1 // SPDX-License-Identifier: GPL-2.0 2 /* 3 * KCSAN core runtime. 4 * 5 * Copyright (C) 2019, Google LLC. 6 */ 7 8 #define pr_fmt(fmt) "kcsan: " fmt 9 10 #include <linux/atomic.h> 11 #include <linux/bug.h> 12 #include <linux/delay.h> 13 #include <linux/export.h> 14 #include <linux/init.h> 15 #include <linux/kernel.h> 16 #include <linux/list.h> 17 #include <linux/minmax.h> 18 #include <linux/moduleparam.h> 19 #include <linux/percpu.h> 20 #include <linux/preempt.h> 21 #include <linux/sched.h> 22 #include <linux/string.h> 23 #include <linux/uaccess.h> 24 25 #include "encoding.h" 26 #include "kcsan.h" 27 #include "permissive.h" 28 29 static bool kcsan_early_enable = IS_ENABLED(CONFIG_KCSAN_EARLY_ENABLE); 30 unsigned int kcsan_udelay_task = CONFIG_KCSAN_UDELAY_TASK; 31 unsigned int kcsan_udelay_interrupt = CONFIG_KCSAN_UDELAY_INTERRUPT; 32 static long kcsan_skip_watch = CONFIG_KCSAN_SKIP_WATCH; 33 static bool kcsan_interrupt_watcher = IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER); 34 35 #ifdef MODULE_PARAM_PREFIX 36 #undef MODULE_PARAM_PREFIX 37 #endif 38 #define MODULE_PARAM_PREFIX "kcsan." 39 module_param_named(early_enable, kcsan_early_enable, bool, 0); 40 module_param_named(udelay_task, kcsan_udelay_task, uint, 0644); 41 module_param_named(udelay_interrupt, kcsan_udelay_interrupt, uint, 0644); 42 module_param_named(skip_watch, kcsan_skip_watch, long, 0644); 43 module_param_named(interrupt_watcher, kcsan_interrupt_watcher, bool, 0444); 44 45 #ifdef CONFIG_KCSAN_WEAK_MEMORY 46 static bool kcsan_weak_memory = true; 47 module_param_named(weak_memory, kcsan_weak_memory, bool, 0644); 48 #else 49 #define kcsan_weak_memory false 50 #endif 51 52 bool kcsan_enabled; 53 54 /* Per-CPU kcsan_ctx for interrupts */ 55 static DEFINE_PER_CPU(struct kcsan_ctx, kcsan_cpu_ctx) = { 56 .scoped_accesses = {LIST_POISON1, NULL}, 57 }; 58 59 /* 60 * Helper macros to index into adjacent slots, starting from address slot 61 * itself, followed by the right and left slots. 62 * 63 * The purpose is 2-fold: 64 * 65 * 1. if during insertion the address slot is already occupied, check if 66 * any adjacent slots are free; 67 * 2. accesses that straddle a slot boundary due to size that exceeds a 68 * slot's range may check adjacent slots if any watchpoint matches. 69 * 70 * Note that accesses with very large size may still miss a watchpoint; however, 71 * given this should be rare, this is a reasonable trade-off to make, since this 72 * will avoid: 73 * 74 * 1. excessive contention between watchpoint checks and setup; 75 * 2. larger number of simultaneous watchpoints without sacrificing 76 * performance. 77 * 78 * Example: SLOT_IDX values for KCSAN_CHECK_ADJACENT=1, where i is [0, 1, 2]: 79 * 80 * slot=0: [ 1, 2, 0] 81 * slot=9: [10, 11, 9] 82 * slot=63: [64, 65, 63] 83 */ 84 #define SLOT_IDX(slot, i) (slot + ((i + KCSAN_CHECK_ADJACENT) % NUM_SLOTS)) 85 86 /* 87 * SLOT_IDX_FAST is used in the fast-path. Not first checking the address's primary 88 * slot (middle) is fine if we assume that races occur rarely. The set of 89 * indices {SLOT_IDX(slot, i) | i in [0, NUM_SLOTS)} is equivalent to 90 * {SLOT_IDX_FAST(slot, i) | i in [0, NUM_SLOTS)}. 91 */ 92 #define SLOT_IDX_FAST(slot, i) (slot + i) 93 94 /* 95 * Watchpoints, with each entry encoded as defined in encoding.h: in order to be 96 * able to safely update and access a watchpoint without introducing locking 97 * overhead, we encode each watchpoint as a single atomic long. The initial 98 * zero-initialized state matches INVALID_WATCHPOINT. 99 * 100 * Add NUM_SLOTS-1 entries to account for overflow; this helps avoid having to 101 * use more complicated SLOT_IDX_FAST calculation with modulo in the fast-path. 102 */ 103 static atomic_long_t watchpoints[CONFIG_KCSAN_NUM_WATCHPOINTS + NUM_SLOTS-1]; 104 105 /* 106 * Instructions to skip watching counter, used in should_watch(). We use a 107 * per-CPU counter to avoid excessive contention. 108 */ 109 static DEFINE_PER_CPU(long, kcsan_skip); 110 111 /* For kcsan_prandom_u32_max(). */ 112 static DEFINE_PER_CPU(u32, kcsan_rand_state); 113 114 static __always_inline atomic_long_t *find_watchpoint(unsigned long addr, 115 size_t size, 116 bool expect_write, 117 long *encoded_watchpoint) 118 { 119 const int slot = watchpoint_slot(addr); 120 const unsigned long addr_masked = addr & WATCHPOINT_ADDR_MASK; 121 atomic_long_t *watchpoint; 122 unsigned long wp_addr_masked; 123 size_t wp_size; 124 bool is_write; 125 int i; 126 127 BUILD_BUG_ON(CONFIG_KCSAN_NUM_WATCHPOINTS < NUM_SLOTS); 128 129 for (i = 0; i < NUM_SLOTS; ++i) { 130 watchpoint = &watchpoints[SLOT_IDX_FAST(slot, i)]; 131 *encoded_watchpoint = atomic_long_read(watchpoint); 132 if (!decode_watchpoint(*encoded_watchpoint, &wp_addr_masked, 133 &wp_size, &is_write)) 134 continue; 135 136 if (expect_write && !is_write) 137 continue; 138 139 /* Check if the watchpoint matches the access. */ 140 if (matching_access(wp_addr_masked, wp_size, addr_masked, size)) 141 return watchpoint; 142 } 143 144 return NULL; 145 } 146 147 static inline atomic_long_t * 148 insert_watchpoint(unsigned long addr, size_t size, bool is_write) 149 { 150 const int slot = watchpoint_slot(addr); 151 const long encoded_watchpoint = encode_watchpoint(addr, size, is_write); 152 atomic_long_t *watchpoint; 153 int i; 154 155 /* Check slot index logic, ensuring we stay within array bounds. */ 156 BUILD_BUG_ON(SLOT_IDX(0, 0) != KCSAN_CHECK_ADJACENT); 157 BUILD_BUG_ON(SLOT_IDX(0, KCSAN_CHECK_ADJACENT+1) != 0); 158 BUILD_BUG_ON(SLOT_IDX(CONFIG_KCSAN_NUM_WATCHPOINTS-1, KCSAN_CHECK_ADJACENT) != ARRAY_SIZE(watchpoints)-1); 159 BUILD_BUG_ON(SLOT_IDX(CONFIG_KCSAN_NUM_WATCHPOINTS-1, KCSAN_CHECK_ADJACENT+1) != ARRAY_SIZE(watchpoints) - NUM_SLOTS); 160 161 for (i = 0; i < NUM_SLOTS; ++i) { 162 long expect_val = INVALID_WATCHPOINT; 163 164 /* Try to acquire this slot. */ 165 watchpoint = &watchpoints[SLOT_IDX(slot, i)]; 166 if (atomic_long_try_cmpxchg_relaxed(watchpoint, &expect_val, encoded_watchpoint)) 167 return watchpoint; 168 } 169 170 return NULL; 171 } 172 173 /* 174 * Return true if watchpoint was successfully consumed, false otherwise. 