Merge branch 'timers/core' into perf/timer, to apply dependent patch

An upcoming patch will depend on tai_ns() and NMI-safe ktime_get_raw_fast(),
so merge timers/core here in a separate topic branch until it's all cooked
and timers/core is merged upstream.
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/arm/plat-omap/counter_32k.c

@@ -103,7 +103,7 @@ int __init omap_init_clocksource_32k(void __iomem *vbase)
 
 	/*
 	 * 120000 rough estimate from the calculations in
-	 * __clocksource_updatefreq_scale.
+	 * __clocksource_update_freq_scale.
 	 */
 	clocks_calc_mult_shift(&persistent_mult, &persistent_shift,
 			32768, NSEC_PER_SEC, 120000);

arch/arm64/kernel/vdso.c

@@ -200,7 +200,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 void update_vsyscall(struct timekeeper *tk)
 {
 	struct timespec xtime_coarse;
-	u32 use_syscall = strcmp(tk->tkr.clock->name, "arch_sys_counter");
+	u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter");
 
 	++vdso_data->tb_seq_count;
 	smp_wmb();
@@ -213,11 +213,11 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 
 	if (!use_syscall) {
-		vdso_data->cs_cycle_last	= tk->tkr.cycle_last;
+		vdso_data->cs_cycle_last	= tk->tkr_mono.cycle_last;
 		vdso_data->xtime_clock_sec	= tk->xtime_sec;
-		vdso_data->xtime_clock_nsec	= tk->tkr.xtime_nsec;
-		vdso_data->cs_mult		= tk->tkr.mult;
-		vdso_data->cs_shift		= tk->tkr.shift;
+		vdso_data->xtime_clock_nsec	= tk->tkr_mono.xtime_nsec;
+		vdso_data->cs_mult		= tk->tkr_mono.mult;
+		vdso_data->cs_shift		= tk->tkr_mono.shift;
 	}
 
 	smp_wmb();

arch/s390/kernel/time.c

@@ -215,20 +215,20 @@ void update_vsyscall(struct timekeeper *tk)
 {
 	u64 nsecps;
 
-	if (tk->tkr.clock != &clocksource_tod)
+	if (tk->tkr_mono.clock != &clocksource_tod)
 		return;
 
 	/* Make userspace gettimeofday spin until we're done. */
 	++vdso_data->tb_update_count;
 	smp_wmb();
-	vdso_data->xtime_tod_stamp = tk->tkr.cycle_last;
+	vdso_data->xtime_tod_stamp = tk->tkr_mono.cycle_last;
 	vdso_data->xtime_clock_sec = tk->xtime_sec;
-	vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec;
+	vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec;
 	vdso_data->wtom_clock_sec =
 		tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
-	vdso_data->wtom_clock_nsec = tk->tkr.xtime_nsec +
-		+ ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr.shift);
-	nsecps = (u64) NSEC_PER_SEC << tk->tkr.shift;
+	vdso_data->wtom_clock_nsec = tk->tkr_mono.xtime_nsec +
+		+ ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift);
+	nsecps = (u64) NSEC_PER_SEC << tk->tkr_mono.shift;
 	while (vdso_data->wtom_clock_nsec >= nsecps) {
 		vdso_data->wtom_clock_nsec -= nsecps;
 		vdso_data->wtom_clock_sec++;
@@ -236,7 +236,7 @@ void update_vsyscall(struct timekeeper *tk)
 
 	vdso_data->xtime_coarse_sec = tk->xtime_sec;
 	vdso_data->xtime_coarse_nsec =
-		(long)(tk->tkr.xtime_nsec >> tk->tkr.shift);
+		(long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
 	vdso_data->wtom_coarse_sec =
 		vdso_data->xtime_coarse_sec + tk->wall_to_monotonic.tv_sec;
 	vdso_data->wtom_coarse_nsec =
@@ -246,8 +246,8 @@ void update_vsyscall(struct timekeeper *tk)
 		vdso_data->wtom_coarse_sec++;
 	}
 
-	vdso_data->tk_mult = tk->tkr.mult;
-	vdso_data->tk_shift = tk->tkr.shift;
+	vdso_data->tk_mult = tk->tkr_mono.mult;
+	vdso_data->tk_shift = tk->tkr_mono.shift;
 	smp_wmb();
 	++vdso_data->tb_update_count;
 }
@@ -283,7 +283,7 @@ void __init time_init(void)
 	if (register_external_irq(EXT_IRQ_TIMING_ALERT, timing_alert_interrupt))
 		panic("Couldn't request external interrupt 0x1406");
 
-	if (clocksource_register(&clocksource_tod) != 0)
+	if (__clocksource_register(&clocksource_tod) != 0)
 		panic("Could not register TOD clock source");
 
