X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fbnxt%2Fbnxt_rxr.c;h=1f47db97bacd29d82e3ca9d0177e3493246aa587;hb=8522f7b12c146e7fa95728b2f23b4029709e14e6;hp=8489a1c40ab74bba33113177144e4458be34fba8;hpb=daef48efe5e5034dac09f8be9904a59ca15b472e;p=dpdk.git

diff --git a/drivers/net/bnxt/bnxt_rxr.c b/drivers/net/bnxt/bnxt_rxr.c
index 8489a1c40a..1f47db97ba 100644
--- a/drivers/net/bnxt/bnxt_rxr.c
+++ b/drivers/net/bnxt/bnxt_rxr.c
@@ -1,49 +1,24 @@
-/*-
- *   BSD LICENSE
- *
- *   Copyright(c) Broadcom Limited.
- *   All rights reserved.
- *
- *   Redistribution and use in source and binary forms, with or without
- *   modification, are permitted provided that the following conditions
- *   are met:
- *
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in
- *       the documentation and/or other materials provided with the
- *       distribution.
- *     * Neither the name of Broadcom Corporation nor the names of its
- *       contributors may be used to endorse or promote products derived
- *       from this software without specific prior written permission.
- *
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2014-2018 Broadcom
+ * All rights reserved.
  */
 
 #include <inttypes.h>
 #include <stdbool.h>
 
+#include <rte_bitmap.h>
 #include <rte_byteorder.h>
 #include <rte_malloc.h>
 #include <rte_memory.h>
 
 #include "bnxt.h"
-#include "bnxt_cpr.h"
 #include "bnxt_ring.h"
 #include "bnxt_rxr.h"
 #include "bnxt_rxq.h"
 #include "hsi_struct_def_dpdk.h"
+#ifdef RTE_LIBRTE_IEEE1588
+#include "bnxt_hwrm.h"
+#endif
 
 /*
  * RX Ring handling
@@ -64,15 +39,18 @@ static inline int bnxt_alloc_rx_data(struct bnxt_rx_queue *rxq,
 {
 	struct rx_prod_pkt_bd *rxbd = &rxr->rx_desc_ring[prod];
 	struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[prod];
-	struct rte_mbuf *data;
+	struct rte_mbuf *mbuf;
 
-	data = __bnxt_alloc_rx_data(rxq->mb_pool);
-	if (!data)
+	mbuf = __bnxt_alloc_rx_data(rxq->mb_pool);
+	if (!mbuf) {
+		rte_atomic64_inc(&rxq->rx_mbuf_alloc_fail);
 		return -ENOMEM;
+	}
 
-	rx_buf->mbuf = data;
+	rx_buf->mbuf = mbuf;
+	mbuf->data_off = RTE_PKTMBUF_HEADROOM;
 
-	rxbd->addr = rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR(rx_buf->mbuf));
+	rxbd->address = rte_cpu_to_le_64(rte_mbuf_data_iova_default(mbuf));
 
 	return 0;
 }
@@ -83,62 +61,345 @@ static inline int bnxt_alloc_ag_data(struct bnxt_rx_queue *rxq,
 {
 	struct rx_prod_pkt_bd *rxbd = &rxr->ag_desc_ring[prod];
 	struct bnxt_sw_rx_bd *rx_buf = &rxr->ag_buf_ring[prod];
-	struct rte_mbuf *data;
+	struct rte_mbuf *mbuf;
 
-	data = __bnxt_alloc_rx_data(rxq->mb_pool);
-	if (!data)
-		return -ENOMEM;
+	if (rxbd == NULL) {
+		PMD_DRV_LOG(ERR, "Jumbo Frame. rxbd is NULL\n");
+		return -EINVAL;
+	}
 
-	if (rxbd == NULL)
-		RTE_LOG(ERR, PMD, "Jumbo Frame. rxbd is NULL\n");
-	if (rx_buf == NULL)
-		RTE_LOG(ERR, PMD, "Jumbo Frame. rx_buf is NULL\n");
+	if (rx_buf == NULL) {
+		PMD_DRV_LOG(ERR, "Jumbo Frame. rx_buf is NULL\n");
+		return -EINVAL;
+	}
 
+	mbuf = __bnxt_alloc_rx_data(rxq->mb_pool);
+	if (!mbuf) {
+		rte_atomic64_inc(&rxq->rx_mbuf_alloc_fail);
+		return -ENOMEM;
+	}
 
-	rx_buf->mbuf = data;
+	rx_buf->mbuf = mbuf;
+	mbuf->data_off = RTE_PKTMBUF_HEADROOM;
 
-	rxbd->addr = rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR(rx_buf->mbuf));
+	rxbd->address = rte_cpu_to_le_64(rte_mbuf_data_iova_default(mbuf));
 
 	return 0;
 }
 
-#ifdef BNXT_DEBUG
-static void bnxt_reuse_rx_mbuf(struct bnxt_rx_ring_info *rxr, uint16_t cons,
+static inline void bnxt_reuse_rx_mbuf(struct bnxt_rx_ring_info *rxr,
 			       struct rte_mbuf *mbuf)
 {
-	uint16_t prod = rxr->rx_prod;
+	uint16_t prod = RING_NEXT(rxr->rx_ring_struct, rxr->rx_prod);
 	struct bnxt_sw_rx_bd *prod_rx_buf;
-	struct rx_prod_pkt_bd *prod_bd, *cons_bd;
+	struct rx_prod_pkt_bd *prod_bd;
 
 	prod_rx_buf = &rxr->rx_buf_ring[prod];
 
+	RTE_ASSERT(prod_rx_buf->mbuf == NULL);
+	RTE_ASSERT(mbuf != NULL);
+
 	prod_rx_buf->mbuf = mbuf;
 
 	prod_bd = &rxr->rx_desc_ring[prod];
-	cons_bd = &rxr->rx_desc_ring[cons];
 
