Merge branch 'master' of git://1984.lsi.us.es/net-next-2.6

Conflicts:
	net/ipv4/route.c

Signed-off-by: Patrick McHardy <kaber@trash.net>

26 files changed, 1890 insertions, 1119 deletions

diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 5faec4fd819..e69d537362c 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -173,9 +173,11 @@ next_hook:
 			     outdev, &elem, okfn, hook_thresh);
 	if (verdict == NF_ACCEPT || verdict == NF_STOP) {
 		ret = 1;
-	} else if (verdict == NF_DROP) {
+	} else if ((verdict & NF_VERDICT_MASK) == NF_DROP) {
 		kfree_skb(skb);
-		ret = -EPERM;
+		ret = -(verdict >> NF_VERDICT_BITS);
+		if (ret == 0)
+			ret = -EPERM;
 	} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
 		if (!nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
 			      verdict >> NF_VERDICT_BITS))
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index a22dac22705..70bd1d0774c 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -4,6 +4,7 @@
 menuconfig IP_VS
 	tristate "IP virtual server support"
 	depends on NET && INET && NETFILTER
+	depends on (NF_CONNTRACK || NF_CONNTRACK=n)
 	---help---
 	  IP Virtual Server support will let you build a high-performance
 	  virtual server based on cluster of two or more real servers. This
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index a475edee091..5c48ffb60c2 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -43,11 +43,6 @@ EXPORT_SYMBOL(register_ip_vs_app);
 EXPORT_SYMBOL(unregister_ip_vs_app);
 EXPORT_SYMBOL(register_ip_vs_app_inc);
 
-/* ipvs application list head */
-static LIST_HEAD(ip_vs_app_list);
-static DEFINE_MUTEX(__ip_vs_app_mutex);
-
-
 /*
  *	Get an ip_vs_app object
  */
@@ -67,7 +62,8 @@ static inline void ip_vs_app_put(struct ip_vs_app *app)
  *	Allocate/initialize app incarnation and register it in proto apps.
  */
 static int
-ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port)
+ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto,
+		  __u16 port)
 {
 	struct ip_vs_protocol *pp;
 	struct ip_vs_app *inc;
@@ -98,7 +94,7 @@ ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port)
 		}
 	}
 
-	ret = pp->register_app(inc);
+	ret = pp->register_app(net, inc);
 	if (ret)
 		goto out;
 
@@ -119,7 +115,7 @@ ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port)
  *	Release app incarnation
  */
 static void
-ip_vs_app_inc_release(struct ip_vs_app *inc)
+ip_vs_app_inc_release(struct net *net, struct ip_vs_app *inc)
 {
 	struct ip_vs_protocol *pp;
 
@@ -127,7 +123,7 @@ ip_vs_app_inc_release(struct ip_vs_app *inc)
 		return;
 
 	if (pp->unregister_app)
-		pp->unregister_app(inc);
+		pp->unregister_app(net, inc);
 
 	IP_VS_DBG(9, "%s App %s:%u unregistered\n",
 		  pp->name, inc->name, ntohs(inc->port));
@@ -168,15 +164,17 @@ void ip_vs_app_inc_put(struct ip_vs_app *inc)
  *	Register an application incarnation in protocol applications
  */
 int
-register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port)
+register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
+		       __u16 port)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	int result;
 
-	mutex_lock(&__ip_vs_app_mutex);
+	mutex_lock(&ipvs->app_mutex);
 
-	result = ip_vs_app_inc_new(app, proto, port);
+	result = ip_vs_app_inc_new(net, app, proto, port);
 
-	mutex_unlock(&__ip_vs_app_mutex);
+	mutex_unlock(&ipvs->app_mutex);
 
 	return result;
 }
@@ -185,16 +183,17 @@ register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port)
 /*
  *	ip_vs_app registration routine
  */
-int register_ip_vs_app(struct ip_vs_app *app)
+int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	/* increase the module use count */
 	ip_vs_use_count_inc();
 
-	mutex_lock(&__ip_vs_app_mutex);
+	mutex_lock(&ipvs->app_mutex);
 
-	list_add(&app->a_list, &ip_vs_app_list);
+	list_add(&app->a_list, &ipvs->app_list);
 
-	mutex_unlock(&__ip_vs_app_mutex);
+	mutex_unlock(&ipvs->app_mutex);
 
 	return 0;
 }
@@ -204,19 +203,20 @@ int register_ip_vs_app(struct ip_vs_app *app)
  *	ip_vs_app unregistration routine
  *	We are sure there are no app incarnations attached to services
  */
-void unregister_ip_vs_app(struct ip_vs_app *app)
+void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_app *inc, *nxt;
 
-	mutex_lock(&__ip_vs_app_mutex);
+	mutex_lock(&ipvs->app_mutex);
 
 	list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) {
-		ip_vs_app_inc_release(inc);
+		ip_vs_app_inc_release(net, inc);
 	}
 
 	list_del(&app->a_list);
 
-	mutex_unlock(&__ip_vs_app_mutex);
+	mutex_unlock(&ipvs->app_mutex);
 
 	/* decrease the module use count */
 	ip_vs_use_count_dec();
@@ -226,7 +226,8 @@ void unregister_ip_vs_app(struct ip_vs_app *app)
 /*
  *	Bind ip_vs_conn to its ip_vs_app (called by cp constructor)
  */
-int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp)
+int ip_vs_bind_app(struct ip_vs_conn *cp,
+		   struct ip_vs_protocol *pp)
 {
 	return pp->app_conn_bind(cp);
 }
@@ -481,11 +482,11 @@ int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb)
  *	/proc/net/ip_vs_app entry function
  */
 
-static struct ip_vs_app *ip_vs_app_idx(loff_t pos)
+static struct ip_vs_app *ip_vs_app_idx(struct netns_ipvs *ipvs, loff_t pos)
 {
 	struct ip_vs_app *app, *inc;
 
-	list_for_each_entry(app, &ip_vs_app_list, a_list) {
+	list_for_each_entry(app, &ipvs->app_list, a_list) {
 		list_for_each_entry(inc, &app->incs_list, a_list) {
 			if (pos-- == 0)
 				return inc;
@@ -497,19 +498,24 @@ static struct ip_vs_app *ip_vs_app_idx(loff_t pos)
 
 static void *ip_vs_app_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	mutex_lock(&__ip_vs_app_mutex);
+	struct net *net = seq_file_net(seq);
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	return *pos ? ip_vs_app_idx(*pos - 1) : SEQ_START_TOKEN;
+	mutex_lock(&ipvs->app_mutex);
+
+	return *pos ? ip_vs_app_idx(ipvs, *pos - 1) : SEQ_START_TOKEN;
 }
 
 static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct ip_vs_app *inc, *app;
 	struct list_head *e;
+	struct net *net = seq_file_net(seq);
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	++*pos;
 	if (v == SEQ_START_TOKEN)
-		return ip_vs_app_idx(0);
+		return ip_vs_app_idx(ipvs, 0);
 
 	inc = v;
 	app = inc->app;
@@ -518,7 +524,7 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		return list_entry(e, struct ip_vs_app, a_list);
 
 	/* go on to next application */
-	for (e = app->a_list.next; e != &ip_vs_app_list; e = e->next) {
+	for (e = app->a_list.next; e != &ipvs->app_list; e = e->next) {
 		app = list_entry(e, struct ip_vs_app, a_list);
 		list_for_each_entry(inc, &app->incs_list, a_list) {
 			return inc;
@@ -529,7 +535,9 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 static void ip_vs_app_seq_stop(struct seq_file *seq, void *v)
 {
-	mutex_unlock(&__ip_vs_app_mutex);
+	struct netns_ipvs *ipvs = net_ipvs(seq_file_net(seq));
+
+	mutex_unlock(&ipvs->app_mutex);
 }
 
 static int ip_vs_app_seq_show(struct seq_file *seq, void *v)
@@ -557,7 +565,8 @@ static const struct seq_operations ip_vs_app_seq_ops = {
 
 static int ip_vs_app_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &ip_vs_app_seq_ops);
+	return seq_open_net(inode, file, &ip_vs_app_seq_ops,
+			    sizeof(struct seq_net_private));
 }
 
 static const struct file_operations ip_vs_app_fops = {
@@ -569,15 +578,36 @@ static const struct file_operations ip_vs_app_fops = {
 };
 #endif
 
