-----Original Message-----
From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Chen Jing D(Mark)
Sent: Tuesday, September 29, 2015 2:04 PM
To: dev@dpdk.org
Subject: [dpdk-dev] [PATCH 06/14] fm10k: add Vector RX function

From: "Chen Jing D(Mark)" <redacted>

Add func fm10k_recv_raw_pkts_vec to parse raw packets, in which
includes possible chained packets.
Add func fm10k_recv_pkts_vec to receive single mbuf packet.

Signed-off-by: Chen Jing D(Mark) <redacted>
---
 drivers/net/fm10k/fm10k.h          |    1 +
 drivers/net/fm10k/fm10k_rxtx_vec.c |  213 ++++++++++++++++++++++++++++++++++++
 2 files changed, 214 insertions(+), 0 deletions(-)

diff --git a/drivers/net/fm10k/fm10k.h b/drivers/net/fm10k/fm10k.h
index d924cae..285254f 100644
--- a/drivers/net/fm10k/fm10k.h
+++ b/drivers/net/fm10k/fm10k.h

@@ -327,4 +327,5 @@ uint16_t fm10k_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 	uint16_t nb_pkts);

 int fm10k_rxq_vec_setup(struct fm10k_rx_queue *rxq);
+uint16_t fm10k_recv_pkts_vec(void *, struct rte_mbuf **, uint16_t);
 #endif

diff --git a/drivers/net/fm10k/fm10k_rxtx_vec.c b/drivers/net/fm10k/fm10k_rxtx_vec.c
index 581a309..63b34b5 100644
--- a/drivers/net/fm10k/fm10k_rxtx_vec.c
+++ b/drivers/net/fm10k/fm10k_rxtx_vec.c

@@ -281,3 +281,216 @@ fm10k_rxq_rearm(struct fm10k_rx_queue *rxq)
 	/* Update the tail pointer on the NIC */
 	FM10K_PCI_REG_WRITE(rxq->tail_ptr, rx_id);
 }
+
+/*
+ * vPMD receive routine, now only accept (nb_pkts == RTE_IXGBE_VPMD_RX_BURST)
+ * in one loop
+ *
+ * Notice:
+ * - nb_pkts < RTE_IXGBE_VPMD_RX_BURST, just return no packet
+ * - nb_pkts > RTE_IXGBE_VPMD_RX_BURST, only scan RTE_IXGBE_VPMD_RX_BURST
+ *   numbers of DD bit
+ * - don't support ol_flags for rss and csum err
+ */
+static inline uint16_t
+fm10k_recv_raw_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+		uint16_t nb_pkts, uint8_t *split_packet)
+{
+	volatile union fm10k_rx_desc *rxdp;
+	struct rte_mbuf **mbufp;
+	uint16_t nb_pkts_recd;
+	int pos;
+	struct fm10k_rx_queue *rxq = rx_queue;
+	uint64_t var;
+	__m128i shuf_msk;
+	__m128i dd_check, eop_check;
+	uint16_t next_dd;
+
+	next_dd = rxq->next_dd;
+
+	if (unlikely(nb_pkts < RTE_FM10K_MAX_RX_BURST))
+		return 0;
+
+	/* Just the act of getting into the function from the application is
+	 * going to cost about 7 cycles
+	 */
+	rxdp = rxq->hw_ring + next_dd;
+
+	_mm_prefetch((const void *)rxdp, _MM_HINT_T0);
+
+	/* See if we need to rearm the RX queue - gives the prefetch a bit
+	 * of time to act
+	 */
+	if (rxq->rxrearm_nb > RTE_FM10K_RXQ_REARM_THRESH)
+		fm10k_rxq_rearm(rxq);
+
+	/* Before we start moving massive data around, check to see if
+	 * there is actually a packet available
+	 */
+	if (!(rxdp->d.staterr & FM10K_RXD_STATUS_DD))
+		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 */
+		15, 14,      /* octet 14~15, low 16 bits vlan_macip */
+		13, 12,      /* octet 12~13, 16 bits data_len */
+		0xFF, 0xFF,  /* skip high 16 bits pkt_len, zero out */
+		13, 12,      /* octet 12~13, low 16 bits pkt_len */
+		0xFF, 0xFF,  /* skip high 16 bits pkt_type */
+		0xFF, 0xFF   /* Skip pkt_type field in shuffle operation */
+		);
+
+	/* Cache is empty -> need to scan the buffer rings, but first move
+	 * the next 'n' mbufs into the cache
+	 */
+	mbufp = &rxq->sw_ring[next_dd];
+
+	/* 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 += RTE_FM10K_DESCS_PER_LOOP,
+			rxdp += RTE_FM10K_DESCS_PER_LOOP) {
+		__m128i descs0[RTE_FM10K_DESCS_PER_LOOP];
+		__m128i pkt_mb1, pkt_mb2, pkt_mb3, pkt_mb4;
+		__m128i zero, staterr, sterr_tmp1, sterr_tmp2;
+		__m128i mbp1, mbp2; /* two mbuf pointer in one XMM reg. */
+
+		if (split_packet) {
+			rte_prefetch0(&rx_pkts[pos]->cacheline1);
+			rte_prefetch0(&rx_pkts[pos + 1]->cacheline1);
+			rte_prefetch0(&rx_pkts[pos + 2]->cacheline1);
+			rte_prefetch0(&rx_pkts[pos + 3]->cacheline1);
+		}