diff options
Diffstat (limited to 'kernel/kcsan')
| -rw-r--r-- | kernel/kcsan/.kunitconfig | 24 | ||||
| -rw-r--r-- | kernel/kcsan/Makefile | 21 | ||||
| -rw-r--r-- | kernel/kcsan/core.c | 1371 | ||||
| -rw-r--r-- | kernel/kcsan/debugfs.c | 275 | ||||
| -rw-r--r-- | kernel/kcsan/encoding.h | 102 | ||||
| -rw-r--r-- | kernel/kcsan/kcsan.h | 142 | ||||
| -rw-r--r-- | kernel/kcsan/kcsan_test.c | 1618 | ||||
| -rw-r--r-- | kernel/kcsan/permissive.h | 94 | ||||
| -rw-r--r-- | kernel/kcsan/report.c | 715 | ||||
| -rw-r--r-- | kernel/kcsan/selftest.c | 272 |
10 files changed, 4634 insertions, 0 deletions
diff --git a/kernel/kcsan/.kunitconfig b/kernel/kcsan/.kunitconfig new file mode 100644 index 000000000..e82f0f52a --- /dev/null +++ b/kernel/kcsan/.kunitconfig @@ -0,0 +1,24 @@ +# Note that the KCSAN tests need to run on an SMP setup. +# Under kunit_tool, this can be done by using the --qemu_args +# option to configure a machine with several cores. For example: +# ./tools/testing/kunit/kunit.py run --kunitconfig=kernel/kcsan \ +# --arch=x86_64 --qemu_args="-smp 8" + +CONFIG_KUNIT=y + +CONFIG_DEBUG_KERNEL=y + +# Need some level of concurrency to test a concurrency sanitizer. +CONFIG_SMP=y + +CONFIG_KCSAN=y +CONFIG_KCSAN_KUNIT_TEST=y + +# Set these if you want to run test_barrier_nothreads +#CONFIG_KCSAN_STRICT=y +#CONFIG_KCSAN_WEAK_MEMORY=y + +# This prevents the test from timing out on many setups. Feel free to remove +# (or alter) this, in conjunction with setting a different test timeout with, +# for example, the --timeout kunit_tool option. +CONFIG_KCSAN_REPORT_ONCE_IN_MS=100 diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile new file mode 100644 index 000000000..a45f3dfc8 --- /dev/null +++ b/kernel/kcsan/Makefile @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: GPL-2.0 +KCSAN_SANITIZE := n +KCOV_INSTRUMENT := n +UBSAN_SANITIZE := n + +CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_debugfs.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE) + +CFLAGS_core.o := $(call cc-option,-fno-conserve-stack) \ + $(call cc-option,-mno-outline-atomics) \ + -fno-stack-protector -DDISABLE_BRANCH_PROFILING + +obj-y := core.o debugfs.o report.o + +KCSAN_INSTRUMENT_BARRIERS_selftest.o := y +obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o + +CFLAGS_kcsan_test.o := $(CFLAGS_KCSAN) -fno-omit-frame-pointer +CFLAGS_kcsan_test.o += $(DISABLE_STRUCTLEAK_PLUGIN) +obj-$(CONFIG_KCSAN_KUNIT_TEST) += kcsan_test.o diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c new file mode 100644 index 000000000..8a7baf4e3 --- /dev/null +++ b/kernel/kcsan/core.c @@ -0,0 +1,1371 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KCSAN core runtime. + * + * Copyright (C) 2019, Google LLC. + */ + +#define pr_fmt(fmt) "kcsan: " fmt + +#include <linux/atomic.h> +#include <linux/bug.h> +#include <linux/delay.h> +#include <linux/export.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/minmax.h> +#include <linux/moduleparam.h> +#include <linux/percpu.h> +#include <linux/preempt.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/uaccess.h> + +#include "encoding.h" +#include "kcsan.h" +#include "permissive.h" + +static bool kcsan_early_enable = IS_ENABLED(CONFIG_KCSAN_EARLY_ENABLE); +unsigned int kcsan_udelay_task = CONFIG_KCSAN_UDELAY_TASK; +unsigned int kcsan_udelay_interrupt = CONFIG_KCSAN_UDELAY_INTERRUPT; +static long kcsan_skip_watch = CONFIG_KCSAN_SKIP_WATCH; +static bool kcsan_interrupt_watcher = IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER); + +#ifdef MODULE_PARAM_PREFIX +#undef MODULE_PARAM_PREFIX +#endif +#define MODULE_PARAM_PREFIX "kcsan." +module_param_named(early_enable, kcsan_early_enable, bool, 0); +module_param_named(udelay_task, kcsan_udelay_task, uint, 0644); +module_param_named(udelay_interrupt, kcsan_udelay_interrupt, uint, 0644); +module_param_named(skip_watch, kcsan_skip_watch, long, 0644); +module_param_named(interrupt_watcher, kcsan_interrupt_watcher, bool, 0444); + +#ifdef CONFIG_KCSAN_WEAK_MEMORY +static bool kcsan_weak_memory = true; +module_param_named(weak_memory, kcsan_weak_memory, bool, 0644); +#else +#define kcsan_weak_memory false +#endif + +bool kcsan_enabled; + +/* Per-CPU kcsan_ctx for interrupts */ +static DEFINE_PER_CPU(struct kcsan_ctx, kcsan_cpu_ctx) = { + .scoped_accesses = {LIST_POISON1, NULL}, +}; + +/* + * Helper macros to index into adjacent slots, starting from address slot + * itself, followed by the right and left slots. + * + * The purpose is 2-fold: + * + * 1. if during insertion the address slot is already occupied, check if + * any adjacent slots are free; + * 2. accesses that straddle a slot boundary due to size that exceeds a + * slot's range may check adjacent slots if any watchpoint matches. + * + * Note that accesses with very large size may still miss a watchpoint; however, + * given this should be rare, this is a reasonable trade-off to make, since this + * will avoid: + * + * 1. excessive contention between watchpoint checks and setup; + * 2. larger number of simultaneous watchpoints without sacrificing + * performance. + * + * Example: SLOT_IDX values for KCSAN_CHECK_ADJACENT=1, where i is [0, 1, 2]: + * + * slot=0: [ 1, 2, 0] + * slot=9: [10, 11, 9] + * slot=63: [64, 65, 63] + */ +#define SLOT_IDX(slot, i) (slot + ((i + KCSAN_CHECK_ADJACENT) % NUM_SLOTS)) + +/* + * SLOT_IDX_FAST is used in the fast-path. Not first checking the address's primary + * slot (middle) is fine if we assume that races occur rarely. The set of + * indices {SLOT_IDX(slot, i) | i in [0, NUM_SLOTS)} is equivalent to + * {SLOT_IDX_FAST(slot, i) | i in [0, NUM_SLOTS)}. + */ +#define SLOT_IDX_FAST(slot, i) (slot + i) + +/* + * Watchpoints, with each entry encoded as defined in encoding.h: in order to be + * able to safely update and access a watchpoint without introducing locking + * overhead, we encode each watchpoint as a single atomic long. The initial + * zero-initialized state matches INVALID_WATCHPOINT. + * + * Add NUM_SLOTS-1 entries to account for overflow; this helps avoid having to + * use more complicated SLOT_IDX_FAST calculation with modulo in the fast-path. + */ +static atomic_long_t watchpoints[CONFIG_KCSAN_NUM_WATCHPOINTS + NUM_SLOTS-1]; + +/* + * Instructions to skip watching counter, used in should_watch(). We use a + * per-CPU counter to avoid excessive contention. + */ +static DEFINE_PER_CPU(long, kcsan_skip); + +/* For kcsan_prandom_u32_max(). */ +static DEFINE_PER_CPU(u32, kcsan_rand_state); + +static __always_inline atomic_long_t *find_watchpoint(unsigned long addr, + size_t size, + bool expect_write, + long *encoded_watchpoint) +{ + const int slot = watchpoint_slot(addr); + const unsigned long addr_masked = addr & WATCHPOINT_ADDR_MASK; + atomic_long_t *watchpoint; + unsigned long wp_addr_masked; + size_t wp_size; + bool is_write; + int i; + + BUILD_BUG_ON(CONFIG_KCSAN_NUM_WATCHPOINTS < NUM_SLOTS); + + for (i = 0; i < NUM_SLOTS; ++i) { + watchpoint = &watchpoints[SLOT_IDX_FAST(slot, i)]; + *encoded_watchpoint = atomic_long_read(watchpoint); + if (!decode_watchpoint(*encoded_watchpoint, &wp_addr_masked, + &wp_size, &is_write)) + continue; + + if (expect_write && !is_write) + continue; + + /* Check if the watchpoint matches the access. */ + if (matching_access(wp_addr_masked, wp_size, addr_masked, size)) + return watchpoint; + } + + return NULL; +} + +static inline atomic_long_t * +insert_watchpoint(unsigned long addr, size_t size, bool is_write) +{ + const int slot = watchpoint_slot(addr); + const long encoded_watchpoint = encode_watchpoint(addr, size, is_write); + atomic_long_t *watchpoint; + int i; + + /* Check slot index logic, ensuring we stay within array bounds. */ + BUILD_BUG_ON(SLOT_IDX(0, 0) != KCSAN_CHECK_ADJACENT); + BUILD_BUG_ON(SLOT_IDX(0, KCSAN_CHECK_ADJACENT+1) != 0); + BUILD_BUG_ON(SLOT_IDX(CONFIG_KCSAN_NUM_WATCHPOINTS-1, KCSAN_CHECK_ADJACENT) != ARRAY_SIZE(watchpoints)-1); + BUILD_BUG_ON(SLOT_IDX(CONFIG_KCSAN_NUM_WATCHPOINTS-1, KCSAN_CHECK_ADJACENT+1) != ARRAY_SIZE(watchpoints) - NUM_SLOTS); + + for (i = 0; i < NUM_SLOTS; ++i) { + long expect_val = INVALID_WATCHPOINT; + + /* Try to acquire this slot. */ + watchpoint = &watchpoints[SLOT_IDX(slot, i)]; + if (atomic_long_try_cmpxchg_relaxed(watchpoint, &expect_val, encoded_watchpoint)) + return watchpoint; + } + + return NULL; +} + +/* + * Return true if watchpoint was successfully consumed, false otherwise. + * + * This may return false if: + * + * 1. another thread already consumed the watchpoint; + * 2. the thread that set up the watchpoint already removed it; + * 3. the watchpoint was removed and then re-used. + */ +static __always_inline bool +try_consume_watchpoint(atomic_long_t *watchpoint, long encoded_watchpoint) +{ + return atomic_long_try_cmpxchg_relaxed(watchpoint, &encoded_watchpoint, CONSUMED_WATCHPOINT); +} + +/* Return true if watchpoint was not touched, false if already consumed. */ +static inline bool consume_watchpoint(atomic_long_t *watchpoint) +{ + return atomic_long_xchg_relaxed(watchpoint, CONSUMED_WATCHPOINT) != CONSUMED_WATCHPOINT; +} + +/* Remove the watchpoint -- its slot may be reused after. */ +static inline void remove_watchpoint(atomic_long_t *watchpoint) +{ + atomic_long_set(watchpoint, INVALID_WATCHPOINT); +} + +static __always_inline struct kcsan_ctx *get_ctx(void) +{ + /* + * In interrupts, use raw_cpu_ptr to avoid unnecessary checks, that would + * also result in calls that generate warnings in uaccess regions. + */ + return in_task() ? ¤t->kcsan_ctx : raw_cpu_ptr(&kcsan_cpu_ctx); +} + +static __always_inline void +check_access(const volatile void *ptr, size_t size, int type, unsigned long ip); + +/* Check scoped accesses; never inline because this is a slow-path! */ +static noinline void kcsan_check_scoped_accesses(void) +{ + struct kcsan_ctx *ctx = get_ctx(); + struct kcsan_scoped_access *scoped_access; + + if (ctx->disable_scoped) + return; + + ctx->disable_scoped++; + list_for_each_entry(scoped_access, &ctx->scoped_accesses, list) { + check_access(scoped_access->ptr, scoped_access->size, + scoped_access->type, scoped_access->ip); + } + ctx->disable_scoped--; +} + +/* Rules for generic atomic accesses. Called from fast-path. */ +static __always_inline bool +is_atomic(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, int type) +{ + if (type & KCSAN_ACCESS_ATOMIC) + return true; + + /* + * Unless explicitly declared atomic, never consider an assertion access + * as atomic. This allows using them also in atomic regions, such as + * seqlocks, without implicitly changing their semantics. + */ + if (type & KCSAN_ACCESS_ASSERT) + return false; + + if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC) && + (type & KCSAN_ACCESS_WRITE) && size <= sizeof(long) && + !(type & KCSAN_ACCESS_COMPOUND) && IS_ALIGNED((unsigned long)ptr, size)) + return true; /* Assume aligned writes up to word size are atomic. */ + + if (ctx->atomic_next > 0) { + /* + * Because we do not have separate contexts for nested + * interrupts, in case atomic_next is set, we simply assume that + * the outer interrupt set atomic_next. In the worst case, we + * will conservatively consider operations as atomic. This is a + * reasonable trade-off to make, since this case should be + * extremely rare; however, even if extremely rare, it could + * lead to false positives otherwise. + */ + if ((hardirq_count() >> HARDIRQ_SHIFT) < 2) + --ctx->atomic_next; /* in task, or outer interrupt */ + return true; + } + + return ctx->atomic_nest_count > 0 || ctx->in_flat_atomic; +} + +static __always_inline bool +should_watch(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, int type) +{ + /* + * Never set up watchpoints when memory operations are atomic. + * + * Need to check this first, before kcsan_skip check below: (1) atomics + * should not count towards skipped instructions, and (2) to actually + * decrement kcsan_atomic_next for consecutive instruction stream. + */ + if (is_atomic(ctx, ptr, size, type)) + return false; + + if (this_cpu_dec_return(kcsan_skip) >= 0) + return false; + + /* + * NOTE: If we get here, kcsan_skip must always be reset in slow path + * via reset_kcsan_skip() to avoid underflow. + */ + + /* this operation should be watched */ + return true; +} + +/* + * Returns a pseudo-random number in interval [0, ep_ro). Simple linear + * congruential generator, using constants from "Numerical Recipes". + */ +static u32 kcsan_prandom_u32_max(u32 ep_ro) +{ + u32 state = this_cpu_read(kcsan_rand_state); + + state = 1664525 * state + 1013904223; + this_cpu_write(kcsan_rand_state, state); + + return state % ep_ro; +} + +static inline void reset_kcsan_skip(void) +{ + long skip_count = kcsan_skip_watch - + (IS_ENABLED(CONFIG_KCSAN_SKIP_WATCH_RANDOMIZE) ? + kcsan_prandom_u32_max(kcsan_skip_watch) : + 0); + this_cpu_write(kcsan_skip, skip_count); +} + +static __always_inline bool kcsan_is_enabled(struct kcsan_ctx *ctx) +{ + return READ_ONCE(kcsan_enabled) && !ctx->disable_count; +} + +/* Introduce delay depending on context and configuration. */ +static void delay_access(int type) +{ + unsigned int delay = in_task() ? kcsan_udelay_task : kcsan_udelay_interrupt; + /* For certain access types, skew the random delay to be longer. */ + unsigned int skew_delay_order = + (type & (KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_ASSERT)) ? 1 : 0; + + delay -= IS_ENABLED(CONFIG_KCSAN_DELAY_RANDOMIZE) ? + kcsan_prandom_u32_max(delay >> skew_delay_order) : + 0; + udelay(delay); +} + +/* + * Reads the instrumented memory for value change detection; value change + * detection is currently done for accesses up to a size of 8 bytes. + */ +static __always_inline u64 read_instrumented_memory(const volatile void *ptr, size_t size) +{ + /* + * In the below we don't necessarily need the read of the location to + * be atomic, and we don't use READ_ONCE(), since all we need for race + * detection is to observe 2 different values. + * + * Furthermore, on certain architectures (such as arm64), READ_ONCE() + * may turn into more complex instructions than a plain load that cannot + * do unaligned accesses. + */ + switch (size) { + case 1: return *(const volatile u8 *)ptr; + case 2: return *(const volatile u16 *)ptr; + case 4: return *(const volatile u32 *)ptr; + case 8: return *(const volatile u64 *)ptr; + default: return 0; /* Ignore; we do not diff the values. */ + } +} + +void kcsan_save_irqtrace(struct task_struct *task) +{ +#ifdef CONFIG_TRACE_IRQFLAGS + task->kcsan_save_irqtrace = task->irqtrace; +#endif +} + +void kcsan_restore_irqtrace(struct task_struct *task) +{ +#ifdef CONFIG_TRACE_IRQFLAGS + task->irqtrace = task->kcsan_save_irqtrace; +#endif +} + +static __always_inline int get_kcsan_stack_depth(void) +{ +#ifdef CONFIG_KCSAN_WEAK_MEMORY + return current->kcsan_stack_depth; +#else + BUILD_BUG(); + return 0; +#endif +} + +static __always_inline void add_kcsan_stack_depth(int val) +{ +#ifdef CONFIG_KCSAN_WEAK_MEMORY + current->kcsan_stack_depth += val; +#else + BUILD_BUG(); +#endif +} + +static __always_inline struct kcsan_scoped_access *get_reorder_access(struct kcsan_ctx *ctx) +{ +#ifdef CONFIG_KCSAN_WEAK_MEMORY + return ctx->disable_scoped ? NULL : &ctx->reorder_access; +#else + return NULL; +#endif +} + +static __always_inline bool +find_reorder_access(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, + int type, unsigned long ip) +{ + struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx); + + if (!reorder_access) + return false; + + /* + * Note: If accesses are repeated while reorder_access is identical, + * never matches the new access, because !(type & KCSAN_ACCESS_SCOPED). + */ + return reorder_access->ptr == ptr && reorder_access->size == size && + reorder_access->type == type && reorder_access->ip == ip; +} + +static inline void +set_reorder_access(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, + int type, unsigned long ip) +{ + struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx); + + if (!reorder_access || !kcsan_weak_memory) + return; + + /* + * To avoid nested interrupts or scheduler (which share kcsan_ctx) + * reading an inconsistent reorder_access, ensure that the below has + * exclusive access to reorder_access by disallowing concurrent use. + */ + ctx->disable_scoped++; + barrier(); + reorder_access->ptr = ptr; + reorder_access->size = size; + reorder_access->type = type | KCSAN_ACCESS_SCOPED; + reorder_access->ip = ip; + reorder_access->stack_depth = get_kcsan_stack_depth(); + barrier(); + ctx->disable_scoped--; +} + +/* + * Pull everything together: check_access() below contains the performance + * critical operations; the fast-path (including check_access) functions should + * all be inlinable by the instrumentation functions. + * + * The slow-path (kcsan_found_watchpoint, kcsan_setup_watchpoint) are + * non-inlinable -- note that, we prefix these with "kcsan_" to ensure they can + * be filtered from the stacktrace, as well as give them unique names for the + * UACCESS whitelist of objtool. Each function uses user_access_save/restore(), + * since they do not access any user memory, but instrumentation is still + * emitted in UACCESS regions. + */ + +static noinline void kcsan_found_watchpoint(const volatile void *ptr, + size_t size, + int type, + unsigned long ip, + atomic_long_t *watchpoint, + long encoded_watchpoint) +{ + const bool is_assert = (type & KCSAN_ACCESS_ASSERT) != 0; + struct kcsan_ctx *ctx = get_ctx(); + unsigned long flags; + bool consumed; + + /* + * We know a watchpoint exists. Let's try to keep the race-window + * between here and finally consuming the watchpoint below as small as + * possible -- avoid unneccessarily complex code until consumed. + */ + + if (!kcsan_is_enabled(ctx)) + return; + + /* + * The access_mask check relies on value-change comparison. To avoid + * reporting a race where e.g. the writer set up the watchpoint, but the + * reader has access_mask!