From: David Howells <dhowells@redhat.com>
To: Matthew Wilcox <willy@infradead.org>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>
Cc: David Howells <dhowells@redhat.com>,
Al Viro <viro@zeniv.linux.org.uk>,
Christoph Hellwig <hch@infradead.org>,
Jens Axboe <axboe@kernel.dk>, Jeff Layton <jlayton@kernel.org>,
Christian Brauner <brauner@kernel.org>,
Chuck Lever III <chuck.lever@oracle.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
netdev@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Keith Busch <kbusch@kernel.org>, Jens Axboe <axboe@fb.com>,
Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
Chaitanya Kulkarni <kch@nvidia.com>,
linux-nvme@lists.infradead.org
Subject: [RFC PATCH v2 42/48] nvme: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage
Date: Wed, 29 Mar 2023 15:13:48 +0100 [thread overview]
Message-ID: <20230329141354.516864-43-dhowells@redhat.com> (raw)
In-Reply-To: <20230329141354.516864-1-dhowells@redhat.com>
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@redhat.com>
cc: Keith Busch <kbusch@kernel.org>
cc: Jens Axboe <axboe@fb.com>
cc: Christoph Hellwig <hch@lst.de>
cc: Sagi Grimberg <sagi@grimberg.me>
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
---
drivers/nvme/host/tcp.c | 44 ++++++++++++++++++------------------
drivers/nvme/target/tcp.c | 47 +++++++++++++++++++++++++--------------
2 files changed, 52 insertions(+), 39 deletions(-)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index fa32969b532f..cc617692702d 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -979,25 +979,23 @@ 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 | MSG_SENDPAGE_NOTLAST;
- 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;
@@ -1036,22 +1034,24 @@ 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 = req->pdu;
+ 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 | MSG_SENDPAGE_NOTLAST;
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;
@@ -1075,6 +1075,8 @@ 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 = req->pdu;
+ 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;
@@ -1083,13 +1085,11 @@ 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 | MSG_SENDPAGE_NOTLAST;
+
+ 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;
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index d6cc557cc539..00b491abf50f 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -548,13 +548,18 @@ static void nvmet_tcp_execute_request(struct nvmet_tcp_cmd *cmd)
static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd)
{
+ struct bio_vec bvec;
+ struct msghdr msg = {
+ .msg_flags = (MSG_DONTWAIT | MSG_MORE | MSG_SENDPAGE_NOTLAST |
+ MSG_SPLICE_PAGES),
+ };
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;
@@ -575,17 +580,21 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
int ret;
while (cmd->cur_sg) {
+ struct bio_vec bvec;
+ struct msghdr msg = {
+ .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES,
+ };
struct page *page = sg_page(cmd->cur_sg);
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 | MSG_SENDPAGE_NOTLAST;
- 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;
@@ -621,18 +630,20 @@ 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 bio_vec bvec;
+ struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, };
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 | MSG_SENDPAGE_NOTLAST;
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;
@@ -649,18 +660,20 @@ 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 bio_vec bvec;
+ struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, };
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 | MSG_SENDPAGE_NOTLAST;
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;
next prev parent reply other threads:[~2023-03-29 14:22 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-29 14:13 [RFC PATCH v2 00/48] splice, net: Replace sendpage with sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:13 ` [RFC PATCH v2 01/48] netfs: Fix netfs_extract_iter_to_sg() for ITER_UBUF/IOVEC David Howells
2023-03-29 14:13 ` [RFC PATCH v2 02/48] iov_iter: Remove last_offset member David Howells
2023-03-29 14:13 ` [RFC PATCH v2 03/48] iov_iter: Add an iterator-of-iterators David Howells
2023-03-29 14:13 ` [RFC PATCH v2 04/48] net: Declare MSG_SPLICE_PAGES internal sendmsg() flag David Howells
2023-03-30 14:28 ` Willem de Bruijn
2023-03-30 15:07 ` David Howells
2023-03-30 17:51 ` Willem de Bruijn
2023-03-29 14:13 ` [RFC PATCH v2 05/48] mm: Move the page fragment allocator from page_alloc.c into its own file David Howells
2023-03-29 14:13 ` [RFC PATCH v2 06/48] mm: Make the page_frag_cache allocator use multipage folios David Howells
2023-03-29 14:13 ` [RFC PATCH v2 07/48] mm: Make the page_frag_cache allocator use per-cpu David Howells
2023-03-29 14:13 ` [RFC PATCH v2 08/48] tcp: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 09/48] tcp: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 10/48] tcp: Convert do_tcp_sendpages() to use MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 11/48] tcp_bpf: Inline do_tcp_sendpages as it's now a wrapper around tcp_sendmsg David Howells
