[PATCH 00/79] netfilter: netfilter update

[PATCH 00/79] netfilter: netfilter update

[kaber]

following is a first batch of netfilter patches for 2.6.39, containing:

- cleanups and removal of atomic operations from Changli Gao

- RCU annotations, removal of atomic operations and cleanups from Eric

- a new queue bypass option for nfnetlink_queue from Florian Westphal

- arp_tables support for xt_CLASSIFY from Frederic Leroy

- a new backup protocol for IPVS from and Schillstrom

- IPVS netns support from Hans Schillstrom

- type and header cleanups from Jan

- missing module aliases from Jan

- a new SNMP conntrack helper from Jiri Olsa

- optional timestamping for conntrack entries to simplify userspace IPFIX,
  implementations, from Pablo

- a new AUDIT target for logging packets through the audit framework,
  from Thomas

- Improvements for the IPVS persistence engine from Simon

ipset from Jozsef will follow soon, once I'm done reviewing it.

Please pull from

git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6.git master

Thanks!

[PATCH 01/79] netfilter: nf_conntrack: don't always initialize ct->proto

[kaber]

From: Changli Gao <xiaosuo@gmail.com>

ct->proto is big(60 bytes) due to structure ip_ct_tcp, and we don't need
to initialize the whole for all the other protocols. This patch moves
proto to the end of structure nf_conn, and pushes the initialization down
to the individual protocols.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_conntrack.h    |    6 +++---
 net/netfilter/nf_conntrack_core.c       |    3 ++-
 net/netfilter/nf_conntrack_netlink.c    |    1 +
 net/netfilter/nf_conntrack_proto_dccp.c |    3 +++
 net/netfilter/nf_conntrack_proto_sctp.c |    1 +
 net/netfilter/nf_conntrack_proto_tcp.c  |   14 +++-----------
 6 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index caf17db..abfff1e 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -116,14 +116,14 @@ struct nf_conn {
 	u_int32_t secmark;
 #endif
 
-	/* Storage reserved for other modules: */
-	union nf_conntrack_proto proto;
-
 	/* Extensions */
 	struct nf_ct_ext *ext;
 #ifdef CONFIG_NET_NS
 	struct net *ct_net;
 #endif
+
+	/* Storage reserved for other modules, must be the last member */
+	union nf_conntrack_proto proto;
 };
 
 static inline struct nf_conn *
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 27a5ea6..0ba7d48 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -651,7 +651,8 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
 	 * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged.
 	 */
 	memset(&ct->tuplehash[IP_CT_DIR_MAX], 0,
-	       sizeof(*ct) - offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX]));
+	       offsetof(struct nf_conn, proto) -
+	       offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX]));
 	spin_lock_init(&ct->lock);
 	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
 	ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index b729ace..7f59be8 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1375,6 +1375,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
 	}
 #endif
 
+	memset(&ct->proto, 0, sizeof(ct->proto));
 	if (cda[CTA_PROTOINFO]) {
 		err = ctnetlink_change_protoinfo(ct, cda);
 		if (err < 0)
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 5292560..9ae57c5 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -452,6 +452,9 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT;
 	ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER;
 	ct->proto.dccp.state = CT_DCCP_NONE;
+	ct->proto.dccp.last_pkt = DCCP_PKT_REQUEST;
+	ct->proto.dccp.last_dir = IP_CT_DIR_ORIGINAL;
+	ct->proto.dccp.handshake_seq = 0;
 	return true;
 
 out_invalid:
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index c6049c2..6f4ee70 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -413,6 +413,7 @@ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	    test_bit(SCTP_CID_COOKIE_ACK, map))
 		return false;
 
+	memset(&ct->proto.sctp, 0, sizeof(ct->proto.sctp));
 	new_state = SCTP_CONNTRACK_MAX;
 	for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) {
 		/* Don't need lock here: this conntrack not in circulation yet */
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 3fb2b73..6f38d0e 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1066,9 +1066,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	BUG_ON(th == NULL);
 
 	/* Don't need lock here: this conntrack not in circulation yet */
-	new_state
-		= tcp_conntracks[0][get_conntrack_index(th)]
-		[TCP_CONNTRACK_NONE];
+	new_state = tcp_conntracks[0][get_conntrack_index(th)][TCP_CONNTRACK_NONE];
 
 	/* Invalid: delete conntrack */
 	if (new_state >= TCP_CONNTRACK_MAX) {
@@ -1077,6 +1075,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	}
 
 	if (new_state == TCP_CONNTRACK_SYN_SENT) {
+		memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp));
 		/* SYN packet */
 		ct->proto.tcp.seen[0].td_end =
 			segment_seq_plus_len(ntohl(th->seq), skb->len,
@@ -1088,11 +1087,11 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 			ct->proto.tcp.seen[0].td_end;
 
 		tcp_options(skb, dataoff, th, &ct->proto.tcp.seen[0]);
-		ct->proto.tcp.seen[1].flags = 0;
 	} else if (nf_ct_tcp_loose == 0) {
 		/* Don't try to pick up connections. */
 		return false;
 	} else {
+		memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp));
 		/*
 		 * We are in the middle of a connection,
 		 * its history is lost for us.
@@ -1107,7 +1106,6 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 		ct->proto.tcp.seen[0].td_maxend =
 			ct->proto.tcp.seen[0].td_end +
 			ct->proto.tcp.seen[0].td_maxwin;
-		ct->proto.tcp.seen[0].td_scale = 0;
 
 		/* We assume SACK and liberal window checking to handle
 		 * window scaling */
@@ -1116,13 +1114,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 					      IP_CT_TCP_FLAG_BE_LIBERAL;
 	}
 
-	ct->proto.tcp.seen[1].td_end = 0;
-	ct->proto.tcp.seen[1].td_maxend = 0;
-	ct->proto.tcp.seen[1].td_maxwin = 0;
-	ct->proto.tcp.seen[1].td_scale = 0;
-
 	/* tcp_packet will set them */
-	ct->proto.tcp.state = TCP_CONNTRACK_NONE;
 	ct->proto.tcp.last_index = TCP_NONE_SET;
 
 	pr_debug("tcp_new: sender end=%u maxend=%u maxwin=%u scale=%i "
-- 
1.7.2.3

[PATCH 02/79] netfilter: xt_NFQUEUE: remove modulo operations

[kaber]

From: Changli Gao <xiaosuo@gmail.com>

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/xt_NFQUEUE.c |    6 ++++--
 1 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index 039cce1..3962770 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -72,10 +72,12 @@ nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par)
 
 	if (info->queues_total > 1) {
 		if (par->family == NFPROTO_IPV4)
-			queue = hash_v4(skb) % info->queues_total + queue;
+			queue = (((u64) hash_v4(skb) * info->queues_total) >>
+				 32) + queue;
 #if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
 		else if (par->family == NFPROTO_IPV6)
-			queue = hash_v6(skb) % info->queues_total + queue;
+			queue = (((u64) hash_v6(skb) * info->queues_total) >>
+				 32) + queue;
 #endif
 	}
 	return NF_QUEUE_NR(queue);
-- 
1.7.2.3

[PATCH 03/79] netfilter: xt_LOG: do print MAC header on FORWARD

[kaber]

From: Jan Engelhardt <jengelh@medozas.de>

I am observing consistent behavior even with bridges, so let's unlock
this. xt_mac is already usable in FORWARD, too. Section 9 of
http://ebtables.sourceforge.net/br_fw_ia/br_fw_ia.html#section9 says
the MAC source address is changed, but my observation does not match
that claim -- the MAC header is retained.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
[Patrick; code inspection seems to confirm this]
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/ipv4/netfilter/ipt_LOG.c  |    3 +--
 net/ipv6/netfilter/ip6t_LOG.c |    3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c
index 72ffc8f..d76d6c9 100644
--- a/net/ipv4/netfilter/ipt_LOG.c
+++ b/net/ipv4/netfilter/ipt_LOG.c
@@ -442,8 +442,7 @@ ipt_log_packet(u_int8_t pf,
 	}
 #endif
 
-	/* MAC logging for input path only. */
-	if (in && !out)
+	if (in != NULL)
 		dump_mac_header(m, loginfo, skb);
 
 	dump_packet(m, loginfo, skb, 0);
diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c
index 09c8889..05027b7 100644
--- a/net/ipv6/netfilter/ip6t_LOG.c
+++ b/net/ipv6/netfilter/ip6t_LOG.c
@@ -452,8 +452,7 @@ ip6t_log_packet(u_int8_t pf,
 	       in ? in->name : "",
 	       out ? out->name : "");
 
-	/* MAC logging for input path only. */
-	if (in && !out)
+	if (in != NULL)
 		dump_mac_header(m, loginfo, skb);
 
 	dump_packet(m, loginfo, skb, skb_network_offset(skb), 1);
-- 
1.7.2.3

[PATCH 04/79] netfilter: ct_extend: fix the wrong alloc_size

[kaber]

From: Changli Gao <xiaosuo@gmail.com>

In function update_alloc_size(), sizeof(struct nf_ct_ext) is added twice
wrongly.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/nf_conntrack_extend.c |    5 ++---
 1 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index bd82450..920f924 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -144,9 +144,8 @@ static void update_alloc_size(struct nf_ct_ext_type *type)
 		if (!t1)
 			continue;
 
-		t1->alloc_size = sizeof(struct nf_ct_ext)
-				 + ALIGN(sizeof(struct nf_ct_ext), t1->align)
-				 + t1->len;
+		t1->alloc_size = ALIGN(sizeof(struct nf_ct_ext), t1->align) +
+				 t1->len;
 		for (j = 0; j < NF_CT_EXT_NUM; j++) {
 			t2 = nf_ct_ext_types[j];
 			if (t2 == NULL || t2 == t1 ||
-- 
1.7.2.3

[PATCH 05/79] netfilter: nf_conntrack: define ct_*_info as needed

[kaber]

From: Changli Gao <xiaosuo@gmail.com>

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_conntrack.h |   13 +++++++++++++
 1 files changed, 13 insertions(+), 0 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index abfff1e..8a58901 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -50,11 +50,24 @@ union nf_conntrack_expect_proto {
 /* per conntrack: application helper private data */
 union nf_conntrack_help {
 	/* insert conntrack helper private data (master) here */
+#if defined(CONFIG_NF_CONNTRACK_FTP) || defined(CONFIG_NF_CONNTRACK_FTP_MODULE)
 	struct nf_ct_ftp_master ct_ftp_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_PPTP) || \
+    defined(CONFIG_NF_CONNTRACK_PPTP_MODULE)
 	struct nf_ct_pptp_master ct_pptp_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_H323) || \
+    defined(CONFIG_NF_CONNTRACK_H323_MODULE)
 	struct nf_ct_h323_master ct_h323_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_SANE) || \
+    defined(CONFIG_NF_CONNTRACK_SANE_MODULE)
 	struct nf_ct_sane_master ct_sane_info;
+#endif
+#if defined(CONFIG_NF_CONNTRACK_SIP) || defined(CONFIG_NF_CONNTRACK_SIP_MODULE)
 	struct nf_ct_sip_master ct_sip_info;
+#endif
 };
 
 #include <linux/types.h>
-- 
1.7.2.3

[PATCH 06/79] netfilter: nf_nat: don't use atomic bit operation

[kaber]

From: Changli Gao <xiaosuo@gmail.com>

As we own the conntrack and the others can't see it until we confirm it,
we don't need to use atomic bit operation on ct->status.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_nat_core.h |    4 ++--
 net/ipv4/netfilter/nf_nat_core.c    |    4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h
index 33602ab..5aec85c 100644
--- a/include/net/netfilter/nf_nat_core.h
+++ b/include/net/netfilter/nf_nat_core.h
@@ -21,9 +21,9 @@ static inline int nf_nat_initialized(struct nf_conn *ct,
 				     enum nf_nat_manip_type manip)
 {
 	if (manip == IP_NAT_MANIP_SRC)
-		return test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status);
+		return ct->status & IPS_SRC_NAT_DONE_BIT;
 	else
-		return test_bit(IPS_DST_NAT_DONE_BIT, &ct->status);
+		return ct->status & IPS_DST_NAT_DONE_BIT;
 }
 
 struct nlattr;
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index c04787c..ab877ac 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -323,9 +323,9 @@ nf_nat_setup_info(struct nf_conn *ct,
 
 	/* It's done. */
 	if (maniptype == IP_NAT_MANIP_DST)
-		set_bit(IPS_DST_NAT_DONE_BIT, &ct->status);
+		ct->status |= IPS_DST_NAT_DONE_BIT;
 	else
-		set_bit(IPS_SRC_NAT_DONE_BIT, &ct->status);
+		ct->status |= IPS_SRC_NAT_DONE_BIT;
 
 	return NF_ACCEPT;
 }
-- 
1.7.2.3

[PATCH 07/79] netfilter: ct_extend: define NF_CT_EXT_* as needed

[kaber]

From: Changli Gao <xiaosuo@gmail.com>

Less IDs make nf_ct_ext smaller.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_conntrack_ecache.h |    8 ++++++++
 include/net/netfilter/nf_conntrack_extend.h |    6 ++++++
 include/net/netfilter/nf_nat.h              |    4 ++++
 3 files changed, 18 insertions(+), 0 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index 96ba5f7..f596b60 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -23,12 +23,17 @@ struct nf_conntrack_ecache {
 static inline struct nf_conntrack_ecache *
 nf_ct_ecache_find(const struct nf_conn *ct)
 {
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
 	return nf_ct_ext_find(ct, NF_CT_EXT_ECACHE);
+#else
+	return NULL;
+#endif
 }
 
 static inline struct nf_conntrack_ecache *
 nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp)
 {
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
 	struct net *net = nf_ct_net(ct);
 	struct nf_conntrack_ecache *e;
 
@@ -45,6 +50,9 @@ nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp)
 		e->expmask = expmask;
 	}
 	return e;
+#else
+	return NULL;
+#endif
 };
 
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 0772d29..1a9f96d 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -7,10 +7,16 @@
 
 enum nf_ct_ext_id {
 	NF_CT_EXT_HELPER,
+#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE)
 	NF_CT_EXT_NAT,
+#endif
 	NF_CT_EXT_ACCT,
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
 	NF_CT_EXT_ECACHE,
+#endif
+#ifdef CONFIG_NF_CONNTRACK_ZONES
 	NF_CT_EXT_ZONE,
+#endif
 	NF_CT_EXT_NUM,
 };
 
diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index f5f09f0..e966092 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -84,7 +84,11 @@ extern int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
 
 static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct)
 {
+#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE)
 	return nf_ct_ext_find(ct, NF_CT_EXT_NAT);
+#else
+	return NULL;
+#endif
 }
 
 #else  /* !__KERNEL__: iptables wants this to compile. */
-- 
1.7.2.3

[PATCH 08/79] netfilter: nf_nat: define nat_pptp_info as needed

[kaber]

From: Changli Gao <xiaosuo@gmail.com>

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_nat.h |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index e966092..aff80b1 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -56,7 +56,9 @@ struct nf_nat_multi_range_compat {
 /* per conntrack: nat application helper private data */
 union nf_conntrack_nat_help {
 	/* insert nat helper private data here */
+#if defined(CONFIG_NF_NAT_PPTP) || defined(CONFIG_NF_NAT_PPTP_MODULE)
 	struct nf_nat_pptp nat_pptp_info;
+#endif
 };
 
 struct nf_conn;
-- 
1.7.2.3

[PATCH 09/79] netfilter: xt_CLASSIFY: add ARP support, allow CLASSIFY target on any table

[kaber]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=UTF-8, Size: 2543 bytes --]

From: Frédéric Leroy <fredo@starox.org>

Signed-off-by: Frédéric Leroy <fredo@starox.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/xt_CLASSIFY.c |   36 ++++++++++++++++++++++++------------
 1 files changed, 24 insertions(+), 12 deletions(-)

diff --git a/net/netfilter/xt_CLASSIFY.c b/net/netfilter/xt_CLASSIFY.c
index c2c0e4a..af9c4da 100644
--- a/net/netfilter/xt_CLASSIFY.c
+++ b/net/netfilter/xt_CLASSIFY.c
@@ -19,12 +19,14 @@
 #include <linux/netfilter_ipv6.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_CLASSIFY.h>
+#include <linux/netfilter_arp.h>
 
 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Xtables: Qdisc classification");
 MODULE_ALIAS("ipt_CLASSIFY");
 MODULE_ALIAS("ip6t_CLASSIFY");
+MODULE_ALIAS("arpt_CLASSIFY");
 
 static unsigned int
 classify_tg(struct sk_buff *skb, const struct xt_action_param *par)
@@ -35,26 +37,36 @@ classify_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	return XT_CONTINUE;
 }
 
-static struct xt_target classify_tg_reg __read_mostly = {
-	.name       = "CLASSIFY",
-	.revision   = 0,
-	.family     = NFPROTO_UNSPEC,
-	.table      = "mangle",
-	.hooks      = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) |
-		      (1 << NF_INET_POST_ROUTING),
-	.target     = classify_tg,
-	.targetsize = sizeof(struct xt_classify_target_info),
-	.me         = THIS_MODULE,
+static struct xt_target classify_tg_reg[] __read_mostly = {
+	{
+		.name       = "CLASSIFY",
+		.revision   = 0,
+		.family     = NFPROTO_UNSPEC,
+		.hooks      = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) |
+		              (1 << NF_INET_POST_ROUTING),
+		.target     = classify_tg,
+		.targetsize = sizeof(struct xt_classify_target_info),
+		.me         = THIS_MODULE,
+	},
+	{
+		.name       = "CLASSIFY",
+		.revision   = 0,
+		.family     = NFPROTO_ARP,
+		.hooks      = (1 << NF_ARP_OUT) | (1 << NF_ARP_FORWARD),
+		.target     = classify_tg,
+		.targetsize = sizeof(struct xt_classify_target_info),
+		.me         = THIS_MODULE,
+	},
 };
 
 static int __init classify_tg_init(void)
 {
-	return xt_register_target(&classify_tg_reg);
+	return xt_register_targets(classify_tg_reg, ARRAY_SIZE(classify_tg_reg));
 }
 
 static void __exit classify_tg_exit(void)
 {
-	xt_unregister_target(&classify_tg_reg);
+	xt_unregister_targets(classify_tg_reg, ARRAY_SIZE(classify_tg_reg));
 }
 
 module_init(classify_tg_init);
-- 
1.7.2.3

[PATCH 10/79] netfilter: add __rcu annotations

[kaber]

From: Eric Dumazet <eric.dumazet@gmail.com>

Add some __rcu annotations and use helpers to reduce number of sparse
warnings (CONFIG_SPARSE_RCU_POINTER=y)

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter.h                    |    6 +++---
 include/net/netfilter/nf_conntrack_ecache.h  |    4 ++--
 include/net/netfilter/nf_conntrack_l3proto.h |    2 +-
 net/netfilter/core.c                         |    4 ++--
 net/netfilter/nf_conntrack_expect.c          |    6 +++---
 net/netfilter/nf_conntrack_proto.c           |   20 +++++++++++++++-----
 net/netfilter/nf_conntrack_standalone.c      |    9 ++++++---
 net/netfilter/nf_log.c                       |    6 ++++--
 net/netfilter/nf_queue.c                     |   18 ++++++++++++++----
 net/netfilter/nfnetlink_log.c                |    6 +++---
 10 files changed, 53 insertions(+), 28 deletions(-)

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 89341c3..928a35e 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -265,7 +265,7 @@ struct nf_afinfo {
 	int		route_key_size;
 };
 
-extern const struct nf_afinfo *nf_afinfo[NFPROTO_NUMPROTO];
+extern const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO];
 static inline const struct nf_afinfo *nf_get_afinfo(unsigned short family)
 {
 	return rcu_dereference(nf_afinfo[family]);
@@ -355,9 +355,9 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
 #endif /*CONFIG_NETFILTER*/
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *);
+extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu;
 extern void nf_ct_attach(struct sk_buff *, struct sk_buff *);
-extern void (*nf_ct_destroy)(struct nf_conntrack *);
+extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu;
 #else
 static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {}
 #endif
diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index f596b60..8fdb04b 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -67,7 +67,7 @@ struct nf_ct_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_ct_event *item);
 };
 
-extern struct nf_ct_event_notifier *nf_conntrack_event_cb;
+extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
 extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb);
 extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb);
 
@@ -167,7 +167,7 @@ struct nf_exp_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_exp_event *item);
 };
 
-extern struct nf_exp_event_notifier *nf_expect_event_cb;
+extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
 extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb);
 extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb);
 
diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h
index a754761..e8010f4 100644
--- a/include/net/netfilter/nf_conntrack_l3proto.h
+++ b/include/net/netfilter/nf_conntrack_l3proto.h
@@ -73,7 +73,7 @@ struct nf_conntrack_l3proto {
 	struct module *me;
 };
 
-extern struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX];
+extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX];
 
 /* Protocol registration. */
 extern int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto);
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 85dabb8..5faec4f 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -212,7 +212,7 @@ EXPORT_SYMBOL(skb_make_writable);
 /* This does not belong here, but locally generated errors need it if connection
    tracking in use: without this, connection may not be in hash table, and hence
    manufactured ICMP or RST packets will not be associated with it. */
-void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *);
+void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu __read_mostly;
 EXPORT_SYMBOL(ip_ct_attach);
 
 void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb)
@@ -229,7 +229,7 @@ void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(nf_ct_attach);
 
-void (*nf_ct_destroy)(struct nf_conntrack *);
+void (*nf_ct_destroy)(struct nf_conntrack *) __rcu __read_mostly;
 EXPORT_SYMBOL(nf_ct_destroy);
 
 void nf_conntrack_destroy(struct nf_conntrack *nfct)
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 46e8966..cab196c 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -482,7 +482,7 @@ static struct hlist_node *ct_expect_get_first(struct seq_file *seq)
 	struct hlist_node *n;
 
 	for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) {
-		n = rcu_dereference(net->ct.expect_hash[st->bucket].first);
+		n = rcu_dereference(hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
 		if (n)
 			return n;
 	}
@@ -495,11 +495,11 @@ static struct hlist_node *ct_expect_get_next(struct seq_file *seq,
 	struct net *net = seq_file_net(seq);
 	struct ct_expect_iter_state *st = seq->private;
 
-	head = rcu_dereference(head->next);
+	head = rcu_dereference(hlist_next_rcu(head));
 	while (head == NULL) {
 		if (++st->bucket >= nf_ct_expect_hsize)
 			return NULL;
-		head = rcu_dereference(net->ct.expect_hash[st->bucket].first);
+		head = rcu_dereference(hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
 	}
 	return head;
 }
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index dc7bb74..03b56a0 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -166,6 +166,7 @@ static void nf_ct_l3proto_unregister_sysctl(struct nf_conntrack_l3proto *l3proto
 int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto)
 {
 	int ret = 0;
+	struct nf_conntrack_l3proto *old;
 
 	if (proto->l3proto >= AF_MAX)
 		return -EBUSY;
@@ -174,7 +175,9 @@ int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto)
 		return -EINVAL;
 
 	mutex_lock(&nf_ct_proto_mutex);
-	if (nf_ct_l3protos[proto->l3proto] != &nf_conntrack_l3proto_generic) {
+	old = rcu_dereference_protected(nf_ct_l3protos[proto->l3proto],
+					lockdep_is_held(&nf_ct_proto_mutex));
+	if (old != &nf_conntrack_l3proto_generic) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
@@ -201,7 +204,9 @@ void nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto)
 	BUG_ON(proto->l3proto >= AF_MAX);
 
 	mutex_lock(&nf_ct_proto_mutex);
-	BUG_ON(nf_ct_l3protos[proto->l3proto] != proto);
+	BUG_ON(rcu_dereference_protected(nf_ct_l3protos[proto->l3proto],
+					 lockdep_is_held(&nf_ct_proto_mutex)
+					 ) != proto);
 	rcu_assign_pointer(nf_ct_l3protos[proto->l3proto],
 			   &nf_conntrack_l3proto_generic);
 	nf_ct_l3proto_unregister_sysctl(proto);
@@ -299,8 +304,10 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto)
 		smp_wmb();
 
 		nf_ct_protos[l4proto->l3proto] = proto_array;
-	} else if (nf_ct_protos[l4proto->l3proto][l4proto->l4proto] !=
-					&nf_conntrack_l4proto_generic) {
+	} else if (rcu_dereference_protected(
+			nf_ct_protos[l4proto->l3proto][l4proto->l4proto],
+			lockdep_is_held(&nf_ct_proto_mutex)
+			) != &nf_conntrack_l4proto_generic) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
@@ -331,7 +338,10 @@ void nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *l4proto)
 	BUG_ON(l4proto->l3proto >= PF_MAX);
 
 	mutex_lock(&nf_ct_proto_mutex);
-	BUG_ON(nf_ct_protos[l4proto->l3proto][l4proto->l4proto] != l4proto);
+	BUG_ON(rcu_dereference_protected(
+			nf_ct_protos[l4proto->l3proto][l4proto->l4proto],
+			lockdep_is_held(&nf_ct_proto_mutex)
+			) != l4proto);
 	rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto],
 			   &nf_conntrack_l4proto_generic);
 	nf_ct_l4proto_unregister_sysctl(l4proto);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 0fb6570..328f1d2 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -29,6 +29,7 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <linux/rculist_nulls.h>
 
 MODULE_LICENSE("GPL");
 
@@ -56,7 +57,7 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
 	for (st->bucket = 0;
 	     st->bucket < net->ct.htable_size;
 	     st->bucket++) {
-		n = rcu_dereference(net->ct.hash[st->bucket].first);
+		n = rcu_dereference(hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
 		if (!is_a_nulls(n))
 			return n;
 	}
@@ -69,13 +70,15 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
 	struct net *net = seq_file_net(seq);
 	struct ct_iter_state *st = seq->private;
 
-	head = rcu_dereference(head->next);
+	head = rcu_dereference(hlist_nulls_next_rcu(head));
 	while (is_a_nulls(head)) {
 		if (likely(get_nulls_value(head) == st->bucket)) {
 			if (++st->bucket >= net->ct.htable_size)
 				return NULL;
 		}
-		head = rcu_dereference(net->ct.hash[st->bucket].first);
+		head = rcu_dereference(
+				hlist_nulls_first_rcu(
+					&net->ct.hash[st->bucket]));
 	}
 	return head;
 }
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index b07393e..20c775c 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -161,7 +161,8 @@ static int seq_show(struct seq_file *s, void *v)
 	struct nf_logger *t;
 	int ret;
 
-	logger = nf_loggers[*pos];
+	logger = rcu_dereference_protected(nf_loggers[*pos],
+					   lockdep_is_held(&nf_log_mutex));
 
 	if (!logger)
 		ret = seq_printf(s, "%2lld NONE (", *pos);
@@ -249,7 +250,8 @@ static int nf_log_proc_dostring(ctl_table *table, int write,
 		mutex_unlock(&nf_log_mutex);
 	} else {
 		mutex_lock(&nf_log_mutex);
-		logger = nf_loggers[tindex];
+		logger = rcu_dereference_protected(nf_loggers[tindex],
+						   lockdep_is_held(&nf_log_mutex));
 		if (!logger)
 			table->data = "NONE";
 		else
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 74aebed..1876f74 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -27,14 +27,17 @@ static DEFINE_MUTEX(queue_handler_mutex);
 int nf_register_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh)
 {
 	int ret;
+	const struct nf_queue_handler *old;
 
 	if (pf >= ARRAY_SIZE(queue_handler))
 		return -EINVAL;
 
 	mutex_lock(&queue_handler_mutex);
-	if (queue_handler[pf] == qh)
+	old = rcu_dereference_protected(queue_handler[pf],
+					lockdep_is_held(&queue_handler_mutex));
+	if (old == qh)
 		ret = -EEXIST;
-	else if (queue_handler[pf])
+	else if (old)
 		ret = -EBUSY;
 	else {
 		rcu_assign_pointer(queue_handler[pf], qh);
@@ -49,11 +52,15 @@ EXPORT_SYMBOL(nf_register_queue_handler);
 /* The caller must flush their queue before this */
 int nf_unregister_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh)
 {
+	const struct nf_queue_handler *old;
+
 	if (pf >= ARRAY_SIZE(queue_handler))
 		return -EINVAL;
 
 	mutex_lock(&queue_handler_mutex);
-	if (queue_handler[pf] && queue_handler[pf] != qh) {
+	old = rcu_dereference_protected(queue_handler[pf],
+					lockdep_is_held(&queue_handler_mutex));
+	if (old && old != qh) {
 		mutex_unlock(&queue_handler_mutex);
 		return -EINVAL;
 	}
@@ -73,7 +80,10 @@ void nf_unregister_queue_handlers(const struct nf_queue_handler *qh)
 
 	mutex_lock(&queue_handler_mutex);
 	for (pf = 0; pf < ARRAY_SIZE(queue_handler); pf++)  {
-		if (queue_handler[pf] == qh)
+		if (rcu_dereference_protected(
+				queue_handler[pf],
+				lockdep_is_held(&queue_handler_mutex)
+				) == qh)
 			rcu_assign_pointer(queue_handler[pf], NULL);
 	}
 	mutex_unlock(&queue_handler_mutex);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 6a1572b..91592da 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -874,19 +874,19 @@ static struct hlist_node *get_first(struct iter_state *st)
 
 	for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) {
 		if (!hlist_empty(&instance_table[st->bucket]))
-			return rcu_dereference_bh(instance_table[st->bucket].first);
+			return rcu_dereference_bh(hlist_first_rcu(&instance_table[st->bucket]));
 	}
 	return NULL;
 }
 
 static struct hlist_node *get_next(struct iter_state *st, struct hlist_node *h)
 {
-	h = rcu_dereference_bh(h->next);
+	h = rcu_dereference_bh(hlist_next_rcu(h));
 	while (!h) {
 		if (++st->bucket >= INSTANCE_BUCKETS)
 			return NULL;
 
-		h = rcu_dereference_bh(instance_table[st->bucket].first);
+		h = rcu_dereference_bh(hlist_first_rcu(&instance_table[st->bucket]));
 	}
 	return h;
 }
-- 
1.7.2.3

[PATCH 11/79] netfilter: nf_ct_frag6_sysctl_table is static

[kaber]

From: Eric Dumazet <eric.dumazet@gmail.com>

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/ipv6/netfilter/nf_conntrack_reasm.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 3a3f129..eb9f1c0 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -73,7 +73,7 @@ static struct inet_frags nf_frags;
 static struct netns_frags nf_init_frags;
 
 #ifdef CONFIG_SYSCTL
-struct ctl_table nf_ct_frag6_sysctl_table[] = {
+static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{
 		.procname	= "nf_conntrack_frag6_timeout",
 		.data		= &nf_init_frags.timeout,
-- 
1.7.2.3

[PATCH 12/79] netfilter: add __rcu annotations

[kaber]

From: Eric Dumazet <eric.dumazet@gmail.com>

Use helpers to reduce number of sparse warnings
(CONFIG_SPARSE_RCU_POINTER=y)

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 .../netfilter/nf_conntrack_l3proto_ipv4_compat.c   |   17 +++++++++++------
 net/ipv4/netfilter/nf_nat_core.c                   |    5 ++++-
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 37f8adb..ab9c05c 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -20,6 +20,7 @@
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_acct.h>
+#include <linux/rculist_nulls.h>
 
 struct ct_iter_state {
 	struct seq_net_private p;
@@ -35,7 +36,8 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
 	for (st->bucket = 0;
 	     st->bucket < net->ct.htable_size;
 	     st->bucket++) {
-		n = rcu_dereference(net->ct.hash[st->bucket].first);
+		n = rcu_dereference(
+			hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
 		if (!is_a_nulls(n))
 			return n;
 	}
@@ -48,13 +50,14 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
 	struct net *net = seq_file_net(seq);
 	struct ct_iter_state *st = seq->private;
 
-	head = rcu_dereference(head->next);
+	head = rcu_dereference(hlist_nulls_next_rcu(head));
 	while (is_a_nulls(head)) {
 		if (likely(get_nulls_value(head) == st->bucket)) {
 			if (++st->bucket >= net->ct.htable_size)
 				return NULL;
 		}
-		head = rcu_dereference(net->ct.hash[st->bucket].first);
+		head = rcu_dereference(
+			hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
 	}
 	return head;
 }
@@ -217,7 +220,8 @@ static struct hlist_node *ct_expect_get_first(struct seq_file *seq)
 	struct hlist_node *n;
 
 	for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) {
-		n = rcu_dereference(net->ct.expect_hash[st->bucket].first);
+		n = rcu_dereference(
+			hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
 		if (n)
 			return n;
 	}
@@ -230,11 +234,12 @@ static struct hlist_node *ct_expect_get_next(struct seq_file *seq,
 	struct net *net = seq_file_net(seq);
 	struct ct_expect_iter_state *st = seq->private;
 
-	head = rcu_dereference(head->next);
+	head = rcu_dereference(hlist_next_rcu(head));
 	while (head == NULL) {
 		if (++st->bucket >= nf_ct_expect_hsize)
 			return NULL;
-		head = rcu_dereference(net->ct.expect_hash[st->bucket].first);
+		head = rcu_dereference(
+			hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
 	}
 	return head;
 }
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index ab877ac..eb55835 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -502,7 +502,10 @@ int nf_nat_protocol_register(const struct nf_nat_protocol *proto)
 	int ret = 0;
 
 	spin_lock_bh(&nf_nat_lock);
-	if (nf_nat_protos[proto->protonum] != &nf_nat_unknown_protocol) {
+	if (rcu_dereference_protected(
+			nf_nat_protos[proto->protonum],
+			lockdep_is_held(&nf_nat_lock)
+			) != &nf_nat_unknown_protocol) {
 		ret = -EBUSY;
 		goto out;
 	}
-- 
1.7.2.3

[PATCH 13/79] netfilter: nf_nat_amanda: rename a variable

[kaber]

From: Eric Dumazet <eric.dumazet@gmail.com>

Avoid a sparse warning about 'ret' variable shadowing

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/ipv4/netfilter/nf_nat_amanda.c |    8 ++++----
 1 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c
index 0f23b3f..703f366f 100644
--- a/net/ipv4/netfilter/nf_nat_amanda.c
+++ b/net/ipv4/netfilter/nf_nat_amanda.c
@@ -44,13 +44,13 @@ static unsigned int help(struct sk_buff *skb,
 
 	/* Try to get same port: if not, try to change it. */
 	for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) {
-		int ret;
+		int res;
 
 		exp->tuple.dst.u.tcp.port = htons(port);
-		ret = nf_ct_expect_related(exp);
-		if (ret == 0)
+		res = nf_ct_expect_related(exp);
+		if (res == 0)
 			break;
-		else if (ret != -EBUSY) {
+		else if (res != -EBUSY) {
 			port = 0;
 			break;
 		}
-- 
1.7.2.3

[PATCH 14/79] netfilter: rcu sparse cleanups

[kaber]

From: Eric Dumazet <eric.dumazet@gmail.com>

Use RCU helpers to reduce number of sparse warnings
(CONFIG_SPARSE_RCU_POINTER=y), and adds lockdep checks.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/nf_conntrack_expect.c |   15 ++++++++++++---
 net/netfilter/nf_conntrack_extend.c |    6 ++++--
 net/netfilter/nf_conntrack_helper.c |   10 ++++++++--
 net/netfilter/nf_conntrack_proto.c  |    4 ++--
 4 files changed, 26 insertions(+), 9 deletions(-)

diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index cab196c..bbb2140 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -337,7 +337,10 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
 	setup_timer(&exp->timeout, nf_ct_expectation_timed_out,
 		    (unsigned long)exp);
 	if (master_help) {
-		p = &master_help->helper->expect_policy[exp->class];
+		p = &rcu_dereference_protected(
+				master_help->helper,
+				lockdep_is_held(&nf_conntrack_lock)
+				)->expect_policy[exp->class];
 		exp->timeout.expires = jiffies + p->timeout * HZ;
 	}
 	add_timer(&exp->timeout);
@@ -373,7 +376,10 @@ static inline int refresh_timer(struct nf_conntrack_expect *i)
 	if (!del_timer(&i->timeout))
 		return 0;
 
-	p = &master_help->helper->expect_policy[i->class];
+	p = &rcu_dereference_protected(
+		master_help->helper,
+		lockdep_is_held(&nf_conntrack_lock)
+		)->expect_policy[i->class];
 	i->timeout.expires = jiffies + p->timeout * HZ;
 	add_timer(&i->timeout);
 	return 1;
@@ -411,7 +417,10 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
 	}
 	/* Will be over limit? */
 	if (master_help) {
-		p = &master_help->helper->expect_policy[expect->class];
+		p = &rcu_dereference_protected(
+			master_help->helper,
+			lockdep_is_held(&nf_conntrack_lock)
+			)->expect_policy[expect->class];
 		if (p->max_expected &&
 		    master_help->expecting[expect->class] >= p->max_expected) {
 			evict_oldest_expect(master, expect);
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 920f924..80a23ed 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -140,14 +140,16 @@ static void update_alloc_size(struct nf_ct_ext_type *type)
 	/* This assumes that extended areas in conntrack for the types
 	   whose NF_CT_EXT_F_PREALLOC bit set are allocated in order */
 	for (i = min; i <= max; i++) {
-		t1 = nf_ct_ext_types[i];
+		t1 = rcu_dereference_protected(nf_ct_ext_types[i],
+				lockdep_is_held(&nf_ct_ext_type_mutex));
 		if (!t1)
 			continue;
 
 		t1->alloc_size = ALIGN(sizeof(struct nf_ct_ext), t1->align) +
 				 t1->len;
 		for (j = 0; j < NF_CT_EXT_NUM; j++) {
-			t2 = nf_ct_ext_types[j];
+			t2 = rcu_dereference_protected(nf_ct_ext_types[j],
+				lockdep_is_held(&nf_ct_ext_type_mutex));
 			if (t2 == NULL || t2 == t1 ||
 			    (t2->flags & NF_CT_EXT_F_PREALLOC) == 0)
 				continue;
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 59e1a4c..767bbe9 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -158,7 +158,10 @@ static inline int unhelp(struct nf_conntrack_tuple_hash *i,
 	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i);
 	struct nf_conn_help *help = nfct_help(ct);
 
-	if (help && help->helper == me) {
+	if (help && rcu_dereference_protected(
+			help->helper,
+			lockdep_is_held(&nf_conntrack_lock)
+			) == me) {
 		nf_conntrack_event(IPCT_HELPER, ct);
 		rcu_assign_pointer(help->helper, NULL);
 	}
@@ -210,7 +213,10 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me,
 		hlist_for_each_entry_safe(exp, n, next,
 					  &net->ct.expect_hash[i], hnode) {
 			struct nf_conn_help *help = nfct_help(exp->master);
-			if ((help->helper == me || exp->helper == me) &&
+			if ((rcu_dereference_protected(
+					help->helper,
+					lockdep_is_held(&nf_conntrack_lock)
+					) == me || exp->helper == me) &&
 			    del_timer(&exp->timeout)) {
 				nf_ct_unlink_expect(exp);
 				nf_ct_expect_put(exp);
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 03b56a0..5701c8d 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -284,7 +284,7 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto)
 	mutex_lock(&nf_ct_proto_mutex);
 	if (!nf_ct_protos[l4proto->l3proto]) {
 		/* l3proto may be loaded latter. */
-		struct nf_conntrack_l4proto **proto_array;
+		struct nf_conntrack_l4proto __rcu **proto_array;
 		int i;
 
 		proto_array = kmalloc(MAX_NF_CT_PROTO *
@@ -296,7 +296,7 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto)
 		}
 
 		for (i = 0; i < MAX_NF_CT_PROTO; i++)
-			proto_array[i] = &nf_conntrack_l4proto_generic;
+			RCU_INIT_POINTER(proto_array[i], &nf_conntrack_l4proto_generic);
 
 		/* Before making proto_array visible to lockless readers,
 		 * we must make sure its content is committed to memory.
-- 
1.7.2.3

[PATCH 15/79] IPVS: Add persistence engine to connection entry

[kaber]

From: Simon Horman <horms@verge.net.au>

The dest of a connection may not exist if it has been created as the result
of connection synchronisation. But in order for connection entries for
templates with persistence engine data created through connection
synchronisation to be valid access to the persistence engine pointer is
required.  So add the persistence engine to the connection itself.

Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |   16 ++++++++++++++--
 net/netfilter/ipvs/ip_vs_conn.c |   19 ++++++++++---------
 net/netfilter/ipvs/ip_vs_ctl.c  |    4 ++--
 net/netfilter/ipvs/ip_vs_pe.c   |   14 ++++----------
 4 files changed, 30 insertions(+), 23 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index b7bbd6c..be2b569 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -422,6 +422,7 @@ struct ip_vs_conn {
 	struct ip_vs_seq        in_seq;         /* incoming seq. struct */
 	struct ip_vs_seq        out_seq;        /* outgoing seq. struct */
 
+	const struct ip_vs_pe	*pe;
 	char			*pe_data;
 	__u8			pe_data_len;
 };
@@ -814,8 +815,19 @@ void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe);
 void ip_vs_unbind_pe(struct ip_vs_service *svc);
 int register_ip_vs_pe(struct ip_vs_pe *pe);
 int unregister_ip_vs_pe(struct ip_vs_pe *pe);
-extern struct ip_vs_pe *ip_vs_pe_get(const char *name);
-extern void ip_vs_pe_put(struct ip_vs_pe *pe);
+struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
+
+static inline void ip_vs_pe_get(const struct ip_vs_pe *pe)
+{
+	if (pe && pe->module)
+		__module_get(pe->module);
+}
+
+static inline void ip_vs_pe_put(const struct ip_vs_pe *pe)
+{
+	if (pe && pe->module)
+		module_put(pe->module);
+}
 
 /*
  *	IPVS protocol functions (from ip_vs_proto.c)
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index e9adecd..64a9ca3 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -176,8 +176,8 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
 	ip_vs_conn_fill_param(cp->af, cp->protocol, &cp->caddr, cp->cport,
 			      NULL, 0, &p);
 
-	if (cp->dest && cp->dest->svc->pe) {
-		p.pe = cp->dest->svc->pe;
+	if (cp->pe) {
+		p.pe = cp->pe;
 		p.pe_data = cp->pe_data;
 		p.pe_data_len = cp->pe_data_len;
 	}
@@ -765,6 +765,7 @@ static void ip_vs_conn_expire(unsigned long data)
 		if (cp->flags & IP_VS_CONN_F_NFCT)
 			ip_vs_conn_drop_conntrack(cp);
 
+		ip_vs_pe_put(cp->pe);
 		kfree(cp->pe_data);
 		if (unlikely(cp->app != NULL))
 			ip_vs_unbind_app(cp);
@@ -826,7 +827,9 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 			&cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
-	if (flags & IP_VS_CONN_F_TEMPLATE && p->pe_data) {
+	if (flags & IP_VS_CONN_F_TEMPLATE && p->pe) {
+		ip_vs_pe_get(p->pe);
+		cp->pe = p->pe;
 		cp->pe_data = p->pe_data;
 		cp->pe_data_len = p->pe_data_len;
 	}
@@ -958,15 +961,13 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
 		char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3];
 		size_t len = 0;
 
-		if (cp->dest && cp->pe_data &&
-		    cp->dest->svc->pe->show_pe_data) {
+		if (cp->pe_data) {
 			pe_data[0] = ' ';
-			len = strlen(cp->dest->svc->pe->name);
-			memcpy(pe_data + 1, cp->dest->svc->pe->name, len);
+			len = strlen(cp->pe->name);
+			memcpy(pe_data + 1, cp->pe->name, len);
 			pe_data[len + 1] = ' ';
 			len += 2;
-			len += cp->dest->svc->pe->show_pe_data(cp,
-							       pe_data + len);
+			len += cp->pe->show_pe_data(cp, pe_data + len);
 		}
 		pe_data[len] = '\0';
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5f5daa3..3e92558 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1139,7 +1139,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u,
 	}
 
 	if (u->pe_name && *u->pe_name) {
-		pe = ip_vs_pe_get(u->pe_name);
+		pe = ip_vs_pe_getbyname(u->pe_name);
 		if (pe == NULL) {
 			pr_info("persistence engine module ip_vs_pe_%s "
 				"not found\n", u->pe_name);
@@ -1250,7 +1250,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 	old_sched = sched;
 
 	if (u->pe_name && *u->pe_name) {
-		pe = ip_vs_pe_get(u->pe_name);
+		pe = ip_vs_pe_getbyname(u->pe_name);
 		if (pe == NULL) {
 			pr_info("persistence engine module ip_vs_pe_%s "
 				"not found\n", u->pe_name);
diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c
index 3414af7..e99f920 100644
--- a/net/netfilter/ipvs/ip_vs_pe.c
+++ b/net/netfilter/ipvs/ip_vs_pe.c
@@ -30,7 +30,7 @@ void ip_vs_unbind_pe(struct ip_vs_service *svc)
 
 /* Get pe in the pe list by name */
 static struct ip_vs_pe *
-ip_vs_pe_getbyname(const char *pe_name)
+__ip_vs_pe_getbyname(const char *pe_name)
 {
 	struct ip_vs_pe *pe;
 
@@ -60,28 +60,22 @@ ip_vs_pe_getbyname(const char *pe_name)
 }
 
 /* Lookup pe and try to load it if it doesn't exist */
-struct ip_vs_pe *ip_vs_pe_get(const char *name)
+struct ip_vs_pe *ip_vs_pe_getbyname(const char *name)
 {
 	struct ip_vs_pe *pe;
 
 	/* Search for the pe by name */
-	pe = ip_vs_pe_getbyname(name);
+	pe = __ip_vs_pe_getbyname(name);
 
 	/* If pe not found, load the module and search again */
 	if (!pe) {
 		request_module("ip_vs_pe_%s", name);
-		pe = ip_vs_pe_getbyname(name);
+		pe = __ip_vs_pe_getbyname(name);
 	}
 
 	return pe;
 }
 
-void ip_vs_pe_put(struct ip_vs_pe *pe)
-{
-	if (pe && pe->module)
-		module_put(pe->module);
-}
-
 /* Register a pe in the pe list */
 int register_ip_vs_pe(struct ip_vs_pe *pe)
 {
-- 
1.7.2.3

[PATCH 16/79] IPVS: Only match pe_data created by the same pe

[kaber]

From: Simon Horman <horms@verge.net.au>

Only match persistence engine data if it was
created by the same persistence engine.

Reported-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_conn.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 64a9ca3..261db1a 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -354,7 +354,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
 		if (p->pe_data && p->pe->ct_match) {
-			if (p->pe->ct_match(p, cp))
+			if (p->pe == cp->pe && p->pe->ct_match(p, cp))
 				goto out;
 			continue;
 		}
-- 
1.7.2.3

[PATCH 17/79] IPVS: Make the cp argument to ip_vs_sync_conn() static

[kaber]

From: Simon Horman <horms@verge.net.au>

Acked-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |    2 +-
 net/netfilter/ipvs/ip_vs_sync.c |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index be2b569..d5a32e4 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -916,7 +916,7 @@ extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
 extern int stop_sync_thread(int state);
-extern void ip_vs_sync_conn(struct ip_vs_conn *cp);
+extern void ip_vs_sync_conn(const struct ip_vs_conn *cp);
 
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index ab85aed..a4dccbc 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -236,7 +236,7 @@ get_curr_sync_buff(unsigned long time)
  *      Add an ip_vs_conn information into the current sync_buff.
  *      Called by ip_vs_in.
  */
-void ip_vs_sync_conn(struct ip_vs_conn *cp)
+void ip_vs_sync_conn(const struct ip_vs_conn *cp)
 {
 	struct ip_vs_sync_mesg *m;
 	struct ip_vs_sync_conn *s;
-- 
1.7.2.3

[PATCH 18/79] IPVS: Remove useless { } block from ip_vs_process_message()

[kaber]

From: Simon Horman <horms@verge.net.au>

Acked-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_sync.c |   24 +++++++++++-------------
 1 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index a4dccbc..72b3d88 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -381,20 +381,18 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
 			}
 		}
 
-		{
-			if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
-					      (union nf_inet_addr *)&s->caddr,
-					      s->cport,
-					      (union nf_inet_addr *)&s->vaddr,
-					      s->vport, &param)) {
-				pr_err("ip_vs_conn_fill_param_sync failed");
-				return;
-			}
-			if (!(flags & IP_VS_CONN_F_TEMPLATE))
-				cp = ip_vs_conn_in_get(&param);
-			else
-				cp = ip_vs_ct_in_get(&param);
+		if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
+					       (union nf_inet_addr *)&s->caddr,
+					       s->cport,
+					       (union nf_inet_addr *)&s->vaddr,
+					       s->vport, &param)) {
+			pr_err("ip_vs_conn_fill_param_sync failed");
+			return;
 		}
+		if (!(flags & IP_VS_CONN_F_TEMPLATE))
+			cp = ip_vs_conn_in_get(&param);
+		else
+			cp = ip_vs_ct_in_get(&param);
 		if (!cp) {
 			/*
 			 * Find the appropriate destination for the connection.
-- 
1.7.2.3

Re: [PATCH 18/79] IPVS: Remove useless { } block from ip_vs_process_message()

[Joe Perches]

On Wed, 2011-01-19 at 20:14 +0100, kaber@trash.net wrote:
> From: Simon Horman <horms@verge.net.au>
>  net/netfilter/ipvs/ip_vs_sync.c |   24 +++++++++++-------------
> diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
> @@ -381,20 +381,18 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
>  			}
>  		}
>  
> -		{
> -			if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
> -					      (union nf_inet_addr *)&s->caddr,
> -					      s->cport,
> -					      (union nf_inet_addr *)&s->vaddr,
> -					      s->vport, &param)) {
> -				pr_err("ip_vs_conn_fill_param_sync failed");
> -				return;
> -			}
> -			if (!(flags & IP_VS_CONN_F_TEMPLATE))
> -				cp = ip_vs_conn_in_get(&param);
> -			else
> -				cp = ip_vs_ct_in_get(&param);
> +		if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
> +					       (union nf_inet_addr *)&s->caddr,
> +					       s->cport,
> +					       (union nf_inet_addr *)&s->vaddr,
> +					       s->vport, &param)) {
> +			pr_err("ip_vs_conn_fill_param_sync failed");

The original and this pr_err is missing a \n before close quote.

Re: [PATCH 18/79] IPVS: Remove useless { } block from ip_vs_process_message()

[Simon Horman]

On Wed, Jan 19, 2011 at 11:40:52AM -0800, Joe Perches wrote:
> On Wed, 2011-01-19 at 20:14 +0100, kaber@trash.net wrote:
> > From: Simon Horman <horms@verge.net.au>
> >  net/netfilter/ipvs/ip_vs_sync.c |   24 +++++++++++-------------
> > diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
> > @@ -381,20 +381,18 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
> >  			}
> >  		}
> >  
> > -		{
> > -			if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
> > -					      (union nf_inet_addr *)&s->caddr,
> > -					      s->cport,
> > -					      (union nf_inet_addr *)&s->vaddr,
> > -					      s->vport, &param)) {
> > -				pr_err("ip_vs_conn_fill_param_sync failed");
> > -				return;
> > -			}
> > -			if (!(flags & IP_VS_CONN_F_TEMPLATE))
> > -				cp = ip_vs_conn_in_get(&param);
> > -			else
> > -				cp = ip_vs_ct_in_get(&param);
> > +		if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
> > +					       (union nf_inet_addr *)&s->caddr,
> > +					       s->cport,
> > +					       (union nf_inet_addr *)&s->vaddr,
> > +					       s->vport, &param)) {
> > +			pr_err("ip_vs_conn_fill_param_sync failed");
> 
> The original and this pr_err is missing a \n before close quote.

Thanks Joe, I'll get this fixed once nf-next-2.6 opens up again.

Re: [PATCH 18/79] IPVS: Remove useless { } block from ip_vs_process_message()

[Simon Horman]

On Tue, Jan 25, 2011 at 12:10:00PM +1000, Simon Horman wrote:
> On Wed, Jan 19, 2011 at 11:40:52AM -0800, Joe Perches wrote:
> > On Wed, 2011-01-19 at 20:14 +0100, kaber@trash.net wrote:
> > > From: Simon Horman <horms@verge.net.au>
> > >  net/netfilter/ipvs/ip_vs_sync.c |   24 +++++++++++-------------
> > > diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
> > > @@ -381,20 +381,18 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
> > >  			}
> > >  		}
> > >  
> > > -		{
> > > -			if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
> > > -					      (union nf_inet_addr *)&s->caddr,
> > > -					      s->cport,
> > > -					      (union nf_inet_addr *)&s->vaddr,
> > > -					      s->vport, &param)) {
> > > -				pr_err("ip_vs_conn_fill_param_sync failed");
> > > -				return;
> > > -			}
> > > -			if (!(flags & IP_VS_CONN_F_TEMPLATE))
> > > -				cp = ip_vs_conn_in_get(&param);
> > > -			else
> > > -				cp = ip_vs_ct_in_get(&param);
> > > +		if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
> > > +					       (union nf_inet_addr *)&s->caddr,
> > > +					       s->cport,
> > > +					       (union nf_inet_addr *)&s->vaddr,
> > > +					       s->vport, &param)) {
> > > +			pr_err("ip_vs_conn_fill_param_sync failed");
> > 
> > The original and this pr_err is missing a \n before close quote.
> 
> Thanks Joe, I'll get this fixed once nf-next-2.6 opens up again.

On closer inspection this line has subsequently been removed.
I also checked and the string passed to all calls to pr_erri()
in that file end in "\n".

[PATCH 19/79] IPVS: buffer argument to ip_vs_process_message() should not be const

[kaber]

From: Simon Horman <horms@verge.net.au>

It is assigned to a non-const variable and its contents are modified.

Acked-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_sync.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 72b3d88..3897d6b 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -303,7 +303,7 @@ ip_vs_conn_fill_param_sync(int af, int protocol,
  *      Process received multicast message and create the corresponding
  *      ip_vs_conn entries.
  */
-static void ip_vs_process_message(const char *buffer, const size_t buflen)
+static void ip_vs_process_message(char *buffer, const size_t buflen)
 {
 	struct ip_vs_sync_mesg *m = (struct ip_vs_sync_mesg *)buffer;
 	struct ip_vs_sync_conn *s;
-- 
1.7.2.3

[PATCH 20/79] ipvs: add static and read_mostly attributes

[kaber]

From: Eric Dumazet <eric.dumazet@gmail.com>

ip_vs_conn_tab_bits & ip_vs_conn_tab_mask are static to
ipvs/ip_vs_conn.c

ip_vs_conn_tab_size, ip_vs_conn_tab_mask, ip_vs_conn_tab [the pointer],
ip_vs_conn_rnd are mostly read.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_conn.c |   10 +++++-----
 1 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 261db1a..7615f9e 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -48,18 +48,18 @@
 /*
  * Connection hash size. Default is what was selected at compile time.
 */
-int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
+static int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
 module_param_named(conn_tab_bits, ip_vs_conn_tab_bits, int, 0444);
 MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size");
 
 /* size and mask values */
-int ip_vs_conn_tab_size;
-int ip_vs_conn_tab_mask;
+int ip_vs_conn_tab_size __read_mostly;
+static int ip_vs_conn_tab_mask __read_mostly;
 
 /*
  *  Connection hash table: for input and output packets lookups of IPVS
  */
-static struct list_head *ip_vs_conn_tab;
+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;
@@ -71,7 +71,7 @@ static atomic_t ip_vs_conn_count = ATOMIC_INIT(0);
 static atomic_t ip_vs_conn_no_cport_cnt = ATOMIC_INIT(0);
 
 /* random value for IPVS connection hash */
-static unsigned int ip_vs_conn_rnd;
+static unsigned int ip_vs_conn_rnd __read_mostly;
 
 /*
  *  Fine locking granularity for big connection hash table
-- 
1.7.2.3

[PATCH 21/79] ipvs: remove shadow rt variable

[kaber]

From: Eric Dumazet <eric.dumazet@gmail.com>

Remove a sparse warning about rt variable.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_xmit.c |    1 -
 1 files changed, 0 insertions(+), 1 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 10bd39c..50b131c 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -188,7 +188,6 @@ __ip_vs_reroute_locally(struct sk_buff *skb)
 			},
 			.mark = skb->mark,
 		};
-		struct rtable *rt;
 
 		if (ip_route_output_key(net, &rt, &fl))
 			return 0;
-- 
1.7.2.3

[PATCH 22/79] ipvs: allow transmit of GRO aggregated skbs

[kaber]

From: Simon Horman <horms@verge.net.au>

Attempt at allowing LVS to transmit skbs of greater than MTU length that
have been aggregated by GRO and can thus be deaggregated by GSO.

Cc: Julian Anastasov <ja@ssi.bg>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_xmit.c |   25 +++++++++++++++----------
 1 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 50b131c..fb2a445 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -407,7 +407,8 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) {
+	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
+	    !skb_is_gso(skb)) {
 		ip_rt_put(rt);
 		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
@@ -460,7 +461,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if (skb->len > mtu) {
+	if (skb->len > mtu && !skb_is_gso(skb)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -560,7 +561,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) {
+	if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
+	    !skb_is_gso(skb)) {
 		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
 		IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0,
 				 "ip_vs_nat_xmit(): frag needed for");
@@ -675,7 +677,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if (skb->len > mtu) {
+	if (skb->len > mtu && !skb_is_gso(skb)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -790,8 +792,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	df |= (old_iph->frag_off & htons(IP_DF));
 
-	if ((old_iph->frag_off & htons(IP_DF))
-	    && mtu < ntohs(old_iph->tot_len)) {
+	if ((old_iph->frag_off & htons(IP_DF) &&
+	    mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
 		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;
@@ -903,7 +905,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	if (skb_dst(skb))
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
 
-	if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) {
+	if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) &&
+	    !skb_is_gso(skb)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -1008,7 +1011,8 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) {
+	if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu &&
+	    !skb_is_gso(skb)) {
 		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
 		ip_rt_put(rt);
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
@@ -1175,7 +1179,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF))) {
+	if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF)) &&
+	    !skb_is_gso(skb)) {
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;
@@ -1289,7 +1294,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	/* MTU checking */
 	mtu = dst_mtu(&rt->dst);
-	if (skb->len > mtu) {
+	if (skb->len > mtu && !skb_is_gso(skb)) {
 		if (!skb->dev) {
 			struct net *net = dev_net(skb_dst(skb)->dev);
 
-- 
1.7.2.3

[PATCH 23/79] netfilter: nf_conntrack: one less atomic op in nf_ct_expect_insert()

[kaber]

From: Eric Dumazet <eric.dumazet@gmail.com>

Instead of doing atomic_inc(&exp->use) twice,
call atomic_add(2, &exp->use);

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/nf_conntrack_expect.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index bbb2140..774f32b 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -323,7 +323,8 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
 	const struct nf_conntrack_expect_policy *p;
 	unsigned int h = nf_ct_expect_dst_hash(&exp->tuple);
 
-	atomic_inc(&exp->use);
+	/* two references : one for hash insert, one for the timer */
+	atomic_add(2, &exp->use);
 
 	if (master_help) {
 		hlist_add_head(&exp->lnode, &master_help->expectations);
@@ -345,7 +346,6 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp)
 	}
 	add_timer(&exp->timeout);
 
-	atomic_inc(&exp->use);
 	NF_CT_STAT_INC(net, expect_create);
 }
 
-- 
1.7.2.3

[PATCH 24/79] IPVS: Backup, Prepare for transferring firewall marks (fwmark) to the backup daemon.

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

One struct will have fwmark added:
 * ip_vs_conn

ip_vs_conn_new() and ip_vs_find_dest()
will have an extra param - fwmark
The effects of that, is in this patch.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |    6 ++++--
 net/netfilter/ipvs/ip_vs_conn.c |    5 +++--
 net/netfilter/ipvs/ip_vs_core.c |    8 ++++----
 net/netfilter/ipvs/ip_vs_ctl.c  |    4 ++--
 net/netfilter/ipvs/ip_vs_ftp.c  |    5 +++--
 net/netfilter/ipvs/ip_vs_sync.c |    4 ++--
 6 files changed, 18 insertions(+), 14 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index d5a32e4..890f01c 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -382,6 +382,7 @@ struct ip_vs_conn {
 	union nf_inet_addr       vaddr;          /* virtual address */
 	union nf_inet_addr       daddr;          /* destination address */
 	volatile __u32           flags;          /* status flags */
+	__u32                    fwmark;         /* Fire wall mark from skb */
 	__be16                   cport;
 	__be16                   vport;
 	__be16                   dport;
@@ -720,7 +721,7 @@ extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
 struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p,
 				  const union nf_inet_addr *daddr,
 				  __be16 dport, unsigned flags,
-				  struct ip_vs_dest *dest);
+				  struct ip_vs_dest *dest, __u32 fwmark);
 extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
 
 extern const char * ip_vs_state_name(__u16 proto, int state);
@@ -901,7 +902,8 @@ extern int ip_vs_control_init(void);
 extern void ip_vs_control_cleanup(void);
 extern struct ip_vs_dest *
 ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport,
-		const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol);
+		const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol,
+		__u32 fwmark);
 extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
 
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 7615f9e..66e4662 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -613,7 +613,7 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
 	if ((cp) && (!cp->dest)) {
 		dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport,
 				       &cp->vaddr, cp->vport,
-				       cp->protocol);
+				       cp->protocol, cp->fwmark);
 		ip_vs_bind_dest(cp, dest);
 		return dest;
 	} else
@@ -803,7 +803,7 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
 struct ip_vs_conn *
 ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	       const union nf_inet_addr *daddr, __be16 dport, unsigned flags,
-	       struct ip_vs_dest *dest)
+	       struct ip_vs_dest *dest, __u32 fwmark)
 {
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp = ip_vs_proto_get(p->protocol);
@@ -827,6 +827,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 			&cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
+	cp->fwmark         = fwmark;
 	if (flags & IP_VS_CONN_F_TEMPLATE && p->pe) {
 		ip_vs_pe_get(p->pe);
 		cp->pe = p->pe;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index b4e51e9..e2bb3cd 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -293,7 +293,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		 * and thus param.pe_data will be destroyed
 		 * when the template expires */
 		ct = ip_vs_conn_new(&param, &dest->addr, dport,
-				    IP_VS_CONN_F_TEMPLATE, dest);
+				    IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
 		if (ct == NULL) {
 			kfree(param.pe_data);
 			return NULL;
@@ -319,7 +319,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	 */
 	ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, ports[0],
 			      &iph.daddr, ports[1], &param);
-	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest);
+	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
 	if (cp == NULL) {
 		ip_vs_conn_put(ct);
 		return NULL;
@@ -423,7 +423,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 				      pptr[0], &iph.daddr, pptr[1], &p);
 		cp = ip_vs_conn_new(&p, &dest->addr,
 				    dest->port ? dest->port : pptr[1],
-				    flags, dest);
+				    flags, dest, skb->mark);
 		if (!cp)
 			return NULL;
 	}
@@ -489,7 +489,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 					      &iph.daddr, pptr[1], &p);
 			cp = ip_vs_conn_new(&p, &daddr, 0,
 					    IP_VS_CONN_F_BYPASS | flags,
-					    NULL);
+					    NULL, skb->mark);
 			if (!cp)
 				return NF_DROP;
 		}
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 3e92558..a5bd002 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -657,12 +657,12 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
 struct ip_vs_dest *ip_vs_find_dest(int af, const union nf_inet_addr *daddr,
 				   __be16 dport,
 				   const union nf_inet_addr *vaddr,
-				   __be16 vport, __u16 protocol)
+				   __be16 vport, __u16 protocol, __u32 fwmark)
 {
 	struct ip_vs_dest *dest;
 	struct ip_vs_service *svc;
 
-	svc = ip_vs_service_get(af, 0, protocol, vaddr, vport);
+	svc = ip_vs_service_get(af, fwmark, protocol, vaddr, vport);
 	if (!svc)
 		return NULL;
 	dest = ip_vs_lookup_dest(svc, daddr, dport);
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 7545500..84aef65 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -208,7 +208,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 			n_cp = ip_vs_conn_new(&p, &from, port,
 					      IP_VS_CONN_F_NO_CPORT |
 					      IP_VS_CONN_F_NFCT,
-					      cp->dest);
+					      cp->dest, skb->mark);
 			if (!n_cp)
 				return 0;
 
@@ -365,7 +365,8 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		if (!n_cp) {
 			n_cp = ip_vs_conn_new(&p, &cp->daddr,
 					      htons(ntohs(cp->dport)-1),
-					      IP_VS_CONN_F_NFCT, cp->dest);
+					      IP_VS_CONN_F_NFCT, cp->dest,
+					      skb->mark);
 			if (!n_cp)
 				return 0;
 
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 3897d6b..47eed67 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -404,7 +404,7 @@ static void ip_vs_process_message(char *buffer, const size_t buflen)
 					       s->dport,
 					       (union nf_inet_addr *)&s->vaddr,
 					       s->vport,
-					       s->protocol);
+					       s->protocol, 0);
 			/*  Set the approprite ativity flag */
 			if (s->protocol == IPPROTO_TCP) {
 				if (state != IP_VS_TCP_S_ESTABLISHED)
@@ -419,7 +419,7 @@ static void ip_vs_process_message(char *buffer, const size_t buflen)
 			}
 			cp = ip_vs_conn_new(&param,
 					    (union nf_inet_addr *)&s->daddr,
-					    s->dport, flags, dest);
+					    s->dport, flags, dest, 0);
 			if (dest)
 				atomic_dec(&dest->refcnt);
 			if (!cp) {
-- 
1.7.2.3

[PATCH 25/79] IPVS: Split ports[2] into src_port and dst_port

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

Avoid sending invalid pointer due to skb_linearize() call.
This patch prepares for next patch where skb_linearize is a part.

In ip_vs_sched_persist() params the ports ptr will be replaced by
src and dst port.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_core.c |   21 +++++++++++----------
 1 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index e2bb3cd..9acdd79 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -200,7 +200,7 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
 static struct ip_vs_conn *
 ip_vs_sched_persist(struct ip_vs_service *svc,
 		    struct sk_buff *skb,
-		    __be16 ports[2])
+		    __be16 src_port, __be16 dst_port)
 {
 	struct ip_vs_conn *cp = NULL;
 	struct ip_vs_iphdr iph;
@@ -224,8 +224,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 
 	IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u "
 		      "mnet %s\n",
-		      IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(ports[0]),
-		      IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(ports[1]),
+		      IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(src_port),
+		      IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(dst_port),
 		      IP_VS_DBG_ADDR(svc->af, &snet));
 
 	/*
@@ -247,14 +247,14 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) };
 		__be16 vport = 0;
 
-		if (ports[1] == svc->port) {
+		if (dst_port == svc->port) {
 			/* non-FTP template:
 			 * <protocol, caddr, 0, vaddr, vport, daddr, dport>
 			 * FTP template:
 			 * <protocol, caddr, 0, vaddr, 0, daddr, 0>
 			 */
 			if (svc->port != FTPPORT)
-				vport = ports[1];
+				vport = dst_port;
 		} else {
 			/* Note: persistent fwmark-based services and
 			 * persistent port zero service are handled here.
@@ -285,7 +285,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 			return NULL;
 		}
 
-		if (ports[1] == svc->port && svc->port != FTPPORT)
+		if (dst_port == svc->port && svc->port != FTPPORT)
 			dport = dest->port;
 
 		/* Create a template
@@ -306,7 +306,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		kfree(param.pe_data);
 	}
 
-	dport = ports[1];
+	dport = dst_port;
 	if (dport == svc->port && dest->port)
 		dport = dest->port;
 
@@ -317,8 +317,9 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	/*
 	 *    Create a new connection according to the template
 	 */
-	ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, ports[0],
-			      &iph.daddr, ports[1], &param);
+	ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, src_port,
+			      &iph.daddr, dst_port, &param);
+
 	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
 	if (cp == NULL) {
 		ip_vs_conn_put(ct);
@@ -388,7 +389,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	 */
 	if (svc->flags & IP_VS_SVC_F_PERSISTENT) {
 		*ignored = 0;
-		return ip_vs_sched_persist(svc, skb, pptr);
+		return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1]);
 	}
 
 	/*
-- 
1.7.2.3

[PATCH 26/79] IPVS: skb defrag in L7 helpers

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

L7 helpers like sip needs skb defrag
since L7 data can be fragmented.

This patch requires "IPVS Break ports-2 into src_port and dst_port" patch

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_pe_sip.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index b8b4e96..0d83bc0 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -71,6 +71,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	struct ip_vs_iphdr iph;
 	unsigned int dataoff, datalen, matchoff, matchlen;
 	const char *dptr;
+	int retc;
 
 	ip_vs_fill_iphdr(p->af, skb_network_header(skb), &iph);
 
@@ -83,6 +84,8 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	if (dataoff >= skb->len)
 		return -EINVAL;
 
+	if ((retc=skb_linearize(skb)) < 0)
+		return retc;
 	dptr = skb->data + dataoff;
 	datalen = skb->len - dataoff;
 
-- 
1.7.2.3

[PATCH 27/79] IPVS: Handle Scheduling errors.

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

If ip_vs_conn_fill_param_persist return an error to ip_vs_sched_persist,
this error must propagate as ignored=-1 to ip_vs_schedule().
Errors from ip_vs_conn_new() in ip_vs_sched_persist() and ip_vs_schedule()
should also return *ignored=-1;

This patch just relies on the fact that ignored is 1 before calling
ip_vs_sched_persist().

Sent from Julian:
  "The new case when ip_vs_conn_fill_param_persist fails
   should set *ignored = -1, so that we can use NF_DROP,
   see below. *ignored = -1 should be also used for ip_vs_conn_new
   failure in ip_vs_sched_persist() and ip_vs_schedule().
   The new negative value should be handled in tcp,udp,sctp"

"To summarize:

- *ignored = 1:
      protocol tried to schedule (eg. on SYN), found svc but the
      svc/scheduler decides that this packet should be accepted with
      NF_ACCEPT because it must not be scheduled.

- *ignored = 0:
      scheduler can not find destination, so try bypass or
      return ICMP and then NF_DROP (ip_vs_leave).

- *ignored = -1:
      scheduler tried to schedule but fatal error occurred, eg.
      ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param
      failure such as missing Call-ID, ENOMEM on skb_linearize
      or pe_data. In this case we should return NF_DROP without
      any attempts to send ICMP with ip_vs_leave."

