[dpdk-dev] [PATCH v2 07/14] common/mlx5: extend flex parser capabilities

[Viacheslav Ovsiienko <viacheslavo@nvidia.com>]

From: Gregory Etelson <getelson@nvidia.com>

MLX5 PARSE_GRAPH_NODE is the main data structure used by the Flex
Parser when a new parsing protocol is defined. While software
creates PARSE_GRAPH_NODE object for a new protocol, it must
verify that configuration parameters it uses comply with
hardware limits.

The patch queries hardware PARSE_GRAPH_NODE capabilities and
stores ones in PMD internal configuration structure:

 - query capabilties from parse_graph_node attribute page
 - query max_num_prog_sample_field capability from HCA page 2

Signed-off-by: Gregory Etelson <getelson@nvidia.com>
---
 drivers/common/mlx5/mlx5_devx_cmds.c | 57 ++++++++++++++++++++++++
 drivers/common/mlx5/mlx5_devx_cmds.h | 65 +++++++++++++++++++++++++++-
 drivers/common/mlx5/mlx5_prm.h       | 50 ++++++++++++++++++++-
 3 files changed, 168 insertions(+), 4 deletions(-)

diff --git a/drivers/common/mlx5/mlx5_devx_cmds.c b/drivers/common/mlx5/mlx5_devx_cmds.c
index 8273e98146..294ac480dc 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.c
+++ b/drivers/common/mlx5/mlx5_devx_cmds.c
@@ -729,6 +729,53 @@ mlx5_devx_cmd_create_flex_parser(void *ctx,
 	return parse_flex_obj;
 }
 
+static int
+mlx5_devx_cmd_query_hca_parse_graph_node_cap
+	(void *ctx, struct mlx5_hca_flex_attr *attr)
+{
+	uint32_t in[MLX5_ST_SZ_DW(query_hca_cap_in)];
+	uint32_t out[MLX5_ST_SZ_DW(query_hca_cap_out)];
+	void *hcattr;
+	int rc;
+
+	hcattr = mlx5_devx_get_hca_cap(ctx, in, out, &rc,
+			MLX5_GET_HCA_CAP_OP_MOD_PARSE_GRAPH_NODE_CAP |
+			MLX5_HCA_CAP_OPMOD_GET_CUR);
+	if (!hcattr)
+		return rc;
+	attr->node_in = MLX5_GET(parse_graph_node_cap, hcattr, node_in);
+	attr->node_out = MLX5_GET(parse_graph_node_cap, hcattr, node_out);
+	attr->header_length_mode = MLX5_GET(parse_graph_node_cap, hcattr,
+					    header_length_mode);
+	attr->sample_offset_mode = MLX5_GET(parse_graph_node_cap, hcattr,
+					    sample_offset_mode);
+	attr->max_num_arc_in = MLX5_GET(parse_graph_node_cap, hcattr,
+					max_num_arc_in);
+	attr->max_num_arc_out = MLX5_GET(parse_graph_node_cap, hcattr,
+					 max_num_arc_out);
+	attr->max_num_sample = MLX5_GET(parse_graph_node_cap, hcattr,
+					max_num_sample);
+	attr->sample_id_in_out = MLX5_GET(parse_graph_node_cap, hcattr,
+					  sample_id_in_out);
+	attr->max_base_header_length = MLX5_GET(parse_graph_node_cap, hcattr,
+						max_base_header_length);
+	attr->max_sample_base_offset = MLX5_GET(parse_graph_node_cap, hcattr,
+						max_sample_base_offset);
+	attr->max_next_header_offset = MLX5_GET(parse_graph_node_cap, hcattr,
+						max_next_header_offset);
+	attr->header_length_mask_width = MLX5_GET(parse_graph_node_cap, hcattr,
+						  header_length_mask_width);
+	/* Get the max supported samples from HCA CAP 2 */
+	hcattr = mlx5_devx_get_hca_cap(ctx, in, out, &rc,
+			MLX5_GET_HCA_CAP_OP_MOD_GENERAL_DEVICE_2 |
+			MLX5_HCA_CAP_OPMOD_GET_CUR);
+	if (!hcattr)
+		return rc;
+	attr->max_num_prog_sample =
+		MLX5_GET(cmd_hca_cap_2, hcattr,	max_num_prog_sample_field);
+	return 0;
+}
+
 static int
 mlx5_devx_query_pkt_integrity_match(void *hcattr)
 {
@@ -933,6 +980,16 @@ mlx5_devx_cmd_query_hca_attr(void *ctx,
 					log_max_num_meter_aso);
 		}
 	}
+	/*
+	 * Flex item support needs max_num_prog_sample_field
+	 * from the Capabilities 2 table for PARSE_GRAPH_NODE
+	 */
+	if (attr->parse_graph_flex_node) {
+		rc = mlx5_devx_cmd_query_hca_parse_graph_node_cap
+			(ctx, &attr->flex);
+		if (rc)
+			return -1;
+	}
 	if (attr->vdpa.valid)
 		mlx5_devx_cmd_query_hca_vdpa_attr(ctx, &attr->vdpa);
 	if (!attr->eth_net_offloads)
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.h b/drivers/common/mlx5/mlx5_devx_cmds.h
index e576e30f24..fcd0b12e22 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.h
+++ b/drivers/common/mlx5/mlx5_devx_cmds.h
@@ -8,6 +8,7 @@
 #include "mlx5_glue.h"
 #include "mlx5_prm.h"
 #include <rte_compat.h>
+#include <rte_bitops.h>
 
