From 0bfbedb14a8a96c529341bec88991a92b41fac72 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Mon, 5 Oct 2009 00:11:22 -0700
Subject: tunnels: Optimize tx path

We currently dirty a cache line to update tunnel device stats
(tx_packets/tx_bytes). We better use the txq->tx_bytes/tx_packets
counters that already are present in cpu cache, in the cache
line shared with txq->_xmit_lock

This patch extends IPTUNNEL_XMIT() macro to use txq pointer
provided by the caller.

Also &tunnel->dev->stats can be replaced by &dev->stats

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'net/ipv6/sit.c')

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index dbd19a78ca7..99da272951d 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -555,7 +555,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 				     struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct net_device_stats *stats = &tunnel->dev->stats;
+	struct net_device_stats *stats = &dev->stats;
+	struct netdev_queue *txq = netdev_get_tx_queue(dev, 0);
 	struct iphdr  *tiph = &tunnel->parms.iph;
 	struct ipv6hdr *iph6 = ipv6_hdr(skb);
 	u8     tos = tunnel->parms.iph.tos;
@@ -688,7 +689,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
 		if (!new_skb) {
 			ip_rt_put(rt);
-			stats->tx_dropped++;
+			txq->tx_dropped++;
 			dev_kfree_skb(skb);
 			return NETDEV_TX_OK;
 		}
-- 
cgit v1.2.3-70-g09d2


From fa857afcf77da669eb6b7031ec07ad14b912c307 Mon Sep 17 00:00:00 2001
From: YOSHIFUJI Hideaki / 吉藤英明 <yoshfuji@linux-ipv6.org>
Date: Tue, 22 Sep 2009 23:43:14 +0000
Subject: ipv6 sit: 6rd (IPv6 Rapid Deployment) Support.

IPv6 Rapid Deployment (6rd; draft-ietf-softwire-ipv6-6rd) builds upon
mechanisms of 6to4 (RFC3056) to enable a service provider to rapidly
deploy IPv6 unicast service to IPv4 sites to which it provides
customer premise equipment.  Like 6to4, it utilizes stateless IPv6 in
IPv4 encapsulation in order to transit IPv4-only network
infrastructure.  Unlike 6to4, a 6rd service provider uses an IPv6
prefix of its own in place of the fixed 6to4 prefix.

With this option enabled, the SIT driver offers 6rd functionality by
providing additional ioctl API to configure the IPv6 Prefix for in
stead of static 2002::/16 for 6to4.

Original patch was done by Alexandre Cassen <acassen@freebox.fr>
based on old Internet-Draft.

Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_tunnel.h |  11 ++++
 include/net/ipip.h        |  13 +++++
 net/ipv6/Kconfig          |  19 +++++++
 net/ipv6/sit.c            | 124 +++++++++++++++++++++++++++++++++++++++++++---
 4 files changed, 159 insertions(+), 8 deletions(-)

(limited to 'net/ipv6/sit.c')

diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h
index 5a9aae4adb4..c53c8e01694 100644
--- a/include/linux/if_tunnel.h
+++ b/include/linux/if_tunnel.h
@@ -15,6 +15,10 @@
 #define SIOCADDPRL      (SIOCDEVPRIVATE + 5)
 #define SIOCDELPRL      (SIOCDEVPRIVATE + 6)
 #define SIOCCHGPRL      (SIOCDEVPRIVATE + 7)
+#define SIOCGET6RD      (SIOCDEVPRIVATE + 8)
+#define SIOCADD6RD      (SIOCDEVPRIVATE + 9)
+#define SIOCDEL6RD      (SIOCDEVPRIVATE + 10)
+#define SIOCCHG6RD      (SIOCDEVPRIVATE + 11)
 
 #define GRE_CSUM	__cpu_to_be16(0x8000)
 #define GRE_ROUTING	__cpu_to_be16(0x4000)
@@ -51,6 +55,13 @@ struct ip_tunnel_prl {
 /* PRL flags */
 #define	PRL_DEFAULT		0x0001
 
+struct ip_tunnel_6rd {
+	struct in6_addr		prefix;
+	__be32			relay_prefix;
+	__u16			prefixlen;
+	__u16			relay_prefixlen;
+};
+
 enum
 {
 	IFLA_GRE_UNSPEC,
diff --git a/include/net/ipip.h b/include/net/ipip.h
index 0159221a850..86f1c8bd040 100644
--- a/include/net/ipip.h
+++ b/include/net/ipip.h
@@ -7,6 +7,15 @@
 /* Keep error state on tunnel for 30 sec */
 #define IPTUNNEL_ERR_TIMEO	(30*HZ)
 
+/* 6rd prefix/relay information */
+struct ip_tunnel_6rd_parm
+{
+	struct in6_addr		prefix;
+	__be32			relay_prefix;
+	u16			prefixlen;
+	u16			relay_prefixlen;
+};
+
 struct ip_tunnel
 {
 	struct ip_tunnel	*next;
@@ -23,6 +32,10 @@ struct ip_tunnel
 
 	struct ip_tunnel_parm	parms;
 
+	/* for SIT */
+#ifdef CONFIG_IPV6_SIT_6RD
+	struct ip_tunnel_6rd_parm	ip6rd;
+#endif
 	struct ip_tunnel_prl_entry	*prl;		/* potential router list */
 	unsigned int			prl_count;	/* # of entries in PRL */
 };
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index ead6c7a42f4..f5619982745 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -170,6 +170,25 @@ config IPV6_SIT
 
 	  Saying M here will produce a module called sit. If unsure, say Y.
 