=0, we have to ignore the found watchpoint. + * + * reorder_access is never created from an access with access_mask set. + */ + if (ctx->access_mask && !find_reorder_access(ctx, ptr, size, type, ip)) + return; + + /* + * If the other thread does not want to ignore the access, and there was + * a value change as a result of this thread's operation, we will still + * generate a report of unknown origin. + * + * Use CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN=n to filter. + */ + if (!is_assert && kcsan_ignore_address(ptr)) + return; + + /* + * Consuming the watchpoint must be guarded by kcsan_is_enabled() to + * avoid erroneously triggering reports if the context is disabled. + */ + consumed = try_consume_watchpoint(watchpoint, encoded_watchpoint); + + /* keep this after try_consume_watchpoint */ + flags = user_access_save(); + + if (consumed) { + kcsan_save_irqtrace(current); + kcsan_report_set_info(ptr, size, type, ip, watchpoint - watchpoints); + kcsan_restore_irqtrace(current); + } else { + /* + * The other thread may not print any diagnostics, as it has + * already removed the watchpoint, or another thread consumed + * the watchpoint before this thread. + */ + atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_REPORT_RACES]); + } + + if (is_assert) + atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]); + else + atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_DATA_RACES]); + + user_access_restore(flags); +} + +static noinline void +kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned long ip) +{ + const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0; + const bool is_assert = (type & KCSAN_ACCESS_ASSERT) != 0; + atomic_long_t *watchpoint; + u64 old, new, diff; + enum kcsan_value_change value_change = KCSAN_VALUE_CHANGE_MAYBE; + bool interrupt_watcher = kcsan_interrupt_watcher; + unsigned long ua_flags = user_access_save(); + struct kcsan_ctx *ctx = get_ctx(); + unsigned long access_mask = ctx->access_mask; + unsigned long irq_flags = 0; + bool is_reorder_access; + + /* + * Always reset kcsan_skip counter in slow-path to avoid underflow; see + * should_watch(). + */ + reset_kcsan_skip(); + + if (!kcsan_is_enabled(ctx)) + goto out; + + /* + * Check to-ignore addresses after kcsan_is_enabled(), as we may access + * memory that is not yet initialized during early boot. + */ + if (!is_assert && kcsan_ignore_address(ptr)) + goto out; + + if (!check_encodable((unsigned long)ptr, size)) { + atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_UNENCODABLE_ACCESSES]); + goto out; + } + + /* + * The local CPU cannot observe reordering of its own accesses, and + * therefore we need to take care of 2 cases to avoid false positives: + * + * 1. Races of the reordered access with interrupts. To avoid, if + * the current access is reorder_access, disable interrupts. + * 2. Avoid races of scoped accesses from nested interrupts (below). + */ + is_reorder_access = find_reorder_access(ctx, ptr, size, type, ip); + if (is_reorder_access) + interrupt_watcher = false; + /* + * Avoid races of scoped accesses from nested interrupts (or scheduler). + * Assume setting up a watchpoint for a non-scoped (normal) access that + * also conflicts with a current scoped access. In a nested interrupt, + * which shares the context, it would check a conflicting scoped access. + * To avoid, disable scoped access checking. + */ + ctx->disable_scoped++; + + /* + * Save and restore the IRQ state trace touched by KCSAN, since KCSAN's + * runtime is entered for every memory access, and potentially useful + * information is lost if dirtied by KCSAN. + */ + kcsan_save_irqtrace(current); + if (!interrupt_watcher) + local_irq_save(irq_flags); + + watchpoint = insert_watchpoint((unsigned long)ptr, size, is_write); + if (watchpoint == NULL) { + /* + * Out of capacity: the size of 'watchpoints', and the frequency + * with which should_watch() returns true should be tweaked so + * that this case happens very rarely. + */ + atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_NO_CAPACITY]); + goto out_unlock; + } + + atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_SETUP_WATCHPOINTS]); + atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_USED_WATCHPOINTS]); + + /* + * Read the current value, to later check and infer a race if the data + * was modified via a non-instrumented access, e.g. from a device. + */ + old = is_reorder_access ? 0 : read_instrumented_memory(ptr, size); + + /* + * Delay this thread, to increase probability of observing a racy + * conflicting access. + */ + delay_access(type); + + /* + * Re-read value, and check if it is as expected; if not, we infer a + * racy access. + */ + if (!is_reorder_access) { + new = read_instrumented_memory(ptr, size); + } else { + /* + * Reordered accesses cannot be used for value change detection, + * because the memory location may no longer be accessible and + * could result in a fault. + */ + new = 0; + access_mask = 0; + } + + diff = old ^ new; + if (access_mask) + diff &= access_mask; + + /* + * Check if we observed a value change. + * + * Also check if the data race should be ignored (the rules depend on + * non-zero diff); if it is to be ignored, the below rules for + * KCSAN_VALUE_CHANGE_MAYBE apply. + */ + if (diff && !kcsan_ignore_data_race(size, type, old, new, diff)) + value_change = KCSAN_VALUE_CHANGE_TRUE; + + /* Check if this access raced with another. */ + if (!consume_watchpoint(watchpoint)) { + /* + * Depending on the access type, map a value_change of MAYBE to + * TRUE (always report) or FALSE (never report). + */ + if (value_change == KCSAN_VALUE_CHANGE_MAYBE) { + if (access_mask != 0) { + /* + * For access with access_mask, we require a + * value-change, as it is likely that races on + * ~access_mask bits are expected. + */ + value_change = KCSAN_VALUE_CHANGE_FALSE; + } else if (size > 8 || is_assert) { + /* Always assume a value-change. */ + value_change = KCSAN_VALUE_CHANGE_TRUE; + } + } + + /* + * No need to increment 'data_races' counter, as the racing + * thread already did. + * + * Count 'assert_failures' for each failed ASSERT access, + * therefore both this thread and the racing thread may + * increment this counter. + */ + if (is_assert && value_change == KCSAN_VALUE_CHANGE_TRUE) + atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]); + + kcsan_report_known_origin(ptr, size, type, ip, + value_change, watchpoint - watchpoints, + old, new, access_mask); + } else if (value_change == KCSAN_VALUE_CHANGE_TRUE) { + /* Inferring a race, since the value should not have changed. */ + + atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN]); + if (is_assert) + atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ASSERT_FAILURES]); + + if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN) || is_assert) { + kcsan_report_unknown_origin(ptr, size, type, ip, + old, new, access_mask); + } + } + + /* + * Remove watchpoint; must be after reporting, since the slot may be + * reused after this point. + */ + remove_watchpoint(watchpoint); + atomic_long_dec(&kcsan_counters[KCSAN_COUNTER_USED_WATCHPOINTS]); + +out_unlock: + if (!interrupt_watcher) + local_irq_restore(irq_flags); + kcsan_restore_irqtrace(current); + ctx->disable_scoped--; + + /* + * Reordered accesses cannot be used for value change detection, + * therefore never consider for reordering if access_mask is set. + * ASSERT_EXCLUSIVE are not real accesses, ignore them as well. + */ + if (!access_mask && !is_assert) + set_reorder_access(ctx, ptr, size, type, ip); +out: + user_access_restore(ua_flags); +} + +static __always_inline void +check_access(const volatile void *ptr, size_t size, int type, unsigned long ip) +{ + atomic_long_t *watchpoint; + long encoded_watchpoint; + + /* + * Do nothing for 0 sized check; this comparison will be optimized out + * for constant sized instrumentation (__tsan_{read,write}N). + */ + if (unlikely(size == 0)) + return; + +again: + /* + * Avoid user_access_save in fast-path: find_watchpoint is safe without + * user_access_save, as the address that ptr points to is only used to + * check if a watchpoint exists; ptr is never dereferenced. + */ + watchpoint = find_watchpoint((unsigned long)ptr, size, + !(type & KCSAN_ACCESS_WRITE), + &encoded_watchpoint); + /* + * It is safe to check kcsan_is_enabled() after find_watchpoint in the + * slow-path, as long as no state changes that cause a race to be + * detected and reported have occurred until kcsan_is_enabled() is + * checked. + */ + + if (unlikely(watchpoint != NULL)) + kcsan_found_watchpoint(ptr, size, type, ip, watchpoint, encoded_watchpoint); + else { + struct kcsan_ctx *ctx = get_ctx(); /* Call only once in fast-path. */ + + if (unlikely(should_watch(ctx, ptr, size, type))) { + kcsan_setup_watchpoint(ptr, size, type, ip); + return; + } + + if (!(type & KCSAN_ACCESS_SCOPED)) { + struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx); + + if (reorder_access) { + /* + * reorder_access check: simulates reordering of + * the access after subsequent operations. + */ + ptr = reorder_access->ptr; + type = reorder_access->type; + ip = reorder_access->ip; + /* + * Upon a nested interrupt, this context's + * reorder_access can be modified (shared ctx). + * We know that upon return, reorder_access is + * always invalidated by setting size to 0 via + * __tsan_func_exit(). Therefore we must read + * and check size after the other fields. + */ + barrier(); + size = READ_ONCE(reorder_access->size); + if (size) + goto again; + } + } + + /* + * Always checked last, right before returning from runtime; + * if reorder_access is valid, checked after it was checked. + */ + if (unlikely(ctx->scoped_accesses.prev)) + kcsan_check_scoped_accesses(); + } +} + +/* === Public interface ===================================================== */ + +void __init kcsan_init(void) +{ + int cpu; + + BUG_ON(!in_task()); + + for_each_possible_cpu(cpu) + per_cpu(kcsan_rand_state, cpu) = (u32)get_cycles(); + + /* + * We are in the init task, and no other tasks should be running; + * WRITE_ONCE without memory barrier is sufficient. + */ + if (kcsan_early_enable) { + pr_info("enabled early\n"); + WRITE_ONCE(kcsan_enabled, true); + } + + if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY) || + IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC) || + IS_ENABLED(CONFIG_KCSAN_PERMISSIVE) || + IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { + pr_warn("non-strict mode configured - use CONFIG_KCSAN_STRICT=y to see all data races\n"); + } else { + pr_info("strict mode configured\n"); + } +} + +/* === Exported interface =================================================== */ + +void kcsan_disable_current(void) +{ + ++get_ctx()->disable_count; +} +EXPORT_SYMBOL(kcsan_disable_current); + +void kcsan_enable_current(void) +{ + if (get_ctx()->disable_count-- == 0) { + /* + * Warn if kcsan_enable_current() calls are unbalanced with + * kcsan_disable_current() calls, which causes disable_count to + * become negative and should not happen. + */ + kcsan_disable_current(); /* restore to 0, KCSAN still enabled */ + kcsan_disable_current(); /* disable to generate warning */ + WARN(1, "Unbalanced %s()", __func__); + kcsan_enable_current(); + } +} +EXPORT_SYMBOL(kcsan_enable_current); + +void kcsan_enable_current_nowarn(void) +{ + if (get_ctx()->disable_count-- == 0) + kcsan_disable_current(); +} +EXPORT_SYMBOL(kcsan_enable_current_nowarn); + +void kcsan_nestable_atomic_begin(void) +{ + /* + * Do *not* check and warn if we are in a flat atomic region: nestable + * and flat atomic regions are independent from each other. + * See include/linux/kcsan.h: struct kcsan_ctx comments for more + * comments. + */ + + ++get_ctx()->atomic_nest_count; +} +EXPORT_SYMBOL(kcsan_nestable_atomic_begin); + +void kcsan_nestable_atomic_end(void) +{ + if (get_ctx()->atomic_nest_count-- == 0) { + /* + * Warn if kcsan_nestable_atomic_end() calls are unbalanced with + * kcsan_nestable_atomic_begin() calls, which causes + * atomic_nest_count to become negative and should not happen. + */ + kcsan_nestable_atomic_begin(); /* restore to 0 */ + kcsan_disable_current(); /* disable to generate warning */ + WARN(1, "Unbalanced %s()", __func__); + kcsan_enable_current(); + } +} +EXPORT_SYMBOL(kcsan_nestable_atomic_end); + +void kcsan_flat_atomic_begin(void) +{ + get_ctx()->in_flat_atomic = true; +} +EXPORT_SYMBOL(kcsan_flat_atomic_begin); + +void kcsan_flat_atomic_end(void) +{ + get_ctx()->in_flat_atomic = false; +} +EXPORT_SYMBOL(kcsan_flat_atomic_end); + +void kcsan_atomic_next(int n) +{ + get_ctx()->atomic_next = n; +} +EXPORT_SYMBOL(kcsan_atomic_next); + +void kcsan_set_access_mask(unsigned long mask) +{ + get_ctx()->access_mask = mask; +} +EXPORT_SYMBOL(kcsan_set_access_mask); + +struct kcsan_scoped_access * +kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type, + struct kcsan_scoped_access *sa) +{ + struct kcsan_ctx *ctx = get_ctx(); + + check_access(ptr, size, type, _RET_IP_); + + ctx->disable_count++; /* Disable KCSAN, in case list debugging is on. */ + + INIT_LIST_HEAD(&sa->list); + sa->ptr = ptr; + sa->size = size; + sa->type = type; + sa->ip = _RET_IP_; + + if (!ctx->scoped_accesses.prev) /* Lazy initialize list head. */ + INIT_LIST_HEAD(&ctx->scoped_accesses); + list_add(&sa->list, &ctx->scoped_accesses); + + ctx->disable_count--; + return sa; +} +EXPORT_SYMBOL(kcsan_begin_scoped_access); + +void kcsan_end_scoped_access(struct kcsan_scoped_access *sa) +{ + struct kcsan_ctx *ctx = get_ctx(); + + if (WARN(!ctx->scoped_accesses.prev, "Unbalanced %s()?", __func__)) + return; + + ctx->disable_count++; /* Disable KCSAN, in case list debugging is on. */ + + list_del(&sa->list); + if (list_empty(&ctx->scoped_accesses)) + /* + * Ensure we do not enter kcsan_check_scoped_accesses() + * slow-path if unnecessary, and avoids requiring list_empty() + * in the fast-path (to avoid a READ_ONCE() and potential + * uaccess warning). + */ + ctx->scoped_accesses.prev = NULL; + + ctx->disable_count--; + + check_access(sa->ptr, sa->size, sa->type, sa->ip); +} +EXPORT_SYMBOL(kcsan_end_scoped_access); + +void __kcsan_check_access(const volatile void *ptr, size_t size, int type) +{ + check_access(ptr, size, type, _RET_IP_); +} +EXPORT_SYMBOL(__kcsan_check_access); + +#define DEFINE_MEMORY_BARRIER(name, order_before_cond) \ + void __kcsan_##name(void) \ + { \ + struct kcsan_scoped_access *sa = get_reorder_access(get_ctx()); \ + if (!sa) \ + return; \ + if (order_before_cond) \ + sa->size = 0; \ + } \ + EXPORT_SYMBOL(__kcsan_##name) + +DEFINE_MEMORY_BARRIER(mb, true); +DEFINE_MEMORY_BARRIER(wmb, sa->type & (KCSAN_ACCESS_WRITE | KCSAN_ACCESS_COMPOUND)); +DEFINE_MEMORY_BARRIER(rmb, !(sa->type & KCSAN_ACCESS_WRITE) || (sa->type & KCSAN_ACCESS_COMPOUND)); +DEFINE_MEMORY_BARRIER(release, true); + +/* + * KCSAN uses the same instrumentation that is emitted by supported compilers + * for ThreadSanitizer (TSAN). + * + * When enabled, the compiler emits instrumentation calls (the functions + * prefixed with "__tsan" below) for all loads and stores that it generated; + * inline asm is not instrumented. + * + * Note that, not all supported compiler versions distinguish aligned/unaligned + * accesses, but e.g. recent versions of Clang do. We simply alias the unaligned + * version to the generic version, which can handle both. + */ + +#define DEFINE_TSAN_READ_WRITE(size) \ + void __tsan_read##size(void *ptr); \ + void __tsan_read##size(void *ptr) \ + { \ + check_access(ptr, size, 0, _RET_IP_); \ + } \ + EXPORT_SYMBOL(__tsan_read##size); \ + void __tsan_unaligned_read##size(void *ptr) \ + __alias(__tsan_read##size); \ + EXPORT_SYMBOL(__tsan_unaligned_read##size); \ + void __tsan_write##size(void *ptr); \ + void __tsan_write##size(void *ptr) \ + { \ + check_access(ptr, size, KCSAN_ACCESS_WRITE, _RET_IP_); \ + } \ + EXPORT_SYMBOL(__tsan_write##size); \ + void __tsan_unaligned_write##size(void *ptr) \ + __alias(__tsan_write##size); \ + EXPORT_SYMBOL(__tsan_unaligned_write##size); \ + void __tsan_read_write##size(void *ptr); \ + void __tsan_read_write##size(void *ptr) \ + { \ + check_access(ptr, size, \ + KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE, \ + _RET_IP_); \ + } \ + EXPORT_SYMBOL(__tsan_read_write##size); \ + void __tsan_unaligned_read_write##size(void *ptr) \ + __alias(__tsan_read_write##size); \ + EXPORT_SYMBOL(__tsan_unaligned_read_write##size) + +DEFINE_TSAN_READ_WRITE(1); +DEFINE_TSAN_READ_WRITE(2); +DEFINE_TSAN_READ_WRITE(4); +DEFINE_TSAN_READ_WRITE(8); +DEFINE_TSAN_READ_WRITE(16); + +void __tsan_read_range(void *ptr, size_t size); +void __tsan_read_range(void *ptr, size_t size) +{ + check_access(ptr, size, 0, _RET_IP_); +} +EXPORT_SYMBOL(__tsan_read_range); + +void __tsan_write_range(void *ptr, size_t size); +void __tsan_write_range(void *ptr, size_t size) +{ + check_access(ptr, size, KCSAN_ACCESS_WRITE, _RET_IP_); +} +EXPORT_SYMBOL(__tsan_write_range); + +/* + * Use of explicit volatile is generally disallowed [1], however, volatile is + * still used in various concurrent context, whether in low-level + * synchronization primitives or for legacy reasons. + * [1] https://lwn.net/Articles/233479/ + * + * We only consider volatile accesses atomic if they are aligned and would pass + * the size-check of compiletime_assert_rwonce_type(). + */ +#define DEFINE_TSAN_VOLATILE_READ_WRITE(size) \ + void __tsan_volatile_read##size(void *ptr); \ + void __tsan_volatile_read##size(void *ptr) \ + { \ + const bool is_atomic = size <= sizeof(long long) && \ + IS_ALIGNED((unsigned long)ptr, size); \ + if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) && is_atomic) \ + return; \ + check_access(ptr, size, is_atomic ? KCSAN_ACCESS_ATOMIC : 0, \ + _RET_IP_); \ + } \ + EXPORT_SYMBOL(__tsan_volatile_read##size); \ + void __tsan_unaligned_volatile_read##size(void *ptr) \ + __alias(__tsan_volatile_read##size); \ + EXPORT_SYMBOL(__tsan_unaligned_volatile_read##size); \ + void __tsan_volatile_write##size(void *ptr); \ + void __tsan_volatile_write##size(void *ptr) \ + { \ + const bool is_atomic = size <= sizeof(long long) && \ + IS_ALIGNED((unsigned long)ptr, size); \ + if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) && is_atomic) \ + return; \ + check_access(ptr, size, \ + KCSAN_ACCESS_WRITE | \ + (is_atomic ? KCSAN_ACCESS_ATOMIC : 0), \ + _RET_IP_); \ + } \ + EXPORT_SYMBOL(__tsan_volatile_write##size); \ + void __tsan_unaligned_volatile_write##size(void *ptr) \ + __alias(__tsan_volatile_write##size); \ + EXPORT_SYMBOL(__tsan_unaligned_volatile_write##size) + +DEFINE_TSAN_VOLATILE_READ_WRITE(1); +DEFINE_TSAN_VOLATILE_READ_WRITE(2); +DEFINE_TSAN_VOLATILE_READ_WRITE(4); +DEFINE_TSAN_VOLATILE_READ_WRITE(8); +DEFINE_TSAN_VOLATILE_READ_WRITE(16); + +/* + * Function entry and exit are used to determine the validty of reorder_access. + * Reordering of the access ends at the end of the function scope where the + * access happened. This is done for two reasons: + * + * 1. Artificially limits the scope where missing barriers are detected. + * This minimizes false positives due to uninstrumented functions that + * contain the required barriers but were missed. + * + * 2. Simplifies generating the stack trace of the access. + */ +void __tsan_func_entry(void *call_pc); +noinline void __tsan_func_entry(void *call_pc) +{ + if (!IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY)) + return; + + add_kcsan_stack_depth(1); +} +EXPORT_SYMBOL(__tsan_func_entry); + +void __tsan_func_exit(void); +noinline void __tsan_func_exit(void) +{ + struct kcsan_scoped_access *reorder_access; + + if (!IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY)) + return; + + reorder_access = get_reorder_access(get_ctx()); + if (!reorder_access) + goto out; + + if (get_kcsan_stack_depth() <= reorder_access->stack_depth) { + /* + * Access check to catch cases where write without a barrier + * (supposed release) was last access in function: because + * instrumentation is inserted before the real access, a data + * race due to the write giving up a c-s would only be caught if + * we do the conflicting access after. + */ + check_access(reorder_access->ptr, reorder_access->size, + reorder_access->type, reorder_access->ip); + reorder_access->size = 0; + reorder_access->stack_depth = INT_MIN; + } +out: + add_kcsan_stack_depth(-1); +} +EXPORT_SYMBOL(__tsan_func_exit); + +void __tsan_init(void); +void __tsan_init(void) +{ +} +EXPORT_SYMBOL(__tsan_init); + +/* + * Instrumentation for atomic builtins (__atomic_*, __sync_*). + * + * Normal kernel code _should not_ be using them directly, but some + * architectures may implement some or all atomics using the compilers' + * builtins. + * + * Note: If an architecture decides to fully implement atomics using the + * builtins, because they are implicitly instrumented by KCSAN (and KASAN, + * etc.), implementing the ARCH_ATOMIC interface (to get instrumentation via + * atomic-instrumented) is no longer necessary. + * + * TSAN instrumentation replaces atomic accesses with calls to any of the below + * functions, whose job is to also execute the operation itself. + */ + +static __always_inline void kcsan_atomic_builtin_memorder(int memorder) +{ + if (memorder == __ATOMIC_RELEASE || + memorder == __ATOMIC_SEQ_CST || + memorder == __ATOMIC_ACQ_REL) + __kcsan_release(); +} + +#define DEFINE_TSAN_ATOMIC_LOAD_STORE(bits) \ + u##bits __tsan_atomic##bits##_load(const u##bits *ptr, int memorder); \ + u##bits __tsan_atomic##bits##_load(const u##bits *ptr, int memorder) \ + { \ + kcsan_atomic_builtin_memorder(memorder); \ + if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ + check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_ATOMIC, _RET_IP_); \ + } \ + return __atomic_load_n(ptr, memorder); \ + } \ + EXPORT_SYMBOL(__tsan_atomic##bits##_load); \ + void __tsan_atomic##bits##_store(u##bits *ptr, u##bits v, int memorder); \ + void __tsan_atomic##bits##_store(u##bits *ptr, u##bits v, int memorder) \ + { \ + kcsan_atomic_builtin_memorder(memorder); \ + if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ + check_access(ptr, bits / BITS_PER_BYTE, \ + KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC, _RET_IP_); \ + } \ + __atomic_store_n(ptr, v, memorder); \ + } \ + EXPORT_SYMBOL(__tsan_atomic##bits##_store) + +#define DEFINE_TSAN_ATOMIC_RMW(op, bits, suffix) \ + u##bits __tsan_atomic##bits##_##op(u##bits *ptr, u##bits v, int memorder); \ + u##bits __tsan_atomic##bits##_##op(u##bits *ptr, u##bits v, int memorder) \ + { \ + kcsan_atomic_builtin_memorder(memorder); \ + if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ + check_access(ptr, bits / BITS_PER_BYTE, \ + KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ + KCSAN_ACCESS_ATOMIC, _RET_IP_); \ + } \ + return __atomic_##op##suffix(ptr, v, memorder); \ + } \ + EXPORT_SYMBOL(__tsan_atomic##bits##_##op) + +/* + * Note: CAS operations are always classified as write, even in case they + * fail. We cannot perform check_access() after a write, as it might lead to + * false positives, in cases such as: + * + * T0: __atomic_compare_exchange_n(&p->flag, &old, 1, ...) + * + * T1: if (__atomic_load_n(&p->flag, ...)) { + * modify *p; + * p->flag = 0; + * } + * + * The only downside is that, if there are 3 threads, with one CAS that + * succeeds, another CAS that fails, and an unmarked racing operation, we may + * point at the wrong CAS as the source of the race. However, if we assume that + * all CAS can succeed in some other execution, the data race is still valid. + */ +#define DEFINE_TSAN_ATOMIC_CMPXCHG(bits, strength, weak) \ + int __tsan_atomic##bits##_compare_exchange_##strength(u##bits *ptr, u##bits *exp, \ + u##bits val, int mo, int fail_mo); \ + int __tsan_atomic##bits##_compare_exchange_##strength(u##bits *ptr, u##bits *exp, \ + u##bits val, int mo, int fail_mo) \ + { \ + kcsan_atomic_builtin_memorder(mo); \ + if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ + check_access(ptr, bits / BITS_PER_BYTE, \ + KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ + KCSAN_ACCESS_ATOMIC, _RET_IP_); \ + } \ + return __atomic_compare_exchange_n(ptr, exp, val, weak, mo, fail_mo); \ + } \ + EXPORT_SYMBOL(__tsan_atomic##bits##_compare_exchange_##strength) + +#define DEFINE_TSAN_ATOMIC_CMPXCHG_VAL(bits) \ + u##bits __tsan_atomic##bits##_compare_exchange_val(u##bits *ptr, u##bits exp, u##bits val, \ + int mo, int fail_mo); \ + u##bits __tsan_atomic##bits##_compare_exchange_val(u##bits *ptr, u##bits exp, u##bits val, \ + int mo, int fail_mo) \ + { \ + kcsan_atomic_builtin_memorder(mo); \ + if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ + check_access(ptr, bits / BITS_PER_BYTE, \ + KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ + KCSAN_ACCESS_ATOMIC, _RET_IP_); \ + } \ + __atomic_compare_exchange_n(ptr, &exp, val, 0, mo, fail_mo); \ + return exp; \ + } \ + EXPORT_SYMBOL(__tsan_atomic##bits##_compare_exchange_val) + +#define DEFINE_TSAN_ATOMIC_OPS(bits) \ + DEFINE_TSAN_ATOMIC_LOAD_STORE(bits); \ + DEFINE_TSAN_ATOMIC_RMW(exchange, bits, _n); \ + DEFINE_TSAN_ATOMIC_RMW(fetch_add, bits, ); \ + DEFINE_TSAN_ATOMIC_RMW(fetch_sub, bits, ); \ + DEFINE_TSAN_ATOMIC_RMW(fetch_and, bits, ); \ + DEFINE_TSAN_ATOMIC_RMW(fetch_or, bits, ); \ + DEFINE_TSAN_ATOMIC_RMW(fetch_xor, bits, ); \ + DEFINE_TSAN_ATOMIC_RMW(fetch_nand, bits, ); \ + DEFINE_TSAN_ATOMIC_CMPXCHG(bits, strong, 0); \ + DEFINE_TSAN_ATOMIC_CMPXCHG(bits, weak, 1); \ + DEFINE_TSAN_ATOMIC_CMPXCHG_VAL(bits) + +DEFINE_TSAN_ATOMIC_OPS(8); +DEFINE_TSAN_ATOMIC_OPS(16); +DEFINE_TSAN_ATOMIC_OPS(32); +#ifdef CONFIG_64BIT +DEFINE_TSAN_ATOMIC_OPS(64); +#endif + +void __tsan_atomic_thread_fence(int memorder); +void __tsan_atomic_thread_fence(int memorder) +{ + kcsan_atomic_builtin_memorder(memorder); + __atomic_thread_fence(memorder); +} +EXPORT_SYMBOL(__tsan_atomic_thread_fence); + +/* + * In instrumented files, we emit instrumentation for barriers by mapping the + * kernel barriers to an __atomic_signal_fence(), which is interpreted specially + * and otherwise has no relation to a real __atomic_signal_fence(). No known + * kernel code uses __atomic_signal_fence(). + * + * Since fsanitize=thread instrumentation handles __atomic_signal_fence(), which + * are turned into calls to __tsan_atomic_signal_fence(), such instrumentation + * can be disabled via the __no_kcsan function attribute (vs. an explicit call + * which could not). When __no_kcsan is requested, __atomic_signal_fence() + * generates no code. + * + * Note: The result of using __atomic_signal_fence() with KCSAN enabled is + * potentially limiting the compiler's ability to reorder operations; however, + * if barriers were instrumented with explicit calls (without LTO), the compiler + * couldn't optimize much anyway. The result of a hypothetical architecture + * using __atomic_signal_fence() in normal code would be KCSAN false negatives. + */ +void __tsan_atomic_signal_fence(int memorder); +noinline void __tsan_atomic_signal_fence(int memorder) +{ + switch (memorder) { + case __KCSAN_BARRIER_TO_SIGNAL_FENCE_mb: + __kcsan_mb(); + break; + case __KCSAN_BARRIER_TO_SIGNAL_FENCE_wmb: + __kcsan_wmb(); + break; + case __KCSAN_BARRIER_TO_SIGNAL_FENCE_rmb: + __kcsan_rmb(); + break; + case __KCSAN_BARRIER_TO_SIGNAL_FENCE_release: + __kcsan_release(); + break; + default: + break; + } +} +EXPORT_SYMBOL(__tsan_atomic_signal_fence); + +#ifdef __HAVE_ARCH_MEMSET +void *__tsan_memset(void *s, int c, size_t count); +noinline void *__tsan_memset(void *s, int c, size_t count) +{ + /* + * Instead of not setting up watchpoints where accessed size is greater + * than MAX_ENCODABLE_SIZE, truncate checked size to MAX_ENCODABLE_SIZE. + */ + size_t check_len = min_t(size_t, count, MAX_ENCODABLE_SIZE); + + check_access(s, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); + return memset(s, c, count); +} +#else +void *__tsan_memset(void *s, int c, size_t count) __alias(memset); +#endif +EXPORT_SYMBOL(__tsan_memset); + +#ifdef __HAVE_ARCH_MEMMOVE +void *__tsan_memmove(void *dst, const void *src, size_t len); +noinline void *__tsan_memmove(void *dst, const void *src, size_t len) +{ + size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); + + check_access(dst, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); + check_access(src, check_len, 0, _RET_IP_); + return memmove(dst, src, len); +} +#else +void *__tsan_memmove(void *dst, const void *src, size_t len) __alias(memmove); +#endif +EXPORT_SYMBOL(__tsan_memmove); + +#ifdef __HAVE_ARCH_MEMCPY +void *__tsan_memcpy(void *dst, const void *src, size_t len); +noinline void *__tsan_memcpy(void *dst, const void *src, size_t len) +{ + size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); + + check_access(dst, check_len, KCSAN_ACCESS_WRITE, _RET_IP_); + check_access(src, check_len, 0, _RET_IP_); + return memcpy(dst, src, len); +} +#else +void *__tsan_memcpy(void *dst, const void *src, size_t len) __alias(memcpy); +#endif +EXPORT_SYMBOL(__tsan_memcpy); diff --git a/kernel/kcsan/debugfs.c b/kernel/kcsan/debugfs.c new file mode 100644 index 000000000..1d1d1b0e4 --- /dev/null +++ b/kernel/kcsan/debugfs.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KCSAN debugfs interface. + * + * Copyright (C) 2019, Google LLC. + */ + +#define pr_fmt(fmt) "kcsan: " fmt + +#include <linux/atomic.h> +#include <linux/bsearch.h> +#include <linux/bug.h> +#include <linux/debugfs.h> +#include <linux/init.h> +#include <linux/kallsyms.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/sort.h> +#include <linux/string.h> +#include <linux/uaccess.h> + +#include "kcsan.h" + +atomic_long_t kcsan_counters[KCSAN_COUNTER_COUNT]; +static const char *const counter_names[] = { + [KCSAN_COUNTER_USED_WATCHPOINTS] = "used_watchpoints", + [KCSAN_COUNTER_SETUP_WATCHPOINTS] = "setup_watchpoints", + [KCSAN_COUNTER_DATA_RACES] = "data_races", + [KCSAN_COUNTER_ASSERT_FAILURES] = "assert_failures", + [KCSAN_COUNTER_NO_CAPACITY] = "no_capacity", + [KCSAN_COUNTER_REPORT_RACES] = "report_races", + [KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN] = "races_unknown_origin", + [KCSAN_COUNTER_UNENCODABLE_ACCESSES] = "unencodable_accesses", + [KCSAN_COUNTER_ENCODING_FALSE_POSITIVES] = "encoding_false_positives", +}; +static_assert(ARRAY_SIZE(counter_names) == KCSAN_COUNTER_COUNT); + +/* + * Addresses for filtering functions from reporting. This list can be used as a + * whitelist or blacklist. + */ +static struct { + unsigned long *addrs; /* array of addresses */ + size_t size; /* current size */ + int used; /* number of elements used */ + bool sorted; /* if elements are sorted */ + bool whitelist; /* if list is a blacklist or whitelist */ +} report_filterlist = { + .addrs = NULL, + .size = 8, /* small initial size */ + .used = 0, + .sorted = false, + .whitelist = false, /* default is blacklist */ +}; +static DEFINE_SPINLOCK(report_filterlist_lock); + +/* + * The microbenchmark allows benchmarking KCSAN core runtime only. To run + * multiple threads, pipe 'microbench=<iters>' from multiple tasks into the + * debugfs file. This will not generate any conflicts, and tests fast-path only. + */ +static noinline void microbenchmark(unsigned long iters) +{ + const struct kcsan_ctx ctx_save = current->kcsan_ctx; + const bool was_enabled = READ_ONCE(kcsan_enabled); + u64 cycles; + + /* We may have been called from an atomic region; reset context. */ + memset(¤t->kcsan_ctx, 0, sizeof(current->kcsan_ctx)); + /* + * Disable to benchmark fast-path for all accesses, and (expected + * negligible) call into slow-path, but never set up watchpoints. + */ + WRITE_ONCE(kcsan_enabled, false); + + pr_info("%s begin | iters: %lu\n", __func__, iters); + + cycles = get_cycles(); + while (iters--) { + unsigned long addr = iters & ((PAGE_SIZE << 8) - 1); + int type = !(iters & 0x7f) ? KCSAN_ACCESS_ATOMIC : + (!(iters & 0xf) ? KCSAN_ACCESS_WRITE : 0); + __kcsan_check_access((void *)addr, sizeof(long), type); + } + cycles = get_cycles() - cycles; + + pr_info("%s end | cycles: %llu\n", __func__, cycles); + + WRITE_ONCE(kcsan_enabled, was_enabled); + /* restore context */ + current->kcsan_ctx = ctx_save; +} + +static int cmp_filterlist_addrs(const void *rhs, const void *lhs) +{ + const unsigned long a = *(const unsigned long *)rhs; + const unsigned long b = *(const unsigned long *)lhs; + + return a < b ? -1 : a == b ? 0 : 1; +} + +bool kcsan_skip_report_debugfs(unsigned long func_addr) +{ + unsigned long symbolsize, offset; + unsigned long flags; + bool ret = false; + + if (!kallsyms_lookup_size_offset(func_addr, &symbolsize, &offset)) + return false; + func_addr -= offset; /* Get function start */ + + spin_lock_irqsave(&report_filterlist_lock, flags); + if (report_filterlist.used == 0) + goto out; + + /* Sort array if it is unsorted, and then do a binary search. */ + if (!report_filterlist.sorted) { + sort(report_filterlist.addrs, report_filterlist.used, + sizeof(unsigned long), cmp_filterlist_addrs, NULL); + report_filterlist.sorted = true; + } + ret = !!bsearch(&func_addr, report_filterlist.addrs, + report_filterlist.used, sizeof(unsigned long), + cmp_filterlist_addrs); + if (report_filterlist.whitelist) + ret = !ret; + +out: + spin_unlock_irqrestore(&report_filterlist_lock, flags); + return ret; +} + +static void set_report_filterlist_whitelist(bool whitelist) +{ + unsigned long flags; + + spin_lock_irqsave(&report_filterlist_lock, flags); + report_filterlist.whitelist = whitelist; + spin_unlock_irqrestore(&report_filterlist_lock, flags); +} + +/* Returns 0 on success, error-code otherwise. */ +static ssize_t insert_report_filterlist(const char *func) +{ + unsigned long flags; + unsigned long addr = kallsyms_lookup_name(func); + ssize_t ret = 0; + + if (!addr) { + pr_err("could not find function: '%s'\n", func); + return -ENOENT; + } + + spin_lock_irqsave(&report_filterlist_lock, flags); + + if (report_filterlist.addrs == NULL) { + /* initial allocation */ + report_filterlist.addrs = + kmalloc_array(report_filterlist.size, + sizeof(unsigned long), GFP_ATOMIC); + if (report_filterlist.addrs == NULL) { + ret = -ENOMEM; + goto out; + } + } else if (report_filterlist.used == report_filterlist.size) { + /* resize filterlist */ + size_t new_size = report_filterlist.size * 2; + unsigned long *new_addrs = + krealloc(report_filterlist.addrs, + new_size * sizeof(unsigned long), GFP_ATOMIC); + + if (new_addrs == NULL) { + /* leave filterlist itself untouched */ + ret = -ENOMEM; + goto out; + } + + report_filterlist.size = new_size; + report_filterlist.addrs = new_addrs; + } + + /* Note: deduplicating should be done in userspace. */ + report_filterlist.addrs[report_filterlist.used++] = + kallsyms_lookup_name(func); + report_filterlist.sorted = false; + +out: + spin_unlock_irqrestore(&report_filterlist_lock, flags); + + return ret; +} + +static int show_info(struct seq_file *file, void *v) +{ + int i; + unsigned long flags; + + /* show stats */ + seq_printf(file, "enabled: %i\n", READ_ONCE(kcsan_enabled)); + for (i = 0; i < KCSAN_COUNTER_COUNT; ++i) { + seq_printf(file, "%s: %ld\n", counter_names[i], + atomic_long_read(&kcsan_counters[i])); + } + + /* show filter functions, and filter type */ + spin_lock_irqsave(&report_filterlist_lock, flags); + seq_printf(file, "\n%s functions: %s\n", + report_filterlist.whitelist ? "whitelisted" : "blacklisted", + report_filterlist.used == 0 ? "none" : ""); + for (i = 0; i < report_filterlist.used; ++i) + seq_printf(file, " %ps\n", (void *)report_filterlist.addrs[i]); + spin_unlock_irqrestore(&report_filterlist_lock, flags); + + return 0; +} + +static int debugfs_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_info, NULL); +} + +static ssize_t +debugfs_write(struct file *file, const char __user *buf, size_t count, loff_t *off) +{ + char kbuf[KSYM_NAME_LEN]; + char *arg; + int read_len = count < (sizeof(kbuf) - 1) ? count : (sizeof(kbuf) - 1); + + if (copy_from_user(kbuf, buf, read_len)) + return -EFAULT; + kbuf[read_len] = '\0'; + arg = strstrip(kbuf); + + if (!strcmp(arg, "on")) { + WRITE_ONCE(kcsan_enabled, true); + } else if (!strcmp(arg, "off")) { + WRITE_ONCE(kcsan_enabled, false); + } else if (str_has_prefix(arg, "microbench=")) { + unsigned long iters; + + if (kstrtoul(&arg[strlen("microbench=")], 0, &iters)) + return -EINVAL; + microbenchmark(iters); + } else if (!strcmp(arg, "whitelist")) { + set_report_filterlist_whitelist(true); + } else if (!strcmp(arg, "blacklist")) { + set_report_filterlist_whitelist(false); + } else if (arg[0] == '!') { + ssize_t ret = insert_report_filterlist(&arg[1]); + + if (ret < 0) + return ret; + } else { + return -EINVAL; + } + + return count; +} + +static const struct file_operations debugfs_ops = +{ + .read = seq_read, + .open = debugfs_open, + .write = debugfs_write, + .release = single_release +}; + +static int __init kcsan_debugfs_init(void) +{ + debugfs_create_file("kcsan", 0644, NULL, NULL, &debugfs_ops); + return 0; +} + +late_initcall(kcsan_debugfs_init); diff --git a/kernel/kcsan/encoding.h b/kernel/kcsan/encoding.h new file mode 100644 index 000000000..170a2bb22 --- /dev/null +++ b/kernel/kcsan/encoding.