This is a note to let you know that I've just added the patch titled
io_uring/net: don't lose partial send_zc on fail
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-lose-partial-send_zc-on-fail.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 21:33:27 +0100
Subject: io_uring/net: don't lose partial send_zc on fail
To: stable@xxxxxxxxxxxxxxx
Cc: Jens Axboe <axboe@xxxxxxxxx>, asml.silence@xxxxxxxxx
Message-ID: <3493fc0ee75f3cf8a111e2e8e1a35f833f29aaf2.1665951939.git.asml.silence@xxxxxxxxx>
From: Pavel Begunkov <asml.silence@xxxxxxxxx>
[ upstream commit 5693bcce892d7b8b15a7a92b011d3d40a023b53c ]
Partial zc send may end up in io_req_complete_failed(), which not only
would return invalid result but also mask out the notification leading
to lifetime issues.
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
Link: https://lore.kernel.org/r/5673285b5e83e6ceca323727b4ddaa584b5cc91e.1663668091.git.asml.silence@xxxxxxxxx
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
io_uring/net.c | 16 ++++++++++++++++
io_uring/net.h | 1 +
io_uring/opdef.c | 1 +
3 files changed, 18 insertions(+)
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1093,6 +1093,22 @@ void io_sendrecv_fail(struct io_kiocb *r
io_req_set_res(req, res, req->cqe.flags);
}
+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);
+}
+
int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_accept *accept = io_kiocb_to_cmd(req, struct io_accept);
--- a/io_uring/net.h
+++ b/io_uring/net.h
@@ -58,6 +58,7 @@ int io_connect(struct io_kiocb *req, uns
int io_sendzc(struct io_kiocb *req, unsigned int issue_flags);
int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
void io_sendzc_cleanup(struct io_kiocb *req);
+void io_send_zc_fail(struct io_kiocb *req);
void io_netmsg_cache_free(struct io_cache_entry *entry);
#else
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -494,6 +494,7 @@ const struct io_op_def io_op_defs[] = {
.issue = io_sendzc,
.prep_async = io_sendzc_prep_async,
.cleanup = io_sendzc_cleanup,
+ .fail = io_send_zc_fail,
#else
.prep = io_eopnotsupp_prep,
#endif
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
