Resguardo inicial

linux-7.2.3/kernel/time/.kunitconfig

@@ -0,0 +1,2 @@
+CONFIG_KUNIT=y
+CONFIG_TIME_KUNIT_TEST=y

linux-7.2.3/kernel/time/Kconfig

@@ -0,0 +1,220 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Timer subsystem related configuration options
+#
+
+# Options selectable by arch Kconfig
+
+# Watchdog function for clocksources to detect instabilities
+config CLOCKSOURCE_WATCHDOG
+	bool
+
+# Architecture has extra clocksource init called from registration
+config ARCH_CLOCKSOURCE_INIT
+	bool
+
+config ARCH_WANTS_CLOCKSOURCE_READ_INLINE
+	bool
+
+# The generic clock events infrastructure
+config GENERIC_CLOCKEVENTS
+	def_bool !LEGACY_TIMER_TICK
+
+# Architecture can handle broadcast in a driver-agnostic way
+config ARCH_HAS_TICK_BROADCAST
+	bool
+
+# Clockevents broadcasting infrastructure
+config GENERIC_CLOCKEVENTS_BROADCAST
+	bool
+	depends on GENERIC_CLOCKEVENTS
+
+# Handle broadcast in default_idle_call()
+config GENERIC_CLOCKEVENTS_BROADCAST_IDLE
+	bool
+	depends on GENERIC_CLOCKEVENTS_BROADCAST
+
+# Automatically adjust the min. reprogramming time for
+# clock event device
+config GENERIC_CLOCKEVENTS_MIN_ADJUST
+	bool
+
+config GENERIC_CLOCKEVENTS_COUPLED
+	bool
+
+config GENERIC_CLOCKEVENTS_COUPLED_INLINE
+	select GENERIC_CLOCKEVENTS_COUPLED
+	bool
+
+# Generic update of CMOS clock
+config GENERIC_CMOS_UPDATE
+	bool
+
+# Deferred rearming of the hrtimer interrupt
+config HRTIMER_REARM_DEFERRED
+       def_bool y
+       depends on GENERIC_ENTRY && HAVE_GENERIC_TIF_BITS
+       depends on HIGH_RES_TIMERS && SCHED_HRTICK
+
+# Select to handle posix CPU timers from task_work
+# and not from the timer interrupt context
+config HAVE_POSIX_CPU_TIMERS_TASK_WORK
+	bool
+
+config POSIX_CPU_TIMERS_TASK_WORK
+	bool
+	default y if POSIX_TIMERS && HAVE_POSIX_CPU_TIMERS_TASK_WORK
+
+config LEGACY_TIMER_TICK
+	bool
+	help
+	  The legacy timer tick helper is used by platforms that
+	  lack support for the generic clockevent framework.
+	  New platforms should use generic clockevents instead.
+
+config TIME_KUNIT_TEST
+	tristate "KUnit test for kernel/time functions" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  Enable this option to test RTC library functions.
+
+	  If unsure, say N.
+
+config CONTEXT_TRACKING
+	bool
+
+config CONTEXT_TRACKING_IDLE
+	bool
+	select CONTEXT_TRACKING
+	help
+	  Tracks idle state on behalf of RCU.
+
+menu "Timers subsystem"
+
+if GENERIC_CLOCKEVENTS
+# Core internal switch. Selected by NO_HZ_COMMON / HIGH_RES_TIMERS. This is
+# only related to the tick functionality. Oneshot clockevent devices
+# are supported independent of this.
+config TICK_ONESHOT
+	bool
+
+config NO_HZ_COMMON
+	bool
+	select TICK_ONESHOT
+
+choice
+	prompt "Timer tick handling"
+	default NO_HZ_IDLE if NO_HZ
+
+config HZ_PERIODIC
+	bool "Periodic timer ticks (constant rate, no dynticks)"
+	help
+	  This option keeps the tick running periodically at a constant
+	  rate, even when the CPU doesn't need it.
+
+config NO_HZ_IDLE
+	bool "Idle dynticks system (tickless idle)"
+	select NO_HZ_COMMON
+	help
+	  This option enables a tickless idle system: timer interrupts
+	  will only trigger on an as-needed basis when the system is idle.
+	  This is usually interesting for energy saving.
+
+	  Most of the time you want to say Y here.
+
+config NO_HZ_FULL
+	bool "Full dynticks system (tickless)"
+	# NO_HZ_COMMON dependency
+	# We need at least one periodic CPU for timekeeping
+	depends on SMP
+	depends on HAVE_CONTEXT_TRACKING_USER
+	# VIRT_CPU_ACCOUNTING_GEN dependency
+	depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
+	select NO_HZ_COMMON
+	select RCU_NOCB_CPU
+	select VIRT_CPU_ACCOUNTING_GEN
+	select IRQ_WORK
+	select CPU_ISOLATION
+	help
+	 Adaptively try to shutdown the tick whenever possible, even when
+	 the CPU is running tasks. Typically this requires running a single
+	 task on the CPU. Chances for running tickless are maximized when
+	 the task mostly runs in userspace and has few kernel activity.
+
+	 You need to fill up the nohz_full boot parameter with the
+	 desired range of dynticks CPUs to use it. This is implemented at
+	 the expense of some overhead in user <-> kernel transitions:
+	 syscalls, exceptions and interrupts.
+
+	 By default, without passing the nohz_full parameter, this behaves just
+	 like NO_HZ_IDLE.
+
+	 If you're a distro say Y.
+
+endchoice
+
+config CONTEXT_TRACKING_USER
+	bool
+	depends on HAVE_CONTEXT_TRACKING_USER
+	select CONTEXT_TRACKING
+	help
+	  Track transitions between kernel and user on behalf of RCU and
+	  tickless cputime accounting. The former case relies on context
+	  tracking to enter/exit RCU extended quiescent states.
+
+config CONTEXT_TRACKING_USER_FORCE
+	bool "Force user context tracking"
+	depends on CONTEXT_TRACKING_USER
+	default y if !NO_HZ_FULL
+	help
+	  The major pre-requirement for full dynticks to work is to
+	  support the user context tracking subsystem. But there are also
+	  other dependencies to provide in order to make the full
+	  dynticks working.
+
+	  This option stands for testing when an arch implements the
+	  user context tracking backend but doesn't yet fulfill all the
+	  requirements to make the full dynticks feature working.
+	  Without the full dynticks, there is no way to test the support
+	  for user context tracking and the subsystems that rely on it: RCU
+	  userspace extended quiescent state and tickless cputime
+	  accounting. This option copes with the absence of the full
+	  dynticks subsystem by forcing the user context tracking on all
+	  CPUs in the system.
+
+	  Say Y only if you're working on the development of an
+	  architecture backend for the user context tracking.
+
+	  Say N otherwise, this option brings an overhead that you
+	  don't want in production.
+
+config NO_HZ
+	bool "Old Idle dynticks config"
+	help
+	  This is the old config entry that enables dynticks idle.
+	  We keep it around for a little while to enforce backward
+	  compatibility with older config files.
+
+config HIGH_RES_TIMERS
+	bool "High Resolution Timer Support"
+	select TICK_ONESHOT
+	help
+	  This option enables high resolution timer support. If your
+	  hardware is not capable then this option only increases
+	  the size of the kernel image.
+
+endif
+
+config POSIX_AUX_CLOCKS
+	bool "Enable auxiliary POSIX clocks"
+	depends on POSIX_TIMERS
+	help
+	  Auxiliary POSIX clocks are clocks which can be steered
+	  independently of the core timekeeper, which controls the
+	  MONOTONIC, REALTIME, BOOTTIME and TAI clocks.  They are useful to
+	  provide e.g. lockless time accessors to independent PTP clocks
+	  and other clock domains, which are not correlated to the TAI/NTP
+	  notion of time.
+
+endmenu

linux-7.2.3/kernel/time/Makefile

@@ -0,0 +1,35 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Branch profiling isn't noinstr-safe
+ifdef CONFIG_TRACE_BRANCH_PROFILING
+CFLAGS_sched_clock.o += -DDISABLE_BRANCH_PROFILING
+endif
+
+obj-y += time.o timer.o hrtimer.o sleep_timeout.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
+obj-y += timeconv.o timecounter.o alarmtimer.o
+
+ifeq ($(CONFIG_POSIX_TIMERS),y)
+ obj-y += posix-timers.o posix-cpu-timers.o posix-clock.o itimer.o
+else
+ obj-y += posix-stubs.o
+endif
+
+obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= clockevents.o tick-common.o
+ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
+ obj-y						+= tick-broadcast.o
+ obj-$(CONFIG_TICK_ONESHOT)			+= tick-broadcast-hrtimer.o
+endif
+obj-$(CONFIG_GENERIC_SCHED_CLOCK)		+= sched_clock.o
+obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o tick-sched.o
+obj-$(CONFIG_LEGACY_TIMER_TICK)			+= tick-legacy.o
+ifeq ($(CONFIG_SMP),y)
+ obj-$(CONFIG_NO_HZ_COMMON)			+= timer_migration.o
+endif
+obj-$(CONFIG_GENERIC_GETTIMEOFDAY)		+= vsyscall.o
+obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
+obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o
+obj-$(CONFIG_TIME_NS)				+= namespace.o
+obj-$(CONFIG_TIME_NS_VDSO)			+= namespace_vdso.o
+obj-$(CONFIG_TEST_CLOCKSOURCE_WATCHDOG)		+= clocksource-wdtest.o
+obj-$(CONFIG_TIME_KUNIT_TEST)			+= time_test.o

linux-7.2.3/kernel/time/alarmtimer.c

@@ -0,0 +1,885 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Alarmtimer interface
+ *
+ * This interface provides a timer which is similar to hrtimers,
+ * but triggers a RTC alarm if the box is suspend.
+ *
+ * This interface is influenced by the Android RTC Alarm timer
+ * interface.
+ *
+ * Copyright (C) 2010 IBM Corporation
+ *
+ * Author: John Stultz <john.stultz@linaro.org>
+ */
+#include <linux/time.h>
+#include <linux/hrtimer.h>
+#include <linux/timerqueue.h>
+#include <linux/rtc.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
+#include <linux/alarmtimer.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/posix-timers.h>
+#include <linux/workqueue.h>
+#include <linux/freezer.h>
+#include <linux/compat.h>
+#include <linux/module.h>
+#include <linux/time_namespace.h>
+
+#include "posix-timers.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/alarmtimer.h>
+
+/**
+ * struct alarm_base - Alarm timer bases
+ * @lock:		Lock for synchronized access to the base
+ * @timerqueue:		Timerqueue head managing the list of events
+ * @get_ktime:		Function to read the time correlating to the base
+ * @get_timespec:	Function to read the namespace time correlating to the base
+ * @base_clockid:	clockid for the base
+ */
+static struct alarm_base {
+	spinlock_t		lock;
+	struct timerqueue_head	timerqueue;
+	ktime_t			(*get_ktime)(void);
+	void			(*get_timespec)(struct timespec64 *tp);
+	clockid_t		base_clockid;
+} alarm_bases[ALARM_NUMTYPE];
+
+#if defined(CONFIG_POSIX_TIMERS) || defined(CONFIG_RTC_CLASS)
+/* freezer information to handle clock_nanosleep triggered wakeups */
+static enum alarmtimer_type freezer_alarmtype;
+static ktime_t freezer_expires;
+static ktime_t freezer_delta;
+static DEFINE_SPINLOCK(freezer_delta_lock);
+#endif
+
+#ifdef CONFIG_RTC_CLASS
+/* rtc timer and device for setting alarm wakeups at suspend */
+static struct rtc_timer		rtctimer;
+static struct rtc_device	*rtcdev;
+static DEFINE_SPINLOCK(rtcdev_lock);
+
+/**
+ * alarmtimer_get_rtcdev - Return selected rtcdevice
+ *
+ * This function returns the rtc device to use for wakealarms.
+ */
+struct rtc_device *alarmtimer_get_rtcdev(void)
+{
+	struct rtc_device *ret;
+
+	guard(spinlock_irqsave)(&rtcdev_lock);
+	ret = rtcdev;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(alarmtimer_get_rtcdev);
+
+static int alarmtimer_rtc_add_device(struct device *dev)
+{
+	struct rtc_device *rtc = to_rtc_device(dev);
+	struct platform_device *pdev;
+	int ret = 0;
+
+	if (rtcdev)
+		return -EBUSY;
+
+	if (!test_bit(RTC_FEATURE_ALARM, rtc->features))
+		return -1;
+	if (!device_may_wakeup(rtc->dev.parent))
+		return -1;
+
+	pdev = platform_device_register_data(dev, "alarmtimer",
+					     PLATFORM_DEVID_AUTO, NULL, 0);
+	if (!IS_ERR(pdev))
+		device_init_wakeup(&pdev->dev, true);
+
+	scoped_guard(spinlock_irqsave, &rtcdev_lock) {
+		if (!IS_ERR(pdev) && !rtcdev && try_module_get(rtc->owner)) {
+			rtcdev = rtc;
+			/* hold a reference so it doesn't go away */
+			get_device(dev);
+			pdev = NULL;
+		} else {
+			ret = -1;
+		}
+	}
+
+	platform_device_unregister(pdev);
+	return ret;
+}
+
+static inline void alarmtimer_rtc_timer_init(void)
+{
+	rtc_timer_init(&rtctimer, NULL, NULL);
+}
+
+static struct class_interface alarmtimer_rtc_interface = {
+	.add_dev = &alarmtimer_rtc_add_device,
+};
+
+static int alarmtimer_rtc_interface_setup(void)
+{
+	alarmtimer_rtc_interface.class = &rtc_class;
+	return class_interface_register(&alarmtimer_rtc_interface);
+}
+static void alarmtimer_rtc_interface_remove(void)
+{
+	class_interface_unregister(&alarmtimer_rtc_interface);
+}
+#else
+static inline int alarmtimer_rtc_interface_setup(void) { return 0; }
+static inline void alarmtimer_rtc_interface_remove(void) { }
+static inline void alarmtimer_rtc_timer_init(void) { }
+#endif
+
+/**
+ * alarmtimer_enqueue - Adds an alarm timer to an alarm_base timerqueue
+ * @base: pointer to the base where the timer is being run
+ * @alarm: pointer to alarm being enqueued.
+ *
+ * Adds alarm to a alarm_base timerqueue
+ *
+ * Must hold base->lock when calling.
+ */
+static void alarmtimer_enqueue(struct alarm_base *base, struct alarm *alarm)
+{
+	if (alarm->state & ALARMTIMER_STATE_ENQUEUED)
+		timerqueue_del(&base->timerqueue, &alarm->node);
+
+	timerqueue_add(&base->timerqueue, &alarm->node);
+	alarm->state |= ALARMTIMER_STATE_ENQUEUED;
+}
+
+/**
+ * alarmtimer_dequeue - Removes an alarm timer from an alarm_base timerqueue
+ * @base: pointer to the base where the timer is running
+ * @alarm: pointer to alarm being removed
+ *
+ * Removes alarm to a alarm_base timerqueue
+ *
+ * Must hold base->lock when calling.
+ */
+static void alarmtimer_dequeue(struct alarm_base *base, struct alarm *alarm)
+{
+	if (!(alarm->state & ALARMTIMER_STATE_ENQUEUED))
+		return;
+
+	timerqueue_del(&base->timerqueue, &alarm->node);
+	alarm->state &= ~ALARMTIMER_STATE_ENQUEUED;
+}
+
+
+/**
+ * alarmtimer_fired - Handles alarm hrtimer being fired.
+ * @timer: pointer to hrtimer being run
+ *
+ * When a alarm timer fires, this runs through the timerqueue to
+ * see which alarms expired, and runs those. If there are more alarm
+ * timers queued for the future, we set the hrtimer to fire when
+ * the next future alarm timer expires.
+ */
+static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
+{
+	struct alarm *alarm = container_of(timer, struct alarm, timer);
+	struct alarm_base *base = &alarm_bases[alarm->type];
+
+	scoped_guard(spinlock_irqsave, &base->lock)
+		alarmtimer_dequeue(base, alarm);
+
+	if (alarm->function)
+		alarm->function(alarm, base->get_ktime());
+
+	trace_alarmtimer_fired(alarm, base->get_ktime());
+	return HRTIMER_NORESTART;
+}
+
+ktime_t alarm_expires_remaining(const struct alarm *alarm)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+	return ktime_sub(alarm->node.expires, base->get_ktime());
+}
+EXPORT_SYMBOL_GPL(alarm_expires_remaining);
+
+#ifdef CONFIG_RTC_CLASS
+/**
+ * alarmtimer_suspend - Suspend time callback
+ * @dev: unused
+ *
+ * When we are going into suspend, we look through the bases
+ * to see which is the soonest timer to expire. We then
+ * set an rtc timer to fire that far into the future, which
+ * will wake us from suspend.
+ */
+static int alarmtimer_suspend(struct device *dev)
+{
+	ktime_t min, now, expires;
+	struct rtc_device *rtc;
+	struct rtc_time tm;
+	int i, ret, type;
+
+	scoped_guard(spinlock_irqsave, &freezer_delta_lock) {
+		min = freezer_delta;
+		expires = freezer_expires;
+		type = freezer_alarmtype;
+		freezer_delta = 0;
+	}
+
+	rtc = alarmtimer_get_rtcdev();
+	/* If we have no rtcdev, just return */
+	if (!rtc)
+		return 0;
+
+	/* Find the soonest timer to expire */
+	for (i = 0; i < ALARM_NUMTYPE; i++) {
+		struct alarm_base *base = &alarm_bases[i];
+		struct timerqueue_node *next;
+		ktime_t next_expires;
+		ktime_t delta;
+
+		scoped_guard(spinlock_irqsave, &base->lock) {
+			next = timerqueue_getnext(&base->timerqueue);
+			if (next)
+				next_expires = next->expires;
+		}
+		if (!next)
+			continue;
+		delta = ktime_sub(next_expires, base->get_ktime());
+		if (!min || (delta < min)) {
+			expires = next_expires;
+			min = delta;
+			type = i;
+		}
+	}
+	if (min == 0)
+		return 0;
+
+	if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) {
+		pm_wakeup_event(dev, 2 * MSEC_PER_SEC);
+		return -EBUSY;
+	}
+
+	trace_alarmtimer_suspend(expires, type);
+
+	/* Setup an rtc timer to fire that far in the future */
+	rtc_timer_cancel(rtc, &rtctimer);
+	rtc_read_time(rtc, &tm);
+	now = rtc_tm_to_ktime(tm);
+
+	/*
+	 * If the RTC alarm timer only supports a limited time offset, set the
+	 * alarm time to the maximum supported value.
+	 * The system may wake up earlier (possibly much earlier) than expected
+	 * when the alarmtimer runs. This is the best the kernel can do if
+	 * the alarmtimer exceeds the time that the rtc device can be programmed
+	 * for.
+	 */
+	min = rtc_bound_alarmtime(rtc, min);
+
+	now = ktime_add(now, min);
+
+	/* Set alarm, if in the past reject suspend briefly to handle */
+	ret = rtc_timer_start(rtc, &rtctimer, now, 0);
+	if (ret < 0)
+		pm_wakeup_event(dev, MSEC_PER_SEC);
+	return ret;
+}
+
+static int alarmtimer_resume(struct device *dev)
+{
+	struct rtc_device *rtc;
+
+	rtc = alarmtimer_get_rtcdev();
+	if (rtc)
+		rtc_timer_cancel(rtc, &rtctimer);
+	return 0;
+}
+
+#else
+static int alarmtimer_suspend(struct device *dev)
+{
+	return 0;
+}
+
+static int alarmtimer_resume(struct device *dev)
+{
+	return 0;
+}
+#endif
+
+static void
+__alarm_init(struct alarm *alarm, enum alarmtimer_type type,
+	     void (*function)(struct alarm *, ktime_t))
+{
+	timerqueue_init(&alarm->node);
+	alarm->function = function;
+	alarm->type = type;
+	alarm->state = ALARMTIMER_STATE_INACTIVE;
+}
+
+/**
+ * alarm_init - Initialize an alarm structure
+ * @alarm: ptr to alarm to be initialized
+ * @type: the type of the alarm
+ * @function: callback that is run when the alarm fires
+ */
+void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
+		void (*function)(struct alarm *, ktime_t))
+{
+	hrtimer_setup(&alarm->timer, alarmtimer_fired, alarm_bases[type].base_clockid,
+		      HRTIMER_MODE_ABS);
+	__alarm_init(alarm, type, function);
+}
+EXPORT_SYMBOL_GPL(alarm_init);
+
+/**
+ * alarm_start_timer - Sets an alarm to fire
+ * @alarm:	Pointer to alarm to set
+ * @expires:	Expiry time
+ * @relative:	True if @expires is relative
+ *
+ * Returns: True if the alarm was queued. False if it already expired
+ */
+bool alarm_start_timer(struct alarm *alarm, ktime_t expires, bool relative)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+
+	if (relative)
+		expires = ktime_add_safe(expires, base->get_ktime());
+
+	trace_alarmtimer_start(alarm, base->get_ktime());
+
+	guard(spinlock_irqsave)(&base->lock);
+	alarm->node.expires = expires;
+	alarmtimer_enqueue(base, alarm);
+	if (!hrtimer_start_range_ns_user(&alarm->timer, expires, 0, HRTIMER_MODE_ABS)) {
+		alarmtimer_dequeue(base, alarm);
+		return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL_GPL(alarm_start_timer);
+
+/**
+ * alarm_try_to_cancel - Tries to cancel an alarm timer
+ * @alarm: ptr to alarm to be canceled
+ *
+ * Returns 1 if the timer was canceled, 0 if it was not running,
+ * and -1 if the callback was running
+ */
+int alarm_try_to_cancel(struct alarm *alarm)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+	int ret;
+
+	scoped_guard(spinlock_irqsave, &base->lock) {
+		ret = hrtimer_try_to_cancel(&alarm->timer);
+		if (ret >= 0)
+			alarmtimer_dequeue(base, alarm);
+	}
+
+	trace_alarmtimer_cancel(alarm, base->get_ktime());
+	return ret;
+}
+EXPORT_SYMBOL_GPL(alarm_try_to_cancel);
+
+
+/**
+ * alarm_cancel - Spins trying to cancel an alarm timer until it is done
+ * @alarm: ptr to alarm to be canceled
+ *
+ * Returns 1 if the timer was canceled, 0 if it was not active.
+ */
+int alarm_cancel(struct alarm *alarm)
+{
+	for (;;) {
+		int ret = alarm_try_to_cancel(alarm);
+		if (ret >= 0)
+			return ret;
+		hrtimer_cancel_wait_running(&alarm->timer);
+	}
+}
+EXPORT_SYMBOL_GPL(alarm_cancel);
+
+
+u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
+{
+	u64 overrun = 1;
+	ktime_t delta;
+
+	delta = ktime_sub(now, alarm->node.expires);
+
+	if (delta < 0)
+		return 0;
+
+	if (unlikely(delta >= interval)) {
+		s64 incr = ktime_to_ns(interval);
+
+		overrun = ktime_divns(delta, incr);
+
+		alarm->node.expires = ktime_add_ns(alarm->node.expires,
+							incr*overrun);
+
+		if (alarm->node.expires > now)
+			return overrun;
+		/*
+		 * This (and the ktime_add() below) is the
+		 * correction for exact:
+		 */
+		overrun++;
+	}
+
+	alarm->node.expires = ktime_add_safe(alarm->node.expires, interval);
+	return overrun;
+}
+EXPORT_SYMBOL_GPL(alarm_forward);
+
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+
+	return alarm_forward(alarm, base->get_ktime(), interval);
+}
+EXPORT_SYMBOL_GPL(alarm_forward_now);
+
+#ifdef CONFIG_POSIX_TIMERS
+
+static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type)
+{
+	struct alarm_base *base;
+	ktime_t delta;
+
+	switch(type) {
+	case ALARM_REALTIME:
+		base = &alarm_bases[ALARM_REALTIME];
+		type = ALARM_REALTIME_FREEZER;
+		break;
+	case ALARM_BOOTTIME:
+		base = &alarm_bases[ALARM_BOOTTIME];
+		type = ALARM_BOOTTIME_FREEZER;
+		break;
+	default:
+		WARN_ONCE(1, "Invalid alarm type: %d\n", type);
+		return;
+	}
+
+	delta = ktime_sub(absexp, base->get_ktime());
+
+	guard(spinlock_irqsave)(&freezer_delta_lock);
+	if (!freezer_delta || (delta < freezer_delta)) {
+		freezer_delta = delta;
+		freezer_expires = absexp;
+		freezer_alarmtype = type;
+	}
+}
+
+/**
+ * clock2alarm - helper that converts from clockid to alarmtypes
+ * @clockid: clockid.
+ */
+static enum alarmtimer_type clock2alarm(clockid_t clockid)
+{
+	if (clockid == CLOCK_REALTIME_ALARM)
+		return ALARM_REALTIME;
+
+	WARN_ON_ONCE(clockid != CLOCK_BOOTTIME_ALARM);
+	return ALARM_BOOTTIME;
+}
+
+/**
+ * alarm_handle_timer - Callback for posix timers
+ * @alarm: alarm that fired
+ * @now: time at the timer expiration
+ *
+ * Posix timer callback for expired alarm timers.
+ */
+static void alarm_handle_timer(struct alarm *alarm, ktime_t now)
+{
+	struct k_itimer *ptr = container_of(alarm, struct k_itimer, it.alarm.alarmtimer);
+
+	guard(spinlock_irqsave)(&ptr->it_lock);
+	posix_timer_queue_signal(ptr);
+}
+
+/**
+ * alarm_timer_rearm - Posix timer callback for rearming timer
+ * @timr:	Pointer to the posixtimer data struct
+ */
+static bool alarm_timer_rearm(struct k_itimer *timr)
+{
+	struct alarm *alarm = &timr->it.alarm.alarmtimer;
+
+	timr->it_overrun += alarm_forward_now(alarm, timr->it_interval);
+	return alarm_start_timer(alarm, alarm->node.expires, false);
+}
+
+/**
+ * alarm_timer_forward - Posix timer callback for forwarding timer
+ * @timr:	Pointer to the posixtimer data struct
+ * @now:	Current time to forward the timer against
+ */
+static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now)
+{
+	struct alarm *alarm = &timr->it.alarm.alarmtimer;
+
+	return alarm_forward(alarm, now, timr->it_interval);
+}
+
+/**
+ * alarm_timer_remaining - Posix timer callback to retrieve remaining time
+ * @timr:	Pointer to the posixtimer data struct
+ * @now:	Current time to calculate against
+ */
+static ktime_t alarm_timer_remaining(struct k_itimer *timr, ktime_t now)
+{
+	struct alarm *alarm = &timr->it.alarm.alarmtimer;
+
+	return ktime_sub(alarm->node.expires, now);
+}
+
+/**
+ * alarm_timer_try_to_cancel - Posix timer callback to cancel a timer
+ * @timr:	Pointer to the posixtimer data struct
+ */
+static int alarm_timer_try_to_cancel(struct k_itimer *timr)
+{
+	return alarm_try_to_cancel(&timr->it.alarm.alarmtimer);
+}
+
+/**
+ * alarm_timer_wait_running - Posix timer callback to wait for a timer
+ * @timr:	Pointer to the posixtimer data struct
+ *
+ * Called from the core code when timer cancel detected that the callback
+ * is running. @timr is unlocked and rcu read lock is held to prevent it
+ * from being freed.
+ */
+static void alarm_timer_wait_running(struct k_itimer *timr)
+{
+	hrtimer_cancel_wait_running(&timr->it.alarm.alarmtimer.timer);
+}
+
+/**
+ * alarm_timer_arm - Posix timer callback to arm a timer
+ * @timr:	Pointer to the posixtimer data struct
+ * @expires:	The new expiry time
+ * @absolute:	Expiry value is absolute time
+ * @sigev_none:	Posix timer does not deliver signals
+ */
+static bool alarm_timer_arm(struct k_itimer *timr, ktime_t expires,
+			    bool absolute, bool sigev_none)
+{
+	struct alarm *alarm = &timr->it.alarm.alarmtimer;
+	struct alarm_base *base = &alarm_bases[alarm->type];
+
+	if (!absolute)
+		expires = ktime_add_safe(expires, base->get_ktime());
+
+	/*
+	 * sigev_none needs to update the expires value and pretend
+	 * that the timer is queued
+	 */
+	if (sigev_none) {
+		alarm->node.expires = expires;
+		return true;
+	}
+	return alarm_start_timer(&timr->it.alarm.alarmtimer, expires, false);
+}
+
+/**
+ * alarm_clock_getres - posix getres interface
+ * @which_clock: clockid
+ * @tp: timespec to fill
+ *
+ * Returns the granularity of underlying alarm base clock
+ */
+static int alarm_clock_getres(const clockid_t which_clock, struct timespec64 *tp)
+{
+	if (!alarmtimer_get_rtcdev())
+		return -EINVAL;
+
+	tp->tv_sec = 0;
+	tp->tv_nsec = hrtimer_resolution;
+	return 0;
+}
+
+/**
+ * alarm_clock_get_timespec - posix clock_get_timespec interface
+ * @which_clock: clockid
+ * @tp: timespec to fill.
+ *
+ * Provides the underlying alarm base time in a tasks time namespace.
+ */
+static int alarm_clock_get_timespec(clockid_t which_clock, struct timespec64 *tp)
+{
+	struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
+
+	if (!alarmtimer_get_rtcdev())
+		return -EINVAL;
+
+	base->get_timespec(tp);
+
+	return 0;
+}
+
+/**
+ * alarm_clock_get_ktime - posix clock_get_ktime interface
+ * @which_clock: clockid
+ *
+ * Provides the underlying alarm base time in the root namespace.
+ */
+static ktime_t alarm_clock_get_ktime(clockid_t which_clock)
+{
+	struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
+
+	if (!alarmtimer_get_rtcdev())
+		return -EINVAL;
+
+	return base->get_ktime();
+}
+
+/**
+ * alarm_timer_create - posix timer_create interface
+ * @new_timer: k_itimer pointer to manage
+ *
+ * Initializes the k_itimer structure.
+ */
+static int alarm_timer_create(struct k_itimer *new_timer)
+{
+	enum  alarmtimer_type type;
+
+	if (!alarmtimer_get_rtcdev())
+		return -EOPNOTSUPP;
+
+	if (!capable(CAP_WAKE_ALARM))
+		return -EPERM;
+
+	type = clock2alarm(new_timer->it_clock);
+	alarm_init(&new_timer->it.alarm.alarmtimer, type, alarm_handle_timer);
+	return 0;
+}
+
+/**
+ * alarmtimer_nsleep_wakeup - Wakeup function for alarm_timer_nsleep
+ * @alarm: ptr to alarm that fired
+ * @now: time at the timer expiration
+ *
+ * Wakes up the task that set the alarmtimer
+ */
+static void alarmtimer_nsleep_wakeup(struct alarm *alarm, ktime_t now)
+{
+	struct task_struct *task = alarm->data;
+
+	alarm->data = NULL;
+	if (task)
+		wake_up_process(task);
+}
+
+/**
+ * alarmtimer_do_nsleep - Internal alarmtimer nsleep implementation
+ * @alarm: ptr to alarmtimer
+ * @absexp: absolute expiration time
+ * @type: alarm type (BOOTTIME/REALTIME).
+ *
+ * Sets the alarm timer and sleeps until it is fired or interrupted.
+ */
+static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp,
+				enum alarmtimer_type type)
+{
+	struct restart_block *restart;
+	alarm->data = (void *)current;
+	do {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!alarm_start_timer(alarm, absexp, false))
+			alarm->data = NULL;
+
+		if (likely(alarm->data))
+			schedule();
+
+		alarm_cancel(alarm);
+	} while (alarm->data && !signal_pending(current));
+
+	__set_current_state(TASK_RUNNING);
+
+	destroy_hrtimer_on_stack(&alarm->timer);
+
+	if (!alarm->data)
+		return 0;
+
+	if (freezing(current))
+		alarmtimer_freezerset(absexp, type);
+	restart = &current->restart_block;
+	if (restart->nanosleep.type != TT_NONE) {
+		struct timespec64 rmt;
+		ktime_t rem;
+
+		rem = ktime_sub(absexp, alarm_bases[type].get_ktime());
+
+		if (rem <= 0)
+			return 0;
+		rmt = ktime_to_timespec64(rem);
+
+		return nanosleep_copyout(restart, &rmt);
+	}
+	return -ERESTART_RESTARTBLOCK;
+}
+
+static void
+alarm_init_on_stack(struct alarm *alarm, enum alarmtimer_type type,
+		    void (*function)(struct alarm *, ktime_t))
+{
+	hrtimer_setup_on_stack(&alarm->timer, alarmtimer_fired, alarm_bases[type].base_clockid,
+			       HRTIMER_MODE_ABS);
+	__alarm_init(alarm, type, function);
+}
+
+/**
+ * alarm_timer_nsleep_restart - restartblock alarmtimer nsleep
+ * @restart: ptr to restart block
+ *
+ * Handles restarted clock_nanosleep calls
+ */
+static long __sched alarm_timer_nsleep_restart(struct restart_block *restart)
+{
+	enum  alarmtimer_type type = restart->nanosleep.clockid;
+	ktime_t exp = restart->nanosleep.expires;
+	struct alarm alarm;
+
+	alarm_init_on_stack(&alarm, type, alarmtimer_nsleep_wakeup);
+
+	return alarmtimer_do_nsleep(&alarm, exp, type);
+}
+
+/**
+ * alarm_timer_nsleep - alarmtimer nanosleep
+ * @which_clock: clockid
+ * @flags: determines abstime or relative
+ * @tsreq: requested sleep time (abs or rel)
+ *
+ * Handles clock_nanosleep calls against _ALARM clockids
+ */
+static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
+			      const struct timespec64 *tsreq)
+{
+	enum  alarmtimer_type type = clock2alarm(which_clock);
+	struct restart_block *restart = &current->restart_block;
+	struct alarm alarm;
+	ktime_t exp;
+	int ret;
+
+	if (!alarmtimer_get_rtcdev())
+		return -EOPNOTSUPP;
+
+	if (flags & ~TIMER_ABSTIME)
+		return -EINVAL;
+
+	if (!capable(CAP_WAKE_ALARM))
+		return -EPERM;
+
+	alarm_init_on_stack(&alarm, type, alarmtimer_nsleep_wakeup);
+
+	exp = timespec64_to_ktime(*tsreq);
+	/* Convert (if necessary) to absolute time */
+	if (flags != TIMER_ABSTIME) {
+		ktime_t now = alarm_bases[type].get_ktime();
+
+		exp = ktime_add_safe(now, exp);
+	} else {
+		exp = timens_ktime_to_host(which_clock, exp);
+	}
+
+	ret = alarmtimer_do_nsleep(&alarm, exp, type);
+	if (ret != -ERESTART_RESTARTBLOCK)
+		return ret;
+
+	/* abs timers don't set remaining time or restart */
+	if (flags == TIMER_ABSTIME)
+		return -ERESTARTNOHAND;
+
+	restart->nanosleep.clockid = type;
+	restart->nanosleep.expires = exp;
+	set_restart_fn(restart, alarm_timer_nsleep_restart);
+	return ret;
+}
+
+const struct k_clock alarm_clock = {
+	.clock_getres		= alarm_clock_getres,
+	.clock_get_ktime	= alarm_clock_get_ktime,
+	.clock_get_timespec	= alarm_clock_get_timespec,
+	.timer_create		= alarm_timer_create,
+	.timer_set		= common_timer_set,
+	.timer_del		= common_timer_del,
+	.timer_get		= common_timer_get,
+	.timer_arm		= alarm_timer_arm,
+	.timer_rearm		= alarm_timer_rearm,
+	.timer_forward		= alarm_timer_forward,
+	.timer_remaining	= alarm_timer_remaining,
+	.timer_try_to_cancel	= alarm_timer_try_to_cancel,
+	.timer_wait_running	= alarm_timer_wait_running,
+	.nsleep			= alarm_timer_nsleep,
+};
+#endif /* CONFIG_POSIX_TIMERS */
+
+
+/* Suspend hook structures */
+static const struct dev_pm_ops alarmtimer_pm_ops = {
+	.suspend = alarmtimer_suspend,
+	.resume = alarmtimer_resume,
+};
+
+static struct platform_driver alarmtimer_driver = {
+	.driver = {
+		.name = "alarmtimer",
+		.pm = &alarmtimer_pm_ops,
+	}
+};
+
+static void get_boottime_timespec(struct timespec64 *tp)
+{
+	ktime_get_boottime_ts64(tp);
+	timens_add_boottime(tp);
+}
+
+/**
+ * alarmtimer_init - Initialize alarm timer code
+ *
+ * This function initializes the alarm bases and registers
+ * the posix clock ids.
+ */
+static int __init alarmtimer_init(void)
+{
+	int error;
+	int i;
+
+	alarmtimer_rtc_timer_init();
+
+	/* Initialize alarm bases */
+	alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME;
+	alarm_bases[ALARM_REALTIME].get_ktime = &ktime_get_real;
+	alarm_bases[ALARM_REALTIME].get_timespec = ktime_get_real_ts64;
+	alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME;
+	alarm_bases[ALARM_BOOTTIME].get_ktime = &ktime_get_boottime;
+	alarm_bases[ALARM_BOOTTIME].get_timespec = get_boottime_timespec;
+	for (i = 0; i < ALARM_NUMTYPE; i++) {
+		timerqueue_init_head(&alarm_bases[i].timerqueue);
+		spin_lock_init(&alarm_bases[i].lock);
+	}
+
+	error = alarmtimer_rtc_interface_setup();
+	if (error)
+		return error;
+
+	error = platform_driver_register(&alarmtimer_driver);
+	if (error)
+		goto out_if;
+
+	return 0;
+out_if:
+	alarmtimer_rtc_interface_remove();
+	return error;
+}
+device_initcall(alarmtimer_init);