-	prod_bd->addr = cons_bd->addr;
+	prod_bd->address = rte_cpu_to_le_64(rte_mbuf_data_iova_default(mbuf));
+
+	rxr->rx_prod = prod;
 }
 
-static void bnxt_reuse_ag_mbuf(struct bnxt_rx_ring_info *rxr, uint16_t cons,
-			       struct rte_mbuf *mbuf)
+static inline
+struct rte_mbuf *bnxt_consume_rx_buf(struct bnxt_rx_ring_info *rxr,
+				     uint16_t cons)
 {
-	uint16_t prod = rxr->ag_prod;
-	struct bnxt_sw_rx_bd *prod_rx_buf;
-	struct rx_prod_pkt_bd *prod_bd, *cons_bd;
+	struct bnxt_sw_rx_bd *cons_rx_buf;
+	struct rte_mbuf *mbuf;
 
-	prod_rx_buf = &rxr->ag_buf_ring[prod];
+	cons_rx_buf = &rxr->rx_buf_ring[cons];
+	RTE_ASSERT(cons_rx_buf->mbuf != NULL);
+	mbuf = cons_rx_buf->mbuf;
+	cons_rx_buf->mbuf = NULL;
+	return mbuf;
+}
 
-	prod_rx_buf->mbuf = mbuf;
+static void bnxt_tpa_start(struct bnxt_rx_queue *rxq,
+			   struct rx_tpa_start_cmpl *tpa_start,
+			   struct rx_tpa_start_cmpl_hi *tpa_start1)
+{
+	struct bnxt_rx_ring_info *rxr = rxq->rx_ring;
+	uint16_t agg_id;
+	uint16_t data_cons;
+	struct bnxt_tpa_info *tpa_info;
+	struct rte_mbuf *mbuf;
+
+	agg_id = bnxt_tpa_start_agg_id(rxq->bp, tpa_start);
 
-	prod_bd = &rxr->ag_desc_ring[prod];
-	cons_bd = &rxr->ag_desc_ring[cons];
+	data_cons = tpa_start->opaque;
+	tpa_info = &rxr->tpa_info[agg_id];
 
-	prod_bd->addr = cons_bd->addr;
+	mbuf = bnxt_consume_rx_buf(rxr, data_cons);
+
+	bnxt_reuse_rx_mbuf(rxr, tpa_info->mbuf);
+
+	tpa_info->agg_count = 0;
+	tpa_info->mbuf = mbuf;
+	tpa_info->len = rte_le_to_cpu_32(tpa_start->len);
+
+	mbuf->nb_segs = 1;
+	mbuf->next = NULL;
+	mbuf->pkt_len = rte_le_to_cpu_32(tpa_start->len);
+	mbuf->data_len = mbuf->pkt_len;
+	mbuf->port = rxq->port_id;
+	mbuf->ol_flags = PKT_RX_LRO;
+	if (likely(tpa_start->flags_type &
+		   rte_cpu_to_le_32(RX_TPA_START_CMPL_FLAGS_RSS_VALID))) {
+		mbuf->hash.rss = rte_le_to_cpu_32(tpa_start->rss_hash);
+		mbuf->ol_flags |= PKT_RX_RSS_HASH;
+	} else {
+		mbuf->hash.fdir.id = rte_le_to_cpu_16(tpa_start1->cfa_code);
+		mbuf->ol_flags |= PKT_RX_FDIR | PKT_RX_FDIR_ID;
+	}
+	if (tpa_start1->flags2 &
+	    rte_cpu_to_le_32(RX_TPA_START_CMPL_FLAGS2_META_FORMAT_VLAN)) {
+		mbuf->vlan_tci = rte_le_to_cpu_32(tpa_start1->metadata);
+		mbuf->ol_flags |= PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED;
+	}
+	if (likely(tpa_start1->flags2 &
+		   rte_cpu_to_le_32(RX_TPA_START_CMPL_FLAGS2_L4_CS_CALC)))
+		mbuf->ol_flags |= PKT_RX_L4_CKSUM_GOOD;
+
+	/* recycle next mbuf */
+	data_cons = RING_NEXT(rxr->rx_ring_struct, data_cons);
+	bnxt_reuse_rx_mbuf(rxr, bnxt_consume_rx_buf(rxr, data_cons));
+}
+
+static int bnxt_agg_bufs_valid(struct bnxt_cp_ring_info *cpr,
+		uint8_t agg_bufs, uint32_t raw_cp_cons)
+{
+	uint16_t last_cp_cons;
+	struct rx_pkt_cmpl *agg_cmpl;
+
+	raw_cp_cons = ADV_RAW_CMP(raw_cp_cons, agg_bufs);
+	last_cp_cons = RING_CMP(cpr->cp_ring_struct, raw_cp_cons);
+	agg_cmpl = (struct rx_pkt_cmpl *)&cpr->cp_desc_ring[last_cp_cons];
+	cpr->valid = FLIP_VALID(raw_cp_cons,
+				cpr->cp_ring_struct->ring_mask,
+				cpr->valid);
+	return CMP_VALID(agg_cmpl, raw_cp_cons, cpr->cp_ring_struct);
+}
+
+/* TPA consume agg buffer out of order, allocate connected data only */
+static int bnxt_prod_ag_mbuf(struct bnxt_rx_queue *rxq)
+{
+	struct bnxt_rx_ring_info *rxr = rxq->rx_ring;
+	uint16_t next = RING_NEXT(rxr->ag_ring_struct, rxr->ag_prod);
+
+	/* TODO batch allocation for better performance */
+	while (rte_bitmap_get(rxr->ag_bitmap, next)) {
+		if (unlikely(bnxt_alloc_ag_data(rxq, rxr, next))) {
+			PMD_DRV_LOG(ERR,
+				"agg mbuf alloc failed: prod=0x%x\n", next);
+			break;
+		}
+		rte_bitmap_clear(rxr->ag_bitmap, next);
+		rxr->ag_prod = next;
+		next = RING_NEXT(rxr->ag_ring_struct, next);
+	}
+
+	return 0;
 }
+
+static int bnxt_rx_pages(struct bnxt_rx_queue *rxq,
+			 struct rte_mbuf *mbuf, uint32_t *tmp_raw_cons,
+			 uint8_t agg_buf, struct bnxt_tpa_info *tpa_info)
+{
+	struct bnxt_cp_ring_info *cpr = rxq->cp_ring;
+	struct bnxt_rx_ring_info *rxr = rxq->rx_ring;
+	int i;
+	uint16_t cp_cons, ag_cons;
+	struct rx_pkt_cmpl *rxcmp;
+	struct rte_mbuf *last = mbuf;
+	bool is_thor_tpa = tpa_info && BNXT_CHIP_THOR(rxq->bp);
+
+	for (i = 0; i < agg_buf; i++) {
+		struct bnxt_sw_rx_bd *ag_buf;
+		struct rte_mbuf *ag_mbuf;
+
+		if (is_thor_tpa) {
+			rxcmp = (void *)&tpa_info->agg_arr[i];
+		} else {
+			*tmp_raw_cons = NEXT_RAW_CMP(*tmp_raw_cons);
+			cp_cons = RING_CMP(cpr->cp_ring_struct, *tmp_raw_cons);
+			rxcmp = (struct rx_pkt_cmpl *)
+					&cpr->cp_desc_ring[cp_cons];
+		}
+
+#ifdef BNXT_DEBUG
+		bnxt_dump_cmpl(cp_cons, rxcmp);
 #endif
 
