1 files changed, 376 insertions, 75 deletions

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index cce484a2cc7c..2a7802ec480c 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -14,10 +14,24 @@
 #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
 #include <linux/tick.h>
 #include <linux/kthread.h>
+#include <linux/prandom.h>
+#include <linux/cpu.h>
 
 #include "tick-internal.h"
 #include "timekeeping_internal.h"
 
+static void clocksource_enqueue(struct clocksource *cs);
+
+static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end)
+{
+	u64 delta = clocksource_delta(end, start, cs->mask, cs->max_raw_delta);
+
+	if (likely(delta < cs->max_cycles))
+		return clocksource_cyc2ns(delta, cs->mult, cs->shift);
+
+	return mul_u64_u32_shr(delta, cs->mult, cs->shift);
+}
+
 /**
  * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks
  * @mult:	pointer to mult variable
@@ -38,7 +52,7 @@
  * calculated mult and shift factors. This guarantees that no 64bit
  * overflow happens when the input value of the conversion is
  * multiplied with the calculated mult factor. Larger ranges may
- * reduce the conversion accuracy by chosing smaller mult and shift
+ * reduce the conversion accuracy by choosing smaller mult and shift
  * factors.
  */
 void
@@ -93,6 +107,48 @@ static char override_name[CS_NAME_LEN];
 static int finished_booting;
 static u64 suspend_start;
 
+/*
+ * Interval: 0.5sec.
+ */
+#define WATCHDOG_INTERVAL (HZ >> 1)
+#define WATCHDOG_INTERVAL_MAX_NS ((2 * WATCHDOG_INTERVAL) * (NSEC_PER_SEC / HZ))
+
+/*
+ * Threshold: 0.0312s, when doubled: 0.0625s.
+ */
+#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 5)
+
+/*
+ * Maximum permissible delay between two readouts of the watchdog
+ * clocksource surrounding a read of the clocksource being validated.
+ * This delay could be due to SMIs, NMIs, or to VCPU preemptions.  Used as
+ * a lower bound for cs->uncertainty_margin values when registering clocks.
+ *
+ * The default of 500 parts per million is based on NTP's limits.
+ * If a clocksource is good enough for NTP, it is good enough for us!
+ *
+ * In other words, by default, even if a clocksource is extremely
+ * precise (for example, with a sub-nanosecond period), the maximum
+ * permissible skew between the clocksource watchdog and the clocksource
+ * under test is not permitted to go below the 500ppm minimum defined
+ * by MAX_SKEW_USEC.  This 500ppm minimum may be overridden using the
+ * CLOCKSOURCE_WATCHDOG_MAX_SKEW_US Kconfig option.
+ */
+#ifdef CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
+#define MAX_SKEW_USEC	CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
+#else
+#define MAX_SKEW_USEC	(125 * WATCHDOG_INTERVAL / HZ)
+#endif
+
+/*
+ * Default for maximum permissible skew when cs->uncertainty_margin is
+ * not specified, and the lower bound even when cs->uncertainty_margin
+ * is specified.  This is also the default that is used when registering
+ * clocks with unspecifed cs->uncertainty_margin, so this macro is used
+ * even in CONFIG_CLOCKSOURCE_WATCHDOG=n kernels.
+ */
+#define WATCHDOG_MAX_SKEW (MAX_SKEW_USEC * NSEC_PER_USEC)
+
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 static void clocksource_watchdog_work(struct work_struct *work);
 static void clocksource_select(void);
@@ -104,6 +160,7 @@ static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
 static DEFINE_SPINLOCK(watchdog_lock);
 static int watchdog_running;
 static atomic_t watchdog_reset_pending;
+static int64_t watchdog_max_interval;
 
 static inline void clocksource_watchdog_lock(unsigned long *flags)
 {
@@ -116,13 +173,6 @@ static inline void clocksource_watchdog_unlock(unsigned long *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)
 {
@@ -142,6 +192,13 @@ static void clocksource_watchdog_work(struct work_struct *work)
 	kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog");
 }
 
