Merge tag 'timers-core-2022-03-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer and timekeeping updates from Thomas Gleixner:
 "Core code:

   - Make the NOHZ handling of the timekeeping/tick core more robust to
     prevent a rare jiffies update stall.

   - Handle softirqs in the NOHZ/idle case correctly

  Drivers:

   - Add support for event stream scaling of the 1GHz counter on ARM(64)

   - Correct an error code check in the timer-of layer

   - The usual cleanups and improvements all over the place"

* tag 'timers-core-2022-03-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  lib/irq_poll: Declare IRQ_POLL softirq vector as ksoftirqd-parking safe
  tick/rcu: Stop allowing RCU_SOFTIRQ in idle
  tick/rcu: Remove obsolete rcu_needs_cpu() parameters
  tick: Detect and fix jiffies update stall
  clocksource/drivers/timer-of: Check return value of of_iomap in timer_of_base_init()
  clocksource/drivers/timer-microchip-pit64b: Use 5MHz for clockevent
  clocksource/drivers/timer-microchip-pit64b: Use notrace
  clocksource/drivers/timer-microchip-pit64b: Remove mmio selection
  dt-bindings: timer: Tegra: Convert text bindings to yaml
  clocksource/drivers/imx-tpm: Move tpm_read_sched_clock() under CONFIG_ARM
  clocksource/drivers/arm_arch_timer: Use event stream scaling when available
  clocksource/drivers/exynos_mct: Increase the size of name array
  clocksource/drivers/exynos_mct: Bump up mct max irq number
  clocksource/drivers/exynos_mct: Remove mct interrupt index enum
  clocksource/drivers/exynos_mct: Handle DTS with higher number of interrupts
  clocksource/drivers/timer-ti-dm: Fix regression from errata i940 fix
  clocksource/drivers/imx-tpm: Exclude sched clock for ARM64
  clocksource: Add a Kconfig option for WATCHDOG_MAX_SKEW
  clocksource/drivers/imx-tpm: Update name of clkevt
  clocksource/drivers/imx-tpm: Add CLOCK_EVT_FEAT_DYNIRQ
  ...

5 files changed, 82 insertions, 19 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a4c25a6283b0..80faf2273ce9 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1086,9 +1086,8 @@ void rcu_irq_enter_irqson(void)
  * Just check whether or not this CPU has non-offloaded RCU callbacks
  * queued.
  */
-int rcu_needs_cpu(u64 basemono, u64 *nextevt)
+int rcu_needs_cpu(void)
 {
-	*nextevt = KTIME_MAX;
 	return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) &&
 		!rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data));
 }
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 04bfd62f5e5c..27b7868b5c30 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -181,5 +181,14 @@ config HIGH_RES_TIMERS
 	  hardware is not capable then this option only increases
 	  the size of the kernel image.
 
+config CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
+	int "Clocksource watchdog maximum allowable skew (in μs)"
+	depends on CLOCKSOURCE_WATCHDOG
+	range 50 1000
+	default 100
+	help
+	  Specify the maximum amount of allowable watchdog skew in
+	  microseconds before reporting the clocksource to be unstable.
+
 endmenu
 endif
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 1cf73807b450..95d7ca35bdf2 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -107,7 +107,13 @@ static u64 suspend_start;
  * 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.
  */
-#define WATCHDOG_MAX_SKEW (100 * NSEC_PER_USEC)
+#ifdef CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
+#define MAX_SKEW_USEC	CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
+#else
+#define MAX_SKEW_USEC	100
+#endif
+
+#define WATCHDOG_MAX_SKEW (MAX_SKEW_USEC * NSEC_PER_USEC)
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 static void clocksource_watchdog_work(struct work_struct *work);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 17a283ce2b20..2d76c91b85de 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -169,6 +169,8 @@ static ktime_t tick_init_jiffy_update(void)
 	return period;
 }
 
+#define MAX_STALLED_JIFFIES 5
+
 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 {
 	int cpu = smp_processor_id();
@@ -196,6 +198,21 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 	if (tick_do_timer_cpu == cpu)
 		tick_do_update_jiffies64(now);
 
+	/*
+	 * If jiffies update stalled for too long (timekeeper in stop_machine()
+	 * or VMEXIT'ed for several msecs), force an update.
+	 */
+	if (ts->last_tick_jiffies != jiffies) {
+		ts->stalled_jiffies = 0;
+		ts->last_tick_jiffies = READ_ONCE(jiffies);
+	} else {
+		if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) {
+			tick_do_update_jiffies64(now);
+			ts->stalled_jiffies = 0;
+			ts->last_tick_jiffies = READ_ONCE(jiffies);
+		}
+	}
+
 	if (ts->inidle)
 		ts->got_idle_tick = 1;
 }
@@ -768,7 +785,7 @@ static inline bool local_timer_softirq_pending(void)
 
 static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 {
-	u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
+	u64 basemono, next_tick, delta, expires;
 	unsigned long basejiff;
 	unsigned int seq;
 
@@ -791,7 +808,7 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 	 * minimal delta which brings us back to this place
 	 * immediately. Lather, rinse and repeat...
 	 */
-	if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() ||
+	if (rcu_needs_cpu() || arch_needs_cpu() ||
 	    irq_work_needs_cpu() || local_timer_softirq_pending()) {
 		next_tick = basemono + TICK_NSEC;
 	} else {
@@ -802,10 +819,8 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 		 * disabled this also looks at the next expiring
 		 * hrtimer.
 		 */
-		next_tmr = get_next_timer_interrupt(basejiff, basemono);
-		ts->next_timer = next_tmr;
-		/* Take the next rcu event into account */
-		next_tick = next_rcu < next_tmr ? next_rcu : next_tmr;
+		next_tick = get_next_timer_interrupt(basejiff, basemono);
+		ts->next_timer = next_tick;
 	}
 
 	/*
@@ -984,6 +999,45 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts)
 	__tick_nohz_full_update_tick(ts, ktime_get());
 }
 
+/*
+ * A pending softirq outside an IRQ (or softirq disabled section) context
+ * should be waiting for ksoftirqd to handle it. Therefore we shouldn't
+ * reach here due to the need_resched() early check in can_stop_idle_tick().
+ *
+ * However if we are between CPUHP_AP_SMPBOOT_THREADS and CPU_TEARDOWN_CPU on the
+ * cpu_down() process, softirqs can still be raised while ksoftirqd is parked,
+ * triggering the below since wakep_softirqd() is ignored.
+ *
+ */
+static bool report_idle_softirq(void)
+{
+	static int ratelimit;
+	unsigned int pending = local_softirq_pending();
+
+	if (likely(!pending))
+		return false;
+
+	/* Some softirqs claim to be safe against hotplug and ksoftirqd parking */
+	if (!cpu_active(smp_processor_id())) {
+		pending &= ~SOFTIRQ_HOTPLUG_SAFE_MASK;
+		if (!pending)
+			return false;
+	}
+
+	if (ratelimit < 10)
+		return false;
+
+	/* On RT, softirqs handling may be waiting on some lock */
+	if (!local_bh_blocked())
+		return false;
+
+	pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n",
+		pending);
+	ratelimit++;
+
+	return true;
+}
+
 static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 {
 	/*
@@ -1010,17 +1064,8 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 	if (need_resched())
 		return false;
 
-	if (unlikely(local_softirq_pending())) {
-		static int ratelimit;
-
-		if (ratelimit < 10 && !local_bh_blocked() &&
-		    (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
-			pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n",
-				(unsigned int) local_softirq_pending());
-			ratelimit++;
-		}
+	if (unlikely(report_idle_softirq()))
 		return false;
-	}
 
 	if (tick_nohz_full_enabled()) {
 		/*
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index d952ae393423..504649513399 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -49,6 +49,8 @@ enum tick_nohz_mode {
  * @timer_expires_base:	Base time clock monotonic for @timer_expires
  * @next_timer:		Expiry time of next expiring timer for debugging purpose only
  * @tick_dep_mask:	Tick dependency mask - is set, if someone needs the tick
+ * @last_tick_jiffies:	Value of jiffies seen on last tick
+ * @stalled_jiffies:	Number of stalled jiffies detected across ticks
  */
 struct tick_sched {
 	struct hrtimer			sched_timer;
@@ -77,6 +79,8 @@ struct tick_sched {
 	u64				next_timer;
 	ktime_t				idle_expires;
 	atomic_t			tick_dep_mask;
+	unsigned long			last_tick_jiffies;
+	unsigned int			stalled_jiffies;
 };
 
 extern struct tick_sched *tick_get_tick_sched(int cpu);