[dpdk-dev] [PATCH v3 01/17] common/mlx5: update common part to support packet pacing

[Viacheslav Ovsiienko <viacheslavo@mellanox.com>]

This patch prepares the common part of the mlx5 PMDs to
support packet send scheduling on mbuf timestamps:

  - the DevX routine to query the packet pacing HCA capabilities
  - packet pacing Send Queue attributes support
  - the hardware related definitions

Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
---
 drivers/common/mlx5/Makefile          | 25 +++++++++++++
 drivers/common/mlx5/linux/meson.build | 10 +++++
 drivers/common/mlx5/linux/mlx5_glue.c | 31 +++++++++++++++-
 drivers/common/mlx5/linux/mlx5_glue.h |  5 +++
 drivers/common/mlx5/mlx5_devx_cmds.c  | 19 +++++++++-
 drivers/common/mlx5/mlx5_devx_cmds.h  | 10 +++++
 drivers/common/mlx5/mlx5_prm.h        | 69 ++++++++++++++++++++++++++++++++---
 7 files changed, 161 insertions(+), 8 deletions(-)

diff --git a/drivers/common/mlx5/Makefile b/drivers/common/mlx5/Makefile
index f6c762b..f9dc376 100644
--- a/drivers/common/mlx5/Makefile
+++ b/drivers/common/mlx5/Makefile
@@ -172,6 +172,16 @@ mlx5_autoconf.h.new: $(RTE_SDK)/buildtools/auto-config-h.sh
 		func mlx5dv_devx_qp_query \
 		$(AUTOCONF_OUTPUT)
 	$Q sh -- '$<' '$@' \
+		HAVE_MLX5DV_DEVX_UAR_OFFSET \
+		infiniband/mlx5dv.h \
+		field "struct mlx5dv_devx_uar.mmap_off" \
+		$(AUTOCONF_OUTPUT)
+	$Q sh -- '$<' '$@' \
+		HAVE_MLX5DV_PP_ALLOC \
+		infiniband/mlx5dv.h \
+		func mlx5dv_pp_alloc \
+		$(AUTOCONF_OUTPUT)
+	$Q sh -- '$<' '$@' \
 		HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR \
 		infiniband/mlx5dv.h \
 		func mlx5dv_dr_action_create_dest_devx_tir \
@@ -207,6 +217,21 @@ mlx5_autoconf.h.new: $(RTE_SDK)/buildtools/auto-config-h.sh
 		func mlx5dv_dr_domain_set_reclaim_device_memory \
 		$(AUTOCONF_OUTPUT)
 	$Q sh -- '$<' '$@' \
+		HAVE_MLX5_OPCODE_ENHANCED_MPSW \
+		infiniband/mlx5dv.h \
+		enum MLX5_OPCODE_ENHANCED_MPSW \
+		$(AUTOCONF_OUTPUT)
+	$Q sh -- '$<' '$@' \
+		HAVE_MLX5_OPCODE_SEND_EN \
+		infiniband/mlx5dv.h \
+		enum MLX5_OPCODE_SEND_EN \
+		$(AUTOCONF_OUTPUT)
+	$Q sh -- '$<' '$@' \
+		HAVE_MLX5_OPCODE_WAIT \
+		infiniband/mlx5dv.h \
+		enum MLX5_OPCODE_WAIT \
+		$(AUTOCONF_OUTPUT)
+	$Q sh -- '$<' '$@' \
 		HAVE_ETHTOOL_LINK_MODE_25G \
 		/usr/include/linux/ethtool.h \
 		enum ETHTOOL_LINK_MODE_25000baseCR_Full_BIT \
diff --git a/drivers/common/mlx5/linux/meson.build b/drivers/common/mlx5/linux/meson.build
index 2294213..48e8ad6 100644
--- a/drivers/common/mlx5/linux/meson.build
+++ b/drivers/common/mlx5/linux/meson.build
@@ -64,6 +64,8 @@ has_member_args = [
 	'struct ibv_counter_set_init_attr', 'counter_set_id' ],
 	[ 'HAVE_IBV_DEVICE_COUNTERS_SET_V45', 'infiniband/verbs.h',
 	'struct ibv_counters_init_attr', 'comp_mask' ],
+	[ 'HAVE_MLX5DV_DEVX_UAR_OFFSET', 'infiniband/mlx5dv.h',
+	'struct mlx5dv_devx_uar', 'mmap_off' ],
 ]
 # input array for meson symbol search:
 # [ "MACRO to define if found", "header for the search",
@@ -101,6 +103,8 @@ has_sym_args = [
 	'mlx5dv_devx_obj_query_async' ],
 	[ 'HAVE_IBV_DEVX_QP', 'infiniband/mlx5dv.h',
 	'mlx5dv_devx_qp_query' ],
+	[ 'HAVE_MLX5DV_PP_ALLOC', 'infiniband/mlx5dv.h',
+	'mlx5dv_pp_alloc' ],
 	[ 'HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR', 'infiniband/mlx5dv.h',
 	'mlx5dv_dr_action_create_dest_devx_tir' ],
 	[ 'HAVE_IBV_DEVX_EVENT', 'infiniband/mlx5dv.h',
@@ -116,6 +120,12 @@ has_sym_args = [
 	[ 'HAVE_MLX5DV_DR_VLAN', 'infiniband/mlx5dv.h',
 	'mlx5dv_dr_action_create_push_vlan' ],
 	[ 'HAVE_IBV_VAR', 'infiniband/mlx5dv.h', 'mlx5dv_alloc_var' ],
+	[ 'HAVE_MLX5_OPCODE_ENHANCED_MPSW', 'infiniband/mlx5dv.h',
+	'MLX5_OPCODE_ENHANCED_MPSW' ],
+	[ 'HAVE_MLX5_OPCODE_SEND_EN', 'infiniband/mlx5dv.h',
+	'MLX5_OPCODE_SEND_EN' ],
+	[ 'HAVE_MLX5_OPCODE_WAIT', 'infiniband/mlx5dv.h',
+	'MLX5_OPCODE_WAIT' ],
 	[ 'HAVE_SUPPORTED_40000baseKR4_Full', 'linux/ethtool.h',
 	'SUPPORTED_40000baseKR4_Full' ],
 	[ 'HAVE_SUPPORTED_40000baseCR4_Full', 'linux/ethtool.h',
diff --git a/drivers/common/mlx5/linux/mlx5_glue.c b/drivers/common/mlx5/linux/mlx5_glue.c
index 395519d..4d3875f 100644
--- a/drivers/common/mlx5/linux/mlx5_glue.c
+++ b/drivers/common/mlx5/linux/mlx5_glue.c
@@ -1195,7 +1195,6 @@
 #endif
 }
 
