Merge branch 'add-support-for-per-action-hw-stats'

Oz Shlomo says:

====================
add support for per action hw stats

There are currently two mechanisms for populating hardware stats:
1. Using flow_offload api to query the flow's statistics.
   The api assumes that the same stats values apply to all
   the flow's actions.
   This assumption breaks when action drops or jumps over following
   actions.
2. Using hw_action api to query specific action stats via a driver
   callback method. This api assures the correct action stats for
   the offloaded action, however, it does not apply to the rest of the
   actions in the flow's actions array, as elaborated below.

The current hw_action api does not apply to the following use cases:
1. Actions that are implicitly created by filters (aka bind actions).
   In the following example only one counter will apply to the rule:
   tc filter add dev $DEV prio 2 protocol ip parent ffff: \
        flower ip_proto tcp dst_ip $IP2 \
        action police rate 1mbit burst 100k conform-exceed drop/pipe \
        action mirred egress redirect dev $DEV2

2. Action preceding a hw action.
   In the following example the same flow stats will apply to the sample and
   mirred actions:
    tc action add police rate 1mbit burst 100k conform-exceed drop / pipe
    tc filter add dev $DEV prio 2 protocol ip parent ffff: \
        flower ip_proto tcp dst_ip $IP2 \
        action sample rate 1 group 10 trunc 60 pipe \
        action police index 1 \
        action mirred egress redirect dev $DEV2

3. Meter action using jump control.
   In the following example the same flow stats will apply to both
   mirred actions:
    tc action add police rate 1mbit burst 100k conform-exceed jump 2 / pipe
    tc filter add dev $DEV prio 2 protocol ip parent ffff: \
        flower ip_proto tcp dst_ip $IP2 \
        action police index 1 \
        action mirred egress redirect dev $DEV2
        action mirred egress redirect dev $DEV3

This series provides the platform to query per action stats for in_hw flows.

The first four patches are preparation patches with no functionality change.
The fifth patch re-uses the existing flow action stats api to query action
stats for both classifier and action dumps.
The rest of the patches add per action stats support to the Mellanox driver.
====================

Link: https://lore.kernel.org/r/20230212132520.12571-1-ozsh@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

3 files changed, 24 insertions, 11 deletions

diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index ba6958b49a8e..90a2fe5839fa 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -296,6 +296,8 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
 u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter);
 void mlx5_fc_query_cached(struct mlx5_fc *counter,
 			  u64 *bytes, u64 *packets, u64 *lastuse);
+void mlx5_fc_query_cached_raw(struct mlx5_fc *counter,
+			      u64 *bytes, u64 *packets, u64 *lastuse);
 int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter,
 		  u64 *packets, u64 *bytes);
 u32 mlx5_fc_id(struct mlx5_fc *counter);
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 0400a0ac8a29..8c05455b1e34 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -228,6 +228,7 @@ void flow_action_cookie_destroy(struct flow_action_cookie *cookie);
 struct flow_action_entry {
 	enum flow_action_id		id;
 	u32				hw_index;
+	unsigned long			act_cookie;
 	enum flow_action_hw_stats	hw_stats;
 	action_destr			destructor;
 	void				*destructor_priv;
@@ -593,6 +594,7 @@ struct flow_cls_common_offload {
 struct flow_cls_offload {
 	struct flow_cls_common_offload common;
 	enum flow_cls_command command;
+	bool use_act_stats;
 	unsigned long cookie;
 	struct flow_rule *rule;
 	struct flow_stats stats;
@@ -610,6 +612,7 @@ struct flow_offload_action {
 	enum offload_act_command  command;
 	enum flow_action_id id;
 	u32 index;
+	unsigned long cookie;
 	struct flow_stats stats;
 	struct flow_action action;
 };
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index cd410a87517b..ace437c6754b 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -292,10 +292,15 @@ static inline void tcf_exts_put_net(struct tcf_exts *exts)
 #define tcf_act_for_each_action(i, a, actions) \
 	for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = actions[i]); i++)
 
+static inline bool tc_act_in_hw(struct tc_action *act)
+{
+	return !!act->in_hw_count;
+}
+
 static inline void
 tcf_exts_hw_stats_update(const struct tcf_exts *exts,
-			 u64 bytes, u64 packets, u64 drops, u64 lastuse,
-			 u8 used_hw_stats, bool used_hw_stats_valid)
+			 struct flow_stats *stats,
+			 bool use_act_stats)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	int i;
@@ -303,16 +308,18 @@ tcf_exts_hw_stats_update(const struct tcf_exts *exts,
 	for (i = 0; i < exts->nr_actions; i++) {
 		struct tc_action *a = exts->actions[i];
 
-		/* if stats from hw, just skip */
-		if (tcf_action_update_hw_stats(a)) {
-			preempt_disable();
-			tcf_action_stats_update(a, bytes, packets, drops,
-						lastuse, true);
-			preempt_enable();
-
-			a->used_hw_stats = used_hw_stats;
-			a->used_hw_stats_valid = used_hw_stats_valid;
+		if (use_act_stats || tc_act_in_hw(a)) {
+			if (!tcf_action_update_hw_stats(a))
+				continue;
 		}
+
+		preempt_disable();
+		tcf_action_stats_update(a, stats->bytes, stats->pkts, stats->drops,
+					stats->lastused, true);
+		preempt_enable();
+
+		a->used_hw_stats = stats->used_hw_stats;
+		a->used_hw_stats_valid = stats->used_hw_stats_valid;
 	}
 #endif
 }
@@ -770,6 +777,7 @@ struct tc_cls_matchall_offload {
 	enum tc_matchall_command command;
 	struct flow_rule *rule;
 	struct flow_stats stats;
+	bool use_act_stats;
 	unsigned long cookie;
 };