linux-kernel.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>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	netdev@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Trond Myklebust <trond.myklebust@hammerspace.com>,
	Anna Schumaker <anna@kernel.org>,
	Chuck Lever <chuck.lever@oracle.com>,
	linux-nfs@vger.kernel.org
Subject: [RFC PATCH 27/28] sunrpc: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage
Date: Thu, 16 Mar 2023 15:26:17 +0000	[thread overview]
Message-ID: <20230316152618.711970-28-dhowells@redhat.com> (raw)
In-Reply-To: <20230316152618.711970-1-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.

To make this work, the data is assembled in a bio_vec array and attached to
a BVEC-type iterator.  The bio_vec array has two extra slots before the
first for headers and one after the last for a trailer.  The headers and
trailer 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: Trond Myklebust <trond.myklebust@hammerspace.com>
cc: Anna Schumaker <anna@kernel.org>
cc: Chuck Lever <chuck.lever@oracle.com>
cc: Jeff Layton <jlayton@kernel.org>
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-nfs@vger.kernel.org
cc: netdev@vger.kernel.org
---
 net/sunrpc/svcsock.c | 70 ++++++++++++--------------------------------
 net/sunrpc/xdr.c     | 24 ++++++++++++---
 2 files changed, 38 insertions(+), 56 deletions(-)

diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 03a4f5615086..1fa41ddbc40e 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -36,6 +36,7 @@
 #include <linux/skbuff.h>
 #include <linux/file.h>
 #include <linux/freezer.h>
+#include <linux/zcopy_alloc.h>
 #include <net/sock.h>
 #include <net/checksum.h>
 #include <net/ip.h>
@@ -1060,16 +1061,8 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 	return 0;	/* record not complete */
 }
 
-static int svc_tcp_send_kvec(struct socket *sock, const struct kvec *vec,
-			      int flags)
-{
-	return kernel_sendpage(sock, virt_to_page(vec->iov_base),
-			       offset_in_page(vec->iov_base),
-			       vec->iov_len, flags);
-}
-
 /*
- * kernel_sendpage() is used exclusively to reduce the number of
+ * MSG_SPLICE_PAGES is used exclusively to reduce the number of
  * copy operations in this path. Therefore the caller must ensure
  * that the pages backing @xdr are unchanging.
  *
@@ -1081,65 +1074,38 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr,
 {
 	const struct kvec *head = xdr->head;
 	const struct kvec *tail = xdr->tail;
-	struct kvec rm = {
-		.iov_base	= &marker,
-		.iov_len	= sizeof(marker),
-	};
 	struct msghdr msg = {
-		.msg_flags	= 0,
+		.msg_flags	= MSG_SPLICE_PAGES,
 	};
-	int ret;
+	int ret, n = xdr_buf_pagecount(xdr), size;
 
 	*sentp = 0;
 	ret = xdr_alloc_bvec(xdr, GFP_KERNEL);
 	if (ret < 0)
 		return ret;
 
-	ret = kernel_sendmsg(sock, &msg, &rm, 1, rm.iov_len);
+	ret = zcopy_memdup(sizeof(marker), &marker, &xdr->bvec[-2], GFP_KERNEL);
 	if (ret < 0)
 		return ret;
-	*sentp += ret;
-	if (ret != rm.iov_len)
-		return -EAGAIN;
 
-	ret = svc_tcp_send_kvec(sock, head, 0);
+	ret = zcopy_memdup(head->iov_len, head->iov_base, &xdr->bvec[-1], GFP_KERNEL);
 	if (ret < 0)
 		return ret;
-	*sentp += ret;
-	if (ret != head->iov_len)
-		goto out;
 
-	if (xdr->page_len) {
-		unsigned int offset, len, remaining;
-		struct bio_vec *bvec;
-
-		bvec = xdr->bvec + (xdr->page_base >> PAGE_SHIFT);
-		offset = offset_in_page(xdr->page_base);
-		remaining = xdr->page_len;
-		while (remaining > 0) {
-			len = min(remaining, bvec->bv_len - offset);
-			ret = kernel_sendpage(sock, bvec->bv_page,
-					      bvec->bv_offset + offset,
-					      len, 0);
-			if (ret < 0)
-				return ret;
-			*sentp += ret;
-			if (ret != len)
-				goto out;
-			remaining -= len;
-			offset = 0;
-			bvec++;
-		}
-	}
+	ret = zcopy_memdup(tail->iov_len, tail->iov_base, &xdr->bvec[n], GFP_KERNEL);
+	if (ret < 0)
+		return ret;
 
