From 8fc54f68919298ff9689d980efb495707ef43f30 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Sat, 23 Aug 2014 20:58:54 +0200
Subject: net: use reciprocal_scale() helper

Replace open codings of (((u64) <x> * <y>) >> 32) with reciprocal_scale().

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/inet6_hashtables.c | 2 +-
 net/ipv6/udp.c              | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 262e13c02ec2..826019008958 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -198,7 +198,7 @@ begin:
 			}
 		} else if (score == hiscore && reuseport) {
 			matches++;
-			if (((u64)phash * matches) >> 32 == 0)
+			if (reciprocal_scale(phash, matches) == 0)
 				result = sk;
 			phash = next_pseudo_random32(phash);
 		}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4836af8f582d..25ffe737b975 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -243,7 +243,7 @@ begin:
 				goto exact_match;
 		} else if (score == badness && reuseport) {
 			matches++;
-			if (((u64)hash * matches) >> 32 == 0)
+			if (reciprocal_scale(hash, matches) == 0)
 				result = sk;
 			hash = next_pseudo_random32(hash);
 		}
@@ -323,7 +323,7 @@ begin:
 			}
 		} else if (score == badness && reuseport) {
 			matches++;
-			if (((u64)hash * matches) >> 32 == 0)
+			if (reciprocal_scale(hash, matches) == 0)
 				result = sk;
 			hash = next_pseudo_random32(hash);
 		}
-- 
cgit v1.2.3


From 149d0774a729497c6a876260d3884826088724b6 Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Fri, 22 Aug 2014 13:34:30 -0700
Subject: tcp: Call skb_gro_checksum_validate

In tcp[64]_gro_receive call skb_gro_checksum_validate to validate TCP
checksum in the gro context.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_offload.c   | 27 +++------------------------
 net/ipv6/tcpv6_offload.c | 26 +++-----------------------
 2 files changed, 6 insertions(+), 47 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index bc1b83cb8309..72912533a191 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -288,35 +288,14 @@ static int tcp_v4_gso_send_check(struct sk_buff *skb)
 
 static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 {
-	/* Use the IP hdr immediately proceeding for this transport */
-	const struct iphdr *iph = skb_gro_network_header(skb);
-	__wsum wsum;
-
 	/* Don't bother verifying checksum if we're going to flush anyway. */
-	if (NAPI_GRO_CB(skb)->flush)
-		goto skip_csum;
-
-	wsum = NAPI_GRO_CB(skb)->csum;
-
-	switch (skb->ip_summed) {
-	case CHECKSUM_NONE:
-		wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb),
-				    0);
-
-		/* fall through */
-
-	case CHECKSUM_COMPLETE:
-		if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
-				  wsum)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			break;
-		}
-
+	if (!NAPI_GRO_CB(skb)->flush &&
+	    skb_gro_checksum_validate(skb, IPPROTO_TCP,
+				      inet_gro_compute_pseudo)) {
 		NAPI_GRO_CB(skb)->flush = 1;
 		return NULL;
 	}
 
-skip_csum:
 	return tcp_gro_receive(head, skb);
 }
 
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 01b0ff9a0c2c..dbb3d9262bf6 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -35,34 +35,14 @@ static int tcp_v6_gso_send_check(struct sk_buff *skb)
 static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
 					 struct sk_buff *skb)
 {
-	const struct ipv6hdr *iph = skb_gro_network_header(skb);
-	__wsum wsum;
-
 	/* Don't bother verifying checksum if we're going to flush anyway. */
-	if (NAPI_GRO_CB(skb)->flush)
-		goto skip_csum;
-
-	wsum = NAPI_GRO_CB(skb)->csum;
-
-	switch (skb->ip_summed) {
-	case CHECKSUM_NONE:
-		wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb),
-				    wsum);
-
-		/* fall through */
-
-	case CHECKSUM_COMPLETE:
-		if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr,
-				  wsum)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			break;
-		}
-
+	if (!NAPI_GRO_CB(skb)->flush &&
+	    skb_gro_checksum_validate(skb, IPPROTO_TCP,
+				      ip6_gro_compute_pseudo)) {
 		NAPI_GRO_CB(skb)->flush = 1;
 		return NULL;
 	}
 
-skip_csum:
 	return tcp_gro_receive(head, skb);
 }
 
-- 
cgit v1.2.3


From 57c67ff4bd92af634f7c91c40eb02a96dd785dda Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Fri, 22 Aug 2014 13:34:44 -0700
Subject: udp: additional GRO support

Implement GRO for UDPv6. Add UDP checksum verification in gro_receive
for both UDP4 and UDP6 calling skb_gro_checksum_validate_zero_check.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h      | 18 +++++++++++++++
 net/ipv4/udp.c         |  1 +
 net/ipv4/udp_offload.c | 61 ++++++++++++++++++++++++++++++++++++--------------
 net/ipv6/udp_offload.c | 33 +++++++++++++++++++++++++++
 4 files changed, 96 insertions(+), 17 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/udp.h b/include/net/udp.h
index 70f941368ace..16f4e80f0519 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -158,6 +158,24 @@ static inline __sum16 udp_v4_check(int len, __be32 saddr,
 void udp_set_csum(bool nocheck, struct sk_buff *skb,
 		  __be32 saddr, __be32 daddr, int len);
 
+struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
+				 struct udphdr *uh);
+int udp_gro_complete(struct sk_buff *skb, int nhoff);
+
+static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
+{
+	struct udphdr *uh;
+	unsigned int hlen, off;
+
+	off  = skb_gro_offset(skb);
+	hlen = off + sizeof(*uh);
+	uh   = skb_gro_header_fast(skb, off);
+	if (skb_gro_header_hard(skb, hlen))
+		uh = skb_gro_header_slow(skb, hlen, off);
+
+	return uh;
+}
+
 /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
 static inline void udp_lib_hash(struct sock *sk)
 {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 32f9571e776b..3549c21fe5f7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -99,6 +99,7 @@
 #include <linux/slab.h>
 #include <net/tcp_states.h>
 #include <linux/skbuff.h>
+#include <linux/netdevice.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <net/net_namespace.h>
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 59035bc3008d..8ed460e3753c 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -228,29 +228,22 @@ unlock:
 }
 EXPORT_SYMBOL(udp_del_offload);
 
-static struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
+				 struct udphdr *uh)
 {
 	struct udp_offload_priv *uo_priv;
 	struct sk_buff *p, **pp = NULL;
-	struct udphdr *uh, *uh2;
-	unsigned int hlen, off;
+	struct udphdr *uh2;
+	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
 
 	if (NAPI_GRO_CB(skb)->udp_mark ||
-	    (!skb->encapsulation && skb->ip_summed != CHECKSUM_COMPLETE))
+	    (!skb->encapsulation && !NAPI_GRO_CB(skb)->csum_valid))
 		goto out;
 
 	/* mark that this skb passed once through the udp gro layer */
 	NAPI_GRO_CB(skb)->udp_mark = 1;
-
-	off  = skb_gro_offset(skb);
-	hlen = off + sizeof(*uh);
-	uh   = skb_gro_header_fast(skb, off);
-	if (skb_gro_header_hard(skb, hlen)) {
-		uh = skb_gro_header_slow(skb, hlen, off);
-		if (unlikely(!uh))
-			goto out;
-	}
+	NAPI_GRO_CB(skb)->encapsulation++;
 
 	rcu_read_lock();
 	uo_priv = rcu_dereference(udp_offload_base);
@@ -269,7 +262,12 @@ unflush:
 			continue;
 
 		uh2 = (struct udphdr   *)(p->data + off);
-		if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) {
+
+		/* Match ports and either checksums are either both zero
+		 * or nonzero.
+		 */
+		if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) ||
+		    (!uh->check ^ !uh2->check)) {
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
 		}
@@ -286,7 +284,24 @@ out:
 	return pp;
 }
 
-static int udp_gro_complete(struct sk_buff *skb, int nhoff)
+static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_gro_udphdr(skb);
+
+	/* Don't bother verifying checksum if we're going to flush anyway. */
+	if (unlikely(!uh) ||
+	    (!NAPI_GRO_CB(skb)->flush &&
+	     skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
+						  inet_gro_compute_pseudo))) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	return udp_gro_receive(head, skb, uh);
+}
+
+int udp_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	struct udp_offload_priv *uo_priv;
 	__be16 newlen = htons(skb->len - nhoff);
@@ -311,12 +326,24 @@ static int udp_gro_complete(struct sk_buff *skb, int nhoff)
 	return err;
 }
 
+int udp4_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
+
+	if (uh->check)
+		uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
+					  iph->daddr, 0);
+
+	return udp_gro_complete(skb, nhoff);
+}
+
 static const struct net_offload udpv4_offload = {
 	.callbacks = {
 		.gso_send_check = udp4_ufo_send_check,
 		.gso_segment = udp4_ufo_fragment,
-		.gro_receive  =	udp_gro_receive,
-		.gro_complete =	udp_gro_complete,
+		.gro_receive  =	udp4_gro_receive,
+		.gro_complete =	udp4_gro_complete,
 	},
 };
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 0ae3d98f83e0..b13e377e9c53 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -10,6 +10,7 @@
  *      UDPv6 GSO support
  */
 #include <linux/skbuff.h>
+#include <linux/netdevice.h>
 #include <net/protocol.h>
 #include <net/ipv6.h>
 #include <net/udp.h>
@@ -127,10 +128,42 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 out:
 	return segs;
 }
+
+static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_gro_udphdr(skb);
+
+	/* Don't bother verifying checksum if we're going to flush anyway. */
+	if (unlikely(!uh) ||
+	    (!NAPI_GRO_CB(skb)->flush &&
+	     skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
+						  ip6_gro_compute_pseudo))) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	return udp_gro_receive(head, skb, uh);
+}
+
+int udp6_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
+
+	if (uh->check)
+		uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr,
+					  &ipv6h->daddr, 0);
+
+	return udp_gro_complete(skb, nhoff);
+}
+
 static const struct net_offload udpv6_offload = {
 	.callbacks = {
 		.gso_send_check =	udp6_ufo_send_check,
 		.gso_segment	=	udp6_ufo_fragment,
+		.gro_receive	=	udp6_gro_receive,
+		.gro_complete	=	udp6_gro_complete,
 	},
 };
 
-- 
cgit v1.2.3


From 67ba4152e8b77eada6a9c64e3c2c84d6112794fc Mon Sep 17 00:00:00 2001
From: Ian Morris
Date: Sun, 24 Aug 2014 21:53:10 +0100
Subject: ipv6: White-space cleansing : Line Layouts

This patch makes no changes to the logic of the code but simply addresses
coding style issues as detected by checkpatch.

Both objdump and diff -w show no differences.

A number of items are addressed in this patch:
* Multiple spaces converted to tabs
* Spaces before tabs removed.
* Spaces in pointer typing cleansed (char *)foo etc.
* Remove space after sizeof
* Ensure spacing around comparators such as if statements.

Signed-off-by: Ian Morris <ipm@chirality.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c              |  12 ++---
 net/ipv6/af_inet6.c              |  12 ++---
 net/ipv6/ah6.c                   |  16 +++----
 net/ipv6/datagram.c              |   8 ++--
 net/ipv6/esp6.c                  |   8 ++--
 net/ipv6/exthdrs.c               |   2 +-
 net/ipv6/icmp.c                  |  10 ++--
 net/ipv6/inet6_connection_sock.c |   2 +-
 net/ipv6/inet6_hashtables.c      |   2 +-
 net/ipv6/ip6_flowlabel.c         |  18 +++----
 net/ipv6/ip6_icmp.c              |   2 +-
 net/ipv6/ip6_input.c             |   6 +--
 net/ipv6/ip6_offload.c           |   2 +-
 net/ipv6/ip6_output.c            |  20 ++++----
 net/ipv6/ip6_tunnel.c            |  32 ++++++-------
 net/ipv6/ip6mr.c                 |   4 +-
 net/ipv6/ipv6_sockglue.c         |  22 ++++-----
 net/ipv6/mcast.c                 | 100 +++++++++++++++++++--------------------
 net/ipv6/ndisc.c                 |  16 +++----
 net/ipv6/output_core.c           |   2 +-
 net/ipv6/proc.c                  |   2 +-
 net/ipv6/raw.c                   |   8 ++--
 net/ipv6/reassembly.c            |   6 +--
 net/ipv6/route.c                 |  20 ++++----
 net/ipv6/sit.c                   |  12 ++---
 net/ipv6/tunnel6.c               |   2 +-
 net/ipv6/udp.c                   |  18 +++----
 net/ipv6/xfrm6_input.c           |   4 +-
 net/ipv6/xfrm6_policy.c          |  22 ++++-----
 net/ipv6/xfrm6_state.c           |  14 +++---
 net/ipv6/xfrm6_tunnel.c          |   2 +-
 31 files changed, 203 insertions(+), 203 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 0b239fc1816e..267ce3caee24 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -180,7 +180,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.rtr_solicits		= MAX_RTR_SOLICITATIONS,
 	.rtr_solicit_interval	= RTR_SOLICITATION_INTERVAL,
 	.rtr_solicit_delay	= MAX_RTR_SOLICITATION_DELAY,
-	.use_tempaddr 		= 0,
+	.use_tempaddr		= 0,
 	.temp_valid_lft		= TEMP_VALID_LIFETIME,
 	.temp_prefered_lft	= TEMP_PREFERRED_LIFETIME,
 	.regen_max_retry	= REGEN_MAX_RETRY,
@@ -1105,8 +1105,8 @@ retry:
 	spin_unlock_bh(&ifp->lock);
 
 	regen_advance = idev->cnf.regen_max_retry *
-	                idev->cnf.dad_transmits *
-	                NEIGH_VAR(idev->nd_parms, RETRANS_TIME) / HZ;
+			idev->cnf.dad_transmits *
+			NEIGH_VAR(idev->nd_parms, RETRANS_TIME) / HZ;
 	write_unlock_bh(&idev->lock);
 
 	/* A temporary address is created only if this calculated Preferred
@@ -3035,7 +3035,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 		struct hlist_head *h = &inet6_addr_lst[i];
 
 		spin_lock_bh(&addrconf_hash_lock);
-	restart:
+restart:
 		hlist_for_each_entry_rcu(ifa, h, addr_lst) {
 			if (ifa->idev == idev) {
 				hlist_del_init_rcu(&ifa->addr_lst);
@@ -3547,8 +3547,8 @@ static void __net_exit if6_proc_net_exit(struct net *net)
 }
 
 static struct pernet_operations if6_proc_net_ops = {
-       .init = if6_proc_net_init,
-       .exit = if6_proc_net_exit,
+	.init = if6_proc_net_init,
+	.exit = if6_proc_net_exit,
 };
 
 int __init if6_proc_init(void)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 2daa3a133e49..b9393e6a21fe 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -7,15 +7,15 @@
  *
  *	Adapted from linux/net/ipv4/af_inet.c
  *
- * 	Fixes:
+ *	Fixes:
  *	piggy, Karl Knutson	:	Socket protocol table
- * 	Hideaki YOSHIFUJI	:	sin6_scope_id support
- * 	Arnaldo Melo		: 	check proc_net_create return, cleanups
+ *	Hideaki YOSHIFUJI	:	sin6_scope_id support
+ *	Arnaldo Melo		:	check proc_net_create return, cleanups
  *
  *	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.
+ *	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.
  */
 
 #define pr_fmt(fmt) "IPv6: " fmt
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 72a4930bdc0a..ac71d9e0a500 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -17,10 +17,10 @@
  * Authors
  *
  *	Mitsuru KANDA @USAGI       : IPv6 Support
- * 	Kazunori MIYAZAWA @USAGI   :
- * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ *	Kazunori MIYAZAWA @USAGI   :
+ *	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
  *
- * 	This file is derived from net/ipv4/ah.c.
+ *	This file is derived from net/ipv4/ah.c.
  */
 
 #define pr_fmt(fmt) "IPv6: " fmt
@@ -284,7 +284,7 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir)
 			ipv6_rearrange_rthdr(iph, exthdr.rth);
 			break;
 
-		default :
+		default:
 			return 0;
 		}
 
@@ -478,7 +478,7 @@ static void ah6_input_done(struct crypto_async_request *base, int err)
 	auth_data = ah_tmp_auth(work_iph, hdr_len);
 	icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len);
 
-	err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0;
+	err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0;
 	if (err)
 		goto out;
 
@@ -622,7 +622,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
 		goto out_free;
 	}
 
-	err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0;
+	err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0;
 	if (err)
 		goto out_free;
 
@@ -647,8 +647,8 @@ static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		   u8 type, u8 code, int offset, __be32 info)
 {
 	struct net *net = dev_net(skb->dev);
-	struct ipv6hdr *iph = (struct ipv6hdr*)skb->data;
-	struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset);
+	struct ipv6hdr *iph = (struct ipv6hdr *)skb->data;
+	struct ip_auth_hdr *ah = (struct ip_auth_hdr *)(skb->data+offset);
 	struct xfrm_state *x;
 
 	if (type != ICMPV6_PKT_TOOBIG &&
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2753319524f1..1844e874a350 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -43,13 +43,13 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a)
 int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
-	struct inet_sock      	*inet = inet_sk(sk);
-	struct ipv6_pinfo      	*np = inet6_sk(sk);
-	struct in6_addr		*daddr, *final_p, final;
+	struct inet_sock	*inet = inet_sk(sk);
+	struct ipv6_pinfo	*np = inet6_sk(sk);
+	struct in6_addr	*daddr, *final_p, final;
 	struct dst_entry	*dst;
 	struct flowi6		fl6;
 	struct ip6_flowlabel	*flowlabel = NULL;
-	struct ipv6_txoptions   *opt;
+	struct ipv6_txoptions	*opt;
 	int			addr_type;
 	int			err;
 
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index d15da1377149..7b6e830ebc6d 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -17,10 +17,10 @@
  * Authors
  *
  *	Mitsuru KANDA @USAGI       : IPv6 Support
- * 	Kazunori MIYAZAWA @USAGI   :
- * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ *	Kazunori MIYAZAWA @USAGI   :
+ *	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
  *
- * 	This file is derived from net/ipv4/esp.c
+ *	This file is derived from net/ipv4/esp.c
  */
 
 #define pr_fmt(fmt) "IPv6: " fmt
@@ -598,7 +598,7 @@ static int esp6_init_state(struct xfrm_state *x)
 	case XFRM_MODE_BEET:
 		if (x->sel.family != AF_INET6)
 			x->props.header_len += IPV4_BEET_PHMAXLEN +
-				               (sizeof(struct ipv6hdr) - sizeof(struct iphdr));
+					       (sizeof(struct ipv6hdr) - sizeof(struct iphdr));
 		break;
 	case XFRM_MODE_TRANSPORT:
 		break;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 8d67900aa003..bfde361b6134 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -142,7 +142,7 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb)
 		default: /* Other TLV code so scan list */
 			if (optlen > len)
 				goto bad;
-			for (curr=procs; curr->type >= 0; curr++) {
+			for (curr = procs; curr->type >= 0; curr++) {
 				if (curr->type == nh[off]) {
 					/* type specific length/alignment
 					   checks will be performed in the
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 06ba3e58320b..394bb824fe4b 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -503,7 +503,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	msg.type = type;
 
 	len = skb->len - msg.offset;
-	len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) -sizeof(struct icmp6hdr));
+	len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr));
 	if (len < 0) {
 		LIMIT_NETDEBUG(KERN_DEBUG "icmp: len problem\n");
 		goto out_dst_release;
@@ -636,7 +636,7 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
 		/* now skip over extension headers */
 		inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
 						&nexthdr, &frag_off);
-		if (inner_offset<0)
+		if (inner_offset < 0)
 			goto out;
 	} else {
 		inner_offset = sizeof(struct ipv6hdr);
@@ -808,7 +808,7 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->saddr = *saddr;
 	fl6->daddr = *daddr;
-	fl6->flowi6_proto 	= IPPROTO_ICMPV6;
+	fl6->flowi6_proto	= IPPROTO_ICMPV6;
 	fl6->fl6_icmp_type	= type;
 	fl6->fl6_icmp_code	= 0;
 	fl6->flowi6_oif		= oif;
@@ -875,8 +875,8 @@ static void __net_exit icmpv6_sk_exit(struct net *net)
 }
 
 static struct pernet_operations icmpv6_sk_ops = {
-       .init = icmpv6_sk_init,
-       .exit = icmpv6_sk_exit,
+	.init = icmpv6_sk_init,
+	.exit = icmpv6_sk_exit,
 };
 
 int __init icmpv6_init(void)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index a245e5ddffbd..8c33a0b52b64 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -163,7 +163,7 @@ void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
 
 EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add);
 
-void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
+void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
 {
 	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;
 
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 826019008958..5f7927c06f18 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -6,7 +6,7 @@
  *		Generic INET6 transport hashtables
  *
  * Authors:	Lotsa people, from code originally in tcp, generalised here
- * 		by Arnaldo Carvalho de Melo <acme@mandriva.com>
+ *		by Arnaldo Carvalho de Melo <acme@mandriva.com>
  *
  *	This program is free software; you can redistribute it and/or
  *      modify it under the terms of the GNU General Public License
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 4052694c6f2c..2ace4749bef4 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -136,7 +136,7 @@ static void ip6_fl_gc(unsigned long dummy)
 
 	spin_lock(&ip6_fl_lock);
 
-	for (i=0; i<=FL_HASH_MASK; i++) {
+	for (i = 0; i <= FL_HASH_MASK; i++) {
 		struct ip6_flowlabel *fl;
 		struct ip6_flowlabel __rcu **flp;
 
@@ -239,7 +239,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net,
 
 /* Socket flowlabel lists */
 
-struct ip6_flowlabel * fl6_sock_lookup(struct sock *sk, __be32 label)
+struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label)
 {
 	struct ipv6_fl_socklist *sfl;
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -293,11 +293,11 @@ void fl6_free_socklist(struct sock *sk)
    following rthdr.
  */
 
-struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space,
-					 struct ip6_flowlabel * fl,
-					 struct ipv6_txoptions * fopt)
+struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
+					 struct ip6_flowlabel *fl,
+					 struct ipv6_txoptions *fopt)
 {
-	struct ipv6_txoptions * fl_opt = fl->opt;
+	struct ipv6_txoptions *fl_opt = fl->opt;
 
 	if (fopt == NULL || fopt->opt_flen == 0)
 		return fl_opt;
@@ -388,7 +388,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 			goto done;
 
 		msg.msg_controllen = olen;
-		msg.msg_control = (void*)(fl->opt+1);
+		msg.msg_control = (void *)(fl->opt+1);
 		memset(&flowi6, 0, sizeof(flowi6));
 
 		err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt,
@@ -517,7 +517,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 	struct net *net = sock_net(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct in6_flowlabel_req freq;
-	struct ipv6_fl_socklist *sfl1=NULL;
+	struct ipv6_fl_socklist *sfl1 = NULL;
 	struct ipv6_fl_socklist *sfl;
 	struct ipv6_fl_socklist __rcu **sflp;
 	struct ip6_flowlabel *fl, *fl1 = NULL;
@@ -542,7 +542,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 		}
 		spin_lock_bh(&ip6_sk_fl_lock);
 		for (sflp = &np->ipv6_fl_list;
-		     (sfl = rcu_dereference(*sflp))!=NULL;
+		     (sfl = rcu_dereference(*sflp)) != NULL;
 		     sflp = &sfl->next) {
 			if (sfl->fl->label == freq.flr_label) {
 				if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 4578e23834f7..14dacc544c3e 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -13,7 +13,7 @@ static ip6_icmp_send_t __rcu *ip6_icmp_send;
 int inet6_register_icmp_sender(ip6_icmp_send_t *fn)
 {
 	return (cmpxchg((ip6_icmp_send_t **)&ip6_icmp_send, NULL, fn) == NULL) ?
-	        0 : -EBUSY;
+		0 : -EBUSY;
 }
 EXPORT_SYMBOL(inet6_register_icmp_sender);
 
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 51d54dc376f3..a3084ab5df6c 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -15,8 +15,8 @@
  */
 /* Changes
  *
- * 	Mitsuru KANDA @USAGI and
- * 	YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs().
+ *	Mitsuru KANDA @USAGI and
+ *	YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs().
  */
 
 #include <linux/errno.h>
@@ -65,7 +65,7 @@ int ip6_rcv_finish(struct sk_buff *skb)
 int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
 {
 	const struct ipv6hdr *hdr;
-	u32 		pkt_len;
+	u32 pkt_len;
 	struct inet6_dev *idev;
 	struct net *net = dev_net(skb->dev);
 
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 65eda2a8af48..5bcda338bcef 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -244,7 +244,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 			continue;
 
 		iph2 = (struct ipv6hdr *)(p->data + off);
-		first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ;
+		first_word = *(__be32 *)iph ^ *(__be32 *)iph2;
 
 		/* All fields must match except length and Traffic Class.
 		 * XXX skbs on the gro_list have all been parsed and pulled
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 315a55d66079..4ead5547b5c6 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -20,7 +20,7 @@
  *				etc.
  *
  *      H. von Brand    :       Added missing #include <linux/string.h>
- *	Imran Patel	: 	frag id should be in NBO
+ *	Imran Patel	:	frag id should be in NBO
  *      Kazunori MIYAZAWA @USAGI
  *			:       add ip6_append_data and related functions
  *				for datagram xmit
@@ -555,14 +555,14 @@ static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
-	struct rt6_info *rt = (struct rt6_info*)skb_dst(skb);
+	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
 	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
 	unsigned int mtu, hlen, left, len;
 	int hroom, troom;
 	__be32 frag_id = 0;
-	int ptr, offset = 0, err=0;
+	int ptr, offset = 0, err = 0;
 	u8 *prevhdr, nexthdr = 0;
 	struct net *net = dev_net(skb_dst(skb)->dev);
 
@@ -637,7 +637,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 		}
 
 		__skb_pull(skb, hlen);
-		fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr));
+		fh = (struct frag_hdr *)__skb_push(skb, sizeof(struct frag_hdr));
 		__skb_push(skb, hlen);
 		skb_reset_network_header(skb);
 		memcpy(skb_network_header(skb), tmp_hdr, hlen);
@@ -662,7 +662,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 			if (frag) {
 				frag->ip_summed = CHECKSUM_NONE;
 				skb_reset_transport_header(frag);
-				fh = (struct frag_hdr*)__skb_push(frag, sizeof(struct frag_hdr));
+				fh = (struct frag_hdr *)__skb_push(frag, sizeof(struct frag_hdr));
 				__skb_push(frag, hlen);
 				skb_reset_network_header(frag);
 				memcpy(skb_network_header(frag), tmp_hdr,
@@ -681,7 +681,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 			}
 
 			err = output(skb);
-			if(!err)
+			if (!err)
 				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 					      IPSTATS_MIB_FRAGCREATES);
 
@@ -742,7 +742,7 @@ slow_path:
 	/*
 	 *	Keep copying data until we run out.
 	 */
-	while(left > 0)	{
+	while (left > 0)	{
 		len = left;
 		/* IF: it doesn't fit, use 'mtu' - the data space left */
 		if (len > mtu)
@@ -865,7 +865,7 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
 	/* Yes, checking route validity in not connected
 	 * case is not very simple. Take into account,
 	 * that we do not support routing by source, TOS,
-	 * and MSG_DONTROUTE 		--ANK (980726)
+	 * and MSG_DONTROUTE		--ANK (980726)
 	 *
 	 * 1. ip6_rt_check(): If route was host route,
 	 *    check that cached destination is current.
@@ -1049,7 +1049,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 			int getfrag(void *from, char *to, int offset, int len,
 			int odd, struct sk_buff *skb),
 			void *from, int length, int hh_len, int fragheaderlen,
-			int transhdrlen, int mtu,unsigned int flags,
+			int transhdrlen, int mtu, unsigned int flags,
 			struct rt6_info *rt)
 
 {
@@ -1072,7 +1072,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		skb_reserve(skb, hh_len);
 
 		/* create space for UDP/IP header */
-		skb_put(skb,fragheaderlen + transhdrlen);
+		skb_put(skb, fragheaderlen + transhdrlen);
 
 		/* initialize network header pointer */
 		skb_reset_network_header(skb);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index f9de5a695072..e01bd0399297 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -408,12 +408,12 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 {
 	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw;
 	__u8 nexthdr = ipv6h->nexthdr;
-	__u16 off = sizeof (*ipv6h);
+	__u16 off = sizeof(*ipv6h);
 
 	while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
 		__u16 optlen = 0;
 		struct ipv6_opt_hdr *hdr;
-		if (raw + off + sizeof (*hdr) > skb->data &&
+		if (raw + off + sizeof(*hdr) > skb->data &&
 		    !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr)))
 			break;
 
@@ -530,7 +530,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
 
-		if ((len = sizeof (*ipv6h) + ntohs(ipv6h->payload_len)) > mtu) {
+		if ((len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len)) > mtu) {
 			rel_type = ICMPV6_PKT_TOOBIG;
 			rel_code = 0;
 			rel_info = mtu;
@@ -991,7 +991,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 				     t->parms.name);
 		goto tx_err_dst_release;
 	}
-	mtu = dst_mtu(dst) - sizeof (*ipv6h);
+	mtu = dst_mtu(dst) - sizeof(*ipv6h);
 	if (encap_limit >= 0) {
 		max_headroom += 8;
 		mtu -= 8;
@@ -1083,7 +1083,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		encap_limit = t->parms.encap_limit;
 
-	memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6));
+	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
 	fl6.flowi6_proto = IPPROTO_IPIP;
 
 	dsfield = ipv4_get_dsfield(iph);
@@ -1135,7 +1135,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		encap_limit = t->parms.encap_limit;
 
-	memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6));
+	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
 	fl6.flowi6_proto = IPPROTO_IPV6;
 
 	dsfield = ipv6_get_dsfield(ipv6h);
@@ -1229,11 +1229,11 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 
 		if (rt->dst.dev) {
 			dev->hard_header_len = rt->dst.dev->hard_header_len +
-				sizeof (struct ipv6hdr);
+				sizeof(struct ipv6hdr);
 
-			dev->mtu = rt->dst.dev->mtu - sizeof (struct ipv6hdr);
+			dev->mtu = rt->dst.dev->mtu - sizeof(struct ipv6hdr);
 			if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
-				dev->mtu-=8;
+				dev->mtu -= 8;
 
 			if (dev->mtu < IPV6_MIN_MTU)
 				dev->mtu = IPV6_MIN_MTU;
@@ -1350,7 +1350,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	switch (cmd) {
 	case SIOCGETTUNNEL:
 		if (dev == ip6n->fb_tnl_dev) {
-			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) {
+			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
 				err = -EFAULT;
 				break;
 			}
@@ -1362,7 +1362,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			memset(&p, 0, sizeof(p));
 		}
 		ip6_tnl_parm_to_user(&p, &t->parms);
-		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof (p))) {
+		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) {
 			err = -EFAULT;
 		}
 		break;
@@ -1372,7 +1372,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			break;
 		err = -EFAULT;
-		if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p)))
+		if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
 			break;
 		err = -EINVAL;
 		if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP &&
@@ -1407,7 +1407,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 		if (dev == ip6n->fb_tnl_dev) {
 			err = -EFAULT;
-			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p)))
+			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
 				break;
 			err = -ENOENT;
 			ip6_tnl_parm_from_user(&p1, &p);
@@ -1482,11 +1482,11 @@ static void ip6_tnl_dev_setup(struct net_device *dev)
 	dev->destructor = ip6_dev_free;
 
 	dev->type = ARPHRD_TUNNEL6;
-	dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr);
-	dev->mtu = ETH_DATA_LEN - sizeof (struct ipv6hdr);
+	dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
+	dev->mtu = ETH_DATA_LEN - sizeof(struct ipv6hdr);
 	t = netdev_priv(dev);
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
-		dev->mtu-=8;
+		dev->mtu -= 8;
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
 	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index f9a3fd320d1d..0171f08325c3 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -845,7 +845,7 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c)
 
 	atomic_dec(&mrt->cache_resolve_queue_len);
 
-	while((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) {
+	while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) {
 		if (ipv6_hdr(skb)->version == 0) {
 			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
 			nlh->nlmsg_type = NLMSG_ERROR;
@@ -1103,7 +1103,7 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt,
 	 *	Play the pending entries through our router
 	 */
 
-	while((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) {
+	while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) {
 		if (ipv6_hdr(skb)->version == 0) {
 			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 0c289982796d..64177efe5cca 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -66,12 +66,12 @@ int ip6_ra_control(struct sock *sk, int sel)
 	if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_RAW)
 		return -ENOPROTOOPT;
 
-	new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
+	new_ra = (sel >= 0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
 
 	write_lock_bh(&ip6_ra_lock);
-	for (rap = &ip6_ra_chain; (ra=*rap) != NULL; rap = &ra->next) {
+	for (rap = &ip6_ra_chain; (ra = *rap) != NULL; rap = &ra->next) {
 		if (ra->sk == sk) {
-			if (sel>=0) {
+			if (sel >= 0) {
 				write_unlock_bh(&ip6_ra_lock);
 				kfree(new_ra);
 				return -EADDRINUSE;
@@ -130,7 +130,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 	int retv = -ENOPROTOOPT;
 
 	if (optval == NULL)
-		val=0;
+		val = 0;
 	else {
 		if (optlen >= sizeof(int)) {
 			if (get_user(val, (int __user *) optval))
@@ -139,7 +139,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 			val = 0;
 	}
 
-	valbool = (val!=0);
+	valbool = (val != 0);
 
 	if (ip6_mroute_opt(optname))
 		return ip6_mroute_setsockopt(sk, optname, optval, optlen);
@@ -474,7 +474,7 @@ sticky_done:
 			goto done;
 
 		msg.msg_controllen = optlen;
-		msg.msg_control = (void*)(opt+1);
+		msg.msg_control = (void *)(opt+1);
 
 		retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk,
 					     &junk, &junk);
@@ -687,7 +687,7 @@ done:
 			retv = -ENOBUFS;
 			break;
 		}
-		gsf = kmalloc(optlen,GFP_KERNEL);
+		gsf = kmalloc(optlen, GFP_KERNEL);
 		if (!gsf) {
 			retv = -ENOBUFS;
 			break;
@@ -921,7 +921,7 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt,
 	if (!opt)
 		return 0;
 
-	switch(optname) {
+	switch (optname) {
 	case IPV6_HOPOPTS:
 		hdr = opt->hopopt;
 		break;
@@ -1284,9 +1284,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		return -ENOPROTOOPT;
 	}
 	len = min_t(unsigned int, sizeof(int), len);
-	if(put_user(len, optlen))
+	if (put_user(len, optlen))
 		return -EFAULT;
-	if(copy_to_user(optval,&val,len))
+	if (copy_to_user(optval, &val, len))
 		return -EFAULT;
 	return 0;
 }
@@ -1299,7 +1299,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname,
 	if (level == SOL_IP && sk->sk_type != SOCK_RAW)
 		return udp_prot.getsockopt(sk, level, optname, optval, optlen);
 
-	if(level != SOL_IPV6)
+	if (level != SOL_IPV6)
 		return -ENOPROTOOPT;
 
 	err = do_ipv6_getsockopt(sk, level, optname, optval, optlen, 0);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 617f0958e164..70881795da96 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -232,7 +232,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	spin_lock(&ipv6_sk_mc_lock);
 	for (lnk = &np->ipv6_mc_list;
 	     (mc_lst = rcu_dereference_protected(*lnk,
-			lockdep_is_held(&ipv6_sk_mc_lock))) !=NULL ;
+			lockdep_is_held(&ipv6_sk_mc_lock))) != NULL;
 	      lnk = &mc_lst->next) {
 		if ((ifindex == 0 || mc_lst->ifindex == ifindex) &&
 		    ipv6_addr_equal(&mc_lst->addr, addr)) {
@@ -390,7 +390,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 		if (!psl)
 			goto done;	/* err = -EADDRNOTAVAIL */
 		rv = !0;
-		for (i=0; i<psl->sl_count; i++) {
+		for (i = 0; i < psl->sl_count; i++) {
 			rv = !ipv6_addr_equal(&psl->sl_addr[i], source);
 			if (rv == 0)
 				break;
@@ -407,7 +407,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 		/* update the interface filter */
 		ip6_mc_del_src(idev, group, omode, 1, source, 1);
 
-		for (j=i+1; j<psl->sl_count; j++)
+		for (j = i+1; j < psl->sl_count; j++)
 			psl->sl_addr[j-1] = psl->sl_addr[j];
 		psl->sl_count--;
 		err = 0;
@@ -433,19 +433,19 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 		newpsl->sl_max = count;
 		newpsl->sl_count = count - IP6_SFBLOCK;
 		if (psl) {
-			for (i=0; i<psl->sl_count; i++)
+			for (i = 0; i < psl->sl_count; i++)
 				newpsl->sl_addr[i] = psl->sl_addr[i];
 			sock_kfree_s(sk, psl, IP6_SFLSIZE(psl->sl_max));
 		}
 		pmc->sflist = psl = newpsl;
 	}
 	rv = 1;	/* > 0 for insert logic below if sl_count is 0 */
-	for (i=0; i<psl->sl_count; i++) {
+	for (i = 0; i < psl->sl_count; i++) {
 		rv = !ipv6_addr_equal(&psl->sl_addr[i], source);
 		if (rv == 0) /* There is an error in the address. */
 			goto done;
 	}
-	for (j=psl->sl_count-1; j>=i; j--)
+	for (j = psl->sl_count-1; j >= i; j--)
 		psl->sl_addr[j+1] = psl->sl_addr[j];
 	psl->sl_addr[i] = *source;
 	psl->sl_count++;
@@ -514,7 +514,7 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf)
 			goto done;
 		}
 		newpsl->sl_max = newpsl->sl_count = gsf->gf_numsrc;
-		for (i=0; i<newpsl->sl_count; ++i) {
+		for (i = 0; i < newpsl->sl_count; ++i) {
 			struct sockaddr_in6 *psin6;
 
 			psin6 = (struct sockaddr_in6 *)&gsf->gf_slist[i];
@@ -606,7 +606,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 	 * on ipv6_sk_mc_lock and a write lock on pmc->sflock. We
 	 * have the socket lock, so reading here is safe.
 	 */
-	for (i=0; i<copycount; i++) {
+	for (i = 0; i < copycount; i++) {
 		struct sockaddr_in6 *psin6;
 		struct sockaddr_storage ss;
 
@@ -648,7 +648,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
 	} else {
 		int i;
 
-		for (i=0; i<psl->sl_count; i++) {
+		for (i = 0; i < psl->sl_count; i++) {
 			if (ipv6_addr_equal(&psl->sl_addr[i], src_addr))
 				break;
 		}
@@ -762,7 +762,7 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 		pmc->mca_tomb = im->mca_tomb;
 		pmc->mca_sources = im->mca_sources;
 		im->mca_tomb = im->mca_sources = NULL;
-		for (psf=pmc->mca_sources; psf; psf=psf->sf_next)
+		for (psf = pmc->mca_sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = pmc->mca_crcount;
 	}
 	spin_unlock_bh(&im->mca_lock);
@@ -780,7 +780,7 @@ static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca)
 
 	spin_lock_bh(&idev->mc_lock);
 	pmc_prev = NULL;
-	for (pmc=idev->mc_tomb; pmc; pmc=pmc->next) {
+	for (pmc = idev->mc_tomb; pmc; pmc = pmc->next) {
 		if (ipv6_addr_equal(&pmc->mca_addr, pmca))
 			break;
 		pmc_prev = pmc;
@@ -794,7 +794,7 @@ static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca)
 	spin_unlock_bh(&idev->mc_lock);
 
 	if (pmc) {
-		for (psf=pmc->mca_tomb; psf; psf=psf_next) {
+		for (psf = pmc->mca_tomb; psf; psf = psf_next) {
 			psf_next = psf->sf_next;
 			kfree(psf);
 		}
@@ -821,14 +821,14 @@ static void mld_clear_delrec(struct inet6_dev *idev)
 
 	/* clear dead sources, too */
 	read_lock_bh(&idev->lock);
-	for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+	for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
 		struct ip6_sf_list *psf, *psf_next;
 
 		spin_lock_bh(&pmc->mca_lock);
 		psf = pmc->mca_tomb;
 		pmc->mca_tomb = NULL;
 		spin_unlock_bh(&pmc->mca_lock);
-		for (; psf; psf=psf_next) {
+		for (; psf; psf = psf_next) {
 			psf_next = psf->sf_next;
 			kfree(psf);
 		}
@@ -917,7 +917,7 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr)
 	struct ifmcaddr6 *ma, **map;
 
 	write_lock_bh(&idev->lock);
-	for (map = &idev->mc_list; (ma=*map) != NULL; map = &ma->next) {
+	for (map = &idev->mc_list; (ma = *map) != NULL; map = &ma->next) {
 		if (ipv6_addr_equal(&ma->mca_addr, addr)) {
 			if (--ma->mca_users == 0) {
 				*map = ma->next;
@@ -968,7 +968,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
 	idev = __in6_dev_get(dev);
 	if (idev) {
 		read_lock_bh(&idev->lock);
-		for (mc = idev->mc_list; mc; mc=mc->next) {
+		for (mc = idev->mc_list; mc; mc = mc->next) {
 			if (ipv6_addr_equal(&mc->mca_addr, group))
 				break;
 		}
@@ -977,7 +977,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
 				struct ip6_sf_list *psf;
 
 				spin_lock_bh(&mc->mca_lock);
-				for (psf=mc->mca_sources;psf;psf=psf->sf_next) {
+				for (psf = mc->mca_sources; psf; psf = psf->sf_next) {
 					if (ipv6_addr_equal(&psf->sf_addr, src_addr))
 						break;
 				}
@@ -986,7 +986,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
 						psf->sf_count[MCAST_EXCLUDE] !=
 						mc->mca_sfcount[MCAST_EXCLUDE];
 				else
-					rv = mc->mca_sfcount[MCAST_EXCLUDE] !=0;
+					rv = mc->mca_sfcount[MCAST_EXCLUDE] != 0;
 				spin_unlock_bh(&mc->mca_lock);
 			} else
 				rv = true; /* don't filter unspecified source */
@@ -1077,10 +1077,10 @@ static bool mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs,
 	int i, scount;
 
 	scount = 0;
-	for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
 		if (scount == nsrcs)
 			break;
-		for (i=0; i<nsrcs; i++) {
+		for (i = 0; i < nsrcs; i++) {
 			/* skip inactive filters */
 			if (psf->sf_count[MCAST_INCLUDE] ||
 			    pmc->mca_sfcount[MCAST_EXCLUDE] !=
@@ -1110,10 +1110,10 @@ static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs,
 	/* mark INCLUDE-mode sources */
 
 	scount = 0;
-	for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
 		if (scount == nsrcs)
 			break;
-		for (i=0; i<nsrcs; i++) {
+		for (i = 0; i < nsrcs; i++) {
 			if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) {
 				psf->sf_gsresp = 1;
 				scount++;
@@ -1364,13 +1364,13 @@ int igmp6_event_query(struct sk_buff *skb)
 
 	read_lock_bh(&idev->lock);
 	if (group_type == IPV6_ADDR_ANY) {
-		for (ma = idev->mc_list; ma; ma=ma->next) {
+		for (ma = idev->mc_list; ma; ma = ma->next) {
 			spin_lock_bh(&ma->mca_lock);
 			igmp6_group_queried(ma, max_delay);
 			spin_unlock_bh(&ma->mca_lock);
 		}
 	} else {
-		for (ma = idev->mc_list; ma; ma=ma->next) {
+		for (ma = idev->mc_list; ma; ma = ma->next) {
 			if (!ipv6_addr_equal(group, &ma->mca_addr))
 				continue;
 			spin_lock_bh(&ma->mca_lock);
@@ -1434,7 +1434,7 @@ int igmp6_event_report(struct sk_buff *skb)
 	 */
 
 	read_lock_bh(&idev->lock);
-	for (ma = idev->mc_list; ma; ma=ma->next) {
+	for (ma = idev->mc_list; ma; ma = ma->next) {
 		if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) {
 			spin_lock(&ma->mca_lock);
 			if (del_timer(&ma->mca_timer))
@@ -1498,7 +1498,7 @@ mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted)
 	struct ip6_sf_list *psf;
 	int scount = 0;
 
