[dpdk-dev] [PATCH 1/5] common/mlx5: add timestamp format support to DevX

[Viacheslav Ovsiienko <viacheslavo@nvidia.com>]

This patch handles the NIC supported timestamp formats via DevX.
There are two different timestamp format can be provided potentially.
The free-running is some opaque values captured from internal clock
counter clocked by some independent oscillator. The free-running
frequency is not pre-defined and should be queried from the NIC.
The real-time timestamps are expressed in nanosecond, captured
from the dedicated UTC counter, that can be adjusted on the fly
and synchronized with some external master clock.

Depending on the version and configuration the hardware might
support either FR or RT timestamps, or both in the same time on
per queue basis. The commit provides the querying information
about the supported timestamp formats and provides the means
to configure ones at queue creation.

Fixes: e2b4925ef7c1 ("net/mlx5: support Direct Rules E-Switch")
Cc: stable@dpdk.org

Signed-off-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
---
 drivers/common/mlx5/mlx5_devx_cmds.c | 35 ++++++++++++++++++++++--
 drivers/common/mlx5/mlx5_devx_cmds.h |  7 +++++
 drivers/common/mlx5/mlx5_prm.h       | 41 +++++++++++++++++++++++++---
 3 files changed, 76 insertions(+), 7 deletions(-)

