Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Ingo Molnar:
 "The main changes in this cycle were:

   - clockevents state machine cleanups and enhancements (Viresh Kumar)

   - clockevents broadcast notifier horror to state machine conversion
     and related cleanups (Thomas Gleixner, Rafael J Wysocki)

   - clocksource and timekeeping core updates (John Stultz)

   - clocksource driver updates and fixes (Ben Dooks, Dmitry Osipenko,
     Hans de Goede, Laurent Pinchart, Maxime Ripard, Xunlei Pang)

   - y2038 fixes (Xunlei Pang, John Stultz)

   - NMI-safe ktime_get_raw_fast() and general refactoring of the clock
     code, in preparation to perf's per event clock ID support (Peter
     Zijlstra)

   - generic sched/clock fixes, optimizations and cleanups (Daniel
     Thompson)

   - clockevents cpu_down() race fix (Preeti U Murthy)"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (94 commits)
  timers/PM: Drop unnecessary braces from tick_freeze()
  timers/PM: Fix up tick_unfreeze()
  timekeeping: Get rid of stale comment
  clockevents: Cleanup dead cpu explicitely
  clockevents: Make tick handover explicit
  clockevents: Remove broadcast oneshot control leftovers
  sched/idle: Use explicit broadcast oneshot control function
  ARM: Tegra: Use explicit broadcast oneshot control function
  ARM: OMAP: Use explicit broadcast oneshot control function
  intel_idle: Use explicit broadcast oneshot control function
  ACPI/idle: Use explicit broadcast control function
  ACPI/PAD: Use explicit broadcast oneshot control function
  x86/amd/idle, clockevents: Use explicit broadcast oneshot control functions
  clockevents: Provide explicit broadcast oneshot control functions
  clockevents: Remove the broadcast control leftovers
  ARM: OMAP: Use explicit broadcast control function
  intel_idle: Use explicit broadcast control function
  cpuidle: Use explicit broadcast control function
  ACPI/processor: Use explicit broadcast control function
  ACPI/PAD: Use explicit broadcast control function
  ...

arch/alpha/kernel/rtc.c

@@ -116,7 +116,7 @@ alpha_rtc_set_time(struct device *dev, struct rtc_time *tm)
 }
 
 static int
-alpha_rtc_set_mmss(struct device *dev, unsigned long nowtime)
+alpha_rtc_set_mmss(struct device *dev, time64_t nowtime)
 {
 	int retval = 0;
 	int real_seconds, real_minutes, cmos_minutes;
@@ -211,7 +211,7 @@ alpha_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 static const struct rtc_class_ops alpha_rtc_ops = {
 	.read_time = alpha_rtc_read_time,
 	.set_time = alpha_rtc_set_time,
-	.set_mmss = alpha_rtc_set_mmss,
+	.set_mmss64 = alpha_rtc_set_mmss,
 	.ioctl = alpha_rtc_ioctl,
 };
 
@@ -276,7 +276,7 @@ do_remote_mmss(void *data)
 }
 
 static int
-remote_set_mmss(struct device *dev, unsigned long now)
+remote_set_mmss(struct device *dev, time64_t now)
 {
 	union remote_data x;
 	if (smp_processor_id() != boot_cpuid) {
@@ -290,7 +290,7 @@ remote_set_mmss(struct device *dev, unsigned long now)
 static const struct rtc_class_ops remote_rtc_ops = {
 	.read_time = remote_read_time,
 	.set_time = remote_set_time,
-	.set_mmss = remote_set_mmss,
+	.set_mmss64 = remote_set_mmss,
 	.ioctl = alpha_rtc_ioctl,
 };
 #endif

arch/arm/common/bL_switcher.c

@@ -151,8 +151,6 @@ static int bL_switch_to(unsigned int new_cluster_id)
 	unsigned int mpidr, this_cpu, that_cpu;
 	unsigned int ob_mpidr, ob_cpu, ob_cluster, ib_mpidr, ib_cpu, ib_cluster;
 	struct completion inbound_alive;
-	struct tick_device *tdev;
-	enum clock_event_mode tdev_mode;
 	long volatile *handshake_ptr;
 	int ipi_nr, ret;
 
@@ -219,13 +217,7 @@ static int bL_switch_to(unsigned int new_cluster_id)
 	/* redirect GIC's SGIs to our counterpart */
 	gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]);
 
-	tdev = tick_get_device(this_cpu);
-	if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu)))
-		tdev = NULL;
-	if (tdev) {
-		tdev_mode = tdev->evtdev->mode;
-		clockevents_set_mode(tdev->evtdev, CLOCK_EVT_MODE_SHUTDOWN);
-	}
+	tick_suspend_local();
 
 	ret = cpu_pm_enter();
 
@@ -251,11 +243,7 @@ static int bL_switch_to(unsigned int new_cluster_id)
 
 	ret = cpu_pm_exit();
 
-	if (tdev) {
-		clockevents_set_mode(tdev->evtdev, tdev_mode);
-		clockevents_program_event(tdev->evtdev,
-					  tdev->evtdev->next_event, 1);
-	}
+	tick_resume_local();
 
 	trace_cpu_migrate_finish(ktime_get_real_ns(), ib_mpidr);
 	local_fiq_enable();

arch/arm/include/asm/mach/time.h

@@ -12,8 +12,7 @@
 
 extern void timer_tick(void);
 
-struct timespec;
-typedef void (*clock_access_fn)(struct timespec *);
+typedef void (*clock_access_fn)(struct timespec64 *);
 extern int register_persistent_clock(clock_access_fn read_boot,
 				     clock_access_fn read_persistent);
 

arch/arm/kernel/time.c

@@ -76,7 +76,7 @@ void timer_tick(void)
 }
 #endif
 
-static void dummy_clock_access(struct timespec *ts)
+static void dummy_clock_access(struct timespec64 *ts)
 {
 	ts->tv_sec = 0;
 	ts->tv_nsec = 0;
@@ -85,12 +85,12 @@ static void dummy_clock_access(struct timespec *ts)
 static clock_access_fn __read_persistent_clock = dummy_clock_access;
 static clock_access_fn __read_boot_clock = dummy_clock_access;;
 
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
 {
 	__read_persistent_clock(ts);
 }
 
-void read_boot_clock(struct timespec *ts)
+void read_boot_clock64(struct timespec64 *ts)
 {
 	__read_boot_clock(ts);
 }

arch/arm/mach-omap2/cpuidle44xx.c

@@ -14,7 +14,7 @@
 #include <linux/cpuidle.h>
 #include <linux/cpu_pm.h>
 #include <linux/export.h>
-#include <linux/clockchips.h>
+#include <linux/tick.h>
 
 #include <asm/cpuidle.h>
 #include <asm/proc-fns.h>
@@ -84,7 +84,6 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 {
 	struct idle_statedata *cx = state_ptr + index;
 	u32 mpuss_can_lose_context = 0;
-	int cpu_id = smp_processor_id();
 
 	/*
 	 * CPU0 has to wait and stay ON until CPU1 is OFF state.
@@ -112,7 +111,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 	mpuss_can_lose_context = (cx->mpu_state == PWRDM_POWER_RET) &&
 				 (cx->mpu_logic_state == PWRDM_POWER_OFF);
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu_id);
+	tick_broadcast_enter();
 
 	/*
 	 * Call idle CPU PM enter notifier chain so that
@@ -169,7 +168,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 	if (dev->cpu == 0 && mpuss_can_lose_context)
 		cpu_cluster_pm_exit();
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu_id);
+	tick_broadcast_exit();
 
 fail:
 	cpuidle_coupled_parallel_barrier(dev, &abort_barrier);
@@ -184,8 +183,7 @@ fail:
  */
 static void omap_setup_broadcast_timer(void *arg)
 {
-	int cpu = smp_processor_id();
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &cpu);
+	tick_broadcast_enable();
 }
 
 static struct cpuidle_driver omap4_idle_driver = {

arch/arm/mach-tegra/cpuidle-tegra114.c

@@ -15,7 +15,7 @@
  */
 
 #include <asm/firmware.h>
-#include <linux/clockchips.h>
+#include <linux/tick.h>
 #include <linux/cpuidle.h>
 #include <linux/cpu_pm.h>
 #include <linux/kernel.h>
@@ -44,7 +44,7 @@ static int tegra114_idle_power_down(struct cpuidle_device *dev,
 	tegra_set_cpu_in_lp2();
 	cpu_pm_enter();
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu);
+	tick_broadcast_enter();
 
 	call_firmware_op(prepare_idle);
 
@@ -52,7 +52,7 @@ static int tegra114_idle_power_down(struct cpuidle_device *dev,
 	if (call_firmware_op(do_idle, 0) == -ENOSYS)
 		cpu_suspend(0, tegra30_sleep_cpu_secondary_finish);
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+	tick_broadcast_exit();
 
 	cpu_pm_exit();
 	tegra_clear_cpu_in_lp2();

arch/arm/mach-tegra/cpuidle-tegra20.c

@@ -20,7 +20,7 @@
  */
 
 #include <linux/clk/tegra.h>
-#include <linux/clockchips.h>
+#include <linux/tick.h>
 #include <linux/cpuidle.h>
 #include <linux/cpu_pm.h>
 #include <linux/kernel.h>
@@ -136,11 +136,11 @@ static bool tegra20_cpu_cluster_power_down(struct cpuidle_device *dev,
 	if (tegra20_reset_cpu_1() || !tegra_cpu_rail_off_ready())
 		return false;
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu);
+	tick_broadcast_enter();
 
 	tegra_idle_lp2_last();
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+	tick_broadcast_exit();
 
 	if (cpu_online(1))
 		tegra20_wake_cpu1_from_reset();
@@ -153,13 +153,13 @@ static bool tegra20_idle_enter_lp2_cpu_1(struct cpuidle_device *dev,
 					 struct cpuidle_driver *drv,
 					 int index)
 {
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu);
+	tick_broadcast_enter();
 
 	cpu_suspend(0, tegra20_sleep_cpu_secondary_finish);
 
 	tegra20_cpu_clear_resettable();
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+	tick_broadcast_exit();
 
 	return true;
 }

arch/arm/mach-tegra/cpuidle-tegra30.c

@@ -20,7 +20,7 @@
  */
 
 #include <linux/clk/tegra.h>
-#include <linux/clockchips.h>
+#include <linux/tick.h>
 #include <linux/cpuidle.h>
 #include <linux/cpu_pm.h>
 #include <linux/kernel.h>
@@ -76,11 +76,11 @@ static bool tegra30_cpu_cluster_power_down(struct cpuidle_device *dev,
 		return false;
 	}
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu);
+	tick_broadcast_enter();
 
 	tegra_idle_lp2_last();
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+	tick_broadcast_exit();
 
 	return true;
 }
@@ -90,13 +90,13 @@ static bool tegra30_cpu_core_power_down(struct cpuidle_device *dev,
 					struct cpuidle_driver *drv,
 					int index)
 {
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu);
+	tick_broadcast_enter();
 
 	smp_wmb();
 
 	cpu_suspend(0, tegra30_sleep_cpu_secondary_finish);
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+	tick_broadcast_exit();
 
 	return true;
 }

arch/arm/plat-omap/counter_32k.c

@@ -44,24 +44,20 @@ static u64 notrace omap_32k_read_sched_clock(void)
 }
 
 /**
- * omap_read_persistent_clock -  Return time from a persistent clock.
+ * omap_read_persistent_clock64 -  Return time from a persistent clock.
  *
  * Reads the time from a source which isn't disabled during PM, the
  * 32k sync timer.  Convert the cycles elapsed since last read into
- * nsecs and adds to a monotonically increasing timespec.
+ * nsecs and adds to a monotonically increasing timespec64.
  */
-static struct timespec persistent_ts;
+static struct timespec64 persistent_ts;
 static cycles_t cycles;
 static unsigned int persistent_mult, persistent_shift;
-static DEFINE_SPINLOCK(read_persistent_clock_lock);
 
