net: openvswitch: add psample action

Add support for a new action: psample.

This action accepts a u32 group id and a variable-length cookie and uses
the psample multicast group to make the packet available for
observability.

The maximum length of the user-defined cookie is set to 16, same as
tc_cookie, to discourage using cookies that will not be offloadable.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Aaron Conole <aconole@redhat.com>
Reviewed-by: Ilya Maximets <i.maximets@ovn.org>
Acked-by: Eelco Chaudron <echaudro@redhat.com>
Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
Link: https://patch.msgid.link/20240704085710.353845-6-amorenoz@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/netlink/specs/ovs_flow.yaml

@@ -727,6 +727,12 @@ attribute-sets:
         name: dec-ttl
         type: nest
         nested-attributes: dec-ttl-attrs
+      -
+        name: psample
+        type: nest
+        nested-attributes: psample-attrs
+        doc: |
+          Sends a packet sample to psample for external observation.
   -
     name: tunnel-key-attrs
     enum-name: ovs-tunnel-key-attr
@@ -938,6 +944,17 @@ attribute-sets:
       -
         name: gbp
         type: u32
+  -
+    name: psample-attrs
+    enum-name: ovs-psample-attr
+    name-prefix: ovs-psample-attr-
+    attributes:
+      -
+        name: group
+        type: u32
+      -
+        name: cookie
+        type: binary
 
 operations:
   name-prefix: ovs-flow-cmd-

include/uapi/linux/openvswitch.h

@@ -914,6 +914,31 @@ struct check_pkt_len_arg {
 };
 #endif
 
+#define OVS_PSAMPLE_COOKIE_MAX_SIZE 16
+/**
+ * enum ovs_psample_attr - Attributes for %OVS_ACTION_ATTR_PSAMPLE
+ * action.
+ *
+ * @OVS_PSAMPLE_ATTR_GROUP: 32-bit number to identify the source of the
+ * sample.
+ * @OVS_PSAMPLE_ATTR_COOKIE: An optional variable-length binary cookie that
+ * contains user-defined metadata. The maximum length is
+ * OVS_PSAMPLE_COOKIE_MAX_SIZE bytes.
+ *
+ * Sends the packet to the psample multicast group with the specified group and
+ * cookie. It is possible to combine this action with the
+ * %OVS_ACTION_ATTR_TRUNC action to limit the size of the sample.
+ */
+enum ovs_psample_attr {
+	OVS_PSAMPLE_ATTR_GROUP = 1,	/* u32 number. */
+	OVS_PSAMPLE_ATTR_COOKIE,	/* Optional, user specified cookie. */
+
+	/* private: */
+	__OVS_PSAMPLE_ATTR_MAX
+};
+
+#define OVS_PSAMPLE_ATTR_MAX (__OVS_PSAMPLE_ATTR_MAX - 1)
+
 /**
  * enum ovs_action_attr - Action types.
  *
@@ -966,6 +991,8 @@ struct check_pkt_len_arg {
  * of l3 tunnel flag in the tun_flags field of OVS_ACTION_ATTR_ADD_MPLS
  * argument.
  * @OVS_ACTION_ATTR_DROP: Explicit drop action.
+ * @OVS_ACTION_ATTR_PSAMPLE: Send a sample of the packet to external observers
+ * via psample.
  *
  * Only a single header can be set with a single %OVS_ACTION_ATTR_SET.  Not all
  * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
@@ -1004,6 +1031,7 @@ enum ovs_action_attr {
 	OVS_ACTION_ATTR_ADD_MPLS,     /* struct ovs_action_add_mpls. */
 	OVS_ACTION_ATTR_DEC_TTL,      /* Nested OVS_DEC_TTL_ATTR_*. */
 	OVS_ACTION_ATTR_DROP,         /* u32 error code. */
+	OVS_ACTION_ATTR_PSAMPLE,      /* Nested OVS_PSAMPLE_ATTR_*. */
 
 	__OVS_ACTION_ATTR_MAX,	      /* Nothing past this will be accepted
 				       * from userspace. */

net/openvswitch/Kconfig

@@ -10,6 +10,7 @@ config OPENVSWITCH
 		   (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \
 				     (!NF_NAT || NF_NAT) && \
 				     (!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT)))
+	depends on PSAMPLE || !PSAMPLE
 	select LIBCRC32C
 	select MPLS
 	select NET_MPLS_GSO

net/openvswitch/actions.c

@@ -24,6 +24,11 @@
 #include <net/checksum.h>
 #include <net/dsfield.h>
 #include <net/mpls.h>
+
+#if IS_ENABLED(CONFIG_PSAMPLE)
+#include <net/psample.h>
+#endif
+
 #include <net/sctp/checksum.h>
 