-	for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
 		if (!is_in(pmc, psf, type, gdeleted, sdeleted))
 			continue;
 		scount++;
@@ -1712,7 +1712,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 	}
 	first = 1;
 	psf_prev = NULL;
-	for (psf=*psf_list; psf; psf=psf_next) {
+	for (psf = *psf_list; psf; psf = psf_next) {
 		struct in6_addr *psrc;
 
 		psf_next = psf->sf_next;
@@ -1791,7 +1791,7 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc)
 
 	read_lock_bh(&idev->lock);
 	if (!pmc) {
-		for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+		for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
 			if (pmc->mca_flags & MAF_NOREPORT)
 				continue;
 			spin_lock_bh(&pmc->mca_lock);
@@ -1824,7 +1824,7 @@ static void mld_clear_zeros(struct ip6_sf_list **ppsf)
 	struct ip6_sf_list *psf_prev, *psf_next, *psf;
 
 	psf_prev = NULL;
-	for (psf=*ppsf; psf; psf = psf_next) {
+	for (psf = *ppsf; psf; psf = psf_next) {
 		psf_next = psf->sf_next;
 		if (psf->sf_crcount == 0) {
 			if (psf_prev)
@@ -1848,7 +1848,7 @@ static void mld_send_cr(struct inet6_dev *idev)
 
 	/* deleted MCA's */
 	pmc_prev = NULL;
-	for (pmc=idev->mc_tomb; pmc; pmc=pmc_next) {
+	for (pmc = idev->mc_tomb; pmc; pmc = pmc_next) {
 		pmc_next = pmc->next;
 		if (pmc->mca_sfmode == MCAST_INCLUDE) {
 			type = MLD2_BLOCK_OLD_SOURCES;
@@ -1881,7 +1881,7 @@ static void mld_send_cr(struct inet6_dev *idev)
 	spin_unlock(&idev->mc_lock);
 
 	/* change recs */
-	for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+	for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
 		spin_lock_bh(&pmc->mca_lock);
 		if (pmc->mca_sfcount[MCAST_EXCLUDE]) {
 			type = MLD2_BLOCK_OLD_SOURCES;
@@ -2018,7 +2018,7 @@ static void mld_send_initial_cr(struct inet6_dev *idev)
 
 	skb = NULL;
 	read_lock_bh(&idev->lock);
-	for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+	for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
 		spin_lock_bh(&pmc->mca_lock);
 		if (pmc->mca_sfcount[MCAST_EXCLUDE])
 			type = MLD2_CHANGE_TO_EXCLUDE;
@@ -2063,7 +2063,7 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode,
 	int rv = 0;
 
 	psf_prev = NULL;
-	for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
 		if (ipv6_addr_equal(&psf->sf_addr, psfsrc))
 			break;
 		psf_prev = psf;
@@ -2104,7 +2104,7 @@ static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 	if (!idev)
 		return -ENODEV;
 	read_lock_bh(&idev->lock);
-	for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+	for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
 		if (ipv6_addr_equal(pmca, &pmc->mca_addr))
 			break;
 	}
@@ -2124,7 +2124,7 @@ static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 		pmc->mca_sfcount[sfmode]--;
 	}
 	err = 0;
-	for (i=0; i<sfcount; i++) {
+	for (i = 0; i < sfcount; i++) {
 		int rv = ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]);
 
 		changerec |= rv > 0;
@@ -2140,7 +2140,7 @@ static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 		pmc->mca_sfmode = MCAST_INCLUDE;
 		pmc->mca_crcount = idev->mc_qrv;
 		idev->mc_ifc_count = pmc->mca_crcount;
-		for (psf=pmc->mca_sources; psf; psf = psf->sf_next)
+		for (psf = pmc->mca_sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = 0;
 		mld_ifc_event(pmc->idev);
 	} else if (sf_setstate(pmc) || changerec)
@@ -2159,7 +2159,7 @@ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode,
 	struct ip6_sf_list *psf, *psf_prev;
 
 	psf_prev = NULL;
-	for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
 		if (ipv6_addr_equal(&psf->sf_addr, psfsrc))
 			break;
 		psf_prev = psf;
@@ -2184,7 +2184,7 @@ static void sf_markstate(struct ifmcaddr6 *pmc)
 	struct ip6_sf_list *psf;
 	int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE];
 
-	for (psf=pmc->mca_sources; psf; psf=psf->sf_next)
+	for (psf = pmc->mca_sources; psf; psf = psf->sf_next)
 		if (pmc->mca_sfcount[MCAST_EXCLUDE]) {
 			psf->sf_oldin = mca_xcount ==
 				psf->sf_count[MCAST_EXCLUDE] &&
@@ -2201,7 +2201,7 @@ static int sf_setstate(struct ifmcaddr6 *pmc)
 	int new_in, rv;
 
 	rv = 0;
-	for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
 		if (pmc->mca_sfcount[MCAST_EXCLUDE]) {
 			new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] &&
 				!psf->sf_count[MCAST_INCLUDE];
@@ -2211,8 +2211,8 @@ static int sf_setstate(struct ifmcaddr6 *pmc)
 			if (!psf->sf_oldin) {
 				struct ip6_sf_list *prev = NULL;
 
-				for (dpsf=pmc->mca_tomb; dpsf;
-				     dpsf=dpsf->sf_next) {
+				for (dpsf = pmc->mca_tomb; dpsf;
+				     dpsf = dpsf->sf_next) {
 					if (ipv6_addr_equal(&dpsf->sf_addr,
 					    &psf->sf_addr))
 						break;
@@ -2234,7 +2234,7 @@ static int sf_setstate(struct ifmcaddr6 *pmc)
 			 * add or update "delete" records if an active filter
 			 * is now inactive
 			 */
-			for (dpsf=pmc->mca_tomb; dpsf; dpsf=dpsf->sf_next)
+			for (dpsf = pmc->mca_tomb; dpsf; dpsf = dpsf->sf_next)
 				if (ipv6_addr_equal(&dpsf->sf_addr,
 				    &psf->sf_addr))
 					break;
@@ -2268,7 +2268,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 	if (!idev)
 		return -ENODEV;
 	read_lock_bh(&idev->lock);
-	for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+	for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
 		if (ipv6_addr_equal(pmca, &pmc->mca_addr))
 			break;
 	}
@@ -2284,7 +2284,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 	if (!delta)
 		pmc->mca_sfcount[sfmode]++;
 	err = 0;
-	for (i=0; i<sfcount; i++) {
+	for (i = 0; i < sfcount; i++) {
 		err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i]);
 		if (err)
 			break;
@@ -2294,7 +2294,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 
 		if (!delta)
 			pmc->mca_sfcount[sfmode]--;
-		for (j=0; j<i; j++)
+		for (j = 0; j < i; j++)
 			ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]);
 	} else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) {
 		struct ip6_sf_list *psf;
@@ -2308,7 +2308,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 
 		pmc->mca_crcount = idev->mc_qrv;
 		idev->mc_ifc_count = pmc->mca_crcount;
-		for (psf=pmc->mca_sources; psf; psf = psf->sf_next)
+		for (psf = pmc->mca_sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = 0;
 		mld_ifc_event(idev);
 	} else if (sf_setstate(pmc))
@@ -2322,12 +2322,12 @@ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc)
 {
 	struct ip6_sf_list *psf, *nextpsf;
 
-	for (psf=pmc->mca_tomb; psf; psf=nextpsf) {
+	for (psf = pmc->mca_tomb; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
 	pmc->mca_tomb = NULL;
-	for (psf=pmc->mca_sources; psf; psf=nextpsf) {
+	for (psf = pmc->mca_sources; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
@@ -2471,7 +2471,7 @@ void ipv6_mc_down(struct inet6_dev *idev)
 	mld_gq_stop_timer(idev);
 	mld_dad_stop_timer(idev);
 
-	for (i = idev->mc_list; i; i=i->next)
+	for (i = idev->mc_list; i; i = i->next)
 		igmp6_group_dropped(i);
 	read_unlock_bh(&idev->lock);
 
@@ -2488,7 +2488,7 @@ void ipv6_mc_up(struct inet6_dev *idev)
 	/* Install multicast list, except for all-nodes (already installed) */
 
 	read_lock_bh(&idev->lock);
-	for (i = idev->mc_list; i; i=i->next)
+	for (i = idev->mc_list; i; i = i->next)
 		igmp6_group_added(i);
 	read_unlock_bh(&idev->lock);
 }
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 339078f95d1b..995a82945994 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -175,7 +175,7 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
 	type = cur->nd_opt_type;
 	do {
 		cur = ((void *)cur) + (cur->nd_opt_len << 3);
-	} while(cur < end && cur->nd_opt_type != type);
+	} while (cur < end && cur->nd_opt_type != type);
 	return cur <= end && cur->nd_opt_type == type ? cur : NULL;
 }
 
@@ -192,7 +192,7 @@ static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur,
 		return NULL;
 	do {
 		cur = ((void *)cur) + (cur->nd_opt_len << 3);
-	} while(cur < end && !ndisc_is_useropt(cur));
+	} while (cur < end && !ndisc_is_useropt(cur));
 	return cur <= end && ndisc_is_useropt(cur) ? cur : NULL;
 }
 
@@ -296,7 +296,7 @@ static u32 ndisc_hash(const void *pkey,
 
 static int ndisc_constructor(struct neighbour *neigh)
 {
-	struct in6_addr *addr = (struct in6_addr*)&neigh->primary_key;
+	struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key;
 	struct net_device *dev = neigh->dev;
 	struct inet6_dev *in6_dev;
 	struct neigh_parms *parms;
@@ -344,7 +344,7 @@ static int ndisc_constructor(struct neighbour *neigh)
 
 static int pndisc_constructor(struct pneigh_entry *n)
 {
-	struct in6_addr *addr = (struct in6_addr*)&n->key;
+	struct in6_addr *addr = (struct in6_addr *)&n->key;
 	struct in6_addr maddr;
 	struct net_device *dev = n->dev;
 
@@ -357,7 +357,7 @@ static int pndisc_constructor(struct pneigh_entry *n)
 
 static void pndisc_destructor(struct pneigh_entry *n)
 {
-	struct in6_addr *addr = (struct in6_addr*)&n->key;
+	struct in6_addr *addr = (struct in6_addr *)&n->key;
 	struct in6_addr maddr;
 	struct net_device *dev = n->dev;
 
@@ -1065,7 +1065,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 	int optlen;
 	unsigned int pref = 0;
 
-	__u8 * opt = (__u8 *)(ra_msg + 1);
+	__u8 *opt = (__u8 *)(ra_msg + 1);
 
 	optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) -
 		sizeof(struct ra_msg);
@@ -1319,7 +1319,7 @@ skip_linkparms:
 				continue;
 			if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
 				continue;
-			rt6_route_rcv(skb->dev, (u8*)p, (p->nd_opt_len) << 3,
+			rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3,
 				      &ipv6_hdr(skb)->saddr);
 		}
 	}
@@ -1352,7 +1352,7 @@ skip_routeinfo:
 		__be32 n;
 		u32 mtu;
 
-		memcpy(&n, ((u8*)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu));
+		memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu));
 		mtu = ntohl(n);
 
 		if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) {
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 5ec867e4a8b7..fc24c390af05 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -35,7 +35,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 			if (found_rhdr)
 				return offset;
 			break;
-		default :
+		default:
 			return offset;
 		}
 
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 2d6f860e5c1e..1752cd0b4882 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -8,7 +8,7 @@
  *		except it reports the sockets in the INET6 address family.
  *
  * Authors:	David S. Miller (davem@caip.rutgers.edu)
- * 		YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
+ *		YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
  *
  *		This program is free software; you can redistribute it and/or
  *		modify it under the terms of the GNU General Public License
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 39d44226e402..896af8807979 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -889,7 +889,7 @@ back_from_confirm:
 	else {
 		lock_sock(sk);
 		err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
-			len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info*)dst,
+			len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info *)dst,
 			msg->msg_flags, dontfrag);
 
 		if (err)
@@ -902,7 +902,7 @@ done:
 	dst_release(dst);
 out:
 	fl6_sock_release(flowlabel);
-	return err<0?err:len;
+	return err < 0 ? err : len;
 do_confirm:
 	dst_confirm(dst);
 	if (!(msg->msg_flags & MSG_PROBE) || len)
@@ -1045,7 +1045,7 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
 	struct raw6_sock *rp = raw6_sk(sk);
 	int val, len;
 
-	if (get_user(len,optlen))
+	if (get_user(len, optlen))
 		return -EFAULT;
 
 	switch (optname) {
@@ -1069,7 +1069,7 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
 
 	if (put_user(len, optlen))
 		return -EFAULT;
-	if (copy_to_user(optval,&val,len))
+	if (copy_to_user(optval, &val, len))
 		return -EFAULT;
 	return 0;
 }
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index c6557d9f7808..fe156d99179e 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -68,7 +68,7 @@ struct ip6frag_skb_cb
 	int			offset;
 };
 
-#define FRAG6_CB(skb)	((struct ip6frag_skb_cb*)((skb)->cb))
+#define FRAG6_CB(skb)	((struct ip6frag_skb_cb *)((skb)->cb))
 
 static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 {
@@ -289,7 +289,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 		goto found;
 	}
 	prev = NULL;
-	for(next = fq->q.fragments; next != NULL; next = next->next) {
+	for (next = fq->q.fragments; next != NULL; next = next->next) {
 		if (FRAG6_CB(next)->offset >= offset)
 			break;	/* bingo! */
 		prev = next;
@@ -529,7 +529,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
 
 	/* Jumbo payload inhibits frag. header */
-	if (hdr->payload_len==0)
+	if (hdr->payload_len == 0)
 		goto fail_hdr;
 
 	if (!pskb_may_pull(skb, (skb_transport_offset(skb) +
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f23fbd28a501..76c793096893 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -813,7 +813,7 @@ out:
 
 }
 
-struct dst_entry * ip6_route_lookup(struct net *net, struct flowi6 *fl6,
+struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
 				    int flags)
 {
 	return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_lookup);
@@ -1024,7 +1024,7 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table
 	return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
 }
 
-struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk,
+struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
 				    struct flowi6 *fl6)
 {
 	int flags = 0;
@@ -1149,7 +1149,7 @@ static void ip6_link_failure(struct sk_buff *skb)
 static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 			       struct sk_buff *skb, u32 mtu)
 {
-	struct rt6_info *rt6 = (struct rt6_info*)dst;
+	struct rt6_info *rt6 = (struct rt6_info *)dst;
 
 	dst_confirm(dst);
 	if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
@@ -1924,7 +1924,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
 		return NULL;
 
 	read_lock_bh(&table->tb6_lock);
-	fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0);
+	fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0);
 	if (!fn)
 		goto out;
 
@@ -1983,7 +1983,7 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev
 		return NULL;
 
 	read_lock_bh(&table->tb6_lock);
-	for (rt = table->tb6_root.leaf; rt; rt=rt->dst.rt6_next) {
+	for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
 		if (dev == rt->dst.dev &&
 		    ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
 		    ipv6_addr_equal(&rt->rt6i_gateway, addr))
@@ -2068,7 +2068,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	struct in6_rtmsg rtmsg;
 	int err;
 
-	switch(cmd) {
+	switch (cmd) {
 	case SIOCADDRT:		/* Add a route */
 	case SIOCDELRT:		/* Delete a route */
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -2191,7 +2191,7 @@ int ip6_route_get_saddr(struct net *net,
 			unsigned int prefs,
 			struct in6_addr *saddr)
 {
-	struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt);
+	struct inet6_dev *idev = ip6_dst_idev((struct dst_entry *)rt);
 	int err = 0;
 	if (rt->rt6i_prefsrc.plen)
 		*saddr = rt->rt6i_prefsrc.addr;
@@ -2486,7 +2486,7 @@ beginning:
 	return last_err;
 }
 
-static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh)
+static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct fib6_config cfg;
 	int err;
@@ -2501,7 +2501,7 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh)
 		return ip6_route_del(&cfg);
 }
 
-static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh)
+static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct fib6_config cfg;
 	int err;
@@ -2693,7 +2693,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg)
 		     prefix, 0, NLM_F_MULTI);
 }
 
-static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh)
+static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[RTA_MAX+1];
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 6163f851dc01..86e3fa81f85e 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -812,9 +812,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	const struct ipv6hdr *iph6 = ipv6_hdr(skb);
 	u8     tos = tunnel->parms.iph.tos;
 	__be16 df = tiph->frag_off;
-	struct rtable *rt;     			/* Route to the other host */
-	struct net_device *tdev;		/* Device to other host */
-	unsigned int max_headroom;		/* The extra header space needed */
+	struct rtable *rt;		/* Route to the other host */
+	struct net_device *tdev;	/* Device to other host */
+	unsigned int max_headroom;	/* The extra header space needed */
 	__be32 dst = tiph->daddr;
 	struct flowi4 fl4;
 	int    mtu;
@@ -1123,7 +1123,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t,
 #endif
 
 static int
-ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
+ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	int err = 0;
 	struct ip_tunnel_parm p;
@@ -1339,10 +1339,10 @@ static void ipip6_dev_free(struct net_device *dev)
 static void ipip6_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &ipip6_netdev_ops;
-	dev->destructor 	= ipip6_dev_free;
+	dev->destructor		= ipip6_dev_free;
 
 	dev->type		= ARPHRD_SIT;
-	dev->hard_header_len 	= LL_MAX_HEADER + sizeof(struct iphdr);
+	dev->hard_header_len	= LL_MAX_HEADER + sizeof(struct iphdr);
 	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr);
 	dev->flags		= IFF_NOARP;
 	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index 2c4e4c5c7614..7a53d397c739 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -15,7 +15,7 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  *
  * Authors	Mitsuru KANDA  <mk@linux-ipv6.org>
- * 		YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
+ *		YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
  */
 
 #define pr_fmt(fmt) "IPv6: " fmt
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 25ffe737b975..12fcce8fba46 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -373,8 +373,8 @@ EXPORT_SYMBOL_GPL(udp6_lib_lookup);
 
 
 /*
- * 	This should be easy, if there is something there we
- * 	return it, otherwise we block.
+ *	This should be easy, if there is something there we
+ *	return it, otherwise we block.
  */
 
 int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
@@ -530,7 +530,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
 	const struct in6_addr *saddr = &hdr->saddr;
 	const struct in6_addr *daddr = &hdr->daddr;
-	struct udphdr *uh = (struct udphdr*)(skb->data+offset);
+	struct udphdr *uh = (struct udphdr *)(skb->data+offset);
 	struct sock *sk;
 	int err;
 	struct net *net = dev_net(skb->dev);
@@ -596,7 +596,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 static __inline__ void udpv6_err(struct sk_buff *skb,
 				 struct inet6_skb_parm *opt, u8 type,
-				 u8 code, int offset, __be32 info     )
+				 u8 code, int offset, __be32 info)
 {
 	__udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
 }
@@ -960,10 +960,10 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
 }
 
 /**
- * 	udp6_hwcsum_outgoing  -  handle outgoing HW checksumming
- * 	@sk: 	socket we are sending on
- * 	@skb: 	sk_buff containing the filled-in UDP header
- * 	        (checksum field must be zeroed out)
+ *	udp6_hwcsum_outgoing  -  handle outgoing HW checksumming
+ *	@sk:	socket we are sending on
+ *	@skb:	sk_buff containing the filled-in UDP header
+ *		(checksum field must be zeroed out)
  */
 static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 				 const struct in6_addr *saddr,
@@ -1294,7 +1294,7 @@ do_append_data:
 	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
 	err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen,
 		sizeof(struct udphdr), hlimit, tclass, opt, &fl6,
-		(struct rt6_info*)dst,
+		(struct rt6_info *)dst,
 		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag);
 	if (err)
 		udp_v6_flush_pending_frames(sk);
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index f8c3cf842f53..cd4c98c7c805 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -3,8 +3,8 @@
  *
  * Authors:
  *	Mitsuru KANDA @USAGI
- * 	Kazunori MIYAZAWA @USAGI
- * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ *	Kazunori MIYAZAWA @USAGI
+ *	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
  *	YOSHIFUJI Hideaki @USAGI
  *		IPv6 support
  */
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 2a0bbda2c76a..ac49f84fe2c3 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -3,11 +3,11 @@
  *
  * Authors:
  *	Mitsuru KANDA @USAGI
- * 	Kazunori MIYAZAWA @USAGI
- * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
- * 		IPv6 support
- * 	YOSHIFUJI Hideaki
- * 		Split up af-specific portion
+ *	Kazunori MIYAZAWA @USAGI
+ *	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ *		IPv6 support
+ *	YOSHIFUJI Hideaki
+ *		Split up af-specific portion
  *
  */
 
@@ -84,7 +84,7 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
 			   int nfheader_len)
 {
 	if (dst->ops->family == AF_INET6) {
-		struct rt6_info *rt = (struct rt6_info*)dst;
+		struct rt6_info *rt = (struct rt6_info *)dst;
 		if (rt->rt6i_node)
 			path->path_cookie = rt->rt6i_node->fn_sernum;
 	}
@@ -97,7 +97,7 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
 static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 			  const struct flowi *fl)
 {
-	struct rt6_info *rt = (struct rt6_info*)xdst->route;
+	struct rt6_info *rt = (struct rt6_info *)xdst->route;
 
 	xdst->u.dst.dev = dev;
 	dev_hold(dev);
@@ -296,7 +296,7 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.family =		AF_INET6,
 	.dst_ops =		&xfrm6_dst_ops,
 	.dst_lookup =		xfrm6_dst_lookup,
-	.get_saddr = 		xfrm6_get_saddr,
+	.get_saddr =		xfrm6_get_saddr,
 	.decode_session =	_decode_session6,
 	.get_tos =		xfrm6_get_tos,
 	.init_dst =		xfrm6_init_dst,
@@ -319,9 +319,9 @@ static void xfrm6_policy_fini(void)
 static struct ctl_table xfrm6_policy_table[] = {
 	{
 		.procname       = "xfrm6_gc_thresh",
-		.data	   	= &init_net.xfrm.xfrm6_dst_ops.gc_thresh,
-		.maxlen	 	= sizeof(int),
-		.mode	   	= 0644,
+		.data		= &init_net.xfrm.xfrm6_dst_ops.gc_thresh,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
 		.proc_handler   = proc_dointvec,
 	},
 	{ }
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index 3fc970135fc6..8a1f9c0d2a13 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -3,11 +3,11 @@
  *
  * Authors:
  *	Mitsuru KANDA @USAGI
- * 	Kazunori MIYAZAWA @USAGI
- * 	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
- * 		IPv6 support
- * 	YOSHIFUJI Hideaki @USAGI
- * 		Split up af-specific portion
+ *	Kazunori MIYAZAWA @USAGI
+ *	Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ *		IPv6 support
+ *	YOSHIFUJI Hideaki @USAGI
+ *		Split up af-specific portion
  *
  */
 
@@ -45,10 +45,10 @@ xfrm6_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl,
 		   const xfrm_address_t *daddr, const xfrm_address_t *saddr)
 {
 	x->id = tmpl->id;
-	if (ipv6_addr_any((struct in6_addr*)&x->id.daddr))
+	if (ipv6_addr_any((struct in6_addr *)&x->id.daddr))
 		memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr));
 	memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr));
-	if (ipv6_addr_any((struct in6_addr*)&x->props.saddr))
+	if (ipv6_addr_any((struct in6_addr *)&x->props.saddr))
 		memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr));
 	x->props.mode = tmpl->mode;
 	x->props.reqid = tmpl->reqid;
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 1c66465a42dd..7b2508be24fd 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -15,7 +15,7 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  *
  * Authors	Mitsuru KANDA  <mk@linux-ipv6.org>
- * 		YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
+ *		YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
  *
  * Based on net/ipv4/xfrm4_tunnel.c
  *
-- 
cgit v1.2.3


From cc24becae3e87d7aa8238f4fcb29bfb68f7ffb97 Mon Sep 17 00:00:00 2001
From: Ian Morris
Date: Sun, 24 Aug 2014 21:53:11 +0100
Subject: ipv6: White-space cleansing : Structure layouts

This patch makes no changes to the logic of the code but simply addresses
coding style issues as detected by checkpatch.

Both objdump and diff -w show no differences.

This patch addresses structure definitions, specifically it cleanses the brace
placement and replaces spaces with tabs in a few places.

Signed-off-by: Ian Morris <ipm@chirality.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ah6.c        |  5 ++---
 net/ipv6/esp6.c       |  7 +++----
 net/ipv6/ipcomp6.c    |  6 ++----
 net/ipv6/mip6.c       | 10 ++++------
 net/ipv6/reassembly.c |  6 ++----
 5 files changed, 13 insertions(+), 21 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index ac71d9e0a500..fcffd4e522c8 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -755,11 +755,10 @@ static int ah6_rcv_cb(struct sk_buff *skb, int err)
 	return 0;
 }
 
-static const struct xfrm_type ah6_type =
-{
+static const struct xfrm_type ah6_type = {
 	.description	= "AH6",
 	.owner		= THIS_MODULE,
-	.proto	     	= IPPROTO_AH,
+	.proto		= IPPROTO_AH,
 	.flags		= XFRM_TYPE_REPLAY_PROT,
 	.init_state	= ah6_init_state,
 	.destructor	= ah6_destroy,
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 7b6e830ebc6d..83fc3a385a26 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -621,11 +621,10 @@ static int esp6_rcv_cb(struct sk_buff *skb, int err)
 	return 0;
 }
 
-static const struct xfrm_type esp6_type =
-{
+static const struct xfrm_type esp6_type = {
 	.description	= "ESP6",
-	.owner	     	= THIS_MODULE,
-	.proto	     	= IPPROTO_ESP,
+	.owner		= THIS_MODULE,
+	.proto		= IPPROTO_ESP,
 	.flags		= XFRM_TYPE_REPLAY_PROT,
 	.init_state	= esp6_init_state,
 	.destructor	= esp6_destroy,
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index d1c793cffcb5..1b9316e1386a 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -181,8 +181,7 @@ static int ipcomp6_rcv_cb(struct sk_buff *skb, int err)
 	return 0;
 }
 
-static const struct xfrm_type ipcomp6_type =
-{
+static const struct xfrm_type ipcomp6_type = {
 	.description	= "IPCOMP6",
 	.owner		= THIS_MODULE,
 	.proto		= IPPROTO_COMP,
@@ -193,8 +192,7 @@ static const struct xfrm_type ipcomp6_type =
 	.hdr_offset	= xfrm6_find_1stfragopt,
 };
 
-static struct xfrm6_protocol ipcomp6_protocol =
-{
+static struct xfrm6_protocol ipcomp6_protocol = {
 	.handler	= xfrm6_rcv,
 	.cb_handler	= ipcomp6_rcv_cb,
 	.err_handler	= ipcomp6_err,
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index db9b6cbc9db3..f61429d391d3 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -336,11 +336,10 @@ static void mip6_destopt_destroy(struct xfrm_state *x)
 {
 }
 
-static const struct xfrm_type mip6_destopt_type =
-{
+static const struct xfrm_type mip6_destopt_type = {
 	.description	= "MIP6DESTOPT",
 	.owner		= THIS_MODULE,
-	.proto	     	= IPPROTO_DSTOPTS,
+	.proto		= IPPROTO_DSTOPTS,
 	.flags		= XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_LOCAL_COADDR,
 	.init_state	= mip6_destopt_init_state,
 	.destructor	= mip6_destopt_destroy,
@@ -469,11 +468,10 @@ static void mip6_rthdr_destroy(struct xfrm_state *x)
 {
 }
 
-static const struct xfrm_type mip6_rthdr_type =
-{
+static const struct xfrm_type mip6_rthdr_type = {
 	.description	= "MIP6RT",
 	.owner		= THIS_MODULE,
-	.proto	     	= IPPROTO_ROUTING,
+	.proto		= IPPROTO_ROUTING,
 	.flags		= XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_REMOTE_COADDR,
 	.init_state	= mip6_rthdr_init_state,
 	.destructor	= mip6_rthdr_destroy,
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index fe156d99179e..1a157ca2ebc1 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -62,8 +62,7 @@
 
 static const char ip6_frag_cache_name[] = "ip6-frags";
 
-struct ip6frag_skb_cb
-{
+struct ip6frag_skb_cb {
 	struct inet6_skb_parm	h;
 	int			offset;
 };
@@ -575,8 +574,7 @@ fail_hdr:
 	return -1;
 }
 
-static const struct inet6_protocol frag_protocol =
-{
+static const struct inet6_protocol frag_protocol = {
 	.handler	=	ipv6_frag_rcv,
 	.flags		=	INET6_PROTO_NOPOLICY,
 };
-- 
cgit v1.2.3


From 4c83acbc565d53296f1731034c5041a0fbabcaeb Mon Sep 17 00:00:00 2001
From: Ian Morris
Date: Sun, 24 Aug 2014 21:53:12 +0100
Subject: ipv6: White-space cleansing : gaps between function and symbol export

This patch makes no changes to the logic of the code but simply addresses
coding style issues as detected by checkpatch.

Both objdump and diff -w show no differences.

This patch removes some blank lines between the end of a function
definition and the EXPORT_SYMBOL_GPL macro in order to prevent
checkpatch warning that EXPORT_SYMBOL must immediately follow
a function.

Signed-off-by: Ian Morris <ipm@chirality.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/inet6_connection_sock.c | 4 ----
 net/ipv6/inet6_hashtables.c      | 3 ---
 net/ipv6/ip6_flowlabel.c         | 1 -
 net/ipv6/ip6_output.c            | 1 -
 net/ipv6/ipv6_sockglue.c         | 4 ----
 net/ipv6/ndisc.c                 | 1 -
 net/ipv6/route.c                 | 2 --
 net/ipv6/tunnel6.c               | 2 --
 net/ipv6/xfrm6_input.c           | 2 --
 net/ipv6/xfrm6_output.c          | 1 -
 net/ipv6/xfrm6_tunnel.c          | 2 --
 11 files changed, 23 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 8c33a0b52b64..29b32206e494 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -63,7 +63,6 @@ int inet6_csk_bind_conflict(const struct sock *sk,
 
 	return sk2 != NULL;
 }
-
 EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict);
 
 struct dst_entry *inet6_csk_route_req(struct sock *sk,
@@ -144,7 +143,6 @@ struct request_sock *inet6_csk_search_req(const struct sock *sk,
 
 	return NULL;
 }
-
 EXPORT_SYMBOL_GPL(inet6_csk_search_req);
 
 void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
@@ -160,7 +158,6 @@ void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
 	reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
 	inet_csk_reqsk_queue_added(sk, timeout);
 }
-
 EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add);
 
 void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
@@ -175,7 +172,6 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
 	sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
 						  sk->sk_bound_dev_if);
 }
-
 EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr);
 
 static inline
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 5f7927c06f18..051dffb49c90 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -222,7 +222,6 @@ begin:
 	rcu_read_unlock();
 	return result;
 }
-
 EXPORT_SYMBOL_GPL(inet6_lookup_listener);
 
 struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
@@ -238,7 +237,6 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
 
 	return sk;
 }
-
 EXPORT_SYMBOL_GPL(inet6_lookup);
 
 static int __inet6_check_established(struct inet_timewait_death_row *death_row,
@@ -324,5 +322,4 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row,
 	return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk),
 			__inet6_check_established, __inet6_hash);
 }
-
 EXPORT_SYMBOL_GPL(inet6_hash_connect);
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 2ace4749bef4..3dd7d4ebd7cd 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -259,7 +259,6 @@ struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label)
 	rcu_read_unlock_bh();
 	return NULL;
 }
-
 EXPORT_SYMBOL_GPL(fl6_sock_lookup);
 
 void fl6_free_socklist(struct sock *sk)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 4ead5547b5c6..b7a3e7b3378e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -233,7 +233,6 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	kfree_skb(skb);
 	return -EMSGSIZE;
 }
-
 EXPORT_SYMBOL(ip6_xmit);
 
 static int ip6_call_ra_chain(struct sk_buff *skb, int sel)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 64177efe5cca..e1a9583bb419 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -873,7 +873,6 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname,
 #endif
 	return err;
 }
-
 EXPORT_SYMBOL(ipv6_setsockopt);
 
 #ifdef CONFIG_COMPAT
@@ -909,7 +908,6 @@ int compat_ipv6_setsockopt(struct sock *sk, int level, int optname,
 #endif
 	return err;
 }
-
 EXPORT_SYMBOL(compat_ipv6_setsockopt);
 #endif
 
@@ -1321,7 +1319,6 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname,
 #endif
 	return err;
 }
-
 EXPORT_SYMBOL(ipv6_getsockopt);
 
 #ifdef CONFIG_COMPAT
@@ -1364,7 +1361,6 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
 #endif
 	return err;
 }
-
 EXPORT_SYMBOL(compat_ipv6_getsockopt);
 #endif
 
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 995a82945994..4cb45c1079a2 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -284,7 +284,6 @@ int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev,
 	}
 	return -EINVAL;
 }
-
 EXPORT_SYMBOL(ndisc_mc_map);
 
 static u32 ndisc_hash(const void *pkey,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 76c793096893..f74b0417bd60 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -843,7 +843,6 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
 
 	return NULL;
 }
-
 EXPORT_SYMBOL(rt6_lookup);
 
 /* ip6_ins_rt is called with FREE table->tb6_lock.
@@ -1041,7 +1040,6 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
 
 	return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output);
 }
-
 EXPORT_SYMBOL(ip6_route_output);
 
 struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index 7a53d397c739..3c758007b327 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -64,7 +64,6 @@ err:
 
 	return ret;
 }
-
 EXPORT_SYMBOL(xfrm6_tunnel_register);
 
 int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family)
@@ -92,7 +91,6 @@ int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family)
 
 	return ret;
 }
-
 EXPORT_SYMBOL(xfrm6_tunnel_deregister);
 
 #define for_each_tunnel_rcu(head, handler)		\
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index cd4c98c7c805..f48fbe4d16f5 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -52,7 +52,6 @@ int xfrm6_rcv(struct sk_buff *skb)
 	return xfrm6_rcv_spi(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],
 			     0);
 }
-
 EXPORT_SYMBOL(xfrm6_rcv);
 
 int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
@@ -142,5 +141,4 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
 drop:
 	return -1;
 }
-
 EXPORT_SYMBOL(xfrm6_input_addr);
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 433672d07d0b..ca3f29b98ae5 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -25,7 +25,6 @@ int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
 {
 	return ip6_find_1stfragopt(skb, prevhdr);
 }
-
 EXPORT_SYMBOL(xfrm6_find_1stfragopt);
 
 static int xfrm6_local_dontfrag(struct sk_buff *skb)
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 7b2508be24fd..5743044cd660 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -110,7 +110,6 @@ __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr)
 	rcu_read_unlock_bh();
 	return htonl(spi);
 }
-
 EXPORT_SYMBOL(xfrm6_tunnel_spi_lookup);
 
 static int __xfrm6_tunnel_spi_check(struct net *net, u32 spi)
@@ -187,7 +186,6 @@ __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr)
 
 	return htonl(spi);
 }
-
 EXPORT_SYMBOL(xfrm6_tunnel_alloc_spi);
 
 static void x6spi_destroy_rcu(struct rcu_head *head)
-- 
cgit v1.2.3


From 253ff51635ad6690276ef065d59523c4bd1cd584 Mon Sep 17 00:00:00 2001
From: Florian Westphal
Date: Tue, 26 Aug 2014 12:55:53 +0200
Subject: tcp: syncookies: mark cookie_secret read_mostly

only written once.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/syncookies.c | 2 +-
 net/ipv6/syncookies.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index c0c75688896e..0431a8f3c8f4 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -25,7 +25,7 @@
 
 extern int sysctl_tcp_syncookies;
 
-static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
+static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
 
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 83cea1d39466..c643dc907ce7 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -24,7 +24,7 @@
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
 
-static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS];
+static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
 
 /* RFC 2460, Section 8.3:
  * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
-- 
cgit v1.2.3


From 2abb7cdc0dc84e99b76ef983a1ae1978922aa9b3 Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Sun, 31 Aug 2014 15:12:43 -0700
Subject: udp: Add support for doing checksum unnecessary conversion

Add support for doing CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE
conversion in UDP tunneling path.

In the normal UDP path, we call skb_checksum_try_convert after locating
the UDP socket. The check is that checksum conversion is enabled for
the socket (new flag in UDP socket) and that checksum field is
non-zero.

In the UDP GRO path, we call skb_gro_checksum_try_convert after
checksum is validated and checksum field is non-zero. Since this is
already in GRO we assume that checksum conversion is always wanted.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h    | 16 +++++++++++++++-
 net/ipv4/udp.c         |  4 ++++
 net/ipv4/udp_offload.c | 25 +++++++++++++++++--------
 net/ipv6/udp.c         |  4 ++++
 net/ipv6/udp_offload.c | 24 +++++++++++++++++-------
 5 files changed, 57 insertions(+), 16 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/linux/udp.h b/include/linux/udp.h
index 247cfdcc4b08..ee3277593222 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -49,7 +49,11 @@ struct udp_sock {
 	unsigned int	 corkflag;	/* Cork is required */
 	__u8		 encap_type;	/* Is this an Encapsulation socket? */
 	unsigned char	 no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
-			 no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */
+			 no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
+			 convert_csum:1;/* On receive, convert checksum
+					 * unnecessary to checksum complete
+					 * if possible.
+					 */
 	/*
 	 * Following member retains the information to create a UDP header
 	 * when the socket is uncorked.
@@ -98,6 +102,16 @@ static inline bool udp_get_no_check6_rx(struct sock *sk)
 	return udp_sk(sk)->no_check6_rx;
 }
 
+static inline void udp_set_convert_csum(struct sock *sk, bool val)
+{
+	udp_sk(sk)->convert_csum = val;
+}
+
+static inline bool udp_get_convert_csum(struct sock *sk)
+{
+	return udp_sk(sk)->convert_csum;
+}
+
 #define udp_portaddr_for_each_entry(__sk, node, list) \
 	hlist_nulls_for_each_entry(__sk, node, list, __sk_common.skc_portaddr_node)
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3549c21fe5f7..0da3849fd35b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1788,6 +1788,10 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (sk != NULL) {
 		int ret;
 
+		if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk))
+			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+						 inet_compute_pseudo);
+
 		ret = udp_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index a6adff98382a..84e0e05c9c0e 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -290,16 +290,25 @@ static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
-	/* Don't bother verifying checksum if we're going to flush anyway. */
-	if (unlikely(!uh) ||
-	    (!NAPI_GRO_CB(skb)->flush &&
-	     skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
-						  inet_gro_compute_pseudo))) {
-		NAPI_GRO_CB(skb)->flush = 1;
-		return NULL;
-	}
+	if (unlikely(!uh))
+		goto flush;
 
+	/* Don't bother verifying checksum if we're going to flush anyway. */
+	if (!NAPI_GRO_CB(skb)->flush)
+		goto skip;
+
+	if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
+						 inet_gro_compute_pseudo))
+		goto flush;
+	else if (uh->check)
+		skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+					     inet_gro_compute_pseudo);
+skip:
 	return udp_gro_receive(head, skb, uh);
+
+flush:
+	NAPI_GRO_CB(skb)->flush = 1;
+	return NULL;
 }
 
 int udp_gro_complete(struct sk_buff *skb, int nhoff)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 12fcce8fba46..f6ba535b6feb 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -891,6 +891,10 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			goto csum_error;
 		}
 
+		if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk))
+			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+						 ip6_compute_pseudo);
+
 		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index b13e377e9c53..89cb9a9b8537 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -134,16 +134,26 @@ static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
+	if (unlikely(!uh))
+		goto flush;
+
 	/* Don't bother verifying checksum if we're going to flush anyway. */
-	if (unlikely(!uh) ||
-	    (!NAPI_GRO_CB(skb)->flush &&
-	     skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
-						  ip6_gro_compute_pseudo))) {
-		NAPI_GRO_CB(skb)->flush = 1;
-		return NULL;
-	}
+	if (!NAPI_GRO_CB(skb)->flush)
+		goto skip;
 
+	if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
+						 ip6_gro_compute_pseudo))
+		goto flush;
+	else if (uh->check)
+		skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+					     ip6_gro_compute_pseudo);
+
+skip:
 	return udp_gro_receive(head, skb, uh);
+
+flush:
+	NAPI_GRO_CB(skb)->flush = 1;
+	return NULL;
 }
 
 int udp6_gro_complete(struct sk_buff *skb, int nhoff)
-- 
cgit v1.2.3


From 364a9e93243d1785f310c0964af0e24bf1adac03 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn
Date: Sun, 31 Aug 2014 21:30:27 -0400
Subject: sock: deduplicate errqueue dequeue

sk->sk_error_queue is dequeued in four locations. All share the
exact same logic. Deduplicate.

Also collapse the two critical sections for dequeue (at the top of
the recv handler) and signal (at the bottom).

This moves signal generation for the next packet forward, which should
be harmless.

It also changes the behavior if the recv handler exits early with an
error. Previously, a signal for follow-up packets on the errqueue
would then not be scheduled. The new behavior, to always signal, is
arguably a bug fix.

For rxrpc, the change causes the same function to be called repeatedly
for each queued packet (because the recv handler == sk_error_report).
It is likely that all packets will fail for the same reason (e.g.,
memory exhaustion).

