1 files changed, 346 insertions, 153 deletions

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 6519cf62d9c..ba3e502c955 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -23,14 +23,16 @@
  *   o Allow clocksource drivers to be unregistered
  */
 
+#include <linux/device.h>
 #include <linux/clocksource.h>
-#include <linux/sysdev.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
 #include <linux/tick.h>
 #include <linux/kthread.h>
 
+#include "tick-internal.h"
+
 void timecounter_init(struct timecounter *tc,
 		      const struct cyclecounter *cc,
 		      u64 start_tstamp)
@@ -174,19 +176,20 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec)
 static struct clocksource *curr_clocksource;
 static LIST_HEAD(clocksource_list);
 static DEFINE_MUTEX(clocksource_mutex);
-static char override_name[32];
+static char override_name[CS_NAME_LEN];
 static int finished_booting;
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 static void clocksource_watchdog_work(struct work_struct *work);
+static void clocksource_select(void);
 
 static LIST_HEAD(watchdog_list);
 static struct clocksource *watchdog;
 static struct timer_list watchdog_timer;
 static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
 static DEFINE_SPINLOCK(watchdog_lock);
-static cycle_t watchdog_last;
 static int watchdog_running;
+static atomic_t watchdog_reset_pending;
 
 static int clocksource_watchdog_kthread(void *data);
 static void __clocksource_change_rating(struct clocksource *cs, int rating);
@@ -248,16 +251,13 @@ static void clocksource_watchdog(unsigned long data)
 	struct clocksource *cs;
 	cycle_t csnow, wdnow;
 	int64_t wd_nsec, cs_nsec;
-	int next_cpu;
+	int next_cpu, reset_pending;
 
 	spin_lock(&watchdog_lock);
 	if (!watchdog_running)
 		goto out;
 
-	wdnow = watchdog->read(watchdog);
-	wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask,
-				     watchdog->mult, watchdog->shift);
-	watchdog_last = wdnow;
+	reset_pending = atomic_read(&watchdog_reset_pending);
 
 	list_for_each_entry(cs, &watchdog_list, wd_list) {
 
@@ -268,20 +268,33 @@ static void clocksource_watchdog(unsigned long data)
 			continue;
 		}
 
+		local_irq_disable();
 		csnow = cs->read(cs);
+		wdnow = watchdog->read(watchdog);
+		local_irq_enable();
 
 		/* Clocksource initialized ? */
-		if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) {
+		if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) ||
+		    atomic_read(&watchdog_reset_pending)) {
 			cs->flags |= CLOCK_SOURCE_WATCHDOG;
-			cs->wd_last = csnow;
+			cs->wd_last = wdnow;
+			cs->cs_last = csnow;
 			continue;
 		}
 
-		/* Check the deviation from the watchdog clocksource. */
-		cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) &
+		wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask,
+					     watchdog->mult, watchdog->shift);
+
+		cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) &
 					     cs->mask, cs->mult, cs->shift);
-		cs->wd_last = csnow;
-		if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
+		cs->cs_last = csnow;
+		cs->wd_last = wdnow;
+
+		if (atomic_read(&watchdog_reset_pending))
+			continue;
+
+		/* Check the deviation from the watchdog clocksource. */
+		if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
 			clocksource_unstable(cs, cs_nsec - wd_nsec);
 			continue;
 		}
@@ -289,17 +302,41 @@ static void clocksource_watchdog(unsigned long data)
 		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
 		    (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
 		    (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
+			/* Mark it valid for high-res. */
 			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+
+			/*
+			 * clocksource_done_booting() will sort it if
+			 * finished_booting is not set yet.
+			 */
+			if (!finished_booting)
+				continue;
+
 			/*
-			 * We just marked the clocksource as highres-capable,
-			 * notify the rest of the system as well so that we
-			 * transition into high-res mode:
+			 * If this is not the current clocksource let
+			 * the watchdog thread reselect it. Due to the
+			 * change to high res this clocksource might
+			 * be preferred now. If it is the current
+			 * clocksource let the tick code know about
+			 * that change.
 			 */
-			tick_clock_notify();
+			if (cs != curr_clocksource) {
+				cs->flags |= CLOCK_SOURCE_RESELECT;
+				schedule_work(&watchdog_work);
+			} else {
+				tick_clock_notify();
+			}
 		}
 	}
 