175 * 176 * This may return false if: 177 * 178 * 1. another thread already consumed the watchpoint; 179 * 2. the thread that set up the watchpoint already removed it; 180 * 3. the watchpoint was removed and then re-used. 181 */ 182 static __always_inline bool 183 try_consume_watchpoint(atomic_long_t *watchpoint, long encoded_watchpoint) 184 { 185 return atomic_long_try_cmpxchg_relaxed(watchpoint, &encoded_watchpoint, CONSUMED_WATCHPOINT); 186 } 187 188 /* Return true if watchpoint was not touched, false if already consumed. */ 189 static inline bool consume_watchpoint(atomic_long_t *watchpoint) 190 { 191 return atomic_long_xchg_relaxed(watchpoint, CONSUMED_WATCHPOINT) != CONSUMED_WATCHPOINT; 192 } 193 194 /* Remove the watchpoint -- its slot may be reused after. */ 195 static inline void remove_watchpoint(atomic_long_t *watchpoint) 196 { 197 atomic_long_set(watchpoint, INVALID_WATCHPOINT); 198 } 199 200 static __always_inline struct kcsan_ctx *get_ctx(void) 201 { 202 /* 203 * In interrupts, use raw_cpu_ptr to avoid unnecessary checks, that would 204 * also result in calls that generate warnings in uaccess regions. 205 */ 206 return in_task() ? ¤t->kcsan_ctx : raw_cpu_ptr(&kcsan_cpu_ctx); 207 } 208 209 static __always_inline void 210 check_access(const volatile void *ptr, size_t size, int type, unsigned long ip); 211 212 /* Check scoped accesses; never inline because this is a slow-path! */ 213 static noinline void kcsan_check_scoped_accesses(void) 214 { 215 struct kcsan_ctx *ctx = get_ctx(); 216 struct kcsan_scoped_access *scoped_access; 217 218 if (ctx->disable_scoped) 219 return; 220 221 ctx->disable_scoped++; 222 list_for_each_entry(scoped_access, &ctx->scoped_accesses, list) { 223 check_access(scoped_access->ptr, scoped_access->size, 224 scoped_access->type, scoped_access->ip); 225 } 226 ctx->disable_scoped--; 227 } 228 229 /* Rules for generic atomic accesses. Called from fast-path. */ 230 static __always_inline bool 231 is_atomic(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, int type) 232 { 233 if (type & KCSAN_ACCESS_ATOMIC) 234 return true; 235 236 /* 237 * Unless explicitly declared atomic, never consider an assertion access 238 * as atomic. This allows using them also in atomic regions, such as 239 * seqlocks, without implicitly changing their semantics. 240 */ 241 if (type & KCSAN_ACCESS_ASSERT) 242 return false; 243 244 if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC) && 245 (type & KCSAN_ACCESS_WRITE) && size <= sizeof(long) && 246 !(type & KCSAN_ACCESS_COMPOUND) && IS_ALIGNED((unsigned long)ptr, size)) 247 return true; /* Assume aligned writes up to word size are atomic. */ 248 249 if (ctx->atomic_next > 0) { 250 /* 251 * Because we do not have separate contexts for nested 252 * interrupts, in case atomic_next is set, we simply assume that 253 * the outer interrupt set atomic_next. In the worst case, we 254 * will conservatively consider operations as atomic. This is a 255 * reasonable trade-off to make, since this case should be 256 * extremely rare; however, even if extremely rare, it could 257 * lead to false positives otherwise. 258 */ 259 if ((hardirq_count() >> HARDIRQ_SHIFT) < 2) 260 --ctx->atomic_next; /* in task, or outer interrupt */ 261 return true; 262 } 263 264 return ctx->atomic_nest_count > 0 || ctx->in_flat_atomic; 265 } 266 267 static __always_inline bool 268 should_watch(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, int type) 269 { 270 /* 271 * Never set up watchpoints when memory operations are atomic. 272 * 273 * Need to check this first, before kcsan_skip check below: (1) atomics 274 * should not count towards skipped instructions, and (2) to actually 275 * decrement kcsan_atomic_next for consecutive instruction stream. 276 */ 277 if (is_atomic(ctx, ptr, size, type)) 278 return false; 279 280 if (this_cpu_dec_return(kcsan_skip) >= 0) 281 return false; 282 283 /* 284 * NOTE: If we get here, kcsan_skip must always be reset in slow path 285 * via reset_kcsan_skip() to avoid underflow. 286 */ 287 288 /* this operation should be watched */ 289 return true; 290 } 291 292 /* 293 * Returns a pseudo-random number in interval [0, ep_ro), or 0 if ep_ro is 0, 294 * which the runtime-tunable callers may pass. Simple linear congruential 295 * generator, using constants from "Numerical Recipes". 296 */ 297 static u32 kcsan_prandom_u32_max(u32 ep_ro) 298 { 299 u32 state = this_cpu_read(kcsan_rand_state); 300 301 state = 1664525 * state + 1013904223; 302 this_cpu_write(kcsan_rand_state, state); 303 304 return reciprocal_scale(state, ep_ro); 305 } 306 307 static inline void reset_kcsan_skip(void) 308 { 309 long skip_count = kcsan_skip_watch - 310 (IS_ENABLED(CONFIG_KCSAN_SKIP_WATCH_RANDOMIZE) ? 311 kcsan_prandom_u32_max(kcsan_skip_watch) : 312 0); 313 this_cpu_write(kcsan_skip, skip_count); 314 } 315 316 static __always_inline bool kcsan_is_enabled(struct kcsan_ctx *ctx) 317 { 318 return READ_ONCE(kcsan_enabled) && !ctx->disable_count; 319 } 320 321 /* Introduce delay depending on context and configuration. */ 322 static void delay_access(int type) 323 { 324 unsigned int delay = in_task() ? kcsan_udelay_task : kcsan_udelay_interrupt; 325 /* For certain access types, skew the random delay to be longer. */ 326 unsigned int skew_delay_order = 327 (type & (KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_ASSERT)) ? 1 : 0; 328 329 delay -= IS_ENABLED(CONFIG_KCSAN_DELAY_RANDOMIZE) ? 330 kcsan_prandom_u32_max(delay >> skew_delay_order) : 331 0; 332 udelay(delay); 333 } 334 335 /* 336 * Reads the instrumented memory for value change detection; value change 337 * detection is currently done for accesses up to a size of 8 bytes. 338 */ 339 static __always_inline u64 read_instrumented_memory(const volatile void *ptr, size_t size) 340 { 341 /* 342 * In the below we don't necessarily need the read of the location to 343 * be atomic, and we don't use READ_ONCE(), since all we need for race 344 * detection is to observe 2 different values. 345 * 346 * Furthermore, on certain architectures (such as arm64), READ_ONCE() 347 * may turn into more complex instructions than a plain load that cannot 348 * do unaligned accesses. 349 */ 350 switch (size) { 351 case 1: return *(const volatile u8 *)ptr; 352 case 2: return *(const volatile u16 *)ptr; 353 case 4: return *(const volatile u32 *)ptr; 354 case 8: return *(const volatile u64 *)ptr; 355 default: return 0; /* Ignore; we do not diff the values. */ 356 } 357 } 358 359 void kcsan_save_irqtrace(struct task_struct *task) 360 { 361 #ifdef CONFIG_TRACE_IRQFLAGS 362 task->kcsan_save_irqtrace = task->irqtrace; 363 #endif 364 } 365 366 void kcsan_restore_irqtrace(struct task_struct *task) 367 { 368 #ifdef CONFIG_TRACE_IRQFLAGS 369 task->irqtrace = task->kcsan_save_irqtrace; 370 #endif 371 } 372 373 static __always_inline int get_kcsan_stack_depth(void) 374 { 375 #ifdef CONFIG_KCSAN_WEAK_MEMORY 376 return current->kcsan_stack_depth; 377 #else 378 BUILD_BUG(); 379 return 0; 380 #endif 381 } 382 383 static __always_inline void add_kcsan_stack_depth(int val) 384 { 385 #ifdef CONFIG_KCSAN_WEAK_MEMORY 386 current->kcsan_stack_depth += val; 387 #else 388 BUILD_BUG(); 389 #endif 390 } 391 392 static __always_inline struct kcsan_scoped_access *get_reorder_access(struct kcsan_ctx *ctx) 393 { 394 #ifdef CONFIG_KCSAN_WEAK_MEMORY 395 return ctx->disable_scoped ? NULL : &ctx->reorder_access; 396 #else 397 return NULL; 398 #endif 399 } 400 401 static __always_inline bool 402 find_reorder_access(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, 403 int type, unsigned long ip) 404 { 405 struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx); 406 407 if (!reorder_access) 408 return false; 409 410 /* 411 * Note: If accesses are repeated while reorder_access is identical, 412 * never matches the new access, because !(type & KCSAN_ACCESS_SCOPED). 413 */ 414 return reorder_access->ptr == ptr && reorder_access->size == size && 415 reorder_access->type == type && reorder_access->ip == ip; 416 } 417 418 static inline void 419 set_reorder_access(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, 420 int type, unsigned long ip) 421 { 422 struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx); 423 424 if (!reorder_access || !kcsan_weak_memory) 425 return; 426 427 /* 428 * To avoid nested interrupts or scheduler (which share kcsan_ctx) 429 * reading an inconsistent reorder_access, ensure that the below has 430 * exclusive access to reorder_access by disallowing concurrent use. 431 */ 432 ctx->disable_scoped++; 433 barrier(); 434 reorder_access->ptr = ptr; 435 reorder_access->size = size; 436 reorder_access->type = type | KCSAN_ACCESS_SCOPED; 437 reorder_access->ip = ip; 438 reorder_access->stack_depth = get_kcsan_stack_depth(); 439 barrier(); 440 ctx->disable_scoped--; 441 } 442 443 /* 444 * Pull everything together: check_access() below contains the performance 445 * critical operations; the fast-path (including check_access) functions should 446 * all be inlinable by the instrumentation functions. 447 * 448 * The slow-path (kcsan_found_watchpoint, kcsan_setup_watchpoint) are 449 * non-inlinable -- note that, we prefix these with "kcsan_" to ensure they can 450 * be filtered from the stacktrace, as well as give them unique names for the 451 * UACCESS whitelist of objtool. Each function uses user_access_save/restore(), 452 * since they do not access any user memory, but instrumentation is still 453 * emitted in UACCESS regions. 454 */ 455 456 static noinline void kcsan_found_watchpoint(const volatile void *ptr, 457 size_t size, 458 int type, 459 unsigned long ip, 460 atomic_long_t *watchpoint, 461 long encoded_watchpoint) 462 { 463 const bool is_assert = (type & KCSAN_ACCESS_ASSERT) != 0; 464 struct kcsan_ctx *ctx = get_ctx(); 465 unsigned long flags; 466 bool consumed; 467 468 /* 469 * We know a watchpoint exists. Let's try to keep the race-window 470 * between here and finally consuming the watchpoint below as small as 471 * possible -- avoid unneccessarily complex code until consumed. 472 */ 473 474 if (!kcsan_is_enabled(ctx)) 475 return; 476 477 /* 478 * The access_mask check relies on value-change comparison. To avoid 479 * reporting a race where e.g. the writer set up the watchpoint, but the 480 * reader has access_mask!=0, we have to ignore the found watchpoint. 481 * 482 * reorder_access is never created from an access with access_mask set. 483 */ 484 if (ctx->access_mask && !find_reorder_access(ctx, ptr, size, type, ip)) 485 return; 486 487 /* 488 * If the other thread does not want to ignore the access, and there was 489 * a value change as a result of this thread's operation, we will still 490 * generate a report of unknown origin. 491 * 492 * Use CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN=n to filter. 493 */ 494 if (!is_assert && kcsan_ignore_address(ptr)) 495 return; 496 497 /* 498 * Consuming the watchpoint must be guarded by kcsan_is_enabled() to 499 * avoid erroneously triggering reports if the context is disabled. 500 */ 501 consumed = try_consume_watchpoint(watchpoint, encoded_watchpoint); 502 503 /* keep this after try_consume_watchpoint */ 504 flags = user_access_save(); 505 506 if (consumed) { 507 kcsan_save_irqtrace(current); 508 kcsan_report_set_info(ptr, size, type, ip, watchpoint - watchpoints); 509 kcsan_restore_irqtrace(current); 510 } else { 511 /* 512 * The other thread may not print any diagnostics, as it has 513 * already removed the watchpoint, or another thread consumed 514 * the watchpoint before this thread. 