DPDK patches and discussions
 help / color / mirror / Atom feed
From: Robin Zhang <robinx.zhang@intel.com>
To: dev@dpdk.org
Cc: beilei.xing@intel.com, jingjing.wu@intel.com,
	qiming.yang@intel.com, stevex.yang@intel.com,
	Robin Zhang <robinx.zhang@intel.com>
Subject: [dpdk-dev] [PATCH 6/8] net/iavf: cleanup Tx buffers
Date: Sun, 27 Sep 2020 07:26:24 +0000
Message-ID: <20200927072626.28374-7-robinx.zhang@intel.com> (raw)
In-Reply-To: <20200927072626.28374-1-robinx.zhang@intel.com>

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

Signed-off-by: Robin Zhang <robinx.zhang@intel.com>
---
 drivers/net/iavf/iavf_ethdev.c |  1 +
 drivers/net/iavf/iavf_rxtx.c   | 68 +++++++++++++++++++++++++++++++++-
 drivers/net/iavf/iavf_rxtx.h   |  1 +
 3 files changed, 69 insertions(+), 1 deletion(-)

diff --git a/drivers/net/iavf/iavf_ethdev.c b/drivers/net/iavf/iavf_ethdev.c
index b32302c43..5b3c68f2e 100644
--- a/drivers/net/iavf/iavf_ethdev.c
+++ b/drivers/net/iavf/iavf_ethdev.c
@@ -121,6 +121,7 @@ static const struct eth_dev_ops iavf_eth_dev_ops = {
 	.rx_queue_intr_enable       = iavf_dev_rx_queue_intr_enable,
 	.rx_queue_intr_disable      = iavf_dev_rx_queue_intr_disable,
 	.filter_ctrl                = iavf_dev_filter_ctrl,
+	.tx_done_cleanup	    = iavf_dev_tx_done_cleanup,
 };
 
 static int
diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c
index 05a7dd898..1b0efe043 100644
--- a/drivers/net/iavf/iavf_rxtx.c
+++ b/drivers/net/iavf/iavf_rxtx.c
@@ -1905,7 +1905,6 @@ iavf_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 		tx_offload.l3_len = tx_pkt->l3_len;
 		tx_offload.l4_len = tx_pkt->l4_len;
 		tx_offload.tso_segsz = tx_pkt->tso_segsz;
-
 		/* Calculate the number of context descriptors needed. */
 		nb_ctx = iavf_calc_context_desc(ol_flags);
 
@@ -2208,6 +2207,73 @@ iavf_set_tx_function(struct rte_eth_dev *dev)
 	dev->tx_pkt_prepare = iavf_prep_pkts;
 }
 
+static int
+iavf_tx_done_cleanup_full(struct iavf_tx_queue *txq,
+			uint32_t free_cnt)
+{
+	struct iavf_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_free == 0 && iavf_xmit_cleanup(txq))
+		return 0;
+
+	nb_tx_to_clean = txq->nb_free;
+	nb_tx_free_last = txq->nb_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->rs_thresh > txq->nb_tx_desc -
+			txq->nb_free || tx_id == tx_last)
+			break;
+
+		if (pkt_cnt < free_cnt) {
+			if (iavf_xmit_cleanup(txq))
+				break;
+
+			nb_tx_to_clean = txq->nb_free - nb_tx_free_last;
+			nb_tx_free_last = txq->nb_free;
+		}
+	}
+
+	return (int)pkt_cnt;
+}
+
+int
+iavf_dev_tx_done_cleanup(void *txq, uint32_t free_cnt)
+{
+	struct iavf_tx_queue *q = (struct iavf_tx_queue *)txq;
+
+	return iavf_tx_done_cleanup_full(q, free_cnt);
+}
+
 void
 iavf_dev_rxq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 		     struct rte_eth_rxq_info *qinfo)
diff --git a/drivers/net/iavf/iavf_rxtx.h b/drivers/net/iavf/iavf_rxtx.h
index 59625a979..3d02c6589 100644
--- a/drivers/net/iavf/iavf_rxtx.h
+++ b/drivers/net/iavf/iavf_rxtx.h
@@ -379,6 +379,7 @@ int iavf_dev_tx_queue_setup(struct rte_eth_dev *dev,
 			   const struct rte_eth_txconf *tx_conf);
 int iavf_dev_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id);
 int iavf_dev_tx_queue_stop(struct rte_eth_dev *dev, uint16_t tx_queue_id);
+int iavf_dev_tx_done_cleanup(void *txq, uint32_t free_cnt);
 void iavf_dev_tx_queue_release(void *txq);
 void iavf_stop_queues(struct rte_eth_dev *dev);
 uint16_t iavf_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
-- 
2.17.1


  parent reply	other threads:[~2020-09-27  7:49 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-27  7:26 [dpdk-dev] [PATCH 0/8] feature porting from i40evf to iavf Robin Zhang
2020-09-27  7:26 ` [dpdk-dev] [PATCH 1/8] net/iavf: use link status helper functions Robin Zhang
2020-09-27  7:26 ` [dpdk-dev] [PATCH 2/8] net/iavf: set min and max MTU for VF Robin Zhang
2020-09-27  7:26 ` [dpdk-dev] [PATCH 3/8] net/iavf: re-program promiscuous mode on VF interface Robin Zhang
2020-09-27  7:26 ` [dpdk-dev] [PATCH 4/8] net/iavf: optimize promiscuous ops Robin Zhang
2020-09-27  7:26 ` [dpdk-dev] [PATCH 5/8] net/iavf: add workaround promiscuous disable Robin Zhang
2020-09-27  7:26 ` Robin Zhang [this message]
2020-09-27  7:26 ` [dpdk-dev] [PATCH 7/8] net/iavf: add extended stats Robin Zhang
2020-09-27  7:26 ` [dpdk-dev] [PATCH 8/8] net/iavf: support check DD bit of a RX descriptor Robin Zhang
2020-10-08 15:05   ` Ferruh Yigit
     [not found]     ` <fe7a8f1f1a1f45908c4094ccfc6b547d@intel.com>
2020-10-12  8:32       ` Ferruh Yigit
2020-10-13  5:58         ` Zhang, Qi Z
2020-10-08 12:23 ` [dpdk-dev] [PATCH 0/8] feature porting from i40evf to iavf Zhang, Qi Z

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200927072626.28374-7-robinx.zhang@intel.com \
    --to=robinx.zhang@intel.com \
    --cc=beilei.xing@intel.com \
    --cc=dev@dpdk.org \
    --cc=jingjing.wu@intel.com \
    --cc=qiming.yang@intel.com \
    --cc=stevex.yang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

DPDK patches and discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ https://inbox.dpdk.org/dev \
		dev@dpdk.org
	public-inbox-index dev

Example config snippet for mirrors.
Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git