Various tsc/clocksource fixes

@@ -1244,7 +1244,7 @@ static void tsc_refine_calibration_work(
 
 	/* Don't bother refining TSC on unstable systems */
 	if (tsc_unstable)
-		return;
+		goto unreg;
 
 	/*
 	 * Since the work is started early in boot, we may be

@@ -1297,11 +1297,12 @@ static void tsc_refine_calibration_work(
 
 out:
 	if (tsc_unstable)
-		return;
+		goto unreg;
 
 	if (boot_cpu_has(X86_FEATURE_ART))
 		art_related_clocksource = &clocksource_tsc;
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
+unreg:
 	clocksource_unregister(&clocksource_tsc_early);
 }
 

@@ -1311,8 +1312,8 @@ static int __init init_tsc_clocksource(v
 	if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
 		return 0;
 
-	if (check_tsc_unstable())
-		return 0;
+	if (tsc_unstable)
+		goto unreg;
 
 	if (tsc_clocksource_reliable)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;

@@ -1328,6 +1329,7 @@ static int __init init_tsc_clocksource(v
 		if (boot_cpu_has(X86_FEATURE_ART))
 			art_related_clocksource = &clocksource_tsc;
 		clocksource_register_khz(&clocksource_tsc, tsc_khz);
+unreg:
 		clocksource_unregister(&clocksource_tsc_early);
 		return 0;
 	}

@@ -119,6 +119,16 @@ static DEFINE_SPINLOCK(watchdog_lock);
 static int watchdog_running;
 static atomic_t watchdog_reset_pending;
 
+static void inline clocksource_watchdog_lock(unsigned long *flags)
+{
+	spin_lock_irqsave(&watchdog_lock, *flags);
+}
+
+static void inline clocksource_watchdog_unlock(unsigned long *flags)
+{
+	spin_unlock_irqrestore(&watchdog_lock, *flags);
+}
+
 static int clocksource_watchdog_kthread(void *data);
 static void __clocksource_change_rating(struct clocksource *cs, int rating);
 

@@ -142,6 +152,9 @@ static void __clocksource_unstable(struc
 	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
 	cs->flags |= CLOCK_SOURCE_UNSTABLE;
 
+	if (list_empty(&cs->list))
+		return;
+
 	if (cs->mark_unstable)
 		cs->mark_unstable(cs);
 

@@ -164,7 +177,7 @@ void clocksource_mark_unstable(struct cl
 
 	spin_lock_irqsave(&watchdog_lock, flags);
 	if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) {
-		if (list_empty(&cs->wd_list))
+		if (!list_empty(&cs->list) && list_empty(&cs->wd_list))
 			list_add(&cs->wd_list, &watchdog_list);
 		__clocksource_unstable(cs);
 	}

@@ -319,9 +332,6 @@ static void clocksource_resume_watchdog(
 
 static void clocksource_enqueue_watchdog(struct clocksource *cs)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&watchdog_lock, flags);
 	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
 		/* cs is a clocksource to be watched. */
 		list_add(&cs->wd_list, &watchdog_list);

@@ -331,7 +341,6 @@ static void clocksource_enqueue_watchdog
 		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
 			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 	}
-	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
 static void clocksource_select_watchdog(bool fallback)

@@ -373,9 +382,6 @@ static void clocksource_select_watchdog(
 
 static void clocksource_dequeue_watchdog(struct clocksource *cs)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&watchdog_lock, flags);
 	if (cs != watchdog) {
 		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
 			/* cs is a watched clocksource. */

@@ -384,21 +390,19 @@ static void clocksource_dequeue_watchdog
 			clocksource_stop_watchdog();
 		}
 	}
-	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
 static int __clocksource_watchdog_kthread(void)
 {
 	struct clocksource *cs, *tmp;
 	unsigned long flags;
-	LIST_HEAD(unstable);
 	int select = 0;
 
 	spin_lock_irqsave(&watchdog_lock, flags);
 	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
 		if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
 			list_del_init(&cs->wd_list);
-			list_add(&cs->wd_list, &unstable);
+			__clocksource_change_rating(cs, 0);
 			select = 1;
 		}
 		if (cs->flags & CLOCK_SOURCE_RESELECT) {

@@ -410,11 +414,6 @@ static int __clocksource_watchdog_kthrea
 	clocksource_stop_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
 
-	/* Needs to be done outside of watchdog lock */
-	list_for_each_entry_safe(cs, tmp, &unstable, wd_list) {
-		list_del_init(&cs->wd_list);
-		__clocksource_change_rating(cs, 0);
-	}
 	return select;
 }
 

