Merge tag 'mlx5-updates-2021-10-18' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

mlx5-updates-2021-10-18

Maor Maor Gottlieb says:
========================
Use hash to select the affinity port in VF LAG

Current VF LAG architecture is based on QP association with a port.
QP must be created after LAG is enabled to allow association with non-native port.
VM Packets going on slow-path to eSwicth manager (SW path or hairpin) will be transmitted
through a different QP than the VM. This means that Different packets of the same flow might
egress from different physical ports.

This patch-set solves this issue by moving the port selection to be based on the hash function
defined by the bond.

When the device is moved to VF LAG mode, the driver creates TTC (traffic type classifier) flow
tables in order to classify the packet and steer it to the relevant hash function. Similar to what
is done in the mlx5 RSS implementation.

Each rule in the TTC table, forwards the packet to port selection flow table which has one hash
split flow group which contains two "catch all" flow table entries. Each entry point to the
relative uplink port. As shown below:

		-------------------
		| FT              |
TTC rule ->	|     ----------- |
		|   FG|   FTE --|-|-----> uplink of port #1
		|     |   FTE --|-|-----> uplink of port #2
		|     ----------- |
		-------------------

Hash split flow group is flow group that created as type of HASH_SPLIT and associated with match definer.
The match definer define the fields which included in the hash calculation.

The driver creates the match definer according to the xmit hash policy of the bond driver.

Patches overview:
========================

Minor E-Switch updates:
- Patch #12, dynamic  allocation of dest array
- Patch #13, increase number of forward destinations to 32

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 293 insertions, 29 deletions

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 109cc8106d16..347167c18802 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1185,6 +1185,7 @@ enum mlx5_cap_type {
 	MLX5_CAP_DEV_EVENT = 0x14,
 	MLX5_CAP_IPSEC,
 	MLX5_CAP_GENERAL_2 = 0x20,
+	MLX5_CAP_PORT_SELECTION = 0x25,
 	/* NUM OF CAP Types */
 	MLX5_CAP_NUM
 };
@@ -1342,6 +1343,20 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET(e_switch_cap, \
 		 mdev->caps.hca[MLX5_CAP_ESWITCH]->max, cap)
 
+#define MLX5_CAP_PORT_SELECTION(mdev, cap) \
+	MLX5_GET(port_selection_cap, \
+		 mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->cur, cap)
+
+#define MLX5_CAP_PORT_SELECTION_MAX(mdev, cap) \
+	MLX5_GET(port_selection_cap, \
+		 mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->max, cap)
+
+#define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \
+	MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap)
+
+#define MLX5_CAP_FLOWTABLE_PORT_SELECTION_MAX(mdev, cap) \
+	MLX5_CAP_PORT_SELECTION_MAX(mdev, flow_table_properties_port_selection.cap)
+
 #define MLX5_CAP_ODP(mdev, cap)\
 	MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap)
 
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 0106c67e8ccb..7a43fec63a35 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -83,6 +83,7 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_RDMA_RX,
 	MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL,
 	MLX5_FLOW_NAMESPACE_RDMA_TX,
+	MLX5_FLOW_NAMESPACE_PORT_SEL,
 };
 
 enum {
@@ -97,6 +98,7 @@ enum {
 
 struct mlx5_pkt_reformat;
 struct mlx5_modify_hdr;
+struct mlx5_flow_definer;
 struct mlx5_flow_table;
 struct mlx5_flow_group;
 struct mlx5_flow_namespace;
@@ -257,6 +259,13 @@ struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
 						 void *modify_actions);
 void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev,
 				struct mlx5_modify_hdr *modify_hdr);
+struct mlx5_flow_definer *
+mlx5_create_match_definer(struct mlx5_core_dev *dev,
+			  enum mlx5_flow_namespace_type ns_type, u16 format_id,
+			  u32 *match_mask);
+void mlx5_destroy_match_definer(struct mlx5_core_dev *dev,
+				struct mlx5_flow_definer *definer);
+int mlx5_get_match_definer_id(struct mlx5_flow_definer *definer);
 
 struct mlx5_pkt_reformat_params {
 	int type;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index c614ad1da44d..09e43019d877 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -94,6 +94,7 @@ enum {
 enum {
 	MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b,
 	MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d,
+	MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018,
 	MLX5_OBJ_TYPE_MKEY = 0xff01,
 	MLX5_OBJ_TYPE_QP = 0xff02,
 	MLX5_OBJ_TYPE_PSV = 0xff03,
@@ -767,6 +768,18 @@ struct mlx5_ifc_flow_table_nic_cap_bits {
 	u8         reserved_at_20c0[0x5f40];
 };
 