-static uint16_t bnxt_rx_pkt(struct rte_mbuf **rx_pkt,
+		ag_cons = rxcmp->opaque;
+		RTE_ASSERT(ag_cons <= rxr->ag_ring_struct->ring_mask);
+		ag_buf = &rxr->ag_buf_ring[ag_cons];
+		ag_mbuf = ag_buf->mbuf;
+		RTE_ASSERT(ag_mbuf != NULL);
+
+		ag_mbuf->data_len = rte_le_to_cpu_16(rxcmp->len);
+
+		mbuf->nb_segs++;
+		mbuf->pkt_len += ag_mbuf->data_len;
+
+		last->next = ag_mbuf;
+		last = ag_mbuf;
+
+		ag_buf->mbuf = NULL;
+
+		/*
+		 * As aggregation buffer consumed out of order in TPA module,
+		 * use bitmap to track freed slots to be allocated and notified
+		 * to NIC
+		 */
+		rte_bitmap_set(rxr->ag_bitmap, ag_cons);
+	}
+	bnxt_prod_ag_mbuf(rxq);
+	return 0;
+}
+
+static inline struct rte_mbuf *bnxt_tpa_end(
+		struct bnxt_rx_queue *rxq,
+		uint32_t *raw_cp_cons,
+		struct rx_tpa_end_cmpl *tpa_end,
+		struct rx_tpa_end_cmpl_hi *tpa_end1)
+{
+	struct bnxt_cp_ring_info *cpr = rxq->cp_ring;
+	struct bnxt_rx_ring_info *rxr = rxq->rx_ring;
+	uint16_t agg_id;
+	struct rte_mbuf *mbuf;
+	uint8_t agg_bufs;
+	uint8_t payload_offset;
+	struct bnxt_tpa_info *tpa_info;
+
+	if (BNXT_CHIP_THOR(rxq->bp)) {
+		struct rx_tpa_v2_end_cmpl *th_tpa_end;
+		struct rx_tpa_v2_end_cmpl_hi *th_tpa_end1;
+
+		th_tpa_end = (void *)tpa_end;
+		th_tpa_end1 = (void *)tpa_end1;
+		agg_id = BNXT_TPA_END_AGG_ID_TH(th_tpa_end);
+		agg_bufs = BNXT_TPA_END_AGG_BUFS_TH(th_tpa_end1);
+		payload_offset = th_tpa_end1->payload_offset;
+	} else {
+		agg_id = BNXT_TPA_END_AGG_ID(tpa_end);
+		agg_bufs = BNXT_TPA_END_AGG_BUFS(tpa_end);
+		if (!bnxt_agg_bufs_valid(cpr, agg_bufs, *raw_cp_cons))
+			return NULL;
+		payload_offset = tpa_end->payload_offset;
+	}
+
+	tpa_info = &rxr->tpa_info[agg_id];
+	mbuf = tpa_info->mbuf;
+	RTE_ASSERT(mbuf != NULL);
+
+	rte_prefetch0(mbuf);
+	if (agg_bufs) {
+		bnxt_rx_pages(rxq, mbuf, raw_cp_cons, agg_bufs, tpa_info);
+	}
+	mbuf->l4_len = payload_offset;
+
+	struct rte_mbuf *new_data = __bnxt_alloc_rx_data(rxq->mb_pool);
+	RTE_ASSERT(new_data != NULL);
+	if (!new_data) {
+		rte_atomic64_inc(&rxq->rx_mbuf_alloc_fail);
+		return NULL;
+	}
+	tpa_info->mbuf = new_data;
+
+	return mbuf;
+}
+
+static uint32_t
+bnxt_parse_pkt_type(struct rx_pkt_cmpl *rxcmp, struct rx_pkt_cmpl_hi *rxcmp1)
+{
+	uint32_t l3, pkt_type = 0;
+	uint32_t t_ipcs = 0, ip6 = 0, vlan = 0;
+	uint32_t flags_type;
+
+	vlan = !!(rxcmp1->flags2 &
+		rte_cpu_to_le_32(RX_PKT_CMPL_FLAGS2_META_FORMAT_VLAN));
+	pkt_type |= vlan ? RTE_PTYPE_L2_ETHER_VLAN : RTE_PTYPE_L2_ETHER;
+
+	t_ipcs = !!(rxcmp1->flags2 &
+		rte_cpu_to_le_32(RX_PKT_CMPL_FLAGS2_T_IP_CS_CALC));
+	ip6 = !!(rxcmp1->flags2 &
+		 rte_cpu_to_le_32(RX_PKT_CMPL_FLAGS2_IP_TYPE));
+
+	flags_type = rxcmp->flags_type &
+		rte_cpu_to_le_32(RX_PKT_CMPL_FLAGS_ITYPE_MASK);
+
+	if (!t_ipcs && !ip6)
+		l3 = RTE_PTYPE_L3_IPV4_EXT_UNKNOWN;
+	else if (!t_ipcs && ip6)
+		l3 = RTE_PTYPE_L3_IPV6_EXT_UNKNOWN;
+	else if (t_ipcs && !ip6)
+		l3 = RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN;
+	else
+		l3 = RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN;
+
+	switch (flags_type) {
+	case RTE_LE32(RX_PKT_CMPL_FLAGS_ITYPE_ICMP):
+		if (!t_ipcs)
+			pkt_type |= l3 | RTE_PTYPE_L4_ICMP;
+		else
+			pkt_type |= l3 | RTE_PTYPE_INNER_L4_ICMP;
+		break;
+
+	case RTE_LE32(RX_PKT_CMPL_FLAGS_ITYPE_TCP):
+		if (!t_ipcs)
+			pkt_type |= l3 | RTE_PTYPE_L4_TCP;
+		else
+			pkt_type |= l3 | RTE_PTYPE_INNER_L4_TCP;
+		break;
+
+	case RTE_LE32(RX_PKT_CMPL_FLAGS_ITYPE_UDP):
+		if (!t_ipcs)
+			pkt_type |= l3 | RTE_PTYPE_L4_UDP;
+		else
+			pkt_type |= l3 | RTE_PTYPE_INNER_L4_UDP;
+		break;
+
+	case RTE_LE32(RX_PKT_CMPL_FLAGS_ITYPE_IP):
+		pkt_type |= l3;
+		break;
+	}
+
+	return pkt_type;
+}
+
+#ifdef RTE_LIBRTE_IEEE1588
+static void
+bnxt_get_rx_ts_thor(struct bnxt *bp, uint32_t rx_ts_cmpl)
+{
+	uint64_t systime_cycles = 0;
+
+	if (!BNXT_CHIP_THOR(bp))
+		return;
+
+	/* On Thor, Rx timestamps are provided directly in the
+	 * Rx completion records to the driver. Only 32 bits of
+	 * the timestamp is present in the completion. Driver needs
+	 * to read the current 48 bit free running timer using the
+	 * HWRM_PORT_TS_QUERY command and combine the upper 16 bits
+	 * from the HWRM response with the lower 32 bits in the
+	 * Rx completion to produce the 48 bit timestamp for the Rx packet
+	 */
+	bnxt_hwrm_port_ts_query(bp, BNXT_PTP_FLAGS_CURRENT_TIME,
+				&systime_cycles);
+	bp->ptp_cfg->rx_timestamp = (systime_cycles & 0xFFFF00000000);
+	bp->ptp_cfg->rx_timestamp |= rx_ts_cmpl;
+}
+#endif
+
+static int bnxt_rx_pkt(struct rte_mbuf **rx_pkt,
 			    struct bnxt_rx_queue *rxq, uint32_t *raw_cons)
 {
 	struct bnxt_cp_ring_info *cpr = rxq->cp_ring;
@@ -148,16 +409,30 @@ static uint16_t bnxt_rx_pkt(struct rte_mbuf **rx_pkt,
 	uint32_t tmp_raw_cons = *raw_cons;
 	uint16_t cons, prod, cp_cons =
 	    RING_CMP(cpr->cp_ring_struct, tmp_raw_cons);
-	uint16_t ag_cons, ag_prod = rxr->ag_prod;
-	struct bnxt_sw_rx_bd *rx_buf;
 	struct rte_mbuf *mbuf;
 	int rc = 0;
-	uint8_t i;
 	uint8_t agg_buf = 0;
+	uint16_t cmp_type;
+	uint32_t flags2_f = 0;
+	uint16_t flags_type;
 
