[PATCH v6 3/4] net/ixgbe: implement mbufs recycle mode

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

Define specific function implementation for ixgbe driver.
Currently, recycle buffer mode can support 128bit
vector path. And can be enabled both in fast free and
no fast free mode.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
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 +
 .../ixgbe/ixgbe_recycle_mbufs_vec_common.c    | 136 ++++++++++++++++++
 drivers/net/ixgbe/ixgbe_rxtx.c                |  29 ++++
 drivers/net/ixgbe/ixgbe_rxtx.h                |   4 +
 drivers/net/ixgbe/meson.build                 |   2 +
 6 files changed, 175 insertions(+)
 create mode 100644 drivers/net/ixgbe/ixgbe_recycle_mbufs_vec_common.c

diff --git a/drivers/net/ixgbe/ixgbe_ethdev.c b/drivers/net/ixgbe/ixgbe_ethdev.c
index 88118bc305..db47100a37 100644
--- a/drivers/net/ixgbe/ixgbe_ethdev.c
+++ b/drivers/net/ixgbe/ixgbe_ethdev.c
@@ -543,6 +543,7 @@ 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,
+	.recycle_rxq_info_get = ixgbe_recycle_rxq_info_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..9169930c7f 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_recycle_rxq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
+		struct rte_eth_recycle_rxq_info *recycle_rxq_info);
+
 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_recycle_mbufs_vec_common.c b/drivers/net/ixgbe/ixgbe_recycle_mbufs_vec_common.c
new file mode 100644
index 0000000000..f234e95e92
--- /dev/null
+++ b/drivers/net/ixgbe/ixgbe_recycle_mbufs_vec_common.c
@@ -0,0 +1,136 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2023 Arm Limited.
+ */
+
+#include <stdint.h>
+#include <ethdev_driver.h>
+
+#include "ixgbe_ethdev.h"
+#include "ixgbe_rxtx.h"
+
+#pragma GCC diagnostic ignored "-Wcast-qual"
+
+void
+ixgbe_recycle_rx_descriptors_refill_vec(void *rx_queue, uint16_t nb_mbufs)
+{
+	struct ixgbe_rx_queue *rxq = rx_queue;
+	struct ixgbe_rx_entry *rxep;
+	volatile union ixgbe_adv_rx_desc *rxdp;
+	uint16_t rx_id;
+	uint64_t paddr;
+	uint64_t dma_addr;
+	uint16_t i;
+
+	rxdp = rxq->rx_ring + rxq->rxrearm_start;
+	rxep = &rxq->sw_ring[rxq->rxrearm_start];
+
+	for (i = 0; i < nb_mbufs; i++) {
+		/* Initialize rxdp descs. */
+		paddr = (rxep[i].mbuf)->buf_iova + RTE_PKTMBUF_HEADROOM;
+		dma_addr = rte_cpu_to_le_64(paddr);
+		/* Flush descriptors with pa dma_addr */
+		rxdp[i].read.hdr_addr = 0;
+		rxdp[i].read.pkt_addr = dma_addr;
+	}
+
+	/* Update the descriptor initializer index */
+	rxq->rxrearm_start += nb_mbufs;
+	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
+		rxq->rxrearm_start = 0;
+
+	rxq->rxrearm_nb -= nb_mbufs;
+
+	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);
+}
+
+uint16_t
+ixgbe_recycle_tx_mbufs_reuse_vec(void *tx_queue,
+		struct rte_eth_recycle_rxq_info *recycle_rxq_info)
+{
+	struct ixgbe_tx_queue *txq = tx_queue;
+	struct ixgbe_tx_entry *txep;
+	struct rte_mbuf **rxep;
+	struct rte_mbuf *m[RTE_IXGBE_TX_MAX_FREE_BUF_SZ];
+	int i, j, n;
+	uint32_t status;
+	uint16_t avail = 0;
+	uint16_t mbuf_ring_size = recycle_rxq_info->mbuf_ring_size;
+	uint16_t mask = recycle_rxq_info->mbuf_ring_size - 1;
+	uint16_t refill_requirement = recycle_rxq_info->refill_requirement;
+	uint16_t refill_head = *recycle_rxq_info->refill_head;
+	uint16_t receive_tail = *recycle_rxq_info->receive_tail;
+
+	/* Get available recycling Rx buffers. */
+	avail = (mbuf_ring_size - (refill_head - receive_tail)) & mask;
+
+	/* Check Tx free thresh and Rx available space. */
+	if (txq->nb_tx_free > txq->tx_free_thresh || avail <= txq->tx_rs_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;
+
+	/* Mbufs recycle can only support no ring buffer wrapping around.
+	 * Two case for this:
+	 *
+	 * case 1: The refill head of Rx buffer ring needs to be aligned with
+	 * buffer ring size. In this case, the number of Tx freeing buffers
+	 * should be equal to refill_requirement.
+	 *
+	 * case 2: The refill head of Rx ring buffer does not need to be aligned
+	 * with buffer ring size. In this case, the update of refill head can not
+	 * exceed the Rx buffer ring size.
+	 */
+	if (refill_requirement != n ||
+		(!refill_requirement && (refill_head + n > mbuf_ring_size)))
+		return 0;
+
+	/* First buffer to free from S/W ring is at index
+	 * tx_next_dd - (tx_rs_thresh-1).
+	 */
+	txep = &txq->sw_ring[txq->tx_next_dd - (n - 1)];
+	rxep = recycle_rxq_info->mbuf_ring;
+	rxep += refill_head;
+
+	if (txq->offloads & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE) {
+		/* Directly put mbufs from Tx to Rx. */
+		for (i = 0; i < n; i++, rxep++, txep++)
+			*rxep = txep[0].mbuf;
+	} else {
+		for (i = 0, j = 0; i < n; i++) {
+			/* Avoid txq contains buffers from expected mempool. */
+			if (unlikely(recycle_rxq_info->mp
+						!= txep[i].mbuf->pool))
+				return 0;
+
+			m[j] = rte_pktmbuf_prefree_seg(txep[i].mbuf);
+
+			/* In case 1, each of Tx buffers should be the
+			 * last reference.
+			 */
+			if (unlikely(m[j] == NULL && refill_requirement))
+				return 0;
+			/* In case 2, the number of valid Tx free
+			 * buffers should be recorded.
+			 */
+			j++;
+		}
+		rte_memcpy(rxep, m, sizeof(void *) * j);
+	}
+
+	/* 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;
+}
diff --git a/drivers/net/ixgbe/ixgbe_rxtx.c b/drivers/net/ixgbe/ixgbe_rxtx.c
index c9d6ca9efe..ef2ea84bfa 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx.c
@@ -2558,6 +2558,7 @@ ixgbe_set_tx_function(struct rte_eth_dev *dev, struct ixgbe_tx_queue *txq)
 				(rte_eal_process_type() != RTE_PROC_PRIMARY ||
 					ixgbe_txq_vec_setup(txq) == 0)) {
 			PMD_INIT_LOG(DEBUG, "Vector tx enabled.");
+			dev->recycle_tx_mbufs_reuse = ixgbe_recycle_tx_mbufs_reuse_vec;
 			dev->tx_pkt_burst = ixgbe_xmit_pkts_vec;
 		} else
 		dev->tx_pkt_burst = ixgbe_xmit_pkts_simple;
@@ -4823,6 +4824,8 @@ ixgbe_set_rx_function(struct rte_eth_dev *dev)
 					    "callback (port=%d).",
 				     dev->data->port_id);
 
