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

Pull networking fixes from David Miller:

 1) Don't halt the firmware in r8152 driver, from Hayes Wang.

 2) Handle full sized 802.1ad frames in bnx2 and tg3 drivers properly,
    from Vlad Yasevich.

 3) Don't sleep while holding tx_clean_lock in netxen driver, fix from
    Manish Chopra.

 4) Certain kinds of ipv6 routes can end up endlessly failing the route
    validation test, causing it to be re-looked up over and over again.
    This particularly kills input route caching in TCP sockets.  Fix
    from Hannes Frederic Sowa.

 5) netvsc_start_xmit() has a use-after-free access to skb->len, fix
    from K Y Srinivasan.

 6) Fix matching of inverted containers in ematch module, from Ignacy
    Gawędzki.

 7) Aggregation of GRO frames via SKB ->frag_list for linear skbs isn't
    handled properly, regression fix from Eric Dumazet.

 8) Don't test return value of ipv4_neigh_lookup(), which returns an
    error pointer, against NULL.  From WANG Cong.

 9) Fix an old regression where we mistakenly allow a double add of the
    same tunnel.  Fixes from Steffen Klassert.

10) macvtap device delete and open can run in parallel and corrupt lists
    etc., fix from Vlad Yasevich.

11) Fix build error with IPV6=m NETFILTER_XT_TARGET_TPROXY=y, from Pablo
    Neira Ayuso.

12) rhashtable_destroy() triggers lockdep splats, fix also from Pablo.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (32 commits)
  bna: Update Maintainer Email
  r8152: disable power cut for RTL8153
  r8152: remove clearing bp
  bnx2: Correctly receive full sized 802.1ad fragmes
  tg3: Allow for recieve of full-size 8021AD frames
  r8152: fix setting RTL8152_UNPLUG
  netxen: Fix bug in Tx completion path.
  netxen: Fix BUG "sleeping function called from invalid context"
  ipv6: remove rt6i_genid
  hyperv: Fix a bug in netvsc_start_xmit()
  net: stmmac: fix stmmac_pci_probe failed when CONFIG_HAVE_CLK is selected
  ematch: Fix matching of inverted containers.
  gro: fix aggregation for skb using frag_list
  neigh: check error pointer instead of NULL for ipv4_neigh_lookup()
  ip6_gre: Return an error when adding an existing tunnel.
  ip6_vti: Return an error when adding an existing tunnel.
  ip6_tunnel: Return an error when adding an existing tunnel.
  ip6gre: add a rtnl link alias for ip6gretap
  net/mlx4_core: Allow not to specify probe_vf in SRIOV IB mode
  r8152: fix the carrier off when autoresuming
  ...

15 files changed, 129 insertions, 21 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index da1378a3e2c7..8d289697cc7a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3152,6 +3152,9 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
                 NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
                 goto done;
         }
+        /* switch back to head shinfo */
+        pinfo = skb_shinfo(p);
+
         if (pinfo->frag_list)
                 goto merge;
         if (skb_gro_len(p) != pinfo->gso_size)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index bd41dd1948b6..bda4bb8ae260 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -764,9 +764,14 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 
                 t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
 
-                if (!t && (cmd == SIOCADDTUNNEL)) {
-                        t = ip_tunnel_create(net, itn, p);
-                        err = PTR_ERR_OR_ZERO(t);
+                if (cmd == SIOCADDTUNNEL) {
+                        if (!t) {
+                                t = ip_tunnel_create(net, itn, p);
+                                err = PTR_ERR_OR_ZERO(t);
+                                break;
+                        }
+
+                        err = -EEXIST;
                         break;
                 }
                 if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 173e7ea54c70..cbadb942c332 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -746,7 +746,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
         }
 
         n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw);
-        if (n) {
+        if (!IS_ERR(n)) {
                 if (!(n->nud_state & NUD_VALID)) {
                         neigh_event_send(n, NULL);
                 } else {
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3342ee64f2e3..3e118dfddd02 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4780,10 +4780,11 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 
                 if (ip6_del_rt(ifp->rt))
                         dst_free(&ifp->rt->dst);
+
+                rt_genid_bump_ipv6(net);
                 break;
         }
         atomic_inc(&net->ipv6.dev_addr_genid);
-        rt_genid_bump_ipv6(net);
 }
 
 static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index e6960457f625..98cc4cd570e2 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -8,6 +8,13 @@
 #include <net/addrconf.h>
 #include <net/ip.h>
 
+/* if ipv6 module registers this function is used by xfrm to force all
+ * sockets to relookup their nodes - this is fairly expensive, be
+ * careful
+ */
+void (*__fib6_flush_trees)(struct net *);
+EXPORT_SYMBOL(__fib6_flush_trees);
+
 #define IPV6_ADDR_SCOPE_TYPE(scope)     ((scope) << 16)
 
 static inline unsigned int ipv6_addr_scope2type(unsigned int scope)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 76b7f5ee8f4c..97b9fa8de377 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1605,6 +1605,24 @@ static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
         fib6_clean_tree(net, fn, fib6_prune_clone, 1, NULL);
 }
 
