Merge branch 'net-allow-user-specify-TC-action-HW-stats-type'

Jiri Pirko says:

====================
net: allow user specify TC action HW stats type

Currently, when user adds a TC action and the action gets offloaded,
the user expects the HW stats to be counted and included in stats dump.
However, since drivers may implement different types of counting, there
is no way to specify which one the user is interested in.

For example for mlx5, only delayed counters are available as the driver
periodically polls for updated stats.

In case of mlxsw, the counters are queried on dump time. However, the
HW resources for this type of counters is quite limited (couple of
thousands). This limits the amount of supported offloaded filters
significantly. Without counter assigned, the HW is capable to carry
millions of those.

On top of that, mlxsw HW is able to support delayed counters as well in
greater numbers. That is going to be added in a follow-up patch.

This patchset allows user to specify one of the following types of HW
stats for added action:
immediate - queried during dump time
delayed - polled from HW periodically or sent by HW in async manner
disabled - no stats needed

Note that if "hw_stats" option is not passed, user does not care about
the type, just expects any type of stats.

Examples:
$ tc filter add dev enp0s16np28 ingress proto ip handle 1 pref 1 flower skip_sw dst_ip 192.168.1.1 action drop hw_stats disabled
$ tc -s filter show dev enp0s16np28 ingress
filter protocol ip pref 1 flower chain 0
filter protocol ip pref 1 flower chain 0 handle 0x1
  eth_type ipv4
  dst_ip 192.168.1.1
  skip_sw
  in_hw in_hw_count 2
        action order 1: gact action drop
         random type none pass val 0
         index 1 ref 1 bind 1 installed 7 sec used 2 sec
        Action statistics:
        Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
        backlog 0b 0p requeues 0
        hw_stats disabled

$ tc filter add dev enp0s16np28 ingress proto ip handle 1 pref 1 flower skip_sw dst_ip 192.168.1.1 action drop hw_stats immediate
$ tc -s filter show dev enp0s16np28 ingress
filter protocol ip pref 1 flower chain 0
filter protocol ip pref 1 flower chain 0 handle 0x1
  eth_type ipv4
  dst_ip 192.168.1.1
  skip_sw
  in_hw in_hw_count 2
        action order 1: gact action drop
         random type none pass val 0
         index 1 ref 1 bind 1 installed 11 sec used 4 sec
        Action statistics:
        Sent 102 bytes 1 pkt (dropped 1, overlimits 0 requeues 0)
        Sent software 0 bytes 0 pkt
        Sent hardware 102 bytes 1 pkt
        backlog 0b 0p requeues 0
        hw_stats immediate
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c

@@ -279,7 +279,8 @@ bnxt_tc_parse_pedit(struct bnxt *bp, struct bnxt_tc_actions *actions,
 
 static int bnxt_tc_parse_actions(struct bnxt *bp,
 				 struct bnxt_tc_actions *actions,
-				 struct flow_action *flow_action)
+				 struct flow_action *flow_action,
+				 struct netlink_ext_ack *extack)
 {
 	/* Used to store the L2 rewrite mask for dmac (6 bytes) followed by
 	 * smac (6 bytes) if rewrite of both is specified, otherwise either
@@ -299,6 +300,9 @@ static int bnxt_tc_parse_actions(struct bnxt *bp,
 		return -EINVAL;
 	}
 
+	if (!flow_action_basic_hw_stats_types_check(flow_action, extack))
+		return -EOPNOTSUPP;
+
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
 		case FLOW_ACTION_DROP:
@@ -491,7 +495,8 @@ static int bnxt_tc_parse_flow(struct bnxt *bp,
 		flow->tun_mask.tp_src = match.mask->src;
 	}
 
-	return bnxt_tc_parse_actions(bp, &flow->actions, &rule->action);
+	return bnxt_tc_parse_actions(bp, &flow->actions, &rule->action,
+				     tc_flow_cmd->common.extack);
 }
 
 static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp,

drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c

@@ -544,7 +544,8 @@ static bool valid_pedit_action(struct net_device *dev,
 }
 
 int cxgb4_validate_flow_actions(struct net_device *dev,
-				struct flow_action *actions)
+				struct flow_action *actions,
+				struct netlink_ext_ack *extack)
 {
 	struct flow_action_entry *act;
 	bool act_redir = false;
@@ -552,6 +553,9 @@ int cxgb4_validate_flow_actions(struct net_device *dev,
 	bool act_vlan = false;
 	int i;
 
