From patchwork Thu Dec 2 20:42:10 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Miller X-Patchwork-Id: 74024 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 527B31007D1 for ; Fri, 3 Dec 2010 07:41:49 +1100 (EST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757896Ab0LBUlo (ORCPT ); Thu, 2 Dec 2010 15:41:44 -0500 Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:37740 "EHLO sunset.davemloft.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757877Ab0LBUln (ORCPT ); Thu, 2 Dec 2010 15:41:43 -0500 Received: from localhost (localhost [127.0.0.1]) by sunset.davemloft.net (Postfix) with ESMTP id 9A41E24C088 for ; Thu, 2 Dec 2010 12:42:10 -0800 (PST) Date: Thu, 02 Dec 2010 12:42:10 -0800 (PST) Message-Id: <20101202.124210.112602035.davem@davemloft.net> To: netdev@vger.kernel.org Subject: [PATCH 3/7] timewait_sock: Create and use getpeer op. From: David Miller X-Mailer: Mew version 6.3 on Emacs 23.1 / Mule 6.0 (HANACHIRUSATO) Mime-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org The only thing AF-specific about remembering the timestamp for a time-wait TCP socket is getting the peer. Abstract that behind a new timewait_sock_ops vector. Support for real IPV6 sockets is not filled in yet, but curiously this makes timewait recycling start to work for v4-mapped ipv6 sockets. Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + include/net/timewait_sock.h | 8 ++++++++ net/ipv4/tcp_ipv4.c | 33 +++++++++++---------------------- net/ipv4/tcp_minisocks.c | 32 ++++++++++++++++++++++++-------- net/ipv6/tcp_ipv6.c | 26 +++++++++++++++++++------- 5 files changed, 63 insertions(+), 37 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 3e23964..4097320 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -313,6 +313,7 @@ extern void tcp_shutdown (struct sock *sk, int how); extern int tcp_v4_rcv(struct sk_buff *skb); extern struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it); +extern void *tcp_v4_tw_get_peer(struct sock *sk); extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size); diff --git a/include/net/timewait_sock.h b/include/net/timewait_sock.h index 97c3b14..053b3cf 100644 --- a/include/net/timewait_sock.h +++ b/include/net/timewait_sock.h @@ -21,6 +21,7 @@ struct timewait_sock_ops { int (*twsk_unique)(struct sock *sk, struct sock *sktw, void *twp); void (*twsk_destructor)(struct sock *sk); + void *(*twsk_getpeer)(struct sock *sk); }; static inline int twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -39,4 +40,11 @@ static inline void twsk_destructor(struct sock *sk) sk->sk_prot->twsk_prot->twsk_destructor(sk); } +static inline void *twsk_getpeer(struct sock *sk) +{ + if (sk->sk_prot->twsk_prot->twsk_getpeer) + return sk->sk_prot->twsk_prot->twsk_getpeer(sk); + return NULL; +} + #endif /* _TIMEWAIT_SOCK_H */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0ddf819..dd55505 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1210,12 +1210,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { }; #endif -static struct timewait_sock_ops tcp_timewait_sock_ops = { - .twsk_obj_size = sizeof(struct tcp_timewait_sock), - .twsk_unique = tcp_twsk_unique, - .twsk_destructor= tcp_twsk_destructor, -}; - int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct tcp_extend_values tmp_ext; @@ -1783,25 +1777,20 @@ struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it) } EXPORT_SYMBOL(tcp_v4_get_peer); -int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw) +void *tcp_v4_tw_get_peer(struct sock *sk) { - struct inet_peer *peer = inet_getpeer_v4(tw->tw_daddr, 1); - - if (peer) { - const struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); - - if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 || - ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && - peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { - peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; - peer->tcp_ts = tcptw->tw_ts_recent; - } - inet_putpeer(peer); - return 1; - } + struct inet_timewait_sock *tw = inet_twsk(sk); - return 0; + return inet_getpeer_v4(tw->tw_daddr, 1); } +EXPORT_SYMBOL(tcp_v4_tw_get_peer); + +static struct timewait_sock_ops tcp_timewait_sock_ops = { + .twsk_obj_size = sizeof(struct tcp_timewait_sock), + .twsk_unique = tcp_twsk_unique, + .twsk_destructor= tcp_twsk_destructor, + .twsk_getpeer = tcp_v4_tw_get_peer, +}; const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 059082c..3527b51 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -78,6 +78,27 @@ static int tcp_remember_stamp(struct sock *sk) return 0; } +static int tcp_tw_remember_stamp(struct inet_timewait_sock *tw) +{ + struct sock *sk = (struct sock *) tw; + struct inet_peer *peer; + + peer = twsk_getpeer(sk); + if (peer) { + const struct tcp_timewait_sock *tcptw = tcp_twsk(sk); + + if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 || + ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && + peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { + peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; + peer->tcp_ts = tcptw->tw_ts_recent; + } + inet_putpeer(peer); + return 1; + } + return 0; +} + static __inline__ int tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) { if (seq == s_win) @@ -178,14 +199,9 @@ kill_with_rst: tcptw->tw_ts_recent = tmp_opt.rcv_tsval; } - /* I am shamed, but failed to make it more elegant. - * Yes, it is direct reference to IP, which is impossible - * to generalize to IPv6. Taking into account that IPv6 - * do not understand recycling in any case, it not - * a big problem in practice. --ANK */ - if (tw->tw_family == AF_INET && - tcp_death_row.sysctl_tw_recycle && tcptw->tw_ts_recent_stamp && - tcp_v4_tw_remember_stamp(tw)) + if (tcp_death_row.sysctl_tw_recycle && + tcptw->tw_ts_recent_stamp && + tcp_tw_remember_stamp(tw)) inet_twsk_schedule(tw, &tcp_death_row, tw->tw_timeout, TCP_TIMEWAIT_LEN); else diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e394d00..5f73a18 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -906,12 +906,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { }; #endif -static struct timewait_sock_ops tcp6_timewait_sock_ops = { - .twsk_obj_size = sizeof(struct tcp6_timewait_sock), - .twsk_unique = tcp_twsk_unique, - .twsk_destructor= tcp_twsk_destructor, -}; - static void __tcp_v6_send_check(struct sk_buff *skb, struct in6_addr *saddr, struct in6_addr *daddr) { @@ -1818,12 +1812,30 @@ do_time_wait: goto discard_it; } -struct inet_peer *tcp_v6_get_peer(struct sock *sk, bool *release_it) +static struct inet_peer *tcp_v6_get_peer(struct sock *sk, bool *release_it) +{ + /* Alas, not yet... */ + return NULL; +} + +static void *tcp_v6_tw_get_peer(struct sock *sk) { + struct inet_timewait_sock *tw = inet_twsk(sk); + + if (tw->tw_family == AF_INET) + return tcp_v4_tw_get_peer(sk); + /* Alas, not yet... */ return NULL; } +static struct timewait_sock_ops tcp6_timewait_sock_ops = { + .twsk_obj_size = sizeof(struct tcp6_timewait_sock), + .twsk_unique = tcp_twsk_unique, + .twsk_destructor= tcp_twsk_destructor, + .twsk_getpeer = tcp_v6_tw_get_peer, +}; + static const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check,