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KCSAN watchpoint encoding. + * + * Copyright (C) 2019, Google LLC. + */ + +#ifndef _KERNEL_KCSAN_ENCODING_H +#define _KERNEL_KCSAN_ENCODING_H + +#include <linux/bits.h> +#include <linux/log2.h> +#include <linux/mm.h> + +#include "kcsan.h" + +#define SLOT_RANGE PAGE_SIZE + +#define INVALID_WATCHPOINT 0 +#define CONSUMED_WATCHPOINT 1 + +/* + * The maximum useful size of accesses for which we set up watchpoints is the + * max range of slots we check on an access. + */ +#define MAX_ENCODABLE_SIZE (SLOT_RANGE * (1 + KCSAN_CHECK_ADJACENT)) + +/* + * Number of bits we use to store size info. + */ +#define WATCHPOINT_SIZE_BITS bits_per(MAX_ENCODABLE_SIZE) +/* + * This encoding for addresses discards the upper (1 for is-write + SIZE_BITS); + * however, most 64-bit architectures do not use the full 64-bit address space. + * Also, in order for a false positive to be observable 2 things need to happen: + * + * 1. different addresses but with the same encoded address race; + * 2. and both map onto the same watchpoint slots; + * + * Both these are assumed to be very unlikely. However, in case it still + * happens, the report logic will filter out the false positive (see report.c). + */ +#define WATCHPOINT_ADDR_BITS (BITS_PER_LONG-1 - WATCHPOINT_SIZE_BITS) + +/* Bitmasks for the encoded watchpoint access information. */ +#define WATCHPOINT_WRITE_MASK BIT(BITS_PER_LONG-1) +#define WATCHPOINT_SIZE_MASK GENMASK(BITS_PER_LONG-2, WATCHPOINT_ADDR_BITS) +#define WATCHPOINT_ADDR_MASK GENMASK(WATCHPOINT_ADDR_BITS-1, 0) +static_assert(WATCHPOINT_ADDR_MASK == (1UL << WATCHPOINT_ADDR_BITS) - 1); +static_assert((WATCHPOINT_WRITE_MASK ^ WATCHPOINT_SIZE_MASK ^ WATCHPOINT_ADDR_MASK) == ~0UL); + +static inline bool check_encodable(unsigned long addr, size_t size) +{ + /* + * While we can encode addrs<PAGE_SIZE, avoid crashing with a NULL + * pointer deref inside KCSAN. + */ + return addr >= PAGE_SIZE && size <= MAX_ENCODABLE_SIZE; +} + +static inline long +encode_watchpoint(unsigned long addr, size_t size, bool is_write) +{ + return (long)((is_write ? WATCHPOINT_WRITE_MASK : 0) | + (size << WATCHPOINT_ADDR_BITS) | + (addr & WATCHPOINT_ADDR_MASK)); +} + +static __always_inline bool decode_watchpoint(long watchpoint, + unsigned long *addr_masked, + size_t *size, + bool *is_write) +{ + if (watchpoint == INVALID_WATCHPOINT || + watchpoint == CONSUMED_WATCHPOINT) + return false; + + *addr_masked = (unsigned long)watchpoint & WATCHPOINT_ADDR_MASK; + *size = ((unsigned long)watchpoint & WATCHPOINT_SIZE_MASK) >> WATCHPOINT_ADDR_BITS; + *is_write = !!((unsigned long)watchpoint & WATCHPOINT_WRITE_MASK); + + return true; +} + +/* + * Return watchpoint slot for an address. + */ +static __always_inline int watchpoint_slot(unsigned long addr) +{ + return (addr / PAGE_SIZE) % CONFIG_KCSAN_NUM_WATCHPOINTS; +} + +static __always_inline bool matching_access(unsigned long addr1, size_t size1, + unsigned long addr2, size_t size2) +{ + unsigned long end_range1 = addr1 + size1 - 1; + unsigned long end_range2 = addr2 + size2 - 1; + + return addr1 <= end_range2 && addr2 <= end_range1; +} + +#endif /* _KERNEL_KCSAN_ENCODING_H */ diff --git a/kernel/kcsan/kcsan.h b/kernel/kcsan/kcsan.h new file mode 100644 index 000000000..ae33c2a7f --- /dev/null +++ b/kernel/kcsan/kcsan.h @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * The Kernel Concurrency Sanitizer (KCSAN) infrastructure. For more info please + * see Documentation/dev-tools/kcsan.rst. + * + * Copyright (C) 2019, Google LLC. + */ + +#ifndef _KERNEL_KCSAN_KCSAN_H +#define _KERNEL_KCSAN_KCSAN_H + +#include <linux/atomic.h> +#include <linux/kcsan.h> +#include <linux/sched.h> + +/* The number of adjacent watchpoints to check. */ +#define KCSAN_CHECK_ADJACENT 1 +#define NUM_SLOTS (1 + 2*KCSAN_CHECK_ADJACENT) + +extern unsigned int kcsan_udelay_task; +extern unsigned int kcsan_udelay_interrupt; + +/* + * Globally enable and disable KCSAN. + */ +extern bool kcsan_enabled; + +/* + * Save/restore IRQ flags state trace dirtied by KCSAN. + */ +void kcsan_save_irqtrace(struct task_struct *task); +void kcsan_restore_irqtrace(struct task_struct *task); + +/* + * Statistics counters displayed via debugfs; should only be modified in + * slow-paths. + */ +enum kcsan_counter_id { + /* + * Number of watchpoints currently in use. + */ + KCSAN_COUNTER_USED_WATCHPOINTS, + + /* + * Total number of watchpoints set up. + */ + KCSAN_COUNTER_SETUP_WATCHPOINTS, + + /* + * Total number of data races. + */ + KCSAN_COUNTER_DATA_RACES, + + /* + * Total number of ASSERT failures due to races. If the observed race is + * due to two conflicting ASSERT type accesses, then both will be + * counted. + */ + KCSAN_COUNTER_ASSERT_FAILURES, + + /* + * Number of times no watchpoints were available. + */ + KCSAN_COUNTER_NO_CAPACITY, + + /* + * A thread checking a watchpoint raced with another checking thread; + * only one will be reported. + */ + KCSAN_COUNTER_REPORT_RACES, + + /* + * Observed data value change, but writer thread unknown. + */ + KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN, + + /* + * The access cannot be encoded to a valid watchpoint. + */ + KCSAN_COUNTER_UNENCODABLE_ACCESSES, + + /* + * Watchpoint encoding caused a watchpoint to fire on mismatching + * accesses. + */ + KCSAN_COUNTER_ENCODING_FALSE_POSITIVES, + + KCSAN_COUNTER_COUNT, /* number of counters */ +}; +extern atomic_long_t kcsan_counters[KCSAN_COUNTER_COUNT]; + +/* + * Returns true if data races in the function symbol that maps to func_addr + * (offsets are ignored) should *not* be reported. + */ +extern bool kcsan_skip_report_debugfs(unsigned long func_addr); + +/* + * Value-change states. + */ +enum kcsan_value_change { + /* + * Did not observe a value-change, however, it is valid to report the + * race, depending on preferences. + */ + KCSAN_VALUE_CHANGE_MAYBE, + + /* + * Did not observe a value-change, and it is invalid to report the race. + */ + KCSAN_VALUE_CHANGE_FALSE, + + /* + * The value was observed to change, and the race should be reported. + */ + KCSAN_VALUE_CHANGE_TRUE, +}; + +/* + * The calling thread hit and consumed a watchpoint: set the access information + * to be consumed by the reporting thread. No report is printed yet. + */ +void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_type, + unsigned long ip, int watchpoint_idx); + +/* + * The calling thread observed that the watchpoint it set up was hit and + * consumed: print the full report based on information set by the racing + * thread. + */ +void kcsan_report_known_origin(const volatile void *ptr, size_t size, int access_type, + unsigned long ip, enum kcsan_value_change value_change, + int watchpoint_idx, u64 old, u64 new, u64 mask); + +/* + * No other thread was observed to race with the access, but the data value + * before and after the stall differs. Reports a race of "unknown origin". + */ +void kcsan_report_unknown_origin(const volatile void *ptr, size_t size, int access_type, + unsigned long ip, u64 old, u64 new, u64 mask); + +#endif /* _KERNEL_KCSAN_KCSAN_H */ diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c new file mode 100644 index 000000000..a60c56172 --- /dev/null +++ b/kernel/kcsan/kcsan_test.c @@ -0,0 +1,1618 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KCSAN test with various race scenarious to test runtime behaviour. Since the + * interface with which KCSAN's reports are obtained is via the console, this is + * the output we should verify. For each test case checks the presence (or + * absence) of generated reports. Relies on 'console' tracepoint to capture + * reports as they appear in the kernel log. + * + * Makes use of KUnit for test organization, and the Torture framework for test + * thread control. + * + * Copyright (C) 2020, Google LLC. + * Author: Marco Elver <elver@google.com> + */ + +#define pr_fmt(fmt) "kcsan_test: " fmt + +#include <kunit/test.h> +#include <linux/atomic.h> +#include <linux/bitops.h> +#include <linux/jiffies.h> +#include <linux/kcsan-checks.h> +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/seqlock.h> +#include <linux/spinlock.h> +#include <linux/string.h> +#include <linux/timer.h> +#include <linux/torture.h> +#include <linux/tracepoint.h> +#include <linux/types.h> +#include <trace/events/printk.h> + +#define KCSAN_TEST_REQUIRES(test, cond) do { \ + if (!(cond)) \ + kunit_skip((test), "Test requires: " #cond); \ +} while (0) + +#ifdef CONFIG_CC_HAS_TSAN_COMPOUND_READ_BEFORE_WRITE +#define __KCSAN_ACCESS_RW(alt) (KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE) +#else +#define __KCSAN_ACCESS_RW(alt) (alt) +#endif + +/* Points to current test-case memory access "kernels". */ +static void (*access_kernels[2])(void); + +static struct task_struct **threads; /* Lists of threads. */ +static unsigned long end_time; /* End time of test. */ + +/* Report as observed from console. */ +static struct { + spinlock_t lock; + int nlines; + char lines[3][512]; +} observed = { + .lock = __SPIN_LOCK_UNLOCKED(observed.lock), +}; + +/* Setup test checking loop. */ +static __no_kcsan inline void +begin_test_checks(void (*func1)(void), void (*func2)(void)) +{ + kcsan_disable_current(); + + /* + * Require at least as long as KCSAN_REPORT_ONCE_IN_MS, to ensure at + * least one race is reported. + */ + end_time = jiffies + msecs_to_jiffies(CONFIG_KCSAN_REPORT_ONCE_IN_MS + 500); + + /* Signal start; release potential initialization of shared data. */ + smp_store_release(&access_kernels[0], func1); + smp_store_release(&access_kernels[1], func2); +} + +/* End test checking loop. */ +static __no_kcsan inline bool +end_test_checks(bool stop) +{ + if (!stop && time_before(jiffies, end_time)) { + /* Continue checking */ + might_sleep(); + return false; + } + + kcsan_enable_current(); + return true; +} + +/* + * Probe for console output: checks if a race was reported, and obtains observed + * lines of interest. + */ +__no_kcsan +static void probe_console(void *ignore, const char *buf, size_t len) +{ + unsigned long flags; + int nlines; + + /* + * Note that KCSAN reports under a global lock, so we do not risk the + * possibility of having multiple reports interleaved. If that were the + * case, we'd expect tests to fail. + */ + + spin_lock_irqsave(&observed.lock, flags); + nlines = observed.nlines; + + if (strnstr(buf, "BUG: KCSAN: ", len) && strnstr(buf, "test_", len)) { + /* + * KCSAN report and related to the test. + * + * The provided @buf is not NUL-terminated; copy no more than + * @len bytes and let strscpy() add the missing NUL-terminator. + */ + strscpy(observed.lines[0], buf, min(len + 1, sizeof(observed.lines[0]))); + nlines = 1; + } else if ((nlines == 1 || nlines == 2) && strnstr(buf, "bytes by", len)) { + strscpy(observed.lines[nlines++], buf, min(len + 1, sizeof(observed.lines[0]))); + + if (strnstr(buf, "race at unknown origin", len)) { + if (WARN_ON(nlines != 2)) + goto out; + + /* No second line of interest. */ + strcpy(observed.lines[nlines++], "<none>"); + } + } + +out: + WRITE_ONCE(observed.nlines, nlines); /* Publish new nlines. */ + spin_unlock_irqrestore(&observed.lock, flags); +} + +/* Check if a report related to the test exists. */ +__no_kcsan +static bool report_available(void) +{ + return READ_ONCE(observed.nlines) == ARRAY_SIZE(observed.lines); +} + +/* Report information we expect in a report. */ +struct expect_report { + /* Access information of both accesses. */ + struct { + void *fn; /* Function pointer to expected function of top frame. */ + void *addr; /* Address of access; unchecked if NULL. */ + size_t size; /* Size of access; unchecked if @addr is NULL. */ + int type; /* Access type, see KCSAN_ACCESS definitions. */ + } access[2]; +}; + +/* Check observed report matches information in @r. */ +__no_kcsan +static bool __report_matches(const struct expect_report *r) +{ + const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT; + bool ret = false; + unsigned long flags; + typeof(*observed.lines) *expect; + const char *end; + char *cur; + int i; + + /* Doubled-checked locking. */ + if (!report_available()) + return false; + + expect = kmalloc(sizeof(observed.lines), GFP_KERNEL); + if (WARN_ON(!expect)) + return false; + + /* Generate expected report contents. */ + + /* Title */ + cur = expect[0]; + end = &expect[0][sizeof(expect[0]) - 1]; + cur += scnprintf(cur, end - cur, "BUG: KCSAN: %s in ", + is_assert ? "assert: race" : "data-race"); + if (r->access[1].fn) { + char tmp[2][64]; + int cmp; + + /* Expect lexographically sorted function names in title. */ + scnprintf(tmp[0], sizeof(tmp[0]), "%pS", r->access[0].fn); + scnprintf(tmp[1], sizeof(tmp[1]), "%pS", r->access[1].fn); + cmp = strcmp(tmp[0], tmp[1]); + cur += scnprintf(cur, end - cur, "%ps / %ps", + cmp < 0 ? r->access[0].fn : r->access[1].fn, + cmp < 0 ? r->access[1].fn : r->access[0].fn); + } else { + scnprintf(cur, end - cur, "%pS", r->access[0].fn); + /* The exact offset won't match, remove it. */ + cur = strchr(expect[0], '+'); + if (cur) + *cur = '\0'; + } + + /* Access 1 */ + cur = expect[1]; + end = &expect[1][sizeof(expect[1]) - 1]; + if (!r->access[1].fn) + cur += scnprintf(cur, end - cur, "race at unknown origin, with "); + + /* Access 1 & 2 */ + for (i = 0; i < 2; ++i) { + const int ty = r->access[i].type; + const char *const access_type = + (ty & KCSAN_ACCESS_ASSERT) ? + ((ty & KCSAN_ACCESS_WRITE) ? + "assert no accesses" : + "assert no writes") : + ((ty & KCSAN_ACCESS_WRITE) ? + ((ty & KCSAN_ACCESS_COMPOUND) ? + "read-write" : + "write") : + "read"); + const bool is_atomic = (ty & KCSAN_ACCESS_ATOMIC); + const bool is_scoped = (ty & KCSAN_ACCESS_SCOPED); + const char *const access_type_aux = + (is_atomic && is_scoped) ? " (marked, reordered)" + : (is_atomic ? " (marked)" + : (is_scoped ? " (reordered)" : "")); + + if (i == 1) { + /* Access 2 */ + cur = expect[2]; + end = &expect[2][sizeof(expect[2]) - 1]; + + if (!r->access[1].fn) { + /* Dummy string if no second access is available. */ + strcpy(cur, "<none>"); + break; + } + } + + cur += scnprintf(cur, end - cur, "%s%s to ", access_type, + access_type_aux); + + if (r->access[i].addr) /* Address is optional. */ + cur += scnprintf(cur, end - cur, "0x%px of %zu bytes", + r->access[i].addr, r->access[i].size); + } + + spin_lock_irqsave(&observed.lock, flags); + if (!report_available()) + goto out; /* A new report is being captured. */ + + /* Finally match expected output to what we actually observed. */ + ret = strstr(observed.lines[0], expect[0]) && + /* Access info may appear in any order. */ + ((strstr(observed.lines[1], expect[1]) && + strstr(observed.lines[2], expect[2])) || + (strstr(observed.lines[1], expect[2]) && + strstr(observed.lines[2], expect[1]))); +out: + spin_unlock_irqrestore(&observed.lock, flags); + kfree(expect); + return ret; +} + +static __always_inline const struct expect_report * +__report_set_scoped(struct expect_report *r, int accesses) +{ + BUILD_BUG_ON(accesses > 3); + + if (accesses & 1) + r->access[0].type |= KCSAN_ACCESS_SCOPED; + else + r->access[0].type &= ~KCSAN_ACCESS_SCOPED; + + if (accesses & 2) + r->access[1].type |= KCSAN_ACCESS_SCOPED; + else + r->access[1].type &= ~KCSAN_ACCESS_SCOPED; + + return r; +} + +__no_kcsan +static bool report_matches_any_reordered(struct expect_report *r) +{ + return __report_matches(__report_set_scoped(r, 0)) || + __report_matches(__report_set_scoped(r, 1)) || + __report_matches(__report_set_scoped(r, 2)) || + __report_matches(__report_set_scoped(r, 3)); +} + +#ifdef CONFIG_KCSAN_WEAK_MEMORY +/* Due to reordering accesses, any access may appear as "(reordered)". */ +#define report_matches report_matches_any_reordered +#else +#define report_matches __report_matches +#endif + +/* ===== Test kernels ===== */ + +static long test_sink; +static long test_var; +/* @test_array should be large enough to fall into multiple watchpoint slots. */ +static long test_array[3 * PAGE_SIZE / sizeof(long)]; +static struct { + long val[8]; +} test_struct; +static DEFINE_SEQLOCK(test_seqlock); +static DEFINE_SPINLOCK(test_spinlock); +static DEFINE_MUTEX(test_mutex); + +/* + * Helper to avoid compiler optimizing out reads, and to generate source values + * for writes. + */ +__no_kcsan +static noinline void sink_value(long v) { WRITE_ONCE(test_sink, v); } + +/* + * Generates a delay and some accesses that enter the runtime but do not produce + * data races. + */ +static noinline void test_delay(int iter) +{ + while (iter--) + sink_value(READ_ONCE(test_sink)); +} + +static noinline void test_kernel_read(void) { sink_value(test_var); } + +static noinline void test_kernel_write(void) +{ + test_var = READ_ONCE_NOCHECK(test_sink) + 1; +} + +static noinline void test_kernel_write_nochange(void) { test_var = 42; } + +/* Suffixed by value-change exception filter. */ +static noinline void test_kernel_write_nochange_rcu(void) { test_var = 42; } + +static noinline void test_kernel_read_atomic(void) +{ + sink_value(READ_ONCE(test_var)); +} + +static noinline void test_kernel_write_atomic(void) +{ + WRITE_ONCE(test_var, READ_ONCE_NOCHECK(test_sink) + 1); +} + +static noinline void test_kernel_atomic_rmw(void) +{ + /* Use builtin, so we can set up the "bad" atomic/non-atomic scenario. */ + __atomic_fetch_add(&test_var, 1, __ATOMIC_RELAXED); +} + +__no_kcsan +static noinline void test_kernel_write_uninstrumented(void) { test_var++; } + +static noinline void test_kernel_data_race(void) { data_race(test_var++); } + +static noinline void test_kernel_assert_writer(void) +{ + ASSERT_EXCLUSIVE_WRITER(test_var); +} + +static noinline void test_kernel_assert_access(void) +{ + ASSERT_EXCLUSIVE_ACCESS(test_var); +} + +#define