[PATCH AUTOSEL 5.2 74/76] io_uring: add need_resched() check in inner poll loop

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Jens Axboe <axboe@xxxxxxxxx>

[ Upstream commit 08f5439f1df25a6cf6cf4c72cf6c13025599ce67 ]

The outer poll loop checks for whether we need to reschedule, and
returns to userspace if we do. However, it's possible to get stuck
in the inner loop as well, if the CPU we are running on needs to
reschedule to finish the IO work.

Add the need_resched() check in the inner loop as well. This fixes
a potential hang if the kernel is configured with
CONFIG_PREEMPT_VOLUNTARY=y.

Reported-by: Sagi Grimberg <sagi@xxxxxxxxxxx>
Reviewed-by: Sagi Grimberg <sagi@xxxxxxxxxxx>
Tested-by: Sagi Grimberg <sagi@xxxxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 fs/io_uring.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 83e3cede11220..03cd8f5bba850 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -716,7 +716,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events,
 				long min)
 {
-	while (!list_empty(&ctx->poll_list)) {
+	while (!list_empty(&ctx->poll_list) && !need_resched()) {
 		int ret;
 
 		ret = io_do_iopoll(ctx, nr_events, min);
@@ -743,6 +743,12 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
 		unsigned int nr_events = 0;
 
 		io_iopoll_getevents(ctx, &nr_events, 1);
+
+		/*
+		 * Ensure we allow local-to-the-cpu processing to take place,
+		 * in this case we need to ensure that we reap all events.
+		 */
+		cond_resched();
 	}
 	mutex_unlock(&ctx->uring_lock);
 }
-- 
2.20.1




[Index of Archives]     [Linux Kernel]     [Kernel Development Newbies]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite Hiking]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux