Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1674 commits)
  qlcnic: adding co maintainer
  ixgbe: add support for active DA cables
  ixgbe: dcb, do not tag tc_prio_control frames
  ixgbe: fix ixgbe_tx_is_paused logic
  ixgbe: always enable vlan strip/insert when DCB is enabled
  ixgbe: remove some redundant code in setting FCoE FIP filter
  ixgbe: fix wrong offset to fc_frame_header in ixgbe_fcoe_ddp
  ixgbe: fix header len when unsplit packet overflows to data buffer
  ipv6: Never schedule DAD timer on dead address
  ipv6: Use POSTDAD state
  ipv6: Use state_lock to protect ifa state
  ipv6: Replace inet6_ifaddr->dead with state
  cxgb4: notify upper drivers if the device is already up when they load
  cxgb4: keep interrupts available when the ports are brought down
  cxgb4: fix initial addition of MAC address
  cnic: Return SPQ credit to bnx2x after ring setup and shutdown.
  cnic: Convert cnic_local_flags to atomic ops.
  can: Fix SJA1000 command register writes on SMP systems
  bridge: fix build for CONFIG_SYSFS disabled
  ARCNET: Limit com20020 PCI ID matches for SOHARD cards
  ...

Fix up various conflicts with pcmcia tree drivers/net/
{pcmcia/3c589_cs.c, wireless/orinoco/orinoco_cs.c and
wireless/orinoco/spectrum_cs.c} and feature removal
(Documentation/feature-removal-schedule.txt).

Also fix a non-content conflict due to pm_qos_requirement getting
renamed in the PM tree (now pm_qos_request) in net/mac80211/scan.c

1 files changed, 650 insertions, 275 deletions

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 82aa9c9e4ed..45889103b3e 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -63,11 +63,40 @@
 #include <net/ipip.h>
 #include <net/checksum.h>
 #include <net/netlink.h>
+#include <net/fib_rules.h>
 
 #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
 #define CONFIG_IP_PIMSM	1
 #endif
 
+struct mr_table {
+	struct list_head	list;
+#ifdef CONFIG_NET_NS
+	struct net		*net;
+#endif
+	u32			id;
+	struct sock		*mroute_sk;
+	struct timer_list	ipmr_expire_timer;
+	struct list_head	mfc_unres_queue;
+	struct list_head	mfc_cache_array[MFC_LINES];
+	struct vif_device	vif_table[MAXVIFS];
+	int			maxvif;
+	atomic_t		cache_resolve_queue_len;
+	int			mroute_do_assert;
+	int			mroute_do_pim;
+#if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2)
+	int			mroute_reg_vif_num;
+#endif
+};
+
+struct ipmr_rule {
+	struct fib_rule		common;
+};
+
+struct ipmr_result {
+	struct mr_table		*mrt;
+};
+
 /* Big lock, protecting vif table, mrt cache and mroute socket state.
    Note that the changes are semaphored via rtnl_lock.
  */
@@ -78,9 +107,7 @@ static DEFINE_RWLOCK(mrt_lock);
  *	Multicast router control variables
  */
 
-#define VIF_EXISTS(_net, _idx) ((_net)->ipv4.vif_table[_idx].dev != NULL)
-
-static struct mfc_cache *mfc_unres_queue;		/* Queue of unresolved entries */
+#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL)
 
 /* Special spinlock for queue of unresolved entries */
 static DEFINE_SPINLOCK(mfc_unres_lock);
@@ -95,12 +122,215 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
 
 static struct kmem_cache *mrt_cachep __read_mostly;
 
-static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local);
-static int ipmr_cache_report(struct net *net,
+static struct mr_table *ipmr_new_table(struct net *net, u32 id);
+static int ip_mr_forward(struct net *net, struct mr_table *mrt,
+			 struct sk_buff *skb, struct mfc_cache *cache,
+			 int local);
+static int ipmr_cache_report(struct mr_table *mrt,
 			     struct sk_buff *pkt, vifi_t vifi, int assert);
-static int ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm);
+static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+			      struct mfc_cache *c, struct rtmsg *rtm);
+static void ipmr_expire_process(unsigned long arg);
+
+#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
+#define ipmr_for_each_table(mrt, net) \
+	list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list)
+
+static struct mr_table *ipmr_get_table(struct net *net, u32 id)
+{
+	struct mr_table *mrt;
+
+	ipmr_for_each_table(mrt, net) {
+		if (mrt->id == id)
+			return mrt;
+	}
+	return NULL;
+}
+
+static int ipmr_fib_lookup(struct net *net, struct flowi *flp,
+			   struct mr_table **mrt)
+{
+	struct ipmr_result res;
+	struct fib_lookup_arg arg = { .result = &res, };
+	int err;
+
+	err = fib_rules_lookup(net->ipv4.mr_rules_ops, flp, 0, &arg);
+	if (err < 0)
+		return err;
+	*mrt = res.mrt;
+	return 0;
+}
+
+static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp,
+			    int flags, struct fib_lookup_arg *arg)
+{
+	struct ipmr_result *res = arg->result;
+	struct mr_table *mrt;
 
