From 9846ada138accc63994b57ebdfa76e3e137729e2 Mon Sep 17 00:00:00 2001
From: Shan Wei <shanwei@cn.fujitsu.com>
Date: Tue, 8 Mar 2011 15:37:27 +0100
Subject: netfilter: ipset: fix the compile warning in ip_set_create
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

net/netfilter/ipset/ip_set_core.c:615: warning: ‘clash’ may be used uninitialized in this function

Signed-off-by: Shan Wei <shanwei@cn.fujitsu.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/ipset/ip_set_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 8b1a54c1e40..618a615acc9 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -612,7 +612,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
 	      const struct nlmsghdr *nlh,
 	      const struct nlattr * const attr[])
 {
-	struct ip_set *set, *clash;
+	struct ip_set *set, *clash = NULL;
 	ip_set_id_t index = IPSET_INVALID_ID;
 	struct nlattr *tb[IPSET_ATTR_CREATE_MAX+1] = {};
 	const char *name, *typename;
-- 
cgit v1.2.3-18-g5258


From adb00ae2ea0ec65f9d3d06079950c0f0ade3b614 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <shemminger@vyatta.com>
Date: Wed, 9 Mar 2011 14:14:26 +0100
Subject: netfilter: x_tables: misuse of try_then_request_module

Since xt_find_match() returns ERR_PTR(xx) on error not NULL,
the macro try_then_request_module won't work correctly here.
The macro expects its first argument will be zero if condition
fails. But ERR_PTR(-ENOENT) is not zero.

The correct solution is to propagate the error value
back.

Found by inspection, and compile tested only.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/x_tables.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 0a77d2ff215..271eed32a6a 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -183,7 +183,7 @@ EXPORT_SYMBOL(xt_unregister_matches);
 /*
  * These are weird, but module loading must not be done with mutex
  * held (since they will register), and we have to have a single
- * function to use try_then_request_module().
+ * function to use.
  */
 
 /* Find match, grabs ref.  Returns ERR_PTR() on error. */
@@ -221,9 +221,13 @@ xt_request_find_match(uint8_t nfproto, const char *name, uint8_t revision)
 {
 	struct xt_match *match;
 
-	match = try_then_request_module(xt_find_match(nfproto, name, revision),
-					"%st_%s", xt_prefix[nfproto], name);
-	return (match != NULL) ? match : ERR_PTR(-ENOENT);
+	match = xt_find_match(nfproto, name, revision);
+	if (IS_ERR(match)) {
+		request_module("%st_%s", xt_prefix[nfproto], name);
+		match = xt_find_match(nfproto, name, revision);
+	}
+
+	return match;
 }
 EXPORT_SYMBOL_GPL(xt_request_find_match);
 
@@ -261,9 +265,13 @@ struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision)
 {
 	struct xt_target *target;
 
-	target = try_then_request_module(xt_find_target(af, name, revision),
-					 "%st_%s", xt_prefix[af], name);
-	return (target != NULL) ? target : ERR_PTR(-ENOENT);
+	target = xt_find_target(af, name, revision);
+	if (IS_ERR(target)) {
+		request_module("%st_%s", xt_prefix[af], name);
+		target = xt_find_target(af, name, revision);
+	}
+
+	return target;
 }
 EXPORT_SYMBOL_GPL(xt_request_find_target);
 
-- 
cgit v1.2.3-18-g5258


From 42046e2e45c109ba703993c510401a11f716c8df Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Mon, 14 Mar 2011 19:11:44 +0100
Subject: netfilter: x_tables: return -ENOENT for non-existant matches/targets

As Stephen correctly points out, we need to return -ENOENT in
xt_find_match()/xt_find_target() after the patch "netfilter: x_tables:
misuse of try_then_request_module" in order to properly indicate
a non-existant module to the caller.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/x_tables.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 271eed32a6a..a9adf4c6b29 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -190,7 +190,7 @@ EXPORT_SYMBOL(xt_unregister_matches);
 struct xt_match *xt_find_match(u8 af, const char *name, u8 revision)
 {
 	struct xt_match *m;
-	int err = 0;
+	int err = -ENOENT;
 
 	if (mutex_lock_interruptible(&xt[af].mutex) != 0)
 		return ERR_PTR(-EINTR);
@@ -235,7 +235,7 @@ EXPORT_SYMBOL_GPL(xt_request_find_match);
 struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
 {
 	struct xt_target *t;
-	int err = 0;
+	int err = -ENOENT;
 
 	if (mutex_lock_interruptible(&xt[af].mutex) != 0)
 		return ERR_PTR(-EINTR);
-- 
cgit v1.2.3-18-g5258


From fe8f661f2c2bb058822f13f6f232e121bde1338f Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <shemminger@vyatta.com>
Date: Mon, 14 Mar 2011 19:20:44 +0100
Subject: netfilter: nf_conntrack: fix sysctl memory leak

Message in log because sysctl table was not empty at netns exit
 WARNING: at net/sysctl_net.c:84 sysctl_net_exit+0x2a/0x2c()

Instrumenting showed that the nf_conntrack_timestamp was the entry
that was being created but not cleared.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/nf_conntrack_core.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'net/netfilter')

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 1909311c392..118123606a2 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1294,6 +1294,7 @@ static void nf_conntrack_cleanup_net(struct net *net)
 
 	nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
 	nf_conntrack_ecache_fini(net);
+	nf_conntrack_tstamp_fini(net);
 	nf_conntrack_acct_fini(net);
 	nf_conntrack_expect_fini(net);
 	kmem_cache_destroy(net->ct.nf_conntrack_cachep);
-- 
cgit v1.2.3-18-g5258


From 097fc76a0805bdca17baf12cad9d3bcb215716a9 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 4 Mar 2011 12:26:17 +0200
Subject: ipvs: avoid lookup for fwmark 0

 	Restore the previous behaviour to lookup for fwmark
service only when fwmark is non-null. This saves only CPU.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c73b0c831a2..f0369d66508 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -411,9 +411,11 @@ ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 	/*
 	 *	Check the table hashed by fwmark first
 	 */
-	svc = __ip_vs_svc_fwm_find(net, af, fwmark);
-	if (fwmark && svc)
-		goto out;
+	if (fwmark) {
+		svc = __ip_vs_svc_fwm_find(net, af, fwmark);
+		if (svc)
+			goto out;
+	}
 
 	/*
 	 *	Check the table hashed by <protocol,addr,port>
-- 
cgit v1.2.3-18-g5258


From 4a569c0c0f833adace1e3aadaa38780ec2fcdf9e Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 4 Mar 2011 12:28:20 +0200
Subject: ipvs: remove _bh from percpu stats reading

 	ip_vs_read_cpu_stats is called only from timer, so
no need for _bh locks.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_est.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index f560a05c965..88bd71647bf 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -69,10 +69,10 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum,
 			sum->inpkts += s->ustats.inpkts;
 			sum->outpkts += s->ustats.outpkts;
 			do {
-				start = u64_stats_fetch_begin_bh(&s->syncp);
+				start = u64_stats_fetch_begin(&s->syncp);
 				inbytes = s->ustats.inbytes;
 				outbytes = s->ustats.outbytes;
-			} while (u64_stats_fetch_retry_bh(&s->syncp, start));
+			} while (u64_stats_fetch_retry(&s->syncp, start));
 			sum->inbytes += inbytes;
 			sum->outbytes += outbytes;
 		} else {
@@ -80,10 +80,10 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum,
 			sum->inpkts = s->ustats.inpkts;
 			sum->outpkts = s->ustats.outpkts;
 			do {
-				start = u64_stats_fetch_begin_bh(&s->syncp);
+				start = u64_stats_fetch_begin(&s->syncp);
 				sum->inbytes = s->ustats.inbytes;
 				sum->outbytes = s->ustats.outbytes;
-			} while (u64_stats_fetch_retry_bh(&s->syncp, start));
+			} while (u64_stats_fetch_retry(&s->syncp, start));
 		}
 	}
 }
-- 
cgit v1.2.3-18-g5258


From 6060c74a3de8ed142c78133e2829e74711f77387 Mon Sep 17 00:00:00 2001
From: Shan Wei <shanwei@cn.fujitsu.com>
Date: Mon, 7 Mar 2011 10:11:34 +0800
Subject: netfilter:ipvs: use kmemdup

The semantic patch that makes this output is available
in scripts/coccinelle/api/memdup.cocci.