TEST_CHANGE_BITS 0xff00ff00 + +static noinline void test_kernel_change_bits(void) +{ + if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { + /* + * Avoid race of unknown origin for this test, just pretend they + * are atomic. + */ + kcsan_nestable_atomic_begin(); + test_var ^= TEST_CHANGE_BITS; + kcsan_nestable_atomic_end(); + } else + WRITE_ONCE(test_var, READ_ONCE(test_var) ^ TEST_CHANGE_BITS); +} + +static noinline void test_kernel_assert_bits_change(void) +{ + ASSERT_EXCLUSIVE_BITS(test_var, TEST_CHANGE_BITS); +} + +static noinline void test_kernel_assert_bits_nochange(void) +{ + ASSERT_EXCLUSIVE_BITS(test_var, ~TEST_CHANGE_BITS); +} + +/* + * Scoped assertions do trigger anywhere in scope. However, the report should + * still only point at the start of the scope. + */ +static noinline void test_enter_scope(void) +{ + int x = 0; + + /* Unrelated accesses to scoped assert. */ + READ_ONCE(test_sink); + kcsan_check_read(&x, sizeof(x)); +} + +static noinline void test_kernel_assert_writer_scoped(void) +{ + ASSERT_EXCLUSIVE_WRITER_SCOPED(test_var); + test_enter_scope(); +} + +static noinline void test_kernel_assert_access_scoped(void) +{ + ASSERT_EXCLUSIVE_ACCESS_SCOPED(test_var); + test_enter_scope(); +} + +static noinline void test_kernel_rmw_array(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(test_array); ++i) + test_array[i]++; +} + +static noinline void test_kernel_write_struct(void) +{ + kcsan_check_write(&test_struct, sizeof(test_struct)); + kcsan_disable_current(); + test_struct.val[3]++; /* induce value change */ + kcsan_enable_current(); +} + +static noinline void test_kernel_write_struct_part(void) +{ + test_struct.val[3] = 42; +} + +static noinline void test_kernel_read_struct_zero_size(void) +{ + kcsan_check_read(&test_struct.val[3], 0); +} + +static noinline void test_kernel_jiffies_reader(void) +{ + sink_value((long)jiffies); +} + +static noinline void test_kernel_seqlock_reader(void) +{ + unsigned int seq; + + do { + seq = read_seqbegin(&test_seqlock); + sink_value(test_var); + } while (read_seqretry(&test_seqlock, seq)); +} + +static noinline void test_kernel_seqlock_writer(void) +{ + unsigned long flags; + + write_seqlock_irqsave(&test_seqlock, flags); + test_var++; + write_sequnlock_irqrestore(&test_seqlock, flags); +} + +static noinline void test_kernel_atomic_builtins(void) +{ + /* + * Generate concurrent accesses, expecting no reports, ensuring KCSAN + * treats builtin atomics as actually atomic. + */ + __atomic_load_n(&test_var, __ATOMIC_RELAXED); +} + +static noinline void test_kernel_xor_1bit(void) +{ + /* Do not report data races between the read-writes. */ + kcsan_nestable_atomic_begin(); + test_var ^= 0x10000; + kcsan_nestable_atomic_end(); +} + +#define TEST_KERNEL_LOCKED(name, acquire, release) \ + static noinline void test_kernel_##name(void) \ + { \ + long *flag = &test_struct.val[0]; \ + long v = 0; \ + if (!(acquire)) \ + return; \ + while (v++ < 100) { \ + test_var++; \ + barrier(); \ + } \ + release; \ + test_delay(10); \ + } + +TEST_KERNEL_LOCKED(with_memorder, + cmpxchg_acquire(flag, 0, 1) == 0, + smp_store_release(flag, 0)); +TEST_KERNEL_LOCKED(wrong_memorder, + cmpxchg_relaxed(flag, 0, 1) == 0, + WRITE_ONCE(*flag, 0)); +TEST_KERNEL_LOCKED(atomic_builtin_with_memorder, + __atomic_compare_exchange_n(flag, &v, 1, 0, __ATOMIC_ACQUIRE, __ATOMIC_RELAXED), + __atomic_store_n(flag, 0, __ATOMIC_RELEASE)); +TEST_KERNEL_LOCKED(atomic_builtin_wrong_memorder, + __atomic_compare_exchange_n(flag, &v, 1, 0, __ATOMIC_RELAXED, __ATOMIC_RELAXED), + __atomic_store_n(flag, 0, __ATOMIC_RELAXED)); + +/* ===== Test cases ===== */ + +/* + * Tests that various barriers have the expected effect on internal state. Not + * exhaustive on atomic_t operations. Unlike the selftest, also checks for + * too-strict barrier instrumentation; these can be tolerated, because it does + * not cause false positives, but at least we should be aware of such cases. + */ +static void test_barrier_nothreads(struct kunit *test) +{ +#ifdef CONFIG_KCSAN_WEAK_MEMORY + struct kcsan_scoped_access *reorder_access = ¤t->kcsan_ctx.reorder_access; +#else + struct kcsan_scoped_access *reorder_access = NULL; +#endif + arch_spinlock_t arch_spinlock = __ARCH_SPIN_LOCK_UNLOCKED; + atomic_t dummy; + + KCSAN_TEST_REQUIRES(test, reorder_access != NULL); + KCSAN_TEST_REQUIRES(test, IS_ENABLED(CONFIG_SMP)); + +#define __KCSAN_EXPECT_BARRIER(access_type, barrier, order_before, name) \ + do { \ + reorder_access->type = (access_type) | KCSAN_ACCESS_SCOPED; \ + reorder_access->size = sizeof(test_var); \ + barrier; \ + KUNIT_EXPECT_EQ_MSG(test, reorder_access->size, \ + order_before ? 0 : sizeof(test_var), \ + "improperly instrumented type=(" #access_type "): " name); \ + } while (0) +#define KCSAN_EXPECT_READ_BARRIER(b, o) __KCSAN_EXPECT_BARRIER(0, b, o, #b) +#define KCSAN_EXPECT_WRITE_BARRIER(b, o) __KCSAN_EXPECT_BARRIER(KCSAN_ACCESS_WRITE, b, o, #b) +#define KCSAN_EXPECT_RW_BARRIER(b, o) __KCSAN_EXPECT_BARRIER(KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE, b, o, #b) + + /* + * Lockdep initialization can strengthen certain locking operations due + * to calling into instrumented files; "warm up" our locks. + */ + spin_lock(&test_spinlock); + spin_unlock(&test_spinlock); + mutex_lock(&test_mutex); + mutex_unlock(&test_mutex); + + /* Force creating a valid entry in reorder_access first. */ + test_var = 0; + while (test_var++ < 1000000 && reorder_access->size != sizeof(test_var)) + __kcsan_check_read(&test_var, sizeof(test_var)); + KUNIT_ASSERT_EQ(test, reorder_access->size, sizeof(test_var)); + + kcsan_nestable_atomic_begin(); /* No watchpoints in called functions. */ + + KCSAN_EXPECT_READ_BARRIER(mb(), true); + KCSAN_EXPECT_READ_BARRIER(wmb(), false); + KCSAN_EXPECT_READ_BARRIER(rmb(), true); + KCSAN_EXPECT_READ_BARRIER(smp_mb(), true); + KCSAN_EXPECT_READ_BARRIER(smp_wmb(), false); + KCSAN_EXPECT_READ_BARRIER(smp_rmb(), true); + KCSAN_EXPECT_READ_BARRIER(dma_wmb(), false); + KCSAN_EXPECT_READ_BARRIER(dma_rmb(), true); + KCSAN_EXPECT_READ_BARRIER(smp_mb__before_atomic(), true); + KCSAN_EXPECT_READ_BARRIER(smp_mb__after_atomic(), true); + KCSAN_EXPECT_READ_BARRIER(smp_mb__after_spinlock(), true); + KCSAN_EXPECT_READ_BARRIER(smp_store_mb(test_var, 0), true); + KCSAN_EXPECT_READ_BARRIER(smp_load_acquire(&test_var), false); + KCSAN_EXPECT_READ_BARRIER(smp_store_release(&test_var, 0), true); + KCSAN_EXPECT_READ_BARRIER(xchg(&test_var, 0), true); + KCSAN_EXPECT_READ_BARRIER(xchg_release(&test_var, 0), true); + KCSAN_EXPECT_READ_BARRIER(xchg_relaxed(&test_var, 0), false); + KCSAN_EXPECT_READ_BARRIER(cmpxchg(&test_var, 0, 0), true); + KCSAN_EXPECT_READ_BARRIER(cmpxchg_release(&test_var, 0, 0), true); + KCSAN_EXPECT_READ_BARRIER(cmpxchg_relaxed(&test_var, 0, 0), false); + KCSAN_EXPECT_READ_BARRIER(atomic_read(&dummy), false); + KCSAN_EXPECT_READ_BARRIER(atomic_read_acquire(&dummy), false); + KCSAN_EXPECT_READ_BARRIER(atomic_set(&dummy, 0), false); + KCSAN_EXPECT_READ_BARRIER(atomic_set_release(&dummy, 0), true); + KCSAN_EXPECT_READ_BARRIER(atomic_add(1, &dummy), false); + KCSAN_EXPECT_READ_BARRIER(atomic_add_return(1, &dummy), true); + KCSAN_EXPECT_READ_BARRIER(atomic_add_return_acquire(1, &dummy), false); + KCSAN_EXPECT_READ_BARRIER(atomic_add_return_release(1, &dummy), true); + KCSAN_EXPECT_READ_BARRIER(atomic_add_return_relaxed(1, &dummy), false); + KCSAN_EXPECT_READ_BARRIER(atomic_fetch_add(1, &dummy), true); + KCSAN_EXPECT_READ_BARRIER(atomic_fetch_add_acquire(1, &dummy), false); + KCSAN_EXPECT_READ_BARRIER(atomic_fetch_add_release(1, &dummy), true); + KCSAN_EXPECT_READ_BARRIER(atomic_fetch_add_relaxed(1, &dummy), false); + KCSAN_EXPECT_READ_BARRIER(test_and_set_bit(0, &test_var), true); + KCSAN_EXPECT_READ_BARRIER(test_and_clear_bit(0, &test_var), true); + KCSAN_EXPECT_READ_BARRIER(test_and_change_bit(0, &test_var), true); + KCSAN_EXPECT_READ_BARRIER(clear_bit_unlock(0, &test_var), true); + KCSAN_EXPECT_READ_BARRIER(__clear_bit_unlock(0, &test_var), true); + KCSAN_EXPECT_READ_BARRIER(arch_spin_lock(&arch_spinlock), false); + KCSAN_EXPECT_READ_BARRIER(arch_spin_unlock(&arch_spinlock), true); + KCSAN_EXPECT_READ_BARRIER(spin_lock(&test_spinlock), false); + KCSAN_EXPECT_READ_BARRIER(spin_unlock(&test_spinlock), true); + KCSAN_EXPECT_READ_BARRIER(mutex_lock(&test_mutex), false); + KCSAN_EXPECT_READ_BARRIER(mutex_unlock(&test_mutex), true); + + KCSAN_EXPECT_WRITE_BARRIER(mb(), true); + KCSAN_EXPECT_WRITE_BARRIER(wmb(), true); + KCSAN_EXPECT_WRITE_BARRIER(rmb(), false); + KCSAN_EXPECT_WRITE_BARRIER(smp_mb(), true); + KCSAN_EXPECT_WRITE_BARRIER(smp_wmb(), true); + KCSAN_EXPECT_WRITE_BARRIER(smp_rmb(), false); + KCSAN_EXPECT_WRITE_BARRIER(dma_wmb(), true); + KCSAN_EXPECT_WRITE_BARRIER(dma_rmb(), false); + KCSAN_EXPECT_WRITE_BARRIER(smp_mb__before_atomic(), true); + KCSAN_EXPECT_WRITE_BARRIER(smp_mb__after_atomic(), true); + KCSAN_EXPECT_WRITE_BARRIER(smp_mb__after_spinlock(), true); + KCSAN_EXPECT_WRITE_BARRIER(smp_store_mb(test_var, 0), true); + KCSAN_EXPECT_WRITE_BARRIER(smp_load_acquire(&test_var), false); + KCSAN_EXPECT_WRITE_BARRIER(smp_store_release(&test_var, 0), true); + KCSAN_EXPECT_WRITE_BARRIER(xchg(&test_var, 0), true); + KCSAN_EXPECT_WRITE_BARRIER(xchg_release(&test_var, 0), true); + KCSAN_EXPECT_WRITE_BARRIER(xchg_relaxed(&test_var, 0), false); + KCSAN_EXPECT_WRITE_BARRIER(cmpxchg(&test_var, 0, 0), true); + KCSAN_EXPECT_WRITE_BARRIER(cmpxchg_release(&test_var, 0, 0), true); + KCSAN_EXPECT_WRITE_BARRIER(cmpxchg_relaxed(&test_var, 0, 0), false); + KCSAN_EXPECT_WRITE_BARRIER(atomic_read(&dummy), false); + KCSAN_EXPECT_WRITE_BARRIER(atomic_read_acquire(&dummy), false); + KCSAN_EXPECT_WRITE_BARRIER(atomic_set(&dummy, 0), false); + KCSAN_EXPECT_WRITE_BARRIER(atomic_set_release(&dummy, 0), true); + KCSAN_EXPECT_WRITE_BARRIER(atomic_add(1, &dummy), false); + KCSAN_EXPECT_WRITE_BARRIER(atomic_add_return(1, &dummy), true); + KCSAN_EXPECT_WRITE_BARRIER(atomic_add_return_acquire(1, &dummy), false); + KCSAN_EXPECT_WRITE_BARRIER(atomic_add_return_release(1, &dummy), true); + KCSAN_EXPECT_WRITE_BARRIER(atomic_add_return_relaxed(1, &dummy), false); + KCSAN_EXPECT_WRITE_BARRIER(atomic_fetch_add(1, &dummy), true); + KCSAN_EXPECT_WRITE_BARRIER(atomic_fetch_add_acquire(1, &dummy), false); + KCSAN_EXPECT_WRITE_BARRIER(atomic_fetch_add_release(1, &dummy), true); + KCSAN_EXPECT_WRITE_BARRIER(atomic_fetch_add_relaxed(1, &dummy), false); + KCSAN_EXPECT_WRITE_BARRIER(test_and_set_bit(0, &test_var), true); + KCSAN_EXPECT_WRITE_BARRIER(test_and_clear_bit(0, &test_var), true); + KCSAN_EXPECT_WRITE_BARRIER(test_and_change_bit(0, &test_var), true); + KCSAN_EXPECT_WRITE_BARRIER(clear_bit_unlock(0, &test_var), true); + KCSAN_EXPECT_WRITE_BARRIER(__clear_bit_unlock(0, &test_var), true); + KCSAN_EXPECT_WRITE_BARRIER(arch_spin_lock(&arch_spinlock), false); + KCSAN_EXPECT_WRITE_BARRIER(arch_spin_unlock(&arch_spinlock), true); + KCSAN_EXPECT_WRITE_BARRIER(spin_lock(&test_spinlock), false); + KCSAN_EXPECT_WRITE_BARRIER(spin_unlock(&test_spinlock), true); + KCSAN_EXPECT_WRITE_BARRIER(mutex_lock(&test_mutex), false); + KCSAN_EXPECT_WRITE_BARRIER(mutex_unlock(&test_mutex), true); + + KCSAN_EXPECT_RW_BARRIER(mb(), true); + KCSAN_EXPECT_RW_BARRIER(wmb(), true); + KCSAN_EXPECT_RW_BARRIER(rmb(), true); + KCSAN_EXPECT_RW_BARRIER(smp_mb(), true); + KCSAN_EXPECT_RW_BARRIER(smp_wmb(), true); + KCSAN_EXPECT_RW_BARRIER(smp_rmb(), true); + KCSAN_EXPECT_RW_BARRIER(dma_wmb(), true); + KCSAN_EXPECT_RW_BARRIER(dma_rmb(), true); + KCSAN_EXPECT_RW_BARRIER(smp_mb__before_atomic(), true); + KCSAN_EXPECT_RW_BARRIER(smp_mb__after_atomic(), true); + KCSAN_EXPECT_RW_BARRIER(smp_mb__after_spinlock(), true); + KCSAN_EXPECT_RW_BARRIER(smp_store_mb(test_var, 0), true); + KCSAN_EXPECT_RW_BARRIER(smp_load_acquire(&test_var), false); + KCSAN_EXPECT_RW_BARRIER(smp_store_release(&test_var, 0), true); + KCSAN_EXPECT_RW_BARRIER(xchg(&test_var, 0), true); + KCSAN_EXPECT_RW_BARRIER(xchg_release(&test_var, 0), true); + KCSAN_EXPECT_RW_BARRIER(xchg_relaxed(&test_var, 0), false); + KCSAN_EXPECT_RW_BARRIER(cmpxchg(&test_var, 0, 0), true); + KCSAN_EXPECT_RW_BARRIER(cmpxchg_release(&test_var, 0, 0), true); + KCSAN_EXPECT_RW_BARRIER(cmpxchg_relaxed(&test_var, 0, 0), false); + KCSAN_EXPECT_RW_BARRIER(atomic_read(&dummy), false); + KCSAN_EXPECT_RW_BARRIER(atomic_read_acquire(&dummy), false); + KCSAN_EXPECT_RW_BARRIER(atomic_set(&dummy, 0), false); + KCSAN_EXPECT_RW_BARRIER(atomic_set_release(&dummy, 0), true); + KCSAN_EXPECT_RW_BARRIER(atomic_add(1, &dummy), false); + KCSAN_EXPECT_RW_BARRIER(atomic_add_return(1, &dummy), true); + KCSAN_EXPECT_RW_BARRIER(atomic_add_return_acquire(1, &dummy), false); + KCSAN_EXPECT_RW_BARRIER(atomic_add_return_release(1, &dummy), true); + KCSAN_EXPECT_RW_BARRIER(atomic_add_return_relaxed(1, &dummy), false); + KCSAN_EXPECT_RW_BARRIER(atomic_fetch_add(1, &dummy), true); + KCSAN_EXPECT_RW_BARRIER(atomic_fetch_add_acquire(1, &dummy), false); + KCSAN_EXPECT_RW_BARRIER(atomic_fetch_add_release(1, &dummy), true); + KCSAN_EXPECT_RW_BARRIER(atomic_fetch_add_relaxed(1, &dummy), false); + KCSAN_EXPECT_RW_BARRIER(test_and_set_bit(0, &test_var), true); + KCSAN_EXPECT_RW_BARRIER(test_and_clear_bit(0, &test_var), true); + KCSAN_EXPECT_RW_BARRIER(test_and_change_bit(0, &test_var), true); + KCSAN_EXPECT_RW_BARRIER(clear_bit_unlock(0, &test_var), true); + KCSAN_EXPECT_RW_BARRIER(__clear_bit_unlock(0, &test_var), true); + KCSAN_EXPECT_RW_BARRIER(arch_spin_lock(&arch_spinlock), false); + KCSAN_EXPECT_RW_BARRIER(arch_spin_unlock(&arch_spinlock), true); + KCSAN_EXPECT_RW_BARRIER(spin_lock(&test_spinlock), false); + KCSAN_EXPECT_RW_BARRIER(spin_unlock(&test_spinlock), true); + KCSAN_EXPECT_RW_BARRIER(mutex_lock(&test_mutex), false); + KCSAN_EXPECT_RW_BARRIER(mutex_unlock(&test_mutex), true); + +#ifdef clear_bit_unlock_is_negative_byte + KCSAN_EXPECT_READ_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true); + KCSAN_EXPECT_WRITE_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true); + KCSAN_EXPECT_RW_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true); +#endif + kcsan_nestable_atomic_end(); +} + +/* Simple test with normal data race. */ +__no_kcsan +static void test_basic(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + struct expect_report never = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect = false; + bool match_never = false; + + begin_test_checks(test_kernel_write, test_kernel_read); + do { + match_expect |= report_matches(&expect); + match_never = report_matches(&never); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_TRUE(test, match_expect); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* + * Stress KCSAN with lots of concurrent races on different addresses until + * timeout. + */ +__no_kcsan +static void test_concurrent_races(struct kunit *test) +{ + struct expect_report expect = { + .access = { + /* NULL will match any address. */ + { test_kernel_rmw_array, NULL, 0, __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) }, + { test_kernel_rmw_array, NULL, 0, __KCSAN_ACCESS_RW(0) }, + }, + }; + struct expect_report never = { + .access = { + { test_kernel_rmw_array, NULL, 0, 0 }, + { test_kernel_rmw_array, NULL, 0, 0 }, + }, + }; + bool match_expect = false; + bool match_never = false; + + begin_test_checks(test_kernel_rmw_array, test_kernel_rmw_array); + do { + match_expect |= report_matches(&expect); + match_never |= report_matches(&never); + } while (!end_test_checks(false)); + KUNIT_EXPECT_TRUE(test, match_expect); /* Sanity check matches exist. */ + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test the KCSAN_REPORT_VALUE_CHANGE_ONLY option. */ +__no_kcsan +static void test_novalue_change(struct kunit *test) +{ + struct expect_report expect_rw = { + .access = { + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + struct expect_report expect_ww = { + .access = { + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + test_kernel_write_nochange(); /* Reset value. */ + begin_test_checks(test_kernel_write_nochange, test_kernel_read); + do { + match_expect = report_matches(&expect_rw) || report_matches(&expect_ww); + } while (!end_test_checks(match_expect)); + if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY)) + KUNIT_EXPECT_FALSE(test, match_expect); + else + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* + * Test that the rules where the KCSAN_REPORT_VALUE_CHANGE_ONLY option should + * never apply work. + */ +__no_kcsan +static void test_novalue_change_exception(struct kunit *test) +{ + struct expect_report expect_rw = { + .access = { + { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + struct expect_report expect_ww = { + .access = { + { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + test_kernel_write_nochange_rcu(); /* Reset value. */ + begin_test_checks(test_kernel_write_nochange_rcu, test_kernel_read); + do { + match_expect = report_matches(&expect_rw) || report_matches(&expect_ww); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* Test that data races of unknown origin are reported. */ +__no_kcsan +static void test_unknown_origin(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { NULL }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_uninstrumented, test_kernel_read); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN)) + KUNIT_EXPECT_TRUE(test, match_expect); + else + KUNIT_EXPECT_FALSE(test, match_expect); +} + +/* Test KCSAN_ASSUME_PLAIN_WRITES_ATOMIC if it is selected. */ +__no_kcsan +static void test_write_write_assume_atomic(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write, test_kernel_write); + do { + sink_value(READ_ONCE(test_var)); /* induce value-change */ + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) + KUNIT_EXPECT_FALSE(test, match_expect); + else + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* + * Test that data races with writes larger than word-size are always reported, + * even if KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected. + */ +__no_kcsan +static void test_write_write_struct(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_struct, test_kernel_write_struct); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* + * Test