From 7f5c6d4f665bb57a19a34ce1fb16cc708c04f219 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Mon, 4 Apr 2011 17:04:03 +0200
Subject: netfilter: get rid of atomic ops in fast path

We currently use a percpu spinlock to 'protect' rule bytes/packets
counters, after various attempts to use RCU instead.

Lately we added a seqlock so that get_counters() can run without
blocking BH or 'writers'. But we really only need the seqcount in it.

Spinlock itself is only locked by the current/owner cpu, so we can
remove it completely.

This cleanups api, using correct 'writer' vs 'reader' semantic.

At replace time, the get_counters() call makes sure all cpus are done
using the old table.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 net/ipv6/netfilter/ip6_tables.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 0b2af9b85cecd..ec7cf579cdd46 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -340,6 +340,7 @@ ip6t_do_table(struct sk_buff *skb,
 	unsigned int *stackptr, origptr, cpu;
 	const struct xt_table_info *private;
 	struct xt_action_param acpar;
+	unsigned int addend;
 
 	/* Initialization */
 	indev = in ? in->name : nulldevname;
@@ -358,7 +359,8 @@ ip6t_do_table(struct sk_buff *skb,
 
 	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
 
-	xt_info_rdlock_bh();
+	local_bh_disable();
+	addend = xt_write_recseq_begin();
 	private = table->private;
 	cpu        = smp_processor_id();
 	table_base = private->entries[cpu];
@@ -442,7 +444,9 @@ ip6t_do_table(struct sk_buff *skb,
 	} while (!acpar.hotdrop);
 
 	*stackptr = origptr;
-	xt_info_rdunlock_bh();
+
+ 	xt_write_recseq_end(addend);
+ 	local_bh_enable();
 
 #ifdef DEBUG_ALLOW_ALL
 	return NF_ACCEPT;
@@ -899,7 +903,7 @@ get_counters(const struct xt_table_info *t,
 	unsigned int i;
 
 	for_each_possible_cpu(cpu) {
-		seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock;
+		seqcount_t *s = &per_cpu(xt_recseq, cpu);
 
 		i = 0;
 		xt_entry_foreach(iter, t->entries[cpu], t->size) {
@@ -907,10 +911,10 @@ get_counters(const struct xt_table_info *t,
 			unsigned int start;
 
 			do {
-				start = read_seqbegin(lock);
+				start = read_seqcount_begin(s);
 				bcnt = iter->counters.bcnt;
 				pcnt = iter->counters.pcnt;
-			} while (read_seqretry(lock, start));
+			} while (read_seqcount_retry(s, start));
 
 			ADD_COUNTER(counters[i], bcnt, pcnt);
 			++i;
@@ -1325,6 +1329,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
 	int ret = 0;
 	const void *loc_cpu_entry;
 	struct ip6t_entry *iter;
+	unsigned int addend;
 #ifdef CONFIG_COMPAT
 	struct compat_xt_counters_info compat_tmp;
 
@@ -1381,13 +1386,13 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
 	i = 0;
 	/* Choose the copy that is on our node */
 	curcpu = smp_processor_id();
-	xt_info_wrlock(curcpu);
+	addend = xt_write_recseq_begin();
 	loc_cpu_entry = private->entries[curcpu];
 	xt_entry_foreach(iter, loc_cpu_entry, private->size) {
 		ADD_COUNTER(iter->counters, paddc[i].bcnt, paddc[i].pcnt);
 		++i;
 	}
-	xt_info_wrunlock(curcpu);
+	xt_write_recseq_end(addend);
 
  unlock_up_free:
 	local_bh_enable();
-- 
cgit v1.2.3


From bd015928bb1713691068c4d0d159afccbaf0f8c0 Mon Sep 17 00:00:00 2001
From: Daniel Walter <sahne@0x90.at>
Date: Wed, 13 Apr 2011 21:09:25 +0000
Subject: ipv6: ignore looped-back NA while dad is running

[ipv6] Ignore looped-back NAs while in Duplicate Address Detection

If we send an unsolicited NA shortly after bringing up an
IPv6 address, the duplicate address detection algorithm
fails and the ip stays in tentative mode forever.
This is due a missing check if the NA is looped-back to us.

Signed-off-by: Daniel Walter <dwalter@barracuda.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ndisc.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 92f952d093db6..f057ff312840a 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -945,9 +945,10 @@ static void ndisc_recv_na(struct sk_buff *skb)
 	}
 	ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1);
 	if (ifp) {
-		if (ifp->flags & IFA_F_TENTATIVE) {
-			addrconf_dad_failure(ifp);
-			return;
+		if (skb->pkt_type != PACKET_LOOPBACK
+		    && (ifp->flags & IFA_F_TENTATIVE)) {
+				addrconf_dad_failure(ifp);
+				return;
 		}
 		/* What should we make now? The advertisement
 		   is invalid, but ndisc specs say nothing
-- 
cgit v1.2.3


From c3968a857a6b6c3d2ef4ead35776b055fb664d74 Mon Sep 17 00:00:00 2001
From: Daniel Walter <sahne@0x90.at>
Date: Wed, 13 Apr 2011 21:10:57 +0000
Subject: ipv6: RTA_PREFSRC support for ipv6 route source address selection

[ipv6] Add support for RTA_PREFSRC

This patch allows a user to select the preferred source address
for a specific IPv6-Route. It can be set via a netlink message
setting RTA_PREFSRC to a valid IPv6 address which must be
up on the device the route will be bound to.

Signed-off-by: Daniel Walter <dwalter@barracuda.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h   |  2 ++
 include/net/ip6_route.h |  7 +++++
 net/ipv6/addrconf.c     |  2 ++
 net/ipv6/ip6_output.c   |  8 +++---
 net/ipv6/route.c        | 72 ++++++++++++++++++++++++++++++++++++++++++++++---
 5 files changed, 84 insertions(+), 7 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index bc3cde0a810c9..98348d53b2b60 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -42,6 +42,7 @@ struct fib6_config {
 
 	struct in6_addr	fc_dst;
 	struct in6_addr	fc_src;
+	struct in6_addr	fc_prefsrc;
 	struct in6_addr	fc_gateway;
 
 	unsigned long	fc_expires;
@@ -107,6 +108,7 @@ struct rt6_info {
 	struct rt6key			rt6i_dst ____cacheline_aligned_in_smp;
 	u32				rt6i_flags;
 	struct rt6key			rt6i_src;
+	struct rt6key			rt6i_prefsrc;
 	u32				rt6i_metric;
 	u32				rt6i_peer_genid;
 
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index c850e5fb967cb..86b1cb4869038 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -84,6 +84,12 @@ extern int			ip6_route_add(struct fib6_config *cfg);
 extern int			ip6_ins_rt(struct rt6_info *);
 extern int			ip6_del_rt(struct rt6_info *);
 
+extern int			ip6_route_get_saddr(struct net *net,
+						    struct rt6_info *rt,
+						    struct in6_addr *daddr,
+						    unsigned int prefs,
+						    struct in6_addr *saddr);
+
 extern struct rt6_info		*rt6_lookup(struct net *net,
 					    const struct in6_addr *daddr,
 					    const struct in6_addr *saddr,
@@ -141,6 +147,7 @@ struct rt6_rtnl_dump_arg {
 extern int rt6_dump_route(struct rt6_info *rt, void *p_arg);
 extern void rt6_ifdown(struct net *net, struct net_device *dev);
 extern void rt6_mtu_change(struct net_device *dev, unsigned mtu);
+extern void rt6_remove_prefsrc(struct inet6_ifaddr *ifp);
 
 
 /*
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 1493534116df4..129d7e1f311c7 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -825,6 +825,8 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 		dst_release(&rt->dst);
 	}
 
+	/* clean up prefsrc entries */
+	rt6_remove_prefsrc(ifp);
 out:
 	in6_ifa_put(ifp);
 }
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 46cf7bea67694..c614d02bf429c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -930,10 +930,10 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 		goto out_err_release;
 
 	if (ipv6_addr_any(&fl6->saddr)) {
-		err = ipv6_dev_get_saddr(net, ip6_dst_idev(*dst)->dev,
-					 &fl6->daddr,
-					 sk ? inet6_sk(sk)->srcprefs : 0,
-					 &fl6->saddr);
+		struct rt6_info *rt = (struct rt6_info *) *dst;
+		err = ip6_route_get_saddr(net, rt, &fl6->daddr,
+					  sk ? inet6_sk(sk)->srcprefs : 0,
+					  &fl6->saddr);
 		if (err)
 			goto out_err_release;
 	}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 843406f14d7b2..af26cc1073cb3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1325,6 +1325,16 @@ int ip6_route_add(struct fib6_config *cfg)
 	if (dev == NULL)
 		goto out;
 
+	if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
+		if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) {
+			err = -EINVAL;
+			goto out;
+		}
+		ipv6_addr_copy(&rt->rt6i_prefsrc.addr, &cfg->fc_prefsrc);
+		rt->rt6i_prefsrc.plen = 128;
+	} else
+		rt->rt6i_prefsrc.plen = 0;
+
 	if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) {
 		rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev);
 		if (IS_ERR(rt->rt6i_nexthop)) {
@@ -2037,6 +2047,55 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 	return rt;
 }
 
+int ip6_route_get_saddr(struct net *net,
+			struct rt6_info *rt,
+			struct in6_addr *daddr,
+			unsigned int prefs,
+			struct in6_addr *saddr)
+{
+	struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt);
+	int err = 0;
+	if (rt->rt6i_prefsrc.plen)
+		ipv6_addr_copy(saddr, &rt->rt6i_prefsrc.addr);
+	else
+		err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
+					 daddr, prefs, saddr);
+	return err;
+}
+
+/* remove deleted ip from prefsrc entries */
+struct arg_dev_net_ip {
+	struct net_device *dev;
+	struct net *net;
+	struct in6_addr *addr;
+};
+
+static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
+{
+	struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev;
+	struct net *net = ((struct arg_dev_net_ip *)arg)->net;
+	struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
+
+	if (((void *)rt->rt6i_dev == dev || dev == NULL) &&
+	    rt != net->ipv6.ip6_null_entry &&
+	    ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
+		/* remove prefsrc entry */
+		rt->rt6i_prefsrc.plen = 0;
+	}
+	return 0;
+}
+
+void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
+{
+	struct net *net = dev_net(ifp->idev->dev);
+	struct arg_dev_net_ip adni = {
+		.dev = ifp->idev->dev,
+		.net = net,
+		.addr = &ifp->addr,
+	};
+	fib6_clean_all(net, fib6_remove_prefsrc, 0, &adni);
+}
+
 struct arg_dev_net {
 	struct net_device *dev;
 	struct net *net;
@@ -2183,6 +2242,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 		nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen);
 	}
 
+	if (tb[RTA_PREFSRC])
+		nla_memcpy(&cfg->fc_prefsrc, tb[RTA_PREFSRC], 16);
+
 	if (tb[RTA_OIF])
 		cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]);
 
@@ -2325,13 +2387,17 @@ static int rt6_fill_node(struct net *net,
 #endif
 			NLA_PUT_U32(skb, RTA_IIF, iif);
 	} else if (dst) {
-		struct inet6_dev *idev = ip6_dst_idev(&rt->dst);
 		struct in6_addr saddr_buf;
-		if (ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
-				       dst, 0, &saddr_buf) == 0)
+		if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0)
 			NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
 	}
 
+	if (rt->rt6i_prefsrc.plen) {
+		struct in6_addr saddr_buf;
+		ipv6_addr_copy(&saddr_buf, &rt->rt6i_prefsrc.addr);
+		NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
+	}
+
 	if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
 		goto nla_put_failure;
 
-- 
cgit v1.2.3


From f3c85dd560f26ceae1351e6f83e83f1322761ead Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 17 Apr 2011 17:04:48 -0700
Subject: netfilter: ip6_tables: Fix set-but-unused variables.

The variable 'target' is set but unused in compat_copy_entry_from_user().

Just kill it off.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/netfilter/ip6_tables.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 5a1c6f27ffafe..4c1492ff473c7 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1578,7 +1578,6 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
 			    struct xt_table_info *newinfo, unsigned char *base)
 {
 	struct xt_entry_target *t;
-	struct xt_target *target;
 	struct ip6t_entry *de;
 	unsigned int origsize;
 	int ret, h;
@@ -1600,7 +1599,6 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
 	}
 	de->target_offset = e->target_offset - (origsize - *size);
 	t = compat_ip6t_get_target(e);
-	target = t->u.kernel.target;
 	xt_compat_target_from_user(t, dstptr, size);
 
 	de->next_offset = e->next_offset - (origsize - *size);
-- 
cgit v1.2.3


From b169f6db40605d0907458d1ff78ceac2b194a44f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 17 Apr 2011 17:06:15 -0700
Subject: netfilter: ip6table_mangle: Fix set-but-unused variables.

The variable 'flowlabel' is set but unused in ip6t_mangle_out().

The intention here was to compare this key to the header value after
mangling, and trigger a route lookup on mismatch.

Make it so.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/netfilter/ip6table_mangle.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 679a0a3b7b3c7..00d19173db7e6 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -64,7 +64,8 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out)
 	    (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
 	     memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
 	     skb->mark != mark ||
-	     ipv6_hdr(skb)->hop_limit != hop_limit))
+	     ipv6_hdr(skb)->hop_limit != hop_limit ||
+	     flowlabel != *((u_int32_t *)ipv6_hdr(skb))))
 		return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP;
 
 	return ret;
-- 
cgit v1.2.3


From f47b94646f30529624c82ab0f9cd5bd3f25ef9d2 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Fri, 15 Apr 2011 13:46:02 +0000
Subject: ipv6: Send unsolicited neighbour advertismements when notified

The NETDEV_NOTIFY_PEERS notifier is a request to send such
advertisements following migration to a different physical link,
e.g. virtual machine migration.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ndisc.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'net/ipv6')

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index f057ff312840a..62cbd15b4cdeb 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -611,6 +611,29 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
 		     inc_opt ? ND_OPT_TARGET_LL_ADDR : 0);
 }
 
+static void ndisc_send_unsol_na(struct net_device *dev)
+{
+	struct inet6_dev *idev;
+	struct inet6_ifaddr *ifa;
+	struct in6_addr mcaddr;
+
+	idev = in6_dev_get(dev);
+	if (!idev)
+		return;
+
+	read_lock_bh(&idev->lock);
+	list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		addrconf_addr_solict_mult(&ifa->addr, &mcaddr);
+		ndisc_send_na(dev, NULL, &mcaddr, &ifa->addr,
+			      /*router=*/ !!idev->cnf.forwarding,
+			      /*solicited=*/ false, /*override=*/ true,
+			      /*inc_opt=*/ true);
+	}
+	read_unlock_bh(&idev->lock);
+
+	in6_dev_put(idev);
+}
+
 void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
 		   const struct in6_addr *solicit,
 		   const struct in6_addr *daddr, const struct in6_addr *saddr)
@@ -1723,6 +1746,9 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
 		neigh_ifdown(&nd_tbl, dev);
 		fib6_run_gc(~0UL, net);
 		break;
+	case NETDEV_NOTIFY_PEERS:
+		ndisc_send_unsol_na(dev);
+		break;
 	default:
 		break;
 	}
-- 
cgit v1.2.3


From 7c89943236750537d26421d9bbb6f6575e2d1e1b Mon Sep 17 00:00:00 2001
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Fri, 15 Apr 2011 13:47:51 +0000
Subject: bonding, ipv4, ipv6, vlan: Handle NETDEV_BONDING_FAILOVER like
 NETDEV_NOTIFY_PEERS

It is undesirable for the bonding driver to be poking into higher
level protocols, and notifiers provide a way to avoid that.  This does
mean removing the ability to configure reptitition of gratuitous ARPs
and unsolicited NAs.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/Makefile     |  3 --
 drivers/net/bonding/bond_main.c  | 94 ----------------------------------------
 drivers/net/bonding/bond_sysfs.c | 80 ----------------------------------
 drivers/net/bonding/bonding.h    | 29 -------------
 net/8021q/vlan.c                 |  3 +-
 net/ipv4/devinet.c               |  1 +
 net/ipv6/ndisc.c                 |  1 +
 7 files changed, 4 insertions(+), 207 deletions(-)

(limited to 'net/ipv6')

diff --git a/drivers/net/bonding/Makefile b/drivers/net/bonding/Makefile
index 3c5c014e82b22..4c21bf6b8b2f0 100644
--- a/drivers/net/bonding/Makefile
+++ b/drivers/net/bonding/Makefile
@@ -9,6 +9,3 @@ bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o bond_debugfs.o
 proc-$(CONFIG_PROC_FS) += bond_procfs.o
 bonding-objs += $(proc-y)
 
-ipv6-$(subst m,y,$(CONFIG_IPV6)) += bond_ipv6.o
-bonding-objs += $(ipv6-y)
-
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index fdf9215ada7dc..4ce14bdf96dd8 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -89,8 +89,6 @@
 
 static int max_bonds	= BOND_DEFAULT_MAX_BONDS;
 static int tx_queues	= BOND_DEFAULT_TX_QUEUES;
-static int num_grat_arp = 1;
-static int num_unsol_na = 1;
 static int miimon	= BOND_LINK_MON_INTERV;
 static int updelay;
 static int downdelay;
@@ -113,10 +111,6 @@ module_param(max_bonds, int, 0);
 MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
 module_param(tx_queues, int, 0);
 MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)");
-module_param(num_grat_arp, int, 0644);
-MODULE_PARM_DESC(num_grat_arp, "Number of gratuitous ARP packets to send on failover event");
-module_param(num_unsol_na, int, 0644);
-MODULE_PARM_DESC(num_unsol_na, "Number of unsolicited IPv6 Neighbor Advertisements packets to send on failover event");
 module_param(miimon, int, 0);
 MODULE_PARM_DESC(miimon, "Link check interval in milliseconds");
 module_param(updelay, int, 0);
@@ -234,7 +228,6 @@ struct bond_parm_tbl ad_select_tbl[] = {
 
 /*-------------------------- Forward declarations ---------------------------*/
 
-static void bond_send_gratuitous_arp(struct bonding *bond);
 static int bond_init(struct net_device *bond_dev);
 static void bond_uninit(struct net_device *bond_dev);
 
@@ -1162,14 +1155,6 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 				bond_do_fail_over_mac(bond, new_active,
 						      old_active);
 
-			if (netif_running(bond->dev)) {
-				bond->send_grat_arp = bond->params.num_grat_arp;
-				bond_send_gratuitous_arp(bond);
-
-				bond->send_unsol_na = bond->params.num_unsol_na;
-				bond_send_unsolicited_na(bond);
-			}
-
 			write_unlock_bh(&bond->curr_slave_lock);
 			read_unlock(&bond->lock);
 
@@ -2580,18 +2565,6 @@ void bond_mii_monitor(struct work_struct *work)
 	if (bond->slave_cnt == 0)
 		goto re_arm;
 
-	if (bond->send_grat_arp) {
-		read_lock(&bond->curr_slave_lock);
-		bond_send_gratuitous_arp(bond);
-		read_unlock(&bond->curr_slave_lock);
-	}
-
-	if (bond->send_unsol_na) {
-		read_lock(&bond->curr_slave_lock);
-		bond_send_unsolicited_na(bond);
-		read_unlock(&bond->curr_slave_lock);
-	}
-
 	if (bond_miimon_inspect(bond)) {
 		read_unlock(&bond->lock);
 		rtnl_lock();
@@ -2753,42 +2726,6 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 	}
 }
 
-/*
- * Kick out a gratuitous ARP for an IP on the bonding master plus one
- * for each VLAN above us.
- *
- * Caller must hold curr_slave_lock for read or better
- */
-static void bond_send_gratuitous_arp(struct bonding *bond)
-{
-	struct slave *slave = bond->curr_active_slave;
-	struct vlan_entry *vlan;
-
-	pr_debug("bond_send_grat_arp: bond %s slave %s\n",
-		 bond->dev->name, slave ? slave->dev->name : "NULL");
-
-	if (!slave || !bond->send_grat_arp ||
-	    test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
-		return;
-
-	bond->send_grat_arp--;
-
-	if (bond->master_ip) {
-		bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip,
-				bond->master_ip, 0);
-	}
-
-	if (!bond->vlgrp)
-		return;
-
-	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
-		if (vlan->vlan_ip) {
-			bond_arp_send(slave->dev, ARPOP_REPLY, vlan->vlan_ip,
-				      vlan->vlan_ip, vlan->vlan_id);
-		}
-	}
-}
-
 static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip)
 {
 	int i;
@@ -3255,18 +3192,6 @@ void bond_activebackup_arp_mon(struct work_struct *work)
 	if (bond->slave_cnt == 0)
 		goto re_arm;
 
-	if (bond->send_grat_arp) {
-		read_lock(&bond->curr_slave_lock);
-		bond_send_gratuitous_arp(bond);
-		read_unlock(&bond->curr_slave_lock);
-	}
-
-	if (bond->send_unsol_na) {
-		read_lock(&bond->curr_slave_lock);
-		bond_send_unsolicited_na(bond);
-		read_unlock(&bond->curr_slave_lock);
-	}
-
 	if (bond_ab_arp_inspect(bond, delta_in_ticks)) {
 		read_unlock(&bond->lock);
 		rtnl_lock();
@@ -3645,9 +3570,6 @@ static int bond_close(struct net_device *bond_dev)
 
 	write_lock_bh(&bond->lock);
 
-	bond->send_grat_arp = 0;
-	bond->send_unsol_na = 0;
-
 	/* signal timers not to re-arm */
 	bond->kill_timers = 1;
 
@@ -4724,18 +4646,6 @@ static int bond_check_params(struct bond_params *params)
 		use_carrier = 1;
 	}
 
-	if (num_grat_arp < 0 || num_grat_arp > 255) {
-		pr_warning("Warning: num_grat_arp (%d) not in range 0-255 so it was reset to 1\n",
-			   num_grat_arp);
-		num_grat_arp = 1;
-	}
-
-	if (num_unsol_na < 0 || num_unsol_na > 255) {
-		pr_warning("Warning: num_unsol_na (%d) not in range 0-255 so it was reset to 1\n",
-			   num_unsol_na);
-		num_unsol_na = 1;
-	}
-
 	/* reset values for 802.3ad */
 	if (bond_mode == BOND_MODE_8023AD) {
 		if (!miimon) {
@@ -4925,8 +4835,6 @@ static int bond_check_params(struct bond_params *params)
 	params->mode = bond_mode;
 	params->xmit_policy = xmit_hashtype;
 	params->miimon = miimon;
-	params->num_grat_arp = num_grat_arp;
-	params->num_unsol_na = num_unsol_na;
 	params->arp_interval = arp_interval;
 	params->arp_validate = arp_validate_value;
 	params->updelay = updelay;
@@ -5121,7 +5029,6 @@ static int __init bonding_init(void)
 
 	register_netdevice_notifier(&bond_netdev_notifier);
 	register_inetaddr_notifier(&bond_inetaddr_notifier);
-	bond_register_ipv6_notifier();
 out:
 	return res;
 err:
@@ -5136,7 +5043,6 @@ static void __exit bonding_exit(void)
 {
 	unregister_netdevice_notifier(&bond_netdev_notifier);
 	unregister_inetaddr_notifier(&bond_inetaddr_notifier);
-	bond_unregister_ipv6_notifier();
 
 	bond_destroy_sysfs();
 	bond_destroy_debugfs();
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index de87aea6d01a1..259ff32cd5731 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -873,84 +873,6 @@ out:
 static DEVICE_ATTR(ad_select, S_IRUGO | S_IWUSR,
 		   bonding_show_ad_select, bonding_store_ad_select);
 
-/*
- * Show and set the number of grat ARP to send after a failover event.
- */
-static ssize_t bonding_show_n_grat_arp(struct device *d,
-				   struct device_attribute *attr,
-				   char *buf)
-{
-	struct bonding *bond = to_bond(d);
-
-	return sprintf(buf, "%d\n", bond->params.num_grat_arp);
-}
-
-static ssize_t bonding_store_n_grat_arp(struct device *d,
-				    struct device_attribute *attr,
-				    const char *buf, size_t count)
-{
-	int new_value, ret = count;
-	struct bonding *bond = to_bond(d);
-
-	if (sscanf(buf, "%d", &new_value) != 1) {
-		pr_err("%s: no num_grat_arp value specified.\n",
-		       bond->dev->name);
-		ret = -EINVAL;
-		goto out;
-	}
-	if (new_value < 0 || new_value > 255) {
-		pr_err("%s: Invalid num_grat_arp value %d not in range 0-255; rejected.\n",
-		       bond->dev->name, new_value);
-		ret = -EINVAL;
-		goto out;
-	} else {
-		bond->params.num_grat_arp = new_value;
-	}
-out:
-	return ret;
-}
-static DEVICE_ATTR(num_grat_arp, S_IRUGO | S_IWUSR,
-		   bonding_show_n_grat_arp, bonding_store_n_grat_arp);
-
-/*
- * Show and set the number of unsolicited NA's to send after a failover event.
- */
-static ssize_t bonding_show_n_unsol_na(struct device *d,
-				       struct device_attribute *attr,
-				       char *buf)
-{
-	struct bonding *bond = to_bond(d);
-
-	return sprintf(buf, "%d\n", bond->params.num_unsol_na);
-}
-
-static ssize_t bonding_store_n_unsol_na(struct device *d,
-					struct device_attribute *attr,
-					const char *buf, size_t count)
-{
-	int new_value, ret = count;
-	struct bonding *bond = to_bond(d);
-
-	if (sscanf(buf, "%d", &new_value) != 1) {
-		pr_err("%s: no num_unsol_na value specified.\n",
-		       bond->dev->name);
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (new_value < 0 || new_value > 255) {
-		pr_err("%s: Invalid num_unsol_na value %d not in range 0-255; rejected.\n",
-		       bond->dev->name, new_value);
-		ret = -EINVAL;
-		goto out;
-	} else
-		bond->params.num_unsol_na = new_value;
-out:
-	return ret;
-}
-static DEVICE_ATTR(num_unsol_na, S_IRUGO | S_IWUSR,
-		   bonding_show_n_unsol_na, bonding_store_n_unsol_na);
-
 /*
  * Show and set the MII monitor interval.  There are two tricky bits
  * here.  First, if MII monitoring is activated, then we must disable
@@ -1650,8 +1572,6 @@ static struct attribute *per_bond_attrs[] = {
 	&dev_attr_lacp_rate.attr,
 	&dev_attr_ad_select.attr,
 	&dev_attr_xmit_hash_policy.attr,
-	&dev_attr_num_grat_arp.attr,
-	&dev_attr_num_unsol_na.attr,
 	&dev_attr_miimon.attr,
 	&dev_attr_primary.attr,
 	&dev_attr_primary_reselect.attr,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 553c764f74075..6126c6a13a749 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -149,8 +149,6 @@ struct bond_params {
 	int mode;
 	int xmit_policy;
 	int miimon;
-	int num_grat_arp;
-	int num_unsol_na;
 	int arp_interval;
 	int arp_validate;
 	int use_carrier;
@@ -178,9 +176,6 @@ struct vlan_entry {
 	struct list_head vlan_list;
 	__be32 vlan_ip;
 	unsigned short vlan_id;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-	struct in6_addr vlan_ipv6;
-#endif
 };
 
 struct slave {
@@ -234,8 +229,6 @@ struct bonding {
 	rwlock_t lock;
 	rwlock_t curr_slave_lock;
 	s8       kill_timers;
-	s8	 send_grat_arp;
-	s8	 send_unsol_na;
 	s8	 setup_by_slave;
 	s8       igmp_retrans;
 #ifdef CONFIG_PROC_FS
@@ -260,9 +253,6 @@ struct bonding {
 	struct   delayed_work alb_work;
 	struct   delayed_work ad_work;
 	struct   delayed_work mcast_work;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-	struct   in6_addr master_ipv6;
-#endif
 #ifdef CONFIG_DEBUG_FS
 	/* debugging suport via debugfs */
 	struct	 dentry *debug_dir;
@@ -460,23 +450,4 @@ extern const struct bond_parm_tbl fail_over_mac_tbl[];
 extern const struct bond_parm_tbl pri_reselect_tbl[];
 extern struct bond_parm_tbl ad_select_tbl[];
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-void bond_send_unsolicited_na(struct bonding *bond);
-void bond_register_ipv6_notifier(void);
-void bond_unregister_ipv6_notifier(void);
-#else
-static inline void bond_send_unsolicited_na(struct bonding *bond)
-{
-	return;
-}
-static inline void bond_register_ipv6_notifier(void)
-{
-	return;
-}
-static inline void bond_unregister_ipv6_notifier(void)
-{
-	return;
-}
-#endif
-
 #endif /* _LINUX_BONDING_H */
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index b2ff70fcf8ead..969e7004cf86a 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -501,13 +501,14 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 		return NOTIFY_BAD;
 
 	case NETDEV_NOTIFY_PEERS:
+	case NETDEV_BONDING_FAILOVER:
 		/* Propagate to vlan devices */
 		for (i = 0; i < VLAN_N_VID; i++) {
 			vlandev = vlan_group_get_device(grp, i);
 			if (!vlandev)
 				continue;
 
-			call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, vlandev);
+			call_netdevice_notifiers(event, vlandev);
 		}
 		break;
 	}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 5345b0bee6df8..acf553f95b5b0 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1203,6 +1203,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
 			break;
 		/* fall through */
 	case NETDEV_NOTIFY_PEERS:
+	case NETDEV_BONDING_FAILOVER:
 		/* Send gratuitous ARP to notify of link change */
 		inetdev_send_gratuitous_arp(dev, in_dev);
 		break;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 62cbd15b4cdeb..01a0ffc7b402c 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1747,6 +1747,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
 		fib6_run_gc(~0UL, net);
 		break;
 	case NETDEV_NOTIFY_PEERS:
+	case NETDEV_BONDING_FAILOVER:
 		ndisc_send_unsol_na(dev);
 		break;
 	default:
-- 
cgit v1.2.3


From b71d1d426d263b0b6cb5760322efebbfc89d4463 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Fri, 22 Apr 2011 04:53:02 +0000
Subject: inet: constify ip headers and in6_addr

Add const qualifiers to structs iphdr, ipv6hdr and in6_addr pointers
where possible, to make code intention more obvious.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h             | 22 ++++++++--------
 include/net/if_inet6.h             |  4 +--
 include/net/inetpeer.h             |  2 +-
 include/net/ip6_fib.h              |  8 +++---
 include/net/ip6_route.h            | 18 ++++++-------
 include/net/ipv6.h                 |  4 +--
 include/net/ndisc.h                |  3 ++-
 include/net/route.h                |  3 ++-
 include/net/xfrm.h                 |  6 ++---
 net/bridge/br_multicast.c          | 12 ++++-----
 net/bridge/br_netfilter.c          |  4 +--
 net/core/dev.c                     |  8 +++---
 net/core/netpoll.c                 |  2 +-
 net/dccp/ipv6.c                    |  8 +++---
 net/ipv4/af_inet.c                 |  4 +--
 net/ipv4/ah4.c                     |  7 ++---
 net/ipv4/esp4.c                    |  7 ++---
 net/ipv4/icmp.c                    | 12 ++++-----
 net/ipv4/inet_diag.c               |  2 +-
 net/ipv4/inet_lro.c                |  4 +--
 net/ipv4/ip_gre.c                  | 28 ++++++++++----------
 net/ipv4/ip_input.c                |  4 +--
 net/ipv4/ip_sockglue.c             |  2 +-
 net/ipv4/ipcomp.c                  |  4 +--
 net/ipv4/ipip.c                    |  8 +++---
 net/ipv4/ipmr.c                    |  2 +-
 net/ipv4/netfilter/nf_nat_helper.c |  2 +-
 net/ipv4/raw.c                     | 10 ++++----
 net/ipv4/route.c                   |  2 +-
 net/ipv4/tcp_ipv4.c                |  8 +++---
 net/ipv4/udp.c                     |  2 +-
 net/ipv4/xfrm4_policy.c            |  2 +-
 net/ipv4/xfrm4_state.c             |  2 +-
 net/ipv6/addrconf.c                | 16 ++++++------
 net/ipv6/af_inet6.c                |  2 +-
 net/ipv6/anycast.c                 | 16 ++++++------
 net/ipv6/esp6.c                    |  5 ++--
 net/ipv6/icmp.c                    |  8 +++---
 net/ipv6/ip6_fib.c                 | 16 ++++++------
 net/ipv6/ip6_input.c               |  6 ++---
 net/ipv6/ip6_output.c              |  8 +++---
 net/ipv6/ip6_tunnel.c              | 36 +++++++++++++-------------
 net/ipv6/ip6mr.c                   |  4 +--
 net/ipv6/ipcomp6.c                 |  5 ++--
 net/ipv6/mcast.c                   | 36 +++++++++++++-------------
 net/ipv6/mip6.c                    |  8 +++---
 net/ipv6/ndisc.c                   | 18 ++++++-------
 net/ipv6/netfilter.c               | 10 ++++----
 net/ipv6/raw.c                     | 14 +++++-----
 net/ipv6/reassembly.c              |  4 +--
 net/ipv6/route.c                   | 52 +++++++++++++++++++-------------------
 net/ipv6/sit.c                     | 25 +++++++++---------
 net/ipv6/syncookies.c              | 13 +++++-----
 net/ipv6/tcp_ipv6.c                | 48 +++++++++++++++++------------------
 net/ipv6/udp.c                     | 20 +++++++--------
 net/ipv6/xfrm6_mode_beet.c         |  2 --
 net/ipv6/xfrm6_mode_tunnel.c       |  6 ++---
 net/ipv6/xfrm6_policy.c            |  2 +-
 net/ipv6/xfrm6_tunnel.c            | 10 ++++----
 net/key/af_key.c                   |  2 +-
 net/sched/sch_sfq.c                |  2 +-
 net/sctp/input.c                   |  2 +-
 net/sctp/ipv6.c                    |  2 +-
 net/xfrm/xfrm_state.c              | 12 ++++-----
 64 files changed, 316 insertions(+), 310 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 23710aa6a1810..7c4d92c0dd1d3 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -61,16 +61,16 @@ extern int			addrconf_set_dstaddr(struct net *net,
 						     void __user *arg);
 
 extern int			ipv6_chk_addr(struct net *net,
-					      struct in6_addr *addr,
+					      const struct in6_addr *addr,
 					      struct net_device *dev,
 					      int strict);
 