+static int fib6_update_sernum(struct rt6_info *rt, void *arg)
+{
+        __u32 sernum = *(__u32 *)arg;
+
+        if (rt->rt6i_node &&
+            rt->rt6i_node->fn_sernum != sernum)
+                rt->rt6i_node->fn_sernum = sernum;
+
+        return 0;
+}
+
+static void fib6_flush_trees(struct net *net)
+{
+        __u32 new_sernum = fib6_new_sernum();
+
+        fib6_clean_all(net, fib6_update_sernum, &new_sernum);
+}
+
 /*
  *      Garbage collection
  */
@@ -1788,6 +1806,8 @@ int __init fib6_init(void)
                               NULL);
         if (ret)
                 goto out_unregister_subsys;
+
+        __fib6_flush_trees = fib6_flush_trees;
 out:
         return ret;
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 5f19dfbc4c6a..f304471477dc 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -314,6 +314,8 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
         struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 
         t = ip6gre_tunnel_find(net, parms, ARPHRD_IP6GRE);
+        if (t && create)
+                return NULL;
         if (t || !create)
                 return t;
 
@@ -1724,4 +1726,5 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)");
 MODULE_DESCRIPTION("GRE over IPv6 tunneling device");
 MODULE_ALIAS_RTNL_LINK("ip6gre");
+MODULE_ALIAS_RTNL_LINK("ip6gretap");
 MODULE_ALIAS_NETDEV("ip6gre0");
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index f9de5a695072..69a84b464009 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -364,8 +364,12 @@ static struct ip6_tnl *ip6_tnl_locate(struct net *net,
              (t = rtnl_dereference(*tp)) != NULL;
              tp = &t->next) {
                 if (ipv6_addr_equal(local, &t->parms.laddr) &&
-                    ipv6_addr_equal(remote, &t->parms.raddr))
+                    ipv6_addr_equal(remote, &t->parms.raddr)) {
+                        if (create)
+                                return NULL;
+
                         return t;
+                }
         }
         if (!create)
                 return NULL;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 7f52fd9fa7b0..5833a2244467 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -253,8 +253,12 @@ static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p,
              (t = rtnl_dereference(*tp)) != NULL;
              tp = &t->next) {
                 if (ipv6_addr_equal(local, &t->parms.laddr) &&
-                    ipv6_addr_equal(remote, &t->parms.raddr))
+                    ipv6_addr_equal(remote, &t->parms.raddr)) {
+                        if (create)
+                                return NULL;
+
                         return t;
+                }
         }
         if (!create)
                 return NULL;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f23fbd28a501..bafde82324c5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -314,7 +314,6 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
 
                 memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
                 rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
-                rt->rt6i_genid = rt_genid_ipv6(net);
                 INIT_LIST_HEAD(&rt->rt6i_siblings);
         }
         return rt;
@@ -1098,9 +1097,6 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
          * DST_OBSOLETE_FORCE_CHK which forces validation calls down
          * into this function always.
          */
-        if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev)))
-                return NULL;
-
         if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
                 return NULL;
 
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index b5c1d3aadb41..6d77cce481d5 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -847,6 +847,7 @@ config NETFILTER_XT_TARGET_TPROXY
         tristate '"TPROXY" target transparent proxying support'
         depends on NETFILTER_XTABLES
         depends on NETFILTER_ADVANCED
+        depends on (IPV6 || IPV6=n)
         depends on IP_NF_MANGLE
         select NF_DEFRAG_IPV4
         select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index c138b8fbe280..f37f0716a9fc 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -222,6 +222,51 @@ replay:
         }
 }
 
+struct nfnl_err {
+        struct list_head        head;
+        struct nlmsghdr         *nlh;
+        int                     err;
+};
+
+static int nfnl_err_add(struct list_head *list, struct nlmsghdr *nlh, int err)
+{
+        struct nfnl_err *nfnl_err;
+
+        nfnl_err = kmalloc(sizeof(struct nfnl_err), GFP_KERNEL);
+        if (nfnl_err == NULL)
+                return -ENOMEM;
+
+        nfnl_err->nlh = nlh;
+        nfnl_err->err = err;
+        list_add_tail(&nfnl_err->head, list);
+
+        return 0;
+}
+
+static void nfnl_err_del(struct nfnl_err *nfnl_err)
+{
+        list_del(&nfnl_err->head);
+        kfree(nfnl_err);
+}
+
+static void nfnl_err_reset(struct list_head *err_list)
+{
+        struct nfnl_err *nfnl_err, *next;
+
+        list_for_each_entry_safe(nfnl_err, next, err_list, head)
+                nfnl_err_del(nfnl_err);
+}
+
+static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb)
+{
+        struct nfnl_err *nfnl_err, *next;
+
+        list_for_each_entry_safe(nfnl_err, next, err_list, head) {
+                netlink_ack(skb, nfnl_err->nlh, nfnl_err->err);
+                nfnl_err_del(nfnl_err);
+        }
+}
+
 static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
                                 u_int16_t subsys_id)
 {
@@ -230,6 +275,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
         const struct nfnetlink_subsystem *ss;
         const struct nfnl_callback *nc;
         bool success = true, done = false;
+        static LIST_HEAD(err_list);
         int err;
 
         if (subsys_id >= NFNL_SUBSYS_COUNT)
@@ -287,6 +333,7 @@ replay:
                 type = nlh->nlmsg_type;
                 if (type == NFNL_MSG_BATCH_BEGIN) {
                         /* Malformed: Batch begin twice */
+                        nfnl_err_reset(&err_list);
                         success = false;
                         goto done;
                 } else if (type == NFNL_MSG_BATCH_END) {
@@ -333,6 +380,7 @@ replay:
                          * original skb.
                          */
                         if (err == -EAGAIN) {
+                                nfnl_err_reset(&err_list);
                                 ss->abort(skb);
                                 nfnl_unlock(subsys_id);
                                 kfree_skb(nskb);
@@ -341,11 +389,24 @@ replay:
                 }
 ack:
                 if (nlh->nlmsg_flags & NLM_F_ACK || err) {
+                        /* Errors are delivered once the full batch has been
+                         * processed, this avoids that the same error is
+                         * reported several times when replaying the batch.
+                         */
+                        if (nfnl_err_add(&err_list, nlh, err) < 0) {
+                                /* We failed to enqueue an error, reset the
+                                 * list of errors and send OOM to userspace
+                                 * pointing to the batch header.
+                                 */
+                                nfnl_err_reset(&err_list);
+                                netlink_ack(skb, nlmsg_hdr(oskb), -ENOMEM);
+                                success = false;
+                                goto done;
+                        }
                         /* We don't stop processing the batch on errors, thus,
                          * userspace gets all the errors that the batch
                          * triggers.
                          */
-                        netlink_ack(skb, nlh, err);
                         if (err)
                                 success = false;
                 }
@@ -361,6 +422,7 @@ done:
         else
                 ss->abort(skb);
 
+        nfnl_err_deliver(&err_list, oskb);
         nfnl_unlock(subsys_id);
         kfree_skb(nskb);
 }
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 28fb8f38e6ba..8892b7b6184a 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -180,15 +180,17 @@ static int nft_hash_init(const struct nft_set *set,
 static void nft_hash_destroy(const struct nft_set *set)
 {
         const struct rhashtable *priv = nft_set_priv(set);
-        const struct bucket_table *tbl;
+        const struct bucket_table *tbl = priv->tbl;
         struct nft_hash_elem *he, *next;
         unsigned int i;
 
-        tbl = rht_dereference(priv->tbl, priv);
-        for (i = 0; i < tbl->size; i++)
-                rht_for_each_entry_safe(he, next, tbl->buckets[i], priv, node)
+        for (i = 0; i < tbl->size; i++) {
+                for (he = rht_entry(tbl->buckets[i], struct nft_hash_elem, node);
+                     he != NULL; he = next) {
+                        next = rht_entry(he->node.next, struct nft_hash_elem, node);
                         nft_hash_elem_destroy(set, he);
-
+                }
+        }
         rhashtable_destroy(priv);
 }
 
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index e1836ff88199..46214f245665 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -234,13 +234,11 @@ static void nft_rbtree_destroy(const struct nft_set *set)
         struct nft_rbtree_elem *rbe;
         struct rb_node *node;
 
-        spin_lock_bh(&nft_rbtree_lock);
         while ((node = priv->root.rb_node) != NULL) {
                 rb_erase(node, &priv->root);
                 rbe = rb_entry(node, struct nft_rbtree_elem, node);
                 nft_rbtree_elem_destroy(set, rbe);
         }
-        spin_unlock_bh(&nft_rbtree_lock);
 }
 
 static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 3a633debb6df..ad57f4444b9c 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -526,9 +526,11 @@ pop_stack:
                 match_idx = stack[--stackp];
                 cur_match = tcf_em_get_match(tree, match_idx);
 
-                if (tcf_em_early_end(cur_match, res))
+                if (tcf_em_early_end(cur_match, res)) {
+                        if (tcf_em_is_inverted(cur_match))
+                                res = !res;
                         goto pop_stack;
-                else {
+                } else {
                         match_idx++;
                         goto proceed;
                 }