nvme-tcp: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage

When transmitting data, call down into TCP using a sendmsg with
MSG_SPLICE_PAGES instead of sendpage.

Signed-off-by: David Howells <[email protected]>
Tested-by: Sagi Grimberg <[email protected]>
Acked-by: Willem de Bruijn <[email protected]>
cc: Keith Busch <[email protected]>
cc: Jens Axboe <[email protected]>
cc: Christoph Hellwig <[email protected]>
cc: Chaitanya Kulkarni <[email protected]>
cc: Jens Axboe <[email protected]>
cc: Matthew Wilcox <[email protected]>
cc: [email protected]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: dhowells

drivers/nvme/host/tcp.c

@@ -997,25 +997,28 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 	u32 h2cdata_left = req->h2cdata_left;
 
 	while (true) {
+		struct bio_vec bvec;
+		struct msghdr msg = {
+			.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES,
+		};
 		struct page *page = nvme_tcp_req_cur_page(req);
 		size_t offset = nvme_tcp_req_cur_offset(req);
 		size_t len = nvme_tcp_req_cur_length(req);
 		bool last = nvme_tcp_pdu_last_send(req, len);
 		int req_data_sent = req->data_sent;
-		int ret, flags = MSG_DONTWAIT;
+		int ret;
 
 		if (last && !queue->data_digest && !nvme_tcp_queue_more(queue))
-			flags |= MSG_EOR;
+			msg.msg_flags |= MSG_EOR;
 		else
-			flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+			msg.msg_flags |= MSG_MORE;
 
-		if (sendpage_ok(page)) {
-			ret = kernel_sendpage(queue->sock, page, offset, len,
-					flags);
-		} else {
-			ret = sock_no_sendpage(queue->sock, page, offset, len,
-					flags);
-		}
+		if (!sendpage_ok(page))
+			msg.msg_flags &= ~MSG_SPLICE_PAGES,
+
+		bvec_set_page(&bvec, page, len, offset);
+		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len);
+		ret = sock_sendmsg(queue->sock, &msg);
 		if (ret <= 0)
 			return ret;
 
@@ -1054,22 +1057,24 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
 {
 	struct nvme_tcp_queue *queue = req->queue;
 	struct nvme_tcp_cmd_pdu *pdu = nvme_tcp_req_cmd_pdu(req);
+	struct bio_vec bvec;
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, };
 	bool inline_data = nvme_tcp_has_inline_data(req);
 	u8 hdgst = nvme_tcp_hdgst_len(queue);
 	int len = sizeof(*pdu) + hdgst - req->offset;
-	int flags = MSG_DONTWAIT;
 	int ret;
 
 	if (inline_data || nvme_tcp_queue_more(queue))
-		flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+		msg.msg_flags |= MSG_MORE;
 	else
-		flags |= MSG_EOR;
+		msg.msg_flags |= MSG_EOR;
 
 	if (queue->hdr_digest && !req->offset)
 		nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
 
-	ret = kernel_sendpage(queue->sock, virt_to_page(pdu),
-			offset_in_page(pdu) + req->offset, len,  flags);
+	bvec_set_virt(&bvec, (void *)pdu + req->offset, len);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len);
+	ret = sock_sendmsg(queue->sock, &msg);
 	if (unlikely(ret <= 0))
 		return ret;
 
@@ -1093,6 +1098,8 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
 {
 	struct nvme_tcp_queue *queue = req->queue;
 	struct nvme_tcp_data_pdu *pdu = nvme_tcp_req_data_pdu(req);
+	struct bio_vec bvec;
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_MORE, };
 	u8 hdgst = nvme_tcp_hdgst_len(queue);
 	int len = sizeof(*pdu) - req->offset + hdgst;
 	int ret;
@@ -1101,13 +1108,11 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
 		nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
 
 	if (!req->h2cdata_left)
-		ret = kernel_sendpage(queue->sock, virt_to_page(pdu),
-				offset_in_page(pdu) + req->offset, len,
-				MSG_DONTWAIT | MSG_MORE | MSG_SENDPAGE_NOTLAST);
-	else
-		ret = sock_no_sendpage(queue->sock, virt_to_page(pdu),
-				offset_in_page(pdu) + req->offset, len,
-				MSG_DONTWAIT | MSG_MORE);
+		msg.msg_flags |= MSG_SPLICE_PAGES;
+
+	bvec_set_virt(&bvec, (void *)pdu + req->offset, len);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len);
+	ret = sock_sendmsg(queue->sock, &msg);
 	if (unlikely(ret <= 0))
 		return ret;