 #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
 extern int			ipv6_chk_home_addr(struct net *net,
-						   struct in6_addr *addr);
+						   const struct in6_addr *addr);
 #endif
 
-extern int			ipv6_chk_prefix(struct in6_addr *addr,
+extern int			ipv6_chk_prefix(const struct in6_addr *addr,
 						struct net_device *dev);
 
 extern struct inet6_ifaddr      *ipv6_get_ifaddr(struct net *net,
@@ -89,9 +89,9 @@ extern int			ipv6_get_lladdr(struct net_device *dev,
 extern int 			ipv6_rcv_saddr_equal(const struct sock *sk,
 						    const struct sock *sk2);
 extern void			addrconf_join_solict(struct net_device *dev,
-					struct in6_addr *addr);
+					const struct in6_addr *addr);
 extern void			addrconf_leave_solict(struct inet6_dev *idev,
-					struct in6_addr *addr);
+					const struct in6_addr *addr);
 
 static inline unsigned long addrconf_timeout_fixup(u32 timeout,
 						    unsigned unit)
@@ -158,15 +158,15 @@ extern void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len);
 /*
  *	anycast prototypes (anycast.c)
  */
-extern int ipv6_sock_ac_join(struct sock *sk,int ifindex,struct in6_addr *addr);
-extern int ipv6_sock_ac_drop(struct sock *sk,int ifindex,struct in6_addr *addr);
+extern int ipv6_sock_ac_join(struct sock *sk,int ifindex, const struct in6_addr *addr);
+extern int ipv6_sock_ac_drop(struct sock *sk,int ifindex, const struct in6_addr *addr);
 extern void ipv6_sock_ac_close(struct sock *sk);
-extern int inet6_ac_check(struct sock *sk, struct in6_addr *addr, int ifindex);
+extern int inet6_ac_check(struct sock *sk, const struct in6_addr *addr, int ifindex);
 
-extern int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr);
-extern int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr);
+extern int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr);
+extern int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr);
 extern int ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
-			       struct in6_addr *addr);
+			       const struct in6_addr *addr);
 
 
 /* Device notifier */
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index fccc2180c61be..3d982f72d48e4 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -196,7 +196,7 @@ struct inet6_dev {
 	struct rcu_head		rcu;
 };
 
-static inline void ipv6_eth_mc_map(struct in6_addr *addr, char *buf)
+static inline void ipv6_eth_mc_map(const struct in6_addr *addr, char *buf)
 {
 	/*
 	 *	+-------+-------+-------+-------+-------+-------+
@@ -210,7 +210,7 @@ static inline void ipv6_eth_mc_map(struct in6_addr *addr, char *buf)
 	memcpy(buf + 2, &addr->s6_addr32[3], sizeof(__u32));
 }
 
-static inline void ipv6_tr_mc_map(struct in6_addr *addr, char *buf)
+static inline void ipv6_tr_mc_map(const struct in6_addr *addr, char *buf)
 {
 	/* All nodes FF01::1, FF02::1, FF02::1:FFxx:xxxx */
 
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index e6dd8da6b2ad6..8a159cc3d68b4 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -80,7 +80,7 @@ static inline struct inet_peer *inet_getpeer_v4(__be32 v4daddr, int create)
 	return inet_getpeer(&daddr, create);
 }
 
-static inline struct inet_peer *inet_getpeer_v6(struct in6_addr *v6daddr, int create)
+static inline struct inet_peer *inet_getpeer_v6(const struct in6_addr *v6daddr, int create)
 {
 	struct inetpeer_addr daddr;
 
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 98348d53b2b60..aca8ef4dd67c1 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -198,12 +198,12 @@ extern struct dst_entry         *fib6_rule_lookup(struct net *net,
 						  pol_lookup_t lookup);
 
 extern struct fib6_node		*fib6_lookup(struct fib6_node *root,
-					     struct in6_addr *daddr,
-					     struct in6_addr *saddr);
+					     const struct in6_addr *daddr,
+					     const struct in6_addr *saddr);
 
 struct fib6_node		*fib6_locate(struct fib6_node *root,
-					     struct in6_addr *daddr, int dst_len,
-					     struct in6_addr *saddr, int src_len);
+					     const struct in6_addr *daddr, int dst_len,
+					     const struct in6_addr *saddr, int src_len);
 
 extern void			fib6_clean_all(struct net *net,
 					       int (*func)(struct rt6_info *, void *arg),
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 86b1cb4869038..d5c21d4d9e7ec 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -86,7 +86,7 @@ extern int			ip6_del_rt(struct rt6_info *);
 
 extern int			ip6_route_get_saddr(struct net *net,
 						    struct rt6_info *rt,
-						    struct in6_addr *daddr,
+						    const struct in6_addr *daddr,
 						    unsigned int prefs,
 						    struct in6_addr *saddr);
 
@@ -112,9 +112,9 @@ extern int			ip6_dst_hoplimit(struct dst_entry *dst);
  *	support functions for ND
  *
  */
-extern struct rt6_info *	rt6_get_dflt_router(struct in6_addr *addr,
+extern struct rt6_info *	rt6_get_dflt_router(const struct in6_addr *addr,
 						    struct net_device *dev);
-extern struct rt6_info *	rt6_add_dflt_router(struct in6_addr *gwaddr,
+extern struct rt6_info *	rt6_add_dflt_router(const struct in6_addr *gwaddr,
 						    struct net_device *dev,
 						    unsigned int pref);
 
@@ -122,17 +122,17 @@ extern void			rt6_purge_dflt_routers(struct net *net);
 
 extern int			rt6_route_rcv(struct net_device *dev,
 					      u8 *opt, int len,
-					      struct in6_addr *gwaddr);
+					      const struct in6_addr *gwaddr);
 
-extern void			rt6_redirect(struct in6_addr *dest,
-					     struct in6_addr *src,
-					     struct in6_addr *saddr,
+extern void			rt6_redirect(const struct in6_addr *dest,
+					     const struct in6_addr *src,
+					     const struct in6_addr *saddr,
 					     struct neighbour *neigh,
 					     u8 *lladdr,
 					     int on_link);
 
-extern void			rt6_pmtu_discovery(struct in6_addr *daddr,
-						   struct in6_addr *saddr,
+extern void			rt6_pmtu_discovery(const struct in6_addr *daddr,
+						   const struct in6_addr *saddr,
 						   struct net_device *dev,
 						   u32 pmtu);
 
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 34200f9e6805c..5da192653153e 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -376,8 +376,8 @@ enum ip6_defrag_users {
 struct ip6_create_arg {
 	__be32 id;
 	u32 user;
-	struct in6_addr *src;
-	struct in6_addr *dst;
+	const struct in6_addr *src;
+	const struct in6_addr *dst;
 };
 
 void ip6_frag_init(struct inet_frag_queue *q, void *a);
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index e0e594f8e9d9a..6144685d601b2 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -102,7 +102,8 @@ extern void			ndisc_send_redirect(struct sk_buff *skb,
 						    struct neighbour *neigh,
 						    const struct in6_addr *target);
 
-extern int			ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int dir);
+extern int			ndisc_mc_map(const struct in6_addr *addr, char *buf,
+					     struct net_device *dev, int dir);
 
 extern struct sk_buff		*ndisc_build_skb(struct net_device *dev,
 						 const struct in6_addr *daddr,
diff --git a/include/net/route.h b/include/net/route.h
index 3782cddd1383e..b3962e249e14e 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -191,7 +191,8 @@ static inline int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 s
 	return ip_route_input_common(skb, dst, src, tos, devin, true);
 }
 
-extern unsigned short	ip_rt_frag_needed(struct net *net, struct iphdr *iph, unsigned short new_mtu, struct net_device *dev);
+extern unsigned short	ip_rt_frag_needed(struct net *net, const struct iphdr *iph,
+					  unsigned short new_mtu, struct net_device *dev);
 extern void		ip_rt_send_redirect(struct sk_buff *skb);
 
 extern unsigned		inet_addr_type(struct net *net, __be32 addr);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 65ea313486313..1cdd4b7b28614 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1475,7 +1475,7 @@ extern int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
 extern int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family);
 extern int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family);
 extern __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr);
-extern __be32 xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr);
+extern __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr);
 extern int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb);
 extern int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
 extern int xfrm6_output(struct sk_buff *skb);
@@ -1569,8 +1569,8 @@ static inline int xfrm_addr_cmp(const xfrm_address_t *a,
 	case AF_INET:
 		return (__force u32)a->a4 - (__force u32)b->a4;
 	case AF_INET6:
-		return ipv6_addr_cmp((struct in6_addr *)a,
-				     (struct in6_addr *)b);
+		return ipv6_addr_cmp((const struct in6_addr *)a,
+				     (const struct in6_addr *)b);
 	}
 }
 
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 59660c909a7ce..2f14eafdeeabe 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -413,7 +413,7 @@ out:
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
-						    struct in6_addr *group)
+						    const struct in6_addr *group)
 {
 	struct sk_buff *skb;
 	struct ipv6hdr *ip6h;
@@ -1115,7 +1115,7 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 				  struct net_bridge_port *port,
 				  struct sk_buff *skb)
 {
-	struct iphdr *iph = ip_hdr(skb);
+	const struct iphdr *iph = ip_hdr(skb);
 	struct igmphdr *ih = igmp_hdr(skb);
 	struct net_bridge_mdb_entry *mp;
 	struct igmpv3_query *ih3;
@@ -1190,7 +1190,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 				  struct net_bridge_port *port,
 				  struct sk_buff *skb)
 {
-	struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	struct mld_msg *mld = (struct mld_msg *) icmp6_hdr(skb);
 	struct net_bridge_mdb_entry *mp;
 	struct mld2_query *mld2q;
@@ -1198,7 +1198,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 	struct net_bridge_port_group __rcu **pp;
 	unsigned long max_delay;
 	unsigned long now = jiffies;
-	struct in6_addr *group = NULL;
+	const struct in6_addr *group = NULL;
 	int err = 0;
 
 	spin_lock(&br->multicast_lock);
@@ -1356,7 +1356,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
 				 struct sk_buff *skb)
 {
 	struct sk_buff *skb2 = skb;
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	struct igmphdr *ih;
 	unsigned len;
 	unsigned offset;
@@ -1452,7 +1452,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 				 struct sk_buff *skb)
 {
 	struct sk_buff *skb2;
-	struct ipv6hdr *ip6h;
+	const struct ipv6hdr *ip6h;
 	struct icmp6hdr *icmp6h;
 	u8 nexthdr;
 	unsigned len;
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index f3bc322c58912..5614907525e18 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -219,7 +219,7 @@ static inline void nf_bridge_update_protocol(struct sk_buff *skb)
 static int br_parse_ip_options(struct sk_buff *skb)
 {
 	struct ip_options *opt;
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	struct net_device *dev = skb->dev;
 	u32 len;
 
@@ -554,7 +554,7 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook,
 					   const struct net_device *out,
 					   int (*okfn)(struct sk_buff *))
 {
-	struct ipv6hdr *hdr;
+	const struct ipv6hdr *hdr;
 	u32 pkt_len;
 
 	if (skb->len < sizeof(struct ipv6hdr))
diff --git a/net/core/dev.c b/net/core/dev.c
index 3871bf69a3868..379c993ff4217 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2502,8 +2502,8 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 __u32 __skb_get_rxhash(struct sk_buff *skb)
 {
 	int nhoff, hash = 0, poff;
-	struct ipv6hdr *ip6;
-	struct iphdr *ip;
+	const struct ipv6hdr *ip6;
+	const struct iphdr *ip;
 	u8 ip_proto;
 	u32 addr1, addr2, ihl;
 	union {
@@ -2518,7 +2518,7 @@ __u32 __skb_get_rxhash(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, sizeof(*ip) + nhoff))
 			goto done;
 
-		ip = (struct iphdr *) (skb->data + nhoff);
+		ip = (const struct iphdr *) (skb->data + nhoff);
 		if (ip->frag_off & htons(IP_MF | IP_OFFSET))
 			ip_proto = 0;
 		else
@@ -2531,7 +2531,7 @@ __u32 __skb_get_rxhash(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff))
 			goto done;
 
-		ip6 = (struct ipv6hdr *) (skb->data + nhoff);
+		ip6 = (const struct ipv6hdr *) (skb->data + nhoff);
 		ip_proto = ip6->nexthdr;
 		addr1 = (__force u32) ip6->saddr.s6_addr32[3];
 		addr2 = (__force u32) ip6->daddr.s6_addr32[3];
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 06be2431753e1..46d9c3a4de2f8 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -539,7 +539,7 @@ int __netpoll_rx(struct sk_buff *skb)
 {
 	int proto, len, ulen;
 	int hits = 0;
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	struct udphdr *uh;
 	struct netpoll_info *npinfo = skb->dev->npinfo;
 	struct netpoll *np, *tmp;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index de1b7e37ad5b7..73add23732479 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -54,8 +54,8 @@ static void dccp_v6_hash(struct sock *sk)
 
 /* add pseudo-header to DCCP checksum stored in skb->csum */
 static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb,
-				      struct in6_addr *saddr,
-				      struct in6_addr *daddr)
+				      const struct in6_addr *saddr,
+				      const struct in6_addr *daddr)
 {
 	return csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_DCCP, skb->csum);
 }
@@ -87,7 +87,7 @@ static inline __u32 dccp_v6_init_sequence(struct sk_buff *skb)
 static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			u8 type, u8 code, int offset, __be32 info)
 {
-	struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data;
+	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
 	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
 	struct dccp_sock *dp;
 	struct ipv6_pinfo *np;
@@ -296,7 +296,7 @@ static void dccp_v6_reqsk_destructor(struct request_sock *req)
 
 static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
 {
-	struct ipv6hdr *rxip6h;
+	const struct ipv6hdr *rxip6h;
 	struct sk_buff *skb;
 	struct flowi6 fl6;
 	struct net *net = dev_net(skb_dst(rxskb)->dev);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 807d83c02ef6b..cae75ef21feab 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1186,7 +1186,7 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
 
 static int inet_gso_send_check(struct sk_buff *skb)
 {
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	const struct net_protocol *ops;
 	int proto;
 	int ihl;
@@ -1293,7 +1293,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 	const struct net_protocol *ops;
 	struct sk_buff **pp = NULL;
 	struct sk_buff *p;
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	unsigned int hlen;
 	unsigned int off;
 	unsigned int id;
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 4286fd3cc0e2b..c1f4154552fc5 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -73,7 +73,7 @@ static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash,
  * into IP header for icv calculation. Options are already checked
  * for validity, so paranoia is not required. */
 
-static int ip_clear_mutable_options(struct iphdr *iph, __be32 *daddr)
+static int ip_clear_mutable_options(const struct iphdr *iph, __be32 *daddr)
 {
 	unsigned char * optptr = (unsigned char*)(iph+1);
 	int  l = iph->ihl*4 - sizeof(struct iphdr);
@@ -396,7 +396,7 @@ out:
 static void ah4_err(struct sk_buff *skb, u32 info)
 {
 	struct net *net = dev_net(skb->dev);
-	struct iphdr *iph = (struct iphdr *)skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct ip_auth_hdr *ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
 	struct xfrm_state *x;
 
@@ -404,7 +404,8 @@ static void ah4_err(struct sk_buff *skb, u32 info)
 	    icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
 		return;
 
-	x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET);
+	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+			      ah->spi, IPPROTO_AH, AF_INET);
 	if (!x)
 		return;
 	printk(KERN_DEBUG "pmtu discovery on SA AH/%08x/%08x\n",
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 03f994bcf7de7..a5b413416da33 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -276,7 +276,7 @@ error:
 
 static int esp_input_done2(struct sk_buff *skb, int err)
 {
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	struct xfrm_state *x = xfrm_input_state(skb);
 	struct esp_data *esp = x->data;
 	struct crypto_aead *aead = esp->aead;
@@ -484,7 +484,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu)
 static void esp4_err(struct sk_buff *skb, u32 info)
 {
 	struct net *net = dev_net(skb->dev);
-	struct iphdr *iph = (struct iphdr *)skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
 	struct xfrm_state *x;
 
@@ -492,7 +492,8 @@ static void esp4_err(struct sk_buff *skb, u32 info)
 	    icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
 		return;
 
-	x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET);
+	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+			      esph->spi, IPPROTO_ESP, AF_INET);
 	if (!x)
 		return;
 	NETDEBUG(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%08x\n",
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index e5f8a71d3a2a3..74e35e5736e2d 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -373,7 +373,7 @@ out_unlock:
 }
 
 static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
-					struct iphdr *iph,
+					const struct iphdr *iph,
 					__be32 saddr, u8 tos,
 					int type, int code,
 					struct icmp_bxm *param)
@@ -637,7 +637,7 @@ EXPORT_SYMBOL(icmp_send);
 
 static void icmp_unreach(struct sk_buff *skb)
 {
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	struct icmphdr *icmph;
 	int hash, protocol;
 	const struct net_protocol *ipprot;
@@ -656,7 +656,7 @@ static void icmp_unreach(struct sk_buff *skb)
 		goto out_err;
 
 	icmph = icmp_hdr(skb);
-	iph   = (struct iphdr *)skb->data;
+	iph   = (const struct iphdr *)skb->data;
 
 	if (iph->ihl < 5) /* Mangled header, drop. */
 		goto out_err;
@@ -729,7 +729,7 @@ static void icmp_unreach(struct sk_buff *skb)
 	if (!pskb_may_pull(skb, iph->ihl * 4 + 8))
 		goto out;
 
-	iph = (struct iphdr *)skb->data;
+	iph = (const struct iphdr *)skb->data;
 	protocol = iph->protocol;
 
 	/*
@@ -758,7 +758,7 @@ out_err:
 
 static void icmp_redirect(struct sk_buff *skb)
 {
-	struct iphdr *iph;
+	const struct iphdr *iph;
 
 	if (skb->len < sizeof(struct iphdr))
 		goto out_err;
@@ -769,7 +769,7 @@ static void icmp_redirect(struct sk_buff *skb)
 	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
 		goto out;
 
-	iph = (struct iphdr *)skb->data;
+	iph = (const struct iphdr *)skb->data;
 
 	switch (icmp_hdr(skb)->code & 7) {
 	case ICMP_REDIR_NET:
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 2ada17129fce6..6ffe94ca5bc98 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -124,7 +124,7 @@ static int inet_csk_diag_fill(struct sock *sk,
 
 #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
 	if (r->idiag_family == AF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
+		const struct ipv6_pinfo *np = inet6_sk(sk);
 
 		ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
 			       &np->rcv_saddr);
diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c
index 47038cb6c1382..85a0f75dae644 100644
--- a/net/ipv4/inet_lro.c
+++ b/net/ipv4/inet_lro.c
@@ -51,8 +51,8 @@ MODULE_DESCRIPTION("Large Receive Offload (ipv4 / tcp)");
  * Basic tcp checks whether packet is suitable for LRO
  */
 
-static int lro_tcp_ip_check(struct iphdr *iph, struct tcphdr *tcph,
-			    int len, struct net_lro_desc *lro_desc)
+static int lro_tcp_ip_check(const struct iphdr *iph, const struct tcphdr *tcph,
+			    int len, const struct net_lro_desc *lro_desc)
 {
         /* check ip header: don't aggregate padded frames */
 	if (ntohs(iph->tot_len) != len)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index da5941f18c3c1..24efd353279a1 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -462,7 +462,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
    by themself???
  */
 
-	struct iphdr *iph = (struct iphdr *)skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	__be16	     *p = (__be16*)(skb->data+(iph->ihl<<2));
 	int grehlen = (iph->ihl<<2) + 4;
 	const int type = icmp_hdr(skb)->type;
@@ -534,7 +534,7 @@ out:
 	rcu_read_unlock();
 }
 
-static inline void ipgre_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
+static inline void ipgre_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb)
 {
 	if (INET_ECN_is_ce(iph->tos)) {
 		if (skb->protocol == htons(ETH_P_IP)) {
@@ -546,19 +546,19 @@ static inline void ipgre_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
 }
 
 static inline u8
-ipgre_ecn_encapsulate(u8 tos, struct iphdr *old_iph, struct sk_buff *skb)
+ipgre_ecn_encapsulate(u8 tos, const struct iphdr *old_iph, struct sk_buff *skb)
 {
 	u8 inner = 0;
 	if (skb->protocol == htons(ETH_P_IP))
 		inner = old_iph->tos;
 	else if (skb->protocol == htons(ETH_P_IPV6))
-		inner = ipv6_get_dsfield((struct ipv6hdr *)old_iph);
+		inner = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
 	return INET_ECN_encapsulate(tos, inner);
 }
 
 static int ipgre_rcv(struct sk_buff *skb)
 {
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	u8     *h;
 	__be16    flags;
 	__sum16   csum = 0;
@@ -697,8 +697,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct pcpu_tstats *tstats;
-	struct iphdr  *old_iph = ip_hdr(skb);
-	struct iphdr  *tiph;
+	const struct iphdr  *old_iph = ip_hdr(skb);
+	const struct iphdr  *tiph;
 	u8     tos;
 	__be16 df;
 	struct rtable *rt;     			/* Route to the other host */
@@ -714,7 +714,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 
 	if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
 		gre_hlen = 0;
-		tiph = (struct iphdr *)skb->data;
+		tiph = (const struct iphdr *)skb->data;
 	} else {
 		gre_hlen = tunnel->hlen;
 		tiph = &tunnel->parms.iph;
@@ -735,14 +735,14 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 		}
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 		else if (skb->protocol == htons(ETH_P_IPV6)) {
-			struct in6_addr *addr6;
+			const struct in6_addr *addr6;
 			int addr_type;
 			struct neighbour *neigh = skb_dst(skb)->neighbour;
 
 			if (neigh == NULL)
 				goto tx_error;
 
-			addr6 = (struct in6_addr *)&neigh->primary_key;
+			addr6 = (const struct in6_addr *)&neigh->primary_key;
 			addr_type = ipv6_addr_type(addr6);
 
 			if (addr_type == IPV6_ADDR_ANY) {
@@ -766,7 +766,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 		if (skb->protocol == htons(ETH_P_IP))
 			tos = old_iph->tos;
 		else if (skb->protocol == htons(ETH_P_IPV6))
-			tos = ipv6_get_dsfield((struct ipv6hdr *)old_iph);
+			tos = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
 	}
 
 	rt = ip_route_output_gre(dev_net(dev), dst, tiph->saddr,
@@ -881,7 +881,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 			iph->ttl = old_iph->ttl;
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 		else if (skb->protocol == htons(ETH_P_IPV6))
-			iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit;
+			iph->ttl = ((const struct ipv6hdr *)old_iph)->hop_limit;
 #endif
 		else
 			iph->ttl = ip4_dst_hoplimit(&rt->dst);
@@ -927,7 +927,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev)
 {
 	struct net_device *tdev = NULL;
 	struct ip_tunnel *tunnel;
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	int hlen = LL_MAX_HEADER;
 	int mtu = ETH_DATA_LEN;
 	int addend = sizeof(struct iphdr) + 4;
@@ -1180,7 +1180,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
 
 static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
 {
-	struct iphdr *iph = (struct iphdr *) skb_mac_header(skb);
+	const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb);
 	memcpy(haddr, &iph->saddr, 4);
 	return 4;
 }
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index d7b2b0987a3b7..c8f48efc5fd3d 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -268,7 +268,7 @@ int ip_local_deliver(struct sk_buff *skb)
 static inline int ip_rcv_options(struct sk_buff *skb)
 {
 	struct ip_options *opt;
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	struct net_device *dev = skb->dev;
 
 	/* It looks as overkill, because not all
@@ -374,7 +374,7 @@ drop:
  */
 int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
 {
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	u32 len;
 
 	/* When the interface is in promisc. mode, drop all the crap
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 3948c86e59ca6..9640900309bbb 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -131,7 +131,7 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
 static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
 	struct sockaddr_in sin;
-	struct iphdr *iph = ip_hdr(skb);
+	const struct iphdr *iph = ip_hdr(skb);
 	__be16 *ports = (__be16 *)skb_transport_header(skb);
 
 	if (skb_transport_offset(skb) + 4 > skb->len)
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 629067571f028..c857f6f49b037 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -27,7 +27,7 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info)
 {
 	struct net *net = dev_net(skb->dev);
 	__be32 spi;
-	struct iphdr *iph = (struct iphdr *)skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct ip_comp_hdr *ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
 	struct xfrm_state *x;
 
@@ -36,7 +36,7 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info)
 		return;
 
 	spi = htonl(ntohs(ipch->cpi));
-	x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr,
+	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
 			      spi, IPPROTO_COMP, AF_INET);
 	if (!x)
 		return;
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index bfc17c5914e7d..ef16377ec73f2 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -319,7 +319,7 @@ static int ipip_err(struct sk_buff *skb, u32 info)
    8 bytes of packet payload. It means, that precise relaying of
    ICMP in the real Internet is absolutely infeasible.
  */
-	struct iphdr *iph = (struct iphdr *)skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
 	struct ip_tunnel *t;
@@ -433,12 +433,12 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct pcpu_tstats *tstats;
-	struct iphdr  *tiph = &tunnel->parms.iph;
+	const struct iphdr  *tiph = &tunnel->parms.iph;
 	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 */
-	struct iphdr  *old_iph = ip_hdr(skb);
+	const struct iphdr  *old_iph = ip_hdr(skb);
 	struct iphdr  *iph;			/* Our new IP header */
 	unsigned int max_headroom;		/* The extra header space needed */
 	__be32 dst = tiph->daddr;
@@ -572,7 +572,7 @@ static void ipip_tunnel_bind_dev(struct net_device *dev)
 {
 	struct net_device *tdev = NULL;
 	struct ip_tunnel *tunnel;
-	struct iphdr *iph;
+	const struct iphdr *iph;
 
 	tunnel = netdev_priv(dev);
 	iph = &tunnel->parms.iph;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 1f62eaeb6de42..c81b9b661d263 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1549,7 +1549,7 @@ static struct notifier_block ip_mr_notifier = {
 static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr)
 {
 	struct iphdr *iph;
-	struct iphdr *old_iph = ip_hdr(skb);
+	const struct iphdr *old_iph = ip_hdr(skb);
 
 	skb_push(skb, sizeof(struct iphdr));
 	skb->transport_header = skb->network_header;
diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c
index 31427fb57aa8a..99cfa28b6d38f 100644
--- a/net/ipv4/netfilter/nf_nat_helper.c
+++ b/net/ipv4/netfilter/nf_nat_helper.c
@@ -153,7 +153,7 @@ void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
 }
 EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust);
 
-static void nf_nat_csum(struct sk_buff *skb, struct iphdr *iph, void *data,
+static void nf_nat_csum(struct sk_buff *skb, const struct iphdr *iph, void *data,
 			int datalen, __sum16 *check, int oldlen)
 {
 	struct rtable *rt = skb_rtable(skb);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 2b50cc2da90a4..abf14dbcb3b9e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -154,7 +154,7 @@ static __inline__ int icmp_filter(struct sock *sk, struct sk_buff *skb)
  * RFC 1122: SHOULD pass TOS value up to the transport layer.
  * -> It does. And not only TOS, but all IP header.
  */
-static int raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash)
+static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 {
 	struct sock *sk;
 	struct hlist_head *head;
@@ -247,7 +247,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 	}
 
 	if (inet->recverr) {
-		struct iphdr *iph = (struct iphdr *)skb->data;
+		const struct iphdr *iph = (const struct iphdr *)skb->data;
 		u8 *payload = skb->data + (iph->ihl << 2);
 
 		if (inet->hdrincl)
@@ -265,7 +265,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
 {
 	int hash;
 	struct sock *raw_sk;
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	struct net *net;
 
 	hash = protocol & (RAW_HTABLE_SIZE - 1);
@@ -273,7 +273,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
 	read_lock(&raw_v4_hashinfo.lock);
 	raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
 	if (raw_sk != NULL) {
-		iph = (struct iphdr *)skb->data;
+		iph = (const struct iphdr *)skb->data;
 		net = dev_net(skb->dev);
 
 		while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol,
@@ -281,7 +281,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
 						skb->dev->ifindex)) != NULL) {
 			raw_err(raw_sk, skb, info);
 			raw_sk = sk_next(raw_sk);
-			iph = (struct iphdr *)skb->data;
+			iph = (const struct iphdr *)skb->data;
 		}
 	}
 	read_unlock(&raw_v4_hashinfo.lock);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e9aee81de3e32..f4b7f806afd8d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1507,7 +1507,7 @@ static inline unsigned short guess_mtu(unsigned short old_mtu)
 	return 68;
 }
 
-unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph,
+unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph,
 				 unsigned short new_mtu,
 				 struct net_device *dev)
 {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f7e6c2c2d2bbc..edf18bd74b875 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -279,7 +279,7 @@ EXPORT_SYMBOL(tcp_v4_connect);
 /*
  * This routine does path mtu discovery as defined in RFC1191.
  */
-static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu)
+static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu)
 {
 	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
@@ -341,7 +341,7 @@ static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu)
 
 void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 {
-	struct iphdr *iph = (struct iphdr *)icmp_skb->data;
+	const struct iphdr *iph = (const struct iphdr *)icmp_skb->data;
 	struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2));
 	struct inet_connection_sock *icsk;
 	struct tcp_sock *tp;
@@ -2527,7 +2527,7 @@ void tcp4_proc_exit(void)
 
 struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 {
-	struct iphdr *iph = skb_gro_network_header(skb);
+	const struct iphdr *iph = skb_gro_network_header(skb);
 
 	switch (skb->ip_summed) {
 	case CHECKSUM_COMPLETE:
@@ -2548,7 +2548,7 @@ struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 
 int tcp4_gro_complete(struct sk_buff *skb)
 {
-	struct iphdr *iph = ip_hdr(skb);
+	const struct iphdr *iph = ip_hdr(skb);
 	struct tcphdr *th = tcp_hdr(skb);
 
 	th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index a15c8fb653af2..bc0dab2593e05 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -578,7 +578,7 @@ found:
 void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 {
 	struct inet_sock *inet;
-	struct iphdr *iph = (struct iphdr *)skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2));
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index d20a05e970d83..59b1340fb3bf1 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -102,7 +102,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 static void
 _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 {
-	struct iphdr *iph = ip_hdr(skb);
+	const struct iphdr *iph = ip_hdr(skb);
 	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
 	struct flowi4 *fl4 = &fl->u.ip4;
 
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 1717c64628d1c..ea983ae96ae64 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -55,7 +55,7 @@ xfrm4_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl,
 
 int xfrm4_extract_header(struct sk_buff *skb)
 {
-	struct iphdr *iph = ip_hdr(skb);
+	const struct iphdr *iph = ip_hdr(skb);
 
 	XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph);
 	XFRM_MODE_SKB_CB(skb)->id = iph->id;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 129d7e1f311c7..c663a3b709245 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1283,7 +1283,7 @@ static int ipv6_count_addresses(struct inet6_dev *idev)
 	return cnt;
 }
 
-int ipv6_chk_addr(struct net *net, struct in6_addr *addr,
+int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 		  struct net_device *dev, int strict)
 {
 	struct inet6_ifaddr *ifp;
@@ -1326,7 +1326,7 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
 	return false;
 }
 
-int ipv6_chk_prefix(struct in6_addr *addr, struct net_device *dev)
+int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev)
 {
 	struct inet6_dev *idev;
 	struct inet6_ifaddr *ifa;
@@ -1457,7 +1457,7 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 
 /* Join to solicited addr multicast group. */
 
