diff options
| author | David Howells <dhowells@redhat.com> | 2023-06-07 19:19:13 +0100 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2023-06-08 19:40:30 -0700 |
| commit | 1d7e4538a5463faa0b0e26a7a7b6bd68c7dfdd78 (patch) | |
| tree | 0d539d1a13f203d607446b9163791db0ad7cab5c /net/ipv4/af_inet.c | |
| parent | d4c1e80b0d1bacbbca5184f122b9893c5920c598 (diff) | |
| download | lwn-1d7e4538a5463faa0b0e26a7a7b6bd68c7dfdd78.tar.gz lwn-1d7e4538a5463faa0b0e26a7a7b6bd68c7dfdd78.zip | |
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>
Diffstat (limited to 'net/ipv4/af_inet.c')
| -rw-r--r-- | net/ipv4/af_inet.c | 18 |
1 files changed, 18 insertions, 0 deletions
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, |