vxlan: test dev->flags & IFF_UP before calling netif_rx()

netif_rx() must be called under a strict contract.

At device dismantle phase, core networking clears IFF_UP
and flush_all_backlogs() is called after rcu grace period
to make sure no incoming packet might be in a cpu backlog
and still referencing the device.

Most drivers call netif_rx() from their interrupt handler,
and since the interrupts are disabled at device dismantle,
netif_rx() does not have to check dev->flags & IFF_UP

Virtual drivers do not have this guarantee, and must
therefore make the check themselves.

Otherwise we risk use-after-free and/or crashes.

Note this patch also fixes a small issue that came
with commit ce6502a8f957 ("vxlan: fix a use after free
in vxlan_encap_bypass"), since the dev->stats.rx_dropped
change was done on the wrong device.

Fixes: d342894c5d2f ("vxlan: virtual extensible lan")
Fixes: ce6502a8f957 ("vxlan: fix a use after free in vxlan_encap_bypass")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Petr Machata <petrm@mellanox.com>
Cc: Ido Schimmel <idosch@mellanox.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 5209ee9aac47846367d7f469a7e69d08c030087e..2aae11feff0c22c1b073a6a119fc6c311cbe1691 100644 (file)
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2219,7 +2219,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
        struct pcpu_sw_netstats *tx_stats, *rx_stats;
        union vxlan_addr loopback;
        union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
-       struct net_device *dev = skb->dev;
+       struct net_device *dev;
        int len = skb->len;
 
        tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
@@ -2239,9 +2239,15 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 #endif
        }
 
+       rcu_read_lock();
+       dev = skb->dev;
+       if (unlikely(!(dev->flags & IFF_UP))) {
+               kfree_skb(skb);
+               goto drop;
+       }
+
        if (dst_vxlan->cfg.flags & VXLAN_F_LEARN)
-               vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source, 0,
-                           vni);
+               vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni);
 
        u64_stats_update_begin(&tx_stats->syncp);
        tx_stats->tx_packets++;
@@ -2254,8 +2260,10 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
                rx_stats->rx_bytes += len;
                u64_stats_update_end(&rx_stats->syncp);
        } else {
+drop:
                dev->stats.rx_dropped++;
        }
+       rcu_read_unlock();
 }
 
 static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev,