net/sched: cls_flower: Classify packet in ip tunnels

Introduce classifying by metadata extracted by the tunnel device.
Outer header fields - source/dest ip and tunnel id, are extracted from
the metadata when classifying.

For example, the following will add a filter on the ingress Qdisc of shared
vxlan device named 'vxlan0'. To forward packets with outer src ip
11.11.0.2, dst ip 11.11.0.1 and tunnel id 11. The packets will be
forwarded to tap device 'vnet0' (after metadata is released):

$ tc filter add dev vxlan0 protocol ip parent ffff: \
    flower \
      enc_src_ip 11.11.0.2 \
      enc_dst_ip 11.11.0.1 \
      enc_key_id 11 \
      dst_ip 11.11.11.1 \
    action tunnel_key release \
    action mirred egress redirect dev vnet0

The action tunnel_key, will be introduced in the next patch in this
series.

Signed-off-by: Amir Vadai <amir@vadai.me>
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index cf9ad5b..b084b2a 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -23,9 +23,13 @@
 #include <net/ip.h>
 #include <net/flow_dissector.h>
 
+#include <net/dst.h>
+#include <net/dst_metadata.h>
+
 struct fl_flow_key {
 	int	indev_ifindex;
 	struct flow_dissector_key_control control;
+	struct flow_dissector_key_control enc_control;
 	struct flow_dissector_key_basic basic;
 	struct flow_dissector_key_eth_addrs eth;
 	struct flow_dissector_key_vlan vlan;
@@ -35,6 +39,11 @@
 		struct flow_dissector_key_ipv6_addrs ipv6;
 	};
 	struct flow_dissector_key_ports tp;
+	struct flow_dissector_key_keyid enc_key_id;
+	union {
+		struct flow_dissector_key_ipv4_addrs enc_ipv4;
+		struct flow_dissector_key_ipv6_addrs enc_ipv6;
+	};
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -124,11 +133,31 @@
 	struct cls_fl_filter *f;
 	struct fl_flow_key skb_key;
 	struct fl_flow_key skb_mkey;
+	struct ip_tunnel_info *info;
 
 	if (!atomic_read(&head->ht.nelems))
 		return -1;
 
 	fl_clear_masked_range(&skb_key, &head->mask);
+
+	info = skb_tunnel_info(skb);
+	if (info) {
+		struct ip_tunnel_key *key = &info->key;
+
+		switch (ip_tunnel_info_af(info)) {
+		case AF_INET:
+			skb_key.enc_ipv4.src = key->u.ipv4.src;
+			skb_key.enc_ipv4.dst = key->u.ipv4.dst;
+			break;
+		case AF_INET6:
+			skb_key.enc_ipv6.src = key->u.ipv6.src;
+			skb_key.enc_ipv6.dst = key->u.ipv6.dst;
+			break;
+		}
+
+		skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id);
+	}
+
 	skb_key.indev_ifindex = skb->skb_iif;
 	/* skb_flow_dissect() does not set n_proto in case an unknown protocol,
 	 * so do it rather here.
@@ -297,7 +326,15 @@
 	[TCA_FLOWER_KEY_VLAN_ID]	= { .type = NLA_U16 },
 	[TCA_FLOWER_KEY_VLAN_PRIO]	= { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_VLAN_ETH_TYPE]	= { .type = NLA_U16 },
-
+	[TCA_FLOWER_KEY_ENC_KEY_ID]	= { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_IPV4_SRC]	= { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK] = { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_IPV4_DST]	= { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_IPV4_DST_MASK] = { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_ENC_IPV6_SRC]	= { .len = sizeof(struct in6_addr) },
+	[TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK] = { .len = sizeof(struct in6_addr) },
+	[TCA_FLOWER_KEY_ENC_IPV6_DST]	= { .len = sizeof(struct in6_addr) },
+	[TCA_FLOWER_KEY_ENC_IPV6_DST_MASK] = { .len = sizeof(struct in6_addr) },
 };
 
 static void fl_set_key_val(struct nlattr **tb,
@@ -409,6 +446,40 @@
 			       sizeof(key->tp.dst));
 	}
 
+	if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] ||
+	    tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) {
+		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+		fl_set_key_val(tb, &key->enc_ipv4.src,
+			       TCA_FLOWER_KEY_ENC_IPV4_SRC,
+			       &mask->enc_ipv4.src,
+			       TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,
+			       sizeof(key->enc_ipv4.src));
+		fl_set_key_val(tb, &key->enc_ipv4.dst,
+			       TCA_FLOWER_KEY_ENC_IPV4_DST,
+			       &mask->enc_ipv4.dst,
+			       TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,
+			       sizeof(key->enc_ipv4.dst));
+	}
+
+	if (tb[TCA_FLOWER_KEY_ENC_IPV6_SRC] ||
+	    tb[TCA_FLOWER_KEY_ENC_IPV6_DST]) {
+		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+		fl_set_key_val(tb, &key->enc_ipv6.src,
+			       TCA_FLOWER_KEY_ENC_IPV6_SRC,
+			       &mask->enc_ipv6.src,
+			       TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,
+			       sizeof(key->enc_ipv6.src));
+		fl_set_key_val(tb, &key->enc_ipv6.dst,
+			       TCA_FLOWER_KEY_ENC_IPV6_DST,
+			       &mask->enc_ipv6.dst,
+			       TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,
+			       sizeof(key->enc_ipv6.dst));
+	}
+
+	fl_set_key_val(tb, &key->enc_key_id.keyid, TCA_FLOWER_KEY_ENC_KEY_ID,
+		       &mask->enc_key_id.keyid, TCA_FLOWER_KEY_ENC_KEY_ID,
+		       sizeof(key->enc_key_id.keyid));
+
 	return 0;
 }
 
@@ -821,6 +892,33 @@
 				  sizeof(key->tp.dst))))
 		goto nla_put_failure;
 
+	if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
+	    (fl_dump_key_val(skb, &key->enc_ipv4.src,
+			    TCA_FLOWER_KEY_ENC_IPV4_SRC, &mask->enc_ipv4.src,
+			    TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,
+			    sizeof(key->enc_ipv4.src)) ||
+	     fl_dump_key_val(skb, &key->enc_ipv4.dst,
+			     TCA_FLOWER_KEY_ENC_IPV4_DST, &mask->enc_ipv4.dst,
+			     TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,
+			     sizeof(key->enc_ipv4.dst))))
+		goto nla_put_failure;
+	else if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS &&
+		 (fl_dump_key_val(skb, &key->enc_ipv6.src,
+			    TCA_FLOWER_KEY_ENC_IPV6_SRC, &mask->enc_ipv6.src,
+			    TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,
+			    sizeof(key->enc_ipv6.src)) ||
+		 fl_dump_key_val(skb, &key->enc_ipv6.dst,
+				 TCA_FLOWER_KEY_ENC_IPV6_DST,
+				 &mask->enc_ipv6.dst,
+				 TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,
+			    sizeof(key->enc_ipv6.dst))))
+		goto nla_put_failure;
+
+	if (fl_dump_key_val(skb, &key->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID,
+			    &mask->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID,
+			    sizeof(key->enc_key_id)))
+		goto nla_put_failure;
+
 	nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags);
 
 	if (tcf_exts_dump(skb, &f->exts))