[dpdk-dev] [PATCH v2 04/15] net/mlx5: support Rx tunnel type identification

[Xueming Li <xuemingl@mellanox.com>]

This patch introduced tunnel type identification based on flow rules.
If flows of multiple tunnel types built on same queue,
RTE_PTYPE_TUNNEL_MASK will be returned, bits in flow mark could be used
as tunnel type identifier.

Signed-off-by: Xueming Li <xuemingl@mellanox.com>
---
 drivers/net/mlx5/mlx5_flow.c          | 125 +++++++++++++++++++++++++++++-----
 drivers/net/mlx5/mlx5_rxq.c           |  11 ++-
 drivers/net/mlx5/mlx5_rxtx.c          |  12 ++--
 drivers/net/mlx5/mlx5_rxtx.h          |   9 ++-
 drivers/net/mlx5/mlx5_rxtx_vec_neon.h |  21 +++---
 drivers/net/mlx5/mlx5_rxtx_vec_sse.h  |  17 +++--
 6 files changed, 157 insertions(+), 38 deletions(-)

diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
index 870d05250..65d7a9b62 100644
--- a/drivers/net/mlx5/mlx5_flow.c
+++ b/drivers/net/mlx5/mlx5_flow.c
@@ -222,6 +222,7 @@ struct rte_flow {
 	struct rte_flow_action_rss rss_conf; /**< RSS configuration */
 	uint16_t (*queues)[]; /**< Queues indexes to use. */
 	uint8_t rss_key[40]; /**< copy of the RSS key. */
+	uint32_t tunnel; /**< Tunnel type of RTE_PTYPE_TUNNEL_XXX. */
 	struct ibv_counter_set *cs; /**< Holds the counters for the rule. */
 	struct mlx5_flow_counter_stats counter_stats;/**<The counter stats. */
 	struct mlx5_flow frxq[RTE_DIM(hash_rxq_init)];
@@ -238,6 +239,19 @@ struct rte_flow {
 	(type) == RTE_FLOW_ITEM_TYPE_VXLAN || \
 	(type) == RTE_FLOW_ITEM_TYPE_GRE)
 
+const uint32_t flow_ptype[] = {
+	[RTE_FLOW_ITEM_TYPE_VXLAN] = RTE_PTYPE_TUNNEL_VXLAN,
+	[RTE_FLOW_ITEM_TYPE_GRE] = RTE_PTYPE_TUNNEL_GRE,
+};
+
+#define PTYPE_IDX(t) ((RTE_PTYPE_TUNNEL_MASK & (t)) >> 12)
+
+const uint32_t ptype_ext[] = {
+	[PTYPE_IDX(RTE_PTYPE_TUNNEL_VXLAN)] = RTE_PTYPE_TUNNEL_VXLAN |
+					      RTE_PTYPE_L4_UDP,
+	[PTYPE_IDX(RTE_PTYPE_TUNNEL_GRE)] = RTE_PTYPE_TUNNEL_GRE,
+};
+
 /** Structure to generate a simple graph of layers supported by the NIC. */
 struct mlx5_flow_items {
 	/** List of possible actions for these items. */
@@ -437,6 +451,7 @@ struct mlx5_flow_parse {
 	uint16_t queues[RTE_MAX_QUEUES_PER_PORT]; /**< Queues indexes to use. */
 	uint8_t rss_key[40]; /**< copy of the RSS key. */
 	enum hash_rxq_type layer; /**< Last pattern layer detected. */
+	uint32_t tunnel; /**< Tunnel type of RTE_PTYPE_TUNNEL_XXX. */
 	struct ibv_counter_set *cs; /**< Holds the counter set for the rule */
 	struct {
 		struct ibv_flow_attr *ibv_attr;
@@ -860,7 +875,7 @@ mlx5_flow_convert_items_validate(const struct rte_flow_item items[],
 		if (ret)
 			goto exit_item_not_supported;
 		if (IS_TUNNEL(items->type)) {
-			if (parser->inner) {
+			if (parser->tunnel) {
 				rte_flow_error_set(error, ENOTSUP,
 						   RTE_FLOW_ERROR_TYPE_ITEM,
 						   items,
@@ -869,6 +884,7 @@ mlx5_flow_convert_items_validate(const struct rte_flow_item items[],
 				return -rte_errno;
 			}
 			parser->inner = IBV_FLOW_SPEC_INNER;
+			parser->tunnel = flow_ptype[items->type];
 		}
 		if (parser->drop) {
 			parser->queue[HASH_RXQ_ETH].offset += cur_item->dst_sz;
@@ -1165,6 +1181,7 @@ mlx5_flow_convert(struct rte_eth_dev *dev,
 	}
 	/* Third step. Conversion parse, fill the specifications. */
 	parser->inner = 0;
+	parser->tunnel = 0;
 	for (; items->type != RTE_FLOW_ITEM_TYPE_END; ++items) {
 		struct mlx5_flow_data data = {
 			.parser = parser,
@@ -1633,6 +1650,7 @@ mlx5_flow_create_vxlan(const struct rte_flow_item *item,
 