-static void omap_read_persistent_clock(struct timespec *ts)
+static void omap_read_persistent_clock64(struct timespec64 *ts)
 {
 	unsigned long long nsecs;
 	cycles_t last_cycles;
-	unsigned long flags;
-
-	spin_lock_irqsave(&read_persistent_clock_lock, flags);
 
 	last_cycles = cycles;
 	cycles = sync32k_cnt_reg ? readl_relaxed(sync32k_cnt_reg) : 0;
@@ -69,11 +65,9 @@ static void omap_read_persistent_clock(struct timespec *ts)
 	nsecs = clocksource_cyc2ns(cycles - last_cycles,
 					persistent_mult, persistent_shift);
 
-	timespec_add_ns(&persistent_ts, nsecs);
+	timespec64_add_ns(&persistent_ts, nsecs);
 
 	*ts = persistent_ts;
-
-	spin_unlock_irqrestore(&read_persistent_clock_lock, flags);
 }
 
 /**
@@ -103,7 +97,7 @@ 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);
@@ -116,7 +110,7 @@ int __init omap_init_clocksource_32k(void __iomem *vbase)
 	}
 
 	sched_clock_register(omap_32k_read_sched_clock, 32, 32768);
-	register_persistent_clock(NULL, omap_read_persistent_clock);
+	register_persistent_clock(NULL, omap_read_persistent_clock64);
 	pr_info("OMAP clocksource: 32k_counter at 32768 Hz\n");
 
 	return 0;

arch/arm64/kernel/vdso.c

@@ -200,7 +200,7 @@ up_fail:
 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/mips/lasat/sysctl.c

@@ -75,11 +75,11 @@ static int rtctmp;
 int proc_dolasatrtc(struct ctl_table *table, int write,
 		       void *buffer, size_t *lenp, loff_t *ppos)
 {
-	struct timespec ts;
+	struct timespec64 ts;
 	int r;
 
 	if (!write) {
-		read_persistent_clock(&ts);
+		read_persistent_clock64(&ts);
 		rtctmp = ts.tv_sec;
 		/* check for time < 0 and set to 0 */
 		if (rtctmp < 0)

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/process.c

@@ -9,7 +9,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/pm.h>
-#include <linux/clockchips.h>
+#include <linux/tick.h>
 #include <linux/random.h>
 #include <linux/user-return-notifier.h>
 #include <linux/dmi.h>
@@ -378,14 +378,11 @@ static void amd_e400_idle(void)
 
 		if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) {
 			cpumask_set_cpu(cpu, amd_e400_c1e_mask);
-			/*
-			 * Force broadcast so ACPI can not interfere.
-			 */
-			clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
-					   &cpu);
+			/* Force broadcast so ACPI can not interfere. */
+			tick_broadcast_force();
 			pr_info("Switch to broadcast mode on CPU%d\n", cpu);
 		}
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
+		tick_broadcast_enter();
 
 		default_idle();
 
@@ -394,7 +391,7 @@ static void amd_e400_idle(void)
 		 * called with interrupts disabled.
 		 */
 		local_irq_disable();
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+		tick_broadcast_exit();
 		local_irq_enable();
 	} else
 		default_idle();

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

@@ -1081,19 +1081,19 @@ 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);
 }

arch/x86/xen/suspend.c

@@ -1,5 +1,5 @@
 #include <linux/types.h>
-#include <linux/clockchips.h>
+#include <linux/tick.h>
 
 #include <xen/interface/xen.h>
 #include <xen/grant_table.h>
@@ -81,17 +81,14 @@ void xen_arch_post_suspend(int cancelled)
 
 static void xen_vcpu_notify_restore(void *data)
 {
-	unsigned long reason = (unsigned long)data;
-
 	/* Boot processor notified via generic timekeeping_resume() */
-	if ( smp_processor_id() == 0)
+	if (smp_processor_id() == 0)
 		return;
 
-	clockevents_notify(reason, NULL);
+	tick_resume_local();
 }
 
 void xen_arch_resume(void)
 {
-	on_each_cpu(xen_vcpu_notify_restore,
-		    (void *)CLOCK_EVT_NOTIFY_RESUME, 1);
+	on_each_cpu(xen_vcpu_notify_restore, NULL, 1);
 }

drivers/acpi/acpi_pad.c

@@ -26,7 +26,7 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/cpu.h>
-#include <linux/clockchips.h>
+#include <linux/tick.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
 #include <asm/mwait.h>
@@ -41,8 +41,6 @@ static unsigned long power_saving_mwait_eax;
 
 static unsigned char tsc_detected_unstable;
 static unsigned char tsc_marked_unstable;
-static unsigned char lapic_detected_unstable;
-static unsigned char lapic_marked_unstable;
 
 static void power_saving_mwait_init(void)
 {
@@ -82,13 +80,10 @@ static void power_saving_mwait_init(void)
 		 */
 		if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 			tsc_detected_unstable = 1;
-		if (!boot_cpu_has(X86_FEATURE_ARAT))
-			lapic_detected_unstable = 1;
 		break;
 	default:
-		/* TSC & LAPIC could halt in idle */
+		/* TSC could halt in idle */
 		tsc_detected_unstable = 1;
-		lapic_detected_unstable = 1;
 	}
 #endif
 }
@@ -155,7 +150,6 @@ static int power_saving_thread(void *data)
 	sched_setscheduler(current, SCHED_RR, &param);
 
 	while (!kthread_should_stop()) {
-		int cpu;
 		unsigned long expire_time;
 
 		try_to_freeze();
@@ -177,28 +171,15 @@ static int power_saving_thread(void *data)
 				mark_tsc_unstable("TSC halts in idle");
 				tsc_marked_unstable = 1;
 			}
-			if (lapic_detected_unstable && !lapic_marked_unstable) {
-				int i;
-				/* LAPIC could halt in idle, so notify users */
-				for_each_online_cpu(i)
-					clockevents_notify(
-						CLOCK_EVT_NOTIFY_BROADCAST_ON,
-						&i);
-				lapic_marked_unstable = 1;
-			}
 			local_irq_disable();
-			cpu = smp_processor_id();
-			if (lapic_marked_unstable)
-				clockevents_notify(
-					CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
+			tick_broadcast_enable();
+			tick_broadcast_enter();
 			stop_critical_timings();
 
 			mwait_idle_with_hints(power_saving_mwait_eax, 1);
 
 			start_critical_timings();
-			if (lapic_marked_unstable)
-				clockevents_notify(
-					CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+			tick_broadcast_exit();
 			local_irq_enable();
 
 			if (time_before(expire_time, jiffies)) {

drivers/acpi/processor_idle.c

@@ -32,7 +32,7 @@
 #include <linux/acpi.h>
 #include <linux/dmi.h>
 #include <linux/sched.h>       /* need_resched() */
-#include <linux/clockchips.h>
+#include <linux/tick.h>
 #include <linux/cpuidle.h>
 #include <linux/syscore_ops.h>
 #include <acpi/processor.h>
@@ -157,12 +157,11 @@ static void lapic_timer_check_state(int state, struct acpi_processor *pr,
 static void __lapic_timer_propagate_broadcast(void *arg)
 {
 	struct acpi_processor *pr = (struct acpi_processor *) arg;
-	unsigned long reason;
 
-	reason = pr->power.timer_broadcast_on_state < INT_MAX ?
-		CLOCK_EVT_NOTIFY_BROADCAST_ON : CLOCK_EVT_NOTIFY_BROADCAST_OFF;
-
-	clockevents_notify(reason, &pr->id);
+	if (pr->power.timer_broadcast_on_state < INT_MAX)
+		tick_broadcast_enable();
+	else
+		tick_broadcast_disable();
 }
 
 static void lapic_timer_propagate_broadcast(struct acpi_processor *pr)
@@ -179,11 +178,10 @@ static void lapic_timer_state_broadcast(struct acpi_processor *pr,
 	int state = cx - pr->power.states;
 
 	if (state >= pr->power.timer_broadcast_on_state) {
-		unsigned long reason;
-
-		reason = broadcast ?  CLOCK_EVT_NOTIFY_BROADCAST_ENTER :
-			CLOCK_EVT_NOTIFY_BROADCAST_EXIT;
-		clockevents_notify(reason, &pr->id);
+		if (broadcast)
+			tick_broadcast_enter();
+		else
+			tick_broadcast_exit();
 	}
 }
 

drivers/clocksource/arm_arch_timer.c

@@ -661,17 +661,17 @@ static const struct of_device_id arch_timer_mem_of_match[] __initconst = {
 };
 
 static bool __init
-arch_timer_probed(int type, const struct of_device_id *matches)
+arch_timer_needs_probing(int type, const struct of_device_id *matches)
 {
 	struct device_node *dn;
-	bool probed = true;
+	bool needs_probing = false;
 
 	dn = of_find_matching_node(NULL, matches);
 	if (dn && of_device_is_available(dn) && !(arch_timers_present & type))
-		probed = false;
+		needs_probing = true;
 	of_node_put(dn);
 
-	return probed;
+	return needs_probing;
 }
 
 static void __init arch_timer_common_init(void)
@@ -680,9 +680,9 @@ static void __init arch_timer_common_init(void)
 
 	/* Wait until both nodes are probed if we have two timers */
 	if ((arch_timers_present & mask) != mask) {
-		if (!arch_timer_probed(ARCH_MEM_TIMER, arch_timer_mem_of_match))
+		if (arch_timer_needs_probing(ARCH_MEM_TIMER, arch_timer_mem_of_match))
 			return;
-		if (!arch_timer_probed(ARCH_CP15_TIMER, arch_timer_of_match))
+		if (arch_timer_needs_probing(ARCH_CP15_TIMER, arch_timer_of_match))
 			return;
 	}
 

drivers/clocksource/dw_apb_timer_of.c

@@ -108,7 +108,7 @@ static void __init add_clocksource(struct device_node *source_timer)
 
 static u64 notrace read_sched_clock(void)
 {
-	return ~__raw_readl(sched_io_base);
+	return ~readl_relaxed(sched_io_base);
 }
 
 static const struct of_device_id sptimer_ids[] __initconst = {

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;
 	}
 

drivers/clocksource/sun4i_timer.c

@@ -170,7 +170,15 @@ static void __init sun4i_timer_init(struct device_node *node)
 	       TIMER_CTL_CLK_SRC(TIMER_CTL_CLK_SRC_OSC24M),
 	       timer_base + TIMER_CTL_REG(1));
 
