Merge branch 'net-sched-expose-HW-stats-types-per-action-used-by-drivers'

Jiri Pirko says:

====================
net: sched: expose HW stats types per action used by drivers

The first patch is just adding a helper used by the second patch too.
The second patch is exposing HW stats types that are used by drivers.

Example:

$ tc filter add dev enp3s0np1 ingress proto ip handle 1 pref 1 flower dst_ip 192.168.1.1 action drop
$ tc -s filter show dev enp3s0np1 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
  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 10 sec used 10 sec
        Action statistics:
        Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
        backlog 0b 0p requeues 0
        used_hw_stats immediate     <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -1639,7 +1639,7 @@ static int bnxt_tc_get_flow_stats(struct bnxt *bp,
 	spin_unlock(&flow->stats_lock);
 
 	flow_stats_update(&tc_flow_cmd->stats, stats.bytes, stats.packets,
-			  lastused);
+			  lastused, FLOW_ACTION_HW_STATS_DELAYED);
 	return 0;
 }
 

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

@@ -903,7 +903,8 @@ int cxgb4_tc_flower_stats(struct net_device *dev,
 			ofld_stats->last_used = jiffies;
 		flow_stats_update(&cls->stats, bytes - ofld_stats->byte_count,
 				  packets - ofld_stats->packet_count,
-				  ofld_stats->last_used);
+				  ofld_stats->last_used,
+				  FLOW_ACTION_HW_STATS_IMMEDIATE);
 
 		ofld_stats->packet_count = packets;
 		ofld_stats->byte_count = bytes;

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

@@ -346,7 +346,8 @@ int cxgb4_tc_matchall_stats(struct net_device *dev,
 		flow_stats_update(&cls_matchall->stats,
 				  bytes - tc_port_matchall->ingress.bytes,
 				  packets - tc_port_matchall->ingress.packets,
-				  tc_port_matchall->ingress.last_used);
+				  tc_port_matchall->ingress.last_used,
+				  FLOW_ACTION_HW_STATS_IMMEDIATE);
 
 		tc_port_matchall->ingress.packets = packets;
 		tc_port_matchall->ingress.bytes = bytes;

drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c

@@ -666,7 +666,8 @@ mlx5_tc_ct_block_flow_offload_stats(struct mlx5_ct_ft *ft,
 		return -ENOENT;
 
 	mlx5_fc_query_cached(entry->counter, &bytes, &packets, &lastuse);
-	flow_stats_update(&f->stats, bytes, packets, lastuse);
+	flow_stats_update(&f->stats, bytes, packets, lastuse,
+			  FLOW_ACTION_HW_STATS_DELAYED);
 
 	return 0;
 }

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

@@ -4468,7 +4468,8 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 no_peer_counter:
 	mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
 out:
-	flow_stats_update(&f->stats, bytes, packets, lastuse);
+	flow_stats_update(&f->stats, bytes, packets, lastuse,
+			  FLOW_ACTION_HW_STATS_DELAYED);
 	trace_mlx5e_stats_flower(f);
 errout:
 	mlx5e_flow_put(priv, flow);
@@ -4585,7 +4586,8 @@ void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv,
 	dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets;
 	dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes;
 	rpriv->prev_vf_vport_stats = cur_stats;
-	flow_stats_update(&ma->stats, dpkts, dbytes, jiffies);
+	flow_stats_update(&ma->stats, dpkts, dbytes, jiffies,
+			  FLOW_ACTION_HW_STATS_DELAYED);
 }
 
 static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv,

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

@@ -786,7 +786,8 @@ struct mlxsw_sp_acl_rule_info *
 mlxsw_sp_acl_rule_rulei(struct mlxsw_sp_acl_rule *rule);
 int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_rule *rule,
-				u64 *packets, u64 *bytes, u64 *last_use);
+				u64 *packets, u64 *bytes, u64 *last_use,
+				enum flow_action_hw_stats *used_hw_stats);
 
 struct mlxsw_sp_fid *mlxsw_sp_acl_dummy_fid(struct mlxsw_sp *mlxsw_sp);
 

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

@@ -967,7 +967,8 @@ static void mlxsw_sp_acl_rule_activity_update_work(struct work_struct *work)
 
 int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_rule *rule,
-				u64 *packets, u64 *bytes, u64 *last_use)
+				u64 *packets, u64 *bytes, u64 *last_use,
+				enum flow_action_hw_stats *used_hw_stats)
 
 {
 	struct mlxsw_sp_acl_rule_info *rulei;
@@ -982,6 +983,7 @@ int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
 						&current_bytes);
 		if (err)
 			return err;
+		*used_hw_stats = FLOW_ACTION_HW_STATS_IMMEDIATE;
 	}
 	*packets = current_packets - rule->last_packets;
 	*bytes = current_bytes - rule->last_bytes;

