Merge branch 'ipv6-loopback'

Eric Dumazet says:

====================
ipv6: remove addrconf reliance on loopback

Second patch in this series removes IPv6 requirement about the netns
loopback device being the last device being dismantled.

This was needed because rt6_uncached_list_flush_dev()
and ip6_dst_ifdown() had to switch dst dev to a known
device (loopback).

Instead of loopback, we can use the (hidden) blackhole_netdev
which is also always there.

This will allow future simplfications of netdev_run_to()
and other parts of the stack like default_device_exit_batch().

Last two patches are optimizations for both IP families.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 64 insertions, 72 deletions

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 40ae8f1b18e5..32c83bb68879 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -367,9 +367,8 @@ struct rt6_statistics {
 	__u32		fib_rt_cache;		/* cached rt entries in exception table */
 	__u32		fib_discarded_routes;	/* total number of routes delete */
 
-	/* The following stats are not protected by any lock */
+	/* The following stat is not protected by any lock */
 	atomic_t	fib_rt_alloc;		/* total number of routes alloced */
-	atomic_t	fib_rt_uncache;		/* rt entries in uncached list */
 };
 
 #define RTN_TL_ROOT	0x0001
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 634766e6c7cc..202d6b1fff43 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1485,6 +1485,7 @@ static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt)
 struct uncached_list {
 	spinlock_t		lock;
 	struct list_head	head;
+	struct list_head	quarantine;
 };
 
 static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list);
@@ -1506,7 +1507,7 @@ void rt_del_uncached_list(struct rtable *rt)
 		struct uncached_list *ul = rt->rt_uncached_list;
 
 		spin_lock_bh(&ul->lock);
-		list_del(&rt->rt_uncached);
+		list_del_init(&rt->rt_uncached);
 		spin_unlock_bh(&ul->lock);
 	}
 }
@@ -1521,20 +1522,24 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
 
 void rt_flush_dev(struct net_device *dev)
 {
-	struct rtable *rt;
+	struct rtable *rt, *safe;
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
 		struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
 
+		if (list_empty(&ul->head))
+			continue;
+
 		spin_lock_bh(&ul->lock);
-		list_for_each_entry(rt, &ul->head, rt_uncached) {
+		list_for_each_entry_safe(rt, safe, &ul->head, rt_uncached) {
 			if (rt->dst.dev != dev)
 				continue;
 			rt->dst.dev = blackhole_netdev;
 			dev_replace_track(dev, blackhole_netdev,
 					  &rt->dst.dev_tracker,
 					  GFP_ATOMIC);
+			list_move(&rt->rt_uncached, &ul->quarantine);
 		}
 		spin_unlock_bh(&ul->lock);
 	}
@@ -3706,6 +3711,7 @@ int __init ip_rt_init(void)
 		struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
 
 		INIT_LIST_HEAD(&ul->head);
+		INIT_LIST_HEAD(&ul->quarantine);
 		spin_lock_init(&ul->lock);
 	}
 #ifdef CONFIG_IP_ROUTE_CLASSID
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4f402bc38f05..02d31d4fcab3 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -372,7 +372,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 
 	ASSERT_RTNL();
 
-	if (dev->mtu < IPV6_MIN_MTU)
+	if (dev->mtu < IPV6_MIN_MTU && dev != blackhole_netdev)
 		return ERR_PTR(-EINVAL);
 
 	ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL);
@@ -400,21 +400,22 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	/* We refer to the device */
 	dev_hold_track(dev, &ndev->dev_tracker, GFP_KERNEL);
 
-	if (snmp6_alloc_dev(ndev) < 0) {
-		netdev_dbg(dev, "%s: cannot allocate memory for statistics\n",
-			   __func__);
-		neigh_parms_release(&nd_tbl, ndev->nd_parms);
-		dev_put_track(dev, &ndev->dev_tracker);
-		kfree(ndev);
-		return ERR_PTR(err);
-	}
+	if (dev != blackhole_netdev) {
+		if (snmp6_alloc_dev(ndev) < 0) {
+			netdev_dbg(dev, "%s: cannot allocate memory for statistics\n",
+				   __func__);
+			neigh_parms_release(&nd_tbl, ndev->nd_parms);
+			dev_put_track(dev, &ndev->dev_tracker);
+			kfree(ndev);
+			return ERR_PTR(err);
+		}
 