This code runs without sk_lock held, so it is not safe to trust that
sk->sk_err is immutable inbetween releasing q->lock and the subsequent
test. Introduce int err just to avoid this potential race.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h     |  1 +
 net/core/skbuff.c      | 20 ++++++++++++++++++++
 net/core/sock.c        | 14 ++------------
 net/ipv4/ip_sockglue.c | 15 ++-------------
 net/ipv6/datagram.c    | 15 ++-------------
 net/rxrpc/ar-error.c   | 14 +-------------
 6 files changed, 28 insertions(+), 51 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/sock.h b/include/net/sock.h
index 7f2ab72f321a..3fde6130789d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2041,6 +2041,7 @@ void sk_stop_timer(struct sock *sk, struct timer_list *timer);
 int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 
 int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
+struct sk_buff *sock_dequeue_err_skb(struct sock *sk);
 
 /*
  *	Recover an error report and clear atomically
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 163b673f9e62..53ce536e3d6e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3491,6 +3491,26 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sock_queue_err_skb);
 
+struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
+{
+	struct sk_buff_head *q = &sk->sk_error_queue;
+	struct sk_buff *skb, *skb_next;
+	int err = 0;
+
+	spin_lock_bh(&q->lock);
+	skb = __skb_dequeue(q);
+	if (skb && (skb_next = skb_peek(q)))
+		err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
+	spin_unlock_bh(&q->lock);
+
+	sk->sk_err = err;
+	if (err)
+		sk->sk_error_report(sk);
+
+	return skb;
+}
+EXPORT_SYMBOL(sock_dequeue_err_skb);
+
 void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		     struct skb_shared_hwtstamps *hwtstamps,
 		     struct sock *sk, int tstype)
diff --git a/net/core/sock.c b/net/core/sock.c
index f7f2352200ad..f1a638ee93d9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2488,11 +2488,11 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
 		       int level, int type)
 {
 	struct sock_exterr_skb *serr;
-	struct sk_buff *skb, *skb2;
+	struct sk_buff *skb;
 	int copied, err;
 
 	err = -EAGAIN;
-	skb = skb_dequeue(&sk->sk_error_queue);
+	skb = sock_dequeue_err_skb(sk);
 	if (skb == NULL)
 		goto out;
 
@@ -2513,16 +2513,6 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
 	msg->msg_flags |= MSG_ERRQUEUE;
 	err = copied;
 
-	/* Reset and regenerate socket error */
-	spin_lock_bh(&sk->sk_error_queue.lock);
-	sk->sk_err = 0;
-	if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
-		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-		sk->sk_error_report(sk);
-	} else
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-
 out_free_skb:
 	kfree_skb(skb);
 out:
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5cb830c78990..455e75bcb167 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -405,7 +405,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	struct sock_exterr_skb *serr;
-	struct sk_buff *skb, *skb2;
+	struct sk_buff *skb;
 	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct {
 		struct sock_extended_err ee;
@@ -415,7 +415,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	int copied;
 
 	err = -EAGAIN;
-	skb = skb_dequeue(&sk->sk_error_queue);
+	skb = sock_dequeue_err_skb(sk);
 	if (skb == NULL)
 		goto out;
 
@@ -462,17 +462,6 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	msg->msg_flags |= MSG_ERRQUEUE;
 	err = copied;
 
-	/* Reset and regenerate socket error */
-	spin_lock_bh(&sk->sk_error_queue.lock);
-	sk->sk_err = 0;
-	skb2 = skb_peek(&sk->sk_error_queue);
-	if (skb2 != NULL) {
-		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-		sk->sk_error_report(sk);
-	} else
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-
 out_free_skb:
 	kfree_skb(skb);
 out:
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 1844e874a350..2cdc38338be3 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -332,7 +332,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sock_exterr_skb *serr;
-	struct sk_buff *skb, *skb2;
+	struct sk_buff *skb;
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name);
 	struct {
 		struct sock_extended_err ee;
@@ -342,7 +342,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	int copied;
 
 	err = -EAGAIN;
-	skb = skb_dequeue(&sk->sk_error_queue);
+	skb = sock_dequeue_err_skb(sk);
 	if (skb == NULL)
 		goto out;
 
@@ -415,17 +415,6 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	msg->msg_flags |= MSG_ERRQUEUE;
 	err = copied;
 
-	/* Reset and regenerate socket error */
-	spin_lock_bh(&sk->sk_error_queue.lock);
-	sk->sk_err = 0;
-	if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
-		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-		sk->sk_error_report(sk);
-	} else {
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-	}
-
 out_free_skb:
 	kfree_skb(skb);
 out:
diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c
index db57458c824c..74c0fcd36838 100644
--- a/net/rxrpc/ar-error.c
+++ b/net/rxrpc/ar-error.c
@@ -37,7 +37,7 @@ void rxrpc_UDP_error_report(struct sock *sk)
 
 	_enter("%p{%d}", sk, local->debug_id);
 
-	skb = skb_dequeue(&sk->sk_error_queue);
+	skb = sock_dequeue_err_skb(sk);
 	if (!skb) {
 		_leave("UDP socket errqueue empty");
 		return;
@@ -111,18 +111,6 @@ void rxrpc_UDP_error_report(struct sock *sk)
 	skb_queue_tail(&trans->error_queue, skb);
 	rxrpc_queue_work(&trans->error_handler);
 
-	/* reset and regenerate socket error */
-	spin_lock_bh(&sk->sk_error_queue.lock);
-	sk->sk_err = 0;
-	skb = skb_peek(&sk->sk_error_queue);
-	if (skb) {
-		sk->sk_err = SKB_EXT_ERR(skb)->ee.ee_errno;
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-		sk->sk_error_report(sk);
-	} else {
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-	}
-
 	_leave("");
 }
 
-- 
cgit v1.2.3


From 2f711939d2ea9dfaecebecd1324d2ec7a7a21f65 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa
Date: Tue, 2 Sep 2014 15:49:25 +0200
Subject: ipv6: add sysctl_mld_qrv to configure query robustness variable

This patch adds a new sysctl_mld_qrv knob to configure the mldv1/v2 query
robustness variable. It specifies how many retransmit of unsolicited mld
retransmit should happen. Admins might want to tune this on lossy links.

Also reset mld state on interface down/up, so we pick up new sysctl
settings during interface up event.

IPv6 certification requests this knob to be available.

I didn't make this knob netns specific, as it is mostly a setting in a
physical environment and should be per host.

Cc: Flavio Leitner <fbl@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  5 +++++
 include/net/ipv6.h                     |  1 +
 net/ipv6/mcast.c                       | 25 +++++++++++++++----------
 net/ipv6/sysctl_net_ipv6.c             | 10 ++++++++++
 4 files changed, 31 insertions(+), 10 deletions(-)

(limited to 'net/ipv6')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 3cce8ea6b139..cfc71ac0f764 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1152,6 +1152,11 @@ anycast_src_echo_reply - BOOLEAN
 	FALSE: disabled
 	Default: FALSE
 
+mld_qrv - INTEGER
+	Controls the MLD query robustness variable (see RFC3810 9.1).
+	Default: 2 (as specified by RFC3810 9.1)
+	Minimum: 1 (as specified by RFC6636 4.5)
+
 IPv6 Fragmentation:
 
 ip6frag_high_thresh - INTEGER
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index a2db816e8461..7e247e9b8765 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -121,6 +121,7 @@ struct frag_hdr {
 
 /* sysctls */
 extern int sysctl_mld_max_msf;
+extern int sysctl_mld_qrv;
 
 #define _DEVINC(net, statname, modifier, idev, field)			\
 ({									\
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 70881795da96..64919425f1ab 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -121,6 +121,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 #define IPV6_MLD_MAX_MSF	64
 
 int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF;
+int sysctl_mld_qrv __read_mostly = MLD_QRV_DEFAULT;
 
 /*
  *	socket join on multicast group
@@ -1191,15 +1192,16 @@ static void mld_update_qrv(struct inet6_dev *idev,
 	 * and SHOULD NOT be one. Catch this here if we ever run
 	 * into such a case in future.
 	 */
+	const int min_qrv = min(MLD_QRV_DEFAULT, sysctl_mld_qrv);
 	WARN_ON(idev->mc_qrv == 0);
 
 	if (mlh2->mld2q_qrv > 0)
 		idev->mc_qrv = mlh2->mld2q_qrv;
 
-	if (unlikely(idev->mc_qrv < 2)) {
+	if (unlikely(idev->mc_qrv < min_qrv)) {
 		net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n",
-				     idev->mc_qrv, MLD_QRV_DEFAULT);
-		idev->mc_qrv = MLD_QRV_DEFAULT;
+				     idev->mc_qrv, min_qrv);
+		idev->mc_qrv = min_qrv;
 	}
 }
 
@@ -2478,6 +2480,14 @@ void ipv6_mc_down(struct inet6_dev *idev)
 	mld_clear_delrec(idev);
 }
 
+static void ipv6_mc_reset(struct inet6_dev *idev)
+{
+	idev->mc_qrv = sysctl_mld_qrv;
+	idev->mc_qi = MLD_QI_DEFAULT;
+	idev->mc_qri = MLD_QRI_DEFAULT;
+	idev->mc_v1_seen = 0;
+	idev->mc_maxdelay = unsolicited_report_interval(idev);
+}
 
 /* Device going up */
 
@@ -2488,6 +2498,7 @@ void ipv6_mc_up(struct inet6_dev *idev)
 	/* Install multicast list, except for all-nodes (already installed) */
 
 	read_lock_bh(&idev->lock);
+	ipv6_mc_reset(idev);
 	for (i = idev->mc_list; i; i = i->next)
 		igmp6_group_added(i);
 	read_unlock_bh(&idev->lock);
@@ -2508,13 +2519,7 @@ void ipv6_mc_init_dev(struct inet6_dev *idev)
 			(unsigned long)idev);
 	setup_timer(&idev->mc_dad_timer, mld_dad_timer_expire,
 		    (unsigned long)idev);
-
-	idev->mc_qrv = MLD_QRV_DEFAULT;
-	idev->mc_qi = MLD_QI_DEFAULT;
-	idev->mc_qri = MLD_QRI_DEFAULT;
-
-	idev->mc_maxdelay = unsolicited_report_interval(idev);
-	idev->mc_v1_seen = 0;
+	ipv6_mc_reset(idev);
 	write_unlock_bh(&idev->lock);
 }
 
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 0c56c93619e0..c5c10fafcfe2 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -16,6 +16,8 @@
 #include <net/addrconf.h>
 #include <net/inet_frag.h>
 
+static int one = 1;
+
 static struct ctl_table ipv6_table_template[] = {
 	{
 		.procname	= "bindv6only",
@@ -63,6 +65,14 @@ static struct ctl_table ipv6_rotable[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "mld_qrv",
+		.data		= &sysctl_mld_qrv,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one
+	},
 	{ }
 };
 
-- 
cgit v1.2.3


From 04317dafd11dd7b0ec19b85f098414abae6ed5f7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Fri, 5 Sep 2014 15:33:32 -0700
Subject: tcp: introduce TCP_SKB_CB(skb)->tcp_tw_isn

TCP_SKB_CB(skb)->when has different meaning in output and input paths.

In output path, it contains a timestamp.
In input path, it contains an ISN, chosen by tcp_timewait_state_process()

Lets add a different name to ease code comprehension.

Note that 'when' field will disappear in following patch,
as skb_mstamp already contains timestamp, the anonymous
union will promptly disappear as well.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h        | 7 ++++++-
 net/ipv4/tcp_input.c     | 2 +-
 net/ipv4/tcp_ipv4.c      | 2 +-
 net/ipv4/tcp_minisocks.c | 2 +-
 net/ipv6/tcp_ipv6.c      | 4 ++--
 5 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 590e01a476ac..0cd7d2c65dc0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -698,7 +698,12 @@ struct tcp_skb_cb {
 	} header;	/* For incoming frames		*/
 	__u32		seq;		/* Starting sequence number	*/
 	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/
-	__u32		when;		/* used to compute rtt's	*/
+	union {
+		/* used in output path */
+		__u32		when;	/* used to compute rtt's	*/
+		/* used in input path */
+		__u32		tcp_tw_isn; /* isn chosen by tcp_timewait_state_process() */
+	};
 	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
 
 	__u8		sacked;		/* State flags for SACK/FACK.	*/
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index aba4926ca095..9c8b9f1dcf69 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5906,7 +5906,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	struct request_sock *req;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct dst_entry *dst = NULL;
-	__u32 isn = TCP_SKB_CB(skb)->when;
+	__u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn;
 	bool want_cookie = false, fastopen;
 	struct flowi fl;
 	struct tcp_fastopen_cookie foc = { .len = -1 };
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 487e2a41667f..02e6cd29ebf1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1627,7 +1627,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff * 4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->when	 = 0;
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
 	TCP_SKB_CB(skb)->sacked	 = 0;
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 1649988bd1b6..a058f411d3a6 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -232,7 +232,7 @@ kill:
 		u32 isn = tcptw->tw_snd_nxt + 65535 + 2;
 		if (isn == 0)
 			isn++;
-		TCP_SKB_CB(skb)->when = isn;
+		TCP_SKB_CB(skb)->tcp_tw_isn = isn;
 		return TCP_TW_SYN;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 29964c3d363c..5b3c70ff7a72 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -738,7 +738,7 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
 		ireq->ir_iif = inet6_iif(skb);
 
-	if (!TCP_SKB_CB(skb)->when &&
+	if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
 	    (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo ||
 	     np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
 	     np->rxopt.bits.rxohlim || np->repflow)) {
@@ -1412,7 +1412,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff*4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->when = 0;
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
 	TCP_SKB_CB(skb)->sacked = 0;
 
-- 
cgit v1.2.3


From 2a5538e9aa4929329813bee69922c9ae4990fcad Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Mon, 25 Aug 2014 12:05:27 +0200
Subject: netfilter: nat: move specific NAT IPv6 to core

Move the specific NAT IPv6 core functions that are called from the
hooks from ip6table_nat.c to nf_nat_l3proto_ipv6.c. This prepares the
ground to allow iptables and nft to use the same NAT engine code that
comes in a follow up patch.

This also renames nf_nat_ipv6_fn to nft_nat_ipv6_fn in
net/ipv6/netfilter/nft_chain_nat_ipv6.c to avoid a compilation breakage.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l3proto.h   |  37 +++++
 net/ipv6/netfilter/ip6table_nat.c        | 233 +++++--------------------------
 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 199 ++++++++++++++++++++++++++
 net/ipv6/netfilter/nft_chain_nat_ipv6.c  |  10 +-
 4 files changed, 275 insertions(+), 204 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h
index bc2d51574489..340c013795a4 100644
--- a/include/net/netfilter/nf_nat_l3proto.h
+++ b/include/net/netfilter/nf_nat_l3proto.h
@@ -84,4 +84,41 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
 				    enum ip_conntrack_info ctinfo,
 				    unsigned int hooknum, unsigned int hdrlen);
 
+unsigned int nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			    const struct net_device *in,
+			    const struct net_device *out,
+			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						     struct sk_buff *skb,
+						     const struct net_device *in,
+						     const struct net_device *out,
+						     struct nf_conn *ct));
+
+unsigned int nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			     const struct net_device *in,
+			     const struct net_device *out,
+			     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						      struct sk_buff *skb,
+						      const struct net_device *in,
+						      const struct net_device *out,
+						      struct nf_conn *ct));
+
+unsigned int nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops,
+				  struct sk_buff *skb,
+				  const struct net_device *in,
+				  const struct net_device *out,
+				  unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+							   struct sk_buff *skb,
+							   const struct net_device *in,
+							   const struct net_device *out,
+							   struct nf_conn *ct));
+
+unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			    const struct net_device *in,
+			    const struct net_device *out,
+			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						     struct sk_buff *skb,
+						     const struct net_device *in,
+						     const struct net_device *out,
+						     struct nf_conn *ct));
+
 #endif /* _NF_NAT_L3PROTO_H */
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 387d8b8fc18d..b0634ac996b7 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -30,222 +30,57 @@ static const struct xt_table nf_nat_ipv6_table = {
 	.af		= NFPROTO_IPV6,
 };
 
-static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
-{
-	/* Force range to this IP; let proto decide mapping for
-	 * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
-	 */
-	struct nf_nat_range range;
-
-	range.flags = 0;
-	pr_debug("Allocating NULL binding for %p (%pI6)\n", ct,
-		 HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip6 :
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip6);
-
-	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
-}
-
-static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
-				     const struct net_device *in,
-				     const struct net_device *out,
-				     struct nf_conn *ct)
+static unsigned int ip6table_nat_do_chain(const struct nf_hook_ops *ops,
+					  struct sk_buff *skb,
+					  const struct net_device *in,
+					  const struct net_device *out,
+					  struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
-	unsigned int ret;
 
-	ret = ip6t_do_table(skb, hooknum, in, out, net->ipv6.ip6table_nat);
-	if (ret == NF_ACCEPT) {
-		if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
-			ret = alloc_null_binding(ct, hooknum);
-	}
-	return ret;
+	return ip6t_do_table(skb, ops->hooknum, in, out, net->ipv6.ip6table_nat);
 }
 
-static unsigned int
-nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
-	       struct sk_buff *skb,
-	       const struct net_device *in,
-	       const struct net_device *out,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_fn(const struct nf_hook_ops *ops,
+				    struct sk_buff *skb,
+				    const struct net_device *in,
+				    const struct net_device *out,
+				    int (*okfn)(struct sk_buff *))
 {
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn_nat *nat;
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
-	__be16 frag_off;
-	int hdrlen;
-	u8 nexthdr;
-
-	ct = nf_ct_get(skb, &ctinfo);
-	/* Can't track?  It's not due to stress, or conntrack would
-	 * have dropped it.  Hence it's the user's responsibilty to
-	 * packet filter it out, or implement conntrack/NAT for that
-	 * protocol. 8) --RR
-	 */
-	if (!ct)
-		return NF_ACCEPT;
-
-	/* Don't try to NAT if this packet is not conntracked */
-	if (nf_ct_is_untracked(ct))
-		return NF_ACCEPT;
-
-	nat = nf_ct_nat_ext_add(ct);
-	if (nat == NULL)
-		return NF_ACCEPT;
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED_REPLY:
-		nexthdr = ipv6_hdr(skb)->nexthdr;
-		hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
-					  &nexthdr, &frag_off);
-
-		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
-			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
-							     ops->hooknum,
-							     hdrlen))
-				return NF_DROP;
-			else
-				return NF_ACCEPT;
-		}
-		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
-	case IP_CT_NEW:
-		/* Seen it before?  This can happen for loopback, retrans,
-		 * or local packets.
-		 */
-		if (!nf_nat_initialized(ct, maniptype)) {
-			unsigned int ret;
-
-			ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct);
-			if (ret != NF_ACCEPT)
-				return ret;
-		} else {
-			pr_debug("Already setup manip %s for ct %p\n",
-				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
-				 ct);
-			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
-				goto oif_changed;
-		}
-		break;
-
-	default:
-		/* ESTABLISHED */
-		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
-			     ctinfo == IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
-			goto oif_changed;
-	}
-
-	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
-
-oif_changed:
-	nf_ct_kill_acct(ct, ctinfo, skb);
-	return NF_DROP;
+	return nf_nat_ipv6_fn(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv6_in(const struct nf_hook_ops *ops,
-	       struct sk_buff *skb,
-	       const struct net_device *in,
-	       const struct net_device *out,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_in(const struct nf_hook_ops *ops,
+				    struct sk_buff *skb,
+				    const struct net_device *in,
+				    const struct net_device *out,
+				    int (*okfn)(struct sk_buff *))
 {
-	unsigned int ret;
-	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
-
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
-		skb_dst_drop(skb);
-
-	return ret;
+	return nf_nat_ipv6_in(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv6_out(const struct nf_hook_ops *ops,
-		struct sk_buff *skb,
-		const struct net_device *in,
-		const struct net_device *out,
-		int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_out(const struct nf_hook_ops *ops,
+				     struct sk_buff *skb,
+				     const struct net_device *in,
+				     const struct net_device *out,
+				     int (*okfn)(struct sk_buff *))
 {
-#ifdef CONFIG_XFRM
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	int err;
-#endif
-	unsigned int ret;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct ipv6hdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
-#ifdef CONFIG_XFRM
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
-				      &ct->tuplehash[!dir].tuple.dst.u3) ||
-		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
-		     ct->tuplehash[dir].tuple.src.u.all !=
-		     ct->tuplehash[!dir].tuple.dst.u.all)) {
-			err = nf_xfrm_me_harder(skb, AF_INET6);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-	}
-#endif
-	return ret;
+	return nf_nat_ipv6_out(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops,
-		     struct sk_buff *skb,
-		     const struct net_device *in,
-		     const struct net_device *out,
-		     int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_local_fn(const struct nf_hook_ops *ops,
+					  struct sk_buff *skb,
+					  const struct net_device *in,
+					  const struct net_device *out,
+					  int (*okfn)(struct sk_buff *))
 {
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	unsigned int ret;
-	int err;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct ipv6hdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
-				      &ct->tuplehash[!dir].tuple.src.u3)) {
-			err = ip6_route_me_harder(skb);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#ifdef CONFIG_XFRM
-		else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
-			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
-			 ct->tuplehash[dir].tuple.dst.u.all !=
-			 ct->tuplehash[!dir].tuple.src.u.all) {
-			err = nf_xfrm_me_harder(skb, AF_INET6);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#endif
-	}
-	return ret;
+	return nf_nat_ipv6_local_fn(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
 static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv6_in,
+		.hook		= ip6table_nat_in,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_PRE_ROUTING,
@@ -253,7 +88,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv6_out,
+		.hook		= ip6table_nat_out,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_POST_ROUTING,
@@ -261,7 +96,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	},
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv6_local_fn,
+		.hook		= ip6table_nat_local_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_LOCAL_OUT,
@@ -269,7 +104,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv6_fn,
+		.hook		= ip6table_nat_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_LOCAL_IN,
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index fc8e49b2ff3e..c5812e1c1ffb 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -261,6 +261,205 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation);
 
+unsigned int
+nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	       const struct net_device *in, const struct net_device *out,
+	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					struct nf_conn *ct))
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn_nat *nat;
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
+	__be16 frag_off;
+	int hdrlen;
+	u8 nexthdr;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	/* Can't track?  It's not due to stress, or conntrack would
+	 * have dropped it.  Hence it's the user's responsibilty to
+	 * packet filter it out, or implement conntrack/NAT for that
+	 * protocol. 8) --RR
+	 */
+	if (!ct)
+		return NF_ACCEPT;
+
+	/* Don't try to NAT if this packet is not conntracked */
+	if (nf_ct_is_untracked(ct))
+		return NF_ACCEPT;
+
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
+
+	switch (ctinfo) {
+	case IP_CT_RELATED:
+	case IP_CT_RELATED_REPLY:
+		nexthdr = ipv6_hdr(skb)->nexthdr;
+		hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
+					  &nexthdr, &frag_off);
+
+		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
+			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
+							     ops->hooknum,
+							     hdrlen))
+				return NF_DROP;
+			else
+				return NF_ACCEPT;
+		}
+		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
+	case IP_CT_NEW:
+		/* Seen it before?  This can happen for loopback, retrans,
+		 * or local packets.
+		 */
+		if (!nf_nat_initialized(ct, maniptype)) {
+			unsigned int ret;
+
+			ret = do_chain(ops, skb, in, out, ct);
+			if (ret != NF_ACCEPT)
+				return ret;
+
+			if (nf_nat_initialized(ct, HOOK2MANIP(ops->hooknum)))
+				break;
+
+			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
+			if (ret != NF_ACCEPT)
+				return ret;
+		} else {
+			pr_debug("Already setup manip %s for ct %p\n",
+				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
+				 ct);
+			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+				goto oif_changed;
+		}
+		break;
+
+	default:
+		/* ESTABLISHED */
+		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
+			     ctinfo == IP_CT_ESTABLISHED_REPLY);
+		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+			goto oif_changed;
+	}
+
+	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
+
+oif_changed:
+	nf_ct_kill_acct(ct, ctinfo, skb);
+	return NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_fn);
+
+unsigned int
+nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	       const struct net_device *in, const struct net_device *out,
+	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					struct nf_conn *ct))
+{
+	unsigned int ret;
+	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
+		skb_dst_drop(skb);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_in);
+
+unsigned int
+nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+		const struct net_device *in, const struct net_device *out,
+		unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					 struct sk_buff *skb,
+					 const struct net_device *in,
+					 const struct net_device *out,
+					 struct nf_conn *ct))
+{
+#ifdef CONFIG_XFRM
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	int err;
+#endif
+	unsigned int ret;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct ipv6hdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+#ifdef CONFIG_XFRM
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
+				      &ct->tuplehash[!dir].tuple.dst.u3) ||
+		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
+		     ct->tuplehash[dir].tuple.src.u.all !=
+		     ct->tuplehash[!dir].tuple.dst.u.all)) {
+			err = nf_xfrm_me_harder(skb, AF_INET6);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+	}
+#endif
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_out);
+
+unsigned int
+nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+		     const struct net_device *in, const struct net_device *out,
+		     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					      struct sk_buff *skb,
+					      const struct net_device *in,
+					      const struct net_device *out,
+					      struct nf_conn *ct))
+{
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned int ret;
+	int err;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct ipv6hdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
+				      &ct->tuplehash[!dir].tuple.src.u3)) {
+			err = ip6_route_me_harder(skb);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#ifdef CONFIG_XFRM
+		else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
+			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
+			 ct->tuplehash[dir].tuple.dst.u.all !=
+			 ct->tuplehash[!dir].tuple.src.u.all) {
+			err = nf_xfrm_me_harder(skb, AF_INET6);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#endif
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_local_fn);
+
 static int __init nf_nat_l3proto_ipv6_init(void)
 {
 	int err;
diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
index d189fcb437fe..c1c74491a10b 100644
--- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
@@ -28,7 +28,7 @@
  * IPv6 NAT chains
  */
 
-static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
+static unsigned int nft_nat_ipv6_fn(const struct nf_hook_ops *ops,
 			      struct sk_buff *skb,
 			      const struct net_device *in,
 			      const struct net_device *out,
@@ -97,7 +97,7 @@ static unsigned int nf_nat_ipv6_prerouting(const struct nf_hook_ops *ops,
 	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
 	unsigned int ret;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+	ret = nft_nat_ipv6_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
 		skb_dst_drop(skb);
@@ -115,7 +115,7 @@ static unsigned int nf_nat_ipv6_postrouting(const struct nf_hook_ops *ops,
 	const struct nf_conn *ct __maybe_unused;
 	unsigned int ret;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+	ret = nft_nat_ipv6_fn(ops, skb, in, out, okfn);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
@@ -143,7 +143,7 @@ static unsigned int nf_nat_ipv6_output(const struct nf_hook_ops *ops,
 	const struct nf_conn *ct;
 	unsigned int ret;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+	ret = nft_nat_ipv6_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
@@ -177,7 +177,7 @@ static const struct nf_chain_type nft_chain_nat_ipv6 = {
 		[NF_INET_PRE_ROUTING]	= nf_nat_ipv6_prerouting,
 		[NF_INET_POST_ROUTING]	= nf_nat_ipv6_postrouting,
 		[NF_INET_LOCAL_OUT]	= nf_nat_ipv6_output,
-		[NF_INET_LOCAL_IN]	= nf_nat_ipv6_fn,
+		[NF_INET_LOCAL_IN]	= nft_nat_ipv6_fn,
 	},
 };
 
-- 
cgit v1.2.3


From 876665eafc0e43523d0c57b5c937b59696fb4a8f Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Tue, 9 Sep 2014 16:31:09 +0200
Subject: netfilter: nft_chain_nat_ipv6: use generic IPv6 NAT code from core

Use the exported IPv6 NAT functions that are provided by the core. This
removes duplicated code so iptables and nft use the same NAT codebase.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv6/netfilter/nft_chain_nat_ipv6.c | 163 +++++++-------------------------
 1 file changed, 36 insertions(+), 127 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
index c1c74491a10b..1c4b75dd425b 100644
--- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
@@ -24,144 +24,53 @@
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/ipv6.h>
 
-/*
- * IPv6 NAT chains
- */
-
-static unsigned int nft_nat_ipv6_fn(const struct nf_hook_ops *ops,
-			      struct sk_buff *skb,
-			      const struct net_device *in,
-			      const struct net_device *out,
-			      int (*okfn)(struct sk_buff *))
+static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops,
+				     struct sk_buff *skb,
+				     const struct net_device *in,
+				     const struct net_device *out,
+				     struct nf_conn *ct)
 {
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
-	struct nf_conn_nat *nat;
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
-	__be16 frag_off;
-	int hdrlen;
-	u8 nexthdr;
 	struct nft_pktinfo pkt;
-	unsigned int ret;
-
-	if (ct == NULL || nf_ct_is_untracked(ct))
-		return NF_ACCEPT;
-
-	nat = nf_ct_nat_ext_add(ct);
-	if (nat == NULL)
-		return NF_ACCEPT;
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED + IP_CT_IS_REPLY:
-		nexthdr = ipv6_hdr(skb)->nexthdr;
-		hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
-					  &nexthdr, &frag_off);
-
-		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
-			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
-							   ops->hooknum,
-							   hdrlen))
-				return NF_DROP;
-			else
-				return NF_ACCEPT;
-		}
-		/* Fall through */
-	case IP_CT_NEW:
-		if (nf_nat_initialized(ct, maniptype))
-			break;
-
-		nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out);
 
-		ret = nft_do_chain(&pkt, ops);
-		if (ret != NF_ACCEPT)
-			return ret;
-		if (!nf_nat_initialized(ct, maniptype)) {
-			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
-			if (ret != NF_ACCEPT)
-				return ret;
-		}
-	default:
-		break;
-	}
+	nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out);
 
-	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
+	return nft_do_chain(&pkt, ops);
 }
 
-static unsigned int nf_nat_ipv6_prerouting(const struct nf_hook_ops *ops,
-				      struct sk_buff *skb,
-				      const struct net_device *in,
-				      const struct net_device *out,
-				      int (*okfn)(struct sk_buff *))
+static unsigned int nft_nat_ipv6_fn(const struct nf_hook_ops *ops,
+				    struct sk_buff *skb,
+				    const struct net_device *in,
+				    const struct net_device *out,
+				    int (*okfn)(struct sk_buff *))
 {
-	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
-	unsigned int ret;
-
-	ret = nft_nat_ipv6_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
-		skb_dst_drop(skb);
-
-	return ret;
+	return nf_nat_ipv6_fn(ops, skb, in, out, nft_nat_do_chain);
 }
 
-static unsigned int nf_nat_ipv6_postrouting(const struct nf_hook_ops *ops,
-				       struct sk_buff *skb,
-				       const struct net_device *in,
-				       const struct net_device *out,
-				       int (*okfn)(struct sk_buff *))
+static unsigned int nft_nat_ipv6_in(const struct nf_hook_ops *ops,
+				    struct sk_buff *skb,
+				    const struct net_device *in,
+				    const struct net_device *out,
+				    int (*okfn)(struct sk_buff *))
 {
-	enum ip_conntrack_info ctinfo __maybe_unused;
-	const struct nf_conn *ct __maybe_unused;
-	unsigned int ret;
-
-	ret = nft_nat_ipv6_fn(ops, skb, in, out, okfn);
-#ifdef CONFIG_XFRM
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
-				      &ct->tuplehash[!dir].tuple.dst.u3) ||
-		    (ct->tuplehash[dir].tuple.src.u.all !=
-		     ct->tuplehash[!dir].tuple.dst.u.all))
-			if (nf_xfrm_me_harder(skb, AF_INET6) < 0)
-				ret = NF_DROP;
-	}
-#endif
-	return ret;
+	return nf_nat_ipv6_in(ops, skb, in, out, nft_nat_do_chain);
 }
 
-static unsigned int nf_nat_ipv6_output(const struct nf_hook_ops *ops,
-				  struct sk_buff *skb,
-				  const struct net_device *in,
-				  const struct net_device *out,
-				  int (*okfn)(struct sk_buff *))
+static unsigned int nft_nat_ipv6_out(const struct nf_hook_ops *ops,
+				     struct sk_buff *skb,
+				     const struct net_device *in,
+				     const struct net_device *out,
+				     int (*okfn)(struct sk_buff *))
 {
-	enum ip_conntrack_info ctinfo;
-	const struct nf_conn *ct;
-	unsigned int ret;
-
-	ret = nft_nat_ipv6_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+	return nf_nat_ipv6_out(ops, skb, in, out, nft_nat_do_chain);
+}
 
-		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
-				      &ct->tuplehash[!dir].tuple.src.u3)) {
-			if (ip6_route_me_harder(skb))
-				ret = NF_DROP;
-		}
-#ifdef CONFIG_XFRM
-		else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
-			 ct->tuplehash[dir].tuple.dst.u.all !=
-			 ct->tuplehash[!dir].tuple.src.u.all)
-			if (nf_xfrm_me_harder(skb, AF_INET6))
-				ret = NF_DROP;
-#endif
-	}
-	return ret;
+static unsigned int nft_nat_ipv6_local_fn(const struct nf_hook_ops *ops,
+					  struct sk_buff *skb,
+					  const struct net_device *in,
+					  const struct net_device *out,
+					  int (*okfn)(struct sk_buff *))
+{
+	return nf_nat_ipv6_local_fn(ops, skb, in, out, nft_nat_do_chain);
 }
 
 static const struct nf_chain_type nft_chain_nat_ipv6 = {
@@ -174,9 +83,9 @@ static const struct nf_chain_type nft_chain_nat_ipv6 = {
 			  (1 << NF_INET_LOCAL_OUT) |
 			  (1 << NF_INET_LOCAL_IN),
 	.hooks		= {
-		[NF_INET_PRE_ROUTING]	= nf_nat_ipv6_prerouting,
-		[NF_INET_POST_ROUTING]	= nf_nat_ipv6_postrouting,
-		[NF_INET_LOCAL_OUT]	= nf_nat_ipv6_output,
+		[NF_INET_PRE_ROUTING]	= nft_nat_ipv6_in,
+		[NF_INET_POST_ROUTING]	= nft_nat_ipv6_out,
+		[NF_INET_LOCAL_OUT]	= nft_nat_ipv6_local_fn,
 		[NF_INET_LOCAL_IN]	= nft_nat_ipv6_fn,
 	},
 };
-- 
cgit v1.2.3


From be6b635cd674add9410efa9ac6f03e0040848b12 Mon Sep 17 00:00:00 2001
From: Arturo Borrero
Date: Thu, 4 Sep 2014 14:06:49 +0200
Subject: netfilter: nf_nat: generalize IPv6 masquerading support for nf_tables

Let's refactor the code so we can reach the masquerade functionality
from outside the xt context (ie. nftables).

The patch includes the addition of an atomic counter to the masquerade
notifier: the stuff to be done by the notifier is the same for xt and
nftables. Therefore, only one notification handler is needed.

This factorization only involves IPv6; a similar patch exists to
handle IPv4.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv6/nf_nat_masquerade.h |  10 +++
 net/ipv6/netfilter/Kconfig                     |   7 ++
 net/ipv6/netfilter/Makefile                    |   1 +
 net/ipv6/netfilter/ip6t_MASQUERADE.c           |  76 ++--------------
 net/ipv6/netfilter/nf_nat_masquerade_ipv6.c    | 120 +++++++++++++++++++++++++
 5 files changed, 143 insertions(+), 71 deletions(-)
 create mode 100644 include/net/netfilter/ipv6/nf_nat_masquerade.h
 create mode 100644 net/ipv6/netfilter/nf_nat_masquerade_ipv6.c

(limited to 'net/ipv6')

diff --git a/include/net/netfilter/ipv6/nf_nat_masquerade.h b/include/net/netfilter/ipv6/nf_nat_masquerade.h
new file mode 100644
index 000000000000..0a13396cd390
--- /dev/null
+++ b/include/net/netfilter/ipv6/nf_nat_masquerade.h
@@ -0,0 +1,10 @@
+#ifndef _NF_NAT_MASQUERADE_IPV6_H_
+#define _NF_NAT_MASQUERADE_IPV6_H_
+
+unsigned int
+nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+		       const struct net_device *out);
+void nf_nat_masquerade_ipv6_register_notifier(void);
+void nf_nat_masquerade_ipv6_unregister_notifier(void);
+
+#endif /* _NF_NAT_MASQUERADE_IPV6_H_ */
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index ac93df16f5af..6c8cfec6836a 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -246,8 +246,15 @@ config NF_NAT_IPV6
 
 if NF_NAT_IPV6
 
+config NF_NAT_MASQUERADE_IPV6
+	tristate "IPv6 masquerade support"
+	help
+	 This is the kernel functionality to provide NAT in the masquerade
+	 flavour (automatic source address selection) for IPv6.
+
 config IP6_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
+	select NF_NAT_MASQUERADE_IPV6
 	help
 	  Masquerading is a special case of NAT: all outgoing connections are
 	  changed to seem to come from a particular interface's address, and
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index c0b263104ed2..89a0bd751f82 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o
 
 nf_nat_ipv6-y		:= nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o
 obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
+obj-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o
 
 # defrag
 nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 3e4e92d5e157..7f9f45d829d2 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -19,33 +19,12 @@
 #include <net/netfilter/nf_nat.h>
 #include <net/addrconf.h>
 #include <net/ipv6.h>
+#include <net/netfilter/ipv6/nf_nat_masquerade.h>
 
 static unsigned int
 masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	const struct nf_nat_range *range = par->targinfo;
-	enum ip_conntrack_info ctinfo;
-	struct in6_addr src;
-	struct nf_conn *ct;
-	struct nf_nat_range newrange;
-
-	ct = nf_ct_get(skb, &ctinfo);
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-			    ctinfo == IP_CT_RELATED_REPLY));
-
-	if (ipv6_dev_get_saddr(dev_net(par->out), par->out,
-			       &ipv6_hdr(skb)->daddr, 0, &src) < 0)
-		return NF_DROP;
-
-	nfct_nat(ct)->masq_index = par->out->ifindex;
-
-	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.in6	= src;
-	newrange.max_addr.in6	= src;
-	newrange.min_proto	= range->min_proto;
-	newrange.max_proto	= range->max_proto;
-
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+	return nf_nat_masquerade_ipv6(skb, par->targinfo, par->out);
 }
 
 static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
@@ -57,48 +36,6 @@ static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
 	return 0;
 }
 
-static int device_cmp(struct nf_conn *ct, void *ifindex)
-{
-	const struct nf_conn_nat *nat = nfct_nat(ct);
-
-	if (!nat)
-		return 0;
-	if (nf_ct_l3num(ct) != NFPROTO_IPV6)
-		return 0;
-	return nat->masq_index == (int)(long)ifindex;
-}
-
-static int masq_device_event(struct notifier_block *this,
-			     unsigned long event, void *ptr)
-{
-	const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct net *net = dev_net(dev);
-
-	if (event == NETDEV_DOWN)
-		nf_ct_iterate_cleanup(net, device_cmp,
-				      (void *)(long)dev->ifindex, 0, 0);
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block masq_dev_notifier = {
-	.notifier_call	= masq_device_event,
-};
-
-static int masq_inet_event(struct notifier_block *this,
-			   unsigned long event, void *ptr)
-{
-	struct inet6_ifaddr *ifa = ptr;
-	struct netdev_notifier_info info;
-
-	netdev_notifier_info_init(&info, ifa->idev->dev);
-	return masq_device_event(this, event, &info);
-}
-
-static struct notifier_block masq_inet_notifier = {
-	.notifier_call	= masq_inet_event,
-};
-
 static struct xt_target masquerade_tg6_reg __read_mostly = {
 	.name		= "MASQUERADE",
 	.family		= NFPROTO_IPV6,
@@ -115,17 +52,14 @@ static int __init masquerade_tg6_init(void)
 	int err;
 
 	err = xt_register_target(&masquerade_tg6_reg);
-	if (err == 0) {
-		register_netdevice_notifier(&masq_dev_notifier);
-		register_inet6addr_notifier(&masq_inet_notifier);
-	}
+	if (err == 0)
+		nf_nat_masquerade_ipv6_register_notifier();
 
 	return err;
 }
 static void __exit masquerade_tg6_exit(void)
 {
-	unregister_inet6addr_notifier(&masq_inet_notifier);
-	unregister_netdevice_notifier(&masq_dev_notifier);
+	nf_nat_masquerade_ipv6_unregister_notifier();
 	xt_unregister_target(&masquerade_tg6_reg);
 }
 
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
new file mode 100644
index 000000000000..7745609665cd
--- /dev/null
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -0,0 +1,120 @@
+/*
+ * Copyright (c) 2011 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 version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/atomic.h>
+#include <linux/netdevice.h>
+#include <linux/ipv6.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+
+unsigned int
+nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+		       const struct net_device *out)
+{
+	enum ip_conntrack_info ctinfo;
+	struct in6_addr src;
+	struct nf_conn *ct;
+	struct nf_nat_range newrange;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
+			    ctinfo == IP_CT_RELATED_REPLY));
+
+	if (ipv6_dev_get_saddr(dev_net(out), out,
+			       &ipv6_hdr(skb)->daddr, 0, &src) < 0)
+		return NF_DROP;
+
+	nfct_nat(ct)->masq_index = out->ifindex;
+
+	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.in6	= src;
+	newrange.max_addr.in6	= src;
+	newrange.min_proto	= range->min_proto;
+	newrange.max_proto	= range->max_proto;
+
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6);
+
+static int device_cmp(struct nf_conn *ct, void *ifindex)
+{
+	const struct nf_conn_nat *nat = nfct_nat(ct);
+
+	if (!nat)
+		return 0;
+	if (nf_ct_l3num(ct) != NFPROTO_IPV6)
+		return 0;
+	return nat->masq_index == (int)(long)ifindex;
+}
+
+static int masq_device_event(struct notifier_block *this,
+			     unsigned long event, void *ptr)
+{
+	const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(dev);
+
+	if (event == NETDEV_DOWN)
+		nf_ct_iterate_cleanup(net, device_cmp,
+				      (void *)(long)dev->ifindex, 0, 0);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block masq_dev_notifier = {
+	.notifier_call	= masq_device_event,
+};
+
+static int masq_inet_event(struct notifier_block *this,
+			   unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = ptr;
+	struct netdev_notifier_info info;
+
+	netdev_notifier_info_init(&info, ifa->idev->dev);
+	return masq_device_event(this, event, &info);
+}
+
+static struct notifier_block masq_inet_notifier = {
+	.notifier_call	= masq_inet_event,
+};
+
+static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+
+void nf_nat_masquerade_ipv6_register_notifier(void)
+{
+	/* check if the notifier is already set */
+	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
+		return;
+
+	register_netdevice_notifier(&masq_dev_notifier);
+	register_inet6addr_notifier(&masq_inet_notifier);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
+
+void nf_nat_masquerade_ipv6_unregister_notifier(void)
+{
+	/* check if the notifier still has clients */
+	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
+		return;
+
+	unregister_inet6addr_notifier(&masq_inet_notifier);
+	unregister_netdevice_notifier(&masq_dev_notifier);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-- 
cgit v1.2.3


From 9ba1f726bec090399eb9bb9157eb32dedc8e8c45 Mon Sep 17 00:00:00 2001
From: Arturo Borrero
Date: Mon, 8 Sep 2014 13:45:00 +0200
Subject: netfilter: nf_tables: add new nft_masq expression

The nft_masq expression is intended to perform NAT in the masquerade flavour.