More information about semantic patching is available at
http://coccinelle.lip6.fr/

Signed-off-by: Shan Wei <shanwei@cn.fujitsu.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_pe_sip.c | 9 ++++-----
 net/netfilter/ipvs/ip_vs_sync.c   | 3 +--
 2 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 0d83bc01fed..13d607ae9c5 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -92,14 +92,13 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen))
 		return -EINVAL;
 
-	p->pe_data = kmalloc(matchlen, GFP_ATOMIC);
-	if (!p->pe_data)
-		return -ENOMEM;
-
 	/* N.B: pe_data is only set on success,
 	 * this allows fallback to the default persistence logic on failure
 	 */
-	memcpy(p->pe_data, dptr + matchoff, matchlen);
+	p->pe_data = kmemdup(dptr + matchoff, matchlen, GFP_ATOMIC);
+	if (!p->pe_data)
+		return -ENOMEM;
+
 	p->pe_data_len = matchlen;
 
 	return 0;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index fecf24de4af..c5d13b05275 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -697,13 +697,12 @@ ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc,
 			return 1;
 		}
 
-		p->pe_data = kmalloc(pe_data_len, GFP_ATOMIC);
+		p->pe_data = kmemdup(pe_data, pe_data_len, GFP_ATOMIC);
 		if (!p->pe_data) {
 			if (p->pe->module)
 				module_put(p->pe->module);
 			return -ENOMEM;
 		}
-		memcpy(p->pe_data, pe_data, pe_data_len);
 		p->pe_data_len = pe_data_len;
 	}
 	return 0;
-- 
cgit v1.2.3-18-g5258


From 2a0751af09c3099cf2837c623ca5d0436317d02d Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 4 Mar 2011 12:20:35 +0200
Subject: ipvs: reorganize tot_stats

 	The global tot_stats contains cpustats field just like the
stats for dest and svc, so better use it to simplify the usage
in estimation_timer. As tot_stats is registered as estimator
we can remove the special ip_vs_read_cpu_stats call for
tot_stats. Fix ip_vs_read_cpu_stats to be called under
stats lock because it is still used as synchronization between
estimation timer and user context (the stats readers).

 	Also, make sure ip_vs_stats_percpu_show reads properly
the u64 stats from user context.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_core.c |  6 +++---
 net/netfilter/ipvs/ip_vs_ctl.c  | 45 ++++++++++++++++++++++-------------------
 net/netfilter/ipvs/ip_vs_est.c  |  3 +--
 3 files changed, 28 insertions(+), 26 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 2d1f932add4..6f4940e86fc 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -132,7 +132,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 		s->ustats.inbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
 
-		s = this_cpu_ptr(ipvs->cpustats);
+		s = this_cpu_ptr(ipvs->tot_stats.cpustats);
 		s->ustats.inpkts++;
 		u64_stats_update_begin(&s->syncp);
 		s->ustats.inbytes += skb->len;
@@ -162,7 +162,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 		s->ustats.outbytes += skb->len;
 		u64_stats_update_end(&s->syncp);
 
-		s = this_cpu_ptr(ipvs->cpustats);
+		s = this_cpu_ptr(ipvs->tot_stats.cpustats);
 		s->ustats.outpkts++;
 		u64_stats_update_begin(&s->syncp);
 		s->ustats.outbytes += skb->len;
@@ -183,7 +183,7 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 	s = this_cpu_ptr(svc->stats.cpustats);
 	s->ustats.conns++;
 
-	s = this_cpu_ptr(ipvs->cpustats);
+	s = this_cpu_ptr(ipvs->tot_stats.cpustats);
 	s->ustats.conns++;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index f0369d66508..a2a67ad7e09 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1481,7 +1481,7 @@ static int ip_vs_zero_all(struct net *net)
 		}
 	}
 
-	ip_vs_zero_stats(net_ipvs(net)->tot_stats);
+	ip_vs_zero_stats(&net_ipvs(net)->tot_stats);
 	return 0;
 }
 
@@ -1963,7 +1963,7 @@ static const struct file_operations ip_vs_info_fops = {
 static int ip_vs_stats_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq_file_single_net(seq);
-	struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats;
+	struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
@@ -2007,7 +2007,8 @@ static const struct file_operations ip_vs_stats_fops = {
 static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq_file_single_net(seq);
-	struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats;
+	struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
+	struct ip_vs_cpu_stats *cpustats = tot_stats->cpustats;
 	int i;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
@@ -2017,11 +2018,20 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 		   "CPU    Conns  Packets  Packets            Bytes            Bytes\n");
 
 	for_each_possible_cpu(i) {
-		struct ip_vs_cpu_stats *u = per_cpu_ptr(net->ipvs->cpustats, i);
+		struct ip_vs_cpu_stats *u = per_cpu_ptr(cpustats, i);
+		unsigned int start;
+		__u64 inbytes, outbytes;
+
+		do {
+			start = u64_stats_fetch_begin_bh(&u->syncp);
+			inbytes = u->ustats.inbytes;
+			outbytes = u->ustats.outbytes;
+		} while (u64_stats_fetch_retry_bh(&u->syncp, start));
+
 		seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n",
-			    i, u->ustats.conns, u->ustats.inpkts,
-			    u->ustats.outpkts, (__u64)u->ustats.inbytes,
-			    (__u64)u->ustats.outbytes);
+			   i, u->ustats.conns, u->ustats.inpkts,
+			   u->ustats.outpkts, (__u64)inbytes,
+			   (__u64)outbytes);
 	}
 
 	spin_lock_bh(&tot_stats->lock);
@@ -3505,17 +3515,12 @@ int __net_init __ip_vs_control_init(struct net *net)
 	atomic_set(&ipvs->nullsvc_counter, 0);
 
 	/* procfs stats */
-	ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL);
-	if (ipvs->tot_stats == NULL) {
-		pr_err("%s(): no memory.\n", __func__);
-		return -ENOMEM;
-	}
-	ipvs->cpustats = alloc_percpu(struct ip_vs_cpu_stats);
-	if (!ipvs->cpustats) {
+	ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
+	if (!ipvs->tot_stats.cpustats) {
 		pr_err("%s() alloc_percpu failed\n", __func__);
 		goto err_alloc;
 	}
-	spin_lock_init(&ipvs->tot_stats->lock);
+	spin_lock_init(&ipvs->tot_stats.lock);
 
 	proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
 	proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
@@ -3563,7 +3568,7 @@ int __net_init __ip_vs_control_init(struct net *net)
 		goto err_dup;
 	}
 #endif
-	ip_vs_new_estimator(net, ipvs->tot_stats);
+	ip_vs_new_estimator(net, &ipvs->tot_stats);
 	ipvs->sysctl_tbl = tbl;
 	/* Schedule defense work */
 	INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
@@ -3571,9 +3576,8 @@ int __net_init __ip_vs_control_init(struct net *net)
 	return 0;
 
 err_dup:
-	free_percpu(ipvs->cpustats);
+	free_percpu(ipvs->tot_stats.cpustats);
 err_alloc:
-	kfree(ipvs->tot_stats);
 	return -ENOMEM;
 }
 
