[dpdk-dev] [PATCH 02/11] common/mlx5: support receive memory pool

[Xueming Li <xuemingl@nvidia.com>]

Adds DevX supports of PRM shared receive memory pool(RMP) object.
RMP is used to support shared Rx queue. Multiple RQ could share same
RMP. Memory buffers are supplied to RMP.

This patch makes RMP RQ optional, created only if mlx5_devx_rq.rmp
is set.

Signed-off-by: Xueming Li <xuemingl@nvidia.com>
---
 drivers/common/mlx5/mlx5_common_devx.c | 310 +++++++++++++++++++++----
 drivers/common/mlx5/mlx5_common_devx.h |  19 +-
 drivers/common/mlx5/mlx5_devx_cmds.c   |  52 +++++
 drivers/common/mlx5/mlx5_devx_cmds.h   |  16 ++
 drivers/common/mlx5/mlx5_prm.h         |  85 ++++++-
 drivers/common/mlx5/version.map        |   1 +
 drivers/net/mlx5/mlx5_devx.c           |   2 +-
 7 files changed, 434 insertions(+), 51 deletions(-)

diff --git a/drivers/common/mlx5/mlx5_common_devx.c b/drivers/common/mlx5/mlx5_common_devx.c
index 22c8d356c45..cd6f13a66b6 100644
--- a/drivers/common/mlx5/mlx5_common_devx.c
+++ b/drivers/common/mlx5/mlx5_common_devx.c
@@ -271,6 +271,39 @@ mlx5_devx_sq_create(void *ctx, struct mlx5_devx_sq *sq_obj, uint16_t log_wqbb_n,
 	return -rte_errno;
 }
 
+/**
+ * Destroy DevX Receive Queue resources.
+ *
+ * @param[in] rq_res
+ *   DevX RQ resource to destroy.
+ */
+static void
+mlx5_devx_wq_res_destroy(struct mlx5_devx_wq_res *rq_res)
+{
+	if (rq_res->umem_obj)
+		claim_zero(mlx5_os_umem_dereg(rq_res->umem_obj));
+	if (rq_res->umem_buf)
+		mlx5_free((void *)(uintptr_t)rq_res->umem_buf);
+	memset(rq_res, 0, sizeof(*rq_res));
+}
+
+/**
+ * Destroy DevX Receive Memory Pool.
+ *
+ * @param[in] rmp
+ *   DevX RMP to destroy.
+ */
+static void
+mlx5_devx_rmp_destroy(struct mlx5_devx_rmp *rmp)
+{
+	MLX5_ASSERT(rmp->ref_cnt == 0);
+	if (rmp->rmp) {
+		claim_zero(mlx5_devx_cmd_destroy(rmp->rmp));
+		rmp->rmp = NULL;
+	}
+	mlx5_devx_wq_res_destroy(&rmp->wq);
+}
+
 /**
  * Destroy DevX Receive Queue.
  *
@@ -280,55 +313,47 @@ mlx5_devx_sq_create(void *ctx, struct mlx5_devx_sq *sq_obj, uint16_t log_wqbb_n,
 void
 mlx5_devx_rq_destroy(struct mlx5_devx_rq *rq)
 {
-	if (rq->rq)
+	if (rq->rq) {
 		claim_zero(mlx5_devx_cmd_destroy(rq->rq));
-	if (rq->umem_obj)
-		claim_zero(mlx5_os_umem_dereg(rq->umem_obj));
-	if (rq->umem_buf)
-		mlx5_free((void *)(uintptr_t)rq->umem_buf);
+		rq->rq = NULL;
+	}
+	if (rq->rmp == NULL) {
+		mlx5_devx_wq_res_destroy(&rq->wq);
+	} else {
+		MLX5_ASSERT(rq->rmp->ref_cnt > 0);
+		rq->rmp->ref_cnt--;
+		if (rq->rmp->ref_cnt == 0)
+			mlx5_devx_rmp_destroy(rq->rmp);
+	}
+	rq->db_rec = 0;
 }
 