-static struct timer_list ipmr_expire_timer;
+	switch (rule->action) {
+	case FR_ACT_TO_TBL:
+		break;
+	case FR_ACT_UNREACHABLE:
+		return -ENETUNREACH;
+	case FR_ACT_PROHIBIT:
+		return -EACCES;
+	case FR_ACT_BLACKHOLE:
+	default:
+		return -EINVAL;
+	}
+
+	mrt = ipmr_get_table(rule->fr_net, rule->table);
+	if (mrt == NULL)
+		return -EAGAIN;
+	res->mrt = mrt;
+	return 0;
+}
+
+static int ipmr_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
+{
+	return 1;
+}
+
+static const struct nla_policy ipmr_rule_policy[FRA_MAX + 1] = {
+	FRA_GENERIC_POLICY,
+};
+
+static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
+			       struct fib_rule_hdr *frh, struct nlattr **tb)
+{
+	return 0;
+}
+
+static int ipmr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
+			     struct nlattr **tb)
+{
+	return 1;
+}
+
+static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
+			  struct fib_rule_hdr *frh)
+{
+	frh->dst_len = 0;
+	frh->src_len = 0;
+	frh->tos     = 0;
+	return 0;
+}
+
+static const struct fib_rules_ops __net_initdata ipmr_rules_ops_template = {
+	.family		= RTNL_FAMILY_IPMR,
+	.rule_size	= sizeof(struct ipmr_rule),
+	.addr_size	= sizeof(u32),
+	.action		= ipmr_rule_action,
+	.match		= ipmr_rule_match,
+	.configure	= ipmr_rule_configure,
+	.compare	= ipmr_rule_compare,
+	.default_pref	= fib_default_rule_pref,
+	.fill		= ipmr_rule_fill,
+	.nlgroup	= RTNLGRP_IPV4_RULE,
+	.policy		= ipmr_rule_policy,
+	.owner		= THIS_MODULE,
+};
+
+static int __net_init ipmr_rules_init(struct net *net)
+{
+	struct fib_rules_ops *ops;
+	struct mr_table *mrt;
+	int err;
+
+	ops = fib_rules_register(&ipmr_rules_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+
+	INIT_LIST_HEAD(&net->ipv4.mr_tables);
+
+	mrt = ipmr_new_table(net, RT_TABLE_DEFAULT);
+	if (mrt == NULL) {
+		err = -ENOMEM;
+		goto err1;
+	}
+
+	err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT, 0);
+	if (err < 0)
+		goto err2;
+
+	net->ipv4.mr_rules_ops = ops;
+	return 0;
+
+err2:
+	kfree(mrt);
+err1:
+	fib_rules_unregister(ops);
+	return err;
+}
+
+static void __net_exit ipmr_rules_exit(struct net *net)
+{
+	struct mr_table *mrt, *next;
+
+	list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list)
+		kfree(mrt);
+	fib_rules_unregister(net->ipv4.mr_rules_ops);
+}
+#else
+#define ipmr_for_each_table(mrt, net) \
+	for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
+
+static struct mr_table *ipmr_get_table(struct net *net, u32 id)
+{
+	return net->ipv4.mrt;
+}
+
+static int ipmr_fib_lookup(struct net *net, struct flowi *flp,
+			   struct mr_table **mrt)
+{
+	*mrt = net->ipv4.mrt;
+	return 0;
+}
+
+static int __net_init ipmr_rules_init(struct net *net)
+{
+	net->ipv4.mrt = ipmr_new_table(net, RT_TABLE_DEFAULT);
+	return net->ipv4.mrt ? 0 : -ENOMEM;
+}
+
+static void __net_exit ipmr_rules_exit(struct net *net)
+{
+	kfree(net->ipv4.mrt);
+}
+#endif
+
+static struct mr_table *ipmr_new_table(struct net *net, u32 id)
+{
+	struct mr_table *mrt;
+	unsigned int i;
+
+	mrt = ipmr_get_table(net, id);
+	if (mrt != NULL)
+		return mrt;
+
+	mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
+	if (mrt == NULL)
+		return NULL;
+	write_pnet(&mrt->net, net);
+	mrt->id = id;
+
+	/* Forwarding cache */
+	for (i = 0; i < MFC_LINES; i++)
+		INIT_LIST_HEAD(&mrt->mfc_cache_array[i]);
+
+	INIT_LIST_HEAD(&mrt->mfc_unres_queue);
+
+	setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process,
+		    (unsigned long)mrt);
+
+#ifdef CONFIG_IP_PIMSM
+	mrt->mroute_reg_vif_num = -1;
+#endif
+#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
+	list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables);
+#endif
+	return mrt;
+}
 
 /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */
 
@@ -201,12 +431,22 @@ failure:
 static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct net *net = dev_net(dev);
+	struct mr_table *mrt;
+	struct flowi fl = {
+		.oif		= dev->ifindex,
+		.iif		= skb->skb_iif,
+		.mark		= skb->mark,
+	};
+	int err;
+
+	err = ipmr_fib_lookup(net, &fl, &mrt);
+	if (err < 0)
+		return err;
 
 	read_lock(&mrt_lock);
 	dev->stats.tx_bytes += skb->len;
 	dev->stats.tx_packets++;
-	ipmr_cache_report(net, skb, net->ipv4.mroute_reg_vif_num,
-			  IGMPMSG_WHOLEPKT);
+	ipmr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, IGMPMSG_WHOLEPKT);
 	read_unlock(&mrt_lock);
 	kfree_skb(skb);
 	return NETDEV_TX_OK;
@@ -226,12 +466,18 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->features		|= NETIF_F_NETNS_LOCAL;
 }
 
-static struct net_device *ipmr_reg_vif(struct net *net)
+static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
 {
 	struct net_device *dev;
 	struct in_device *in_dev;
+	char name[IFNAMSIZ];
+
+	if (mrt->id == RT_TABLE_DEFAULT)
+		sprintf(name, "pimreg");
+	else
+		sprintf(name, "pimreg%u", mrt->id);
 
-	dev = alloc_netdev(0, "pimreg", reg_vif_setup);
+	dev = alloc_netdev(0, name, reg_vif_setup);
 
 	if (dev == NULL)
 		return NULL;
@@ -276,17 +522,17 @@ failure:
  *	@notify: Set to 1, if the caller is a notifier_call
  */
 
-static int vif_delete(struct net *net, int vifi, int notify,
+static int vif_delete(struct mr_table *mrt, int vifi, int notify,
 		      struct list_head *head)
 {
 	struct vif_device *v;
 	struct net_device *dev;
 	struct in_device *in_dev;
 
-	if (vifi < 0 || vifi >= net->ipv4.maxvif)
+	if (vifi < 0 || vifi >= mrt->maxvif)
 		return -EADDRNOTAVAIL;
 
-	v = &net->ipv4.vif_table[vifi];
+	v = &mrt->vif_table[vifi];
 
 	write_lock_bh(&mrt_lock);
 	dev = v->dev;
@@ -298,17 +544,17 @@ static int vif_delete(struct net *net, int vifi, int notify,
 	}
 
 #ifdef CONFIG_IP_PIMSM
-	if (vifi == net->ipv4.mroute_reg_vif_num)
-		net->ipv4.mroute_reg_vif_num = -1;
+	if (vifi == mrt->mroute_reg_vif_num)
+		mrt->mroute_reg_vif_num = -1;
 #endif
 
-	if (vifi+1 == net->ipv4.maxvif) {
+	if (vifi+1 == mrt->maxvif) {
 		int tmp;
 		for (tmp=vifi-1; tmp>=0; tmp--) {
-			if (VIF_EXISTS(net, tmp))
+			if (VIF_EXISTS(mrt, tmp))
 				break;
 		}
-		net->ipv4.maxvif = tmp+1;
+		mrt->maxvif = tmp+1;
 	}
 
 	write_unlock_bh(&mrt_lock);
@@ -329,7 +575,6 @@ static int vif_delete(struct net *net, int vifi, int notify,
 
 static inline void ipmr_cache_free(struct mfc_cache *c)
 {
-	release_net(mfc_net(c));
 	kmem_cache_free(mrt_cachep, c);
 }
 
@@ -337,13 +582,13 @@ static inline void ipmr_cache_free(struct mfc_cache *c)
    and reporting error to netlink readers.
  */
 
-static void ipmr_destroy_unres(struct mfc_cache *c)
+static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c)
 {
+	struct net *net = read_pnet(&mrt->net);
 	struct sk_buff *skb;
 	struct nlmsgerr *e;
-	struct net *net = mfc_net(c);
 
-	atomic_dec(&net->ipv4.cache_resolve_queue_len);
+	atomic_dec(&mrt->cache_resolve_queue_len);
 
 	while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) {
 		if (ip_hdr(skb)->version == 0) {
@@ -364,42 +609,40 @@ static void ipmr_destroy_unres(struct mfc_cache *c)
 }
 
 
-/* Single timer process for all the unresolved queue. */
+/* Timer process for the unresolved queue. */
 
-static void ipmr_expire_process(unsigned long dummy)
+static void ipmr_expire_process(unsigned long arg)
 {
+	struct mr_table *mrt = (struct mr_table *)arg;
 	unsigned long now;
 	unsigned long expires;
-	struct mfc_cache *c, **cp;
+	struct mfc_cache *c, *next;
 
 	if (!spin_trylock(&mfc_unres_lock)) {
-		mod_timer(&ipmr_expire_timer, jiffies+HZ/10);
+		mod_timer(&mrt->ipmr_expire_timer, jiffies+HZ/10);
 		return;
 	}
 
-	if (mfc_unres_queue == NULL)
+	if (list_empty(&mrt->mfc_unres_queue))
 		goto out;
 
 	now = jiffies;
 	expires = 10*HZ;
-	cp = &mfc_unres_queue;
 
-	while ((c=*cp) != NULL) {
+	list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) {
 		if (time_after(c->mfc_un.unres.expires, now)) {
 			unsigned long interval = c->mfc_un.unres.expires - now;
 			if (interval < expires)
 				expires = interval;
-			cp = &c->next;
 			continue;
 		}
 
-		*cp = c->next;
-
-		ipmr_destroy_unres(c);
+		list_del(&c->list);
+		ipmr_destroy_unres(mrt, c);
 	}
 
-	if (mfc_unres_queue != NULL)
-		mod_timer(&ipmr_expire_timer, jiffies + expires);
+	if (!list_empty(&mrt->mfc_unres_queue))
+		mod_timer(&mrt->ipmr_expire_timer, jiffies + expires);
 
 out:
 	spin_unlock(&mfc_unres_lock);
@@ -407,17 +650,17 @@ out:
 
 /* Fill oifs list. It is called under write locked mrt_lock. */
 
-static void ipmr_update_thresholds(struct mfc_cache *cache, unsigned char *ttls)
+static void ipmr_update_thresholds(struct mr_table *mrt, struct mfc_cache *cache,
+				   unsigned char *ttls)
 {
 	int vifi;
-	struct net *net = mfc_net(cache);
 
 	cache->mfc_un.res.minvif = MAXVIFS;
 	cache->mfc_un.res.maxvif = 0;
 	memset(cache->mfc_un.res.ttls, 255, MAXVIFS);
 
-	for (vifi = 0; vifi < net->ipv4.maxvif; vifi++) {
-		if (VIF_EXISTS(net, vifi) &&
+	for (vifi = 0; vifi < mrt->maxvif; vifi++) {
+		if (VIF_EXISTS(mrt, vifi) &&
 		    ttls[vifi] && ttls[vifi] < 255) {
 			cache->mfc_un.res.ttls[vifi] = ttls[vifi];
 			if (cache->mfc_un.res.minvif > vifi)
@@ -428,16 +671,17 @@ static void ipmr_update_thresholds(struct mfc_cache *cache, unsigned char *ttls)
 	}
 }
 
-static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock)
+static int vif_add(struct net *net, struct mr_table *mrt,
+		   struct vifctl *vifc, int mrtsock)
 {
 	int vifi = vifc->vifc_vifi;
-	struct vif_device *v = &net->ipv4.vif_table[vifi];
+	struct vif_device *v = &mrt->vif_table[vifi];
 	struct net_device *dev;
 	struct in_device *in_dev;
 	int err;
 
 	/* Is vif busy ? */
-	if (VIF_EXISTS(net, vifi))
+	if (VIF_EXISTS(mrt, vifi))
 		return -EADDRINUSE;
 
 	switch (vifc->vifc_flags) {
@@ -447,9 +691,9 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock)
 		 * Special Purpose VIF in PIM
 		 * All the packets will be sent to the daemon
 		 */
-		if (net->ipv4.mroute_reg_vif_num >= 0)
+		if (mrt->mroute_reg_vif_num >= 0)
 			return -EADDRINUSE;
-		dev = ipmr_reg_vif(net);
+		dev = ipmr_reg_vif(net, mrt);
 		if (!dev)
 			return -ENOBUFS;
 		err = dev_set_allmulti(dev, 1);
@@ -525,49 +769,47 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock)
 	v->dev = dev;
 #ifdef CONFIG_IP_PIMSM
 	if (v->flags&VIFF_REGISTER)
-		net->ipv4.mroute_reg_vif_num = vifi;
+		mrt->mroute_reg_vif_num = vifi;
 #endif
-	if (vifi+1 > net->ipv4.maxvif)
-		net->ipv4.maxvif = vifi+1;
+	if (vifi+1 > mrt->maxvif)
+		mrt->maxvif = vifi+1;
 	write_unlock_bh(&mrt_lock);
 	return 0;
 }
 
-static struct mfc_cache *ipmr_cache_find(struct net *net,
+static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt,
 					 __be32 origin,
 					 __be32 mcastgrp)
 {
 	int line = MFC_HASH(mcastgrp, origin);
 	struct mfc_cache *c;
 
-	for (c = net->ipv4.mfc_cache_array[line]; c; c = c->next) {
-		if (c->mfc_origin==origin && c->mfc_mcastgrp==mcastgrp)
-			break;
+	list_for_each_entry(c, &mrt->mfc_cache_array[line], list) {
+		if (c->mfc_origin == origin && c->mfc_mcastgrp == mcastgrp)
+			return c;
 	}
-	return c;
+	return NULL;
 }
 
 /*
  *	Allocate a multicast cache entry
  */
-static struct mfc_cache *ipmr_cache_alloc(struct net *net)
+static struct mfc_cache *ipmr_cache_alloc(void)
 {
 	struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
 	if (c == NULL)
 		return NULL;
 	c->mfc_un.res.minvif = MAXVIFS;
-	mfc_net_set(c, net);
 	return c;
 }
 
-static struct mfc_cache *ipmr_cache_alloc_unres(struct net *net)
+static struct mfc_cache *ipmr_cache_alloc_unres(void)
 {
 	struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC);
 	if (c == NULL)
 		return NULL;
 	skb_queue_head_init(&c->mfc_un.unres.unresolved);
 	c->mfc_un.unres.expires = jiffies + 10*HZ;
-	mfc_net_set(c, net);
 	return c;
 }
 
@@ -575,7 +817,8 @@ static struct mfc_cache *ipmr_cache_alloc_unres(struct net *net)
  *	A cache entry has gone into a resolved state from queued
  */
 
-static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
+static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt,
+			       struct mfc_cache *uc, struct mfc_cache *c)
 {
 	struct sk_buff *skb;
 	struct nlmsgerr *e;
@@ -588,7 +831,7 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
 		if (ip_hdr(skb)->version == 0) {
 			struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr));
 
-			if (ipmr_fill_mroute(skb, c, NLMSG_DATA(nlh)) > 0) {
+			if (__ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
 				nlh->nlmsg_len = (skb_tail_pointer(skb) -
 						  (u8 *)nlh);
 			} else {
@@ -600,9 +843,9 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
 				memset(&e->msg, 0, sizeof(e->msg));
 			}
 
-			rtnl_unicast(skb, mfc_net(c), NETLINK_CB(skb).pid);
+			rtnl_unicast(skb, net, NETLINK_CB(skb).pid);
 		} else
-			ip_mr_forward(skb, c, 0);
+			ip_mr_forward(net, mrt, skb, c, 0);
 	}
 }
 
@@ -613,7 +856,7 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
  *	Called under mrt_lock.
  */
 
-static int ipmr_cache_report(struct net *net,
+static int ipmr_cache_report(struct mr_table *mrt,
 			     struct sk_buff *pkt, vifi_t vifi, int assert)
 {
 	struct sk_buff *skb;
@@ -646,7 +889,7 @@ static int ipmr_cache_report(struct net *net,
 		memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr));
 		msg->im_msgtype = IGMPMSG_WHOLEPKT;
 		msg->im_mbz = 0;
-		msg->im_vif = net->ipv4.mroute_reg_vif_num;
+		msg->im_vif = mrt->mroute_reg_vif_num;
 		ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2;
 		ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) +
 					     sizeof(struct iphdr));
@@ -678,7 +921,7 @@ static int ipmr_cache_report(struct net *net,
 	skb->transport_header = skb->network_header;
 	}
 
-	if (net->ipv4.mroute_sk == NULL) {
+	if (mrt->mroute_sk == NULL) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
@@ -686,7 +929,7 @@ static int ipmr_cache_report(struct net *net,
 	/*
 	 *	Deliver to mrouted
 	 */
-	ret = sock_queue_rcv_skb(net->ipv4.mroute_sk, skb);
+	ret = sock_queue_rcv_skb(mrt->mroute_sk, skb);
 	if (ret < 0) {
 		if (net_ratelimit())
 			printk(KERN_WARNING "mroute: pending queue full, dropping entries.\n");
@@ -701,27 +944,29 @@ static int ipmr_cache_report(struct net *net,
  */
 
 static int
-ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
+ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb)
 {
+	bool found = false;
 	int err;
 	struct mfc_cache *c;
 	const struct iphdr *iph = ip_hdr(skb);
 
 	spin_lock_bh(&mfc_unres_lock);
-	for (c=mfc_unres_queue; c; c=c->next) {
-		if (net_eq(mfc_net(c), net) &&
-		    c->mfc_mcastgrp == iph->daddr &&
-		    c->mfc_origin == iph->saddr)
+	list_for_each_entry(c, &mrt->mfc_unres_queue, list) {
+		if (c->mfc_mcastgrp == iph->daddr &&
+		    c->mfc_origin == iph->saddr) {
+			found = true;
 			break;
+		}
 	}
 
-	if (c == NULL) {
+	if (!found) {
 		/*
 		 *	Create a new entry if allowable
 		 */
 
-		if (atomic_read(&net->ipv4.cache_resolve_queue_len) >= 10 ||
-		    (c = ipmr_cache_alloc_unres(net)) == NULL) {
+		if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 ||
+		    (c = ipmr_cache_alloc_unres()) == NULL) {
 			spin_unlock_bh(&mfc_unres_lock);
 
 			kfree_skb(skb);
@@ -738,7 +983,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 		/*
 		 *	Reflect first query at mrouted.
 		 */
-		err = ipmr_cache_report(net, skb, vifi, IGMPMSG_NOCACHE);
+		err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE);
 		if (err < 0) {
 			/* If the report failed throw the cache entry
 			   out - Brad Parker
@@ -750,12 +995,11 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
 			return err;
 		}
 
-		atomic_inc(&net->ipv4.cache_resolve_queue_len);
-		c->next = mfc_unres_queue;
-		mfc_unres_queue = c;
+		atomic_inc(&mrt->cache_resolve_queue_len);
+		list_add(&c->list, &mrt->mfc_unres_queue);
 
-		if (atomic_read(&net->ipv4.cache_resolve_queue_len) == 1)
-			mod_timer(&ipmr_expire_timer, c->mfc_un.unres.expires);
+		if (atomic_read(&mrt->cache_resolve_queue_len) == 1)
+			mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires);
 	}
 
 	/*
@@ -777,19 +1021,18 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb)
  *	MFC cache manipulation by user space mroute daemon
  */
 
-static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc)
+static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc)
 {
 	int line;
-	struct mfc_cache *c, **cp;
+	struct mfc_cache *c, *next;
 
 	line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
 
-	for (cp = &net->ipv4.mfc_cache_array[line];
-	     (c = *cp) != NULL; cp = &c->next) {
+	list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) {
 		if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
 		    c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
 			write_lock_bh(&mrt_lock);
-			*cp = c->next;
+			list_del(&c->list);
 			write_unlock_bh(&mrt_lock);
 
 			ipmr_cache_free(c);
@@ -799,27 +1042,30 @@ static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc)
 	return -ENOENT;
 }
 
-static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
+static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
+			struct mfcctl *mfc, int mrtsock)
 {
+	bool found = false;
 	int line;
-	struct mfc_cache *uc, *c, **cp;
+	struct mfc_cache *uc, *c;
 
 	if (mfc->mfcc_parent >= MAXVIFS)
 		return -ENFILE;
 
 	line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr);
 
-	for (cp = &net->ipv4.mfc_cache_array[line];
-	     (c = *cp) != NULL; cp = &c->next) {
+	list_for_each_entry(c, &mrt->mfc_cache_array[line], list) {
 		if (c->mfc_origin == mfc->mfcc_origin.s_addr &&
-		    c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr)
+		    c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) {
+			found = true;
 			break;
+		}
 	}
 
-	if (c != NULL) {
+	if (found) {
 		write_lock_bh(&mrt_lock);
 		c->mfc_parent = mfc->mfcc_parent;
-		ipmr_update_thresholds(c, mfc->mfcc_ttls);
+		ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls);
 		if (!mrtsock)
 			c->mfc_flags |= MFC_STATIC;
 		write_unlock_bh(&mrt_lock);
@@ -829,43 +1075,42 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
 	if (!ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr))
 		return -EINVAL;
 
-	c = ipmr_cache_alloc(net);
+	c = ipmr_cache_alloc();
 	if (c == NULL)
 		return -ENOMEM;
 
 	c->mfc_origin = mfc->mfcc_origin.s_addr;
 	c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr;
 	c->mfc_parent = mfc->mfcc_parent;
-	ipmr_update_thresholds(c, mfc->mfcc_ttls);
+	ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls);
 	if (!mrtsock)
 		c->mfc_flags |= MFC_STATIC;
 
 	write_lock_bh(&mrt_lock);
-	c->next = net->ipv4.mfc_cache_array[line];
-	net->ipv4.mfc_cache_array[line] = c;
+	list_add(&c->list, &mrt->mfc_cache_array[line]);
 	write_unlock_bh(&mrt_lock);
 
 	/*
 	 *	Check to see if we resolved a queued list. If so we
 	 *	need to send on the frames and tidy up.
 	 */
+	found = false;
 	spin_lock_bh(&mfc_unres_lock);
-	for (cp = &mfc_unres_queue; (uc=*cp) != NULL;
-	     cp = &uc->next) {
-		if (net_eq(mfc_net(uc), net) &&
-		    uc->mfc_origin == c->mfc_origin &&
+	list_for_each_entry(uc, &mrt->mfc_unres_queue, list) {
+		if (uc->mfc_origin == c->mfc_origin &&
 		    uc->mfc_mcastgrp == c->mfc_mcastgrp) {
-			*cp = uc->next;
-			atomic_dec(&net->ipv4.cache_resolve_queue_len);
+			list_del(&uc->list);
+			atomic_dec(&mrt->cache_resolve_queue_len);
+			found = true;
 			break;
 		}
 	}
-	if (mfc_unres_queue == NULL)
-		del_timer(&ipmr_expire_timer);
+	if (list_empty(&mrt->mfc_unres_queue))
+		del_timer(&mrt->ipmr_expire_timer);
 	spin_unlock_bh(&mfc_unres_lock);
 
-	if (uc) {
-		ipmr_cache_resolve(uc, c);
+	if (found) {
+		ipmr_cache_resolve(net, mrt, uc, c);
 		ipmr_cache_free(uc);
 	}
 	return 0;
@@ -875,53 +1120,41 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct net *net)
+static void mroute_clean_tables(struct mr_table *mrt)
 {
 	int i;
 	LIST_HEAD(list);
+	struct mfc_cache *c, *next;
 
