X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fbnxt%2Fbnxt_ring.c;h=7940d489a102c00ca4f15f70d78743bc414264b2;hb=7e8d5583f7d34bcf7fe8fe9a5806b7d8366ded27;hp=9b19459b659a34ef94cc36dadd15bb758a34c544;hpb=fe7848521581926a2edb8dedc5720d0d6f0af899;p=dpdk.git

diff --git a/drivers/net/bnxt/bnxt_ring.c b/drivers/net/bnxt/bnxt_ring.c
index 9b19459b65..7940d489a1 100644
--- a/drivers/net/bnxt/bnxt_ring.c
+++ b/drivers/net/bnxt/bnxt_ring.c
@@ -1,14 +1,14 @@
 /* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2014-2018 Broadcom
+ * Copyright(c) 2014-2021 Broadcom
  * All rights reserved.
  */
 
 #include <rte_bitmap.h>
 #include <rte_memzone.h>
+#include <rte_malloc.h>
 #include <unistd.h>
 
 #include "bnxt.h"
-#include "bnxt_cpr.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ring.h"
 #include "bnxt_rxq.h"
@@ -38,13 +38,44 @@ void bnxt_free_ring(struct bnxt_ring *ring)
  * Ring groups
  */
 
-int bnxt_init_ring_grps(struct bnxt *bp)
+static void bnxt_init_ring_grps(struct bnxt *bp)
 {
 	unsigned int i;
 
 	for (i = 0; i < bp->max_ring_grps; i++)
 		memset(&bp->grp_info[i], (uint8_t)HWRM_NA_SIGNATURE,
 		       sizeof(struct bnxt_ring_grp_info));
+}
+
+int bnxt_alloc_ring_grps(struct bnxt *bp)
+{
+	if (bp->max_tx_rings == 0) {
+		PMD_DRV_LOG(ERR, "No TX rings available!\n");
+		return -EBUSY;
+	}
+
+	/* THOR does not support ring groups.
+	 * But we will use the array to save RSS context IDs.
+	 */
+	if (BNXT_CHIP_P5(bp)) {
+		bp->max_ring_grps = BNXT_MAX_RSS_CTXTS_P5;
+	} 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");
+		return -ENOSPC;
+	}
+
+	if (BNXT_HAS_RING_GRPS(bp)) {
+		bp->grp_info = rte_zmalloc("bnxt_grp_info",
+					   sizeof(*bp->grp_info) *
+					   bp->max_ring_grps, 0);
+		if (!bp->grp_info) {
+			PMD_DRV_LOG(ERR,
+				    "Failed to alloc grp info tbl.\n");
+			return -ENOMEM;
+		}
+		bnxt_init_ring_grps(bp);
+	}
 
 	return 0;
 }
@@ -63,7 +94,7 @@ int bnxt_init_ring_grps(struct bnxt *bp)
  * tx bd ring - Only non-zero length if tx_ring_info is not NULL
  * rx bd ring - Only non-zero length if rx_ring_info is not NULL
  */
-int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
+int bnxt_alloc_rings(struct bnxt *bp, unsigned int socket_id, uint16_t qidx,
 			    struct bnxt_tx_queue *txq,
 			    struct bnxt_rx_queue *rxq,
 			    struct bnxt_cp_ring_info *cp_ring_info,
@@ -73,15 +104,19 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 	struct bnxt_ring *cp_ring = cp_ring_info->cp_ring_struct;
 	struct bnxt_rx_ring_info *rx_ring_info = rxq ? rxq->rx_ring : NULL;
 	struct bnxt_tx_ring_info *tx_ring_info = txq ? txq->tx_ring : NULL;
-	struct bnxt_ring *tx_ring;
-	struct bnxt_ring *rx_ring;
-	struct rte_pci_device *pdev = bp->pdev;
 	uint64_t rx_offloads = bp->eth_dev->data->dev_conf.rxmode.offloads;
+	int ag_ring_start, ag_bitmap_start, tpa_info_start;
+	int ag_vmem_start, cp_ring_start, nq_ring_start;
+	int total_alloc_len, rx_ring_start, rx_ring_len;
+	struct rte_pci_device *pdev = bp->pdev;
+	struct bnxt_ring *tx_ring, *rx_ring;
 	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 ag_bitmap_len =  0;
+	int tpa_info_len = 0;
+	int ag_vmem_len = 0;
+	int ag_ring_len = 0;
 
 	int stats_len = (tx_ring_info || rx_ring_info) ?
 	    RTE_CACHE_LINE_ROUNDUP(sizeof(struct hwrm_stat_ctx_query_output) -
@@ -92,7 +127,7 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 	int cp_vmem_len = RTE_CACHE_LINE_ROUNDUP(cp_ring->vmem_size);
 	cp_vmem_len = RTE_ALIGN(cp_vmem_len, 128);
 
-	int nq_vmem_len = BNXT_CHIP_THOR(bp) ?
+	int nq_vmem_len = nq_ring_info ?
 		RTE_CACHE_LINE_ROUNDUP(cp_ring->vmem_size) : 0;
 	nq_vmem_len = RTE_ALIGN(nq_vmem_len, 128);
 