-
 static void
 mlx5_glue_dr_reclaim_domain_memory(void *domain, uint32_t enable)
 {
@@ -1207,6 +1206,34 @@
 #endif
 }
 
+static struct mlx5dv_pp *
+mlx5_glue_dv_alloc_pp(struct ibv_context *context,
+		      size_t pp_context_sz,
+		      const void *pp_context,
+		      uint32_t flags)
+{
+#ifdef HAVE_MLX5DV_PP_ALLOC
+	return mlx5dv_pp_alloc(context, pp_context_sz, pp_context, flags);
+#else
+	RTE_SET_USED(context);
+	RTE_SET_USED(pp_context_sz);
+	RTE_SET_USED(pp_context);
+	RTE_SET_USED(flags);
+	errno = ENOTSUP;
+	return NULL;
+#endif
+}
+
+static void
+mlx5_glue_dv_free_pp(struct mlx5dv_pp *pp)
+{
+#ifdef HAVE_MLX5DV_PP_ALLOC
+	mlx5dv_pp_free(pp);
+#else
+	RTE_SET_USED(pp);
+#endif
+}
+
 __rte_cache_aligned
 const struct mlx5_glue *mlx5_glue = &(const struct mlx5_glue) {
 	.version = MLX5_GLUE_VERSION,
@@ -1319,4 +1346,6 @@
 	.devx_free_uar = mlx5_glue_devx_free_uar,
 	.dv_alloc_var = mlx5_glue_dv_alloc_var,
 	.dv_free_var = mlx5_glue_dv_free_var,
+	.dv_alloc_pp = mlx5_glue_dv_alloc_pp,
+	.dv_free_pp = mlx5_glue_dv_free_pp,
 };
diff --git a/drivers/common/mlx5/linux/mlx5_glue.h b/drivers/common/mlx5/linux/mlx5_glue.h
index 069d854..c4f9b00 100644
--- a/drivers/common/mlx5/linux/mlx5_glue.h
+++ b/drivers/common/mlx5/linux/mlx5_glue.h
@@ -304,6 +304,11 @@ struct mlx5_glue {
 			 struct mlx5dv_devx_async_event_hdr *event_data,
 			 size_t event_resp_len);
 	void (*dr_reclaim_domain_memory)(void *domain, uint32_t enable);
+	struct mlx5dv_pp *(*dv_alloc_pp)(struct ibv_context *context,
+					 size_t pp_context_sz,
+					 const void *pp_context,
+					 uint32_t flags);
+	void (*dv_free_pp)(struct mlx5dv_pp *pp);
 };
 