+config IPV6_SIT_6RD
+	bool "IPv6: IPv6 Rapid Development (6RD) (EXPERIMENTAL)"
+	depends on IPV6_SIT && EXPERIMENTAL
+	default n
+	---help---
+	  IPv6 Rapid Deployment (6rd; draft-ietf-softwire-ipv6-6rd) builds upon
+	  mechanisms of 6to4 (RFC3056) to enable a service provider to rapidly
+	  deploy IPv6 unicast service to IPv4 sites to which it provides
+	  customer premise equipment.  Like 6to4, it utilizes stateless IPv6 in
+	  IPv4 encapsulation in order to transit IPv4-only network
+	  infrastructure.  Unlike 6to4, a 6rd service provider uses an IPv6
+	  prefix of its own in place of the fixed 6to4 prefix.
+
+	  With this option enabled, the SIT driver offers 6rd functionality by
+	  providing additional ioctl API to configure the IPv6 Prefix for in
+	  stead of static 2002::/16 for 6to4.
+
+	  If unsure, say N.
+
 config IPV6_NDISC_NODETYPE
 	bool
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 99da272951d..6955654262a 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -161,6 +161,21 @@ static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t)
 	write_unlock_bh(&ipip6_lock);
 }
 
+static void ipip6_tunnel_clone_6rd(struct ip_tunnel *t, struct sit_net *sitn)
+{
+#ifdef CONFIG_IPV6_SIT_6RD
+	if (t->dev == sitn->fb_tunnel_dev) {
+		ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
+		t->ip6rd.relay_prefix = 0;
+		t->ip6rd.prefixlen = 16;
+		t->ip6rd.relay_prefixlen = 0;
+	} else {
+		struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev);
+		memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd));
+	}
+#endif
+}
+
 static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
 		struct ip_tunnel_parm *parms, int create)
 {
@@ -213,6 +228,8 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
 
 	dev_hold(dev);
 
+	ipip6_tunnel_clone_6rd(t, sitn);
+
 	ipip6_tunnel_link(sitn, nt);
 	return nt;
 
@@ -532,17 +549,41 @@ out:
 	return 0;
 }
 
-/* Returns the embedded IPv4 address if the IPv6 address
-   comes from 6to4 (RFC 3056) addr space */
-
-static inline __be32 try_6to4(struct in6_addr *v6dst)
+/*
+ * Returns the embedded IPv4 address if the IPv6 address
+ * comes from 6rd / 6to4 (RFC 3056) addr space.
+ */
+static inline
+__be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel)
 {
 	__be32 dst = 0;
 
+#ifdef CONFIG_IPV6_SIT_6RD
+	if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix,
+			      tunnel->ip6rd.prefixlen)) {
+		unsigned pbw0, pbi0;
+		int pbi1;
+		u32 d;
+
+		pbw0 = tunnel->ip6rd.prefixlen >> 5;
+		pbi0 = tunnel->ip6rd.prefixlen & 0x1f;
+
+		d = (ntohl(tunnel->ip6rd.prefix.s6_addr32[pbw0]) << pbi0) >>
+		    tunnel->ip6rd.relay_prefixlen;
+
+		pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen;
+		if (pbi1 > 0)
+			d |= ntohl(tunnel->ip6rd.prefix.s6_addr32[pbw0 + 1]) >>
+			     (32 - pbi1);
+
+		dst = tunnel->ip6rd.relay_prefix | htonl(d);
+	}
+#else
 	if (v6dst->s6_addr16[0] == htons(0x2002)) {
 		/* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */
 		memcpy(&dst, &v6dst->s6_addr16[1], 4);
 	}
+#endif
 	return dst;
 }
 
@@ -596,7 +637,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	}
 
 	if (!dst)
-		dst = try_6to4(&iph6->daddr);
+		dst = try_6rd(&iph6->daddr, tunnel);
 
 	if (!dst) {
 		struct neighbour *neigh = NULL;
@@ -786,9 +827,15 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 	struct ip_tunnel *t;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
+#ifdef CONFIG_IPV6_SIT_6RD
+	struct ip_tunnel_6rd ip6rd;
+#endif
 
 	switch (cmd) {
 	case SIOCGETTUNNEL:
+#ifdef CONFIG_IPV6_SIT_6RD
+	case SIOCGET6RD:
+#endif
 		t = NULL;
 		if (dev == sitn->fb_tunnel_dev) {
 			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
@@ -799,9 +846,25 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 		}
 		if (t == NULL)
 			t = netdev_priv(dev);
-		memcpy(&p, &t->parms, sizeof(p));
-		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
-			err = -EFAULT;
+
+		err = -EFAULT;
+		if (cmd == SIOCGETTUNNEL) {
+			memcpy(&p, &t->parms, sizeof(p));
+			if (copy_to_user(ifr->ifr_ifru.ifru_data, &p,
+					 sizeof(p)))
+				goto done;
+#ifdef CONFIG_IPV6_SIT_6RD
+		} else {
+			ipv6_addr_copy(&ip6rd.prefix, &t->ip6rd.prefix);
+			ip6rd.relay_prefix = t->ip6rd.relay_prefix;
+			ip6rd.prefixlen = t->ip6rd.prefixlen;
+			ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen;
+			if (copy_to_user(ifr->ifr_ifru.ifru_data, &ip6rd,
+					 sizeof(ip6rd)))
+				goto done;
+#endif
+		}
+		err = 0;
 		break;
 
 	case SIOCADDTUNNEL:
@@ -922,6 +985,51 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 		netdev_state_change(dev);
 		break;
 
