Hi, We would like to report the following bug which has been found by our modified version of syzkaller. ====================================================== description: KASAN: use-after-free Read in __io_remove_buffers affected file: fs/io_uring.c kernel version: 5.19-rc6 kernel commit: 32346491ddf24599decca06190ebca03ff9de7f8 git tree: upstream kernel config: https://syzkaller.appspot.com/text?tag=KernelConfig&x=cd73026ceaed1402 crash reproducer: attached ====================================================== Crash log: ====================================================== BUG: KASAN: use-after-free in __io_remove_buffers.isra.0+0x401/0x530 fs/io_uring.c:5540 Read of size 2 at addr ffff88812e562012 by task kworker/u4:9/3708 CPU: 0 PID: 3708 Comm: kworker/u4:9 Tainted: G OE 5.19.0-rc6-g2eae0556bb9d #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Workqueue: events_unbound io_ring_exit_work Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:313 [inline] print_report.cold+0xe5/0x659 mm/kasan/report.c:429 kasan_report+0x8a/0x1b0 mm/kasan/report.c:491 __io_remove_buffers.isra.0+0x401/0x530 fs/io_uring.c:5540 io_destroy_buffers fs/io_uring.c:11077 [inline] io_ring_ctx_free fs/io_uring.c:11159 [inline] io_ring_exit_work+0x9a2/0xf4b fs/io_uring.c:11338 process_one_work+0x9cc/0x1650 kernel/workqueue.c:2289 worker_thread+0x623/0x1070 kernel/workqueue.c:2436 kthread+0x2e9/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:302 </TASK> Allocated by task 10568: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:39 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:441 [inline] ____kasan_kmalloc mm/kasan/common.c:526 [inline] ____kasan_kmalloc mm/kasan/common.c:479 [inline] __kasan_kmalloc+0xb5/0xe0 mm/kasan/common.c:535 kasan_kmalloc include/linux/kasan.h:234 [inline] __kmalloc+0x1c9/0x4c0 mm/slub.c:4446 kcalloc include/linux/slab.h:671 [inline] io_init_bl_list.isra.0+0x24/0x102 fs/io_uring.c:5703 io_register_pbuf_ring fs/io_uring.c:12955 [inline] __io_uring_register.cold+0xd/0x10b5 fs/io_uring.c:13151 __do_sys_io_uring_register fs/io_uring.c:13187 [inline] __se_sys_io_uring_register fs/io_uring.c:13167 [inline] __x64_sys_io_uring_register+0x2f2/0x650 fs/io_uring.c:13167 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Freed by task 10568: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:39 kasan_set_track+0x21/0x30 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:378 ____kasan_slab_free mm/kasan/common.c:371 [inline] ____kasan_slab_free mm/kasan/common.c:329 [inline] __kasan_slab_free+0x12b/0x1a0 mm/kasan/common.c:379 kasan_slab_free include/linux/kasan.h:200 [inline] slab_free_hook mm/slub.c:1754 [inline] slab_free_freelist_hook mm/slub.c:1780 [inline] slab_free mm/slub.c:3536 [inline] kfree+0xec/0x4b0 mm/slub.c:4584 io_register_pbuf_ring fs/io_uring.c:12975 [inline] __io_uring_register+0x16aa/0x19d0 fs/io_uring.c:13151 __do_sys_io_uring_register fs/io_uring.c:13187 [inline] __se_sys_io_uring_register fs/io_uring.c:13167 [inline] __x64_sys_io_uring_register+0x2f2/0x650 fs/io_uring.c:13167 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Last potentially related work creation: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:39 __kasan_record_aux_stack+0xbe/0xd0 mm/kasan/generic.c:356 call_rcu kernel/rcu/tree.c:3126 [inline] call_rcu+0x99/0x740 kernel/rcu/tree.c:3101 netlink_release+0xe42/0x1cb0 net/netlink/af_netlink.c:815 __sock_release+0xcd/0x280 net/socket.c:650 sock_close+0x18/0x20 net/socket.c:1365 __fput+0x277/0x9d0 fs/file_table.c:317 task_work_run+0xe0/0x1a0 kernel/task_work.c:177 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:169 [inline] exit_to_user_mode_prepare+0x253/0x260 kernel/entry/common.c:201 __syscall_exit_to_user_mode_work kernel/entry/common.c:283 [inline] syscall_exit_to_user_mode+0x19/0x50 kernel/entry/common.c:294 do_syscall_64+0x42/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Second to last potentially related work