Merge branch 'mlxsw-ipv4-host-dpipe-table'

Jiri Pirko says:

====================
mlxsw: Add IPv4 host dpipe table

Arkadi says:

This patchset adds IPv4 host dpipe table support. This will provide the
ability to observe the hardware offloaded IPv4 neighbors.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -5000,6 +5000,15 @@ enum mlxsw_reg_rauht_trap_id {
  */
 MLXSW_ITEM32(reg, rauht, trap_id, 0x60, 0, 9);
 
+enum mlxsw_reg_flow_counter_set_type {
+	/* No count */
+	MLXSW_REG_FLOW_COUNTER_SET_TYPE_NO_COUNT = 0x00,
+	/* Count packets and bytes */
+	MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
+	/* Count only packets */
+	MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS = 0x05,
+};
+
 /* reg_rauht_counter_set_type
  * Counter set type for flow counters
  * Access: RW
@@ -5045,6 +5054,14 @@ static inline void mlxsw_reg_rauht_pack6(char *payload,
 	mlxsw_reg_rauht_dip6_memcpy_to(payload, dip);
 }
 
+static inline void mlxsw_reg_rauht_pack_counter(char *payload,
+						u64 counter_index)
+{
+	mlxsw_reg_rauht_counter_index_set(payload, counter_index);
+	mlxsw_reg_rauht_counter_set_type_set(payload,
+					     MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES);
+}
+
 /* RALEU - Router Algorithmic LPM ECMP Update Register
  * ---------------------------------------------------
  * The register enables updating the ECMP section in the action for multiple
@@ -6041,15 +6058,6 @@ static inline void mlxsw_reg_mpsc_pack(char *payload, u8 local_port, bool e,
 
 MLXSW_REG_DEFINE(mgpc, MLXSW_REG_MGPC_ID, MLXSW_REG_MGPC_LEN);
 
-enum mlxsw_reg_mgpc_counter_set_type {
-	/* No count */
-	MLXSW_REG_MGPC_COUNTER_SET_TYPE_NO_COUT = 0x00,
-	/* Count packets and bytes */
-	MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03,
-	/* Count only packets */
-	MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS = 0x05,
-};
-
 /* reg_mgpc_counter_set_type
  * Counter set type.
  * Access: OP
@@ -6089,7 +6097,7 @@ MLXSW_ITEM64(reg, mgpc, packet_counter, 0x10, 0, 64);
 
 static inline void mlxsw_reg_mgpc_pack(char *payload, u32 counter_index,
 				       enum mlxsw_reg_mgpc_opcode opcode,
-				       enum mlxsw_reg_mgpc_counter_set_type set_type)
+				       enum mlxsw_reg_flow_counter_set_type set_type)
 {
 	MLXSW_REG_ZERO(mgpc, payload);
 	mlxsw_reg_mgpc_counter_index_set(payload, counter_index);

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

@@ -382,11 +382,13 @@ int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_NOP,
-			    MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES);
+			    MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl);
 	if (err)
 		return err;
+	if (packets)
 		*packets = mlxsw_reg_mgpc_packet_counter_get(mgpc_pl);
+	if (bytes)
 		*bytes = mlxsw_reg_mgpc_byte_counter_get(mgpc_pl);
 	return 0;
 }
@@ -397,7 +399,7 @@ static int mlxsw_sp_flow_counter_clear(struct mlxsw_sp *mlxsw_sp,
 	char mgpc_pl[MLXSW_REG_MGPC_LEN];
 
 	mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_CLEAR,
-			    MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES);
+			    MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl);
 }
 

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

@@ -39,5 +39,6 @@ int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp);
 
 #define MLXSW_SP_DPIPE_TABLE_NAME_ERIF "mlxsw_erif"
+#define MLXSW_SP_DPIPE_TABLE_NAME_HOST4 "mlxsw_host4"
 
 #endif /* _MLXSW_PIPELINE_H_*/

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

@@ -901,6 +901,8 @@ struct mlxsw_sp_neigh_entry {
 					* this neigh entry
 					*/
 	struct list_head nexthop_neighs_list_node;
+	unsigned int counter_index;
+	bool counter_valid;
 };
 
 static const struct rhashtable_params mlxsw_sp_neigh_ht_params = {
@@ -909,6 +911,53 @@ static const struct rhashtable_params mlxsw_sp_neigh_ht_params = {
 	.key_len = sizeof(struct mlxsw_sp_neigh_key),
 };
 
