[dpdk-dev] [PATCH v7 3/8] net/ice: support vector SSE in RX

[Wenzhuo Lu <wenzhuo.lu@intel.com>]

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
---
 doc/guides/nics/features/ice_vec.ini  |  33 +++
 drivers/net/ice/Makefile              |   3 +
 drivers/net/ice/ice_ethdev.c          |   2 -
 drivers/net/ice/ice_ethdev.h          |   2 +
 drivers/net/ice/ice_rxtx.c            |  27 +-
 drivers/net/ice/ice_rxtx.h            |  21 +-
 drivers/net/ice/ice_rxtx_vec_common.h | 160 +++++++++++
 drivers/net/ice/ice_rxtx_vec_sse.c    | 490 ++++++++++++++++++++++++++++++++++
 drivers/net/ice/meson.build           |   4 +
 9 files changed, 736 insertions(+), 6 deletions(-)
 create mode 100644 doc/guides/nics/features/ice_vec.ini
 create mode 100644 drivers/net/ice/ice_rxtx_vec_common.h
 create mode 100644 drivers/net/ice/ice_rxtx_vec_sse.c

diff --git a/doc/guides/nics/features/ice_vec.ini b/doc/guides/nics/features/ice_vec.ini
new file mode 100644
index 0000000..1a19788
--- /dev/null
+++ b/doc/guides/nics/features/ice_vec.ini
@@ -0,0 +1,33 @@
+;
+; Supported features of the 'ice_vec' network poll mode driver.
+;
+; Refer to default.ini for the full list of available PMD features.
+;
+[Features]
+Speed capabilities   = Y
+Link status          = Y
+Link status event    = Y
+Rx interrupt         = Y
+Queue start/stop     = Y
+MTU update           = Y
+Jumbo frame          = Y
+Scattered Rx         = Y
+Promiscuous mode     = Y
+Allmulticast mode    = Y
+Unicast MAC filter   = Y
+Multicast MAC filter = Y
+RSS hash             = Y
+RSS key update       = Y
+RSS reta update      = Y
+VLAN filter          = Y
+Packet type parsing  = Y
+Rx descriptor status = Y
+Basic stats          = Y
+Extended stats       = Y
+FW version           = Y
+Module EEPROM dump   = Y
+BSD nic_uio          = Y
+Linux UIO            = Y
+Linux VFIO           = Y
+x86-32               = Y
+x86-64               = Y
diff --git a/drivers/net/ice/Makefile b/drivers/net/ice/Makefile
index 61846ca..92594bb 100644
--- a/drivers/net/ice/Makefile
+++ b/drivers/net/ice/Makefile
@@ -54,5 +54,8 @@ SRCS-$(CONFIG_RTE_LIBRTE_ICE_PMD) += ice_flow.c
 
 SRCS-$(CONFIG_RTE_LIBRTE_ICE_PMD) += ice_ethdev.c
 SRCS-$(CONFIG_RTE_LIBRTE_ICE_PMD) += ice_rxtx.c
+ifeq ($(CONFIG_RTE_ARCH_X86), y)
+SRCS-$(CONFIG_RTE_LIBRTE_ICE_PMD) += ice_rxtx_vec_sse.c
+endif
 
 include $(RTE_SDK)/mk/rte.lib.mk
diff --git a/drivers/net/ice/ice_ethdev.c b/drivers/net/ice/ice_ethdev.c
index 7233c3e..c468962 100644
--- a/drivers/net/ice/ice_ethdev.c
+++ b/drivers/net/ice/ice_ethdev.c
@@ -2,8 +2,6 @@
  * Copyright(c) 2018 Intel Corporation
  */
 
-#include <rte_ethdev_pci.h>
-
 #include "base/ice_sched.h"
 #include "ice_ethdev.h"
 #include "ice_rxtx.h"
diff --git a/drivers/net/ice/ice_ethdev.h b/drivers/net/ice/ice_ethdev.h
index 3cefa5b..151a09e 100644
--- a/drivers/net/ice/ice_ethdev.h
+++ b/drivers/net/ice/ice_ethdev.h
@@ -7,6 +7,8 @@
 
 #include <rte_kvargs.h>
 
+#include <rte_ethdev_pci.h>
+
 #include "base/ice_common.h"
 #include "base/ice_adminq_cmd.h"
 
diff --git a/drivers/net/ice/ice_rxtx.c b/drivers/net/ice/ice_rxtx.c
index 22e1fb5..1c6121f 100644
--- a/drivers/net/ice/ice_rxtx.c
+++ b/drivers/net/ice/ice_rxtx.c
@@ -7,8 +7,6 @@
 
 #include "ice_rxtx.h"
 
