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>

17 files changed, 375 insertions, 48 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index cd4a1ab0ea78..06f511fcbd8e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -47,7 +47,7 @@ mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en_tc.o en/rep/tc.o en/rep/neigh.o \
 					en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \
 					en/tc_tun_mplsoudp.o diag/en_tc_tracepoint.o \
 					en/tc/post_act.o en/tc/int_port.o en/tc/meter.o \
-					en/tc/post_meter.o
+					en/tc/post_meter.o en/tc/act_stats.o
 
 mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en/tc/act/act.o en/tc/act/drop.o en/tc/act/trap.o \
 					en/tc/act/accept.o en/tc/act/mark.o en/tc/act/goto.o \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index b08339d986d5..3b590cfe33b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -589,7 +589,7 @@ mlx5e_rep_indr_stats_act(struct mlx5e_rep_priv *rpriv,
 
 	act = mlx5e_tc_act_get(fl_act->id, ns_type);
 	if (!act || !act->stats_action)
-		return -EOPNOTSUPP;
+		return mlx5e_tc_fill_action_stats(priv, fl_act);
 
 	return act->stats_action(priv, fl_act);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c
new file mode 100644
index 000000000000..f71766dca660
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+#include <linux/rhashtable.h>
+#include <net/flow_offload.h>
+#include "en/tc_priv.h"
+#include "act_stats.h"
+#include "en/fs.h"
+
+struct mlx5e_tc_act_stats_handle {
+	struct rhashtable ht;
+	spinlock_t ht_lock; /* protects hashtable */
+};
+
+struct mlx5e_tc_act_stats {
+	unsigned long		tc_act_cookie;
+
+	struct mlx5_fc		*counter;
+	u64			lastpackets;
+	u64			lastbytes;
+
+	struct rhash_head	hash;
+	struct rcu_head		rcu_head;
+};
+
+static const struct rhashtable_params act_counters_ht_params = {
+	.head_offset = offsetof(struct mlx5e_tc_act_stats, hash),
+	.key_offset = 0,
+	.key_len = offsetof(struct mlx5e_tc_act_stats, counter),
+	.automatic_shrinking = true,
+};
+
+struct mlx5e_tc_act_stats_handle *
+mlx5e_tc_act_stats_create(void)
+{
+	struct mlx5e_tc_act_stats_handle *handle;
+	int err;
+
+	handle = kvzalloc(sizeof(*handle), GFP_KERNEL);
+	if (IS_ERR(handle))
+		return ERR_PTR(-ENOMEM);
+
+	err = rhashtable_init(&handle->ht, &act_counters_ht_params);
+	if (err)
+		goto err;
+
+	spin_lock_init(&handle->ht_lock);
+	return handle;
+err:
+	kvfree(handle);
+	return ERR_PTR(err);
+}
+
+void mlx5e_tc_act_stats_free(struct mlx5e_tc_act_stats_handle *handle)
+{
+	rhashtable_destroy(&handle->ht);
+	kvfree(handle);
+}
+
+static int
+mlx5e_tc_act_stats_add(struct mlx5e_tc_act_stats_handle *handle,
+		       unsigned long act_cookie,
+		       struct mlx5_fc *counter)
+{
+	struct mlx5e_tc_act_stats *act_stats, *old_act_stats;
+	struct rhashtable *ht = &handle->ht;
+	int err = 0;
+
+	act_stats = kvzalloc(sizeof(*act_stats), GFP_KERNEL);
+	if (!act_stats)
+		return -ENOMEM;
+
+	act_stats->tc_act_cookie = act_cookie;
+	act_stats->counter = counter;
+
+	rcu_read_lock();
+	old_act_stats = rhashtable_lookup_get_insert_fast(ht,
+							  &act_stats->hash,
+							  act_counters_ht_params);
+	if (IS_ERR(old_act_stats)) {
+		err = PTR_ERR(old_act_stats);
+		goto err_hash_insert;
+	} else if (old_act_stats) {
+		err = -EEXIST;
+		goto err_hash_insert;
+	}
+	rcu_read_unlock();
+
+	return 0;
+
+err_hash_insert:
+	rcu_read_unlock();
+	kvfree(act_stats);
+	return err;
+}
+
+void
+mlx5e_tc_act_stats_del_flow(struct mlx5e_tc_act_stats_handle *handle,
+			    struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_flow_attr *attr;
