Merge branch 'net-sched-flower-num-vlan-tags'

Boris Sukholitko says:

====================
net/sched: flower: match on the number of vlan tags

Our customers in the fiber telecom world have network configurations
where they would like to control their traffic according to the number
of tags appearing in the packet.

For example, TR247 GPON conformance test suite specification mostly
talks about untagged, single, double tagged packets and gives lax
guidelines on the vlan protocol vs. number of vlan tags.

This is different from the common IT networks where 802.1Q and 802.1ad
protocols are usually describe single and double tagged packet. GPON
configurations that we work with have arbitrary mix the above protocols
and number of vlan tags in the packet.

The following patch series implement number of vlans flower filter. They
add num_of_vlans flower filter as an alternative to vlan ethtype protocol
matching. The end result is that the following command becomes possible:

tc filter add dev eth1 ingress flower \
  num_of_vlans 1 vlan_prio 5 action drop

Also, from our logs, we have redirect rules such that:

tc filter add dev $GPON ingress flower num_of_vlans $N \
     action mirred egress redirect dev $DEV

where N can range from 0 to 3 and $DEV is the function of $N.

Also there are rules setting skb mark based on the number of vlans:

tc filter add dev $GPON ingress flower num_of_vlans $N vlan_prio \
    $P action skbedit mark $M

More about the patch series:
  - patches 1-2 remove duplicate code by introducing is_key_vlan
    helper.
  - patch 3, 4 implement num_of_vlans in the dissector and in the
    flower.
  - patch 5 uses the num_of_vlans filter to allow further matching on
    vlan attributes.

Complementary iproute2 patches are being sent separately.

Thanks,
Boris.

- v4: rebased to the latest net-next
- v3:
    - more example commands in patch 3 description (request by Jamal)
    - patch 5 description made clearer (thanks to Jiri)
- v2:
    - add suitable subject prefixes
    - more evolved patch 5 description
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/flow_dissector.h

@@ -253,6 +253,14 @@ struct flow_dissector_key_hash {
 	u32 hash;
 };
 
+/**
+ * struct flow_dissector_key_num_of_vlans:
+ * @num_of_vlans: num_of_vlans value
+ */
+struct flow_dissector_key_num_of_vlans {
+	u8 num_of_vlans;
+};
+
 enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */
 	FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
@@ -282,6 +290,7 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */
 	FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */
 	FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */
+	FLOW_DISSECTOR_KEY_NUM_OF_VLANS, /* struct flow_dissector_key_num_of_vlans */
 
 	FLOW_DISSECTOR_KEY_MAX,
 };

include/uapi/linux/pkt_cls.h

@@ -587,6 +587,8 @@ enum {
 	TCA_FLOWER_KEY_HASH,		/* u32 */
 	TCA_FLOWER_KEY_HASH_MASK,	/* u32 */
 
+	TCA_FLOWER_KEY_NUM_OF_VLANS,    /* u8 */
+
 	__TCA_FLOWER_MAX,
 };
 

net/core/flow_dissector.c

@@ -1035,6 +1035,16 @@ bool __skb_flow_dissect(const struct net *net,
 		memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs));
 	}
 
+	if (dissector_uses_key(flow_dissector,
+			       FLOW_DISSECTOR_KEY_NUM_OF_VLANS)) {
+		struct flow_dissector_key_num_of_vlans *key_num_of_vlans;
+
+		key_num_of_vlans = skb_flow_dissector_target(flow_dissector,
+							     FLOW_DISSECTOR_KEY_NUM_OF_VLANS,
+							     target_container);
+		key_num_of_vlans->num_of_vlans = 0;
+	}
+
 proto_again:
 	fdret = FLOW_DISSECT_RET_CONTINUE;
 
@@ -1158,6 +1168,16 @@ bool __skb_flow_dissect(const struct net *net,
 			nhoff += sizeof(*vlan);
 		}
 
+		if (dissector_uses_key(flow_dissector,
+				       FLOW_DISSECTOR_KEY_NUM_OF_VLANS)) {
+			struct flow_dissector_key_num_of_vlans *key_nvs;
+
+			key_nvs = skb_flow_dissector_target(flow_dissector,
+							    FLOW_DISSECTOR_KEY_NUM_OF_VLANS,
+							    target_container);
+			key_nvs->num_of_vlans++;
+		}
+
 		if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) {
 			dissector_vlan = FLOW_DISSECTOR_KEY_VLAN;
 		} else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) {

net/sched/cls_flower.c

@@ -72,6 +72,7 @@ struct fl_flow_key {
 	} tp_range;
 	struct flow_dissector_key_ct ct;
 	struct flow_dissector_key_hash hash;
+	struct flow_dissector_key_num_of_vlans num_of_vlans;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -712,6 +713,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_FLAGS]		= { .type = NLA_U32 },
 	[TCA_FLOWER_KEY_HASH]		= { .type = NLA_U32 },
 	[TCA_FLOWER_KEY_HASH_MASK]	= { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_NUM_OF_VLANS]	= { .type = NLA_U8 },
 