More or less all ideas and input to this patch is work from
Julian Anastasov

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_core.c       |   56 +++++++++++++++++++++++---------
 net/netfilter/ipvs/ip_vs_proto_sctp.c |   11 +++++--
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |   10 +++++-
 net/netfilter/ipvs/ip_vs_proto_udp.c  |   10 +++++-
 4 files changed, 64 insertions(+), 23 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 9acdd79..3445da6 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -177,7 +177,7 @@ ip_vs_set_state(struct ip_vs_conn *cp, int direction,
 	return pp->state_transition(cp, direction, skb, pp);
 }
 
-static inline void
+static inline int
 ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
 			      struct sk_buff *skb, int protocol,
 			      const union nf_inet_addr *caddr, __be16 cport,
@@ -187,7 +187,9 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
 	ip_vs_conn_fill_param(svc->af, protocol, caddr, cport, vaddr, vport, p);
 	p->pe = svc->pe;
 	if (p->pe && p->pe->fill_param)
-		p->pe->fill_param(p, skb);
+		return p->pe->fill_param(p, skb);
+
+	return 0;
 }
 
 /*
@@ -200,7 +202,7 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
 static struct ip_vs_conn *
 ip_vs_sched_persist(struct ip_vs_service *svc,
 		    struct sk_buff *skb,
-		    __be16 src_port, __be16 dst_port)
+		    __be16 src_port, __be16 dst_port, int *ignored)
 {
 	struct ip_vs_conn *cp = NULL;
 	struct ip_vs_iphdr iph;
@@ -268,20 +270,27 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 				vaddr = &fwmark;
 			}
 		}
-		ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0,
-					      vaddr, vport, &param);
+		/* return *ignored = -1 so NF_DROP can be used */
+		if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0,
+						  vaddr, vport, &param) < 0) {
+			*ignored = -1;
+			return NULL;
+		}
 	}
 
 	/* Check if a template already exists */
 	ct = ip_vs_ct_in_get(&param);
 	if (!ct || !ip_vs_check_template(ct)) {
-		/* No template found or the dest of the connection
+		/*
+		 * No template found or the dest of the connection
 		 * template is not available.
+		 * return *ignored=0 i.e. ICMP and NF_DROP
 		 */
 		dest = svc->scheduler->schedule(svc, skb);
 		if (!dest) {
 			IP_VS_DBG(1, "p-schedule: no dest found.\n");
 			kfree(param.pe_data);
+			*ignored = 0;
 			return NULL;
 		}
 
@@ -296,6 +305,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 				    IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
 		if (ct == NULL) {
 			kfree(param.pe_data);
+			*ignored = -1;
 			return NULL;
 		}
 
@@ -323,6 +333,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
 	if (cp == NULL) {
 		ip_vs_conn_put(ct);
+		*ignored = -1;
 		return NULL;
 	}
 
@@ -342,6 +353,21 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
  *  It selects a server according to the virtual service, and
  *  creates a connection entry.
  *  Protocols supported: TCP, UDP
+ *
+ *  Usage of *ignored
+ *
+ * 1 :   protocol tried to schedule (eg. on SYN), found svc but the
+ *       svc/scheduler decides that this packet should be accepted with
+ *       NF_ACCEPT because it must not be scheduled.
+ *
+ * 0 :   scheduler can not find destination, so try bypass or
+ *       return ICMP and then NF_DROP (ip_vs_leave).
+ *
+ * -1 :  scheduler tried to schedule but fatal error occurred, eg.
+ *       ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param
+ *       failure such as missing Call-ID, ENOMEM on skb_linearize
+ *       or pe_data. In this case we should return NF_DROP without
+ *       any attempts to send ICMP with ip_vs_leave.
  */
 struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
@@ -372,11 +398,9 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	}
 
 	/*
-	 * Do not schedule replies from local real server. It is risky
-	 * for fwmark services but mostly for persistent services.
+	 *    Do not schedule replies from local real server.
 	 */
 	if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
-	    (svc->flags & IP_VS_SVC_F_PERSISTENT || svc->fwmark) &&
 	    (cp = pp->conn_in_get(svc->af, skb, pp, &iph, iph.len, 1))) {
 		IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
 			      "Not scheduling reply for existing connection");
@@ -387,10 +411,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	/*
 	 *    Persistent service
 	 */
-	if (svc->flags & IP_VS_SVC_F_PERSISTENT) {
-		*ignored = 0;
-		return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1]);
-	}
+	if (svc->flags & IP_VS_SVC_F_PERSISTENT)
+		return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored);
+
+	*ignored = 0;
 
 	/*
 	 *    Non-persistent service
@@ -403,8 +427,6 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 		return NULL;
 	}
 
-	*ignored = 0;
-
 	dest = svc->scheduler->schedule(svc, skb);
 	if (dest == NULL) {
 		IP_VS_DBG(1, "Schedule: no dest found.\n");
@@ -425,8 +447,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 		cp = ip_vs_conn_new(&p, &dest->addr,
 				    dest->port ? dest->port : pptr[1],
 				    flags, dest, skb->mark);
-		if (!cp)
+		if (!cp) {
+			*ignored = -1;
 			return NULL;
+		}
 	}
 
 	IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u "
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 1ea96bc..a315159 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -47,13 +47,18 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		 * incoming connection, and create a connection entry.
 		 */
 		*cpp = ip_vs_schedule(svc, skb, pp, &ignored);
-		if (!*cpp && !ignored) {
-			*verdict = ip_vs_leave(svc, skb, pp);
+		if (!*cpp && ignored <= 0) {
+			if (!ignored)
+				*verdict = ip_vs_leave(svc, skb, pp);
+			else {
+				ip_vs_service_put(svc);
+				*verdict = NF_DROP;
+			}
 			return 0;
 		}
 		ip_vs_service_put(svc);
 	}
-
+	/* NF_ACCEPT */
 	return 1;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index f6c5200..1cdab12 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -64,12 +64,18 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		 * incoming connection, and create a connection entry.
 		 */
 		*cpp = ip_vs_schedule(svc, skb, pp, &ignored);
-		if (!*cpp && !ignored) {
-			*verdict = ip_vs_leave(svc, skb, pp);
+		if (!*cpp && ignored <= 0) {
+			if (!ignored)
+				*verdict = ip_vs_leave(svc, skb, pp);
+			else {
+				ip_vs_service_put(svc);
+				*verdict = NF_DROP;
+			}
 			return 0;
 		}
 		ip_vs_service_put(svc);
 	}
+	/* NF_ACCEPT */
 	return 1;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 9d106a0..cd398de 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -63,12 +63,18 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		 * incoming connection, and create a connection entry.
 		 */
 		*cpp = ip_vs_schedule(svc, skb, pp, &ignored);
-		if (!*cpp && !ignored) {
-			*verdict = ip_vs_leave(svc, skb, pp);
+		if (!*cpp && ignored <= 0) {
+			if (!ignored)
+				*verdict = ip_vs_leave(svc, skb, pp);
+			else {
+				ip_vs_service_put(svc);
+				*verdict = NF_DROP;
+			}
 			return 0;
 		}
 		ip_vs_service_put(svc);
 	}
+	/* NF_ACCEPT */
 	return 1;
 }
 
-- 
1.7.2.3

[PATCH 28/79] IPVS: Backup, Adding structs for new sync format

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

New structs defined for version 1 of sync.

 * ip_vs_sync_v4       Ipv4 base format struct
 * ip_vs_sync_v6       Ipv6 base format struct

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_sync.c |  154 ++++++++++++++++++++++++++++++++++++---
 1 files changed, 142 insertions(+), 12 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 47eed67..566482f 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -43,11 +43,13 @@
 #define IP_VS_SYNC_GROUP 0xe0000051    /* multicast addr - 224.0.0.81 */
 #define IP_VS_SYNC_PORT  8848          /* multicast port */
 
+#define SYNC_PROTO_VER  1		/* Protocol version in header */
 
 /*
  *	IPVS sync connection entry
+ *	Version 0, i.e. original version.
  */
-struct ip_vs_sync_conn {
+struct ip_vs_sync_conn_v0 {
 	__u8			reserved;
 
 	/* Protocol, addresses and port numbers */
@@ -71,40 +73,157 @@ struct ip_vs_sync_conn_options {
 	struct ip_vs_seq        out_seq;        /* outgoing seq. struct */
 };
 
+/*
+     Sync Connection format (sync_conn)
+
+       0                   1                   2                   3
+       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |    Type       |    Protocol   | Ver.  |        Size           |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |                             Flags                             |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |            State              |         cport                 |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |            vport              |         dport                 |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |                             fwmark                            |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |                             timeout  (in sec.)                |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |                              ...                              |
+      |                        IP-Addresses  (v4 or v6)               |
+      |                              ...                              |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+  Optional Parameters.
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      | Param. Type    | Param. Length |   Param. data                |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+                               |
+      |                              ...                              |
+      |                               +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |                               | Param Type    | Param. Length |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |                           Param  data                         |
+      |         Last Param data should be padded for 32 bit alignment |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+*/
+
+/*
+ *  Type 0, IPv4 sync connection format
+ */
+struct ip_vs_sync_v4 {
+	__u8			type;
+	__u8			protocol;	/* Which protocol (TCP/UDP) */
+	__be16			ver_size;	/* Version msb 4 bits */
+	/* Flags and state transition */
+	__be32			flags;		/* status flags */
+	__be16			state;		/* state info 	*/
+	/* Protocol, addresses and port numbers */
+	__be16			cport;
+	__be16			vport;
+	__be16			dport;
+	__be32			fwmark;		/* Firewall mark from skb */
+	__be32			timeout;	/* cp timeout */
+	__be32			caddr;		/* client address */
+	__be32			vaddr;		/* virtual address */
+	__be32			daddr;		/* destination address */
+	/* The sequence options start here */
+	/* PE data padded to 32bit alignment after seq. options */
+};
+/*
+ * Type 2 messages IPv6
+ */
+struct ip_vs_sync_v6 {
+	__u8			type;
+	__u8			protocol;	/* Which protocol (TCP/UDP) */
+	__be16			ver_size;	/* Version msb 4 bits */
+	/* Flags and state transition */
+	__be32			flags;		/* status flags */
+	__be16			state;		/* state info 	*/
+	/* Protocol, addresses and port numbers */
+	__be16			cport;
+	__be16			vport;
+	__be16			dport;
+	__be32			fwmark;		/* Firewall mark from skb */
+	__be32			timeout;	/* cp timeout */
+	struct in6_addr		caddr;		/* client address */
+	struct in6_addr		vaddr;		/* virtual address */
+	struct in6_addr		daddr;		/* destination address */
+	/* The sequence options start here */
+	/* PE data padded to 32bit alignment after seq. options */
+};
+
+union ip_vs_sync_conn {
+	struct ip_vs_sync_v4	v4;
+	struct ip_vs_sync_v6	v6;
+};
+
+/* Bits in Type field in above */
+#define STYPE_INET6		0
+#define STYPE_F_INET6		(1 << STYPE_INET6)
+
+#define SVER_SHIFT		12		/* Shift to get version */
+#define SVER_MASK		0x0fff		/* Mask to strip version */
+
+#define IPVS_OPT_SEQ_DATA	1
+#define IPVS_OPT_PE_DATA	2
+#define IPVS_OPT_PE_NAME	3
+#define IPVS_OPT_PARAM		7
+
+#define IPVS_OPT_F_SEQ_DATA	(1 << (IPVS_OPT_SEQ_DATA-1))
+#define IPVS_OPT_F_PE_DATA	(1 << (IPVS_OPT_PE_DATA-1))
+#define IPVS_OPT_F_PE_NAME	(1 << (IPVS_OPT_PE_NAME-1))
+#define IPVS_OPT_F_PARAM	(1 << (IPVS_OPT_PARAM-1))
+
 struct ip_vs_sync_thread_data {
 	struct socket *sock;
 	char *buf;
 };
 
-#define SIMPLE_CONN_SIZE  (sizeof(struct ip_vs_sync_conn))
+/* Version 0 definition of packet sizes */
+#define SIMPLE_CONN_SIZE  (sizeof(struct ip_vs_sync_conn_v0))
 #define FULL_CONN_SIZE  \
-(sizeof(struct ip_vs_sync_conn) + sizeof(struct ip_vs_sync_conn_options))
+(sizeof(struct ip_vs_sync_conn_v0) + sizeof(struct ip_vs_sync_conn_options))
 
 
 /*
-  The master mulitcasts messages to the backup load balancers in the
-  following format.
+  The master mulitcasts messages (Datagrams) to the backup load balancers
+  in the following format.
+
+ Version 1:
+  Note, first byte should be Zero, so ver 0 receivers will drop the packet.
 
        0                   1                   2                   3
        0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-      |  Count Conns  |    SyncID     |            Size               |
+      |      0        |    SyncID     |            Size               |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |  Count Conns  |    Version    |    Reserved, set to Zero      |
       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
       |                                                               |
       |                    IPVS Sync Connection (1)                   |
       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
       |                            .                                  |
-      |                            .                                  |
+      ~                            .                                  ~
       |                            .                                  |
       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
       |                                                               |
       |                    IPVS Sync Connection (n)                   |
       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+ Version 0 Header
+       0                   1                   2                   3
+       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |  Count Conns  |    SyncID     |            Size               |
+      +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+      |                    IPVS Sync Connection (1)                   |
 */
 
 #define SYNC_MESG_HEADER_LEN	4
 #define MAX_CONNS_PER_SYNCBUFF	255 /* nr_conns in ip_vs_sync_mesg is 8 bit */
 
+/* Version 0 header */
 struct ip_vs_sync_mesg {
 	__u8                    nr_conns;
 	__u8                    syncid;
@@ -113,6 +232,17 @@ struct ip_vs_sync_mesg {
 	/* ip_vs_sync_conn entries start here */
 };
 
+/* Version 1 header */
+struct ip_vs_sync_mesg_v2 {
+	__u8			reserved;	/* must be zero */
+	__u8			syncid;
+	__u16			size;
+	__u8			nr_conns;
+	__s8			version;	/* SYNC_PROTO_VER  */
+	__u16			spare;
+	/* ip_vs_sync_conn entries start here */
+};
+
 /* the maximum length of sync (sending/receiving) message */
 static int sync_send_mesg_maxlen;
 static int sync_recv_mesg_maxlen;
@@ -239,7 +369,7 @@ get_curr_sync_buff(unsigned long time)
 void ip_vs_sync_conn(const struct ip_vs_conn *cp)
 {
 	struct ip_vs_sync_mesg *m;
-	struct ip_vs_sync_conn *s;
+	struct ip_vs_sync_conn_v0 *s;
 	int len;
 
 	spin_lock(&curr_sb_lock);
@@ -254,7 +384,7 @@ void ip_vs_sync_conn(const struct ip_vs_conn *cp)
 	len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE :
 		SIMPLE_CONN_SIZE;
 	m = curr_sb->mesg;
-	s = (struct ip_vs_sync_conn *)curr_sb->head;
+	s = (struct ip_vs_sync_conn_v0 *)curr_sb->head;
 
 	/* copy members */
 	s->protocol = cp->protocol;
@@ -306,7 +436,7 @@ ip_vs_conn_fill_param_sync(int af, int protocol,
 static void ip_vs_process_message(char *buffer, const size_t buflen)
 {
 	struct ip_vs_sync_mesg *m = (struct ip_vs_sync_mesg *)buffer;
-	struct ip_vs_sync_conn *s;
+	struct ip_vs_sync_conn_v0 *s;
 	struct ip_vs_sync_conn_options *opt;
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
@@ -343,7 +473,7 @@ static void ip_vs_process_message(char *buffer, const size_t buflen)
 			IP_VS_ERR_RL("bogus conn in sync message\n");
 			return;
 		}
-		s = (struct ip_vs_sync_conn *) p;
+		s = (struct ip_vs_sync_conn_v0 *) p;
 		flags = ntohs(s->flags) | IP_VS_CONN_F_SYNC;
 		flags &= ~IP_VS_CONN_F_HASHED;
 		if (flags & IP_VS_CONN_F_SEQ_MASK) {
@@ -849,7 +979,7 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
 
 	IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
 	IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n",
-		  sizeof(struct ip_vs_sync_conn));
+		  sizeof(struct ip_vs_sync_conn_v0));
 
 	if (state == IP_VS_STATE_MASTER) {
 		if (sync_master_thread)
-- 
1.7.2.3

[PATCH 29/79] IPVS: Backup, Adding Version 1 receive capability

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

Functionality improvements
 * flags  changed from 16 to 32 bits
 * fwmark added (32 bits)
 * timeout in sec. added (32 bits)
 * pe data added (Variable length)
 * IPv6 capabilities (3x16 bytes for addr.)
 * Version and type in every conn msg.

ip_vs_process_message() now handles Version 1 messages
and will call ip_vs_process_message_v0() for version 0 messages.

ip_vs_proc_conn() is common for both version, and handles the update of
connection hash.

ip_vs_conn_fill_param_sync()    - Version 1 messages only
ip_vs_conn_fill_param_sync_v0() - Version 0 messages only

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/linux/ip_vs.h           |    8 +
 include/net/ip_vs.h             |    1 +
 net/netfilter/ipvs/ip_vs_pe.c   |    5 +-
 net/netfilter/ipvs/ip_vs_sync.c |  549 ++++++++++++++++++++++++++++++---------
 4 files changed, 440 insertions(+), 123 deletions(-)

diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h
index 5f43a3b..4deb383 100644
--- a/include/linux/ip_vs.h
+++ b/include/linux/ip_vs.h
@@ -89,6 +89,14 @@
 #define IP_VS_CONN_F_TEMPLATE	0x1000		/* template, not connection */
 #define IP_VS_CONN_F_ONE_PACKET	0x2000		/* forward only one packet */
 
+#define IP_VS_CONN_F_BACKUP_MASK (IP_VS_CONN_F_FWD_MASK | \
+				  IP_VS_CONN_F_NOOUTPUT | \
+				  IP_VS_CONN_F_INACTIVE | \
+				  IP_VS_CONN_F_SEQ_MASK | \
+				  IP_VS_CONN_F_NO_CPORT | \
+				  IP_VS_CONN_F_TEMPLATE \
+				 )
+
 /* Flags that are not sent to backup server start from bit 16 */
 #define IP_VS_CONN_F_NFCT	(1 << 16)	/* use netfilter conntrack */
 
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 890f01c..4069484 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -817,6 +817,7 @@ void ip_vs_unbind_pe(struct ip_vs_service *svc);
 int register_ip_vs_pe(struct ip_vs_pe *pe);
 int unregister_ip_vs_pe(struct ip_vs_pe *pe);
 struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
+struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name);
 
 static inline void ip_vs_pe_get(const struct ip_vs_pe *pe)
 {
diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c
index e99f920..5cf859c 100644
--- a/net/netfilter/ipvs/ip_vs_pe.c
+++ b/net/netfilter/ipvs/ip_vs_pe.c
@@ -29,12 +29,11 @@ void ip_vs_unbind_pe(struct ip_vs_service *svc)
 }
 
 /* Get pe in the pe list by name */
-static struct ip_vs_pe *
-__ip_vs_pe_getbyname(const char *pe_name)
+struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name)
 {
 	struct ip_vs_pe *pe;
 
-	IP_VS_DBG(2, "%s(): pe_name \"%s\"\n", __func__,
+	IP_VS_DBG(10, "%s(): pe_name \"%s\"\n", __func__,
 		  pe_name);
 
 	spin_lock_bh(&ip_vs_pe_lock);
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 566482f..e071508 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -35,6 +35,8 @@
 #include <linux/wait.h>
 #include <linux/kernel.h>
 
+#include <asm/unaligned.h>		/* Used for ntoh_seq and hton_seq */
+
 #include <net/ip.h>
 #include <net/sock.h>
 
@@ -286,6 +288,16 @@ static struct sockaddr_in mcast_addr = {
 	.sin_addr.s_addr	= cpu_to_be32(IP_VS_SYNC_GROUP),
 };
 
+/*
+ * Copy of struct ip_vs_seq
+ * From unaligned network order to aligned host order
+ */
+static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho)
+{
+	ho->init_seq       = get_unaligned_be32(&no->init_seq);
+	ho->delta          = get_unaligned_be32(&no->delta);
+	ho->previous_delta = get_unaligned_be32(&no->previous_delta);
+}
 
 static inline struct ip_vs_sync_buff *sb_dequeue(void)
 {
@@ -418,59 +430,186 @@ void ip_vs_sync_conn(const struct ip_vs_conn *cp)
 		ip_vs_sync_conn(cp->control);
 }
 
+/*
+ *  fill_param used by version 1
+ */
 static inline int
-ip_vs_conn_fill_param_sync(int af, int protocol,
-			   const union nf_inet_addr *caddr, __be16 cport,
-			   const union nf_inet_addr *vaddr, __be16 vport,
-			   struct ip_vs_conn_param *p)
+ip_vs_conn_fill_param_sync(int af, union ip_vs_sync_conn *sc,
+			   struct ip_vs_conn_param *p,
+			   __u8 *pe_data, unsigned int pe_data_len,
+			   __u8 *pe_name, unsigned int pe_name_len)
 {
-	/* XXX: Need to take into account persistence engine */
-	ip_vs_conn_fill_param(af, protocol, caddr, cport, vaddr, vport, p);
+#ifdef CONFIG_IP_VS_IPV6
+	if (af == AF_INET6)
+		ip_vs_conn_fill_param(af, sc->v6.protocol,
+				      (const union nf_inet_addr *)&sc->v6.caddr,
+				      sc->v6.cport,
+				      (const union nf_inet_addr *)&sc->v6.vaddr,
+				      sc->v6.vport, p);
+	else
+#endif
+		ip_vs_conn_fill_param(af, sc->v4.protocol,
+				      (const union nf_inet_addr *)&sc->v4.caddr,
+				      sc->v4.cport,
+				      (const union nf_inet_addr *)&sc->v4.vaddr,
+				      sc->v4.vport, p);
+	/* Handle pe data */
+	if (pe_data_len) {
+		if (pe_name_len) {
+			char buff[IP_VS_PENAME_MAXLEN+1];
+
+			memcpy(buff, pe_name, pe_name_len);
+			buff[pe_name_len]=0;
+			p->pe = __ip_vs_pe_getbyname(buff);
+			if (!p->pe) {
+				IP_VS_DBG(3, "BACKUP, no %s engine found/loaded\n", buff);
+				return 1;
+			}
+		} else {
+			IP_VS_ERR_RL("BACKUP, Invalid PE parameters\n");
+			return 1;
+		}
+
+		p->pe_data = kmalloc(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;
 }
 
 /*
- *      Process received multicast message and create the corresponding
- *      ip_vs_conn entries.
+ *  Connection Add / Update.
+ *  Common for version 0 and 1 reception of backup sync_conns.
+ *  Param: ...
+ *         timeout is in sec.
+ */
+static void ip_vs_proc_conn(struct ip_vs_conn_param *param,  unsigned flags,
+			    unsigned state, unsigned protocol, unsigned type,
+			    const union nf_inet_addr *daddr, __be16 dport,
+			    unsigned long timeout, __u32 fwmark,
+			    struct ip_vs_sync_conn_options *opt,
+			    struct ip_vs_protocol *pp)
+{
+	struct ip_vs_dest *dest;
+	struct ip_vs_conn *cp;
+
+
+	if (!(flags & IP_VS_CONN_F_TEMPLATE))
+		cp = ip_vs_conn_in_get(param);
+	else
+		cp = ip_vs_ct_in_get(param);
+
+	if (cp && param->pe_data) 	/* Free pe_data */
+		kfree(param->pe_data);
+	if (!cp) {
+		/*
+		 * Find the appropriate destination for the connection.
+		 * If it is not found the connection will remain unbound
+		 * but still handled.
+		 */
+		dest = ip_vs_find_dest(type, daddr, dport, param->vaddr,
+				       param->vport, protocol, fwmark);
+
+		/*  Set the approprite ativity flag */
+		if (protocol == IPPROTO_TCP) {
+			if (state != IP_VS_TCP_S_ESTABLISHED)
+				flags |= IP_VS_CONN_F_INACTIVE;
+			else
+				flags &= ~IP_VS_CONN_F_INACTIVE;
+		} else if (protocol == IPPROTO_SCTP) {
+			if (state != IP_VS_SCTP_S_ESTABLISHED)
+				flags |= IP_VS_CONN_F_INACTIVE;
+			else
+				flags &= ~IP_VS_CONN_F_INACTIVE;
+		}
+		cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark);
+		if (dest)
+			atomic_dec(&dest->refcnt);
+		if (!cp) {
+			if (param->pe_data)
+				kfree(param->pe_data);
+			IP_VS_DBG(2, "BACKUP, add new conn. failed\n");
+			return;
+		}
+	} else if (!cp->dest) {
+		dest = ip_vs_try_bind_dest(cp);
+		if (dest)
+			atomic_dec(&dest->refcnt);
+	} else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) &&
+		(cp->state != state)) {
+		/* update active/inactive flag for the connection */
+		dest = cp->dest;
+		if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
+			(state != IP_VS_TCP_S_ESTABLISHED)) {
+			atomic_dec(&dest->activeconns);
+			atomic_inc(&dest->inactconns);
+			cp->flags |= IP_VS_CONN_F_INACTIVE;
+		} else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
+			(state == IP_VS_TCP_S_ESTABLISHED)) {
+			atomic_inc(&dest->activeconns);
+			atomic_dec(&dest->inactconns);
+			cp->flags &= ~IP_VS_CONN_F_INACTIVE;
+		}
+	} else if ((cp->dest) && (cp->protocol == IPPROTO_SCTP) &&
+		(cp->state != state)) {
+		dest = cp->dest;
+		if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
+		(state != IP_VS_SCTP_S_ESTABLISHED)) {
+			atomic_dec(&dest->activeconns);
+			atomic_inc(&dest->inactconns);
+			cp->flags &= ~IP_VS_CONN_F_INACTIVE;
+		}
+	}
+
+	if (opt)
+		memcpy(&cp->in_seq, opt, sizeof(*opt));
+	atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]);
+	cp->state = state;
+	cp->old_state = cp->state;
+	/*
+	 * For Ver 0 messages style
+	 *  - Not possible to recover the right timeout for templates
+	 *  - can not find the right fwmark
+	 *    virtual service. If needed, we can do it for
+	 *    non-fwmark persistent services.
+	 * Ver 1 messages style.
+	 *  - No problem.
+	 */
+	if (timeout) {
+		if (timeout > MAX_SCHEDULE_TIMEOUT / HZ)
+			timeout = MAX_SCHEDULE_TIMEOUT / HZ;
+		cp->timeout = timeout*HZ;
+	} else if (!(flags & IP_VS_CONN_F_TEMPLATE) && pp->timeout_table)
+		cp->timeout = pp->timeout_table[state];
+	else
+		cp->timeout = (3*60*HZ);
+	ip_vs_conn_put(cp);
+}
+
+/*
+ *  Process received multicast message for Version 0
  */
-static void ip_vs_process_message(char *buffer, const size_t buflen)
+static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
 {
 	struct ip_vs_sync_mesg *m = (struct ip_vs_sync_mesg *)buffer;
 	struct ip_vs_sync_conn_v0 *s;
 	struct ip_vs_sync_conn_options *opt;
-	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
-	struct ip_vs_dest *dest;
 	struct ip_vs_conn_param param;
 	char *p;
 	int i;
 
-	if (buflen < sizeof(struct ip_vs_sync_mesg)) {
-		IP_VS_ERR_RL("sync message header too short\n");
-		return;
-	}
-
-	/* Convert size back to host byte order */
-	m->size = ntohs(m->size);
-
-	if (buflen != m->size) {
-		IP_VS_ERR_RL("bogus sync message size\n");
-		return;
-	}
-
-	/* SyncID sanity check */
-	if (ip_vs_backup_syncid != 0 && m->syncid != ip_vs_backup_syncid) {
-		IP_VS_DBG(7, "Ignoring incoming msg with syncid = %d\n",
-			  m->syncid);
-		return;
-	}
-
 	p = (char *)buffer + sizeof(struct ip_vs_sync_mesg);
 	for (i=0; i<m->nr_conns; i++) {
 		unsigned flags, state;
 
 		if (p + SIMPLE_CONN_SIZE > buffer+buflen) {
-			IP_VS_ERR_RL("bogus conn in sync message\n");
+			IP_VS_ERR_RL("BACKUP v0, bogus conn\n");
 			return;
 		}
 		s = (struct ip_vs_sync_conn_v0 *) p;
@@ -480,7 +619,7 @@ static void ip_vs_process_message(char *buffer, const size_t buflen)
 			opt = (struct ip_vs_sync_conn_options *)&s[1];
 			p += FULL_CONN_SIZE;
 			if (p > buffer+buflen) {
-				IP_VS_ERR_RL("bogus conn options in sync message\n");
+				IP_VS_ERR_RL("BACKUP v0, Dropping buffer bogus conn options\n");
 				return;
 			}
 		} else {
@@ -492,12 +631,12 @@ static void ip_vs_process_message(char *buffer, const size_t buflen)
 		if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
 			pp = ip_vs_proto_get(s->protocol);
 			if (!pp) {
-				IP_VS_ERR_RL("Unsupported protocol %u in sync msg\n",
+				IP_VS_DBG(2, "BACKUP v0, Unsupported protocol %u\n",
 					s->protocol);
 				continue;
 			}
 			if (state >= pp->num_states) {
-				IP_VS_DBG(2, "Invalid %s state %u in sync msg\n",
+				IP_VS_DBG(2, "BACKUP v0, Invalid %s state %u\n",
 					pp->name, state);
 				continue;
 			}
@@ -505,103 +644,273 @@ static void ip_vs_process_message(char *buffer, const size_t buflen)
 			/* protocol in templates is not used for state/timeout */
 			pp = NULL;
 			if (state > 0) {
-				IP_VS_DBG(2, "Invalid template state %u in sync msg\n",
+				IP_VS_DBG(2, "BACKUP v0, Invalid template state %u\n",
 					state);
 				state = 0;
 			}
 		}
 
-		if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol,
-					       (union nf_inet_addr *)&s->caddr,
-					       s->cport,
-					       (union nf_inet_addr *)&s->vaddr,
-					       s->vport, &param)) {
-			pr_err("ip_vs_conn_fill_param_sync failed");
-			return;
+		ip_vs_conn_fill_param(AF_INET, s->protocol,
+				      (const union nf_inet_addr *)&s->caddr,
+				      s->cport,
+				      (const union nf_inet_addr *)&s->vaddr,
+				      s->vport, &param);
+
+		/* Send timeout as Zero */
+		ip_vs_proc_conn(&param, flags, state, s->protocol, AF_INET,
+				(union nf_inet_addr *)&s->daddr, s->dport,
+				0, 0, opt, pp);
+	}
+}
+
+/*
+ * Handle options
+ */
+static inline int ip_vs_proc_seqopt(__u8 *p, unsigned int plen,
+				    __u32 *opt_flags,
+				    struct ip_vs_sync_conn_options *opt)
+{
+	struct ip_vs_sync_conn_options *topt;
+
+	topt = (struct ip_vs_sync_conn_options *)p;
+
+	if (plen != sizeof(struct ip_vs_sync_conn_options)) {
+		IP_VS_DBG(2, "BACKUP, bogus conn options length\n");
+		return -EINVAL;
+	}
+	if (*opt_flags & IPVS_OPT_F_SEQ_DATA) {
+		IP_VS_DBG(2, "BACKUP, conn options found twice\n");
+		return -EINVAL;
+	}
+	ntoh_seq(&topt->in_seq, &opt->in_seq);
+	ntoh_seq(&topt->out_seq, &opt->out_seq);
+	*opt_flags |= IPVS_OPT_F_SEQ_DATA;
+	return 0;
+}
+
+static int ip_vs_proc_str(__u8 *p, unsigned int plen, unsigned int *data_len,
+			  __u8 **data, unsigned int maxlen,
+			  __u32 *opt_flags, __u32 flag)
+{
+	if (plen > maxlen) {
+		IP_VS_DBG(2, "BACKUP, bogus par.data len > %d\n", maxlen);
+		return -EINVAL;
+	}
+	if (*opt_flags & flag) {
+		IP_VS_DBG(2, "BACKUP, Par.data found twice 0x%x\n", flag);
+		return -EINVAL;
+	}
+	*data_len = plen;
+	*data = p;
+	*opt_flags |= flag;
+	return 0;
+}
+/*
+ *   Process a Version 1 sync. connection
+ */
+static inline int ip_vs_proc_sync_conn(__u8 *p, __u8 *msg_end)
+{
+	struct ip_vs_sync_conn_options opt;
+	union  ip_vs_sync_conn *s;
+	struct ip_vs_protocol *pp;
+	struct ip_vs_conn_param param;
+	__u32 flags;
+	unsigned int af, state, pe_data_len=0, pe_name_len=0;
+	__u8 *pe_data=NULL, *pe_name=NULL;
+	__u32 opt_flags=0;
+	int retc=0;
+
+	s = (union ip_vs_sync_conn *) p;
+
+	if (s->v6.type & STYPE_F_INET6) {
+#ifdef CONFIG_IP_VS_IPV6
+		af = AF_INET6;
+		p += sizeof(struct ip_vs_sync_v6);
+#else
+		IP_VS_DBG(3,"BACKUP, IPv6 msg received, and IPVS is not compiled for IPv6\n");
+		retc = 10;
+		goto out;
+#endif
+	} else if (!s->v4.type) {
+		af = AF_INET;
+		p += sizeof(struct ip_vs_sync_v4);
+	} else {
+		return -10;
+	}
+	if (p > msg_end)
+		return -20;
+
+	/* Process optional params check Type & Len. */
+	while (p < msg_end) {
+		int ptype;
+		int plen;
+
+		if (p+2 > msg_end)
+			return -30;
+		ptype = *(p++);
+		plen  = *(p++);
+
+		if (!plen || ((p + plen) > msg_end))
+			return -40;
+		/* Handle seq option  p = param data */
+		switch (ptype & ~IPVS_OPT_F_PARAM) {
+		case IPVS_OPT_SEQ_DATA:
+			if (ip_vs_proc_seqopt(p, plen, &opt_flags, &opt))
+				return -50;
+			break;
+
+		case IPVS_OPT_PE_DATA:
+			if (ip_vs_proc_str(p, plen, &pe_data_len, &pe_data,
+					   IP_VS_PEDATA_MAXLEN, &opt_flags,
+					   IPVS_OPT_F_PE_DATA))
+				return -60;
+			break;
+
+		case IPVS_OPT_PE_NAME:
+			if (ip_vs_proc_str(p, plen,&pe_name_len, &pe_name,
+					   IP_VS_PENAME_MAXLEN, &opt_flags,
+					   IPVS_OPT_F_PE_NAME))
+				return -70;
+			break;
+
+		default:
+			/* Param data mandatory ? */
+			if (!(ptype & IPVS_OPT_F_PARAM)) {
+				IP_VS_DBG(3, "BACKUP, Unknown mandatory param %d found\n",
+					  ptype & ~IPVS_OPT_F_PARAM);
+				retc = 20;
+				goto out;
+			}
 		}
-		if (!(flags & IP_VS_CONN_F_TEMPLATE))
-			cp = ip_vs_conn_in_get(&param);
-		else
-			cp = ip_vs_ct_in_get(&param);
-		if (!cp) {
-			/*
-			 * Find the appropriate destination for the connection.
-			 * If it is not found the connection will remain unbound
-			 * but still handled.
-			 */
-			dest = ip_vs_find_dest(AF_INET,
-					       (union nf_inet_addr *)&s->daddr,
-					       s->dport,
-					       (union nf_inet_addr *)&s->vaddr,
-					       s->vport,
-					       s->protocol, 0);
-			/*  Set the approprite ativity flag */
-			if (s->protocol == IPPROTO_TCP) {
-				if (state != IP_VS_TCP_S_ESTABLISHED)
-					flags |= IP_VS_CONN_F_INACTIVE;
-				else
-					flags &= ~IP_VS_CONN_F_INACTIVE;
-			} else if (s->protocol == IPPROTO_SCTP) {
-				if (state != IP_VS_SCTP_S_ESTABLISHED)
-					flags |= IP_VS_CONN_F_INACTIVE;
-				else
-					flags &= ~IP_VS_CONN_F_INACTIVE;
+		p += plen;  /* Next option */
+	}
+
+	/* Get flags and Mask off unsupported */
+	flags  = ntohl(s->v4.flags) & IP_VS_CONN_F_BACKUP_MASK;
+	flags |= IP_VS_CONN_F_SYNC;
+	state = ntohs(s->v4.state);
+
+	if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
+		pp = ip_vs_proto_get(s->v4.protocol);
+		if (!pp) {
+			IP_VS_DBG(3,"BACKUP, Unsupported protocol %u\n",
+				s->v4.protocol);
+			retc = 30;
+			goto out;
+		}
+		if (state >= pp->num_states) {
+			IP_VS_DBG(3, "BACKUP, Invalid %s state %u\n",
+				pp->name, state);
+			retc = 40;
+			goto out;
+		}
+	} else {
+		/* protocol in templates is not used for state/timeout */
+		pp = NULL;
+		if (state > 0) {
+			IP_VS_DBG(3, "BACKUP, Invalid template state %u\n",
+				state);
+			state = 0;
+		}
+	}
+	if (ip_vs_conn_fill_param_sync(af, s, &param,
+					pe_data, pe_data_len,
+					pe_name, pe_name_len)) {
+		retc = 50;
+		goto out;
+	}
+	/* If only IPv4, just silent skip IPv6 */
+	if (af == AF_INET)
+		ip_vs_proc_conn(&param, flags, state, s->v4.protocol, af,
+				(union nf_inet_addr *)&s->v4.daddr, s->v4.dport,
+				ntohl(s->v4.timeout), ntohl(s->v4.fwmark),
+				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL),
+				pp);
+#ifdef CONFIG_IP_VS_IPV6
+	else
+		ip_vs_proc_conn(&param, flags, state, s->v6.protocol, af,
+				(union nf_inet_addr *)&s->v6.daddr, s->v6.dport,
+				ntohl(s->v6.timeout), ntohl(s->v6.fwmark),
+				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL),
+				pp);
+#endif
+	return 0;
+	/* Error exit */
+out:
+	IP_VS_DBG(2, "BACKUP, Single msg dropped err:%d\n", retc);
+	return retc;
+
+}
+/*
+ *      Process received multicast message and create the corresponding
+ *      ip_vs_conn entries.
+ *      Handles Version 0 & 1
+ */
+static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
+{
+	struct ip_vs_sync_mesg_v2 *m2 = (struct ip_vs_sync_mesg_v2 *)buffer;
+	__u8 *p, *msg_end;
+	unsigned int i, nr_conns;
+
+	if (buflen < sizeof(struct ip_vs_sync_mesg)) {
+		IP_VS_DBG(2, "BACKUP, message header too short\n");
+		return;
+	}
+	/* Convert size back to host byte order */
+	m2->size = ntohs(m2->size);
+
+	if (buflen != m2->size) {
+		IP_VS_DBG(2, "BACKUP, bogus message size\n");
+		return;
+	}
+	/* SyncID sanity check */
+	if (ip_vs_backup_syncid != 0 && m2->syncid != ip_vs_backup_syncid) {
+		IP_VS_DBG(7, "BACKUP, Ignoring syncid = %d\n", m2->syncid);
+		return;
+	}
+	/* Handle version 1  message */
+	if ((m2->version == SYNC_PROTO_VER) && (m2->reserved == 0)
+	    && (m2->spare == 0)) {
+
+		msg_end = buffer + sizeof(struct ip_vs_sync_mesg_v2);
+		nr_conns = m2->nr_conns;
+
+		for (i=0; i<nr_conns; i++) {
+			union ip_vs_sync_conn *s;
+			unsigned size;
+			int retc;
+
+			p = msg_end;
+			if (p + sizeof(s->v4) > buffer+buflen) {
+				IP_VS_ERR_RL("BACKUP, Dropping buffer, to small\n");
+				return;
 			}
-			cp = ip_vs_conn_new(&param,
-					    (union nf_inet_addr *)&s->daddr,
-					    s->dport, flags, dest, 0);
-			if (dest)
-				atomic_dec(&dest->refcnt);
-			if (!cp) {
-				pr_err("ip_vs_conn_new failed\n");
+			s = (union ip_vs_sync_conn *)p;
+			size = ntohs(s->v4.ver_size) & SVER_MASK;
+			msg_end = p + size;
+			/* Basic sanity checks */
+			if (msg_end  > buffer+buflen) {
+				IP_VS_ERR_RL("BACKUP, Dropping buffer, msg > buffer\n");
 				return;
 			}
-		} else if (!cp->dest) {
-			dest = ip_vs_try_bind_dest(cp);
-			if (dest)
-				atomic_dec(&dest->refcnt);
-		} else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) &&
-			   (cp->state != state)) {
-			/* update active/inactive flag for the connection */
-			dest = cp->dest;
-			if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
-				(state != IP_VS_TCP_S_ESTABLISHED)) {
-				atomic_dec(&dest->activeconns);
-				atomic_inc(&dest->inactconns);
-				cp->flags |= IP_VS_CONN_F_INACTIVE;
-			} else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
-				(state == IP_VS_TCP_S_ESTABLISHED)) {
-				atomic_inc(&dest->activeconns);
-				atomic_dec(&dest->inactconns);
-				cp->flags &= ~IP_VS_CONN_F_INACTIVE;
+			if (ntohs(s->v4.ver_size) >> SVER_SHIFT) {
+				IP_VS_ERR_RL("BACKUP, Dropping buffer, Unknown version %d\n",
+					      ntohs(s->v4.ver_size) >> SVER_SHIFT);
+				return;
 			}
-		} else if ((cp->dest) && (cp->protocol == IPPROTO_SCTP) &&
-			   (cp->state != state)) {
-			dest = cp->dest;
-			if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
-			     (state != IP_VS_SCTP_S_ESTABLISHED)) {
-			    atomic_dec(&dest->activeconns);
-			    atomic_inc(&dest->inactconns);
-			    cp->flags &= ~IP_VS_CONN_F_INACTIVE;
+			/* Process a single sync_conn */
+			if ((retc=ip_vs_proc_sync_conn(p, msg_end)) < 0) {
+				IP_VS_ERR_RL("BACKUP, Dropping buffer, Err: %d in decoding\n",
+					     retc);
+				return;
 			}
+			/* Make sure we have 32 bit alignment */
+			msg_end = p + ((size + 3) & ~3);
 		}
-
-		if (opt)
-			memcpy(&cp->in_seq, opt, sizeof(*opt));
-		atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]);
-		cp->state = state;
-		cp->old_state = cp->state;
-		/*
-		 * We can not recover the right timeout for templates
-		 * in all cases, we can not find the right fwmark
-		 * virtual service. If needed, we can do it for
-		 * non-fwmark persistent services.
-		 */
-		if (!(flags & IP_VS_CONN_F_TEMPLATE) && pp->timeout_table)
-			cp->timeout = pp->timeout_table[state];
-		else
-			cp->timeout = (3*60*HZ);
-		ip_vs_conn_put(cp);
+	} else {
+		/* Old type of message */
+		ip_vs_process_message_v0(buffer, buflen);
+		return;
 	}
 }
 
-- 
1.7.2.3

[PATCH 30/79] IPVS: Backup, Change sending to Version 1 format

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

Enable sending and removal of version 0 sending
Affected functions,

ip_vs_sync_buff_create()
ip_vs_sync_conn()

ip_vs_core.c removal of IPv4 check.

*v5
 Just check cp->pe_data_len in ip_vs_sync_conn
 Check if padding needed before adding a new sync_conn
 to the buffer, i.e. avoid sending padding at the end.

*v4
 moved sanity check and pe_name_len after sloop.
 use cp->pe instead of cp->dest->svc->pe
 real length in each sync_conn, not padded length
 however total size of a sync_msg includes padding.

*v3
 Sending ip_vs_sync_conn_options in network order.
 Sending Templates for ONE_PACKET conn.
 Renaming of ip_vs_sync_mesg to ip_vs_sync_mesg_v0

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |    2 +-
 net/netfilter/ipvs/ip_vs_core.c |   13 ++-
 net/netfilter/ipvs/ip_vs_sync.c |  189 ++++++++++++++++++++++++++++++---------
 3 files changed, 156 insertions(+), 48 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4069484..a715f3d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -919,7 +919,7 @@ extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
 extern int stop_sync_thread(int state);
-extern void ip_vs_sync_conn(const struct ip_vs_conn *cp);
+extern void ip_vs_sync_conn(struct ip_vs_conn *cp);
 
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 3445da6..5287771 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1560,9 +1560,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	 *
 	 * Sync connection if it is about to close to
 	 * encorage the standby servers to update the connections timeout
+	 *
+	 * For ONE_PKT let ip_vs_sync_conn() do the filter work.
 	 */
-	pkts = atomic_add_return(1, &cp->in_pkts);
-	if (af == AF_INET && (ip_vs_sync_state & IP_VS_STATE_MASTER) &&
+	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+		pkts = sysctl_ip_vs_sync_threshold[0];
+	else
+		pkts = atomic_add_return(1, &cp->in_pkts);
+
+	if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
 	    cp->protocol == IPPROTO_SCTP) {
 		if ((cp->state == IP_VS_SCTP_S_ESTABLISHED &&
 			(pkts % sysctl_ip_vs_sync_threshold[1]
@@ -1577,8 +1583,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	}
 
 	/* Keep this block last: TCP and others with pp->num_states <= 1 */
-	else if (af == AF_INET &&
-	    (ip_vs_sync_state & IP_VS_STATE_MASTER) &&
+	else if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
 	    (((cp->protocol != IPPROTO_TCP ||
 	       cp->state == IP_VS_TCP_S_ESTABLISHED) &&
 	      (pkts % sysctl_ip_vs_sync_threshold[1]
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index e071508..df5abf0 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -226,7 +226,7 @@ struct ip_vs_sync_thread_data {
 #define MAX_CONNS_PER_SYNCBUFF	255 /* nr_conns in ip_vs_sync_mesg is 8 bit */
 
 /* Version 0 header */
-struct ip_vs_sync_mesg {
+struct ip_vs_sync_mesg_v0 {
 	__u8                    nr_conns;
 	__u8                    syncid;
 	__u16                   size;
@@ -235,7 +235,7 @@ struct ip_vs_sync_mesg {
 };
 
 /* Version 1 header */
-struct ip_vs_sync_mesg_v2 {
+struct ip_vs_sync_mesg {
 	__u8			reserved;	/* must be zero */
 	__u8			syncid;
 	__u16			size;
@@ -299,6 +299,17 @@ static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho)
 	ho->previous_delta = get_unaligned_be32(&no->previous_delta);
 }
 
+/*
+ * Copy of struct ip_vs_seq
+ * From Aligned host order to unaligned network order
+ */
+static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no)
+{
+	put_unaligned_be32(ho->init_seq, &no->init_seq);
+	put_unaligned_be32(ho->delta, &no->delta);
+	put_unaligned_be32(ho->previous_delta, &no->previous_delta);
+}
+
 static inline struct ip_vs_sync_buff *sb_dequeue(void)
 {
 	struct ip_vs_sync_buff *sb;
@@ -317,6 +328,9 @@ static inline struct ip_vs_sync_buff *sb_dequeue(void)
 	return sb;
 }
 
+/*
+ * Create a new sync buffer for Version 1 proto.
+ */
 static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(void)
 {
 	struct ip_vs_sync_buff *sb;
@@ -328,11 +342,15 @@ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(void)
 		kfree(sb);
 		return NULL;
 	}
-	sb->mesg->nr_conns = 0;
+	sb->mesg->reserved = 0;  /* old nr_conns i.e. must be zeo now */
+	sb->mesg->version = SYNC_PROTO_VER;
 	sb->mesg->syncid = ip_vs_master_syncid;
-	sb->mesg->size = 4;
-	sb->head = (unsigned char *)sb->mesg + 4;
+	sb->mesg->size = sizeof(struct ip_vs_sync_mesg);
+	sb->mesg->nr_conns = 0;
+	sb->mesg->spare = 0;
+	sb->head = (unsigned char *)sb->mesg + sizeof(struct ip_vs_sync_mesg);
 	sb->end = (unsigned char *)sb->mesg + sync_send_mesg_maxlen;
+
 	sb->firstuse = jiffies;
 	return sb;
 }
@@ -373,18 +391,60 @@ get_curr_sync_buff(unsigned long time)
 	return sb;
 }
 
-
 /*
  *      Add an ip_vs_conn information into the current sync_buff.
  *      Called by ip_vs_in.
+ *      Sending Version 1 messages
  */
-void ip_vs_sync_conn(const struct ip_vs_conn *cp)
+void ip_vs_sync_conn(struct ip_vs_conn *cp)
 {
 	struct ip_vs_sync_mesg *m;
-	struct ip_vs_sync_conn_v0 *s;
-	int len;
+	union ip_vs_sync_conn *s;
+	__u8 *p;
+	unsigned int len, pe_name_len, pad;
+
+	/* Do not sync ONE PACKET */
+	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+		goto control;
+sloop:
+	/* Sanity checks */
+	pe_name_len = 0;
+	if (cp->pe_data_len) {
+		if (!cp->pe_data || !cp->dest) {
+			IP_VS_ERR_RL("SYNC, connection pe_data invalid\n");
+			return;
+		}
+		pe_name_len = strnlen(cp->pe->name, IP_VS_PENAME_MAXLEN);
+	}
 
 	spin_lock(&curr_sb_lock);
+
+#ifdef CONFIG_IP_VS_IPV6
+	if (cp->af == AF_INET6)
+		len = sizeof(struct ip_vs_sync_v6);
+	else
+#endif
+		len = sizeof(struct ip_vs_sync_v4);
+
+	if (cp->flags & IP_VS_CONN_F_SEQ_MASK)
+		len += sizeof(struct ip_vs_sync_conn_options) + 2;
+
+	if (cp->pe_data_len)
+		len += cp->pe_data_len + 2;	/* + Param hdr field */
+	if (pe_name_len)
+		len += pe_name_len + 2;
+
+	/* check if there is a space for this one  */
+	pad = 0;
+	if (curr_sb) {
+		pad = (4 - (size_t)curr_sb->head) & 3;
+		if (curr_sb->head + len + pad > curr_sb->end) {
+			sb_queue_tail(curr_sb);
+			curr_sb = NULL;
+			pad = 0;
+		}
+	}
+
 	if (!curr_sb) {
 		if (!(curr_sb=ip_vs_sync_buff_create())) {
 			spin_unlock(&curr_sb_lock);
@@ -393,41 +453,84 @@ void ip_vs_sync_conn(const struct ip_vs_conn *cp)
 		}
 	}
 
-	len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE :
-		SIMPLE_CONN_SIZE;
 	m = curr_sb->mesg;
-	s = (struct ip_vs_sync_conn_v0 *)curr_sb->head;
-
-	/* copy members */
-	s->protocol = cp->protocol;
-	s->cport = cp->cport;
-	s->vport = cp->vport;
-	s->dport = cp->dport;
-	s->caddr = cp->caddr.ip;
-	s->vaddr = cp->vaddr.ip;
-	s->daddr = cp->daddr.ip;
-	s->flags = htons(cp->flags & ~IP_VS_CONN_F_HASHED);
-	s->state = htons(cp->state);
-	if (cp->flags & IP_VS_CONN_F_SEQ_MASK) {
-		struct ip_vs_sync_conn_options *opt =
-			(struct ip_vs_sync_conn_options *)&s[1];
-		memcpy(opt, &cp->in_seq, sizeof(*opt));
-	}
-
+	p = curr_sb->head;
+	curr_sb->head += pad + len;
+	m->size += pad + len;
+	/* Add ev. padding from prev. sync_conn */
+	while (pad--)
+		*(p++) = 0;
+
+	s = (union ip_vs_sync_conn *)p;
+
+	/* Set message type  & copy members */
+	s->v4.type = (cp->af == AF_INET6 ? STYPE_F_INET6 : 0);
+	s->v4.ver_size = htons(len & SVER_MASK);	/* Version 0 */
+	s->v4.flags = htonl(cp->flags & ~IP_VS_CONN_F_HASHED);
+	s->v4.state = htons(cp->state);
+	s->v4.protocol = cp->protocol;
+	s->v4.cport = cp->cport;
+	s->v4.vport = cp->vport;
+	s->v4.dport = cp->dport;
+	s->v4.fwmark = htonl(cp->fwmark);
+	s->v4.timeout = htonl(cp->timeout / HZ);
 	m->nr_conns++;
-	m->size += len;
-	curr_sb->head += len;
 
-	/* check if there is a space for next one */
-	if (curr_sb->head+FULL_CONN_SIZE > curr_sb->end) {
-		sb_queue_tail(curr_sb);
-		curr_sb = NULL;
+#ifdef CONFIG_IP_VS_IPV6
+	if (cp->af == AF_INET6) {
+		p += sizeof(struct ip_vs_sync_v6);
+		ipv6_addr_copy(&s->v6.caddr, &cp->caddr.in6);
+		ipv6_addr_copy(&s->v6.vaddr, &cp->vaddr.in6);
+		ipv6_addr_copy(&s->v6.daddr, &cp->daddr.in6);
+	} else
+#endif
+	{
+		p += sizeof(struct ip_vs_sync_v4);	/* options ptr */
+		s->v4.caddr = cp->caddr.ip;
+		s->v4.vaddr = cp->vaddr.ip;
+		s->v4.daddr = cp->daddr.ip;
+	}
+	if (cp->flags & IP_VS_CONN_F_SEQ_MASK) {
+		*(p++) = IPVS_OPT_SEQ_DATA;
+		*(p++) = sizeof(struct ip_vs_sync_conn_options);
+		hton_seq((struct ip_vs_seq *)p, &cp->in_seq);
+		p += sizeof(struct ip_vs_seq);
+		hton_seq((struct ip_vs_seq *)p, &cp->out_seq);
+		p += sizeof(struct ip_vs_seq);
 	}
+	/* Handle pe data */
+	if (cp->pe_data_len && cp->pe_data) {
+		*(p++) = IPVS_OPT_PE_DATA;
+		*(p++) = cp->pe_data_len;
+		memcpy(p, cp->pe_data, cp->pe_data_len);
+		p += cp->pe_data_len;
+		if (pe_name_len) {
+			/* Add PE_NAME */
+			*(p++) = IPVS_OPT_PE_NAME;
+			*(p++) = pe_name_len;
+			memcpy(p, cp->pe->name, pe_name_len);
+			p += pe_name_len;
+		}
+	}
+
 	spin_unlock(&curr_sb_lock);
 
+control:
 	/* synchronize its controller if it has */
-	if (cp->control)
-		ip_vs_sync_conn(cp->control);
+	cp = cp->control;
+	if (!cp)
+		return;
+	/*
+	 * Reduce sync rate for templates
+	 * i.e only increment in_pkts for Templates.
+	 */
+	if (cp->flags & IP_VS_CONN_F_TEMPLATE) {
+		int pkts = atomic_add_return(1, &cp->in_pkts);
+
+		if (pkts % sysctl_ip_vs_sync_threshold[1] != 1)
+			return;
+	}
+	goto sloop;
 }
 
 /*
@@ -596,7 +699,7 @@ static void ip_vs_proc_conn(struct ip_vs_conn_param *param,  unsigned flags,
  */
 static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
 {
-	struct ip_vs_sync_mesg *m = (struct ip_vs_sync_mesg *)buffer;
+	struct ip_vs_sync_mesg_v0 *m = (struct ip_vs_sync_mesg_v0 *)buffer;
 	struct ip_vs_sync_conn_v0 *s;
 	struct ip_vs_sync_conn_options *opt;
 	struct ip_vs_protocol *pp;
@@ -604,7 +707,7 @@ static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
 	char *p;
 	int i;
 
-	p = (char *)buffer + sizeof(struct ip_vs_sync_mesg);
+	p = (char *)buffer + sizeof(struct ip_vs_sync_mesg_v0);
 	for (i=0; i<m->nr_conns; i++) {
 		unsigned flags, state;
 
@@ -848,11 +951,11 @@ out:
  */
 static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
 {
-	struct ip_vs_sync_mesg_v2 *m2 = (struct ip_vs_sync_mesg_v2 *)buffer;
+	struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer;
 	__u8 *p, *msg_end;
-	unsigned int i, nr_conns;
+	int i, nr_conns;
 
-	if (buflen < sizeof(struct ip_vs_sync_mesg)) {
+	if (buflen < sizeof(struct ip_vs_sync_mesg_v0)) {
 		IP_VS_DBG(2, "BACKUP, message header too short\n");
 		return;
 	}
@@ -872,7 +975,7 @@ static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
 	if ((m2->version == SYNC_PROTO_VER) && (m2->reserved == 0)
 	    && (m2->spare == 0)) {
 
-		msg_end = buffer + sizeof(struct ip_vs_sync_mesg_v2);
+		msg_end = buffer + sizeof(struct ip_vs_sync_mesg);
 		nr_conns = m2->nr_conns;
 
 		for (i=0; i<nr_conns; i++) {
-- 
1.7.2.3

[PATCH 31/79] IPVS: Backup, adding version 0 sending capabilities

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

This patch adds a sysclt net.ipv4.vs.sync_version
that can be used to send sync msg in version 0 or 1 format.

sync_version value is logical,
     Value 1 (default) New version
           0 Plain old version

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |    2 +
 net/netfilter/ipvs/ip_vs_ctl.c  |   28 ++++++++-
 net/netfilter/ipvs/ip_vs_sync.c |  134 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 163 insertions(+), 1 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index a715f3d..d858264 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -883,7 +883,9 @@ extern int sysctl_ip_vs_conntrack;
 extern int sysctl_ip_vs_snat_reroute;
 extern struct ip_vs_stats ip_vs_stats;
 extern const struct ctl_path net_vs_ctl_path[];
+extern int sysctl_ip_vs_sync_ver;
 
+extern void ip_vs_sync_switch_mode(int mode);
 extern struct ip_vs_service *
 ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index a5bd002..d12a13c 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -92,7 +92,7 @@ int sysctl_ip_vs_nat_icmp_send = 0;
 int sysctl_ip_vs_conntrack;
 #endif
 int sysctl_ip_vs_snat_reroute = 1;
-
+int sysctl_ip_vs_sync_ver = 1;		/* Default version of sync proto */
 
 #ifdef CONFIG_IP_VS_DEBUG
 static int sysctl_ip_vs_debug_level = 0;
@@ -1536,6 +1536,25 @@ proc_do_sync_threshold(ctl_table *table, int write,
 	return rc;
 }
 
+static int
+proc_do_sync_mode(ctl_table *table, int write,
+		     void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int *valp = table->data;
+	int val = *valp;
+	int rc;
+
+	rc = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (write && (*valp != val)) {
+		if ((*valp < 0) || (*valp > 1)) {
+			/* Restore the correct value */
+			*valp = val;
+		} else {
+			ip_vs_sync_switch_mode(val);
+		}
+	}
+	return rc;
+}
 
 /*
  *	IPVS sysctl table (under the /proc/sys/net/ipv4/vs/)
@@ -1602,6 +1621,13 @@ static struct ctl_table vs_vars[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.procname	= "sync_version",
+		.data		= &sysctl_ip_vs_sync_ver,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_do_sync_mode,
+	},
 #if 0
 	{
 		.procname	= "timeout_established",
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index df5abf0..c1c167a 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -5,6 +5,18 @@
  *              high-performance and highly available server based on a
  *              cluster of servers.
  *
+ * Version 1,   is capable of handling both version 0 and 1 messages.
+ *              Version 0 is the plain old format.
+ *              Note Version 0 receivers will just drop Ver 1 messages.
+ *              Version 1 is capable of handle IPv6, Persistence data,
+ *              time-outs, and firewall marks.
+ *              In ver.1 "ip_vs_sync_conn_options" will be sent in netw. order.
+ *              Ver. 0 can be turned on by sysctl -w net.ipv4.vs.sync_version=0
+ *
+ * Definitions  Message: is a complete datagram
+ *              Sync_conn: is a part of a Message
+ *              Param Data is an option to a Sync_conn.
+ *
  * Authors:     Wensong Zhang <wensong@linuxvirtualserver.org>
  *
  * ip_vs_sync:  sync connection info from master load balancer to backups
@@ -15,6 +27,8 @@
  *	Alexandre Cassen	:	Added SyncID support for incoming sync
  *					messages filtering.
  *	Justin Ossevoort	:	Fix endian problem on sync message size.
+ *	Hans Schillstrom	:	Added Version 1: i.e. IPv6,
+ *					Persistence support, fwmark and time-out.
  */
 
 #define KMSG_COMPONENT "IPVS"
@@ -392,6 +406,121 @@ get_curr_sync_buff(unsigned long time)
 }
 
 /*
+ * Switch mode from sending version 0 or 1
+ *  - must handle sync_buf
+ */
+void ip_vs_sync_switch_mode(int mode) {
+
+	if (!ip_vs_sync_state & IP_VS_STATE_MASTER)
+		return;
+	if (mode == sysctl_ip_vs_sync_ver || !curr_sb)
+		return;
+
+	spin_lock_bh(&curr_sb_lock);
+	/* Buffer empty ? then let buf_create do the job  */
+	if ( curr_sb->mesg->size <=  sizeof(struct ip_vs_sync_mesg)) {
+		kfree(curr_sb);
+		curr_sb = NULL;
+	} else {
+		spin_lock_bh(&ip_vs_sync_lock);
+		if (ip_vs_sync_state & IP_VS_STATE_MASTER)
+			list_add_tail(&curr_sb->list, &ip_vs_sync_queue);
+		else
+			ip_vs_sync_buff_release(curr_sb);
+		spin_unlock_bh(&ip_vs_sync_lock);
+	}
+	spin_unlock_bh(&curr_sb_lock);
+}
+
+/*
+ * Create a new sync buffer for Version 0 proto.
+ */
+static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create_v0(void)
+{
+	struct ip_vs_sync_buff *sb;
+	struct ip_vs_sync_mesg_v0 *mesg;
+
+	if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC)))
+		return NULL;
+
+	if (!(sb->mesg=kmalloc(sync_send_mesg_maxlen, GFP_ATOMIC))) {
+		kfree(sb);
+		return NULL;
+	}
+	mesg = (struct ip_vs_sync_mesg_v0 *)sb->mesg;
+	mesg->nr_conns = 0;
+	mesg->syncid = ip_vs_master_syncid;
+	mesg->size = 4;
+	sb->head = (unsigned char *)mesg + 4;
+	sb->end = (unsigned char *)mesg + sync_send_mesg_maxlen;
+	sb->firstuse = jiffies;
+	return sb;
+}
+
+/*
+ *      Version 0 , could be switched in by sys_ctl.
+ *      Add an ip_vs_conn information into the current sync_buff.
+ */
+void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
+{
+	struct ip_vs_sync_mesg_v0 *m;
+	struct ip_vs_sync_conn_v0 *s;
+	int len;
+
+	if (unlikely(cp->af != AF_INET))
+		return;
+	/* Do not sync ONE PACKET */
+	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+		return;
+
+	spin_lock(&curr_sb_lock);
+	if (!curr_sb) {
+		if (!(curr_sb=ip_vs_sync_buff_create_v0())) {
+			spin_unlock(&curr_sb_lock);
+			pr_err("ip_vs_sync_buff_create failed.\n");
+			return;
+		}
+	}
+
+	len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE :
+		SIMPLE_CONN_SIZE;
+	m = (struct ip_vs_sync_mesg_v0 *)curr_sb->mesg;
+	s = (struct ip_vs_sync_conn_v0 *)curr_sb->head;
+
+	/* copy members */
+	s->reserved = 0;
+	s->protocol = cp->protocol;
+	s->cport = cp->cport;
+	s->vport = cp->vport;
+	s->dport = cp->dport;
+	s->caddr = cp->caddr.ip;
+	s->vaddr = cp->vaddr.ip;
+	s->daddr = cp->daddr.ip;
+	s->flags = htons(cp->flags & ~IP_VS_CONN_F_HASHED);
+	s->state = htons(cp->state);
+	if (cp->flags & IP_VS_CONN_F_SEQ_MASK) {
+		struct ip_vs_sync_conn_options *opt =
+			(struct ip_vs_sync_conn_options *)&s[1];
+		memcpy(opt, &cp->in_seq, sizeof(*opt));
+	}
+
+	m->nr_conns++;
+	m->size += len;
+	curr_sb->head += len;
+
+	/* check if there is a space for next one */
+	if (curr_sb->head + FULL_CONN_SIZE > curr_sb->end) {
+		sb_queue_tail(curr_sb);
+		curr_sb = NULL;
+	}
+	spin_unlock(&curr_sb_lock);
+
+	/* synchronize its controller if it has */
+	if (cp->control)
+		ip_vs_sync_conn(cp->control);
+}
+
+/*
  *      Add an ip_vs_conn information into the current sync_buff.
  *      Called by ip_vs_in.
  *      Sending Version 1 messages
@@ -403,6 +532,11 @@ void ip_vs_sync_conn(struct ip_vs_conn *cp)
 	__u8 *p;
 	unsigned int len, pe_name_len, pad;
 
+	/* Handle old version of the protocol */
+	if (sysctl_ip_vs_sync_ver == 0) {
+		ip_vs_sync_conn_v0(cp);
+		return;
+	}
 	/* Do not sync ONE PACKET */
 	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
 		goto control;
-- 
1.7.2.3

[PATCH 32/79] netfilter: xtables: use guarded types

[kaber]

From: Jan Engelhardt <jengelh@medozas.de>

We are supposed to use the kernel's own types in userspace exports.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/xt_CT.h          |   10 +++++-----
 include/linux/netfilter/xt_TCPOPTSTRIP.h |    2 +-
 include/linux/netfilter/xt_TPROXY.h      |    8 ++++----
 include/linux/netfilter/xt_cluster.h     |    8 ++++----
 include/linux/netfilter/xt_quota.h       |    6 +++---
 include/linux/netfilter/xt_time.h        |   14 +++++++-------
 include/linux/netfilter/xt_u32.h         |   16 ++++++++--------
 7 files changed, 32 insertions(+), 32 deletions(-)

diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h
index 1b56410..fbf4c56 100644
--- a/include/linux/netfilter/xt_CT.h
+++ b/include/linux/netfilter/xt_CT.h
@@ -4,11 +4,11 @@
 #define XT_CT_NOTRACK	0x1
 
 struct xt_ct_target_info {
-	u_int16_t	flags;
-	u_int16_t	zone;
-	u_int32_t	ct_events;
-	u_int32_t	exp_events;
-	char		helper[16];
+	__u16 flags;
+	__u16 zone;
+	__u32 ct_events;
+	__u32 exp_events;
+	char helper[16];
 
 	/* Used internally by the kernel */
 	struct nf_conn	*ct __attribute__((aligned(8)));
diff --git a/include/linux/netfilter/xt_TCPOPTSTRIP.h b/include/linux/netfilter/xt_TCPOPTSTRIP.h
index 2db5432..342ef14 100644
--- a/include/linux/netfilter/xt_TCPOPTSTRIP.h
+++ b/include/linux/netfilter/xt_TCPOPTSTRIP.h
@@ -7,7 +7,7 @@
 	(((1U << (idx & 31)) & bmap[(idx) >> 5]) != 0)
 
 struct xt_tcpoptstrip_target_info {
-	u_int32_t strip_bmap[8];
+	__u32 strip_bmap[8];
 };
 
 #endif /* _XT_TCPOPTSTRIP_H */
diff --git a/include/linux/netfilter/xt_TPROXY.h b/include/linux/netfilter/xt_TPROXY.h
index 3f3d693..8097e0b 100644
--- a/include/linux/netfilter/xt_TPROXY.h
+++ b/include/linux/netfilter/xt_TPROXY.h
@@ -5,15 +5,15 @@
  * redirection. We can get rid of that whenever we get support for
  * mutliple targets in the same rule. */
 struct xt_tproxy_target_info {
-	u_int32_t mark_mask;
-	u_int32_t mark_value;
+	__u32 mark_mask;
+	__u32 mark_value;
 	__be32 laddr;
 	__be16 lport;
 };
 
 struct xt_tproxy_target_info_v1 {
-	u_int32_t mark_mask;
-	u_int32_t mark_value;
+	__u32 mark_mask;
+	__u32 mark_value;
 	union nf_inet_addr laddr;
 	__be16 lport;
 };
diff --git a/include/linux/netfilter/xt_cluster.h b/include/linux/netfilter/xt_cluster.h
index 8866826..66cfa3c 100644
--- a/include/linux/netfilter/xt_cluster.h
+++ b/include/linux/netfilter/xt_cluster.h
@@ -6,10 +6,10 @@ enum xt_cluster_flags {
 };
 
 struct xt_cluster_match_info {
-	u_int32_t		total_nodes;
-	u_int32_t		node_mask;
-	u_int32_t		hash_seed;
-	u_int32_t		flags;
+	__u32 total_nodes;
+	__u32 node_mask;
+	__u32 hash_seed;
+	__u32 flags;
 };
 
 #define XT_CLUSTER_NODES_MAX	32
diff --git a/include/linux/netfilter/xt_quota.h b/include/linux/netfilter/xt_quota.h
index b0d28c6..8bda65f 100644
--- a/include/linux/netfilter/xt_quota.h
+++ b/include/linux/netfilter/xt_quota.h
@@ -9,9 +9,9 @@ enum xt_quota_flags {
 struct xt_quota_priv;
 
 struct xt_quota_info {
-	u_int32_t		flags;
-	u_int32_t		pad;
-	aligned_u64		quota;
+	__u32 flags;
+	__u32 pad;
+	aligned_u64 quota;
 
 	/* Used internally by the kernel */
 	struct xt_quota_priv	*master;
diff --git a/include/linux/netfilter/xt_time.h b/include/linux/netfilter/xt_time.h
index 14b6df4..b8bd456 100644
--- a/include/linux/netfilter/xt_time.h
+++ b/include/linux/netfilter/xt_time.h
@@ -2,13 +2,13 @@
 #define _XT_TIME_H 1
 
 struct xt_time_info {
-	u_int32_t date_start;
-	u_int32_t date_stop;
-	u_int32_t daytime_start;
-	u_int32_t daytime_stop;
-	u_int32_t monthdays_match;
-	u_int8_t weekdays_match;
-	u_int8_t flags;
+	__u32 date_start;
+	__u32 date_stop;
+	__u32 daytime_start;
+	__u32 daytime_stop;
+	__u32 monthdays_match;
+	__u8 weekdays_match;
+	__u8 flags;
 };
 
 enum {
diff --git a/include/linux/netfilter/xt_u32.h b/include/linux/netfilter/xt_u32.h
index 9947f56..e8c3d87 100644
--- a/include/linux/netfilter/xt_u32.h
+++ b/include/linux/netfilter/xt_u32.h
@@ -9,13 +9,13 @@ enum xt_u32_ops {
 };
 
 struct xt_u32_location_element {
-	u_int32_t number;
-	u_int8_t nextop;
+	__u32 number;
+	__u8 nextop;
 };
 
 struct xt_u32_value_element {
-	u_int32_t min;
-	u_int32_t max;
+	__u32 min;
+	__u32 max;
 };
 
 /*
@@ -27,14 +27,14 @@ struct xt_u32_value_element {
 struct xt_u32_test {
 	struct xt_u32_location_element location[XT_U32_MAXSIZE+1];
 	struct xt_u32_value_element value[XT_U32_MAXSIZE+1];
-	u_int8_t nnums;
-	u_int8_t nvalues;
+	__u8 nnums;
+	__u8 nvalues;
 };
 
 struct xt_u32 {
 	struct xt_u32_test tests[XT_U32_MAXSIZE+1];
-	u_int8_t ntests;
-	u_int8_t invert;
+	__u8 ntests;
+	__u8 invert;
 };
 
 #endif /* _XT_U32_H */
-- 
1.7.2.3

[PATCH 33/79] netfilter: fix compilation when conntrack is disabled but tproxy is enabled

[kaber]

From: KOVACS Krisztian <hidden@balabit.hu>

The IPv6 tproxy patches split IPv6 defragmentation off of conntrack, but
failed to update the #ifdef stanzas guarding the defragmentation related
fields and code in skbuff and conntrack related code in nf_defrag_ipv6.c.