 extern const struct mlx5_glue *mlx5_glue;
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.c b/drivers/common/mlx5/mlx5_devx_cmds.c
index 2179a83..093636c 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.c
+++ b/drivers/common/mlx5/mlx5_devx_cmds.c
@@ -467,6 +467,14 @@ struct mlx5_devx_obj *
 	attr->vdpa.queue_counters_valid = !!(MLX5_GET64(cmd_hca_cap, hcattr,
 							general_obj_types) &
 				  MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_Q_COUNTERS);
+	attr->wqe_index_ignore = MLX5_GET(cmd_hca_cap, hcattr,
+					  wqe_index_ignore_cap);
+	attr->cross_channel = MLX5_GET(cmd_hca_cap, hcattr, cd);
+	attr->non_wire_sq = MLX5_GET(cmd_hca_cap, hcattr, non_wire_sq);
+	attr->log_max_static_sq_wq = MLX5_GET(cmd_hca_cap, hcattr,
+					      log_max_static_sq_wq);
+	attr->dev_freq_khz = MLX5_GET(cmd_hca_cap, hcattr,
+				      device_frequency_khz);
 	if (attr->qos.sup) {
 		MLX5_SET(query_hca_cap_in, in, op_mod,
 			 MLX5_GET_HCA_CAP_OP_MOD_QOS_CAP |
@@ -487,9 +495,13 @@ struct mlx5_devx_obj *
 		attr->qos.log_max_flow_meter =
 				MLX5_GET(qos_cap, hcattr, log_max_flow_meter);
 		attr->qos.flow_meter_reg_c_ids =
-			MLX5_GET(qos_cap, hcattr, flow_meter_reg_id);
+				MLX5_GET(qos_cap, hcattr, flow_meter_reg_id);
 		attr->qos.flow_meter_reg_share =
-			MLX5_GET(qos_cap, hcattr, flow_meter_reg_share);
+				MLX5_GET(qos_cap, hcattr, flow_meter_reg_share);
+		attr->qos.packet_pacing =
+				MLX5_GET(qos_cap, hcattr, packet_pacing);
+		attr->qos.wqe_rate_pp =
+				MLX5_GET(qos_cap, hcattr, wqe_rate_pp);
 	}
 	if (attr->vdpa.valid)
 		mlx5_devx_cmd_query_hca_vdpa_attr(ctx, &attr->vdpa);
@@ -971,6 +983,8 @@ struct mlx5_devx_obj *
 	MLX5_SET(sqc, sq_ctx, reg_umr, sq_attr->reg_umr);
 	MLX5_SET(sqc, sq_ctx, allow_swp, sq_attr->allow_swp);
 	MLX5_SET(sqc, sq_ctx, hairpin, sq_attr->hairpin);
+	MLX5_SET(sqc, sq_ctx, non_wire, sq_attr->non_wire);
+	MLX5_SET(sqc, sq_ctx, static_sq_wq, sq_attr->static_sq_wq);
 	MLX5_SET(sqc, sq_ctx, user_index, sq_attr->user_index);
 	MLX5_SET(sqc, sq_ctx, cqn, sq_attr->cqn);
 	MLX5_SET(sqc, sq_ctx, packet_pacing_rate_limit_index,
@@ -1185,6 +1199,7 @@ struct mlx5_devx_obj *
 	} else {
 		MLX5_SET64(cqc, cqctx, dbr_addr, attr->db_addr);
 	}
+	MLX5_SET(cqc, cqctx, cqe_sz, attr->cqe_size);
 	MLX5_SET(cqc, cqctx, cc, attr->use_first_only);
 	MLX5_SET(cqc, cqctx, oi, attr->overrun_ignore);
 	MLX5_SET(cqc, cqctx, log_cq_size, attr->log_cq_size);
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.h b/drivers/common/mlx5/mlx5_devx_cmds.h
index 25704ef..c79b349 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.h
+++ b/drivers/common/mlx5/mlx5_devx_cmds.h
@@ -29,6 +29,8 @@ struct mlx5_devx_mkey_attr {
 struct mlx5_hca_qos_attr {
 	uint32_t sup:1;	/* Whether QOS is supported. */
 	uint32_t srtcm_sup:1; /* Whether srTCM mode is supported. */
+	uint32_t packet_pacing:1; /* Packet pacing is supported. */
+	uint32_t wqe_rate_pp:1; /* Packet pacing WQE rate mode. */
 	uint32_t flow_meter_reg_share:1;
 	/* Whether reg_c share is supported. */
 	uint8_t log_max_flow_meter;
@@ -90,6 +92,11 @@ struct mlx5_hca_attr {
 	uint32_t vhca_id:16;
 	uint32_t relaxed_ordering_write:1;
 	uint32_t relaxed_ordering_read:1;
+	uint32_t wqe_index_ignore:1;
+	uint32_t cross_channel:1;
+	uint32_t non_wire_sq:1; /* SQ with non-wire ops is supported. */
+	uint32_t log_max_static_sq_wq:5; /* Static WQE size SQ. */
+	uint32_t dev_freq_khz; /* Timestamp counter frequency, kHz. */
 	struct mlx5_hca_qos_attr qos;
 	struct mlx5_hca_vdpa_attr vdpa;
 };
@@ -207,6 +214,8 @@ struct mlx5_devx_create_sq_attr {
 	uint32_t reg_umr:1;
 	uint32_t allow_swp:1;
 	uint32_t hairpin:1;
+	uint32_t non_wire:1;
+	uint32_t static_sq_wq:1;
 	uint32_t user_index:24;
 	uint32_t cqn:24;
 	uint32_t packet_pacing_rate_limit_index:16;
@@ -230,6 +239,7 @@ struct mlx5_devx_cq_attr {
 	uint32_t db_umem_valid:1;
 	uint32_t use_first_only:1;
 	uint32_t overrun_ignore:1;
+	uint32_t cqe_size:3;
 	uint32_t log_cq_size:5;
 	uint32_t log_page_size:5;
 	uint32_t uar_page_id;
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index c63795f..cf47103 100644
--- a/drivers/common/mlx5/mlx5_prm.h
+++ b/drivers/common/mlx5/mlx5_prm.h
@@ -41,6 +41,10 @@
 /* Invalidate a CQE. */
 #define MLX5_CQE_INVALIDATE (MLX5_CQE_INVALID << 4)
 