+#ifdef CONFIG_IPV6_SIT_6RD
+	case SIOCADD6RD:
+	case SIOCCHG6RD:
+	case SIOCDEL6RD:
+		err = -EPERM;
+		if (!capable(CAP_NET_ADMIN))
+			goto done;
+
+		err = -EFAULT;
+		if (copy_from_user(&ip6rd, ifr->ifr_ifru.ifru_data,
+				   sizeof(ip6rd)))
+			goto done;
+
+		t = netdev_priv(dev);
+
+		if (cmd != SIOCDEL6RD) {
+			struct in6_addr prefix;
+			__be32 relay_prefix;
+
+			err = -EINVAL;
+			if (ip6rd.relay_prefixlen > 32 ||
+			    ip6rd.prefixlen + (32 - ip6rd.relay_prefixlen) > 64)
+				goto done;
+
+			ipv6_addr_prefix(&prefix, &ip6rd.prefix,
+					 ip6rd.prefixlen);
+			if (!ipv6_addr_equal(&prefix, &ip6rd.prefix))
+				goto done;
+			relay_prefix = ip6rd.relay_prefix &
+				       htonl(0xffffffffUL <<
+					     (32 - ip6rd.relay_prefixlen));
+			if (relay_prefix != ip6rd.relay_prefix)
+				goto done;
+
+			ipv6_addr_copy(&t->ip6rd.prefix, &prefix);
+			t->ip6rd.relay_prefix = relay_prefix;
+			t->ip6rd.prefixlen = ip6rd.prefixlen;
+			t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen;
+		} else
+			ipip6_tunnel_clone_6rd(t, sitn);
+
+		err = 0;
+		break;
+#endif
+
 	default:
 		err = -EINVAL;
 	}
-- 
cgit v1.2.3-70-g09d2


From e0c93948154328e13b4c0b0502d66af93f0fdfc4 Mon Sep 17 00:00:00 2001
From: YOSHIFUJI Hideaki / 吉藤英明 <yoshfuji@linux-ipv6.org>
Date: Sun, 11 Oct 2009 03:31:34 +0000
Subject: ipv6 sit: Ensure to initialize 6rd parameters.

ipv6 sit: Ensure to initialize 6rd parameters.

Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

(limited to 'net/ipv6/sit.c')

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 6955654262a..8594451c747 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -161,9 +161,11 @@ static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t)
 	write_unlock_bh(&ipip6_lock);
 }
 
-static void ipip6_tunnel_clone_6rd(struct ip_tunnel *t, struct sit_net *sitn)
+static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
 {
 #ifdef CONFIG_IPV6_SIT_6RD
+	struct ip_tunnel *t = netdev_priv(dev);
+
 	if (t->dev == sitn->fb_tunnel_dev) {
 		ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
 		t->ip6rd.relay_prefix = 0;
@@ -219,6 +221,7 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
 
 	nt->parms = *parms;
 	ipip6_tunnel_init(dev);
+	ipip6_tunnel_clone_6rd(dev, sitn);
 
 	if (parms->i_flags & SIT_ISATAP)
 		dev->priv_flags |= IFF_ISATAP;
@@ -228,8 +231,6 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
 
 	dev_hold(dev);
 
-	ipip6_tunnel_clone_6rd(t, sitn);
-
 	ipip6_tunnel_link(sitn, nt);
 	return nt;
 
@@ -1024,7 +1025,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 			t->ip6rd.prefixlen = ip6rd.prefixlen;
 			t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen;
 		} else
-			ipip6_tunnel_clone_6rd(t, sitn);
+			ipip6_tunnel_clone_6rd(dev, sitn);
 
 		err = 0;
 		break;
@@ -1148,6 +1149,7 @@ static int sit_init_net(struct net *net)
 	dev_net_set(sitn->fb_tunnel_dev, net);
 
 	ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
+	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
 
 	if ((err = register_netdev(sitn->fb_tunnel_dev)))
 		goto err_reg_dev;
-- 
cgit v1.2.3-70-g09d2


From e7db38c38fe8df1d890ae772737e27308bdc5956 Mon Sep 17 00:00:00 2001
From: YOSHIFUJI Hideaki / 吉藤英明 <yoshfuji@linux-ipv6.org>
Date: Sun, 11 Oct 2009 03:44:45 +0000
Subject: ipv6 sit: Fix 6rd relay address.

ipv6 sit: Fix 6rd relay address.

Relay's address should be extracted from real IPv6 address
instead of configured prefix.

Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
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/sit.c')

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 8594451c747..193d0c6c5ce 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -569,12 +569,12 @@ __be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel)
 		pbw0 = tunnel->ip6rd.prefixlen >> 5;
 		pbi0 = tunnel->ip6rd.prefixlen & 0x1f;
 
-		d = (ntohl(tunnel->ip6rd.prefix.s6_addr32[pbw0]) << pbi0) >>
+		d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >>
 		    tunnel->ip6rd.relay_prefixlen;
 
 		pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen;
 		if (pbi1 > 0)
-			d |= ntohl(tunnel->ip6rd.prefix.s6_addr32[pbw0 + 1]) >>
+			d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >>
 			     (32 - pbi1);
 
 		dst = tunnel->ip6rd.relay_prefix | htonl(d);
-- 
cgit v1.2.3-70-g09d2


From 91b2a3f9bb0fa8d64b365a10b0624b0341e1a338 Mon Sep 17 00:00:00 2001
From: YOSHIFUJI Hideaki / 吉藤英明 <yoshfuji@linux-ipv6.org>
Date: Sun, 11 Oct 2009 03:45:13 +0000
Subject: ipv6 sit: Set relay to 0.0.0.0 directly if relay_prefixlen == 0.

ipv6 sit: Set relay to 0.0.0.0 directly if relay_prefixlen == 0.

Do not use bit-shift if relay_prefixlen == 0;
relay_prefix << 32 does not result in 0.

Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'net/ipv6/sit.c')

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 193d0c6c5ce..510d31f3cb9 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1014,9 +1014,12 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 					 ip6rd.prefixlen);
 			if (!ipv6_addr_equal(&prefix, &ip6rd.prefix))
 				goto done;
-			relay_prefix = ip6rd.relay_prefix &
-				       htonl(0xffffffffUL <<
-					     (32 - ip6rd.relay_prefixlen));
+			if (ip6rd.relay_prefixlen)
+				relay_prefix = ip6rd.relay_prefix &
+					       htonl(0xffffffffUL <<
+						     (32 - ip6rd.relay_prefixlen));
+			else
+				relay_prefix = 0;
 			if (relay_prefix != ip6rd.relay_prefix)
 				goto done;
 
-- 
cgit v1.2.3-70-g09d2


From ef9a9d1183b36fbf3de327f44596533b770c3005 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Fri, 23 Oct 2009 17:51:26 +0000
Subject: ipv6 sit: RCU conversion phase I

SIT tunnels use one rwlock to protect their prl entries.

This first patch adds RCU locking for prl management,
with standard call_rcu() calls.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipip.h |  1 +
 net/ipv6/sit.c     | 73 +++++++++++++++++++++++++++++++++++++-----------------
 2 files changed, 51 insertions(+), 23 deletions(-)

(limited to 'net/ipv6/sit.c')

diff --git a/include/net/ipip.h b/include/net/ipip.h
index 86f1c8bd040..b3db2fd6e61 100644
--- a/include/net/ipip.h
+++ b/include/net/ipip.h
@@ -45,6 +45,7 @@ struct ip_tunnel_prl_entry
 	struct ip_tunnel_prl_entry	*next;
 	__be32				addr;
 	u16				flags;
+	struct rcu_head			rcu_head;
 };
 
 #define IPTUNNEL_XMIT() do {						\
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 510d31f3cb9..8cdcc2ad048 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -240,15 +240,22 @@ failed:
 	return NULL;
 }
 
+static DEFINE_SPINLOCK(ipip6_prl_lock);
+
+#define for_each_prl_rcu(start)			\
+	for (prl = rcu_dereference(start);	\
+	     prl;				\
+	     prl = rcu_dereference(prl->next))
+
 static struct ip_tunnel_prl_entry *
 __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr)
 {
-	struct ip_tunnel_prl_entry *p = (struct ip_tunnel_prl_entry *)NULL;
+	struct ip_tunnel_prl_entry *prl;
 
-	for (p = t->prl; p; p = p->next)
-		if (p->addr == addr)
+	for_each_prl_rcu(t->prl)
+		if (prl->addr == addr)
 			break;
-	return p;
+	return prl;
 
 }
 
@@ -273,7 +280,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
 		kcalloc(cmax, sizeof(*kp), GFP_KERNEL) :
 		NULL;
 
-	read_lock(&ipip6_lock);
+	rcu_read_lock();
 
 	ca = t->prl_count < cmax ? t->prl_count : cmax;
 
@@ -291,7 +298,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
 	}
 
 	c = 0;
-	for (prl = t->prl; prl; prl = prl->next) {
+	for_each_prl_rcu(t->prl) {
 		if (c >= cmax)
 			break;
 		if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr)
@@ -303,7 +310,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
 			break;
 	}
 out:
-	read_unlock(&ipip6_lock);
+	rcu_read_unlock();
 
 	len = sizeof(*kp) * c;
 	ret = 0;
@@ -324,12 +331,14 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
 	if (a->addr == htonl(INADDR_ANY))
 		return -EINVAL;
 
-	write_lock(&ipip6_lock);
+	spin_lock(&ipip6_prl_lock);
 
 	for (p = t->prl; p; p = p->next) {
 		if (p->addr == a->addr) {
-			if (chg)
-				goto update;
+			if (chg) {
+				p->flags = a->flags;
+				goto out;
+			}
 			err = -EEXIST;
 			goto out;
 		}
@@ -346,46 +355,63 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
 		goto out;
 	}
 
+	INIT_RCU_HEAD(&p->rcu_head);
 	p->next = t->prl;
-	t->prl = p;
-	t->prl_count++;
-update:
 	p->addr = a->addr;
 	p->flags = a->flags;
+	t->prl_count++;
+	rcu_assign_pointer(t->prl, p);
 out:
-	write_unlock(&ipip6_lock);
+	spin_unlock(&ipip6_prl_lock);
 	return err;
 }
 