+	if (!flow_action_basic_hw_stats_types_check(actions, extack))
+		return -EOPNOTSUPP;
+
 	flow_action_for_each(i, act, actions) {
 		switch (act->id) {
 		case FLOW_ACTION_ACCEPT:
@@ -642,7 +646,7 @@ int cxgb4_tc_flower_replace(struct net_device *dev,
 	struct filter_ctx ctx;
 	int fidx, ret;
 
-	if (cxgb4_validate_flow_actions(dev, &rule->action))
+	if (cxgb4_validate_flow_actions(dev, &rule->action, extack))
 		return -EOPNOTSUPP;
 
 	if (cxgb4_validate_flow_match(dev, cls))

drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h

@@ -112,7 +112,8 @@ void cxgb4_process_flow_actions(struct net_device *in,
 				struct flow_action *actions,
 				struct ch_filter_specification *fs);
 int cxgb4_validate_flow_actions(struct net_device *dev,
-				struct flow_action *actions);
+				struct flow_action *actions,
+				struct netlink_ext_ack *extack);
 
 int cxgb4_tc_flower_replace(struct net_device *dev,
 			    struct flow_cls_offload *cls);

drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c

@@ -286,7 +286,8 @@ int cxgb4_tc_matchall_replace(struct net_device *dev,
 		}
 
 		ret = cxgb4_validate_flow_actions(dev,
-						  &cls_matchall->rule->action);
+						  &cls_matchall->rule->action,
+						  extack);
 		if (ret)
 			return ret;
 

drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c

@@ -1082,6 +1082,9 @@ static int mvpp2_port_c2_tcam_rule_add(struct mvpp2_port *port,
 	u8 qh, ql, pmap;
 	int index, ctx;
 
+	if (!flow_action_basic_hw_stats_types_check(&rule->flow->action, NULL))
+		return -EOPNOTSUPP;
+
 	memset(&c2, 0, sizeof(c2));
 
 	index = mvpp2_cls_c2_port_flow_index(port, rule->loc);
@@ -1305,6 +1308,9 @@ static int mvpp2_cls_rfs_parse_rule(struct mvpp2_rfs_rule *rule)
 	struct flow_rule *flow = rule->flow;
 	struct flow_action_entry *act;
 
+	if (!flow_action_basic_hw_stats_types_check(&rule->flow->action, NULL))
+		return -EOPNOTSUPP;
+
 	act = &flow->action.entries[0];
 	if (act->id != FLOW_ACTION_QUEUE && act->id != FLOW_ACTION_DROP)
 		return -EOPNOTSUPP;

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -2878,6 +2878,10 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 	if (!flow_action_has_entries(flow_action))
 		return -EINVAL;
 
+	if (!flow_action_hw_stats_types_check(flow_action, extack,
+					      FLOW_ACTION_HW_STATS_TYPE_DELAYED))
+		return -EOPNOTSUPP;
+
 	attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
 
 	flow_action_for_each(i, act, flow_action) {
@@ -3330,6 +3334,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 	if (!flow_action_has_entries(flow_action))
 		return -EINVAL;
 
+	if (!flow_action_hw_stats_types_check(flow_action, extack,
+					      FLOW_ACTION_HW_STATS_TYPE_DELAYED))
+		return -EOPNOTSUPP;
+
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
 		case FLOW_ACTION_DROP:
@@ -4148,6 +4156,9 @@ static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
+	if (!flow_action_basic_hw_stats_types_check(flow_action, extack))
+		return -EOPNOTSUPP;
+
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
 		case FLOW_ACTION_POLICE:

drivers/net/ethernet/mellanox/mlxsw/spectrum.h

@@ -641,7 +641,8 @@ struct mlxsw_sp_acl_rule_info {
 	struct mlxsw_afa_block *act_block;
 	u8 action_created:1,
 	   ingress_bind_blocker:1,
-	   egress_bind_blocker:1;
+	   egress_bind_blocker:1,
+	   counter_valid:1;
 	unsigned int counter_index;
 };
 

drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c

@@ -642,8 +642,14 @@ int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_rule_info *rulei,
 				 struct netlink_ext_ack *extack)
 {
-	return mlxsw_afa_block_append_counter(rulei->act_block,
-					      &rulei->counter_index, extack);
+	int err;
+
+	err = mlxsw_afa_block_append_counter(rulei->act_block,
+					     &rulei->counter_index, extack);
+	if (err)
+		return err;
+	rulei->counter_valid = true;
+	return 0;
 }
 
 int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp,
@@ -857,16 +863,18 @@ int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
 