-void addrconf_join_solict(struct net_device *dev, struct in6_addr *addr)
+void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr)
 {
 	struct in6_addr maddr;
 
@@ -1468,7 +1468,7 @@ void addrconf_join_solict(struct net_device *dev, struct in6_addr *addr)
 	ipv6_dev_mc_inc(dev, &maddr);
 }
 
-void addrconf_leave_solict(struct inet6_dev *idev, struct in6_addr *addr)
+void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct in6_addr maddr;
 
@@ -2113,7 +2113,7 @@ err_exit:
 /*
  *	Manual configuration of address on an interface
  */
-static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx,
+static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *pfx,
 			  unsigned int plen, __u8 ifa_flags, __u32 prefered_lft,
 			  __u32 valid_lft)
 {
@@ -2187,7 +2187,7 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx,
 	return PTR_ERR(ifp);
 }
 
-static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx,
+static int inet6_addr_del(struct net *net, int ifindex, const struct in6_addr *pfx,
 			  unsigned int plen)
 {
 	struct inet6_ifaddr *ifp;
@@ -2350,7 +2350,7 @@ static void init_loopback(struct net_device *dev)
 	add_addr(idev, &in6addr_loopback, 128, IFA_HOST);
 }
 
-static void addrconf_add_linklocal(struct inet6_dev *idev, struct in6_addr *addr)
+static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct inet6_ifaddr * ifp;
 	u32 addr_flags = IFA_F_PERMANENT;
@@ -3121,7 +3121,7 @@ void if6_proc_exit(void)
 
 #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
 /* Check if address is a home address configured on any interface. */
-int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr)
+int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
 {
 	int ret = 0;
 	struct inet6_ifaddr *ifp = NULL;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index afcc7099f96de..b7919f901fbf7 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -740,7 +740,7 @@ static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
 
 static int ipv6_gso_send_check(struct sk_buff *skb)
 {
-	struct ipv6hdr *ipv6h;
+	const struct ipv6hdr *ipv6h;
 	const struct inet6_protocol *ops;
 	int err = -EINVAL;
 
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 0e5e943446f08..674255f5e6b74 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -44,7 +44,7 @@
 
 #include <net/checksum.h>
 
-static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr);
+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_RWLOCK(ipv6_sk_ac_lock);
@@ -54,7 +54,7 @@ static DEFINE_RWLOCK(ipv6_sk_ac_lock);
  *	socket join an anycast group
  */
 
-int ipv6_sock_ac_join(struct sock *sk, int ifindex, struct in6_addr *addr)
+int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net_device *dev = NULL;
@@ -145,7 +145,7 @@ error:
 /*
  *	socket leave an anycast group
  */
-int ipv6_sock_ac_drop(struct sock *sk, int ifindex, struct in6_addr *addr)
+int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net_device *dev;
@@ -252,7 +252,7 @@ static void aca_put(struct ifacaddr6 *ac)
 /*
  *	device anycast group inc (add if not found)
  */
-int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr)
+int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr)
 {
 	struct ifacaddr6 *aca;
 	struct inet6_dev *idev;
@@ -324,7 +324,7 @@ out:
 /*
  *	device anycast group decrement
  */
-int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr)
+int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct ifacaddr6 *aca, *prev_aca;
 
@@ -358,7 +358,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr)
 }
 
 /* called with rcu_read_lock() */
-static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr)
+static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr)
 {
 	struct inet6_dev *idev = __in6_dev_get(dev);
 
@@ -371,7 +371,7 @@ static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr)
  *	check if the interface has this anycast address
  *	called with rcu_read_lock()
  */
-static int ipv6_chk_acast_dev(struct net_device *dev, struct in6_addr *addr)
+static int ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *addr)
 {
 	struct inet6_dev *idev;
 	struct ifacaddr6 *aca;
@@ -392,7 +392,7 @@ static int ipv6_chk_acast_dev(struct net_device *dev, struct in6_addr *addr)
  *	check if given interface (or any, if dev==0) has this anycast address
  */
 int ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
-			struct in6_addr *addr)
+			const struct in6_addr *addr)
 {
 	int found = 0;
 
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 5aa8ec88f1946..e97b4b7ca2f2f 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -430,7 +430,7 @@ static void esp6_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;
+	const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
 	struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data + offset);
 	struct xfrm_state *x;
 
@@ -438,7 +438,8 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	    type != ICMPV6_PKT_TOOBIG)
 		return;
 
-	x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6);
+	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+			      esph->spi, IPPROTO_ESP, AF_INET6);
 	if (!x)
 		return;
 	printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%pI6\n",
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 83cb4f9add81b..11900417b1cc0 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -372,7 +372,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct sock *sk;
 	struct ipv6_pinfo *np;
-	struct in6_addr *saddr = NULL;
+	const struct in6_addr *saddr = NULL;
 	struct dst_entry *dst;
 	struct icmp6hdr tmp_hdr;
 	struct flowi6 fl6;
@@ -521,7 +521,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	struct sock *sk;
 	struct inet6_dev *idev;
 	struct ipv6_pinfo *np;
-	struct in6_addr *saddr = NULL;
+	const struct in6_addr *saddr = NULL;
 	struct icmp6hdr *icmph = icmp6_hdr(skb);
 	struct icmp6hdr tmp_hdr;
 	struct flowi6 fl6;
@@ -645,8 +645,8 @@ static int icmpv6_rcv(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	struct inet6_dev *idev = __in6_dev_get(dev);
-	struct in6_addr *saddr, *daddr;
-	struct ipv6hdr *orig_hdr;
+	const struct in6_addr *saddr, *daddr;
+	const struct ipv6hdr *orig_hdr;
 	struct icmp6hdr *hdr;
 	u8 type;
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7548905e79e11..dd88df0a5d7f8 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -134,9 +134,9 @@ static __inline__ u32 fib6_new_sernum(void)
 # define BITOP_BE32_SWIZZLE	0
 #endif
 
-static __inline__ __be32 addr_bit_set(void *token, int fn_bit)
+static __inline__ __be32 addr_bit_set(const void *token, int fn_bit)
 {
-	__be32 *addr = token;
+	const __be32 *addr = token;
 	/*
 	 * Here,
 	 * 	1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)
@@ -822,7 +822,7 @@ st_failure:
 
 struct lookup_args {
 	int		offset;		/* key offset on rt6_info	*/
-	struct in6_addr	*addr;		/* search key			*/
+	const struct in6_addr	*addr;		/* search key			*/
 };
 
 static struct fib6_node * fib6_lookup_1(struct fib6_node *root,
@@ -881,8 +881,8 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root,
 	return NULL;
 }
 
-struct fib6_node * fib6_lookup(struct fib6_node *root, struct in6_addr *daddr,
-			       struct in6_addr *saddr)
+struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
+			       const struct in6_addr *saddr)
 {
 	struct fib6_node *fn;
 	struct lookup_args args[] = {
@@ -916,7 +916,7 @@ struct fib6_node * fib6_lookup(struct fib6_node *root, struct in6_addr *daddr,
 
 
 static struct fib6_node * fib6_locate_1(struct fib6_node *root,
-					struct in6_addr *addr,
+					const struct in6_addr *addr,
 					int plen, int offset)
 {
 	struct fib6_node *fn;
@@ -946,8 +946,8 @@ static struct fib6_node * fib6_locate_1(struct fib6_node *root,
 }
 
 struct fib6_node * fib6_locate(struct fib6_node *root,
-			       struct in6_addr *daddr, int dst_len,
-			       struct in6_addr *saddr, int src_len)
+			       const struct in6_addr *daddr, int dst_len,
+			       const struct in6_addr *saddr, int src_len)
 {
 	struct fib6_node *fn;
 
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index a83e9209cecc3..027c7ff6f1e53 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -57,7 +57,7 @@ inline 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)
 {
-	struct ipv6hdr *hdr;
+	const struct ipv6hdr *hdr;
 	u32 		pkt_len;
 	struct inet6_dev *idev;
 	struct net *net = dev_net(skb->dev);
@@ -186,7 +186,7 @@ resubmit:
 		int ret;
 
 		if (ipprot->flags & INET6_PROTO_FINAL) {
-			struct ipv6hdr *hdr;
+			const struct ipv6hdr *hdr;
 
 			/* Free reference early: we don't need it any more,
 			   and it may hold ip_conntrack module loaded
@@ -242,7 +242,7 @@ int ip6_input(struct sk_buff *skb)
 
 int ip6_mc_input(struct sk_buff *skb)
 {
-	struct ipv6hdr *hdr;
+	const struct ipv6hdr *hdr;
 	int deliver;
 
 	IP6_UPD_PO_STATS_BH(dev_net(skb_dst(skb)->dev),
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index c614d02bf429c..4cfbb24b9e040 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -869,9 +869,9 @@ fail:
 	return err;
 }
 
-static inline int ip6_rt_check(struct rt6key *rt_key,
-			       struct in6_addr *fl_addr,
-			       struct in6_addr *addr_cache)
+static inline int ip6_rt_check(const struct rt6key *rt_key,
+			       const struct in6_addr *fl_addr,
+			       const struct in6_addr *addr_cache)
 {
 	return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) &&
 		(addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache));
@@ -879,7 +879,7 @@ static inline int ip6_rt_check(struct rt6key *rt_key,
 
 static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
 					  struct dst_entry *dst,
-					  struct flowi6 *fl6)
+					  const struct flowi6 *fl6)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct rt6_info *rt = (struct rt6_info *)dst;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index c1b1bd312df24..9dd0e964b8bda 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -162,7 +162,7 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
 static struct ip6_tnl *
-ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local)
+ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local)
 {
 	unsigned int h0 = HASH(remote);
 	unsigned int h1 = HASH(local);
@@ -194,10 +194,10 @@ ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local)
  **/
 
 static struct ip6_tnl __rcu **
-ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p)
+ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct ip6_tnl_parm *p)
 {
-	struct in6_addr *remote = &p->raddr;
-	struct in6_addr *local = &p->laddr;
+	const struct in6_addr *remote = &p->raddr;
+	const struct in6_addr *local = &p->laddr;
 	unsigned h = 0;
 	int prio = 0;
 
@@ -321,8 +321,8 @@ failed:
 static struct ip6_tnl *ip6_tnl_locate(struct net *net,
 		struct ip6_tnl_parm *p, int create)
 {
-	struct in6_addr *remote = &p->raddr;
-	struct in6_addr *local = &p->laddr;
+	const struct in6_addr *remote = &p->raddr;
+	const struct in6_addr *local = &p->laddr;
 	struct ip6_tnl __rcu **tp;
 	struct ip6_tnl *t;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
@@ -374,7 +374,7 @@ ip6_tnl_dev_uninit(struct net_device *dev)
 static __u16
 parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw)
 {
-	struct ipv6hdr *ipv6h = (struct ipv6hdr *) raw;
+	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw;
 	__u8 nexthdr = ipv6h->nexthdr;
 	__u16 off = sizeof (*ipv6h);
 
@@ -435,7 +435,7 @@ static int
 ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 	    u8 *type, u8 *code, int *msg, __u32 *info, int offset)
 {
-	struct ipv6hdr *ipv6h = (struct ipv6hdr *) skb->data;
+	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) skb->data;
 	struct ip6_tnl *t;
 	int rel_msg = 0;
 	u8 rel_type = ICMPV6_DEST_UNREACH;
@@ -535,7 +535,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	__u32 rel_info = ntohl(info);
 	int err;
 	struct sk_buff *skb2;
-	struct iphdr *eiph;
+	const struct iphdr *eiph;
 	struct rtable *rt;
 
 	err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code,
@@ -669,8 +669,8 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	return 0;
 }
 
-static void ip4ip6_dscp_ecn_decapsulate(struct ip6_tnl *t,
-					struct ipv6hdr *ipv6h,
+static void ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t,
+					const struct ipv6hdr *ipv6h,
 					struct sk_buff *skb)
 {
 	__u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK;
@@ -682,8 +682,8 @@ static void ip4ip6_dscp_ecn_decapsulate(struct ip6_tnl *t,
 		IP_ECN_set_ce(ip_hdr(skb));
 }
 
-static void ip6ip6_dscp_ecn_decapsulate(struct ip6_tnl *t,
-					struct ipv6hdr *ipv6h,
+static void ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t,
+					const struct ipv6hdr *ipv6h,
 					struct sk_buff *skb)
 {
 	if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
@@ -726,12 +726,12 @@ static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t)
 
 static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
 		       __u8 ipproto,
-		       void (*dscp_ecn_decapsulate)(struct ip6_tnl *t,
-						    struct ipv6hdr *ipv6h,
+		       void (*dscp_ecn_decapsulate)(const struct ip6_tnl *t,
+						    const struct ipv6hdr *ipv6h,
 						    struct sk_buff *skb))
 {
 	struct ip6_tnl *t;
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 
 	rcu_read_lock();
 
@@ -828,7 +828,7 @@ static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit)
  **/
 
 static inline int
-ip6_tnl_addr_conflict(struct ip6_tnl *t, struct ipv6hdr *hdr)
+ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr)
 {
 	return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
 }
@@ -1005,7 +1005,7 @@ static inline int
 ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct iphdr  *iph = ip_hdr(skb);
+	const struct iphdr  *iph = ip_hdr(skb);
 	int encap_limit = -1;
 	struct flowi6 fl6;
 	__u8 dsfield;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 29e48593bf22c..82a809901f8e9 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -989,8 +989,8 @@ static int mif6_add(struct net *net, struct mr6_table *mrt,
 }
 
 static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt,
-					   struct in6_addr *origin,
-					   struct in6_addr *mcastgrp)
+					   const struct in6_addr *origin,
+					   const struct in6_addr *mcastgrp)
 {
 	int line = MFC6_HASH(mcastgrp, origin);
 	struct mfc6_cache *c;
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 85cccd6ed0b73..bba658d9a03cf 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -55,7 +55,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 {
 	struct net *net = dev_net(skb->dev);
 	__be32 spi;
-	struct ipv6hdr *iph = (struct ipv6hdr*)skb->data;
+	const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
 	struct ip_comp_hdr *ipcomph =
 		(struct ip_comp_hdr *)(skb->data + offset);
 	struct xfrm_state *x;
@@ -64,7 +64,8 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		return;
 
 	spi = htonl(ntohs(ipcomph->cpi));
-	x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6);
+	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+			      spi, IPPROTO_COMP, AF_INET6);
 	if (!x)
 		return;
 
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 76b893771e6e0..ff62e33ead07d 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -92,16 +92,16 @@ static void mld_gq_timer_expire(unsigned long data);
 static void mld_ifc_timer_expire(unsigned long data);
 static void mld_ifc_event(struct inet6_dev *idev);
 static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc);
-static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *addr);
+static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *addr);
 static void mld_clear_delrec(struct inet6_dev *idev);
 static int sf_setstate(struct ifmcaddr6 *pmc);
 static void sf_markstate(struct ifmcaddr6 *pmc);
 static void ip6_mc_clear_src(struct ifmcaddr6 *pmc);
-static int ip6_mc_del_src(struct inet6_dev *idev, struct in6_addr *pmca,
-			  int sfmode, int sfcount, struct in6_addr *psfsrc,
+static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca,
+			  int sfmode, int sfcount, const struct in6_addr *psfsrc,
 			  int delta);
-static int ip6_mc_add_src(struct inet6_dev *idev, struct in6_addr *pmca,
-			  int sfmode, int sfcount, struct in6_addr *psfsrc,
+static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
+			  int sfmode, int sfcount, const struct in6_addr *psfsrc,
 			  int delta);
 static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 			    struct inet6_dev *idev);
@@ -250,7 +250,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 /* called with rcu_read_lock() */
 static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net,
-					     struct in6_addr *group,
+					     const struct in6_addr *group,
 					     int ifindex)
 {
 	struct net_device *dev = NULL;
@@ -451,7 +451,7 @@ done:
 
 int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf)
 {
-	struct in6_addr *group;
+	const struct in6_addr *group;
 	struct ipv6_mc_socklist *pmc;
 	struct inet6_dev *idev;
 	struct ipv6_pinfo *inet6 = inet6_sk(sk);
@@ -542,7 +542,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 	struct group_filter __user *optval, int __user *optlen)
 {
 	int err, i, count, copycount;
-	struct in6_addr *group;
+	const struct in6_addr *group;
 	struct ipv6_mc_socklist *pmc;
 	struct inet6_dev *idev;
 	struct ipv6_pinfo *inet6 = inet6_sk(sk);
@@ -752,7 +752,7 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 	spin_unlock_bh(&idev->mc_lock);
 }
 
-static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *pmca)
+static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca)
 {
 	struct ifmcaddr6 *pmc, *pmc_prev;
 	struct ip6_sf_list *psf, *psf_next;
@@ -1052,7 +1052,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime)
 
 /* mark EXCLUDE-mode sources */
 static int mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs,
-	struct in6_addr *srcs)
+	const struct in6_addr *srcs)
 {
 	struct ip6_sf_list *psf;
 	int i, scount;
@@ -1080,7 +1080,7 @@ static int mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs,
 }
 
 static int mld_marksources(struct ifmcaddr6 *pmc, int nsrcs,
-	struct in6_addr *srcs)
+	const struct in6_addr *srcs)
 {
 	struct ip6_sf_list *psf;
 	int i, scount;
@@ -1115,7 +1115,7 @@ int igmp6_event_query(struct sk_buff *skb)
 {
 	struct mld2_query *mlh2 = NULL;
 	struct ifmcaddr6 *ma;
-	struct in6_addr *group;
+	const struct in6_addr *group;
 	unsigned long max_delay;
 	struct inet6_dev *idev;
 	struct mld_msg *mld;
@@ -1821,7 +1821,7 @@ err_out:
 }
 
 static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode,
-	struct in6_addr *psfsrc)
+	const struct in6_addr *psfsrc)
 {
 	struct ip6_sf_list *psf, *psf_prev;
 	int rv = 0;
@@ -1857,8 +1857,8 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode,
 	return rv;
 }
 
-static int ip6_mc_del_src(struct inet6_dev *idev, struct in6_addr *pmca,
-			  int sfmode, int sfcount, struct in6_addr *psfsrc,
+static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca,
+			  int sfmode, int sfcount, const struct in6_addr *psfsrc,
 			  int delta)
 {
 	struct ifmcaddr6 *pmc;
@@ -1918,7 +1918,7 @@ static int ip6_mc_del_src(struct inet6_dev *idev, struct in6_addr *pmca,
  * Add multicast single-source filter to the interface list
  */
 static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode,
-	struct in6_addr *psfsrc, int delta)
+	const struct in6_addr *psfsrc, int delta)
 {
 	struct ip6_sf_list *psf, *psf_prev;
 
@@ -2021,8 +2021,8 @@ static int sf_setstate(struct ifmcaddr6 *pmc)
 /*
  * Add multicast source filter list to the interface list
  */
-static int ip6_mc_add_src(struct inet6_dev *idev, struct in6_addr *pmca,
-			  int sfmode, int sfcount, struct in6_addr *psfsrc,
+static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
+			  int sfmode, int sfcount, const struct in6_addr *psfsrc,
 			  int delta)
 {
 	struct ifmcaddr6 *pmc;
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index 9b210482fb056..43242e6e61030 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -126,7 +126,7 @@ static struct mip6_report_rate_limiter mip6_report_rl = {
 
 static int mip6_destopt_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct ipv6_destopt_hdr *destopt = (struct ipv6_destopt_hdr *)skb->data;
 	int err = destopt->nexthdr;
 
@@ -181,8 +181,8 @@ static int mip6_destopt_output(struct xfrm_state *x, struct sk_buff *skb)
 }
 
 static inline int mip6_report_rl_allow(struct timeval *stamp,
-				       struct in6_addr *dst,
-				       struct in6_addr *src, int iif)
+				       const struct in6_addr *dst,
+				       const struct in6_addr *src, int iif)
 {
 	int allow = 0;
 
@@ -349,7 +349,7 @@ static const struct xfrm_type mip6_destopt_type =
 
 static int mip6_rthdr_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct rt2_hdr *rt2 = (struct rt2_hdr *)skb->data;
 	int err = rt2->rt_hdr.nexthdr;
 
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 01a0ffc7b402c..69aacd18e0662 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -324,7 +324,7 @@ static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p,
 	return lladdr + prepad;
 }
 
-int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int dir)
+int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir)
 {
 	switch (dev->type) {
 	case ARPHRD_ETHER:
@@ -748,8 +748,8 @@ static int pndisc_is_router(const void *pkey,
 static void ndisc_recv_ns(struct sk_buff *skb)
 {
 	struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
-	struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
-	struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
+	const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
+	const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
 	u8 *lladdr = NULL;
 	u32 ndoptlen = skb->tail - (skb->transport_header +
 				    offsetof(struct nd_msg, opt));
@@ -924,8 +924,8 @@ out:
 static void ndisc_recv_na(struct sk_buff *skb)
 {
 	struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
-	struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
-	struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
+	const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
+	const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
 	u8 *lladdr = NULL;
 	u32 ndoptlen = skb->tail - (skb->transport_header +
 				    offsetof(struct nd_msg, opt));
@@ -1038,7 +1038,7 @@ static void ndisc_recv_rs(struct sk_buff *skb)
 	unsigned long ndoptlen = skb->len - sizeof(*rs_msg);
 	struct neighbour *neigh;
 	struct inet6_dev *idev;
-	struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
+	const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
 	struct ndisc_options ndopts;
 	u8 *lladdr = NULL;
 
@@ -1435,8 +1435,8 @@ static void ndisc_redirect_rcv(struct sk_buff *skb)
 {
 	struct inet6_dev *in6_dev;
 	struct icmp6hdr *icmph;
-	struct in6_addr *dest;
-	struct in6_addr *target;	/* new first hop to destination */
+	const struct in6_addr *dest;
+	const struct in6_addr *target;	/* new first hop to destination */
 	struct neighbour *neigh;
 	int on_link = 0;
 	struct ndisc_options ndopts;
@@ -1469,7 +1469,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb)
 	}
 
 	icmph = icmp6_hdr(skb);
-	target = (struct in6_addr *) (icmph + 1);
+	target = (const struct in6_addr *) (icmph + 1);
 	dest = target + 1;
 
 	if (ipv6_addr_is_multicast(dest)) {
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 28bc1f644b7b3..30fcee4654486 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -13,7 +13,7 @@
 int ip6_route_me_harder(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct dst_entry *dst;
 	struct flowi6 fl6 = {
 		.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
@@ -67,7 +67,7 @@ static void nf_ip6_saveroute(const struct sk_buff *skb,
 	struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
 	if (entry->hook == NF_INET_LOCAL_OUT) {
-		struct ipv6hdr *iph = ipv6_hdr(skb);
+		const struct ipv6hdr *iph = ipv6_hdr(skb);
 
 		rt_info->daddr = iph->daddr;
 		rt_info->saddr = iph->saddr;
@@ -81,7 +81,7 @@ static int nf_ip6_reroute(struct sk_buff *skb,
 	struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
 
 	if (entry->hook == NF_INET_LOCAL_OUT) {
-		struct ipv6hdr *iph = ipv6_hdr(skb);
+		const struct ipv6hdr *iph = ipv6_hdr(skb);
 		if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
 		    !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
 		    skb->mark != rt_info->mark)
@@ -108,7 +108,7 @@ static int nf_ip6_route(struct net *net, struct dst_entry **dst,
 __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
 			     unsigned int dataoff, u_int8_t protocol)
 {
-	struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	__sum16 csum = 0;
 
 	switch (skb->ip_summed) {
@@ -142,7 +142,7 @@ static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook,
 				       unsigned int dataoff, unsigned int len,
 				       u_int8_t protocol)
 {
-	struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	__wsum hsum;
 	__sum16 csum = 0;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 4a1c3b46c56b5..e5e5425fe7d0b 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -67,8 +67,8 @@ static struct raw_hashinfo raw_v6_hashinfo = {
 };
 
 static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
-		unsigned short num, struct in6_addr *loc_addr,
-		struct in6_addr *rmt_addr, int dif)
+		unsigned short num, const struct in6_addr *loc_addr,
+		const struct in6_addr *rmt_addr, int dif)
 {
 	struct hlist_node *node;
 	int is_multicast = ipv6_addr_is_multicast(loc_addr);
@@ -154,8 +154,8 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister);
  */
 static int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
 {
-	struct in6_addr *saddr;
-	struct in6_addr *daddr;
+	const struct in6_addr *saddr;
+	const struct in6_addr *daddr;
 	struct sock *sk;
 	int delivered = 0;
 	__u8 hash;
@@ -348,7 +348,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
 {
 	struct sock *sk;
 	int hash;
-	struct in6_addr *saddr, *daddr;
+	const struct in6_addr *saddr, *daddr;
 	struct net *net;
 
 	hash = nexthdr & (RAW_HTABLE_SIZE - 1);
@@ -357,7 +357,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
 	sk = sk_head(&raw_v6_hashinfo.ht[hash]);
 	if (sk != NULL) {
 		/* Note: ipv6_hdr(skb) != skb->data */
-		struct ipv6hdr *ip6h = (struct ipv6hdr *)skb->data;
+		const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data;
 		saddr = &ip6h->saddr;
 		daddr = &ip6h->daddr;
 		net = dev_net(skb->dev);
@@ -1231,7 +1231,7 @@ struct proto rawv6_prot = {
 static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
 {
 	struct ipv6_pinfo *np = inet6_sk(sp);
-	struct in6_addr *dest, *src;
+	const struct in6_addr *dest, *src;
 	__u16 destp, srcp;
 
 	dest  = &np->daddr;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 07beeb06f752d..7b954e2539d08 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -224,7 +224,7 @@ out:
 }
 
 static __inline__ struct frag_queue *
-fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst)
+fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6_addr *dst)
 {
 	struct inet_frag_queue *q;
 	struct ip6_create_arg arg;
@@ -535,7 +535,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 {
 	struct frag_hdr *fhdr;
 	struct frag_queue *fq;
-	struct ipv6hdr *hdr = ipv6_hdr(skb);
+	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct net *net = dev_net(skb_dst(skb)->dev);
 
 	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index af26cc1073cb3..852fc28ca8180 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -89,12 +89,12 @@ static void		ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct rt6_info *rt6_add_route_info(struct net *net,
-					   struct in6_addr *prefix, int prefixlen,
-					   struct in6_addr *gwaddr, int ifindex,
+					   const struct in6_addr *prefix, int prefixlen,
+					   const struct in6_addr *gwaddr, int ifindex,
 					   unsigned pref);
 static struct rt6_info *rt6_get_route_info(struct net *net,
-					   struct in6_addr *prefix, int prefixlen,
-					   struct in6_addr *gwaddr, int ifindex);
+					   const struct in6_addr *prefix, int prefixlen,
+					   const struct in6_addr *gwaddr, int ifindex);
 #endif
 
 static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
@@ -283,7 +283,7 @@ static __inline__ int rt6_check_expired(const struct rt6_info *rt)
 		time_after(jiffies, rt->rt6i_expires);
 }
 
-static inline int rt6_need_strict(struct in6_addr *daddr)
+static inline int rt6_need_strict(const struct in6_addr *daddr)
 {
 	return ipv6_addr_type(daddr) &
 		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
@@ -295,7 +295,7 @@ static inline int rt6_need_strict(struct in6_addr *daddr)
 
 static inline struct rt6_info *rt6_device_match(struct net *net,
 						    struct rt6_info *rt,
-						    struct in6_addr *saddr,
+						    const struct in6_addr *saddr,
 						    int oif,
 						    int flags)
 {
@@ -507,7 +507,7 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
-		  struct in6_addr *gwaddr)
+		  const struct in6_addr *gwaddr)
 {
 	struct net *net = dev_net(dev);
 	struct route_info *rinfo = (struct route_info *) opt;
@@ -670,8 +670,8 @@ int ip6_ins_rt(struct rt6_info *rt)
 	return __ip6_ins_rt(rt, &info);
 }
 
-static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr,
-				      struct in6_addr *saddr)
+static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_addr *daddr,
+				      const struct in6_addr *saddr)
 {
 	struct rt6_info *rt;
 
@@ -739,7 +739,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad
 	return rt;
 }
 
-static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *daddr)
+static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, const struct in6_addr *daddr)
 {
 	struct rt6_info *rt = ip6_rt_copy(ort);
 	if (rt) {
@@ -830,7 +830,7 @@ static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *
 
 void ip6_route_input(struct sk_buff *skb)
 {
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct net *net = dev_net(skb->dev);
 	int flags = RT6_LOOKUP_F_HAS_SADDR;
 	struct flowi6 fl6 = {
@@ -1272,7 +1272,7 @@ int ip6_route_add(struct fib6_config *cfg)
 	}
 
 	if (cfg->fc_flags & RTF_GATEWAY) {
-		struct in6_addr *gw_addr;
+		const struct in6_addr *gw_addr;
 		int gwa_type;
 
 		gw_addr = &cfg->fc_gateway;
@@ -1512,9 +1512,9 @@ out:
 	return rt;
 };
 
-static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
-					   struct in6_addr *src,
-					   struct in6_addr *gateway,
+static struct rt6_info *ip6_route_redirect(const struct in6_addr *dest,
+					   const struct in6_addr *src,
+					   const struct in6_addr *gateway,
 					   struct net_device *dev)
 {
 	int flags = RT6_LOOKUP_F_HAS_SADDR;
@@ -1536,8 +1536,8 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
 						   flags, __ip6_route_redirect);
 }
 
-void rt6_redirect(struct in6_addr *dest, struct in6_addr *src,
-		  struct in6_addr *saddr,
+void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
+		  const struct in6_addr *saddr,
 		  struct neighbour *neigh, u8 *lladdr, int on_link)
 {
 	struct rt6_info *rt, *nrt = NULL;
@@ -1611,7 +1611,7 @@ out:
  *	i.e. Path MTU discovery
  */
 
-static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr,
+static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr *saddr,
 			     struct net *net, u32 pmtu, int ifindex)
 {
 	struct rt6_info *rt, *nrt;
@@ -1696,7 +1696,7 @@ out:
 	dst_release(&rt->dst);
 }
 
-void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
+void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *saddr,
 			struct net_device *dev, u32 pmtu)
 {
 	struct net *net = dev_net(dev);
@@ -1756,8 +1756,8 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct rt6_info *rt6_get_route_info(struct net *net,
-					   struct in6_addr *prefix, int prefixlen,
-					   struct in6_addr *gwaddr, int ifindex)
+					   const struct in6_addr *prefix, int prefixlen,
+					   const struct in6_addr *gwaddr, int ifindex)
 {
 	struct fib6_node *fn;
 	struct rt6_info *rt = NULL;
@@ -1788,8 +1788,8 @@ out:
 }
 
 static struct rt6_info *rt6_add_route_info(struct net *net,
-					   struct in6_addr *prefix, int prefixlen,
-					   struct in6_addr *gwaddr, int ifindex,
+					   const struct in6_addr *prefix, int prefixlen,
+					   const struct in6_addr *gwaddr, int ifindex,
 					   unsigned pref)
 {
 	struct fib6_config cfg = {
@@ -1817,7 +1817,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 }
 #endif
 
-struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev)
+struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev)
 {
 	struct rt6_info *rt;
 	struct fib6_table *table;
@@ -1839,7 +1839,7 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d
 	return rt;
 }
 
-struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr,
+struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
 				     struct net_device *dev,
 				     unsigned int pref)
 {
@@ -2049,7 +2049,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 
 int ip6_route_get_saddr(struct net *net,
 			struct rt6_info *rt,
-			struct in6_addr *daddr,
+			const struct in6_addr *daddr,
 			unsigned int prefs,
 			struct in6_addr *saddr)
 {
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 43b33373adb2e..34d896426701a 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -452,7 +452,7 @@ out:
 }
 
 static int
-isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t)
+isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t)
 {
 	struct ip_tunnel_prl_entry *p;
 	int ok = 1;
@@ -465,7 +465,8 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t)
 		else
 			skb->ndisc_nodetype = NDISC_NODETYPE_NODEFAULT;
 	} else {
-		struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr;
+		const struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr;
+
 		if (ipv6_addr_is_isatap(addr6) &&
 		    (addr6->s6_addr32[3] == iph->saddr) &&
 		    ipv6_chk_prefix(addr6, t->dev))
@@ -499,7 +500,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
    8 bytes of packet payload. It means, that precise relaying of
    ICMP in the real Internet is absolutely infeasible.
  */
-	struct iphdr *iph = (struct iphdr*)skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
 	struct ip_tunnel *t;
@@ -557,7 +558,7 @@ out:
 	return err;
 }
 
-static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
+static inline void ipip6_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb)
 {
 	if (INET_ECN_is_ce(iph->tos))
 		IP6_ECN_set_ce(ipv6_hdr(skb));
@@ -565,7 +566,7 @@ static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
 
 static int ipip6_rcv(struct sk_buff *skb)
 {
-	struct iphdr *iph;
+	const struct iphdr *iph;
 	struct ip_tunnel *tunnel;
 