515 */ 516 atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_REPORT_RACES]); 517 } 518 519 if (is_assert) 520 atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]); 521 else 522 atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_DATA_RACES]); 523 524 user_access_restore(flags); 525 } 526 527 static noinline void 528 kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned long ip) 529 { 530 const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0; 531 const bool is_assert = (type & KCSAN_ACCESS_ASSERT) != 0; 532 atomic_long_t *watchpoint; 533 u64 old, new, diff; 534 enum kcsan_value_change value_change = KCSAN_VALUE_CHANGE_MAYBE; 535 bool interrupt_watcher = kcsan_interrupt_watcher; 536 unsigned long ua_flags = user_access_save(); 537 struct kcsan_ctx *ctx = get_ctx(); 538 unsigned long access_mask = ctx->access_mask; 539 unsigned long irq_flags = 0; 540 bool is_reorder_access; 541 542 /* 543 * Always reset kcsan_skip counter in slow-path to avoid underflow; see 544 * should_watch(). 545 */ 546 reset_kcsan_skip(); 547 548 if (!kcsan_is_enabled(ctx)) 549 goto out; 550 551 /* 552 * Check to-ignore addresses after kcsan_is_enabled(), as we may access 553 * memory that is not yet initialized during early boot. 554 */ 555 if (!is_assert && kcsan_ignore_address(ptr)) 556 goto out; 557 558 if (!check_encodable((unsigned long)ptr, size)) { 559 atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_UNENCODABLE_ACCESSES]); 560 goto out; 561 } 562 563 /* 564 * The local CPU cannot observe reordering of its own accesses, and 565 * therefore we need to take care of 2 cases to avoid false positives: 566 * 567 * 1. Races of the reordered access with interrupts. To avoid, if 568 * the current access is reorder_access, disable interrupts. 569 * 2. Avoid races of scoped accesses from nested interrupts (below). 570 */ 571 is_reorder_access = find_reorder_access(ctx, ptr, size, type, ip); 572 if (is_reorder_access) 573 interrupt_watcher = false; 574 /* 575 * Avoid races of scoped accesses from nested interrupts (or scheduler). 576 * Assume setting up a watchpoint for a non-scoped (normal) access that 577 * also conflicts with a current scoped access. In a nested interrupt, 578 * which shares the context, it would check a conflicting scoped access. 579 * To avoid, disable scoped access checking. 580 */ 581 ctx->disable_scoped++; 582 583 /* 584 * Save and restore the IRQ state trace touched by KCSAN, since KCSAN's 585 * runtime is entered for every memory access, and potentially useful 586 * information is lost if dirtied by KCSAN. 587 */ 588 kcsan_save_irqtrace(current); 589 if (!interrupt_watcher) { 590 local_irq_save(irq_flags); 591 /* 592 * NMIs can still fire, disable checking for all interrupt 593 * contexts. 594 */ 595 raw_cpu_ptr(&kcsan_cpu_ctx)->disable_count++; 596 } 597 598 watchpoint = insert_watchpoint((unsigned long)ptr, size, is_write); 599 if (watchpoint == NULL) { 600 /* 601 * Out of capacity: the size of 'watchpoints', and the frequency 602 * with which should_watch() returns true should be tweaked so 603 * that this case happens very rarely. 604 */ 605 atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_NO_CAPACITY]); 606 goto out_unlock; 607 } 608 609 atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_SETUP_WATCHPOINTS]); 610 atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_USED_WATCHPOINTS]); 611 612 /* 613 * Read the current value, to later check and infer a race if the data 614 * was modified via a non-instrumented access, e.g. from a device. 615 */ 616 old = is_reorder_access ? 0 : read_instrumented_memory(ptr, size); 617 618 /* 619 * Delay this thread, to increase probability of observing a racy 620 * conflicting access. 621 */ 622 delay_access(type); 623 624 /* 625 * Re-read value, and check if it is as expected; if not, we infer a 626 * racy access. 627 */ 628 if (!is_reorder_access) { 629 new = read_instrumented_memory(ptr, size); 630 } else { 631 /* 632 * Reordered accesses cannot be used for value change detection, 633 * because the memory location may no longer be accessible and 634 * could result in a fault. 635 */ 636 new = 0; 637 access_mask = 0; 638 } 639 640 diff = old ^ new; 641 if (access_mask) 642 diff &= access_mask; 643 644 /* 645 * Check if we observed a value change. 646 * 647 * Also check if the data race should be ignored (the rules depend on 648 * non-zero diff); if it is to be ignored, the below rules for 649 * KCSAN_VALUE_CHANGE_MAYBE apply. 650 */ 651 if (diff && !kcsan_ignore_data_race(size, type, old, new, diff)) 652 value_change = KCSAN_VALUE_CHANGE_TRUE; 653 654 /* Check if this access raced with another. */ 655 if (!consume_watchpoint(watchpoint)) { 656 /* 657 * Depending on the access type, map a value_change of MAYBE to 658 * TRUE (always report) or FALSE (never report). 659 */ 660 if (value_change == KCSAN_VALUE_CHANGE_MAYBE) { 661 if (access_mask != 0) { 662 /* 663 * For access with access_mask, we require a 664 * value-change, as it is likely that races on 665 * ~access_mask bits are expected. 666 */ 667 value_change = KCSAN_VALUE_CHANGE_FALSE; 668 } else if (size > 8 || is_assert) { 669 /* Always assume a value-change. */ 670 value_change = KCSAN_VALUE_CHANGE_TRUE; 671 } 672 } 673 674 /* 675 * No need to increment 'data_races' counter, as the racing 676 * thread already did. 677 * 678 * Count 'assert_failures' for each failed ASSERT access, 679 * therefore both this thread and the racing thread may 680 * increment this counter. 681 */ 682 if (is_assert && value_change == KCSAN_VALUE_CHANGE_TRUE) 683 atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]); 684 685 kcsan_report_known_origin(ptr, size, type, ip, 686 value_change, watchpoint - watchpoints, 687 old, new, access_mask); 688 } else if (value_change == KCSAN_VALUE_CHANGE_TRUE) { 689 /* Inferring a race, since the value should not have changed. */ 690 691 atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN]); 692 if (is_assert) 693 atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]); 694 695 if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN) || is_assert) { 696 kcsan_report_unknown_origin(ptr, size, type, ip, 697 old, new, access_mask); 698 } 699 } 700 701 /* 702 * Remove watchpoint; must be after reporting, since the slot may be 703 * reused after this point. 