From: Lance Richardson <lance.richardson@broadcom.com>
Date: Sun, 2 Jun 2019 17:42:44 +0000 (-0400)
Subject: net/bnxt: support thor controller
X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=f8168ca0e690c31578d32bbf6ff7394b94459c4d;p=dpdk.git

net/bnxt: support thor controller

This commit adds support to the bnxt PMD for devices
based on the BCM57508 "thor" Ethernet controller.

Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Lance Richardson <lance.richardson@broadcom.com>
---

diff --git a/doc/guides/nics/bnxt.rst b/doc/guides/nics/bnxt.rst
index 697b97e602..d88e021160 100644
--- a/doc/guides/nics/bnxt.rst
+++ b/doc/guides/nics/bnxt.rst
@@ -7,10 +7,10 @@ BNXT Poll Mode Driver
 The bnxt poll mode library (**librte_pmd_bnxt**) implements support for:
 
   * **Broadcom NetXtreme-C®/NetXtreme-E®/NetXtreme-S®
-    BCM5730X / BCM574XX / BCM58000 family of Ethernet Network Controllers**
+    BCM5730X / BCM574XX / BCM58000 / BCM575XX family of Ethernet Network Controllers**
 
-    These adapters support Standards compliant 10/25/50/100Gbps 30MPPS
-    full-duplex throughput.
+    Adapters based on this family of controllers support standards-compliant Ethernet
+    operation with link speeds of 10/25/50/100/200Gbps.
 
     Information about the NetXtreme family of adapters can be found in the
     `NetXtreme® Brand section
diff --git a/doc/guides/rel_notes/release_19_08.rst b/doc/guides/rel_notes/release_19_08.rst
index 7b36d64e26..6d518b31b1 100644
--- a/doc/guides/rel_notes/release_19_08.rst
+++ b/doc/guides/rel_notes/release_19_08.rst
@@ -62,6 +62,12 @@ New Features
   * Added support for SSE vector mode
   * Updated HWRM API to version 1.10.0.74
 
+* **Added support for Broadcom NetXtreme-E BCM57500 Ethernet controllers.**
+
+  Added support to the bnxt PMD for the BCM57500 (a.k.a. "Thor") family
+  of Ethernet controllers. These controllers support link speeds up to
+  200Gbps, 50G PAM-4, and PCIe 4.0.
+
 * **Added memif PMD.**
 
   Added the new Shared Memory Packet Interface (``memif``) PMD.
diff --git a/drivers/net/bnxt/bnxt.h b/drivers/net/bnxt/bnxt.h
index 9bb8d825da..641790fef2 100644
--- a/drivers/net/bnxt/bnxt.h
+++ b/drivers/net/bnxt/bnxt.h
@@ -239,6 +239,93 @@ struct bnxt_coal {
 	uint16_t			cmpl_aggr_dma_tmr_during_int;
 };
 
+/* 64-bit doorbell */
+#define DBR_XID_SFT				32
+#define DBR_PATH_L2				(0x1ULL << 56)
+#define DBR_TYPE_SQ				(0x0ULL << 60)
+#define DBR_TYPE_SRQ				(0x2ULL << 60)
+#define DBR_TYPE_CQ				(0x4ULL << 60)
+#define DBR_TYPE_NQ				(0xaULL << 60)
+
+#define BNXT_RSS_TBL_SIZE_THOR		512
+#define BNXT_RSS_ENTRIES_PER_CTX_THOR	64
+#define BNXT_MAX_RSS_CTXTS_THOR \
+	(BNXT_RSS_TBL_SIZE_THOR / BNXT_RSS_ENTRIES_PER_CTX_THOR)
+
+#define BNXT_MAX_TC    8
+#define BNXT_MAX_QUEUE 8
+#define BNXT_MAX_TC_Q  (BNXT_MAX_TC + 1)
+#define BNXT_MAX_Q     (bp->max_q + 1)
+#define BNXT_PAGE_SHFT 12
+#define BNXT_PAGE_SIZE (1 << BNXT_PAGE_SHFT)
+#define MAX_CTX_PAGES  (BNXT_PAGE_SIZE / 8)
+
+#define PTU_PTE_VALID             0x1UL
+#define PTU_PTE_LAST              0x2UL
+#define PTU_PTE_NEXT_TO_LAST      0x4UL
+
+struct bnxt_ring_mem_info {
+	int				nr_pages;
+	int				page_size;
+	uint32_t			flags;
+#define BNXT_RMEM_VALID_PTE_FLAG	1
+#define BNXT_RMEM_RING_PTE_FLAG		2
+
+	void				**pg_arr;
+	rte_iova_t			*dma_arr;
+	const struct rte_memzone	*mz;
+
+	uint64_t			*pg_tbl;
+	rte_iova_t			pg_tbl_map;
+	const struct rte_memzone	*pg_tbl_mz;
+
+	int				vmem_size;
+	void				**vmem;
+};
+
+struct bnxt_ctx_pg_info {
+	uint32_t	entries;
+	void		*ctx_pg_arr[MAX_CTX_PAGES];
+	rte_iova_t	ctx_dma_arr[MAX_CTX_PAGES];
+	struct bnxt_ring_mem_info ring_mem;
+};
+
+struct bnxt_ctx_mem_info {
+	uint32_t        qp_max_entries;
+	uint16_t        qp_min_qp1_entries;
+	uint16_t        qp_max_l2_entries;
+	uint16_t        qp_entry_size;
+	uint16_t        srq_max_l2_entries;
+	uint32_t        srq_max_entries;
+	uint16_t        srq_entry_size;
+	uint16_t        cq_max_l2_entries;
+	uint32_t        cq_max_entries;
+	uint16_t        cq_entry_size;
+	uint16_t        vnic_max_vnic_entries;
+	uint16_t        vnic_max_ring_table_entries;
+	uint16_t        vnic_entry_size;
+	uint32_t        stat_max_entries;
+	uint16_t        stat_entry_size;
+	uint16_t        tqm_entry_size;
+	uint32_t        tqm_min_entries_per_ring;
+	uint32_t        tqm_max_entries_per_ring;
+	uint32_t        mrav_max_entries;
+	uint16_t        mrav_entry_size;
+	uint16_t        tim_entry_size;
+	uint32_t        tim_max_entries;
+	uint8_t         tqm_entries_multiple;
+
+	uint32_t        flags;
+#define BNXT_CTX_FLAG_INITED    0x01
+
+	struct bnxt_ctx_pg_info qp_mem;
+	struct bnxt_ctx_pg_info srq_mem;
+	struct bnxt_ctx_pg_info cq_mem;
+	struct bnxt_ctx_pg_info vnic_mem;
+	struct bnxt_ctx_pg_info stat_mem;
+	struct bnxt_ctx_pg_info *tqm_mem[BNXT_MAX_TC_Q];
+};
+
 #define BNXT_HWRM_SHORT_REQ_LEN		sizeof(struct hwrm_short_input)
 struct bnxt {
 	void				*bar0;
@@ -262,6 +349,7 @@ struct bnxt {
 #define BNXT_FLAG_KONG_MB_EN	(1 << 10)
 #define BNXT_FLAG_TRUSTED_VF_EN	(1 << 11)
 #define BNXT_FLAG_DFLT_VNIC_SET	(1 << 12)
+#define BNXT_FLAG_THOR_CHIP	(1 << 13)
 #define BNXT_FLAG_NEW_RM	(1 << 30)
 #define BNXT_FLAG_INIT_DONE	(1U << 31)
 #define BNXT_PF(bp)		(!((bp)->flags & BNXT_FLAG_VF))
@@ -272,6 +360,9 @@ struct bnxt {
 #define BNXT_USE_CHIMP_MB	0 //For non-CFA commands, everything uses Chimp.
 #define BNXT_USE_KONG(bp)	((bp)->flags & BNXT_FLAG_KONG_MB_EN)
 #define BNXT_VF_IS_TRUSTED(bp)	((bp)->flags & BNXT_FLAG_TRUSTED_VF_EN)
+#define BNXT_CHIP_THOR(bp)	((bp)->flags & BNXT_FLAG_THOR_CHIP)
+#define BNXT_HAS_NQ(bp)		BNXT_CHIP_THOR(bp)
+#define BNXT_HAS_RING_GRPS(bp)	(!BNXT_CHIP_THOR(bp))
 
 	unsigned int		rx_nr_rings;
 	unsigned int		rx_cp_nr_rings;
@@ -325,6 +416,9 @@ struct bnxt {
 	struct bnxt_link_info	link_info;
 	struct bnxt_cos_queue_info	cos_queue[BNXT_COS_QUEUE_COUNT];
 	uint8_t			tx_cosq_id;
+	uint8_t                 max_tc;
+	uint8_t                 max_lltc;
+	uint8_t                 max_q;
 
 	uint16_t		fw_fid;
 	uint8_t			dflt_mac_addr[RTE_ETHER_ADDR_LEN];
@@ -332,11 +426,12 @@ struct bnxt {
 	uint16_t		max_cp_rings;
 	uint16_t		max_tx_rings;
 	uint16_t		max_rx_rings;
+	uint16_t		max_nq_rings;
 	uint16_t		max_l2_ctx;
 	uint16_t		max_vnics;
 	uint16_t		max_stat_ctx;
 	uint16_t		vlan;
-	struct bnxt_pf_info		pf;
+	struct bnxt_pf_info	pf;
 	uint8_t			port_partition_type;
 	uint8_t			dev_stopped;
 	uint8_t			vxlan_port_cnt;
@@ -352,6 +447,7 @@ struct bnxt {
 	uint8_t			num_leds;
 	struct bnxt_ptp_cfg     *ptp_cfg;
 	uint16_t		vf_resv_strategy;
+	struct bnxt_ctx_mem_info        *ctx;
 };
 
 int bnxt_link_update_op(struct rte_eth_dev *eth_dev, int wait_to_complete);
diff --git a/drivers/net/bnxt/bnxt_cpr.h b/drivers/net/bnxt/bnxt_cpr.h
index 77a22d2418..8c6a34b611 100644
--- a/drivers/net/bnxt/bnxt_cpr.h
+++ b/drivers/net/bnxt/bnxt_cpr.h
@@ -19,6 +19,10 @@ struct bnxt_db_info;
 	(!!(rte_le_to_cpu_32(((struct cmpl_base *)(cmp))->info3_v) &	\
 	    CMPL_BASE_V) == !(v))
 
+#define NQ_CMP_VALID(nqcmp, raw_cons, ring)		\
+	(!!((nqcmp)->v & rte_cpu_to_le_32(NQ_CN_V)) ==	\
+	 !((raw_cons) & ((ring)->ring_size)))
+
 #define CMP_TYPE(cmp)						\
 	(((struct cmpl_base *)cmp)->type & CMPL_BASE_TYPE_MASK)
 
@@ -70,8 +74,12 @@ struct bnxt_db_info;
 		    ((cpr)->cp_db.doorbell))
 
 struct bnxt_db_info {
-	void		*doorbell;
-	uint32_t	db_key32;
+	void                    *doorbell;
+	union {
+		uint64_t        db_key64;
+		uint32_t        db_key32;
+	};
+	bool                    db_64;
 };
 
 struct bnxt_ring;
diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers/net/bnxt/bnxt_ethdev.c
index 72679bed96..c0a84bb910 100644
--- a/drivers/net/bnxt/bnxt_ethdev.c
+++ b/drivers/net/bnxt/bnxt_ethdev.c
@@ -71,6 +71,10 @@ int bnxt_logtype_driver;
 #define BROADCOM_DEV_ID_57407_MF 0x16ea
 #define BROADCOM_DEV_ID_57414_MF 0x16ec
 #define BROADCOM_DEV_ID_57416_MF 0x16ee
+#define BROADCOM_DEV_ID_57508 0x1750
+#define BROADCOM_DEV_ID_57504 0x1751
+#define BROADCOM_DEV_ID_57502 0x1752
+#define BROADCOM_DEV_ID_57500_VF 0x1807
 #define BROADCOM_DEV_ID_58802 0xd802
 #define BROADCOM_DEV_ID_58804 0xd804
 #define BROADCOM_DEV_ID_58808 0x16f0
@@ -119,6 +123,10 @@ static const struct rte_pci_id bnxt_pci_id_map[] = {
 	{ RTE_PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, BROADCOM_DEV_ID_58804) },
 	{ RTE_PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, BROADCOM_DEV_ID_58808) },
 	{ RTE_PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, BROADCOM_DEV_ID_58802_VF) },
+	{ RTE_PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, BROADCOM_DEV_ID_57508) },
+	{ RTE_PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, BROADCOM_DEV_ID_57504) },
+	{ RTE_PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, BROADCOM_DEV_ID_57502) },
+	{ RTE_PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, BROADCOM_DEV_ID_57500_VF) },
 	{ .vendor_id = 0, /* sentinel */ },
 };
 
