linux-rdma.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
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,
	Santosh Shilimkar <santosh.shilimkar@oracle.com>,
	linux-rdma@vger.kernel.org, rds-devel@oss.oracle.com
Subject: [PATCH v3 46/55] rds: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage
Date: Fri, 31 Mar 2023 17:09:05 +0100	[thread overview]
Message-ID: <20230331160914.1608208-47-dhowells@redhat.com> (raw)
In-Reply-To: <20230331160914.1608208-1-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 and data
pages.

To make this work, the data is assembled in a bio_vec array and attached to
a BVEC-type iterator.  The header are copied into memory acquired from
zcopy_alloc() which just breaks a page up into small pieces that can be
freed with put_page().

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Santosh Shilimkar <santosh.shilimkar@oracle.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-rdma@vger.kernel.org
cc: rds-devel@oss.oracle.com
cc: netdev@vger.kernel.org
---
 net/rds/tcp_send.c | 86 +++++++++++++++++++++-------------------------
 1 file changed, 40 insertions(+), 46 deletions(-)

diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 8c4d1d6e9249..660d9f203d99 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -52,29 +52,24 @@ void rds_tcp_xmit_path_complete(struct rds_conn_path *cp)
 	tcp_sock_set_cork(tc->t_sock->sk, false);
 }
 
-/* the core send_sem serializes this with other xmit and shutdown */
-static int rds_tcp_sendmsg(struct socket *sock, void *data, unsigned int len)
-{
-	struct kvec vec = {
-		.iov_base = data,
-		.iov_len = len,
-	};
-	struct msghdr msg = {
-		.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL,
-	};
-
-	return kernel_sendmsg(sock, &msg, &vec, 1, vec.iov_len);
-}
-
 /* the core send_sem serializes this with other xmit and shutdown */
 int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
 		 unsigned int hdr_off, unsigned int sg, unsigned int off)
 {
 	struct rds_conn_path *cp = rm->m_inc.i_conn_path;
 	struct rds_tcp_connection *tc = cp->cp_transport_data;
+	struct msghdr msg = {
+		.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT | MSG_NOSIGNAL,
+	};
+	struct bio_vec *bvec;
+	unsigned int i, size = 0, ix = 0;
+	bool free_hdr = false;
 	int done = 0;
-	int ret = 0;
-	int more;
+	int ret = -ENOMEM;
+
+	bvec = kmalloc_array(1 + sg, sizeof(struct bio_vec), GFP_KERNEL);
+	if (!bvec)
+		goto out;
 
 	if (hdr_off == 0) {
 		/*
@@ -99,43 +94,37 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
 
 	if (hdr_off < sizeof(struct rds_header)) {
 		/* see rds_tcp_write_space() */
+		void *p;
+
 		set_bit(SOCK_NOSPACE, &tc->t_sock->sk->sk_socket->flags);
 
-		ret = rds_tcp_sendmsg(tc->t_sock,
-				      (void *)&rm->m_inc.i_hdr + hdr_off,
-				      sizeof(rm->m_inc.i_hdr) - hdr_off);
-		if (ret < 0)
-			goto out;
-		done += ret;
-		if (hdr_off + done != sizeof(struct rds_header))
+		ret = -ENOMEM;
+		p = page_frag_memdup(NULL,
+				     (void *)&rm->m_inc.i_hdr + hdr_off,
+				     sizeof(rm->m_inc.i_hdr) - hdr_off,
+				     GFP_KERNEL, ULONG_MAX);
+		if (!p)
 			goto out;
+		bvec_set_virt(&bvec[ix], p, sizeof(rm->m_inc.i_hdr) - hdr_off);
+		free_hdr = true;
+		size += bvec[ix].bv_len;
+		ix++;
 	}
 
-	more = rm->data.op_nents > 1 ? (MSG_MORE | MSG_SENDPAGE_NOTLAST) : 0;
-	while (sg < rm->data.op_nents) {
-		int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
-
-		ret = tc->t_sock->ops->sendpage(tc->t_sock,
-						sg_page(&rm->data.op_sg[sg]),
-						rm->data.op_sg[sg].offset + off,
-						rm->data.op_sg[sg].length - off,
-						flags);
-		rdsdebug("tcp sendpage %p:%u:%u ret %d\n", (void *)sg_page(&rm->data.op_sg[sg]),
-			 rm->data.op_sg[sg].offset + off, rm->data.op_sg[sg].length - off,
-			 ret);
-		if (ret <= 0)
-			break;
-
-		off += ret;
-		done += ret;
-		if (off == rm->data.op_sg[sg].length) {
-			off = 0;
-			sg++;
-		}
-		if (sg == rm->data.op_nents - 1)
-			more = 0;
+	for (i = sg; i < rm->data.op_nents; i++) {
+		bvec_set_page(&bvec[ix],
+			      sg_page(&rm->data.op_sg[i]),
+			      rm->data.op_sg[i].length - off,
+			      rm->data.op_sg[i].offset + off);
+		off = 0;
+		size += bvec[ix].bv_len;
+		ix++;
 	}
 
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, bvec, ix, size);
+	ret = sock_sendmsg(tc->t_sock, &msg);
+	rdsdebug("tcp sendmsg-splice %u,%u ret %d\n", ix, size, ret);
+
 out:
 	if (ret <= 0) {
 		/* write_space will hit after EAGAIN, all else fatal */
@@ -158,6 +147,11 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
 	}
 	if (done == 0)
 		done = ret;
+	if (bvec) {
+		if (free_hdr)
+			put_page(bvec[0].bv_page);
+		kfree(bvec);
+	}
 	return done;
 }
 


  parent reply	other threads:[~2023-03-31 16:19 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20230331160914.1608208-1-dhowells@redhat.com>
2023-03-31 16:08 ` [PATCH v3 04/55] mm: Move the page fragment allocator from page_alloc.c into its own file David Howells
2023-03-31 16:08 ` [PATCH v3 13/55] siw: Inline do_tcp_sendpages() David Howells
2023-03-31 16:08 ` [PATCH v3 38/55] siw: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage to transmit David Howells
2023-04-04 10:52   ` Bernard Metzler
2023-04-05  8:18   ` David Howells
2023-03-31 16:09 ` David Howells [this message]
2023-03-31 16:09 ` [PATCH v3 55/55] sock: Remove ->sendpage*() in favour of sendmsg(MSG_SPLICE_PAGES) 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=20230331160914.1608208-47-dhowells@redhat.com \
    --to=dhowells@redhat.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=jlayton@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=rds-devel@oss.oracle.com \
    --cc=santosh.shilimkar@oracle.com \
    --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).