+struct mlx5_ifc_port_selection_cap_bits {
+	u8         reserved_at_0[0x10];
+	u8         port_select_flow_table[0x1];
+	u8         reserved_at_11[0xf];
+
+	u8         reserved_at_20[0x1e0];
+
+	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_port_selection;
+
+	u8         reserved_at_400[0x7c00];
+};
+
 enum {
 	MLX5_FDB_TO_VPORT_REG_C_0 = 0x01,
 	MLX5_FDB_TO_VPORT_REG_C_1 = 0x02,
@@ -1515,7 +1528,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         uar_4k[0x1];
 	u8         reserved_at_241[0x9];
 	u8         uar_sz[0x6];
-	u8         reserved_at_248[0x2];
+	u8         port_selection_cap[0x1];
+	u8         reserved_at_248[0x1];
 	u8         umem_uid_0[0x1];
 	u8         reserved_at_250[0x5];
 	u8         log_pg_sz[0x8];
@@ -1718,7 +1732,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         flex_parser_id_outer_first_mpls_over_gre[0x4];
 	u8         flex_parser_id_outer_first_mpls_over_udp_label[0x4];
 
-	u8	   reserved_at_6e0[0x10];
+	u8         max_num_match_definer[0x10];
 	u8	   sf_base_id[0x10];
 
 	u8         flex_parser_id_gtpu_dw_2[0x4];
@@ -1733,7 +1747,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8	   reserved_at_760[0x20];
 	u8	   vhca_tunnel_commands[0x40];
-	u8	   reserved_at_7c0[0x40];
+	u8         match_definer_format_supported[0x40];
 };
 
 struct mlx5_ifc_cmd_hca_cap_2_bits {
@@ -1752,6 +1766,7 @@ enum mlx5_flow_destination_type {
 	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE   = 0x1,
 	MLX5_FLOW_DESTINATION_TYPE_TIR          = 0x2,
 	MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6,
+	MLX5_FLOW_DESTINATION_TYPE_UPLINK       = 0x8,
 
 	MLX5_FLOW_DESTINATION_TYPE_PORT         = 0x99,
 	MLX5_FLOW_DESTINATION_TYPE_COUNTER      = 0x100,
@@ -3164,6 +3179,7 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap;
 	struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap;
 	struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
+	struct mlx5_ifc_port_selection_cap_bits port_selection_cap;
 	struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap;
 	struct mlx5_ifc_qos_cap_bits qos_cap;
 	struct mlx5_ifc_debug_cap_bits debug_cap;
@@ -5652,6 +5668,236 @@ struct mlx5_ifc_query_fte_in_bits {
 	u8         reserved_at_120[0xe0];
 };
 
