From 5a5f3a8db9d70c90e9d55b46e02b2d8deb1c2c2e Mon Sep 17 00:00:00 2001
From: Jianjun Kong <jianjun@zeuux.org>
Date: Mon, 3 Nov 2008 00:24:34 -0800
Subject: net: clean up net/ipv4/ipip.c raw.c tcp.c tcp_minisocks.c tcp_yeah.c
 xfrm4_policy.c

Signed-off-by: Jianjun Kong <jianjun@zeuux.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'net/ipv4/tcp.c')

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index eccb7165a80c..60c28add96b8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1681,7 +1681,7 @@ void tcp_set_state(struct sock *sk, int state)
 			inet_put_port(sk);
 		/* fall through */
 	default:
-		if (oldstate==TCP_ESTABLISHED)
+		if (oldstate == TCP_ESTABLISHED)
 			TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
 	}
 
@@ -1691,7 +1691,7 @@ void tcp_set_state(struct sock *sk, int state)
 	sk->sk_state = state;
 
 #ifdef STATE_TRACE
-	SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n",sk, statename[oldstate],statename[state]);
+	SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]);
 #endif
 }
 EXPORT_SYMBOL_GPL(tcp_set_state);
@@ -2651,7 +2651,7 @@ EXPORT_SYMBOL(tcp_md5_hash_key);
 
 void tcp_done(struct sock *sk)
 {
-	if(sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
+	if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
 		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
 
 	tcp_set_state(sk, TCP_CLOSE);
-- 
cgit v1.2.3-59-g8ed1b


From 3ab5aee7fe840b5b1b35a8d1ac11c3de5281e611 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <dada1@cosmosbay.com>
Date: Sun, 16 Nov 2008 19:40:17 -0800
Subject: net: Convert TCP & DCCP hash tables to use RCU / hlist_nulls

RCU was added to UDP lookups, using a fast infrastructure :
- sockets kmem_cache use SLAB_DESTROY_BY_RCU and dont pay the
  price of call_rcu() at freeing time.
- hlist_nulls permits to use few memory barriers.

This patch uses same infrastructure for TCP/DCCP established
and timewait sockets.

Thanks to SLAB_DESTROY_BY_RCU, no slowdown for applications
using short lived TCP connections. A followup patch, converting
rwlocks to spinlocks will even speedup this case.

__inet_lookup_established() is pretty fast now we dont have to
dirty a contended cache line (read_lock/read_unlock)

Only established and timewait hashtable are converted to RCU
(bind table and listen table are still using traditional locking)

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h    |  4 +--
 include/net/inet_timewait_sock.h | 10 +++---
 net/core/sock.c                  |  4 ++-
 net/dccp/ipv4.c                  |  1 +
 net/dccp/ipv6.c                  |  1 +
 net/dccp/proto.c                 |  4 +--
 net/ipv4/inet_diag.c             |  7 ++--
 net/ipv4/inet_hashtables.c       | 78 ++++++++++++++++++++++++++++------------
 net/ipv4/inet_timewait_sock.c    | 26 ++++++++------
 net/ipv4/tcp.c                   |  4 +--
 net/ipv4/tcp_ipv4.c              | 25 ++++++-------
 net/ipv6/inet6_hashtables.c      | 70 ++++++++++++++++++++++++------------
 net/ipv6/tcp_ipv6.c              |  1 +
 13 files changed, 151 insertions(+), 84 deletions(-)

(limited to 'net/ipv4/tcp.c')

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index cb31fbf8ae2a..481896045111 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -41,8 +41,8 @@
  * I'll experiment with dynamic table growth later.
  */
 struct inet_ehash_bucket {
-	struct hlist_head chain;
-	struct hlist_head twchain;
+	struct hlist_nulls_head chain;
+	struct hlist_nulls_head twchain;
 };
 
 /* There are a few simple rules, which allow for local port reuse by
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 80e4977631b8..4b8ece22b8e9 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -110,7 +110,7 @@ struct inet_timewait_sock {
 #define tw_state		__tw_common.skc_state
 #define tw_reuse		__tw_common.skc_reuse
 #define tw_bound_dev_if		__tw_common.skc_bound_dev_if
-#define tw_node			__tw_common.skc_node
+#define tw_node			__tw_common.skc_nulls_node
 #define tw_bind_node		__tw_common.skc_bind_node
 #define tw_refcnt		__tw_common.skc_refcnt
 #define tw_hash			__tw_common.skc_hash
@@ -137,10 +137,10 @@ struct inet_timewait_sock {
 	struct hlist_node	tw_death_node;
 };
 
-static inline void inet_twsk_add_node(struct inet_timewait_sock *tw,
-				      struct hlist_head *list)
+static inline void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
+				      struct hlist_nulls_head *list)
 {
-	hlist_add_head(&tw->tw_node, list);
+	hlist_nulls_add_head_rcu(&tw->tw_node, list);
 }
 
 static inline void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
@@ -175,7 +175,7 @@ static inline int inet_twsk_del_dead_node(struct inet_timewait_sock *tw)
 }
 
 #define inet_twsk_for_each(tw, node, head) \
-	hlist_for_each_entry(tw, node, head, tw_node)
+	hlist_nulls_for_each_entry(tw, node, head, tw_node)
 
