Merge branch 'v2.6.36-rc8' into for-2.6.37/barrier

Conflicts:
	block/blk-core.c
	drivers/block/loop.c
	mm/swapfile.c

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

10 files changed, 119 insertions, 149 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ab70a3fbcafa..324fac3b6c16 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4637,10 +4637,12 @@ int __init addrconf_init(void)
         if (err < 0) {
                 printk(KERN_CRIT "IPv6 Addrconf:"
                        " cannot initialize default policy table: %d.\n", err);
-                return err;
+                goto out;
         }
 
-        register_pernet_subsys(&addrconf_ops);
+        err = register_pernet_subsys(&addrconf_ops);
+        if (err < 0)
+                goto out_addrlabel;
 
         /* The addrconf netdev notifier requires that loopback_dev
          * has it's ipv6 private information allocated and setup
@@ -4692,7 +4694,9 @@ errout:
         unregister_netdevice_notifier(&ipv6_dev_notf);
 errlo:
         unregister_pernet_subsys(&addrconf_ops);
-
+out_addrlabel:
+        ipv6_addr_label_cleanup();
+out:
         return err;
 }
 
@@ -4703,6 +4707,7 @@ void addrconf_cleanup(void)
 
         unregister_netdevice_notifier(&ipv6_dev_notf);
         unregister_pernet_subsys(&addrconf_ops);
+        ipv6_addr_label_cleanup();
 
         rtnl_lock();
 
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index f0e774cea386..8175f802651b 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -393,6 +393,11 @@ int __init ipv6_addr_label_init(void)
         return register_pernet_subsys(&ipv6_addr_label_ops);
 }
 
+void ipv6_addr_label_cleanup(void)
+{
+        unregister_pernet_subsys(&ipv6_addr_label_ops);
+}
+
 static const struct nla_policy ifal_policy[IFAL_MAX+1] = {
         [IFAL_ADDRESS]          = { .len = sizeof(struct in6_addr), },
         [IFAL_LABEL]            = { .len = sizeof(u32), },
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 7d929a22cbc2..ef371aa01ac5 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -105,9 +105,12 @@ ipv4_connected:
                 if (ipv6_addr_any(&np->saddr))
                         ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
 
-                if (ipv6_addr_any(&np->rcv_saddr))
+                if (ipv6_addr_any(&np->rcv_saddr)) {
                         ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
                                                &np->rcv_saddr);
+                        if (sk->sk_prot->rehash)
+                                sk->sk_prot->rehash(sk);
+                }
 
                 goto out;
         }
@@ -181,6 +184,8 @@ ipv4_connected:
         if (ipv6_addr_any(&np->rcv_saddr)) {
                 ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src);
                 inet->inet_rcv_saddr = LOOPBACK4_IPV6;
+                if (sk->sk_prot->rehash)
+                        sk->sk_prot->rehash(sk);
         }
 
         ip6_dst_store(sk, dst,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d40b330c0ee6..980912ed7a38 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -639,7 +639,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
         if (skb_has_frags(skb)) {
                 int first_len = skb_pagelen(skb);
-                int truesizes = 0;
+                struct sk_buff *frag2;
 
                 if (first_len - hlen > mtu ||
                     ((first_len - hlen) & 7) ||
@@ -651,18 +651,18 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
                         if (frag->len > mtu ||
                             ((frag->len & 7) && frag->next) ||
                             skb_headroom(frag) < hlen)
-                            goto slow_path;
+                                goto slow_path_clean;
 
                         /* Partially cloned skb? */
                         if (skb_shared(frag))
-                                goto slow_path;
+                                goto slow_path_clean;
 