 #include "datapath.h"
@@ -1299,6 +1304,40 @@ static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key)
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_PSAMPLE)
+static void execute_psample(struct datapath *dp, struct sk_buff *skb,
+			    const struct nlattr *attr)
+{
+	struct psample_group psample_group = {};
+	struct psample_metadata md = {};
+	const struct nlattr *a;
+	int rem;
+
+	nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) {
+		switch (nla_type(a)) {
+		case OVS_PSAMPLE_ATTR_GROUP:
+			psample_group.group_num = nla_get_u32(a);
+			break;
+
+		case OVS_PSAMPLE_ATTR_COOKIE:
+			md.user_cookie = nla_data(a);
+			md.user_cookie_len = nla_len(a);
+			break;
+		}
+	}
+
+	psample_group.net = ovs_dp_get_net(dp);
+	md.in_ifindex = OVS_CB(skb)->input_vport->dev->ifindex;
+	md.trunc_size = skb->len - OVS_CB(skb)->cutlen;
+
+	psample_sample_packet(&psample_group, skb, 0, &md);
+}
+#else
+static void execute_psample(struct datapath *dp, struct sk_buff *skb,
+			    const struct nlattr *attr)
+{}
+#endif
+
 /* Execute a list of actions against 'skb'. */
 static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			      struct sw_flow_key *key,
@@ -1502,6 +1541,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			ovs_kfree_skb_reason(skb, reason);
 			return 0;
 		}
+
+		case OVS_ACTION_ATTR_PSAMPLE:
+			execute_psample(dp, skb, a);
+			OVS_CB(skb)->cutlen = 0;
+			if (nla_is_last(a, rem)) {
+				consume_skb(skb);
+				return 0;
+			}
+			break;
 		}
 
 		if (unlikely(err)) {

net/openvswitch/flow_netlink.c

@@ -64,6 +64,7 @@ static bool actions_may_change_flow(const struct nlattr *actions)
 		case OVS_ACTION_ATTR_TRUNC:
 		case OVS_ACTION_ATTR_USERSPACE:
 		case OVS_ACTION_ATTR_DROP:
+		case OVS_ACTION_ATTR_PSAMPLE:
 			break;
 
 		case OVS_ACTION_ATTR_CT:
@@ -2409,7 +2410,7 @@ static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len)
 	/* Whenever new actions are added, the need to update this
 	 * function should be considered.
 	 */
-	BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 24);
+	BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 25);
 
 	if (!actions)
 		return;
@@ -3157,6 +3158,28 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 	return 0;
 }
 
+static int validate_psample(const struct nlattr *attr)
+{
+	static const struct nla_policy policy[OVS_PSAMPLE_ATTR_MAX + 1] = {
+		[OVS_PSAMPLE_ATTR_GROUP] = { .type = NLA_U32 },
+		[OVS_PSAMPLE_ATTR_COOKIE] = {
+			.type = NLA_BINARY,
+			.len = OVS_PSAMPLE_COOKIE_MAX_SIZE,
+		},
+	};
+	struct nlattr *a[OVS_PSAMPLE_ATTR_MAX + 1];
+	int err;
+
+	if (!IS_ENABLED(CONFIG_PSAMPLE))
+		return -EOPNOTSUPP;
+
+	err = nla_parse_nested(a, OVS_PSAMPLE_ATTR_MAX, attr, policy, NULL);
+	if (err)
+		return err;
+
+	return a[OVS_PSAMPLE_ATTR_GROUP] ? 0 : -EINVAL;
+}
+
 static int copy_action(const struct nlattr *from,
 		       struct sw_flow_actions **sfa, bool log)
 {
@@ -3212,6 +3235,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			[OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls),
 			[OVS_ACTION_ATTR_DEC_TTL] = (u32)-1,
 			[OVS_ACTION_ATTR_DROP] = sizeof(u32),
+			[OVS_ACTION_ATTR_PSAMPLE] = (u32)-1,
 		};
 		const struct ovs_action_push_vlan *vlan;
 		int type = nla_type(a);
@@ -3490,6 +3514,12 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				return -EINVAL;
 			break;
 
+		case OVS_ACTION_ATTR_PSAMPLE:
+			err = validate_psample(a);
+			if (err)
+				return err;
+			break;
+
 		default:
 			OVS_NLERR(log, "Unknown Action type %d", type);
 			return -EINVAL;