@@ -224,6 +232,12 @@ static int bnxt_init_chip(struct bnxt *bp)
 		bp->flags &= ~BNXT_FLAG_JUMBO;
 	}
 
+	/* THOR does not support ring groups.
+	 * But we will use the array to save RSS context IDs.
+	 */
+	if (BNXT_CHIP_THOR(bp))
+		bp->max_ring_grps = BNXT_MAX_RSS_CTXTS_THOR;
+
 	rc = bnxt_alloc_all_hwrm_stat_ctxs(bp);
 	if (rc) {
 		PMD_DRV_LOG(ERR, "HWRM stat ctx alloc failure rc: %x\n", rc);
@@ -317,7 +331,7 @@ static int bnxt_init_chip(struct bnxt *bp)
 				    "rxq[%d]->vnic=%p vnic->fw_grp_ids=%p\n",
 				    j, rxq->vnic, rxq->vnic->fw_grp_ids);
 
-			if (rxq->rx_deferred_start)
+			if (BNXT_HAS_RING_GRPS(bp) && rxq->rx_deferred_start)
 				rxq->vnic->fw_grp_ids[j] = INVALID_HW_RING_ID;
 		}
 
@@ -573,22 +587,16 @@ static int bnxt_dev_configure_op(struct rte_eth_dev *eth_dev)
 	    eth_dev->data->nb_rx_queues + eth_dev->data->nb_tx_queues >
 	    bp->max_cp_rings ||
 	    eth_dev->data->nb_rx_queues + eth_dev->data->nb_tx_queues >
-	    bp->max_stat_ctx ||
-	    (uint32_t)(eth_dev->data->nb_rx_queues) > bp->max_ring_grps ||
-	    (!(eth_dev->data->dev_conf.rxmode.mq_mode & ETH_MQ_RX_RSS) &&
-	     bp->max_vnics < eth_dev->data->nb_rx_queues)) {
-		PMD_DRV_LOG(ERR,
-			"Insufficient resources to support requested config\n");
-		PMD_DRV_LOG(ERR,
-			"Num Queues Requested: Tx %d, Rx %d\n",
-			eth_dev->data->nb_tx_queues,
-			eth_dev->data->nb_rx_queues);
-		PMD_DRV_LOG(ERR,
-			"MAX: TxQ %d, RxQ %d, CQ %d Stat %d, Grp %d, Vnic %d\n",
-			bp->max_tx_rings, bp->max_rx_rings, bp->max_cp_rings,
-			bp->max_stat_ctx, bp->max_ring_grps, bp->max_vnics);
-		return -ENOSPC;
-	}
+	    bp->max_stat_ctx)
+		goto resource_error;
+
+	if (BNXT_HAS_RING_GRPS(bp) &&
+	    (uint32_t)(eth_dev->data->nb_rx_queues) > bp->max_ring_grps)
+		goto resource_error;
+
+	if (!(eth_dev->data->dev_conf.rxmode.mq_mode & ETH_MQ_RX_RSS) &&
+	    bp->max_vnics < eth_dev->data->nb_rx_queues)
+		goto resource_error;
 
 	bp->rx_cp_nr_rings = bp->rx_nr_rings;
 	bp->tx_cp_nr_rings = bp->tx_nr_rings;
@@ -601,6 +609,19 @@ static int bnxt_dev_configure_op(struct rte_eth_dev *eth_dev)
 		bnxt_mtu_set_op(eth_dev, eth_dev->data->mtu);
 	}
 	return 0;
+
+resource_error:
+	PMD_DRV_LOG(ERR,
+		    "Insufficient resources to support requested config\n");
+	PMD_DRV_LOG(ERR,
+		    "Num Queues Requested: Tx %d, Rx %d\n",
+		    eth_dev->data->nb_tx_queues,
+		    eth_dev->data->nb_rx_queues);
+	PMD_DRV_LOG(ERR,
+		    "MAX: TxQ %d, RxQ %d, CQ %d Stat %d, Grp %d, Vnic %d\n",
+		    bp->max_tx_rings, bp->max_rx_rings, bp->max_cp_rings,
+		    bp->max_stat_ctx, bp->max_ring_grps, bp->max_vnics);
+	return -ENOSPC;
 }
 
 static void bnxt_print_link_info(struct rte_eth_dev *eth_dev)
@@ -3265,7 +3286,8 @@ static bool bnxt_vf_pciid(uint16_t id)
 	    id == BROADCOM_DEV_ID_57414_VF ||
 	    id == BROADCOM_DEV_ID_STRATUS_NIC_VF1 ||
 	    id == BROADCOM_DEV_ID_STRATUS_NIC_VF2 ||
-	    id == BROADCOM_DEV_ID_58802_VF)
+	    id == BROADCOM_DEV_ID_58802_VF ||
+	    id == BROADCOM_DEV_ID_57500_VF)
 		return true;
 	return false;
 }
@@ -3327,6 +3349,245 @@ init_err_disable:
 	return rc;
 }
 
+static int bnxt_alloc_ctx_mem_blk(__rte_unused struct bnxt *bp,
+				  struct bnxt_ctx_pg_info *ctx_pg,
+				  uint32_t mem_size,
+				  const char *suffix,
+				  uint16_t idx)
+{
+	struct bnxt_ring_mem_info *rmem = &ctx_pg->ring_mem;
+	const struct rte_memzone *mz = NULL;
+	char mz_name[RTE_MEMZONE_NAMESIZE];
+	rte_iova_t mz_phys_addr;
+	uint64_t valid_bits = 0;
+	uint32_t sz;
+	int i;
+
+	if (!mem_size)
+		return 0;
+
+	rmem->nr_pages = RTE_ALIGN_MUL_CEIL(mem_size, BNXT_PAGE_SIZE) /
+			 BNXT_PAGE_SIZE;
+	rmem->page_size = BNXT_PAGE_SIZE;
+	rmem->pg_arr = ctx_pg->ctx_pg_arr;
+	rmem->dma_arr = ctx_pg->ctx_dma_arr;
+	rmem->flags = BNXT_RMEM_VALID_PTE_FLAG;
+
+	valid_bits = PTU_PTE_VALID;
+
+	if (rmem->nr_pages > 1) {
+		snprintf(mz_name, RTE_MEMZONE_NAMESIZE, "bnxt_ctx_pg_tbl%s_%x",
+			 suffix, idx);
+		mz_name[RTE_MEMZONE_NAMESIZE - 1] = 0;
+		mz = rte_memzone_lookup(mz_name);
+		if (!mz) {
+			mz = rte_memzone_reserve_aligned(mz_name,
+						rmem->nr_pages * 8,
+						SOCKET_ID_ANY,
+						RTE_MEMZONE_2MB |
+						RTE_MEMZONE_SIZE_HINT_ONLY |
+						RTE_MEMZONE_IOVA_CONTIG,
+						BNXT_PAGE_SIZE);
+			if (mz == NULL)
+				return -ENOMEM;
+		}
+
+		memset(mz->addr, 0, mz->len);
+		mz_phys_addr = mz->iova;
+		if ((unsigned long)mz->addr == mz_phys_addr) {
+			PMD_DRV_LOG(WARNING,
+				"Memzone physical address same as virtual.\n");
+			PMD_DRV_LOG(WARNING,
+				    "Using rte_mem_virt2iova()\n");
+			mz_phys_addr = rte_mem_virt2iova(mz->addr);
+			if (mz_phys_addr == 0) {
+				PMD_DRV_LOG(ERR,
+					"unable to map addr to phys memory\n");
+				return -ENOMEM;
+			}
+		}
+		rte_mem_lock_page(((char *)mz->addr));
+
+		rmem->pg_tbl = mz->addr;
+		rmem->pg_tbl_map = mz_phys_addr;
+		rmem->pg_tbl_mz = mz;
+	}
+
+	snprintf(mz_name, RTE_MEMZONE_NAMESIZE, "bnxt_ctx_%s_%x", suffix, idx);
+	mz = rte_memzone_lookup(mz_name);
+	if (!mz) {
+		mz = rte_memzone_reserve_aligned(mz_name,
+						 mem_size,
+						 SOCKET_ID_ANY,
+						 RTE_MEMZONE_1GB |
+						 RTE_MEMZONE_SIZE_HINT_ONLY |
+						 RTE_MEMZONE_IOVA_CONTIG,
+						 BNXT_PAGE_SIZE);
+		if (mz == NULL)
+			return -ENOMEM;
+	}
+
+	memset(mz->addr, 0, mz->len);
+	mz_phys_addr = mz->iova;
+	if ((unsigned long)mz->addr == mz_phys_addr) {
+		PMD_DRV_LOG(WARNING,
+			    "Memzone physical address same as virtual.\n");
+		PMD_DRV_LOG(WARNING,
+			    "Using rte_mem_virt2iova()\n");
+		for (sz = 0; sz < mem_size; sz += BNXT_PAGE_SIZE)
+			rte_mem_lock_page(((char *)mz->addr) + sz);
+		mz_phys_addr = rte_mem_virt2iova(mz->addr);
+		if (mz_phys_addr == RTE_BAD_IOVA) {
+			PMD_DRV_LOG(ERR,
+				    "unable to map addr to phys memory\n");
+			return -ENOMEM;
+		}
+	}
+
+	for (sz = 0, i = 0; sz < mem_size; sz += BNXT_PAGE_SIZE, i++) {
+		rte_mem_lock_page(((char *)mz->addr) + sz);
+		rmem->pg_arr[i] = ((char *)mz->addr) + sz;
+		rmem->dma_arr[i] = mz_phys_addr + sz;
+
+		if (rmem->nr_pages > 1) {
+			if (i == rmem->nr_pages - 2 &&
+			    (rmem->flags & BNXT_RMEM_RING_PTE_FLAG))
+				valid_bits |= PTU_PTE_NEXT_TO_LAST;
+			else if (i == rmem->nr_pages - 1 &&
+				 (rmem->flags & BNXT_RMEM_RING_PTE_FLAG))
+				valid_bits |= PTU_PTE_LAST;
+
+			rmem->pg_tbl[i] = rte_cpu_to_le_64(rmem->dma_arr[i] |
+							   valid_bits);
+		}
+	}
+
+	rmem->mz = mz;
+	if (rmem->vmem_size)
+		rmem->vmem = (void **)mz->addr;
+	rmem->dma_arr[0] = mz_phys_addr;
+	return 0;
+}
+
+static void bnxt_free_ctx_mem(struct bnxt *bp)
+{
+	int i;
+
+	if (!bp->ctx || !(bp->ctx->flags & BNXT_CTX_FLAG_INITED))
+		return;
+
+	bp->ctx->flags &= ~BNXT_CTX_FLAG_INITED;
+	rte_memzone_free(bp->ctx->qp_mem.ring_mem.mz);
+	rte_memzone_free(bp->ctx->srq_mem.ring_mem.mz);
+	rte_memzone_free(bp->ctx->cq_mem.ring_mem.mz);
+	rte_memzone_free(bp->ctx->vnic_mem.ring_mem.mz);
+	rte_memzone_free(bp->ctx->stat_mem.ring_mem.mz);
+	rte_memzone_free(bp->ctx->qp_mem.ring_mem.pg_tbl_mz);
+	rte_memzone_free(bp->ctx->srq_mem.ring_mem.pg_tbl_mz);
+	rte_memzone_free(bp->ctx->cq_mem.ring_mem.pg_tbl_mz);
+	rte_memzone_free(bp->ctx->vnic_mem.ring_mem.pg_tbl_mz);
+	rte_memzone_free(bp->ctx->stat_mem.ring_mem.pg_tbl_mz);
+
+	for (i = 0; i < BNXT_MAX_Q; i++) {
+		if (bp->ctx->tqm_mem[i])
+			rte_memzone_free(bp->ctx->tqm_mem[i]->ring_mem.mz);
+	}
+
+	rte_free(bp->ctx);
+	bp->ctx = NULL;
+}
+
+#define roundup(x, y)   ((((x) + ((y) - 1)) / (y)) * (y))
+
+#define min_t(type, x, y) ({                    \
+	type __min1 = (x);                      \
+	type __min2 = (y);                      \
+	__min1 < __min2 ? __min1 : __min2; })
+
+#define max_t(type, x, y) ({                    \
+	type __max1 = (x);                      \
+	type __max2 = (y);                      \
+	__max1 > __max2 ? __max1 : __max2; })
+
+#define clamp_t(type, _x, min, max)     min_t(type, max_t(type, _x, min), max)
+
+int bnxt_alloc_ctx_mem(struct bnxt *bp)
+{
+	struct bnxt_ctx_pg_info *ctx_pg;
+	struct bnxt_ctx_mem_info *ctx;
+	uint32_t mem_size, ena, entries;
+	int i, rc;
+
+	rc = bnxt_hwrm_func_backing_store_qcaps(bp);
+	if (rc) {
+		PMD_DRV_LOG(ERR, "Query context mem capability failed\n");
+		return rc;
+	}
+	ctx = bp->ctx;
+	if (!ctx || (ctx->flags & BNXT_CTX_FLAG_INITED))
+		return 0;
+
+	ctx_pg = &ctx->qp_mem;
+	ctx_pg->entries = ctx->qp_min_qp1_entries + ctx->qp_max_l2_entries;
+	mem_size = ctx->qp_entry_size * ctx_pg->entries;
+	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size, "qp_mem", 0);
+	if (rc)
+		return rc;
+
+	ctx_pg = &ctx->srq_mem;
+	ctx_pg->entries = ctx->srq_max_l2_entries;
+	mem_size = ctx->srq_entry_size * ctx_pg->entries;
+	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size, "srq_mem", 0);
+	if (rc)
+		return rc;
+
+	ctx_pg = &ctx->cq_mem;
+	ctx_pg->entries = ctx->cq_max_l2_entries;
+	mem_size = ctx->cq_entry_size * ctx_pg->entries;
+	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size, "cq_mem", 0);
+	if (rc)
+		return rc;
+
+	ctx_pg = &ctx->vnic_mem;
+	ctx_pg->entries = ctx->vnic_max_vnic_entries +
+		ctx->vnic_max_ring_table_entries;
+	mem_size = ctx->vnic_entry_size * ctx_pg->entries;
+	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size, "vnic_mem", 0);
+	if (rc)
+		return rc;
+
+	ctx_pg = &ctx->stat_mem;
+	ctx_pg->entries = ctx->stat_max_entries;
+	mem_size = ctx->stat_entry_size * ctx_pg->entries;
+	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size, "stat_mem", 0);
+	if (rc)
+		return rc;
+
+	entries = ctx->qp_max_l2_entries;
+	entries = roundup(entries, ctx->tqm_entries_multiple);
+	entries = clamp_t(uint32_t, entries, ctx->tqm_min_entries_per_ring,
+			  ctx->tqm_max_entries_per_ring);
+	for (i = 0, ena = 0; i < BNXT_MAX_Q; i++) {
+		ctx_pg = ctx->tqm_mem[i];
+		/* use min tqm entries for now. */
+		ctx_pg->entries = entries;
+		mem_size = ctx->tqm_entry_size * ctx_pg->entries;
+		rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size, "tqm_mem", i);
+		if (rc)
+			return rc;
+		ena |= HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_TQM_SP << i;
+	}
+
+	ena |= FUNC_BACKING_STORE_CFG_INPUT_DFLT_ENABLES;
+	rc = bnxt_hwrm_func_backing_store_cfg(bp, ena);
+	if (rc)
+		PMD_DRV_LOG(ERR,
+			    "Failed to configure context mem: rc = %d\n", rc);
+	else
+		ctx->flags |= BNXT_CTX_FLAG_INITED;
+
+	return 0;
+}
 