-#define ICE_TD_CMD ICE_TX_DESC_CMD_EOP
-
 #define ICE_TX_CKSUM_OFFLOAD_MASK (		 \
 		PKT_TX_IP_CKSUM |		 \
 		PKT_TX_L4_MASK |		 \
@@ -325,6 +323,9 @@
 	rxq->nb_rx_hold = 0;
 	rxq->pkt_first_seg = NULL;
 	rxq->pkt_last_seg = NULL;
+
+	rxq->rxrearm_start = 0;
+	rxq->rxrearm_nb = 0;
 }
 
 int
@@ -1501,6 +1502,12 @@
 #endif
 	    dev->rx_pkt_burst == ice_recv_scattered_pkts)
 		return ptypes;
+
+#ifdef RTE_ARCH_X86
+	if (dev->rx_pkt_burst == ice_recv_pkts_vec)
+		return ptypes;
+#endif
+
 	return NULL;
 }
 
@@ -2232,6 +2239,22 @@ void __attribute__((cold))
 	PMD_INIT_FUNC_TRACE();
 	struct ice_adapter *ad =
 		ICE_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
+#ifdef RTE_ARCH_X86
+	struct ice_rx_queue *rxq;
+	int i;
+
+	if (!ice_rx_vec_dev_check(dev)) {
+		for (i = 0; i < dev->data->nb_rx_queues; i++) {
+			rxq = dev->data->rx_queues[i];
+			(void)ice_rxq_vec_setup(rxq);
+		}
+		PMD_DRV_LOG(DEBUG, "Using Vector Rx (port %d).",
+			    dev->data->port_id);
+		dev->rx_pkt_burst = ice_recv_pkts_vec;
+
+		return;
+	}
+#endif
 
 	if (dev->data->scattered_rx) {
 		/* Set the non-LRO scattered function */
diff --git a/drivers/net/ice/ice_rxtx.h b/drivers/net/ice/ice_rxtx.h
index 78b4928..656ca0d 100644
--- a/drivers/net/ice/ice_rxtx.h
+++ b/drivers/net/ice/ice_rxtx.h
@@ -27,6 +27,15 @@
 
 #define ICE_SUPPORT_CHAIN_NUM 5
 
+#define ICE_TD_CMD                      ICE_TX_DESC_CMD_EOP
+
+#define ICE_VPMD_RX_BURST           32
+#define ICE_VPMD_TX_BURST           32
+#define ICE_RXQ_REARM_THRESH        32
+#define ICE_MAX_RX_BURST            ICE_RXQ_REARM_THRESH
+#define ICE_TX_MAX_FREE_BUF_SZ      64
+#define ICE_DESCS_PER_LOOP          4
+
 typedef void (*ice_rx_release_mbufs_t)(struct ice_rx_queue *rxq);
 typedef void (*ice_tx_release_mbufs_t)(struct ice_tx_queue *txq);
 