+struct mlx5_ifc_match_definer_format_0_bits {
+	u8         reserved_at_0[0x100];
+
+	u8         metadata_reg_c_0[0x20];
+
+	u8         metadata_reg_c_1[0x20];
+
+	u8         outer_dmac_47_16[0x20];
+
+	u8         outer_dmac_15_0[0x10];
+	u8         outer_ethertype[0x10];
+
+	u8         reserved_at_180[0x1];
+	u8         sx_sniffer[0x1];
+	u8         functional_lb[0x1];
+	u8         outer_ip_frag[0x1];
+	u8         outer_qp_type[0x2];
+	u8         outer_encap_type[0x2];
+	u8         port_number[0x2];
+	u8         outer_l3_type[0x2];
+	u8         outer_l4_type[0x2];
+	u8         outer_first_vlan_type[0x2];
+	u8         outer_first_vlan_prio[0x3];
+	u8         outer_first_vlan_cfi[0x1];
+	u8         outer_first_vlan_vid[0xc];
+
+	u8         outer_l4_type_ext[0x4];
+	u8         reserved_at_1a4[0x2];
+	u8         outer_ipsec_layer[0x2];
+	u8         outer_l2_type[0x2];
+	u8         force_lb[0x1];
+	u8         outer_l2_ok[0x1];
+	u8         outer_l3_ok[0x1];
+	u8         outer_l4_ok[0x1];
+	u8         outer_second_vlan_type[0x2];
+	u8         outer_second_vlan_prio[0x3];
+	u8         outer_second_vlan_cfi[0x1];
+	u8         outer_second_vlan_vid[0xc];
+
+	u8         outer_smac_47_16[0x20];
+
+	u8         outer_smac_15_0[0x10];
+	u8         inner_ipv4_checksum_ok[0x1];
+	u8         inner_l4_checksum_ok[0x1];
+	u8         outer_ipv4_checksum_ok[0x1];
+	u8         outer_l4_checksum_ok[0x1];
+	u8         inner_l3_ok[0x1];
+	u8         inner_l4_ok[0x1];
+	u8         outer_l3_ok_duplicate[0x1];
+	u8         outer_l4_ok_duplicate[0x1];
+	u8         outer_tcp_cwr[0x1];
+	u8         outer_tcp_ece[0x1];
+	u8         outer_tcp_urg[0x1];
+	u8         outer_tcp_ack[0x1];
+	u8         outer_tcp_psh[0x1];
+	u8         outer_tcp_rst[0x1];
+	u8         outer_tcp_syn[0x1];
+	u8         outer_tcp_fin[0x1];
+};
+
+struct mlx5_ifc_match_definer_format_22_bits {
+	u8         reserved_at_0[0x100];
+
+	u8         outer_ip_src_addr[0x20];
+
+	u8         outer_ip_dest_addr[0x20];
+
+	u8         outer_l4_sport[0x10];
+	u8         outer_l4_dport[0x10];
+
+	u8         reserved_at_160[0x1];
+	u8         sx_sniffer[0x1];
+	u8         functional_lb[0x1];
+	u8         outer_ip_frag[0x1];
+	u8         outer_qp_type[0x2];
+	u8         outer_encap_type[0x2];
+	u8         port_number[0x2];
+	u8         outer_l3_type[0x2];
+	u8         outer_l4_type[0x2];
+	u8         outer_first_vlan_type[0x2];
+	u8         outer_first_vlan_prio[0x3];
+	u8         outer_first_vlan_cfi[0x1];
+	u8         outer_first_vlan_vid[0xc];
+
+	u8         metadata_reg_c_0[0x20];
+
+	u8         outer_dmac_47_16[0x20];
+
+	u8         outer_smac_47_16[0x20];
+
+	u8         outer_smac_15_0[0x10];
+	u8         outer_dmac_15_0[0x10];
+};
+
+struct mlx5_ifc_match_definer_format_23_bits {
+	u8         reserved_at_0[0x100];
+
+	u8         inner_ip_src_addr[0x20];
+
+	u8         inner_ip_dest_addr[0x20];
+
+	u8         inner_l4_sport[0x10];
+	u8         inner_l4_dport[0x10];
+
+	u8         reserved_at_160[0x1];
+	u8         sx_sniffer[0x1];
+	u8         functional_lb[0x1];
+	u8         inner_ip_frag[0x1];
+	u8         inner_qp_type[0x2];
+	u8         inner_encap_type[0x2];
+	u8         port_number[0x2];
+	u8         inner_l3_type[0x2];
+	u8         inner_l4_type[0x2];
+	u8         inner_first_vlan_type[0x2];
+	u8         inner_first_vlan_prio[0x3];
+	u8         inner_first_vlan_cfi[0x1];
+	u8         inner_first_vlan_vid[0xc];
+
+	u8         tunnel_header_0[0x20];
+
+	u8         inner_dmac_47_16[0x20];
+
+	u8         inner_smac_47_16[0x20];
+
+	u8         inner_smac_15_0[0x10];
+	u8         inner_dmac_15_0[0x10];
+};
+
+struct mlx5_ifc_match_definer_format_29_bits {
+	u8         reserved_at_0[0xc0];
+
+	u8         outer_ip_dest_addr[0x80];
+
+	u8         outer_ip_src_addr[0x80];
+
+	u8         outer_l4_sport[0x10];
+	u8         outer_l4_dport[0x10];
+
+	u8         reserved_at_1e0[0x20];
+};
+
+struct mlx5_ifc_match_definer_format_30_bits {
+	u8         reserved_at_0[0xa0];
+
+	u8         outer_ip_dest_addr[0x80];
+
+	u8         outer_ip_src_addr[0x80];
+
+	u8         outer_dmac_47_16[0x20];
+
+	u8         outer_smac_47_16[0x20];
+
+	u8         outer_smac_15_0[0x10];
+	u8         outer_dmac_15_0[0x10];
+};
+
+struct mlx5_ifc_match_definer_format_31_bits {
+	u8         reserved_at_0[0xc0];
+
+	u8         inner_ip_dest_addr[0x80];
+
+	u8         inner_ip_src_addr[0x80];
+
+	u8         inner_l4_sport[0x10];
+	u8         inner_l4_dport[0x10];
+
+	u8         reserved_at_1e0[0x20];
+};
+
+struct mlx5_ifc_match_definer_format_32_bits {
+	u8         reserved_at_0[0xa0];
+
+	u8         inner_ip_dest_addr[0x80];
+
+	u8         inner_ip_src_addr[0x80];
+
+	u8         inner_dmac_47_16[0x20];
+
+	u8         inner_smac_47_16[0x20];
+
+	u8         inner_smac_15_0[0x10];
+	u8         inner_dmac_15_0[0x10];
+};
+
+struct mlx5_ifc_match_definer_bits {
+	u8         modify_field_select[0x40];
+
+	u8         reserved_at_40[0x40];
+
+	u8         reserved_at_80[0x10];
+	u8         format_id[0x10];
+
+	u8         reserved_at_a0[0x160];
+
+	u8         match_mask[16][0x20];
+};
+
+struct mlx5_ifc_general_obj_in_cmd_hdr_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         vhca_tunnel_id[0x10];
+	u8         obj_type[0x10];
+
+	u8         obj_id[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_general_obj_out_cmd_hdr_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         obj_id[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_create_match_definer_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+
+	struct mlx5_ifc_match_definer_bits obj_context;
+};
+
+struct mlx5_ifc_create_match_definer_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
 enum {
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS    = 0x0,
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS  = 0x1,
@@ -8126,6 +8372,11 @@ struct mlx5_ifc_create_flow_group_out_bits {
 };
 