 #define ALLOW_FUNC(x)	\
 	{ \
@@ -3361,6 +3622,12 @@ bnxt_dev_init(struct rte_eth_dev *eth_dev)
 	if (bnxt_vf_pciid(pci_dev->id.device_id))
 		bp->flags |= BNXT_FLAG_VF;
 
+	if (pci_dev->id.device_id == BROADCOM_DEV_ID_57508 ||
+	    pci_dev->id.device_id == BROADCOM_DEV_ID_57504 ||
+	    pci_dev->id.device_id == BROADCOM_DEV_ID_57502 ||
+	    pci_dev->id.device_id == BROADCOM_DEV_ID_57500_VF)
+		bp->flags |= BNXT_FLAG_THOR_CHIP;
+
 	rc = bnxt_init_board(eth_dev);
 	if (rc) {
 		PMD_DRV_LOG(ERR,
@@ -3497,13 +3764,6 @@ skip_ext_stats:
 		PMD_DRV_LOG(ERR, "hwrm queue qportcfg failed\n");
 		goto error_free;
 	}
-
-	rc = bnxt_hwrm_func_qcfg(bp);
-	if (rc) {
-		PMD_DRV_LOG(ERR, "hwrm func qcfg failed\n");
-		goto error_free;
-	}
-
 	/* Get the MAX capabilities for this function */
 	rc = bnxt_hwrm_func_qcaps(bp);
 	if (rc) {
@@ -3538,7 +3798,12 @@ skip_ext_stats:
 	memcpy(bp->mac_addr, bp->dflt_mac_addr, sizeof(bp->mac_addr));
 	memcpy(&eth_dev->data->mac_addrs[0], bp->mac_addr, RTE_ETHER_ADDR_LEN);
 
-	if (bp->max_ring_grps < bp->rx_cp_nr_rings) {
+	/* THOR does not support ring groups.
+	 * But we will use the array to save RSS context IDs.
+	 */
+	if (BNXT_CHIP_THOR(bp)) {
+		bp->max_ring_grps = BNXT_MAX_RSS_CTXTS_THOR;
+	} else if (bp->max_ring_grps < bp->rx_cp_nr_rings) {
 		/* 1 ring is for default completion ring */
 		PMD_DRV_LOG(ERR, "Insufficient resource: Ring Group\n");
 		rc = -ENOSPC;
@@ -3592,6 +3857,11 @@ skip_ext_stats:
 		pci_dev->mem_resource[0].phys_addr,
 		pci_dev->mem_resource[0].addr);
 
+	rc = bnxt_hwrm_func_qcfg(bp);
+	if (rc) {
+		PMD_DRV_LOG(ERR, "hwrm func qcfg failed\n");
+		goto error_free;
+	}
 
 	if (BNXT_PF(bp)) {
 		//if (bp->pf.active_vfs) {
@@ -3677,6 +3947,7 @@ bnxt_dev_uninit(struct rte_eth_dev *eth_dev)
 		bnxt_dev_close_op(eth_dev);
 	if (bp->pf.vf_info)
 		rte_free(bp->pf.vf_info);
+	bnxt_free_ctx_mem(bp);
 	eth_dev->dev_ops = NULL;
 	eth_dev->rx_pkt_burst = NULL;
 	eth_dev->tx_pkt_burst = NULL;
diff --git a/drivers/net/bnxt/bnxt_hwrm.c b/drivers/net/bnxt/bnxt_hwrm.c
index 45d37f176a..29f270195f 100644
--- a/drivers/net/bnxt/bnxt_hwrm.c
+++ b/drivers/net/bnxt/bnxt_hwrm.c
@@ -29,6 +29,7 @@
 #define HWRM_CMD_TIMEOUT		6000000
 #define HWRM_SPEC_CODE_1_8_3		0x10803
 #define HWRM_VERSION_1_9_1		0x10901
+#define HWRM_VERSION_1_9_2		0x10903
 
 struct bnxt_plcmodes_cfg {
 	uint32_t	flags;
@@ -62,6 +63,18 @@ static int page_roundup(size_t size)
 	return 1 << page_getenum(size);
 }
 
+static void bnxt_hwrm_set_pg_attr(struct bnxt_ring_mem_info *rmem,
+				  uint8_t *pg_attr,
+				  uint64_t *pg_dir)
+{
+	if (rmem->nr_pages > 1) {
+		*pg_attr = 1;
+		*pg_dir = rte_cpu_to_le_64(rmem->pg_tbl_map);
+	} else {
+		*pg_dir = rte_cpu_to_le_64(rmem->dma_arr[0]);
+	}
+}
+
 /*
  * HWRM Functions (sent to HWRM)
  * These are named bnxt_hwrm_*() and return -1 if bnxt_hwrm_send_message()
@@ -608,6 +621,10 @@ int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 
 	rc = __bnxt_hwrm_func_qcaps(bp);
 	if (!rc && bp->hwrm_spec_code >= HWRM_SPEC_CODE_1_8_3) {
+		rc = bnxt_alloc_ctx_mem(bp);
+		if (rc)
+			return rc;
+
 		rc = bnxt_hwrm_func_resc_qcaps(bp);
 		if (!rc)
 			bp->flags |= BNXT_FLAG_NEW_RM;
@@ -703,13 +720,16 @@ int bnxt_hwrm_func_reserve_vf_resc(struct bnxt *bp, bool test)
 
 	HWRM_PREP(req, FUNC_VF_CFG, BNXT_USE_CHIMP_MB);
 
-	req.enables = rte_cpu_to_le_32
-			(HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_RX_RINGS  |
-			HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_TX_RINGS   |
-			HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_STAT_CTXS  |
-			HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_CMPL_RINGS |
-			HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_HW_RING_GRPS |
-			HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_VNICS);
+	enables = HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_RX_RINGS  |
+		  HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_TX_RINGS   |
+		  HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_STAT_CTXS  |
+		  HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_CMPL_RINGS |
+		  HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_VNICS;
+
+	if (BNXT_HAS_RING_GRPS(bp)) {
+		enables |= HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_HW_RING_GRPS;
+		req.num_hw_ring_grps = rte_cpu_to_le_16(bp->rx_nr_rings);
+	}
 
 	req.num_tx_rings = rte_cpu_to_le_16(bp->tx_nr_rings);
 	req.num_rx_rings = rte_cpu_to_le_16(bp->rx_nr_rings *
@@ -717,14 +737,12 @@ int bnxt_hwrm_func_reserve_vf_resc(struct bnxt *bp, bool test)
 	req.num_stat_ctxs = rte_cpu_to_le_16(bp->rx_nr_rings + bp->tx_nr_rings);
 	req.num_cmpl_rings = rte_cpu_to_le_16(bp->rx_nr_rings +
 					      bp->tx_nr_rings);
-	req.num_hw_ring_grps = rte_cpu_to_le_16(bp->rx_nr_rings);
 	req.num_vnics = rte_cpu_to_le_16(bp->rx_nr_rings);
 	if (bp->vf_resv_strategy ==
 	    HWRM_FUNC_RESOURCE_QCAPS_OUTPUT_VF_RESV_STRATEGY_MINIMAL_STATIC) {
-		enables = HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_VNICS |
-				HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_L2_CTXS |
-				HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_RSSCOS_CTXS;
-		req.enables |= rte_cpu_to_le_32(enables);
+		enables |= HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_VNICS |
+			   HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_L2_CTXS |
+			   HWRM_FUNC_VF_CFG_INPUT_ENABLES_NUM_RSSCOS_CTXS;
 		req.num_rsscos_ctxs = rte_cpu_to_le_16(BNXT_VF_RSV_NUM_RSS_CTX);
 		req.num_l2_ctxs = rte_cpu_to_le_16(BNXT_VF_RSV_NUM_L2_CTX);
 		req.num_vnics = rte_cpu_to_le_16(BNXT_VF_RSV_NUM_VNIC);
@@ -738,7 +756,11 @@ int bnxt_hwrm_func_reserve_vf_resc(struct bnxt *bp, bool test)
 			HWRM_FUNC_VF_CFG_INPUT_FLAGS_STAT_CTX_ASSETS_TEST |
 			HWRM_FUNC_VF_CFG_INPUT_FLAGS_VNIC_ASSETS_TEST;
 
+	if (test && BNXT_HAS_RING_GRPS(bp))
+		flags |= HWRM_FUNC_VF_CFG_INPUT_FLAGS_RING_GRP_ASSETS_TEST;
+
 	req.flags = rte_cpu_to_le_32(flags);
+	req.enables |= rte_cpu_to_le_32(enables);
 
 	rc = bnxt_hwrm_send_message(bp, &req, sizeof(req), BNXT_USE_CHIMP_MB);
 