@@ -45,13 +54,16 @@ struct ice_rx_queue {
 	uint16_t nb_rx_hold; /* number of held free RX desc */
 	struct rte_mbuf *pkt_first_seg; /**< first segment of current packet */
 	struct rte_mbuf *pkt_last_seg; /**< last segment of current packet */
-#ifdef RTE_LIBRTE_ICE_RX_ALLOW_BULK_ALLOC
 	uint16_t rx_nb_avail; /**< number of staged packets ready */
 	uint16_t rx_next_avail; /**< index of next staged packets */
 	uint16_t rx_free_trigger; /**< triggers rx buffer allocation */
 	struct rte_mbuf fake_mbuf; /**< dummy mbuf */
 	struct rte_mbuf *rx_stage[ICE_RX_MAX_BURST * 2];
-#endif
+
+	uint16_t rxrearm_nb;	/**< number of remaining to be re-armed */
+	uint16_t rxrearm_start;	/**< the idx we start the re-arming from */
+	uint64_t mbuf_initializer; /**< value to init mbufs */
+
 	uint8_t port_id; /* device port ID */
 	uint8_t crc_len; /* 0 if CRC stripped, 4 otherwise */
 	uint16_t queue_id; /* RX queue index */
@@ -156,4 +168,9 @@ void ice_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 int ice_tx_descriptor_status(void *tx_queue, uint16_t offset);
 void ice_set_default_ptype_table(struct rte_eth_dev *dev);
 const uint32_t *ice_dev_supported_ptypes_get(struct rte_eth_dev *dev);
+
+int ice_rx_vec_dev_check(struct rte_eth_dev *dev);
+int ice_rxq_vec_setup(struct ice_rx_queue *rxq);
+uint16_t ice_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+			   uint16_t nb_pkts);
 #endif /* _ICE_RXTX_H_ */
diff --git a/drivers/net/ice/ice_rxtx_vec_common.h b/drivers/net/ice/ice_rxtx_vec_common.h
new file mode 100644
index 0000000..d41232d
--- /dev/null
+++ b/drivers/net/ice/ice_rxtx_vec_common.h
@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Intel Corporation
+ */
+
+#ifndef _ICE_RXTX_VEC_COMMON_H_
+#define _ICE_RXTX_VEC_COMMON_H_
+
+#include "ice_rxtx.h"
+
+static inline uint16_t
+ice_rx_reassemble_packets(struct ice_rx_queue *rxq, struct rte_mbuf **rx_bufs,
+			  uint16_t nb_bufs, uint8_t *split_flags)
+{
+	struct rte_mbuf *pkts[ICE_VPMD_RX_BURST] = {0}; /*finished pkts*/
+	struct rte_mbuf *start = rxq->pkt_first_seg;
+	struct rte_mbuf *end =  rxq->pkt_last_seg;
+	unsigned int pkt_idx, buf_idx;
+
+	for (buf_idx = 0, pkt_idx = 0; buf_idx < nb_bufs; buf_idx++) {
+		if (end) {
+			/* processing a split packet */
+			end->next = rx_bufs[buf_idx];
+			rx_bufs[buf_idx]->data_len += rxq->crc_len;
+
+			start->nb_segs++;
+			start->pkt_len += rx_bufs[buf_idx]->data_len;
+			end = end->next;
+
+			if (!split_flags[buf_idx]) {
+				/* it's the last packet of the set */
+				start->hash = end->hash;
+				start->ol_flags = end->ol_flags;
+				/* we need to strip crc for the whole packet */
+				start->pkt_len -= rxq->crc_len;
+				if (end->data_len > rxq->crc_len) {
+					end->data_len -= rxq->crc_len;
+				} else {
+					/* free up last mbuf */
+					struct rte_mbuf *secondlast = start;
+
+					start->nb_segs--;
+					while (secondlast->next != end)
+						secondlast = secondlast->next;
+					secondlast->data_len -= (rxq->crc_len -
+							end->data_len);
+					secondlast->next = NULL;
+					rte_pktmbuf_free_seg(end);
+				}
+				pkts[pkt_idx++] = start;
+				start = NULL;
+				end = NULL;
+			}
+		} else {
+			/* not processing a split packet */
+			if (!split_flags[buf_idx]) {
+				/* not a split packet, save and skip */
+				pkts[pkt_idx++] = rx_bufs[buf_idx];
+				continue;
+			}
+			start = rx_bufs[buf_idx];
+			end = start;
+			rx_bufs[buf_idx]->data_len += rxq->crc_len;
+			rx_bufs[buf_idx]->pkt_len += rxq->crc_len;
+		}
+	}
+
+	/* save the partial packet for next time */
+	rxq->pkt_first_seg = start;
+	rxq->pkt_last_seg = end;
+	rte_memcpy(rx_bufs, pkts, pkt_idx * (sizeof(*pkts)));
+	return pkt_idx;
+}
+
+static inline void
+_ice_rx_queue_release_mbufs_vec(struct ice_rx_queue *rxq)
+{
+	const unsigned int mask = rxq->nb_rx_desc - 1;
+	unsigned int i;
+
+	if (unlikely(!rxq->sw_ring)) {