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
@@ -621,7 +622,7 @@ out:
  * comes from 6rd / 6to4 (RFC 3056) addr space.
  */
 static inline
-__be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel)
+__be32 try_6rd(const struct in6_addr *v6dst, struct ip_tunnel *tunnel)
 {
 	__be32 dst = 0;
 
@@ -664,8 +665,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct pcpu_tstats *tstats;
-	struct iphdr  *tiph = &tunnel->parms.iph;
-	struct ipv6hdr *iph6 = ipv6_hdr(skb);
+	const struct iphdr  *tiph = &tunnel->parms.iph;
+	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 */
@@ -674,7 +675,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	unsigned int max_headroom;		/* The extra header space needed */
 	__be32 dst = tiph->daddr;
 	int    mtu;
-	struct in6_addr *addr6;
+	const struct in6_addr *addr6;
 	int addr_type;
 
 	if (skb->protocol != htons(ETH_P_IPV6))
@@ -693,7 +694,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			goto tx_error;
 		}
 
-		addr6 = (struct in6_addr*)&neigh->primary_key;
+		addr6 = (const struct in6_addr*)&neigh->primary_key;
 		addr_type = ipv6_addr_type(addr6);
 
 		if ((addr_type & IPV6_ADDR_UNICAST) &&
@@ -718,7 +719,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			goto tx_error;
 		}
 
-		addr6 = (struct in6_addr*)&neigh->primary_key;
+		addr6 = (const struct in6_addr*)&neigh->primary_key;
 		addr_type = ipv6_addr_type(addr6);
 
 		if (addr_type == IPV6_ADDR_ANY) {
@@ -849,7 +850,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 {
 	struct net_device *tdev = NULL;
 	struct ip_tunnel *tunnel;
-	struct iphdr *iph;
+	const struct iphdr *iph;
 
 	tunnel = netdev_priv(dev);
 	iph = &tunnel->parms.iph;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 352c26081f5d5..8b9644a8b6978 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -66,7 +66,7 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
 		      ipv6_cookie_scratch);
 
-static u32 cookie_hash(struct in6_addr *saddr, struct in6_addr *daddr,
+static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr,
 		       __be16 sport, __be16 dport, u32 count, int c)
 {
 	__u32 *tmp = __get_cpu_var(ipv6_cookie_scratch);
@@ -86,7 +86,8 @@ static u32 cookie_hash(struct in6_addr *saddr, struct in6_addr *daddr,
 	return tmp[17];
 }
 
-static __u32 secure_tcp_syn_cookie(struct in6_addr *saddr, struct in6_addr *daddr,
+static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
+				   const struct in6_addr *daddr,
 				   __be16 sport, __be16 dport, __u32 sseq,
 				   __u32 count, __u32 data)
 {
@@ -96,8 +97,8 @@ static __u32 secure_tcp_syn_cookie(struct in6_addr *saddr, struct in6_addr *dadd
 		& COOKIEMASK));
 }
 
-static __u32 check_tcp_syn_cookie(__u32 cookie, struct in6_addr *saddr,
-				  struct in6_addr *daddr, __be16 sport,
+static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr,
+				  const struct in6_addr *daddr, __be16 sport,
 				  __be16 dport, __u32 sseq, __u32 count,
 				  __u32 maxdiff)
 {
@@ -116,7 +117,7 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, struct in6_addr *saddr,
 
 __u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
 {
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	const struct tcphdr *th = tcp_hdr(skb);
 	int mssind;
 	const __u16 mss = *mssp;
@@ -138,7 +139,7 @@ __u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
 
 static inline int cookie_check(struct sk_buff *skb, __u32 cookie)
 {
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	const struct tcphdr *th = tcp_hdr(skb);
 	__u32 seq = ntohl(th->seq) - 1;
 	__u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4f49e5dd41bbb..cb7658aceb6c0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -76,8 +76,8 @@ static void	tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 
 static int	tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
 static void	__tcp_v6_send_check(struct sk_buff *skb,
-				    struct in6_addr *saddr,
-				    struct in6_addr *daddr);
+				    const struct in6_addr *saddr,
+				    const struct in6_addr *daddr);
 
 static const struct inet_connection_sock_af_ops ipv6_mapped;
 static const struct inet_connection_sock_af_ops ipv6_specific;
@@ -86,7 +86,7 @@ static const struct tcp_sock_af_ops tcp_sock_ipv6_specific;
 static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific;
 #else
 static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
-						   struct in6_addr *addr)
+						   const struct in6_addr *addr)
 {
 	return NULL;
 }
@@ -106,8 +106,8 @@ static void tcp_v6_hash(struct sock *sk)
 }
 
 static __inline__ __sum16 tcp_v6_check(int len,
-				   struct in6_addr *saddr,
-				   struct in6_addr *daddr,
+				   const struct in6_addr *saddr,
+				   const struct in6_addr *daddr,
 				   __wsum base)
 {
 	return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base);
@@ -331,7 +331,7 @@ failure:
 static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		u8 type, u8 code, int offset, __be32 info)
 {
-	struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
+	const struct ipv6hdr *hdr = (const struct ipv6hdr*)skb->data;
 	const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
 	struct ipv6_pinfo *np;
 	struct sock *sk;
@@ -551,7 +551,7 @@ static void tcp_v6_reqsk_destructor(struct request_sock *req)
 
 #ifdef CONFIG_TCP_MD5SIG
 static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
-						   struct in6_addr *addr)
+						   const struct in6_addr *addr)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int i;
@@ -580,7 +580,7 @@ static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk,
 	return tcp_v6_md5_do_lookup(sk, &inet6_rsk(req)->rmt_addr);
 }
 
-static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer,
+static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer,
 			     char *newkey, u8 newkeylen)
 {
 	/* Add key to the list */
@@ -645,7 +645,7 @@ static int tcp_v6_md5_add_func(struct sock *sk, struct sock *addr_sk,
 				 newkey, newkeylen);
 }
 
-static int tcp_v6_md5_do_del(struct sock *sk, struct in6_addr *peer)
+static int tcp_v6_md5_do_del(struct sock *sk, const struct in6_addr *peer)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int i;
@@ -753,8 +753,8 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
 }
 
 static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
-					struct in6_addr *daddr,
-					struct in6_addr *saddr, int nbytes)
+					const struct in6_addr *daddr,
+					const struct in6_addr *saddr, int nbytes)
 {
 	struct tcp6_pseudohdr *bp;
 	struct scatterlist sg;
@@ -771,7 +771,7 @@ static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
 }
 
 static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
-			       struct in6_addr *daddr, struct in6_addr *saddr,
+			       const struct in6_addr *daddr, struct in6_addr *saddr,
 			       struct tcphdr *th)
 {
 	struct tcp_md5sig_pool *hp;
@@ -807,7 +807,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
 			       struct sock *sk, struct request_sock *req,
 			       struct sk_buff *skb)
 {
-	struct in6_addr *saddr, *daddr;
+	const struct in6_addr *saddr, *daddr;
 	struct tcp_md5sig_pool *hp;
 	struct hash_desc *desc;
 	struct tcphdr *th = tcp_hdr(skb);
@@ -819,7 +819,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
 		saddr = &inet6_rsk(req)->loc_addr;
 		daddr = &inet6_rsk(req)->rmt_addr;
 	} else {
-		struct ipv6hdr *ip6h = ipv6_hdr(skb);
+		const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 		saddr = &ip6h->saddr;
 		daddr = &ip6h->daddr;
 	}
@@ -857,7 +857,7 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb)
 {
 	__u8 *hash_location = NULL;
 	struct tcp_md5sig_key *hash_expected;
-	struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	struct tcphdr *th = tcp_hdr(skb);
 	int genhash;
 	u8 newhash[16];
@@ -915,7 +915,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 #endif
 
 static void __tcp_v6_send_check(struct sk_buff *skb,
-				struct in6_addr *saddr, struct in6_addr *daddr)
+				const struct in6_addr *saddr, const struct in6_addr *daddr)
 {
 	struct tcphdr *th = tcp_hdr(skb);
 
@@ -939,7 +939,7 @@ static void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
 
 static int tcp_v6_gso_send_check(struct sk_buff *skb)
 {
-	struct ipv6hdr *ipv6h;
+	const struct ipv6hdr *ipv6h;
 	struct tcphdr *th;
 
 	if (!pskb_may_pull(skb, sizeof(*th)))
@@ -957,7 +957,7 @@ 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)
 {
-	struct ipv6hdr *iph = skb_gro_network_header(skb);
+	const struct ipv6hdr *iph = skb_gro_network_header(skb);
 
 	switch (skb->ip_summed) {
 	case CHECKSUM_COMPLETE:
@@ -978,7 +978,7 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
 
 static int tcp6_gro_complete(struct sk_buff *skb)
 {
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct tcphdr *th = tcp_hdr(skb);
 
 	th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb),
@@ -1702,7 +1702,7 @@ ipv6_pktoptions:
 static int tcp_v6_rcv(struct sk_buff *skb)
 {
 	struct tcphdr *th;
-	struct ipv6hdr *hdr;
+	const struct ipv6hdr *hdr;
 	struct sock *sk;
 	int ret;
 	struct net *net = dev_net(skb->dev);
@@ -2028,8 +2028,8 @@ static void get_openreq6(struct seq_file *seq,
 			 struct sock *sk, struct request_sock *req, int i, int uid)
 {
 	int ttd = req->expires - jiffies;
-	struct in6_addr *src = &inet6_rsk(req)->loc_addr;
-	struct in6_addr *dest = &inet6_rsk(req)->rmt_addr;
+	const struct in6_addr *src = &inet6_rsk(req)->loc_addr;
+	const struct in6_addr *dest = &inet6_rsk(req)->rmt_addr;
 
 	if (ttd < 0)
 		ttd = 0;
@@ -2057,7 +2057,7 @@ static void get_openreq6(struct seq_file *seq,
 
 static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 {
-	struct in6_addr *dest, *src;
+	const struct in6_addr *dest, *src;
 	__u16 destp, srcp;
 	int timer_active;
 	unsigned long timer_expires;
@@ -2114,7 +2114,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 static void get_timewait6_sock(struct seq_file *seq,
 			       struct inet_timewait_sock *tw, int i)
 {
-	struct in6_addr *dest, *src;
+	const struct in6_addr *dest, *src;
 	__u16 destp, srcp;
 	struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw);
 	int ttd = tw->tw_ttd - jiffies;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 15c37746845ed..1bdc5f053db84 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -311,7 +311,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 					  struct udp_table *udptable)
 {
 	struct sock *sk;
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
 
 	if (unlikely(sk = skb_steal_sock(skb)))
 		return sk;
@@ -463,9 +463,9 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		    struct udp_table *udptable)
 {
 	struct ipv6_pinfo *np;
-	struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
-	struct in6_addr *saddr = &hdr->saddr;
-	struct in6_addr *daddr = &hdr->daddr;
+	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 sock *sk;
 	int err;
@@ -553,8 +553,8 @@ drop_no_sk_drops_inc:
 }
 
 static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
-				      __be16 loc_port, struct in6_addr *loc_addr,
-				      __be16 rmt_port, struct in6_addr *rmt_addr,
+				      __be16 loc_port, const struct in6_addr *loc_addr,
+				      __be16 rmt_port, const struct in6_addr *rmt_addr,
 				      int dif)
 {
 	struct hlist_nulls_node *node;
@@ -633,7 +633,7 @@ drop:
  * so we don't need to lock the hashes.
  */
 static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
-		struct in6_addr *saddr, struct in6_addr *daddr,
+		const struct in6_addr *saddr, const struct in6_addr *daddr,
 		struct udp_table *udptable)
 {
 	struct sock *sk, *stack[256 / sizeof(struct sock *)];
@@ -716,7 +716,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	struct net *net = dev_net(skb->dev);
 	struct sock *sk;
 	struct udphdr *uh;
-	struct in6_addr *saddr, *daddr;
+	const struct in6_addr *saddr, *daddr;
 	u32 ulen = 0;
 
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
@@ -1278,7 +1278,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
 
 static int udp6_ufo_send_check(struct sk_buff *skb)
 {
-	struct ipv6hdr *ipv6h;
+	const struct ipv6hdr *ipv6h;
 	struct udphdr *uh;
 
 	if (!pskb_may_pull(skb, sizeof(*uh)))
@@ -1382,7 +1382,7 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket
 {
 	struct inet_sock *inet = inet_sk(sp);
 	struct ipv6_pinfo *np = inet6_sk(sp);
-	struct in6_addr *dest, *src;
+	const struct in6_addr *dest, *src;
 	__u16 destp, srcp;
 
 	dest  = &np->daddr;
diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c
index bbd48b101baee..3437d7d4eed6d 100644
--- a/net/ipv6/xfrm6_mode_beet.c
+++ b/net/ipv6/xfrm6_mode_beet.c
@@ -41,10 +41,8 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct ipv6hdr *top_iph;
 	struct ip_beet_phdr *ph;
-	struct iphdr *iphv4;
 	int optlen, hdr_len;
 
-	iphv4 = ip_hdr(skb);
 	hdr_len = 0;
 	optlen = XFRM_MODE_SKB_CB(skb)->optlen;
 	if (unlikely(optlen))
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 645cb968d4504..4d6edff0498f6 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -20,7 +20,7 @@
 
 static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
 {
-	struct ipv6hdr *outer_iph = ipv6_hdr(skb);
+	const struct ipv6hdr *outer_iph = ipv6_hdr(skb);
 	struct ipv6hdr *inner_iph = ipipv6_hdr(skb);
 
 	if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
@@ -55,8 +55,8 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 		dsfield &= ~INET_ECN_MASK;
 	ipv6_change_dsfield(top_iph, 0, dsfield);
 	top_iph->hop_limit = ip6_dst_hoplimit(dst->child);
-	ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
-	ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
+	ipv6_addr_copy(&top_iph->saddr, (const struct in6_addr *)&x->props.saddr);
+	ipv6_addr_copy(&top_iph->daddr, (const struct in6_addr *)&x->id.daddr);
 	return 0;
 }
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 05e34c8ec913b..d879f7efbd10b 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -124,7 +124,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 	struct flowi6 *fl6 = &fl->u.ip6;
 	int onlyproto = 0;
 	u16 offset = skb_network_header_len(skb);
-	struct ipv6hdr *hdr = ipv6_hdr(skb);
+	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct ipv6_opt_hdr *exthdr;
 	const unsigned char *nh = skb_network_header(skb);
 	u8 nexthdr = nh[IP6CB(skb)->nhoff];
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 2969cad408dee..a6770a04e3bd3 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -68,7 +68,7 @@ static DEFINE_SPINLOCK(xfrm6_tunnel_spi_lock);
 
 static struct kmem_cache *xfrm6_tunnel_spi_kmem __read_mostly;
 
-static inline unsigned xfrm6_tunnel_spi_hash_byaddr(xfrm_address_t *addr)
+static inline unsigned xfrm6_tunnel_spi_hash_byaddr(const xfrm_address_t *addr)
 {
 	unsigned h;
 
@@ -85,7 +85,7 @@ static inline unsigned xfrm6_tunnel_spi_hash_byspi(u32 spi)
 	return spi % XFRM6_TUNNEL_SPI_BYSPI_HSIZE;
 }
 
-static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr)
+static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr)
 {
 	struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
 	struct xfrm6_tunnel_spi *x6spi;
@@ -101,7 +101,7 @@ static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, xfrm_
 	return NULL;
 }
 
-__be32 xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr)
+__be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr)
 {
 	struct xfrm6_tunnel_spi *x6spi;
 	u32 spi;
@@ -237,10 +237,10 @@ static int xfrm6_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 static int xfrm6_tunnel_rcv(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	__be32 spi;
 
-	spi = xfrm6_tunnel_spi_lookup(net, (xfrm_address_t *)&iph->saddr);
+	spi = xfrm6_tunnel_spi_lookup(net, (const xfrm_address_t *)&iph->saddr);
 	return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi) > 0 ? : 0;
 }
 
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 7db86ffcf0705..d62401c256843 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -712,7 +712,7 @@ static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port
 		sin6->sin6_family = AF_INET6;
 		sin6->sin6_port = port;
 		sin6->sin6_flowinfo = 0;
-		ipv6_addr_copy(&sin6->sin6_addr, (struct in6_addr *)xaddr->a6);
+		ipv6_addr_copy(&sin6->sin6_addr, (const struct in6_addr *)xaddr->a6);
 		sin6->sin6_scope_id = 0;
 		return 128;
 	    }
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index c2e628dfaaccb..7ef87f9eb675d 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -169,7 +169,7 @@ static unsigned int sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
 	}
 	case htons(ETH_P_IPV6):
 	{
-		struct ipv6hdr *iph;
+		const struct ipv6hdr *iph;
 		int poff;
 
 		if (!pskb_network_may_pull(skb, sizeof(*iph)))
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 3a8eb79eb78b9..741ed1648838c 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -565,7 +565,7 @@ void sctp_err_finish(struct sock *sk, struct sctp_association *asoc)
  */
 void sctp_v4_err(struct sk_buff *skb, __u32 info)
 {
-	struct iphdr *iph = (struct iphdr *)skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	const int ihlen = iph->ihl * 4;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 865ce7ba4e14e..321f175055bf3 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -531,7 +531,7 @@ static int sctp_v6_is_any(const union sctp_addr *addr)
 static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp)
 {
 	int type;
-	struct in6_addr *in6 = (struct in6_addr *)&addr->v6.sin6_addr;
+	const struct in6_addr *in6 = (const struct in6_addr *)&addr->v6.sin6_addr;
 
 	type = ipv6_addr_type(in6);
 	if (IPV6_ADDR_ANY == type)
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index dd78536d40dee..d70f85eb7864f 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1036,15 +1036,15 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m,
 
 		case AF_INET6:
 			ipv6_addr_copy((struct in6_addr *)x->sel.daddr.a6,
-				       (struct in6_addr *)daddr);
+				       (const struct in6_addr *)daddr);
 			ipv6_addr_copy((struct in6_addr *)x->sel.saddr.a6,
-				       (struct in6_addr *)saddr);
+				       (const struct in6_addr *)saddr);
 			x->sel.prefixlen_d = 128;
 			x->sel.prefixlen_s = 128;
 			ipv6_addr_copy((struct in6_addr *)x->props.saddr.a6,
-				       (struct in6_addr *)saddr);
+				       (const struct in6_addr *)saddr);
 			ipv6_addr_copy((struct in6_addr *)x->id.daddr.a6,
-				       (struct in6_addr *)daddr);
+				       (const struct in6_addr *)daddr);
 			break;
 		}
 
@@ -2092,8 +2092,8 @@ static void xfrm_audit_helper_sainfo(struct xfrm_state *x,
 static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family,
 				      struct audit_buffer *audit_buf)
 {
-	struct iphdr *iph4;
-	struct ipv6hdr *iph6;
+	const struct iphdr *iph4;
+	const struct ipv6hdr *iph6;
 
 	switch (family) {
 	case AF_INET:
-- 
cgit v1.2.3


From f6d8bd051c391c1c0458a30b2a7abcd939329259 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 21 Apr 2011 09:45:37 +0000
Subject: inet: add RCU protection to inet->opt

We lack proper synchronization to manipulate inet->opt ip_options

Problem is ip_make_skb() calls ip_setup_cork() and
ip_setup_cork() possibly makes a copy of ipc->opt (struct ip_options),
without any protection against another thread manipulating inet->opt.

Another thread can change inet->opt pointer and free old one under us.

Use RCU to protect inet->opt (changed to inet->inet_opt).

Instead of handling atomic refcounts, just copy ip_options when
necessary, to avoid cache line dirtying.

We cant insert an rcu_head in struct ip_options since its included in
skb->cb[], so this patch is large because I had to introduce a new
ip_options_rcu structure.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h         |  14 +++--
 include/net/ip.h                |  11 ++--
 net/dccp/ipv4.c                 |  16 +++---
 net/dccp/ipv6.c                 |   2 +-
 net/ipv4/af_inet.c              |  17 ++++--
 net/ipv4/cipso_ipv4.c           | 113 ++++++++++++++++++++++------------------
 net/ipv4/icmp.c                 |  23 ++++----
 net/ipv4/inet_connection_sock.c |   6 +--
 net/ipv4/ip_options.c           |  38 +++++++-------
 net/ipv4/ip_output.c            |  44 ++++++++--------
 net/ipv4/ip_sockglue.c          |  35 +++++++++----
 net/ipv4/raw.c                  |  19 +++++--
 net/ipv4/syncookies.c           |   4 +-
 net/ipv4/tcp_ipv4.c             |  34 +++++++-----
 net/ipv4/udp.c                  |  21 ++++++--
 net/ipv6/tcp_ipv6.c             |   2 +-
 net/l2tp/l2tp_ip.c              |  10 ++--
 17 files changed, 241 insertions(+), 168 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 7a37369f8ea3f..ed2ba6eca7247 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -57,7 +57,15 @@ struct ip_options {
 	unsigned char	__data[0];
 };
 
-#define optlength(opt) (sizeof(struct ip_options) + opt->optlen)
+struct ip_options_rcu {
+	struct rcu_head rcu;
+	struct ip_options opt;
+};
+
+struct ip_options_data {
+	struct ip_options_rcu	opt;
+	char			data[40];
+};
 
 struct inet_request_sock {
 	struct request_sock	req;
@@ -78,7 +86,7 @@ struct inet_request_sock {
 				acked	   : 1,
 				no_srccheck: 1;
 	kmemcheck_bitfield_end(flags);
-	struct ip_options	*opt;
+	struct ip_options_rcu	*opt;
 };
 
 static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
@@ -140,7 +148,7 @@ struct inet_sock {
 	__be16			inet_sport;
 	__u16			inet_id;
 
-	struct ip_options	*opt;
+	struct ip_options_rcu __rcu	*inet_opt;
 	__u8			tos;
 	__u8			min_ttl;
 	__u8			mc_ttl;
diff --git a/include/net/ip.h b/include/net/ip.h
index 7c416583b7104..3a59bf99aa3a1 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -52,7 +52,7 @@ static inline unsigned int ip_hdrlen(const struct sk_buff *skb)
 struct ipcm_cookie {
 	__be32			addr;
 	int			oif;
-	struct ip_options	*opt;
+	struct ip_options_rcu	*opt;
 	__u8			tx_flags;
 };
 
@@ -92,7 +92,7 @@ extern int		igmp_mc_proc_init(void);
 
 extern int		ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 					      __be32 saddr, __be32 daddr,
-					      struct ip_options *opt);
+					      struct ip_options_rcu *opt);
 extern int		ip_rcv(struct sk_buff *skb, struct net_device *dev,
 			       struct packet_type *pt, struct net_device *orig_dev);
 extern int		ip_local_deliver(struct sk_buff *skb);
@@ -416,14 +416,15 @@ extern int ip_forward(struct sk_buff *skb);
  *	Functions provided by ip_options.c
  */
  
-extern void ip_options_build(struct sk_buff *skb, struct ip_options *opt, __be32 daddr, struct rtable *rt, int is_frag);
+extern void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
+			     __be32 daddr, struct rtable *rt, int is_frag);
 extern int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb);
 extern void ip_options_fragment(struct sk_buff *skb);
 extern int ip_options_compile(struct net *net,
 			      struct ip_options *opt, struct sk_buff *skb);
-extern int ip_options_get(struct net *net, struct ip_options **optp,
+extern int ip_options_get(struct net *net, struct ip_options_rcu **optp,
 			  unsigned char *data, int optlen);
-extern int ip_options_get_from_user(struct net *net, struct ip_options **optp,
+extern int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
 				    unsigned char __user *data, int optlen);
 extern void ip_options_undo(struct ip_options * opt);
 extern void ip_forward_options(struct sk_buff *skb);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index b92ab655d44ef..cbbcc6c036e02 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -48,6 +48,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct flowi4 fl4;
 	struct rtable *rt;
 	int err;
+	struct ip_options_rcu *inet_opt;
 
 	dp->dccps_role = DCCP_ROLE_CLIENT;
 
@@ -58,10 +59,13 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		return -EAFNOSUPPORT;
 
 	nexthop = daddr = usin->sin_addr.s_addr;
-	if (inet->opt != NULL && inet->opt->srr) {
+
+	inet_opt = rcu_dereference_protected(inet->inet_opt,
+					     sock_owned_by_user(sk));
+	if (inet_opt != NULL && inet_opt->opt.srr) {
 		if (daddr == 0)
 			return -EINVAL;
-		nexthop = inet->opt->faddr;
+		nexthop = inet_opt->opt.faddr;
 	}
 
 	orig_sport = inet->inet_sport;
@@ -78,7 +82,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		return -ENETUNREACH;
 	}
 
-	if (inet->opt == NULL || !inet->opt->srr)
+	if (inet_opt == NULL || !inet_opt->opt.srr)
 		daddr = rt->rt_dst;
 
 	if (inet->inet_saddr == 0)
@@ -89,8 +93,8 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	inet->inet_daddr = daddr;
 
 	inet_csk(sk)->icsk_ext_hdr_len = 0;
-	if (inet->opt != NULL)
-		inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
+	if (inet_opt)
+		inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
 	/*
 	 * Socket identity is still unknown (sport may be zero).
 	 * However we set state to DCCP_REQUESTING and not releasing socket
@@ -405,7 +409,7 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newinet->inet_daddr	= ireq->rmt_addr;
 	newinet->inet_rcv_saddr = ireq->loc_addr;
 	newinet->inet_saddr	= ireq->loc_addr;
-	newinet->opt	   = ireq->opt;
+	newinet->inet_opt	= ireq->opt;
 	ireq->opt	   = NULL;
 	newinet->mc_index  = inet_iif(skb);
 	newinet->mc_ttl	   = ip_hdr(skb)->ttl;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 73add23732479..8dc4348774a58 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -573,7 +573,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 	   First: no IPv4 options.
 	 */
-	newinet->opt = NULL;
+	newinet->inet_opt = NULL;
 
 	/* Clone RX bits */
 	newnp->rxopt.all = np->rxopt.all;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 0413af3e22859..963a621e75c7a 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -153,7 +153,7 @@ void inet_sock_destruct(struct sock *sk)
 	WARN_ON(sk->sk_wmem_queued);
 	WARN_ON(sk->sk_forward_alloc);
 
-	kfree(inet->opt);
+	kfree(rcu_dereference_protected(inet->inet_opt, 1));
 	dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
 	sk_refcnt_debug_dec(sk);
 }
@@ -1106,9 +1106,12 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 	struct flowi4 fl4;
 	struct rtable *rt;
 	__be32 new_saddr;
+	struct ip_options_rcu *inet_opt;
 
-	if (inet->opt && inet->opt->srr)
-		daddr = inet->opt->faddr;
+	inet_opt = rcu_dereference_protected(inet->inet_opt,
+					     sock_owned_by_user(sk));
+	if (inet_opt && inet_opt->opt.srr)
+		daddr = inet_opt->opt.faddr;
 
 	/* Query new route. */
 	rt = ip_route_connect(&fl4, daddr, 0, RT_CONN_FLAGS(sk),
@@ -1148,6 +1151,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 	struct inet_sock *inet = inet_sk(sk);
 	struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0);
 	__be32 daddr;
+	struct ip_options_rcu *inet_opt;
 	int err;
 
 	/* Route is OK, nothing to do. */
@@ -1155,9 +1159,12 @@ int inet_sk_rebuild_header(struct sock *sk)
 		return 0;
 
 	/* Reroute. */
+	rcu_read_lock();
+	inet_opt = rcu_dereference(inet->inet_opt);
 	daddr = inet->inet_daddr;
-	if (inet->opt && inet->opt->srr)
-		daddr = inet->opt->faddr;
+	if (inet_opt && inet_opt->opt.srr)
+		daddr = inet_opt->opt.faddr;
+	rcu_read_unlock();
 	rt = ip_route_output_ports(sock_net(sk), sk, daddr, inet->inet_saddr,
 				   inet->inet_dport, inet->inet_sport,
 				   sk->sk_protocol, RT_CONN_FLAGS(sk),
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index a0af7ea87870a..2b3c23c287cdf 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1857,6 +1857,11 @@ static int cipso_v4_genopt(unsigned char *buf, u32 buf_len,
 	return CIPSO_V4_HDR_LEN + ret_val;
 }
 
+static void opt_kfree_rcu(struct rcu_head *head)
+{
+	kfree(container_of(head, struct ip_options_rcu, rcu));
+}
+
 /**
  * cipso_v4_sock_setattr - Add a CIPSO option to a socket
  * @sk: the socket
@@ -1879,7 +1884,7 @@ int cipso_v4_sock_setattr(struct sock *sk,
 	unsigned char *buf = NULL;
 	u32 buf_len;
 	u32 opt_len;
-	struct ip_options *opt = NULL;
+	struct ip_options_rcu *old, *opt = NULL;
 	struct inet_sock *sk_inet;
 	struct inet_connection_sock *sk_conn;
 
@@ -1915,22 +1920,25 @@ int cipso_v4_sock_setattr(struct sock *sk,
 		ret_val = -ENOMEM;
 		goto socket_setattr_failure;
 	}
-	memcpy(opt->__data, buf, buf_len);
-	opt->optlen = opt_len;
-	opt->cipso = sizeof(struct iphdr);
+	memcpy(opt->opt.__data, buf, buf_len);
+	opt->opt.optlen = opt_len;
+	opt->opt.cipso = sizeof(struct iphdr);
 	kfree(buf);
 	buf = NULL;
 
 	sk_inet = inet_sk(sk);
+
+	old = rcu_dereference_protected(sk_inet->inet_opt, sock_owned_by_user(sk));
 	if (sk_inet->is_icsk) {
 		sk_conn = inet_csk(sk);
-		if (sk_inet->opt)
-			sk_conn->icsk_ext_hdr_len -= sk_inet->opt->optlen;
-		sk_conn->icsk_ext_hdr_len += opt->optlen;
+		if (old)
+			sk_conn->icsk_ext_hdr_len -= old->opt.optlen;
+		sk_conn->icsk_ext_hdr_len += opt->opt.optlen;
 		sk_conn->icsk_sync_mss(sk, sk_conn->icsk_pmtu_cookie);
 	}
-	opt = xchg(&sk_inet->opt, opt);
-	kfree(opt);
+	rcu_assign_pointer(sk_inet->inet_opt, opt);
+	if (old)
+		call_rcu(&old->rcu, opt_kfree_rcu);
 
 	return 0;
 
@@ -1960,7 +1968,7 @@ int cipso_v4_req_setattr(struct request_sock *req,
 	unsigned char *buf = NULL;
 	u32 buf_len;
 	u32 opt_len;
-	struct ip_options *opt = NULL;
+	struct ip_options_rcu *opt = NULL;
 	struct inet_request_sock *req_inet;
 
 	/* We allocate the maximum CIPSO option size here so we are probably
@@ -1988,15 +1996,16 @@ int cipso_v4_req_setattr(struct request_sock *req,
 		ret_val = -ENOMEM;
 		goto req_setattr_failure;
 	}
-	memcpy(opt->__data, buf, buf_len);
-	opt->optlen = opt_len;
-	opt->cipso = sizeof(struct iphdr);
+	memcpy(opt->opt.__data, buf, buf_len);
+	opt->opt.optlen = opt_len;
+	opt->opt.cipso = sizeof(struct iphdr);
 	kfree(buf);
 	buf = NULL;
 
 	req_inet = inet_rsk(req);
 	opt = xchg(&req_inet->opt, opt);
-	kfree(opt);
+	if (opt)
+		call_rcu(&opt->rcu, opt_kfree_rcu);
 
 	return 0;
 
@@ -2016,34 +2025,34 @@ req_setattr_failure:
  * values on failure.
  *
  */
-static int cipso_v4_delopt(struct ip_options **opt_ptr)
+static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr)
 {
 	int hdr_delta = 0;
-	struct ip_options *opt = *opt_ptr;
+	struct ip_options_rcu *opt = *opt_ptr;
 
-	if (opt->srr || opt->rr || opt->ts || opt->router_alert) {
+	if (opt->opt.srr || opt->opt.rr || opt->opt.ts || opt->opt.router_alert) {
 		u8 cipso_len;
 		u8 cipso_off;
 		unsigned char *cipso_ptr;
 		int iter;
 		int optlen_new;
 
-		cipso_off = opt->cipso - sizeof(struct iphdr);
-		cipso_ptr = &opt->__data[cipso_off];
+		cipso_off = opt->opt.cipso - sizeof(struct iphdr);
+		cipso_ptr = &opt->opt.__data[cipso_off];
 		cipso_len = cipso_ptr[1];
 