diff --git a/drivers/common/mlx5/mlx5_devx_cmds.c b/drivers/common/mlx5/mlx5_devx_cmds.c
index 0060c37fc0..bf9921b78a 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.c
+++ b/drivers/common/mlx5/mlx5_devx_cmds.c
@@ -715,6 +715,9 @@ mlx5_devx_cmd_query_hca_attr(void *ctx,
 				      device_frequency_khz);
 	attr->scatter_fcs_w_decap_disable =
 		MLX5_GET(cmd_hca_cap, hcattr, scatter_fcs_w_decap_disable);
+	attr->roce = MLX5_GET(cmd_hca_cap, hcattr, roce);
+	attr->rq_ts_format = MLX5_GET(cmd_hca_cap, hcattr, rq_ts_format);
+	attr->sq_ts_format = MLX5_GET(cmd_hca_cap, hcattr, sq_ts_format);
 	attr->regex = MLX5_GET(cmd_hca_cap, hcattr, regexp);
 	attr->regexp_num_of_engines = MLX5_GET(cmd_hca_cap, hcattr,
 					       regexp_num_of_engines);
@@ -859,9 +862,32 @@ mlx5_devx_cmd_query_hca_attr(void *ctx,
 	attr->rss_ind_tbl_cap = MLX5_GET
 					(per_protocol_networking_offload_caps,
 					 hcattr, rss_ind_tbl_cap);
-	if (attr->wqe_inline_mode != MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
-		return 0;
-	if (attr->eth_virt) {
+	/* Query HCA attribute for ROCE. */
+	if (attr->roce) {
+		memset(in, 0, sizeof(in));
+		memset(out, 0, sizeof(out));
+		MLX5_SET(query_hca_cap_in, in, opcode,
+			 MLX5_CMD_OP_QUERY_HCA_CAP);
+		MLX5_SET(query_hca_cap_in, in, op_mod,
+			 MLX5_GET_HCA_CAP_OP_MOD_ROCE |
+			 MLX5_HCA_CAP_OPMOD_GET_CUR);
+		rc = mlx5_glue->devx_general_cmd(ctx, in, sizeof(in),
+						 out, sizeof(out));
+		if (rc)
+			goto error;
+		status = MLX5_GET(query_hca_cap_out, out, status);
+		syndrome = MLX5_GET(query_hca_cap_out, out, syndrome);
+		if (status) {
+			DRV_LOG(DEBUG,
+				"Failed to query devx HCA ROCE capabilities, "
+				"status %x, syndrome = %x", status, syndrome);
+			return -1;
+		}
+		hcattr = MLX5_ADDR_OF(query_hca_cap_out, out, capability);
+		attr->qp_ts_format = MLX5_GET(roce_caps, hcattr, qp_ts_format);
+	}
+	if (attr->eth_virt &&
+	    attr->wqe_inline_mode == MLX5_CAP_INLINE_MODE_VPORT_CONTEXT) {
 		rc = mlx5_devx_cmd_query_nic_vport_context(ctx, 0, attr);
 		if (rc) {
 			attr->eth_virt = 0;
@@ -1004,6 +1030,7 @@ mlx5_devx_cmd_create_rq(void *ctx,
 	MLX5_SET(rqc, rq_ctx, cqn, rq_attr->cqn);
 	MLX5_SET(rqc, rq_ctx, counter_set_id, rq_attr->counter_set_id);
 	MLX5_SET(rqc, rq_ctx, rmpn, rq_attr->rmpn);
+	MLX5_SET(sqc, rq_ctx, ts_format, rq_attr->ts_format);
 	wq_ctx = MLX5_ADDR_OF(rqc, rq_ctx, wq);
 	wq_attr = &rq_attr->wq_attr;
 	devx_cmd_fill_wq_data(wq_ctx, wq_attr);
@@ -1376,6 +1403,7 @@ mlx5_devx_cmd_create_sq(void *ctx,
 		 sq_attr->packet_pacing_rate_limit_index);
 	MLX5_SET(sqc, sq_ctx, tis_lst_sz, sq_attr->tis_lst_sz);
 	MLX5_SET(sqc, sq_ctx, tis_num_0, sq_attr->tis_num);
+	MLX5_SET(sqc, sq_ctx, ts_format, sq_attr->ts_format);
 	wq_ctx = MLX5_ADDR_OF(sqc, sq_ctx, wq);
 	wq_attr = &sq_attr->wq_attr;
 	devx_cmd_fill_wq_data(wq_ctx, wq_attr);
@@ -1825,6 +1853,7 @@ mlx5_devx_cmd_create_qp(void *ctx,
 	MLX5_SET(create_qp_in, in, opcode, MLX5_CMD_OP_CREATE_QP);
 	MLX5_SET(qpc, qpc, st, MLX5_QP_ST_RC);
 	MLX5_SET(qpc, qpc, pd, attr->pd);
+	MLX5_SET(qpc, qpc, ts_format, attr->ts_format);
 	if (attr->uar_index) {
 		MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
 		MLX5_SET(qpc, qpc, uar_page, attr->uar_index);
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.h b/drivers/common/mlx5/mlx5_devx_cmds.h
index bc66d28e83..2826c0b2c6 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.h
+++ b/drivers/common/mlx5/mlx5_devx_cmds.h
@@ -121,6 +121,10 @@ struct mlx5_hca_attr {
 	uint32_t dev_freq_khz; /* Timestamp counter frequency, kHz. */
 	uint32_t scatter_fcs_w_decap_disable:1;
 	uint32_t flow_hit_aso:1; /* General obj type FLOW_HIT_ASO supported. */
+	uint32_t roce:1;
+	uint32_t rq_ts_format:2;
+	uint32_t sq_ts_format:2;
+	uint32_t qp_ts_format:2;
 	uint32_t regex:1;
 	uint32_t reg_c_preserve:1;
 	uint32_t regexp_num_of_engines;
@@ -188,6 +192,7 @@ struct mlx5_devx_create_rq_attr {
 	uint32_t state:4;
 	uint32_t flush_in_error_en:1;
 	uint32_t hairpin:1;
+	uint32_t ts_format:2;
 	uint32_t user_index:24;
 	uint32_t cqn:24;
 	uint32_t counter_set_id:8;
@@ -271,6 +276,7 @@ struct mlx5_devx_create_sq_attr {
 	uint32_t hairpin:1;
 	uint32_t non_wire:1;
 	uint32_t static_sq_wq:1;
+	uint32_t ts_format:2;
 	uint32_t user_index:24;
 	uint32_t cqn:24;
 	uint32_t packet_pacing_rate_limit_index:16;
@@ -354,6 +360,7 @@ struct mlx5_devx_qp_attr {
 	uint32_t rq_size:17; /* Must be power of 2. */
 	uint32_t log_rq_stride:3;
 	uint32_t sq_size:17; /* Must be power of 2. */
+	uint32_t ts_format:2;
 	uint32_t dbr_umem_valid:1;
 	uint32_t dbr_umem_id;
 	uint64_t dbr_address;
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index 01a039f1f7..b0120e05d7 100644
--- a/drivers/common/mlx5/mlx5_prm.h
+++ b/drivers/common/mlx5/mlx5_prm.h
@@ -1116,6 +1116,7 @@ enum {
 	MLX5_GET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0 << 1,
 	MLX5_GET_HCA_CAP_OP_MOD_ETHERNET_OFFLOAD_CAPS = 0x1 << 1,
 	MLX5_GET_HCA_CAP_OP_MOD_QOS_CAP = 0xc << 1,
+	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,
 };
@@ -1153,6 +1154,20 @@ enum {
 	MLX5_INLINE_MODE_INNER_TCP_UDP,
 };
 
