softlockup: add sched_clock_tick() to avoid kernel warning on kgdb resume

When CONFIG_HAVE_UNSTABLE_SCHED_CLOCK is set sched_clock() gets the
time from hardware, such as from TSC.  In this configuration kgdb will
report a softlock warning messages on resuming or detaching from a
debug session.

Sequence of events in the problem case:

1) "cpu sched clock" and "hardware time" are at 100 sec prior
   to a call to kgdb_handle_exception()

2) Debugger waits in kgdb_handle_exception() for 80 sec and on exit
   the following is called ...  touch_softlockup_watchdog() -->
   __raw_get_cpu_var(touch_timestamp) = 0;

3) "cpu sched clock" = 100s (it was not updated, because the interrupt
   was disabled in kgdb) but the "hardware time" = 180 sec

4) The first timer interrupt after resuming from kgdb_handle_exception
   updates the watchdog from the "cpu sched clock"

update_process_times() { ...  run_local_timers() --> softlockup_tick()
--> check (touch_timestamp == 0) (it is "YES" here, we have set
"touch_timestamp = 0" at kgdb) --> __touch_softlockup_watchdog()
***(A)--> reset "touch_timestamp" to "get_timestamp()" (Here, the
"touch_timestamp" will still be set to 100s.)  ...

    scheduler_tick() ***(B)--> sched_clock_tick() (update "cpu sched
    clock" to "hardware time" = 180s) ...  }

5) The Second timer interrupt handler appears to have a large jump and
   trips the softlockup warning.

update_process_times() { ...  run_local_timers() --> softlockup_tick()
--> "cpu sched clock" - "touch_timestamp" = 180s-100s > 60s --> printk
"soft lockup error messages" ...  }

note: ***(A) reset "touch_timestamp" to "get_timestamp(this_cpu)"

Why "touch_timestamp" is 100 sec, instead of 180 sec?

With the CONFIG_HAVE_UNSTABLE_SCHED_CLOCK" set the call trace of
get_timestamp() is:

get_timestamp(this_cpu) -->cpu_clock(this_cpu)
-->sched_clock_cpu(this_cpu) -->__update_sched_clock(sched_clock_data,
now)

The __update_sched_clock() function uses the GTOD tick value to create
a window to normalize the "now" values.  So if "now" values is too big
for sched_clock_data, it will be ignored.

The fix is to invoke sched_clock_tick() to update "cpu sched clock" in
order to recover from this state.  This is done by introducing the
function touch_softlockup_watchdog_sync(), which allows kgdb to
request that the sched clock is updated when the watchdog thread runs
the first time after a resume from kgdb.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Dongdong Deng <Dongdong.Deng@windriver.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: peterz@infradead.org

include/linux/sched.h

@@ -300,6 +300,7 @@ extern void sched_show_task(struct task_struct *p);
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 extern void softlockup_tick(void);
 extern void touch_softlockup_watchdog(void);
+extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
 extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
 				    struct file *filp, void __user *buffer,
@@ -313,6 +314,9 @@ static inline void softlockup_tick(void)
 static inline void touch_softlockup_watchdog(void)
 {
 }
+static inline void touch_softlockup_watchdog_sync(void)
+{
+}
 static inline void touch_all_softlockup_watchdogs(void)
 {
 }

kernel/kgdb.c

@@ -595,7 +595,7 @@ static void kgdb_wait(struct pt_regs *regs)
 
 	/* Signal the primary CPU that we are done: */
 	atomic_set(&cpu_in_kgdb[cpu], 0);
-	touch_softlockup_watchdog();
+	touch_softlockup_watchdog_sync();
 	clocksource_touch_watchdog();
 	local_irq_restore(flags);
 }
@@ -1438,7 +1438,7 @@ acquirelock:
 	    atomic_read(&kgdb_cpu_doing_single_step) != cpu) {
 
 		atomic_set(&kgdb_active, -1);
-		touch_softlockup_watchdog();
+		touch_softlockup_watchdog_sync();
 		clocksource_touch_watchdog();
 		local_irq_restore(flags);
 
@@ -1531,7 +1531,7 @@ acquirelock:
 kgdb_restore:
 	/* Free kgdb_active */
 	atomic_set(&kgdb_active, -1);
-	touch_softlockup_watchdog();
+	touch_softlockup_watchdog_sync();
 	clocksource_touch_watchdog();
 	local_irq_restore(flags);
 

kernel/softlockup.c

@@ -79,6 +79,14 @@ void touch_softlockup_watchdog(void)
 }
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 
+static int softlock_touch_sync[NR_CPUS];
+
+void touch_softlockup_watchdog_sync(void)
+{
+	softlock_touch_sync[raw_smp_processor_id()] = 1;
+	__raw_get_cpu_var(touch_timestamp) = 0;
+}
+
 void touch_all_softlockup_watchdogs(void)
 {
 	int cpu;
@@ -118,6 +126,14 @@ void softlockup_tick(void)
 	}
 
 	if (touch_timestamp == 0) {
+		if (unlikely(softlock_touch_sync[this_cpu])) {
+			/*
+			 * If the time stamp was touched atomically
+			 * make sure the scheduler tick is up to date.
+			 */
+			softlock_touch_sync[this_cpu] = 0;
+			sched_clock_tick();
+		}
 		__touch_softlockup_watchdog();
 		return;
 	}