DPDK patches and discussions
 help / color / mirror / Atom feed
From: longli@linuxonhyperv.com
To: Stephen Hemminger <sthemmin@microsoft.com>
Cc: dev@dpdk.org, Long Li <longli@microsoft.com>
Subject: [dpdk-dev] [PATCH 2/2] net/netvsc: detach external buffer on failure
Date: Tue, 23 Jun 2020 18:11:46 -0700	[thread overview]
Message-ID: <1592961106-82820-2-git-send-email-longli@linuxonhyperv.com> (raw)
In-Reply-To: <1592961106-82820-1-git-send-email-longli@linuxonhyperv.com>

From: Long Li <longli@microsoft.com>

When external buffer is used, driver should detach it if it doesn't make it
successfully to the queue.

Signed-off-by: Long Li <longli@microsoft.com>
---
 drivers/net/netvsc/hn_rxtx.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/netvsc/hn_rxtx.c b/drivers/net/netvsc/hn_rxtx.c
index aece38e2d..52f5c0191 100644
--- a/drivers/net/netvsc/hn_rxtx.c
+++ b/drivers/net/netvsc/hn_rxtx.c
@@ -550,6 +550,7 @@ static void hn_rxpkt(struct hn_rx_queue *rxq, struct hn_rx_bufinfo *rxb,
 {
 	struct hn_data *hv = rxq->hv;
 	struct rte_mbuf *m;
+	bool use_extbuf = false;
 
 	m = rte_pktmbuf_alloc(rxq->mb_pool);
 	if (unlikely(!m)) {
@@ -587,6 +588,7 @@ static void hn_rxpkt(struct hn_rx_queue *rxq, struct hn_rx_bufinfo *rxb,
 		rte_pktmbuf_attach_extbuf(m, data, iova,
 					  dlen + headroom, shinfo);
 		m->data_off = headroom;
+		use_extbuf = true;
 	} else {
 		/* Mbuf's in pool must be large enough to hold small packets */
 		if (unlikely(rte_pktmbuf_tailroom(m) < dlen)) {
@@ -614,6 +616,8 @@ static void hn_rxpkt(struct hn_rx_queue *rxq, struct hn_rx_bufinfo *rxb,
 		if (!hv->vlan_strip && rte_vlan_insert(&m)) {
 			PMD_DRV_LOG(DEBUG, "vlan insert failed");
 			++rxq->stats.errors;
+			if (use_extbuf)
+				rte_pktmbuf_detach_extbuf(m);
 			rte_pktmbuf_free(m);
 			return;
 		}
@@ -648,6 +652,8 @@ static void hn_rxpkt(struct hn_rx_queue *rxq, struct hn_rx_bufinfo *rxb,
 	if (unlikely(rte_ring_sp_enqueue(rxq->rx_ring, m) != 0)) {
 		++rxq->stats.ring_full;
 		PMD_RX_LOG(DEBUG, "rx ring full");
+		if (use_extbuf)
+			rte_pktmbuf_detach_extbuf(m);
 		rte_pktmbuf_free(m);
 	}
 }
-- 
2.17.1


  reply	other threads:[~2020-06-24  1:12 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-24  1:11 [dpdk-dev] [PATCH 1/2] net/netvsc: fix underflow error when external mbuf are used in the receive path longli
2020-06-24  1:11 ` longli [this message]
2020-07-02  0:05   ` [dpdk-dev] [PATCH 2/2] net/netvsc: detach external buffer on failure Stephen Hemminger
2020-07-02  0:06 ` [dpdk-dev] [PATCH 1/2] net/netvsc: fix underflow error when external mbuf are used in the receive path Stephen Hemminger
2020-07-09 15:28   ` Ferruh Yigit

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=1592961106-82820-2-git-send-email-longli@linuxonhyperv.com \
    --to=longli@linuxonhyperv.com \
    --cc=dev@dpdk.org \
    --cc=longli@microsoft.com \
    --cc=sthemmin@microsoft.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).