@@ -109,14 +144,12 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 		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;
+	if (bnxt_need_agg_ring(bp->eth_dev))
+		ag_vmem_len = rx_ring_info && rx_ring_info->ag_ring_struct ?
+			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);
 
@@ -126,48 +159,55 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 	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 nq_ring_len = nq_ring_info ? cp_ring_len : 0;
 
 	int tx_ring_start = nq_ring_start + nq_ring_len;
+	tx_ring_start = RTE_ALIGN(tx_ring_start, 4096);
 	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 ?
+	rx_ring_start = tx_ring_start + tx_ring_len;
+	rx_ring_start = RTE_ALIGN(rx_ring_start, 4096);
+	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);
+	ag_ring_start = rx_ring_start + rx_ring_len;
+	ag_ring_start = RTE_ALIGN(ag_ring_start, 4096);
+
+	if (bnxt_need_agg_ring(bp->eth_dev)) {
+		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 ?
+		ag_bitmap_len =  rx_ring_info ?
 		RTE_CACHE_LINE_ROUNDUP(rte_bitmap_get_memory_footprint(
 			rx_ring_info->rx_ring_struct->ring_size *
 			AGG_RING_SIZE_FACTOR)) : 0;
 
-	int tpa_info_start = ag_bitmap_start + ag_bitmap_len;
-	int tpa_info_len = rx_ring_info ?
-		RTE_CACHE_LINE_ROUNDUP(BNXT_TPA_MAX *
-				       sizeof(struct bnxt_tpa_info)) : 0;
+		if (rx_ring_info && (rx_offloads & RTE_ETH_RX_OFFLOAD_TCP_LRO)) {
+			int tpa_max = BNXT_TPA_MAX_AGGS(bp);
+
+			tpa_info_len = tpa_max * sizeof(struct bnxt_tpa_info);
+			tpa_info_len = RTE_CACHE_LINE_ROUNDUP(tpa_info_len);
+		}
+	}
 
-	int total_alloc_len = tpa_info_start;
-	if (rx_offloads & DEV_RX_OFFLOAD_TCP_LRO)
-		total_alloc_len += tpa_info_len;
+	ag_bitmap_start = ag_ring_start + ag_ring_len;
+	tpa_info_start = ag_bitmap_start + ag_bitmap_len;
+	total_alloc_len = tpa_info_start + tpa_info_len;
 
 	snprintf(mz_name, RTE_MEMZONE_NAMESIZE,
-		 "bnxt_%04x:%02x:%02x:%02x-%04x_%s", pdev->addr.domain,
+		 "bnxt_" PCI_PRI_FMT "-%04x_%s", pdev->addr.domain,
 		 pdev->addr.bus, pdev->addr.devid, pdev->addr.function, qidx,
 		 suffix);
 	mz_name[RTE_MEMZONE_NAMESIZE - 1] = 0;
 	mz = rte_memzone_lookup(mz_name);
 	if (!mz) {
 		mz = rte_memzone_reserve_aligned(mz_name, total_alloc_len,
-				SOCKET_ID_ANY,
+				socket_id,
 				RTE_MEMZONE_2MB |
 				RTE_MEMZONE_SIZE_HINT_ONLY |
 				RTE_MEMZONE_IOVA_CONTIG,
@@ -176,23 +216,7 @@ 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_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,
-			"unable to map ring address to physical memory\n");
-			return -ENOMEM;
-		}
-	}
 
 	if (tx_ring_info) {
 		txq->mz = mz;
@@ -210,7 +234,7 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 			tx_ring->vmem =
 			    (void **)((char *)mz->addr + tx_vmem_start);
 			tx_ring_info->tx_buf_ring =
-			    (struct bnxt_sw_tx_bd *)tx_ring->vmem;
+			    (struct rte_mbuf **)tx_ring->vmem;
 		}
 	}
 
@@ -231,37 +255,39 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 			rx_ring->vmem =
 			    (void **)((char *)mz->addr + rx_vmem_start);
 			rx_ring_info->rx_buf_ring =
-			    (struct bnxt_sw_rx_bd *)rx_ring->vmem;
+			    (struct rte_mbuf **)rx_ring->vmem;
 		}
 