@@ -3582,7 +3586,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	ip_vs_trash_cleanup(net);
-	ip_vs_kill_estimator(net, ipvs->tot_stats);
+	ip_vs_kill_estimator(net, &ipvs->tot_stats);
 	cancel_delayed_work_sync(&ipvs->defense_work);
 	cancel_work_sync(&ipvs->defense_work.work);
 #ifdef CONFIG_SYSCTL
@@ -3591,8 +3595,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 	proc_net_remove(net, "ip_vs_stats_percpu");
 	proc_net_remove(net, "ip_vs_stats");
 	proc_net_remove(net, "ip_vs");
-	free_percpu(ipvs->cpustats);
-	kfree(ipvs->tot_stats);
+	free_percpu(ipvs->tot_stats.cpustats);
 }
 
 static struct pernet_operations ipvs_control_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index 88bd71647bf..b3751cfede2 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -101,13 +101,12 @@ static void estimation_timer(unsigned long arg)
 	struct netns_ipvs *ipvs;
 
 	ipvs = net_ipvs(net);
-	ip_vs_read_cpu_stats(&ipvs->tot_stats->ustats, ipvs->cpustats);
 	spin_lock(&ipvs->est_lock);
 	list_for_each_entry(e, &ipvs->est_list, list) {
 		s = container_of(e, struct ip_vs_stats, est);
 
-		ip_vs_read_cpu_stats(&s->ustats, s->cpustats);
 		spin_lock(&s->lock);
+		ip_vs_read_cpu_stats(&s->ustats, s->cpustats);
 		n_conns = s->ustats.conns;
 		n_inpkts = s->ustats.inpkts;
 		n_outpkts = s->ustats.outpkts;
-- 
cgit v1.2.3-18-g5258


From 55a3d4e15c7c953ecc55b96b83d2679abf8a7899 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Mon, 14 Mar 2011 01:37:49 +0200
Subject: ipvs: properly zero stats and rates

 	Currently, the new percpu counters are not zeroed and
the zero commands do not work as expected, we still show the old
sum of percpu values. OTOH, we can not reset the percpu counters
from user context without causing the incrementing to use old
and bogus values.

 	So, as Eric Dumazet suggested fix that by moving all overhead
to stats reading in user context. Do not introduce overhead in
timer context (estimator) and incrementing (packet handling in
softirqs).

 	The new ustats0 field holds the zero point for all
counter values, the rates always use 0 as base value as before.
When showing the values to user space just give the difference
between counters and the base values. The only drawback is that
percpu stats are not zeroed, they are accessible only from /proc
and are new interface, so it should not be a compatibility problem
as long as the sum stats are correct after zeroing.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 96 ++++++++++++++++++++++++++----------------
 net/netfilter/ipvs/ip_vs_est.c | 15 ++++---
 2 files changed, 68 insertions(+), 43 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index a2a67ad7e09..804fee7be69 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -711,13 +711,51 @@ static void ip_vs_trash_cleanup(struct net *net)
 	}
 }
 
+static void
+ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
+{
+#define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->ustats.c - src->ustats0.c
+#define IP_VS_SHOW_STATS_RATE(r) dst->r = src->ustats.r
+
+	spin_lock_bh(&src->lock);
+
+	IP_VS_SHOW_STATS_COUNTER(conns);
+	IP_VS_SHOW_STATS_COUNTER(inpkts);
+	IP_VS_SHOW_STATS_COUNTER(outpkts);
+	IP_VS_SHOW_STATS_COUNTER(inbytes);
+	IP_VS_SHOW_STATS_COUNTER(outbytes);
+
+	IP_VS_SHOW_STATS_RATE(cps);
+	IP_VS_SHOW_STATS_RATE(inpps);
+	IP_VS_SHOW_STATS_RATE(outpps);
+	IP_VS_SHOW_STATS_RATE(inbps);
+	IP_VS_SHOW_STATS_RATE(outbps);
+
+	spin_unlock_bh(&src->lock);
+}
 
 static void
 ip_vs_zero_stats(struct ip_vs_stats *stats)
 {
 	spin_lock_bh(&stats->lock);
 
-	memset(&stats->ustats, 0, sizeof(stats->ustats));
+	/* get current counters as zero point, rates are zeroed */
+
+#define IP_VS_ZERO_STATS_COUNTER(c) stats->ustats0.c = stats->ustats.c
+#define IP_VS_ZERO_STATS_RATE(r) stats->ustats.r = 0
+
+	IP_VS_ZERO_STATS_COUNTER(conns);
+	IP_VS_ZERO_STATS_COUNTER(inpkts);
+	IP_VS_ZERO_STATS_COUNTER(outpkts);
+	IP_VS_ZERO_STATS_COUNTER(inbytes);
+	IP_VS_ZERO_STATS_COUNTER(outbytes);
+
+	IP_VS_ZERO_STATS_RATE(cps);
+	IP_VS_ZERO_STATS_RATE(inpps);
+	IP_VS_ZERO_STATS_RATE(outpps);
+	IP_VS_ZERO_STATS_RATE(inbps);
+	IP_VS_ZERO_STATS_RATE(outbps);
+
 	ip_vs_zero_estimator(stats);
 
 	spin_unlock_bh(&stats->lock);
@@ -1963,7 +2001,7 @@ static const struct file_operations ip_vs_info_fops = {
 static int ip_vs_stats_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq_file_single_net(seq);
-	struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
+	struct ip_vs_stats_user show;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
@@ -1971,22 +2009,18 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v)
 	seq_printf(seq,
 		   "   Conns  Packets  Packets            Bytes            Bytes\n");
 
-	spin_lock_bh(&tot_stats->lock);
-	seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", tot_stats->ustats.conns,
-		   tot_stats->ustats.inpkts, tot_stats->ustats.outpkts,
-		   (unsigned long long) tot_stats->ustats.inbytes,
-		   (unsigned long long) tot_stats->ustats.outbytes);
+	ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats);
+	seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", show.conns,
+		   show.inpkts, show.outpkts,
+		   (unsigned long long) show.inbytes,
+		   (unsigned long long) show.outbytes);
 
 /*                 01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
 		   " Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
-	seq_printf(seq,"%8X %8X %8X %16X %16X\n",
-			tot_stats->ustats.cps,
-			tot_stats->ustats.inpps,
-			tot_stats->ustats.outpps,
-			tot_stats->ustats.inbps,
-			tot_stats->ustats.outbps);
-	spin_unlock_bh(&tot_stats->lock);
+	seq_printf(seq, "%8X %8X %8X %16X %16X\n",
+			show.cps, show.inpps, show.outpps,
+			show.inbps, show.outbps);
 
 	return 0;
 }
@@ -2297,14 +2331,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 }
 
 
-static void
-ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
-{
-	spin_lock_bh(&src->lock);
-	memcpy(dst, &src->ustats, sizeof(*dst));
-	spin_unlock_bh(&src->lock);
-}
-
 static void
 ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
 {
@@ -2691,31 +2717,29 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = {
 static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type,
 				 struct ip_vs_stats *stats)
 {
+	struct ip_vs_stats_user ustats;
 	struct nlattr *nl_stats = nla_nest_start(skb, container_type);
 	if (!nl_stats)
 		return -EMSGSIZE;
 
-	spin_lock_bh(&stats->lock);
-
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_CONNS, stats->ustats.conns);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPKTS, stats->ustats.inpkts);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPKTS, stats->ustats.outpkts);
-	NLA_PUT_U64(skb, IPVS_STATS_ATTR_INBYTES, stats->ustats.inbytes);
-	NLA_PUT_U64(skb, IPVS_STATS_ATTR_OUTBYTES, stats->ustats.outbytes);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_CPS, stats->ustats.cps);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPPS, stats->ustats.inpps);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPPS, stats->ustats.outpps);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INBPS, stats->ustats.inbps);
-	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTBPS, stats->ustats.outbps);
+	ip_vs_copy_stats(&ustats, stats);
 
-	spin_unlock_bh(&stats->lock);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_CONNS, ustats.conns);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPKTS, ustats.inpkts);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPKTS, ustats.outpkts);
+	NLA_PUT_U64(skb, IPVS_STATS_ATTR_INBYTES, ustats.inbytes);
+	NLA_PUT_U64(skb, IPVS_STATS_ATTR_OUTBYTES, ustats.outbytes);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_CPS, ustats.cps);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INPPS, ustats.inpps);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTPPS, ustats.outpps);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_INBPS, ustats.inbps);
+	NLA_PUT_U32(skb, IPVS_STATS_ATTR_OUTBPS, ustats.outbps);
 
 	nla_nest_end(skb, nl_stats);
 
 	return 0;
 
 nla_put_failure:
-	spin_unlock_bh(&stats->lock);
 	nla_nest_cancel(skb, nl_stats);
 	return -EMSGSIZE;
 }
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index b3751cfede2..a8500879637 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -184,13 +184,14 @@ void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats)
 void ip_vs_zero_estimator(struct ip_vs_stats *stats)
 {
 	struct ip_vs_estimator *est = &stats->est;
-
-	/* set counters zero, caller must hold the stats->lock lock */
-	est->last_inbytes = 0;
-	est->last_outbytes = 0;
-	est->last_conns = 0;
-	est->last_inpkts = 0;
-	est->last_outpkts = 0;
+	struct ip_vs_stats_user *u = &stats->ustats;
+
+	/* reset counters, caller must hold the stats->lock lock */
+	est->last_inbytes = u->inbytes;
+	est->last_outbytes = u->outbytes;
+	est->last_conns = u->conns;
+	est->last_inpkts = u->inpkts;
+	est->last_outpkts = u->outpkts;
 	est->cps = 0;
 	est->inpps = 0;
 	est->outpps = 0;
-- 
cgit v1.2.3-18-g5258


From ea9f22cce9c2530d659f9122819940b69506b2d9 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Mon, 14 Mar 2011 01:41:54 +0200
Subject: ipvs: optimize rates reading

 	Move the estimator reading from estimation_timer to user
context. ip_vs_read_estimator() will be used to decode the rate
values. As the decoded rates are not set by estimation timer
there is no need to reset them in ip_vs_zero_stats.

 	There is no need ip_vs_new_estimator() to encode stats
to rates, if the destination is in trash both the stats and the
rates are inactive.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 31 ++++++++++++-------------------
 net/netfilter/ipvs/ip_vs_est.c | 33 +++++++++++++--------------------
 2 files changed, 25 insertions(+), 39 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 804fee7be69..c93d806e73b 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -715,7 +715,6 @@ static void
 ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
 {
 #define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->ustats.c - src->ustats0.c
-#define IP_VS_SHOW_STATS_RATE(r) dst->r = src->ustats.r
 
 	spin_lock_bh(&src->lock);
 
@@ -725,11 +724,7 @@ ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
 	IP_VS_SHOW_STATS_COUNTER(inbytes);
 	IP_VS_SHOW_STATS_COUNTER(outbytes);
 
-	IP_VS_SHOW_STATS_RATE(cps);
-	IP_VS_SHOW_STATS_RATE(inpps);
-	IP_VS_SHOW_STATS_RATE(outpps);
-	IP_VS_SHOW_STATS_RATE(inbps);
-	IP_VS_SHOW_STATS_RATE(outbps);
+	ip_vs_read_estimator(dst, src);
 
 	spin_unlock_bh(&src->lock);
 }
@@ -742,7 +737,6 @@ ip_vs_zero_stats(struct ip_vs_stats *stats)
 	/* get current counters as zero point, rates are zeroed */
 
 #define IP_VS_ZERO_STATS_COUNTER(c) stats->ustats0.c = stats->ustats.c
-#define IP_VS_ZERO_STATS_RATE(r) stats->ustats.r = 0
 
 	IP_VS_ZERO_STATS_COUNTER(conns);
 	IP_VS_ZERO_STATS_COUNTER(inpkts);
@@ -750,12 +744,6 @@ ip_vs_zero_stats(struct ip_vs_stats *stats)
 	IP_VS_ZERO_STATS_COUNTER(inbytes);
 	IP_VS_ZERO_STATS_COUNTER(outbytes);
 
-	IP_VS_ZERO_STATS_RATE(cps);
-	IP_VS_ZERO_STATS_RATE(inpps);
-	IP_VS_ZERO_STATS_RATE(outpps);
-	IP_VS_ZERO_STATS_RATE(inbps);
-	IP_VS_ZERO_STATS_RATE(outbps);
-
 	ip_vs_zero_estimator(stats);
 
 	spin_unlock_bh(&stats->lock);
@@ -2043,6 +2031,7 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 	struct net *net = seq_file_single_net(seq);
 	struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
 	struct ip_vs_cpu_stats *cpustats = tot_stats->cpustats;
+	struct ip_vs_stats_user rates;
 	int i;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
@@ -2069,22 +2058,26 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 	}
 
 	spin_lock_bh(&tot_stats->lock);
+
 	seq_printf(seq, "  ~ %8X %8X %8X %16LX %16LX\n\n",
 		   tot_stats->ustats.conns, tot_stats->ustats.inpkts,
 		   tot_stats->ustats.outpkts,
 		   (unsigned long long) tot_stats->ustats.inbytes,
 		   (unsigned long long) tot_stats->ustats.outbytes);
 
+	ip_vs_read_estimator(&rates, tot_stats);
+
+	spin_unlock_bh(&tot_stats->lock);
+
 /*                 01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
 		   "     Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
 	seq_printf(seq, "    %8X %8X %8X %16X %16X\n",
-			tot_stats->ustats.cps,
-			tot_stats->ustats.inpps,
-			tot_stats->ustats.outpps,
-			tot_stats->ustats.inbps,
-			tot_stats->ustats.outbps);
-	spin_unlock_bh(&tot_stats->lock);
+			rates.cps,
+			rates.inpps,
+			rates.outpps,
+			rates.inbps,
+			rates.outbps);
 
 	return 0;
 }
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index a8500879637..fda75be231e 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -117,27 +117,22 @@ static void estimation_timer(unsigned long arg)
 		rate = (n_conns - e->last_conns) << 9;
 		e->last_conns = n_conns;
 		e->cps += ((long)rate - (long)e->cps) >> 2;
-		s->ustats.cps = (e->cps + 0x1FF) >> 10;
 
 		rate = (n_inpkts - e->last_inpkts) << 9;
 		e->last_inpkts = n_inpkts;
 		e->inpps += ((long)rate - (long)e->inpps) >> 2;
-		s->ustats.inpps = (e->inpps + 0x1FF) >> 10;
 
 		rate = (n_outpkts - e->last_outpkts) << 9;
 		e->last_outpkts = n_outpkts;
 		e->outpps += ((long)rate - (long)e->outpps) >> 2;
-		s->ustats.outpps = (e->outpps + 0x1FF) >> 10;
 
 		rate = (n_inbytes - e->last_inbytes) << 4;
 		e->last_inbytes = n_inbytes;
 		e->inbps += ((long)rate - (long)e->inbps) >> 2;
-		s->ustats.inbps = (e->inbps + 0xF) >> 5;
 
 		rate = (n_outbytes - e->last_outbytes) << 4;
 		e->last_outbytes = n_outbytes;
 		e->outbps += ((long)rate - (long)e->outbps) >> 2;
-		s->ustats.outbps = (e->outbps + 0xF) >> 5;
 		spin_unlock(&s->lock);
 	}
 	spin_unlock(&ipvs->est_lock);
@@ -151,21 +146,6 @@ void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
 
 	INIT_LIST_HEAD(&est->list);
 