@@ -779,14 +778,19 @@ EXPORT_SYMBOL_GPL(__clocksource_update_f
  */
 int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
+	unsigned long flags;
 
 	/* Initialize mult/shift and max_idle_ns */
 	__clocksource_update_freq_scale(cs, scale, freq);
 
 	/* Add clocksource to the clocksource list */
 	mutex_lock(&clocksource_mutex);
+
+	clocksource_watchdog_lock(&flags);
 	clocksource_enqueue(cs);
 	clocksource_enqueue_watchdog(cs);
+	clocksource_watchdog_unlock(&flags);
+
 	clocksource_select();
 	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);

@@ -808,8 +812,13 @@ static void __clocksource_change_rating(
  */
 void clocksource_change_rating(struct clocksource *cs, int rating)
 {
+	unsigned long flags;
+
 	mutex_lock(&clocksource_mutex);
+	clocksource_watchdog_lock(&flags);
 	__clocksource_change_rating(cs, rating);
+	clocksource_watchdog_unlock(&flags);
+
 	clocksource_select();
 	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);

@@ -821,6 +830,8 @@ EXPORT_SYMBOL(clocksource_change_rating)
  */
 static int clocksource_unbind(struct clocksource *cs)
 {
+	unsigned long flags;
+
 	if (clocksource_is_watchdog(cs)) {
 		/* Select and try to install a replacement watchdog. */
 		clocksource_select_watchdog(true);

@@ -834,8 +845,12 @@ static int clocksource_unbind(struct clo
 		if (curr_clocksource == cs)
 			return -EBUSY;
 	}
+
+	clocksource_watchdog_lock(&flags);
 	clocksource_dequeue_watchdog(cs);
 	list_del_init(&cs->list);
+	clocksource_watchdog_unlock(&flags);
+
 	return 0;
 }
 

@@ -119,6 +119,16 @@ static DEFINE_SPINLOCK(watchdog_lock);
 static int watchdog_running;
 static atomic_t watchdog_reset_pending;
 
+static void inline clocksource_watchdog_lock(unsigned long *flags)
+{
+	spin_lock_irqsave(&watchdog_lock, *flags);
+}
+
+static void inline clocksource_watchdog_unlock(unsigned long *flags)
+{
+	spin_unlock_irqrestore(&watchdog_lock, *flags);
+}
+
 static int clocksource_watchdog_kthread(void *data);
 static void __clocksource_change_rating(struct clocksource *cs, int rating);
 

@@ -142,6 +152,9 @@ static void __clocksource_unstable(struc
 	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
 	cs->flags |= CLOCK_SOURCE_UNSTABLE;
 
+	if (list_empty(&cs->list))
+		return;
+
 	if (cs->mark_unstable)
 		cs->mark_unstable(cs);
 

@@ -164,7 +177,7 @@ void clocksource_mark_unstable(struct cl
 
 	spin_lock_irqsave(&watchdog_lock, flags);
 	if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) {
-		if (list_empty(&cs->wd_list))
+		if (!list_empty(&cs->list) && list_empty(&cs->wd_list))
 			list_add(&cs->wd_list, &watchdog_list);
 		__clocksource_unstable(cs);
 	}

@@ -319,9 +332,6 @@ static void clocksource_resume_watchdog(
 
 static void clocksource_enqueue_watchdog(struct clocksource *cs)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&watchdog_lock, flags);
 	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
 		/* cs is a clocksource to be watched. */
 		list_add(&cs->wd_list, &watchdog_list);

@@ -331,7 +341,6 @@ static void clocksource_enqueue_watchdog
 		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
 			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 	}
-	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
 static void clocksource_select_watchdog(bool fallback)

@@ -373,9 +382,6 @@ static void clocksource_select_watchdog(
 
 static void clocksource_dequeue_watchdog(struct clocksource *cs)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&watchdog_lock, flags);
 	if (cs != watchdog) {
 		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
 			/* cs is a watched clocksource. */

@@ -384,21 +390,19 @@ static void clocksource_dequeue_watchdog
 			clocksource_stop_watchdog();
 		}
 	}
-	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
 static int __clocksource_watchdog_kthread(void)
 {
 	struct clocksource *cs, *tmp;
 	unsigned long flags;
-	LIST_HEAD(unstable);
 	int select = 0;
 
 	spin_lock_irqsave(&watchdog_lock, flags);
 	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
 		if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
 			list_del_init(&cs->wd_list);
-			list_add(&cs->wd_list, &unstable);
+			__clocksource_change_rating(cs, 0);
 			select = 1;
 		}
 		if (cs->flags & CLOCK_SOURCE_RESELECT) {