linux-7.2.3/kernel/time/clockevents.c

@@ -0,0 +1,828 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains functions which manage clock event devices.
+ *
+ * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ */
+
+#include <linux/clockchips.h>
+#include <linux/hrtimer.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/device.h>
+
+#include "tick-internal.h"
+
+/* The registered clock event devices */
+static LIST_HEAD(clockevent_devices);
+static LIST_HEAD(clockevents_released);
+/* Protection for the above */
+static DEFINE_RAW_SPINLOCK(clockevents_lock);
+/* Protection for unbind operations */
+static DEFINE_MUTEX(clockevents_mutex);
+
+struct ce_unbind {
+	struct clock_event_device *ce;
+	int res;
+};
+
+static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt,
+			bool ismax)
+{
+	u64 clc = (u64) latch << evt->shift;
+	u64 rnd;
+
+	if (WARN_ON(!evt->mult))
+		evt->mult = 1;
+	rnd = (u64) evt->mult - 1;
+
+	/*
+	 * Upper bound sanity check. If the backwards conversion is
+	 * not equal latch, we know that the above shift overflowed.
+	 */
+	if ((clc >> evt->shift) != (u64)latch)
+		clc = ~0ULL;
+
+	/*
+	 * Scaled math oddities:
+	 *
+	 * For mult <= (1 << shift) we can safely add mult - 1 to
+	 * prevent integer rounding loss. So the backwards conversion
+	 * from nsec to device ticks will be correct.
+	 *
+	 * For mult > (1 << shift), i.e. device frequency is > 1GHz we
+	 * need to be careful. Adding mult - 1 will result in a value
+	 * which when converted back to device ticks can be larger
+	 * than latch by up to (mult - 1) >> shift. For the min_delta
+	 * calculation we still want to apply this in order to stay
+	 * above the minimum device ticks limit. For the upper limit
+	 * we would end up with a latch value larger than the upper
+	 * limit of the device, so we omit the add to stay below the
+	 * device upper boundary.
+	 *
+	 * Also omit the add if it would overflow the u64 boundary.
+	 */
+	if ((~0ULL - clc > rnd) &&
+	    (!ismax || evt->mult <= (1ULL << evt->shift)))
+		clc += rnd;
+
+	do_div(clc, evt->mult);
+
+	/* Deltas less than 1usec are pointless noise */
+	return clc > 1000 ? clc : 1000;
+}
+
+/**
+ * clockevent_delta2ns - Convert a latch value (device ticks) to nanoseconds
+ * @latch:	value to convert
+ * @evt:	pointer to clock event device descriptor
+ *
+ * Math helper, returns latch value converted to nanoseconds (bound checked)
+ */
+u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
+{
+	return cev_delta2ns(latch, evt, false);
+}
+EXPORT_SYMBOL_GPL(clockevent_delta2ns);
+
+static int __clockevents_switch_state(struct clock_event_device *dev,
+				      enum clock_event_state state)
+{
+	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
+		return 0;
+
+	/* On state transitions clear the forced flag unconditionally */
+	dev->next_event_forced = 0;
+
+	/* Transition with new state-specific callbacks */
+	switch (state) {
+	case CLOCK_EVT_STATE_DETACHED:
+		/* The clockevent device is getting replaced. Shut it down. */
+
+	case CLOCK_EVT_STATE_SHUTDOWN:
+		if (dev->set_state_shutdown)
+			return dev->set_state_shutdown(dev);
+		return 0;
+
+	case CLOCK_EVT_STATE_PERIODIC:
+		/* Core internal bug */
+		if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC))
+			return -ENOSYS;
+		if (dev->set_state_periodic)
+			return dev->set_state_periodic(dev);
+		return 0;
+
+	case CLOCK_EVT_STATE_ONESHOT:
+		/* Core internal bug */
+		if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+			return -ENOSYS;
+		if (dev->set_state_oneshot)
+			return dev->set_state_oneshot(dev);
+		return 0;
+
+	case CLOCK_EVT_STATE_ONESHOT_STOPPED:
+		/* Core internal bug */
+		if (WARN_ONCE(!clockevent_state_oneshot(dev),
+			      "Current state: %d\n",
+			      clockevent_get_state(dev)))
+			return -EINVAL;
+
+		if (dev->set_state_oneshot_stopped)
+			return dev->set_state_oneshot_stopped(dev);
+		else
+			return -ENOSYS;
+
+	default:
+		return -ENOSYS;
+	}
+}
+
+/**
+ * clockevents_switch_state - set the operating state of a clock event device
+ * @dev:	device to modify
+ * @state:	new state
+ *
+ * Must be called with interrupts disabled !
+ */
+void clockevents_switch_state(struct clock_event_device *dev,
+			      enum clock_event_state state)
+{
+	if (clockevent_get_state(dev) != state) {
+		if (__clockevents_switch_state(dev, state))
+			return;
+
+		clockevent_set_state(dev, state);
+
+		/*
+		 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
+		 * on it, so fix it up and emit a warning:
+		 */
+		if (clockevent_state_oneshot(dev)) {
+			if (WARN_ON(!dev->mult))
+				dev->mult = 1;
+		}
+	}
+}
+
+/**
+ * clockevents_shutdown - shutdown the device and clear next_event
+ * @dev:	device to shutdown
+ */
+void clockevents_shutdown(struct clock_event_device *dev)
+{
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
+	dev->next_event = KTIME_MAX;
+	dev->next_event_forced = 0;
+}
+
+/**
+ * clockevents_tick_resume -	Resume the tick device before using it again
+ * @dev:			device to resume
+ */
+int clockevents_tick_resume(struct clock_event_device *dev)
+{
+	int ret = 0;
+
+	if (dev->tick_resume)
+		ret = dev->tick_resume(dev);
+
+	return ret;
+}
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST
+
+/* Limit min_delta to a jiffy */
+#define MIN_DELTA_LIMIT		(NSEC_PER_SEC / HZ)
+
+/**
+ * clockevents_increase_min_delta - raise minimum delta of a clock event device
+ * @dev:       device to increase the minimum delta
+ *
+ * Returns 0 on success, -ETIME when the minimum delta reached the limit.
+ */
+static int clockevents_increase_min_delta(struct clock_event_device *dev)
+{
+	/* Nothing to do if we already reached the limit */
+	if (dev->min_delta_ns >= MIN_DELTA_LIMIT) {
+		printk_deferred(KERN_WARNING
+				"CE: Reprogramming failure. Giving up\n");
+		dev->next_event = KTIME_MAX;
+		return -ETIME;
+	}
+
+	if (dev->min_delta_ns < 5000)
+		dev->min_delta_ns = 5000;
+	else
+		dev->min_delta_ns += dev->min_delta_ns >> 1;
+
+	if (dev->min_delta_ns > MIN_DELTA_LIMIT)
+		dev->min_delta_ns = MIN_DELTA_LIMIT;
+
+	printk_deferred(KERN_WARNING
+			"CE: %s increased min_delta_ns to %llu nsec\n",
+			dev->name ? dev->name : "?",
+			(unsigned long long) dev->min_delta_ns);
+	return 0;
+}
+
+/**
+ * clockevents_program_min_delta - Set clock event device to the minimum delay.
+ * @dev:	device to program
+ *
+ * Returns 0 on success, -ETIME when the retry loop failed.
+ */
+static int clockevents_program_min_delta(struct clock_event_device *dev)
+{
+	unsigned long long clc;
+	int64_t delta;
+	int i;
+
+	for (i = 0;;) {
+		delta = dev->min_delta_ns;
+		dev->next_event = ktime_add_ns(ktime_get(), delta);
+
+		if (clockevent_state_shutdown(dev))
+			return 0;
+
+		dev->retries++;
+		clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
+		if (dev->set_next_event((unsigned long) clc, dev) == 0)
+			return 0;
+
+		if (++i > 2) {
+			/*
+			 * We tried 3 times to program the device with the
+			 * given min_delta_ns. Try to increase the minimum
+			 * delta, if that fails as well get out of here.
+			 */
+			if (clockevents_increase_min_delta(dev))
+				return -ETIME;
+			i = 0;
+		}
+	}
+}
+
+#else  /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */
+
+/**
+ * clockevents_program_min_delta - Set clock event device to the minimum delay.
+ * @dev:	device to program
+ *
+ * Returns 0 on success, -ETIME when the retry loop failed.
+ */
+static int clockevents_program_min_delta(struct clock_event_device *dev)
+{
+	unsigned long long clc;
+	int64_t delta = 0;
+	int i;
+
+	for (i = 0; i < 10; i++) {
+		delta += dev->min_delta_ns;
+		dev->next_event = ktime_add_ns(ktime_get(), delta);
+
+		if (clockevent_state_shutdown(dev))
+			return 0;
+
+		dev->retries++;
+		clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
+		if (dev->set_next_event((unsigned long) clc, dev) == 0)
+			return 0;
+	}
+	return -ETIME;
+}
+
+#endif /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_COUPLED
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_COUPLED_INLINE
+#include <asm/clock_inlined.h>
+#else
+static __always_inline void
+arch_inlined_clockevent_set_next_coupled(u64 cycles, struct clock_event_device *dev) { }
+#endif
+
+static inline bool clockevent_set_next_coupled(struct clock_event_device *dev, ktime_t expires)
+{
+	u64 cycles;
+
+	if (unlikely(!(dev->features & CLOCK_EVT_FEAT_CLOCKSOURCE_COUPLED)))
+		return false;
+
+	if (unlikely(!ktime_expiry_to_cycles(dev->cs_id, expires, &cycles)))
+		return false;
+
+	if (IS_ENABLED(CONFIG_GENERIC_CLOCKEVENTS_COUPLED_INLINE))
+		arch_inlined_clockevent_set_next_coupled(cycles, dev);
+	else
+		dev->set_next_coupled(cycles, dev);
+	return true;
+}
+
+#else
+static inline bool clockevent_set_next_coupled(struct clock_event_device *dev, ktime_t expires)
+{
+	return false;
+}
+#endif
+
+/**
+ * clockevents_program_event - Reprogram the clock event device.
+ * @dev:	device to program
+ * @expires:	absolute expiry time (monotonic clock)
+ * @force:	program minimum delay if expires can not be set
+ *
+ * Returns 0 on success, -ETIME when the event is in the past.
+ */
+int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, bool force)
+{
+	int64_t delta;
+	u64 cycles;
+
+	if (WARN_ON_ONCE(expires < 0))
+		return -ETIME;
+
+	dev->next_event = expires;
+
+	if (clockevent_state_shutdown(dev))
+		return 0;
+
+	/* We must be in ONESHOT state here */
+	WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n",
+		  clockevent_get_state(dev));
+
+	/* ktime_t based reprogramming for the broadcast hrtimer device */
+	if (unlikely(dev->features & CLOCK_EVT_FEAT_HRTIMER))
+		return dev->set_next_ktime(expires, dev);
+
+	if (likely(clockevent_set_next_coupled(dev, expires)))
+		return 0;
+
+	delta = ktime_to_ns(ktime_sub(expires, ktime_get()));
+
+	/* Required for tick_periodic() during early boot */
+	if (delta <= 0 && !force)
+		return -ETIME;
+
+	if (delta > (int64_t)dev->min_delta_ns) {
+		delta = min(delta, (int64_t) dev->max_delta_ns);
+		cycles = ((u64)delta * dev->mult) >> dev->shift;
+		if (!dev->set_next_event((unsigned long) cycles, dev)) {
+			dev->next_event_forced = 0;
+			return 0;
+		}
+	}
+
+	if (dev->next_event_forced)
+		return 0;
+
+	if (dev->set_next_event(dev->min_delta_ticks, dev)) {
+		if (!force || clockevents_program_min_delta(dev))
+			return -ETIME;
+	}
+	dev->next_event_forced = 1;
+	return 0;
+}
+
+/*
+ * Called after a clockevent has been added which might
+ * have replaced a current regular or broadcast device. A
+ * released normal device might be a suitable replacement
+ * for the current broadcast device. Similarly a released
+ * broadcast device might be a suitable replacement for a
+ * normal device.
+ */
+static void clockevents_notify_released(void)
+{
+	struct clock_event_device *dev;
+
+	/*
+	 * Keep iterating as long as tick_check_new_device()
+	 * replaces a device.
+	 */
+	while (!list_empty(&clockevents_released)) {
+		dev = list_entry(clockevents_released.next,
+				 struct clock_event_device, list);
+		list_move(&dev->list, &clockevent_devices);
+		tick_check_new_device(dev);
+	}
+}
+
+/*
+ * Try to install a replacement clock event device
+ */
+static int clockevents_replace(struct clock_event_device *ced)
+{
+	struct clock_event_device *dev, *newdev = NULL;
+
+	list_for_each_entry(dev, &clockevent_devices, list) {
+		if (dev == ced || !clockevent_state_detached(dev))
+			continue;
+
+		if (!tick_check_replacement(newdev, dev))
+			continue;
+
+		if (!try_module_get(dev->owner))
+			continue;
+
+		if (newdev)
+			module_put(newdev->owner);
+		newdev = dev;
+	}
+	if (newdev) {
+		tick_install_replacement(newdev);
+		list_del_init(&ced->list);
+	}
+	return newdev ? 0 : -EBUSY;
+}
+
+/*
+ * Called with clockevents_mutex and clockevents_lock held
+ */
+static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu)
+{
+	/* Fast track. Device is unused */
+	if (clockevent_state_detached(ced)) {
+		list_del_init(&ced->list);
+		return 0;
+	}
+
+	return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY;
+}
+
+/*
+ * SMP function call to unbind a device
+ */
+static void __clockevents_unbind(void *arg)
+{
+	struct ce_unbind *cu = arg;
+	int res;
+
+	raw_spin_lock(&clockevents_lock);
+	res = __clockevents_try_unbind(cu->ce, smp_processor_id());
+	if (res == -EAGAIN)
+		res = clockevents_replace(cu->ce);
+	cu->res = res;
+	raw_spin_unlock(&clockevents_lock);
+}
+
+/*
+ * Issues smp function call to unbind a per cpu device. Called with
+ * clockevents_mutex held.
+ */
+static int clockevents_unbind(struct clock_event_device *ced, int cpu)
+{
+	struct ce_unbind cu = { .ce = ced, .res = -ENODEV };
+
+	smp_call_function_single(cpu, __clockevents_unbind, &cu, 1);
+	return cu.res;
+}
+
+/*
+ * Unbind a clockevents device.
+ */
+int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
+{
+	int ret;
+
+	mutex_lock(&clockevents_mutex);
+	ret = clockevents_unbind(ced, cpu);
+	mutex_unlock(&clockevents_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clockevents_unbind_device);
+
+/**
+ * clockevents_register_device - register a clock event device
+ * @dev:	device to register
+ */
+void clockevents_register_device(struct clock_event_device *dev)
+{
+	unsigned long flags;
+
+	/* Initialize state to DETACHED */
+	clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
+
+	if (!dev->cpumask) {
+		WARN_ON(num_possible_cpus() > 1);
+		dev->cpumask = cpumask_of(smp_processor_id());
+	}
+
+	if (dev->cpumask == cpu_all_mask) {
+		WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n",
+		     dev->name);
+		dev->cpumask = cpu_possible_mask;
+	}
+
+	raw_spin_lock_irqsave(&clockevents_lock, flags);
+
+	list_add(&dev->list, &clockevent_devices);
+	tick_check_new_device(dev);
+	clockevents_notify_released();
+
+	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+}
+EXPORT_SYMBOL_GPL(clockevents_register_device);
+
+static void clockevents_config(struct clock_event_device *dev, u32 freq)
+{
+	u64 sec;
+
+	if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+		return;
+
+	/*
+	 * Calculate the maximum number of seconds we can sleep. Limit
+	 * to 10 minutes for hardware which can program more than
+	 * 32bit ticks so we still get reasonable conversion values.
+	 */
+	sec = dev->max_delta_ticks;
+	do_div(sec, freq);
+	if (!sec)
+		sec = 1;
+	else if (sec > 600 && dev->max_delta_ticks > UINT_MAX)
+		sec = 600;
+
+	clockevents_calc_mult_shift(dev, freq, sec);
+	dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false);
+	dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true);
+}
+
+/**
+ * clockevents_config_and_register - Configure and register a clock event device
+ * @dev:	device to register
+ * @freq:	The clock frequency
+ * @min_delta:	The minimum clock ticks to program in oneshot mode
+ * @max_delta:	The maximum clock ticks to program in oneshot mode
+ *
+ * min/max_delta can be 0 for devices which do not support oneshot mode.
+ */
+void clockevents_config_and_register(struct clock_event_device *dev,
+				     u32 freq, unsigned long min_delta,
+				     unsigned long max_delta)
+{
+	dev->min_delta_ticks = min_delta;
+	dev->max_delta_ticks = max_delta;
+	clockevents_config(dev, freq);
+	clockevents_register_device(dev);
+}
+EXPORT_SYMBOL_GPL(clockevents_config_and_register);
+
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
+{
+	clockevents_config(dev, freq);
+
+	if (clockevent_state_oneshot(dev))
+		return clockevents_program_event(dev, dev->next_event, false);
+
+	if (clockevent_state_periodic(dev))
+		return __clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
+
+	return 0;
+}
+
+/**
+ * clockevents_update_freq - Update frequency and reprogram a clock event device.
+ * @dev:	device to modify
+ * @freq:	new device frequency
+ *
+ * Reconfigure and reprogram a clock event device in oneshot
+ * mode. Must be called on the cpu for which the device delivers per
+ * cpu timer events. If called for the broadcast device the core takes
+ * care of serialization.
+ *
+ * Returns 0 on success, -ETIME when the event is in the past.
+ */
+int clockevents_update_freq(struct clock_event_device *dev, u32 freq)
+{
+	unsigned long flags;
+	int ret;
+
+	local_irq_save(flags);
+	ret = tick_broadcast_update_freq(dev, freq);
+	if (ret == -ENODEV)
+		ret = __clockevents_update_freq(dev, freq);
+	local_irq_restore(flags);
+	return ret;
+}
+
+/*
+ * Noop handler when we shut down an event device
+ */
+void clockevents_handle_noop(struct clock_event_device *dev)
+{
+}
+
+/**
+ * clockevents_exchange_device - release and request clock devices
+ * @old:	device to release (can be NULL)
+ * @new:	device to request (can be NULL)
+ *
+ * Called from various tick functions with clockevents_lock held and
+ * interrupts disabled.
+ */
+void clockevents_exchange_device(struct clock_event_device *old,
+				 struct clock_event_device *new)
+{
+	/*
+	 * Caller releases a clock event device. We queue it into the
+	 * released list and do a notify add later.
+	 */
+	if (old) {
+		module_put(old->owner);
+		clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED);
+		list_move(&old->list, &clockevents_released);
+	}
+
+	if (new) {
+		BUG_ON(!clockevent_state_detached(new));
+		clockevents_shutdown(new);
+	}
+}
+
+/**
+ * clockevents_suspend - suspend clock devices
+ */
+void clockevents_suspend(void)
+{
+	struct clock_event_device *dev;
+
+	list_for_each_entry_reverse(dev, &clockevent_devices, list)
+		if (dev->suspend && !clockevent_state_detached(dev))
+			dev->suspend(dev);
+}
+
+/**
+ * clockevents_resume - resume clock devices
+ */
+void clockevents_resume(void)
+{
+	struct clock_event_device *dev;
+
+	list_for_each_entry(dev, &clockevent_devices, list)
+		if (dev->resume && !clockevent_state_detached(dev))
+			dev->resume(dev);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/**
+ * tick_offline_cpu - Shutdown all clock events related
+ *                    to this CPU and take it out of the
+ *                    broadcast mechanism.
+ * @cpu:	The outgoing CPU
+ *
+ * Called by the dying CPU during teardown.
+ */
+void tick_offline_cpu(unsigned int cpu)
+{
+	struct clock_event_device *dev, *tmp;
+
+	raw_spin_lock(&clockevents_lock);
+
+	tick_broadcast_offline(cpu);
+	tick_shutdown();
+
+	/*
+	 * Unregister the clock event devices which were
+	 * released above.
+	 */
+	list_for_each_entry_safe(dev, tmp, &clockevents_released, list)
+		list_del(&dev->list);
+
+	/*
+	 * Now check whether the CPU has left unused per cpu devices
+	 */
+	list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) {
+		if (cpumask_test_cpu(cpu, dev->cpumask) &&
+		    cpumask_weight(dev->cpumask) == 1 &&
+		    !tick_is_broadcast_device(dev)) {
+			BUG_ON(!clockevent_state_detached(dev));
+			list_del(&dev->list);
+		}
+	}
+
+	raw_spin_unlock(&clockevents_lock);
+}
+#endif
+
+#ifdef CONFIG_SYSFS
+static const struct bus_type clockevents_subsys = {
+	.name		= "clockevents",
+	.dev_name       = "clockevent",
+};
+
+static DEFINE_PER_CPU(struct device, tick_percpu_dev);
+static struct tick_device *tick_get_tick_dev(struct device *dev);
+
+static ssize_t current_device_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buf)
+{
+	struct tick_device *td;
+	ssize_t count = 0;
+
+	raw_spin_lock_irq(&clockevents_lock);
+	td = tick_get_tick_dev(dev);
+	if (td && td->evtdev)
+		count = sysfs_emit(buf, "%s\n", td->evtdev->name);
+	raw_spin_unlock_irq(&clockevents_lock);
+	return count;
+}
+static DEVICE_ATTR_RO(current_device);
+
+/* We don't support the abomination of removable broadcast devices */
+static ssize_t unbind_device_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t count)
+{
+	char name[CS_NAME_LEN];
+	ssize_t ret = sysfs_get_uname(buf, name, count);
+	struct clock_event_device *ce = NULL, *iter;
+
+	if (ret < 0)
+		return ret;
+
+	ret = -ENODEV;
+	mutex_lock(&clockevents_mutex);
+	raw_spin_lock_irq(&clockevents_lock);
+	list_for_each_entry(iter, &clockevent_devices, list) {
+		if (!strcmp(iter->name, name)) {
+			ret = __clockevents_try_unbind(iter, dev->id);
+			ce = iter;
+			break;
+		}
+	}
+	raw_spin_unlock_irq(&clockevents_lock);
+	/*
+	 * We hold clockevents_mutex, so ce can't go away
+	 */
+	if (ret == -EAGAIN)
+		ret = clockevents_unbind(ce, dev->id);
+	mutex_unlock(&clockevents_mutex);
+	return ret ? ret : count;
+}
+static DEVICE_ATTR_WO(unbind_device);
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+static struct device tick_bc_dev = {
+	.init_name	= "broadcast",
+	.id		= 0,
+	.bus		= &clockevents_subsys,
+};
+
+static struct tick_device *tick_get_tick_dev(struct device *dev)
+{
+	return dev == &tick_bc_dev ? tick_get_broadcast_device() :
+		&per_cpu(tick_cpu_device, dev->id);
+}
+
+static __init int tick_broadcast_init_sysfs(void)
+{
+	int err = device_register(&tick_bc_dev);
+
+	if (!err)
+		err = device_create_file(&tick_bc_dev, &dev_attr_current_device);
+	return err;
+}
+#else
+static struct tick_device *tick_get_tick_dev(struct device *dev)
+{
+	return &per_cpu(tick_cpu_device, dev->id);
+}
+static inline int tick_broadcast_init_sysfs(void) { return 0; }
+#endif
+
+static int __init tick_init_sysfs(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct device *dev = &per_cpu(tick_percpu_dev, cpu);
+		int err;
+
+		dev->id = cpu;
+		dev->bus = &clockevents_subsys;
+		err = device_register(dev);
+		if (!err)
+			err = device_create_file(dev, &dev_attr_current_device);
+		if (!err)
+			err = device_create_file(dev, &dev_attr_unbind_device);
+		if (err)
+			return err;
+	}
+	return tick_broadcast_init_sysfs();
+}
+
+static int __init clockevents_init_sysfs(void)
+{
+	int err = subsys_system_register(&clockevents_subsys, NULL);
+
+	if (!err)
+		err = tick_init_sysfs();
+	return err;
+}
+device_initcall(clockevents_init_sysfs);
+#endif /* SYSFS */

