Merge branch 'net-sched-Add-hardware-specific-counters-to-TC-actions'

Eelco Chaudron says:

====================
net/sched: Add hardware specific counters to TC actions

Add hardware specific counters to TC actions which will be exported
through the netlink API. This makes troubleshooting TC flower offload
easier, as it possible to differentiate the packets being offloaded.

v2 - Rebased on latest net-next
====================

Signed-off-by: Eelco Chaudron <echaudro@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 85 insertions, 28 deletions

diff --git a/include/net/act_api.h b/include/net/act_api.h
index c6f195b3c706..1ddff3360592 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -31,10 +31,12 @@ struct tc_action {
 	int				tcfa_action;
 	struct tcf_t			tcfa_tm;
 	struct gnet_stats_basic_packed	tcfa_bstats;
+	struct gnet_stats_basic_packed	tcfa_bstats_hw;
 	struct gnet_stats_queue		tcfa_qstats;
 	struct net_rate_estimator __rcu *tcfa_rate_est;
 	spinlock_t			tcfa_lock;
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats_hw;
 	struct gnet_stats_queue __percpu *cpu_qstats;
 	struct tc_cookie	__rcu *act_cookie;
 	struct tcf_chain	*goto_chain;
@@ -94,7 +96,7 @@ struct tc_action_ops {
 			struct netlink_callback *, int,
 			const struct tc_action_ops *,
 			struct netlink_ext_ack *);
-	void	(*stats_update)(struct tc_action *, u64, u32, u64);
+	void	(*stats_update)(struct tc_action *, u64, u32, u64, bool);
 	size_t  (*get_fill_size)(const struct tc_action *act);
 	struct net_device *(*get_dev)(const struct tc_action *a);
 	void	(*put_dev)(struct net_device *dev);
@@ -182,13 +184,13 @@ int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
 #endif /* CONFIG_NET_CLS_ACT */
 
 static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
-					   u64 packets, u64 lastuse)
+					   u64 packets, u64 lastuse, bool hw)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	if (!a->ops->stats_update)
 		return;
 
-	a->ops->stats_update(a, bytes, packets, lastuse);
+	a->ops->stats_update(a, bytes, packets, lastuse, hw);
 #endif
 }
 
diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index 883bb9085f15..946bd53a9f81 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -44,6 +44,10 @@ void __gnet_stats_copy_basic(const seqcount_t *running,
 			     struct gnet_stats_basic_packed *bstats,
 			     struct gnet_stats_basic_cpu __percpu *cpu,
 			     struct gnet_stats_basic_packed *b);
+int gnet_stats_copy_basic_hw(const seqcount_t *running,
+			     struct gnet_dump *d,
+			     struct gnet_stats_basic_cpu __percpu *cpu,
+			     struct gnet_stats_basic_packed *b);
 int gnet_stats_copy_rate_est(struct gnet_dump *d,
 			     struct net_rate_estimator __rcu **ptr);
 int gnet_stats_copy_queue(struct gnet_dump *d,
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 75a3f3fdb359..bbfe27f86d5f 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -318,7 +318,7 @@ tcf_exts_stats_update(const struct tcf_exts *exts,
 	for (i = 0; i < exts->nr_actions; i++) {
 		struct tc_action *a = exts->actions[i];
 
-		tcf_action_stats_update(a, bytes, packets, lastuse);
+		tcf_action_stats_update(a, bytes, packets, lastuse, true);
 	}
 
 	preempt_enable();
diff --git a/include/uapi/linux/gen_stats.h b/include/uapi/linux/gen_stats.h
index 24a861c0d29d..065408e16a80 100644
--- a/include/uapi/linux/gen_stats.h
+++ b/include/uapi/linux/gen_stats.h
@@ -12,6 +12,7 @@ enum {
 	TCA_STATS_APP,
 	TCA_STATS_RATE_EST64,
 	TCA_STATS_PAD,
+	TCA_STATS_BASIC_HW,
 	__TCA_STATS_MAX,
 };
 #define TCA_STATS_MAX (__TCA_STATS_MAX - 1)
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 188d693cb251..65a2e820364f 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -162,30 +162,18 @@ __gnet_stats_copy_basic(const seqcount_t *running,
 }
 EXPORT_SYMBOL(__gnet_stats_copy_basic);
 
-/**
- * gnet_stats_copy_basic - copy basic statistics into statistic TLV
- * @running: seqcount_t pointer
- * @d: dumping handle
- * @cpu: copy statistic per cpu
- * @b: basic statistics
- *
- * Appends the basic statistics to the top level TLV created by
- * gnet_stats_start_copy().
- *
- * Returns 0 on success or -1 with the statistic lock released
- * if the room in the socket buffer was not sufficient.
- */
 int
-gnet_stats_copy_basic(const seqcount_t *running,
-		      struct gnet_dump *d,
-		      struct gnet_stats_basic_cpu __percpu *cpu,
-		      struct gnet_stats_basic_packed *b)
+___gnet_stats_copy_basic(const seqcount_t *running,
+			 struct gnet_dump *d,
+			 struct gnet_stats_basic_cpu __percpu *cpu,
+			 struct gnet_stats_basic_packed *b,
+			 int type)
 {
 	struct gnet_stats_basic_packed bstats = {0};
 