-		rx_ring = rx_ring_info->ag_ring_struct;
-
-		rx_ring->bd = ((char *)mz->addr + ag_ring_start);
-		rx_ring_info->ag_desc_ring =
-		    (struct rx_prod_pkt_bd *)rx_ring->bd;
-		rx_ring->bd_dma = mz->iova + ag_ring_start;
-		rx_ring_info->ag_desc_mapping = rx_ring->bd_dma;
-		rx_ring->mem_zone = (const void *)mz;
-
-		if (!rx_ring->bd)
-			return -ENOMEM;
-		if (rx_ring->vmem_size) {
-			rx_ring->vmem =
-			    (void **)((char *)mz->addr + ag_vmem_start);
-			rx_ring_info->ag_buf_ring =
-			    (struct bnxt_sw_rx_bd *)rx_ring->vmem;
+		if (bnxt_need_agg_ring(bp->eth_dev)) {
+			rx_ring = rx_ring_info->ag_ring_struct;
+
+			rx_ring->bd = ((char *)mz->addr + ag_ring_start);
+			rx_ring_info->ag_desc_ring =
+			    (struct rx_prod_pkt_bd *)rx_ring->bd;
+			rx_ring->bd_dma = mz->iova + ag_ring_start;
+			rx_ring_info->ag_desc_mapping = rx_ring->bd_dma;
+			rx_ring->mem_zone = (const void *)mz;
+
+			if (!rx_ring->bd)
+				return -ENOMEM;
+			if (rx_ring->vmem_size) {
+				rx_ring->vmem =
+				    (void **)((char *)mz->addr + ag_vmem_start);
+				rx_ring_info->ag_buf_ring =
+				    (struct rte_mbuf **)rx_ring->vmem;
+			}
+
+			rx_ring_info->ag_bitmap =
+			    rte_bitmap_init(rx_ring_info->rx_ring_struct->ring_size *
+					    AGG_RING_SIZE_FACTOR, (uint8_t *)mz->addr +
+					    ag_bitmap_start, ag_bitmap_len);
+
+			/* TPA info */
+			if (rx_offloads & RTE_ETH_RX_OFFLOAD_TCP_LRO)
+				rx_ring_info->tpa_info =
+					((struct bnxt_tpa_info *)
+					 ((char *)mz->addr + tpa_info_start));
 		}
-
-		rx_ring_info->ag_bitmap =
-		    rte_bitmap_init(rx_ring_info->rx_ring_struct->ring_size *
-				    AGG_RING_SIZE_FACTOR, (uint8_t *)mz->addr +
-				    ag_bitmap_start, ag_bitmap_len);
-
-		/* TPA info */
-		if (rx_offloads & DEV_RX_OFFLOAD_TCP_LRO)
-			rx_ring_info->tpa_info =
-				((struct bnxt_tpa_info *)((char *)mz->addr +
-							  tpa_info_start));
 	}
 
 	cp_ring->bd = ((char *)mz->addr + cp_ring_start);
@@ -280,7 +306,7 @@ int bnxt_alloc_rings(struct bnxt *bp, uint16_t qidx,
 	}
 	cp_ring_info->hw_stats_ctx_id = HWRM_NA_SIGNATURE;
 
-	if (BNXT_HAS_NQ(bp)) {
+	if (nq_ring_info) {
 		struct bnxt_ring *nq_ring = nq_ring_info->cp_ring_struct;
 
 		nq_ring->bd = (char *)mz->addr + nq_ring_start;
@@ -322,13 +348,11 @@ static void bnxt_set_db(struct bnxt *bp,
 			struct bnxt_db_info *db,
 			uint32_t ring_type,
 			uint32_t map_idx,
-			uint32_t fid)
+			uint32_t fid,
+			uint32_t ring_mask)
 {
-	if (BNXT_CHIP_THOR(bp)) {
-		if (BNXT_PF(bp))
-			db->doorbell = (char *)bp->doorbell_base + 0x10000;
-		else
-			db->doorbell = (char *)bp->doorbell_base + 0x4000;
+	if (BNXT_CHIP_P5(bp)) {
+		int db_offset = DB_PF_OFFSET;
 		switch (ring_type) {
 		case HWRM_RING_ALLOC_INPUT_RING_TYPE_TX:
 			db->db_key64 = DBR_PATH_L2 | DBR_TYPE_SQ;
@@ -341,9 +365,17 @@ static void bnxt_set_db(struct bnxt *bp,
 			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;
+			db->db_key64 = DBR_PATH_L2;
 			break;
 		}
+		if (BNXT_CHIP_SR2(bp)) {
+			db->db_key64 |= DBR_VALID;
+			db_offset = bp->legacy_db_size;
+		} else if (BNXT_VF(bp)) {
+			db_offset = DB_VF_OFFSET;
+		}
+
+		db->doorbell = (char *)bp->doorbell_base + db_offset;
 		db->db_key64 |= (uint64_t)fid << DBR_XID_SFT;
 		db->db_64 = true;
 	} else {
@@ -361,14 +393,22 @@ static void bnxt_set_db(struct bnxt *bp,
 		}
 		db->db_64 = false;
 	}
+	db->db_ring_mask = ring_mask;
+
+	if (BNXT_CHIP_SR2(bp)) {
+		db->db_epoch_mask = db->db_ring_mask + 1;
+		db->db_epoch_shift = DBR_EPOCH_SFT -
+					rte_log2_u32(db->db_epoch_mask);
+	}
 }
 
 static int bnxt_alloc_cmpl_ring(struct bnxt *bp, int queue_index,
-				struct bnxt_cp_ring_info *cpr,
-				struct bnxt_cp_ring_info *nqr)
+				struct bnxt_cp_ring_info *cpr)
 {
 	struct bnxt_ring *cp_ring = cpr->cp_ring_struct;
 	uint32_t nq_ring_id = HWRM_NA_SIGNATURE;
+	int cp_ring_index = queue_index + BNXT_RX_VEC_START;
+	struct bnxt_cp_ring_info *nqr = bp->rxtx_nq_ring;
 	uint8_t ring_type;
 	int rc = 0;
 