+	struct mlx5e_tc_act_stats *act_stats;
+	int i;
+
+	if (!flow_flag_test(flow, USE_ACT_STATS))
+		return;
+
+	list_for_each_entry(attr, &flow->attrs, list) {
+		for (i = 0; i < attr->tc_act_cookies_count; i++) {
+			struct rhashtable *ht = &handle->ht;
+
+			spin_lock(&handle->ht_lock);
+			act_stats = rhashtable_lookup_fast(ht,
+							   &attr->tc_act_cookies[i],
+							   act_counters_ht_params);
+			if (act_stats &&
+			    rhashtable_remove_fast(ht, &act_stats->hash,
+						   act_counters_ht_params) == 0)
+				kvfree_rcu(act_stats, rcu_head);
+
+			spin_unlock(&handle->ht_lock);
+		}
+	}
+}
+
+int
+mlx5e_tc_act_stats_add_flow(struct mlx5e_tc_act_stats_handle *handle,
+			    struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_fc *curr_counter = NULL;
+	unsigned long last_cookie = 0;
+	struct mlx5_flow_attr *attr;
+	int err;
+	int i;
+
+	if (!flow_flag_test(flow, USE_ACT_STATS))
+		return 0;
+
+	list_for_each_entry(attr, &flow->attrs, list) {
+		if (attr->counter)
+			curr_counter = attr->counter;
+
+		for (i = 0; i < attr->tc_act_cookies_count; i++) {
+			/* jump over identical ids (e.g. pedit)*/
+			if (last_cookie == attr->tc_act_cookies[i])
+				continue;
+
+			err = mlx5e_tc_act_stats_add(handle, attr->tc_act_cookies[i], curr_counter);
+			if (err)
+				goto out_err;
+			last_cookie = attr->tc_act_cookies[i];
+		}
+	}
+
+	return 0;
+out_err:
+	mlx5e_tc_act_stats_del_flow(handle, flow);
+	return err;
+}
+
+int
+mlx5e_tc_act_stats_fill_stats(struct mlx5e_tc_act_stats_handle *handle,
+			      struct flow_offload_action *fl_act)
+{
+	struct rhashtable *ht = &handle->ht;
+	struct mlx5e_tc_act_stats *item;
+	struct mlx5e_tc_act_stats key;
+	u64 pkts, bytes, lastused;
+	int err = 0;
+
+	key.tc_act_cookie = fl_act->cookie;
+
+	rcu_read_lock();
+	item = rhashtable_lookup(ht, &key, act_counters_ht_params);
+	if (!item) {
+		rcu_read_unlock();
+		err = -ENOENT;
+		goto err_out;
+	}
+
+	mlx5_fc_query_cached_raw(item->counter,
+				 &bytes, &pkts, &lastused);
+
+	flow_stats_update(&fl_act->stats,
+			  bytes - item->lastbytes,
+			  pkts - item->lastpackets,
+			  0, lastused, FLOW_ACTION_HW_STATS_DELAYED);
+
+	item->lastpackets = pkts;
+	item->lastbytes = bytes;
+	rcu_read_unlock();
+
+	return 0;
+
+err_out:
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.h
new file mode 100644
index 000000000000..002292c2567c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef __MLX5_EN_ACT_STATS_H__
+#define __MLX5_EN_ACT_STATS_H__
+
+#include <net/flow_offload.h>
+#include "en/tc_priv.h"
+
+struct mlx5e_tc_act_stats_handle;
+
+struct mlx5e_tc_act_stats_handle *mlx5e_tc_act_stats_create(void);
+void mlx5e_tc_act_stats_free(struct mlx5e_tc_act_stats_handle *handle);
+
+int
+mlx5e_tc_act_stats_add_flow(struct mlx5e_tc_act_stats_handle *handle,
+			    struct mlx5e_tc_flow *flow);
+
+void
+mlx5e_tc_act_stats_del_flow(struct mlx5e_tc_act_stats_handle *handle,
+			    struct mlx5e_tc_flow *flow);
+
+int
+mlx5e_tc_act_stats_fill_stats(struct mlx5e_tc_act_stats_handle *handle,
+			      struct flow_offload_action *fl_act);
+
+#endif /* __MLX5_EN_ACT_STATS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
index f575646d2f50..451fd4342a5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
@@ -30,6 +30,7 @@ enum {
 	MLX5E_TC_FLOW_FLAG_TUN_RX                = MLX5E_TC_FLOW_BASE + 9,
 	MLX5E_TC_FLOW_FLAG_FAILED                = MLX5E_TC_FLOW_BASE + 10,
 	MLX5E_TC_FLOW_FLAG_SAMPLE                = MLX5E_TC_FLOW_BASE + 11,
+	MLX5E_TC_FLOW_FLAG_USE_ACT_STATS	 = MLX5E_TC_FLOW_BASE + 12,
 };
 