+		PMD_DRV_LOG(DEBUG, "sw_ring is NULL");
+		return;
+	}
+
+	if (rxq->rxrearm_nb >= rxq->nb_rx_desc)
+		return;
+
+	/* free all mbufs that are valid in the ring */
+	if (rxq->rxrearm_nb == 0) {
+		for (i = 0; i < rxq->nb_rx_desc; i++) {
+			if (rxq->sw_ring[i].mbuf)
+				rte_pktmbuf_free_seg(rxq->sw_ring[i].mbuf);
+		}
+	} else {
+		for (i = rxq->rx_tail;
+		     i != rxq->rxrearm_start;
+		     i = (i + 1) & mask) {
+			if (rxq->sw_ring[i].mbuf)
+				rte_pktmbuf_free_seg(rxq->sw_ring[i].mbuf);
+		}
+	}
+
+	rxq->rxrearm_nb = rxq->nb_rx_desc;
+
+	/* set all entries to NULL */
+	memset(rxq->sw_ring, 0, sizeof(rxq->sw_ring[0]) * rxq->nb_rx_desc);
+}
+
+static inline int
+ice_rxq_vec_setup_default(struct ice_rx_queue *rxq)
+{
+	uintptr_t p;
+	struct rte_mbuf mb_def = { .buf_addr = 0 }; /* zeroed mbuf */
+
+	mb_def.nb_segs = 1;
+	mb_def.data_off = RTE_PKTMBUF_HEADROOM;
+	mb_def.port = rxq->port_id;
+	rte_mbuf_refcnt_set(&mb_def, 1);
+
+	/* prevent compiler reordering: rearm_data covers previous fields */
+	rte_compiler_barrier();
+	p = (uintptr_t)&mb_def.rearm_data;
+	rxq->mbuf_initializer = *(uint64_t *)p;
+	return 0;
+}
+
+static inline int
+ice_rx_vec_queue_default(struct ice_rx_queue *rxq)
+{
+	if (!rxq)
+		return -1;
+
+	if (!rte_is_power_of_2(rxq->nb_rx_desc))
+		return -1;
+
+	if (rxq->rx_free_thresh < ICE_VPMD_RX_BURST)
+		return -1;
+
+	if (rxq->nb_rx_desc % rxq->rx_free_thresh)
+		return -1;
+
+	return 0;
+}
+
+static inline int
+ice_rx_vec_dev_check_default(struct rte_eth_dev *dev)
+{
+	int i;
+	struct ice_rx_queue *rxq;
+
+	for (i = 0; i < dev->data->nb_rx_queues; i++) {
+		rxq = dev->data->rx_queues[i];
+		if (ice_rx_vec_queue_default(rxq))
+			return -1;
+	}
+
+	return 0;
+}
+
+#endif
diff --git a/drivers/net/ice/ice_rxtx_vec_sse.c b/drivers/net/ice/ice_rxtx_vec_sse.c
new file mode 100644
index 0000000..ec31e36
--- /dev/null
+++ b/drivers/net/ice/ice_rxtx_vec_sse.c
@@ -0,0 +1,490 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Intel Corporation
+ */
+
+#include "ice_rxtx_vec_common.h"
+
+#include <tmmintrin.h>
+
+#ifndef __INTEL_COMPILER
+#pragma GCC diagnostic ignored "-Wcast-qual"
+#endif
+
+static inline void
+ice_rxq_rearm(struct ice_rx_queue *rxq)
+{
+	int i;
+	uint16_t rx_id;
+	volatile union ice_rx_desc *rxdp;
+	struct ice_rx_entry *rxep = &rxq->sw_ring[rxq->rxrearm_start];
+	struct rte_mbuf *mb0, *mb1;
+	__m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM,
+					  RTE_PKTMBUF_HEADROOM);
+	__m128i dma_addr0, dma_addr1;
+
+	rxdp = rxq->rx_ring + rxq->rxrearm_start;
+
+	/* Pull 'n' more MBUFs into the software ring */
+	if (rte_mempool_get_bulk(rxq->mp,
+				 (void *)rxep,
+				 ICE_RXQ_REARM_THRESH) < 0) {
+		if (rxq->rxrearm_nb + ICE_RXQ_REARM_THRESH >=
+		    rxq->nb_rx_desc) {
+			dma_addr0 = _mm_setzero_si128();
+			for (i = 0; i < ICE_DESCS_PER_LOOP; i++) {
+				rxep[i].mbuf = &rxq->fake_mbuf;
+				_mm_store_si128((__m128i *)&rxdp[i].read,
+						dma_addr0);
+			}
+		}
+		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
+			ICE_RXQ_REARM_THRESH;
+		return;
+	}
+
+	/* Initialize the mbufs in vector, process 2 mbufs in one loop */
+	for (i = 0; i < ICE_RXQ_REARM_THRESH; i += 2, rxep += 2) {
+		__m128i vaddr0, vaddr1;
+
+		mb0 = rxep[0].mbuf;
+		mb1 = rxep[1].mbuf;
+
+		/* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */
+		RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
+				 offsetof(struct rte_mbuf, buf_addr) + 8);
+		vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr);
+		vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr);
+
+		/* convert pa to dma_addr hdr/data */
+		dma_addr0 = _mm_unpackhi_epi64(vaddr0, vaddr0);
+		dma_addr1 = _mm_unpackhi_epi64(vaddr1, vaddr1);
+
+		/* add headroom to pa values */
+		dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room);
+		dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