 /**
- * Create Receive Queue using DevX API.
- *
- * Get a pointer to partially initialized attributes structure, and updates the
- * following fields:
- *   wq_umem_valid
- *   wq_umem_id
- *   wq_umem_offset
- *   dbr_umem_valid
- *   dbr_umem_id
- *   dbr_addr
- *   log_wq_pg_sz
- * All other fields are updated by caller.
+ * Create WQ resources using DevX API.
  *
  * @param[in] ctx
  *   Context returned from mlx5 open_device() glue function.
- * @param[in/out] rq_obj
- *   Pointer to RQ to create.
+ * @param[in/out] rq_rest
+ *   Pointer to RQ resource to create.
  * @param[in] wqe_size
  *   Size of WQE structure.
  * @param[in] log_wqbb_n
  *   Log of number of WQBBs in queue.
- * @param[in] attr
- *   Pointer to RQ attributes structure.
- * @param[in] socket
- *   Socket to use for allocation.
+ * @param[in] wq_attr
+ *   Pointer to WQ attributes structure.
  *
  * @return
  *   0 on success, a negative errno value otherwise and rte_errno is set.
  */
-int
-mlx5_devx_rq_create(void *ctx, struct mlx5_devx_rq *rq_obj, uint32_t wqe_size,
-		    uint16_t log_wqbb_n,
-		    struct mlx5_devx_create_rq_attr *attr, int socket)
+static int
+mlx5_devx_wq_res_create(void *ctx, struct mlx5_devx_wq_res *rq_res,
+			uint32_t wqe_size, uint16_t log_wqbb_n,
+			struct mlx5_devx_wq_attr *wq_attr, int socket)
 {
-	struct mlx5_devx_obj *rq = NULL;
 	struct mlx5dv_devx_umem *umem_obj = NULL;
 	void *umem_buf = NULL;
 	size_t alignment = MLX5_WQE_BUF_ALIGNMENT;
-	uint32_t umem_size, umem_dbrec;
-	uint16_t rq_size = 1 << log_wqbb_n;
+	uint32_t umem_size;
 	int ret;
 
 	if (alignment == (size_t)-1) {
@@ -337,8 +362,7 @@ mlx5_devx_rq_create(void *ctx, struct mlx5_devx_rq *rq_obj, uint32_t wqe_size,
 		return -rte_errno;
 	}
 	/* Allocate memory buffer for WQEs and doorbell record. */
-	umem_size = wqe_size * rq_size;
-	umem_dbrec = RTE_ALIGN(umem_size, MLX5_DBR_SIZE);
+	umem_size = wqe_size * (1 << log_wqbb_n);
 	umem_size += MLX5_DBR_SIZE;
 	umem_buf = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO, umem_size,
 			       alignment, socket);
@@ -355,14 +379,58 @@ mlx5_devx_rq_create(void *ctx, struct mlx5_devx_rq *rq_obj, uint32_t wqe_size,
 		rte_errno = errno;
 		goto error;
 	}
-	/* Fill attributes for RQ object creation. */
-	attr->wq_attr.wq_umem_valid = 1;
