If we successfully cancel a work item but that work item needs to be
processed through task_work, then we can be sleeping uninterruptibly
in io_uring_cancel_generic() and never process it. Hence we don't
make forward progress and we end up with an uninterruptible sleep
warning.
Add the waitqueue earlier to ensure that any wakeups from cancelations
are seen, and switch to using uninterruptible sleep so that postponed
task_work additions get seen and processed.
While in there, correct a comment that should be IFF, not IIF.
Reported-by: syzbot+21e6887c0be14181206d@xxxxxxxxxxxxxxxxxxxxxxxxx
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
fs/io_uring.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index b4d5b8d168bf..738076264436 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -9826,7 +9826,7 @@ static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
/*
* Find any io_uring ctx that this task has registered or done IO on, and cancel
- * requests. @sqd should be not-null IIF it's an SQPOLL thread cancellation.
+ * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation.
*/
static __cold void io_uring_cancel_generic(bool cancel_all,
struct io_sq_data *sqd)
@@ -9851,6 +9851,8 @@ static __cold void io_uring_cancel_generic(bool cancel_all,
if (!inflight)
break;
+ prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE);
+
if (!sqd) {
struct io_tctx_node *node;
unsigned long index;
@@ -9868,8 +9870,9 @@ static __cold void io_uring_cancel_generic(bool cancel_all,
cancel_all);
}
- prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
+ io_run_task_work();
io_uring_drop_tctx_refs(current);
+
/*
* If we've seen completions, retry without waiting. This
* avoids a race where a completion comes in before we did
--
2.34.1