 	/* Enable TOD clock interrupts on the boot cpu. */

arch/sparc/kernel/time_32.c

@@ -181,17 +181,13 @@ static struct clocksource timer_cs = {
 	.rating	= 100,
 	.read	= timer_cs_read,
 	.mask	= CLOCKSOURCE_MASK(64),
-	.shift	= 2,
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static __init int setup_timer_cs(void)
 {
 	timer_cs_enabled = 1;
-	timer_cs.mult = clocksource_hz2mult(sparc_config.clock_rate,
-	                                    timer_cs.shift);
-
-	return clocksource_register(&timer_cs);
+	return clocksource_register_hz(&timer_cs, sparc_config.clock_rate);
 }
 
 #ifdef CONFIG_SMP

arch/tile/kernel/time.c

@@ -257,34 +257,34 @@ void update_vsyscall_tz(void)
 
 void update_vsyscall(struct timekeeper *tk)
 {
-	if (tk->tkr.clock != &cycle_counter_cs)
+	if (tk->tkr_mono.clock != &cycle_counter_cs)
 		return;
 
 	write_seqcount_begin(&vdso_data->tb_seq);
 
-	vdso_data->cycle_last		= tk->tkr.cycle_last;
-	vdso_data->mask			= tk->tkr.mask;
-	vdso_data->mult			= tk->tkr.mult;
-	vdso_data->shift		= tk->tkr.shift;
+	vdso_data->cycle_last		= tk->tkr_mono.cycle_last;
+	vdso_data->mask			= tk->tkr_mono.mask;
+	vdso_data->mult			= tk->tkr_mono.mult;
+	vdso_data->shift		= tk->tkr_mono.shift;
 
 	vdso_data->wall_time_sec	= tk->xtime_sec;
-	vdso_data->wall_time_snsec	= tk->tkr.xtime_nsec;
+	vdso_data->wall_time_snsec	= tk->tkr_mono.xtime_nsec;
 
 	vdso_data->monotonic_time_sec	= tk->xtime_sec
 					+ tk->wall_to_monotonic.tv_sec;
-	vdso_data->monotonic_time_snsec	= tk->tkr.xtime_nsec
+	vdso_data->monotonic_time_snsec	= tk->tkr_mono.xtime_nsec
 					+ ((u64)tk->wall_to_monotonic.tv_nsec
-						<< tk->tkr.shift);
+						<< tk->tkr_mono.shift);
 	while (vdso_data->monotonic_time_snsec >=
-					(((u64)NSEC_PER_SEC) << tk->tkr.shift)) {
+					(((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
 		vdso_data->monotonic_time_snsec -=
-					((u64)NSEC_PER_SEC) << tk->tkr.shift;
+					((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
 		vdso_data->monotonic_time_sec++;
 	}
 
 	vdso_data->wall_time_coarse_sec	= tk->xtime_sec;
-	vdso_data->wall_time_coarse_nsec = (long)(tk->tkr.xtime_nsec >>
-						 tk->tkr.shift);
+	vdso_data->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >>
+						 tk->tkr_mono.shift);
 
 	vdso_data->monotonic_time_coarse_sec =
 		vdso_data->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;

arch/x86/kernel/vsyscall_gtod.c

@@ -31,30 +31,30 @@ void update_vsyscall(struct timekeeper *tk)
 	gtod_write_begin(vdata);
 
 	/* copy vsyscall data */
-	vdata->vclock_mode	= tk->tkr.clock->archdata.vclock_mode;
-	vdata->cycle_last	= tk->tkr.cycle_last;
-	vdata->mask		= tk->tkr.mask;
-	vdata->mult		= tk->tkr.mult;
-	vdata->shift		= tk->tkr.shift;
+	vdata->vclock_mode	= tk->tkr_mono.clock->archdata.vclock_mode;
+	vdata->cycle_last	= tk->tkr_mono.cycle_last;
+	vdata->mask		= tk->tkr_mono.mask;
+	vdata->mult		= tk->tkr_mono.mult;
+	vdata->shift		= tk->tkr_mono.shift;
 
 	vdata->wall_time_sec		= tk->xtime_sec;
-	vdata->wall_time_snsec		= tk->tkr.xtime_nsec;
+	vdata->wall_time_snsec		= tk->tkr_mono.xtime_nsec;
 
 	vdata->monotonic_time_sec	= tk->xtime_sec
 					+ tk->wall_to_monotonic.tv_sec;
-	vdata->monotonic_time_snsec	= tk->tkr.xtime_nsec
+	vdata->monotonic_time_snsec	= tk->tkr_mono.xtime_nsec
 					+ ((u64)tk->wall_to_monotonic.tv_nsec
-						<< tk->tkr.shift);
+						<< tk->tkr_mono.shift);
 	while (vdata->monotonic_time_snsec >=
-					(((u64)NSEC_PER_SEC) << tk->tkr.shift)) {
+					(((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
 		vdata->monotonic_time_snsec -=
-					((u64)NSEC_PER_SEC) << tk->tkr.shift;
+					((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
 		vdata->monotonic_time_sec++;
 	}
 
