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@xxxxxxxxx>
Signed-off-by: Dylan Yudaken <dylany@xxxxxx>
---
fs/io_uring.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 63299896555d..fced35d3ee85 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -968,6 +968,7 @@ 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 */
@@ -1062,6 +1063,7 @@ 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,
base-commit: 6d4809f49bec8dc3b244debcb97f78239e52f5bb
--
2.30.2
