summary refs log tree commit diff
path: root/fs/io_uring.c
diff options
context:
space:
mode:
authorDylan Yudaken <dylany@fb.com>2022-03-25 02:37:55 -0700
committerJens Axboe <axboe@kernel.dk>2022-03-25 06:30:23 -0600
commit52dd86406dfa322c8d42b3a4328858abdc6f1d85 (patch)
tree401c67c36d89fd07932342b741a74d1c745dc933 /fs/io_uring.c
parent34d2bfe7d4b65b375d0edf704133a6b6970f9d81 (diff)
downloadlinux-52dd86406dfa322c8d42b3a4328858abdc6f1d85.tar.gz
io_uring: enable EPOLLEXCLUSIVE for accept poll
When polling sockets for accept, use EPOLLEXCLUSIVE. This is helpful
when multiple accept SQEs are submitted.

For O_NONBLOCK sockets multiple queued SQEs would previously have all
completed at once, but most with -EAGAIN as the result. Now only one
wakes up and completes.

For sockets without O_NONBLOCK there is no user facing change, but
internally the extra requests would previously be queued onto a worker
thread as they would wake up with no connection waiting, and be
punted. Now they do not wake up unnecessarily.

Co-developed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Dylan Yudaken <dylany@fb.com>
Link: https://lore.kernel.org/r/20220325093755.4123343-1-dylany@fb.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'fs/io_uring.c')
-rw-r--r--fs/io_uring.c5
1 files changed, 4 insertions, 1 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c
index bb40c80fd9ca..e72f58e2d06d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -967,6 +967,7 @@ struct io_op_def {
 	/* set if opcode supports polled "wait" */
 	unsigned		pollin : 1;
 	unsigned		pollout : 1;
+	unsigned		poll_exclusive : 1;
 	/* op supports buffer selection */
 	unsigned		buffer_select : 1;
 	/* do prep async if is going to be punted */
@@ -1061,6 +1062,7 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
 		.pollin			= 1,
+		.poll_exclusive		= 1,
 	},
 	[IORING_OP_ASYNC_CANCEL] = {
 		.audit_skip		= 1,
@@ -6280,7 +6282,8 @@ static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
 	} else {
 		mask |= POLLOUT | POLLWRNORM;
 	}
-
+	if (def->poll_exclusive)
+		mask |= EPOLLEXCLUSIVE;
 	if (!(issue_flags & IO_URING_F_UNLOCKED) &&
 	    !list_empty(&ctx->apoll_cache)) {
 		apoll = list_first_entry(&ctx->apoll_cache, struct async_poll,