-	if (snmp6_register_dev(ndev) < 0) {
-		netdev_dbg(dev, "%s: cannot create /proc/net/dev_snmp6/%s\n",
-			   __func__, dev->name);
-		goto err_release;
+		if (snmp6_register_dev(ndev) < 0) {
+			netdev_dbg(dev, "%s: cannot create /proc/net/dev_snmp6/%s\n",
+				   __func__, dev->name);
+			goto err_release;
+		}
 	}
-
 	/* One reference from device. */
 	refcount_set(&ndev->refcnt, 1);
 
@@ -445,25 +446,28 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 
 	ipv6_mc_init_dev(ndev);
 	ndev->tstamp = jiffies;
-	err = addrconf_sysctl_register(ndev);
-	if (err) {
-		ipv6_mc_destroy_dev(ndev);
-		snmp6_unregister_dev(ndev);
-		goto err_release;
+	if (dev != blackhole_netdev) {
+		err = addrconf_sysctl_register(ndev);
+		if (err) {
+			ipv6_mc_destroy_dev(ndev);
+			snmp6_unregister_dev(ndev);
+			goto err_release;
+		}
 	}
 	/* protected by rtnl_lock */
 	rcu_assign_pointer(dev->ip6_ptr, ndev);
 
-	/* Join interface-local all-node multicast group */
-	ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allnodes);
+	if (dev != blackhole_netdev) {
+		/* Join interface-local all-node multicast group */
+		ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allnodes);
 
-	/* Join all-node multicast group */
-	ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes);
-
-	/* Join all-router multicast group if forwarding is set */
-	if (ndev->cnf.forwarding && (dev->flags & IFF_MULTICAST))
-		ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters);
+		/* Join all-node multicast group */
+		ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes);
 
+		/* Join all-router multicast group if forwarding is set */
+		if (ndev->cnf.forwarding && (dev->flags & IFF_MULTICAST))
+			ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters);
+	}
 	return ndev;
 
 err_release:
@@ -7233,26 +7237,8 @@ int __init addrconf_init(void)
 		goto out_nowq;
 	}
 
-	/* The addrconf netdev notifier requires that loopback_dev
-	 * has it's ipv6 private information allocated and setup
-	 * before it can bring up and give link-local addresses
-	 * to other devices which are up.
-	 *
-	 * Unfortunately, loopback_dev is not necessarily the first
-	 * entry in the global dev_base list of net devices.  In fact,
-	 * it is likely to be the very last entry on that list.
-	 * So this causes the notifier registry below to try and
-	 * give link-local addresses to all devices besides loopback_dev
-	 * first, then loopback_dev, which cases all the non-loopback_dev
-	 * devices to fail to get a link-local address.
-	 *
-	 * So, as a temporary fix, allocate the ipv6 structure for
-	 * loopback_dev first by hand.
-	 * Longer term, all of the dependencies ipv6 has upon the loopback
-	 * device and it being up should be removed.
-	 */
 	rtnl_lock();
-	idev = ipv6_add_dev(init_net.loopback_dev);
+	idev = ipv6_add_dev(blackhole_netdev);
 	rtnl_unlock();
 	if (IS_ERR(idev)) {
 		err = PTR_ERR(idev);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index dd98a11fbdb6..46c7a1b36075 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -130,6 +130,7 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
 struct uncached_list {
 	spinlock_t		lock;
 	struct list_head	head;
+	struct list_head	quarantine;
 };
 
 static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list);
@@ -149,35 +150,34 @@ void rt6_uncached_list_del(struct rt6_info *rt)
 {
 	if (!list_empty(&rt->rt6i_uncached)) {
 		struct uncached_list *ul = rt->rt6i_uncached_list;
-		struct net *net = dev_net(rt->dst.dev);
 
 		spin_lock_bh(&ul->lock);
-		list_del(&rt->rt6i_uncached);
-		atomic_dec(&net->ipv6.rt6_stats->fib_rt_uncache);
+		list_del_init(&rt->rt6i_uncached);
 		spin_unlock_bh(&ul->lock);
 	}
 }
 
