From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 21 Apr 2022 01:27:41 +0000 (-0600)
Subject: io_uring: allow re-poll if we made progress
X-Git-Tag: v5.19-rc1~250^2~11
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=10c873334febaeea9aa0c25c10b5ac0951b77a5f;p=thirdparty%2Fkernel%2Flinux.git

io_uring: allow re-poll if we made progress

We currently check REQ_F_POLLED before arming async poll for a
notification to retry. If it's set, then we don't allow poll and will
punt to io-wq instead. This is done to prevent a situation where a buggy
driver will repeatedly return that there's space/data available yet we
get -EAGAIN.

However, if we already transferred data, then it should be safe to rely
on poll again. Gate the check on whether or not REQ_F_PARTIAL_IO is
also set.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---

diff --git a/fs/io_uring.c b/fs/io_uring.c
index e18d8891b98b6..97ed7f419daee 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6266,7 +6266,9 @@ static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
 
 	if (!def->pollin && !def->pollout)
 		return IO_APOLL_ABORTED;
-	if (!file_can_poll(req->file) || (req->flags & REQ_F_POLLED))
+	if (!file_can_poll(req->file))
+		return IO_APOLL_ABORTED;
+	if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED)
 		return IO_APOLL_ABORTED;
 
 	if (def->pollin) {
@@ -6281,8 +6283,10 @@ static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
 	}
 	if (def->poll_exclusive)
 		mask |= EPOLLEXCLUSIVE;
-	if (!(issue_flags & IO_URING_F_UNLOCKED) &&
-	    !list_empty(&ctx->apoll_cache)) {
+	if (req->flags & REQ_F_POLLED) {
+		apoll = req->apoll;
+	} else if (!(issue_flags & IO_URING_F_UNLOCKED) &&
+		   !list_empty(&ctx->apoll_cache)) {
 		apoll = list_first_entry(&ctx->apoll_cache, struct async_poll,
 						poll.wait.entry);
 		list_del_init(&apoll->poll.wait.entry);