From 4670fd819e7f47392c7c6fc6168ea2857c66d163 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 9 Jun 2012 01:25:47 -0700 Subject: tcp: Get rid of inetpeer special cases. The get_peer method TCP uses is full of special cases that make no sense accommodating, and it also gets in the way of doing more reasonable things here. First of all, if the socket doesn't have a usable cached route, there is no sense in trying to optimize timewait recycling. Likewise for the case where we have IP options, such as SRR enabled, that make the IP header destination address (and thus the destination address of the route key) differ from that of the connection's destination address. Just return a NULL peer in these cases, and thus we're also able to get rid of the clumsy inetpeer release logic. Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net/inet_connection_sock.h') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 7d83f90f203f..e1b7734c456f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -43,7 +43,7 @@ struct inet_connection_sock_af_ops { struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); - struct inet_peer *(*get_peer)(struct sock *sk, bool *release_it); + struct inet_peer *(*get_peer)(struct sock *sk); u16 net_header_len; u16 net_frag_header_len; u16 sockaddr_len; -- cgit v1.2.3 From 7586eceb0abc0ea1c2b023e3e5d4dfd4ff40930a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 20 Jun 2012 05:02:19 +0000 Subject: ipv4: tcp: dont cache output dst for syncookies Don't cache output dst for syncookies, as this adds pressure on IP route cache and rcu subsystem for no gain. Signed-off-by: Eric Dumazet Cc: Hans Schillstrom Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/net/flow.h | 1 + include/net/inet_connection_sock.h | 3 ++- net/dccp/ipv4.c | 2 +- net/ipv4/inet_connection_sock.c | 8 ++++++-- net/ipv4/route.c | 5 ++++- net/ipv4/tcp_ipv4.c | 12 +++++++----- 6 files changed, 21 insertions(+), 10 deletions(-) (limited to 'include/net/inet_connection_sock.h') diff --git a/include/net/flow.h b/include/net/flow.h index 6c469dbdb917..bd524f598561 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -22,6 +22,7 @@ struct flowi_common { #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_PRECOW_METRICS 0x02 #define FLOWI_FLAG_CAN_SLEEP 0x04 +#define FLOWI_FLAG_RT_NOCACHE 0x08 __u32 flowic_secid; }; diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index e1b7734c456f..af3c743a40e4 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -251,7 +251,8 @@ extern int inet_csk_get_port(struct sock *sk, unsigned short snum); extern struct dst_entry* inet_csk_route_req(struct sock *sk, struct flowi4 *fl4, - const struct request_sock *req); + const struct request_sock *req, + bool nocache); extern struct dst_entry* inet_csk_route_child_sock(struct sock *sk, struct sock *newsk, const struct request_sock *req); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 07f5579ca756..3eb76b5f221a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -504,7 +504,7 @@ static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, struct dst_entry *dst; struct flowi4 fl4; - dst = inet_csk_route_req(sk, &fl4, req); + dst = inet_csk_route_req(sk, &fl4, req, false); if (dst == NULL) goto out; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f9ee7417f6a0..034ddbe42adf 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -368,17 +368,21 @@ EXPORT_SYMBOL(inet_csk_reset_keepalive_timer); struct dst_entry *inet_csk_route_req(struct sock *sk, struct flowi4 *fl4, - const struct request_sock *req) + const struct request_sock *req, + bool nocache) { struct rtable *rt; const struct inet_request_sock *ireq = inet_rsk(req); struct ip_options_rcu *opt = inet_rsk(req)->opt; struct net *net = sock_net(sk); + int flags = inet_sk_flowi_flags(sk) & ~FLOWI_FLAG_PRECOW_METRICS; + if (nocache) + flags |= FLOWI_FLAG_RT_NOCACHE; flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, - inet_sk_flowi_flags(sk) & ~FLOWI_FLAG_PRECOW_METRICS, + flags, (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr, ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport); security_req_classify_flow(req, flowi4_to_flowi(fl4)); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a91f6d33804c..8d62d85e68dc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1156,7 +1156,7 @@ restart: candp = NULL; now = jiffies; - if (!rt_caching(dev_net(rt->dst.dev))) { + if (!rt_caching(dev_net(rt->dst.dev)) || (rt->dst.flags & DST_NOCACHE)) { /* * If we're