 	id.vni[0] = 0;
 	parser->inner = IBV_FLOW_SPEC_INNER;
+	parser->tunnel = ptype_ext[PTYPE_IDX(RTE_PTYPE_TUNNEL_VXLAN)];
 	if (spec) {
 		if (!mask)
 			mask = default_mask;
@@ -1686,6 +1704,7 @@ mlx5_flow_create_gre(const struct rte_flow_item *item __rte_unused,
 	};
 
 	parser->inner = IBV_FLOW_SPEC_INNER;
+	parser->tunnel = ptype_ext[PTYPE_IDX(RTE_PTYPE_TUNNEL_GRE)];
 	mlx5_flow_create_copy(parser, &tunnel, size);
 	return 0;
 }
@@ -1864,7 +1883,8 @@ mlx5_flow_create_action_queue_rss(struct rte_eth_dev *dev,
 				      parser->rss_conf.key_len,
 				      hash_fields,
 				      parser->rss_conf.queue,
-				      parser->rss_conf.queue_num);
+				      parser->rss_conf.queue_num,
+				      parser->tunnel);
 		if (flow->frxq[i].hrxq)
 			continue;
 		flow->frxq[i].hrxq =
@@ -1873,7 +1893,8 @@ mlx5_flow_create_action_queue_rss(struct rte_eth_dev *dev,
 				      parser->rss_conf.key_len,
 				      hash_fields,
 				      parser->rss_conf.queue,
-				      parser->rss_conf.queue_num);
+				      parser->rss_conf.queue_num,
+				      parser->tunnel);
 		if (!flow->frxq[i].hrxq) {
 			return rte_flow_error_set(error, ENOMEM,
 						  RTE_FLOW_ERROR_TYPE_HANDLE,
@@ -1885,6 +1906,40 @@ mlx5_flow_create_action_queue_rss(struct rte_eth_dev *dev,
 }
 