 	vdata->wall_time_coarse_sec	= tk->xtime_sec;
-	vdata->wall_time_coarse_nsec	= (long)(tk->tkr.xtime_nsec >>
-						 tk->tkr.shift);
+	vdata->wall_time_coarse_nsec	= (long)(tk->tkr_mono.xtime_nsec >>
+						 tk->tkr_mono.shift);
 
 	vdata->monotonic_time_coarse_sec =
 		vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;

arch/x86/kvm/x86.c

@@ -1070,19 +1070,19 @@ static void update_pvclock_gtod(struct timekeeper *tk)
 	struct pvclock_gtod_data *vdata = &pvclock_gtod_data;
 	u64 boot_ns;
 
-	boot_ns = ktime_to_ns(ktime_add(tk->tkr.base_mono, tk->offs_boot));
+	boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot));
 
 	write_seqcount_begin(&vdata->seq);
 
 	/* copy pvclock gtod data */
-	vdata->clock.vclock_mode	= tk->tkr.clock->archdata.vclock_mode;
-	vdata->clock.cycle_last		= tk->tkr.cycle_last;
-	vdata->clock.mask		= tk->tkr.mask;
-	vdata->clock.mult		= tk->tkr.mult;
-	vdata->clock.shift		= tk->tkr.shift;
+	vdata->clock.vclock_mode	= tk->tkr_mono.clock->archdata.vclock_mode;
+	vdata->clock.cycle_last		= tk->tkr_mono.cycle_last;
+	vdata->clock.mask		= tk->tkr_mono.mask;
+	vdata->clock.mult		= tk->tkr_mono.mult;
+	vdata->clock.shift		= tk->tkr_mono.shift;
 
 	vdata->boot_ns			= boot_ns;
-	vdata->nsec_base		= tk->tkr.xtime_nsec;
+	vdata->nsec_base		= tk->tkr_mono.xtime_nsec;
 
 	write_seqcount_end(&vdata->seq);
 }

drivers/clocksource/em_sti.c

@@ -210,7 +210,7 @@ static int em_sti_clocksource_enable(struct clocksource *cs)
 
 	ret = em_sti_start(p, USER_CLOCKSOURCE);
 	if (!ret)
-		__clocksource_updatefreq_hz(cs, p->rate);
+		__clocksource_update_freq_hz(cs, p->rate);
 	return ret;
 }
 

drivers/clocksource/sh_cmt.c

@@ -641,7 +641,7 @@ static int sh_cmt_clocksource_enable(struct clocksource *cs)
 
 	ret = sh_cmt_start(ch, FLAG_CLOCKSOURCE);
 	if (!ret) {
-		__clocksource_updatefreq_hz(cs, ch->rate);
+		__clocksource_update_freq_hz(cs, ch->rate);
 		ch->cs_enabled = true;
 	}
 	return ret;

drivers/clocksource/sh_tmu.c

@@ -272,7 +272,7 @@ static int sh_tmu_clocksource_enable(struct clocksource *cs)
 
 	ret = sh_tmu_enable(ch);
 	if (!ret) {
-		__clocksource_updatefreq_hz(cs, ch->rate);
+		__clocksource_update_freq_hz(cs, ch->rate);
 		ch->cs_enabled = true;
 	}
 

include/linux/clockchips.h

@@ -39,6 +39,8 @@ enum clock_event_mode {
 	CLOCK_EVT_MODE_PERIODIC,
 	CLOCK_EVT_MODE_ONESHOT,
 	CLOCK_EVT_MODE_RESUME,
+
+	/* Legacy ->set_mode() callback doesn't support below modes */
 };
 
 /*
@@ -81,7 +83,11 @@ enum clock_event_mode {
  * @mode:		operating mode assigned by the management code
  * @features:		features
  * @retries:		number of forced programming retries
- * @set_mode:		set mode function
+ * @set_mode:		legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME.
+ * @set_mode_periodic:	switch mode to periodic, if !set_mode
+ * @set_mode_oneshot:	switch mode to oneshot, if !set_mode
+ * @set_mode_shutdown:	switch mode to shutdown, if !set_mode
+ * @set_mode_resume:	resume clkevt device, if !set_mode
  * @broadcast:		function to broadcast events
  * @min_delta_ticks:	minimum delta value in ticks stored for reconfiguration
  * @max_delta_ticks:	maximum delta value in ticks stored for reconfiguration
@@ -108,9 +114,20 @@ struct clock_event_device {
 	unsigned int		features;
 	unsigned long		retries;
 
