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
Subject: [RFC PATCH 22/28] net: Use sendmsg(MSG_SPLICE_PAGES) not sendpage in skb_send_sock()
Date: Thu, 16 Mar 2023 15:26:12 +0000 [thread overview]
Message-ID: <20230316152618.711970-23-dhowells@redhat.com> (raw)
In-Reply-To: <20230316152618.711970-1-dhowells@redhat.com>
Use sendmsg() with MSG_SPLICE_PAGES rather than sendpage in
skb_send_sock(). This causes pages to be spliced from the source iterator
if possible (the iterator must be ITER_BVEC and the pages must be
spliceable).
This allows ->sendpage() to be replaced by something that can handle
multiple multipage folios in a single transaction.
Note that this could perhaps be improved to fill out a bvec array with all
the frags and then make a single sendmsg call, possibly sticking the header
on the front also.
Signed-off-by: David Howells <dhowells@redhat.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: netdev@vger.kernel.org
---
net/core/skbuff.c | 49 ++++++++++++++++++++++++++---------------------
1 file changed, 27 insertions(+), 22 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index eb7d33b41e71..9fa333e26b7d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2927,32 +2927,32 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
}
EXPORT_SYMBOL_GPL(skb_splice_bits);
-static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg,
- struct kvec *vec, size_t num, size_t size)
+static int sendmsg_locked(struct sock *sk, struct msghdr *msg)
{
struct socket *sock = sk->sk_socket;
+ size_t size = msg_data_left(msg);
if (!sock)
return -EINVAL;
- return kernel_sendmsg(sock, msg, vec, num, size);
+
+ if (!sock->ops->sendmsg_locked)
+ return sock_no_sendmsg_locked(sk, msg, size);
+
+ return sock->ops->sendmsg_locked(sk, msg, size);
}
-static int sendpage_unlocked(struct sock *sk, struct page *page, int offset,
- size_t size, int flags)
+static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg)
{
struct socket *sock = sk->sk_socket;
if (!sock)
return -EINVAL;
- return kernel_sendpage(sock, page, offset, size, flags);
+ return sock_sendmsg(sock, msg);
}
-typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg,
- struct kvec *vec, size_t num, size_t size);
-typedef int (*sendpage_func)(struct sock *sk, struct page *page, int offset,
- size_t size, int flags);
+typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg);
static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
- int len, sendmsg_func sendmsg, sendpage_func sendpage)
+ int len, sendmsg_func sendmsg)
{
unsigned int orig_len = len;
struct sk_buff *head = skb;
@@ -2972,8 +2972,9 @@ static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
memset(&msg, 0, sizeof(msg));
msg.msg_flags = MSG_DONTWAIT;
- ret = INDIRECT_CALL_2(sendmsg, kernel_sendmsg_locked,
- sendmsg_unlocked, sk, &msg, &kv, 1, slen);
+ iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen);
+ ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
+ sendmsg_unlocked, sk, &msg);
if (ret <= 0)
goto error;
@@ -3004,11 +3005,17 @@ static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
slen = min_t(size_t, len, skb_frag_size(frag) - offset);
while (slen) {
- ret = INDIRECT_CALL_2(sendpage, kernel_sendpage_locked,
- sendpage_unlocked, sk,
- skb_frag_page(frag),
- skb_frag_off(frag) + offset,
- slen, MSG_DONTWAIT);
+ struct bio_vec bvec;
+ struct msghdr msg = {
+ .msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT,
+ };
+
+ bvec_set_page(&bvec, skb_frag_page(frag), slen,
+ skb_frag_off(frag) + offset);
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, slen);
+
+ ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
+ sendmsg_unlocked, sk, &msg);
if (ret <= 0)
goto error;
@@ -3045,16 +3052,14 @@ static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset,
int len)
{
- return __skb_send_sock(sk, skb, offset, len, kernel_sendmsg_locked,
- kernel_sendpage_locked);
+ return __skb_send_sock(sk, skb, offset, len, sendmsg_locked);
}
EXPORT_SYMBOL_GPL(skb_send_sock_locked);
/* Send skb data on a socket. Socket must be unlocked. */
int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len)
{
- return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked,
- sendpage_unlocked);
+ return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked);
}
/**
next prev parent reply other threads:[~2023-03-16 15:30 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 ` David Howells [this message]
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 ` [RFC PATCH 27/28] sunrpc: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage David Howells
2023-03-16 16:17 ` 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=20230316152618.711970-23-dhowells@redhat.com \
--to=dhowells@redhat.com \
--cc=axboe@kernel.dk \
--cc=brauner@kernel.org \
--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=netdev@vger.kernel.org \
--cc=pabeni@redhat.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).