DPDK patches and discussions
 help / color / mirror / Atom feed
From: Pankaj Gupta <pagupta@vmware.com>
To: jbehrens@vmware.com, yongwang@vmware.com
Cc: dev@dpdk.org, pagupta@vmware.com
Subject: [PATCH v4 3/8] net/vmxnet3: add Rx queue usage count utility
Date: Thu,  5 May 2022 18:00:14 -0400	[thread overview]
Message-ID: <20220505220019.31166-4-pagupta@vmware.com> (raw)
In-Reply-To: <20220505220019.31166-1-pagupta@vmware.com>

Count the number of entries in the Rx queue for debugging.

Tested, using testpmd, for different hardware version on ESXi 7.0 Update 2

Signed-off-by: Pankaj Gupta <pagupta@vmware.com>
Reviewed-by: Jochen Behrens <jbehrens@vmware.com>
---
 drivers/net/vmxnet3/vmxnet3_ethdev.c |  1 +
 drivers/net/vmxnet3/vmxnet3_ethdev.h |  3 +++
 drivers/net/vmxnet3/vmxnet3_rxtx.c   | 30 ++++++++++++++++++++++++++++
 3 files changed, 34 insertions(+)

diff --git a/drivers/net/vmxnet3/vmxnet3_ethdev.c b/drivers/net/vmxnet3/vmxnet3_ethdev.c
index d5f9903946..2725e49ae9 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethdev.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethdev.c
@@ -294,6 +294,7 @@ eth_vmxnet3_dev_init(struct rte_eth_dev *eth_dev)
 	eth_dev->rx_pkt_burst = &vmxnet3_recv_pkts;
 	eth_dev->tx_pkt_burst = &vmxnet3_xmit_pkts;
 	eth_dev->tx_pkt_prepare = vmxnet3_prep_pkts;
+	eth_dev->rx_queue_count = vmxnet3_dev_rx_queue_count,
 	pci_dev = RTE_ETH_DEV_TO_PCI(eth_dev);
 
 	/* extra mbuf field is required to guess MSS */
diff --git a/drivers/net/vmxnet3/vmxnet3_ethdev.h b/drivers/net/vmxnet3/vmxnet3_ethdev.h
index 7ec3b2e1f0..ceaeb66392 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethdev.h
+++ b/drivers/net/vmxnet3/vmxnet3_ethdev.h
@@ -193,6 +193,9 @@ int  vmxnet3_dev_rx_queue_setup(struct rte_eth_dev *dev, uint16_t rx_queue_id,
 				uint16_t nb_rx_desc, unsigned int socket_id,
 				const struct rte_eth_rxconf *rx_conf,
 				struct rte_mempool *mb_pool);
+
+uint32_t vmxnet3_dev_rx_queue_count(void *rx_queue);
+
 int  vmxnet3_dev_tx_queue_setup(struct rte_eth_dev *dev, uint16_t tx_queue_id,
 				uint16_t nb_tx_desc, unsigned int socket_id,
 				const struct rte_eth_txconf *tx_conf);
diff --git a/drivers/net/vmxnet3/vmxnet3_rxtx.c b/drivers/net/vmxnet3/vmxnet3_rxtx.c
index d745064bc4..e15b377d8c 100644
--- a/drivers/net/vmxnet3/vmxnet3_rxtx.c
+++ b/drivers/net/vmxnet3/vmxnet3_rxtx.c
@@ -1019,6 +1019,36 @@ vmxnet3_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 	return nb_rx;
 }
 
+uint32_t
+vmxnet3_dev_rx_queue_count(void *rx_queue)
+{
+	const vmxnet3_rx_queue_t *rxq;
+	const Vmxnet3_RxCompDesc *rcd;
+	uint32_t idx, nb_rxd = 0;
+	uint8_t gen;
+
+	rxq = rx_queue;
+	if (unlikely(rxq->stopped)) {
+		PMD_RX_LOG(DEBUG, "Rx queue is stopped.");
+		return 0;
+	}
+
+	gen = rxq->comp_ring.gen;
+	idx = rxq->comp_ring.next2proc;
+	rcd = &rxq->comp_ring.base[idx].rcd;
+	while (rcd->gen == gen) {
+		if (rcd->eop)
+			++nb_rxd;
+		if (++idx == rxq->comp_ring.size) {
+			idx = 0;
+			gen ^= 1;
+		}
+		rcd = &rxq->comp_ring.base[idx].rcd;
+	}
+
+	return nb_rxd;
+}
+
 int
 vmxnet3_dev_tx_queue_setup(struct rte_eth_dev *dev,
 			   uint16_t queue_idx,
-- 
2.17.1


  parent reply	other threads:[~2022-05-05 22:00 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-05 22:00 [PATCH v4 0/8] vmxnet3 version V5 and V6 Pankaj Gupta
2022-05-05 22:00 ` [PATCH v4 1/8] net/vmxnet3: add V5 support Pankaj Gupta
2022-05-05 22:00 ` [PATCH v4 2/8] net/vmxnet3: implement reta query and reta update Pankaj Gupta
2022-05-12 10:58   ` Andrew Rybchenko
2022-05-05 22:00 ` Pankaj Gupta [this message]
2022-05-12 10:59   ` [PATCH v4 3/8] net/vmxnet3: add Rx queue usage count utility Andrew Rybchenko
2022-05-05 22:00 ` [PATCH v4 4/8] net/vmxnet3: report HW version on FW version get Pankaj Gupta
2022-05-05 22:00 ` [PATCH v4 5/8] net/vmxnet3: version 6 Pankaj Gupta
2022-05-12 10:57   ` Andrew Rybchenko
2022-05-05 22:00 ` [PATCH v4 6/8] net/vmxnet3: advertise RETA size in device info Pankaj Gupta
2022-05-05 22:00 ` [PATCH v4 7/8] net/vmxnet3: set packet type for fragmented packet Pankaj Gupta
2022-05-05 22:00 ` [PATCH v4 8/8] Fixes: 046f11619567 ("net/vmxnet3: support MSI-X interrupt") Pankaj Gupta

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=20220505220019.31166-4-pagupta@vmware.com \
    --to=pagupta@vmware.com \
    --cc=dev@dpdk.org \
    --cc=jbehrens@vmware.com \
    --cc=yongwang@vmware.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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).