Merge branch 'packet-sampling-offload'

Jiri Pirko says:

====================
Add support for offloading packet-sampling

Yotam says:

The first patch introduces the psample module, a netlink channel dedicated
to packet sampling implemented using generic netlink. This module provides
a generic way for kernel modules to sample packets, while not being tied
to any specific subsystem like NFLOG.

The second patch adds the sample tc action, which uses psample to randomly
sample packets that match a classifier. The user can configure the psample
group number, the sampling rate and the packet's truncation (to save
kernel-user traffic).

The last two patches add the support for offloading the matchall-sample
tc command in the mlxsw driver, for ingress qdiscs.

An example for psample usage can be found in the libpsample project at:
https://github.com/Mellanox/libpsample

v1->v2:
- Reword first patch's commit message
- Fix typo in comment in second patch
- Change order of tc_sample uapi enum to match convention
- Rename act_sample action callback tcf_sample -> tcf_sample_act
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 149 insertions, 0 deletions

diff --git a/include/net/psample.h b/include/net/psample.h
new file mode 100644
index 000000000000..8888b0e1a82e
--- /dev/null
+++ b/include/net/psample.h
@@ -0,0 +1,36 @@
+#ifndef __NET_PSAMPLE_H
+#define __NET_PSAMPLE_H
+
+#include <uapi/linux/psample.h>
+#include <linux/module.h>
+#include <linux/list.h>
+
+struct psample_group {
+	struct list_head list;
+	struct net *net;
+	u32 group_num;
+	u32 refcount;
+	u32 seq;
+};
+
+struct psample_group *psample_group_get(struct net *net, u32 group_num);
+void psample_group_put(struct psample_group *group);
+
+#if IS_ENABLED(CONFIG_PSAMPLE)
+
+void psample_sample_packet(struct psample_group *group, struct sk_buff *skb,
+			   u32 trunc_size, int in_ifindex, int out_ifindex,
+			   u32 sample_rate);
+
+#else
+
+static inline void psample_sample_packet(struct psample_group *group,
+					 struct sk_buff *skb, u32 trunc_size,
+					 int in_ifindex, int out_ifindex,
+					 u32 sample_rate)
+{
+}
+
+#endif
+
+#endif /* __NET_PSAMPLE_H */
diff --git a/include/net/tc_act/tc_sample.h b/include/net/tc_act/tc_sample.h
new file mode 100644
index 000000000000..89e9305be880
--- /dev/null
+++ b/include/net/tc_act/tc_sample.h
@@ -0,0 +1,50 @@
+#ifndef __NET_TC_SAMPLE_H
+#define __NET_TC_SAMPLE_H
+
+#include <net/act_api.h>
+#include <linux/tc_act/tc_sample.h>
+#include <net/psample.h>
+
+struct tcf_sample {
+	struct tc_action common;
+	u32 rate;
+	bool truncate;
+	u32 trunc_size;
+	struct psample_group __rcu *psample_group;
+	u32 psample_group_num;
+	struct list_head tcfm_list;
+	struct rcu_head rcu;
+};
+#define to_sample(a) ((struct tcf_sample *)a)
+
+static inline bool is_tcf_sample(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	return a->ops && a->ops->type == TCA_ACT_SAMPLE;
+#else
+	return false;
+#endif
+}
+
+static inline __u32 tcf_sample_rate(const struct tc_action *a)
+{
+	return to_sample(a)->rate;
+}
+
+static inline bool tcf_sample_truncate(const struct tc_action *a)
+{
+	return to_sample(a)->truncate;
+}
+
+static inline int tcf_sample_trunc_size(const struct tc_action *a)
+{
+	return to_sample(a)->trunc_size;
+}
+
+static inline struct psample_group *
+tcf_sample_psample_group(const struct tc_action *a)
+{
+	return rcu_dereference(to_sample(a)->psample_group);
+}
+
+#endif /* __NET_TC_SAMPLE_H */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index e600b50be77e..80ad741a42fa 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -305,6 +305,7 @@ header-y += netrom.h
 header-y += net_namespace.h
 header-y += net_tstamp.h
 header-y += nfc.h
+header-y += psample.h
 header-y += nfs2.h
 header-y += nfs3.h
 header-y += nfs4.h
diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h
new file mode 100644
index 000000000000..ed48996ec0e8
--- /dev/null
+++ b/include/uapi/linux/psample.h
@@ -0,0 +1,35 @@
+#ifndef __UAPI_PSAMPLE_H
+#define __UAPI_PSAMPLE_H
+
+enum {
+	/* sampled packet metadata */
+	PSAMPLE_ATTR_IIFINDEX,
+	PSAMPLE_ATTR_OIFINDEX,
+	PSAMPLE_ATTR_ORIGSIZE,
+	PSAMPLE_ATTR_SAMPLE_GROUP,
+	PSAMPLE_ATTR_GROUP_SEQ,
+	PSAMPLE_ATTR_SAMPLE_RATE,
+	PSAMPLE_ATTR_DATA,
+
+	/* commands attributes */
+	PSAMPLE_ATTR_GROUP_REFCOUNT,
+
+	__PSAMPLE_ATTR_MAX
+};
+
+enum psample_command {
+	PSAMPLE_CMD_SAMPLE,
+	PSAMPLE_CMD_GET_GROUP,
+	PSAMPLE_CMD_NEW_GROUP,
+	PSAMPLE_CMD_DEL_GROUP,
+};
+
+/* Can be overridden at runtime by module option */
+#define PSAMPLE_ATTR_MAX (__PSAMPLE_ATTR_MAX - 1)
+
+#define PSAMPLE_NL_MCGRP_CONFIG_NAME "config"
+#define PSAMPLE_NL_MCGRP_SAMPLE_NAME "packets"
+#define PSAMPLE_GENL_NAME "psample"
+#define PSAMPLE_GENL_VERSION 1
+
+#endif
diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild
index e3db7403296f..ba62ddf0e58a 100644
--- a/include/uapi/linux/tc_act/Kbuild
+++ b/include/uapi/linux/tc_act/Kbuild
@@ -4,6 +4,7 @@ header-y += tc_defact.h
 header-y += tc_gact.h
 header-y += tc_ipt.h
 header-y += tc_mirred.h
+header-y += tc_sample.h
 header-y += tc_nat.h
 header-y += tc_pedit.h
 header-y += tc_skbedit.h
diff --git a/include/uapi/linux/tc_act/tc_sample.h b/include/uapi/linux/tc_act/tc_sample.h
new file mode 100644
index 000000000000..edc9058bb30d
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_sample.h
@@ -0,0 +1,26 @@
+#ifndef __LINUX_TC_SAMPLE_H
+#define __LINUX_TC_SAMPLE_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+#include <linux/if_ether.h>
+
+#define TCA_ACT_SAMPLE 26
+
+struct tc_sample {
+	tc_gen;
+};
+
+enum {
+	TCA_SAMPLE_UNSPEC,
+	TCA_SAMPLE_TM,
+	TCA_SAMPLE_PARMS,
+	TCA_SAMPLE_RATE,
+	TCA_SAMPLE_TRUNC_SIZE,
+	TCA_SAMPLE_PSAMPLE_GROUP,
+	TCA_SAMPLE_PAD,
+	__TCA_SAMPLE_MAX
+};
+#define TCA_SAMPLE_MAX (__TCA_SAMPLE_MAX - 1)
+
+#endif