that data races where only one write is larger than word-size are always + * reported, even if KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected. + */ +__no_kcsan +static void test_write_write_struct_part(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_write_struct_part, &test_struct.val[3], sizeof(test_struct.val[3]), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_struct, test_kernel_write_struct_part); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* Test that races with atomic accesses never result in reports. */ +__no_kcsan +static void test_read_atomic_write_atomic(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_read_atomic, test_kernel_write_atomic); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test that a race with an atomic and plain access result in reports. */ +__no_kcsan +static void test_read_plain_atomic_write(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { test_kernel_write_atomic, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC }, + }, + }; + bool match_expect = false; + + KCSAN_TEST_REQUIRES(test, !IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)); + + begin_test_checks(test_kernel_read, test_kernel_write_atomic); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* Test that atomic RMWs generate correct report. */ +__no_kcsan +static void test_read_plain_atomic_rmw(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { test_kernel_atomic_rmw, &test_var, sizeof(test_var), + KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC }, + }, + }; + bool match_expect = false; + + KCSAN_TEST_REQUIRES(test, !IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)); + + begin_test_checks(test_kernel_read, test_kernel_atomic_rmw); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* Zero-sized accesses should never cause data race reports. */ +__no_kcsan +static void test_zero_size_access(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + }, + }; + struct expect_report never = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_read_struct_zero_size, &test_struct.val[3], 0, 0 }, + }, + }; + bool match_expect = false; + bool match_never = false; + + begin_test_checks(test_kernel_write_struct, test_kernel_read_struct_zero_size); + do { + match_expect |= report_matches(&expect); + match_never = report_matches(&never); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_TRUE(test, match_expect); /* Sanity check. */ + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test the data_race() macro. */ +__no_kcsan +static void test_data_race(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_data_race, test_kernel_data_race); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +__no_kcsan +static void test_assert_exclusive_writer(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_assert_writer, test_kernel_write_nochange); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +__no_kcsan +static void test_assert_exclusive_access(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_assert_access, test_kernel_read); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +__no_kcsan +static void test_assert_exclusive_access_writer(struct kunit *test) +{ + struct expect_report expect_access_writer = { + .access = { + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + }, + }; + struct expect_report expect_access_access = { + .access = { + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + }, + }; + struct expect_report never = { + .access = { + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + }, + }; + bool match_expect_access_writer = false; + bool match_expect_access_access = false; + bool match_never = false; + + begin_test_checks(test_kernel_assert_access, test_kernel_assert_writer); + do { + match_expect_access_writer |= report_matches(&expect_access_writer); + match_expect_access_access |= report_matches(&expect_access_access); + match_never |= report_matches(&never); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_TRUE(test, match_expect_access_writer); + KUNIT_EXPECT_TRUE(test, match_expect_access_access); + KUNIT_EXPECT_FALSE(test, match_never); +} + +__no_kcsan +static void test_assert_exclusive_bits_change(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_assert_bits_change, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + { test_kernel_change_bits, &test_var, sizeof(test_var), + KCSAN_ACCESS_WRITE | (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) ? 0 : KCSAN_ACCESS_ATOMIC) }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_assert_bits_change, test_kernel_change_bits); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +__no_kcsan +static void test_assert_exclusive_bits_nochange(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_assert_bits_nochange, test_kernel_change_bits); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +__no_kcsan +static void test_assert_exclusive_writer_scoped(struct kunit *test) +{ + struct expect_report expect_start = { + .access = { + { test_kernel_assert_writer_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + struct expect_report expect_inscope = { + .access = { + { test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect_start = false; + bool match_expect_inscope = false; + + begin_test_checks(test_kernel_assert_writer_scoped, test_kernel_write_nochange); + do { + match_expect_start |= report_matches(&expect_start); + match_expect_inscope |= report_matches(&expect_inscope); + } while (!end_test_checks(match_expect_inscope)); + KUNIT_EXPECT_TRUE(test, match_expect_start); + KUNIT_EXPECT_FALSE(test, match_expect_inscope); +} + +__no_kcsan +static void test_assert_exclusive_access_scoped(struct kunit *test) +{ + struct expect_report expect_start1 = { + .access = { + { test_kernel_assert_access_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + struct expect_report expect_start2 = { + .access = { expect_start1.access[0], expect_start1.access[0] }, + }; + struct expect_report expect_inscope = { + .access = { + { test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect_start = false; + bool match_expect_inscope = false; + + begin_test_checks(test_kernel_assert_access_scoped, test_kernel_read); + end_time += msecs_to_jiffies(1000); /* This test requires a bit more time. */ + do { + match_expect_start |= report_matches(&expect_start1) || report_matches(&expect_start2); + match_expect_inscope |= report_matches(&expect_inscope); + } while (!end_test_checks(match_expect_inscope)); + KUNIT_EXPECT_TRUE(test, match_expect_start); + KUNIT_EXPECT_FALSE(test, match_expect_inscope); +} + +/* + * jiffies is special (declared to be volatile) and its accesses are typically + * not marked; this test ensures that the compiler nor KCSAN gets confused about + * jiffies's declaration on different architectures. + */ +__no_kcsan +static void test_jiffies_noreport(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_jiffies_reader, test_kernel_jiffies_reader); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test that racing accesses in seqlock critical sections are not reported. */ +__no_kcsan +static void test_seqlock_noreport(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_seqlock_reader, test_kernel_seqlock_writer); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* + * Test atomic builtins work and required instrumentation functions exist. We + * also test that KCSAN understands they're atomic by racing with them via + * test_kernel_atomic_builtins(), and expect no reports. + * + * The atomic builtins _SHOULD NOT_ be used in normal kernel code! + */ +static void test_atomic_builtins(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_atomic_builtins, test_kernel_atomic_builtins); + do { + long tmp; + + kcsan_enable_current(); + + __atomic_store_n(&test_var, 42L, __ATOMIC_RELAXED); + KUNIT_EXPECT_EQ(test, 42L, __atomic_load_n(&test_var, __ATOMIC_RELAXED)); + + KUNIT_EXPECT_EQ(test, 42L, __atomic_exchange_n(&test_var, 20, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 20L, test_var); + + tmp = 20L; + KUNIT_EXPECT_TRUE(test, __atomic_compare_exchange_n(&test_var, &tmp, 30L, + 0, __ATOMIC_RELAXED, + __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, tmp, 20L); + KUNIT_EXPECT_EQ(test, test_var, 30L); + KUNIT_EXPECT_FALSE(test, __atomic_compare_exchange_n(&test_var, &tmp, 40L, + 1, __ATOMIC_RELAXED, + __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, tmp, 30L); + KUNIT_EXPECT_EQ(test, test_var, 30L); + + KUNIT_EXPECT_EQ(test, 30L, __atomic_fetch_add(&test_var, 1, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 31L, __atomic_fetch_sub(&test_var, 1, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 30L, __atomic_fetch_and(&test_var, 0xf, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 14L, __atomic_fetch_xor(&test_var, 0xf, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 1L, __atomic_fetch_or(&test_var, 0xf0, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 241L, __atomic_fetch_nand(&test_var, 0xf, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, -2L, test_var); + + __atomic_thread_fence(__ATOMIC_SEQ_CST); + __atomic_signal_fence(__ATOMIC_SEQ_CST); + + kcsan_disable_current(); + + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +__no_kcsan +static void test_1bit_value_change(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { test_kernel_xor_1bit, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) }, + }, + }; + bool match = false; + + begin_test_checks(test_kernel_read, test_kernel_xor_1bit); + do { + match = IS_ENABLED(CONFIG_KCSAN_PERMISSIVE) + ? report_available() + : report_matches(&expect); + } while (!end_test_checks(match)); + if (IS_ENABLED(CONFIG_KCSAN_PERMISSIVE)) + KUNIT_EXPECT_FALSE(test, match); + else + KUNIT_EXPECT_TRUE(test, match); +} + +__no_kcsan +static void test_correct_barrier(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_with_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) }, + { test_kernel_with_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(0) }, + }, + }; + bool match_expect = false; + + test_struct.val[0] = 0; /* init unlocked */ + begin_test_checks(test_kernel_with_memorder, test_kernel_with_memorder); + do { + match_expect = report_matches_any_reordered(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_FALSE(test, match_expect); +} + +__no_kcsan +static void test_missing_barrier(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_wrong_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) }, + { test_kernel_wrong_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(0) }, + }, + }; + bool match_expect = false; + + test_struct.val[0] = 0; /* init unlocked */ + begin_test_checks(test_kernel_wrong_memorder, test_kernel_wrong_memorder); + do { + match_expect = report_matches_any_reordered(&expect); + } while (!end_test_checks(match_expect)); + if (IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY)) + KUNIT_EXPECT_TRUE(test, match_expect); + else + KUNIT_EXPECT_FALSE(test, match_expect); +} + +__no_kcsan +static void test_atomic_builtins_correct_barrier(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_atomic_builtin_with_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) }, + { test_kernel_atomic_builtin_with_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(0) }, + }, + }; + bool match_expect = false; + + test_struct.val[0] = 0; /* init unlocked */ + begin_test_checks(test_kernel_atomic_builtin_with_memorder, + test_kernel_atomic_builtin_with_memorder); + do { + match_expect = report_matches_any_reordered(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_FALSE(test, match_expect); +} + +__no_kcsan +static void test_atomic_builtins_missing_barrier(struct kunit *test) +{ + struct expect_report expect = { + .access = { + { test_kernel_atomic_builtin_wrong_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) }, + { test_kernel_atomic_builtin_wrong_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(0) }, + }, + }; + bool match_expect = false; + + test_struct.val[0] = 0; /* init unlocked */ + begin_test_checks(test_kernel_atomic_builtin_wrong_memorder, + test_kernel_atomic_builtin_wrong_memorder); + do { + match_expect = report_matches_any_reordered(&expect); + } while (!end_test_checks(match_expect)); + if (IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY)) + KUNIT_EXPECT_TRUE(test, match_expect); + else + KUNIT_EXPECT_FALSE(test, match_expect); +} + +/* + * Generate thread counts for all test cases. Values generated are in interval + * [2, 5] followed by exponentially increasing thread counts from 8 to 32. + * + * The thread counts are chosen to cover potentially interesting boundaries and + * corner cases (2 to 5), and then stress the system with larger counts. + */ +static const void *nthreads_gen_params(const void *prev, char *desc) +{ + long nthreads = (long)prev; + + if (nthreads < 0 || nthreads >= 32) + nthreads = 0; /* stop */ + else if (!nthreads) + nthreads = 2; /* initial value */ + else if (nthreads < 5) + nthreads++; + else if (nthreads == 5) + nthreads = 8; + else + nthreads *= 2; + + if (!preempt_model_preemptible() || + !IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER)) { + /* + * Without any preemption, keep 2 CPUs free for other tasks, one + * of which is the main test case function checking for + * completion or failure. + */ + const long min_unused_cpus = preempt_model_none() ? 2 : 0; + const long min_required_cpus = 2 + min_unused_cpus; + + if (num_online_cpus() < min_required_cpus) { + pr_err_once("Too few online CPUs (%u < %ld) for test\n", + num_online_cpus(), min_required_cpus); + nthreads = 0; + } else if (nthreads >= num_online_cpus() - min_unused_cpus) { + /* Use negative value to indicate last param. */ + nthreads = -(num_online_cpus() - min_unused_cpus); + pr_warn_once("Limiting number of threads to %ld (only %d online CPUs)\n", + -nthreads, num_online_cpus()); + } + } + + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "threads=%ld", abs(nthreads)); + return (void *)nthreads; +} + +#define KCSAN_KUNIT_CASE(test_name) KUNIT_CASE_PARAM(test_name, nthreads_gen_params) +static struct kunit_case kcsan_test_cases[] = { + KUNIT_CASE(test_barrier_nothreads), + KCSAN_KUNIT_CASE(test_basic), + KCSAN_KUNIT_CASE(test_concurrent_races), + KCSAN_KUNIT_CASE(test_novalue_change), + KCSAN_KUNIT_CASE(test_novalue_change_exception), + KCSAN_KUNIT_CASE(test_unknown_origin), + KCSAN_KUNIT_CASE(test_write_write_assume_atomic), + KCSAN_KUNIT_CASE(test_write_write_struct), + KCSAN_KUNIT_CASE(test_write_write_struct_part), + KCSAN_KUNIT_CASE(test_read_atomic_write_atomic), + KCSAN_KUNIT_CASE(test_read_plain_atomic_write), + KCSAN_KUNIT_CASE(test_read_plain_atomic_rmw), + KCSAN_KUNIT_CASE(test_zero_size_access), + KCSAN_KUNIT_CASE(test_data_race), + KCSAN_KUNIT_CASE(test_assert_exclusive_writer), + KCSAN_KUNIT_CASE(test_assert_exclusive_access), + KCSAN_KUNIT_CASE(test_assert_exclusive_access_writer), + KCSAN_KUNIT_CASE(test_assert_exclusive_bits_change), + KCSAN_KUNIT_CASE(test_assert_exclusive_bits_nochange), + KCSAN_KUNIT_CASE(test_assert_exclusive_writer_scoped), + KCSAN_KUNIT_CASE(test_assert_exclusive_access_scoped), + KCSAN_KUNIT_CASE(test_jiffies_noreport), + KCSAN_KUNIT_CASE(test_seqlock_noreport), + KCSAN_KUNIT_CASE(test_atomic_builtins), + KCSAN_KUNIT_CASE(test_1bit_value_change), + KCSAN_KUNIT_CASE(test_correct_barrier), + KCSAN_KUNIT_CASE(test_missing_barrier), + KCSAN_KUNIT_CASE(test_atomic_builtins_correct_barrier), + KCSAN_KUNIT_CASE(test_atomic_builtins_missing_barrier), + {}, +}; + +/* ===== End test cases ===== */ + +/* Concurrent accesses from interrupts. */ +__no_kcsan +static void access_thread_timer(struct timer_list *timer) +{ + static atomic_t cnt = ATOMIC_INIT(0); + unsigned int idx; + void (*func)(void); + + idx = (unsigned int)atomic_inc_return(&cnt) % ARRAY_SIZE(access_kernels); + /* Acquire potential initialization. */ + func = smp_load_acquire(&access_kernels[idx]); + if (func) + func(); +} + +/* The main loop for each thread. */ +__no_kcsan +static int access_thread(void *arg) +{ + struct timer_list timer; + unsigned int cnt = 0; + unsigned int idx; + void (*func)(void); + + timer_setup_on_stack(&timer, access_thread_timer, 0); + do { + might_sleep(); + + if (!timer_pending(&timer)) + mod_timer(&timer, jiffies + 1); + else { + /* Iterate through all kernels. */ + idx = cnt++ % ARRAY_SIZE(access_kernels); + /* Acquire potential initialization. */ + func = smp_load_acquire(&access_kernels[idx]); + if (func) + func(); + } + } while (!torture_must_stop()); + del_timer_sync(&timer); + destroy_timer_on_stack(&timer); + + torture_kthread_stopping("access_thread"); + return 0; +} + +__no_kcsan +static int test_init(struct kunit *test) +{ + unsigned long flags; + int nthreads; + int i; + + spin_lock_irqsave(&observed.lock, flags); + for (i = 0; i < ARRAY_SIZE(observed.lines); ++i) + observed.lines[i][0] = '\0'; + observed.nlines = 0; + spin_unlock_irqrestore(&observed.lock, flags); + + if (strstr(test->name, "nothreads")) + return 0; + + if (!torture_init_begin((char *)test->name, 1)) + return -EBUSY; + + if (WARN_ON(threads)) + goto err; + + for (i = 0; i < ARRAY_SIZE(access_kernels); ++i) { + if (WARN_ON(access_kernels[i])) + goto err; + } + + nthreads = abs((long)test->param_value); + if (WARN_ON(!nthreads)) + goto err; + + threads = kcalloc(nthreads + 1, sizeof(struct task_struct *), GFP_KERNEL); + if (WARN_ON(!threads)) + goto err; + + threads[nthreads] = NULL; + for (i = 0; i < nthreads; ++i) { + if (torture_create_kthread(access_thread, NULL, threads[i])) + goto err; + } + + torture_init_end(); + + return 0; + +err: + kfree(threads); + threads = NULL; + torture_init_end(); + return -EINVAL; +} + +__no_kcsan +static void test_exit(struct kunit *test) +{ + struct task_struct **stop_thread; + int i; + + if (strstr(test->name, "nothreads")) + return; + + if (torture_cleanup_begin()) + return; + + for (i = 0; i < ARRAY_SIZE(access_kernels); ++i) + WRITE_ONCE(access_kernels[i], NULL); + + if (threads) { + for (stop_thread = threads; *stop_thread; stop_thread++) + torture_stop_kthread(reader_thread, *stop_thread); + + kfree(threads); + threads = NULL; + } + + torture_cleanup_end(); +} + +__no_kcsan +static void register_tracepoints(struct tracepoint *tp, void *ignore) +{ + check_trace_callback_type_console(probe_console); + if (!strcmp(tp->name, "console")) + WARN_ON(tracepoint_probe_register(tp, probe_console, NULL)); +} + +__no_kcsan +static void unregister_tracepoints(struct tracepoint *tp, void *ignore) +{ + if (!strcmp(tp->name, "console")) + tracepoint_probe_unregister(tp, probe_console, NULL); +} + +static int kcsan_suite_init(struct kunit_suite *suite) +{ + /* + * Because we want to be able to build the test as a module, we need to + * iterate through all known tracepoints, since the static registration + * won't work here. + */ + for_each_kernel_tracepoint(register_tracepoints, NULL); + return 0; +} + +static void kcsan_suite_exit(struct kunit_suite *suite) +{ + for_each_kernel_tracepoint(unregister_tracepoints, NULL); + tracepoint_synchronize_unregister(); +} + +static struct kunit_suite kcsan_test_suite = { + .name = "kcsan", + .test_cases = kcsan_test_cases, + .init = test_init, + .exit = test_exit, + .suite_init = kcsan_suite_init, + .suite_exit = kcsan_suite_exit, +}; + +kunit_test_suites(&kcsan_test_suite); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Marco Elver <elver@google.com>"); diff --git a/kernel/kcsan/permissive.h b/kernel/kcsan/permissive.h new file mode 100644 index 000000000..2c01fe4a5 --- /dev/null +++ b/kernel/kcsan/permissive.h @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Special rules for ignoring entire classes of data-racy memory accesses. None + * of the rules here imply that such data races are generally safe! + * + * All rules in this file can be configured via CONFIG_KCSAN_PERMISSIVE. Keep + * them separate from core code to make it easier to audit. + * + * Copyright (C) 2019, Google LLC. + */ + +#ifndef _KERNEL_KCSAN_PERMISSIVE_H +#define _KERNEL_KCSAN_PERMISSIVE_H + +#include <linux/bitops.h> +#include <linux/sched.h> +#include <linux/types.h> + +/* + * Access ignore rules based on address. + */ +static __always_inline bool kcsan_ignore_address(const volatile void *ptr) +{ + if (!IS_ENABLED(CONFIG_KCSAN_PERMISSIVE)) + return false; + + /* + * Data-racy bitops on current->flags are too common, ignore completely + * for now. + */ + return ptr == ¤t->flags; +} + +/* + * Data race ignore rules based on access type and value change patterns. + */ +static bool +kcsan_ignore_data_race(size_t size, int type, u64 old, u64 new, u64 diff) +{ + if (!IS_ENABLED(CONFIG_KCSAN_PERMISSIVE)) + return false; + + /* + * Rules here are only for plain read accesses, so that we still report + * data races between plain read-write accesses. + */ + if (type || size > sizeof(long)) + return false; + + /* + * A common pattern is checking/setting just 1 bit in a variable; for + * example: + * + * if (flags & SOME_FLAG) { ... } + * + * and elsewhere flags is updated concurrently: + * + * flags |= SOME_OTHER_FLAG; // just 1 bit + * + * While it is still recommended that such accesses be marked + * appropriately, in many cases these types of data races are so common + * that marking them all is often unrealistic and left to maintainer + * preference. + * + * The assumption in all cases is that with all known compiler + * optimizations (including those that tear accesses), because no more + * than 1 bit changed, the plain accesses are safe despite the presence + * of data races. + * + * The rules here will ignore the data races if we observe no more than + * 1 bit changed. + * + * Of course many operations can effecively change just 1 bit, but the + * general assuption that data races involving 1-bit changes can be + * tolerated still applies. + * + * And in case a true bug is missed, the bug likely manifests as a + * reportable data race elsewhere. + */ + if (hweight64(diff) == 1) { + /* + * Exception: Report data races where the values look like + * ordinary booleans (one of them was 0 and the 0th bit was + * changed) More often than not, they come with interesting + * memory ordering requirements, so let's report them. + */ + if (!((!old || !new) && diff == 1)) + return true; + } + + return false; +} + +#endif /* _KERNEL_KCSAN_PERMISSIVE_H */ diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c new file mode 100644 index 000000000..e95ce7d7a --- /dev/null +++ b/kernel/kcsan/report.c @@ -0,0 +1,715 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KCSAN reporting. + * + * Copyright (C) 2019, Google LLC. + */ + +#include <linux/debug_locks.h> +#include <linux/delay.h> +#include <linux/jiffies.h> +#include <linux/kallsyms.h> +#include <linux/kernel.h> +#include <linux/lockdep.h> +#include <linux/preempt.h> +#include <linux/printk.h> +#include <linux/sched.h> +#include <linux/spinlock.h> +#include <linux/stacktrace.h> + +#include "kcsan.h" +#include "encoding.h" + +/* + * Max. number of stack entries to show in the report. + */ +#define NUM_STACK_ENTRIES 64 + +/* Common access info. */ +struct access_info { + const volatile void *ptr; + size_t size; + int access_type; + int task_pid; + int cpu_id; + unsigned long ip; +}; + +/* + * Other thread info: communicated from other racing thread to thread that set + * up the watchpoint, which then prints the complete report atomically. + */ +struct other_info { + struct access_info ai; + unsigned long stack_entries[NUM_STACK_ENTRIES]; + int num_stack_entries; + + /* + * Optionally pass @current. Typically we do not need to pass @current + * via @other_info since just @task_pid is sufficient. Passing @current + * has additional overhead. + * + * To safely pass @current, we must either use get_task_struct/ + * put_task_struct, or stall the thread that populated @other_info. + * + * We cannot rely on get_task_struct/put_task_struct in case + * release_report() races with a task being released, and would have to + * free it in release_report(). This may result in deadlock if we want + * to use KCSAN on the allocators. + * + * Since we also want to reliably print held locks for + * CONFIG_KCSAN_VERBOSE, the current implementation stalls the thread + * that populated @other_info until it has been consumed. + */ + struct task_struct *task; +}; + +/* + * To never block any producers of struct other_info, we need as many elements + * as we have watchpoints (upper bound on concurrent races to report). + */ +static struct other_info other_infos[CONFIG_KCSAN_NUM_WATCHPOINTS + NUM_SLOTS-1]; + +/* + * Information about reported races; used to rate limit reporting. + */ +struct report_time { + /* + * The last time the race was reported. + */ + unsigned long time; + + /* + * The frames of the 2 threads; if only 1 thread is known, one frame + * will be 0. + */ + unsigned long frame1; + unsigned long frame2; +}; + +/* + * Since we also want to be able to debug allocators with KCSAN, to avoid + * deadlock, report_times cannot be dynamically resized with krealloc in + * rate_limit_report. + * + * Therefore, we use a fixed-size array, which at most will occupy a page. This + * still adequately rate limits reports, assuming that a) number of unique data + * races is not excessive, and b) occurrence of unique races within the + * same time window is limited. + */ +#define REPORT_TIMES_MAX (PAGE_SIZE / sizeof(struct report_time)) +#define REPORT_TIMES_SIZE \ + (CONFIG_KCSAN_REPORT_ONCE_IN_MS > REPORT_TIMES_MAX ? \ + REPORT_TIMES_MAX : \ + CONFIG_KCSAN_REPORT_ONCE_IN_MS) +static struct report_time report_times[REPORT_TIMES_SIZE]; + +/* + * Spinlock serializing report generation, and access to @other_infos. Although + * it could make sense to have a finer-grained locking story for @other_infos, + * report generation needs to be serialized either way, so not much is gained. + */ +static DEFINE_RAW_SPINLOCK(report_lock); + +/* + * Checks if the race identified by thread frames frame1 and frame2 has + * been reported since (now - KCSAN_REPORT_ONCE_IN_MS). + */ +static bool rate_limit_report(unsigned long frame1, unsigned long frame2) +{ + struct report_time *use_entry = &report_times[0]; + unsigned long invalid_before; + int i; + + BUILD_BUG_ON(CONFIG_KCSAN_REPORT_ONCE_IN_MS != 0 && REPORT_TIMES_SIZE == 0); + + if (CONFIG_KCSAN_REPORT_ONCE_IN_MS == 0) + return false; + + invalid_before = jiffies - msecs_to_jiffies(CONFIG_KCSAN_REPORT_ONCE_IN_MS); + + /* Check if a matching race report exists. */ + for (i = 0; i < REPORT_TIMES_SIZE; ++i) { + struct report_time *rt = &report_times[i]; + + /* + * Must always select an entry for use to store info as we + * cannot resize report_times; at the end of the scan, use_entry + * will be the oldest entry, which ideally also happened before + * KCSAN_REPORT_ONCE_IN_MS ago. + */ + if (time_before(rt->time, use_entry->time)) + use_entry = rt; + + /* + * Initially, no need to check any further as this entry as well + * as following entries have never been used. + */ + if (rt->time == 0) + break; + + /* Check if entry expired. */ + if (time_before(rt->time, invalid_before)) + continue; /* before KCSAN_REPORT_ONCE_IN_MS ago */ + + /* Reported recently, check if race matches. */ + if ((rt->frame1 == frame1 && rt->frame2 == frame2) || + (rt->frame1 == frame2 && rt->frame2 == frame1)) + return true; + } + + use_entry->time = jiffies; + use_entry->frame1 = frame1; + use_entry->frame2 = frame2; + return false; +} + +/* + * Special rules to skip reporting. + */ +static bool +skip_report(enum kcsan_value_change value_change, unsigned long top_frame) +{ + /* Should never get here if value_change==FALSE. */ + WARN_ON_ONCE(value_change == KCSAN_VALUE_CHANGE_FALSE); + + /* + * The first call to skip_report always has value_change==TRUE, since we + * cannot know the value written of an instrumented access. For the 2nd + * call there are 6 cases with CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY: + * + * 1. read watchpoint, conflicting write (value_change==TRUE): report; + * 2. read watchpoint, conflicting write (value_change==MAYBE): skip; + * 3. write watchpoint, conflicting write (value_change==TRUE): report; + * 4. write watchpoint, conflicting write (value_change==MAYBE): skip; + * 5. write watchpoint, conflicting read (value_change==MAYBE): skip; + * 6. write watchpoint, conflicting read (value_change==TRUE): report; + * + * Cases 1-4 are intuitive and expected; case 5 ensures we do not report + * data races where the write may have rewritten the same value; case 6 + * is possible either if the size is larger than what we check value + * changes for or the access type is KCSAN_ACCESS_ASSERT. + */ + if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY) && + value_change == KCSAN_VALUE_CHANGE_MAYBE) { + /* + * The access is a write, but the data value did not change. + * + * We opt-out of this filter for certain functions at request of + * maintainers. + */ + char buf[64]; + int len = scnprintf(buf, sizeof(buf), "%ps", (void *)top_frame); + + if (!strnstr(buf, "rcu_", len) && + !strnstr(buf, "_rcu", len) && + !strnstr(buf, "_srcu", len)) + return true; + } + + return kcsan_skip_report_debugfs(top_frame); +} + +static const char *get_access_type(int type) +{ + if (type & KCSAN_ACCESS_ASSERT) { + if (type & KCSAN_ACCESS_SCOPED) { + if (type & KCSAN_ACCESS_WRITE) + return "assert no accesses (reordered)"; + else + return "assert no writes (reordered)"; + } else { + if (type & KCSAN_ACCESS_WRITE) + return "assert no accesses"; + else + return "assert no writes"; + } + } + + switch (type) { + case 0: + return "read"; + case KCSAN_ACCESS_ATOMIC: + return "read (marked)"; + case KCSAN_ACCESS_WRITE: + return "write"; + case KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC: + return "write (marked)"; + case KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE: + return "read-write"; + case KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC: + return "read-write (marked)"; + case KCSAN_ACCESS_SCOPED: + return "read (reordered)"; + case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_ATOMIC: + return "read (marked, reordered)"; + case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE: + return "write (reordered)"; + case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC: + return "write (marked, reordered)"; + case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE: + return "read-write (reordered)"; + case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC: + return "read-write (marked, reordered)"; + default: + BUG(); + } +} + +static const char *get_bug_type(int type) +{ + return (type & KCSAN_ACCESS_ASSERT) != 0 ? "assert: race" : "data-race"; +} + +/* Return thread description: in task or interrupt. */ +static const char *get_thread_desc(int task_id) +{ + if (task_id != -1) { + static char buf[32]; /* safe: protected by report_lock */ + + snprintf(buf, sizeof(buf), "task %i", task_id); + return buf; + } + return "interrupt"; +} + +/* Helper to skip KCSAN-related functions in stack-trace. */ +static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries) +{ + char buf[64]; + char *cur; + int len, skip; + + for (skip = 0; skip < num_entries; ++skip) { + len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skip]); + + /* Never show tsan_* or {read,write}_once_size. */ + if (strnstr(buf, "tsan_", len) || + strnstr(buf, "_once_size", len)) + continue; + + cur = strnstr(buf, "kcsan_", len); + if (cur) { + cur += strlen("kcsan_"); + if (!str_has_prefix(cur, "test")) + continue; /* KCSAN runtime function. */ + /* KCSAN related test. */ + } + + /* + * No match for runtime functions -- @skip entries to skip to + * get to first frame of interest. + */ + break; + } + + return skip; +} + +/* + * Skips to the first entry that matches the function of @ip, and then replaces + * that entry with @ip, returning the entries to skip with @replaced containing + * the replaced entry. + */ +static int +replace_stack_entry(unsigned long stack_entries[], int num_entries, unsigned long ip, + unsigned long *replaced) +{ + unsigned long symbolsize, offset; + unsigned long target_func; + int skip; + + if (kallsyms_lookup_size_offset(ip, &symbolsize, &offset)) + target_func = ip - offset; + else + goto fallback; + + for (skip = 0; skip < num_entries; ++skip) { + unsigned long func = stack_entries[skip]; + + if (!kallsyms_lookup_size_offset(func, &symbolsize, &offset)) + goto fallback; + func -= offset; + + if (func == target_func) { + *replaced = stack_entries[skip]; + stack_entries[skip] = ip; + return skip; + } + } + +fallback: + /* Should not happen; the resulting stack trace is likely misleading. */ + WARN_ONCE(1, "Cannot find frame for %pS in stack trace", (void *)ip); + return get_stack_skipnr(stack_entries, num_entries); +} + +static int +sanitize_stack_entries(unsigned long stack_entries[], int num_entries, unsigned long ip, + unsigned long *replaced) +{ + return ip ? replace_stack_entry(stack_entries, num_entries, ip, replaced) : + get_stack_skipnr(stack_entries, num_entries); +} + +/* Compares symbolized strings of addr1 and addr2. */ +static int sym_strcmp(void *addr1, void *addr2) +{ + char buf1[64]; + char buf2[64]; + + snprintf(buf1, sizeof(buf1), "%pS", addr1); + snprintf(buf2, sizeof(buf2), "%pS", addr2); + + return strncmp(buf1, buf2, sizeof(buf1)); +} + +static void +print_stack_trace(unsigned long stack_entries[], int num_entries, unsigned long reordered_to) +{ + stack_trace_print(stack_entries, num_entries, 0); + if (reordered_to) + pr_err(" |\n +-> reordered to: %pS\n", (void *)reordered_to); +} + +static void print_verbose_info(struct task_struct *task) +{ + if (!task) + return; + + /* Restore IRQ state trace for printing. */ + kcsan_restore_irqtrace(task); + + pr_err("\n"); + debug_show_held_locks(task); + print_irqtrace_events(task); +} + +static void print_report(enum kcsan_value_change value_change, + const struct access_info *ai, + struct other_info *other_info, + u64 old, u64 new, u64 mask) +{ + unsigned long reordered_to = 0; + unsigned long stack_entries[NUM_STACK_ENTRIES] = { 0 }; + int num_stack_entries = stack_trace_save(stack_entries, NUM_STACK_ENTRIES, 1); + int skipnr = sanitize_stack_entries(stack_entries, num_stack_entries, ai->ip, &reordered_to); + unsigned long this_frame = stack_entries[skipnr]; + unsigned long other_reordered_to = 0; + unsigned long other_frame = 0; + int other_skipnr = 0; /* silence uninit warnings */ + + /* + * Must check report filter rules before starting to print. + */ + if (skip_report(KCSAN_VALUE_CHANGE_TRUE, stack_entries[skipnr])) + return; + + if (other_info) { + other_skipnr = sanitize_stack_entries(other_info->stack_entries, + other_info->num_stack_entries, + other_info->ai.ip, &other_reordered_to); + other_frame = other_info->stack_entries[other_skipnr]; + + /* @value_change is only known for the other thread */ + if (skip_report(value_change, other_frame)) + return; + } + + if (rate_limit_report(this_frame, other_frame)) + return; + + /* Print report header. */ + pr_err("==================================================================\n"); + if (other_info) { + int cmp; + + /* + * Order functions lexographically for consistent bug titles. + * Do not print offset of functions to keep title short. + */ + cmp = sym_strcmp((void *)other_frame, (void *)this_frame); + pr_err("BUG: KCSAN: %s in %ps / %ps\n", + get_bug_type(ai->access_type | other_info->ai.access_type), + (void *)(cmp < 0 ? other_frame : this_frame), + (void *)(cmp < 0 ? this_frame : other_frame)); + } else { + pr_err("BUG: KCSAN: %s in %pS\n", get_bug_type(ai->access_type), + (void *)this_frame); + } + + pr_err("\n"); + + /* Print information about the racing accesses. */ + if (other_info) { + pr_err("%s to 0x%px of %zu bytes by %s on cpu %i:\n", + get_access_type(other_info->ai.access_type), other_info->ai.ptr, + other_info->ai.size, get_thread_desc(other_info->ai.task_pid), + other_info->ai.cpu_id); + + /* Print the other thread's stack trace. */ + print_stack_trace(other_info->stack_entries + other_skipnr, + other_info->num_stack_entries - other_skipnr, + other_reordered_to); + if (IS_ENABLED(CONFIG_KCSAN_VERBOSE)) + print_verbose_info(other_info->task); + + pr_err("\n"); + pr_err("%s to 0x%px of %zu bytes by %s on cpu %i:\n", + get_access_type(ai->access_type), ai->ptr, ai->size, + get_thread_desc(ai->task_pid), ai->cpu_id); + } else { + pr_err("race at unknown origin, with %s to 0x%px of %zu bytes by %s on cpu %i:\n", + get_access_type(ai->access_type), ai->ptr, ai->size, + get_thread_desc(ai->task_pid), ai->cpu_id); + } + /* Print stack trace of this thread. */ + print_stack_trace(stack_entries + skipnr, num_stack_entries - skipnr, reordered_to); + if (IS_ENABLED(CONFIG_KCSAN_VERBOSE)) + print_verbose_info(current); + + /* Print observed value change. */ + if (ai->size <= 8) { + int hex_len = ai->size * 2; + u64 diff = old ^ new; + + if (mask) + diff &= mask; + if (diff) { + pr_err("\n"); + pr_err("value changed: 0x%0*llx -> 0x%0*llx\n", + hex_len, old, hex_len, new); + if (mask) { + pr_err(" bits changed: 0x%0*llx with mask 0x%0*llx\n", + hex_len, diff, hex_len, mask); + } + } + } + + /* Print report footer. */ + pr_err("\n"); + pr_err("Reported by Kernel Concurrency Sanitizer on:\n"); + dump_stack_print_info(KERN_DEFAULT); + pr_err("==================================================================\n"); + + check_panic_on_warn("KCSAN"); +} + +static void release_report(unsigned long *flags, struct other_info *other_info) +{ + /* + * Use size to denote valid/invalid, since KCSAN entirely ignores + * 0-sized accesses. + */ + other_info->ai.size = 0; + raw_spin_unlock_irqrestore(&report_lock, *flags); +} + +/* + * Sets @other_info->task and awaits consumption of @other_info. + * + * Precondition: report_lock is held. + * Postcondition: report_lock is held. + */ +static void set_other_info_task_blocking(unsigned long *flags, + const struct access_info *ai, + struct other_info *other_info) +{ + /* + * We may be instrumenting a code-path where current->state is already + * something other than TASK_RUNNING. + */ + const bool is_running = task_is_running(current); + /* + * To avoid deadlock in case we are in an interrupt here and this is a + * race with a task on the same CPU (KCSAN_INTERRUPT_WATCHER), provide a + * timeout to ensure this works in all contexts. + * + * Await approximately the worst case delay of the reporting thread (if + * we are not interrupted). + */ + int timeout = max(kcsan_udelay_task, kcsan_udelay_interrupt); + + other_info->task = current; + do { + if (is_running) { + /* + * Let lockdep know the real task is sleeping, to print + * the held locks (recall we turned lockdep off, so + * locking/unlocking @report_lock won't be recorded). + */ + set_current_state(TASK_UNINTERRUPTIBLE); + } + raw_spin_unlock_irqrestore(&report_lock, *flags); + /* + * We cannot call schedule() since we also cannot reliably + * determine if sleeping here is permitted -- see in_atomic(). + */ + + udelay(1); + raw_spin_lock_irqsave(&report_lock, *flags); + if (timeout-- < 0) { + /* + * Abort. Reset @other_info->task to NULL, since it + * appears the other thread is still going to consume + * it. It will result in no verbose info printed for + * this task. + */ + other_info->task = NULL; + break; + } + /* + * If invalid, or @ptr nor @current matches, then @other_info + * has been consumed and we may continue. If not, retry. + */ + } while (other_info->ai.size && other_info->ai.ptr == ai->ptr && + other_info->task == current); + if (is_running) + set_current_state(TASK_RUNNING); +} + +/* Populate @other_info; requires that the provided @other_info not in use. */ +static void prepare_report_producer(unsigned long *flags, + const struct access_info *ai, + struct other_info *other_info) +{ + raw_spin_lock_irqsave(&report_lock, *flags); + + /* + * The same @other_infos entry cannot be used concurrently, because + * there is a one-to-one mapping to watchpoint slots (@watchpoints in + * core.c), and a watchpoint is only released for reuse after reporting + * is done by the consumer of @other_info. Therefore, it is impossible + * for another concurrent prepare_report_producer() to set the same + * @other_info, and are guaranteed exclusivity for the @other_infos + * entry pointed to by @other_info. + * + * To check this property holds, size should never be non-zero here, + * because every consumer of struct other_info resets size to 0 in + * release_report(). + */ + WARN_ON(other_info->ai.size); + + other_info->ai = *ai; + other_info->num_stack_entries = stack_trace_save(other_info->stack_entries, NUM_STACK_ENTRIES, 2); + + if (IS_ENABLED(CONFIG_KCSAN_VERBOSE)) + set_other_info_task_blocking(flags, ai, other_info); + + raw_spin_unlock_irqrestore(&report_lock, *flags); +} + +/* Awaits producer to fill @other_info and then returns. */ +static bool prepare_report_consumer(unsigned long *flags, + const struct access_info *ai, + struct other_info *other_info) +{ + + raw_spin_lock_irqsave(&report_lock, *flags); + while (!other_info->ai.size) { /* Await valid @other_info. */ + raw_spin_unlock_irqrestore(&report_lock, *flags); + cpu_relax(); + raw_spin_lock_irqsave(&report_lock, *flags); + } + + /* Should always have a matching access based on watchpoint encoding. */ + if (WARN_ON(!matching_access((unsigned long)other_info->ai.ptr & WATCHPOINT_ADDR_MASK, other_info->ai.size, + (unsigned long)ai->ptr & WATCHPOINT_ADDR_MASK, ai->size))) + goto discard; + + if (!matching_access((unsigned long)other_info->ai.ptr, other_info->ai.size, + (unsigned long)ai->ptr, ai->size)) { + /* + * If the actual accesses to not match, this was a false + * positive due to watchpoint encoding. + */ + atomic_long_inc(&kcsan_counters[KCSAN_COUNTER_ENCODING_FALSE_POSITIVES]); + goto discard; + } + + return true; + +discard: + release_report(flags, other_info); + return false; +} + +static struct access_info prepare_access_info(const volatile void *ptr, size_t size, + int access_type, unsigned long ip) +{ + return (struct access_info) { + .ptr = ptr, + .size = size, + .access_type = access_type, + .task_pid = in_task() ? task_pid_nr(current) : -1, + .cpu_id = raw_smp_processor_id(), + /* Only replace stack entry with @ip if scoped access. */ + .ip = (access_type & KCSAN_ACCESS_SCOPED) ? ip : 0, + }; +} + +void kcsan_report_set_info(const volatile void *ptr, size_t size, int access_type, + unsigned long ip, int watchpoint_idx) +{ + const struct access_info ai = prepare_access_info(ptr, size, access_type, ip); + unsigned long flags; + + kcsan_disable_current(); + lockdep_off(); /* See kcsan_report_known_origin(). */ + + prepare_report_producer(&flags, &ai, &other_infos[watchpoint_idx]); + + lockdep_on(); + kcsan_enable_current(); +} + +void kcsan_report_known_origin(const volatile void *ptr, size_t size, int access_type, + unsigned long ip, enum kcsan_value_change value_change, + int watchpoint_idx, u64 old, u64 new, u64 mask) +{ + const struct access_info ai = prepare_access_info(ptr, size, access_type, ip); + struct other_info *other_info = &other_infos[watchpoint_idx]; + unsigned long flags = 0; + + kcsan_disable_current(); + /* + * Because we may generate reports when we're in scheduler code, the use + * of printk() could deadlock. Until such time that all printing code + * called in print_report() is scheduler-safe, accept the risk, and just + * get our message out. As such, also disable lockdep to hide the + * warning, and avoid disabling lockdep for the rest of the kernel. + */ + lockdep_off(); + + if (!prepare_report_consumer(&flags, &ai, other_info)) + goto out; + /* + * Never report if value_change is FALSE, only when it is + * either TRUE or MAYBE. In case of MAYBE, further filtering may + * be done once we know the full stack trace in print_report(). + */ + if (value_change != KCSAN_VALUE_CHANGE_FALSE) + print_report(value_change, &ai, other_info, old, new, mask); + + release_report(&flags, other_info); +out: + lockdep_on(); + kcsan_enable_current(); +} + +void kcsan_report_unknown_origin(const volatile void *ptr, size_t size, int access_type, + unsigned long ip, u64 old, u64 new, u64 mask) +{ + const struct access_info ai = prepare_access_info(ptr, size, access_type, ip); + unsigned long flags; + + kcsan_disable_current(); + lockdep_off(); /* See kcsan_report_known_origin(). */ + + raw_spin_lock_irqsave(&report_lock, flags); + print_report(KCSAN_VALUE_CHANGE_TRUE, &ai, NULL, old, new, mask); + raw_spin_unlock_irqrestore(&report_lock, flags); + + lockdep_on(); + kcsan_enable_current(); +} diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c new file mode 100644 index 000000000..00cdf8fa5 --- /dev/null +++ b/kernel/kcsan/selftest.c @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KCSAN short boot-time selftests. + * + * Copyright (C) 2019, Google LLC. + */ + +#define pr_fmt(fmt) "kcsan: " fmt + +#include <linux/atomic.h> +#include <linux/bitops.h> +#include <linux/init.h> +#include <linux/kcsan-checks.h> +#include <linux/kernel.h> +#include <linux/printk.h> +#include <linux/random.h> +#include <linux/sched.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include "encoding.h" + +#define ITERS_PER_TEST 2000 + +/* Test requirements. */ +static bool __init test_requires(void) +{ + /* random should be initialized for the below tests */ + return get_random_u32() + get_random_u32() != 0; +} + +/* + * Test watchpoint encode and decode: check that encoding some access's info, + * and then subsequent decode preserves the access's info. + */ +static bool __init test_encode_decode(void) +{ + int i; + + for (i = 0; i < ITERS_PER_TEST; ++i) { + size_t size = prandom_u32_max(MAX_ENCODABLE_SIZE) + 1; + bool is_write = !!prandom_u32_max(2); + unsigned long verif_masked_addr; + long encoded_watchpoint; + bool verif_is_write; + unsigned long addr; + size_t verif_size; + + get_random_bytes(&addr, sizeof(addr)); + if (addr < PAGE_SIZE) + addr = PAGE_SIZE; + + if (WARN_ON(!check_encodable(addr, size))) + return false; + + encoded_watchpoint = encode_watchpoint(addr, size, is_write); + + /* Check special watchpoints */ + if (WARN_ON(decode_watchpoint(INVALID_WATCHPOINT, &verif_masked_addr, &verif_size, &verif_is_write))) + return false; + if (WARN_ON(decode_watchpoint(CONSUMED_WATCHPOINT, &verif_masked_addr, &verif_size, &verif_is_write))) + return false; + + /* Check decoding watchpoint returns same data */ + if (WARN_ON(!decode_watchpoint(encoded_watchpoint, &verif_masked_addr, &verif_size, &verif_is_write))) + return false; + if (WARN_ON(verif_masked_addr != (addr & WATCHPOINT_ADDR_MASK))) + goto fail; + if (WARN_ON(verif_size != size)) + goto fail; + if (WARN_ON(is_write != verif_is_write)) + goto fail; + + continue; +fail: + pr_err("%s fail: %s %zu bytes @ %lx -> encoded: %lx -> %s %zu bytes @ %lx\n", + __func__, is_write ? "write" : "read", size, addr, encoded_watchpoint, + verif_is_write ? "write" : "read", verif_size, verif_masked_addr); + return false; + } + + return true; +} + +/* Test access matching function. */ +static bool __init test_matching_access(void) +{ + if (WARN_ON(!matching_access(10, 1, 10, 1))) + return false; + if (WARN_ON(!matching_access(10, 2, 11, 1))) + return false; + if (WARN_ON(!matching_access(10, 1, 9, 2))) + return false; + if (WARN_ON(matching_access(10, 1, 11, 1))) + return false; + if (WARN_ON(matching_access(9, 1, 10, 1))) + return false; + + /* + * An access of size 0 could match another access, as demonstrated here. + * Rather than add more comparisons to 'matching_access()', which would + * end up in the fast-path for *all* checks, check_access() simply + * returns for all accesses of size 0. + */ + if (WARN_ON(!matching_access(8, 8, 12, 0))) + return false; + + return true; +} + +/* + * Correct memory barrier instrumentation is critical to avoiding false + * positives: simple test to check at boot certain barriers are always properly + * instrumented. See kcsan_test for a more complete test. + */ +static DEFINE_SPINLOCK(test_spinlock); +static bool __init test_barrier(void) +{ +#ifdef CONFIG_KCSAN_WEAK_MEMORY + struct kcsan_scoped_access *reorder_access = ¤t->kcsan_ctx.reorder_access; +#else + struct kcsan_scoped_access *reorder_access = NULL; +#endif + bool ret = true; + arch_spinlock_t arch_spinlock = __ARCH_SPIN_LOCK_UNLOCKED; + atomic_t dummy; + long test_var; + + if (!reorder_access || !IS_ENABLED(CONFIG_SMP)) + return true; + +#define __KCSAN_CHECK_BARRIER(access_type, barrier, name) \ + do { \ + reorder_access->type = (access_type) | KCSAN_ACCESS_SCOPED; \ + reorder_access->size = 1; \ + barrier; \ + if (reorder_access->size != 0) { \ + pr_err("improperly instrumented type=(" #access_type "): " name "\n"); \ + ret = false; \ + } \ + } while (0) +#define KCSAN_CHECK_READ_BARRIER(b) __KCSAN_CHECK_BARRIER(0, b, #b) +#define KCSAN_CHECK_WRITE_BARRIER(b) __KCSAN_CHECK_BARRIER(KCSAN_ACCESS_WRITE, b, #b) +#define KCSAN_CHECK_RW_BARRIER(b) __KCSAN_CHECK_BARRIER(KCSAN_ACCESS_WRITE | KCSAN_ACCESS_COMPOUND, b, #b) + + kcsan_nestable_atomic_begin(); /* No watchpoints in called functions. */ + + KCSAN_CHECK_READ_BARRIER(mb()); + KCSAN_CHECK_READ_BARRIER(rmb()); + KCSAN_CHECK_READ_BARRIER(smp_mb()); + KCSAN_CHECK_READ_BARRIER(smp_rmb()); + KCSAN_CHECK_READ_BARRIER(dma_rmb()); + KCSAN_CHECK_READ_BARRIER(smp_mb__before_atomic()); + KCSAN_CHECK_READ_BARRIER(smp_mb__after_atomic()); + KCSAN_CHECK_READ_BARRIER(smp_mb__after_spinlock()); + KCSAN_CHECK_READ_BARRIER(smp_store_mb(test_var, 0)); + KCSAN_CHECK_READ_BARRIER(smp_store_release(&test_var, 0)); + KCSAN_CHECK_READ_BARRIER(xchg(&test_var, 0)); + KCSAN_CHECK_READ_BARRIER(xchg_release(&test_var, 0)); + KCSAN_CHECK_READ_BARRIER(cmpxchg(&test_var, 0, 0)); + KCSAN_CHECK_READ_BARRIER(cmpxchg_release(&test_var, 0, 0)); + KCSAN_CHECK_READ_BARRIER(atomic_set_release(&dummy, 0)); + KCSAN_CHECK_READ_BARRIER(atomic_add_return(1, &dummy)); + KCSAN_CHECK_READ_BARRIER(atomic_add_return_release(1, &dummy)); + KCSAN_CHECK_READ_BARRIER(atomic_fetch_add(1, &dummy)); + KCSAN_CHECK_READ_BARRIER(atomic_fetch_add_release(1, &dummy)); + KCSAN_CHECK_READ_BARRIER(test_and_set_bit(0, &test_var)); + KCSAN_CHECK_READ_BARRIER(test_and_clear_bit(0, &test_var)); + KCSAN_CHECK_READ_BARRIER(test_and_change_bit(0, &test_var)); + KCSAN_CHECK_READ_BARRIER(clear_bit_unlock(0, &test_var)); + KCSAN_CHECK_READ_BARRIER(__clear_bit_unlock(0, &test_var)); + arch_spin_lock(&arch_spinlock); + KCSAN_CHECK_READ_BARRIER(arch_spin_unlock(&arch_spinlock)); + spin_lock(&test_spinlock); + KCSAN_CHECK_READ_BARRIER(spin_unlock(&test_spinlock)); + + KCSAN_CHECK_WRITE_BARRIER(mb()); + KCSAN_CHECK_WRITE_BARRIER(wmb()); + KCSAN_CHECK_WRITE_BARRIER(smp_mb()); + KCSAN_CHECK_WRITE_BARRIER(smp_wmb()); + KCSAN_CHECK_WRITE_BARRIER(dma_wmb()); + KCSAN_CHECK_WRITE_BARRIER(smp_mb__before_atomic()); + KCSAN_CHECK_WRITE_BARRIER(smp_mb__after_atomic()); + KCSAN_CHECK_WRITE_BARRIER(smp_mb__after_spinlock()); + KCSAN_CHECK_WRITE_BARRIER(smp_store_mb(test_var, 0)); + KCSAN_CHECK_WRITE_BARRIER(smp_store_release(&test_var, 0)); + KCSAN_CHECK_WRITE_BARRIER(xchg(&test_var, 0)); + KCSAN_CHECK_WRITE_BARRIER(xchg_release(&test_var, 0)); + KCSAN_CHECK_WRITE_BARRIER(cmpxchg(&test_var, 0, 0)); + KCSAN_CHECK_WRITE_BARRIER(cmpxchg_release(&test_var, 0, 0)); + KCSAN_CHECK_WRITE_BARRIER(atomic_set_release(&dummy, 0)); + KCSAN_CHECK_WRITE_BARRIER(atomic_add_return(1, &dummy)); + KCSAN_CHECK_WRITE_BARRIER(atomic_add_return_release(1, &dummy)); + KCSAN_CHECK_WRITE_BARRIER(atomic_fetch_add(1, &dummy)); + KCSAN_CHECK_WRITE_BARRIER(atomic_fetch_add_release(1, &dummy)); + KCSAN_CHECK_WRITE_BARRIER(test_and_set_bit(0, &test_var)); + KCSAN_CHECK_WRITE_BARRIER(test_and_clear_bit(0, &test_var)); + KCSAN_CHECK_WRITE_BARRIER(test_and_change_bit(0, &test_var)); + KCSAN_CHECK_WRITE_BARRIER(clear_bit_unlock(0, &test_var)); + KCSAN_CHECK_WRITE_BARRIER(__clear_bit_unlock(0, &test_var)); + arch_spin_lock(&arch_spinlock); + KCSAN_CHECK_WRITE_BARRIER(arch_spin_unlock(&arch_spinlock)); + spin_lock(&test_spinlock); + KCSAN_CHECK_WRITE_BARRIER(spin_unlock(&test_spinlock)); + + KCSAN_CHECK_RW_BARRIER(mb()); + KCSAN_CHECK_RW_BARRIER(wmb()); + KCSAN_CHECK_RW_BARRIER(rmb()); + KCSAN_CHECK_RW_BARRIER(smp_mb()); + KCSAN_CHECK_RW_BARRIER(smp_wmb()); + KCSAN_CHECK_RW_BARRIER(smp_rmb()); + KCSAN_CHECK_RW_BARRIER(dma_wmb()); + KCSAN_CHECK_RW_BARRIER(dma_rmb()); + KCSAN_CHECK_RW_BARRIER(smp_mb__before_atomic()); + KCSAN_CHECK_RW_BARRIER(smp_mb__after_atomic()); + KCSAN_CHECK_RW_BARRIER(smp_mb__after_spinlock()); + KCSAN_CHECK_RW_BARRIER(smp_store_mb(test_var, 0)); + KCSAN_CHECK_RW_BARRIER(smp_store_release(&test_var, 0)); + KCSAN_CHECK_RW_BARRIER(xchg(&test_var, 0)); + KCSAN_CHECK_RW_BARRIER(xchg_release(&test_var, 0)); + KCSAN_CHECK_RW_BARRIER(cmpxchg(&test_var, 0, 0)); + KCSAN_CHECK_RW_BARRIER(cmpxchg_release(&test_var, 0, 0)); + KCSAN_CHECK_RW_BARRIER(atomic_set_release(&dummy, 0)); + KCSAN_CHECK_RW_BARRIER(atomic_add_return(1, &dummy)); + KCSAN_CHECK_RW_BARRIER(atomic_add_return_release(1, &dummy)); + KCSAN_CHECK_RW_BARRIER(atomic_fetch_add(1, &dummy)); + KCSAN_CHECK_RW_BARRIER(atomic_fetch_add_release(1, &dummy)); + KCSAN_CHECK_RW_BARRIER(test_and_set_bit(0, &test_var)); + KCSAN_CHECK_RW_BARRIER(test_and_clear_bit(0, &test_var)); + KCSAN_CHECK_RW_BARRIER(test_and_change_bit(0, &test_var)); + KCSAN_CHECK_RW_BARRIER(clear_bit_unlock(0, &test_var)); + KCSAN_CHECK_RW_BARRIER(__clear_bit_unlock(0, &test_var)); + arch_spin_lock(&arch_spinlock); + KCSAN_CHECK_RW_BARRIER(arch_spin_unlock(&arch_spinlock)); + spin_lock(&test_spinlock); + KCSAN_CHECK_RW_BARRIER(spin_unlock(&test_spinlock)); + +#ifdef clear_bit_unlock_is_negative_byte + KCSAN_CHECK_RW_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var)); + KCSAN_CHECK_READ_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var)); + KCSAN_CHECK_WRITE_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var)); +#endif + kcsan_nestable_atomic_end(); + + return ret; +} + +static int __init kcsan_selftest(void) +{ + int passed = 0; + int total = 0; + +#define RUN_TEST(do_test) \ + do { \ + ++total; \ + if (do_test()) \ + ++passed; \ + else \ + pr_err("selftest: " #do_test " failed"); \ + } while (0) + + RUN_TEST(test_requires); + RUN_TEST(test_encode_decode); + RUN_TEST(test_matching_access); + RUN_TEST(test_barrier); + + pr_info("selftest: %d/%d tests passed\n", passed, total); + if (passed != total) + panic("selftests failed"); + return 0; +} +postcore_initcall(kcsan_selftest); |