-	void			(*broadcast)(const struct cpumask *mask);
+	/*
+	 * Mode transition callback(s): Only one of the two groups should be
+	 * defined:
+	 * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME.
+	 * - set_mode_{shutdown|periodic|oneshot|resume}().
+	 */
 	void			(*set_mode)(enum clock_event_mode mode,
 					    struct clock_event_device *);
+	int			(*set_mode_periodic)(struct clock_event_device *);
+	int			(*set_mode_oneshot)(struct clock_event_device *);
+	int			(*set_mode_shutdown)(struct clock_event_device *);
+	int			(*set_mode_resume)(struct clock_event_device *);
+
+	void			(*broadcast)(const struct cpumask *mask);
 	void			(*suspend)(struct clock_event_device *);
 	void			(*resume)(struct clock_event_device *);
 	unsigned long		min_delta_ticks;

include/linux/clocksource.h

@@ -56,6 +56,7 @@ struct module;
  * @shift:		cycle to nanosecond divisor (power of two)
  * @max_idle_ns:	max idle time permitted by the clocksource (nsecs)
  * @maxadj:		maximum adjustment value to mult (~11%)
+ * @max_cycles:		maximum safe cycle value which won't overflow on multiplication
  * @flags:		flags describing special properties
  * @archdata:		arch-specific data
  * @suspend:		suspend function for the clocksource, if necessary
@@ -76,7 +77,7 @@ struct clocksource {
 #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
 	struct arch_clocksource_data archdata;
 #endif
-
+	u64 max_cycles;
 	const char *name;
 	struct list_head list;
 	int rating;
@@ -178,7 +179,6 @@ static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift)
 }
 
 
-extern int clocksource_register(struct clocksource*);
 extern int clocksource_unregister(struct clocksource*);
 extern void clocksource_touch_watchdog(void);
 extern struct clocksource* clocksource_get_next(void);
@@ -189,7 +189,7 @@ extern struct clocksource * __init clocksource_default_clock(void);
 extern void clocksource_mark_unstable(struct clocksource *cs);
 
 extern u64
-clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask);
+clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cycles);
 extern void
 clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec);
 
@@ -200,7 +200,16 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec);
 extern int
 __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq);
 extern void
-__clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq);
+__clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq);
+
+/*
+ * Don't call this unless you are a default clocksource
+ * (AKA: jiffies) and absolutely have to.
+ */
+static inline int __clocksource_register(struct clocksource *cs)
+{
+	return __clocksource_register_scale(cs, 1, 0);
+}
 
 static inline int clocksource_register_hz(struct clocksource *cs, u32 hz)
 {
@@ -212,14 +221,14 @@ static inline int clocksource_register_khz(struct clocksource *cs, u32 khz)
 	return __clocksource_register_scale(cs, 1000, khz);
 }
 
-static inline void __clocksource_updatefreq_hz(struct clocksource *cs, u32 hz)
+static inline void __clocksource_update_freq_hz(struct clocksource *cs, u32 hz)
 {
-	__clocksource_updatefreq_scale(cs, 1, hz);
+	__clocksource_update_freq_scale(cs, 1, hz);
 }
 
-static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz)
+static inline void __clocksource_update_freq_khz(struct clocksource *cs, u32 khz)
 {
-	__clocksource_updatefreq_scale(cs, 1000, khz);
+	__clocksource_update_freq_scale(cs, 1000, khz);
 }
 
 

include/linux/timekeeper_internal.h

@@ -16,16 +16,16 @@
  * @read:	Read function of @clock
  * @mask:	Bitmask for two's complement subtraction of non 64bit clocks
  * @cycle_last: @clock cycle value at last update
- * @mult:	NTP adjusted multiplier for scaled math conversion
+ * @mult:	(NTP adjusted) multiplier for scaled math conversion
  * @shift:	Shift value for scaled math conversion
  * @xtime_nsec: Shifted (fractional) nano seconds offset for readout
- * @base_mono:  ktime_t (nanoseconds) base time for readout
+ * @base:	ktime_t (nanoseconds) base time for readout
  *
  * This struct has size 56 byte on 64 bit. Together with a seqcount it
  * occupies a single 64byte cache line.
  *
  * The struct is separate from struct timekeeper as it is also used
- * for a fast NMI safe accessor to clock monotonic.
+ * for a fast NMI safe accessors.
  */
 struct tk_read_base {
 	struct clocksource	*clock;
@@ -35,12 +35,13 @@ struct tk_read_base {
 	u32			mult;
 	u32			shift;
 	u64			xtime_nsec;
-	ktime_t			base_mono;
+	ktime_t			base;
 };
 