 	rxcmp = (struct rx_pkt_cmpl *)
 	    &cpr->cp_desc_ring[cp_cons];
 
+	cmp_type = CMP_TYPE(rxcmp);
+
+	if (cmp_type == RX_TPA_V2_ABUF_CMPL_TYPE_RX_TPA_AGG) {
+		struct rx_tpa_v2_abuf_cmpl *rx_agg = (void *)rxcmp;
+		uint16_t agg_id = rte_cpu_to_le_16(rx_agg->agg_id);
+		struct bnxt_tpa_info *tpa_info;
+
+		tpa_info = &rxr->tpa_info[agg_id];
+		RTE_ASSERT(tpa_info->agg_count < 16);
+		tpa_info->agg_arr[tpa_info->agg_count++] = *rx_agg;
+		rc = -EINVAL; /* Continue w/o new mbuf */
+		goto next_rx;
+	}
+
 	tmp_raw_cons = NEXT_RAW_CMP(tmp_raw_cons);
 	cp_cons = RING_CMP(cpr->cp_ring_struct, tmp_raw_cons);
 	rxcmp1 = (struct rx_pkt_cmpl_hi *)&cpr->cp_desc_ring[cp_cons];
@@ -165,102 +440,124 @@ static uint16_t bnxt_rx_pkt(struct rte_mbuf **rx_pkt,
 	if (!CMP_VALID(rxcmp1, tmp_raw_cons, cpr->cp_ring_struct))
 		return -EBUSY;
 
