From 41063e9dd11956f2d285e12e4342e1d232ba0ea2 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 19 Jun 2012 21:22:05 -0700 Subject: ipv4: Early TCP socket demux. Input packet processing for local sockets involves two major demuxes. One for the route and one for the socket. But we can optimize this down to one demux for certain kinds of local sockets. Currently we only do this for established TCP sockets, but it could at least in theory be expanded to other kinds of connections. If a TCP socket is established then it's identity is fully specified. This means that whatever input route was used during the three-way handshake must work equally well for the rest of the connection since the keys will not change. Once we move to established state, we cache the receive packet's input route to use later. Like the existing cached route in sk->sk_dst_cache used for output packets, we have to check for route invalidations using dst->obsolete and dst->ops->check(). Early demux occurs outside of a socket locked section, so when a route invalidation occurs we defer the fixup of sk->sk_rx_dst until we are actually inside of established state packet processing and thus have the socket locked. Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 18 ++++++++++-------- net/ipv4/ip_input.c | 39 ++++++++++++++++++++++++++------------- net/ipv4/tcp_input.c | 16 +++++++++++++++- net/ipv4/tcp_ipv4.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_minisocks.c | 2 ++ 5 files changed, 99 insertions(+), 22 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 85a3b1763136..07a02f6e9696 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -157,6 +157,7 @@ void inet_sock_destruct(struct sock *sk) kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_check(sk->sk_dst_cache, 1)); + dst_release(sk->sk_rx_dst); sk_refcnt_debug_dec(sk); } EXPORT_SYMBOL(inet_sock_destruct); @@ -1518,14 +1519,15 @@ static const struct net_protocol igmp_protocol = { #endif static const struct net_protocol tcp_protocol = { - .handler = tcp_v4_rcv, - .err_handler = tcp_v4_err, - .gso_send_check = tcp_v4_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp4_gro_receive, - .gro_complete = tcp4_gro_complete, - .no_policy = 1, - .netns_ok = 1, + .early_demux = tcp_v4_early_demux, + .handler = tcp_v4_rcv, + .err_handler = tcp_v4_err, + .gso_send_check = tcp_v4_gso_send_check, + .gso_segment = tcp_tso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, + .no_policy = 1, + .netns_ok = 1, }; static const struct net_protocol udp_protocol = { diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index c4fe1d271131..93b092c9a394 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -323,19 +323,32 @@ static int ip_rcv_finish(struct sk_buff *skb) * how the packet travels inside Linux networking. */ if (skb_dst(skb) == NULL) { - int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - iph->tos, skb->dev); - if (unlikely(err)) { - if (err == -EHOSTUNREACH) - IP_INC_STATS_BH(dev_net(skb->dev), - IPSTATS_MIB_INADDRERRORS); - else if (err == -ENETUNREACH) - IP_INC_STATS_BH(dev_net(skb->dev), - IPSTATS_MIB_INNOROUTES); - else if (err == -EXDEV) - NET_INC_STATS_BH(dev_net(skb->dev), - LINUX_MIB_IPRPFILTER); - goto drop; + const struct net_protocol *ipprot; + int protocol = iph->protocol; + int err; + + rcu_read_lock(); + ipprot = rcu_dereference(inet_protos[protocol]); + err = -ENOENT; + if (ipprot && ipprot->early_demux) + err = ipprot->early_demux(skb); + rcu_read_unlock(); + + if (err) { + err = ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, skb->dev); + if (unlikely(err)) { + if (err == -EHOSTUNREACH) + IP_INC_STATS_BH(dev_net(skb->dev), + IPSTATS_MIB_INADDRERRORS); + else if (err == -ENETUNREACH) + IP_INC_STATS_BH(dev_net(skb->dev), + IPSTATS_MIB_INNOROUTES); + else if (err == -EXDEV) + NET_INC_STATS_BH(dev_net(skb->dev), + LINUX_MIB_IPRPFILTER); + goto drop; + } } } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b224eb8bce8b..8416f8a68e65 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5518,6 +5518,18 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); int res; + if (sk->sk_rx_dst) { + struct dst_entry *dst = sk->sk_rx_dst; + if (unlikely(dst->obsolete)) { + if (dst->ops->check(dst, 0) == NULL) { + dst_release(dst); + sk->sk_rx_dst = NULL; + } + } + } + if (unlikely(sk->sk_rx_dst == NULL)) + sk->sk_rx_dst = dst_clone(skb_dst(skb)); + /* * Header prediction. * The code loosely follows the one in the famous @@ -5729,8 +5741,10 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) tcp_set_state(sk, TCP_ESTABLISHED); - if (skb != NULL) + if (skb != NULL) { + sk->sk_rx_dst = dst_clone(skb_dst(skb)); security_inet_conn_established(sk, skb); + } /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fda2ca17135e..13857df1dae1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1671,6 +1671,52 @@ csum_err: } EXPORT_SYMBOL(tcp_v4_do_rcv); +int tcp_v4_early_demux(struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + const struct iphdr *iph; + const struct tcphdr *th; + struct sock *sk; + int err; + + err = -ENOENT; + if (skb->pkt_type != PACKET_HOST) + goto out_err; + + if (!pskb_may_pull(skb, ip_hdrlen(skb) + sizeof(struct tcphdr))) + goto out_err; + + iph = ip_hdr(skb); + th = (struct tcphdr *) ((char *)iph + ip_hdrlen(skb)); + + if (th->doff < sizeof(struct tcphdr) / 4) + goto out_err; + + if (!pskb_may_pull(skb, ip_hdrlen(skb) + th->doff * 4)) + goto out_err; + + sk = __inet_lookup_established(net, &tcp_hashinfo, + iph->saddr, th->source, + iph->daddr, th->dest, + skb->dev->ifindex); + if (sk) { + skb->sk = sk; + skb->destructor = sock_edemux; + if (sk->sk_state != TCP_TIME_WAIT) { + struct dst_entry *dst = sk->sk_rx_dst; + if (dst) + dst = dst_check(dst, 0); + if (dst) { + skb_dst_set_noref(skb, dst); + err = 0; + } + } + } + +out_err: + return err; +} + /* * From tcp_input.c */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index cb015317c9f7..72b7c63b1a39 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -445,6 +445,8 @@ 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; + newsk->sk_rx_dst = dst_clone(skb_dst(skb)); + /* TCP Cookie Transactions require space for the cookie pair, * as it differs for each connection. There is no need to * copy any s_data_payload stored at the original socket. -- cgit v1.2.3