 	/*
+	 * We only clear the watchdog_reset_pending, when we did a
+	 * full cycle through all clocksources.
+	 */
+	if (reset_pending)
+		atomic_dec(&watchdog_reset_pending);
+
+	/*
 	 * Cycle through CPUs to check if the CPUs stay synchronized
 	 * to each other.
 	 */
@@ -318,7 +355,6 @@ static inline void clocksource_start_watchdog(void)
 		return;
 	init_timer(&watchdog_timer);
 	watchdog_timer.function = clocksource_watchdog;
-	watchdog_last = watchdog->read(watchdog);
 	watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
 	add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask));
 	watchdog_running = 1;
@@ -342,23 +378,7 @@ static inline void clocksource_reset_watchdog(void)
 
 static void clocksource_resume_watchdog(void)
 {
-	unsigned long flags;
-
-	/*
-	 * We use trylock here to avoid a potential dead lock when
-	 * kgdb calls this code after the kernel has been stopped with
-	 * watchdog_lock held. When watchdog_lock is held we just
-	 * return and accept, that the watchdog might trigger and mark
-	 * the monitored clock source (usually TSC) unstable.
-	 *
-	 * This does not affect the other caller clocksource_resume()
-	 * because at this point the kernel is UP, interrupts are
-	 * disabled and nothing can hold watchdog_lock.
-	 */
-	if (!spin_trylock_irqsave(&watchdog_lock, flags))
-		return;
-	clocksource_reset_watchdog();
-	spin_unlock_irqrestore(&watchdog_lock, flags);
+	atomic_inc(&watchdog_reset_pending);
 }
 
 static void clocksource_enqueue_watchdog(struct clocksource *cs)
@@ -388,44 +408,39 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 
 static void clocksource_dequeue_watchdog(struct clocksource *cs)
 {
-	struct clocksource *tmp;
 	unsigned long flags;
 
 	spin_lock_irqsave(&watchdog_lock, flags);
-	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
-		/* cs is a watched clocksource. */
-		list_del_init(&cs->wd_list);
-	} else if (cs == watchdog) {
-		/* Reset watchdog cycles */
-		clocksource_reset_watchdog();
-		/* Current watchdog is removed. Find an alternative. */
-		watchdog = NULL;
-		list_for_each_entry(tmp, &clocksource_list, list) {
-			if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY)
-				continue;
-			if (!watchdog || tmp->rating > watchdog->rating)
-				watchdog = tmp;
+	if (cs != watchdog) {
+		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
+			/* cs is a watched clocksource. */
+			list_del_init(&cs->wd_list);
+			/* Check if the watchdog timer needs to be stopped. */
+			clocksource_stop_watchdog();
 		}
 	}
-	cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
-	/* Check if the watchdog timer needs to be stopped. */
-	clocksource_stop_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
-static int clocksource_watchdog_kthread(void *data)
+static int __clocksource_watchdog_kthread(void)
 {
 	struct clocksource *cs, *tmp;
 	unsigned long flags;
 	LIST_HEAD(unstable);
+	int select = 0;
 
-	mutex_lock(&clocksource_mutex);
 	spin_lock_irqsave(&watchdog_lock, flags);
-	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list)
+	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);
+			select = 1;
 		}
+		if (cs->flags & CLOCK_SOURCE_RESELECT) {
+			cs->flags &= ~CLOCK_SOURCE_RESELECT;
+			select = 1;
+		}
+	}
 	/* Check if the watchdog timer needs to be stopped. */
 	clocksource_stop_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
@@ -435,10 +450,23 @@ static int clocksource_watchdog_kthread(void *data)
 		list_del_init(&cs->wd_list);
 		__clocksource_change_rating(cs, 0);
 	}
+	return select;
+}
+
+static int clocksource_watchdog_kthread(void *data)
+{
+	mutex_lock(&clocksource_mutex);
+	if (__clocksource_watchdog_kthread())
+		clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
 