We decided to have the masquerade functionality in a separated expression other
than nft_nat.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nft_masq.h         | 16 ++++++
 include/uapi/linux/netfilter/nf_tables.h | 11 ++++
 net/ipv4/netfilter/Kconfig               |  6 +++
 net/ipv4/netfilter/Makefile              |  1 +
 net/ipv4/netfilter/nft_masq_ipv4.c       | 89 ++++++++++++++++++++++++++++++++
 net/ipv6/netfilter/Kconfig               |  6 +++
 net/ipv6/netfilter/Makefile              |  1 +
 net/ipv6/netfilter/nft_masq_ipv6.c       | 89 ++++++++++++++++++++++++++++++++
 net/netfilter/Kconfig                    |  9 ++++
 net/netfilter/Makefile                   |  1 +
 net/netfilter/nft_masq.c                 | 59 +++++++++++++++++++++
 11 files changed, 288 insertions(+)
 create mode 100644 include/net/netfilter/nft_masq.h
 create mode 100644 net/ipv4/netfilter/nft_masq_ipv4.c
 create mode 100644 net/ipv6/netfilter/nft_masq_ipv6.c
 create mode 100644 net/netfilter/nft_masq.c

(limited to 'net/ipv6')

diff --git a/include/net/netfilter/nft_masq.h b/include/net/netfilter/nft_masq.h
new file mode 100644
index 000000000000..c72729f954f4
--- /dev/null
+++ b/include/net/netfilter/nft_masq.h
@@ -0,0 +1,16 @@
+#ifndef _NFT_MASQ_H_
+#define _NFT_MASQ_H_
+
+struct nft_masq {
+	u32	flags;
+};
+
+extern const struct nla_policy nft_masq_policy[];
+
+int nft_masq_init(const struct nft_ctx *ctx,
+		  const struct nft_expr *expr,
+		  const struct nlattr * const tb[]);
+
+int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr);
+
+#endif /* _NFT_MASQ_H_ */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 6022c6e6be18..eeec0ae845ef 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -800,4 +800,15 @@ enum nft_nat_attributes {
 };
 #define NFTA_NAT_MAX		(__NFTA_NAT_MAX - 1)
 
+/**
+ * enum nft_masq_attributes - nf_tables masquerade expression attributes
+ *
+ * @NFTA_MASQ_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32)
+ */
+enum nft_masq_attributes {
+	NFTA_MASQ_FLAGS,
+	__NFTA_MASQ_MAX
+};
+#define NFTA_MASQ_MAX		(__NFTA_MASQ_MAX - 1)
+
 #endif /* _LINUX_NF_TABLES_H */
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 4be3e541350e..8dd3d9f19d82 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -190,6 +190,12 @@ config NF_NAT_MASQUERADE_IPV4
 	This is the kernel functionality to provide NAT in the masquerade
 	flavour (automatic source address selection).
 
+config NFT_MASQ_IPV4
+	tristate "IPv4 masquerading support for nf_tables"
+	depends on NF_TABLES_IPV4
+	depends on NFT_MASQ
+	select NF_NAT_MASQUERADE_IPV4
+
 config IP_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
 	select NF_NAT_MASQUERADE_IPV4
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 42056b2fd0e3..7d019aefb0ed 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -36,6 +36,7 @@ obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
+obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o
 obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
 # generic IP tables 
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
new file mode 100644
index 000000000000..6ea1d207b6a5
--- /dev/null
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_masq.h>
+#include <net/netfilter/ipv4/nf_nat_masquerade.h>
+
+static void nft_masq_ipv4_eval(const struct nft_expr *expr,
+			       struct nft_data data[NFT_REG_MAX + 1],
+			       const struct nft_pktinfo *pkt)
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+	struct nf_nat_range range;
+	unsigned int verdict;
+
+	range.flags = priv->flags;
+
+	verdict = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum,
+					 &range, pkt->out);
+
+	data[NFT_REG_VERDICT].verdict = verdict;
+}
+
+static int nft_masq_ipv4_init(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nlattr * const tb[])
+{
+	int err;
+
+	err = nft_masq_init(ctx, expr, tb);
+	if (err < 0)
+		return err;
+
+	nf_nat_masquerade_ipv4_register_notifier();
+	return 0;
+}
+
+static void nft_masq_ipv4_destroy(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr)
+{
+	nf_nat_masquerade_ipv4_unregister_notifier();
+}
+
+static struct nft_expr_type nft_masq_ipv4_type;
+static const struct nft_expr_ops nft_masq_ipv4_ops = {
+	.type		= &nft_masq_ipv4_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
+	.eval		= nft_masq_ipv4_eval,
+	.init		= nft_masq_ipv4_init,
+	.destroy	= nft_masq_ipv4_destroy,
+	.dump		= nft_masq_dump,
+};
+
+static struct nft_expr_type nft_masq_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.name		= "masq",
+	.ops		= &nft_masq_ipv4_ops,
+	.policy		= nft_masq_policy,
+	.maxattr	= NFTA_MASQ_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_masq_ipv4_module_init(void)
+{
+	return nft_register_expr(&nft_masq_ipv4_type);
+}
+
+static void __exit nft_masq_ipv4_module_exit(void)
+{
+	nft_unregister_expr(&nft_masq_ipv4_type);
+}
+
+module_init(nft_masq_ipv4_module_init);
+module_exit(nft_masq_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "masq");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 6c8cfec6836a..24c535f66df0 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -252,6 +252,12 @@ config NF_NAT_MASQUERADE_IPV6
 	 This is the kernel functionality to provide NAT in the masquerade
 	 flavour (automatic source address selection) for IPv6.
 
+config NFT_MASQ_IPV6
+	tristate "IPv6 masquerade support for nf_tables"
+	depends on NF_TABLES_IPV6
+	depends on NFT_MASQ
+	select NF_NAT_MASQUERADE_IPV6
+
 config IP6_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
 	select NF_NAT_MASQUERADE_IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 89a0bd751f82..482c4dff273f 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
 obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
+obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o
 
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
new file mode 100644
index 000000000000..4e51334ef6b7
--- /dev/null
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nft_masq.h>
+#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+
+static void nft_masq_ipv6_eval(const struct nft_expr *expr,
+			       struct nft_data data[NFT_REG_MAX + 1],
+			       const struct nft_pktinfo *pkt)
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+	struct nf_nat_range range;
+	unsigned int verdict;
+
+	range.flags = priv->flags;
+
+	verdict = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out);
+
+	data[NFT_REG_VERDICT].verdict = verdict;
+}
+
+static int nft_masq_ipv6_init(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nlattr * const tb[])
+{
+	int err;
+
+	err = nft_masq_init(ctx, expr, tb);
+	if (err < 0)
+		return err;
+
+	nf_nat_masquerade_ipv6_register_notifier();
+	return 0;
+}
+
+static void nft_masq_ipv6_destroy(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr)
+{
+	nf_nat_masquerade_ipv6_unregister_notifier();
+}
+
+static struct nft_expr_type nft_masq_ipv6_type;
+static const struct nft_expr_ops nft_masq_ipv6_ops = {
+	.type		= &nft_masq_ipv6_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
+	.eval		= nft_masq_ipv6_eval,
+	.init		= nft_masq_ipv6_init,
+	.destroy	= nft_masq_ipv6_destroy,
+	.dump		= nft_masq_dump,
+};
+
+static struct nft_expr_type nft_masq_ipv6_type __read_mostly = {
+	.family		= NFPROTO_IPV6,
+	.name		= "masq",
+	.ops		= &nft_masq_ipv6_ops,
+	.policy		= nft_masq_policy,
+	.maxattr	= NFTA_MASQ_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_masq_ipv6_module_init(void)
+{
+	return nft_register_expr(&nft_masq_ipv6_type);
+}
+
+static void __exit nft_masq_ipv6_module_exit(void)
+{
+	nft_unregister_expr(&nft_masq_ipv6_type);
+}
+
+module_init(nft_masq_ipv6_module_init);
+module_exit(nft_masq_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "masq");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index ad751fe2e82b..37428723394f 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -496,6 +496,15 @@ config NFT_LIMIT
 	  This option adds the "limit" expression that you can use to
 	  ratelimit rule matchings.
 
+config NFT_MASQ
+	depends on NF_TABLES
+	depends on NF_CONNTRACK
+	depends on NF_NAT
+	tristate "Netfilter nf_tables masquerade support"
+	help
+	  This option adds the "masquerade" expression that you can use
+	  to perform NAT in the masquerade flavour.
+
 config NFT_NAT
 	depends on NF_TABLES
 	depends on NF_CONNTRACK
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 8308624a406a..0637792f6faf 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -87,6 +87,7 @@ obj-$(CONFIG_NFT_RBTREE)	+= nft_rbtree.o
 obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
 obj-$(CONFIG_NFT_LOG)		+= nft_log.o
+obj-$(CONFIG_NFT_MASQ)		+= nft_masq.o
 
 # generic X tables 
 obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
new file mode 100644
index 000000000000..6637bab00567
--- /dev/null
+++ b/net/netfilter/nft_masq.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nft_masq.h>
+
+const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = {
+	[NFTA_MASQ_FLAGS]	= { .type = NLA_U32 },
+};
+EXPORT_SYMBOL_GPL(nft_masq_policy);
+
+int nft_masq_init(const struct nft_ctx *ctx,
+		  const struct nft_expr *expr,
+		  const struct nlattr * const tb[])
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+
+	if (tb[NFTA_MASQ_FLAGS] == NULL)
+		return 0;
+
+	priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS]));
+	if (priv->flags & ~NF_NAT_RANGE_MASK)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_masq_init);
+
+int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_masq *priv = nft_expr_priv(expr);
+
+	if (priv->flags == 0)
+		return 0;
+
+	if (nla_put_be32(skb, NFTA_MASQ_FLAGS, htonl(priv->flags)))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+EXPORT_SYMBOL_GPL(nft_masq_dump);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
-- 
cgit v1.2.3


From 49a601589caaf0e93194c0cc9b4ecddbe75dd2d5 Mon Sep 17 00:00:00 2001
From: Vincent Bernat
Date: Fri, 5 Sep 2014 15:09:03 +0200
Subject: net/ipv4: bind ip_nonlocal_bind to current netns

net.ipv4.ip_nonlocal_bind sysctl was global to all network
namespaces. This patch allows to set a different value for each
network namespace.

Signed-off-by: Vincent Bernat <vincent@bernat.im>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h           |  2 --
 include/net/netns/ipv4.h   |  1 +
 net/ipv4/af_inet.c         |  6 +-----
 net/ipv4/ping.c            |  2 +-
 net/ipv4/sysctl_net_ipv4.c | 14 +++++++-------
 net/ipv6/af_inet6.c        |  2 +-
 net/sctp/protocol.c        |  2 +-
 7 files changed, 12 insertions(+), 17 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/ip.h b/include/net/ip.h
index c8fd6112bd0b..14bfc8e1bcf9 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -229,8 +229,6 @@ static inline int inet_is_local_reserved_port(struct net *net, int port)
 }
 #endif
 
-extern int sysctl_ip_nonlocal_bind;
-
 /* From inetpeer.c */
 extern int inet_peer_threshold;
 extern int inet_peer_minttl;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index aec5e12f9f19..24945cefc4fd 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -76,6 +76,7 @@ struct netns_ipv4 {
 	int sysctl_tcp_ecn;
 	int sysctl_ip_no_pmtu_disc;
 	int sysctl_ip_fwd_use_pmtu;
+	int sysctl_ip_nonlocal_bind;
 
 	int sysctl_fwmark_reflect;
 	int sysctl_tcp_fwmark_accept;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d156b3c5f363..b537bd94906c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -418,10 +418,6 @@ int inet_release(struct socket *sock)
 }
 EXPORT_SYMBOL(inet_release);
 
-/* It is off by default, see below. */
-int sysctl_ip_nonlocal_bind __read_mostly;
-EXPORT_SYMBOL(sysctl_ip_nonlocal_bind);
-
 int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
@@ -461,7 +457,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	 *  is temporarily down)
 	 */
 	err = -EADDRNOTAVAIL;
-	if (!sysctl_ip_nonlocal_bind &&
+	if (!net->ipv4.sysctl_ip_nonlocal_bind &&
 	    !(inet->freebind || inet->transparent) &&
 	    addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
 	    chk_addr_ret != RTN_LOCAL &&
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index a3c59a077a5f..57f7c9804139 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -311,7 +311,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 		if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
 			chk_addr_ret = RTN_LOCAL;
 
-		if ((sysctl_ip_nonlocal_bind == 0 &&
+		if ((net->ipv4.sysctl_ip_nonlocal_bind == 0 &&
 		    isk->freebind == 0 && isk->transparent == 0 &&
 		     chk_addr_ret != RTN_LOCAL) ||
 		    chk_addr_ret == RTN_MULTICAST ||
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 45d156dacd61..1599966f4639 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -285,13 +285,6 @@ static struct ctl_table ipv4_table[] = {
 		.extra1		= &ip_ttl_min,
 		.extra2		= &ip_ttl_max,
 	},
-	{
-		.procname	= "ip_nonlocal_bind",
-		.data		= &sysctl_ip_nonlocal_bind,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 	{
 		.procname	= "tcp_syn_retries",
 		.data		= &sysctl_tcp_syn_retries,
@@ -848,6 +841,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "ip_nonlocal_bind",
+		.data		= &init_net.ipv4.sysctl_ip_nonlocal_bind,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 	{
 		.procname	= "fwmark_reflect",
 		.data		= &init_net.ipv4.sysctl_fwmark_reflect,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index b9393e6a21fe..e4865a3ebe1d 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -302,7 +302,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		/* Reproduce AF_INET checks to make the bindings consistent */
 		v4addr = addr->sin6_addr.s6_addr32[3];
 		chk_addr_ret = inet_addr_type(net, v4addr);
-		if (!sysctl_ip_nonlocal_bind &&
+		if (!net->ipv4.sysctl_ip_nonlocal_bind &&
 		    !(inet->freebind || inet->transparent) &&
 		    v4addr != htonl(INADDR_ANY) &&
 		    chk_addr_ret != RTN_LOCAL &&
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 6240834f4b95..9d2c6c9facb6 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -366,7 +366,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
 	if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
 	   ret != RTN_LOCAL &&
 	   !sp->inet.freebind &&
-	   !sysctl_ip_nonlocal_bind)
+	   !net->ipv4.sysctl_ip_nonlocal_bind)
 		return 0;
 
 	if (ipv6_only_sock(sctp_opt2sk(sp)))
-- 
cgit v1.2.3


From ca777eff51f7fbaebd954e645d8ecb781a906b4a Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Mon, 8 Sep 2014 08:06:07 -0700
Subject: tcp: remove dst refcount false sharing for prequeue mode

Alexander Duyck reported high false sharing on dst refcount in tcp stack
when prequeue is used. prequeue is the mechanism used when a thread is
blocked in recvmsg()/read() on a TCP socket, using a blocking model
rather than select()/poll()/epoll() non blocking one.

We already try to use RCU in input path as much as possible, but we were
forced to take a refcount on the dst when skb escaped RCU protected
region. When/if the user thread runs on different cpu, dst_release()
will then touch dst refcount again.

Commit 093162553c33 (tcp: force a dst refcount when prequeue packet)
was an example of a race fix.

It turns out the only remaining usage of skb->dst for a packet stored
in a TCP socket prequeue is IP early demux.

We can add a logic to detect when IP early demux is probably going
to use skb->dst. Because we do an optimistic check rather than duplicate
existing logic, we need to guard inet_sk_rx_dst_set() and
inet6_sk_rx_dst_set() from using a NULL dst.

Many thanks to Alexander for providing a nice bug report, git bisection,
and reproducer.

Tested using Alexander script on a 40Gb NIC, 8 RX queues.
Hosts have 24 cores, 48 hyper threads.

echo 0 >/proc/sys/net/ipv4/tcp_autocorking

for i in `seq 0 47`
do
  for j in `seq 0 2`
  do
     netperf -H $DEST -t TCP_STREAM -l 1000 \
             -c -C -T $i,$i -P 0 -- \
             -m 64 -s 64K -D &
  done
done

Before patch : ~6Mpps and ~95% cpu usage on receiver
After patch : ~9Mpps and ~35% cpu usage on receiver.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 20 ++++++++++++++++----
 net/ipv6/tcp_ipv6.c | 15 +++++++++------
 2 files changed, 25 insertions(+), 10 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3f9bc3f0bba0..7881b96d2b72 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1559,7 +1559,17 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 	    skb_queue_len(&tp->ucopy.prequeue) == 0)
 		return false;
 
-	skb_dst_force(skb);
+	/* Before escaping RCU protected region, we need to take care of skb
+	 * dst. Prequeue is only enabled for established sockets.
+	 * For such sockets, we might need the skb dst only to set sk->sk_rx_dst
+	 * Instead of doing full sk_rx_dst validity here, let's perform
+	 * an optimistic check.
+	 */
+	if (likely(sk->sk_rx_dst))
+		skb_dst_drop(skb);
+	else
+		skb_dst_force(skb);
+
 	__skb_queue_tail(&tp->ucopy.prequeue, skb);
 	tp->ucopy.memory += skb->truesize;
 	if (tp->ucopy.memory > sk->sk_rcvbuf) {
@@ -1765,9 +1775,11 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
-	dst_hold(dst);
-	sk->sk_rx_dst = dst;
-	inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+	if (dst) {
+		dst_hold(dst);
+		sk->sk_rx_dst = dst;
+		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+	}
 }
 EXPORT_SYMBOL(inet_sk_rx_dst_set);
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5b3c70ff7a72..1835480336ac 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -93,13 +93,16 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
 static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
-	const struct rt6_info *rt = (const struct rt6_info *)dst;
 
-	dst_hold(dst);
-	sk->sk_rx_dst = dst;
-	inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
-	if (rt->rt6i_node)
-		inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+	if (dst) {
+		const struct rt6_info *rt = (const struct rt6_info *)dst;
+
+		dst_hold(dst);
+		sk->sk_rx_dst = dst;
+		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+		if (rt->rt6i_node)
+			inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+	}
 }
 
 static void tcp_v6_hash(struct sock *sk)
-- 
cgit v1.2.3


From cbeddd5d163ba7a6cd96a96509f7043cce4f68d2 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Sep 2014 13:07:32 +0200
Subject: ipv6: mcast: remove dead debugging defines

It's not used anywhere, so just remove these.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 6833dd07b2c2..484a94215d88 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -64,15 +64,6 @@
 
 #include <net/ip6_checksum.h>
 
-/* Set to 3 to get tracing... */
-#define MCAST_DEBUG 2
-
-#if MCAST_DEBUG >= 3
-#define MDBG(x) printk x
-#else
-#define MDBG(x)
-#endif
-
 /* Ensure that we have struct in6_addr aligned on 32bit word. */
 static void *__mld2_query_bugs[] __attribute__((__unused__)) = {
 	BUILD_BUG_ON_NULL(offsetof(struct mld2_query, mld2q_srcs) % 4),
-- 
cgit v1.2.3


From cc9c668a0805cdf6141ffae3d8e9a94875ec7a54 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Tue, 9 Sep 2014 08:16:17 -0700
Subject: ipv6: udp6_gro_complete() is static

net/ipv6/udp_offload.c:159:5: warning: symbol 'udp6_gro_complete' was
not declared. Should it be static?

Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 57c67ff4bd92 ("udp: additional GRO support")
Cc: Tom Herbert <therbert@google.com>
Acked-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 89cb9a9b8537..a1ad34b1c4ec 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -156,7 +156,7 @@ flush:
 	return NULL;
 }
 
-int udp6_gro_complete(struct sk_buff *skb, int nhoff)
+static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
-- 
cgit v1.2.3


From 46cfd725c377bc5bb32b56b5151d6de4cb5a71e3 Mon Sep 17 00:00:00 2001
From: Florian Westphal
Date: Wed, 10 Sep 2014 01:08:46 +0200
Subject: net: use kfree_skb_list() helper in more places

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c  | 6 +-----
 net/xfrm/xfrm_output.c | 6 +-----
 2 files changed, 2 insertions(+), 10 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index b7a3e7b3378e..2e6a0dbf7fb3 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -701,11 +701,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 			return 0;
 		}
 
-		while (frag) {
-			skb = frag->next;
-			kfree_skb(frag);
-			frag = skb;
-		}
+		kfree_skb_list(frag);
 
 		IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 			      IPSTATS_MIB_FRAGFAILS);
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index c51e8f7b8653..499d6c18a8ce 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -166,11 +166,7 @@ static int xfrm_output_gso(struct sk_buff *skb)
 		err = xfrm_output2(segs);
 
 		if (unlikely(err)) {
-			while ((segs = nskb)) {
-				nskb = segs->next;
-				segs->next = NULL;
-				kfree_skb(segs);
-			}
+			kfree_skb_list(nskb);
 			return err;
 		}
 
-- 
cgit v1.2.3


From 03d56daafe9d4e04a8a0d305789cd3eda250746b Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Tue, 9 Sep 2014 11:23:14 -0700
Subject: ipv6: Clear flush_id to make GRO work

In TCP gro we check flush_id which is derived from the IP identifier.
In IPv4 gro path the flush_id is set with the expectation that every
matched packet increments IP identifier. In IPv6, the flush_id is
never set and thus is uinitialized. What's worse is that in IPv6
over IPv4 encapsulation, the IP identifier is taken from the outer
header which is currently not incremented on every packet for Linux
stack, so GRO in this case never matches packets (identifier is
not increasing).

This patch clears flush_id for every time for a matched packet in
IPv6 gro_receive. We need to do this each time to overwrite the
setting that would be done in IPv4 gro_receive per the outer
header in IPv6 over Ipv4 encapsulation.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_offload.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'net/ipv6')

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 5bcda338bcef..929bbbcd0c8e 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -261,6 +261,9 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 		/* flush if Traffic Class fields are different */
 		NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000));
 		NAPI_GRO_CB(p)->flush |= flush;
+
+		/* Clear flush_id, there's really no concept of ID in IPv6. */
+		NAPI_GRO_CB(p)->flush_id = 0;
 	}
 
 	NAPI_GRO_CB(skb)->flush |= flush;
-- 
cgit v1.2.3


From 19424e052fb44da2f00d1a868cbb51f3e9f4bbb5 Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Tue, 9 Sep 2014 11:23:16 -0700
Subject: sit: Add gro callbacks to sit_offload

Add ipv6_gro_receive and ipv6_gro_complete to sit_offload to
support GRO.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_offload.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'net/ipv6')

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 929bbbcd0c8e..9952f3fce30a 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -317,6 +317,8 @@ static const struct net_offload sit_offload = {
 	.callbacks = {
 		.gso_send_check = ipv6_gso_send_check,
 		.gso_segment	= ipv6_gso_segment,
+		.gro_receive	= ipv6_gro_receive,
+		.gro_complete	= ipv6_gro_complete,
 	},
 };
 
-- 
cgit v1.2.3


From 3e8dc212a0e68a9a90c97f34a92c4cdd97d19dd3 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Thu, 11 Sep 2014 17:42:00 +0200
Subject: netfilter: NFT_CHAIN_NAT_IPV* is independent of NFT_NAT

Now that we have masquerading support in nf_tables, the NAT chain can
be use with it, not only for SNAT/DNAT. So make this chain type
independent of it.

While at it, move it inside the scope of 'if NF_NAT_IPV*' to simplify
dependencies.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/Kconfig | 19 +++++++++----------
 net/ipv6/netfilter/Kconfig | 23 +++++++++++++----------
 2 files changed, 22 insertions(+), 20 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index d189c5262bdb..eb6995fc4f67 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -61,16 +61,6 @@ config NFT_CHAIN_ROUTE_IPV4
 	  fields such as the source, destination, type of service and
 	  the packet mark.
 
-config NFT_CHAIN_NAT_IPV4
-	depends on NF_TABLES_IPV4
-	depends on NF_NAT_IPV4 && NFT_NAT
-	tristate "IPv4 nf_tables nat chain support"
-	help
-	  This option enables the "nat" chain for IPv4 in nf_tables. This
-	  chain type is used to perform Network Address Translation (NAT)
-	  packet transformations such as the source, destination address and
-	  source and destination ports.
-
 config NFT_REJECT_IPV4
 	depends on NF_TABLES_IPV4
 	default NFT_REJECT
@@ -94,6 +84,15 @@ config NF_NAT_IPV4
 
 if NF_NAT_IPV4
 
+config NFT_CHAIN_NAT_IPV4
+	depends on NF_TABLES_IPV4
+	tristate "IPv4 nf_tables nat chain support"
+	help
+	  This option enables the "nat" chain for IPv4 in nf_tables. This
+	  chain type is used to perform Network Address Translation (NAT)
+	  packet transformations such as the source, destination address and
+	  source and destination ports.
+
 config NF_NAT_SNMP_BASIC
 	tristate "Basic SNMP-ALG support"
 	depends on NF_CONNTRACK_SNMP
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index a8f25306a46a..e854062d0c36 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -40,16 +40,6 @@ config NFT_CHAIN_ROUTE_IPV6
 	  fields such as the source, destination, flowlabel, hop-limit and
 	  the packet mark.
 
-config NFT_CHAIN_NAT_IPV6
-	depends on NF_TABLES_IPV6
-	depends on NF_NAT_IPV6 && NFT_NAT
-	tristate "IPv6 nf_tables nat chain support"
-	help
-	  This option enables the "nat" chain for IPv6 in nf_tables. This
-	  chain type is used to perform Network Address Translation (NAT)
-	  packet transformations such as the source, destination address and
-	  source and destination ports.
-
 config NFT_REJECT_IPV6
 	depends on NF_TABLES_IPV6
 	default NFT_REJECT
@@ -70,6 +60,19 @@ config NF_NAT_IPV6
 	  forms of full Network Address Port Translation. This can be
 	  controlled by iptables or nft.
 
+if NF_NAT_IPV6
+
+config NFT_CHAIN_NAT_IPV6
+	depends on NF_TABLES_IPV6
+	tristate "IPv6 nf_tables nat chain support"
+	help
+	  This option enables the "nat" chain for IPv6 in nf_tables. This
+	  chain type is used to perform Network Address Translation (NAT)
+	  packet transformations such as the source, destination address and
+	  source and destination ports.
+
+endif # NF_NAT_IPV6
+
 config IP6_NF_IPTABLES
 	tristate "IP6 tables support (required for filtering)"
 	depends on INET && IPV6
-- 
cgit v1.2.3


From 0bbe80e571c7b866afd92a98edd32a969467a7a9 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Thu, 11 Sep 2014 17:51:27 +0200
Subject: netfilter: masquerading needs to be independent of x_tables in
 Kconfig

Users are starting to test nf_tables with no x_tables support. Therefore,
masquerading needs to be indenpendent of it from Kconfig.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/Kconfig | 27 +++++++++++++++------------
 net/ipv6/netfilter/Kconfig | 27 +++++++++++++++------------
 2 files changed, 30 insertions(+), 24 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index eb6995fc4f67..345242a79db6 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -93,6 +93,21 @@ config NFT_CHAIN_NAT_IPV4
 	  packet transformations such as the source, destination address and
 	  source and destination ports.
 
+config NF_NAT_MASQUERADE_IPV4
+	tristate "IPv4 masquerade support"
+	help
+	  This is the kernel functionality to provide NAT in the masquerade
+	  flavour (automatic source address selection).
+
+config NFT_MASQ_IPV4
+	tristate "IPv4 masquerading support for nf_tables"
+	depends on NF_TABLES_IPV4
+	depends on NFT_MASQ
+	select NF_NAT_MASQUERADE_IPV4
+	help
+	  This is the expression that provides IPv4 masquerading support for
+	  nf_tables.
+
 config NF_NAT_SNMP_BASIC
 	tristate "Basic SNMP-ALG support"
 	depends on NF_CONNTRACK_SNMP
@@ -231,18 +246,6 @@ config IP_NF_NAT
 
 if IP_NF_NAT
 
-config NF_NAT_MASQUERADE_IPV4
-	tristate "IPv4 masquerade support"
-	help
-	This is the kernel functionality to provide NAT in the masquerade
-	flavour (automatic source address selection).
-
-config NFT_MASQ_IPV4
-	tristate "IPv4 masquerading support for nf_tables"
-	depends on NF_TABLES_IPV4
-	depends on NFT_MASQ
-	select NF_NAT_MASQUERADE_IPV4
-
 config IP_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
 	select NF_NAT_MASQUERADE_IPV4
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index e854062d0c36..bb1a40db7be1 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -71,6 +71,21 @@ config NFT_CHAIN_NAT_IPV6
 	  packet transformations such as the source, destination address and
 	  source and destination ports.
 
+config NF_NAT_MASQUERADE_IPV6
+	tristate "IPv6 masquerade support"
+	help
+	  This is the kernel functionality to provide NAT in the masquerade
+	  flavour (automatic source address selection) for IPv6.
+
+config NFT_MASQ_IPV6
+	tristate "IPv6 masquerade support for nf_tables"
+	depends on NF_TABLES_IPV6
+	depends on NFT_MASQ
+	select NF_NAT_MASQUERADE_IPV6
+	help
+	  This is the expression that provides IPv4 masquerading support for
+	  nf_tables.
+
 endif # NF_NAT_IPV6
 
 config IP6_NF_IPTABLES
@@ -261,18 +276,6 @@ config IP6_NF_NAT
 
 if IP6_NF_NAT
 
-config NF_NAT_MASQUERADE_IPV6
-	tristate "IPv6 masquerade support"
-	help
-	 This is the kernel functionality to provide NAT in the masquerade
-	 flavour (automatic source address selection) for IPv6.
-
-config NFT_MASQ_IPV6
-	tristate "IPv6 masquerade support for nf_tables"
-	depends on NF_TABLES_IPV6
-	depends on NFT_MASQ
-	select NF_NAT_MASQUERADE_IPV6
-
 config IP6_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
 	select NF_NAT_MASQUERADE_IPV6
-- 
cgit v1.2.3


From 2d8f7e2c8a63131828e8d4e2d98835399f27319e Mon Sep 17 00:00:00 2001
From: Scott Wood
Date: Wed, 10 Sep 2014 21:23:18 -0500
Subject: udp: Fix inverted NAPI_GRO_CB(skb)->flush test

Commit 2abb7cdc0d ("udp: Add support for doing checksum unnecessary
conversion") caused napi_gro_cb structs with the "flush" field zero to
take the "udp_gro_receive" path rather than the "set flush to 1" path
that they would previously take.  As a result I saw booting from an NFS
root hang shortly after starting userspace, with "server not
responding" messages.

This change to the handling of "flush == 0" packets appears to be
incidental to the goal of adding new code in the case where
skb_gro_checksum_validate_zero_check() returns zero.  Based on that and
the fact that it breaks things, I'm assuming that it is unintentional.

Fixes: 2abb7cdc0d ("udp: Add support for doing checksum unnecessary conversion")
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp_offload.c | 2 +-
 net/ipv6/udp_offload.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 52d5f46abf86..adab393b2fe5 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -294,7 +294,7 @@ static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
 		goto flush;
 
 	/* Don't bother verifying checksum if we're going to flush anyway. */
-	if (!NAPI_GRO_CB(skb)->flush)
+	if (NAPI_GRO_CB(skb)->flush)
 		goto skip;
 
 	if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index a1ad34b1c4ec..de85f809bf29 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -138,7 +138,7 @@ static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
 		goto flush;
 
 	/* Don't bother verifying checksum if we're going to flush anyway. */
-	if (!NAPI_GRO_CB(skb)->flush)
+	if (NAPI_GRO_CB(skb)->flush)
 		goto skip;
 
 	if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
-- 
cgit v1.2.3


From 6c555490e0ce885a9caf0a045db69382a3ccbc9c Mon Sep 17 00:00:00 2001
From: WANG Cong
Date: Thu, 11 Sep 2014 15:35:09 -0700
Subject: ipv6: drop useless rcu_read_lock() in anycast

These code is now protected by rtnl lock, rcu read lock
is useless now.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  4 ++--
 net/core/dev.c            | 14 ++++++++------
 net/ipv6/anycast.c        | 18 ++++++------------
 3 files changed, 16 insertions(+), 20 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ae721f53739e..ee38b948d9a0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2083,8 +2083,8 @@ void __dev_remove_pack(struct packet_type *pt);
 void dev_add_offload(struct packet_offload *po);
 void dev_remove_offload(struct packet_offload *po);
 
-struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags,
-					unsigned short mask);
+struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
+				      unsigned short mask);
 struct net_device *dev_get_by_name(struct net *net, const char *name);
 struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
 struct net_device *__dev_get_by_name(struct net *net, const char *name);
diff --git a/net/core/dev.c b/net/core/dev.c
index b3d6dbc0c696..e916ba8caccf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -897,23 +897,25 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
 EXPORT_SYMBOL(dev_getfirstbyhwtype);
 
 /**
- *	dev_get_by_flags_rcu - find any device with given flags
+ *	__dev_get_by_flags - find any device with given flags
  *	@net: the applicable net namespace
  *	@if_flags: IFF_* values
  *	@mask: bitmask of bits in if_flags to check
  *
  *	Search for any interface with the given flags. Returns NULL if a device
  *	is not found or a pointer to the device. Must be called inside
- *	rcu_read_lock(), and result refcount is unchanged.
+ *	rtnl_lock(), and result refcount is unchanged.
  */
 
-struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags,
-				    unsigned short mask)
+struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags,
+				      unsigned short mask)
 {
 	struct net_device *dev, *ret;
 
+	ASSERT_RTNL();
+
 	ret = NULL;
-	for_each_netdev_rcu(net, dev) {
+	for_each_netdev(net, dev) {
 		if (((dev->flags ^ if_flags) & mask) == 0) {
 			ret = dev;
 			break;
@@ -921,7 +923,7 @@ struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags
 	}
 	return ret;
 }
-EXPORT_SYMBOL(dev_get_by_flags_rcu);
+EXPORT_SYMBOL(__dev_get_by_flags);
 
 /**
  *	dev_valid_name - check if name is okay for network device
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index ff2de7d9d8e6..3b0429bc6b5a 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -78,7 +78,6 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	pac->acl_addr = *addr;
 
 	rtnl_lock();
-	rcu_read_lock();
 	if (ifindex == 0) {
 		struct rt6_info *rt;
 
@@ -91,11 +90,11 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			goto error;
 		} else {
 			/* router, no matching interface: just pick one */
-			dev = dev_get_by_flags_rcu(net, IFF_UP,
-						   IFF_UP | IFF_LOOPBACK);
+			dev = __dev_get_by_flags(net, IFF_UP,
+						 IFF_UP | IFF_LOOPBACK);
 		}
 	} else
-		dev = dev_get_by_index_rcu(net, ifindex);
+		dev = __dev_get_by_index(net, ifindex);
 
 	if (dev == NULL) {
 		err = -ENODEV;
@@ -137,7 +136,6 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	}
 
 error:
-	rcu_read_unlock();
 	rtnl_unlock();
 	if (pac)
 		sock_kfree_s(sk, pac, sizeof(*pac));
@@ -174,11 +172,9 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	spin_unlock_bh(&ipv6_sk_ac_lock);
 
 	rtnl_lock();
-	rcu_read_lock();
-	dev = dev_get_by_index_rcu(net, pac->acl_ifindex);
+	dev = __dev_get_by_index(net, pac->acl_ifindex);
 	if (dev)
 		ipv6_dev_ac_dec(dev, &pac->acl_addr);
-	rcu_read_unlock();
 	rtnl_unlock();
 
 	sock_kfree_s(sk, pac, sizeof(*pac));
@@ -203,12 +199,11 @@ void ipv6_sock_ac_close(struct sock *sk)
 
 	prev_index = 0;
 	rtnl_lock();
-	rcu_read_lock();
 	while (pac) {
 		struct ipv6_ac_socklist *next = pac->acl_next;
 
 		if (pac->acl_ifindex != prev_index) {
-			dev = dev_get_by_index_rcu(net, pac->acl_ifindex);
+			dev = __dev_get_by_index(net, pac->acl_ifindex);
 			prev_index = pac->acl_ifindex;
 		}
 		if (dev)
@@ -216,7 +211,6 @@ void ipv6_sock_ac_close(struct sock *sk)
 		sock_kfree_s(sk, pac, sizeof(*pac));
 		pac = next;
 	}
-	rcu_read_unlock();
 	rtnl_unlock();
 }
 
@@ -341,7 +335,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
 	return 0;
 }
 
-/* called with rcu_read_lock() */
+/* called with rtnl_lock() */
 static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr)
 {
 	struct inet6_dev *idev = __in6_dev_get(dev);
-- 
cgit v1.2.3


From b03a9c04a3a605815c232506e1d76281afe0946f Mon Sep 17 00:00:00 2001
From: WANG Cong
Date: Thu, 11 Sep 2014 15:35:10 -0700
Subject: ipv6: remove ipv6_sk_ac_lock

Just move rtnl lock up, so that the anycast list can be protected
by rtnl lock now.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/anycast.c | 17 +++--------------
 1 file changed, 3 insertions(+), 14 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 3b0429bc6b5a..d10f2e2b49c6 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -46,10 +46,6 @@
 
 static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr);
 
-/* Big ac list lock for all the sockets */
-static DEFINE_SPINLOCK(ipv6_sk_ac_lock);
-
-
 /*
  *	socket join an anycast group
  */
@@ -128,10 +124,8 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	err = ipv6_dev_ac_inc(dev, addr);
 	if (!err) {
-		spin_lock_bh(&ipv6_sk_ac_lock);
 		pac->acl_next = np->ipv6_ac_list;
 		np->ipv6_ac_list = pac;
-		spin_unlock_bh(&ipv6_sk_ac_lock);
 		pac = NULL;
 	}
 
@@ -152,7 +146,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	struct ipv6_ac_socklist *pac, *prev_pac;
 	struct net *net = sock_net(sk);
 
-	spin_lock_bh(&ipv6_sk_ac_lock);
+	rtnl_lock();
 	prev_pac = NULL;
 	for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) {
 		if ((ifindex == 0 || pac->acl_ifindex == ifindex) &&
@@ -161,7 +155,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		prev_pac = pac;
 	}
 	if (!pac) {
-		spin_unlock_bh(&ipv6_sk_ac_lock);
+		rtnl_unlock();
 		return -ENOENT;
 	}
 	if (prev_pac)
@@ -169,9 +163,6 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	else
 		np->ipv6_ac_list = pac->acl_next;
 
-	spin_unlock_bh(&ipv6_sk_ac_lock);
-
-	rtnl_lock();
 	dev = __dev_get_by_index(net, pac->acl_ifindex);
 	if (dev)
 		ipv6_dev_ac_dec(dev, &pac->acl_addr);
@@ -192,13 +183,11 @@ void ipv6_sock_ac_close(struct sock *sk)
 	if (!np->ipv6_ac_list)
 		return;
 
-	spin_lock_bh(&ipv6_sk_ac_lock);
+	rtnl_lock();
 	pac = np->ipv6_ac_list;
 	np->ipv6_ac_list = NULL;
-	spin_unlock_bh(&ipv6_sk_ac_lock);
 
 	prev_index = 0;
-	rtnl_lock();
 	while (pac) {
 		struct ipv6_ac_socklist *next = pac->acl_next;
 
-- 
cgit v1.2.3


From 013b4d90387a5dca54281263e0d4650db97bd67c Mon Sep 17 00:00:00 2001
From: WANG Cong
Date: Thu, 11 Sep 2014 15:35:11 -0700
Subject: ipv6: clean up ipv6_dev_ac_inc()

Make it accept inet6_dev, and rename it to __ipv6_dev_ac_inc()
to reflect this change.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h |  2 +-
 net/ipv6/addrconf.c    |  2 +-
 net/ipv6/anycast.c     | 13 ++++---------
 3 files changed, 6 insertions(+), 11 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index f679877bb601..9b1d42e66cca 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -202,7 +202,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
 void ipv6_sock_ac_close(struct sock *sk);
 
-int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr);
+int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr);
 int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr);
 bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
 			 const struct in6_addr *addr);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ad4598fcc416..6b6a373a30b2 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1725,7 +1725,7 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
 	if (ipv6_addr_any(&addr))
 		return;
-	ipv6_dev_ac_inc(ifp->idev->dev, &addr);
+	__ipv6_dev_ac_inc(ifp->idev, &addr);
 }
 
 /* caller must hold RTNL */
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index d10f2e2b49c6..66c19320119a 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -122,7 +122,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			goto error;
 	}
 
-	err = ipv6_dev_ac_inc(dev, addr);
+	err = __ipv6_dev_ac_inc(idev, addr);
 	if (!err) {
 		pac->acl_next = np->ipv6_ac_list;
 		np->ipv6_ac_list = pac;
@@ -215,20 +215,15 @@ static void aca_put(struct ifacaddr6 *ac)
 /*
  *	device anycast group inc (add if not found)
  */
-int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr)
+int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct ifacaddr6 *aca;
-	struct inet6_dev *idev;
 	struct rt6_info *rt;
 	int err;
 
 	ASSERT_RTNL();
 
-	idev = in6_dev_get(dev);
-
-	if (idev == NULL)
-		return -EINVAL;
-
+	in6_dev_hold(idev);
 	write_lock_bh(&idev->lock);
 	if (idev->dead) {
 		err = -ENODEV;
@@ -276,7 +271,7 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr)
 
 	ip6_ins_rt(rt);
 
-	addrconf_join_solict(dev, &aca->aca_addr);
+	addrconf_join_solict(idev->dev, &aca->aca_addr);
 
 	aca_put(aca);
 	return 0;
-- 
cgit v1.2.3


From 83aa29eefdb152d65e65a90605593766b4f793ef Mon Sep 17 00:00:00 2001
From: WANG Cong
Date: Thu, 11 Sep 2014 15:35:12 -0700
Subject: ipv6: refactor __ipv6_dev_ac_inc()

Refactor out allocation and initialization and make
the refcount code more readable.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/anycast.c | 62 ++++++++++++++++++++++++++++++++++--------------------
 1 file changed, 39 insertions(+), 23 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 66c19320119a..952c1fd06150 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -203,6 +203,11 @@ void ipv6_sock_ac_close(struct sock *sk)
 	rtnl_unlock();
 }
 
+static void aca_get(struct ifacaddr6 *aca)
+{
+	atomic_inc(&aca->aca_refcnt);
+}
+
 static void aca_put(struct ifacaddr6 *ac)
 {
 	if (atomic_dec_and_test(&ac->aca_refcnt)) {
@@ -212,6 +217,29 @@ static void aca_put(struct ifacaddr6 *ac)
 	}
 }
 