 {
 	struct mlxsw_sp_acl_rule_info *rulei;
-	u64 current_packets;
-	u64 current_bytes;
+	u64 current_packets = 0;
+	u64 current_bytes = 0;
 	int err;
 
 	rulei = mlxsw_sp_acl_rule_rulei(rule);
-	err = mlxsw_sp_flow_counter_get(mlxsw_sp, rulei->counter_index,
-					&current_packets, &current_bytes);
-	if (err)
-		return err;
-
+	if (rulei->counter_valid) {
+		err = mlxsw_sp_flow_counter_get(mlxsw_sp, rulei->counter_index,
+						&current_packets,
+						&current_bytes);
+		if (err)
+			return err;
+	}
 	*packets = current_packets - rule->last_packets;
 	*bytes = current_bytes - rule->last_bytes;
 	*last_use = rule->last_used;

drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c

@@ -26,11 +26,20 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 
 	if (!flow_action_has_entries(flow_action))
 		return 0;
+	if (!flow_action_mixed_hw_stats_types_check(flow_action, extack))
+		return -EOPNOTSUPP;
 
-	/* Count action is inserted first */
-	err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei, extack);
-	if (err)
-		return err;
+	act = flow_action_first_entry_get(flow_action);
+	if (act->hw_stats_type == FLOW_ACTION_HW_STATS_TYPE_ANY ||
+	    act->hw_stats_type == FLOW_ACTION_HW_STATS_TYPE_IMMEDIATE) {
+		/* Count action is inserted first */
+		err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei, extack);
+		if (err)
+			return err;
+	} else if (act->hw_stats_type != FLOW_ACTION_HW_STATS_TYPE_DISABLED) {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported action HW stats type");
+		return -EOPNOTSUPP;
+	}
 
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {

drivers/net/ethernet/mscc/ocelot_flower.c

@@ -14,7 +14,11 @@ static int ocelot_flower_parse_action(struct flow_cls_offload *f,
 	const struct flow_action_entry *a;
 	int i;
 
-	if (f->rule->action.num_entries != 1)
+	if (!flow_offload_has_one_action(&f->rule->action))
+		return -EOPNOTSUPP;
+
+	if (!flow_action_basic_hw_stats_types_check(&f->rule->action,
+						    f->common.extack))
 		return -EOPNOTSUPP;
 
 	flow_action_for_each(i, a, &f->rule->action) {

drivers/net/ethernet/netronome/nfp/flower/action.c

@@ -1207,6 +1207,10 @@ int nfp_flower_compile_action(struct nfp_app *app,
 	bool pkt_host = false;
 	u32 csum_updated = 0;
 
+	if (!flow_action_basic_hw_stats_types_check(&flow->rule->action,
+						    extack))
+		return -EOPNOTSUPP;
+
 	memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ);
 	nfp_flow->meta.act_len = 0;
 	tun_type = NFP_FL_TUNNEL_NONE;

drivers/net/ethernet/qlogic/qede/qede_filter.c

@@ -1746,7 +1746,8 @@ int qede_get_arfs_filter_count(struct qede_dev *edev)
 }
 
 static int qede_parse_actions(struct qede_dev *edev,
-			      struct flow_action *flow_action)
+			      struct flow_action *flow_action,
+			      struct netlink_ext_ack *extack)
 {
 	const struct flow_action_entry *act;
 	int i;
@@ -1756,6 +1757,9 @@ static int qede_parse_actions(struct qede_dev *edev,
 		return -EINVAL;
 	}
 
+	if (!flow_action_basic_hw_stats_types_check(flow_action, extack))
+		return -EOPNOTSUPP;
+
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
 		case FLOW_ACTION_DROP:
@@ -1970,7 +1974,7 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
 	}
 