This patch adds the required #ifdefs so that IPv6 tproxy can truly be used
without connection tracking.

Original report:
http://marc.info/?l=linux-netdev&m=129010118516341&w=2

Reported-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: KOVACS Krisztian <hidden@balabit.hu>
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/skbuff.h                         |   15 +++++++++++++++
 include/net/netfilter/ipv6/nf_conntrack_ipv6.h |   10 ----------
 include/net/netfilter/ipv6/nf_defrag_ipv6.h    |   10 ++++++++++
 net/core/skbuff.c                              |    2 ++
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c      |    8 +++++++-
 5 files changed, 34 insertions(+), 11 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e6ba898..4f2db79 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -255,6 +255,11 @@ typedef unsigned int sk_buff_data_t;
 typedef unsigned char *sk_buff_data_t;
 #endif
 
+#if defined(CONFIG_NF_DEFRAG_IPV4) || defined(CONFIG_NF_DEFRAG_IPV4_MODULE) || \
+    defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
+#define NET_SKBUFF_NF_DEFRAG_NEEDED 1
+#endif
+
 /** 
  *	struct sk_buff - socket buffer
  *	@next: Next buffer in list
@@ -362,6 +367,8 @@ struct sk_buff {
 	void			(*destructor)(struct sk_buff *skb);
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	struct nf_conntrack	*nfct;
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 	struct sk_buff		*nfct_reasm;
 #endif
 #ifdef CONFIG_BRIDGE_NETFILTER
@@ -2051,6 +2058,8 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct)
 	if (nfct)
 		atomic_inc(&nfct->use);
 }
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 static inline void nf_conntrack_get_reasm(struct sk_buff *skb)
 {
 	if (skb)
@@ -2079,6 +2088,8 @@ static inline void nf_reset(struct sk_buff *skb)
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(skb->nfct);
 	skb->nfct = NULL;
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 	nf_conntrack_put_reasm(skb->nfct_reasm);
 	skb->nfct_reasm = NULL;
 #endif
@@ -2095,6 +2106,8 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 	dst->nfct = src->nfct;
 	nf_conntrack_get(src->nfct);
 	dst->nfctinfo = src->nfctinfo;
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 	dst->nfct_reasm = src->nfct_reasm;
 	nf_conntrack_get_reasm(src->nfct_reasm);
 #endif
@@ -2108,6 +2121,8 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(dst->nfct);
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 	nf_conntrack_put_reasm(dst->nfct_reasm);
 #endif
 #ifdef CONFIG_BRIDGE_NETFILTER
diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
index 1ee717e..a4c9936 100644
--- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h
@@ -7,16 +7,6 @@ extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6;
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6;
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6;
 
-extern int nf_ct_frag6_init(void);
-extern void nf_ct_frag6_cleanup(void);
-extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
-extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
-			       struct net_device *in,
-			       struct net_device *out,
-			       int (*okfn)(struct sk_buff *));
-
-struct inet_frags_ctl;
-
 #include <linux/sysctl.h>
 extern struct ctl_table nf_ct_ipv6_sysctl_table[];
 
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index 94dd54d..fd79c9a 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -3,4 +3,14 @@
 
 extern void nf_defrag_ipv6_enable(void);
 
+extern int nf_ct_frag6_init(void);
+extern void nf_ct_frag6_cleanup(void);
+extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
+extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
+			       struct net_device *in,
+			       struct net_device *out,
+			       int (*okfn)(struct sk_buff *));
+
+struct inet_frags_ctl;
+
 #endif /* _NF_DEFRAG_IPV6_H */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 104f844..74ebf4b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -380,6 +380,8 @@ static void skb_release_head_state(struct sk_buff *skb)
 	}
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(skb->nfct);
+#endif
+#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
 	nf_conntrack_put_reasm(skb->nfct_reasm);
 #endif
 #ifdef CONFIG_BRIDGE_NETFILTER
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index 99abfb5..97c5b21 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -19,13 +19,15 @@
 
 #include <linux/netfilter_ipv6.h>
 #include <linux/netfilter_bridge.h>
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
+#endif
+#include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 
 static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
@@ -33,8 +35,10 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
 {
 	u16 zone = NF_CT_DEFAULT_ZONE;
 
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	if (skb->nfct)
 		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
+#endif
 
 #ifdef CONFIG_BRIDGE_NETFILTER
 	if (skb->nf_bridge &&
@@ -56,9 +60,11 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
 {
 	struct sk_buff *reasm;
 
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	/* Previously seen (loopback)?	*/
 	if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct))
 		return NF_ACCEPT;
+#endif
 
 	reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb));
 	/* queued */
-- 
1.7.2.3

[PATCH 34/79] IPVS: netns, add basic init per netns.

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

Preparation for network name-space init, in this stage
some empty functions exists.

In most files there is a check if it is root ns i.e. init_net
if (!net_eq(net, &init_net))
        return ...
this will be removed by the last patch, when enabling name-space.

*v3
 ip_vs_conn.c merge error corrected.
 net_ipvs #ifdef removed as sugested by Jan Engelhardt

[ horms@verge.net.au: Removed whitespace-change-only hunks ]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h              |   11 ++++++
 include/net/net_namespace.h      |    2 +
 include/net/netns/ip_vs.h        |   25 +++++++++++++++
 net/netfilter/ipvs/ip_vs_app.c   |   28 ++++++++++++++--
 net/netfilter/ipvs/ip_vs_conn.c  |   34 +++++++++++++++++---
 net/netfilter/ipvs/ip_vs_core.c  |   63 ++++++++++++++++++++++++++++++++++++-
 net/netfilter/ipvs/ip_vs_ctl.c   |   49 ++++++++++++++++++++++++-----
 net/netfilter/ipvs/ip_vs_est.c   |   20 +++++++++++-
 net/netfilter/ipvs/ip_vs_ftp.c   |   34 ++++++++++++++++++--
 net/netfilter/ipvs/ip_vs_lblc.c  |   37 ++++++++++++++++++++--
 net/netfilter/ipvs/ip_vs_lblcr.c |   38 ++++++++++++++++++++--
 net/netfilter/ipvs/ip_vs_proto.c |   19 +++++++++++
 net/netfilter/ipvs/ip_vs_sync.c  |   27 ++++++++++++++++
 13 files changed, 354 insertions(+), 33 deletions(-)
 create mode 100644 include/net/netns/ip_vs.h

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index d858264..c1c2ece 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -28,6 +28,15 @@
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 #include <net/netfilter/nf_conntrack.h>
 #endif
+#include <net/net_namespace.h>		/* Netw namespace */
+
+/*
+ * Generic access of ipvs struct
+ */
+static inline struct netns_ipvs *net_ipvs(struct net* net)
+{
+	return net->ipvs;
+}
 
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
@@ -922,6 +931,8 @@ extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
 extern int stop_sync_thread(int state);
 extern void ip_vs_sync_conn(struct ip_vs_conn *cp);
+extern int ip_vs_sync_init(void);
+extern void ip_vs_sync_cleanup(void);
 
 
 /*
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 1bf812b..b3b4a34 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -20,6 +20,7 @@
 #include <net/netns/conntrack.h>
 #endif
 #include <net/netns/xfrm.h>
+#include <net/netns/ip_vs.h>
 
 struct proc_dir_entry;
 struct net_device;
@@ -94,6 +95,7 @@ struct net {
 #ifdef CONFIG_XFRM
 	struct netns_xfrm	xfrm;
 #endif
+	struct netns_ipvs	*ipvs;
 };
 
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
new file mode 100644
index 0000000..12fe840
--- /dev/null
+++ b/include/net/netns/ip_vs.h
@@ -0,0 +1,25 @@
+/*
+ *  IP Virtual Server
+ *  Data structure for network namspace
+ *
+ */
+
+#ifndef IP_VS_H_
+#define IP_VS_H_
+
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/list_nulls.h>
+#include <linux/ip_vs.h>
+#include <asm/atomic.h>
+#include <linux/in.h>
+
+struct ip_vs_stats;
+struct ip_vs_sync_buff;
+struct ctl_table_header;
+
+struct netns_ipvs {
+	int			gen;		/* Generation */
+};
+
+#endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index a475ede..40b09cc 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -569,15 +569,35 @@ 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);
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	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 66e4662..7c1b502 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1201,11 +1201,36 @@ static void ip_vs_conn_flush(void)
 		goto flush_again;
 	}
 }
+/*
+ * per netns init and exit
+ */
+int __net_init __ip_vs_conn_init(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
 
+	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)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+
+	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 +1268,21 @@ 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)
 {
+	unregister_pernet_subsys(&ipvs_conn_ops);
 	/* flush all the connection entries first */
 	ip_vs_conn_flush();
 
 	/* 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 5287771..206f40c 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)
@@ -1813,6 +1820,44 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 #endif
 };
 
+/*
+ *	Initialize IP Virtual Server netns mem.
+ */
+static int __net_init __ip_vs_init(struct net *net)
+{
+	struct netns_ipvs *ipvs;
+
+	if (!net_eq(net, &init_net)) {
+		pr_err("The final patch for enabling netns is missing\n");
+		return -EPERM;
+	}
+	ipvs = net_generic(net, ip_vs_net_id);
+	if (ipvs == NULL) {
+		pr_err("%s(): no memory.\n", __func__);
+		return -ENOMEM;
+	}
+	/* Counters used for creating unique names */
+	ipvs->gen = atomic_read(&ipvs_netns_cnt);
+	atomic_inc(&ipvs_netns_cnt);
+	net->ipvs = ipvs;
+	printk(KERN_INFO "IPVS: Creating netns size=%lu id=%d\n",
+			 sizeof(struct netns_ipvs), ipvs->gen);
+	return 0;
+}
+
+static void __net_exit __ip_vs_cleanup(struct net *net)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	IP_VS_DBG(10, "ipvs netns %d released\n", ipvs->gen);
+}
+
+static struct pernet_operations ipvs_core_ops = {
+	.init = __ip_vs_init,
+	.exit = __ip_vs_cleanup,
+	.id   = &ip_vs_net_id,
+	.size = sizeof(struct netns_ipvs),
+};
 
 /*
  *	Initialize IP Virtual Server
@@ -1821,8 +1866,11 @@ static int __init ip_vs_init(void)
 {
 	int ret;
 
-	ip_vs_estimator_init();
+	ret = register_pernet_subsys(&ipvs_core_ops);	/* Alloc ip_vs struct */
+	if (ret < 0)
+		return ret;
 
+	ip_vs_estimator_init();
 	ret = ip_vs_control_init();
 	if (ret < 0) {
 		pr_err("can't setup control.\n");
@@ -1843,15 +1891,23 @@ static int __init ip_vs_init(void)
 		goto cleanup_app;
 	}
 
+	ret = ip_vs_sync_init();
+	if (ret < 0) {
+		pr_err("can't setup sync data.\n");
+		goto cleanup_conn;
+	}
+
 	ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	if (ret < 0) {
 		pr_err("can't register hooks.\n");
-		goto cleanup_conn;
+		goto cleanup_sync;
 	}
 
 	pr_info("ipvs loaded.\n");
 	return ret;
 
+cleanup_sync:
+	ip_vs_sync_cleanup();
   cleanup_conn:
 	ip_vs_conn_cleanup();
   cleanup_app:
@@ -1861,17 +1917,20 @@ static int __init ip_vs_init(void)
 	ip_vs_control_cleanup();
   cleanup_estimator:
 	ip_vs_estimator_cleanup();
+	unregister_pernet_subsys(&ipvs_core_ops);	/* free ip_vs struct */
 	return ret;
 }
 
 static void __exit ip_vs_cleanup(void)
 {
 	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
+	ip_vs_sync_cleanup();
 	ip_vs_conn_cleanup();
 	ip_vs_app_cleanup();
 	ip_vs_protocol_cleanup();
 	ip_vs_control_cleanup();
 	ip_vs_estimator_cleanup();
+	unregister_pernet_subsys(&ipvs_core_ops);	/* free ip_vs struct */
 	pr_info("ipvs unloaded.\n");
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index ca49e92..ceeef43 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3406,6 +3406,42 @@ static void ip_vs_genl_unregister(void)
 
 /* End of Generic Netlink interface definitions */
 
+/*
+ * per netns intit/exit func.
+ */
+int __net_init __ip_vs_control_init(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	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);
+	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
+						  vs_vars);
+	if (sysctl_header == NULL)
+		goto err_reg;
+	ip_vs_new_estimator(&ip_vs_stats);
+	return 0;
+
+err_reg:
+	return -ENOMEM;
+}
+
+static void __net_exit __ip_vs_control_cleanup(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+
+	ip_vs_kill_estimator(&ip_vs_stats);
+	unregister_net_sysctl_table(sysctl_header);
+	proc_net_remove(net, "ip_vs_stats");
+	proc_net_remove(net, "ip_vs");
+}
+
+static struct pernet_operations ipvs_control_ops = {
+	.init = __ip_vs_control_init,
+	.exit = __ip_vs_control_cleanup,
+};
 
 int __init ip_vs_control_init(void)
 {
@@ -3437,12 +3473,9 @@ int __init ip_vs_control_init(void)
 		return ret;
 	}
 
-	proc_net_fops_create(&init_net, "ip_vs", 0, &ip_vs_info_fops);
-	proc_net_fops_create(&init_net, "ip_vs_stats",0, &ip_vs_stats_fops);
-
-	sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars);
-
-	ip_vs_new_estimator(&ip_vs_stats);
+	ret = register_pernet_subsys(&ipvs_control_ops);
+	if (ret)
+		return ret;
 
 	/* Hook the defense timer */
 	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);
@@ -3459,9 +3492,7 @@ void ip_vs_control_cleanup(void)
 	cancel_delayed_work_sync(&defense_work);
 	cancel_work_sync(&defense_work.work);
 	ip_vs_kill_estimator(&ip_vs_stats);
-	unregister_sysctl_table(sysctl_header);
-	proc_net_remove(&init_net, "ip_vs_stats");
-	proc_net_remove(&init_net, "ip_vs");
+	unregister_pernet_subsys(&ipvs_control_ops);
 	ip_vs_genl_unregister();
 	nf_unregister_sockopt(&ip_vs_sockopts);
 	LeaveFunction(2);
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index ff28801..7417a0c 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -157,13 +157,31 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats)
 	est->outbps = 0;
 }
 
+static int __net_init __ip_vs_estimator_init(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	return 0;
+}
+
+static struct pernet_operations ip_vs_app_ops = {
+	.init = __ip_vs_estimator_init,
+};
+
 int __init ip_vs_estimator_init(void)
 {
+	int rv;
+
+	rv = register_pernet_subsys(&ip_vs_app_ops);
+	if (rv < 0)
+		return rv;
 	mod_timer(&est_timer, jiffies + 2 * HZ);
-	return 0;
+	return rv;
 }
 
 void ip_vs_estimator_cleanup(void)
 {
 	del_timer_sync(&est_timer);
+	unregister_pernet_subsys(&ip_vs_app_ops);
 }
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 84aef65..0e762f3 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -399,15 +399,17 @@ static struct ip_vs_app ip_vs_ftp = {
 	.pkt_in =	ip_vs_ftp_in,
 };
 
-
 /*
- *	ip_vs_ftp initialization
+ *	per netns ip_vs_ftp initialization
  */
-static int __init ip_vs_ftp_init(void)
+static int __net_init __ip_vs_ftp_init(struct net *net)
 {
 	int i, ret;
 	struct ip_vs_app *app = &ip_vs_ftp;
 
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
 	ret = register_ip_vs_app(app);
 	if (ret)
 		return ret;
@@ -427,14 +429,38 @@ static int __init ip_vs_ftp_init(void)
 
 	return ret;
 }
+/*
+ *	netns exit
+ */
+static void __ip_vs_ftp_exit(struct net *net)
+{
+	struct ip_vs_app *app = &ip_vs_ftp;
+
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+
+	unregister_ip_vs_app(app);
+}
+
+static struct pernet_operations ip_vs_ftp_ops = {
+	.init = __ip_vs_ftp_init,
+	.exit = __ip_vs_ftp_exit,
+};
 
+int __init ip_vs_ftp_init(void)
+{
+	int rv;
+
+	rv = register_pernet_subsys(&ip_vs_ftp_ops);
+	return rv;
+}
 
 /*
  *	ip_vs_ftp finish.
  */
 static void __exit ip_vs_ftp_exit(void)
 {
-	unregister_ip_vs_app(&ip_vs_ftp);
+	unregister_pernet_subsys(&ip_vs_ftp_ops);
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 9323f89..84278fb 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -543,23 +543,54 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler =
 	.schedule =		ip_vs_lblc_schedule,
 };
 
+/*
+ *  per netns init.
+ */
+static int __net_init __ip_vs_lblc_init(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
+						  vs_vars_table);
+	if (!sysctl_header)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __net_exit __ip_vs_lblc_exit(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+
+	unregister_net_sysctl_table(sysctl_header);
+}
+
+static struct pernet_operations ip_vs_lblc_ops = {
+	.init = __ip_vs_lblc_init,
+	.exit = __ip_vs_lblc_exit,
+};
 
 static int __init ip_vs_lblc_init(void)
 {
 	int ret;
 
-	sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table);
+	ret = register_pernet_subsys(&ip_vs_lblc_ops);
+	if (ret)
+		return ret;
+
 	ret = register_ip_vs_scheduler(&ip_vs_lblc_scheduler);
 	if (ret)
-		unregister_sysctl_table(sysctl_header);
+		unregister_pernet_subsys(&ip_vs_lblc_ops);
 	return ret;
 }
 
 
 static void __exit ip_vs_lblc_cleanup(void)
 {
-	unregister_sysctl_table(sysctl_header);
 	unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler);
+	unregister_pernet_subsys(&ip_vs_lblc_ops);
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index dbeed8e..7c7396a 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -744,23 +744,53 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler =
 	.schedule =		ip_vs_lblcr_schedule,
 };
 
+/*
+ *  per netns init.
+ */
+static int __net_init __ip_vs_lblcr_init(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
+						  vs_vars_table);
+	if (!sysctl_header)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __net_exit __ip_vs_lblcr_exit(struct net *net)
+{
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+
+	unregister_net_sysctl_table(sysctl_header);
+}
+
+static struct pernet_operations ip_vs_lblcr_ops = {
+	.init = __ip_vs_lblcr_init,
+	.exit = __ip_vs_lblcr_exit,
+};
 
 static int __init ip_vs_lblcr_init(void)
 {
 	int ret;
 
-	sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table);
+	ret = register_pernet_subsys(&ip_vs_lblcr_ops);
+	if (ret)
+		return ret;
+
 	ret = register_ip_vs_scheduler(&ip_vs_lblcr_scheduler);
 	if (ret)
-		unregister_sysctl_table(sysctl_header);
+		unregister_pernet_subsys(&ip_vs_lblcr_ops);
 	return ret;
 }
 
-
 static void __exit ip_vs_lblcr_cleanup(void)
 {
-	unregister_sysctl_table(sysctl_header);
 	unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler);
+	unregister_pernet_subsys(&ip_vs_lblcr_ops);
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index c539983..4539294 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -236,6 +236,23 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
 		ip_vs_tcpudp_debug_packet_v4(pp, skb, offset, msg);
 }
 
+/*
+ * per network name-space init
+ */
+static int __net_init __ip_vs_protocol_init(struct net *net)
+{
+	return 0;
+}
+
+static void __net_exit __ip_vs_protocol_cleanup(struct net *net)
+{
+	/* empty */
+}
+
+static struct pernet_operations ipvs_proto_ops = {
+	.init = __ip_vs_protocol_init,
+	.exit = __ip_vs_protocol_cleanup,
+};
 
 int __init ip_vs_protocol_init(void)
 {
@@ -265,6 +282,7 @@ int __init ip_vs_protocol_init(void)
 	REGISTER_PROTOCOL(&ip_vs_protocol_esp);
 #endif
 	pr_info("Registered protocols (%s)\n", &protocols[2]);
+	return register_pernet_subsys(&ipvs_proto_ops);
 
 	return 0;
 }
@@ -275,6 +293,7 @@ void ip_vs_protocol_cleanup(void)
 	struct ip_vs_protocol *pp;
 	int i;
 
+	unregister_pernet_subsys(&ipvs_proto_ops);
 	/* unregister all the ipvs protocols */
 	for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
 		while ((pp = ip_vs_proto_table[i]) != NULL)
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index c1c167a..3668739 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1639,3 +1639,30 @@ int stop_sync_thread(int state)
 
 	return 0;
 }
+
+/*
+ * Initialize data struct for each netns
+ */
+static int __net_init __ip_vs_sync_init(struct net *net)
+{
+	return 0;
+}
+
+static void __ip_vs_sync_cleanup(struct net *net)
+{
+}
+static struct pernet_operations ipvs_sync_ops = {
+	.init = __ip_vs_sync_init,
+	.exit = __ip_vs_sync_cleanup,
+};
+
+
+int __init ip_vs_sync_init(void)
+{
+	return register_pernet_subsys(&ipvs_sync_ops);
+}
+
+void __exit ip_vs_sync_cleanup(void)
+{
+	unregister_pernet_subsys(&ipvs_sync_ops);
+}
-- 
1.7.2.3

[PATCH 35/79] IPVS: netns to services part 1

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

Services hash tables got netns ptr a hash arg,
While Real Servers (rs) has been moved to ipvs struct.
Two new inline functions added to get net ptr from skb.

Since ip_vs is called from different contexts there is two
places to dig for the net ptr skb->dev or skb->sk
this is handled in skb_net() and skb_sknet()

Global functions, ip_vs_service_get() ip_vs_lookup_real_service()
etc have got  struct net *net as first param.
If possible get net ptr skb etc,
 - if not &init_net is used at this early stage of patching.

ip_vs_ctl.c  procfs not ready for netns yet.

*v3
 Comments by Julian
- __ip_vs_service_find and __ip_vs_svc_fwm_find are fast path,
  net_eq(svc->net, net) so the check is at the end now.
- net = skb_net(skb) in ip_vs_out moved after check for skb_dst.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                   |   64 +++++++++-
 include/net/netns/ip_vs.h             |    8 +
 net/netfilter/ipvs/ip_vs_conn.c       |    2 +-
 net/netfilter/ipvs/ip_vs_core.c       |    4 +-
 net/netfilter/ipvs/ip_vs_ctl.c        |  232 +++++++++++++++++++--------------
 net/netfilter/ipvs/ip_vs_proto_sctp.c |    5 +-
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |    7 +-
 net/netfilter/ipvs/ip_vs_proto_udp.c  |    5 +-
 net/netfilter/ipvs/ip_vs_sync.c       |    2 +-
 9 files changed, 214 insertions(+), 115 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index c1c2ece..d551e0d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -37,6 +37,59 @@ static inline struct netns_ipvs *net_ipvs(struct net* net)
 {
 	return net->ipvs;
 }
+/*
+ * Get net ptr from skb in traffic cases
+ * use skb_sknet when call is from userland (ioctl or netlink)
+ */
+static inline struct net *skb_net(struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_NS
+#ifdef CONFIG_IP_VS_DEBUG
+	/*
+	 * This is used for debug only.
+	 * Start with the most likely hit
+	 * End with BUG
+	 */
+	if (likely(skb->dev && skb->dev->nd_net))
+		return dev_net(skb->dev);
+	if (skb_dst(skb)->dev)
+		return dev_net(skb_dst(skb)->dev);
+	WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n",
+		      __func__, __LINE__);
+	if (likely(skb->sk && skb->sk->sk_net))
+		return sock_net(skb->sk);
+	pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
+		__func__, __LINE__);
+	BUG();
+#else
+	return dev_net(skb->dev ? : skb_dst(skb)->dev);
+#endif
+#else
+	return &init_net;
+#endif
+}
+
+static inline struct net *skb_sknet(struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_NS
+#ifdef CONFIG_IP_VS_DEBUG
+	/* Start with the most likely hit */
+	if (likely(skb->sk && skb->sk->sk_net))
+		return sock_net(skb->sk);
+	WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n",
+		       __func__, __LINE__);
+	if (likely(skb->dev && skb->dev->nd_net))
+		return dev_net(skb->dev);
+	pr_err("There is no net ptr to find in the skb in %s() line:%d\n",
+		__func__, __LINE__);
+	BUG();
+#else
+	return sock_net(skb->sk);
+#endif
+#else
+	return &init_net;
+#endif
+}
 
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
@@ -496,6 +549,7 @@ struct ip_vs_service {
 	unsigned		flags;	  /* service status flags */
 	unsigned		timeout;  /* persistent timeout in ticks */
 	__be32			netmask;  /* grouping granularity */
+	struct net		*net;
 
 	struct list_head	destinations;  /* real server d-linked list */
 	__u32			num_dests;     /* number of servers */
@@ -896,7 +950,7 @@ extern int sysctl_ip_vs_sync_ver;
 
 extern void ip_vs_sync_switch_mode(int mode);
 extern struct ip_vs_service *
-ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
+ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport);
 
 static inline void ip_vs_service_put(struct ip_vs_service *svc)
@@ -905,7 +959,7 @@ static inline void ip_vs_service_put(struct ip_vs_service *svc)
 }
 
 extern struct ip_vs_dest *
-ip_vs_lookup_real_service(int af, __u16 protocol,
+ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
 			  const union nf_inet_addr *daddr, __be16 dport);
 
 extern int ip_vs_use_count_inc(void);
@@ -913,9 +967,9 @@ extern void ip_vs_use_count_dec(void);
 extern int ip_vs_control_init(void);
 extern void ip_vs_control_cleanup(void);
 extern struct ip_vs_dest *
-ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport,
-		const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol,
-		__u32 fwmark);
+ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
+		__be16 dport, const union nf_inet_addr *vaddr, __be16 vport,
+		__u16 protocol, __u32 fwmark);
 extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 12fe840..5b87d22 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -20,6 +20,14 @@ struct ctl_table_header;
 
 struct netns_ipvs {
 	int			gen;		/* Generation */
+	/*
+	 *	Hash table: for real service lookups
+	 */
+	#define IP_VS_RTAB_BITS 4
+	#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
+	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
+
+	struct list_head	rs_table[IP_VS_RTAB_SIZE];
 };
 
 #endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 7c1b502..7a0e79e 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -611,7 +611,7 @@ 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,
+		dest = ip_vs_find_dest(&init_net, cp->af, &cp->daddr, cp->dport,
 				       &cp->vaddr, cp->vport,
 				       cp->protocol, cp->fwmark);
 		ip_vs_bind_dest(cp, dest);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 206f40c..d0616ea 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1031,6 +1031,7 @@ drop:
 static unsigned int
 ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 {
+	struct net *net = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_protocol *pp;
 	struct ip_vs_conn *cp;
@@ -1054,6 +1055,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	if (unlikely(!skb_dst(skb)))
 		return NF_ACCEPT;
 
+	net = skb_net(skb);
 	ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
@@ -1119,7 +1121,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 					  sizeof(_ports), _ports);
 		if (pptr == NULL)
 			return NF_ACCEPT;	/* Not for me */
-		if (ip_vs_lookup_real_service(af, iph.protocol,
+		if (ip_vs_lookup_real_service(net, af, iph.protocol,
 					      &iph.saddr,
 					      pptr[0])) {
 			/*
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index ceeef43..2d7c96b 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -288,15 +288,6 @@ static struct list_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
 static struct list_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];
 
 /*
- *	Hash table: for real service lookups
- */
-#define IP_VS_RTAB_BITS 4
-#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
-#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
-
-static struct list_head ip_vs_rtable[IP_VS_RTAB_SIZE];
-
-/*
  *	Trash for destinations
  */
 static LIST_HEAD(ip_vs_dest_trash);
@@ -311,9 +302,9 @@ static atomic_t ip_vs_nullsvc_counter = ATOMIC_INIT(0);
 /*
  *	Returns hash value for virtual service
  */
-static __inline__ unsigned
-ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr,
-		  __be16 port)
+static inline unsigned
+ip_vs_svc_hashkey(struct net *net, int af, unsigned proto,
+		  const union nf_inet_addr *addr, __be16 port)
 {
 	register unsigned porth = ntohs(port);
 	__be32 addr_fold = addr->ip;
@@ -323,6 +314,7 @@ ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr,
 		addr_fold = addr->ip6[0]^addr->ip6[1]^
 			    addr->ip6[2]^addr->ip6[3];
 #endif
+	addr_fold ^= ((size_t)net>>8);
 
 	return (proto^ntohl(addr_fold)^(porth>>IP_VS_SVC_TAB_BITS)^porth)
 		& IP_VS_SVC_TAB_MASK;
@@ -331,13 +323,13 @@ ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr,
 /*
  *	Returns hash value of fwmark for virtual service lookup
  */
-static __inline__ unsigned ip_vs_svc_fwm_hashkey(__u32 fwmark)
+static inline unsigned ip_vs_svc_fwm_hashkey(struct net *net, __u32 fwmark)
 {
-	return fwmark & IP_VS_SVC_TAB_MASK;
+	return (((size_t)net>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK;
 }
 
 /*
- *	Hashes a service in the ip_vs_svc_table by <proto,addr,port>
+ *	Hashes a service in the ip_vs_svc_table by <netns,proto,addr,port>
  *	or in the ip_vs_svc_fwm_table by fwmark.
  *	Should be called with locked tables.
  */
@@ -353,16 +345,16 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc)
 
 	if (svc->fwmark == 0) {
 		/*
-		 *  Hash it by <protocol,addr,port> in ip_vs_svc_table
+		 *  Hash it by <netns,protocol,addr,port> in ip_vs_svc_table
 		 */
-		hash = ip_vs_svc_hashkey(svc->af, svc->protocol, &svc->addr,
-					 svc->port);
+		hash = ip_vs_svc_hashkey(svc->net, svc->af, svc->protocol,
+					 &svc->addr, svc->port);
 		list_add(&svc->s_list, &ip_vs_svc_table[hash]);
 	} else {
 		/*
-		 *  Hash it by fwmark in ip_vs_svc_fwm_table
+		 *  Hash it by fwmark in svc_fwm_table
 		 */
-		hash = ip_vs_svc_fwm_hashkey(svc->fwmark);
+		hash = ip_vs_svc_fwm_hashkey(svc->net, svc->fwmark);
 		list_add(&svc->f_list, &ip_vs_svc_fwm_table[hash]);
 	}
 
@@ -374,7 +366,7 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc)
 
 
 /*
- *	Unhashes a service from ip_vs_svc_table/ip_vs_svc_fwm_table.
+ *	Unhashes a service from svc_table / svc_fwm_table.
  *	Should be called with locked tables.
  */
 static int ip_vs_svc_unhash(struct ip_vs_service *svc)
@@ -386,10 +378,10 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc)
 	}
 
 	if (svc->fwmark == 0) {
-		/* Remove it from the ip_vs_svc_table table */
+		/* Remove it from the svc_table table */
 		list_del(&svc->s_list);
 	} else {
-		/* Remove it from the ip_vs_svc_fwm_table table */
+		/* Remove it from the svc_fwm_table table */
 		list_del(&svc->f_list);
 	}
 
@@ -400,23 +392,24 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc)
 
 
 /*
- *	Get service by {proto,addr,port} in the service table.
+ *	Get service by {netns, proto,addr,port} in the service table.
  */
 static inline struct ip_vs_service *
-__ip_vs_service_find(int af, __u16 protocol, const union nf_inet_addr *vaddr,
-		    __be16 vport)
+__ip_vs_service_find(struct net *net, int af, __u16 protocol,
+		     const union nf_inet_addr *vaddr, __be16 vport)
 {
 	unsigned hash;
 	struct ip_vs_service *svc;
 
 	/* Check for "full" addressed entries */
-	hash = ip_vs_svc_hashkey(af, protocol, vaddr, vport);
+	hash = ip_vs_svc_hashkey(net, af, protocol, vaddr, vport);
 
 	list_for_each_entry(svc, &ip_vs_svc_table[hash], s_list){
 		if ((svc->af == af)
 		    && ip_vs_addr_equal(af, &svc->addr, vaddr)
 		    && (svc->port == vport)
-		    && (svc->protocol == protocol)) {
+		    && (svc->protocol == protocol)
+		    && net_eq(svc->net, net)) {
 			/* HIT */
 			return svc;
 		}
@@ -430,16 +423,17 @@ __ip_vs_service_find(int af, __u16 protocol, const union nf_inet_addr *vaddr,
  *	Get service by {fwmark} in the service table.
  */
 static inline struct ip_vs_service *
-__ip_vs_svc_fwm_find(int af, __u32 fwmark)
+__ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark)
 {
 	unsigned hash;
 	struct ip_vs_service *svc;
 
 	/* Check for fwmark addressed entries */
-	hash = ip_vs_svc_fwm_hashkey(fwmark);
+	hash = ip_vs_svc_fwm_hashkey(net, fwmark);
 
 	list_for_each_entry(svc, &ip_vs_svc_fwm_table[hash], f_list) {
-		if (svc->fwmark == fwmark && svc->af == af) {
+		if (svc->fwmark == fwmark && svc->af == af
+		    && net_eq(svc->net, net)) {
 			/* HIT */
 			return svc;
 		}
@@ -449,7 +443,7 @@ __ip_vs_svc_fwm_find(int af, __u32 fwmark)
 }
 
 struct ip_vs_service *
-ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
+ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport)
 {
 	struct ip_vs_service *svc;
@@ -459,14 +453,15 @@ ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
 	/*
 	 *	Check the table hashed by fwmark first
 	 */
-	if (fwmark && (svc = __ip_vs_svc_fwm_find(af, fwmark)))
+	svc = __ip_vs_svc_fwm_find(net, af, fwmark);
+	if (fwmark && svc)
 		goto out;
 
 	/*
 	 *	Check the table hashed by <protocol,addr,port>
 	 *	for "full" addressed entries
 	 */
-	svc = __ip_vs_service_find(af, protocol, vaddr, vport);
+	svc = __ip_vs_service_find(net, af, protocol, vaddr, vport);
 
 	if (svc == NULL
 	    && protocol == IPPROTO_TCP
@@ -476,7 +471,7 @@ ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
 		 * Check if ftp service entry exists, the packet
 		 * might belong to FTP data connections.
 		 */
-		svc = __ip_vs_service_find(af, protocol, vaddr, FTPPORT);
+		svc = __ip_vs_service_find(net, af, protocol, vaddr, FTPPORT);
 	}
 
 	if (svc == NULL
@@ -484,7 +479,7 @@ ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
 		/*
 		 * Check if the catch-all port (port zero) exists
 		 */
-		svc = __ip_vs_service_find(af, protocol, vaddr, 0);
+		svc = __ip_vs_service_find(net, af, protocol, vaddr, 0);
 	}
 
   out:
@@ -545,10 +540,10 @@ static inline unsigned ip_vs_rs_hashkey(int af,
 }
 
 /*
- *	Hashes ip_vs_dest in ip_vs_rtable by <proto,addr,port>.
+ *	Hashes ip_vs_dest in rs_table by <proto,addr,port>.
  *	should be called with locked tables.
  */
-static int ip_vs_rs_hash(struct ip_vs_dest *dest)
+static int ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest)
 {
 	unsigned hash;
 
@@ -562,19 +557,19 @@ static int ip_vs_rs_hash(struct ip_vs_dest *dest)
 	 */
 	hash = ip_vs_rs_hashkey(dest->af, &dest->addr, dest->port);
 
-	list_add(&dest->d_list, &ip_vs_rtable[hash]);
+	list_add(&dest->d_list, &ipvs->rs_table[hash]);
 
 	return 1;
 }
 
 /*
- *	UNhashes ip_vs_dest from ip_vs_rtable.
+ *	UNhashes ip_vs_dest from rs_table.
  *	should be called with locked tables.
  */
 static int ip_vs_rs_unhash(struct ip_vs_dest *dest)
 {
 	/*
-	 * Remove it from the ip_vs_rtable table.
+	 * Remove it from the rs_table table.
 	 */
 	if (!list_empty(&dest->d_list)) {
 		list_del(&dest->d_list);
@@ -588,10 +583,11 @@ static int ip_vs_rs_unhash(struct ip_vs_dest *dest)
  *	Lookup real service by <proto,addr,port> in the real service table.
  */
 struct ip_vs_dest *
-ip_vs_lookup_real_service(int af, __u16 protocol,
+ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
 			  const union nf_inet_addr *daddr,
 			  __be16 dport)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	unsigned hash;
 	struct ip_vs_dest *dest;
 
@@ -602,7 +598,7 @@ ip_vs_lookup_real_service(int af, __u16 protocol,
 	hash = ip_vs_rs_hashkey(af, daddr, dport);
 
 	read_lock(&__ip_vs_rs_lock);
-	list_for_each_entry(dest, &ip_vs_rtable[hash], d_list) {
+	list_for_each_entry(dest, &ipvs->rs_table[hash], d_list) {
 		if ((dest->af == af)
 		    && ip_vs_addr_equal(af, &dest->addr, daddr)
 		    && (dest->port == dport)
@@ -652,7 +648,8 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
  * ip_vs_lookup_real_service() looked promissing, but
  * seems not working as expected.
  */
-struct ip_vs_dest *ip_vs_find_dest(int af, const union nf_inet_addr *daddr,
+struct ip_vs_dest *ip_vs_find_dest(struct net  *net, int af,
+				   const union nf_inet_addr *daddr,
 				   __be16 dport,
 				   const union nf_inet_addr *vaddr,
 				   __be16 vport, __u16 protocol, __u32 fwmark)
@@ -660,7 +657,7 @@ struct ip_vs_dest *ip_vs_find_dest(int af, const union nf_inet_addr *daddr,
 	struct ip_vs_dest *dest;
 	struct ip_vs_service *svc;
 
-	svc = ip_vs_service_get(af, fwmark, protocol, vaddr, vport);
+	svc = ip_vs_service_get(net, af, fwmark, protocol, vaddr, vport);
 	if (!svc)
 		return NULL;
 	dest = ip_vs_lookup_dest(svc, daddr, dport);
@@ -768,6 +765,7 @@ static void
 __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 		    struct ip_vs_dest_user_kern *udest, int add)
 {
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 	int conn_flags;
 
 	/* set the weight and the flags */
@@ -780,11 +778,11 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 		conn_flags |= IP_VS_CONN_F_NOOUTPUT;
 	} else {
 		/*
-		 *    Put the real service in ip_vs_rtable if not present.
+		 *    Put the real service in rs_table if not present.
 		 *    For now only for NAT!
 		 */
 		write_lock_bh(&__ip_vs_rs_lock);
-		ip_vs_rs_hash(dest);
+		ip_vs_rs_hash(ipvs, dest);
 		write_unlock_bh(&__ip_vs_rs_lock);
 	}
 	atomic_set(&dest->conn_flags, conn_flags);
@@ -1117,7 +1115,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
  *	Add a service into the service hash table
  */
 static int
-ip_vs_add_service(struct ip_vs_service_user_kern *u,
+ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 		  struct ip_vs_service **svc_p)
 {
 	int ret = 0;
@@ -1172,6 +1170,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u,
 	svc->flags = u->flags;
 	svc->timeout = u->timeout * HZ;
 	svc->netmask = u->netmask;
+	svc->net = net;
 
 	INIT_LIST_HEAD(&svc->destinations);
 	rwlock_init(&svc->sched_lock);
@@ -1428,17 +1427,19 @@ static int ip_vs_del_service(struct ip_vs_service *svc)
 /*
  *	Flush all the virtual services
  */
-static int ip_vs_flush(void)
+static int ip_vs_flush(struct net *net)
 {
 	int idx;
 	struct ip_vs_service *svc, *nxt;
 
 	/*
-	 * Flush the service table hashed by <protocol,addr,port>
+	 * Flush the service table hashed by <netns,protocol,addr,port>
 	 */
 	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
-		list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx], s_list) {
-			ip_vs_unlink_service(svc);
+		list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx],
+					 s_list) {
+			if (net_eq(svc->net, net))
+				ip_vs_unlink_service(svc);
 		}
 	}
 
@@ -1448,7 +1449,8 @@ static int ip_vs_flush(void)
 	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry_safe(svc, nxt,
 					 &ip_vs_svc_fwm_table[idx], f_list) {
-			ip_vs_unlink_service(svc);
+			if (net_eq(svc->net, net))
+				ip_vs_unlink_service(svc);
 		}
 	}
 
@@ -1472,20 +1474,22 @@ static int ip_vs_zero_service(struct ip_vs_service *svc)
 	return 0;
 }
 
-static int ip_vs_zero_all(void)
+static int ip_vs_zero_all(struct net *net)
 {
 	int idx;
 	struct ip_vs_service *svc;
 
 	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
-			ip_vs_zero_service(svc);
+			if (net_eq(svc->net, net))
+				ip_vs_zero_service(svc);
 		}
 	}
 
 	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
-			ip_vs_zero_service(svc);
+			if (net_eq(svc->net, net))
+				ip_vs_zero_service(svc);
 		}
 	}
 
@@ -1763,6 +1767,7 @@ static struct ctl_table_header * sysctl_header;
 #ifdef CONFIG_PROC_FS
 
 struct ip_vs_iter {
+	struct seq_net_private p;  /* Do not move this, netns depends upon it*/
 	struct list_head *table;
 	int bucket;
 };
@@ -1789,6 +1794,7 @@ static inline const char *ip_vs_fwd_name(unsigned flags)
 /* Get the Nth entry in the two lists */
 static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
 {
+	struct net *net = seq_file_net(seq);
 	struct ip_vs_iter *iter = seq->private;
 	int idx;
 	struct ip_vs_service *svc;
@@ -1796,7 +1802,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
 	/* look in hash by protocol */
 	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
-			if (pos-- == 0){
+			if (net_eq(svc->net, net) && pos-- == 0) {
 				iter->table = ip_vs_svc_table;
 				iter->bucket = idx;
 				return svc;
@@ -1807,7 +1813,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
 	/* keep looking in fwmark */
 	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
-			if (pos-- == 0) {
+			if (net_eq(svc->net, net) && pos-- == 0) {
 				iter->table = ip_vs_svc_fwm_table;
 				iter->bucket = idx;
 				return svc;
@@ -1961,7 +1967,7 @@ static const struct seq_operations ip_vs_info_seq_ops = {
 
 static int ip_vs_info_open(struct inode *inode, struct file *file)
 {
-	return seq_open_private(file, &ip_vs_info_seq_ops,
+	return seq_open_net(inode, file, &ip_vs_info_seq_ops,
 			sizeof(struct ip_vs_iter));
 }
 
@@ -2011,7 +2017,7 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v)
 
 static int ip_vs_stats_seq_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, ip_vs_stats_show, NULL);
+	return single_open_net(inode, file, ip_vs_stats_show);
 }
 
 static const struct file_operations ip_vs_stats_fops = {
@@ -2113,6 +2119,7 @@ static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest,
 static int
 do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 {
+	struct net *net = sock_net(sk);
 	int ret;
 	unsigned char arg[MAX_ARG_LEN];
 	struct ip_vs_service_user *usvc_compat;
@@ -2147,7 +2154,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 
 	if (cmd == IP_VS_SO_SET_FLUSH) {
 		/* Flush the virtual service */
-		ret = ip_vs_flush();
+		ret = ip_vs_flush(net);
 		goto out_unlock;
 	} else if (cmd == IP_VS_SO_SET_TIMEOUT) {
 		/* Set timeout values for (tcp tcpfin udp) */
@@ -2174,7 +2181,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 	if (cmd == IP_VS_SO_SET_ZERO) {
 		/* if no service address is set, zero counters in all */
 		if (!usvc.fwmark && !usvc.addr.ip && !usvc.port) {
-			ret = ip_vs_zero_all();
+			ret = ip_vs_zero_all(net);
 			goto out_unlock;
 		}
 	}
@@ -2191,10 +2198,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 
 	/* Lookup the exact service by <protocol, addr, port> or fwmark */
 	if (usvc.fwmark == 0)
-		svc = __ip_vs_service_find(usvc.af, usvc.protocol,
+		svc = __ip_vs_service_find(net, usvc.af, usvc.protocol,
 					   &usvc.addr, usvc.port);
 	else
-		svc = __ip_vs_svc_fwm_find(usvc.af, usvc.fwmark);
+		svc = __ip_vs_svc_fwm_find(net, usvc.af, usvc.fwmark);
 
 	if (cmd != IP_VS_SO_SET_ADD
 	    && (svc == NULL || svc->protocol != usvc.protocol)) {
@@ -2207,7 +2214,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 		if (svc != NULL)
 			ret = -EEXIST;
 		else
-			ret = ip_vs_add_service(&usvc, &svc);
+			ret = ip_vs_add_service(net, &usvc, &svc);
 		break;
 	case IP_VS_SO_SET_EDIT:
 		ret = ip_vs_edit_service(svc, &usvc);
@@ -2267,7 +2274,8 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
 }
 
 static inline int
-__ip_vs_get_service_entries(const struct ip_vs_get_services *get,
+__ip_vs_get_service_entries(struct net *net,
+			    const struct ip_vs_get_services *get,
 			    struct ip_vs_get_services __user *uptr)
 {
 	int idx, count=0;
@@ -2278,7 +2286,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get,
 	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
 			/* Only expose IPv4 entries to old interface */
-			if (svc->af != AF_INET)
+			if (svc->af != AF_INET || !net_eq(svc->net, net))
 				continue;
 
 			if (count >= get->num_services)
@@ -2297,7 +2305,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get,
 	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
 		list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
 			/* Only expose IPv4 entries to old interface */
-			if (svc->af != AF_INET)
+			if (svc->af != AF_INET || !net_eq(svc->net, net))
 				continue;
 
 			if (count >= get->num_services)
@@ -2317,7 +2325,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get,
 }
 
 static inline int
-__ip_vs_get_dest_entries(const struct ip_vs_get_dests *get,
+__ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
 			 struct ip_vs_get_dests __user *uptr)
 {
 	struct ip_vs_service *svc;
@@ -2325,9 +2333,9 @@ __ip_vs_get_dest_entries(const struct ip_vs_get_dests *get,
 	int ret = 0;
 
 	if (get->fwmark)
-		svc = __ip_vs_svc_fwm_find(AF_INET, get->fwmark);
+		svc = __ip_vs_svc_fwm_find(net, AF_INET, get->fwmark);
 	else
-		svc = __ip_vs_service_find(AF_INET, get->protocol, &addr,
+		svc = __ip_vs_service_find(net, AF_INET, get->protocol, &addr,
 					   get->port);
 
 	if (svc) {
@@ -2401,7 +2409,9 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	unsigned char arg[128];
 	int ret = 0;
 	unsigned int copylen;
+	struct net *net = sock_net(sk);
 
+	BUG_ON(!net);
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 
@@ -2463,7 +2473,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 			ret = -EINVAL;
 			goto out;
 		}
-		ret = __ip_vs_get_service_entries(get, user);
+		ret = __ip_vs_get_service_entries(net, get, user);
 	}
 	break;
 
@@ -2476,10 +2486,11 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 		entry = (struct ip_vs_service_entry *)arg;
 		addr.ip = entry->addr;
 		if (entry->fwmark)
-			svc = __ip_vs_svc_fwm_find(AF_INET, entry->fwmark);
+			svc = __ip_vs_svc_fwm_find(net, AF_INET, entry->fwmark);
 		else
-			svc = __ip_vs_service_find(AF_INET, entry->protocol,
-						   &addr, entry->port);
+			svc = __ip_vs_service_find(net, AF_INET,
+						   entry->protocol, &addr,
+						   entry->port);
 		if (svc) {
 			ip_vs_copy_service(entry, svc);
 			if (copy_to_user(user, entry, sizeof(*entry)) != 0)
@@ -2502,7 +2513,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 			ret = -EINVAL;
 			goto out;
 		}
-		ret = __ip_vs_get_dest_entries(get, user);
+		ret = __ip_vs_get_dest_entries(net, get, user);
 	}
 	break;
 
@@ -2722,11 +2733,12 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb,
 	int idx = 0, i;
 	int start = cb->args[0];
 	struct ip_vs_service *svc;
+	struct net *net = skb_sknet(skb);
 
 	mutex_lock(&__ip_vs_mutex);
 	for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
 		list_for_each_entry(svc, &ip_vs_svc_table[i], s_list) {
-			if (++idx <= start)
+			if (++idx <= start || !net_eq(svc->net, net))
 				continue;
 			if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
 				idx--;
@@ -2737,7 +2749,7 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb,
 
 	for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
 		list_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) {
-			if (++idx <= start)
+			if (++idx <= start || !net_eq(svc->net, net))
 				continue;
 			if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
 				idx--;
@@ -2753,7 +2765,8 @@ nla_put_failure:
 	return skb->len;
 }
 
-static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc,
+static int ip_vs_genl_parse_service(struct net *net,
+				    struct ip_vs_service_user_kern *usvc,
 				    struct nlattr *nla, int full_entry,
 				    struct ip_vs_service **ret_svc)
 {
@@ -2796,9 +2809,9 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc,
 	}
 
 	if (usvc->fwmark)
-		svc = __ip_vs_svc_fwm_find(usvc->af, usvc->fwmark);
+		svc = __ip_vs_svc_fwm_find(net, usvc->af, usvc->fwmark);
 	else
-		svc = __ip_vs_service_find(usvc->af, usvc->protocol,
+		svc = __ip_vs_service_find(net, usvc->af, usvc->protocol,
 					   &usvc->addr, usvc->port);
 	*ret_svc = svc;
 
@@ -2835,13 +2848,14 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc,
 	return 0;
 }
 
-static struct ip_vs_service *ip_vs_genl_find_service(struct nlattr *nla)
+static struct ip_vs_service *ip_vs_genl_find_service(struct net *net,
+						     struct nlattr *nla)
 {
 	struct ip_vs_service_user_kern usvc;
 	struct ip_vs_service *svc;
 	int ret;
 
-	ret = ip_vs_genl_parse_service(&usvc, nla, 0, &svc);
+	ret = ip_vs_genl_parse_service(net, &usvc, nla, 0, &svc);
 	return ret ? ERR_PTR(ret) : svc;
 }
 
@@ -2909,6 +2923,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
 	struct ip_vs_service *svc;
 	struct ip_vs_dest *dest;
 	struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1];
+	struct net *net;
 
 	mutex_lock(&__ip_vs_mutex);
 
@@ -2917,7 +2932,8 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
 			IPVS_CMD_ATTR_MAX, ip_vs_cmd_policy))
 		goto out_err;
 
-	svc = ip_vs_genl_find_service(attrs[IPVS_CMD_ATTR_SERVICE]);
+	net = skb_sknet(skb);
+	svc = ip_vs_genl_find_service(net, attrs[IPVS_CMD_ATTR_SERVICE]);
 	if (IS_ERR(svc) || svc == NULL)
 		goto out_err;
 
@@ -3102,13 +3118,15 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 	struct ip_vs_dest_user_kern udest;
 	int ret = 0, cmd;
 	int need_full_svc = 0, need_full_dest = 0;
+	struct net *net;
 
+	net = skb_sknet(skb);
 	cmd = info->genlhdr->cmd;
 
 	mutex_lock(&__ip_vs_mutex);
 
 	if (cmd == IPVS_CMD_FLUSH) {
-		ret = ip_vs_flush();
+		ret = ip_vs_flush(net);
 		goto out;
 	} else if (cmd == IPVS_CMD_SET_CONFIG) {
 		ret = ip_vs_genl_set_config(info->attrs);
@@ -3133,7 +3151,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 	} else if (cmd == IPVS_CMD_ZERO &&
 		   !info->attrs[IPVS_CMD_ATTR_SERVICE]) {
-		ret = ip_vs_zero_all();
+		ret = ip_vs_zero_all(net);
 		goto out;
 	}
 
@@ -3143,7 +3161,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 	if (cmd == IPVS_CMD_NEW_SERVICE || cmd == IPVS_CMD_SET_SERVICE)
 		need_full_svc = 1;
 
-	ret = ip_vs_genl_parse_service(&usvc,
+	ret = ip_vs_genl_parse_service(net, &usvc,
 				       info->attrs[IPVS_CMD_ATTR_SERVICE],
 				       need_full_svc, &svc);
 	if (ret)
@@ -3173,7 +3191,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 	switch (cmd) {
 	case IPVS_CMD_NEW_SERVICE:
 		if (svc == NULL)
-			ret = ip_vs_add_service(&usvc, &svc);
+			ret = ip_vs_add_service(net, &usvc, &svc);
 		else
 			ret = -EEXIST;
 		break;
@@ -3211,7 +3229,9 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
 	struct sk_buff *msg;
 	void *reply;
 	int ret, cmd, reply_cmd;
+	struct net *net;
 
+	net = skb_sknet(skb);
 	cmd = info->genlhdr->cmd;
 
 	if (cmd == IPVS_CMD_GET_SERVICE)
@@ -3240,7 +3260,8 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
 	{
 		struct ip_vs_service *svc;
 
-		svc = ip_vs_genl_find_service(info->attrs[IPVS_CMD_ATTR_SERVICE]);
+		svc = ip_vs_genl_find_service(net,
+					      info->attrs[IPVS_CMD_ATTR_SERVICE]);
 		if (IS_ERR(svc)) {
 			ret = PTR_ERR(svc);
 			goto out_err;
@@ -3411,9 +3432,15 @@ static void ip_vs_genl_unregister(void)
  */
 int __net_init __ip_vs_control_init(struct net *net)
 {
+	int idx;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
 
+	for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
+		INIT_LIST_HEAD(&ipvs->rs_table[idx]);
+
 	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);
 	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
@@ -3445,43 +3472,48 @@ static struct pernet_operations ipvs_control_ops = {
 
 int __init ip_vs_control_init(void)
 {
-	int ret;
 	int idx;
+	int ret;
 
 	EnterFunction(2);
 
-	/* Initialize ip_vs_svc_table, ip_vs_svc_fwm_table, ip_vs_rtable */
+	/* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */
 	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++)  {
 		INIT_LIST_HEAD(&ip_vs_svc_table[idx]);
 		INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]);
 	}
-	for(idx = 0; idx < IP_VS_RTAB_SIZE; idx++)  {
-		INIT_LIST_HEAD(&ip_vs_rtable[idx]);
+
+	ret = register_pernet_subsys(&ipvs_control_ops);
+	if (ret) {
+		pr_err("cannot register namespace.\n");
+		goto err;
 	}
-	smp_wmb();
+
+	smp_wmb();	/* Do we really need it now ? */
 
 	ret = nf_register_sockopt(&ip_vs_sockopts);
 	if (ret) {
 		pr_err("cannot register sockopt.\n");
-		return ret;
+		goto err_net;
 	}
 
 	ret = ip_vs_genl_register();
 	if (ret) {
 		pr_err("cannot register Generic Netlink interface.\n");
 		nf_unregister_sockopt(&ip_vs_sockopts);
-		return ret;
+		goto err_net;
 	}
 
-	ret = register_pernet_subsys(&ipvs_control_ops);
-	if (ret)
-		return ret;
-
 	/* Hook the defense timer */
 	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);
 
 	LeaveFunction(2);
 	return 0;
+
+err_net:
+	unregister_pernet_subsys(&ipvs_control_ops);
+err:
+	return ret;
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index a315159..521b827 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -12,6 +12,7 @@ static int
 sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		   int *verdict, struct ip_vs_conn **cpp)
 {
+	struct net *net;
 	struct ip_vs_service *svc;
 	sctp_chunkhdr_t _schunkh, *sch;
 	sctp_sctphdr_t *sh, _sctph;
@@ -27,9 +28,9 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 				 sizeof(_schunkh), &_schunkh);
 	if (sch == NULL)
 		return 0;
-
+	net = skb_net(skb);
 	if ((sch->type == SCTP_CID_INIT) &&
-	    (svc = ip_vs_service_get(af, skb->mark, iph.protocol,
+	    (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
 				     &iph.daddr, sh->dest))) {
 		int ignored;
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 1cdab12..c175d31 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -31,6 +31,7 @@ static int
 tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		  int *verdict, struct ip_vs_conn **cpp)
 {
+	struct net *net;
 	struct ip_vs_service *svc;
 	struct tcphdr _tcph, *th;
 	struct ip_vs_iphdr iph;
@@ -42,11 +43,11 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		*verdict = NF_DROP;
 		return 0;
 	}
-
+	net = skb_net(skb);
 	/* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */
 	if (th->syn &&
-	    (svc = ip_vs_service_get(af, skb->mark, iph.protocol, &iph.daddr,
-				     th->dest))) {
+	    (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
+				     &iph.daddr, th->dest))) {
 		int ignored;
 
 		if (ip_vs_todrop()) {
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index cd398de..5ab54f6 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -31,6 +31,7 @@ static int
 udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		  int *verdict, struct ip_vs_conn **cpp)
 {
+	struct net *net;
 	struct ip_vs_service *svc;
 	struct udphdr _udph, *uh;
 	struct ip_vs_iphdr iph;
@@ -42,8 +43,8 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		*verdict = NF_DROP;
 		return 0;
 	}
-
-	svc = ip_vs_service_get(af, skb->mark, iph.protocol,
+	net = skb_net(skb);
+	svc = ip_vs_service_get(net, af, skb->mark, iph.protocol,
 				&iph.daddr, uh->dest);
 	if (svc) {
 		int ignored;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 3668739..662aa2c 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -749,7 +749,7 @@ static void ip_vs_proc_conn(struct ip_vs_conn_param *param,  unsigned flags,
 		 * If it is not found the connection will remain unbound
 		 * but still handled.
 		 */
-		dest = ip_vs_find_dest(type, daddr, dport, param->vaddr,
+		dest = ip_vs_find_dest(&init_net, type, daddr, dport, param->vaddr,
 				       param->vport, protocol, fwmark);
 
 		/*  Set the approprite ativity flag */
-- 
1.7.2.3

[PATCH 36/79] IPVS: netns awarness to lblcr sheduler

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

var sysctl_ip_vs_lblcr_expiration moved to ipvs struct as
    sysctl_lblcr_expiration

procfs updated to handle this.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/netns/ip_vs.h        |    5 +++
 net/netfilter/ipvs/ip_vs_lblcr.c |   54 +++++++++++++++++++++++++------------
 2 files changed, 41 insertions(+), 18 deletions(-)

diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 5b87d22..51a92ee 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -28,6 +28,11 @@ struct netns_ipvs {
 	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
 
 	struct list_head	rs_table[IP_VS_RTAB_SIZE];
+
+	/* ip_vs_lblcr */
+	int			sysctl_lblcr_expiration;
+	struct ctl_table_header	*lblcr_ctl_header;
+	struct ctl_table	*lblcr_ctl_table;
 };
 
 #endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 7c7396a..61ae8cf 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -70,8 +70,6 @@
  *    entries that haven't been touched for a day.
  */
 #define COUNT_FOR_FULL_EXPIRATION   30
-static int sysctl_ip_vs_lblcr_expiration = 24*60*60*HZ;
-
 
 /*
  *     for IPVS lblcr entry hash table
@@ -296,7 +294,7 @@ struct ip_vs_lblcr_table {
 static ctl_table vs_vars_table[] = {
 	{
 		.procname	= "lblcr_expiration",
-		.data		= &sysctl_ip_vs_lblcr_expiration,
+		.data		= NULL,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -304,8 +302,6 @@ static ctl_table vs_vars_table[] = {
 	{ }
 };
 
-static struct ctl_table_header * sysctl_header;
-
 static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en)
 {
 	list_del(&en->list);
@@ -425,14 +421,15 @@ 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+sysctl_ip_vs_lblcr_expiration,
-				       now))
+			if (time_after(en->lastuse
+					+ ipvs->sysctl_lblcr_expiration, now))
 				continue;
 
 			ip_vs_lblcr_free(en);
@@ -664,6 +661,7 @@ 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;
 
@@ -675,7 +673,7 @@ 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 +
-				sysctl_ip_vs_lblcr_expiration)) {
+				ipvs->sysctl_lblcr_expiration)) {
 			struct ip_vs_dest *m;
 
 			write_lock(&en->set.lock);
@@ -749,23 +747,43 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler =
  */
 static int __net_init __ip_vs_lblcr_init(struct net *net)
 {
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return -EPERM;
-
-	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
-						  vs_vars_table);
-	if (!sysctl_header)
-		return -ENOMEM;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	if (!net_eq(net, &init_net)) {
+		ipvs->lblcr_ctl_table = kmemdup(vs_vars_table,
+						sizeof(vs_vars_table),
+						GFP_KERNEL);
+		if (ipvs->lblcr_ctl_table == NULL)
+			goto err_dup;
+	} else
+		ipvs->lblcr_ctl_table = vs_vars_table;
+	ipvs->sysctl_lblcr_expiration = 24*60*60*HZ;
+	ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration;
+
+	ipvs->lblcr_ctl_header =
+		register_net_sysctl_table(net, net_vs_ctl_path,
+					  ipvs->lblcr_ctl_table);
+	if (!ipvs->lblcr_ctl_header)
+		goto err_reg;
 
 	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblcr_ctl_table);
+
+err_dup:
+	return -ENOMEM;
 }
 
 static void __net_exit __ip_vs_lblcr_exit(struct net *net)
 {
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	unregister_net_sysctl_table(ipvs->lblcr_ctl_header);
 
-	unregister_net_sysctl_table(sysctl_header);
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblcr_ctl_table);
 }
 
 static struct pernet_operations ip_vs_lblcr_ops = {
-- 
1.7.2.3

[PATCH 37/79] IPVS: netns awarness to lblc sheduler

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

var sysctl_ip_vs_lblc_expiration moved to ipvs struct as
    sysctl_lblc_expiration

procfs updated to handle this.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/netns/ip_vs.h       |    4 +++
 net/netfilter/ipvs/ip_vs_lblc.c |   50 ++++++++++++++++++++++++++------------
 2 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 51a92ee..d14581c 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -29,6 +29,10 @@ struct netns_ipvs {
 
 	struct list_head	rs_table[IP_VS_RTAB_SIZE];
 
+	/* ip_vs_lblc */
+	int			sysctl_lblc_expiration;
+	struct ctl_table_header	*lblc_ctl_header;
+	struct ctl_table	*lblc_ctl_table;
 	/* ip_vs_lblcr */
 	int			sysctl_lblcr_expiration;
 	struct ctl_table_header	*lblcr_ctl_header;
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 84278fb..d5bec33 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -70,7 +70,6 @@
  *    entries that haven't been touched for a day.
  */
 #define COUNT_FOR_FULL_EXPIRATION   30
-static int sysctl_ip_vs_lblc_expiration = 24*60*60*HZ;
 
 
 /*
@@ -117,7 +116,7 @@ struct ip_vs_lblc_table {
 static ctl_table vs_vars_table[] = {
 	{
 		.procname	= "lblc_expiration",
-		.data		= &sysctl_ip_vs_lblc_expiration,
+		.data		= NULL,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -125,8 +124,6 @@ static ctl_table vs_vars_table[] = {
 	{ }
 };
 
-static struct ctl_table_header * sysctl_header;
-
 static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en)
 {
 	list_del(&en->list);
@@ -248,6 +245,7 @@ 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;
@@ -255,7 +253,8 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
 		write_lock(&svc->sched_lock);
 		list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
 			if (time_before(now,
-					en->lastuse + sysctl_ip_vs_lblc_expiration))
+					en->lastuse +
+					ipvs->sysctl_lblc_expiration))
 				continue;
 
 			ip_vs_lblc_free(en);
@@ -548,23 +547,43 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler =
  */
 static int __net_init __ip_vs_lblc_init(struct net *net)
 {
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return -EPERM;
-
-	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
-						  vs_vars_table);
-	if (!sysctl_header)
-		return -ENOMEM;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	if (!net_eq(net, &init_net)) {
+		ipvs->lblc_ctl_table = kmemdup(vs_vars_table,
+						sizeof(vs_vars_table),
+						GFP_KERNEL);
+		if (ipvs->lblc_ctl_table == NULL)
+			goto err_dup;
+	} else
+		ipvs->lblc_ctl_table = vs_vars_table;
+	ipvs->sysctl_lblc_expiration = 24*60*60*HZ;
+	ipvs->lblc_ctl_table[0].data = &ipvs->sysctl_lblc_expiration;
+
+	ipvs->lblc_ctl_header =
+		register_net_sysctl_table(net, net_vs_ctl_path,
+					  ipvs->lblc_ctl_table);
+	if (!ipvs->lblc_ctl_header)
+		goto err_reg;
 
 	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblc_ctl_table);
+
+err_dup:
+	return -ENOMEM;
 }
 
 static void __net_exit __ip_vs_lblc_exit(struct net *net)
 {
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	unregister_net_sysctl_table(ipvs->lblc_ctl_header);
 
-	unregister_net_sysctl_table(sysctl_header);
+	if (!net_eq(net, &init_net))
+		kfree(ipvs->lblc_ctl_table);
 }
 
 static struct pernet_operations ip_vs_lblc_ops = {
@@ -586,7 +605,6 @@ static int __init ip_vs_lblc_init(void)
 	return ret;
 }
 
-
 static void __exit ip_vs_lblc_cleanup(void)
 {
 	unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler);
-- 
1.7.2.3

[PATCH 38/79] IPVS: netns, prepare protocol

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

Add support for protocol data per name-space.
in struct ip_vs_protocol, appcnt will be removed when all protos
are modified for network name-space.

This patch causes warnings of unused functions, they will be used
when next patch will be applied.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h              |   20 +++++++++++-
 include/net/netns/ip_vs.h        |    3 ++
 net/netfilter/ipvs/ip_vs_proto.c |   66 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 88 insertions(+), 1 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index d551e0d..88d4e40 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -352,6 +352,7 @@ struct iphdr;
 struct ip_vs_conn;
 struct ip_vs_app;
 struct sk_buff;
+struct ip_vs_proto_data;
 
 struct ip_vs_protocol {
 	struct ip_vs_protocol	*next;
@@ -366,6 +367,10 @@ struct ip_vs_protocol {
 
 	void (*exit)(struct ip_vs_protocol *pp);
 
+	void (*init_netns)(struct net *net, struct ip_vs_proto_data *pd);
+
+	void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd);
+
 	int (*conn_schedule)(int af, struct sk_buff *skb,
 			     struct ip_vs_protocol *pp,
 			     int *verdict, struct ip_vs_conn **cpp);
@@ -417,7 +422,20 @@ struct ip_vs_protocol {
 	int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to);
 };
 
-extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto);
+/*
+ * protocol data per netns
+ */
+struct ip_vs_proto_data {
+	struct ip_vs_proto_data	*next;
+	struct ip_vs_protocol	*pp;
+	int			*timeout_table;	/* protocol timeout table */
+	atomic_t		appcnt;		/* counter of proto app incs. */
+	struct tcp_states_t	*tcp_state_table;
+};
+
+extern struct ip_vs_protocol   *ip_vs_proto_get(unsigned short proto);
+extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net,
+						     unsigned short proto);
 
 struct ip_vs_conn_param {
 	const union nf_inet_addr	*caddr;
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index d14581c..6f4e089 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -28,6 +28,9 @@ struct netns_ipvs {
 	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
 
 	struct list_head	rs_table[IP_VS_RTAB_SIZE];
+	/* ip_vs_proto */
+	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
+	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 4539294..576e296 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -60,6 +60,31 @@ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp)
 	return 0;
 }
 
+/*
+ *	register an ipvs protocols netns related data
+ */
+static int
+register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	unsigned hash = IP_VS_PROTO_HASH(pp->protocol);
+	struct ip_vs_proto_data *pd =
+			kzalloc(sizeof(struct ip_vs_proto_data), GFP_ATOMIC);
+
+	if (!pd) {
+		pr_err("%s(): no memory.\n", __func__);
+		return -ENOMEM;
+	}
+	pd->pp = pp;	/* For speed issues */
+	pd->next = ipvs->proto_data_table[hash];
+	ipvs->proto_data_table[hash] = pd;
+	atomic_set(&pd->appcnt, 0);	/* Init app counter */
+
+	if (pp->init_netns != NULL)
+		pp->init_netns(net, pd);
+
+	return 0;
+}
 
 /*
  *	unregister an ipvs protocol
@@ -82,6 +107,29 @@ static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp)
 	return -ESRCH;
 }
 
+/*
+ *	unregister an ipvs protocols netns data
+ */
+static int
+unregister_ip_vs_proto_netns(struct net *net, struct ip_vs_proto_data *pd)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data **pd_p;
+	unsigned hash = IP_VS_PROTO_HASH(pd->pp->protocol);
+
+	pd_p = &ipvs->proto_data_table[hash];
+	for (; *pd_p; pd_p = &(*pd_p)->next) {
+		if (*pd_p == pd) {
+			*pd_p = pd->next;
+			if (pd->pp->exit_netns != NULL)
+				pd->pp->exit_netns(net, pd);
+			kfree(pd);
+			return 0;
+		}
+	}
+
+	return -ESRCH;
+}
 
 /*
  *	get ip_vs_protocol object by its proto.
@@ -100,6 +148,24 @@ struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto)
 }
 EXPORT_SYMBOL(ip_vs_proto_get);
 
+/*
+ *	get ip_vs_protocol object data by netns and proto
+ */
+struct ip_vs_proto_data *
+ip_vs_proto_data_get(struct net *net, unsigned short proto)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd;
+	unsigned hash = IP_VS_PROTO_HASH(proto);
+
+	for (pd = ipvs->proto_data_table[hash]; pd; pd = pd->next) {
+		if (pd->pp->protocol == proto)
+			return pd;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(ip_vs_proto_data_get);
 
 /*
  *	Propagate event for state change to all protocols
-- 
1.7.2.3

[PATCH 39/79] IPVS: netns preparation for proto_tcp

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

In this phase (one), all local vars will be moved to ipvs struct.