 /**
+ * RXQ update after flow rule creation.
+ *
+ * @param dev
+ *   Pointer to Ethernet device.
+ * @param flow
+ *   Pointer to the flow rule.
+ */
+static void
+mlx5_flow_create_update_rxqs(struct rte_eth_dev *dev, struct rte_flow *flow)
+{
+	struct priv *priv = dev->data->dev_private;
+	unsigned int i;
+
+	if (!dev->data->dev_started)
+		return;
+	for (i = 0; i != flow->rss_conf.queue_num; ++i) {
+		struct mlx5_rxq_data *rxq_data = (*priv->rxqs)
+						 [(*flow->queues)[i]];
+		struct mlx5_rxq_ctrl *rxq_ctrl =
+			container_of(rxq_data, struct mlx5_rxq_ctrl, rxq);
+		uint8_t tunnel = PTYPE_IDX(flow->tunnel);
+
+		rxq_data->mark |= flow->mark;
+		if (!tunnel)
+			continue;
+		rxq_ctrl->tunnel_types[tunnel] += 1;
+		if (rxq_data->tunnel != flow->tunnel)
+			rxq_data->tunnel = rxq_data->tunnel ?
+					   RTE_PTYPE_TUNNEL_MASK :
+					   flow->tunnel;
+	}
+}
+
+/**
  * Complete flow rule creation.
  *
  * @param dev
@@ -1944,12 +1999,7 @@ mlx5_flow_create_action_queue(struct rte_eth_dev *dev,
 				   NULL, "internal error in flow creation");
 		goto error;
 	}
-	for (i = 0; i != parser->rss_conf.queue_num; ++i) {
-		struct mlx5_rxq_data *q =
-			(*priv->rxqs)[parser->rss_conf.queue[i]];
-
-		q->mark |= parser->mark;
-	}
+	mlx5_flow_create_update_rxqs(dev, flow);
 	return 0;
 error:
 	ret = rte_errno; /* Save rte_errno before cleanup. */
@@ -2022,6 +2072,7 @@ mlx5_flow_list_create(struct rte_eth_dev *dev,
 	}
 	/* Copy configuration. */
 	flow->queues = (uint16_t (*)[])(flow + 1);
+	flow->tunnel = parser.tunnel;
 	flow->rss_conf = (struct rte_flow_action_rss){
 		.func = RTE_ETH_HASH_FUNCTION_DEFAULT,
 		.level = 0,
@@ -2113,9 +2164,38 @@ mlx5_flow_list_destroy(struct rte_eth_dev *dev, struct mlx5_flows *list,
 	struct priv *priv = dev->data->dev_private;
 	unsigned int i;
 
-	if (flow->drop || !flow->mark)
+	if (flow->drop || !dev->data->dev_started)
 		goto free;
-	for (i = 0; i != flow->rss_conf.queue_num; ++i) {
+	for (i = 0; flow->tunnel && i != flow->rss_conf.queue_num; ++i) {
+		/* Update queue tunnel type. */
+		struct mlx5_rxq_data *rxq_data = (*priv->rxqs)
+						 [(*flow->queues)[i]];
+		struct mlx5_rxq_ctrl *rxq_ctrl =
+			container_of(rxq_data, struct mlx5_rxq_ctrl, rxq);
+		uint8_t tunnel = PTYPE_IDX(flow->tunnel);
+
+		RTE_ASSERT(rxq_ctrl->tunnel_types[tunnel] > 0);
+		rxq_ctrl->tunnel_types[tunnel] -= 1;
+		if (!rxq_ctrl->tunnel_types[tunnel]) {
+			/* Update tunnel type. */
+			uint8_t j;
+			uint8_t types = 0;
+			uint8_t last;
+
+			for (j = 0; j < RTE_DIM(rxq_ctrl->tunnel_types); j++)
+				if (rxq_ctrl->tunnel_types[j]) {
+					types += 1;
+					last = j;
+				}
+			/* Keep same if more than one tunnel types left. */
+			if (types == 1)
+				rxq_data->tunnel = ptype_ext[last];
+			else if (types == 0)
+				/* No tunnel type left. */
+				rxq_data->tunnel = 0;
+		}
+	}
+	for (i = 0; flow->mark && i != flow->rss_conf.queue_num; ++i) {
 		struct rte_flow *tmp;
 		int mark = 0;
 
@@ -2334,9 +2414,9 @@ mlx5_flow_stop(struct rte_eth_dev *dev, struct mlx5_flows *list)
 {
 	struct priv *priv = dev->data->dev_private;
 	struct rte_flow *flow;
+	unsigned int i;
 
 	TAILQ_FOREACH_REVERSE(flow, list, mlx5_flows, next) {
-		unsigned int i;
 		struct mlx5_ind_table_ibv *ind_tbl = NULL;
 
 		if (flow->drop) {
@@ -2382,6 +2462,16 @@ mlx5_flow_stop(struct rte_eth_dev *dev, struct mlx5_flows *list)
 		DRV_LOG(DEBUG, "port %u flow %p removed", dev->data->port_id,
 			(void *)flow);
 	}
+	/* Cleanup Rx queue tunnel info. */
+	for (i = 0; i != priv->rxqs_n; ++i) {
+		struct mlx5_rxq_data *q = (*priv->rxqs)[i];
+		struct mlx5_rxq_ctrl *rxq_ctrl =
+			container_of(q, struct mlx5_rxq_ctrl, rxq);
+
+		memset((void *)rxq_ctrl->tunnel_types, 0,
+		       sizeof(rxq_ctrl->tunnel_types));
+		q->tunnel = 0;
+	}
 }
 