                         BUG_ON(frag->sk);
                         if (skb->sk) {
                                 frag->sk = skb->sk;
                                 frag->destructor = sock_wfree;
-                                truesizes += frag->truesize;
                         }
+                        skb->truesize -= frag->truesize;
                 }
 
                 err = 0;
@@ -693,7 +693,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
                 first_len = skb_pagelen(skb);
                 skb->data_len = first_len - skb_headlen(skb);
-                skb->truesize -= truesizes;
                 skb->len = first_len;
                 ipv6_hdr(skb)->payload_len = htons(first_len -
                                                    sizeof(struct ipv6hdr));
@@ -756,6 +755,15 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
                               IPSTATS_MIB_FRAGFAILS);
                 dst_release(&rt->dst);
                 return err;
+
+slow_path_clean:
+                skb_walk_frags(skb, frag2) {
+                        if (frag2 == frag)
+                                break;
+                        frag2->sk = NULL;
+                        frag2->destructor = NULL;
+                        skb->truesize += frag2->truesize;
+                }
         }
 
 slow_path:
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 29a7bca29e3f..8e754be92c24 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1766,6 +1766,9 @@ translate_compat_table(struct net *net,
                 if (ret != 0)
                         break;
                 ++i;
+                if (strcmp(ip6t_get_target(iter1)->u.user.name,
+                    XT_ERROR_TARGET) == 0)
+                        ++newinfo->stacksize;
         }
         if (ret) {
                 /*
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 13ef5bc05cf5..578f3c1a16db 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -113,14 +113,6 @@ static void nf_skb_free(struct sk_buff *skb)
                 kfree_skb(NFCT_FRAG6_CB(skb)->orig);
 }
 
-/* Memory Tracking Functions. */
-static void frag_kfree_skb(struct sk_buff *skb)
-{
-        atomic_sub(skb->truesize, &nf_init_frags.mem);
-        nf_skb_free(skb);
-        kfree_skb(skb);
-}
-
 /* Destruction primitives. */
 
 static __inline__ void fq_put(struct nf_ct_frag6_queue *fq)
@@ -282,66 +274,22 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
         }
 
 found:
-        /* We found where to put this one.  Check for overlap with
-         * preceding fragment, and, if needed, align things so that
-         * any overlaps are eliminated.
-         */
-        if (prev) {
-                int i = (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset;
-
-                if (i > 0) {
-                        offset += i;
-                        if (end <= offset) {
-                                pr_debug("overlap\n");
-                                goto err;
-                        }
-                        if (!pskb_pull(skb, i)) {
-                                pr_debug("Can't pull\n");
-                                goto err;
-                        }
-                        if (skb->ip_summed != CHECKSUM_UNNECESSARY)
-                                skb->ip_summed = CHECKSUM_NONE;
-                }
-        }
-
-        /* Look for overlap with succeeding segments.
-         * If we can merge fragments, do it.
+        /* RFC5722, Section 4:
+         *                                  When reassembling an IPv6 datagram, if
+         *   one or more its constituent fragments is determined to be an
+         *   overlapping fragment, the entire datagram (and any constituent
+         *   fragments, including those not yet received) MUST be silently
+         *   discarded.
          */
-        while (next && NFCT_FRAG6_CB(next)->offset < end) {
-                /* overlap is 'i' bytes */
-                int i = end - NFCT_FRAG6_CB(next)->offset;
-
-                if (i < next->len) {
-                        /* Eat head of the next overlapped fragment
-                         * and leave the loop. The next ones cannot overlap.
-                         */
-                        pr_debug("Eat head of the overlapped parts.: %d", i);
-                        if (!pskb_pull(next, i))
-                                goto err;
 
-                        /* next fragment */
-                        NFCT_FRAG6_CB(next)->offset += i;
-                        fq->q.meat -= i;
-                        if (next->ip_summed != CHECKSUM_UNNECESSARY)
-                                next->ip_summed = CHECKSUM_NONE;
-                        break;
-                } else {
-                        struct sk_buff *free_it = next;
-
-                        /* Old fragmnet is completely overridden with
-                         * new one drop it.
-                         */
-                        next = next->next;
+        /* Check for overlap with preceding fragment. */
+        if (prev &&
+            (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset > 0)
+                goto discard_fq;
 
-                        if (prev)
-                                prev->next = next;
-                        else
-                                fq->q.fragments = next;
-
-                        fq->q.meat -= free_it->len;
-                        frag_kfree_skb(free_it);
-                }
-        }
+        /* Look for overlap with succeeding segment. */
+        if (next && NFCT_FRAG6_CB(next)->offset < end)
+                goto discard_fq;
 
         NFCT_FRAG6_CB(skb)->offset = offset;
 