 #define inet_twsk_for_each_inmate(tw, node, jail) \
 	hlist_for_each_entry(tw, node, jail, tw_death_node)
diff --git a/net/core/sock.c b/net/core/sock.c
index ded1eb5d2fd4..38de9c3f563b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2082,7 +2082,9 @@ int proto_register(struct proto *prot, int alloc_slab)
 			prot->twsk_prot->twsk_slab =
 				kmem_cache_create(timewait_sock_slab_name,
 						  prot->twsk_prot->twsk_obj_size,
-						  0, SLAB_HWCACHE_ALIGN,
+						  0,
+						  SLAB_HWCACHE_ALIGN |
+							prot->slab_flags,
 						  NULL);
 			if (prot->twsk_prot->twsk_slab == NULL)
 				goto out_free_timewait_sock_slab_name;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 528baa2e5be4..d1dd95289b89 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -938,6 +938,7 @@ static struct proto dccp_v4_prot = {
 	.orphan_count		= &dccp_orphan_count,
 	.max_header		= MAX_DCCP_HEADER,
 	.obj_size		= sizeof(struct dccp_sock),
+	.slab_flags		= SLAB_DESTROY_BY_RCU,
 	.rsk_prot		= &dccp_request_sock_ops,
 	.twsk_prot		= &dccp_timewait_sock_ops,
 	.h.hashinfo		= &dccp_hashinfo,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 4aa1148cdb20..f033e845bb07 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1140,6 +1140,7 @@ static struct proto dccp_v6_prot = {
 	.orphan_count	   = &dccp_orphan_count,
 	.max_header	   = MAX_DCCP_HEADER,
 	.obj_size	   = sizeof(struct dccp6_sock),
+	.slab_flags	   = SLAB_DESTROY_BY_RCU,
 	.rsk_prot	   = &dccp6_request_sock_ops,
 	.twsk_prot	   = &dccp6_timewait_sock_ops,
 	.h.hashinfo	   = &dccp_hashinfo,
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 46cb3490d48e..1117d4d8c8f1 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1090,8 +1090,8 @@ static int __init dccp_init(void)
 	}
 
 	for (i = 0; i < dccp_hashinfo.ehash_size; i++) {
-		INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].chain);
-		INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].twchain);
+		INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i);
+		INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].twchain, i);
 	}
 
 	if (inet_ehash_locks_alloc(&dccp_hashinfo))
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 564230dabcb8..41b36720e977 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -778,18 +778,19 @@ skip_listen_ht:
 		struct inet_ehash_bucket *head = &hashinfo->ehash[i];
 		rwlock_t *lock = inet_ehash_lockp(hashinfo, i);
 		struct sock *sk;
-		struct hlist_node *node;
+		struct hlist_nulls_node *node;
 
 		num = 0;
 
-		if (hlist_empty(&head->chain) && hlist_empty(&head->twchain))
+		if (hlist_nulls_empty(&head->chain) &&
+			hlist_nulls_empty(&head->twchain))
 			continue;
 
 		if (i > s_i)
 			s_num = 0;
 
 		read_lock_bh(lock);
-		sk_for_each(sk, node, &head->chain) {
+		sk_nulls_for_each(sk, node, &head->chain) {
 			struct inet_sock *inet = inet_sk(sk);
 
 			if (num < s_num)
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index be41ebbec4eb..fd269cfef0ec 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -223,35 +223,65 @@ struct sock * __inet_lookup_established(struct net *net,
 	INET_ADDR_COOKIE(acookie, saddr, daddr)
 	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
 	struct sock *sk;
-	const struct hlist_node *node;
+	const struct hlist_nulls_node *node;
 	/* Optimize here for direct hit, only listening connections can
 	 * have wildcards anyways.
 	 */
 	unsigned int hash = inet_ehashfn(net, daddr, hnum, saddr, sport);
-	struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash);
-	rwlock_t *lock = inet_ehash_lockp(hashinfo, hash);
+	unsigned int slot = hash & (hashinfo->ehash_size - 1);
+	struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
 
-	prefetch(head->chain.first);
-	read_lock(lock);
-	sk_for_each(sk, node, &head->chain) {
+	rcu_read_lock();
+begin:
+	sk_nulls_for_each_rcu(sk, node, &head->chain) {
 		if (INET_MATCH(sk, net, hash, acookie,
-					saddr, daddr, ports, dif))
-			goto hit; /* You sunk my battleship! */
+					saddr, daddr, ports, dif)) {
+			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
+				goto begintw;
+			if (unlikely(!INET_MATCH(sk, net, hash, acookie,
+				saddr, daddr, ports, dif))) {
+				sock_put(sk);
+				goto begin;
+			}
+			goto out;
+		}
 	}
+	/*
+	 * if the nulls value we got at the end of this lookup is
+	 * not the expected one, we must restart lookup.
+	 * We probably met an item that was moved to another chain.
+	 */
+	if (get_nulls_value(node) != slot)
+		goto begin;
 
+begintw:
 	/* Must check for a TIME_WAIT'er before going to listener hash. */
-	sk_for_each(sk, node, &head->twchain) {
+	sk_nulls_for_each_rcu(sk, node, &head->twchain) {
 		if (INET_TW_MATCH(sk, net, hash, acookie,
-					saddr, daddr, ports, dif))
-			goto hit;
+					saddr, daddr, ports, dif)) {
+			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
+				sk = NULL;
+				goto out;
+			}
+			if (unlikely(!INET_TW_MATCH(sk, net, hash, acookie,
+				 saddr, daddr, ports, dif))) {
+				sock_put(sk);
+				goto begintw;
+			}
+			goto out;
+		}
 	}
+	/*
+	 * if the nulls value we got at the end of this lookup is
+	 * not the expected one, we must restart lookup.
+	 * We probably met an item that was moved to another chain.
+	 */
+	if (get_nulls_value(node) != slot)
+		goto begintw;
 	sk = NULL;
 out:
-	read_unlock(lock);
+	rcu_read_unlock();
 	return sk;
-hit:
-	sock_hold(sk);
-	goto out;
 }
 EXPORT_SYMBOL_GPL(__inet_lookup_established);
 