 enum {
+	MLX5_CREATE_FLOW_GROUP_IN_GROUP_TYPE_TCAM_SUBTABLE  = 0x0,
+	MLX5_CREATE_FLOW_GROUP_IN_GROUP_TYPE_HASH_SPLIT     = 0x1,
+};
+
+enum {
 	MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS     = 0x0,
 	MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS   = 0x1,
 	MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_INNER_HEADERS     = 0x2,
@@ -8146,7 +8397,9 @@ struct mlx5_ifc_create_flow_group_in_bits {
 	u8         reserved_at_60[0x20];
 
 	u8         table_type[0x8];
-	u8         reserved_at_88[0x18];
+	u8         reserved_at_88[0x4];
+	u8         group_type[0x4];
+	u8         reserved_at_90[0x10];
 
 	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
@@ -8161,7 +8414,10 @@ struct mlx5_ifc_create_flow_group_in_bits {
 
 	u8         end_flow_index[0x20];
 
-	u8         reserved_at_140[0xa0];
+	u8         reserved_at_140[0x10];
+	u8         match_definer_id[0x10];
+
+	u8         reserved_at_160[0x80];
 
 	u8         reserved_at_1e0[0x18];
 	u8         match_criteria_enable[0x8];
@@ -10434,9 +10690,16 @@ struct mlx5_ifc_dcbx_param_bits {
 	u8         reserved_at_a0[0x160];
 };
 
+enum {
+	MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY = 0,
+	MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT,
+};
+
 struct mlx5_ifc_lagc_bits {
 	u8         fdb_selection_mode[0x1];
-	u8         reserved_at_1[0x1c];
+	u8         reserved_at_1[0x14];
+	u8         port_select_mode[0x3];
+	u8         reserved_at_18[0x5];
 	u8         lag_state[0x3];
 
 	u8         reserved_at_20[0x14];
@@ -10650,29 +10913,6 @@ struct mlx5_ifc_dealloc_memic_out_bits {
 	u8         reserved_at_40[0x40];
 };
 
-struct mlx5_ifc_general_obj_in_cmd_hdr_bits {
-	u8         opcode[0x10];
-	u8         uid[0x10];
-
-	u8         vhca_tunnel_id[0x10];
-	u8         obj_type[0x10];
-
-	u8         obj_id[0x20];
-
-	u8         reserved_at_60[0x20];
-};
-
-struct mlx5_ifc_general_obj_out_cmd_hdr_bits {
-	u8         status[0x8];
-	u8         reserved_at_8[0x18];
-
-	u8         syndrome[0x20];
-
-	u8         obj_id[0x20];
-
-	u8         reserved_at_60[0x20];
-};
-
 struct mlx5_ifc_umem_bits {
 	u8         reserved_at_0[0x80];