 	__gnet_stats_copy_basic(running, &bstats, cpu, b);
 
-	if (d->compat_tc_stats) {
+	if (d->compat_tc_stats && type == TCA_STATS_BASIC) {
 		d->tc_stats.bytes = bstats.bytes;
 		d->tc_stats.packets = bstats.packets;
 	}
@@ -196,14 +184,61 @@ gnet_stats_copy_basic(const seqcount_t *running,
 		memset(&sb, 0, sizeof(sb));
 		sb.bytes = bstats.bytes;
 		sb.packets = bstats.packets;
-		return gnet_stats_copy(d, TCA_STATS_BASIC, &sb, sizeof(sb),
+		return gnet_stats_copy(d, type, &sb, sizeof(sb),
 				       TCA_STATS_PAD);
 	}
 	return 0;
 }
+
+/**
+ * gnet_stats_copy_basic - copy basic statistics into statistic TLV
+ * @running: seqcount_t pointer
+ * @d: dumping handle
+ * @cpu: copy statistic per cpu
+ * @b: basic statistics
+ *
+ * Appends the basic statistics to the top level TLV created by
+ * gnet_stats_start_copy().
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
+int
+gnet_stats_copy_basic(const seqcount_t *running,
+		      struct gnet_dump *d,
+		      struct gnet_stats_basic_cpu __percpu *cpu,
+		      struct gnet_stats_basic_packed *b)
+{
+	return ___gnet_stats_copy_basic(running, d, cpu, b,
+					TCA_STATS_BASIC);
+}
 EXPORT_SYMBOL(gnet_stats_copy_basic);
 
 /**
+ * gnet_stats_copy_basic_hw - copy basic hw statistics into statistic TLV
+ * @running: seqcount_t pointer
+ * @d: dumping handle
+ * @cpu: copy statistic per cpu
+ * @b: basic statistics
+ *
+ * Appends the basic statistics to the top level TLV created by
+ * gnet_stats_start_copy().
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
+int
+gnet_stats_copy_basic_hw(const seqcount_t *running,
+			 struct gnet_dump *d,
+			 struct gnet_stats_basic_cpu __percpu *cpu,
+			 struct gnet_stats_basic_packed *b)
+{
+	return ___gnet_stats_copy_basic(running, d, cpu, b,
+					TCA_STATS_BASIC_HW);
+}
+EXPORT_SYMBOL(gnet_stats_copy_basic_hw);
+
+/**
  * gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV
  * @d: dumping handle
  * @rate_est: rate estimator
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index fac8c769454f..3c7c23421885 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -81,6 +81,7 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
 static void free_tcf(struct tc_action *p)
 {
 	free_percpu(p->cpu_bstats);
+	free_percpu(p->cpu_bstats_hw);
 	free_percpu(p->cpu_qstats);
 
 	tcf_set_action_cookie(&p->act_cookie, NULL);
@@ -390,9 +391,12 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 		p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
 		if (!p->cpu_bstats)
 			goto err1;
+		p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
+		if (!p->cpu_bstats_hw)
+			goto err2;
 		p->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
 		if (!p->cpu_qstats)
-			goto err2;
+			goto err3;
 	}
 	spin_lock_init(&p->tcfa_lock);
 	p->tcfa_index = index;
@@ -404,15 +408,17 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 					&p->tcfa_rate_est,
 					&p->tcfa_lock, NULL, est);
 		if (err)
-			goto err3;
+			goto err4;
 	}
 
 	p->idrinfo = idrinfo;
 	p->ops = ops;
 	*a = p;
 	return 0;
-err3:
+err4:
 	free_percpu(p->cpu_qstats);
+err3:
+	free_percpu(p->cpu_bstats_hw);
 err2:
 	free_percpu(p->cpu_bstats);
 err1:
@@ -997,6 +1003,8 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p,
 		goto errout;
 
 	if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 ||
+	    gnet_stats_copy_basic_hw(NULL, &d, p->cpu_bstats_hw,
+				     &p->tcfa_bstats_hw) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 ||
 	    gnet_stats_copy_queue(&d, p->cpu_qstats,
 				  &p->tcfa_qstats,
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index aa44d14b43c7..c89a7fa43d1b 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -157,7 +157,7 @@ static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a,
 }
 
 static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
-				  u64 lastuse)
+				  u64 lastuse, bool hw)
 {
 	struct tcf_gact *gact = to_gact(a);
 	int action = READ_ONCE(gact->tcf_action);
@@ -168,6 +168,10 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 	if (action == TC_ACT_SHOT)
 		this_cpu_ptr(gact->common.cpu_qstats)->drops += packets;
 
+	if (hw)
+		_bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats_hw),
+				   bytes, packets);
+
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index a9d64bfe5a2a..1dae5f2b358f 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -283,12 +283,15 @@ out:
 }
 
 static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
-			     u64 lastuse)
+			     u64 lastuse, bool hw)
 {
 	struct tcf_mirred *m = to_mirred(a);
 	struct tcf_t *tm = &m->tcf_tm;
 
 	_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
+	if (hw)
+		_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
+				   bytes, packets);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }