[PATCH v2] tracing/function-graph-tracer: prevent from hrtimer interruptinfinite loop

[Frederic Weisbecker]

Impact: fix a system hang on slow systems

While testing the function graph tracer on VirtualBox, I had a system hang
immediatly after enabling the tracer.
If hrtimer is enabled on kernel, a slow system can spend too much time during
tracing the hrtimer_interrupt which will do eternal loops, assuming it always
have to retry its process because too much time elapsed during its time
update.
Now we provide a feature which lurks at the number of retries on
hrtimer_interrupt. After 10 retries, the function graph tracer will definetly stop
its tracing.

Changes in v2 (Andrew's comments):

_ Moved ftrace_graph_hrtimer_*() from linux/ftrace.h to kernel/trace/trace.c, also
  uninlined them.
_ Turn ftrace_graph_hrtimer_loop into static
_ Fix my evil english :-)
_ Very small other fixes...

Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
 include/linux/ftrace.h |   10 ++++++++++
 kernel/hrtimer.c       |    5 +++++
 kernel/trace/ftrace.c  |   29 +++++++++++++++++++++++++++++
 3 files changed, 44 insertions(+), 0 deletions(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 286af82..4874782 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -408,6 +408,13 @@ extern void unregister_ftrace_graph(void);
 extern void ftrace_graph_init_task(struct task_struct *t);
 extern void ftrace_graph_exit_task(struct task_struct *t);
 
+/*
+ * Prevent infinite loops on hrtimer_interrupt()
+ * due to tracing on slow systems.
+ */
+extern void ftrace_graph_hrtimer_enter(void);
+extern void ftrace_graph_hrtimer_retry(void);
+
 static inline int task_curr_ret_stack(struct task_struct *t)
 {
 	return t->curr_ret_stack;
@@ -437,6 +444,9 @@ static inline int task_curr_ret_stack(struct task_struct *tsk)
 
 static inline void pause_graph_tracing(void) { }
 static inline void unpause_graph_tracing(void) { }
+
+static inline void ftrace_graph_hrtimer_enter(void) { }
+static inline void ftrace_graph_hrtimer_retry(void) { }
 #endif
 
 #ifdef CONFIG_TRACING
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index b741f85..12fa4d9 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -44,6 +44,7 @@
 #include <linux/seq_file.h>
 #include <linux/err.h>
 #include <linux/debugobjects.h>
+#include <linux/ftrace.h>
 
 #include <asm/uaccess.h>
 
@@ -1186,7 +1187,11 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	cpu_base->nr_events++;
 	dev->next_event.tv64 = KTIME_MAX;
 
+	ftrace_graph_hrtimer_enter();
  retry:
+	/* Prevent from infinite loop on slow systems while tracing */
+	ftrace_graph_hrtimer_retry();
+
 	now = ktime_get();
 
 	expires_next.tv64 = KTIME_MAX;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a12f80e..0b3a7a8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1955,6 +1955,9 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 static atomic_t ftrace_graph_active;
 
+/* Count number of retries attempts in hrtimer_interrupt() */
+static DEFINE_PER_CPU(int, ftrace_graph_hrtimer_loop);
+
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 {
 	return 0;
@@ -2095,6 +2098,32 @@ void ftrace_graph_exit_task(struct task_struct *t)
 	kfree(ret_stack);
 }
 
+/*
+ * Those two functions prevent infinite loops on hrtimer_interrupt
+ * because the function graph tracer can consume too much time processing
+ * on slow systems, and the hrtimer_interrupt can relaunch its processing
+ * if too much time elapsed during its previous time update.
+ *
+ * Note that we don't need an atomic counter for loops here because
+ * interrupts are disabled in hrtimer_interrupt.
+ */
+
+void ftrace_graph_hrtimer_enter(void)
+{
+	__get_cpu_var(ftrace_graph_hrtimer_loop) = 0;
+}
+
+void ftrace_graph_hrtimer_retry(void)
+{
+	__get_cpu_var(ftrace_graph_hrtimer_loop)++;
+
+	if (__get_cpu_var(ftrace_graph_hrtimer_loop) == 10) {
+		ftrace_graph_stop();
+		printk(KERN_WARNING "function-graph-tracer: hrtimer_interrupt exceeded"
+				" 10 loops. Stopping tracing\n");
+	}
+}
+
 void ftrace_graph_stop(void)
 {
 	ftrace_stop();
-- 
1.6.0.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/