linux-7.2.3/kernel/time/clocksource-wdtest.c

@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Unit test for the clocksource watchdog.
+ *
+ * Copyright (C) 2021 Facebook, Inc.
+ * Copyright (C) 2026 Intel Corp.
+ *
+ * Author: Paul E. McKenney <paulmck@kernel.org>
+ * Author: Thomas Gleixner <tglx@kernel.org>
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clocksource.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+
+#include "tick-internal.h"
+#include "timekeeping_internal.h"
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Clocksource watchdog unit test");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@kernel.org>");
+MODULE_AUTHOR("Thomas Gleixner <tglx@kernel.org>");
+
+enum wdtest_states {
+	WDTEST_INJECT_NONE,
+	WDTEST_INJECT_DELAY,
+	WDTEST_INJECT_POSITIVE,
+	WDTEST_INJECT_NEGATIVE,
+	WDTEST_INJECT_PERCPU	= 0x100,
+};
+
+static enum wdtest_states wdtest_state;
+static unsigned long wdtest_test_count;
+static ktime_t wdtest_last_ts, wdtest_offset;
+
+#define SHIFT_4000PPM	8
+
+static ktime_t wdtest_get_offset(struct clocksource *cs)
+{
+	if (wdtest_state < WDTEST_INJECT_PERCPU)
+		return wdtest_test_count & 0x1 ? 0 : wdtest_offset >> SHIFT_4000PPM;
+
+	/* Only affect the readout of the "remote" CPU */
+	return cs->wd_cpu == smp_processor_id() ? 0 : NSEC_PER_MSEC;
+}
+
+static u64 wdtest_ktime_read(struct clocksource *cs)
+{
+	ktime_t now = ktime_get_raw_fast_ns();
+	ktime_t intv = now - wdtest_last_ts;
+
+	/*
+	 * Only increment the test counter once per watchdog interval and
+	 * store the interval for the offset calculation of this step. This
+	 * guarantees a consistent behaviour even if the other side needs
+	 * to repeat due to a watchdog read timeout.
+	 */
+	if (intv > (NSEC_PER_SEC / 4)) {
+		WRITE_ONCE(wdtest_test_count, wdtest_test_count + 1);
+		wdtest_last_ts = now;
+		wdtest_offset = intv;
+	}
+
+	switch (wdtest_state & ~WDTEST_INJECT_PERCPU) {
+	case WDTEST_INJECT_POSITIVE:
+		return now + wdtest_get_offset(cs);
+	case WDTEST_INJECT_NEGATIVE:
+		return now - wdtest_get_offset(cs);
+	case WDTEST_INJECT_DELAY:
+		udelay(500);
+		return now;
+	default:
+		return now;
+	}
+}
+
+#define KTIME_FLAGS (CLOCK_SOURCE_IS_CONTINUOUS |	\
+		     CLOCK_SOURCE_CALIBRATED |		\
+		     CLOCK_SOURCE_MUST_VERIFY |		\
+		     CLOCK_SOURCE_WDTEST)
+
+static struct clocksource clocksource_wdtest_ktime = {
+	.name			= "wdtest-ktime",
+	.rating			= 10,
+	.read			= wdtest_ktime_read,
+	.mask			= CLOCKSOURCE_MASK(64),
+	.flags			= KTIME_FLAGS,
+	.list			= LIST_HEAD_INIT(clocksource_wdtest_ktime.list),
+};
+
+static void wdtest_clocksource_reset(enum wdtest_states which, bool percpu)
+{
+	clocksource_unregister(&clocksource_wdtest_ktime);
+
+	pr_info("Test: State %d percpu %d\n", which, percpu);
+
+	wdtest_state = which;
+	if (percpu)
+		wdtest_state |= WDTEST_INJECT_PERCPU;
+	wdtest_test_count = 0;
+	wdtest_last_ts = 0;
+
+	clocksource_wdtest_ktime.rating = 10;
+	clocksource_wdtest_ktime.flags = KTIME_FLAGS;
+	if (percpu)
+		clocksource_wdtest_ktime.flags |= CLOCK_SOURCE_WDTEST_PERCPU;
+	clocksource_register_khz(&clocksource_wdtest_ktime, 1000 * 1000);
+}
+
+static bool wdtest_execute(enum wdtest_states which, bool percpu, unsigned int expect,
+			   unsigned long calls)
+{
+	wdtest_clocksource_reset(which, percpu);
+
+	for (; READ_ONCE(wdtest_test_count) < calls; msleep(100)) {
+		unsigned int flags = READ_ONCE(clocksource_wdtest_ktime.flags);
+
+		if (kthread_should_stop())
+			return false;
+
+		if (flags & CLOCK_SOURCE_UNSTABLE) {
+			if (expect & CLOCK_SOURCE_UNSTABLE)
+				return true;
+			pr_warn("Fail: Unexpected unstable\n");
+			return false;
+		}
+		if (flags & CLOCK_SOURCE_VALID_FOR_HRES) {
+			if (expect & CLOCK_SOURCE_VALID_FOR_HRES)
+				return true;
+			pr_warn("Fail: Unexpected valid for highres\n");
+			return false;
+		}
+	}
+
+	if (!expect)
+		return true;
+
+	pr_warn("Fail: Timed out\n");
+	return false;
+}
+
+static bool wdtest_run(bool percpu)
+{
+	if (!wdtest_execute(WDTEST_INJECT_NONE, percpu, CLOCK_SOURCE_VALID_FOR_HRES, 8))
+		return false;
+
+	if (!wdtest_execute(WDTEST_INJECT_DELAY, percpu, 0, 4))
+		return false;
+
+	if (!wdtest_execute(WDTEST_INJECT_POSITIVE, percpu, CLOCK_SOURCE_UNSTABLE, 8))
+		return false;
+
+	if (!wdtest_execute(WDTEST_INJECT_NEGATIVE, percpu, CLOCK_SOURCE_UNSTABLE, 8))
+		return false;
+
+	return true;
+}
+
+static int wdtest_func(void *arg)
+{
+	clocksource_register_khz(&clocksource_wdtest_ktime, 1000 * 1000);
+	if (wdtest_run(false)) {
+		if (wdtest_run(true))
+			pr_info("Success: All tests passed\n");
+	}
+	clocksource_unregister(&clocksource_wdtest_ktime);
+
+	if (!IS_MODULE(CONFIG_TEST_CLOCKSOURCE_WATCHDOG))
+		return 0;
+
+	while (!kthread_should_stop())
+		schedule_timeout_interruptible(3600 * HZ);
+	return 0;
+}
+
+static struct task_struct *wdtest_thread;
+
+static int __init clocksource_wdtest_init(void)
+{
+	struct task_struct *t = kthread_run(wdtest_func, NULL, "wdtest");
+
+	if (IS_ERR(t)) {
+		pr_warn("Failed to create wdtest kthread.\n");
+		return PTR_ERR(t);
+	}
+	wdtest_thread = t;
+	return 0;
+}
+module_init(clocksource_wdtest_init);
+
+static void clocksource_wdtest_cleanup(void)
+{
+	if (wdtest_thread)
+		kthread_stop(wdtest_thread);
+}
+module_exit(clocksource_wdtest_cleanup);

linux-7.2.3/kernel/time/itimer.c

@@ -0,0 +1,422 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 1992 Darren Senn
+ */
+
+/* These are all the functions necessary to implement itimers */
+
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/syscalls.h>
+#include <linux/time.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/cputime.h>
+#include <linux/posix-timers.h>
+#include <linux/hrtimer.h>
+#include <trace/events/timer.h>
+#include <linux/compat.h>
+
+#include <linux/uaccess.h>
+
+/**
+ * itimer_get_remtime - get remaining time for the timer
+ *
+ * @timer: the timer to read
+ *
+ * Returns the delta between the expiry time and now, which can be
+ * less than zero or 1usec for an pending expired timer
+ */
+static struct timespec64 itimer_get_remtime(struct hrtimer *timer)
+{
+	ktime_t rem = __hrtimer_get_remaining(timer, true);
+
+	/*
+	 * Racy but safe: if the itimer expires after the above
+	 * hrtimer_get_remtime() call but before this condition
+	 * then we return 0 - which is correct.
+	 */
+	if (hrtimer_active(timer)) {
+		if (rem <= 0)
+			rem = NSEC_PER_USEC;
+	} else
+		rem = 0;
+
+	return ktime_to_timespec64(rem);
+}
+
+static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+			   struct itimerspec64 *const value)
+{
+	u64 val, interval;
+	struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+	spin_lock_irq(&tsk->sighand->siglock);
+
+	val = it->expires;
+	interval = it->incr;
+	if (val) {
+		u64 t, samples[CPUCLOCK_MAX];
+
+		thread_group_sample_cputime(tsk, samples);
+		t = samples[clock_id];
+
+		if (val < t)
+			/* about to fire */
+			val = TICK_NSEC;
+		else
+			val -= t;
+	}
+
+	spin_unlock_irq(&tsk->sighand->siglock);
+
+	value->it_value = ns_to_timespec64(val);
+	value->it_interval = ns_to_timespec64(interval);
+}
+
+static int do_getitimer(int which, struct itimerspec64 *value)
+{
+	struct task_struct *tsk = current;
+
+	switch (which) {
+	case ITIMER_REAL:
+		spin_lock_irq(&tsk->sighand->siglock);
+		value->it_value = itimer_get_remtime(&tsk->signal->real_timer);
+		value->it_interval =
+			ktime_to_timespec64(tsk->signal->it_real_incr);
+		spin_unlock_irq(&tsk->sighand->siglock);
+		break;
+	case ITIMER_VIRTUAL:
+		get_cpu_itimer(tsk, CPUCLOCK_VIRT, value);
+		break;
+	case ITIMER_PROF:
+		get_cpu_itimer(tsk, CPUCLOCK_PROF, value);
+		break;
+	default:
+		return(-EINVAL);
+	}
+	return 0;
+}
+
+static int put_itimerval(struct __kernel_old_itimerval __user *o,
+			 const struct itimerspec64 *i)
+{
+	struct __kernel_old_itimerval v;
+
+	v.it_interval.tv_sec = i->it_interval.tv_sec;
+	v.it_interval.tv_usec = i->it_interval.tv_nsec / NSEC_PER_USEC;
+	v.it_value.tv_sec = i->it_value.tv_sec;
+	v.it_value.tv_usec = i->it_value.tv_nsec / NSEC_PER_USEC;
+	return copy_to_user(o, &v, sizeof(struct __kernel_old_itimerval)) ? -EFAULT : 0;
+}
+
+
+SYSCALL_DEFINE2(getitimer, int, which, struct __kernel_old_itimerval __user *, value)
+{
+	struct itimerspec64 get_buffer;
+	int error = do_getitimer(which, &get_buffer);
+
+	if (!error && put_itimerval(value, &get_buffer))
+		error = -EFAULT;
+	return error;
+}
+
+#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
+struct old_itimerval32 {
+	struct old_timeval32	it_interval;
+	struct old_timeval32	it_value;
+};
+
+static int put_old_itimerval32(struct old_itimerval32 __user *o,
+			       const struct itimerspec64 *i)
+{
+	struct old_itimerval32 v32;
+
+	v32.it_interval.tv_sec = i->it_interval.tv_sec;
+	v32.it_interval.tv_usec = i->it_interval.tv_nsec / NSEC_PER_USEC;
+	v32.it_value.tv_sec = i->it_value.tv_sec;
+	v32.it_value.tv_usec = i->it_value.tv_nsec / NSEC_PER_USEC;
+	return copy_to_user(o, &v32, sizeof(struct old_itimerval32)) ? -EFAULT : 0;
+}
+
+COMPAT_SYSCALL_DEFINE2(getitimer, int, which,
+		       struct old_itimerval32 __user *, value)
+{
+	struct itimerspec64 get_buffer;
+	int error = do_getitimer(which, &get_buffer);
+
+	if (!error && put_old_itimerval32(value, &get_buffer))
+		error = -EFAULT;
+	return error;
+}
+#endif
+
+/*
+ * Invoked from dequeue_signal() when SIG_ALRM is delivered.
+ *
+ * Restart the ITIMER_REAL timer if it is armed as periodic timer.  Doing
+ * this in the signal delivery path instead of self rearming prevents a DoS
+ * with small increments in the high reolution timer case and reduces timer
+ * noise in general.
+ */
+void posixtimer_rearm_itimer(struct task_struct *tsk)
+{
+	struct hrtimer *tmr = &tsk->signal->real_timer;
+
+	if (!hrtimer_is_queued(tmr) && tsk->signal->it_real_incr != 0) {
+		hrtimer_forward_now(tmr, tsk->signal->it_real_incr);
+		hrtimer_restart(tmr);
+	}
+}
+
+/*
+ * Interval timers are restarted in the signal delivery path.  See
+ * posixtimer_rearm_itimer().
+ */
+enum hrtimer_restart it_real_fn(struct hrtimer *timer)
+{
+	struct signal_struct *sig =
+		container_of(timer, struct signal_struct, real_timer);
+	struct pid *leader_pid = sig->pids[PIDTYPE_TGID];
+
+	trace_itimer_expire(ITIMER_REAL, leader_pid, 0);
+	kill_pid_info(SIGALRM, SEND_SIG_PRIV, leader_pid);
+
+	return HRTIMER_NORESTART;
+}
+
+static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+			   const struct itimerspec64 *const value,
+			   struct itimerspec64 *const ovalue)
+{
+	u64 oval, nval, ointerval, ninterval;
+	struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+	nval = timespec64_to_ns(&value->it_value);
+	ninterval = timespec64_to_ns(&value->it_interval);
+
+	spin_lock_irq(&tsk->sighand->siglock);
+
+	oval = it->expires;
+	ointerval = it->incr;
+	if (oval || nval) {
+		if (nval > 0)
+			nval += TICK_NSEC;
+		set_process_cpu_timer(tsk, clock_id, &nval, &oval);
+	}
+	it->expires = nval;
+	it->incr = ninterval;
+	trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
+			   ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
+
+	spin_unlock_irq(&tsk->sighand->siglock);
+
+	if (ovalue) {
+		ovalue->it_value = ns_to_timespec64(oval);
+		ovalue->it_interval = ns_to_timespec64(ointerval);
+	}
+}
+
+/*
+ * Returns true if the timeval is in canonical form
+ */
+#define timeval_valid(t) \
+	(((t)->tv_sec >= 0) && (((unsigned long) (t)->tv_usec) < USEC_PER_SEC))
+
+static int do_setitimer(int which, struct itimerspec64 *value,
+			struct itimerspec64 *ovalue)
+{
+	struct task_struct *tsk = current;
+	struct hrtimer *timer;
+	ktime_t expires;
+
+	switch (which) {
+	case ITIMER_REAL:
+again:
+		spin_lock_irq(&tsk->sighand->siglock);
+		timer = &tsk->signal->real_timer;
+		if (ovalue) {
+			ovalue->it_value = itimer_get_remtime(timer);
+			ovalue->it_interval
+				= ktime_to_timespec64(tsk->signal->it_real_incr);
+		}
+		/* We are sharing ->siglock with it_real_fn() */
+		if (hrtimer_try_to_cancel(timer) < 0) {
+			spin_unlock_irq(&tsk->sighand->siglock);
+			hrtimer_cancel_wait_running(timer);
+			goto again;
+		}
+		expires = timespec64_to_ktime(value->it_value);
+		if (expires != 0) {
+			tsk->signal->it_real_incr =
+				timespec64_to_ktime(value->it_interval);
+			hrtimer_start(timer, expires, HRTIMER_MODE_REL);
+		} else
+			tsk->signal->it_real_incr = 0;
+
+		trace_itimer_state(ITIMER_REAL, value, 0);
+		spin_unlock_irq(&tsk->sighand->siglock);
+		break;
+	case ITIMER_VIRTUAL:
+		set_cpu_itimer(tsk, CPUCLOCK_VIRT, value, ovalue);
+		break;
+	case ITIMER_PROF:
+		set_cpu_itimer(tsk, CPUCLOCK_PROF, value, ovalue);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+#ifdef CONFIG_SECURITY_SELINUX
+void clear_itimer(void)
+{
+	struct itimerspec64 v = {};
+	int i;
+
+	for (i = 0; i < 3; i++)
+		do_setitimer(i, &v, NULL);
+}
+#endif
+
+#ifdef __ARCH_WANT_SYS_ALARM
+
+/**
+ * alarm_setitimer - set alarm in seconds
+ *
+ * @seconds:	number of seconds until alarm
+ *		0 disables the alarm
+ *
+ * Returns the remaining time in seconds of a pending timer or 0 when
+ * the timer is not active.
+ *
+ * On 32 bit machines the seconds value is limited to (INT_MAX/2) to avoid
+ * negative timeval settings which would cause immediate expiry.
+ */
+static unsigned int alarm_setitimer(unsigned int seconds)
+{
+	struct itimerspec64 it_new, it_old;
+
+#if BITS_PER_LONG < 64
+	if (seconds > INT_MAX)
+		seconds = INT_MAX;
+#endif
+	it_new.it_value.tv_sec = seconds;
+	it_new.it_value.tv_nsec = 0;
+	it_new.it_interval.tv_sec = it_new.it_interval.tv_nsec = 0;
+
+	do_setitimer(ITIMER_REAL, &it_new, &it_old);
+
+	/*
+	 * We can't return 0 if we have an alarm pending ...  And we'd
+	 * better return too much than too little anyway
+	 */
+	if ((!it_old.it_value.tv_sec && it_old.it_value.tv_nsec) ||
+	      it_old.it_value.tv_nsec >= (NSEC_PER_SEC / 2))
+		it_old.it_value.tv_sec++;
+
+	return it_old.it_value.tv_sec;
+}
+
+/*
+ * For backwards compatibility?  This can be done in libc so Alpha
+ * and all newer ports shouldn't need it.
+ */
+SYSCALL_DEFINE1(alarm, unsigned int, seconds)
+{
+	return alarm_setitimer(seconds);
+}
+
+#endif
+
+static int get_itimerval(struct itimerspec64 *o, const struct __kernel_old_itimerval __user *i)
+{
+	struct __kernel_old_itimerval v;
+
+	if (copy_from_user(&v, i, sizeof(struct __kernel_old_itimerval)))
+		return -EFAULT;
+
+	/* Validate the timevals in value. */
+	if (!timeval_valid(&v.it_value) ||
+	    !timeval_valid(&v.it_interval))
+		return -EINVAL;
+
+	o->it_interval.tv_sec = v.it_interval.tv_sec;
+	o->it_interval.tv_nsec = v.it_interval.tv_usec * NSEC_PER_USEC;
+	o->it_value.tv_sec = v.it_value.tv_sec;
+	o->it_value.tv_nsec = v.it_value.tv_usec * NSEC_PER_USEC;
+	return 0;
+}
+
+SYSCALL_DEFINE3(setitimer, int, which, struct __kernel_old_itimerval __user *, value,
+		struct __kernel_old_itimerval __user *, ovalue)
+{
+	struct itimerspec64 set_buffer, get_buffer;
+	int error;
+
+	if (value) {
+		error = get_itimerval(&set_buffer, value);
+		if (error)
+			return error;
+	} else {
+		memset(&set_buffer, 0, sizeof(set_buffer));
+		printk_once(KERN_WARNING "%s calls setitimer() with new_value NULL pointer."
+			    " Misfeature support will be removed\n",
+			    current->comm);
+	}
+
+	error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL);
+	if (error || !ovalue)
+		return error;
+
+	if (put_itimerval(ovalue, &get_buffer))
+		return -EFAULT;
+	return 0;
+}
+
+#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
+static int get_old_itimerval32(struct itimerspec64 *o, const struct old_itimerval32 __user *i)
+{
+	struct old_itimerval32 v32;
+
+	if (copy_from_user(&v32, i, sizeof(struct old_itimerval32)))
+		return -EFAULT;
+
+	/* Validate the timevals in value.  */
+	if (!timeval_valid(&v32.it_value) ||
+	    !timeval_valid(&v32.it_interval))
+		return -EINVAL;
+
+	o->it_interval.tv_sec = v32.it_interval.tv_sec;
+	o->it_interval.tv_nsec = v32.it_interval.tv_usec * NSEC_PER_USEC;
+	o->it_value.tv_sec = v32.it_value.tv_sec;
+	o->it_value.tv_nsec = v32.it_value.tv_usec * NSEC_PER_USEC;
+	return 0;
+}
+
+COMPAT_SYSCALL_DEFINE3(setitimer, int, which,
+		       struct old_itimerval32 __user *, value,
+		       struct old_itimerval32 __user *, ovalue)
+{
+	struct itimerspec64 set_buffer, get_buffer;
+	int error;
+
+	if (value) {
+		error = get_old_itimerval32(&set_buffer, value);
+		if (error)
+			return error;
+	} else {
+		memset(&set_buffer, 0, sizeof(set_buffer));
+		printk_once(KERN_WARNING "%s calls setitimer() with new_value NULL pointer."
+			    " Misfeature support will be removed\n",
+			    current->comm);
+	}
+
+	error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL);
+	if (error || !ovalue)
+		return error;
+	if (put_old_itimerval32(ovalue, &get_buffer))
+		return -EFAULT;
+	return 0;
+}
+#endif