-	est->last_conns = stats->ustats.conns;
-	est->cps = stats->ustats.cps<<10;
-
-	est->last_inpkts = stats->ustats.inpkts;
-	est->inpps = stats->ustats.inpps<<10;
-
-	est->last_outpkts = stats->ustats.outpkts;
-	est->outpps = stats->ustats.outpps<<10;
-
-	est->last_inbytes = stats->ustats.inbytes;
-	est->inbps = stats->ustats.inbps<<5;
-
-	est->last_outbytes = stats->ustats.outbytes;
-	est->outbps = stats->ustats.outbps<<5;
-
 	spin_lock_bh(&ipvs->est_lock);
 	list_add(&est->list, &ipvs->est_list);
 	spin_unlock_bh(&ipvs->est_lock);
@@ -199,6 +179,19 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats)
 	est->outbps = 0;
 }
 
+/* Get decoded rates */
+void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
+			  struct ip_vs_stats *stats)
+{
+	struct ip_vs_estimator *e = &stats->est;
+
+	dst->cps = (e->cps + 0x1FF) >> 10;
+	dst->inpps = (e->inpps + 0x1FF) >> 10;
+	dst->outpps = (e->outpps + 0x1FF) >> 10;
+	dst->inbps = (e->inbps + 0xF) >> 5;
+	dst->outbps = (e->outbps + 0xF) >> 5;
+}
+
 static int __net_init __ip_vs_estimator_init(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
-- 
cgit v1.2.3-18-g5258


From 6ef757f965c9133e82116475eab7f30df391c7fa Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Mon, 14 Mar 2011 01:44:28 +0200
Subject: ipvs: rename estimator functions

 	Rename ip_vs_new_estimator to ip_vs_start_estimator
and ip_vs_kill_estimator to ip_vs_stop_estimator to better
match their logic.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 12 ++++++------
 net/netfilter/ipvs/ip_vs_est.c |  4 ++--
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c93d806e73b..c5b1234b630 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -802,7 +802,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	spin_unlock(&dest->dst_lock);
 
 	if (add)
-		ip_vs_new_estimator(svc->net, &dest->stats);
+		ip_vs_start_estimator(svc->net, &dest->stats);
 
 	write_lock_bh(&__ip_vs_svc_lock);
 
@@ -1008,7 +1008,7 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	ip_vs_kill_estimator(net, &dest->stats);
+	ip_vs_stop_estimator(net, &dest->stats);
 
 	/*
 	 *  Remove it from the d-linked list with the real services.
@@ -1201,7 +1201,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	else if (svc->port == 0)
 		atomic_inc(&ipvs->nullsvc_counter);
 
-	ip_vs_new_estimator(net, &svc->stats);
+	ip_vs_start_estimator(net, &svc->stats);
 
 	/* Count only IPv4 services for old get/setsockopt interface */
 	if (svc->af == AF_INET)
@@ -1353,7 +1353,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 	if (svc->af == AF_INET)
 		ipvs->num_services--;
 
-	ip_vs_kill_estimator(svc->net, &svc->stats);
+	ip_vs_stop_estimator(svc->net, &svc->stats);
 
 	/* Unbind scheduler */
 	old_sched = svc->scheduler;
@@ -3585,7 +3585,7 @@ int __net_init __ip_vs_control_init(struct net *net)
 		goto err_dup;
 	}
 #endif
-	ip_vs_new_estimator(net, &ipvs->tot_stats);
+	ip_vs_start_estimator(net, &ipvs->tot_stats);
 	ipvs->sysctl_tbl = tbl;
 	/* Schedule defense work */
 	INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
@@ -3603,7 +3603,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	ip_vs_trash_cleanup(net);
-	ip_vs_kill_estimator(net, &ipvs->tot_stats);
+	ip_vs_stop_estimator(net, &ipvs->tot_stats);
 	cancel_delayed_work_sync(&ipvs->defense_work);
 	cancel_work_sync(&ipvs->defense_work.work);
 #ifdef CONFIG_SYSCTL
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index fda75be231e..8c8766ca56a 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -139,7 +139,7 @@ static void estimation_timer(unsigned long arg)
 	mod_timer(&ipvs->est_timer, jiffies + 2*HZ);
 }
 
-void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
+void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_estimator *est = &stats->est;
@@ -151,7 +151,7 @@ void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
 	spin_unlock_bh(&ipvs->est_lock);
 }
 
-void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats)
+void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_estimator *est = &stats->est;
-- 
cgit v1.2.3-18-g5258


From ba4fd7e966fa837557a3ec846c5fd15328b212af Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:01 +0900
Subject: IPVS: Add ip_vs_route_me_harder()

Add ip_vs_route_me_harder() to avoid repeating the same code twice.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_core.c | 48 +++++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 26 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 6f4940e86fc..299c7f33e18 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -631,6 +631,24 @@ static inline int ip_vs_gather_frags_v6(struct sk_buff *skb, u_int32_t user)
 }
 #endif
 
+static int ip_vs_route_me_harder(int af, struct sk_buff *skb)
+{
+	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+
+#ifdef CONFIG_IP_VS_IPV6
+	if (af == AF_INET6) {
+		if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
+			return 1;
+	} else
+#endif
+		if ((ipvs->sysctl_snat_reroute ||
+		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
+		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
+			return 1;
+
+	return 0;
+}
+
 /*
  * Packet has been made sufficiently writable in caller
  * - inout: 1=in->out, 0=out->in
@@ -737,7 +755,6 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 				struct ip_vs_protocol *pp,
 				unsigned int offset, unsigned int ihl)
 {
-	struct netns_ipvs *ipvs;
 	unsigned int verdict = NF_DROP;
 
 	if (IP_VS_FWD_METHOD(cp) != 0) {
@@ -759,8 +776,6 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 	if (!skb_make_writable(skb, offset))
 		goto out;
 
-	ipvs = net_ipvs(skb_net(skb));
-
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
 		ip_vs_nat_icmp_v6(skb, pp, cp, 1);
@@ -768,16 +783,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 #endif
 		ip_vs_nat_icmp(skb, pp, cp, 1);
 
-#ifdef CONFIG_IP_VS_IPV6
-	if (af == AF_INET6) {
-		if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
-			goto out;
-	} else
-#endif
-		if ((ipvs->sysctl_snat_reroute ||
-		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
-		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
-			goto out;
+	if (ip_vs_route_me_harder(af, skb))
+		goto out;
 
 	/* do the statistics and put it back */
 	ip_vs_out_stats(cp, skb);
@@ -985,7 +992,6 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		struct ip_vs_conn *cp, int ihl)
 {
 	struct ip_vs_protocol *pp = pd->pp;
-	struct netns_ipvs *ipvs;
 
 	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet");
 
@@ -1021,18 +1027,8 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	 * if it came from this machine itself.  So re-compute
 	 * the routing information.
 	 */
-	ipvs = net_ipvs(skb_net(skb));
-
-#ifdef CONFIG_IP_VS_IPV6
-	if (af == AF_INET6) {
-		if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
-			goto drop;
-	} else
-#endif
-		if ((ipvs->sysctl_snat_reroute ||
-		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
-		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
-			goto drop;
+	if (ip_vs_route_me_harder(af, skb))
+		goto drop;
 
 	IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
 
-- 
cgit v1.2.3-18-g5258


From 84b3cee39ff1ffc97f4f6fba8ad26786c1f6d8f5 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:01 +0900
Subject: IPVS: Add sysctl_snat_reroute()

In preparation for not including sysctl_snat_reroute in
struct netns_ipvs when CONFIG_SYCTL is not defined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_core.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 299c7f33e18..1d8a2a22615 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -599,6 +599,20 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 	return NF_DROP;
 }
 
+#ifdef CONFIG_SYSCTL
+
+static int sysctl_snat_reroute(struct sk_buff *skb)
+{
+	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+	return ipvs->sysctl_snat_reroute;
+}
+
+#else
+
+static int sysctl_snat_reroute(struct sk_buff *skb) { return 0; }
+
+#endif
+
 __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
 {
 	return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
@@ -633,15 +647,13 @@ static inline int ip_vs_gather_frags_v6(struct sk_buff *skb, u_int32_t user)
 
 static int ip_vs_route_me_harder(int af, struct sk_buff *skb)
 {
-	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
-
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
+		if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0)
 			return 1;
 	} else
 #endif
-		if ((ipvs->sysctl_snat_reroute ||
+		if ((sysctl_snat_reroute(skb) ||
 		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
 		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
 			return 1;
-- 
cgit v1.2.3-18-g5258