+struct mlxsw_sp_neigh_entry *
+mlxsw_sp_rif_neigh_next(struct mlxsw_sp_rif *rif,
+			struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	if (!neigh_entry) {
+		if (list_empty(&rif->neigh_list))
+			return NULL;
+		else
+			return list_first_entry(&rif->neigh_list,
+						typeof(*neigh_entry),
+						rif_list_node);
+	}
+	if (neigh_entry->rif_list_node.next == &rif->neigh_list)
+		return NULL;
+	return list_next_entry(neigh_entry, rif_list_node);
+}
+
+int mlxsw_sp_neigh_entry_type(struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	return neigh_entry->key.n->tbl->family;
+}
+
+unsigned char *
+mlxsw_sp_neigh_entry_ha(struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	return neigh_entry->ha;
+}
+
+u32 mlxsw_sp_neigh4_entry_dip(struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	struct neighbour *n;
+
+	n = neigh_entry->key.n;
+	return ntohl(*((__be32 *) n->primary_key));
+}
+
+int mlxsw_sp_neigh_counter_get(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_neigh_entry *neigh_entry,
+			       u64 *p_counter)
+{
+	if (!neigh_entry->counter_valid)
+		return -EINVAL;
+
+	return mlxsw_sp_flow_counter_get(mlxsw_sp, neigh_entry->counter_index,
+					 p_counter, NULL);
+}
+
 static struct mlxsw_sp_neigh_entry *
 mlxsw_sp_neigh_entry_alloc(struct mlxsw_sp *mlxsw_sp, struct neighbour *n,
 			   u16 rif)
@@ -949,6 +998,41 @@ mlxsw_sp_neigh_entry_remove(struct mlxsw_sp *mlxsw_sp,
 			       mlxsw_sp_neigh_ht_params);
 }
 
+static bool
+mlxsw_sp_neigh4_counter_should_alloc(struct mlxsw_sp *mlxsw_sp)
+{
+	struct devlink *devlink;
+
+	devlink = priv_to_devlink(mlxsw_sp->core);
+	return devlink_dpipe_table_counter_enabled(devlink,
+						   MLXSW_SP_DPIPE_TABLE_NAME_HOST4);
+}
+
+static void
+mlxsw_sp_neigh_counter_alloc(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	if (mlxsw_sp_neigh_entry_type(neigh_entry) != AF_INET ||
+	    !mlxsw_sp_neigh4_counter_should_alloc(mlxsw_sp))
+		return;
+
+	if (mlxsw_sp_flow_counter_alloc(mlxsw_sp, &neigh_entry->counter_index))
+		return;
+
+	neigh_entry->counter_valid = true;
+}
+
+static void
+mlxsw_sp_neigh_counter_free(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	if (!neigh_entry->counter_valid)
+		return;
+	mlxsw_sp_flow_counter_free(mlxsw_sp,
+				   neigh_entry->counter_index);
+	neigh_entry->counter_valid = false;
+}
+
 static struct mlxsw_sp_neigh_entry *
 mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n)
 {
@@ -968,6 +1052,7 @@ mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n)
 	if (err)
 		goto err_neigh_entry_insert;
 
+	mlxsw_sp_neigh_counter_alloc(mlxsw_sp, neigh_entry);
 	list_add(&neigh_entry->rif_list_node, &rif->neigh_list);
 
 	return neigh_entry;
@@ -982,6 +1067,7 @@ mlxsw_sp_neigh_entry_destroy(struct mlxsw_sp *mlxsw_sp,
 			     struct mlxsw_sp_neigh_entry *neigh_entry)
 {
 	list_del(&neigh_entry->rif_list_node);
+	mlxsw_sp_neigh_counter_free(mlxsw_sp, neigh_entry);
 	mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry);
 	mlxsw_sp_neigh_entry_free(neigh_entry);
 }
@@ -1287,6 +1373,9 @@ mlxsw_sp_router_neigh_entry_op4(struct mlxsw_sp *mlxsw_sp,
 
 	mlxsw_reg_rauht_pack4(rauht_pl, op, neigh_entry->rif, neigh_entry->ha,
 			      dip);
+	if (neigh_entry->counter_valid)
+		mlxsw_reg_rauht_pack_counter(rauht_pl,
+					     neigh_entry->counter_index);
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
 }
 
@@ -1301,6 +1390,9 @@ mlxsw_sp_router_neigh_entry_op6(struct mlxsw_sp *mlxsw_sp,
 
 	mlxsw_reg_rauht_pack6(rauht_pl, op, neigh_entry->rif, neigh_entry->ha,
 			      dip);
+	if (neigh_entry->counter_valid)
+		mlxsw_reg_rauht_pack_counter(rauht_pl,
+					     neigh_entry->counter_index);
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
 }
 
@@ -1337,6 +1429,18 @@ mlxsw_sp_neigh_entry_update(struct mlxsw_sp *mlxsw_sp,
 	}
 }
 