 struct mlx5e_tc_flow_parse_attr {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index b4e691760da9..0abe3313c673 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -100,6 +100,9 @@ struct mlx5_rep_uplink_priv {
 	struct mlx5e_tc_int_port_priv *int_port_priv;
 
 	struct mlx5e_flow_meters *flow_meters;
+
+	/* tc action stats */
+	struct mlx5e_tc_act_stats_handle *action_stats_handle;
 };
 
 struct mlx5e_rep_priv {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e2ec80ebde58..2d06b4412762 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -45,6 +45,7 @@
 #include <net/bonding.h>
 #include "en.h"
 #include "en/tc/post_act.h"
+#include "en/tc/act_stats.h"
 #include "en_rep.h"
 #include "en/rep/tc.h"
 #include "en/rep/neigh.h"
@@ -101,6 +102,9 @@ struct mlx5e_tc_table {
 	struct mapping_ctx             *mapping;
 	struct mlx5e_hairpin_params    hairpin_params;
 	struct dentry                  *dfs_root;
+
+	/* tc action stats */
+	struct mlx5e_tc_act_stats_handle *action_stats_handle;
 };
 
 struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = {
@@ -286,6 +290,24 @@ mlx5e_tc_match_to_reg_set_and_get_id(struct mlx5_core_dev *mdev,
 	return err;
 }
 
+static struct mlx5e_tc_act_stats_handle  *
+get_act_stats_handle(struct mlx5e_priv *priv)
+{
+	struct mlx5e_tc_table *tc = mlx5e_fs_get_tc(priv->fs);
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	struct mlx5e_rep_priv *uplink_rpriv;
+
+	if (is_mdev_switchdev_mode(priv->mdev)) {
+		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+		uplink_priv = &uplink_rpriv->uplink_priv;
+
+		return uplink_priv->action_stats_handle;
+	}
+
+	return tc->action_stats_handle;
+}
+
 struct mlx5e_tc_int_port_priv *
 mlx5e_get_int_port_priv(struct mlx5e_priv *priv)
 {
@@ -2026,6 +2048,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto err_out;
 
+	err = mlx5e_tc_act_stats_add_flow(get_act_stats_handle(priv), flow);
+	if (err)
+		goto err_out;
+
 	/* we get here if one of the following takes place:
 	 * (1) there's no error
 	 * (2) there's an encap action and we don't have valid neigh
@@ -2120,6 +2146,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	if (flow_flag_test(flow, L3_TO_L2_DECAP))
 		mlx5e_detach_decap(priv, flow);
 
