io_uring: fix potential ABBA deadlock in ->show_fdinfo()

syzbot reports a potential lock deadlock between the normal IO path and
->show_fdinfo():

======================================================
WARNING: possible circular locking dependency detected
5.9.0-rc6-syzkaller #0 Not tainted
------------------------------------------------------
syz-executor.2/19710 is trying to acquire lock:
ffff888098ddc450 (sb_writers#4){.+.+}-{0:0}, at: io_write+0x6b5/0xb30 fs/io_uring.c:3296

but task is already holding lock:
ffff8880a11b8428 (&ctx->uring_lock){+.+.}-{3:3}, at: __do_sys_io_uring_enter+0xe9a/0x1bd0 fs/io_uring.c:8348

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #2 (&ctx->uring_lock){+.+.}-{3:3}:
       __mutex_lock_common kernel/locking/mutex.c:956 [inline]
       __mutex_lock+0x134/0x10e0 kernel/locking/mutex.c:1103
       __io_uring_show_fdinfo fs/io_uring.c:8417 [inline]
       io_uring_show_fdinfo+0x194/0xc70 fs/io_uring.c:8460
       seq_show+0x4a8/0x700 fs/proc/fd.c:65
       seq_read+0x432/0x1070 fs/seq_file.c:208
       do_loop_readv_writev fs/read_write.c:734 [inline]
       do_loop_readv_writev fs/read_write.c:721 [inline]
       do_iter_read+0x48e/0x6e0 fs/read_write.c:955
       vfs_readv+0xe5/0x150 fs/read_write.c:1073
       kernel_readv fs/splice.c:355 [inline]
       default_file_splice_read.constprop.0+0x4e6/0x9e0 fs/splice.c:412
       do_splice_to+0x137/0x170 fs/splice.c:871
       splice_direct_to_actor+0x307/0x980 fs/splice.c:950
       do_splice_direct+0x1b3/0x280 fs/splice.c:1059
       do_sendfile+0x55f/0xd40 fs/read_write.c:1540
       __do_sys_sendfile64 fs/read_write.c:1601 [inline]
       __se_sys_sendfile64 fs/read_write.c:1587 [inline]
       __x64_sys_sendfile64+0x1cc/0x210 fs/read_write.c:1587
       do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
       entry_SYSCALL_64_after_hwframe+0x44/0xa9

-> #1 (&p->lock){+.+.}-{3:3}:
       __mutex_lock_common kernel/locking/mutex.c:956 [inline]
       __mutex_lock+0x134/0x10e0 kernel/locking/mutex.c:1103
       seq_read+0x61/0x1070 fs/seq_file.c:155
       pde_read fs/proc/inode.c:306 [inline]
       proc_reg_read+0x221/0x300 fs/proc/inode.c:318
       do_loop_readv_writev fs/read_write.c:734 [inline]
       do_loop_readv_writev fs/read_write.c:721 [inline]
       do_iter_read+0x48e/0x6e0 fs/read_write.c:955
       vfs_readv+0xe5/0x150 fs/read_write.c:1073
       kernel_readv fs/splice.c:355 [inline]
       default_file_splice_read.constprop.0+0x4e6/0x9e0 fs/splice.c:412
       do_splice_to+0x137/0x170 fs/splice.c:871
       splice_direct_to_actor+0x307/0x980 fs/splice.c:950
       do_splice_direct+0x1b3/0x280 fs/splice.c:1059
       do_sendfile+0x55f/0xd40 fs/read_write.c:1540
       __do_sys_sendfile64 fs/read_write.c:1601 [inline]
       __se_sys_sendfile64 fs/read_write.c:1587 [inline]
       __x64_sys_sendfile64+0x1cc/0x210 fs/read_write.c:1587
       do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
       entry_SYSCALL_64_after_hwframe+0x44/0xa9

-> #0 (sb_writers#4){.+.+}-{0:0}:
       check_prev_add kernel/locking/lockdep.c:2496 [inline]
       check_prevs_add kernel/locking/lockdep.c:2601 [inline]
       validate_chain kernel/locking/lockdep.c:3218 [inline]
       __lock_acquire+0x2a96/0x5780 kernel/locking/lockdep.c:4441
       lock_acquire+0x1f3/0xaf0 kernel/locking/lockdep.c:5029
       percpu_down_read include/linux/percpu-rwsem.h:51 [inline]
       __sb_start_write+0x228/0x450 fs/super.c:1672
       io_write+0x6b5/0xb30 fs/io_uring.c:3296
       io_issue_sqe+0x18f/0x5c50 fs/io_uring.c:5719
       __io_queue_sqe+0x280/0x1160 fs/io_uring.c:6175
       io_queue_sqe+0x692/0xfa0 fs/io_uring.c:6254
       io_submit_sqe fs/io_uring.c:6324 [inline]
       io_submit_sqes+0x1761/0x2400 fs/io_uring.c:6521
       __do_sys_io_uring_enter+0xeac/0x1bd0 fs/io_uring.c:8349
       do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
       entry_SYSCALL_64_after_hwframe+0x44/0xa9

other info that might help us debug this:

