Web lists-archives.com

Re: unregister_netdevice: waiting for DEV to become free (2)




On 4/15/19 7:36 AM, Tetsuo Handa wrote:
> I traced using debug printk() patch shown below.
> 

I find tracepoints (see attached patch) and perf are easier to use to
debug device refcnt problems.

For example, limit the stack you have to deal with via sysctl -w
kernel.perf_event_max_stack=16, and add a filter (e.g., --filter 'name
== "lo"') to limit collection to a specific device.
From 068b1b8362ec5fd1b9dffdbd6e84474ada2eb829 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@xxxxxxxxxxxxxxxxxxx>
Date: Thu, 11 Feb 2016 02:40:12 -0800
Subject: [PATCH] Add tracepoints to dev_hold and dev_put

Signed-off-by: David Ahern <dsa@xxxxxxxxxxxxxxxxxxx>
---
 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