-	if (tail->iov_len) {
-		ret = svc_tcp_send_kvec(sock, tail, 0);
-		if (ret < 0)
-			return ret;
-		*sentp += ret;
-	}
+	size = sizeof(marker) + head->iov_len + xdr->page_len + tail->iov_len;
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, xdr->bvec - 2, n + 3, size);
 
-out:
+	ret = sock_sendmsg(sock, &msg);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		*sentp = ret;
+	if (ret != size)
+		return -EAGAIN;
 	return 0;
 }
 
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 36835b2f5446..6dff0b4f17b8 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -145,14 +145,19 @@ xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp)
 {
 	size_t i, n = xdr_buf_pagecount(buf);
 
-	if (n != 0 && buf->bvec == NULL) {
-		buf->bvec = kmalloc_array(n, sizeof(buf->bvec[0]), gfp);
+	if (buf->bvec == NULL) {
+		/* Allow for two headers and a trailer to be attached */
+		buf->bvec = kmalloc_array(n + 3, sizeof(buf->bvec[0]), gfp);
 		if (!buf->bvec)
 			return -ENOMEM;
+		buf->bvec += 2;
+		buf->bvec[-2].bv_page = NULL;
+		buf->bvec[-1].bv_page = NULL;
 		for (i = 0; i < n; i++) {
 			bvec_set_page(&buf->bvec[i], buf->pages[i], PAGE_SIZE,
 				      0);
 		}
+		buf->bvec[n].bv_page = NULL;
 	}
 	return 0;
 }
@@ -160,8 +165,19 @@ xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp)
 void
 xdr_free_bvec(struct xdr_buf *buf)
 {
-	kfree(buf->bvec);
-	buf->bvec = NULL;
+	if (buf->bvec) {
+		size_t n = xdr_buf_pagecount(buf);
+
+		if (buf->bvec[-2].bv_page)
+			put_page(buf->bvec[-2].bv_page);
+		if (buf->bvec[-1].bv_page)
+			put_page(buf->bvec[-1].bv_page);
+		if (buf->bvec[n].bv_page)
+			put_page(buf->bvec[n].bv_page);
+		buf->bvec -= 2;
+		kfree(buf->bvec);
+		buf->bvec = NULL;
+	}
 }
 
 /**


  parent reply	other threads:[~2023-03-16 15:31 UTC|newest]

