// https://syzkaller.appspot.com/bug?id=db58a4022d476752fca3c46386b33ca799d3a7f0 // autogenerated by syzkaller (https://github.com/google/syzkaller) #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include static unsigned long long procid; static void sleep_ms(uint64_t ms) { usleep(ms * 1000); } static uint64_t current_time_ms(void) { struct timespec ts; if (clock_gettime(CLOCK_MONOTONIC, &ts)) exit(1); return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000; } static void use_temporary_dir(void) { char tmpdir_template[] = "./syzkaller.XXXXXX"; char* tmpdir = mkdtemp(tmpdir_template); if (!tmpdir) exit(1); if (chmod(tmpdir, 0777)) exit(1); if (chdir(tmpdir)) exit(1); } static void thread_start(void* (*fn)(void*), void* arg) { pthread_t th; pthread_attr_t attr; pthread_attr_init(&attr); pthread_attr_setstacksize(&attr, 128 << 10); int i = 0; for (; i < 100; i++) { if (pthread_create(&th, &attr, fn, arg) == 0) { pthread_attr_destroy(&attr); return; } if (errno == EAGAIN) { usleep(50); continue; } break; } exit(1); } 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 (ev->state) 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); } static int event_isset(event_t* ev) { return __atomic_load_n(&ev->state, __ATOMIC_ACQUIRE); } static int event_timedwait(event_t* ev, uint64_t timeout) { uint64_t start = current_time_ms(); uint64_t now = start; for (;;) { uint64_t remain = timeout - (now - start); struct timespec ts; ts.tv_sec = remain / 1000; ts.tv_nsec = (remain % 1000) * 1000 * 1000; syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, &ts); if (__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE)) return 1; now = current_time_ms(); if (now - start > timeout) return 0; } } static bool write_file(const char* file, const char* what, ...) { char buf[1024]; va_list args; va_start(args, what); vsnprintf(buf, sizeof(buf), what, args); va_end(args); buf[sizeof(buf) - 1] = 0; int len = strlen(buf); int fd = open(file, O_WRONLY | O_CLOEXEC); if (fd == -1) return false; if (write(fd, buf, len) != len) { int err = errno; close(fd); errno = err; return false; } close(fd); return true; } #define SIZEOF_IO_URING_SQE 64 #define SIZEOF_IO_URING_CQE 16 #define SQ_HEAD_OFFSET 0 #define SQ_TAIL_OFFSET 64 #define SQ_RING_MASK_OFFSET 256 #define SQ_RING_ENTRIES_OFFSET 264 #define SQ_FLAGS_OFFSET 276 #define SQ_DROPPED_OFFSET 272 #define CQ_HEAD_OFFSET 128 #define CQ_TAIL_OFFSET 192 #define CQ_RING_MASK_OFFSET 260 #define CQ_RING_ENTRIES_OFFSET 268 #define CQ_RING_OVERFLOW_OFFSET 284 #define CQ_FLAGS_OFFSET 280 #define CQ_CQES_OFFSET 320 struct io_sqring_offsets { uint32_t head; uint32_t tail; uint32_t ring_mask; uint32_t ring_entries; uint32_t flags; uint32_t dropped; uint32_t array; uint32_t resv1; uint64_t resv2; }; struct io_cqring_offsets { uint32_t head; uint32_t tail; uint32_t ring_mask; uint32_t ring_entries; uint32_t overflow; uint32_t cqes; uint64_t resv[2]; }; struct io_uring_params { uint32_t sq_entries; uint32_t cq_entries; uint32_t flags; uint32_t sq_thread_cpu; uint32_t sq_thread_idle; uint32_t features; uint32_t resv[4]; struct io_sqring_offsets sq_off; struct io_cqring_offsets cq_off; }; #define IORING_OFF_SQ_RING 0 #define IORING_OFF_SQES 0x10000000ULL #define sys_io_uring_setup 425 static long syz_io_uring_setup(volatile long a0, volatile long a1, volatile long a2, volatile long a3, volatile long a4, volatile long a5) { uint32_t entries = (uint32_t)a0; struct io_uring_params* setup_params = (struct io_uring_params*)a1; void* vma1 = (void*)a2; void* vma2 = (void*)a3; void** ring_ptr_out = (void**)a4; void** sqes_ptr_out = (void**)a5; uint32_t fd_io_uring = syscall(sys_io_uring_setup, entries, setup_params); uint32_t sq_ring_sz = setup_params->sq_off.array + setup_params->sq_entries * sizeof(uint32_t); uint32_t cq_ring_sz = setup_params->cq_off.cqes + setup_params->cq_entries * SIZEOF_IO_URING_CQE; uint32_t ring_sz = sq_ring_sz > cq_ring_sz ? sq_ring_sz : cq_ring_sz; *ring_ptr_out = mmap(vma1, ring_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE | MAP_FIXED, fd_io_uring, IORING_OFF_SQ_RING); uint32_t sqes_sz = setup_params->sq_entries * SIZEOF_IO_URING_SQE; *sqes_ptr_out = mmap(vma2, sqes_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE | MAP_FIXED, fd_io_uring, IORING_OFF_SQES); return fd_io_uring; } #define MAX_FDS 30 static void setup_cgroups() { if (mkdir("/syzcgroup", 0777)) { } if (mkdir("/syzcgroup/unified", 0777)) { } if (mount("none", "/syzcgroup/unified", "cgroup2", 0, NULL)) { } if (chmod("/syzcgroup/unified", 0777)) { } write_file("/syzcgroup/unified/cgroup.subtree_control", "+cpu +memory +io +pids +rdma"); if (mkdir("/syzcgroup/cpu", 0777)) { } if (mount("none", "/syzcgroup/cpu", "cgroup", 0, "cpuset,cpuacct,perf_event,hugetlb")) { } write_file("/syzcgroup/cpu/cgroup.clone_children", "1"); write_file("/syzcgroup/cpu/cpuset.memory_pressure_enabled", "1"); if (chmod("/syzcgroup/cpu", 0777)) { } if (mkdir("/syzcgroup/net", 0777)) { } if (mount("none", "/syzcgroup/net", "cgroup", 0, "net_cls,net_prio,devices,freezer")) { } if (chmod("/syzcgroup/net", 0777)) { } } static void setup_cgroups_loop() { int pid = getpid(); char file[128]; char cgroupdir[64]; snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/unified/syz%llu", procid); if (mkdir(cgroupdir, 0777)) { } snprintf(file, sizeof(file), "%s/pids.max", cgroupdir); write_file(file, "32"); snprintf(file, sizeof(file), "%s/memory.low", cgroupdir); write_file(file, "%d", 298 << 20); snprintf(file, sizeof(file), "%s/memory.high", cgroupdir); write_file(file, "%d", 299 << 20); snprintf(file, sizeof(file), "%s/memory.max", cgroupdir); write_file(file, "%d", 300 << 20); snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir); write_file(file, "%d", pid); snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/cpu/syz%llu", procid); if (mkdir(cgroupdir, 0777)) { } snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir); write_file(file, "%d", pid); snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/net/syz%llu", procid); if (mkdir(cgroupdir, 0777)) { } snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir); write_file(file, "%d", pid); } static void setup_cgroups_test() { char cgroupdir[64]; snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/unified/syz%llu", procid); if (symlink(cgroupdir, "./cgroup")) { } snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/cpu/syz%llu", procid); if (symlink(cgroupdir, "./cgroup.cpu")) { } snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/net/syz%llu", procid); if (symlink(cgroupdir, "./cgroup.net")) { } } static void setup_common() { if (mount(0, "/sys/fs/fuse/connections", "fusectl", 0, 0)) { } setup_cgroups(); } static void loop(); static void sandbox_common() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setsid(); struct rlimit rlim; rlim.rlim_cur = rlim.rlim_max = (200 << 20); setrlimit(RLIMIT_AS, &rlim); rlim.rlim_cur = rlim.rlim_max = 32 << 20; setrlimit(RLIMIT_MEMLOCK, &rlim); rlim.rlim_cur = rlim.rlim_max = 136 << 20; setrlimit(RLIMIT_FSIZE, &rlim); rlim.rlim_cur = rlim.rlim_max = 1 << 20; setrlimit(RLIMIT_STACK, &rlim); rlim.rlim_cur = rlim.rlim_max = 0; setrlimit(RLIMIT_CORE, &rlim); rlim.rlim_cur = rlim.rlim_max = 256; setrlimit(RLIMIT_NOFILE, &rlim); if (unshare(CLONE_NEWNS)) { } if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)) { } if (unshare(CLONE_NEWIPC)) { } if (unshare(0x02000000)) { } if (unshare(CLONE_NEWUTS)) { } if (unshare(CLONE_SYSVSEM)) { } typedef struct { const char* name; const char* value; } sysctl_t; static const sysctl_t sysctls[] = { {"/proc/sys/kernel/shmmax", "16777216"}, {"/proc/sys/kernel/shmall", "536870912"}, {"/proc/sys/kernel/shmmni", "1024"}, {"/proc/sys/kernel/msgmax", "8192"}, {"/proc/sys/kernel/msgmni", "1024"}, {"/proc/sys/kernel/msgmnb", "1024"}, {"/proc/sys/kernel/sem", "1024 1048576 500 1024"}, }; unsigned i; for (i = 0; i < sizeof(sysctls) / sizeof(sysctls[0]); i++) write_file(sysctls[i].name, sysctls[i].value); } static int wait_for_loop(int pid) { if (pid < 0) exit(1); int status = 0; while (waitpid(-1, &status, __WALL) != pid) { } return WEXITSTATUS(status); } static void drop_caps(void) { struct __user_cap_header_struct cap_hdr = {}; struct __user_cap_data_struct cap_data[2] = {}; cap_hdr.version = _LINUX_CAPABILITY_VERSION_3; cap_hdr.pid = getpid(); if (syscall(SYS_capget, &cap_hdr, &cap_data)) exit(1); const int drop = (1 << CAP_SYS_PTRACE) | (1 << CAP_SYS_NICE); cap_data[0].effective &= ~drop; cap_data[0].permitted &= ~drop; cap_data[0].inheritable &= ~drop; if (syscall(SYS_capset, &cap_hdr, &cap_data)) exit(1); } static int do_sandbox_none(void) { if (unshare(CLONE_NEWPID)) { } int pid = fork(); if (pid != 0) return wait_for_loop(pid); setup_common(); sandbox_common(); drop_caps(); if (unshare(CLONE_NEWNET)) { } loop(); exit(1); } #define FS_IOC_SETFLAGS _IOW('f', 2, long) static void remove_dir(const char* dir) { int iter = 0; DIR* dp = 0; retry: while (umount2(dir, MNT_DETACH) == 0) { } dp = opendir(dir); if (dp == NULL) { if (errno == EMFILE) { exit(1); } exit(1); } struct dirent* ep = 0; while ((ep = readdir(dp))) { if (strcmp(ep->d_name, ".") == 0 || strcmp(ep->d_name, "..") == 0) continue; char filename[FILENAME_MAX]; snprintf(filename, sizeof(filename), "%s/%s", dir, ep->d_name); while (umount2(filename, MNT_DETACH) == 0) { } struct stat st; if (lstat(filename, &st)) exit(1); if (S_ISDIR(st.st_mode)) { remove_dir(filename); continue; } int i; for (i = 0;; i++) { if (unlink(filename) == 0) break; if (errno == EPERM) { int fd = open(filename, O_RDONLY); if (fd != -1) { long flags = 0; if (ioctl(fd, FS_IOC_SETFLAGS, &flags) == 0) { } close(fd); continue; } } if (errno == EROFS) { break; } if (errno != EBUSY || i > 100) exit(1); if (umount2(filename, MNT_DETACH)) exit(1); } } closedir(dp); for (int i = 0;; i++) { if (rmdir(dir) == 0) break; if (i < 100) { if (errno == EPERM) { int fd = open(dir, O_RDONLY); if (fd != -1) { long flags = 0; if (ioctl(fd, FS_IOC_SETFLAGS, &flags) == 0) { } close(fd); continue; } } if (errno == EROFS) { break; } if (errno == EBUSY) { if (umount2(dir, MNT_DETACH)) exit(1); continue; } if (errno == ENOTEMPTY) { if (iter < 100) { iter++; goto retry; } } } exit(1); } } static void kill_and_wait(int pid, int* status) { kill(-pid, SIGKILL); kill(pid, SIGKILL); for (int i = 0; i < 100; i++) { if (waitpid(-1, status, WNOHANG | __WALL) == pid) return; usleep(1000); } DIR* dir = opendir("/sys/fs/fuse/connections"); if (dir) { for (;;) { struct dirent* ent = readdir(dir); if (!ent) break; if (strcmp(ent->d_name, ".") == 0 || strcmp(ent->d_name, "..") == 0) continue; char abort[300]; snprintf(abort, sizeof(abort), "/sys/fs/fuse/connections/%s/abort", ent->d_name); int fd = open(abort, O_WRONLY); if (fd == -1) { continue; } if (write(fd, abort, 1) < 0) { } close(fd); } closedir(dir); } else { } while (waitpid(-1, status, __WALL) != pid) { } } static void setup_loop() { setup_cgroups_loop(); } static void setup_test() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setpgrp(); setup_cgroups_test(); write_file("/proc/self/oom_score_adj", "1000"); } static void close_fds() { for (int fd = 3; fd < MAX_FDS; fd++) close(fd); } struct thread_t { int created, call; event_t ready, done; }; static struct thread_t threads[16]; static void execute_call(int call); static int running; static void* thr(void* arg) { struct thread_t* th = (struct thread_t*)arg; for (;;) { event_wait(&th->ready); event_reset(&th->ready); execute_call(th->call); __atomic_fetch_sub(&running, 1, __ATOMIC_RELAXED); event_set(&th->done); } return 0; } static void execute_one(void) { int i, call, thread; int collide = 0; again: for (call = 0; call < 5; call++) { for (thread = 0; thread < (int)(sizeof(threads) / sizeof(threads[0])); thread++) { struct thread_t* th = &threads[thread]; if (!th->created) { th->created = 1; event_init(&th->ready); event_init(&th->done); event_set(&th->done); thread_start(thr, th); } if (!event_isset(&th->done)) continue; event_reset(&th->done); th->call = call; __atomic_fetch_add(&running, 1, __ATOMIC_RELAXED); event_set(&th->ready); if (collide && (call % 2) == 0) break; event_timedwait(&th->done, 50); break; } } for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++) sleep_ms(1); close_fds(); if (!collide) { collide = 1; goto again; } } static void execute_one(void); #define WAIT_FLAGS __WALL static void loop(void) { setup_loop(); int iter = 0; for (;; iter++) { char cwdbuf[32]; sprintf(cwdbuf, "./%d", iter); if (mkdir(cwdbuf, 0777)) exit(1); int pid = fork(); if (pid < 0) exit(1); if (pid == 0) { if (chdir(cwdbuf)) exit(1); setup_test(); execute_one(); exit(0); } int status = 0; uint64_t start = current_time_ms(); for (;;) { if (waitpid(-1, &status, WNOHANG | WAIT_FLAGS) == pid) break; sleep_ms(1); if (current_time_ms() - start < 5000) { continue; } kill_and_wait(pid, &status); break; } remove_dir(cwdbuf); } } #ifndef __NR_io_uring_enter #define __NR_io_uring_enter 426 #endif #ifndef __NR_io_uring_register #define __NR_io_uring_register 427 #endif uint64_t r[1] = {0xffffffffffffffff}; void execute_call(int call) { intptr_t res = 0; switch (call) { case 0: syscall(__NR_clone, 0x20002004ffcul, 0ul, 0x9999999999999999ul, 0ul, -1ul); break; case 1: *(uint32_t*)0x20000084 = 0; *(uint32_t*)0x20000088 = 0x10; *(uint32_t*)0x2000008c = 1; *(uint32_t*)0x20000090 = 0; *(uint32_t*)0x20000098 = -1; *(uint32_t*)0x2000009c = 0; *(uint32_t*)0x200000a0 = 0; *(uint32_t*)0x200000a4 = 0; res = -1; res = syz_io_uring_setup(0x4af6, 0x20000080, 0x20556000, 0x20558000, 0x20000000, 0x20000040); if (res != -1) r[0] = res; break; case 2: syscall(__NR_clone, 0x20000ul, 0x20000100ul, 0ul, 0ul, 0ul); break; case 3: syscall(__NR_io_uring_register, r[0], 0ul, 0ul, 0ul); break; case 4: syscall(__NR_io_uring_enter, r[0], 0, 0xd6c8, 1ul, 0ul, 0ul); break; } } int main(void) { syscall(__NR_mmap, 0x1ffff000ul, 0x1000ul, 0ul, 0x32ul, -1, 0ul); syscall(__NR_mmap, 0x20000000ul, 0x1000000ul, 7ul, 0x32ul, -1, 0ul); syscall(__NR_mmap, 0x21000000ul, 0x1000ul, 0ul, 0x32ul, -1, 0ul); use_temporary_dir(); do_sandbox_none(); return 0; }