-		if (opt->srr > opt->cipso)
-			opt->srr -= cipso_len;
-		if (opt->rr > opt->cipso)
-			opt->rr -= cipso_len;
-		if (opt->ts > opt->cipso)
-			opt->ts -= cipso_len;
-		if (opt->router_alert > opt->cipso)
-			opt->router_alert -= cipso_len;
-		opt->cipso = 0;
+		if (opt->opt.srr > opt->opt.cipso)
+			opt->opt.srr -= cipso_len;
+		if (opt->opt.rr > opt->opt.cipso)
+			opt->opt.rr -= cipso_len;
+		if (opt->opt.ts > opt->opt.cipso)
+			opt->opt.ts -= cipso_len;
+		if (opt->opt.router_alert > opt->opt.cipso)
+			opt->opt.router_alert -= cipso_len;
+		opt->opt.cipso = 0;
 
 		memmove(cipso_ptr, cipso_ptr + cipso_len,
-			opt->optlen - cipso_off - cipso_len);
+			opt->opt.optlen - cipso_off - cipso_len);
 
 		/* determining the new total option length is tricky because of
 		 * the padding necessary, the only thing i can think to do at
@@ -2052,21 +2061,21 @@ static int cipso_v4_delopt(struct ip_options **opt_ptr)
 		 * from there we can determine the new total option length */
 		iter = 0;
 		optlen_new = 0;
-		while (iter < opt->optlen)
-			if (opt->__data[iter] != IPOPT_NOP) {
-				iter += opt->__data[iter + 1];
+		while (iter < opt->opt.optlen)
+			if (opt->opt.__data[iter] != IPOPT_NOP) {
+				iter += opt->opt.__data[iter + 1];
 				optlen_new = iter;
 			} else
 				iter++;
-		hdr_delta = opt->optlen;
-		opt->optlen = (optlen_new + 3) & ~3;
-		hdr_delta -= opt->optlen;
+		hdr_delta = opt->opt.optlen;
+		opt->opt.optlen = (optlen_new + 3) & ~3;
+		hdr_delta -= opt->opt.optlen;
 	} else {
 		/* only the cipso option was present on the socket so we can
 		 * remove the entire option struct */
 		*opt_ptr = NULL;
-		hdr_delta = opt->optlen;
-		kfree(opt);
+		hdr_delta = opt->opt.optlen;
+		call_rcu(&opt->rcu, opt_kfree_rcu);
 	}
 
 	return hdr_delta;
@@ -2083,15 +2092,15 @@ static int cipso_v4_delopt(struct ip_options **opt_ptr)
 void cipso_v4_sock_delattr(struct sock *sk)
 {
 	int hdr_delta;
-	struct ip_options *opt;
+	struct ip_options_rcu *opt;
 	struct inet_sock *sk_inet;
 
 	sk_inet = inet_sk(sk);
-	opt = sk_inet->opt;
-	if (opt == NULL || opt->cipso == 0)
+	opt = rcu_dereference_protected(sk_inet->inet_opt, 1);
+	if (opt == NULL || opt->opt.cipso == 0)
 		return;
 
-	hdr_delta = cipso_v4_delopt(&sk_inet->opt);
+	hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt);
 	if (sk_inet->is_icsk && hdr_delta > 0) {
 		struct inet_connection_sock *sk_conn = inet_csk(sk);
 		sk_conn->icsk_ext_hdr_len -= hdr_delta;
@@ -2109,12 +2118,12 @@ void cipso_v4_sock_delattr(struct sock *sk)
  */
 void cipso_v4_req_delattr(struct request_sock *req)
 {
-	struct ip_options *opt;
+	struct ip_options_rcu *opt;
 	struct inet_request_sock *req_inet;
 
 	req_inet = inet_rsk(req);
 	opt = req_inet->opt;
-	if (opt == NULL || opt->cipso == 0)
+	if (opt == NULL || opt->opt.cipso == 0)
 		return;
 
 	cipso_v4_delopt(&req_inet->opt);
@@ -2184,14 +2193,18 @@ getattr_return:
  */
 int cipso_v4_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr)
 {
-	struct ip_options *opt;
+	struct ip_options_rcu *opt;
+	int res = -ENOMSG;
 
-	opt = inet_sk(sk)->opt;
-	if (opt == NULL || opt->cipso == 0)
-		return -ENOMSG;
-
-	return cipso_v4_getattr(opt->__data + opt->cipso - sizeof(struct iphdr),
-				secattr);
+	rcu_read_lock();
+	opt = rcu_dereference(inet_sk(sk)->inet_opt);
+	if (opt && opt->opt.cipso)
+		res = cipso_v4_getattr(opt->opt.__data +
+						opt->opt.cipso -
+						sizeof(struct iphdr),
+				       secattr);
+	rcu_read_unlock();
+	return res;
 }
 
 /**
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 74e35e5736e2d..cfeca3c2152d0 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -108,8 +108,7 @@ struct icmp_bxm {
 		__be32	       times[3];
 	} data;
 	int head_len;
-	struct ip_options replyopts;
-	unsigned char  optbuf[40];
+	struct ip_options_data replyopts;
 };
 
 /* An array of errno for error messages from dest unreach. */
@@ -333,7 +332,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	struct inet_sock *inet;
 	__be32 daddr;
 
-	if (ip_options_echo(&icmp_param->replyopts, skb))
+	if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb))
 		return;
 
 	sk = icmp_xmit_lock(net);
@@ -347,10 +346,10 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	daddr = ipc.addr = rt->rt_src;
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
-	if (icmp_param->replyopts.optlen) {
-		ipc.opt = &icmp_param->replyopts;
-		if (ipc.opt->srr)
-			daddr = icmp_param->replyopts.faddr;
+	if (icmp_param->replyopts.opt.opt.optlen) {
+		ipc.opt = &icmp_param->replyopts.opt;
+		if (ipc.opt->opt.srr)
+			daddr = icmp_param->replyopts.opt.opt.faddr;
 	}
 	{
 		struct flowi4 fl4 = {
@@ -379,8 +378,8 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,
 					struct icmp_bxm *param)
 {
 	struct flowi4 fl4 = {
-		.daddr = (param->replyopts.srr ?
-			  param->replyopts.faddr : iph->saddr),
+		.daddr = (param->replyopts.opt.opt.srr ?
+			  param->replyopts.opt.opt.faddr : iph->saddr),
 		.saddr = saddr,
 		.flowi4_tos = RT_TOS(tos),
 		.flowi4_proto = IPPROTO_ICMP,
@@ -581,7 +580,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 					   IPTOS_PREC_INTERNETCONTROL) :
 					  iph->tos;
 
-	if (ip_options_echo(&icmp_param.replyopts, skb_in))
+	if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in))
 		goto out_unlock;
 
 
@@ -597,7 +596,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	icmp_param.offset = skb_network_offset(skb_in);
 	inet_sk(sk)->tos = tos;
 	ipc.addr = iph->saddr;
-	ipc.opt = &icmp_param.replyopts;
+	ipc.opt = &icmp_param.replyopts.opt;
 	ipc.tx_flags = 0;
 
 	rt = icmp_route_lookup(net, skb_in, iph, saddr, tos,
@@ -613,7 +612,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	room = dst_mtu(&rt->dst);
 	if (room > 576)
 		room = 576;
-	room -= sizeof(struct iphdr) + icmp_param.replyopts.optlen;
+	room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
 	room -= sizeof(struct icmphdr);
 
 	icmp_param.data_len = skb_in->len - icmp_param.offset;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8514db54a7f4a..3282cb2de3935 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -354,20 +354,20 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 {
 	struct rtable *rt;
 	const struct inet_request_sock *ireq = inet_rsk(req);
-	struct ip_options *opt = inet_rsk(req)->opt;
+	struct ip_options_rcu *opt = inet_rsk(req)->opt;
 	struct net *net = sock_net(sk);
 	struct flowi4 fl4;
 
 	flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
-			   (opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
+			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
 			   ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
 	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
+	if (opt && opt->opt.is_strictroute && rt->rt_dst != rt->rt_gateway)
 		goto route_err;
 	return &rt->dst;
 
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 2391b24e8251e..01fc409658489 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -36,7 +36,7 @@
  * saddr is address of outgoing interface.
  */
 
-void ip_options_build(struct sk_buff * skb, struct ip_options * opt,
+void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
 			    __be32 daddr, struct rtable *rt, int is_frag)
 {
 	unsigned char *iph = skb_network_header(skb);
@@ -83,9 +83,9 @@ void ip_options_build(struct sk_buff * skb, struct ip_options * opt,
  * NOTE: dopt cannot point to skb.
  */
 
-int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb)
+int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb)
 {
-	struct ip_options *sopt;
+	const struct ip_options *sopt;
 	unsigned char *sptr, *dptr;
 	int soffset, doffset;
 	int	optlen;
@@ -95,10 +95,8 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb)
 
 	sopt = &(IPCB(skb)->opt);
 
-	if (sopt->optlen == 0) {
-		dopt->optlen = 0;
+	if (sopt->optlen == 0)
 		return 0;
-	}
 
 	sptr = skb_network_header(skb);
 	dptr = dopt->__data;
@@ -157,7 +155,7 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb)
 		dopt->optlen += optlen;
 	}
 	if (sopt->srr) {
-		unsigned char * start = sptr+sopt->srr;
+		unsigned char *start = sptr+sopt->srr;
 		__be32 faddr;
 
 		optlen  = start[1];
@@ -499,19 +497,19 @@ void ip_options_undo(struct ip_options * opt)
 	}
 }
 
-static struct ip_options *ip_options_get_alloc(const int optlen)
+static struct ip_options_rcu *ip_options_get_alloc(const int optlen)
 {
-	return kzalloc(sizeof(struct ip_options) + ((optlen + 3) & ~3),
+	return kzalloc(sizeof(struct ip_options_rcu) + ((optlen + 3) & ~3),
 		       GFP_KERNEL);
 }
 
-static int ip_options_get_finish(struct net *net, struct ip_options **optp,
-				 struct ip_options *opt, int optlen)
+static int ip_options_get_finish(struct net *net, struct ip_options_rcu **optp,
+				 struct ip_options_rcu *opt, int optlen)
 {
 	while (optlen & 3)
-		opt->__data[optlen++] = IPOPT_END;
-	opt->optlen = optlen;
-	if (optlen && ip_options_compile(net, opt, NULL)) {
+		opt->opt.__data[optlen++] = IPOPT_END;
+	opt->opt.optlen = optlen;
+	if (optlen && ip_options_compile(net, &opt->opt, NULL)) {
 		kfree(opt);
 		return -EINVAL;
 	}
@@ -520,29 +518,29 @@ static int ip_options_get_finish(struct net *net, struct ip_options **optp,
 	return 0;
 }
 
-int ip_options_get_from_user(struct net *net, struct ip_options **optp,
+int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
 			     unsigned char __user *data, int optlen)
 {
-	struct ip_options *opt = ip_options_get_alloc(optlen);
+	struct ip_options_rcu *opt = ip_options_get_alloc(optlen);
 
 	if (!opt)
 		return -ENOMEM;
-	if (optlen && copy_from_user(opt->__data, data, optlen)) {
+	if (optlen && copy_from_user(opt->opt.__data, data, optlen)) {
 		kfree(opt);
 		return -EFAULT;
 	}
 	return ip_options_get_finish(net, optp, opt, optlen);
 }
 
-int ip_options_get(struct net *net, struct ip_options **optp,
+int ip_options_get(struct net *net, struct ip_options_rcu **optp,
 		   unsigned char *data, int optlen)
 {
-	struct ip_options *opt = ip_options_get_alloc(optlen);
+	struct ip_options_rcu *opt = ip_options_get_alloc(optlen);
 
 	if (!opt)
 		return -ENOMEM;
 	if (optlen)
-		memcpy(opt->__data, data, optlen);
+		memcpy(opt->opt.__data, data, optlen);
 	return ip_options_get_finish(net, optp, opt, optlen);
 }
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index bdad3d60aa828..362e66f7d2fbb 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -140,14 +140,14 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
  *
  */
 int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
-			  __be32 saddr, __be32 daddr, struct ip_options *opt)
+			  __be32 saddr, __be32 daddr, struct ip_options_rcu *opt)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct rtable *rt = skb_rtable(skb);
 	struct iphdr *iph;
 
 	/* Build the IP header. */
-	skb_push(skb, sizeof(struct iphdr) + (opt ? opt->optlen : 0));
+	skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0));
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
 	iph->version  = 4;
@@ -163,9 +163,9 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 	iph->protocol = sk->sk_protocol;
 	ip_select_ident(iph, &rt->dst, sk);
 
-	if (opt && opt->optlen) {
-		iph->ihl += opt->optlen>>2;
-		ip_options_build(skb, opt, daddr, rt, 0);
+	if (opt && opt->opt.optlen) {
+		iph->ihl += opt->opt.optlen>>2;
+		ip_options_build(skb, &opt->opt, daddr, rt, 0);
 	}
 
 	skb->priority = sk->sk_priority;
@@ -316,7 +316,7 @@ int ip_queue_xmit(struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
-	struct ip_options *opt = inet->opt;
+	struct ip_options_rcu *inet_opt;
 	struct rtable *rt;
 	struct iphdr *iph;
 	int res;
@@ -325,6 +325,7 @@ int ip_queue_xmit(struct sk_buff *skb)
 	 * f.e. by something like SCTP.
 	 */
 	rcu_read_lock();
+	inet_opt = rcu_dereference(inet->inet_opt);
 	rt = skb_rtable(skb);
 	if (rt != NULL)
 		goto packet_routed;
@@ -336,8 +337,8 @@ int ip_queue_xmit(struct sk_buff *skb)
 
 		/* Use correct destination address if we have options. */
 		daddr = inet->inet_daddr;
-		if(opt && opt->srr)
-			daddr = opt->faddr;
+		if (inet_opt && inet_opt->opt.srr)
+			daddr = inet_opt->opt.faddr;
 
 		/* If this fails, retransmit mechanism of transport layer will
 		 * keep trying until route appears or the connection times
@@ -357,11 +358,11 @@ int ip_queue_xmit(struct sk_buff *skb)
 	skb_dst_set_noref(skb, &rt->dst);
 
 packet_routed:
-	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
+	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_dst != rt->rt_gateway)
 		goto no_route;
 
 	/* OK, we know where to send it, allocate and build IP header. */
-	skb_push(skb, sizeof(struct iphdr) + (opt ? opt->optlen : 0));
+	skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0));
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
 	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
@@ -375,9 +376,9 @@ packet_routed:
 	iph->daddr    = rt->rt_dst;
 	/* Transport layer set skb->h.foo itself. */
 
-	if (opt && opt->optlen) {
-		iph->ihl += opt->optlen >> 2;
-		ip_options_build(skb, opt, inet->inet_daddr, rt, 0);
+	if (inet_opt && inet_opt->opt.optlen) {
+		iph->ihl += inet_opt->opt.optlen >> 2;
+		ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
 	}
 
 	ip_select_ident_more(iph, &rt->dst, sk,
@@ -1033,7 +1034,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 			 struct ipcm_cookie *ipc, struct rtable **rtp)
 {
 	struct inet_sock *inet = inet_sk(sk);
-	struct ip_options *opt;
+	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
 	/*
@@ -1047,7 +1048,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 			if (unlikely(cork->opt == NULL))
 				return -ENOBUFS;
 		}
-		memcpy(cork->opt, opt, sizeof(struct ip_options) + opt->optlen);
+		memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen);
 		cork->flags |= IPCORK_OPT;
 		cork->addr = ipc->addr;
 	}
@@ -1451,26 +1452,23 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
 		   unsigned int len)
 {
 	struct inet_sock *inet = inet_sk(sk);
-	struct {
-		struct ip_options	opt;
-		char			data[40];
-	} replyopts;
+	struct ip_options_data replyopts;
 	struct ipcm_cookie ipc;
 	__be32 daddr;
 	struct rtable *rt = skb_rtable(skb);
 
-	if (ip_options_echo(&replyopts.opt, skb))
+	if (ip_options_echo(&replyopts.opt.opt, skb))
 		return;
 
 	daddr = ipc.addr = rt->rt_src;
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
 
-	if (replyopts.opt.optlen) {
+	if (replyopts.opt.opt.optlen) {
 		ipc.opt = &replyopts.opt;
 
-		if (ipc.opt->srr)
-			daddr = replyopts.opt.faddr;
+		if (replyopts.opt.opt.srr)
+			daddr = replyopts.opt.opt.faddr;
 	}
 
 	{
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 9640900309bbb..ab0c9efd1efab 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -451,6 +451,11 @@ out:
 }
 
 
+static void opt_kfree_rcu(struct rcu_head *head)
+{
+	kfree(container_of(head, struct ip_options_rcu, rcu));
+}
+
 /*
  *	Socket option code for IP. This is the end of the line after any
  *	TCP,UDP etc options on an IP socket.
@@ -497,13 +502,16 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 	switch (optname) {
 	case IP_OPTIONS:
 	{
-		struct ip_options *opt = NULL;
+		struct ip_options_rcu *old, *opt = NULL;
+
 		if (optlen > 40)
 			goto e_inval;
 		err = ip_options_get_from_user(sock_net(sk), &opt,
 					       optval, optlen);
 		if (err)
 			break;
+		old = rcu_dereference_protected(inet->inet_opt,
+						sock_owned_by_user(sk));
 		if (inet->is_icsk) {
 			struct inet_connection_sock *icsk = inet_csk(sk);
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
@@ -512,17 +520,18 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 			       (TCPF_LISTEN | TCPF_CLOSE)) &&
 			     inet->inet_daddr != LOOPBACK4_IPV6)) {
 #endif
-				if (inet->opt)
-					icsk->icsk_ext_hdr_len -= inet->opt->optlen;
+				if (old)
+					icsk->icsk_ext_hdr_len -= old->opt.optlen;
 				if (opt)
-					icsk->icsk_ext_hdr_len += opt->optlen;
+					icsk->icsk_ext_hdr_len += opt->opt.optlen;
 				icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 			}
 #endif
 		}
-		opt = xchg(&inet->opt, opt);
-		kfree(opt);
+		rcu_assign_pointer(inet->inet_opt, opt);
+		if (old)
+			call_rcu(&old->rcu, opt_kfree_rcu);
 		break;
 	}
 	case IP_PKTINFO:
@@ -1081,12 +1090,16 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_OPTIONS:
 	{
 		unsigned char optbuf[sizeof(struct ip_options)+40];
-		struct ip_options * opt = (struct ip_options *)optbuf;
+		struct ip_options *opt = (struct ip_options *)optbuf;
+		struct ip_options_rcu *inet_opt;
+
+		inet_opt = rcu_dereference_protected(inet->inet_opt,
+						     sock_owned_by_user(sk));
 		opt->optlen = 0;
-		if (inet->opt)
-			memcpy(optbuf, inet->opt,
-			       sizeof(struct ip_options)+
-			       inet->opt->optlen);
+		if (inet_opt)
+			memcpy(optbuf, &inet_opt->opt,
+			       sizeof(struct ip_options) +
+			       inet_opt->opt.optlen);
 		release_sock(sk);
 
 		if (opt->optlen == 0)
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index abf14dbcb3b9e..a8659e0c4a6e3 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -460,6 +460,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	__be32 saddr;
 	u8  tos;
 	int err;
+	struct ip_options_data opt_copy;
 
 	err = -EMSGSIZE;
 	if (len > 0xFFFF)
@@ -520,8 +521,18 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	saddr = ipc.addr;
 	ipc.addr = daddr;
 
-	if (!ipc.opt)
-		ipc.opt = inet->opt;
+	if (!ipc.opt) {
+		struct ip_options_rcu *inet_opt;
+
+		rcu_read_lock();
+		inet_opt = rcu_dereference(inet->inet_opt);
+		if (inet_opt) {
+			memcpy(&opt_copy, inet_opt,
+			       sizeof(*inet_opt) + inet_opt->opt.optlen);
+			ipc.opt = &opt_copy.opt;
+		}
+		rcu_read_unlock();
+	}
 
 	if (ipc.opt) {
 		err = -EINVAL;
@@ -530,10 +541,10 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		 */
 		if (inet->hdrincl)
 			goto done;
-		if (ipc.opt->srr) {
+		if (ipc.opt->opt.srr) {
 			if (!daddr)
 				goto done;
-			daddr = ipc.opt->faddr;
+			daddr = ipc.opt->opt.faddr;
 		}
 	}
 	tos = RT_CONN_FLAGS(sk);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 71e029691908d..26461492a847d 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -321,10 +321,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
 	 */
 	if (opt && opt->optlen) {
-		int opt_size = sizeof(struct ip_options) + opt->optlen;
+		int opt_size = sizeof(struct ip_options_rcu) + opt->optlen;
 
 		ireq->opt = kmalloc(opt_size, GFP_ATOMIC);
-		if (ireq->opt != NULL && ip_options_echo(ireq->opt, skb)) {
+		if (ireq->opt != NULL && ip_options_echo(&ireq->opt->opt, skb)) {
 			kfree(ireq->opt);
 			ireq->opt = NULL;
 		}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 310454c2f4d13..d60732fe5f21e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -154,6 +154,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct flowi4 fl4;
 	struct rtable *rt;
 	int err;
+	struct ip_options_rcu *inet_opt;
 
 	if (addr_len < sizeof(struct sockaddr_in))
 		return -EINVAL;
@@ -162,10 +163,12 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		return -EAFNOSUPPORT;
 
 	nexthop = daddr = usin->sin_addr.s_addr;
-	if (inet->opt && inet->opt->srr) {
+	inet_opt = rcu_dereference_protected(inet->inet_opt,
+					     sock_owned_by_user(sk));
+	if (inet_opt && inet_opt->opt.srr) {
 		if (!daddr)
 			return -EINVAL;
-		nexthop = inet->opt->faddr;
+		nexthop = inet_opt->opt.faddr;
 	}
 
 	orig_sport = inet->inet_sport;
@@ -186,7 +189,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		return -ENETUNREACH;
 	}
 
-	if (!inet->opt || !inet->opt->srr)
+	if (!inet_opt || !inet_opt->opt.srr)
 		daddr = rt->rt_dst;
 
 	if (!inet->inet_saddr)
@@ -222,8 +225,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	inet->inet_daddr = daddr;
 
 	inet_csk(sk)->icsk_ext_hdr_len = 0;
-	if (inet->opt)
-		inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
+	if (inet_opt)
+		inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
 
 	tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT;
 
@@ -820,17 +823,18 @@ static void syn_flood_warning(const struct sk_buff *skb)
 /*
  * Save and compile IPv4 options into the request_sock if needed.
  */
-static struct ip_options *tcp_v4_save_options(struct sock *sk,
-					      struct sk_buff *skb)
+static struct ip_options_rcu *tcp_v4_save_options(struct sock *sk,
+						  struct sk_buff *skb)
 {
-	struct ip_options *opt = &(IPCB(skb)->opt);
-	struct ip_options *dopt = NULL;
+	const struct ip_options *opt = &(IPCB(skb)->opt);
+	struct ip_options_rcu *dopt = NULL;
 
 	if (opt && opt->optlen) {
-		int opt_size = optlength(opt);
+		int opt_size = sizeof(*dopt) + opt->optlen;
+
 		dopt = kmalloc(opt_size, GFP_ATOMIC);
 		if (dopt) {
-			if (ip_options_echo(dopt, skb)) {
+			if (ip_options_echo(&dopt->opt, skb)) {
 				kfree(dopt);
 				dopt = NULL;
 			}
@@ -1411,6 +1415,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 #ifdef CONFIG_TCP_MD5SIG
 	struct tcp_md5sig_key *key;
 #endif
+	struct ip_options_rcu *inet_opt;
 
 	if (sk_acceptq_is_full(sk))
 		goto exit_overflow;
@@ -1431,13 +1436,14 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newinet->inet_daddr   = ireq->rmt_addr;
 	newinet->inet_rcv_saddr = ireq->loc_addr;
 	newinet->inet_saddr	      = ireq->loc_addr;
-	newinet->opt	      = ireq->opt;
+	inet_opt	      = ireq->opt;
+	rcu_assign_pointer(newinet->inet_opt, inet_opt);
 	ireq->opt	      = NULL;
 	newinet->mc_index     = inet_iif(skb);
 	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (newinet->opt)
-		inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen;
+	if (inet_opt)
+		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
 	newinet->inet_id = newtp->write_seq ^ jiffies;
 
 	tcp_mtup_init(newsk);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index bc0dab2593e05..544f435d1affe 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -804,6 +804,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
 	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
 	struct sk_buff *skb;
+	struct ip_options_data opt_copy;
 
 	if (len > 0xFFFF)
 		return -EMSGSIZE;
@@ -877,22 +878,32 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			free = 1;
 		connected = 0;
 	}
-	if (!ipc.opt)
-		ipc.opt = inet->opt;
+	if (!ipc.opt) {
+		struct ip_options_rcu *inet_opt;
+
+		rcu_read_lock();
+		inet_opt = rcu_dereference(inet->inet_opt);
+		if (inet_opt) {
+			memcpy(&opt_copy, inet_opt,
+			       sizeof(*inet_opt) + inet_opt->opt.optlen);
+			ipc.opt = &opt_copy.opt;
+		}
+		rcu_read_unlock();
+	}
 
 	saddr = ipc.addr;
 	ipc.addr = faddr = daddr;
 
-	if (ipc.opt && ipc.opt->srr) {
+	if (ipc.opt && ipc.opt->opt.srr) {
 		if (!daddr)
 			return -EINVAL;
-		faddr = ipc.opt->faddr;
+		faddr = ipc.opt->opt.faddr;
 		connected = 0;
 	}
 	tos = RT_TOS(inet->tos);
 	if (sock_flag(sk, SOCK_LOCALROUTE) ||
 	    (msg->msg_flags & MSG_DONTROUTE) ||
-	    (ipc.opt && ipc.opt->is_strictroute)) {
+	    (ipc.opt && ipc.opt->opt.is_strictroute)) {
 		tos |= RTO_ONLINK;
 		connected = 0;
 	}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index cb7658aceb6c0..868366470b4af 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1469,7 +1469,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	   First: no IPv4 options.
 	 */
-	newinet->opt = NULL;
+	newinet->inet_opt = NULL;
 	newnp->ipv6_fl_list = NULL;
 
 	/* Clone RX bits */
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index cc673677c5de8..962a607b51da8 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -416,7 +416,6 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 	int rc;
 	struct l2tp_ip_sock *lsa = l2tp_ip_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);
-	struct ip_options *opt = inet->opt;
 	struct rtable *rt = NULL;
 	int connected = 0;
 	__be32 daddr;
@@ -471,9 +470,14 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		rt = (struct rtable *) __sk_dst_check(sk, 0);
 
 	if (rt == NULL) {
+		struct ip_options_rcu *inet_opt;
+
+		inet_opt = rcu_dereference_protected(inet->inet_opt,
+						     sock_owned_by_user(sk));
+
 		/* Use correct destination address if we have options. */
-		if (opt && opt->srr)
-			daddr = opt->faddr;
+		if (inet_opt && inet_opt->opt.srr)
+			daddr = inet_opt->opt.faddr;
 
 		/* If this fails, retransmit mechanism of transport layer will
 		 * keep trying until route appears or the connection times
-- 
cgit v1.2.3


From 96339d6c490a32de35fa798ca7922d13a8538ecd Mon Sep 17 00:00:00 2001
From: Shan Wei <shanwei@cn.fujitsu.com>
Date: Fri, 22 Apr 2011 19:07:41 +0800
Subject: net:use help function of skb_checksum_start_offset to calculate
 offset

Although these are equivalent, but the skb_checksum_start_offset() is more readable.

Signed-off-by: Shan Wei <shanwei@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tile/tilepro.c | 2 +-
 net/ipv6/udp.c             | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/ipv6')

diff --git a/drivers/net/tile/tilepro.c b/drivers/net/tile/tilepro.c
index 0825db6d883fb..1e980fdd9d777 100644
--- a/drivers/net/tile/tilepro.c
+++ b/drivers/net/tile/tilepro.c
@@ -1930,7 +1930,7 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev)
 	unsigned int len = skb->len;
 	unsigned char *data = skb->data;
 
-	unsigned int csum_start = skb->csum_start - skb_headroom(skb);
+	unsigned int csum_start = skb_checksum_start_offset(skb);
 
 	lepp_frag_t frags[LEPP_MAX_FRAGS];
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 98ecfd7359e29..fc0c42a88e549 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1328,7 +1328,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features)
 	/* 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->csum_start - skb_headroom(skb);
+	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);
-- 
cgit v1.2.3


From 5c1e6aa300a7a669dc469d2dcb20172c6bd8fed9 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 28 Apr 2011 14:13:38 -0700
Subject: net: Make dst_alloc() take more explicit initializations.