@@ -371,6 +319,8 @@ found:
         write_unlock(&nf_frags.lock);
         return 0;
 
+discard_fq:
+        fq_kill(fq);
 err:
         return -1;
 }
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 545c4141b755..64cfef1b0a4c 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -149,13 +149,6 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a)
 }
 EXPORT_SYMBOL(ip6_frag_match);
 
-/* Memory Tracking Functions. */
-static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb)
-{
-        atomic_sub(skb->truesize, &nf->mem);
-        kfree_skb(skb);
-}
-
 void ip6_frag_init(struct inet_frag_queue *q, void *a)
 {
         struct frag_queue *fq = container_of(q, struct frag_queue, q);
@@ -346,58 +339,22 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
         }
 
 found:
-        /* We found where to put this one.  Check for overlap with
-         * preceding fragment, and, if needed, align things so that
-         * any overlaps are eliminated.
+        /* RFC5722, Section 4:
+         *                                  When reassembling an IPv6 datagram, if
+         *   one or more its constituent fragments is determined to be an
+         *   overlapping fragment, the entire datagram (and any constituent
+         *   fragments, including those not yet received) MUST be silently
+         *   discarded.
          */
-        if (prev) {
-                int i = (FRAG6_CB(prev)->offset + prev->len) - offset;
 
-                if (i > 0) {
-                        offset += i;
-                        if (end <= offset)
-                                goto err;
-                        if (!pskb_pull(skb, i))
-                                goto err;
-                        if (skb->ip_summed != CHECKSUM_UNNECESSARY)
-                                skb->ip_summed = CHECKSUM_NONE;
-                }
-        }
+        /* Check for overlap with preceding fragment. */
+        if (prev &&
+            (FRAG6_CB(prev)->offset + prev->len) - offset > 0)
+                goto discard_fq;
 
-        /* Look for overlap with succeeding segments.
-         * If we can merge fragments, do it.
-         */
-        while (next && FRAG6_CB(next)->offset < end) {
-                int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */
-
-                if (i < next->len) {
-                        /* Eat head of the next overlapped fragment
-                         * and leave the loop. The next ones cannot overlap.
-                         */
-                        if (!pskb_pull(next, i))
-                                goto err;
-                        FRAG6_CB(next)->offset += i;    /* next fragment */
-                        fq->q.meat -= i;
-                        if (next->ip_summed != CHECKSUM_UNNECESSARY)
-                                next->ip_summed = CHECKSUM_NONE;
-                        break;
-                } else {
-                        struct sk_buff *free_it = next;
-
-                        /* Old fragment is completely overridden with
-                         * new one drop it.
-                         */
-                        next = next->next;
-
-                        if (prev)
-                                prev->next = next;
-                        else
-                                fq->q.fragments = next;
-
-                        fq->q.meat -= free_it->len;
-                        frag_kfree_skb(fq->q.net, free_it);
-                }
-        }
+        /* Look for overlap with succeeding segment. */
+        if (next && FRAG6_CB(next)->offset < end)
+                goto discard_fq;
 
         FRAG6_CB(skb)->offset = offset;
 
@@ -436,6 +393,8 @@ found:
         write_unlock(&ip6_frags.lock);
         return -1;
 
+discard_fq:
+        fq_kill(fq);
 err:
         IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
                       IPSTATS_MIB_REASMFAILS);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d126365ac046..a275c6e1e25c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -670,7 +670,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad
 
                         if (net_ratelimit())
                                 printk(KERN_WARNING
-                                       "Neighbour table overflow.\n");
+                                       "ipv6: Neighbour table overflow.\n");
                         dst_free(&rt->dst);
                         return NULL;
                 }
@@ -1556,14 +1556,13 @@ out:
  *      i.e. Path MTU discovery
  */
 
-void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
-                        struct net_device *dev, u32 pmtu)
+static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr,
+                             struct net *net, u32 pmtu, int ifindex)
 {
         struct rt6_info *rt, *nrt;
-        struct net *net = dev_net(dev);
         int allfrag = 0;
 
-        rt = rt6_lookup(net, daddr, saddr, dev->ifindex, 0);
+        rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
         if (rt == NULL)
                 return;
 
