6 files changed, 129 insertions, 24 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index d2c8a06b3a98..9abc503b19b7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2418,7 +2418,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault);
  * 2. No high memory really exists on this machine.
  */
 
-static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_HIGHMEM
         int i;
@@ -2493,38 +2493,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
 }
 
 static netdev_features_t harmonize_features(struct sk_buff *skb,
-                                            const struct net_device *dev,
-                                            netdev_features_t features)
+        netdev_features_t features)
 {
         int tmp;
 
         if (skb->ip_summed != CHECKSUM_NONE &&
             !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
                 features &= ~NETIF_F_ALL_CSUM;
-        } else if (illegal_highdma(dev, skb)) {
+        } else if (illegal_highdma(skb->dev, skb)) {
                 features &= ~NETIF_F_SG;
         }
 
         return features;
 }
 
-netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
-                                         const struct net_device *dev)
+netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
         __be16 protocol = skb->protocol;
-        netdev_features_t features = dev->features;
+        netdev_features_t features = skb->dev->features;
 
-        if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
+        if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
                 features &= ~NETIF_F_GSO_MASK;
 
         if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
                 struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
                 protocol = veh->h_vlan_encapsulated_proto;
         } else if (!vlan_tx_tag_present(skb)) {
-                return harmonize_features(skb, dev, features);
+                return harmonize_features(skb, features);
         }
 
-        features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+        features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
                                                NETIF_F_HW_VLAN_STAG_TX);
 
         if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))
@@ -2532,9 +2530,9 @@ netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
                                 NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
                                 NETIF_F_HW_VLAN_STAG_TX;
 
-        return harmonize_features(skb, dev, features);
+        return harmonize_features(skb, features);
 }
-EXPORT_SYMBOL(netif_skb_dev_features);
+EXPORT_SYMBOL(netif_skb_features);
 
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
                         struct netdev_queue *txq)
@@ -3953,6 +3951,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
         }
         NAPI_GRO_CB(skb)->count = 1;
         NAPI_GRO_CB(skb)->age = jiffies;
+        NAPI_GRO_CB(skb)->last = skb;
         skb_shinfo(skb)->gso_size = skb_gro_len(skb);
         skb->next = napi->gro_list;
         napi->gro_list = skb;
@@ -4543,6 +4542,32 @@ void *netdev_adjacent_get_private(struct list_head *adj_list)
 EXPORT_SYMBOL(netdev_adjacent_get_private);
 
 /**
+ * netdev_upper_get_next_dev_rcu - Get the next dev from upper list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next device from the dev's upper list, starting from iter
+ * position. The caller must hold RCU read lock.
+ */
+struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
+                                                 struct list_head **iter)
+{
+        struct netdev_adjacent *upper;
+
+        WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
+
+        upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+        if (&upper->list == &dev->adj_list.upper)
+                return NULL;
+
+        *iter = &upper->list;
+
+        return upper->dev;
+}
+EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+
+/**
  * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
  * @dev: device
  * @iter: list_head ** of the current position
@@ -4624,6 +4649,32 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
 
 /**
+ * netdev_lower_get_next - Get the next device from the lower neighbour
+ *                         list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold RTNL lock or
+ * its own locking that guarantees that the neighbour lower
+ * list will remain unchainged.
+ */
+void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
+{
+        struct netdev_adjacent *lower;
+
+        lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+        if (&lower->list == &dev->adj_list.lower)
+                return NULL;
+
+        *iter = &lower->list;
+
+        return lower->dev;
+}
+EXPORT_SYMBOL(netdev_lower_get_next);
+
+/**
  * netdev_lower_get_first_private_rcu - Get the first ->private from the
  *                                     lower neighbour list, RCU
  *                                     variant
@@ -5073,6 +5124,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_lower_dev_get_private);
 
+
+int dev_get_nest_level(struct net_device *dev,
+                       bool (*type_check)(struct net_device *dev))
+{
+        struct net_device *lower = NULL;
+        struct list_head *iter;
+        int max_nest = -1;
+        int nest;
+
+        ASSERT_RTNL();
+
+        netdev_for_each_lower_dev(dev, lower, iter) {
+                nest = dev_get_nest_level(lower, type_check);
+                if (max_nest < nest)
+                        max_nest = nest;
+        }
+
+        if (type_check(dev))
+                max_nest++;
+
+        return max_nest;
+}
+EXPORT_SYMBOL(dev_get_nest_level);
+
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
         const struct net_device_ops *ops = dev->netdev_ops;
@@ -5238,7 +5313,6 @@ void __dev_set_rx_mode(struct net_device *dev)
         if (ops->ndo_set_rx_mode)
                 ops->ndo_set_rx_mode(dev);
 }
-EXPORT_SYMBOL(__dev_set_rx_mode);
 
 void dev_set_rx_mode(struct net_device *dev)
 {
@@ -5543,7 +5617,7 @@ static int dev_new_index(struct net *net)
 
