public inbox for dev@dpdk.org
 help / color / mirror / Atom feed
From: Long Li <longli@microsoft.com>
To: dev@dpdk.org, Wei Hu <weh@microsoft.com>,
	Stephen Hemminger <stephen@networkplumber.org>,
	stable@dpdk.org, Dariusz Sosnowski <dsosnowski@nvidia.com>,
	Viacheslav Ovsiienko <viacheslavo@nvidia.com>,
	Bing Zhao <bingz@nvidia.com>, Ori Kam <orika@nvidia.com>,
	Suanming Mou <suanmingm@nvidia.com>,
	Matan Azrad <matan@nvidia.com>
Cc: Long Li <longli@microsoft.com>
Subject: [PATCH v5 7/7] net/mlx4: fix fast-path ops setup in secondary process
Date: Thu, 26 Feb 2026 17:59:27 -0800	[thread overview]
Message-ID: <20260227015928.14338-8-longli@microsoft.com> (raw)
In-Reply-To: <20260227015928.14338-1-longli@microsoft.com>

The secondary process MLX4_MP_REQ_START_RXTX handler sets
dev->rx_pkt_burst and dev->tx_pkt_burst, but does not update
rte_eth_fp_ops[].rxq.data and txq.data. Since rte_eth_rx_burst()
uses rte_eth_fp_ops (which is process-local), the secondary
retains stale queue data pointers after VF hot-add, causing a
segfault.

Similarly, the MLX4_MP_REQ_STOP_RXTX handler sets dev burst
functions to dummy but does not update rte_eth_fp_ops burst
pointers, leaving the secondary calling into freed resources.

Fix by updating rte_eth_fp_ops rxq.data and txq.data in the
START_RXTX handler, and rte_eth_fp_ops burst function pointers
in the STOP_RXTX handler.

Fixes: 080d8bc15905 ("net/mlx4: sync stop/start with secondary process")
Cc: stable@dpdk.org
Signed-off-by: Long Li <longli@microsoft.com>
---
 drivers/net/mlx4/mlx4_mp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/mlx4/mlx4_mp.c b/drivers/net/mlx4/mlx4_mp.c
index 534cb31151..0784b2d59a 100644
--- a/drivers/net/mlx4/mlx4_mp.c
+++ b/drivers/net/mlx4/mlx4_mp.c
@@ -149,6 +149,10 @@ mp_secondary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
 		}
 #endif
 		close(mp_msg->fds[0]);
+		rte_eth_fp_ops[param->port_id].rx_pkt_burst = dev->rx_pkt_burst;
+		rte_eth_fp_ops[param->port_id].tx_pkt_burst = dev->tx_pkt_burst;
+		rte_eth_fp_ops[param->port_id].rxq.data = dev->data->rx_queues;
+		rte_eth_fp_ops[param->port_id].txq.data = dev->data->tx_queues;
 		rte_mb();
 		mp_init_msg(dev, &mp_res, param->type);
 		res->result = 0;
@@ -158,6 +162,8 @@ mp_secondary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
 		INFO("port %u stopping datapath", dev->data->port_id);
 		dev->tx_pkt_burst = rte_eth_pkt_burst_dummy;
 		dev->rx_pkt_burst = rte_eth_pkt_burst_dummy;
+		rte_eth_fp_ops[param->port_id].rx_pkt_burst = rte_eth_pkt_burst_dummy;
+		rte_eth_fp_ops[param->port_id].tx_pkt_burst = rte_eth_pkt_burst_dummy;
 		rte_mb();
 		mp_init_msg(dev, &mp_res, param->type);
 		res->result = 0;
-- 
2.43.0


  parent reply	other threads:[~2026-02-27  2:00 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-27  1:59 [PATCH v5 0/7] multi-process and VF hotplug fixes Long Li
2026-02-27  1:59 ` [PATCH v5 1/7] net/netvsc: fix race conditions on VF add/remove events Long Li
2026-02-27  1:59 ` [PATCH v5 2/7] net/netvsc: add multi-process VF device removal support Long Li
2026-02-27  1:59 ` [PATCH v5 3/7] net/mana: fix PD resource leak on device close Long Li
2026-02-27  1:59 ` [PATCH v5 4/7] net/netvsc: fix devargs memory leak on hotplug Long Li
2026-02-27  1:59 ` [PATCH v5 5/7] net/mana: fix fast-path ops setup in secondary process Long Li
2026-02-27  1:59 ` [PATCH v5 6/7] net/mlx5: " Long Li
2026-02-27  1:59 ` Long Li [this message]
2026-02-28  0:41 ` [PATCH v5 0/7] multi-process and VF hotplug fixes Stephen Hemminger
2026-02-28  1:36   ` [EXTERNAL] " Long Li
2026-02-28 17:03 ` Stephen Hemminger
2026-03-01  5:00   ` [EXTERNAL] " Long Li

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=20260227015928.14338-8-longli@microsoft.com \
    --to=longli@microsoft.com \
    --cc=bingz@nvidia.com \
    --cc=dev@dpdk.org \
    --cc=dsosnowski@nvidia.com \
    --cc=matan@nvidia.com \
    --cc=orika@nvidia.com \
    --cc=stable@dpdk.org \
    --cc=stephen@networkplumber.org \
    --cc=suanmingm@nvidia.com \
    --cc=viacheslavo@nvidia.com \
    --cc=weh@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