+/* Hardware index widths. */
+#define MLX5_CQ_INDEX_WIDTH 24
+#define MLX5_WQ_INDEX_WIDTH 16
+
 /* WQE Segment sizes in bytes. */
 #define MLX5_WSEG_SIZE 16u
 #define MLX5_WQE_CSEG_SIZE sizeof(struct mlx5_wqe_cseg)
@@ -126,7 +130,17 @@
 				  MLX5_ESEG_MIN_INLINE_SIZE)
 
 /* Missed in mlv5dv.h, should define here. */
+#ifndef HAVE_MLX5_OPCODE_ENHANCED_MPSW
 #define MLX5_OPCODE_ENHANCED_MPSW 0x29u
+#endif
+
+#ifndef HAVE_MLX5_OPCODE_SEND_EN
+#define MLX5_OPCODE_SEND_EN 0x17u
+#endif
+
+#ifndef HAVE_MLX5_OPCODE_WAIT
+#define MLX5_OPCODE_WAIT 0x0fu
+#endif
 
 /* CQE value to inform that VLAN is stripped. */
 #define MLX5_CQE_VLAN_STRIPPED (1u << 0)
@@ -255,6 +269,9 @@
 /* The alignment needed for WQ buffer. */
 #define MLX5_WQE_BUF_ALIGNMENT sysconf(_SC_PAGESIZE)
 
+/* The alignment needed for CQ buffer. */
+#define MLX5_CQE_BUF_ALIGNMENT sysconf(_SC_PAGESIZE)
+
 /* Completion mode. */
 enum mlx5_completion_mode {
 	MLX5_COMP_ONLY_ERR = 0x0,
@@ -314,6 +331,13 @@ struct mlx5_wqe_eseg {
 	};
 } __rte_packed;
 
