Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Pavel Begunkov <asml.silence@gmail.com>
To:     io-uring@vger.kernel.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org
Cc:     "David S . Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>,
        Jonathan Lemon <jonathan.lemon@gmail.com>,
        Willem de Bruijn <willemb@google.com>,
        Jens Axboe <axboe@kernel.dk>, David Ahern <dsahern@kernel.org>,
        kernel-team@fb.com, Pavel Begunkov <asml.silence@gmail.com>
Subject: [PATCH net-next v4 16/27] io_uring: complete notifiers in tw
Date:   Thu,  7 Jul 2022 12:49:47 +0100
Message-Id: <3f3cb9e30bd344d1fb21e9505785b653ca38f069.1657194434.git.asml.silence@gmail.com>
In-Reply-To: <cover.1657194434.git.asml.silence@gmail.com>
References: <cover.1657194434.git.asml.silence@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

We need a task context to post CQEs but using wq is too expensive.
Try to complete notifiers using task_work and fall back to wq if fails.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 io_uring/notif.c | 22 +++++++++++++++++++---
 io_uring/notif.h |  3 +++
 2 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/io_uring/notif.c b/io_uring/notif.c
index b257db2120b4..aec74f88fc33 100644
--- a/io_uring/notif.c
+++ b/io_uring/notif.c
@@ -13,6 +13,11 @@ static void __io_notif_complete_tw(struct callback_head *cb)
 	struct io_notif *notif = container_of(cb, struct io_notif, task_work);
 	struct io_ring_ctx *ctx = notif->ctx;
 
+	if (likely(notif->task)) {
+		io_put_task(notif->task, 1);
+		notif->task = NULL;
+	}
+
 	io_cq_lock(ctx);
 	io_fill_cqe_aux(ctx, notif->tag, 0, notif->seq, true);
 
@@ -43,6 +48,14 @@ static void io_uring_tx_zerocopy_callback(struct sk_buff *skb,
 
 	if (!refcount_dec_and_test(&uarg->refcnt))
 		return;
+
+	if (likely(notif->task)) {
+		init_task_work(&notif->task_work, __io_notif_complete_tw);
+		if (likely(!task_work_add(notif->task, &notif->task_work,
+					  TWA_SIGNAL)))
+			return;
+	}
+
 	INIT_WORK(&notif->commit_work, io_notif_complete_wq);
 	queue_work(system_unbound_wq, &notif->commit_work);
 }
@@ -134,12 +147,15 @@ __cold int io_notif_unregister(struct io_ring_ctx *ctx)
 	for (i = 0; i < ctx->nr_notif_slots; i++) {
 		struct io_notif_slot *slot = &ctx->notif_slots[i];
 
-		if (slot->notif)
-			io_notif_slot_flush(slot);
+		if (!slot->notif)
+			continue;
+		if (WARN_ON_ONCE(slot->notif->task))
+			slot->notif->task = NULL;
+		io_notif_slot_flush(slot);
 	}
 
 	kvfree(ctx->notif_slots);
 	ctx->notif_slots = NULL;
 	ctx->nr_notif_slots = 0;
 	return 0;
-}
\ No newline at end of file
+}
diff --git a/io_uring/notif.h b/io_uring/notif.h
index b23c9c0515bb..23ca7620fff9 100644
--- a/io_uring/notif.h
+++ b/io_uring/notif.h
@@ -11,6 +11,9 @@ struct io_notif {
 	struct ubuf_info	uarg;
 	struct io_ring_ctx	*ctx;
 
+	/* complete via tw if ->task is non-NULL, fallback to wq otherwise */
+	struct task_struct	*task;
+
 	/* cqe->user_data, io_notif_slot::tag if not overridden */
 	u64			tag;
 	/* see struct io_notif_slot::seq */
-- 
2.36.1