+
+		/* flush desc with pa dma_addr */
+		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
+		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
+	}
+
+	rxq->rxrearm_start += ICE_RXQ_REARM_THRESH;
+	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
+		rxq->rxrearm_start = 0;
+
+	rxq->rxrearm_nb -= ICE_RXQ_REARM_THRESH;
+
+	rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
+			   (rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
+
+	/* Update the tail pointer on the NIC */
+	ICE_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+}
+
+static inline void
+ice_rx_desc_to_olflags_v(struct ice_rx_queue *rxq, __m128i descs[4],
+			 struct rte_mbuf **rx_pkts)
+{
+	const __m128i mbuf_init = _mm_set_epi64x(0, rxq->mbuf_initializer);
+	__m128i rearm0, rearm1, rearm2, rearm3;
+
+	__m128i vlan0, vlan1, rss, l3_l4e;
+
+	/* mask everything except RSS, flow director and VLAN flags
+	 * bit2 is for VLAN tag, bit11 for flow director indication
+	 * bit13:12 for RSS indication.
+	 */
+	const __m128i rss_vlan_msk = _mm_set_epi32(0x1c03804, 0x1c03804,
+						   0x1c03804, 0x1c03804);
+
+	const __m128i cksum_mask = _mm_set_epi32(PKT_RX_IP_CKSUM_GOOD |
+						 PKT_RX_IP_CKSUM_BAD |
+						 PKT_RX_L4_CKSUM_GOOD |
+						 PKT_RX_L4_CKSUM_BAD |
+						 PKT_RX_EIP_CKSUM_BAD,
+						 PKT_RX_IP_CKSUM_GOOD |
+						 PKT_RX_IP_CKSUM_BAD |
+						 PKT_RX_L4_CKSUM_GOOD |
+						 PKT_RX_L4_CKSUM_BAD |
+						 PKT_RX_EIP_CKSUM_BAD,
+						 PKT_RX_IP_CKSUM_GOOD |
+						 PKT_RX_IP_CKSUM_BAD |
+						 PKT_RX_L4_CKSUM_GOOD |
+						 PKT_RX_L4_CKSUM_BAD |
+						 PKT_RX_EIP_CKSUM_BAD,
+						 PKT_RX_IP_CKSUM_GOOD |
+						 PKT_RX_IP_CKSUM_BAD |
+						 PKT_RX_L4_CKSUM_GOOD |
+						 PKT_RX_L4_CKSUM_BAD |
+						 PKT_RX_EIP_CKSUM_BAD);
+
+	/* map rss and vlan type to rss hash and vlan flag */
+	const __m128i vlan_flags = _mm_set_epi8(0, 0, 0, 0,
+			0, 0, 0, 0,
+			0, 0, 0, PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
+			0, 0, 0, 0);
+
+	const __m128i rss_flags = _mm_set_epi8(0, 0, 0, 0,
+			0, 0, 0, 0,
+			PKT_RX_RSS_HASH | PKT_RX_FDIR, PKT_RX_RSS_HASH, 0, 0,
+			0, 0, PKT_RX_FDIR, 0);
+
+	const __m128i l3_l4e_flags = _mm_set_epi8(0, 0, 0, 0, 0, 0, 0, 0,
+			/* shift right 1 bit to make sure it not exceed 255 */
+			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+			 PKT_RX_IP_CKSUM_BAD) >> 1,
+			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD |
+			 PKT_RX_L4_CKSUM_BAD) >> 1,
+			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD) >> 1,
+			(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> 1,
+			PKT_RX_IP_CKSUM_BAD >> 1,
+			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD) >> 1);
+
+	vlan0 = _mm_unpackhi_epi32(descs[0], descs[1]);
+	vlan1 = _mm_unpackhi_epi32(descs[2], descs[3]);
+	vlan0 = _mm_unpacklo_epi64(vlan0, vlan1);
+
+	vlan1 = _mm_and_si128(vlan0, rss_vlan_msk);
+	vlan0 = _mm_shuffle_epi8(vlan_flags, vlan1);
+
+	rss = _mm_srli_epi32(vlan1, 11);
+	rss = _mm_shuffle_epi8(rss_flags, rss);
+
+	l3_l4e = _mm_srli_epi32(vlan1, 22);
+	l3_l4e = _mm_shuffle_epi8(l3_l4e_flags, l3_l4e);
+	/* then we shift left 1 bit */
+	l3_l4e = _mm_slli_epi32(l3_l4e, 1);
+	/* we need to mask out the reduntant bits */
+	l3_l4e = _mm_and_si128(l3_l4e, cksum_mask);
+
+	vlan0 = _mm_or_si128(vlan0, rss);
+	vlan0 = _mm_or_si128(vlan0, l3_l4e);
+
+	/**
+	 * At this point, we have the 4 sets of flags in the low 16-bits
+	 * of each 32-bit value in vlan0.
+	 * We want to extract these, and merge them with the mbuf init data
+	 * so we can do a single 16-byte write to the mbuf to set the flags
+	 * and all the other initialization fields. Extracting the
+	 * appropriate flags means that we have to do a shift and blend for
+	 * each mbuf before we do the write.
+	 */
+	rearm0 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vlan0, 8), 0x10);
