use ARM NEON intrinsic to implement ixgbe vPMD

Signed-off-by: Jianbo Liu <redacted>
---
 drivers/net/ixgbe/Makefile              |   4 +
 drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c | 561 ++++++++++++++++++++++++++++++++
 2 files changed, 565 insertions(+)
 create mode 100644 drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c

diff --git a/drivers/net/ixgbe/Makefile b/drivers/net/ixgbe/Makefile
index 50bf51c..b1c7a60 100644
--- a/drivers/net/ixgbe/Makefile
+++ b/drivers/net/ixgbe/Makefile

@@ -108,7 +108,11 @@ SRCS-$(CONFIG_RTE_LIBRTE_IXGBE_PMD) += ixgbe_rxtx.c
 SRCS-$(CONFIG_RTE_LIBRTE_IXGBE_PMD) += ixgbe_ethdev.c
 SRCS-$(CONFIG_RTE_LIBRTE_IXGBE_PMD) += ixgbe_fdir.c
 SRCS-$(CONFIG_RTE_LIBRTE_IXGBE_PMD) += ixgbe_pf.c
+ifeq ($(CONFIG_RTE_ARCH_ARM64),y)
+SRCS-$(CONFIG_RTE_IXGBE_INC_VECTOR) += ixgbe_rxtx_vec_neon.c
+else
 SRCS-$(CONFIG_RTE_IXGBE_INC_VECTOR) += ixgbe_rxtx_vec.c
+endif
 
 ifeq ($(CONFIG_RTE_NIC_BYPASS),y)
 SRCS-$(CONFIG_RTE_LIBRTE_IXGBE_PMD) += ixgbe_bypass.c

diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
new file mode 100644
index 0000000..11a6115
--- /dev/null
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c

