Merge branch 'mlxsw-Add-support-for-non-equal-cost-multi-path'

Jiri Pirko says:

====================
mlxsw: Add support for non-equal-cost multi-path

Ido says:

In the device, nexthops are stored as adjacency entries in an array
called the KVD linear (KVDL). When a multi-path route is hit the
packet's headers are hashed and then converted to an index into KVDL
based on the adjacency group's size and base index.

Up until now the driver ignored the `weight` parameter for multi-path
routes and allocated only one adjacency entry for each nexthop with a
limit of 32 nexthops in a group. This set makes the driver take the
`weight` parameter into account when allocating adjacency entries.

First patch teaches dpipe to show the size of the adjacency group, so
that users will be able to determine the actual weight of each nexthop.
The second patch refactors the KVDL allocator, making it more receptive
towards the addition of another partition later in the set.

Patches 3-5 introduce small changes towards the actual change in the
sixth patch that populates the adjacency entries according to their
relative weight.

Last two patches finally add another partition to the KVDL, which allows
us to allocate more than 32 entries per-group and thus support more
nexthops and also provide higher accuracy with regards to the requested
weights.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

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

@@ -3726,10 +3726,16 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		return err;
 	}
 
+	err = mlxsw_sp_kvdl_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize KVDL\n");
+		return err;
+	}
+
 	err = mlxsw_sp_fids_init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize FIDs\n");
-		return err;
+		goto err_fids_init;
 	}
 
 	err = mlxsw_sp_traps_init(mlxsw_sp);
@@ -3834,6 +3840,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp_traps_fini(mlxsw_sp);
 err_traps_init:
 	mlxsw_sp_fids_fini(mlxsw_sp);
+err_fids_init:
+	mlxsw_sp_kvdl_fini(mlxsw_sp);
 	return err;
 }
 
@@ -3854,6 +3862,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 	mlxsw_sp_buffers_fini(mlxsw_sp);
 	mlxsw_sp_traps_fini(mlxsw_sp);
 	mlxsw_sp_fids_fini(mlxsw_sp);
+	mlxsw_sp_kvdl_fini(mlxsw_sp);
 }
 
 static const struct mlxsw_config_profile mlxsw_sp_config_profile = {
@@ -3876,8 +3885,8 @@ static const struct mlxsw_config_profile mlxsw_sp_config_profile = {
 	.max_pkey			= 0,
 	.used_kvd_split_data		= 1,
 	.kvd_hash_granularity		= MLXSW_SP_KVD_GRANULARITY,
-	.kvd_hash_single_parts		= 2,
-	.kvd_hash_double_parts		= 1,
+	.kvd_hash_single_parts		= 59,
+	.kvd_hash_double_parts		= 41,
 	.kvd_linear_size		= MLXSW_SP_KVD_LINEAR_SIZE,
 	.swid_config			= {
 		{

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

@@ -62,7 +62,7 @@
 
 #define MLXSW_SP_PORT_BASE_SPEED 25000	/* Mb/s */
 
-#define MLXSW_SP_KVD_LINEAR_SIZE 65536 /* entries */
+#define MLXSW_SP_KVD_LINEAR_SIZE 98304 /* entries */
 #define MLXSW_SP_KVD_GRANULARITY 128
 
 struct mlxsw_sp_port;
@@ -143,6 +143,7 @@ struct mlxsw_sp_mr;
 struct mlxsw_sp_acl;
 struct mlxsw_sp_counter_pool;
 struct mlxsw_sp_fid_core;
+struct mlxsw_sp_kvdl;
 
 struct mlxsw_sp {
 	struct mlxsw_sp_port **ports;
@@ -158,9 +159,7 @@ struct mlxsw_sp {
 	struct mlxsw_afa *afa;
 	struct mlxsw_sp_acl *acl;
 	struct mlxsw_sp_fid_core *fid_core;
-	struct {
-		DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE);
-	} kvdl;
+	struct mlxsw_sp_kvdl *kvdl;
 	struct notifier_block netdevice_nb;
 
 	struct mlxsw_sp_counter_pool *counter_pool;
@@ -411,9 +410,14 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 
 /* spectrum_kvdl.c */
+int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
 			u32 *p_entry_index);
 void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
+int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
+				   unsigned int entry_count,
+				   unsigned int *p_alloc_size);
 
 struct mlxsw_sp_acl_rule_info {
 	unsigned int priority;

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

@@ -44,6 +44,7 @@ enum mlxsw_sp_field_metadata_id {
 	MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD,
 	MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP,
 	MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX,
+	MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_SIZE,
 	MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX,
 };
 