Now the dst->dev, dev->obsolete, and dst->flags values can
be specified as well.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h      |  3 ++-
 net/core/dst.c         | 18 +++++++++++++-----
 net/decnet/dn_route.c  | 13 ++-----------
 net/ipv4/route.c       | 40 +++++++++++++++-------------------------
 net/ipv6/route.c       | 29 +++++++++++------------------
 net/xfrm/xfrm_policy.c |  2 +-
 6 files changed, 44 insertions(+), 61 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/dst.h b/include/net/dst.h
index d7bb74062df1a..2588a9a88cc6d 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -350,7 +350,8 @@ static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb)
 }
 
 extern int dst_discard(struct sk_buff *skb);
-extern void *dst_alloc(struct dst_ops * ops, int initial_ref);
+extern void *dst_alloc(struct dst_ops * ops, struct net_device *dev,
+		       int initial_ref, int initial_obsolete, int flags);
 extern void __dst_free(struct dst_entry * dst);
 extern struct dst_entry *dst_destroy(struct dst_entry * dst);
 
diff --git a/net/core/dst.c b/net/core/dst.c
index 91104d35de7d9..9505778ec800e 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -166,7 +166,8 @@ EXPORT_SYMBOL(dst_discard);
 
 const u32 dst_default_metrics[RTAX_MAX];
 
-void *dst_alloc(struct dst_ops *ops, int initial_ref)
+void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
+		int initial_ref, int initial_obsolete, int flags)
 {
 	struct dst_entry *dst;
 
@@ -177,12 +178,19 @@ void *dst_alloc(struct dst_ops *ops, int initial_ref)
 	dst = kmem_cache_zalloc(ops->kmem_cachep, GFP_ATOMIC);
 	if (!dst)
 		return NULL;
-	atomic_set(&dst->__refcnt, initial_ref);
 	dst->ops = ops;
-	dst->lastuse = jiffies;
-	dst->path = dst;
-	dst->input = dst->output = dst_discard;
+	dst->dev = dev;
+	if (dev)
+		dev_hold(dev);
 	dst_init_metrics(dst, dst_default_metrics, true);
+	dst->path = dst;
+	dst->input = dst_discard;
+	dst->output = dst_discard;
+
+	dst->obsolete = initial_obsolete;
+	atomic_set(&dst->__refcnt, initial_ref);
+	dst->lastuse = jiffies;
+	dst->flags = flags;
 #if RT_CACHE_DEBUG >= 2
 	atomic_inc(&dst_total);
 #endif
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 9f09d4fc2880d..f489b081c25d4 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1125,13 +1125,10 @@ make_route:
 	if (dev_out->flags & IFF_LOOPBACK)
 		flags |= RTCF_LOCAL;
 
-	rt = dst_alloc(&dn_dst_ops, 0);
+	rt = dst_alloc(&dn_dst_ops, dev_out, 1, 0, DST_HOST);
 	if (rt == NULL)
 		goto e_nobufs;
 
-	atomic_set(&rt->dst.__refcnt, 1);
-	rt->dst.flags   = DST_HOST;
-
 	rt->fld.saddr        = oldflp->saddr;
 	rt->fld.daddr        = oldflp->daddr;
 	rt->fld.flowidn_oif  = oldflp->flowidn_oif;
@@ -1146,8 +1143,6 @@ make_route:
 	rt->rt_dst_map    = fld.daddr;
 	rt->rt_src_map    = fld.saddr;
 
-	rt->dst.dev = dev_out;
-	dev_hold(dev_out);
 	rt->dst.neighbour = neigh;
 	neigh = NULL;
 
@@ -1399,7 +1394,7 @@ static int dn_route_input_slow(struct sk_buff *skb)
 	}
 
 make_route:
-	rt = dst_alloc(&dn_dst_ops, 0);
+	rt = dst_alloc(&dn_dst_ops, out_dev, 0, 0, DST_HOST);
 	if (rt == NULL)
 		goto e_nobufs;
 
@@ -1419,9 +1414,7 @@ make_route:
 	rt->fld.flowidn_iif  = in_dev->ifindex;
 	rt->fld.flowidn_mark = fld.flowidn_mark;
 
-	rt->dst.flags = DST_HOST;
 	rt->dst.neighbour = neigh;
-	rt->dst.dev = out_dev;
 	rt->dst.lastuse = jiffies;
 	rt->dst.output = dn_rt_bug;
 	switch(res.type) {
@@ -1440,8 +1433,6 @@ make_route:
 			rt->dst.input = dst_discard;
 	}
 	rt->rt_flags = flags;
-	if (rt->dst.dev)
-		dev_hold(rt->dst.dev);
 
 	err = dn_rt_set_next_hop(rt, &res);
 	if (err)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d63f780c6941d..b471d89b57ee6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1833,17 +1833,13 @@ static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *oldflp4,
 	rt->rt_type = type;
 }
 
-static struct rtable *rt_dst_alloc(bool nopolicy, bool noxfrm)
+static struct rtable *rt_dst_alloc(struct net_device *dev,
+				   bool nopolicy, bool noxfrm)
 {
-	struct rtable *rt = dst_alloc(&ipv4_dst_ops, 1);
-	if (rt) {
-		rt->dst.obsolete = -1;
-
-		rt->dst.flags = DST_HOST |
-			(nopolicy ? DST_NOPOLICY : 0) |
-			(noxfrm ? DST_NOXFRM : 0);
-	}
-	return rt;
+	return dst_alloc(&ipv4_dst_ops, dev, 1, -1,
+			 DST_HOST |
+			 (nopolicy ? DST_NOPOLICY : 0) |
+			 (noxfrm ? DST_NOXFRM : 0));
 }
 
 /* called in rcu_read_lock() section */
@@ -1876,7 +1872,8 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		if (err < 0)
 			goto e_err;
 	}
-	rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+	rth = rt_dst_alloc(init_net.loopback_dev,
+			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
 	if (!rth)
 		goto e_nobufs;
 
@@ -1893,8 +1890,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 #endif
 	rth->rt_route_iif = dev->ifindex;
 	rth->rt_iif	= dev->ifindex;
-	rth->dst.dev	= init_net.loopback_dev;
-	dev_hold(rth->dst.dev);
 	rth->rt_oif	= 0;
 	rth->rt_gateway	= daddr;
 	rth->rt_spec_dst= spec_dst;
@@ -2013,7 +2008,8 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
-	rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY),
+	rth = rt_dst_alloc(out_dev->dev,
+			   IN_DEV_CONF_GET(in_dev, NOPOLICY),
 			   IN_DEV_CONF_GET(out_dev, NOXFRM));
 	if (!rth) {
 		err = -ENOBUFS;
@@ -2029,8 +2025,6 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->rt_gateway	= daddr;
 	rth->rt_route_iif = in_dev->dev->ifindex;
 	rth->rt_iif 	= in_dev->dev->ifindex;
-	rth->dst.dev	= (out_dev)->dev;
-	dev_hold(rth->dst.dev);
 	rth->rt_oif 	= 0;
 	rth->rt_spec_dst= spec_dst;
 
@@ -2188,7 +2182,8 @@ brd_input:
 	RT_CACHE_STAT_INC(in_brd);
 
 local_input:
-	rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+	rth = rt_dst_alloc(net->loopback_dev,
+			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
 	if (!rth)
 		goto e_nobufs;
 
@@ -2206,8 +2201,6 @@ local_input:
 #endif
 	rth->rt_route_iif = dev->ifindex;
 	rth->rt_iif	= dev->ifindex;
-	rth->dst.dev	= net->loopback_dev;
-	dev_hold(rth->dst.dev);
 	rth->rt_gateway	= daddr;
 	rth->rt_spec_dst= spec_dst;
 	rth->dst.input= ip_local_deliver;
@@ -2392,7 +2385,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 			fi = NULL;
 	}
 
-	rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY),
+	rth = rt_dst_alloc(dev_out,
+			   IN_DEV_CONF_GET(in_dev, NOPOLICY),
 			   IN_DEV_CONF_GET(in_dev, NOXFRM));
 	if (!rth)
 		return ERR_PTR(-ENOBUFS);
@@ -2406,10 +2400,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	rth->rt_src	= fl4->saddr;
 	rth->rt_route_iif = 0;
 	rth->rt_iif	= oldflp4->flowi4_oif ? : dev_out->ifindex;
-	/* get references to the devices that are to be hold by the routing
-	   cache entry */
-	rth->dst.dev	= dev_out;
-	dev_hold(dev_out);
 	rth->rt_gateway = fl4->daddr;
 	rth->rt_spec_dst= fl4->saddr;
 
@@ -2711,7 +2701,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
 
 struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
 {
-	struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, 1);
+	struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, 0, 0);
 	struct rtable *ort = (struct rtable *) dst_orig;
 
 	if (rt) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 19a77d0e03080..e8b2bb9060ef1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -227,9 +227,10 @@ static struct rt6_info ip6_blk_hole_entry_template = {
 #endif
 
 /* allocate dst with ip6_dst_ops */
-static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops)
+static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops,
+					     struct net_device *dev)
 {
-	return (struct rt6_info *)dst_alloc(ops, 0);
+	return (struct rt6_info *)dst_alloc(ops, dev, 0, 0, 0);
 }
 
 static void ip6_dst_destroy(struct dst_entry *dst)
@@ -881,10 +882,10 @@ EXPORT_SYMBOL(ip6_route_output);
 
 struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
 {
-	struct rt6_info *rt = dst_alloc(&ip6_dst_blackhole_ops, 1);
-	struct rt6_info *ort = (struct rt6_info *) dst_orig;
+	struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig;
 	struct dst_entry *new = NULL;
 
+	rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0);
 	if (rt) {
 		new = &rt->dst;
 
@@ -893,9 +894,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 		new->output = dst_discard;
 
 		dst_copy_metrics(new, &ort->dst);
-		new->dev = ort->dst.dev;
-		if (new->dev)
-			dev_hold(new->dev);
 		rt->rt6i_idev = ort->rt6i_idev;
 		if (rt->rt6i_idev)
 			in6_dev_hold(rt->rt6i_idev);
@@ -1038,13 +1036,12 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	if (unlikely(idev == NULL))
 		return NULL;
 
-	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev);
 	if (unlikely(rt == NULL)) {
 		in6_dev_put(idev);
 		goto out;
 	}
 
-	dev_hold(dev);
 	if (neigh)
 		neigh_hold(neigh);
 	else {
@@ -1053,7 +1050,6 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 			neigh = NULL;
 	}
 
-	rt->rt6i_dev	  = dev;
 	rt->rt6i_idev     = idev;
 	rt->rt6i_nexthop  = neigh;
 	atomic_set(&rt->dst.__refcnt, 1);
@@ -1212,7 +1208,7 @@ int ip6_route_add(struct fib6_config *cfg)
 		goto out;
 	}
 
-	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL);
 
 	if (rt == NULL) {
 		err = -ENOMEM;
@@ -1731,7 +1727,8 @@ void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *sad
 static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
 {
 	struct net *net = dev_net(ort->rt6i_dev);
-	struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+	struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
+					    ort->dst.dev);
 
 	if (rt) {
 		rt->dst.input = ort->dst.input;
@@ -1739,9 +1736,6 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
 
 		dst_copy_metrics(&rt->dst, &ort->dst);
 		rt->dst.error = ort->dst.error;
-		rt->dst.dev = ort->dst.dev;
-		if (rt->dst.dev)
-			dev_hold(rt->dst.dev);
 		rt->rt6i_idev = ort->rt6i_idev;
 		if (rt->rt6i_idev)
 			in6_dev_hold(rt->rt6i_idev);
@@ -2011,7 +2005,8 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 				    int anycast)
 {
 	struct net *net = dev_net(idev->dev);
-	struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+	struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
+					    net->loopback_dev);
 	struct neighbour *neigh;
 
 	if (rt == NULL) {
@@ -2021,13 +2016,11 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	dev_hold(net->loopback_dev);
 	in6_dev_hold(idev);
 
 	rt->dst.flags = DST_HOST;
 	rt->dst.input = ip6_input;
 	rt->dst.output = ip6_output;
-	rt->rt6i_dev = net->loopback_dev;
 	rt->rt6i_idev = idev;
 	rt->dst.obsolete = -1;
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 15792d8b62721..70552c4e22726 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1348,7 +1348,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
 	default:
 		BUG();
 	}
-	xdst = dst_alloc(dst_ops, 0);
+	xdst = dst_alloc(dst_ops, NULL, 0, 0, 0);
 	xfrm_policy_put_afinfo(afinfo);
 
 	if (likely(xdst))
-- 
cgit v1.2.3


From cf91166223772ef4a2ed98b9874958bf6a2470df Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 28 Apr 2011 14:31:47 -0700
Subject: net: Use non-zero allocations in dst_alloc().

Make dst_alloc() and it's users explicitly initialize the entire
entry.

The zero'ing done by kmem_cache_zalloc() was almost entirely
redundant.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dst.c         | 20 +++++++++++--
 net/decnet/dn_route.c  |  2 ++
 net/ipv4/route.c       | 78 ++++++++++++++++++++++++++++++--------------------
 net/ipv6/route.c       |  8 +++++-
 net/xfrm/xfrm_policy.c |  1 +
 5 files changed, 74 insertions(+), 35 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/core/dst.c b/net/core/dst.c
index 9505778ec800e..30f009327b629 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -175,22 +175,36 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
 		if (ops->gc(ops))
 			return NULL;
 	}
-	dst = kmem_cache_zalloc(ops->kmem_cachep, GFP_ATOMIC);
+	dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC);
 	if (!dst)
 		return NULL;
-	dst->ops = ops;
+	dst->child = NULL;
 	dst->dev = dev;
 	if (dev)
 		dev_hold(dev);
+	dst->ops = ops;
 	dst_init_metrics(dst, dst_default_metrics, true);
+	dst->expires = 0UL;
 	dst->path = dst;
+	dst->neighbour = NULL;
+	dst->hh = NULL;
+#ifdef CONFIG_XFRM
+	dst->xfrm = NULL;
+#endif
 	dst->input = dst_discard;
 	dst->output = dst_discard;
-
+	dst->error = 0;
 	dst->obsolete = initial_obsolete;
+	dst->header_len = 0;
+	dst->trailer_len = 0;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	dst->tclassid = 0;
+#endif
 	atomic_set(&dst->__refcnt, initial_ref);
+	dst->__use = 0;
 	dst->lastuse = jiffies;
 	dst->flags = flags;
+	dst->next = NULL;
 #if RT_CACHE_DEBUG >= 2
 	atomic_inc(&dst_total);
 #endif
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index f489b081c25d4..74544bc6fdecf 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1129,6 +1129,7 @@ make_route:
 	if (rt == NULL)
 		goto e_nobufs;
 
+	memset(&rt->fld, 0, sizeof(rt->fld));
 	rt->fld.saddr        = oldflp->saddr;
 	rt->fld.daddr        = oldflp->daddr;
 	rt->fld.flowidn_oif  = oldflp->flowidn_oif;
@@ -1398,6 +1399,7 @@ make_route:
 	if (rt == NULL)
 		goto e_nobufs;
 
+	memset(&rt->fld, 0, sizeof(rt->fld));
 	rt->rt_saddr      = fld.saddr;
 	rt->rt_daddr      = fld.daddr;
 	rt->rt_gateway    = fld.daddr;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b471d89b57ee6..fb9211adf0795 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1830,7 +1830,6 @@ static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *oldflp4,
 #endif
 	set_class_tag(rt, itag);
 #endif
-	rt->rt_type = type;
 }
 
 static struct rtable *rt_dst_alloc(struct net_device *dev,
@@ -1877,25 +1876,28 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (!rth)
 		goto e_nobufs;
 
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	rth->dst.tclassid = itag;
+#endif
 	rth->dst.output = ip_rt_bug;
 
 	rth->rt_key_dst	= daddr;
-	rth->rt_dst	= daddr;
-	rth->rt_tos	= tos;
-	rth->rt_mark    = skb->mark;
 	rth->rt_key_src	= saddr;
+	rth->rt_genid	= rt_genid(dev_net(dev));
+	rth->rt_flags	= RTCF_MULTICAST;
+	rth->rt_type	= RTN_MULTICAST;
+	rth->rt_tos	= tos;
+	rth->rt_dst	= daddr;
 	rth->rt_src	= saddr;
-#ifdef CONFIG_IP_ROUTE_CLASSID
-	rth->dst.tclassid = itag;
-#endif
 	rth->rt_route_iif = dev->ifindex;
 	rth->rt_iif	= dev->ifindex;
 	rth->rt_oif	= 0;
+	rth->rt_mark    = skb->mark;
 	rth->rt_gateway	= daddr;
 	rth->rt_spec_dst= spec_dst;
-	rth->rt_genid	= rt_genid(dev_net(dev));
-	rth->rt_flags	= RTCF_MULTICAST;
-	rth->rt_type	= RTN_MULTICAST;
+	rth->rt_peer_genid = 0;
+	rth->peer = NULL;
+	rth->fi = NULL;
 	if (our) {
 		rth->dst.input= ip_local_deliver;
 		rth->rt_flags |= RTCF_LOCAL;
@@ -2017,25 +2019,28 @@ static int __mkroute_input(struct sk_buff *skb,
 	}
 
 	rth->rt_key_dst	= daddr;
-	rth->rt_dst	= daddr;
-	rth->rt_tos	= tos;
-	rth->rt_mark    = skb->mark;
 	rth->rt_key_src	= saddr;
+	rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
+	rth->rt_flags = flags;
+	rth->rt_type = res->type;
+	rth->rt_tos	= tos;
+	rth->rt_dst	= daddr;
 	rth->rt_src	= saddr;
-	rth->rt_gateway	= daddr;
 	rth->rt_route_iif = in_dev->dev->ifindex;
 	rth->rt_iif 	= in_dev->dev->ifindex;
 	rth->rt_oif 	= 0;
+	rth->rt_mark    = skb->mark;
+	rth->rt_gateway	= daddr;
 	rth->rt_spec_dst= spec_dst;
+	rth->rt_peer_genid = 0;
+	rth->peer = NULL;
+	rth->fi = NULL;
 
 	rth->dst.input = ip_forward;
 	rth->dst.output = ip_output;
-	rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
 
 	rt_set_nexthop(rth, NULL, res, res->fi, res->type, itag);
 
-	rth->rt_flags = flags;
-
 	*result = rth;
 	err = 0;
  cleanup:
@@ -2187,30 +2192,37 @@ local_input:
 	if (!rth)
 		goto e_nobufs;
 
+	rth->dst.input= ip_local_deliver;
 	rth->dst.output= ip_rt_bug;
-	rth->rt_genid = rt_genid(net);
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	rth->dst.tclassid = itag;
+#endif
 
 	rth->rt_key_dst	= daddr;
-	rth->rt_dst	= daddr;
-	rth->rt_tos	= tos;
-	rth->rt_mark    = skb->mark;
 	rth->rt_key_src	= saddr;
+	rth->rt_genid = rt_genid(net);
+	rth->rt_flags 	= flags|RTCF_LOCAL;
+	rth->rt_type	= res.type;
+	rth->rt_tos	= tos;
+	rth->rt_dst	= daddr;
 	rth->rt_src	= saddr;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
 #endif
 	rth->rt_route_iif = dev->ifindex;
 	rth->rt_iif	= dev->ifindex;
+	rth->rt_oif	= 0;
+	rth->rt_mark    = skb->mark;
 	rth->rt_gateway	= daddr;
 	rth->rt_spec_dst= spec_dst;
-	rth->dst.input= ip_local_deliver;
-	rth->rt_flags 	= flags|RTCF_LOCAL;
+	rth->rt_peer_genid = 0;
+	rth->peer = NULL;
+	rth->fi = NULL;
 	if (res.type == RTN_UNREACHABLE) {
 		rth->dst.input= ip_error;
 		rth->dst.error= -err;
 		rth->rt_flags 	&= ~RTCF_LOCAL;
 	}
-	rth->rt_type	= res.type;
 	hash = rt_hash(daddr, saddr, fl4.flowi4_iif, rt_genid(net));
 	rth = rt_intern_hash(hash, rth, skb, fl4.flowi4_iif);
 	err = 0;
@@ -2391,20 +2403,25 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	if (!rth)
 		return ERR_PTR(-ENOBUFS);
 
+	rth->dst.output = ip_output;
+
 	rth->rt_key_dst	= oldflp4->daddr;
-	rth->rt_tos	= tos;
 	rth->rt_key_src	= oldflp4->saddr;
-	rth->rt_oif	= oldflp4->flowi4_oif;
-	rth->rt_mark    = oldflp4->flowi4_mark;
+	rth->rt_genid = rt_genid(dev_net(dev_out));
+	rth->rt_flags	= flags;
+	rth->rt_type	= type;
+	rth->rt_tos	= tos;
 	rth->rt_dst	= fl4->daddr;
 	rth->rt_src	= fl4->saddr;
 	rth->rt_route_iif = 0;
 	rth->rt_iif	= oldflp4->flowi4_oif ? : dev_out->ifindex;
+	rth->rt_oif	= oldflp4->flowi4_oif;
+	rth->rt_mark    = oldflp4->flowi4_mark;
 	rth->rt_gateway = fl4->daddr;
 	rth->rt_spec_dst= fl4->saddr;
-
-	rth->dst.output=ip_output;
-	rth->rt_genid = rt_genid(dev_net(dev_out));
+	rth->rt_peer_genid = 0;
+	rth->peer = NULL;
+	rth->fi = NULL;
 
 	RT_CACHE_STAT_INC(out_slow_tot);
 
@@ -2432,7 +2449,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 
 	rt_set_nexthop(rth, oldflp4, res, fi, type, 0);
 
-	rth->rt_flags = flags;
 	return rth;
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e8b2bb9060ef1..f1be5c5c85ef6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -230,7 +230,11 @@ static struct rt6_info ip6_blk_hole_entry_template = {
 static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops,
 					     struct net_device *dev)
 {
-	return (struct rt6_info *)dst_alloc(ops, dev, 0, 0, 0);
+	struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, 0);
+
+	memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
+
+	return rt;
 }
 
 static void ip6_dst_destroy(struct dst_entry *dst)
@@ -887,6 +891,8 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 
 	rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0);
 	if (rt) {
+		memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
+
 		new = &rt->dst;
 
 		new->__use = 1;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 70552c4e22726..00bcb88386c28 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1349,6 +1349,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
 		BUG();
 	}
 	xdst = dst_alloc(dst_ops, NULL, 0, 0, 0);
+	memset(&xdst->u.rt6.rt6i_table, 0, sizeof(*xdst) - sizeof(struct dst_entry));
 	xfrm_policy_put_afinfo(afinfo);
 
 	if (likely(xdst))
-- 
cgit v1.2.3


From ad246c992bea6d33c6421ba1f03e2b405792adf9 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Tue, 26 Apr 2011 15:25:52 +0000
Subject: ipv4, ipv6, bonding: Restore control over number of peer
 notifications

For backward compatibility, we should retain the module parameters and
sysfs attributes to control the number of peer notifications
(gratuitous ARPs and unsolicited NAs) sent after bonding failover.
Also, it is possible for failover to take place even though the new
active slave does not have link up, and in that case the peer
notification should be deferred until it does.

Change ipv4 and ipv6 so they do not automatically send peer
notifications on bonding failover.

Change the bonding driver to send separate NETDEV_NOTIFY_PEERS
notifications when the link is up, as many times as requested.  Since
it does not directly control which protocols send notifications, make
num_grat_arp and num_unsol_na aliases for a single parameter.  Bump
the bonding version number and update its documentation.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: Jay Vosburgh <fubar@us.ibm.com>
Acked-by: Brian Haley <brian.haley@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/bonding.txt | 34 ++++++++++-----------
 drivers/net/bonding/bond_main.c      | 59 ++++++++++++++++++++++++++++++++++++
 drivers/net/bonding/bond_sysfs.c     | 26 ++++++++++++++++
 drivers/net/bonding/bonding.h        |  6 ++--
 net/ipv4/devinet.c                   |  1 -
 net/ipv6/ndisc.c                     |  1 -
 6 files changed, 105 insertions(+), 22 deletions(-)

(limited to 'net/ipv6')

diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index e27202bb8d752..1f45bd887d656 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -1,7 +1,7 @@
 
 		Linux Ethernet Bonding Driver HOWTO
 
-		Latest update: 23 September 2009
+		Latest update: 27 April 2011
 
 Initial release : Thomas Davis <tadavis at lbl.gov>
 Corrections, HA extensions : 2000/10/03-15 :
@@ -585,25 +585,23 @@ mode
 		chosen.
 
 num_grat_arp
-
-	Specifies the number of gratuitous ARPs to be issued after a
-	failover event.  One gratuitous ARP is issued immediately after
-	the failover, subsequent ARPs are sent at a rate of one per link
-	monitor interval (arp_interval or miimon, whichever is active).
-
-	The valid range is 0 - 255; the default value is 1.  This option
-	affects only the active-backup mode.  This option was added for
-	bonding version 3.3.0.
-
 num_unsol_na
 
-	Specifies the number of unsolicited IPv6 Neighbor Advertisements
-	to be issued after a failover event.  One unsolicited NA is issued
-	immediately after the failover.
-
-	The valid range is 0 - 255; the default value is 1.  This option
-	affects only the active-backup mode.  This option was added for
-	bonding version 3.4.0.
+	Specify the number of peer notifications (gratuitous ARPs and
+	unsolicited IPv6 Neighbor Advertisements) to be issued after a
+	failover event.  As soon as the link is up on the new slave
+	(possibly immediately) a peer notification is sent on the
+	bonding device and each VLAN sub-device.  This is repeated at
+	each link monitor interval (arp_interval or miimon, whichever
+	is active) if the number is greater than 1.
+
+	The valid range is 0 - 255; the default value is 1.  These options
+	affect only the active-backup mode.  These options were added for
+	bonding versions 3.3.0 and 3.4.0 respectively.
+
+	From Linux 2.6.40 and bonding version 3.7.1, these notifications
+	are generated by the ipv4 and ipv6 code and the numbers of
+	repetitions cannot be set independently.
 
 primary
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 66d9dc6e5cacd..22bd03bd1d359 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -89,6 +89,7 @@
 
 static int max_bonds	= BOND_DEFAULT_MAX_BONDS;
 static int tx_queues	= BOND_DEFAULT_TX_QUEUES;
+static int num_peer_notif = 1;
 static int miimon	= BOND_LINK_MON_INTERV;
 static int updelay;
 static int downdelay;
@@ -111,6 +112,10 @@ module_param(max_bonds, int, 0);
 MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
 module_param(tx_queues, int, 0);
 MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)");
+module_param_named(num_grat_arp, num_peer_notif, int, 0644);
+MODULE_PARM_DESC(num_grat_arp, "Number of peer notifications to send on failover event (alias of num_unsol_na)");
+module_param_named(num_unsol_na, num_peer_notif, int, 0644);
+MODULE_PARM_DESC(num_unsol_na, "Number of peer notifications to send on failover event (alias of num_grat_arp)");
 module_param(miimon, int, 0);
 MODULE_PARM_DESC(miimon, "Link check interval in milliseconds");
 module_param(updelay, int, 0);
@@ -1082,6 +1087,21 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
 	return bestslave;
 }
 
+static bool bond_should_notify_peers(struct bonding *bond)
+{
+	struct slave *slave = bond->curr_active_slave;
+
+	pr_debug("bond_should_notify_peers: bond %s slave %s\n",
+		 bond->dev->name, slave ? slave->dev->name : "NULL");
+
+	if (!slave || !bond->send_peer_notif ||
+	    test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
+		return false;
+
+	bond->send_peer_notif--;
+	return true;
+}
+
 /**
  * change_active_interface - change the active slave into the specified one
  * @bond: our bonding struct
@@ -1149,16 +1169,28 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 			bond_set_slave_inactive_flags(old_active);
 
 		if (new_active) {
+			bool should_notify_peers = false;
+
 			bond_set_slave_active_flags(new_active);
 
 			if (bond->params.fail_over_mac)
 				bond_do_fail_over_mac(bond, new_active,
 						      old_active);
 
+			if (netif_running(bond->dev)) {
+				bond->send_peer_notif =
+					bond->params.num_peer_notif;
+				should_notify_peers =
+					bond_should_notify_peers(bond);
+			}
+
 			write_unlock_bh(&bond->curr_slave_lock);
 			read_unlock(&bond->lock);
 
 			netdev_bonding_change(bond->dev, NETDEV_BONDING_FAILOVER);
+			if (should_notify_peers)
+				netdev_bonding_change(bond->dev,
+						      NETDEV_NOTIFY_PEERS);
 
 			read_lock(&bond->lock);
 			write_lock_bh(&bond->curr_slave_lock);
@@ -2556,6 +2588,7 @@ void bond_mii_monitor(struct work_struct *work)
 {
 	struct bonding *bond = container_of(work, struct bonding,
 					    mii_work.work);
+	bool should_notify_peers = false;
 
 	read_lock(&bond->lock);
 	if (bond->kill_timers)
@@ -2564,6 +2597,8 @@ void bond_mii_monitor(struct work_struct *work)
 	if (bond->slave_cnt == 0)
 		goto re_arm;
 
+	should_notify_peers = bond_should_notify_peers(bond);
+
 	if (bond_miimon_inspect(bond)) {
 		read_unlock(&bond->lock);
 		rtnl_lock();
@@ -2582,6 +2617,12 @@ re_arm:
 				   msecs_to_jiffies(bond->params.miimon));
 out:
 	read_unlock(&bond->lock);
+
+	if (should_notify_peers) {
+		rtnl_lock();
+		netdev_bonding_change(bond->dev, NETDEV_NOTIFY_PEERS);
+		rtnl_unlock();
+	}
 }
 
 static __be32 bond_glean_dev_ip(struct net_device *dev)
@@ -3154,6 +3195,7 @@ void bond_activebackup_arp_mon(struct work_struct *work)
 {
 	struct bonding *bond = container_of(work, struct bonding,
 					    arp_work.work);
+	bool should_notify_peers = false;
 	int delta_in_ticks;
 
 	read_lock(&bond->lock);
@@ -3166,6 +3208,8 @@ void bond_activebackup_arp_mon(struct work_struct *work)
 	if (bond->slave_cnt == 0)
 		goto re_arm;
 
+	should_notify_peers = bond_should_notify_peers(bond);
+
 	if (bond_ab_arp_inspect(bond, delta_in_ticks)) {
 		read_unlock(&bond->lock);
 		rtnl_lock();
@@ -3185,6 +3229,12 @@ re_arm:
 		queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
 out:
 	read_unlock(&bond->lock);
+
+	if (should_notify_peers) {
+		rtnl_lock();
+		netdev_bonding_change(bond->dev, NETDEV_NOTIFY_PEERS);
+		rtnl_unlock();
+	}
 }
 
 /*-------------------------- netdev event handling --------------------------*/
@@ -3494,6 +3544,8 @@ static int bond_close(struct net_device *bond_dev)
 
 	write_lock_bh(&bond->lock);
 
+	bond->send_peer_notif = 0;
+
 	/* signal timers not to re-arm */
 	bond->kill_timers = 1;
 
@@ -4571,6 +4623,12 @@ static int bond_check_params(struct bond_params *params)
 		use_carrier = 1;
 	}
 
+	if (num_peer_notif < 0 || num_peer_notif > 255) {
+		pr_warning("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n",
+			   num_peer_notif);
+		num_peer_notif = 1;
+	}
+
 	/* reset values for 802.3ad */
 	if (bond_mode == BOND_MODE_8023AD) {
 		if (!miimon) {
@@ -4760,6 +4818,7 @@ static int bond_check_params(struct bond_params *params)
 	params->mode = bond_mode;
 	params->xmit_policy = xmit_hashtype;
 	params->miimon = miimon;
+	params->num_peer_notif = num_peer_notif;
 	params->arp_interval = arp_interval;
 	params->arp_validate = arp_validate_value;
 	params->updelay = updelay;
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 935406aa5f0c3..4059bfc73dbf5 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -868,6 +868,30 @@ out:
 static DEVICE_ATTR(ad_select, S_IRUGO | S_IWUSR,
 		   bonding_show_ad_select, bonding_store_ad_select);
 
+/*
+ * Show and set the number of peer notifications to send after a failover event.
+ */
+static ssize_t bonding_show_num_peer_notif(struct device *d,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct bonding *bond = to_bond(d);
+	return sprintf(buf, "%d\n", bond->params.num_peer_notif);
+}
+
+static ssize_t bonding_store_num_peer_notif(struct device *d,
+					    struct device_attribute *attr,
+					    const char *buf, size_t count)
+{
+	struct bonding *bond = to_bond(d);
+	int err = kstrtou8(buf, 10, &bond->params.num_peer_notif);
+	return err ? err : count;
+}
+static DEVICE_ATTR(num_grat_arp, S_IRUGO | S_IWUSR,
+		   bonding_show_num_peer_notif, bonding_store_num_peer_notif);
+static DEVICE_ATTR(num_unsol_na, S_IRUGO | S_IWUSR,
+		   bonding_show_num_peer_notif, bonding_store_num_peer_notif);
+
 /*
  * Show and set the MII monitor interval.  There are two tricky bits
  * here.  First, if MII monitoring is activated, then we must disable
@@ -1566,6 +1590,8 @@ static struct attribute *per_bond_attrs[] = {
 	&dev_attr_lacp_rate.attr,
 	&dev_attr_ad_select.attr,
 	&dev_attr_xmit_hash_policy.attr,
+	&dev_attr_num_grat_arp.attr,
+	&dev_attr_num_unsol_na.attr,
 	&dev_attr_miimon.attr,
 	&dev_attr_primary.attr,
 	&dev_attr_primary_reselect.attr,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 85fb8220e283e..d08362e1a0dd1 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -24,8 +24,8 @@
 #include "bond_3ad.h"
 #include "bond_alb.h"
 
-#define DRV_VERSION	"3.7.0"
-#define DRV_RELDATE	"June 2, 2010"
+#define DRV_VERSION	"3.7.1"
+#define DRV_RELDATE	"April 27, 2011"
 #define DRV_NAME	"bonding"
 #define DRV_DESCRIPTION	"Ethernet Channel Bonding Driver"
 
@@ -149,6 +149,7 @@ struct bond_params {
 	int mode;
 	int xmit_policy;
 	int miimon;
+	u8 num_peer_notif;
 	int arp_interval;
 	int arp_validate;
 	int use_carrier;
@@ -231,6 +232,7 @@ struct bonding {
 	rwlock_t lock;
 	rwlock_t curr_slave_lock;
 	s8       kill_timers;
+	u8	 send_peer_notif;
 	s8	 setup_by_slave;
 	s8       igmp_retrans;
 #ifdef CONFIG_PROC_FS
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index acf553f95b5b0..5345b0bee6df8 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1203,7 +1203,6 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
 			break;
 		/* fall through */
 	case NETDEV_NOTIFY_PEERS:
-	case NETDEV_BONDING_FAILOVER:
 		/* Send gratuitous ARP to notify of link change */
 		inetdev_send_gratuitous_arp(dev, in_dev);
 		break;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 69aacd18e0662..7596f071d3088 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1747,7 +1747,6 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
 		fib6_run_gc(~0UL, net);
 		break;
 	case NETDEV_NOTIFY_PEERS:
-	case NETDEV_BONDING_FAILOVER:
 		ndisc_send_unsol_na(dev);
 		break;
 	default:
-- 
cgit v1.2.3


From e67f88dd12f610da98ca838822f2c9b4e7c6100e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Wed, 27 Apr 2011 22:56:07 +0000
Subject: net: dont hold rtnl mutex during netlink dump callbacks

Four years ago, Patrick made a change to hold rtnl mutex during netlink
dump callbacks.

I believe it was a wrong move. This slows down concurrent dumps, making
good old /proc/net/ files faster than rtnetlink in some situations.

This occurred to me because one "ip link show dev ..." was _very_ slow
on a workload adding/removing network devices in background.

All dump callbacks are able to use RCU locking now, so this patch does
roughly a revert of commits :

1c2d670f366 : [RTNETLINK]: Hold rtnl_mutex during netlink dump callbacks
6313c1e0992 : [RTNETLINK]: Remove unnecessary locking in dump callbacks

This let writers fight for rtnl mutex and readers going full speed.