@@ -410,11 +414,6 @@ static int __clocksource_watchdog_kthrea
 	clocksource_stop_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
 
-	/* Needs to be done outside of watchdog lock */
-	list_for_each_entry_safe(cs, tmp, &unstable, wd_list) {
-		list_del_init(&cs->wd_list);
-		__clocksource_change_rating(cs, 0);
-	}
 	return select;
 }
 

@@ -447,6 +446,9 @@ static inline int __clocksource_watchdog
 static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
 void clocksource_mark_unstable(struct clocksource *cs) { }
 
+static void inline clocksource_watchdog_lock(unsigned long *flags) { }
+static void inline clocksource_watchdog_unlock(unsigned long *flags) { }
+
 #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
 /**

@@ -779,14 +781,19 @@ EXPORT_SYMBOL_GPL(__clocksource_update_f
  */
 int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
+	unsigned long flags;
 
 	/* Initialize mult/shift and max_idle_ns */
 	__clocksource_update_freq_scale(cs, scale, freq);
 
 	/* Add clocksource to the clocksource list */
 	mutex_lock(&clocksource_mutex);
+
+	clocksource_watchdog_lock(&flags);
 	clocksource_enqueue(cs);
 	clocksource_enqueue_watchdog(cs);
+	clocksource_watchdog_unlock(&flags);
+
 	clocksource_select();
 	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);

@@ -808,8 +815,13 @@ static void __clocksource_change_rating(
  */
 void clocksource_change_rating(struct clocksource *cs, int rating)
 {
+	unsigned long flags;
+
 	mutex_lock(&clocksource_mutex);
+	clocksource_watchdog_lock(&flags);
 	__clocksource_change_rating(cs, rating);
+	clocksource_watchdog_unlock(&flags);
+
 	clocksource_select();
 	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);

@@ -821,6 +833,8 @@ EXPORT_SYMBOL(clocksource_change_rating)
  */
 static int clocksource_unbind(struct clocksource *cs)
 {
+	unsigned long flags;
+
 	if (clocksource_is_watchdog(cs)) {
 		/* Select and try to install a replacement watchdog. */
 		clocksource_select_watchdog(true);

@@ -834,8 +848,12 @@ static int clocksource_unbind(struct clo
 		if (curr_clocksource == cs)
 			return -EBUSY;
 	}
+
+	clocksource_watchdog_lock(&flags);
 	clocksource_dequeue_watchdog(cs);
 	list_del_init(&cs->list);
+	clocksource_watchdog_unlock(&flags);
+
 	return 0;
 }
 

@@ -332,6 +332,8 @@ static void clocksource_resume_watchdog(
 
 static void clocksource_enqueue_watchdog(struct clocksource *cs)
 {
+	INIT_LIST_HEAD(&cs->wd_list);
+
 	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
 		/* cs is a clocksource to be watched. */
 		list_add(&cs->wd_list, &watchdog_list);

@@ -1067,6 +1067,7 @@ static struct clocksource clocksource_ts
 	.resume			= tsc_resume,
 	.mark_unstable		= tsc_cs_mark_unstable,
 	.tick_stable		= tsc_cs_tick_stable,
+	.list			= LIST_HEAD_INIT(clocksource_tsc_early.list),
 };
 
 /*

@@ -1086,6 +1087,7 @@ static struct clocksource clocksource_ts
 	.resume			= tsc_resume,
 	.mark_unstable		= tsc_cs_mark_unstable,
 	.tick_stable		= tsc_cs_tick_stable,
+	.list			= LIST_HEAD_INIT(clocksource_tsc.list),
 };
 
 void mark_tsc_unstable(char *reason)

@@ -1098,13 +1100,9 @@ void mark_tsc_unstable(char *reason)
 		clear_sched_clock_stable();
 	disable_sched_clock_irqtime();
 	pr_info("Marking TSC unstable due to %s\n", reason);
-	/* Change only the rating, when not registered */
-	if (clocksource_tsc.mult) {
-		clocksource_mark_unstable(&clocksource_tsc);
-	} else {
-		clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
-		clocksource_tsc.rating = 0;
-	}
+
+	clocksource_mark_unstable(&clocksource_tsc_early);
+	clocksource_mark_unstable(&clocksource_tsc);
 }
 
 EXPORT_SYMBOL_GPL(mark_tsc_unstable);

@@ -152,12 +152,19 @@ static void __clocksource_unstable(struc
 	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
 	cs->flags |= CLOCK_SOURCE_UNSTABLE;
 