 	/*
 	 *	Shut down all active vif entries
 	 */
-	for (i = 0; i < net->ipv4.maxvif; i++) {
-		if (!(net->ipv4.vif_table[i].flags&VIFF_STATIC))
-			vif_delete(net, i, 0, &list);
+	for (i = 0; i < mrt->maxvif; i++) {
+		if (!(mrt->vif_table[i].flags&VIFF_STATIC))
+			vif_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
 	/*
 	 *	Wipe the cache
 	 */
-	for (i=0; i<MFC_LINES; i++) {
-		struct mfc_cache *c, **cp;
-
-		cp = &net->ipv4.mfc_cache_array[i];
-		while ((c = *cp) != NULL) {
-			if (c->mfc_flags&MFC_STATIC) {
-				cp = &c->next;
+	for (i = 0; i < MFC_LINES; i++) {
+		list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
+			if (c->mfc_flags&MFC_STATIC)
 				continue;
-			}
 			write_lock_bh(&mrt_lock);
-			*cp = c->next;
+			list_del(&c->list);
 			write_unlock_bh(&mrt_lock);
 
 			ipmr_cache_free(c);
 		}
 	}
 
-	if (atomic_read(&net->ipv4.cache_resolve_queue_len) != 0) {
-		struct mfc_cache *c, **cp;
-
+	if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
 		spin_lock_bh(&mfc_unres_lock);
-		cp = &mfc_unres_queue;
-		while ((c = *cp) != NULL) {
-			if (!net_eq(mfc_net(c), net)) {
-				cp = &c->next;
-				continue;
-			}
-			*cp = c->next;
-
-			ipmr_destroy_unres(c);
+		list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) {
+			list_del(&c->list);
+			ipmr_destroy_unres(mrt, c);
 		}
 		spin_unlock_bh(&mfc_unres_lock);
 	}
@@ -930,16 +1163,19 @@ static void mroute_clean_tables(struct net *net)
 static void mrtsock_destruct(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
+	struct mr_table *mrt;
 
 	rtnl_lock();
-	if (sk == net->ipv4.mroute_sk) {
-		IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
+	ipmr_for_each_table(mrt, net) {
+		if (sk == mrt->mroute_sk) {
+			IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
 
-		write_lock_bh(&mrt_lock);
-		net->ipv4.mroute_sk = NULL;
-		write_unlock_bh(&mrt_lock);
+			write_lock_bh(&mrt_lock);
+			mrt->mroute_sk = NULL;
+			write_unlock_bh(&mrt_lock);
 
-		mroute_clean_tables(net);
+			mroute_clean_tables(mrt);
+		}
 	}
 	rtnl_unlock();
 }
@@ -957,9 +1193,14 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 	struct vifctl vif;
 	struct mfcctl mfc;
 	struct net *net = sock_net(sk);
+	struct mr_table *mrt;
+
+	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
+	if (mrt == NULL)
+		return -ENOENT;
 
 	if (optname != MRT_INIT) {
-		if (sk != net->ipv4.mroute_sk && !capable(CAP_NET_ADMIN))
+		if (sk != mrt->mroute_sk && !capable(CAP_NET_ADMIN))
 			return -EACCES;
 	}
 
@@ -972,7 +1213,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 			return -ENOPROTOOPT;
 
 		rtnl_lock();
-		if (net->ipv4.mroute_sk) {
+		if (mrt->mroute_sk) {
 			rtnl_unlock();
 			return -EADDRINUSE;
 		}
@@ -980,7 +1221,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 		ret = ip_ra_control(sk, 1, mrtsock_destruct);
 		if (ret == 0) {
 			write_lock_bh(&mrt_lock);
-			net->ipv4.mroute_sk = sk;
+			mrt->mroute_sk = sk;
 			write_unlock_bh(&mrt_lock);
 
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)++;
@@ -988,7 +1229,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 		rtnl_unlock();
 		return ret;
 	case MRT_DONE:
-		if (sk != net->ipv4.mroute_sk)
+		if (sk != mrt->mroute_sk)
 			return -EACCES;
 		return ip_ra_control(sk, 0, NULL);
 	case MRT_ADD_VIF:
@@ -1001,9 +1242,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 			return -ENFILE;
 		rtnl_lock();
 		if (optname == MRT_ADD_VIF) {
-			ret = vif_add(net, &vif, sk == net->ipv4.mroute_sk);
+			ret = vif_add(net, mrt, &vif, sk == mrt->mroute_sk);
 		} else {
-			ret = vif_delete(net, vif.vifc_vifi, 0, NULL);
+			ret = vif_delete(mrt, vif.vifc_vifi, 0, NULL);
 		}
 		rtnl_unlock();
 		return ret;
@@ -1020,9 +1261,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 			return -EFAULT;
 		rtnl_lock();
 		if (optname == MRT_DEL_MFC)
-			ret = ipmr_mfc_delete(net, &mfc);
+			ret = ipmr_mfc_delete(mrt, &mfc);
 		else
-			ret = ipmr_mfc_add(net, &mfc, sk == net->ipv4.mroute_sk);
+			ret = ipmr_mfc_add(net, mrt, &mfc, sk == mrt->mroute_sk);
 		rtnl_unlock();
 		return ret;
 		/*
@@ -1033,7 +1274,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 		int v;
 		if (get_user(v,(int __user *)optval))
 			return -EFAULT;
-		net->ipv4.mroute_do_assert = (v) ? 1 : 0;
+		mrt->mroute_do_assert = (v) ? 1 : 0;
 		return 0;
 	}
 #ifdef CONFIG_IP_PIMSM
@@ -1047,14 +1288,35 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
 