@@ -272,14 +302,14 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
 	rwlock_t *lock = inet_ehash_lockp(hinfo, hash);
 	struct sock *sk2;
-	const struct hlist_node *node;
+	const struct hlist_nulls_node *node;
 	struct inet_timewait_sock *tw;
 
 	prefetch(head->chain.first);
 	write_lock(lock);
 
 	/* Check TIME-WAIT sockets first. */
-	sk_for_each(sk2, node, &head->twchain) {
+	sk_nulls_for_each(sk2, node, &head->twchain) {
 		tw = inet_twsk(sk2);
 
 		if (INET_TW_MATCH(sk2, net, hash, acookie,
@@ -293,7 +323,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 	tw = NULL;
 
 	/* And established part... */
-	sk_for_each(sk2, node, &head->chain) {
+	sk_nulls_for_each(sk2, node, &head->chain) {
 		if (INET_MATCH(sk2, net, hash, acookie,
 					saddr, daddr, ports, dif))
 			goto not_unique;
@@ -306,7 +336,7 @@ unique:
 	inet->sport = htons(lport);
 	sk->sk_hash = hash;
 	WARN_ON(!sk_unhashed(sk));
-	__sk_add_node(sk, &head->chain);
+	__sk_nulls_add_node_rcu(sk, &head->chain);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 	write_unlock(lock);
 
@@ -338,7 +368,7 @@ static inline u32 inet_sk_port_offset(const struct sock *sk)
 void __inet_hash_nolisten(struct sock *sk)
 {
 	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
-	struct hlist_head *list;
+	struct hlist_nulls_head *list;
 	rwlock_t *lock;
 	struct inet_ehash_bucket *head;
 
@@ -350,7 +380,7 @@ void __inet_hash_nolisten(struct sock *sk)
 	lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
 
 	write_lock(lock);
-	__sk_add_node(sk, list);
+	__sk_nulls_add_node_rcu(sk, list);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 	write_unlock(lock);
 }
@@ -400,13 +430,15 @@ void inet_unhash(struct sock *sk)
 		local_bh_disable();
 		inet_listen_wlock(hashinfo);
 		lock = &hashinfo->lhash_lock;
+		if (__sk_del_node_init(sk))
+			sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	} else {
 		lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
 		write_lock_bh(lock);
+		if (__sk_nulls_del_node_init_rcu(sk))
+			sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	}
 
-	if (__sk_del_node_init(sk))
-		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	write_unlock_bh(lock);
 out:
 	if (sk->sk_state == TCP_LISTEN)
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 1c5fd38f8824..60689951ecdb 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -23,12 +23,12 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw,
 	rwlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
 
 	write_lock(lock);
-	if (hlist_unhashed(&tw->tw_node)) {
+	if (hlist_nulls_unhashed(&tw->tw_node)) {
 		write_unlock(lock);
 		return;
 	}
-	__hlist_del(&tw->tw_node);
-	sk_node_init(&tw->tw_node);
+	hlist_nulls_del_rcu(&tw->tw_node);
+	sk_nulls_node_init(&tw->tw_node);
 	write_unlock(lock);
 
 	/* Disassociate with bind bucket. */
@@ -92,13 +92,17 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 
 	write_lock(lock);
 
-	/* Step 2: Remove SK from established hash. */
-	if (__sk_del_node_init(sk))
-		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-
-	/* Step 3: Hash TW into TIMEWAIT chain. */
-	inet_twsk_add_node(tw, &ehead->twchain);
+	/*
+	 * Step 2: Hash TW into TIMEWAIT chain.
+	 * Should be done before removing sk from established chain
+	 * because readers are lockless and search established first.
+	 */
 	atomic_inc(&tw->tw_refcnt);
+	inet_twsk_add_node_rcu(tw, &ehead->twchain);
+
+	/* Step 3: Remove SK from established hash. */
+	if (__sk_nulls_del_node_init_rcu(sk))
+		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 
 	write_unlock(lock);
 }
@@ -416,7 +420,7 @@ void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo,
 {
 	struct inet_timewait_sock *tw;
 	struct sock *sk;
-	struct hlist_node *node;
+	struct hlist_nulls_node *node;
 	int h;
 
 	local_bh_disable();
@@ -426,7 +430,7 @@ void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo,
 		rwlock_t *lock = inet_ehash_lockp(hashinfo, h);
 restart:
 		write_lock(lock);
-		sk_for_each(sk, node, &head->twchain) {
+		sk_nulls_for_each(sk, node, &head->twchain) {
 
 			tw = inet_twsk(sk);
 			if (!net_eq(twsk_net(tw), net) ||
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f60a5917e54d..044224a341eb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2707,8 +2707,8 @@ void __init tcp_init(void)
 					thash_entries ? 0 : 512 * 1024);
 	tcp_hashinfo.ehash_size = 1 << tcp_hashinfo.ehash_size;
 	for (i = 0; i < tcp_hashinfo.ehash_size; i++) {
-		INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].chain);
-		INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].twchain);
+		INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i);
+		INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].twchain, i);
 	}
 	if (inet_ehash_locks_alloc(&tcp_hashinfo))
 		panic("TCP: failed to alloc ehash_locks");
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d49233f409b5..b2e3ab2287ba 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1857,16 +1857,16 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock);
 #ifdef CONFIG_PROC_FS
 /* Proc filesystem TCP sock list dumping. */
 