+			dev->recycle_rx_descriptors_refill =
+				ixgbe_recycle_rx_descriptors_refill_vec;
 			dev->rx_pkt_burst = ixgbe_recv_scattered_pkts_vec;
 		} else if (adapter->rx_bulk_alloc_allowed) {
 			PMD_INIT_LOG(DEBUG, "Using a Scattered with bulk "
@@ -4852,6 +4855,7 @@ ixgbe_set_rx_function(struct rte_eth_dev *dev)
 			     RTE_IXGBE_DESCS_PER_LOOP,
 			     dev->data->port_id);
 
+		dev->recycle_rx_descriptors_refill = ixgbe_recycle_rx_descriptors_refill_vec;
 		dev->rx_pkt_burst = ixgbe_recv_pkts_vec;
 	} else if (adapter->rx_bulk_alloc_allowed) {
 		PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions are "
@@ -5623,6 +5627,31 @@ ixgbe_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 	qinfo->conf.tx_deferred_start = txq->tx_deferred_start;
 }
 
+void
+ixgbe_recycle_rxq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
+	struct rte_eth_recycle_rxq_info *recycle_rxq_info)
+{
+	struct ixgbe_rx_queue *rxq;
+	struct ixgbe_adapter *adapter = dev->data->dev_private;
+
+	rxq = dev->data->rx_queues[queue_id];
+
+	recycle_rxq_info->mbuf_ring = (void *)rxq->sw_ring;
+	recycle_rxq_info->mp = rxq->mb_pool;
+	recycle_rxq_info->mbuf_ring_size = rxq->nb_rx_desc;
+	recycle_rxq_info->receive_tail = &rxq->rx_tail;
+
+	if (adapter->rx_vec_allowed) {
+#if defined(RTE_ARCH_X86) || defined(RTE_ARCH_ARM)
+		recycle_rxq_info->refill_requirement = RTE_IXGBE_RXQ_REARM_THRESH;
+		recycle_rxq_info->refill_head = &rxq->rxrearm_start;
+#endif
+	} else {
+		recycle_rxq_info->refill_requirement = rxq->rx_free_thresh;
+		recycle_rxq_info->refill_head = &rxq->rx_free_trigger;
+	}
+}
+
 /*
  * [VF] Initializes Receive Unit.
  */
diff --git a/drivers/net/ixgbe/ixgbe_rxtx.h b/drivers/net/ixgbe/ixgbe_rxtx.h
index 668a5b9814..ee89c89929 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];
 
+uint16_t ixgbe_recycle_tx_mbufs_reuse_vec(void *tx_queue,
+		struct rte_eth_recycle_rxq_info *recycle_rxq_info);
+void ixgbe_recycle_rx_descriptors_refill_vec(void *rx_queue, uint16_t nb_mbufs);
+
 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/meson.build b/drivers/net/ixgbe/meson.build
index a18908ef7c..0ae12dd5ff 100644
--- a/drivers/net/ixgbe/meson.build
+++ b/drivers/net/ixgbe/meson.build
@@ -26,11 +26,13 @@ deps += ['hash', 'security']
 
 if arch_subdir == 'x86'
     sources += files('ixgbe_rxtx_vec_sse.c')
+    sources += files('ixgbe_recycle_mbufs_vec_common.c')
     if is_windows and cc.get_id() != 'clang'
         cflags += ['-fno-asynchronous-unwind-tables']
     endif
 elif arch_subdir == 'arm'
     sources += files('ixgbe_rxtx_vec_neon.c')
+    sources += files('ixgbe_recycle_mbufs_vec_common.c')
 endif
 
 includes += include_directories('base')
-- 
2.25.1