-int __init ip_vs_app_init(void)
+static int __net_init __ip_vs_app_init(struct net *net)
 {
-	/* we will replace it with proc_net_ipvs_create() soon */
-	proc_net_fops_create(&init_net, "ip_vs_app", 0, &ip_vs_app_fops);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	INIT_LIST_HEAD(&ipvs->app_list);
+	__mutex_init(&ipvs->app_mutex, "ipvs->app_mutex", &ipvs->app_key);
+	proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops);
 	return 0;
 }
 
+static void __net_exit __ip_vs_app_cleanup(struct net *net)
+{
+	proc_net_remove(net, "ip_vs_app");
+}
+
+static struct pernet_operations ip_vs_app_ops = {
+	.init = __ip_vs_app_init,
+	.exit = __ip_vs_app_cleanup,
+};
+
+int __init ip_vs_app_init(void)
+{
+	int rv;
+
+	rv = register_pernet_subsys(&ip_vs_app_ops);
+	return rv;
+}
+
 
 void ip_vs_app_cleanup(void)
 {
-	proc_net_remove(&init_net, "ip_vs_app");
+	unregister_pernet_subsys(&ip_vs_app_ops);
 }
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 66e4662925d..83233fe24a0 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -64,9 +64,6 @@ static struct list_head *ip_vs_conn_tab __read_mostly;
 /*  SLAB cache for IPVS connections */
 static struct kmem_cache *ip_vs_conn_cachep __read_mostly;
 
-/*  counter for current IPVS connections */
-static atomic_t ip_vs_conn_count = ATOMIC_INIT(0);
-
 /*  counter for no client port connections */
 static atomic_t ip_vs_conn_no_cport_cnt = ATOMIC_INIT(0);
 
@@ -76,7 +73,7 @@ static unsigned int ip_vs_conn_rnd __read_mostly;
 /*
  *  Fine locking granularity for big connection hash table
  */
-#define CT_LOCKARRAY_BITS  4
+#define CT_LOCKARRAY_BITS  5
 #define CT_LOCKARRAY_SIZE  (1<<CT_LOCKARRAY_BITS)
 #define CT_LOCKARRAY_MASK  (CT_LOCKARRAY_SIZE-1)
 
@@ -133,19 +130,19 @@ static inline void ct_write_unlock_bh(unsigned key)
 /*
  *	Returns hash value for IPVS connection entry
  */
-static unsigned int ip_vs_conn_hashkey(int af, unsigned proto,
+static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned proto,
 				       const union nf_inet_addr *addr,
 				       __be16 port)
 {
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
-		return jhash_3words(jhash(addr, 16, ip_vs_conn_rnd),
-				    (__force u32)port, proto, ip_vs_conn_rnd)
-			& ip_vs_conn_tab_mask;
+		return (jhash_3words(jhash(addr, 16, ip_vs_conn_rnd),
+				    (__force u32)port, proto, ip_vs_conn_rnd) ^
+			((size_t)net>>8)) & ip_vs_conn_tab_mask;
 #endif
-	return jhash_3words((__force u32)addr->ip, (__force u32)port, proto,
-			    ip_vs_conn_rnd)
-		& ip_vs_conn_tab_mask;
+	return (jhash_3words((__force u32)addr->ip, (__force u32)port, proto,
+			    ip_vs_conn_rnd) ^
+		((size_t)net>>8)) & ip_vs_conn_tab_mask;
 }
 
 static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p,
@@ -166,15 +163,15 @@ static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p,
 		port = p->vport;
 	}
 
-	return ip_vs_conn_hashkey(p->af, p->protocol, addr, port);
+	return ip_vs_conn_hashkey(p->net, p->af, p->protocol, addr, port);
 }
 
 static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
 {
 	struct ip_vs_conn_param p;
 
-	ip_vs_conn_fill_param(cp->af, cp->protocol, &cp->caddr, cp->cport,
-			      NULL, 0, &p);
+	ip_vs_conn_fill_param(ip_vs_conn_net(cp), cp->af, cp->protocol,
+			      &cp->caddr, cp->cport, NULL, 0, &p);
 
 	if (cp->pe) {
 		p.pe = cp->pe;
@@ -186,7 +183,7 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
 }
 