 /* Delayed registration/unregisteration */
 static LIST_HEAD(net_todo_list);
-static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
+DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
 
 static void net_set_todo(struct net_device *dev)
 {
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8f8a96ef9f3f..32d872eec7f5 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1248,8 +1248,8 @@ void __neigh_set_probe_once(struct neighbour *neigh)
         neigh->updated = jiffies;
         if (!(neigh->nud_state & NUD_FAILED))
                 return;
-        neigh->nud_state = NUD_PROBE;
-        atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES));
+        neigh->nud_state = NUD_INCOMPLETE;
+        atomic_set(&neigh->probes, neigh_max_probes(neigh));
         neigh_add_timer(neigh,
                         jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME));
 }
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 81d3a9a08453..7c8ffd974961 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -24,7 +24,7 @@
 
 static LIST_HEAD(pernet_list);
 static struct list_head *first_device = &pernet_list;
-static DEFINE_MUTEX(net_mutex);
+DEFINE_MUTEX(net_mutex);
 
 LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9837bebf93ce..2d8d8fcfa060 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -353,15 +353,46 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops)
 }
 EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
 
+/* Return with the rtnl_lock held when there are no network
+ * devices unregistering in any network namespace.
+ */
+static void rtnl_lock_unregistering_all(void)
+{
+        struct net *net;
+        bool unregistering;
+        DEFINE_WAIT(wait);
+
+        for (;;) {
+                prepare_to_wait(&netdev_unregistering_wq, &wait,
+                                TASK_UNINTERRUPTIBLE);
+                unregistering = false;
+                rtnl_lock();
+                for_each_net(net) {
+                        if (net->dev_unreg_count > 0) {
+                                unregistering = true;
+                                break;
+                        }
+                }
+                if (!unregistering)
+                        break;
+                __rtnl_unlock();
+                schedule();
+        }
+        finish_wait(&netdev_unregistering_wq, &wait);
+}
+
 /**
  * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
  * @ops: struct rtnl_link_ops * to unregister
  */
 void rtnl_link_unregister(struct rtnl_link_ops *ops)
 {
-        rtnl_lock();
+        /* Close the race with cleanup_net() */
+        mutex_lock(&net_mutex);
+        rtnl_lock_unregistering_all();
         __rtnl_link_unregister(ops);
         rtnl_unlock();
+        mutex_unlock(&net_mutex);
 }
 EXPORT_SYMBOL_GPL(rtnl_link_unregister);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1b62343f5837..8383b2bddeb9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3076,7 +3076,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
         if (unlikely(p->len + len >= 65536))
                 return -E2BIG;
 
-        lp = NAPI_GRO_CB(p)->last ?: p;
+        lp = NAPI_GRO_CB(p)->last;
         pinfo = skb_shinfo(lp);
 
         if (headlen <= offset) {
@@ -3192,7 +3192,7 @@ merge:
 
         __skb_pull(skb, offset);
 
-        if (!NAPI_GRO_CB(p)->last)
+        if (NAPI_GRO_CB(p)->last == p)
                 skb_shinfo(p)->frag_list = skb;
         else
                 NAPI_GRO_CB(p)->last->next = skb;
diff --git a/net/core/utils.c b/net/core/utils.c
index 2f737bf90b3f..eed34338736c 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w)
 {
         struct __net_random_once_work *work =
                 container_of(w, struct __net_random_once_work, work);
-        if (!static_key_enabled(work->key))
-                static_key_slow_inc(work->key);
+        BUG_ON(!static_key_enabled(work->key));
+        static_key_slow_dec(work->key);
         kfree(work);
 }
 
@@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key)
 }
 
 bool __net_get_random_once(void *buf, int nbytes, bool *done,
-                           struct static_key *done_key)
+                           struct static_key *once_key)
 {
         static DEFINE_SPINLOCK(lock);
         unsigned long flags;
@@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done,
         *done = true;
         spin_unlock_irqrestore(&lock, flags);
 
-        __net_random_once_disable_jump(done_key);
+        __net_random_once_disable_jump(once_key);
 
         return true;
 }