 /**
  * struct timekeeper - Structure holding internal timekeeping values.
- * @tkr:		The readout base structure
+ * @tkr_mono:		The readout base structure for CLOCK_MONOTONIC
+ * @tkr_raw:		The readout base structure for CLOCK_MONOTONIC_RAW
  * @xtime_sec:		Current CLOCK_REALTIME time in seconds
  * @ktime_sec:		Current CLOCK_MONOTONIC time in seconds
  * @wall_to_monotonic:	CLOCK_REALTIME to CLOCK_MONOTONIC offset
@@ -48,7 +49,6 @@ struct tk_read_base {
  * @offs_boot:		Offset clock monotonic -> clock boottime
  * @offs_tai:		Offset clock monotonic -> clock tai
  * @tai_offset:		The current UTC to TAI offset in seconds
- * @base_raw:		Monotonic raw base time in ktime_t format
  * @raw_time:		Monotonic raw base time in timespec64 format
  * @cycle_interval:	Number of clock cycles in one NTP interval
  * @xtime_interval:	Number of clock shifted nano seconds in one NTP
@@ -76,7 +76,8 @@ struct tk_read_base {
  * used instead.
  */
 struct timekeeper {
-	struct tk_read_base	tkr;
+	struct tk_read_base	tkr_mono;
+	struct tk_read_base	tkr_raw;
 	u64			xtime_sec;
 	unsigned long		ktime_sec;
 	struct timespec64	wall_to_monotonic;
@@ -84,7 +85,6 @@ struct timekeeper {
 	ktime_t			offs_boot;
 	ktime_t			offs_tai;
 	s32			tai_offset;
-	ktime_t			base_raw;
 	struct timespec64	raw_time;
 
 	/* The following members are for timekeeping internal use */

include/linux/timekeeping.h

@@ -214,12 +214,18 @@ static inline u64 ktime_get_boot_ns(void)
 	return ktime_to_ns(ktime_get_boottime());
 }
 
+static inline u64 ktime_get_tai_ns(void)
+{
+	return ktime_to_ns(ktime_get_clocktai());
+}
+
 static inline u64 ktime_get_raw_ns(void)
 {
 	return ktime_to_ns(ktime_get_raw());
 }
 
 extern u64 ktime_get_mono_fast_ns(void);
+extern u64 ktime_get_raw_fast_ns(void);
 
 /*
  * Timespec interfaces utilizing the ktime based ones

kernel/time/clockevents.c

@@ -94,6 +94,57 @@ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
 }
 EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 
+static int __clockevents_set_mode(struct clock_event_device *dev,
+				  enum clock_event_mode mode)
+{
+	/* Transition with legacy set_mode() callback */
+	if (dev->set_mode) {
+		/* Legacy callback doesn't support new modes */
+		if (mode > CLOCK_EVT_MODE_RESUME)
+			return -ENOSYS;
+		dev->set_mode(mode, dev);
+		return 0;
+	}
+
+	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
+		return 0;
+
+	/* Transition with new mode-specific callbacks */
+	switch (mode) {
+	case CLOCK_EVT_MODE_UNUSED:
+		/*
+		 * This is an internal state, which is guaranteed to go from
+		 * SHUTDOWN to UNUSED. No driver interaction required.
+		 */
+		return 0;
+
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		return dev->set_mode_shutdown(dev);
+
+	case CLOCK_EVT_MODE_PERIODIC:
+		/* Core internal bug */
+		if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC))
+			return -ENOSYS;
+		return dev->set_mode_periodic(dev);
+
+	case CLOCK_EVT_MODE_ONESHOT:
+		/* Core internal bug */
+		if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+			return -ENOSYS;
+		return dev->set_mode_oneshot(dev);
+
+	case CLOCK_EVT_MODE_RESUME:
+		/* Optional callback */
+		if (dev->set_mode_resume)
+			return dev->set_mode_resume(dev);
+		else
+			return 0;
+
+	default:
+		return -ENOSYS;
+	}
+}
+
 /**
  * clockevents_set_mode - set the operating mode of a clock event device
  * @dev:	device to modify
@@ -105,7 +156,9 @@ void clockevents_set_mode(struct clock_event_device *dev,
 				 enum clock_event_mode mode)
 {
 	if (dev->mode != mode) {
-		dev->set_mode(mode, dev);
+		if (__clockevents_set_mode(dev, mode))
+			return;
+
 		dev->mode = mode;
 
 		/*
@@ -373,6 +426,35 @@ int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
 }
 EXPORT_SYMBOL_GPL(clockevents_unbind);
 
+/* Sanity check of mode transition callbacks */
+static int clockevents_sanity_check(struct clock_event_device *dev)
+{
+	/* Legacy set_mode() callback */
+	if (dev->set_mode) {
+		/* We shouldn't be supporting new modes now */
+		WARN_ON(dev->set_mode_periodic || dev->set_mode_oneshot ||
+			dev->set_mode_shutdown || dev->set_mode_resume);
+		return 0;
+	}
+
+	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
+		return 0;
+
+	/* New mode-specific callbacks */
+	if (!dev->set_mode_shutdown)
+		return -EINVAL;
+
+	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
+	    !dev->set_mode_periodic)
+		return -EINVAL;
+
+	if ((dev->features & CLOCK_EVT_FEAT_ONESHOT) &&
+	    !dev->set_mode_oneshot)
+		return -EINVAL;
+
+	return 0;
+}
+
 /**
  * clockevents_register_device - register a clock event device
  * @dev:	device to register
@@ -382,6 +464,8 @@ void clockevents_register_device(struct clock_event_device *dev)
 	unsigned long flags;
 