-static inline struct inet_timewait_sock *tw_head(struct hlist_head *head)
+static inline struct inet_timewait_sock *tw_head(struct hlist_nulls_head *head)
 {
-	return hlist_empty(head) ? NULL :
+	return hlist_nulls_empty(head) ? NULL :
 		list_entry(head->first, struct inet_timewait_sock, tw_node);
 }
 
 static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw)
 {
-	return tw->tw_node.next ?
-		hlist_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
+	return !is_a_nulls(tw->tw_node.next) ?
+		hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
 }
 
 static void *listening_get_next(struct seq_file *seq, void *cur)
@@ -1954,8 +1954,8 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
 
 static inline int empty_bucket(struct tcp_iter_state *st)
 {
-	return hlist_empty(&tcp_hashinfo.ehash[st->bucket].chain) &&
-		hlist_empty(&tcp_hashinfo.ehash[st->bucket].twchain);
+	return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain) &&
+		hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain);
 }
 
 static void *established_get_first(struct seq_file *seq)
@@ -1966,7 +1966,7 @@ static void *established_get_first(struct seq_file *seq)
 
 	for (st->bucket = 0; st->bucket < tcp_hashinfo.ehash_size; ++st->bucket) {
 		struct sock *sk;
-		struct hlist_node *node;
+		struct hlist_nulls_node *node;
 		struct inet_timewait_sock *tw;
 		rwlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);
 
@@ -1975,7 +1975,7 @@ static void *established_get_first(struct seq_file *seq)
 			continue;
 
 		read_lock_bh(lock);
-		sk_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
+		sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
 			if (sk->sk_family != st->family ||
 			    !net_eq(sock_net(sk), net)) {
 				continue;
@@ -2004,7 +2004,7 @@ static void *established_get_next(struct seq_file *seq, void *cur)
 {
 	struct sock *sk = cur;
 	struct inet_timewait_sock *tw;
-	struct hlist_node *node;
+	struct hlist_nulls_node *node;
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 
@@ -2032,11 +2032,11 @@ get_tw:
 			return NULL;
 
 		read_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
-		sk = sk_head(&tcp_hashinfo.ehash[st->bucket].chain);
+		sk = sk_nulls_head(&tcp_hashinfo.ehash[st->bucket].chain);
 	} else
-		sk = sk_next(sk);
+		sk = sk_nulls_next(sk);
 
-	sk_for_each_from(sk, node) {
+	sk_nulls_for_each_from(sk, node) {
 		if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
 			goto found;
 	}
@@ -2375,6 +2375,7 @@ struct proto tcp_prot = {
 	.sysctl_rmem		= sysctl_tcp_rmem,
 	.max_header		= MAX_TCP_HEADER,
 	.obj_size		= sizeof(struct tcp_sock),
+	.slab_flags		= SLAB_DESTROY_BY_RCU,
 	.twsk_prot		= &tcp_timewait_sock_ops,
 	.rsk_prot		= &tcp_request_sock_ops,
 	.h.hashinfo		= &tcp_hashinfo,
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 1646a5658255..c1b4d401fd95 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -25,24 +25,28 @@
 void __inet6_hash(struct sock *sk)
 {
 	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
-	struct hlist_head *list;
 	rwlock_t *lock;
 
 	WARN_ON(!sk_unhashed(sk));
 
 	if (sk->sk_state == TCP_LISTEN) {
+		struct hlist_head *list;
+
 		list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
 		lock = &hashinfo->lhash_lock;
 		inet_listen_wlock(hashinfo);
+		__sk_add_node(sk, list);
 	} else {
 		unsigned int hash;
+		struct hlist_nulls_head *list;
+
 		sk->sk_hash = hash = inet6_sk_ehashfn(sk);
 		list = &inet_ehash_bucket(hashinfo, hash)->chain;
 		lock = inet_ehash_lockp(hashinfo, hash);
 		write_lock(lock);
+		__sk_nulls_add_node_rcu(sk, list);
 	}
 
-	__sk_add_node(sk, list);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 	write_unlock(lock);
 }
@@ -63,33 +67,53 @@ struct sock *__inet6_lookup_established(struct net *net,
 					   const int dif)
 {
 	struct sock *sk;
-	const struct hlist_node *node;
+	const struct hlist_nulls_node *node;
 	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
 	/* Optimize here for direct hit, only listening connections can
 	 * have wildcards anyways.
 	 */
 	unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
-	struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash);
-	rwlock_t *lock = inet_ehash_lockp(hashinfo, hash);
+	unsigned int slot = hash & (hashinfo->ehash_size - 1);
+	struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
 
-	prefetch(head->chain.first);
-	read_lock(lock);
-	sk_for_each(sk, node, &head->chain) {
+
+	rcu_read_lock();
+begin:
+	sk_nulls_for_each_rcu(sk, node, &head->chain) {
 		/* For IPV6 do the cheaper port and family tests first. */
-		if (INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif))
-			goto hit; /* You sunk my battleship! */
+		if (INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
+			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
+				goto begintw;
+			if (!INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
+				sock_put(sk);
+				goto begin;
+			}
+		goto out;
+		}
 	}
+	if (get_nulls_value(node) != slot)
+		goto begin;
+
+begintw:
 	/* Must check for a TIME_WAIT'er before going to listener hash. */
-	sk_for_each(sk, node, &head->twchain) {
-		if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif))
-			goto hit;
+	sk_nulls_for_each_rcu(sk, node, &head->twchain) {
+		if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
+			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
+				sk = NULL;
+				goto out;
+			}
+			if (!INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
+				sock_put(sk);
+				goto begintw;
+			}
+			goto out;
+		}
 	}
-	read_unlock(lock);
-	return NULL;
-
-hit:
-	sock_hold(sk);
-	read_unlock(lock);
+	if (get_nulls_value(node) != slot)
+		goto begintw;
+	sk = NULL;
+out:
+	rcu_read_unlock();
 	return sk;
 }
 EXPORT_SYMBOL(__inet6_lookup_established);
@@ -172,14 +196,14 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
 	rwlock_t *lock = inet_ehash_lockp(hinfo, hash);
 	struct sock *sk2;
-	const struct hlist_node *node;
+	const struct hlist_nulls_node *node;
 	struct inet_timewait_sock *tw;
 
 	prefetch(head->chain.first);
 	write_lock(lock);
 