+static struct ifacaddr6 *aca_alloc(struct rt6_info *rt,
+				   const struct in6_addr *addr)
+{
+	struct inet6_dev *idev = rt->rt6i_idev;
+	struct ifacaddr6 *aca;
+
+	aca = kzalloc(sizeof(*aca), GFP_ATOMIC);
+	if (aca == NULL)
+		return NULL;
+
+	aca->aca_addr = *addr;
+	in6_dev_hold(idev);
+	aca->aca_idev = idev;
+	aca->aca_rt = rt;
+	aca->aca_users = 1;
+	/* aca_tstamp should be updated upon changes */
+	aca->aca_cstamp = aca->aca_tstamp = jiffies;
+	atomic_set(&aca->aca_refcnt, 1);
+	spin_lock_init(&aca->aca_lock);
+
+	return aca;
+}
+
 /*
  *	device anycast group inc (add if not found)
  */
@@ -223,7 +251,6 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
 
 	ASSERT_RTNL();
 
-	in6_dev_hold(idev);
 	write_lock_bh(&idev->lock);
 	if (idev->dead) {
 		err = -ENODEV;
@@ -238,35 +265,25 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
 		}
 	}
 
-	/*
-	 *	not found: create a new one.
-	 */
-
-	aca = kzalloc(sizeof(struct ifacaddr6), GFP_ATOMIC);
-
-	if (aca == NULL) {
-		err = -ENOMEM;
-		goto out;
-	}
-
 	rt = addrconf_dst_alloc(idev, addr, true);
 	if (IS_ERR(rt)) {
-		kfree(aca);
 		err = PTR_ERR(rt);
 		goto out;
 	}
-
-	aca->aca_addr = *addr;
-	aca->aca_idev = idev;
-	aca->aca_rt = rt;
-	aca->aca_users = 1;
-	/* aca_tstamp should be updated upon changes */
-	aca->aca_cstamp = aca->aca_tstamp = jiffies;
-	atomic_set(&aca->aca_refcnt, 2);
-	spin_lock_init(&aca->aca_lock);
+	aca = aca_alloc(rt, addr);
+	if (aca == NULL) {
+		ip6_rt_put(rt);
+		err = -ENOMEM;
+		goto out;
+	}
 
 	aca->aca_next = idev->ac_list;
 	idev->ac_list = aca;
+
+	/* Hold this for addrconf_join_solict() below before we unlock,
+	 * it is already exposed via idev->ac_list.
+	 */
+	aca_get(aca);
 	write_unlock_bh(&idev->lock);
 
 	ip6_ins_rt(rt);
@@ -277,7 +294,6 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
 	return 0;
 out:
 	write_unlock_bh(&idev->lock);
-	in6_dev_put(idev);
 	return err;
 }
 
-- 
cgit v1.2.3


From b5350916bfd49f737d73c4c512fbea1b3537c703 Mon Sep 17 00:00:00 2001
From: WANG Cong
Date: Thu, 11 Sep 2014 15:35:13 -0700
Subject: ipv6: drop ipv6_sk_mc_lock in mcast

Similarly the code is already protected by rtnl lock.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 484a94215d88..27ca0b741ccc 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -73,9 +73,6 @@ static void *__mld2_query_bugs[] __attribute__((__unused__)) = {
 
 static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT;
 
-/* Big mc list lock for all the sockets */
-static DEFINE_SPINLOCK(ipv6_sk_mc_lock);
-
 static void igmp6_join_group(struct ifmcaddr6 *ma);
 static void igmp6_leave_group(struct ifmcaddr6 *ma);
 static void igmp6_timer_handler(unsigned long data);
@@ -201,10 +198,8 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		return err;
 	}
 
-	spin_lock(&ipv6_sk_mc_lock);
 	mc_lst->next = np->ipv6_mc_list;
 	rcu_assign_pointer(np->ipv6_mc_list, mc_lst);
-	spin_unlock(&ipv6_sk_mc_lock);
 
 	rcu_read_unlock();
 	rtnl_unlock();
@@ -226,17 +221,14 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		return -EINVAL;
 
 	rtnl_lock();
-	spin_lock(&ipv6_sk_mc_lock);
 	for (lnk = &np->ipv6_mc_list;
-	     (mc_lst = rcu_dereference_protected(*lnk,
-			lockdep_is_held(&ipv6_sk_mc_lock))) != NULL;
+	     (mc_lst = rtnl_dereference(*lnk)) != NULL;
 	      lnk = &mc_lst->next) {
 		if ((ifindex == 0 || mc_lst->ifindex == ifindex) &&
 		    ipv6_addr_equal(&mc_lst->addr, addr)) {
 			struct net_device *dev;
 
 			*lnk = mc_lst->next;
-			spin_unlock(&ipv6_sk_mc_lock);
 
 			rcu_read_lock();
 			dev = dev_get_by_index_rcu(net, mc_lst->ifindex);
@@ -256,7 +248,6 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			return 0;
 		}
 	}
-	spin_unlock(&ipv6_sk_mc_lock);
 	rtnl_unlock();
 
 	return -EADDRNOTAVAIL;
@@ -303,13 +294,10 @@ void ipv6_sock_mc_close(struct sock *sk)
 		return;
 
 	rtnl_lock();
-	spin_lock(&ipv6_sk_mc_lock);
-	while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list,
-				lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) {
+	while ((mc_lst = rtnl_dereference(np->ipv6_mc_list)) != NULL) {
 		struct net_device *dev;
 
 		np->ipv6_mc_list = mc_lst->next;
-		spin_unlock(&ipv6_sk_mc_lock);
 
 		rcu_read_lock();
 		dev = dev_get_by_index_rcu(net, mc_lst->ifindex);
@@ -326,9 +314,7 @@ void ipv6_sock_mc_close(struct sock *sk)
 		atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc);
 		kfree_rcu(mc_lst, rcu);
 
-		spin_lock(&ipv6_sk_mc_lock);
 	}
-	spin_unlock(&ipv6_sk_mc_lock);
 	rtnl_unlock();
 }
 
-- 
cgit v1.2.3


From 414b6c943fe25c5c576b6f0ce9077c29a150d826 Mon Sep 17 00:00:00 2001
From: WANG Cong
Date: Thu, 11 Sep 2014 15:35:14 -0700
Subject: ipv6: drop some rcu_read_lock in mcast

Similarly the code is already protected by rtnl lock.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 27ca0b741ccc..4fb761d4002d 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -162,7 +162,6 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	mc_lst->addr = *addr;
 
 	rtnl_lock();
-	rcu_read_lock();
 	if (ifindex == 0) {
 		struct rt6_info *rt;
 		rt = rt6_lookup(net, addr, NULL, 0, 0);
@@ -171,10 +170,9 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			ip6_rt_put(rt);
 		}
 	} else
-		dev = dev_get_by_index_rcu(net, ifindex);
+		dev = __dev_get_by_index(net, ifindex);
 
 	if (dev == NULL) {
-		rcu_read_unlock();
 		rtnl_unlock();
 		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
 		return -ENODEV;
@@ -192,7 +190,6 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	err = ipv6_dev_mc_inc(dev, addr);
 
 	if (err) {
-		rcu_read_unlock();
 		rtnl_unlock();
 		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
 		return err;
@@ -201,7 +198,6 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	mc_lst->next = np->ipv6_mc_list;
 	rcu_assign_pointer(np->ipv6_mc_list, mc_lst);
 
-	rcu_read_unlock();
 	rtnl_unlock();
 
 	return 0;
@@ -230,8 +226,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 			*lnk = mc_lst->next;
 
-			rcu_read_lock();
-			dev = dev_get_by_index_rcu(net, mc_lst->ifindex);
+			dev = __dev_get_by_index(net, mc_lst->ifindex);
 			if (dev != NULL) {
 				struct inet6_dev *idev = __in6_dev_get(dev);
 
@@ -240,7 +235,6 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 					__ipv6_dev_mc_dec(idev, &mc_lst->addr);
 			} else
 				(void) ip6_mc_leave_src(sk, mc_lst, NULL);
-			rcu_read_unlock();
 			rtnl_unlock();
 
 			atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc);
@@ -299,8 +293,7 @@ void ipv6_sock_mc_close(struct sock *sk)
 
 		np->ipv6_mc_list = mc_lst->next;
 
-		rcu_read_lock();
-		dev = dev_get_by_index_rcu(net, mc_lst->ifindex);
+		dev = __dev_get_by_index(net, mc_lst->ifindex);
 		if (dev) {
 			struct inet6_dev *idev = __in6_dev_get(dev);
 
@@ -309,7 +302,6 @@ void ipv6_sock_mc_close(struct sock *sk)
 				__ipv6_dev_mc_dec(idev, &mc_lst->addr);
 		} else
 			(void) ip6_mc_leave_src(sk, mc_lst, NULL);
-		rcu_read_unlock();
 
 		atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc);
 		kfree_rcu(mc_lst, rcu);
@@ -934,7 +926,7 @@ int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr)
 	struct inet6_dev *idev;
 	int err;
 
-	rcu_read_lock();
+	ASSERT_RTNL();
 
 	idev = __in6_dev_get(dev);
 	if (!idev)
@@ -942,7 +934,6 @@ int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr)
 	else
 		err = __ipv6_dev_mc_dec(idev, addr);
 
-	rcu_read_unlock();
 	return err;
 }
 
-- 
cgit v1.2.3


From f7ed925c1b4d62e82b72d8e99fa4be52fb0c73b6 Mon Sep 17 00:00:00 2001
From: WANG Cong
Date: Thu, 11 Sep 2014 15:35:15 -0700
Subject: ipv6: update the comment in mcast.c

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 4fb761d4002d..d64e26366cb8 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -556,9 +556,8 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 	}
 
 	err = -EADDRNOTAVAIL;
-	/*
-	 * changes to the ipv6_mc_list require the socket lock and
-	 * a read lock on ip6_sk_mc_lock. We have the socket lock,
+	/* changes to the ipv6_mc_list require the socket lock and
+	 * rtnl lock. We have the socket lock and rcu read lock,
 	 * so reading the list is safe.
 	 */
 
@@ -582,9 +581,8 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 	    copy_to_user(optval, gsf, GROUP_FILTER_SIZE(0))) {
 		return -EFAULT;
 	}
-	/* changes to psl require the socket lock, a read lock on
-	 * on ipv6_sk_mc_lock and a write lock on pmc->sflock. We
-	 * have the socket lock, so reading here is safe.
+	/* changes to psl require the socket lock, and a write lock
+	 * on pmc->sflock. We have the socket lock so reading here is safe.
 	 */
 	for (i = 0; i < copycount; i++) {
 		struct sockaddr_in6 *psin6;
@@ -2350,7 +2348,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 {
 	int err;
 
-	/* callers have the socket lock and a write lock on ipv6_sk_mc_lock,
+	/* callers have the socket lock and rtnl lock
 	 * so no other readers or writers of iml or its sflist
 	 */
 	if (!iml->sflist) {
-- 
cgit v1.2.3


From 1691c63ea42d6f57ba769df401b9773664edb936 Mon Sep 17 00:00:00 2001
From: WANG Cong
Date: Thu, 11 Sep 2014 15:35:16 -0700
Subject: ipv6: refactor ipv6_dev_mc_inc()

Refactor out allocation and initialization and make
the refcount code more readable.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 82 +++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 49 insertions(+), 33 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index d64e26366cb8..592eba61e78a 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -641,14 +641,6 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
 	return rv;
 }
 
-static void ma_put(struct ifmcaddr6 *mc)
-{
-	if (atomic_dec_and_test(&mc->mca_refcnt)) {
-		in6_dev_put(mc->idev);
-		kfree(mc);
-	}
-}
-
 static void igmp6_group_added(struct ifmcaddr6 *mc)
 {
 	struct net_device *dev = mc->idev->dev;
@@ -814,6 +806,48 @@ static void mld_clear_delrec(struct inet6_dev *idev)
 	read_unlock_bh(&idev->lock);
 }
 
+static void mca_get(struct ifmcaddr6 *mc)
+{
+	atomic_inc(&mc->mca_refcnt);
+}
+
+static void ma_put(struct ifmcaddr6 *mc)
+{
+	if (atomic_dec_and_test(&mc->mca_refcnt)) {
+		in6_dev_put(mc->idev);
+		kfree(mc);
+	}
+}
+
+static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
+				   const struct in6_addr *addr)
+{
+	struct ifmcaddr6 *mc;
+
+	mc = kzalloc(sizeof(*mc), GFP_ATOMIC);
+	if (mc == NULL)
+		return NULL;
+
+	setup_timer(&mc->mca_timer, igmp6_timer_handler, (unsigned long)mc);
+
+	mc->mca_addr = *addr;
+	mc->idev = idev; /* reference taken by caller */
+	mc->mca_users = 1;
+	/* mca_stamp should be updated upon changes */
+	mc->mca_cstamp = mc->mca_tstamp = jiffies;
+	atomic_set(&mc->mca_refcnt, 1);
+	spin_lock_init(&mc->mca_lock);
+
+	/* initial mode is (EX, empty) */
+	mc->mca_sfmode = MCAST_EXCLUDE;
+	mc->mca_sfcount[MCAST_EXCLUDE] = 1;
+
+	if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) ||
+	    IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL)
+		mc->mca_flags |= MAF_NOREPORT;
+
+	return mc;
+}
 
 /*
  *	device multicast group inc (add if not found)
@@ -849,38 +883,20 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 		}
 	}
 
-	/*
-	 *	not found: create a new one.
-	 */
-
-	mc = kzalloc(sizeof(struct ifmcaddr6), GFP_ATOMIC);
-
-	if (mc == NULL) {
+	mc = mca_alloc(idev, addr);
+	if (!mc) {
 		write_unlock_bh(&idev->lock);
 		in6_dev_put(idev);
 		return -ENOMEM;
 	}
 
-	setup_timer(&mc->mca_timer, igmp6_timer_handler, (unsigned long)mc);
-
-	mc->mca_addr = *addr;
-	mc->idev = idev; /* (reference taken) */
-	mc->mca_users = 1;
-	/* mca_stamp should be updated upon changes */
-	mc->mca_cstamp = mc->mca_tstamp = jiffies;
-	atomic_set(&mc->mca_refcnt, 2);
-	spin_lock_init(&mc->mca_lock);
-
-	/* initial mode is (EX, empty) */
-	mc->mca_sfmode = MCAST_EXCLUDE;
-	mc->mca_sfcount[MCAST_EXCLUDE] = 1;
-
-	if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) ||
-	    IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL)
-		mc->mca_flags |= MAF_NOREPORT;
-
 	mc->next = idev->mc_list;
 	idev->mc_list = mc;
+
+	/* Hold this for the code below before we unlock,
+	 * it is already exposed via idev->mc_list.
+	 */
+	mca_get(mc);
 	write_unlock_bh(&idev->lock);
 
 	mld_del_delrec(idev, &mc->mca_addr);
-- 
cgit v1.2.3


From 3ce62a84d53cd3d3cc5377bbf339e9b08ddf9c36 Mon Sep 17 00:00:00 2001
From: WANG Cong
Date: Thu, 11 Sep 2014 15:07:16 -0700
Subject: ipv6: exit early in addrconf_notify() if IPv6 is disabled

If IPv6 is explicitly disabled before the interface comes up,
it makes no sense to continue when it comes up, even just
print a message.

(I am not sure about other cases though, so I prefer not to touch)

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'net/ipv6')

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6b6a373a30b2..39d33355d7e8 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2844,6 +2844,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 		if (dev->flags & IFF_SLAVE)
 			break;
 
+		if (idev && idev->cnf.disable_ipv6)
+			break;
+
 		if (event == NETDEV_UP) {
 			if (!addrconf_qdisc_ok(dev)) {
 				/* device is not ready yet. */
-- 
cgit v1.2.3


From e11ecddf5128011c936cc5360780190cbc901fdc Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Mon, 15 Sep 2014 04:19:51 -0700
Subject: tcp: use TCP_SKB_CB(skb)->tcp_flags in input path

Input path of TCP do not currently uses TCP_SKB_CB(skb)->tcp_flags,
which is only used in output path.

tcp_recvmsg(), looks at tcp_hdr(skb)->syn for every skb found in receive queue,
and its unfortunate because this bit is located in a cache line right before
the payload.

We can simplify TCP by copying tcp flags into TCP_SKB_CB(skb)->tcp_flags.

This patch does so, and avoids the cache line miss in tcp_recvmsg()

Following patches will
- allow a segment with FIN being coalesced in tcp_try_coalesce()
- simplify tcp_collapse() by not copying the headers.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c       | 18 ++++++++++--------
 net/ipv4/tcp_input.c | 10 +++++-----
 net/ipv4/tcp_ipv4.c  |  1 +
 net/ipv6/tcp_ipv6.c  |  1 +
 4 files changed, 17 insertions(+), 13 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 541f26a67ba2..070aeff1b131 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1510,9 +1510,9 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 
 	while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
 		offset = seq - TCP_SKB_CB(skb)->seq;
-		if (tcp_hdr(skb)->syn)
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 			offset--;
-		if (offset < skb->len || tcp_hdr(skb)->fin) {
+		if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) {
 			*off = offset;
 			return skb;
 		}
@@ -1585,7 +1585,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 			if (offset + 1 != skb->len)
 				continue;
 		}
-		if (tcp_hdr(skb)->fin) {
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
 			sk_eat_skb(sk, skb, false);
 			++seq;
 			break;
@@ -1722,11 +1722,11 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 				break;
 
 			offset = *seq - TCP_SKB_CB(skb)->seq;
-			if (tcp_hdr(skb)->syn)
+			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 				offset--;
 			if (offset < skb->len)
 				goto found_ok_skb;
-			if (tcp_hdr(skb)->fin)
+			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 				goto found_fin_ok;
 			WARN(!(flags & MSG_PEEK),
 			     "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
@@ -1959,7 +1959,7 @@ skip_copy:
 		if (used + offset < skb->len)
 			continue;
 
-		if (tcp_hdr(skb)->fin)
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
 		if (!(flags & MSG_PEEK)) {
 			sk_eat_skb(sk, skb, copied_early);
@@ -2160,8 +2160,10 @@ void tcp_close(struct sock *sk, long timeout)
 	 *  reader process may not have drained the data yet!
 	 */
 	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
-		u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq -
-			  tcp_hdr(skb)->fin;
+		u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq;
+
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+			len--;
 		data_was_unread += len;
 		__kfree_skb(skb);
 	}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f97003ad0af5..8f639a4face9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4093,7 +4093,7 @@ static void tcp_ofo_queue(struct sock *sk)
 		__skb_unlink(skb, &tp->out_of_order_queue);
 		__skb_queue_tail(&sk->sk_receive_queue, skb);
 		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-		if (tcp_hdr(skb)->fin)
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			tcp_fin(sk);
 	}
 }
@@ -4513,7 +4513,7 @@ restart:
 		 * - bloated or contains data before "start" or
 		 *   overlaps to the next one.
 		 */
-		if (!tcp_hdr(skb)->syn && !tcp_hdr(skb)->fin &&
+		if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
 		    (tcp_win_from_space(skb->truesize) > skb->len ||
 		     before(TCP_SKB_CB(skb)->seq, start))) {
 			end_of_skbs = false;
@@ -4532,7 +4532,8 @@ restart:
 		/* Decided to skip this, advance start seq. */
 		start = TCP_SKB_CB(skb)->end_seq;
 	}
-	if (end_of_skbs || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin)
+	if (end_of_skbs ||
+	    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
 		return;
 
 	while (before(start, end)) {
@@ -4579,8 +4580,7 @@ restart:
 				skb = tcp_collapse_one(sk, skb, list);
 				if (!skb ||
 				    skb == tail ||
-				    tcp_hdr(skb)->syn ||
-				    tcp_hdr(skb)->fin)
+				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
 					return;
 			}
 		}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7881b96d2b72..006b045716d8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1638,6 +1638,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff * 4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
 	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
 	TCP_SKB_CB(skb)->sacked	 = 0;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 1835480336ac..de51a88bec6f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1415,6 +1415,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff*4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
 	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
 	TCP_SKB_CB(skb)->sacked = 0;
-- 
cgit v1.2.3


From 689f1c9de2abbd76fda224d12cea5f43568a4335 Mon Sep 17 00:00:00 2001
From: Herbert Xu
Date: Thu, 18 Sep 2014 16:38:18 +0800
Subject: ipsec: Remove obsolete MAX_AH_AUTH_LEN

While tracking down the MAX_AH_AUTH_LEN crash in an old kernel
I thought that this limit was rather arbitrary and we should
just get rid of it.

In fact it seems that we've already done all the work needed
to remove it apart from actually removing it.  This limit was
there in order to limit stack usage.  Since we've already
switched over to allocating scratch space using kmalloc, there
is no longer any need to limit the authentication length.

This patch kills all references to it, including the BUG_ONs
that led me here.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/ah.h     | 3 ---
 net/ipv4/ah4.c       | 2 --
 net/ipv6/ah6.c       | 2 --
 net/xfrm/xfrm_user.c | 3 +--
 4 files changed, 1 insertion(+), 9 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/ah.h b/include/net/ah.h
index ca95b98969dd..4e2dfa474a7e 100644
--- a/include/net/ah.h
+++ b/include/net/ah.h
@@ -3,9 +3,6 @@
 
 #include <linux/skbuff.h>
 
-/* This is the maximum truncated ICV length that we know of. */
-#define MAX_AH_AUTH_LEN	64
-
 struct crypto_ahash;
 
 struct ah_data {
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index a2afa89513a0..ac9a32ec3ee4 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -505,8 +505,6 @@ static int ah_init_state(struct xfrm_state *x)
 	ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8;
 	ahp->icv_trunc_len = x->aalg->alg_trunc_len/8;
 
-	BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN);
-
 	if (x->props.flags & XFRM_STATE_ALIGN4)
 		x->props.header_len = XFRM_ALIGN4(sizeof(struct ip_auth_hdr) +
 						  ahp->icv_trunc_len);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index fcffd4e522c8..6d16eb0e0c7f 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -713,8 +713,6 @@ static int ah6_init_state(struct xfrm_state *x)
 	ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8;
 	ahp->icv_trunc_len = x->aalg->alg_trunc_len/8;
 
-	BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN);
-
 	x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) +
 					  ahp->icv_trunc_len);
 	switch (x->props.mode) {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index eaf8a8f1cbe8..e812e988c111 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -333,8 +333,7 @@ static int attach_auth_trunc(struct xfrm_algo_auth **algpp, u8 *props,
 	algo = xfrm_aalg_get_byname(ualg->alg_name, 1);
 	if (!algo)
 		return -ENOSYS;
-	if ((ualg->alg_trunc_len / 8) > MAX_AH_AUTH_LEN ||
-	    ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits)
+	if (ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits)
 		return -EINVAL;
 	*props = algo->desc.sadb_alg_id;
 
-- 
cgit v1.2.3


From fd384412e199b62c3ddaabd18dce86d0e164c5b9 Mon Sep 17 00:00:00 2001
From: Andy Zhou
Date: Tue, 16 Sep 2014 17:31:16 -0700
Subject: udp_tunnel: Seperate ipv6 functions into its own file.

Add ip6_udp_tunnel.c for ipv6 UDP tunnel functions to avoid ifdefs
in udp_tunnel.c

Signed-off-by: Andy Zhou <azhou@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp_tunnel.h  | 28 ++++++++++++++--
 net/ipv4/udp_tunnel.c     | 85 ++++++++++++-----------------------------------
 net/ipv6/Makefile         |  1 +
 net/ipv6/ip6_udp_tunnel.c | 63 +++++++++++++++++++++++++++++++++++
 4 files changed, 111 insertions(+), 66 deletions(-)
 create mode 100644 net/ipv6/ip6_udp_tunnel.c

(limited to 'net/ipv6')

diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index ffd69cbded35..0b9e017c9038 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -26,7 +26,31 @@ struct udp_port_cfg {
 				use_udp6_rx_checksums:1;
 };
 
-int udp_sock_create(struct net *net, struct udp_port_cfg *cfg,
-		    struct socket **sockp);
+int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
+		     struct socket **sockp);
+
+#if IS_ENABLED(CONFIG_IPV6)
+int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
+		     struct socket **sockp);
+#else
+static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
+				   struct socket **sockp)
+{
+	return 0;
+}
+#endif
+
+static inline int udp_sock_create(struct net *net,
+				  struct udp_port_cfg *cfg,
+				  struct socket **sockp)
+{
+	if (cfg->family == AF_INET)
+		return udp_sock_create4(net, cfg, sockp);
+
+	if (cfg->family == AF_INET6)
+		return udp_sock_create6(net, cfg, sockp);
+
+	return -EPFNOSUPPORT;
+}
 
 #endif
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 61ec1a65207e..7fccf6c3417a 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -8,83 +8,40 @@
 #include <net/udp_tunnel.h>
 #include <net/net_namespace.h>
 
-int udp_sock_create(struct net *net, struct udp_port_cfg *cfg,
-		    struct socket **sockp)
+int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
+		     struct socket **sockp)
 {
 	int err = -EINVAL;
 	struct socket *sock = NULL;
+	struct sockaddr_in udp_addr;
 
-#if IS_ENABLED(CONFIG_IPV6)
-	if (cfg->family == AF_INET6) {
-		struct sockaddr_in6 udp6_addr;
+	err = sock_create_kern(AF_INET, SOCK_DGRAM, 0, &sock);
+	if (err < 0)
+		goto error;
 
-		err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock);
-		if (err < 0)
-			goto error;
-
-		sk_change_net(sock->sk, net);
-
-		udp6_addr.sin6_family = AF_INET6;
-		memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6,
-		       sizeof(udp6_addr.sin6_addr));
-		udp6_addr.sin6_port = cfg->local_udp_port;
-		err = kernel_bind(sock, (struct sockaddr *)&udp6_addr,
-				  sizeof(udp6_addr));
-		if (err < 0)
-			goto error;
-
-		if (cfg->peer_udp_port) {
-			udp6_addr.sin6_family = AF_INET6;
-			memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6,
-			       sizeof(udp6_addr.sin6_addr));
-			udp6_addr.sin6_port = cfg->peer_udp_port;
-			err = kernel_connect(sock,
-					     (struct sockaddr *)&udp6_addr,
-					     sizeof(udp6_addr), 0);
-		}
-		if (err < 0)
-			goto error;
-
-		udp_set_no_check6_tx(sock->sk, !cfg->use_udp6_tx_checksums);
-		udp_set_no_check6_rx(sock->sk, !cfg->use_udp6_rx_checksums);
-	} else
-#endif
-	if (cfg->family == AF_INET) {
-		struct sockaddr_in udp_addr;
-
-		err = sock_create_kern(AF_INET, SOCK_DGRAM, 0, &sock);
-		if (err < 0)
-			goto error;
+	sk_change_net(sock->sk, net);
 
-		sk_change_net(sock->sk, net);
+	udp_addr.sin_family = AF_INET;
+	udp_addr.sin_addr = cfg->local_ip;
+	udp_addr.sin_port = cfg->local_udp_port;
+	err = kernel_bind(sock, (struct sockaddr *)&udp_addr,
+			  sizeof(udp_addr));
+	if (err < 0)
+		goto error;
 
+	if (cfg->peer_udp_port) {
 		udp_addr.sin_family = AF_INET;
-		udp_addr.sin_addr = cfg->local_ip;
-		udp_addr.sin_port = cfg->local_udp_port;
-		err = kernel_bind(sock, (struct sockaddr *)&udp_addr,
-				  sizeof(udp_addr));
+		udp_addr.sin_addr = cfg->peer_ip;
+		udp_addr.sin_port = cfg->peer_udp_port;
+		err = kernel_connect(sock, (struct sockaddr *)&udp_addr,
+				     sizeof(udp_addr), 0);
 		if (err < 0)
 			goto error;
-
-		if (cfg->peer_udp_port) {
-			udp_addr.sin_family = AF_INET;
-			udp_addr.sin_addr = cfg->peer_ip;
-			udp_addr.sin_port = cfg->peer_udp_port;
-			err = kernel_connect(sock,
-					     (struct sockaddr *)&udp_addr,
-					     sizeof(udp_addr), 0);
-			if (err < 0)
-				goto error;
-		}
-
-		sock->sk->sk_no_check_tx = !cfg->use_udp_checksums;
-	} else {
-		return -EPFNOSUPPORT;
 	}
 
+	sock->sk->sk_no_check_tx = !cfg->use_udp_checksums;
 
 	*sockp = sock;
-
 	return 0;
 
 error:
@@ -95,6 +52,6 @@ error:
 	*sockp = NULL;
 	return err;
 }
-EXPORT_SYMBOL(udp_sock_create);
+EXPORT_SYMBOL(udp_sock_create4);
 
 MODULE_LICENSE("GPL");
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 2fe68364bb20..45f830e5f820 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -35,6 +35,7 @@ obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o
 obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o
 obj-$(CONFIG_IPV6_MIP6) += mip6.o
 obj-$(CONFIG_NETFILTER)	+= netfilter/
+obj-$(CONFIG_NET_UDP_TUNNEL) += ip6_udp_tunnel.o
 
 obj-$(CONFIG_IPV6_VTI) += ip6_vti.o
 obj-$(CONFIG_IPV6_SIT) += sit.o
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
new file mode 100644
index 000000000000..bcfbb4b496fc
--- /dev/null
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -0,0 +1,63 @@
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/socket.h>
+#include <linux/udp.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/in6.h>
+#include <net/udp.h>
+#include <net/udp_tunnel.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/ip6_tunnel.h>
+#include <net/ip6_checksum.h>
+
+int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
+		     struct socket **sockp)
+{
+	struct sockaddr_in6 udp6_addr;
+	int err;
+	struct socket *sock = NULL;
+
+	err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock);
+	if (err < 0)
+		goto error;
+
+	sk_change_net(sock->sk, net);
+
+	udp6_addr.sin6_family = AF_INET6;
+	memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6,
+	       sizeof(udp6_addr.sin6_addr));
+	udp6_addr.sin6_port = cfg->local_udp_port;
+	err = kernel_bind(sock, (struct sockaddr *)&udp6_addr,
+			  sizeof(udp6_addr));
+	if (err < 0)
+		goto error;
+
+	if (cfg->peer_udp_port) {
+		udp6_addr.sin6_family = AF_INET6;
+		memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6,
+		       sizeof(udp6_addr.sin6_addr));
+		udp6_addr.sin6_port = cfg->peer_udp_port;
+		err = kernel_connect(sock,
+				     (struct sockaddr *)&udp6_addr,
+				     sizeof(udp6_addr), 0);
+	}
+	if (err < 0)
+		goto error;
+
+	udp_set_no_check6_tx(sock->sk, !cfg->use_udp6_tx_checksums);
+	udp_set_no_check6_rx(sock->sk, !cfg->use_udp6_rx_checksums);
+
+	*sockp = sock;
+	return 0;
+
+error:
+	if (sock) {
+		kernel_sock_shutdown(sock, SHUT_RDWR);
+		sk_release_kernel(sock->sk);
+	}
+	*sockp = NULL;
+	return err;
+}
+EXPORT_SYMBOL_GPL(udp_sock_create6);
-- 
cgit v1.2.3


From 6a93cc9052748c6355ec9d5b6c38b77f85f1cb0d Mon Sep 17 00:00:00 2001
From: Andy Zhou
Date: Tue, 16 Sep 2014 17:31:17 -0700
Subject: udp-tunnel: Add a few more UDP tunnel APIs

Added a few more UDP tunnel APIs that can be shared by UDP based
tunnel protocol implementation. The main ones are highlighted below.

setup_udp_tunnel_sock() configures UDP listener socket for
receiving UDP encapsulated packets.

udp_tunnel_xmit_skb() and upd_tunnel6_xmit_skb() transmit skb
using UDP encapsulation.

udp_tunnel_sock_release() closes the UDP tunnel listener socket.

Signed-off-by: Andy Zhou <azhou@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp_tunnel.h  | 57 +++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/udp_tunnel.c     | 53 ++++++++++++++++++++++++++++++++++++++++++-
 net/ipv6/ip6_udp_tunnel.c | 42 ++++++++++++++++++++++++++++++++++
 3 files changed, 151 insertions(+), 1 deletion(-)

(limited to 'net/ipv6')

diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 0b9e017c9038..a47790bcaa38 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -1,6 +1,14 @@
 #ifndef __NET_UDP_TUNNEL_H
 #define __NET_UDP_TUNNEL_H
 
+#include <net/ip_tunnels.h>
+#include <net/udp.h>
+
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ipv6.h>
+#include <net/addrconf.h>
+#endif
+
 struct udp_port_cfg {
 	u8			family;
 
@@ -53,4 +61,53 @@ static inline int udp_sock_create(struct net *net,
 	return -EPFNOSUPPORT;
 }
 
+typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
+typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
+
+struct udp_tunnel_sock_cfg {
+	void *sk_user_data;     /* user data used by encap_rcv call back */
+	/* Used for setting up udp_sock fields, see udp.h for details */
+	__u8  encap_type;
+	udp_tunnel_encap_rcv_t encap_rcv;
+	udp_tunnel_encap_destroy_t encap_destroy;
+};
+
+/* Setup the given (UDP) sock to receive UDP encapsulated packets */
+void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
+			   struct udp_tunnel_sock_cfg *sock_cfg);
+
+/* Transmit the skb using UDP encapsulation. */
+int udp_tunnel_xmit_skb(struct socket *sock, struct rtable *rt,
+			struct sk_buff *skb, __be32 src, __be32 dst,
+			__u8 tos, __u8 ttl, __be16 df, __be16 src_port,
+			__be16 dst_port, bool xnet);
+
+#if IS_ENABLED(CONFIG_IPV6)
+int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
+			 struct sk_buff *skb, struct net_device *dev,
+			 struct in6_addr *saddr, struct in6_addr *daddr,
+			 __u8 prio, __u8 ttl, __be16 src_port,
+			 __be16 dst_port);
+#endif
+
+void udp_tunnel_sock_release(struct socket *sock);
+
+static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb,
+							 bool udp_csum)
+{
+	int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+
+	return iptunnel_handle_offloads(skb, udp_csum, type);
+}
+
+static inline void udp_tunnel_encap_enable(struct socket *sock)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sock->sk->sk_family == PF_INET6)
+		ipv6_stub->udpv6_encap_enable();
+	else
+#endif
+		udp_encap_enable();
+}
+
 #endif
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 7fccf6c3417a..1671263e5fa0 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -11,7 +11,7 @@
 int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
 		     struct socket **sockp)
 {
-	int err = -EINVAL;
+	int err;
 	struct socket *sock = NULL;
 	struct sockaddr_in udp_addr;
 
@@ -54,4 +54,55 @@ error:
 }
 EXPORT_SYMBOL(udp_sock_create4);
 
+void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
+			   struct udp_tunnel_sock_cfg *cfg)
+{
+	struct sock *sk = sock->sk;
+
+	/* Disable multicast loopback */
+	inet_sk(sk)->mc_loop = 0;
+
+	/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
+	udp_set_convert_csum(sk, true);
+
+	rcu_assign_sk_user_data(sk, cfg->sk_user_data);
+
+	udp_sk(sk)->encap_type = cfg->encap_type;
+	udp_sk(sk)->encap_rcv = cfg->encap_rcv;
+	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
+
+	udp_tunnel_encap_enable(sock);
+}
+EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
+
+int udp_tunnel_xmit_skb(struct socket *sock, struct rtable *rt,
+			struct sk_buff *skb, __be32 src, __be32 dst,
+			__u8 tos, __u8 ttl, __be16 df, __be16 src_port,
+			__be16 dst_port, bool xnet)
+{
+	struct udphdr *uh;
+
+	__skb_push(skb, sizeof(*uh));
+	skb_reset_transport_header(skb);
+	uh = udp_hdr(skb);
+
+	uh->dest = dst_port;
+	uh->source = src_port;
+	uh->len = htons(skb->len);
+
+	udp_set_csum(sock->sk->sk_no_check_tx, skb, src, dst, skb->len);
+
+	return iptunnel_xmit(sock->sk, rt, skb, src, dst, IPPROTO_UDP,
+			     tos, ttl, df, xnet);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
+
+void udp_tunnel_sock_release(struct socket *sock)
+{
+	rcu_assign_sk_user_data(sock->sk, NULL);
+	kernel_sock_shutdown(sock, SHUT_RDWR);
+	sk_release_kernel(sock->sk);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_sock_release);
+
 MODULE_LICENSE("GPL");
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index bcfbb4b496fc..cbc990712cc1 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -61,3 +61,45 @@ error:
 	return err;
 }
 EXPORT_SYMBOL_GPL(udp_sock_create6);
+
+int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
+			 struct sk_buff *skb, struct net_device *dev,
+			 struct in6_addr *saddr, struct in6_addr *daddr,
+			 __u8 prio, __u8 ttl, __be16 src_port, __be16 dst_port)
+{
+	struct udphdr *uh;
+	struct ipv6hdr *ip6h;
+	struct sock *sk = sock->sk;
+
+	__skb_push(skb, sizeof(*uh));
+	skb_reset_transport_header(skb);
+	uh = udp_hdr(skb);
+
+	uh->dest = dst_port;
+	uh->source = src_port;
+
+	uh->len = htons(skb->len);
+	uh->check = 0;
+
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
+			    | IPSKB_REROUTED);
+	skb_dst_set(skb, dst);
+
+	udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr,
+		      &sk->sk_v6_daddr, skb->len);
+
+	__skb_push(skb, sizeof(*ip6h));
+	skb_reset_network_header(skb);
+	ip6h		  = ipv6_hdr(skb);
+	ip6_flow_hdr(ip6h, prio, htonl(0));
+	ip6h->payload_len = htons(skb->len);
+	ip6h->nexthdr     = IPPROTO_UDP;
+	ip6h->hop_limit   = ttl;
+	ip6h->daddr	  = *daddr;
+	ip6h->saddr	  = *saddr;
+
+	ip6tunnel_xmit(skb, dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb);
-- 
cgit v1.2.3


From ce3e02867ed8e12c6e6e83a793d273c1f4d929ea Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Wed, 17 Sep 2014 12:25:55 -0700
Subject: net: Export inet_offloads and inet6_offloads

Want to be able to use these in foo-over-udp offloads, etc.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/protocol.c | 1 +
 net/ipv6/protocol.c | 1 +
 2 files changed, 2 insertions(+)

(limited to 'net/ipv6')

diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 46d6a1c923a8..4b7c0ec65251 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -30,6 +30,7 @@
 
 const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
 const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
+EXPORT_SYMBOL(inet_offloads);
 
 int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
 {
diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c
index e048cf1bb6a2..e3770abe688a 100644
--- a/net/ipv6/protocol.c
+++ b/net/ipv6/protocol.c
@@ -51,6 +51,7 @@ EXPORT_SYMBOL(inet6_del_protocol);
 #endif
 
 const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS] __read_mostly;
+EXPORT_SYMBOL(inet6_offloads);
 
 int inet6_add_offload(const struct net_offload *prot, unsigned char protocol)
 {
-- 
cgit v1.2.3


From 14909664e4e192f4c6f6fcdccd9919af7cf783ab Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Wed, 17 Sep 2014 12:25:59 -0700
Subject: sit: Setup and TX path for sit/UDP foo-over-udp encapsulation

Added netlink handling of IP tunnel encapulation paramters, properly
adjust MTU for encapsulation. Added ip_tunnel_encap call to
ipip6_tunnel_xmit to actually perform FOU encapsulation.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 107 +++++++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 97 insertions(+), 10 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 86e3fa81f85e..db75809ab843 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -822,6 +822,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	int addr_type;
 	u8 ttl;
 	int err;
+	u8 protocol = IPPROTO_IPV6;
+	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
 	if (skb->protocol != htons(ETH_P_IPV6))
 		goto tx_error;
@@ -911,8 +913,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		goto tx_error;
 	}
 
+	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT);
+	if (IS_ERR(skb)) {
+		ip_rt_put(rt);
+		goto out;
+	}
+
 	if (df) {
-		mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
+		mtu = dst_mtu(&rt->dst) - t_hlen;
 
 		if (mtu < 68) {
 			dev->stats.collisions++;
@@ -947,7 +955,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	/*
 	 * Okay, now see if we can stuff it in the buffer as-is.
 	 */
-	max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr);
+	max_headroom = LL_RESERVED_SPACE(tdev) + t_hlen;
 
 	if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
 	    (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
@@ -969,14 +977,13 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		ttl = iph6->hop_limit;
 	tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
 
-	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT);
-	if (IS_ERR(skb)) {
+	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) {
 		ip_rt_put(rt);
-		goto out;
+		goto tx_error;
 	}
 
 	err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr,
-			    IPPROTO_IPV6, tos, ttl, df,
+			    protocol, tos, ttl, df,
 			    !net_eq(tunnel->net, dev_net(dev)));
 	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
 	return NETDEV_TX_OK;
@@ -1059,8 +1066,10 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 		tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);
 
 	if (tdev) {
+		int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+
 		dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
-		dev->mtu = tdev->mtu - sizeof(struct iphdr);
+		dev->mtu = tdev->mtu - t_hlen;
 		if (dev->mtu < IPV6_MIN_MTU)
 			dev->mtu = IPV6_MIN_MTU;
 	}
@@ -1307,7 +1316,10 @@ done:
 
 static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu)
 {
-	if (new_mtu < IPV6_MIN_MTU || new_mtu > 0xFFF8 - sizeof(struct iphdr))
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+
+	if (new_mtu < IPV6_MIN_MTU || new_mtu > 0xFFF8 - t_hlen)
 		return -EINVAL;
 	dev->mtu = new_mtu;
 	return 0;
@@ -1338,12 +1350,15 @@ static void ipip6_dev_free(struct net_device *dev)
 
 static void ipip6_tunnel_setup(struct net_device *dev)
 {
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+
 	dev->netdev_ops		= &ipip6_netdev_ops;
 	dev->destructor		= ipip6_dev_free;
 
 	dev->type		= ARPHRD_SIT;
-	dev->hard_header_len	= LL_MAX_HEADER + sizeof(struct iphdr);
-	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr);
+	dev->hard_header_len	= LL_MAX_HEADER + t_hlen;
+	dev->mtu		= ETH_DATA_LEN - t_hlen;
 	dev->flags		= IFF_NOARP;
 	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
 	dev->iflink		= 0;
@@ -1466,6 +1481,40 @@ static void ipip6_netlink_parms(struct nlattr *data[],
 
 }
 
+/* This function returns true when ENCAP attributes are present in the nl msg */
+static bool ipip6_netlink_encap_parms(struct nlattr *data[],
+				      struct ip_tunnel_encap *ipencap)
+{
+	bool ret = false;
+
+	memset(ipencap, 0, sizeof(*ipencap));
+
+	if (!data)
+		return ret;
+
+	if (data[IFLA_IPTUN_ENCAP_TYPE]) {
+		ret = true;
+		ipencap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]);
+	}
+
+	if (data[IFLA_IPTUN_ENCAP_FLAGS]) {
+		ret = true;
+		ipencap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]);
+	}
+
+	if (data[IFLA_IPTUN_ENCAP_SPORT]) {
+		ret = true;
+		ipencap->sport = nla_get_u16(data[IFLA_IPTUN_ENCAP_SPORT]);
+	}
+
+	if (data[IFLA_IPTUN_ENCAP_DPORT]) {
+		ret = true;
+		ipencap->dport = nla_get_u16(data[IFLA_IPTUN_ENCAP_DPORT]);
+	}
+
+	return ret;
+}
+
 #ifdef CONFIG_IPV6_SIT_6RD
 /* This function returns true when 6RD attributes are present in the nl msg */
 static bool ipip6_netlink_6rd_parms(struct nlattr *data[],
@@ -1509,12 +1558,20 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 {
 	struct net *net = dev_net(dev);
 	struct ip_tunnel *nt;
+	struct ip_tunnel_encap ipencap;
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel_6rd ip6rd;
 #endif
 	int err;
 
 	nt = netdev_priv(dev);
+
+	if (ipip6_netlink_encap_parms(data, &ipencap)) {
+		err = ip_tunnel_encap_setup(nt, &ipencap);
+		if (err < 0)
+			return err;
+	}
+
 	ipip6_netlink_parms(data, &nt->parms);
 
 	if (ipip6_tunnel_locate(net, &nt->parms, 0))
@@ -1537,15 +1594,23 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
 {
 	struct ip_tunnel *t = netdev_priv(dev);
 	struct ip_tunnel_parm p;
+	struct ip_tunnel_encap ipencap;
 	struct net *net = t->net;
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel_6rd ip6rd;
 #endif
+	int err;
 
 	if (dev == sitn->fb_tunnel_dev)
 		return -EINVAL;
 
+	if (ipip6_netlink_encap_parms(data, &ipencap)) {
+		err = ip_tunnel_encap_setup(t, &ipencap);
+		if (err < 0)
+			return err;
+	}
+
 	ipip6_netlink_parms(data, &p);
 
 	if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) ||
@@ -1599,6 +1664,14 @@ static size_t ipip6_get_size(const struct net_device *dev)
 		/* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */
 		nla_total_size(2) +
 #endif
+		/* IFLA_IPTUN_ENCAP_TYPE */
+		nla_total_size(2) +
+		/* IFLA_IPTUN_ENCAP_FLAGS */
+		nla_total_size(2) +
+		/* IFLA_IPTUN_ENCAP_SPORT */
+		nla_total_size(2) +
+		/* IFLA_IPTUN_ENCAP_DPORT */
+		nla_total_size(2) +
 		0;
 }
 
@@ -1630,6 +1703,16 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		goto nla_put_failure;
 #endif
 
+	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
+			tunnel->encap.type) ||
+	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_SPORT,
+			tunnel->encap.sport) ||
+	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_DPORT,
+			tunnel->encap.dport) ||
+	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS,
+			tunnel->encap.dport))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
@@ -1651,6 +1734,10 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_6RD_PREFIXLEN]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 },
 #endif
+	[IFLA_IPTUN_ENCAP_TYPE]		= { .type = NLA_U16 },
+	[IFLA_IPTUN_ENCAP_FLAGS]	= { .type = NLA_U16 },
+	[IFLA_IPTUN_ENCAP_SPORT]	= { .type = NLA_U16 },
+	[IFLA_IPTUN_ENCAP_DPORT]	= { .type = NLA_U16 },
 };
 
 static void ipip6_dellink(struct net_device *dev, struct list_head *head)
-- 
cgit v1.2.3


From 6d967f8789249628a6388a3a4314c5fef423f36a Mon Sep 17 00:00:00 2001
From: Andy Zhou
Date: Fri, 19 Sep 2014 18:02:53 -0700
Subject: udp_tunnel: Only build ip6_udp_tunnel.c when IPV6 is selected

Functions supplied in ip6_udp_tunnel.c are only needed when IPV6 is
selected. When IPV6 is not selected, those functions are stubbed out
in udp_tunnel.h.