2023-03-29 14:13 ` [RFC PATCH v2 12/48] espintcp: Inline do_tcp_sendpages() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 13/48] tls: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 14/48] siw: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 15/48] tcp: Fold do_tcp_sendpages() into tcp_sendpage_locked() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 16/48] ip, udp: Support MSG_SPLICE_PAGES David Howells
2023-03-30 14:20 ` Willem de Bruijn
2023-03-30 14:39 ` David Howells
2023-03-30 17:46 ` Willem de Bruijn
2023-03-30 15:11 ` David Howells
2023-03-30 17:55 ` Willem de Bruijn
2023-03-30 19:49 ` David Howells
2023-03-29 14:13 ` [RFC PATCH v2 17/48] ip, udp: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 18/48] udp: Convert udp_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 19/48] af_unix: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 20/48] af_unix: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 21/48] crypto: af_alg: Pin pages rather than ref'ing if appropriate David Howells
2023-03-29 14:13 ` [RFC PATCH v2 22/48] crypto: af_alg: Use netfs_extract_iter_to_sg() to create scatterlists David Howells
2023-03-29 14:13 ` [RFC PATCH v2 23/48] crypto: af_alg: Indent the loop in af_alg_sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 24/48] crypto: af_alg: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 25/48] crypto: af_alg: Convert af_alg_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 26/48] crypto: af_alg/hash: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 27/48] splice, net: Use sendmsg(MSG_SPLICE_PAGES) rather than ->sendpage() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 28/48] splice: Reimplement splice_to_socket() to pass multiple bufs to sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 29/48] Remove file->f_op->sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 30/48] siw: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage to transmit David Howells
2023-03-29 15:18 ` Bernard Metzler
2023-03-29 15:32 ` David Howells
2023-03-29 14:13 ` [RFC PATCH v2 31/48] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 32/48] iscsi: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 33/48] iscsi: Assume "sendpage" is okay in iscsi_tcp_segment_map() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 34/48] tcp_bpf: Make tcp_bpf_sendpage() go through tcp_bpf_sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:13 ` [RFC PATCH v2 35/48] net: Use sendmsg(MSG_SPLICE_PAGES) not sendpage in skb_send_sock() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 36/48] algif: Remove hash_sendpage*() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 37/48] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage() David Howells
2023-03-30 1:45 ` Xiubo Li
2023-03-30 6:48 ` David Howells
2023-03-31 13:05 ` Xiubo Li
2023-04-03 3:27 ` Xiubo Li
2023-04-03 8:32 ` David Howells
2023-04-10 0:38 ` Xiubo Li
2023-03-29 14:13 ` [RFC PATCH v2 38/48] rds: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 39/48] dlm: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 40/48] sunrpc: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage David Howells
2023-03-29 15:28 ` Chuck Lever III
2023-03-29 19:58 ` David Howells
2023-03-30 9:29 ` David Howells
2023-03-30 9:41 ` David Howells
2023-03-30 13:16 ` Chuck Lever III
2023-03-30 13:01 ` David Howells
2023-03-30 13:16 ` David Howells
2023-03-30 13:27 ` Chuck Lever III
2023-03-30 14:26 ` David Howells
2023-03-30 16:36 ` Chuck Lever III
2023-04-14 14:41 ` Daire Byrne
2023-03-29 14:13 ` [RFC PATCH v2 41/48] sunrpc: Rely on TCP sendmsg + MSG_SPLICE_PAGES to copy unspliceable data David Howells
2023-03-29 14:13 ` David Howells [this message]
2023-03-29 14:13 ` [RFC PATCH v2 43/48] kcm: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 44/48] smc: Drop smc_sendpage() in favour of smc_sendmsg() + MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 45/48] ocfs2: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 46/48] drbd: Use sendmsg(MSG_SPLICE_PAGES) rather than sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 47/48] drdb: Send an entire bio in a single sendmsg David Howells
2023-03-29 14:13 ` [RFC PATCH v2 48/48] sock: Remove ->sendpage*() in favour of sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:23 ` Hannes Reinecke
2023-03-29 14:39 ` David Howells
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230329141354.516864-43-dhowells@redhat.com \
--to=dhowells@redhat.com \
--cc=axboe@fb.com \
--cc=axboe@kernel.dk \
--cc=brauner@kernel.org \
--cc=chuck.lever@oracle.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hch@infradead.org \
--cc=hch@lst.de \
--cc=jlayton@kernel.org \
--cc=kbusch@kernel.org \
--cc=kch@nvidia.com \
--cc=kuba@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvme@lists.infradead.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=sagi@grimberg.me \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).