+static void prl_entry_destroy_rcu(struct rcu_head *head)
+{
+	kfree(container_of(head, struct ip_tunnel_prl_entry, rcu_head));
+}
+
+static void prl_list_destroy_rcu(struct rcu_head *head)
+{
+	struct ip_tunnel_prl_entry *p, *n;
+
+	p = container_of(head, struct ip_tunnel_prl_entry, rcu_head);
+	do {
+		n = p->next;
+		kfree(p);
+		p = n;
+	} while (p);
+}
+
 static int
 ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a)
 {
 	struct ip_tunnel_prl_entry *x, **p;
 	int err = 0;
 
-	write_lock(&ipip6_lock);
+	spin_lock(&ipip6_prl_lock);
 
 	if (a && a->addr != htonl(INADDR_ANY)) {
 		for (p = &t->prl; *p; p = &(*p)->next) {
 			if ((*p)->addr == a->addr) {
 				x = *p;
 				*p = x->next;
-				kfree(x);
+				call_rcu(&x->rcu_head, prl_entry_destroy_rcu);
 				t->prl_count--;
 				goto out;
 			}
 		}
 		err = -ENXIO;
 	} else {
-		while (t->prl) {
+		if (t->prl) {
+			t->prl_count = 0;
 			x = t->prl;
-			t->prl = t->prl->next;
-			kfree(x);
-			t->prl_count--;
+			call_rcu(&x->rcu_head, prl_list_destroy_rcu);
+			t->prl = NULL;
 		}
 	}
 out:
-	write_unlock(&ipip6_lock);
+	spin_unlock(&ipip6_prl_lock);
 	return err;
 }
 
@@ -395,7 +421,7 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t)
 	struct ip_tunnel_prl_entry *p;
 	int ok = 1;
 
-	read_lock(&ipip6_lock);
+	rcu_read_lock();
 	p = __ipip6_tunnel_locate_prl(t, iph->saddr);
 	if (p) {
 		if (p->flags & PRL_DEFAULT)
@@ -411,7 +437,7 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t)
 		else
 			ok = 0;
 	}
-	read_unlock(&ipip6_lock);
+	rcu_read_unlock();
 	return ok;
 }
 
@@ -1192,6 +1218,7 @@ static void __exit sit_cleanup(void)
 	xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
 
 	unregister_pernet_gen_device(sit_net_id, &sit_net_ops);
+	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }
 
 static int __init sit_init(void)
-- 
cgit v1.2.3-70-g09d2


From 4543c10de267bdd4f9acdb7708456909ed7eed3c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Fri, 23 Oct 2009 17:52:14 +0000
Subject: ipv6 sit: RCU conversion phase II

SIT tunnels use one rwlock to protect their hash tables.

This locking scheme can be converted to RCU for free, since netdevice
already must wait for a RCU grace period at dismantle time.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 45 +++++++++++++++++++++++++++------------------
 1 file changed, 27 insertions(+), 18 deletions(-)

(limited to 'net/ipv6/sit.c')

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 8cdcc2ad048..b6b16264b30 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -77,8 +77,17 @@ struct sit_net {
 	struct net_device *fb_tunnel_dev;
 };
 
-static DEFINE_RWLOCK(ipip6_lock);
+/*
+ * Locking : hash tables are protected by RCU and a spinlock
+ */
+static DEFINE_SPINLOCK(ipip6_lock);
+
+#define for_each_ip_tunnel_rcu(start) \
+	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
+/*
+ * Must be invoked with rcu_read_lock
+ */
 static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net,
 		struct net_device *dev, __be32 remote, __be32 local)
 {
@@ -87,26 +96,26 @@ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net,
 	struct ip_tunnel *t;
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 
-	for (t = sitn->tunnels_r_l[h0^h1]; t; t = t->next) {
+	for_each_ip_tunnel_rcu(sitn->tunnels_r_l[h0 ^ h1]) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
 		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
-	for (t = sitn->tunnels_r[h0]; t; t = t->next) {
+	for_each_ip_tunnel_rcu(sitn->tunnels_r[h0]) {
 		if (remote == t->parms.iph.daddr &&
 		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
-	for (t = sitn->tunnels_l[h1]; t; t = t->next) {
+	for_each_ip_tunnel_rcu(sitn->tunnels_l[h1]) {
 		if (local == t->parms.iph.saddr &&
 		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
-	t = sitn->tunnels_wc[0];
+	t = rcu_dereference(sitn->tunnels_wc[0]);
 	if ((t != NULL) && (t->dev->flags & IFF_UP))
 		return t;
 	return NULL;
@@ -143,9 +152,9 @@ static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t)
 
 	for (tp = ipip6_bucket(sitn, t); *tp; tp = &(*tp)->next) {
 		if (t == *tp) {
-			write_lock_bh(&ipip6_lock);
+			spin_lock_bh(&ipip6_lock);
 			*tp = t->next;
-			write_unlock_bh(&ipip6_lock);
+			spin_unlock_bh(&ipip6_lock);
 			break;
 		}
 	}
@@ -155,10 +164,10 @@ static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t)
 {
 	struct ip_tunnel **tp = ipip6_bucket(sitn, t);
 