+static void clocksource_change_rating(struct clocksource *cs, int rating)
+{
+	list_del(&cs->list);
+	cs->rating = rating;
+	clocksource_enqueue(cs);
+}
+
 static void __clocksource_unstable(struct clocksource *cs)
 {
 	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
@@ -184,12 +241,201 @@ void clocksource_mark_unstable(struct clocksource *cs)
 	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
-static void clocksource_watchdog(struct timer_list *unused)
+static int verify_n_cpus = 8;
+module_param(verify_n_cpus, int, 0644);
+
+enum wd_read_status {
+	WD_READ_SUCCESS,
+	WD_READ_UNSTABLE,
+	WD_READ_SKIP
+};
+
+static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow)
+{
+	int64_t md = 2 * watchdog->uncertainty_margin;
+	unsigned int nretries, max_retries;
+	int64_t wd_delay, wd_seq_delay;
+	u64 wd_end, wd_end2;
+
+	max_retries = clocksource_get_max_watchdog_retry();
+	for (nretries = 0; nretries <= max_retries; nretries++) {
+		local_irq_disable();
+		*wdnow = watchdog->read(watchdog);
+		*csnow = cs->read(cs);
+		wd_end = watchdog->read(watchdog);
+		wd_end2 = watchdog->read(watchdog);
+		local_irq_enable();
+
+		wd_delay = cycles_to_nsec_safe(watchdog, *wdnow, wd_end);
+		if (wd_delay <= md + cs->uncertainty_margin) {
+			if (nretries > 1 && nretries >= max_retries) {
+				pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n",
+					smp_processor_id(), watchdog->name, nretries);
+			}
+			return WD_READ_SUCCESS;
+		}
+
+		/*
+		 * Now compute delay in consecutive watchdog read to see if
+		 * there is too much external interferences that cause
+		 * significant delay in reading both clocksource and watchdog.
+		 *
+		 * If consecutive WD read-back delay > md, report
+		 * system busy, reinit the watchdog and skip the current
+		 * watchdog test.
+		 */
+		wd_seq_delay = cycles_to_nsec_safe(watchdog, wd_end, wd_end2);
+		if (wd_seq_delay > md)
+			goto skip_test;
+	}
+
+	pr_warn("timekeeping watchdog on CPU%d: wd-%s-wd excessive read-back delay of %lldns vs. limit of %ldns, wd-wd read-back delay only %lldns, attempt %d, marking %s unstable\n",
+		smp_processor_id(), cs->name, wd_delay, WATCHDOG_MAX_SKEW, wd_seq_delay, nretries, cs->name);
+	return WD_READ_UNSTABLE;
+
+skip_test:
+	pr_info("timekeeping watchdog on CPU%d: %s wd-wd read-back delay of %lldns\n",
+		smp_processor_id(), watchdog->name, wd_seq_delay);
+	pr_info("wd-%s-wd read-back delay of %lldns, clock-skew test skipped!\n",
+		cs->name, wd_delay);
+	return WD_READ_SKIP;
+}
+
+static u64 csnow_mid;
+static cpumask_t cpus_ahead;
+static cpumask_t cpus_behind;
+static cpumask_t cpus_chosen;
+
+static void clocksource_verify_choose_cpus(void)
+{
+	int cpu, i, n = verify_n_cpus;
+
+	if (n < 0) {
+		/* Check all of the CPUs. */
+		cpumask_copy(&cpus_chosen, cpu_online_mask);
+		cpumask_clear_cpu(smp_processor_id(), &cpus_chosen);
+		return;
+	}
+
+	/* If no checking desired, or no other CPU to check, leave. */
+	cpumask_clear(&cpus_chosen);
+	if (n == 0 || num_online_cpus() <= 1)
+		return;
+
+	/* Make sure to select at least one CPU other than the current CPU. */
+	cpu = cpumask_first(cpu_online_mask);
+	if (cpu == smp_processor_id())
+		cpu = cpumask_next(cpu, cpu_online_mask);
+	if (WARN_ON_ONCE(cpu >= nr_cpu_ids))
+		return;
+	cpumask_set_cpu(cpu, &cpus_chosen);
+
+	/* Force a sane value for the boot parameter. */
