From: Tony Lu <tonylu@linux.alibaba.com>
To: davem@davemloft.net
Cc: xiyou.wangcong@gmail.com, eric.dumazet@gmail.com,
shemminger@osdl.org, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: [PATCH v2 2/2] net: add trace events for net_device refcnt
Date: Tue, 12 Nov 2019 21:05:13 +0800 [thread overview]
Message-ID: <20191112130510.91570-2-tonylu@linux.alibaba.com> (raw)
In-Reply-To: <20191112130510.91570-1-tonylu@linux.alibaba.com>
The net_device refcnt leak is hard to trace and debug for now. We need
the ability to know when and who manipulated the refcnt.
Adding the trace events for net_device pcpu_refcnt and also tracepoints
in dev_put()/dev_hold(), provides the history of net_device refcnt inc
and desc. With trace logs analysis, paring the put and hold history, we
can find out who leaked.
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
---
include/trace/events/net.h | 41 ++++++++++++++++++++++++++++++++++++++
net/core/dev.c | 4 ++++
2 files changed, 45 insertions(+)
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 3b28843652d2..3bf6dd738882 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -326,6 +326,47 @@ DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit,
TP_ARGS(ret)
);
+DECLARE_EVENT_CLASS(net_dev_refcnt_template,
+
+ TP_PROTO(struct net_device *dev, void *location),
+
+ TP_ARGS(dev, location),
+
+ TP_STRUCT__entry(
+ __string( name, dev->name )
+ __field( int, refcnt )
+ __field( void *, location )
+ ),
+
+ TP_fast_assign(
+ int i, refcnt = 0;
+
+ for_each_possible_cpu(i)
+ refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i);
+
+ __assign_str(name, dev->name);
+ __entry->refcnt = refcnt;
+ __entry->location = location;
+ ),
+
+ TP_printk("dev=%s refcnt=%d location=%p",
+ __get_str(name), __entry->refcnt, __entry->location)
+);
+
+DEFINE_EVENT(net_dev_refcnt_template, net_dev_put,
+
+ TP_PROTO(struct net_device *dev, void *location),
+
+ TP_ARGS(dev, location)
+);
+
+DEFINE_EVENT(net_dev_refcnt_template, net_dev_hold,
+
+ TP_PROTO(struct net_device *dev, void *location),
+
+ TP_ARGS(dev, location)
+);
+
#endif /* _TRACE_NET_H */
/* This part must be outside protection */
diff --git a/net/core/dev.c b/net/core/dev.c
index 620fb3d6718a..163870a09984 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1302,6 +1302,8 @@ EXPORT_SYMBOL(netdev_notify_peers);
*/
void dev_put(struct net_device *dev)
{
+ trace_net_dev_put(dev, __builtin_return_address(0));
+
this_cpu_dec(*dev->pcpu_refcnt);
}
EXPORT_SYMBOL(dev_put);
@@ -1314,6 +1316,8 @@ EXPORT_SYMBOL(dev_put);
*/
void dev_hold(struct net_device *dev)
{
+ trace_net_dev_hold(dev, __builtin_return_address(0));
+
this_cpu_inc(*dev->pcpu_refcnt);
}
EXPORT_SYMBOL(dev_hold);
--
2.24.0
next prev parent reply other threads:[~2019-11-12 13:08 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-12 13:05 [PATCH v2 1/2] net: remove static inline from dev_put()/dev_hold() Tony Lu
2019-11-12 13:05 ` Tony Lu [this message]
2019-11-12 15:27 ` [PATCH v2 2/2] net: add trace events for net_device refcnt David Ahern
2019-11-16 19:47 ` Cong Wang
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=20191112130510.91570-2-tonylu@linux.alibaba.com \
--to=tonylu@linux.alibaba.com \
--cc=davem@davemloft.net \
--cc=eric.dumazet@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=shemminger@osdl.org \
--cc=xiyou.wangcong@gmail.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).