 	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
+	BUG_ON(clockevents_sanity_check(dev));
+
 	if (!dev->cpumask) {
 		WARN_ON(num_possible_cpus() > 1);
 		dev->cpumask = cpumask_of(smp_processor_id());
@@ -449,7 +533,7 @@ int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
 		return clockevents_program_event(dev, dev->next_event, false);
 
 	if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
-		dev->set_mode(CLOCK_EVT_MODE_PERIODIC, dev);
+		return __clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
 
 	return 0;
 }

kernel/time/clocksource.c

@@ -142,13 +142,6 @@ static void __clocksource_unstable(struct clocksource *cs)
 		schedule_work(&watchdog_work);
 }
 
-static void clocksource_unstable(struct clocksource *cs, int64_t delta)
-{
-	printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n",
-	       cs->name, delta);
-	__clocksource_unstable(cs);
-}
-
 /**
  * clocksource_mark_unstable - mark clocksource unstable via watchdog
  * @cs:		clocksource to be marked unstable
@@ -174,7 +167,7 @@ void clocksource_mark_unstable(struct clocksource *cs)
 static void clocksource_watchdog(unsigned long data)
 {
 	struct clocksource *cs;
-	cycle_t csnow, wdnow, delta;
+	cycle_t csnow, wdnow, cslast, wdlast, delta;
 	int64_t wd_nsec, cs_nsec;
 	int next_cpu, reset_pending;
 
@@ -213,6 +206,8 @@ static void clocksource_watchdog(unsigned long data)
 
 		delta = clocksource_delta(csnow, cs->cs_last, cs->mask);
 		cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift);
+		wdlast = cs->wd_last; /* save these in case we print them */
+		cslast = cs->cs_last;
 		cs->cs_last = csnow;
 		cs->wd_last = wdnow;
 
@@ -221,7 +216,12 @@ static void clocksource_watchdog(unsigned long data)
 
 		/* Check the deviation from the watchdog clocksource. */
 		if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
-			clocksource_unstable(cs, cs_nsec - wd_nsec);
+			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable, because the skew is too large:\n", cs->name);
+			pr_warn("	'%s' wd_now: %llx wd_last: %llx mask: %llx\n",
+				watchdog->name, wdnow, wdlast, watchdog->mask);
+			pr_warn("	'%s' cs_now: %llx cs_last: %llx mask: %llx\n",
+				cs->name, csnow, cslast, cs->mask);
+			__clocksource_unstable(cs);
 			continue;
 		}
 
@@ -469,26 +469,22 @@ static u32 clocksource_max_adjustment(struct clocksource *cs)
  * @shift:	cycle to nanosecond divisor (power of two)
  * @maxadj:	maximum adjustment value to mult (~11%)
  * @mask:	bitmask for two's complement subtraction of non 64 bit counters
+ * @max_cyc:	maximum cycle value before potential overflow (does not include
+ *		any safety margin)
+ *
+ * NOTE: This function includes a safety margin of 50%, so that bad clock values
+ * can be detected.
  */
-u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask)
+u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cyc)
 {
 	u64 max_nsecs, max_cycles;
 
 	/*
 	 * Calculate the maximum number of cycles that we can pass to the
-	 * cyc2ns function without overflowing a 64-bit signed result. The
-	 * maximum number of cycles is equal to ULLONG_MAX/(mult+maxadj)
-	 * which is equivalent to the below.
-	 * max_cycles < (2^63)/(mult + maxadj)
-	 * max_cycles < 2^(log2((2^63)/(mult + maxadj)))
-	 * max_cycles < 2^(log2(2^63) - log2(mult + maxadj))
-	 * max_cycles < 2^(63 - log2(mult + maxadj))
-	 * max_cycles < 1 << (63 - log2(mult + maxadj))
-	 * Please note that we add 1 to the result of the log2 to account for
-	 * any rounding errors, ensure the above inequality is satisfied and
-	 * no overflow will occur.
+	 * cyc2ns() function without overflowing a 64-bit result.
 	 */
-	max_cycles = 1ULL << (63 - (ilog2(mult + maxadj) + 1));
+	max_cycles = ULLONG_MAX;
+	do_div(max_cycles, mult+maxadj);
 
 	/*
 	 * The actual maximum number of cycles we can defer the clocksource is
@@ -499,27 +495,26 @@ u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask)
 	max_cycles = min(max_cycles, mask);
 	max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift);
 
+	/* return the max_cycles value as well if requested */
+	if (max_cyc)
+		*max_cyc = max_cycles;
+
+	/* Return 50% of the actual maximum, so we can detect bad values */
+	max_nsecs >>= 1;
+
 	return max_nsecs;
 }
 