 /*
- *	Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port.
+ *	Hashes ip_vs_conn in ip_vs_conn_tab by netns,proto,addr,port.
  *	returns bool success.
  */
 static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
@@ -269,11 +266,12 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
 		if (cp->af == p->af &&
+		    p->cport == cp->cport && p->vport == cp->vport &&
 		    ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) &&
 		    ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) &&
-		    p->cport == cp->cport && p->vport == cp->vport &&
 		    ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) &&
-		    p->protocol == cp->protocol) {
+		    p->protocol == cp->protocol &&
+		    ip_vs_conn_net_eq(cp, p->net)) {
 			/* HIT */
 			atomic_inc(&cp->refcnt);
 			ct_read_unlock(hash);
@@ -313,23 +311,23 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
 			    struct ip_vs_conn_param *p)
 {
 	__be16 _ports[2], *pptr;
+	struct net *net = skb_net(skb);
 
 	pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
 	if (pptr == NULL)
 		return 1;
 
 	if (likely(!inverse))
-		ip_vs_conn_fill_param(af, iph->protocol, &iph->saddr, pptr[0],
-				      &iph->daddr, pptr[1], p);
+		ip_vs_conn_fill_param(net, af, iph->protocol, &iph->saddr,
+				      pptr[0], &iph->daddr, pptr[1], p);
 	else
-		ip_vs_conn_fill_param(af, iph->protocol, &iph->daddr, pptr[1],
-				      &iph->saddr, pptr[0], p);
+		ip_vs_conn_fill_param(net, af, iph->protocol, &iph->daddr,
+				      pptr[1], &iph->saddr, pptr[0], p);
 	return 0;
 }
 
 struct ip_vs_conn *
 ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
-			struct ip_vs_protocol *pp,
 			const struct ip_vs_iphdr *iph,
 			unsigned int proto_off, int inverse)
 {
@@ -353,6 +351,8 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
 	ct_read_lock(hash);
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+		if (!ip_vs_conn_net_eq(cp, p->net))
+			continue;
 		if (p->pe_data && p->pe->ct_match) {
 			if (p->pe == cp->pe && p->pe->ct_match(p, cp))
 				goto out;
@@ -404,10 +404,11 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
 		if (cp->af == p->af &&
+		    p->vport == cp->cport && p->cport == cp->dport &&
 		    ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) &&
 		    ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) &&
-		    p->vport == cp->cport && p->cport == cp->dport &&
-		    p->protocol == cp->protocol) {
+		    p->protocol == cp->protocol &&
+		    ip_vs_conn_net_eq(cp, p->net)) {
 			/* HIT */
 			atomic_inc(&cp->refcnt);
 			ret = cp;
@@ -428,7 +429,6 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 
 struct ip_vs_conn *
 ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
-			 struct ip_vs_protocol *pp,
 			 const struct ip_vs_iphdr *iph,
 			 unsigned int proto_off, int inverse)
 {
@@ -611,8 +611,8 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
 	struct ip_vs_dest *dest;
 
 	if ((cp) && (!cp->dest)) {
-		dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport,
-				       &cp->vaddr, cp->vport,
+		dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr,
+				       cp->dport, &cp->vaddr, cp->vport,
 				       cp->protocol, cp->fwmark);
 		ip_vs_bind_dest(cp, dest);
 		return dest;
@@ -686,13 +686,14 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
 int ip_vs_check_template(struct ip_vs_conn *ct)
 {
 	struct ip_vs_dest *dest = ct->dest;
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(ct));
 
 	/*
 	 * Checking the dest server status.
 	 */
 	if ((dest == NULL) ||
 	    !(dest->flags & IP_VS_DEST_F_AVAILABLE) ||
-	    (sysctl_ip_vs_expire_quiescent_template &&
+	    (ipvs->sysctl_expire_quiescent_template &&
 	     (atomic_read(&dest->weight) == 0))) {
 		IP_VS_DBG_BUF(9, "check_template: dest not available for "
 			      "protocol %s s:%s:%d v:%s:%d "
@@ -730,6 +731,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct)
 static void ip_vs_conn_expire(unsigned long data)
 {
 	struct ip_vs_conn *cp = (struct ip_vs_conn *)data;
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
 
 	cp->timeout = 60*HZ;
 