 /**
@@ -2429,7 +2519,8 @@ mlx5_flow_start(struct rte_eth_dev *dev, struct mlx5_flows *list)
 					      flow->rss_conf.key_len,
 					      hash_rxq_init[i].hash_fields,
 					      flow->rss_conf.queue,
-					      flow->rss_conf.queue_num);
+					      flow->rss_conf.queue_num,
+					      flow->tunnel);
 			if (flow->frxq[i].hrxq)
 				goto flow_create;
 			flow->frxq[i].hrxq =
@@ -2437,7 +2528,8 @@ mlx5_flow_start(struct rte_eth_dev *dev, struct mlx5_flows *list)
 					      flow->rss_conf.key_len,
 					      hash_rxq_init[i].hash_fields,
 					      flow->rss_conf.queue,
-					      flow->rss_conf.queue_num);
+					      flow->rss_conf.queue_num,
+					      flow->tunnel);
 			if (!flow->frxq[i].hrxq) {
 				DRV_LOG(DEBUG,
 					"port %u flow %p cannot be applied",
@@ -2459,10 +2551,7 @@ mlx5_flow_start(struct rte_eth_dev *dev, struct mlx5_flows *list)
 			DRV_LOG(DEBUG, "port %u flow %p applied",
 				dev->data->port_id, (void *)flow);
 		}
-		if (!flow->mark)
-			continue;
-		for (i = 0; i != flow->rss_conf.queue_num; ++i)
-			(*priv->rxqs)[flow->rss_conf.queue[i]]->mark = 1;
+		mlx5_flow_create_update_rxqs(dev, flow);
 	}
 	return 0;
 }
diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
index 1e4354ab3..351acfc0f 100644
--- a/drivers/net/mlx5/mlx5_rxq.c
+++ b/drivers/net/mlx5/mlx5_rxq.c
@@ -1386,6 +1386,8 @@ mlx5_ind_table_ibv_verify(struct rte_eth_dev *dev)
  *   first queue index will be taken for the indirection table.
  * @param queues_n
  *   Number of queues.
+ * @param tunnel
+ *   Tunnel type.
  *
  * @return
  *   The Verbs object initialised, NULL otherwise and rte_errno is set.
@@ -1394,7 +1396,7 @@ struct mlx5_hrxq *
 mlx5_hrxq_new(struct rte_eth_dev *dev,
 	      const uint8_t *rss_key, uint32_t rss_key_len,
 	      uint64_t hash_fields,
-	      const uint16_t *queues, uint32_t queues_n)
+	      const uint16_t *queues, uint32_t queues_n, uint32_t tunnel)
 {
 	struct priv *priv = dev->data->dev_private;
 	struct mlx5_hrxq *hrxq;
@@ -1438,6 +1440,7 @@ mlx5_hrxq_new(struct rte_eth_dev *dev,
 	hrxq->qp = qp;
 	hrxq->rss_key_len = rss_key_len;
 	hrxq->hash_fields = hash_fields;
+	hrxq->tunnel = tunnel;
 	memcpy(hrxq->rss_key, rss_key, rss_key_len);
 	rte_atomic32_inc(&hrxq->refcnt);
 	LIST_INSERT_HEAD(&priv->hrxqs, hrxq, next);
@@ -1466,6 +1469,8 @@ mlx5_hrxq_new(struct rte_eth_dev *dev,
  *   first queue index will be taken for the indirection table.
  * @param queues_n
  *   Number of queues.
+ * @param tunnel
+ *   Tunnel type.
  *
  * @return
  *   An hash Rx queue on success.
@@ -1474,7 +1479,7 @@ struct mlx5_hrxq *
 mlx5_hrxq_get(struct rte_eth_dev *dev,
 	      const uint8_t *rss_key, uint32_t rss_key_len,
 	      uint64_t hash_fields,
-	      const uint16_t *queues, uint32_t queues_n)
+	      const uint16_t *queues, uint32_t queues_n, uint32_t tunnel)
 {
 	struct priv *priv = dev->data->dev_private;
 	struct mlx5_hrxq *hrxq;
@@ -1489,6 +1494,8 @@ mlx5_hrxq_get(struct rte_eth_dev *dev,
 			continue;
 		if (hrxq->hash_fields != hash_fields)
 			continue;
+		if (hrxq->tunnel != tunnel)
+			continue;
 		ind_tbl = mlx5_ind_table_ibv_get(dev, queues, queues_n);
 		if (!ind_tbl)
 			continue;
diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
index 1f422c70b..d061dfc8a 100644
--- a/drivers/net/mlx5/mlx5_rxtx.c
+++ b/drivers/net/mlx5/mlx5_rxtx.c
@@ -34,7 +34,7 @@
 #include "mlx5_prm.h"
 