@@ -774,6 +796,7 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp)
 		bp->max_vnics = rte_le_to_cpu_16(resp->max_vnics);
 		bp->max_stat_ctx = rte_le_to_cpu_16(resp->max_stat_ctx);
 	}
+	bp->max_nq_rings = rte_le_to_cpu_16(resp->max_msix);
 	bp->vf_resv_strategy = rte_le_to_cpu_16(resp->vf_reservation_strategy);
 	if (bp->vf_resv_strategy >
 	    HWRM_FUNC_RESOURCE_QCAPS_OUTPUT_VF_RESV_STRATEGY_MINIMAL_STATIC)
@@ -1092,6 +1115,13 @@ int bnxt_hwrm_queue_qportcfg(struct bnxt *bp)
 			}
 		}
 	}
+
+	bp->max_tc = resp->max_configurable_queues;
+	bp->max_lltc = resp->max_configurable_lossless_queues;
+	if (bp->max_tc > BNXT_MAX_QUEUE)
+		bp->max_tc = BNXT_MAX_QUEUE;
+	bp->max_q = bp->max_tc;
+
 	PMD_DRV_LOG(DEBUG, "Tx Cos Queue to use: %d\n", bp->tx_cosq_id);
 
 	return rc;
@@ -1106,6 +1136,8 @@ int bnxt_hwrm_ring_alloc(struct bnxt *bp,
 	uint32_t enables = 0;
 	struct hwrm_ring_alloc_input req = {.req_type = 0 };
 	struct hwrm_ring_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	struct rte_mempool *mb_pool;
+	uint16_t rx_buf_size;
 
 	HWRM_PREP(req, RING_ALLOC, BNXT_USE_CHIMP_MB);
 
@@ -1117,24 +1149,59 @@ int bnxt_hwrm_ring_alloc(struct bnxt *bp,
 
 	switch (ring_type) {
 	case HWRM_RING_ALLOC_INPUT_RING_TYPE_TX:
+		req.ring_type = ring_type;
+		req.cmpl_ring_id = rte_cpu_to_le_16(cmpl_ring_id);
+		req.stat_ctx_id = rte_cpu_to_le_32(stats_ctx_id);
 		req.queue_id = rte_cpu_to_le_16(bp->tx_cosq_id);
-		/* FALLTHROUGH */
+		if (stats_ctx_id != INVALID_STATS_CTX_ID)
+			enables |=
+			HWRM_RING_ALLOC_INPUT_ENABLES_STAT_CTX_ID_VALID;
+		break;
 	case HWRM_RING_ALLOC_INPUT_RING_TYPE_RX:
 		req.ring_type = ring_type;
 		req.cmpl_ring_id = rte_cpu_to_le_16(cmpl_ring_id);
 		req.stat_ctx_id = rte_cpu_to_le_32(stats_ctx_id);
+		if (BNXT_CHIP_THOR(bp)) {
+			mb_pool = bp->rx_queues[0]->mb_pool;
+			rx_buf_size = rte_pktmbuf_data_room_size(mb_pool) -
+				      RTE_PKTMBUF_HEADROOM;
+			req.rx_buf_size = rte_cpu_to_le_16(rx_buf_size);
+			enables |=
+				HWRM_RING_ALLOC_INPUT_ENABLES_RX_BUF_SIZE_VALID;
+		}
 		if (stats_ctx_id != INVALID_STATS_CTX_ID)
 			enables |=
-			HWRM_RING_ALLOC_INPUT_ENABLES_STAT_CTX_ID_VALID;
+				HWRM_RING_ALLOC_INPUT_ENABLES_STAT_CTX_ID_VALID;
 		break;
 	case HWRM_RING_ALLOC_INPUT_RING_TYPE_L2_CMPL:
 		req.ring_type = ring_type;
-		/*
-		 * TODO: Some HWRM versions crash with
-		 * HWRM_RING_ALLOC_INPUT_INT_MODE_POLL
-		 */
+		if (BNXT_HAS_NQ(bp)) {
+			/* Association of cp ring with nq */
+			req.nq_ring_id = rte_cpu_to_le_16(cmpl_ring_id);
+			enables |=
+				HWRM_RING_ALLOC_INPUT_ENABLES_NQ_RING_ID_VALID;
+		}
 		req.int_mode = HWRM_RING_ALLOC_INPUT_INT_MODE_MSIX;
 		break;
+	case HWRM_RING_ALLOC_INPUT_RING_TYPE_NQ:
+		req.ring_type = ring_type;
+		req.page_size = BNXT_PAGE_SHFT;
+		req.int_mode = HWRM_RING_ALLOC_INPUT_INT_MODE_MSIX;
+		break;
+	case HWRM_RING_ALLOC_INPUT_RING_TYPE_RX_AGG:
+		req.ring_type = ring_type;
+		req.rx_ring_id = rte_cpu_to_le_16(ring->fw_rx_ring_id);
+
+		mb_pool = bp->rx_queues[0]->mb_pool;
+		rx_buf_size = rte_pktmbuf_data_room_size(mb_pool) -
+			      RTE_PKTMBUF_HEADROOM;
+		req.rx_buf_size = rte_cpu_to_le_16(rx_buf_size);
+
+		req.stat_ctx_id = rte_cpu_to_le_32(stats_ctx_id);
+		enables |= HWRM_RING_ALLOC_INPUT_ENABLES_RX_RING_ID_VALID |
+			   HWRM_RING_ALLOC_INPUT_ENABLES_RX_BUF_SIZE_VALID |
+			   HWRM_RING_ALLOC_INPUT_ENABLES_STAT_CTX_ID_VALID;
+		break;
 	default:
 		PMD_DRV_LOG(ERR, "hwrm alloc invalid ring type %d\n",
 			ring_type);
@@ -1156,12 +1223,23 @@ int bnxt_hwrm_ring_alloc(struct bnxt *bp,
 			return rc;
 		case HWRM_RING_ALLOC_INPUT_RING_TYPE_RX:
 			PMD_DRV_LOG(ERR,
-				"hwrm_ring_alloc rx failed. rc:%d\n", rc);
+				    "hwrm_ring_alloc rx failed. rc:%d\n", rc);
+			HWRM_UNLOCK();
+			return rc;
+		case HWRM_RING_ALLOC_INPUT_RING_TYPE_RX_AGG:
+			PMD_DRV_LOG(ERR,
+				    "hwrm_ring_alloc rx agg failed. rc:%d\n",
+				    rc);
 			HWRM_UNLOCK();
 			return rc;
 		case HWRM_RING_ALLOC_INPUT_RING_TYPE_TX:
 			PMD_DRV_LOG(ERR,
-				"hwrm_ring_alloc tx failed. rc:%d\n", rc);
+				    "hwrm_ring_alloc tx failed. rc:%d\n", rc);
+			HWRM_UNLOCK();
+			return rc;
+		case HWRM_RING_ALLOC_INPUT_RING_TYPE_NQ:
+			PMD_DRV_LOG(ERR,
+				    "hwrm_ring_alloc nq failed. rc:%d\n", rc);
 			HWRM_UNLOCK();
 			return rc;
 		default:
@@ -1208,6 +1286,14 @@ int bnxt_hwrm_ring_free(struct bnxt *bp,
 			PMD_DRV_LOG(ERR, "hwrm_ring_free tx failed. rc:%d\n",
 				rc);
 			return rc;
+		case HWRM_RING_FREE_INPUT_RING_TYPE_NQ:
+			PMD_DRV_LOG(ERR,
+				    "hwrm_ring_free nq failed. rc:%d\n", rc);
+			return rc;
+		case HWRM_RING_FREE_INPUT_RING_TYPE_RX_AGG:
+			PMD_DRV_LOG(ERR,
+				    "hwrm_ring_free agg failed. rc:%d\n", rc);
+			return rc;
 		default:
 			PMD_DRV_LOG(ERR, "Invalid ring, rc:%d\n", rc);
 			return rc;
@@ -1332,6 +1418,9 @@ int bnxt_hwrm_vnic_alloc(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 	struct hwrm_vnic_alloc_input req = { 0 };
 	struct hwrm_vnic_alloc_output *resp = bp->hwrm_cmd_resp_addr;
 
+	if (!BNXT_HAS_RING_GRPS(bp))
+		goto skip_ring_grps;
+
 	/* map ring groups to this vnic */
 	PMD_DRV_LOG(DEBUG, "Alloc VNIC. Start %x, End %x\n",
 		vnic->start_grp_id, vnic->end_grp_id);
@@ -1342,6 +1431,8 @@ int bnxt_hwrm_vnic_alloc(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 	vnic->rss_rule = (uint16_t)HWRM_NA_SIGNATURE;
 	vnic->cos_rule = (uint16_t)HWRM_NA_SIGNATURE;
 	vnic->lb_rule = (uint16_t)HWRM_NA_SIGNATURE;
+
+skip_ring_grps:
 	vnic->mru = bp->eth_dev->data->mtu + RTE_ETHER_HDR_LEN +
 				RTE_ETHER_CRC_LEN + VLAN_TAG_SIZE;
 	HWRM_PREP(req, VNIC_ALLOC, BNXT_USE_CHIMP_MB);
@@ -1423,6 +1514,7 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 	struct hwrm_vnic_cfg_output *resp = bp->hwrm_cmd_resp_addr;
 	uint32_t ctx_enable_flag = 0;
 	struct bnxt_plcmodes_cfg pmodes;
+	uint32_t enables = 0;
 
 	if (vnic->fw_vnic_id == INVALID_HW_RING_ID) {
 		PMD_DRV_LOG(DEBUG, "VNIC ID %x\n", vnic->fw_vnic_id);
@@ -1435,9 +1527,22 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 
 	HWRM_PREP(req, VNIC_CFG, BNXT_USE_CHIMP_MB);
 
+	if (BNXT_CHIP_THOR(bp)) {
+		struct bnxt_rx_queue *rxq = bp->eth_dev->data->rx_queues[0];
+		struct bnxt_rx_ring_info *rxr = rxq->rx_ring;
+		struct bnxt_cp_ring_info *cpr = bp->def_cp_ring;
+
+		req.default_rx_ring_id =
+			rte_cpu_to_le_16(rxr->rx_ring_struct->fw_ring_id);
+		req.default_cmpl_ring_id =
+			rte_cpu_to_le_16(cpr->cp_ring_struct->fw_ring_id);
+		enables = HWRM_VNIC_CFG_INPUT_ENABLES_DEFAULT_RX_RING_ID |
+			  HWRM_VNIC_CFG_INPUT_ENABLES_DEFAULT_CMPL_RING_ID;
+		goto config_mru;
+	}
+
 	/* Only RSS support for now TBD: COS & LB */
-	req.enables =
-	    rte_cpu_to_le_32(HWRM_VNIC_CFG_INPUT_ENABLES_DFLT_RING_GRP);
+	enables = HWRM_VNIC_CFG_INPUT_ENABLES_DFLT_RING_GRP;
 	if (vnic->lb_rule != 0xffff)
 		ctx_enable_flag |= HWRM_VNIC_CFG_INPUT_ENABLES_LB_RULE;
 	if (vnic->cos_rule != 0xffff)
@@ -1446,12 +1551,15 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 		ctx_enable_flag |= HWRM_VNIC_CFG_INPUT_ENABLES_MRU;
 		ctx_enable_flag |= HWRM_VNIC_CFG_INPUT_ENABLES_RSS_RULE;
 	}
-	req.enables |= rte_cpu_to_le_32(ctx_enable_flag);
-	req.vnic_id = rte_cpu_to_le_16(vnic->fw_vnic_id);
+	enables |= ctx_enable_flag;
 	req.dflt_ring_grp = rte_cpu_to_le_16(vnic->dflt_ring_grp);
 	req.rss_rule = rte_cpu_to_le_16(vnic->rss_rule);
 	req.cos_rule = rte_cpu_to_le_16(vnic->cos_rule);
 	req.lb_rule = rte_cpu_to_le_16(vnic->lb_rule);
+
+config_mru:
+	req.enables = rte_cpu_to_le_32(enables);
+	req.vnic_id = rte_cpu_to_le_16(vnic->fw_vnic_id);
 	req.mru = rte_cpu_to_le_16(vnic->mru);
 	/* Configure default VNIC only once. */
 	if (vnic->func_default && !(bp->flags & BNXT_FLAG_DFLT_VNIC_SET)) {
@@ -1672,6 +1780,9 @@ int bnxt_hwrm_vnic_tpa_cfg(struct bnxt *bp,
 	struct hwrm_vnic_tpa_cfg_input req = {.req_type = 0 };
 	struct hwrm_vnic_tpa_cfg_output *resp = bp->hwrm_cmd_resp_addr;
 
