Commit c336a799 authored by David Howells's avatar David Howells Committed by Jakub Kicinski
Browse files

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



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: default avatarDavid Howells <dhowells@redhat.com>
Tested-by: default avatarSagi Grimberg <sagi@grimberg.me>
Acked-by: default avatarWillem 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: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-nvme@lists.infradead.org
Link: https://lore.kernel.org/r/20230623225513.2732256-9-dhowells@redhat.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 77698878

drivers/nvme/target/tcp.c

+29 −17
Original line number Diff line number Diff line
@@ -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;