net/i40e: cleanup Tx buffers

Add support to the i40e driver for the API rte_eth_tx_done_cleanup
to force free consumed buffers on Tx ring.

Signed-off-by: Chenxu Di <chenxux.di@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

drivers/net/i40e/i40e_ethdev.c

@@ -524,6 +524,7 @@ static const struct eth_dev_ops i40e_eth_dev_ops = {
 	.mac_addr_set                 = i40e_set_default_mac_addr,
 	.mtu_set                      = i40e_dev_mtu_set,
 	.tm_ops_get                   = i40e_tm_ops_get,
+	.tx_done_cleanup              = i40e_tx_done_cleanup,
 };
 
 /* store statistics names and its offset in stats structure */

drivers/net/i40e/i40e_ethdev_vf.c

@@ -215,6 +215,7 @@ static const struct eth_dev_ops i40evf_eth_dev_ops = {
 	.rss_hash_conf_get    = i40evf_dev_rss_hash_conf_get,
 	.mtu_set              = i40evf_dev_mtu_set,
 	.mac_addr_set         = i40evf_set_default_mac_addr,
+	.tx_done_cleanup      = i40e_tx_done_cleanup,
 };
 
 /*

drivers/net/i40e/i40e_rxtx.c

@@ -2498,6 +2498,113 @@ i40e_tx_queue_release_mbufs(struct i40e_tx_queue *txq)
 	}
 }
 
+static int
+i40e_tx_done_cleanup_full(struct i40e_tx_queue *txq,
+			uint32_t free_cnt)
+{
+	struct i40e_tx_entry *swr_ring = txq->sw_ring;
+	uint16_t i, tx_last, tx_id;
+	uint16_t nb_tx_free_last;
+	uint16_t nb_tx_to_clean;
+	uint32_t pkt_cnt;
+
+	/* Start free mbuf from the next of tx_tail */
+	tx_last = txq->tx_tail;
+	tx_id  = swr_ring[tx_last].next_id;
+
+	if (txq->nb_tx_free == 0 && i40e_xmit_cleanup(txq))
+		return 0;
+
+	nb_tx_to_clean = txq->nb_tx_free;
+	nb_tx_free_last = txq->nb_tx_free;
+	if (!free_cnt)
+		free_cnt = txq->nb_tx_desc;
+
+	/* Loop through swr_ring to count the amount of
+	 * freeable mubfs and packets.
+	 */
+	for (pkt_cnt = 0; pkt_cnt < free_cnt; ) {
+		for (i = 0; i < nb_tx_to_clean &&
+			pkt_cnt < free_cnt &&
+			tx_id != tx_last; i++) {
+			if (swr_ring[tx_id].mbuf != NULL) {
+				rte_pktmbuf_free_seg(swr_ring[tx_id].mbuf);
+				swr_ring[tx_id].mbuf = NULL;
+
+				/*
+				 * last segment in the packet,
+				 * increment packet count
+				 */
+				pkt_cnt += (swr_ring[tx_id].last_id == tx_id);
+			}
+
+			tx_id = swr_ring[tx_id].next_id;
+		}
+
+		if (txq->tx_rs_thresh > txq->nb_tx_desc -
+			txq->nb_tx_free || tx_id == tx_last)
+			break;
+
+		if (pkt_cnt < free_cnt) {
+			if (i40e_xmit_cleanup(txq))
+				break;
+
+			nb_tx_to_clean = txq->nb_tx_free - nb_tx_free_last;
+			nb_tx_free_last = txq->nb_tx_free;
+		}
+	}
+
+	return (int)pkt_cnt;
+}
+
+static int
+i40e_tx_done_cleanup_simple(struct i40e_tx_queue *txq,
+			uint32_t free_cnt)
+{
+	int i, n, cnt;
+
+	if (free_cnt == 0 || free_cnt > txq->nb_tx_desc)
+		free_cnt = txq->nb_tx_desc;
+
+	cnt = free_cnt - free_cnt % txq->tx_rs_thresh;
+
+	for (i = 0; i < cnt; i += n) {
+		if (txq->nb_tx_desc - txq->nb_tx_free < txq->tx_rs_thresh)
+			break;
+
+		n = i40e_tx_free_bufs(txq);
+
+		if (n == 0)
+			break;
+	}
+
+	return i;
+}
+
+static int
+i40e_tx_done_cleanup_vec(struct i40e_tx_queue *txq __rte_unused,
+			uint32_t free_cnt __rte_unused)
+{
+	return -ENOTSUP;
+}
+int
+i40e_tx_done_cleanup(void *txq, uint32_t free_cnt)
+{
+	struct i40e_tx_queue *q = (struct i40e_tx_queue *)txq;
+	struct rte_eth_dev *dev = &rte_eth_devices[q->port_id];
+	struct i40e_adapter *ad =
+		I40E_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
+
+	if (ad->tx_simple_allowed) {
+		if (ad->tx_vec_allowed)
+			return i40e_tx_done_cleanup_vec(q, free_cnt);
+		else
+			return i40e_tx_done_cleanup_simple(q, free_cnt);
+	} else {
+		return i40e_tx_done_cleanup_full(q, free_cnt);
+	}
+}
+
 void
 i40e_reset_tx_queue(struct i40e_tx_queue *txq)
 {

drivers/net/i40e/i40e_rxtx.h

@@ -212,6 +212,7 @@ void i40e_dev_free_queues(struct rte_eth_dev *dev);
 void i40e_reset_rx_queue(struct i40e_rx_queue *rxq);
 void i40e_reset_tx_queue(struct i40e_tx_queue *txq);
 void i40e_tx_queue_release_mbufs(struct i40e_tx_queue *txq);
+int i40e_tx_done_cleanup(void *txq, uint32_t free_cnt);
 int i40e_alloc_rx_queue_mbufs(struct i40e_rx_queue *rxq);
 void i40e_rx_queue_release_mbufs(struct i40e_rx_queue *rxq);