[PATCH v3 3/3] net/ixgbe: enable direct rearm with separate API

[Feifei Wang <feifei.wang2@arm.com>]

Add internal API to separate direct rearm operations between
Rx and Tx.

Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
---
 drivers/net/ixgbe/ixgbe_ethdev.c          |  1 +
 drivers/net/ixgbe/ixgbe_ethdev.h          |  3 ++
 drivers/net/ixgbe/ixgbe_rxtx.c            | 19 +++++++++
 drivers/net/ixgbe/ixgbe_rxtx.h            |  4 ++
 drivers/net/ixgbe/ixgbe_rxtx_vec_common.h | 48 +++++++++++++++++++++
 drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c   | 52 +++++++++++++++++++++++
 6 files changed, 127 insertions(+)

diff --git a/drivers/net/ixgbe/ixgbe_ethdev.c b/drivers/net/ixgbe/ixgbe_ethdev.c
index ae9f65b334..e5383d7dbc 100644
--- a/drivers/net/ixgbe/ixgbe_ethdev.c
+++ b/drivers/net/ixgbe/ixgbe_ethdev.c
@@ -542,6 +542,7 @@ static const struct eth_dev_ops ixgbe_eth_dev_ops = {
 	.set_mc_addr_list     = ixgbe_dev_set_mc_addr_list,
 	.rxq_info_get         = ixgbe_rxq_info_get,
 	.txq_info_get         = ixgbe_txq_info_get,
+	.rxq_rearm_data_get   = ixgbe_rxq_rearm_data_get,
 	.timesync_enable      = ixgbe_timesync_enable,
 	.timesync_disable     = ixgbe_timesync_disable,
 	.timesync_read_rx_timestamp = ixgbe_timesync_read_rx_timestamp,
diff --git a/drivers/net/ixgbe/ixgbe_ethdev.h b/drivers/net/ixgbe/ixgbe_ethdev.h
index 48290af512..2a8ae5af7a 100644
--- a/drivers/net/ixgbe/ixgbe_ethdev.h
+++ b/drivers/net/ixgbe/ixgbe_ethdev.h
@@ -625,6 +625,9 @@ void ixgbe_rxq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 void ixgbe_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 	struct rte_eth_txq_info *qinfo);
 
+void ixgbe_rxq_rearm_data_get(struct rte_eth_dev *dev, uint16_t queue_id,
+	struct rte_eth_rxq_rearm_data *rxq_rearm_data);
+
 int ixgbevf_dev_rx_init(struct rte_eth_dev *dev);
 
 void ixgbevf_dev_tx_init(struct rte_eth_dev *dev);
diff --git a/drivers/net/ixgbe/ixgbe_rxtx.c b/drivers/net/ixgbe/ixgbe_rxtx.c
index c9d6ca9efe..2d7fe710e4 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx.c
@@ -2559,6 +2559,9 @@ ixgbe_set_tx_function(struct rte_eth_dev *dev, struct ixgbe_tx_queue *txq)
 					ixgbe_txq_vec_setup(txq) == 0)) {
 			PMD_INIT_LOG(DEBUG, "Vector tx enabled.");
 			dev->tx_pkt_burst = ixgbe_xmit_pkts_vec;
+#ifdef RTE_ARCH_ARM64
+			dev->tx_fill_sw_ring = ixgbe_tx_fill_sw_ring;
+#endif
 		} else
 		dev->tx_pkt_burst = ixgbe_xmit_pkts_simple;
 	} else {
@@ -4853,6 +4856,9 @@ ixgbe_set_rx_function(struct rte_eth_dev *dev)
 			     dev->data->port_id);
 
 		dev->rx_pkt_burst = ixgbe_recv_pkts_vec;
+#ifdef RTE_ARCH_ARM64
+		dev->rx_flush_descriptor = ixgbe_rx_flush_descriptor_vec;
+#endif
 	} else if (adapter->rx_bulk_alloc_allowed) {
 		PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions are "
 				    "satisfied. Rx Burst Bulk Alloc function "
@@ -5623,6 +5629,19 @@ ixgbe_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 	qinfo->conf.tx_deferred_start = txq->tx_deferred_start;
 }
 
+void
+ixgbe_rxq_rearm_data_get(struct rte_eth_dev *dev, uint16_t queue_id,
+	struct rte_eth_rxq_rearm_data *rxq_rearm_data)
+{
+	struct ixgbe_rx_queue *rxq;
+
+	rxq = dev->data->rx_queues[queue_id];
+
+	rxq_rearm_data->rx_sw_ring = rxq->sw_ring;
+	rxq_rearm_data->rearm_start = &rxq->rxrearm_start;
+	rxq_rearm_data->rearm_nb = &rxq->rxrearm_nb;
+}
+
 /*
  * [VF] Initializes Receive Unit.
  */
diff --git a/drivers/net/ixgbe/ixgbe_rxtx.h b/drivers/net/ixgbe/ixgbe_rxtx.h
index 668a5b9814..7c90426f49 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx.h
+++ b/drivers/net/ixgbe/ixgbe_rxtx.h
@@ -295,6 +295,10 @@ int ixgbe_dev_tx_done_cleanup(void *tx_queue, uint32_t free_cnt);
 extern const uint32_t ptype_table[IXGBE_PACKET_TYPE_MAX];
 extern const uint32_t ptype_table_tn[IXGBE_PACKET_TYPE_TN_MAX];
 
