linux/include/net/inet_common.h
Willy Tarreau 3979ad7e82 net/tcp-fastopen: make connect()'s return case more consistent with non-TFO
Without TFO, any subsequent connect() call after a successful one returns
-1 EISCONN. The last API update ensured that __inet_stream_connect() can
return -1 EINPROGRESS in response to sendmsg() when TFO is in use to
indicate that the connection is now in progress. Unfortunately since this
function is used both for connect() and sendmsg(), it has the undesired
side effect of making connect() now return -1 EINPROGRESS as well after
a successful call, while at the same time poll() returns POLLOUT. This
can confuse some applications which happen to call connect() and to
check for -1 EISCONN to ensure the connection is usable, and for which
EINPROGRESS indicates a need to poll, causing a loop.

This problem was encountered in haproxy where a call to connect() is
precisely used in certain cases to confirm a connection's readiness.
While arguably haproxy's behaviour should be improved here, it seems
important to aim at a more robust behaviour when the goal of the new
API is to make it easier to implement TFO in existing applications.

This patch simply ensures that we preserve the same semantics as in
the non-TFO case on the connect() syscall when using TFO, while still
returning -1 EINPROGRESS on sendmsg(). For this we simply tell
__inet_stream_connect() whether we're doing a regular connect() or in
fact connecting for a sendmsg() call.

Cc: Wei Wang <weiwan@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-25 14:12:21 -05:00

54 lines
1.8 KiB
C

#ifndef _INET_COMMON_H
#define _INET_COMMON_H
extern const struct proto_ops inet_stream_ops;
extern const struct proto_ops inet_dgram_ops;
/*
* INET4 prototypes used by INET6
*/
struct msghdr;
struct sock;
struct sockaddr;
struct socket;
int inet_release(struct socket *sock);
int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags);
int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags, int is_sendmsg);
int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags);
int inet_accept(struct socket *sock, struct socket *newsock, int flags);
int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size);
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,
int flags);
int inet_shutdown(struct socket *sock, int how);
int inet_listen(struct socket *sock, int backlog);
void inet_sock_destruct(struct sock *sk);
int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
int inet_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len,
int peer);
int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int inet_ctl_sock_create(struct sock **sk, unsigned short family,
unsigned short type, unsigned char protocol,
struct net *net);
int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
int *addr_len);
struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb);
int inet_gro_complete(struct sk_buff *skb, int nhoff);
struct sk_buff *inet_gso_segment(struct sk_buff *skb,
netdev_features_t features);
static inline void inet_ctl_sock_destroy(struct sock *sk)
{
if (sk)
sock_release(sk->sk_socket);
}
#endif