 };
 
@@ -1028,8 +1030,10 @@ static void fl_set_key_vlan(struct nlattr **tb,
 			VLAN_PRIORITY_MASK;
 		key_mask->vlan_priority = VLAN_PRIORITY_MASK;
 	}
+	if (ethertype) {
 		key_val->vlan_tpid = ethertype;
 		key_mask->vlan_tpid = cpu_to_be16(~0);
+	}
 	if (tb[vlan_next_eth_type_key]) {
 		key_val->vlan_eth_type =
 			nla_get_be16(tb[vlan_next_eth_type_key]);
@@ -1579,6 +1583,26 @@ static int fl_set_key_ct(struct nlattr **tb,
 	return 0;
 }
 
+static bool is_vlan_key(struct nlattr *tb, __be16 *ethertype,
+			struct fl_flow_key *key, struct fl_flow_key *mask,
+			int vthresh)
+{
+	const bool good_num_of_vlans = key->num_of_vlans.num_of_vlans > vthresh;
+
+	if (!tb) {
+		*ethertype = 0;
+		return good_num_of_vlans;
+	}
+
+	*ethertype = nla_get_be16(tb);
+	if (good_num_of_vlans || eth_type_vlan(*ethertype))
+		return true;
+
+	key->basic.n_proto = *ethertype;
+	mask->basic.n_proto = cpu_to_be16(~0);
+	return false;
+}
+
 static int fl_set_key(struct net *net, struct nlattr **tb,
 		      struct fl_flow_key *key, struct fl_flow_key *mask,
 		      struct netlink_ext_ack *extack)
@@ -1600,19 +1624,20 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 	fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC,
 		       mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK,
 		       sizeof(key->eth.src));
+	fl_set_key_val(tb, &key->num_of_vlans,
+		       TCA_FLOWER_KEY_NUM_OF_VLANS,
+		       &mask->num_of_vlans,
+		       TCA_FLOWER_UNSPEC,
+		       sizeof(key->num_of_vlans));
 
-	if (tb[TCA_FLOWER_KEY_ETH_TYPE]) {
-		ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_ETH_TYPE]);
-
-		if (eth_type_vlan(ethertype)) {
+	if (is_vlan_key(tb[TCA_FLOWER_KEY_ETH_TYPE], &ethertype, key, mask, 0)) {
 		fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID,
 				TCA_FLOWER_KEY_VLAN_PRIO,
 				TCA_FLOWER_KEY_VLAN_ETH_TYPE,
 				&key->vlan, &mask->vlan);
 
-			if (tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]) {
-				ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]);
-				if (eth_type_vlan(ethertype)) {
+		if (is_vlan_key(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE],
+				&ethertype, key, mask, 1)) {
 			fl_set_key_vlan(tb, ethertype,
 					TCA_FLOWER_KEY_CVLAN_ID,
 					TCA_FLOWER_KEY_CVLAN_PRIO,
@@ -1623,14 +1648,6 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 				       &mask->basic.n_proto,
 				       TCA_FLOWER_UNSPEC,
 				       sizeof(key->basic.n_proto));
-				} else {
-					key->basic.n_proto = ethertype;
-					mask->basic.n_proto = cpu_to_be16(~0);
-				}
-			}
-		} else {
-			key->basic.n_proto = ethertype;
-			mask->basic.n_proto = cpu_to_be16(~0);
 		}
 	}
 
@@ -1904,6 +1921,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
 			     FLOW_DISSECTOR_KEY_CT, ct);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_HASH, hash);
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+			     FLOW_DISSECTOR_KEY_NUM_OF_VLANS, num_of_vlans);
 
 	skb_flow_dissector_init(dissector, keys, cnt);
 }
@@ -2992,6 +3011,11 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
 			    sizeof(key->basic.n_proto)))
 		goto nla_put_failure;
 
+	if (mask->num_of_vlans.num_of_vlans) {
+		if (nla_put_u8(skb, TCA_FLOWER_KEY_NUM_OF_VLANS, key->num_of_vlans.num_of_vlans))
+			goto nla_put_failure;
+	}
+
 	if (fl_dump_key_mpls(skb, &key->mpls, &mask->mpls))
 		goto nla_put_failure;