[PATCH][v3] rtnetlink: add rtnl_lock debug log

@@ -2027,6 +2027,16 @@ config KCOV_IRQ_AREA_SIZE
 	  soft interrupts. This specifies the size of those areas in the
 	  number of unsigned long words.
 
+config RTNL_LOCK_DEBUG
+	bool "rtnl_lock debugging, deadlock detection"
+	depends on STACKTRACE_SUPPORT
+	select STACKTRACE
+	help
+	  If you say Y here then the kernel will detect whether any function
+	  hold rtnl_lock too long and some key information will be printed
+	  out to help locate the problem.
+	  If unsure, say N.
+
 menuconfig RUNTIME_TESTING_MENU
 	bool "Runtime Testing"
 	def_bool y

@@ -12,6 +12,8 @@
  *	Vitaly E. Lavrov		RTA_OK arithmetics was wrong.
  */
 
+#define pr_fmt(fmt) "rtnetlink: " fmt
+
 #include <linux/bitops.h>
 #include <linux/errno.h>
 #include <linux/module.h>

@@ -57,6 +59,81 @@
 #define RTNL_MAX_TYPE		50
 #define RTNL_SLAVE_MAX_TYPE	40
 
+#ifdef CONFIG_RTNL_LOCK_DEBUG
+
+#include <linux/sched/debug.h>
+#include <linux/stacktrace.h>
+
+/* Debug log and btrace will be printed when the rtnl_lock
+ * is held for more than RTNL_LOCK_MAX_HOLD_TIME seconds
+ */
+#define RTNL_LOCK_MAX_HOLD_TIME 2
+
+#define RTNL_LOCK_MAX_TRACE     10    /* stack trace length */
+
+struct rtnl_debug_btrace_t {
+	struct task_struct *task;
+	int pid;
+	unsigned long long start_time;
+	unsigned long long end_time;
+	unsigned long addrs[RTNL_LOCK_MAX_TRACE];
+	unsigned int  nr_entries;
+};
+
+static struct rtnl_debug_btrace_t rtnl_instance;
+
+static void rtnl_print_btrace(struct timer_list *unused);
+static DEFINE_TIMER(rtnl_chk_timer, rtnl_print_btrace);
+
+/* Save stack trace to the given array of RTNL_LOCK_MAX_TRACE size.
+ */
+static int __save_stack_trace(unsigned long *trace)
+{
+	return stack_trace_save(trace, RTNL_LOCK_MAX_TRACE, 0);
+}
+
+static void rtnl_get_btrace(struct task_struct *who)
+{
+	unsigned long expires;
+
+	rtnl_instance.task = who;
+	rtnl_instance.pid = who->pid;
+	rtnl_instance.start_time = sched_clock();
+	rtnl_instance.end_time = 0;
+	rtnl_instance.nr_entries = __save_stack_trace(rtnl_instance.addrs);
+
+	expires = jiffies + RTNL_LOCK_MAX_HOLD_TIME * HZ;
+	mod_timer(&rtnl_chk_timer, expires);
+}
+
+static void rtnl_print_btrace(struct timer_list *unused)
+{
+	pr_info("-- %s start --\n", __func__);
+	pr_info("%s[%d][%c] hold rtnl_lock more than %d sec, start time: %llu\n",
+		rtnl_instance.task->comm,
+		rtnl_instance.pid,
+		task_state_to_char(rtnl_instance.task),
+		RTNL_LOCK_MAX_HOLD_TIME,
+		rtnl_instance.start_time);
+	stack_trace_print(rtnl_instance.addrs, rtnl_instance.nr_entries, 0);
+	show_stack(rtnl_instance.task, NULL, KERN_INFO);
+	pr_info("-- %s end --\n", __func__);
+}
+
+static void rtnl_relase_btrace(void)
+{
+	rtnl_instance.end_time = sched_clock();
+	del_timer_sync(&rtnl_chk_timer);
+
+	if (rtnl_instance.end_time - rtnl_instance.start_time > 2 * NSEC_PER_SEC) {
+		pr_info("rtnl_lock is held by [%d] from [%llu] to [%llu]\n",
+			rtnl_instance.pid,
+			rtnl_instance.start_time,
+			rtnl_instance.end_time);
+	}
+}
+#endif
+
 struct rtnl_link {
 	rtnl_doit_func		doit;
 	rtnl_dumpit_func	dumpit;

@@ -70,6 +147,10 @@ static DEFINE_MUTEX(rtnl_mutex);
 void rtnl_lock(void)
 {
 	mutex_lock(&rtnl_mutex);
+
+#ifdef CONFIG_RTNL_LOCK_DEBUG
+	rtnl_get_btrace(current);
+#endif
 }
 EXPORT_SYMBOL(rtnl_lock);
 

@@ -95,6 +176,10 @@ void __rtnl_unlock(void)
 
 	defer_kfree_skb_list = NULL;
 
+#ifdef CONFIG_RTNL_LOCK_DEBUG
+	rtnl_relase_btrace();
+#endif
+
 	mutex_unlock(&rtnl_mutex);
 
 	while (head) {