[PATCH] net: ipv6: fix TCP early demux
From: Eric Dumazet <hidden>
Date: 2012-08-06 15:09:38
From: Eric Dumazet <edumazet@google.com> 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 <edumazet@google.com> --- Note: we could group sk_rx_dst/rx_dst_ifindex/rx_dst_cookie in same cache line (in sk) 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(-)
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 379e433..879db26 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 5ee66f5..ba1d361 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 83b567f..613cfa4 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 2fd2bc9..85308b9 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 42b2a6a..272241f 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 232a90c..d9c9dce 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 c66b90f..5a439e9 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),