Merge tag 'timers-core-2024-07-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "Updates for timers, timekeeping and related functionality:

  Core:

   - Make the takeover of a hrtimer based broadcast timer reliable
     during CPU hot-unplug. The current implementation suffers from a
     race which can lead to broadcast timer starvation in the worst
     case.

   - VDSO related cleanups and simplifications

   - Small cleanups and enhancements all over the place

  PTP:

   - Replace the architecture specific base clock to clocksource, e.g.
     ART to TSC, conversion function with generic functionality to avoid
     exposing such internals to drivers and convert all existing drivers
     over. This also allows to provide functionality which converts the
     other way round in the core code based on the same parameter set.

   - Provide a function to convert CLOCK_REALTIME to the base clock to
     support the upcoming PPS output driver on Intel platforms.

  Drivers:

   - A set of Device Tree bindings for new hardware

   - Cleanups and enhancements all over the place"

* tag 'timers-core-2024-07-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  clocksource/drivers/realtek: Add timer driver for rtl-otto platforms
  dt-bindings: timer: Add schema for realtek,otto-timer
  dt-bindings: timer: Add SOPHGO SG2002 clint
  dt-bindings: timer: renesas,tmu: Add R-Car Gen2 support
  dt-bindings: timer: renesas,tmu: Add RZ/G1 support
  dt-bindings: timer: renesas,tmu: Add R-Mobile APE6 support
  clocksource/drivers/mips-gic-timer: Correct sched_clock width
  clocksource/drivers/mips-gic-timer: Refine rating computation
  clocksource/drivers/sh_cmt: Address race condition for clock events
  clocksource/driver/arm_global_timer: Remove unnecessary ‘0’ values from err
  clocksource/drivers/arm_arch_timer: Remove unnecessary ‘0’ values from irq
  tick/broadcast: Make takeover of broadcast hrtimer reliable
  tick/sched: Combine WARN_ON_ONCE and print_once
  x86/vdso: Remove unused include
  x86/vgtod: Remove unused typedef gtod_long_t
  x86/vdso: Fix function reference in comment
  vdso: Add comment about reason for vdso struct ordering
  vdso/gettimeofday: Clarify comment about open coded function
  timekeeping: Add missing kernel-doc function comments
  tick: Remove unnused tick_nohz_get_idle_calls()
  ...

6 files changed, 160 insertions, 19 deletions

diff --git a/kernel/time/clocksource-wdtest.c b/kernel/time/clocksource-wdtest.c
index d06185e054ea..62e73444ffe4 100644
--- a/kernel/time/clocksource-wdtest.c
+++ b/kernel/time/clocksource-wdtest.c
@@ -22,6 +22,7 @@
 #include "tick-internal.h"
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Clocksource watchdog unit test");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@kernel.org>");
 
 static int holdoff = IS_BUILTIN(CONFIG_TEST_CLOCKSOURCE_WATCHDOG) ? 10 : 0;
diff --git a/kernel/time/test_udelay.c b/kernel/time/test_udelay.c
index 20d5df631570..783f2297111b 100644
--- a/kernel/time/test_udelay.c
+++ b/kernel/time/test_udelay.c
@@ -155,5 +155,6 @@ static void __exit udelay_test_exit(void)
 
 module_exit(udelay_test_exit);
 
+MODULE_DESCRIPTION("udelay test module");
 MODULE_AUTHOR("David Riley <davidriley@chromium.org>");
 MODULE_LICENSE("GPL");
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 771d1e040303..b4843099a8da 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -1141,6 +1141,7 @@ void tick_broadcast_switch_to_oneshot(void)
 #ifdef CONFIG_HOTPLUG_CPU
 void hotplug_cpu__broadcast_tick_pull(int deadcpu)
 {
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	struct clock_event_device *bc;
 	unsigned long flags;
 