@@ -383,43 +423,99 @@ static int bnxt_alloc_cmpl_ring(struct bnxt *bp, int queue_index,
 		}
 	}
 
-	rc = bnxt_hwrm_ring_alloc(bp, cp_ring, ring_type, queue_index,
-				  HWRM_NA_SIGNATURE, nq_ring_id);
+	rc = bnxt_hwrm_ring_alloc(bp, cp_ring, ring_type, cp_ring_index,
+				  HWRM_NA_SIGNATURE, nq_ring_id, 0);
 	if (rc)
 		return rc;
 
-	cpr->cp_cons = 0;
-	bnxt_set_db(bp, &cpr->cp_db, ring_type, queue_index,
-		    cp_ring->fw_ring_id);
+	cpr->cp_raw_cons = 0;
+	bnxt_set_db(bp, &cpr->cp_db, ring_type, cp_ring_index,
+		    cp_ring->fw_ring_id, cp_ring->ring_mask);
 	bnxt_db_cq(cpr);
 
 	return 0;
 }
 
-static int bnxt_alloc_nq_ring(struct bnxt *bp, int queue_index,
-			      struct bnxt_cp_ring_info *nqr)
+int bnxt_alloc_rxtx_nq_ring(struct bnxt *bp)
 {
-	struct bnxt_ring *nq_ring = nqr->cp_ring_struct;
+	struct bnxt_cp_ring_info *nqr;
+	struct bnxt_ring *ring;
+	int ring_index = BNXT_NUM_ASYNC_CPR(bp);
 	uint8_t ring_type;
 	int rc = 0;
 
-	if (!BNXT_HAS_NQ(bp))
-		return -EINVAL;
+	if (!BNXT_HAS_NQ(bp) || bp->rxtx_nq_ring)
+		return 0;
+
+	nqr = rte_zmalloc_socket("nqr",
+				 sizeof(struct bnxt_cp_ring_info),
+				 RTE_CACHE_LINE_SIZE,
+				 bp->eth_dev->device->numa_node);
+	if (nqr == NULL)
+		return -ENOMEM;
+
+	ring = rte_zmalloc_socket("bnxt_cp_ring_struct",
+				  sizeof(struct bnxt_ring),
+				  RTE_CACHE_LINE_SIZE,
+				  bp->eth_dev->device->numa_node);
+	if (ring == NULL) {
+		rte_free(nqr);
+		return -ENOMEM;
+	}
+
+	ring->bd = (void *)nqr->cp_desc_ring;
+	ring->bd_dma = nqr->cp_desc_mapping;
+	ring->ring_size = rte_align32pow2(DEFAULT_CP_RING_SIZE);
+	ring->ring_mask = ring->ring_size - 1;
+	ring->vmem_size = 0;
+	ring->vmem = NULL;
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+
+	nqr->cp_ring_struct = ring;
+	rc = bnxt_alloc_rings(bp, bp->eth_dev->device->numa_node, 0, NULL,
+			      NULL, nqr, NULL, "l2_nqr");
+	if (rc) {
+		rte_free(ring);
+		rte_free(nqr);
+		return -ENOMEM;
+	}
 
 	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)
+	rc = bnxt_hwrm_ring_alloc(bp, ring, ring_type, ring_index,
+				  HWRM_NA_SIGNATURE, HWRM_NA_SIGNATURE, 0);
+	if (rc) {
+		rte_free(ring);
+		rte_free(nqr);
 		return rc;
+	}
 
-	bnxt_set_db(bp, &nqr->cp_db, ring_type, queue_index,
-		    nq_ring->fw_ring_id);
+	bnxt_set_db(bp, &nqr->cp_db, ring_type, ring_index,
+		    ring->fw_ring_id, ring->ring_mask);
 	bnxt_db_nq(nqr);
 
+	bp->rxtx_nq_ring = nqr;
+
 	return 0;
 }
 
+/* Free RX/TX NQ ring.  */
+void bnxt_free_rxtx_nq_ring(struct bnxt *bp)
+{
+	struct bnxt_cp_ring_info *nqr = bp->rxtx_nq_ring;
+
+	if (!nqr)
+		return;
+
+	bnxt_free_nq_ring(bp, nqr);
+
+	bnxt_free_ring(nqr->cp_ring_struct);
+	rte_free(nqr->cp_ring_struct);
+	nqr->cp_ring_struct = NULL;
+	rte_free(nqr);
+	bp->rxtx_nq_ring = NULL;
+}
+
 static int bnxt_alloc_rx_ring(struct bnxt *bp, int queue_index)
 {
 	struct bnxt_rx_queue *rxq = bp->rx_queues[queue_index];
@@ -434,15 +530,16 @@ static int bnxt_alloc_rx_ring(struct bnxt *bp, int queue_index)
 
 	rc = bnxt_hwrm_ring_alloc(bp, ring, ring_type,
 				  queue_index, cpr->hw_stats_ctx_id,
-				  cp_ring->fw_ring_id);
+				  cp_ring->fw_ring_id, 0);
 	if (rc)
 		return rc;
 
-	rxr->rx_prod = 0;
+	rxr->rx_raw_prod = 0;
 	if (BNXT_HAS_RING_GRPS(bp))
 		bp->grp_info[queue_index].rx_fw_ring_id = ring->fw_ring_id;
-	bnxt_set_db(bp, &rxr->rx_db, ring_type, queue_index, ring->fw_ring_id);
-	bnxt_db_write(&rxr->rx_db, rxr->rx_prod);
+	bnxt_set_db(bp, &rxr->rx_db, ring_type, queue_index, ring->fw_ring_id,
+		    ring->ring_mask);
+	bnxt_db_write(&rxr->rx_db, rxr->rx_raw_prod);
 
 	return 0;
 }
@@ -459,9 +556,12 @@ static int bnxt_alloc_rx_agg_ring(struct bnxt *bp, int queue_index)
 	uint8_t ring_type;
 	int rc = 0;
 
+	if (!bnxt_need_agg_ring(bp->eth_dev))
+		return 0;
+
 	ring->fw_rx_ring_id = rxr->rx_ring_struct->fw_ring_id;
 
-	if (BNXT_CHIP_THOR(bp)) {
+	if (BNXT_CHIP_P5(bp)) {
 		ring_type = HWRM_RING_ALLOC_INPUT_RING_TYPE_RX_AGG;
 		hw_stats_ctx_id = cpr->hw_stats_ctx_id;
 	} else {
@@ -469,16 +569,17 @@ static int bnxt_alloc_rx_agg_ring(struct bnxt *bp, int queue_index)
 	}
 
 	rc = bnxt_hwrm_ring_alloc(bp, ring, ring_type, map_idx,
-				  hw_stats_ctx_id, cp_ring->fw_ring_id);
+				  hw_stats_ctx_id, cp_ring->fw_ring_id, 0);
 
 	if (rc)
 		return rc;
 
-	rxr->ag_prod = 0;
+	rxr->ag_raw_prod = 0;
 	if (BNXT_HAS_RING_GRPS(bp))
 		bp->grp_info[queue_index].ag_fw_ring_id = ring->fw_ring_id;
-	bnxt_set_db(bp, &rxr->ag_db, ring_type, map_idx, ring->fw_ring_id);
-	bnxt_db_write(&rxr->ag_db, rxr->ag_prod);
+	bnxt_set_db(bp, &rxr->ag_db, ring_type, map_idx, ring->fw_ring_id,
+		    ring->ring_mask);
+	bnxt_db_write(&rxr->ag_db, rxr->ag_raw_prod);
 
 	return 0;
 }
@@ -488,16 +589,27 @@ 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;
+	struct bnxt_coal coal;
+	int rc;
 
-	if (BNXT_HAS_NQ(bp)) {
-		if (bnxt_alloc_nq_ring(bp, queue_index, nqr))
-			goto err_out;
-	}
+	/*
+	 * Storage for the cp ring is allocated based on worst-case
+	 * usage, the actual size to be used by hw is computed here.
+	 */
+	cp_ring->ring_size = rxr->rx_ring_struct->ring_size * 2;
+
+	if (bnxt_need_agg_ring(bp->eth_dev))
+		cp_ring->ring_size *= AGG_RING_SIZE_FACTOR;
+
+	cp_ring->ring_mask = cp_ring->ring_size - 1;
 
-	if (bnxt_alloc_cmpl_ring(bp, queue_index, cpr, nqr))
+	rc = bnxt_alloc_cmpl_ring(bp, queue_index, cpr);
+	if (rc)
+		goto err_out;
+
+	rc = bnxt_hwrm_stat_ctx_alloc(bp, cpr);
+	if (rc)
 		goto err_out;
 
 	if (BNXT_HAS_RING_GRPS(bp)) {
@@ -505,49 +617,99 @@ int bnxt_alloc_hwrm_rx_ring(struct bnxt *bp, int queue_index)
 		bp->grp_info[queue_index].cp_fw_ring_id = cp_ring->fw_ring_id;
 	}
 
-	if (!queue_index) {
+	bnxt_init_dflt_coal(&coal);
+	bnxt_hwrm_set_ring_coal(bp, &coal, cp_ring->fw_ring_id);
+
+	if (!BNXT_NUM_ASYNC_CPR(bp) && !queue_index) {
 		/*
-		 * In order to save completion resources, use the first
-		 * completion ring from PF or VF as the default completion ring
-		 * for async event and HWRM forward response handling.
+		 * If a dedicated async event completion ring is not enabled,
+		 * use the first completion ring from PF or VF as the default
+		 * completion ring for async event handling.
 		 */
-		bp->def_cp_ring = cpr;
+		bp->async_cp_ring = cpr;
 		rc = bnxt_hwrm_set_async_event_cr(bp);
 		if (rc)
 			goto err_out;
 	}
 