+	mlx5e_tc_act_stats_del_flow(get_act_stats_handle(priv), flow);
+
 	free_flow_post_acts(flow);
 	free_branch_attr(flow, attr->branch_true);
 	free_branch_attr(flow, attr->branch_false);
@@ -3785,6 +3813,8 @@ mlx5e_clone_flow_attr_for_post_act(struct mlx5_flow_attr *attr,
 	INIT_LIST_HEAD(&attr2->list);
 	parse_attr->filter_dev = attr->parse_attr->filter_dev;
 	attr2->action = 0;
+	attr2->counter = NULL;
+	attr->tc_act_cookies_count = 0;
 	attr2->flags = 0;
 	attr2->parse_attr = parse_attr;
 	attr2->dest_chain = 0;
@@ -4084,6 +4114,11 @@ parse_branch_ctrl(struct flow_action_entry *act, struct mlx5e_tc_act *tc_act,
 		jump_state->jumping_attr = attr->branch_false;
 
 	jump_state->jump_count = jump_count;
+
+	/* branching action requires its own counter */
+	attr->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_flag_set(flow, USE_ACT_STATS);
+
 	return 0;
 
 err_branch_false:
@@ -4144,6 +4179,8 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state,
 			goto out_free;
 
 		parse_state->actions |= attr->action;
+		if (!tc_act->stats_action)
+			attr->tc_act_cookies[attr->tc_act_cookies_count++] = act->act_cookie;
 
 		/* Split attr for multi table act if not the last act. */
 		if (jump_state.jump_target ||
@@ -4931,6 +4968,12 @@ errout:
 	return err;
 }
 
+int mlx5e_tc_fill_action_stats(struct mlx5e_priv *priv,
+			       struct flow_offload_action *fl_act)
+{
+	return mlx5e_tc_act_stats_fill_stats(get_act_stats_handle(priv), fl_act);
+}
+
 int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		       struct flow_cls_offload *f, unsigned long flags)
 {
@@ -4957,11 +5000,15 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	}
 
 	if (mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, CT)) {
-		counter = mlx5e_tc_get_counter(flow);
-		if (!counter)
-			goto errout;
+		if (flow_flag_test(flow, USE_ACT_STATS)) {
+			f->use_act_stats = true;
+		} else {
+			counter = mlx5e_tc_get_counter(flow);
+			if (!counter)
+				goto errout;
 
-		mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+			mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+		}
 	}
 
 	/* Under multipath it's possible for one rule to be currently
@@ -4977,14 +5024,18 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		u64 packets2;
 		u64 lastuse2;
 
-		counter = mlx5e_tc_get_counter(flow->peer_flow);
-		if (!counter)
-			goto no_peer_counter;
-		mlx5_fc_query_cached(counter, &bytes2, &packets2, &lastuse2);
-
-		bytes += bytes2;
-		packets += packets2;
-		lastuse = max_t(u64, lastuse, lastuse2);
+		if (flow_flag_test(flow, USE_ACT_STATS)) {
+			f->use_act_stats = true;
+		} else {
+			counter = mlx5e_tc_get_counter(flow->peer_flow);
+			if (!counter)
+				goto no_peer_counter;
+			mlx5_fc_query_cached(counter, &bytes2, &packets2, &lastuse2);
+
+			bytes += bytes2;
+			packets += packets2;
+			lastuse = max_t(u64, lastuse, lastuse2);
+		}
 	}
 
 no_peer_counter:
@@ -5323,8 +5374,16 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 
 	mlx5e_tc_debugfs_init(tc, mlx5e_fs_get_debugfs_root(priv->fs));
 
+	tc->action_stats_handle = mlx5e_tc_act_stats_create();
+	if (IS_ERR(tc->action_stats_handle))
+		goto err_act_stats;
+
 	return 0;
 