 	/* parse tc actions and get the vf_id */
-	if (qede_parse_actions(edev, &f->rule->action))
+	if (qede_parse_actions(edev, &f->rule->action, f->common.extack))
 		goto unlock;
 
 	if (qede_flow_find_fltr(edev, &t)) {
@@ -2038,7 +2042,7 @@ static int qede_flow_spec_validate(struct qede_dev *edev,
 		return -EINVAL;
 	}
 
-	if (qede_parse_actions(edev, flow_action))
+	if (qede_parse_actions(edev, flow_action, NULL))
 		return -EINVAL;
 
 	return 0;

drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c

@@ -367,7 +367,8 @@ static int tc_setup_cbs(struct stmmac_priv *priv,
 
 static int tc_parse_flow_actions(struct stmmac_priv *priv,
 				 struct flow_action *action,
-				 struct stmmac_flow_entry *entry)
+				 struct stmmac_flow_entry *entry,
+				 struct netlink_ext_ack *extack)
 {
 	struct flow_action_entry *act;
 	int i;
@@ -375,6 +376,9 @@ static int tc_parse_flow_actions(struct stmmac_priv *priv,
 	if (!flow_action_has_entries(action))
 		return -EINVAL;
 
+	if (!flow_action_basic_hw_stats_types_check(action, extack))
+		return -EOPNOTSUPP;
+
 	flow_action_for_each(i, act, action) {
 		switch (act->id) {
 		case FLOW_ACTION_DROP:
@@ -530,7 +534,8 @@ static int tc_add_flow(struct stmmac_priv *priv,
 			return -ENOENT;
 	}
 
-	ret = tc_parse_flow_actions(priv, &rule->action, entry);
+	ret = tc_parse_flow_actions(priv, &rule->action, entry,
+				    cls->common.extack);
 	if (ret)
 		return ret;
 

include/net/act_api.h

@@ -41,6 +41,7 @@ struct tc_action {
 	struct tc_cookie	__rcu *act_cookie;
 	struct tcf_chain	__rcu *goto_chain;
 	u32			tcfa_flags;
+	u8			hw_stats_type;
 };
 #define tcf_index	common.tcfa_index
 #define tcf_refcnt	common.tcfa_refcnt
@@ -52,6 +53,9 @@ struct tc_action {
 #define tcf_rate_est	common.tcfa_rate_est
 #define tcf_lock	common.tcfa_lock
 
+#define TCA_ACT_HW_STATS_TYPE_ANY (TCA_ACT_HW_STATS_TYPE_IMMEDIATE | \
+				   TCA_ACT_HW_STATS_TYPE_DELAYED)
+
 /* Update lastuse only if needed, to avoid dirtying a cache line.
  * We use a temp variable to avoid fetching jiffies twice.
  */

include/net/flow_offload.h

@@ -3,6 +3,7 @@
 
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/netlink.h>
 #include <net/flow_dissector.h>
 #include <linux/rhashtable.h>
 
@@ -154,6 +155,12 @@ enum flow_action_mangle_base {
 	FLOW_ACT_MANGLE_HDR_TYPE_UDP,
 };
 
+#define FLOW_ACTION_HW_STATS_TYPE_IMMEDIATE BIT(0)
+#define FLOW_ACTION_HW_STATS_TYPE_DELAYED BIT(1)
+#define FLOW_ACTION_HW_STATS_TYPE_ANY (FLOW_ACTION_HW_STATS_TYPE_IMMEDIATE | \
+				       FLOW_ACTION_HW_STATS_TYPE_DELAYED)
+#define FLOW_ACTION_HW_STATS_TYPE_DISABLED 0
+
 typedef void (*action_destr)(void *priv);
 
 struct flow_action_cookie {
@@ -168,6 +175,7 @@ void flow_action_cookie_destroy(struct flow_action_cookie *cookie);
 
 struct flow_action_entry {
 	enum flow_action_id		id;
+	u8				hw_stats_type;
 	action_destr			destructor;
 	void				*destructor_priv;
 	union {
@@ -248,6 +256,66 @@ static inline bool flow_offload_has_one_action(const struct flow_action *action)
 	return action->num_entries == 1;
 }
 