+	cpr->valid = FLIP_VALID(cp_cons,
+				cpr->cp_ring_struct->ring_mask,
+				cpr->valid);
+
+	if (cmp_type == RX_TPA_START_CMPL_TYPE_RX_TPA_START) {
+		bnxt_tpa_start(rxq, (struct rx_tpa_start_cmpl *)rxcmp,
+			       (struct rx_tpa_start_cmpl_hi *)rxcmp1);
+		rc = -EINVAL; /* Continue w/o new mbuf */
+		goto next_rx;
+	} else if (cmp_type == RX_TPA_END_CMPL_TYPE_RX_TPA_END) {
+		mbuf = bnxt_tpa_end(rxq, &tmp_raw_cons,
+				   (struct rx_tpa_end_cmpl *)rxcmp,
+				   (struct rx_tpa_end_cmpl_hi *)rxcmp1);
+		if (unlikely(!mbuf))
+			return -EBUSY;
+		*rx_pkt = mbuf;
+		goto next_rx;
+	} else if (cmp_type != 0x11) {
+		rc = -EINVAL;
+		goto next_rx;
+	}
+
+	agg_buf = (rxcmp->agg_bufs_v1 & RX_PKT_CMPL_AGG_BUFS_MASK)
+			>> RX_PKT_CMPL_AGG_BUFS_SFT;
+	if (agg_buf && !bnxt_agg_bufs_valid(cpr, agg_buf, tmp_raw_cons))
+		return -EBUSY;
+
 	prod = rxr->rx_prod;
 
-	/* EW - GRO deferred to phase 3 */
 	cons = rxcmp->opaque;
-	rx_buf = &rxr->rx_buf_ring[cons];
-	mbuf = rx_buf->mbuf;
-	rte_prefetch0(mbuf);
-
+	mbuf = bnxt_consume_rx_buf(rxr, cons);
 	if (mbuf == NULL)
-		return -ENOMEM;
+		return -EBUSY;
+
+	rte_prefetch0(mbuf);
 
+	mbuf->data_off = RTE_PKTMBUF_HEADROOM;
 	mbuf->nb_segs = 1;
 	mbuf->next = NULL;
 	mbuf->pkt_len = rxcmp->len;
 	mbuf->data_len = mbuf->pkt_len;
 	mbuf->port = rxq->port_id;
 	mbuf->ol_flags = 0;
-	if (rxcmp->flags_type & RX_PKT_CMPL_FLAGS_RSS_VALID) {
+
+	flags_type = rte_le_to_cpu_16(rxcmp->flags_type);
+	if (flags_type & RX_PKT_CMPL_FLAGS_RSS_VALID) {
 		mbuf->hash.rss = rxcmp->rss_hash;
 		mbuf->ol_flags |= PKT_RX_RSS_HASH;
-	} else {
-		mbuf->hash.fdir.id = rxcmp1->cfa_code;
-		mbuf->ol_flags |= PKT_RX_FDIR | PKT_RX_FDIR_ID;
 	}
 
-	agg_buf = (rxcmp->agg_bufs_v1 & RX_PKT_CMPL_AGG_BUFS_MASK)
-			>> RX_PKT_CMPL_AGG_BUFS_SFT;
-	if (agg_buf) {
-		cp_cons = RING_CMP(cpr->cp_ring_struct, tmp_raw_cons + agg_buf);
-		rxcmp = (struct rx_pkt_cmpl *)
-					&cpr->cp_desc_ring[cp_cons];
-		if (!CMP_VALID(rxcmp, tmp_raw_cons + agg_buf,
-			       cpr->cp_ring_struct))
-			return -EBUSY;
-		RTE_LOG(DEBUG, PMD, "JUMBO Frame %d. %x, agg_buf %x,\n",
-			mbuf->pkt_len, rxcmp->agg_bufs_v1,  agg_buf);
-	}
-
-	for (i = 0; i < agg_buf; i++) {
-		struct bnxt_sw_rx_bd *ag_buf;
-		struct rte_mbuf *ag_mbuf;
-		tmp_raw_cons = NEXT_RAW_CMP(tmp_raw_cons);
-		cp_cons = RING_CMP(cpr->cp_ring_struct, tmp_raw_cons);
-		rxcmp = (struct rx_pkt_cmpl *)
-					&cpr->cp_desc_ring[cp_cons];
-		ag_cons = rxcmp->opaque;
-		ag_buf = &rxr->ag_buf_ring[ag_cons];
-		ag_mbuf = ag_buf->mbuf;
-		ag_mbuf->nb_segs = 1;
-		ag_mbuf->data_len = rxcmp->len;
-
-		mbuf->nb_segs++;
-		mbuf->pkt_len += ag_mbuf->data_len;
-		if (mbuf->next == NULL) {
-			mbuf->next = ag_mbuf;
-		} else {
-			struct rte_mbuf *temp_mbuf = mbuf;
-
-			while (temp_mbuf->next != NULL)
-				temp_mbuf = temp_mbuf->next;
-			temp_mbuf->next = ag_mbuf;
-		}
-		ag_buf->mbuf = NULL;
-
-		ag_prod = RING_NEXT(rxr->ag_ring_struct, ag_prod);
-		if (bnxt_alloc_ag_data(rxq, rxr, ag_prod)) {
-			RTE_LOG(ERR, PMD,
-				"agg mbuf alloc failed: prod=0x%x\n",
-				ag_prod);
-			rc = -ENOMEM;
-		}
-		rxr->ag_prod = ag_prod;
+	bnxt_set_mark_in_mbuf(rxq->bp, rxcmp1, mbuf);
 
