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:   David Howells <dhowells@redhat.com>
To:     netdev@vger.kernel.org
Cc:     David Howells <dhowells@redhat.com>,
        Alexander Duyck <alexander.duyck@gmail.com>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        Willem de Bruijn <willemdebruijn.kernel@gmail.com>,
        David Ahern <dsahern@kernel.org>,
        Matthew Wilcox <willy@infradead.org>,
        Jens Axboe <axboe@kernel.dk>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org, Sagi Grimberg <sagi@grimberg.me>,
        Willem de Bruijn <willemb@google.com>,
        Keith Busch <kbusch@kernel.org>, Jens Axboe <axboe@fb.com>,
        Christoph Hellwig <hch@lst.de>,
        Chaitanya Kulkarni <kch@nvidia.com>,
        linux-nvme@lists.infradead.org
Subject: [PATCH net-next v5 08/16] nvmet-tcp: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage
Date:   Fri, 23 Jun 2023 23:55:05 +0100
Message-ID: <20230623225513.2732256-9-dhowells@redhat.com>
In-Reply-To: <20230623225513.2732256-1-dhowells@redhat.com>
References: <20230623225513.2732256-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

When transmitting data, call down into TCP using a single sendmsg with
MSG_SPLICE_PAGES to indicate that content should be spliced rather than
copied instead of calling sendpage.

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Sagi Grimberg <sagi@grimberg.me>
Acked-by: Willem de Bruijn <willemb@google.com>
cc: Keith Busch <kbusch@kernel.org>
cc: Jens Axboe <axboe@fb.com>
cc: Christoph Hellwig <hch@lst.de>
cc: Chaitanya Kulkarni <kch@nvidia.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-nvme@lists.infradead.org
cc: netdev@vger.kernel.org
---

Notes:
    ver #3)
     - Split nvme/host from nvme/target changes.
    
    ver #2)
     - Wrap lines at 80.

 drivers/nvme/target/tcp.c | 46 ++++++++++++++++++++++++---------------
 1 file changed, 29 insertions(+), 17 deletions(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index ed98df72c76b..868aa4de2e4c 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -576,13 +576,17 @@ static void nvmet_tcp_execute_request(struct nvmet_tcp_cmd *cmd)
 
 static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd)
 {
+	struct msghdr msg = {
+		.msg_flags = MSG_DONTWAIT | MSG_MORE | MSG_SPLICE_PAGES,
+	};
+	struct bio_vec bvec;
 	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
 	int left = sizeof(*cmd->data_pdu) - cmd->offset + hdgst;
 	int ret;
 
-	ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->data_pdu),
-			offset_in_page(cmd->data_pdu) + cmd->offset,
-			left, MSG_DONTWAIT | MSG_MORE | MSG_SENDPAGE_NOTLAST);
+	bvec_set_virt(&bvec, (void *)cmd->data_pdu + cmd->offset, left);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
+	ret = sock_sendmsg(cmd->queue->sock, &msg);
 	if (ret <= 0)
 		return ret;
 
@@ -603,17 +607,21 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 	int ret;
 
 	while (cmd->cur_sg) {
+		struct msghdr msg = {
+			.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES,
+		};
 		struct page *page = sg_page(cmd->cur_sg);
+		struct bio_vec bvec;
 		u32 left = cmd->cur_sg->length - cmd->offset;
-		int flags = MSG_DONTWAIT;
 
 		if ((!last_in_batch && cmd->queue->send_list_len) ||
 		    cmd->wbytes_done + left < cmd->req.transfer_len ||
 		    queue->data_digest || !queue->nvme_sq.sqhd_disabled)
-			flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+			msg.msg_flags |= MSG_MORE;
 
-		ret = kernel_sendpage(cmd->queue->sock, page, cmd->offset,
-					left, flags);
+		bvec_set_page(&bvec, page, left, cmd->offset);
+		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
+		ret = sock_sendmsg(cmd->queue->sock, &msg);
 		if (ret <= 0)
 			return ret;
 
@@ -649,18 +657,20 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
 		bool last_in_batch)
 {
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, };
+	struct bio_vec bvec;
 	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
 	int left = sizeof(*cmd->rsp_pdu) - cmd->offset + hdgst;
-	int flags = MSG_DONTWAIT;
 	int ret;
 
 	if (!last_in_batch && cmd->queue->send_list_len)
-		flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+		msg.msg_flags |= MSG_MORE;
 	else
-		flags |= MSG_EOR;
+		msg.msg_flags |= MSG_EOR;
 
-	ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->rsp_pdu),
-		offset_in_page(cmd->rsp_pdu) + cmd->offset, left, flags);
+	bvec_set_virt(&bvec, (void *)cmd->rsp_pdu + cmd->offset, left);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
+	ret = sock_sendmsg(cmd->queue->sock, &msg);
 	if (ret <= 0)
 		return ret;
 	cmd->offset += ret;
@@ -677,18 +687,20 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
 
 static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 {
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, };
+	struct bio_vec bvec;
 	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
 	int left = sizeof(*cmd->r2t_pdu) - cmd->offset + hdgst;
-	int flags = MSG_DONTWAIT;
 	int ret;
 
 	if (!last_in_batch && cmd->queue->send_list_len)
-		flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+		msg.msg_flags |= MSG_MORE;
 	else
-		flags |= MSG_EOR;
+		msg.msg_flags |= MSG_EOR;
 
-	ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->r2t_pdu),
-		offset_in_page(cmd->r2t_pdu) + cmd->offset, left, flags);
+	bvec_set_virt(&bvec, (void *)cmd->r2t_pdu + cmd->offset, left);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
+	ret = sock_sendmsg(cmd->queue->sock, &msg);
 	if (ret <= 0)
 		return ret;
 	cmd->offset += ret;