 	/* Check TIME-WAIT sockets first. */
-	sk_for_each(sk2, node, &head->twchain) {
+	sk_nulls_for_each(sk2, node, &head->twchain) {
 		tw = inet_twsk(sk2);
 
 		if (INET6_TW_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) {
@@ -192,7 +216,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 	tw = NULL;
 
 	/* And established part... */
-	sk_for_each(sk2, node, &head->chain) {
+	sk_nulls_for_each(sk2, node, &head->chain) {
 		if (INET6_MATCH(sk2, net, hash, saddr, daddr, ports, dif))
 			goto not_unique;
 	}
@@ -203,7 +227,7 @@ unique:
 	inet->num = lport;
 	inet->sport = htons(lport);
 	WARN_ON(!sk_unhashed(sk));
-	__sk_add_node(sk, &head->chain);
+	__sk_nulls_add_node_rcu(sk, &head->chain);
 	sk->sk_hash = hash;
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 	write_unlock(lock);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 984276463a8d..b35787056313 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2043,6 +2043,7 @@ struct proto tcpv6_prot = {
 	.sysctl_rmem		= sysctl_tcp_rmem,
 	.max_header		= MAX_TCP_HEADER,
 	.obj_size		= sizeof(struct tcp6_sock),
+	.slab_flags		= SLAB_DESTROY_BY_RCU,
 	.twsk_prot		= &tcp6_timewait_sock_ops,
 	.rsk_prot		= &tcp6_request_sock_ops,
 	.h.hashinfo		= &tcp_hashinfo,
-- 
cgit v1.2.3-59-g8ed1b


From 1748376b6626acf59c24e9592ac67b3fe2a0e026 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <dada1@cosmosbay.com>
Date: Tue, 25 Nov 2008 21:16:35 -0800
Subject: net: Use a percpu_counter for sockets_allocated

Instead of using one atomic_t per protocol, use a percpu_counter
for "sockets_allocated", to reduce cache line contention on
heavy duty network servers.

Note : We revert commit (248969ae31e1b3276fc4399d67ce29a5d81e6fd9
net: af_unix can make unix_nr_socks visbile in /proc),
since it is not anymore used after sock_prot_inuse_add() addition

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h |  1 +
 include/net/sock.h      |  2 +-
 include/net/tcp.h       |  2 +-
 net/core/sock.c         | 10 +++++++---
 net/ipv4/proc.c         |  3 ++-
 net/ipv4/tcp.c          |  8 ++++++--
 net/ipv4/tcp_ipv4.c     |  4 ++--
 net/ipv6/tcp_ipv6.c     |  2 +-
 net/sctp/protocol.c     |  6 +++++-
 net/sctp/socket.c       |  6 +++---
 net/unix/af_unix.c      |  1 -
 11 files changed, 29 insertions(+), 16 deletions(-)

(limited to 'net/ipv4/tcp.c')

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 23797506f593..bbb7742195b0 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -138,6 +138,7 @@ void sctp_write_space(struct sock *sk);
 unsigned int sctp_poll(struct file *file, struct socket *sock,
 		poll_table *wait);
 void sctp_sock_rfree(struct sk_buff *skb);
+extern struct percpu_counter sctp_sockets_allocated;
 
 /*
  * sctp/primitive.c
diff --git a/include/net/sock.h b/include/net/sock.h
index 00cd486d362f..a2a3890959c4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -649,7 +649,7 @@ struct proto {
 	/* Memory pressure */
 	void			(*enter_memory_pressure)(struct sock *sk);
 	atomic_t		*memory_allocated;	/* Current allocated memory. */
-	atomic_t		*sockets_allocated;	/* Current number of sockets. */
+	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
 	/*
 	 * Pressure flag: try to collapse.
 	 * Technical note: it is used by multiple contexts non atomically.
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e8ae90a8c35e..cbca3b8a133d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -238,7 +238,7 @@ extern int sysctl_tcp_slow_start_after_idle;
 extern int sysctl_tcp_max_ssthresh;
 
 extern atomic_t tcp_memory_allocated;
-extern atomic_t tcp_sockets_allocated;
+extern struct percpu_counter tcp_sockets_allocated;
 extern int tcp_memory_pressure;
 
 /*
diff --git a/net/core/sock.c b/net/core/sock.c
index a4e840e5a053..7a081b647bf9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1071,7 +1071,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 		newsk->sk_sleep	 = NULL;
 
 		if (newsk->sk_prot->sockets_allocated)
-			atomic_inc(newsk->sk_prot->sockets_allocated);
+			percpu_counter_inc(newsk->sk_prot->sockets_allocated);
 	}
 out:
 	return newsk;
@@ -1463,8 +1463,12 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
 	}
 
 	if (prot->memory_pressure) {
-		if (!*prot->memory_pressure ||
-		    prot->sysctl_mem[2] > atomic_read(prot->sockets_allocated) *
+		int alloc;
+
+		if (!*prot->memory_pressure)
+			return 1;
+		alloc = percpu_counter_read_positive(prot->sockets_allocated);
+		if (prot->sysctl_mem[2] > alloc *
 		    sk_mem_pages(sk->sk_wmem_queued +
 				 atomic_read(&sk->sk_rmem_alloc) +
 				 sk->sk_forward_alloc))
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 731789bb499f..4944b47ad628 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -55,7 +55,8 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 	seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n",
 		   sock_prot_inuse_get(net, &tcp_prot),
 		   atomic_read(&tcp_orphan_count),
-		   tcp_death_row.tw_count, atomic_read(&tcp_sockets_allocated),
+		   tcp_death_row.tw_count,
+		   (int)percpu_counter_sum_positive(&tcp_sockets_allocated),
 		   atomic_read(&tcp_memory_allocated));
 	seq_printf(seq, "UDP: inuse %d mem %d\n",
 		   sock_prot_inuse_get(net, &udp_prot),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 044224a341eb..e6fade9ebf62 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -290,9 +290,12 @@ EXPORT_SYMBOL(sysctl_tcp_rmem);
 EXPORT_SYMBOL(sysctl_tcp_wmem);
 
 atomic_t tcp_memory_allocated;	/* Current allocated memory. */
-atomic_t tcp_sockets_allocated;	/* Current number of TCP sockets. */
-
 EXPORT_SYMBOL(tcp_memory_allocated);
+
+/*
+ * Current number of TCP sockets.
+ */
+struct percpu_counter tcp_sockets_allocated;
 EXPORT_SYMBOL(tcp_sockets_allocated);
 