-	sched_clock_register(sun4i_timer_sched_read, 32, rate);
+	/*
+	 * sched_clock_register does not have priorities, and on sun6i and
+	 * later there is a better sched_clock registered by arm_arch_timer.c
+	 */
+	if (of_machine_is_compatible("allwinner,sun4i-a10") ||
+	    of_machine_is_compatible("allwinner,sun5i-a13") ||
+	    of_machine_is_compatible("allwinner,sun5i-a10s"))
+		sched_clock_register(sun4i_timer_sched_read, 32, rate);
+
 	clocksource_mmio_init(timer_base + TIMER_CNTVAL_REG(1), node->name,
 			      rate, 350, 32, clocksource_mmio_readl_down);
 

drivers/clocksource/tegra20_timer.c

@@ -51,15 +51,15 @@
 static void __iomem *timer_reg_base;
 static void __iomem *rtc_base;
 
-static struct timespec persistent_ts;
+static struct timespec64 persistent_ts;
 static u64 persistent_ms, last_persistent_ms;
 
 static struct delay_timer tegra_delay_timer;
 
 #define timer_writel(value, reg) \
-	__raw_writel(value, timer_reg_base + (reg))
+	writel_relaxed(value, timer_reg_base + (reg))
 #define timer_readl(reg) \
-	__raw_readl(timer_reg_base + (reg))
+	readl_relaxed(timer_reg_base + (reg))
 
 static int tegra_timer_set_next_event(unsigned long cycles,
 					 struct clock_event_device *evt)
@@ -120,26 +120,25 @@ static u64 tegra_rtc_read_ms(void)
 }
 
 /*
- * tegra_read_persistent_clock -  Return time from a persistent clock.
+ * tegra_read_persistent_clock64 -  Return time from a persistent clock.
  *
  * Reads the time from a source which isn't disabled during PM, the
  * 32k sync timer.  Convert the cycles elapsed since last read into
- * nsecs and adds to a monotonically increasing timespec.
+ * nsecs and adds to a monotonically increasing timespec64.
  * Care must be taken that this funciton is not called while the
  * tegra_rtc driver could be executing to avoid race conditions
  * on the RTC shadow register
  */
-static void tegra_read_persistent_clock(struct timespec *ts)
+static void tegra_read_persistent_clock64(struct timespec64 *ts)
 {
 	u64 delta;
-	struct timespec *tsp = &persistent_ts;
 
 	last_persistent_ms = persistent_ms;
 	persistent_ms = tegra_rtc_read_ms();
 	delta = persistent_ms - last_persistent_ms;
 
-	timespec_add_ns(tsp, delta * NSEC_PER_MSEC);
-	*ts = *tsp;
+	timespec64_add_ns(&persistent_ts, delta * NSEC_PER_MSEC);
+	*ts = persistent_ts;
 }
 
 static unsigned long tegra_delay_timer_read_counter_long(void)
@@ -252,7 +251,7 @@ static void __init tegra20_init_rtc(struct device_node *np)
 	else
 		clk_prepare_enable(clk);
 
-	register_persistent_clock(NULL, tegra_read_persistent_clock);
+	register_persistent_clock(NULL, tegra_read_persistent_clock64);
 }
 CLOCKSOURCE_OF_DECLARE(tegra20_rtc, "nvidia,tegra20-rtc", tegra20_init_rtc);
 

drivers/clocksource/time-efm32.c

@@ -111,7 +111,7 @@ static irqreturn_t efm32_clock_event_handler(int irq, void *dev_id)
 static struct efm32_clock_event_ddata clock_event_ddata = {
 	.evtdev = {
 		.name = "efm32 clockevent",
-		.features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_MODE_PERIODIC,
+		.features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
 		.set_mode = efm32_clock_event_set_mode,
 		.set_next_event = efm32_clock_event_set_next_event,
 		.rating = 200,

drivers/clocksource/timer-atmel-pit.c

@@ -61,12 +61,12 @@ static inline struct pit_data *clkevt_to_pit_data(struct clock_event_device *clk
 
 static inline unsigned int pit_read(void __iomem *base, unsigned int reg_offset)
 {
-	return __raw_readl(base + reg_offset);
+	return readl_relaxed(base + reg_offset);
 }
 
 static inline void pit_write(void __iomem *base, unsigned int reg_offset, unsigned long value)
 {
-	__raw_writel(value, base + reg_offset);
+	writel_relaxed(value, base + reg_offset);
 }
 
 /*

drivers/clocksource/timer-sun5i.c

@@ -17,6 +17,7 @@
 #include <linux/irq.h>
 #include <linux/irqreturn.h>
 #include <linux/reset.h>
+#include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -36,8 +37,31 @@
 
 #define TIMER_SYNC_TICKS	3
 
-static void __iomem *timer_base;
-static u32 ticks_per_jiffy;
+struct sun5i_timer {
+	void __iomem		*base;
+	struct clk		*clk;
+	struct notifier_block	clk_rate_cb;
+	u32			ticks_per_jiffy;
+};
+
+#define to_sun5i_timer(x) \
+	container_of(x, struct sun5i_timer, clk_rate_cb)
+
+struct sun5i_timer_clksrc {
+	struct sun5i_timer	timer;
+	struct clocksource	clksrc;
+};
+
+#define to_sun5i_timer_clksrc(x) \
+	container_of(x, struct sun5i_timer_clksrc, clksrc)
+
+struct sun5i_timer_clkevt {
+	struct sun5i_timer		timer;
+	struct clock_event_device	clkevt;
+};
+
+#define to_sun5i_timer_clkevt(x) \
+	container_of(x, struct sun5i_timer_clkevt, clkevt)
 
 /*
  * When we disable a timer, we need to wait at least for 2 cycles of
@@ -45,30 +69,30 @@ static u32 ticks_per_jiffy;
  * that is already setup and runs at the same frequency than the other
  * timers, and we never will be disabled.
  */
-static void sun5i_clkevt_sync(void)
+static void sun5i_clkevt_sync(struct sun5i_timer_clkevt *ce)
 {
-	u32 old = readl(timer_base + TIMER_CNTVAL_LO_REG(1));
+	u32 old = readl(ce->timer.base + TIMER_CNTVAL_LO_REG(1));
 
-	while ((old - readl(timer_base + TIMER_CNTVAL_LO_REG(1))) < TIMER_SYNC_TICKS)
+	while ((old - readl(ce->timer.base + TIMER_CNTVAL_LO_REG(1))) < TIMER_SYNC_TICKS)
 		cpu_relax();
 }
 
-static void sun5i_clkevt_time_stop(u8 timer)
+static void sun5i_clkevt_time_stop(struct sun5i_timer_clkevt *ce, u8 timer)
 {
-	u32 val = readl(timer_base + TIMER_CTL_REG(timer));
-	writel(val & ~TIMER_CTL_ENABLE, timer_base + TIMER_CTL_REG(timer));
+	u32 val = readl(ce->timer.base + TIMER_CTL_REG(timer));
+	writel(val & ~TIMER_CTL_ENABLE, ce->timer.base + TIMER_CTL_REG(timer));
 
-	sun5i_clkevt_sync();
+	sun5i_clkevt_sync(ce);
 }
 
-static void sun5i_clkevt_time_setup(u8 timer, u32 delay)
+static void sun5i_clkevt_time_setup(struct sun5i_timer_clkevt *ce, u8 timer, u32 delay)
 {
-	writel(delay, timer_base + TIMER_INTVAL_LO_REG(timer));
+	writel(delay, ce->timer.base + TIMER_INTVAL_LO_REG(timer));
 }
 
-static void sun5i_clkevt_time_start(u8 timer, bool periodic)
+static void sun5i_clkevt_time_start(struct sun5i_timer_clkevt *ce, u8 timer, bool periodic)
 {
-	u32 val = readl(timer_base + TIMER_CTL_REG(timer));
+	u32 val = readl(ce->timer.base + TIMER_CTL_REG(timer));
 
 	if (periodic)
 		val &= ~TIMER_CTL_ONESHOT;
@@ -76,75 +100,230 @@ static void sun5i_clkevt_time_start(u8 timer, bool periodic)
 		val |= TIMER_CTL_ONESHOT;
 
 	writel(val | TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
-	       timer_base + TIMER_CTL_REG(timer));
+	       ce->timer.base + TIMER_CTL_REG(timer));
 }
 
 static void sun5i_clkevt_mode(enum clock_event_mode mode,
-			      struct clock_event_device *clk)
+			      struct clock_event_device *clkevt)
 {
+	struct sun5i_timer_clkevt *ce = to_sun5i_timer_clkevt(clkevt);
+
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
-		sun5i_clkevt_time_stop(0);
-		sun5i_clkevt_time_setup(0, ticks_per_jiffy);
-		sun5i_clkevt_time_start(0, true);
+		sun5i_clkevt_time_stop(ce, 0);
+		sun5i_clkevt_time_setup(ce, 0, ce->timer.ticks_per_jiffy);
+		sun5i_clkevt_time_start(ce, 0, true);
 		break;
 	case CLOCK_EVT_MODE_ONESHOT:
-		sun5i_clkevt_time_stop(0);
-		sun5i_clkevt_time_start(0, false);
+		sun5i_clkevt_time_stop(ce, 0);
+		sun5i_clkevt_time_start(ce, 0, false);
 		break;
 	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
 	default:
-		sun5i_clkevt_time_stop(0);
+		sun5i_clkevt_time_stop(ce, 0);
 		break;
 	}
 }
 
 static int sun5i_clkevt_next_event(unsigned long evt,
-				   struct clock_event_device *unused)
+				   struct clock_event_device *clkevt)
 {
-	sun5i_clkevt_time_stop(0);
-	sun5i_clkevt_time_setup(0, evt - TIMER_SYNC_TICKS);
-	sun5i_clkevt_time_start(0, false);
+	struct sun5i_timer_clkevt *ce = to_sun5i_timer_clkevt(clkevt);
+
+	sun5i_clkevt_time_stop(ce, 0);
+	sun5i_clkevt_time_setup(ce, 0, evt - TIMER_SYNC_TICKS);
+	sun5i_clkevt_time_start(ce, 0, false);
 
 	return 0;
 }
 
-static struct clock_event_device sun5i_clockevent = {
-	.name = "sun5i_tick",
-	.rating = 340,
-	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode = sun5i_clkevt_mode,
-	.set_next_event = sun5i_clkevt_next_event,
-};
-
-
 static irqreturn_t sun5i_timer_interrupt(int irq, void *dev_id)
 {
-	struct clock_event_device *evt = (struct clock_event_device *)dev_id;
+	struct sun5i_timer_clkevt *ce = (struct sun5i_timer_clkevt *)dev_id;
 
