wake_tx_queue)(struct ieee80211_hw *hw, struct ieee80211_txq *txq); void (*sync_rx_queues)(struct ieee80211_hw *hw); int (*start_nan)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_nan_conf *conf); int (*stop_nan)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*nan_change_conf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_nan_conf *conf, u32 changes); int (*add_nan_func)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const struct cfg80211_nan_func *nan_func); void (*del_nan_func)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u8 instance_id); bool (*can_aggregate_in_amsdu)(struct ieee80211_hw *hw, struct sk_buff *head, struct sk_buff *skb); int (*get_ftm_responder_stats)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_ftm_responder_stats *ftm_stats); int (*start_pmsr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_pmsr_request *request); void (*abort_pmsr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_pmsr_request *request); int (*set_tid_config)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct cfg80211_tid_config *tid_conf); int (*reset_tid_config)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, u8 tids); void (*update_vif_offload)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*sta_set_4addr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, bool enabled); int (*set_sar_specs)(struct ieee80211_hw *hw, const struct cfg80211_sar_specs *sar); void (*sta_set_decap_offload)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, bool enabled); void (*add_twt_setup)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct ieee80211_twt_setup *twt); void (*twt_teardown_request)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u8 flowid); int (*set_radar_background)(struct ieee80211_hw *hw, struct cfg80211_chan_def *chandef); int (*net_fill_forward_path)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct net_device_path_ctx *ctx, struct net_device_path *path); bool (*can_activate_links)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 active_links); int (*change_vif_links)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 old_links, u16 new_links, struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS]); int (*change_sta_links)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, u16 old_links, u16 new_links); int (*set_hw_timestamp)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_set_hw_timestamp *hwts); int (*net_setup_tc)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct net_device *dev, enum tc_setup_type type, void *type_data); enum ieee80211_neg_ttlm_res (*can_neg_ttlm)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_neg_ttlm *ttlm); void (*prep_add_interface)(struct ieee80211_hw *hw, enum nl80211_iftype type); }; /** * ieee80211_alloc_hw_nm - Allocate a new hardware device * * This must be called once for each hardware device. The returned pointer * must be used to refer to this device when calling other functions. * mac80211 allocates a private data area for the driver pointed to by * @priv in &struct ieee80211_hw, the size of this area is given as * @priv_data_len. * * @priv_data_len: length of private data * @ops: callbacks for this device * @requested_name: Requested name for this device. * NULL is valid value, and means use the default naming (phy%d) * * Return: A pointer to the new hardware device, or %NULL on error. */ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, const struct ieee80211_ops *ops, const char *requested_name); /** * ieee80211_alloc_hw - Allocate a new hardware device * * This must be called once for each hardware device. The returned pointer * must be used to refer to this device when calling other functions. * mac80211 allocates a private data area for the driver pointed to by * @priv in &struct ieee80211_hw, the size of this area is given as * @priv_data_len. * * @priv_data_len: length of private data * @ops: callbacks for this device * * Return: A pointer to the new hardware device, or %NULL on error. */ static inline struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, const struct ieee80211_ops *ops) { return ieee80211_alloc_hw_nm(priv_data_len, ops, NULL); } /** * ieee80211_register_hw - Register hardware device * * You must call this function before any other functions in * mac80211. Note that before a hardware can be registered, you * need to fill the contained wiphy's information. * * @hw: the device to register as returned by ieee80211_alloc_hw() * * Return: 0 on success. An error code otherwise. */ int ieee80211_register_hw(struct ieee80211_hw *hw); /** * struct ieee80211_tpt_blink - throughput blink description * @throughput: throughput in Kbit/sec * @blink_time: blink time in milliseconds * (full cycle, ie. one off + one on period) */ struct ieee80211_tpt_blink { int throughput; int blink_time; }; /** * enum ieee80211_tpt_led_trigger_flags - throughput trigger flags * @IEEE80211_TPT_LEDTRIG_FL_RADIO: enable blinking with radio * @IEEE80211_TPT_LEDTRIG_FL_WORK: enable blinking when working * @IEEE80211_TPT_LEDTRIG_FL_CONNECTED: enable blinking when at least one * interface is connected in some way, including being an AP */ enum ieee80211_tpt_led_trigger_flags { IEEE80211_TPT_LEDTRIG_FL_RADIO = BIT(0), IEEE80211_TPT_LEDTRIG_FL_WORK = BIT(1), IEEE80211_TPT_LEDTRIG_FL_CONNECTED = BIT(2), }; #ifdef CONFIG_MAC80211_LEDS const char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw); const char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw); const char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw); const char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw); const char * __ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, unsigned int flags, const struct ieee80211_tpt_blink *blink_table, unsigned int blink_table_len); #endif /** * ieee80211_get_tx_led_name - get name of TX LED * * mac80211 creates a transmit LED trigger for each wireless hardware * that can be used to drive LEDs if your driver registers a LED device. * This function returns the name (or %NULL if not configured for LEDs) * of the trigger so you can automatically link the LED device. * * @hw: the hardware to get the LED trigger name for * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ static inline const char *ieee80211_get_tx_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_tx_led_name(hw); #else return NULL; #endif } /** * ieee80211_get_rx_led_name - get name of RX LED * * mac80211 creates a receive LED trigger for each wireless hardware * that can be used to drive LEDs if your driver registers a LED device. * This function returns the name (or %NULL if not configured for LEDs) * of the trigger so you can automatically link the LED device. * * @hw: the hardware to get the LED trigger name for * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ static inline const char *ieee80211_get_rx_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_rx_led_name(hw); #else return NULL; #endif } /** * ieee80211_get_assoc_led_name - get name of association LED * * mac80211 creates a association LED trigger for each wireless hardware * that can be used to drive LEDs if your driver registers a LED device. * This function returns the name (or %NULL if not configured for LEDs) * of the trigger so you can automatically link the LED device. * * @hw: the hardware to get the LED trigger name for * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ static inline const char *ieee80211_get_assoc_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_assoc_led_name(hw); #else return NULL; #endif } /** * ieee80211_get_radio_led_name - get name of radio LED * * mac80211 creates a radio change LED trigger for each wireless hardware * that can be used to drive LEDs if your driver registers a LED device. * This function returns the name (or %NULL if not configured for LEDs) * of the trigger so you can automatically link the LED device. * * @hw: the hardware to get the LED trigger name for * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ static inline const char *ieee80211_get_radio_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_radio_led_name(hw); #else return NULL; #endif } /** * ieee80211_create_tpt_led_trigger - create throughput LED trigger * @hw: the hardware to create the trigger for * @flags: trigger flags, see &enum ieee80211_tpt_led_trigger_flags * @blink_table: the blink table -- needs to be ordered by throughput * @blink_table_len: size of the blink table * * Return: %NULL (in case of error, or if no LED triggers are * configured) or the name of the new trigger. * * Note: This function must be called before ieee80211_register_hw(). */ static inline const char * ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, unsigned int flags, const struct ieee80211_tpt_blink *blink_table, unsigned int blink_table_len) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_create_tpt_led_trigger(hw, flags, blink_table, blink_table_len); #else return NULL; #endif } /** * ieee80211_unregister_hw - Unregister a hardware device * * This function instructs mac80211 to free allocated resources * and unregister netdevices from the networking subsystem. * * @hw: the hardware to unregister */ void ieee80211_unregister_hw(struct ieee80211_hw *hw); /** * ieee80211_free_hw - free hardware descriptor * * This function frees everything that was allocated, including the * private data for the driver. You must call ieee80211_unregister_hw() * before calling this function. * * @hw: the hardware to free */ void ieee80211_free_hw(struct ieee80211_hw *hw); /** * ieee80211_restart_hw - restart hardware completely * * Call this function when the hardware was restarted for some reason * (hardware error, ...) and the driver is unable to restore its state * by itself. mac80211 assumes that at this point the driver/hardware * is completely uninitialised and stopped, it starts the process by * calling the ->start() operation. The driver will need to reset all * internal state that it has prior to calling this function. * * @hw: the hardware to restart */ void ieee80211_restart_hw(struct ieee80211_hw *hw); /** * ieee80211_rx_list - receive frame and store processed skbs in a list * * Use this function to hand received frames to mac80211. The receive * buffer in @skb must start with an IEEE 802.11 header. In case of a * paged @skb is used, the driver is recommended to put the ieee80211 * header of the frame on the linear part of the @skb to avoid memory * allocation and/or memcpy by the stack. * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls to * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be * mixed for a single hardware. Must not run concurrently with * ieee80211_tx_status_skb() or ieee80211_tx_status_ni(). * * This function must be called with BHs disabled and RCU read lock * * @hw: the hardware this frame came in on * @sta: the station the frame was received from, or %NULL * @skb: the buffer to receive, owned by mac80211 after this call * @list: the destination list */ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct sk_buff *skb, struct list_head *list); /** * ieee80211_rx_napi - receive frame from NAPI context * * Use this function to hand received frames to mac80211. The receive * buffer in @skb must start with an IEEE 802.11 header. In case of a * paged @skb is used, the driver is recommended to put the ieee80211 * header of the frame on the linear part of the @skb to avoid memory * allocation and/or memcpy by the stack. * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls to * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be * mixed for a single hardware. Must not run concurrently with * ieee80211_tx_status_skb() or ieee80211_tx_status_ni(). * * This function must be called with BHs disabled. * * @hw: the hardware this frame came in on * @sta: the station the frame was received from, or %NULL * @skb: the buffer to receive, owned by mac80211 after this call * @napi: the NAPI context */ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct sk_buff *skb, struct napi_struct *napi); /** * ieee80211_rx - receive frame * * Use this function to hand received frames to mac80211. The receive * buffer in @skb must start with an IEEE 802.11 header. In case of a * paged @skb is used, the driver is recommended to put the ieee80211 * header of the frame on the linear part of the @skb to avoid memory * allocation and/or memcpy by the stack. * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls to * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be * mixed for a single hardware. Must not run concurrently with * ieee80211_tx_status_skb() or ieee80211_tx_status_ni(). * * In process context use instead ieee80211_rx_ni(). * * @hw: the hardware this frame came in on * @skb: the buffer to receive, owned by mac80211 after this call */ static inline void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) { ieee80211_rx_napi(hw, NULL, skb, NULL); } /** * ieee80211_rx_irqsafe - receive frame * * Like ieee80211_rx() but can be called in IRQ context * (internally defers to a tasklet.) * * Calls to this function, ieee80211_rx() or ieee80211_rx_ni() may not * be mixed for a single hardware.Must not run concurrently with * ieee80211_tx_status_skb() or ieee80211_tx_status_ni(). * * @hw: the hardware this frame came in on * @skb: the buffer to receive, owned by mac80211 after this call */ void ieee80211_rx_irqsafe(struct ieee80211_hw *hw, struct sk_buff *skb); /** * ieee80211_rx_ni - receive frame (in process context) * * Like ieee80211_rx() but can be called in process context * (internally disables bottom halves). * * Calls to this function, ieee80211_rx() and ieee80211_rx_irqsafe() may * not be mixed for a single hardware. Must not run concurrently with * ieee80211_tx_status_skb() or ieee80211_tx_status_ni(). * * @hw: the hardware this frame came in on * @skb: the buffer to receive, owned by mac80211 after this call */ static inline void ieee80211_rx_ni(struct ieee80211_hw *hw, struct sk_buff *skb) { local_bh_disable(); ieee80211_rx(hw, skb); local_bh_enable(); } /** * ieee80211_sta_ps_transition - PS transition for connected sta * * When operating in AP mode with the %IEEE80211_HW_AP_LINK_PS * flag set, use this function to inform mac80211 about a connected station * entering/leaving PS mode. * * This function may not be called in IRQ context or with softirqs enabled. * * Calls to this function for a single hardware must be synchronized against * each other. * * @sta: currently connected sta * @start: start or stop PS * * Return: 0 on success. -EINVAL when the requested PS mode is already set. */ int ieee80211_sta_ps_transition(struct ieee80211_sta *sta, bool start); /** * ieee80211_sta_ps_transition_ni - PS transition for connected sta * (in process context) * * Like ieee80211_sta_ps_transition() but can be called in process context * (internally disables bottom halves). Concurrent call restriction still * applies. * * @sta: currently connected sta * @start: start or stop PS * * Return: Like ieee80211_sta_ps_transition(). */ static inline int ieee80211_sta_ps_transition_ni(struct ieee80211_sta *sta, bool start) { int ret; local_bh_disable(); ret = ieee80211_sta_ps_transition(sta, start); local_bh_enable(); return ret; } /** * ieee80211_sta_pspoll - PS-Poll frame received * @sta: currently connected station * * When operating in AP mode with the %IEEE80211_HW_AP_LINK_PS flag set, * use this function to inform mac80211 that a PS-Poll frame from a * connected station was received. * This must be used in conjunction with ieee80211_sta_ps_transition() * and possibly ieee80211_sta_uapsd_trigger(); calls to all three must * be serialized. */ void ieee80211_sta_pspoll(struct ieee80211_sta *sta); /** * ieee80211_sta_uapsd_trigger - (potential) U-APSD trigger frame received * @sta: currently connected station * @tid: TID of the received (potential) trigger frame * * When operating in AP mode with the %IEEE80211_HW_AP_LINK_PS flag set, * use this function to inform mac80211 that a (potential) trigger frame * from a connected station was received. * This must be used in conjunction with ieee80211_sta_ps_transition() * and possibly ieee80211_sta_pspoll(); calls to all three must be * serialized. * %IEEE80211_NUM_TIDS can be passed as the tid if the tid is unknown. * In this case, mac80211 will not check that this tid maps to an AC * that is trigger enabled and assume that the caller did the proper * checks. */ void ieee80211_sta_uapsd_trigger(struct ieee80211_sta *sta, u8 tid); /* * The TX headroom reserved by mac80211 for its own tx_status functions. * This is enough for the radiotap header. */ #define IEEE80211_TX_STATUS_HEADROOM ALIGN(14, 4) /** * ieee80211_sta_set_buffered - inform mac80211 about driver-buffered frames * @sta: &struct ieee80211_sta pointer for the sleeping station * @tid: the TID that has buffered frames * @buffered: indicates whether or not frames are buffered for this TID * * If a driver buffers frames for a powersave station instead of passing * them back to mac80211 for retransmission, the station may still need * to be told that there are buffered frames via the TIM bit. * * This function informs mac80211 whether or not there are frames that are * buffered in the driver for a given TID; mac80211 can then use this data * to set the TIM bit (NOTE: This may call back into the driver's set_tim * call! Beware of the locking!) * * If all frames are released to the station (due to PS-poll or uAPSD) * then the driver needs to inform mac80211 that there no longer are * frames buffered. However, when the station wakes up mac80211 assumes * that all buffered frames will be transmitted and clears this data, * drivers need to make sure they inform mac80211 about all buffered * frames on the sleep transition (sta_notify() with %STA_NOTIFY_SLEEP). * * Note that technically mac80211 only needs to know this per AC, not per * TID, but since driver buffering will inevitably happen per TID (since * it is related to aggregation) it is easier to make mac80211 map the * TID to the AC as required instead of keeping track in all drivers that * use this API. */ void ieee80211_sta_set_buffered(struct ieee80211_sta *sta, u8 tid, bool buffered); /** * ieee80211_get_tx_rates - get the selected transmit rates for a packet * * Call this function in a driver with per-packet rate selection support * to combine the rate info in the packet tx info with the most recent * rate selection table for the station entry. * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @sta: the receiver station to which this packet is sent. * @skb: the frame to be transmitted. * @dest: buffer for extracted rate/retry information * @max_rates: maximum number of rates to fetch */ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct sk_buff *skb, struct ieee80211_tx_rate *dest, int max_rates); /** * ieee80211_sta_set_expected_throughput - set the expected tpt for a station * * Call this function to notify mac80211 about a change in expected throughput * to a station. A driver for a device that does rate control in firmware can * call this function when the expected throughput estimate towards a station * changes. The information is used to tune the CoDel AQM applied to traffic * going towards that station (which can otherwise be too aggressive and cause * slow stations to starve). * * @pubsta: the station to set throughput for. * @thr: the current expected throughput in kbps. */ void ieee80211_sta_set_expected_throughput(struct ieee80211_sta *pubsta, u32 thr); /** * ieee80211_tx_rate_update - transmit rate update callback * * Drivers should call this functions with a non-NULL pub sta * This function can be used in drivers that does not have provision * in updating the tx rate in data path. * * @hw: the hardware the frame was transmitted by * @pubsta: the station to update the tx rate for. * @info: tx status information */ void ieee8 |