creation: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:39 __kasan_record_aux_stack+0xbe/0xd0 mm/kasan/generic.c:356 call_rcu kernel/rcu/tree.c:3126 [inline] call_rcu+0x99/0x740 kernel/rcu/tree.c:3101 netlink_release+0xe42/0x1cb0 net/netlink/af_netlink.c:815 __sock_release+0xcd/0x280 net/socket.c:650 sock_close+0x18/0x20 net/socket.c:1365 __fput+0x277/0x9d0 fs/file_table.c:317 task_work_run+0xe0/0x1a0 kernel/task_work.c:177 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0xb1e/0x2dd0 kernel/exit.c:797 do_group_exit+0xd2/0x2f0 kernel/exit.c:927 get_signal+0x2842/0x2870 kernel/signal.c:2857 arch_do_signal_or_restart+0x82/0x2270 arch/x86/kernel/signal.c:869 exit_to_user_mode_loop kernel/entry/common.c:166 [inline] exit_to_user_mode_prepare+0x174/0x260 kernel/entry/common.c:201 __syscall_exit_to_user_mode_work kernel/entry/common.c:283 [inline] syscall_exit_to_user_mode+0x19/0x50 kernel/entry/common.c:294 do_syscall_64+0x42/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x46/0xb0 The buggy address belongs to the object at ffff88812e562000 which belongs to the cache kmalloc-2k of size 2048 The buggy address is located 18 bytes inside of 2048-byte region [ffff88812e562000, ffff88812e562800) The buggy address belongs to the physical page: page:ffffea0004b95800 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x12e560 head:ffffea0004b95800 order:3 compound_mapcount:0 compound_pincount:0 flags: 0x17ff00000010200(slab|head|node=0|zone=2|lastcpupid=0x7ff) raw: 017ff00000010200 ffffea0005da9600 dead000000000002 ffff888100042000 raw: 0000000000000000 0000000080080008 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd28c0(GFP_NOWAIT|__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 6706, tgid 6706 (syz-executor.4), ts 116920478716, free_ts 0 set_page_owner include/linux/page_owner.h:31 [inline] post_alloc_hook mm/page_alloc.c:2449 [inline] prep_new_page+0x297/0x330 mm/page_alloc.c:2456 get_page_from_freelist+0x2142/0x3c80 mm/page_alloc.c:4198 __alloc_pages+0x321/0x710 mm/page_alloc.c:5426 alloc_pages+0x119/0x250 mm/mempolicy.c:2272 alloc_slab_page mm/slub.c:1824 [inline] allocate_slab mm/slub.c:1969 [inline] new_slab+0x2a9/0x3f0 mm/slub.c:2029 ___slab_alloc+0xd5a/0x1140 mm/slub.c:3031 __slab_alloc.isra.0+0x4d/0xa0 mm/slub.c:3118 slab_alloc_node mm/slub.c:3209 [inline] __kmalloc_node_track_caller+0x321/0x440 mm/slub.c:4979 kmalloc_reserve+0x32/0xd0 net/core/skbuff.c:354 pskb_expand_head+0x148/0x1060 net/core/skbuff.c:1695 netlink_trim+0x1ea/0x240 net/netlink/af_netlink.c:1301 netlink_broadcast+0x5b/0xd00 net/netlink/af_netlink.c:1497 nlmsg_multicast include/net/netlink.h:1033 [inline] nlmsg_notify+0x8f/0x280 net/netlink/af_netlink.c:2544 rtnl_notify net/core/rtnetlink.c:767 [inline] rtmsg_ifinfo_send net/core/rtnetlink.c:3928 [inline] rtmsg_ifinfo_event.part.0+0xb6/0xe0 net/core/rtnetlink.c:3943 rtmsg_ifinfo_event net/core/rtnetlink.c:6147 [inline] rtnetlink_event+0x11e/0x150 net/core/rtnetlink.c:6140 notifier_call_chain+0xb5/0x200 kernel/notifier.c:87 page_owner free stack trace missing Memory state around the buggy address: ffff88812e561f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88812e561f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff88812e562000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88812e562080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88812e562100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb -- Thanks and Regards, Dipanjan
