Merge tag 'v3.9-rc5' into wq/for-3.10

Writeback conversion to workqueue will be based on top of wq/for-3.10
branch to take advantage of custom attrs and NUMA support for unbound
workqueues.  Mainline currently contains two commits which result in
non-trivial merge conflicts with wq/for-3.10 and because
block/for-3.10/core is based on v3.9-rc3 which contains one of the
conflicting commits, we need a pre-merge-window merge anyway.  Let's
pull v3.9-rc5 into wq/for-3.10 so that the block tree doesn't suffer
from workqueue merge conflicts.

The two conflicts and their resolutions:

* e68035fb65 ("workqueue: convert to idr_alloc()") in mainline changes
  worker_pool_assign_id() to use idr_alloc() instead of the old idr
  interface.  worker_pool_assign_id() goes through multiple locking
  changes in wq/for-3.10 causing the following conflict.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

  <<<<<<< HEAD
	  lockdep_assert_held(&wq_pool_mutex);

	  do {
		  if (!idr_pre_get(&worker_pool_idr, GFP_KERNEL))
			  return -ENOMEM;
		  ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
	  } while (ret == -EAGAIN);
  =======
	  mutex_lock(&worker_pool_idr_mutex);
	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0)
		  pool->id = ret;
	  mutex_unlock(&worker_pool_idr_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

	  return ret < 0 ? ret : 0;
  }

  We want locking from the former and idr_alloc() usage from the
  latter, which can be combined to the following.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

	  lockdep_assert_held(&wq_pool_mutex);

	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0) {
		  pool->id = ret;
		  return 0;
	  }
	  return ret;
   }

* eb2834285c ("workqueue: fix possible pool stall bug in
  wq_unbind_fn()") updated wq_unbind_fn() such that it has single
  larger for_each_std_worker_pool() loop instead of two separate loops
  with a schedule() call inbetween.  wq/for-3.10 renamed
  pool->assoc_mutex to pool->manager_mutex causing the following
  conflict (earlier function body and comments omitted for brevity).

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
  <<<<<<< HEAD
		  mutex_unlock(&pool->manager_mutex);
	  }
  =======
		  mutex_unlock(&pool->assoc_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

		  schedule();

  <<<<<<< HEAD
	  for_each_cpu_worker_pool(pool, cpu)
  =======
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89
		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

  The resolution is mostly trivial.  We want the control flow of the
  latter with the rename of the former.

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
		  mutex_unlock(&pool->manager_mutex);

		  schedule();

		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

Signed-off-by: Tejun Heo <tj@kernel.org>

8 files changed, 47 insertions, 28 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f2c7e61..26512250 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4784,26 +4784,20 @@ static void addrconf_sysctl_unregister(struct inet6_dev *idev)
 
 static int __net_init addrconf_init_net(struct net *net)
 {
-	int err;
+	int err = -ENOMEM;
 	struct ipv6_devconf *all, *dflt;
 
-	err = -ENOMEM;
-	all = &ipv6_devconf;
-	dflt = &ipv6_devconf_dflt;
+	all = kmemdup(&ipv6_devconf, sizeof(ipv6_devconf), GFP_KERNEL);
+	if (all == NULL)
+		goto err_alloc_all;
 
-	if (!net_eq(net, &init_net)) {
-		all = kmemdup(all, sizeof(ipv6_devconf), GFP_KERNEL);
-		if (all == NULL)
-			goto err_alloc_all;
+	dflt = kmemdup(&ipv6_devconf_dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL);
+	if (dflt == NULL)
+		goto err_alloc_dflt;
 
-		dflt = kmemdup(dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL);
-		if (dflt == NULL)
-			goto err_alloc_dflt;
-	} else {
-		/* these will be inherited by all namespaces */
-		dflt->autoconf = ipv6_defaults.autoconf;
-		dflt->disable_ipv6 = ipv6_defaults.disable_ipv6;
-	}
+	/* these will be inherited by all namespaces */
+	dflt->autoconf = ipv6_defaults.autoconf;
+	dflt->disable_ipv6 = ipv6_defaults.disable_ipv6;
 
 	net->ipv6.devconf_all = all;
 	net->ipv6.devconf_dflt = dflt;
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 5b10414..e33fe0a 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -241,9 +241,11 @@ resubmit:
 				icmpv6_send(skb, ICMPV6_PARAMPROB,
 					    ICMPV6_UNK_NEXTHDR, nhoff);
 			}
-		} else
+			kfree_skb(skb);
+		} else {
 			IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS);
-		kfree_skb(skb);
+			consume_skb(skb);
+		}
 	}
 	rcu_read_unlock();
 	return 0;
@@ -279,7 +281,8 @@ int ip6_mc_input(struct sk_buff *skb)
 	 *      IPv6 multicast router mode is now supported ;)
 	 */
 	if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
-	    !(ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) &&
+	    !(ipv6_addr_type(&hdr->daddr) &
+	      (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) &&
 	    likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
 		/*
 		 * Okay, we try to forward - split and duplicate
diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c
index 83acc14..33608c6 100644
--- a/net/ipv6/netfilter/ip6t_NPT.c
+++ b/net/ipv6/netfilter/ip6t_NPT.c
@@ -114,6 +114,7 @@ ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par)
 static struct xt_target ip6t_npt_target_reg[] __read_mostly = {
 	{
 		.name		= "SNPT",
+		.table		= "mangle",
 		.target		= ip6t_snpt_tg,
 		.targetsize	= sizeof(struct ip6t_npt_tginfo),
 		.checkentry	= ip6t_npt_checkentry,
@@ -124,6 +125,7 @@ static struct xt_target ip6t_npt_target_reg[] __read_mostly = {
 	},
 	{
 		.name		= "DNPT",
+		.table		= "mangle",
 		.target		= ip6t_dnpt_tg,
 		.targetsize	= sizeof(struct ip6t_npt_tginfo),
 		.checkentry	= ip6t_npt_checkentry,
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 54087e9..6700069 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -14,6 +14,8 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) "IPv6-nf: " fmt
+
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -180,13 +182,11 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 
 	q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
 	local_bh_enable();
-	if (q == NULL)
-		goto oom;
-
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
+		return NULL;
+	}
 	return container_of(q, struct frag_queue, q);
-
-oom:
-	return NULL;
 }
 
 
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 3c6a772..196ab93 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -26,6 +26,9 @@
  *	YOSHIFUJI,H. @USAGI	Always remove fragment header to
  *				calculate ICV correctly.
  */
+
+#define pr_fmt(fmt) "IPv6: " fmt
+
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -185,9 +188,10 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6
 	hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd);
 
 	q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
-	if (q == NULL)
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
 		return NULL;
-
+	}
 	return container_of(q, struct frag_queue, q);
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9282665..e5fe004 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1915,7 +1915,8 @@ void rt6_purge_dflt_routers(struct net *net)
 restart:
 	read_lock_bh(&table->tb6_lock);
 	for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
-		if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) {
+		if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
+		    (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
 			dst_hold(&rt->dst);
 			read_unlock_bh(&table->tb6_lock);
 			ip6_del_rt(rt);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9b64600..f6d629f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -389,6 +389,13 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	}
 
 	if (type == ICMPV6_PKT_TOOBIG) {
+		/* We are not interested in TCP_LISTEN and open_requests
+		 * (SYN-ACKs send out by Linux are always <576bytes so
+		 * they should go through unfragmented).
+		 */
+		if (sk->sk_state == TCP_LISTEN)
+			goto out;
+
 		tp->mtu_info = ntohl(info);
 		if (!sock_owned_by_user(sk))
 			tcp_v6_mtu_reduced(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 599e1ba6..d8e5e85 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1285,10 +1285,18 @@ do_confirm:
 
 void udpv6_destroy_sock(struct sock *sk)
 {
+	struct udp_sock *up = udp_sk(sk);
 	lock_sock(sk);
 	udp_v6_flush_pending_frames(sk);
 	release_sock(sk);
 
+	if (static_key_false(&udpv6_encap_needed) && up->encap_type) {
+		void (*encap_destroy)(struct sock *sk);
+		encap_destroy = ACCESS_ONCE(up->encap_destroy);
+		if (encap_destroy)
+			encap_destroy(sk);
+	}
+
 	inet6_destroy_sock(sk);
 }