+	spin_lock_bh(&ipip6_lock);
 	t->next = *tp;
-	write_lock_bh(&ipip6_lock);
-	*tp = t;
-	write_unlock_bh(&ipip6_lock);
+	rcu_assign_pointer(*tp, t);
+	spin_unlock_bh(&ipip6_lock);
 }
 
 static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
@@ -447,9 +456,9 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 
 	if (dev == sitn->fb_tunnel_dev) {
-		write_lock_bh(&ipip6_lock);
+		spin_lock_bh(&ipip6_lock);
 		sitn->tunnels_wc[0] = NULL;
-		write_unlock_bh(&ipip6_lock);
+		spin_unlock_bh(&ipip6_lock);
 		dev_put(dev);
 	} else {
 		ipip6_tunnel_unlink(sitn, netdev_priv(dev));
@@ -502,7 +511,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	err = -ENOENT;
 
-	read_lock(&ipip6_lock);
+	rcu_read_lock();
 	t = ipip6_tunnel_lookup(dev_net(skb->dev),
 				skb->dev,
 				iph->daddr,
@@ -520,7 +529,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 		t->err_count = 1;
 	t->err_time = jiffies;
 out:
-	read_unlock(&ipip6_lock);
+	rcu_read_unlock();
 	return err;
 }
 
@@ -540,7 +549,7 @@ static int ipip6_rcv(struct sk_buff *skb)
 
 	iph = ip_hdr(skb);
 
-	read_lock(&ipip6_lock);
+	rcu_read_lock();
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
 				     iph->saddr, iph->daddr);
 	if (tunnel != NULL) {
@@ -554,7 +563,7 @@ static int ipip6_rcv(struct sk_buff *skb)
 		if ((tunnel->dev->priv_flags & IFF_ISATAP) &&
 		    !isatap_chksrc(skb, iph, tunnel)) {
 			tunnel->dev->stats.rx_errors++;
-			read_unlock(&ipip6_lock);
+			rcu_read_unlock();
 			kfree_skb(skb);
 			return 0;
 		}
@@ -565,12 +574,12 @@ static int ipip6_rcv(struct sk_buff *skb)
 		nf_reset(skb);
 		ipip6_ecn_decapsulate(iph, skb);
 		netif_rx(skb);
-		read_unlock(&ipip6_lock);
+		rcu_read_unlock();
 		return 0;
 	}
 
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
-	read_unlock(&ipip6_lock);
+	rcu_read_unlock();
 out:
 	kfree_skb(skb);
 	return 0;
-- 
cgit v1.2.3-70-g09d2


From 62808f91237181dbac74c2b5be4fa92adfbbbe40 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Wed, 28 Oct 2009 04:37:43 +0000
Subject: ipv6 sit: Optimize multiple unregistration

Speedup module unloading by factorizing synchronize_rcu() calls

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

(limited to 'net/ipv6/sit.c')

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b6b16264b30..2362a3397e9 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1145,16 +1145,19 @@ static struct xfrm_tunnel sit_handler = {
 	.priority	=	1,
 };
 
-static void sit_destroy_tunnels(struct sit_net *sitn)
+static void sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head)
 {
 	int prio;
 
 	for (prio = 1; prio < 4; prio++) {
 		int h;
 		for (h = 0; h < HASH_SIZE; h++) {
-			struct ip_tunnel *t;
-			while ((t = sitn->tunnels[prio][h]) != NULL)
-				unregister_netdevice(t->dev);
+			struct ip_tunnel *t = sitn->tunnels[prio][h];
+
+			while (t != NULL) {
+				unregister_netdevice_queue(t->dev, head);
+				t = t->next;
+			}
 		}
 	}
 }
@@ -1208,11 +1211,13 @@ err_alloc:
 static void sit_exit_net(struct net *net)
 {
 	struct sit_net *sitn;
+	LIST_HEAD(list);
 
 	sitn = net_generic(net, sit_net_id);
 	rtnl_lock();
-	sit_destroy_tunnels(sitn);
-	unregister_netdevice(sitn->fb_tunnel_dev);
+	sit_destroy_tunnels(sitn, &list);
+	unregister_netdevice_queue(sitn->fb_tunnel_dev, &list);
+	unregister_netdevice_many(&list);
 	rtnl_unlock();
 	kfree(sitn);
 }
-- 
cgit v1.2.3-70-g09d2


From 292f4f3ce4b57f17a667cb34c72bca081dcc0281 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 9 Nov 2009 08:42:01 +0000
Subject: sit: Clean up DF code by copying from IPIP

This patch rearranges the SIT DF bit handling using the new IPIP DF
code.  The only externally visible effect should be the case where
PMTU is enabled and the MTU is exactly 1280 bytes.  In this case the
previous code would send packets out with DF off while the new code
would set the DF bit.  This is inline with RFC 4213.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

Thanks,
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 42 +++++++++++++++++++++---------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

(limited to 'net/ipv6/sit.c')

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 2362a3397e9..b6e145a673a 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -637,6 +637,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	struct iphdr  *tiph = &tunnel->parms.iph;
 	struct ipv6hdr *iph6 = ipv6_hdr(skb);
 	u8     tos = tunnel->parms.iph.tos;
+	__be16 df = tiph->frag_off;
 	struct rtable *rt;     			/* Route to the other host */
 	struct net_device *tdev;			/* Device to other host */
 	struct iphdr  *iph;			/* Our new IP header */
@@ -726,25 +727,28 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		goto tx_error;
 	}
 
-	if (tiph->frag_off)
+	if (df) {
 		mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
-	else
-		mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
-	if (mtu < 68) {
-		stats->collisions++;
-		ip_rt_put(rt);
-		goto tx_error;
-	}
-	if (mtu < IPV6_MIN_MTU)
-		mtu = IPV6_MIN_MTU;
-	if (tunnel->parms.iph.daddr && skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+		if (mtu < 68) {
+			stats->collisions++;
+			ip_rt_put(rt);
+			goto tx_error;
+		}
 