+void
+mlxsw_sp_neigh_entry_counter_update(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_neigh_entry *neigh_entry,
+				    bool adding)
+{
+	if (adding)
+		mlxsw_sp_neigh_counter_alloc(mlxsw_sp, neigh_entry);
+	else
+		mlxsw_sp_neigh_counter_free(mlxsw_sp, neigh_entry);
+	mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, true);
+}
+
 struct mlxsw_sp_neigh_event_work {
 	struct work_struct work;
 	struct mlxsw_sp *mlxsw_sp;

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

@@ -42,6 +42,8 @@ enum mlxsw_sp_rif_counter_dir {
 	MLXSW_SP_RIF_COUNTER_EGRESS,
 };
 
+struct mlxsw_sp_neigh_entry;
+
 struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
 					   u16 rif_index);
 u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
@@ -56,5 +58,23 @@ void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp,
 int mlxsw_sp_rif_counter_alloc(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_rif *rif,
 			       enum mlxsw_sp_rif_counter_dir dir);
+struct mlxsw_sp_neigh_entry *
+mlxsw_sp_rif_neigh_next(struct mlxsw_sp_rif *rif,
+			struct mlxsw_sp_neigh_entry *neigh_entry);
+int mlxsw_sp_neigh_entry_type(struct mlxsw_sp_neigh_entry *neigh_entry);
+unsigned char *
+mlxsw_sp_neigh_entry_ha(struct mlxsw_sp_neigh_entry *neigh_entry);
+u32 mlxsw_sp_neigh4_entry_dip(struct mlxsw_sp_neigh_entry *neigh_entry);
+
+#define mlxsw_sp_rif_neigh_for_each(neigh_entry, rif)				\
+	for (neigh_entry = mlxsw_sp_rif_neigh_next(rif, NULL); neigh_entry;	\
+	     neigh_entry = mlxsw_sp_rif_neigh_next(rif, neigh_entry))
+int mlxsw_sp_neigh_counter_get(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_neigh_entry *neigh_entry,
+			       u64 *p_counter);
+void
+mlxsw_sp_neigh_entry_counter_update(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_neigh_entry *neigh_entry,
+				    bool adding);
 
 #endif /* _MLXSW_ROUTER_H_*/

include/net/devlink.h

@@ -178,7 +178,6 @@ struct devlink_dpipe_table_ops;
  * struct devlink_dpipe_table - table object
  * @priv: private
  * @name: table name
- * @size: maximum number of entries
  * @counters_enabled: indicates if counters are active
  * @counter_control_extern: indicates if counter control is in dpipe or
  *			    external tool
@@ -189,7 +188,6 @@ struct devlink_dpipe_table {
 	void *priv;
 	struct list_head list;
 	const char *name;
-	u64 size;
 	bool counters_enabled;
 	bool counter_control_extern;
 	struct devlink_dpipe_table_ops *table_ops;
@@ -204,6 +202,7 @@ struct devlink_dpipe_table {
  * @counters_set_update - when changing the counter status hardware sync
  *			  maybe needed to allocate/free counter related
  *			  resources
+ * @size_get - get size
  */
 struct devlink_dpipe_table_ops {
 	int (*actions_dump)(void *priv, struct sk_buff *skb);
@@ -211,6 +210,7 @@ struct devlink_dpipe_table_ops {
 	int (*entries_dump)(void *priv, bool counters_enabled,
 			    struct devlink_dpipe_dump_ctx *dump_ctx);
 	int (*counters_set_update)(void *priv, bool enable);
+	u64 (*size_get)(void *priv);
 };
 
 /**
@@ -311,8 +311,7 @@ void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index);
 int devlink_dpipe_table_register(struct devlink *devlink,
 				 const char *table_name,
 				 struct devlink_dpipe_table_ops *table_ops,
-				 void *priv, u64 size,
-				 bool counter_control_extern);
+				 void *priv, bool counter_control_extern);
 void devlink_dpipe_table_unregister(struct devlink *devlink,
 				    const char *table_name);
 int devlink_dpipe_headers_register(struct devlink *devlink,
@@ -324,10 +323,13 @@ int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx);
 int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
 				   struct devlink_dpipe_entry *entry);
 int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx);
+void devlink_dpipe_entry_clear(struct devlink_dpipe_entry *entry);
 int devlink_dpipe_action_put(struct sk_buff *skb,
 			     struct devlink_dpipe_action *action);
 int devlink_dpipe_match_put(struct sk_buff *skb,
 			    struct devlink_dpipe_match *match);
+extern struct devlink_dpipe_header devlink_dpipe_header_ethernet;
+extern struct devlink_dpipe_header devlink_dpipe_header_ipv4;
 
 #else
 
@@ -447,6 +449,11 @@ devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
 	return 0;
 }
 