 		rtnl_lock();
 		ret = 0;
-		if (v != net->ipv4.mroute_do_pim) {
-			net->ipv4.mroute_do_pim = v;
-			net->ipv4.mroute_do_assert = v;
+		if (v != mrt->mroute_do_pim) {
+			mrt->mroute_do_pim = v;
+			mrt->mroute_do_assert = v;
 		}
 		rtnl_unlock();
 		return ret;
 	}
 #endif
+#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
+	case MRT_TABLE:
+	{
+		u32 v;
+
+		if (optlen != sizeof(u32))
+			return -EINVAL;
+		if (get_user(v, (u32 __user *)optval))
+			return -EFAULT;
+		if (sk == mrt->mroute_sk)
+			return -EBUSY;
+
+		rtnl_lock();
+		ret = 0;
+		if (!ipmr_new_table(net, v))
+			ret = -ENOMEM;
+		raw_sk(sk)->ipmr_table = v;
+		rtnl_unlock();
+		return ret;
+	}
+#endif
 	/*
 	 *	Spurious command, or MRT_VERSION which you cannot
 	 *	set.
@@ -1073,6 +1335,11 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
 	int olr;
 	int val;
 	struct net *net = sock_net(sk);
+	struct mr_table *mrt;
+
+	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
+	if (mrt == NULL)
+		return -ENOENT;
 
 	if (optname != MRT_VERSION &&
 #ifdef CONFIG_IP_PIMSM
@@ -1094,10 +1361,10 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int
 		val = 0x0305;
 #ifdef CONFIG_IP_PIMSM
 	else if (optname == MRT_PIM)
-		val = net->ipv4.mroute_do_pim;
+		val = mrt->mroute_do_pim;
 #endif
 	else
-		val = net->ipv4.mroute_do_assert;
+		val = mrt->mroute_do_assert;
 	if (copy_to_user(optval, &val, olr))
 		return -EFAULT;
 	return 0;
@@ -1114,16 +1381,21 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
 	struct vif_device *vif;
 	struct mfc_cache *c;
 	struct net *net = sock_net(sk);
+	struct mr_table *mrt;
+
+	mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
+	if (mrt == NULL)
+		return -ENOENT;
 
 	switch (cmd) {
 	case SIOCGETVIFCNT:
 		if (copy_from_user(&vr, arg, sizeof(vr)))
 			return -EFAULT;
-		if (vr.vifi >= net->ipv4.maxvif)
+		if (vr.vifi >= mrt->maxvif)
 			return -EINVAL;
 		read_lock(&mrt_lock);
-		vif = &net->ipv4.vif_table[vr.vifi];
-		if (VIF_EXISTS(net, vr.vifi)) {
+		vif = &mrt->vif_table[vr.vifi];
+		if (VIF_EXISTS(mrt, vr.vifi)) {
 			vr.icount = vif->pkt_in;
 			vr.ocount = vif->pkt_out;
 			vr.ibytes = vif->bytes_in;
@@ -1141,7 +1413,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
 			return -EFAULT;
 
 		read_lock(&mrt_lock);
-		c = ipmr_cache_find(net, sr.src.s_addr, sr.grp.s_addr);
+		c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr);
 		if (c) {
 			sr.pktcnt = c->mfc_un.res.pkt;
 			sr.bytecnt = c->mfc_un.res.bytes;
@@ -1164,16 +1436,20 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v
 {
 	struct net_device *dev = ptr;
 	struct net *net = dev_net(dev);
+	struct mr_table *mrt;
 	struct vif_device *v;
 	int ct;
 	LIST_HEAD(list);
 
 	if (event != NETDEV_UNREGISTER)
 		return NOTIFY_DONE;
-	v = &net->ipv4.vif_table[0];
-	for (ct = 0; ct < net->ipv4.maxvif; ct++, v++) {
-		if (v->dev == dev)
-			vif_delete(net, ct, 1, &list);
+
+	ipmr_for_each_table(mrt, net) {
+		v = &mrt->vif_table[0];
+		for (ct = 0; ct < mrt->maxvif; ct++, v++) {
+			if (v->dev == dev)
+				vif_delete(mrt, ct, 1, &list);
+		}
 	}
 	unregister_netdevice_many(&list);
 	retu