==================================================================
 net/ipv6/ip6_udp_tunnel.c:15:5: error: redefinition of 'udp_sock_create6'
     int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
 In file included from net/ipv6/ip6_udp_tunnel.c:9:0:
      include/net/udp_tunnel.h:36:19: note: previous definition of 'udp_sock_create6' was here
       static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
==================================================================

Fixes:  fd384412e udp_tunnel: Seperate ipv6 functions into its own file
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/Makefile | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 45f830e5f820..2e8c06108ab9 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -35,7 +35,6 @@ obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o
 obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o
 obj-$(CONFIG_IPV6_MIP6) += mip6.o
 obj-$(CONFIG_NETFILTER)	+= netfilter/
-obj-$(CONFIG_NET_UDP_TUNNEL) += ip6_udp_tunnel.o
 
 obj-$(CONFIG_IPV6_VTI) += ip6_vti.o
 obj-$(CONFIG_IPV6_SIT) += sit.o
@@ -46,3 +45,7 @@ obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o
 obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload)
 
 obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o
+
+ifneq ($(CONFIG_IPV6),)
+obj-$(CONFIG_NET_UDP_TUNNEL) += ip6_udp_tunnel.o
+endif
-- 
cgit v1.2.3


From 3fcb95a84fdb11e922cfac3b5cd3a9d96a9e9995 Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Mon, 22 Sep 2014 11:39:44 -0700
Subject: udp: Need to make ip6_udp_tunnel.c have GPL license

Unable to load various tunneling modules without this:

[   80.679049] fou: Unknown symbol udp_sock_create6 (err 0)
[   91.439939] ip6_udp_tunnel: Unknown symbol ip6_local_out (err 0)
[   91.439954] ip6_udp_tunnel: Unknown symbol __put_net (err 0)
[   91.457792] vxlan: Unknown symbol udp_sock_create6 (err 0)
[   91.457831] vxlan: Unknown symbol udp_tunnel6_xmit_skb (err 0)

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_udp_tunnel.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'net/ipv6')

diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index cbc990712cc1..b04ed72c4542 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -103,3 +103,5 @@ int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb);
+
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 35f7aa5309c048bb70e58571942795fa9411ce6a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Sat, 20 Sep 2014 14:03:55 +0200
Subject: ipv6: mld: answer mldv2 queries with mldv1 reports in mldv1 fallback

RFC2710 (MLDv1), section 3.7. says:

  The length of a received MLD message is computed by taking the
  IPv6 Payload Length value and subtracting the length of any IPv6
  extension headers present between the IPv6 header and the MLD
  message. If that length is greater than 24 octets, that indicates
  that there are other fields present *beyond* the fields described
  above, perhaps belonging to a *future backwards-compatible* version
  of MLD. An implementation of the version of MLD specified in this
  document *MUST NOT* send an MLD message longer than 24 octets and
  MUST ignore anything past the first 24 octets of a received MLD
  message.

RFC3810 (MLDv2), section 8.2.1. states for *listeners* regarding
presence of MLDv1 routers:

  In order to be compatible with MLDv1 routers, MLDv2 hosts MUST
  operate in version 1 compatibility mode. [...] When Host
  Compatibility Mode is MLDv2, a host acts using the MLDv2 protocol
  on that interface. When Host Compatibility Mode is MLDv1, a host
  acts in MLDv1 compatibility mode, using *only* the MLDv1 protocol,
  on that interface. [...]

While section 8.3.1. specifies *router* behaviour regarding presence
of MLDv1 routers:

  MLDv2 routers may be placed on a network where there is at least
  one MLDv1 router. The following requirements apply:

  If an MLDv1 router is present on the link, the Querier MUST use
  the *lowest* version of MLD present on the network. This must be
  administratively assured. Routers that desire to be compatible
  with MLDv1 MUST have a configuration option to act in MLDv1 mode;
  if an MLDv1 router is present on the link, the system administrator
  must explicitly configure all MLDv2 routers to act in MLDv1 mode.
  When in MLDv1 mode, the Querier MUST send periodic General Queries
  truncated at the Multicast Address field (i.e., 24 bytes long),
  and SHOULD also warn about receiving an MLDv2 Query (such warnings
  must be rate-limited). The Querier MUST also fill in the Maximum
  Response Delay in the Maximum Response Code field, i.e., the
  exponential algorithm described in section 5.1.3. is not used. [...]

That means that we should not get queries from different versions of
MLD. When there's a MLDv1 router present, MLDv2 enforces truncation
and MRC == MRD (both fields are overlapping within the 24 octet range).

Section 8.3.2. specifies behaviour in the presence of MLDv1 multicast
address *listeners*:

  MLDv2 routers may be placed on a network where there are hosts
  that have not yet been upgraded to MLDv2. In order to be compatible
  with MLDv1 hosts, MLDv2 routers MUST operate in version 1 compatibility
  mode. MLDv2 routers keep a compatibility mode per multicast address
  record. The compatibility mode of a multicast address is determined
  from the Multicast Address Compatibility Mode variable, which can be
  in one of the two following states: MLDv1 or MLDv2.

  The Multicast Address Compatibility Mode of a multicast address
  record is set to MLDv1 whenever an MLDv1 Multicast Listener Report is
  *received* for that multicast address. At the same time, the Older
  Version Host Present timer for the multicast address is set to Older
  Version Host Present Timeout seconds. The timer is re-set whenever a
  new MLDv1 Report is received for that multicast address. If the Older
  Version Host Present timer expires, the router switches back to
  Multicast Address Compatibility Mode of MLDv2 for that multicast
  address. [...]

That means, what can happen is the following scenario, that hosts can
act in MLDv1 compatibility mode when they previously have received an
MLDv1 query (or, simply operate in MLDv1 mode-only); and at the same
time, an MLDv2 router could start up and transmits MLDv2 startup query
messages while being unaware of the current operational mode.

Given RFC2710, section 3.7 we would need to answer to that with an MLDv1
listener report, so that the router according to RFC3810, section 8.3.2.
would receive that and internally switch to MLDv1 compatibility as well.

Right now, I believe since the initial implementation of MLDv2, Linux
hosts would just silently drop such MLDv2 queries instead of replying
with an MLDv1 listener report, which would prevent a MLDv2 router going
into fallback mode (until it receives other MLDv1 queries).

Since the mapping of MRC to MRD in exactly such cases can make use of
the exponential algorithm from 5.1.3, we cannot [strictly speaking] be
aware in MLDv1 of the encoding in MRC, it seems also not mentioned by
the RFC. Since encodings are the same up to 32767, assume in such a
situation this value as a hard upper limit we would clamp. We have asked
one of the RFC authors on that regard, and he mentioned that there seem
not to be any implementations that make use of that exponential algorithm
on startup messages. In any case, this patch fixes this MLD
interoperability issue.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/mld.h |  5 ++++-
 net/ipv6/mcast.c  | 41 +++++++++++++++++++++++++++++++----------
 2 files changed, 35 insertions(+), 11 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/mld.h b/include/net/mld.h
index faa1d161bf24..01d751303498 100644
--- a/include/net/mld.h
+++ b/include/net/mld.h
@@ -88,12 +88,15 @@ struct mld2_query {
 #define MLDV2_QQIC_EXP(value)	(((value) >> 4) & 0x07)
 #define MLDV2_QQIC_MAN(value)	((value) & 0x0f)
 
+#define MLD_EXP_MIN_LIMIT	32768UL
+#define MLDV1_MRD_MAX_COMPAT	(MLD_EXP_MIN_LIMIT - 1)
+
 static inline unsigned long mldv2_mrc(const struct mld2_query *mlh2)
 {
 	/* RFC3810, 5.1.3. Maximum Response Code */
 	unsigned long ret, mc_mrc = ntohs(mlh2->mld2q_mrc);
 
-	if (mc_mrc < 32768) {
+	if (mc_mrc < MLD_EXP_MIN_LIMIT) {
 		ret = mc_mrc;
 	} else {
 		unsigned long mc_man, mc_exp;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 592eba61e78a..9648de2b6745 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1237,7 +1237,7 @@ static void mld_update_qri(struct inet6_dev *idev,
 }
 
 static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld,
-			  unsigned long *max_delay)
+			  unsigned long *max_delay, bool v1_query)
 {
 	unsigned long mldv1_md;
 
@@ -1245,11 +1245,32 @@ static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld,
 	if (mld_in_v2_mode_only(idev))
 		return -EINVAL;
 
-	/* MLDv1 router present */
 	mldv1_md = ntohs(mld->mld_maxdelay);
+
+	/* When in MLDv1 fallback and a MLDv2 router start-up being
+	 * unaware of current MLDv1 operation, the MRC == MRD mapping
+	 * only works when the exponential algorithm is not being
+	 * used (as MLDv1 is unaware of such things).
+	 *
+	 * According to the RFC author, the MLDv2 implementations
+	 * he's aware of all use a MRC < 32768 on start up queries.
+	 *
+	 * Thus, should we *ever* encounter something else larger
+	 * than that, just assume the maximum possible within our
+	 * reach.
+	 */
+	if (!v1_query)
+		mldv1_md = min(mldv1_md, MLDV1_MRD_MAX_COMPAT);
+
 	*max_delay = max(msecs_to_jiffies(mldv1_md), 1UL);
 
-	mld_set_v1_mode(idev);
+	/* MLDv1 router present: we need to go into v1 mode *only*
+	 * when an MLDv1 query is received as per section 9.12. of
+	 * RFC3810! And we know from RFC2710 section 3.7 that MLDv1
+	 * queries MUST be of exactly 24 octets.
+	 */
+	if (v1_query)
+		mld_set_v1_mode(idev);
 
 	/* cancel MLDv2 report timer */
 	mld_gq_stop_timer(idev);
@@ -1264,10 +1285,6 @@ static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld,
 static int mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld,
 			  unsigned long *max_delay)
 {
-	/* hosts need to stay in MLDv1 mode, discard MLDv2 queries */
-	if (mld_in_v1_mode(idev))
-		return -EINVAL;
-
 	*max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL);
 
 	mld_update_qrv(idev, mld);
@@ -1324,8 +1341,11 @@ int igmp6_event_query(struct sk_buff *skb)
 	    !(group_type&IPV6_ADDR_MULTICAST))
 		return -EINVAL;
 
-	if (len == MLD_V1_QUERY_LEN) {
-		err = mld_process_v1(idev, mld, &max_delay);
+	if (len < MLD_V1_QUERY_LEN) {
+		return -EINVAL;
+	} else if (len == MLD_V1_QUERY_LEN || mld_in_v1_mode(idev)) {
+		err = mld_process_v1(idev, mld, &max_delay,
+				     len == MLD_V1_QUERY_LEN);
 		if (err < 0)
 			return err;
 	} else if (len >= MLD_V2_QUERY_LEN_MIN) {
@@ -1357,8 +1377,9 @@ int igmp6_event_query(struct sk_buff *skb)
 			mlh2 = (struct mld2_query *)skb_transport_header(skb);
 			mark = 1;
 		}
-	} else
+	} else {
 		return -EINVAL;
+	}
 
 	read_lock_bh(&idev->lock);
 	if (group_type == IPV6_ADDR_ANY) {
-- 
cgit v1.2.3


From 4cdf507d54525842dfd9f6313fdafba039084046 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Fri, 19 Sep 2014 07:38:40 -0700
Subject: icmp: add a global rate limitation

Current ICMP rate limiting uses inetpeer cache, which is an RBL tree
protected by a lock, meaning that hosts can be stuck hard if all cpus
want to check ICMP limits.

When say a DNS or NTP server process is restarted, inetpeer tree grows
quick and machine comes to its knees.

iptables can not help because the bottleneck happens before ICMP
messages are even cooked and sent.

This patch adds a new global limitation, using a token bucket filter,
controlled by two new sysctl :

icmp_msgs_per_sec - INTEGER
    Limit maximal number of ICMP packets sent per second from this host.
    Only messages whose type matches icmp_ratemask are
    controlled by this limit.
    Default: 1000

icmp_msgs_burst - INTEGER
    icmp_msgs_per_sec controls number of ICMP packets sent per second,
    while icmp_msgs_burst controls the burst size of these packets.
    Default: 50

Note that if we really want to send millions of ICMP messages per
second, we might extend idea and infra added in commit 04ca6973f7c1a
("ip: make IP identifiers less predictable") :
add a token bucket in the ip_idents hash and no longer rely on inetpeer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 13 +++++++
 include/net/ip.h                       |  4 +++
 net/ipv4/icmp.c                        | 64 +++++++++++++++++++++++++++++++---
 net/ipv4/sysctl_net_ipv4.c             | 16 +++++++++
 net/ipv6/icmp.c                        | 20 ++++++-----
 5 files changed, 105 insertions(+), 12 deletions(-)

(limited to 'net/ipv6')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 1b5581a30d77..c7a81ace35d0 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -769,8 +769,21 @@ icmp_ratelimit - INTEGER
 	icmp_ratemask (see below) to specific targets.
 	0 to disable any limiting,
 	otherwise the minimal space between responses in milliseconds.
+	Note that another sysctl, icmp_msgs_per_sec limits the number
+	of ICMP packets	sent on all targets.
 	Default: 1000
 
+icmp_msgs_per_sec - INTEGER
+	Limit maximal number of ICMP packets sent per second from this host.
+	Only messages whose type matches icmp_ratemask (see below) are
+	controlled by this limit.
+	Default: 1000
+
+icmp_msgs_burst - INTEGER
+	icmp_msgs_per_sec controls number of ICMP packets sent per second,
+	while icmp_msgs_burst controls the burst size of these packets.
+	Default: 50
+
 icmp_ratemask - INTEGER
 	Mask made of ICMP types for which rates are being limited.
 	Significant bits: IHGFEDCBA9876543210
diff --git a/include/net/ip.h b/include/net/ip.h
index 14bfc8e1bcf9..fcd9068fb8c3 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -548,6 +548,10 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
 void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
 		    u32 info);
 
+bool icmp_global_allow(void);
+extern int sysctl_icmp_msgs_per_sec;
+extern int sysctl_icmp_msgs_burst;
+
 #ifdef CONFIG_PROC_FS
 int ip_misc_proc_init(void);
 #endif
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index ea7d4afe8205..5882f584910e 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -231,12 +231,62 @@ static inline void icmp_xmit_unlock(struct sock *sk)
 	spin_unlock_bh(&sk->sk_lock.slock);
 }
 
+int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
+int sysctl_icmp_msgs_burst __read_mostly = 50;
+
+static struct {
+	spinlock_t	lock;
+	u32		credit;
+	u32		stamp;
+} icmp_global = {
+	.lock		= __SPIN_LOCK_UNLOCKED(icmp_global.lock),
+};
+
+/**
+ * icmp_global_allow - Are we allowed to send one more ICMP message ?
+ *
+ * Uses a token bucket to limit our ICMP messages to sysctl_icmp_msgs_per_sec.
+ * Returns false if we reached the limit and can not send another packet.
+ * Note: called with BH disabled
+ */
+bool icmp_global_allow(void)
+{
+	u32 credit, delta, incr = 0, now = (u32)jiffies;
+	bool rc = false;
+
+	/* Check if token bucket is empty and cannot be refilled
+	 * without taking the spinlock.
+	 */
+	if (!icmp_global.credit) {
+		delta = min_t(u32, now - icmp_global.stamp, HZ);
+		if (delta < HZ / 50)
+			return false;
+	}
+
+	spin_lock(&icmp_global.lock);
+	delta = min_t(u32, now - icmp_global.stamp, HZ);
+	if (delta >= HZ / 50) {
+		incr = sysctl_icmp_msgs_per_sec * delta / HZ ;
+		if (incr)
+			icmp_global.stamp = now;
+	}
+	credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
+	if (credit) {
+		credit--;
+		rc = true;
+	}
+	icmp_global.credit = credit;
+	spin_unlock(&icmp_global.lock);
+	return rc;
+}
+EXPORT_SYMBOL(icmp_global_allow);
+
 /*
  *	Send an ICMP frame.
  */
 
-static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
-				      struct flowi4 *fl4, int type, int code)
+static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
+			       struct flowi4 *fl4, int type, int code)
 {
 	struct dst_entry *dst = &rt->dst;
 	bool rc = true;
@@ -253,8 +303,14 @@ static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
 		goto out;
 
 	/* Limit if icmp type is enabled in ratemask. */
-	if ((1 << type) & net->ipv4.sysctl_icmp_ratemask) {
-		struct inet_peer *peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1);
+	if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
+		goto out;
+
+	rc = false;
+	if (icmp_global_allow()) {
+		struct inet_peer *peer;
+
+		peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1);
 		rc = inet_peer_xrlim_allow(peer,
 					   net->ipv4.sysctl_icmp_ratelimit);
 		if (peer)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1599966f4639..8a25509c35b3 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -730,6 +730,22 @@ static struct ctl_table ipv4_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+	{
+		.procname	= "icmp_msgs_per_sec",
+		.data		= &sysctl_icmp_msgs_per_sec,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+	},
+	{
+		.procname	= "icmp_msgs_burst",
+		.data		= &sysctl_icmp_msgs_burst,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+	},
 	{
 		.procname	= "udp_mem",
 		.data		= &sysctl_udp_mem,
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 394bb824fe4b..141e1f3ab74e 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -170,11 +170,11 @@ static bool is_ineligible(const struct sk_buff *skb)
 /*
  * Check the ICMP output rate limit
  */
-static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
-				      struct flowi6 *fl6)
+static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
+			       struct flowi6 *fl6)
 {
-	struct dst_entry *dst;
 	struct net *net = sock_net(sk);
+	struct dst_entry *dst;
 	bool res = false;
 
 	/* Informational messages are not limited. */
@@ -199,16 +199,20 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 	} else {
 		struct rt6_info *rt = (struct rt6_info *)dst;
 		int tmo = net->ipv6.sysctl.icmpv6_time;
-		struct inet_peer *peer;
 
 		/* Give more bandwidth to wider prefixes. */
 		if (rt->rt6i_dst.plen < 128)
 			tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
 
-		peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
-		res = inet_peer_xrlim_allow(peer, tmo);
-		if (peer)
-			inet_putpeer(peer);
+		if (icmp_global_allow()) {
+			struct inet_peer *peer;
+
+			peer = inet_getpeer_v6(net->ipv6.peers,
+					       &rt->rt6i_dst.addr, 1);
+			res = inet_peer_xrlim_allow(peer, tmo);
+			if (peer)
+				inet_putpeer(peer);
+		}
 	}
 	dst_release(dst);
 	return res;
-- 
cgit v1.2.3


From d020f8f73318589bf41f864b7f89f95669350873 Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Sat, 20 Sep 2014 14:52:28 -0700
Subject: tcp: move logic out of tcp_v[64]_gso_send_check

In tcp_v[46]_gso_send_check the TCP checksum is initialized to the
pseudo header checksum using __tcp_v[46]_send_check. We can move this
logic into new tcp[46]_gso_segment functions to be done when
ip_summed != CHECKSUM_PARTIAL (ip_summed == CHECKSUM_PARTIAL should be
the common case, possibly always true when taking GSO path). After this
change tcp_v[46]_gso_send_check is no-op.

Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_offload.c   | 39 +++++++++++++++++++++++----------------
 net/ipv6/tcpv6_offload.c | 37 ++++++++++++++++++++++++-------------
 2 files changed, 47 insertions(+), 29 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 72912533a191..7cd12b0458ff 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -29,6 +29,28 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq,
 	}
 }
 
+struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
+				 netdev_features_t features)
+{
+	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
+		return ERR_PTR(-EINVAL);
+
+	if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
+		const struct iphdr *iph = ip_hdr(skb);
+		struct tcphdr *th = tcp_hdr(skb);
+
+		/* Set up checksum pseudo header, usually expect stack to
+		 * have done this already.
+		 */
+
+		th->check = 0;
+		skb->ip_summed = CHECKSUM_PARTIAL;
+		__tcp_v4_send_check(skb, iph->saddr, iph->daddr);
+	}
+
+	return tcp_gso_segment(skb, features);
+}
+
 struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 				netdev_features_t features)
 {
@@ -44,9 +66,6 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	__sum16 newcheck;
 	bool ooo_okay, copy_destructor;
 
-	if (!pskb_may_pull(skb, sizeof(*th)))
-		goto out;
-
 	th = tcp_hdr(skb);
 	thlen = th->doff * 4;
 	if (thlen < sizeof(*th))
@@ -271,18 +290,6 @@ EXPORT_SYMBOL(tcp_gro_complete);
 
 static int tcp_v4_gso_send_check(struct sk_buff *skb)
 {
-	const struct iphdr *iph;
-	struct tcphdr *th;
-
-	if (!pskb_may_pull(skb, sizeof(*th)))
-		return -EINVAL;
-
-	iph = ip_hdr(skb);
-	th = tcp_hdr(skb);
-
-	th->check = 0;
-	skb->ip_summed = CHECKSUM_PARTIAL;
-	__tcp_v4_send_check(skb, iph->saddr, iph->daddr);
 	return 0;
 }
 
@@ -314,7 +321,7 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 static const struct net_offload tcpv4_offload = {
 	.callbacks = {
 		.gso_send_check	=	tcp_v4_gso_send_check,
-		.gso_segment	=	tcp_gso_segment,
+		.gso_segment	=	tcp4_gso_segment,
 		.gro_receive	=	tcp4_gro_receive,
 		.gro_complete	=	tcp4_gro_complete,
 	},
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index dbb3d9262bf6..96253154db3a 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -17,18 +17,6 @@
 
 static int tcp_v6_gso_send_check(struct sk_buff *skb)
 {
-	const struct ipv6hdr *ipv6h;
-	struct tcphdr *th;
-
-	if (!pskb_may_pull(skb, sizeof(*th)))
-		return -EINVAL;
-
-	ipv6h = ipv6_hdr(skb);
-	th = tcp_hdr(skb);
-
-	th->check = 0;
-	skb->ip_summed = CHECKSUM_PARTIAL;
-	__tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr);
 	return 0;
 }
 
@@ -58,10 +46,33 @@ static int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 	return tcp_gro_complete(skb);
 }
 
+struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
+				 netdev_features_t features)
+{
+	struct tcphdr *th;
+
+	if (!pskb_may_pull(skb, sizeof(*th)))
+		return ERR_PTR(-EINVAL);
+
+	if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
+		const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+		struct tcphdr *th = tcp_hdr(skb);
+
+		/* Set up pseudo header, usually expect stack to have done
+		 * this.
+		 */
+
+		th->check = 0;
+		skb->ip_summed = CHECKSUM_PARTIAL;
+		__tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr);
+	}
+
+	return tcp_gso_segment(skb, features);
+}
 static const struct net_offload tcpv6_offload = {
 	.callbacks = {
 		.gso_send_check	=	tcp_v6_gso_send_check,
-		.gso_segment	=	tcp_gso_segment,
+		.gso_segment	=	tcp6_gso_segment,
 		.gro_receive	=	tcp6_gro_receive,
 		.gro_complete	=	tcp6_gro_complete,
 	},
-- 
cgit v1.2.3


From f71470b37e79d6eb151debd47364d920b7babd30 Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Sat, 20 Sep 2014 14:52:29 -0700
Subject: udp: move logic out of udp[46]_ufo_send_check

In udp[46]_ufo_send_check the UDP checksum initialized to the pseudo
header checksum. We can move this logic into udp[46]_ufo_fragment.
After this change udp[64]_ufo_send_check is a no-op.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp_offload.c | 37 +++++++++++++++----------------------
 net/ipv6/udp_offload.c | 40 ++++++++++++++++++----------------------
 2 files changed, 33 insertions(+), 44 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index d7c43f764c71..2918cc914824 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -27,23 +27,6 @@ struct udp_offload_priv {
 
 static int udp4_ufo_send_check(struct sk_buff *skb)
 {
-	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
-		return -EINVAL;
-
-	if (likely(!skb->encapsulation)) {
-		const struct iphdr *iph;
-		struct udphdr *uh;
-
-		iph = ip_hdr(skb);
-		uh = udp_hdr(skb);
-
-		uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
-				IPPROTO_UDP, 0);
-		skb->csum_start = skb_transport_header(skb) - skb->head;
-		skb->csum_offset = offsetof(struct udphdr, check);
-		skb->ip_summed = CHECKSUM_PARTIAL;
-	}
-
 	return 0;
 }
 
@@ -128,8 +111,9 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	unsigned int mss;
-	int offset;
 	__wsum csum;
+	struct udphdr *uh;
+	struct iphdr *iph;
 
 	if (skb->encapsulation &&
 	    (skb_shinfo(skb)->gso_type &
@@ -138,6 +122,9 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 		goto out;
 	}
 
+	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+		goto out;
+
 	mss = skb_shinfo(skb)->gso_size;
 	if (unlikely(skb->len <= mss))
 		goto out;
@@ -165,10 +152,16 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	 * HW cannot do checksum of UDP packets sent as multiple
 	 * IP fragments.
 	 */
-	offset = skb_checksum_start_offset(skb);
-	csum = skb_checksum(skb, offset, skb->len - offset, 0);
-	offset += skb->csum_offset;
-	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
+
+	uh = udp_hdr(skb);
+	iph = ip_hdr(skb);
+
+	uh->check = 0;
+	csum = skb_checksum(skb, 0, skb->len, 0);
+	uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum);
+	if (uh->check == 0)
+		uh->check = CSUM_MANGLED_0;
+
 	skb->ip_summed = CHECKSUM_NONE;
 
 	/* Fragment the skb. IP headers of the fragments are updated in
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index de85f809bf29..e4af6437ea3b 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -19,23 +19,6 @@
 
 static int udp6_ufo_send_check(struct sk_buff *skb)
 {
-	const struct ipv6hdr *ipv6h;
-	struct udphdr *uh;
-
-	if (!pskb_may_pull(skb, sizeof(*uh)))
-		return -EINVAL;
-
-	if (likely(!skb->encapsulation)) {
-		ipv6h = ipv6_hdr(skb);
-		uh = udp_hdr(skb);
-
-		uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len,
-					     IPPROTO_UDP, 0);
-		skb->csum_start = skb_transport_header(skb) - skb->head;
-		skb->csum_offset = offsetof(struct udphdr, check);
-		skb->ip_summed = CHECKSUM_PARTIAL;
-	}
-
 	return 0;
 }
 
@@ -49,7 +32,6 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 	u8 *packet_start, *prevhdr;
 	u8 nexthdr;
 	u8 frag_hdr_sz = sizeof(struct frag_hdr);
-	int offset;
 	__wsum csum;
 	int tnl_hlen;
 
@@ -83,13 +65,27 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 	    (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
 		segs = skb_udp_tunnel_segment(skb, features);
 	else {
+		const struct ipv6hdr *ipv6h;
+		struct udphdr *uh;
+
+		if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+			goto out;
+
 		/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
 		 * do checksum of UDP packets sent as multiple IP fragments.
 		 */
-		offset = skb_checksum_start_offset(skb);
-		csum = skb_checksum(skb, offset, skb->len - offset, 0);
-		offset += skb->csum_offset;
-		*(__sum16 *)(skb->data + offset) = csum_fold(csum);
+
+		uh = udp_hdr(skb);
+		ipv6h = ipv6_hdr(skb);
+
+		uh->check = 0;
+		csum = skb_checksum(skb, 0, skb->len, 0);
+		uh->check = udp_v6_check(skb->len, &ipv6h->saddr,
+					  &ipv6h->daddr, csum);
+
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+
 		skb->ip_summed = CHECKSUM_NONE;
 
 		/* Check if there is enough headroom to insert fragment header. */
-- 
cgit v1.2.3


From 53e50398968d43338c4d932114e68bc099fc5fbd Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Sat, 20 Sep 2014 14:52:30 -0700
Subject: net: Remove gso_send_check as an offload callback

The send_check logic was only interesting in cases of TCP offload and
UDP UFO where the checksum needed to be initialized to the pseudo
header checksum. Now we've moved that logic into the related
gso_segment functions so gso_send_check is no longer needed.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  1 -
 net/core/dev.c            | 10 ----------
 net/ipv4/af_inet.c        | 36 ------------------------------------
 net/ipv4/gre_offload.c    | 11 +++--------
 net/ipv4/tcp_offload.c    |  6 ------
 net/ipv4/udp_offload.c    |  6 ------
 net/ipv6/ip6_offload.c    | 27 ---------------------------
 net/ipv6/tcpv6_offload.c  |  6 ------
 net/ipv6/udp_offload.c    |  6 ------
 net/mpls/mpls_gso.c       |  7 -------
 10 files changed, 3 insertions(+), 113 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4354b4307e37..9f5d293a0281 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1911,7 +1911,6 @@ struct packet_type {
 struct offload_callbacks {
 	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
 						netdev_features_t features);
-	int			(*gso_send_check)(struct sk_buff *skb);
 	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
 					       struct sk_buff *skb);
 	int			(*gro_complete)(struct sk_buff *skb, int nhoff);
diff --git a/net/core/dev.c b/net/core/dev.c
index db0388607329..e2ced01c01e4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2422,16 +2422,6 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, &offload_base, list) {
 		if (ptype->type == type && ptype->callbacks.gso_segment) {
-			if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
-				int err;
-
-				err = ptype->callbacks.gso_send_check(skb);
-				segs = ERR_PTR(err);
-				if (err || skb_gso_ok(skb, features))
-					break;
-				__skb_push(skb, (skb->data -
-						 skb_network_header(skb)));
-			}
 			segs = ptype->callbacks.gso_segment(skb, features);
 			break;
 		}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 72011cc4c13b..28e589c5f32d 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1197,40 +1197,6 @@ int inet_sk_rebuild_header(struct sock *sk)
 }
 EXPORT_SYMBOL(inet_sk_rebuild_header);
 
-static int inet_gso_send_check(struct sk_buff *skb)
-{
-	const struct net_offload *ops;
-	const struct iphdr *iph;
-	int proto;
-	int ihl;
-	int err = -EINVAL;
-
-	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
-		goto out;
-
-	iph = ip_hdr(skb);
-	ihl = iph->ihl * 4;
-	if (ihl < sizeof(*iph))
-		goto out;
-
-	proto = iph->protocol;
-
-	/* Warning: after this point, iph might be no longer valid */
-	if (unlikely(!pskb_may_pull(skb, ihl)))
-		goto out;
-	__skb_pull(skb, ihl);
-
-	skb_reset_transport_header(skb);
-	err = -EPROTONOSUPPORT;
-
-	ops = rcu_dereference(inet_offloads[proto]);
-	if (likely(ops && ops->callbacks.gso_send_check))
-		err = ops->callbacks.gso_send_check(skb);
-
-out:
-	return err;
-}
-
 static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 					netdev_features_t features)
 {
@@ -1655,7 +1621,6 @@ static int ipv4_proc_init(void);
 static struct packet_offload ip_packet_offload __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IP),
 	.callbacks = {
-		.gso_send_check = inet_gso_send_check,
 		.gso_segment = inet_gso_segment,
 		.gro_receive = inet_gro_receive,
 		.gro_complete = inet_gro_complete,
@@ -1664,7 +1629,6 @@ static struct packet_offload ip_packet_offload __read_mostly = {
 
 static const struct net_offload ipip_offload = {
 	.callbacks = {
-		.gso_send_check = inet_gso_send_check,
 		.gso_segment	= inet_gso_segment,
 		.gro_receive	= inet_gro_receive,
 		.gro_complete	= inet_gro_complete,
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index d3fe2ac05167..a77729503071 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -15,13 +15,6 @@
 #include <net/protocol.h>
 #include <net/gre.h>
 
-static int gre_gso_send_check(struct sk_buff *skb)
-{
-	if (!skb->encapsulation)
-		return -EINVAL;
-	return 0;
-}
-
 static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {
@@ -46,6 +39,9 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_IPIP)))
 		goto out;
 
+	if (!skb->encapsulation)
+		goto out;
+
 	if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
 		goto out;
 
@@ -256,7 +252,6 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload gre_offload = {
 	.callbacks = {
-		.gso_send_check = gre_gso_send_check,
 		.gso_segment = gre_gso_segment,
 		.gro_receive = gre_gro_receive,
 		.gro_complete = gre_gro_complete,
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 7cd12b0458ff..5b90f2f447a5 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -288,11 +288,6 @@ int tcp_gro_complete(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_gro_complete);
 
-static int tcp_v4_gso_send_check(struct sk_buff *skb)
-{
-	return 0;
-}
-
 static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 {
 	/* Don't bother verifying checksum if we're going to flush anyway. */
@@ -320,7 +315,6 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 
 static const struct net_offload tcpv4_offload = {
 	.callbacks = {
-		.gso_send_check	=	tcp_v4_gso_send_check,
 		.gso_segment	=	tcp4_gso_segment,
 		.gro_receive	=	tcp4_gro_receive,
 		.gro_complete	=	tcp4_gro_complete,
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 2918cc914824..19ebe6a39ddc 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -25,11 +25,6 @@ struct udp_offload_priv {
 	struct udp_offload_priv __rcu *next;
 };
 
-static int udp4_ufo_send_check(struct sk_buff *skb)
-{
-	return 0;
-}
-
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {
@@ -346,7 +341,6 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload udpv4_offload = {
 	.callbacks = {
-		.gso_send_check = udp4_ufo_send_check,
 		.gso_segment = udp4_ufo_fragment,
 		.gro_receive  =	udp4_gro_receive,
 		.gro_complete =	udp4_gro_complete,
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 9952f3fce30a..9034f76ae013 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -53,31 +53,6 @@ static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
 	return proto;
 }
 
-static int ipv6_gso_send_check(struct sk_buff *skb)
-{
-	const struct ipv6hdr *ipv6h;
-	const struct net_offload *ops;
-	int err = -EINVAL;
-
-	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
-		goto out;
-
-	ipv6h = ipv6_hdr(skb);
-	__skb_pull(skb, sizeof(*ipv6h));
-	err = -EPROTONOSUPPORT;
-
-	ops = rcu_dereference(inet6_offloads[
-		ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]);
-
-	if (likely(ops && ops->callbacks.gso_send_check)) {
-		skb_reset_transport_header(skb);
-		err = ops->callbacks.gso_send_check(skb);
-	}
-
-out:
-	return err;
-}
-
 static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	netdev_features_t features)
 {
@@ -306,7 +281,6 @@ out_unlock:
 static struct packet_offload ipv6_packet_offload __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IPV6),
 	.callbacks = {
-		.gso_send_check = ipv6_gso_send_check,
 		.gso_segment = ipv6_gso_segment,
 		.gro_receive = ipv6_gro_receive,
 		.gro_complete = ipv6_gro_complete,
@@ -315,7 +289,6 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
 
 static const struct net_offload sit_offload = {
 	.callbacks = {
-		.gso_send_check = ipv6_gso_send_check,
 		.gso_segment	= ipv6_gso_segment,
 		.gro_receive	= ipv6_gro_receive,
 		.gro_complete	= ipv6_gro_complete,
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 96253154db3a..c1ab77105b4c 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -15,11 +15,6 @@
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
-static int tcp_v6_gso_send_check(struct sk_buff *skb)
-{
-	return 0;
-}
-
 static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
 					 struct sk_buff *skb)
 {
@@ -71,7 +66,6 @@ struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
 }
 static const struct net_offload tcpv6_offload = {
 	.callbacks = {
-		.gso_send_check	=	tcp_v6_gso_send_check,
 		.gso_segment	=	tcp6_gso_segment,
 		.gro_receive	=	tcp6_gro_receive,
 		.gro_complete	=	tcp6_gro_complete,
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index e4af6437ea3b..212ebfc7973f 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -17,11 +17,6 @@
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
-static int udp6_ufo_send_check(struct sk_buff *skb)
-{
-	return 0;
-}
-
 static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 					 netdev_features_t features)
 {
@@ -166,7 +161,6 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload udpv6_offload = {
 	.callbacks = {
-		.gso_send_check =	udp6_ufo_send_check,
 		.gso_segment	=	udp6_ufo_fragment,
 		.gro_receive	=	udp6_gro_receive,
 		.gro_complete	=	udp6_gro_complete,
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index 6b38d083e1c9..e28ed2ef5b06 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -65,15 +65,9 @@ out:
 	return segs;
 }
 
-static int mpls_gso_send_check(struct sk_buff *skb)
-{
-	return 0;
-}
-
 static struct packet_offload mpls_mc_offload = {
 	.type = cpu_to_be16(ETH_P_MPLS_MC),
 	.callbacks = {
-		.gso_send_check =	mpls_gso_send_check,
 		.gso_segment    =	mpls_gso_segment,
 	},
 };
@@ -81,7 +75,6 @@ static struct packet_offload mpls_mc_offload = {
 static struct packet_offload mpls_uc_offload = {
 	.type = cpu_to_be16(ETH_P_MPLS_UC),
 	.callbacks = {
-		.gso_send_check =	mpls_gso_send_check,
 		.gso_segment    =	mpls_gso_segment,
 	},
 };
-- 
cgit v1.2.3


From a224772db8420ecb7ce91a9ba5d535ee3a50d982 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Sat, 27 Sep 2014 09:50:56 -0700
Subject: ipv6: add a struct inet6_skb_parm param to ipv6_opt_accepted()

ipv6_opt_accepted() assumes IP6CB(skb) holds the struct inet6_skb_parm
that it needs. Lets not assume this, as TCP stack might use a different
place.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h    | 3 ++-
 net/dccp/ipv6.c       | 2 +-
 net/ipv6/af_inet6.c   | 4 ++--
 net/ipv6/syncookies.c | 2 +-
 net/ipv6/tcp_ipv6.c   | 5 +++--
 5 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 7e247e9b8765..97f472012438 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -288,7 +288,8 @@ struct ipv6_txoptions *ipv6_renew_options(struct sock *sk,
 struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
 					  struct ipv6_txoptions *opt);
 
-bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb);
+bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
+		       const struct inet6_skb_parm *opt);
 
 static inline bool ipv6_accept_ra(struct inet6_dev *idev)
 {
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 04cb17d4b0ce..ad2acfe1ca61 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -404,7 +404,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
 
-	if (ipv6_opt_accepted(sk, skb) ||
+	if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) ||
 	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
 		atomic_inc(&skb->users);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e4865a3ebe1d..34f726f59814 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -672,10 +672,10 @@ int inet6_sk_rebuild_header(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(inet6_sk_rebuild_header);
 
-bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb)
+bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
+		       const struct inet6_skb_parm *opt)
 {
 	const struct ipv6_pinfo *np = inet6_sk(sk);
-	const struct inet6_skb_parm *opt = IP6CB(skb);
 
 	if (np->rxopt.all) {
 		if ((opt->hop && (np->rxopt.bits.hopopts ||
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index c643dc907ce7..9a2838e93cc5 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -203,7 +203,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	ireq->ir_num = ntohs(th->dest);
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
-	if (ipv6_opt_accepted(sk, skb) ||
+	if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
 	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
 		atomic_inc(&skb->users);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index de51a88bec6f..9400b4326f22 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -742,7 +742,8 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
 		ireq->ir_iif = inet6_iif(skb);
 
 	if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
-	    (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo ||
+	    (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
+	     np->rxopt.bits.rxinfo ||
 	     np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
 	     np->rxopt.bits.rxohlim || np->repflow)) {
 		atomic_inc(&skb->users);
@@ -1367,7 +1368,7 @@ ipv6_pktoptions:
 			np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
 		if (np->repflow)
 			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
-		if (ipv6_opt_accepted(sk, opt_skb)) {
+		if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
 			skb_set_owner_r(opt_skb, sk);
 			opt_skb = xchg(&np->pktoptions, opt_skb);
 		} else {
-- 
cgit v1.2.3


From 971f10eca186cab238c49daa91f703c5a001b0b1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Sat, 27 Sep 2014 09:50:57 -0700
Subject: tcp: better TCP_SKB_CB layout to reduce cache line misses

TCP maintains lists of skb in write queue, and in receive queues
(in order and out of order queues)

Scanning these lists both in input and output path usually requires
access to skb->next, TCP_SKB_CB(skb)->seq, and TCP_SKB_CB(skb)->end_seq

These fields are currently in two different cache lines, meaning we
waste lot of memory bandwidth when these queues are big and flows
have either packet drops or packet reorders.