+err_act_stats:
+	unregister_netdevice_notifier_dev_net(priv->netdev,
+					      &tc->netdevice_nb,
+					      &tc->netdevice_nn);
 err_reg:
 	mlx5_tc_ct_clean(tc->ct);
 	mlx5e_tc_post_act_destroy(tc->post_act);
@@ -5374,6 +5433,7 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv)
 	mapping_destroy(tc->mapping);
 	mlx5_chains_destroy(tc->chains);
 	mlx5e_tc_nic_destroy_miss_table(priv);
+	mlx5e_tc_act_stats_free(tc->action_stats_handle);
 }
 
 int mlx5e_tc_ht_init(struct rhashtable *tc_ht)
@@ -5450,8 +5510,14 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv)
 		goto err_register_fib_notifier;
 	}
 
+	uplink_priv->action_stats_handle = mlx5e_tc_act_stats_create();
+	if (IS_ERR(uplink_priv->action_stats_handle))
+		goto err_action_counter;
+
 	return 0;
 
+err_action_counter:
+	mlx5e_tc_tun_cleanup(uplink_priv->encap);
 err_register_fib_notifier:
 	mapping_destroy(uplink_priv->tunnel_enc_opts_mapping);
 err_enc_opts_mapping:
@@ -5478,6 +5544,7 @@ void mlx5e_tc_esw_cleanup(struct mlx5_rep_uplink_priv *uplink_priv)
 	mlx5_tc_ct_clean(uplink_priv->ct_priv);
 	mlx5e_flow_meters_cleanup(uplink_priv->flow_meters);
 	mlx5e_tc_post_act_destroy(uplink_priv->post_act);
+	mlx5e_tc_act_stats_free(uplink_priv->action_stats_handle);
 }
 
 int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index ce516dc7f3fd..e8e39fdcda73 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -69,6 +69,7 @@ struct mlx5_nic_flow_attr {
 
 struct mlx5_flow_attr {
 	u32 action;
+	unsigned long tc_act_cookies[TCA_ACT_MAX_PRIO];
 	struct mlx5_fc *counter;
 	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5e_mod_hdr_handle *mh; /* attached mod header instance */
@@ -79,6 +80,7 @@ struct mlx5_flow_attr {
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	u32 chain;
 	u16 prio;
+	u16 tc_act_cookies_count;
 	u32 dest_chain;
 	struct mlx5_flow_table *ft;
 	struct mlx5_flow_table *dest_ft;
@@ -197,6 +199,8 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 
 int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		       struct flow_cls_offload *f, unsigned long flags);
+int mlx5e_tc_fill_action_stats(struct mlx5e_priv *priv,
+			       struct flow_offload_action *fl_act);
 
 int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv,
 				struct tc_cls_matchall_offload *f);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index b406e0367af6..17fe30a4c06c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -504,6 +504,16 @@ void mlx5_fc_query_cached(struct mlx5_fc *counter,
 	counter->lastpackets = c.packets;
 }
 
+void mlx5_fc_query_cached_raw(struct mlx5_fc *counter,
+			      u64 *bytes, u64 *packets, u64 *lastuse)
+{
+	struct mlx5_fc_cache c = counter->cache;
+
+	*bytes = c.bytes;
+	*packets = c.packets;
+	*lastuse = c.lastuse;
+}
+
 void mlx5_fc_queue_stats_work(struct mlx5_core_dev *dev,
 			      struct delayed_work *dwork,
 			      unsigned long delay)
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;
 };
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index cd09ef49df22..eda58b78da13 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -169,11 +169,6 @@ static bool tc_act_skip_sw(u32 flags)
 	return (flags & TCA_ACT_FLAGS_SKIP_SW) ? true : false;
 }
 
-static bool tc_act_in_hw(struct tc_action *act)
-{
-	return !!act->in_hw_count;
-}
-
 /* SKIP_HW and SKIP_SW are mutually exclusive flags. */
 static bool tc_act_flags_valid(u32 flags)
 {
@@ -192,6 +187,7 @@ static int offload_action_init(struct flow_offload_action *fl_action,
 	fl_action->extack = extack;
 	fl_action->command = cmd;
 	fl_action->index = act->tcfa_index;
+	fl_action->cookie = (unsigned long)act;
 
 	if (act->ops->offload_act_setup) {
 		spin_lock_bh(&act->tcfa_lock);
@@ -307,9 +303,6 @@ int tcf_action_update_hw_stats(struct tc_action *action)
 	struct flow_offload_action fl_act = {};
 	int err;
 