704 */ 705 remove_watchpoint(watchpoint); 706 atomic_long_dec(&kcsan_counters[KCSAN_COUNTER_USED_WATCHPOINTS]); 707 708 out_unlock: 709 if (!interrupt_watcher) { 710 raw_cpu_ptr(&kcsan_cpu_ctx)->disable_count--; 711 local_irq_restore(irq_flags); 712 } 713 kcsan_restore_irqtrace(current); 714 ctx->disable_scoped--; 715 716 /* 717 * Reordered accesses cannot be used for value change detection, 718 * therefore never consider for reordering if access_mask is set. 719 * ASSERT_EXCLUSIVE are not real accesses, ignore them as well. 720 */ 721 if (!access_mask && !is_assert) 722 set_reorder_access(ctx, ptr, size, type, ip); 723 out: 724 user_access_restore(ua_flags); 725 } 726 727 static __always_inline void 728 check_access(const volatile void *ptr, size_t size, int type, unsigned long ip) 729 { 730 atomic_long_t *watchpoint; 731 long encoded_watchpoint; 732 733 /* 734 * Do nothing for 0 sized check; this comparison will be optimized out 735 * for constant sized instrumentation (__tsan_{read,write}N). 736 */ 737 if (unlikely(size == 0)) 738 return; 739 740 again: 741 /* 742 * Avoid user_access_save in fast-path: find_watchpoint is safe without 743 * user_access_save, as the address that ptr points to is only used to 744 * check if a watchpoint exists; ptr is never dereferenced. 745 */ 746 watchpoint = find_watchpoint((unsigned long)ptr, size, 747 !(type & KCSAN_ACCESS_WRITE), 748 &encoded_watchpoint); 749 /* 750 * It is safe to check kcsan_is_enabled() after find_watchpoint in the 751 * slow-path, as long as no state changes that cause a race to be 752 * detected and reported have occurred until kcsan_is_enabled() is 753 * checked. 754 */ 755 756 if (unlikely(watchpoint != NULL)) 757 kcsan_found_watchpoint(ptr, size, type, ip, watchpoint, encoded_watchpoint); 758 else { 759 struct kcsan_ctx *ctx = get_ctx(); /* Call only once in fast-path. */ 760 761 if (unlikely(should_watch(ctx, ptr, size, type))) { 762 kcsan_setup_watchpoint(ptr, size, type, ip); 763 return; 764 } 765 766 if (!(type & KCSAN_ACCESS_SCOPED)) { 767 struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx); 768 769 if (reorder_access) { 770 /* 771 * reorder_access check: simulates reordering of 772 * the access after subsequent operations. 773 */ 774 ptr = reorder_access->ptr; 775 type = reorder_access->type; 776 ip = reorder_access->ip; 777 /* 778 * Upon a nested interrupt, this context's 779 * reorder_access can be modified (shared ctx). 780 * We know that upon return, reorder_access is 781 * always invalidated by setting size to 0 via 782 * __tsan_func_exit(). Therefore we must read 783 * and check size after the other fields. 784 */ 785 barrier(); 786 size = READ_ONCE(reorder_access->size); 787 if (size) 788 goto again; 789 } 790 } 791 792 /* 793 * Always checked last, right before returning from runtime; 794 * if reorder_access is valid, checked after it was checked. 795 */ 796 if (unlikely(ctx->scoped_accesses.prev)) 797 kcsan_check_scoped_accesses(); 798 } 799 } 800 801 /* === Public interface ===================================================== */ 802 803 void __init kcsan_init(void) 804 { 805 int cpu; 806 807 BUG_ON(!in_task()); 808 809 for_each_possible_cpu(cpu) 810 per_cpu(kcsan_rand_state, cpu) = (u32)get_cycles(); 811 812 /* 813 * We are in the init task, and no other tasks should be running; 814 * WRITE_ONCE without memory barrier is sufficient. 815 */ 816 if (kcsan_early_enable) { 817 pr_info("enabled early\n"); 818 WRITE_ONCE(kcsan_enabled, true); 819 } 820 821 if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY) || 822 IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC) || 823 IS_ENABLED(CONFIG_KCSAN_PERMISSIVE) || 824 IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { 825 pr_warn("non-strict mode configured - use CONFIG_KCSAN_STRICT=y to see all data races\n"); 826 } else { 827 pr_info("strict mode configured\n"); 828 } 829 } 830 831 /* === Exported interface =================================================== */ 832 833 void kcsan_disable_current(void) 834 { 835 ++get_ctx()->disable_count; 836 } 837 EXPORT_SYMBOL(kcsan_disable_current); 838 839 void kcsan_enable_current(void) 840 { 841 if (get_ctx()->disable_count-- == 0) { 842 /* 843 * Warn if kcsan_enable_current() calls are unbalanced with 844 * kcsan_disable_current() calls, which causes disable_count to 845 * become negative and should not happen. 846 */ 847 kcsan_disable_current(); /* restore to 0, KCSAN still enabled */ 848 kcsan_disable_current(); /* disable to generate warning */ 849 WARN(1, "Unbalanced %s()", __func__); 850 kcsan_enable_current(); 851 } 852 } 853 EXPORT_SYMBOL(kcsan_enable_current); 854 855 void kcsan_enable_current_nowarn(void) 856 { 857 if (get_ctx()->disable_count-- == 0) 858 kcsan_disable_current(); 859 } 860 EXPORT_SYMBOL(kcsan_enable_current_nowarn); 861 862 void kcsan_nestable_atomic_begin(void) 863 { 864 /* 865 * Do *not* check and warn if we are in a flat atomic region: nestable 866 * and flat atomic regions are independent from each other. 867 * See include/linux/kcsan.h: struct kcsan_ctx comments for more 868 * comments. 869 */ 870 871 ++get_ctx()->atomic_nest_count; 872 } 873 EXPORT_SYMBOL(kcsan_nestable_atomic_begin); 874 875 void kcsan_nestable_atomic_end(void) 876 { 877 if (get_ctx()->atomic_nest_count-- == 0) { 878 /* 879 * Warn if kcsan_nestable_atomic_end() calls are unbalanced with 880 * kcsan_nestable_atomic_begin() calls, which causes 881 * atomic_nest_count to become negative and should not happen. 