Syzkaller hit 'memory leak in __kernfs_iattrs' bug. BUG: memory leak unreferenced object 0xffff88800d27eb60 (size 144): comm "syz-executor979", pid 270, jiffies 4294926649 (age 21.331s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 de 45 ec 61 00 00 00 00 .........E.a.... ce a5 81 30 00 00 00 00 de 45 ec 61 00 00 00 00 ...0.....E.a.... backtrace: [<00000000b52e38b6>] kmem_cache_zalloc include/linux/slab.h:654 [inline] [<00000000b52e38b6>] __kernfs_iattrs+0xb8/0x460 fs/kernfs/inode.c:43 [<0000000076017a40>] kernfs_iattrs fs/kernfs/inode.c:66 [inline] [<0000000076017a40>] kernfs_xattr_set+0x2b/0x70 fs/kernfs/inode.c:304 [<00000000793deab6>] selinux_kernfs_init_security+0x268/0x4c0 security/selinux/hooks.c:3515 [<00000000896d6f6b>] security_kernfs_init_security+0x4e/0xa0 security/security.c:1441 [<00000000024c2dc3>] __kernfs_new_node+0x531/0x840 fs/kernfs/dir.c:666 [<00000000b14fbdd6>] kernfs_new_node fs/kernfs/dir.c:689 [inline] [<00000000b14fbdd6>] kernfs_create_dir_ns+0x9c/0x220 fs/kernfs/dir.c:1026 [<00000000dc89dec8>] kernfs_create_dir include/linux/kernfs.h:561 [inline] [<00000000dc89dec8>] cgroup_create kernel/cgroup/cgroup.c:5233 [inline] [<00000000dc89dec8>] cgroup_mkdir+0x318/0xfc0 kernel/cgroup/cgroup.c:5367 [<00000000fc87b482>] kernfs_iop_mkdir+0x149/0x1d0 fs/kernfs/dir.c:1127 [<00000000cad9f703>] vfs_mkdir+0x41f/0x660 fs/namei.c:3641 [<00000000ec808790>] do_mkdirat+0x145/0x2a0 fs/namei.c:3664 [<00000000c7948bc1>] do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46 [<000000007366bb8b>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 BUG: memory leak unreferenced object 0xffff88800d27ec30 (size 144): comm "syz-executor979", pid 270, jiffies 4294926699 (age 21.281s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 de 45 ec 61 00 00 00 00 .........E.a.... d6 d4 78 33 00 00 00 00 de 45 ec 61 00 00 00 00 ..x3.....E.a.... backtrace: [<00000000b52e38b6>] kmem_cache_zalloc include/linux/slab.h:654 [inline] [<00000000b52e38b6>] __kernfs_iattrs+0xb8/0x460 fs/kernfs/inode.c:43 [<0000000076017a40>] kernfs_iattrs fs/kernfs/inode.c:66 [inline] [<0000000076017a40>] kernfs_xattr_set+0x2b/0x70 fs/kernfs/inode.c:304 [<00000000793deab6>] selinux_kernfs_init_security+0x268/0x4c0 security/selinux/hooks.c:3515 [<00000000896d6f6b>] security_kernfs_init_security+0x4e/0xa0 security/security.c:1441 [<00000000024c2dc3>] __kernfs_new_node+0x531/0x840 fs/kernfs/dir.c:666 [<00000000b14fbdd6>] kernfs_new_node fs/kernfs/dir.c:689 [inline] [<00000000b14fbdd6>] kernfs_create_dir_ns+0x9c/0x220 fs/kernfs/dir.c:1026 [<00000000dc89dec8>] kernfs_create_dir include/linux/kernfs.h:561 [inline] [<00000000dc89dec8>] cgroup_create kernel/cgroup/cgroup.c:5233 [inline] [<00000000dc89dec8>] cgroup_mkdir+0x318/0xfc0 kernel/cgroup/cgroup.c:5367 [<00000000fc87b482>] kernfs_iop_mkdir+0x149/0x1d0 fs/kernfs/dir.c:1127 [<00000000cad9f703>] vfs_mkdir+0x41f/0x660 fs/namei.c:3641 [<00000000ec808790>] do_mkdirat+0x145/0x2a0 fs/namei.c:3664 [<00000000c7948bc1>] do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46 [<000000007366bb8b>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 BUG: memory leak unreferenced object 0xffff88801ca2bc30 (size 144): comm "syz-executor979", pid 274, jiffies 4294935738 (age 12.242s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 e7 45 ec 61 00 00 00 00 .........E.a.... fb 79 c6 35 00 00 00 00 e7 45 ec 61 00 00 00 00 .y.5.....E.a.... backtrace: [<00000000b52e38b6>] kmem_cache_zalloc include/linux/slab.h:654 [inline] [<00000000b52e38b6>] __kernfs_iattrs+0xb8/0x460 fs/kernfs/inode.c:43 [<0000000076017a40>] kernfs_iattrs fs/kernfs/inode.c:66 [inline] [<0000000076017a40>] kernfs_xattr_set+0x2b/0x70 fs/kernfs/inode.c:304 [<00000000793deab6>] selinux_kernfs_init_security+0x268/0x4c0 security/selinux/hooks.c:3515 [<00000000896d6f6b>] security_kernfs_init_security+0x4e/0xa0 security/security.c:1441 [<00000000024c2dc3>] __kernfs_new_node+0x531/0x840 fs/kernfs/dir.c:666 [<00000000b14fbdd6>] kernfs_new_node fs/kernfs/dir.c:689 [inline] [<00000000b14fbdd6>] kernfs_create_dir_ns+0x9c/0x220 fs/kernfs/dir.c:1026 [<00000000dc89dec8>] kernfs_create_dir include/linux/kernfs.h:561 [inline] [<00000000dc89dec8>] cgroup_create kernel/cgroup/cgroup.c:5233 [inline] [<00000000dc89dec8>] cgroup_mkdir+0x318/0xfc0 kernel/cgroup/cgroup.c:5367 [<00000000fc87b482>] kernfs_iop_mkdir+0x149/0x1d0 fs/kernfs/dir.c:1127 [<00000000cad9f703>] vfs_mkdir+0x41f/0x660 fs/namei.c:3641 [<00000000ec808790>] do_mkdirat+0x145/0x2a0 fs/namei.c:3664 [<00000000c7948bc1>] do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46 [<000000007366bb8b>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Syzkaller reproducer: # {Threaded:true Collide:true Repeat:true RepeatTimes:0 Procs:1 Slowdown:1 Sandbox: Leak:true NetInjection:false NetDevices:false NetReset:false Cgroups:false BinfmtMisc:false CloseFDs:false KCSAN:false DevlinkPCI:false USB:false VhciInjection:false Wifi:false IEEE802154:false Sysctl:false UseTmpDir:false HandleSegv:true Repro:false Trace:false LegacyOptions:{Fault:false FaultCall:0 FaultNth:0}} mount(0x0, &(0x7f00000004c0)='./file0\x00', &(0x7f0000000000)='cgroup2\x00', 0x0, 0x0) r0 = syz_mount_image$vfat(0x0, &(0x7f0000000100)='./file0\x00', 0x0, 0x0, 0x0, 0x100020, 0x0) unlinkat(r0, &(0x7f00000004c0)='./file0\x00', 0x200) r1 = open(&(0x7f0000000180)='./file0\x00', 0x240880, 0x0) mkdirat(r1, &(0x7f0000000200)='./file0\x00', 0x86) (fail_nth: 30) C reproducer: // 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 static unsigned long long procid; static __thread int skip_segv; static __thread jmp_buf segv_env; static void segv_handler(int sig, siginfo_t* info, void* ctx) { uintptr_t addr = (uintptr_t)info->si_addr; const uintptr_t prog_start = 1 << 20; const uintptr_t prog_end = 100 << 20; int skip = __atomic_load_n(&skip_segv, __ATOMIC_RELAXED) != 0; int valid = addr < prog_start || addr > prog_end; if (skip && valid) { _longjmp(segv_env, 1); } exit(sig); } static void install_segv_handler(void) { struct sigaction sa; memset(&sa, 0, sizeof(sa)); sa.sa_handler = SIG_IGN; syscall(SYS_rt_sigaction, 0x20, &sa, NULL, 8); syscall(SYS_rt_sigaction, 0x21, &sa, NULL, 8); memset(&sa, 0, sizeof(sa)); sa.sa_sigaction = segv_handler; sa.sa_flags = SA_NODEFER | SA_SIGINFO; sigaction(SIGSEGV, &sa, NULL); sigaction(SIGBUS, &sa, NULL); } #define NONFAILING(...) ({ int ok = 1; __atomic_fetch_add(&skip_segv, 1, __ATOMIC_SEQ_CST); if (_setjmp(segv_env) == 0) { __VA_ARGS__; } else ok = 0; __atomic_fetch_sub(&skip_segv, 1, __ATOMIC_SEQ_CST); ok; }) 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 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; } struct fs_image_segment { void* data; uintptr_t size; uintptr_t offset; }; #define IMAGE_MAX_SEGMENTS 4096 #define IMAGE_MAX_SIZE (129 << 20) #define sys_memfd_create 