-#ifdef BNXT_DEBUG
-		if (!CMP_VALID((struct cmpl_base *)
-			&cpr->cp_desc_ring[cp_cons], tmp_raw_cons,
-			cpr->cp_ring_struct))
-			return -EBUSY;
-#endif
+#ifdef RTE_LIBRTE_IEEE1588
+	if (unlikely((flags_type & RX_PKT_CMPL_FLAGS_MASK) ==
+		     RX_PKT_CMPL_FLAGS_ITYPE_PTP_W_TIMESTAMP)) {
+		mbuf->ol_flags |= PKT_RX_IEEE1588_PTP | PKT_RX_IEEE1588_TMST;
+		bnxt_get_rx_ts_thor(rxq->bp, rxcmp1->reorder);
 	}
+#endif
+	if (agg_buf)
+		bnxt_rx_pages(rxq, mbuf, &tmp_raw_cons, agg_buf, NULL);
 
 	if (rxcmp1->flags2 & RX_PKT_CMPL_FLAGS2_META_FORMAT_VLAN) {
 		mbuf->vlan_tci = rxcmp1->metadata &
 			(RX_PKT_CMPL_METADATA_VID_MASK |
 			RX_PKT_CMPL_METADATA_DE |
 			RX_PKT_CMPL_METADATA_PRI_MASK);
-		mbuf->ol_flags |= PKT_RX_VLAN_PKT;
+		mbuf->ol_flags |= PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED;
+	}
+
+	flags2_f = flags2_0xf(rxcmp1);
+	/* IP Checksum */
+	if (likely(IS_IP_NONTUNNEL_PKT(flags2_f))) {
+		if (unlikely(RX_CMP_IP_CS_ERROR(rxcmp1)))
+			mbuf->ol_flags |= PKT_RX_IP_CKSUM_BAD;
+		else if (unlikely(RX_CMP_IP_CS_UNKNOWN(rxcmp1)))
+			mbuf->ol_flags |= PKT_RX_IP_CKSUM_UNKNOWN;
+		else
+			mbuf->ol_flags |= PKT_RX_IP_CKSUM_GOOD;
+	} else if (IS_IP_TUNNEL_PKT(flags2_f)) {
+		if (unlikely(RX_CMP_IP_OUTER_CS_ERROR(rxcmp1) ||
+			     RX_CMP_IP_CS_ERROR(rxcmp1)))
+			mbuf->ol_flags |= PKT_RX_IP_CKSUM_BAD;
+		else if (unlikely(RX_CMP_IP_CS_UNKNOWN(rxcmp1)))
+			mbuf->ol_flags |= PKT_RX_IP_CKSUM_UNKNOWN;
+		else
+			mbuf->ol_flags |= PKT_RX_IP_CKSUM_GOOD;
 	}
 
-	rx_buf->mbuf = NULL;
+	/* L4 Checksum */
+	if (likely(IS_L4_NONTUNNEL_PKT(flags2_f))) {
+		if (unlikely(RX_CMP_L4_INNER_CS_ERR2(rxcmp1)))
+			mbuf->ol_flags |= PKT_RX_L4_CKSUM_BAD;
+		else
+			mbuf->ol_flags |= PKT_RX_L4_CKSUM_GOOD;
+	} else if (IS_L4_TUNNEL_PKT(flags2_f)) {
+		if (unlikely(RX_CMP_L4_INNER_CS_ERR2(rxcmp1)))
+			mbuf->ol_flags |= PKT_RX_L4_CKSUM_BAD;
+		else
+			mbuf->ol_flags |= PKT_RX_L4_CKSUM_GOOD;
+		if (unlikely(RX_CMP_L4_OUTER_CS_ERR2(rxcmp1))) {
+			mbuf->ol_flags |= PKT_RX_OUTER_L4_CKSUM_BAD;
+		} else if (unlikely(IS_L4_TUNNEL_PKT_ONLY_INNER_L4_CS
+				    (flags2_f))) {
+			mbuf->ol_flags |= PKT_RX_OUTER_L4_CKSUM_UNKNOWN;
+		} else {
+			mbuf->ol_flags |= PKT_RX_OUTER_L4_CKSUM_GOOD;
+		}
+	} else if (unlikely(RX_CMP_L4_CS_UNKNOWN(rxcmp1))) {
+		mbuf->ol_flags |= PKT_RX_L4_CKSUM_UNKNOWN;
+	}
+
+	mbuf->packet_type = bnxt_parse_pkt_type(rxcmp, rxcmp1);
+
 #ifdef BNXT_DEBUG
 	if (rxcmp1->errors_v2 & RX_CMP_L2_ERRORS) {
 		/* Re-install the mbuf back to the rx ring */
 		bnxt_reuse_rx_mbuf(rxr, cons, mbuf);
-		if (agg_buf)
-			bnxt_reuse_ag_mbuf(rxr, ag_cons, mbuf);
 
 		rc = -EIO;
 		goto next_rx;
@@ -283,19 +580,20 @@ static uint16_t bnxt_rx_pkt(struct rte_mbuf **rx_pkt,
 	 */
 	prod = RING_NEXT(rxr->rx_ring_struct, prod);
 	if (bnxt_alloc_rx_data(rxq, rxr, prod)) {
-		RTE_LOG(ERR, PMD, "mbuf alloc failed with prod=0x%x\n", prod);
+		PMD_DRV_LOG(ERR, "mbuf alloc failed with prod=0x%x\n", prod);
 		rc = -ENOMEM;
+		goto rx;
 	}
 	rxr->rx_prod = prod;
 	/*
 	 * All MBUFs are allocated with the same size under DPDK,
 	 * no optimization for rx_copy_thresh
 	 */
-
+rx:
 	*rx_pkt = mbuf;
-#ifdef BNXT_DEBUG
+
 next_rx:
-#endif
+
 	*raw_cons = tmp_raw_cons;
 
 	return rc;
@@ -313,54 +611,124 @@ uint16_t bnxt_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 	struct rx_pkt_cmpl *rxcmp;
 	uint16_t prod = rxr->rx_prod;
 	uint16_t ag_prod = rxr->ag_prod;
+	int rc = 0;
+	bool evt = false;
+
+	if (unlikely(is_bnxt_in_error(rxq->bp)))
+		return 0;
+
+	/* If Rx Q was stopped return */
+	if (unlikely(!rxq->rx_started ||
+		     !rte_spinlock_trylock(&rxq->lock)))
+		return 0;
 