We can move TCP_SKB_CB(skb)->header at the end of TCP_SKB_CB, because
this header is not used in fast path. This allows TCP to search much faster
in the skb lists.

Even with regular flows, we save one cache line miss in fast path.

Thanks to Christoph Paasch for noticing we need to cleanup
skb->cb[] (IPCB/IP6CB) before entering IP stack in tx path,
and that I forgot IPCB use in tcp_v4_hnd_req() and tcp_v4_save_options().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 12 ++++++------
 net/ipv4/tcp_ipv4.c   | 19 ++++++++++++-------
 net/ipv4/tcp_output.c |  5 +++++
 net/ipv6/tcp_ipv6.c   |  7 +++++++
 4 files changed, 30 insertions(+), 13 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index a4201ef216e8..4dc6641ee990 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -696,12 +696,6 @@ static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
  * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately.
  */
 struct tcp_skb_cb {
-	union {
-		struct inet_skb_parm	h4;
-#if IS_ENABLED(CONFIG_IPV6)
-		struct inet6_skb_parm	h6;
-#endif
-	} header;	/* For incoming frames		*/
 	__u32		seq;		/* Starting sequence number	*/
 	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/
 	__u32		tcp_tw_isn;	/* isn chosen by tcp_timewait_state_process() */
@@ -720,6 +714,12 @@ struct tcp_skb_cb {
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
 	/* 1 byte hole */
 	__u32		ack_seq;	/* Sequence number ACK'd	*/
+	union {
+		struct inet_skb_parm	h4;
+#if IS_ENABLED(CONFIG_IPV6)
+		struct inet6_skb_parm	h6;
+#endif
+	} header;	/* For incoming frames		*/
 };
 
 #define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 28ab90382c01..9ce3eac02957 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -886,18 +886,16 @@ EXPORT_SYMBOL(tcp_syn_flood_action);
  */
 static struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
 {
-	const struct ip_options *opt = &(IPCB(skb)->opt);
+	const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
 	struct ip_options_rcu *dopt = NULL;
 
 	if (opt && opt->optlen) {
 		int opt_size = sizeof(*dopt) + opt->optlen;
 
 		dopt = kmalloc(opt_size, GFP_ATOMIC);
-		if (dopt) {
-			if (ip_options_echo(&dopt->opt, skb)) {
-				kfree(dopt);
-				dopt = NULL;
-			}
+		if (dopt && __ip_options_echo(&dopt->opt, skb, opt)) {
+			kfree(dopt);
+			dopt = NULL;
 		}
 	}
 	return dopt;
@@ -1431,7 +1429,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_SYN_COOKIES
 	if (!th->syn)
-		sk = cookie_v4_check(sk, skb, &(IPCB(skb)->opt));
+		sk = cookie_v4_check(sk, skb, &TCP_SKB_CB(skb)->header.h4.opt);
 #endif
 	return sk;
 }
@@ -1636,6 +1634,13 @@ int tcp_v4_rcv(struct sk_buff *skb)
 
 	th = tcp_hdr(skb);
 	iph = ip_hdr(skb);
+	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
+	 * barrier() makes sure compiler wont play fool^Waliasing games.
+	 */
+	memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
+		sizeof(struct inet_skb_parm));
+	barrier();
+
 	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff * 4);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f173b1c4f815..a462fb1db896 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -974,6 +974,11 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	/* Our usage of tstamp should remain private */
 	skb->tstamp.tv64 = 0;
+
+	/* Cleanup our debris for IP stacks */
+	memset(skb->cb, 0, max(sizeof(struct inet_skb_parm),
+			       sizeof(struct inet6_skb_parm)));
+
 	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
 
 	if (likely(err <= 0))
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9400b4326f22..132bac137aed 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1412,6 +1412,13 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 
 	th = tcp_hdr(skb);
 	hdr = ipv6_hdr(skb);
+	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
+	 * barrier() makes sure compiler wont play fool^Waliasing games.
+	 */
+	memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb),
+		sizeof(struct inet6_skb_parm));
+	barrier();
+
 	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff*4);
-- 
cgit v1.2.3


From 8bce6d7d0d1ede22af334ee241841e9278365278 Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Mon, 29 Sep 2014 20:22:29 -0700
Subject: udp: Generalize skb_udp_segment

skb_udp_segment is the function called from udp4_ufo_fragment to
segment a UDP tunnel packet. This function currently assumes
segmentation is transparent Ethernet bridging (i.e. VXLAN
encapsulation). This patch generalizes the function to
operate on either Ethertype or IP protocol.

The inner_protocol field must be set to the protocol of the inner
header. This can now be either an Ethertype or an IP protocol
(in a union). A new flag in the skbuff indicates which type is
effective. skb_set_inner_protocol and skb_set_inner_ipproto
helper functions were added to set the inner_protocol. These
functions are called from the point where the tunnel encapsulation
is occuring.

When skb_udp_tunnel_segment is called, the function to segment the
inner packet is selected based on the inner IP or Ethertype. In the
case of an IP protocol encapsulation, the function is derived from
inet[6]_offloads. In the case of Ethertype, skb->protocol is
set to the inner_protocol and skb_mac_gso_segment is called. (GRE
currently does this, but it might be possible to lookup the protocol
in offload_base and call the appropriate segmenation function
directly).

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 26 +++++++++++++++++++++++--
 include/net/udp.h      |  3 ++-
 net/ipv4/udp_offload.c | 51 +++++++++++++++++++++++++++++++++++++++++++++-----
 net/ipv6/udp_offload.c |  2 +-
 4 files changed, 73 insertions(+), 9 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d8f7d74d5a4d..7c5036d11feb 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -596,7 +596,8 @@ struct sk_buff {
 	__u8			ndisc_nodetype:2;
 #endif
 	__u8			ipvs_property:1;
-	/* 5 or 7 bit hole */
+	__u8			inner_protocol_type:1;
+	/* 4 or 6 bit hole */
 
 #ifdef CONFIG_NET_SCHED
 	__u16			tc_index;	/* traffic control index */
@@ -632,7 +633,11 @@ struct sk_buff {
 		__u32		reserved_tailroom;
 	};
 
-	__be16			inner_protocol;
+	union {
+		__be16		inner_protocol;
+		__u8		inner_ipproto;
+	};
+
 	__u16			inner_transport_header;
 	__u16			inner_network_header;
 	__u16			inner_mac_header;
@@ -1762,6 +1767,23 @@ static inline void skb_reserve(struct sk_buff *skb, int len)
 	skb->tail += len;
 }
 
+#define ENCAP_TYPE_ETHER	0
+#define ENCAP_TYPE_IPPROTO	1
+
+static inline void skb_set_inner_protocol(struct sk_buff *skb,
+					  __be16 protocol)
+{
+	skb->inner_protocol = protocol;
+	skb->inner_protocol_type = ENCAP_TYPE_ETHER;
+}
+
+static inline void skb_set_inner_ipproto(struct sk_buff *skb,
+					 __u8 ipproto)
+{
+	skb->inner_ipproto = ipproto;
+	skb->inner_protocol_type = ENCAP_TYPE_IPPROTO;
+}
+
 static inline void skb_reset_inner_headers(struct sk_buff *skb)
 {
 	skb->inner_mac_header = skb->mac_header;
diff --git a/include/net/udp.h b/include/net/udp.h
index 16f4e80f0519..07f9b70962f6 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -239,7 +239,8 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 int udp_disconnect(struct sock *sk, int flags);
 unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait);
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
-				       netdev_features_t features);
+				       netdev_features_t features,
+				       bool is_ipv6);
 int udp_lib_getsockopt(struct sock *sk, int level, int optname,
 		       char __user *optval, int __user *optlen);
 int udp_lib_setsockopt(struct sock *sk, int level, int optname,
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 19ebe6a39ddc..8c35f2c939ee 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -25,8 +25,11 @@ struct udp_offload_priv {
 	struct udp_offload_priv __rcu *next;
 };
 
-struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
-				       netdev_features_t features)
+static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
+	netdev_features_t features,
+	struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
+					     netdev_features_t features),
+	__be16 new_protocol)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	u16 mac_offset = skb->mac_header;
@@ -48,7 +51,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 	skb_reset_mac_header(skb);
 	skb_set_network_header(skb, skb_inner_network_offset(skb));
 	skb->mac_len = skb_inner_network_offset(skb);
-	skb->protocol = htons(ETH_P_TEB);
+	skb->protocol = new_protocol;
 
 	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM);
 	if (need_csum)
@@ -56,7 +59,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 
 	/* segment inner packet. */
 	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
-	segs = skb_mac_gso_segment(skb, enc_features);
+	segs = gso_inner_segment(skb, enc_features);
 	if (IS_ERR_OR_NULL(segs)) {
 		skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
 				     mac_len);
@@ -101,6 +104,44 @@ out:
 	return segs;
 }
 
+struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
+				       netdev_features_t features,
+				       bool is_ipv6)
+{
+	__be16 protocol = skb->protocol;
+	const struct net_offload **offloads;
+	const struct net_offload *ops;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
+					     netdev_features_t features);
+
+	rcu_read_lock();
+
+	switch (skb->inner_protocol_type) {
+	case ENCAP_TYPE_ETHER:
+		protocol = skb->inner_protocol;
+		gso_inner_segment = skb_mac_gso_segment;
+		break;
+	case ENCAP_TYPE_IPPROTO:
+		offloads = is_ipv6 ? inet6_offloads : inet_offloads;
+		ops = rcu_dereference(offloads[skb->inner_ipproto]);
+		if (!ops || !ops->callbacks.gso_segment)
+			goto out_unlock;
+		gso_inner_segment = ops->callbacks.gso_segment;
+		break;
+	default:
+		goto out_unlock;
+	}
+
+	segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment,
+					protocol);
+
+out_unlock:
+	rcu_read_unlock();
+
+	return segs;
+}
+
 static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 					 netdev_features_t features)
 {
@@ -113,7 +154,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	if (skb->encapsulation &&
 	    (skb_shinfo(skb)->gso_type &
 	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
-		segs = skb_udp_tunnel_segment(skb, features);
+		segs = skb_udp_tunnel_segment(skb, features, false);
 		goto out;
 	}
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 212ebfc7973f..8f96988c1db2 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -58,7 +58,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 
 	if (skb->encapsulation && skb_shinfo(skb)->gso_type &
 	    (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
-		segs = skb_udp_tunnel_segment(skb, features);
+		segs = skb_udp_tunnel_segment(skb, features, true);
 	else {
 		const struct ipv6hdr *ipv6h;
 		struct udphdr *uh;
-- 
cgit v1.2.3


From 469471cdfc1902861fedafe8c5c1c8dbf5ad6ba6 Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Mon, 29 Sep 2014 20:22:30 -0700
Subject: sit: Set inner IP protocol in sit

Call skb_set_inner_ipproto to set inner IP protocol to IPPROTO_IPV6
before tunnel_xmit. This is needed if UDP encapsulation (fou) is
being done.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'net/ipv6')

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index db75809ab843..0d4e27466f82 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -982,6 +982,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		goto tx_error;
 	}
 
+	skb_set_inner_ipproto(skb, IPPROTO_IPV6);
+
 	err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr,
 			    protocol, tos, ttl, df,
 			    !net_eq(tunnel->net, dev_net(dev)));
@@ -1006,6 +1008,8 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (IS_ERR(skb))
 		goto out;
 
+	skb_set_inner_ipproto(skb, IPPROTO_IPIP);
+
 	ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP);
 	return NETDEV_TX_OK;
 out:
-- 
cgit v1.2.3


From 54bc9bac307861aea5abb747cb58bf0275f2175f Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Mon, 29 Sep 2014 20:22:32 -0700
Subject: gre: Set inner protocol in v4 and v6 GRE transmit

Call skb_set_inner_protocol to set inner Ethernet protocol to
protocol being encapsulation by GRE before tunnel_xmit. This is
needed for GSO if UDP encapsulation (fou) is being done.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c  | 2 ++
 net/ipv6/ip6_gre.c | 8 ++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 829aff8bf723..0485ef18d254 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -241,6 +241,8 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
 	/* Push GRE header. */
 	gre_build_header(skb, &tpi, tunnel->tun_hlen);
 
+	skb_set_inner_protocol(skb, tpi.proto);
+
 	ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol);
 }
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 5f19dfbc4c6a..9a0a1aafe727 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -616,6 +616,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 	int err = -1;
 	u8 proto;
 	struct sk_buff *new_skb;
+	__be16 protocol;
 
 	if (dev->type == ARPHRD_ETHER)
 		IPCB(skb)->flags = 0;
@@ -732,8 +733,9 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 	ipv6h->daddr = fl6->daddr;
 
 	((__be16 *)(ipv6h + 1))[0] = tunnel->parms.o_flags;
-	((__be16 *)(ipv6h + 1))[1] = (dev->type == ARPHRD_ETHER) ?
-				   htons(ETH_P_TEB) : skb->protocol;
+	protocol = (dev->type == ARPHRD_ETHER) ?
+		    htons(ETH_P_TEB) : skb->protocol;
+	((__be16 *)(ipv6h + 1))[1] = protocol;
 
 	if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) {
 		__be32 *ptr = (__be32 *)(((u8 *)ipv6h) + tunnel->hlen - 4);
@@ -754,6 +756,8 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 		}
 	}
 
+	skb_set_inner_protocol(skb, protocol);
+
 	ip6tunnel_xmit(skb, dev);
 	if (ndst)
 		ip6_tnl_dst_store(tunnel, ndst);
-- 
cgit v1.2.3


From c8d7b98bec43faaa6583c3135030be5eb4693acb Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Fri, 26 Sep 2014 14:35:15 +0200
Subject: netfilter: move nf_send_resetX() code to nf_reject_ipvX modules

Move nf_send_reset() and nf_send_reset6() to nf_reject_ipv4 and
nf_reject_ipv6 respectively. This code is shared by x_tables and
nf_tables.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv4/nf_reject.h | 118 +-----------------------
 net/ipv4/netfilter/Kconfig             |   6 ++
 net/ipv4/netfilter/Makefile            |   3 +
 net/ipv4/netfilter/nf_reject_ipv4.c    | 127 +++++++++++++++++++++++++
 net/ipv6/netfilter/Kconfig             |   6 ++
 net/ipv6/netfilter/Makefile            |   3 +
 net/ipv6/netfilter/nf_reject_ipv6.c    | 163 +++++++++++++++++++++++++++++++++
 7 files changed, 309 insertions(+), 117 deletions(-)
 create mode 100644 net/ipv4/netfilter/nf_reject_ipv4.c
 create mode 100644 net/ipv6/netfilter/nf_reject_ipv6.c

(limited to 'net/ipv6')

diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h
index 8ce06385a552..e8427193c777 100644
--- a/include/net/netfilter/ipv4/nf_reject.h
+++ b/include/net/netfilter/ipv4/nf_reject.h
@@ -1,10 +1,6 @@
 #ifndef _IPV4_NF_REJECT_H
 #define _IPV4_NF_REJECT_H
 
-#include <net/ip.h>
-#include <net/tcp.h>
-#include <net/route.h>
-#include <net/dst.h>
 #include <net/icmp.h>
 
 static inline void nf_send_unreach(struct sk_buff *skb_in, int code)
@@ -12,118 +8,6 @@ static inline void nf_send_unreach(struct sk_buff *skb_in, int code)
 	icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
 }
 
-/* Send RST reply */
-static void nf_send_reset(struct sk_buff *oldskb, int hook)
-{
-	struct sk_buff *nskb;
-	const struct iphdr *oiph;
-	struct iphdr *niph;
-	const struct tcphdr *oth;
-	struct tcphdr _otcph, *tcph;
-
-	/* IP header checks: fragment. */
-	if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
-		return;
-
-	oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
-				 sizeof(_otcph), &_otcph);
-	if (oth == NULL)
-		return;
-
-	/* No RST for RST. */
-	if (oth->rst)
-		return;
-
-	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
-		return;
-
-	/* Check checksum */
-	if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
-		return;
-	oiph = ip_hdr(oldskb);
-
-	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
-			 LL_MAX_HEADER, GFP_ATOMIC);
-	if (!nskb)
-		return;
-
-	skb_reserve(nskb, LL_MAX_HEADER);
-
-	skb_reset_network_header(nskb);
-	niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
-	niph->version	= 4;
-	niph->ihl	= sizeof(struct iphdr) / 4;
-	niph->tos	= 0;
-	niph->id	= 0;
-	niph->frag_off	= htons(IP_DF);
-	niph->protocol	= IPPROTO_TCP;
-	niph->check	= 0;
-	niph->saddr	= oiph->daddr;
-	niph->daddr	= oiph->saddr;
-
-	skb_reset_transport_header(nskb);
-	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
-	memset(tcph, 0, sizeof(*tcph));
-	tcph->source	= oth->dest;
-	tcph->dest	= oth->source;
-	tcph->doff	= sizeof(struct tcphdr) / 4;
-
-	if (oth->ack)
-		tcph->seq = oth->ack_seq;
-	else {
-		tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
-				      oldskb->len - ip_hdrlen(oldskb) -
-				      (oth->doff << 2));
-		tcph->ack = 1;
-	}
-
-	tcph->rst	= 1;
-	tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
-				    niph->daddr, 0);
-	nskb->ip_summed = CHECKSUM_PARTIAL;
-	nskb->csum_start = (unsigned char *)tcph - nskb->head;
-	nskb->csum_offset = offsetof(struct tcphdr, check);
-
-	/* ip_route_me_harder expects skb->dst to be set */
-	skb_dst_set_noref(nskb, skb_dst(oldskb));
-
-	nskb->protocol = htons(ETH_P_IP);
-	if (ip_route_me_harder(nskb, RTN_UNSPEC))
-		goto free_nskb;
-
-	niph->ttl	= ip4_dst_hoplimit(skb_dst(nskb));
-
-	/* "Never happens" */
-	if (nskb->len > dst_mtu(skb_dst(nskb)))
-		goto free_nskb;
-
-	nf_ct_attach(nskb, oldskb);
-
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	/* If we use ip_local_out for bridged traffic, the MAC source on
-	 * the RST will be ours, instead of the destination's.  This confuses
-	 * some routers/firewalls, and they drop the packet.  So we need to
-	 * build the eth header using the original destination's MAC as the
-	 * source, and send the RST packet directly.
-	 */
-	if (oldskb->nf_bridge) {
-		struct ethhdr *oeth = eth_hdr(oldskb);
-		nskb->dev = oldskb->nf_bridge->physindev;
-		niph->tot_len = htons(nskb->len);
-		ip_send_check(niph);
-		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
-				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
-			goto free_nskb;
-		dev_queue_xmit(nskb);
-	} else
-#endif
-		ip_local_out(nskb);
-
-	return;
-
- free_nskb:
-	kfree_skb(nskb);
-}
-
+void nf_send_reset(struct sk_buff *oldskb, int hook);
 
 #endif /* _IPV4_NF_REJECT_H */
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 345242a79db6..4c019d5c3f57 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -61,8 +61,13 @@ config NFT_CHAIN_ROUTE_IPV4
 	  fields such as the source, destination, type of service and
 	  the packet mark.
 
+config NF_REJECT_IPV4
+	tristate "IPv4 packet rejection"
+	default m if NETFILTER_ADVANCED=n
+
 config NFT_REJECT_IPV4
 	depends on NF_TABLES_IPV4
+	select NF_REJECT_IPV4
 	default NFT_REJECT
 	tristate
 
@@ -208,6 +213,7 @@ config IP_NF_FILTER
 config IP_NF_TARGET_REJECT
 	tristate "REJECT target support"
 	depends on IP_NF_FILTER
+	select NF_REJECT_IPV4
 	default m if NETFILTER_ADVANCED=n
 	help
 	  The REJECT target allows a filtering rule to specify that an ICMP
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 14488cc5fd2c..f4cef5af0969 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -23,6 +23,9 @@ obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o
 obj-$(CONFIG_NF_LOG_ARP) += nf_log_arp.o
 obj-$(CONFIG_NF_LOG_IPV4) += nf_log_ipv4.o
 
+# reject
+obj-$(CONFIG_NF_REJECT_IPV4) += nf_reject_ipv4.o
+
 # NAT helpers (nf_conntrack)
 obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o
 obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
new file mode 100644
index 000000000000..b023b4eb1a96
--- /dev/null
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -0,0 +1,127 @@
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2004 Netfilter Core Team <coreteam@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.
+ */
+
+#include <net/ip.h>
+#include <net/tcp.h>
+#include <net/route.h>
+#include <net/dst.h>
+#include <linux/netfilter_ipv4.h>
+
+/* Send RST reply */
+void nf_send_reset(struct sk_buff *oldskb, int hook)
+{
+	struct sk_buff *nskb;
+	const struct iphdr *oiph;
+	struct iphdr *niph;
+	const struct tcphdr *oth;
+	struct tcphdr _otcph, *tcph;
+
+	/* IP header checks: fragment. */
+	if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
+		return;
+
+	oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
+				 sizeof(_otcph), &_otcph);
+	if (oth == NULL)
+		return;
+
+	/* No RST for RST. */
+	if (oth->rst)
+		return;
+
+	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
+		return;
+
+	/* Check checksum */
+	if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
+		return;
+	oiph = ip_hdr(oldskb);
+
+	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
+			 LL_MAX_HEADER, GFP_ATOMIC);
+	if (!nskb)
+		return;
+
+	skb_reserve(nskb, LL_MAX_HEADER);
+
+	skb_reset_network_header(nskb);
+	niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
+	niph->version	= 4;
+	niph->ihl	= sizeof(struct iphdr) / 4;
+	niph->tos	= 0;
+	niph->id	= 0;
+	niph->frag_off	= htons(IP_DF);
+	niph->protocol	= IPPROTO_TCP;
+	niph->check	= 0;
+	niph->saddr	= oiph->daddr;
+	niph->daddr	= oiph->saddr;
+
+	skb_reset_transport_header(nskb);
+	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
+	memset(tcph, 0, sizeof(*tcph));
+	tcph->source	= oth->dest;
+	tcph->dest	= oth->source;
+	tcph->doff	= sizeof(struct tcphdr) / 4;
+
+	if (oth->ack)
+		tcph->seq = oth->ack_seq;
+	else {
+		tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
+				      oldskb->len - ip_hdrlen(oldskb) -
+				      (oth->doff << 2));
+		tcph->ack = 1;
+	}
+
+	tcph->rst	= 1;
+	tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
+				    niph->daddr, 0);
+	nskb->ip_summed = CHECKSUM_PARTIAL;
+	nskb->csum_start = (unsigned char *)tcph - nskb->head;
+	nskb->csum_offset = offsetof(struct tcphdr, check);
+
+	/* ip_route_me_harder expects skb->dst to be set */
+	skb_dst_set_noref(nskb, skb_dst(oldskb));
+
+	nskb->protocol = htons(ETH_P_IP);
+	if (ip_route_me_harder(nskb, RTN_UNSPEC))
+		goto free_nskb;
+
+	niph->ttl	= ip4_dst_hoplimit(skb_dst(nskb));
+
+	/* "Never happens" */
+	if (nskb->len > dst_mtu(skb_dst(nskb)))
+		goto free_nskb;
+
+	nf_ct_attach(nskb, oldskb);
+
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	/* If we use ip_local_out for bridged traffic, the MAC source on
+	 * the RST will be ours, instead of the destination's.  This confuses
+	 * some routers/firewalls, and they drop the packet.  So we need to
+	 * build the eth header using the original destination's MAC as the
+	 * source, and send the RST packet directly.
+	 */
+	if (oldskb->nf_bridge) {
+		struct ethhdr *oeth = eth_hdr(oldskb);
+		nskb->dev = oldskb->nf_bridge->physindev;
+		niph->tot_len = htons(nskb->len);
+		ip_send_check(niph);
+		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
+				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
+			goto free_nskb;
+		dev_queue_xmit(nskb);
+	} else
+#endif
+		ip_local_out(nskb);
+
+	return;
+
+ free_nskb:
+	kfree_skb(nskb);
+}
+EXPORT_SYMBOL_GPL(nf_send_reset);
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index bb1a40db7be1..6af874fc187f 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -40,8 +40,13 @@ config NFT_CHAIN_ROUTE_IPV6
 	  fields such as the source, destination, flowlabel, hop-limit and
 	  the packet mark.
 
+config NF_REJECT_IPV6
+	tristate "IPv6 packet rejection"
+	default m if NETFILTER_ADVANCED=n
+
 config NFT_REJECT_IPV6
 	depends on NF_TABLES_IPV6
+	select NF_REJECT_IPV6
 	default NFT_REJECT
 	tristate
 
@@ -208,6 +213,7 @@ config IP6_NF_FILTER
 config IP6_NF_TARGET_REJECT
 	tristate "REJECT target support"
 	depends on IP6_NF_FILTER
+	select NF_REJECT_IPV6
 	default m if NETFILTER_ADVANCED=n
 	help
 	  The REJECT target allows a filtering rule to specify that an ICMPv6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 0f7e5b3f328d..fbb25f01143c 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -27,6 +27,9 @@ obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
 # logging
 obj-$(CONFIG_NF_LOG_IPV6) += nf_log_ipv6.o
 
+# reject
+obj-$(CONFIG_NF_REJECT_IPV6) += nf_reject_ipv6.o
+
 # nf_tables
 obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
new file mode 100644
index 000000000000..5f5f0438d74d
--- /dev/null
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -0,0 +1,163 @@
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2004 Netfilter Core Team <coreteam@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.
+ */
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/ip6_fib.h>
+#include <net/ip6_checksum.h>
+#include <linux/netfilter_ipv6.h>
+
+void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
+{
+	struct sk_buff *nskb;
+	struct tcphdr otcph, *tcph;
+	unsigned int otcplen, hh_len;
+	int tcphoff, needs_ack;
+	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
+	struct ipv6hdr *ip6h;
+#define DEFAULT_TOS_VALUE	0x0U
+	const __u8 tclass = DEFAULT_TOS_VALUE;
+	struct dst_entry *dst = NULL;
+	u8 proto;
+	__be16 frag_off;
+	struct flowi6 fl6;
+
+	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
+	    (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
+		pr_debug("addr is not unicast.\n");
+		return;
+	}
+
+	proto = oip6h->nexthdr;
+	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
+
+	if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
+		pr_debug("Cannot get TCP header.\n");
+		return;
+	}
+
+	otcplen = oldskb->len - tcphoff;
+
+	/* IP header checks: fragment, too short. */
+	if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
+		pr_debug("proto(%d) != IPPROTO_TCP, "
+			 "or too short. otcplen = %d\n",
+			 proto, otcplen);
+		return;
+	}
+
+	if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr)))
+		BUG();
+
+	/* No RST for RST. */
+	if (otcph.rst) {
+		pr_debug("RST is set\n");
+		return;
+	}
+
+	/* Check checksum. */
+	if (nf_ip6_checksum(oldskb, hook, tcphoff, IPPROTO_TCP)) {
+		pr_debug("TCP checksum is invalid\n");
+		return;
+	}
+
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_TCP;
+	fl6.saddr = oip6h->daddr;
+	fl6.daddr = oip6h->saddr;
+	fl6.fl6_sport = otcph.dest;
+	fl6.fl6_dport = otcph.source;
+	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
+	dst = ip6_route_output(net, NULL, &fl6);
+	if (dst == NULL || dst->error) {
+		dst_release(dst);
+		return;
+	}
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
+	if (IS_ERR(dst))
+		return;
+
+	hh_len = (dst->dev->hard_header_len + 15)&~15;
+	nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
+			 + sizeof(struct tcphdr) + dst->trailer_len,
+			 GFP_ATOMIC);
+
+	if (!nskb) {
+		net_dbg_ratelimited("cannot alloc skb\n");
+		dst_release(dst);
+		return;
+	}
+
+	skb_dst_set(nskb, dst);
+
+	skb_reserve(nskb, hh_len + dst->header_len);
+
+	skb_put(nskb, sizeof(struct ipv6hdr));
+	skb_reset_network_header(nskb);
+	ip6h = ipv6_hdr(nskb);
+	ip6_flow_hdr(ip6h, tclass, 0);
+	ip6h->hop_limit = ip6_dst_hoplimit(dst);
+	ip6h->nexthdr = IPPROTO_TCP;
+	ip6h->saddr = oip6h->daddr;
+	ip6h->daddr = oip6h->saddr;
+
+	skb_reset_transport_header(nskb);
+	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
+	/* Truncate to length (no data) */
+	tcph->doff = sizeof(struct tcphdr)/4;
+	tcph->source = otcph.dest;
+	tcph->dest = otcph.source;
+
+	if (otcph.ack) {
+		needs_ack = 0;
+		tcph->seq = otcph.ack_seq;
+		tcph->ack_seq = 0;
+	} else {
+		needs_ack = 1;
+		tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin
+				      + otcplen - (otcph.doff<<2));
+		tcph->seq = 0;
+	}
+
+	/* Reset flags */
+	((u_int8_t *)tcph)[13] = 0;
+	tcph->rst = 1;
+	tcph->ack = needs_ack;
+	tcph->window = 0;
+	tcph->urg_ptr = 0;
+	tcph->check = 0;
+
+	/* Adjust TCP checksum */
+	tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,
+				      &ipv6_hdr(nskb)->daddr,
+				      sizeof(struct tcphdr), IPPROTO_TCP,
+				      csum_partial(tcph,
+						   sizeof(struct tcphdr), 0));
+
+	nf_ct_attach(nskb, oldskb);
+
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	/* If we use ip6_local_out for bridged traffic, the MAC source on
+	 * the RST will be ours, instead of the destination's.  This confuses
+	 * some routers/firewalls, and they drop the packet.  So we need to
+	 * build the eth header using the original destination's MAC as the
+	 * source, and send the RST packet directly.
+	 */
+	if (oldskb->nf_bridge) {
+		struct ethhdr *oeth = eth_hdr(oldskb);
+		nskb->dev = oldskb->nf_bridge->physindev;
+		nskb->protocol = htons(ETH_P_IPV6);
+		ip6h->payload_len = htons(sizeof(struct tcphdr));
+		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
+				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
+			return;
+		dev_queue_xmit(nskb);
+	} else
+#endif
+		ip6_local_out(nskb);
+}
+EXPORT_SYMBOL_GPL(nf_send_reset6);
-- 
cgit v1.2.3


From 1109a90c01177e8f4a5fd95c5b685ad02f1fe9bb Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso
Date: Wed, 1 Oct 2014 11:19:17 +0200
Subject: netfilter: use IS_ENABLED(CONFIG_BRIDGE_NETFILTER)

In 34666d4 ("netfilter: bridge: move br_netfilter out of the core"),
the bridge netfilter code has been modularized.

Use IS_ENABLED instead of ifdef to cover the module case.

Fixes: 34666d4 ("netfilter: bridge: move br_netfilter out of the core")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/core/skbuff.c                          |  2 +-
 net/ipv4/ip_output.c                       |  2 +-
 net/ipv4/netfilter/ipt_REJECT.c            |  2 +-
 net/ipv4/netfilter/nf_defrag_ipv4.c        |  2 +-
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c  |  2 +-
 net/netfilter/ipset/ip_set_hash_netiface.c |  4 ++--
 net/netfilter/nf_log_common.c              |  2 +-
 net/netfilter/nf_queue.c                   |  4 ++--
 net/netfilter/nfnetlink_log.c              |  8 ++++----
 net/netfilter/nfnetlink_queue_core.c       | 12 ++++++------
 10 files changed, 20 insertions(+), 20 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 4be570a4ab21..7de3d679f3e0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -566,7 +566,7 @@ static void skb_release_head_state(struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	nf_conntrack_put(skb->nfct);
 #endif
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	nf_bridge_put(skb->nf_bridge);
 #endif
 /* XXX: IS this still necessary? - JHS */
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c8fa62476461..e35b71289156 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -516,7 +516,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 	hlen = iph->ihl * 4;
 	mtu = mtu - hlen;	/* Size of data space */
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (skb->nf_bridge)
 		mtu -= nf_bridge_mtu_reduction(skb);
 #endif
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index 5b6e0df4ccff..8f48f5517e33 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -20,7 +20,7 @@
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ipt_REJECT.h>
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 #include <linux/netfilter_bridge.h>
 #endif
 
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 76bd1aef257f..7e5ca6f2d0cd 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -50,7 +50,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
 		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
 #endif
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (skb->nf_bridge &&
 	    skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
 		return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index 7b9a748c6bac..e70382e4dfb5 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -40,7 +40,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
 		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
 #endif
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (skb->nf_bridge &&
 	    skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
 		return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 03cdb69ac9bf..35dd35873442 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -237,7 +237,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
 #define SRCDIR		(opt->flags & IPSET_DIM_TWO_SRC)
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		const struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 
 		if (!nf_bridge)
@@ -474,7 +474,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	ip6_netmask(&e.ip, e.cidr);
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		const struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 
 		if (!nf_bridge)
diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c
index eeb8ef4ff1a3..a2233e77cf39 100644
--- a/net/netfilter/nf_log_common.c
+++ b/net/netfilter/nf_log_common.c
@@ -158,7 +158,7 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf,
 	       '0' + loginfo->u.log.level, prefix,
 	       in ? in->name : "",
 	       out ? out->name : "");
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (skb->nf_bridge) {
 		const struct net_device *physindev;
 		const struct net_device *physoutdev;
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 5d24b1fdb593..4c8b68e5fa16 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -52,7 +52,7 @@ void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
 		dev_put(entry->indev);
 	if (entry->outdev)
 		dev_put(entry->outdev);
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (entry->skb->nf_bridge) {
 		struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge;
 
@@ -77,7 +77,7 @@ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry)
 		dev_hold(entry->indev);
 	if (entry->outdev)
 		dev_hold(entry->outdev);
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (entry->skb->nf_bridge) {
 		struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge;
 		struct net_device *physdev;
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index a11c5ff2f720..b1e3a0579416 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -36,7 +36,7 @@
 
 #include <linux/atomic.h>
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 #include "../bridge/br_private.h"
 #endif
 
@@ -429,7 +429,7 @@ __build_packet_message(struct nfnl_log_net *log,
 		goto nla_put_failure;
 
 	if (indev) {
-#ifndef CONFIG_BRIDGE_NETFILTER
+#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV,
 				 htonl(indev->ifindex)))
 			goto nla_put_failure;
@@ -460,7 +460,7 @@ __build_packet_message(struct nfnl_log_net *log,
 	}
 
 	if (outdev) {
-#ifndef CONFIG_BRIDGE_NETFILTER
+#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV,
 				 htonl(outdev->ifindex)))
 			goto nla_put_failure;
@@ -640,7 +640,7 @@ nfulnl_log_packet(struct net *net,
 		+ nla_total_size(sizeof(struct nfulnl_msg_packet_hdr))
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 #endif
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index 108120f216b1..a82077d9f59b 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -36,7 +36,7 @@
 
 #include <linux/atomic.h>
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 #include "../bridge/br_private.h"
 #endif
 
@@ -302,7 +302,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 		+ nla_total_size(sizeof(struct nfqnl_msg_packet_hdr))
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
 #endif
@@ -380,7 +380,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 
 	indev = entry->indev;
 	if (indev) {
-#ifndef CONFIG_BRIDGE_NETFILTER
+#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex)))
 			goto nla_put_failure;
 #else
@@ -410,7 +410,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	}
 
 	if (outdev) {
-#ifndef CONFIG_BRIDGE_NETFILTER
+#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 		if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex)))
 			goto nla_put_failure;
 #else
@@ -569,7 +569,7 @@ nf_queue_entry_dup(struct nf_queue_entry *e)
 	return NULL;
 }
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 /* When called from bridge netfilter, skb->data must point to MAC header
  * before calling skb_gso_segment(). Else, original MAC header is lost
  * and segmented skbs will be sent to wrong destination.
@@ -763,7 +763,7 @@ dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex)
 	if (entry->outdev)
 		if (entry->outdev->ifindex == ifindex)
 			return 1;
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (entry->skb->nf_bridge) {
 		if (entry->skb->nf_bridge->physindev &&
 		    entry->skb->nf_bridge->physindev->ifindex == ifindex)
-- 
cgit v1.2.3


From 8da4cc1b10c1aeba090d1d862b17174e4dbd50a4 Mon Sep 17 00:00:00 2001
From: Arturo Borrero
Date: Fri, 3 Oct 2014 14:13:36 +0200
Subject: netfilter: nft_masq: register/unregister notifiers on module
 init/exit

We have to register the notifiers in the masquerade expression from
the the module _init and _exit path.

This fixes crashes when removing the masquerade rule with no
ipt_MASQUERADE support in place (which was masking the problem).

Fixes: 9ba1f72 ("netfilter: nf_tables: add new nft_masq expression")
Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/nft_masq_ipv4.c | 34 +++++++++++-----------------------
 net/ipv6/netfilter/nft_masq_ipv6.c | 34 +++++++++++-----------------------
 2 files changed, 22 insertions(+), 46 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index 6ea1d207b6a5..1c636d6b5b50 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -32,33 +32,12 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr,
 	data[NFT_REG_VERDICT].verdict = verdict;
 }
 
-static int nft_masq_ipv4_init(const struct nft_ctx *ctx,
-			      const struct nft_expr *expr,
-			      const struct nlattr * const tb[])
-{
-	int err;
-
-	err = nft_masq_init(ctx, expr, tb);
-	if (err < 0)
-		return err;
-
-	nf_nat_masquerade_ipv4_register_notifier();
-	return 0;
-}
-
-static void nft_masq_ipv4_destroy(const struct nft_ctx *ctx,
-				  const struct nft_expr *expr)
-{
-	nf_nat_masquerade_ipv4_unregister_notifier();
-}
-
 static struct nft_expr_type nft_masq_ipv4_type;
 static const struct nft_expr_ops nft_masq_ipv4_ops = {
 	.type		= &nft_masq_ipv4_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
 	.eval		= nft_masq_ipv4_eval,
-	.init		= nft_masq_ipv4_init,
-	.destroy	= nft_masq_ipv4_destroy,
+	.init		= nft_masq_init,
 	.dump		= nft_masq_dump,
 };
 
@@ -73,12 +52,21 @@ static struct nft_expr_type nft_masq_ipv4_type __read_mostly = {
 
 static int __init nft_masq_ipv4_module_init(void)
 {
-	return nft_register_expr(&nft_masq_ipv4_type);
+	int ret;
+
+	ret = nft_register_expr(&nft_masq_ipv4_type);
+	if (ret < 0)
+		return ret;
+
+	nf_nat_masquerade_ipv4_register_notifier();
+
+	return ret;
 }
 
 static void __exit nft_masq_ipv4_module_exit(void)
 {
 	nft_unregister_expr(&nft_masq_ipv4_type);
+	nf_nat_masquerade_ipv4_unregister_notifier();
 }
 
 module_init(nft_masq_ipv4_module_init);
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index 4e51334ef6b7..556262f40761 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -32,33 +32,12 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr,
 	data[NFT_REG_VERDICT].verdict = verdict;
 }
 
-static int nft_masq_ipv6_init(const struct nft_ctx *ctx,
-			      const struct nft_expr *expr,
-			      const struct nlattr * const tb[])
-{
-	int err;
-
-	err = nft_masq_init(ctx, expr, tb);
-	if (err < 0)
-		return err;
-
-	nf_nat_masquerade_ipv6_register_notifier();
-	return 0;
-}
-
-static void nft_masq_ipv6_destroy(const struct nft_ctx *ctx,
-				  const struct nft_expr *expr)
-{
-	nf_nat_masquerade_ipv6_unregister_notifier();
-}
-
 static struct nft_expr_type nft_masq_ipv6_type;
 static const struct nft_expr_ops nft_masq_ipv6_ops = {
 	.type		= &nft_masq_ipv6_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
 	.eval		= nft_masq_ipv6_eval,
-	.init		= nft_masq_ipv6_init,
-	.destroy	= nft_masq_ipv6_destroy,
+	.init		= nft_masq_init,
 	.dump		= nft_masq_dump,
 };
 
@@ -73,12 +52,21 @@ static struct nft_expr_type nft_masq_ipv6_type __read_mostly = {
 
 static int __init nft_masq_ipv6_module_init(void)
 {
-	return nft_register_expr(&nft_masq_ipv6_type);
+	int ret;
+
+	ret = nft_register_expr(&nft_masq_ipv6_type);
+	if (ret < 0)
+		return ret;
+
+	nf_nat_masquerade_ipv6_register_notifier();
+
+	return ret;
 }
 
 static void __exit nft_masq_ipv6_module_exit(void)
 {
 	nft_unregister_expr(&nft_masq_ipv6_type);
+	nf_nat_masquerade_ipv6_unregister_notifier();
 }
 
 module_init(nft_masq_ipv6_module_init);
-- 
cgit v1.2.3


From efc98d08e1ec4fd131f794370b274dceaf32c958 Mon Sep 17 00:00:00 2001
From: Tom Herbert
Date: Fri, 3 Oct 2014 15:48:08 -0700
Subject: fou: eliminate IPv4,v6 specific GRO functions

This patch removes fou[46]_gro_receive and fou[46]_gro_complete
functions. The v4 or v6 variants were chosen for the UDP offloads
based on the address family of the socket this is not necessary
or correct. Alternatively, this patch adds is_ipv6 to napi_gro_skb.
This is set in udp6_gro_receive and unset in udp4_gro_receive. In
fou_gro_receive the value is used to select the correct inet_offloads
for the protocol of the outer IP header.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  3 +++
 net/ipv4/fou.c            | 48 ++++++++---------------------------------------
 net/ipv4/udp_offload.c    |  1 +
 net/ipv6/udp_offload.c    |  1 +
 4 files changed, 13 insertions(+), 40 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 910fb17ad148..22d54b9b700d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1886,6 +1886,9 @@ struct napi_gro_cb {
 	/* Number of checksums via CHECKSUM_UNNECESSARY */
 	u8	csum_cnt:3;
 
+	/* Used in foo-over-udp, set in udp[46]_gro_receive */
+	u8	is_ipv6:1;
+
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
 
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index dced89fbe480..7e2126a31f2e 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -65,14 +65,15 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
 }
 
 static struct sk_buff **fou_gro_receive(struct sk_buff **head,
-					struct sk_buff *skb,
-					const struct net_offload **offloads)
+					struct sk_buff *skb)
 {
 	const struct net_offload *ops;
 	struct sk_buff **pp = NULL;
 	u8 proto = NAPI_GRO_CB(skb)->proto;
+	const struct net_offload **offloads;
 
 	rcu_read_lock();
+	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
 	ops = rcu_dereference(offloads[proto]);
 	if (!ops || !ops->callbacks.gro_receive)
 		goto out_unlock;
@@ -85,14 +86,15 @@ out_unlock:
 	return pp;
 }
 
-static int fou_gro_complete(struct sk_buff *skb, int nhoff,
-			    const struct net_offload **offloads)
+static int fou_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct net_offload *ops;
 	u8 proto = NAPI_GRO_CB(skb)->proto;
 	int err = -ENOSYS;
+	const struct net_offload **offloads;
 
 	rcu_read_lock();
+	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
 	ops = rcu_dereference(offloads[proto]);
 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
 		goto out_unlock;
@@ -105,28 +107,6 @@ out_unlock:
 	return err;
 }
 
-static struct sk_buff **fou4_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
-{
-	return fou_gro_receive(head, skb, inet_offloads);
-}
-
-static int fou4_gro_complete(struct sk_buff *skb, int nhoff)
-{
-	return fou_gro_complete(skb, nhoff, inet_offloads);
-}
-
-static struct sk_buff **fou6_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
-{
-	return fou_gro_receive(head, skb, inet6_offloads);
-}
-
-static int fou6_gro_complete(struct sk_buff *skb, int nhoff)
-{
-	return fou_gro_complete(skb, nhoff, inet6_offloads);
-}
-
 static int fou_add_to_port_list(struct fou *fou)
 {
 	struct fou *fout;
@@ -199,20 +179,8 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 
 	sk->sk_allocation = GFP_ATOMIC;
 
-	switch (cfg->udp_config.family) {
-	case AF_INET:
-		fou->udp_offloads.callbacks.gro_receive = fou4_gro_receive;
-		fou->udp_offloads.callbacks.gro_complete = fou4_gro_complete;
-		break;
-	case AF_INET6:
-		fou->udp_offloads.callbacks.gro_receive = fou6_gro_receive;
-		fou->udp_offloads.callbacks.gro_complete = fou6_gro_complete;
-		break;
-	default:
-		err = -EPFNOSUPPORT;
-		goto error;
-	}
-
+	fou->udp_offloads.callbacks.gro_receive = fou_gro_receive;
+	fou->udp_offloads.callbacks.gro_complete = fou_gro_complete;
 	fou->udp_offloads.port = cfg->udp_config.local_udp_port;
 	fou->udp_offloads.ipproto = cfg->protocol;
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 8c35f2c939ee..507310ef4b56 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -334,6 +334,7 @@ static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
 		skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
 					     inet_gro_compute_pseudo);
 skip:
+	NAPI_GRO_CB(skb)->is_ipv6 = 0;
 	return udp_gro_receive(head, skb, uh);
 
 flush:
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 8f96988c1db2..6b8f543f6ac6 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -140,6 +140,7 @@ static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
 					     ip6_gro_compute_pseudo);
 
 skip:
+	NAPI_GRO_CB(skb)->is_ipv6 = 1;
 	return udp_gro_receive(head, skb, uh);
 
 flush:
-- 
cgit v1.2.3


From 3be07244b7337760a3269d56b2f4a63e72218648 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel
Date: Thu, 2 Oct 2014 18:26:49 +0200
Subject: ip6_gre: fix flowi6_proto value in xmit path

In xmit path, we build a flowi6 which will be used for the output route lookup.
We are sending a GRE packet, neither IPv4 nor IPv6 encapsulated packet, thus the
protocol should be IPPROTO_GRE.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Reported-by: Matthieu Ternisien d'Ouville <matthieu.tdo@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index f304471477dc..97299d76c1b0 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -782,7 +782,7 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 		encap_limit = t->parms.encap_limit;
 
 	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_IPIP;
+	fl6.flowi6_proto = IPPROTO_GRE;
 
 	dsfield = ipv4_get_dsfield(iph);
 
@@ -832,7 +832,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
 		encap_limit = t->parms.encap_limit;
 
 	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_IPV6;
+	fl6.flowi6_proto = IPPROTO_GRE;
 
 	dsfield = ipv6_get_dsfield(ipv6h);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
-- 
cgit v1.2.3


From 94b2cfe02bfe3f1918d91bd6f498e308c5605cbc Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa
Date: Mon, 6 Oct 2014 19:58:34 +0200
Subject: ipv6: minor fib6 cleanups like type safety, bool conversion, inline
 removal

Also renamed struct fib6_walker_t to fib6_walker and enum fib_walk_state_t
to fib6_walk_state as recommended by Cong Wang.