@@ -772,7 +774,7 @@ static void ip_vs_conn_expire(unsigned long data)
 		ip_vs_unbind_dest(cp);
 		if (cp->flags & IP_VS_CONN_F_NO_CPORT)
 			atomic_dec(&ip_vs_conn_no_cport_cnt);
-		atomic_dec(&ip_vs_conn_count);
+		atomic_dec(&ipvs->conn_count);
 
 		kmem_cache_free(ip_vs_conn_cachep, cp);
 		return;
@@ -806,7 +808,9 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	       struct ip_vs_dest *dest, __u32 fwmark)
 {
 	struct ip_vs_conn *cp;
-	struct ip_vs_protocol *pp = ip_vs_proto_get(p->protocol);
+	struct netns_ipvs *ipvs = net_ipvs(p->net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->net,
+							   p->protocol);
 
 	cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC);
 	if (cp == NULL) {
@@ -816,6 +820,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 
 	INIT_LIST_HEAD(&cp->c_list);
 	setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
+	ip_vs_conn_net_set(cp, p->net);
 	cp->af		   = p->af;
 	cp->protocol	   = p->protocol;
 	ip_vs_addr_copy(p->af, &cp->caddr, p->caddr);
@@ -846,7 +851,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	atomic_set(&cp->n_control, 0);
 	atomic_set(&cp->in_pkts, 0);
 
-	atomic_inc(&ip_vs_conn_count);
+	atomic_inc(&ipvs->conn_count);
 	if (flags & IP_VS_CONN_F_NO_CPORT)
 		atomic_inc(&ip_vs_conn_no_cport_cnt);
 
@@ -865,8 +870,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 #endif
 		ip_vs_bind_xmit(cp);
 
-	if (unlikely(pp && atomic_read(&pp->appcnt)))
-		ip_vs_bind_app(cp, pp);
+	if (unlikely(pd && atomic_read(&pd->appcnt)))
+		ip_vs_bind_app(cp, pd->pp);
 
 	/*
 	 * Allow conntrack to be preserved. By default, conntrack
@@ -875,7 +880,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	 * IP_VS_CONN_F_ONE_PACKET too.
 	 */
 
-	if (ip_vs_conntrack_enabled())
+	if (ip_vs_conntrack_enabled(ipvs))
 		cp->flags |= IP_VS_CONN_F_NFCT;
 
 	/* Hash it in the ip_vs_conn_tab finally */
@@ -888,17 +893,22 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
  *	/proc/net/ip_vs_conn entries
  */
 #ifdef CONFIG_PROC_FS
+struct ip_vs_iter_state {
+	struct seq_net_private p;
+	struct list_head *l;
+};
 
 static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
 {
 	int idx;
 	struct ip_vs_conn *cp;
+	struct ip_vs_iter_state *iter = seq->private;
 
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
 		ct_read_lock_bh(idx);
 		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
 			if (pos-- == 0) {
-				seq->private = &ip_vs_conn_tab[idx];
+				iter->l = &ip_vs_conn_tab[idx];
 			return cp;
 			}
 		}
@@ -910,14 +920,17 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
 
 static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	seq->private = NULL;
+	struct ip_vs_iter_state *iter = seq->private;
+
+	iter->l = NULL;
 	return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN;
 }
 
 static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct ip_vs_conn *cp = v;
-	struct list_head *e, *l = seq->private;
+	struct ip_vs_iter_state *iter = seq->private;
+	struct list_head *e, *l = iter->l;
 	int idx;
 
 	++*pos;
@@ -934,18 +947,19 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	while (++idx < ip_vs_conn_tab_size) {
 		ct_read_lock_bh(idx);
 		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
-			seq->private = &ip_vs_conn_tab[idx];
+			iter->l = &ip_vs_conn_tab[idx];
 			return cp;
 		}
 		ct_read_unlock_bh(idx);
 	}
-	seq->private = NULL;
+	iter->l = NULL;
 	return NULL;
 }
 
 static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v)
 {
-	struct list_head *l = seq->private;
+	struct ip_vs_iter_state *iter = seq->private;
+	struct list_head *l = iter->l;
 
 	if (l)
 		ct_read_unlock_bh(l - ip_vs_conn_tab);
@@ -959,9 +973,12 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
    "Pro FromIP   FPrt ToIP     TPrt DestIP   DPrt State       Expires PEName PEData\n");
 	else {
 		const struct ip_vs_conn *cp = v;
+		struct net *net = seq_file_net(seq);
 		char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3];
 		size_t len = 0;
 