+static inline void
+devlink_dpipe_entry_clear(struct devlink_dpipe_entry *entry)
+{
+}
+
 static inline int
 devlink_dpipe_action_put(struct sk_buff *skb,
 			 struct devlink_dpipe_action *action)

include/uapi/linux/devlink.h

@@ -226,4 +226,17 @@ enum devlink_dpipe_action_type {
 	DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY,
 };
 
+enum devlink_dpipe_field_ethernet_id {
+	DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC,
+};
+
+enum devlink_dpipe_field_ipv4_id {
+	DEVLINK_DPIPE_FIELD_IPV4_DST_IP,
+};
+
+enum devlink_dpipe_header_id {
+	DEVLINK_DPIPE_HEADER_ETHERNET,
+	DEVLINK_DPIPE_HEADER_IPV4,
+};
+
 #endif /* _UAPI_LINUX_DEVLINK_H_ */

net/core/devlink.c

@@ -29,6 +29,40 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/devlink.h>
 
+static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = {
+	{
+		.name = "destination_mac",
+		.id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC,
+		.bitwidth = 48,
+	},
+};
+
+struct devlink_dpipe_header devlink_dpipe_header_ethernet = {
+	.name = "ethernet",
+	.id = DEVLINK_DPIPE_HEADER_ETHERNET,
+	.fields = devlink_dpipe_fields_ethernet,
+	.fields_count = ARRAY_SIZE(devlink_dpipe_fields_ethernet),
+	.global = true,
+};
+EXPORT_SYMBOL(devlink_dpipe_header_ethernet);
+
+static struct devlink_dpipe_field devlink_dpipe_fields_ipv4[] = {
+	{
+		.name = "destination ip",
+		.id = DEVLINK_DPIPE_FIELD_IPV4_DST_IP,
+		.bitwidth = 32,
+	},
+};
+
+struct devlink_dpipe_header devlink_dpipe_header_ipv4 = {
+	.name = "ipv4",
+	.id = DEVLINK_DPIPE_HEADER_IPV4,
+	.fields = devlink_dpipe_fields_ipv4,
+	.fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv4),
+	.global = true,
+};
+EXPORT_SYMBOL(devlink_dpipe_header_ipv4);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
 
 static LIST_HEAD(devlink_list);
@@ -1613,13 +1647,15 @@ static int devlink_dpipe_table_put(struct sk_buff *skb,
 				   struct devlink_dpipe_table *table)
 {
 	struct nlattr *table_attr;
+	u64 table_size;
 
+	table_size = table->table_ops->size_get(table->priv);
 	table_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE);
 	if (!table_attr)
 		return -EMSGSIZE;
 
 	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) ||
-	    nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table->size,
+	    nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table_size,
 			      DEVLINK_ATTR_PAD))
 		goto nla_put_failure;
 	if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED,
@@ -1960,6 +1996,28 @@ int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
 }
 EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close);
 
+void devlink_dpipe_entry_clear(struct devlink_dpipe_entry *entry)
+
+{
+	unsigned int value_count, value_index;
+	struct devlink_dpipe_value *value;
+
+	value = entry->action_values;
+	value_count = entry->action_values_count;
+	for (value_index = 0; value_index < value_count; value_index++) {
+		kfree(value[value_index].value);
+		kfree(value[value_index].mask);
+	}
+
+	value = entry->match_values;
+	value_count = entry->match_values_count;
+	for (value_index = 0; value_index < value_count; value_index++) {
+		kfree(value[value_index].value);
+		kfree(value[value_index].mask);
+	}
+}
+EXPORT_SYMBOL(devlink_dpipe_entry_clear);
+
 static int devlink_dpipe_entries_fill(struct genl_info *info,
 				      enum devlink_command cmd, int flags,
 				      struct devlink_dpipe_table *table)
@@ -2684,20 +2742,21 @@ EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled);
  *	@table_name: table name
  *	@table_ops: table ops
  *	@priv: priv
- *	@size: size
  *	@counter_control_extern: external control for counters
  */
 int devlink_dpipe_table_register(struct devlink *devlink,
 				 const char *table_name,
 				 struct devlink_dpipe_table_ops *table_ops,
-				 void *priv, u64 size,
-				 bool counter_control_extern)
+				 void *priv, bool counter_control_extern)
 {
 	struct devlink_dpipe_table *table;
 
 	if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name))
 		return -EEXIST;
 
+	if (WARN_ON(!table_ops->size_get))
+		return -EINVAL;
+
 	table = kzalloc(sizeof(*table), GFP_KERNEL);
 	if (!table)
 		return -ENOMEM;
@@ -2705,7 +2764,6 @@ int devlink_dpipe_table_register(struct devlink *devlink,
 	table->name = table_name;
 	table->table_ops = table_ops;
 	table->priv = priv;
-	table->size = size;
 	table->counter_control_extern = counter_control_extern;
 
 	mutex_lock(&devlink_mutex);