-	writel(0x1, timer_base + TIMER_IRQ_ST_REG);
-	evt->event_handler(evt);
+	writel(0x1, ce->timer.base + TIMER_IRQ_ST_REG);
+	ce->clkevt.event_handler(&ce->clkevt);
 
 	return IRQ_HANDLED;
 }
 
-static struct irqaction sun5i_timer_irq = {
-	.name = "sun5i_timer0",
-	.flags = IRQF_TIMER | IRQF_IRQPOLL,
-	.handler = sun5i_timer_interrupt,
-	.dev_id = &sun5i_clockevent,
-};
+static cycle_t sun5i_clksrc_read(struct clocksource *clksrc)
+{
+	struct sun5i_timer_clksrc *cs = to_sun5i_timer_clksrc(clksrc);
+
+	return ~readl(cs->timer.base + TIMER_CNTVAL_LO_REG(1));
+}
+
+static int sun5i_rate_cb_clksrc(struct notifier_block *nb,
+				unsigned long event, void *data)
+{
+	struct clk_notifier_data *ndata = data;
+	struct sun5i_timer *timer = to_sun5i_timer(nb);
+	struct sun5i_timer_clksrc *cs = container_of(timer, struct sun5i_timer_clksrc, timer);
+
+	switch (event) {
+	case PRE_RATE_CHANGE:
+		clocksource_unregister(&cs->clksrc);
+		break;
+
+	case POST_RATE_CHANGE:
+		clocksource_register_hz(&cs->clksrc, ndata->new_rate);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int __init sun5i_setup_clocksource(struct device_node *node,
+					  void __iomem *base,
+					  struct clk *clk, int irq)
+{
+	struct sun5i_timer_clksrc *cs;
+	unsigned long rate;
+	int ret;
+
+	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
+	if (!cs)
+		return -ENOMEM;
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("Couldn't enable parent clock\n");
+		goto err_free;
+	}
+
+	rate = clk_get_rate(clk);
+
+	cs->timer.base = base;
+	cs->timer.clk = clk;
+	cs->timer.clk_rate_cb.notifier_call = sun5i_rate_cb_clksrc;
+	cs->timer.clk_rate_cb.next = NULL;
+
+	ret = clk_notifier_register(clk, &cs->timer.clk_rate_cb);
+	if (ret) {
+		pr_err("Unable to register clock notifier.\n");
+		goto err_disable_clk;
+	}
+
+	writel(~0, base + TIMER_INTVAL_LO_REG(1));
+	writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
+	       base + TIMER_CTL_REG(1));
+
+	cs->clksrc.name = node->name;
+	cs->clksrc.rating = 340;
+	cs->clksrc.read = sun5i_clksrc_read;
+	cs->clksrc.mask = CLOCKSOURCE_MASK(32);
+	cs->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS;
+
+	ret = clocksource_register_hz(&cs->clksrc, rate);
+	if (ret) {
+		pr_err("Couldn't register clock source.\n");
+		goto err_remove_notifier;
+	}
+
+	return 0;
+
+err_remove_notifier:
+	clk_notifier_unregister(clk, &cs->timer.clk_rate_cb);
+err_disable_clk:
+	clk_disable_unprepare(clk);
+err_free:
+	kfree(cs);
+	return ret;
+}
+
+static int sun5i_rate_cb_clkevt(struct notifier_block *nb,
+				unsigned long event, void *data)
+{
+	struct clk_notifier_data *ndata = data;
+	struct sun5i_timer *timer = to_sun5i_timer(nb);
+	struct sun5i_timer_clkevt *ce = container_of(timer, struct sun5i_timer_clkevt, timer);
+
+	if (event == POST_RATE_CHANGE) {
+		clockevents_update_freq(&ce->clkevt, ndata->new_rate);
+		ce->timer.ticks_per_jiffy = DIV_ROUND_UP(ndata->new_rate, HZ);
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int __init sun5i_setup_clockevent(struct device_node *node, void __iomem *base,
+					 struct clk *clk, int irq)
+{
+	struct sun5i_timer_clkevt *ce;
+	unsigned long rate;
+	int ret;
+	u32 val;
+
+	ce = kzalloc(sizeof(*ce), GFP_KERNEL);
+	if (!ce)
+		return -ENOMEM;
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("Couldn't enable parent clock\n");
+		goto err_free;
+	}
+
+	rate = clk_get_rate(clk);
+
+	ce->timer.base = base;
+	ce->timer.ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
+	ce->timer.clk = clk;
+	ce->timer.clk_rate_cb.notifier_call = sun5i_rate_cb_clkevt;
+	ce->timer.clk_rate_cb.next = NULL;
+
+	ret = clk_notifier_register(clk, &ce->timer.clk_rate_cb);
+	if (ret) {
+		pr_err("Unable to register clock notifier.\n");
+		goto err_disable_clk;
+	}
+
+	ce->clkevt.name = node->name;
+	ce->clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+	ce->clkevt.set_next_event = sun5i_clkevt_next_event;
+	ce->clkevt.set_mode = sun5i_clkevt_mode;
+	ce->clkevt.rating = 340;
+	ce->clkevt.irq = irq;
+	ce->clkevt.cpumask = cpu_possible_mask;
+
+	/* Enable timer0 interrupt */
+	val = readl(base + TIMER_IRQ_EN_REG);
+	writel(val | TIMER_IRQ_EN(0), base + TIMER_IRQ_EN_REG);
+
+	clockevents_config_and_register(&ce->clkevt, rate,
+					TIMER_SYNC_TICKS, 0xffffffff);
+
+	ret = request_irq(irq, sun5i_timer_interrupt, IRQF_TIMER | IRQF_IRQPOLL,
+			  "sun5i_timer0", ce);
+	if (ret) {
+		pr_err("Unable to register interrupt\n");
+		goto err_remove_notifier;
+	}
+
+	return 0;
+
+err_remove_notifier:
+	clk_notifier_unregister(clk, &ce->timer.clk_rate_cb);
+err_disable_clk:
+	clk_disable_unprepare(clk);
+err_free:
+	kfree(ce);
+	return ret;
+}
 
 static void __init sun5i_timer_init(struct device_node *node)
 {
 	struct reset_control *rstc;
-	unsigned long rate;
+	void __iomem *timer_base;
 	struct clk *clk;
-	int ret, irq;
-	u32 val;
+	int irq;
 
-	timer_base = of_iomap(node, 0);
+	timer_base = of_io_request_and_map(node, 0, of_node_full_name(node));
 	if (!timer_base)
 		panic("Can't map registers");
 
@@ -155,35 +334,13 @@ static void __init sun5i_timer_init(struct device_node *node)
 	clk = of_clk_get(node, 0);
 	if (IS_ERR(clk))
 		panic("Can't get timer clock");
-	clk_prepare_enable(clk);
-	rate = clk_get_rate(clk);
 
 	rstc = of_reset_control_get(node, NULL);
 	if (!IS_ERR(rstc))
 		reset_control_deassert(rstc);
 
-	writel(~0, timer_base + TIMER_INTVAL_LO_REG(1));
-	writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
-	       timer_base + TIMER_CTL_REG(1));
-
-	clocksource_mmio_init(timer_base + TIMER_CNTVAL_LO_REG(1), node->name,
-			      rate, 340, 32, clocksource_mmio_readl_down);
-
-	ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
-
-	/* Enable timer0 interrupt */
-	val = readl(timer_base + TIMER_IRQ_EN_REG);
-	writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG);
-
-	sun5i_clockevent.cpumask = cpu_possible_mask;
-	sun5i_clockevent.irq = irq;
-
-	clockevents_config_and_register(&sun5i_clockevent, rate,
-					TIMER_SYNC_TICKS, 0xffffffff);
-
-	ret = setup_irq(irq, &sun5i_timer_irq);
-	if (ret)
-		pr_warn("failed to setup irq %d\n", irq);
+	sun5i_setup_clocksource(node, timer_base, clk, irq);
+	sun5i_setup_clockevent(node, timer_base, clk, irq);
 }
 CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer",
 		       sun5i_timer_init);

drivers/cpuidle/driver.c

@@ -13,7 +13,7 @@
 #include <linux/sched.h>
 #include <linux/cpuidle.h>
 #include <linux/cpumask.h>
-#include <linux/clockchips.h>
+#include <linux/tick.h>
 
 #include "cpuidle.h"
 
@@ -130,21 +130,20 @@ static inline void __cpuidle_unset_driver(struct cpuidle_driver *drv)
 #endif
 
 /**
- * cpuidle_setup_broadcast_timer - enable/disable the broadcast timer
+ * cpuidle_setup_broadcast_timer - enable/disable the broadcast timer on a cpu
  * @arg: a void pointer used to match the SMP cross call API
  *
- * @arg is used as a value of type 'long' with one of the two values:
- * - CLOCK_EVT_NOTIFY_BROADCAST_ON
- * - CLOCK_EVT_NOTIFY_BROADCAST_OFF
+ * If @arg is NULL broadcast is disabled otherwise enabled
  *
- * Set the broadcast timer notification for the current CPU.  This function
- * is executed per CPU by an SMP cross call.  It not supposed to be called
- * directly.
+ * This function is executed per CPU by an SMP cross call.  It's not
+ * supposed to be called directly.
  */
 static void cpuidle_setup_broadcast_timer(void *arg)
 {
-	int cpu = smp_processor_id();
-	clockevents_notify((long)(arg), &cpu);
+	if (arg)
+		tick_broadcast_enable();
+	else
+		tick_broadcast_disable();
 }
 
 /**
@@ -239,7 +238,7 @@ static int __cpuidle_register_driver(struct cpuidle_driver *drv)
 
 	if (drv->bctimer)
 		on_each_cpu_mask(drv->cpumask, cpuidle_setup_broadcast_timer,
-				 (void *)CLOCK_EVT_NOTIFY_BROADCAST_ON, 1);
+				 (void *)1, 1);
 
 	poll_idle_init(drv);
 
@@ -263,7 +262,7 @@ static void __cpuidle_unregister_driver(struct cpuidle_driver *drv)
 	if (drv->bctimer) {
 		drv->bctimer = 0;
 		on_each_cpu_mask(drv->cpumask, cpuidle_setup_broadcast_timer,
-				 (void *)CLOCK_EVT_NOTIFY_BROADCAST_OFF, 1);
+				 NULL, 1);
 	}
 
 	__cpuidle_unset_driver(drv);

drivers/idle/intel_idle.c

@@ -55,7 +55,7 @@
 
 #include <linux/kernel.h>
 #include <linux/cpuidle.h>
-#include <linux/clockchips.h>
+#include <linux/tick.h>
 #include <trace/events/power.h>
 #include <linux/sched.h>
 #include <linux/notifier.h>
@@ -638,12 +638,12 @@ static int intel_idle(struct cpuidle_device *dev,
 		leave_mm(cpu);
 
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
+		tick_broadcast_enter();
 
 	mwait_idle_with_hints(eax, ecx);
 
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+		tick_broadcast_exit();
 
 	return index;
 }
@@ -665,13 +665,12 @@ static void intel_idle_freeze(struct cpuidle_device *dev,
 
 static void __setup_broadcast_timer(void *arg)
 {
-	unsigned long reason = (unsigned long)arg;
-	int cpu = smp_processor_id();
-
-	reason = reason ?
-		CLOCK_EVT_NOTIFY_BROADCAST_ON : CLOCK_EVT_NOTIFY_BROADCAST_OFF;
+	unsigned long on = (unsigned long)arg;
 
-	clockevents_notify(reason, &cpu);
+	if (on)
+		tick_broadcast_enable();
+	else
+		tick_broadcast_disable();
 }
 
 static int cpu_hotplug_notify(struct notifier_block *n,

drivers/rtc/class.c

@@ -55,7 +55,7 @@ static int rtc_suspend(struct device *dev)
 	struct timespec64	delta, delta_delta;
 	int err;
 