-	if (!tc_act_in_hw(action))
-		return -EOPNOTSUPP;
-
 	err = offload_action_init(&fl_act, action, FLOW_ACT_STATS, NULL);
 	if (err)
 		return err;
@@ -539,6 +532,8 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 			       (unsigned long)p->tcfa_tm.lastuse))
 			continue;
 
+		tcf_action_update_hw_stats(p);
+
 		nest = nla_nest_start_noflag(skb, n_i);
 		if (!nest) {
 			index--;
@@ -1539,9 +1534,6 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p,
 	if (p == NULL)
 		goto errout;
 
-	/* update hw stats for this action */
-	tcf_action_update_hw_stats(p);
-
 	/* compat_mode being true specifies a call that is supposed
 	 * to add additional backward compatibility statistic TLVs.
 	 */
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index c42fcc47dd6d..35ebe5d5c261 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -545,7 +545,28 @@ static int tcf_pedit_offload_act_setup(struct tc_action *act, void *entry_data,
 		}
 		*index_inc = k;
 	} else {
-		return -EOPNOTSUPP;
+		struct flow_offload_action *fl_action = entry_data;
+		u32 cmd = tcf_pedit_cmd(act, 0);
+		int k;
+
+		switch (cmd) {
+		case TCA_PEDIT_KEY_EX_CMD_SET:
+			fl_action->id = FLOW_ACTION_MANGLE;
+			break;
+		case TCA_PEDIT_KEY_EX_CMD_ADD:
+			fl_action->id = FLOW_ACTION_ADD;
+			break;
+		default:
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit command offload");
+			return -EOPNOTSUPP;
+		}
+
+		for (k = 1; k < tcf_pedit_nkeys(act); k++) {
+			if (cmd != tcf_pedit_cmd(act, k)) {
+				NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit command offload");
+				return -EOPNOTSUPP;
+			}
+		}
 	}
 
 	return 0;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 5b4a95e8a1ee..bfabc9c95fa9 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3577,6 +3577,7 @@ int tc_setup_action(struct flow_action *flow_action,
 		for (k = 0; k < index ; k++) {
 			entry[k].hw_stats = tc_act_hw_stats(act->hw_stats);
 			entry[k].hw_index = act->tcfa_index;
+			entry[k].act_cookie = (unsigned long)act;
 		}
 
 		j += index;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 0b15698b3531..885c95191ccf 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -502,12 +502,7 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f,
 	tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false,
 			 rtnl_held);
 
-	tcf_exts_hw_stats_update(&f->exts, cls_flower.stats.bytes,
-				 cls_flower.stats.pkts,
-				 cls_flower.stats.drops,
-				 cls_flower.stats.lastused,
-				 cls_flower.stats.used_hw_stats,
-				 cls_flower.stats.used_hw_stats_valid);
+	tcf_exts_hw_stats_update(&f->exts, &cls_flower.stats, cls_flower.use_act_stats);
 }
 
 static void __fl_put(struct cls_fl_filter *f)
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 705f63da2c21..fa3bbd187eb9 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -331,11 +331,7 @@ static void mall_stats_hw_filter(struct tcf_proto *tp,
 
 	tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false, true);
 
-	tcf_exts_hw_stats_update(&head->exts, cls_mall.stats.bytes,
-				 cls_mall.stats.pkts, cls_mall.stats.drops,
-				 cls_mall.stats.lastused,
-				 cls_mall.stats.used_hw_stats,
-				 cls_mall.stats.used_hw_stats_valid);
+	tcf_exts_hw_stats_update(&head->exts, &cls_mall.stats, cls_mall.use_act_stats);
 }
 
 static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,