net/sched: Introduce sample tc action

This action allows the user to sample traffic matched by tc classifier.
The sampling consists of choosing packets randomly and sampling them using
the psample module. The user can configure the psample group number, the
sampling rate and the packet's truncation (to save kernel-user traffic).

Example:
To sample ingress traffic from interface eth1, one may use the commands:

tc qdisc add dev eth1 handle ffff: ingress

tc filter add dev eth1 parent ffff: \
	   matchall action sample rate 12 group 4

Where the first command adds an ingress qdisc and the second starts
sampling randomly with an average of one sampled packet per 12 packets on
dev eth1 to psample group 4.

Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 364 insertions, 0 deletions

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/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
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index a9aa38d43fa7..72cfa3a6bac0 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -650,6 +650,18 @@ config NET_ACT_MIRRED
 	  To compile this code as a module, choose M here: the
 	  module will be called act_mirred.
 
+config NET_ACT_SAMPLE
+        tristate "Traffic Sampling"
+        depends on NET_CLS_ACT
+        select PSAMPLE
+        ---help---
+	  Say Y here to allow packet sampling tc action. The packet sample
+	  action consists of statistically choosing packets and sampling
+	  them using the psample module.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called act_sample.
+
 config NET_ACT_IPT
         tristate "IPtables targets"
         depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 4bdda3634e0b..7b915d226de7 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_NET_CLS_ACT)	+= act_api.o
 obj-$(CONFIG_NET_ACT_POLICE)	+= act_police.o
 obj-$(CONFIG_NET_ACT_GACT)	+= act_gact.o
 obj-$(CONFIG_NET_ACT_MIRRED)	+= act_mirred.o
+obj-$(CONFIG_NET_ACT_SAMPLE)	+= act_sample.o
 obj-$(CONFIG_NET_ACT_IPT)	+= act_ipt.o
 obj-$(CONFIG_NET_ACT_NAT)	+= act_nat.o
 obj-$(CONFIG_NET_ACT_PEDIT)	+= act_pedit.o
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
new file mode 100644
index 000000000000..39229756de07
--- /dev/null
+++ b/net/sched/act_sample.c
@@ -0,0 +1,274 @@
+/*
+ * net/sched/act_sample.c - Packet sampling tc action
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/gfp.h>
+#include <net/net_namespace.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <linux/tc_act/tc_sample.h>
+#include <net/tc_act/tc_sample.h>
+#include <net/psample.h>
+
+#include <linux/if_arp.h>
+
+#define SAMPLE_TAB_MASK     7
+static unsigned int sample_net_id;
+static struct tc_action_ops act_sample_ops;
+
+static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = {
+	[TCA_SAMPLE_PARMS]		= { .len = sizeof(struct tc_sample) },
+	[TCA_SAMPLE_RATE]		= { .type = NLA_U32 },
+	[TCA_SAMPLE_TRUNC_SIZE]		= { .type = NLA_U32 },
+	[TCA_SAMPLE_PSAMPLE_GROUP]	= { .type = NLA_U32 },
+};
+
+static int tcf_sample_init(struct net *net, struct nlattr *nla,
+			   struct nlattr *est, struct tc_action **a, int ovr,
+			   int bind)
+{
+	struct tc_action_net *tn = net_generic(net, sample_net_id);
+	struct nlattr *tb[TCA_SAMPLE_MAX + 1];
+	struct psample_group *psample_group;
+	struct tc_sample *parm;
+	struct tcf_sample *s;
+	bool exists = false;
+	int ret;
+
+	if (!nla)
+		return -EINVAL;
+	ret = nla_parse_nested(tb, TCA_SAMPLE_MAX, nla, sample_policy);
+	if (ret < 0)
+		return ret;
+	if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] ||
+	    !tb[TCA_SAMPLE_PSAMPLE_GROUP])
+		return -EINVAL;
+
+	parm = nla_data(tb[TCA_SAMPLE_PARMS]);
+
+	exists = tcf_hash_check(tn, parm->index, a, bind);
+	if (exists && bind)
+		return 0;
+
+	if (!exists) {
+		ret = tcf_hash_create(tn, parm->index, est, a,
+				      &act_sample_ops, bind, false);
+		if (ret)
+			return ret;
+		ret = ACT_P_CREATED;
+	} else {
+		tcf_hash_release(*a, bind);
+		if (!ovr)
+			return -EEXIST;
+	}
+	s = to_sample(*a);
+
+	ASSERT_RTNL();
+	s->tcf_action = parm->action;
+	s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+	s->psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
+	psample_group = psample_group_get(net, s->psample_group_num);
+	if (!psample_group)
+		return -ENOMEM;
+	RCU_INIT_POINTER(s->psample_group, psample_group);
+
+	if (tb[TCA_SAMPLE_TRUNC_SIZE]) {
+		s->truncate = true;
+		s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]);
+	}
+
+	if (ret == ACT_P_CREATED)
+		tcf_hash_insert(tn, *a);
