1 files changed, 82 insertions, 73 deletions

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index e5b260aa0e02..6a8bc7da9062 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -20,6 +20,18 @@
 #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
@@ -103,7 +115,6 @@ static u64 suspend_start;
 
 /*
  * Threshold: 0.0312s, when doubled: 0.0625s.
- * Also a default for cs->uncertainty_margin when registering clocks.
  */
 #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 5)
 
@@ -115,6 +126,13 @@ static u64 suspend_start;
  *
  * 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
@@ -122,6 +140,13 @@ static u64 suspend_start;
 #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
@@ -148,7 +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);
 
 static void clocksource_watchdog_work(struct work_struct *work)
 {
@@ -168,6 +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);
@@ -221,9 +252,10 @@ enum wd_read_status {
 
 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;
-	u64 wd_end, wd_end2, wd_delta;
 	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++) {
@@ -234,11 +266,9 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow,
 		wd_end2 = watchdog->read(watchdog);
 		local_irq_enable();
 
-		wd_delta = clocksource_delta(wd_end, *wdnow, watchdog->mask);
-		wd_delay = clocksource_cyc2ns(wd_delta, watchdog->mult,
-					      watchdog->shift);
-		if (wd_delay <= WATCHDOG_MAX_SKEW) {
-			if (nretries > 1 || nretries >= max_retries) {
+		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);
 			}
@@ -250,13 +280,12 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow,
 		 * there is too much external interferences that cause
 		 * significant delay in reading both clocksource and watchdog.
 		 *
-		 * If consecutive WD read-back delay > WATCHDOG_MAX_SKEW/2,
-		 * report system busy, reinit the watchdog and skip the current
+		 * If consecutive WD read-back delay > md, report
+		 * system busy, reinit the watchdog and skip the current
 		 * watchdog test.
 		 */
-		wd_delta = clocksource_delta(wd_end2, wd_end, watchdog->mask);
-		wd_seq_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, watchdog->shift);
-		if (wd_seq_delay > WATCHDOG_MAX_SKEW/2)
+		wd_seq_delay = cycles_to_nsec_safe(watchdog, wd_end, wd_end2);
+		if (wd_seq_delay > md)
 			goto skip_test;
 	}
 
@@ -281,7 +310,7 @@ static void clocksource_verify_choose_cpus(void)
 {
 	int cpu, i, n = verify_n_cpus;
 
-	if (n < 0) {
+	if (n < 0 || n >= num_online_cpus()) {
 		/* Check all of the CPUs. */
 		cpumask_copy(&cpus_chosen, cpu_online_mask);
 		cpumask_clear_cpu(smp_processor_id(), &cpus_chosen);
@@ -344,16 +373,18 @@ void clocksource_verify_percpu(struct clocksource *cs)
 	cpumask_clear(&cpus_ahead);
 	cpumask_clear(&cpus_behind);
 	cpus_read_lock();
-	preempt_disable();
+	migrate_disable();
 	clocksource_verify_choose_cpus();
 	if (cpumask_empty(&cpus_chosen)) {
-		preempt_enable();
+		migrate_enable();
 		cpus_read_unlock();
 		pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name);
 		return;
 	}
 	testcpu = smp_processor_id();
-	pr_warn("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n", cs->name, testcpu, cpumask_pr_args(&cpus_chosen));
+	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;
@@ -366,14 +397,14 @@ void clocksource_verify_percpu(struct clocksource *cs)
 		delta = (csnow_end - csnow_mid) & cs->mask;
 		if (delta < 0)
 			cpumask_set_cpu(cpu, &cpus_ahead);
-		delta = clocksource_delta(csnow_end, csnow_begin, cs->mask);
-		cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift);
+		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",
@@ -398,8 +429,8 @@ static inline void clocksource_reset_watchdog(void)
 
 static void clocksource_watchdog(struct timer_list *unused)
 {
-	u64 csnow, wdnow, cslast, wdlast, delta;
 	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;
@@ -456,12 +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;
@@ -592,7 +619,7 @@ static inline void clocksource_stop_watchdog(void)
 {
 	if (!watchdog_running || (watchdog && !list_empty(&watchdog_list)))
 		return;
-	del_timer(&watchdog_timer);
+	timer_delete(&watchdog_timer);
 	watchdog_running = 0;
 }
 
@@ -681,7 +708,7 @@ static int __clocksource_watchdog_kthread(void)
 	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) {
@@ -832,7 +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;
@@ -847,12 +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
@@ -973,6 +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)
@@ -1148,14 +1180,19 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq
 	}
 
 	/*
-	 * 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.  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.
+	 * 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);
@@ -1238,34 +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
  */
@@ -1336,7 +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;
@@ -1501,7 +1510,7 @@ static int __init boot_override_clocksource(char* str)
 {
 	mutex_lock(&clocksource_mutex);
 	if (str)
-		strscpy(override_name, str, sizeof(override_name));
+		strscpy(override_name, str);
 	mutex_unlock(&clocksource_mutex);
 	return 1;
 }