[PATCH 5.11 10/36] io_uring: dont take uring_lock during iowq cancel

From: gregkh
Date: Wed Mar 10 2021 - 08:25:30 EST


From: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

From: Pavel Begunkov <asml.silence@xxxxxxxxx>

commit 792bb6eb862333658bf1bd2260133f0507e2da8d upstream

[ 97.866748] a.out/2890 is trying to acquire lock:
[ 97.867829] ffff8881046763e8 (&ctx->uring_lock){+.+.}-{3:3}, at:
io_wq_submit_work+0x155/0x240
[ 97.869735]
[ 97.869735] but task is already holding lock:
[ 97.871033] ffff88810dfe0be8 (&ctx->uring_lock){+.+.}-{3:3}, at:
__x64_sys_io_uring_enter+0x3f0/0x5b0
[ 97.873074]
[ 97.873074] other info that might help us debug this:
[ 97.874520] Possible unsafe locking scenario:
[ 97.874520]
[ 97.875845] CPU0
[ 97.876440] ----
[ 97.877048] lock(&ctx->uring_lock);
[ 97.877961] lock(&ctx->uring_lock);
[ 97.878881]
[ 97.878881] *** DEADLOCK ***
[ 97.878881]
[ 97.880341] May be due to missing lock nesting notation
[ 97.880341]
[ 97.881952] 1 lock held by a.out/2890:
[ 97.882873] #0: ffff88810dfe0be8 (&ctx->uring_lock){+.+.}-{3:3}, at:
__x64_sys_io_uring_enter+0x3f0/0x5b0
[ 97.885108]
[ 97.885108] stack backtrace:
[ 97.890457] Call Trace:
[ 97.891121] dump_stack+0xac/0xe3
[ 97.891972] __lock_acquire+0xab6/0x13a0
[ 97.892940] lock_acquire+0x2c3/0x390
[ 97.894894] __mutex_lock+0xae/0x9f0
[ 97.901101] io_wq_submit_work+0x155/0x240
[ 97.902112] io_wq_cancel_cb+0x162/0x490
[ 97.904126] io_async_find_and_cancel+0x3b/0x140
[ 97.905247] io_issue_sqe+0x86d/0x13e0
[ 97.909122] __io_queue_sqe+0x10b/0x550
[ 97.913971] io_queue_sqe+0x235/0x470
[ 97.914894] io_submit_sqes+0xcce/0xf10
[ 97.917872] __x64_sys_io_uring_enter+0x3fb/0x5b0
[ 97.921424] do_syscall_64+0x2d/0x40
[ 97.922329] entry_SYSCALL_64_after_hwframe+0x44/0xa9

While holding uring_lock, e.g. from inline execution, async cancel
request may attempt cancellations through io_wq_submit_work, which may
try to grab a lock. Delay it to task_work, so we do it from a clean
context and don't have to worry about locking.

Cc: <stable@xxxxxxxxxxxxxxx> # 5.5+
Fixes: c07e6719511e ("io_uring: hold uring_lock while completing failed polled io in io_wq_submit_work()")
Reported-by: Abaci <abaci@xxxxxxxxxxxxxxxxx>
Reported-by: Hao Xu <haoxu@xxxxxxxxxxxxxxxxx>
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
fs/io_uring.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)

--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2198,7 +2198,9 @@ static void io_req_task_cancel(struct ca
struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
struct io_ring_ctx *ctx = req->ctx;

+ mutex_lock(&ctx->uring_lock);
__io_req_task_cancel(req, -ECANCELED);
+ mutex_unlock(&ctx->uring_lock);
percpu_ref_put(&ctx->refs);
}

@@ -6372,8 +6374,13 @@ static void io_wq_submit_work(struct io_
if (timeout)
io_queue_linked_timeout(timeout);

- if (work->flags & IO_WQ_WORK_CANCEL)
- ret = -ECANCELED;
+ if (work->flags & IO_WQ_WORK_CANCEL) {
+ /* io-wq is going to take down one */
+ refcount_inc(&req->refs);
+ percpu_ref_get(&req->ctx->refs);
+ io_req_task_work_add_fallback(req, io_req_task_cancel);
+ return;
+ }

if (!ret) {
do {