[PATCH 5.10 003/103] io_uring: limit {io|sq}poll submit locking scope

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

 



From: Pavel Begunkov <asml.silence@xxxxxxxxx>

commit 89448c47b8452b67c146dc6cad6f737e004c5caf upstream

We don't need to take uring_lock for SQPOLL|IOPOLL to do
io_cqring_overflow_flush() when cq_overflow_list is empty, remove it
from the hot path.

Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 fs/io_uring.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3974b4f124b6a..5ba312ab99786 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -9024,10 +9024,13 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	 */
 	ret = 0;
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
-		io_ring_submit_lock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
-		if (!list_empty_careful(&ctx->cq_overflow_list))
+		if (!list_empty_careful(&ctx->cq_overflow_list)) {
+			bool needs_lock = ctx->flags & IORING_SETUP_IOPOLL;
+
+			io_ring_submit_lock(ctx, needs_lock);
 			io_cqring_overflow_flush(ctx, false, NULL, NULL);
-		io_ring_submit_unlock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
+			io_ring_submit_unlock(ctx, needs_lock);
+		}
 		if (flags & IORING_ENTER_SQ_WAKEUP)
 			wake_up(&ctx->sq_data->wait);
 		if (flags & IORING_ENTER_SQ_WAIT)
-- 
2.27.0






[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