 /**
- * clocksource_max_deferment - Returns max time the clocksource can be deferred
- * @cs:         Pointer to clocksource
+ * clocksource_update_max_deferment - Updates the clocksource max_idle_ns & max_cycles
+ * @cs:         Pointer to clocksource to be updated
  *
  */
-static u64 clocksource_max_deferment(struct clocksource *cs)
+static inline void clocksource_update_max_deferment(struct clocksource *cs)
 {
-	u64 max_nsecs;
-
-	max_nsecs = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj,
-					  cs->mask);
-	/*
-	 * To ensure that the clocksource does not wrap whilst we are idle,
-	 * limit the time the clocksource can be deferred by 12.5%. Please
-	 * note a margin of 12.5% is used because this can be computed with
-	 * a shift, versus say 10% which would require division.
-	 */
-	return max_nsecs - (max_nsecs >> 3);
+	cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift,
+						cs->maxadj, cs->mask,
+						&cs->max_cycles);
 }
 
 #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
@@ -648,7 +643,7 @@ static void clocksource_enqueue(struct clocksource *cs)
 }
 
 /**
- * __clocksource_updatefreq_scale - Used update clocksource with new freq
+ * __clocksource_update_freq_scale - Used update clocksource with new freq
  * @cs:		clocksource to be registered
  * @scale:	Scale factor multiplied against freq to get clocksource hz
  * @freq:	clocksource frequency (cycles per second) divided by scale
@@ -656,48 +651,64 @@ static void clocksource_enqueue(struct clocksource *cs)
  * This should only be called from the clocksource->enable() method.
  *
  * This *SHOULD NOT* be called directly! Please use the
- * clocksource_updatefreq_hz() or clocksource_updatefreq_khz helper functions.
+ * __clocksource_update_freq_hz() or __clocksource_update_freq_khz() helper
+ * functions.
  */
-void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
+void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
 	u64 sec;
+
 	/*
-	 * Calc the maximum number of seconds which we can run before
-	 * wrapping around. For clocksources which have a mask > 32bit
-	 * we need to limit the max sleep time to have a good
-	 * conversion precision. 10 minutes is still a reasonable
-	 * amount. That results in a shift value of 24 for a
-	 * clocksource with mask >= 40bit and f >= 4GHz. That maps to
-	 * ~ 0.06ppm granularity for NTP. We apply the same 12.5%
-	 * margin as we do in clocksource_max_deferment()
+	 * Default clocksources are *special* and self-define their mult/shift.
+	 * But, you're not special, so you should specify a freq value.
 	 */
-	sec = (cs->mask - (cs->mask >> 3));
-	do_div(sec, freq);
-	do_div(sec, scale);
-	if (!sec)
-		sec = 1;
-	else if (sec > 600 && cs->mask > UINT_MAX)
-		sec = 600;
-
-	clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
-			       NSEC_PER_SEC / scale, sec * scale);
-
+	if (freq) {
+		/*
+		 * Calc the maximum number of seconds which we can run before
+		 * wrapping around. For clocksources which have a mask > 32-bit
+		 * we need to limit the max sleep time to have a good
+		 * conversion precision. 10 minutes is still a reasonable
+		 * amount. That results in a shift value of 24 for a
+		 * clocksource with mask >= 40-bit and f >= 4GHz. That maps to
+		 * ~ 0.06ppm granularity for NTP.
+		 */
+		sec = cs->mask;
+		do_div(sec, freq);
+		do_div(sec, scale);
+		if (!sec)
+			sec = 1;
+		else if (sec > 600 && cs->mask > UINT_MAX)
+			sec = 600;
+
+		clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
+				       NSEC_PER_SEC / scale, sec * scale);
+	}
 	/*
-	 * for clocksources that have large mults, to avoid overflow.
-	 * Since mult may be adjusted by ntp, add an safety extra margin
-	 *
+	 * Ensure clocksources that have large 'mult' values don't overflow
+	 * when adjusted.
 	 */
 	cs->maxadj = clocksource_max_adjustment(cs);
-	while ((cs->mult + cs->maxadj < cs->mult)
-		|| (cs->mult - cs->maxadj > cs->mult)) {
+	while (freq && ((cs->mult + cs->maxadj < cs->mult)
+		|| (cs->mult - cs->maxadj > cs->mult))) {
 		cs->mult >>= 1;
 		cs->shift--;
 		cs->maxadj = clocksource_max_adjustment(cs);
 	}
 
-	cs->max_idle_ns = clocksource_max_deferment(cs);
+	/*
+	 * Only warn for *special* clocksources that self-define
+	 * their mult/shift values and don't specify a freq.
+	 */
+	WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+		"timekeeping: Clocksource %s might overflow on 11%% adjustment\n",
+		cs->name);
+
+	clocksource_update_max_deferment(cs);
+
+	pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
+			cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
 }
-EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
+EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
 
