// https://syzkaller.appspot.com/bug?id=86ced160b3c394018a4d5dd1db69824b7b1b6734 #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include #include // Copyright 2026 syzkaller project authors. All rights reserved. // Use of this source code is governed by Apache 2 LICENSE that can be found in the LICENSE file. // IMPORTANT: Do not copy the macros or definitions below directly into your reproducer. // Instead, add the following line to your reproducer: // #include "race_toolkit.h" // --- Race Condition Toolkit --- // Macros and snippets for CPU pinning, memory barriers, and userfaultfd. #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include #include #include #include #include #include // Unbuffered I/O: Ensure logs are written immediately. #define SETUP_UNBUFFERED_IO() setvbuf(stdout, NULL, _IONBF, 0) // CPU Pinning: Pin the current thread to a specific CPU core. #define PIN_TO_CPU(cpu) \ do { \ cpu_set_t mask; \ CPU_ZERO(&mask); \ CPU_SET(cpu, &mask); \ if (sched_setaffinity(0, sizeof(mask), &mask) == -1) { \ perror("sched_setaffinity"); \ } \ } while (0) // Memory Barrier: Ensure memory ordering. #define MB() __atomic_thread_fence(__ATOMIC_SEQ_CST) // Spin-wait Barrier: Wait until a memory location has a specific value. // Best for tight race windows (low latency, no context switches). #define WAIT_ON(addr, val) \ do { \ while (__atomic_load_n(addr, __ATOMIC_ACQUIRE) != (val)) \ ; \ } while (0) // Signal: Set a memory location to a specific value to release a WAIT_ON. #define SIGNAL(addr, val) __atomic_store_n(addr, val, __ATOMIC_RELEASE) // --- Timing Primitives --- // Robust timing loops in VM environments (using CLOCK_MONOTONIC to avoid time(NULL) jumps). static inline double timer_elapsed_sec(struct timespec* start) { struct timespec now; if (clock_gettime(CLOCK_MONOTONIC, &now) == -1) { perror("clock_gettime(CLOCK_MONOTONIC) elapsed"); exit(1); } return (double)(now.tv_sec - start->tv_sec) + (double)(now.tv_nsec - start->tv_nsec) / 1e9; } // Initialize a monotonic timer variable. #define TIMER_START(t) \ struct timespec t; \ if (clock_gettime(CLOCK_MONOTONIC, &t) == -1) { \ perror("clock_gettime(CLOCK_MONOTONIC) start"); \ exit(1); \ } // Check if the elapsed time since 't' is less than 'sec' seconds. #define TIMER_NOT_EXPIRED(t, sec) (timer_elapsed_sec(&(t)) < (double)(sec)) // Futex-based Event: Shared with syzkaller executor. // Best for general synchronization or longer waits to save CPU. typedef struct { int state; } event_t; static void event_init(event_t* ev) { ev->state = 0; } static void event_reset(event_t* ev) { ev->state = 0; } static void event_set(event_t* ev) { if (__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE)) { fprintf(stderr, "event already set\n"); exit(1); } __atomic_store_n(&ev->state, 1, __ATOMIC_RELEASE); syscall(SYS_futex, &ev->state, FUTEX_WAKE | FUTEX_PRIVATE_FLAG, 1000000); } static void event_wait(event_t* ev) { while (!__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE)) syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, 0); } // userfaultfd setup: Register a memory range for page fault handling. static int setup_uffd(void* addr, size_t len) { int uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); if (uffd == -1) return -1; struct uffdio_api api = {.api = UFFD_API, .features = 0}; if (ioctl(uffd, UFFDIO_API, &api) == -1) { close(uffd); return -1; } struct uffdio_register reg = { .range = {.start = (uintptr_t)addr, .len = len}, .mode = UFFDIO_REGISTER_MODE_MISSING}; if (ioctl(uffd, UFFDIO_REGISTER, ®) == -1) { close(uffd); return -1; } return uffd; } // --- Guidance on Usage --- // 1. Use WAIT_ON/SIGNAL for tight race conditions to avoid scheduling overhead. // 2. Use event_t (futexes) for general coordination or when waiting for longer periods. // 3. Always use PIN_TO_CPU to increase race probability on multi-core systems. // 4. Use setup_uffd to register a memory range for page fault handling. This allows you to // pause a thread accessing that memory until you handle the fault, creating a reliable // and controllable race window. // 5. Call SETUP_UNBUFFERED_IO() at the start of main() to ensure that logs are printed // immediately. This is essential for understanding the exact interleaving of events // when debugging race conditions. // 6. For timing-based loops (e.g., running a race for 10 seconds), do NOT use time(NULL) // or loops relying on real-time clocks, as VM clocks are highly unreliable and can fail or drift. // Instead, use the robust monotonic timing primitives TIMER_START and TIMER_NOT_EXPIRED: // TIMER_START(start); // while (TIMER_NOT_EXPIRED(start, 10.0)) { // // Your race logic here // } int futex_word = 0; char trace_base[256]; /* Thread 1: Continuously toggles record-cmd */ void *toggler(void *arg) { PIN_TO_CPU(0); char path[512]; snprintf(path, sizeof(path), "%s/options/record-cmd", trace_base); int fd = open(path, O_WRONLY); if (fd < 0) { printf("[-] Failed to open %s: %s\n", path, strerror(errno)); return NULL; } while (1) { if (write(fd, "0\n", 2) < 0) {} if (write(fd, "1\n", 2) < 0) {} } return NULL; } /* Threads 2+: Continuously wake up waiting threads */ void *waker(void *arg) { PIN_TO_CPU(1); while (1) { syscall(SYS_futex, &futex_word, FUTEX_WAKE, 1, NULL, NULL, 0); } return NULL; } /* Threads 3+: Continuously go to sleep on a futex */ void *waiter(void *arg) { PIN_TO_CPU(1); while (1) { syscall(SYS_futex, &futex_word, FUTEX_WAIT, futex_word, NULL, NULL, 0); } return NULL; } int write_file(const char *path, const char *val) { int fd = open(path, O_WRONLY | O_TRUNC); if (fd < 0) return -1; int ret = write(fd, val, strlen(val)); close(fd); return ret; } int main() { SETUP_UNBUFFERED_IO(); const char *base_dirs[] = { "/sys/kernel/tracing", "/sys/kernel/debug/tracing", NULL }; int found = 0; for (int i = 0; base_dirs[i]; i++) { if (access(base_dirs[i], F_OK) == 0) { strcpy(trace_base, base_dirs[i]); found = 1; break; } } if (!found) { printf("[-] Tracefs not found.\n"); exit(1); } printf("[+] Tracefs found at %s\n", trace_base); char path[512]; /* Clear all events */ snprintf(path, sizeof(path), "%s/set_event", trace_base); if (write_file(path, "") < 0) { printf("[-] Failed to clear events: %s\n", strerror(errno)); exit(1); } printf("[+] Cleared events.\n"); /* Ensure record-cmd is enabled */ snprintf(path, sizeof(path), "%s/options/record-cmd", trace_base); if (write_file(path, "1\n") < 0) { printf("[-] Failed to enable record-cmd: %s\n", strerror(errno)); } else { printf("[+] Enabled record-cmd.\n"); } /* Enable sched_wakeup */ snprintf(path, sizeof(path), "%s/events/sched/sched_wakeup/enable", trace_base); if (write_file(path, "1\n") < 0) { printf("[-] Failed to enable sched_wakeup: %s\n", strerror(errno)); exit(1); } printf("[+] Enabled sched_wakeup.\n"); /* Enable record-tgid */ /* This is critical: it keeps sched_tgid_ref > 0, which prevents tracing_sched_unregister() from being called when record-cmd is toggled. This completely bypasses the RCU sync delay, allowing the race window to be hit thousands of times per second. */ snprintf(path, sizeof(path), "%s/options/record-tgid", trace_base); if (write_file(path, "1\n") < 0) { printf("[-] Failed to enable record-tgid: %s\n", strerror(errno)); } else { printf("[+] Enabled record-tgid.\n"); } pthread_t t_toggler; if (pthread_create(&t_toggler, NULL, toggler, NULL) != 0) { printf("[-] Failed to create toggler thread.\n"); exit(1); } #define NUM_THREADS 4 pthread_t t_wakers[NUM_THREADS]; pthread_t t_waiters[NUM_THREADS]; for (int i = 0; i < NUM_THREADS; i++) { pthread_create(&t_wakers[i], NULL, waker, NULL); pthread_create(&t_waiters[i], NULL, waiter, NULL); } printf("[+] Started waker and waiter threads.\n"); /* Infinite loop, let syzbot timeout and kill us. This avoids triggering unrelated data races during process exit. */ while (1) { sleep(1); } return 0; }