+static bool clocksource_is_watchdog(struct clocksource *cs)
+{
+	return cs == watchdog;
+}
+
 #else /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
 static void clocksource_enqueue_watchdog(struct clocksource *cs)
@@ -449,7 +477,9 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 
 static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
 static inline void clocksource_resume_watchdog(void) { }
-static inline int clocksource_watchdog_kthread(void *data) { return 0; }
+static inline int __clocksource_watchdog_kthread(void) { return 0; }
+static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
+void clocksource_mark_unstable(struct clocksource *cs) { }
 
 #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
@@ -492,66 +522,118 @@ void clocksource_touch_watchdog(void)
 }
 
 /**
- * clocksource_max_deferment - Returns max time the clocksource can be deferred
+ * clocksource_max_adjustment- Returns max adjustment amount
  * @cs:         Pointer to clocksource
  *
  */
-static u64 clocksource_max_deferment(struct clocksource *cs)
+static u32 clocksource_max_adjustment(struct clocksource *cs)
+{
+	u64 ret;
+	/*
+	 * We won't try to correct for more than 11% adjustments (110,000 ppm),
+	 */
+	ret = (u64)cs->mult * 11;
+	do_div(ret,100);
+	return (u32)ret;
+}
+
+/**
+ * clocks_calc_max_nsecs - Returns maximum nanoseconds that can be converted
+ * @mult:	cycle to nanosecond multiplier
+ * @shift:	cycle to nanosecond divisor (power of two)
+ * @maxadj:	maximum adjustment value to mult (~11%)
+ * @mask:	bitmask for two's complement subtraction of non 64 bit counters
+ */
+u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask)
 {
 	u64 max_nsecs, max_cycles;
 
 	/*
 	 * Calculate the maximum number of cycles that we can pass to the
 	 * cyc2ns function without overflowing a 64-bit signed result. The
-	 * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
-	 * is equivalent to the below.
-	 * max_cycles < (2^63)/cs->mult
-	 * max_cycles < 2^(log2((2^63)/cs->mult))
-	 * max_cycles < 2^(log2(2^63) - log2(cs->mult))
-	 * max_cycles < 2^(63 - log2(cs->mult))
-	 * max_cycles < 1 << (63 - log2(cs->mult))
+	 * maximum number of cycles is equal to ULLONG_MAX/(mult+maxadj)
+	 * which is equivalent to the below.
+	 * max_cycles < (2^63)/(mult + maxadj)
+	 * max_cycles < 2^(log2((2^63)/(mult + maxadj)))
+	 * max_cycles < 2^(log2(2^63) - log2(mult + maxadj))
+	 * max_cycles < 2^(63 - log2(mult + maxadj))
+	 * max_cycles < 1 << (63 - log2(mult + maxadj))
 	 * Please note that we add 1 to the result of the log2 to account for
 	 * any rounding errors, ensure the above inequality is satisfied and
 	 * no overflow will occur.
 	 */
-	max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+	max_cycles = 1ULL << (63 - (ilog2(mult + maxadj) + 1));
 
 	/*
 	 * The actual maximum number of cycles we can defer the clocksource is
-	 * determined by the minimum of max_cycles and cs->mask.
+	 * determined by the minimum of max_cycles and mask.
+	 * Note: Here we subtract the maxadj to make sure we don't sleep for
+	 * too long if there's a large negative adjustment.
 	 */
-	max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
-	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+	max_cycles = min(max_cycles, mask);
+	max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift);
+
+	return max_nsecs;
+}
+
+/**
+ * clocksource_max_deferment - Returns max time the clocksource can be deferred
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u64 clocksource_max_deferment(struct clocksource *cs)
+{
+	u64 max_nsecs;
 