+	rearm1 = _mm_blend_epi16(mbuf_init, _mm_slli_si128(vlan0, 4), 0x10);
+	rearm2 = _mm_blend_epi16(mbuf_init, vlan0, 0x10);
+	rearm3 = _mm_blend_epi16(mbuf_init, _mm_srli_si128(vlan0, 4), 0x10);
+
+	/* write the rearm data and the olflags in one write */
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, ol_flags) !=
+			 offsetof(struct rte_mbuf, rearm_data) + 8);
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, rearm_data) !=
+			 RTE_ALIGN(offsetof(struct rte_mbuf, rearm_data), 16));
+	_mm_store_si128((__m128i *)&rx_pkts[0]->rearm_data, rearm0);
+	_mm_store_si128((__m128i *)&rx_pkts[1]->rearm_data, rearm1);
+	_mm_store_si128((__m128i *)&rx_pkts[2]->rearm_data, rearm2);
+	_mm_store_si128((__m128i *)&rx_pkts[3]->rearm_data, rearm3);
+}
+
+#define PKTLEN_SHIFT     10
+
+static inline void
+ice_rx_desc_to_ptype_v(__m128i descs[4], struct rte_mbuf **rx_pkts,
+		       uint32_t *ptype_tbl)
+{
+	__m128i ptype0 = _mm_unpackhi_epi64(descs[0], descs[1]);
+	__m128i ptype1 = _mm_unpackhi_epi64(descs[2], descs[3]);
+
+	ptype0 = _mm_srli_epi64(ptype0, 30);
+	ptype1 = _mm_srli_epi64(ptype1, 30);
+
+	rx_pkts[0]->packet_type = ptype_tbl[_mm_extract_epi8(ptype0, 0)];
+	rx_pkts[1]->packet_type = ptype_tbl[_mm_extract_epi8(ptype0, 8)];
+	rx_pkts[2]->packet_type = ptype_tbl[_mm_extract_epi8(ptype1, 0)];
+	rx_pkts[3]->packet_type = ptype_tbl[_mm_extract_epi8(ptype1, 8)];
+}
+
+/**
+ * Notice:
+ * - nb_pkts < ICE_DESCS_PER_LOOP, just return no packet
+ * - nb_pkts > ICE_VPMD_RX_BURST, only scan ICE_VPMD_RX_BURST
+ *   numbers of DD bits
+ */
+static inline uint16_t
+_ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
+		       uint16_t nb_pkts, uint8_t *split_packet)
+{
+	volatile union ice_rx_desc *rxdp;
+	struct ice_rx_entry *sw_ring;
+	uint16_t nb_pkts_recd;
+	int pos;
+	uint64_t var;
+	__m128i shuf_msk;
+	uint32_t *ptype_tbl = rxq->vsi->adapter->ptype_tbl;
+
+	__m128i crc_adjust = _mm_set_epi16
+				(0, 0, 0,    /* ignore non-length fields */
+				 -rxq->crc_len, /* sub crc on data_len */
+				 0,          /* ignore high-16bits of pkt_len */
+				 -rxq->crc_len, /* sub crc on pkt_len */
+				 0, 0            /* ignore pkt_type field */
+				);
+	/**
+	 * compile-time check the above crc_adjust layout is correct.
+	 * NOTE: the first field (lowest address) is given last in set_epi16
+	 * call above.
+	 */
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, pkt_len) !=
+			 offsetof(struct rte_mbuf, rx_descriptor_fields1) + 4);
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, data_len) !=
+			 offsetof(struct rte_mbuf, rx_descriptor_fields1) + 8);
+	__m128i dd_check, eop_check;
+
+	/* nb_pkts shall be less equal than ICE_MAX_RX_BURST */
+	nb_pkts = RTE_MIN(nb_pkts, ICE_MAX_RX_BURST);
+
+	/* nb_pkts has to be floor-aligned to ICE_DESCS_PER_LOOP */
+	nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, ICE_DESCS_PER_LOOP);
+
+	/* Just the act of getting into the function from the application is
+	 * going to cost about 7 cycles
+	 */
+	rxdp = rxq->rx_ring + rxq->rx_tail;
+
+	rte_prefetch0(rxdp);
+
+	/* See if we need to rearm the RX queue - gives the prefetch a bit
+	 * of time to act
+	 */
+	if (rxq->rxrearm_nb > ICE_RXQ_REARM_THRESH)
+		ice_rxq_rearm(rxq);
+
+	/* Before we start moving massive data around, check to see if
+	 * there is actually a packet available
+	 */
+	if (!(rxdp->wb.qword1.status_error_len &
+	      rte_cpu_to_le_32(1 << ICE_RX_DESC_STATUS_DD_S)))
+		return 0;
+
+	/* 4 packets DD mask */
+	dd_check = _mm_set_epi64x(0x0000000100000001LL, 0x0000000100000001LL);
+
+	/* 4 packets EOP mask */
+	eop_check = _mm_set_epi64x(0x0000000200000002LL, 0x0000000200000002LL);
+
+	/* mask to shuffle from desc. to mbuf */
+	shuf_msk = _mm_set_epi8
+			(7, 6, 5, 4,  /* octet 4~7, 32bits rss */
+			 3, 2,        /* octet 2~3, low 16 bits vlan_macip */
+			 15, 14,      /* octet 15~14, 16 bits data_len */