-	attr->wq_attr.wq_umem_id = mlx5_os_get_umem_id(umem_obj);
-	attr->wq_attr.wq_umem_offset = 0;
-	attr->wq_attr.dbr_umem_valid = 1;
-	attr->wq_attr.dbr_umem_id = attr->wq_attr.wq_umem_id;
-	attr->wq_attr.dbr_addr = umem_dbrec;
-	attr->wq_attr.log_wq_pg_sz = MLX5_LOG_PAGE_SIZE;
+	rq_res->umem_buf = umem_buf;
+	rq_res->umem_obj = umem_obj;
+	/* Fill WQ attributes. */
+	wq_attr->wq_umem_valid = 1;
+	wq_attr->wq_umem_id = mlx5_os_get_umem_id(umem_obj);
+	wq_attr->wq_umem_offset = 0;
+	wq_attr->dbr_umem_valid = 1;
+	wq_attr->dbr_umem_id = wq_attr->wq_umem_id;
+	wq_attr->dbr_addr = RTE_ALIGN(umem_size, MLX5_DBR_SIZE);
+	wq_attr->log_wq_pg_sz = MLX5_LOG_PAGE_SIZE;
+	return 0;
+error:
+	ret = rte_errno;
+	if (umem_obj)
+		claim_zero(mlx5_os_umem_dereg(umem_obj));
+	if (umem_buf)
+		mlx5_free((void *)(uintptr_t)umem_buf);
+	rte_errno = ret;
+	return -rte_errno;
+}
+
+/**
+ * Create standalone Receive Queue using DevX API.
+ *
+ * @param[in] ctx
+ *   Context returned from mlx5 open_device() glue function.
+ * @param[in/out] rq_obj
+ *   Pointer to RQ to create.
+ * @param[in] wqe_size
+ *   Size of WQE structure.
+ * @param[in] log_wqbb_n
+ *   Log of number of WQBBs in queue.
+ * @param[in] attr
+ *   Pointer to RQ attributes structure.
+ * @param[in] socket
+ *   Socket to use for allocation.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_devx_rq_std_create(void *ctx, struct mlx5_devx_rq *rq_obj,
+			uint32_t wqe_size, uint16_t log_wqbb_n,
+			struct mlx5_devx_create_rq_attr *attr, int socket)
+{
+	struct mlx5_devx_obj *rq = NULL;
+	int ret;
+
+	ret = mlx5_devx_wq_res_create(ctx, &rq_obj->wq, wqe_size, log_wqbb_n,
+				      &attr->wq_attr, socket);
+	if (ret != 0)
+		return ret;
 	/* Create receive queue object with DevX. */
 	rq = mlx5_devx_cmd_create_rq(ctx, attr, socket);
 	if (!rq) {
@@ -370,18 +438,166 @@ mlx5_devx_rq_create(void *ctx, struct mlx5_devx_rq *rq_obj, uint32_t wqe_size,
 		rte_errno = ENOMEM;
 		goto error;
 	}
-	rq_obj->umem_buf = umem_buf;
-	rq_obj->umem_obj = umem_obj;
 	rq_obj->rq = rq;
-	rq_obj->db_rec = RTE_PTR_ADD(rq_obj->umem_buf, umem_dbrec);
 	return 0;
 error:
 	ret = rte_errno;
-	if (umem_obj)
-		claim_zero(mlx5_os_umem_dereg(umem_obj));
-	if (umem_buf)
-		mlx5_free((void *)(uintptr_t)umem_buf);
+	mlx5_devx_wq_res_destroy(&rq_obj->wq);
 	rte_errno = ret;
 	return -rte_errno;
 }
 