linux-7.2.3/kernel/time/jiffies.c

@@ -0,0 +1,316 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * This file contains the jiffies based clocksource.
+ *
+ * Copyright (C) 2004, 2005 IBM, John Stultz (johnstul@us.ibm.com)
+ */
+#include <linux/clocksource.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include "timekeeping.h"
+#include "tick-internal.h"
+
+
+static u64 jiffies_read(struct clocksource *cs)
+{
+	return (u64) jiffies;
+}
+
+/*
+ * The Jiffies based clocksource is the lowest common
+ * denominator clock source which should function on
+ * all systems. It has the same coarse resolution as
+ * the timer interrupt frequency HZ and it suffers
+ * inaccuracies caused by missed or lost timer
+ * interrupts and the inability for the timer
+ * interrupt hardware to accurately tick at the
+ * requested HZ value. It is also not recommended
+ * for "tick-less" systems.
+ */
+static struct clocksource clocksource_jiffies = {
+	.name			= "jiffies",
+	.rating			= 1, /* lowest valid rating*/
+	.read			= jiffies_read,
+	.mask			= CLOCKSOURCE_MASK(32),
+	.mult			= TICK_NSEC << JIFFIES_SHIFT, /* details above */
+	.shift			= JIFFIES_SHIFT,
+	.max_cycles		= 10,
+};
+
+__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock);
+__cacheline_aligned_in_smp seqcount_raw_spinlock_t jiffies_seq =
+	SEQCNT_RAW_SPINLOCK_ZERO(jiffies_seq, &jiffies_lock);
+
+#if (BITS_PER_LONG < 64)
+u64 get_jiffies_64(void)
+{
+	unsigned int seq;
+	u64 ret;
+
+	do {
+		seq = read_seqcount_begin(&jiffies_seq);
+		ret = jiffies_64;
+	} while (read_seqcount_retry(&jiffies_seq, seq));
+	return ret;
+}
+EXPORT_SYMBOL(get_jiffies_64);
+#endif
+
+EXPORT_SYMBOL(jiffies);
+
+static bool cs_jiffies_registered __initdata;
+
+struct clocksource * __init __weak clocksource_default_clock(void)
+{
+	if (!cs_jiffies_registered) {
+		__clocksource_register(&clocksource_jiffies);
+		cs_jiffies_registered = true;
+	}
+	return &clocksource_jiffies;
+}
+
+static struct clocksource refined_jiffies;
+
+void __init register_refined_jiffies(long cycles_per_second)
+{
+	u64 nsec_per_tick, shift_hz;
+	long cycles_per_tick;
+
+	refined_jiffies = clocksource_jiffies;
+	refined_jiffies.name = "refined-jiffies";
+	refined_jiffies.rating++;
+
+	/* Calc cycles per tick */
+	cycles_per_tick = (cycles_per_second + HZ/2)/HZ;
+	/* shift_hz stores hz<<8 for extra accuracy */
+	shift_hz = (u64)cycles_per_second << 8;
+	shift_hz += cycles_per_tick/2;
+	do_div(shift_hz, cycles_per_tick);
+	/* Calculate nsec_per_tick using shift_hz */
+	nsec_per_tick = (u64)NSEC_PER_SEC << 8;
+	nsec_per_tick += (u32)shift_hz/2;
+	do_div(nsec_per_tick, (u32)shift_hz);
+
+	refined_jiffies.mult = ((u32)nsec_per_tick) << JIFFIES_SHIFT;
+
+	__clocksource_register(&refined_jiffies);
+}
+
+#ifdef CONFIG_PROC_SYSCTL
+static ulong mult_hz(const ulong val)
+{
+	return val * HZ;
+}
+
+static ulong div_hz(const ulong val)
+{
+	return val / HZ;
+}
+
+static int sysctl_u2k_int_conv_hz(const bool *negp, const ulong *u_ptr, int *k_ptr)
+{
+	return proc_int_u2k_conv_uop(u_ptr, k_ptr, negp, mult_hz);
+}
+
+static int sysctl_k2u_int_conv_hz(bool *negp, ulong *u_ptr, const int *k_ptr)
+{
+	return proc_int_k2u_conv_kop(u_ptr, k_ptr, negp, div_hz);
+}
+
+static int sysctl_u2k_int_conv_userhz(const bool *negp, const ulong *u_ptr, int *k_ptr)
+{
+	return proc_int_u2k_conv_uop(u_ptr, k_ptr, negp, clock_t_to_jiffies);
+}
+
+static ulong sysctl_jiffies_to_clock_t(const ulong val)
+{
+	return jiffies_to_clock_t(val);
+}
+
+static int sysctl_k2u_int_conv_userhz(bool *negp, ulong *u_ptr, const int *k_ptr)
+{
+	return proc_int_k2u_conv_kop(u_ptr, k_ptr, negp, sysctl_jiffies_to_clock_t);
+}
+
+static ulong sysctl_msecs_to_jiffies(const ulong val)
+{
+	return msecs_to_jiffies(val);
+}
+
+static int sysctl_u2k_int_conv_ms(const bool *negp, const ulong *u_ptr, int *k_ptr)
+{
+	return proc_int_u2k_conv_uop(u_ptr, k_ptr, negp, sysctl_msecs_to_jiffies);
+}
+
+static ulong sysctl_jiffies_to_msecs(const ulong val)
+{
+	return jiffies_to_msecs(val);
+}
+
+static int sysctl_k2u_int_conv_ms(bool *negp, ulong *u_ptr, const int *k_ptr)
+{
+	return proc_int_k2u_conv_kop(u_ptr, k_ptr, negp, sysctl_jiffies_to_msecs);
+}
+
+static int do_proc_int_conv_jiffies(bool *negp, ulong *u_ptr, int *k_ptr,
+				    int dir, const struct ctl_table *tbl)
+{
+	return proc_int_conv(negp, u_ptr, k_ptr, dir, tbl, false,
+			     sysctl_u2k_int_conv_hz, sysctl_k2u_int_conv_hz);
+}
+
+static int do_proc_int_conv_userhz_jiffies(bool *negp, ulong *u_ptr,
+					   int *k_ptr, int dir,
+					   const struct ctl_table *tbl)
+{
+	return proc_int_conv(negp, u_ptr, k_ptr, dir, tbl, false,
+			     sysctl_u2k_int_conv_userhz,
+			     sysctl_k2u_int_conv_userhz);
+}
+
+static int do_proc_int_conv_ms_jiffies(bool *negp, ulong *u_ptr, int *k_ptr,
+				       int dir, const struct ctl_table *tbl)
+{
+	return proc_int_conv(negp, u_ptr, k_ptr, dir, tbl, false,
+			     sysctl_u2k_int_conv_ms, sysctl_k2u_int_conv_ms);
+}
+
+static int do_proc_int_conv_ms_jiffies_minmax(bool *negp, ulong *u_ptr,
+					      int *k_ptr, int dir,
+					      const struct ctl_table *tbl)
+{
+	return proc_int_conv(negp, u_ptr, k_ptr, dir, tbl, false,
+			     sysctl_u2k_int_conv_ms, sysctl_k2u_int_conv_ms);
+}
+
+#else // CONFIG_PROC_SYSCTL
+static int do_proc_int_conv_jiffies(bool *negp, ulong *u_ptr, int *k_ptr,
+				    int dir, const struct ctl_table *tbl)
+{
+	return -ENOSYS;
+}
+
+static int do_proc_int_conv_userhz_jiffies(bool *negp, ulong *u_ptr,
+					   int *k_ptr, int dir,
+					   const struct ctl_table *tbl)
+{
+	return -ENOSYS;
+}
+
+static int do_proc_int_conv_ms_jiffies(bool *negp, ulong *u_ptr, int *k_ptr,
+				       int dir, const struct ctl_table *tbl)
+{
+	return -ENOSYS;
+}
+
+static int do_proc_int_conv_ms_jiffies_minmax(bool *negp, ulong *u_ptr,
+					      int *k_ptr, int dir,
+					      const struct ctl_table *tbl)
+{
+	return -ENOSYS;
+}
+#endif
+
+/**
+ * proc_dointvec_jiffies - read a vector of integers as seconds
+ * @table: the sysctl table
+ * @dir: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string.
+ * The values read are assumed to be in seconds, and are converted into
+ * jiffies.
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec_jiffies(const struct ctl_table *table, int dir,
+			  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return proc_dointvec_conv(table, dir, buffer, lenp, ppos,
+				  do_proc_int_conv_jiffies);
+}
+EXPORT_SYMBOL(proc_dointvec_jiffies);
+
+/**
+ * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds
+ * @table: the sysctl table
+ * @dir: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: pointer to the file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string.
+ * The values read are assumed to be in 1/USER_HZ seconds, and
+ * are converted into jiffies.
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int dir,
+				 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return proc_dointvec_conv(table, dir, buffer, lenp, ppos,
+				  do_proc_int_conv_userhz_jiffies);
+}
+EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
+
+/**
+ * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds
+ * @table: the sysctl table
+ * @dir: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: the current position in the file
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string.
+ * The values read are assumed to be in 1/1000 seconds, and
+ * are converted into jiffies.
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec_ms_jiffies(const struct ctl_table *table, int dir, void *buffer,
+		size_t *lenp, loff_t *ppos)
+{
+	return proc_dointvec_conv(table, dir, buffer, lenp, ppos,
+				  do_proc_int_conv_ms_jiffies);
+}
+EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
+
+int proc_dointvec_ms_jiffies_minmax(const struct ctl_table *table, int dir,
+			  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return proc_dointvec_conv(table, dir, buffer, lenp, ppos,
+				  do_proc_int_conv_ms_jiffies_minmax);
+}
+
+/**
+ * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values
+ * @table: the sysctl table
+ * @dir: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long
+ * values from/to the user buffer, treated as an ASCII string. The values
+ * are treated as milliseconds, and converted to jiffies when they are stored.
+ *
+ * This routine will ensure the values are within the range specified by
+ * table->extra1 (min) and table->extra2 (max).
+ *
+ * Returns 0 on success.
+ */
+int proc_doulongvec_ms_jiffies_minmax(const struct ctl_table *table, int dir,
+				      void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return proc_doulongvec_minmax_conv(table, dir, buffer, lenp, ppos,
+					   HZ, 1000l);
+}
+EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);
+

linux-7.2.3/kernel/time/namespace.c

@@ -0,0 +1,360 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: Andrei Vagin <avagin@openvz.org>
+ * Author: Dmitry Safonov <dima@arista.com>
+ */
+
+#include <linux/time_namespace.h>
+#include <linux/user_namespace.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/clocksource.h>
+#include <linux/seq_file.h>
+#include <linux/proc_ns.h>
+#include <linux/export.h>
+#include <linux/nstree.h>
+#include <linux/time.h>
+#include <linux/slab.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <linux/mm.h>
+#include <linux/cleanup.h>
+
+#include "namespace_internal.h"
+
+ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim,
+				struct timens_offsets *ns_offsets)
+{
+	ktime_t offset;
+
+	switch (clockid) {
+	case CLOCK_MONOTONIC:
+		offset = timespec64_to_ktime(ns_offsets->monotonic);
+		break;
+	case CLOCK_BOOTTIME:
+	case CLOCK_BOOTTIME_ALARM:
+		offset = timespec64_to_ktime(ns_offsets->boottime);
+		break;
+	default:
+		return tim;
+	}
+
+	/*
+	 * Check that @tim value is in [offset, KTIME_MAX + offset]
+	 * and subtract offset.
+	 */
+	if (tim < offset) {
+		/*
+		 * User can specify @tim *absolute* value - if it's lesser than
+		 * the time namespace's offset - it's already expired.
+		 */
+		tim = 0;
+	} else {
+		tim = ktime_sub(tim, offset);
+		if (unlikely(tim > KTIME_MAX))
+			tim = KTIME_MAX;
+	}
+
+	return tim;
+}
+EXPORT_SYMBOL_GPL(do_timens_ktime_to_host);
+
+static struct ucounts *inc_time_namespaces(struct user_namespace *ns)
+{
+	return inc_ucount(ns, current_euid(), UCOUNT_TIME_NAMESPACES);
+}
+
+static void dec_time_namespaces(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_TIME_NAMESPACES);
+}
+
+/**
+ * clone_time_ns - Clone a time namespace
+ * @user_ns:	User namespace which owns a new namespace.
+ * @old_ns:	Namespace to clone
+ *
+ * Clone @old_ns and set the clone refcount to 1
+ *
+ * Return: The new namespace or ERR_PTR.
+ */
+static struct time_namespace *clone_time_ns(struct user_namespace *user_ns,
+					  struct time_namespace *old_ns)
+{
+	struct time_namespace *ns;
+	struct ucounts *ucounts;
+	int err;
+
+	err = -ENOSPC;
+	ucounts = inc_time_namespaces(user_ns);
+	if (!ucounts)
+		goto fail;
+
+	err = -ENOMEM;
+	ns = kzalloc_obj(*ns, GFP_KERNEL_ACCOUNT);
+	if (!ns)
+		goto fail_dec;
+
+	err = timens_vdso_alloc_vvar_page(ns);
+	if (err)
+		goto fail_free;
+
+	err = ns_common_init(ns);
+	if (err)
+		goto fail_free_page;
+
+	ns->ucounts = ucounts;
+	ns->user_ns = get_user_ns(user_ns);
+	ns->offsets = old_ns->offsets;
+	ns->frozen_offsets = false;
+	ns_tree_add(ns);
+	return ns;
+
+fail_free_page:
+	timens_vdso_free_vvar_page(ns);
+fail_free:
+	kfree(ns);
+fail_dec:
+	dec_time_namespaces(ucounts);
+fail:
+	return ERR_PTR(err);
+}
+
+/**
+ * copy_time_ns - Create timens_for_children from @old_ns
+ * @flags:	Cloning flags
+ * @user_ns:	User namespace which owns a new namespace.
+ * @old_ns:	Namespace to clone
+ *
+ * If CLONE_NEWTIME specified in @flags, creates a new timens_for_children;
+ * adds a refcounter to @old_ns otherwise.
+ *
+ * Return: timens_for_children namespace or ERR_PTR.
+ */
+struct time_namespace *copy_time_ns(u64 flags,
+	struct user_namespace *user_ns, struct time_namespace *old_ns)
+{
+	if (!(flags & CLONE_NEWTIME))
+		return get_time_ns(old_ns);
+
+	return clone_time_ns(user_ns, old_ns);
+}
+
+DEFINE_MUTEX(timens_offset_lock);
+
+void free_time_ns(struct time_namespace *ns)
+{
+	ns_tree_remove(ns);
+	dec_time_namespaces(ns->ucounts);
+	put_user_ns(ns->user_ns);
+	ns_common_free(ns);
+	timens_vdso_free_vvar_page(ns);
+	/* Concurrent nstree traversal depends on a grace period. */
+	kfree_rcu(ns, ns.ns_rcu);
+}
+
+static struct ns_common *timens_get(struct task_struct *task)
+{
+	struct time_namespace *ns;
+	struct nsproxy *nsproxy;
+
+	guard(task_lock)(task);
+	nsproxy = task->nsproxy;
+	if (!nsproxy)
+		return NULL;
+
+	ns = nsproxy->time_ns;
+	get_time_ns(ns);
+	return &ns->ns;
+}
+
+static struct ns_common *timens_for_children_get(struct task_struct *task)
+{
+	struct time_namespace *ns;
+	struct nsproxy *nsproxy;
+
+	guard(task_lock)(task);
+	nsproxy = task->nsproxy;
+	if (!nsproxy)
+		return NULL;
+
+	ns = nsproxy->time_ns_for_children;
+	get_time_ns(ns);
+	return &ns->ns;
+}
+
+static void timens_put(struct ns_common *ns)
+{
+	put_time_ns(to_time_ns(ns));
+}
+
+static int timens_install(struct nsset *nsset, struct ns_common *new)
+{
+	struct nsproxy *nsproxy = nsset->nsproxy;
+	struct time_namespace *ns = to_time_ns(new);
+
+	if (!current_is_single_threaded())
+		return -EUSERS;
+
+	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
+	    !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	get_time_ns(ns);
+	put_time_ns(nsproxy->time_ns);
+	nsproxy->time_ns = ns;
+
+	get_time_ns(ns);
+	put_time_ns(nsproxy->time_ns_for_children);
+	nsproxy->time_ns_for_children = ns;
+	return 0;
+}
+
+void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk)
+{
+	struct ns_common *nsc = &nsproxy->time_ns_for_children->ns;
+	struct time_namespace *ns = to_time_ns(nsc);
+
+	/* create_new_namespaces() already incremented the ref counter */
+	if (nsproxy->time_ns == nsproxy->time_ns_for_children)
+		return;
+
+	get_time_ns(ns);
+	put_time_ns(nsproxy->time_ns);
+	nsproxy->time_ns = ns;
+
+	timens_commit(tsk, ns);
+}
+
+static struct user_namespace *timens_owner(struct ns_common *ns)
+{
+	return to_time_ns(ns)->user_ns;
+}
+
+static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts)
+{
+	char *clock;
+
+	switch (clockid) {
+	case CLOCK_BOOTTIME:
+		clock = "boottime";
+		break;
+	case CLOCK_MONOTONIC:
+		clock = "monotonic";
+		break;
+	default:
+		clock = "unknown";
+		break;
+	}
+	seq_printf(m, "%-10s %10lld %9ld\n", clock, ts->tv_sec, ts->tv_nsec);
+}
+
+void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m)
+{
+	struct time_namespace *time_ns __free(time_ns) = NULL;
+	struct ns_common *ns = timens_for_children_get(p);
+
+	if (!ns)
+		return;
+
+	time_ns = to_time_ns(ns);
+
+	show_offset(m, CLOCK_MONOTONIC, &time_ns->offsets.monotonic);
+	show_offset(m, CLOCK_BOOTTIME, &time_ns->offsets.boottime);
+}
+
+int proc_timens_set_offset(struct file *file, struct task_struct *p,
+			   struct proc_timens_offset *offsets, int noffsets)
+{
+	struct time_namespace *time_ns __free(time_ns) = NULL;
+	struct ns_common *ns = timens_for_children_get(p);
+	struct timespec64 tp;
+	int i;
+
+	if (!ns)
+		return -ESRCH;
+
+	time_ns = to_time_ns(ns);
+
+	if (!file_ns_capable(file, time_ns->user_ns, CAP_SYS_TIME))
+		return -EPERM;
+
+	for (i = 0; i < noffsets; i++) {
+		struct proc_timens_offset *off = &offsets[i];
+
+		switch (off->clockid) {
+		case CLOCK_MONOTONIC:
+			ktime_get_ts64(&tp);
+			break;
+		case CLOCK_BOOTTIME:
+			ktime_get_boottime_ts64(&tp);
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		if (off->val.tv_sec > KTIME_SEC_MAX ||
+		    off->val.tv_sec < -KTIME_SEC_MAX)
+			return -ERANGE;
+
+		tp = timespec64_add(tp, off->val);
+		/*
+		 * KTIME_SEC_MAX is divided by 2 to be sure that KTIME_MAX is
+		 * still unreachable.
+		 */
+		if (tp.tv_sec < 0 || tp.tv_sec > KTIME_SEC_MAX / 2)
+			return -ERANGE;
+	}
+
+	guard(mutex)(&timens_offset_lock);
+	if (time_ns->frozen_offsets)
+		return -EACCES;
+
+	/* Don't report errors after this line */
+	for (i = 0; i < noffsets; i++) {
+		struct proc_timens_offset *off = &offsets[i];
+		struct timespec64 *offset = NULL;
+
+		switch (off->clockid) {
+		case CLOCK_MONOTONIC:
+			offset = &time_ns->offsets.monotonic;
+			break;
+		case CLOCK_BOOTTIME:
+			offset = &time_ns->offsets.boottime;
+			break;
+		}
+
+		*offset = off->val;
+	}
+
+	return 0;
+}
+
+const struct proc_ns_operations timens_operations = {
+	.name		= "time",
+	.get		= timens_get,
+	.put		= timens_put,
+	.install	= timens_install,
+	.owner		= timens_owner,
+};
+
+const struct proc_ns_operations timens_for_children_operations = {
+	.name		= "time_for_children",
+	.real_ns_name	= "time",
+	.get		= timens_for_children_get,
+	.put		= timens_put,
+	.install	= timens_install,
+	.owner		= timens_owner,
+};
+
+struct time_namespace init_time_ns = {
+	.ns		= NS_COMMON_INIT(init_time_ns),
+	.user_ns	= &init_user_ns,
+	.frozen_offsets	= true,
+};
+EXPORT_SYMBOL_GPL(init_time_ns);
+
+void __init time_ns_init(void)
+{
+	ns_tree_add(&init_time_ns);
+}

linux-7.2.3/kernel/time/namespace_internal.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TIME_NAMESPACE_INTERNAL_H
+#define _TIME_NAMESPACE_INTERNAL_H
+
+#include <linux/mutex.h>
+
+struct time_namespace;
+
+/*
+ * Protects possibly multiple offsets writers racing each other
+ * and tasks entering the namespace.
+ */
+extern struct mutex timens_offset_lock;
+
+#ifdef CONFIG_TIME_NS_VDSO
+int timens_vdso_alloc_vvar_page(struct time_namespace *ns);
+void timens_vdso_free_vvar_page(struct time_namespace *ns);
+#else /* !CONFIG_TIME_NS_VDSO */
+static inline int timens_vdso_alloc_vvar_page(struct time_namespace *ns)
+{
+	return 0;
+}
+static inline void timens_vdso_free_vvar_page(struct time_namespace *ns)
+{
+}
+#endif /* CONFIG_TIME_NS_VDSO */
+
+#endif /* _TIME_NAMESPACE_INTERNAL_H */

linux-7.2.3/kernel/time/namespace_vdso.c

@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: Andrei Vagin <avagin@openvz.org>
+ * Author: Dmitry Safonov <dima@arista.com>
+ */
+
+#include <linux/cleanup.h>
+#include <linux/mm.h>
+#include <linux/time_namespace.h>
+#include <linux/time.h>
+#include <linux/vdso_datastore.h>
+
+#include <vdso/clocksource.h>
+#include <vdso/datapage.h>
+
+#include "namespace_internal.h"
+
+static struct timens_offset offset_from_ts(struct timespec64 off)
+{
+	struct timens_offset ret;
+
+	ret.sec = off.tv_sec;
+	ret.nsec = off.tv_nsec;
+
+	return ret;
+}
+
+/*
+ * A time namespace VVAR page has the same layout as the VVAR page which
+ * contains the system wide VDSO data.
+ *
+ * For a normal task the VVAR pages are installed in the normal ordering:
+ *     VVAR
+ *     PVCLOCK
+ *     HVCLOCK
+ *     TIMENS   <- Not really required
+ *
+ * Now for a timens task the pages are installed in the following order:
+ *     TIMENS
+ *     PVCLOCK
+ *     HVCLOCK
+ *     VVAR
+ *
+ * The check for vdso_clock->clock_mode is in the unlikely path of
+ * the seq begin magic. So for the non-timens case most of the time
+ * 'seq' is even, so the branch is not taken.
+ *
+ * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check
+ * for vdso_clock->clock_mode is a non-issue. The task is spin waiting for the
+ * update to finish and for 'seq' to become even anyway.
+ *
+ * Timens page has vdso_clock->clock_mode set to VDSO_CLOCKMODE_TIMENS which
+ * enforces the time namespace handling path.
+ */
+static void timens_setup_vdso_clock_data(struct vdso_clock *vc,
+					 struct time_namespace *ns)
+{
+	struct timens_offset *offset = vc->offset;
+	struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic);
+	struct timens_offset boottime = offset_from_ts(ns->offsets.boottime);
+
+	vc->seq				= 1;
+	vc->clock_mode			= VDSO_CLOCKMODE_TIMENS;
+	offset[CLOCK_MONOTONIC]		= monotonic;
+	offset[CLOCK_MONOTONIC_RAW]	= monotonic;
+	offset[CLOCK_MONOTONIC_COARSE]	= monotonic;
+	offset[CLOCK_BOOTTIME]		= boottime;
+	offset[CLOCK_BOOTTIME_ALARM]	= boottime;
+}
+
+struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_mm == current->mm))
+		return current->nsproxy->time_ns->vvar_page;
+
+	/*
+	 * VM_PFNMAP | VM_IO protect .fault() handler from being called
+	 * through interfaces like /proc/$pid/mem or
+	 * process_vm_{readv,writev}() as long as there's no .access()
+	 * in special_mapping_vmops().
+	 * For more details check_vma_flags() and __access_remote_vm()
+	 */
+
+	WARN(1, "vvar_page accessed remotely");
+
+	return NULL;
+}
+
+static void timens_set_vvar_page(struct task_struct *task,
+				struct time_namespace *ns)
+{
+	struct vdso_time_data *vdata;
+	struct vdso_clock *vc;
+	unsigned int i;
+
+	if (ns == &init_time_ns)
+		return;
+
+	/* Fast-path, taken by every task in namespace except the first. */
+	if (likely(ns->frozen_offsets))
+		return;
+
+	guard(mutex)(&timens_offset_lock);
+	/* Nothing to-do: vvar_page has been already initialized. */
+	if (ns->frozen_offsets)
+		return;
+
+	ns->frozen_offsets = true;
+	vdata = page_address(ns->vvar_page);
+	vc = vdata->clock_data;
+
+	for (i = 0; i < CS_BASES; i++)
+		timens_setup_vdso_clock_data(&vc[i], ns);
+
+	if (IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS)) {
+		for (i = 0; i < ARRAY_SIZE(vdata->aux_clock_data); i++)
+			timens_setup_vdso_clock_data(&vdata->aux_clock_data[i], ns);
+	}
+}
+
+/*
+ * The vvar page layout depends on whether a task belongs to the root or
+ * non-root time namespace. Whenever a task changes its namespace, the VVAR
+ * page tables are cleared and then they will be re-faulted with a
+ * corresponding layout.
+ * See also the comment near timens_setup_vdso_clock_data() for details.
+ */
+static int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
+
+	guard(mmap_read_lock)(mm);
+	for_each_vma(vmi, vma) {
+		if (vma_is_special_mapping(vma, &vdso_vvar_mapping))
+			zap_vma(vma);
+	}
+	return 0;
+}
+
+void timens_commit(struct task_struct *tsk, struct time_namespace *ns)
+{
+	timens_set_vvar_page(tsk, ns);
+	vdso_join_timens(tsk, ns);
+}
+
+int timens_vdso_alloc_vvar_page(struct time_namespace *ns)
+{
+	ns->vvar_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	if (!ns->vvar_page)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void timens_vdso_free_vvar_page(struct time_namespace *ns)
+{
+	__free_page(ns->vvar_page);
+}

linux-7.2.3/kernel/time/ntp_internal.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_NTP_INTERNAL_H
+#define _LINUX_NTP_INTERNAL_H
+
+extern void ntp_init(void);
+extern void ntp_clear(unsigned int tkid);
+/* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
+extern u64 ntp_tick_length(unsigned int tkid);
+extern ktime_t ntp_get_next_leap(unsigned int tkid);
+extern int second_overflow(unsigned int tkid, time64_t secs);
+extern int ntp_adjtimex(unsigned int tkid, struct __kernel_timex *txc, const struct timespec64 *ts,
+			s32 *time_tai, struct audit_ntp_data *ad);
+extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts);
+
+#if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC)
+extern void ntp_notify_cmos_timer(bool offset_set);
+#else
+static inline void ntp_notify_cmos_timer(bool offset_set) { }
+#endif
+
+#endif /* _LINUX_NTP_INTERNAL_H */

linux-7.2.3/kernel/time/posix-clock.c

@@ -0,0 +1,318 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Support for dynamic clock devices
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ */
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/file.h>
+#include <linux/posix-clock.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+
+#include "posix-timers.h"
+
+/*
+ * Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
+ */
+static struct posix_clock *get_posix_clock(struct file *fp)
+{
+	struct posix_clock_context *pccontext = fp->private_data;
+	struct posix_clock *clk = pccontext->clk;
+
+	down_read(&clk->rwsem);
+
+	if (!clk->zombie)
+		return clk;
+
+	up_read(&clk->rwsem);
+
+	return NULL;
+}
+
+static void put_posix_clock(struct posix_clock *clk)
+{
+	up_read(&clk->rwsem);
+}
+
+static ssize_t posix_clock_read(struct file *fp, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct posix_clock_context *pccontext = fp->private_data;
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -EINVAL;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.read)
+		err = clk->ops.read(pccontext, fp->f_flags, buf, count);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static __poll_t posix_clock_poll(struct file *fp, poll_table *wait)
+{
+	struct posix_clock_context *pccontext = fp->private_data;
+	struct posix_clock *clk = get_posix_clock(fp);
+	__poll_t result = 0;
+
+	if (!clk)
+		return EPOLLERR;
+
+	if (clk->ops.poll)
+		result = clk->ops.poll(pccontext, fp, wait);
+
+	put_posix_clock(clk);
+
+	return result;
+}
+
+static long posix_clock_ioctl(struct file *fp,
+			      unsigned int cmd, unsigned long arg)
+{
+	struct posix_clock_context *pccontext = fp->private_data;
+	struct posix_clock *clk = get_posix_clock(fp);
+	int err = -ENOTTY;
+
+	if (!clk)
+		return -ENODEV;
+
+	if (clk->ops.ioctl)
+		err = clk->ops.ioctl(pccontext, cmd, arg);
+
+	put_posix_clock(clk);
+
+	return err;
+}
+
+static int posix_clock_open(struct inode *inode, struct file *fp)
+{
+	int err;
+	struct posix_clock *clk =
+		container_of(inode->i_cdev, struct posix_clock, cdev);
+	struct posix_clock_context *pccontext;
+
+	down_read(&clk->rwsem);
+
+	if (clk->zombie) {
+		err = -ENODEV;
+		goto out;
+	}
+	pccontext = kzalloc_obj(*pccontext);
+	if (!pccontext) {
+		err = -ENOMEM;
+		goto out;
+	}
+	pccontext->clk = clk;
+	pccontext->fp = fp;
+	if (clk->ops.open) {
+		err = clk->ops.open(pccontext, fp->f_mode);
+		if (err) {
+			kfree(pccontext);
+			goto out;
+		}
+	}
+
+	fp->private_data = pccontext;
+	get_device(clk->dev);
+	err = 0;
+out:
+	up_read(&clk->rwsem);
+	return err;
+}
+
+static int posix_clock_release(struct inode *inode, struct file *fp)
+{
+	struct posix_clock_context *pccontext = fp->private_data;
+	struct posix_clock *clk;
+	int err = 0;
+
+	if (!pccontext)
+		return -ENODEV;
+	clk = pccontext->clk;
+
+	if (clk->ops.release)
+		err = clk->ops.release(pccontext);
+
+	put_device(clk->dev);
+
+	kfree(pccontext);
+	fp->private_data = NULL;
+
+	return err;
+}
+
+static const struct file_operations posix_clock_file_operations = {
+	.owner		= THIS_MODULE,
+	.read		= posix_clock_read,
+	.poll		= posix_clock_poll,
+	.unlocked_ioctl	= posix_clock_ioctl,
+	.compat_ioctl	= posix_clock_ioctl,
+	.open		= posix_clock_open,
+	.release	= posix_clock_release,
+};
+
+int posix_clock_register(struct posix_clock *clk, struct device *dev)
+{
+	int err;
+
+	init_rwsem(&clk->rwsem);
+
+	cdev_init(&clk->cdev, &posix_clock_file_operations);
+	err = cdev_device_add(&clk->cdev, dev);
+	if (err) {
+		pr_err("%s unable to add device %d:%d\n",
+			dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt));
+		return err;
+	}
+	clk->cdev.owner = clk->ops.owner;
+	clk->dev = dev;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(posix_clock_register);
+
+void posix_clock_unregister(struct posix_clock *clk)
+{
+	cdev_device_del(&clk->cdev, clk->dev);
+
+	down_write(&clk->rwsem);
+	clk->zombie = true;
+	up_write(&clk->rwsem);
+
+	put_device(clk->dev);
+}
+EXPORT_SYMBOL_GPL(posix_clock_unregister);
+
+struct posix_clock_desc {
+	struct file *fp;
+	struct posix_clock *clk;
+};
+
+static int get_clock_desc(const clockid_t id, struct posix_clock_desc *cd)
+{
+	struct file *fp = fget(clockid_to_fd(id));
+	int err = -EINVAL;
+
+	if (!fp)
+		return err;
+
+	if (fp->f_op->open != posix_clock_open || !fp->private_data)
+		goto out;
+
+	cd->fp = fp;
+	cd->clk = get_posix_clock(fp);
+
+	err = cd->clk ? 0 : -ENODEV;
+out:
+	if (err)
+		fput(fp);
+	return err;
+}
+
+static void put_clock_desc(struct posix_clock_desc *cd)
+{
+	put_posix_clock(cd->clk);
+	fput(cd->fp);
+}
+
+static int pc_clock_adjtime(clockid_t id, struct __kernel_timex *tx)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (tx->modes && (cd.fp->f_mode & FMODE_WRITE) == 0) {
+		err = -EACCES;
+		goto out;
+	}
+
+	if (cd.clk->ops.clock_adjtime)
+		err = cd.clk->ops.clock_adjtime(cd.clk, tx);
+	else
+		err = -EOPNOTSUPP;
+out:
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_gettime(clockid_t id, struct timespec64 *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_gettime)
+		err = cd.clk->ops.clock_gettime(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_getres(clockid_t id, struct timespec64 *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if (cd.clk->ops.clock_getres)
+		err = cd.clk->ops.clock_getres(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+static int pc_clock_settime(clockid_t id, const struct timespec64 *ts)
+{
+	struct posix_clock_desc cd;
+	int err;
+
+	if (!timespec64_valid_strict(ts))
+		return -EINVAL;
+
+	err = get_clock_desc(id, &cd);
+	if (err)
+		return err;
+
+	if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
+		err = -EACCES;
+		goto out;
+	}
+
+	if (cd.clk->ops.clock_settime)
+		err = cd.clk->ops.clock_settime(cd.clk, ts);
+	else
+		err = -EOPNOTSUPP;
+out:
+	put_clock_desc(&cd);
+
+	return err;
+}
+
+const struct k_clock clock_posix_dynamic = {
+	.clock_getres		= pc_clock_getres,
+	.clock_set		= pc_clock_settime,
+	.clock_get_timespec	= pc_clock_gettime,
+	.clock_adj		= pc_clock_adjtime,
+};

