netdev - Re: [PATCH net-next v3 10/18] nvme/host: Use sendmsg(MSG_SPLICE

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: <87f547b0-7826-b232-cd01-c879b6829951@grimberg.me>
Date: Wed, 21 Jun 2023 13:15:15 +0300
From: Sagi Grimberg <sagi@...mberg.me>
To: David Howells <dhowells@...hat.com>, netdev@...r.kernel.org
Cc: Alexander Duyck <alexander.duyck@...il.com>,
 "David S. Miller" <davem@...emloft.net>, Eric Dumazet <edumazet@...gle.com>,
 Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>,
 Willem de Bruijn <willemdebruijn.kernel@...il.com>,
 David Ahern <dsahern@...nel.org>, Matthew Wilcox <willy@...radead.org>,
 Jens Axboe <axboe@...nel.dk>, linux-mm@...ck.org,
 linux-kernel@...r.kernel.org, Willem de Bruijn <willemb@...gle.com>,
 Keith Busch <kbusch@...nel.org>, Jens Axboe <axboe@...com>,
 Christoph Hellwig <hch@....de>, Chaitanya Kulkarni <kch@...dia.com>,
 linux-nvme@...ts.infradead.org
Subject: Re: [PATCH net-next v3 10/18] nvme/host: Use
 sendmsg(MSG_SPLICE_PAGES) rather then sendpage

One comment:

format for title in nvme-tcp is:

"nvme-tcp: ..." for host patches, and
"nvmet-tcp: ..." for target patches.

But this can be fixed up when applying the patch set.

Other than that, for both nvme patches:
Reviewed-by: Sagi Grimberg <sagi@...mberg.me>

What tree will this be going from btw?

On 6/20/23 17:53, David Howells wrote:
> When transmitting data, call down into TCP using a single sendmsg with
> MSG_SPLICE_PAGES to indicate that content should be spliced rather than
> performing several sendmsg and sendpage calls to transmit header, data
> pages and trailer.
> 
> Signed-off-by: David Howells <dhowells@...hat.com>
> Tested-by: Sagi Grimberg <sagi@...mberg.me>
> Acked-by: Willem de Bruijn <willemb@...gle.com>
> cc: Keith Busch <kbusch@...nel.org>
> cc: Jens Axboe <axboe@...com>
> cc: Christoph Hellwig <hch@....de>
> cc: Chaitanya Kulkarni <kch@...dia.com>
> cc: "David S. Miller" <davem@...emloft.net>
> cc: Eric Dumazet <edumazet@...gle.com>
> cc: Jakub Kicinski <kuba@...nel.org>
> cc: Paolo Abeni <pabeni@...hat.com>
> cc: Jens Axboe <axboe@...nel.dk>
> cc: Matthew Wilcox <willy@...radead.org>
> cc: linux-nvme@...ts.infradead.org
> cc: netdev@...r.kernel.org
> ---
> 
> Notes:
>      ver #2)
>       - Wrap lines at 80.
>      
>      ver #3)
>       - Split nvme/host from nvme/target changes.
> 
>   drivers/nvme/host/tcp.c | 46 +++++++++++++++++++++--------------------
>   1 file changed, 24 insertions(+), 22 deletions(-)
> 
> diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
> index bf0230442d57..6f31cdbb696a 100644
> --- a/drivers/nvme/host/tcp.c
> +++ b/drivers/nvme/host/tcp.c
> @@ -997,25 +997,25 @@ 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);
> -		}
> +		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 +1054,24 @@ 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 +1095,8 @@ 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 +1105,11 @@ 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;
>   
>