@@ -1148,6 +1149,28 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
 	bc = tick_broadcast_device.evtdev;
 
 	if (bc && broadcast_needs_cpu(bc, deadcpu)) {
+		/*
+		 * If the broadcast force bit of the current CPU is set,
+		 * then the current CPU has not yet reprogrammed the local
+		 * timer device to avoid a ping-pong race. See
+		 * ___tick_broadcast_oneshot_control().
+		 *
+		 * If the broadcast device is hrtimer based then
+		 * programming the broadcast event below does not have any
+		 * effect because the local clockevent device is not
+		 * running and not programmed because the broadcast event
+		 * is not earlier than the pending event of the local clock
+		 * event device. As a consequence all CPUs waiting for a
+		 * broadcast event are stuck forever.
+		 *
+		 * Detect this condition and reprogram the cpu local timer
+		 * device to avoid the starvation.
+		 */
+		if (tick_check_broadcast_expired()) {
+			cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask);
+			tick_program_event(td->evtdev->next_event, 1);
+		}
+
 		/* This moves the broadcast assignment to this CPU: */
 		clockevents_program_event(bc, bc->next_event, 1);
 	}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 71a792cd8936..753a184c7090 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1026,10 +1026,10 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 		if (expires == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer))
 			return;
 
-		WARN_ON_ONCE(1);
-		printk_once("basemono: %llu ts->next_tick: %llu dev->next_event: %llu timer->active: %d timer->expires: %llu\n",
-			    basemono, ts->next_tick, dev->next_event,
-			    hrtimer_active(&ts->sched_timer), hrtimer_get_expires(&ts->sched_timer));
+		WARN_ONCE(1, "basemono: %llu ts->next_tick: %llu dev->next_event: %llu "
+			  "timer->active: %d timer->expires: %llu\n", basemono, ts->next_tick,
+			  dev->next_event, hrtimer_active(&ts->sched_timer),
+			  hrtimer_get_expires(&ts->sched_timer));
 	}
 
 	/*
@@ -1385,20 +1385,6 @@ unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
 	return ts->idle_calls;
 }
 
-/**
- * tick_nohz_get_idle_calls - return the current idle calls counter value
- *
- * Called from the schedutil frequency scaling governor in scheduler context.
- *
- * Return: the current idle calls counter value for the current CPU
- */
-unsigned long tick_nohz_get_idle_calls(void)
-{
-	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
-
-	return ts->idle_calls;
-}
-
 static void tick_nohz_account_idle_time(struct tick_sched *ts,
 					ktime_t now)
 {
diff --git a/kernel/time/time_test.c b/kernel/time/time_test.c
index 3e5d422dd15c..2889763165e5 100644
--- a/kernel/time/time_test.c
+++ b/kernel/time/time_test.c
@@ -96,4 +96,5 @@ static struct kunit_suite time_test_suite = {
 };
 
 kunit_test_suite(time_test_suite);
+MODULE_DESCRIPTION("time unit test suite");
 MODULE_LICENSE("GPL");
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4e18db1819f8..2fa87dcfeda9 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1195,6 +1195,108 @@ static bool timestamp_in_interval(u64 start, u64 end, u64 ts)
 	return false;
 }
 
