[PATCH net-next] macvlan: handle fragmented multicast frames

[Eric Dumazet <eric.dumazet@gmail.com>]

Le mercredi 05 octobre 2011 à 15:35 -0700, Ben Greear a écrit :

> If someone wants to cook up macvlan-ip-defrag patch I'll be happy
> to test it.  But, as far as I can tell, this problem can happen on
> any two interfaces.  The reason that some of mine work (.1q vlans)
> and macvlan didn't is probably because those were separated by
> some virtual network links that imparted extra delay...so the
> vlan consumed all its fragments and passed the complete pkt up
> the stack before the mac-vlan ever saw the initial frame.
> 
> With this in mind, it seems that using multiple udp multicast
> sockets bound to specific devices is fundamentally broken for
> fragmented packets.
> 
> I have no pressing need for this feature, so now that I better understand
> the problem I can just document it and move on to other things.
> 
> Thanks for all the help.
> 

Please test following patch (note I had no time to test it, sorry !)

Based on net-next tree, might apply on 3.0 kernel...

[PATCH net-next] macvlan: handle fragmented multicast frames

Fragmented multicast frames are delivered to a single macvlan port,
because ip defrag logic considers other samples are redundant.

Implement a defrag step before trying to send the multicast frame.

Reported-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
 drivers/net/macvlan.c  |    3 +++
 include/net/ip.h       |    9 +++++++++
 net/ipv4/ip_fragment.c |   36 ++++++++++++++++++++++++++++++++++++
 net/packet/af_packet.c |   39 +--------------------------------------

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index b100c90..40366eb 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -169,6 +169,9 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 
 	port = macvlan_port_get_rcu(skb->dev);
 	if (is_multicast_ether_addr(eth->h_dest)) {
+		skb = ip_check_defrag(skb, IP_DEFRAG_MACVLAN);
+		if (!skb)
+			return RX_HANDLER_CONSUMED;
 		src = macvlan_hash_lookup(port, eth->h_source);
 		if (!src)
 			/* frame comes from an external address */
diff --git a/include/net/ip.h b/include/net/ip.h
index aa76c7a..c7e066a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -406,9 +406,18 @@ enum ip_defrag_users {
 	IP_DEFRAG_VS_OUT,
 	IP_DEFRAG_VS_FWD,
 	IP_DEFRAG_AF_PACKET,
+	IP_DEFRAG_MACVLAN,
 };
 
 int ip_defrag(struct sk_buff *skb, u32 user);
+#ifdef CONFIG_INET
+struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user);
+#else
+static inline struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
+{
+	return skb;
+}
+#endif
 int ip_frag_mem(struct net *net);
 int ip_frag_nqueues(struct net *net);
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 0e0ab98..763589a 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -682,6 +682,42 @@ int ip_defrag(struct sk_buff *skb, u32 user)
 }
 EXPORT_SYMBOL(ip_defrag);
 
+struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
+{
+	const struct iphdr *iph;
+	u32 len;
+
+	if (skb->protocol != htons(ETH_P_IP))
+		return skb;
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		return skb;
+
+	iph = ip_hdr(skb);
+	if (iph->ihl < 5 || iph->version != 4)
+		return skb;
+	if (!pskb_may_pull(skb, iph->ihl*4))
+		return skb;
+	iph = ip_hdr(skb);
+	len = ntohs(iph->tot_len);
+	if (skb->len < len || len < (iph->ihl * 4))
+		return skb;
+
+	if (ip_is_fragment(ip_hdr(skb))) {
+		skb = skb_share_check(skb, GFP_ATOMIC);
+		if (skb) {
+			if (pskb_trim_rcsum(skb, len))
+				return skb;
+			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+			if (ip_defrag(skb, user))
+				return NULL;
+			skb->rxhash = 0;
+		}
+	}
+	return skb;
+}
+EXPORT_SYMBOL(ip_check_defrag);
+
 #ifdef CONFIG_SYSCTL
 static int zero;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 25e68f5..ff9eed7 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1213,43 +1213,6 @@ static struct sock *fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *sk
 	return f->arr[cpu % num];
 }
 
-static struct sk_buff *fanout_check_defrag(struct sk_buff *skb)
-{
-#ifdef CONFIG_INET
-	const struct iphdr *iph;
-	u32 len;
-
-	if (skb->protocol != htons(ETH_P_IP))
-		return skb;
-
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		return skb;
-
-	iph = ip_hdr(skb);
-	if (iph->ihl < 5 || iph->version != 4)
-		return skb;
-	if (!pskb_may_pull(skb, iph->ihl*4))
-		return skb;
-	iph = ip_hdr(skb);
-	len = ntohs(iph->tot_len);
-	if (skb->len < len || len < (iph->ihl * 4))
-		return skb;
-
-	if (ip_is_fragment(ip_hdr(skb))) {
-		skb = skb_share_check(skb, GFP_ATOMIC);
-		if (skb) {
-			if (pskb_trim_rcsum(skb, len))
-				return skb;
-			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
-			if (ip_defrag(skb, IP_DEFRAG_AF_PACKET))
-				return NULL;
-			skb->rxhash = 0;
-		}
-	}
-#endif
-	return skb;
-}
-
 static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			     struct packet_type *pt, struct net_device *orig_dev)
 {
@@ -1268,7 +1231,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 	case PACKET_FANOUT_HASH:
 	default:
 		if (f->defrag) {
-			skb = fanout_check_defrag(skb);
+			skb = ip_check_defrag(skb, IP_DEFRAG_AF_PACKET);
 			if (!skb)
 				return 0;
 		}