+	if (BNXT_CHIP_THOR(bp))
+		return 0;
+
 	HWRM_PREP(req, VNIC_TPA_CFG, BNXT_USE_CHIMP_MB);
 
 	if (enable) {
@@ -1887,6 +1998,9 @@ int bnxt_free_all_hwrm_ring_grps(struct bnxt *bp)
 	uint16_t idx;
 	uint32_t rc = 0;
 
+	if (!BNXT_HAS_RING_GRPS(bp))
+		return 0;
+
 	for (idx = 0; idx < bp->rx_cp_nr_rings; idx++) {
 
 		if (bp->grp_info[idx].fw_grp_id == INVALID_HW_RING_ID)
@@ -1900,6 +2014,18 @@ int bnxt_free_all_hwrm_ring_grps(struct bnxt *bp)
 	return rc;
 }
 
+static void bnxt_free_nq_ring(struct bnxt *bp, struct bnxt_cp_ring_info *cpr)
+{
+	struct bnxt_ring *cp_ring = cpr->cp_ring_struct;
+
+	bnxt_hwrm_ring_free(bp, cp_ring,
+			    HWRM_RING_FREE_INPUT_RING_TYPE_NQ);
+	cp_ring->fw_ring_id = INVALID_HW_RING_ID;
+	memset(cpr->cp_desc_ring, 0, cpr->cp_ring_struct->ring_size *
+				     sizeof(*cpr->cp_desc_ring));
+	cpr->cp_raw_cons = 0;
+}
+
 static void bnxt_free_cp_ring(struct bnxt *bp, struct bnxt_cp_ring_info *cpr)
 {
 	struct bnxt_ring *cp_ring = cpr->cp_ring_struct;
@@ -1935,6 +2061,8 @@ void bnxt_free_hwrm_rx_ring(struct bnxt *bp, int queue_index)
 	ring = rxr->ag_ring_struct;
 	if (ring->fw_ring_id != INVALID_HW_RING_ID) {
 		bnxt_hwrm_ring_free(bp, ring,
+				    BNXT_CHIP_THOR(bp) ?
+				    HWRM_RING_FREE_INPUT_RING_TYPE_RX_AGG :
 				    HWRM_RING_FREE_INPUT_RING_TYPE_RX);
 		ring->fw_ring_id = INVALID_HW_RING_ID;
 		memset(rxr->ag_buf_ring, 0,
@@ -1943,8 +2071,11 @@ void bnxt_free_hwrm_rx_ring(struct bnxt *bp, int queue_index)
 		rxr->ag_prod = 0;
 		bp->grp_info[queue_index].ag_fw_ring_id = INVALID_HW_RING_ID;
 	}
-	if (cpr->cp_ring_struct->fw_ring_id != INVALID_HW_RING_ID)
+	if (cpr->cp_ring_struct->fw_ring_id != INVALID_HW_RING_ID) {
 		bnxt_free_cp_ring(bp, cpr);
+		if (rxq->nq_ring)
+			bnxt_free_nq_ring(bp, rxq->nq_ring);
+	}
 
 	bp->grp_info[queue_index].cp_fw_ring_id = INVALID_HW_RING_ID;
 }
@@ -1975,6 +2106,8 @@ int bnxt_free_all_hwrm_rings(struct bnxt *bp)
 		if (cpr->cp_ring_struct->fw_ring_id != INVALID_HW_RING_ID) {
 			bnxt_free_cp_ring(bp, cpr);
 			cpr->cp_ring_struct->fw_ring_id = INVALID_HW_RING_ID;
+			if (txq->nq_ring)
+				bnxt_free_nq_ring(bp, txq->nq_ring);
 		}
 	}
 
@@ -1989,6 +2122,9 @@ int bnxt_alloc_all_hwrm_ring_grps(struct bnxt *bp)
 	uint16_t i;
 	uint32_t rc = 0;
 
+	if (!BNXT_HAS_RING_GRPS(bp))
+		return 0;
+
 	for (i = 0; i < bp->rx_cp_nr_rings; i++) {
 		rc = bnxt_hwrm_ring_grp_alloc(bp, i);
 		if (rc)
@@ -2516,18 +2652,27 @@ static int bnxt_hwrm_pf_func_cfg(struct bnxt *bp, int tx_rings)
 {
 	struct hwrm_func_cfg_input req = {0};
 	struct hwrm_func_cfg_output *resp = bp->hwrm_cmd_resp_addr;
+	uint32_t enables;
 	int rc;
 
-	req.enables = rte_cpu_to_le_32(HWRM_FUNC_CFG_INPUT_ENABLES_MTU |
-			HWRM_FUNC_CFG_INPUT_ENABLES_MRU |
-			HWRM_FUNC_CFG_INPUT_ENABLES_NUM_RSSCOS_CTXS |
-			HWRM_FUNC_CFG_INPUT_ENABLES_NUM_STAT_CTXS |
-			HWRM_FUNC_CFG_INPUT_ENABLES_NUM_CMPL_RINGS |
-			HWRM_FUNC_CFG_INPUT_ENABLES_NUM_TX_RINGS |
-			HWRM_FUNC_CFG_INPUT_ENABLES_NUM_RX_RINGS |
-			HWRM_FUNC_CFG_INPUT_ENABLES_NUM_L2_CTXS |
-			HWRM_FUNC_CFG_INPUT_ENABLES_NUM_VNICS |
-			HWRM_FUNC_CFG_INPUT_ENABLES_NUM_HW_RING_GRPS);
+	enables = HWRM_FUNC_CFG_INPUT_ENABLES_MTU |
+		  HWRM_FUNC_CFG_INPUT_ENABLES_MRU |
+		  HWRM_FUNC_CFG_INPUT_ENABLES_NUM_RSSCOS_CTXS |
+		  HWRM_FUNC_CFG_INPUT_ENABLES_NUM_STAT_CTXS |
+		  HWRM_FUNC_CFG_INPUT_ENABLES_NUM_CMPL_RINGS |
+		  HWRM_FUNC_CFG_INPUT_ENABLES_NUM_TX_RINGS |
+		  HWRM_FUNC_CFG_INPUT_ENABLES_NUM_RX_RINGS |
+		  HWRM_FUNC_CFG_INPUT_ENABLES_NUM_L2_CTXS |
+		  HWRM_FUNC_CFG_INPUT_ENABLES_NUM_VNICS;
+
+	if (BNXT_HAS_RING_GRPS(bp)) {
+		enables |= HWRM_FUNC_CFG_INPUT_ENABLES_NUM_HW_RING_GRPS;
+		req.num_hw_ring_grps = rte_cpu_to_le_16(bp->max_ring_grps);
+	} else if (BNXT_HAS_NQ(bp)) {
+		enables |= HWRM_FUNC_CFG_INPUT_ENABLES_NUM_MSIX;
+		req.num_msix = rte_cpu_to_le_16(bp->max_nq_rings);
+	}
+
 	req.flags = rte_cpu_to_le_32(bp->pf.func_cfg_flags);
 	req.mtu = rte_cpu_to_le_16(BNXT_MAX_MTU);
 	req.mru = rte_cpu_to_le_16(bp->eth_dev->data->mtu + RTE_ETHER_HDR_LEN +
@@ -2540,8 +2685,8 @@ static int bnxt_hwrm_pf_func_cfg(struct bnxt *bp, int tx_rings)
 	req.num_rx_rings = rte_cpu_to_le_16(bp->max_rx_rings);
 	req.num_l2_ctxs = rte_cpu_to_le_16(bp->max_l2_ctx);
 	req.num_vnics = rte_cpu_to_le_16(bp->max_vnics);
-	req.num_hw_ring_grps = rte_cpu_to_le_16(bp->max_ring_grps);
 	req.fid = rte_cpu_to_le_16(0xffff);
+	req.enables = rte_cpu_to_le_32(enables);
 
 	HWRM_PREP(req, FUNC_CFG, BNXT_USE_CHIMP_MB);
 
@@ -2711,6 +2856,7 @@ int bnxt_hwrm_allocate_pf_only(struct bnxt *bp)
 	bp->pf.func_cfg_flags |=
 		HWRM_FUNC_CFG_INPUT_FLAGS_STD_TX_RING_MODE_DISABLE;
 	rc = bnxt_hwrm_pf_func_cfg(bp, bp->max_tx_rings);
+	rc = __bnxt_hwrm_func_qcaps(bp);
 	return rc;
 }
 
@@ -3970,6 +4116,192 @@ int bnxt_hwrm_set_ring_coal(struct bnxt *bp,
 	return 0;
 }
 