 	/* Handle RX burst request */
 	while (1) {
-		int rc;
-
 		cons = RING_CMP(cpr->cp_ring_struct, raw_cons);
 		rte_prefetch0(&cpr->cp_desc_ring[cons]);
 		rxcmp = (struct rx_pkt_cmpl *)&cpr->cp_desc_ring[cons];
 
 		if (!CMP_VALID(rxcmp, raw_cons, cpr->cp_ring_struct))
 			break;
+		cpr->valid = FLIP_VALID(cons,
+					cpr->cp_ring_struct->ring_mask,
+					cpr->valid);
 
 		/* TODO: Avoid magic numbers... */
 		if ((CMP_TYPE(rxcmp) & 0x30) == 0x10) {
 			rc = bnxt_rx_pkt(&rx_pkts[nb_rx_pkts], rxq, &raw_cons);
-			if (likely(!rc))
+			if (likely(!rc) || rc == -ENOMEM)
 				nb_rx_pkts++;
-			else if (rc == -EBUSY)	/* partial completion */
+			if (rc == -EBUSY)	/* partial completion */
 				break;
+		} else if (!BNXT_NUM_ASYNC_CPR(rxq->bp)) {
+			evt =
+			bnxt_event_hwrm_resp_handler(rxq->bp,
+						     (struct cmpl_base *)rxcmp);
+			/* If the async event is Fatal error, return */
+			if (unlikely(is_bnxt_in_error(rxq->bp)))
+				goto done;
 		}
+
 		raw_cons = NEXT_RAW_CMP(raw_cons);
-		if (nb_rx_pkts == nb_pkts)
+		if (nb_rx_pkts == nb_pkts || evt)
 			break;
+		/* Post some Rx buf early in case of larger burst processing */
+		if (nb_rx_pkts == BNXT_RX_POST_THRESH)
+			bnxt_db_write(&rxr->rx_db, rxr->rx_prod);
 	}
 
-	if (prod == rxr->rx_prod && ag_prod == rxr->ag_prod) {
+	cpr->cp_raw_cons = raw_cons;
+	if (!nb_rx_pkts && !evt) {
 		/*
 		 * For PMD, there is no need to keep on pushing to REARM
 		 * the doorbell if there are no new completions
 		 */
-		return nb_rx_pkts;
+		goto done;
 	}
-	cpr->cp_raw_cons = raw_cons;
 
-	B_CP_DIS_DB(cpr, cpr->cp_raw_cons);
-	B_RX_DB(rxr->rx_doorbell, rxr->rx_prod);
+	if (prod != rxr->rx_prod)
+		bnxt_db_write(&rxr->rx_db, rxr->rx_prod);
+
 	/* Ring the AGG ring DB */
-	B_RX_DB(rxr->ag_doorbell, rxr->ag_prod);
+	if (ag_prod != rxr->ag_prod)
+		bnxt_db_write(&rxr->ag_db, rxr->ag_prod);
+
+	bnxt_db_cq(cpr);
+
+	/* Attempt to alloc Rx buf in case of a previous allocation failure. */
+	if (rc == -ENOMEM) {
+		int i;
+
+		for (i = prod; i <= nb_rx_pkts;
+			i = RING_NEXT(rxr->rx_ring_struct, i)) {
+			struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[i];
+
+			/* Buffer already allocated for this index. */
+			if (rx_buf->mbuf != NULL)
+				continue;
+
+			/* This slot is empty. Alloc buffer for Rx */
+			if (!bnxt_alloc_rx_data(rxq, rxr, i)) {
+				rxr->rx_prod = i;
+				bnxt_db_write(&rxr->rx_db, rxr->rx_prod);
+			} else {
+				PMD_DRV_LOG(ERR, "Alloc  mbuf failed\n");
+				break;
+			}
+		}
+	}
+
+done:
+	rte_spinlock_unlock(&rxq->lock);
+
 	return nb_rx_pkts;
 }
 
+/*
+ * Dummy DPDK callback for RX.
+ *
+ * This function is used to temporarily replace the real callback during
+ * unsafe control operations on the queue, or in case of error.
+ */
+uint16_t
+bnxt_dummy_recv_pkts(void *rx_queue __rte_unused,
+		     struct rte_mbuf **rx_pkts __rte_unused,
+		     uint16_t nb_pkts __rte_unused)
+{
+	return 0;
+}
+
 void bnxt_free_rx_rings(struct bnxt *bp)
 {
 	int i;
+	struct bnxt_rx_queue *rxq;
 
-	for (i = 0; i < (int)bp->rx_nr_rings; i++) {
-		struct bnxt_rx_queue *rxq = bp->rx_queues[i];
+	if (!bp->rx_queues)
+		return;
 
+	for (i = 0; i < (int)bp->rx_nr_rings; i++) {
+		rxq = bp->rx_queues[i];
 		if (!rxq)
 			continue;
 
@@ -389,9 +757,7 @@ int bnxt_init_rx_ring_struct(struct bnxt_rx_queue *rxq, unsigned int socket_id)
 	struct bnxt_rx_ring_info *rxr;
 	struct bnxt_ring *ring;
 