-static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
+static void rt6_uncached_list_flush_dev(struct net_device *dev)
 {
-	struct net_device *loopback_dev = net->loopback_dev;
 	int cpu;
 
-	if (dev == loopback_dev)
-		return;
-
 	for_each_possible_cpu(cpu) {
 		struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
-		struct rt6_info *rt;
+		struct rt6_info *rt, *safe;
+
+		if (list_empty(&ul->head))
+			continue;
 
 		spin_lock_bh(&ul->lock);
-		list_for_each_entry(rt, &ul->head, rt6i_uncached) {
+		list_for_each_entry_safe(rt, safe, &ul->head, rt6i_uncached) {
 			struct inet6_dev *rt_idev = rt->rt6i_idev;
 			struct net_device *rt_dev = rt->dst.dev;
+			bool handled = false;
 
 			if (rt_idev->dev == dev) {
-				rt->rt6i_idev = in6_dev_get(loopback_dev);
+				rt->rt6i_idev = in6_dev_get(blackhole_netdev);
 				in6_dev_put(rt_idev);
+				handled = true;
 			}
 
 			if (rt_dev == dev) {
@@ -185,7 +185,11 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
 				dev_replace_track(rt_dev, blackhole_netdev,
 						  &rt->dst.dev_tracker,
 						  GFP_ATOMIC);
+				handled = true;
 			}
+			if (handled)
+				list_move(&rt->rt6i_uncached,
+					  &ul->quarantine);
 		}
 		spin_unlock_bh(&ul->lock);
 	}
@@ -373,13 +377,12 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 {
 	struct rt6_info *rt = (struct rt6_info *)dst;
 	struct inet6_dev *idev = rt->rt6i_idev;
-	struct net_device *loopback_dev =
-		dev_net(dev)->loopback_dev;
 
-	if (idev && idev->dev != loopback_dev) {
-		struct inet6_dev *loopback_idev = in6_dev_get(loopback_dev);
-		if (loopback_idev) {
-			rt->rt6i_idev = loopback_idev;
+	if (idev && idev->dev != blackhole_netdev) {
+		struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev);
+
+		if (blackhole_idev) {
+			rt->rt6i_idev = blackhole_idev;
 			in6_dev_put(idev);
 		}
 	}
@@ -2244,7 +2247,6 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 			 * if caller sets RT6_LOOKUP_F_DST_NOREF flag.
 			 */
 			rt6_uncached_list_add(rt);
-			atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache);
 			rcu_read_unlock();
 
 			return rt;
@@ -3287,7 +3289,6 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	 * do proper release of the net_device
 	 */
 	rt6_uncached_list_add(rt);
-	atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache);
 
 	dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0);
 
@@ -4896,7 +4897,7 @@ void rt6_sync_down_dev(struct net_device *dev, unsigned long event)
 void rt6_disable_ip(struct net_device *dev, unsigned long event)
 {
 	rt6_sync_down_dev(dev, event);
-	rt6_uncached_list_flush_dev(dev_net(dev), dev);
+	rt6_uncached_list_flush_dev(dev);
 	neigh_ifdown(&nd_tbl, dev);
 }
 
@@ -6736,6 +6737,7 @@ int __init ip6_route_init(void)
 		struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
 
 		INIT_LIST_HEAD(&ul->head);
+		INIT_LIST_HEAD(&ul->quarantine);
 		spin_lock_init(&ul->lock);
 	}
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index fad687ee6dd8..55bb2cbae13d 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -92,7 +92,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	xdst->u.rt6.rt6i_src = rt->rt6i_src;
 	INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached);
 	rt6_uncached_list_add(&xdst->u.rt6);
-	atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache);
 
 	return 0;
 }