linux-kernel - [PATCH v2 7/8] io_uring: refactor __io_cq_unlock_post

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <baa9b8d822f024e4ee01c40209dbbe38d9c8c11d.1680782017.git.asml.silence@gmail.com>
Date:   Thu,  6 Apr 2023 14:20:13 +0100
From:   Pavel Begunkov <asml.silence@...il.com>
To:     io-uring@...r.kernel.org
Cc:     Jens Axboe <axboe@...nel.dk>, asml.silence@...il.com,
        linux-kernel@...r.kernel.org
Subject: [PATCH v2 7/8] io_uring: refactor __io_cq_unlock_post_flush()

Separate ->task_complete path in __io_cq_unlock_post_flush().

Signed-off-by: Pavel Begunkov <asml.silence@...il.com>
---
 io_uring/io_uring.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 8a327a81beaf..0ea50c46f27f 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -627,21 +627,23 @@ static inline void __io_cq_unlock_post(struct io_ring_ctx *ctx)
 	io_cqring_wake(ctx);
 }
 
-static inline void __io_cq_unlock_post_flush(struct io_ring_ctx *ctx)
+static void __io_cq_unlock_post_flush(struct io_ring_ctx *ctx)
 	__releases(ctx->completion_lock)
 {
 	io_commit_cqring(ctx);
-	__io_cq_unlock(ctx);
-	io_commit_cqring_flush(ctx);
 
-	/*
-	 * As ->task_complete implies that the ring is single tasked, cq_wait
-	 * may only be waited on by the current in io_cqring_wait(), but since
-	 * it will re-check the wakeup conditions once we return we can safely
-	 * skip waking it up.
-	 */
-	if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN))
+	if (ctx->task_complete) {
+		/*
+		 * ->task_complete implies that only current might be waiting
+		 * for CQEs, and obviously, we currently don't. No one is
+		 * waiting, wakeups are futile, skip them.
+		 */
+		io_commit_cqring_flush(ctx);
+	} else {
+		__io_cq_unlock(ctx);
+		io_commit_cqring_flush(ctx);
 		io_cqring_wake(ctx);
+	}
 }
 
 void io_cq_unlock_post(struct io_ring_ctx *ctx)
-- 
2.40.0