-	if (has_persistent_clock())
+	if (timekeeping_rtc_skipsuspend())
 		return 0;
 
 	if (strcmp(dev_name(&rtc->dev), CONFIG_RTC_HCTOSYS_DEVICE) != 0)
@@ -102,7 +102,7 @@ static int rtc_resume(struct device *dev)
 	struct timespec64	sleep_time;
 	int err;
 
-	if (has_persistent_clock())
+	if (timekeeping_rtc_skipresume())
 		return 0;
 
 	rtc_hctosys_ret = -ENODEV;
@@ -117,10 +117,6 @@ static int rtc_resume(struct device *dev)
 		return 0;
 	}
 
-	if (rtc_valid_tm(&tm) != 0) {
-		pr_debug("%s:  bogus resume time\n", dev_name(&rtc->dev));
-		return 0;
-	}
 	new_rtc.tv_sec = rtc_tm_to_time64(&tm);
 	new_rtc.tv_nsec = 0;
 

drivers/rtc/interface.c

@@ -72,7 +72,11 @@ int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm)
 		err = -ENODEV;
 	else if (rtc->ops->set_time)
 		err = rtc->ops->set_time(rtc->dev.parent, tm);
-	else if (rtc->ops->set_mmss) {
+	else if (rtc->ops->set_mmss64) {
+		time64_t secs64 = rtc_tm_to_time64(tm);
+
+		err = rtc->ops->set_mmss64(rtc->dev.parent, secs64);
+	} else if (rtc->ops->set_mmss) {
 		time64_t secs64 = rtc_tm_to_time64(tm);
 		err = rtc->ops->set_mmss(rtc->dev.parent, secs64);
 	} else
@@ -96,6 +100,8 @@ int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs)
 
 	if (!rtc->ops)
 		err = -ENODEV;
+	else if (rtc->ops->set_mmss64)
+		err = rtc->ops->set_mmss64(rtc->dev.parent, secs);
 	else if (rtc->ops->set_mmss)
 		err = rtc->ops->set_mmss(rtc->dev.parent, secs);
 	else if (rtc->ops->read_time && rtc->ops->set_time) {

drivers/rtc/rtc-ab3100.c

@@ -43,21 +43,21 @@
 /*
  * RTC clock functions and device struct declaration
  */
-static int ab3100_rtc_set_mmss(struct device *dev, unsigned long secs)
+static int ab3100_rtc_set_mmss(struct device *dev, time64_t secs)
 {
 	u8 regs[] = {AB3100_TI0, AB3100_TI1, AB3100_TI2,
 		     AB3100_TI3, AB3100_TI4, AB3100_TI5};
 	unsigned char buf[6];
-	u64 fat_time = (u64) secs * AB3100_RTC_CLOCK_RATE * 2;
+	u64 hw_counter = secs * AB3100_RTC_CLOCK_RATE * 2;
 	int err = 0;
 	int i;
 
-	buf[0] = (fat_time) & 0xFF;
-	buf[1] = (fat_time >> 8) & 0xFF;
-	buf[2] = (fat_time >> 16) & 0xFF;
-	buf[3] = (fat_time >> 24) & 0xFF;
-	buf[4] = (fat_time >> 32) & 0xFF;
-	buf[5] = (fat_time >> 40) & 0xFF;
+	buf[0] = (hw_counter) & 0xFF;
+	buf[1] = (hw_counter >> 8) & 0xFF;
+	buf[2] = (hw_counter >> 16) & 0xFF;
+	buf[3] = (hw_counter >> 24) & 0xFF;
+	buf[4] = (hw_counter >> 32) & 0xFF;
+	buf[5] = (hw_counter >> 40) & 0xFF;
 
 	for (i = 0; i < 6; i++) {
 		err = abx500_set_register_interruptible(dev, 0,
@@ -75,7 +75,7 @@ static int ab3100_rtc_set_mmss(struct device *dev, unsigned long secs)
 
 static int ab3100_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
-	unsigned long time;
+	time64_t time;
 	u8 rtcval;
 	int err;
 
@@ -88,7 +88,7 @@ static int ab3100_rtc_read_time(struct device *dev, struct rtc_time *tm)
 		dev_info(dev, "clock not set (lost power)");
 		return -EINVAL;
 	} else {
-		u64 fat_time;
+		u64 hw_counter;
 		u8 buf[6];
 
 		/* Read out time registers */
@@ -98,22 +98,21 @@ static int ab3100_rtc_read_time(struct device *dev, struct rtc_time *tm)
 		if (err != 0)
 			return err;
 
-		fat_time = ((u64) buf[5] << 40) | ((u64) buf[4] << 32) |
+		hw_counter = ((u64) buf[5] << 40) | ((u64) buf[4] << 32) |
 			((u64) buf[3] << 24) | ((u64) buf[2] << 16) |
 			((u64) buf[1] << 8) | (u64) buf[0];
-		time = (unsigned long) (fat_time /
-					(u64) (AB3100_RTC_CLOCK_RATE * 2));
+		time = hw_counter / (u64) (AB3100_RTC_CLOCK_RATE * 2);
 	}
 
-	rtc_time_to_tm(time, tm);
+	rtc_time64_to_tm(time, tm);
 
 	return rtc_valid_tm(tm);
 }
 
 static int ab3100_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
-	unsigned long time;
-	u64 fat_time;
+	time64_t time;
+	u64 hw_counter;
 	u8 buf[6];
 	u8 rtcval;
 	int err;
@@ -134,11 +133,11 @@ static int ab3100_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 						     AB3100_AL0, buf, 4);
 	if (err)
 		return err;
-	fat_time = ((u64) buf[3] << 40) | ((u64) buf[2] << 32) |
+	hw_counter = ((u64) buf[3] << 40) | ((u64) buf[2] << 32) |
 		((u64) buf[1] << 24) | ((u64) buf[0] << 16);
-	time = (unsigned long) (fat_time / (u64) (AB3100_RTC_CLOCK_RATE * 2));
+	time = hw_counter / (u64) (AB3100_RTC_CLOCK_RATE * 2);
 
-	rtc_time_to_tm(time, &alarm->time);
+	rtc_time64_to_tm(time, &alarm->time);
 
 	return rtc_valid_tm(&alarm->time);
 }
@@ -147,17 +146,17 @@ static int ab3100_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
 	u8 regs[] = {AB3100_AL0, AB3100_AL1, AB3100_AL2, AB3100_AL3};
 	unsigned char buf[4];
-	unsigned long secs;
-	u64 fat_time;
+	time64_t secs;
+	u64 hw_counter;
 	int err;
 	int i;
 
-	rtc_tm_to_time(&alarm->time, &secs);
-	fat_time = (u64) secs * AB3100_RTC_CLOCK_RATE * 2;
-	buf[0] = (fat_time >> 16) & 0xFF;
-	buf[1] = (fat_time >> 24) & 0xFF;
-	buf[2] = (fat_time >> 32) & 0xFF;
-	buf[3] = (fat_time >> 40) & 0xFF;
+	secs = rtc_tm_to_time64(&alarm->time);
+	hw_counter = secs * AB3100_RTC_CLOCK_RATE * 2;
+	buf[0] = (hw_counter >> 16) & 0xFF;
+	buf[1] = (hw_counter >> 24) & 0xFF;
+	buf[2] = (hw_counter >> 32) & 0xFF;
+	buf[3] = (hw_counter >> 40) & 0xFF;
 
 	/* Set the alarm */
 	for (i = 0; i < 4; i++) {
@@ -193,7 +192,7 @@ static int ab3100_rtc_irq_enable(struct device *dev, unsigned int enabled)
 
 static const struct rtc_class_ops ab3100_rtc_ops = {
 	.read_time	= ab3100_rtc_read_time,
-	.set_mmss	= ab3100_rtc_set_mmss,
+	.set_mmss64	= ab3100_rtc_set_mmss,
 	.read_alarm	= ab3100_rtc_read_alarm,
 	.set_alarm	= ab3100_rtc_set_alarm,
 	.alarm_irq_enable = ab3100_rtc_irq_enable,

drivers/rtc/rtc-mc13xxx.c

@@ -83,20 +83,19 @@ static int mc13xxx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 			return ret;
 	} while (days1 != days2);
 
-	rtc_time_to_tm(days1 * SEC_PER_DAY + seconds, tm);
+	rtc_time64_to_tm((time64_t)days1 * SEC_PER_DAY + seconds, tm);
 
 	return rtc_valid_tm(tm);
 }
 
-static int mc13xxx_rtc_set_mmss(struct device *dev, unsigned long secs)
+static int mc13xxx_rtc_set_mmss(struct device *dev, time64_t secs)
 {
 	struct mc13xxx_rtc *priv = dev_get_drvdata(dev);
 	unsigned int seconds, days;
 	unsigned int alarmseconds;
 	int ret;
 
-	seconds = secs % SEC_PER_DAY;
-	days = secs / SEC_PER_DAY;
+	days = div_s64_rem(secs, SEC_PER_DAY, &seconds);
 
 	mc13xxx_lock(priv->mc13xxx);
 
@@ -159,7 +158,7 @@ static int mc13xxx_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
 	struct mc13xxx_rtc *priv = dev_get_drvdata(dev);
 	unsigned seconds, days;
-	unsigned long s1970;
+	time64_t s1970;
 	int enabled, pending;
 	int ret;
 
@@ -189,10 +188,10 @@ out:
 	alarm->enabled = enabled;
 	alarm->pending = pending;
 
-	s1970 = days * SEC_PER_DAY + seconds;
+	s1970 = (time64_t)days * SEC_PER_DAY + seconds;
 
-	rtc_time_to_tm(s1970, &alarm->time);
-	dev_dbg(dev, "%s: %lu\n", __func__, s1970);
+	rtc_time64_to_tm(s1970, &alarm->time);
+	dev_dbg(dev, "%s: %lld\n", __func__, (long long)s1970);
 
 	return 0;
 }
@@ -200,8 +199,8 @@ out:
 static int mc13xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
 	struct mc13xxx_rtc *priv = dev_get_drvdata(dev);
-	unsigned long s1970;
-	unsigned seconds, days;
+	time64_t s1970;
+	u32 seconds, days;
 	int ret;
 
 	mc13xxx_lock(priv->mc13xxx);
@@ -215,20 +214,17 @@ static int mc13xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 	if (unlikely(ret))
 		goto out;
 
-	ret = rtc_tm_to_time(&alarm->time, &s1970);
-	if (unlikely(ret))
-		goto out;
+	s1970 = rtc_tm_to_time64(&alarm->time);
 
-	dev_dbg(dev, "%s: o%2.s %lu\n", __func__, alarm->enabled ? "n" : "ff",
-			s1970);
+	dev_dbg(dev, "%s: o%2.s %lld\n", __func__, alarm->enabled ? "n" : "ff",
+			(long long)s1970);
 
 	ret = mc13xxx_rtc_irq_enable_unlocked(dev, alarm->enabled,
 			MC13XXX_IRQ_TODA);
 	if (unlikely(ret))
 		goto out;
 
