IO-Uring Archive on lore.kernel.org
 help / color / Atom feed
* [PATCH liburing] Fix hang in in io_uring_get_cqe() with iopoll
@ 2020-06-21 10:30 Pavel Begunkov
  2020-06-21 15:23 ` Jens Axboe
  0 siblings, 1 reply; 3+ messages in thread
From: Pavel Begunkov @ 2020-06-21 10:30 UTC (permalink / raw)
  To: Jens Axboe, io-uring

Because of need_resched() check, io_uring_enter() -> io_iopoll_check()
can return 0 even if @min_complete wasn't satisfied. If that's the
case, __io_uring_get_cqe() sets submit=0 and wait_nr=0, disabling
setting IORING_ENTER_GETEVENTS as well. So, it goes crazy calling
io_uring_enter() in a loop, not actually submitting nor polling.

Set @wait_nr based on actual number of CQEs ready.
BTW, atomic_load_acquire() in io_uring_cq_ready() can be replaced
with a relaxed one for this particular place.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 src/queue.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/src/queue.c b/src/queue.c
index 14a0777..638d0ac 100644
--- a/src/queue.c
+++ b/src/queue.c
@@ -32,6 +32,14 @@ static inline bool sq_ring_needs_enter(struct io_uring *ring,
 	return false;
 }
 
+static inline unsigned int io_adjut_wait_nr(struct io_uring *ring,
+					    unsigned int to_wait)
+{
+	unsigned int ready = io_uring_cq_ready(ring);
+
+	return (to_wait <= ready) ? 0 : (to_wait - ready);
+}
+
 int __io_uring_get_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr,
 		       unsigned submit, unsigned wait_nr, sigset_t *sigmask)
 {
@@ -60,7 +68,8 @@ int __io_uring_get_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr,
 			err = -errno;
 		} else if (ret == (int)submit) {
 			submit = 0;
-			wait_nr = 0;
+			if (to_wait)
+				wait_nr = io_adjut_wait_nr(ring, to_wait);
 		} else {
 			submit -= ret;
 		}
-- 
2.24.0


^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH liburing] Fix hang in in io_uring_get_cqe() with iopoll
  2020-06-21 10:30 [PATCH liburing] Fix hang in in io_uring_get_cqe() with iopoll Pavel Begunkov
@ 2020-06-21 15:23 ` Jens Axboe
  2020-06-21 15:30   ` Pavel Begunkov
  0 siblings, 1 reply; 3+ messages in thread
From: Jens Axboe @ 2020-06-21 15:23 UTC (permalink / raw)
  To: Pavel Begunkov, io-uring

On 6/21/20 4:30 AM, Pavel Begunkov wrote:
> Because of need_resched() check, io_uring_enter() -> io_iopoll_check()
> can return 0 even if @min_complete wasn't satisfied. If that's the
> case, __io_uring_get_cqe() sets submit=0 and wait_nr=0, disabling
> setting IORING_ENTER_GETEVENTS as well. So, it goes crazy calling
> io_uring_enter() in a loop, not actually submitting nor polling.
> 
> Set @wait_nr based on actual number of CQEs ready.
> BTW, atomic_load_acquire() in io_uring_cq_ready() can be replaced
> with a relaxed one for this particular place.

Can you preface this with an addition of __io_uring_cqe_ready() that
doesn't include the load acquire?

Also, s/io_adjut_wait_nr/io_adjust_wait_nr for the patch.

-- 
Jens Axboe


^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH liburing] Fix hang in in io_uring_get_cqe() with iopoll
  2020-06-21 15:23 ` Jens Axboe
@ 2020-06-21 15:30   ` Pavel Begunkov
  0 siblings, 0 replies; 3+ messages in thread
From: Pavel Begunkov @ 2020-06-21 15:30 UTC (permalink / raw)
  To: Jens Axboe, io-uring

On 21/06/2020 18:23, Jens Axboe wrote:
> On 6/21/20 4:30 AM, Pavel Begunkov wrote:
>> Because of need_resched() check, io_uring_enter() -> io_iopoll_check()
>> can return 0 even if @min_complete wasn't satisfied. If that's the
>> case, __io_uring_get_cqe() sets submit=0 and wait_nr=0, disabling
>> setting IORING_ENTER_GETEVENTS as well. So, it goes crazy calling
>> io_uring_enter() in a loop, not actually submitting nor polling.
>>
>> Set @wait_nr based on actual number of CQEs ready.
>> BTW, atomic_load_acquire() in io_uring_cq_ready() can be replaced
>> with a relaxed one for this particular place.
> 
> Can you preface this with an addition of __io_uring_cqe_ready() that
> doesn't include the load acquire?

Sure

> Also, s/io_adjut_wait_nr/io_adjust_wait_nr for the patch.
Ouch, a typo


-- 
Pavel Begunkov

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, back to index

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-06-21 10:30 [PATCH liburing] Fix hang in in io_uring_get_cqe() with iopoll Pavel Begunkov
2020-06-21 15:23 ` Jens Axboe
2020-06-21 15:30   ` Pavel Begunkov

IO-Uring Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/io-uring/0 io-uring/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 io-uring io-uring/ https://lore.kernel.org/io-uring \
		io-uring@vger.kernel.org
	public-inbox-index io-uring

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.io-uring


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git