6 files changed, 110 insertions, 79 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 5379b0c1190a..f1129706ce7b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1090,7 +1090,7 @@ int dev_open(struct net_device *dev)
                 /*
                  *      Enable NET_DMA
                  */
-                dmaengine_get();
+                net_dmaengine_get();
 
                 /*
                  *      Initialize multicasting status
@@ -1172,7 +1172,7 @@ int dev_close(struct net_device *dev)
         /*
          *      Shutdown NET_DMA
          */
-        dmaengine_put();
+        net_dmaengine_put();
 
         return 0;
 }
@@ -2267,12 +2267,6 @@ int netif_receive_skb(struct sk_buff *skb)
 
         rcu_read_lock();
 
-        /* Don't receive packets in an exiting network namespace */
-        if (!net_alive(dev_net(skb->dev))) {
-                kfree_skb(skb);
-                goto out;
-        }
-
 #ifdef CONFIG_NET_CLS_ACT
         if (skb->tc_verd & TC_NCLS) {
                 skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
@@ -2488,6 +2482,9 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 
 int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
+        if (netpoll_receive_skb(skb))
+                return NET_RX_DROP;
+
         switch (__napi_gro_receive(napi, skb)) {
         case -1:
                 return netif_receive_skb(skb);
@@ -2558,6 +2555,9 @@ int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info)
         if (!skb)
                 goto out;
 
+        if (netpoll_receive_skb(skb))
+                goto out;
+
         err = NET_RX_SUCCESS;
 
         switch (__napi_gro_receive(napi, skb)) {
@@ -4282,6 +4282,39 @@ unsigned long netdev_fix_features(unsigned long features, const char *name)
 }
 EXPORT_SYMBOL(netdev_fix_features);
 
+/* Some devices need to (re-)set their netdev_ops inside
+ * ->init() or similar.  If that happens, we have to setup
+ * the compat pointers again.
+ */
+void netdev_resync_ops(struct net_device *dev)
+{
+#ifdef CONFIG_COMPAT_NET_DEV_OPS
+        const struct net_device_ops *ops = dev->netdev_ops;
+
+        dev->init = ops->ndo_init;
+        dev->uninit = ops->ndo_uninit;
+        dev->open = ops->ndo_open;
+        dev->change_rx_flags = ops->ndo_change_rx_flags;
+        dev->set_rx_mode = ops->ndo_set_rx_mode;
+        dev->set_multicast_list = ops->ndo_set_multicast_list;
+        dev->set_mac_address = ops->ndo_set_mac_address;
+        dev->validate_addr = ops->ndo_validate_addr;
+        dev->do_ioctl = ops->ndo_do_ioctl;
+        dev->set_config = ops->ndo_set_config;
+        dev->change_mtu = ops->ndo_change_mtu;
+        dev->neigh_setup = ops->ndo_neigh_setup;
+        dev->tx_timeout = ops->ndo_tx_timeout;
+        dev->get_stats = ops->ndo_get_stats;
+        dev->vlan_rx_register = ops->ndo_vlan_rx_register;
+        dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid;
+        dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid;
+#ifdef CONFIG_NET_POLL_CONTROLLER
+        dev->poll_controller = ops->ndo_poll_controller;
+#endif
+#endif
+}
+EXPORT_SYMBOL(netdev_resync_ops);
+
 /**
  *      register_netdevice      - register a network device
  *      @dev: device to register
@@ -4326,27 +4359,7 @@ int register_netdevice(struct net_device *dev)
          * This is temporary until all network devices are converted.
          */
         if (dev->netdev_ops) {
-                const struct net_device_ops *ops = dev->netdev_ops;
-
-                dev->init = ops->ndo_init;
-                dev->uninit = ops->ndo_uninit;
-                dev->open = ops->ndo_open;
-                dev->change_rx_flags = ops->ndo_change_rx_flags;
-                dev->set_rx_mode = ops->ndo_set_rx_mode;
-                dev->set_multicast_list = ops->ndo_set_multicast_list;
-                dev->set_mac_address = ops->ndo_set_mac_address;
-                dev->validate_addr = ops->ndo_validate_addr;
-                dev->do_ioctl = ops->ndo_do_ioctl;
-                dev->set_config = ops->ndo_set_config;
-                dev->change_mtu = ops->ndo_change_mtu;
-                dev->tx_timeout = ops->ndo_tx_timeout;
-                dev->get_stats = ops->ndo_get_stats;
-                dev->vlan_rx_register = ops->ndo_vlan_rx_register;
-                dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid;
-                dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid;
-#ifdef CONFIG_NET_POLL_CONTROLLER
-                dev->poll_controller = ops->ndo_poll_controller;
-#endif
+                netdev_resync_ops(dev);
         } else {
                 char drivername[64];
                 pr_info("%s (%s): not using net_device_ops yet\n",
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f66c58df8953..278a142d1047 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1994,8 +1994,8 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
                         if (!net_eq(neigh_parms_net(p), net))
                                 continue;
 
-                        if (nidx++ < neigh_skip)
-                                continue;
+                        if (nidx < neigh_skip)
+                                goto next;
 
                         if (neightbl_fill_param_info(skb, tbl, p,
                                                      NETLINK_CB(cb->skb).pid,
@@ -2003,6 +2003,8 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
                                                      RTM_NEWNEIGHTBL,
                                                      NLM_F_MULTI) <= 0)
                                 goto out;
+                next:
+                        nidx++;
                 }
 
                 neigh_skip = 0;
@@ -2082,12 +2084,10 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
                 if (h > s_h)
                         s_idx = 0;
                 for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) {
-                        int lidx;
                         if (dev_net(n->dev) != net)
                                 continue;
-                        lidx = idx++;
-                        if (lidx < s_idx)
-                                continue;
+                        if (idx < s_idx)
+                                goto next;
                         if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid,
                                             cb->nlh->nlmsg_seq,
                                             RTM_NEWNEIGH,
@@ -2096,6 +2096,8 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
                                 rc = -1;
                                 goto out;
                         }
+                next:
+                        idx++;
                 }
         }
         read_unlock_bh(&tbl->lock);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 6ac29a46e23e..484f58750eba 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -77,7 +77,9 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
         if (endp == buf)
                 goto err;
 
-        rtnl_lock();
+        if (!rtnl_trylock())
+                return -ERESTARTSYS;
+
         if (dev_isalive(net)) {
                 if ((ret = (*set)(net, new)) == 0)
                         ret = len;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 55151faaf90c..e3bebd36f053 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -32,24 +32,14 @@ static __net_init int setup_net(struct net *net)
 {
         /* Must be called with net_mutex held */
         struct pernet_operations *ops;
-        int error;
-        struct net_generic *ng;
+        int error = 0;
 
         atomic_set(&net->count, 1);
+
 #ifdef NETNS_REFCNT_DEBUG
         atomic_set(&net->use_count, 0);
 #endif
 
-        error = -ENOMEM;
-        ng = kzalloc(sizeof(struct net_generic) +
-                        INITIAL_NET_GEN_PTRS * sizeof(void *), GFP_KERNEL);
-        if (ng == NULL)
-                goto out;
-
-        ng->len = INITIAL_NET_GEN_PTRS;
-        rcu_assign_pointer(net->gen, ng);
-
-        error = 0;
         list_for_each_entry(ops, &pernet_list, list) {
                 if (ops->init) {
                         error = ops->init(net);
@@ -70,24 +60,50 @@ out_undo:
         }
 
         rcu_barrier();
-        kfree(ng);
         goto out;
 }
 
+static struct net_generic *net_alloc_generic(void)
+{
+        struct net_generic *ng;
+        size_t generic_size = sizeof(struct net_generic) +
+                INITIAL_NET_GEN_PTRS * sizeof(void *);
+
+        ng = kzalloc(generic_size, GFP_KERNEL);
+        if (ng)
+                ng->len = INITIAL_NET_GEN_PTRS;
+
+        return ng;
+}
+
 #ifdef CONFIG_NET_NS
 static struct kmem_cache *net_cachep;
 static struct workqueue_struct *netns_wq;
 