-	seconds = s1970 % SEC_PER_DAY;
-	days = s1970 / SEC_PER_DAY;
+	days = div_s64_rem(s1970, SEC_PER_DAY, &seconds);
 
 	ret = mc13xxx_reg_write(priv->mc13xxx, MC13XXX_RTCDAYA, days);
 	if (unlikely(ret))
@@ -268,7 +264,7 @@ static irqreturn_t mc13xxx_rtc_update_handler(int irq, void *dev)
 
 static const struct rtc_class_ops mc13xxx_rtc_ops = {
 	.read_time = mc13xxx_rtc_read_time,
-	.set_mmss = mc13xxx_rtc_set_mmss,
+	.set_mmss64 = mc13xxx_rtc_set_mmss,
 	.read_alarm = mc13xxx_rtc_read_alarm,
 	.set_alarm = mc13xxx_rtc_set_alarm,
 	.alarm_irq_enable = mc13xxx_rtc_alarm_irq_enable,

drivers/rtc/rtc-mxc.c

@@ -106,7 +106,7 @@ static inline int is_imx1_rtc(struct rtc_plat_data *data)
  * This function is used to obtain the RTC time or the alarm value in
  * second.
  */
-static u32 get_alarm_or_time(struct device *dev, int time_alarm)
+static time64_t get_alarm_or_time(struct device *dev, int time_alarm)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
@@ -129,29 +129,28 @@ static u32 get_alarm_or_time(struct device *dev, int time_alarm)
 	hr = hr_min >> 8;
 	min = hr_min & 0xff;
 
-	return (((day * 24 + hr) * 60) + min) * 60 + sec;
+	return ((((time64_t)day * 24 + hr) * 60) + min) * 60 + sec;
 }
 
 /*
  * This function sets the RTC alarm value or the time value.
  */
-static void set_alarm_or_time(struct device *dev, int time_alarm, u32 time)
+static void set_alarm_or_time(struct device *dev, int time_alarm, time64_t time)
 {
-	u32 day, hr, min, sec, temp;
+	u32 tod, day, hr, min, sec, temp;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
 	void __iomem *ioaddr = pdata->ioaddr;
 
-	day = time / 86400;
-	time -= day * 86400;
+	day = div_s64_rem(time, 86400, &tod);
 
 	/* time is within a day now */
-	hr = time / 3600;
-	time -= hr * 3600;
+	hr = tod / 3600;
+	tod -= hr * 3600;
 
 	/* time is within an hour now */
-	min = time / 60;
-	sec = time - min * 60;
+	min = tod / 60;
+	sec = tod - min * 60;
 
 	temp = (hr << 8) + min;
 
@@ -173,29 +172,18 @@ static void set_alarm_or_time(struct device *dev, int time_alarm, u32 time)
  * This function updates the RTC alarm registers and then clears all the
  * interrupt status bits.
  */
-static int rtc_update_alarm(struct device *dev, struct rtc_time *alrm)
+static void rtc_update_alarm(struct device *dev, struct rtc_time *alrm)
 {
-	struct rtc_time alarm_tm, now_tm;
-	unsigned long now, time;
+	time64_t time;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
 	void __iomem *ioaddr = pdata->ioaddr;
 
-	now = get_alarm_or_time(dev, MXC_RTC_TIME);
-	rtc_time_to_tm(now, &now_tm);
-	alarm_tm.tm_year = now_tm.tm_year;
-	alarm_tm.tm_mon = now_tm.tm_mon;
-	alarm_tm.tm_mday = now_tm.tm_mday;
-	alarm_tm.tm_hour = alrm->tm_hour;
-	alarm_tm.tm_min = alrm->tm_min;
-	alarm_tm.tm_sec = alrm->tm_sec;
-	rtc_tm_to_time(&alarm_tm, &time);
+	time = rtc_tm_to_time64(alrm);
 
 	/* clear all the interrupt status bits */
 	writew(readw(ioaddr + RTC_RTCISR), ioaddr + RTC_RTCISR);
 	set_alarm_or_time(dev, MXC_RTC_ALARM, time);
-
-	return 0;
 }
 
 static void mxc_rtc_irq_enable(struct device *dev, unsigned int bit,
@@ -283,14 +271,14 @@ static int mxc_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
  */
 static int mxc_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
-	u32 val;
+	time64_t val;
 
 	/* Avoid roll-over from reading the different registers */
 	do {
 		val = get_alarm_or_time(dev, MXC_RTC_TIME);
 	} while (val != get_alarm_or_time(dev, MXC_RTC_TIME));
 
-	rtc_time_to_tm(val, tm);
+	rtc_time64_to_tm(val, tm);
 
 	return 0;
 }
@@ -298,7 +286,7 @@ static int mxc_rtc_read_time(struct device *dev, struct rtc_time *tm)
 /*
  * This function sets the internal RTC time based on tm in Gregorian date.
  */
-static int mxc_rtc_set_mmss(struct device *dev, unsigned long time)
+static int mxc_rtc_set_mmss(struct device *dev, time64_t time)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
@@ -309,9 +297,9 @@ static int mxc_rtc_set_mmss(struct device *dev, unsigned long time)
 	if (is_imx1_rtc(pdata)) {
 		struct rtc_time tm;
 
-		rtc_time_to_tm(time, &tm);
+		rtc_time64_to_tm(time, &tm);
 		tm.tm_year = 70;
-		rtc_tm_to_time(&tm, &time);
+		time = rtc_tm_to_time64(&tm);
 	}
 
 	/* Avoid roll-over from reading the different registers */
@@ -333,7 +321,7 @@ static int mxc_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
 	void __iomem *ioaddr = pdata->ioaddr;
 
-	rtc_time_to_tm(get_alarm_or_time(dev, MXC_RTC_ALARM), &alrm->time);
+	rtc_time64_to_tm(get_alarm_or_time(dev, MXC_RTC_ALARM), &alrm->time);
 	alrm->pending = ((readw(ioaddr + RTC_RTCISR) & RTC_ALM_BIT)) ? 1 : 0;
 
 	return 0;
@@ -346,11 +334,8 @@ static int mxc_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
-	int ret;
 
-	ret = rtc_update_alarm(dev, &alrm->time);
-	if (ret)
-		return ret;
+	rtc_update_alarm(dev, &alrm->time);
 
 	memcpy(&pdata->g_rtc_alarm, &alrm->time, sizeof(struct rtc_time));
 	mxc_rtc_irq_enable(dev, RTC_ALM_BIT, alrm->enabled);
@@ -362,7 +347,7 @@ static int mxc_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 static struct rtc_class_ops mxc_rtc_ops = {
 	.release		= mxc_rtc_release,
 	.read_time		= mxc_rtc_read_time,
-	.set_mmss		= mxc_rtc_set_mmss,
+	.set_mmss64		= mxc_rtc_set_mmss,
 	.read_alarm		= mxc_rtc_read_alarm,
 	.set_alarm		= mxc_rtc_set_alarm,
 	.alarm_irq_enable	= mxc_rtc_alarm_irq_enable,

drivers/rtc/rtc-test.c

@@ -13,6 +13,10 @@
 #include <linux/rtc.h>
 #include <linux/platform_device.h>
 
+static int test_mmss64;
+module_param(test_mmss64, int, 0644);
+MODULE_PARM_DESC(test_mmss64, "Test struct rtc_class_ops.set_mmss64().");
+
 static struct platform_device *test0 = NULL, *test1 = NULL;
 
 static int test_rtc_read_alarm(struct device *dev,
@@ -30,7 +34,13 @@ static int test_rtc_set_alarm(struct device *dev,
 static int test_rtc_read_time(struct device *dev,
 	struct rtc_time *tm)
 {
-	rtc_time_to_tm(get_seconds(), tm);
+	rtc_time64_to_tm(ktime_get_real_seconds(), tm);
+	return 0;
+}
+
+static int test_rtc_set_mmss64(struct device *dev, time64_t secs)
+{
+	dev_info(dev, "%s, secs = %lld\n", __func__, (long long)secs);
 	return 0;
 }
 
@@ -55,7 +65,7 @@ static int test_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 	return 0;
 }
 
-static const struct rtc_class_ops test_rtc_ops = {
+static struct rtc_class_ops test_rtc_ops = {
 	.proc = test_rtc_proc,
 	.read_time = test_rtc_read_time,
 	.read_alarm = test_rtc_read_alarm,
@@ -101,6 +111,11 @@ static int test_probe(struct platform_device *plat_dev)
 	int err;
 	struct rtc_device *rtc;
 
+	if (test_mmss64) {
+		test_rtc_ops.set_mmss64 = test_rtc_set_mmss64;
+		test_rtc_ops.set_mmss = NULL;
+	}
+
 	rtc = devm_rtc_device_register(&plat_dev->dev, "test",
 				&test_rtc_ops, THIS_MODULE);
 	if (IS_ERR(rtc)) {

drivers/rtc/systohc.c

@@ -11,7 +11,7 @@
  * rtc_set_ntp_time - Save NTP synchronized time to the RTC
  * @now: Current time of day
  *
- * Replacement for the NTP platform function update_persistent_clock
+ * Replacement for the NTP platform function update_persistent_clock64
  * that stores time for later retrieval by rtc_hctosys.
  *
  * Returns 0 on successful RTC update, -ENODEV if a RTC update is not
@@ -35,7 +35,10 @@ int rtc_set_ntp_time(struct timespec64 now)
 	if (rtc) {
 		/* rtc_hctosys exclusively uses UTC, so we call set_time here,
 		 * not set_mmss. */
-		if (rtc->ops && (rtc->ops->set_time || rtc->ops->set_mmss))
+		if (rtc->ops &&
+		    (rtc->ops->set_time ||
+		     rtc->ops->set_mmss64 ||
+		     rtc->ops->set_mmss))
 			err = rtc_set_time(rtc, &tm);
 		rtc_class_close(rtc);
 	}

include/linux/clockchips.h

@@ -8,64 +8,69 @@
 #ifndef _LINUX_CLOCKCHIPS_H
 #define _LINUX_CLOCKCHIPS_H
 
-/* Clock event notification values */
-enum clock_event_nofitiers {
-	CLOCK_EVT_NOTIFY_ADD,
-	CLOCK_EVT_NOTIFY_BROADCAST_ON,
-	CLOCK_EVT_NOTIFY_BROADCAST_OFF,
-	CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
-	CLOCK_EVT_NOTIFY_BROADCAST_ENTER,
-	CLOCK_EVT_NOTIFY_BROADCAST_EXIT,
-	CLOCK_EVT_NOTIFY_SUSPEND,
-	CLOCK_EVT_NOTIFY_RESUME,
-	CLOCK_EVT_NOTIFY_CPU_DYING,
-	CLOCK_EVT_NOTIFY_CPU_DEAD,
-};
-
-#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
 
-#include <linux/clocksource.h>
-#include <linux/cpumask.h>
-#include <linux/ktime.h>
-#include <linux/notifier.h>
+# include <linux/clocksource.h>
+# include <linux/cpumask.h>
+# include <linux/ktime.h>
+# include <linux/notifier.h>
 
 struct clock_event_device;
 struct module;
 