+#define BNXT_RTE_MEMZONE_FLAG  (RTE_MEMZONE_1GB | RTE_MEMZONE_IOVA_CONTIG)
+int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
+{
+	struct hwrm_func_backing_store_qcaps_input req = {0};
+	struct hwrm_func_backing_store_qcaps_output *resp =
+		bp->hwrm_cmd_resp_addr;
+	int rc;
+
+	if (!BNXT_CHIP_THOR(bp) ||
+	    bp->hwrm_spec_code < HWRM_VERSION_1_9_2 ||
+	    BNXT_VF(bp) ||
+	    bp->ctx)
+		return 0;
+
+	HWRM_PREP(req, FUNC_BACKING_STORE_QCAPS, BNXT_USE_CHIMP_MB);
+	rc = bnxt_hwrm_send_message(bp, &req, sizeof(req), BNXT_USE_CHIMP_MB);
+	HWRM_CHECK_RESULT_SILENT();
+
+	if (!rc) {
+		struct bnxt_ctx_pg_info *ctx_pg;
+		struct bnxt_ctx_mem_info *ctx;
+		int total_alloc_len;
+		int i;
+
+		total_alloc_len = sizeof(*ctx);
+		ctx = rte_malloc("bnxt_ctx_mem", total_alloc_len,
+				 RTE_CACHE_LINE_SIZE);
+		if (!ctx) {
+			rc = -ENOMEM;
+			goto ctx_err;
+		}
+		memset(ctx, 0, total_alloc_len);
+
+		ctx_pg = rte_malloc("bnxt_ctx_pg_mem",
+				    sizeof(*ctx_pg) * BNXT_MAX_Q,
+				    RTE_CACHE_LINE_SIZE);
+		if (!ctx_pg) {
+			rc = -ENOMEM;
+			goto ctx_err;
+		}
+		for (i = 0; i < BNXT_MAX_Q; i++, ctx_pg++)
+			ctx->tqm_mem[i] = ctx_pg;
+
+		bp->ctx = ctx;
+		ctx->qp_max_entries = rte_le_to_cpu_32(resp->qp_max_entries);
+		ctx->qp_min_qp1_entries =
+			rte_le_to_cpu_16(resp->qp_min_qp1_entries);
+		ctx->qp_max_l2_entries =
+			rte_le_to_cpu_16(resp->qp_max_l2_entries);
+		ctx->qp_entry_size = rte_le_to_cpu_16(resp->qp_entry_size);
+		ctx->srq_max_l2_entries =
+			rte_le_to_cpu_16(resp->srq_max_l2_entries);
+		ctx->srq_max_entries = rte_le_to_cpu_32(resp->srq_max_entries);
+		ctx->srq_entry_size = rte_le_to_cpu_16(resp->srq_entry_size);
+		ctx->cq_max_l2_entries =
+			rte_le_to_cpu_16(resp->cq_max_l2_entries);
+		ctx->cq_max_entries = rte_le_to_cpu_32(resp->cq_max_entries);
+		ctx->cq_entry_size = rte_le_to_cpu_16(resp->cq_entry_size);
+		ctx->vnic_max_vnic_entries =
+			rte_le_to_cpu_16(resp->vnic_max_vnic_entries);
+		ctx->vnic_max_ring_table_entries =
+			rte_le_to_cpu_16(resp->vnic_max_ring_table_entries);
+		ctx->vnic_entry_size = rte_le_to_cpu_16(resp->vnic_entry_size);
+		ctx->stat_max_entries =
+			rte_le_to_cpu_32(resp->stat_max_entries);
+		ctx->stat_entry_size = rte_le_to_cpu_16(resp->stat_entry_size);
+		ctx->tqm_entry_size = rte_le_to_cpu_16(resp->tqm_entry_size);
+		ctx->tqm_min_entries_per_ring =
+			rte_le_to_cpu_32(resp->tqm_min_entries_per_ring);
+		ctx->tqm_max_entries_per_ring =
+			rte_le_to_cpu_32(resp->tqm_max_entries_per_ring);
+		ctx->tqm_entries_multiple = resp->tqm_entries_multiple;
+		if (!ctx->tqm_entries_multiple)
+			ctx->tqm_entries_multiple = 1;
+		ctx->mrav_max_entries =
+			rte_le_to_cpu_32(resp->mrav_max_entries);
+		ctx->mrav_entry_size = rte_le_to_cpu_16(resp->mrav_entry_size);
+		ctx->tim_entry_size = rte_le_to_cpu_16(resp->tim_entry_size);
+		ctx->tim_max_entries = rte_le_to_cpu_32(resp->tim_max_entries);
+	} else {
+		rc = 0;
+	}
+ctx_err:
+	HWRM_UNLOCK();
+	return rc;
+}
+
+int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, uint32_t enables)
+{
+	struct hwrm_func_backing_store_cfg_input req = {0};
+	struct hwrm_func_backing_store_cfg_output *resp =
+		bp->hwrm_cmd_resp_addr;
+	struct bnxt_ctx_mem_info *ctx = bp->ctx;
+	struct bnxt_ctx_pg_info *ctx_pg;
+	uint32_t *num_entries;
+	uint64_t *pg_dir;
+	uint8_t *pg_attr;
+	uint32_t ena;
+	int i, rc;
+
+	if (!ctx)
+		return 0;
+
+	HWRM_PREP(req, FUNC_BACKING_STORE_CFG, BNXT_USE_CHIMP_MB);
+	req.enables = rte_cpu_to_le_32(enables);
+
+	if (enables & HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_QP) {
+		ctx_pg = &ctx->qp_mem;
+		req.qp_num_entries = rte_cpu_to_le_32(ctx_pg->entries);
+		req.qp_num_qp1_entries =
+			rte_cpu_to_le_16(ctx->qp_min_qp1_entries);
+		req.qp_num_l2_entries =
+			rte_cpu_to_le_16(ctx->qp_max_l2_entries);
+		req.qp_entry_size = rte_cpu_to_le_16(ctx->qp_entry_size);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req.qpc_pg_size_qpc_lvl,
+				      &req.qpc_page_dir);
+	}
+
+	if (enables & HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_SRQ) {
+		ctx_pg = &ctx->srq_mem;
+		req.srq_num_entries = rte_cpu_to_le_32(ctx_pg->entries);
+		req.srq_num_l2_entries =
+				 rte_cpu_to_le_16(ctx->srq_max_l2_entries);
+		req.srq_entry_size = rte_cpu_to_le_16(ctx->srq_entry_size);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req.srq_pg_size_srq_lvl,
+				      &req.srq_page_dir);
+	}
+
+	if (enables & HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_CQ) {
+		ctx_pg = &ctx->cq_mem;
+		req.cq_num_entries = rte_cpu_to_le_32(ctx_pg->entries);
+		req.cq_num_l2_entries =
+				rte_cpu_to_le_16(ctx->cq_max_l2_entries);
+		req.cq_entry_size = rte_cpu_to_le_16(ctx->cq_entry_size);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req.cq_pg_size_cq_lvl,
+				      &req.cq_page_dir);
+	}
+
+	if (enables & HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_VNIC) {
+		ctx_pg = &ctx->vnic_mem;
+		req.vnic_num_vnic_entries =
+			rte_cpu_to_le_16(ctx->vnic_max_vnic_entries);
+		req.vnic_num_ring_table_entries =
+			rte_cpu_to_le_16(ctx->vnic_max_ring_table_entries);
+		req.vnic_entry_size = rte_cpu_to_le_16(ctx->vnic_entry_size);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req.vnic_pg_size_vnic_lvl,
+				      &req.vnic_page_dir);
+	}
+
+	if (enables & HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_STAT) {
+		ctx_pg = &ctx->stat_mem;
+		req.stat_num_entries = rte_cpu_to_le_16(ctx->stat_max_entries);
+		req.stat_entry_size = rte_cpu_to_le_16(ctx->stat_entry_size);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req.stat_pg_size_stat_lvl,
+				      &req.stat_page_dir);
+	}
+
+	req.tqm_entry_size = rte_cpu_to_le_16(ctx->tqm_entry_size);
+	num_entries = &req.tqm_sp_num_entries;
+	pg_attr = &req.tqm_sp_pg_size_tqm_sp_lvl;
+	pg_dir = &req.tqm_sp_page_dir;
+	ena = HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_TQM_SP;
+	for (i = 0; i < 9; i++, num_entries++, pg_attr++, pg_dir++, ena <<= 1) {
+		if (!(enables & ena))
+			continue;
+
+		req.tqm_entry_size = rte_cpu_to_le_16(ctx->tqm_entry_size);
+
+		ctx_pg = ctx->tqm_mem[i];
+		*num_entries = rte_cpu_to_le_16(ctx_pg->entries);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem, pg_attr, pg_dir);
+	}
+
+	rc = bnxt_hwrm_send_message(bp, &req, sizeof(req), BNXT_USE_CHIMP_MB);
+	HWRM_CHECK_RESULT();
+	HWRM_UNLOCK();
+	if (rc)
+		rc = -EIO;
+	return rc;
+}
+
 int bnxt_hwrm_ext_port_qstats(struct bnxt *bp)
 {
 	struct hwrm_port_qstats_ext_input req = {0};
diff --git a/drivers/net/bnxt/bnxt_hwrm.h b/drivers/net/bnxt/bnxt_hwrm.h
index 53d79f0461..ffd99de345 100644
--- a/drivers/net/bnxt/bnxt_hwrm.h
+++ b/drivers/net/bnxt/bnxt_hwrm.h
@@ -36,6 +36,13 @@ struct bnxt_cp_ring_info;
 #define HWRM_SPEC_CODE_1_9_0		0x10900
 #define HWRM_SPEC_CODE_1_9_2		0x10902
 
+#define FUNC_BACKING_STORE_CFG_INPUT_DFLT_ENABLES              \
+	(HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_QP |        \
+	HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_SRQ |        \
+	HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_CQ |         \
+	HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_VNIC |       \
+	HWRM_FUNC_BACKING_STORE_CFG_INPUT_ENABLES_STAT)
+
 int bnxt_hwrm_cfa_l2_clear_rx_mask(struct bnxt *bp,
 				   struct bnxt_vnic_info *vnic);
 int bnxt_hwrm_cfa_l2_set_rx_mask(struct bnxt *bp, struct bnxt_vnic_info *vnic,
@@ -179,4 +186,7 @@ int bnxt_hwrm_set_ring_coal(struct bnxt *bp,
 			struct bnxt_coal *coal, uint16_t ring_id);
 int bnxt_hwrm_check_vf_rings(struct bnxt *bp);
 int bnxt_hwrm_ext_port_qstats(struct bnxt *bp);
+int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp);
+int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, uint32_t enables);
+int bnxt_alloc_ctx_mem(struct bnxt *bp);
 #endif
diff --git a/drivers/net/bnxt/bnxt_ring.c b/drivers/net/bnxt/bnxt_ring.c
index 8473e4abe7..56bb463a65 100644
--- a/drivers/net/bnxt/bnxt_ring.c
+++ b/drivers/net/bnxt/bnxt_ring.c
@@ -67,6 +67,7 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 			    struct bnxt_tx_queue *txq,
 			    struct bnxt_rx_queue *rxq,
 			    struct bnxt_cp_ring_info *cp_ring_info,
+			    struct bnxt_cp_ring_info *nq_ring_info,
 			    const char *suffix)
 {
 	struct bnxt_ring *cp_ring = cp_ring_info->cp_ring_struct;
@@ -78,49 +79,70 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 	uint64_t rx_offloads = bp->eth_dev->data->dev_conf.rxmode.offloads;
 	const struct rte_memzone *mz = NULL;
 	char mz_name[RTE_MEMZONE_NAMESIZE];
+	rte_iova_t mz_phys_addr_base;
 	rte_iova_t mz_phys_addr;
 	int sz;
 
 	int stats_len = (tx_ring_info || rx_ring_info) ?
 	    RTE_CACHE_LINE_ROUNDUP(sizeof(struct hwrm_stat_ctx_query_output) -
 				   sizeof (struct hwrm_resp_hdr)) : 0;
+	stats_len = RTE_ALIGN(stats_len, 128);
 
 	int cp_vmem_start = stats_len;
 	int cp_vmem_len = RTE_CACHE_LINE_ROUNDUP(cp_ring->vmem_size);
+	cp_vmem_len = RTE_ALIGN(cp_vmem_len, 128);
 
-	int tx_vmem_start = cp_vmem_start + cp_vmem_len;
+	int nq_vmem_len = BNXT_CHIP_THOR(bp) ?
+		RTE_CACHE_LINE_ROUNDUP(cp_ring->vmem_size) : 0;
+	nq_vmem_len = RTE_ALIGN(nq_vmem_len, 128);
+
+	int nq_vmem_start = cp_vmem_start + cp_vmem_len;
+
+	int tx_vmem_start = nq_vmem_start + nq_vmem_len;
 	int tx_vmem_len =
 	    tx_ring_info ? RTE_CACHE_LINE_ROUNDUP(tx_ring_info->
 						tx_ring_struct->vmem_size) : 0;
+	tx_vmem_len = RTE_ALIGN(tx_vmem_len, 128);
 
 	int rx_vmem_start = tx_vmem_start + tx_vmem_len;
 	int rx_vmem_len = rx_ring_info ?
 		RTE_CACHE_LINE_ROUNDUP(rx_ring_info->
 						rx_ring_struct->vmem_size) : 0;
+	rx_vmem_len = RTE_ALIGN(rx_vmem_len, 128);
 	int ag_vmem_start = 0;
 	int ag_vmem_len = 0;
 	int cp_ring_start =  0;
+	int nq_ring_start = 0;
 
 	ag_vmem_start = rx_vmem_start + rx_vmem_len;
 	ag_vmem_len = rx_ring_info ? RTE_CACHE_LINE_ROUNDUP(
 				rx_ring_info->ag_ring_struct->vmem_size) : 0;
 	cp_ring_start = ag_vmem_start + ag_vmem_len;
+	cp_ring_start = RTE_ALIGN(cp_ring_start, 4096);
 
 	int cp_ring_len = RTE_CACHE_LINE_ROUNDUP(cp_ring->ring_size *
 						 sizeof(struct cmpl_base));
+	cp_ring_len = RTE_ALIGN(cp_ring_len, 128);
+	nq_ring_start = cp_ring_start + cp_ring_len;
+	nq_ring_start = RTE_ALIGN(nq_ring_start, 4096);
+
+	int nq_ring_len = BNXT_CHIP_THOR(bp) ? cp_ring_len : 0;
 