@@ -0,0 +1,561 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2010-2015 Intel Corporation. All rights reserved.
+ *   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 Intel 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.
+ */
+
+#include <stdint.h>
+#include <rte_ethdev.h>
+#include <rte_malloc.h>
+
+#include "ixgbe_ethdev.h"
+#include "ixgbe_rxtx.h"
+#include "ixgbe_rxtx_vec_common.h"
+
+#include <arm_neon.h>
+
+#pragma GCC diagnostic ignored "-Wcast-qual"
+
+static inline void
+ixgbe_rxq_rearm(struct ixgbe_rx_queue *rxq)
+{
+	int i;
+	uint16_t rx_id;
+	volatile union ixgbe_adv_rx_desc *rxdp;
+	struct ixgbe_rx_entry *rxep = &rxq->sw_ring[rxq->rxrearm_start];
+	struct rte_mbuf *mb0, *mb1;
+	uint64x2_t dma_addr0, dma_addr1;
+	uint64x2_t zero = vdupq_n_u64(0);
+	uint64_t paddr;
+	uint8x8_t p;
+
+	rxdp = rxq->rx_ring + rxq->rxrearm_start;
+
+	/* Pull 'n' more MBUFs into the software ring */
+	if (unlikely(rte_mempool_get_bulk(rxq->mb_pool,
+					  (void *)rxep,
+					  RTE_IXGBE_RXQ_REARM_THRESH) < 0)) {
+		if (rxq->rxrearm_nb + RTE_IXGBE_RXQ_REARM_THRESH >=
+		    rxq->nb_rx_desc) {
+			for (i = 0; i < RTE_IXGBE_DESCS_PER_LOOP; i++) {
+				rxep[i].mbuf = &rxq->fake_mbuf;
+				vst1q_u64((uint64_t *)&rxdp[i].read,
+					  zero);
+			}
+		}
+		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
+			RTE_IXGBE_RXQ_REARM_THRESH;
+		return;
+	}
+
+	p = vld1_u8((uint8_t *)&rxq->mbuf_initializer);
+
+	/* Initialize the mbufs in vector, process 2 mbufs in one loop */
+	for (i = 0; i < RTE_IXGBE_RXQ_REARM_THRESH; i += 2, rxep += 2) {
+		mb0 = rxep[0].mbuf;
+		mb1 = rxep[1].mbuf;
+
+		/*
+		 * Flush mbuf with pkt template.
+		 * Data to be rearmed is 6 bytes long.
+		 * Though, RX will overwrite ol_flags that are coming next
+		 * anyway. So overwrite whole 8 bytes with one load:
+		 * 6 bytes of rearm_data plus first 2 bytes of ol_flags.
+		 */
+		vst1_u8((uint8_t *)&mb0->rearm_data, p);
+		paddr = mb0->buf_physaddr + RTE_PKTMBUF_HEADROOM;
+		dma_addr0 = vsetq_lane_u64(paddr, zero, 0);
+		/* flush desc with pa dma_addr */
+		vst1q_u64((uint64_t *)&rxdp++->read, dma_addr0);
+
+		vst1_u8((uint8_t *)&mb1->rearm_data, p);
+		paddr = mb1->buf_physaddr + RTE_PKTMBUF_HEADROOM;
+		dma_addr1 = vsetq_lane_u64(paddr, zero, 0);
+		vst1q_u64((uint64_t *)&rxdp++->read, dma_addr1);
+	}
+
+	rxq->rxrearm_start += RTE_IXGBE_RXQ_REARM_THRESH;
+	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
+		rxq->rxrearm_start = 0;
+
+	rxq->rxrearm_nb -= RTE_IXGBE_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 */
+	IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, rx_id);
+}
+
+/* Handling the offload flags (olflags) field takes computation
+ * time when receiving packets. Therefore we provide a flag to disable
+ * the processing of the olflags field when they are not needed. This
+ * gives improved performance, at the cost of losing the offload info
+ * in the received packet
+ */
+#ifdef RTE_IXGBE_RX_OLFLAGS_ENABLE
+
+#define VTAG_SHIFT     (3)
+
+static inline void
+desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
+		  uint8x16_t staterr, struct rte_mbuf **rx_pkts)
+{
+	uint8x16_t ptype;
+	uint8x16_t vtag;
+
+	union {
+		uint8_t e[4];
+		uint32_t word;
+	} vol;
+
+	const uint8x16_t pkttype_msk = {
+			PKT_RX_VLAN_PKT, PKT_RX_VLAN_PKT,
+			PKT_RX_VLAN_PKT, PKT_RX_VLAN_PKT,
+			0x00, 0x00, 0x00, 0x00,
+			0x00, 0x00, 0x00, 0x00,
+			0x00, 0x00, 0x00, 0x00};
+
