From: Wang Zhan <wang.zhan@smartx.com>
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
pabeni@redhat.com, horms@kernel.org, keyong.sun@smartx.com,
Wang Zhan <wang.zhan@smartx.com>
Subject: [PATCH net-next v2 2/2] net: sysfs: use ops lock for speed and duplex
Date: Thu, 3 Sep 2026 21:33:14 +0800 [thread overview]
Message-ID: <20260903133314.3703381-3-wang.zhan@smartx.com> (raw)
In-Reply-To: <20260903133314.3703381-1-wang.zhan@smartx.com>
Reading /sys/class/net/<dev>/{speed,duplex} takes rtnl_lock() even for
ops-locked devices whose get_link_ksettings callback does not require it.
This unnecessarily serializes monitoring reads with unrelated rtnetlink
operations.
On CPU-throttled hosts, a periodic reader such as node-exporter can hold
RTNL for hundreds of milliseconds while an mlx5 callback runs, delaying
unrelated rtnetlink operations.
Use the netdev instance lock for these devices. Retain sysfs_rtnl_lock()
for legacy devices and callbacks that request
ETHTOOL_OP_NEEDS_RTNL_LINKSETTINGS.
Preserve the existing speed and duplex sysfs ABI, including -EINVAL for
devices that are down or callbacks that fail.
Assisted-by: LLM
Signed-off-by: Wang Zhan <wang.zhan@smartx.com>
---
net/core/net-sysfs.c | 27 +++++++++++++++++++++------
1 file changed, 21 insertions(+), 6 deletions(-)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 7bb8bbc1f71ea..fa790e4425704 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -123,26 +123,41 @@ static int sysfs_get_link_ksettings(struct device *dev,
struct ethtool_link_ksettings *cmd)
{
struct net_device *netdev = to_net_dev(dev);
+ bool need_rtnl;
int ret;
/*
- * The check is also done in __ethtool_get_link_ksettings; this helps
+ * The check is also done in netif_get_link_ksettings; this helps
* returning early without hitting the locking section below.
*/
if (!netdev->ethtool_ops->get_link_ksettings)
return -EINVAL;
- ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
- if (ret)
- return ret;
+ need_rtnl = !netdev_need_ops_lock(netdev) ||
+ (netdev->ethtool_ops->op_needs_rtnl &
+ ETHTOOL_OP_NEEDS_RTNL_LINKSETTINGS);
+ if (need_rtnl) {
+ ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+ if (ret)
+ return ret;
+ }
+ netdev_lock_ops(netdev);
+
+ if (!dev_isalive(netdev)) {
+ ret = -ENODEV;
+ goto unlock;
+ }
ret = -EINVAL;
if (netif_running(netdev)) {
- if (!__ethtool_get_link_ksettings(netdev, cmd))
+ if (!netif_get_link_ksettings(netdev, cmd))
ret = 0;
}
- rtnl_unlock();
+unlock:
+ netdev_unlock_ops(netdev);
+ if (need_rtnl)
+ rtnl_unlock();
return ret;
}
--
2.47.3
next prev parent reply other threads:[~2026-09-03 13:34 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-03 13:33 [PATCH net-next v2 0/2] net: sysfs: use ops lock for speed and duplex Wang Zhan
2026-09-03 13:33 ` [PATCH net-next v2 1/2] net: sysfs: factor out link settings read Wang Zhan
2026-09-03 13:33 ` Wang Zhan [this message]
2026-09-08 13:40 ` [PATCH net-next v2 0/2] net: sysfs: use ops lock for speed and duplex patchwork-bot+netdevbpf
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=20260903133314.3703381-3-wang.zhan@smartx.com \
--to=wang.zhan@smartx.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=horms@kernel.org \
--cc=keyong.sun@smartx.com \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.