-	rxq->rx_buf_use_size = BNXT_MAX_MTU + ETHER_HDR_LEN + ETHER_CRC_LEN +
-			       (2 * VLAN_TAG_SIZE);
-	rxq->rx_buf_size = rxq->rx_buf_use_size + sizeof(struct rte_mbuf);
+	rxq->rx_buf_size = BNXT_MAX_PKT_LEN + sizeof(struct rte_mbuf);
 
 	rxr = rte_zmalloc_socket("bnxt_rx_ring",
 				 sizeof(struct bnxt_rx_ring_info),
@@ -476,10 +842,9 @@ int bnxt_init_one_rx_ring(struct bnxt_rx_queue *rxq)
 	uint16_t size;
 
 	size = rte_pktmbuf_data_room_size(rxq->mb_pool) - RTE_PKTMBUF_HEADROOM;
-	if (rxq->rx_buf_use_size <= size)
-		size = rxq->rx_buf_use_size;
+	size = RTE_MIN(BNXT_MAX_PKT_LEN, size);
 
-	type = RX_PROD_PKT_BD_TYPE_RX_PROD_PKT;
+	type = RX_PROD_PKT_BD_TYPE_RX_PROD_PKT | RX_PROD_PKT_BD_FLAGS_EOP_PAD;
 
 	rxr = rxq->rx_ring;
 	ring = rxr->rx_ring_struct;
@@ -488,7 +853,7 @@ int bnxt_init_one_rx_ring(struct bnxt_rx_queue *rxq)
 	prod = rxr->rx_prod;
 	for (i = 0; i < ring->ring_size; i++) {
 		if (bnxt_alloc_rx_data(rxq, rxr, prod) != 0) {
-			RTE_LOG(WARNING, PMD,
+			PMD_DRV_LOG(WARNING,
 				"init'ed rx ring %d with %d/%d mbufs only\n",
 				rxq->queue_id, i, ring->ring_size);
 			break;
@@ -496,7 +861,6 @@ int bnxt_init_one_rx_ring(struct bnxt_rx_queue *rxq)
 		rxr->rx_prod = prod;
 		prod = RING_NEXT(rxr->rx_ring_struct, prod);
 	}
-	RTE_LOG(DEBUG, PMD, "%s\n", __func__);
 
 	ring = rxr->ag_ring_struct;
 	type = RX_PROD_AGG_BD_TYPE_RX_PROD_AGG;
@@ -505,7 +869,7 @@ int bnxt_init_one_rx_ring(struct bnxt_rx_queue *rxq)
 
 	for (i = 0; i < ring->ring_size; i++) {
 		if (bnxt_alloc_ag_data(rxq, rxr, prod) != 0) {
-			RTE_LOG(WARNING, PMD,
+			PMD_DRV_LOG(WARNING,
 			"init'ed AG ring %d with %d/%d mbufs only\n",
 			rxq->queue_id, i, ring->ring_size);
 			break;
@@ -513,7 +877,62 @@ int bnxt_init_one_rx_ring(struct bnxt_rx_queue *rxq)
 		rxr->ag_prod = prod;
 		prod = RING_NEXT(rxr->ag_ring_struct, prod);
 	}
-	RTE_LOG(DEBUG, PMD, "%s AGG Done!\n", __func__);
+	PMD_DRV_LOG(DEBUG, "AGG Done!\n");
+
+	if (rxr->tpa_info) {
+		unsigned int max_aggs = BNXT_TPA_MAX_AGGS(rxq->bp);
+
+		for (i = 0; i < max_aggs; i++) {
+			rxr->tpa_info[i].mbuf =
+				__bnxt_alloc_rx_data(rxq->mb_pool);
+			if (!rxr->tpa_info[i].mbuf) {
+				rte_atomic64_inc(&rxq->rx_mbuf_alloc_fail);
+				return -ENOMEM;
+			}
+		}
+	}
+	PMD_DRV_LOG(DEBUG, "TPA alloc Done!\n");
 
 	return 0;
 }
+
+void bnxt_set_mark_in_mbuf(struct bnxt *bp,
+			   struct rx_pkt_cmpl_hi *rxcmp1,
+			   struct rte_mbuf *mbuf)
+{
+	uint32_t cfa_code = 0;
+	uint8_t meta_fmt =  0;
+	uint16_t flags2 = 0;
+	uint32_t meta =  0;
+
+	cfa_code = rte_le_to_cpu_16(rxcmp1->cfa_code);
+	if (!cfa_code)
+		return;
+
+	if (cfa_code && !bp->mark_table[cfa_code].valid)
+		return;
+
+	flags2 = rte_le_to_cpu_16(rxcmp1->flags2);
+	meta = rte_le_to_cpu_32(rxcmp1->metadata);
+	if (meta) {
+		meta >>= BNXT_RX_META_CFA_CODE_SHIFT;
+
+		/*
+		 * The flags field holds extra bits of info from [6:4]
+		 * which indicate if the flow is in TCAM or EM or EEM
+		 */
+		meta_fmt = (flags2 & BNXT_CFA_META_FMT_MASK) >>
+			   BNXT_CFA_META_FMT_SHFT;
+
+		/*
+		 * meta_fmt == 4 => 'b100 => 'b10x => EM.
+		 * meta_fmt == 5 => 'b101 => 'b10x => EM + VLAN
+		 * meta_fmt == 6 => 'b110 => 'b11x => EEM
+		 * meta_fmt == 7 => 'b111 => 'b11x => EEM + VLAN.
+		 */
+		meta_fmt >>= BNXT_CFA_META_FMT_EM_EEM_SHFT;
+	}
+
+	mbuf->hash.fdir.hi = bp->mark_table[cfa_code].mark_id;
+	mbuf->ol_flags |= PKT_RX_FDIR | PKT_RX_FDIR_ID;
+}