1 files changed, 76 insertions, 24 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index be9924f60ec3..94c1eeed25e5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1448,13 +1448,10 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
         if (skb->len > (dev->mtu + dev->hard_header_len))
                 return NET_RX_DROP;
 
-        skb_dst_drop(skb);
+        skb_set_dev(skb, dev);
         skb->tstamp.tv64 = 0;
         skb->pkt_type = PACKET_HOST;
         skb->protocol = eth_type_trans(skb, dev);
-        skb->mark = 0;
-        secpath_reset(skb);
-        nf_reset(skb);
         return netif_rx(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
@@ -1614,6 +1611,36 @@ static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb)
         return false;
 }
 
+/**
+ * skb_dev_set -- assign a new device to a buffer
+ * @skb: buffer for the new device
+ * @dev: network device
+ *
+ * If an skb is owned by a device already, we have to reset
+ * all data private to the namespace a device belongs to
+ * before assigning it a new device.
+ */
+#ifdef CONFIG_NET_NS
+void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
+{
+        skb_dst_drop(skb);
+        if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
+                secpath_reset(skb);
+                nf_reset(skb);
+                skb_init_secmark(skb);
+                skb->mark = 0;
+                skb->priority = 0;
+                skb->nf_trace = 0;
+                skb->ipvs_property = 0;
+#ifdef CONFIG_NET_SCHED
+                skb->tc_index = 0;
+#endif
+        }
+        skb->dev = dev;
+}
+EXPORT_SYMBOL(skb_set_dev);
+#endif /* CONFIG_NET_NS */
+
 /*
  * Invalidate hardware checksum when packet is to be mangled, and
  * complete checksum manually on outgoing path.
@@ -1853,6 +1880,14 @@ gso:
 
                 skb->next = nskb->next;
                 nskb->next = NULL;
+
+                /*
+                 * If device doesnt need nskb->dst, release it right now while
+                 * its hot in this cpu cache
+                 */
+                if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
+                        skb_dst_drop(nskb);
+
                 rc = ops->ndo_start_xmit(nskb, dev);
                 if (unlikely(rc != NETDEV_TX_OK)) {
                         if (rc & ~NETDEV_TX_MASK)
@@ -1974,6 +2009,21 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
         return rc;
 }
 
+/*
+ * Returns true if either:
+ *      1. skb has frag_list and the device doesn't support FRAGLIST, or
+ *      2. skb is fragmented and the device does not support SG, or if
+ *         at least one of fragments is in highmem and device does not
+ *         support DMA from it.
+ */
+static inline int skb_needs_linearize(struct sk_buff *skb,
+                                      struct net_device *dev)
+{
+        return (skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST)) ||
+               (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) ||
+                                              illegal_highdma(dev, skb)));
+}
+
 /**
  *      dev_queue_xmit - transmit a buffer
  *      @skb: buffer to transmit
@@ -2010,18 +2060,8 @@ int dev_queue_xmit(struct sk_buff *skb)
         if (netif_needs_gso(dev, skb))
                 goto gso;
 
-        if (skb_has_frags(skb) &&
-            !(dev->features & NETIF_F_FRAGLIST) &&
-            __skb_linearize(skb))
-                goto out_kfree_skb;
-
-        /* Fragmented skb is linearized if device does not support SG,
-         * or if at least one of fragments is in highmem and device
-         * does not support DMA from it.
-         */
-        if (skb_shinfo(skb)->nr_frags &&
-            (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) &&
-            __skb_linearize(skb))
+        /* Convert a paged skb to linear, if required */
+        if (skb_needs_linearize(skb, dev) && __skb_linearize(skb))
                 goto out_kfree_skb;
 
         /* If packet is not checksummed and device does not support
@@ -2422,6 +2462,7 @@ int netif_receive_skb(struct sk_buff *skb)
         struct packet_type *ptype, *pt_prev;
         struct net_device *orig_dev;
         struct net_device *null_or_orig;
+        struct net_device *null_or_bond;
         int ret = NET_RX_DROP;
         __be16 type;
 
@@ -2487,12 +2528,24 @@ ncls:
         if (!skb)
                 goto out;
 
+        /*
+         * Make sure frames received on VLAN interfaces stacked on
+         * bonding interfaces still make their way to any base bonding
+         * device that may have registered for a specific ptype.  The
+         * handler may have to adjust skb->dev and orig_dev.
+         */
+        null_or_bond = NULL;
+        if ((skb->dev->priv_flags & IFF_802_1Q_VLAN) &&
+            (vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING)) {
+                null_or_bond = vlan_dev_real_dev(skb->dev);
+        }
+
         type = skb->protocol;
         list_for_each_entry_rcu(ptype,
                         &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
-                if (ptype->type == type &&
-                    (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
-                     ptype->dev == orig_dev)) {
+                if (ptype->type == type && (ptype->dev == null_or_orig ||
+                     ptype->dev == skb->dev || ptype->dev == orig_dev ||
+                     ptype->dev == null_or_bond)) {
                         if (pt_prev)
                                 ret = deliver_skb(skb, pt_prev, orig_dev);
                         pt_prev = ptype;
@@ -2561,7 +2614,7 @@ out:
         return netif_receive_skb(skb);
 }
 
-void napi_gro_flush(struct napi_struct *napi)
+static void napi_gro_flush(struct napi_struct *napi)
 {
         struct sk_buff *skb, *next;
 
@@ -2574,7 +2627,6 @@ void napi_gro_flush(struct napi_struct *napi)
         napi->gro_count = 0;
         napi->gro_list = NULL;
 }
-EXPORT_SYMBOL(napi_gro_flush);
 
 enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
@@ -3185,7 +3237,7 @@ static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
 {
         const struct net_device_stats *stats = dev_get_stats(dev);
 
-        seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
+        seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
                    "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
                    dev->name, stats->rx_bytes, stats->rx_packets,
                    stats->rx_errors,
@@ -3640,10 +3692,10 @@ void __dev_set_rx_mode(struct net_device *dev)
                 /* Unicast addresses changes may only happen under the rtnl,
                  * therefore calling __dev_set_promiscuity here is safe.
                  */
-                if (dev->uc.count > 0 && !dev->uc_promisc) {
+                if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
                         __dev_set_promiscuity(dev, 1);
                         dev->uc_promisc = 1;
-                } else if (dev->uc.count == 0 && dev->uc_promisc) {
+                } else if (netdev_uc_empty(dev) && dev->uc_promisc) {
                         __dev_set_promiscuity(dev, -1);
                         dev->uc_promisc = 0;
                 }