+int ixgbe_tx_fill_sw_ring(void *tx_queue,
+		struct rte_eth_rxq_rearm_data *rxq_rearm_data);
+int ixgbe_rx_flush_descriptor_vec(void *rx_queue, uint16_t nb_rearm);
+
 uint16_t ixgbe_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
 				    uint16_t nb_pkts);
 int ixgbe_txq_vec_setup(struct ixgbe_tx_queue *txq);
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_common.h b/drivers/net/ixgbe/ixgbe_rxtx_vec_common.h
index a4d9ec9b08..36799dd7f5 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_common.h
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_common.h
@@ -129,6 +129,54 @@ ixgbe_tx_free_bufs(struct ixgbe_tx_queue *txq)
 	return txq->tx_rs_thresh;
 }
 
+int
+ixgbe_tx_fill_sw_ring(void *tx_queue,
+		struct rte_eth_rxq_rearm_data *rxq_rearm_data)
+{
+	struct ixgbe_tx_queue *txq = tx_queue;
+	struct ixgbe_tx_entry_v *txep;
+	void **rxep;
+	uint32_t status;
+	struct rte_mbuf *m;
+	int i, n;
+	int nb_rearm = 0;
+
+	if (*rxq_rearm_data->rearm_nb < txq->tx_rs_thresh ||
+			txq->nb_tx_free > txq->tx_free_thresh)
+		return 0;
+
+	/* check DD bits on threshold descriptor */
+	status = txq->tx_ring[txq->tx_next_dd].wb.status;
+	if (!(status & IXGBE_ADVTXD_STAT_DD))
+		return 0;
+
+	n = txq->tx_rs_thresh;
+
+	/* first buffer to free from S/W ring is at index
+	 * tx_next_dd - (tx_rs_thresh-1)
+	 */
+	txep = &txq->sw_ring_v[txq->tx_next_dd - (n - 1)];
+	rxep = rxq_rearm_data->rx_sw_ring;
+	rxep += *rxq_rearm_data->rearm_start;
+
+	for (i = 0; i < n; i++, rxep++) {
+		m = rte_pktmbuf_prefree_seg(txep[i].mbuf);
+		if (m != NULL) {
+			*rxep = m;
+			nb_rearm++;
+		}
+	}
+	n = nb_rearm;
+
+	/* update counters for Tx */
+	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free + txq->tx_rs_thresh);
+	txq->tx_next_dd = (uint16_t)(txq->tx_next_dd + txq->tx_rs_thresh);
+	if (txq->tx_next_dd >= txq->nb_tx_desc)
+		txq->tx_next_dd = (uint16_t)(txq->tx_rs_thresh - 1);
+
+	return n;
+}
+
 static __rte_always_inline void
 tx_backlog_entry(struct ixgbe_tx_entry_v *txep,
 		 struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
index 90b254ea26..af6a66c2d5 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
@@ -633,6 +633,58 @@ ixgbe_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
 	return nb_pkts;
 }
 
+int
+ixgbe_rx_flush_descriptor_vec(void *rx_queue, uint16_t nb_rearm)
+{
+	struct ixgbe_rx_queue *rxq = rx_queue;
+	struct ixgbe_rx_entry *rxep;
+	volatile union ixgbe_adv_rx_desc *rxdp;
+	struct rte_mbuf *mb;
+	uint16_t rx_id;
+	uint64x2_t dma_addr;
+	uint64x2_t zero = vdupq_n_u64(0);
+	uint64_t paddr;
+	uint8x8_t p;
+	uint16_t i;
+
+	rxdp = rxq->rx_ring + rxq->rxrearm_start;
+	rxep = &rxq->sw_ring[rxq->rxrearm_start];
+
+	p = vld1_u8((uint8_t *)&rxq->mbuf_initializer);
+
+	for (i = 0; i < nb_rearm; i++) {
+		mb = rxep[i].mbuf;
+		/*
+		 * Flush mbuf with pkt template.
+		 * Data to be rearmed is 6 bytes long.
+		 */
+		vst1_u8((uint8_t *)&mb->rearm_data, p);
+		/* Initialize rxdp descs */
+		paddr = mb->buf_iova + RTE_PKTMBUF_HEADROOM;
+		dma_addr = vsetq_lane_u64(paddr, zero, 0);
+		/* flush desc with pa dma_addr */
+		vst1q_u64((uint64_t *)&rxdp++->read, dma_addr);
+	}
+
+	/* Update the descriptor initializer index */
+	rxq->rxrearm_start += nb_rearm;
+	rx_id = rxq->rxrearm_start - 1;
+
+	if (unlikely(rxq->rxrearm_start >= rxq->nb_rx_desc)) {
+		rxq->rxrearm_start = rxq->rxrearm_start - rxq->nb_rx_desc;
+		if (!rxq->rxrearm_start)
+			rx_id = rxq->nb_rx_desc - 1;
+		else
+			rx_id = rxq->rxrearm_start - 1;
+	}
+	rxq->rxrearm_nb -= nb_rearm;
+
+	/* Update the tail pointer on the NIC */
+	IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, rx_id);
+
+	return 0;
+}
+
 static void __rte_cold
 ixgbe_tx_queue_release_mbufs_vec(struct ixgbe_tx_queue *txq)
 {
-- 
2.25.1