-	if (bnxt_alloc_rx_ring(bp, queue_index))
+	rc = bnxt_alloc_rx_ring(bp, queue_index);
+	if (rc)
 		goto err_out;
 
-	if (bnxt_alloc_rx_agg_ring(bp, queue_index))
+	rc = bnxt_alloc_rx_agg_ring(bp, queue_index);
+	if (rc)
 		goto err_out;
 
-	rxq->rx_buf_use_size = BNXT_MAX_MTU + RTE_ETHER_HDR_LEN +
-		RTE_ETHER_CRC_LEN + (2 * VLAN_TAG_SIZE);
+	if (BNXT_HAS_RING_GRPS(bp)) {
+		rc = bnxt_hwrm_ring_grp_alloc(bp, queue_index);
+		if (rc)
+			goto err_out;
+	}
 
-	if (bp->eth_dev->data->rx_queue_state[queue_index] ==
-	    RTE_ETH_QUEUE_STATE_STARTED) {
+	if (rxq->rx_started) {
 		if (bnxt_init_one_rx_ring(rxq)) {
-			RTE_LOG(ERR, PMD,
-				"bnxt_init_one_rx_ring failed!\n");
-			bnxt_rx_queue_release_op(rxq);
+			PMD_DRV_LOG(ERR, "bnxt_init_one_rx_ring failed!\n");
+			bnxt_rx_queue_release_op(bp->eth_dev, queue_index);
 			rc = -ENOMEM;
 			goto err_out;
 		}
-		bnxt_db_write(&rxr->rx_db, rxr->rx_prod);
-		bnxt_db_write(&rxr->ag_db, rxr->ag_prod);
+		bnxt_db_write(&rxr->rx_db, rxr->rx_raw_prod);
+		if (bnxt_need_agg_ring(bp->eth_dev))
+			bnxt_db_write(&rxr->ag_db, rxr->ag_raw_prod);
 	}
 	rxq->index = queue_index;
-	PMD_DRV_LOG(INFO,
-		    "queue %d, rx_deferred_start %d, state %d!\n",
-		    queue_index, rxq->rx_deferred_start,
-		    bp->eth_dev->data->rx_queue_state[queue_index]);
+#if defined(RTE_ARCH_X86) || defined(RTE_ARCH_ARM64)
+	bnxt_rxq_vec_setup(rxq);
+#endif
+
+	return 0;
 
 err_out:
+	PMD_DRV_LOG(ERR,
+		    "Failed to allocate receive queue %d, rc %d.\n",
+		    queue_index, rc);
 	return rc;
 }
 
+/* Initialise all rings to -1, its used to free rings later if allocation
+ * of few rings fails.
+ */
+static void bnxt_init_all_rings(struct bnxt *bp)
+{
+	unsigned int i = 0;
+	struct bnxt_rx_queue *rxq;
+	struct bnxt_ring *cp_ring;
+	struct bnxt_ring *ring;
+	struct bnxt_rx_ring_info *rxr;
+	struct bnxt_tx_queue *txq;
+
+	for (i = 0; i < bp->rx_cp_nr_rings; i++) {
+		rxq = bp->rx_queues[i];
+		/* Rx-compl */
+		cp_ring = rxq->cp_ring->cp_ring_struct;
+		cp_ring->fw_ring_id = INVALID_HW_RING_ID;
+		/* Rx-Reg */
+		rxr = rxq->rx_ring;
+		ring = rxr->rx_ring_struct;
+		ring->fw_ring_id = INVALID_HW_RING_ID;
+		/* Rx-AGG */
+		if (bnxt_need_agg_ring(bp->eth_dev)) {
+			ring = rxr->ag_ring_struct;
+			if (ring != NULL)
+				ring->fw_ring_id = INVALID_HW_RING_ID;
+		}
+	}
+	for (i = 0; i < bp->tx_cp_nr_rings; i++) {
+		txq = bp->tx_queues[i];
+		/* Tx cmpl */
+		cp_ring = txq->cp_ring->cp_ring_struct;
+		cp_ring->fw_ring_id = INVALID_HW_RING_ID;
+		/*Tx Ring */
+		ring = txq->tx_ring->tx_ring_struct;
+		ring->fw_ring_id = INVALID_HW_RING_ID;
+	}
+}
+
 /* ring_grp usage:
  * [0] = default completion ring
  * [1 -> +rx_cp_nr_rings] = rx_cp, rx rings
@@ -557,98 +719,188 @@ int bnxt_alloc_hwrm_rings(struct bnxt *bp)
 {
 	struct bnxt_coal coal;
 	unsigned int i;
-	uint8_t ring_type;
 	int rc = 0;
 
 	bnxt_init_dflt_coal(&coal);
+	bnxt_init_all_rings(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;
+		unsigned int soc_id = bp->eth_dev->device->numa_node;
+		struct bnxt_rx_queue *rxq  = bp->rx_queues[i];
 		struct bnxt_rx_ring_info *rxr = rxq->rx_ring;
-
-		if (BNXT_HAS_NQ(bp)) {
-			if (bnxt_alloc_nq_ring(bp, i, nqr))
-				goto err_out;
+		struct bnxt_ring *ring;
+
+		if (bnxt_need_agg_ring(bp->eth_dev)) {
+			ring = rxr->ag_ring_struct;
+			if (ring == NULL) {
+				bnxt_free_rxq_mem(rxq);
+
+				rc = bnxt_init_rx_ring_struct(rxq, soc_id);
+				if (rc)
+					goto err_out;
+
+				rc = bnxt_alloc_rings(bp, soc_id,
+						      i, NULL, rxq,
+						      rxq->cp_ring, NULL,
+						      "rxr");
+				if (rc)
+					goto err_out;
+			}
 		}
 
-		if (bnxt_alloc_cmpl_ring(bp, i, cpr, nqr))
+		rc = bnxt_alloc_hwrm_rx_ring(bp, i);
+		if (rc)
 			goto err_out;
+	}
 
-		if (BNXT_HAS_RING_GRPS(bp)) {
-			bp->grp_info[i].fw_stats_ctx = cpr->hw_stats_ctx_id;
-			bp->grp_info[i].cp_fw_ring_id = cp_ring->fw_ring_id;
-		}
+	/* If something is wrong with Rx ring alloc, skip Tx ring alloc */
+	for (i = 0; i < bp->tx_cp_nr_rings; i++) {
+		rc = bnxt_alloc_hwrm_tx_ring(bp, i);
+		if (rc)
+			goto err_out;
+	}
 
-		bnxt_hwrm_set_ring_coal(bp, &coal, cp_ring->fw_ring_id);
-
-		if (!i) {
-			/*
-			 * In order to save completion resource, use the first
-			 * completion ring from PF or VF as the default
-			 * completion ring for async event & HWRM
-			 * forward response handling.
-			 */
-			bp->def_cp_ring = cpr;
-			rc = bnxt_hwrm_set_async_event_cr(bp);
-			if (rc)
-				goto err_out;
-		}
+err_out:
+	return rc;
+}
 
-		if (bnxt_alloc_rx_ring(bp, i))
-			goto err_out;
+/* Allocate dedicated async completion ring. */
+int bnxt_alloc_async_cp_ring(struct bnxt *bp)
+{
+	struct bnxt_cp_ring_info *cpr = bp->async_cp_ring;
+	struct bnxt_ring *cp_ring;
+	uint8_t ring_type;
+	int rc;
 
-		if (bnxt_alloc_rx_agg_ring(bp, i))
-			goto err_out;
+	if (BNXT_NUM_ASYNC_CPR(bp) == 0 || cpr == NULL)
+		return 0;
 
-		rxq->rx_buf_use_size = BNXT_MAX_MTU + RTE_ETHER_HDR_LEN +
-					RTE_ETHER_CRC_LEN + (2 * VLAN_TAG_SIZE);
-		if (bnxt_init_one_rx_ring(rxq)) {
-			PMD_DRV_LOG(ERR, "bnxt_init_one_rx_ring failed!\n");
-			bnxt_rx_queue_release_op(rxq);
-			return -ENOMEM;
-		}
-		bnxt_db_write(&rxr->rx_db, rxr->rx_prod);
-		bnxt_db_write(&rxr->ag_db, rxr->ag_prod);
-		rxq->index = i;
-#ifdef RTE_ARCH_X86
-		bnxt_rxq_vec_setup(rxq);
-#endif
-	}
+	cp_ring = cpr->cp_ring_struct;
 
-	for (i = 0; i < bp->tx_cp_nr_rings; i++) {
-		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_HAS_NQ(bp)) {
-			if (bnxt_alloc_nq_ring(bp, idx, nqr))
-				goto err_out;
-		}
+	if (BNXT_HAS_NQ(bp))
+		ring_type = HWRM_RING_ALLOC_INPUT_RING_TYPE_NQ;
+	else
+		ring_type = HWRM_RING_ALLOC_INPUT_RING_TYPE_L2_CMPL;
 
-		if (bnxt_alloc_cmpl_ring(bp, idx, cpr, nqr))
-			goto err_out;
+	rc = bnxt_hwrm_ring_alloc(bp, cp_ring, ring_type, 0,
+				  HWRM_NA_SIGNATURE, HWRM_NA_SIGNATURE, 0);
 
-		/* Tx ring */
-		ring_type = HWRM_RING_ALLOC_INPUT_RING_TYPE_TX;
-		rc = bnxt_hwrm_ring_alloc(bp, ring,
-					  ring_type,
-					  i, cpr->hw_stats_ctx_id,
-					  cp_ring->fw_ring_id);
-		if (rc)
-			goto err_out;
+	if (rc)
+		return rc;
 
-		bnxt_set_db(bp, &txr->tx_db, ring_type, i, ring->fw_ring_id);
-		txq->index = idx;
-		bnxt_hwrm_set_ring_coal(bp, &coal, cp_ring->fw_ring_id);
+	cpr->cp_raw_cons = 0;
+	bnxt_set_db(bp, &cpr->cp_db, ring_type, 0,
+		    cp_ring->fw_ring_id, cp_ring->ring_mask);
+
+	if (BNXT_HAS_NQ(bp))
+		bnxt_db_nq(cpr);
+	else
+		bnxt_db_cq(cpr);
+
+	return bnxt_hwrm_set_async_event_cr(bp);
+}
+
+/* Free dedicated async completion ring. */
+void bnxt_free_async_cp_ring(struct bnxt *bp)
+{
+	struct bnxt_cp_ring_info *cpr = bp->async_cp_ring;
+
+	if (BNXT_NUM_ASYNC_CPR(bp) == 0 || cpr == NULL)
+		return;
+
+	if (BNXT_HAS_NQ(bp))
+		bnxt_free_nq_ring(bp, cpr);
+	else
+		bnxt_free_cp_ring(bp, cpr);
+
+	bnxt_free_ring(cpr->cp_ring_struct);
+	rte_free(cpr->cp_ring_struct);
+	cpr->cp_ring_struct = NULL;
+	rte_free(cpr);
+	bp->async_cp_ring = NULL;
+}
+
+int bnxt_alloc_async_ring_struct(struct bnxt *bp)
+{
+	struct bnxt_cp_ring_info *cpr = NULL;
+	struct bnxt_ring *ring = NULL;
+
+	if (BNXT_NUM_ASYNC_CPR(bp) == 0)
+		return 0;
+
+	cpr = rte_zmalloc_socket("cpr",
+				 sizeof(struct bnxt_cp_ring_info),
+				 RTE_CACHE_LINE_SIZE,
+				 bp->eth_dev->device->numa_node);
+	if (cpr == NULL)
+		return -ENOMEM;
+
+	ring = rte_zmalloc_socket("bnxt_cp_ring_struct",
+				  sizeof(struct bnxt_ring),
+				  RTE_CACHE_LINE_SIZE,
+				  bp->eth_dev->device->numa_node);
+	if (ring == NULL) {
+		rte_free(cpr);
+		return -ENOMEM;
 	}
 
+	ring->bd = (void *)cpr->cp_desc_ring;
+	ring->bd_dma = cpr->cp_desc_mapping;
+	ring->ring_size = rte_align32pow2(DEFAULT_CP_RING_SIZE);
+	ring->ring_mask = ring->ring_size - 1;
+	ring->vmem_size = 0;
+	ring->vmem = NULL;
+
+	bp->async_cp_ring = cpr;
+	cpr->cp_ring_struct = ring;
+
+	return bnxt_alloc_rings(bp, bp->eth_dev->device->numa_node, 0, NULL,
+				NULL, bp->async_cp_ring, NULL, "def_cp");
+}
+
+int bnxt_alloc_hwrm_tx_ring(struct bnxt *bp, int queue_index)
+{
+	struct bnxt_tx_queue *txq = bp->tx_queues[queue_index];
+	struct bnxt_cp_ring_info *cpr = txq->cp_ring;
+	struct bnxt_ring *cp_ring = cpr->cp_ring_struct;
+	struct bnxt_tx_ring_info *txr = txq->tx_ring;
+	struct bnxt_ring *ring = txr->tx_ring_struct;
+	unsigned int idx = queue_index + bp->rx_cp_nr_rings;
+	uint16_t tx_cosq_id = 0;
+	struct bnxt_coal coal;
+	int rc = 0;
+
+	rc = bnxt_alloc_cmpl_ring(bp, idx, cpr);
+	if (rc)
+		goto err_out;
+
+	bnxt_init_dflt_coal(&coal);
+	bnxt_hwrm_set_ring_coal(bp, &coal, cp_ring->fw_ring_id);
+
+	rc = bnxt_hwrm_stat_ctx_alloc(bp, cpr);
+	if (rc)
+		goto err_out;
+
+	if (bp->vnic_cap_flags & BNXT_VNIC_CAP_COS_CLASSIFY)
+		tx_cosq_id = bp->tx_cosq_id[queue_index < bp->max_lltc ? queue_index : 0];
+	else
+		tx_cosq_id = bp->tx_cosq_id[0];
+
+	rc = bnxt_hwrm_ring_alloc(bp, ring,
+				  HWRM_RING_ALLOC_INPUT_RING_TYPE_TX,
+				  queue_index, cpr->hw_stats_ctx_id,
+				  cp_ring->fw_ring_id,
+				  tx_cosq_id);
+	if (rc)
+		goto err_out;
+
+	bnxt_set_db(bp, &txr->tx_db, HWRM_RING_ALLOC_INPUT_RING_TYPE_TX,
+		    queue_index, ring->fw_ring_id,
+		    ring->ring_mask);
+	txq->index = idx;
+
+	return rc;
 err_out:
+	bnxt_free_hwrm_tx_ring(bp, queue_index);
 	return rc;
 }