// autogenerated by syzkaller (https://github.com/google/syzkaller) #define _GNU_SOURCE #include <dirent.h> #include <endian.h> #include <errno.h> #include <fcntl.h> #include <pthread.h> #include <setjmp.h> #include <signal.h> #include <stdarg.h> #include <stdbool.h> #include <stdint.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/prctl.h> #include <sys/stat.h> #include <sys/syscall.h> #include <sys/types.h> #include <sys/wait.h> #include <time.h> #include <unistd.h> #include <linux/futex.h> #ifndef __NR_io_uring_register #define __NR_io_uring_register 427 #endif #ifndef __NR_io_uring_setup #define __NR_io_uring_setup 425 #endif static __thread int clone_ongoing; static __thread int skip_segv; static __thread jmp_buf segv_env; static void segv_handler(int sig, siginfo_t* info, void* ctx) { if (__atomic_load_n(&clone_ongoing, __ATOMIC_RELAXED) != 0) { exit(sig); } 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; } #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 static long syz_io_uring_submit(volatile long a0, volatile long a1, volatile long a2, volatile long a3) { char* ring_ptr = (char*)a0; char* sqes_ptr = (char*)a1; char* sqe = (char*)a2; uint32_t sqes_index = (uint32_t)a3; uint32_t sq_ring_entries = *(uint32_t*)(ring_ptr + SQ_RING_ENTRIES_OFFSET); uint32_t cq_ring_entries = *(uint32_t*)(ring_ptr + CQ_RING_ENTRIES_OFFSET); uint32_t sq_array_off = (CQ_CQES_OFFSET + cq_ring_entries * SIZEOF_IO_URING_CQE + 63) & ~63; if (sq_ring_entries) sqes_index %= sq_ring_entries; char* sqe_dest = sqes_ptr + sqes_index * SIZEOF_IO_URING_SQE; memcpy(sqe_dest, sqe, SIZEOF_IO_URING_SQE); uint32_t sq_ring_mask = *(uint32_t*)(ring_ptr + SQ_RING_MASK_OFFSET); uint32_t* sq_tail_ptr = (uint32_t*)(ring_ptr + SQ_TAIL_OFFSET); uint32_t sq_tail = *sq_tail_ptr & sq_ring_mask; uint32_t sq_tail_next = *sq_tail_ptr + 1; uint32_t* sq_array = (uint32_t*)(ring_ptr + sq_array_off); *(sq_array + sq_tail) = sqes_index; __atomic_store_n(sq_tail_ptr, sq_tail_next, __ATOMIC_RELEASE); return 0; } 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_test() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setpgrp(); write_file("/proc/self/oom_score_adj", "1000"); } 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; 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 (call == 3) break; event_timedwait(&th->done, 50); break; } } for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++) sleep_ms(1); } static void execute_one(void); #define WAIT_FLAGS __WALL static void loop(void) { int iter = 0; for (;; iter++) { 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; } } } uint64_t r[3] = {0xffffffffffffffff, 0xffffffffffffffff, 0x0}; void execute_call(int call) { intptr_t res = 0; switch (call) { case 0: NONFAILING(*(uint32_t*)0x20000284 = 0); NONFAILING(*(uint32_t*)0x20000288 = 0); NONFAILING(*(uint32_t*)0x2000028c = 0); NONFAILING(*(uint32_t*)0x20000290 = 0); NONFAILING(*(uint32_t*)0x20000298 = -1); NONFAILING(memset((void*)0x2000029c, 0, 12)); res = syscall(__NR_io_uring_setup, 0x1224, 0x20000280ul); if (res != -1) r[0] = res; break; case 1: NONFAILING(*(uint32_t*)0x20000284 = 0); NONFAILING(*(uint32_t*)0x20000288 = 0); NONFAILING(*(uint32_t*)0x2000028c = 0); NONFAILING(*(uint32_t*)0x20000290 = 0); NONFAILING(*(uint32_t*)0x20000298 = -1); NONFAILING(memset((void*)0x2000029c, 0, 12)); res = syscall(__NR_io_uring_setup, 0x1224, 0x20000280ul); if (res != -1) r[1] = res; break; case 2: res = syscall(__NR_io_uring_register, r[1], 9ul, 0ul, 0ul); if (res != -1) r[2] = res; break; case 3: syscall(__NR_io_uring_register, r[0], 0x16ul, 0x20000000ul, r[2]); break; case 4: NONFAILING(*(uint8_t*)0x200001c0 = 0x1c); NONFAILING(*(uint8_t*)0x200001c1 = 0); NONFAILING(*(uint16_t*)0x200001c2 = 0); NONFAILING(*(uint32_t*)0x200001c4 = -1); NONFAILING(*(uint64_t*)0x200001c8 = 0x20000000); NONFAILING(*(uint64_t*)0x20000000 = 0x40000); NONFAILING(*(uint64_t*)0x20000008 = 8); NONFAILING(*(uint64_t*)0x20000010 = 0); NONFAILING(*(uint64_t*)0x200001d0 = 0); NONFAILING(*(uint32_t*)0x200001d8 = 0x18); NONFAILING(*(uint32_t*)0x200001dc = 0); NONFAILING(*(uint64_t*)0x200001e0 = 0x23456); NONFAILING(*(uint16_t*)0x200001e8 = 0); NONFAILING(*(uint16_t*)0x200001ea = r[2]); NONFAILING(memset((void*)0x200001ec, 0, 20)); NONFAILING(syz_io_uring_submit(0, 0, 0x200001c0, 8)); 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); install_segv_handler(); loop(); return 0; }
Attachment:
repro.syz
Description: Binary data