+	return ret;
+}
+
+static void tcf_sample_cleanup_rcu(struct rcu_head *rcu)
+{
+	struct tcf_sample *s = container_of(rcu, struct tcf_sample, rcu);
+	struct psample_group *psample_group;
+
+	psample_group = rcu_dereference_protected(s->psample_group, 1);
+	RCU_INIT_POINTER(s->psample_group, NULL);
+	psample_group_put(psample_group);
+}
+
+static void tcf_sample_cleanup(struct tc_action *a, int bind)
+{
+	struct tcf_sample *s = to_sample(a);
+
+	call_rcu(&s->rcu, tcf_sample_cleanup_rcu);
+}
+
+static bool tcf_sample_dev_ok_push(struct net_device *dev)
+{
+	switch (dev->type) {
+	case ARPHRD_TUNNEL:
+	case ARPHRD_TUNNEL6:
+	case ARPHRD_SIT:
+	case ARPHRD_IPGRE:
+	case ARPHRD_VOID:
+	case ARPHRD_NONE:
+		return false;
+	default:
+		return true;
+	}
+}
+
+static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a,
+			  struct tcf_result *res)
+{
+	struct tcf_sample *s = to_sample(a);
+	struct psample_group *psample_group;
+	int retval;
+	int size;
+	int iif;
+	int oif;
+
+	tcf_lastuse_update(&s->tcf_tm);
+	bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb);
+	retval = READ_ONCE(s->tcf_action);
+
+	rcu_read_lock();
+	psample_group = rcu_dereference(s->psample_group);
+
+	/* randomly sample packets according to rate */
+	if (psample_group && (prandom_u32() % s->rate == 0)) {
+		if (!skb_at_tc_ingress(skb)) {
+			iif = skb->skb_iif;
+			oif = skb->dev->ifindex;
+		} else {
+			iif = skb->dev->ifindex;
+			oif = 0;
+		}
+
+		/* on ingress, the mac header gets popped, so push it back */
+		if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev))
+			skb_push(skb, skb->mac_len);
+
+		size = s->truncate ? s->trunc_size : skb->len;
+		psample_sample_packet(psample_group, skb, size, iif, oif,
+				      s->rate);
+
+		if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev))
+			skb_pull(skb, skb->mac_len);
+	}
+
+	rcu_read_unlock();
+	return retval;
+}
+
+static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a,
+			   int bind, int ref)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tcf_sample *s = to_sample(a);
+	struct tc_sample opt = {
+		.index      = s->tcf_index,
+		.action     = s->tcf_action,
+		.refcnt     = s->tcf_refcnt - ref,
+		.bindcnt    = s->tcf_bindcnt - bind,
+	};
+	struct tcf_t t;
+
+	if (nla_put(skb, TCA_SAMPLE_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	tcf_tm_dump(&t, &s->tcf_tm);
+	if (nla_put_64bit(skb, TCA_SAMPLE_TM, sizeof(t), &t, TCA_SAMPLE_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_SAMPLE_RATE, s->rate))
+		goto nla_put_failure;
+
+	if (s->truncate)
+		if (nla_put_u32(skb, TCA_SAMPLE_TRUNC_SIZE, s->trunc_size))
+			goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_SAMPLE_PSAMPLE_GROUP, s->psample_group_num))
+		goto nla_put_failure;
+	return skb->len;
+
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
+static int tcf_sample_walker(struct net *net, struct sk_buff *skb,
+			     struct netlink_callback *cb, int type,
+			     const struct tc_action_ops *ops)
+{
+	struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+	return tcf_generic_walker(tn, skb, cb, type, ops);
+}
+
+static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+	return tcf_hash_search(tn, a, index);
+}
+
+static struct tc_action_ops act_sample_ops = {
+	.kind	  = "sample",
+	.type	  = TCA_ACT_SAMPLE,
+	.owner	  = THIS_MODULE,
+	.act	  = tcf_sample_act,
+	.dump	  = tcf_sample_dump,
+	.init	  = tcf_sample_init,
+	.cleanup  = tcf_sample_cleanup,
+	.walk	  = tcf_sample_walker,
+	.lookup	  = tcf_sample_search,
+	.size	  = sizeof(struct tcf_sample),
+};
+
+static __net_init int sample_init_net(struct net *net)
+{
+	struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+	return tc_action_net_init(tn, &act_sample_ops, SAMPLE_TAB_MASK);
+}
+
+static void __net_exit sample_exit_net(struct net *net)
+{
+	struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+	tc_action_net_exit(tn);
+}
+
+static struct pernet_operations sample_net_ops = {
+	.init = sample_init_net,
+	.exit = sample_exit_net,
+	.id   = &sample_net_id,
+	.size = sizeof(struct tc_action_net),
+};
+
+static int __init sample_init_module(void)
+{
+	return tcf_register_action(&act_sample_ops, &sample_net_ops);
+}
+
+static void __exit sample_cleanup_module(void)
+{
+	tcf_unregister_action(&act_sample_ops, &sample_net_ops);
+}
+
+module_init(sample_init_module);
+module_exit(sample_cleanup_module);
+
+MODULE_AUTHOR("Yotam Gigi <yotamg@mellanox.com>");
+MODULE_DESCRIPTION("Packet sampling action");
+MODULE_LICENSE("GPL v2");