882 */ 883 kcsan_nestable_atomic_begin(); /* restore to 0 */ 884 kcsan_disable_current(); /* disable to generate warning */ 885 WARN(1, "Unbalanced %s()", __func__); 886 kcsan_enable_current(); 887 } 888 } 889 EXPORT_SYMBOL(kcsan_nestable_atomic_end); 890 891 void kcsan_flat_atomic_begin(void) 892 { 893 get_ctx()->in_flat_atomic = true; 894 } 895 EXPORT_SYMBOL(kcsan_flat_atomic_begin); 896 897 void kcsan_flat_atomic_end(void) 898 { 899 get_ctx()->in_flat_atomic = false; 900 } 901 EXPORT_SYMBOL(kcsan_flat_atomic_end); 902 903 void kcsan_atomic_next(int n) 904 { 905 get_ctx()->atomic_next = n; 906 } 907 EXPORT_SYMBOL(kcsan_atomic_next); 908 909 void kcsan_set_access_mask(unsigned long mask) 910 { 911 get_ctx()->access_mask = mask; 912 } 913 EXPORT_SYMBOL(kcsan_set_access_mask); 914 915 struct kcsan_scoped_access * 916 kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type, 917 struct kcsan_scoped_access *sa) 918 { 919 struct kcsan_ctx *ctx = get_ctx(); 920 921 check_access(ptr, size, type, _RET_IP_); 922 923 ctx->disable_count++; /* Disable KCSAN, in case list debugging is on. */ 924 925 INIT_LIST_HEAD(&sa->list); 926 sa->ptr = ptr; 927 sa->size = size; 928 sa->type = type; 929 sa->ip = _RET_IP_; 930 931 if (!ctx->scoped_accesses.prev) /* Lazy initialize list head. */ 932 INIT_LIST_HEAD(&ctx->scoped_accesses); 933 list_add(&sa->list, &ctx->scoped_accesses); 934 935 ctx->disable_count--; 936 return sa; 937 } 938 EXPORT_SYMBOL(kcsan_begin_scoped_access); 939 940 void kcsan_end_scoped_access(struct kcsan_scoped_access *sa) 941 { 942 struct kcsan_ctx *ctx = get_ctx(); 943 944 if (WARN(!ctx->scoped_accesses.prev, "Unbalanced %s()?", __func__)) 945 return; 946 947 ctx->disable_count++; /* Disable KCSAN, in case list debugging is on. */ 948 949 list_del(&sa->list); 950 if (list_empty(&ctx->scoped_accesses)) 951 /* 952 * Ensure we do not enter kcsan_check_scoped_accesses() 953 * slow-path if unnecessary, and avoids requiring list_empty() 954 * in the fast-path (to avoid a READ_ONCE() and potential 955 * uaccess warning). 956 */ 957 ctx->scoped_accesses.prev = NULL; 958 959 ctx->disable_count--; 960 961 check_access(sa->ptr, sa->size, sa->type, sa->ip); 962 } 963 EXPORT_SYMBOL(kcsan_end_scoped_access); 964 965 void __kcsan_check_access(const volatile void *ptr, size_t size, int type) 966 { 967 check_access(ptr, size, type, _RET_IP_); 968 } 969 EXPORT_SYMBOL(__kcsan_check_access); 970 971 #define DEFINE_MEMORY_BARRIER(name, order_before_cond) \ 972 void __kcsan_##name(void) \ 973 { \ 974 struct kcsan_scoped_access *sa = get_reorder_access(get_ctx()); \ 975 if (!sa) \ 976 return; \ 977 if (order_before_cond) \ 978 sa->size = 0; \ 979 } \ 980 EXPORT_SYMBOL(__kcsan_##name) 981 982 DEFINE_MEMORY_BARRIER(mb, true); 983 DEFINE_MEMORY_BARRIER(wmb, sa->type & (KCSAN_ACCESS_WRITE | KCSAN_ACCESS_COMPOUND)); 984 DEFINE_MEMORY_BARRIER(rmb, !(sa->type & KCSAN_ACCESS_WRITE) || (sa->type & KCSAN_ACCESS_COMPOUND)); 985 DEFINE_MEMORY_BARRIER(release, true); 986 987 /* 988 * KCSAN uses the same instrumentation that is emitted by supported compilers 989 * for ThreadSanitizer (TSAN). 990 * 991 * When enabled, the compiler emits instrumentation calls (the functions 992 * prefixed with "__tsan" below) for all loads and stores that it generated; 993 * inline asm is not instrumented. 994 * 995 * Note that, not all supported compiler versions distinguish aligned/unaligned 996 * accesses, but e.g. recent versions of Clang do. We simply alias the unaligned 997 * version to the generic version, which can handle both. 998 */ 999 1000 #define DEFINE_TSAN_READ_WRITE(size) \ 1001 void __tsan_read##size(void *ptr); \ 1002 void __tsan_read##size(void *ptr) \ 1003 { \ 1004 check_access(ptr, size, 0, _RET_IP_); \ 1005 } \ 1006 EXPORT_SYMBOL(__tsan_read##size); \ 1007 void __tsan_unaligned_read##size(void *ptr) \ 1008 __alias(__tsan_read##size); \ 1009 EXPORT_SYMBOL(__tsan_unaligned_read##size); \ 1010 void __tsan_write##size(void *ptr); \ 1011 void __tsan_write##size(void *ptr) \ 1012 { \ 1013 check_access(ptr, size, KCSAN_ACCESS_WRITE, _RET_IP_); \ 1014 } \ 1015 EXPORT_SYMBOL(__tsan_write##size); \ 1016 void __tsan_unaligned_write##size(void *ptr) \ 1017 __alias(__tsan_write##size); \ 1018 EXPORT_SYMBOL(__tsan_unaligned_write##size); \ 1019 void __tsan_read_write##size(void *ptr); \ 1020 void __tsan_read_write##size(void *ptr) \ 1021 { \ 1022 check_access(ptr, size, \ 1023 KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE, \ 1024 _RET_IP_); \ 1025 } \ 1026 EXPORT_SYMBOL(__tsan_read_write##size); \ 1027 void __tsan_unaligned_read_write##size(void *ptr) \ 1028 __alias(__tsan_read_write##size); \ 1029 EXPORT_SYMBOL(__tsan_unaligned_read_write##size) 1030 1031 DEFINE_TSAN_READ_WRITE(1); 1032 DEFINE_TSAN_READ_WRITE(2); 1033 DEFINE_TSAN_READ_WRITE(4); 1034 DEFINE_TSAN_READ_WRITE(8); 1035 DEFINE_TSAN_READ_WRITE(16); 1036 1037 void __tsan_read_range(void *ptr, size_t size); 1038 void __tsan_read_range(void *ptr, size_t size) 1039 { 1040 check_access(ptr, size, 0, _RET_IP_); 1041 } 1042 EXPORT_SYMBOL(__tsan_read_range); 1043 1044 void __tsan_write_range(void *ptr, size_t size); 1045 void __tsan_write_range(void *ptr, size_t size) 1046 { 1047 check_access(ptr, size, KCSAN_ACCESS_WRITE, _RET_IP_); 1048 } 1049 EXPORT_SYMBOL(__tsan_write_range); 1050 1051 /* 1052 * Use of explicit volatile is generally disallowed [1], however, volatile is 1053 * still used in various concurrent context, whether in low-level 1054 * synchronization primitives or for legacy reasons. 1055 * [1] https://lwn.net/Articles/233479/ 1056 * 1057 * We only consider volatile accesses atomic if they are aligned and would pass 1058 * the size-check of compiletime_assert_rwonce_type(). 