+		if (!ip_vs_conn_net_eq(cp, net))
+			return 0;
 		if (cp->pe_data) {
 			pe_data[0] = ' ';
 			len = strlen(cp->pe->name);
@@ -1006,7 +1023,8 @@ static const struct seq_operations ip_vs_conn_seq_ops = {
 
 static int ip_vs_conn_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &ip_vs_conn_seq_ops);
+	return seq_open_net(inode, file, &ip_vs_conn_seq_ops,
+			    sizeof(struct ip_vs_iter_state));
 }
 
 static const struct file_operations ip_vs_conn_fops = {
@@ -1033,6 +1051,10 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
    "Pro FromIP   FPrt ToIP     TPrt DestIP   DPrt State       Origin Expires\n");
 	else {
 		const struct ip_vs_conn *cp = v;
+		struct net *net = seq_file_net(seq);
+
+		if (!ip_vs_conn_net_eq(cp, net))
+			return 0;
 
 #ifdef CONFIG_IP_VS_IPV6
 		if (cp->af == AF_INET6)
@@ -1069,7 +1091,8 @@ static const struct seq_operations ip_vs_conn_sync_seq_ops = {
 
 static int ip_vs_conn_sync_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &ip_vs_conn_sync_seq_ops);
+	return seq_open_net(inode, file, &ip_vs_conn_sync_seq_ops,
+			    sizeof(struct ip_vs_iter_state));
 }
 
 static const struct file_operations ip_vs_conn_sync_fops = {
@@ -1115,7 +1138,7 @@ static inline int todrop_entry(struct ip_vs_conn *cp)
 }
 
 /* Called from keventd and must protect itself from softirqs */
-void ip_vs_random_dropentry(void)
+void ip_vs_random_dropentry(struct net *net)
 {
 	int idx;
 	struct ip_vs_conn *cp;
@@ -1135,7 +1158,8 @@ void ip_vs_random_dropentry(void)
 			if (cp->flags & IP_VS_CONN_F_TEMPLATE)
 				/* connection template */
 				continue;
-
+			if (!ip_vs_conn_net_eq(cp, net))
+				continue;
 			if (cp->protocol == IPPROTO_TCP) {
 				switch(cp->state) {
 				case IP_VS_TCP_S_SYN_RECV:
@@ -1170,12 +1194,13 @@ void ip_vs_random_dropentry(void)
 /*
  *      Flush all the connection entries in the ip_vs_conn_tab
  */
-static void ip_vs_conn_flush(void)
+static void ip_vs_conn_flush(struct net *net)
 {
 	int idx;
 	struct ip_vs_conn *cp;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
-  flush_again:
+flush_again:
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
 		/*
 		 *  Lock is actually needed in this loop.
@@ -1183,7 +1208,8 @@ static void ip_vs_conn_flush(void)
 		ct_write_lock_bh(idx);
 
 		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
-
+			if (!ip_vs_conn_net_eq(cp, net))
+				continue;
 			IP_VS_DBG(4, "del connection\n");
 			ip_vs_conn_expire_now(cp);
 			if (cp->control) {
@@ -1196,16 +1222,41 @@ static void ip_vs_conn_flush(void)
 
 	/* the counter may be not NULL, because maybe some conn entries
 	   are run by slow timer handler or unhashed but still referred */
-	if (atomic_read(&ip_vs_conn_count) != 0) {
+	if (atomic_read(&ipvs->conn_count) != 0) {
 		schedule();
 		goto flush_again;
 	}
 }
+/*
+ * per netns init and exit
+ */
+int __net_init __ip_vs_conn_init(struct net *net)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	atomic_set(&ipvs->conn_count, 0);
+
+	proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops);
+	proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops);
+	return 0;
+}
 
+static void __net_exit __ip_vs_conn_cleanup(struct net *net)
+{
+	/* flush all the connection entries first */
+	ip_vs_conn_flush(net);
+	proc_net_remove(net, "ip_vs_conn");
+	proc_net_remove(net, "ip_vs_conn_sync");
+}
+static struct pernet_operations ipvs_conn_ops = {
+	.init = __ip_vs_conn_init,
+	.exit = __ip_vs_conn_cleanup,
+};
 
 int __init ip_vs_conn_init(void)
 {
 	int idx;
+	int retc;
 