+static bool convert_clock(u64 *val, u32 numerator, u32 denominator)
+{
+	u64 rem, res;
+
+	if (!numerator || !denominator)
+		return false;
+
+	res = div64_u64_rem(*val, denominator, &rem) * numerator;
+	*val = res + div_u64(rem * numerator, denominator);
+	return true;
+}
+
+static bool convert_base_to_cs(struct system_counterval_t *scv)
+{
+	struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock;
+	struct clocksource_base *base;
+	u32 num, den;
+
+	/* The timestamp was taken from the time keeper clock source */
+	if (cs->id == scv->cs_id)
+		return true;
+
+	/*
+	 * Check whether cs_id matches the base clock. Prevent the compiler from
+	 * re-evaluating @base as the clocksource might change concurrently.
+	 */
+	base = READ_ONCE(cs->base);
+	if (!base || base->id != scv->cs_id)
+		return false;
+
+	num = scv->use_nsecs ? cs->freq_khz : base->numerator;
+	den = scv->use_nsecs ? USEC_PER_SEC : base->denominator;
+
+	if (!convert_clock(&scv->cycles, num, den))
+		return false;
+
+	scv->cycles += base->offset;
+	return true;
+}
+
+static bool convert_cs_to_base(u64 *cycles, enum clocksource_ids base_id)
+{
+	struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock;
+	struct clocksource_base *base;
+
+	/*
+	 * Check whether base_id matches the base clock. Prevent the compiler from
+	 * re-evaluating @base as the clocksource might change concurrently.
+	 */
+	base = READ_ONCE(cs->base);
+	if (!base || base->id != base_id)
+		return false;
+
+	*cycles -= base->offset;
+	if (!convert_clock(cycles, base->denominator, base->numerator))
+		return false;
+	return true;
+}
+
+static bool convert_ns_to_cs(u64 *delta)
+{
+	struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono;
+
+	if (BITS_TO_BYTES(fls64(*delta) + tkr->shift) >= sizeof(*delta))
+		return false;
+
+	*delta = div_u64((*delta << tkr->shift) - tkr->xtime_nsec, tkr->mult);
+	return true;
+}
+
+/**
+ * ktime_real_to_base_clock() - Convert CLOCK_REALTIME timestamp to a base clock timestamp
+ * @treal:	CLOCK_REALTIME timestamp to convert
+ * @base_id:	base clocksource id
+ * @cycles:	pointer to store the converted base clock timestamp
+ *
+ * Converts a supplied, future realtime clock value to the corresponding base clock value.
+ *
+ * Return:  true if the conversion is successful, false otherwise.
+ */
+bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+	unsigned int seq;
+	u64 delta;
+
+	do {
+		seq = read_seqcount_begin(&tk_core.seq);
+		if ((u64)treal < tk->tkr_mono.base_real)
+			return false;
+		delta = (u64)treal - tk->tkr_mono.base_real;
+		if (!convert_ns_to_cs(&delta))
+			return false;
+		*cycles = tk->tkr_mono.cycle_last + delta;
+		if (!convert_cs_to_base(cycles, base_id))
+			return false;
+	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(ktime_real_to_base_clock);
+
 /**
  * get_device_system_crosststamp - Synchronously capture system/device timestamp
  * @get_time_fn:	Callback to get simultaneous device time and
@@ -1241,7 +1343,7 @@ int get_device_system_crosststamp(int (*get_time_fn)
 		 * installed timekeeper clocksource
 		 */
 		if (system_counterval.cs_id == CSID_GENERIC ||
-		    tk->tkr_mono.clock->id != system_counterval.cs_id)
+		    !convert_base_to_cs(&system_counterval))
 			return -ENODEV;
 		cycles = system_counterval.cycles;
 
@@ -1307,6 +1409,30 @@ int get_device_system_crosststamp(int (*get_time_fn)
 EXPORT_SYMBOL_GPL(get_device_system_crosststamp);
 
 /**
+ * timekeeping_clocksource_has_base - Check whether the current clocksource
+ *				      is based on given a base clock
+ * @id:		base clocksource ID
+ *
+ * Note:	The return value is a snapshot which can become invalid right
+ *		after the function returns.
+ *
+ * Return:	true if the timekeeper clocksource has a base clock with @id,
+ *		false otherwise
+ */
+bool timekeeping_clocksource_has_base(enum clocksource_ids id)
+{
+	/*
+	 * This is a snapshot, so no point in using the sequence
+	 * count. Just prevent the compiler from re-evaluating @base as the
+	 * clocksource might change concurrently.
+	 */
+	struct clocksource_base *base = READ_ONCE(tk_core.timekeeper.tkr_mono.clock->base);
+
+	return base ? base->id == id : false;
+}
+EXPORT_SYMBOL_GPL(timekeeping_clocksource_has_base);
+
+/**
  * do_settimeofday64 - Sets the time of day.
  * @ts:     pointer to the timespec64 variable containing the new time
  *
@@ -2421,6 +2547,7 @@ EXPORT_SYMBOL_GPL(random_get_entropy_fallback);
 
 /**
  * do_adjtimex() - Accessor function to NTP __do_adjtimex function
+ * @txc:	Pointer to kernel_timex structure containing NTP parameters
  */
 int do_adjtimex(struct __kernel_timex *txc)
 {
@@ -2489,6 +2616,8 @@ int do_adjtimex(struct __kernel_timex *txc)
 #ifdef CONFIG_NTP_PPS
 /**
  * hardpps() - Accessor function to NTP __hardpps function
+ * @phase_ts:	Pointer to timespec64 structure representing phase timestamp
+ * @raw_ts:	Pointer to timespec64 structure representing raw timestamp
  */
 void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts)
 {