ipvlan: fix various issues in ipvlan_process_multicast()

1) netif_rx() / dev_forward_skb() should not be called from process
context.

2) ipvlan_count_rx() should be called with preemption disabled.

3) We should check if ipvlan->dev is up before feeding packets
to netif_rx()

4) We need to prevent device from disappearing if some packets
are in the multicast backlog.

5) One kfree_skb() should be a consume_skb() eventually

Fixes: ba35f8588f47 ("ipvlan: Defer multicast / broadcast processing to
a work-queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 31 insertions, 14 deletions

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index b4e990743e1d..ea6bc1e12cdf 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -207,6 +207,9 @@ void ipvlan_process_multicast(struct work_struct *work)
         spin_unlock_bh(&port->backlog.lock);
 
         while ((skb = __skb_dequeue(&list)) != NULL) {
+                struct net_device *dev = skb->dev;
+                bool consumed = false;
+
                 ethh = eth_hdr(skb);
                 hlocal = ether_addr_equal(ethh->h_source, port->dev->dev_addr);
                 mac_hash = ipvlan_mac_hash(ethh->h_dest);
@@ -219,27 +222,29 @@ void ipvlan_process_multicast(struct work_struct *work)
                 dlocal = false;
                 rcu_read_lock();
                 list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
-                        if (hlocal && (ipvlan->dev == skb->dev)) {
+                        if (hlocal && (ipvlan->dev == dev)) {
                                 dlocal = true;
                                 continue;
                         }
                         if (!test_bit(mac_hash, ipvlan->mac_filters))
                                 continue;
-
+                        if (!(ipvlan->dev->flags & IFF_UP))
+                                continue;
                         ret = NET_RX_DROP;
                         len = skb->len + ETH_HLEN;
                         nskb = skb_clone(skb, GFP_ATOMIC);
-                        if (!nskb)
-                                goto acct;
-
-                        nskb->pkt_type = pkt_type;
-                        nskb->dev = ipvlan->dev;
-                        if (hlocal)
-                                ret = dev_forward_skb(ipvlan->dev, nskb);
-                        else
-                                ret = netif_rx(nskb);
-acct:
+                        local_bh_disable();
+                        if (nskb) {
+                                consumed = true;
+                                nskb->pkt_type = pkt_type;
+                                nskb->dev = ipvlan->dev;
+                                if (hlocal)
+                                        ret = dev_forward_skb(ipvlan->dev, nskb);
+                                else
+                                        ret = netif_rx(nskb);
+                        }
                         ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
+                        local_bh_enable();
                 }
                 rcu_read_unlock();
 
@@ -249,8 +254,13 @@ acct:
                         skb->pkt_type = pkt_type;
                         dev_queue_xmit(skb);
                 } else {
-                        kfree_skb(skb);
+                        if (consumed)
+                                consume_skb(skb);
+                        else
+                                kfree_skb(skb);
                 }
+                if (dev)
+                        dev_put(dev);
         }
 }
 
@@ -479,6 +489,8 @@ static void ipvlan_multicast_enqueue(struct ipvl_port *port,
 
         spin_lock(&port->backlog.lock);
         if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) {
+                if (skb->dev)
+                        dev_hold(skb->dev);
                 __skb_queue_tail(&port->backlog, skb);
                 spin_unlock(&port->backlog.lock);
                 schedule_work(&port->wq);
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 693ec5b66222..8b0f99300cbc 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -135,6 +135,7 @@ err:
 static void ipvlan_port_destroy(struct net_device *dev)
 {
         struct ipvl_port *port = ipvlan_port_get_rtnl(dev);
+        struct sk_buff *skb;
 
         dev->priv_flags &= ~IFF_IPVLAN_MASTER;
         if (port->mode == IPVLAN_MODE_L3S) {
@@ -144,7 +145,11 @@ static void ipvlan_port_destroy(struct net_device *dev)
         }
         netdev_rx_handler_unregister(dev);
         cancel_work_sync(&port->wq);
-        __skb_queue_purge(&port->backlog);
+        while ((skb = __skb_dequeue(&port->backlog)) != NULL) {
+                if (skb->dev)
+                        dev_put(skb->dev);
+                kfree_skb(skb);
+        }
         kfree(port);
 }