+	max_nsecs = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj,
+					  cs->mask);
 	/*
 	 * To ensure that the clocksource does not wrap whilst we are idle,
 	 * limit the time the clocksource can be deferred by 12.5%. Please
 	 * note a margin of 12.5% is used because this can be computed with
 	 * a shift, versus say 10% which would require division.
 	 */
-	return max_nsecs - (max_nsecs >> 5);
+	return max_nsecs - (max_nsecs >> 3);
 }
 
 #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
 
-/**
- * clocksource_select - Select the best clocksource available
- *
- * Private function. Must hold clocksource_mutex when called.
- *
- * Select the clocksource with the best rating, or the clocksource,
- * which is selected by userspace override.
- */
-static void clocksource_select(void)
+static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur)
 {
-	struct clocksource *best, *cs;
+	struct clocksource *cs;
 
 	if (!finished_booting || list_empty(&clocksource_list))
+		return NULL;
+
+	/*
+	 * We pick the clocksource with the highest rating. If oneshot
+	 * mode is active, we pick the highres valid clocksource with
+	 * the best rating.
+	 */
+	list_for_each_entry(cs, &clocksource_list, list) {
+		if (skipcur && cs == curr_clocksource)
+			continue;
+		if (oneshot && !(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES))
+			continue;
+		return cs;
+	}
+	return NULL;
+}
+
+static void __clocksource_select(bool skipcur)
+{
+	bool oneshot = tick_oneshot_mode_active();
+	struct clocksource *best, *cs;
+
+	/* Find the best suitable clocksource */
+	best = clocksource_find_best(oneshot, skipcur);
+	if (!best)
 		return;
-	/* First clocksource on the list has the best rating. */
-	best = list_first_entry(&clocksource_list, struct clocksource, list);
+
 	/* Check for the override clocksource. */
 	list_for_each_entry(cs, &clocksource_list, list) {
+		if (skipcur && cs == curr_clocksource)
+			continue;
 		if (strcmp(cs->name, override_name) != 0)
 			continue;
 		/*
@@ -559,8 +641,7 @@ static void clocksource_select(void)
 		 * capable clocksource if the tick code is in oneshot
 		 * mode (highres or nohz)
 		 */
-		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
-		    tick_oneshot_mode_active()) {
+		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) {
 			/* Override clocksource cannot be used. */
 			printk(KERN_WARNING "Override clocksource %s is not "
 			       "HRT compatible. Cannot switch while in "
@@ -571,16 +652,35 @@ static void clocksource_select(void)
 			best = cs;
 		break;
 	}
-	if (curr_clocksource != best) {
-		printk(KERN_INFO "Switching to clocksource %s\n", best->name);
+
+	if (curr_clocksource != best && !timekeeping_notify(best)) {
+		pr_info("Switched to clocksource %s\n", best->name);
 		curr_clocksource = best;
-		timekeeping_notify(curr_clocksource);
 	}
 }
 
+/**
+ * clocksource_select - Select the best clocksource available
+ *
+ * Private function. Must hold clocksource_mutex when called.
+ *
+ * Select the clocksource with the best rating, or the clocksource,
+ * which is selected by userspace override.
+ */
+static void clocksource_select(void)
+{
+	return __clocksource_select(false);
+}
+
+static void clocksource_select_fallback(void)
+{
+	return __clocksource_select(true);
+}
+
 #else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */
 
 static inline void clocksource_select(void) { }
+static inline void clocksource_select_fallback(void) { }
 
 #endif
 
@@ -595,16 +695,11 @@ static int __init clocksource_done_booting(void)
 {
 	mutex_lock(&clocksource_mutex);
 	curr_clocksource = clocksource_default_clock();
-	mutex_unlock(&clocksource_mutex);
-
 	finished_booting = 1;
-
 	/*
 	 * Run the watchdog first to eliminate unstable clock sources
 	 */
-	clocksource_watchdog_kthread(NULL);
-
-	mutex_lock(&clocksource_mutex);
+	__clocksource_watchdog_kthread();
 	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;
@@ -626,22 +721,9 @@ static void clocksource_enqueue(struct clocksource *cs)
 	list_add(&cs->list, entry);
 }
 