 /*
  * Defines the amount of retries to allocate the first UAR in the page.
@@ -94,6 +95,64 @@ struct mlx5_hca_flow_attr {
 	uint32_t tunnel_header_2_3;
 };
 
+/**
+ * Accumulate port PARSE_GRAPH_NODE capabilities from
+ * PARSE_GRAPH_NODE Capabilities and HCA Capabilities 2 tables
+ */
+__extension__
+struct mlx5_hca_flex_attr {
+	uint32_t node_in;
+	uint32_t node_out;
+	uint16_t header_length_mode;
+	uint16_t sample_offset_mode;
+	uint8_t  max_num_arc_in;
+	uint8_t  max_num_arc_out;
+	uint8_t  max_num_sample;
+	uint8_t  max_num_prog_sample:5;	/* From HCA CAP 2 */
+	uint8_t  sample_id_in_out:1;
+	uint16_t max_base_header_length;
+	uint8_t  max_sample_base_offset;
+	uint16_t max_next_header_offset;
+	uint8_t  header_length_mask_width;
+};
+
+/* ISO C restricts enumerator values to range of 'int' */
+__extension__
+enum {
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_HEAD          = RTE_BIT32(1),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_MAC           = RTE_BIT32(2),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_IP            = RTE_BIT32(3),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_GRE           = RTE_BIT32(4),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_UDP           = RTE_BIT32(5),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_MPLS          = RTE_BIT32(6),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_TCP           = RTE_BIT32(7),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_VXLAN_GRE     = RTE_BIT32(8),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_GENEVE        = RTE_BIT32(9),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_IPSEC_ESP     = RTE_BIT32(10),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_IPV4          = RTE_BIT32(11),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_IPV6          = RTE_BIT32(12),
+	PARSE_GRAPH_NODE_CAP_SUPPORTED_PROTOCOL_PROGRAMMABLE  = RTE_BIT32(31)
+};
+
+enum {
+	PARSE_GRAPH_NODE_CAP_LENGTH_MODE_FIXED          = RTE_BIT32(0),
+	PARSE_GRAPH_NODE_CAP_LENGTH_MODE_EXPLISIT_FIELD = RTE_BIT32(1),
+	PARSE_GRAPH_NODE_CAP_LENGTH_MODE_BITMASK_FIELD  = RTE_BIT32(2)
+};
+
+/*
+ * DWORD shift is the base for calculating header_length_field_mask
+ * value in the MLX5_GRAPH_NODE_LEN_FIELD mode.
+ */
+#define MLX5_PARSE_GRAPH_NODE_HDR_LEN_SHIFT_DWORD 0x02
+
+static inline uint32_t
+mlx5_hca_parse_graph_node_base_hdr_len_mask
+	(const struct mlx5_hca_flex_attr *attr)
+{
+	return (1 << attr->header_length_mask_width) - 1;
+}
+
 /* HCA supports this number of time periods for LRO. */
 #define MLX5_LRO_NUM_SUPP_PERIODS 4
 
@@ -164,6 +223,7 @@ struct mlx5_hca_attr {
 	struct mlx5_hca_qos_attr qos;
 	struct mlx5_hca_vdpa_attr vdpa;
 	struct mlx5_hca_flow_attr flow;
+	struct mlx5_hca_flex_attr flex;
 	int log_max_qp_sz;
 	int log_max_cq_sz;
 	int log_max_qp;
@@ -570,8 +630,9 @@ int mlx5_devx_cmd_query_parse_samples(struct mlx5_devx_obj *flex_obj,
 				      uint32_t ids[], uint32_t num);
 
 __rte_internal
-struct mlx5_devx_obj *mlx5_devx_cmd_create_flex_parser(void *ctx,
-					struct mlx5_devx_graph_node_attr *data);
+struct mlx5_devx_obj *
+mlx5_devx_cmd_create_flex_parser(void *ctx,
+				 struct mlx5_devx_graph_node_attr *data);
 