Chain exists of:
  sb_writers#4 --> &p->lock --> &ctx->uring_lock

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&ctx->uring_lock);
                               lock(&p->lock);
                               lock(&ctx->uring_lock);
  lock(sb_writers#4);

 *** DEADLOCK ***

1 lock held by syz-executor.2/19710:
 #0: ffff8880a11b8428 (&ctx->uring_lock){+.+.}-{3:3}, at: __do_sys_io_uring_enter+0xe9a/0x1bd0 fs/io_uring.c:8348

stack backtrace:
CPU: 0 PID: 19710 Comm: syz-executor.2 Not tainted 5.9.0-rc6-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x198/0x1fd lib/dump_stack.c:118
 check_noncircular+0x324/0x3e0 kernel/locking/lockdep.c:1827
 check_prev_add kernel/locking/lockdep.c:2496 [inline]
 check_prevs_add kernel/locking/lockdep.c:2601 [inline]
 validate_chain kernel/locking/lockdep.c:3218 [inline]
 __lock_acquire+0x2a96/0x5780 kernel/locking/lockdep.c:4441
 lock_acquire+0x1f3/0xaf0 kernel/locking/lockdep.c:5029
 percpu_down_read include/linux/percpu-rwsem.h:51 [inline]
 __sb_start_write+0x228/0x450 fs/super.c:1672
 io_write+0x6b5/0xb30 fs/io_uring.c:3296
 io_issue_sqe+0x18f/0x5c50 fs/io_uring.c:5719
 __io_queue_sqe+0x280/0x1160 fs/io_uring.c:6175
 io_queue_sqe+0x692/0xfa0 fs/io_uring.c:6254
 io_submit_sqe fs/io_uring.c:6324 [inline]
 io_submit_sqes+0x1761/0x2400 fs/io_uring.c:6521
 __do_sys_io_uring_enter+0xeac/0x1bd0 fs/io_uring.c:8349
 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45e179
Code: 3d b2 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 0b b2 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f1194e74c78 EFLAGS: 00000246 ORIG_RAX: 00000000000001aa
RAX: ffffffffffffffda RBX: 00000000000082c0 RCX: 000000000045e179
RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000004
RBP: 000000000118cf98 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 000000000118cf4c
R13: 00007ffd1aa5756f R14: 00007f1194e759c0 R15: 000000000118cf4c

Fix this by just not diving into details if we fail to trylock the
io_uring mutex. We know the ctx isn't going away during this operation,
but we cannot safely iterate buffers/files/personalities if we don't
hold the io_uring mutex.

Reported-by: syzbot+2f8fa4e860edc3066aba@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 14 insertions, 5 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5dcc77b42f0d..556e4a2ead07 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8414,11 +8414,19 @@ static int io_uring_show_cred(int id, void *p, void *data)
 
 static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 {
+	bool has_lock;
 	int i;
 
-	mutex_lock(&ctx->uring_lock);
+	/*
+	 * Avoid ABBA deadlock between the seq lock and the io_uring mutex,
+	 * since fdinfo case grabs it in the opposite direction of normal use
+	 * cases. If we fail to get the lock, we just don't iterate any
+	 * structures that could be going away outside the io_uring mutex.
+	 */
+	has_lock = mutex_trylock(&ctx->uring_lock);
+
 	seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files);
-	for (i = 0; i < ctx->nr_user_files; i++) {
+	for (i = 0; has_lock && i < ctx->nr_user_files; i++) {
 		struct fixed_file_table *table;
 		struct file *f;
 
@@ -8430,13 +8438,13 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 			seq_printf(m, "%5u: <none>\n", i);
 	}
 	seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs);
-	for (i = 0; i < ctx->nr_user_bufs; i++) {
+	for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) {
 		struct io_mapped_ubuf *buf = &ctx->user_bufs[i];
 
 		seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf,
 						(unsigned int) buf->len);
 	}
-	if (!idr_is_empty(&ctx->personality_idr)) {
+	if (has_lock && !idr_is_empty(&ctx->personality_idr)) {
 		seq_printf(m, "Personalities:\n");
 		idr_for_each(&ctx->personality_idr, io_uring_show_cred, m);
 	}
@@ -8451,7 +8459,8 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 					req->task->task_works != NULL);
 	}
 	spin_unlock_irq(&ctx->completion_lock);
-	mutex_unlock(&ctx->uring_lock);
+	if (has_lock)
+		mutex_unlock(&ctx->uring_lock);
 }
 
 static void io_uring_show_fdinfo(struct seq_file *m, struct file *f)