net/mlx5e: TC, map tc action cookie to a hw counter

Currently a hardware counter is associated with a flow cookie.
This does not apply to flows using branching action which are required to
return per action stats.

A single counter may apply to multiple actions.
Scan the flow actions in reverse (from the last to the first action) while
caching the last counter.
Associate all the flow attribute tc action cookies with the current
cached counter.

Signed-off-by: Oz Shlomo <ozsh@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Author: ozshlomo

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 \

drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c

@@ -0,0 +1,153 @@
+// 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;
+
+	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;
+
+	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;
+}

drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.h

@@ -0,0 +1,23 @@
+/* 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);
+
+#endif /* __MLX5_EN_ACT_STATS_H__ */

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 {

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);
@@ -5331,8 +5359,16 @@ 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);
@@ -5382,6 +5418,7 @@ 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)
@@ -5458,8 +5495,14 @@ 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:
@@ -5486,6 +5529,7 @@ 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)