-/* Clock event mode commands */
+/* Clock event mode commands for legacy ->set_mode(): OBSOLETE */
 enum clock_event_mode {
-	CLOCK_EVT_MODE_UNUSED = 0,
+	CLOCK_EVT_MODE_UNUSED,
 	CLOCK_EVT_MODE_SHUTDOWN,
 	CLOCK_EVT_MODE_PERIODIC,
 	CLOCK_EVT_MODE_ONESHOT,
 	CLOCK_EVT_MODE_RESUME,
 };
 
+/*
+ * Possible states of a clock event device.
+ *
+ * DETACHED:	Device is not used by clockevents core. Initial state or can be
+ *		reached from SHUTDOWN.
+ * SHUTDOWN:	Device is powered-off. Can be reached from PERIODIC or ONESHOT.
+ * PERIODIC:	Device is programmed to generate events periodically. Can be
+ *		reached from DETACHED or SHUTDOWN.
+ * ONESHOT:	Device is programmed to generate event only once. Can be reached
+ *		from DETACHED or SHUTDOWN.
+ */
+enum clock_event_state {
+	CLOCK_EVT_STATE_DETACHED,
+	CLOCK_EVT_STATE_SHUTDOWN,
+	CLOCK_EVT_STATE_PERIODIC,
+	CLOCK_EVT_STATE_ONESHOT,
+};
+
 /*
  * Clock event features
  */
-#define CLOCK_EVT_FEAT_PERIODIC		0x000001
-#define CLOCK_EVT_FEAT_ONESHOT		0x000002
-#define CLOCK_EVT_FEAT_KTIME		0x000004
+# define CLOCK_EVT_FEAT_PERIODIC	0x000001
+# define CLOCK_EVT_FEAT_ONESHOT		0x000002
+# define CLOCK_EVT_FEAT_KTIME		0x000004
+
 /*
- * x86(64) specific misfeatures:
+ * x86(64) specific (mis)features:
  *
  * - Clockevent source stops in C3 State and needs broadcast support.
  * - Local APIC timer is used as a dummy device.
  */
-#define CLOCK_EVT_FEAT_C3STOP		0x000008
-#define CLOCK_EVT_FEAT_DUMMY		0x000010
+# define CLOCK_EVT_FEAT_C3STOP		0x000008
+# define CLOCK_EVT_FEAT_DUMMY		0x000010
 
 /*
  * Core shall set the interrupt affinity dynamically in broadcast mode
  */
-#define CLOCK_EVT_FEAT_DYNIRQ		0x000020
-#define CLOCK_EVT_FEAT_PERCPU		0x000040
+# define CLOCK_EVT_FEAT_DYNIRQ		0x000020
+# define CLOCK_EVT_FEAT_PERCPU		0x000040
 
 /*
  * Clockevent device is based on a hrtimer for broadcast
  */
-#define CLOCK_EVT_FEAT_HRTIMER		0x000080
+# define CLOCK_EVT_FEAT_HRTIMER		0x000080
 
 /**
  * struct clock_event_device - clock event device descriptor
@@ -78,10 +83,15 @@ enum clock_event_mode {
  * @min_delta_ns:	minimum delta value in ns
  * @mult:		nanosecond to cycles multiplier
  * @shift:		nanoseconds to cycles divisor (power of two)
- * @mode:		operating mode assigned by the management code
+ * @mode:		operating mode, relevant only to ->set_mode(), OBSOLETE
+ * @state:		current state of the device, assigned by the core 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_state_periodic:	switch state to periodic, if !set_mode
+ * @set_state_oneshot:	switch state to oneshot, if !set_mode
+ * @set_state_shutdown:	switch state to shutdown, if !set_mode
+ * @tick_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
@@ -95,22 +105,31 @@ enum clock_event_mode {
  */
 struct clock_event_device {
 	void			(*event_handler)(struct clock_event_device *);
-	int			(*set_next_event)(unsigned long evt,
-						  struct clock_event_device *);
-	int			(*set_next_ktime)(ktime_t expires,
-						  struct clock_event_device *);
+	int			(*set_next_event)(unsigned long evt, struct clock_event_device *);
+	int			(*set_next_ktime)(ktime_t expires, struct clock_event_device *);
 	ktime_t			next_event;
 	u64			max_delta_ns;
 	u64			min_delta_ns;
 	u32			mult;
 	u32			shift;
 	enum clock_event_mode	mode;
+	enum clock_event_state	state;
 	unsigned int		features;
 	unsigned long		retries;
 
+	/*
+	 * State transition callback(s): Only one of the two groups should be
+	 * defined:
+	 * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME.
+	 * - set_state_{shutdown|periodic|oneshot}(), tick_resume().
+	 */
+	void			(*set_mode)(enum clock_event_mode mode, struct clock_event_device *);
+	int			(*set_state_periodic)(struct clock_event_device *);
+	int			(*set_state_oneshot)(struct clock_event_device *);
+	int			(*set_state_shutdown)(struct clock_event_device *);
+	int			(*tick_resume)(struct clock_event_device *);
+
 	void			(*broadcast)(const struct cpumask *mask);
-	void			(*set_mode)(enum clock_event_mode mode,
-					    struct clock_event_device *);
 	void			(*suspend)(struct clock_event_device *);
 	void			(*resume)(struct clock_event_device *);
 	unsigned long		min_delta_ticks;
@@ -136,18 +155,18 @@ struct clock_event_device {
  *
  * factor = (clock_ticks << shift) / nanoseconds
  */
-static inline unsigned long div_sc(unsigned long ticks, unsigned long nsec,
-				   int shift)
+static inline unsigned long
+div_sc(unsigned long ticks, unsigned long nsec, int shift)
 {
-	uint64_t tmp = ((uint64_t)ticks) << shift;
+	u64 tmp = ((u64)ticks) << shift;
 
 	do_div(tmp, nsec);
+
 	return (unsigned long) tmp;
 }
 
 /* Clock event layer functions */
-extern u64 clockevent_delta2ns(unsigned long latch,
-			       struct clock_event_device *evt);
+extern u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt);
 extern void clockevents_register_device(struct clock_event_device *dev);
 extern int clockevents_unbind_device(struct clock_event_device *ced, int cpu);
 
@@ -158,57 +177,42 @@ extern void clockevents_config_and_register(struct clock_event_device *dev,
 
 extern int clockevents_update_freq(struct clock_event_device *ce, u32 freq);
 
-extern void clockevents_exchange_device(struct clock_event_device *old,
-					struct clock_event_device *new);
-extern void clockevents_set_mode(struct clock_event_device *dev,
-				 enum clock_event_mode mode);
-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);
-
 static inline void
 clockevents_calc_mult_shift(struct clock_event_device *ce, u32 freq, u32 minsec)
 {
-	return clocks_calc_mult_shift(&ce->mult, &ce->shift, NSEC_PER_SEC,
-				      freq, minsec);
+	return clocks_calc_mult_shift(&ce->mult, &ce->shift, NSEC_PER_SEC, freq, minsec);
 }
 
 extern void clockevents_suspend(void);
 extern void clockevents_resume(void);
 
-#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
-#ifdef CONFIG_ARCH_HAS_TICK_BROADCAST
+# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+#  ifdef CONFIG_ARCH_HAS_TICK_BROADCAST
 extern void tick_broadcast(const struct cpumask *mask);
-#else
-#define tick_broadcast	NULL
-#endif
+#  else
+#   define tick_broadcast	NULL
+#  endif
 extern int tick_receive_broadcast(void);
-#endif
+# endif
 
-#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
+# if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
 extern void tick_setup_hrtimer_broadcast(void);
 extern int tick_check_broadcast_expired(void);
-#else
+# else
 static inline int tick_check_broadcast_expired(void) { return 0; }
-static inline void tick_setup_hrtimer_broadcast(void) {};
-#endif
+static inline void tick_setup_hrtimer_broadcast(void) { }
+# endif
 
-#ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern int clockevents_notify(unsigned long reason, void *arg);
-#else
-static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; }
-#endif
-
-#else /* CONFIG_GENERIC_CLOCKEVENTS_BUILD */
 
-static inline void clockevents_suspend(void) {}
-static inline void clockevents_resume(void) {}
+#else /* !CONFIG_GENERIC_CLOCKEVENTS: */
 
+static inline void clockevents_suspend(void) { }
+static inline void clockevents_resume(void) { }
 static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; }
 static inline int tick_check_broadcast_expired(void) { return 0; }
-static inline void tick_setup_hrtimer_broadcast(void) {};
+static inline void tick_setup_hrtimer_broadcast(void) { }
 
-#endif
+#endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
-#endif
+#endif /* _LINUX_CLOCKCHIPS_H */

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/rtc.h

@@ -77,6 +77,7 @@ struct rtc_class_ops {
 	int (*read_alarm)(struct device *, struct rtc_wkalrm *);
 	int (*set_alarm)(struct device *, struct rtc_wkalrm *);
 	int (*proc)(struct device *, struct seq_file *);
+	int (*set_mmss64)(struct device *, time64_t secs);
 	int (*set_mmss)(struct device *, unsigned long secs);
 	int (*read_callback)(struct device *, int data);
 	int (*alarm_irq_enable)(struct device *, unsigned int enabled);