linux-7.2.3/kernel/time/posix-stubs.c

@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Dummy stubs used when CONFIG_POSIX_TIMERS=n
+ *
+ * Created by:  Nicolas Pitre, July 2016
+ * Copyright:   (C) 2016 Linaro Limited
+ */
+
+#include <linux/linkage.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <linux/syscalls.h>
+#include <linux/ktime.h>
+#include <linux/timekeeping.h>
+#include <linux/posix-timers.h>
+#include <linux/time_namespace.h>
+#include <linux/compat.h>
+
+/*
+ * We preserve minimal support for CLOCK_REALTIME and CLOCK_MONOTONIC
+ * as it is easy to remain compatible with little code. CLOCK_BOOTTIME
+ * is also included for convenience as at least systemd uses it.
+ */
+
+SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
+		const struct __kernel_timespec __user *, tp)
+{
+	struct timespec64 new_tp;
+
+	if (which_clock != CLOCK_REALTIME)
+		return -EINVAL;
+	if (get_timespec64(&new_tp, tp))
+		return -EFAULT;
+
+	return do_sys_settimeofday64(&new_tp, NULL);
+}
+
+static int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
+{
+	switch (which_clock) {
+	case CLOCK_REALTIME:
+		ktime_get_real_ts64(tp);
+		break;
+	case CLOCK_MONOTONIC:
+		ktime_get_ts64(tp);
+		timens_add_monotonic(tp);
+		break;
+	case CLOCK_BOOTTIME:
+		ktime_get_boottime_ts64(tp);
+		timens_add_boottime(tp);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
+		struct __kernel_timespec __user *, tp)
+{
+	int ret;
+	struct timespec64 kernel_tp;
+
+	ret = do_clock_gettime(which_clock, &kernel_tp);
+	if (ret)
+		return ret;
+
+	if (put_timespec64(&kernel_tp, tp))
+		return -EFAULT;
+	return 0;
+}
+
+SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct __kernel_timespec __user *, tp)
+{
+	struct timespec64 rtn_tp = {
+		.tv_sec = 0,
+		.tv_nsec = hrtimer_resolution,
+	};
+
+	switch (which_clock) {
+	case CLOCK_REALTIME:
+	case CLOCK_MONOTONIC:
+	case CLOCK_BOOTTIME:
+		if (put_timespec64(&rtn_tp, tp))
+			return -EFAULT;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
+		const struct __kernel_timespec __user *, rqtp,
+		struct __kernel_timespec __user *, rmtp)
+{
+	struct timespec64 t;
+	ktime_t texp;
+
+	switch (which_clock) {
+	case CLOCK_REALTIME:
+	case CLOCK_MONOTONIC:
+	case CLOCK_BOOTTIME:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (get_timespec64(&t, rqtp))
+		return -EFAULT;
+	if (!timespec64_valid(&t))
+		return -EINVAL;
+	if (flags & TIMER_ABSTIME)
+		rmtp = NULL;
+	current->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
+	current->restart_block.nanosleep.rmtp = rmtp;
+	texp = timespec64_to_ktime(t);
+	if (flags & TIMER_ABSTIME)
+		texp = timens_ktime_to_host(which_clock, texp);
+	return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
+				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
+				 which_clock);
+}
+
+#ifdef CONFIG_COMPAT_32BIT_TIME
+
+SYSCALL_DEFINE2(clock_settime32, const clockid_t, which_clock,
+		struct old_timespec32 __user *, tp)
+{
+	struct timespec64 new_tp;
+
+	if (which_clock != CLOCK_REALTIME)
+		return -EINVAL;
+	if (get_old_timespec32(&new_tp, tp))
+		return -EFAULT;
+
+	return do_sys_settimeofday64(&new_tp, NULL);
+}
+
+SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock,
+		struct old_timespec32 __user *, tp)
+{
+	int ret;
+	struct timespec64 kernel_tp;
+
+	ret = do_clock_gettime(which_clock, &kernel_tp);
+	if (ret)
+		return ret;
+
+	if (put_old_timespec32(&kernel_tp, tp))
+		return -EFAULT;
+	return 0;
+}
+
+SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock,
+		struct old_timespec32 __user *, tp)
+{
+	struct timespec64 rtn_tp = {
+		.tv_sec = 0,
+		.tv_nsec = hrtimer_resolution,
+	};
+
+	switch (which_clock) {
+	case CLOCK_REALTIME:
+	case CLOCK_MONOTONIC:
+	case CLOCK_BOOTTIME:
+		if (put_old_timespec32(&rtn_tp, tp))
+			return -EFAULT;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags,
+		struct old_timespec32 __user *, rqtp,
+		struct old_timespec32 __user *, rmtp)
+{
+	struct timespec64 t;
+	ktime_t texp;
+
+	switch (which_clock) {
+	case CLOCK_REALTIME:
+	case CLOCK_MONOTONIC:
+	case CLOCK_BOOTTIME:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (get_old_timespec32(&t, rqtp))
+		return -EFAULT;
+	if (!timespec64_valid(&t))
+		return -EINVAL;
+	if (flags & TIMER_ABSTIME)
+		rmtp = NULL;
+	current->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
+	current->restart_block.nanosleep.compat_rmtp = rmtp;
+	texp = timespec64_to_ktime(t);
+	if (flags & TIMER_ABSTIME)
+		texp = timens_ktime_to_host(which_clock, texp);
+	return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ?
+				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
+				 which_clock);
+}
+#endif

linux-7.2.3/kernel/time/posix-timers.h

@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#define TIMER_RETRY 1
+
+enum posix_timer_state {
+	POSIX_TIMER_DISARMED,
+	POSIX_TIMER_ARMED,
+	POSIX_TIMER_REQUEUE_PENDING,
+};
+
+struct k_clock {
+	int	(*clock_getres)(const clockid_t which_clock,
+				struct timespec64 *tp);
+	int	(*clock_set)(const clockid_t which_clock,
+			     const struct timespec64 *tp);
+	/* Returns the clock value in the current time namespace. */
+	int	(*clock_get_timespec)(const clockid_t which_clock,
+				      struct timespec64 *tp);
+	/* Returns the clock value in the root time namespace. */
+	ktime_t	(*clock_get_ktime)(const clockid_t which_clock);
+	int	(*clock_adj)(const clockid_t which_clock, struct __kernel_timex *tx);
+	int	(*timer_create)(struct k_itimer *timer);
+	int	(*nsleep)(const clockid_t which_clock, int flags,
+			  const struct timespec64 *);
+	int	(*timer_set)(struct k_itimer *timr, int flags,
+			     struct itimerspec64 *new_setting,
+			     struct itimerspec64 *old_setting);
+	int	(*timer_del)(struct k_itimer *timr);
+	void	(*timer_get)(struct k_itimer *timr,
+			     struct itimerspec64 *cur_setting);
+	bool	(*timer_rearm)(struct k_itimer *timr);
+	s64	(*timer_forward)(struct k_itimer *timr, ktime_t now);
+	ktime_t	(*timer_remaining)(struct k_itimer *timr, ktime_t now);
+	int	(*timer_try_to_cancel)(struct k_itimer *timr);
+	bool	(*timer_arm)(struct k_itimer *timr, ktime_t expires,
+			     bool absolute, bool sigev_none);
+	void	(*timer_wait_running)(struct k_itimer *timr);
+};
+
+extern const struct k_clock clock_posix_cpu;
+extern const struct k_clock clock_posix_dynamic;
+extern const struct k_clock clock_process;
+extern const struct k_clock clock_thread;
+extern const struct k_clock alarm_clock;
+extern const struct k_clock clock_aux;
+
+void posix_timer_queue_signal(struct k_itimer *timr);
+
+void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting);
+int common_timer_set(struct k_itimer *timr, int flags,
+		     struct itimerspec64 *new_setting,
+		     struct itimerspec64 *old_setting);
+void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_setting);
+int common_timer_del(struct k_itimer *timer);

linux-7.2.3/kernel/time/sched_clock.c

@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Generic sched_clock() support, to extend low level hardware time
+ * counters to full 64-bit ns values.
+ */
+#include <linux/clocksource.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/ktime.h>
+#include <linux/kernel.h>
+#include <linux/math.h>
+#include <linux/moduleparam.h>
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+#include <linux/syscore_ops.h>
+#include <linux/hrtimer.h>
+#include <linux/sched_clock.h>
+#include <linux/seqlock.h>
+#include <linux/bitops.h>
+
+#include "timekeeping.h"
+
+/**
+ * struct clock_data - all data needed for sched_clock() (including
+ *                     registration of a new clock source)
+ *
+ * @seq:		Sequence counter for protecting updates. The lowest
+ *			bit is the index for @read_data.
+ * @read_data:		Data required to read from sched_clock.
+ * @wrap_kt:		Duration for which clock can run before wrapping.
+ * @rate:		Tick rate of the registered clock.
+ * @actual_read_sched_clock: Registered hardware level clock read function.
+ *
+ * The ordering of this structure has been chosen to optimize cache
+ * performance. In particular 'seq' and 'read_data[0]' (combined) should fit
+ * into a single 64-byte cache line.
+ */
+struct clock_data {
+	seqcount_latch_t	seq;
+	struct clock_read_data	read_data[2];
+	ktime_t			wrap_kt;
+	unsigned long		rate;
+
+	u64 (*actual_read_sched_clock)(void);
+};
+
+static struct hrtimer sched_clock_timer;
+static int irqtime = -1;
+
+core_param(irqtime, irqtime, int, 0400);
+
+static u64 notrace jiffy_sched_clock_read(void)
+{
+	/*
+	 * We don't need to use get_jiffies_64 on 32-bit arches here
+	 * because we register with BITS_PER_LONG
+	 */
+	return (u64)(jiffies - INITIAL_JIFFIES);
+}
+
+static struct clock_data cd ____cacheline_aligned = {
+	.read_data[0] = { .mult = NSEC_PER_SEC / HZ,
+			  .read_sched_clock = jiffy_sched_clock_read, },
+	.actual_read_sched_clock = jiffy_sched_clock_read,
+};
+
+static __always_inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+{
+	return (cyc * mult) >> shift;
+}
+
+notrace struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
+{
+	*seq = read_seqcount_latch(&cd.seq);
+	return cd.read_data + (*seq & 1);
+}
+
+notrace int sched_clock_read_retry(unsigned int seq)
+{
+	return read_seqcount_latch_retry(&cd.seq, seq);
+}
+
+static __always_inline unsigned long long __sched_clock(void)
+{
+	struct clock_read_data *rd;
+	unsigned int seq;
+	u64 cyc, res;
+
+	do {
+		seq = raw_read_seqcount_latch(&cd.seq);
+		rd = cd.read_data + (seq & 1);
+
+		cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
+		      rd->sched_clock_mask;
+		res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift);
+	} while (raw_read_seqcount_latch_retry(&cd.seq, seq));
+
+	return res;
+}
+
+unsigned long long noinstr sched_clock_noinstr(void)
+{
+	return __sched_clock();
+}
+
+unsigned long long notrace sched_clock(void)
+{
+	unsigned long long ns;
+	preempt_disable_notrace();
+	/*
+	 * All of __sched_clock() is a seqcount_latch reader critical section,
+	 * but relies on the raw helpers which are uninstrumented. For KCSAN,
+	 * mark all accesses in __sched_clock() as atomic.
+	 */
+	kcsan_nestable_atomic_begin();
+	ns = __sched_clock();
+	kcsan_nestable_atomic_end();
+	preempt_enable_notrace();
+	return ns;
+}
+
+/*
+ * Updating the data required to read the clock.
+ *
+ * sched_clock() will never observe mis-matched data even if called from
+ * an NMI. We do this by maintaining an odd/even copy of the data and
+ * steering sched_clock() to one or the other using a sequence counter.
+ * In order to preserve the data cache profile of sched_clock() as much
+ * as possible the system reverts back to the even copy when the update
+ * completes; the odd copy is used *only* during an update.
+ */
+static void update_clock_read_data(struct clock_read_data *rd)
+{
+	/* steer readers towards the odd copy */
+	write_seqcount_latch_begin(&cd.seq);
+
+	/* now its safe for us to update the normal (even) copy */
+	cd.read_data[0] = *rd;
+
+	/* switch readers back to the even copy */
+	write_seqcount_latch(&cd.seq);
+
+	/* update the backup (odd) copy with the new data */
+	cd.read_data[1] = *rd;
+
+	write_seqcount_latch_end(&cd.seq);
+}
+
+/*
+ * Atomically update the sched_clock() epoch.
+ */
+static void update_sched_clock(void)
+{
+	u64 cyc;
+	u64 ns;
+	struct clock_read_data rd;
+
+	rd = cd.read_data[0];
+
+	cyc = cd.actual_read_sched_clock();
+	ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift);
+
+	rd.epoch_ns = ns;
+	rd.epoch_cyc = cyc;
+
+	update_clock_read_data(&rd);
+}
+
+static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
+{
+	update_sched_clock();
+	hrtimer_forward_now(hrt, cd.wrap_kt);
+
+	return HRTIMER_RESTART;
+}
+
+void sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
+{
+	u64 res, wrap, new_mask, new_epoch, cyc, ns;
+	u32 new_mult, new_shift;
+	unsigned long r, flags;
+	char r_unit;
+	struct clock_read_data rd;
+
+	if (cd.rate > rate)
+		return;
+
+	/* Cannot register a sched_clock with interrupts on */
+	local_irq_save(flags);
+
+	/* Calculate the mult/shift to convert counter ticks to ns. */
+	clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
+
+	new_mask = CLOCKSOURCE_MASK(bits);
+	cd.rate = rate;
+
+	/* Calculate how many nanosecs until we risk wrapping */
+	wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL);
+	cd.wrap_kt = ns_to_ktime(wrap);
+
+	rd = cd.read_data[0];
+
+	/* Update epoch for new counter and update 'epoch_ns' from old counter*/
+	new_epoch = read();
+	cyc = cd.actual_read_sched_clock();
+	ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift);
+	cd.actual_read_sched_clock = read;
+
+	rd.read_sched_clock	= read;
+	rd.sched_clock_mask	= new_mask;
+	rd.mult			= new_mult;
+	rd.shift		= new_shift;
+	rd.epoch_cyc		= new_epoch;
+	rd.epoch_ns		= ns;
+
+	update_clock_read_data(&rd);
+
+	if (ACCESS_PRIVATE(&sched_clock_timer, function) != NULL) {
+		/* update timeout for clock wrap */
+		hrtimer_start(&sched_clock_timer, cd.wrap_kt,
+			      HRTIMER_MODE_REL_HARD);
+	}
+
+	r = rate;
+	if (r >= 4000000) {
+		r = DIV_ROUND_CLOSEST(r, 1000000);
+		r_unit = 'M';
+	} else if (r >= 4000) {
+		r = DIV_ROUND_CLOSEST(r, 1000);
+		r_unit = 'k';
+	} else {
+		r_unit = ' ';
+	}
+
+	/* Calculate the ns resolution of this counter */
+	res = cyc_to_ns(1ULL, new_mult, new_shift);
+
+	pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
+		bits, r, r_unit, res, wrap);
+
+	/* Enable IRQ time accounting if we have a fast enough sched_clock() */
+	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
+		enable_sched_clock_irqtime();
+
+	local_irq_restore(flags);
+
+	pr_debug("Registered %pS as sched_clock source\n", read);
+}
+EXPORT_SYMBOL_GPL(sched_clock_register);
+
+void __init generic_sched_clock_init(void)
+{
+	/*
+	 * If no sched_clock() function has been provided at that point,
+	 * make it the final one.
+	 */
+	if (cd.actual_read_sched_clock == jiffy_sched_clock_read)
+		sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ);
+
+	update_sched_clock();
+
+	/*
+	 * Start the timer to keep sched_clock() properly updated and
+	 * sets the initial epoch.
+	 */
+	hrtimer_setup(&sched_clock_timer, sched_clock_poll, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
+	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD);
+}
+
+/*
+ * Clock read function for use when the clock is suspended.
+ *
+ * This function makes it appear to sched_clock() as if the clock
+ * stopped counting at its last update.
+ *
+ * This function must only be called from the critical
+ * section in sched_clock(). It relies on the read_seqcount_retry()
+ * at the end of the critical section to be sure we observe the
+ * correct copy of 'epoch_cyc'.
+ */
+static u64 notrace suspended_sched_clock_read(void)
+{
+	unsigned int seq = read_seqcount_latch(&cd.seq);
+
+	return cd.read_data[seq & 1].epoch_cyc;
+}
+
+int sched_clock_suspend(void)
+{
+	struct clock_read_data *rd = &cd.read_data[0];
+
+	update_sched_clock();
+	hrtimer_cancel(&sched_clock_timer);
+	rd->read_sched_clock = suspended_sched_clock_read;
+
+	return 0;
+}
+
+static int sched_clock_syscore_suspend(void *data)
+{
+	return sched_clock_suspend();
+}
+
+void sched_clock_resume(void)
+{
+	struct clock_read_data *rd = &cd.read_data[0];
+
+	rd->epoch_cyc = cd.actual_read_sched_clock();
+	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD);
+	rd->read_sched_clock = cd.actual_read_sched_clock;
+}
+
+static void sched_clock_syscore_resume(void *data)
+{
+	sched_clock_resume();
+}
+
+static const struct syscore_ops sched_clock_syscore_ops = {
+	.suspend	= sched_clock_syscore_suspend,
+	.resume		= sched_clock_syscore_resume,
+};
+
+static struct syscore sched_clock_syscore = {
+	.ops = &sched_clock_syscore_ops,
+};
+
+static int __init sched_clock_syscore_init(void)
+{
+	register_syscore(&sched_clock_syscore);
+
+	return 0;
+}
+device_initcall(sched_clock_syscore_init);

linux-7.2.3/kernel/time/sleep_timeout.c

@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Kernel internal schedule timeout and sleeping functions
+ */
+
+#include <linux/delay.h>
+#include <linux/jiffies.h>
+#include <linux/timer.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
+
+#include "tick-internal.h"
+
+/*
+ * Since schedule_timeout()'s timer is defined on the stack, it must store
+ * the target task on the stack as well.
+ */
+struct process_timer {
+	struct timer_list timer;
+	struct task_struct *task;
+};
+
+static void process_timeout(struct timer_list *t)
+{
+	struct process_timer *timeout = timer_container_of(timeout, t, timer);
+
+	wake_up_process(timeout->task);
+}
+
+/**
+ * schedule_timeout - sleep until timeout
+ * @timeout: timeout value in jiffies
+ *
+ * Make the current task sleep until @timeout jiffies have elapsed.
+ * The function behavior depends on the current task state
+ * (see also set_current_state() description):
+ *
+ * %TASK_RUNNING - the scheduler is called, but the task does not sleep
+ * at all. That happens because sched_submit_work() does nothing for
+ * tasks in %TASK_RUNNING state.
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
+ * pass before the routine returns unless the current task is explicitly
+ * woken up, (e.g. by wake_up_process()).
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task or the current task is explicitly woken
+ * up.
+ *
+ * The current task state is guaranteed to be %TASK_RUNNING when this
+ * routine returns.
+ *
+ * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
+ * the CPU away without a bound on the timeout. In this case the return
+ * value will be %MAX_SCHEDULE_TIMEOUT.
+ *
+ * Returns: 0 when the timer has expired otherwise the remaining time in
+ * jiffies will be returned. In all cases the return value is guaranteed
+ * to be non-negative.
+ */
+signed long __sched schedule_timeout(signed long timeout)
+{
+	struct process_timer timer;
+	unsigned long expire;
+
+	switch (timeout) {
+	case MAX_SCHEDULE_TIMEOUT:
+		/*
+		 * These two special cases are useful to be comfortable
+		 * in the caller. Nothing more. We could take
+		 * MAX_SCHEDULE_TIMEOUT from one of the negative value
+		 * but I' d like to return a valid offset (>=0) to allow
+		 * the caller to do everything it want with the retval.
+		 */
+		schedule();
+		goto out;
+	default:
+		/*
+		 * Another bit of PARANOID. Note that the retval will be
+		 * 0 since no piece of kernel is supposed to do a check
+		 * for a negative retval of schedule_timeout() (since it
+		 * should never happens anyway). You just have the printk()
+		 * that will tell you if something is gone wrong and where.
+		 */
+		if (timeout < 0) {
+			pr_err("%s: wrong timeout value %lx\n", __func__, timeout);
+			dump_stack();
+			__set_current_state(TASK_RUNNING);
+			goto out;
+		}
+	}
+
+	expire = timeout + jiffies;
+
+	timer.task = current;
+	timer_setup_on_stack(&timer.timer, process_timeout, 0);
+	timer.timer.expires = expire;
+	add_timer(&timer.timer);
+	schedule();
+	timer_delete_sync(&timer.timer);
+
+	/* Remove the timer from the object tracker */
+	timer_destroy_on_stack(&timer.timer);
+
+	timeout = expire - jiffies;
+
+ out:
+	return timeout < 0 ? 0 : timeout;
+}
+EXPORT_SYMBOL(schedule_timeout);
+
+/*
+ * __set_current_state() can be used in schedule_timeout_*() functions, because
+ * schedule_timeout() calls schedule() unconditionally.
+ */
+
+/**
+ * schedule_timeout_interruptible - sleep until timeout (interruptible)
+ * @timeout: timeout value in jiffies
+ *
+ * See schedule_timeout() for details.
+ *
+ * Task state is set to TASK_INTERRUPTIBLE before starting the timeout.
+ */
+signed long __sched schedule_timeout_interruptible(signed long timeout)
+{
+	__set_current_state(TASK_INTERRUPTIBLE);
+	return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_interruptible);
+
+/**
+ * schedule_timeout_killable - sleep until timeout (killable)
+ * @timeout: timeout value in jiffies
+ *
+ * See schedule_timeout() for details.
+ *
+ * Task state is set to TASK_KILLABLE before starting the timeout.
+ */
+signed long __sched schedule_timeout_killable(signed long timeout)
+{
+	__set_current_state(TASK_KILLABLE);
+	return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_killable);
+
+/**
+ * schedule_timeout_uninterruptible - sleep until timeout (uninterruptible)
+ * @timeout: timeout value in jiffies
+ *
+ * See schedule_timeout() for details.
+ *
+ * Task state is set to TASK_UNINTERRUPTIBLE before starting the timeout.
+ */
+signed long __sched schedule_timeout_uninterruptible(signed long timeout)
+{
+	__set_current_state(TASK_UNINTERRUPTIBLE);
+	return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_uninterruptible);
+
+/**
+ * schedule_timeout_idle - sleep until timeout (idle)
+ * @timeout: timeout value in jiffies
+ *
+ * See schedule_timeout() for details.
+ *
+ * Task state is set to TASK_IDLE before starting the timeout. It is similar to
+ * schedule_timeout_uninterruptible(), except this task will not contribute to
+ * load average.
+ */
+signed long __sched schedule_timeout_idle(signed long timeout)
+{
+	__set_current_state(TASK_IDLE);
+	return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_idle);
+
+/**
+ * schedule_hrtimeout_range_clock - sleep until timeout
+ * @expires:	timeout value (ktime_t)
+ * @delta:	slack in expires timeout (ktime_t)
+ * @mode:	timer mode
+ * @clock_id:	timer clock to be used
+ *
+ * Details are explained in schedule_hrtimeout_range() function description as
+ * this function is commonly used.
+ */
+int __sched schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
+					   const enum hrtimer_mode mode, clockid_t clock_id)
+{
+	struct hrtimer_sleeper t;
+
+	/*
+	 * Optimize when a zero timeout value is given. It does not
+	 * matter whether this is an absolute or a relative time.
+	 */
+	if (expires && *expires == 0) {
+		__set_current_state(TASK_RUNNING);
+		return 0;
+	}
+
+	/*
+	 * A NULL parameter means "infinite"
+	 */
+	if (!expires) {
+		schedule();
+		return -EINTR;
+	}
+
+	hrtimer_setup_sleeper_on_stack(&t, clock_id, mode);
+	hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
+	hrtimer_sleeper_start_expires(&t, mode);
+
+	if (likely(t.task))
+		schedule();
+
+	hrtimer_cancel(&t.timer);
+	destroy_hrtimer_on_stack(&t.timer);
+
+	__set_current_state(TASK_RUNNING);
+
+	return !t.task ? 0 : -EINTR;
+}
+EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock);
+
+/**
+ * schedule_hrtimeout_range - sleep until timeout
+ * @expires:	timeout value (ktime_t)
+ * @delta:	slack in expires timeout (ktime_t)
+ * @mode:	timer mode
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * The @delta argument gives the kernel the freedom to schedule the
+ * actual wakeup to a time that is both power and performance friendly
+ * for regular (non RT/DL) tasks.
+ * The kernel give the normal best effort behavior for "@expires+@delta",
+ * but may decide to fire the timer earlier, but no earlier than @expires.
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns unless the current task is explicitly
+ * woken up, (e.g. by wake_up_process()).
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task or the current task is explicitly woken
+ * up.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns: 0 when the timer has expired. If the task was woken before the
+ * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or
+ * by an explicit wakeup, it returns -EINTR.
+ */
+int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta,
+				     const enum hrtimer_mode mode)
+{
+	return schedule_hrtimeout_range_clock(expires, delta, mode,
+					      CLOCK_MONOTONIC);
+}
+EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
+
+/**
+ * schedule_hrtimeout - sleep until timeout
+ * @expires:	timeout value (ktime_t)
+ * @mode:	timer mode
+ *
+ * See schedule_hrtimeout_range() for details. @delta argument of
+ * schedule_hrtimeout_range() is set to 0 and has therefore no impact.
+ */
+int __sched schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode)
+{
+	return schedule_hrtimeout_range(expires, 0, mode);
+}
+EXPORT_SYMBOL_GPL(schedule_hrtimeout);
+
+/**
+ * msleep - sleep safely even with waitqueue interruptions
+ * @msecs:	Requested sleep duration in milliseconds
+ *
+ * msleep() uses jiffy based timeouts for the sleep duration. Because of the
+ * design of the timer wheel, the maximum additional percentage delay (slack) is
+ * 12.5%. This is only valid for timers which will end up in level 1 or a higher
+ * level of the timer wheel. For explanation of those 12.5% please check the
+ * detailed description about the basics of the timer wheel.
+ *
+ * The slack of timers which will end up in level 0 depends on sleep duration
+ * (msecs) and HZ configuration and can be calculated in the following way (with
+ * the timer wheel design restriction that the slack is not less than 12.5%):
+ *
+ *   ``slack = MSECS_PER_TICK / msecs``
+ *
+ * When the allowed slack of the callsite is known, the calculation could be
+ * turned around to find the minimal allowed sleep duration to meet the
+ * constraints. For example:
+ *
+ * * ``HZ=1000`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 1 / (1/4) = 4``:
+ *   all sleep durations greater or equal 4ms will meet the constraints.
+ * * ``HZ=1000`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 1 / (1/8) = 8``:
+ *   all sleep durations greater or equal 8ms will meet the constraints.
+ * * ``HZ=250`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 4 / (1/4) = 16``:
+ *   all sleep durations greater or equal 16ms will meet the constraints.
+ * * ``HZ=250`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 4 / (1/8) = 32``:
+ *   all sleep durations greater or equal 32ms will meet the constraints.
+ *
+ * See also the signal aware variant msleep_interruptible().
+ */
+void msleep(unsigned int msecs)
+{
+	unsigned long timeout = msecs_to_jiffies(msecs);
+
+	while (timeout)
+		timeout = schedule_timeout_uninterruptible(timeout);
+}
+EXPORT_SYMBOL(msleep);
+
+/**
+ * msleep_interruptible - sleep waiting for signals
+ * @msecs:	Requested sleep duration in milliseconds
+ *
+ * See msleep() for some basic information.
+ *
+ * The difference between msleep() and msleep_interruptible() is that the sleep
+ * could be interrupted by a signal delivery and then returns early.
+ *
+ * Returns: The remaining time of the sleep duration transformed to msecs (see
+ * schedule_timeout() for details).
+ */
+unsigned long msleep_interruptible(unsigned int msecs)
+{
+	unsigned long timeout = msecs_to_jiffies(msecs);
+
+	while (timeout && !signal_pending(current))
+		timeout = schedule_timeout_interruptible(timeout);
+	return jiffies_to_msecs(timeout);
+}
+EXPORT_SYMBOL(msleep_interruptible);
+
+/**
+ * usleep_range_state - Sleep for an approximate time in a given state
+ * @min:	Minimum time in usecs to sleep
+ * @max:	Maximum time in usecs to sleep
+ * @state:	State of the current task that will be while sleeping
+ *
+ * usleep_range_state() sleeps at least for the minimum specified time but not
+ * longer than the maximum specified amount of time. The range might reduce
+ * power usage by allowing hrtimers to coalesce an already scheduled interrupt
+ * with this hrtimer. In the worst case, an interrupt is scheduled for the upper
+ * bound.
+ *
+ * The sleeping task is set to the specified state before starting the sleep.
+ *
+ * In non-atomic context where the exact wakeup time is flexible, use
+ * usleep_range() or its variants instead of udelay(). The sleep improves
+ * responsiveness by avoiding the CPU-hogging busy-wait of udelay().
+ */
+void __sched usleep_range_state(unsigned long min, unsigned long max, unsigned int state)
+{
+	ktime_t exp = ktime_add_us(ktime_get(), min);
+	u64 delta = (u64)(max - min) * NSEC_PER_USEC;
+
+	if (WARN_ON_ONCE(max < min))
+		delta = 0;
+
+	for (;;) {
+		__set_current_state(state);
+		/* Do not return before the requested sleep time has elapsed */
+		if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS))
+			break;
+	}
+}
+EXPORT_SYMBOL(usleep_range_state);