Remaining work, add param struct net *net to a couple of
functions that is common for all protos and use all
ip_vs_proto_data

*v3
Removed unused function as sugested by Simon

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                  |    2 +-
 include/net/netns/ip_vs.h            |    8 +++
 net/netfilter/ipvs/ip_vs_ftp.c       |    8 ++-
 net/netfilter/ipvs/ip_vs_proto.c     |   13 ++++-
 net/netfilter/ipvs/ip_vs_proto_tcp.c |   97 ++++++++++++++++++----------------
 5 files changed, 79 insertions(+), 49 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 88d4e40..3c45a00 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -807,7 +807,7 @@ extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
 
 extern const char * ip_vs_state_name(__u16 proto, int state);
 
-extern void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp);
+extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp);
 extern int ip_vs_check_template(struct ip_vs_conn *ct);
 extern void ip_vs_random_dropentry(void);
 extern int ip_vs_conn_init(void);
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 6f4e089..ac77363 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -31,6 +31,14 @@ struct netns_ipvs {
 	/* ip_vs_proto */
 	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
 	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
+	/* ip_vs_proto_tcp */
+#ifdef CONFIG_IP_VS_PROTO_TCP
+	#define	TCP_APP_TAB_BITS	4
+	#define	TCP_APP_TAB_SIZE	(1 << TCP_APP_TAB_BITS)
+	#define	TCP_APP_TAB_MASK	(TCP_APP_TAB_SIZE - 1)
+	struct list_head	tcp_apps[TCP_APP_TAB_SIZE];
+	spinlock_t		tcp_app_lock;
+#endif
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 0e762f3..b38ae94 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -157,6 +157,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	int ret = 0;
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn *ct;
+	struct net *net;
 
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
@@ -257,8 +258,9 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		 * would be adjusted twice.
 		 */
 
+		net = skb_net(skb);
 		cp->app_data = NULL;
-		ip_vs_tcp_conn_listen(n_cp);
+		ip_vs_tcp_conn_listen(net, n_cp);
 		ip_vs_conn_put(n_cp);
 		return ret;
 	}
@@ -287,6 +289,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	union nf_inet_addr to;
 	__be16 port;
 	struct ip_vs_conn *n_cp;
+	struct net *net;
 
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
@@ -378,7 +381,8 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	/*
 	 *	Move tunnel to listen state
 	 */
-	ip_vs_tcp_conn_listen(n_cp);
+	net = skb_net(skb);
+	ip_vs_tcp_conn_listen(net, n_cp);
 	ip_vs_conn_put(n_cp);
 
 	return 1;
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 576e296..320c6a6 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -307,12 +307,23 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
  */
 static int __net_init __ip_vs_protocol_init(struct net *net)
 {
+#ifdef CONFIG_IP_VS_PROTO_TCP
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp);
+#endif
 	return 0;
 }
 
 static void __net_exit __ip_vs_protocol_cleanup(struct net *net)
 {
-	/* empty */
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd;
+	int i;
+
+	/* unregister all the ipvs proto data for this netns */
+	for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
+		while ((pd = ipvs->proto_data_table[i]) != NULL)
+			unregister_ip_vs_proto_netns(net, pd);
+	}
 }
 
 static struct pernet_operations ipvs_proto_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index c175d31..9d9df3d 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -9,8 +9,12 @@
  *              as published by the Free Software Foundation; either version
  *              2 of the License, or (at your option) any later version.
  *
- * Changes:
+ * Changes:     Hans Schillstrom <hans.schillstrom@ericsson.com>
  *
+ *              Network name space (netns) aware.
+ *              Global data moved to netns i.e struct netns_ipvs
+ *              tcp_timeouts table has copy per netns in a hash table per
+ *              protocol ip_vs_proto_data and is handled by netns
  */
 
 #define KMSG_COMPONENT "IPVS"
@@ -345,7 +349,7 @@ static const int tcp_state_off[IP_VS_DIR_LAST] = {
 /*
  *	Timeout table[state]
  */
-static int tcp_timeouts[IP_VS_TCP_S_LAST+1] = {
+static const int tcp_timeouts[IP_VS_TCP_S_LAST+1] = {
 	[IP_VS_TCP_S_NONE]		=	2*HZ,
 	[IP_VS_TCP_S_ESTABLISHED]	=	15*60*HZ,
 	[IP_VS_TCP_S_SYN_SENT]		=	2*60*HZ,
@@ -460,13 +464,6 @@ static void tcp_timeout_change(struct ip_vs_protocol *pp, int flags)
 	tcp_state_table = (on? tcp_states_dos : tcp_states);
 }
 
-static int
-tcp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to)
-{
-	return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_TCP_S_LAST,
-				       tcp_state_name_table, sname, to);
-}
-
 static inline int tcp_state_idx(struct tcphdr *th)
 {
 	if (th->rst)
@@ -487,6 +484,7 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 	int state_idx;
 	int new_state = IP_VS_TCP_S_CLOSE;
 	int state_off = tcp_state_off[direction];
+	struct ip_vs_proto_data *pd;  /* Temp fix */
 
 	/*
 	 *    Update state offset to INPUT_ONLY if necessary
@@ -542,10 +540,13 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 		}
 	}
 
-	cp->timeout = pp->timeout_table[cp->state = new_state];
+	pd = ip_vs_proto_data_get(&init_net, pp->protocol);
+	if (likely(pd))
+		cp->timeout = pd->timeout_table[cp->state = new_state];
+	else	/* What to do ? */
+		cp->timeout = tcp_timeouts[cp->state = new_state];
 }
 
-
 /*
  *	Handle state transitions
  */
@@ -573,17 +574,6 @@ tcp_state_transition(struct ip_vs_conn *cp, int direction,
 	return 1;
 }
 
-
-/*
- *	Hash table for TCP application incarnations
- */
-#define	TCP_APP_TAB_BITS	4
-#define	TCP_APP_TAB_SIZE	(1 << TCP_APP_TAB_BITS)
-#define	TCP_APP_TAB_MASK	(TCP_APP_TAB_SIZE - 1)
-
-static struct list_head tcp_apps[TCP_APP_TAB_SIZE];
-static DEFINE_SPINLOCK(tcp_app_lock);
-
 static inline __u16 tcp_app_hashkey(__be16 port)
 {
 	return (((__force u16)port >> TCP_APP_TAB_BITS) ^ (__force u16)port)
@@ -597,21 +587,23 @@ static int tcp_register_app(struct ip_vs_app *inc)
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_TCP);
 
 	hash = tcp_app_hashkey(port);
 
-	spin_lock_bh(&tcp_app_lock);
-	list_for_each_entry(i, &tcp_apps[hash], p_list) {
+	spin_lock_bh(&ipvs->tcp_app_lock);
+	list_for_each_entry(i, &ipvs->tcp_apps[hash], p_list) {
 		if (i->port == port) {
 			ret = -EEXIST;
 			goto out;
 		}
 	}
-	list_add(&inc->p_list, &tcp_apps[hash]);
-	atomic_inc(&ip_vs_protocol_tcp.appcnt);
+	list_add(&inc->p_list, &ipvs->tcp_apps[hash]);
+	atomic_inc(&pd->pp->appcnt);
 
   out:
-	spin_unlock_bh(&tcp_app_lock);
+	spin_unlock_bh(&ipvs->tcp_app_lock);
 	return ret;
 }
 
@@ -619,16 +611,20 @@ static int tcp_register_app(struct ip_vs_app *inc)
 static void
 tcp_unregister_app(struct ip_vs_app *inc)
 {
-	spin_lock_bh(&tcp_app_lock);
-	atomic_dec(&ip_vs_protocol_tcp.appcnt);
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_TCP);
+
+	spin_lock_bh(&ipvs->tcp_app_lock);
+	atomic_dec(&pd->pp->appcnt);
 	list_del(&inc->p_list);
-	spin_unlock_bh(&tcp_app_lock);
+	spin_unlock_bh(&ipvs->tcp_app_lock);
 }
 
 
 static int
 tcp_app_conn_bind(struct ip_vs_conn *cp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
@@ -640,12 +636,12 @@ tcp_app_conn_bind(struct ip_vs_conn *cp)
 	/* Lookup application incarnations and bind the right one */
 	hash = tcp_app_hashkey(cp->vport);
 
-	spin_lock(&tcp_app_lock);
-	list_for_each_entry(inc, &tcp_apps[hash], p_list) {
+	spin_lock(&ipvs->tcp_app_lock);
+	list_for_each_entry(inc, &ipvs->tcp_apps[hash], p_list) {
 		if (inc->port == cp->vport) {
 			if (unlikely(!ip_vs_app_inc_get(inc)))
 				break;
-			spin_unlock(&tcp_app_lock);
+			spin_unlock(&ipvs->tcp_app_lock);
 
 			IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->"
 				      "%s:%u to app %s on port %u\n",
@@ -662,7 +658,7 @@ tcp_app_conn_bind(struct ip_vs_conn *cp)
 			goto out;
 		}
 	}
-	spin_unlock(&tcp_app_lock);
+	spin_unlock(&ipvs->tcp_app_lock);
 
   out:
 	return result;
@@ -672,24 +668,34 @@ tcp_app_conn_bind(struct ip_vs_conn *cp)
 /*
  *	Set LISTEN timeout. (ip_vs_conn_put will setup timer)
  */
-void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp)
+void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp)
 {
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
+
 	spin_lock(&cp->lock);
 	cp->state = IP_VS_TCP_S_LISTEN;
-	cp->timeout = ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_LISTEN];
+	cp->timeout = (pd ? pd->timeout_table[IP_VS_TCP_S_LISTEN]
+			   : tcp_timeouts[IP_VS_TCP_S_LISTEN]);
 	spin_unlock(&cp->lock);
 }
 
-
-static void ip_vs_tcp_init(struct ip_vs_protocol *pp)
+/* ---------------------------------------------
+ *   timeouts is netns related now.
+ * ---------------------------------------------
+ */
+static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd)
 {
-	IP_VS_INIT_HASH_TABLE(tcp_apps);
-	pp->timeout_table = tcp_timeouts;
-}
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
+	ip_vs_init_hash_table(ipvs->tcp_apps, TCP_APP_TAB_SIZE);
+	spin_lock_init(&ipvs->tcp_app_lock);
+	pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts,
+							sizeof(tcp_timeouts));
+}
 
-static void ip_vs_tcp_exit(struct ip_vs_protocol *pp)
+static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd)
 {
+	kfree(pd->timeout_table);
 }
 
 
@@ -699,8 +705,10 @@ struct ip_vs_protocol ip_vs_protocol_tcp = {
 	.num_states =		IP_VS_TCP_S_LAST,
 	.dont_defrag =		0,
 	.appcnt =		ATOMIC_INIT(0),
-	.init =			ip_vs_tcp_init,
-	.exit =			ip_vs_tcp_exit,
+	.init =			NULL,
+	.exit =			NULL,
+	.init_netns =		__ip_vs_tcp_init,
+	.exit_netns =		__ip_vs_tcp_exit,
 	.register_app =		tcp_register_app,
 	.unregister_app =	tcp_unregister_app,
 	.conn_schedule =	tcp_conn_schedule,
@@ -714,5 +722,4 @@ struct ip_vs_protocol ip_vs_protocol_tcp = {
 	.app_conn_bind =	tcp_app_conn_bind,
 	.debug_packet =		ip_vs_tcpudp_debug_packet,
 	.timeout_change =	tcp_timeout_change,
-	.set_state_timeout =	tcp_set_state_timeout,
 };
-- 
1.7.2.3

[PATCH 40/79] IPVS: netns preparation for proto_udp

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

In this phase (one), all local vars will be moved to ipvs struct.

Remaining work, add param struct net *net to a couple of
functions that is common for all protos and use ip_vs_proto_data

*v3
Removed unused function set_state_timeout()

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/netns/ip_vs.h            |    8 +++
 net/netfilter/ipvs/ip_vs_proto.c     |    3 +
 net/netfilter/ipvs/ip_vs_proto_udp.c |   86 +++++++++++++++++-----------------
 3 files changed, 54 insertions(+), 43 deletions(-)

diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index ac77363..62b1448 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -39,6 +39,14 @@ struct netns_ipvs {
 	struct list_head	tcp_apps[TCP_APP_TAB_SIZE];
 	spinlock_t		tcp_app_lock;
 #endif
+	/* ip_vs_proto_udp */
+#ifdef CONFIG_IP_VS_PROTO_UDP
+	#define	UDP_APP_TAB_BITS	4
+	#define	UDP_APP_TAB_SIZE	(1 << UDP_APP_TAB_BITS)
+	#define	UDP_APP_TAB_MASK	(UDP_APP_TAB_SIZE - 1)
+	struct list_head	udp_apps[UDP_APP_TAB_SIZE];
+	spinlock_t		udp_app_lock;
+#endif
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 320c6a6..cdc4142 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -310,6 +310,9 @@ static int __net_init __ip_vs_protocol_init(struct net *net)
 #ifdef CONFIG_IP_VS_PROTO_TCP
 	register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp);
 #endif
+#ifdef CONFIG_IP_VS_PROTO_UDP
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_udp);
+#endif
 	return 0;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 5ab54f6..71a4721 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -9,7 +9,8 @@
  *              as published by the Free Software Foundation; either version
  *              2 of the License, or (at your option) any later version.
  *
- * Changes:
+ * Changes:     Hans Schillstrom <hans.schillstrom@ericsson.com>
+ *              Network name space (netns) aware.
  *
  */
 
@@ -345,19 +346,6 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
 	return 1;
 }
 
-
-/*
- *	Note: the caller guarantees that only one of register_app,
- *	unregister_app or app_conn_bind is called each time.
- */
-
-#define	UDP_APP_TAB_BITS	4
-#define	UDP_APP_TAB_SIZE	(1 << UDP_APP_TAB_BITS)
-#define	UDP_APP_TAB_MASK	(UDP_APP_TAB_SIZE - 1)
-
-static struct list_head udp_apps[UDP_APP_TAB_SIZE];
-static DEFINE_SPINLOCK(udp_app_lock);
-
 static inline __u16 udp_app_hashkey(__be16 port)
 {
 	return (((__force u16)port >> UDP_APP_TAB_BITS) ^ (__force u16)port)
@@ -371,22 +359,24 @@ static int udp_register_app(struct ip_vs_app *inc)
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
 
 	hash = udp_app_hashkey(port);
 
 
-	spin_lock_bh(&udp_app_lock);
-	list_for_each_entry(i, &udp_apps[hash], p_list) {
+	spin_lock_bh(&ipvs->udp_app_lock);
+	list_for_each_entry(i, &ipvs->udp_apps[hash], p_list) {
 		if (i->port == port) {
 			ret = -EEXIST;
 			goto out;
 		}
 	}
-	list_add(&inc->p_list, &udp_apps[hash]);
-	atomic_inc(&ip_vs_protocol_udp.appcnt);
+	list_add(&inc->p_list, &ipvs->udp_apps[hash]);
+	atomic_inc(&pd->pp->appcnt);
 
   out:
-	spin_unlock_bh(&udp_app_lock);
+	spin_unlock_bh(&ipvs->udp_app_lock);
 	return ret;
 }
 
@@ -394,15 +384,19 @@ static int udp_register_app(struct ip_vs_app *inc)
 static void
 udp_unregister_app(struct ip_vs_app *inc)
 {
-	spin_lock_bh(&udp_app_lock);
-	atomic_dec(&ip_vs_protocol_udp.appcnt);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+
+	spin_lock_bh(&ipvs->udp_app_lock);
+	atomic_dec(&pd->pp->appcnt);
 	list_del(&inc->p_list);
-	spin_unlock_bh(&udp_app_lock);
+	spin_unlock_bh(&ipvs->udp_app_lock);
 }
 
 
 static int udp_app_conn_bind(struct ip_vs_conn *cp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
@@ -414,12 +408,12 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp)
 	/* Lookup application incarnations and bind the right one */
 	hash = udp_app_hashkey(cp->vport);
 
-	spin_lock(&udp_app_lock);
-	list_for_each_entry(inc, &udp_apps[hash], p_list) {
+	spin_lock(&ipvs->udp_app_lock);
+	list_for_each_entry(inc, &ipvs->udp_apps[hash], p_list) {
 		if (inc->port == cp->vport) {
 			if (unlikely(!ip_vs_app_inc_get(inc)))
 				break;
-			spin_unlock(&udp_app_lock);
+			spin_unlock(&ipvs->udp_app_lock);
 
 			IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->"
 				      "%s:%u to app %s on port %u\n",
@@ -436,14 +430,14 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp)
 			goto out;
 		}
 	}
-	spin_unlock(&udp_app_lock);
+	spin_unlock(&ipvs->udp_app_lock);
 
   out:
 	return result;
 }
 
 
-static int udp_timeouts[IP_VS_UDP_S_LAST+1] = {
+static const int udp_timeouts[IP_VS_UDP_S_LAST+1] = {
 	[IP_VS_UDP_S_NORMAL]		=	5*60*HZ,
 	[IP_VS_UDP_S_LAST]		=	2*HZ,
 };
@@ -453,14 +447,6 @@ static const char *const udp_state_name_table[IP_VS_UDP_S_LAST+1] = {
 	[IP_VS_UDP_S_LAST]		=	"BUG!",
 };
 
-
-static int
-udp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to)
-{
-	return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_UDP_S_LAST,
-				       udp_state_name_table, sname, to);
-}
-
 static const char * udp_state_name(int state)
 {
 	if (state >= IP_VS_UDP_S_LAST)
@@ -473,18 +459,31 @@ udp_state_transition(struct ip_vs_conn *cp, int direction,
 		     const struct sk_buff *skb,
 		     struct ip_vs_protocol *pp)
 {
-	cp->timeout = pp->timeout_table[IP_VS_UDP_S_NORMAL];
+	struct ip_vs_proto_data *pd;   /* Temp fix, pp will be replaced by pd */
+
+	pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
+	if (unlikely(!pd)) {
+		pr_err("UDP no ns data\n");
+		return 0;
+	}
+
+	cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL];
 	return 1;
 }
 
-static void udp_init(struct ip_vs_protocol *pp)
+static void __udp_init(struct net *net, struct ip_vs_proto_data *pd)
 {
-	IP_VS_INIT_HASH_TABLE(udp_apps);
-	pp->timeout_table = udp_timeouts;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	ip_vs_init_hash_table(ipvs->udp_apps, UDP_APP_TAB_SIZE);
+	spin_lock_init(&ipvs->udp_app_lock);
+	pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts,
+							sizeof(udp_timeouts));
 }
 
-static void udp_exit(struct ip_vs_protocol *pp)
+static void __udp_exit(struct net *net, struct ip_vs_proto_data *pd)
 {
+	kfree(pd->timeout_table);
 }
 
 
@@ -493,8 +492,10 @@ struct ip_vs_protocol ip_vs_protocol_udp = {
 	.protocol =		IPPROTO_UDP,
 	.num_states =		IP_VS_UDP_S_LAST,
 	.dont_defrag =		0,
-	.init =			udp_init,
-	.exit =			udp_exit,
+	.init =			NULL,
+	.exit =			NULL,
+	.init_netns =		__udp_init,
+	.exit_netns =		__udp_exit,
 	.conn_schedule =	udp_conn_schedule,
 	.conn_in_get =		ip_vs_conn_in_get_proto,
 	.conn_out_get =		ip_vs_conn_out_get_proto,
@@ -508,5 +509,4 @@ struct ip_vs_protocol ip_vs_protocol_udp = {
 	.app_conn_bind =	udp_app_conn_bind,
 	.debug_packet =		ip_vs_tcpudp_debug_packet,
 	.timeout_change =	NULL,
-	.set_state_timeout =	udp_set_state_timeout,
 };
-- 
1.7.2.3

[PATCH 41/79] IPVS: netns preparation for proto_sctp

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

In this phase (one), all local vars will be moved to ipvs struct.

Remaining work, add param struct net *net to a couple of
functions that is common for all protos and use ip_vs_proto_data

*v3
 Removed unuset function set_state_timeout()

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/netns/ip_vs.h             |    9 +++
 net/netfilter/ipvs/ip_vs_proto.c      |    3 +
 net/netfilter/ipvs/ip_vs_proto_sctp.c |  121 ++++++++++++++++-----------------
 3 files changed, 70 insertions(+), 63 deletions(-)

diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 62b1448..58bd3fd 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -47,6 +47,15 @@ struct netns_ipvs {
 	struct list_head	udp_apps[UDP_APP_TAB_SIZE];
 	spinlock_t		udp_app_lock;
 #endif
+	/* ip_vs_proto_sctp */
+#ifdef CONFIG_IP_VS_PROTO_SCTP
+	#define SCTP_APP_TAB_BITS	4
+	#define SCTP_APP_TAB_SIZE	(1 << SCTP_APP_TAB_BITS)
+	#define SCTP_APP_TAB_MASK	(SCTP_APP_TAB_SIZE - 1)
+	/* Hash table for SCTP application incarnations	 */
+	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
+	spinlock_t		sctp_app_lock;
+#endif
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index cdc4142..001b2f8 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -313,6 +313,9 @@ static int __net_init __ip_vs_protocol_init(struct net *net)
 #ifdef CONFIG_IP_VS_PROTO_UDP
 	register_ip_vs_proto_netns(net, &ip_vs_protocol_udp);
 #endif
+#ifdef CONFIG_IP_VS_PROTO_SCTP
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_sctp);
+#endif
 	return 0;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 521b827..f826dd1 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -862,7 +862,7 @@ static struct ipvs_sctp_nextstate
 /*
  *      Timeout table[state]
  */
-static int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = {
+static const int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = {
 	[IP_VS_SCTP_S_NONE]         =     2 * HZ,
 	[IP_VS_SCTP_S_INIT_CLI]     =     1 * 60 * HZ,
 	[IP_VS_SCTP_S_INIT_SER]     =     1 * 60 * HZ,
@@ -906,18 +906,6 @@ static const char *sctp_state_name(int state)
 	return "?";
 }
 
-static void sctp_timeout_change(struct ip_vs_protocol *pp, int flags)
-{
-}
-
-static int
-sctp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to)
-{
-
-return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_SCTP_S_LAST,
-				sctp_state_name_table, sname, to);
-}
-
 static inline int
 set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 		int direction, const struct sk_buff *skb)
@@ -926,6 +914,7 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 	unsigned char chunk_type;
 	int event, next_state;
 	int ihl;
+	struct ip_vs_proto_data *pd;
 
 #ifdef CONFIG_IP_VS_IPV6
 	ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr);
@@ -1001,10 +990,13 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 			}
 		}
 	}
+	pd = ip_vs_proto_data_get(&init_net, pp->protocol); /* tmp fix */
+	if (likely(pd))
+		cp->timeout = pd->timeout_table[cp->state = next_state];
+	else	/* What to do ? */
+		cp->timeout = sctp_timeouts[cp->state = next_state];
 
-	 cp->timeout = pp->timeout_table[cp->state = next_state];
-
-	 return 1;
+	return 1;
 }
 
 static int
@@ -1020,16 +1012,6 @@ sctp_state_transition(struct ip_vs_conn *cp, int direction,
 	return ret;
 }
 
-/*
- *      Hash table for SCTP application incarnations
- */
-#define SCTP_APP_TAB_BITS        4
-#define SCTP_APP_TAB_SIZE        (1 << SCTP_APP_TAB_BITS)
-#define SCTP_APP_TAB_MASK        (SCTP_APP_TAB_SIZE - 1)
-
-static struct list_head sctp_apps[SCTP_APP_TAB_SIZE];
-static DEFINE_SPINLOCK(sctp_app_lock);
-
 static inline __u16 sctp_app_hashkey(__be16 port)
 {
 	return (((__force u16)port >> SCTP_APP_TAB_BITS) ^ (__force u16)port)
@@ -1042,34 +1024,40 @@ static int sctp_register_app(struct ip_vs_app *inc)
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_SCTP);
 
 	hash = sctp_app_hashkey(port);
 
-	spin_lock_bh(&sctp_app_lock);
-	list_for_each_entry(i, &sctp_apps[hash], p_list) {
+	spin_lock_bh(&ipvs->sctp_app_lock);
+	list_for_each_entry(i, &ipvs->sctp_apps[hash], p_list) {
 		if (i->port == port) {
 			ret = -EEXIST;
 			goto out;
 		}
 	}
-	list_add(&inc->p_list, &sctp_apps[hash]);
-	atomic_inc(&ip_vs_protocol_sctp.appcnt);
+	list_add(&inc->p_list, &ipvs->sctp_apps[hash]);
+	atomic_inc(&pd->pp->appcnt);
 out:
-	spin_unlock_bh(&sctp_app_lock);
+	spin_unlock_bh(&ipvs->sctp_app_lock);
 
 	return ret;
 }
 
 static void sctp_unregister_app(struct ip_vs_app *inc)
 {
-	spin_lock_bh(&sctp_app_lock);
-	atomic_dec(&ip_vs_protocol_sctp.appcnt);
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_SCTP);
+
+	spin_lock_bh(&ipvs->sctp_app_lock);
+	atomic_dec(&pd->pp->appcnt);
 	list_del(&inc->p_list);
-	spin_unlock_bh(&sctp_app_lock);
+	spin_unlock_bh(&ipvs->sctp_app_lock);
 }
 
 static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
@@ -1080,12 +1068,12 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 	/* Lookup application incarnations and bind the right one */
 	hash = sctp_app_hashkey(cp->vport);
 
-	spin_lock(&sctp_app_lock);
-	list_for_each_entry(inc, &sctp_apps[hash], p_list) {
+	spin_lock(&ipvs->sctp_app_lock);
+	list_for_each_entry(inc, &ipvs->sctp_apps[hash], p_list) {
 		if (inc->port == cp->vport) {
 			if (unlikely(!ip_vs_app_inc_get(inc)))
 				break;
-			spin_unlock(&sctp_app_lock);
+			spin_unlock(&ipvs->sctp_app_lock);
 
 			IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->"
 					"%s:%u to app %s on port %u\n",
@@ -1101,43 +1089,50 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 			goto out;
 		}
 	}
-	spin_unlock(&sctp_app_lock);
+	spin_unlock(&ipvs->sctp_app_lock);
 out:
 	return result;
 }
 
-static void ip_vs_sctp_init(struct ip_vs_protocol *pp)
+/* ---------------------------------------------
+ *   timeouts is netns related now.
+ * ---------------------------------------------
+ */
+static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd)
 {
-	IP_VS_INIT_HASH_TABLE(sctp_apps);
-	pp->timeout_table = sctp_timeouts;
-}
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
+	ip_vs_init_hash_table(ipvs->sctp_apps, SCTP_APP_TAB_SIZE);
+	spin_lock_init(&ipvs->tcp_app_lock);
+	pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts,
+							sizeof(sctp_timeouts));
+}
 
-static void ip_vs_sctp_exit(struct ip_vs_protocol *pp)
+static void __ip_vs_sctp_exit(struct net *net, struct ip_vs_proto_data *pd)
 {
-
+	kfree(pd->timeout_table);
 }
 
 struct ip_vs_protocol ip_vs_protocol_sctp = {
-	.name = "SCTP",
-	.protocol = IPPROTO_SCTP,
-	.num_states = IP_VS_SCTP_S_LAST,
-	.dont_defrag = 0,
-	.appcnt = ATOMIC_INIT(0),
-	.init = ip_vs_sctp_init,
-	.exit = ip_vs_sctp_exit,
-	.register_app = sctp_register_app,
+	.name		= "SCTP",
+	.protocol	= IPPROTO_SCTP,
+	.num_states	= IP_VS_SCTP_S_LAST,
+	.dont_defrag	= 0,
+	.init		= NULL,
+	.exit		= NULL,
+	.init_netns	= __ip_vs_sctp_init,
+	.exit_netns	= __ip_vs_sctp_exit,
+	.register_app	= sctp_register_app,
 	.unregister_app = sctp_unregister_app,
-	.conn_schedule = sctp_conn_schedule,
-	.conn_in_get = ip_vs_conn_in_get_proto,
-	.conn_out_get = ip_vs_conn_out_get_proto,
-	.snat_handler = sctp_snat_handler,
-	.dnat_handler = sctp_dnat_handler,
-	.csum_check = sctp_csum_check,
-	.state_name = sctp_state_name,
+	.conn_schedule	= sctp_conn_schedule,
+	.conn_in_get	= ip_vs_conn_in_get_proto,
+	.conn_out_get	= ip_vs_conn_out_get_proto,
+	.snat_handler	= sctp_snat_handler,
+	.dnat_handler	= sctp_dnat_handler,
+	.csum_check	= sctp_csum_check,
+	.state_name	= sctp_state_name,
 	.state_transition = sctp_state_transition,
-	.app_conn_bind = sctp_app_conn_bind,
-	.debug_packet = ip_vs_tcpudp_debug_packet,
-	.timeout_change = sctp_timeout_change,
-	.set_state_timeout = sctp_set_state_timeout,
+	.app_conn_bind	= sctp_app_conn_bind,
+	.debug_packet	= ip_vs_tcpudp_debug_packet,
+	.timeout_change	= NULL,
 };
-- 
1.7.2.3

[PATCH 42/79] IPVS: netns preparation for proto_ah_esp

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

In this phase (one), all local vars will be moved to ipvs struct.

Remaining work, add param struct net *net to a couple of
functions that common for all protos.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_proto.c        |    6 ++++++
 net/netfilter/ipvs/ip_vs_proto_ah_esp.c |   20 ++++----------------
 2 files changed, 10 insertions(+), 16 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 001b2f8..9f609d4 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -316,6 +316,12 @@ static int __net_init __ip_vs_protocol_init(struct net *net)
 #ifdef CONFIG_IP_VS_PROTO_SCTP
 	register_ip_vs_proto_netns(net, &ip_vs_protocol_sctp);
 #endif
+#ifdef CONFIG_IP_VS_PROTO_AH
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_ah);
+#endif
+#ifdef CONFIG_IP_VS_PROTO_ESP
+	register_ip_vs_proto_netns(net, &ip_vs_protocol_esp);
+#endif
 	return 0;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
index 3a04611..b8b37fa 100644
--- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
@@ -117,26 +117,14 @@ ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 	return 0;
 }
 
-static void ah_esp_init(struct ip_vs_protocol *pp)
-{
-	/* nothing to do now */
-}
-
-
-static void ah_esp_exit(struct ip_vs_protocol *pp)
-{
-	/* nothing to do now */
-}
-
-
 #ifdef CONFIG_IP_VS_PROTO_AH
 struct ip_vs_protocol ip_vs_protocol_ah = {
 	.name =			"AH",
 	.protocol =		IPPROTO_AH,
 	.num_states =		1,
 	.dont_defrag =		1,
-	.init =			ah_esp_init,
-	.exit =			ah_esp_exit,
+	.init =			NULL,
+	.exit =			NULL,
 	.conn_schedule =	ah_esp_conn_schedule,
 	.conn_in_get =		ah_esp_conn_in_get,
 	.conn_out_get =		ah_esp_conn_out_get,
@@ -159,8 +147,8 @@ struct ip_vs_protocol ip_vs_protocol_esp = {
 	.protocol =		IPPROTO_ESP,
 	.num_states =		1,
 	.dont_defrag =		1,
-	.init =			ah_esp_init,
-	.exit =			ah_esp_exit,
+	.init =			NULL,
+	.exit =			NULL,
 	.conn_schedule =	ah_esp_conn_schedule,
 	.conn_in_get =		ah_esp_conn_in_get,
 	.conn_out_get =		ah_esp_conn_out_get,
-- 
1.7.2.3

[PATCH 43/79] IPVS: netns, use ip_vs_proto_data as param.

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

ip_vs_protocol *pp is replaced by ip_vs_proto_data *pd in
function call in ip_vs_protocol struct i.e. :,
 - timeout_change()
 - state_transition()

ip_vs_protocol_timeout_change() got ipvs as param, due to above
and a upcoming patch - defence work

Most of this changes are triggered by Julians comment:
"tcp_timeout_change should work with the new struct ip_vs_proto_data
        so that tcp_state_table will go to pd->state_table
        and set_tcp_state will get pd instead of pp"

*v3
Mostly comments from Julian
The pp -> pd conversion should start from functions like
ip_vs_out() that use pp = ip_vs_proto_get(iph.protocol),
now they should use ip_vs_proto_data_get(net, iph.protocol).
conn_in_get() and conn_out_get() unused param *pp, removed.

*v4
ip_vs_protocol_timeout_change() walk the proto_data path.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                     |   18 ++-----
 net/netfilter/ipvs/ip_vs_conn.c         |    2 -
 net/netfilter/ipvs/ip_vs_core.c         |   77 +++++++++++++++++++------------
 net/netfilter/ipvs/ip_vs_ctl.c          |   55 ++++++++++++++--------
 net/netfilter/ipvs/ip_vs_proto.c        |   21 ++++++---
 net/netfilter/ipvs/ip_vs_proto_ah_esp.c |   10 ++--
 net/netfilter/ipvs/ip_vs_proto_sctp.c   |   16 +++----
 net/netfilter/ipvs/ip_vs_proto_tcp.c    |   27 +++++------
 net/netfilter/ipvs/ip_vs_proto_udp.c    |   11 ++---
 net/netfilter/xt_ipvs.c                 |    2 +-
 10 files changed, 129 insertions(+), 110 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 3c45a00..464ea36 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -372,13 +372,12 @@ struct ip_vs_protocol {
 	void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd);
 
 	int (*conn_schedule)(int af, struct sk_buff *skb,
-			     struct ip_vs_protocol *pp,
+			     struct ip_vs_proto_data *pd,
 			     int *verdict, struct ip_vs_conn **cpp);
 
 	struct ip_vs_conn *
 	(*conn_in_get)(int af,
 		       const struct sk_buff *skb,
-		       struct ip_vs_protocol *pp,
 		       const struct ip_vs_iphdr *iph,
 		       unsigned int proto_off,
 		       int inverse);
@@ -386,7 +385,6 @@ struct ip_vs_protocol {
 	struct ip_vs_conn *
 	(*conn_out_get)(int af,
 			const struct sk_buff *skb,
-			struct ip_vs_protocol *pp,
 			const struct ip_vs_iphdr *iph,
 			unsigned int proto_off,
 			int inverse);
@@ -404,7 +402,7 @@ struct ip_vs_protocol {
 
 	int (*state_transition)(struct ip_vs_conn *cp, int direction,
 				const struct sk_buff *skb,
-				struct ip_vs_protocol *pp);
+				struct ip_vs_proto_data *pd);
 
 	int (*register_app)(struct ip_vs_app *inc);
 
@@ -417,9 +415,7 @@ struct ip_vs_protocol {
 			     int offset,
 			     const char *msg);
 
-	void (*timeout_change)(struct ip_vs_protocol *pp, int flags);
-
-	int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to);
+	void (*timeout_change)(struct ip_vs_proto_data *pd, int flags);
 };
 
 /*
@@ -778,7 +774,6 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p);
 struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p);
 
 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);
@@ -786,7 +781,6 @@ struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
 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);
@@ -917,7 +911,7 @@ static inline void ip_vs_pe_put(const struct ip_vs_pe *pe)
  */
 extern int ip_vs_protocol_init(void);
 extern void ip_vs_protocol_cleanup(void);
-extern void ip_vs_protocol_timeout_change(int flags);
+extern void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags);
 extern int *ip_vs_create_timeout_table(int *table, int size);
 extern int
 ip_vs_set_state_timeout(int *table, int num, const char *const *names,
@@ -947,9 +941,9 @@ extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
 extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
 extern struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
-	       struct ip_vs_protocol *pp, int *ignored);
+	       struct ip_vs_proto_data *pd, int *ignored);
 extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
-			struct ip_vs_protocol *pp);
+			struct ip_vs_proto_data *pd);
 
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 7a0e79e..a7aba6a 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -329,7 +329,6 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb,
 
 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)
 {
@@ -428,7 +427,6 @@ 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)
 {
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index d0616ea..9317aff 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -177,11 +177,11 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 static inline int
 ip_vs_set_state(struct ip_vs_conn *cp, int direction,
 		const struct sk_buff *skb,
-		struct ip_vs_protocol *pp)
+		struct ip_vs_proto_data *pd)
 {
-	if (unlikely(!pp->state_transition))
+	if (unlikely(!pd->pp->state_transition))
 		return 0;
-	return pp->state_transition(cp, direction, skb, pp);
+	return pd->pp->state_transition(cp, direction, skb, pd);
 }
 
 static inline int
@@ -378,8 +378,9 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
  */
 struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
-	       struct ip_vs_protocol *pp, int *ignored)
+	       struct ip_vs_proto_data *pd, int *ignored)
 {
+	struct ip_vs_protocol *pp = pd->pp;
 	struct ip_vs_conn *cp = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_dest *dest;
@@ -408,7 +409,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	 *    Do not schedule replies from local real server.
 	 */
 	if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
-	    (cp = pp->conn_in_get(svc->af, skb, pp, &iph, iph.len, 1))) {
+	    (cp = pp->conn_in_get(svc->af, skb, &iph, iph.len, 1))) {
 		IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
 			      "Not scheduling reply for existing connection");
 		__ip_vs_conn_put(cp);
@@ -479,11 +480,12 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
  *  no destination is available for a new connection.
  */
 int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
-		struct ip_vs_protocol *pp)
+		struct ip_vs_proto_data *pd)
 {
 	__be16 _ports[2], *pptr;
 	struct ip_vs_iphdr iph;
 	int unicast;
+
 	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
 
 	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
@@ -530,10 +532,10 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_in_stats(cp, skb);
 
 		/* set state */
-		cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);
+		cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
 
 		/* transmit the first SYN packet */
-		ret = cp->packet_xmit(skb, cp, pp);
+		ret = cp->packet_xmit(skb, cp, pd->pp);
 		/* do not touch skb anymore */
 
 		atomic_inc(&cp->in_pkts);
@@ -840,7 +842,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
 
 	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -917,7 +919,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 
 	ip_vs_fill_iphdr(AF_INET6, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -956,9 +958,11 @@ static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len)
  * Used for NAT and local client.
  */
 static unsigned int
-handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+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;
+
 	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet");
 
 	if (!skb_make_writable(skb, ihl))
@@ -1007,7 +1011,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 	IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
 
 	ip_vs_out_stats(cp, skb);
-	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp);
+	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd);
 	skb->ipvs_property = 1;
 	if (!(cp->flags & IP_VS_CONN_F_NFCT))
 		ip_vs_notrack(skb);
@@ -1034,6 +1038,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	struct net *net = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
 
 	EnterFunction(11);
@@ -1079,9 +1084,10 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 
-	pp = ip_vs_proto_get(iph.protocol);
-	if (unlikely(!pp))
+	pd = ip_vs_proto_data_get(net, iph.protocol);
+	if (unlikely(!pd))
 		return NF_ACCEPT;
+	pp = pd->pp;
 
 	/* reassemble IP fragments */
 #ifdef CONFIG_IP_VS_IPV6
@@ -1107,10 +1113,10 @@ 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, pp, &iph, iph.len, 0);
+	cp = pp->conn_out_get(af, skb, &iph, iph.len, 0);
 
 	if (likely(cp))
-		return handle_response(af, skb, pp, cp, iph.len);
+		return handle_response(af, skb, pd, cp, iph.len);
 	if (sysctl_ip_vs_nat_icmp_send &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
@@ -1236,12 +1242,14 @@ ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb,
 static int
 ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 {
+	struct net *net = NULL;
 	struct iphdr *iph;
 	struct icmphdr	_icmph, *ic;
 	struct iphdr	_ciph, *cih;	/* The ip header contained within the ICMP */
 	struct ip_vs_iphdr ciph;
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	unsigned int offset, ihl, verdict;
 	union nf_inet_addr snet;
 
@@ -1283,9 +1291,11 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 	if (cih == NULL)
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
 
-	pp = ip_vs_proto_get(cih->protocol);
-	if (!pp)
+	net = skb_net(skb);
+	pd = ip_vs_proto_data_get(net, cih->protocol);
+	if (!pd)
 		return NF_ACCEPT;
+	pp = pd->pp;
 
 	/* Is the embedded protocol header present? */
 	if (unlikely(cih->frag_off & htons(IP_OFFSET) &&
@@ -1299,10 +1309,10 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_in_get(AF_INET, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1);
 	if (!cp) {
 		/* The packet could also belong to a local client */
-		cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1);
+		cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1);
 		if (cp) {
 			snet.ip = iph->saddr;
 			return handle_response_icmp(AF_INET, skb, &snet,
@@ -1346,6 +1356,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 static int
 ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 {
+	struct net *net = NULL;
 	struct ipv6hdr *iph;
 	struct icmp6hdr	_icmph, *ic;
 	struct ipv6hdr	_ciph, *cih;	/* The ip header contained
@@ -1353,6 +1364,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	struct ip_vs_iphdr ciph;
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	unsigned int offset, verdict;
 	union nf_inet_addr snet;
 	struct rt6_info *rt;
@@ -1395,9 +1407,11 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 	if (cih == NULL)
 		return NF_ACCEPT; /* The packet looks wrong, ignore */
 
-	pp = ip_vs_proto_get(cih->nexthdr);
-	if (!pp)
+	net = skb_net(skb);
+	pd = ip_vs_proto_data_get(net, cih->nexthdr);
+	if (!pd)
 		return NF_ACCEPT;
+	pp = pd->pp;
 
 	/* Is the embedded protocol header present? */
 	/* TODO: we don't support fragmentation at the moment anyways */
@@ -1411,10 +1425,10 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	ip_vs_fill_iphdr(AF_INET6, cih, &ciph);
 	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_in_get(AF_INET6, skb, pp, &ciph, offset, 1);
+	cp = pp->conn_in_get(AF_INET6, skb, &ciph, offset, 1);
 	if (!cp) {
 		/* The packet could also belong to a local client */
-		cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1);
+		cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1);
 		if (cp) {
 			ipv6_addr_copy(&snet.in6, &iph->saddr);
 			return handle_response_icmp(AF_INET6, skb, &snet,
@@ -1457,8 +1471,10 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 static unsigned int
 ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 {
+	struct net *net = NULL;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
 	int ret, restart, pkts;
 
@@ -1514,20 +1530,21 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 			ip_vs_fill_iphdr(af, skb_network_header(skb), &iph);
 		}
 
+	net = skb_net(skb);
 	/* Protocol supported? */
-	pp = ip_vs_proto_get(iph.protocol);
-	if (unlikely(!pp))
+	pd = ip_vs_proto_data_get(net, iph.protocol);
+	if (unlikely(!pd))
 		return NF_ACCEPT;
-
+	pp = pd->pp;
 	/*
 	 * Check if the packet belongs to an existing connection entry
 	 */
-	cp = pp->conn_in_get(af, skb, pp, &iph, iph.len, 0);
+	cp = pp->conn_in_get(af, skb, &iph, iph.len, 0);
 
 	if (unlikely(!cp)) {
 		int v;
 
-		if (!pp->conn_schedule(af, skb, pp, &v, &cp))
+		if (!pp->conn_schedule(af, skb, pd, &v, &cp))
 			return v;
 	}
 
@@ -1555,7 +1572,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	}
 
 	ip_vs_in_stats(cp, skb);
-	restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);
+	restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
 	if (cp->packet_xmit)
 		ret = cp->packet_xmit(skb, cp, pp);
 		/* do not touch skb anymore */
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 2d7c96b..88474f1 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -38,6 +38,7 @@
 #include <linux/mutex.h>
 
 #include <net/net_namespace.h>
+#include <linux/nsproxy.h>
 #include <net/ip.h>
 #ifdef CONFIG_IP_VS_IPV6
 #include <net/ipv6.h>
@@ -125,7 +126,7 @@ static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr)
  *	update_defense_level is called from keventd and from sysctl,
  *	so it needs to protect itself from softirqs
  */
-static void update_defense_level(void)
+static void update_defense_level(struct netns_ipvs *ipvs)
 {
 	struct sysinfo i;
 	static int old_secure_tcp = 0;
@@ -239,7 +240,8 @@ static void update_defense_level(void)
 	}
 	old_secure_tcp = sysctl_ip_vs_secure_tcp;
 	if (to_change >= 0)
-		ip_vs_protocol_timeout_change(sysctl_ip_vs_secure_tcp>1);
+		ip_vs_protocol_timeout_change(ipvs,
+					     sysctl_ip_vs_secure_tcp > 1);
 	spin_unlock(&ip_vs_securetcp_lock);
 
 	local_bh_enable();
@@ -255,7 +257,10 @@ static DECLARE_DELAYED_WORK(defense_work, defense_work_handler);
 
 static void defense_work_handler(struct work_struct *work)
 {
-	update_defense_level();
+	struct net *net = &init_net;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	update_defense_level(ipvs);
 	if (atomic_read(&ip_vs_dropentry))
 		ip_vs_random_dropentry();
 
@@ -1502,6 +1507,7 @@ static int
 proc_do_defense_mode(ctl_table *table, int write,
 		     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct net *net = current->nsproxy->net_ns;
 	int *valp = table->data;
 	int val = *valp;
 	int rc;
@@ -1512,7 +1518,7 @@ proc_do_defense_mode(ctl_table *table, int write,
 			/* Restore the correct value */
 			*valp = val;
 		} else {
-			update_defense_level();
+			update_defense_level(net_ipvs(net));
 		}
 	}
 	return rc;
@@ -2033,8 +2039,10 @@ static const struct file_operations ip_vs_stats_fops = {
 /*
  *	Set timeout values for tcp tcpfin udp in the timeout_table.
  */
-static int ip_vs_set_timeout(struct ip_vs_timeout_user *u)
+static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u)
 {
+	struct ip_vs_proto_data *pd;
+
 	IP_VS_DBG(2, "Setting timeout tcp:%d tcpfin:%d udp:%d\n",
 		  u->tcp_timeout,
 		  u->tcp_fin_timeout,
@@ -2042,19 +2050,22 @@ static int ip_vs_set_timeout(struct ip_vs_timeout_user *u)
 
 #ifdef CONFIG_IP_VS_PROTO_TCP
 	if (u->tcp_timeout) {
-		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_ESTABLISHED]
+		pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
+		pd->timeout_table[IP_VS_TCP_S_ESTABLISHED]
 			= u->tcp_timeout * HZ;
 	}
 
 	if (u->tcp_fin_timeout) {
-		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_FIN_WAIT]
+		pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
+		pd->timeout_table[IP_VS_TCP_S_FIN_WAIT]
 			= u->tcp_fin_timeout * HZ;
 	}
 #endif
 
 #ifdef CONFIG_IP_VS_PROTO_UDP
 	if (u->udp_timeout) {
-		ip_vs_protocol_udp.timeout_table[IP_VS_UDP_S_NORMAL]
+		pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
+		pd->timeout_table[IP_VS_UDP_S_NORMAL]
 			= u->udp_timeout * HZ;
 	}
 #endif
@@ -2158,7 +2169,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 		goto out_unlock;
 	} else if (cmd == IP_VS_SO_SET_TIMEOUT) {
 		/* Set timeout values for (tcp tcpfin udp) */
-		ret = ip_vs_set_timeout((struct ip_vs_timeout_user *)arg);
+		ret = ip_vs_set_timeout(net, (struct ip_vs_timeout_user *)arg);
 		goto out_unlock;
 	} else if (cmd == IP_VS_SO_SET_STARTDAEMON) {
 		struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
@@ -2370,17 +2381,19 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
 }
 
 static inline void
-__ip_vs_get_timeouts(struct ip_vs_timeout_user *u)
+__ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u)
 {
+	struct ip_vs_proto_data *pd;
+
 #ifdef CONFIG_IP_VS_PROTO_TCP
-	u->tcp_timeout =
-		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ;
-	u->tcp_fin_timeout =
-		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ;
+	pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
+	u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ;
+	u->tcp_fin_timeout = pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ;
 #endif
 #ifdef CONFIG_IP_VS_PROTO_UDP
+	pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
 	u->udp_timeout =
-		ip_vs_protocol_udp.timeout_table[IP_VS_UDP_S_NORMAL] / HZ;
+			pd->timeout_table[IP_VS_UDP_S_NORMAL] / HZ;
 #endif
 }
 
@@ -2521,7 +2534,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	{
 		struct ip_vs_timeout_user t;
 
-		__ip_vs_get_timeouts(&t);
+		__ip_vs_get_timeouts(net, &t);
 		if (copy_to_user(user, &t, sizeof(t)) != 0)
 			ret = -EFAULT;
 	}
@@ -3092,11 +3105,11 @@ static int ip_vs_genl_del_daemon(struct nlattr **attrs)
 	return stop_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
 }
 
-static int ip_vs_genl_set_config(struct nlattr **attrs)
+static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs)
 {
 	struct ip_vs_timeout_user t;
 
-	__ip_vs_get_timeouts(&t);
+	__ip_vs_get_timeouts(net, &t);
 
 	if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP])
 		t.tcp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]);
@@ -3108,7 +3121,7 @@ static int ip_vs_genl_set_config(struct nlattr **attrs)
 	if (attrs[IPVS_CMD_ATTR_TIMEOUT_UDP])
 		t.udp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]);
 
-	return ip_vs_set_timeout(&t);
+	return ip_vs_set_timeout(net, &t);
 }
 
 static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
@@ -3129,7 +3142,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 		ret = ip_vs_flush(net);
 		goto out;
 	} else if (cmd == IPVS_CMD_SET_CONFIG) {
-		ret = ip_vs_genl_set_config(info->attrs);
+		ret = ip_vs_genl_set_config(net, info->attrs);
 		goto out;
 	} else if (cmd == IPVS_CMD_NEW_DAEMON ||
 		   cmd == IPVS_CMD_DEL_DAEMON) {
@@ -3281,7 +3294,7 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
 	{
 		struct ip_vs_timeout_user t;
 
-		__ip_vs_get_timeouts(&t);
+		__ip_vs_get_timeouts(net, &t);
 #ifdef CONFIG_IP_VS_PROTO_TCP
 		NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP, t.tcp_timeout);
 		NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP_FIN,
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 9f609d4..6ac986c 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -152,9 +152,8 @@ EXPORT_SYMBOL(ip_vs_proto_get);
  *	get ip_vs_protocol object data by netns and proto
  */
 struct ip_vs_proto_data *
-ip_vs_proto_data_get(struct net *net, unsigned short proto)
+__ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto)
 {
-	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_proto_data *pd;
 	unsigned hash = IP_VS_PROTO_HASH(proto);
 
@@ -165,20 +164,28 @@ ip_vs_proto_data_get(struct net *net, unsigned short proto)
 
 	return NULL;
 }
+
+struct ip_vs_proto_data *
+ip_vs_proto_data_get(struct net *net, unsigned short proto)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	return __ipvs_proto_data_get(ipvs, proto);
+}
 EXPORT_SYMBOL(ip_vs_proto_data_get);
 
 /*
  *	Propagate event for state change to all protocols
  */
-void ip_vs_protocol_timeout_change(int flags)
+void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags)
 {
-	struct ip_vs_protocol *pp;
+	struct ip_vs_proto_data *pd;
 	int i;
 
 	for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) {
-		for (pp = ip_vs_proto_table[i]; pp; pp = pp->next) {
-			if (pp->timeout_change)
-				pp->timeout_change(pp, flags);
+		for (pd = ipvs->proto_data_table[i]; pd; pd = pd->next) {
+			if (pd->pp->timeout_change)
+				pd->pp->timeout_change(pd, flags);
 		}
 	}
 }
diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
index b8b37fa..28039cb 100644
--- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
@@ -55,7 +55,7 @@ ah_esp_conn_fill_param_proto(int af, const struct ip_vs_iphdr *iph,
 }
 
 static struct ip_vs_conn *
-ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
+ah_esp_conn_in_get(int af, const struct sk_buff *skb,
 		   const struct ip_vs_iphdr *iph, unsigned int proto_off,
 		   int inverse)
 {
@@ -72,7 +72,7 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
 		IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for outin packet "
 			      "%s%s %s->%s\n",
 			      inverse ? "ICMP+" : "",
-			      pp->name,
+			      ip_vs_proto_get(iph->protocol)->name,
 			      IP_VS_DBG_ADDR(af, &iph->saddr),
 			      IP_VS_DBG_ADDR(af, &iph->daddr));
 	}
@@ -83,7 +83,6 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
 
 static struct ip_vs_conn *
 ah_esp_conn_out_get(int af, const struct sk_buff *skb,
-		    struct ip_vs_protocol *pp,
 		    const struct ip_vs_iphdr *iph,
 		    unsigned int proto_off,
 		    int inverse)
@@ -97,7 +96,7 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb,
 		IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet "
 			      "%s%s %s->%s\n",
 			      inverse ? "ICMP+" : "",
-			      pp->name,
+			      ip_vs_proto_get(iph->protocol)->name,
 			      IP_VS_DBG_ADDR(af, &iph->saddr),
 			      IP_VS_DBG_ADDR(af, &iph->daddr));
 	}
@@ -107,7 +106,7 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb,
 
 
 static int
-ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		     int *verdict, struct ip_vs_conn **cpp)
 {
 	/*
@@ -137,7 +136,6 @@ struct ip_vs_protocol ip_vs_protocol_ah = {
 	.app_conn_bind =	NULL,
 	.debug_packet =		ip_vs_tcpudp_debug_packet,
 	.timeout_change =	NULL,		/* ISAKMP */
-	.set_state_timeout =	NULL,
 };
 #endif
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index f826dd1..19bc379 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -9,7 +9,7 @@
 #include <net/ip_vs.h>
 
 static int
-sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		   int *verdict, struct ip_vs_conn **cpp)
 {
 	struct net *net;
@@ -47,10 +47,10 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pp, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pp);
+				*verdict = ip_vs_leave(svc, skb, pd);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -907,14 +907,13 @@ static const char *sctp_state_name(int state)
 }
 
 static inline int
-set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
+set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 		int direction, const struct sk_buff *skb)
 {
 	sctp_chunkhdr_t _sctpch, *sch;
 	unsigned char chunk_type;
 	int event, next_state;
 	int ihl;
-	struct ip_vs_proto_data *pd;
 
 #ifdef CONFIG_IP_VS_IPV6
 	ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr);
@@ -966,7 +965,7 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 
 		IP_VS_DBG_BUF(8, "%s %s  %s:%d->"
 				"%s:%d state: %s->%s conn->refcnt:%d\n",
-				pp->name,
+				pd->pp->name,
 				((direction == IP_VS_DIR_OUTPUT) ?
 				 "output " : "input "),
 				IP_VS_DBG_ADDR(cp->af, &cp->daddr),
@@ -990,7 +989,6 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 			}
 		}
 	}
-	pd = ip_vs_proto_data_get(&init_net, pp->protocol); /* tmp fix */
 	if (likely(pd))
 		cp->timeout = pd->timeout_table[cp->state = next_state];
 	else	/* What to do ? */
@@ -1001,12 +999,12 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 
 static int
 sctp_state_transition(struct ip_vs_conn *cp, int direction,
-		const struct sk_buff *skb, struct ip_vs_protocol *pp)
+		const struct sk_buff *skb, struct ip_vs_proto_data *pd)
 {
 	int ret = 0;
 
 	spin_lock(&cp->lock);
-	ret = set_sctp_state(pp, cp, direction, skb);
+	ret = set_sctp_state(pd, cp, direction, skb);
 	spin_unlock(&cp->lock);
 
 	return ret;
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 9d9df3d..d7c2455 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -32,7 +32,7 @@
 #include <net/ip_vs.h>
 
 static int
-tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		  int *verdict, struct ip_vs_conn **cpp)
 {
 	struct net *net;
@@ -68,10 +68,10 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pp, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pp);
+				*verdict = ip_vs_leave(svc, skb, pd);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -448,10 +448,7 @@ static struct tcp_states_t tcp_states_dos [] = {
 /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
 };
 
-static struct tcp_states_t *tcp_state_table = tcp_states;
-
-
-static void tcp_timeout_change(struct ip_vs_protocol *pp, int flags)
+static void tcp_timeout_change(struct ip_vs_proto_data *pd, int flags)
 {
 	int on = (flags & 1);		/* secure_tcp */
 
@@ -461,7 +458,7 @@ static void tcp_timeout_change(struct ip_vs_protocol *pp, int flags)
 	** for most if not for all of the applications. Something
 	** like "capabilities" (flags) for each object.
 	*/
-	tcp_state_table = (on? tcp_states_dos : tcp_states);
+	pd->tcp_state_table = (on ? tcp_states_dos : tcp_states);
 }
 
 static inline int tcp_state_idx(struct tcphdr *th)
@@ -478,13 +475,12 @@ static inline int tcp_state_idx(struct tcphdr *th)
 }
 
 static inline void
-set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
+set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 	      int direction, struct tcphdr *th)
 {
 	int state_idx;
 	int new_state = IP_VS_TCP_S_CLOSE;
 	int state_off = tcp_state_off[direction];
-	struct ip_vs_proto_data *pd;  /* Temp fix */
 
 	/*
 	 *    Update state offset to INPUT_ONLY if necessary
@@ -502,7 +498,8 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 		goto tcp_state_out;
 	}
 
-	new_state = tcp_state_table[state_off+state_idx].next_state[cp->state];
+	new_state =
+		pd->tcp_state_table[state_off+state_idx].next_state[cp->state];
 
   tcp_state_out:
 	if (new_state != cp->state) {
@@ -510,7 +507,7 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 
 		IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] %s:%d->"
 			      "%s:%d state: %s->%s conn->refcnt:%d\n",
-			      pp->name,
+			      pd->pp->name,
 			      ((state_off == TCP_DIR_OUTPUT) ?
 			       "output " : "input "),
 			      th->syn ? 'S' : '.',
@@ -540,7 +537,6 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 		}
 	}
 
-	pd = ip_vs_proto_data_get(&init_net, pp->protocol);
 	if (likely(pd))
 		cp->timeout = pd->timeout_table[cp->state = new_state];
 	else	/* What to do ? */
@@ -553,7 +549,7 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp,
 static int
 tcp_state_transition(struct ip_vs_conn *cp, int direction,
 		     const struct sk_buff *skb,
-		     struct ip_vs_protocol *pp)
+		     struct ip_vs_proto_data *pd)
 {
 	struct tcphdr _tcph, *th;
 
@@ -568,7 +564,7 @@ tcp_state_transition(struct ip_vs_conn *cp, int direction,
 		return 0;
 
 	spin_lock(&cp->lock);
-	set_tcp_state(pp, cp, direction, th);
+	set_tcp_state(pd, cp, direction, th);
 	spin_unlock(&cp->lock);
 
 	return 1;
@@ -691,6 +687,7 @@ static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd)
 	spin_lock_init(&ipvs->tcp_app_lock);
 	pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts,
 							sizeof(tcp_timeouts));
+	pd->tcp_state_table =  tcp_states;
 }
 
 static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd)
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 71a4721..aa85df2 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -29,7 +29,7 @@
 #include <net/ip6_checksum.h>
 
 static int
-udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
+udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 		  int *verdict, struct ip_vs_conn **cpp)
 {
 	struct net *net;
@@ -64,10 +64,10 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
 		 * Let the virtual server select a real server for the
 		 * incoming connection, and create a connection entry.
 		 */
-		*cpp = ip_vs_schedule(svc, skb, pp, &ignored);
+		*cpp = ip_vs_schedule(svc, skb, pd, &ignored);
 		if (!*cpp && ignored <= 0) {
 			if (!ignored)
-				*verdict = ip_vs_leave(svc, skb, pp);
+				*verdict = ip_vs_leave(svc, skb, pd);
 			else {
 				ip_vs_service_put(svc);
 				*verdict = NF_DROP;
@@ -457,11 +457,8 @@ static const char * udp_state_name(int state)
 static int
 udp_state_transition(struct ip_vs_conn *cp, int direction,
 		     const struct sk_buff *skb,
-		     struct ip_vs_protocol *pp)
+		     struct ip_vs_proto_data *pd)
 {
-	struct ip_vs_proto_data *pd;   /* Temp fix, pp will be replaced by pd */
-
-	pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
 	if (unlikely(!pd)) {
 		pr_err("UDP no ns data\n");
 		return 0;
diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c
index 9127a3d..bb10b07 100644
--- a/net/netfilter/xt_ipvs.c
+++ b/net/netfilter/xt_ipvs.c
@@ -85,7 +85,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	/*
 	 * Check if the packet belongs to an existing entry
 	 */
-	cp = pp->conn_out_get(family, skb, pp, &iph, iph.len, 1 /* inverse */);
+	cp = pp->conn_out_get(family, skb, &iph, iph.len, 1 /* inverse */);
 	if (unlikely(cp == NULL)) {
 		match = false;
 		goto out;
-- 
1.7.2.3

[PATCH 44/79] IPVS: netns, common protocol changes and use of appcnt.