+static inline bool
+flow_action_mixed_hw_stats_types_check(const struct flow_action *action,
+				       struct netlink_ext_ack *extack)
+{
+	const struct flow_action_entry *action_entry;
+	u8 uninitialized_var(last_hw_stats_type);
+	int i;
+
+	if (flow_offload_has_one_action(action))
+		return true;
+
+	for (i = 0; i < action->num_entries; i++) {
+		action_entry = &action->entries[i];
+		if (i && action_entry->hw_stats_type != last_hw_stats_type) {
+			NL_SET_ERR_MSG_MOD(extack, "Mixing HW stats types for actions is not supported");
+			return false;
+		}
+		last_hw_stats_type = action_entry->hw_stats_type;
+	}
+	return true;
+}
+
+static inline const struct flow_action_entry *
+flow_action_first_entry_get(const struct flow_action *action)
+{
+	WARN_ON(!flow_action_has_entries(action));
+	return &action->entries[0];
+}
+
+static inline bool
+flow_action_hw_stats_types_check(const struct flow_action *action,
+				 struct netlink_ext_ack *extack,
+				 u8 allowed_hw_stats_type)
+{
+	const struct flow_action_entry *action_entry;
+
+	if (!flow_action_has_entries(action))
+		return true;
+	if (!flow_action_mixed_hw_stats_types_check(action, extack))
+		return false;
+	action_entry = flow_action_first_entry_get(action);
+	if (allowed_hw_stats_type == 0 &&
+	    action_entry->hw_stats_type != FLOW_ACTION_HW_STATS_TYPE_ANY) {
+		NL_SET_ERR_MSG_MOD(extack, "Driver supports only default HW stats type \"any\"");
+		return false;
+	} else if (allowed_hw_stats_type != 0 &&
+		   action_entry->hw_stats_type != allowed_hw_stats_type) {
+		NL_SET_ERR_MSG_MOD(extack, "Driver does not support selected HW stats type");
+		return false;
+	}
+	return true;
+}
+
+static inline bool
+flow_action_basic_hw_stats_types_check(const struct flow_action *action,
+				       struct netlink_ext_ack *extack)
+{
+	return flow_action_hw_stats_types_check(action, extack, 0);
+}
+
 #define flow_action_for_each(__i, __act, __actions)			\
         for (__i = 0, __act = &(__actions)->entries[0]; __i < (__actions)->num_entries; __act = &(__actions)->entries[++__i])
 

include/uapi/linux/pkt_cls.h

@@ -17,6 +17,7 @@ enum {
 	TCA_ACT_PAD,
 	TCA_ACT_COOKIE,
 	TCA_ACT_FLAGS,
+	TCA_ACT_HW_STATS_TYPE,
 	__TCA_ACT_MAX
 };
 
@@ -24,6 +25,27 @@ enum {
 					 * actions stats.
 					 */
 
+/* tca HW stats type
+ * When user does not pass the attribute, he does not care.
+ * It is the same as if he would pass the attribute with
+ * all supported bits set.
+ * In case no bits are set, user is not interested in getting any HW statistics.
+ */
+#define TCA_ACT_HW_STATS_TYPE_IMMEDIATE (1 << 0) /* Means that in dump, user
+						  * gets the current HW stats
+						  * state from the device
+						  * queried at the dump time.
+						  */
+#define TCA_ACT_HW_STATS_TYPE_DELAYED (1 << 1) /* Means that in dump, user gets
+						* HW stats that might be out
+						* of date for some time, maybe
+						* couple of seconds. This is
+						* the case when driver polls
+						* stats updates periodically
+						* or when it gets async stats update
+						* from the device.
+						*/
+
 #define TCA_ACT_MAX __TCA_ACT_MAX
 #define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
 #define TCA_ACT_MAX_PRIO 32

net/dsa/slave.c

@@ -865,6 +865,10 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev,
 	if (!flow_offload_has_one_action(&cls->rule->action))
 		return err;
 
+	if (!flow_action_basic_hw_stats_types_check(&cls->rule->action,
+						    cls->common.extack))
+		return err;
+
 	act = &cls->rule->action.entries[0];
 
 	if (act->id == FLOW_ACTION_MIRRED && protocol == htons(ETH_P_ALL)) {

net/sched/act_api.c

@@ -185,6 +185,7 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act)
 	return  nla_total_size(0) /* action number nested */
 		+ nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */
 		+ cookie_len /* TCA_ACT_COOKIE */
+		+ nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_HW_STATS_TYPE */
 		+ nla_total_size(0) /* TCA_ACT_STATS nested */
 		+ nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */
 		/* TCA_STATS_BASIC */
@@ -788,6 +789,17 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 	}
 	rcu_read_unlock();
 