@@ -1631,6 +1630,27 @@ out:
         dst_release(&rt->dst);
 }
 
+void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
+                        struct net_device *dev, u32 pmtu)
+{
+        struct net *net = dev_net(dev);
+
+        /*
+         * RFC 1981 states that a node "MUST reduce the size of the packets it
+         * is sending along the path" that caused the Packet Too Big message.
+         * Since it's not possible in the general case to determine which
+         * interface was used to send the original packet, we update the MTU
+         * on the interface that will be used to send future packets. We also
+         * update the MTU on the interface that received the Packet Too Big in
+         * case the original packet was forced out that interface with
+         * SO_BINDTODEVICE or similar. This is the next best thing to the
+         * correct behaviour, which would be to update the MTU on all
+         * interfaces.
+         */
+        rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0);
+        rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex);
+}
+
 /*
  *      Misc support functions
  */
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1dd1affdead2..5acb3560ff15 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -111,6 +111,15 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
         return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr);
 }
 
+static void udp_v6_rehash(struct sock *sk)
+{
+        u16 new_hash = udp6_portaddr_hash(sock_net(sk),
+                                          &inet6_sk(sk)->rcv_saddr,
+                                          inet_sk(sk)->inet_num);
+
+        udp_lib_rehash(sk, new_hash);
+}
+
 static inline int compute_score(struct sock *sk, struct net *net,
                                 unsigned short hnum,
                                 struct in6_addr *saddr, __be16 sport,
@@ -1447,6 +1456,7 @@ struct proto udpv6_prot = {
         .backlog_rcv       = udpv6_queue_rcv_skb,
         .hash              = udp_lib_hash,
         .unhash            = udp_lib_unhash,
+        .rehash            = udp_v6_rehash,
         .get_port          = udp_v6_get_port,
         .memory_allocated  = &udp_memory_allocated,
         .sysctl_mem        = sysctl_udp_mem,
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index f417b77fa0e1..a67575d472a3 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -20,23 +20,27 @@
 #include <net/addrconf.h>
 
 static void
-__xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl,
-                     struct xfrm_tmpl *tmpl,
-                     xfrm_address_t *daddr, xfrm_address_t *saddr)
+__xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl)
 {
         /* Initialize temporary selector matching only
          * to current session. */
-        ipv6_addr_copy((struct in6_addr *)&x->sel.daddr, &fl->fl6_dst);
-        ipv6_addr_copy((struct in6_addr *)&x->sel.saddr, &fl->fl6_src);
-        x->sel.dport = xfrm_flowi_dport(fl);
-        x->sel.dport_mask = htons(0xffff);
-        x->sel.sport = xfrm_flowi_sport(fl);
-        x->sel.sport_mask = htons(0xffff);
-        x->sel.family = AF_INET6;
-        x->sel.prefixlen_d = 128;
-        x->sel.prefixlen_s = 128;
-        x->sel.proto = fl->proto;
-        x->sel.ifindex = fl->oif;
+        ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst);
+        ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src);
+        sel->dport = xfrm_flowi_dport(fl);
+        sel->dport_mask = htons(0xffff);
+        sel->sport = xfrm_flowi_sport(fl);
+        sel->sport_mask = htons(0xffff);
+        sel->family = AF_INET6;
+        sel->prefixlen_d = 128;
+        sel->prefixlen_s = 128;
+        sel->proto = fl->proto;
+        sel->ifindex = fl->oif;
+}
+
+static void
+xfrm6_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
+                   xfrm_address_t *daddr, xfrm_address_t *saddr)
+{
         x->id = tmpl->id;
         if (ipv6_addr_any((struct in6_addr*)&x->id.daddr))
                 memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr));
@@ -168,6 +172,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = {
         .eth_proto              = htons(ETH_P_IPV6),
         .owner                  = THIS_MODULE,
         .init_tempsel           = __xfrm6_init_tempsel,
+        .init_temprop           = xfrm6_init_temprop,
         .tmpl_sort              = __xfrm6_tmpl_sort,
         .state_sort             = __xfrm6_state_sort,
         .output                 = xfrm6_output,