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

appcnt and timeout_table moved from struct ip_vs_protocol to
ip_vs proto_data.

struct net *net added as first param to
 - register_app()
 - unregister_app()
 - app_conn_bind()
 - ip_vs_conn_new()

[horms@verge.net.au: removed cosmetic-change-only hunk]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                   |    2 -
 net/netfilter/ipvs/ip_vs_conn.c       |    6 ++--
 net/netfilter/ipvs/ip_vs_proto_sctp.c |    4 +-
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |    5 +--
 net/netfilter/ipvs/ip_vs_proto_udp.c  |    4 +-
 net/netfilter/ipvs/ip_vs_sync.c       |   55 ++++++++++++++++++---------------
 6 files changed, 39 insertions(+), 37 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 464ea36..cc6ae62 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -360,8 +360,6 @@ struct ip_vs_protocol {
 	u16			protocol;
 	u16			num_states;
 	int			dont_defrag;
-	atomic_t		appcnt;		/* counter of proto app incs */
-	int			*timeout_table;	/* protocol timeout table */
 
 	void (*init)(struct ip_vs_protocol *pp);
 
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index a7aba6a..b2024c9 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -804,7 +804,7 @@ 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 ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, p->protocol);
 
 	cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC);
 	if (cp == NULL) {
@@ -863,8 +863,8 @@ 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
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 19bc379..0f14f79 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -1035,7 +1035,7 @@ static int sctp_register_app(struct ip_vs_app *inc)
 		}
 	}
 	list_add(&inc->p_list, &ipvs->sctp_apps[hash]);
-	atomic_inc(&pd->pp->appcnt);
+	atomic_inc(&pd->appcnt);
 out:
 	spin_unlock_bh(&ipvs->sctp_app_lock);
 
@@ -1048,7 +1048,7 @@ static void sctp_unregister_app(struct ip_vs_app *inc)
 	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_SCTP);
 
 	spin_lock_bh(&ipvs->sctp_app_lock);
-	atomic_dec(&pd->pp->appcnt);
+	atomic_dec(&pd->appcnt);
 	list_del(&inc->p_list);
 	spin_unlock_bh(&ipvs->sctp_app_lock);
 }
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index d7c2455..290b380 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -596,7 +596,7 @@ static int tcp_register_app(struct ip_vs_app *inc)
 		}
 	}
 	list_add(&inc->p_list, &ipvs->tcp_apps[hash]);
-	atomic_inc(&pd->pp->appcnt);
+	atomic_inc(&pd->appcnt);
 
   out:
 	spin_unlock_bh(&ipvs->tcp_app_lock);
@@ -611,7 +611,7 @@ tcp_unregister_app(struct ip_vs_app *inc)
 	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_TCP);
 
 	spin_lock_bh(&ipvs->tcp_app_lock);
-	atomic_dec(&pd->pp->appcnt);
+	atomic_dec(&pd->appcnt);
 	list_del(&inc->p_list);
 	spin_unlock_bh(&ipvs->tcp_app_lock);
 }
@@ -701,7 +701,6 @@ struct ip_vs_protocol ip_vs_protocol_tcp = {
 	.protocol =		IPPROTO_TCP,
 	.num_states =		IP_VS_TCP_S_LAST,
 	.dont_defrag =		0,
-	.appcnt =		ATOMIC_INIT(0),
 	.init =			NULL,
 	.exit =			NULL,
 	.init_netns =		__ip_vs_tcp_init,
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index aa85df2..3719837 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -373,7 +373,7 @@ static int udp_register_app(struct ip_vs_app *inc)
 		}
 	}
 	list_add(&inc->p_list, &ipvs->udp_apps[hash]);
-	atomic_inc(&pd->pp->appcnt);
+	atomic_inc(&pd->appcnt);
 
   out:
 	spin_unlock_bh(&ipvs->udp_app_lock);
@@ -388,7 +388,7 @@ udp_unregister_app(struct ip_vs_app *inc)
 	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 
 	spin_lock_bh(&ipvs->udp_app_lock);
-	atomic_dec(&pd->pp->appcnt);
+	atomic_dec(&pd->appcnt);
 	list_del(&inc->p_list);
 	spin_unlock_bh(&ipvs->udp_app_lock);
 }
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 662aa2c..6831e8f 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -725,17 +725,16 @@ ip_vs_conn_fill_param_sync(int af, union ip_vs_sync_conn *sc,
  *  Param: ...
  *         timeout is in sec.
  */
-static void ip_vs_proc_conn(struct ip_vs_conn_param *param,  unsigned flags,
-			    unsigned state, unsigned protocol, unsigned type,
+static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
+			    unsigned int flags, unsigned int state,
+			    unsigned int protocol, unsigned int type,
 			    const union nf_inet_addr *daddr, __be16 dport,
 			    unsigned long timeout, __u32 fwmark,
-			    struct ip_vs_sync_conn_options *opt,
-			    struct ip_vs_protocol *pp)
+			    struct ip_vs_sync_conn_options *opt)
 {
 	struct ip_vs_dest *dest;
 	struct ip_vs_conn *cp;
 
-
 	if (!(flags & IP_VS_CONN_F_TEMPLATE))
 		cp = ip_vs_conn_in_get(param);
 	else
@@ -821,17 +820,23 @@ static void ip_vs_proc_conn(struct ip_vs_conn_param *param,  unsigned flags,
 		if (timeout > MAX_SCHEDULE_TIMEOUT / HZ)
 			timeout = MAX_SCHEDULE_TIMEOUT / HZ;
 		cp->timeout = timeout*HZ;
-	} else if (!(flags & IP_VS_CONN_F_TEMPLATE) && pp->timeout_table)
-		cp->timeout = pp->timeout_table[state];
-	else
-		cp->timeout = (3*60*HZ);
+	} else {
+		struct ip_vs_proto_data *pd;
+
+		pd = ip_vs_proto_data_get(net, protocol);
+		if (!(flags & IP_VS_CONN_F_TEMPLATE) && pd && pd->timeout_table)
+			cp->timeout = pd->timeout_table[state];
+		else
+			cp->timeout = (3*60*HZ);
+	}
 	ip_vs_conn_put(cp);
 }
 
 /*
  *  Process received multicast message for Version 0
  */
-static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
+static void ip_vs_process_message_v0(struct net *net, const char *buffer,
+				     const size_t buflen)
 {
 	struct ip_vs_sync_mesg_v0 *m = (struct ip_vs_sync_mesg_v0 *)buffer;
 	struct ip_vs_sync_conn_v0 *s;
@@ -879,7 +884,6 @@ static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
 			}
 		} else {
 			/* protocol in templates is not used for state/timeout */
-			pp = NULL;
 			if (state > 0) {
 				IP_VS_DBG(2, "BACKUP v0, Invalid template state %u\n",
 					state);
@@ -894,9 +898,9 @@ static void ip_vs_process_message_v0(const char *buffer, const size_t buflen)
 				      s->vport, &param);
 
 		/* Send timeout as Zero */
-		ip_vs_proc_conn(&param, flags, state, s->protocol, AF_INET,
+		ip_vs_proc_conn(net, &param, flags, state, s->protocol, AF_INET,
 				(union nf_inet_addr *)&s->daddr, s->dport,
-				0, 0, opt, pp);
+				0, 0, opt);
 	}
 }
 
@@ -945,7 +949,7 @@ static int ip_vs_proc_str(__u8 *p, unsigned int plen, unsigned int *data_len,
 /*
  *   Process a Version 1 sync. connection
  */
-static inline int ip_vs_proc_sync_conn(__u8 *p, __u8 *msg_end)
+static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end)
 {
 	struct ip_vs_sync_conn_options opt;
 	union  ip_vs_sync_conn *s;
@@ -1043,7 +1047,6 @@ static inline int ip_vs_proc_sync_conn(__u8 *p, __u8 *msg_end)
 		}
 	} else {
 		/* protocol in templates is not used for state/timeout */
-		pp = NULL;
 		if (state > 0) {
 			IP_VS_DBG(3, "BACKUP, Invalid template state %u\n",
 				state);
@@ -1058,18 +1061,18 @@ static inline int ip_vs_proc_sync_conn(__u8 *p, __u8 *msg_end)
 	}
 	/* If only IPv4, just silent skip IPv6 */
 	if (af == AF_INET)
-		ip_vs_proc_conn(&param, flags, state, s->v4.protocol, af,
+		ip_vs_proc_conn(net, &param, flags, state, s->v4.protocol, af,
 				(union nf_inet_addr *)&s->v4.daddr, s->v4.dport,
 				ntohl(s->v4.timeout), ntohl(s->v4.fwmark),
-				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL),
-				pp);
+				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL)
+				);
 #ifdef CONFIG_IP_VS_IPV6
 	else
-		ip_vs_proc_conn(&param, flags, state, s->v6.protocol, af,
+		ip_vs_proc_conn(net, &param, flags, state, s->v6.protocol, af,
 				(union nf_inet_addr *)&s->v6.daddr, s->v6.dport,
 				ntohl(s->v6.timeout), ntohl(s->v6.fwmark),
-				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL),
-				pp);
+				(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL)
+				);
 #endif
 	return 0;
 	/* Error exit */
@@ -1083,7 +1086,8 @@ out:
  *      ip_vs_conn entries.
  *      Handles Version 0 & 1
  */
-static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
+static void ip_vs_process_message(struct net *net, __u8 *buffer,
+				  const size_t buflen)
 {
 	struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer;
 	__u8 *p, *msg_end;
@@ -1136,7 +1140,8 @@ static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
 				return;
 			}
 			/* Process a single sync_conn */
-			if ((retc=ip_vs_proc_sync_conn(p, msg_end)) < 0) {
+			retc = ip_vs_proc_sync_conn(net, p, msg_end);
+			if (retc < 0) {
 				IP_VS_ERR_RL("BACKUP, Dropping buffer, Err: %d in decoding\n",
 					     retc);
 				return;
@@ -1146,7 +1151,7 @@ static void ip_vs_process_message(__u8 *buffer, const size_t buflen)
 		}
 	} else {
 		/* Old type of message */
-		ip_vs_process_message_v0(buffer, buflen);
+		ip_vs_process_message_v0(net, buffer, buflen);
 		return;
 	}
 }
@@ -1500,7 +1505,7 @@ static int sync_thread_backup(void *data)
 			/* disable bottom half, because it accesses the data
 			   shared by softirq while getting/creating conns */
 			local_bh_disable();
-			ip_vs_process_message(tinfo->buf, len);
+			ip_vs_process_message(&init_net, tinfo->buf, len);
 			local_bh_enable();
 		}
 	}
-- 
1.7.2.3

[PATCH 45/79] IPVS: netns awareness to ip_vs_app

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

All variables moved to struct ipvs,
most external changes fixed (i.e. init_net removed)

in ip_vs_protocol param struct net *net added to:
 - register_app()
 - unregister_app()
This affected almost all proto_xxx.c files

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                   |   12 +++---
 include/net/netns/ip_vs.h             |    5 ++
 net/netfilter/ipvs/ip_vs_app.c        |   73 +++++++++++++++++++-------------
 net/netfilter/ipvs/ip_vs_ftp.c        |    8 ++--
 net/netfilter/ipvs/ip_vs_proto_sctp.c |   12 +++---
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |   12 +++---
 net/netfilter/ipvs/ip_vs_proto_udp.c  |   12 +++---
 7 files changed, 76 insertions(+), 58 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index cc6ae62..0cdd8ce 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -402,9 +402,9 @@ struct ip_vs_protocol {
 				const struct sk_buff *skb,
 				struct ip_vs_proto_data *pd);
 
-	int (*register_app)(struct ip_vs_app *inc);
+	int (*register_app)(struct net *net, struct ip_vs_app *inc);
 
-	void (*unregister_app)(struct ip_vs_app *inc);
+	void (*unregister_app)(struct net *net, struct ip_vs_app *inc);
 
 	int (*app_conn_bind)(struct ip_vs_conn *cp);
 
@@ -871,12 +871,12 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp)
  *      (from ip_vs_app.c)
  */
 #define IP_VS_APP_MAX_PORTS  8
-extern int register_ip_vs_app(struct ip_vs_app *app);
-extern void unregister_ip_vs_app(struct ip_vs_app *app);
+extern int register_ip_vs_app(struct net *net, struct ip_vs_app *app);
+extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app);
 extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
 extern void ip_vs_unbind_app(struct ip_vs_conn *cp);
-extern int
-register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port);
+extern int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app,
+				  __u16 proto, __u16 port);
 extern int ip_vs_app_inc_get(struct ip_vs_app *inc);
 extern void ip_vs_app_inc_put(struct ip_vs_app *inc);
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 58bd3fd..03f7fe1 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -28,6 +28,11 @@ struct netns_ipvs {
 	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
 
 	struct list_head	rs_table[IP_VS_RTAB_SIZE];
+	/* ip_vs_app */
+	struct list_head	app_list;
+	struct mutex		app_mutex;
+	struct lock_class_key	app_key;	/* mutex debuging */
+
 	/* ip_vs_proto */
 	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
 	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 40b09cc..286f465 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);
+
+	mutex_lock(&ipvs->app_mutex);
 
-	return *pos ? ip_vs_app_idx(*pos - 1) : SEQ_START_TOKEN;
+	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 = {
@@ -571,9 +580,13 @@ static const struct file_operations ip_vs_app_fops = {
 
 static int __net_init __ip_vs_app_init(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
 
+	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;
 }
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index b38ae94..77b0036 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -414,14 +414,14 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
 
-	ret = register_ip_vs_app(app);
+	ret = register_ip_vs_app(net, app);
 	if (ret)
 		return ret;
 
 	for (i=0; i<IP_VS_APP_MAX_PORTS; i++) {
 		if (!ports[i])
 			continue;
-		ret = register_ip_vs_app_inc(app, app->protocol, ports[i]);
+		ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]);
 		if (ret)
 			break;
 		pr_info("%s: loaded support on port[%d] = %d\n",
@@ -429,7 +429,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
 	}
 
 	if (ret)
-		unregister_ip_vs_app(app);
+		unregister_ip_vs_app(net, app);
 
 	return ret;
 }
@@ -443,7 +443,7 @@ static void __ip_vs_ftp_exit(struct net *net)
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return;
 
-	unregister_ip_vs_app(app);
+	unregister_ip_vs_app(net, app);
 }
 
 static struct pernet_operations ip_vs_ftp_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 0f14f79..569e77b 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -1016,14 +1016,14 @@ static inline __u16 sctp_app_hashkey(__be16 port)
 		& SCTP_APP_TAB_MASK;
 }
 
-static int sctp_register_app(struct ip_vs_app *inc)
+static int sctp_register_app(struct net *net, struct ip_vs_app *inc)
 {
 	struct ip_vs_app *i;
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_SCTP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP);
 
 	hash = sctp_app_hashkey(port);
 
@@ -1042,10 +1042,10 @@ out:
 	return ret;
 }
 
-static void sctp_unregister_app(struct ip_vs_app *inc)
+static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_SCTP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP);
 
 	spin_lock_bh(&ipvs->sctp_app_lock);
 	atomic_dec(&pd->appcnt);
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 290b380..757aaaf 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -577,14 +577,14 @@ static inline __u16 tcp_app_hashkey(__be16 port)
 }
 
 
-static int tcp_register_app(struct ip_vs_app *inc)
+static int tcp_register_app(struct net *net, struct ip_vs_app *inc)
 {
 	struct ip_vs_app *i;
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_TCP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
 
 	hash = tcp_app_hashkey(port);
 
@@ -605,10 +605,10 @@ static int tcp_register_app(struct ip_vs_app *inc)
 
 
 static void
-tcp_unregister_app(struct ip_vs_app *inc)
+tcp_unregister_app(struct net *net, struct ip_vs_app *inc)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_TCP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
 
 	spin_lock_bh(&ipvs->tcp_app_lock);
 	atomic_dec(&pd->appcnt);
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 3719837..1dc3941 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -353,14 +353,14 @@ static inline __u16 udp_app_hashkey(__be16 port)
 }
 
 
-static int udp_register_app(struct ip_vs_app *inc)
+static int udp_register_app(struct net *net, struct ip_vs_app *inc)
 {
 	struct ip_vs_app *i;
 	__u16 hash;
 	__be16 port = inc->port;
 	int ret = 0;
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
 
 	hash = udp_app_hashkey(port);
 
@@ -382,10 +382,10 @@ static int udp_register_app(struct ip_vs_app *inc)
 
 
 static void
-udp_unregister_app(struct ip_vs_app *inc)
+udp_unregister_app(struct net *net, struct ip_vs_app *inc)
 {
-	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(&init_net, IPPROTO_UDP);
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	spin_lock_bh(&ipvs->udp_app_lock);
 	atomic_dec(&pd->appcnt);
-- 
1.7.2.3

[PATCH 46/79] IPVS: netns awareness to ip_vs_est

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

All variables moved to struct ipvs,
most external changes fixed (i.e. init_net removed)

*v3
 timer per ns instead of a common timer in estimator.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |    4 +-
 include/net/netns/ip_vs.h      |    4 ++
 net/netfilter/ipvs/ip_vs_ctl.c |   20 +++++-----
 net/netfilter/ipvs/ip_vs_est.c |   86 ++++++++++++++++++++++-----------------
 4 files changed, 64 insertions(+), 50 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 0cdd8ce..c08927b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1004,8 +1004,8 @@ extern void ip_vs_sync_cleanup(void);
  */
 extern int ip_vs_estimator_init(void);
 extern void ip_vs_estimator_cleanup(void);
-extern void ip_vs_new_estimator(struct ip_vs_stats *stats);
-extern void ip_vs_kill_estimator(struct ip_vs_stats *stats);
+extern void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats);
+extern void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats);
 extern void ip_vs_zero_estimator(struct ip_vs_stats *stats);
 
 /*
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 03f7fe1..db02401 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -70,6 +70,10 @@ struct netns_ipvs {
 	int			sysctl_lblcr_expiration;
 	struct ctl_table_header	*lblcr_ctl_header;
 	struct ctl_table	*lblcr_ctl_table;
+	/* ip_vs_est */
+	struct list_head	est_list;	/* estimator list */
+	spinlock_t		est_lock;
+	struct timer_list	est_timer;	/* Estimation timer */
 };
 
 #endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 88474f1..c89beb8 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -816,7 +816,7 @@ __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(&dest->stats);
+		ip_vs_new_estimator(svc->net, &dest->stats);
 
 	write_lock_bh(&__ip_vs_svc_lock);
 
@@ -1009,9 +1009,9 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 /*
  *	Delete a destination (must be already unlinked from the service)
  */
-static void __ip_vs_del_dest(struct ip_vs_dest *dest)
+static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
 {
-	ip_vs_kill_estimator(&dest->stats);
+	ip_vs_kill_estimator(net, &dest->stats);
 
 	/*
 	 *  Remove it from the d-linked list with the real services.
@@ -1080,6 +1080,7 @@ static int
 ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 {
 	struct ip_vs_dest *dest;
+	struct net *net = svc->net;
 	__be16 dport = udest->port;
 
 	EnterFunction(2);
@@ -1108,7 +1109,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 	/*
 	 *	Delete the destination
 	 */
-	__ip_vs_del_dest(dest);
+	__ip_vs_del_dest(net, dest);
 
 	LeaveFunction(2);
 
@@ -1197,7 +1198,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	else if (svc->port == 0)
 		atomic_inc(&ip_vs_nullsvc_counter);
 
-	ip_vs_new_estimator(&svc->stats);
+	ip_vs_new_estimator(net, &svc->stats);
 
 	/* Count only IPv4 services for old get/setsockopt interface */
 	if (svc->af == AF_INET)
@@ -1345,7 +1346,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 	if (svc->af == AF_INET)
 		ip_vs_num_services--;
 
-	ip_vs_kill_estimator(&svc->stats);
+	ip_vs_kill_estimator(svc->net, &svc->stats);
 
 	/* Unbind scheduler */
 	old_sched = svc->scheduler;
@@ -1368,7 +1369,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 	 */
 	list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) {
 		__ip_vs_unlink_dest(svc, dest, 0);
-		__ip_vs_del_dest(dest);
+		__ip_vs_del_dest(svc->net, dest);
 	}
 
 	/*
@@ -3460,7 +3461,7 @@ int __net_init __ip_vs_control_init(struct net *net)
 						  vs_vars);
 	if (sysctl_header == NULL)
 		goto err_reg;
-	ip_vs_new_estimator(&ip_vs_stats);
+	ip_vs_new_estimator(net, &ip_vs_stats);
 	return 0;
 
 err_reg:
@@ -3472,7 +3473,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return;
 
-	ip_vs_kill_estimator(&ip_vs_stats);
+	ip_vs_kill_estimator(net, &ip_vs_stats);
 	unregister_net_sysctl_table(sysctl_header);
 	proc_net_remove(net, "ip_vs_stats");
 	proc_net_remove(net, "ip_vs");
@@ -3536,7 +3537,6 @@ void ip_vs_control_cleanup(void)
 	ip_vs_trash_cleanup();
 	cancel_delayed_work_sync(&defense_work);
 	cancel_work_sync(&defense_work.work);
-	ip_vs_kill_estimator(&ip_vs_stats);
 	unregister_pernet_subsys(&ipvs_control_ops);
 	ip_vs_genl_unregister();
 	nf_unregister_sockopt(&ip_vs_sockopts);
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index 7417a0c..07d839b 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -8,8 +8,12 @@
  *              as published by the Free Software Foundation; either version
  *              2 of the License, or (at your option) any later version.
  *
- * Changes:
- *
+ * Changes:     Hans Schillstrom <hans.schillstrom@ericsson.com>
+ *              Network name space (netns) aware.
+ *              Global data moved to netns i.e struct netns_ipvs
+ *              Affected data: est_list and est_lock.
+ *              estimation_timer() runs with timer per netns.
+ *              get_stats()) do the per cpu summing.
  */
 
 #define KMSG_COMPONENT "IPVS"
@@ -48,12 +52,6 @@
  */
 
 
-static void estimation_timer(unsigned long arg);
-
-static LIST_HEAD(est_list);
-static DEFINE_SPINLOCK(est_lock);
-static DEFINE_TIMER(est_timer, estimation_timer, 0, 0);
-
 static void estimation_timer(unsigned long arg)
 {
 	struct ip_vs_estimator *e;
@@ -62,9 +60,12 @@ static void estimation_timer(unsigned long arg)
 	u32 n_inpkts, n_outpkts;
 	u64 n_inbytes, n_outbytes;
 	u32 rate;
+	struct net *net = (struct net *)arg;
+	struct netns_ipvs *ipvs;
 
-	spin_lock(&est_lock);
-	list_for_each_entry(e, &est_list, list) {
+	ipvs = net_ipvs(net);
+	spin_lock(&ipvs->est_lock);
+	list_for_each_entry(e, &ipvs->est_list, list) {
 		s = container_of(e, struct ip_vs_stats, est);
 
 		spin_lock(&s->lock);
@@ -75,38 +76,39 @@ static void estimation_timer(unsigned long arg)
 		n_outbytes = s->ustats.outbytes;
 
 		/* scaled by 2^10, but divided 2 seconds */
-		rate = (n_conns - e->last_conns)<<9;
+		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;
+		e->cps += ((long)rate - (long)e->cps) >> 2;
+		s->ustats.cps = (e->cps + 0x1FF) >> 10;
 
-		rate = (n_inpkts - e->last_inpkts)<<9;
+		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;
+		e->inpps += ((long)rate - (long)e->inpps) >> 2;
+		s->ustats.inpps = (e->inpps + 0x1FF) >> 10;
 
-		rate = (n_outpkts - e->last_outpkts)<<9;
+		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;
+		e->outpps += ((long)rate - (long)e->outpps) >> 2;
+		s->ustats.outpps = (e->outpps + 0x1FF) >> 10;
 
-		rate = (n_inbytes - e->last_inbytes)<<4;
+		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;
+		e->inbps += ((long)rate - (long)e->inbps) >> 2;
+		s->ustats.inbps = (e->inbps + 0xF) >> 5;
 
-		rate = (n_outbytes - e->last_outbytes)<<4;
+		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;
+		e->outbps += ((long)rate - (long)e->outbps) >> 2;
+		s->ustats.outbps = (e->outbps + 0xF) >> 5;
 		spin_unlock(&s->lock);
 	}
-	spin_unlock(&est_lock);
-	mod_timer(&est_timer, jiffies + 2*HZ);
+	spin_unlock(&ipvs->est_lock);
+	mod_timer(&ipvs->est_timer, jiffies + 2*HZ);
 }
 
-void ip_vs_new_estimator(struct ip_vs_stats *stats)
+void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_estimator *est = &stats->est;
 
 	INIT_LIST_HEAD(&est->list);
@@ -126,18 +128,19 @@ void ip_vs_new_estimator(struct ip_vs_stats *stats)
 	est->last_outbytes = stats->ustats.outbytes;
 	est->outbps = stats->ustats.outbps<<5;
 
-	spin_lock_bh(&est_lock);
-	list_add(&est->list, &est_list);
-	spin_unlock_bh(&est_lock);
+	spin_lock_bh(&ipvs->est_lock);
+	list_add(&est->list, &ipvs->est_list);
+	spin_unlock_bh(&ipvs->est_lock);
 }
 
-void ip_vs_kill_estimator(struct ip_vs_stats *stats)
+void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_estimator *est = &stats->est;
 
-	spin_lock_bh(&est_lock);
+	spin_lock_bh(&ipvs->est_lock);
 	list_del(&est->list);
-	spin_unlock_bh(&est_lock);
+	spin_unlock_bh(&ipvs->est_lock);
 }
 
 void ip_vs_zero_estimator(struct ip_vs_stats *stats)
@@ -159,14 +162,25 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats)
 
 static int __net_init __ip_vs_estimator_init(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
 
+	INIT_LIST_HEAD(&ipvs->est_list);
+	spin_lock_init(&ipvs->est_lock);
+	setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)net);
+	mod_timer(&ipvs->est_timer, jiffies + 2 * HZ);
 	return 0;
 }
 
+static void __net_exit __ip_vs_estimator_exit(struct net *net)
+{
+	del_timer_sync(&net_ipvs(net)->est_timer);
+}
 static struct pernet_operations ip_vs_app_ops = {
 	.init = __ip_vs_estimator_init,
+	.exit = __ip_vs_estimator_exit,
 };
 
 int __init ip_vs_estimator_init(void)
@@ -174,14 +188,10 @@ int __init ip_vs_estimator_init(void)
 	int rv;
 
 	rv = register_pernet_subsys(&ip_vs_app_ops);
-	if (rv < 0)
-		return rv;
-	mod_timer(&est_timer, jiffies + 2 * HZ);
 	return rv;
 }
 
 void ip_vs_estimator_cleanup(void)
 {
-	del_timer_sync(&est_timer);
 	unregister_pernet_subsys(&ip_vs_app_ops);
 }
-- 
1.7.2.3

[PATCH 47/79] IPVS: netns awareness to ip_vs_sync

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

All global variables moved to struct ipvs,
most external changes fixed (i.e. init_net removed)
in sync_buf create  + 4 replaced by sizeof(struct..)

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |   14 +-
 include/net/netns/ip_vs.h       |   16 ++
 net/netfilter/ipvs/ip_vs_core.c |   15 +-
 net/netfilter/ipvs/ip_vs_ctl.c  |   52 ++++---
 net/netfilter/ipvs/ip_vs_sync.c |  334 +++++++++++++++++++++------------------
 5 files changed, 240 insertions(+), 191 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index c08927b..4265b5e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -958,7 +958,7 @@ extern struct ip_vs_stats ip_vs_stats;
 extern const struct ctl_path net_vs_ctl_path[];
 extern int sysctl_ip_vs_sync_ver;
 
-extern void ip_vs_sync_switch_mode(int mode);
+extern void ip_vs_sync_switch_mode(struct net *net, int mode);
 extern struct ip_vs_service *
 ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport);
@@ -987,14 +987,10 @@ extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
  *      IPVS sync daemon data and function prototypes
  *      (from ip_vs_sync.c)
  */
-extern volatile int ip_vs_sync_state;
-extern volatile int ip_vs_master_syncid;
-extern volatile int ip_vs_backup_syncid;
-extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
-extern int stop_sync_thread(int state);
-extern void ip_vs_sync_conn(struct ip_vs_conn *cp);
+extern int start_sync_thread(struct net *net, int state, char *mcast_ifn,
+			     __u8 syncid);
+extern int stop_sync_thread(struct net *net, int state);
+extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp);
 extern int ip_vs_sync_init(void);
 extern void ip_vs_sync_cleanup(void);
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index db02401..aba78f3 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -74,6 +74,22 @@ struct netns_ipvs {
 	struct list_head	est_list;	/* estimator list */
 	spinlock_t		est_lock;
 	struct timer_list	est_timer;	/* Estimation timer */
+	/* ip_vs_sync */
+	struct list_head	sync_queue;
+	spinlock_t		sync_lock;
+	struct ip_vs_sync_buff  *sync_buff;
+	spinlock_t		sync_buff_lock;
+	struct sockaddr_in	sync_mcast_addr;
+	struct task_struct	*master_thread;
+	struct task_struct	*backup_thread;
+	int			send_mesg_maxlen;
+	int			recv_mesg_maxlen;
+	volatile int		sync_state;
+	volatile int		master_syncid;
+	volatile int		backup_syncid;
+	/* multicast interface name */
+	char			master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
+	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 };
 
 #endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 9317aff..5531d56 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1471,12 +1471,13 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
 static unsigned int
 ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 {
-	struct net *net = NULL;
+	struct net *net;
 	struct ip_vs_iphdr iph;
 	struct ip_vs_protocol *pp;
 	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
 	int ret, restart, pkts;
+	struct netns_ipvs *ipvs;
 
 	/* Already marked as IPVS request or reply? */
 	if (skb->ipvs_property)
@@ -1556,7 +1557,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	}
 
 	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet");
-
+	net = skb_net(skb);
+	ipvs = net_ipvs(net);
 	/* Check the server status */
 	if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
 		/* the destination server is not available */
@@ -1589,12 +1591,13 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	 *
 	 * For ONE_PKT let ip_vs_sync_conn() do the filter work.
 	 */
+
 	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
 		pkts = sysctl_ip_vs_sync_threshold[0];
 	else
 		pkts = atomic_add_return(1, &cp->in_pkts);
 
-	if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
+	if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    cp->protocol == IPPROTO_SCTP) {
 		if ((cp->state == IP_VS_SCTP_S_ESTABLISHED &&
 			(pkts % sysctl_ip_vs_sync_threshold[1]
@@ -1603,13 +1606,13 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 				 ((cp->state == IP_VS_SCTP_S_CLOSED) ||
 				  (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) ||
 				  (cp->state == IP_VS_SCTP_S_SHUT_ACK_SER)))) {
-			ip_vs_sync_conn(cp);
+			ip_vs_sync_conn(net, cp);
 			goto out;
 		}
 	}
 
 	/* Keep this block last: TCP and others with pp->num_states <= 1 */
-	else if ((ip_vs_sync_state & IP_VS_STATE_MASTER) &&
+	else if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
 	    (((cp->protocol != IPPROTO_TCP ||
 	       cp->state == IP_VS_TCP_S_ESTABLISHED) &&
 	      (pkts % sysctl_ip_vs_sync_threshold[1]
@@ -1619,7 +1622,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	       (cp->state == IP_VS_TCP_S_CLOSE) ||
 	       (cp->state == IP_VS_TCP_S_CLOSE_WAIT) ||
 	       (cp->state == IP_VS_TCP_S_TIME_WAIT)))))
-		ip_vs_sync_conn(cp);
+		ip_vs_sync_conn(net, cp);
 out:
 	cp->old_state = cp->state;
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c89beb8..03f8631 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1559,7 +1559,8 @@ proc_do_sync_mode(ctl_table *table, int write,
 			/* Restore the correct value */
 			*valp = val;
 		} else {
-			ip_vs_sync_switch_mode(val);
+			struct net *net = current->nsproxy->net_ns;
+			ip_vs_sync_switch_mode(net, val);
 		}
 	}
 	return rc;
@@ -2174,11 +2175,12 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 		goto out_unlock;
 	} else if (cmd == IP_VS_SO_SET_STARTDAEMON) {
 		struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
-		ret = start_sync_thread(dm->state, dm->mcast_ifn, dm->syncid);
+		ret = start_sync_thread(net, dm->state, dm->mcast_ifn,
+					dm->syncid);
 		goto out_unlock;
 	} else if (cmd == IP_VS_SO_SET_STOPDAEMON) {
 		struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
-		ret = stop_sync_thread(dm->state);
+		ret = stop_sync_thread(net, dm->state);
 		goto out_unlock;
 	}
 
@@ -2424,6 +2426,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	int ret = 0;
 	unsigned int copylen;
 	struct net *net = sock_net(sk);
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	BUG_ON(!net);
 	if (!capable(CAP_NET_ADMIN))
@@ -2546,15 +2549,17 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 		struct ip_vs_daemon_user d[2];
 
 		memset(&d, 0, sizeof(d));
-		if (ip_vs_sync_state & IP_VS_STATE_MASTER) {
+		if (ipvs->sync_state & IP_VS_STATE_MASTER) {
 			d[0].state = IP_VS_STATE_MASTER;
-			strlcpy(d[0].mcast_ifn, ip_vs_master_mcast_ifn, sizeof(d[0].mcast_ifn));
-			d[0].syncid = ip_vs_master_syncid;
+			strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn,
+				sizeof(d[0].mcast_ifn));
+			d[0].syncid = ipvs->master_syncid;
 		}
-		if (ip_vs_sync_state & IP_VS_STATE_BACKUP) {
+		if (ipvs->sync_state & IP_VS_STATE_BACKUP) {
 			d[1].state = IP_VS_STATE_BACKUP;
-			strlcpy(d[1].mcast_ifn, ip_vs_backup_mcast_ifn, sizeof(d[1].mcast_ifn));
-			d[1].syncid = ip_vs_backup_syncid;
+			strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn,
+				sizeof(d[1].mcast_ifn));
+			d[1].syncid = ipvs->backup_syncid;
 		}
 		if (copy_to_user(user, &d, sizeof(d)) != 0)
 			ret = -EFAULT;
@@ -3061,20 +3066,23 @@ nla_put_failure:
 static int ip_vs_genl_dump_daemons(struct sk_buff *skb,
 				   struct netlink_callback *cb)
 {
+	struct net *net = skb_net(skb);
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	mutex_lock(&__ip_vs_mutex);
-	if ((ip_vs_sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) {
+	if ((ipvs->sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) {
 		if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER,
-					   ip_vs_master_mcast_ifn,
-					   ip_vs_master_syncid, cb) < 0)
+					   ipvs->master_mcast_ifn,
+					   ipvs->master_syncid, cb) < 0)
 			goto nla_put_failure;
 
 		cb->args[0] = 1;
 	}
 
-	if ((ip_vs_sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) {
+	if ((ipvs->sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) {
 		if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_BACKUP,
-					   ip_vs_backup_mcast_ifn,
-					   ip_vs_backup_syncid, cb) < 0)
+					   ipvs->backup_mcast_ifn,
+					   ipvs->backup_syncid, cb) < 0)
 			goto nla_put_failure;
 
 		cb->args[1] = 1;
@@ -3086,24 +3094,26 @@ nla_put_failure:
 	return skb->len;
 }
 
-static int ip_vs_genl_new_daemon(struct nlattr **attrs)
+static int ip_vs_genl_new_daemon(struct net *net, struct nlattr **attrs)
 {
 	if (!(attrs[IPVS_DAEMON_ATTR_STATE] &&
 	      attrs[IPVS_DAEMON_ATTR_MCAST_IFN] &&
 	      attrs[IPVS_DAEMON_ATTR_SYNC_ID]))
 		return -EINVAL;
 
-	return start_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]),
+	return start_sync_thread(net,
+				 nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]),
 				 nla_data(attrs[IPVS_DAEMON_ATTR_MCAST_IFN]),
 				 nla_get_u32(attrs[IPVS_DAEMON_ATTR_SYNC_ID]));
 }
 
-static int ip_vs_genl_del_daemon(struct nlattr **attrs)
+static int ip_vs_genl_del_daemon(struct net *net, struct nlattr **attrs)
 {
 	if (!attrs[IPVS_DAEMON_ATTR_STATE])
 		return -EINVAL;
 
-	return stop_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
+	return stop_sync_thread(net,
+				nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
 }
 
 static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs)
@@ -3159,9 +3169,9 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 		}
 
 		if (cmd == IPVS_CMD_NEW_DAEMON)
-			ret = ip_vs_genl_new_daemon(daemon_attrs);
+			ret = ip_vs_genl_new_daemon(net, daemon_attrs);
 		else
-			ret = ip_vs_genl_del_daemon(daemon_attrs);
+			ret = ip_vs_genl_del_daemon(net, daemon_attrs);
 		goto out;
 	} else if (cmd == IPVS_CMD_ZERO &&
 		   !info->attrs[IPVS_CMD_ATTR_SERVICE]) {
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 6831e8f..c29e73d 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -192,6 +192,7 @@ union ip_vs_sync_conn {
 #define IPVS_OPT_F_PARAM	(1 << (IPVS_OPT_PARAM-1))
 
 struct ip_vs_sync_thread_data {
+	struct net *net;
 	struct socket *sock;
 	char *buf;
 };
@@ -259,10 +260,6 @@ struct ip_vs_sync_mesg {
 	/* ip_vs_sync_conn entries start here */
 };
 
-/* the maximum length of sync (sending/receiving) message */
-static int sync_send_mesg_maxlen;
-static int sync_recv_mesg_maxlen;
-
 struct ip_vs_sync_buff {
 	struct list_head        list;
 	unsigned long           firstuse;
@@ -273,28 +270,6 @@ struct ip_vs_sync_buff {
 	unsigned char           *end;
 };
 
-
-/* the sync_buff list head and the lock */
-static LIST_HEAD(ip_vs_sync_queue);
-static DEFINE_SPINLOCK(ip_vs_sync_lock);
-
-/* current sync_buff for accepting new conn entries */
-static struct ip_vs_sync_buff   *curr_sb = NULL;
-static DEFINE_SPINLOCK(curr_sb_lock);
-
-/* ipvs sync daemon state */
-volatile int ip_vs_sync_state = IP_VS_STATE_NONE;
-volatile int ip_vs_master_syncid = 0;
-volatile int ip_vs_backup_syncid = 0;
-
-/* multicast interface name */
-char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
-
-/* sync daemon tasks */
-static struct task_struct *sync_master_thread;
-static struct task_struct *sync_backup_thread;
-
 /* multicast addr */
 static struct sockaddr_in mcast_addr = {
 	.sin_family		= AF_INET,
@@ -324,20 +299,20 @@ static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no)
 	put_unaligned_be32(ho->previous_delta, &no->previous_delta);
 }
 
-static inline struct ip_vs_sync_buff *sb_dequeue(void)
+static inline struct ip_vs_sync_buff *sb_dequeue(struct netns_ipvs *ipvs)
 {
 	struct ip_vs_sync_buff *sb;
 
-	spin_lock_bh(&ip_vs_sync_lock);
-	if (list_empty(&ip_vs_sync_queue)) {
+	spin_lock_bh(&ipvs->sync_lock);
+	if (list_empty(&ipvs->sync_queue)) {
 		sb = NULL;
 	} else {
-		sb = list_entry(ip_vs_sync_queue.next,
+		sb = list_entry(ipvs->sync_queue.next,
 				struct ip_vs_sync_buff,
 				list);
 		list_del(&sb->list);
 	}
-	spin_unlock_bh(&ip_vs_sync_lock);
+	spin_unlock_bh(&ipvs->sync_lock);
 
 	return sb;
 }
@@ -345,25 +320,27 @@ static inline struct ip_vs_sync_buff *sb_dequeue(void)
 /*
  * Create a new sync buffer for Version 1 proto.
  */
-static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(void)
+static inline struct ip_vs_sync_buff *
+ip_vs_sync_buff_create(struct netns_ipvs *ipvs)
 {
 	struct ip_vs_sync_buff *sb;
 
 	if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC)))
 		return NULL;
 
-	if (!(sb->mesg=kmalloc(sync_send_mesg_maxlen, GFP_ATOMIC))) {
+	sb->mesg = kmalloc(ipvs->send_mesg_maxlen, GFP_ATOMIC);
+	if (!sb->mesg) {
 		kfree(sb);
 		return NULL;
 	}
 	sb->mesg->reserved = 0;  /* old nr_conns i.e. must be zeo now */
 	sb->mesg->version = SYNC_PROTO_VER;
-	sb->mesg->syncid = ip_vs_master_syncid;
+	sb->mesg->syncid = ipvs->master_syncid;
 	sb->mesg->size = sizeof(struct ip_vs_sync_mesg);
 	sb->mesg->nr_conns = 0;
 	sb->mesg->spare = 0;
 	sb->head = (unsigned char *)sb->mesg + sizeof(struct ip_vs_sync_mesg);
-	sb->end = (unsigned char *)sb->mesg + sync_send_mesg_maxlen;
+	sb->end = (unsigned char *)sb->mesg + ipvs->send_mesg_maxlen;
 
 	sb->firstuse = jiffies;
 	return sb;
@@ -375,14 +352,16 @@ static inline void ip_vs_sync_buff_release(struct ip_vs_sync_buff *sb)
 	kfree(sb);
 }
 
-static inline void sb_queue_tail(struct ip_vs_sync_buff *sb)
+static inline void sb_queue_tail(struct netns_ipvs *ipvs)
 {
-	spin_lock(&ip_vs_sync_lock);
-	if (ip_vs_sync_state & IP_VS_STATE_MASTER)
-		list_add_tail(&sb->list, &ip_vs_sync_queue);
+	struct ip_vs_sync_buff *sb = ipvs->sync_buff;
+
+	spin_lock(&ipvs->sync_lock);
+	if (ipvs->sync_state & IP_VS_STATE_MASTER)
+		list_add_tail(&sb->list, &ipvs->sync_queue);
 	else
 		ip_vs_sync_buff_release(sb);
-	spin_unlock(&ip_vs_sync_lock);
+	spin_unlock(&ipvs->sync_lock);
 }
 
 /*
@@ -390,18 +369,18 @@ static inline void sb_queue_tail(struct ip_vs_sync_buff *sb)
  *	than the specified time or the specified time is zero.
  */
 static inline struct ip_vs_sync_buff *
-get_curr_sync_buff(unsigned long time)
+get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time)
 {
 	struct ip_vs_sync_buff *sb;
 
-	spin_lock_bh(&curr_sb_lock);
-	if (curr_sb && (time == 0 ||
-			time_before(jiffies - curr_sb->firstuse, time))) {
-		sb = curr_sb;
-		curr_sb = NULL;
+	spin_lock_bh(&ipvs->sync_buff_lock);
+	if (ipvs->sync_buff && (time == 0 ||
+	    time_before(jiffies - ipvs->sync_buff->firstuse, time))) {
+		sb = ipvs->sync_buff;
+		ipvs->sync_buff = NULL;
 	} else
 		sb = NULL;
-	spin_unlock_bh(&curr_sb_lock);
+	spin_unlock_bh(&ipvs->sync_buff_lock);
 	return sb;
 }
 
@@ -409,33 +388,37 @@ get_curr_sync_buff(unsigned long time)
  * Switch mode from sending version 0 or 1
  *  - must handle sync_buf
  */
-void ip_vs_sync_switch_mode(int mode) {
+void ip_vs_sync_switch_mode(struct net *net, int mode)
+{
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	if (!ip_vs_sync_state & IP_VS_STATE_MASTER)
+	if (!ipvs->sync_state & IP_VS_STATE_MASTER)
 		return;
-	if (mode == sysctl_ip_vs_sync_ver || !curr_sb)
+	if (mode == sysctl_ip_vs_sync_ver || !ipvs->sync_buff)
 		return;
 
-	spin_lock_bh(&curr_sb_lock);
+	spin_lock_bh(&ipvs->sync_buff_lock);
 	/* Buffer empty ? then let buf_create do the job  */
-	if ( curr_sb->mesg->size <=  sizeof(struct ip_vs_sync_mesg)) {
-		kfree(curr_sb);
-		curr_sb = NULL;
+	if (ipvs->sync_buff->mesg->size <=  sizeof(struct ip_vs_sync_mesg)) {
+		kfree(ipvs->sync_buff);
+		ipvs->sync_buff = NULL;
 	} else {
-		spin_lock_bh(&ip_vs_sync_lock);
-		if (ip_vs_sync_state & IP_VS_STATE_MASTER)
-			list_add_tail(&curr_sb->list, &ip_vs_sync_queue);
+		spin_lock_bh(&ipvs->sync_lock);
+		if (ipvs->sync_state & IP_VS_STATE_MASTER)
+			list_add_tail(&ipvs->sync_buff->list,
+				      &ipvs->sync_queue);
 		else
-			ip_vs_sync_buff_release(curr_sb);
-		spin_unlock_bh(&ip_vs_sync_lock);
+			ip_vs_sync_buff_release(ipvs->sync_buff);
+		spin_unlock_bh(&ipvs->sync_lock);
 	}
-	spin_unlock_bh(&curr_sb_lock);
+	spin_unlock_bh(&ipvs->sync_buff_lock);
 }
 
 /*
  * Create a new sync buffer for Version 0 proto.
  */
-static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create_v0(void)
+static inline struct ip_vs_sync_buff *
+ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs)
 {
 	struct ip_vs_sync_buff *sb;
 	struct ip_vs_sync_mesg_v0 *mesg;
@@ -443,16 +426,17 @@ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create_v0(void)
 	if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC)))
 		return NULL;
 
-	if (!(sb->mesg=kmalloc(sync_send_mesg_maxlen, GFP_ATOMIC))) {
+	sb->mesg = kmalloc(ipvs->send_mesg_maxlen, GFP_ATOMIC);
+	if (!sb->mesg) {
 		kfree(sb);
 		return NULL;
 	}
 	mesg = (struct ip_vs_sync_mesg_v0 *)sb->mesg;
 	mesg->nr_conns = 0;
-	mesg->syncid = ip_vs_master_syncid;
-	mesg->size = 4;
-	sb->head = (unsigned char *)mesg + 4;
-	sb->end = (unsigned char *)mesg + sync_send_mesg_maxlen;
+	mesg->syncid = ipvs->master_syncid;
+	mesg->size = sizeof(struct ip_vs_sync_mesg_v0);
+	sb->head = (unsigned char *)mesg + sizeof(struct ip_vs_sync_mesg_v0);
+	sb->end = (unsigned char *)mesg + ipvs->send_mesg_maxlen;
 	sb->firstuse = jiffies;
 	return sb;
 }
@@ -461,8 +445,9 @@ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create_v0(void)
  *      Version 0 , could be switched in by sys_ctl.
  *      Add an ip_vs_conn information into the current sync_buff.
  */
-void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
+void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_sync_mesg_v0 *m;
 	struct ip_vs_sync_conn_v0 *s;
 	int len;
@@ -473,10 +458,12 @@ void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
 	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
 		return;
 
-	spin_lock(&curr_sb_lock);
-	if (!curr_sb) {
-		if (!(curr_sb=ip_vs_sync_buff_create_v0())) {
-			spin_unlock(&curr_sb_lock);
+	spin_lock(&ipvs->sync_buff_lock);
+	if (!ipvs->sync_buff) {
+		ipvs->sync_buff =
+			ip_vs_sync_buff_create_v0(ipvs);
+		if (!ipvs->sync_buff) {
+			spin_unlock(&ipvs->sync_buff_lock);
 			pr_err("ip_vs_sync_buff_create failed.\n");
 			return;
 		}
@@ -484,8 +471,8 @@ void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
 
 	len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE :
 		SIMPLE_CONN_SIZE;
-	m = (struct ip_vs_sync_mesg_v0 *)curr_sb->mesg;
-	s = (struct ip_vs_sync_conn_v0 *)curr_sb->head;
+	m = (struct ip_vs_sync_mesg_v0 *)ipvs->sync_buff->mesg;
+	s = (struct ip_vs_sync_conn_v0 *)ipvs->sync_buff->head;
 
 	/* copy members */
 	s->reserved = 0;
@@ -506,18 +493,18 @@ void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
 
 	m->nr_conns++;
 	m->size += len;
-	curr_sb->head += len;
+	ipvs->sync_buff->head += len;
 
 	/* check if there is a space for next one */
-	if (curr_sb->head + FULL_CONN_SIZE > curr_sb->end) {
-		sb_queue_tail(curr_sb);
-		curr_sb = NULL;
+	if (ipvs->sync_buff->head + FULL_CONN_SIZE > ipvs->sync_buff->end) {
+		sb_queue_tail(ipvs);
+		ipvs->sync_buff = NULL;
 	}
-	spin_unlock(&curr_sb_lock);
+	spin_unlock(&ipvs->sync_buff_lock);
 
 	/* synchronize its controller if it has */
 	if (cp->control)
-		ip_vs_sync_conn(cp->control);
+		ip_vs_sync_conn(net, cp->control);
 }
 
 /*
@@ -525,8 +512,9 @@ void ip_vs_sync_conn_v0(struct ip_vs_conn *cp)
  *      Called by ip_vs_in.
  *      Sending Version 1 messages
  */
-void ip_vs_sync_conn(struct ip_vs_conn *cp)
+void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_sync_mesg *m;
 	union ip_vs_sync_conn *s;
 	__u8 *p;
@@ -534,7 +522,7 @@ void ip_vs_sync_conn(struct ip_vs_conn *cp)
 
 	/* Handle old version of the protocol */
 	if (sysctl_ip_vs_sync_ver == 0) {
-		ip_vs_sync_conn_v0(cp);
+		ip_vs_sync_conn_v0(net, cp);
 		return;
 	}
 	/* Do not sync ONE PACKET */
@@ -551,7 +539,7 @@ sloop:
 		pe_name_len = strnlen(cp->pe->name, IP_VS_PENAME_MAXLEN);
 	}
 
-	spin_lock(&curr_sb_lock);
+	spin_lock(&ipvs->sync_buff_lock);
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (cp->af == AF_INET6)
@@ -570,26 +558,27 @@ sloop:
 
 	/* check if there is a space for this one  */
 	pad = 0;
-	if (curr_sb) {
-		pad = (4 - (size_t)curr_sb->head) & 3;
-		if (curr_sb->head + len + pad > curr_sb->end) {
-			sb_queue_tail(curr_sb);
-			curr_sb = NULL;
+	if (ipvs->sync_buff) {
+		pad = (4 - (size_t)ipvs->sync_buff->head) & 3;
+		if (ipvs->sync_buff->head + len + pad > ipvs->sync_buff->end) {
+			sb_queue_tail(ipvs);
+			ipvs->sync_buff = NULL;
 			pad = 0;
 		}
 	}
 
-	if (!curr_sb) {
-		if (!(curr_sb=ip_vs_sync_buff_create())) {
-			spin_unlock(&curr_sb_lock);
+	if (!ipvs->sync_buff) {
+		ipvs->sync_buff = ip_vs_sync_buff_create(ipvs);
+		if (!ipvs->sync_buff) {
+			spin_unlock(&ipvs->sync_buff_lock);
 			pr_err("ip_vs_sync_buff_create failed.\n");
 			return;
 		}
 	}
 
-	m = curr_sb->mesg;
-	p = curr_sb->head;
-	curr_sb->head += pad + len;
+	m = ipvs->sync_buff->mesg;
+	p = ipvs->sync_buff->head;
+	ipvs->sync_buff->head += pad + len;
 	m->size += pad + len;
 	/* Add ev. padding from prev. sync_conn */
 	while (pad--)
@@ -647,7 +636,7 @@ sloop:
 		}
 	}
 
-	spin_unlock(&curr_sb_lock);
+	spin_unlock(&ipvs->sync_buff_lock);
 
 control:
 	/* synchronize its controller if it has */
@@ -699,7 +688,8 @@ ip_vs_conn_fill_param_sync(int af, union ip_vs_sync_conn *sc,
 			buff[pe_name_len]=0;
 			p->pe = __ip_vs_pe_getbyname(buff);
 			if (!p->pe) {
-				IP_VS_DBG(3, "BACKUP, no %s engine found/loaded\n", buff);
+				IP_VS_DBG(3, "BACKUP, no %s engine found/loaded\n",
+					     buff);
 				return 1;
 			}
 		} else {
@@ -748,7 +738,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 		 * If it is not found the connection will remain unbound
 		 * but still handled.
 		 */
-		dest = ip_vs_find_dest(&init_net, type, daddr, dport, param->vaddr,
+		dest = ip_vs_find_dest(net, type, daddr, dport, param->vaddr,
 				       param->vport, protocol, fwmark);
 
 		/*  Set the approprite ativity flag */
@@ -1089,6 +1079,7 @@ out:
 static void ip_vs_process_message(struct net *net, __u8 *buffer,
 				  const size_t buflen)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer;
 	__u8 *p, *msg_end;
 	int i, nr_conns;
@@ -1105,7 +1096,7 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer,
 		return;
 	}
 	/* SyncID sanity check */
-	if (ip_vs_backup_syncid != 0 && m2->syncid != ip_vs_backup_syncid) {
+	if (ipvs->backup_syncid != 0 && m2->syncid != ipvs->backup_syncid) {
 		IP_VS_DBG(7, "BACKUP, Ignoring syncid = %d\n", m2->syncid);
 		return;
 	}
@@ -1190,8 +1181,10 @@ static int set_mcast_if(struct sock *sk, char *ifname)
 {
 	struct net_device *dev;
 	struct inet_sock *inet = inet_sk(sk);
+	struct net *net = sock_net(sk);
 
-	if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL)
+	dev = __dev_get_by_name(net, ifname);
+	if (!dev)
 		return -ENODEV;
 
 	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
@@ -1210,30 +1203,33 @@ static int set_mcast_if(struct sock *sk, char *ifname)
  *	Set the maximum length of sync message according to the
  *	specified interface's MTU.
  */
-static int set_sync_mesg_maxlen(int sync_state)
+static int set_sync_mesg_maxlen(struct net *net, int sync_state)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct net_device *dev;
 	int num;
 
 	if (sync_state == IP_VS_STATE_MASTER) {
-		if ((dev = __dev_get_by_name(&init_net, ip_vs_master_mcast_ifn)) == NULL)
+		dev = __dev_get_by_name(net, ipvs->master_mcast_ifn);
+		if (!dev)
 			return -ENODEV;
 
 		num = (dev->mtu - sizeof(struct iphdr) -
 		       sizeof(struct udphdr) -
 		       SYNC_MESG_HEADER_LEN - 20) / SIMPLE_CONN_SIZE;
-		sync_send_mesg_maxlen = SYNC_MESG_HEADER_LEN +
+		ipvs->send_mesg_maxlen = SYNC_MESG_HEADER_LEN +
 			SIMPLE_CONN_SIZE * min(num, MAX_CONNS_PER_SYNCBUFF);
 		IP_VS_DBG(7, "setting the maximum length of sync sending "
-			  "message %d.\n", sync_send_mesg_maxlen);
+			  "message %d.\n", ipvs->send_mesg_maxlen);
 	} else if (sync_state == IP_VS_STATE_BACKUP) {
-		if ((dev = __dev_get_by_name(&init_net, ip_vs_backup_mcast_ifn)) == NULL)
+		dev = __dev_get_by_name(net, ipvs->backup_mcast_ifn);
+		if (!dev)
 			return -ENODEV;
 
-		sync_recv_mesg_maxlen = dev->mtu -
+		ipvs->recv_mesg_maxlen = dev->mtu -
 			sizeof(struct iphdr) - sizeof(struct udphdr);
 		IP_VS_DBG(7, "setting the maximum length of sync receiving "
-			  "message %d.\n", sync_recv_mesg_maxlen);
+			  "message %d.\n", ipvs->recv_mesg_maxlen);
 	}
 
 	return 0;
@@ -1248,6 +1244,7 @@ static int set_sync_mesg_maxlen(int sync_state)
 static int
 join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
 {
+	struct net *net = sock_net(sk);
 	struct ip_mreqn mreq;
 	struct net_device *dev;
 	int ret;
@@ -1255,7 +1252,8 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
 	memset(&mreq, 0, sizeof(mreq));
 	memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));
 
-	if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL)
+	dev = __dev_get_by_name(net, ifname);
+	if (!dev)
 		return -ENODEV;
 	if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
 		return -EINVAL;
@@ -1272,11 +1270,13 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
 
 static int bind_mcastif_addr(struct socket *sock, char *ifname)
 {
+	struct net *net = sock_net(sock->sk);
 	struct net_device *dev;
 	__be32 addr;
 	struct sockaddr_in sin;
 
-	if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL)
+	dev = __dev_get_by_name(net, ifname);
+	if (!dev)
 		return -ENODEV;
 
 	addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
@@ -1298,8 +1298,9 @@ static int bind_mcastif_addr(struct socket *sock, char *ifname)
 /*
  *      Set up sending multicast socket over UDP
  */
-static struct socket * make_send_sock(void)
+static struct socket *make_send_sock(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct socket *sock;
 	int result;
 
@@ -1310,7 +1311,7 @@ static struct socket * make_send_sock(void)
 		return ERR_PTR(result);
 	}
 
-	result = set_mcast_if(sock->sk, ip_vs_master_mcast_ifn);
+	result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn);
 	if (result < 0) {
 		pr_err("Error setting outbound mcast interface\n");
 		goto error;
@@ -1319,7 +1320,7 @@ static struct socket * make_send_sock(void)
 	set_mcast_loop(sock->sk, 0);
 	set_mcast_ttl(sock->sk, 1);
 
-	result = bind_mcastif_addr(sock, ip_vs_master_mcast_ifn);
+	result = bind_mcastif_addr(sock, ipvs->master_mcast_ifn);
 	if (result < 0) {
 		pr_err("Error binding address of the mcast interface\n");
 		goto error;
@@ -1343,8 +1344,9 @@ static struct socket * make_send_sock(void)
 /*
  *      Set up receiving multicast socket over UDP
  */
-static struct socket * make_receive_sock(void)
+static struct socket *make_receive_sock(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct socket *sock;
 	int result;
 
@@ -1368,7 +1370,7 @@ static struct socket * make_receive_sock(void)
 	/* join the multicast group */
 	result = join_mcast_group(sock->sk,
 			(struct in_addr *) &mcast_addr.sin_addr,
-			ip_vs_backup_mcast_ifn);
+			ipvs->backup_mcast_ifn);
 	if (result < 0) {
 		pr_err("Error joining to the multicast group\n");
 		goto error;
@@ -1439,20 +1441,21 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
 static int sync_thread_master(void *data)
 {
 	struct ip_vs_sync_thread_data *tinfo = data;
+	struct netns_ipvs *ipvs = net_ipvs(tinfo->net);
 	struct ip_vs_sync_buff *sb;
 
 	pr_info("sync thread started: state = MASTER, mcast_ifn = %s, "
 		"syncid = %d\n",
-		ip_vs_master_mcast_ifn, ip_vs_master_syncid);
+		ipvs->master_mcast_ifn, ipvs->master_syncid);
 
 	while (!kthread_should_stop()) {
-		while ((sb = sb_dequeue())) {
+		while ((sb = sb_dequeue(ipvs))) {
 			ip_vs_send_sync_msg(tinfo->sock, sb->mesg);
 			ip_vs_sync_buff_release(sb);
 		}
 
-		/* check if entries stay in curr_sb for 2 seconds */
-		sb = get_curr_sync_buff(2 * HZ);
+		/* check if entries stay in ipvs->sync_buff for 2 seconds */
+		sb = get_curr_sync_buff(ipvs, 2 * HZ);
 		if (sb) {
 			ip_vs_send_sync_msg(tinfo->sock, sb->mesg);
 			ip_vs_sync_buff_release(sb);
@@ -1462,14 +1465,13 @@ static int sync_thread_master(void *data)
 	}
 
 	/* clean up the sync_buff queue */
-	while ((sb=sb_dequeue())) {
+	while ((sb = sb_dequeue(ipvs)))
 		ip_vs_sync_buff_release(sb);
-	}
 
 	/* clean up the current sync_buff */
-	if ((sb = get_curr_sync_buff(0))) {
+	sb = get_curr_sync_buff(ipvs, 0);
+	if (sb)
 		ip_vs_sync_buff_release(sb);
-	}
 
 	/* release the sending multicast socket */
 	sock_release(tinfo->sock);
@@ -1482,11 +1484,12 @@ static int sync_thread_master(void *data)
 static int sync_thread_backup(void *data)
 {
 	struct ip_vs_sync_thread_data *tinfo = data;
+	struct netns_ipvs *ipvs = net_ipvs(tinfo->net);
 	int len;
 
 	pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, "
 		"syncid = %d\n",
-		ip_vs_backup_mcast_ifn, ip_vs_backup_syncid);
+		ipvs->backup_mcast_ifn, ipvs->backup_syncid);
 
 	while (!kthread_should_stop()) {
 		wait_event_interruptible(*sk_sleep(tinfo->sock->sk),
@@ -1496,7 +1499,7 @@ static int sync_thread_backup(void *data)
 		/* do we have data now? */
 		while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) {
 			len = ip_vs_receive(tinfo->sock, tinfo->buf,
-					sync_recv_mesg_maxlen);
+					ipvs->recv_mesg_maxlen);
 			if (len <= 0) {
 				pr_err("receiving message error\n");
 				break;
@@ -1505,7 +1508,7 @@ static int sync_thread_backup(void *data)
 			/* disable bottom half, because it accesses the data
 			   shared by softirq while getting/creating conns */
 			local_bh_disable();
-			ip_vs_process_message(&init_net, tinfo->buf, len);
+			ip_vs_process_message(tinfo->net, tinfo->buf, len);
 			local_bh_enable();
 		}
 	}
@@ -1519,11 +1522,12 @@ static int sync_thread_backup(void *data)
 }
 
 
-int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
+int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid)
 {
 	struct ip_vs_sync_thread_data *tinfo;
 	struct task_struct **realtask, *task;
 	struct socket *sock;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 	char *name, *buf = NULL;
 	int (*threadfn)(void *data);
 	int result = -ENOMEM;
@@ -1533,27 +1537,27 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
 		  sizeof(struct ip_vs_sync_conn_v0));
 
 	if (state == IP_VS_STATE_MASTER) {
-		if (sync_master_thread)
+		if (ipvs->master_thread)
 			return -EEXIST;
 
-		strlcpy(ip_vs_master_mcast_ifn, mcast_ifn,
-			sizeof(ip_vs_master_mcast_ifn));
-		ip_vs_master_syncid = syncid;
-		realtask = &sync_master_thread;
-		name = "ipvs_syncmaster";
+		strlcpy(ipvs->master_mcast_ifn, mcast_ifn,
+			sizeof(ipvs->master_mcast_ifn));
+		ipvs->master_syncid = syncid;
+		realtask = &ipvs->master_thread;
+		name = "ipvs_master:%d";
 		threadfn = sync_thread_master;
-		sock = make_send_sock();
+		sock = make_send_sock(net);
 	} else if (state == IP_VS_STATE_BACKUP) {
-		if (sync_backup_thread)
+		if (ipvs->backup_thread)
 			return -EEXIST;
 
-		strlcpy(ip_vs_backup_mcast_ifn, mcast_ifn,
-			sizeof(ip_vs_backup_mcast_ifn));
-		ip_vs_backup_syncid = syncid;
-		realtask = &sync_backup_thread;
-		name = "ipvs_syncbackup";
+		strlcpy(ipvs->backup_mcast_ifn, mcast_ifn,
+			sizeof(ipvs->backup_mcast_ifn));
+		ipvs->backup_syncid = syncid;
+		realtask = &ipvs->backup_thread;
+		name = "ipvs_backup:%d";
 		threadfn = sync_thread_backup;
-		sock = make_receive_sock();
+		sock = make_receive_sock(net);
 	} else {
 		return -EINVAL;
 	}
@@ -1563,9 +1567,9 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
 		goto out;
 	}
 
-	set_sync_mesg_maxlen(state);
+	set_sync_mesg_maxlen(net, state);
 	if (state == IP_VS_STATE_BACKUP) {
-		buf = kmalloc(sync_recv_mesg_maxlen, GFP_KERNEL);
+		buf = kmalloc(ipvs->recv_mesg_maxlen, GFP_KERNEL);
 		if (!buf)
 			goto outsocket;
 	}
@@ -1574,10 +1578,11 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
 	if (!tinfo)
 		goto outbuf;
 
+	tinfo->net = net;
 	tinfo->sock = sock;
 	tinfo->buf = buf;
 
-	task = kthread_run(threadfn, tinfo, name);
+	task = kthread_run(threadfn, tinfo, name, ipvs->gen);
 	if (IS_ERR(task)) {
 		result = PTR_ERR(task);
 		goto outtinfo;
@@ -1585,7 +1590,7 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
 
 	/* mark as active */
 	*realtask = task;
-	ip_vs_sync_state |= state;
+	ipvs->sync_state |= state;
 
 	/* increase the module use count */
 	ip_vs_use_count_inc();
@@ -1603,16 +1608,18 @@ out:
 }
 
 
-int stop_sync_thread(int state)
+int stop_sync_thread(struct net *net, int state)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
 
 	if (state == IP_VS_STATE_MASTER) {
-		if (!sync_master_thread)
+		if (!ipvs->master_thread)
 			return -ESRCH;
 
 		pr_info("stopping master sync thread %d ...\n",
-			task_pid_nr(sync_master_thread));
+			task_pid_nr(ipvs->master_thread));
 
 		/*
 		 * The lock synchronizes with sb_queue_tail(), so that we don't
@@ -1620,21 +1627,21 @@ int stop_sync_thread(int state)
 		 * progress of stopping the master sync daemon.
 		 */
 
-		spin_lock_bh(&ip_vs_sync_lock);
-		ip_vs_sync_state &= ~IP_VS_STATE_MASTER;
-		spin_unlock_bh(&ip_vs_sync_lock);
-		kthread_stop(sync_master_thread);
-		sync_master_thread = NULL;
+		spin_lock_bh(&ipvs->sync_lock);
+		ipvs->sync_state &= ~IP_VS_STATE_MASTER;
+		spin_unlock_bh(&ipvs->sync_lock);
+		kthread_stop(ipvs->master_thread);
+		ipvs->master_thread = NULL;
 	} else if (state == IP_VS_STATE_BACKUP) {
-		if (!sync_backup_thread)
+		if (!ipvs->backup_thread)
 			return -ESRCH;
 
 		pr_info("stopping backup sync thread %d ...\n",
-			task_pid_nr(sync_backup_thread));
+			task_pid_nr(ipvs->backup_thread));
 
-		ip_vs_sync_state &= ~IP_VS_STATE_BACKUP;
-		kthread_stop(sync_backup_thread);
-		sync_backup_thread = NULL;
+		ipvs->sync_state &= ~IP_VS_STATE_BACKUP;
+		kthread_stop(ipvs->backup_thread);
+		ipvs->backup_thread = NULL;
 	} else {
 		return -EINVAL;
 	}
@@ -1650,12 +1657,29 @@ int stop_sync_thread(int state)
  */
 static int __net_init __ip_vs_sync_init(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return -EPERM;
+
+	INIT_LIST_HEAD(&ipvs->sync_queue);
+	spin_lock_init(&ipvs->sync_lock);
+	spin_lock_init(&ipvs->sync_buff_lock);
+
+	ipvs->sync_mcast_addr.sin_family = AF_INET;
+	ipvs->sync_mcast_addr.sin_port = cpu_to_be16(IP_VS_SYNC_PORT);
+	ipvs->sync_mcast_addr.sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP);
 	return 0;
 }
 
 static void __ip_vs_sync_cleanup(struct net *net)
 {
+	if (!net_eq(net, &init_net))	/* netns not enabled yet */
+		return;
+	stop_sync_thread(net, IP_VS_STATE_MASTER);
+	stop_sync_thread(net, IP_VS_STATE_BACKUP);
 }
+
 static struct pernet_operations ipvs_sync_ops = {
 	.init = __ip_vs_sync_init,
 	.exit = __ip_vs_sync_cleanup,
-- 
1.7.2.3

[PATCH 48/79] IPVS: netns, ip_vs_stats and its procfs

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

The statistic counter locks for every packet are now removed,
and that statistic is now per CPU, i.e. no locks needed.
However summing is made in ip_vs_est into ip_vs_stats struct
which is moved to ipvs struc.

procfs, ip_vs_stats now have a "per cpu" count and a grand total.
A new function seq_file_single_net() in ip_vs.h created for handling of
single_open_net() since it does not place net ptr in a struct, like others.

/var/lib/lxc # cat /proc/net/ip_vs_stats_percpu
       Total Incoming Outgoing         Incoming         Outgoing
CPU    Conns  Packets  Packets            Bytes            Bytes
  0        0        3        1               9D               34
  1        0        1        2               49               70
  2        0        1        2               34               76
  3        1        2        2               70               74
  ~        1        7        7              18A              18E

     Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s
           0        0        0                0                0

*v3
ip_vs_stats reamains as before, instead ip_vs_stats_percpu is added.
u64 seq lock added

*v4
Bug correction inbytes and outbytes as own vars..
per_cpu counter for all stats now as suggested by Julian.

[horms@verge.net.au: removed whitespace-change-only hunk]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |   51 ++++++++++++++-
 include/net/netns/ip_vs.h       |    4 +
 net/netfilter/ipvs/ip_vs_core.c |   89 +++++++++++++++-----------
 net/netfilter/ipvs/ip_vs_ctl.c  |  134 +++++++++++++++++++++++++++++++++------
 net/netfilter/ipvs/ip_vs_est.c  |   39 +++++++++++
 5 files changed, 256 insertions(+), 61 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4265b5e..605d5db 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -90,6 +90,18 @@ static inline struct net *skb_sknet(struct sk_buff *skb)
 	return &init_net;
 #endif
 }
+/*
+ * This one needed for single_open_net since net is stored directly in
+ * private not as a struct i.e. seq_file_net cant be used.
+ */
+static inline struct net *seq_file_single_net(struct seq_file *seq)
+{
+#ifdef CONFIG_NET_NS
+	return (struct net *)seq->private;
+#else
+	return &init_net;
+#endif
+}
 
 /* Connections' size value needed by ip_vs_ctl.c */
 extern int ip_vs_conn_tab_size;
@@ -320,6 +332,23 @@ struct ip_vs_seq {
 						   before last resized pkt */
 };
 
+/*
+ * counters per cpu
+ */
+struct ip_vs_counters {
+	__u32		conns;		/* connections scheduled */
+	__u32		inpkts;		/* incoming packets */
+	__u32		outpkts;	/* outgoing packets */
+	__u64		inbytes;	/* incoming bytes */
+	__u64		outbytes;	/* outgoing bytes */
+};
+/*
+ * Stats per cpu
+ */
+struct ip_vs_cpu_stats {
+	struct ip_vs_counters   ustats;
+	struct u64_stats_sync   syncp;
+};
 
 /*
  *	IPVS statistics objects
@@ -341,12 +370,28 @@ struct ip_vs_estimator {
 };
 
 struct ip_vs_stats {
-	struct ip_vs_stats_user	ustats;         /* statistics */
+	struct ip_vs_stats_user	ustats;		/* statistics */
 	struct ip_vs_estimator	est;		/* estimator */
-
-	spinlock_t              lock;           /* spin lock */
+	struct ip_vs_cpu_stats	*cpustats;	/* per cpu counters */
+	spinlock_t		lock;		/* spin lock */
 };
 
+/*
+ * Helper Macros for per cpu
+ * ipvs->tot_stats->ustats.count
+ */
+#define IPVS_STAT_INC(ipvs, count)	\
+	__this_cpu_inc((ipvs)->ustats->count)
+
+#define IPVS_STAT_ADD(ipvs, count, value) \
+	do {\
+		write_seqcount_begin(per_cpu_ptr((ipvs)->ustats_seq, \
+				     raw_smp_processor_id())); \
+		__this_cpu_add((ipvs)->ustats->count, value); \
+		write_seqcount_end(per_cpu_ptr((ipvs)->ustats_seq, \
+				   raw_smp_processor_id())); \
+	} while (0)
+
 struct dst_entry;
 struct iphdr;
 struct ip_vs_conn;
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index aba78f3..bd1dad8 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -61,6 +61,10 @@ struct netns_ipvs {
 	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
 	spinlock_t		sctp_app_lock;
 #endif
+	/* ip_vs_ctl */
+	struct ip_vs_stats		*tot_stats;  /* Statistics & est. */
+	struct ip_vs_cpu_stats __percpu *cpustats;   /* Stats per cpu */
+	seqcount_t			*ustats_seq; /* u64 read retry */
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 5531d56..7e6a2a0 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -115,21 +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);
 	}
 }
 
@@ -138,21 +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->syncp);
+		s->ustats.outbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(dest->svc->stats.cpustats);
+		s->ustats.outpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.outbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
+
+		s = this_cpu_ptr(ipvs->cpustats);
+		s->ustats.outpkts++;
+		u64_stats_update_begin(&s->syncp);
+		s->ustats.outbytes += skb->len;
+		u64_stats_update_end(&s->syncp);
 	}
 }
 
@@ -160,17 +174,17 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 static inline void
 ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 {
-	spin_lock(&cp->dest->stats.lock);
-	cp->dest->stats.ustats.conns++;
-	spin_unlock(&cp->dest->stats.lock);
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
+	struct ip_vs_cpu_stats *s;
 
-	spin_lock(&svc->stats.lock);
-	svc->stats.ustats.conns++;
-	spin_unlock(&svc->stats.lock);
+	s = this_cpu_ptr(cp->dest->stats.cpustats);
+	s->ustats.conns++;
 
-	spin_lock(&ip_vs_stats.lock);
-	ip_vs_stats.ustats.conns++;
-	spin_unlock(&ip_vs_stats.lock);
+	s = this_cpu_ptr(svc->stats.cpustats);
+	s->ustats.conns++;
+
+	s = this_cpu_ptr(ipvs->cpustats);
+	s->ustats.conns++;
 }
 
 
@@ -1841,7 +1855,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 	},
 #endif
 };
-
 /*
  *	Initialize IP Virtual Server netns mem.
  */
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 03f8631..cbd58c6 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -257,8 +257,7 @@ static DECLARE_DELAYED_WORK(defense_work, defense_work_handler);
 
 static void defense_work_handler(struct work_struct *work)
 {
-	struct net *net = &init_net;
-	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 
 	update_defense_level(ipvs);
 	if (atomic_read(&ip_vs_dropentry))
@@ -519,6 +518,7 @@ __ip_vs_unbind_svc(struct ip_vs_dest *dest)
 			      svc->fwmark,
 			      IP_VS_DBG_ADDR(svc->af, &svc->addr),
 			      ntohs(svc->port), atomic_read(&svc->usecnt));
+		free_percpu(svc->stats.cpustats);
 		kfree(svc);
 	}
 }
@@ -722,6 +722,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
 			list_del(&dest->n_list);
 			ip_vs_dst_reset(dest);
 			__ip_vs_unbind_svc(dest);
+			free_percpu(dest->stats.cpustats);
 			kfree(dest);
 		}
 	}
@@ -747,6 +748,7 @@ static void ip_vs_trash_cleanup(void)
 		list_del(&dest->n_list);
 		ip_vs_dst_reset(dest);
 		__ip_vs_unbind_svc(dest);
+		free_percpu(dest->stats.cpustats);
 		kfree(dest);
 	}
 }
@@ -868,6 +870,11 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 		pr_err("%s(): no memory.\n", __func__);
 		return -ENOMEM;
 	}
+	dest->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
+	if (!dest->stats.cpustats) {
+		pr_err("%s() alloc_percpu failed\n", __func__);
+		goto err_alloc;
+	}
 
 	dest->af = svc->af;
 	dest->protocol = svc->protocol;
@@ -891,6 +898,10 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 
 	LeaveFunction(2);
 	return 0;
+
+err_alloc:
+	kfree(dest);
+	return -ENOMEM;
 }
 
 
@@ -1037,6 +1048,7 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
 		   and only one user context can update virtual service at a
 		   time, so the operation here is OK */
 		atomic_dec(&dest->svc->refcnt);
+		free_percpu(dest->stats.cpustats);
 		kfree(dest);
 	} else {
 		IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, "
@@ -1163,6 +1175,11 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 		ret = -ENOMEM;
 		goto out_err;
 	}
+	svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
+	if (!svc->stats.cpustats) {
+		pr_err("%s() alloc_percpu failed\n", __func__);
+		goto out_err;
+	}
 
 	/* I'm the first user of the service */
 	atomic_set(&svc->usecnt, 0);
@@ -1212,6 +1229,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	*svc_p = svc;
 	return 0;
 
+
  out_err:
 	if (svc != NULL) {
 		ip_vs_unbind_scheduler(svc);
@@ -1220,6 +1238,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 			ip_vs_app_inc_put(svc->inc);
 			local_bh_enable();
 		}
+		if (svc->stats.cpustats)
+			free_percpu(svc->stats.cpustats);
 		kfree(svc);
 	}
 	ip_vs_scheduler_put(sched);
@@ -1388,6 +1408,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 			      svc->fwmark,
 			      IP_VS_DBG_ADDR(svc->af, &svc->addr),
 			      ntohs(svc->port), atomic_read(&svc->usecnt));
+		free_percpu(svc->stats.cpustats);
 		kfree(svc);
 	}
 
@@ -1499,7 +1520,7 @@ static int ip_vs_zero_all(struct net *net)
 		}
 	}
 
-	ip_vs_zero_stats(&ip_vs_stats);
+	ip_vs_zero_stats(net_ipvs(net)->tot_stats);
 	return 0;
 }
 
@@ -1989,13 +2010,11 @@ static const struct file_operations ip_vs_info_fops = {
 
 #endif
 
-struct ip_vs_stats ip_vs_stats = {
-	.lock = __SPIN_LOCK_UNLOCKED(ip_vs_stats.lock),
-};
-
 #ifdef CONFIG_PROC_FS
 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;
 
 /*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
 	seq_puts(seq,
@@ -2003,22 +2022,22 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v)
 	seq_printf(seq,
 		   "   Conns  Packets  Packets            Bytes            Bytes\n");
 
-	spin_lock_bh(&ip_vs_stats.lock);
-	seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", ip_vs_stats.ustats.conns,
-		   ip_vs_stats.ustats.inpkts, ip_vs_stats.ustats.outpkts,
-		   (unsigned long long) ip_vs_stats.ustats.inbytes,
-		   (unsigned long long) ip_vs_stats.ustats.outbytes);
+	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);
 
 /*                 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",
-			ip_vs_stats.ustats.cps,
-			ip_vs_stats.ustats.inpps,
-			ip_vs_stats.ustats.outpps,
-			ip_vs_stats.ustats.inbps,
-			ip_vs_stats.ustats.outbps);
-	spin_unlock_bh(&ip_vs_stats.lock);
+			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);
 
 	return 0;
 }
@@ -2036,6 +2055,59 @@ static const struct file_operations ip_vs_stats_fops = {
 	.release = single_release,
 };
 
+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;
+	int i;
+
+/*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
+	seq_puts(seq,
+		 "       Total Incoming Outgoing         Incoming         Outgoing\n");
+	seq_printf(seq,
+		   "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);
+		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);
+	}
+
+	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);
+
+/*                 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);
+
+	return 0;
+}
+
+static int ip_vs_stats_percpu_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open_net(inode, file, ip_vs_stats_percpu_show);
+}
+
+static const struct file_operations ip_vs_stats_percpu_fops = {
+	.owner = THIS_MODULE,
+	.open = ip_vs_stats_percpu_seq_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
 #endif
 
 /*
@@ -3461,32 +3533,54 @@ int __net_init __ip_vs_control_init(struct net *net)
 
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
+	/* 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) {
+		pr_err("%s() alloc_percpu failed\n", __func__);
+		goto err_alloc;
+	}
+	spin_lock_init(&ipvs->tot_stats->lock);
 
 	for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
 		INIT_LIST_HEAD(&ipvs->rs_table[idx]);
 
 	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);
 	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
 						  vs_vars);
 	if (sysctl_header == NULL)
 		goto err_reg;
-	ip_vs_new_estimator(net, &ip_vs_stats);
+	ip_vs_new_estimator(net, ipvs->tot_stats);
 	return 0;
 
 err_reg:
+	free_percpu(ipvs->cpustats);
+err_alloc:
+	kfree(ipvs->tot_stats);
 	return -ENOMEM;
 }
 
 static void __net_exit __ip_vs_control_cleanup(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return;
 
-	ip_vs_kill_estimator(net, &ip_vs_stats);
+	ip_vs_kill_estimator(net, ipvs->tot_stats);
 	unregister_net_sysctl_table(sysctl_header);
+	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);
 }
 
 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 07d839b..d13616b 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -52,6 +52,43 @@
  */
 
 
+/*
+ * Make a summary from each cpu
+ */
+static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum,
+				 struct ip_vs_cpu_stats *stats)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i);
+		unsigned int start;
+		__u64 inbytes, outbytes;
+		if (i) {
+			sum->conns += s->ustats.conns;
+			sum->inpkts += s->ustats.inpkts;
+			sum->outpkts += s->ustats.outpkts;
+			do {
+				start = u64_stats_fetch_begin_bh(&s->syncp);
+				inbytes = s->ustats.inbytes;
+				outbytes = s->ustats.outbytes;
+			} while (u64_stats_fetch_retry_bh(&s->syncp, start));
+			sum->inbytes += inbytes;
+			sum->outbytes += outbytes;
+		} else {
+			sum->conns = s->ustats.conns;
+			sum->inpkts = s->ustats.inpkts;
+			sum->outpkts = s->ustats.outpkts;
+			do {
+				start = u64_stats_fetch_begin_bh(&s->syncp);
+				sum->inbytes = s->ustats.inbytes;
+				sum->outbytes = s->ustats.outbytes;
+			} while (u64_stats_fetch_retry_bh(&s->syncp, start));
+		}
+	}
+}
+
+
 static void estimation_timer(unsigned long arg)
 {
 	struct ip_vs_estimator *e;
@@ -64,10 +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);
 		n_conns = s->ustats.conns;
 		n_inpkts = s->ustats.inpkts;
-- 
1.7.2.3

[PATCH 49/79] IPVS: netns, connection hash got net as param.