+	if (n > nr_cpu_ids)
+		n = nr_cpu_ids;
+
+	/*
+	 * Randomly select the specified number of CPUs.  If the same
+	 * CPU is selected multiple times, that CPU is checked only once,
+	 * and no replacement CPU is selected.  This gracefully handles
+	 * situations where verify_n_cpus is greater than the number of
+	 * CPUs that are currently online.
+	 */
+	for (i = 1; i < n; i++) {
+		cpu = get_random_u32_below(nr_cpu_ids);
+		cpu = cpumask_next(cpu - 1, cpu_online_mask);
+		if (cpu >= nr_cpu_ids)
+			cpu = cpumask_first(cpu_online_mask);
+		if (!WARN_ON_ONCE(cpu >= nr_cpu_ids))
+			cpumask_set_cpu(cpu, &cpus_chosen);
+	}
+
+	/* Don't verify ourselves. */
+	cpumask_clear_cpu(smp_processor_id(), &cpus_chosen);
+}
+
+static void clocksource_verify_one_cpu(void *csin)
+{
+	struct clocksource *cs = (struct clocksource *)csin;
+
+	csnow_mid = cs->read(cs);
+}
+
+void clocksource_verify_percpu(struct clocksource *cs)
+{
+	int64_t cs_nsec, cs_nsec_max = 0, cs_nsec_min = LLONG_MAX;
+	u64 csnow_begin, csnow_end;
+	int cpu, testcpu;
+	s64 delta;
+
+	if (verify_n_cpus == 0)
+		return;
+	cpumask_clear(&cpus_ahead);
+	cpumask_clear(&cpus_behind);
+	cpus_read_lock();
+	migrate_disable();
+	clocksource_verify_choose_cpus();
+	if (cpumask_empty(&cpus_chosen)) {
+		migrate_enable();
+		cpus_read_unlock();
+		pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name);
+		return;
+	}
+	testcpu = smp_processor_id();
+	pr_info("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n",
+		cs->name, testcpu, cpumask_pr_args(&cpus_chosen));
+	preempt_disable();
+	for_each_cpu(cpu, &cpus_chosen) {
+		if (cpu == testcpu)
+			continue;
+		csnow_begin = cs->read(cs);
+		smp_call_function_single(cpu, clocksource_verify_one_cpu, cs, 1);
+		csnow_end = cs->read(cs);
+		delta = (s64)((csnow_mid - csnow_begin) & cs->mask);
+		if (delta < 0)
+			cpumask_set_cpu(cpu, &cpus_behind);
+		delta = (csnow_end - csnow_mid) & cs->mask;
+		if (delta < 0)
+			cpumask_set_cpu(cpu, &cpus_ahead);
+		cs_nsec = cycles_to_nsec_safe(cs, csnow_begin, csnow_end);
+		if (cs_nsec > cs_nsec_max)
+			cs_nsec_max = cs_nsec;
+		if (cs_nsec < cs_nsec_min)
+			cs_nsec_min = cs_nsec;
+	}
+	preempt_enable();
+	migrate_enable();
+	cpus_read_unlock();
+	if (!cpumask_empty(&cpus_ahead))
+		pr_warn("        CPUs %*pbl ahead of CPU %d for clocksource %s.\n",
+			cpumask_pr_args(&cpus_ahead), testcpu, cs->name);
+	if (!cpumask_empty(&cpus_behind))
+		pr_warn("        CPUs %*pbl behind CPU %d for clocksource %s.\n",
+			cpumask_pr_args(&cpus_behind), testcpu, cs->name);
+	if (!cpumask_empty(&cpus_ahead) || !cpumask_empty(&cpus_behind))
+		pr_warn("        CPU %d check durations %lldns - %lldns for clocksource %s.\n",
+			testcpu, cs_nsec_min, cs_nsec_max, cs->name);
+}
+EXPORT_SYMBOL_GPL(clocksource_verify_percpu);
+
+static inline void clocksource_reset_watchdog(void)
 {
 	struct clocksource *cs;
-	u64 csnow, wdnow, cslast, wdlast, delta;
-	int64_t wd_nsec, cs_nsec;
+
+	list_for_each_entry(cs, &watchdog_list, wd_list)
+		cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
+}
+
+
+static void clocksource_watchdog(struct timer_list *unused)
+{
+	int64_t wd_nsec, cs_nsec, interval;
+	u64 csnow, wdnow, cslast, wdlast;
 	int next_cpu, reset_pending;
+	struct clocksource *cs;
+	enum wd_read_status read_ret;
+	unsigned long extra_wait = 0;
+	u32 md;
 
