[PATCH v7 7/8] net/ice: support Rx scatter AVX2 vector

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

Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
---
 drivers/net/ice/ice_rxtx.c          | 10 ++++--
 drivers/net/ice/ice_rxtx.h          |  3 ++
 drivers/net/ice/ice_rxtx_vec_avx2.c | 64 +++++++++++++++++++++++++++++++++++++
 3 files changed, 74 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ice/ice_rxtx.c b/drivers/net/ice/ice_rxtx.c
index 28d5974..860155f 100644
--- a/drivers/net/ice/ice_rxtx.c
+++ b/drivers/net/ice/ice_rxtx.c
@@ -1506,7 +1506,8 @@
 #ifdef RTE_ARCH_X86
 	if (dev->rx_pkt_burst == ice_recv_pkts_vec ||
 	    dev->rx_pkt_burst == ice_recv_scattered_pkts_vec ||
-	    dev->rx_pkt_burst == ice_recv_pkts_vec_avx2)
+	    dev->rx_pkt_burst == ice_recv_pkts_vec_avx2 ||
+	    dev->rx_pkt_burst == ice_recv_scattered_pkts_vec_avx2)
 		return ptypes;
 #endif
 
@@ -2258,9 +2259,12 @@ void __attribute__((cold))
 
 		if (dev->data->scattered_rx) {
 			PMD_DRV_LOG(DEBUG,
-				    "Using Vector Scattered Rx (port %d).",
+				    "Using %sVector Scattered Rx (port %d).",
+				    use_avx2 ? "avx2 " : "",
 				    dev->data->port_id);
-			dev->rx_pkt_burst = ice_recv_scattered_pkts_vec;
+			dev->rx_pkt_burst = use_avx2 ?
+					    ice_recv_scattered_pkts_vec_avx2 :
+					    ice_recv_scattered_pkts_vec;
 		} else {
 			PMD_DRV_LOG(DEBUG, "Using %sVector Rx (port %d).",
 				    use_avx2 ? "avx2 " : "",
diff --git a/drivers/net/ice/ice_rxtx.h b/drivers/net/ice/ice_rxtx.h
index d1c9b92..dfc3224 100644
--- a/drivers/net/ice/ice_rxtx.h
+++ b/drivers/net/ice/ice_rxtx.h
@@ -181,4 +181,7 @@ uint16_t ice_xmit_pkts_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
 			   uint16_t nb_pkts);
 uint16_t ice_recv_pkts_vec_avx2(void *rx_queue, struct rte_mbuf **rx_pkts,
 				uint16_t nb_pkts);
+uint16_t ice_recv_scattered_pkts_vec_avx2(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_avx2.c b/drivers/net/ice/ice_rxtx_vec_avx2.c
index 42f761d..2459ff3 100644
--- a/drivers/net/ice/ice_rxtx_vec_avx2.c
+++ b/drivers/net/ice/ice_rxtx_vec_avx2.c
@@ -620,3 +620,67 @@
 {
 	return _ice_recv_raw_pkts_vec_avx2(rx_queue, rx_pkts, nb_pkts, NULL);
 }
+
+/**
+ * vPMD receive routine that reassembles single burst of 32 scattered packets
+ * Notice:
+ * - nb_pkts < ICE_DESCS_PER_LOOP, just return no packet
+ */
+static uint16_t
+ice_recv_scattered_burst_vec_avx2(void *rx_queue, struct rte_mbuf **rx_pkts,
+				  uint16_t nb_pkts)
+{
+	struct ice_rx_queue *rxq = rx_queue;
+	uint8_t split_flags[ICE_VPMD_RX_BURST] = {0};
+
+	/* get some new buffers */
+	uint16_t nb_bufs = _ice_recv_raw_pkts_vec_avx2(rxq, rx_pkts, nb_pkts,
+						       split_flags);
+	if (nb_bufs == 0)
+		return 0;
+
+	/* happy day case, full burst + no packets to be joined */
+	const uint64_t *split_fl64 = (uint64_t *)split_flags;
+
+	if (!rxq->pkt_first_seg &&
+	    split_fl64[0] == 0 && split_fl64[1] == 0 &&
+	    split_fl64[2] == 0 && split_fl64[3] == 0)
+		return nb_bufs;
+
+	/* reassemble any packets that need reassembly*/
+	unsigned int i = 0;
+
+	if (!rxq->pkt_first_seg) {
+		/* find the first split flag, and only reassemble then*/
+		while (i < nb_bufs && !split_flags[i])
+			i++;
+		if (i == nb_bufs)
+			return nb_bufs;
+	}
+	return i + ice_rx_reassemble_packets(rxq, &rx_pkts[i], nb_bufs - i,
+					     &split_flags[i]);
+}
+
+/**
+ * vPMD receive routine that reassembles scattered packets.
+ * Main receive routine that can handle arbitrary burst sizes
+ * Notice:
+ * - nb_pkts < ICE_DESCS_PER_LOOP, just return no packet
+ */
+uint16_t
+ice_recv_scattered_pkts_vec_avx2(void *rx_queue, struct rte_mbuf **rx_pkts,
+				 uint16_t nb_pkts)
+{
+	uint16_t retval = 0;
+
+	while (nb_pkts > ICE_VPMD_RX_BURST) {
+		uint16_t burst = ice_recv_scattered_burst_vec_avx2(rx_queue,
+				rx_pkts + retval, ICE_VPMD_RX_BURST);
+		retval += burst;
+		nb_pkts -= burst;
+		if (burst < ICE_VPMD_RX_BURST)
+			return retval;
+	}
+	return retval + ice_recv_scattered_burst_vec_avx2(rx_queue,
+				rx_pkts + retval, nb_pkts);
+}
-- 
1.9.3