1059 */ 1060 #define DEFINE_TSAN_VOLATILE_READ_WRITE(size) \ 1061 void __tsan_volatile_read##size(void *ptr); \ 1062 void __tsan_volatile_read##size(void *ptr) \ 1063 { \ 1064 const bool is_atomic = size <= sizeof(long long) && \ 1065 IS_ALIGNED((unsigned long)ptr, size); \ 1066 if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) && is_atomic) \ 1067 return; \ 1068 check_access(ptr, size, is_atomic ? KCSAN_ACCESS_ATOMIC : 0, \ 1069 _RET_IP_); \ 1070 } \ 1071 EXPORT_SYMBOL(__tsan_volatile_read##size); \ 1072 void __tsan_unaligned_volatile_read##size(void *ptr) \ 1073 __alias(__tsan_volatile_read##size); \ 1074 EXPORT_SYMBOL(__tsan_unaligned_volatile_read##size); \ 1075 void __tsan_volatile_write##size(void *ptr); \ 1076 void __tsan_volatile_write##size(void *ptr) \ 1077 { \ 1078 const bool is_atomic = size <= sizeof(long long) && \ 1079 IS_ALIGNED((unsigned long)ptr, size); \ 1080 if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) && is_atomic) \ 1081 return; \ 1082 check_access(ptr, size, \ 1083 KCSAN_ACCESS_WRITE | \ 1084 (is_atomic ? KCSAN_ACCESS_ATOMIC : 0), \ 1085 _RET_IP_); \ 1086 } \ 1087 EXPORT_SYMBOL(__tsan_volatile_write##size); \ 1088 void __tsan_unaligned_volatile_write##size(void *ptr) \ 1089 __alias(__tsan_volatile_write##size); \ 1090 EXPORT_SYMBOL(__tsan_unaligned_volatile_write##size) 1091 1092 DEFINE_TSAN_VOLATILE_READ_WRITE(1); 1093 DEFINE_TSAN_VOLATILE_READ_WRITE(2); 1094 DEFINE_TSAN_VOLATILE_READ_WRITE(4); 1095 DEFINE_TSAN_VOLATILE_READ_WRITE(8); 1096 DEFINE_TSAN_VOLATILE_READ_WRITE(16); 1097 1098 /* 1099 * Function entry and exit are used to determine the validty of reorder_access. 1100 * Reordering of the access ends at the end of the function scope where the 1101 * access happened. This is done for two reasons: 1102 * 1103 * 1. Artificially limits the scope where missing barriers are detected. 1104 * This minimizes false positives due to uninstrumented functions that 1105 * contain the required barriers but were missed. 1106 * 1107 * 2. Simplifies generating the stack trace of the access. 1108 */ 1109 void __tsan_func_entry(void *call_pc); 1110 noinline void __tsan_func_entry(void *call_pc) 1111 { 1112 if (!IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY)) 1113 return; 1114 1115 add_kcsan_stack_depth(1); 1116 } 1117 EXPORT_SYMBOL(__tsan_func_entry); 1118 1119 void __tsan_func_exit(void); 1120 noinline void __tsan_func_exit(void) 1121 { 1122 struct kcsan_scoped_access *reorder_access; 1123 1124 if (!IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY)) 1125 return; 1126 1127 reorder_access = get_reorder_access(get_ctx()); 1128 if (!reorder_access) 1129 goto out; 1130 1131 if (get_kcsan_stack_depth() <= reorder_access->stack_depth) { 1132 /* 1133 * Access check to catch cases where write without a barrier 1134 * (supposed release) was last access in function: because 1135 * instrumentation is inserted before the real access, a data 1136 * race due to the write giving up a c-s would only be caught if 1137 * we do the conflicting access after. 1138 */ 1139 check_access(reorder_access->ptr, reorder_access->size, 1140 reorder_access->type, reorder_access->ip); 1141 reorder_access->size = 0; 1142 reorder_access->stack_depth = INT_MIN; 1143 } 1144 out: 1145 add_kcsan_stack_depth(-1); 1146 } 1147 EXPORT_SYMBOL(__tsan_func_exit); 1148 1149 void __tsan_init(void); 1150 void __tsan_init(void) 1151 { 1152 } 1153 EXPORT_SYMBOL(__tsan_init); 1154 1155 /* 1156 * Instrumentation for atomic builtins (__atomic_*, __sync_*). 1157 * 1158 * Normal kernel code _should not_ be using them directly, but some 1159 * architectures may implement some or all atomics using the compilers' 1160 * builtins. 1161 * 1162 * Note: If an architecture decides to fully implement atomics using the 1163 * builtins, because they are implicitly instrumented by KCSAN (and KASAN, 1164 * etc.), implementing the ARCH_ATOMIC interface (to get instrumentation via 1165 * atomic-instrumented) is no longer necessary. 1166 * 1167 * TSAN instrumentation replaces atomic accesses with calls to any of the below 1168 * functions, whose job is to also execute the operation itself. 1169 */ 1170 1171 static __always_inline void kcsan_atomic_builtin_memorder(int memorder) 1172 { 1173 if (memorder == __ATOMIC_RELEASE || 1174 memorder == __ATOMIC_SEQ_CST || 1175 memorder == __ATOMIC_ACQ_REL) 1176 __kcsan_release(); 1177 } 1178 1179 #define DEFINE_TSAN_ATOMIC_LOAD_STORE(bits) \ 1180 u##bits __tsan_atomic##bits##_load(const u##bits *ptr, int memorder); \ 1181 u##bits __tsan_atomic##bits##_load(const u##bits *ptr, int memorder) \ 1182 { \ 1183 kcsan_atomic_builtin_memorder(memorder); \ 1184 if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ 1185 check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_ATOMIC, _RET_IP_); \ 1186 } \ 1187 return __atomic_load_n(ptr, memorder); \ 1188 } \ 1189 EXPORT_SYMBOL(__tsan_atomic##bits##_load); \ 1190 void __tsan_atomic##bits##_store(u##bits *ptr, u##bits v, int memorder); \ 1191 void __tsan_atomic##bits##_store(u##bits *ptr, u##bits v, int memorder) \ 1192 { \ 1193 kcsan_atomic_builtin_memorder(memorder); \ 1194 if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ 1195 check_access(ptr, bits / BITS_PER_BYTE, \ 1196 KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC, _RET_IP_); \ 1197 } \ 1198 __atomic_store_n(ptr, v, memorder); \ 1199 } \ 1200 EXPORT_SYMBOL(__tsan_atomic##bits##_store) 1201 1202 #define DEFINE_TSAN_ATOMIC_RMW(op, bits, suffix) \ 1203 u##bits __tsan_atomic##bits##_##op(u##bits *ptr, u##bits v, int memorder); \ 1204 u##bits __tsan_atomic##bits##_##op(u##bits *ptr, u##bits v, int memorder) \ 1205 { \ 1206 kcsan_atomic_builtin_memorder(memorder); \ 1207 if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ 1208 check_access(ptr, bits / BITS_PER_BYTE, \ 1209 KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ 1210 KCSAN_ACCESS_ATOMIC, _RET_IP_); \ 1211 } \ 1212 return __atomic_##op##suffix(ptr, v, memorder); \ 1213 } \ 1214 EXPORT_SYMBOL(__tsan_atomic##bits##_##op) 1215 1216 /* 1217 * Note: CAS operations are always classified as write, even in case they 1218 * fail. We cannot perform check_access() after a write, as it might lead to 1219 * false positives, in cases such as: 1220 * 1221 * T0: __atomic_compare_exchange_n(&p->flag, &old, 1, ...) 1222 * 1223 * T1: if (__atomic_load_n(&p->flag, ...)) { 1224 * modify *p; 1225 * p->flag = 0; 1226 * } 1227 * 1228 * The only downside is that, if there are 3 threads, with one CAS that 1229 * succeeds, another CAS that fails, and an unmarked racing operation, we may 1230 * point at the wrong CAS as the source of the race. However, if we assume that 1231 * all CAS can succeed in some other execution, the data race is still valid. 