+	if (a->hw_stats_type != TCA_ACT_HW_STATS_TYPE_ANY) {
+		struct nla_bitfield32 hw_stats_type = {
+			a->hw_stats_type,
+			TCA_ACT_HW_STATS_TYPE_ANY,
+		};
+
+		if (nla_put(skb, TCA_ACT_HW_STATS_TYPE, sizeof(hw_stats_type),
+			    &hw_stats_type))
+			goto nla_put_failure;
+	}
+
 	if (a->tcfa_flags) {
 		struct nla_bitfield32 flags = { a->tcfa_flags,
 						a->tcfa_flags, };
@@ -854,7 +866,23 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 	return c;
 }
 
+static u8 tcf_action_hw_stats_type_get(struct nlattr *hw_stats_type_attr)
+{
+	struct nla_bitfield32 hw_stats_type_bf;
+
+	/* If the user did not pass the attr, that means he does
+	 * not care about the type. Return "any" in that case
+	 * which is setting on all supported types.
+	 */
+	if (!hw_stats_type_attr)
+		return TCA_ACT_HW_STATS_TYPE_ANY;
+	hw_stats_type_bf = nla_get_bitfield32(hw_stats_type_attr);
+	return hw_stats_type_bf.value;
+}
+
 static const u32 tca_act_flags_allowed = TCA_ACT_FLAGS_NO_PERCPU_STATS;
+static const u32 tca_act_hw_stats_type_allowed = TCA_ACT_HW_STATS_TYPE_ANY;
+
 static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
 	[TCA_ACT_KIND]		= { .type = NLA_STRING },
 	[TCA_ACT_INDEX]		= { .type = NLA_U32 },
@@ -863,6 +891,8 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
 	[TCA_ACT_OPTIONS]	= { .type = NLA_NESTED },
 	[TCA_ACT_FLAGS]		= { .type = NLA_BITFIELD32,
 				    .validation_data = &tca_act_flags_allowed },
+	[TCA_ACT_HW_STATS_TYPE]	= { .type = NLA_BITFIELD32,
+				    .validation_data = &tca_act_hw_stats_type_allowed },
 };
 
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
@@ -871,6 +901,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    bool rtnl_held,
 				    struct netlink_ext_ack *extack)
 {
+	u8 hw_stats_type = TCA_ACT_HW_STATS_TYPE_ANY;
 	struct nla_bitfield32 flags = { 0, 0 };
 	struct tc_action *a;
 	struct tc_action_ops *a_o;
@@ -903,6 +934,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				goto err_out;
 			}
 		}
+		hw_stats_type =
+			tcf_action_hw_stats_type_get(tb[TCA_ACT_HW_STATS_TYPE]);
 		if (tb[TCA_ACT_FLAGS])
 			flags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]);
 	} else {
@@ -953,6 +986,9 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	if (!name && tb[TCA_ACT_COOKIE])
 		tcf_set_action_cookie(&a->act_cookie, cookie);
 
+	if (!name)
+		a->hw_stats_type = hw_stats_type;
+
 	/* module count goes up only when brand new policy is created
 	 * if it exists and is only bound to in a_o->init() then
 	 * ACT_P_CREATED is not returned (a zero is).

net/sched/cls_api.c

@@ -3464,6 +3464,10 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 	struct tc_action *act;
 	int i, j, k, err = 0;
 
+	BUILD_BUG_ON(TCA_ACT_HW_STATS_TYPE_ANY != FLOW_ACTION_HW_STATS_TYPE_ANY);
+	BUILD_BUG_ON(TCA_ACT_HW_STATS_TYPE_IMMEDIATE != FLOW_ACTION_HW_STATS_TYPE_IMMEDIATE);
+	BUILD_BUG_ON(TCA_ACT_HW_STATS_TYPE_DELAYED != FLOW_ACTION_HW_STATS_TYPE_DELAYED);
+
 	if (!exts)
 		return 0;
 
@@ -3476,6 +3480,9 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 		err = tcf_act_get_cookie(entry, act);
 		if (err)
 			goto err_out_locked;
+
+		entry->hw_stats_type = act->hw_stats_type;
+
 		if (is_tcf_gact_ok(act)) {
 			entry->id = FLOW_ACTION_ACCEPT;
 		} else if (is_tcf_gact_shot(act)) {