From 0cfa558e2c21644a0dd6c21cfadd8bbeaf9fe1a0 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:01 +0900
Subject: IPVS: Add sysctl_nat_icmp_send()

In preparation for not including sysctl_nat_icmp_send in
struct netns_ipvs when CONFIG_SYCTL is not defined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_core.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 1d8a2a22615..c9b83728f3c 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -607,9 +607,16 @@ static int sysctl_snat_reroute(struct sk_buff *skb)
 	return ipvs->sysctl_snat_reroute;
 }
 
+static int sysctl_nat_icmp_send(struct net *net)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	return ipvs->sysctl_nat_icmp_send;
+}
+
 #else
 
 static int sysctl_snat_reroute(struct sk_buff *skb) { return 0; }
+static int sysctl_nat_icmp_send(struct net *net) { return 0; }
 
 #endif
 
@@ -1074,7 +1081,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	struct ip_vs_protocol *pp;
 	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
-	struct netns_ipvs *ipvs;
 
 	EnterFunction(11);
 
@@ -1149,11 +1155,10 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	 * Check if the packet belongs to an existing entry
 	 */
 	cp = pp->conn_out_get(af, skb, &iph, iph.len, 0);
-	ipvs = net_ipvs(net);
 
 	if (likely(cp))
 		return handle_response(af, skb, pd, cp, iph.len);
-	if (ipvs->sysctl_nat_icmp_send &&
+	if (sysctl_nat_icmp_send(net) &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
 	     pp->protocol == IPPROTO_SCTP)) {
-- 
cgit v1.2.3-18-g5258


From 59e0350eada0516a810cb780db37746165f1d516 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:01 +0900
Subject: IPVS: Add {sysctl_sync_threshold,period}()

In preparation for not including sysctl_sync_threshold in
struct netns_ipvs when CONFIG_SYCTL is not defined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_core.c | 10 +++++-----
 net/netfilter/ipvs/ip_vs_ctl.c  |  4 ++--
 net/netfilter/ipvs/ip_vs_sync.c |  4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index c9b83728f3c..6a0053d9174 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1613,15 +1613,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	 */
 
 	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
-		pkts = ipvs->sysctl_sync_threshold[0];
+		pkts = sysctl_sync_threshold(ipvs);
 	else
 		pkts = atomic_add_return(1, &cp->in_pkts);
 
 	if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    cp->protocol == IPPROTO_SCTP) {
 		if ((cp->state == IP_VS_SCTP_S_ESTABLISHED &&
-			(pkts % ipvs->sysctl_sync_threshold[1]
-			 == ipvs->sysctl_sync_threshold[0])) ||
+			(pkts % sysctl_sync_period(ipvs)
+			 == sysctl_sync_threshold(ipvs))) ||
 				(cp->old_state != cp->state &&
 				 ((cp->state == IP_VS_SCTP_S_CLOSED) ||
 				  (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) ||
@@ -1635,8 +1635,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	else if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    (((cp->protocol != IPPROTO_TCP ||
 	       cp->state == IP_VS_TCP_S_ESTABLISHED) &&
-	      (pkts % ipvs->sysctl_sync_threshold[1]
-	       == ipvs->sysctl_sync_threshold[0])) ||
+	      (pkts % sysctl_sync_period(ipvs)
+	       == sysctl_sync_threshold(ipvs))) ||
 	     ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) &&
 	      ((cp->state == IP_VS_TCP_S_FIN_WAIT) ||
 	       (cp->state == IP_VS_TCP_S_CLOSE) ||
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c5b1234b630..364520f66b7 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3569,8 +3569,8 @@ int __net_init __ip_vs_control_init(struct net *net)
 	tbl[idx++].data = &ipvs->sysctl_cache_bypass;
 	tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn;
 	tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template;
-	ipvs->sysctl_sync_threshold[0] = 3;
-	ipvs->sysctl_sync_threshold[1] = 50;
+	ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD;
+	ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD;
 	tbl[idx].data = &ipvs->sysctl_sync_threshold;
 	tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold);
 	tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index c5d13b05275..e84987fa1bf 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -650,7 +650,7 @@ control:
 	if (cp->flags & IP_VS_CONN_F_TEMPLATE) {
 		int pkts = atomic_add_return(1, &cp->in_pkts);
 
-		if (pkts % ipvs->sysctl_sync_threshold[1] != 1)
+		if (pkts % sysctl_sync_period(ipvs) != 1)
 			return;
 	}
 	goto sloop;
@@ -794,7 +794,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 
 	if (opt)
 		memcpy(&cp->in_seq, opt, sizeof(*opt));
-	atomic_set(&cp->in_pkts, ipvs->sysctl_sync_threshold[0]);
+	atomic_set(&cp->in_pkts, sysctl_sync_threshold(ipvs));
 	cp->state = state;
 	cp->old_state = cp->state;
 	/*
-- 
cgit v1.2.3-18-g5258


From 7532e8d40ccfdde6667169eeac4fd7778d6eb462 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:01 +0900
Subject: IPVS: Add sysctl_sync_ver()

In preparation for not including sysctl_sync_ver in
struct netns_ipvs when CONFIG_SYCTL is not defined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_sync.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index e84987fa1bf..3e7961e85e9 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -394,7 +394,7 @@ void ip_vs_sync_switch_mode(struct net *net, int mode)
 
 	if (!(ipvs->sync_state & IP_VS_STATE_MASTER))
 		return;
-	if (mode == ipvs->sysctl_sync_ver || !ipvs->sync_buff)
+	if (mode == sysctl_sync_ver(ipvs) || !ipvs->sync_buff)
 		return;
 
 	spin_lock_bh(&ipvs->sync_buff_lock);
@@ -521,7 +521,7 @@ void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp)
 	unsigned int len, pe_name_len, pad;
 
 	/* Handle old version of the protocol */
-	if (ipvs->sysctl_sync_ver == 0) {
+	if (sysctl_sync_ver(ipvs) == 0) {
 		ip_vs_sync_conn_v0(net, cp);
 		return;
 	}
-- 
cgit v1.2.3-18-g5258


From 71a8ab6cad63b4816711f2ea518755677a870f6f Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:01 +0900
Subject: IPVS: Add sysctl_expire_nodest_conn()

In preparation for not including sysctl_expire_nodest_conn in
struct netns_ipvs when CONFIG_SYCTL is not defined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_core.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 6a0053d9174..d418bc60d00 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -613,10 +613,16 @@ static int sysctl_nat_icmp_send(struct net *net)
 	return ipvs->sysctl_nat_icmp_send;
 }
 
+static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_expire_nodest_conn;
+}
+
 #else
 
 static int sysctl_snat_reroute(struct sk_buff *skb) { return 0; }
 static int sysctl_nat_icmp_send(struct net *net) { return 0; }
+static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) { return 0; }
 
 #endif
 
@@ -1583,7 +1589,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
 		/* the destination server is not available */
 
-		if (ipvs->sysctl_expire_nodest_conn) {
+		if (sysctl_expire_nodest_conn(ipvs)) {
 			/* try to expire the connection immediately */
 			ip_vs_conn_expire_now(cp);
 		}
-- 
cgit v1.2.3-18-g5258


From 8e1b0b1b560019cafebe45a7d9e6ec1122fedc7b Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:01 +0900
Subject: IPVS: Add expire_quiescent_template()

In preparation for not including sysctl_expire_quiescent_template in
struct netns_ipvs when CONFIG_SYCTL is not defined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_conn.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 9c2a517b69c..f289306cbf1 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -680,6 +680,16 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
 	atomic_dec(&dest->refcnt);
 }
 
