Commit 1d7e4538 authored by David Howells's avatar David Howells Committed by Jakub Kicinski
Browse files

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: default avatarLinus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/CAHk-=wh=V579PDYvkpnTobCLGczbgxpMgGmmhqiTyE34Cpi5Gg@mail.gmail.com/


Signed-off-by: default avatarDavid 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: default avatarJakub Kicinski <kuba@kernel.org>
parent d4c1e80b

include/net/inet_common.h

+1 −0
Original line number Diff line number Diff line
@@ -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,

include/net/tcp.h

+1 −0
Original line number Diff line number Diff line
@@ -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,

include/net/udp.h

+1 −0
Original line number Diff line number Diff line
@@ -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);

net/ipv4/af_inet.c

+18 −0
Original line number Diff line number Diff line
@@ -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,

net/ipv4/tcp.c

+16 −0
Original line number Diff line number Diff line
@@ -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)