-	int tx_ring_start = cp_ring_start + cp_ring_len;
+	int tx_ring_start = nq_ring_start + nq_ring_len;
 	int tx_ring_len = tx_ring_info ?
 	    RTE_CACHE_LINE_ROUNDUP(tx_ring_info->tx_ring_struct->ring_size *
 				   sizeof(struct tx_bd_long)) : 0;
+	tx_ring_len = RTE_ALIGN(tx_ring_len, 4096);
 
 	int rx_ring_start = tx_ring_start + tx_ring_len;
 	int rx_ring_len =  rx_ring_info ?
 		RTE_CACHE_LINE_ROUNDUP(rx_ring_info->rx_ring_struct->ring_size *
 		sizeof(struct rx_prod_pkt_bd)) : 0;
+	rx_ring_len = RTE_ALIGN(rx_ring_len, 4096);
 
 	int ag_ring_start = rx_ring_start + rx_ring_len;
 	int ag_ring_len = rx_ring_len * AGG_RING_SIZE_FACTOR;
+	ag_ring_len = RTE_ALIGN(ag_ring_len, 4096);
 
 	int ag_bitmap_start = ag_ring_start + ag_ring_len;
 	int ag_bitmap_len =  rx_ring_info ?
@@ -154,14 +176,16 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 			return -ENOMEM;
 	}
 	memset(mz->addr, 0, mz->len);
+	mz_phys_addr_base = mz->iova;
 	mz_phys_addr = mz->iova;
-	if ((unsigned long)mz->addr == mz_phys_addr) {
+	if ((unsigned long)mz->addr == mz_phys_addr_base) {
 		PMD_DRV_LOG(WARNING,
 			"Memzone physical address same as virtual.\n");
 		PMD_DRV_LOG(WARNING,
 			"Using rte_mem_virt2iova()\n");
 		for (sz = 0; sz < total_alloc_len; sz += getpagesize())
 			rte_mem_lock_page(((char *)mz->addr) + sz);
+		mz_phys_addr_base = rte_mem_virt2iova(mz->addr);
 		mz_phys_addr = rte_mem_virt2iova(mz->addr);
 		if (mz_phys_addr == 0) {
 			PMD_DRV_LOG(ERR,
@@ -255,6 +279,24 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 		cp_ring_info->hw_stats_map = mz_phys_addr;
 	}
 	cp_ring_info->hw_stats_ctx_id = HWRM_NA_SIGNATURE;
+
+	if (BNXT_HAS_NQ(bp)) {
+		struct bnxt_ring *nq_ring = nq_ring_info->cp_ring_struct;
+
+		nq_ring->bd = (char *)mz->addr + nq_ring_start;
+		nq_ring->bd_dma = mz_phys_addr + nq_ring_start;
+		nq_ring_info->cp_desc_ring = nq_ring->bd;
+		nq_ring_info->cp_desc_mapping = nq_ring->bd_dma;
+		nq_ring->mem_zone = (const void *)mz;
+
+		if (!nq_ring->bd)
+			return -ENOMEM;
+		if (nq_ring->vmem_size)
+			*nq_ring->vmem = (char *)mz->addr + nq_vmem_start;
+
+		nq_ring_info->hw_stats_ctx_id = HWRM_NA_SIGNATURE;
+	}
+
 	return 0;
 }
 
@@ -279,43 +321,109 @@ static void bnxt_init_dflt_coal(struct bnxt_coal *coal)
 static void bnxt_set_db(struct bnxt *bp,
 			struct bnxt_db_info *db,
 			uint32_t ring_type,
-			uint32_t map_idx)
+			uint32_t map_idx,
+			uint32_t fid)
 {
-	db->doorbell = (char *)bp->doorbell_base + map_idx * 0x80;
-	switch (ring_type) {
-	case HWRM_RING_ALLOC_INPUT_RING_TYPE_TX:
-		db->db_key32 = DB_KEY_TX;
-		break;
-	case HWRM_RING_ALLOC_INPUT_RING_TYPE_RX:
-		db->db_key32 = DB_KEY_RX;
-		break;
-	case HWRM_RING_ALLOC_INPUT_RING_TYPE_L2_CMPL:
-		db->db_key32 = DB_KEY_CP;
-		break;
+	if (BNXT_CHIP_THOR(bp)) {
+		if (BNXT_PF(bp))
+			db->doorbell = (char *)bp->doorbell_base + 0x10000;
+		else
+			db->doorbell = (char *)bp->doorbell_base + 0x4000;
+		switch (ring_type) {
+		case HWRM_RING_ALLOC_INPUT_RING_TYPE_TX:
+			db->db_key64 = DBR_PATH_L2 | DBR_TYPE_SQ;
+			break;
+		case HWRM_RING_ALLOC_INPUT_RING_TYPE_RX:
+		case HWRM_RING_ALLOC_INPUT_RING_TYPE_RX_AGG:
+			db->db_key64 = DBR_PATH_L2 | DBR_TYPE_SRQ;
+			break;
+		case HWRM_RING_ALLOC_INPUT_RING_TYPE_L2_CMPL:
+			db->db_key64 = DBR_PATH_L2 | DBR_TYPE_CQ;
+			break;
+		case HWRM_RING_ALLOC_INPUT_RING_TYPE_NQ:
+			db->db_key64 = DBR_PATH_L2 | DBR_TYPE_NQ;
+			break;
+		}
+		db->db_key64 |= (uint64_t)fid << DBR_XID_SFT;
+		db->db_64 = true;
+	} else {
+		db->doorbell = (char *)bp->doorbell_base + map_idx * 0x80;
+		switch (ring_type) {
+		case HWRM_RING_ALLOC_INPUT_RING_TYPE_TX:
+			db->db_key32 = DB_KEY_TX;
+			break;
+		case HWRM_RING_ALLOC_INPUT_RING_TYPE_RX:
+			db->db_key32 = DB_KEY_RX;
+			break;
+		case HWRM_RING_ALLOC_INPUT_RING_TYPE_L2_CMPL:
+			db->db_key32 = DB_KEY_CP;
+			break;
+		}
+		db->db_64 = false;
 	}
 }
 
 static int bnxt_alloc_cmpl_ring(struct bnxt *bp, int queue_index,
-				struct bnxt_cp_ring_info *cpr)
+				struct bnxt_cp_ring_info *cpr,
+				struct bnxt_cp_ring_info *nqr)
 {
 	struct bnxt_ring *cp_ring = cpr->cp_ring_struct;
+	uint32_t nq_ring_id = HWRM_NA_SIGNATURE;
 	uint8_t ring_type;
 	int rc = 0;
 
 	ring_type = HWRM_RING_ALLOC_INPUT_RING_TYPE_L2_CMPL;
 
+	if (BNXT_HAS_NQ(bp)) {
+		if (nqr) {
+			nq_ring_id = nqr->cp_ring_struct->fw_ring_id;
+		} else {
+			PMD_DRV_LOG(ERR, "NQ ring is NULL\n");
+			return -EINVAL;
+		}
+	}
+
 	rc = bnxt_hwrm_ring_alloc(bp, cp_ring, ring_type, queue_index,
-				  HWRM_NA_SIGNATURE, HWRM_NA_SIGNATURE);
+				  HWRM_NA_SIGNATURE, nq_ring_id);
 	if (rc)
 		return rc;
 
 	cpr->cp_cons = 0;
-	bnxt_set_db(bp, &cpr->cp_db, ring_type, queue_index);
+	bnxt_set_db(bp, &cpr->cp_db, ring_type, queue_index,
+		    cp_ring->fw_ring_id);
 	bnxt_db_cq(cpr);
 
 	return 0;
 }
 
+static int bnxt_alloc_nq_ring(struct bnxt *bp, int queue_index,
+			      struct bnxt_cp_ring_info *nqr,
+			      bool rx)
+{
+	struct bnxt_ring *nq_ring = nqr->cp_ring_struct;
+	uint8_t ring_type;
+	int rc = 0;
+
+	if (!BNXT_HAS_NQ(bp))
+		return -EINVAL;
+
+	ring_type = HWRM_RING_ALLOC_INPUT_RING_TYPE_NQ;
+
+	rc = bnxt_hwrm_ring_alloc(bp, nq_ring, ring_type, queue_index,
+				  HWRM_NA_SIGNATURE, HWRM_NA_SIGNATURE);
+	if (rc)
+		return rc;
+
+	if (rx)
+		bp->grp_info[queue_index].cp_fw_ring_id = nq_ring->fw_ring_id;
+
+	bnxt_set_db(bp, &nqr->cp_db, ring_type, queue_index,
+		    nq_ring->fw_ring_id);
+	bnxt_db_nq(nqr);
+
+	return 0;
+}
+
 static int bnxt_alloc_rx_ring(struct bnxt *bp, int queue_index)
 {
 	struct bnxt_rx_queue *rxq = bp->rx_queues[queue_index];
@@ -336,7 +444,7 @@ static int bnxt_alloc_rx_ring(struct bnxt *bp, int queue_index)
 
 	rxr->rx_prod = 0;
 	bp->grp_info[queue_index].rx_fw_ring_id = ring->fw_ring_id;
-	bnxt_set_db(bp, &rxr->rx_db, ring_type, queue_index);
+	bnxt_set_db(bp, &rxr->rx_db, ring_type, queue_index, ring->fw_ring_id);
 	bnxt_db_write(&rxr->rx_db, rxr->rx_prod);
 
 	return 0;
@@ -354,7 +462,14 @@ static int bnxt_alloc_rx_agg_ring(struct bnxt *bp, int queue_index)
 	uint8_t ring_type;
 	int rc = 0;
 
-	ring_type = HWRM_RING_ALLOC_INPUT_RING_TYPE_RX;
+	ring->fw_rx_ring_id = rxr->rx_ring_struct->fw_ring_id;
+
+	if (BNXT_CHIP_THOR(bp)) {
+		ring_type = HWRM_RING_ALLOC_INPUT_RING_TYPE_RX_AGG;
+		hw_stats_ctx_id = cpr->hw_stats_ctx_id;
+	} else {
+		ring_type = HWRM_RING_ALLOC_INPUT_RING_TYPE_RX;
+	}
 
 	rc = bnxt_hwrm_ring_alloc(bp, ring, ring_type, map_idx,
 				  hw_stats_ctx_id, cp_ring->fw_ring_id);
@@ -364,7 +479,7 @@ static int bnxt_alloc_rx_agg_ring(struct bnxt *bp, int queue_index)
 
 	rxr->ag_prod = 0;
 	bp->grp_info[queue_index].ag_fw_ring_id = ring->fw_ring_id;
-	bnxt_set_db(bp, &rxr->ag_db, ring_type, map_idx);
+	bnxt_set_db(bp, &rxr->ag_db, ring_type, map_idx, ring->fw_ring_id);
 	bnxt_db_write(&rxr->ag_db, rxr->ag_prod);
 
 	return 0;
@@ -375,10 +490,16 @@ int bnxt_alloc_hwrm_rx_ring(struct bnxt *bp, int queue_index)
 	struct bnxt_rx_queue *rxq = bp->rx_queues[queue_index];
 	struct bnxt_cp_ring_info *cpr = rxq->cp_ring;
 	struct bnxt_ring *cp_ring = cpr->cp_ring_struct;
+	struct bnxt_cp_ring_info *nqr = rxq->nq_ring;
 	struct bnxt_rx_ring_info *rxr = rxq->rx_ring;
 	int rc = 0;
 
-	if (bnxt_alloc_cmpl_ring(bp, queue_index, cpr))
+	if (BNXT_HAS_NQ(bp)) {
+		if (bnxt_alloc_nq_ring(bp, queue_index, nqr, true))
+			goto err_out;
+	}
+
+	if (bnxt_alloc_cmpl_ring(bp, queue_index, cpr, nqr))
 		goto err_out;
 
 	bp->grp_info[queue_index].fw_stats_ctx = cpr->hw_stats_ctx_id;
@@ -444,12 +565,16 @@ int bnxt_alloc_hwrm_rings(struct bnxt *bp)
 	for (i = 0; i < bp->rx_cp_nr_rings; i++) {
 		struct bnxt_rx_queue *rxq = bp->rx_queues[i];
 		struct bnxt_cp_ring_info *cpr = rxq->cp_ring;
+		struct bnxt_cp_ring_info *nqr = rxq->nq_ring;
 		struct bnxt_ring *cp_ring = cpr->cp_ring_struct;
 		struct bnxt_rx_ring_info *rxr = rxq->rx_ring;
 
-		bp->grp_info[i].fw_stats_ctx = cpr->hw_stats_ctx_id;
+		if (BNXT_HAS_NQ(bp)) {
+			if (bnxt_alloc_nq_ring(bp, i, nqr, true))
+				goto err_out;
+		}
 
-		if (bnxt_alloc_cmpl_ring(bp, i, cpr))
+		if (bnxt_alloc_cmpl_ring(bp, i, cpr, nqr))
 			goto err_out;
 
 		bp->grp_info[i].fw_stats_ctx = cpr->hw_stats_ctx_id;
@@ -492,11 +617,17 @@ int bnxt_alloc_hwrm_rings(struct bnxt *bp)
 		struct bnxt_tx_queue *txq = bp->tx_queues[i];
 		struct bnxt_cp_ring_info *cpr = txq->cp_ring;
 		struct bnxt_ring *cp_ring = cpr->cp_ring_struct;
+		struct bnxt_cp_ring_info *nqr = txq->nq_ring;
 		struct bnxt_tx_ring_info *txr = txq->tx_ring;
 		struct bnxt_ring *ring = txr->tx_ring_struct;
 		unsigned int idx = i + bp->rx_cp_nr_rings;
 
