This is a note to let you know that I've just added the patch titled
io_uring/net: don't skip notifs for failed requests
to the 6.0-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
io_uring-net-don-t-skip-notifs-for-failed-requests.patch
and it can be found in the queue-6.0 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From foo@baz Mon Oct 17 11:35:32 AM CEST 2022
From: Pavel Begunkov <asml.silence@xxxxxxxxx>
Date: Sun, 16 Oct 2022 21:33:29 +0100
Subject: io_uring/net: don't skip notifs for failed requests
To: stable@xxxxxxxxxxxxxxx
Cc: Jens Axboe <axboe@xxxxxxxxx>, asml.silence@xxxxxxxxx
Message-ID: <6e84a6e0dbfbbb43379a82abd262ce0bd4311ca2.1665951939.git.asml.silence@xxxxxxxxx>
From: Pavel Begunkov <asml.silence@xxxxxxxxx>
[ upstream commit 6ae91ac9a6aa7d6005c3c6d0f4d263fbab9f377f ]
We currently only add a notification CQE when the send succeded, i.e.
cqe.res >= 0. However, it'd be more robust to do buffer notifications
for failed requests as well in case drivers decide do something fanky.
Always return a buffer notification after initial prep, don't hide it.
This behaviour is better aligned with documentation and the patch also
helps the userspace to respect it.
Cc: stable@xxxxxxxxxxxxxxx # 6.0
Suggested-by: Stefan Metzmacher <metze@xxxxxxxxx>
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
Link: https://lore.kernel.org/r/9c8bead87b2b980fcec441b8faef52188b4a6588.1664292100.git.asml.silence@xxxxxxxxx
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
io_uring/net.c | 22 ++++++----------------
1 file changed, 6 insertions(+), 16 deletions(-)
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -879,7 +879,6 @@ void io_send_zc_cleanup(struct io_kiocb
{
struct io_sr_msg *zc = io_kiocb_to_cmd(req, struct io_sr_msg);
- zc->notif->flags |= REQ_F_CQE_SKIP;
io_notif_flush(zc->notif);
zc->notif = NULL;
}
@@ -996,7 +995,7 @@ int io_send_zc(struct io_kiocb *req, uns
struct msghdr msg;
struct iovec iov;
struct socket *sock;
- unsigned msg_flags, cflags;
+ unsigned msg_flags;
int ret, min_ret = 0;
sock = sock_from_file(req->file);
@@ -1064,8 +1063,6 @@ int io_send_zc(struct io_kiocb *req, uns
req->flags |= REQ_F_PARTIAL_IO;
return io_setup_async_addr(req, addr, issue_flags);
}
- if (ret < 0 && !zc->done_io)
- zc->notif->flags |= REQ_F_CQE_SKIP;
if (ret == -ERESTARTSYS)
ret = -EINTR;
req_set_fail(req);
@@ -1078,8 +1075,7 @@ int io_send_zc(struct io_kiocb *req, uns
io_notif_flush(zc->notif);
req->flags &= ~REQ_F_NEED_CLEANUP;
- cflags = ret >= 0 ? IORING_CQE_F_MORE : 0;
- io_req_set_res(req, ret, cflags);
+ io_req_set_res(req, ret, IORING_CQE_F_MORE);
return IOU_OK;
}
@@ -1096,17 +1092,11 @@ void io_sendrecv_fail(struct io_kiocb *r
void io_send_zc_fail(struct io_kiocb *req)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
- int res = req->cqe.res;
- if (req->flags & REQ_F_PARTIAL_IO) {
- if (req->flags & REQ_F_NEED_CLEANUP) {
- io_notif_flush(sr->notif);
- sr->notif = NULL;
- req->flags &= ~REQ_F_NEED_CLEANUP;
- }
- res = sr->done_io;
- }
- io_req_set_res(req, res, req->cqe.flags);
+ if (req->flags & REQ_F_PARTIAL_IO)
+ req->cqe.res = sr->done_io;
+ if (req->flags & REQ_F_NEED_CLEANUP)
+ req->cqe.flags |= IORING_CQE_F_MORE;
}
int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
Patches currently in stable-queue which might be from asml.silence@xxxxxxxxx are
queue-6.0/io_uring-correct-pinned_vm-accounting.patch
queue-6.0/io_uring-net-fix-notif-cqe-reordering.patch
queue-6.0/io_uring-net-don-t-update-msg_name-if-not-provided.patch
queue-6.0/io_uring-rw-fix-unexpected-link-breakage.patch
queue-6.0/io_uring-net-don-t-skip-notifs-for-failed-requests.patch
queue-6.0/io_uring-net-rename-io_sendzc.patch
queue-6.0/io_uring-net-refactor-io_sr_msg-types.patch
queue-6.0/io_uring-fix-cqe-reordering.patch
queue-6.0/io_uring-net-don-t-lose-partial-send-recv-on-fail.patch
queue-6.0/io_uring-rw-don-t-lose-partial-io-result-on-fail.patch
queue-6.0/io_uring-net-fix-fast_iov-assignment-in-io_setup_async_msg.patch
queue-6.0/io_uring-net-don-t-lose-partial-send_zc-on-fail.patch
queue-6.0/io_uring-limit-registration-w-single_issuer.patch
queue-6.0/io_uring-net-use-io_sr_msg-for-sendzc.patch
queue-6.0/io_uring-add-custom-opcode-hooks-on-fail.patch
queue-6.0/io_uring-rw-don-t-lose-short-results-on-io_setup_async_rw.patch
queue-6.0/io_uring-af_unix-defer-registered-files-gc-to-io_uring-release.patch
