On 9/8/16 6:35 PM, Jojy Varghese wrote:
> Thanks for the feedback guys. I appreciate it.
>
> I am working with 4.4.3 kernel. I will try to reproduce the issue
> with the kernel tree at
> https://git.kernel.org/cgit/linux/kernel/git/davem/net.git.
>
> In the meantime, the only data I have now is :
> - "dst-ifdown" does not look correct since it will never release
> reference to loopback device.
> - One way to fix might be to assign the 'dst''s net device to the
> init net device. I thought adding reference to init net device's
> loopback might be safe.
>
> Any suggestion on debugging further is much appreciated.
>
Last 2 times I chased down netdev refcnts I used the attach patch. It adds
tracepoints to dev_hold and dev_put.
perf record -e net:dev_hold,net:dev_put -a -g -- <run your test>
You probably will need to increase memory for perf buffers (e.g., -m 8192).
It will dump a lot of data but you will find the missing put; you just have to
be patient wading through the data and matching up hold and put references.
python/perl script with perf script can make that easier.
---
Have you looked at whether there are open sockets? e.g., perhaps a dst
reference is cached on a socket
From 068b1b8362ec5fd1b9dffdbd6e84474ada2eb829 Mon Sep 17 00:00:00 2001
From: David Ahern <d...@cumulusnetworks.com>
Date: Thu, 11 Feb 2016 02:40:12 -0800
Subject: [PATCH] Add tracepoints to dev_hold and dev_put
Signed-off-by: David Ahern <d...@cumulusnetworks.com>
---
include/linux/netdevice.h | 6 ++++++
include/trace/events/net.h | 38 ++++++++++++++++++++++++++++++++++++++
net/core/dev.c | 21 +++++++++++++++++++++
3 files changed, 65 insertions(+)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 219f53c30cb3..7ef6fc672dfb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3193,6 +3193,7 @@ extern int netdev_budget;
/* Called by rtnetlink.c:rtnl_unlock() */
void netdev_run_todo(void);
+#if 0
/**
* dev_put - release reference to device
* @dev: network device
@@ -3214,6 +3215,11 @@ static inline void dev_hold(struct net_device *dev)
{
this_cpu_inc(*dev->pcpu_refcnt);
}
+#else
+void dev_put(struct net_device *dev);
+void dev_hold(struct net_device *dev);
+
+#endif
/* Carrier loss detection, dial on demand. The functions netif_carrier_on
* and _off may be called from IRQ context, but it is caller
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 49cc7c3de252..9ed73dfe9d09 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -236,6 +236,44 @@ DEFINE_EVENT(net_dev_rx_verbose_template,
netif_rx_ni_entry,
TP_ARGS(skb)
);
+TRACE_EVENT(dev_put,
+
+ TP_PROTO(struct net_device *dev),
+
+ TP_ARGS(dev),
+
+ TP_STRUCT__entry(
+ __string( name, dev->name )
+ __field( int, refcnt )
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, dev->name);
+ __entry->refcnt = netdev_refcnt_read(dev);
+ ),
+
+ TP_printk("dev=%s refcnt %d", __get_str(name), __entry->refcnt)
+);
+
+TRACE_EVENT(dev_hold,
+
+ TP_PROTO(struct net_device *dev),
+
+ TP_ARGS(dev),
+
+ TP_STRUCT__entry(
+ __string( name, dev->name )
+ __field( int, refcnt )
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, dev->name);
+ __entry->refcnt = netdev_refcnt_read(dev);
+ ),
+
+ TP_printk("dev=%s refcnt %d", __get_str(name), __entry->refcnt)
+);
+
#endif /* _TRACE_NET_H */
/* This part must be outside protection */
diff --git a/net/core/dev.c b/net/core/dev.c
index f1284835b8c9..99ac067afd18 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8117,3 +8117,24 @@ static int __init net_dev_init(void)
}
subsys_initcall(net_dev_init);
+
+
+void dev_put(struct net_device *dev)
+{
+ this_cpu_dec(*dev->pcpu_refcnt);
+ trace_dev_put(dev);
+}
+EXPORT_SYMBOL(dev_put);
+
+/**
+ * dev_hold - get reference to device
+ * @dev: network device
+ *
+ * Hold reference to device to keep it from being freed.
+ */
+void dev_hold(struct net_device *dev)
+{
+ this_cpu_inc(*dev->pcpu_refcnt);
+ trace_dev_hold(dev);
+}
+EXPORT_SYMBOL(dev_hold);
--
2.1.4
