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
Message-Id: <20230316152618.711970-23-dhowells@redhat.com>
In-Reply-To: <20230316152618.711970-1-dhowells@redhat.com>
References: <20230316152618.711970-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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);
 }
 
 /**