linux-7.2.3/kernel/time/test_udelay.c

@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * udelay() test kernel module
+ *
+ * Test is executed by writing and reading to /sys/kernel/debug/udelay_test
+ * Tests are configured by writing: USECS ITERATIONS
+ * Tests are executed by reading from the same file.
+ * Specifying usecs of 0 or negative values will run multiples tests.
+ *
+ * Copyright (C) 2014 Google, Inc.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/ktime.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+#define DEFAULT_ITERATIONS 100
+
+#define DEBUGFS_FILENAME "udelay_test"
+
+static DEFINE_MUTEX(udelay_test_lock);
+static int udelay_test_usecs;
+static int udelay_test_iterations = DEFAULT_ITERATIONS;
+
+static int udelay_test_single(struct seq_file *s, int usecs, uint32_t iters)
+{
+	int min = 0, max = 0, fail_count = 0;
+	uint64_t sum = 0;
+	uint64_t avg;
+	int i;
+	/* Allow udelay to be up to 0.5% fast */
+	int allowed_error_ns = usecs * 5;
+
+	for (i = 0; i < iters; ++i) {
+		s64 kt1, kt2;
+		int time_passed;
+
+		kt1 = ktime_get_ns();
+		udelay(usecs);
+		kt2 = ktime_get_ns();
+		time_passed = kt2 - kt1;
+
+		if (i == 0 || time_passed < min)
+			min = time_passed;
+		if (i == 0 || time_passed > max)
+			max = time_passed;
+		if ((time_passed + allowed_error_ns) / 1000 < usecs)
+			++fail_count;
+		WARN_ON(time_passed < 0);
+		sum += time_passed;
+	}
+
+	avg = sum;
+	do_div(avg, iters);
+	seq_printf(s, "%d usecs x %d: exp=%d allowed=%d min=%d avg=%lld max=%d",
+			usecs, iters, usecs * 1000,
+			(usecs * 1000) - allowed_error_ns, min, avg, max);
+	if (fail_count)
+		seq_printf(s, " FAIL=%d", fail_count);
+	seq_puts(s, "\n");
+
+	return 0;
+}
+
+static int udelay_test_show(struct seq_file *s, void *v)
+{
+	int usecs;
+	int iters;
+	int ret = 0;
+
+	mutex_lock(&udelay_test_lock);
+	usecs = udelay_test_usecs;
+	iters = udelay_test_iterations;
+	mutex_unlock(&udelay_test_lock);
+
+	if (usecs > 0 && iters > 0) {
+		return udelay_test_single(s, usecs, iters);
+	} else if (usecs == 0) {
+		struct timespec64 ts;
+
+		ktime_get_ts64(&ts);
+		seq_printf(s, "udelay() test (lpj=%ld kt=%lld.%09ld)\n",
+				loops_per_jiffy, (s64)ts.tv_sec, ts.tv_nsec);
+		seq_puts(s, "usage:\n");
+		seq_puts(s, "echo USECS [ITERS] > " DEBUGFS_FILENAME "\n");
+		seq_puts(s, "cat " DEBUGFS_FILENAME "\n");
+	}
+
+	return ret;
+}
+
+static int udelay_test_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, udelay_test_show, inode->i_private);
+}
+
+static ssize_t udelay_test_write(struct file *file, const char __user *buf,
+		size_t count, loff_t *pos)
+{
+	char lbuf[32];
+	int ret;
+	int usecs;
+	int iters;
+
+	if (count >= sizeof(lbuf))
+		return -EINVAL;
+
+	if (copy_from_user(lbuf, buf, count))
+		return -EFAULT;
+	lbuf[count] = '\0';
+
+	ret = sscanf(lbuf, "%d %d", &usecs, &iters);
+	if (ret < 1)
+		return -EINVAL;
+	else if (ret < 2)
+		iters = DEFAULT_ITERATIONS;
+
+	mutex_lock(&udelay_test_lock);
+	udelay_test_usecs = usecs;
+	udelay_test_iterations = iters;
+	mutex_unlock(&udelay_test_lock);
+
+	return count;
+}
+
+static const struct file_operations udelay_test_debugfs_ops = {
+	.owner = THIS_MODULE,
+	.open = udelay_test_open,
+	.read = seq_read,
+	.write = udelay_test_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init udelay_test_init(void)
+{
+	mutex_lock(&udelay_test_lock);
+	debugfs_create_file(DEBUGFS_FILENAME, S_IRUSR, NULL, NULL,
+			    &udelay_test_debugfs_ops);
+	mutex_unlock(&udelay_test_lock);
+
+	return 0;
+}
+
+module_init(udelay_test_init);
+
+static void __exit udelay_test_exit(void)
+{
+	mutex_lock(&udelay_test_lock);
+	debugfs_lookup_and_remove(DEBUGFS_FILENAME, NULL);
+	mutex_unlock(&udelay_test_lock);
+}
+
+module_exit(udelay_test_exit);
+
+MODULE_DESCRIPTION("udelay test module");
+MODULE_AUTHOR("David Riley <davidriley@chromium.org>");
+MODULE_LICENSE("GPL");

linux-7.2.3/kernel/time/tick-broadcast-hrtimer.c

@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Emulate a local clock event device via a pseudo clock device.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/clockchips.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+
+#include "tick-internal.h"
+
+static struct hrtimer bctimer;
+
+static int bc_shutdown(struct clock_event_device *evt)
+{
+	/*
+	 * Note, we cannot cancel the timer here as we might
+	 * run into the following live lock scenario:
+	 *
+	 * cpu 0		cpu1
+	 * lock(broadcast_lock);
+	 *			hrtimer_interrupt()
+	 *			bc_handler()
+	 *			   tick_handle_oneshot_broadcast();
+	 *			    lock(broadcast_lock);
+	 * hrtimer_cancel()
+	 *  wait_for_callback()
+	 */
+	hrtimer_try_to_cancel(&bctimer);
+	return 0;
+}
+
+/*
+ * This is called from the guts of the broadcast code when the cpu
+ * which is about to enter idle has the earliest broadcast timer event.
+ */
+static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
+{
+	/*
+	 * This is called either from enter/exit idle code or from the
+	 * broadcast handler. In all cases tick_broadcast_lock is held.
+	 *
+	 * hrtimer_cancel() cannot be called here neither from the
+	 * broadcast handler nor from the enter/exit idle code. The idle
+	 * code can run into the problem described in bc_shutdown() and the
+	 * broadcast handler cannot wait for itself to complete for obvious
+	 * reasons.
+	 *
+	 * Each caller tries to arm the hrtimer on its own CPU, but if the
+	 * hrtimer callback function is currently running, then
+	 * hrtimer_start() cannot move it and the timer stays on the CPU on
+	 * which it is assigned at the moment.
+	 */
+	hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED_HARD);
+	/*
+	 * The core tick broadcast mode expects bc->bound_on to be set
+	 * correctly to prevent a CPU which has the broadcast hrtimer
+	 * armed from going deep idle.
+	 *
+	 * As tick_broadcast_lock is held, nothing can change the cpu
+	 * base which was just established in hrtimer_start() above. So
+	 * the below access is safe even without holding the hrtimer
+	 * base lock.
+	 */
+	bc->bound_on = bctimer.base->cpu_base->cpu;
+
+	return 0;
+}
+
+static struct clock_event_device ce_broadcast_hrtimer = {
+	.name			= "bc_hrtimer",
+	.set_state_shutdown	= bc_shutdown,
+	.set_next_ktime		= bc_set_next,
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_HRTIMER,
+	.rating			= 0,
+	.bound_on		= -1,
+	.min_delta_ns		= 1,
+	.max_delta_ns		= KTIME_MAX,
+	.min_delta_ticks	= 1,
+	.max_delta_ticks	= ULONG_MAX,
+	.mult			= 1,
+	.shift			= 0,
+	.cpumask		= cpu_possible_mask,
+};
+
+static enum hrtimer_restart bc_handler(struct hrtimer *t)
+{
+	ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
+
+	return HRTIMER_NORESTART;
+}
+
+void tick_setup_hrtimer_broadcast(void)
+{
+	hrtimer_setup(&bctimer, bc_handler, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
+	clockevents_register_device(&ce_broadcast_hrtimer);
+}

linux-7.2.3/kernel/time/tick-common.c

@@ -0,0 +1,595 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains the base functions to manage periodic tick
+ * related events.
+ *
+ * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ */
+#include <linux/compiler.h>
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/nmi.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <trace/events/power.h>
+
+#include <asm/irq_regs.h>
+
+#include "tick-internal.h"
+
+/*
+ * Tick devices
+ */
+DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
+/*
+ * Tick next event: keeps track of the tick time. It's updated by the
+ * CPU which handles the tick and protected by jiffies_lock. There is
+ * no requirement to write hold the jiffies seqcount for it.
+ */
+ktime_t tick_next_period;
+
+/*
+ * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
+ * which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
+ * variable has two functions:
+ *
+ * 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
+ *    timekeeping lock all at once. Only the CPU which is assigned to do the
+ *    update is handling it.
+ *
+ * 2) Hand off the duty in the NOHZ idle case by setting the value to
+ *    TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
+ *    at it will take over and keep the time keeping alive.  The handover
+ *    procedure also covers cpu hotplug.
+ */
+int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
+#ifdef CONFIG_NO_HZ_FULL
+/*
+ * tick_do_timer_boot_cpu indicates the boot CPU temporarily owns
+ * tick_do_timer_cpu and it should be taken over by an eligible secondary
+ * when one comes online.
+ */
+static int tick_do_timer_boot_cpu __read_mostly = -1;
+#endif
+
+/*
+ * Debugging: see timer_list.c
+ */
+struct tick_device *tick_get_device(int cpu)
+{
+	return &per_cpu(tick_cpu_device, cpu);
+}
+
+/**
+ * tick_is_oneshot_available - check for a oneshot capable event device
+ */
+int tick_is_oneshot_available(void)
+{
+	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
+
+	if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+		return 0;
+	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
+		return 1;
+	return tick_broadcast_oneshot_available();
+}
+
+/*
+ * Periodic tick
+ */
+static void tick_periodic(int cpu)
+{
+	if (READ_ONCE(tick_do_timer_cpu) == cpu) {
+		raw_spin_lock(&jiffies_lock);
+		write_seqcount_begin(&jiffies_seq);
+
+		/* Keep track of the next tick event */
+		tick_next_period = ktime_add_ns(tick_next_period, TICK_NSEC);
+
+		do_timer(1);
+		write_seqcount_end(&jiffies_seq);
+		raw_spin_unlock(&jiffies_lock);
+		update_wall_time();
+	}
+
+	update_process_times(user_mode(get_irq_regs()));
+	profile_tick(CPU_PROFILING);
+}
+
+/*
+ * Event handler for periodic ticks
+ */
+void tick_handle_periodic(struct clock_event_device *dev)
+{
+	int cpu = smp_processor_id();
+	ktime_t next = dev->next_event;
+
+	dev->next_event_forced = 0;
+	tick_periodic(cpu);
+
+	/*
+	 * The cpu might have transitioned to HIGHRES or NOHZ mode via
+	 * update_process_times() -> run_local_timers() ->
+	 * hrtimer_run_queues().
+	 */
+	if (IS_ENABLED(CONFIG_TICK_ONESHOT) && dev->event_handler != tick_handle_periodic)
+		return;
+
+	if (!clockevent_state_oneshot(dev))
+		return;
+	for (;;) {
+		/*
+		 * Setup the next period for devices, which do not have
+		 * periodic mode:
+		 */
+		next = ktime_add_ns(next, TICK_NSEC);
+
+		if (!clockevents_program_event(dev, next, false))
+			return;
+		/*
+		 * Have to be careful here. If we're in oneshot mode,
+		 * before we call tick_periodic() in a loop, we need
+		 * to be sure we're using a real hardware clocksource.
+		 * Otherwise we could get trapped in an infinite
+		 * loop, as the tick_periodic() increments jiffies,
+		 * which then will increment time, possibly causing
+		 * the loop to trigger again and again.
+		 */
+		if (timekeeping_valid_for_hres())
+			tick_periodic(cpu);
+	}
+}
+
+/*
+ * Setup the device for a periodic tick
+ */
+void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
+{
+	tick_set_periodic_handler(dev, broadcast);
+
+	/* Broadcast setup ? */
+	if (!tick_device_is_functional(dev))
+		return;
+
+	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
+	    !tick_broadcast_oneshot_active()) {
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
+	} else {
+		unsigned int seq;
+		ktime_t next;
+
+		do {
+			seq = read_seqcount_begin(&jiffies_seq);
+			next = tick_next_period;
+		} while (read_seqcount_retry(&jiffies_seq, seq));
+
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
+
+		for (;;) {
+			if (!clockevents_program_event(dev, next, false))
+				return;
+			next = ktime_add_ns(next, TICK_NSEC);
+		}
+	}
+}
+
+/*
+ * Setup the tick device
+ */
+static void tick_setup_device(struct tick_device *td,
+			      struct clock_event_device *newdev, int cpu,
+			      const struct cpumask *cpumask)
+{
+	void (*handler)(struct clock_event_device *) = NULL;
+	ktime_t next_event = 0;
+
+	/*
+	 * First device setup ?
+	 */
+	if (!td->evtdev) {
+		/*
+		 * If no cpu took the do_timer update, assign it to
+		 * this cpu:
+		 */
+		if (READ_ONCE(tick_do_timer_cpu) == TICK_DO_TIMER_BOOT) {
+			WRITE_ONCE(tick_do_timer_cpu, cpu);
+			tick_next_period = ktime_get();
+#ifdef CONFIG_NO_HZ_FULL
+			/*
+			 * The boot CPU may be nohz_full, in which case the
+			 * first housekeeping secondary will take do_timer()
+			 * from it.
+			 */
+			if (tick_nohz_full_cpu(cpu))
+				tick_do_timer_boot_cpu = cpu;
+
+		} else if (tick_do_timer_boot_cpu != -1 && !tick_nohz_full_cpu(cpu)) {
+			tick_do_timer_boot_cpu = -1;
+			/*
+			 * The boot CPU will stay in periodic (NOHZ disabled)
+			 * mode until clocksource_done_booting() called after
+			 * smp_init() selects a high resolution clocksource and
+			 * timekeeping_notify() kicks the NOHZ stuff alive.
+			 *
+			 * So this WRITE_ONCE can only race with the READ_ONCE
+			 * check in tick_periodic() but this race is harmless.
+			 */
+			WRITE_ONCE(tick_do_timer_cpu, cpu);
+#endif
+		}
+
+		/*
+		 * Startup in periodic mode first.
+		 */
+		td->mode = TICKDEV_MODE_PERIODIC;
+	} else {
+		handler = td->evtdev->event_handler;
+		next_event = td->evtdev->next_event;
+		td->evtdev->event_handler = clockevents_handle_noop;
+	}
+
+	td->evtdev = newdev;
+
+	/*
+	 * When the device is not per cpu, pin the interrupt to the
+	 * current cpu:
+	 */
+	if (!cpumask_equal(newdev->cpumask, cpumask))
+		irq_set_affinity(newdev->irq, cpumask);
+
+	/*
+	 * When global broadcasting is active, check if the current
+	 * device is registered as a placeholder for broadcast mode.
+	 * This allows us to handle this x86 misfeature in a generic
+	 * way. This function also returns !=0 when we keep the
+	 * current active broadcast state for this CPU.
+	 */
+	if (tick_device_uses_broadcast(newdev, cpu))
+		return;
+
+	if (td->mode == TICKDEV_MODE_PERIODIC)
+		tick_setup_periodic(newdev, 0);
+	else
+		tick_setup_oneshot(newdev, handler, next_event);
+}
+
+void tick_install_replacement(struct clock_event_device *newdev)
+{
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+	int cpu = smp_processor_id();
+
+	clockevents_exchange_device(td->evtdev, newdev);
+	tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
+	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
+		tick_oneshot_notify();
+}
+
+static bool tick_check_percpu(struct clock_event_device *curdev,
+			      struct clock_event_device *newdev, int cpu)
+{
+	if (!cpumask_test_cpu(cpu, newdev->cpumask))
+		return false;
+	if (cpumask_equal(newdev->cpumask, cpumask_of(cpu)))
+		return true;
+	/* Check if irq affinity can be set */
+	if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq))
+		return false;
+	/* Prefer an existing cpu local device */
+	if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
+		return false;
+	return true;
+}
+
+static bool tick_check_preferred(struct clock_event_device *curdev,
+				 struct clock_event_device *newdev)
+{
+	/* Prefer oneshot capable device */
+	if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) {
+		if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT))
+			return false;
+		if (tick_oneshot_mode_active())
+			return false;
+	}
+
+	/*
+	 * Use the higher rated one, but prefer a CPU local device with a lower
+	 * rating than a non-CPU local device
+	 */
+	return !curdev ||
+		newdev->rating > curdev->rating ||
+	       !cpumask_equal(curdev->cpumask, newdev->cpumask);
+}
+
+/*
+ * Check whether the new device is a better fit than curdev. curdev
+ * can be NULL !
+ */
+bool tick_check_replacement(struct clock_event_device *curdev,
+			    struct clock_event_device *newdev)
+{
+	if (!tick_check_percpu(curdev, newdev, smp_processor_id()))
+		return false;
+
+	return tick_check_preferred(curdev, newdev);
+}
+
+/*
+ * Check, if the new registered device should be used. Called with
+ * clockevents_lock held and interrupts disabled.
+ */
+void tick_check_new_device(struct clock_event_device *newdev)
+{
+	struct clock_event_device *curdev;
+	struct tick_device *td;
+	int cpu;
+
+	cpu = smp_processor_id();
+	td = &per_cpu(tick_cpu_device, cpu);
+	curdev = td->evtdev;
+
+	if (!tick_check_replacement(curdev, newdev))
+		goto out_bc;
+
+	if (!try_module_get(newdev->owner))
+		return;
+
+	/*
+	 * Replace the eventually existing device by the new
+	 * device. If the current device is the broadcast device, do
+	 * not give it back to the clockevents layer !
+	 */
+	if (tick_is_broadcast_device(curdev)) {
+		clockevents_shutdown(curdev);
+		curdev = NULL;
+	}
+	clockevents_exchange_device(curdev, newdev);
+	tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
+	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
+		tick_oneshot_notify();
+	return;
+
+out_bc:
+	/*
+	 * Can the new device be used as a broadcast device ?
+	 */
+	tick_install_broadcast_device(newdev, cpu);
+}
+
+/**
+ * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode
+ * @state:	The target state (enter/exit)
+ *
+ * The system enters/leaves a state, where affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
+ *
+ * Called with interrupts disabled, so clockevents_lock is not
+ * required here because the local clock event device cannot go away
+ * under us.
+ */
+int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+
+	if (!(td->evtdev->features & CLOCK_EVT_FEAT_C3STOP))
+		return 0;
+
+	return __tick_broadcast_oneshot_control(state);
+}
+EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
+
+#ifdef CONFIG_HOTPLUG_CPU
+void tick_assert_timekeeping_handover(void)
+{
+	WARN_ON_ONCE(tick_do_timer_cpu == smp_processor_id());
+}
+/*
+ * Stop the tick and transfer the timekeeping job away from a dying cpu.
+ */
+int tick_cpu_dying(unsigned int dying_cpu)
+{
+	/*
+	 * If the current CPU is the timekeeper, it's the only one that can
+	 * safely hand over its duty. Also all online CPUs are in stop
+	 * machine, guaranteed not to be idle, therefore there is no
+	 * concurrency and it's safe to pick any online successor.
+	 */
+	if (tick_do_timer_cpu == dying_cpu)
+		tick_do_timer_cpu = cpumask_first(cpu_online_mask);
+
+	/* Make sure the CPU won't try to retake the timekeeping duty */
+	tick_sched_timer_dying(dying_cpu);
+
+	/* Remove CPU from timer broadcasting */
+	tick_offline_cpu(dying_cpu);
+
+	return 0;
+}
+
+/*
+ * Shutdown an event device on the outgoing CPU:
+ *
+ * Called by the dying CPU during teardown, with clockevents_lock held
+ * and interrupts disabled.
+ */
+void tick_shutdown(void)
+{
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+	struct clock_event_device *dev = td->evtdev;
+
+	td->mode = TICKDEV_MODE_PERIODIC;
+	if (dev) {
+		clockevents_exchange_device(dev, NULL);
+		dev->event_handler = clockevents_handle_noop;
+		td->evtdev = NULL;
+	}
+}
+#endif
+
+/**
+ * tick_suspend_local - Suspend the local tick device
+ *
+ * Called from the local cpu for freeze with interrupts disabled.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_suspend_local(void)
+{
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+
+	clockevents_shutdown(td->evtdev);
+}
+
+/**
+ * tick_resume_local - Resume the local tick device
+ *
+ * Called from the local CPU for unfreeze or XEN resume magic.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_resume_local(void)
+{
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+	bool broadcast = tick_resume_check_broadcast();
+
+	clockevents_tick_resume(td->evtdev);
+	if (!broadcast) {
+		if (td->mode == TICKDEV_MODE_PERIODIC)
+			tick_setup_periodic(td->evtdev, 0);
+		else
+			tick_resume_oneshot();
+	}
+
+	/*
+	 * Ensure that hrtimers are up to date and the clockevents device
+	 * is reprogrammed correctly when high resolution timers are
+	 * enabled.
+	 */
+	hrtimers_resume_local();
+}
+
+/**
+ * tick_suspend - Suspend the tick and the broadcast device
+ *
+ * Called from syscore_suspend() via timekeeping_suspend with only one
+ * CPU online and interrupts disabled or from tick_unfreeze() under
+ * tick_freeze_lock.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_suspend(void)
+{
+	tick_suspend_local();
+	tick_suspend_broadcast();
+}
+
+/**
+ * tick_resume - Resume the tick and the broadcast device
+ *
+ * Called from syscore_resume() via timekeeping_resume with only one
+ * CPU online and interrupts disabled.
+ *
+ * No locks required. Nothing can change the per cpu device.
+ */
+void tick_resume(void)
+{
+	tick_resume_broadcast();
+	tick_resume_local();
+}
+
+#ifdef CONFIG_SUSPEND
+static DEFINE_RAW_SPINLOCK(tick_freeze_lock);
+static DEFINE_WAIT_OVERRIDE_MAP(tick_freeze_map, LD_WAIT_SLEEP);
+static unsigned int tick_freeze_depth;
+
+/**
+ * tick_freeze - Suspend the local tick and (possibly) timekeeping.
+ *
+ * Check if this is the last online CPU executing the function and if so,
+ * suspend timekeeping.  Otherwise suspend the local tick.
+ *
+ * Call with interrupts disabled.  Must be balanced with %tick_unfreeze().
+ * Interrupts must not be enabled before the subsequent %tick_unfreeze().
+ */
+void tick_freeze(void)
+{
+	raw_spin_lock(&tick_freeze_lock);
+
+	tick_freeze_depth++;
+	if (tick_freeze_depth == num_online_cpus()) {
+		trace_suspend_resume(TPS("timekeeping_freeze"),
+				     smp_processor_id(), true);
+		/*
+		 * All other CPUs have their interrupts disabled and are
+		 * suspended to idle. Other tasks have been frozen so there
+		 * is no scheduling happening. This means that there is no
+		 * concurrency in the system at this point. Therefore it is
+		 * okay to acquire a sleeping lock on PREEMPT_RT, such as a
+		 * spinlock, because the lock cannot be held by other CPUs
+		 * or threads and acquiring it cannot block.
+		 *
+		 * Inform lockdep about the situation.
+		 */
+		lock_map_acquire_try(&tick_freeze_map);
+		system_state = SYSTEM_SUSPEND;
+		sched_clock_suspend();
+		timekeeping_suspend();
+		lock_map_release(&tick_freeze_map);
+	} else {
+		tick_suspend_local();
+	}
+
+	raw_spin_unlock(&tick_freeze_lock);
+}
+
+/**
+ * tick_unfreeze - Resume the local tick and (possibly) timekeeping.
+ *
+ * Check if this is the first CPU executing the function and if so, resume
+ * timekeeping.  Otherwise resume the local tick.
+ *
+ * Call with interrupts disabled.  Must be balanced with %tick_freeze().
+ * Interrupts must not be enabled after the preceding %tick_freeze().
+ */
+void tick_unfreeze(void)
+{
+	raw_spin_lock(&tick_freeze_lock);
+
+	if (tick_freeze_depth == num_online_cpus()) {
+		/*
+		 * Similar to tick_freeze(). On resumption the first CPU may
+		 * acquire uncontended sleeping locks while other CPUs block on
+		 * tick_freeze_lock.
+		 */
+		lock_map_acquire_try(&tick_freeze_map);
+		timekeeping_resume();
+		sched_clock_resume();
+		lock_map_release(&tick_freeze_map);
+
+		system_state = SYSTEM_RUNNING;
+		trace_suspend_resume(TPS("timekeeping_freeze"),
+				     smp_processor_id(), false);
+	} else {
+		touch_softlockup_watchdog();
+		tick_resume_local();
+	}
+
+	tick_freeze_depth--;
+
+	raw_spin_unlock(&tick_freeze_lock);
+}
+#endif /* CONFIG_SUSPEND */
+
+/**
+ * tick_init - initialize the tick control
+ */
+void __init tick_init(void)
+{
+	tick_broadcast_init();
+	tick_nohz_init();
+}