+static int expire_quiescent_template(struct netns_ipvs *ipvs,
+				     struct ip_vs_dest *dest)
+{
+#ifdef CONFIG_SYSCTL
+	return ipvs->sysctl_expire_quiescent_template &&
+		(atomic_read(&dest->weight) == 0);
+#else
+	return 0;
+#endif
+}
 
 /*
  *	Checking if the destination of a connection template is available.
@@ -696,8 +706,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct)
 	 */
 	if ((dest == NULL) ||
 	    !(dest->flags & IP_VS_DEST_F_AVAILABLE) ||
-	    (ipvs->sysctl_expire_quiescent_template &&
-	     (atomic_read(&dest->weight) == 0))) {
+	    expire_quiescent_template(ipvs, dest)) {
 		IP_VS_DBG_BUF(9, "check_template: dest not available for "
 			      "protocol %s s:%s:%d v:%s:%d "
 			      "-> d:%s:%d\n",
-- 
cgit v1.2.3-18-g5258


From b27d777ec54205eb56cf4e873d043a426881c629 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:01 +0900
Subject: IPVS: Conditinally use sysctl_lblc{r}_expiration

In preparation for not including sysctl_lblc{r}_expiration in
struct netns_ipvs when CONFIG_SYCTL is not defined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_lblc.c  | 16 +++++++++++++---
 net/netfilter/ipvs/ip_vs_lblcr.c | 21 +++++++++++++++------
 2 files changed, 28 insertions(+), 9 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 6bf7a807649..51a27f58030 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -63,6 +63,8 @@
 #define CHECK_EXPIRE_INTERVAL   (60*HZ)
 #define ENTRY_TIMEOUT           (6*60*HZ)
 
+#define DEFAULT_EXPIRATION	(24*60*60*HZ)
+
 /*
  *    It is for full expiration check.
  *    When there is no partial expiration check (garbage collection)
@@ -238,6 +240,15 @@ static void ip_vs_lblc_flush(struct ip_vs_lblc_table *tbl)
 	}
 }
 
+static int sysctl_lblc_expiration(struct ip_vs_service *svc)
+{
+#ifdef CONFIG_SYSCTL
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
+	return ipvs->sysctl_lblc_expiration;
+#else
+	return DEFAULT_EXPIRATION;
+#endif
+}
 
 static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
 {
@@ -245,7 +256,6 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
 	struct ip_vs_lblc_entry *en, *nxt;
 	unsigned long now = jiffies;
 	int i, j;
-	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 
 	for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
 		j = (j + 1) & IP_VS_LBLC_TAB_MASK;
@@ -254,7 +264,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
 		list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
 			if (time_before(now,
 					en->lastuse +
-					ipvs->sysctl_lblc_expiration))
+					sysctl_lblc_expiration(svc)))
 				continue;
 
 			ip_vs_lblc_free(en);
@@ -550,7 +560,7 @@ static int __net_init __ip_vs_lblc_init(struct net *net)
 			return -ENOMEM;
 	} else
 		ipvs->lblc_ctl_table = vs_vars_table;
-	ipvs->sysctl_lblc_expiration = 24*60*60*HZ;
+	ipvs->sysctl_lblc_expiration = DEFAULT_EXPIRATION;
 	ipvs->lblc_ctl_table[0].data = &ipvs->sysctl_lblc_expiration;
 
 #ifdef CONFIG_SYSCTL
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 00631765b92..7fb91906129 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -63,6 +63,8 @@
 #define CHECK_EXPIRE_INTERVAL   (60*HZ)
 #define ENTRY_TIMEOUT           (6*60*HZ)
 
+#define DEFAULT_EXPIRATION	(24*60*60*HZ)
+
 /*
  *    It is for full expiration check.
  *    When there is no partial expiration check (garbage collection)
@@ -410,6 +412,15 @@ static void ip_vs_lblcr_flush(struct ip_vs_lblcr_table *tbl)
 	}
 }
 
+static int sysctl_lblcr_expiration(struct ip_vs_service *svc)
+{
+#ifdef CONFIG_SYSCTL
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
+	return ipvs->sysctl_lblcr_expiration;
+#else
+	return DEFAULT_EXPIRATION;
+#endif
+}
 
 static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
 {
@@ -417,15 +428,14 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
 	unsigned long now = jiffies;
 	int i, j;
 	struct ip_vs_lblcr_entry *en, *nxt;
-	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 
 	for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) {
 		j = (j + 1) & IP_VS_LBLCR_TAB_MASK;
 
 		write_lock(&svc->sched_lock);
 		list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
-			if (time_after(en->lastuse
-					+ ipvs->sysctl_lblcr_expiration, now))
+			if (time_after(en->lastuse +
+				       sysctl_lblcr_expiration(svc), now))
 				continue;
 
 			ip_vs_lblcr_free(en);
@@ -650,7 +660,6 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	read_lock(&svc->sched_lock);
 	en = ip_vs_lblcr_get(svc->af, tbl, &iph.daddr);
 	if (en) {
-		struct netns_ipvs *ipvs = net_ipvs(svc->net);
 		/* We only hold a read lock, but this is atomic */
 		en->lastuse = jiffies;
 
@@ -662,7 +671,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 		/* More than one destination + enough time passed by, cleanup */
 		if (atomic_read(&en->set.size) > 1 &&
 				time_after(jiffies, en->set.lastmod +
-				ipvs->sysctl_lblcr_expiration)) {
+				sysctl_lblcr_expiration(svc))) {
 			struct ip_vs_dest *m;
 
 			write_lock(&en->set.lock);
@@ -746,7 +755,7 @@ static int __net_init __ip_vs_lblcr_init(struct net *net)
 			return -ENOMEM;
 	} else
 		ipvs->lblcr_ctl_table = vs_vars_table;
-	ipvs->sysctl_lblcr_expiration = 24*60*60*HZ;
+	ipvs->sysctl_lblcr_expiration = DEFAULT_EXPIRATION;
 	ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration;
 
 #ifdef CONFIG_SYSCTL
-- 
cgit v1.2.3-18-g5258


From a7a86b8616bc1595c4f5f109b7c39d4eb5d55e32 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:02 +0900
Subject: IPVS: Minimise ip_vs_leave when CONFIG_SYSCTL is undefined

Much of ip_vs_leave() is unnecessary if CONFIG_SYSCTL is undefined.

I tried an approach of breaking the now #ifdef'ed portions out
into a separate function. However this appeared to grow the
compiled code on x86_64 by about 200 bytes in the case where
CONFIG_SYSCTL is defined. So I have gone with the simpler though
less elegant #ifdef'ed solution for now.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_core.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index d418bc60d00..07accf6b240 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -499,11 +499,13 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		struct ip_vs_proto_data *pd)
 {
-	struct net *net;
-	struct netns_ipvs *ipvs;
 	__be16 _ports[2], *pptr;
 	struct ip_vs_iphdr iph;
+#ifdef CONFIG_SYSCTL
+	struct net *net;
+	struct netns_ipvs *ipvs;
 	int unicast;
+#endif
 
 	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
 
@@ -512,6 +514,8 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_service_put(svc);
 		return NF_DROP;
 	}
+
+#ifdef CONFIG_SYSCTL
 	net = skb_net(skb);
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -563,6 +567,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_conn_put(cp);
 		return ret;
 	}
+#endif
 
 	/*
 	 * When the virtual ftp service is presented, packets destined
-- 
cgit v1.2.3-18-g5258


