[PATCH net] ipvlan: add xmit recursion protection

[Tristan Madani]

From: Tristan Madani <tristan@xxxxxxxxxxxxxxxxxxx>

ipvlan devices can enter infinite transmit recursion when combined with
packet forwarding configurations (such as IPVS) that route traffic back
through the same ipvlan interface.

The recursion path is:

  ipvlan_start_xmit -> ipvlan_queue_xmit -> ipvlan_xmit_mode_l3
  -> ipvlan_process_outbound -> ip_local_out -> netfilter hooks
  -> dev_queue_xmit -> ipvlan_start_xmit (recurse)

The existing per-CPU xmit recursion counter in __dev_queue_xmit()
(XMIT_RECURSION_LIMIT = 8) does detect the loop, but fires too late:
each recursion level consumes roughly 2KB of stack space through
ip_local_out and netfilter, and at 8 levels the cumulative usage
exceeds the 16KB kernel stack on x86_64. The resulting stack overflow
hits the VMAP_STACK guard page and causes a kernel panic.

Add a per-CPU counter that prevents any re-entry into
ipvlan_queue_xmit() while it is already executing on the same CPU.
This mirrors the approach used by tunnel devices (see
IP_TUNNEL_RECURSION_LIMIT in ip_tunnels.h) but with a stricter limit
appropriate for ipvlan.

Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Tristan Madani <tristan@xxxxxxxxxxxxxxxxxxx>
---
 drivers/net/ipvlan/ipvlan_core.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 835e04835..ab99eb624 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -9,6 +9,8 @@
 
 static u32 ipvlan_jhash_secret __read_mostly;
 
+static DEFINE_PER_CPU(int, ipvlan_xmit_depth);
+
 void ipvlan_init_secret(void)
 {
 	net_get_random_once(&ipvlan_jhash_secret, sizeof(ipvlan_jhash_secret));
@@ -676,6 +678,7 @@ int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 	struct ipvl_port *port = ipvlan_port_get_rcu_bh(ipvlan->phy_dev);
+	int ret = NET_XMIT_DROP;
 
 	if (!port)
 		goto out;
@@ -683,18 +686,32 @@ int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr))))
 		goto out;
 
+	if (this_cpu_read(ipvlan_xmit_depth)) {
+		net_crit_ratelimited("ipvlan: xmit recursion detected on dev %s\n",
+				     dev->name);
+		goto out;
+	}
+
+	this_cpu_inc(ipvlan_xmit_depth);
 	switch(port->mode) {
 	case IPVLAN_MODE_L2:
-		return ipvlan_xmit_mode_l2(skb, dev);
+		ret = ipvlan_xmit_mode_l2(skb, dev);
+		break;
 	case IPVLAN_MODE_L3:
 #ifdef CONFIG_IPVLAN_L3S
 	case IPVLAN_MODE_L3S:
 #endif
-		return ipvlan_xmit_mode_l3(skb, dev);
+		ret = ipvlan_xmit_mode_l3(skb, dev);
+		break;
+	default:
+		WARN_ONCE(true, "%s called for mode = [%x]\n",
+			  __func__, port->mode);
+		kfree_skb(skb);
+		break;
 	}
+	this_cpu_dec(ipvlan_xmit_depth);
+	return ret;
 
-	/* Should not reach here */
-	WARN_ONCE(true, "%s called for mode = [%x]\n", __func__, port->mode);
 out:
 	kfree_skb(skb);
 	return NET_XMIT_DROP;
-- 
2.47.3