Merge tag 'timers_urgent_for_v6.8_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer fixes from Borislav Petkov:

 - Preserve the number of idle calls and sleep entries across CPU
   hotplug events in order to be able to compute correct averages

 - Limit the duration of the clocksource watchdog checking interval as
   too long intervals lead to wrongly marking the TSC as unstable

* tag 'timers_urgent_for_v6.8_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  tick/sched: Preserve number of idle sleeps across CPU hotplug events
  clocksource: Skip watchdog check for large watchdog intervals

Author: torvalds

kernel/time/clocksource.c

@@ -99,6 +99,7 @@ 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.
@@ -134,6 +135,7 @@ 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)
 {
@@ -399,8 +401,8 @@ 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;
 	int next_cpu, reset_pending;
-	int64_t wd_nsec, cs_nsec;
 	struct clocksource *cs;
 	enum wd_read_status read_ret;
 	unsigned long extra_wait = 0;
@@ -470,6 +472,27 @@ 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. */
 		md = cs->uncertainty_margin + watchdog->uncertainty_margin;
 		if (abs(cs_nsec - wd_nsec) > md) {

kernel/time/tick-sched.c

@@ -1577,6 +1577,7 @@ void tick_cancel_sched_timer(int cpu)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	ktime_t idle_sleeptime, iowait_sleeptime;
+	unsigned long idle_calls, idle_sleeps;
 
 # ifdef CONFIG_HIGH_RES_TIMERS
 	if (ts->sched_timer.base)
@@ -1585,9 +1586,13 @@ void tick_cancel_sched_timer(int cpu)
 
 	idle_sleeptime = ts->idle_sleeptime;
 	iowait_sleeptime = ts->iowait_sleeptime;
+	idle_calls = ts->idle_calls;
+	idle_sleeps = ts->idle_sleeps;
 	memset(ts, 0, sizeof(*ts));
 	ts->idle_sleeptime = idle_sleeptime;
 	ts->iowait_sleeptime = iowait_sleeptime;
+	ts->idle_calls = idle_calls;
+	ts->idle_sleeps = idle_sleeps;
 }
 #endif