 /*
@@ -2685,6 +2688,7 @@ void __init tcp_init(void)
 
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
 
+	percpu_counter_init(&tcp_sockets_allocated, 0);
 	tcp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("tcp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cab2458f86fd..26b9030747cc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1797,7 +1797,7 @@ static int tcp_v4_init_sock(struct sock *sk)
 	sk->sk_sndbuf = sysctl_tcp_wmem[1];
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
-	atomic_inc(&tcp_sockets_allocated);
+	percpu_counter_inc(&tcp_sockets_allocated);
 
 	return 0;
 }
@@ -1845,7 +1845,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 		sk->sk_sndmsg_page = NULL;
 	}
 
-	atomic_dec(&tcp_sockets_allocated);
+	percpu_counter_dec(&tcp_sockets_allocated);
 }
 
 EXPORT_SYMBOL(tcp_v4_destroy_sock);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f259c9671f3e..8702b06cb60a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1830,7 +1830,7 @@ static int tcp_v6_init_sock(struct sock *sk)
 	sk->sk_sndbuf = sysctl_tcp_wmem[1];
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
-	atomic_inc(&tcp_sockets_allocated);
+	percpu_counter_inc(&tcp_sockets_allocated);
 
 	return 0;
 }
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index a8ca743241ee..d5ea232c9126 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -102,6 +102,8 @@ struct sock *sctp_get_ctl_sock(void)
 /* Set up the proc fs entry for the SCTP protocol. */
 static __init int sctp_proc_init(void)
 {
+	if (percpu_counter_init(&sctp_sockets_allocated, 0))
+		goto out_nomem;
 #ifdef CONFIG_PROC_FS
 	if (!proc_net_sctp) {
 		struct proc_dir_entry *ent;
@@ -110,7 +112,7 @@ static __init int sctp_proc_init(void)
 			ent->owner = THIS_MODULE;
 			proc_net_sctp = ent;
 		} else
-			goto out_nomem;
+			goto out_free_percpu;
 	}
 
 	if (sctp_snmp_proc_init())
@@ -135,6 +137,8 @@ out_snmp_proc_init:
 		proc_net_sctp = NULL;
 		remove_proc_entry("sctp", init_net.proc_net);
 	}
+out_free_percpu:
+	percpu_counter_destroy(&sctp_sockets_allocated);
 out_nomem:
 	return -ENOMEM;
 #else
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ba81fe3ccab8..a2de585888d0 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -114,7 +114,7 @@ extern int sysctl_sctp_wmem[3];
 
 static int sctp_memory_pressure;
 static atomic_t sctp_memory_allocated;
-static atomic_t sctp_sockets_allocated;
+struct percpu_counter sctp_sockets_allocated;
 
 static void sctp_enter_memory_pressure(struct sock *sk)
 {
@@ -3613,7 +3613,7 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
 	sp->hmac = NULL;
 
 	SCTP_DBG_OBJCNT_INC(sock);
-	atomic_inc(&sctp_sockets_allocated);
+	percpu_counter_inc(&sctp_sockets_allocated);
 
 	local_bh_disable();
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -3632,7 +3632,7 @@ SCTP_STATIC void sctp_destroy_sock(struct sock *sk)
 	/* Release our hold on the endpoint. */
 	ep = sctp_sk(sk)->ep;
 	sctp_endpoint_free(ep);
-	atomic_dec(&sctp_sockets_allocated);
+	percpu_counter_dec(&sctp_sockets_allocated);
 	local_bh_disable();
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	local_bh_enable();
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 3a35a6e8bf91..5aaf23e43f1d 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -571,7 +571,6 @@ static const struct proto_ops unix_seqpacket_ops = {
 static struct proto unix_proto = {
 	.name			= "UNIX",
 	.owner			= THIS_MODULE,
-	.sockets_allocated	= &unix_nr_socks,
 	.obj_size		= sizeof(struct unix_sock),
 };
 
-- 
cgit v1.2.3-59-g8ed1b


From dd24c00191d5e4a1ae896aafe33c6b8095ab4bd1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <dada1@cosmosbay.com>
Date: Tue, 25 Nov 2008 21:17:14 -0800
Subject: net: Use a percpu_counter for orphan_count

Instead of using one atomic_t per protocol, use a percpu_counter
for "orphan_count", to reduce cache line contention on
heavy duty network servers.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h              |  2 +-
 include/net/tcp.h               |  2 +-
 net/dccp/dccp.h                 |  2 +-
 net/dccp/proto.c                | 16 ++++++++++------
 net/ipv4/inet_connection_sock.c |  4 ++--
 net/ipv4/proc.c                 |  2 +-
 net/ipv4/tcp.c                  | 12 +++++++-----
 net/ipv4/tcp_timer.c            |  2 +-
 8 files changed, 24 insertions(+), 18 deletions(-)

(limited to 'net/ipv4/tcp.c')

diff --git a/include/net/sock.h b/include/net/sock.h
index a2a3890959c4..5a3a151bd730 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -666,7 +666,7 @@ struct proto {
 	unsigned int		obj_size;
 	int			slab_flags;
 
