diff options
| author | Jens Axboe | 2026-01-27 21:01:41 -0700 |
|---|---|---|
| committer | Sasha Levin | 2026-03-04 07:21:28 -0500 |
| commit | 43ef31a60e0a7016f523f9ce7cdbd3a04ee18d7d (patch) | |
| tree | 5be7de93b89de5c902b4faa1cd4cd2461b48ed79 /io_uring | |
| parent | 8f2d7100e1c3301fba61166bfbbbc83af393aa8f (diff) | |
io_uring/net: don't continue send bundle if poll was required for retry
[ Upstream commit 806ae939c41e5da1d94a1e2b31f5702e96b6c3e3 ]
If a send bundle has picked a bunch of buffers, then it needs to send
all of those to be complete. This may require poll arming, if the send
buffer ends up being full. Once a send bundle has been poll armed, no
further bundles should be attempted.
This allows a current bundle to complete even though it needs to go
through polling to do so, but it will not allow another bundle to be
started once that has happened. Ideally we would abort a bundle if it
was only partially sent, but as some parts of it already went out on the
wire, this obviously isn't feasible. Not continuing more bundle attempts
post encountering a full socket buffer is the second best thing.
Cc: stable@vger.kernel.org
Fixes: a05d1f625c7a ("io_uring/net: support bundles for send")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Diffstat (limited to 'io_uring')
| -rw-r--r-- | io_uring/net.c | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/io_uring/net.c b/io_uring/net.c index 519ea055b761..d9a4b83804a2 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -515,7 +515,11 @@ static inline bool io_send_finish(struct io_kiocb *req, cflags = io_put_kbufs(req, sel->val, sel->buf_list, io_bundle_nbufs(kmsg, sel->val)); - if (bundle_finished || req->flags & REQ_F_BL_EMPTY) + /* + * Don't start new bundles if the buffer list is empty, or if the + * current operation needed to go through polling to complete. + */ + if (bundle_finished || req->flags & (REQ_F_BL_EMPTY | REQ_F_POLLED)) goto finish; /* |