 static __rte_always_inline uint32_t
-rxq_cq_to_pkt_type(volatile struct mlx5_cqe *cqe);
+rxq_cq_to_pkt_type(struct mlx5_rxq_data *rxq, volatile struct mlx5_cqe *cqe);
 
 static __rte_always_inline int
 mlx5_rx_poll_len(struct mlx5_rxq_data *rxq, volatile struct mlx5_cqe *cqe,
@@ -125,12 +125,14 @@ mlx5_set_ptype_table(void)
 	(*p)[0x8a] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
 		     RTE_PTYPE_L4_UDP;
 	/* Tunneled - L3 */
+	(*p)[0x40] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN;
 	(*p)[0x41] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
 		     RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
 		     RTE_PTYPE_INNER_L4_NONFRAG;
 	(*p)[0x42] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
 		     RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
 		     RTE_PTYPE_INNER_L4_NONFRAG;
+	(*p)[0xc0] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN;
 	(*p)[0xc1] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
 		     RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
 		     RTE_PTYPE_INNER_L4_NONFRAG;
@@ -1577,6 +1579,8 @@ mlx5_tx_burst_empw(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
 /**
  * Translate RX completion flags to packet type.
  *
+ * @param[in] rxq
+ *   Pointer to RX queue structure.
  * @param[in] cqe
  *   Pointer to CQE.
  *
@@ -1586,7 +1590,7 @@ mlx5_tx_burst_empw(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
  *   Packet type for struct rte_mbuf.
  */
 static inline uint32_t
-rxq_cq_to_pkt_type(volatile struct mlx5_cqe *cqe)
+rxq_cq_to_pkt_type(struct mlx5_rxq_data *rxq, volatile struct mlx5_cqe *cqe)
 {
 	uint8_t idx;
 	uint8_t pinfo = cqe->pkt_info;
@@ -1601,7 +1605,7 @@ rxq_cq_to_pkt_type(volatile struct mlx5_cqe *cqe)
 	 * bit[7] = outer_l3_type
 	 */
 	idx = ((pinfo & 0x3) << 6) | ((ptype & 0xfc00) >> 10);
-	return mlx5_ptype_table[idx];
+	return mlx5_ptype_table[idx] | rxq->tunnel * !!(idx & (1 << 6));
 }
 
 /**
@@ -1833,7 +1837,7 @@ mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
 			pkt = seg;
 			assert(len >= (rxq->crc_present << 2));
 			/* Update packet information. */
-			pkt->packet_type = rxq_cq_to_pkt_type(cqe);
+			pkt->packet_type = rxq_cq_to_pkt_type(rxq, cqe);
 			pkt->ol_flags = 0;
 			if (rss_hash_res && rxq->rss_hash) {
 				pkt->hash.rss = rss_hash_res;
diff --git a/drivers/net/mlx5/mlx5_rxtx.h b/drivers/net/mlx5/mlx5_rxtx.h
index a702cb603..6866f6818 100644
--- a/drivers/net/mlx5/mlx5_rxtx.h
+++ b/drivers/net/mlx5/mlx5_rxtx.h
@@ -104,6 +104,7 @@ struct mlx5_rxq_data {
 	void *cq_uar; /* CQ user access region. */
 	uint32_t cqn; /* CQ number. */
 	uint8_t cq_arm_sn; /* CQ arm seq number. */
+	uint32_t tunnel; /* Tunnel information. */
 } __rte_cache_aligned;
 
