From a185f1db59f13de73aa470559030e90e50b34d93 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 23 Mar 2021 10:52:38 +0000
Subject: [PATCH] io_uring: do ctx sqd ejection in a clear context
WARNING: CPU: 1 PID: 27907 at fs/io_uring.c:7147 io_sq_thread_park+0xb5/0xd0 fs/io_uring.c:7147
CPU: 1 PID: 27907 Comm: iou-sqp-27905 Not tainted 5.12.0-rc4-syzkaller #0
RIP: 0010:io_sq_thread_park+0xb5/0xd0 fs/io_uring.c:7147
Call Trace:
io_ring_ctx_wait_and_kill+0x214/0x700 fs/io_uring.c:8619
io_uring_release+0x3e/0x50 fs/io_uring.c:8646
__fput+0x288/0x920 fs/file_table.c:280
task_work_run+0xdd/0x1a0 kernel/task_work.c:140
io_run_task_work fs/io_uring.c:2238 [inline]
io_run_task_work fs/io_uring.c:2228 [inline]
io_uring_try_cancel_requests+0x8ec/0xc60 fs/io_uring.c:8770
io_uring_cancel_sqpoll+0x1cf/0x290 fs/io_uring.c:8974
io_sqpoll_cancel_cb+0x87/0xb0 fs/io_uring.c:8907
io_run_task_work_head+0x58/0xb0 fs/io_uring.c:1961
io_sq_thread+0x3e2/0x18d0 fs/io_uring.c:6763
ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294
May happen that last ctx ref is killed in io_uring_cancel_sqpoll(), so
fput callback (i.e. io_uring_release()) is enqueued through task_work,
and run by same cancellation. As it's deeply nested we can't do parking
or taking sqd->lock there, because its state is unclear. So avoid
ctx ejection from sqd list from io_ring_ctx_wait_and_kill() and do it
in a clear context in io_ring_exit_work().
Fixes: f6d54255f423 ("io_uring: halt SQO submission on ctx exit")
Reported-by: syzbot+e3a3f84f5cecf61f0583@syzkaller.appspotmail.com
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/e90df88b8ff2cabb14a7534601d35d62ab4cb8c7.1616496707.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/io_uring.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index f3ae83a2d7bc04..8c5789b96dbb6e 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -8564,6 +8564,14 @@ static void io_ring_exit_work(struct work_struct *work)
struct io_tctx_node *node;
int ret;
+ /* prevent SQPOLL from submitting new requests */
+ if (ctx->sq_data) {
+ io_sq_thread_park(ctx->sq_data);
+ list_del_init(&ctx->sqd_list);
+ io_sqd_update_thread_idle(ctx->sq_data);
+ io_sq_thread_unpark(ctx->sq_data);
+ }
+
/*
* If we're doing polled IO and end up having requests being
* submitted async (out-of-line), then completions can come in while
@@ -8615,14 +8623,6 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
io_unregister_personality(ctx, index);
mutex_unlock(&ctx->uring_lock);
- /* prevent SQPOLL from submitting new requests */
- if (ctx->sq_data) {
- io_sq_thread_park(ctx->sq_data);
- list_del_init(&ctx->sqd_list);
- io_sqd_update_thread_idle(ctx->sq_data);
- io_sq_thread_unpark(ctx->sq_data);
- }
-
io_kill_timeouts(ctx, NULL, NULL);
io_poll_remove_all(ctx, NULL, NULL);
--
GitLab