linux-7.2.3/kernel/time/tick-internal.h

@@ -0,0 +1,213 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * tick internal variable and functions used by low/high res code
+ */
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+
+#include "timekeeping.h"
+#include "tick-sched.h"
+
+struct timer_events {
+	u64	local;
+	u64	global;
+};
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+
+# define TICK_DO_TIMER_NONE	-1
+# define TICK_DO_TIMER_BOOT	-2
+
+DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
+extern ktime_t tick_next_period;
+extern int tick_do_timer_cpu __read_mostly;
+
+extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
+extern void tick_handle_periodic(struct clock_event_device *dev);
+extern void tick_check_new_device(struct clock_event_device *dev);
+extern void tick_offline_cpu(unsigned int cpu);
+extern void tick_shutdown(void);
+extern void tick_suspend(void);
+extern void tick_resume(void);
+extern bool tick_check_replacement(struct clock_event_device *curdev,
+				   struct clock_event_device *newdev);
+extern void tick_install_replacement(struct clock_event_device *dev);
+extern int tick_is_oneshot_available(void);
+extern struct tick_device *tick_get_device(int cpu);
+
+extern int clockevents_tick_resume(struct clock_event_device *dev);
+/* Check, if the device is functional or a dummy for broadcast */
+static inline int tick_device_is_functional(struct clock_event_device *dev)
+{
+	return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
+}
+
+static inline enum clock_event_state clockevent_get_state(struct clock_event_device *dev)
+{
+	return dev->state_use_accessors;
+}
+
+static inline void clockevent_set_state(struct clock_event_device *dev,
+					enum clock_event_state state)
+{
+	dev->state_use_accessors = state;
+}
+
+extern void clockevents_shutdown(struct clock_event_device *dev);
+extern void clockevents_exchange_device(struct clock_event_device *old,
+					struct clock_event_device *new);
+extern void clockevents_switch_state(struct clock_event_device *dev,
+				     enum clock_event_state state);
+extern int clockevents_program_event(struct clock_event_device *dev,
+				     ktime_t expires, bool force);
+extern void clockevents_handle_noop(struct clock_event_device *dev);
+extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
+
+/* Broadcasting support */
+# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
+extern void tick_install_broadcast_device(struct clock_event_device *dev, int cpu);
+extern int tick_is_broadcast_device(struct clock_event_device *dev);
+extern void tick_suspend_broadcast(void);
+extern void tick_resume_broadcast(void);
+extern bool tick_resume_check_broadcast(void);
+extern void tick_broadcast_init(void);
+extern void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
+extern int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq);
+extern struct tick_device *tick_get_broadcast_device(void);
+extern struct cpumask *tick_get_broadcast_mask(void);
+extern const struct clock_event_device *tick_get_wakeup_device(int cpu);
+# else /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST: */
+static inline void tick_install_broadcast_device(struct clock_event_device *dev, int cpu) { }
+static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; }
+static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; }
+static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { }
+static inline void tick_suspend_broadcast(void) { }
+static inline void tick_resume_broadcast(void) { }
+static inline bool tick_resume_check_broadcast(void) { return false; }
+static inline void tick_broadcast_init(void) { }
+static inline int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq) { return -ENODEV; }
+
+/* Set the periodic handler in non broadcast mode */
+static inline void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
+{
+	dev->event_handler = tick_handle_periodic;
+}
+# endif /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST */
+
+#else /* !GENERIC_CLOCKEVENTS: */
+static inline void tick_suspend(void) { }
+static inline void tick_resume(void) { }
+#endif /* !GENERIC_CLOCKEVENTS */
+
+/* Oneshot related functions */
+#ifdef CONFIG_TICK_ONESHOT
+extern void tick_setup_oneshot(struct clock_event_device *newdev,
+			       void (*handler)(struct clock_event_device *),
+			       ktime_t nextevt);
+extern int tick_program_event(ktime_t expires, int force);
+extern void tick_oneshot_notify(void);
+extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
+extern void tick_resume_oneshot(void);
+static inline bool tick_oneshot_possible(void) { return true; }
+extern int tick_oneshot_mode_active(void);
+extern void tick_clock_notify(void);
+extern int tick_check_oneshot_change(int allow_nohz);
+extern int tick_init_highres(void);
+#else /* !CONFIG_TICK_ONESHOT: */
+static inline
+void tick_setup_oneshot(struct clock_event_device *newdev,
+			void (*handler)(struct clock_event_device *),
+			ktime_t nextevt) { BUG(); }
+static inline void tick_resume_oneshot(void) { BUG(); }
+static inline int tick_program_event(ktime_t expires, int force) { return 0; }
+static inline void tick_oneshot_notify(void) { }
+static inline bool tick_oneshot_possible(void) { return false; }
+static inline int tick_oneshot_mode_active(void) { return 0; }
+static inline void tick_clock_notify(void) { }
+static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
+#endif /* !CONFIG_TICK_ONESHOT */
+
+/* Functions related to oneshot broadcasting */
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
+extern void tick_broadcast_switch_to_oneshot(void);
+extern int tick_broadcast_oneshot_active(void);
+extern void tick_check_oneshot_broadcast_this_cpu(void);
+bool tick_broadcast_oneshot_available(void);
+extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
+#else /* !(BROADCAST && ONESHOT): */
+static inline void tick_broadcast_switch_to_oneshot(void) { }
+static inline int tick_broadcast_oneshot_active(void) { return 0; }
+static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
+static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
+#endif /* !(BROADCAST && ONESHOT) */
+
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU)
+extern void tick_broadcast_offline(unsigned int cpu);
+#else
+static inline void tick_broadcast_offline(unsigned int cpu) { }
+#endif
+
+/* NO_HZ_FULL internal */
+#ifdef CONFIG_NO_HZ_FULL
+extern void tick_nohz_init(void);
+# else
+static inline void tick_nohz_init(void) { }
+#endif
+
+#ifdef CONFIG_NO_HZ_COMMON
+extern void timers_update_nohz(void);
+extern u64 get_jiffies_update(unsigned long *basej);
+# ifdef CONFIG_SMP
+extern struct static_key_false timers_migration_enabled;
+extern void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem,
+					      struct timer_events *tevt,
+					      unsigned int cpu);
+extern void timer_lock_remote_bases(unsigned int cpu);
+extern void timer_unlock_remote_bases(unsigned int cpu);
+extern bool timer_base_is_idle(void);
+extern void timer_expire_remote(unsigned int cpu);
+# endif
+#else /* CONFIG_NO_HZ_COMMON */
+static inline void timers_update_nohz(void) { }
+#endif
+
+DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
+
+extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem);
+u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle);
+void timer_clear_idle(void);
+
+#define CLOCK_SET_WALL							\
+	(BIT(HRTIMER_BASE_REALTIME) | BIT(HRTIMER_BASE_REALTIME_SOFT) |	\
+	 BIT(HRTIMER_BASE_TAI) | BIT(HRTIMER_BASE_TAI_SOFT))
+
+#define CLOCK_SET_BOOT							\
+	(BIT(HRTIMER_BASE_BOOTTIME) | BIT(HRTIMER_BASE_BOOTTIME_SOFT))
+
+void clock_was_set(unsigned int bases);
+void clock_was_set_delayed(void);
+
+void hrtimers_resume_local(void);
+
+/* Since jiffies uses a simple TICK_NSEC multiplier
+ * conversion, the .shift value could be zero. However
+ * this would make NTP adjustments impossible as they are
+ * in units of 1/2^.shift. Thus we use JIFFIES_SHIFT to
+ * shift both the nominator and denominator the same
+ * amount, and give ntp adjustments in units of 1/2^8
+ *
+ * The value 8 is somewhat carefully chosen, as anything
+ * larger can result in overflows. TICK_NSEC grows as HZ
+ * shrinks, so values greater than 8 overflow 32bits when
+ * HZ=100.
+ */
+#if HZ < 34
+#define JIFFIES_SHIFT	6
+#elif HZ < 67
+#define JIFFIES_SHIFT	7
+#else
+#define JIFFIES_SHIFT	8
+#endif
+
+extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);

linux-7.2.3/kernel/time/tick-legacy.c

@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Timer tick function for architectures that lack generic clockevents,
+ * consolidated here from m68k/ia64/parisc/arm.
+ */
+
+#include <linux/irq.h>
+#include <linux/profile.h>
+#include <linux/timekeeper_internal.h>
+
+#include "tick-internal.h"
+
+/**
+ * legacy_timer_tick() - advances the timekeeping infrastructure
+ * @ticks:	number of ticks, that have elapsed since the last call.
+ *
+ * This is used by platforms that have not been converted to
+ * generic clockevents.
+ *
+ * If 'ticks' is zero, the CPU is not handling timekeeping, so
+ * only perform process accounting and profiling.
+ *
+ * Must be called with interrupts disabled.
+ */
+void legacy_timer_tick(unsigned long ticks)
+{
+	if (ticks) {
+		raw_spin_lock(&jiffies_lock);
+		write_seqcount_begin(&jiffies_seq);
+		do_timer(ticks);
+		write_seqcount_end(&jiffies_seq);
+		raw_spin_unlock(&jiffies_lock);
+		update_wall_time();
+	}
+	update_process_times(user_mode(get_irq_regs()));
+	profile_tick(CPU_PROFILING);
+}

linux-7.2.3/kernel/time/tick-oneshot.c

@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains functions which manage high resolution tick
+ * related events.
+ *
+ * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+
+#include "tick-internal.h"
+
+/**
+ * tick_program_event - program the CPU local timer device for the next event
+ * @expires: the time at which the next timer event should occur
+ * @force: flag to force reprograming even if the event time hasn't changed
+ *
+ * Return: 0 on success, negative error code on failure
+ */
+int tick_program_event(ktime_t expires, int force)
+{
+	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
+
+	if (unlikely(expires == KTIME_MAX)) {
+		/*
+		 * We don't need the clock event device any more, stop it.
+		 */
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED);
+		dev->next_event = KTIME_MAX;
+		return 0;
+	}
+
+	if (unlikely(clockevent_state_oneshot_stopped(dev))) {
+		/*
+		 * We need the clock event again, configure it in ONESHOT mode
+		 * before using it.
+		 */
+		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
+	}
+
+	return clockevents_program_event(dev, expires, force);
+}
+
+/**
+ * tick_resume_oneshot - resume oneshot mode
+ */
+void tick_resume_oneshot(void)
+{
+	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
+
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
+	clockevents_program_event(dev, ktime_get(), true);
+}
+
+/**
+ * tick_setup_oneshot - setup the event device for oneshot mode (hres or nohz)
+ * @newdev: Pointer to the clock event device to configure
+ * @handler: Function to be called when the event device triggers an interrupt
+ * @next_event: Initial expiry time for the next event (in ktime)
+ *
+ * Configures the specified clock event device for onshot mode,
+ * assigns the given handler as its event callback, and programs
+ * the device to trigger at the specified next event time.
+ */
+void tick_setup_oneshot(struct clock_event_device *newdev,
+			void (*handler)(struct clock_event_device *),
+			ktime_t next_event)
+{
+	newdev->event_handler = handler;
+	clockevents_switch_state(newdev, CLOCK_EVT_STATE_ONESHOT);
+	clockevents_program_event(newdev, next_event, true);
+}
+
+/**
+ * tick_switch_to_oneshot - switch to oneshot mode
+ * @handler: function to call when an event occurs on the tick device
+ *
+ * Return: 0 on success, -EINVAL if the tick device is not present,
+ *         not functional, or does not support oneshot mode.
+ */
+int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
+{
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+	struct clock_event_device *dev = td->evtdev;
+
+	if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
+		    !tick_device_is_functional(dev)) {
+
+		pr_info("Clockevents: could not switch to one-shot mode:");
+		if (!dev) {
+			pr_cont(" no tick device\n");
+		} else {
+			if (!tick_device_is_functional(dev))
+				pr_cont(" %s is not functional.\n", dev->name);
+			else
+				pr_cont(" %s does not support one-shot mode.\n",
+					dev->name);
+		}
+		return -EINVAL;
+	}
+
+	td->mode = TICKDEV_MODE_ONESHOT;
+	dev->event_handler = handler;
+	clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
+	tick_broadcast_switch_to_oneshot();
+	return 0;
+}
+
+/**
+ * tick_oneshot_mode_active - check whether the system is in oneshot mode
+ *
+ * Return: 1 when either nohz or highres are enabled, otherwise 0.
+ */
+int tick_oneshot_mode_active(void)
+{
+	unsigned long flags;
+	int ret;
+
+	local_irq_save(flags);
+	ret = __this_cpu_read(tick_cpu_device.mode) == TICKDEV_MODE_ONESHOT;
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+/**
+ * tick_init_highres - switch to high resolution mode
+ *
+ * Called with interrupts disabled.
+ *
+ * Return: 0 on success, -EINVAL if the tick device cannot switch
+ *         to oneshot/high-resolution mode.
+ */
+int tick_init_highres(void)
+{
+	return tick_switch_to_oneshot(hrtimer_interrupt);
+}
+#endif

linux-7.2.3/kernel/time/tick-sched.h

@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TICK_SCHED_H
+#define _TICK_SCHED_H
+
+#include <linux/hrtimer.h>
+
+enum tick_device_mode {
+	TICKDEV_MODE_PERIODIC,
+	TICKDEV_MODE_ONESHOT,
+};
+
+struct tick_device {
+	struct clock_event_device *evtdev;
+	enum tick_device_mode mode;
+};
+
+/* The CPU is in the tick idle mode */
+#define TS_FLAG_INIDLE		BIT(0)
+/* The idle tick has been stopped */
+#define TS_FLAG_STOPPED		BIT(1)
+/*
+ * Indicator that the CPU is actively in the tick idle mode;
+ * it is reset during irq handling phases.
+ */
+#define TS_FLAG_IDLE_ACTIVE	BIT(2)
+/* CPU was the last one doing do_timer before going idle */
+#define TS_FLAG_DO_TIMER_LAST	BIT(3)
+/* NO_HZ is enabled */
+#define TS_FLAG_NOHZ		BIT(4)
+/* High resolution tick mode */
+#define TS_FLAG_HIGHRES		BIT(5)
+
+/**
+ * struct tick_sched - sched tick emulation and no idle tick control/stats
+ *
+ * @flags:		State flags gathering the TS_FLAG_* features
+ * @got_idle_tick:	Tick timer function has run with @inidle set
+ * @stalled_jiffies:	Number of stalled jiffies detected across ticks
+ * @last_tick_jiffies:	Value of jiffies seen on last tick
+ * @sched_timer:	hrtimer to schedule the periodic tick in high
+ *			resolution mode
+ * @last_tick:		Store the last tick expiry time when the tick
+ *			timer is modified for nohz sleeps. This is necessary
+ *			to resume the tick timer operation in the timeline
+ *			when the CPU returns from nohz sleep.
+ * @next_tick:		Next tick to be fired when in dynticks mode.
+ * @idle_waketime:	Time when the idle was interrupted
+ * @idle_entrytime:	Time when the idle call was entered
+ * @last_jiffies:	Base jiffies snapshot when next event was last computed
+ * @timer_expires_base:	Base time clock monotonic for @timer_expires
+ * @timer_expires:	Anticipated timer expiration time (in case sched tick is stopped)
+ * @next_timer:		Expiry time of next expiring timer for debugging purpose only
+ * @idle_expires:	Next tick in idle, for debugging purpose only
+ * @idle_calls:		Total number of idle calls
+ * @idle_sleeps:	Number of idle calls, where the sched tick was stopped
+ * @tick_dep_mask:	Tick dependency mask - is set, if someone needs the tick
+ * @check_clocks:	Notification mechanism about clocksource changes
+ */
+struct tick_sched {
+	/* Common flags */
+	unsigned long			flags;
+
+	/* Tick handling: jiffies stall check */
+	unsigned int			stalled_jiffies;
+	unsigned long			last_tick_jiffies;
+
+	/* Tick handling */
+	struct hrtimer			sched_timer;
+	ktime_t				last_tick;
+	ktime_t				next_tick;
+	ktime_t				idle_waketime;
+	unsigned int			got_idle_tick;
+
+	/* Idle entry */
+	ktime_t				idle_entrytime;
+
+	/* Tick stop */
+	unsigned long			last_jiffies;
+	u64				timer_expires_base;
+	u64				timer_expires;
+	u64				next_timer;
+	ktime_t				idle_expires;
+	unsigned long			idle_calls;
+	unsigned long			idle_sleeps;
+
+	/* Full dynticks handling */
+	atomic_t			tick_dep_mask;
+
+	/* Clocksource changes */
+	unsigned long			check_clocks;
+};
+
+extern struct tick_sched *tick_get_tick_sched(int cpu);
+
+extern void tick_setup_sched_timer(bool hrtimer);
+#if defined CONFIG_TICK_ONESHOT
+extern void tick_sched_timer_dying(int cpu);
+#else
+static inline void tick_sched_timer_dying(int cpu) { }
+#endif
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern int __tick_broadcast_oneshot_control(enum tick_broadcast_state state);
+#else
+static inline int
+__tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	return -EBUSY;
+}
+#endif
+
+#endif

linux-7.2.3/kernel/time/time_test.c

@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: LGPL-2.1+
+
+#include <kunit/test.h>
+#include <linux/time.h>
+
+/*
+ * Traditional implementation of leap year evaluation, but note that long
+ * is a signed type and the tests do cover negative year values. So this
+ * can't use the is_leap_year() helper from rtc.h.
+ */
+static bool is_leap(long year)
+{
+	return year % 4 == 0 && (year % 100 != 0 || year % 400 == 0);
+}
+
+/*
+ * Gets the last day of a month.
+ */
+static int last_day_of_month(long year, int month)
+{
+	if (month == 2)
+		return 28 + is_leap(year);
+	if (month == 4 || month == 6 || month == 9 || month == 11)
+		return 30;
+	return 31;
+}
+
+/*
+ * Advances a date by one day.
+ */
+static void advance_date(long *year, int *month, int *mday, int *yday)
+{
+	if (*mday != last_day_of_month(*year, *month)) {
+		++*mday;
+		++*yday;
+		return;
+	}
+
+	*mday = 1;
+	if (*month != 12) {
+		++*month;
+		++*yday;
+		return;
+	}
+
+	*month = 1;
+	*yday  = 0;
+	++*year;
+}
+
+/*
+ * Checks every day in a 160000 years interval centered at 1970-01-01
+ * against the expected result.
+ */
+static void time64_to_tm_test_date_range(struct kunit *test)
+{
+	/*
+	 * 80000 years	= (80000 / 400) * 400 years
+	 *		= (80000 / 400) * 146097 days
+	 *		= (80000 / 400) * 146097 * 86400 seconds
+	 */
+	time64_t total_secs = ((time64_t) 80000) / 400 * 146097 * 86400;
+	long year = 1970 - 80000;
+	int month = 1;
+	int mdday = 1;
+	int yday = 0;
+
+	struct tm result;
+	time64_t secs;
+	s64 days;
+
+	for (secs = -total_secs; secs <= total_secs; secs += 86400) {
+
+		time64_to_tm(secs, 0, &result);
+
+		days = div_s64(secs, 86400);
+
+		#define FAIL_MSG "%05ld/%02d/%02d (%2d) : %lld", \
+			year, month, mdday, yday, days
+
+		KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG);
+		KUNIT_ASSERT_EQ_MSG(test, month - 1, result.tm_mon, FAIL_MSG);
+		KUNIT_ASSERT_EQ_MSG(test, mdday, result.tm_mday, FAIL_MSG);
+		KUNIT_ASSERT_EQ_MSG(test, yday, result.tm_yday, FAIL_MSG);
+
+		advance_date(&year, &month, &mdday, &yday);
+	}
+}
+
+static struct kunit_case time_test_cases[] = {
+	KUNIT_CASE_SLOW(time64_to_tm_test_date_range),
+	{}
+};
+
+static struct kunit_suite time_test_suite = {
+	.name = "time_test_cases",
+	.test_cases = time_test_cases,
+};
+
+kunit_test_suite(time_test_suite);
+MODULE_DESCRIPTION("time unit test suite");
+MODULE_LICENSE("GPL");

linux-7.2.3/kernel/time/timeconst.bc

@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+scale=0
+
+define gcd(a,b) {
+	auto t;
+	while (b) {
+		t = b;
+		b = a % b;
+		a = t;
+	}
+	return a;
+}
+
+/* Division by reciprocal multiplication. */
+define fmul(b,n,d) {
+       return (2^b*n+d-1)/d;
+}
+
+/* Adjustment factor when a ceiling value is used.  Use as:
+   (imul * n) + (fmulxx * n + fadjxx) >> xx) */
+define fadj(b,n,d) {
+	auto v;
+	d = d/gcd(n,d);
+	v = 2^b*(d-1)/d;
+	return v;
+}
+
+/* Compute the appropriate mul/adj values as well as a shift count,
+   which brings the mul value into the range 2^b-1 <= x < 2^b.  Such
+   a shift value will be correct in the signed integer range and off
+   by at most one in the upper half of the unsigned range. */
+define fmuls(b,n,d) {
+	auto s, m;
+	for (s = 0; 1; s++) {
+		m = fmul(s,n,d);
+		if (m >= 2^(b-1))
+			return s;
+	}
+	return 0;
+}
+
+define timeconst(hz) {
+	print "/* Automatically generated by kernel/time/timeconst.bc */\n"
+	print "/* Time conversion constants for HZ == ", hz, " */\n"
+	print "\n"
+
+	print "#ifndef KERNEL_TIMECONST_H\n"
+	print "#define KERNEL_TIMECONST_H\n\n"
+
+	print "#include <linux/param.h>\n"
+	print "#include <linux/types.h>\n\n"
+
+	print "#if HZ != ", hz, "\n"
+	print "#error \qinclude/generated/timeconst.h has the wrong HZ value!\q\n"
+	print "#endif\n\n"
+
+	if (hz < 2) {
+		print "#error Totally bogus HZ value!\n"
+	} else {
+		s=fmuls(32,1000,hz)
+		obase=16
+		print "#define HZ_TO_MSEC_MUL32\tU64_C(0x", fmul(s,1000,hz), ")\n"
+		print "#define HZ_TO_MSEC_ADJ32\tU64_C(0x", fadj(s,1000,hz), ")\n"
+		obase=10
+		print "#define HZ_TO_MSEC_SHR32\t", s, "\n"
+
+		s=fmuls(32,hz,1000)
+		obase=16
+		print "#define MSEC_TO_HZ_MUL32\tU64_C(0x", fmul(s,hz,1000), ")\n"
+		print "#define MSEC_TO_HZ_ADJ32\tU64_C(0x", fadj(s,hz,1000), ")\n"
+		obase=10
+		print "#define MSEC_TO_HZ_SHR32\t", s, "\n"
+
+		obase=10
+		cd=gcd(hz,1000)
+		print "#define HZ_TO_MSEC_NUM\t\t", 1000/cd, "\n"
+		print "#define HZ_TO_MSEC_DEN\t\t", hz/cd, "\n"
+		print "#define MSEC_TO_HZ_NUM\t\t", hz/cd, "\n"
+		print "#define MSEC_TO_HZ_DEN\t\t", 1000/cd, "\n"
+		print "\n"
+
+		s=fmuls(32,1000000,hz)
+		obase=16
+		print "#define HZ_TO_USEC_MUL32\tU64_C(0x", fmul(s,1000000,hz), ")\n"
+		print "#define HZ_TO_USEC_ADJ32\tU64_C(0x", fadj(s,1000000,hz), ")\n"
+		obase=10
+		print "#define HZ_TO_USEC_SHR32\t", s, "\n"
+
+		s=fmuls(32,hz,1000000)
+		obase=16
+		print "#define USEC_TO_HZ_MUL32\tU64_C(0x", fmul(s,hz,1000000), ")\n"
+		print "#define USEC_TO_HZ_ADJ32\tU64_C(0x", fadj(s,hz,1000000), ")\n"
+		obase=10
+		print "#define USEC_TO_HZ_SHR32\t", s, "\n"
+
+		obase=10
+		cd=gcd(hz,1000000)
+		print "#define HZ_TO_USEC_NUM\t\t", 1000000/cd, "\n"
+		print "#define HZ_TO_USEC_DEN\t\t", hz/cd, "\n"
+		print "#define USEC_TO_HZ_NUM\t\t", hz/cd, "\n"
+		print "#define USEC_TO_HZ_DEN\t\t", 1000000/cd, "\n"
+
+		cd=gcd(hz,1000000000)
+		print "#define HZ_TO_NSEC_NUM\t\t", 1000000000/cd, "\n"
+		print "#define HZ_TO_NSEC_DEN\t\t", hz/cd, "\n"
+		print "#define NSEC_TO_HZ_NUM\t\t", hz/cd, "\n"
+		print "#define NSEC_TO_HZ_DEN\t\t", 1000000000/cd, "\n"
+		print "\n"
+
+		print "#endif /* KERNEL_TIMECONST_H */\n"
+	}
+	halt
+}
+
+hz = read();
+timeconst(hz)

linux-7.2.3/kernel/time/timeconv.c

@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: LGPL-2.0+
+/*
+ * Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc.
+ * This file is part of the GNU C Library.
+ * Contributed by Paul Eggert (eggert@twinsun.com).
+ *
+ * The GNU C Library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Library General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * The GNU C Library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Library General Public License for more details.
+ *
+ * You should have received a copy of the GNU Library General Public
+ * License along with the GNU C Library; see the file COPYING.LIB.  If not,
+ * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ */
+
+/*
+ * Converts the calendar time to broken-down time representation
+ *
+ * 2009-7-14:
+ *   Moved from glibc-2.6 to kernel by Zhaolei<zhaolei@cn.fujitsu.com>
+ * 2021-06-02:
+ *   Reimplemented by Cassio Neri <cassio.neri@gmail.com>
+ */
+
+#include <linux/time.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+
+#define SECS_PER_HOUR	(60 * 60)
+#define SECS_PER_DAY	(SECS_PER_HOUR * 24)
+
+/**
+ * time64_to_tm - converts the calendar time to local broken-down time
+ *
+ * @totalsecs:	the number of seconds elapsed since 00:00:00 on January 1, 1970,
+ *		Coordinated Universal Time (UTC).
+ * @offset:	offset seconds adding to totalsecs.
+ * @result:	pointer to struct tm variable to receive broken-down time
+ */
+void time64_to_tm(time64_t totalsecs, int offset, struct tm *result)
+{
+	u32 u32tmp, day_of_century, year_of_century, day_of_year, month, day;
+	u64 u64tmp, udays, century, year;
+	bool is_Jan_or_Feb, is_leap_year;
+	long days, rem;
+	int remainder;
+
+	days = div_s64_rem(totalsecs, SECS_PER_DAY, &remainder);
+	rem = remainder;
+	rem += offset;
+	while (rem < 0) {
+		rem += SECS_PER_DAY;
+		--days;
+	}
+	while (rem >= SECS_PER_DAY) {
+		rem -= SECS_PER_DAY;
+		++days;
+	}
+
+	result->tm_hour = rem / SECS_PER_HOUR;
+	rem %= SECS_PER_HOUR;
+	result->tm_min = rem / 60;
+	result->tm_sec = rem % 60;
+
+	/* January 1, 1970 was a Thursday. */
+	result->tm_wday = (4 + days) % 7;
+	if (result->tm_wday < 0)
+		result->tm_wday += 7;
+
+	/*
+	 * The following algorithm is, basically, Proposition 6.3 of Neri
+	 * and Schneider [1]. In a few words: it works on the computational
+	 * (fictitious) calendar where the year starts in March, month = 2
+	 * (*), and finishes in February, month = 13. This calendar is
+	 * mathematically convenient because the day of the year does not
+	 * depend on whether the year is leap or not. For instance:
+	 *
+	 * March 1st		0-th day of the year;
+	 * ...
+	 * April 1st		31-st day of the year;
+	 * ...
+	 * January 1st		306-th day of the year; (Important!)
+	 * ...
+	 * February 28th	364-th day of the year;
+	 * February 29th	365-th day of the year (if it exists).
+	 *
+	 * After having worked out the date in the computational calendar
+	 * (using just arithmetics) it's easy to convert it to the
+	 * corresponding date in the Gregorian calendar.
+	 *
+	 * [1] "Euclidean Affine Functions and Applications to Calendar
+	 * Algorithms". https://arxiv.org/abs/2102.06959
+	 *
+	 * (*) The numbering of months follows tm more closely and thus,
+	 * is slightly different from [1].
+	 */
+
+	udays	= ((u64) days) + 2305843009213814918ULL;
+
+	u64tmp		= 4 * udays + 3;
+	century		= div64_u64_rem(u64tmp, 146097, &u64tmp);
+	day_of_century	= (u32) (u64tmp / 4);
+
+	u32tmp		= 4 * day_of_century + 3;
+	u64tmp		= 2939745ULL * u32tmp;
+	year_of_century	= upper_32_bits(u64tmp);
+	day_of_year	= lower_32_bits(u64tmp) / 2939745 / 4;
+
+	year		= 100 * century + year_of_century;
+	is_leap_year	= year_of_century ? !(year_of_century % 4) : !(century % 4);
+
+	u32tmp		= 2141 * day_of_year + 132377;
+	month		= u32tmp >> 16;
+	day		= ((u16) u32tmp) / 2141;
+
+	/*
+	 * Recall that January 1st is the 306-th day of the year in the
+	 * computational (not Gregorian) calendar.
+	 */
+	is_Jan_or_Feb	= day_of_year >= 306;
+
+	/* Convert to the Gregorian calendar and adjust to Unix time. */
+	year		= year + is_Jan_or_Feb - 6313183731940000ULL;
+	month		= is_Jan_or_Feb ? month - 12 : month;
+	day		= day + 1;
+	day_of_year	+= is_Jan_or_Feb ? -306 : 31 + 28 + is_leap_year;
+
+	/* Convert to tm's format. */
+	result->tm_year = (long) (year - 1900);
+	result->tm_mon  = (int) month;
+	result->tm_mday = (int) day;
+	result->tm_yday = (int) day_of_year;
+}
+EXPORT_SYMBOL(time64_to_tm);

linux-7.2.3/kernel/time/timecounter.c

@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Based on clocksource code. See commit 74d23cc704d1
+ */
+#include <linux/export.h>
+#include <linux/timecounter.h>
+
+void timecounter_init(struct timecounter *tc,
+		      struct cyclecounter *cc,
+		      u64 start_tstamp)
+{
+	tc->cc = cc;
+	tc->cycle_last = cc->read(cc);
+	tc->nsec = start_tstamp;
+	tc->mask = (1ULL << cc->shift) - 1;
+	tc->frac = 0;
+}
+EXPORT_SYMBOL_GPL(timecounter_init);
+
+/**
+ * timecounter_read_delta - get nanoseconds since last call of this function
+ * @tc:         Pointer to time counter
+ *
+ * When the underlying cycle counter runs over, this will be handled
+ * correctly as long as it does not run over more than once between
+ * calls.
+ *
+ * The first call to this function for a new time counter initializes
+ * the time tracking and returns an undefined result.
+ */
+static u64 timecounter_read_delta(struct timecounter *tc)
+{
+	u64 cycle_now, cycle_delta;
+	u64 ns_offset;
+
+	/* read cycle counter: */
+	cycle_now = tc->cc->read(tc->cc);
+
+	/* calculate the delta since the last timecounter_read_delta(): */
+	cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask;
+
+	/* convert to nanoseconds: */
+	ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta,
+					tc->mask, &tc->frac);
+
+	/* update time stamp of timecounter_read_delta() call: */
+	tc->cycle_last = cycle_now;
+
+	return ns_offset;
+}
+
+u64 timecounter_read(struct timecounter *tc)
+{
+	u64 nsec;
+
+	/* increment time by nanoseconds since last call */
+	nsec = timecounter_read_delta(tc);
+	nsec += tc->nsec;
+	tc->nsec = nsec;
+
+	return nsec;
+}
+EXPORT_SYMBOL_GPL(timecounter_read);
+