+	const uint8x16_t rsstype_msk = {
+			0x0F, 0x0F, 0x0F, 0x0F,
+			0x00, 0x00, 0x00, 0x00,
+			0x00, 0x00, 0x00, 0x00,
+			0x00, 0x00, 0x00, 0x00};
+
+	const uint8x16_t rss_flags = {
+			0, PKT_RX_RSS_HASH, PKT_RX_RSS_HASH, PKT_RX_RSS_HASH,
+			0, PKT_RX_RSS_HASH, 0, PKT_RX_RSS_HASH,
+			PKT_RX_RSS_HASH, 0, 0, 0,
+			0, 0, 0, PKT_RX_FDIR};
+
+	ptype = vzipq_u8(sterr_tmp1.val[0], sterr_tmp2.val[0]).val[0];
+	ptype = vandq_u8(ptype, rsstype_msk);
+	ptype = vqtbl1q_u8(rss_flags, ptype);
+
+	vtag = vshrq_n_u8(staterr, VTAG_SHIFT);
+	vtag = vandq_u8(vtag, pkttype_msk);
+	vtag = vorrq_u8(ptype, vtag);
+
+	vol.word = vgetq_lane_u32(vreinterpretq_u32_u8(vtag), 0);
+
+	rx_pkts[0]->ol_flags = vol.e[0];
+	rx_pkts[1]->ol_flags = vol.e[1];
+	rx_pkts[2]->ol_flags = vol.e[2];
+	rx_pkts[3]->ol_flags = vol.e[3];
+}
+#else
+#define desc_to_olflags_v(sterr_tmp1, sterr_tmp2, staterr, rx_pkts)
+#endif
+
+/*
+ * vPMD raw receive routine, only accept(nb_pkts >= RTE_IXGBE_DESCS_PER_LOOP)
+ *
+ * Notice:
+ * - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet
+ * - nb_pkts > RTE_IXGBE_MAX_RX_BURST, only scan RTE_IXGBE_MAX_RX_BURST
+ *   numbers of DD bit
+ * - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two
+ * - don't support ol_flags for rss and csum err
+ */
+
+#define IXGBE_VPMD_DESC_DD_MASK		0x01010101
+#define IXGBE_VPMD_DESC_EOP_MASK	0x02020202
+
+static inline uint16_t
+_recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
+		   uint16_t nb_pkts, uint8_t *split_packet)
+{
+	volatile union ixgbe_adv_rx_desc *rxdp;
+	struct ixgbe_rx_entry *sw_ring;
+	uint16_t nb_pkts_recd;
+	int pos;
+	uint64_t var;
+	uint8x16_t shuf_msk = {
+		0xFF, 0xFF,
+		0xFF, 0xFF,  /* skip 32 bits pkt_type */
+		12, 13,      /* octet 12~13, low 16 bits pkt_len */
+		0xFF, 0xFF,  /* skip high 16 bits pkt_len, zero out */
+		12, 13,      /* octet 12~13, 16 bits data_len */
+		14, 15,      /* octet 14~15, low 16 bits vlan_macip */
+		4, 5, 6, 7  /* octet 4~7, 32bits rss */
+		};
+	uint16x8_t crc_adjust = {0, 0, rxq->crc_len, 0,
+				 rxq->crc_len, 0, 0, 0};
+
+	/* nb_pkts shall be less equal than RTE_IXGBE_MAX_RX_BURST */
+	nb_pkts = RTE_MIN(nb_pkts, RTE_IXGBE_MAX_RX_BURST);
+
+	/* nb_pkts has to be floor-aligned to RTE_IXGBE_DESCS_PER_LOOP */
+	nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_IXGBE_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_prefetch_non_temporal(rxdp);
+
+	/* See if we need to rearm the RX queue - gives the prefetch a bit
+	 * of time to act
+	 */
+	if (rxq->rxrearm_nb > RTE_IXGBE_RXQ_REARM_THRESH)
+		ixgbe_rxq_rearm(rxq);
+
+	/* Before we start moving massive data around, check to see if
+	 * there is actually a packet available
+	 */
+	if (!(rxdp->wb.upper.status_error &
+				rte_cpu_to_le_32(IXGBE_RXDADV_STAT_DD)))
+		return 0;
+
+	/* 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
+	 * 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 += RTE_IXGBE_DESCS_PER_LOOP,
+			rxdp += RTE_IXGBE_DESCS_PER_LOOP) {
+		uint64x2_t descs[RTE_IXGBE_DESCS_PER_LOOP];
+		uint8x16_t pkt_mb1, pkt_mb2, pkt_mb3, pkt_mb4;
+		uint8x16x2_t sterr_tmp1, sterr_tmp2;
+		uint64x2_t mbp1, mbp2;
+		uint8x16_t staterr;
+		uint16x8_t tmp;
+		uint32_t stat;
+
+		/* B.1 load 1 mbuf point */
+		mbp1 = vld1q_u64((uint64_t *)&sw_ring[pos]);
+
+		/* Read desc statuses backwards to avoid race condition */
+		/* A.1 load 4 pkts desc */
+		descs[3] =  vld1q_u64((uint64_t *)(rxdp + 3));
+		rte_rmb();