-
-/*
- * Maximum time we expect to go between ticks. This includes idle
- * tickless time. It provides the trade off between selecting a
- * mult/shift pair that is very precise but can only handle a short
- * period of time, vs. a mult/shift pair that can handle long periods
- * of time but isn't as precise.
- *
- * This is a subsystem constant, and actual hardware limitations
- * may override it (ie: clocksources that wrap every 3 seconds).
- */
-#define MAX_UPDATE_LENGTH 5 /* Seconds */
-
 /**
  * __clocksource_updatefreq_scale - Used update clocksource with new freq
- * @t:		clocksource to be registered
+ * @cs:		clocksource to be registered
  * @scale:	Scale factor multiplied against freq to get clocksource hz
  * @freq:	clocksource frequency (cycles per second) divided by scale
  *
@@ -652,22 +734,48 @@ static void clocksource_enqueue(struct clocksource *cs)
  */
 void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
+	u64 sec;
 	/*
-	 * Ideally we want to use  some of the limits used in
-	 * clocksource_max_deferment, to provide a more informed
-	 * MAX_UPDATE_LENGTH. But for now this just gets the
-	 * register interface working properly.
+	 * Calc the maximum number of seconds which we can run before
+	 * wrapping around. For clocksources which have a mask > 32bit
+	 * we need to limit the max sleep time to have a good
+	 * conversion precision. 10 minutes is still a reasonable
+	 * amount. That results in a shift value of 24 for a
+	 * clocksource with mask >= 40bit and f >= 4GHz. That maps to
+	 * ~ 0.06ppm granularity for NTP. We apply the same 12.5%
+	 * margin as we do in clocksource_max_deferment()
 	 */
+	sec = (cs->mask - (cs->mask >> 3));
+	do_div(sec, freq);
+	do_div(sec, scale);
+	if (!sec)
+		sec = 1;
+	else if (sec > 600 && cs->mask > UINT_MAX)
+		sec = 600;
+
 	clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
-				      NSEC_PER_SEC/scale,
-				      MAX_UPDATE_LENGTH*scale);
+			       NSEC_PER_SEC / scale, sec * scale);
+
+	/*
+	 * for clocksources that have large mults, to avoid overflow.
+	 * Since mult may be adjusted by ntp, add an safety extra margin
+	 *
+	 */
+	cs->maxadj = clocksource_max_adjustment(cs);
+	while ((cs->mult + cs->maxadj < cs->mult)
+		|| (cs->mult - cs->maxadj > cs->mult)) {
+		cs->mult >>= 1;
+		cs->shift--;
+		cs->maxadj = clocksource_max_adjustment(cs);
+	}
+
 	cs->max_idle_ns = clocksource_max_deferment(cs);
 }
 EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
 
 /**
  * __clocksource_register_scale - Used to install new clocksources
- * @t:		clocksource to be registered
+ * @cs:		clocksource to be registered
  * @scale:	Scale factor multiplied against freq to get clocksource hz
  * @freq:	clocksource frequency (cycles per second) divided by scale
  *
@@ -685,8 +793,8 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 	/* Add clocksource to the clcoksource list */
 	mutex_lock(&clocksource_mutex);
 	clocksource_enqueue(cs);
-	clocksource_select();
 	clocksource_enqueue_watchdog(cs);
+	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
@@ -695,19 +803,25 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale);
 
 /**
  * clocksource_register - Used to install new clocksources
- * @t:		clocksource to be registered
+ * @cs:		clocksource to be registered
  *
  * Returns -EBUSY if registration fails, zero otherwise.
  */
 int clocksource_register(struct clocksource *cs)
 {
+	/* calculate max adjustment for given mult/shift */
+	cs->maxadj = clocksource_max_adjustment(cs);
+	WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+		"Clocksource %s might overflow on 11%% adjustment\n",
+		cs->name);
+
 	/* calculate max idle time permitted for this clocksource */
 	cs->max_idle_ns = clocksource_max_deferment(cs);
 
 	mutex_lock(&clocksource_mutex);
 	clocksource_enqueue(cs);
-	clocksource_select();
 	clocksource_enqueue_watchdog(cs);
+	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
@@ -718,30 +832,58 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating)
 	list_del(&cs->list);
 	cs->rating = rating;
 	clocksource_enqueue(cs);
-	clocksource_select();
 }
 
 /**
  * clocksource_change_rating - Change the rating of a registered clocksource
+ * @cs:		clocksource to be changed
+ * @rating:	new rating
  */
 void clocksource_change_rating(struct clocksource *cs, int rating)
 {
 	mutex_lock(&clocksource_mutex);
 	__clocksource_change_rating(cs, rating);
+	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 }
 EXPORT_SYMBOL(clocksource_change_rating);
 
+/*
+ * Unbind clocksource @cs. Called with clocksource_mutex held
+ */
+static int clocksource_unbind(struct clocksource *cs)
+{
+	/*
+	 * I really can't convince myself to support this on hardware
+	 * designed by lobotomized monkeys.
+	 */
+	if (clocksource_is_watchdog(cs))
+		return -EBUSY;
+
+	if (cs == curr_clocksource) {
+		/* Select and try to install a replacement clock source */
+		clocksource_select_fallback();
+		if (curr_clocksource == cs)
+			return -EBUSY;
+	}
+	clocksource_dequeue_watchdog(cs);
+	list_del_init(&cs->list);
+	return 0;
+}
+
 /**
  * clocksource_unregister - remove a registered clocksource
+ * @cs:	clocksource to be unregistered
  */
-void clocksource_unregister(struct clocksource *cs)
+int clocksource_unregister(struct clocksource *cs)
 {
+	int ret = 0;
+
 	mutex_lock(&clocksource_mutex);
-	clocksource_dequeue_watchdog(cs);
-	list_del(&cs->list);
-	clocksource_select();
+	if (!list_empty(&cs->list))
+		ret = clocksource_unbind(cs);
 	mutex_unlock(&clocksource_mutex);
+	return ret;
 }
 EXPORT_SYMBOL(clocksource_unregister);
 
@@ -749,13 +891,14 @@ EXPORT_SYMBOL(clocksource_unregister);
 /**
  * sysfs_show_current_clocksources - sysfs interface for current clocksource
  * @dev:	unused
+ * @attr:	unused
  * @buf:	char buffer to be filled with clocksource list
  *
  * Provides sysfs interface for listing current clocksource.
  */
 static ssize_t
-sysfs_show_current_clocksources(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+sysfs_show_current_clocksources(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	ssize_t count = 0;
 
@@ -766,35 +909,44 @@ sysfs_show_current_clocksources(struct sys_device *dev,
 	return count;
 }
 
+ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt)
+{
+	size_t ret = cnt;
+
+	/* strings from sysfs write are not 0 terminated! */
+	if (!cnt || cnt >= CS_NAME_LEN)
+		return -EINVAL;
+
+	/* strip of \n: */
+	if (buf[cnt-1] == '\n')
+		cnt--;
+	if (cnt > 0)
+		memcpy(dst, buf, cnt);
+	dst[cnt] = 0;
+	return ret;
+}
+
 /**
  * sysfs_override_clocksource - interface for manually overriding clocksource
  * @dev:	unused
+ * @attr:	unused
  * @buf:	name of override clocksource
  * @count:	length of buffer
  *
  * Takes input from sysfs interface for manually overriding the default
  * clocksource selection.
  */
-static ssize_t sysfs_override_clocksource(struct sys_device *dev,
-					  struct sysdev_attribute *attr,
+static ssize_t sysfs_override_clocksource(struct device *dev,
+					  struct device_attribute *attr,
 					  const char *buf, size_t count)
 {
-	size_t ret = count;
-
-	/* strings from sysfs write are not 0 terminated! */
-	if (count >= sizeof(override_name))
-		return -EINVAL;
-
-	/* strip of \n: */
-	if (buf[count-1] == '\n')
-		count--;
+	ssize_t ret;
 
 	mutex_lock(&clocksource_mutex);
 