 /* Verbs Rx queue elements. */
@@ -125,6 +126,7 @@ struct mlx5_rxq_ctrl {
 	struct mlx5_rxq_ibv *ibv; /* Verbs elements. */
 	struct mlx5_rxq_data rxq; /* Data path structure. */
 	unsigned int socket; /* CPU socket ID for allocations. */
+	uint32_t tunnel_types[16]; /* Tunnel type counter. */
 	unsigned int irq:1; /* Whether IRQ is enabled. */
 	uint16_t idx; /* Queue index. */
 };
@@ -145,6 +147,7 @@ struct mlx5_hrxq {
 	struct mlx5_ind_table_ibv *ind_table; /* Indirection table. */
 	struct ibv_qp *qp; /* Verbs queue pair. */
 	uint64_t hash_fields; /* Verbs Hash fields. */
+	uint32_t tunnel; /* Tunnel type. */
 	uint32_t rss_key_len; /* Hash key length in bytes. */
 	uint8_t rss_key[]; /* Hash key. */
 };
@@ -248,11 +251,13 @@ int mlx5_ind_table_ibv_verify(struct rte_eth_dev *dev);
 struct mlx5_hrxq *mlx5_hrxq_new(struct rte_eth_dev *dev,
 				const uint8_t *rss_key, uint32_t rss_key_len,
 				uint64_t hash_fields,
-				const uint16_t *queues, uint32_t queues_n);
+				const uint16_t *queues, uint32_t queues_n,
+				uint32_t tunnel);
 struct mlx5_hrxq *mlx5_hrxq_get(struct rte_eth_dev *dev,
 				const uint8_t *rss_key, uint32_t rss_key_len,
 				uint64_t hash_fields,
-				const uint16_t *queues, uint32_t queues_n);
+				const uint16_t *queues, uint32_t queues_n,
+				uint32_t tunnel);
 int mlx5_hrxq_release(struct rte_eth_dev *dev, struct mlx5_hrxq *hxrq);
 int mlx5_hrxq_ibv_verify(struct rte_eth_dev *dev);
 uint64_t mlx5_get_rx_port_offloads(void);
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
index bbe1818ef..9f9136108 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
@@ -551,6 +551,7 @@ rxq_cq_to_ptype_oflags_v(struct mlx5_rxq_data *rxq,
 	const uint64x1_t mbuf_init = vld1_u64(&rxq->mbuf_initializer);
 	const uint64x1_t r32_mask = vcreate_u64(0xffffffff);
 	uint64x2_t rearm0, rearm1, rearm2, rearm3;
+	uint8_t pt_idx0, pt_idx1, pt_idx2, pt_idx3;
 