+/* The supported timestamp formats reported in HCA attributes. */
+enum {
+	MLX5_HCA_CAP_TIMESTAMP_FORMAT_FR = 0x0,
+	MLX5_HCA_CAP_TIMESTAMP_FORMAT_RT = 0x1,
+	MLX5_HCA_CAP_TIMESTAMP_FORMAT_FR_RT = 0x2,
+};
+
+/* The timestamp format attributes to configure queues (RQ/SQ/QP). */
+enum {
+	MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0,
+	MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT      = 0x1,
+	MLX5_QPC_TIMESTAMP_FORMAT_REAL_TIME    = 0x2,
+};
+
 /* HCA bit masks indicating which Flex parser protocols are already enabled. */
 #define MLX5_HCA_FLEX_IPV4_OVER_VXLAN_ENABLED (1UL << 0)
 #define MLX5_HCA_FLEX_IPV6_OVER_VXLAN_ENABLED (1UL << 1)
@@ -1431,7 +1446,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8 reserved_at_3f8[0x3];
 	u8 log_max_current_uc_list[0x5];
 	u8 general_obj_types[0x40];
-	u8 reserved_at_440[0x20];
+	u8 sq_ts_format[0x2];
+	u8 rq_ts_format[0x2];
+	u8 reserved_at_444[0x1C];
 	u8 reserved_at_460[0x10];
 	u8 max_num_eqs[0x10];
 	u8 reserved_at_480[0x3];
@@ -1623,6 +1640,15 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8 reserved_at_c0[0x140];
 };
 
+struct mlx5_ifc_roce_caps_bits {
+	u8 reserved_0[0x5];
+	u8 fl_rc_qp_when_roce_disabled[0x1];
+	u8 fl_rc_qp_when_roce_enabled[0x1];
+	u8 reserved_at_7[0x17];
+	u8 qp_ts_format[0x2];
+	u8 reserved_at_20[0x7e0];
+};
+
 struct mlx5_ifc_flow_table_nic_cap_bits {
 	u8	   reserved_at_0[0x200];
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties;
@@ -1635,6 +1661,7 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_qos_cap_bits qos_cap;
 	struct mlx5_ifc_virtio_emulation_cap_bits vdpa_caps;
 	struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap;
+	struct mlx5_ifc_roce_caps_bits roce_caps;
 	u8 reserved_at_0[0x8000];
 };
 
@@ -1851,7 +1878,9 @@ struct mlx5_ifc_rqc_bits {
 	u8 reserved_at_c[0x1];
 	u8 flush_in_error_en[0x1];
 	u8 hairpin[0x1];
-	u8 reserved_at_f[0x11];
+	u8 reserved_at_f[0xB];
+	u8 ts_format[0x02];
+	u8 reserved_at_1c[0x4];
 	u8 reserved_at_20[0x8];
 	u8 user_index[0x18];
 	u8 reserved_at_40[0x8];
@@ -2157,7 +2186,9 @@ struct mlx5_ifc_sqc_bits {
 	u8 hairpin[0x1];
 	u8 non_wire[0x1];
 	u8 static_sq_wq[0x1];
-	u8 reserved_at_11[0xf];
+	u8 reserved_at_11[0x9];
+	u8 ts_format[0x02];
+	u8 reserved_at_1c[0x4];
 	u8 reserved_at_20[0x8];
 	u8 user_index[0x18];
 	u8 reserved_at_40[0x8];
@@ -2684,7 +2715,9 @@ struct mlx5_ifc_qpc_bits {
 	u8 log_rq_stride[0x3];
 	u8 no_sq[0x1];
 	u8 log_sq_size[0x4];
-	u8 reserved_at_55[0x6];
+	u8 reserved_at_55[0x3];
+	u8 ts_format[0x2];
+	u8 reserved_at_5a[0x1];
 	u8 rlky[0x1];
 	u8 ulp_stateless_offload_mode[0x4];
 	u8 counter_set_id[0x8];
-- 
2.28.0