@@ -561,6 +561,7 @@ void tcp_cwnd_application_limited(struct sock *sk);
void tcp_resume_early_retransmit(struct sock *sk);
void tcp_rearm_rto(struct sock *sk);
void tcp_reset(struct sock *sk);
+void tcp_fin(struct sock *sk);
/* tcp_timer.c */
void tcp_init_xmit_timers(struct sock *);
@@ -199,4 +199,7 @@ struct tcp_md5sig {
__u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */
};
+/* Conntroll message types to repair tcp connections */
+#define TCP_REPAIR_SEND_FIN 1
+
#endif /* _UAPI_LINUX_TCP_H */
@@ -1070,6 +1070,34 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
return err;
}
+static int tcp_repair_cmsg(struct sock *sk, struct msghdr *msg)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct cmsghdr *cmsg;
+
+ for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+ if (!CMSG_OK(msg, cmsg))
+ return -EINVAL;
+ if (cmsg->cmsg_level != SOL_TCP)
+ continue;
+
+ switch (cmsg->cmsg_type) {
+ case TCP_REPAIR_SEND_FIN:
+ if (tp->repair_queue == TCP_RECV_QUEUE)
+ tcp_fin(sk);
+ else if (tp->repair_queue == TCP_SEND_QUEUE)
+ tcp_shutdown(sk, SEND_SHUTDOWN);
+ else
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t size)
{
@@ -1090,6 +1118,18 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (tp->repair_queue == TCP_NO_QUEUE)
goto out_err;
+ if (msg->msg_controllen) {
+ if (size != 0)
+ return -EINVAL;
+
+ err = tcp_repair_cmsg(sk, msg);
+ if (err < 0)
+ goto out_err;
+
+ goto out;
+ }
+
+ err = -EINVAL;
if (sk->sk_state != TCP_ESTABLISHED)
goto out_err;
@@ -3820,7 +3820,7 @@ void tcp_reset(struct sock *sk)
*
* If we are in FINWAIT-2, a received FIN moves us to TIME-WAIT.
*/
-static void tcp_fin(struct sock *sk)
+void tcp_fin(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
const struct dst_entry *dst;
It's required for restoring sockets in closing states: TCP_FIN_WAIT{1,2}, TCP_WAIT_STOP, TCP_CLOSING, TCP_LAST_ACK. A fin packet is restored by sending a control message (ancillary data). In which queue a packet is restored depends on a value of tp->repair_queue. This interface is choosen, because we are goint to use sendmsg for restoring sockets in TCP_SYN_RECV states. Requests in the TCP_SYN_RECV state will be restored by sending messages in a proper listen socket. A message will contain address and a control messages with sequence numbers. Cc: "David S. Miller" <davem@davemloft.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: James Morris <jmorris@namei.org> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: Patrick McHardy <kaber@trash.net> Cc: Eric Dumazet <edumazet@google.com> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: Andrey Vagin <avagin@openvz.org> --- include/net/tcp.h | 1 + include/uapi/linux/tcp.h | 3 +++ net/ipv4/tcp.c | 40 ++++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_input.c | 2 +- 4 files changed, 45 insertions(+), 1 deletion(-)