+struct mlx5_wqe_qseg {
+	uint32_t reserved0;
+	uint32_t reserved1;
+	uint32_t max_index;
+	uint32_t qpn_cqn;
+} __rte_packed;
+
 /* The title WQEBB, header of WQE. */
 struct mlx5_wqe {
 	union {
@@ -373,6 +397,14 @@ struct mlx5_cqe {
 	uint8_t op_own;
 };
 
+struct mlx5_cqe_ts {
+	uint64_t timestamp;
+	uint32_t sop_drop_qpn;
+	uint16_t wqe_counter;
+	uint8_t rsvd5;
+	uint8_t op_own;
+};
+
 /* Adding direct verbs to data-path. */
 
 /* CQ sequence number mask. */
@@ -992,7 +1024,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8 reserved_at_40[0x40];
 	u8 log_max_srq_sz[0x8];
 	u8 log_max_qp_sz[0x8];
-	u8 reserved_at_90[0xb];
+	u8 reserved_at_90[0x9];
+	u8 wqe_index_ignore_cap[0x1];
+	u8 dynamic_qp_allocation[0x1];
 	u8 log_max_qp[0x5];
 	u8 reserved_at_a0[0xb];
 	u8 log_max_srq[0x5];
@@ -1018,9 +1052,12 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8 umr_extended_translation_offset[0x1];
 	u8 null_mkey[0x1];
 	u8 log_max_klm_list_size[0x6];
-	u8 reserved_at_120[0xa];
+	u8 non_wire_sq[0x1];
+	u8 reserved_at_121[0x9];
 	u8 log_max_ra_req_dc[0x6];
-	u8 reserved_at_130[0xa];
+	u8 reserved_at_130[0x3];
+	u8 log_max_static_sq_wq[0x5];
+	u8 reserved_at_138[0x2];
 	u8 log_max_ra_res_dc[0x6];
 	u8 reserved_at_140[0xa];
 	u8 log_max_ra_req_qp[0x6];
@@ -1271,7 +1308,8 @@ struct mlx5_ifc_qos_cap_bits {
 	u8 reserved_at_8[0x8];
 	u8 log_max_flow_meter[0x8];
 	u8 flow_meter_reg_id[0x8];
-	u8 reserved_at_25[0x8];
+	u8 wqe_rate_pp[0x1];
+	u8 reserved_at_25[0x7];
 	u8 flow_meter_reg_share[0x1];
 	u8 reserved_at_2e[0x17];
 	u8 packet_pacing_max_rate[0x20];
@@ -1835,7 +1873,9 @@ struct mlx5_ifc_sqc_bits {
 	u8 reg_umr[0x1];
 	u8 allow_swp[0x1];
 	u8 hairpin[0x1];
-	u8 reserved_at_f[0x11];
+	u8 non_wire[0x1];
+	u8 static_sq_wq[0x1];
+	u8 reserved_at_11[0xf];
 	u8 reserved_at_20[0x8];
 	u8 user_index[0x18];
 	u8 reserved_at_40[0x8];
@@ -1935,6 +1975,11 @@ struct mlx5_ifc_flow_meter_parameters_bits {
 	u8         reserved_at_8[0x60];		// 14h-1Ch
 };
 
+enum {
+	MLX5_CQE_SIZE_64B = 0x0,
+	MLX5_CQE_SIZE_128B = 0x1,
+};
+
 struct mlx5_ifc_cqc_bits {
 	u8 status[0x4];
 	u8 as_notify[0x1];
@@ -2486,6 +2531,20 @@ struct mlx5_ifc_query_qp_in_bits {
 	u8 reserved_at_60[0x20];
 };
 
+enum {
+	MLX5_DATA_RATE = 0x0,
+	MLX5_WQE_RATE = 0x1,
+};
+
+struct mlx5_ifc_set_pp_rate_limit_context_bits {
+	u8 rate_limit[0x20];
+	u8 burst_upper_bound[0x20];
+	u8 reserved_at_40[0xC];
+	u8 rate_mode[0x4];
+	u8 typical_packet_size[0x10];
+	u8 reserved_at_60[0x120];
+};
+
 /* CQE format mask. */
 #define MLX5E_CQE_FORMAT_MASK 0xc
 
-- 
1.8.3.1