-	atomic_t		*orphan_count;
+	struct percpu_counter	*orphan_count;
 
 	struct request_sock_ops	*rsk_prot;
 	struct timewait_sock_ops *twsk_prot;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index cbca3b8a133d..de1e91d959b8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -46,7 +46,7 @@
 
 extern struct inet_hashinfo tcp_hashinfo;
 
-extern atomic_t tcp_orphan_count;
+extern struct percpu_counter tcp_orphan_count;
 extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 
 #define MAX_TCP_HEADER	(128 + MAX_HEADER)
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 031ce350d3c1..33a1127270c1 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -49,7 +49,7 @@ extern int dccp_debug;
 
 extern struct inet_hashinfo dccp_hashinfo;
 
-extern atomic_t dccp_orphan_count;
+extern struct percpu_counter dccp_orphan_count;
 
 extern void dccp_time_wait(struct sock *sk, int state, int timeo);
 
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index ea85c423cdbd..db225f93cd5a 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -40,8 +40,7 @@ DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly;
 
 EXPORT_SYMBOL_GPL(dccp_statistics);
 
-atomic_t dccp_orphan_count = ATOMIC_INIT(0);
-
+struct percpu_counter dccp_orphan_count;
 EXPORT_SYMBOL_GPL(dccp_orphan_count);
 
 struct inet_hashinfo dccp_hashinfo;
@@ -1000,7 +999,7 @@ adjudge_to_death:
 	state = sk->sk_state;
 	sock_hold(sk);
 	sock_orphan(sk);
-	atomic_inc(sk->sk_prot->orphan_count);
+	percpu_counter_inc(sk->sk_prot->orphan_count);
 
 	/*
 	 * It is the last release_sock in its life. It will remove backlog.
@@ -1064,18 +1063,21 @@ static int __init dccp_init(void)
 {
 	unsigned long goal;
 	int ehash_order, bhash_order, i;
-	int rc = -ENOBUFS;
+	int rc;
 
 	BUILD_BUG_ON(sizeof(struct dccp_skb_cb) >
 		     FIELD_SIZEOF(struct sk_buff, cb));
-
+	rc = percpu_counter_init(&dccp_orphan_count, 0);
+	if (rc)
+		goto out;
+	rc = -ENOBUFS;
 	inet_hashinfo_init(&dccp_hashinfo);
 	dccp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("dccp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
 				  SLAB_HWCACHE_ALIGN, NULL);
 	if (!dccp_hashinfo.bind_bucket_cachep)
-		goto out;
+		goto out_free_percpu;
 
 	/*
 	 * Size and allocate the main established and bind bucket
@@ -1168,6 +1170,8 @@ out_free_dccp_ehash:
 out_free_bind_bucket_cachep:
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
 	dccp_hashinfo.bind_bucket_cachep = NULL;
+out_free_percpu:
+	percpu_counter_destroy(&dccp_orphan_count);
 	goto out;
 }
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 05af807ca9b9..1ccdbba528be 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -561,7 +561,7 @@ void inet_csk_destroy_sock(struct sock *sk)
 
 	sk_refcnt_debug_release(sk);
 
-	atomic_dec(sk->sk_prot->orphan_count);
+	percpu_counter_dec(sk->sk_prot->orphan_count);
 	sock_put(sk);
 }
 
@@ -641,7 +641,7 @@ void inet_csk_listen_stop(struct sock *sk)
 
 		sock_orphan(child);
 
-		atomic_inc(sk->sk_prot->orphan_count);
+		percpu_counter_inc(sk->sk_prot->orphan_count);
 
 		inet_csk_destroy_sock(child);
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 4944b47ad628..614958b7c276 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -54,7 +54,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 	socket_seq_show(seq);
 	seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n",
 		   sock_prot_inuse_get(net, &tcp_prot),
-		   atomic_read(&tcp_orphan_count),
+		   (int)percpu_counter_sum_positive(&tcp_orphan_count),
 		   tcp_death_row.tw_count,
 		   (int)percpu_counter_sum_positive(&tcp_sockets_allocated),
 		   atomic_read(&tcp_memory_allocated));
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e6fade9ebf62..019243408623 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -277,8 +277,7 @@
 
 int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 
-atomic_t tcp_orphan_count = ATOMIC_INIT(0);
-
+struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
 int sysctl_tcp_mem[3] __read_mostly;
@@ -1837,7 +1836,7 @@ adjudge_to_death:
 	state = sk->sk_state;
 	sock_hold(sk);
 	sock_orphan(sk);
-	atomic_inc(sk->sk_prot->orphan_count);
+	percpu_counter_inc(sk->sk_prot->orphan_count);
 
 	/* It is the last release_sock in its life. It will remove backlog. */
 	release_sock(sk);
@@ -1888,9 +1887,11 @@ adjudge_to_death:
 		}
 	}
 	if (sk->sk_state != TCP_CLOSE) {
+		int orphan_count = percpu_counter_read_positive(
+						sk->sk_prot->orphan_count);
+
 		sk_mem_reclaim(sk);
-		if (tcp_too_many_orphans(sk,
-				atomic_read(sk->sk_prot->orphan_count))) {
+		if (tcp_too_many_orphans(sk, orphan_count)) {
 			if (net_ratelimit())
 				printk(KERN_INFO "TCP: too many of orphaned "
 				       "sockets\n");
@@ -2689,6 +2690,7 @@ void __init tcp_init(void)
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
 
 	percpu_counter_init(&tcp_sockets_allocated, 0);
+	percpu_counter_init(&tcp_orphan_count, 0);
 	tcp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("tcp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 3df339e3e363..cc4e6d27dedc 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -65,7 +65,7 @@ static void tcp_write_err(struct sock *sk)
 static int tcp_out_of_resources(struct sock *sk, int do_reset)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	int orphans = atomic_read(&tcp_orphan_count);
+	int orphans = percpu_counter_read_positive(&tcp_orphan_count);
 
