openvswitch: add TTL decrement action

New action to decrement TTL instead of setting it to a fixed value.
This action will decrement the TTL and, in case of expired TTL, drop it
or execute an action passed via a nested attribute.
The default TTL expired action is to drop the packet.

Supports both IPv4 and IPv6 via the ttl and hop_limit fields, respectively.

Tested with a corresponding change in the userspace:

    # ovs-dpctl dump-flows
    in_port(2),eth(),eth_type(0x0800), packets:0, bytes:0, used:never, actions:dec_ttl{ttl<=1 action:(drop)},1
    in_port(1),eth(),eth_type(0x0800), packets:0, bytes:0, used:never, actions:dec_ttl{ttl<=1 action:(drop)},2
    in_port(1),eth(),eth_type(0x0806), packets:0, bytes:0, used:never, actions:2
    in_port(2),eth(),eth_type(0x0806), packets:0, bytes:0, used:never, actions:1

    # ping -c1 192.168.0.2 -t 42
    IP (tos 0x0, ttl 41, id 61647, offset 0, flags [DF], proto ICMP (1), length 84)
        192.168.0.1 > 192.168.0.2: ICMP echo request, id 386, seq 1, length 64
    # ping -c1 192.168.0.2 -t 120
    IP (tos 0x0, ttl 119, id 62070, offset 0, flags [DF], proto ICMP (1), length 84)
        192.168.0.1 > 192.168.0.2: ICMP echo request, id 388, seq 1, length 64
    # ping -c1 192.168.0.2 -t 1
    #

Co-developed-by: Bindiya Kurle <bindiyakurle@gmail.com>
Signed-off-by: Bindiya Kurle <bindiyakurle@gmail.com>
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 67 insertions, 0 deletions

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 7fbfe2adfffa..fc0efd8833c8 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -964,6 +964,25 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 	return ovs_dp_upcall(dp, skb, key, &upcall, cutlen);
 }
 
+static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb,
+				     struct sw_flow_key *key,
+				     const struct nlattr *attr, bool last)
+{
+	/* The first action is always 'OVS_DEC_TTL_ATTR_ARG'. */
+	struct nlattr *dec_ttl_arg = nla_data(attr);
+	int rem = nla_len(attr);
+
+	if (nla_len(dec_ttl_arg)) {
+		struct nlattr *actions = nla_next(dec_ttl_arg, &rem);
+
+		if (actions)
+			return clone_execute(dp, skb, key, 0, actions, rem,
+					     last, false);
+	}
+	consume_skb(skb);
+	return 0;
+}
+
 /* When 'last' is true, sample() should always consume the 'skb'.
  * Otherwise, sample() should keep 'skb' intact regardless what
  * actions are executed within sample().
@@ -1180,6 +1199,45 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
 			     nla_len(actions), last, clone_flow_key);
 }
 
+static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	int err;
+
+	if (skb->protocol == htons(ETH_P_IPV6)) {
+		struct ipv6hdr *nh;
+
+		err = skb_ensure_writable(skb, skb_network_offset(skb) +
+					  sizeof(*nh));
+		if (unlikely(err))
+			return err;
+
+		nh = ipv6_hdr(skb);
+
+		if (nh->hop_limit <= 1)
+			return -EHOSTUNREACH;
+
+		key->ip.ttl = --nh->hop_limit;
+	} else {
+		struct iphdr *nh;
+		u8 old_ttl;
+
+		err = skb_ensure_writable(skb, skb_network_offset(skb) +
+					  sizeof(*nh));
+		if (unlikely(err))
+			return err;
+
+		nh = ip_hdr(skb);
+		if (nh->ttl <= 1)
+			return -EHOSTUNREACH;
+
+		old_ttl = nh->ttl--;
+		csum_replace2(&nh->check, htons(old_ttl << 8),
+			      htons(nh->ttl << 8));
+		key->ip.ttl = nh->ttl;
+	}
+	return 0;
+}
+
 /* Execute a list of actions against 'skb'. */
 static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			      struct sw_flow_key *key,
@@ -1365,6 +1423,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 			break;
 		}
+
+		case OVS_ACTION_ATTR_DEC_TTL:
+			err = execute_dec_ttl(skb, key);
+			if (err == -EHOSTUNREACH) {
+				err = dec_ttl_exception_handler(dp, skb, key,
+								a, true);
+				return err;
+			}
+			break;
 		}
 
 		if (unlikely(err)) {