-	if (skb->len > mtu) {
-		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
-		ip_rt_put(rt);
-		goto tx_error;
+		if (mtu < IPV6_MIN_MTU) {
+			mtu = IPV6_MIN_MTU;
+			df = 0;
+		}
+
+		if (tunnel->parms.iph.daddr && skb_dst(skb))
+			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+
+		if (skb->len > mtu) {
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
+			ip_rt_put(rt);
+			goto tx_error;
+		}
 	}
 
 	if (tunnel->err_count > 0) {
@@ -792,11 +796,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	iph 			=	ip_hdr(skb);
 	iph->version		=	4;
 	iph->ihl		=	sizeof(struct iphdr)>>2;
-	if (mtu > IPV6_MIN_MTU)
-		iph->frag_off	=	tiph->frag_off;
-	else
-		iph->frag_off	=	0;
-
+	iph->frag_off		=	df;
 	iph->protocol		=	IPPROTO_IPV6;
 	iph->tos		=	INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
 	iph->daddr		=	rt->rt_dst;
-- 
cgit v1.2.3-70-g09d2


From f99189b186f3922ede4fa33c02f6edc735b8c981 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Tue, 17 Nov 2009 10:42:49 +0000
Subject: netns: net_identifiers should be read_mostly

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c         | 2 +-
 drivers/net/ppp_generic.c               | 2 +-
 drivers/net/pppoe.c                     | 2 +-
 drivers/net/pppol2tp.c                  | 2 +-
 net/8021q/vlan.c                        | 2 +-
 net/ipv4/ip_gre.c                       | 2 +-
 net/ipv4/ipip.c                         | 2 +-
 net/ipv6/ip6_tunnel.c                   | 2 +-
 net/ipv6/sit.c                          | 2 +-
 net/key/af_key.c                        | 2 +-
 net/netfilter/nf_conntrack_proto_dccp.c | 2 +-
 net/netfilter/nf_conntrack_proto_gre.c  | 2 +-
 net/phonet/pn_dev.c                     | 2 +-
 13 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'net/ipv6/sit.c')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index ecea6c29413..726bd755338 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -158,7 +158,7 @@ MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to the
 static const char * const version =
 	DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n";
 
-int bond_net_id;
+int bond_net_id __read_mostly;
 
 static __be32 arp_target[BOND_MAX_ARP_TARGETS];
 static int arp_ip_count;
diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c
index 965adb6174c..0a56a778af0 100644
--- a/drivers/net/ppp_generic.c
+++ b/drivers/net/ppp_generic.c
@@ -184,7 +184,7 @@ static atomic_t ppp_unit_count = ATOMIC_INIT(0);
 static atomic_t channel_count = ATOMIC_INIT(0);
 
 /* per-net private data for this module */
-static int ppp_net_id;
+static int ppp_net_id __read_mostly;
 struct ppp_net {
 	/* units to ppp mapping */
 	struct idr units_idr;
diff --git a/drivers/net/pppoe.c b/drivers/net/pppoe.c
index 60c8d233209..a1dcba255b0 100644
--- a/drivers/net/pppoe.c
+++ b/drivers/net/pppoe.c
@@ -97,7 +97,7 @@ static const struct proto_ops pppoe_ops;
 static struct ppp_channel_ops pppoe_chan_ops;
 
 /* per-net private data for this module */
-static int pppoe_net_id;
+static int pppoe_net_id __read_mostly;
 struct pppoe_net {
 	/*
 	 * we could use _single_ hash table for all
diff --git a/drivers/net/pppol2tp.c b/drivers/net/pppol2tp.c
index 849cc9c62c2..442c382c2c8 100644
--- a/drivers/net/pppol2tp.c
+++ b/drivers/net/pppol2tp.c
@@ -232,7 +232,7 @@ static struct ppp_channel_ops pppol2tp_chan_ops = { pppol2tp_xmit , NULL };
 static const struct proto_ops pppol2tp_ops;
 
 /* per-net private data for this module */
-static int pppol2tp_net_id;
+static int pppol2tp_net_id __read_mostly;
 struct pppol2tp_net {
 	struct list_head pppol2tp_tunnel_list;
 	rwlock_t pppol2tp_tunnel_list_lock;
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 39f8d012010..d9cb020029b 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -41,7 +41,7 @@
 
 /* Global VLAN variables */
 
-int vlan_net_id;
+int vlan_net_id __read_mostly;
 
 /* Our listing of VLAN group(s) */
 static struct hlist_head vlan_group_hash[VLAN_GRP_HASH_SIZE];
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index a7de9e3a8f1..c5f6af5d0f3 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -125,7 +125,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev);
 
 #define HASH_SIZE  16
 
-static int ipgre_net_id;
+static int ipgre_net_id __read_mostly;
 struct ipgre_net {
 	struct ip_tunnel *tunnels[4][HASH_SIZE];
 
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index c5b1f71c3cd..7242ffcc44e 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -119,7 +119,7 @@
 #define HASH_SIZE  16
 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
 
