From 5d134f1c1f36166e8a738de92c4d2f4c262ff91b Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Sat, 5 Jan 2013 16:10:48 +0000 Subject: tcp: make sysctl_tcp_ecn namespace aware As per suggestion from Eric Dumazet this patch makes tcp_ecn sysctl namespace aware. The reason behind this patch is to ease the testing of ecn problems on the internet and allows applications to tune their own use of ecn. Cc: Eric Dumazet Cc: David Miller Cc: Stephen Hemminger Signed-off-by: Hannes Frederic Sowa Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 54139fa514e6..c6ce9ca98d23 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1568,7 +1568,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, skb); + TCP_ECN_create_request(req, skb, sock_net(sk)); if (want_cookie) { isn = cookie_v4_init_sequence(sk, skb, &req->mss); @@ -2888,6 +2888,7 @@ EXPORT_SYMBOL(tcp_prot); static int __net_init tcp_sk_init(struct net *net) { + net->ipv4.sysctl_tcp_ecn = 2; return 0; } -- cgit v1.2.3 From da5e36308d9f7151845018369148201a5d28b46d Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 22 Jan 2013 09:50:24 +0000 Subject: soreuseport: TCP/IPv4 implementation Allow multiple listener sockets to bind to the same port. Motivation for soresuseport would be something like a web server binding to port 80 running with multiple threads, where each thread might have it's own listener socket. This could be done as an alternative to other models: 1) have one listener thread which dispatches completed connections to workers. 2) accept on a single listener socket from multiple threads. In case #1 the listener thread can easily become the bottleneck with high connection turn-over rate. In case #2, the proportion of connections accepted per thread tends to be uneven under high connection load (assuming simple event loop: while (1) { accept(); process() }, wakeup does not promote fairness among the sockets. We have seen the disproportion to be as high as 3:1 ratio between thread accepting most connections and the one accepting the fewest. With so_reusport the distribution is uniform. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c6ce9ca98d23..bbbdcc5c1973 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -657,7 +657,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) * no RST generated if md5 hash doesn't match. */ sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev), - &tcp_hashinfo, ip_hdr(skb)->daddr, + &tcp_hashinfo, ip_hdr(skb)->saddr, + th->source, ip_hdr(skb)->daddr, ntohs(th->source), inet_iif(skb)); /* don't send rst if it can't find key */ if (!sk1) @@ -2074,6 +2075,7 @@ do_time_wait: case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, + iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); if (sk2) { -- cgit v1.2.3 From 2aeef18d37aa8c0bfca169d4ede1790d972bf649 Mon Sep 17 00:00:00 2001 From: Nivedita Singhvi Date: Mon, 28 Jan 2013 17:52:37 +0000 Subject: tcp: Increment LISTENOVERFLOW and LISTENDROPS in tcp_v4_conn_request() We drop a connection request if the accept backlog is full and there are sufficient packets in the syn queue to warrant starting drops. Increment the appropriate counters so this isn't silent, for accurate stats and help in debugging. This patch assumes LINUX_MIB_LISTENDROPS is a superset of/includes the counter LINUX_MIB_LISTENOVERFLOWS. Signed-off-by: Nivedita Singhvi Acked-by: Vijay Subramanian Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 70b09ef2463b..629937d514eb 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1500,8 +1500,11 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * clogging syn queue with openreqs with exponentially increasing * timeout. */ - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto drop; + } req = inet_reqsk_alloc(&tcp_request_sock_ops); if (!req) -- cgit v1.2.3 From 848bf15f361c7c22da7998c81d50ed3dffbc827d Mon Sep 17 00:00:00 2001 From: Vijay Subramanian Date: Thu, 31 Jan 2013 08:24:06 +0000 Subject: tcp: Update MIB counters for drops This patch updates LINUX_MIB_LISTENDROPS in tcp_v4_conn_request() and tcp_v4_err(). tcp_v4_conn_request() in particular can drop SYNs for various reasons which are not currently tracked. Signed-off-by: Vijay Subramanian Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 629937d514eb..eadb693eef55 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -496,6 +496,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) * errors returned from accept(). */ inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; case TCP_SYN_SENT: @@ -1502,7 +1503,6 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) */ if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto drop; } @@ -1669,6 +1669,7 @@ drop_and_release: drop_and_free: reqsk_free(req); drop: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; } EXPORT_SYMBOL(tcp_v4_conn_request); -- cgit v1.2.3 From ee684b6f2830047d19877e5547989740f18b1a5d Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Mon, 11 Feb 2013 05:50:19 +0000 Subject: tcp: send packets with a socket timestamp A socket timestamp is a sum of the global tcp_time_stamp and a per-socket offset. A socket offset is added in places where externally visible tcp timestamp option is parsed/initialized. Connections in the SYN_RECV state are not supported, global tcp_time_stamp is used for them, because repair mode doesn't support this state. In a future it can be implemented by the similar way as for TIME_WAIT sockets. Cc: "David S. Miller" Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Cc: Eric Dumazet Cc: Pavel Emelyanov Signed-off-by: Andrey Vagin Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0eaf685bddc9..77f5050efc8d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -726,7 +726,7 @@ release_sk1: */ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, - u32 win, u32 ts, int oif, + u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int reply_flags, u8 tos) { @@ -747,12 +747,12 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); - if (ts) { + if (tsecr) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); - rep.opt[1] = htonl(tcp_time_stamp); - rep.opt[2] = htonl(ts); + rep.opt[1] = htonl(tsval); + rep.opt[2] = htonl(tsecr); arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED; } @@ -767,7 +767,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, #ifdef CONFIG_TCP_MD5SIG if (key) { - int offset = (ts) ? 3 : 0; + int offset = (tsecr) ? 3 : 0; rep.opt[offset++] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -802,6 +802,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, + tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), @@ -821,6 +822,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, req->rcv_wnd, + tcp_time_stamp, req->ts_recent, 0, tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, -- cgit v1.2.3 From ece31ffd539e8e2b586b1ca5f50bc4f4591e3893 Mon Sep 17 00:00:00 2001 From: Gao feng Date: Mon, 18 Feb 2013 01:34:56 +0000 Subject: net: proc: change proc_net_remove to remove_proc_entry proc_net_remove is only used to remove proc entries that under /proc/net,it's not a general function for removing proc entries of netns. if we want to remove some proc entries which under /proc/net/stat/, we still need to call remove_proc_entry. this patch use remove_proc_entry to replace proc_net_remove. we can remove proc_net_remove after this patch. Signed-off-by: Gao feng Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 77f5050efc8d..145d3bf8df86 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2616,7 +2616,7 @@ EXPORT_SYMBOL(tcp_proc_register); void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo) { - proc_net_remove(net, afinfo->name); + remove_proc_entry(afinfo->name, net->proc_net); } EXPORT_SYMBOL(tcp_proc_unregister); -- cgit v1.2.3 From b67bfe0d42cac56c512dd5da4b1b347a23f4b70a Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 27 Feb 2013 17:06:00 -0800 Subject: hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin Acked-by: Paul E. McKenney Signed-off-by: Sasha Levin Cc: Wu Fengguang Cc: Marcelo Tosatti Cc: Gleb Natapov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- net/ipv4/tcp_ipv4.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 145d3bf8df86..4a8ec457310f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -954,7 +954,6 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; - struct hlist_node *pos; unsigned int size = sizeof(struct in_addr); struct tcp_md5sig_info *md5sig; @@ -968,7 +967,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, if (family == AF_INET6) size = sizeof(struct in6_addr); #endif - hlist_for_each_entry_rcu(key, pos, &md5sig->head, node) { + hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; if (!memcmp(&key->addr, addr, size)) @@ -1069,14 +1068,14 @@ static void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; - struct hlist_node *pos, *n; + struct hlist_node *n; struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, 1); if (!hlist_empty(&md5sig->head)) tcp_free_md5sig_pool(); - hlist_for_each_entry_safe(key, pos, n, &md5sig->head, node) { + hlist_for_each_entry_safe(key, n, &md5sig->head, node) { hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); -- cgit v1.2.3