clocksource: fix resume logic

We need to make sure that the clocksources are resumed, when timekeeping is
resumed.  The current resume logic does not guarantee this.

Add a resume function pointer to the clocksource struct, so clocksource
drivers which need to reinitialize the clocksource can provide a resume
function.

Add a resume function, which calls the maybe available clocksource resume
functions and resets the watchdog function, so a stable TSC can be used
accross suspend/resume.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: john stultz <johnstul@us.ibm.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 50 insertions, 0 deletions

diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 2665ca04cf8f..bf297b03a4e4 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -49,6 +49,7 @@ struct clocksource;
  * @shift:              cycle to nanosecond divisor (power of two)
  * @flags:              flags describing special properties
  * @vread:              vsyscall based read
+ * @resume:             resume function for the clocksource, if necessary
  * @cycle_interval:     Used internally by timekeeping core, please ignore.
  * @xtime_interval:     Used internally by timekeeping core, please ignore.
  */
@@ -65,6 +66,7 @@ struct clocksource {
         u32 shift;
         unsigned long flags;
         cycle_t (*vread)(void);
+        void (*resume)(void);
 
         /* timekeeping specific data, ignore */
         cycle_t cycle_interval;
@@ -209,6 +211,7 @@ static inline void clocksource_calculate_interval(struct clocksource *c,
 extern int clocksource_register(struct clocksource*);
 extern struct clocksource* clocksource_get_next(void);
 extern void clocksource_change_rating(struct clocksource *cs, int rating);
+extern void clocksource_resume(void);
 
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL
 extern void update_vsyscall(struct timespec *ts, struct clocksource *c);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index db0c725de5ea..3db5c3c460d7 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -74,6 +74,8 @@ static struct clocksource *watchdog;
 static struct timer_list watchdog_timer;
 static DEFINE_SPINLOCK(watchdog_lock);
 static cycle_t watchdog_last;
+static int watchdog_resumed;
+
 /*
  * Interval: 0.5sec Threshold: 0.0625s
  */
@@ -98,15 +100,26 @@ static void clocksource_watchdog(unsigned long data)
         struct clocksource *cs, *tmp;
         cycle_t csnow, wdnow;
         int64_t wd_nsec, cs_nsec;
+        int resumed;
 
         spin_lock(&watchdog_lock);
 
+        resumed = watchdog_resumed;
+        if (unlikely(resumed))
+                watchdog_resumed = 0;
+
         wdnow = watchdog->read();
         wd_nsec = cyc2ns(watchdog, (wdnow - watchdog_last) & watchdog->mask);
         watchdog_last = wdnow;
 
         list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
                 csnow = cs->read();
+
+                if (unlikely(resumed)) {
+                        cs->wd_last = csnow;
+                        continue;
+                }
+
                 /* Initialized ? */
                 if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) {
                         if ((cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
@@ -136,6 +149,13 @@ static void clocksource_watchdog(unsigned long data)
         }
         spin_unlock(&watchdog_lock);
 }
+static void clocksource_resume_watchdog(void)
+{
+        spin_lock(&watchdog_lock);
+        watchdog_resumed = 1;
+        spin_unlock(&watchdog_lock);
+}
+
 static void clocksource_check_watchdog(struct clocksource *cs)
 {
         struct clocksource *cse;
@@ -182,9 +202,34 @@ static void clocksource_check_watchdog(struct clocksource *cs)
         if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
                 cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 }
+
+static inline void clocksource_resume_watchdog(void) { }
 #endif
 
 /**
+ * clocksource_resume - resume the clocksource(s)
+ */
+void clocksource_resume(void)
+{
+        struct list_head *tmp;
+        unsigned long flags;
+
+        spin_lock_irqsave(&clocksource_lock, flags);
+
+        list_for_each(tmp, &clocksource_list) {
+                struct clocksource *cs;
+
+                cs = list_entry(tmp, struct clocksource, list);
+                if (cs->resume)
+                        cs->resume();
+        }
+
+        clocksource_resume_watchdog();
+
+        spin_unlock_irqrestore(&clocksource_lock, flags);
+}
+
+/**
  * clocksource_get_next - Returns the selected clocksource
  *
  */
diff --git a/kernel/timer.c b/kernel/timer.c
index de85f8491c1d..59a28b1752f8 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1499,6 +1499,8 @@ unregister_time_interpolator(struct time_interpolator *ti)
                 prev = &curr->next;
         }
 
+        clocksource_resume();
+
         write_seqlock_irqsave(&xtime_lock, flags);
         if (ti == time_interpolator) {
                 /* we lost the best time-interpolator: */