-static int ipip_net_id;
+static int ipip_net_id __read_mostly;
 struct ipip_net {
 	struct ip_tunnel *tunnels_r_l[HASH_SIZE];
 	struct ip_tunnel *tunnels_r[HASH_SIZE];
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 1d614113a4b..e5c0f6bb831 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -78,7 +78,7 @@ static void ip6_fb_tnl_dev_init(struct net_device *dev);
 static void ip6_tnl_dev_init(struct net_device *dev);
 static void ip6_tnl_dev_setup(struct net_device *dev);
 
-static int ip6_tnl_net_id;
+static int ip6_tnl_net_id __read_mostly;
 struct ip6_tnl_net {
 	/* the IPv6 tunnel fallback device */
 	struct net_device *fb_tnl_dev;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b6e145a673a..d9deaa7753e 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -66,7 +66,7 @@ static void ipip6_fb_tunnel_init(struct net_device *dev);
 static void ipip6_tunnel_init(struct net_device *dev);
 static void ipip6_tunnel_setup(struct net_device *dev);
 
-static int sit_net_id;
+static int sit_net_id __read_mostly;
 struct sit_net {
 	struct ip_tunnel *tunnels_r_l[HASH_SIZE];
 	struct ip_tunnel *tunnels_r[HASH_SIZE];
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 86b2c22d091..478c8b32a5f 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -35,7 +35,7 @@
 #define _X2KEY(x) ((x) == XFRM_INF ? 0 : (x))
 #define _KEY2X(x) ((x) == 0 ? XFRM_INF : (x))
 
-static int pfkey_net_id;
+static int pfkey_net_id __read_mostly;
 struct netns_pfkey {
 	/* List of all pfkey sockets. */
 	struct hlist_head table;
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 1b816a2ea81..80abdf297b3 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -384,7 +384,7 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] =
 };
 
 /* this module per-net specifics */
-static int dccp_net_id;
+static int dccp_net_id __read_mostly;
 struct dccp_net {
 	int dccp_loose;
 	unsigned int dccp_timeout[CT_DCCP_MAX + 1];
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index a54a0af0edb..91d0e719d67 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -43,7 +43,7 @@
 #define GRE_TIMEOUT		(30 * HZ)
 #define GRE_STREAM_TIMEOUT	(180 * HZ)
 
-static int proto_gre_net_id;
+static int proto_gre_net_id __read_mostly;
 struct netns_proto_gre {
 	rwlock_t		keymap_lock;
 	struct list_head	keymap_list;
diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c
index 3287f8f0b5c..d5ad7947d77 100644
--- a/net/phonet/pn_dev.c
+++ b/net/phonet/pn_dev.c
@@ -43,7 +43,7 @@ struct phonet_net {
 	struct phonet_routes routes;
 };
 
-int phonet_net_id;
+int phonet_net_id __read_mostly;
 
 struct phonet_device_list *phonet_device_list(struct net *net)
 {
-- 
cgit v1.2.3-70-g09d2


From 671011720baa222b6de667cd688aed4dc8908924 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sun, 29 Nov 2009 15:46:16 +0000
Subject: net: Simplify ipip6 aka sit pernet operations.

Take advantage of the new pernet automatic storage management,
and stop using compatibility network namespace functions.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 25 ++++++-------------------
 1 file changed, 6 insertions(+), 19 deletions(-)

(limited to 'net/ipv6/sit.c')

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index d9deaa7753e..976e68244b9 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1164,17 +1164,8 @@ static void sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head)
 
 static int sit_init_net(struct net *net)
 {
+	struct sit_net *sitn = net_generic(net, sit_net_id);
 	int err;
-	struct sit_net *sitn;
-
-	err = -ENOMEM;
-	sitn = kzalloc(sizeof(struct sit_net), GFP_KERNEL);
-	if (sitn == NULL)
-		goto err_alloc;
-
-	err = net_assign_generic(net, sit_net_id, sitn);
-	if (err < 0)
-		goto err_assign;
 
 	sitn->tunnels[0] = sitn->tunnels_wc;
 	sitn->tunnels[1] = sitn->tunnels_l;
@@ -1201,37 +1192,33 @@ err_reg_dev:
 	dev_put(sitn->fb_tunnel_dev);
 	free_netdev(sitn->fb_tunnel_dev);
 err_alloc_dev:
-	/* nothing */
-err_assign:
-	kfree(sitn);
-err_alloc:
 	return err;
 }
 
 static void sit_exit_net(struct net *net)
 {
-	struct sit_net *sitn;
+	struct sit_net *sitn = net_generic(net, sit_net_id);
 	LIST_HEAD(list);
 
-	sitn = net_generic(net, sit_net_id);
 	rtnl_lock();
 	sit_destroy_tunnels(sitn, &list);
 	unregister_netdevice_queue(sitn->fb_tunnel_dev, &list);
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
-	kfree(sitn);
 }
 
 static struct pernet_operations sit_net_ops = {
 	.init = sit_init_net,
 	.exit = sit_exit_net,
+	.id   = &sit_net_id,
+	.size = sizeof(struct sit_net),
 };
 
 static void __exit sit_cleanup(void)
 {
 	xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
 
-	unregister_pernet_gen_device(sit_net_id, &sit_net_ops);
+	unregister_pernet_device(&sit_net_ops);
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }
 
@@ -1246,7 +1233,7 @@ static int __init sit_init(void)
 		return -EAGAIN;
 	}
 
-	err = register_pernet_gen_device(&sit_net_id, &sit_net_ops);
+	err = register_pernet_device(&sit_net_ops);
 	if (err < 0)
 		xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
 
-- 
cgit v1.2.3-70-g09d2