Cc: Cong Wang <cwang@twopensource.com>
Cc: YOSHIFUJI Hideaki <hideaki@yoshifuji.org>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 18 ++++++++++---
 net/ipv6/ip6_fib.c    | 71 ++++++++++++++++++++++-----------------------------
 2 files changed, 45 insertions(+), 44 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index cf485f9aa563..9221bf4c64f7 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -202,15 +202,25 @@ static inline void ip6_rt_put(struct rt6_info *rt)
 	dst_release(&rt->dst);
 }
 
-struct fib6_walker_t {
+enum fib6_walk_state {
+#ifdef CONFIG_IPV6_SUBTREES
+	FWS_S,
+#endif
+	FWS_L,
+	FWS_R,
+	FWS_C,
+	FWS_U
+};
+
+struct fib6_walker {
 	struct list_head lh;
 	struct fib6_node *root, *node;
 	struct rt6_info *leaf;
-	unsigned char state;
-	unsigned char prune;
+	enum fib6_walk_state state;
+	bool prune;
 	unsigned int skip;
 	unsigned int count;
-	int (*func)(struct fib6_walker_t *);
+	int (*func)(struct fib6_walker *);
 	void *args;
 };
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 97b9fa8de377..e8d7465b1597 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -46,18 +46,8 @@
 
 static struct kmem_cache *fib6_node_kmem __read_mostly;
 
-enum fib_walk_state_t {
-#ifdef CONFIG_IPV6_SUBTREES
-	FWS_S,
-#endif
-	FWS_L,
-	FWS_R,
-	FWS_C,
-	FWS_U
-};
-
-struct fib6_cleaner_t {
-	struct fib6_walker_t w;
+struct fib6_cleaner {
+	struct fib6_walker w;
 	struct net *net;
 	int (*func)(struct rt6_info *, void *arg);
 	void *arg;
@@ -74,8 +64,8 @@ static DEFINE_RWLOCK(fib6_walker_lock);
 static void fib6_prune_clones(struct net *net, struct fib6_node *fn);
 static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
 static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
-static int fib6_walk(struct fib6_walker_t *w);
-static int fib6_walk_continue(struct fib6_walker_t *w);
+static int fib6_walk(struct fib6_walker *w);
+static int fib6_walk_continue(struct fib6_walker *w);
 
 /*
  *	A routing update causes an increase of the serial number on the
@@ -91,20 +81,21 @@ static void fib6_gc_timer_cb(unsigned long arg);
 static LIST_HEAD(fib6_walkers);
 #define FOR_WALKERS(w) list_for_each_entry(w, &fib6_walkers, lh)
 
-static inline void fib6_walker_link(struct fib6_walker_t *w)
+static void fib6_walker_link(struct fib6_walker *w)
 {
 	write_lock_bh(&fib6_walker_lock);
 	list_add(&w->lh, &fib6_walkers);
 	write_unlock_bh(&fib6_walker_lock);
 }
 
-static inline void fib6_walker_unlink(struct fib6_walker_t *w)
+static void fib6_walker_unlink(struct fib6_walker *w)
 {
 	write_lock_bh(&fib6_walker_lock);
 	list_del(&w->lh);
 	write_unlock_bh(&fib6_walker_lock);
 }
-static __inline__ u32 fib6_new_sernum(void)
+
+static u32 fib6_new_sernum(void)
 {
 	u32 n = ++rt_sernum;
 	if ((__s32)n <= 0)
@@ -128,7 +119,7 @@ static __inline__ u32 fib6_new_sernum(void)
 # define BITOP_BE32_SWIZZLE	0
 #endif
 
-static __inline__ __be32 addr_bit_set(const void *token, int fn_bit)
+static __be32 addr_bit_set(const void *token, int fn_bit)
 {
 	const __be32 *addr = token;
 	/*
@@ -142,7 +133,7 @@ static __inline__ __be32 addr_bit_set(const void *token, int fn_bit)
 	       addr[fn_bit >> 5];
 }
 
-static __inline__ struct fib6_node *node_alloc(void)
+static struct fib6_node *node_alloc(void)
 {
 	struct fib6_node *fn;
 
@@ -151,12 +142,12 @@ static __inline__ struct fib6_node *node_alloc(void)
 	return fn;
 }
 
-static __inline__ void node_free(struct fib6_node *fn)
+static void node_free(struct fib6_node *fn)
 {
 	kmem_cache_free(fib6_node_kmem, fn);
 }
 
-static __inline__ void rt6_release(struct rt6_info *rt)
+static void rt6_release(struct rt6_info *rt)
 {
 	if (atomic_dec_and_test(&rt->rt6i_ref))
 		dst_free(&rt->dst);
@@ -267,7 +258,7 @@ static void __net_init fib6_tables_init(struct net *net)
 
 #endif
 
-static int fib6_dump_node(struct fib6_walker_t *w)
+static int fib6_dump_node(struct fib6_walker *w)
 {
 	int res;
 	struct rt6_info *rt;
@@ -287,7 +278,7 @@ static int fib6_dump_node(struct fib6_walker_t *w)
 
 static void fib6_dump_end(struct netlink_callback *cb)
 {
-	struct fib6_walker_t *w = (void *)cb->args[2];
+	struct fib6_walker *w = (void *)cb->args[2];
 
 	if (w) {
 		if (cb->args[4]) {
@@ -310,7 +301,7 @@ static int fib6_dump_done(struct netlink_callback *cb)
 static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
 			   struct netlink_callback *cb)
 {
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	int res;
 
 	w = (void *)cb->args[2];
@@ -355,7 +346,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned int h, s_h;
 	unsigned int e = 0, s_e;
 	struct rt6_rtnl_dump_arg arg;
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	struct fib6_table *tb;
 	struct hlist_head *head;
 	int res = 0;
@@ -627,7 +618,7 @@ insert_above:
 	return ln;
 }
 
-static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt)
+static bool rt6_qualify_for_ecmp(struct rt6_info *rt)
 {
 	return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
 	       RTF_GATEWAY;
@@ -820,7 +811,7 @@ add:
 	return 0;
 }
 
-static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt)
+static void fib6_start_gc(struct net *net, struct rt6_info *rt)
 {
 	if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
 	    (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE)))
@@ -1174,7 +1165,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 	int children;
 	int nstate;
 	struct fib6_node *child, *pn;
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	int iter = 0;
 
 	for (;;) {
@@ -1276,7 +1267,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 			   struct nl_info *info)
 {
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	struct rt6_info *rt = *rtp;
 	struct net *net = info->nl_net;
 
@@ -1414,7 +1405,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
  *	<0  -> walk is terminated by an error.
  */
 
-static int fib6_walk_continue(struct fib6_walker_t *w)
+static int fib6_walk_continue(struct fib6_walker *w)
 {
 	struct fib6_node *fn, *pn;
 
@@ -1498,7 +1489,7 @@ skip:
 	}
 }
 
-static int fib6_walk(struct fib6_walker_t *w)
+static int fib6_walk(struct fib6_walker *w)
 {
 	int res;
 
@@ -1512,11 +1503,11 @@ static int fib6_walk(struct fib6_walker_t *w)
 	return res;
 }
 
-static int fib6_clean_node(struct fib6_walker_t *w)
+static int fib6_clean_node(struct fib6_walker *w)
 {
 	int res;
 	struct rt6_info *rt;
-	struct fib6_cleaner_t *c = container_of(w, struct fib6_cleaner_t, w);
+	struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w);
 	struct nl_info info = {
 		.nl_net = c->net,
 	};
@@ -1554,9 +1545,9 @@ static int fib6_clean_node(struct fib6_walker_t *w)
 
 static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 			    int (*func)(struct rt6_info *, void *arg),
-			    int prune, void *arg)
+			    bool prune, void *arg)
 {
-	struct fib6_cleaner_t c;
+	struct fib6_cleaner c;
 
 	c.w.root = root;
 	c.w.func = fib6_clean_node;
@@ -1583,7 +1574,7 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
 			write_lock_bh(&table->tb6_lock);
 			fib6_clean_tree(net, &table->tb6_root,
-					func, 0, arg);
+					func, false, arg);
 			write_unlock_bh(&table->tb6_lock);
 		}
 	}
@@ -1602,7 +1593,7 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg)
 
 static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
 {
-	fib6_clean_tree(net, fn, fib6_prune_clone, 1, NULL);
+	fib6_clean_tree(net, fn, fib6_prune_clone, true, NULL);
 }
 
 static int fib6_update_sernum(struct rt6_info *rt, void *arg)
@@ -1828,7 +1819,7 @@ void fib6_gc_cleanup(void)
 
 struct ipv6_route_iter {
 	struct seq_net_private p;
-	struct fib6_walker_t w;
+	struct fib6_walker w;
 	loff_t skip;
 	struct fib6_table *tbl;
 	__u32 sernum;
@@ -1859,7 +1850,7 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int ipv6_route_yield(struct fib6_walker_t *w)
+static int ipv6_route_yield(struct fib6_walker *w)
 {
 	struct ipv6_route_iter *iter = w->args;
 
@@ -1980,7 +1971,7 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos)
 
 static bool ipv6_route_iter_active(struct ipv6_route_iter *iter)
 {
-	struct fib6_walker_t *w = &iter->w;
+	struct fib6_walker *w = &iter->w;
 	return w->node && !(w->state == FWS_U && w->node == w->root);
 }
 
-- 
cgit v1.2.3


From 42b18706469a02c1f84375ac0ee2f30f28d85d4c Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa
Date: Mon, 6 Oct 2014 19:58:35 +0200
Subject: ipv6: make rt_sernum atomic and serial number fields ordinary ints

Cc: YOSHIFUJI Hideaki <hideaki@yoshifuji.org>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  2 +-
 net/ipv6/ip6_fib.c    | 23 +++++++++++++----------
 2 files changed, 14 insertions(+), 11 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 9221bf4c64f7..8eea35d32a75 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -64,7 +64,7 @@ struct fib6_node {
 
 	__u16			fn_bit;		/* bit key */
 	__u16			fn_flags;
-	__u32			fn_sernum;
+	int			fn_sernum;
 	struct rt6_info		*rr_ptr;
 };
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e8d7465b1597..332f1e0ff8e2 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -74,7 +74,7 @@ static int fib6_walk_continue(struct fib6_walker *w);
  *	result of redirects, path MTU changes, etc.
  */
 
-static __u32 rt_sernum;
+static atomic_t rt_sernum = ATOMIC_INIT(1);
 
 static void fib6_gc_timer_cb(unsigned long arg);
 
@@ -95,12 +95,15 @@ static void fib6_walker_unlink(struct fib6_walker *w)
 	write_unlock_bh(&fib6_walker_lock);
 }
 
-static u32 fib6_new_sernum(void)
+static int fib6_new_sernum(void)
 {
-	u32 n = ++rt_sernum;
-	if ((__s32)n <= 0)
-		rt_sernum = n = 1;
-	return n;
+	int new, old;
+
+	do {
+		old = atomic_read(&rt_sernum);
+		new = old < INT_MAX ? old + 1 : 1;
+	} while (atomic_cmpxchg(&rt_sernum, old, new) != old);
+	return new;
 }
 
 /*
@@ -421,7 +424,7 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 	struct rt6key *key;
 	int	bit;
 	__be32	dir = 0;
-	__u32	sernum = fib6_new_sernum();
+	int	sernum = fib6_new_sernum();
 
 	RT6_TRACE("fib6_add_1\n");
 
@@ -1598,7 +1601,7 @@ static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
 
 static int fib6_update_sernum(struct rt6_info *rt, void *arg)
 {
-	__u32 sernum = *(__u32 *)arg;
+	int sernum = *(int *)arg;
 
 	if (rt->rt6i_node &&
 	    rt->rt6i_node->fn_sernum != sernum)
@@ -1609,7 +1612,7 @@ static int fib6_update_sernum(struct rt6_info *rt, void *arg)
 
 static void fib6_flush_trees(struct net *net)
 {
-	__u32 new_sernum = fib6_new_sernum();
+	int new_sernum = fib6_new_sernum();
 
 	fib6_clean_all(net, fib6_update_sernum, &new_sernum);
 }
@@ -1822,7 +1825,7 @@ struct ipv6_route_iter {
 	struct fib6_walker w;
 	loff_t skip;
 	struct fib6_table *tbl;
-	__u32 sernum;
+	int sernum;
 };
 
 static int ipv6_route_seq_show(struct seq_file *seq, void *v)
-- 
cgit v1.2.3


From c8c4d42a6b46ea9f81816c47ac8d6ae25cf533fc Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa
Date: Mon, 6 Oct 2014 19:58:36 +0200
Subject: ipv6: only generate one new serial number per fib mutation

Cc: YOSHIFUJI Hideaki <hideaki@yoshifuji.org>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 332f1e0ff8e2..be9cb09b05f7 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -417,14 +417,13 @@ out:
 static struct fib6_node *fib6_add_1(struct fib6_node *root,
 				     struct in6_addr *addr, int plen,
 				     int offset, int allow_create,
-				     int replace_required)
+				     int replace_required, int sernum)
 {
 	struct fib6_node *fn, *in, *ln;
 	struct fib6_node *pn = NULL;
 	struct rt6key *key;
 	int	bit;
 	__be32	dir = 0;
-	int	sernum = fib6_new_sernum();
 
 	RT6_TRACE("fib6_add_1\n");
 
@@ -842,6 +841,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 	int err = -ENOMEM;
 	int allow_create = 1;
 	int replace_required = 0;
+	int sernum = fib6_new_sernum();
 
 	if (info->nlh) {
 		if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -854,7 +854,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 
 	fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen,
 			offsetof(struct rt6_info, rt6i_dst), allow_create,
-			replace_required);
+			replace_required, sernum);
 	if (IS_ERR(fn)) {
 		err = PTR_ERR(fn);
 		fn = NULL;
@@ -888,14 +888,14 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 			sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
 			atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
 			sfn->fn_flags = RTN_ROOT;
-			sfn->fn_sernum = fib6_new_sernum();
+			sfn->fn_sernum = sernum;
 
 			/* Now add the first leaf node to new subtree */
 
 			sn = fib6_add_1(sfn, &rt->rt6i_src.addr,
 					rt->rt6i_src.plen,
 					offsetof(struct rt6_info, rt6i_src),
-					allow_create, replace_required);
+					allow_create, replace_required, sernum);
 
 			if (IS_ERR(sn)) {
 				/* If it is failed, discard just allocated
@@ -914,7 +914,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 			sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr,
 					rt->rt6i_src.plen,
 					offsetof(struct rt6_info, rt6i_src),
-					allow_create, replace_required);
+					allow_create, replace_required, sernum);
 
 			if (IS_ERR(sn)) {
 				err = PTR_ERR(sn);
-- 
cgit v1.2.3


From 812918c464eca0e8c145f975932ca5020e9c05cb Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa
Date: Mon, 6 Oct 2014 19:58:37 +0200
Subject: ipv6: make fib6 serial number per namespace

Try to reduce number of possible fn_sernum mutation by constraining them
to their namespace.

Also remove rt_genid which I forgot to remove in 705f1c869d577c ("ipv6:
remove rt6i_genid").

Cc: YOSHIFUJI Hideaki <hideaki@yoshifuji.org>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv6.h |  2 +-
 net/ipv6/af_inet6.c      |  2 +-
 net/ipv6/ip6_fib.c       | 13 ++++++-------
 3 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index eade27adecf3..69ae41f2098c 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -76,7 +76,7 @@ struct netns_ipv6 {
 #endif
 #endif
 	atomic_t		dev_addr_genid;
-	atomic_t		rt_genid;
+	atomic_t		fib6_sernum;
 };
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 34f726f59814..e8c4400f23e9 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -766,7 +766,7 @@ static int __net_init inet6_net_init(struct net *net)
 	net->ipv6.sysctl.icmpv6_time = 1*HZ;
 	net->ipv6.sysctl.flowlabel_consistency = 1;
 	net->ipv6.sysctl.auto_flowlabels = 0;
-	atomic_set(&net->ipv6.rt_genid, 0);
+	atomic_set(&net->ipv6.fib6_sernum, 1);
 
 	err = ipv6_init_mibs(net);
 	if (err)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index be9cb09b05f7..6f9beb1f2861 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -74,8 +74,6 @@ static int fib6_walk_continue(struct fib6_walker *w);
  *	result of redirects, path MTU changes, etc.
  */
 
-static atomic_t rt_sernum = ATOMIC_INIT(1);
-
 static void fib6_gc_timer_cb(unsigned long arg);
 
 static LIST_HEAD(fib6_walkers);
@@ -95,14 +93,15 @@ static void fib6_walker_unlink(struct fib6_walker *w)
 	write_unlock_bh(&fib6_walker_lock);
 }
 
-static int fib6_new_sernum(void)
+static int fib6_new_sernum(struct net *net)
 {
 	int new, old;
 
 	do {
-		old = atomic_read(&rt_sernum);
+		old = atomic_read(&net->ipv6.fib6_sernum);
 		new = old < INT_MAX ? old + 1 : 1;
-	} while (atomic_cmpxchg(&rt_sernum, old, new) != old);
+	} while (atomic_cmpxchg(&net->ipv6.fib6_sernum,
+				old, new) != old);
 	return new;
 }
 
@@ -841,7 +840,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 	int err = -ENOMEM;
 	int allow_create = 1;
 	int replace_required = 0;
-	int sernum = fib6_new_sernum();
+	int sernum = fib6_new_sernum(info->nl_net);
 
 	if (info->nlh) {
 		if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -1612,7 +1611,7 @@ static int fib6_update_sernum(struct rt6_info *rt, void *arg)
 
 static void fib6_flush_trees(struct net *net)
 {
-	int new_sernum = fib6_new_sernum();
+	int new_sernum = fib6_new_sernum(net);
 
 	fib6_clean_all(net, fib6_update_sernum, &new_sernum);
 }
-- 
cgit v1.2.3


From 327571cb100cad587c9eda351e7a2d182466873b Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa
Date: Mon, 6 Oct 2014 19:58:38 +0200
Subject: ipv6: don't walk node's leaf during serial number update

Cc: YOSHIFUJI Hideaki <hideaki@yoshifuji.org>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 47 ++++++++++++++++++++++++++++++-----------------
 1 file changed, 30 insertions(+), 17 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 6f9beb1f2861..b2d1838897c9 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -50,6 +50,7 @@ struct fib6_cleaner {
 	struct fib6_walker w;
 	struct net *net;
 	int (*func)(struct rt6_info *, void *arg);
+	int sernum;
 	void *arg;
 };
 
@@ -105,6 +106,10 @@ static int fib6_new_sernum(struct net *net)
 	return new;
 }
 
+enum {
+	FIB6_NO_SERNUM_CHANGE = 0,
+};
+
 /*
  *	Auxiliary address test functions for the radix tree.
  *
@@ -1514,6 +1519,16 @@ static int fib6_clean_node(struct fib6_walker *w)
 		.nl_net = c->net,
 	};
 
+	if (c->sernum != FIB6_NO_SERNUM_CHANGE &&
+	    w->node->fn_sernum != c->sernum)
+		w->node->fn_sernum = c->sernum;
+
+	if (!c->func) {
+		WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE);
+		w->leaf = NULL;
+		return 0;
+	}
+
 	for (rt = w->leaf; rt; rt = rt->dst.rt6_next) {
 		res = c->func(rt, c->arg);
 		if (res < 0) {
@@ -1547,7 +1562,7 @@ static int fib6_clean_node(struct fib6_walker *w)
 
 static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 			    int (*func)(struct rt6_info *, void *arg),
-			    bool prune, void *arg)
+			    bool prune, int sernum, void *arg)
 {
 	struct fib6_cleaner c;
 
@@ -1557,14 +1572,16 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 	c.w.count = 0;
 	c.w.skip = 0;
 	c.func = func;
+	c.sernum = sernum;
 	c.arg = arg;
 	c.net = net;
 
 	fib6_walk(&c.w);
 }
 
-void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
-		    void *arg)
+static void __fib6_clean_all(struct net *net,
+			     int (*func)(struct rt6_info *, void *),
+			     int sernum, void *arg)
 {
 	struct fib6_table *table;
 	struct hlist_head *head;
@@ -1576,13 +1593,19 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
 			write_lock_bh(&table->tb6_lock);
 			fib6_clean_tree(net, &table->tb6_root,
-					func, false, arg);
+					func, false, sernum, arg);
 			write_unlock_bh(&table->tb6_lock);
 		}
 	}
 	rcu_read_unlock();
 }
 
+void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *),
+		    void *arg)
+{
+	__fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
+}
+
 static int fib6_prune_clone(struct rt6_info *rt, void *arg)
 {
 	if (rt->rt6i_flags & RTF_CACHE) {
@@ -1595,25 +1618,15 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg)
 
 static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
 {
-	fib6_clean_tree(net, fn, fib6_prune_clone, true, NULL);
-}
-
-static int fib6_update_sernum(struct rt6_info *rt, void *arg)
-{
-	int sernum = *(int *)arg;
-
-	if (rt->rt6i_node &&
-	    rt->rt6i_node->fn_sernum != sernum)
-		rt->rt6i_node->fn_sernum = sernum;
-
-	return 0;
+	fib6_clean_tree(net, fn, fib6_prune_clone, true,
+			FIB6_NO_SERNUM_CHANGE, NULL);
 }
 
 static void fib6_flush_trees(struct net *net)
 {
 	int new_sernum = fib6_new_sernum(net);
 
-	fib6_clean_all(net, fib6_update_sernum, &new_sernum);
+	__fib6_clean_all(net, NULL, new_sernum, NULL);
 }
 
 /*
-- 
cgit v1.2.3


From 0287587884b15041203b3a362d485e1ab1f24445 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Sun, 5 Oct 2014 18:38:35 -0700
Subject: net: better IFF_XMIT_DST_RELEASE support

Testing xmit_more support with netperf and connected UDP sockets,
I found strange dst refcount false sharing.

Current handling of IFF_XMIT_DST_RELEASE is not optimal.

Dropping dst in validate_xmit_skb() is certainly too late in case
packet was queued by cpu X but dequeued by cpu Y

The logical point to take care of drop/force is in __dev_queue_xmit()
before even taking qdisc lock.

As Julian Anastasov pointed out, need for skb_dst() might come from some
packet schedulers or classifiers.

This patch adds new helper to cleanly express needs of various drivers
or qdiscs/classifiers.

Drivers that need skb_dst() in their ndo_start_xmit() should call
following helper in their setup instead of the prior :

	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
->
	netif_keep_dst(dev);

Instead of using a single bit, we use two bits, one being
eventually rebuilt in bonding/team drivers.

The other one, is permanent and blocks IFF_XMIT_DST_RELEASE being
rebuilt in bonding/team. Eventually, we could add something
smarter later.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/ulp/ipoib/ipoib_main.c |  2 +-
 drivers/net/appletalk/ipddp.c             |  2 +-
 drivers/net/bonding/bond_main.c           |  9 ++++++---
 drivers/net/eql.c                         |  2 +-
 drivers/net/ifb.c                         |  3 ++-
 drivers/net/loopback.c                    |  2 +-
 drivers/net/macvlan.c                     |  3 ++-
 drivers/net/ppp/ppp_generic.c             |  2 +-
 drivers/net/team/team.c                   |  8 +++++---
 drivers/net/vxlan.c                       |  2 +-
 drivers/net/wan/hdlc_fr.c                 |  2 +-
 drivers/s390/net/qeth_l3_main.c           |  2 +-
 include/linux/netdevice.h                 |  8 ++++++++
 net/8021q/vlan_dev.c                      |  3 ++-
 net/atm/clip.c                            |  2 +-
 net/core/dev.c                            | 19 +++++++++----------
 net/ipv4/ip_gre.c                         |  2 +-
 net/ipv4/ip_vti.c                         |  2 +-
 net/ipv4/ipip.c                           |  2 +-
 net/ipv6/ip6_gre.c                        |  2 +-
 net/ipv6/ip6_tunnel.c                     |  2 +-
 net/ipv6/ip6_vti.c                        |  2 +-
 net/ipv6/sit.c                            |  2 +-
 net/sched/cls_flow.c                      |  2 ++
 net/sched/cls_route.c                     |  1 +
 net/sched/sch_generic.c                   |  3 ---
 net/sched/sch_teql.c                      |  2 +-
 27 files changed, 54 insertions(+), 39 deletions(-)

(limited to 'net/ipv6')

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 13e6e0431592..58b5aa3b6f2d 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1364,7 +1364,7 @@ void ipoib_setup(struct net_device *dev)
 	dev->tx_queue_len	 = ipoib_sendq_size * 2;
 	dev->features		 = (NETIF_F_VLAN_CHALLENGED	|
 				    NETIF_F_HIGHDMA);
-	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 
 	memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN);
 
diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c
index 10d0dba572c2..e90c6a7333d7 100644
--- a/drivers/net/appletalk/ipddp.c
+++ b/drivers/net/appletalk/ipddp.c
@@ -74,7 +74,7 @@ static struct net_device * __init ipddp_init(void)
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	strcpy(dev->name, "ipddp%d");
 
 	if (version_printed++ == 0)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3ad5413d4f57..c9ac06cfe6b7 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1002,7 +1002,8 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 
 static void bond_compute_features(struct bonding *bond)
 {
-	unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE;
+	unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
+					IFF_XMIT_DST_RELEASE_PERM;
 	netdev_features_t vlan_features = BOND_VLAN_FEATURES;
 	netdev_features_t enc_features  = BOND_ENC_FEATURES;
 	struct net_device *bond_dev = bond->dev;
@@ -1038,8 +1039,10 @@ done:
 	bond_dev->gso_max_segs = gso_max_segs;
 	netif_set_gso_max_size(bond_dev, gso_max_size);
 
-	flags = bond_dev->priv_flags & ~IFF_XMIT_DST_RELEASE;
-	bond_dev->priv_flags = flags | dst_release_flag;
+	bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	if ((bond_dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) &&
+	    dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
+		bond_dev->priv_flags |= IFF_XMIT_DST_RELEASE;
 
 	netdev_change_features(bond_dev);
 }
diff --git a/drivers/net/eql.c b/drivers/net/eql.c
index 957e5c0cede3..a10ad74cc8d2 100644
--- a/drivers/net/eql.c
+++ b/drivers/net/eql.c
@@ -199,7 +199,7 @@ static void __init eql_setup(struct net_device *dev)
 
 	dev->type       	= ARPHRD_SLIP;
 	dev->tx_queue_len 	= 5;		/* Hands them off fast */
-	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 static int eql_open(struct net_device *dev)
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index d2d4a3d2237f..34f846b4bd05 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -185,7 +185,8 @@ static void ifb_setup(struct net_device *dev)
 
 	dev->flags |= IFF_NOARP;
 	dev->flags &= ~IFF_MULTICAST;
-	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	netif_keep_dst(dev);
 	eth_hw_addr_random(dev);
 }
 
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 8f2262540561..c76283c2f84a 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -169,7 +169,7 @@ static void loopback_setup(struct net_device *dev)
 	dev->type		= ARPHRD_LOOPBACK;	/* 0x0001*/
 	dev->flags		= IFF_LOOPBACK;
 	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE;
-	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	dev->hw_features	= NETIF_F_ALL_TSO | NETIF_F_UFO;
 	dev->features 		= NETIF_F_SG | NETIF_F_FRAGLIST
 		| NETIF_F_ALL_TSO
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index e8a453f1b458..38b4fae61f04 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1025,7 +1025,8 @@ void macvlan_common_setup(struct net_device *dev)
 {
 	ether_setup(dev);
 
-	dev->priv_flags	       &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+	dev->priv_flags	       &= ~IFF_TX_SKB_SHARING;
+	netif_keep_dst(dev);
 	dev->priv_flags	       |= IFF_UNICAST_FLT;
 	dev->netdev_ops		= &macvlan_netdev_ops;
 	dev->destructor		= free_netdev;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index fa0d71727894..80e6f3430f65 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1103,7 +1103,7 @@ static void ppp_setup(struct net_device *dev)
 	dev->type = ARPHRD_PPP;
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
 	dev->features |= NETIF_F_NETNS_LOCAL;
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 /*
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 2277c3679a51..a94a9df3e6bd 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -970,7 +970,8 @@ static void __team_compute_features(struct team *team)
 	struct team_port *port;
 	u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
 	unsigned short max_hard_header_len = ETH_HLEN;
-	unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE;
+	unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
+					IFF_XMIT_DST_RELEASE_PERM;
 
 	list_for_each_entry(port, &team->port_list, list) {
 		vlan_features = netdev_increment_features(vlan_features,
@@ -985,8 +986,9 @@ static void __team_compute_features(struct team *team)
 	team->dev->vlan_features = vlan_features;
 	team->dev->hard_header_len = max_hard_header_len;
 
-	flags = team->dev->priv_flags & ~IFF_XMIT_DST_RELEASE;
-	team->dev->priv_flags = flags | dst_release_flag;
+	team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
+		team->dev->priv_flags |= IFF_XMIT_DST_RELEASE;
 
 	netdev_change_features(team->dev);
 }
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2af795d6ba05..2a51e6e48e1e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2193,7 +2193,7 @@ static void vxlan_setup(struct net_device *dev)
 	dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
 	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
-	dev->priv_flags	&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	INIT_LIST_HEAD(&vxlan->next);
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index e5c7e6165a4b..3ebed1c40abb 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -1047,7 +1047,7 @@ static void pvc_setup(struct net_device *dev)
 	dev->flags = IFF_POINTOPOINT;
 	dev->hard_header_len = 10;
 	dev->addr_len = 2;
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 static const struct net_device_ops pvc_ops = {
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index f8427a2c4840..afebb9709763 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3306,7 +3306,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 	card->dev->features |=	NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
-	card->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(card->dev);
 	card->dev->gso_max_size = 15 * PAGE_SIZE;
 
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2df86f50261c..3a4315b39d20 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1206,6 +1206,7 @@ enum netdev_priv_flags {
 	IFF_SUPP_NOFCS			= 1<<19,
 	IFF_LIVE_ADDR_CHANGE		= 1<<20,
 	IFF_MACVLAN			= 1<<21,
+	IFF_XMIT_DST_RELEASE_PERM	= 1<<22,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1230,6 +1231,7 @@ enum netdev_priv_flags {
 #define IFF_SUPP_NOFCS			IFF_SUPP_NOFCS
 #define IFF_LIVE_ADDR_CHANGE		IFF_LIVE_ADDR_CHANGE
 #define IFF_MACVLAN			IFF_MACVLAN
+#define IFF_XMIT_DST_RELEASE_PERM	IFF_XMIT_DST_RELEASE_PERM
 
 /**
  *	struct net_device - The DEVICE structure.
@@ -3588,6 +3590,12 @@ static inline bool netif_supports_nofcs(struct net_device *dev)
 	return dev->priv_flags & IFF_SUPP_NOFCS;
 }
 
+/* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
+static inline void netif_keep_dst(struct net_device *dev)
+{
+	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM);
+}
+
 extern struct pernet_operations __net_initdata loopback_net_ops;
 
 /* Logging, debugging and troubleshooting/diagnostic helpers. */
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 35a6b6b15e8a..0d441ec8763e 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -799,7 +799,8 @@ void vlan_setup(struct net_device *dev)
 	ether_setup(dev);
 
 	dev->priv_flags		|= IFF_802_1Q_VLAN;
-	dev->priv_flags		&= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+	dev->priv_flags		&= ~IFF_TX_SKB_SHARING;
+	netif_keep_dst(dev);
 	dev->tx_queue_len	= 0;
 
 	dev->netdev_ops		= &vlan_netdev_ops;
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 1d9eaa4f041a..17e55dfecbe2 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -501,7 +501,7 @@ static void clip_setup(struct net_device *dev)
 	/* without any more elaborate queuing. 100 is a reasonable */
 	/* compromise between decent burst-tolerance and protection */
 	/* against memory hogs. */
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 static int clip_create(int number)
diff --git a/net/core/dev.c b/net/core/dev.c
index a63b8c43c1b6..3c5bdaa44486 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2665,12 +2665,6 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 	if (skb->next)
 		return skb;
 
-	/* If device doesn't need skb->dst, release it right now while
-	 * its hot in this cpu cache
-	 */
-	if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
-		skb_dst_drop(skb);
-
 	features = netif_skb_features(skb);
 	skb = validate_xmit_vlan(skb, features);
 	if (unlikely(!skb))
@@ -2811,8 +2805,6 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 		 * waiting to be sent out; and the qdisc is not running -
 		 * xmit the skb directly.
 		 */
-		if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
-			skb_dst_force(skb);
 
 		qdisc_bstats_update(q, skb);
 
@@ -2827,7 +2819,6 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 		rc = NET_XMIT_SUCCESS;
 	} else {
-		skb_dst_force(skb);
 		rc = q->enqueue(skb, q) & NET_XMIT_MASK;
 		if (qdisc_run_begin(q)) {
 			if (unlikely(contended)) {
@@ -2924,6 +2915,14 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 
 	skb_update_prio(skb);
 
+	/* If device/qdisc don't need skb->dst, release it right now while
+	 * its hot in this cpu cache.
+	 */
+	if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
+		skb_dst_drop(skb);
+	else
+		skb_dst_force(skb);
+
 	txq = netdev_pick_tx(dev, skb, accel_priv);
 	q = rcu_dereference_bh(txq->qdisc);
 
@@ -6674,7 +6673,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	INIT_LIST_HEAD(&dev->adj_list.lower);
 	INIT_LIST_HEAD(&dev->all_adj_list.upper);
 	INIT_LIST_HEAD(&dev->all_adj_list.lower);
-	dev->priv_flags = IFF_XMIT_DST_RELEASE;
+	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
 	dev->num_tx_queues = txqs;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 0485ef18d254..12055fdbe716 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -510,7 +510,7 @@ static int ipgre_tunnel_init(struct net_device *dev)
 	memcpy(dev->broadcast, &iph->daddr, 4);
 
 	dev->flags		= IFF_NOARP;
-	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	dev->addr_len		= 4;
 
 	if (iph->daddr) {
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index e453cb724a95..3e861011e4a3 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -364,7 +364,7 @@ static int vti_tunnel_init(struct net_device *dev)
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
-	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 
 	return ip_tunnel_init(dev);
 }
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index ea88ab3102a8..37096d64730e 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -289,7 +289,7 @@ static void ipip_tunnel_setup(struct net_device *dev)
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
-	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 
 	dev->features		|= IPIP_FEATURES;
 	dev->hw_features	|= IPIP_FEATURES;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 74b677916a70..de3b1c86b8d3 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1242,7 +1242,7 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
 	dev->flags |= IFF_NOARP;
 	dev->iflink = 0;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 static int ip6gre_tunnel_init(struct net_device *dev)
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index d3e8888ad611..9409887fb664 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1493,7 +1493,7 @@ static void ip6_tnl_dev_setup(struct net_device *dev)
 		dev->mtu -= 8;
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	/* This perm addr will be used as interface identifier by IPv6 */
 	dev->addr_assign_type = NET_ADDR_RANDOM;
 	eth_random_addr(dev->perm_addr);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 5833a2244467..d440bb585524 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -807,7 +807,7 @@ static void vti6_dev_setup(struct net_device *dev)
 	dev->mtu = ETH_DATA_LEN;
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 /**
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 0d4e27466f82..6eab37cf5345 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1364,7 +1364,7 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	dev->hard_header_len	= LL_MAX_HEADER + t_hlen;
 	dev->mtu		= ETH_DATA_LEN - t_hlen;
 	dev->flags		= IFF_NOARP;
-	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index a5d2b20db560..4ac515f2a6ce 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -493,6 +493,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 	tcf_exts_change(tp, &fnew->exts, &e);
 	tcf_em_tree_change(tp, &fnew->ematches, &t);
 
+	netif_keep_dst(qdisc_dev(tp->q));
+
 	if (tb[TCA_FLOW_KEYS]) {
 		fnew->keymask = keymask;
 		fnew->nkeys   = nkeys;
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 6f22baae0afa..109a329b7198 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -524,6 +524,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 		if (f->handle < f1->handle)
 			break;
 
+	netif_keep_dst(qdisc_dev(tp->q));
 	rcu_assign_pointer(f->next, f1);
 	rcu_assign_pointer(*fp, f);
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 2b349a4de3c8..38d58e6cef07 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -47,7 +47,6 @@ EXPORT_SYMBOL(default_qdisc_ops);
 
 static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 {
-	skb_dst_force(skb);
 	q->gso_skb = skb;
 	q->qstats.requeues++;
 	q->q.qlen++;	/* it's still part of the queue */
@@ -218,8 +217,6 @@ static inline int qdisc_restart(struct Qdisc *q)
 	if (unlikely(!skb))
 		return 0;
 
-	WARN_ON_ONCE(skb_dst_is_noref(skb));
-
 	root_lock = qdisc_lock(q);
 	dev = qdisc_dev(q);
 	txq = skb_get_tx_queue(dev, skb);
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 5cd291bd00e4..6ada42396a24 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -470,7 +470,7 @@ static __init void teql_master_setup(struct net_device *dev)
 	dev->tx_queue_len	= 100;
 	dev->flags		= IFF_NOARP;
 	dev->hard_header_len	= LL_MAX_HEADER;
-	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 static LIST_HEAD(master_dev_list);
-- 
cgit v1.2.3


From ea85a0a2dc7263de733b7d1d13a433d35fcf36f7 Mon Sep 17 00:00:00 2001
From: David S. Miller
Date: Tue, 7 Oct 2014 16:33:53 -0400
Subject: ipv6: Do not warn for informational ICMP messages, regardless of
 type.

There is no reason to emit a log message for these.

Based upon a suggestion from Hannes Frederic Sowa.

Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
 net/ipv6/icmp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 141e1f3ab74e..97ae70077a4f 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -777,12 +777,12 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		break;
 
 	default:
-		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6: msg of unknown type\n");
-
 		/* informational */
 		if (type & ICMPV6_INFOMSG_MASK)
 			break;
 
+		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6: msg of unknown type\n");
+
 		/*
 		 * error of unknown type.
 		 * must pass to upper level
-- 
cgit v1.2.3