It also takes care of phonet : phonet_route_get() is now called from rcu
read section. I renamed it to phonet_route_get_rcu()

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Remi Denis-Courmont <remi.denis-courmont@nokia.com>
Acked-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/phonet/pn_dev.h |  2 +-
 net/bridge/br_netlink.c     |  7 ++++---
 net/core/fib_rules.c        |  3 ++-
 net/core/rtnetlink.c        | 12 +++++-------
 net/decnet/dn_dev.c         | 10 ++++++----
 net/ipv6/ip6_fib.c          |  4 +++-
 net/phonet/pn_dev.c         |  6 +-----
 net/phonet/pn_netlink.c     |  4 +++-
 8 files changed, 25 insertions(+), 23 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h
index 13649eb57413d..8639de5750f64 100644
--- a/include/net/phonet/pn_dev.h
+++ b/include/net/phonet/pn_dev.h
@@ -51,7 +51,7 @@ void phonet_address_notify(int event, struct net_device *dev, u8 addr);
 int phonet_route_add(struct net_device *dev, u8 daddr);
 int phonet_route_del(struct net_device *dev, u8 daddr);
 void rtm_phonet_notify(int event, struct net_device *dev, u8 dst);
-struct net_device *phonet_route_get(struct net *net, u8 daddr);
+struct net_device *phonet_route_get_rcu(struct net *net, u8 daddr);
 struct net_device *phonet_route_output(struct net *net, u8 daddr);
 
 #define PN_NO_ADDR	0xff
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 134a2ff6b98bc..ffb0dc4cc0e80 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -120,8 +120,9 @@ static int br_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	int idx;
 
 	idx = 0;
-	for_each_netdev(net, dev) {
-		struct net_bridge_port *port = br_port_get_rtnl(dev);
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		struct net_bridge_port *port = br_port_get_rcu(dev);
 
 		/* not a bridge port */
 		if (!port || idx < cb->args[0])
@@ -135,7 +136,7 @@ static int br_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 skip:
 		++idx;
 	}
-
+	rcu_read_unlock();
 	cb->args[0] = idx;
 
 	return skb->len;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 8248ebb5891d0..3911586e12e4b 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -590,7 +590,8 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
 	int idx = 0;
 	struct fib_rule *rule;
 
-	list_for_each_entry(rule, &ops->rules_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
 		if (idx < cb->args[1])
 			goto skip;
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d7c4bb4b18208..2963312571954 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1007,10 +1007,11 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	s_h = cb->args[0];
 	s_idx = cb->args[1];
 
+	rcu_read_lock();
 	for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
 		idx = 0;
 		head = &net->dev_index_head[h];
-		hlist_for_each_entry(dev, node, head, index_hlist) {
+		hlist_for_each_entry_rcu(dev, node, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
 			if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
@@ -1023,6 +1024,7 @@ cont:
 		}
 	}
 out:
+	rcu_read_unlock();
 	cb->args[1] = idx;
 	cb->args[0] = h;
 
@@ -1879,7 +1881,6 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int min_len;
 	int family;
 	int type;
-	int err;
 
 	type = nlh->nlmsg_type;
 	if (type > RTM_MAX)
@@ -1906,11 +1907,8 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (dumpit == NULL)
 			return -EOPNOTSUPP;
 
-		__rtnl_unlock();
 		rtnl = net->rtnl;
-		err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL);
-		rtnl_lock();
-		return err;
+		return netlink_dump_start(rtnl, skb, nlh, dumpit, NULL);
 	}
 
 	memset(rta_buf, 0, (rtattr_max * sizeof(struct rtattr *)));
@@ -1980,7 +1978,7 @@ static int __net_init rtnetlink_net_init(struct net *net)
 {
 	struct sock *sk;
 	sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX,
-				   rtnetlink_rcv, &rtnl_mutex, THIS_MODULE);
+				   rtnetlink_rcv, NULL, THIS_MODULE);
 	if (!sk)
 		return -ENOMEM;
 	net->rtnl = sk;
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 0dcaa903e00e0..404fa15910274 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -752,7 +752,8 @@ static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 	skip_naddr = cb->args[1];
 
 	idx = 0;
-	for_each_netdev(&init_net, dev) {
+	rcu_read_lock();
+	for_each_netdev_rcu(&init_net, dev) {
 		if (idx < skip_ndevs)
 			goto cont;
 		else if (idx > skip_ndevs) {
@@ -761,11 +762,11 @@ static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 			skip_naddr = 0;
 		}
 
-		if ((dn_db = rtnl_dereference(dev->dn_ptr)) == NULL)
+		if ((dn_db = rcu_dereference(dev->dn_ptr)) == NULL)
 			goto cont;
 
-		for (ifa = rtnl_dereference(dn_db->ifa_list), dn_idx = 0; ifa;
-		     ifa = rtnl_dereference(ifa->ifa_next), dn_idx++) {
+		for (ifa = rcu_dereference(dn_db->ifa_list), dn_idx = 0; ifa;
+		     ifa = rcu_dereference(ifa->ifa_next), dn_idx++) {
 			if (dn_idx < skip_naddr)
 				continue;
 
@@ -778,6 +779,7 @@ cont:
 		idx++;
 	}
 done:
+	rcu_read_unlock();
 	cb->args[0] = idx;
 	cb->args[1] = dn_idx;
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index dd88df0a5d7f8..4076a0b14b209 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -394,10 +394,11 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	arg.net = net;
 	w->args = &arg;
 
+	rcu_read_lock();
 	for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) {
 		e = 0;
 		head = &net->ipv6.fib_table_hash[h];
-		hlist_for_each_entry(tb, node, head, tb6_hlist) {
+		hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) {
 			if (e < s_e)
 				goto next;
 			res = fib6_dump_table(tb, skb, cb);
@@ -408,6 +409,7 @@ next:
 		}
 	}
 out:
+	rcu_read_unlock();
 	cb->args[1] = e;
 	cb->args[0] = h;
 
diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c
index 947038ddd04cb..47b3452675b67 100644
--- a/net/phonet/pn_dev.c
+++ b/net/phonet/pn_dev.c
@@ -426,18 +426,14 @@ int phonet_route_del(struct net_device *dev, u8 daddr)
 	return 0;
 }
 
-struct net_device *phonet_route_get(struct net *net, u8 daddr)
+struct net_device *phonet_route_get_rcu(struct net *net, u8 daddr)
 {
 	struct phonet_net *pnn = phonet_pernet(net);
 	struct phonet_routes *routes = &pnn->routes;
 	struct net_device *dev;
 
-	ASSERT_RTNL(); /* no need to hold the device */
-
 	daddr >>= 2;
-	rcu_read_lock();
 	dev = rcu_dereference(routes->table[daddr]);
-	rcu_read_unlock();
 	return dev;
 }
 
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index 58b3b1f991ed2..438accb7a5a8a 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -264,10 +264,11 @@ static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	struct net *net = sock_net(skb->sk);
 	u8 addr, addr_idx = 0, addr_start_idx = cb->args[0];
 
+	rcu_read_lock();
 	for (addr = 0; addr < 64; addr++) {
 		struct net_device *dev;
 
-		dev = phonet_route_get(net, addr << 2);
+		dev = phonet_route_get_rcu(net, addr << 2);
 		if (!dev)
 			continue;
 
@@ -279,6 +280,7 @@ static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 
 out:
+	rcu_read_unlock();
 	cb->args[0] = addr_idx;
 	cb->args[1] = 0;
 
-- 
cgit v1.2.3


From 31e4543db29fb85496a122b965d6482c8d1a2bfe Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 3 May 2011 20:25:42 -0700
Subject: ipv4: Make caller provide on-stack flow key to
 ip_route_output_ports().

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/cxgb3/iwch_cm.c |  3 ++-
 drivers/infiniband/hw/cxgb4/cm.c      |  3 ++-
 drivers/net/pptp.c                    |  6 ++++--
 drivers/scsi/cxgbi/libcxgbi.c         |  3 ++-
 include/net/route.h                   | 11 +++++------
 net/ipv4/af_inet.c                    |  3 ++-
 net/ipv4/igmp.c                       |  6 ++++--
 net/ipv4/ip_output.c                  |  3 ++-
 net/ipv4/ipip.c                       | 19 +++++++++++--------
 net/ipv4/ipmr.c                       |  5 +++--
 net/ipv6/ip6_tunnel.c                 |  5 +++--
 net/ipv6/sit.c                        |  6 ++++--
 net/l2tp/l2tp_ip.c                    |  3 ++-
 net/rxrpc/ar-peer.c                   |  3 ++-
 14 files changed, 48 insertions(+), 31 deletions(-)

(limited to 'net/ipv6')

diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index 3216bcad7e820..2391841389944 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -338,8 +338,9 @@ static struct rtable *find_route(struct t3cdev *dev, __be32 local_ip,
 				 __be16 peer_port, u8 tos)
 {
 	struct rtable *rt;
+	struct flowi4 fl4;
 
-	rt = ip_route_output_ports(&init_net, NULL, peer_ip, local_ip,
+	rt = ip_route_output_ports(&init_net, &fl4, NULL, peer_ip, local_ip,
 				   peer_port, local_port, IPPROTO_TCP,
 				   tos, 0);
 	if (IS_ERR(rt))
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 9d8dcfab2b38a..6aa53cd694781 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -315,8 +315,9 @@ static struct rtable *find_route(struct c4iw_dev *dev, __be32 local_ip,
 				 __be16 peer_port, u8 tos)
 {
 	struct rtable *rt;
+	struct flowi4 fl4;
 
-	rt = ip_route_output_ports(&init_net, NULL, peer_ip, local_ip,
+	rt = ip_route_output_ports(&init_net, &fl4, NULL, peer_ip, local_ip,
 				   peer_port, local_port, IPPROTO_TCP,
 				   tos, 0);
 	if (IS_ERR(rt))
diff --git a/drivers/net/pptp.c b/drivers/net/pptp.c
index 51dfcf8023c7c..e771e8d27eb72 100644
--- a/drivers/net/pptp.c
+++ b/drivers/net/pptp.c
@@ -175,6 +175,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	struct pptp_opt *opt = &po->proto.pptp;
 	struct pptp_gre_header *hdr;
 	unsigned int header_len = sizeof(*hdr);
+	struct flowi4 fl4;
 	int islcp;
 	int len;
 	unsigned char *data;
@@ -189,7 +190,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	if (sk_pppox(po)->sk_state & PPPOX_DEAD)
 		goto tx_error;
 
-	rt = ip_route_output_ports(&init_net, NULL,
+	rt = ip_route_output_ports(&init_net, &fl4, NULL,
 				   opt->dst_addr.sin_addr.s_addr,
 				   opt->src_addr.sin_addr.s_addr,
 				   0, 0, IPPROTO_GRE,
@@ -434,6 +435,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	struct pppox_sock *po = pppox_sk(sk);
 	struct pptp_opt *opt = &po->proto.pptp;
 	struct rtable *rt;
+	struct flowi4 fl4;
 	int error = 0;
 
 	if (sp->sa_protocol != PX_PROTO_PPTP)
@@ -463,7 +465,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	po->chan.private = sk;
 	po->chan.ops = &pptp_chan_ops;
 
-	rt = ip_route_output_ports(&init_net, sk,
+	rt = ip_route_output_ports(&init_net, &fl4, sk,
 				   opt->dst_addr.sin_addr.s_addr,
 				   opt->src_addr.sin_addr.s_addr,
 				   0, 0,
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index de764ea7419d4..0c33d250c7d70 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -454,8 +454,9 @@ static struct rtable *find_route_ipv4(__be32 saddr, __be32 daddr,
 				      __be16 sport, __be16 dport, u8 tos)
 {
 	struct rtable *rt;
+	struct flowi4 fl4;
 
-	rt = ip_route_output_ports(&init_net, NULL, daddr, saddr,
+	rt = ip_route_output_ports(&init_net, &fl4, NULL, daddr, saddr,
 				   dport, sport, IPPROTO_TCP, tos, 0);
 	if (IS_ERR(rt))
 		return NULL;
diff --git a/include/net/route.h b/include/net/route.h
index f07609e831417..8c02c871a8cea 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -137,20 +137,19 @@ static inline struct rtable *ip_route_output(struct net *net, __be32 daddr,
 	return ip_route_output_key(net, &fl4);
 }
 
-static inline struct rtable *ip_route_output_ports(struct net *net, struct sock *sk,
+static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi4 *fl4,
+						   struct sock *sk,
 						   __be32 daddr, __be32 saddr,
 						   __be16 dport, __be16 sport,
 						   __u8 proto, __u8 tos, int oif)
 {
-	struct flowi4 fl4;
-
-	flowi4_init_output(&fl4, oif, sk ? sk->sk_mark : 0, tos,
+	flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos,
 			   RT_SCOPE_UNIVERSE, proto,
 			   sk ? inet_sk_flowi_flags(sk) : 0,
 			   daddr, saddr, dport, sport);
 	if (sk)
-		security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
-	return ip_route_output_flow(net, &fl4, sk);
+		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
+	return ip_route_output_flow(net, fl4, sk);
 }
 
 static inline struct rtable *ip_route_output_gre(struct net *net,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4e734992e266a..7b91fa8bf83cb 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1152,6 +1152,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 	struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0);
 	__be32 daddr;
 	struct ip_options_rcu *inet_opt;
+	struct flowi4 fl4;
 	int err;
 
 	/* Route is OK, nothing to do. */
@@ -1165,7 +1166,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 	if (inet_opt && inet_opt->opt.srr)
 		daddr = inet_opt->opt.faddr;
 	rcu_read_unlock();
-	rt = ip_route_output_ports(sock_net(sk), sk, daddr, inet->inet_saddr,
+	rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, inet->inet_saddr,
 				   inet->inet_dport, inet->inet_sport,
 				   sk->sk_protocol, RT_CONN_FLAGS(sk),
 				   sk->sk_bound_dev_if);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 8ae0a5702f563..7c2ef59e3f7db 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -309,6 +309,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	struct iphdr *pip;
 	struct igmpv3_report *pig;
 	struct net *net = dev_net(dev);
+	struct flowi4 fl4;
 
 	while (1) {
 		skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev),
@@ -321,7 +322,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	}
 	igmp_skb_size(skb) = size;
 
-	rt = ip_route_output_ports(net, NULL, IGMPV3_ALL_MCR, 0,
+	rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0,
 				   0, 0,
 				   IPPROTO_IGMP, 0, dev->ifindex);
 	if (IS_ERR(rt)) {
@@ -650,6 +651,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	struct net_device *dev = in_dev->dev;
 	struct net *net = dev_net(dev);
 	__be32	group = pmc ? pmc->multiaddr : 0;
+	struct flowi4 fl4;
 	__be32	dst;
 
 	if (type == IGMPV3_HOST_MEMBERSHIP_REPORT)
@@ -659,7 +661,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	else
 		dst = group;
 
-	rt = ip_route_output_ports(net, NULL, dst, 0,
+	rt = ip_route_output_ports(net, &fl4, NULL, dst, 0,
 				   0, 0,
 				   IPPROTO_IGMP, 0, dev->ifindex);
 	if (IS_ERR(rt))
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 362e66f7d2fbb..3aa4c31e5448e 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -333,6 +333,7 @@ int ip_queue_xmit(struct sk_buff *skb)
 	/* Make sure we can route this packet. */
 	rt = (struct rtable *)__sk_dst_check(sk, 0);
 	if (rt == NULL) {
+		struct flowi4 fl4;
 		__be32 daddr;
 
 		/* Use correct destination address if we have options. */
@@ -344,7 +345,7 @@ int ip_queue_xmit(struct sk_buff *skb)
 		 * keep trying until route appears or the connection times
 		 * itself out.
 		 */
-		rt = ip_route_output_ports(sock_net(sk), sk,
+		rt = ip_route_output_ports(sock_net(sk), &fl4, sk,
 					   daddr, inet->inet_saddr,
 					   inet->inet_dport,
 					   inet->inet_sport,
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index ef16377ec73f2..88d96bde95009 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -442,6 +442,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct iphdr  *iph;			/* Our new IP header */
 	unsigned int max_headroom;		/* The extra header space needed */
 	__be32 dst = tiph->daddr;
+	struct flowi4 fl4;
 	int    mtu;
 
 	if (skb->protocol != htons(ETH_P_IP))
@@ -460,7 +461,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 			goto tx_error_icmp;
 	}
 
-	rt = ip_route_output_ports(dev_net(dev), NULL,
+	rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
 				   dst, tiph->saddr,
 				   0, 0,
 				   IPPROTO_IPIP, RT_TOS(tos),
@@ -578,13 +579,15 @@ static void ipip_tunnel_bind_dev(struct net_device *dev)
 	iph = &tunnel->parms.iph;
 
 	if (iph->daddr) {
-		struct rtable *rt = ip_route_output_ports(dev_net(dev), NULL,
-							  iph->daddr, iph->saddr,
-							  0, 0,
-							  IPPROTO_IPIP,
-							  RT_TOS(iph->tos),
-							  tunnel->parms.link);
-
+		struct rtable *rt;
+		struct flowi4 fl4;
+
+		rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
+					   iph->daddr, iph->saddr,
+					   0, 0,
+					   IPPROTO_IPIP,
+					   RT_TOS(iph->tos),
+					   tunnel->parms.link);
 		if (!IS_ERR(rt)) {
 			tdev = rt->dst.dev;
 			ip_rt_put(rt);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 3ad38a4495889..86033b7a05ba4 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1595,6 +1595,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 	struct vif_device *vif = &mrt->vif_table[vifi];
 	struct net_device *dev;
 	struct rtable *rt;
+	struct flowi4 fl4;
 	int    encap = 0;
 
 	if (vif->dev == NULL)
@@ -1612,7 +1613,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 #endif
 
 	if (vif->flags & VIFF_TUNNEL) {
-		rt = ip_route_output_ports(net, NULL,
+		rt = ip_route_output_ports(net, &fl4, NULL,
 					   vif->remote, vif->local,
 					   0, 0,
 					   IPPROTO_IPIP,
@@ -1621,7 +1622,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 			goto out_free;
 		encap = sizeof(struct iphdr);
 	} else {
-		rt = ip_route_output_ports(net, NULL, iph->daddr, 0,
+		rt = ip_route_output_ports(net, &fl4, NULL, iph->daddr, 0,
 					   0, 0,
 					   IPPROTO_IPIP,
 					   RT_TOS(iph->tos), vif->link);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 9dd0e964b8bda..3dff27cba95c2 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -537,6 +537,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	struct sk_buff *skb2;
 	const struct iphdr *eiph;
 	struct rtable *rt;
+	struct flowi4 fl4;
 
 	err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code,
 			  &rel_msg, &rel_info, offset);
@@ -577,7 +578,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	eiph = ip_hdr(skb2);
 
 	/* Try to guess incoming interface */
-	rt = ip_route_output_ports(dev_net(skb->dev), NULL,
+	rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL,
 				   eiph->saddr, 0,
 				   0, 0,
 				   IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
@@ -590,7 +591,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (rt->rt_flags & RTCF_LOCAL) {
 		ip_rt_put(rt);
 		rt = NULL;
-		rt = ip_route_output_ports(dev_net(skb->dev), NULL,
+		rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL,
 					   eiph->daddr, eiph->saddr,
 					   0, 0,
 					   IPPROTO_IPIP,
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 34d896426701a..a24fb14d91f30 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -674,6 +674,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	struct iphdr  *iph;			/* Our new IP header */
 	unsigned int max_headroom;		/* The extra header space needed */
 	__be32 dst = tiph->daddr;
+	struct flowi4 fl4;
 	int    mtu;
 	const struct in6_addr *addr6;
 	int addr_type;
@@ -733,7 +734,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		dst = addr6->s6_addr32[3];
 	}
 
-	rt = ip_route_output_ports(dev_net(dev), NULL,
+	rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
 				   dst, tiph->saddr,
 				   0, 0,
 				   IPPROTO_IPV6, RT_TOS(tos),
@@ -851,12 +852,13 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 	struct net_device *tdev = NULL;
 	struct ip_tunnel *tunnel;
 	const struct iphdr *iph;
+	struct flowi4 fl4;
 
 	tunnel = netdev_priv(dev);
 	iph = &tunnel->parms.iph;
 
 	if (iph->daddr) {
-		struct rtable *rt = ip_route_output_ports(dev_net(dev), NULL,
+		struct rtable *rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
 							  iph->daddr, iph->saddr,
 							  0, 0,
 							  IPPROTO_IPV6,
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index a4d2dfa1fdbfc..81899600abe24 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -471,6 +471,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 
 	if (rt == NULL) {
 		struct ip_options_rcu *inet_opt;
+		struct flowi4 fl4;
 
 		rcu_read_lock();
 		inet_opt = rcu_dereference(inet->inet_opt);
@@ -485,7 +486,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		 * keep trying until route appears or the connection times
 		 * itself out.
 		 */
-		rt = ip_route_output_ports(sock_net(sk), sk,
+		rt = ip_route_output_ports(sock_net(sk), &fl4, sk,
 					   daddr, inet->inet_saddr,
 					   inet->inet_dport, inet->inet_sport,
 					   sk->sk_protocol, RT_CONN_FLAGS(sk),
diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c
index 55b93dc60d0cb..b6ff06351d677 100644
--- a/net/rxrpc/ar-peer.c
+++ b/net/rxrpc/ar-peer.c
@@ -36,10 +36,11 @@ static void rxrpc_destroy_peer(struct work_struct *work);
 static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
 {
 	struct rtable *rt;
+	struct flowi4 fl4;
 
 	peer->if_mtu = 1500;
 
-	rt = ip_route_output_ports(&init_net, NULL,
+	rt = ip_route_output_ports(&init_net, &fl4, NULL,
 				   peer->srx.transport.sin.sin_addr.s_addr, 0,
 				   htons(7000), htons(7001),
 				   IPPROTO_UDP, 0, 0);
-- 
cgit v1.2.3


From 301102cc832f9f3e24c5748705f152eaa7c307f6 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 4 May 2011 12:46:24 -0700
Subject: ipv6: Use flowi4->{daddr,saddr} in ipip6_tunnel_xmit().

Instead of rt->rt_{dst,src}

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/ipv6')

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a24fb14d91f30..c53abcf50d298 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -828,8 +828,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	iph->frag_off		=	df;
 	iph->protocol		=	IPPROTO_IPV6;
 	iph->tos		=	INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
-	iph->daddr		=	rt->rt_dst;
-	iph->saddr		=	rt->rt_src;
+	iph->daddr		=	fl4.daddr;
+	iph->saddr		=	fl4.saddr;
 
 	if ((iph->ttl = tiph->ttl) == 0)
 		iph->ttl	=	iph6->hop_limit;
-- 
cgit v1.2.3


From 1c5cae815d19ffe02bdfda1260949ef2b1806171 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jpirko@redhat.com>
Date: Sat, 30 Apr 2011 01:21:32 +0000
Subject: net: call dev_alloc_name from register_netdevice

Force dev_alloc_name() to be called from register_netdevice() by
dev_get_valid_name(). That allows to remove multiple explicit
dev_alloc_name() calls.

The possibility to call dev_alloc_name in advance remains.

This also fixes veth creation regresion caused by
84c49d8c3e4abefb0a41a77b25aa37ebe8d6b743

Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ieee802154/fakehard.c             | 10 ----------
 drivers/net/bonding/bond_main.c           | 21 +++------------------
 drivers/net/dummy.c                       |  4 ----
 drivers/net/hamradio/bpqether.c           |  4 ----
 drivers/net/ifb.c                         |  4 ----
 drivers/net/tun.c                         |  6 ------
 drivers/net/wan/dlci.c                    |  4 ----
 drivers/net/wan/hdlc_fr.c                 |  9 +--------
 drivers/net/wan/lapbether.c               |  4 ----
 drivers/net/wireless/hostap/hostap_main.c |  7 +------
 drivers/net/wireless/mac80211_hwsim.c     | 11 +----------
 drivers/net/wireless/mwifiex/main.c       |  4 ----
 drivers/s390/net/netiucv.c                |  2 --
 net/core/dev.c                            | 24 ++++++------------------
 net/core/rtnetlink.c                      |  8 --------
 net/ipv4/ip_gre.c                         |  5 -----
 net/ipv4/ipip.c                           |  5 -----
 net/ipv6/ip6_tunnel.c                     |  5 -----
 net/ipv6/sit.c                            |  5 -----
 net/mac80211/iface.c                      |  4 ----
 20 files changed, 12 insertions(+), 134 deletions(-)

(limited to 'net/ipv6')

diff --git a/drivers/ieee802154/fakehard.c b/drivers/ieee802154/fakehard.c
index d9d0e13efe47b..a5a49a1baae72 100644
--- a/drivers/ieee802154/fakehard.c
+++ b/drivers/ieee802154/fakehard.c
@@ -393,16 +393,6 @@ static int __devinit ieee802154fake_probe(struct platform_device *pdev)
 	priv = netdev_priv(dev);
 	priv->phy = phy;
 
-	/*
-	 * If the name is a format string the caller wants us to do a
-	 * name allocation.
-	 */
-	if (strchr(dev->name, '%')) {
-		err = dev_alloc_name(dev, dev->name);
-		if (err < 0)
-			goto out;
-	}
-
 	wpan_phy_set_dev(phy, &pdev->dev);
 	SET_NETDEV_DEV(dev, &phy->dev);
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 22bd03bd1d359..9a5feaf4bab9a 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4917,8 +4917,9 @@ int bond_create(struct net *net, const char *name)
 
 	rtnl_lock();
 
-	bond_dev = alloc_netdev_mq(sizeof(struct bonding), name ? name : "",
-				bond_setup, tx_queues);
+	bond_dev = alloc_netdev_mq(sizeof(struct bonding),
+				   name ? name : "bond%d",
+				   bond_setup, tx_queues);
 	if (!bond_dev) {
 		pr_err("%s: eek! can't alloc netdev!\n", name);
 		rtnl_unlock();
@@ -4928,26 +4929,10 @@ int bond_create(struct net *net, const char *name)
 	dev_net_set(bond_dev, net);
 	bond_dev->rtnl_link_ops = &bond_link_ops;
 
-	if (!name) {
-		res = dev_alloc_name(bond_dev, "bond%d");
-		if (res < 0)
-			goto out;
-	} else {
-		/*
-		 * If we're given a name to register
-		 * we need to ensure that its not already
-		 * registered
-		 */
-		res = -EEXIST;
-		if (__dev_get_by_name(net, name) != NULL)
-			goto out;
-	}
-
 	res = register_netdevice(bond_dev);
 
 	netif_carrier_off(bond_dev);
 
-out:
 	rtnl_unlock();
 	if (res < 0)
 		bond_destructor(bond_dev);
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index ff2d29b178587..39cf9b9bd673c 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -168,10 +168,6 @@ static int __init dummy_init_one(void)
 	if (!dev_dummy)
 		return -ENOMEM;
 
-	err = dev_alloc_name(dev_dummy, dev_dummy->name);
-	if (err < 0)
-		goto err;
-
 	dev_dummy->rtnl_link_ops = &dummy_link_ops;
 	err = register_netdevice(dev_dummy);
 	if (err < 0)
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index 8931168d3e743..18d8affecd1bf 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -516,10 +516,6 @@ static int bpq_new_device(struct net_device *edev)
 	memcpy(bpq->dest_addr, bcast_addr, sizeof(bpq_eth_addr));
 	memcpy(bpq->acpt_addr, bcast_addr, sizeof(bpq_eth_addr));
 
-	err = dev_alloc_name(ndev, ndev->name);
-	if (err < 0) 
-		goto error;
-
 	err = register_netdevice(ndev);
 	if (err)
 		goto error;
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index e07d487f015a7..4fecaed67fc4c 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -233,10 +233,6 @@ static int __init ifb_init_one(int index)
 	if (!dev_ifb)
 		return -ENOMEM;
 
-	err = dev_alloc_name(dev_ifb, dev_ifb->name);
-	if (err < 0)
-		goto err;
-
 	dev_ifb->rtnl_link_ops = &ifb_link_ops;
 	err = register_netdevice(dev_ifb);
 	if (err < 0)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 0636f70403259..74e94054ab1a2 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1099,12 +1099,6 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		tun_net_init(dev);
 
-		if (strchr(dev->name, '%')) {
-			err = dev_alloc_name(dev, dev->name);
-			if (err < 0)
-				goto err_free_sk;
-		}
-
 		dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST |
 			TUN_USER_FEATURES;
 		dev->features = dev->hw_features;
diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
index 1481a446fefbf..21b104db5a908 100644
--- a/drivers/net/wan/dlci.c
+++ b/drivers/net/wan/dlci.c
@@ -341,10 +341,6 @@ static int dlci_add(struct dlci_add *dlci)
 		}
 	}
 
-	err = dev_alloc_name(master, master->name);
-	if (err < 0)
-		goto err2;
-
 	*(short *)(master->dev_addr) = dlci->dlci;
 
 	dlp = netdev_priv(master);
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index 0edb535bb2b5a..fc433f28c047c 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -1070,7 +1070,7 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
 	hdlc_device *hdlc = dev_to_hdlc(frad);
 	pvc_device *pvc;
 	struct net_device *dev;
-	int result, used;
+	int used;
 
 	if ((pvc = add_pvc(frad, dlci)) == NULL) {
 		printk(KERN_WARNING "%s: Memory squeeze on fr_add_pvc()\n",
@@ -1106,13 +1106,6 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
 	dev->tx_queue_len = 0;
 	dev->ml_priv = pvc;
 
-	result = dev_alloc_name(dev, dev->name);
-	if (result < 0) {
-		free_netdev(dev);
-		delete_unused_pvcs(hdlc);
-		return result;
-	}
-
 	if (register_netdevice(dev) != 0) {
 		free_netdev(dev);
 		delete_unused_pvcs(hdlc);
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 7f5bb913c8b92..eec463f99c096 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -338,10 +338,6 @@ static int lapbeth_new_device(struct net_device *dev)
 	dev_hold(dev);
 	lapbeth->ethdev = dev;
 
-	rc = dev_alloc_name(ndev, ndev->name);
-	if (rc < 0) 
-		goto fail;
-
 	rc = -EIO;
 	if (register_netdevice(ndev))
 		goto fail;
diff --git a/drivers/net/wireless/hostap/hostap_main.c b/drivers/net/wireless/hostap/hostap_main.c
index 1d9aed6457234..d5084829c9e54 100644
--- a/drivers/net/wireless/hostap/hostap_main.c
+++ b/drivers/net/wireless/hostap/hostap_main.c
@@ -79,13 +79,8 @@ struct net_device * hostap_add_interface(struct local_info *local,
 	if (!rtnl_locked)
 		rtnl_lock();
 
-	ret = 0;
-	if (strchr(dev->name, '%'))
-		ret = dev_alloc_name(dev, dev->name);
-
 	SET_NETDEV_DEV(dev, mdev->dev.parent);
-	if (ret >= 0)
-		ret = register_netdevice(dev);
+	ret = register_netdevice(dev);
 
 	if (!rtnl_locked)
 		rtnl_unlock();
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index f4f4257a9d67e..9d4a40ee16c4f 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1515,19 +1515,10 @@ static int __init init_mac80211_hwsim(void)
 	if (hwsim_mon == NULL)
 		goto failed;
 
-	rtnl_lock();
-
-	err = dev_alloc_name(hwsim_mon, hwsim_mon->name);
+	err = register_netdev(hwsim_mon);
 	if (err < 0)
 		goto failed_mon;
 
-
-	err = register_netdevice(hwsim_mon);
-	if (err < 0)
-		goto failed_mon;
-
-	rtnl_unlock();
-
 	return 0;
 
 failed_mon:
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index c5971880e7b37..d16cea770fa36 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -706,10 +706,6 @@ static struct mwifiex_private *mwifiex_add_interface(
 		dev_err(adapter->dev, "no memory available for netdevice\n");
 		goto error;
 	}
-	if (dev_alloc_name(dev, dev->name)) {
-		dev_err(adapter->dev, "unable to alloc name for netdevice\n");
-		goto error;
-	}
 
 	if (mwifiex_register_cfg80211(dev, adapter->priv[bss_index]->curr_addr,
 				      adapter->priv[bss_index]) != 0) {
diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c
index b6a6356d09b3a..3251333a23df1 100644
--- a/drivers/s390/net/netiucv.c
+++ b/drivers/s390/net/netiucv.c
@@ -1994,8 +1994,6 @@ static struct net_device *netiucv_init_netdevice(char *username)
 			   netiucv_setup_netdevice);
 	if (!dev)
 		return NULL;
-	if (dev_alloc_name(dev, dev->name) < 0)
-		goto out_netdev;
 
 	privptr = netdev_priv(dev);
 	privptr->fsm = init_fsm("netiucvdev", dev_state_names,
diff --git a/net/core/dev.c b/net/core/dev.c
index e95dc30110ebe..3b79bad3d02d3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -948,7 +948,7 @@ int dev_alloc_name(struct net_device *dev, const char *name)
 }
 EXPORT_SYMBOL(dev_alloc_name);
 
-static int dev_get_valid_name(struct net_device *dev, const char *name, bool fmt)
+static int dev_get_valid_name(struct net_device *dev, const char *name)
 {
 	struct net *net;
 
@@ -958,7 +958,7 @@ static int dev_get_valid_name(struct net_device *dev, const char *name, bool fmt
 	if (!dev_valid_name(name))
 		return -EINVAL;
 
-	if (fmt && strchr(name, '%'))
+	if (strchr(name, '%'))
 		return dev_alloc_name(dev, name);
 	else if (__dev_get_by_name(net, name))
 		return -EEXIST;
@@ -995,7 +995,7 @@ int dev_change_name(struct net_device *dev, const char *newname)
 
 	memcpy(oldname, dev->name, IFNAMSIZ);
 
-	err = dev_get_valid_name(dev, newname, 1);
+	err = dev_get_valid_name(dev, newname);
 	if (err < 0)
 		return err;
 
@@ -5420,8 +5420,8 @@ int register_netdevice(struct net_device *dev)
 		}
 	}
 
-	ret = dev_get_valid_name(dev, dev->name, 0);
-	if (ret)
+	ret = dev_get_valid_name(dev, dev->name);
+	if (ret < 0)
 		goto err_uninit;
 
 	dev->ifindex = dev_new_index(net);
@@ -5562,19 +5562,7 @@ int register_netdev(struct net_device *dev)
 	int err;
 
 	rtnl_lock();
-
-	/*
-	 * If the name is a format string the caller wants us to do a
-	 * name allocation.
-	 */
-	if (strchr(dev->name, '%')) {
-		err = dev_alloc_name(dev, dev->name);
-		if (err < 0)
-			goto out;
-	}
-
 	err = register_netdevice(dev);
-out:
 	rtnl_unlock();
 	return err;
 }
@@ -6056,7 +6044,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 		/* We get here if we can't use the current device name */
 		if (!pat)
 			goto out;
-		if (dev_get_valid_name(dev, pat, 1))
+		if (dev_get_valid_name(dev, pat) < 0)
 			goto out;
 	}
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2963312571954..5a160f4a1ba0d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1572,12 +1572,6 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net,
 	dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
 	dev->real_num_tx_queues = real_num_queues;
 
-	if (strchr(dev->name, '%')) {
-		err = dev_alloc_name(dev, dev->name);
-		if (err < 0)
-			goto err_free;
-	}
-
 	if (tb[IFLA_MTU])
 		dev->mtu = nla_get_u32(tb[IFLA_MTU]);
 	if (tb[IFLA_ADDRESS])
@@ -1597,8 +1591,6 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net,
 
 	return dev;
 
-err_free:
-	free_netdev(dev);
 err:
 	return ERR_PTR(err);
 }
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 10e9b5aea0703..8871067560dba 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -413,11 +413,6 @@ static struct ip_tunnel *ipgre_tunnel_locate(struct net *net,
 
 	dev_net_set(dev, net);
 
-	if (strchr(name, '%')) {
-		if (dev_alloc_name(dev, name) < 0)
-			goto failed_free;
-	}
-
 	nt = netdev_priv(dev);
 	nt->parms = *parms;
 	dev->rtnl_link_ops = &ipgre_link_ops;
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index bfa0b9895040c..378b20b7ca6e7 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -276,11 +276,6 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net,
 
 	dev_net_set(dev, net);
 
-	if (strchr(name, '%')) {
-		if (dev_alloc_name(dev, name) < 0)
-			goto failed_free;
-	}
-
 	nt = netdev_priv(dev);
 	nt->parms = *parms;
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 3dff27cba95c2..36c2842a86b25 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -280,11 +280,6 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p)
 
 	dev_net_set(dev, net);
 
-	if (strchr(name, '%')) {
-		if (dev_alloc_name(dev, name) < 0)
-			goto failed_free;
-	}
-
 	t = netdev_priv(dev);
 	t->parms = *p;
 	err = ip6_tnl_dev_init(dev);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index c53abcf50d298..a6a32b39b6074 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -250,11 +250,6 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
 
 	dev_net_set(dev, net);
 
-	if (strchr(name, '%')) {
-		if (dev_alloc_name(dev, name) < 0)
-			goto failed_free;
-	}
-
 	nt = netdev_priv(dev);
 
 	nt->parms = *parms;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 4054399be907f..80c29d626aa4a 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1144,10 +1144,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 				+ IEEE80211_ENCRYPT_HEADROOM;
 	ndev->needed_tailroom = IEEE80211_ENCRYPT_TAILROOM;
 
-	ret = dev_alloc_name(ndev, ndev->name);
-	if (ret < 0)
-		goto fail;
-
 	ieee80211_assign_perm_addr(local, ndev, type);
 	memcpy(ndev->dev_addr, ndev->perm_addr, ETH_ALEN);
 	SET_NETDEV_DEV(ndev, wiphy_dev(local->hw.wiphy));
-- 
cgit v1.2.3


From bdc712b4c2baf9515887de3a52e7ecd89fafc0c7 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 6 May 2011 15:02:07 -0700
Subject: inet: Decrease overhead of on-stack inet_cork.

