summaryrefslogtreecommitdiff
path: root/fs/io-wq.c
diff options
context:
space:
mode:
authorJens Axboe <axboe@kernel.dk>2021-03-25 10:16:12 -0600
committerJens Axboe <axboe@kernel.dk>2021-03-25 10:16:12 -0600
commitf5d2d23bf0d948ce0b9307b7bacae7ff0bc03c71 (patch)
treeea53dc43d81e409182217b7914b761d5bea545a5 /fs/io-wq.c
parenta185f1db59f13de73aa470559030e90e50b34d93 (diff)
io-wq: fix race around pending work on teardown
syzbot reports that it's triggering the warning condition on having pending work on shutdown: WARNING: CPU: 1 PID: 12346 at fs/io-wq.c:1061 io_wq_destroy fs/io-wq.c:1061 [inline] WARNING: CPU: 1 PID: 12346 at fs/io-wq.c:1061 io_wq_put+0x153/0x260 fs/io-wq.c:1072 Modules linked in: CPU: 1 PID: 12346 Comm: syz-executor.5 Not tainted 5.12.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:io_wq_destroy fs/io-wq.c:1061 [inline] RIP: 0010:io_wq_put+0x153/0x260 fs/io-wq.c:1072 Code: 8d e8 71 90 ea 01 49 89 c4 41 83 fc 40 7d 4f e8 33 4d 97 ff 42 80 7c 2d 00 00 0f 85 77 ff ff ff e9 7a ff ff ff e8 1d 4d 97 ff <0f> 0b eb b9 8d 6b ff 89 ee 09 de bf ff ff ff ff e8 18 51 97 ff 09 RSP: 0018:ffffc90001ebfb08 EFLAGS: 00010293 RAX: ffffffff81e16083 RBX: ffff888019038040 RCX: ffff88801e86b780 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000040 RBP: 1ffff1100b2f8a80 R08: ffffffff81e15fce R09: ffffed100b2f8a82 R10: ffffed100b2f8a82 R11: 0000000000000000 R12: 0000000000000000 R13: dffffc0000000000 R14: ffff8880597c5400 R15: ffff888019038000 FS: 00007f8dcd89c700(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055e9a054e160 CR3: 000000001dfb8000 CR4: 00000000001506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: io_uring_clean_tctx+0x1b7/0x210 fs/io_uring.c:8802 __io_uring_files_cancel+0x13c/0x170 fs/io_uring.c:8820 io_uring_files_cancel include/linux/io_uring.h:47 [inline] do_exit+0x258/0x2340 kernel/exit.c:780 do_group_exit+0x168/0x2d0 kernel/exit.c:922 get_signal+0x1734/0x1ef0 kernel/signal.c:2773 arch_do_signal_or_restart+0x3c/0x610 arch/x86/kernel/signal.c:811 handle_signal_work kernel/entry/common.c:147 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0xac/0x1e0 kernel/entry/common.c:208 __syscall_exit_to_user_mode_work kernel/entry/common.c:290 [inline] syscall_exit_to_user_mode+0x48/0x180 kernel/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x465f69 which shouldn't happen, but seems to be possible due to a race on whether or not the io-wq manager sees a fatal signal first, or whether the io-wq workers do. If we race with queueing work and then send a fatal signal to the owning task, and the io-wq worker sees that before the manager sets IO_WQ_BIT_EXIT, then it's possible to have the worker exit and leave work behind. Just turn the WARN_ON_ONCE() into a cancelation condition instead. Reported-by: syzbot+77a738a6bc947bf639ca@syzkaller.appspotmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'fs/io-wq.c')
-rw-r--r--fs/io-wq.c6
1 files changed, 5 insertions, 1 deletions
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 2dd43bdb9c7b..b7c1fa932cb3 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -1063,7 +1063,11 @@ static void io_wq_destroy(struct io_wq *wq)
for_each_node(node) {
struct io_wqe *wqe = wq->wqes[node];
- WARN_ON_ONCE(!wq_list_empty(&wqe->work_list));
+ struct io_cb_cancel_data match = {
+ .fn = io_wq_work_match_all,
+ .cancel_all = true,
+ };
+ io_wqe_cancel_pending_work(wqe, &match);
kfree(wqe);
}
io_wq_put_hash(wq->hash);