+/**
+ * Create Receive Memory Pool using DevX API.
+ *
+ * @param[in] ctx
+ *   Context returned from mlx5 open_device() glue function.
+ * @param[in/out] rq_obj
+ *   Pointer to RQ to create.
+ * @param[in] wqe_size
+ *   Size of WQE structure.
+ * @param[in] log_wqbb_n
+ *   Log of number of WQBBs in queue.
+ * @param[in] attr
+ *   Pointer to RQ attributes structure.
+ * @param[in] socket
+ *   Socket to use for allocation.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_devx_rmp_create(void *ctx, struct mlx5_devx_rmp *rmp_obj,
+		     uint32_t wqe_size, uint16_t log_wqbb_n,
+		     struct mlx5_devx_wq_attr *wq_attr, int socket)
+{
+	struct mlx5_devx_create_rmp_attr rmp_attr = { 0 };
+	int ret;
+
+	rmp_attr.wq_attr = *wq_attr;
+	ret = mlx5_devx_wq_res_create(ctx, &rmp_obj->wq, wqe_size, log_wqbb_n,
+				      &rmp_attr.wq_attr, socket);
+	if (ret != 0)
+		return ret;
+	rmp_attr.state = MLX5_RMPC_STATE_RDY;
+	rmp_attr.basic_cyclic_rcv_wqe =
+		wq_attr->wq_type == MLX5_WQ_TYPE_CYCLIC_STRIDING_RQ ?
+		0 : 1;
+	/* Create receive queue object with DevX. */
+	rmp_obj->rmp = mlx5_devx_cmd_create_rmp(ctx, &rmp_attr, socket);
+	if (rmp_obj->rmp == NULL) {
+		DRV_LOG(ERR, "Can't create DevX RMP object.");
+		rte_errno = ENOMEM;
+		goto error;
+	}
+	return 0;
+error:
+	ret = rte_errno;
+	mlx5_devx_wq_res_destroy(&rmp_obj->wq);
+	rte_errno = ret;
+	return -rte_errno;
+}
+
+/**
+ * Create Shared Receive Queue based on RMP using DevX API.
+ *
+ * @param[in] ctx
+ *   Context returned from mlx5 open_device() glue function.
+ * @param[in/out] rq_obj
+ *   Pointer to RQ to create.
+ * @param[in] wqe_size
+ *   Size of WQE structure.
+ * @param[in] log_wqbb_n
+ *   Log of number of WQBBs in queue.
+ * @param[in] attr
+ *   Pointer to RQ attributes structure.
+ * @param[in] socket
+ *   Socket to use for allocation.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_devx_rq_shared_create(void *ctx, struct mlx5_devx_rq *rq_obj,
+			   uint32_t wqe_size, uint16_t log_wqbb_n,
+			   struct mlx5_devx_create_rq_attr *attr, int socket)
+{
+	struct mlx5_devx_obj *rq = NULL;
+	int ret;
+
+	ret = mlx5_devx_rmp_create(ctx, rq_obj->rmp, wqe_size, log_wqbb_n,
+				   &attr->wq_attr, socket);
+	if (ret != 0)
+		return ret;
+	rq_obj->rmp->ref_cnt++;
+	attr->mem_rq_type = MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_RMP;
+	attr->rmpn = rq_obj->rmp->rmp->id;
+	attr->flush_in_error_en = 0;
+	memset(&attr->wq_attr, 0, sizeof(attr->wq_attr));
+	/* Create receive queue object with DevX. */
+	rq = mlx5_devx_cmd_create_rq(ctx, attr, socket);
+	if (!rq) {
+		DRV_LOG(ERR, "Can't create DevX RMP RQ object.");
+		rte_errno = ENOMEM;
+		goto error;
+	}
+	rq_obj->rq = rq;
+	return 0;
+error:
+	ret = rte_errno;
+	mlx5_devx_rq_destroy(rq_obj);
+	rte_errno = ret;
+	return -rte_errno;
+}
+
+/**
+ * Create Receive Queue using DevX API. Shared RQ is created only if rmp set.
+ *
+ * Get a pointer to partially initialized attributes structure, and updates the
+ * following fields:
+ *   wq_umem_valid
+ *   wq_umem_id
+ *   wq_umem_offset
+ *   dbr_umem_valid
+ *   dbr_umem_id
+ *   dbr_addr
+ *   log_wq_pg_sz
+ * All other fields are updated by caller.
+ *
+ * @param[in] ctx
+ *   Context returned from mlx5 open_device() glue function.
+ * @param[in/out] rq_obj
+ *   Pointer to RQ to create.
+ * @param[in] wqe_size
+ *   Size of WQE structure.
+ * @param[in] log_wqbb_n
+ *   Log of number of WQBBs in queue.
+ * @param[in] attr
+ *   Pointer to RQ attributes structure.
+ * @param[in] socket
+ *   Socket to use for allocation.
+ *
+ * @return
+ *   0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_devx_rq_create(void *ctx, struct mlx5_devx_rq *rq_obj,
+		    uint32_t wqe_size, uint16_t log_wqbb_n,
+		    struct mlx5_devx_create_rq_attr *attr, int socket)
+{
+	uint32_t umem_size, umem_dbrec;
+	int ret;
+
+	if (rq_obj->rmp == NULL)
+		ret = mlx5_devx_rq_std_create(ctx, rq_obj, wqe_size,
+					      log_wqbb_n, attr, socket);
+	else
+		ret = mlx5_devx_rq_shared_create(ctx, rq_obj, wqe_size,
+						 log_wqbb_n, attr, socket);
+	if (ret != 0)
+		return ret;
+	umem_size = wqe_size * (1 << log_wqbb_n);
+	umem_dbrec = RTE_ALIGN(umem_size, MLX5_DBR_SIZE);
+	rq_obj->db_rec = RTE_PTR_ADD(rq_obj->wq.umem_buf, umem_dbrec);
+	return 0;
+}
diff --git a/drivers/common/mlx5/mlx5_common_devx.h b/drivers/common/mlx5/mlx5_common_devx.h
index aad0184e5ac..328b6ce9324 100644
--- a/drivers/common/mlx5/mlx5_common_devx.h
+++ b/drivers/common/mlx5/mlx5_common_devx.h
@@ -33,11 +33,26 @@ struct mlx5_devx_sq {
 	volatile uint32_t *db_rec; /* The SQ doorbell record. */
 };
 