linux-7.2.3/kernel/time/timekeeping.h

@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _KERNEL_TIME_TIMEKEEPING_H
+#define _KERNEL_TIME_TIMEKEEPING_H
+/*
+ * Internal interfaces for kernel/time/
+ */
+extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq,
+					    ktime_t *offs_real,
+					    ktime_t *offs_boot,
+					    ktime_t *offs_tai);
+
+bool ktime_expiry_to_cycles(enum clocksource_ids id, ktime_t expires_ns, u64 *cycles);
+
+extern int timekeeping_valid_for_hres(void);
+extern u64 timekeeping_max_deferment(void);
+extern void timekeeping_warp_clock(void);
+extern int timekeeping_suspend(void);
+extern void timekeeping_resume(void);
+#ifdef CONFIG_GENERIC_SCHED_CLOCK
+extern int sched_clock_suspend(void);
+extern void sched_clock_resume(void);
+#else
+static inline int sched_clock_suspend(void) { return 0; }
+static inline void sched_clock_resume(void) { }
+#endif
+
+extern void update_process_times(int user);
+extern void do_timer(unsigned long ticks);
+extern void update_wall_time(void);
+
+extern raw_spinlock_t jiffies_lock;
+extern seqcount_raw_spinlock_t jiffies_seq;
+
+#define CS_NAME_LEN	32
+
+#endif

linux-7.2.3/kernel/time/timekeeping_debug.c

@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * debugfs file to track time spent in suspend
+ *
+ * Copyright (c) 2011, Google, Inc.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+#include <linux/suspend.h>
+#include <linux/time.h>
+
+#include "timekeeping_internal.h"
+
+#define NUM_BINS 32
+
+/* Incremented every time mg_floor is updated */
+DEFINE_PER_CPU(unsigned long, timekeeping_mg_floor_swaps);
+
+static unsigned int sleep_time_bin[NUM_BINS] = {0};
+
+static int tk_debug_sleep_time_show(struct seq_file *s, void *data)
+{
+	unsigned int bin;
+	seq_puts(s, "      time (secs)        count\n");
+	seq_puts(s, "------------------------------\n");
+	for (bin = 0; bin < 32; bin++) {
+		if (sleep_time_bin[bin] == 0)
+			continue;
+		seq_printf(s, "%10u - %-10u %4u\n",
+			bin ? 1 << (bin - 1) : 0, 1 << bin,
+				sleep_time_bin[bin]);
+	}
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(tk_debug_sleep_time);
+
+static int __init tk_debug_sleep_time_init(void)
+{
+	debugfs_create_file("sleep_time", 0444, NULL, NULL,
+			    &tk_debug_sleep_time_fops);
+	return 0;
+}
+late_initcall(tk_debug_sleep_time_init);
+
+void tk_debug_account_sleep_time(const struct timespec64 *t)
+{
+	/* Cap bin index so we don't overflow the array */
+	int bin = min(fls(t->tv_sec), NUM_BINS-1);
+
+	sleep_time_bin[bin]++;
+	pm_deferred_pr_dbg("Timekeeping suspended for %lld.%03lu seconds\n",
+			   (s64)t->tv_sec, t->tv_nsec / NSEC_PER_MSEC);
+}
+
+unsigned long timekeeping_get_mg_floor_swaps(void)
+{
+	unsigned long sum = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		sum += data_race(per_cpu(timekeeping_mg_floor_swaps, cpu));
+
+	return sum;
+}

linux-7.2.3/kernel/time/timekeeping_internal.h

@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TIMEKEEPING_INTERNAL_H
+#define _TIMEKEEPING_INTERNAL_H
+
+#include <linux/clocksource.h>
+#include <linux/spinlock.h>
+#include <linux/time.h>
+
+/*
+ * timekeeping debug functions
+ */
+#ifdef CONFIG_DEBUG_FS
+
+DECLARE_PER_CPU(unsigned long, timekeeping_mg_floor_swaps);
+
+static inline void timekeeping_inc_mg_floor_swaps(void)
+{
+	this_cpu_inc(timekeeping_mg_floor_swaps);
+}
+
+extern void tk_debug_account_sleep_time(const struct timespec64 *t);
+
+#else
+
+#define tk_debug_account_sleep_time(x)
+
+static inline void timekeeping_inc_mg_floor_swaps(void)
+{
+}
+
+#endif
+
+static inline u64 clocksource_delta(u64 now, u64 last, u64 mask, u64 max_delta)
+{
+	u64 ret = (now - last) & mask;
+
+	/*
+	 * Prevent time going backwards by checking the result against
+	 * @max_delta. If greater, return 0.
+	 */
+	return ret > max_delta ? 0 : ret;
+}
+
+/* Semi public for serialization of non timekeeper VDSO updates. */
+unsigned long timekeeper_lock_irqsave(void);
+void timekeeper_unlock_irqrestore(unsigned long flags);
+
+/* NTP specific interface to access the current seconds value */
+long ktime_get_ntp_seconds(unsigned int id);
+
+#endif /* _TIMEKEEPING_INTERNAL_H */

linux-7.2.3/kernel/time/timer_list.c

@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * List pending timers
+ *
+ * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+#include <linux/nmi.h>
+
+#include <linux/uaccess.h>
+
+#include "tick-internal.h"
+
+struct timer_list_iter {
+	int cpu;
+	bool second_pass;
+	u64 now;
+};
+
+/*
+ * This allows printing both to /proc/timer_list and
+ * to the console (on SysRq-Q):
+ */
+__printf(2, 3)
+static void SEQ_printf(struct seq_file *m, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+
+	if (m)
+		seq_vprintf(m, fmt, args);
+	else
+		vprintk(fmt, args);
+
+	va_end(args);
+}
+
+static void
+print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer,
+	    int idx, u64 now)
+{
+	SEQ_printf(m, " #%d: <%p>, %ps", idx, taddr, ACCESS_PRIVATE(timer, function));
+	SEQ_printf(m, ", S:%02x", timer->is_queued);
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n",
+		(unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)),
+		(unsigned long long)ktime_to_ns(hrtimer_get_expires(timer)),
+		(long long)(ktime_to_ns(hrtimer_get_softexpires(timer)) - now),
+		(long long)(ktime_to_ns(hrtimer_get_expires(timer)) - now));
+}
+
+static void print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
+{
+	struct timerqueue_linked_node *curr;
+	struct hrtimer *timer, tmp;
+	unsigned long next = 0, i;
+	unsigned long flags;
+
+next_one:
+	i = 0;
+
+	touch_nmi_watchdog();
+
+	raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
+
+	curr = timerqueue_linked_first(&base->active);
+	/*
+	 * Crude but we have to do this O(N*N) thing, because
+	 * we have to unlock the base when printing:
+	 */
+	while (curr && i < next) {
+		curr = timerqueue_linked_next(curr);
+		i++;
+	}
+
+	if (curr) {
+
+		timer = container_of(curr, struct hrtimer, node);
+		tmp = *timer;
+		raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+
+		print_timer(m, timer, &tmp, i, now);
+		next++;
+		goto next_one;
+	}
+	raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
+}
+
+static void
+print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
+{
+	SEQ_printf(m, "  .base:       %p\n", base);
+	SEQ_printf(m, "  .index:      %d\n", base->index);
+
+	SEQ_printf(m, "  .resolution: %u nsecs\n", hrtimer_resolution);
+#ifdef CONFIG_HIGH_RES_TIMERS
+	SEQ_printf(m, "  .offset:     %Ld nsecs\n",
+		   (long long) base->offset);
+#endif
+	SEQ_printf(m,   "active timers:\n");
+	print_active_timers(m, base, now + ktime_to_ns(base->offset));
+}
+
+static void print_cpu(struct seq_file *m, int cpu, u64 now)
+{
+	struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
+	int i;
+
+	SEQ_printf(m, "cpu: %d\n", cpu);
+	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+		SEQ_printf(m, " clock %d:\n", i);
+		print_base(m, cpu_base->clock_base + i, now);
+	}
+#define P(x) \
+	SEQ_printf(m, "  .%-15s: %Lu\n", #x, \
+		   (unsigned long long)(cpu_base->x))
+#define P_ns(x) \
+	SEQ_printf(m, "  .%-15s: %Lu nsecs\n", #x, \
+		   (unsigned long long)(ktime_to_ns(cpu_base->x)))
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+	P_ns(expires_next);
+	P(hres_active);
+	P(nr_events);
+	P(nr_retries);
+	P(nr_hangs);
+	P(max_hang_time);
+#endif
+#undef P
+#undef P_ns
+
+#ifdef CONFIG_TICK_ONESHOT
+# define P(x) \
+	SEQ_printf(m, "  .%-15s: %Lu\n", #x, \
+		   (unsigned long long)(ts->x))
+# define P_ns(x) \
+	SEQ_printf(m, "  .%-15s: %Lu nsecs\n", #x, \
+		   (unsigned long long)(ktime_to_ns(ts->x)))
+# define P_flag(x, f)			    \
+	SEQ_printf(m, "  .%-15s: %d\n", #x, !!(ts->flags & (f)))
+
+	{
+		struct tick_sched *ts = tick_get_tick_sched(cpu);
+		P_flag(nohz, TS_FLAG_NOHZ);
+		P_flag(highres, TS_FLAG_HIGHRES);
+		P_ns(last_tick);
+		P_flag(tick_stopped, TS_FLAG_STOPPED);
+		P(idle_calls);
+		P(idle_sleeps);
+		P_ns(idle_entrytime);
+		P_ns(idle_waketime);
+		P(last_jiffies);
+		P(next_timer);
+		P_ns(idle_expires);
+		SEQ_printf(m, "jiffies: %Lu\n",
+			   (unsigned long long)jiffies);
+	}
+#endif
+
+#undef P
+#undef P_ns
+	SEQ_printf(m, "\n");
+}
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+static void
+print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
+{
+	struct clock_event_device *dev = td->evtdev;
+
+	touch_nmi_watchdog();
+
+	SEQ_printf(m, "Tick Device: mode:     %d\n", td->mode);
+	if (cpu < 0)
+		SEQ_printf(m, "Broadcast device\n");
+	else
+		SEQ_printf(m, "Per CPU device: %d\n", cpu);
+
+	SEQ_printf(m, "Clock Event Device: ");
+	if (!dev) {
+		SEQ_printf(m, "<NULL>\n");
+		return;
+	}
+	SEQ_printf(m, "%s\n", dev->name);
+	SEQ_printf(m, " max_delta_ns:   %llu\n",
+		   (unsigned long long) dev->max_delta_ns);
+	SEQ_printf(m, " min_delta_ns:   %llu\n",
+		   (unsigned long long) dev->min_delta_ns);
+	SEQ_printf(m, " mult:           %u\n", dev->mult);
+	SEQ_printf(m, " shift:          %u\n", dev->shift);
+	SEQ_printf(m, " mode:           %d\n", clockevent_get_state(dev));
+	SEQ_printf(m, " next_event:     %Ld nsecs\n",
+		   (unsigned long long) ktime_to_ns(dev->next_event));
+
+	SEQ_printf(m, " set_next_event: %ps\n", dev->set_next_event);
+
+	if (dev->set_state_shutdown)
+		SEQ_printf(m, " shutdown:       %ps\n",
+			dev->set_state_shutdown);
+
+	if (dev->set_state_periodic)
+		SEQ_printf(m, " periodic:       %ps\n",
+			dev->set_state_periodic);
+
+	if (dev->set_state_oneshot)
+		SEQ_printf(m, " oneshot:        %ps\n",
+			dev->set_state_oneshot);
+
+	if (dev->set_state_oneshot_stopped)
+		SEQ_printf(m, " oneshot stopped: %ps\n",
+			dev->set_state_oneshot_stopped);
+
+	if (dev->tick_resume)
+		SEQ_printf(m, " resume:         %ps\n",
+			dev->tick_resume);
+
+	SEQ_printf(m, " event_handler:  %ps\n", dev->event_handler);
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, " retries:        %lu\n", dev->retries);
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+	if (cpu >= 0) {
+		const struct clock_event_device *wd = tick_get_wakeup_device(cpu);
+
+		SEQ_printf(m, "Wakeup Device: %s\n", wd ? wd->name : "<NULL>");
+	}
+#endif
+	SEQ_printf(m, "\n");
+}
+
+static void timer_list_show_tickdevices_header(struct seq_file *m)
+{
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+	print_tickdevice(m, tick_get_broadcast_device(), -1);
+	SEQ_printf(m, "tick_broadcast_mask: %*pb\n",
+		   cpumask_pr_args(tick_get_broadcast_mask()));
+#ifdef CONFIG_TICK_ONESHOT
+	SEQ_printf(m, "tick_broadcast_oneshot_mask: %*pb\n",
+		   cpumask_pr_args(tick_get_broadcast_oneshot_mask()));
+#endif
+	SEQ_printf(m, "\n");
+#endif
+}
+#endif
+
+static inline void timer_list_header(struct seq_file *m, u64 now)
+{
+	SEQ_printf(m, "Timer List Version: v0.11\n");
+	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
+	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
+	SEQ_printf(m, "\n");
+}
+
+void sysrq_timer_list_show(void)
+{
+	u64 now = ktime_to_ns(ktime_get());
+	int cpu;
+
+	timer_list_header(NULL, now);
+
+	for_each_online_cpu(cpu)
+		print_cpu(NULL, cpu, now);
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+	timer_list_show_tickdevices_header(NULL);
+	for_each_online_cpu(cpu)
+		print_tickdevice(NULL, tick_get_device(cpu), cpu);
+#endif
+	return;
+}
+
+#ifdef CONFIG_PROC_FS
+static int timer_list_show(struct seq_file *m, void *v)
+{
+	struct timer_list_iter *iter = v;
+
+	if (iter->cpu == -1 && !iter->second_pass)
+		timer_list_header(m, iter->now);
+	else if (!iter->second_pass)
+		print_cpu(m, iter->cpu, iter->now);
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+	else if (iter->cpu == -1 && iter->second_pass)
+		timer_list_show_tickdevices_header(m);
+	else
+		print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu);
+#endif
+	return 0;
+}
+
+static void *move_iter(struct timer_list_iter *iter, loff_t offset)
+{
+	for (; offset; offset--) {
+		iter->cpu = cpumask_next(iter->cpu, cpu_online_mask);
+		if (iter->cpu >= nr_cpu_ids) {
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+			if (!iter->second_pass) {
+				iter->cpu = -1;
+				iter->second_pass = true;
+			} else
+				return NULL;
+#else
+			return NULL;
+#endif
+		}
+	}
+	return iter;
+}
+
+static void *timer_list_start(struct seq_file *file, loff_t *offset)
+{
+	struct timer_list_iter *iter = file->private;
+
+	if (!*offset)
+		iter->now = ktime_to_ns(ktime_get());
+	iter->cpu = -1;
+	iter->second_pass = false;
+	return move_iter(iter, *offset);
+}
+
+static void *timer_list_next(struct seq_file *file, void *v, loff_t *offset)
+{
+	struct timer_list_iter *iter = file->private;
+	++*offset;
+	return move_iter(iter, 1);
+}
+
+static void timer_list_stop(struct seq_file *seq, void *v)
+{
+}
+
+static const struct seq_operations timer_list_sops = {
+	.start = timer_list_start,
+	.next = timer_list_next,
+	.stop = timer_list_stop,
+	.show = timer_list_show,
+};
+
+static int __init init_timer_list_procfs(void)
+{
+	struct proc_dir_entry *pe;
+
+	pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops,
+			sizeof(struct timer_list_iter), NULL);
+	if (!pe)
+		return -ENOMEM;
+	return 0;
+}
+__initcall(init_timer_list_procfs);
+#endif

linux-7.2.3/kernel/time/timer_migration.h

@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _KERNEL_TIME_MIGRATION_H
+#define _KERNEL_TIME_MIGRATION_H
+
+/* Per group capacity. Must be a power of 2! */
+#define TMIGR_CHILDREN_PER_GROUP 8
+
+/**
+ * struct tmigr_hierarchy - a hierarchy associated to a given CPU capacity.
+ *                          Homogeneous systems have only one hierarchy.
+ *                          Heterogenous have one hierarchy per CPU capacity.
+ * @cpumask:	CPUs belonging to this hierarchy
+ * @root:	The current root of the hierarchy
+ * @capacity:	CPU capacity associated to this hierarchy
+ * @node:	Node in the global hierarchy list
+ * @level_list:	Per level lists of tmigr groups
+ */
+struct tmigr_hierarchy {
+	struct cpumask		*cpumask;
+	struct tmigr_group	*root;
+	unsigned long		capacity;
+	struct list_head	node;
+	struct list_head	level_list[];
+};
+
+/**
+ * struct tmigr_event - a timer event associated to a CPU
+ * @nextevt:	The node to enqueue an event in the parent group queue
+ * @cpu:	The CPU to which this event belongs
+ * @ignore:	Hint whether the event could be ignored; it is set when
+ *		CPU or group is active;
+ */
+struct tmigr_event {
+	struct timerqueue_node	nextevt;
+	unsigned int		cpu;
+	bool			ignore;
+};
+
+/**
+ * struct tmigr_group - timer migration hierarchy group
+ * @lock:		Lock protecting the event information and group hierarchy
+ *			information during setup
+ * @parent:		Pointer to the parent group. Pointer is updated when a
+ *			new hierarchy level is added because of a CPU coming
+ *			online the first time. Once it is set, the pointer will
+ *			not be removed or updated. When accessing parent pointer
+ *			lock less to decide whether to abort a propagation or
+ *			not, it is not a problem. The worst outcome is an
+ *			unnecessary/early CPU wake up. But do not access parent
+ *			pointer several times in the same 'action' (like
+ *			activation, deactivation, check for remote expiry,...)
+ *			without holding the lock as it is not ensured that value
+ *			will not change.
+ * @groupevt:		Next event of the group which is only used when the
+ *			group is !active. The group event is then queued into
+ *			the parent timer queue.
+ *			Ignore bit of @groupevt is set when the group is active.
+ * @next_expiry:	Base monotonic expiry time of the next event of the
+ *			group; It is used for the racy lockless check whether a
+ *			remote expiry is required; it is always reliable
+ * @events:		Timer queue for child events queued in the group
+ * @migr_state:		State of the group (see union tmigr_state)
+ * @level:		Hierarchy level of the group; Required during setup
+ * @numa_node:		Required for setup only to make sure CPU and low level
+ *			group information is NUMA local. It is set to NUMA node
+ *			as long as the group level is per NUMA node (level <
+ *			tmigr_crossnode_level); otherwise it is set to
+ *			NUMA_NO_NODE
+ * @num_children:	Counter of group children to make sure the group is only
+ *			filled with TMIGR_CHILDREN_PER_GROUP; Required for setup
+ *			only
+ * @groupmask:		mask of the group in the parent group; is set during
+ *			setup and will never change; can be read lockless
+ * @list:		List head that is added to the per level
+ *			tmigr_level_list; is required during setup when a
+ *			new group needs to be connected to the existing
+ *			hierarchy groups
+ */
+struct tmigr_group {
+	raw_spinlock_t		lock;
+	struct tmigr_group	*parent;
+	struct tmigr_event	groupevt;
+	u64			next_expiry;
+	struct timerqueue_head	events;
+	atomic_t		migr_state;
+	unsigned int		level;
+	int			numa_node;
+	unsigned int		num_children;
+	u8			groupmask;
+	struct list_head	list;
+};
+
+/**
+ * struct tmigr_cpu - timer migration per CPU group
+ * @lock:		Lock protecting the tmigr_cpu group information
+ * @available:		Indicates whether the CPU is available for handling
+ *			global timers. In the deactivate path it is required to
+ *			know whether the migrator in the top level group is to
+ *			be set offline, while a timer is pending. Then another
+ *			available CPU needs to be notified to take over the
+ *			migrator role. Furthermore the information is required
+ *			in the CPU hotplug path as the CPU is able to go idle
+ *			before the timer migration hierarchy hotplug callback is
+ *			reached.  During this phase, the CPU has to handle the
+ *			global timers on its own and must not act as a migrator.
+
+ * @idle:		Indicates whether the CPU is idle in the timer migration
+ *			hierarchy
+ * @remote:		Is set when timers of the CPU are expired remotely
+ * @tmgroup:		Pointer to the parent group
+ * @groupmask:		mask of tmigr_cpu in the parent group
+ * @wakeup:		Stores the first timer when the timer migration
+ *			hierarchy is completely idle and remote expiry was done;
+ *			is returned to timer code in the idle path and is only
+ *			used in idle path.
+ * @cpuevt:		CPU event which could be enqueued into the parent group
+ */
+struct tmigr_cpu {
+	raw_spinlock_t		lock;
+	bool			available;
+	bool			idle;
+	bool			remote;
+	struct tmigr_group	*tmgroup;
+	u8			groupmask;
+	u64			wakeup;
+	struct tmigr_event	cpuevt;
+};
+
+/**
+ * union tmigr_state - state of tmigr_group
+ * @state:	Combined version of the state - only used for atomic
+ *		read/cmpxchg function
+ * &anon struct: Split version of the state - only use the struct members to
+ *		update information to stay independent of endianness
+ * @active:	Contains each mask bit of the active children
+ * @migrator:	Contains mask of the child which is migrator
+ * @seq:	Sequence counter needs to be increased when an update
+ *		to the tmigr_state is done. It prevents a race when
+ *		updates in the child groups are propagated in changed
+ *		order. Detailed information about the scenario is
+ *		given in the documentation at the begin of
+ *		timer_migration.c.
+ */
+union tmigr_state {
+	u32 state;
+	struct {
+		u8	active;
+		u8	migrator;
+		u16	seq;
+	} __packed;
+};
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern void tmigr_handle_remote(void);
+extern bool tmigr_requires_handle_remote(void);
+extern void tmigr_cpu_activate(void);
+extern u64 tmigr_cpu_deactivate(u64 nextevt);
+extern u64 tmigr_cpu_new_timer(u64 nextevt);
+extern u64 tmigr_quick_check(u64 nextevt);
+#else
+static inline void tmigr_handle_remote(void) { }
+static inline bool tmigr_requires_handle_remote(void) { return false; }
+static inline void tmigr_cpu_activate(void) { }
+#endif
+
+#endif

linux-7.2.3/kernel/time/vsyscall.c

@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 ARM Ltd.
+ *
+ * Generic implementation of update_vsyscall and update_vsyscall_tz.
+ *
+ * Based on the x86 specific implementation.
+ */
+
+#include <linux/hrtimer.h>
+#include <linux/timekeeper_internal.h>
+#include <vdso/datapage.h>
+#include <vdso/helpers.h>
+#include <vdso/vsyscall.h>
+
+#include "timekeeping_internal.h"
+
+static inline void fill_clock_configuration(struct vdso_clock *vc, const struct tk_read_base *base)
+{
+	vc->cycle_last	= base->cycle_last;
+#ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT
+	vc->max_cycles	= base->clock->max_cycles;
+#endif
+	vc->mask	= base->mask;
+	vc->mult	= base->mult;
+	vc->shift	= base->shift;
+}
+
+static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct timekeeper *tk)
+{
+	struct vdso_clock *vc = vdata->clock_data;
+	struct vdso_timestamp *vdso_ts;
+	u64 nsec, sec;
+
+	fill_clock_configuration(&vc[CS_HRES_COARSE],	&tk->tkr_mono);
+	fill_clock_configuration(&vc[CS_RAW],		&tk->tkr_raw);
+
+	/* CLOCK_MONOTONIC */
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC];
+	vdso_ts->sec	= tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
+
+	nsec = tk->tkr_mono.xtime_nsec;
+	nsec += ((u64)tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift);
+	while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
+		nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift);
+		vdso_ts->sec++;
+	}
+	vdso_ts->nsec	= nsec;
+
+	/* Copy MONOTONIC time for BOOTTIME */
+	sec	= vdso_ts->sec;
+	/* Add the boot offset */
+	sec	+= tk->monotonic_to_boot.tv_sec;
+	nsec	+= (u64)tk->monotonic_to_boot.tv_nsec << tk->tkr_mono.shift;
+
+	/* CLOCK_BOOTTIME */
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME];
+	vdso_ts->sec	= sec;
+
+	while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
+		nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift);
+		vdso_ts->sec++;
+	}
+	vdso_ts->nsec	= nsec;
+
+	/* CLOCK_MONOTONIC_RAW */
+	vdso_ts		= &vc[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
+	vdso_ts->sec	= tk->raw_sec;
+	vdso_ts->nsec	= tk->tkr_raw.xtime_nsec;
+
+	/* CLOCK_TAI */
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_TAI];
+	vdso_ts->sec	= tk->xtime_sec + (s64)tk->tai_offset;
+	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec;
+}
+
+void update_vsyscall(struct timekeeper *tk)
+{
+	struct vdso_time_data *vdata = vdso_k_time_data;
+	struct vdso_clock *vc = vdata->clock_data;
+	struct vdso_timestamp *vdso_ts;
+	s32 clock_mode;
+	u64 nsec;
+
+	/* copy vsyscall data */
+	vdso_write_begin(vdata);
+
+	clock_mode = tk->tkr_mono.clock->vdso_clock_mode;
+	vc[CS_HRES_COARSE].clock_mode	= clock_mode;
+	vc[CS_RAW].clock_mode		= clock_mode;
+
+	/* CLOCK_REALTIME also required for time() */
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME];
+	vdso_ts->sec	= tk->xtime_sec;
+	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec;
+
+	/* CLOCK_REALTIME_COARSE */
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
+	vdso_ts->sec	= tk->xtime_sec;
+	vdso_ts->nsec	= tk->coarse_nsec;
+
+	/* CLOCK_MONOTONIC_COARSE */
+	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE];
+	vdso_ts->sec	= tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
+	nsec		= tk->coarse_nsec;
+	nsec		= nsec + tk->wall_to_monotonic.tv_nsec;
+	vdso_ts->sec	+= __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);
+
+	/*
+	 * Read without the seqlock held by clock_getres().
+	 */
+	WRITE_ONCE(vdata->hrtimer_res, hrtimer_resolution);
+
+	/*
+	 * If the current clocksource is not VDSO capable, then spare the
+	 * update of the high resolution parts.
+	 */
+	if (clock_mode != VDSO_CLOCKMODE_NONE)
+		update_vdso_time_data(vdata, tk);
+
+	__arch_update_vdso_clock(&vc[CS_HRES_COARSE]);
+	__arch_update_vdso_clock(&vc[CS_RAW]);
+
+	vdso_write_end(vdata);
+
+	__arch_sync_vdso_time_data(vdata);
+}
+
+void update_vsyscall_tz(void)
+{
+	struct vdso_time_data *vdata = vdso_k_time_data;
+
+	vdata->tz_minuteswest = sys_tz.tz_minuteswest;
+	vdata->tz_dsttime = sys_tz.tz_dsttime;
+
+	__arch_sync_vdso_time_data(vdata);
+}
+
+#ifdef CONFIG_POSIX_AUX_CLOCKS
+void vdso_time_update_aux(struct timekeeper *tk)
+{
+	struct vdso_time_data *vdata = vdso_k_time_data;
+	struct vdso_timestamp *vdso_ts;
+	struct vdso_clock *vc;
+	s32 clock_mode;
+	u64 nsec;
+
+	vc = &vdata->aux_clock_data[tk->id - TIMEKEEPER_AUX_FIRST];
+	vdso_ts = &vc->basetime[VDSO_BASE_AUX];
+	clock_mode = tk->tkr_mono.clock->vdso_clock_mode;
+	if (!tk->clock_valid)
+		clock_mode = VDSO_CLOCKMODE_NONE;
+
+	/* copy vsyscall data */
+	vdso_write_begin_clock(vc);
+
+	vc->clock_mode = clock_mode;
+
+	if (clock_mode != VDSO_CLOCKMODE_NONE) {
+		fill_clock_configuration(vc, &tk->tkr_mono);
+
+		vdso_ts->sec = tk->xtime_sec + tk->monotonic_to_aux.tv_sec;
+
+		nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+		nsec += tk->monotonic_to_aux.tv_nsec;
+		vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &nsec);
+		nsec = nsec << tk->tkr_mono.shift;
+		vdso_ts->nsec = nsec;
+	}
+
+	__arch_update_vdso_clock(vc);
+
+	vdso_write_end_clock(vc);
+
+	__arch_sync_vdso_time_data(vdata);
+}
+#endif
+
+/**
+ * vdso_update_begin - Start of a VDSO update section
+ *
+ * Allows architecture code to safely update the architecture specific VDSO
+ * data. Disables interrupts, acquires timekeeper lock to serialize against
+ * concurrent updates from timekeeping and invalidates the VDSO data
+ * sequence counter to prevent concurrent readers from accessing
+ * inconsistent data.
+ *
+ * Returns: Saved interrupt flags which need to be handed in to
+ * vdso_update_end().
+ */
+unsigned long vdso_update_begin(void)
+{
+	struct vdso_time_data *vdata = vdso_k_time_data;
+	unsigned long flags = timekeeper_lock_irqsave();
+
+	vdso_write_begin(vdata);
+	return flags;
+}
+
+/**
+ * vdso_update_end - End of a VDSO update section
+ * @flags:	Interrupt flags as returned from vdso_update_begin()
+ *
+ * Pairs with vdso_update_begin(). Marks vdso data consistent, invokes data
+ * synchronization if the architecture requires it, drops timekeeper lock
+ * and restores interrupt flags.
+ */
+void vdso_update_end(unsigned long flags)
+{
+	struct vdso_time_data *vdata = vdso_k_time_data;
+
+	vdso_write_end(vdata);
+	__arch_sync_vdso_time_data(vdata);
+	timekeeper_unlock_irqrestore(flags);
+}