From fb1de432c1c7c26afb2e86d166fc37888b6a4423 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:02 +0900
Subject: IPVS: Conditionally define and use ip_vs_lblc{r}_table

ip_vs_lblc_table and ip_vs_lblcr_table, and code that uses them
are unnecessary when CONFIG_SYSCTL is undefined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_lblc.c  | 15 ++++++++++-----
 net/netfilter/ipvs/ip_vs_lblcr.c | 14 ++++++++++----
 2 files changed, 20 insertions(+), 9 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 51a27f58030..f276df9896b 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -114,7 +114,7 @@ struct ip_vs_lblc_table {
 /*
  *      IPVS LBLC sysctl table
  */
-
+#ifdef CONFIG_SYSCTL
 static ctl_table vs_vars_table[] = {
 	{
 		.procname	= "lblc_expiration",
@@ -125,6 +125,7 @@ static ctl_table vs_vars_table[] = {
 	},
 	{ }
 };
+#endif
 
 static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en)
 {
@@ -548,6 +549,7 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler =
 /*
  *  per netns init.
  */
+#ifdef CONFIG_SYSCTL
 static int __net_init __ip_vs_lblc_init(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
@@ -563,7 +565,6 @@ static int __net_init __ip_vs_lblc_init(struct net *net)
 	ipvs->sysctl_lblc_expiration = DEFAULT_EXPIRATION;
 	ipvs->lblc_ctl_table[0].data = &ipvs->sysctl_lblc_expiration;
 
-#ifdef CONFIG_SYSCTL
 	ipvs->lblc_ctl_header =
 		register_net_sysctl_table(net, net_vs_ctl_path,
 					  ipvs->lblc_ctl_table);
@@ -572,7 +573,6 @@ static int __net_init __ip_vs_lblc_init(struct net *net)
 			kfree(ipvs->lblc_ctl_table);
 		return -ENOMEM;
 	}
-#endif
 
 	return 0;
 }
@@ -581,14 +581,19 @@ static void __net_exit __ip_vs_lblc_exit(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-#ifdef CONFIG_SYSCTL
 	unregister_net_sysctl_table(ipvs->lblc_ctl_header);
-#endif
 
 	if (!net_eq(net, &init_net))
 		kfree(ipvs->lblc_ctl_table);
 }
 
+#else
+
+static int __net_init __ip_vs_lblc_init(struct net *net) { return 0; }
+static void __net_exit __ip_vs_lblc_exit(struct net *net) { }
+
+#endif
+
 static struct pernet_operations ip_vs_lblc_ops = {
 	.init = __ip_vs_lblc_init,
 	.exit = __ip_vs_lblc_exit,
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 7fb91906129..cb1c9913d38 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -285,6 +285,7 @@ struct ip_vs_lblcr_table {
 };
 
 
+#ifdef CONFIG_SYSCTL
 /*
  *      IPVS LBLCR sysctl table
  */
@@ -299,6 +300,7 @@ static ctl_table vs_vars_table[] = {
 	},
 	{ }
 };
+#endif
 
 static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en)
 {
@@ -743,6 +745,7 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler =
 /*
  *  per netns init.
  */
+#ifdef CONFIG_SYSCTL
 static int __net_init __ip_vs_lblcr_init(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
@@ -758,7 +761,6 @@ static int __net_init __ip_vs_lblcr_init(struct net *net)
 	ipvs->sysctl_lblcr_expiration = DEFAULT_EXPIRATION;
 	ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration;
 
-#ifdef CONFIG_SYSCTL
 	ipvs->lblcr_ctl_header =
 		register_net_sysctl_table(net, net_vs_ctl_path,
 					  ipvs->lblcr_ctl_table);
@@ -767,7 +769,6 @@ static int __net_init __ip_vs_lblcr_init(struct net *net)
 			kfree(ipvs->lblcr_ctl_table);
 		return -ENOMEM;
 	}
-#endif
 
 	return 0;
 }
@@ -776,14 +777,19 @@ static void __net_exit __ip_vs_lblcr_exit(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-#ifdef CONFIG_SYSCTL
 	unregister_net_sysctl_table(ipvs->lblcr_ctl_header);
-#endif
 
 	if (!net_eq(net, &init_net))
 		kfree(ipvs->lblcr_ctl_table);
 }
 
+#else
+
+static int __net_init __ip_vs_lblcr_init(struct net *net) { return 0; }
+static void __net_exit __ip_vs_lblcr_exit(struct net *net) { }
+
+#endif
+
 static struct pernet_operations ip_vs_lblcr_ops = {
 	.init = __ip_vs_lblcr_init,
 	.exit = __ip_vs_lblcr_exit,
-- 
cgit v1.2.3-18-g5258


From 14e405461e664b777e2a5636e10b2ebf36a686ec Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Fri, 4 Feb 2011 18:33:02 +0900
Subject: IPVS: Add __ip_vs_control_{init,cleanup}_sysctl()

Break out the portions of __ip_vs_control_init() and
__ip_vs_control_cleanup() where aren't necessary when
CONFIG_SYSCTL is undefined.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 98 ++++++++++++++++++++++++++----------------
 1 file changed, 62 insertions(+), 36 deletions(-)

(limited to 'net/netfilter')

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 364520f66b7..fa6d44c62de 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -88,6 +88,8 @@ static int __ip_vs_addr_is_local_v6(struct net *net,
 	return 0;
 }
 #endif
+
+#ifdef CONFIG_SYSCTL
 /*
  *	update_defense_level is called from keventd and from sysctl,
  *	so it needs to protect itself from softirqs
@@ -229,6 +231,7 @@ static void defense_work_handler(struct work_struct *work)
 		ip_vs_random_dropentry(ipvs->net);
 	schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
 }
+#endif
 
 int
 ip_vs_use_count_inc(void)
@@ -1511,7 +1514,7 @@ static int ip_vs_zero_all(struct net *net)
 	return 0;
 }
 
-
+#ifdef CONFIG_SYSCTL
 static int
 proc_do_defense_mode(ctl_table *table, int write,
 		     void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -1533,7 +1536,6 @@ proc_do_defense_mode(ctl_table *table, int write,
 	return rc;
 }
 
-
 static int
 proc_do_sync_threshold(ctl_table *table, int write,
 		       void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -1767,6 +1769,7 @@ const struct ctl_path net_vs_ctl_path[] = {
 	{ }
 };
 EXPORT_SYMBOL_GPL(net_vs_ctl_path);
+#endif
 
 #ifdef CONFIG_PROC_FS
 
@@ -3511,7 +3514,8 @@ static void ip_vs_genl_unregister(void)
 /*
  * per netns intit/exit func.
  */
-int __net_init __ip_vs_control_init(struct net *net)
+#ifdef CONFIG_SYSCTL
+int __net_init __ip_vs_control_init_sysctl(struct net *net)
 {
 	int idx;
 	struct netns_ipvs *ipvs = net_ipvs(net);
@@ -3521,33 +3525,11 @@ int __net_init __ip_vs_control_init(struct net *net)
 	spin_lock_init(&ipvs->dropentry_lock);
 	spin_lock_init(&ipvs->droppacket_lock);
 	spin_lock_init(&ipvs->securetcp_lock);
-	ipvs->rs_lock = __RW_LOCK_UNLOCKED(ipvs->rs_lock);
-
-	/* Initialize rs_table */
-	for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
-		INIT_LIST_HEAD(&ipvs->rs_table[idx]);
-
-	INIT_LIST_HEAD(&ipvs->dest_trash);
-	atomic_set(&ipvs->ftpsvc_counter, 0);
-	atomic_set(&ipvs->nullsvc_counter, 0);
-
-	/* procfs stats */
-	ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
-	if (!ipvs->tot_stats.cpustats) {
-		pr_err("%s() alloc_percpu failed\n", __func__);
-		goto err_alloc;
-	}
-	spin_lock_init(&ipvs->tot_stats.lock);
-
-	proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
-	proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
-	proc_net_fops_create(net, "ip_vs_stats_percpu", 0,
-			     &ip_vs_stats_percpu_fops);
 
 	if (!net_eq(net, &init_net)) {
 		tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL);
 		if (tbl == NULL)
-			goto err_dup;
+			return -ENOMEM;
 	} else
 		tbl = vs_vars;
 	/* Initialize sysctl defaults */
@@ -3576,25 +3558,73 @@ int _