@@ -69,6 +70,11 @@ static struct devlink_dpipe_field mlxsw_sp_dpipe_fields_metadata[] = {
 		.id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX,
 		.bitwidth = 32,
 	},
+	{
+		.name = "adj_size",
+		.id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_SIZE,
+		.bitwidth = 32,
+	},
 	{
 		.name = "adj_hash_index",
 		.id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX,
@@ -851,6 +857,14 @@ static int mlxsw_sp_dpipe_table_adj_matches_dump(void *priv,
 	match.header = &mlxsw_sp_dpipe_header_metadata;
 	match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX;
 
+	err = devlink_dpipe_match_put(skb, &match);
+	if (err)
+		return err;
+
+	match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match.header = &mlxsw_sp_dpipe_header_metadata;
+	match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_SIZE;
+
 	err = devlink_dpipe_match_put(skb, &match);
 	if (err)
 		return err;
@@ -897,6 +911,7 @@ static u64 mlxsw_sp_dpipe_table_adj_size(struct mlxsw_sp *mlxsw_sp)
 
 enum mlxsw_sp_dpipe_table_adj_match {
 	MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX,
+	MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_SIZE,
 	MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX,
 	MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT,
 };
@@ -919,6 +934,11 @@ mlxsw_sp_dpipe_table_adj_match_action_prepare(struct devlink_dpipe_match *matche
 	match->header = &mlxsw_sp_dpipe_header_metadata;
 	match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX;
 
+	match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_SIZE];
+	match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
+	match->header = &mlxsw_sp_dpipe_header_metadata;
+	match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_SIZE;
+
 	match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX];
 	match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT;
 	match->header = &mlxsw_sp_dpipe_header_metadata;
@@ -955,6 +975,15 @@ mlxsw_sp_dpipe_table_adj_entry_prepare(struct devlink_dpipe_entry *entry,
 	match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX];
 	match_value = &match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX];
 
+	match_value->match = match;
+	match_value->value_size = sizeof(u32);
+	match_value->value = kmalloc(match_value->value_size, GFP_KERNEL);
+	if (!match_value->value)
+		return -ENOMEM;
+
+	match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_SIZE];
+	match_value = &match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_SIZE];
+
 	match_value->match = match;
 	match_value->value_size = sizeof(u32);
 	match_value->value = kmalloc(match_value->value_size, GFP_KERNEL);
@@ -993,8 +1022,8 @@ mlxsw_sp_dpipe_table_adj_entry_prepare(struct devlink_dpipe_entry *entry,
 
 static void
 __mlxsw_sp_dpipe_table_adj_entry_fill(struct devlink_dpipe_entry *entry,
-				      u32 adj_index, u32 adj_hash_index,
-				      unsigned char *ha,
+				      u32 adj_index, u32 adj_size,
+				      u32 adj_hash_index, unsigned char *ha,
 				      struct mlxsw_sp_rif *rif)
 {
 	struct devlink_dpipe_value *value;
@@ -1005,6 +1034,10 @@ __mlxsw_sp_dpipe_table_adj_entry_fill(struct devlink_dpipe_entry *entry,
 	p_index = value->value;
 	*p_index = adj_index;
 
+	value = &entry->match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_SIZE];
+	p_index = value->value;
+	*p_index = adj_size;
+
 	value = &entry->match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX];
 	p_index = value->value;
 	*p_index = adj_hash_index;
@@ -1027,10 +1060,11 @@ static void mlxsw_sp_dpipe_table_adj_entry_fill(struct mlxsw_sp *mlxsw_sp,
 	unsigned char *ha = mlxsw_sp_nexthop_ha(nh);
 	u32 adj_hash_index = 0;
 	u32 adj_index = 0;
+	u32 adj_size = 0;
 	int err;
 
-	mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_hash_index);
-	__mlxsw_sp_dpipe_table_adj_entry_fill(entry, adj_index,
+	mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_size, &adj_hash_index);
+	__mlxsw_sp_dpipe_table_adj_entry_fill(entry, adj_index, adj_size,
 					      adj_hash_index, ha, rif);
 	err = mlxsw_sp_nexthop_counter_get(mlxsw_sp, nh, &entry->counter);
 	if (!err)
@@ -1138,13 +1172,15 @@ static int mlxsw_sp_dpipe_table_adj_counters_update(void *priv, bool enable)
 	struct mlxsw_sp_nexthop *nh;
 	u32 adj_hash_index = 0;
 	u32 adj_index = 0;
+	u32 adj_size = 0;
 
 	mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) {
 		if (!mlxsw_sp_nexthop_offload(nh) ||
 		    mlxsw_sp_nexthop_group_has_ipip(nh))
 			continue;
 
-		mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_hash_index);
+		mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_size,
+					 &adj_hash_index);
 		if (enable)
 			mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
 		else