Thread overview: 60+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-03-16 15:25 [RFC PATCH 00/28] splice, net: Replace sendpage with sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-16 15:25 ` [RFC PATCH 01/28] net: Declare MSG_SPLICE_PAGES internal sendmsg() flag David Howells
2023-03-16 15:25 ` [RFC PATCH 02/28] Add a special allocator for staging netfs protocol to MSG_SPLICE_PAGES David Howells
2023-03-16 17:28   ` Matthew Wilcox
2023-03-16 18:00   ` David Howells
2023-03-16 15:25 ` [RFC PATCH 03/28] tcp: Support MSG_SPLICE_PAGES David Howells
2023-03-16 18:37   ` Willem de Bruijn
2023-03-16 18:44   ` David Howells
2023-03-16 19:00     ` Willem de Bruijn
2023-03-21  0:38     ` David Howells
2023-03-21 14:22       ` Willem de Bruijn
2023-03-22 13:56         ` [RFC PATCH 0/3] net: Drop size arg from ->sendmsg() and pass msghdr into __ip{,6}_append_data() David Howells
2023-03-22 13:56           ` [RFC PATCH 1/3] net: Drop the size argument from ->sendmsg() David Howells
2023-03-22 13:56           ` [RFC PATCH 2/3] ip: Make __ip{,6}_append_data() and co. take a msghdr* David Howells
2023-03-22 13:56           ` [RFC PATCH 3/3] net: Declare MSG_SPLICE_PAGES internal sendmsg() flag David Howells
2023-03-23  1:17           ` [RFC PATCH 0/3] net: Drop size arg from ->sendmsg() and pass msghdr into __ip{,6}_append_data() Willem de Bruijn
2023-03-16 15:25 ` [RFC PATCH 04/28] tcp: Convert do_tcp_sendpages() to use MSG_SPLICE_PAGES David Howells
2023-03-16 15:25 ` [RFC PATCH 05/28] tcp_bpf: Inline do_tcp_sendpages as it's now a wrapper around tcp_sendmsg David Howells
2023-03-16 15:25 ` [RFC PATCH 06/28] espintcp: Inline do_tcp_sendpages() David Howells
2023-03-16 15:25 ` [RFC PATCH 07/28] tls: " David Howells
2023-03-16 15:25 ` [RFC PATCH 08/28] siw: " David Howells
2023-03-16 15:25 ` [RFC PATCH 09/28] tcp: Fold do_tcp_sendpages() into tcp_sendpage_locked() David Howells
2023-03-16 15:26 ` [RFC PATCH 10/28] ip, udp: Support MSG_SPLICE_PAGES David Howells
2023-03-16 15:26 ` [RFC PATCH 11/28] udp: Convert udp_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-16 15:26 ` [RFC PATCH 12/28] af_unix: Support MSG_SPLICE_PAGES David Howells
2023-03-16 15:26 ` [RFC PATCH 13/28] crypto: af_alg: Indent the loop in af_alg_sendmsg() David Howells
2023-03-16 15:26 ` [RFC PATCH 14/28] crypto: af_alg: Support MSG_SPLICE_PAGES David Howells
2023-03-16 15:26 ` [RFC PATCH 15/28] crypto: af_alg: Convert af_alg_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-16 15:26 ` [RFC PATCH 16/28] splice, net: Use sendmsg(MSG_SPLICE_PAGES) rather than ->sendpage() David Howells
2023-03-16 15:26 ` [RFC PATCH 17/28] Remove file->f_op->sendpage David Howells
2023-03-16 15:26 ` [RFC PATCH 18/28] siw: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage to transmit David Howells
2023-03-16 15:26 ` [RFC PATCH 19/28] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-16 15:26 ` [RFC PATCH 20/28] iscsi: " David Howells
2023-03-16 15:26 ` [RFC PATCH 21/28] tcp_bpf: Make tcp_bpf_sendpage() go through tcp_bpf_sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-16 15:26 ` [RFC PATCH 22/28] net: Use sendmsg(MSG_SPLICE_PAGES) not sendpage in skb_send_sock() David Howells
2023-03-16 15:26 ` [RFC PATCH 23/28] algif: Remove hash_sendpage*() David Howells
2023-03-17  2:40   ` Herbert Xu
2023-03-24 16:47     ` David Howells
2023-03-25  6:00       ` Herbert Xu
2023-03-25  7:44       ` David Howells
2023-03-25  9:21         ` Herbert Xu
2023-03-16 15:26 ` [RFC PATCH 24/28] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage() David Howells
2023-03-16 15:26 ` [RFC PATCH 25/28] rds: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-16 15:26 ` [RFC PATCH 26/28] dlm: " David Howells
2023-03-16 15:26 ` David Howells [this message]
2023-03-16 16:17   ` [RFC PATCH 27/28] sunrpc: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage Trond Myklebust
2023-03-16 17:10     ` Chuck Lever III
2023-03-16 17:28     ` David Howells
2023-03-16 17:41       ` Chuck Lever III
2023-03-16 21:21     ` David Howells
2023-03-17 15:29       ` Chuck Lever III
2023-03-16 16:24   ` David Howells
2023-03-16 18:06     ` David Howells
2023-03-16 19:01       ` Trond Myklebust
2023-03-22 13:10       ` David Howells
2023-03-22 18:15       ` [RFC PATCH] iov_iter: Add an iterator-of-iterators David Howells
2023-03-22 18:47         ` Trond Myklebust
2023-03-22 18:49         ` Matthew Wilcox
2023-03-16 15:26 ` [RFC PATCH 28/28] sock: Remove ->sendpage*() in favour of sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-16 15:57   ` Marc Kleine-Budde

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=20230316152618.711970-28-dhowells@redhat.com \
    --to=dhowells@redhat.com \
    --cc=anna@kernel.org \
    --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-nfs@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=torvalds@linux-foundation.org \
    --cc=trond.myklebust@hammerspace.com \
    --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).