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

Connection hash table is now name space aware.
i.e. net ptr >> 8 is xor:ed to the hash,
and this is the first param to be compared.
The net struct is 0xa40 in size ( a little bit smaller for 32 bit arch:s)
and cache-line aligned, so a ptr >> 5 might be a more clever solution ?

All lookups where net is compared uses net_eq() which returns 1 when netns
is disabled, and the compiler seems to do something clever in that case.

ip_vs_conn_fill_param() have *net as first param now.

Three new inlines added to keep conn struct smaller
when names space is disabled.
- ip_vs_conn_net()
- ip_vs_conn_net_set()
- ip_vs_conn_net_eq()

*v3
  moved net compare to the end in "fast path"

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                     |   53 ++++++++++++---
 include/net/netns/ip_vs.h               |    2 +
 net/netfilter/ipvs/ip_vs_conn.c         |  112 +++++++++++++++++++------------
 net/netfilter/ipvs/ip_vs_core.c         |   15 +++--
 net/netfilter/ipvs/ip_vs_ftp.c          |   14 ++--
 net/netfilter/ipvs/ip_vs_nfct.c         |    6 +-
 net/netfilter/ipvs/ip_vs_proto_ah_esp.c |   15 +++--
 net/netfilter/ipvs/ip_vs_proto_sctp.c   |    2 +-
 net/netfilter/ipvs/ip_vs_proto_tcp.c    |    2 +-
 net/netfilter/ipvs/ip_vs_proto_udp.c    |    2 +-
 net/netfilter/ipvs/ip_vs_sync.c         |   13 ++--
 11 files changed, 153 insertions(+), 83 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 605d5db..f82c0ff 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -477,6 +477,7 @@ extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net,
 						     unsigned short proto);
 
 struct ip_vs_conn_param {
+	struct net			*net;
 	const union nf_inet_addr	*caddr;
 	const union nf_inet_addr	*vaddr;
 	__be16				cport;
@@ -494,17 +495,19 @@ struct ip_vs_conn_param {
  */
 struct ip_vs_conn {
 	struct list_head        c_list;         /* hashed list heads */
-
+#ifdef CONFIG_NET_NS
+	struct net              *net;           /* Name space */
+#endif
 	/* Protocol, addresses and port numbers */
-	u16                      af;		/* address family */
-	union nf_inet_addr       caddr;          /* client address */
-	union nf_inet_addr       vaddr;          /* virtual address */
-	union nf_inet_addr       daddr;          /* destination address */
-	volatile __u32           flags;          /* status flags */
-	__u32                    fwmark;         /* Fire wall mark from skb */
-	__be16                   cport;
-	__be16                   vport;
-	__be16                   dport;
+	u16                     af;             /* address family */
+	__be16                  cport;
+	__be16                  vport;
+	__be16                  dport;
+	__u32                   fwmark;         /* Fire wall mark from skb */
+	union nf_inet_addr      caddr;          /* client address */
+	union nf_inet_addr      vaddr;          /* virtual address */
+	union nf_inet_addr      daddr;          /* destination address */
+	volatile __u32          flags;          /* status flags */
 	__u16                   protocol;       /* Which protocol (TCP/UDP) */
 
 	/* counter and timer */
@@ -547,6 +550,33 @@ struct ip_vs_conn {
 	__u8			pe_data_len;
 };
 
+/*
+ *  To save some memory in conn table when name space is disabled.
+ */
+static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp)
+{
+#ifdef CONFIG_NET_NS
+	return cp->net;
+#else
+	return &init_net;
+#endif
+}
+static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net)
+{
+#ifdef CONFIG_NET_NS
+	cp->net = net;
+#endif
+}
+
+static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp,
+				    struct net *net)
+{
+#ifdef CONFIG_NET_NS
+	return cp->net == net;
+#else
+	return 1;
+#endif
+}
 
 /*
  *	Extended internal versions of struct ip_vs_service_user and
@@ -796,13 +826,14 @@ enum {
 	IP_VS_DIR_LAST,
 };
 
-static inline void ip_vs_conn_fill_param(int af, int protocol,
+static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol,
 					 const union nf_inet_addr *caddr,
 					 __be16 cport,
 					 const union nf_inet_addr *vaddr,
 					 __be16 vport,
 					 struct ip_vs_conn_param *p)
 {
+	p->net = net;
 	p->af = af;
 	p->protocol = protocol;
 	p->caddr = caddr;
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index bd1dad8..1acfb33 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -66,6 +66,8 @@ struct netns_ipvs {
 	struct ip_vs_cpu_stats __percpu *cpustats;   /* Stats per cpu */
 	seqcount_t			*ustats_seq; /* u64 read retry */
 
+	/* ip_vs_conn */
+	atomic_t		conn_count;         /*  connection counter */
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
 	struct ctl_table_header	*lblc_ctl_header;
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index b2024c9..0d5e4fe 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);
@@ -313,17 +311,18 @@ 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;
 }
 
@@ -352,6 +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;
@@ -403,10 +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;
@@ -609,8 +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(&init_net, 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;
@@ -728,6 +730,7 @@ 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;
 
@@ -770,7 +773,7 @@ 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;
@@ -804,7 +807,9 @@ 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_proto_data *pd = ip_vs_proto_data_get(&init_net, 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) {
@@ -814,6 +819,7 @@ 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);
@@ -844,7 +850,7 @@ 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);
 
@@ -886,17 +892,22 @@ 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;
 			}
 		}
@@ -908,14 +919,17 @@ 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;
@@ -932,18 +946,19 @@ 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);
@@ -957,9 +972,12 @@ 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);
@@ -1004,7 +1022,8 @@ 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 = {
@@ -1031,6 +1050,10 @@ 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)
@@ -1067,7 +1090,8 @@ 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 = {
@@ -1168,10 +1192,11 @@ 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:
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
@@ -1181,7 +1206,8 @@ 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) {
@@ -1194,7 +1220,7 @@ 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;
 	}
@@ -1204,8 +1230,11 @@ static void ip_vs_conn_flush(void)
  */
 int __net_init __ip_vs_conn_init(struct net *net)
 {
+	struct netns_ipvs *ipvs = net_ipvs(net);
+
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
+	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);
@@ -1217,6 +1246,8 @@ static void __net_exit __ip_vs_conn_cleanup(struct net *net)
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return;
 
+	/* 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");
 }
@@ -1277,9 +1308,6 @@ int __init ip_vs_conn_init(void)
 void ip_vs_conn_cleanup(void)
 {
 	unregister_pernet_subsys(&ipvs_conn_ops);
-	/* flush all the connection entries first */
-	ip_vs_conn_flush();
-
 	/* Release the empty cache */
 	kmem_cache_destroy(ip_vs_conn_cachep);
 	vfree(ip_vs_conn_tab);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 7e6a2a0..7205b49 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -205,7 +205,8 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
 			      const union nf_inet_addr *vaddr, __be16 vport,
 			      struct ip_vs_conn_param *p)
 {
-	ip_vs_conn_fill_param(svc->af, protocol, caddr, cport, vaddr, vport, p);
+	ip_vs_conn_fill_param(svc->net, svc->af, protocol, caddr, cport, vaddr,
+			      vport, p);
 	p->pe = svc->pe;
 	if (p->pe && p->pe->fill_param)
 		return p->pe->fill_param(p, skb);
@@ -348,8 +349,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	/*
 	 *    Create a new connection according to the template
 	 */
-	ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, src_port,
-			      &iph.daddr, dst_port, &param);
+	ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr,
+			      src_port, &iph.daddr, dst_port, &param);
 
 	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
 	if (cp == NULL) {
@@ -464,8 +465,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	 */
 	{
 		struct ip_vs_conn_param p;
-		ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr,
-				      pptr[0], &iph.daddr, pptr[1], &p);
+
+		ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
+				      &iph.saddr, pptr[0], &iph.daddr, pptr[1],
+				      &p);
 		cp = ip_vs_conn_new(&p, &dest->addr,
 				    dest->port ? dest->port : pptr[1],
 				    flags, dest, skb->mark);
@@ -532,7 +535,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
 		{
 			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(svc->af, iph.protocol,
+			ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol,
 					      &iph.saddr, pptr[0],
 					      &iph.daddr, pptr[1], &p);
 			cp = ip_vs_conn_new(&p, &daddr, 0,
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 77b0036..6a04f9a 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -198,13 +198,15 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		 */
 		{
 			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(AF_INET, iph->protocol,
-					      &from, port, &cp->caddr, 0, &p);
+			ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET,
+					      iph->protocol, &from, port,
+					      &cp->caddr, 0, &p);
 			n_cp = ip_vs_conn_out_get(&p);
 		}
 		if (!n_cp) {
 			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(AF_INET, IPPROTO_TCP, &cp->caddr,
+			ip_vs_conn_fill_param(ip_vs_conn_net(cp),
+					      AF_INET, IPPROTO_TCP, &cp->caddr,
 					      0, &cp->vaddr, port, &p);
 			n_cp = ip_vs_conn_new(&p, &from, port,
 					      IP_VS_CONN_F_NO_CPORT |
@@ -361,9 +363,9 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 
 	{
 		struct ip_vs_conn_param p;
-		ip_vs_conn_fill_param(AF_INET, iph->protocol, &to, port,
-				      &cp->vaddr, htons(ntohs(cp->vport)-1),
-				      &p);
+		ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET,
+				      iph->protocol, &to, port, &cp->vaddr,
+				      htons(ntohs(cp->vport)-1), &p);
 		n_cp = ip_vs_conn_in_get(&p);
 		if (!n_cp) {
 			n_cp = ip_vs_conn_new(&p, &cp->daddr,
diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index 4680647..f454c80 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -141,6 +141,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct,
 	struct nf_conntrack_tuple *orig, new_reply;
 	struct ip_vs_conn *cp;
 	struct ip_vs_conn_param p;
+	struct net *net = nf_ct_net(ct);
 
 	if (exp->tuple.src.l3num != PF_INET)
 		return;
@@ -155,7 +156,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct,
 
 	/* RS->CLIENT */
 	orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
-	ip_vs_conn_fill_param(exp->tuple.src.l3num, orig->dst.protonum,
+	ip_vs_conn_fill_param(net, exp->tuple.src.l3num, orig->dst.protonum,
 			      &orig->src.u3, orig->src.u.tcp.port,
 			      &orig->dst.u3, orig->dst.u.tcp.port, &p);
 	cp = ip_vs_conn_out_get(&p);
@@ -268,7 +269,8 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 		" for conn " FMT_CONN "\n",
 		__func__, ARG_TUPLE(&tuple), ARG_CONN(cp));
 
-	h = nf_conntrack_find_get(&init_net, NF_CT_DEFAULT_ZONE, &tuple);
+	h = nf_conntrack_find_get(ip_vs_conn_net(cp), NF_CT_DEFAULT_ZONE,
+				  &tuple);
 	if (h) {
 		ct = nf_ct_tuplehash_to_ctrack(h);
 		/* Show what happens instead of calling nf_ct_kill() */
diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
index 28039cb..5b8eb8b 100644
--- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c
@@ -41,15 +41,16 @@ struct isakmp_hdr {
 #define PORT_ISAKMP	500
 
 static void
-ah_esp_conn_fill_param_proto(int af, const struct ip_vs_iphdr *iph,
-			     int inverse, struct ip_vs_conn_param *p)
+ah_esp_conn_fill_param_proto(struct net *net, int af,
+			     const struct ip_vs_iphdr *iph, int inverse,
+			     struct ip_vs_conn_param *p)
 {
 	if (likely(!inverse))
-		ip_vs_conn_fill_param(af, IPPROTO_UDP,
+		ip_vs_conn_fill_param(net, af, IPPROTO_UDP,
 				      &iph->saddr, htons(PORT_ISAKMP),
 				      &iph->daddr, htons(PORT_ISAKMP), p);
 	else
-		ip_vs_conn_fill_param(af, IPPROTO_UDP,
+		ip_vs_conn_fill_param(net, af, IPPROTO_UDP,
 				      &iph->daddr, htons(PORT_ISAKMP),
 				      &iph->saddr, htons(PORT_ISAKMP), p);
 }
@@ -61,8 +62,9 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb,
 {
 	struct ip_vs_conn *cp;
 	struct ip_vs_conn_param p;
+	struct net *net = skb_net(skb);
 
-	ah_esp_conn_fill_param_proto(af, iph, inverse, &p);
+	ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p);
 	cp = ip_vs_conn_in_get(&p);
 	if (!cp) {
 		/*
@@ -89,8 +91,9 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb,
 {
 	struct ip_vs_conn *cp;
 	struct ip_vs_conn_param p;
+	struct net *net = skb_net(skb);
 
-	ah_esp_conn_fill_param_proto(af, iph, inverse, &p);
+	ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p);
 	cp = ip_vs_conn_out_get(&p);
 	if (!cp) {
 		IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet "
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 569e77b..550365a 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -1055,7 +1055,7 @@ static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc)
 
 static int sctp_app_conn_bind(struct ip_vs_conn *cp)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 757aaaf..d8b3f9f 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -620,7 +620,7 @@ tcp_unregister_app(struct net *net, struct ip_vs_app *inc)
 static int
 tcp_app_conn_bind(struct ip_vs_conn *cp)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 1dc3941..581157b 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -396,7 +396,7 @@ udp_unregister_app(struct net *net, struct ip_vs_app *inc)
 
 static int udp_app_conn_bind(struct ip_vs_conn *cp)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp));
 	int hash;
 	struct ip_vs_app *inc;
 	int result = 0;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index c29e73d..f85e47d 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -660,21 +660,21 @@ control:
  *  fill_param used by version 1
  */
 static inline int
-ip_vs_conn_fill_param_sync(int af, union ip_vs_sync_conn *sc,
+ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc,
 			   struct ip_vs_conn_param *p,
 			   __u8 *pe_data, unsigned int pe_data_len,
 			   __u8 *pe_name, unsigned int pe_name_len)
 {
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
-		ip_vs_conn_fill_param(af, sc->v6.protocol,
+		ip_vs_conn_fill_param(net, af, sc->v6.protocol,
 				      (const union nf_inet_addr *)&sc->v6.caddr,
 				      sc->v6.cport,
 				      (const union nf_inet_addr *)&sc->v6.vaddr,
 				      sc->v6.vport, p);
 	else
 #endif
-		ip_vs_conn_fill_param(af, sc->v4.protocol,
+		ip_vs_conn_fill_param(net, af, sc->v4.protocol,
 				      (const union nf_inet_addr *)&sc->v4.caddr,
 				      sc->v4.cport,
 				      (const union nf_inet_addr *)&sc->v4.vaddr,
@@ -881,7 +881,7 @@ static void ip_vs_process_message_v0(struct net *net, const char *buffer,
 			}
 		}
 
-		ip_vs_conn_fill_param(AF_INET, s->protocol,
+		ip_vs_conn_fill_param(net, AF_INET, s->protocol,
 				      (const union nf_inet_addr *)&s->caddr,
 				      s->cport,
 				      (const union nf_inet_addr *)&s->vaddr,
@@ -1043,9 +1043,8 @@ static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end)
 			state = 0;
 		}
 	}
-	if (ip_vs_conn_fill_param_sync(af, s, &param,
-					pe_data, pe_data_len,
-					pe_name, pe_name_len)) {
+	if (ip_vs_conn_fill_param_sync(net, af, s, &param, pe_data,
+				       pe_data_len, pe_name, pe_name_len)) {
 		retc = 50;
 		goto out;
 	}
-- 
1.7.2.3

[PATCH 50/79] IPVS: netns, ip_vs_ctl local vars moved to ipvs struct.

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

Moving global vars to ipvs struct, except for svc table lock.
Next patch for ctl will be drop-rate handling.

*v3
__ip_vs_mutex remains global
 ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h                   |   27 ++--
 include/net/netns/ip_vs.h             |   37 ++++-
 net/netfilter/ipvs/ip_vs_conn.c       |    7 +-
 net/netfilter/ipvs/ip_vs_core.c       |   34 +++--
 net/netfilter/ipvs/ip_vs_ctl.c        |  291 +++++++++++++++++----------------
 net/netfilter/ipvs/ip_vs_proto_sctp.c |    2 +-
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |    2 +-
 net/netfilter/ipvs/ip_vs_proto_udp.c  |    2 +-
 net/netfilter/ipvs/ip_vs_sync.c       |    9 +-
 9 files changed, 230 insertions(+), 181 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index f82c0ff..af9acf4 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -41,7 +41,7 @@ static inline struct netns_ipvs *net_ipvs(struct net* net)
  * Get net ptr from skb in traffic cases
  * use skb_sknet when call is from userland (ioctl or netlink)
  */
-static inline struct net *skb_net(struct sk_buff *skb)
+static inline struct net *skb_net(const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_NS
 #ifdef CONFIG_IP_VS_DEBUG
@@ -69,7 +69,7 @@ static inline struct net *skb_net(struct sk_buff *skb)
 #endif
 }
 
-static inline struct net *skb_sknet(struct sk_buff *skb)
+static inline struct net *skb_sknet(const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_NS
 #ifdef CONFIG_IP_VS_DEBUG
@@ -1023,13 +1023,6 @@ extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 /*
  *      IPVS control data and functions (from ip_vs_ctl.c)
  */
-extern int sysctl_ip_vs_cache_bypass;
-extern int sysctl_ip_vs_expire_nodest_conn;
-extern int sysctl_ip_vs_expire_quiescent_template;
-extern int sysctl_ip_vs_sync_threshold[2];
-extern int sysctl_ip_vs_nat_icmp_send;
-extern int sysctl_ip_vs_conntrack;
-extern int sysctl_ip_vs_snat_reroute;
 extern struct ip_vs_stats ip_vs_stats;
 extern const struct ctl_path net_vs_ctl_path[];
 extern int sysctl_ip_vs_sync_ver;
@@ -1119,11 +1112,13 @@ extern int ip_vs_icmp_xmit_v6
 extern int ip_vs_drop_rate;
 extern int ip_vs_drop_counter;
 
-static __inline__ int ip_vs_todrop(void)
+static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
 {
-	if (!ip_vs_drop_rate) return 0;
-	if (--ip_vs_drop_counter > 0) return 0;
-	ip_vs_drop_counter = ip_vs_drop_rate;
+	if (!ipvs->drop_rate)
+		return 0;
+	if (--ipvs->drop_counter > 0)
+		return 0;
+	ipvs->drop_counter = ipvs->drop_rate;
 	return 1;
 }
 
@@ -1211,9 +1206,9 @@ static inline void ip_vs_notrack(struct sk_buff *skb)
  *      Netfilter connection tracking
  *      (from ip_vs_nfct.c)
  */
-static inline int ip_vs_conntrack_enabled(void)
+static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
 {
-	return sysctl_ip_vs_conntrack;
+	return ipvs->sysctl_conntrack;
 }
 
 extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
@@ -1226,7 +1221,7 @@ extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp);
 
 #else
 
-static inline int ip_vs_conntrack_enabled(void)
+static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
 {
 	return 0;
 }
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 1acfb33..c4b1abf 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -61,13 +61,46 @@ struct netns_ipvs {
 	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
 	spinlock_t		sctp_app_lock;
 #endif
+	/* ip_vs_conn */
+	atomic_t		conn_count;      /*  connection counter */
+
 	/* ip_vs_ctl */
 	struct ip_vs_stats		*tot_stats;  /* Statistics & est. */
 	struct ip_vs_cpu_stats __percpu *cpustats;   /* Stats per cpu */
 	seqcount_t			*ustats_seq; /* u64 read retry */
 
-	/* ip_vs_conn */
-	atomic_t		conn_count;         /*  connection counter */
+	int			num_services;    /* no of virtual services */
+	/* 1/rate drop and drop-entry variables */
+	int			drop_rate;
+	int			drop_counter;
+	atomic_t		dropentry;
+	/* locks in ctl.c */
+	spinlock_t		dropentry_lock;  /* drop entry handling */
+	spinlock_t		droppacket_lock; /* drop packet handling */
+	spinlock_t		securetcp_lock;  /* state and timeout tables */
+	rwlock_t		rs_lock;         /* real services table */
+	/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
+	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
+	/* sys-ctl struct */
+	struct ctl_table_header	*sysctl_hdr;
+	struct ctl_table	*sysctl_tbl;
+	/* sysctl variables */
+	int			sysctl_amemthresh;
+	int			sysctl_am_droprate;
+	int			sysctl_drop_entry;
+	int			sysctl_drop_packet;
+	int			sysctl_secure_tcp;
+#ifdef CONFIG_IP_VS_NFCT
+	int			sysctl_conntrack;
+#endif
+	int			sysctl_snat_reroute;
+	int			sysctl_sync_ver;
+	int			sysctl_cache_bypass;
+	int			sysctl_expire_nodest_conn;
+	int			sysctl_expire_quiescent_template;
+	int			sysctl_sync_threshold[2];
+	int			sysctl_nat_icmp_send;
+
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
 	struct ctl_table_header	*lblc_ctl_header;
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 0d5e4fe..5ba205a 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -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 "
@@ -879,7 +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 */
@@ -1198,7 +1199,7 @@ static void ip_vs_conn_flush(struct net *net)
 	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.
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 7205b49..a7c59a7 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -499,6 +499,7 @@ 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 netns_ipvs *ipvs;
 	__be16 _ports[2], *pptr;
 	struct ip_vs_iphdr iph;
 	int unicast;
@@ -521,7 +522,8 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 	/* if it is fwmark-based service, the cache_bypass sysctl is up
 	   and the destination is a non-local unicast, then create
 	   a cache_bypass connection entry */
-	if (sysctl_ip_vs_cache_bypass && svc->fwmark && unicast) {
+	ipvs = net_ipvs(skb_net(skb));
+	if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) {
 		int ret, cs;
 		struct ip_vs_conn *cp;
 		unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
@@ -733,6 +735,7 @@ 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) {
@@ -754,6 +757,8 @@ 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);
@@ -763,11 +768,11 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0)
+		if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
 			goto out;
 	} else
 #endif
-		if ((sysctl_ip_vs_snat_reroute ||
+		if ((ipvs->sysctl_snat_reroute ||
 		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
 		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
 			goto out;
@@ -979,6 +984,7 @@ 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");
 
@@ -1014,13 +1020,15 @@ 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 (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0)
+		if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
 			goto drop;
 	} else
 #endif
-		if ((sysctl_ip_vs_snat_reroute ||
+		if ((ipvs->sysctl_snat_reroute ||
 		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
 		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
 			goto drop;
@@ -1057,6 +1065,7 @@ 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);
 
@@ -1131,10 +1140,11 @@ 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 (sysctl_ip_vs_nat_icmp_send &&
+	if (ipvs->sysctl_nat_icmp_send &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
 	     pp->protocol == IPPROTO_SCTP)) {
@@ -1580,7 +1590,7 @@ 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 (sysctl_ip_vs_expire_nodest_conn) {
+		if (ipvs->sysctl_expire_nodest_conn) {
 			/* try to expire the connection immediately */
 			ip_vs_conn_expire_now(cp);
 		}
@@ -1610,15 +1620,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	 */
 
 	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
-		pkts = sysctl_ip_vs_sync_threshold[0];
+		pkts = ipvs->sysctl_sync_threshold[0];
 	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 % sysctl_ip_vs_sync_threshold[1]
-			 == sysctl_ip_vs_sync_threshold[0])) ||
+			(pkts % ipvs->sysctl_sync_threshold[1]
+			 == ipvs->sysctl_sync_threshold[0])) ||
 				(cp->old_state != cp->state &&
 				 ((cp->state == IP_VS_SCTP_S_CLOSED) ||
 				  (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) ||
@@ -1632,8 +1642,8 @@ 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 % sysctl_ip_vs_sync_threshold[1]
-	       == sysctl_ip_vs_sync_threshold[0])) ||
+	      (pkts % ipvs->sysctl_sync_threshold[1]
+	       == ipvs->sysctl_sync_threshold[0])) ||
 	     ((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 cbd58c6..183ac18 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -58,42 +58,7 @@ static DEFINE_MUTEX(__ip_vs_mutex);
 /* lock for service table */
 static DEFINE_RWLOCK(__ip_vs_svc_lock);
 
-/* lock for table with the real services */
-static DEFINE_RWLOCK(__ip_vs_rs_lock);
-
-/* lock for state and timeout tables */
-static DEFINE_SPINLOCK(ip_vs_securetcp_lock);
-
-/* lock for drop entry handling */
-static DEFINE_SPINLOCK(__ip_vs_dropentry_lock);
-
-/* lock for drop packet handling */
-static DEFINE_SPINLOCK(__ip_vs_droppacket_lock);
-
-/* 1/rate drop and drop-entry variables */
-int ip_vs_drop_rate = 0;
-int ip_vs_drop_counter = 0;
-static atomic_t ip_vs_dropentry = ATOMIC_INIT(0);
-
-/* number of virtual services */
-static int ip_vs_num_services = 0;
-
 /* sysctl variables */
-static int sysctl_ip_vs_drop_entry = 0;
-static int sysctl_ip_vs_drop_packet = 0;
-static int sysctl_ip_vs_secure_tcp = 0;
-static int sysctl_ip_vs_amemthresh = 1024;
-static int sysctl_ip_vs_am_droprate = 10;
-int sysctl_ip_vs_cache_bypass = 0;
-int sysctl_ip_vs_expire_nodest_conn = 0;
-int sysctl_ip_vs_expire_quiescent_template = 0;
-int sysctl_ip_vs_sync_threshold[2] = { 3, 50 };
-int sysctl_ip_vs_nat_icmp_send = 0;
-#ifdef CONFIG_IP_VS_NFCT
-int sysctl_ip_vs_conntrack;
-#endif
-int sysctl_ip_vs_snat_reroute = 1;
-int sysctl_ip_vs_sync_ver = 1;		/* Default version of sync proto */
 
 #ifdef CONFIG_IP_VS_DEBUG
 static int sysctl_ip_vs_debug_level = 0;
@@ -142,73 +107,73 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 	/* si_swapinfo(&i); */
 	/* availmem = availmem - (i.totalswap - i.freeswap); */
 
-	nomem = (availmem < sysctl_ip_vs_amemthresh);
+	nomem = (availmem < ipvs->sysctl_amemthresh);
 
 	local_bh_disable();
 
 	/* drop_entry */
-	spin_lock(&__ip_vs_dropentry_lock);
-	switch (sysctl_ip_vs_drop_entry) {
+	spin_lock(&ipvs->dropentry_lock);
+	switch (ipvs->sysctl_drop_entry) {
 	case 0:
-		atomic_set(&ip_vs_dropentry, 0);
+		atomic_set(&ipvs->dropentry, 0);
 		break;
 	case 1:
 		if (nomem) {
-			atomic_set(&ip_vs_dropentry, 1);
-			sysctl_ip_vs_drop_entry = 2;
+			atomic_set(&ipvs->dropentry, 1);
+			ipvs->sysctl_drop_entry = 2;
 		} else {
-			atomic_set(&ip_vs_dropentry, 0);
+			atomic_set(&ipvs->dropentry, 0);
 		}
 		break;
 	case 2:
 		if (nomem) {
-			atomic_set(&ip_vs_dropentry, 1);
+			atomic_set(&ipvs->dropentry, 1);
 		} else {
-			atomic_set(&ip_vs_dropentry, 0);
-			sysctl_ip_vs_drop_entry = 1;
+			atomic_set(&ipvs->dropentry, 0);
+			ipvs->sysctl_drop_entry = 1;
 		};
 		break;
 	case 3:
-		atomic_set(&ip_vs_dropentry, 1);
+		atomic_set(&ipvs->dropentry, 1);
 		break;
 	}
-	spin_unlock(&__ip_vs_dropentry_lock);
+	spin_unlock(&ipvs->dropentry_lock);
 
 	/* drop_packet */
-	spin_lock(&__ip_vs_droppacket_lock);
-	switch (sysctl_ip_vs_drop_packet) {
+	spin_lock(&ipvs->droppacket_lock);
+	switch (ipvs->sysctl_drop_packet) {
 	case 0:
-		ip_vs_drop_rate = 0;
+		ipvs->drop_rate = 0;
 		break;
 	case 1:
 		if (nomem) {
-			ip_vs_drop_rate = ip_vs_drop_counter
-				= sysctl_ip_vs_amemthresh /
-				(sysctl_ip_vs_amemthresh-availmem);
-			sysctl_ip_vs_drop_packet = 2;
+			ipvs->drop_rate = ipvs->drop_counter
+				= ipvs->sysctl_amemthresh /
+				(ipvs->sysctl_amemthresh-availmem);
+			ipvs->sysctl_drop_packet = 2;
 		} else {
-			ip_vs_drop_rate = 0;
+			ipvs->drop_rate = 0;
 		}
 		break;
 	case 2:
 		if (nomem) {
-			ip_vs_drop_rate = ip_vs_drop_counter
-				= sysctl_ip_vs_amemthresh /
-				(sysctl_ip_vs_amemthresh-availmem);
+			ipvs->drop_rate = ipvs->drop_counter
+				= ipvs->sysctl_amemthresh /
+				(ipvs->sysctl_amemthresh-availmem);
 		} else {
-			ip_vs_drop_rate = 0;
-			sysctl_ip_vs_drop_packet = 1;
+			ipvs->drop_rate = 0;
+			ipvs->sysctl_drop_packet = 1;
 		}
 		break;
 	case 3:
-		ip_vs_drop_rate = sysctl_ip_vs_am_droprate;
+		ipvs->drop_rate = ipvs->sysctl_am_droprate;
 		break;
 	}
-	spin_unlock(&__ip_vs_droppacket_lock);
+	spin_unlock(&ipvs->droppacket_lock);
 
 	/* secure_tcp */
-	spin_lock(&ip_vs_securetcp_lock);
-	switch (sysctl_ip_vs_secure_tcp) {
+	spin_lock(&ipvs->securetcp_lock);
+	switch (ipvs->sysctl_secure_tcp) {
 	case 0:
 		if (old_secure_tcp >= 2)
 			to_change = 0;
@@ -217,7 +182,7 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 		if (nomem) {
 			if (old_secure_tcp < 2)
 				to_change = 1;
-			sysctl_ip_vs_secure_tcp = 2;
+			ipvs->sysctl_secure_tcp = 2;
 		} else {
 			if (old_secure_tcp >= 2)
 				to_change = 0;
@@ -230,7 +195,7 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 		} else {
 			if (old_secure_tcp >= 2)
 				to_change = 0;
-			sysctl_ip_vs_secure_tcp = 1;
+			ipvs->sysctl_secure_tcp = 1;
 		}
 		break;
 	case 3:
@@ -238,11 +203,11 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 			to_change = 1;
 		break;
 	}
-	old_secure_tcp = sysctl_ip_vs_secure_tcp;
+	old_secure_tcp = ipvs->sysctl_secure_tcp;
 	if (to_change >= 0)
 		ip_vs_protocol_timeout_change(ipvs,
-					     sysctl_ip_vs_secure_tcp > 1);
-	spin_unlock(&ip_vs_securetcp_lock);
+					      ipvs->sysctl_secure_tcp > 1);
+	spin_unlock(&ipvs->securetcp_lock);
 
 	local_bh_enable();
 }
@@ -260,7 +225,7 @@ static void defense_work_handler(struct work_struct *work)
 	struct netns_ipvs *ipvs = net_ipvs(&init_net);
 
 	update_defense_level(ipvs);
-	if (atomic_read(&ip_vs_dropentry))
+	if (atomic_read(&ipvs->dropentry))
 		ip_vs_random_dropentry();
 
 	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);
@@ -602,7 +567,7 @@ ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
 	 */
 	hash = ip_vs_rs_hashkey(af, daddr, dport);
 
-	read_lock(&__ip_vs_rs_lock);
+	read_lock(&ipvs->rs_lock);
 	list_for_each_entry(dest, &ipvs->rs_table[hash], d_list) {
 		if ((dest->af == af)
 		    && ip_vs_addr_equal(af, &dest->addr, daddr)
@@ -610,11 +575,11 @@ ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
 		    && ((dest->protocol == protocol) ||
 			dest->vfwmark)) {
 			/* HIT */
-			read_unlock(&__ip_vs_rs_lock);
+			read_unlock(&ipvs->rs_lock);
 			return dest;
 		}
 	}
-	read_unlock(&__ip_vs_rs_lock);
+	read_unlock(&ipvs->rs_lock);
 
 	return NULL;
 }
@@ -788,9 +753,9 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 		 *    Put the real service in rs_table if not present.
 		 *    For now only for NAT!
 		 */
-		write_lock_bh(&__ip_vs_rs_lock);
+		write_lock_bh(&ipvs->rs_lock);
 		ip_vs_rs_hash(ipvs, dest);
-		write_unlock_bh(&__ip_vs_rs_lock);
+		write_unlock_bh(&ipvs->rs_lock);
 	}
 	atomic_set(&dest->conn_flags, conn_flags);
 
@@ -1022,14 +987,16 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
  */
 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);
 
 	/*
 	 *  Remove it from the d-linked list with the real services.
 	 */
-	write_lock_bh(&__ip_vs_rs_lock);
+	write_lock_bh(&ipvs->rs_lock);
 	ip_vs_rs_unhash(dest);
-	write_unlock_bh(&__ip_vs_rs_lock);
+	write_unlock_bh(&ipvs->rs_lock);
 
 	/*
 	 *  Decrease the refcnt of the dest, and free the dest
@@ -1092,7 +1059,6 @@ static int
 ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 {
 	struct ip_vs_dest *dest;
-	struct net *net = svc->net;
 	__be16 dport = udest->port;
 
 	EnterFunction(2);
@@ -1121,7 +1087,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 	/*
 	 *	Delete the destination
 	 */
-	__ip_vs_del_dest(net, dest);
+	__ip_vs_del_dest(svc->net, dest);
 
 	LeaveFunction(2);
 
@@ -1140,6 +1106,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	struct ip_vs_scheduler *sched = NULL;
 	struct ip_vs_pe *pe = NULL;
 	struct ip_vs_service *svc = NULL;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	/* increase the module use count */
 	ip_vs_use_count_inc();
@@ -1219,7 +1186,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 
 	/* Count only IPv4 services for old get/setsockopt interface */
 	if (svc->af == AF_INET)
-		ip_vs_num_services++;
+		ipvs->num_services++;
 
 	/* Hash the service into the service table */
 	write_lock_bh(&__ip_vs_svc_lock);
@@ -1359,12 +1326,13 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 	struct ip_vs_dest *dest, *nxt;
 	struct ip_vs_scheduler *old_sched;
 	struct ip_vs_pe *old_pe;
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 
 	pr_info("%s: enter\n", __func__);
 
 	/* Count only IPv4 services for old get/setsockopt interface */
 	if (svc->af == AF_INET)
-		ip_vs_num_services--;
+		ipvs->num_services--;
 
 	ip_vs_kill_estimator(svc->net, &svc->stats);
 
@@ -1589,42 +1557,31 @@ proc_do_sync_mode(ctl_table *table, int write,
 
 /*
  *	IPVS sysctl table (under the /proc/sys/net/ipv4/vs/)
+ *	Do not change order or insert new entries without
+ *	align with netns init in __ip_vs_control_init()
  */
 
 static struct ctl_table vs_vars[] = {
 	{
 		.procname	= "amemthresh",
-		.data		= &sysctl_ip_vs_amemthresh,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#ifdef CONFIG_IP_VS_DEBUG
-	{
-		.procname	= "debug_level",
-		.data		= &sysctl_ip_vs_debug_level,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-#endif
 	{
 		.procname	= "am_droprate",
-		.data		= &sysctl_ip_vs_am_droprate,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
 	{
 		.procname	= "drop_entry",
-		.data		= &sysctl_ip_vs_drop_entry,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_do_defense_mode,
 	},
 	{
 		.procname	= "drop_packet",
-		.data		= &sysctl_ip_vs_drop_packet,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_do_defense_mode,
@@ -1632,7 +1589,6 @@ static struct ctl_table vs_vars[] = {
 #ifdef CONFIG_IP_VS_NFCT
 	{
 		.procname	= "conntrack",
-		.data		= &sysctl_ip_vs_conntrack,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
@@ -1640,25 +1596,62 @@ static struct ctl_table vs_vars[] = {
 #endif
 	{
 		.procname	= "secure_tcp",
-		.data		= &sysctl_ip_vs_secure_tcp,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_do_defense_mode,
 	},
 	{
 		.procname	= "snat_reroute",
-		.data		= &sysctl_ip_vs_snat_reroute,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
 	{
 		.procname	= "sync_version",
-		.data		= &sysctl_ip_vs_sync_ver,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= &proc_do_sync_mode,
 	},
+	{
+		.procname	= "cache_bypass",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "expire_nodest_conn",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "expire_quiescent_template",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "sync_threshold",
+		.maxlen		=
+			sizeof(((struct netns_ipvs *)0)->sysctl_sync_threshold),
+		.mode		= 0644,
+		.proc_handler	= proc_do_sync_threshold,
+	},
+	{
+		.procname	= "nat_icmp_send",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#ifdef CONFIG_IP_VS_DEBUG
+	{
+		.procname	= "debug_level",
+		.data		= &sysctl_ip_vs_debug_level,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#endif
 #if 0
 	{
 		.procname	= "timeout_established",
@@ -1745,41 +1738,6 @@ static struct ctl_table vs_vars[] = {
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 #endif
-	{
-		.procname	= "cache_bypass",
-		.data		= &sysctl_ip_vs_cache_bypass,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "expire_nodest_conn",
-		.data		= &sysctl_ip_vs_expire_nodest_conn,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "expire_quiescent_template",
-		.data		= &sysctl_ip_vs_expire_quiescent_template,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "sync_threshold",
-		.data		= &sysctl_ip_vs_sync_threshold,
-		.maxlen		= sizeof(sysctl_ip_vs_sync_threshold),
-		.mode		= 0644,
-		.proc_handler	= proc_do_sync_threshold,
-	},
-	{
-		.procname	= "nat_icmp_send",
-		.data		= &sysctl_ip_vs_nat_icmp_send,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{ }
 };
 
@@ -1791,8 +1749,6 @@ const struct ctl_path net_vs_ctl_path[] = {
 };
 EXPORT_SYMBOL_GPL(net_vs_ctl_path);
 
-static struct ctl_table_header * sysctl_header;
-
 #ifdef CONFIG_PROC_FS
 
 struct ip_vs_iter {
@@ -2543,7 +2499,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 		struct ip_vs_getinfo info;
 		info.version = IP_VS_VERSION_CODE;
 		info.size = ip_vs_conn_tab_size;
-		info.num_services = ip_vs_num_services;
+		info.num_services = ipvs->num_services;
 		if (copy_to_user(user, &info, sizeof(info)) != 0)
 			ret = -EFAULT;
 	}
@@ -3014,7 +2970,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
 	struct ip_vs_service *svc;
 	struct ip_vs_dest *dest;
 	struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1];
-	struct net *net;
+	struct net *net = skb_sknet(skb);
 
 	mutex_lock(&__ip_vs_mutex);
 
@@ -3023,7 +2979,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
 			IPVS_CMD_ATTR_MAX, ip_vs_cmd_policy))
 		goto out_err;
 
-	net = skb_sknet(skb);
+
 	svc = ip_vs_genl_find_service(net, attrs[IPVS_CMD_ATTR_SERVICE]);
 	if (IS_ERR(svc) || svc == NULL)
 		goto out_err;
@@ -3215,8 +3171,10 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 	int ret = 0, cmd;
 	int need_full_svc = 0, need_full_dest = 0;
 	struct net *net;
+	struct netns_ipvs *ipvs;
 
 	net = skb_sknet(skb);
+	ipvs = net_ipvs(net);
 	cmd = info->genlhdr->cmd;
 
 	mutex_lock(&__ip_vs_mutex);
@@ -3326,8 +3284,10 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info)
 	void *reply;
 	int ret, cmd, reply_cmd;
 	struct net *net;
+	struct netns_ipvs *ipvs;
 
 	net = skb_sknet(skb);
+	ipvs = net_ipvs(net);
 	cmd = info->genlhdr->cmd;
 
 	if (cmd == IPVS_CMD_GET_SERVICE)
@@ -3530,9 +3490,21 @@ int __net_init __ip_vs_control_init(struct net *net)
 {
 	int idx;
 	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ctl_table *tbl;
 
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return -EPERM;
+
+	atomic_set(&ipvs->dropentry, 0);
+	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]);
+
 	/* procfs stats */
 	ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL);
 	if (ipvs->tot_stats == NULL) {
@@ -3553,14 +3525,51 @@ int __net_init __ip_vs_control_init(struct net *net)
 	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);
-	sysctl_header = register_net_sysctl_table(net, net_vs_ctl_path,
+
+	if (!net_eq(net, &init_net)) {
+		tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL);
+		if (tbl == NULL)
+			goto err_dup;
+	} else
+		tbl = vs_vars;
+	/* Initialize sysctl defaults */
+	idx = 0;
+	ipvs->sysctl_amemthresh = 1024;
+	tbl[idx++].data = &ipvs->sysctl_amemthresh;
+	ipvs->sysctl_am_droprate = 10;
+	tbl[idx++].data = &ipvs->sysctl_am_droprate;
+	tbl[idx++].data = &ipvs->sysctl_drop_entry;
+	tbl[idx++].data = &ipvs->sysctl_drop_packet;
+#ifdef CONFIG_IP_VS_NFCT
+	tbl[idx++].data = &ipvs->sysctl_conntrack;
+#endif
+	tbl[idx++].data = &ipvs->sysctl_secure_tcp;
+	ipvs->sysctl_snat_reroute = 1;
+	tbl[idx++].data = &ipvs->sysctl_snat_reroute;
+	ipvs->sysctl_sync_ver = 1;
+	tbl[idx++].data = &ipvs->sysctl_sync_ver;
+	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;
+	tbl[idx].data = &ipvs->sysctl_sync_threshold;
+	tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold);
+	tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
+
+
+	ipvs->sysctl_hdr = register_net_sysctl_table(net, net_vs_ctl_path,
 						  vs_vars);
-	if (sysctl_header == NULL)
+	if (ipvs->sysctl_hdr == NULL)
 		goto err_reg;
 	ip_vs_new_estimator(net, ipvs->tot_stats);
+	ipvs->sysctl_tbl = tbl;
 	return 0;
 
 err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(tbl);
+err_dup:
 	free_percpu(ipvs->cpustats);
 err_alloc:
 	kfree(ipvs->tot_stats);
@@ -3575,7 +3584,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 		return;
 
 	ip_vs_kill_estimator(net, ipvs->tot_stats);
-	unregister_net_sysctl_table(sysctl_header);
+	unregister_net_sysctl_table(ipvs->sysctl_hdr);
 	proc_net_remove(net, "ip_vs_stats_percpu");
 	proc_net_remove(net, "ip_vs_stats");
 	proc_net_remove(net, "ip_vs");
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 550365a..fb2d04a 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -34,7 +34,7 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 				     &iph.daddr, sh->dest))) {
 		int ignored;
 
-		if (ip_vs_todrop()) {
+		if (ip_vs_todrop(net_ipvs(net))) {
 			/*
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index d8b3f9f..c0cc341 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -54,7 +54,7 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 				     &iph.daddr, th->dest))) {
 		int ignored;
 
-		if (ip_vs_todrop()) {
+		if (ip_vs_todrop(net_ipvs(net))) {
 			/*
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 581157b..f1282cb 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -50,7 +50,7 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 	if (svc) {
 		int ignored;
 
-		if (ip_vs_todrop()) {
+		if (ip_vs_todrop(net_ipvs(net))) {
 			/*
 			 * It seems that we are very loaded.
 			 * We have to drop this packet :(
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index f85e47d..b178056 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 == sysctl_ip_vs_sync_ver || !ipvs->sync_buff)
+	if (mode == ipvs->sysctl_sync_ver || !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 (sysctl_ip_vs_sync_ver == 0) {
+	if (ipvs->sysctl_sync_ver == 0) {
 		ip_vs_sync_conn_v0(net, cp);
 		return;
 	}
@@ -650,7 +650,7 @@ control:
 	if (cp->flags & IP_VS_CONN_F_TEMPLATE) {
 		int pkts = atomic_add_return(1, &cp->in_pkts);
 
-		if (pkts % sysctl_ip_vs_sync_threshold[1] != 1)
+		if (pkts % ipvs->sysctl_sync_threshold[1] != 1)
 			return;
 	}
 	goto sloop;
@@ -724,6 +724,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 {
 	struct ip_vs_dest *dest;
 	struct ip_vs_conn *cp;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	if (!(flags & IP_VS_CONN_F_TEMPLATE))
 		cp = ip_vs_conn_in_get(param);
@@ -794,7 +795,7 @@ 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, sysctl_ip_vs_sync_threshold[0]);
+	atomic_set(&cp->in_pkts, ipvs->sysctl_sync_threshold[0]);
 	cp->state = state;
 	cp->old_state = cp->state;
 	/*
-- 
1.7.2.3

[PATCH 51/79] IPVS: netns, defense work timer.

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

This patch makes defense work timer per name-space,
A net ptr had to be added to the ipvs struct,
since it's needed by defense_work_handler.

[ horms@verge.net.au: Use cancel_delayed_work_sync() instead of
	              cancel_rearming_delayed_work(). Found during
		      merge conflict resoliution ]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |    2 +-
 include/net/netns/ip_vs.h       |    3 +++
 net/netfilter/ipvs/ip_vs_conn.c |    5 +++--
 net/netfilter/ipvs/ip_vs_core.c |    1 +
 net/netfilter/ipvs/ip_vs_ctl.c  |   20 +++++++++-----------
 5 files changed, 17 insertions(+), 14 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index af9acf4..fbe660f 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -877,7 +877,7 @@ extern const char * ip_vs_state_name(__u16 proto, int state);
 
 extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp);
 extern int ip_vs_check_template(struct ip_vs_conn *ct);
-extern void ip_vs_random_dropentry(void);
+extern void ip_vs_random_dropentry(struct net *net);
 extern int ip_vs_conn_init(void);
 extern void ip_vs_conn_cleanup(void);
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index c4b1abf..4133261 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -71,6 +71,7 @@ struct netns_ipvs {
 
 	int			num_services;    /* no of virtual services */
 	/* 1/rate drop and drop-entry variables */
+	struct delayed_work	defense_work;   /* Work handler */
 	int			drop_rate;
 	int			drop_counter;
 	atomic_t		dropentry;
@@ -129,6 +130,8 @@ struct netns_ipvs {
 	/* multicast interface name */
 	char			master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
+	/* net name space ptr */
+	struct net		*net;            /* Needed by timer routines */
 };
 
 #endif /* IP_VS_H_ */
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 5ba205a..28bdaf7 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1138,7 +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;
@@ -1158,7 +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:
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index a7c59a7..bdda346 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1884,6 +1884,7 @@ static int __net_init __ip_vs_init(struct net *net)
 		pr_err("%s(): no memory.\n", __func__);
 		return -ENOMEM;
 	}
+	ipvs->net = net;
 	/* Counters used for creating unique names */
 	ipvs->gen = atomic_read(&ipvs_netns_cnt);
 	atomic_inc(&ipvs_netns_cnt);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 183ac18..6a963d4 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -217,18 +217,16 @@ static void update_defense_level(struct netns_ipvs *ipvs)
  *	Timer for checking the defense
  */
 #define DEFENSE_TIMER_PERIOD	1*HZ
-static void defense_work_handler(struct work_struct *work);
-static DECLARE_DELAYED_WORK(defense_work, defense_work_handler);
 
 static void defense_work_handler(struct work_struct *work)
 {
-	struct netns_ipvs *ipvs = net_ipvs(&init_net);
+	struct netns_ipvs *ipvs =
+		container_of(work, struct netns_ipvs, defense_work.work);
 
 	update_defense_level(ipvs);
 	if (atomic_read(&ipvs->dropentry))
-		ip_vs_random_dropentry();
-
-	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);
+		ip_vs_random_dropentry(ipvs->net);
+	schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
 }
 
 int
@@ -3564,6 +3562,9 @@ int __net_init __ip_vs_control_init(struct net *net)
 		goto err_reg;
 	ip_vs_new_estimator(net, ipvs->tot_stats);
 	ipvs->sysctl_tbl = tbl;
+	/* Schedule defense work */
+	INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
+	schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
 	return 0;
 
 err_reg:
@@ -3588,6 +3589,8 @@ 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");
+	cancel_delayed_work_sync(&ipvs->defense_work);
+	cancel_work_sync(&ipvs->defense_work.work);
 	free_percpu(ipvs->cpustats);
 	kfree(ipvs->tot_stats);
 }
@@ -3631,9 +3634,6 @@ int __init ip_vs_control_init(void)
 		goto err_net;
 	}
 
-	/* Hook the defense timer */
-	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);
-
 	LeaveFunction(2);
 	return 0;
 
@@ -3648,8 +3648,6 @@ void ip_vs_control_cleanup(void)
 {
 	EnterFunction(2);
 	ip_vs_trash_cleanup();
-	cancel_delayed_work_sync(&defense_work);
-	cancel_work_sync(&defense_work.work);
 	unregister_pernet_subsys(&ipvs_control_ops);
 	ip_vs_genl_unregister();
 	nf_unregister_sockopt(&ip_vs_sockopts);
-- 
1.7.2.3

[PATCH 52/79] IPVS: netns, trash handling

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

trash list per namspace,
and reordering of some params in dst struct.

[ horms@verge.net.au: Use cancel_delayed_work_sync() instead of
	              cancel_rearming_delayed_work(). Found during
		      merge conflict resoliution ]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |    4 ++--
 include/net/netns/ip_vs.h      |    3 +++
 net/netfilter/ipvs/ip_vs_ctl.c |   23 +++++++++++------------
 3 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index fbe660f..b23bea6 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -662,8 +662,8 @@ struct ip_vs_dest {
 	struct list_head	d_list;   /* for table with all the dests */
 
 	u16			af;		/* address family */
-	union nf_inet_addr	addr;		/* IP address of the server */
 	__be16			port;		/* port number of the server */
+	union nf_inet_addr	addr;		/* IP address of the server */
 	volatile unsigned	flags;		/* dest status flags */
 	atomic_t		conn_flags;	/* flags to copy to conn */
 	atomic_t		weight;		/* server weight */
@@ -690,8 +690,8 @@ struct ip_vs_dest {
 	/* for virtual service */
 	struct ip_vs_service	*svc;		/* service it belongs to */
 	__u16			protocol;	/* which protocol (TCP/UDP) */
-	union nf_inet_addr	vaddr;		/* virtual IP address */
 	__be16			vport;		/* virtual port number */
+	union nf_inet_addr	vaddr;		/* virtual IP address */
 	__u32			vfwmark;	/* firewall mark of service */
 };
 
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 4133261..67ca1cf 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -82,6 +82,9 @@ struct netns_ipvs {
 	rwlock_t		rs_lock;         /* real services table */
 	/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
 	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
+	/* Trash for destinations */
+	struct list_head	dest_trash;
+
 	/* sys-ctl struct */
 	struct ctl_table_header	*sysctl_hdr;
 	struct ctl_table	*sysctl_tbl;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 6a963d4..442edf4 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -255,11 +255,6 @@ static struct list_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
 static struct list_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];
 
 /*
- *	Trash for destinations
- */
-static LIST_HEAD(ip_vs_dest_trash);
-
-/*
  *	FTP & NULL virtual service counters
  */
 static atomic_t ip_vs_ftpsvc_counter = ATOMIC_INIT(0);
@@ -650,11 +645,12 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
 		     __be16 dport)
 {
 	struct ip_vs_dest *dest, *nxt;
+	struct netns_ipvs *ipvs = net_ipvs(svc->net);
 
 	/*
 	 * Find the destination in trash
 	 */
-	list_for_each_entry_safe(dest, nxt, &ip_vs_dest_trash, n_list) {
+	list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) {
 		IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, "
 			      "dest->refcnt=%d\n",
 			      dest->vfwmark,
@@ -703,11 +699,12 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
  *  are expired, and the refcnt of each destination in the trash must
  *  be 1, so we simply release them here.
  */
-static void ip_vs_trash_cleanup(void)
+static void ip_vs_trash_cleanup(struct net *net)
 {
 	struct ip_vs_dest *dest, *nxt;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	list_for_each_entry_safe(dest, nxt, &ip_vs_dest_trash, n_list) {
+	list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) {
 		list_del(&dest->n_list);
 		ip_vs_dst_reset(dest);
 		__ip_vs_unbind_svc(dest);
@@ -1021,7 +1018,7 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
 			      IP_VS_DBG_ADDR(dest->af, &dest->addr),
 			      ntohs(dest->port),
 			      atomic_read(&dest->refcnt));
-		list_add(&dest->n_list, &ip_vs_dest_trash);
+		list_add(&dest->n_list, &ipvs->dest_trash);
 		atomic_inc(&dest->refcnt);
 	}
 }
@@ -3503,6 +3500,8 @@ int __net_init __ip_vs_control_init(struct net *net)
 	for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
 		INIT_LIST_HEAD(&ipvs->rs_table[idx]);
 
+	INIT_LIST_HEAD(&ipvs->dest_trash);
+
 	/* procfs stats */
 	ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL);
 	if (ipvs->tot_stats == NULL) {
@@ -3584,13 +3583,14 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 	if (!net_eq(net, &init_net))	/* netns not enabled yet */
 		return;
 
+	ip_vs_trash_cleanup(net);
 	ip_vs_kill_estimator(net, ipvs->tot_stats);
+	cancel_delayed_work_sync(&ipvs->defense_work);
+	cancel_work_sync(&ipvs->defense_work.work);
 	unregister_net_sysctl_table(ipvs->sysctl_hdr);
 	proc_net_remove(net, "ip_vs_stats_percpu");
 	proc_net_remove(net, "ip_vs_stats");
 	proc_net_remove(net, "ip_vs");
-	cancel_delayed_work_sync(&ipvs->defense_work);
-	cancel_work_sync(&ipvs->defense_work.work);
 	free_percpu(ipvs->cpustats);
 	kfree(ipvs->tot_stats);
 }
@@ -3647,7 +3647,6 @@ err:
 void ip_vs_control_cleanup(void)
 {
 	EnterFunction(2);
-	ip_vs_trash_cleanup();
 	unregister_pernet_subsys(&ipvs_control_ops);
 	ip_vs_genl_unregister();
 	nf_unregister_sockopt(&ip_vs_sockopts);
-- 
1.7.2.3

[PATCH 53/79] IPVS: netns, svc counters moved in ip_vs_ctl,c

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

Last two global vars to be moved,
ip_vs_ftpsvc_counter and ip_vs_nullsvc_counter.

[horms@verge.net.au: removed whitespace-change-only hunk]
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/netns/ip_vs.h      |    3 +++
 net/netfilter/ipvs/ip_vs_ctl.c |   21 +++++++++------------
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
index 67ca1cf..259ebac 100644
--- a/include/net/netns/ip_vs.h
+++ b/include/net/netns/ip_vs.h
@@ -84,6 +84,9 @@ struct netns_ipvs {
 	struct lock_class_key	ctl_key;	/* ctl_mutex debuging */
 	/* Trash for destinations */
 	struct list_head	dest_trash;
+	/* Service counters */
+	atomic_t		ftpsvc_counter;
+	atomic_t		nullsvc_counter;
 
 	/* sys-ctl struct */
 	struct ctl_table_header	*sysctl_hdr;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 442edf4..65f5de4 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -254,12 +254,6 @@ static struct list_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
 /* the service table hashed by fwmark */
 static struct list_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];
 
-/*
- *	FTP & NULL virtual service counters
- */
-static atomic_t ip_vs_ftpsvc_counter = ATOMIC_INIT(0);
-static atomic_t ip_vs_nullsvc_counter = ATOMIC_INIT(0);
-
 
 /*
  *	Returns hash value for virtual service
@@ -409,6 +403,7 @@ ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport)
 {
 	struct ip_vs_service *svc;
+	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	read_lock(&__ip_vs_svc_lock);
 
@@ -427,7 +422,7 @@ ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 
 	if (svc == NULL
 	    && protocol == IPPROTO_TCP
-	    && atomic_read(&ip_vs_ftpsvc_counter)
+	    && atomic_read(&ipvs->ftpsvc_counter)
 	    && (vport == FTPDATA || ntohs(vport) >= PROT_SOCK)) {
 		/*
 		 * Check if ftp service entry exists, the packet
@@ -437,7 +432,7 @@ ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
 	}
 
 	if (svc == NULL
-	    && atomic_read(&ip_vs_nullsvc_counter)) {
+	    && atomic_read(&ipvs->nullsvc_counter)) {
 		/*
 		 * Check if the catch-all port (port zero) exists
 		 */
@@ -1173,9 +1168,9 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 
 	/* Update the virtual service counters */
 	if (svc->port == FTPPORT)
-		atomic_inc(&ip_vs_ftpsvc_counter);
+		atomic_inc(&ipvs->ftpsvc_counter);
 	else if (svc->port == 0)
-		atomic_inc(&ip_vs_nullsvc_counter);
+		atomic_inc(&ipvs->nullsvc_counter);
 
 	ip_vs_new_estimator(net, &svc->stats);
 
@@ -1359,9 +1354,9 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
 	 *    Update the virtual service counters
 	 */
 	if (svc->port == FTPPORT)
-		atomic_dec(&ip_vs_ftpsvc_counter);
+		atomic_dec(&ipvs->ftpsvc_counter);
 	else if (svc->port == 0)
-		atomic_dec(&ip_vs_nullsvc_counter);
+		atomic_dec(&ipvs->nullsvc_counter);
 
 	/*
 	 *    Free the service if nobody refers to it
@@ -3501,6 +3496,8 @@ int __net_init __ip_vs_control_init(struct net *net)
 		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 = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL);
-- 
1.7.2.3

[PATCH 54/79] IPVS: netns, misc init_net removal in core.

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

init_net removed in __ip_vs_addr_is_local_v6, and got net as param.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_core.c |    6 ++++--
 net/netfilter/ipvs/ip_vs_ctl.c  |    9 +++++----
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index bdda346..9e10c7a 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -499,6 +499,7 @@ 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;
@@ -511,18 +512,19 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_service_put(svc);
 		return NF_DROP;
 	}
+	net = skb_net(skb);
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (svc->af == AF_INET6)
 		unicast = ipv6_addr_type(&iph.daddr.in6) & IPV6_ADDR_UNICAST;
 	else
 #endif
-		unicast = (inet_addr_type(&init_net, iph.daddr.ip) == RTN_UNICAST);
+		unicast = (inet_addr_type(net, iph.daddr.ip) == RTN_UNICAST);
 
 	/* if it is fwmark-based service, the cache_bypass sysctl is up
 	   and the destination is a non-local unicast, then create
 	   a cache_bypass connection entry */
-	ipvs = net_ipvs(skb_net(skb));
+	ipvs = net_ipvs(net);
 	if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) {
 		int ret, cs;
 		struct ip_vs_conn *cp;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 65f5de4..edf2b6d 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -71,7 +71,8 @@ int ip_vs_get_debug_level(void)
 
 #ifdef CONFIG_IP_VS_IPV6
 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */
-static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr)
+static int __ip_vs_addr_is_local_v6(struct net *net,
+				    const struct in6_addr *addr)
 {
 	struct rt6_info *rt;
 	struct flowi fl = {
@@ -80,7 +81,7 @@ static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr)
 		.fl6_src = { .s6_addr32 = {0, 0, 0, 0} },
 	};
 
-	rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl);
+	rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl);
 	if (rt && rt->rt6i_dev && (rt->rt6i_dev->flags & IFF_LOOPBACK))
 			return 1;
 
@@ -810,12 +811,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 		atype = ipv6_addr_type(&udest->addr.in6);
 		if ((!(atype & IPV6_ADDR_UNICAST) ||
 			atype & IPV6_ADDR_LINKLOCAL) &&
-			!__ip_vs_addr_is_local_v6(&udest->addr.in6))
+			!__ip_vs_addr_is_local_v6(svc->net, &udest->addr.in6))
 			return -EINVAL;
 	} else
 #endif
 	{
-		atype = inet_addr_type(&init_net, udest->addr.ip);
+		atype = inet_addr_type(svc->net, udest->addr.ip);
 		if (atype != RTN_LOCAL && atype != RTN_UNICAST)
 			return -EINVAL;
 	}
-- 
1.7.2.3

[PATCH 55/79] IPVS: netns, final patch enabling network name space.

[kaber]

From: Hans Schillstrom <hans.schillstrom@ericsson.com>

all init_net removed, (except for some alloc related
that needs to be there)

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_app.c  |    3 ---
 net/netfilter/ipvs/ip_vs_conn.c |    5 -----
 net/netfilter/ipvs/ip_vs_core.c |    4 ----
 net/netfilter/ipvs/ip_vs_ctl.c  |    7 +------
 net/netfilter/ipvs/ip_vs_est.c  |    3 ---
 net/netfilter/ipvs/ip_vs_ftp.c  |    6 ------
 net/netfilter/ipvs/ip_vs_sync.c |    5 -----
 7 files changed, 1 insertions(+), 32 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 286f465..5c48ffb 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -582,9 +582,6 @@ static int __net_init __ip_vs_app_init(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return -EPERM;
-
 	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);
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 28bdaf7..83233fe 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1234,8 +1234,6 @@ int __net_init __ip_vs_conn_init(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return -EPERM;
 	atomic_set(&ipvs->conn_count, 0);
 
 	proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops);
@@ -1245,9 +1243,6 @@ int __net_init __ip_vs_conn_init(struct net *net)
 
 static void __net_exit __ip_vs_conn_cleanup(struct net *net)
 {
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return;
-
 	/* flush all the connection entries first */
 	ip_vs_conn_flush(net);
 	proc_net_remove(net, "ip_vs_conn");
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 9e10c7a..f36a84f 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1877,10 +1877,6 @@ static int __net_init __ip_vs_init(struct net *net)
 {
 	struct netns_ipvs *ipvs;
 
-	if (!net_eq(net, &init_net)) {
-		pr_err("The final patch for enabling netns is missing\n");
-		return -EPERM;
-	}
 	ipvs = net_generic(net, ip_vs_net_id);
 	if (ipvs == NULL) {
 		pr_err("%s(): no memory.\n", __func__);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index edf2b6d..09ca2ce 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2617,6 +2617,7 @@ static struct genl_family ip_vs_genl_family = {
 	.name		= IPVS_GENL_NAME,
 	.version	= IPVS_GENL_VERSION,
 	.maxattr	= IPVS_CMD_MAX,
+	.netnsok        = true,         /* Make ipvsadm to work on netns */
 };
 
 /* Policy used for first-level command attributes */
@@ -3483,9 +3484,6 @@ int __net_init __ip_vs_control_init(struct net *net)
 	struct netns_ipvs *ipvs = net_ipvs(net);
 	struct ctl_table *tbl;
 
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return -EPERM;
-
 	atomic_set(&ipvs->dropentry, 0);
 	spin_lock_init(&ipvs->dropentry_lock);
 	spin_lock_init(&ipvs->droppacket_lock);
@@ -3578,9 +3576,6 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return;
-
 	ip_vs_trash_cleanup(net);
 	ip_vs_kill_estimator(net, ipvs->tot_stats);
 	cancel_delayed_work_sync(&ipvs->defense_work);
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index d13616b..f560a05 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -203,9 +203,6 @@ static int __net_init __ip_vs_estimator_init(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return -EPERM;
-
 	INIT_LIST_HEAD(&ipvs->est_list);
 	spin_lock_init(&ipvs->est_lock);
 	setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)net);
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 6a04f9a..6b5dd6d 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -413,9 +413,6 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
 	int i, ret;
 	struct ip_vs_app *app = &ip_vs_ftp;
 
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return -EPERM;
-
 	ret = register_ip_vs_app(net, app);
 	if (ret)
 		return ret;
@@ -442,9 +439,6 @@ static void __ip_vs_ftp_exit(struct net *net)
 {
 	struct ip_vs_app *app = &ip_vs_ftp;
 
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return;
-
 	unregister_ip_vs_app(net, app);
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index b178056..d1adf98 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1659,9 +1659,6 @@ static int __net_init __ip_vs_sync_init(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return -EPERM;
-
 	INIT_LIST_HEAD(&ipvs->sync_queue);
 	spin_lock_init(&ipvs->sync_lock);
 	spin_lock_init(&ipvs->sync_buff_lock);
@@ -1674,8 +1671,6 @@ static int __net_init __ip_vs_sync_init(struct net *net)
 
 static void __ip_vs_sync_cleanup(struct net *net)
 {
-	if (!net_eq(net, &init_net))	/* netns not enabled yet */
-		return;
 	stop_sync_thread(net, IP_VS_STATE_MASTER);
 	stop_sync_thread(net, IP_VS_STATE_BACKUP);
 }
-- 
1.7.2.3

[PATCH 56/79] netfilter: xt_comment: drop unneeded unsigned qualifier

[kaber]

From: Jan Engelhardt <jengelh@medozas.de>

Since a string is stored, and not something like a MAC address that
would rely on (un)signedness, drop the qualifier.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/xt_comment.h |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/include/linux/netfilter/xt_comment.h b/include/linux/netfilter/xt_comment.h
index eacfedc..0ea5e79 100644
--- a/include/linux/netfilter/xt_comment.h
+++ b/include/linux/netfilter/xt_comment.h
@@ -4,7 +4,7 @@
 #define XT_MAX_COMMENT_LEN 256
 
 struct xt_comment_info {
-	unsigned char comment[XT_MAX_COMMENT_LEN];
+	char comment[XT_MAX_COMMENT_LEN];
 };
 
 #endif /* XT_COMMENT_H */
-- 
1.7.2.3

[PATCH 57/79] netfilter: xt_conntrack: support matching on port ranges

[kaber]

From: Patrick McHardy <kaber@trash.net>

Add a new revision 3 that contains port ranges for all of origsrc,
origdst, replsrc and repldst. The high ports are appended to the
original v2 data structure to allow sharing most of the code with
v1 and v2. Use of the revision specific port matching function is
made dependant on par->match->revision.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/xt_conntrack.h |   15 ++++++
 net/netfilter/xt_conntrack.c           |   75 +++++++++++++++++++++++++++++++-
 2 files changed, 88 insertions(+), 2 deletions(-)

diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h
index 54f47a2..74b904d 100644
--- a/include/linux/netfilter/xt_conntrack.h
+++ b/include/linux/netfilter/xt_conntrack.h
@@ -58,4 +58,19 @@ struct xt_conntrack_mtinfo2 {
 	__u16 state_mask, status_mask;
 };
 
+struct xt_conntrack_mtinfo3 {
+	union nf_inet_addr origsrc_addr, origsrc_mask;
+	union nf_inet_addr origdst_addr, origdst_mask;
+	union nf_inet_addr replsrc_addr, replsrc_mask;
+	union nf_inet_addr repldst_addr, repldst_mask;
+	__u32 expires_min, expires_max;
+	__u16 l4proto;
+	__u16 origsrc_port, origdst_port;
+	__u16 replsrc_port, repldst_port;
+	__u16 match_flags, invert_flags;
+	__u16 state_mask, status_mask;
+	__u16 origsrc_port_high, origdst_port_high;
+	__u16 replsrc_port_high, repldst_port_high;
+};
+
 #endif /*_XT_CONNTRACK_H*/
diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index e536710..4ef1b63 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -112,6 +112,54 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info,
 	return true;
 }
 
+static inline bool
+port_match(u16 min, u16 max, u16 port, bool invert)
+{
+	return (port >= min && port <= max) ^ invert;
+}
+
+static inline bool
+ct_proto_port_check_v3(const struct xt_conntrack_mtinfo3 *info,
+		       const struct nf_conn *ct)
+{
+	const struct nf_conntrack_tuple *tuple;
+
+	tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
+	if ((info->match_flags & XT_CONNTRACK_PROTO) &&
+	    (nf_ct_protonum(ct) == info->l4proto) ^
+	    !(info->invert_flags & XT_CONNTRACK_PROTO))
+		return false;
+
+	/* Shortcut to match all recognized protocols by using ->src.all. */
+	if ((info->match_flags & XT_CONNTRACK_ORIGSRC_PORT) &&
+	    !port_match(info->origsrc_port, info->origsrc_port_high,
+			ntohs(tuple->src.u.all),
+			info->invert_flags & XT_CONNTRACK_ORIGSRC_PORT))
+		return false;
+
+	if ((info->match_flags & XT_CONNTRACK_ORIGDST_PORT) &&
+	    !port_match(info->origdst_port, info->origdst_port_high,
+			ntohs(tuple->dst.u.all),
+			info->invert_flags & XT_CONNTRACK_ORIGDST_PORT))
+		return false;
+
+	tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+
+	if ((info->match_flags & XT_CONNTRACK_REPLSRC_PORT) &&
+	    !port_match(info->replsrc_port, info->replsrc_port_high,
+			ntohs(tuple->src.u.all),
+			info->invert_flags & XT_CONNTRACK_REPLSRC_PORT))
+		return false;
+
+	if ((info->match_flags & XT_CONNTRACK_REPLDST_PORT) &&
+	    !port_match(info->repldst_port, info->repldst_port_high,
+			ntohs(tuple->dst.u.all),
+			info->invert_flags & XT_CONNTRACK_REPLDST_PORT))
+		return false;
+
+	return true;
+}
+
 static bool
 conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par,
              u16 state_mask, u16 status_mask)
@@ -170,8 +218,13 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par,
 		    !(info->invert_flags & XT_CONNTRACK_REPLDST))
 			return false;
 
-	if (!ct_proto_port_check(info, ct))
-		return false;
+	if (par->match->revision != 3) {
+		if (!ct_proto_port_check(info, ct))
+			return false;
+	} else {
+		if (!ct_proto_port_check_v3(par->matchinfo, ct))
+			return false;
+	}
 
 	if ((info->match_flags & XT_CONNTRACK_STATUS) &&
 	    (!!(status_mask & ct->status) ^
@@ -207,6 +260,14 @@ conntrack_mt_v2(const struct sk_buff *skb, struct xt_action_param *par)
 	return conntrack_mt(skb, par, info->state_mask, info->status_mask);
 }
 
+static bool
+conntrack_mt_v3(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_conntrack_mtinfo3 *info = par->matchinfo;
+
+	return conntrack_mt(skb, par, info->state_mask, info->status_mask);
+}
+
 static int conntrack_mt_check(const struct xt_mtchk_param *par)
 {
 	int ret;
@@ -244,6 +305,16 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = {
 		.destroy    = conntrack_mt_destroy,
 		.me         = THIS_MODULE,
 	},
+	{
+		.name       = "conntrack",
+		.revision   = 3,
+		.family     = NFPROTO_UNSPEC,
+		.matchsize  = sizeof(struct xt_conntrack_mtinfo3),
+		.match      = conntrack_mt_v3,
+		.checkentry = conntrack_mt_check,
+		.destroy    = conntrack_mt_destroy,
+		.me         = THIS_MODULE,
+	},
 };
 
 static int __init conntrack_mt_init(void)
-- 
1.7.2.3

[PATCH 58/79] netfilter: x_table: speedup compat operations

[kaber]

From: Eric Dumazet <eric.dumazet@gmail.com>

One iptables invocation with 135000 rules takes 35 seconds of cpu time
on a recent server, using a 32bit distro and a 64bit kernel.

