ipv4, ipv6: Use splice_eof() to flush

Allow splice to undo the effects of MSG_MORE after prematurely ending a
splice/sendfile due to getting an EOF condition (->splice_read() returned
0) after splice had called sendmsg() with MSG_MORE set when the user didn't
set MSG_MORE.

For UDP, a pending packet will not be emitted if the socket is closed
before it is flushed; with this change, it be flushed by ->splice_eof().

For TCP, it's not clear that MSG_MORE is actually effective.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/CAHk-=wh=V579PDYvkpnTobCLGczbgxpMgGmmhqiTyE34Cpi5Gg@mail.gmail.com/
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Kuniyuki Iwashima <kuniyu@amazon.com>
cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
cc: David Ahern <dsahern@kernel.org>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

10 files changed, 71 insertions, 0 deletions

diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 77f4b0ef5b92..a75333342c4e 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -35,6 +35,7 @@ void __inet_accept(struct socket *sock, struct socket *newsock,
 		   struct sock *newsk);
 int inet_send_prepare(struct sock *sk);
 int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size);
+void inet_splice_eof(struct socket *sock);
 ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
 		      size_t size, int flags);
 int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 68990a8f556a..49611af31bb7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -327,6 +327,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size);
 int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
 			 size_t size, struct ubuf_info *uarg);
+void tcp_splice_eof(struct socket *sock);
 int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
 		 int flags);
 int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
diff --git a/include/net/udp.h b/include/net/udp.h
index 5cad44318d71..4ed0b47c5582 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -278,6 +278,7 @@ int udp_get_port(struct sock *sk, unsigned short snum,
 int udp_err(struct sk_buff *, u32);
 int udp_abort(struct sock *sk, int err);
 int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
+void udp_splice_eof(struct socket *sock);
 int udp_push_pending_frames(struct sock *sk);
 void udp_flush_pending_frames(struct sock *sk);
 int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index b5735b3551cf..fd233c4195ac 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -831,6 +831,21 @@ int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 }
 EXPORT_SYMBOL(inet_sendmsg);
 
+void inet_splice_eof(struct socket *sock)
+{
+	const struct proto *prot;
+	struct sock *sk = sock->sk;
+
+	if (unlikely(inet_send_prepare(sk)))
+		return;
+
+	/* IPV6_ADDRFORM can change sk->sk_prot under us. */
+	prot = READ_ONCE(sk->sk_prot);
+	if (prot->splice_eof)
+		prot->splice_eof(sock);
+}
+EXPORT_SYMBOL_GPL(inet_splice_eof);
+
 ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
 		      size_t size, int flags)
 {
@@ -1050,6 +1065,7 @@ const struct proto_ops inet_stream_ops = {
 #ifdef CONFIG_MMU
 	.mmap		   = tcp_mmap,
 #endif
+	.splice_eof	   = inet_splice_eof,
 	.sendpage	   = inet_sendpage,
 	.splice_read	   = tcp_splice_read,
 	.read_sock	   = tcp_read_sock,
@@ -1084,6 +1100,7 @@ const struct proto_ops inet_dgram_ops = {
 	.read_skb	   = udp_read_skb,
 	.recvmsg	   = inet_recvmsg,
 	.mmap		   = sock_no_mmap,
+	.splice_eof	   = inet_splice_eof,
 	.sendpage	   = inet_sendpage,
 	.set_peek_off	   = sk_set_peek_off,
 #ifdef CONFIG_COMPAT
@@ -1115,6 +1132,7 @@ static const struct proto_ops inet_sockraw_ops = {
 	.sendmsg	   = inet_sendmsg,
 	.recvmsg	   = inet_recvmsg,
 	.mmap		   = sock_no_mmap,
+	.splice_eof	   = inet_splice_eof,
 	.sendpage	   = inet_sendpage,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	   = inet_compat_ioctl,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 53b7751b68e1..09f03221a6f1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1371,6 +1371,22 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 }
 EXPORT_SYMBOL(tcp_sendmsg);
 