+			 0xFF, 0xFF,  /* skip high 16 bits pkt_len, zero out */
+			 15, 14,      /* octet 15~14, low 16 bits pkt_len */
+			 0xFF, 0xFF,  /* pkt_type set as unknown */
+			 0xFF, 0xFF  /*pkt_type set as unknown */
+			);
+	/**
+	 * Compile-time verify the shuffle mask
+	 * NOTE: some field positions already verified above, but duplicated
+	 * here for completeness in case of future modifications.
+	 */
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, pkt_len) !=
+			 offsetof(struct rte_mbuf, rx_descriptor_fields1) + 4);
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, data_len) !=
+			 offsetof(struct rte_mbuf, rx_descriptor_fields1) + 8);
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, vlan_tci) !=
+			 offsetof(struct rte_mbuf, rx_descriptor_fields1) + 10);
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, hash) !=
+			 offsetof(struct rte_mbuf, rx_descriptor_fields1) + 12);
+
+	/* Cache is empty -> need to scan the buffer rings, but first move
+	 * the next 'n' mbufs into the cache
+	 */
+	sw_ring = &rxq->sw_ring[rxq->rx_tail];
+
+	/* A. load 4 packet in one loop
+	 * [A*. mask out 4 unused dirty field in desc]
+	 * B. copy 4 mbuf point from swring to rx_pkts
+	 * C. calc the number of DD bits among the 4 packets
+	 * [C*. extract the end-of-packet bit, if requested]
+	 * D. fill info. from desc to mbuf
+	 */
+
+	for (pos = 0, nb_pkts_recd = 0; pos < nb_pkts;
+	     pos += ICE_DESCS_PER_LOOP,
+	     rxdp += ICE_DESCS_PER_LOOP) {
+		__m128i descs[ICE_DESCS_PER_LOOP];
+		__m128i pkt_mb1, pkt_mb2, pkt_mb3, pkt_mb4;
+		__m128i zero, staterr, sterr_tmp1, sterr_tmp2;
+		/* 2 64 bit or 4 32 bit mbuf pointers in one XMM reg. */
+		__m128i mbp1;
+#if defined(RTE_ARCH_X86_64)
+		__m128i mbp2;
+#endif
+
+		/* B.1 load 2 (64 bit) or 4 (32 bit) mbuf points */
+		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
+		/* Read desc statuses backwards to avoid race condition */
+		/* A.1 load 4 pkts desc */
+		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
+		rte_compiler_barrier();
+
+		/* B.2 copy 2 64 bit or 4 32 bit mbuf point into rx_pkts */
+		_mm_storeu_si128((__m128i *)&rx_pkts[pos], mbp1);
+
+#if defined(RTE_ARCH_X86_64)
+		/* B.1 load 2 64 bit mbuf points */
+		mbp2 = _mm_loadu_si128((__m128i *)&sw_ring[pos + 2]);
+#endif
+
+		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
+		rte_compiler_barrier();
+		/* B.1 load 2 mbuf point */
+		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
+		rte_compiler_barrier();
+		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
+
+#if defined(RTE_ARCH_X86_64)
+		/* B.2 copy 2 mbuf point into rx_pkts  */
+		_mm_storeu_si128((__m128i *)&rx_pkts[pos + 2], mbp2);
+#endif
+
+		if (split_packet) {
+			rte_mbuf_prefetch_part2(rx_pkts[pos]);
+			rte_mbuf_prefetch_part2(rx_pkts[pos + 1]);
+			rte_mbuf_prefetch_part2(rx_pkts[pos + 2]);
+			rte_mbuf_prefetch_part2(rx_pkts[pos + 3]);
+		}
+
+		/* avoid compiler reorder optimization */
+		rte_compiler_barrier();
+
+		/* pkt 3,4 shift the pktlen field to be 16-bit aligned*/
+		const __m128i len3 = _mm_slli_epi32(descs[3], PKTLEN_SHIFT);
+		const __m128i len2 = _mm_slli_epi32(descs[2], PKTLEN_SHIFT);
+
+		/* merge the now-aligned packet length fields back in */
+		descs[3] = _mm_blend_epi16(descs[3], len3, 0x80);
+		descs[2] = _mm_blend_epi16(descs[2], len2, 0x80);
+
+		/* D.1 pkt 3,4 convert format from desc to pktmbuf */
+		pkt_mb4 = _mm_shuffle_epi8(descs[3], shuf_msk);
+		pkt_mb3 = _mm_shuffle_epi8(descs[2], shuf_msk);
+
+		/* C.1 4=>2 filter staterr info only */
+		sterr_tmp2 = _mm_unpackhi_epi32(descs[3], descs[2]);
+		/* C.1 4=>2 filter staterr info only */
+		sterr_tmp1 = _mm_unpackhi_epi32(descs[1], descs[0]);
+
+		ice_rx_desc_to_olflags_v(rxq, descs, &rx_pkts[pos]);
+
+		/* D.2 pkt 3,4 set in_port/nb_seg and remove crc */