not caching, just tell the caller we * were successful and don't touch the route. The @@ -2582,6 +2582,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rt_set_nexthop(rth, fl4, res, fi, type, 0); + if (fl4->flowi4_flags & FLOWI_FLAG_RT_NOCACHE) + rth->dst.flags |= DST_NOCACHE; + return rth; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 21e22a00481a..b52934f5334e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -825,7 +825,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct request_values *rvp, - u16 queue_mapping) + u16 queue_mapping, + bool nocache) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; @@ -833,7 +834,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, struct sk_buff * skb; /* First, grab a route. */ - if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) + if (!dst && (dst = inet_csk_route_req(sk, &fl4, req, nocache)) == NULL) return -1; skb = tcp_make_synack(sk, dst, req, rvp); @@ -855,7 +856,7 @@ static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v4_send_synack(sk, NULL, req, rvp, 0); + return tcp_v4_send_synack(sk, NULL, req, rvp, 0, false); } /* @@ -1388,7 +1389,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) */ if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && - (dst = inet_csk_route_req(sk, &fl4, req)) != NULL && + (dst = inet_csk_route_req(sk, &fl4, req, want_cookie)) != NULL && fl4.daddr == saddr && (peer = rt_get_peer((struct rtable *)dst, fl4.daddr)) != NULL) { inet_peer_refcheck(peer); @@ -1424,7 +1425,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (tcp_v4_send_synack(sk, dst, req, (struct request_values *)&tmp_ext, - skb_get_queue_mapping(skb)) || + skb_get_queue_mapping(skb), + want_cookie) || want_cookie) goto drop_and_free; -- cgit v1.2.3 From 16d1839907e695387654901995f9286b65fbbc6a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 10 Jul 2012 03:32:59 -0700 Subject: inet: Remove ->get_peer() method. No longer used. Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 1 - net/ipv4/tcp_ipv4.c | 16 ---------------- net/ipv6/tcp_ipv6.c | 16 ---------------- 3 files changed, 33 deletions(-) (limited to 'include/net/inet_connection_sock.h') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index af3c743a40e4..291e7cee14e7 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -43,7 +43,6 @@ struct inet_connection_sock_af_ops { struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); - struct inet_peer *(*get_peer)(struct sock *sk); u16 net_header_len; u16 net_frag_header_len; u16 sockaddr_len; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d406bf7f37d9..ddefd39ac0cf 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1847,21 +1847,6 @@ do_time_wait: goto discard_it; } -struct inet_peer *tcp_v4_get_peer(struct sock *sk) -{ - struct rtable *rt = (struct rtable *) __sk_dst_get(sk); - struct inet_sock *inet = inet_sk(sk); - - /* If we don't have a valid cached route, or we're doing IP - * options which make the IPv4 header destination address - * different from our peer's, do not bother with this. - */ - if (!rt || inet->cork.fl.u.ip4.daddr != inet->inet_daddr) - return NULL; - return rt_get_peer_create(rt, inet->inet_daddr); -} -EXPORT_SYMBOL(tcp_v4_get_peer); - static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp_timewait_sock), .twsk_unique = tcp_twsk_unique, @@ -1874,7 +1859,6 @@ const struct inet_connection_sock_af_ops ipv4_specific = { .rebuild_header = inet_sk_rebuild_header, .conn_request = tcp_v4_conn_request, .syn_recv_sock = tcp_v4_syn_recv_sock, - .get_peer = tcp_v4_get_peer, .net_header_len = sizeof(struct iphdr), .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 9e96b5f21d2a..61175cb2478f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1689,20 +1689,6 @@ do_time_wait: goto discard_it; } -static struct inet_peer *tcp_v6_get_peer(struct sock *sk) -{ - struct rt6_info *rt = (struct rt6_info *) __sk_dst_get(sk); - struct ipv6_pinfo *np = inet6_sk(sk); - - /* If we don't have a valid cached route, or we're doing IP - * options which make the IPv6 header destination address - * different from our peer's, do not bother with this. - */ - if (!rt || !ipv6_addr_equal(&np->daddr, &rt->rt6i_dst.addr)) - return NULL; - return rt6_get_peer_create(rt); -} - static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_unique = tcp_twsk_unique, @@ -1715,7 +1701,6 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { .rebuild_header = inet6_sk_rebuild_header, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, - .get_peer = tcp_v6_get_peer, .net_header_len = sizeof(struct ipv6hdr), .net_frag_header_len = sizeof(struct frag_hdr), .setsockopt = ipv6_setsockopt, @@ -1747,7 +1732,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .rebuild_header = inet_sk_rebuild_header, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, - .get_peer = tcp_v4_get_peer, .net_header_len = sizeof(struct iphdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, -- cgit v1.2.3 From 80d0a69fc57715dc9080c0567df1ed911b78abea Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 16 Jul 2012 03:28:06 -0700 Subject: ipv4: Add helper inet_csk_update_pmtu(). This abstracts away the call to dst_ops->update_pmtu() so that we can transparently handle the fact that, in the future, the dst itself can be invalidated by the PMTU update (when we have non-host routes cached in sockets). So we try to rebuild the socket cached route after the method invocation if necessary. This isn't used by SCTP because it needs to cache dsts per-transport, and thus will need it's own local version of this helper. Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 ++ net/dccp/ipv4.c | 11 ++------- net/ipv4/inet_connection_sock.c | 46 ++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_ipv4.c | 11 ++------- 4 files changed, 52 insertions(+), 18 deletions(-) (limited to 'include/net/inet_connection_sock.h') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 291e7cee14e7..2cf44b4ed2e6 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -337,4 +337,6 @@ extern int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); + +extern struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 129ed8f74138..683902fcc8ed 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -161,17 +161,10 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, if (sk->sk_state == DCCP_LISTEN) return; - /* We don't check in the destentry if pmtu discovery is forbidden - * on this route. We just assume that no packet_to_big packets - * are send back when pmtu discovery is not active. - * There is a small race when the user changes this flag in the - * route, but I think that's acceptable. - */ - if ((dst = __sk_dst_check(sk, 0)) == NULL) + dst = inet_csk_update_pmtu(sk, mtu); + if (!dst) return; - dst->ops->update_pmtu(dst, mtu); - /* Something is about to be wrong... Remember soft error * for the case, if this connection will not able to recover. */ diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 76825be3b643..200d21809379 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -803,3 +803,49 @@ int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, } EXPORT_SYMBOL_GPL(inet_csk_compat_setsockopt); #endif + +static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl) +{ + struct inet_sock *inet = inet_sk(sk); + struct ip_options_rcu *inet_opt; + __be32 daddr = inet->inet_daddr; + struct flowi4 *fl4; + struct rtable *rt; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; + fl4 = &fl->u.ip4; + rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, + inet->inet_saddr, inet->inet_dport, + inet->inet_sport, sk->sk_protocol, + RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + if (IS_ERR(rt)) + rt = NULL; + if (rt) + sk_setup_caps(sk, &rt->dst); + rcu_read_unlock(); + + return &rt->dst; +} + +struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) +{ + struct dst_entry *dst = __sk_dst_check(sk, 0); + struct inet_sock *inet = inet_sk(sk); + + if (!dst) { + dst = inet_csk_rebuild_route(sk, &inet->cork.fl); + if (!dst) + goto out; + } + dst->ops->update_pmtu(dst, mtu); + + dst = __sk_dst_check(sk, 0); + if (!dst) + dst = inet_csk_rebuild_route(sk, &inet->cork.fl); +out: + return dst; +} +EXPORT_SYMBOL_GPL(inet_csk_update_pmtu); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7a0062cb4ed0..b8e7e0595407 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -289,17 +289,10 @@ static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu) if (sk->sk_state == TCP_LISTEN) return; - /* We don't check in the destentry if pmtu discovery is forbidden - * on this route. We just assume that no packet_to_big packets - * are send back when pmtu discovery is not active. - * There is a small race when the user changes this flag in the - * route, but I think that's acceptable. - */ - if ((dst = __sk_dst_check(sk, 0)) == NULL) + dst = inet_csk_update_pmtu(sk, mtu); + if (!dst) return; - dst->ops->update_pmtu(dst, mtu); - /* Something is about to