-	if (list_empty(&cs->list))
+	/*
+	 * If the clocksource is registered clocksource_watchdog_kthread() will
+	 * re-rate and re-select.
+	 */
+	if (list_empty(&cs->list)) {
+		cs->rating = 0;
 		return;
+	}
 
 	if (cs->mark_unstable)
 		cs->mark_unstable(cs);
 
+	/* kick clocksource_watchdog_kthread() */
 	if (finished_booting)
 		schedule_work(&watchdog_work);
 }

@@ -173,10 +173,8 @@ static void __clocksource_unstable(struc
  * clocksource_mark_unstable - mark clocksource unstable via watchdog
  * @cs:		clocksource to be marked unstable
  *
- * This function is called instead of clocksource_change_rating from
- * cpu hotplug code to avoid a deadlock between the clocksource mutex
- * and the cpu hotplug mutex. It defers the update of the clocksource
- * to the watchdog thread.
+ * This function is called by the x86 TSC code to mark clocksources as unstable;
+ * it defers demotion and re-selection to a kthread.
  */
 void clocksource_mark_unstable(struct clocksource *cs)
 {

@@ -129,31 +129,19 @@ static void inline clocksource_watchdog_
 	spin_unlock_irqrestore(&watchdog_lock, *flags);
 }
 
-static int clocksource_watchdog_kthread(void *data);
-static void __clocksource_change_rating(struct clocksource *cs, int rating);
-
 /*
  * Interval: 0.5sec Threshold: 0.0625s
  */
 #define WATCHDOG_INTERVAL (HZ >> 1)
 #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4)
 
-static void clocksource_watchdog_work(struct work_struct *work)
-{
-	/*
-	 * If kthread_run fails the next watchdog scan over the
-	 * watchdog_list will find the unstable clock again.
-	 */
-	kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog");
-}
-
 static void __clocksource_unstable(struct clocksource *cs)
 {
 	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
 	cs->flags |= CLOCK_SOURCE_UNSTABLE;
 
 	/*
-	 * If the clocksource is registered clocksource_watchdog_kthread() will
+	 * If the clocksource is registered clocksource_watchdog_work() will
 	 * re-rate and re-select.
 	 */
 	if (list_empty(&cs->list)) {

@@ -164,7 +152,7 @@ static void __clocksource_unstable(struc
 	if (cs->mark_unstable)
 		cs->mark_unstable(cs);
 
-	/* kick clocksource_watchdog_kthread() */
+	/* kick clocksource_watchdog_work() */
 	if (finished_booting)
 		schedule_work(&watchdog_work);
 }

@@ -174,7 +162,7 @@ static void __clocksource_unstable(struc
  * @cs:		clocksource to be marked unstable
  *
  * This function is called by the x86 TSC code to mark clocksources as unstable;
- * it defers demotion and re-selection to a kthread.
+ * it defers demotion and re-selection to a work.
  */
 void clocksource_mark_unstable(struct clocksource *cs)
 {

@@ -399,7 +387,9 @@ static void clocksource_dequeue_watchdog
 	}
 }
 
-static int __clocksource_watchdog_kthread(void)
+static void __clocksource_change_rating(struct clocksource *cs, int rating);
+
+static int __clocksource_watchdog_work(void)
 {
 	struct clocksource *cs, *tmp;
 	unsigned long flags;

@@ -424,13 +414,12 @@ static int __clocksource_watchdog_kthrea
 	return select;
 }
 
-static int clocksource_watchdog_kthread(void *data)
+static void clocksource_watchdog_work(struct work_struct *work)
 {
 	mutex_lock(&clocksource_mutex);
-	if (__clocksource_watchdog_kthread())
+	if (__clocksource_watchdog_work())
 		clocksource_select();
 	mutex_unlock(&clocksource_mutex);
-	return 0;
 }
 
 static bool clocksource_is_watchdog(struct clocksource *cs)

@@ -449,7 +438,7 @@ static void clocksource_enqueue_watchdog
 static void clocksource_select_watchdog(bool fallback) { }
 static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
 static inline void clocksource_resume_watchdog(void) { }
-static inline int __clocksource_watchdog_kthread(void) { return 0; }
+static inline int __clocksource_watchdog_work(void) { return 0; }
 static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
 void clocksource_mark_unstable(struct clocksource *cs) { }
 

@@ -680,7 +669,7 @@ static int __init clocksource_done_booti
 	/*
 	 * Run the watchdog first to eliminate unstable clock sources
 	 */
-	__clocksource_watchdog_kthread();
+	__clocksource_watchdog_work();
 	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;