 	if (rxq->mark) {
 		const uint32x4_t ft_def = vdupq_n_u32(MLX5_FLOW_MARK_DEFAULT);
@@ -583,14 +584,18 @@ rxq_cq_to_ptype_oflags_v(struct mlx5_rxq_data *rxq,
 	ptype = vshrn_n_u32(ptype_info, 10);
 	/* Errored packets will have RTE_PTYPE_ALL_MASK. */
 	ptype = vorr_u16(ptype, op_err);
-	pkts[0]->packet_type =
-		mlx5_ptype_table[vget_lane_u8(vreinterpret_u8_u16(ptype), 6)];
-	pkts[1]->packet_type =
-		mlx5_ptype_table[vget_lane_u8(vreinterpret_u8_u16(ptype), 4)];
-	pkts[2]->packet_type =
-		mlx5_ptype_table[vget_lane_u8(vreinterpret_u8_u16(ptype), 2)];
-	pkts[3]->packet_type =
-		mlx5_ptype_table[vget_lane_u8(vreinterpret_u8_u16(ptype), 0)];
+	pt_idx0 = vget_lane_u8(vreinterpret_u8_u16(ptype), 6);
+	pt_idx1 = vget_lane_u8(vreinterpret_u8_u16(ptype), 4);
+	pt_idx2 = vget_lane_u8(vreinterpret_u8_u16(ptype), 2);
+	pt_idx3 = vget_lane_u8(vreinterpret_u8_u16(ptype), 0);
+	pkts[0]->packet_type = mlx5_ptype_table[pt_idx0] |
+			       !!(pt_idx0 & (1 << 6)) * rxq->tunnel;
+	pkts[1]->packet_type = mlx5_ptype_table[pt_idx1] |
+			       !!(pt_idx1 & (1 << 6)) * rxq->tunnel;
+	pkts[2]->packet_type = mlx5_ptype_table[pt_idx2] |
+			       !!(pt_idx2 & (1 << 6)) * rxq->tunnel;
+	pkts[3]->packet_type = mlx5_ptype_table[pt_idx3] |
+			       !!(pt_idx3 & (1 << 6)) * rxq->tunnel;
 	/* Fill flags for checksum and VLAN. */
 	pinfo = vandq_u32(ptype_info, ptype_ol_mask);
 	pinfo = vreinterpretq_u32_u8(
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
index c088bcb51..d2492481d 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
@@ -542,6 +542,7 @@ rxq_cq_to_ptype_oflags_v(struct mlx5_rxq_data *rxq, __m128i cqes[4],
 	const __m128i mbuf_init =
 		_mm_loadl_epi64((__m128i *)&rxq->mbuf_initializer);
 	__m128i rearm0, rearm1, rearm2, rearm3;
+	uint8_t pt_idx0, pt_idx1, pt_idx2, pt_idx3;
 
 	/* Extract pkt_info field. */
 	pinfo0 = _mm_unpacklo_epi32(cqes[0], cqes[1]);
@@ -595,10 +596,18 @@ rxq_cq_to_ptype_oflags_v(struct mlx5_rxq_data *rxq, __m128i cqes[4],
 	/* Errored packets will have RTE_PTYPE_ALL_MASK. */
 	op_err = _mm_srli_epi16(op_err, 8);
 	ptype = _mm_or_si128(ptype, op_err);
-	pkts[0]->packet_type = mlx5_ptype_table[_mm_extract_epi8(ptype, 0)];
-	pkts[1]->packet_type = mlx5_ptype_table[_mm_extract_epi8(ptype, 2)];
-	pkts[2]->packet_type = mlx5_ptype_table[_mm_extract_epi8(ptype, 4)];
-	pkts[3]->packet_type = mlx5_ptype_table[_mm_extract_epi8(ptype, 6)];
+	pt_idx0 = _mm_extract_epi8(ptype, 0);
+	pt_idx1 = _mm_extract_epi8(ptype, 2);
+	pt_idx2 = _mm_extract_epi8(ptype, 4);
+	pt_idx3 = _mm_extract_epi8(ptype, 6);
+	pkts[0]->packet_type = mlx5_ptype_table[pt_idx0] |
+			       !!(pt_idx0 & (1 << 6)) * rxq->tunnel;
+	pkts[1]->packet_type = mlx5_ptype_table[pt_idx1] |
+			       !!(pt_idx1 & (1 << 6)) * rxq->tunnel;
+	pkts[2]->packet_type = mlx5_ptype_table[pt_idx2] |
+			       !!(pt_idx2 & (1 << 6)) * rxq->tunnel;
+	pkts[3]->packet_type = mlx5_ptype_table[pt_idx3] |
+			       !!(pt_idx3 & (1 << 6)) * rxq->tunnel;
 	/* Fill flags for checksum and VLAN. */
 	pinfo = _mm_and_si128(pinfo, ptype_ol_mask);
 	pinfo = _mm_shuffle_epi8(cv_flag_sel, pinfo);
-- 
2.13.3