-	if (count > 0)
-		memcpy(override_name, buf, count);
-	override_name[count] = 0;
-	clocksource_select();
+	ret = sysfs_get_uname(buf, override_name, count);
+	if (ret >= 0)
+		clocksource_select();
 
 	mutex_unlock(&clocksource_mutex);
 
@@ -802,15 +954,50 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
 }
 
 /**
+ * sysfs_unbind_current_clocksource - interface for manually unbinding clocksource
+ * @dev:	unused
+ * @attr:	unused
+ * @buf:	unused
+ * @count:	length of buffer
+ *
+ * Takes input from sysfs interface for manually unbinding a clocksource.
+ */
+static ssize_t sysfs_unbind_clocksource(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
+{
+	struct clocksource *cs;
+	char name[CS_NAME_LEN];
+	ssize_t ret;
+
+	ret = sysfs_get_uname(buf, name, count);
+	if (ret < 0)
+		return ret;
+
+	ret = -ENODEV;
+	mutex_lock(&clocksource_mutex);
+	list_for_each_entry(cs, &clocksource_list, list) {
+		if (strcmp(cs->name, name))
+			continue;
+		ret = clocksource_unbind(cs);
+		break;
+	}
+	mutex_unlock(&clocksource_mutex);
+
+	return ret ? ret : count;
+}
+
+/**
  * sysfs_show_available_clocksources - sysfs interface for listing clocksource
  * @dev:	unused
+ * @attr:	unused
  * @buf:	char buffer to be filled with clocksource list
  *
  * Provides sysfs interface for listing registered clocksources
  */
 static ssize_t
-sysfs_show_available_clocksources(struct sys_device *dev,
-				  struct sysdev_attribute *attr,
+sysfs_show_available_clocksources(struct device *dev,
+				  struct device_attribute *attr,
 				  char *buf)
 {
 	struct clocksource *src;
@@ -839,35 +1026,41 @@ sysfs_show_available_clocksources(struct sys_device *dev,
 /*
  * Sysfs setup bits:
  */
-static SYSDEV_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources,
+static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources,
 		   sysfs_override_clocksource);
 
-static SYSDEV_ATTR(available_clocksource, 0444,
+static DEVICE_ATTR(unbind_clocksource, 0200, NULL, sysfs_unbind_clocksource);
+
+static DEVICE_ATTR(available_clocksource, 0444,
 		   sysfs_show_available_clocksources, NULL);
 
-static struct sysdev_class clocksource_sysclass = {
+static struct bus_type clocksource_subsys = {
 	.name = "clocksource",
+	.dev_name = "clocksource",
 };
 
-static struct sys_device device_clocksource = {
+static struct device device_clocksource = {
 	.id	= 0,
-	.cls	= &clocksource_sysclass,
+	.bus	= &clocksource_subsys,
 };
 
 static int __init init_clocksource_sysfs(void)
 {
-	int error = sysdev_class_register(&clocksource_sysclass);
+	int error = subsys_system_register(&clocksource_subsys, NULL);
 
 	if (!error)
-		error = sysdev_register(&device_clocksource);
+		error = device_register(&device_clocksource);
 	if (!error)
-		error = sysdev_create_file(
+		error = device_create_file(
 				&device_clocksource,
-				&attr_current_clocksource);
+				&dev_attr_current_clocksource);
+	if (!error)
+		error = device_create_file(&device_clocksource,
+					   &dev_attr_unbind_clocksource);
 	if (!error)
-		error = sysdev_create_file(
+		error = device_create_file(
 				&device_clocksource,
-				&attr_available_clocksource);
+				&dev_attr_available_clocksource);
 	return error;
 }