be wrong... Remember soft error * for the case, if this connection will not able to recover. */ -- cgit v1.2.3 From ba3f7f04ef2b19aace38f855aedd17fe43035d50 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 17 Jul 2012 14:02:46 -0700 Subject: ipv4: Kill FLOWI_FLAG_RT_NOCACHE and associated code. Signed-off-by: David S. Miller --- include/net/flow.h | 1 - include/net/inet_connection_sock.h | 3 +-- net/dccp/ipv4.c | 2 +- net/ipv4/inet_connection_sock.c | 5 +---- net/ipv4/route.c | 3 --- net/ipv4/tcp_ipv4.c | 4 ++-- 6 files changed, 5 insertions(+), 13 deletions(-) (limited to 'include/net/inet_connection_sock.h') diff --git a/include/net/flow.h b/include/net/flow.h index ce9cb7656b47..e1dd5082ec7e 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -21,7 +21,6 @@ struct flowi_common { __u8 flowic_flags; #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_CAN_SLEEP 0x02 -#define FLOWI_FLAG_RT_NOCACHE 0x04 __u32 flowic_secid; }; diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 2cf44b4ed2e6..5ee66f517b4f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -250,8 +250,7 @@ extern int inet_csk_get_port(struct sock *sk, unsigned short snum); extern struct dst_entry* inet_csk_route_req(struct sock *sk, struct flowi4 *fl4, - const struct request_sock *req, - bool nocache); + const struct request_sock *req); extern struct dst_entry* inet_csk_route_child_sock(struct sock *sk, struct sock *newsk, const struct request_sock *req); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ab4f44c9bb21..25428d0c50c9 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -508,7 +508,7 @@ static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, struct dst_entry *dst; struct flowi4 fl4; - dst = inet_csk_route_req(sk, &fl4, req, false); + dst = inet_csk_route_req(sk, &fl4, req); if (dst == NULL) goto out; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0a290d719bc7..db0cf17c00f7 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -368,8 +368,7 @@ EXPORT_SYMBOL(inet_csk_reset_keepalive_timer); struct dst_entry *inet_csk_route_req(struct sock *sk, struct flowi4 *fl4, - const struct request_sock *req, - bool nocache) + const struct request_sock *req) { struct rtable *rt; const struct inet_request_sock *ireq = inet_rsk(req); @@ -377,8 +376,6 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, struct net *net = sock_net(sk); int flags = inet_sk_flowi_flags(sk); - if (nocache) - flags |= FLOWI_FLAG_RT_NOCACHE; flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 97cca8a03d94..7e1c0ed0ef70 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1836,9 +1836,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0); - if (fl4->flowi4_flags & FLOWI_FLAG_RT_NOCACHE) - rth->dst.flags |= DST_NOCACHE; - return rth; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1d8b75a58981..59110caeb074 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -824,7 +824,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, struct sk_buff * skb; /* First, grab a route. */ - if (!dst && (dst = inet_csk_route_req(sk, &fl4, req, nocache)) == NULL) + if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; skb = tcp_make_synack(sk, dst, req, rvp); @@ -1378,7 +1378,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) */ if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && - (dst = inet_csk_route_req(sk, &fl4, req, want_cookie)) != NULL && + (dst = inet_csk_route_req(sk, &fl4, req)) != NULL && fl4.daddr == saddr) { if (!tcp_peer_is_proven(req, dst, true)) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); -- cgit v1.2.3 From 5d299f3d3c8a2fbc732b1bf03af36333ccec3130 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Aug 2012 05:09:33 +0000 Subject: net: ipv6: fix TCP early demux IPv6 needs a cookie in dst_check() call. We need to add rx_dst_cookie and provide a family independent sk_rx_dst_set(sk, skb) method to properly support IPv6 TCP early demux. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + include/net/inet_connection_sock.h | 1 + include/net/inet_sock.h | 9 --------- net/ipv4/tcp_input.c | 4 +++- net/ipv4/tcp_ipv4.c | 13 ++++++++++--- net/ipv4/tcp_minisocks.c | 2 +- net/ipv6/tcp_ipv6.c | 27 +++++++++++++++++++++++++-- 7 files changed, 41 insertions(+), 16 deletions(-) (limited to 'include/net/inet_connection_sock.h') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 379e433e15e0..879db26ec401 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -369,6 +369,7 @@ struct ipv6_pinfo { __u8 rcv_tclass; __u32 dst_cookie; + __u32 rx_dst_cookie; struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 5ee66f517b4f..ba1d3615acbb 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -39,6 +39,7 @@ struct inet_connection_sock_af_ops { int (*queue_xmit)(struct sk_buff *skb, struct flowi *fl); void (*send_check)(struct sock *sk, struct sk_buff *skb); int (*rebuild_header)(struct sock *sk); + void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb); int (*conn_request)(struct sock *sk, struct sk_buff *skb); struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb, struct request_sock *req, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 83b567fe1941..613cfa401672 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -249,13 +249,4 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk) return flags; } -static inline void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - - dst_hold(dst); - sk->sk_rx_dst = dst; - inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; -} - #endif /* _INET_SOCK_H */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2fd2bc9e3c64..85308b90df80 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5392,6 +5392,8 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); + if (unlikely(sk->sk_rx_dst == NULL)) + inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* * Header prediction. * The code loosely follows the one in the famous @@ -5605,7 +5607,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) tcp_set_state(sk, TCP_ESTABLISHED); if (skb != NULL) { - inet_sk_rx_dst_set(sk, skb); + icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 42b2a6a73092..272241f16fcb 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1627,9 +1627,6 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) sk->sk_rx_dst = NULL; } } - if (unlikely(sk->sk_rx_dst == NULL)) - inet_sk_rx_dst_set(sk, skb); - if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) { rsk = sk; goto reset; @@ -1872,10 +1869,20 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_destructor= tcp_twsk_destructor, }; +static void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + + dst_hold(dst); + sk->sk_rx_dst = dst; + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; +} + const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, + .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v4_conn_request, .syn_recv_sock = tcp_v4_syn_recv_sock, .net_header_len = sizeof(struct iphdr), diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 232a90c3ec86..d9c9dcef2de3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -387,7 +387,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct tcp_sock *oldtp = tcp_sk(sk); struct tcp_cookie_values *oldcvp = oldtp->cookie_values; - inet_sk_rx_dst_set(newsk, skb); + newicsk->icsk_af_ops->sk_rx_dst_set(newsk, skb); /* TCP Cookie Transactions require space for the cookie pair, * as it differs for each connection. There is no need to diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c66b90f71c9b..5a439e9a4c01 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1447,7 +1447,17 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC)); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ + struct dst_entry *dst = sk->sk_rx_dst; + sock_rps_save_rxhash(sk, skb); + if (dst) { + if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || + dst->ops->check(dst, np->rx_dst_cookie) == NULL) { + dst_release(dst); + sk->sk_rx_dst = NULL; + } + } + if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) goto reset; if (opt_skb) @@ -1705,9 +1715,9 @@ static void tcp_v6_early_demux(struct sk_buff *skb) struct dst_entry *dst = sk->sk_rx_dst; struct inet_sock *icsk = inet_sk(sk); if (dst) - dst = dst_check(dst, 0); + dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); if (dst && - icsk->rx_dst_ifindex == inet6_iif(skb)) + icsk->rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } @@ -1719,10 +1729,23 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_destructor= tcp_twsk_destructor, }; +static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + const struct rt6_info *rt = (const struct rt6_info *)dst; + + dst_hold(dst); + sk->sk_rx_dst = dst; + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; + if (rt->rt6i_node) + inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum; +} + static const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, + .sk_rx_dst_set = inet6_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct ipv6hdr), -- cgit v1.2.3