+		pkt_mb4 = _mm_add_epi16(pkt_mb4, crc_adjust);
+		pkt_mb3 = _mm_add_epi16(pkt_mb3, crc_adjust);
+
+		/* pkt 1,2 shift the pktlen field to be 16-bit aligned*/
+		const __m128i len1 = _mm_slli_epi32(descs[1], PKTLEN_SHIFT);
+		const __m128i len0 = _mm_slli_epi32(descs[0], PKTLEN_SHIFT);
+
+		/* merge the now-aligned packet length fields back in */
+		descs[1] = _mm_blend_epi16(descs[1], len1, 0x80);
+		descs[0] = _mm_blend_epi16(descs[0], len0, 0x80);
+
+		/* D.1 pkt 1,2 convert format from desc to pktmbuf */
+		pkt_mb2 = _mm_shuffle_epi8(descs[1], shuf_msk);
+		pkt_mb1 = _mm_shuffle_epi8(descs[0], shuf_msk);
+
+		/* C.2 get 4 pkts staterr value  */
+		zero = _mm_xor_si128(dd_check, dd_check);
+		staterr = _mm_unpacklo_epi32(sterr_tmp1, sterr_tmp2);
+
+		/* D.3 copy final 3,4 data to rx_pkts */
+		_mm_storeu_si128
+			((void *)&rx_pkts[pos + 3]->rx_descriptor_fields1,
+			 pkt_mb4);
+		_mm_storeu_si128
+			((void *)&rx_pkts[pos + 2]->rx_descriptor_fields1,
+			 pkt_mb3);
+
+		/* D.2 pkt 1,2 set in_port/nb_seg and remove crc */
+		pkt_mb2 = _mm_add_epi16(pkt_mb2, crc_adjust);
+		pkt_mb1 = _mm_add_epi16(pkt_mb1, crc_adjust);
+
+		/* C* extract and record EOP bit */
+		if (split_packet) {
+			__m128i eop_shuf_mask = _mm_set_epi8(0xFF, 0xFF,
+							     0xFF, 0xFF,
+							     0xFF, 0xFF,
+							     0xFF, 0xFF,
+							     0xFF, 0xFF,
+							     0xFF, 0xFF,
+							     0x04, 0x0C,
+							     0x00, 0x08);
+
+			/* and with mask to extract bits, flipping 1-0 */
+			__m128i eop_bits = _mm_andnot_si128(staterr, eop_check);
+			/* the staterr values are not in order, as the count
+			 * count of dd bits doesn't care. However, for end of
+			 * packet tracking, we do care, so shuffle. This also
+			 * compresses the 32-bit values to 8-bit
+			 */
+			eop_bits = _mm_shuffle_epi8(eop_bits, eop_shuf_mask);
+			/* store the resulting 32-bit value */
+			*(int *)split_packet = _mm_cvtsi128_si32(eop_bits);
+			split_packet += ICE_DESCS_PER_LOOP;
+		}
+
+		/* C.3 calc available number of desc */
+		staterr = _mm_and_si128(staterr, dd_check);
+		staterr = _mm_packs_epi32(staterr, zero);
+
+		/* D.3 copy final 1,2 data to rx_pkts */
+		_mm_storeu_si128
+			((void *)&rx_pkts[pos + 1]->rx_descriptor_fields1,
+			 pkt_mb2);
+		_mm_storeu_si128((void *)&rx_pkts[pos]->rx_descriptor_fields1,
+				 pkt_mb1);
+		ice_rx_desc_to_ptype_v(descs, &rx_pkts[pos], ptype_tbl);
+		/* C.4 calc avaialbe number of desc */
+		var = __builtin_popcountll(_mm_cvtsi128_si64(staterr));
+		nb_pkts_recd += var;
+		if (likely(var != ICE_DESCS_PER_LOOP))
+			break;
+	}
+
+	/* Update our internal tail pointer */
+	rxq->rx_tail = (uint16_t)(rxq->rx_tail + nb_pkts_recd);
+	rxq->rx_tail = (uint16_t)(rxq->rx_tail & (rxq->nb_rx_desc - 1));
+	rxq->rxrearm_nb = (uint16_t)(rxq->rxrearm_nb + nb_pkts_recd);
+
+	return nb_pkts_recd;
+}
+
+/**
+ * Notice:
+ * - nb_pkts < ICE_DESCS_PER_LOOP, just return no packet
+ * - nb_pkts > ICE_VPMD_RX_BURST, only scan ICE_VPMD_RX_BURST
+ *   numbers of DD bits
+ */
+uint16_t
+ice_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+		  uint16_t nb_pkts)
+{
+	return _ice_recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
+}
+
+int __attribute__((cold))
+ice_rxq_vec_setup(struct ice_rx_queue *rxq)
+{
+	if (!rxq)
+		return -1;
+
+	rxq->rx_rel_mbufs = _ice_rx_queue_release_mbufs_vec;
+	return ice_rxq_vec_setup_default(rxq);
+}
+
+int __attribute__((cold))
+ice_rx_vec_dev_check(struct rte_eth_dev *dev)
+{
+	return ice_rx_vec_dev_check_default(dev);
+}
diff --git a/drivers/net/ice/meson.build b/drivers/net/ice/meson.build
index 857dc0e..469264d 100644
--- a/drivers/net/ice/meson.build
+++ b/drivers/net/ice/meson.build
@@ -11,3 +11,7 @@ sources = files(
 
 deps += ['hash']
 includes += include_directories('base')
+
+if arch_subdir == 'x86'
+	sources += files('ice_rxtx_vec_sse.c')
+endif
-- 
1.9.3