We eventually trigger NMI/RCU watchdog.

INFO: rcu_sched_state detected stall on CPU 3 (t=6000 jiffies)

COMPAT mode has quadratic behavior and consume 16 bytes of memory per
rule.

Switch the xt_compat algos to use an array instead of list, and use a
binary search to locate an offset in the sorted array.

This halves memory need (8 bytes per rule), and removes quadratic
behavior [ O(N*N) -> O(N*log2(N)) ]

Time of iptables goes from 35 s to 150 ms.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/x_tables.h |    3 +-
 net/bridge/netfilter/ebtables.c    |    1 +
 net/ipv4/netfilter/arp_tables.c    |    2 +
 net/ipv4/netfilter/ip_tables.c     |    2 +
 net/ipv6/netfilter/ip6_tables.c    |    2 +
 net/netfilter/x_tables.c           |   82 +++++++++++++++++++++---------------
 6 files changed, 57 insertions(+), 35 deletions(-)

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 742bec0..0f04d98 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -611,8 +611,9 @@ struct _compat_xt_align {
 extern void xt_compat_lock(u_int8_t af);
 extern void xt_compat_unlock(u_int8_t af);
 
-extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta);
+extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta);
 extern void xt_compat_flush_offsets(u_int8_t af);
+extern void xt_compat_init_offsets(u_int8_t af, unsigned int number);
 extern int xt_compat_calc_jump(u_int8_t af, unsigned int offset);
 
 extern int xt_compat_match_offset(const struct xt_match *match);
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 16df053..5f1825d 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1764,6 +1764,7 @@ static int compat_table_info(const struct ebt_table_info *info,
 
 	newinfo->entries_size = size;
 
+	xt_compat_init_offsets(AF_INET, info->nentries);
 	return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
 							entries, newinfo);
 }
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 3fac340..47e5178 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -883,6 +883,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(NFPROTO_ARP, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1350,6 +1351,7 @@ static int translate_compat_table(const char *name,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(NFPROTO_ARP);
+	xt_compat_init_offsets(NFPROTO_ARP, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index a846d63..c5a75d7 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1080,6 +1080,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(AF_INET, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1681,6 +1682,7 @@ translate_compat_table(struct net *net,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET);
+	xt_compat_init_offsets(AF_INET, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 4555823..0c9973a 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1093,6 +1093,7 @@ static int compat_table_info(const struct xt_table_info *info,
 	memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
 	newinfo->initial_entries = 0;
 	loc_cpu_entry = info->entries[raw_smp_processor_id()];
+	xt_compat_init_offsets(AF_INET6, info->number);
 	xt_entry_foreach(iter, loc_cpu_entry, info->size) {
 		ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
 		if (ret != 0)
@@ -1696,6 +1697,7 @@ translate_compat_table(struct net *net,
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET6);
+	xt_compat_init_offsets(AF_INET6, number);
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter0, entry0, total_size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 8046350..ee5de3a 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -38,9 +38,8 @@ MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module");
 #define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1))
 
 struct compat_delta {
-	struct compat_delta *next;
-	unsigned int offset;
-	int delta;
+	unsigned int offset; /* offset in kernel */
+	int delta; /* delta in 32bit user land */
 };
 
 struct xt_af {
@@ -49,7 +48,9 @@ struct xt_af {
 	struct list_head target;
 #ifdef CONFIG_COMPAT
 	struct mutex compat_mutex;
-	struct compat_delta *compat_offsets;
+	struct compat_delta *compat_tab;
+	unsigned int number; /* number of slots in compat_tab[] */
+	unsigned int cur; /* number of used slots in compat_tab[] */
 #endif
 };
 
@@ -414,54 +415,67 @@ int xt_check_match(struct xt_mtchk_param *par,
 EXPORT_SYMBOL_GPL(xt_check_match);
 
 #ifdef CONFIG_COMPAT
-int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta)
+int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta)
 {
-	struct compat_delta *tmp;
+	struct xt_af *xp = &xt[af];
 
-	tmp = kmalloc(sizeof(struct compat_delta), GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
+	if (!xp->compat_tab) {
+		if (!xp->number)
+			return -EINVAL;
+		xp->compat_tab = vmalloc(sizeof(struct compat_delta) * xp->number);
+		if (!xp->compat_tab)
+			return -ENOMEM;
+		xp->cur = 0;
+	}
 
-	tmp->offset = offset;
-	tmp->delta = delta;
+	if (xp->cur >= xp->number)
+		return -EINVAL;
 
-	if (xt[af].compat_offsets) {
-		tmp->next = xt[af].compat_offsets->next;
-		xt[af].compat_offsets->next = tmp;
-	} else {
-		xt[af].compat_offsets = tmp;
-		tmp->next = NULL;
-	}
+	if (xp->cur)
+		delta += xp->compat_tab[xp->cur - 1].delta;
+	xp->compat_tab[xp->cur].offset = offset;
+	xp->compat_tab[xp->cur].delta = delta;
+	xp->cur++;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xt_compat_add_offset);
 
 void xt_compat_flush_offsets(u_int8_t af)
 {
-	struct compat_delta *tmp, *next;
-
-	if (xt[af].compat_offsets) {
-		for (tmp = xt[af].compat_offsets; tmp; tmp = next) {
-			next = tmp->next;
-			kfree(tmp);
-		}
-		xt[af].compat_offsets = NULL;
+	if (xt[af].compat_tab) {
+		vfree(xt[af].compat_tab);
+		xt[af].compat_tab = NULL;
+		xt[af].number = 0;
 	}
 }
 EXPORT_SYMBOL_GPL(xt_compat_flush_offsets);
 
 int xt_compat_calc_jump(u_int8_t af, unsigned int offset)
 {
-	struct compat_delta *tmp;
-	int delta;
-
-	for (tmp = xt[af].compat_offsets, delta = 0; tmp; tmp = tmp->next)
-		if (tmp->offset < offset)
-			delta += tmp->delta;
-	return delta;
+	struct compat_delta *tmp = xt[af].compat_tab;
+	int mid, left = 0, right = xt[af].cur - 1;
+
+	while (left <= right) {
+		mid = (left + right) >> 1;
+		if (offset > tmp[mid].offset)
+			left = mid + 1;
+		else if (offset < tmp[mid].offset)
+			right = mid - 1;
+		else
+			return mid ? tmp[mid - 1].delta : 0;
+	}
+	WARN_ON_ONCE(1);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(xt_compat_calc_jump);
 
+void xt_compat_init_offsets(u_int8_t af, unsigned int number)
+{
+	xt[af].number = number;
+	xt[af].cur = 0;
+}
+EXPORT_SYMBOL(xt_compat_init_offsets);
+
 int xt_compat_match_offset(const struct xt_match *match)
 {
 	u_int16_t csize = match->compatsize ? : match->matchsize;
@@ -1337,7 +1351,7 @@ static int __init xt_init(void)
 		mutex_init(&xt[i].mutex);
 #ifdef CONFIG_COMPAT
 		mutex_init(&xt[i].compat_mutex);
-		xt[i].compat_offsets = NULL;
+		xt[i].compat_tab = NULL;
 #endif
 		INIT_LIST_HEAD(&xt[i].target);
 		INIT_LIST_HEAD(&xt[i].match);
-- 
1.7.2.3

[PATCH 59/79] netfilter: ebt_ip6: allow matching on ipv6-icmp types/codes

[kaber]

From: Florian Westphal <fw@strlen.de>

To avoid adding a new match revision icmp type/code are stored
in the sport/dport area.

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Holger Eitzenberger <holger@eitzenberger.org>
Reviewed-by: Bart De Schuymer<bdschuym@pandora.be>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_bridge/ebt_ip6.h |   15 ++++++++--
 net/bridge/netfilter/ebt_ip6.c           |   46 ++++++++++++++++++++++--------
 2 files changed, 46 insertions(+), 15 deletions(-)

diff --git a/include/linux/netfilter_bridge/ebt_ip6.h b/include/linux/netfilter_bridge/ebt_ip6.h
index e5de987..22af18a 100644
--- a/include/linux/netfilter_bridge/ebt_ip6.h
+++ b/include/linux/netfilter_bridge/ebt_ip6.h
@@ -18,8 +18,11 @@
 #define EBT_IP6_PROTO 0x08
 #define EBT_IP6_SPORT 0x10
 #define EBT_IP6_DPORT 0x20
+#define EBT_IP6_ICMP6 0x40
+
 #define EBT_IP6_MASK (EBT_IP6_SOURCE | EBT_IP6_DEST | EBT_IP6_TCLASS |\
-		      EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT)
+		      EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT | \
+		      EBT_IP6_ICMP6)
 #define EBT_IP6_MATCH "ip6"
 
 /* the same values are used for the invflags */
@@ -32,8 +35,14 @@ struct ebt_ip6_info {
 	uint8_t  protocol;
 	uint8_t  bitmask;
 	uint8_t  invflags;
-	uint16_t sport[2];
-	uint16_t dport[2];
+	union {
+		uint16_t sport[2];
+		uint8_t icmpv6_type[2];
+	};
+	union {
+		uint16_t dport[2];
+		uint8_t icmpv6_code[2];
+	};
 };
 
 #endif
diff --git a/net/bridge/netfilter/ebt_ip6.c b/net/bridge/netfilter/ebt_ip6.c
index 50a46af..2ed0056 100644
--- a/net/bridge/netfilter/ebt_ip6.c
+++ b/net/bridge/netfilter/ebt_ip6.c
@@ -22,9 +22,15 @@
 #include <linux/netfilter_bridge/ebtables.h>
 #include <linux/netfilter_bridge/ebt_ip6.h>
 
-struct tcpudphdr {
-	__be16 src;
-	__be16 dst;
+union pkthdr {
+	struct {
+		__be16 src;
+		__be16 dst;
+	} tcpudphdr;
+	struct {
+		u8 type;
+		u8 code;
+	} icmphdr;
 };
 
 static bool
@@ -33,8 +39,8 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	const struct ebt_ip6_info *info = par->matchinfo;
 	const struct ipv6hdr *ih6;
 	struct ipv6hdr _ip6h;
-	const struct tcpudphdr *pptr;
-	struct tcpudphdr _ports;
+	const union pkthdr *pptr;
+	union pkthdr _pkthdr;
 
 	ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h);
 	if (ih6 == NULL)
@@ -56,26 +62,34 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
 			return false;
 		if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
 			return false;
-		if (!(info->bitmask & EBT_IP6_DPORT) &&
-		    !(info->bitmask & EBT_IP6_SPORT))
+		if (!(info->bitmask & ( EBT_IP6_DPORT |
+					EBT_IP6_SPORT | EBT_IP6_ICMP6)))
 			return true;
-		pptr = skb_header_pointer(skb, offset_ph, sizeof(_ports),
-					  &_ports);
+
+		/* min icmpv6 headersize is 4, so sizeof(_pkthdr) is ok. */
+		pptr = skb_header_pointer(skb, offset_ph, sizeof(_pkthdr),
+					  &_pkthdr);
 		if (pptr == NULL)
 			return false;
 		if (info->bitmask & EBT_IP6_DPORT) {
-			u32 dst = ntohs(pptr->dst);
+			u16 dst = ntohs(pptr->tcpudphdr.dst);
 			if (FWINV(dst < info->dport[0] ||
 				  dst > info->dport[1], EBT_IP6_DPORT))
 				return false;
 		}
 		if (info->bitmask & EBT_IP6_SPORT) {
-			u32 src = ntohs(pptr->src);
+			u16 src = ntohs(pptr->tcpudphdr.src);
 			if (FWINV(src < info->sport[0] ||
 				  src > info->sport[1], EBT_IP6_SPORT))
 			return false;
 		}
-		return true;
+		if ((info->bitmask & EBT_IP6_ICMP6) &&
+		     FWINV(pptr->icmphdr.type < info->icmpv6_type[0] ||
+			   pptr->icmphdr.type > info->icmpv6_type[1] ||
+			   pptr->icmphdr.code < info->icmpv6_code[0] ||
+			   pptr->icmphdr.code > info->icmpv6_code[1],
+							EBT_IP6_ICMP6))
+			return false;
 	}
 	return true;
 }
@@ -103,6 +117,14 @@ static int ebt_ip6_mt_check(const struct xt_mtchk_param *par)
 		return -EINVAL;
 	if (info->bitmask & EBT_IP6_SPORT && info->sport[0] > info->sport[1])
 		return -EINVAL;
+	if (info->bitmask & EBT_IP6_ICMP6) {
+		if ((info->invflags & EBT_IP6_PROTO) ||
+		     info->protocol != IPPROTO_ICMPV6)
+			return -EINVAL;
+		if (info->icmpv6_type[0] > info->icmpv6_type[1] ||
+		    info->icmpv6_code[0] > info->icmpv6_code[1])
+			return -EINVAL;
+	}
 	return 0;
 }
 
-- 
1.7.2.3

[PATCH 60/79] netfilter: fix Kconfig dependencies

[kaber]

From: Patrick McHardy <kaber@trash.net>

Fix dependencies of netfilter realm match: it depends on NET_CLS_ROUTE,
which itself depends on NET_SCHED; this dependency is missing from netfilter.

Since matching on realms is also useful without having NET_SCHED enabled and
the option really only controls whether the tclassid member is included in
route and dst entries, rename the config option to IP_ROUTE_CLASSID and move
it outside of traffic scheduling context to get rid of the NET_SCHED dependeny.

Reported-by: Vladis Kletnieks <Valdis.Kletnieks@vt.edu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/dst.h        |    2 +-
 include/net/ip_fib.h     |    6 +++---
 net/ipv4/Kconfig         |    4 +++-
 net/ipv4/fib_rules.c     |   10 +++++-----
 net/ipv4/fib_semantics.c |   14 +++++++-------
 net/ipv4/ip_input.c      |    2 +-
 net/ipv4/route.c         |   26 +++++++++++++-------------
 net/netfilter/Kconfig    |    2 +-
 net/sched/Kconfig        |    5 +----
 net/sched/cls_flow.c     |    2 +-
 net/sched/em_meta.c      |    2 +-
 11 files changed, 37 insertions(+), 38 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index a5bd726..6baba83 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -72,7 +72,7 @@ struct dst_entry {
 
 	u32			metrics[RTAX_MAX];
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	__u32			tclassid;
 #else
 	__u32			__pad2;
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 07bdb5e..65d1fcd 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -55,7 +55,7 @@ struct fib_nh {
 	int			nh_weight;
 	int			nh_power;
 #endif
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	__u32			nh_tclassid;
 #endif
 	int			nh_oif;
@@ -201,7 +201,7 @@ static inline int fib_lookup(struct net *net, const struct flowi *flp,
 extern int __net_init fib4_rules_init(struct net *net);
 extern void __net_exit fib4_rules_exit(struct net *net);
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 extern u32 fib_rules_tclass(struct fib_result *res);
 #endif
 
@@ -235,7 +235,7 @@ extern struct fib_table *fib_hash_table(u32 id);
 
 static inline void fib_combine_itag(u32 *itag, struct fib_result *res)
 {
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	u32 rtag;
 #endif
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 9e95d7f..dcb2e18 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -140,6 +140,9 @@ config IP_ROUTE_VERBOSE
 	  handled by the klogd daemon which is responsible for kernel messages
 	  ("man klogd").
 
+config IP_ROUTE_CLASSID
+	bool
+
 config IP_PNP
 	bool "IP: kernel level autoconfiguration"
 	help
@@ -655,4 +658,3 @@ config TCP_MD5SIG
 	  on the Internet.
 
 	  If unsure, say N.
-
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 7981a24..9cefe72 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -41,12 +41,12 @@ struct fib4_rule {
 	__be32			srcmask;
 	__be32			dst;
 	__be32			dstmask;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	u32			tclassid;
 #endif
 };
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 u32 fib_rules_tclass(struct fib_result *res)
 {
 	return res->r ? ((struct fib4_rule *) res->r)->tclassid : 0;
@@ -165,7 +165,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	if (frh->dst_len)
 		rule4->dst = nla_get_be32(tb[FRA_DST]);
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (tb[FRA_FLOW])
 		rule4->tclassid = nla_get_u32(tb[FRA_FLOW]);
 #endif
@@ -195,7 +195,7 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 	if (frh->tos && (rule4->tos != frh->tos))
 		return 0;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW])))
 		return 0;
 #endif
@@ -224,7 +224,7 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 	if (rule4->src_len)
 		NLA_PUT_BE32(skb, FRA_SRC, rule4->src);
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (rule4->tclassid)
 		NLA_PUT_U32(skb, FRA_FLOW, rule4->tclassid);
 #endif
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3e0da3e..a72c62d 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -200,7 +200,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 		    nh->nh_weight != onh->nh_weight ||
 #endif
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		    nh->nh_tclassid != onh->nh_tclassid ||
 #endif
 		    ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_F_DEAD))
@@ -422,7 +422,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
 			nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
 #endif
@@ -476,7 +476,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla && nla_get_be32(nla) != nh->nh_gw)
 				return 1;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
 			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
 				return 1;
@@ -783,7 +783,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 			goto err_inval;
 		if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw)
 			goto err_inval;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow)
 			goto err_inval;
 #endif
@@ -796,7 +796,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 		nh->nh_oif = cfg->fc_oif;
 		nh->nh_gw = cfg->fc_gw;
 		nh->nh_flags = cfg->fc_flags;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		nh->nh_tclassid = cfg->fc_flow;
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -1006,7 +1006,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 
 		if (fi->fib_nh->nh_oif)
 			NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		if (fi->fib_nh[0].nh_tclassid)
 			NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid);
 #endif
@@ -1031,7 +1031,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 
 			if (nh->nh_gw)
 				NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 			if (nh->nh_tclassid)
 				NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid);
 #endif
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index d859bcc..d7b2b09 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -340,7 +340,7 @@ static int ip_rcv_finish(struct sk_buff *skb)
 		}
 	}
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (unlikely(skb_dst(skb)->tclassid)) {
 		struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
 		u32 idx = skb_dst(skb)->tclassid;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 66610ea..f70ae1b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -511,7 +511,7 @@ static const struct file_operations rt_cpu_seq_fops = {
 	.release = seq_release,
 };
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 static int rt_acct_proc_show(struct seq_file *m, void *v)
 {
 	struct ip_rt_acct *dst, *src;
@@ -564,14 +564,14 @@ static int __net_init ip_rt_do_proc_init(struct net *net)
 	if (!pde)
 		goto err2;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);
 	if (!pde)
 		goto err3;
 #endif
 	return 0;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 err3:
 	remove_proc_entry("rt_cache", net->proc_net_stat);
 #endif
@@ -585,7 +585,7 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net)
 {
 	remove_proc_entry("rt_cache", net->proc_net_stat);
 	remove_proc_entry("rt_cache", net->proc_net);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	remove_proc_entry("rt_acct", net->proc_net);
 #endif
 }
@@ -1784,7 +1784,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt)
 	memcpy(addr, &src, 4);
 }
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 static void set_class_tag(struct rtable *rt, u32 tag)
 {
 	if (!(rt->dst.tclassid & 0xFFFF))
@@ -1811,7 +1811,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 			    rt->dst.dev->mtu > 576)
 				rt->dst.metrics[RTAX_MTU-1] = 576;
 		}
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = FIB_RES_NH(*res).nh_tclassid;
 #endif
 	} else
@@ -1827,7 +1827,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
 	if (dst_metric(&rt->dst, RTAX_ADVMSS) > 65535 - 40)
 		rt->dst.metrics[RTAX_ADVMSS-1] = 65535 - 40;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	set_class_tag(rt, fib_rules_tclass(res));
 #endif
@@ -1883,7 +1883,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	rth->fl.mark    = skb->mark;
 	rth->fl.fl4_src	= saddr;
 	rth->rt_src	= saddr;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
 #endif
 	rth->rt_iif	=
@@ -2202,7 +2202,7 @@ local_input:
 	rth->fl.mark    = skb->mark;
 	rth->fl.fl4_src	= saddr;
 	rth->rt_src	= saddr;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
 #endif
 	rth->rt_iif	=
@@ -2820,7 +2820,7 @@ static int rt_fill_info(struct net *net,
 	}
 	if (rt->dst.dev)
 		NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (rt->dst.tclassid)
 		NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid);
 #endif
@@ -3245,9 +3245,9 @@ static __net_initdata struct pernet_operations rt_genid_ops = {
 };
 
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
-#endif /* CONFIG_NET_CLS_ROUTE */
+#endif /* CONFIG_IP_ROUTE_CLASSID */
 
 static __initdata unsigned long rhash_entries;
 static int __init set_rhash_entries(char *str)
@@ -3263,7 +3263,7 @@ int __init ip_rt_init(void)
 {
 	int rc = 0;
 
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)
 		panic("IP: failed to allocate ip_rt_acct\n");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 1534f2b..1b79353 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -886,7 +886,7 @@ config NETFILTER_XT_MATCH_RATEEST
 config NETFILTER_XT_MATCH_REALM
 	tristate  '"realm" match support'
 	depends on NETFILTER_ADVANCED
-	select NET_CLS_ROUTE
+	select IP_ROUTE_CLASSID
 	help
 	  This option adds a `realm' match, which allows you to use the realm
 	  key from the routing subsystem inside iptables.
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index a36270a..4b753ef 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -243,7 +243,7 @@ config NET_CLS_TCINDEX
 
 config NET_CLS_ROUTE4
 	tristate "Routing decision (ROUTE)"
-	select NET_CLS_ROUTE
+	select IP_ROUTE_CLASSID
 	select NET_CLS
 	---help---
 	  If you say Y here, you will be able to classify packets
@@ -252,9 +252,6 @@ config NET_CLS_ROUTE4
 	  To compile this code as a module, choose M here: the
 	  module will be called cls_route.
 
-config NET_CLS_ROUTE
-	bool
-
 config NET_CLS_FW
 	tristate "Netfilter mark (FW)"
 	select NET_CLS
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 5b271a1..a3b293d 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -276,7 +276,7 @@ fallback:
 
 static u32 flow_get_rtclassid(const struct sk_buff *skb)
 {
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	if (skb_dst(skb))
 		return skb_dst(skb)->tclassid;
 #endif
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 34da5e2..0d66e58 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -255,7 +255,7 @@ META_COLLECTOR(int_rtclassid)
 	if (unlikely(skb_dst(skb) == NULL))
 		*err = -1;
 	else
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 		dst->value = skb_dst(skb)->tclassid;
 #else
 		dst->value = 0;
-- 
1.7.2.3

[PATCH 61/79] netfilter: nf_conntrack: use is_vmalloc_addr()

[kaber]

From: Patrick McHardy <kaber@trash.net>

Use is_vmalloc_addr() in nf_ct_free_hashtable() and get rid of
the vmalloc flags to indicate that a hash table has been allocated
using vmalloc().

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_conntrack.h |    4 ++--
 include/net/netns/conntrack.h        |    2 --
 include/net/netns/ipv4.h             |    1 -
 net/ipv4/netfilter/nf_nat_core.c     |    6 ++----
 net/netfilter/nf_conntrack_core.c    |   26 +++++++++-----------------
 net/netfilter/nf_conntrack_expect.c  |    9 +++------
 net/netfilter/nf_conntrack_helper.c  |   10 +++-------
 7 files changed, 19 insertions(+), 39 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 2bc344c..d0d1337 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -202,9 +202,9 @@ extern void nf_ct_l3proto_module_put(unsigned short l3proto);
  * Allocate a hashtable of hlist_head (if nulls == 0),
  * or hlist_nulls_head (if nulls == 1)
  */
-extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls);
+extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls);
 
-extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size);
+extern void nf_ct_free_hashtable(void *hash, unsigned int size);
 
 extern struct nf_conntrack_tuple_hash *
 __nf_conntrack_find(struct net *net, u16 zone,
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index d4958d4..5cf8a8c 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -28,8 +28,6 @@ struct netns_ct {
 	struct ctl_table_header	*acct_sysctl_header;
 	struct ctl_table_header	*event_sysctl_header;
 #endif
-	int			hash_vmalloc;
-	int			expect_vmalloc;
 	char			*slabname;
 };
 #endif
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index d68c3f1..e2e2ef5 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -43,7 +43,6 @@ struct netns_ipv4 {
 	struct xt_table		*nat_table;
 	struct hlist_head	*nat_bysource;
 	unsigned int		nat_htable_size;
-	int			nat_vmalloced;
 #endif
 
 	int sysctl_icmp_echo_ignore_all;
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index eb55835..6972cee 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -682,8 +682,7 @@ static int __net_init nf_nat_net_init(struct net *net)
 {
 	/* Leave them the same for the moment. */
 	net->ipv4.nat_htable_size = net->ct.htable_size;
-	net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size,
-						       &net->ipv4.nat_vmalloced, 0);
+	net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size, 0);
 	if (!net->ipv4.nat_bysource)
 		return -ENOMEM;
 	return 0;
@@ -705,8 +704,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 {
 	nf_ct_iterate_cleanup(net, &clean_nat, NULL);
 	synchronize_rcu();
-	nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_vmalloced,
-			     net->ipv4.nat_htable_size);
+	nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_htable_size);
 }
 
 static struct pernet_operations nf_nat_net_ops = {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index e95ac42..dc2ff2c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1202,9 +1202,9 @@ static int kill_all(struct nf_conn *i, void *data)
 	return 1;
 }
 
-void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size)
+void nf_ct_free_hashtable(void *hash, unsigned int size)
 {
-	if (vmalloced)
+	if (is_vmalloc_addr(hash))
 		vfree(hash);
 	else
 		free_pages((unsigned long)hash,
@@ -1271,8 +1271,7 @@ static void nf_conntrack_cleanup_net(struct net *net)
 		goto i_see_dead_people;
 	}
 
-	nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc,
-			     net->ct.htable_size);
+	nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
 	nf_conntrack_ecache_fini(net);
 	nf_conntrack_acct_fini(net);
 	nf_conntrack_expect_fini(net);
@@ -1301,21 +1300,18 @@ void nf_conntrack_cleanup(struct net *net)
 	}
 }
 
-void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls)
+void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)
 {
 	struct hlist_nulls_head *hash;
 	unsigned int nr_slots, i;
 	size_t sz;
 
-	*vmalloced = 0;
-
 	BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head));
 	nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head));
 	sz = nr_slots * sizeof(struct hlist_nulls_head);
 	hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO,
 					get_order(sz));
 	if (!hash) {
-		*vmalloced = 1;
 		printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n");
 		hash = __vmalloc(sz, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
 				 PAGE_KERNEL);
@@ -1331,7 +1327,7 @@ EXPORT_SYMBOL_GPL(nf_ct_alloc_hashtable);
 
 int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 {
-	int i, bucket, vmalloced, old_vmalloced;
+	int i, bucket;
 	unsigned int hashsize, old_size;
 	struct hlist_nulls_head *hash, *old_hash;
 	struct nf_conntrack_tuple_hash *h;
@@ -1348,7 +1344,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 	if (!hashsize)
 		return -EINVAL;
 
-	hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced, 1);
+	hash = nf_ct_alloc_hashtable(&hashsize, 1);
 	if (!hash)
 		return -ENOMEM;
 
@@ -1370,15 +1366,13 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 		}
 	}
 	old_size = init_net.ct.htable_size;
-	old_vmalloced = init_net.ct.hash_vmalloc;
 	old_hash = init_net.ct.hash;
 
 	init_net.ct.htable_size = nf_conntrack_htable_size = hashsize;
-	init_net.ct.hash_vmalloc = vmalloced;
 	init_net.ct.hash = hash;
 	spin_unlock_bh(&nf_conntrack_lock);
 
-	nf_ct_free_hashtable(old_hash, old_vmalloced, old_size);
+	nf_ct_free_hashtable(old_hash, old_size);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize);
@@ -1491,8 +1485,7 @@ static int nf_conntrack_init_net(struct net *net)
 	}
 
 	net->ct.htable_size = nf_conntrack_htable_size;
-	net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size,
-					     &net->ct.hash_vmalloc, 1);
+	net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1);
 	if (!net->ct.hash) {
 		ret = -ENOMEM;
 		printk(KERN_ERR "Unable to create nf_conntrack_hash\n");
@@ -1515,8 +1508,7 @@ err_ecache:
 err_acct:
 	nf_conntrack_expect_fini(net);
 err_expect:
-	nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc,
-			     net->ct.htable_size);
+	nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
 err_hash:
 	kmem_cache_destroy(net->ct.nf_conntrack_cachep);
 err_cache:
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 4a9ed23..cd1e8e0 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -639,8 +639,7 @@ int nf_conntrack_expect_init(struct net *net)
 	}
 
 	net->ct.expect_count = 0;
-	net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize,
-						  &net->ct.expect_vmalloc, 0);
+	net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0);
 	if (net->ct.expect_hash == NULL)
 		goto err1;
 
@@ -662,8 +661,7 @@ err3:
 	if (net_eq(net, &init_net))
 		kmem_cache_destroy(nf_ct_expect_cachep);
 err2:
-	nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc,
-			     nf_ct_expect_hsize);
+	nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize);
 err1:
 	return err;
 }
@@ -675,6 +673,5 @@ void nf_conntrack_expect_fini(struct net *net)
 		rcu_barrier(); /* Wait for call_rcu() before destroy */
 		kmem_cache_destroy(nf_ct_expect_cachep);
 	}
-	nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc,
-			     nf_ct_expect_hsize);
+	nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize);
 }
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 767bbe9..1bdfea3 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -33,7 +33,6 @@ static DEFINE_MUTEX(nf_ct_helper_mutex);
 static struct hlist_head *nf_ct_helper_hash __read_mostly;
 static unsigned int nf_ct_helper_hsize __read_mostly;
 static unsigned int nf_ct_helper_count __read_mostly;
-static int nf_ct_helper_vmalloc;
 
 
 /* Stupid hash, but collision free for the default registrations of the
@@ -267,8 +266,7 @@ int nf_conntrack_helper_init(void)
 	int err;
 
 	nf_ct_helper_hsize = 1; /* gets rounded up to use one page */
-	nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize,
-						  &nf_ct_helper_vmalloc, 0);
+	nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0);
 	if (!nf_ct_helper_hash)
 		return -ENOMEM;
 
@@ -279,14 +277,12 @@ int nf_conntrack_helper_init(void)
 	return 0;
 
 err1:
-	nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_vmalloc,
-			     nf_ct_helper_hsize);
+	nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize);
 	return err;
 }
 
 void nf_conntrack_helper_fini(void)
 {
 	nf_ct_extend_unregister(&helper_extend);
-	nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_vmalloc,
-			     nf_ct_helper_hsize);
+	nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize);
 }
-- 
1.7.2.3

[PATCH 62/79] netfilter: audit target to record accepted/dropped packets

[kaber]

From: Thomas Graf <tgraf@infradead.org>

This patch adds a new netfilter target which creates audit records
for packets traversing a certain chain.

It can be used to record packets which are rejected administraively
as follows:

  -N AUDIT_DROP
  -A AUDIT_DROP -j AUDIT --type DROP
  -A AUDIT_DROP -j DROP

a rule which would typically drop or reject a packet would then
invoke the new chain to record packets before dropping them.

  -j AUDIT_DROP

The module is protocol independant and works for iptables, ip6tables
and ebtables.

The following information is logged:
 - netfilter hook
 - packet length
 - incomming/outgoing interface
 - MAC src/dst/proto for ethernet packets
 - src/dst/protocol address for IPv4/IPv6
 - src/dst port for TCP/UDP/UDPLITE
 - icmp type/code

Cc: Patrick McHardy <kaber@trash.net>
Cc: Eric Paris <eparis@parisplace.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Thomas Graf <tgraf@redhat.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/audit.h              |    1 +
 include/linux/netfilter/Kbuild     |    1 +
 include/linux/netfilter/xt_AUDIT.h |   30 ++++++
 net/netfilter/Kconfig              |   10 ++
 net/netfilter/Makefile             |    1 +
 net/netfilter/xt_AUDIT.c           |  204 ++++++++++++++++++++++++++++++++++++
 6 files changed, 247 insertions(+), 0 deletions(-)
 create mode 100644 include/linux/netfilter/xt_AUDIT.h
 create mode 100644 net/netfilter/xt_AUDIT.c

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 8b5c062..ae227df 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -103,6 +103,7 @@
 #define AUDIT_BPRM_FCAPS	1321	/* Information about fcaps increasing perms */
 #define AUDIT_CAPSET		1322	/* Record showing argument to sys_capset */
 #define AUDIT_MMAP		1323	/* Record showing descriptor and flags in mmap */
+#define AUDIT_NETFILTER_PKT	1324	/* Packets traversing netfilter chains */
 
 #define AUDIT_AVC		1400	/* SE Linux avc denial or grant */
 #define AUDIT_SELINUX_ERR	1401	/* Internal SE Linux Errors */
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 9d40eff..9f11fbc 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -9,6 +9,7 @@ header-y += nfnetlink_conntrack.h
 header-y += nfnetlink_log.h
 header-y += nfnetlink_queue.h
 header-y += x_tables.h
+header-y += xt_AUDIT.h
 header-y += xt_CHECKSUM.h
 header-y += xt_CLASSIFY.h
 header-y += xt_CONNMARK.h
diff --git a/include/linux/netfilter/xt_AUDIT.h b/include/linux/netfilter/xt_AUDIT.h
new file mode 100644
index 0000000..38751d2
--- /dev/null
+++ b/include/linux/netfilter/xt_AUDIT.h
@@ -0,0 +1,30 @@
+/*
+ * Header file for iptables xt_AUDIT target
+ *
+ * (C) 2010-2011 Thomas Graf <tgraf@redhat.com>
+ * (C) 2010-2011 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _XT_AUDIT_TARGET_H
+#define _XT_AUDIT_TARGET_H
+
+#include <linux/types.h>
+
+enum {
+	XT_AUDIT_TYPE_ACCEPT = 0,
+	XT_AUDIT_TYPE_DROP,
+	XT_AUDIT_TYPE_REJECT,
+	__XT_AUDIT_TYPE_MAX,
+};
+
+#define XT_AUDIT_TYPE_MAX (__XT_AUDIT_TYPE_MAX - 1)
+
+struct xt_audit_info {
+	__u8 type; /* XT_AUDIT_TYPE_* */
+};
+
+#endif /* _XT_AUDIT_TARGET_H */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 1b79353..93918f0 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -326,6 +326,16 @@ config NETFILTER_XT_CONNMARK
 
 comment "Xtables targets"
 
+config NETFILTER_XT_TARGET_AUDIT
+	tristate "AUDIT target support"
+	depends on AUDIT
+	depends on NETFILTER_ADVANCED
+	---help---
+	  This option adds a 'AUDIT' target, which can be used to create
+	  audit records for packets dropped/accepted.
+
+	  To compileit as a module, choose M here. If unsure, say N.
+
 config NETFILTER_XT_TARGET_CHECKSUM
 	tristate "CHECKSUM target support"
 	depends on IP_NF_MANGLE || IP6_NF_MANGLE
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 441050f..401d574 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -45,6 +45,7 @@ obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o
 obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o
 
 # targets
+obj-$(CONFIG_NETFILTER_XT_TARGET_AUDIT) += xt_AUDIT.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CHECKSUM) += xt_CHECKSUM.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o
diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c
new file mode 100644
index 0000000..81802d2
--- /dev/null
+++ b/net/netfilter/xt_AUDIT.c
@@ -0,0 +1,204 @@
+/*
+ * Creates audit record for dropped/accepted packets
+ *
+ * (C) 2010-2011 Thomas Graf <tgraf@redhat.com>
+ * (C) 2010-2011 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/audit.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/if_arp.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_AUDIT.h>
+#include <net/ipv6.h>
+#include <net/ip.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Thomas Graf <tgraf@redhat.com>");
+MODULE_DESCRIPTION("Xtables: creates audit records for dropped/accepted packets");
+MODULE_ALIAS("ipt_AUDIT");
+MODULE_ALIAS("ip6t_AUDIT");
+MODULE_ALIAS("ebt_AUDIT");
+MODULE_ALIAS("arpt_AUDIT");
+
+static void audit_proto(struct audit_buffer *ab, struct sk_buff *skb,
+			unsigned int proto, unsigned int offset)
+{
+	switch (proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE: {
+		const __be16 *pptr;
+		__be16 _ports[2];
+
+		pptr = skb_header_pointer(skb, offset, sizeof(_ports), _ports);
+		if (pptr == NULL) {
+			audit_log_format(ab, " truncated=1");
+			return;
+		}
+
+		audit_log_format(ab, " sport=%hu dport=%hu",
+				 ntohs(pptr[0]), ntohs(pptr[1]));
+		}
+		break;
+
+	case IPPROTO_ICMP:
+	case IPPROTO_ICMPV6: {
+		const u8 *iptr;
+		u8 _ih[2];
+
+		iptr = skb_header_pointer(skb, offset, sizeof(_ih), &_ih);
+		if (iptr == NULL) {
+			audit_log_format(ab, " truncated=1");
+			return;
+		}
+
+		audit_log_format(ab, " icmptype=%hhu icmpcode=%hhu",
+				 iptr[0], iptr[1]);
+
+		}
+		break;
+	}
+}
+
+static void audit_ip4(struct audit_buffer *ab, struct sk_buff *skb)
+{
+	struct iphdr _iph;
+	const struct iphdr *ih;
+
+	ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
+	if (!ih) {
+		audit_log_format(ab, " truncated=1");
+		return;
+	}
+
+	audit_log_format(ab, " saddr=%pI4 daddr=%pI4 ipid=%hu proto=%hhu",
+		&ih->saddr, &ih->daddr, ntohs(ih->id), ih->protocol);
+
+	if (ntohs(ih->frag_off) & IP_OFFSET) {
+		audit_log_format(ab, " frag=1");
+		return;
+	}
+
+	audit_proto(ab, skb, ih->protocol, ih->ihl * 4);
+}
+
+static void audit_ip6(struct audit_buffer *ab, struct sk_buff *skb)
+{
+	struct ipv6hdr _ip6h;
+	const struct ipv6hdr *ih;
+	u8 nexthdr;
+	int offset;
+
+	ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_ip6h), &_ip6h);
+	if (!ih) {
+		audit_log_format(ab, " truncated=1");
+		return;
+	}
+
+	nexthdr = ih->nexthdr;
+	offset = ipv6_skip_exthdr(skb, skb_network_offset(skb) + sizeof(_ip6h),
+				  &nexthdr);
+
+	audit_log_format(ab, " saddr=%pI6c daddr=%pI6c proto=%hhu",
+			 &ih->saddr, &ih->daddr, nexthdr);
+
+	if (offset)
+		audit_proto(ab, skb, nexthdr, offset);
+}
+
+static unsigned int
+audit_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct xt_audit_info *info = par->targinfo;
+	struct audit_buffer *ab;
+
+	ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT);
+	if (ab == NULL)
+		goto errout;
+
+	audit_log_format(ab, "action=%hhu hook=%u len=%u inif=%s outif=%s",
+			 info->type, par->hooknum, skb->len,
+			 par->in ? par->in->name : "?",
+			 par->out ? par->out->name : "?");
+
+	if (skb->mark)
+		audit_log_format(ab, " mark=%#x", skb->mark);
+
+	if (skb->dev && skb->dev->type == ARPHRD_ETHER) {
+		audit_log_format(ab, " smac=%pM dmac=%pM macproto=0x%04x",
+				 eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
+				 ntohs(eth_hdr(skb)->h_proto));
+
+		if (par->family == NFPROTO_BRIDGE) {
+			switch (eth_hdr(skb)->h_proto) {
+			case __constant_htons(ETH_P_IP):
+				audit_ip4(ab, skb);
+				break;
+
+			case __constant_htons(ETH_P_IPV6):
+				audit_ip6(ab, skb);
+				break;
+			}
+		}
+	}
+
+	switch (par->family) {
+	case NFPROTO_IPV4:
+		audit_ip4(ab, skb);
+		break;
+
+	case NFPROTO_IPV6:
+		audit_ip6(ab, skb);
+		break;
+	}
+
+	audit_log_end(ab);
+
+errout:
+	return XT_CONTINUE;
+}
+
+static int audit_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct xt_audit_info *info = par->targinfo;
+
+	if (info->type > XT_AUDIT_TYPE_MAX) {
+		pr_info("Audit type out of range (valid range: 0..%hhu)\n",
+			XT_AUDIT_TYPE_MAX);
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+static struct xt_target audit_tg_reg __read_mostly = {
+	.name		= "AUDIT",
+	.family		= NFPROTO_UNSPEC,
+	.target		= audit_tg,
+	.targetsize	= sizeof(struct xt_audit_info),
+	.checkentry	= audit_tg_check,
+	.me		= THIS_MODULE,
+};
+
+static int __init audit_tg_init(void)
+{
+	return xt_register_target(&audit_tg_reg);
+}
+
+static void __exit audit_tg_exit(void)
+{
+	xt_unregister_target(&audit_tg_reg);
+}
+
+module_init(audit_tg_init);
+module_exit(audit_tg_exit);
-- 
1.7.2.3

[PATCH 63/79] netfilter: create audit records for x_tables replaces

[kaber]

From: Thomas Graf <tgraf@infradead.org>

The setsockopt() syscall to replace tables is already recorded
in the audit logs. This patch stores additional information
such as table name and netfilter protocol.

Cc: Patrick McHardy <kaber@trash.net>
Cc: Eric Paris <eparis@parisplace.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Thomas Graf <tgraf@redhat.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/audit.h    |    1 +
 net/netfilter/x_tables.c |   16 ++++++++++++++++
 2 files changed, 17 insertions(+), 0 deletions(-)

diff --git a/include/linux/audit.h b/include/linux/audit.h
index ae227df..32b5c62 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -104,6 +104,7 @@
 #define AUDIT_CAPSET		1322	/* Record showing argument to sys_capset */
 #define AUDIT_MMAP		1323	/* Record showing descriptor and flags in mmap */
 #define AUDIT_NETFILTER_PKT	1324	/* Packets traversing netfilter chains */
+#define AUDIT_NETFILTER_CFG	1325	/* Netfilter chain modifications */
 
 #define AUDIT_AVC		1400	/* SE Linux avc denial or grant */
 #define AUDIT_SELINUX_ERR	1401	/* Internal SE Linux Errors */
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index ee5de3a..fbc2b72 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -23,6 +23,7 @@
 #include <linux/mutex.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/audit.h>
 #include <net/net_namespace.h>
 
 #include <linux/netfilter/x_tables.h>
@@ -834,6 +835,21 @@ xt_replace_table(struct xt_table *table,
 	 */
 	local_bh_enable();
 
+#ifdef CONFIG_AUDIT
+	if (audit_enabled) {
+		struct audit_buffer *ab;
+
+		ab = audit_log_start(current->audit_context, GFP_KERNEL,
+				     AUDIT_NETFILTER_CFG);
+		if (ab) {
+			audit_log_format(ab, "table=%s family=%u entries=%u",
+					 table->name, table->af,
+					 private->number);
+			audit_log_end(ab);
+		}
+	}
+#endif
+
 	return private;
 }
 EXPORT_SYMBOL_GPL(xt_replace_table);
-- 
1.7.2.3

[PATCH 64/79] netfilter: xtables: add missing aliases for autoloading via iptables

[kaber]

From: Jan Engelhardt <jengelh@medozas.de>

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 net/netfilter/xt_IDLETIMER.c |    2 ++
 net/netfilter/xt_LED.c       |    2 ++
 net/netfilter/xt_cpu.c       |    2 ++
 3 files changed, 6 insertions(+), 0 deletions(-)

diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index be1f22e..3bdd443 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -313,3 +313,5 @@ MODULE_AUTHOR("Timo Teras <ext-timo.teras@nokia.com>");
 MODULE_AUTHOR("Luciano Coelho <luciano.coelho@nokia.com>");
 MODULE_DESCRIPTION("Xtables: idle time monitor");
 MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("ipt_IDLETIMER");
+MODULE_ALIAS("ip6t_IDLETIMER");
diff --git a/net/netfilter/xt_LED.c b/net/netfilter/xt_LED.c
index a414050..993de2b 100644
--- a/net/netfilter/xt_LED.c
+++ b/net/netfilter/xt_LED.c
@@ -31,6 +31,8 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adam Nielsen <a.nielsen@shikadi.net>");
 MODULE_DESCRIPTION("Xtables: trigger LED devices on packet match");
+MODULE_ALIAS("ipt_LED");
+MODULE_ALIAS("ip6t_LED");
 
 static LIST_HEAD(xt_led_triggers);
 static DEFINE_MUTEX(xt_led_mutex);
diff --git a/net/netfilter/xt_cpu.c b/net/netfilter/xt_cpu.c
index b39db8a..c7a2e54 100644
--- a/net/netfilter/xt_cpu.c
+++ b/net/netfilter/xt_cpu.c
@@ -22,6 +22,8 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Eric Dumazet <eric.dumazet@gmail.com>");
 MODULE_DESCRIPTION("Xtables: CPU match");
+MODULE_ALIAS("ipt_cpu");
+MODULE_ALIAS("ip6t_cpu");
 
 static int cpu_mt_check(const struct xt_mtchk_param *par)
 {
-- 
1.7.2.3

[PATCH 65/79] audit: export symbol for use with xt_AUDIT

[kaber]

From: Jan Engelhardt <jengelh@medozas.de>

When xt_AUDIT is built as a module, modpost reports a problem.

	MODPOST 322 modules
	ERROR: "audit_enabled" [net/netfilter/x_tables.ko] undefined!
	WARNING: modpost: Found 1 section mismatch(es).

Cc: Thomas Graf <tgraf@redhat.com>
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 kernel/audit.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/kernel/audit.c b/kernel/audit.c
index 77770a0..5842f65 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -74,6 +74,8 @@ static int	audit_initialized;
 int		audit_enabled;
 int		audit_ever_enabled;
 
+EXPORT_SYMBOL_GPL(audit_enabled);
+
 /* Default state when kernel boots without any parameters. */
 static int	audit_default;
 
-- 
1.7.2.3

[PATCH 66/79] netfilter: xt_connlimit: use hotdrop jump mark

[kaber]

From: Richard Weinberger <richard@nod.at>

Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 net/netfilter/xt_connlimit.c |    6 ++----
 1 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index 5c5b6b9..452bc16 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -204,11 +204,9 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	                         &info->mask, par->family);
 	spin_unlock_bh(&info->data->lock);
 
-	if (connections < 0) {
+	if (connections < 0)
 		/* kmalloc failed, drop it entirely */
-		par->hotdrop = true;
-		return false;
-	}
+		goto hotdrop;
 
 	return (connections > info->limit) ^ info->inverse;
 
-- 
1.7.2.3

[PATCH 67/79] netfilter: xtables: use __uXX guarded types for userspace exports

[kaber]

From: Jan Engelhardt <jengelh@medozas.de>

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 include/linux/netfilter_bridge/ebt_802_3.h     |   24 ++++++++++++------------
 include/linux/netfilter_bridge/ebt_among.h     |    2 +-
 include/linux/netfilter_bridge/ebt_arp.h       |    4 ++--
 include/linux/netfilter_bridge/ebt_ip.h        |   12 ++++++------
 include/linux/netfilter_bridge/ebt_ip6.h       |   16 ++++++++--------
 include/linux/netfilter_bridge/ebt_limit.h     |    8 ++++----
 include/linux/netfilter_bridge/ebt_log.h       |    6 +++---
 include/linux/netfilter_bridge/ebt_mark_m.h    |    4 ++--
 include/linux/netfilter_bridge/ebt_nflog.h     |   10 +++++-----
 include/linux/netfilter_bridge/ebt_pkttype.h   |    4 ++--
 include/linux/netfilter_bridge/ebt_stp.h       |   24 ++++++++++++------------
 include/linux/netfilter_bridge/ebt_ulog.h      |    2 +-
 include/linux/netfilter_bridge/ebt_vlan.h      |    8 ++++----
 include/linux/netfilter_ipv4/ipt_CLUSTERIP.h   |   14 +++++++-------
 include/linux/netfilter_ipv4/ipt_ECN.h         |    6 +++---
 include/linux/netfilter_ipv4/ipt_SAME.h        |    6 +++---
 include/linux/netfilter_ipv4/ipt_TTL.h         |    4 ++--
 include/linux/netfilter_ipv4/ipt_addrtype.h    |   14 +++++++-------
 include/linux/netfilter_ipv4/ipt_ah.h          |    4 ++--
 include/linux/netfilter_ipv4/ipt_ecn.h         |    8 ++++----
 include/linux/netfilter_ipv4/ipt_ttl.h         |    4 ++--
 include/linux/netfilter_ipv6/ip6t_HL.h         |    4 ++--
 include/linux/netfilter_ipv6/ip6t_REJECT.h     |    2 +-
 include/linux/netfilter_ipv6/ip6t_ah.h         |    8 ++++----
 include/linux/netfilter_ipv6/ip6t_frag.h       |    8 ++++----
 include/linux/netfilter_ipv6/ip6t_hl.h         |    4 ++--
 include/linux/netfilter_ipv6/ip6t_ipv6header.h |    6 +++---
 include/linux/netfilter_ipv6/ip6t_mh.h         |    4 ++--
 include/linux/netfilter_ipv6/ip6t_opts.h       |   10 +++++-----
 include/linux/netfilter_ipv6/ip6t_rt.h         |   12 ++++++------
 30 files changed, 121 insertions(+), 121 deletions(-)

diff --git a/include/linux/netfilter_bridge/ebt_802_3.h b/include/linux/netfilter_bridge/ebt_802_3.h
index c73ef0b..c427764 100644
--- a/include/linux/netfilter_bridge/ebt_802_3.h
+++ b/include/linux/netfilter_bridge/ebt_802_3.h
@@ -24,24 +24,24 @@
 
 /* ui has one byte ctrl, ni has two */
 struct hdr_ui {
-	uint8_t dsap;
-	uint8_t ssap;
-	uint8_t ctrl;
-	uint8_t orig[3];
+	__u8 dsap;
+	__u8 ssap;
+	__u8 ctrl;
+	__u8 orig[3];
 	__be16 type;
 };
 
 struct hdr_ni {
-	uint8_t dsap;
-	uint8_t ssap;
+	__u8 dsap;
+	__u8 ssap;
 	__be16 ctrl;
-	uint8_t  orig[3];
+	__u8  orig[3];
 	__be16 type;
 };
 
 struct ebt_802_3_hdr {
-	uint8_t  daddr[6];
-	uint8_t  saddr[6];
+	__u8  daddr[6];
+	__u8  saddr[6];
 	__be16 len;
 	union {
 		struct hdr_ui ui;
@@ -59,10 +59,10 @@ static inline struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb)
 #endif
 
 struct ebt_802_3_info {
-	uint8_t  sap;
+	__u8  sap;
 	__be16 type;
-	uint8_t  bitmask;
-	uint8_t  invflags;
+	__u8  bitmask;
+	__u8  invflags;
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_among.h b/include/linux/netfilter_bridge/ebt_among.h
index 0009558..686c961 100644
--- a/include/linux/netfilter_bridge/ebt_among.h
+++ b/include/linux/netfilter_bridge/ebt_among.h
@@ -30,7 +30,7 @@
  */
 
 struct ebt_mac_wormhash_tuple {
-	uint32_t cmp[2];
+	__u32 cmp[2];
 	__be32 ip;
 };
 
diff --git a/include/linux/netfilter_bridge/ebt_arp.h b/include/linux/netfilter_bridge/ebt_arp.h
index cbf4843..e62b5af 100644
--- a/include/linux/netfilter_bridge/ebt_arp.h
+++ b/include/linux/netfilter_bridge/ebt_arp.h
@@ -27,8 +27,8 @@ struct ebt_arp_info
 	unsigned char smmsk[ETH_ALEN];
 	unsigned char dmaddr[ETH_ALEN];
 	unsigned char dmmsk[ETH_ALEN];
-	uint8_t  bitmask;
-	uint8_t  invflags;
+	__u8  bitmask;
+	__u8  invflags;
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_ip.h b/include/linux/netfilter_bridge/ebt_ip.h
index 6a708fb..d99de58 100644
--- a/include/linux/netfilter_bridge/ebt_ip.h
+++ b/include/linux/netfilter_bridge/ebt_ip.h
@@ -31,12 +31,12 @@ struct ebt_ip_info {
 	__be32 daddr;
 	__be32 smsk;
 	__be32 dmsk;
-	uint8_t  tos;
-	uint8_t  protocol;
-	uint8_t  bitmask;
-	uint8_t  invflags;
-	uint16_t sport[2];
-	uint16_t dport[2];
+	__u8  tos;
+	__u8  protocol;
+	__u8  bitmask;
+	__u8  invflags;
+	__u16 sport[2];
+	__u16 dport[2];
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_ip6.h b/include/linux/netfilter_bridge/ebt_ip6.h
index 22af18a..998e9d5 100644
--- a/include/linux/netfilter_bridge/ebt_ip6.h
+++ b/include/linux/netfilter_bridge/ebt_ip6.h
@@ -31,17 +31,17 @@ struct ebt_ip6_info {
 	struct in6_addr daddr;
 	struct in6_addr smsk;
 	struct in6_addr dmsk;
-	uint8_t  tclass;
-	uint8_t  protocol;
-	uint8_t  bitmask;
-	uint8_t  invflags;
+	__u8  tclass;
+	__u8  protocol;
+	__u8  bitmask;
+	__u8  invflags;
 	union {
-		uint16_t sport[2];
-		uint8_t icmpv6_type[2];
+		__u16 sport[2];
+		__u8 icmpv6_type[2];
 	};
 	union {
-		uint16_t dport[2];
-		uint8_t icmpv6_code[2];
+		__u16 dport[2];
+		__u8 icmpv6_code[2];
 	};
 };
 
diff --git a/include/linux/netfilter_bridge/ebt_limit.h b/include/linux/netfilter_bridge/ebt_limit.h
index 4bf76b7..721d51f 100644
--- a/include/linux/netfilter_bridge/ebt_limit.h
+++ b/include/linux/netfilter_bridge/ebt_limit.h
@@ -10,13 +10,13 @@
    seconds, or one every 59 hours. */
 
 struct ebt_limit_info {
-	u_int32_t avg;    /* Average secs between packets * scale */
-	u_int32_t burst;  /* Period multiplier for upper limit. */
+	__u32 avg;    /* Average secs between packets * scale */
+	__u32 burst;  /* Period multiplier for upper limit. */
 
 	/* Used internally by the kernel */
 	unsigned long prev;
-	u_int32_t credit;
-	u_int32_t credit_cap, cost;
+	__u32 credit;
+	__u32 credit_cap, cost;
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_log.h b/include/linux/netfilter_bridge/ebt_log.h
index cc2cdfb..564beb4 100644
--- a/include/linux/netfilter_bridge/ebt_log.h
+++ b/include/linux/netfilter_bridge/ebt_log.h
@@ -10,9 +10,9 @@
 #define EBT_LOG_WATCHER "log"
 
 struct ebt_log_info {
-	uint8_t loglevel;
-	uint8_t prefix[EBT_LOG_PREFIX_SIZE];
-	uint32_t bitmask;
+	__u8 loglevel;
+	__u8 prefix[EBT_LOG_PREFIX_SIZE];
+	__u32 bitmask;
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_mark_m.h b/include/linux/netfilter_bridge/ebt_mark_m.h
index 9ceb10e..97b96c4 100644
--- a/include/linux/netfilter_bridge/ebt_mark_m.h
+++ b/include/linux/netfilter_bridge/ebt_mark_m.h
@@ -6,8 +6,8 @@
 #define EBT_MARK_MASK (EBT_MARK_AND | EBT_MARK_OR)
 struct ebt_mark_m_info {
 	unsigned long mark, mask;
-	uint8_t invert;
-	uint8_t bitmask;
+	__u8 invert;
+	__u8 bitmask;
 };
 #define EBT_MARK_MATCH "mark_m"
 
diff --git a/include/linux/netfilter_bridge/ebt_nflog.h b/include/linux/netfilter_bridge/ebt_nflog.h
index 0528178..477315b 100644
--- a/include/linux/netfilter_bridge/ebt_nflog.h
+++ b/include/linux/netfilter_bridge/ebt_nflog.h
@@ -10,11 +10,11 @@
 #define EBT_NFLOG_DEFAULT_THRESHOLD	1
 
 struct ebt_nflog_info {
-	u_int32_t len;
-	u_int16_t group;
-	u_int16_t threshold;
-	u_int16_t flags;
-	u_int16_t pad;
+	__u32 len;
+	__u16 group;
+	__u16 threshold;
+	__u16 flags;
+	__u16 pad;
 	char prefix[EBT_NFLOG_PREFIX_SIZE];
 };
 
diff --git a/include/linux/netfilter_bridge/ebt_pkttype.h b/include/linux/netfilter_bridge/ebt_pkttype.h
index 51a7998..7c0fb0f 100644
--- a/include/linux/netfilter_bridge/ebt_pkttype.h
+++ b/include/linux/netfilter_bridge/ebt_pkttype.h
@@ -2,8 +2,8 @@
 #define __LINUX_BRIDGE_EBT_PKTTYPE_H
 
 struct ebt_pkttype_info {
-	uint8_t pkt_type;
-	uint8_t invert;
+	__u8 pkt_type;
+	__u8 invert;
 };
 #define EBT_PKTTYPE_MATCH "pkttype"
 
diff --git a/include/linux/netfilter_bridge/ebt_stp.h b/include/linux/netfilter_bridge/ebt_stp.h
index e503a0a..13a0bd4 100644
--- a/include/linux/netfilter_bridge/ebt_stp.h
+++ b/include/linux/netfilter_bridge/ebt_stp.h
@@ -21,24 +21,24 @@
 #define EBT_STP_MATCH "stp"
 
 struct ebt_stp_config_info {
-	uint8_t flags;
-	uint16_t root_priol, root_priou;
+	__u8 flags;
+	__u16 root_priol, root_priou;
 	char root_addr[6], root_addrmsk[6];
-	uint32_t root_costl, root_costu;
-	uint16_t sender_priol, sender_priou;
+	__u32 root_costl, root_costu;
+	__u16 sender_priol, sender_priou;
 	char sender_addr[6], sender_addrmsk[6];
-	uint16_t portl, portu;
-	uint16_t msg_agel, msg_ageu;
-	uint16_t max_agel, max_ageu;
-	uint16_t hello_timel, hello_timeu;
-	uint16_t forward_delayl, forward_delayu;
+	__u16 portl, portu;
+	__u16 msg_agel, msg_ageu;
+	__u16 max_agel, max_ageu;
+	__u16 hello_timel, hello_timeu;
+	__u16 forward_delayl, forward_delayu;
 };
 
 struct ebt_stp_info {
-	uint8_t type;
+	__u8 type;
 	struct ebt_stp_config_info config;
-	uint16_t bitmask;
-	uint16_t invflags;
+	__u16 bitmask;
+	__u16 invflags;
 };
 
 #endif
diff --git a/include/linux/netfilter_bridge/ebt_ulog.h b/include/linux/netfilter_bridge/ebt_ulog.h
index b677e26..de35a51 100644
--- a/include/linux/netfilter_bridge/ebt_ulog.h
+++ b/include/linux/netfilter_bridge/ebt_ulog.h
@@ -10,7 +10,7 @@
 #define EBT_ULOG_VERSION 1
 
 struct ebt_ulog_info {
-	uint32_t nlgroup;
+	__u32 nlgroup;
 	unsigned int cprange;
 	unsigned int qthreshold;
 	char prefix[EBT_ULOG_PREFIX_LEN];
diff --git a/include/linux/netfilter_bridge/ebt_vlan.h b/include/linux/netfilter_bridge/ebt_vlan.h
index 1d98be4..48dffc1 100644
--- a/include/linux/netfilter_bridge/ebt_vlan.h
+++ b/include/linux/netfilter_bridge/ebt_vlan.h
@@ -8,12 +8,12 @@
 #define EBT_VLAN_MATCH "vlan"
 
 struct ebt_vlan_info {
-	uint16_t id;		/* VLAN ID {1-4095} */
-	uint8_t prio;		/* VLAN User Priority {0-7} */
+	__u16 id;		/* VLAN ID {1-4095} */
+	__u8 prio;		/* VLAN User Priority {0-7} */
 	__be16 encap;		/* VLAN Encapsulated frame code {0-65535} */
-	uint8_t bitmask;		/* Args bitmask bit 1=1 - ID arg,
+	__u8 bitmask;		/* Args bitmask bit 1=1 - ID arg,
 				   bit 2=1 User-Priority arg, bit 3=1 encap*/
-	uint8_t invflags;		/* Inverse bitmask  bit 1=1 - inversed ID arg, 
+	__u8 invflags;		/* Inverse bitmask  bit 1=1 - inversed ID arg, 
 				   bit 2=1 - inversed Pirority arg */
 };
 
diff --git a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h
index e5a3687..3114f06 100644
--- a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h
+++ b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h
@@ -17,15 +17,15 @@ struct clusterip_config;
 
 struct ipt_clusterip_tgt_info {
 
-	u_int32_t flags;
+	__u32 flags;
 
 	/* only relevant for new ones */
-	u_int8_t clustermac[6];
-	u_int16_t num_total_nodes;
-	u_int16_t num_local_nodes;
-	u_int16_t local_nodes[CLUSTERIP_MAX_NODES];
-	u_int32_t hash_mode;
-	u_int32_t hash_initval;
+	__u8 clustermac[6];
+	__u16 num_total_nodes;
+	__u16 num_local_nodes;
+	__u16 local_nodes[CLUSTERIP_MAX_NODES];
+	__u32 hash_mode;
+	__u32 hash_initval;
 
 	/* Used internally by the kernel */
 	struct clusterip_config *config;
diff --git a/include/linux/netfilter_ipv4/ipt_ECN.h b/include/linux/netfilter_ipv4/ipt_ECN.h
index 7ca4591..c6e3e01 100644
--- a/include/linux/netfilter_ipv4/ipt_ECN.h
+++ b/include/linux/netfilter_ipv4/ipt_ECN.h
@@ -19,11 +19,11 @@
 #define IPT_ECN_OP_MASK		0xce
 
 struct ipt_ECN_info {
-	u_int8_t operation;	/* bitset of operations */
-	u_int8_t ip_ect;	/* ECT codepoint of IPv4 header, pre-shifted */
+	__u8 operation;	/* bitset of operations */
+	__u8 ip_ect;	/* ECT codepoint of IPv4 header, pre-shifted */
 	union {
 		struct {
-			u_int8_t ece:1, cwr:1; /* TCP ECT bits */
+			__u8 ece:1, cwr:1; /* TCP ECT bits */
 		} tcp;
 	} proto;
 };
diff --git a/include/linux/netfilter_ipv4/ipt_SAME.h b/include/linux/netfilter_ipv4/ipt_SAME.h
index 2529660..fa0ebec 100644
--- a/include/linux/netfilter_ipv4/ipt_SAME.h
+++ b/include/linux/netfilter_ipv4/ipt_SAME.h
@@ -7,9 +7,9 @@
 
 struct ipt_same_info {
 	unsigned char info;
-	u_int32_t rangesize;
-	u_int32_t ipnum;
-	u_int32_t *iparray;
+	__u32 rangesize;
+	__u32 ipnum;
+	__u32 *iparray;
 
 	/* hangs off end. */
 	struct nf_nat_range range[IPT_SAME_MAX_RANGE];
diff --git a/include/linux/netfilter_ipv4/ipt_TTL.h b/include/linux/netfilter_ipv4/ipt_TTL.h
index ee6611e..f6250e4 100644
--- a/include/linux/netfilter_ipv4/ipt_TTL.h
+++ b/include/linux/netfilter_ipv4/ipt_TTL.h
@@ -13,8 +13,8 @@ enum {
 #define IPT_TTL_MAXMODE	IPT_TTL_DEC
 
 struct ipt_TTL_info {
-	u_int8_t	mode;
-	u_int8_t	ttl;
+	__u8	mode;
+	__u8	ttl;
 };
 
 
diff --git a/include/linux/netfilter_ipv4/ipt_addrtype.h b/include/linux/netfilter_ipv4/ipt_addrtype.h
index 446de6a..f29c3cf 100644
--- a/include/linux/netfilter_ipv4/ipt_addrtype.h
+++ b/include/linux/netfilter_ipv4/ipt_addrtype.h
@@ -9,17 +9,17 @@ enum {
 };
 
 struct ipt_addrtype_info_v1 {
-	u_int16_t	source;		/* source-type mask */
-	u_int16_t	dest;		/* dest-type mask */
-	u_int32_t	flags;
+	__u16	source;		/* source-type mask */
+	__u16	dest;		/* dest-type mask */
+	__u32	flags;
 };
 
 /* revision 0 */
 struct ipt_addrtype_info {
-	u_int16_t	source;		/* source-type mask */
-	u_int16_t	dest;		/* dest-type mask */
-	u_int32_t	invert_source;
-	u_int32_t	invert_dest;
+	__u16	source;		/* source-type mask */
+	__u16	dest;		/* dest-type mask */
+	__u32	invert_source;
+	__u32	invert_dest;
 };
 
 #endif
diff --git a/include/linux/netfilter_ipv4/ipt_ah.h b/include/linux/netfilter_ipv4/ipt_ah.h
index 2e555b4..8fea283 100644
--- a/include/linux/netfilter_ipv4/ipt_ah.h
+++ b/include/linux/netfilter_ipv4/ipt_ah.h
@@ -2,8 +2,8 @@
 #define _IPT_AH_H
 
 struct ipt_ah {
-	u_int32_t spis[2];			/* Security Parameter Index */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 spis[2];			/* Security Parameter Index */
+	__u8  invflags;			/* Inverse flags */
 };
 
 
diff --git a/include/linux/netfilter_ipv4/ipt_ecn.h b/include/linux/netfilter_ipv4/ipt_ecn.h
index 9945baa..78b98aa 100644
--- a/include/linux/netfilter_ipv4/ipt_ecn.h
+++ b/include/linux/netfilter_ipv4/ipt_ecn.h
@@ -20,12 +20,12 @@
 