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

@@ -571,6 +571,7 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 			  struct mlxsw_sp_acl_block *block,
 			  struct flow_cls_offload *f)
 {
+	enum flow_action_hw_stats used_hw_stats = FLOW_ACTION_HW_STATS_DISABLED;
 	struct mlxsw_sp_acl_ruleset *ruleset;
 	struct mlxsw_sp_acl_rule *rule;
 	u64 packets;
@@ -589,11 +590,11 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 		return -EINVAL;
 
 	err = mlxsw_sp_acl_rule_get_stats(mlxsw_sp, rule, &packets, &bytes,
-					  &lastuse);
+					  &lastuse, &used_hw_stats);
 	if (err)
 		goto err_rule_get_stats;
 
-	flow_stats_update(&f->stats, bytes, packets, lastuse);
+	flow_stats_update(&f->stats, bytes, packets, lastuse, used_hw_stats);
 
 	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
 	return 0;

drivers/net/ethernet/mscc/ocelot_flower.c

@@ -224,7 +224,8 @@ int ocelot_cls_flower_stats(struct ocelot *ocelot, int port,
 	if (ret)
 		return ret;
 
-	flow_stats_update(&f->stats, 0x0, ace.stats.pkts, 0x0);
+	flow_stats_update(&f->stats, 0x0, ace.stats.pkts, 0x0,
+			  FLOW_ACTION_HW_STATS_IMMEDIATE);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ocelot_cls_flower_stats);

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

@@ -1490,7 +1490,8 @@ nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
 		nfp_flower_update_merge_stats(app, nfp_flow);
 
 	flow_stats_update(&flow->stats, priv->stats[ctx_id].bytes,
-			  priv->stats[ctx_id].pkts, priv->stats[ctx_id].used);
+			  priv->stats[ctx_id].pkts, priv->stats[ctx_id].used,
+			  FLOW_ACTION_HW_STATS_DELAYED);
 
 	priv->stats[ctx_id].pkts = 0;
 	priv->stats[ctx_id].bytes = 0;

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

@@ -320,7 +320,8 @@ nfp_flower_stats_rate_limiter(struct nfp_app *app, struct net_device *netdev,
 	spin_unlock_bh(&fl_priv->qos_stats_lock);
 
 	flow_stats_update(&flow->stats, diff_bytes, diff_pkts,
-			  repr_priv->qos_table.last_update);
+			  repr_priv->qos_table.last_update,
+			  FLOW_ACTION_HW_STATS_DELAYED);
 	return 0;
 }
 

include/net/act_api.h

@@ -42,6 +42,8 @@ struct tc_action {
 	struct tcf_chain	__rcu *goto_chain;
 	u32			tcfa_flags;
 	u8			hw_stats;
+	u8			used_hw_stats;
+	bool			used_hw_stats_valid;
 };
 #define tcf_index	common.tcfa_index
 #define tcf_refcnt	common.tcfa_refcnt

include/net/flow_offload.h

@@ -370,14 +370,24 @@ struct flow_stats {
 	u64	pkts;
 	u64	bytes;
 	u64	lastused;
+	enum flow_action_hw_stats used_hw_stats;
+	bool used_hw_stats_valid;
 };
 
 static inline void flow_stats_update(struct flow_stats *flow_stats,
-				     u64 bytes, u64 pkts, u64 lastused)
+				     u64 bytes, u64 pkts, u64 lastused,
+				     enum flow_action_hw_stats used_hw_stats)
 {
 	flow_stats->pkts	+= pkts;
 	flow_stats->bytes	+= bytes;
 	flow_stats->lastused	= max_t(u64, flow_stats->lastused, lastused);
+
+	/* The driver should pass value with a maximum of one bit set.
+	 * Passing FLOW_ACTION_HW_STATS_ANY is invalid.
+	 */
+	WARN_ON(used_hw_stats == FLOW_ACTION_HW_STATS_ANY);
+	flow_stats->used_hw_stats |= used_hw_stats;
+	flow_stats->used_hw_stats_valid = true;
 }
 
 enum flow_block_command {

include/net/netlink.h

@@ -1465,6 +1465,21 @@ static inline int nla_put_in6_addr(struct sk_buff *skb, int attrtype,
 	return nla_put(skb, attrtype, sizeof(*addr), addr);
 }
 
