[Cake] [PATCH net-next 1/5] sch_cake: fix IP protocol handling in the presence of VLAN tags

[Toke Høiland-Jørgensen]

From: Ilya Ponetayev <i.ponetaev at ndmsystems.com>

CAKE was using the return value of tc_skb_protocol() and expecting it to be
the IP protocol type. This can fail in the presence of QinQ VLAN tags,
making CAKE unable to handle ECN marking and diffserv parsing in this case.
Fix this by implementing our own version of tc_skb_protocol(), which will
use skb->protocol directly, but also parse and skip over any VLAN tags and
return the inner protocol number instead.

Also fix CE marking by implementing a version of INET_ECN_set_ce() that
uses the same parsing routine.

Fixes: ea82511518f4 ("sch_cake: Add NAT awareness to packet classifier")
Fixes: b2100cc56fca ("sch_cake: Use tc_skb_protocol() helper for getting packet protocol")
Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc")
Signed-off-by: Ilya Ponetayev <i.ponetaev at ndmsystems.com>
[ squash original two patches, rewrite commit message ]
Signed-off-by: Toke Høiland-Jørgensen <toke at redhat.com>
---
 net/sched/sch_cake.c |   52 +++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 49 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 60f8ae578819..0f594d88a957 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -497,6 +497,52 @@ static bool cobalt_queue_empty(struct cobalt_vars *vars,
 	return down;
 }
 
+static __be16 cake_skb_proto(const struct sk_buff *skb)
+{
+	unsigned int offset = skb_mac_offset(skb) + sizeof(struct ethhdr);
+	__be16 proto = skb->protocol;
+	struct vlan_hdr vhdr, *vh;
+
+	while (proto == htons(ETH_P_8021Q) || proto == htons(ETH_P_8021AD)) {
+		vh = skb_header_pointer(skb, offset, sizeof(vhdr), &vhdr);
+		if (!vh)
+			break;
+
+		proto = vh->h_vlan_encapsulated_proto;
+		offset += sizeof(vhdr);
+	}
+
+	return proto;
+}
+
+static int cake_set_ce(struct sk_buff *skb)
+{
+	int wlen = skb_network_offset(skb);
+
+	switch (cake_skb_proto(skb)) {
+	case htons(ETH_P_IP):
+		wlen += sizeof(struct iphdr);
+		if (!pskb_may_pull(skb, wlen) ||
+		    skb_try_make_writable(skb, wlen))
+			return 0;
+
+		return IP_ECN_set_ce(ip_hdr(skb));
+
+	case htons(ETH_P_IPV6):
+		wlen += sizeof(struct ipv6hdr);
+		if (!pskb_may_pull(skb, wlen) ||
+		    skb_try_make_writable(skb, wlen))
+			return 0;
+
+		return IP6_ECN_set_ce(skb, ipv6_hdr(skb));
+
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
 /* Call this with a freshly dequeued packet for possible congestion marking.
  * Returns true as an instruction to drop the packet, false for delivery.
  */
@@ -549,7 +595,7 @@ static bool cobalt_should_drop(struct cobalt_vars *vars,
 
 	if (next_due && vars->dropping) {
 		/* Use ECN mark if possible, otherwise drop */
-		drop = !(vars->ecn_marked = INET_ECN_set_ce(skb));
+		drop = !(vars->ecn_marked = cake_set_ce(skb));
 
 		vars->count++;
 		if (!vars->count)
@@ -592,7 +638,7 @@ static bool cake_update_flowkeys(struct flow_keys *keys,
 	bool rev = !skb->_nfct, upd = false;
 	__be32 ip;
 
-	if (tc_skb_protocol(skb) != htons(ETH_P_IP))
+	if (cake_skb_proto(skb) != htons(ETH_P_IP))
 		return false;
 
 	if (!nf_ct_get_tuple_skb(&tuple, skb))
@@ -1556,7 +1602,7 @@ static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
 	int wlen = skb_network_offset(skb);
 	u8 dscp;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (cake_skb_proto(skb)) {
 	case htons(ETH_P_IP):
 		wlen += sizeof(struct iphdr);
 		if (!pskb_may_pull(skb, wlen) ||