319 static unsigned long fs_image_segment_check(unsigned long size, unsigned long nsegs, struct fs_image_segment* segs) { if (nsegs > IMAGE_MAX_SEGMENTS) nsegs = IMAGE_MAX_SEGMENTS; for (size_t i = 0; i < nsegs; i++) { if (segs[i].size > IMAGE_MAX_SIZE) segs[i].size = IMAGE_MAX_SIZE; segs[i].offset %= IMAGE_MAX_SIZE; if (segs[i].offset > IMAGE_MAX_SIZE - segs[i].size) segs[i].offset = IMAGE_MAX_SIZE - segs[i].size; if (size < segs[i].offset + segs[i].offset) size = segs[i].offset + segs[i].offset; } if (size > IMAGE_MAX_SIZE) size = IMAGE_MAX_SIZE; return size; } static int setup_loop_device(long unsigned size, long unsigned nsegs, struct fs_image_segment* segs, const char* loopname, int* memfd_p, int* loopfd_p) { int err = 0, loopfd = -1; size = fs_image_segment_check(size, nsegs, segs); int memfd = syscall(sys_memfd_create, "syzkaller", 0); if (memfd == -1) { err = errno; goto error; } if (ftruncate(memfd, size)) { err = errno; goto error_close_memfd; } for (size_t i = 0; i < nsegs; i++) { if (pwrite(memfd, segs[i].data, segs[i].size, segs[i].offset) < 0) { } } loopfd = open(loopname, O_RDWR); if (loopfd == -1) { err = errno; goto error_close_memfd; } if (ioctl(loopfd, LOOP_SET_FD, memfd)) { if (errno != EBUSY) { err = errno; goto error_close_loop; } ioctl(loopfd, LOOP_CLR_FD, 0); usleep(1000); if (ioctl(loopfd, LOOP_SET_FD, memfd)) { err = errno; goto error_close_loop; } } *memfd_p = memfd; *loopfd_p = loopfd; return 0; error_close_loop: close(loopfd); error_close_memfd: close(memfd); error: errno = err; return -1; } static long syz_mount_image(volatile long fsarg, volatile long dir, volatile unsigned long size, volatile unsigned long nsegs, volatile long segments, volatile long flags, volatile long optsarg) { struct fs_image_segment* segs = (struct fs_image_segment*)segments; int res = -1, err = 0, loopfd = -1, memfd = -1, need_loop_device = !!segs; char* mount_opts = (char*)optsarg; char* target = (char*)dir; char* fs = (char*)fsarg; char* source = NULL; char loopname[64]; if (need_loop_device) { memset(loopname, 0, sizeof(loopname)); snprintf(loopname, sizeof(loopname), "/dev/loop%llu", procid); if (setup_loop_device(size, nsegs, segs, loopname, &memfd, &loopfd) == -1) return -1; source = loopname; } mkdir(target, 0777); char opts[256]; memset(opts, 0, sizeof(opts)); if (strlen(mount_opts) > (sizeof(opts) - 32)) { } strncpy(opts, mount_opts, sizeof(opts) - 32); if (strcmp(fs, "iso9660") == 0) { flags |= MS_RDONLY; } else if (strncmp(fs, "ext", 3) == 0) { if (strstr(opts, "errors=panic") || strstr(opts, "errors=remount-ro") == 0) strcat(opts, ",errors=continue"); } else if (strcmp(fs, "xfs") == 0) { strcat(opts, ",nouuid"); } res = mount(source, target, fs, flags, opts); if (res == -1) { err = errno; goto error_clear_loop; } res = open(target, O_RDONLY | O_DIRECTORY); if (res == -1) { err = errno; } error_clear_loop: if (need_loop_device) { ioctl(loopfd, LOOP_CLR_FD, 0); close(loopfd); close(memfd); } errno = err; return res; } static int inject_fault(int nth) { int fd; fd = open("/proc/thread-self/fail-nth", O_RDWR); if (fd == -1) exit(1); char buf[16]; sprintf(buf, "%d", nth); if (write(fd, buf, strlen(buf)) != (ssize_t)strlen(buf)) exit(1); return fd; } 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 reset_loop() { char buf[64]; snprintf(buf, sizeof(buf), "/dev/loop%llu", procid); int loopfd = open(buf, O_RDWR); if (loopfd != -1) { ioctl(loopfd, LOOP_CLR_FD, 0); close(loopfd); } } static void setup_test() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setpgrp(); write_file("/proc/self/oom_score_adj", "1000"); } static void setup_fault() { static struct { const char* file; const char* val; bool fatal; } files[] = { {"/sys/kernel/debug/failslab/ignore-gfp-wait", "N", true}, {"/sys/kernel/debug/fail_futex/ignore-private", "N", false}, {"/sys/kernel/debug/fail_page_alloc/ignore-gfp-highmem", "N", false}, {"/sys/kernel/debug/fail_page_alloc/ignore-gfp-wait", "N", false}, {"/sys/kernel/debug/fail_page_alloc/min-order", "0", false}, }; unsigned i; for (i = 0; i < sizeof(files) / sizeof(files[0]); i++) { if (!write_file(files[i].file, files[i].val)) { if (files[i].fatal) exit(1); } } } #define KMEMLEAK_FILE "/sys/kernel/debug/kmemleak" static void setup_leak() { if (!write_file(KMEMLEAK_FILE, "scan")) exit(1); sleep(5); if (!write_file(KMEMLEAK_FILE, "scan")) exit(1); if (!write_file(KMEMLEAK_FILE, "clear")) exit(1); } static void check_leaks(void) { int fd = open(KMEMLEAK_FILE, O_RDWR); if (fd == -1) exit(1); uint64_t start = current_time_ms(); if (write(fd, "scan", 4) != 4) exit(1); sleep(1); while (current_time_ms() - start < 4 * 1000) sleep(1); if (write(fd, "scan", 4) != 4) exit(1); static char buf[128 << 10]; ssize_t n = read(fd, buf, sizeof(buf) - 1); if (n < 0) exit(1); int nleaks = 0; if (n != 0) { sleep(1); if (write(fd, "scan", 4) != 4) exit(1); if (lseek(fd, 0, SEEK_SET) < 0) exit(1); n = read(fd, buf, sizeof(buf) - 1); if (n < 0) exit(1); buf[n] = 0; char* pos = buf; char* end = buf + n; while (pos < end) { char* next = strstr(pos + 1, "unreferenced object"); if (!next) next = end; char prev = *next; *next = 0; fprintf(stderr, "BUG: memory leak\n%s\n", pos); *next = prev; pos = next; nleaks++; } } if (write(fd, "clear", 5) != 5) exit(1); close(fd); if (nleaks) exit(1); } 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 + (call == 1 ? 50 : 0)); break; } } for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++) sleep_ms(1); if (!collide) { collide = 1; goto again; } } static void execute_one(void); #define WAIT_FLAGS __WALL static void loop(void) { int iter = 0; for (;; iter++) { reset_loop(); int pid = fork(); if (pid < 0) exit(1); if (pid == 0) { 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; } check_leaks(); } } uint64_t r[2] = {0xffffffffffffffff, 0xffffffffffffffff}; void execute_call(int call) { intptr_t res = 0; switch (call) { case 0: NONFAILING(memcpy((void*)0x200004c0, "./file0\000", 8)); NONFAILING(memcpy((void*)0x20000000, "cgroup2\000", 8)); syscall(__NR_mount, 0ul, 0x200004c0ul, 0x20000000ul, 0ul, 0ul); break; case 1: NONFAILING(memcpy((void*)0x20000100, "./file0\000", 8)); res = -1; NONFAILING(res = syz_mount_image(0, 0x20000100, 0, 0, 0, 0x100020, 0)); if (res != -1) r[0] = res; break; case 2: NONFAILING(memcpy((void*)0x200004c0, "./file0\000", 8)); syscall(__NR_unlinkat, r[0], 0x200004c0ul, 0x200ul); break; case 3: NONFAILING(memcpy((void*)0x20000180, "./file0\000", 8)); res = syscall(__NR_open, 0x20000180ul, 0x240880ul, 0ul); if (res != -1) r[1] = res; break; case 4: NONFAILING(memcpy((void*)0x20000200, "./file0\000", 8)); inject_fault(30); syscall(__NR_mkdirat, r[1], 0x20000200ul, 0x86ul); 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); setup_leak(); setup_fault(); install_segv_handler(); loop(); return 0; }