+void tcp_splice_eof(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct tcp_sock *tp = tcp_sk(sk);
+	int mss_now, size_goal;
+
+	if (!tcp_write_queue_tail(sk))
+		return;
+
+	lock_sock(sk);
+	mss_now = tcp_send_mss(sk, &size_goal, 0);
+	tcp_push(sk, 0, mss_now, tp->nonagle, size_goal);
+	release_sock(sk);
+}
+EXPORT_SYMBOL_GPL(tcp_splice_eof);
+
 /*
  *	Handle reading urgent data. BSD has very simple semantics for
  *	this, no blocking and very strange errors 8)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 53e9ce2f05bb..84a5d557dc1a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3116,6 +3116,7 @@ struct proto tcp_prot = {
 	.keepalive		= tcp_set_keepalive,
 	.recvmsg		= tcp_recvmsg,
 	.sendmsg		= tcp_sendmsg,
+	.splice_eof		= tcp_splice_eof,
 	.sendpage		= tcp_sendpage,
 	.backlog_rcv		= tcp_v4_do_rcv,
 	.release_cb		= tcp_release_cb,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index fd3dae081f3a..df5e407286d7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1324,6 +1324,21 @@ do_confirm:
 }
 EXPORT_SYMBOL(udp_sendmsg);
 
+void udp_splice_eof(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct udp_sock *up = udp_sk(sk);
+
+	if (!up->pending || READ_ONCE(up->corkflag))
+		return;
+
+	lock_sock(sk);
+	if (up->pending && !READ_ONCE(up->corkflag))
+		udp_push_pending_frames(sk);
+	release_sock(sk);
+}
+EXPORT_SYMBOL_GPL(udp_splice_eof);
+
 int udp_sendpage(struct sock *sk, struct page *page, int offset,
 		 size_t size, int flags)
 {
@@ -2918,6 +2933,7 @@ struct proto udp_prot = {
 	.getsockopt		= udp_getsockopt,
 	.sendmsg		= udp_sendmsg,
 	.recvmsg		= udp_recvmsg,
+	.splice_eof		= udp_splice_eof,
 	.sendpage		= udp_sendpage,
 	.release_cb		= ip4_datagram_release_cb,
 	.hash			= udp_lib_hash,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 2bbf13216a3d..564942bee067 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -695,6 +695,7 @@ const struct proto_ops inet6_stream_ops = {
 #ifdef CONFIG_MMU
 	.mmap		   = tcp_mmap,
 #endif
+	.splice_eof	   = inet_splice_eof,
 	.sendpage	   = inet_sendpage,
 	.sendmsg_locked    = tcp_sendmsg_locked,
 	.sendpage_locked   = tcp_sendpage_locked,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d657713d1c71..c17c8ff94b79 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2150,6 +2150,7 @@ struct proto tcpv6_prot = {
 	.keepalive		= tcp_set_keepalive,
 	.recvmsg		= tcp_recvmsg,
 	.sendmsg		= tcp_sendmsg,
+	.splice_eof		= tcp_splice_eof,
 	.sendpage		= tcp_sendpage,
 	.backlog_rcv		= tcp_v6_do_rcv,
 	.release_cb		= tcp_release_cb,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e5a337e6b970..317b01c9bc39 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1653,6 +1653,20 @@ do_confirm:
 }
 EXPORT_SYMBOL(udpv6_sendmsg);
 
+static void udpv6_splice_eof(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct udp_sock *up = udp_sk(sk);
+
+	if (!up->pending || READ_ONCE(up->corkflag))
+		return;
+
+	lock_sock(sk);
+	if (up->pending && !READ_ONCE(up->corkflag))
+		udp_v6_push_pending_frames(sk);
+	release_sock(sk);
+}
+
 void udpv6_destroy_sock(struct sock *sk)
 {
 	struct udp_sock *up = udp_sk(sk);
@@ -1764,6 +1778,7 @@ struct proto udpv6_prot = {
 	.getsockopt		= udpv6_getsockopt,
 	.sendmsg		= udpv6_sendmsg,
 	.recvmsg		= udpv6_recvmsg,
+	.splice_eof		= udpv6_splice_eof,
 	.release_cb		= ip6_datagram_release_cb,
 	.hash			= udp_lib_hash,
 	.unhash			= udp_lib_unhash,