 static struct net *net_alloc(void)
 {
-        return kmem_cache_zalloc(net_cachep, GFP_KERNEL);
+        struct net *net = NULL;
+        struct net_generic *ng;
+
+        ng = net_alloc_generic();
+        if (!ng)
+                goto out;
+
+        net = kmem_cache_zalloc(net_cachep, GFP_KERNEL);
+        if (!net)
+                goto out_free;
+
+        rcu_assign_pointer(net->gen, ng);
+out:
+        return net;
+
+out_free:
+        kfree(ng);
+        goto out;
 }
 
 static void net_free(struct net *net)
 {
-        if (!net)
-                return;
-
 #ifdef NETNS_REFCNT_DEBUG
         if (unlikely(atomic_read(&net->use_count) != 0)) {
                 printk(KERN_EMERG "network namespace not free! Usage: %d\n",
@@ -112,27 +128,28 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
         err = -ENOMEM;
         new_net = net_alloc();
         if (!new_net)
-                goto out;
+                goto out_err;
 
         mutex_lock(&net_mutex);
         err = setup_net(new_net);
-        if (err)
-                goto out_unlock;
-
-        rtnl_lock();
-        list_add_tail(&new_net->list, &net_namespace_list);
-        rtnl_unlock();
-
-
-out_unlock:
+        if (!err) {
+                rtnl_lock();
+                list_add_tail(&new_net->list, &net_namespace_list);
+                rtnl_unlock();
+        }
         mutex_unlock(&net_mutex);
+
+        if (err)
+                goto out_free;
 out:
         put_net(old_net);
-        if (err) {
-                net_free(new_net);
-                new_net = ERR_PTR(err);
-        }
         return new_net;
+
+out_free:
+        net_free(new_net);
+out_err:
+        new_net = ERR_PTR(err);
+        goto out;
 }
 
 static void cleanup_net(struct work_struct *work)
@@ -140,9 +157,6 @@ static void cleanup_net(struct work_struct *work)
         struct pernet_operations *ops;
         struct net *net;
 
-        /* Be very certain incoming network packets will not find us */
-        rcu_barrier();
-
         net = container_of(work, struct net, work);
 
         mutex_lock(&net_mutex);
@@ -188,6 +202,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 
 static int __init net_ns_init(void)
 {
+        struct net_generic *ng;
         int err;
 
         printk(KERN_INFO "net_namespace: %zd bytes\n", sizeof(struct net));
@@ -202,6 +217,12 @@ static int __init net_ns_init(void)
                 panic("Could not create netns workq");
 #endif
 
+        ng = net_alloc_generic();
+        if (!ng)
+                panic("Could not allocate generic netns");
+
+        rcu_assign_pointer(init_net.gen, ng);
+
         mutex_lock(&net_mutex);
         err = setup_net(&init_net);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index da74b844f4ea..c6a6b166f8d6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -143,14 +143,6 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here)
         BUG();
 }
 
-void skb_truesize_bug(struct sk_buff *skb)
-{
-        WARN(net_ratelimit(), KERN_ERR "SKB BUG: Invalid truesize (%u) "
-               "len=%u, sizeof(sk_buff)=%Zd\n",
-               skb->truesize, skb->len, sizeof(struct sk_buff));
-}
-EXPORT_SYMBOL(skb_truesize_bug);
-
 /*      Allocate a new skbuff. We do this ourselves so we can fill in a few
  *      'private' fields and also do memory statistics to find all the
  *      [BEEP] leaks.
diff --git a/net/core/sock.c b/net/core/sock.c
index f3a0d08cbb48..5f97caa158e8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -696,6 +696,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
         if (len < 0)
                 return -EINVAL;
 
+        memset(&v, 0, sizeof(v));
+
         switch(optname) {
         case SO_DEBUG:
                 v.val = sock_flag(sk, SOCK_DBG);
@@ -1135,7 +1137,6 @@ void sock_rfree(struct sk_buff *skb)
 {
         struct sock *sk = skb->sk;
 
-        skb_truesize_check(skb);
         atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
         sk_mem_uncharge(skb->sk, skb->truesize);
 }