Merge branch 'net-openvswitch-add-sample-multicasting'

Adrian Moreno says:

====================
net: openvswitch: Add sample multicasting.

** Background **
Currently, OVS supports several packet sampling mechanisms (sFlow,
per-bridge IPFIX, per-flow IPFIX). These end up being translated into a
userspace action that needs to be handled by ovs-vswitchd's handler
threads only to be forwarded to some third party application that
will somehow process the sample and provide observability on the
datapath.

A particularly interesting use-case is controller-driven
per-flow IPFIX sampling where the OpenFlow controller can add metadata
to samples (via two 32bit integers) and this metadata is then available
to the sample-collecting system for correlation.

** Problem **
The fact that sampled traffic share netlink sockets and handler thread
time with upcalls, apart from being a performance bottleneck in the
sample extraction itself, can severely compromise the datapath,
yielding this solution unfit for highly loaded production systems.

Users are left with little options other than guessing what sampling
rate will be OK for their traffic pattern and system load and dealing
with the lost accuracy.

Looking at available infrastructure, an obvious candidated would be
to use psample. However, it's current state does not help with the
use-case at stake because sampled packets do not contain user-defined
metadata.

** Proposal **
This series is an attempt to fix this situation by extending the
existing psample infrastructure to carry a variable length
user-defined cookie.

The main existing user of psample is tc's act_sample. It is also
extended to forward the action's cookie to psample.

Finally, a new OVS action (OVS_SAMPLE_ATTR_PSAMPLE) is created.
It accepts a group and an optional cookie and uses psample to
multicast the packet and the metadata.
====================

Link: https://patch.msgid.link/20240704085710.353845-1-amorenoz@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 64 insertions, 2 deletions

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 964225580824..101f9a23792c 100644
--- a/net/openvswitch/actions.c
+++ b/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"
@@ -1043,12 +1048,15 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 	struct nlattr *sample_arg;
 	int rem = nla_len(attr);
 	const struct sample_arg *arg;
+	u32 init_probability;
 	bool clone_flow_key;
+	int err;
 
 	/* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */
 	sample_arg = nla_data(attr);
 	arg = nla_data(sample_arg);
 	actions = nla_next(sample_arg, &rem);
+	init_probability = OVS_CB(skb)->probability;
 
 	if ((arg->probability != U32_MAX) &&
 	    (!arg->probability || get_random_u32() > arg->probability)) {
@@ -1057,9 +1065,16 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 		return 0;
 	}
 
+	OVS_CB(skb)->probability = arg->probability;
+
 	clone_flow_key = !arg->exec;
-	return clone_execute(dp, skb, key, 0, actions, rem, last,
-			     clone_flow_key);
+	err = clone_execute(dp, skb, key, 0, actions, rem, last,
+			    clone_flow_key);
+
+	if (!last)
+		OVS_CB(skb)->probability = init_probability;
+
+	return err;
 }
 
 /* When 'last' is true, clone() should always consume the 'skb'.
@@ -1299,6 +1314,44 @@ 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;
+	u32 rate;
+	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;
+	md.rate_as_probability = 1;
+
+	rate = OVS_CB(skb)->probability ? OVS_CB(skb)->probability : U32_MAX;
+
+	psample_sample_packet(&psample_group, skb, rate, &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 +1555,15 @@ 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)) {