When we fast path datagram sends to avoid locking by putting
the inet_cork on the stack we use up lots of space that isn't
necessary.

This is because inet_cork contains a "struct flowi" which isn't
used in these code paths.

Split inet_cork to two parts, "inet_cork" and "inet_cork_full".
Only the latter of which has the "struct flowi" and is what is
stored in inet_sock.

Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
---
 include/net/inet_sock.h | 12 ++++++++----
 include/net/ip.h        |  2 +-
 net/ipv4/ip_output.c    | 22 ++++++++++++----------
 net/ipv6/ip6_output.c   | 34 ++++++++++++++++++----------------
 net/ipv6/raw.c          |  4 ++--
 5 files changed, 41 insertions(+), 33 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index ed2ba6eca7247..caaff5f5f39f5 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -96,17 +96,21 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
 
 struct inet_cork {
 	unsigned int		flags;
-	unsigned int		fragsize;
+	__be32			addr;
 	struct ip_options	*opt;
+	unsigned int		fragsize;
 	struct dst_entry	*dst;
 	int			length; /* Total length of all frames */
-	__be32			addr;
-	struct flowi		fl;
 	struct page		*page;
 	u32			off;
 	u8			tx_flags;
 };
 
+struct inet_cork_full {
+	struct inet_cork	base;
+	struct flowi		fl;
+};
+
 struct ip_mc_socklist;
 struct ipv6_pinfo;
 struct rtable;
@@ -164,7 +168,7 @@ struct inet_sock {
 	int			mc_index;
 	__be32			mc_addr;
 	struct ip_mc_socklist __rcu	*mc_list;
-	struct inet_cork	cork;
+	struct inet_cork_full	cork;
 };
 
 #define IPCORK_OPT	1	/* ip-options has been held in ipcork.opt */
diff --git a/include/net/ip.h b/include/net/ip.h
index 3a59bf99aa3a1..095e392d5f16f 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -132,7 +132,7 @@ extern struct sk_buff  *ip_make_skb(struct sock *sk,
 
 static inline struct sk_buff *ip_finish_skb(struct sock *sk)
 {
-	return __ip_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork);
+	return __ip_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
 }
 
 /* datagram.c */
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index db38c1822de8e..eb0647a2f0738 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1096,14 +1096,14 @@ int ip_append_data(struct sock *sk,
 		return 0;
 
 	if (skb_queue_empty(&sk->sk_write_queue)) {
-		err = ip_setup_cork(sk, &inet->cork, ipc, rtp);
+		err = ip_setup_cork(sk, &inet->cork.base, ipc, rtp);
 		if (err)
 			return err;
 	} else {
 		transhdrlen = 0;
 	}
 
-	return __ip_append_data(sk, &sk->sk_write_queue, &inet->cork, getfrag,
+	return __ip_append_data(sk, &sk->sk_write_queue, &inet->cork.base, getfrag,
 				from, length, transhdrlen, flags);
 }
 
@@ -1114,6 +1114,7 @@ ssize_t	ip_append_page(struct sock *sk, struct page *page,
 	struct sk_buff *skb;
 	struct rtable *rt;
 	struct ip_options *opt = NULL;
+	struct inet_cork *cork;
 	int hh_len;
 	int mtu;
 	int len;
@@ -1129,20 +1130,21 @@ ssize_t	ip_append_page(struct sock *sk, struct page *page,
 	if (skb_queue_empty(&sk->sk_write_queue))
 		return -EINVAL;
 
-	rt = (struct rtable *)inet->cork.dst;
-	if (inet->cork.flags & IPCORK_OPT)
-		opt = inet->cork.opt;
+	cork = &inet->cork.base;
+	rt = (struct rtable *)cork->dst;
+	if (cork->flags & IPCORK_OPT)
+		opt = cork->opt;
 
 	if (!(rt->dst.dev->features&NETIF_F_SG))
 		return -EOPNOTSUPP;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
-	mtu = inet->cork.fragsize;
+	mtu = cork->fragsize;
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
 
-	if (inet->cork.length + size > 0xFFFF - fragheaderlen) {
+	if (cork->length + size > 0xFFFF - fragheaderlen) {
 		ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, mtu);
 		return -EMSGSIZE;
 	}
@@ -1150,7 +1152,7 @@ ssize_t	ip_append_page(struct sock *sk, struct page *page,
 	if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
 		return -EINVAL;
 
-	inet->cork.length += size;
+	cork->length += size;
 	if ((size + skb->len > mtu) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO)) {
@@ -1245,7 +1247,7 @@ ssize_t	ip_append_page(struct sock *sk, struct page *page,
 	return 0;
 
 error:
-	inet->cork.length -= size;
+	cork->length -= size;
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
 	return err;
 }
@@ -1396,7 +1398,7 @@ static void __ip_flush_pending_frames(struct sock *sk,
 
 void ip_flush_pending_frames(struct sock *sk)
 {
-	__ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork);
+	__ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
 }
 
 struct sk_buff *ip_make_skb(struct sock *sk,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 4cfbb24b9e040..9d4b165837d6a 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1150,6 +1150,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct inet_cork *cork;
 	struct sk_buff *skb;
 	unsigned int maxfraglen, fragheaderlen;
 	int exthdrlen;
@@ -1163,6 +1164,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 
 	if (flags&MSG_PROBE)
 		return 0;
+	cork = &inet->cork.base;
 	if (skb_queue_empty(&sk->sk_write_queue)) {
 		/*
 		 * setup for corking
@@ -1202,7 +1204,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 			/* need source address above miyazawa*/
 		}
 		dst_hold(&rt->dst);
-		inet->cork.dst = &rt->dst;
+		cork->dst = &rt->dst;
 		inet->cork.fl.u.ip6 = *fl6;
 		np->cork.hop_limit = hlimit;
 		np->cork.tclass = tclass;
@@ -1212,10 +1214,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 			if (np->frag_size)
 				mtu = np->frag_size;
 		}
-		inet->cork.fragsize = mtu;
+		cork->fragsize = mtu;
 		if (dst_allfrag(rt->dst.path))
-			inet->cork.flags |= IPCORK_ALLFRAG;
-		inet->cork.length = 0;
+			cork->flags |= IPCORK_ALLFRAG;
+		cork->length = 0;
 		sk->sk_sndmsg_page = NULL;
 		sk->sk_sndmsg_off = 0;
 		exthdrlen = rt->dst.header_len + (opt ? opt->opt_flen : 0) -
@@ -1223,12 +1225,12 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		length += exthdrlen;
 		transhdrlen += exthdrlen;
 	} else {
-		rt = (struct rt6_info *)inet->cork.dst;
+		rt = (struct rt6_info *)cork->dst;
 		fl6 = &inet->cork.fl.u.ip6;
 		opt = np->cork.opt;
 		transhdrlen = 0;
 		exthdrlen = 0;
-		mtu = inet->cork.fragsize;
+		mtu = cork->fragsize;
 	}
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
@@ -1238,7 +1240,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
 
 	if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
-		if (inet->cork.length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
+		if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
 			ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen);
 			return -EMSGSIZE;
 		}
@@ -1267,7 +1269,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	 * --yoshfuji
 	 */
 
-	inet->cork.length += length;
+	cork->length += length;
 	if (length > mtu) {
 		int proto = sk->sk_protocol;
 		if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
@@ -1292,7 +1294,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 
 	while (length > 0) {
 		/* Check if the remaining data fits into current packet. */
-		copy = (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
+		copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
 		if (copy < length)
 			copy = maxfraglen - skb->len;
 
@@ -1317,7 +1319,7 @@ alloc_new_skb:
 			 * we know we need more fragment(s).
 			 */
 			datalen = length + fraggap;
-			if (datalen > (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
+			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
 				datalen = maxfraglen - fragheaderlen;
 
 			fraglen = datalen + fragheaderlen;
@@ -1481,7 +1483,7 @@ alloc_new_skb:
 	}
 	return 0;
 error:
-	inet->cork.length -= length;
+	cork->length -= length;
 	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	return err;
 }
@@ -1497,10 +1499,10 @@ static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
 		np->cork.opt = NULL;
 	}
 
-	if (inet->cork.dst) {
-		dst_release(inet->cork.dst);
-		inet->cork.dst = NULL;
-		inet->cork.flags &= ~IPCORK_ALLFRAG;
+	if (inet->cork.base.dst) {
+		dst_release(inet->cork.base.dst);
+		inet->cork.base.dst = NULL;
+		inet->cork.base.flags &= ~IPCORK_ALLFRAG;
 	}
 	memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
 }
@@ -1515,7 +1517,7 @@ int ip6_push_pending_frames(struct sock *sk)
 	struct net *net = sock_net(sk);
 	struct ipv6hdr *hdr;
 	struct ipv6_txoptions *opt = np->cork.opt;
-	struct rt6_info *rt = (struct rt6_info *)inet->cork.dst;
+	struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst;
 	struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
 	unsigned char proto = fl6->flowi6_proto;
 	int err = 0;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index e5e5425fe7d0b..ae64984f81aa8 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -542,8 +542,8 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 		goto out;
 
 	offset = rp->offset;
-	total_len = inet_sk(sk)->cork.length - (skb_network_header(skb) -
-						skb->data);
+	total_len = inet_sk(sk)->cork.base.length - (skb_network_header(skb) -
+						     skb->data);
 	if (offset >= total_len - 1) {
 		err = -EINVAL;
 		ip6_flush_pending_frames(sk);
-- 
cgit v1.2.3


From d9d8da805dcb503ef8ee49918a94d49085060f23 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 6 May 2011 22:23:20 -0700
Subject: inet: Pass flowi to ->queue_xmit().

This allows us to acquire the exact route keying information from the
protocol, however that might be managed.

It handles all of the possibilities, from the simplest case of storing
the key in inet->cork.fl to the more complex setup SCTP has where
individual transports determine the flow.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet6_connection_sock.h |  2 +-
 include/net/inet_connection_sock.h  |  2 +-
 include/net/ip.h                    |  2 +-
 net/dccp/output.c                   |  4 ++--
 net/ipv4/ip_output.c                |  4 ++--
 net/ipv4/tcp_output.c               |  2 +-
 net/ipv6/inet6_connection_sock.c    |  2 +-
 net/l2tp/l2tp_core.c                | 10 ++++++----
 net/l2tp/l2tp_ip.c                  |  2 +-
 net/sctp/protocol.c                 |  2 +-
 10 files changed, 17 insertions(+), 15 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h
index ff013505236ba..3207e58ee0198 100644
--- a/include/net/inet6_connection_sock.h
+++ b/include/net/inet6_connection_sock.h
@@ -41,5 +41,5 @@ extern void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
 
 extern void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
 
-extern int inet6_csk_xmit(struct sk_buff *skb);
+extern int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl);
 #endif /* _INET6_CONNECTION_SOCK_H */
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 4367d913c0e22..96546cae1cba8 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -36,7 +36,7 @@ struct tcp_congestion_ops;
  * (i.e. things that depend on the address family)
  */
 struct inet_connection_sock_af_ops {
-	int	    (*queue_xmit)(struct sk_buff *skb);
+	int	    (*queue_xmit)(struct sk_buff *skb, struct flowi *fl);
 	void	    (*send_check)(struct sock *sk, struct sk_buff *skb);
 	int	    (*rebuild_header)(struct sock *sk);
 	int	    (*conn_request)(struct sock *sk, struct sk_buff *skb);
diff --git a/include/net/ip.h b/include/net/ip.h
index 095e392d5f16f..acf8b7814c4e5 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -104,7 +104,7 @@ extern int		ip_do_nat(struct sk_buff *skb);
 extern void		ip_send_check(struct iphdr *ip);
 extern int		__ip_local_out(struct sk_buff *skb);
 extern int		ip_local_out(struct sk_buff *skb);
-extern int		ip_queue_xmit(struct sk_buff *skb);
+extern int		ip_queue_xmit(struct sk_buff *skb, struct flowi *fl);
 extern void		ip_init(void);
 extern int		ip_append_data(struct sock *sk,
 				       int getfrag(void *from, char *to, int offset, int len,
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 136d41cbcd02a..fab108e51e5a8 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -43,7 +43,7 @@ static void dccp_skb_entail(struct sock *sk, struct sk_buff *skb)
 static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 {
 	if (likely(skb != NULL)) {
-		const struct inet_sock *inet = inet_sk(sk);
+		struct inet_sock *inet = inet_sk(sk);
 		const struct inet_connection_sock *icsk = inet_csk(sk);
 		struct dccp_sock *dp = dccp_sk(sk);
 		struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
@@ -136,7 +136,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 
 		DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
 
-		err = icsk->icsk_af_ops->queue_xmit(skb);
+		err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl);
 		return net_xmit_eval(err);
 	}
 	return -ENOBUFS;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4ba26d4040eda..14ee1e47720c5 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -312,7 +312,7 @@ int ip_output(struct sk_buff *skb)
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
-int ip_queue_xmit(struct sk_buff *skb)
+int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
 {
 	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
@@ -332,7 +332,7 @@ int ip_queue_xmit(struct sk_buff *skb)
 		goto packet_routed;
 
 	/* Make sure we can route this packet. */
-	fl4 = &inet->cork.fl.u.ip4;
+	fl4 = &fl->u.ip4;
 	rt = (struct rtable *)__sk_dst_check(sk, 0);
 	if (rt == NULL) {
 		__be32 daddr;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 17388c7f49c45..882e0b0964d04 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -899,7 +899,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
 			      tcp_skb_pcount(skb));
 
-	err = icsk->icsk_af_ops->queue_xmit(skb);
+	err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl);
 	if (likely(err <= 0))
 		return err;
 
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index f2c5b0fc0f218..8a58e8cf6646b 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -203,7 +203,7 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
 	return dst;
 }
 
-int inet6_csk_xmit(struct sk_buff *skb)
+int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused)
 {
 	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 78530299ae38d..9be095e00450a 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -954,7 +954,7 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf)
 }
 
 static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
-			  size_t data_len)
+			  struct flowi *fl, size_t data_len)
 {
 	struct l2tp_tunnel *tunnel = session->tunnel;
 	unsigned int len = skb->len;
@@ -987,7 +987,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
 
 	/* Queue the packet to IP for output */
 	skb->local_df = 1;
-	error = ip_queue_xmit(skb);
+	error = ip_queue_xmit(skb, fl);
 
 	/* Update stats */
 	if (error >= 0) {
@@ -1028,6 +1028,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 	int data_len = skb->len;
 	struct l2tp_tunnel *tunnel = session->tunnel;
 	struct sock *sk = tunnel->sock;
+	struct flowi *fl;
 	struct udphdr *uh;
 	struct inet_sock *inet;
 	__wsum csum;
@@ -1070,10 +1071,11 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 	skb_dst_drop(skb);
 	skb_dst_set(skb, dst_clone(__sk_dst_get(sk)));
 
+	inet = inet_sk(sk);
+	fl = &inet->cork.fl;
 	switch (tunnel->encap) {
 	case L2TP_ENCAPTYPE_UDP:
 		/* Setup UDP header */
-		inet = inet_sk(sk);
 		__skb_push(skb, sizeof(*uh));
 		skb_reset_transport_header(skb);
 		uh = udp_hdr(skb);
@@ -1111,7 +1113,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 
 	l2tp_skb_set_owner_w(skb, sk);
 
-	l2tp_xmit_core(session, skb, data_len);
+	l2tp_xmit_core(session, skb, fl, data_len);
 out_unlock:
 	bh_unlock_sock(sk);
 
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 1ca74892ff09d..f7fb09ecaf890 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -508,7 +508,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 	skb_dst_set(skb, dst_clone(&rt->dst));
 
 	/* Queue the packet to IP for output */
-	rc = ip_queue_xmit(skb);
+	rc = ip_queue_xmit(skb, &inet->cork.fl);
 
 error:
 	/* Update stats */
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 69fbc55cf18ed..847193b7995f0 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -855,7 +855,7 @@ static inline int sctp_v4_xmit(struct sk_buff *skb,
 			 IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
 
 	SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS);
-	return ip_queue_xmit(skb);
+	return ip_queue_xmit(skb, &transport->fl);
 }
 
 static struct sctp_af sctp_af_inet;
-- 
cgit v1.2.3


From be281e554e2a4cf2478df7a8b8926c89454bccfa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 19 May 2011 01:14:23 +0000
Subject: ipv6: reduce per device ICMP mib sizes

ipv6 has per device ICMP SNMP counters, taking too much space because
they use percpu storage.

needed size per device is :
(512+4)*sizeof(long)*number_of_possible_cpus*2

On a 32bit kernel, 16 possible cpus, this wastes more than 64kbytes of
memory per ipv6 enabled network device, taken in vmalloc pool.

Since ICMP messages are rare, just use shared counters (atomic_long_t)

Per network space ICMP counters are still using percpu memory, we might
also convert them to shared counters in a future patch.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Denys Fedoryshchenko <denys@visp.net.lb>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/if_inet6.h |  4 ++--
 include/net/ipv6.h     | 19 ++++++++++++++-----
 include/net/snmp.h     | 14 ++++++++++++++
 net/ipv6/addrconf.c    | 24 ++++++++++++------------
 net/ipv6/proc.c        | 40 ++++++++++++++++++++++++++--------------
 5 files changed, 68 insertions(+), 33 deletions(-)

(limited to 'net/ipv6')

diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 0c603fe653773..11cf373970a96 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -154,8 +154,8 @@ struct ifacaddr6 {
 struct ipv6_devstat {
 	struct proc_dir_entry	*proc_dir_entry;
 	DEFINE_SNMP_STAT(struct ipstats_mib, ipv6);
-	DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6);
-	DEFINE_SNMP_STAT(struct icmpv6msg_mib, icmpv6msg);
+	DEFINE_SNMP_STAT_ATOMIC(struct icmpv6_mib_device, icmpv6dev);
+	DEFINE_SNMP_STAT_ATOMIC(struct icmpv6msg_mib_device, icmpv6msgdev);
 };
 
 struct inet6_dev {
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index e1c60b43e73bf..c033ed00df7da 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -123,6 +123,15 @@ extern struct ctl_path net_ipv6_ctl_path[];
 	SNMP_INC_STATS##modifier((net)->mib.statname##_statistics, (field));\
 })
 
+/* per device counters are atomic_long_t */
+#define _DEVINCATOMIC(net, statname, modifier, idev, field)		\
+({									\
+	struct inet6_dev *_idev = (idev);				\
+	if (likely(_idev != NULL))					\
+		SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \
+	SNMP_INC_STATS##modifier((net)->mib.statname##_statistics, (field));\
+})
+
 #define _DEVADD(net, statname, modifier, idev, field, val)		\
 ({									\
 	struct inet6_dev *_idev = (idev);				\
@@ -154,16 +163,16 @@ extern struct ctl_path net_ipv6_ctl_path[];
 #define IP6_UPD_PO_STATS_BH(net, idev,field,val)   \
 		_DEVUPD(net, ipv6, 64_BH, idev, field, val)
 #define ICMP6_INC_STATS(net, idev, field)	\
-		_DEVINC(net, icmpv6, , idev, field)
+		_DEVINCATOMIC(net, icmpv6, , idev, field)
 #define ICMP6_INC_STATS_BH(net, idev, field)	\
-		_DEVINC(net, icmpv6, _BH, idev, field)
+		_DEVINCATOMIC(net, icmpv6, _BH, idev, field)
 
 #define ICMP6MSGOUT_INC_STATS(net, idev, field)		\
-	_DEVINC(net, icmpv6msg, , idev, field +256)
+	_DEVINCATOMIC(net, icmpv6msg, , idev, field +256)
 #define ICMP6MSGOUT_INC_STATS_BH(net, idev, field)	\
-	_DEVINC(net, icmpv6msg, _BH, idev, field +256)
+	_DEVINCATOMIC(net, icmpv6msg, _BH, idev, field +256)
 #define ICMP6MSGIN_INC_STATS_BH(net, idev, field)	\
-	_DEVINC(net, icmpv6msg, _BH, idev, field)
+	_DEVINCATOMIC(net, icmpv6msg, _BH, idev, field)
 
 struct ip6_ra_chain {
 	struct ip6_ra_chain	*next;
diff --git a/include/net/snmp.h b/include/net/snmp.h
index 27461d6dd46f2..479083a78b0c0 100644
--- a/include/net/snmp.h
+++ b/include/net/snmp.h
@@ -72,14 +72,24 @@ struct icmpmsg_mib {
 
 /* ICMP6 (IPv6-ICMP) */
 #define ICMP6_MIB_MAX	__ICMP6_MIB_MAX
+/* per network ns counters */
 struct icmpv6_mib {
 	unsigned long	mibs[ICMP6_MIB_MAX];
 };
+/* per device counters, (shared on all cpus) */
+struct icmpv6_mib_device {
+	atomic_long_t	mibs[ICMP6_MIB_MAX];
+};
 
 #define ICMP6MSG_MIB_MAX  __ICMP6MSG_MIB_MAX
+/* per network ns counters */
 struct icmpv6msg_mib {
 	unsigned long	mibs[ICMP6MSG_MIB_MAX];
 };
+/* per device counters, (shared on all cpus) */
+struct icmpv6msg_mib_device {
+	atomic_long_t	mibs[ICMP6MSG_MIB_MAX];
+};
 
 
 /* TCP */
@@ -114,6 +124,8 @@ struct linux_xfrm_mib {
  */ 
 #define DEFINE_SNMP_STAT(type, name)	\
 	__typeof__(type) __percpu *name[2]
+#define DEFINE_SNMP_STAT_ATOMIC(type, name)	\
+	__typeof__(type) *name
 #define DECLARE_SNMP_STAT(type, name)	\
 	extern __typeof__(type) __percpu *name[2]
 
@@ -124,6 +136,8 @@ struct linux_xfrm_mib {
 			__this_cpu_inc(mib[0]->mibs[field])
 #define SNMP_INC_STATS_USER(mib, field)	\
 			this_cpu_inc(mib[1]->mibs[field])
+#define SNMP_INC_STATS_ATOMIC_LONG(mib, field)	\
+			atomic_long_inc(&mib->mibs[field])
 #define SNMP_INC_STATS(mib, field)	\
 			this_cpu_inc(mib[!in_softirq()]->mibs[field])
 #define SNMP_DEC_STATS(mib, field)	\
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f2f9b2e3cfe9f..3cfbbf3387a0c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -289,19 +289,19 @@ static int snmp6_alloc_dev(struct inet6_dev *idev)
 			  sizeof(struct ipstats_mib),
 			  __alignof__(struct ipstats_mib)) < 0)
 		goto err_ip;
-	if (snmp_mib_init((void __percpu **)idev->stats.icmpv6,
-			  sizeof(struct icmpv6_mib),
-			  __alignof__(struct icmpv6_mib)) < 0)
+	idev->stats.icmpv6dev = kzalloc(sizeof(struct icmpv6_mib_device),
+					GFP_KERNEL);
+	if (!idev->stats.icmpv6dev)
 		goto err_icmp;
-	if (snmp_mib_init((void __percpu **)idev->stats.icmpv6msg,
-			  sizeof(struct icmpv6msg_mib),
-			  __alignof__(struct icmpv6msg_mib)) < 0)
+	idev->stats.icmpv6msgdev = kzalloc(sizeof(struct icmpv6msg_mib_device),
+					   GFP_KERNEL);
+	if (!idev->stats.icmpv6msgdev)
 		goto err_icmpmsg;
 
 	return 0;
 
 err_icmpmsg:
-	snmp_mib_free((void __percpu **)idev->stats.icmpv6);
+	kfree(idev->stats.icmpv6dev);
 err_icmp:
 	snmp_mib_free((void __percpu **)idev->stats.ipv6);
 err_ip:
@@ -310,8 +310,8 @@ err_ip:
 
 static void snmp6_free_dev(struct inet6_dev *idev)
 {
-	snmp_mib_free((void __percpu **)idev->stats.icmpv6msg);
-	snmp_mib_free((void __percpu **)idev->stats.icmpv6);
+	kfree(idev->stats.icmpv6msgdev);
+	kfree(idev->stats.icmpv6dev);
 	snmp_mib_free((void __percpu **)idev->stats.ipv6);
 }
 
@@ -3838,7 +3838,7 @@ static inline size_t inet6_if_nlmsg_size(void)
 	       + nla_total_size(inet6_ifla6_size()); /* IFLA_PROTINFO */
 }
 
-static inline void __snmp6_fill_stats(u64 *stats, void __percpu **mib,
+static inline void __snmp6_fill_statsdev(u64 *stats, atomic_long_t *mib,
 				      int items, int bytes)
 {
 	int i;
@@ -3848,7 +3848,7 @@ static inline void __snmp6_fill_stats(u64 *stats, void __percpu **mib,
 	/* Use put_unaligned() because stats may not be aligned for u64. */
 	put_unaligned(items, &stats[0]);
 	for (i = 1; i < items; i++)
-		put_unaligned(snmp_fold_field(mib, i), &stats[i]);
+		put_unaligned(atomic_long_read(&mib[i]), &stats[i]);
 
 	memset(&stats[items], 0, pad);
 }
@@ -3877,7 +3877,7 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
 				     IPSTATS_MIB_MAX, bytes, offsetof(struct ipstats_mib, syncp));
 		break;
 	case IFLA_INET6_ICMP6STATS:
-		__snmp6_fill_stats(stats, (void __percpu **)idev->stats.icmpv6, ICMP6_MIB_MAX, bytes);
+		__snmp6_fill_statsdev(stats, idev->stats.icmpv6dev->mibs, ICMP6_MIB_MAX, bytes);
 		break;
 	}
 }
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 24b3558b8e673..18ff5df7ec027 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -141,7 +141,11 @@ static const struct snmp_mib snmp6_udplite6_list[] = {
 	SNMP_MIB_SENTINEL
 };
 
-static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **mib)
+/* can be called either with percpu mib (pcpumib != NULL),
+ * or shared one (smib != NULL)
+ */
+static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **pcpumib,
+				     atomic_long_t *smib)
 {
 	char name[32];
 	int i;
@@ -158,14 +162,14 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **mib)
 		snprintf(name, sizeof(name), "Icmp6%s%s",
 			i & 0x100 ? "Out" : "In", p);
 		seq_printf(seq, "%-32s\t%lu\n", name,
-			snmp_fold_field(mib, i));
+			pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i));
 	}
 
 	/* print by number (nonzero only) - ICMPMsgStat format */
 	for (i = 0; i < ICMP6MSG_MIB_MAX; i++) {
 		unsigned long val;
 
-		val = snmp_fold_field(mib, i);
+		val = pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i);
 		if (!val)
 			continue;
 		snprintf(name, sizeof(name), "Icmp6%sType%u",
@@ -174,14 +178,22 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **mib)
 	}
 }
 
-static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **mib,
+/* can be called either with percpu mib (pcpumib != NULL),
+ * or shared one (smib != NULL)
+ */
+static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **pcpumib,
+				atomic_long_t *smib,
 				const struct snmp_mib *itemlist)
 {
 	int i;
+	unsigned long val;
 
-	for (i = 0; itemlist[i].name; i++)
-		seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name,
-			   snmp_fold_field(mib, itemlist[i].entry));
+	for (i = 0; itemlist[i].name; i++) {
+		val = pcpumib ?
+			snmp_fold_field(pcpumib, itemlist[i].entry) :
+			atomic_long_read(smib + itemlist[i].entry);
+		seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, val);
+	}
 }
 
 static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu **mib,
@@ -201,13 +213,13 @@ static int snmp6_seq_show(struct seq_file *seq, void *v)
 	snmp6_seq_show_item64(seq, (void __percpu **)net->mib.ipv6_statistics,
 			    snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp));
 	snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics,
-			    snmp6_icmp6_list);
+			    NULL, snmp6_icmp6_list);
 	snmp6_seq_show_icmpv6msg(seq,
-			    (void __percpu **)net->mib.icmpv6msg_statistics);
+			    (void __percpu **)net->mib.icmpv6msg_statistics, NULL);
 	snmp6_seq_show_item(seq, (void __percpu **)net->mib.udp_stats_in6,
-			    snmp6_udp6_list);
+			    NULL, snmp6_udp6_list);
 	snmp6_seq_show_item(seq, (void __percpu **)net->mib.udplite_stats_in6,
-			    snmp6_udplite6_list);
+			    NULL, snmp6_udplite6_list);
 	return 0;
 }
 
@@ -229,11 +241,11 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v)
 	struct inet6_dev *idev = (struct inet6_dev *)seq->private;
 
 	seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex);
-	snmp6_seq_show_item(seq, (void __percpu **)idev->stats.ipv6,
+	snmp6_seq_show_item(seq, (void __percpu **)idev->stats.ipv6, NULL,
 			    snmp6_ipstats_list);
-	snmp6_seq_show_item(seq, (void __percpu **)idev->stats.icmpv6,
+	snmp6_seq_show_item(seq, NULL, idev->stats.icmpv6dev->mibs,
 			    snmp6_icmp6_list);
-	snmp6_seq_show_icmpv6msg(seq, (void __percpu **)idev->stats.icmpv6msg);
+	snmp6_seq_show_icmpv6msg(seq, NULL, idev->stats.icmpv6msgdev->mibs);
 	return 0;
 }
 
-- 
cgit v1.2.3