+/* DevX Receive Queue resource structure. */
+struct mlx5_devx_wq_res {
+	void *umem_obj; /* The RQ umem object. */
+	volatile void *umem_buf;
+};
+
+/* DevX Receive Queue structure. */
+struct mlx5_devx_rmp {
+	struct mlx5_devx_obj *rmp; /* The RMP DevX object. */
+	uint32_t ref_cnt; /* Reference count. */
+	struct mlx5_devx_wq_res wq;
+};
+
 /* DevX Receive Queue structure. */
 struct mlx5_devx_rq {
 	struct mlx5_devx_obj *rq; /* The RQ DevX object. */
-	void *umem_obj; /* The RQ umem object. */
-	volatile void *umem_buf;
+	union {
+		struct mlx5_devx_rmp *rmp; /* Shared RQ RMP object. */
+		struct mlx5_devx_wq_res wq; /* WQ resource of standalone RQ. */
+	};
 	volatile uint32_t *db_rec; /* The RQ doorbell record. */
 };
 
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.c b/drivers/common/mlx5/mlx5_devx_cmds.c
index 56407cc332f..120331e9c87 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.c
+++ b/drivers/common/mlx5/mlx5_devx_cmds.c
@@ -766,6 +766,8 @@ mlx5_devx_cmd_query_hca_attr(void *ctx,
 			MLX5_GET(cmd_hca_cap, hcattr, flow_counter_bulk_alloc);
 	attr->flow_counters_dump = MLX5_GET(cmd_hca_cap, hcattr,
 					    flow_counters_dump);
+	attr->log_max_rmp = MLX5_GET(cmd_hca_cap, hcattr, log_max_rmp);
+	attr->mem_rq_rmp = MLX5_GET(cmd_hca_cap, hcattr, mem_rq_rmp);
 	attr->log_max_rqt_size = MLX5_GET(cmd_hca_cap, hcattr,
 					  log_max_rqt_size);
 	attr->eswitch_manager = MLX5_GET(cmd_hca_cap, hcattr, eswitch_manager);
@@ -1250,6 +1252,56 @@ mlx5_devx_cmd_modify_rq(struct mlx5_devx_obj *rq,
 }
 
 /**
+ * Create RMP using DevX API.
+ *
+ * @param[in] ctx
+ *   Context returned from mlx5 open_device() glue function.
+ * @param [in] rmp_attr
+ *   Pointer to create RMP attributes structure.
+ * @param [in] socket
+ *   CPU socket ID for allocations.
+ *
+ * @return
+ *   The DevX object created, NULL otherwise and rte_errno is set.
+ */
+struct mlx5_devx_obj *
+mlx5_devx_cmd_create_rmp(void *ctx,
+			 struct mlx5_devx_create_rmp_attr *rmp_attr,
+			 int socket)
+{
+	uint32_t in[MLX5_ST_SZ_DW(create_rmp_in)] = {0};
+	uint32_t out[MLX5_ST_SZ_DW(create_rmp_out)] = {0};
+	void *rmp_ctx, *wq_ctx;
+	struct mlx5_devx_wq_attr *wq_attr;
+	struct mlx5_devx_obj *rmp = NULL;
+
+	rmp = mlx5_malloc(MLX5_MEM_ZERO, sizeof(*rmp), 0, socket);
+	if (!rmp) {
+		DRV_LOG(ERR, "Failed to allocate RMP data");
+		rte_errno = ENOMEM;
+		return NULL;
+	}
+	MLX5_SET(create_rmp_in, in, opcode, MLX5_CMD_OP_CREATE_RMP);
+	rmp_ctx = MLX5_ADDR_OF(create_rmp_in, in, ctx);
+	MLX5_SET(rmpc, rmp_ctx, state, rmp_attr->state);
+	MLX5_SET(rmpc, rmp_ctx, basic_cyclic_rcv_wqe,
+		 rmp_attr->basic_cyclic_rcv_wqe);
+	wq_ctx = MLX5_ADDR_OF(rmpc, rmp_ctx, wq);
+	wq_attr = &rmp_attr->wq_attr;
+	devx_cmd_fill_wq_data(wq_ctx, wq_attr);
+	rmp->obj = mlx5_glue->devx_obj_create(ctx, in, sizeof(in), out,
+					      sizeof(out));
+	if (!rmp->obj) {
+		DRV_LOG(ERR, "Failed to create RMP using DevX");
+		rte_errno = errno;
+		mlx5_free(rmp);
+		return NULL;
+	}
+	rmp->id = MLX5_GET(create_rmp_out, out, rmpn);
+	return rmp;
+}
+
+/*
  * Create TIR using DevX API.
  *
  * @param[in] ctx
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.h b/drivers/common/mlx5/mlx5_devx_cmds.h
index e576e30f242..fa8ba89abe6 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.h
+++ b/drivers/common/mlx5/mlx5_devx_cmds.h
@@ -101,6 +101,8 @@ struct mlx5_hca_flow_attr {
 struct mlx5_hca_attr {
 	uint32_t eswitch_manager:1;
 	uint32_t flow_counters_dump:1;
+	uint32_t mem_rq_rmp:1;
+	uint32_t log_max_rmp:5;
 	uint32_t log_max_rqt_size:5;
 	uint32_t parse_graph_flex_node:1;
 	uint8_t flow_counter_bulk_alloc_bitmap;
@@ -245,6 +247,17 @@ struct mlx5_devx_modify_rq_attr {
 	uint32_t lwm:16; /* Contained WQ lwm. */
 };
 