-		if (bnxt_alloc_cmpl_ring(bp, idx, cpr))
+		if (BNXT_HAS_NQ(bp)) {
+			if (bnxt_alloc_nq_ring(bp, idx, nqr, false))
+				goto err_out;
+		}
+
+		if (bnxt_alloc_cmpl_ring(bp, idx, cpr, nqr))
 			goto err_out;
 
 		/* Tx ring */
@@ -508,7 +639,7 @@ int bnxt_alloc_hwrm_rings(struct bnxt *bp)
 		if (rc)
 			goto err_out;
 
-		bnxt_set_db(bp, &txr->tx_db, ring_type, idx);
+		bnxt_set_db(bp, &txr->tx_db, ring_type, idx, ring->fw_ring_id);
 		txq->index = idx;
 		bnxt_hwrm_set_ring_coal(bp, &coal, cp_ring->fw_ring_id);
 	}
diff --git a/drivers/net/bnxt/bnxt_ring.h b/drivers/net/bnxt/bnxt_ring.h
index 8cb0e8eb01..af2c5762ff 100644
--- a/drivers/net/bnxt/bnxt_ring.h
+++ b/drivers/net/bnxt/bnxt_ring.h
@@ -49,6 +49,7 @@ struct bnxt_ring {
 	void			**vmem;
 
 	uint16_t		fw_ring_id; /* Ring id filled by Chimp FW */
+	uint16_t                fw_rx_ring_id;
 	const void		*mem_zone;
 };
 
@@ -70,19 +71,40 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 			    struct bnxt_tx_queue *txq,
 			    struct bnxt_rx_queue *rxq,
 			    struct bnxt_cp_ring_info *cp_ring_info,
+			    struct bnxt_cp_ring_info *nq_ring_info,
 			    const char *suffix);
 int bnxt_alloc_hwrm_rx_ring(struct bnxt *bp, int queue_index);
 int bnxt_alloc_hwrm_rings(struct bnxt *bp);
 
 static inline void bnxt_db_write(struct bnxt_db_info *db, uint32_t idx)
 {
-	rte_write32(db->db_key32 | idx, db->doorbell);
+	if (db->db_64)
+		rte_write64_relaxed(db->db_key64 | idx, db->doorbell);
+	else
+		rte_write32(db->db_key32 | idx, db->doorbell);
+}
+
+static inline void bnxt_db_nq(struct bnxt_cp_ring_info *cpr)
+{
+	struct bnxt_db_info *db = &cpr->cp_db;
+
+	rte_smp_wmb();
+	if (likely(db->db_64))
+		rte_write64(db->db_key64 | DBR_TYPE_NQ |
+			    RING_CMP(cpr->cp_ring_struct, cpr->cp_raw_cons),
+			    db->doorbell);
 }
 
 static inline void bnxt_db_cq(struct bnxt_cp_ring_info *cpr)
 {
+	struct bnxt_db_info *db = &cpr->cp_db;
+	uint32_t idx = RING_CMP(cpr->cp_ring_struct, cpr->cp_raw_cons);
+
 	rte_smp_wmb();
-	B_CP_DIS_DB(cpr, cpr->cp_raw_cons);
+	if (db->db_64)
+		rte_write64(db->db_key64 | idx, db->doorbell);
+	else
+		B_CP_DIS_DB(cpr, cpr->cp_raw_cons);
 }
 
 #endif
diff --git a/drivers/net/bnxt/bnxt_rxq.c b/drivers/net/bnxt/bnxt_rxq.c
index 31ab38f1ff..6919acbb4d 100644
--- a/drivers/net/bnxt/bnxt_rxq.c
+++ b/drivers/net/bnxt/bnxt_rxq.c
@@ -341,7 +341,7 @@ int bnxt_rx_queue_setup_op(struct rte_eth_dev *eth_dev,
 	eth_dev->data->rx_queues[queue_idx] = rxq;
 	/* Allocate RX ring hardware descriptors */
 	if (bnxt_alloc_rings(bp, queue_idx, NULL, rxq, rxq->cp_ring,
-			"rxr")) {
+			rxq->nq_ring, "rxr")) {
 		PMD_DRV_LOG(ERR,
 			"ring_dma_zone_reserve for rx_ring failed!\n");
 		bnxt_rx_queue_release_op(rxq);
@@ -424,15 +424,18 @@ int bnxt_rx_queue_start(struct rte_eth_dev *dev, uint16_t rx_queue_id)
 	if (dev_conf->rxmode.mq_mode & ETH_MQ_RX_RSS_FLAG) {
 		vnic = rxq->vnic;
 
-		if (vnic->fw_grp_ids[rx_queue_id] != INVALID_HW_RING_ID)
-			return 0;
+		if (BNXT_HAS_RING_GRPS(bp)) {
+			if (vnic->fw_grp_ids[rx_queue_id] != INVALID_HW_RING_ID)
+				return 0;
+
+			vnic->fw_grp_ids[rx_queue_id] =
+					bp->grp_info[rx_queue_id].fw_grp_id;
+		}
 
 		PMD_DRV_LOG(DEBUG,
 			    "vnic = %p fw_grp_id = %d\n",
 			    vnic, bp->grp_info[rx_queue_id].fw_grp_id);
 
-		vnic->fw_grp_ids[rx_queue_id] =
-					bp->grp_info[rx_queue_id].fw_grp_id;
 		rc = bnxt_vnic_rss_configure(bp, vnic);
 	}
 
@@ -469,7 +472,8 @@ int bnxt_rx_queue_stop(struct rte_eth_dev *dev, uint16_t rx_queue_id)
 
 	if (dev_conf->rxmode.mq_mode & ETH_MQ_RX_RSS_FLAG) {
 		vnic = rxq->vnic;
-		vnic->fw_grp_ids[rx_queue_id] = INVALID_HW_RING_ID;
+		if (BNXT_HAS_RING_GRPS(bp))
+			vnic->fw_grp_ids[rx_queue_id] = INVALID_HW_RING_ID;
 		rc = bnxt_vnic_rss_configure(bp, vnic);
 	}
 
diff --git a/drivers/net/bnxt/bnxt_rxq.h b/drivers/net/bnxt/bnxt_rxq.h
index 7c6b4dec90..b5e42d01c0 100644
--- a/drivers/net/bnxt/bnxt_rxq.h
+++ b/drivers/net/bnxt/bnxt_rxq.h
@@ -39,6 +39,7 @@ struct bnxt_rx_queue {
 	uint32_t			rx_buf_use_size;  /* useable size */
 	struct bnxt_rx_ring_info	*rx_ring;
 	struct bnxt_cp_ring_info	*cp_ring;
+	struct bnxt_cp_ring_info	*nq_ring;
 	rte_atomic64_t		rx_mbuf_alloc_fail;
 	const struct rte_memzone *mz;
 };
diff --git a/drivers/net/bnxt/bnxt_rxr.c b/drivers/net/bnxt/bnxt_rxr.c
index 75d2c76a51..44303f3b02 100644
--- a/drivers/net/bnxt/bnxt_rxr.c
+++ b/drivers/net/bnxt/bnxt_rxr.c
@@ -637,6 +637,7 @@ void bnxt_free_rx_rings(struct bnxt *bp)
 int bnxt_init_rx_ring_struct(struct bnxt_rx_queue *rxq, unsigned int socket_id)
 {
 	struct bnxt_cp_ring_info *cpr;
+	struct bnxt_cp_ring_info *nqr;
 	struct bnxt_rx_ring_info *rxr;
 	struct bnxt_ring *ring;
 
@@ -685,6 +686,32 @@ int bnxt_init_rx_ring_struct(struct bnxt_rx_queue *rxq, unsigned int socket_id)
 	ring->vmem_size = 0;
 	ring->vmem = NULL;
 
+	if (BNXT_HAS_NQ(rxq->bp)) {
+		nqr = rte_zmalloc_socket("bnxt_rx_ring_cq",
+					 sizeof(struct bnxt_cp_ring_info),
+					 RTE_CACHE_LINE_SIZE, socket_id);
+		if (nqr == NULL)
+			return -ENOMEM;
+
+		rxq->nq_ring = nqr;
+
+		ring = rte_zmalloc_socket("bnxt_rx_ring_struct",
+					  sizeof(struct bnxt_ring),
+					  RTE_CACHE_LINE_SIZE, socket_id);
+		if (ring == NULL)
+			return -ENOMEM;
+
+		nqr->cp_ring_struct = ring;
+		ring->ring_size =
+			rte_align32pow2(rxr->rx_ring_struct->ring_size *
+					(2 + AGG_RING_SIZE_FACTOR));
+		ring->ring_mask = ring->ring_size - 1;
+		ring->bd = (void *)nqr->cp_desc_ring;
+		ring->bd_dma = nqr->cp_desc_mapping;
+		ring->vmem_size = 0;
+		ring->vmem = NULL;
+	}
+
 	/* Allocate Aggregator rings */
 	ring = rte_zmalloc_socket("bnxt_rx_ring_struct",
 				   sizeof(struct bnxt_ring),
diff --git a/drivers/net/bnxt/bnxt_txq.c b/drivers/net/bnxt/bnxt_txq.c
index 665bfbc126..43b3496c1e 100644
--- a/drivers/net/bnxt/bnxt_txq.c
+++ b/drivers/net/bnxt/bnxt_txq.c
@@ -134,7 +134,7 @@ int bnxt_tx_queue_setup_op(struct rte_eth_dev *eth_dev,
 
 	/* Allocate TX ring hardware descriptors */
 	if (bnxt_alloc_rings(bp, queue_idx, txq, NULL, txq->cp_ring,
-			"txr")) {
+			txq->nq_ring, "txr")) {
 		PMD_DRV_LOG(ERR, "ring_dma_zone_reserve for tx_ring failed!");
 		bnxt_tx_queue_release_op(txq);
 		rc = -ENOMEM;
diff --git a/drivers/net/bnxt/bnxt_txq.h b/drivers/net/bnxt/bnxt_txq.h
index a0d4678d9d..9190e3f731 100644
--- a/drivers/net/bnxt/bnxt_txq.h
+++ b/drivers/net/bnxt/bnxt_txq.h
@@ -32,6 +32,7 @@ struct bnxt_tx_queue {
 
 	unsigned int		cp_nr_rings;
 	struct bnxt_cp_ring_info	*cp_ring;
+	struct bnxt_cp_ring_info        *nq_ring;
 	const struct rte_memzone *mz;
 	struct rte_mbuf **free;
 };
diff --git a/drivers/net/bnxt/bnxt_txr.c b/drivers/net/bnxt/bnxt_txr.c
index 4bb177f7e0..124186e8f5 100644
--- a/drivers/net/bnxt/bnxt_txr.c
+++ b/drivers/net/bnxt/bnxt_txr.c
@@ -57,6 +57,7 @@ int bnxt_init_one_tx_ring(struct bnxt_tx_queue *txq)
 int bnxt_init_tx_ring_struct(struct bnxt_tx_queue *txq, unsigned int socket_id)
 {
 	struct bnxt_cp_ring_info *cpr;
+	struct bnxt_cp_ring_info *nqr;
 	struct bnxt_tx_ring_info *txr;
 	struct bnxt_ring *ring;
 
@@ -100,6 +101,30 @@ int bnxt_init_tx_ring_struct(struct bnxt_tx_queue *txq, unsigned int socket_id)
 	ring->vmem_size = 0;
 	ring->vmem = NULL;
 
+	if (BNXT_HAS_NQ(txq->bp)) {
+		nqr = rte_zmalloc_socket("bnxt_tx_ring_nq",
+					 sizeof(struct bnxt_cp_ring_info),
+					 RTE_CACHE_LINE_SIZE, socket_id);
+		if (nqr == NULL)
+			return -ENOMEM;
+
+		txq->nq_ring = nqr;
+
+		ring = rte_zmalloc_socket("bnxt_tx_ring_struct",
+					  sizeof(struct bnxt_ring),
+					  RTE_CACHE_LINE_SIZE, socket_id);
+		if (ring == NULL)
+			return -ENOMEM;
+
+		nqr->cp_ring_struct = ring;
+		ring->ring_size = txr->tx_ring_struct->ring_size;
+		ring->ring_mask = ring->ring_size - 1;
+		ring->bd = (void *)nqr->cp_desc_ring;
+		ring->bd_dma = nqr->cp_desc_mapping;
+		ring->vmem_size = 0;
+		ring->vmem = NULL;
+	}
+
 	return 0;
 }