 	spin_lock(&watchdog_lock);
 	if (!watchdog_running)
@@ -206,10 +452,31 @@ static void clocksource_watchdog(struct timer_list *unused)
 			continue;
 		}
 
-		local_irq_disable();
-		csnow = cs->read(cs);
-		wdnow = watchdog->read(watchdog);
-		local_irq_enable();
+		read_ret = cs_watchdog_read(cs, &csnow, &wdnow);
+
+		if (read_ret == WD_READ_UNSTABLE) {
+			/* Clock readout unreliable, so give it up. */
+			__clocksource_unstable(cs);
+			continue;
+		}
+
+		/*
+		 * When WD_READ_SKIP is returned, it means the system is likely
+		 * under very heavy load, where the latency of reading
+		 * watchdog/clocksource is very big, and affect the accuracy of
+		 * watchdog check. So give system some space and suspend the
+		 * watchdog check for 5 minutes.
+		 */
+		if (read_ret == WD_READ_SKIP) {
+			/*
+			 * As the watchdog timer will be suspended, and
+			 * cs->last could keep unchanged for 5 minutes, reset
+			 * the counters.
+			 */
+			clocksource_reset_watchdog();
+			extra_wait = HZ * 300;
+			break;
+		}
 
 		/* Clocksource initialized ? */
 		if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) ||
@@ -220,12 +487,8 @@ static void clocksource_watchdog(struct timer_list *unused)
 			continue;
 		}
 
-		delta = clocksource_delta(wdnow, cs->wd_last, watchdog->mask);
-		wd_nsec = clocksource_cyc2ns(delta, watchdog->mult,
-					     watchdog->shift);
-
-		delta = clocksource_delta(csnow, cs->cs_last, cs->mask);
-		cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift);
+		wd_nsec = cycles_to_nsec_safe(watchdog, cs->wd_last, wdnow);
+		cs_nsec = cycles_to_nsec_safe(cs, cs->cs_last, csnow);
 		wdlast = cs->wd_last; /* save these in case we print them */
 		cslast = cs->cs_last;
 		cs->cs_last = csnow;
@@ -234,14 +497,50 @@ static void clocksource_watchdog(struct timer_list *unused)
 		if (atomic_read(&watchdog_reset_pending))
 			continue;
 
+		/*
+		 * The processing of timer softirqs can get delayed (usually
+		 * on account of ksoftirqd not getting to run in a timely
+		 * manner), which causes the watchdog interval to stretch.
+		 * Skew detection may fail for longer watchdog intervals
+		 * on account of fixed margins being used.
+		 * Some clocksources, e.g. acpi_pm, cannot tolerate
+		 * watchdog intervals longer than a few seconds.
+		 */
+		interval = max(cs_nsec, wd_nsec);
+		if (unlikely(interval > WATCHDOG_INTERVAL_MAX_NS)) {
+			if (system_state > SYSTEM_SCHEDULING &&
+			    interval > 2 * watchdog_max_interval) {
+				watchdog_max_interval = interval;
+				pr_warn("Long readout interval, skipping watchdog check: cs_nsec: %lld wd_nsec: %lld\n",
+					cs_nsec, wd_nsec);
+			}
+			watchdog_timer.expires = jiffies;
+			continue;
+		}
+
 		/* Check the deviation from the watchdog clocksource. */
-		if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
+		md = cs->uncertainty_margin + watchdog->uncertainty_margin;
+		if (abs(cs_nsec - wd_nsec) > md) {
+			s64 cs_wd_msec;
+			s64 wd_msec;
+			u32 wd_rem;
+
 			pr_warn("timekeeping watchdog on CPU%d: Marking clocksource '%s' as unstable because the skew is too large:\n",
 				smp_processor_id(), cs->name);
-			pr_warn("                      '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
-				watchdog->name, wdnow, wdlast, watchdog->mask);
-			pr_warn("                      '%s' cs_now: %llx cs_last: %llx mask: %llx\n",
-				cs->name, csnow, cslast, cs->mask);
+			pr_warn("                      '%s' wd_nsec: %lld wd_now: %llx wd_last: %llx mask: %llx\n",
+				watchdog->name, wd_nsec, wdnow, wdlast, watchdog->mask);
+			pr_warn("                      '%s' cs_nsec: %lld cs_now: %llx cs_last: %llx mask: %llx\n",
+				cs->name, cs_nsec, csnow, cslast, cs->mask);
+			cs_wd_msec = div_s64_rem(cs_nsec - wd_nsec, 1000 * 1000, &wd_rem);
+			wd_msec = div_s64_rem(wd_nsec, 1000 * 1000, &wd_rem);
+			pr_warn("                      Clocksource '%s' skewed %lld ns (%lld ms) over watchdog '%s' interval of %lld ns (%lld ms)\n",
+				cs->name, cs_nsec - wd_nsec, cs_wd_msec, watchdog->name, wd_nsec, wd_msec);
+			if (curr_clocksource == cs)
+				pr_warn("                      '%s' is current clocksource.\n", cs->name);
+			else if (curr_clocksource)
+				pr_warn("                      '%s' (not '%s') is current clocksource.\n", curr_clocksource->name, cs->name);
+			else
+				pr_warn("                      No current clocksource.\n");
 			__clocksource_unstable(cs);
 			continue;
 		}
@@ -299,7 +598,7 @@ static void clocksource_watchdog(struct timer_list *unused)
 	 * pair clocksource_stop_watchdog() clocksource_start_watchdog().
 	 */
 	if (!timer_pending(&watchdog_timer)) {
-		watchdog_timer.expires += WATCHDOG_INTERVAL;
+		watchdog_timer.expires += WATCHDOG_INTERVAL + extra_wait;
 		add_timer_on(&watchdog_timer, next_cpu);
 	}
 out:
@@ -324,14 +623,6 @@ static inline void clocksource_stop_watchdog(void)
 	watchdog_running = 0;
 }
 
-static inline void clocksource_reset_watchdog(void)
-{
-	struct clocksource *cs;
-
-	list_for_each_entry(cs, &watchdog_list, wd_list)
-		cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
-}
-
 static void clocksource_resume_watchdog(void)
 {
 	atomic_inc(&watchdog_reset_pending);
@@ -407,11 +698,17 @@ static int __clocksource_watchdog_kthread(void)
 	unsigned long flags;
 	int select = 0;
 
+	/* Do any required per-CPU skew verification. */
+	if (curr_clocksource &&
+	    curr_clocksource->flags & CLOCK_SOURCE_UNSTABLE &&
+	    curr_clocksource->flags & CLOCK_SOURCE_VERIFY_PERCPU)
+		clocksource_verify_percpu(curr_clocksource);
+
 	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);
-			__clocksource_change_rating(cs, 0);
+			clocksource_change_rating(cs, 0);
 			select = 1;
 		}
 		if (cs->flags & CLOCK_SOURCE_RESELECT) {
@@ -518,7 +815,7 @@ static void clocksource_suspend_select(bool fallback)
  * the suspend time when resuming system.
  *
  * This function is called late in the suspend process from timekeeping_suspend(),
- * that means processes are freezed, non-boot cpus and interrupts are disabled
+ * that means processes are frozen, non-boot cpus and interrupts are disabled
  * now. It is therefore possible to start the suspend timer without taking the
  * clocksource mutex.
  */
@@ -562,7 +859,7 @@ void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles)
  */
 u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now)
 {
-	u64 now, delta, nsec = 0;
+	u64 now, nsec = 0;
 
 	if (!suspend_clocksource)
 		return 0;
@@ -577,12 +874,8 @@ u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now)
 	else
 		now = suspend_clocksource->read(suspend_clocksource);
 
-	if (now > suspend_start) {
-		delta = clocksource_delta(now, suspend_start,
-					  suspend_clocksource->mask);
-		nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult,
-				       suspend_clocksource->shift);
-	}
+	if (now > suspend_start)
+		nsec = cycles_to_nsec_safe(suspend_clocksource, suspend_start, now);
 