 __rte_internal
 int mlx5_devx_cmd_register_read(void *ctx, uint16_t reg_id,
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index d361bcf90e..3ff14b4a5a 100644
--- a/drivers/common/mlx5/mlx5_prm.h
+++ b/drivers/common/mlx5/mlx5_prm.h
@@ -975,7 +975,14 @@ struct mlx5_ifc_fte_match_set_misc4_bits {
 	u8 prog_sample_field_id_2[0x20];
 	u8 prog_sample_field_value_3[0x20];
 	u8 prog_sample_field_id_3[0x20];
-	u8 reserved_at_100[0x100];
+	u8 prog_sample_field_value_4[0x20];
+	u8 prog_sample_field_id_4[0x20];
+	u8 prog_sample_field_value_5[0x20];
+	u8 prog_sample_field_id_5[0x20];
+	u8 prog_sample_field_value_6[0x20];
+	u8 prog_sample_field_id_6[0x20];
+	u8 prog_sample_field_value_7[0x20];
+	u8 prog_sample_field_id_7[0x20];
 };
 
 struct mlx5_ifc_fte_match_set_misc5_bits {
@@ -1244,6 +1251,7 @@ enum {
 	MLX5_GET_HCA_CAP_OP_MOD_ROCE = 0x4 << 1,
 	MLX5_GET_HCA_CAP_OP_MOD_NIC_FLOW_TABLE = 0x7 << 1,
 	MLX5_GET_HCA_CAP_OP_MOD_VDPA_EMULATION = 0x13 << 1,
+	MLX5_GET_HCA_CAP_OP_MOD_PARSE_GRAPH_NODE_CAP = 0x1C << 1,
 	MLX5_GET_HCA_CAP_OP_MOD_GENERAL_DEVICE_2 = 0x20 << 1,
 };
 
@@ -1750,6 +1758,27 @@ struct mlx5_ifc_virtio_emulation_cap_bits {
 	u8 reserved_at_1c0[0x620];
 };
 
+/**
+ * PARSE_GRAPH_NODE Capabilities Field Descriptions
+ */
+struct mlx5_ifc_parse_graph_node_cap_bits {
+	u8 node_in[0x20];
+	u8 node_out[0x20];
+	u8 header_length_mode[0x10];
+	u8 sample_offset_mode[0x10];
+	u8 max_num_arc_in[0x08];
+	u8 max_num_arc_out[0x08];
+	u8 max_num_sample[0x08];
+	u8 reserved_at_78[0x07];
+	u8 sample_id_in_out[0x1];
+	u8 max_base_header_length[0x10];
+	u8 reserved_at_90[0x08];
+	u8 max_sample_base_offset[0x08];
+	u8 max_next_header_offset[0x10];
+	u8 reserved_at_b0[0x08];
+	u8 header_length_mask_width[0x08];
+};
+
 struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8 ft_support[0x1];
 	u8 flow_tag[0x1];
@@ -1844,9 +1873,14 @@ struct mlx5_ifc_flow_table_nic_cap_bits {
 		ft_field_support_2_nic_receive;
 };
 
+/*
+ *  HCA Capabilities 2
+ */
 struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8 reserved_at_0[0x80]; /* End of DW4. */
-	u8 reserved_at_80[0xb];
+	u8 reserved_at_80[0x3];
+	u8 max_num_prog_sample_field[0x5];
+	u8 reserved_at_88[0x3];
 	u8 log_max_num_reserved_qpn[0x5];
 	u8 reserved_at_90[0x3];
 	u8 log_reserved_qpn_granularity[0x5];
@@ -3877,6 +3911,12 @@ enum mlx5_parse_graph_flow_match_sample_offset_mode {
 	MLX5_GRAPH_SAMPLE_OFFSET_BITMASK = 0x2,
 };
 
+enum mlx5_parse_graph_flow_match_sample_tunnel_mode {
+	MLX5_GRAPH_SAMPLE_TUNNEL_OUTER = 0x0,
+	MLX5_GRAPH_SAMPLE_TUNNEL_INNER = 0x1,
+	MLX5_GRAPH_SAMPLE_TUNNEL_FIRST = 0x2
+};
+
 /* Node index for an input / output arc of the flex parser graph. */
 enum mlx5_parse_graph_arc_node_index {
 	MLX5_GRAPH_ARC_NODE_NULL = 0x0,
@@ -3890,9 +3930,15 @@ enum mlx5_parse_graph_arc_node_index {
 	MLX5_GRAPH_ARC_NODE_VXLAN_GPE = 0x8,
 	MLX5_GRAPH_ARC_NODE_GENEVE = 0x9,
 	MLX5_GRAPH_ARC_NODE_IPSEC_ESP = 0xa,
+	MLX5_GRAPH_ARC_NODE_IPV4 = 0xb,
+	MLX5_GRAPH_ARC_NODE_IPV6 = 0xc,
 	MLX5_GRAPH_ARC_NODE_PROGRAMMABLE = 0x1f,
 };
 
+#define MLX5_PARSE_GRAPH_FLOW_SAMPLE_MAX 8
+#define MLX5_PARSE_GRAPH_IN_ARC_MAX 8
+#define MLX5_PARSE_GRAPH_OUT_ARC_MAX 8
+
 /**
  * Convert a user mark to flow mark.
  *
-- 
2.18.1