 /**
  * __clocksource_register_scale - Used to install new clocksources
@@ -714,7 +725,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
 
 	/* Initialize mult/shift and max_idle_ns */
-	__clocksource_updatefreq_scale(cs, scale, freq);
+	__clocksource_update_freq_scale(cs, scale, freq);
 
 	/* Add clocksource to the clocksource list */
 	mutex_lock(&clocksource_mutex);
@@ -726,33 +737,6 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 }
 EXPORT_SYMBOL_GPL(__clocksource_register_scale);
 
-
-/**
- * clocksource_register - Used to install new clocksources
- * @cs:		clocksource to be registered
- *
- * Returns -EBUSY if registration fails, zero otherwise.
- */
-int clocksource_register(struct clocksource *cs)
-{
-	/* calculate max adjustment for given mult/shift */
-	cs->maxadj = clocksource_max_adjustment(cs);
-	WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
-		"Clocksource %s might overflow on 11%% adjustment\n",
-		cs->name);
-
-	/* calculate max idle time permitted for this clocksource */
-	cs->max_idle_ns = clocksource_max_deferment(cs);
-
-	mutex_lock(&clocksource_mutex);
-	clocksource_enqueue(cs);
-	clocksource_enqueue_watchdog(cs);
-	clocksource_select();
-	mutex_unlock(&clocksource_mutex);
-	return 0;
-}
-EXPORT_SYMBOL(clocksource_register);
-
 static void __clocksource_change_rating(struct clocksource *cs, int rating)
 {
 	list_del(&cs->list);

kernel/time/jiffies.c

@@ -71,6 +71,7 @@ static struct clocksource clocksource_jiffies = {
 	.mask		= 0xffffffff, /*32bits*/
 	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
 	.shift		= JIFFIES_SHIFT,
+	.max_cycles	= 10,
 };
 
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
@@ -94,7 +95,7 @@ EXPORT_SYMBOL(jiffies);
 
 static int __init init_jiffies_clocksource(void)
 {
-	return clocksource_register(&clocksource_jiffies);
+	return __clocksource_register(&clocksource_jiffies);
 }
 
 core_initcall(init_jiffies_clocksource);
@@ -130,6 +131,6 @@ int register_refined_jiffies(long cycles_per_second)
 
 	refined_jiffies.mult = ((u32)nsec_per_tick) << JIFFIES_SHIFT;
 
-	clocksource_register(&refined_jiffies);
+	__clocksource_register(&refined_jiffies);
 	return 0;
 }

kernel/time/timer_list.c

@@ -228,9 +228,35 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 	print_name_offset(m, dev->set_next_event);
 	SEQ_printf(m, "\n");
 
-	SEQ_printf(m, " set_mode:       ");
-	print_name_offset(m, dev->set_mode);
-	SEQ_printf(m, "\n");
+	if (dev->set_mode) {
+		SEQ_printf(m, " set_mode:       ");
+		print_name_offset(m, dev->set_mode);
+		SEQ_printf(m, "\n");
+	} else {
+		if (dev->set_mode_shutdown) {
+			SEQ_printf(m, " shutdown: ");
+			print_name_offset(m, dev->set_mode_shutdown);
+			SEQ_printf(m, "\n");
+		}
+
+		if (dev->set_mode_periodic) {
+			SEQ_printf(m, " periodic: ");
+			print_name_offset(m, dev->set_mode_periodic);
+			SEQ_printf(m, "\n");
+		}
+
+		if (dev->set_mode_oneshot) {
+			SEQ_printf(m, " oneshot:  ");
+			print_name_offset(m, dev->set_mode_oneshot);
+			SEQ_printf(m, "\n");
+		}
+
+		if (dev->set_mode_resume) {
+			SEQ_printf(m, " resume:   ");
+			print_name_offset(m, dev->set_mode_resume);
+			SEQ_printf(m, "\n");
+		}
+	}
 
 	SEQ_printf(m, " event_handler:  ");
 	print_name_offset(m, dev->event_handler);

lib/Kconfig.debug

@@ -865,6 +865,19 @@ config SCHED_STACK_END_CHECK
 	  data corruption or a sporadic crash at a later stage once the region
 	  is examined. The runtime overhead introduced is minimal.
 
+config DEBUG_TIMEKEEPING
+	bool "Enable extra timekeeping sanity checking"
+	help
+	  This option will enable additional timekeeping sanity checks
+	  which may be helpful when diagnosing issues where timekeeping
+	  problems are suspected.
+
+	  This may include checks in the timekeeping hotpaths, so this
+	  option may have a (very small) performance impact to some
+	  workloads.
+
+	  If unsure, say N.
+
 config TIMER_STATS
 	bool "Collect kernel timers statistics"
 	depends on DEBUG_KERNEL && PROC_FS