+/* Create RMP attributes structure, used by create RMP operation. */
+struct mlx5_devx_create_rmp_attr {
+	uint32_t rsvd0:8;
+	uint32_t state:4;
+	uint32_t rsvd1:20;
+	uint32_t basic_cyclic_rcv_wqe:1;
+	uint32_t rsvd4:31;
+	uint32_t rsvd8[10];
+	struct mlx5_devx_wq_attr wq_attr;
+};
+
 struct mlx5_rx_hash_field_select {
 	uint32_t l3_prot_type:1;
 	uint32_t l4_prot_type:1;
@@ -520,6 +533,9 @@ __rte_internal
 int mlx5_devx_cmd_modify_rq(struct mlx5_devx_obj *rq,
 			    struct mlx5_devx_modify_rq_attr *rq_attr);
 __rte_internal
+struct mlx5_devx_obj *mlx5_devx_cmd_create_rmp(void *ctx,
+			struct mlx5_devx_create_rmp_attr *rq_attr, int socket);
+__rte_internal
 struct mlx5_devx_obj *mlx5_devx_cmd_create_tir(void *ctx,
 					   struct mlx5_devx_tir_attr *tir_attr);
 __rte_internal
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index 72af3710a8f..df0991ee402 100644
--- a/drivers/common/mlx5/mlx5_prm.h
+++ b/drivers/common/mlx5/mlx5_prm.h
@@ -1061,6 +1061,10 @@ enum {
 	MLX5_CMD_OP_CREATE_RQ = 0x908,
 	MLX5_CMD_OP_MODIFY_RQ = 0x909,
 	MLX5_CMD_OP_QUERY_RQ = 0x90b,
+	MLX5_CMD_OP_CREATE_RMP = 0x90c,
+	MLX5_CMD_OP_MODIFY_RMP = 0x90d,
+	MLX5_CMD_OP_DESTROY_RMP = 0x90e,
+	MLX5_CMD_OP_QUERY_RMP = 0x90f,
 	MLX5_CMD_OP_CREATE_TIS = 0x912,
 	MLX5_CMD_OP_QUERY_TIS = 0x915,
 	MLX5_CMD_OP_CREATE_RQT = 0x916,
@@ -1557,7 +1561,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8 reserved_at_378[0x3];
 	u8 log_max_tis[0x5];
 	u8 basic_cyclic_rcv_wqe[0x1];
-	u8 reserved_at_381[0x2];
+	u8 reserved_at_381[0x1];
+	u8 mem_rq_rmp[0x1];
 	u8 log_max_rmp[0x5];
 	u8 reserved_at_388[0x3];
 	u8 log_max_rqt[0x5];
@@ -2159,6 +2164,84 @@ struct mlx5_ifc_query_rq_in_bits {
 	u8 reserved_at_60[0x20];
 };
 