 	/*
 	 * Disable the suspend timer to save power if current clocksource is
@@ -703,6 +996,15 @@ static inline void clocksource_update_max_deferment(struct clocksource *cs)
 	cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift,
 						cs->maxadj, cs->mask,
 						&cs->max_cycles);
+
+	/*
+	 * Threshold for detecting negative motion in clocksource_delta().
+	 *
+	 * Allow for 0.875 of the counter width so that overly long idle
+	 * sleeps, which go slightly over mask/2, do not trigger the
+	 * negative motion detection.
+	 */
+	cs->max_raw_delta = (cs->mask >> 1) + (cs->mask >> 2) + (cs->mask >> 3);
 }
 
 static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur)
@@ -876,6 +1178,31 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq
 		clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
 				       NSEC_PER_SEC / scale, sec * scale);
 	}
+
+	/*
+	 * If the uncertainty margin is not specified, calculate it.  If
+	 * both scale and freq are non-zero, calculate the clock period, but
+	 * bound below at 2*WATCHDOG_MAX_SKEW, that is, 500ppm by default.
+	 * However, if either of scale or freq is zero, be very conservative
+	 * and take the tens-of-milliseconds WATCHDOG_THRESHOLD value
+	 * for the uncertainty margin.  Allow stupidly small uncertainty
+	 * margins to be specified by the caller for testing purposes,
+	 * but warn to discourage production use of this capability.
+	 *
+	 * Bottom line:  The sum of the uncertainty margins of the
+	 * watchdog clocksource and the clocksource under test will be at
+	 * least 500ppm by default.  For more information, please see the
+	 * comment preceding CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US above.
+	 */
+	if (scale && freq && !cs->uncertainty_margin) {
+		cs->uncertainty_margin = NSEC_PER_SEC / (scale * freq);
+		if (cs->uncertainty_margin < 2 * WATCHDOG_MAX_SKEW)
+			cs->uncertainty_margin = 2 * WATCHDOG_MAX_SKEW;
+	} else if (!cs->uncertainty_margin) {
+		cs->uncertainty_margin = WATCHDOG_THRESHOLD;
+	}
+	WARN_ON_ONCE(cs->uncertainty_margin < 2 * WATCHDOG_MAX_SKEW);
+
 	/*
 	 * Ensure clocksources that have large 'mult' values don't overflow
 	 * when adjusted.
@@ -920,6 +1247,8 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 
 	clocksource_arch_init(cs);
 
+	if (WARN_ON_ONCE((unsigned int)cs->id >= CSID_MAX))
+		cs->id = CSID_GENERIC;
 	if (cs->vdso_clock_mode < 0 ||
 	    cs->vdso_clock_mode >= VDSO_CLOCKMODE_MAX) {
 		pr_warn("clocksource %s registered with invalid VDSO mode %d. Disabling VDSO support.\n",
@@ -946,34 +1275,6 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 }
 EXPORT_SYMBOL_GPL(__clocksource_register_scale);
 
-static void __clocksource_change_rating(struct clocksource *cs, int rating)
-{
-	list_del(&cs->list);
-	cs->rating = rating;
-	clocksource_enqueue(cs);
-}
-
-/**
- * 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)
-{
-	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);
-	clocksource_suspend_select(false);
-	mutex_unlock(&clocksource_mutex);
-}
-EXPORT_SYMBOL(clocksource_change_rating);
-
 /*
  * Unbind clocksource @cs. Called with clocksource_mutex held
  */
@@ -1044,7 +1345,7 @@ static ssize_t current_clocksource_show(struct device *dev,
 	ssize_t count = 0;
 
 	mutex_lock(&clocksource_mutex);
-	count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name);
+	count = sysfs_emit(buf, "%s\n", curr_clocksource->name);
 	mutex_unlock(&clocksource_mutex);
 
 	return count;
@@ -1174,7 +1475,7 @@ static struct attribute *clocksource_attrs[] = {
 };
 ATTRIBUTE_GROUPS(clocksource);
 
-static struct bus_type clocksource_subsys = {
+static const struct bus_type clocksource_subsys = {
 	.name = "clocksource",
 	.dev_name = "clocksource",
 };
@@ -1209,7 +1510,7 @@ static int __init boot_override_clocksource(char* str)
 {
 	mutex_lock(&clocksource_mutex);
 	if (str)
-		strlcpy(override_name, str, sizeof(override_name));
+		strscpy(override_name, str, sizeof(override_name));
 	mutex_unlock(&clocksource_mutex);
 	return 1;
 }