 	/* Compute size and mask */
 	ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
@@ -1243,24 +1294,18 @@ int __init ip_vs_conn_init(void)
 		rwlock_init(&__ip_vs_conntbl_lock_array[idx].l);
 	}
 
-	proc_net_fops_create(&init_net, "ip_vs_conn", 0, &ip_vs_conn_fops);
-	proc_net_fops_create(&init_net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops);
+	retc = register_pernet_subsys(&ipvs_conn_ops);
 
 	/* calculate the random value for connection hash */
 	get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd));
 
-	return 0;
+	return retc;
 }
 
-
 void ip_vs_conn_cleanup(void)
 {
-	/* flush all the connection entries first */
-	ip_vs_conn_flush();
-
+	unregister_pernet_subsys(&ipvs_conn_ops);
 	/* Release the empty cache */
 	kmem_cache_destroy(ip_vs_conn_cachep);
-	proc_net_remove(&init_net, "ip_vs_conn");
-	proc_net_remove(&init_net, "ip_vs_conn_sync");
 	vfree(ip_vs_conn_tab);
 }
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 5287771d064..f36a84f33ef 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -41,6 +41,7 @@
 #include <net/icmp.h>                   /* for icmp_send */
 #include <net/route.h>
 #include <net/ip6_checksum.h>
+#include <net/netns/generic.h>		/* net_generic() */
 
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
@@ -68,6 +69,12 @@ EXPORT_SYMBOL(ip_vs_conn_put);
 EXPORT_SYMBOL(ip_vs_get_debug_level);
 #endif
 
+int ip_vs_net_id __read_mostly;
+#ifdef IP_VS_GENERIC_NETNS
+EXPORT_SYMBOL(ip_vs_net_id);
+#endif
+/* netns cnt used for uniqueness */
+static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0);
 
 /* ID used in ICMP lookups */
 #define icmp_id(icmph)          (((icmph)->un).echo.id)
@@ -108,21 +115,28 @@ static inline void
 ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 {
 	struct ip_vs_dest *dest = cp->dest;
+	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+
 	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
-		spin_lock(&dest->stats.lock);
-		dest->stats.ustats.inpkts++;
-		dest->stats.ustats.inbytes += skb->len;
-		spin_unlock(&dest->stats.lock);
-
-		spin_lock(&dest->svc->stats.lock);
-		dest->svc->stats.ustats.inpkts++;
-		dest->svc->stats.ustats.inbytes += skb->len;
-		spin_unlock(&dest->svc->stats.lock);
-
-		spin_lock(&ip_vs_stats.lock);
-		ip_vs_stats.ustats.inpkts++;
-		ip_vs_stats.ustats.inbytes += skb->len;
-		spin_unlock(&ip_vs_stats.lock);
+		struct ip_vs_cpu_stats *s;
+
+		s = this_cpu_ptr(dest->stats.cpustats);
+		s->ustats.inpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.inbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(dest->svc->stats.cpustats);
+		s->ustats.inpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.inbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(ipvs->cpustats);
+		s->ustats.inpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.inbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
 	}
 }
 
@@ -131,21 +145,28 @@ static inline void
 ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 {
 	struct ip_vs_dest *dest = cp->dest;
+	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+
 	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
-		spin_lock(&dest->stats.lock);
-		dest->stats.ustats.outpkts++;
-		dest->stats.ustats.outbytes += skb->len;
-		spin_unlock(&dest->stats.lock);
-
-		spin_lock(&dest->svc->stats.lock);
-		dest->svc->stats.ustats.outpkts++;
-		dest->svc->stats.ustats.outbytes += skb->len;
-		spin_unlock(&dest->svc->stats.lock);
-
-		spin_lock(&ip_vs_stats.lock);
-		ip_vs_stats.ustats.outpkts++;
-		ip_vs_stats.ustats.outbytes += skb->len;
-		spin_unlock(&ip_vs_stats.lock);
+		struct ip_vs_cpu_stats *s;
+
+		s = this_cpu_ptr(dest->stats.cpustats);
+		s->ustats.outpkts++;
+		u64_stats_update_begin(&s->s