 /* match info */
 struct ipt_ecn_info {
-	u_int8_t operation;
-	u_int8_t invert;
-	u_int8_t ip_ect;
+	__u8 operation;
+	__u8 invert;
+	__u8 ip_ect;
 	union {
 		struct {
-			u_int8_t ect;
+			__u8 ect;
 		} tcp;
 	} proto;
 };
diff --git a/include/linux/netfilter_ipv4/ipt_ttl.h b/include/linux/netfilter_ipv4/ipt_ttl.h
index ee24fd8..93d9a06 100644
--- a/include/linux/netfilter_ipv4/ipt_ttl.h
+++ b/include/linux/netfilter_ipv4/ipt_ttl.h
@@ -13,8 +13,8 @@ enum {
 
 
 struct ipt_ttl_info {
-	u_int8_t	mode;
-	u_int8_t	ttl;
+	__u8	mode;
+	__u8	ttl;
 };
 
 
diff --git a/include/linux/netfilter_ipv6/ip6t_HL.h b/include/linux/netfilter_ipv6/ip6t_HL.h
index afb7813..81cdaf0 100644
--- a/include/linux/netfilter_ipv6/ip6t_HL.h
+++ b/include/linux/netfilter_ipv6/ip6t_HL.h
@@ -14,8 +14,8 @@ enum {
 #define IP6T_HL_MAXMODE	IP6T_HL_DEC
 
 struct ip6t_HL_info {
-	u_int8_t	mode;
-	u_int8_t	hop_limit;
+	__u8	mode;
+	__u8	hop_limit;
 };
 
 
diff --git a/include/linux/netfilter_ipv6/ip6t_REJECT.h b/include/linux/netfilter_ipv6/ip6t_REJECT.h
index 6be6504..b999aa4 100644
--- a/include/linux/netfilter_ipv6/ip6t_REJECT.h
+++ b/include/linux/netfilter_ipv6/ip6t_REJECT.h
@@ -12,7 +12,7 @@ enum ip6t_reject_with {
 };
 
 struct ip6t_reject_info {
-	u_int32_t	with;	/* reject type */
+	__u32	with;	/* reject type */
 };
 
 #endif /*_IP6T_REJECT_H*/
diff --git a/include/linux/netfilter_ipv6/ip6t_ah.h b/include/linux/netfilter_ipv6/ip6t_ah.h
index 17a745c..a602c16 100644
--- a/include/linux/netfilter_ipv6/ip6t_ah.h
+++ b/include/linux/netfilter_ipv6/ip6t_ah.h
@@ -2,10 +2,10 @@
 #define _IP6T_AH_H
 
 struct ip6t_ah {
-	u_int32_t spis[2];			/* Security Parameter Index */
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t  hdrres;			/* Test of the Reserved Filed */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 spis[2];			/* Security Parameter Index */
+	__u32 hdrlen;			/* Header Length */
+	__u8  hdrres;			/* Test of the Reserved Filed */
+	__u8  invflags;			/* Inverse flags */
 };
 
 #define IP6T_AH_SPI 0x01
diff --git a/include/linux/netfilter_ipv6/ip6t_frag.h b/include/linux/netfilter_ipv6/ip6t_frag.h
index 3724d08..538b31e 100644
--- a/include/linux/netfilter_ipv6/ip6t_frag.h
+++ b/include/linux/netfilter_ipv6/ip6t_frag.h
@@ -2,10 +2,10 @@
 #define _IP6T_FRAG_H
 
 struct ip6t_frag {
-	u_int32_t ids[2];			/* Security Parameter Index */
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t  flags;			/*  */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 ids[2];			/* Security Parameter Index */
+	__u32 hdrlen;			/* Header Length */
+	__u8  flags;			/*  */
+	__u8  invflags;			/* Inverse flags */
 };
 
 #define IP6T_FRAG_IDS 		0x01
diff --git a/include/linux/netfilter_ipv6/ip6t_hl.h b/include/linux/netfilter_ipv6/ip6t_hl.h
index 5ef91b8..c6fddcb 100644
--- a/include/linux/netfilter_ipv6/ip6t_hl.h
+++ b/include/linux/netfilter_ipv6/ip6t_hl.h
@@ -14,8 +14,8 @@ enum {
 
 
 struct ip6t_hl_info {
-	u_int8_t	mode;
-	u_int8_t	hop_limit;
+	__u8	mode;
+	__u8	hop_limit;
 };
 
 
diff --git a/include/linux/netfilter_ipv6/ip6t_ipv6header.h b/include/linux/netfilter_ipv6/ip6t_ipv6header.h
index 01dfd44..73d53bd 100644
--- a/include/linux/netfilter_ipv6/ip6t_ipv6header.h
+++ b/include/linux/netfilter_ipv6/ip6t_ipv6header.h
@@ -9,9 +9,9 @@ on whether they contain certain headers */
 #define __IPV6HEADER_H
 
 struct ip6t_ipv6header_info {
-	u_int8_t matchflags;
-	u_int8_t invflags;
-	u_int8_t modeflag;
+	__u8 matchflags;
+	__u8 invflags;
+	__u8 modeflag;
 };
 
 #define MASK_HOPOPTS    128
diff --git a/include/linux/netfilter_ipv6/ip6t_mh.h b/include/linux/netfilter_ipv6/ip6t_mh.h
index 18549bc..98c8cf6 100644
--- a/include/linux/netfilter_ipv6/ip6t_mh.h
+++ b/include/linux/netfilter_ipv6/ip6t_mh.h
@@ -3,8 +3,8 @@
 
 /* MH matching stuff */
 struct ip6t_mh {
-	u_int8_t types[2];	/* MH type range */
-	u_int8_t invflags;	/* Inverse flags */
+	__u8 types[2];	/* MH type range */
+	__u8 invflags;	/* Inverse flags */
 };
 
 /* Values for "invflags" field in struct ip6t_mh. */
diff --git a/include/linux/netfilter_ipv6/ip6t_opts.h b/include/linux/netfilter_ipv6/ip6t_opts.h
index 62d89bc..405d309 100644
--- a/include/linux/netfilter_ipv6/ip6t_opts.h
+++ b/include/linux/netfilter_ipv6/ip6t_opts.h
@@ -4,11 +4,11 @@
 #define IP6T_OPTS_OPTSNR 16
 
 struct ip6t_opts {
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t flags;				/*  */
-	u_int8_t invflags;			/* Inverse flags */
-	u_int16_t opts[IP6T_OPTS_OPTSNR];	/* opts */
-	u_int8_t optsnr;			/* Nr of OPts */
+	__u32 hdrlen;			/* Header Length */
+	__u8 flags;				/*  */
+	__u8 invflags;			/* Inverse flags */
+	__u16 opts[IP6T_OPTS_OPTSNR];	/* opts */
+	__u8 optsnr;			/* Nr of OPts */
 };
 
 #define IP6T_OPTS_LEN 		0x01
diff --git a/include/linux/netfilter_ipv6/ip6t_rt.h b/include/linux/netfilter_ipv6/ip6t_rt.h
index ab91bfd..e8dad20 100644
--- a/include/linux/netfilter_ipv6/ip6t_rt.h
+++ b/include/linux/netfilter_ipv6/ip6t_rt.h
@@ -6,13 +6,13 @@
 #define IP6T_RT_HOPS 16
 
 struct ip6t_rt {
-	u_int32_t rt_type;			/* Routing Type */
-	u_int32_t segsleft[2];			/* Segments Left */
-	u_int32_t hdrlen;			/* Header Length */
-	u_int8_t  flags;			/*  */
-	u_int8_t  invflags;			/* Inverse flags */
+	__u32 rt_type;			/* Routing Type */
+	__u32 segsleft[2];			/* Segments Left */
+	__u32 hdrlen;			/* Header Length */
+	__u8  flags;			/*  */
+	__u8  invflags;			/* Inverse flags */
 	struct in6_addr addrs[IP6T_RT_HOPS];	/* Hops */
-	u_int8_t addrnr;			/* Nr of Addresses */
+	__u8 addrnr;			/* Nr of Addresses */
 };
 
 #define IP6T_RT_TYP 		0x01
-- 
1.7.2.3

[PATCH 68/79] netfilter: xtables: add missing header files to export list

[kaber]

From: Jan Engelhardt <jengelh@medozas.de>

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 include/linux/netfilter/Kbuild |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 9f11fbc..fc4e0aa 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -56,6 +56,8 @@ header-y += xt_rateest.h
 header-y += xt_realm.h
 header-y += xt_recent.h
 header-y += xt_sctp.h
+header-y += xt_secmark.h
+header-y += xt_socket.h
 header-y += xt_state.h
 header-y += xt_statistic.h
 header-y += xt_string.h
-- 
1.7.2.3

[PATCH 69/79] netfilter: nf_nat: fix conversion to non-atomic bit ops

[kaber]

From: Changli Gao <xiaosuo@gmail.com>

My previous patch (netfilter: nf_nat: don't use atomic bit operation)
made a mistake when converting atomic_set to a normal bit 'or'.
IPS_*_BIT should be replaced with IPS_*.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Cc: Tim Gardner <tim.gardner@canonical.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_nat_core.h |    4 ++--
 net/ipv4/netfilter/nf_nat_core.c    |    4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h
index 5aec85c..3dc7b98 100644
--- a/include/net/netfilter/nf_nat_core.h
+++ b/include/net/netfilter/nf_nat_core.h
@@ -21,9 +21,9 @@ static inline int nf_nat_initialized(struct nf_conn *ct,
 				     enum nf_nat_manip_type manip)
 {
 	if (manip == IP_NAT_MANIP_SRC)
-		return ct->status & IPS_SRC_NAT_DONE_BIT;
+		return ct->status & IPS_SRC_NAT_DONE;
 	else
-		return ct->status & IPS_DST_NAT_DONE_BIT;
+		return ct->status & IPS_DST_NAT_DONE;
 }
 
 struct nlattr;
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 6972cee..3002c04 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -323,9 +323,9 @@ nf_nat_setup_info(struct nf_conn *ct,
 
 	/* It's done. */
 	if (maniptype == IP_NAT_MANIP_DST)
-		ct->status |= IPS_DST_NAT_DONE_BIT;
+		ct->status |= IPS_DST_NAT_DONE;
 	else
-		ct->status |= IPS_SRC_NAT_DONE_BIT;
+		ct->status |= IPS_SRC_NAT_DONE;
 
 	return NF_ACCEPT;
 }
-- 
1.7.2.3

[PATCH 70/79] netfilter: nf_conntrack: remove an atomic bit operation

[kaber]

From: Changli Gao <xiaosuo@gmail.com>

As this ct won't be seen by the others, we don't need to set the
IPS_CONFIRMED_BIT in atomic way.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Cc: Tim Gardner <tim.gardner@canonical.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/nf_conntrack_core.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index dc2ff2c..f47ac67 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -486,7 +486,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	ct->timeout.expires += jiffies;
 	add_timer(&ct->timeout);
 	atomic_inc(&ct->ct_general.use);
-	set_bit(IPS_CONFIRMED_BIT, &ct->status);
+	ct->status |= IPS_CONFIRMED;
 
 	/* Since the lookup is lockless, hash insertion must be done after
 	 * starting the timer and setting the CONFIRMED bit. The RCU barriers
-- 
1.7.2.3

[PATCH 71/79] netfilter: Kconfig: NFQUEUE is useless without NETFILTER_NETLINK_QUEUE

[kaber]

From: Florian Westphal <fw@strlen.de>

NFLOG already does the same thing for NETFILTER_NETLINK_LOG.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/Kconfig |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 93918f0..e2480bd 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -487,6 +487,7 @@ config NETFILTER_XT_TARGET_NFLOG
 config NETFILTER_XT_TARGET_NFQUEUE
 	tristate '"NFQUEUE" target Support'
 	depends on NETFILTER_ADVANCED
+	select NETFILTER_NETLINK_QUEUE
 	help
 	  This target replaced the old obsolete QUEUE target.
 
-- 
1.7.2.3

[PATCH 72/79] netfilter: nfnetlink_queue: return error number to caller

[kaber]

From: Florian Westphal <fw@strlen.de>

instead of returning -1 on error, return an error number to allow the
caller to handle some errors differently.

ECANCELED is used to indicate that the hook is going away and should be
ignored.

A followup patch will introduce more 'ignore this hook' conditions,
(depending on queue settings) and will move kfree_skb responsibility
to the caller.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/core.c            |    6 +++-
 net/netfilter/nf_queue.c        |   44 +++++++++++++++++++++++++++-----------
 net/netfilter/nfnetlink_queue.c |   22 ++++++++++++-------
 3 files changed, 49 insertions(+), 23 deletions(-)

diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index e69d537..91d66d2f 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -179,9 +179,11 @@ next_hook:
 		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))
+		ret = nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
+			       verdict >> NF_VERDICT_BITS);
+		if (ret == -ECANCELED)
 			goto next_hook;
+		ret = 0;
 	}
 	rcu_read_unlock();
 	return ret;
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 1876f74..ad25c7e 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -125,7 +125,7 @@ static int __nf_queue(struct sk_buff *skb,
 		      int (*okfn)(struct sk_buff *),
 		      unsigned int queuenum)
 {
-	int status;
+	int status = -ENOENT;
 	struct nf_queue_entry *entry = NULL;
 #ifdef CONFIG_BRIDGE_NETFILTER
 	struct net_device *physindev;
@@ -146,8 +146,10 @@ static int __nf_queue(struct sk_buff *skb,
 		goto err_unlock;
 
 	entry = kmalloc(sizeof(*entry) + afinfo->route_key_size, GFP_ATOMIC);
-	if (!entry)
+	if (!entry) {
+		status = -ENOMEM;
 		goto err_unlock;
+	}
 
 	*entry = (struct nf_queue_entry) {
 		.skb	= skb,
@@ -163,9 +165,8 @@ static int __nf_queue(struct sk_buff *skb,
 	if (!try_module_get(entry->elem->owner)) {
 		rcu_read_unlock();
 		kfree(entry);
-		return 0;
+		return -ECANCELED;
 	}
-
 	/* Bump dev refs so they don't vanish while packet is out */
 	if (indev)
 		dev_hold(indev);
@@ -192,14 +193,14 @@ static int __nf_queue(struct sk_buff *skb,
 		goto err;
 	}
 
-	return 1;
+	return 0;
 
 err_unlock:
 	rcu_read_unlock();
 err:
 	kfree_skb(skb);
 	kfree(entry);
-	return 1;
+	return status;
 }
 
 int nf_queue(struct sk_buff *skb,
@@ -211,6 +212,8 @@ int nf_queue(struct sk_buff *skb,
 	     unsigned int queuenum)
 {
 	struct sk_buff *segs;
+	int err;
+	unsigned int queued;
 
 	if (!skb_is_gso(skb))
 		return __nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
@@ -227,19 +230,32 @@ int nf_queue(struct sk_buff *skb,
 
 	segs = skb_gso_segment(skb, 0);
 	kfree_skb(skb);
+	/* Does not use PTR_ERR to limit the number of error codes that can be
+	 * returned by nf_queue.  For instance, callers rely on -ECANCELED to mean
+	 * 'ignore this hook'.
+	 */
 	if (IS_ERR(segs))
-		return 1;
+		return -EINVAL;
 
+	queued = 0;
+	err = 0;
 	do {
 		struct sk_buff *nskb = segs->next;
 
 		segs->next = NULL;
-		if (!__nf_queue(segs, elem, pf, hook, indev, outdev, okfn,
-				queuenum))
+		if (err == 0)
+			err = __nf_queue(segs, elem, pf, hook, indev,
+					   outdev, okfn, queuenum);
+		if (err == 0)
+			queued++;
+		else
 			kfree_skb(segs);
 		segs = nskb;
 	} while (segs);
-	return 1;
+
+	if (unlikely(err && queued))
+		err = 0;
+	return err;
 }
 
 void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
@@ -247,6 +263,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 	struct sk_buff *skb = entry->skb;
 	struct list_head *elem = &entry->elem->list;
 	const struct nf_afinfo *afinfo;
+	int err;
 
 	rcu_read_lock();
 
@@ -280,9 +297,10 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 		local_bh_enable();
 		break;
 	case NF_QUEUE:
-		if (!__nf_queue(skb, elem, entry->pf, entry->hook,
-				entry->indev, entry->outdev, entry->okfn,
-				verdict >> NF_VERDICT_BITS))
+		err = __nf_queue(skb, elem, entry->pf, entry->hook,
+				 entry->indev, entry->outdev, entry->okfn,
+				 verdict >> NF_VERDICT_BITS);
+		if (err == -ECANCELED)
 			goto next_hook;
 		break;
 	case NF_STOLEN:
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 68e67d1..b83123f 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -387,25 +387,31 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
 {
 	struct sk_buff *nskb;
 	struct nfqnl_instance *queue;
-	int err;
+	int err = -ENOBUFS;
 
 	/* rcu_read_lock()ed by nf_hook_slow() */
 	queue = instance_lookup(queuenum);
-	if (!queue)
+	if (!queue) {
+		err = -ESRCH;
 		goto err_out;
+	}
 
-	if (queue->copy_mode == NFQNL_COPY_NONE)
+	if (queue->copy_mode == NFQNL_COPY_NONE) {
+		err = -EINVAL;
 		goto err_out;
+	}
 
 	nskb = nfqnl_build_packet_message(queue, entry);
-	if (nskb == NULL)
+	if (nskb == NULL) {
+		err = -ENOMEM;
 		goto err_out;
-
+	}
 	spin_lock_bh(&queue->lock);
 
-	if (!queue->peer_pid)
+	if (!queue->peer_pid) {
+		err = -EINVAL;
 		goto err_out_free_nskb;
-
+	}
 	if (queue->queue_total >= queue->queue_maxlen) {
 		queue->queue_dropped++;
 		if (net_ratelimit())
@@ -432,7 +438,7 @@ err_out_free_nskb:
 err_out_unlock:
 	spin_unlock_bh(&queue->lock);
 err_out:
-	return -1;
+	return err;
 }
 
 static int
-- 
1.7.2.3

[PATCH 73/79] netfilter: nfnetlink_queue: do not free skb on error

[kaber]

From: Florian Westphal <fw@strlen.de>

Move free responsibility from nf_queue to caller.
This enables more flexible error handling; we can now accept the skb
instead of freeing it.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/core.c     |    7 +++++--
 net/netfilter/nf_queue.c |   17 ++++++++++-------
 2 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 91d66d2f..0c5b796 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -181,8 +181,11 @@ next_hook:
 	} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
 		ret = nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
 			       verdict >> NF_VERDICT_BITS);
-		if (ret == -ECANCELED)
-			goto next_hook;
+		if (ret < 0) {
+			if (ret == -ECANCELED)
+				goto next_hook;
+			kfree_skb(skb);
+		}
 		ret = 0;
 	}
 	rcu_read_unlock();
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index ad25c7e..5c4b730 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -163,9 +163,8 @@ static int __nf_queue(struct sk_buff *skb,
 
 	/* If it's going away, ignore hook. */
 	if (!try_module_get(entry->elem->owner)) {
-		rcu_read_unlock();
-		kfree(entry);
-		return -ECANCELED;
+		status = -ECANCELED;
+		goto err_unlock;
 	}
 	/* Bump dev refs so they don't vanish while packet is out */
 	if (indev)
@@ -198,7 +197,6 @@ static int __nf_queue(struct sk_buff *skb,
 err_unlock:
 	rcu_read_unlock();
 err:
-	kfree_skb(skb);
 	kfree(entry);
 	return status;
 }
@@ -229,7 +227,6 @@ int nf_queue(struct sk_buff *skb,
 	}
 
 	segs = skb_gso_segment(skb, 0);
-	kfree_skb(skb);
 	/* Does not use PTR_ERR to limit the number of error codes that can be
 	 * returned by nf_queue.  For instance, callers rely on -ECANCELED to mean
 	 * 'ignore this hook'.
@@ -253,8 +250,11 @@ int nf_queue(struct sk_buff *skb,
 		segs = nskb;
 	} while (segs);
 
+	/* also free orig skb if only some segments were queued */
 	if (unlikely(err && queued))
 		err = 0;
+	if (err == 0)
+		kfree_skb(skb);
 	return err;
 }
 
@@ -300,8 +300,11 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 		err = __nf_queue(skb, elem, entry->pf, entry->hook,
 				 entry->indev, entry->outdev, entry->okfn,
 				 verdict >> NF_VERDICT_BITS);
-		if (err == -ECANCELED)
-			goto next_hook;
+		if (err < 0) {
+			if (err == -ECANCELED)
+				goto next_hook;
+			kfree_skb(skb);
+		}
 		break;
 	case NF_STOLEN:
 	default:
-- 
1.7.2.3

[PATCH 74/79] netfilter: reduce NF_VERDICT_MASK to 0xff

[kaber]

From: Florian Westphal <fw@strlen.de>

NF_VERDICT_MASK is currently 0xffff. This is because the upper
16 bits are used to store errno (for NF_DROP) or the queue number
(NF_QUEUE verdict).

As there are up to 0xffff different queues available, there is no more
room to store additional flags.

At the moment there are only 6 different verdicts, i.e. we can reduce
NF_VERDICT_MASK to 0xff to allow storing additional flags in the 0xff00 space.

NF_VERDICT_BITS would then be reduced to 8, but because the value is
exported to userspace, this might cause breakage; e.g.:

e.g. 'queuenr = (1 << NF_VERDICT_BITS) | NF_QUEUE'  would now break.

Thus, remove NF_VERDICT_BITS usage in the kernel and move the old value
to the 'userspace compat' section.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter.h |   20 +++++++++++++++-----
 net/netfilter/core.c      |    4 ++--
 net/netfilter/nf_queue.c  |    2 +-
 3 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 0ab7ca7..78b73cc 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -24,16 +24,19 @@
 #define NF_MAX_VERDICT NF_STOP
 
 /* we overload the higher bits for encoding auxiliary data such as the queue
- * number. Not nice, but better than additional function arguments. */
-#define NF_VERDICT_MASK 0x0000ffff
-#define NF_VERDICT_BITS 16
+ * number or errno values. Not nice, but better than additional function
+ * arguments. */
+#define NF_VERDICT_MASK 0x000000ff
+
+/* extra verdict flags have mask 0x0000ff00 */
 
+/* queue number (NF_QUEUE) or errno (NF_DROP) */
 #define NF_VERDICT_QMASK 0xffff0000
 #define NF_VERDICT_QBITS 16
 
-#define NF_QUEUE_NR(x) ((((x) << NF_VERDICT_BITS) & NF_VERDICT_QMASK) | NF_QUEUE)
+#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE)
 
-#define NF_DROP_ERR(x) (((-x) << NF_VERDICT_BITS) | NF_DROP)
+#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP)
 
 /* only for userspace compatibility */
 #ifndef __KERNEL__
@@ -41,6 +44,9 @@
    <= 0x2000 is used for protocol-flags. */
 #define NFC_UNKNOWN 0x4000
 #define NFC_ALTERED 0x8000
+
+/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */
+#define NF_VERDICT_BITS 16
 #endif
 
 enum nf_inet_hooks {
@@ -72,6 +78,10 @@ union nf_inet_addr {
 
 #ifdef __KERNEL__
 #ifdef CONFIG_NETFILTER
+static inline int NF_DROP_GETERR(int verdict)
+{
+	return -(verdict >> NF_VERDICT_QBITS);
+}
 
 static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1,
 				   const union nf_inet_addr *a2)
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 0c5b796..4d88e45 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -175,12 +175,12 @@ next_hook:
 		ret = 1;
 	} else if ((verdict & NF_VERDICT_MASK) == NF_DROP) {
 		kfree_skb(skb);
-		ret = -(verdict >> NF_VERDICT_BITS);
+		ret = NF_DROP_GETERR(verdict);
 		if (ret == 0)
 			ret = -EPERM;
 	} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
 		ret = nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
-			       verdict >> NF_VERDICT_BITS);
+			       verdict >> NF_VERDICT_QBITS);
 		if (ret < 0) {
 			if (ret == -ECANCELED)
 				goto next_hook;
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 5c4b730..ce1150d4a 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -299,7 +299,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 	case NF_QUEUE:
 		err = __nf_queue(skb, elem, entry->pf, entry->hook,
 				 entry->indev, entry->outdev, entry->okfn,
-				 verdict >> NF_VERDICT_BITS);
+				 verdict >> NF_VERDICT_QBITS);
 		if (err < 0) {
 			if (err == -ECANCELED)
 				goto next_hook;
-- 
1.7.2.3

[PATCH 75/79] netfilter: allow NFQUEUE bypass if no listener is available

[kaber]

From: Florian Westphal <fw@strlen.de>

If an skb is to be NF_QUEUE'd, but no program has opened the queue, the
packet is dropped.

This adds a v2 target revision of xt_NFQUEUE that allows packets to
continue through the ruleset instead.

Because the actual queueing happens outside of the target context, the
'bypass' flag has to be communicated back to the netfilter core.

Unfortunately the only choice to do this without adding a new function
argument is to use the target function return value (i.e. the verdict).

In the NF_QUEUE case, the upper 16bit already contain the queue number
to use.  The previous patch reduced NF_VERDICT_MASK to 0xff, i.e.
we now have extra room for a new flag.

If a hook issued a NF_QUEUE verdict, then the netfilter core will
continue packet processing if the queueing hook
returns -ESRCH (== "this queue does not exist") and the new
NF_VERDICT_FLAG_QUEUE_BYPASS flag is set in the verdict value.

Note: If the queue exists, but userspace does not consume packets fast
enough, the skb will still be dropped.

Signed-off-by: Florian Westphal <fwestphal@astaro.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter.h            |    1 +
 include/linux/netfilter/xt_NFQUEUE.h |    6 ++++++
 net/netfilter/core.c                 |    3 +++
 net/netfilter/nf_queue.c             |    7 ++++++-
 net/netfilter/xt_NFQUEUE.c           |   28 +++++++++++++++++++++++++---
 5 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 78b73cc..eeec00a 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -29,6 +29,7 @@
 #define NF_VERDICT_MASK 0x000000ff
 
 /* extra verdict flags have mask 0x0000ff00 */
+#define NF_VERDICT_FLAG_QUEUE_BYPASS	0x00008000
 
 /* queue number (NF_QUEUE) or errno (NF_DROP) */
 #define NF_VERDICT_QMASK 0xffff0000
diff --git a/include/linux/netfilter/xt_NFQUEUE.h b/include/linux/netfilter/xt_NFQUEUE.h
index 2584f4a..9eafdbb 100644
--- a/include/linux/netfilter/xt_NFQUEUE.h
+++ b/include/linux/netfilter/xt_NFQUEUE.h
@@ -20,4 +20,10 @@ struct xt_NFQ_info_v1 {
 	__u16 queues_total;
 };
 
+struct xt_NFQ_info_v2 {
+	__u16 queuenum;
+	__u16 queues_total;
+	__u16 bypass;
+};
+
 #endif /* _XT_NFQ_TARGET_H */
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 4d88e45..1e00bf7 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -184,6 +184,9 @@ next_hook:
 		if (ret < 0) {
 			if (ret == -ECANCELED)
 				goto next_hook;
+			if (ret == -ESRCH &&
+			   (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
+				goto next_hook;
 			kfree_skb(skb);
 		}
 		ret = 0;
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index ce1150d4a..5ab22e2 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -138,8 +138,10 @@ static int __nf_queue(struct sk_buff *skb,
 	rcu_read_lock();
 
 	qh = rcu_dereference(queue_handler[pf]);
-	if (!qh)
+	if (!qh) {
+		status = -ESRCH;
 		goto err_unlock;
+	}
 
 	afinfo = nf_get_afinfo(pf);
 	if (!afinfo)
@@ -303,6 +305,9 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 		if (err < 0) {
 			if (err == -ECANCELED)
 				goto next_hook;
+			if (err == -ESRCH &&
+			   (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
+				goto next_hook;
 			kfree_skb(skb);
 		}
 		break;
diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index 3962770..d4f4b5d 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -83,9 +83,20 @@ nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par)
 	return NF_QUEUE_NR(queue);
 }
 
-static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par)
+static unsigned int
+nfqueue_tg_v2(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	const struct xt_NFQ_info_v1 *info = par->targinfo;
+	const struct xt_NFQ_info_v2 *info = par->targinfo;
+	unsigned int ret = nfqueue_tg_v1(skb, par);
+
+	if (info->bypass)
+		ret |= NF_VERDICT_FLAG_QUEUE_BYPASS;
+	return ret;
+}
+
+static int nfqueue_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct xt_NFQ_info_v2 *info = par->targinfo;
 	u32 maxid;
 
 	if (unlikely(!rnd_inited)) {
@@ -102,6 +113,8 @@ static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par)
 		       info->queues_total, maxid);
 		return -ERANGE;
 	}
+	if (par->target->revision == 2 && info->bypass > 1)
+		return -EINVAL;
 	return 0;
 }
 
@@ -117,11 +130,20 @@ static struct xt_target nfqueue_tg_reg[] __read_mostly = {
 		.name		= "NFQUEUE",
 		.revision	= 1,
 		.family		= NFPROTO_UNSPEC,
-		.checkentry	= nfqueue_tg_v1_check,
+		.checkentry	= nfqueue_tg_check,
 		.target		= nfqueue_tg_v1,
 		.targetsize	= sizeof(struct xt_NFQ_info_v1),
 		.me		= THIS_MODULE,
 	},
+	{
+		.name		= "NFQUEUE",
+		.revision	= 2,
+		.family		= NFPROTO_UNSPEC,
+		.checkentry	= nfqueue_tg_check,
+		.target		= nfqueue_tg_v2,
+		.targetsize	= sizeof(struct xt_NFQ_info_v2),
+		.me		= THIS_MODULE,
+	},
 };
 
 static int __init nfqueue_tg_init(void)
-- 
1.7.2.3

[PATCH 76/79] netfilter: ipt_CLUSTERIP: remove "no conntrack!"

[kaber]

From: Eric Dumazet <eric.dumazet@gmail.com>

When a packet is meant to be handled by another node of the cluster,
silently drop it instead of flooding kernel log.

Note : INVALID packets are also dropped without notice.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/ipv4/netfilter/ipt_CLUSTERIP.c |    7 +------
 1 files changed, 1 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 1e26a48..403ca57 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -300,13 +300,8 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	 * that the ->target() function isn't called after ->destroy() */
 
 	ct = nf_ct_get(skb, &ctinfo);
-	if (ct == NULL) {
-		pr_info("no conntrack!\n");
-			/* FIXME: need to drop invalid ones, since replies
-			 * to outgoing connections of other nodes will be
-			 * marked as INVALID */
+	if (ct == NULL)
 		return NF_DROP;
-	}
 
 	/* special case: ICMP error handling. conntrack distinguishes between
 	 * error messages (RELATED) and information requests (see below) */
-- 
1.7.2.3

[PATCH 77/79] netfilter: nf_conntrack: nf_conntrack snmp helper

[kaber]

From: Jiri Olsa <jolsa@redhat.com>

Adding support for SNMP broadcast connection tracking. The SNMP
broadcast requests are now paired with the SNMP responses.
Thus allowing using SNMP broadcasts with firewall enabled.

Please refer to the following conversation:
http://marc.info/?l=netfilter-devel&m=125992205006600&w=2

Patrick McHardy wrote:
> > The best solution would be to add generic broadcast tracking, the
> > use of expectations for this is a bit of abuse.
> > The second best choice I guess would be to move the help() function
> > to a shared module and generalize it so it can be used for both.
This patch implements the "second best choice".

Since the netbios-ns conntrack module uses the same helper
functionality as the snmp, only one helper function is added
for both snmp and netbios-ns modules into the new object -
nf_conntrack_broadcast.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/nf_conntrack_snmp.h |    9 +++
 include/net/netfilter/nf_conntrack_helper.h |    6 ++
 net/ipv4/netfilter/Kconfig                  |    3 +-
 net/ipv4/netfilter/nf_nat_snmp_basic.c      |    9 ++-
 net/netfilter/Kconfig                       |   19 ++++++
 net/netfilter/Makefile                      |    2 +
 net/netfilter/nf_conntrack_broadcast.c      |   82 +++++++++++++++++++++++++++
 net/netfilter/nf_conntrack_netbios_ns.c     |   74 +++---------------------
 net/netfilter/nf_conntrack_snmp.c           |   77 +++++++++++++++++++++++++
 9 files changed, 211 insertions(+), 70 deletions(-)
 create mode 100644 include/linux/netfilter/nf_conntrack_snmp.h
 create mode 100644 net/netfilter/nf_conntrack_broadcast.c
 create mode 100644 net/netfilter/nf_conntrack_snmp.c

diff --git a/include/linux/netfilter/nf_conntrack_snmp.h b/include/linux/netfilter/nf_conntrack_snmp.h
new file mode 100644
index 0000000..064bc63
--- /dev/null
+++ b/include/linux/netfilter/nf_conntrack_snmp.h
@@ -0,0 +1,9 @@
+#ifndef _NF_CONNTRACK_SNMP_H
+#define _NF_CONNTRACK_SNMP_H
+
+extern int (*nf_nat_snmp_hook)(struct sk_buff *skb,
+				unsigned int protoff,
+				struct nf_conn *ct,
+				enum ip_conntrack_info ctinfo);
+
+#endif /* _NF_CONNTRACK_SNMP_H */
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 32c305d..f1c1311 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -63,4 +63,10 @@ static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct)
 extern int nf_conntrack_helper_init(void);
 extern void nf_conntrack_helper_fini(void);
 
+extern int nf_conntrack_broadcast_help(struct sk_buff *skb,
+				       unsigned int protoff,
+				       struct nf_conn *ct,
+				       enum ip_conntrack_info ctinfo,
+				       unsigned int timeout);
+
 #endif /*_NF_CONNTRACK_HELPER_H*/
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index babd1a2..f926a31 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -206,8 +206,9 @@ config IP_NF_TARGET_REDIRECT
 
 config NF_NAT_SNMP_BASIC
 	tristate "Basic SNMP-ALG support"
-	depends on NF_NAT
+	depends on NF_CONNTRACK_SNMP && NF_NAT
 	depends on NETFILTER_ADVANCED
+	default NF_NAT && NF_CONNTRACK_SNMP
 	---help---
 
 	  This module implements an Application Layer Gateway (ALG) for
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index ee5f419..8812a02 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -54,6 +54,7 @@
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_nat_helper.h>
+#include <linux/netfilter/nf_conntrack_snmp.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
@@ -1310,9 +1311,9 @@ static int __init nf_nat_snmp_basic_init(void)
 {
 	int ret = 0;
 
-	ret = nf_conntrack_helper_register(&snmp_helper);
-	if (ret < 0)
-		return ret;
+	BUG_ON(nf_nat_snmp_hook != NULL);
+	rcu_assign_pointer(nf_nat_snmp_hook, help);
+
 	ret = nf_conntrack_helper_register(&snmp_trap_helper);
 	if (ret < 0) {
 		nf_conntrack_helper_unregister(&snmp_helper);
@@ -1323,7 +1324,7 @@ static int __init nf_nat_snmp_basic_init(void)
 
 static void __exit nf_nat_snmp_basic_fini(void)
 {
-	nf_conntrack_helper_unregister(&snmp_helper);
+	rcu_assign_pointer(nf_nat_snmp_hook, NULL);
 	nf_conntrack_helper_unregister(&snmp_trap_helper);
 }
 
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index e2480bd..939b504 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -185,9 +185,13 @@ config NF_CONNTRACK_IRC
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NF_CONNTRACK_BROADCAST
+	tristate
+
 config NF_CONNTRACK_NETBIOS_NS
 	tristate "NetBIOS name service protocol support"
 	depends on NETFILTER_ADVANCED
+	select NF_CONNTRACK_BROADCAST
 	help
 	  NetBIOS name service requests are sent as broadcast messages from an
 	  unprivileged port and responded to with unicast messages to the
@@ -204,6 +208,21 @@ config NF_CONNTRACK_NETBIOS_NS
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NF_CONNTRACK_SNMP
+	tristate "SNMP service protocol support"
+	depends on NETFILTER_ADVANCED
+	select NF_CONNTRACK_BROADCAST
+	help
+	  SNMP service requests are sent as broadcast messages from an
+	  unprivileged port and responded to with unicast messages to the
+	  same port. This make them hard to firewall properly because connection
+	  tracking doesn't deal with broadcasts. This helper tracks locally
+	  originating SNMP service requests and the corresponding
+	  responses. It relies on correct IP address configuration, specifically
+	  netmask and broadcast address.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config NF_CONNTRACK_PPTP
 	tristate "PPtP protocol support"
 	depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 401d574..2c2628d 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -28,7 +28,9 @@ obj-$(CONFIG_NF_CONNTRACK_AMANDA) += nf_conntrack_amanda.o
 obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o
 obj-$(CONFIG_NF_CONNTRACK_H323) += nf_conntrack_h323.o
 obj-$(CONFIG_NF_CONNTRACK_IRC) += nf_conntrack_irc.o
+obj-$(CONFIG_NF_CONNTRACK_BROADCAST) += nf_conntrack_broadcast.o
 obj-$(CONFIG_NF_CONNTRACK_NETBIOS_NS) += nf_conntrack_netbios_ns.o
+obj-$(CONFIG_NF_CONNTRACK_SNMP) += nf_conntrack_snmp.o
 obj-$(CONFIG_NF_CONNTRACK_PPTP) += nf_conntrack_pptp.o
 obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o
 obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o
diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c
new file mode 100644
index 0000000..4e99cca
--- /dev/null
+++ b/net/netfilter/nf_conntrack_broadcast.c
@@ -0,0 +1,82 @@
+/*
+ *      broadcast connection tracking helper
+ *
+ *      (c) 2005 Patrick McHardy <kaber@trash.net>
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <net/route.h>
+#include <linux/inetdevice.h>
+#include <linux/skbuff.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+
+int nf_conntrack_broadcast_help(struct sk_buff *skb,
+				unsigned int protoff,
+				struct nf_conn *ct,
+				enum ip_conntrack_info ctinfo,
+				unsigned int timeout)
+{
+	struct nf_conntrack_expect *exp;
+	struct iphdr *iph = ip_hdr(skb);
+	struct rtable *rt = skb_rtable(skb);
+	struct in_device *in_dev;
+	struct nf_conn_help *help = nfct_help(ct);
+	__be32 mask = 0;
+
+	/* we're only interested in locally generated packets */
+	if (skb->sk == NULL)
+		goto out;
+	if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST))
+		goto out;
+	if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
+		goto out;
+
+	rcu_read_lock();
+	in_dev = __in_dev_get_rcu(rt->dst.dev);
+	if (in_dev != NULL) {
+		for_primary_ifa(in_dev) {
+			if (ifa->ifa_broadcast == iph->daddr) {
+				mask = ifa->ifa_mask;
+				break;
+			}
+		} endfor_ifa(in_dev);
+	}
+	rcu_read_unlock();
+
+	if (mask == 0)
+		goto out;
+
+	exp = nf_ct_expect_alloc(ct);
+	if (exp == NULL)
+		goto out;
+
+	exp->tuple                = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+	exp->tuple.src.u.udp.port = help->helper->tuple.src.u.udp.port;
+
+	exp->mask.src.u3.ip       = mask;
+	exp->mask.src.u.udp.port  = htons(0xFFFF);
+
+	exp->expectfn             = NULL;
+	exp->flags                = NF_CT_EXPECT_PERMANENT;
+	exp->class		  = NF_CT_EXPECT_CLASS_DEFAULT;
+	exp->helper               = NULL;
+
+	nf_ct_expect_related(exp);
+	nf_ct_expect_put(exp);
+
+	nf_ct_refresh(ct, skb, timeout * HZ);
+out:
+	return NF_ACCEPT;
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_broadcast_help);
+
+MODULE_LICENSE("GPL");
diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c
index aadde01..4c8f30a 100644
--- a/net/netfilter/nf_conntrack_netbios_ns.c
+++ b/net/netfilter/nf_conntrack_netbios_ns.c
@@ -18,14 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <linux/inetdevice.h>
-#include <linux/if_addr.h>
 #include <linux/in.h>
-#include <linux/ip.h>
-#include <linux/netfilter.h>
-#include <net/route.h>
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_helper.h>
@@ -40,75 +33,26 @@ MODULE_ALIAS("ip_conntrack_netbios_ns");
 MODULE_ALIAS_NFCT_HELPER("netbios_ns");
 
 static unsigned int timeout __read_mostly = 3;
-module_param(timeout, uint, 0400);
+module_param(timeout, uint, S_IRUSR);
 MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds");
 
-static int help(struct sk_buff *skb, unsigned int protoff,
-		struct nf_conn *ct, enum ip_conntrack_info ctinfo)
-{
-	struct nf_conntrack_expect *exp;
-	struct iphdr *iph = ip_hdr(skb);
-	struct rtable *rt = skb_rtable(skb);
-	struct in_device *in_dev;
-	__be32 mask = 0;
-
-	/* we're only interested in locally generated packets */
-	if (skb->sk == NULL)
-		goto out;
-	if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST))
-		goto out;
-	if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
-		goto out;
-
-	rcu_read_lock();
-	in_dev = __in_dev_get_rcu(rt->dst.dev);
-	if (in_dev != NULL) {
-		for_primary_ifa(in_dev) {
-			if (ifa->ifa_broadcast == iph->daddr) {
-				mask = ifa->ifa_mask;
-				break;
-			}
-		} endfor_ifa(in_dev);
-	}
-	rcu_read_unlock();
-
-	if (mask == 0)
-		goto out;
-
-	exp = nf_ct_expect_alloc(ct);
-	if (exp == NULL)
-		goto out;
-
-	exp->tuple                = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
-	exp->tuple.src.u.udp.port = htons(NMBD_PORT);
-
-	exp->mask.src.u3.ip       = mask;
-	exp->mask.src.u.udp.port  = htons(0xFFFF);
-
-	exp->expectfn             = NULL;
-	exp->flags                = NF_CT_EXPECT_PERMANENT;
-	exp->class		  = NF_CT_EXPECT_CLASS_DEFAULT;
-	exp->helper               = NULL;
-
-	nf_ct_expect_related(exp);
-	nf_ct_expect_put(exp);
-
-	nf_ct_refresh(ct, skb, timeout * HZ);
-out:
-	return NF_ACCEPT;
-}
-
 static struct nf_conntrack_expect_policy exp_policy = {
 	.max_expected	= 1,
 };
 
+static int netbios_ns_help(struct sk_buff *skb, unsigned int protoff,
+		   struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+{
+	return nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout);
+}
+
 static struct nf_conntrack_helper helper __read_mostly = {
 	.name			= "netbios-ns",
-	.tuple.src.l3num	= AF_INET,
+	.tuple.src.l3num	= NFPROTO_IPV4,
 	.tuple.src.u.udp.port	= cpu_to_be16(NMBD_PORT),
 	.tuple.dst.protonum	= IPPROTO_UDP,
 	.me			= THIS_MODULE,
-	.help			= help,
+	.help			= netbios_ns_help,
 	.expect_policy		= &exp_policy,
 };
 
diff --git a/net/netfilter/nf_conntrack_snmp.c b/net/netfilter/nf_conntrack_snmp.c
new file mode 100644
index 0000000..6e545e2
--- /dev/null
+++ b/net/netfilter/nf_conntrack_snmp.c
@@ -0,0 +1,77 @@
+/*
+ *      SNMP service broadcast connection tracking helper
+ *
+ *      (c) 2011 Jiri Olsa <jolsa@redhat.com>
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/in.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+
+#define SNMP_PORT	161
+
+MODULE_AUTHOR("Jiri Olsa <jolsa@redhat.com>");
+MODULE_DESCRIPTION("SNMP service broadcast connection tracking helper");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NFCT_HELPER("snmp");
+
+static unsigned int timeout __read_mostly = 30;
+module_param(timeout, uint, S_IRUSR);
+MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds");
+
+int (*nf_nat_snmp_hook)(struct sk_buff *skb,
+			unsigned int protoff,
+			struct nf_conn *ct,
+			enum ip_conntrack_info ctinfo);
+EXPORT_SYMBOL_GPL(nf_nat_snmp_hook);
+
+static int snmp_conntrack_help(struct sk_buff *skb, unsigned int protoff,
+		struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+{
+	typeof(nf_nat_snmp_hook) nf_nat_snmp;
+
+	nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout);
+
+	nf_nat_snmp = rcu_dereference(nf_nat_snmp_hook);
+	if (nf_nat_snmp && ct->status & IPS_NAT_MASK)
+		return nf_nat_snmp(skb, protoff, ct, ctinfo);
+
+	return NF_ACCEPT;
+}
+
+static struct nf_conntrack_expect_policy exp_policy = {
+	.max_expected	= 1,
+};
+
+static struct nf_conntrack_helper helper __read_mostly = {
+	.name			= "snmp",
+	.tuple.src.l3num	= NFPROTO_IPV4,
+	.tuple.src.u.udp.port	= cpu_to_be16(SNMP_PORT),
+	.tuple.dst.protonum	= IPPROTO_UDP,
+	.me			= THIS_MODULE,
+	.help			= snmp_conntrack_help,
+	.expect_policy		= &exp_policy,
+};
+
+static int __init nf_conntrack_snmp_init(void)
+{
+	exp_policy.timeout = timeout;
+	return nf_conntrack_helper_register(&helper);
+}
+
+static void __exit nf_conntrack_snmp_fini(void)
+{
+	nf_conntrack_helper_unregister(&helper);
+}
+
+module_init(nf_conntrack_snmp_init);
+module_exit(nf_conntrack_snmp_fini);
-- 
1.7.2.3

[PATCH 78/79] netfilter: nf_conntrack_tstamp: add flow-based timestamp extension

[kaber]

From: Pablo Neira Ayuso <pablo@netfilter.org>

This patch adds flow-based timestamping for conntracks. This
conntrack extension is disabled by default. Basically, we use
two 64-bits variables to store the creation timestamp once the
conntrack has been confirmed and the other to store the deletion
time. This extension is disabled by default, to enable it, you
have to:

echo 1 > /proc/sys/net/netfilter/nf_conntrack_timestamp

This patch allows to save memory for user-space flow-based
loogers such as ulogd2. In short, ulogd2 does not need to
keep a hashtable with the conntrack in user-space to know
when they were created and destroyed, instead we use the
kernel timestamp. If we want to have a sane IPFIX implementation
in user-space, this nanosecs resolution timestamps are also
useful. Other custom user-space applications can benefit from
this via libnetfilter_conntrack.

This patch modifies the /proc output to display the delta time
in seconds since the flow start. You can also obtain the
flow-start date by means of the conntrack-tools.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/nfnetlink_conntrack.h  |    9 ++
 include/net/netfilter/nf_conntrack_extend.h    |    4 +
 include/net/netfilter/nf_conntrack_timestamp.h |   53 +++++++++++
 include/net/netns/conntrack.h                  |    2 +
 net/netfilter/Kconfig                          |   11 ++
 net/netfilter/Makefile                         |    1 +
 net/netfilter/nf_conntrack_core.c              |   26 +++++
 net/netfilter/nf_conntrack_netlink.c           |   46 +++++++++-
 net/netfilter/nf_conntrack_standalone.c        |   41 ++++++++
 net/netfilter/nf_conntrack_timestamp.c         |  120 ++++++++++++++++++++++++
 10 files changed, 312 insertions(+), 1 deletions(-)
 create mode 100644 include/net/netfilter/nf_conntrack_timestamp.h
 create mode 100644 net/netfilter/nf_conntrack_timestamp.c

diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h
index 19711e3..debf1ae 100644
--- a/include/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/linux/netfilter/nfnetlink_conntrack.h
@@ -42,6 +42,7 @@ enum ctattr_type {
 	CTA_SECMARK,		/* obsolete */
 	CTA_ZONE,
 	CTA_SECCTX,
+	CTA_TIMESTAMP,
 	__CTA_MAX
 };
 #define CTA_MAX (__CTA_MAX - 1)
@@ -127,6 +128,14 @@ enum ctattr_counters {
 };
 #define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1)
 
+enum ctattr_tstamp {
+	CTA_TIMESTAMP_UNSPEC,
+	CTA_TIMESTAMP_START,
+	CTA_TIMESTAMP_STOP,
+	__CTA_TIMESTAMP_MAX
+};
+#define CTA_TIMESTAMP_MAX (__CTA_TIMESTAMP_MAX - 1)
+
 enum ctattr_nat {
 	CTA_NAT_UNSPEC,
 	CTA_NAT_MINIP,
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 1a9f96d..2dcf317 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -17,6 +17,9 @@ enum nf_ct_ext_id {
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	NF_CT_EXT_ZONE,
 #endif
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	NF_CT_EXT_TSTAMP,
+#endif
 	NF_CT_EXT_NUM,
 };
 
@@ -25,6 +28,7 @@ enum nf_ct_ext_id {
 #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter
 #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache
 #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone
+#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp
 
 /* Extensions: optional stuff which isn't permanently in struct. */
 struct nf_ct_ext {
diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h
new file mode 100644
index 0000000..f17dcb6
--- /dev/null
+++ b/include/net/netfilter/nf_conntrack_timestamp.h
@@ -0,0 +1,53 @@
+#ifndef _NF_CONNTRACK_TSTAMP_H
+#define _NF_CONNTRACK_TSTAMP_H
+
+#include <net/net_namespace.h>
+#include <linux/netfilter/nf_conntrack_common.h>
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_extend.h>
+
+struct nf_conn_tstamp {
+	u_int64_t start;
+	u_int64_t stop;
+};
+
+static inline
+struct nf_conn_tstamp *nf_conn_tstamp_find(const struct nf_conn *ct)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	return nf_ct_ext_find(ct, NF_CT_EXT_TSTAMP);
+#else
+	return NULL;
+#endif
+}
+
+static inline
+struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	struct net *net = nf_ct_net(ct);
+
+	if (!net->ct.sysctl_tstamp)
+		return NULL;
+
+	return nf_ct_ext_add(ct, NF_CT_EXT_TSTAMP, gfp);
+#else
+	return NULL;
+#endif
+};
+
+static inline bool nf_ct_tstamp_enabled(struct net *net)
+{
+	return net->ct.sysctl_tstamp != 0;
+}
+
+static inline void nf_ct_set_tstamp(struct net *net, bool enable)
+{
+	net->ct.sysctl_tstamp = enable;
+}
+
+extern int nf_conntrack_tstamp_init(struct net *net);
+extern void nf_conntrack_tstamp_fini(struct net *net);
+
+#endif /* _NF_CONNTRACK_TSTAMP_H */
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 5cf8a8c..341eb08 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -21,11 +21,13 @@ struct netns_ct {
 	int			sysctl_events;
 	unsigned int		sysctl_events_retry_timeout;
 	int			sysctl_acct;
+	int			sysctl_tstamp;
 	int			sysctl_checksum;
 	unsigned int		sysctl_log_invalid; /* Log invalid packets */
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*sysctl_header;
 	struct ctl_table_header	*acct_sysctl_header;
+	struct ctl_table_header	*tstamp_sysctl_header;
 	struct ctl_table_header	*event_sysctl_header;
 #endif
 	char			*slabname;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 939b504..faf7412 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -85,6 +85,17 @@ config NF_CONNTRACK_EVENTS
 
 	  If unsure, say `N'.
 
+config NF_CONNTRACK_TIMESTAMP
+	bool  'Connection tracking timestamping'
+	depends on NETFILTER_ADVANCED
+	help
+	  This option enables support for connection tracking timestamping.
+	  This allows you to store the flow start-time and to obtain
+	  the flow-stop time (once it has been destroyed) via Connection
+	  tracking events.
+
+	  If unsure, say `N'.
+
 config NF_CT_PROTO_DCCP
 	tristate 'DCCP protocol connection tracking support (EXPERIMENTAL)'
 	depends on EXPERIMENTAL
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 2c2628d..9ae6878 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -1,6 +1,7 @@
 netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o
 
 nf_conntrack-y	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o
+nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
 
 obj-$(CONFIG_NETFILTER) = netfilter.o
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f47ac67..1909311 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -43,6 +43,7 @@
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_core.h>
 
@@ -282,6 +283,11 @@ EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list);
 static void death_by_timeout(unsigned long ul_conntrack)
 {
 	struct nf_conn *ct = (void *)ul_conntrack;
+	struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(ct);
+	if (tstamp && tstamp->stop == 0)
+		tstamp->stop = ktime_to_ns(ktime_get_real());
 
 	if (!test_bit(IPS_DYING_BIT, &ct->status) &&
 	    unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) {
@@ -419,6 +425,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
 	struct nf_conn_help *help;
+	struct nf_conn_tstamp *tstamp;
 	struct hlist_nulls_node *n;
 	enum ip_conntrack_info ctinfo;
 	struct net *net;
@@ -488,6 +495,14 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	atomic_inc(&ct->ct_general.use);
 	ct->status |= IPS_CONFIRMED;
 
+	/* set conntrack timestamp, if enabled. */
+	tstamp = nf_conn_tstamp_find(ct);
+	if (tstamp) {
+		if (skb->tstamp.tv64 == 0)
+			__net_timestamp((struct sk_buff *)skb);
+
+		tstamp->start = ktime_to_ns(skb->tstamp);
+	}
 	/* Since the lookup is lockless, hash insertion must be done after
 	 * starting the timer and setting the CONFIRMED bit. The RCU barriers
 	 * guarantee that no other CPU can find the conntrack before the above
@@ -746,6 +761,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	}
 
 	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
+	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
 
 	ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL;
 	nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0,
@@ -1186,6 +1202,11 @@ struct __nf_ct_flush_report {
 static int kill_report(struct nf_conn *i, void *data)
 {
 	struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data;
+	struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(i);
+	if (tstamp && tstamp->stop == 0)
+		tstamp->stop = ktime_to_ns(ktime_get_real());
 
 	/* If we fail to deliver the event, death_by_timeout() will retry */
 	if (nf_conntrack_event_report(IPCT_DESTROY, i,
@@ -1497,6 +1518,9 @@ static int nf_conntrack_init_net(struct net *net)
 	ret = nf_conntrack_acct_init(net);
 	if (ret < 0)
 		goto err_acct;
+	ret = nf_conntrack_tstamp_init(net);
+	if (ret < 0)
+		goto err_tstamp;
 	ret = nf_conntrack_ecache_init(net);
 	if (ret < 0)
 		goto err_ecache;
@@ -1504,6 +1528,8 @@ static int nf_conntrack_init_net(struct net *net)
 	return 0;
 
 err_ecache:
+	nf_conntrack_tstamp_fini(net);
+err_tstamp:
 	nf_conntrack_acct_fini(net);
 err_acct:
 	nf_conntrack_expect_fini(net);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 9eabaa6..715d56c 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -42,6 +42,7 @@
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
 #ifdef CONFIG_NF_NAT_NEEDED
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_protocol.h>
@@ -230,6 +231,33 @@ nla_put_failure:
 	return -1;
 }
 
+static int
+ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct)
+{
+	struct nlattr *nest_count;
+	const struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(ct);
+	if (!tstamp)
+		return 0;
+
+	nest_count = nla_nest_start(skb, CTA_TIMESTAMP | NLA_F_NESTED);
+	if (!nest_count)
+		goto nla_put_failure;
+
+	NLA_PUT_BE64(skb, CTA_TIMESTAMP_START, cpu_to_be64(tstamp->start));
+	if (tstamp->stop != 0) {
+		NLA_PUT_BE64(skb, CTA_TIMESTAMP_STOP,
+			     cpu_to_be64(tstamp->stop));
+	}
+	nla_nest_end(skb, nest_count);
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
 #ifdef CONFIG_NF_CONNTRACK_MARK
 static inline int
 ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct)
@@ -404,6 +432,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
 	    ctnetlink_dump_timeout(skb, ct) < 0 ||
 	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
 	    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 ||
+	    ctnetlink_dump_timestamp(skb, ct) < 0 ||
 	    ctnetlink_dump_protoinfo(skb, ct) < 0 ||
 	    ctnetlink_dump_helpinfo(skb, ct) < 0 ||
 	    ctnetlink_dump_mark(skb, ct) < 0 ||
@@ -471,6 +500,18 @@ ctnetlink_secctx_size(const struct nf_conn *ct)
 }
 
 static inline size_t
+ctnetlink_timestamp_size(const struct nf_conn *ct)
+{
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+	if (!nf_ct_ext_exist(ct, NF_CT_EXT_TSTAMP))
+		return 0;
+	return nla_total_size(0) + 2 * nla_total_size(sizeof(uint64_t));
+#else
+	return 0;
+#endif
+}
+
+static inline size_t
 ctnetlink_nlmsg_size(const struct nf_conn *ct)
 {
 	return NLMSG_ALIGN(sizeof(struct nfgenmsg))
@@ -481,6 +522,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */
 	       + ctnetlink_counters_size(ct)
+	       + ctnetlink_timestamp_size(ct)
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */
 	       + nla_total_size(0) /* CTA_PROTOINFO */
 	       + nla_total_size(0) /* CTA_HELP */
@@ -571,7 +613,8 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 
 	if (events & (1 << IPCT_DESTROY)) {
 		if (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 ||
-		    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0)
+		    ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 ||
+		    ctnetlink_dump_timestamp(skb, ct) < 0)
 			goto nla_put_failure;
 	} else {
 		if (ctnetlink_dump_timeout(skb, ct) < 0)
@@ -1360,6 +1403,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
 	}
 
 	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
+	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
 	nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC);
 	/* we must add conntrack extensions before confirmation. */
 	ct->status |= IPS_CONFIRMED;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 8257bf6..69107fd 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -29,6 +29,7 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_acct.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
 #include <linux/rculist_nulls.h>
 
 MODULE_LICENSE("GPL");
@@ -46,6 +47,7 @@ EXPORT_SYMBOL_GPL(print_tuple);
 struct ct_iter_state {
 	struct seq_net_private p;
 	unsigned int bucket;
+	u_int64_t time_now;
 };
 
 static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
@@ -96,6 +98,9 @@ static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos)
 static void *ct_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(RCU)
 {
+	struct ct_iter_state *st = seq->private;
+
+	st->time_now = ktime_to_ns(ktime_get_real());
 	rcu_read_lock();
 	return ct_get_idx(seq, *pos);
 }
@@ -135,6 +140,39 @@ static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 }
 #endif
 
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+static u_int64_t ct_delta_time(u_int64_t time_now, const struct nf_conn *ct)
+{
+	struct nf_conn_tstamp *tstamp;
+
+	tstamp = nf_conn_tstamp_find(ct);
+	if (tstamp) {
+		u_int64_t delta_time = time_now - tstamp->start;
+		return delta_time > 0 ? div_s64(delta_time, NSEC_PER_SEC) : 0;
+	}
+	return -1;
+}
+
+static int ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
+{
+	struct ct_iter_state *st = s->private;
+	u_int64_t delta_time;
+
+	delta_time = ct_delta_time(st->time_now, ct);
+	if (delta_time < 0)
+		return 0;
+
+	return seq_printf(s, "delta-time=%llu ",
+			  (unsigned long long)delta_time);
+}
+#else
+static inline int
+ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
+{
+	return 0;
+}
+#endif
+
 /* return 0 on success, 1 in case of error */
 static int ct_seq_show(struct seq_file *s, void *v)
 {
@@ -203,6 +241,9 @@ static int ct_seq_show(struct seq_file *s, void *v)
 		goto release;
 #endif
 
+	if (ct_show_delta_time(s, ct))
+		goto release;
+
 	if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)))
 		goto release;
 
diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c
new file mode 100644
index 0000000..af7dd31
--- /dev/null
+++ b/net/netfilter/nf_conntrack_timestamp.c
@@ -0,0 +1,120 @@
+/*
+ * (C) 2010 Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation (or any later at your option).
+ */
+
+#include <linux/netfilter.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_extend.h>
+#include <net/netfilter/nf_conntrack_timestamp.h>
+
+static int nf_ct_tstamp __read_mostly;
+
+module_param_named(tstamp, nf_ct_tstamp, bool, 0644);
+MODULE_PARM_DESC(tstamp, "Enable connection tracking flow timestamping.");
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table tstamp_sysctl_table[] = {
+	{
+		.procname	= "nf_conntrack_timestamp",
+		.data		= &init_net.ct.sysctl_tstamp,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{}
+};
+#endif /* CONFIG_SYSCTL */
+
+static struct nf_ct_ext_type tstamp_extend __read_mostly = {
+	.len	= sizeof(struct nf_conn_tstamp),
+	.align	= __alignof__(struct nf_conn_tstamp),
+	.id	= NF_CT_EXT_TSTAMP,
+};
+
+#ifdef CONFIG_SYSCTL
+static int nf_conntrack_tstamp_init_sysctl(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = kmemdup(tstamp_sysctl_table, sizeof(tstamp_sysctl_table),
+			GFP_KERNEL);
+	if (!table)
+		goto out;
+
+	table[0].data = &net->ct.sysctl_tstamp;
+
+	net->ct.tstamp_sysctl_header = register_net_sysctl_table(net,
+			nf_net_netfilter_sysctl_path, table);
+	if (!net->ct.tstamp_sysctl_header) {
+		printk(KERN_ERR "nf_ct_tstamp: can't register to sysctl.\n");
+		goto out_register;
+	}
+	return 0;
+
+out_register:
+	kfree(table);
+out:
+	return -ENOMEM;
+}
+
+static void nf_conntrack_tstamp_fini_sysctl(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = net->ct.tstamp_sysctl_header->ctl_table_arg;
+	unregister_net_sysctl_table(net->ct.tstamp_sysctl_header);
+	kfree(table);
+}
+#else
+static int nf_conntrack_tstamp_init_sysctl(struct net *net)
+{
+	return 0;
+}
+
+static void nf_conntrack_tstamp_fini_sysctl(struct net *net)
+{
+}
+#endif
+
+int nf_conntrack_tstamp_init(struct net *net)
+{
+	int ret;
+
+	net->ct.sysctl_tstamp = nf_ct_tstamp;
+
+	if (net_eq(net, &init_net)) {
+		ret = nf_ct_extend_register(&tstamp_extend);
+		if (ret < 0) {
+			printk(KERN_ERR "nf_ct_tstamp: Unable to register "
+					"extension\n");
+			goto out_extend_register;
+		}
+	}
+
+	ret = nf_conntrack_tstamp_init_sysctl(net);
+	if (ret < 0)
+		goto out_sysctl;
+
+	return 0;
+
+out_sysctl:
+	if (net_eq(net, &init_net))
+		nf_ct_extend_unregister(&tstamp_extend);
+out_extend_register:
+	return ret;
+}
+
+void nf_conntrack_tstamp_fini(struct net *net)
+{
+	nf_conntrack_tstamp_fini_sysctl(net);
+	if (net_eq(net, &init_net))
+		nf_ct_extend_unregister(&tstamp_extend);
+}
-- 
1.7.2.3

[PATCH 79/79] netfilter: nf_conntrack: fix lifetime display for disabled connections

[kaber]

From: Patrick McHardy <kaber@trash.net>

When no tstamp extension exists, ct_delta_time() returns -1, which is
then assigned to an u64 and tested for negative values to decide
whether to display the lifetime. This obviously doesn't work, use
a s64 and merge the two minor functions into one.

Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/netfilter/nf_conntrack_standalone.c |   29 ++++++++++++-----------------
 1 files changed, 12 insertions(+), 17 deletions(-)

diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 69107fd..0ae1428 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -141,29 +141,24 @@ static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 #endif
 
 #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
-static u_int64_t ct_delta_time(u_int64_t time_now, const struct nf_conn *ct)
+static int ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
 {
+	struct ct_iter_state *st = s->private;
 	struct nf_conn_tstamp *tstamp;
+	s64 delta_time;
 
 	tstamp = nf_conn_tstamp_find(ct);
 	if (tstamp) {
-		u_int64_t delta_time = time_now - tstamp->start;
-		return delta_time > 0 ? div_s64(delta_time, NSEC_PER_SEC) : 0;
+		delta_time = st->time_now - tstamp->start;
+		if (delta_time > 0)
+			delta_time = div_s64(delta_time, NSEC_PER_SEC);
+		else
+			delta_time = 0;
+
+		return seq_printf(s, "delta-time=%llu ",
+				  (unsigned long long)delta_time);
 	}
-	return -1;
-}
-
-static int ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct)
-{
-	struct ct_iter_state *st = s->private;
-	u_int64_t delta_time;
-
-	delta_time = ct_delta_time(st->time_now, ct);
-	if (delta_time < 0)
-		return 0;
-
-	return seq_printf(s, "delta-time=%llu ",
-			  (unsigned long long)delta_time);
+	return 0;
 }
 #else
 static inline int
-- 
1.7.2.3

Re: [PATCH 00/79] netfilter: netfilter update

[David Miller]

From: kaber@trash.net
Date: Wed, 19 Jan 2011 20:14:00 +0100

> Please pull from
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6.git master

Pulled, thanks.

Re: [PATCH 00/79] netfilter: netfilter update

[David Miller]

From: David Miller <davem@davemloft.net>
Date: Wed, 19 Jan 2011 13:55:04 -0800 (PST)

> From: kaber@trash.net
> Date: Wed, 19 Jan 2011 20:14:00 +0100
> 
>> Please pull from
>> 
>> git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6.git master
> 
> Pulled, thanks.

I'm undoing my pull, what was this build tested against?
In particular this commit breaks the build:

Subject: [PATCH 68/79] netfilter: xtables: add missing header files to export list

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
 ...
@@ -56,6 +56,8 @@ header-y += xt_rateest.h
 header-y += xt_realm.h
 header-y += xt_recent.h
 header-y += xt_sctp.h
+header-y += xt_secmark.h
+header-y += xt_socket.h
 header-y += xt_state.h
 header-y += xt_statistic.h
 header-y += xt_string.h

No active tree has a include/linux/netfilter/xt_secmark.h file.  Therefore
we end up with:

make[2]: `scripts/unifdef' is up to date.
make[4]: *** No rule to make target `/home/davem/src/GIT/net-next-2.6/include/linux/netfilter/xt_secmark.h', needed by `/home/davem/src/GIT/net-next-2.6/usr/include/linux/netfilter/.install'.  Stop.

Did you mean xt_SECMARK.h (caps)?

Please fix this up and resubmit your pull request, thanks.

Re: [PATCH 00/79] netfilter: netfilter update

[Jan Engelhardt]

On Thursday 2011-01-20 01:50, David Miller wrote:
>> 
>>> Please pull from
>>> 
>>> git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6.git master
>> 
>> Pulled, thanks.
>
>I'm undoing my pull, what was this build tested against?
>In particular this commit breaks the build:
>
>Subject: [PATCH 68/79] netfilter: xtables: add missing header files to export list
>
>Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
> ...
>@@ -56,6 +56,8 @@ header-y += xt_rateest.h
> header-y += xt_realm.h
> header-y += xt_recent.h
> header-y += xt_sctp.h
>+header-y += xt_secmark.h
>+header-y += xt_socket.h
> header-y += xt_state.h
> header-y += xt_statistic.h
> header-y += xt_string.h
>
>No active tree has a include/linux/netfilter/xt_secmark.h file.  Therefore
>we end up with:
>
>make[2]: `scripts/unifdef' is up to date.
>make[4]: *** No rule to make target `/home/davem/src/GIT/net-next-2.6/include/linux/netfilter/xt_secmark.h', needed by `/home/davem/src/GIT/net-next-2.6/usr/include/linux/netfilter/.install'.  Stop.
>
>Did you mean xt_SECMARK.h (caps)?

My git was weak there. The lower-case secmark line should just be removed.

Re: [PATCH 00/79] netfilter: netfilter update

[Patrick McHardy]

On 20.01.2011 01:50, David Miller wrote:
> I'm undoing my pull, what was this build tested against?

My build tests didn't include header-install. No idea what Jan
tested against.

> In particular this commit breaks the build:
> 
> Subject: [PATCH 68/79] netfilter: xtables: add missing header files to export list
> 
> Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
>  ...
> @@ -56,6 +56,8 @@ header-y += xt_rateest.h
>  header-y += xt_realm.h
>  header-y += xt_recent.h
>  header-y += xt_sctp.h
> +header-y += xt_secmark.h
> +header-y += xt_socket.h
>  header-y += xt_state.h
>  header-y += xt_statistic.h
>  header-y += xt_string.h
> 
> No active tree has a include/linux/netfilter/xt_secmark.h file.  Therefore
> we end up with:
> 
> make[2]: `scripts/unifdef' is up to date.
> make[4]: *** No rule to make target `/home/davem/src/GIT/net-next-2.6/include/linux/netfilter/xt_secmark.h', needed by `/home/davem/src/GIT/net-next-2.6/usr/include/linux/netfilter/.install'.  Stop.
> 
> Did you mean xt_SECMARK.h (caps)?

I guess so. Jan, please fix this up.

Re: [PATCH 00/79] netfilter: netfilter update

[Jan Engelhardt]

On Thursday 2011-01-20 02:13, Patrick McHardy wrote:
>> +header-y += xt_secmark.h
>> 
>> No active tree has a include/linux/netfilter/xt_secmark.h file.  Therefore
>> we end up with:
>> 
>> Did you mean xt_SECMARK.h (caps)?
>
>I guess so. Jan, please fix this up.

parent f5c88f56b35599ab9ff2d3398e0153e4cd4a4c82 (v2.6.37-3820-gf5c88f5)
commit 51c7fc9e4e086e4a145617945fdda92a8ae0290f
Author: Jan Engelhardt <jengelh@medozas.de>
Date:   Thu Jan 20 02:34:48 2011 +0100

netfilter: xtables: remove extraneous header that slipped in

Commit 0b8ad876275c74e4bfb6ec3150793f3c0ecfcee2 erroneously added
this.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 include/linux/netfilter/Kbuild |    1 -
 1 files changed, 0 insertions(+), 1 deletions(-)

diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index fc4e0aa..89c0d1e 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -56,7 +56,6 @@ header-y += xt_rateest.h
 header-y += xt_realm.h
 header-y += xt_recent.h
 header-y += xt_sctp.h
-header-y += xt_secmark.h
 header-y += xt_socket.h
 header-y += xt_state.h
 header-y += xt_statistic.h
-- 
# Created with git-export-patch

Re: [PATCH 00/79] netfilter: netfilter update

[Patrick McHardy]

On 20.01.2011 02:36, Jan Engelhardt wrote:
> netfilter: xtables: remove extraneous header that slipped in
> 
> Commit 0b8ad876275c74e4bfb6ec3150793f3c0ecfcee2 erroneously added
> this.

Please use the title when referencing commits unless its already
in Linus' tree.

Applied.