+enum {
+	MLX5_RMPC_STATE_RDY = 0x1,
+	MLX5_RMPC_STATE_ERR = 0x3,
+};
+
+struct mlx5_ifc_rmpc_bits {
+	u8 reserved_at_0[0x8];
+	u8 state[0x4];
+	u8 reserved_at_c[0x14];
+	u8 basic_cyclic_rcv_wqe[0x1];
+	u8 reserved_at_21[0x1f];
+	u8 reserved_at_40[0x140];
+	struct mlx5_ifc_wq_bits wq;
+};
+
+struct mlx5_ifc_query_rmp_out_bits {
+	u8 status[0x8];
+	u8 reserved_at_8[0x18];
+	u8 syndrome[0x20];
+	u8 reserved_at_40[0xc0];
+	struct mlx5_ifc_rmpc_bits rmp_context;
+};
+
+struct mlx5_ifc_query_rmp_in_bits {
+	u8 opcode[0x10];
+	u8 reserved_at_10[0x10];
+	u8 reserved_at_20[0x10];
+	u8 op_mod[0x10];
+	u8 reserved_at_40[0x8];
+	u8 rmpn[0x18];
+	u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_modify_rmp_out_bits {
+	u8 status[0x8];
+	u8 reserved_at_8[0x18];
+	u8 syndrome[0x20];
+	u8 reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_rmp_bitmask_bits {
+	u8 reserved_at_0[0x20];
+	u8 reserved_at_20[0x1f];
+	u8 lwm[0x1];
+};
+
+struct mlx5_ifc_modify_rmp_in_bits {
+	u8 opcode[0x10];
+	u8 uid[0x10];
+	u8 reserved_at_20[0x10];
+	u8 op_mod[0x10];
+	u8 rmp_state[0x4];
+	u8 reserved_at_44[0x4];
+	u8 rmpn[0x18];
+	u8 reserved_at_60[0x20];
+	struct mlx5_ifc_rmp_bitmask_bits bitmask;
+	u8 reserved_at_c0[0x40];
+	struct mlx5_ifc_rmpc_bits ctx;
+};
+
+struct mlx5_ifc_create_rmp_out_bits {
+	u8 status[0x8];
+	u8 reserved_at_8[0x18];
+	u8 syndrome[0x20];
+	u8 reserved_at_40[0x8];
+	u8 rmpn[0x18];
+	u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_create_rmp_in_bits {
+	u8 opcode[0x10];
+	u8 uid[0x10];
+	u8 reserved_at_20[0x10];
+	u8 op_mod[0x10];
+	u8 reserved_at_40[0xc0];
+	struct mlx5_ifc_rmpc_bits ctx;
+};
+
 struct mlx5_ifc_create_tis_out_bits {
 	u8 status[0x8];
 	u8 reserved_at_8[0x18];
diff --git a/drivers/common/mlx5/version.map b/drivers/common/mlx5/version.map
index e5cb6b70604..40975078cc4 100644
--- a/drivers/common/mlx5/version.map
+++ b/drivers/common/mlx5/version.map
@@ -31,6 +31,7 @@ INTERNAL {
 	mlx5_devx_cmd_create_geneve_tlv_option;
 	mlx5_devx_cmd_create_import_kek_obj;
 	mlx5_devx_cmd_create_qp;
+	mlx5_devx_cmd_create_rmp;
 	mlx5_devx_cmd_create_rq;
 	mlx5_devx_cmd_create_rqt;
 	mlx5_devx_cmd_create_sq;
diff --git a/drivers/net/mlx5/mlx5_devx.c b/drivers/net/mlx5/mlx5_devx.c
index 447d6bafb93..4d479c19e6c 100644
--- a/drivers/net/mlx5/mlx5_devx.c
+++ b/drivers/net/mlx5/mlx5_devx.c
@@ -514,7 +514,7 @@ mlx5_rxq_devx_obj_new(struct rte_eth_dev *dev, uint16_t idx)
 	ret = mlx5_devx_modify_rq(tmpl, MLX5_RXQ_MOD_RST2RDY);
 	if (ret)
 		goto error;
-	rxq_data->wqes = (void *)(uintptr_t)tmpl->rq_obj.umem_buf;
+	rxq_data->wqes = (void *)(uintptr_t)tmpl->rq_obj.wq.umem_buf;
 	rxq_data->rq_db = (uint32_t *)(uintptr_t)tmpl->rq_obj.db_rec;
 	rxq_data->cq_arm_sn = 0;
 	rxq_data->cq_ci = 0;
-- 
2.33.0