+/**
+ * nla_put_bitfield32 - Add a bitfield32 netlink attribute to a socket buffer
+ * @skb: socket buffer to add attribute to
+ * @attrtype: attribute type
+ * @value: value carrying bits
+ * @selector: selector of valid bits
+ */
+static inline int nla_put_bitfield32(struct sk_buff *skb, int attrtype,
+				     __u32 value, __u32 selector)
+{
+	struct nla_bitfield32 tmp = { value, selector, };
+
+	return nla_put(skb, attrtype, sizeof(tmp), &tmp);
+}
+
 /**
  * nla_get_u32 - return payload of u32 attribute
  * @nla: u32 netlink attribute

include/net/pkt_cls.h

@@ -262,7 +262,8 @@ static inline void tcf_exts_put_net(struct tcf_exts *exts)
 
 static inline void
 tcf_exts_stats_update(const struct tcf_exts *exts,
-		      u64 bytes, u64 packets, u64 lastuse)
+		      u64 bytes, u64 packets, u64 lastuse,
+		      u8 used_hw_stats, bool used_hw_stats_valid)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	int i;
@@ -273,6 +274,8 @@ tcf_exts_stats_update(const struct tcf_exts *exts,
 		struct tc_action *a = exts->actions[i];
 
 		tcf_action_stats_update(a, bytes, packets, lastuse, true);
+		a->used_hw_stats = used_hw_stats;
+		a->used_hw_stats_valid = used_hw_stats_valid;
 	}
 
 	preempt_enable();

include/uapi/linux/pkt_cls.h

@@ -18,6 +18,7 @@ enum {
 	TCA_ACT_COOKIE,
 	TCA_ACT_FLAGS,
 	TCA_ACT_HW_STATS,
+	TCA_ACT_USED_HW_STATS,
 	__TCA_ACT_MAX
 };
 

net/sched/act_api.c

@@ -789,23 +789,20 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 	}
 	rcu_read_unlock();
 
-	if (a->hw_stats != TCA_ACT_HW_STATS_ANY) {
-		struct nla_bitfield32 hw_stats = {
-			a->hw_stats,
-			TCA_ACT_HW_STATS_ANY,
-		};
-
-		if (nla_put(skb, TCA_ACT_HW_STATS, sizeof(hw_stats), &hw_stats))
+	if (a->hw_stats != TCA_ACT_HW_STATS_ANY &&
+	    nla_put_bitfield32(skb, TCA_ACT_HW_STATS,
+			       a->hw_stats, TCA_ACT_HW_STATS_ANY))
 		goto nla_put_failure;
-	}
 
-	if (a->tcfa_flags) {
-		struct nla_bitfield32 flags = { a->tcfa_flags,
-						a->tcfa_flags, };
+	if (a->used_hw_stats_valid &&
+	    nla_put_bitfield32(skb, TCA_ACT_USED_HW_STATS,
+			       a->used_hw_stats, TCA_ACT_HW_STATS_ANY))
+		goto nla_put_failure;
 
-		if (nla_put(skb, TCA_ACT_FLAGS, sizeof(flags), &flags))
+	if (a->tcfa_flags &&
+	    nla_put_bitfield32(skb, TCA_ACT_FLAGS,
+			       a->tcfa_flags, a->tcfa_flags))
 		goto nla_put_failure;
-	}
 
 	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)

net/sched/cls_flower.c

@@ -492,7 +492,9 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f,
 
 	tcf_exts_stats_update(&f->exts, cls_flower.stats.bytes,
 			      cls_flower.stats.pkts,
-			      cls_flower.stats.lastused);
+			      cls_flower.stats.lastused,
+			      cls_flower.stats.used_hw_stats,
+			      cls_flower.stats.used_hw_stats_valid);
 }
 
 static void __fl_put(struct cls_fl_filter *f)

net/sched/cls_matchall.c

@@ -338,7 +338,9 @@ static void mall_stats_hw_filter(struct tcf_proto *tp,
 	tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false, true);
 
 	tcf_exts_stats_update(&head->exts, cls_mall.stats.bytes,
-			      cls_mall.stats.pkts, cls_mall.stats.lastused);
+			      cls_mall.stats.pkts, cls_mall.stats.lastused,
+			      cls_mall.stats.used_hw_stats,
+			      cls_mall.stats.used_hw_stats_valid);
 }
 
 static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,

net/sched/sch_red.c

@@ -349,10 +349,6 @@ static int red_dump_offload_stats(struct Qdisc *sch)
 static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
-	struct nla_bitfield32 flags_bf = {
-		.selector = red_supported_flags,
-		.value = q->flags,
-	};
 	struct nlattr *opts = NULL;
 	struct tc_red_qopt opt = {
 		.limit		= q->limit,
@@ -375,7 +371,8 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
 		goto nla_put_failure;
 	if (nla_put(skb, TCA_RED_PARMS, sizeof(opt), &opt) ||
 	    nla_put_u32(skb, TCA_RED_MAX_P, q->parms.max_P) ||
-	    nla_put(skb, TCA_RED_FLAGS, sizeof(flags_bf), &flags_bf))
+	    nla_put_bitfield32(skb, TCA_RED_FLAGS,
+			       q->flags, red_supported_flags))
 		goto nla_put_failure;
 	return nla_nest_end(skb, opts);