1232 */ 1233 #define DEFINE_TSAN_ATOMIC_CMPXCHG(bits, strength, weak) \ 1234 int __tsan_atomic##bits##_compare_exchange_##strength(u##bits *ptr, u##bits *exp, \ 1235 u##bits val, int mo, int fail_mo); \ 1236 int __tsan_atomic##bits##_compare_exchange_##strength(u##bits *ptr, u##bits *exp, \ 1237 u##bits val, int mo, int fail_mo) \ 1238 { \ 1239 kcsan_atomic_builtin_memorder(mo); \ 1240 if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ 1241 check_access(ptr, bits / BITS_PER_BYTE, \ 1242 KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ 1243 KCSAN_ACCESS_ATOMIC, _RET_IP_); \ 1244 } \ 1245 return __atomic_compare_exchange_n(ptr, exp, val, weak, mo, fail_mo); \ 1246 } \ 1247 EXPORT_SYMBOL(__tsan_atomic##bits##_compare_exchange_##strength) 1248 1249 #define DEFINE_TSAN_ATOMIC_CMPXCHG_VAL(bits) \ 1250 u##bits __tsan_atomic##bits##_compare_exchange_val(u##bits *ptr, u##bits exp, u##bits val, \ 1251 int mo, int fail_mo); \ 1252 u##bits __tsan_atomic##bits##_compare_exchange_val(u##bits *ptr, u##bits exp, u##bits val, \ 1253 int mo, int fail_mo) \ 1254 { \ 1255 kcsan_atomic_builtin_memorder(mo); \ 1256 if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ 1257 check_access(ptr, bits / BITS_PER_BYTE, \ 1258 KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ 1259 KCSAN_ACCESS_ATOMIC, _RET_IP_); \ 1260 } \ 1261 __atomic_compare_exchange_n(ptr, &exp, val, 0, mo, fail_mo); \ 1262 return exp; \ 1263 } \ 1264 EXPORT_SYMBOL(__tsan_atomic##bits##_compare_exchange_val) 1265 1266 #define DEFINE_TSAN_ATOMIC_OPS(bits) \ 1267 DEFINE_TSAN_ATOMIC_LOAD_STORE(bits); \ 1268 DEFINE_TSAN_ATOMIC_RMW(exchange, bits, _n); \ 1269 DEFINE_TSAN_ATOMIC_RMW(fetch_add, bits, ); \ 1270 DEFINE_TSAN_ATOMIC_RMW(fetch_sub, bits, ); \ 1271 DEFINE_TSAN_ATOMIC_RMW(fetch_and, bits, ); \ 1272 DEFINE_TSAN_ATOMIC_RMW(fetch_or, bits, ); \ 1273 DEFINE_TSAN_ATOMIC_RMW(fetch_xor, bits, ); \ 1274 DEFINE_TSAN_ATOMIC_RMW(fetch_nand, bits, ); \ 1275 DEFINE_TSAN_ATOMIC_CMPXCHG(bits, strong, 0); \ 1276 DEFINE_TSAN_ATOMIC_CMPXCHG(bits, weak, 1); \ 1277 DEFINE_TSAN_ATOMIC_CMPXCHG_VAL(bits) 1278 1279 DEFINE_TSAN_ATOMIC_OPS(8); 1280 DEFINE_TSAN_ATOMIC_OPS(16); 1281 DEFINE_TSAN_ATOMIC_OPS(32); 1282 #ifdef CONFIG_64BIT 1283 DEFINE_TSAN_ATOMIC_OPS(64); 1284 #endif 1285 1286 void __tsan_atomic_thread_fence(int memorder); 1287 void __tsan_atomic_thread_fence(int memorder) 1288 { 1289 kcsan_atomic_builtin_memorder(memorder); 1290 __atomic_thread_fence(memorder); 1291 } 1292 EXPORT_SYMBOL(__tsan_atomic_thread_fence); 1293 1294 /* 1295 * In instrumented files, we emit instrumentation for barriers by mapping the 1296 * kernel barriers to an __atomic_signal_fence(), which is interpreted specially 1297 * and otherwise has no relation to a real __atomic_signal_fence(). No known 1298 * kernel code uses __atomic_signal_fence(). 1299 * 1300 * Since fsanitize=thread instrumentation handles __atomic_signal_fence(), which 1301 * are turned into calls to __tsan_atomic_signal_fence(), such instrumentation 1302 * can be disabled via the __no_kcsan function attribute (vs. an explicit call 1303 * which could not). When __no_kcsan is requested, __atomic_signal_fence() 1304 * generates no code. 1305 * 1306 * Note: The result of using __atomic_signal_fence() with KCSAN enabled is 1307 * potentially limiting the compiler's ability to reorder operations; however, 1308 * if barriers were instrumented with explicit calls (without LTO), the compiler 1309 * couldn't optimize much anyway. The result of a hypothetical architecture 1310 * using __atomic_signal_fence() in normal code would be KCSAN false negatives. 1311 */ 1312 void __tsan_atomic_signal_fence(int memorder); 1313 noinline void __tsan_atomic_signal_fence(int memorder) 1314 { 1315 switch (memorder) { 1316 case __KCSAN_BARRIER_TO_SIGNAL_FENCE_mb: 1317 __kcsan_mb(); 1318 break; 1319 case __KCSAN_BARRIER_TO_SIGNAL_FENCE_wmb: 1320 __kcsan_wmb(); 1321 break; 1322 case __KCSAN_BARRIER_TO_SIGNAL_FENCE_rmb: 1323 __kcsan_rmb(); 1324 break; 1325 case __KCSAN_BARRIER_TO_SIGNAL_FENCE_release: 1326 __kcsan_release(); 1327 break; 1328 default: 1329 break; 1330 } 1331 } 1332 EXPORT_SYMBOL(__tsan_atomic_signal_fence); 1333 1334 #ifdef __HAVE_ARCH_MEMSET 1335 void *__tsan_memset(void *s, int c, size_t count); 1336 noinline void *__tsan_memset(void *s, int c, size_t count) 1337 { 1338 /* 1339 * Instead of not setting up watchpoints where accessed size is greater 1340 * than MAX_ENCODABLE_SIZE, truncate checked size to MAX_ENCODABLE_SIZE. 1341 */ 1342 size_t check_len = min_t(size_t, count, MAX_ENCODABLE_SIZE); 1343 1344 check_access(s, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); 1345 return memset(s, c, count); 1346 } 1347 #else 1348 void *__tsan_memset(void *s, int c, size_t count) __alias(memset); 1349 #endif 1350 EXPORT_SYMBOL(__tsan_memset); 1351 1352 #ifdef __HAVE_ARCH_MEMMOVE 1353 void *__tsan_memmove(void *dst, const void *src, size_t len); 1354 noinline void *__tsan_memmove(void *dst, const void *src, size_t len) 1355 { 1356 size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); 1357 1358 check_access(dst, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); 1359 check_access(src, check_len, 0, _RET_IP_); 1360 return memmove(dst, src, len); 1361 } 1362 #else 1363 void *__tsan_memmove(void *dst, const void *src, size_t len) __alias(memmove); 1364 #endif 1365 EXPORT_SYMBOL(__tsan_memmove); 1366 1367 #ifdef __HAVE_ARCH_MEMCPY 1368 void *__tsan_memcpy(void *dst, const void *src, size_t len); 1369 noinline void *__tsan_memcpy(void *dst, const void *src, size_t len) 1370 { 1371 size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); 1372 1373 check_access(dst, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); 1374 check_access(src, check_len, 0, _RET_IP_); 1375 return memcpy(dst, src, len); 1376 } 1377 #else 1378 void *__tsan_memcpy(void *dst, const void *src, size_t len) __alias(memcpy); 1379 #endif 1380 EXPORT_SYMBOL(__tsan_memcpy); 1381