 	/* If peer does not open window for long time, or did not transmit
 	 * anything for long time, penalize it. */
-- 
cgit v1.2.3-59-g8ed1b


From bf296b125b21b8d558ceb6ec30bb4eba2730cd6b Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 15 Dec 2008 23:43:36 -0800
Subject: tcp: Add GRO support

This patch adds the TCP-specific portion of GRO.  The criterion for
merging is extremely strict (the TCP header must match exactly apart
from the checksum) so as to allow refragmentation.  Otherwise this
is pretty much identical to LRO, except that we support the merging
of ECN packets.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h   |   6 ++++
 net/ipv4/af_inet.c  |   2 ++
 net/ipv4/tcp.c      | 100 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/tcp_ipv4.c |  35 ++++++++++++++++++
 4 files changed, 143 insertions(+)

(limited to 'net/ipv4/tcp.c')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index de1e91d959b8..218235de8963 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1358,6 +1358,12 @@ extern void tcp_v4_destroy_sock(struct sock *sk);
 
 extern int tcp_v4_gso_send_check(struct sk_buff *skb);
 extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features);
+extern struct sk_buff **tcp_gro_receive(struct sk_buff **head,
+					struct sk_buff *skb);
+extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb);
+extern int tcp_gro_complete(struct sk_buff *skb);
+extern int tcp4_gro_complete(struct sk_buff *skb);
 
 #ifdef CONFIG_PROC_FS
 extern int  tcp4_proc_init(void);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index a85595307fa7..664ff0ee1c83 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1410,6 +1410,8 @@ static struct net_protocol tcp_protocol = {
 	.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,
 };
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 019243408623..1f3d52946b3b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2465,6 +2465,106 @@ out:
 }
 EXPORT_SYMBOL(tcp_tso_segment);
 
+struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+	struct sk_buff **pp = NULL;
+	struct sk_buff *p;
+	struct tcphdr *th;
+	struct tcphdr *th2;
+	unsigned int thlen;
+	unsigned int flags;
+	unsigned int total;
+	unsigned int mss = 1;
+	int flush = 1;
+
+	if (!pskb_may_pull(skb, sizeof(*th)))
+		goto out;
+
+	th = tcp_hdr(skb);
+	thlen = th->doff * 4;
+	if (thlen < sizeof(*th))
+		goto out;
+
+	if (!pskb_may_pull(skb, thlen))
+		goto out;
+
+	th = tcp_hdr(skb);
+	__skb_pull(skb, thlen);
+
+	flags = tcp_flag_word(th);
+
+	for (; (p = *head); head = &p->next) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		th2 = tcp_hdr(p);
+
+		if (th->source != th2->source || th->dest != th2->dest) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+
+		goto found;
+	}
+
+	goto out_check_final;
+
+found:
+	flush = NAPI_GRO_CB(p)->flush;
+	flush |= flags & TCP_FLAG_CWR;
+	flush |= (flags ^ tcp_flag_word(th2)) &
+		  ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH);
+	flush |= th->ack_seq != th2->ack_seq || th->window != th2->window;
+	flush |= memcmp(th + 1, th2 + 1, thlen - sizeof(*th));
+
+	total = p->len;
+	mss = total;
+	if (skb_shinfo(p)->frag_list)
+		mss = skb_shinfo(p)->frag_list->len;
+
+	flush |= skb->len > mss || skb->len <= 0;
+	flush |= ntohl(th2->seq) + total != ntohl(th->seq);
+
+	if (flush || skb_gro_receive(head, skb)) {
+		mss = 1;
+		goto out_check_final;
+	}
+
+	p = *head;
+	th2 = tcp_hdr(p);
+	tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
+
+out_check_final:
+	flush = skb->len < mss;
+	flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST |
+			  TCP_FLAG_SYN | TCP_FLAG_FIN);
+
+	if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
+		pp = head;
+
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+
+	return pp;
+}
+
+int tcp_gro_complete(struct sk_buff *skb)
+{
+	struct tcphdr *th = tcp_hdr(skb);
+
+	skb->csum_start = skb_transport_header(skb) - skb->head;
+	skb->csum_offset = offsetof(struct tcphdr, check);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+
+	skb_shinfo(skb)->gso_size = skb_shinfo(skb)->frag_list->len;
+	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+	if (th->cwr)
+		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+
+	return 0;
+}
+
 #ifdef CONFIG_TCP_MD5SIG
 static unsigned long tcp_md5sig_users;
 static struct tcp_md5sig_pool **tcp_md5sig_pool;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 26b9030747cc..10172487921b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2346,6 +2346,41 @@ void tcp4_proc_exit(void)
 }
 #endif /* CONFIG_PROC_FS */
 
+struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+	struct iphdr *iph = ip_hdr(skb);
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		if (!tcp_v4_check(skb->len, iph->saddr, iph->daddr,
+				  skb->csum)) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			break;
+		}
+
+		/* fall through */
+	case CHECKSUM_NONE:
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	return tcp_gro_receive(head, skb);
+}
+EXPORT_SYMBOL(tcp4_gro_receive);
+
+int tcp4_gro_complete(struct sk_buff *skb)
+{
+	struct iphdr *iph = ip_hdr(skb);
+	struct tcphdr *th = tcp_hdr(skb);
+
+	th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
+				  iph->saddr, iph->daddr, 0);
+	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+
+	return tcp_gro_complete(skb);
+}
+EXPORT_SYMBOL(tcp4_gro_complete);
+
 struct proto tcp_prot = {
 	.name			= "TCP",
 	.owner			= THIS_MODULE,
-- 
cgit v1.2.3-59-g8ed1b