include/linux/tick.h

@@ -1,7 +1,5 @@
-/*  linux/include/linux/tick.h
- *
- *  This file contains the structure definitions for tick related functions
- *
+/*
+ * Tick related global functions
  */
 #ifndef _LINUX_TICK_H
 #define _LINUX_TICK_H
@@ -9,149 +7,99 @@
 #include <linux/clockchips.h>
 #include <linux/irqflags.h>
 #include <linux/percpu.h>
-#include <linux/hrtimer.h>
 #include <linux/context_tracking_state.h>
 #include <linux/cpumask.h>
 #include <linux/sched.h>
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
-
-enum tick_device_mode {
-	TICKDEV_MODE_PERIODIC,
-	TICKDEV_MODE_ONESHOT,
-};
-
-struct tick_device {
-	struct clock_event_device *evtdev;
-	enum tick_device_mode mode;
-};
-
-enum tick_nohz_mode {
-	NOHZ_MODE_INACTIVE,
-	NOHZ_MODE_LOWRES,
-	NOHZ_MODE_HIGHRES,
-};
-
-/**
- * struct tick_sched - sched tick emulation and no idle tick control/stats
- * @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.
- * @tick_stopped:	Indicator that the idle tick has been stopped
- * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
- * @idle_calls:		Total number of idle calls
- * @idle_sleeps:	Number of idle calls, where the sched tick was stopped
- * @idle_entrytime:	Time when the idle call was entered
- * @idle_waketime:	Time when the idle was interrupted
- * @idle_exittime:	Time when the idle state was left
- * @idle_sleeptime:	Sum of the time slept in idle with sched tick stopped
- * @iowait_sleeptime:	Sum of the time slept in idle with sched tick stopped, with IO outstanding
- * @sleep_length:	Duration of the current idle sleep
- * @do_timer_lst:	CPU was the last one doing do_timer before going idle
- */
-struct tick_sched {
-	struct hrtimer			sched_timer;
-	unsigned long			check_clocks;
-	enum tick_nohz_mode		nohz_mode;
-	ktime_t				last_tick;
-	int				inidle;
-	int				tick_stopped;
-	unsigned long			idle_jiffies;
-	unsigned long			idle_calls;
-	unsigned long			idle_sleeps;
-	int				idle_active;
-	ktime_t				idle_entrytime;
-	ktime_t				idle_waketime;
-	ktime_t				idle_exittime;
-	ktime_t				idle_sleeptime;
-	ktime_t				iowait_sleeptime;
-	ktime_t				sleep_length;
-	unsigned long			last_jiffies;
-	unsigned long			next_jiffies;
-	ktime_t				idle_expires;
-	int				do_timer_last;
-};
-
 extern void __init tick_init(void);
-extern int tick_is_oneshot_available(void);
-extern struct tick_device *tick_get_device(int cpu);
-
 extern void tick_freeze(void);
 extern void tick_unfreeze(void);
+/* Should be core only, but ARM BL switcher requires it */
+extern void tick_suspend_local(void);
+/* Should be core only, but XEN resume magic and ARM BL switcher require it */
+extern void tick_resume_local(void);
+extern void tick_handover_do_timer(void);
+extern void tick_cleanup_dead_cpu(int cpu);
+#else /* CONFIG_GENERIC_CLOCKEVENTS */
+static inline void tick_init(void) { }
+static inline void tick_freeze(void) { }
+static inline void tick_unfreeze(void) { }
+static inline void tick_suspend_local(void) { }
+static inline void tick_resume_local(void) { }
+static inline void tick_handover_do_timer(void) { }
+static inline void tick_cleanup_dead_cpu(int cpu) { }
+#endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
-# ifdef CONFIG_HIGH_RES_TIMERS
-extern int tick_init_highres(void);
-extern int tick_program_event(ktime_t expires, int force);
-extern void tick_setup_sched_timer(void);
-# endif
-
-# if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
-extern void tick_cancel_sched_timer(int cpu);
-# else
-static inline void tick_cancel_sched_timer(int cpu) { }
-# endif
-
-# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
-extern struct tick_device *tick_get_broadcast_device(void);
-extern struct cpumask *tick_get_broadcast_mask(void);
-
-#  ifdef CONFIG_TICK_ONESHOT
-extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
-#  endif
-
-# endif /* BROADCAST */
-
-# ifdef CONFIG_TICK_ONESHOT
-extern void tick_clock_notify(void);
-extern int tick_check_oneshot_change(int allow_nohz);
-extern struct tick_sched *tick_get_tick_sched(int cpu);
+#ifdef CONFIG_TICK_ONESHOT
 extern void tick_irq_enter(void);
-extern int tick_oneshot_mode_active(void);
 #  ifndef arch_needs_cpu
 #   define arch_needs_cpu() (0)
 #  endif
 # else
-static inline void tick_clock_notify(void) { }
-static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
 static inline void tick_irq_enter(void) { }
-static inline int tick_oneshot_mode_active(void) { return 0; }
-# endif
+#endif
 
-#else /* CONFIG_GENERIC_CLOCKEVENTS */
-static inline void tick_init(void) { }
-static inline void tick_freeze(void) { }
-static inline void tick_unfreeze(void) { }
-static inline void tick_cancel_sched_timer(int cpu) { }
-static inline void tick_clock_notify(void) { }
-static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
-static inline void tick_irq_enter(void) { }
-static inline int tick_oneshot_mode_active(void) { return 0; }
-#endif /* !CONFIG_GENERIC_CLOCKEVENTS */
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
+extern void hotplug_cpu__broadcast_tick_pull(int dead_cpu);
+#else
+static inline void hotplug_cpu__broadcast_tick_pull(int dead_cpu) { }
+#endif
 
-# ifdef CONFIG_NO_HZ_COMMON
-DECLARE_PER_CPU(struct tick_sched, tick_cpu_sched);
+enum tick_broadcast_mode {
+	TICK_BROADCAST_OFF,
+	TICK_BROADCAST_ON,
+	TICK_BROADCAST_FORCE,
+};
+
+enum tick_broadcast_state {
+	TICK_BROADCAST_EXIT,
+	TICK_BROADCAST_ENTER,
+};
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern void tick_broadcast_control(enum tick_broadcast_mode mode);
+#else
+static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { }
+#endif /* BROADCAST */
+
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
+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 0; }
+#endif
 
-static inline int tick_nohz_tick_stopped(void)
+static inline void tick_broadcast_enable(void)
+{
+	tick_broadcast_control(TICK_BROADCAST_ON);
+}
+static inline void tick_broadcast_disable(void)
+{
+	tick_broadcast_control(TICK_BROADCAST_OFF);
+}
+static inline void tick_broadcast_force(void)
+{
+	tick_broadcast_control(TICK_BROADCAST_FORCE);
+}
+static inline int tick_broadcast_enter(void)
 {
-	return __this_cpu_read(tick_cpu_sched.tick_stopped);
+	return tick_broadcast_oneshot_control(TICK_BROADCAST_ENTER);
+}
+static inline void tick_broadcast_exit(void)
+{
+	tick_broadcast_oneshot_control(TICK_BROADCAST_EXIT);
 }
 
+#ifdef CONFIG_NO_HZ_COMMON
+extern int tick_nohz_tick_stopped(void);
 extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
 extern void tick_nohz_irq_exit(void);
 extern ktime_t tick_nohz_get_sleep_length(void);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
 extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
-
-# else /* !CONFIG_NO_HZ_COMMON */
-static inline int tick_nohz_tick_stopped(void)
-{
-	return 0;
-}
-
+#else /* !CONFIG_NO_HZ_COMMON */
+static inline int tick_nohz_tick_stopped(void) { return 0; }
 static inline void tick_nohz_idle_enter(void) { }
 static inline void tick_nohz_idle_exit(void) { }
 
@@ -163,7 +111,7 @@ static inline ktime_t tick_nohz_get_sleep_length(void)
 }
 static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
 static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
-# endif /* !CONFIG_NO_HZ_COMMON */
+#endif /* !CONFIG_NO_HZ_COMMON */
 
 #ifdef CONFIG_NO_HZ_FULL
 extern bool tick_nohz_full_running;

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
@@ -242,6 +248,9 @@ static inline void timekeeping_clocktai(struct timespec *ts)
 /*
  * RTC specific
  */
+extern bool timekeeping_rtc_skipsuspend(void);
+extern bool timekeeping_rtc_skipresume(void);
+
 extern void timekeeping_inject_sleeptime64(struct timespec64 *delta);
 
 /*
@@ -253,17 +262,14 @@ extern void getnstime_raw_and_real(struct timespec *ts_raw,
 /*
  * Persistent clock related interfaces
  */
-extern bool persistent_clock_exist;
 extern int persistent_clock_is_local;
 
-static inline bool has_persistent_clock(void)
-{
-	return persistent_clock_exist;
-}
-
 extern void read_persistent_clock(struct timespec *ts);
+extern void read_persistent_clock64(struct timespec64 *ts);
 extern void read_boot_clock(struct timespec *ts);
+extern void read_boot_clock64(struct timespec64 *ts);
 extern int update_persistent_clock(struct timespec now);
+extern int update_persistent_clock64(struct timespec64 now);
 
 
 #endif

kernel/cpu.c

@@ -20,6 +20,7 @@
 #include <linux/gfp.h>
 #include <linux/suspend.h>
 #include <linux/lockdep.h>
+#include <linux/tick.h>
 #include <trace/events/power.h>
 
 #include "smpboot.h"
@@ -338,6 +339,8 @@ static int __ref take_cpu_down(void *_param)
 		return err;
 
 	cpu_notify(CPU_DYING | param->mod, param->hcpu);
+	/* Give up timekeeping duties */
+	tick_handover_do_timer();
 	/* Park the stopper thread */
 	kthread_park(current);
 	return 0;
@@ -411,10 +414,12 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	while (!idle_cpu(cpu))
 		cpu_relax();
 
+	hotplug_cpu__broadcast_tick_pull(cpu);
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);
 
 	/* CPU is completely dead: tell everyone.  Too late to complain. */
+	tick_cleanup_dead_cpu(cpu);
 	cpu_notify_nofail(CPU_DEAD | mod, hcpu);
 
 	check_for_tasks(cpu);

kernel/sched/idle.c

@@ -158,8 +158,7 @@ static void cpuidle_idle_call(void)
 	 * is used from another cpu as a broadcast timer, this call may
 	 * fail if it is not available
 	 */
-	if (broadcast &&
-	    clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
+	if (broadcast && tick_broadcast_enter())
 		goto use_default;
 
 	/* Take note of the planned idle state. */
@@ -176,7 +175,7 @@ static void cpuidle_idle_call(void)
 	idle_set_state(this_rq(), NULL);
 
 	if (broadcast)
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+		tick_broadcast_exit();
 
 	/*
 	 * Give the governor an opportunity to reflect on the outcome

kernel/time/Kconfig

@@ -33,12 +33,6 @@ config ARCH_USES_GETTIMEOFFSET
 config GENERIC_CLOCKEVENTS
 	bool
 
-# Migration helper. Builds, but does not invoke
-config GENERIC_CLOCKEVENTS_BUILD
-	bool
-	default y
-	depends on GENERIC_CLOCKEVENTS
-
 # Architecture can handle broadcast in a driver-agnostic way
 config ARCH_HAS_TICK_BROADCAST
 	bool

kernel/time/Makefile

@@ -2,15 +2,13 @@ obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o
 obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
 obj-y += timeconv.o timecounter.o posix-clock.o alarmtimer.o
 
-obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
-obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
+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-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o
-obj-$(CONFIG_TICK_ONESHOT)			+= tick-sched.o
+obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o tick-sched.o
 obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o

kernel/time/clockevents.c

@@ -94,25 +94,76 @@ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
 }
 EXPORT_SYMBOL_GPL(clockevent_delta2ns);
 
+static int __clockevents_set_state(struct clock_event_device *dev,
+				   enum clock_event_state state)
+{
+	/* Transition with legacy set_mode() callback */
+	if (dev->set_mode) {
+		/* Legacy callback doesn't support new modes */
+		if (state > CLOCK_EVT_STATE_ONESHOT)
+			return -ENOSYS;
+		/*
+		 * 'clock_event_state' and 'clock_event_mode' have 1-to-1
+		 * mapping until *_ONESHOT, and so a simple cast will work.
+		 */
+		dev->set_mode((enum clock_event_mode)state, dev);
+		dev->mode = (enum clock_event_mode)state;
+		return 0;
+	}
+
+	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
+		return 0;
+
+	/* Transition with new state-specific callbacks */
+	switch (state) {
+	case CLOCK_EVT_STATE_DETACHED:
+		/*
+		 * This is an internal state, which is guaranteed to go from
+		 * SHUTDOWN to DETACHED. No driver interaction required.
+		 */
+		return 0;
+
+	case CLOCK_EVT_STATE_SHUTDOWN:
+		return dev->set_state_shutdown(dev);
+
+	case CLOCK_EVT_STATE_PERIODIC:
+		/* Core internal bug */
+		if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC))
+			return -ENOSYS;
+		return dev->set_state_periodic(dev);
+
+	case CLOCK_EVT_STATE_ONESHOT:
+		/* Core internal bug */
+		if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+			return -ENOSYS;
+		return dev->set_state_oneshot(dev);
+
+	default:
+		return -ENOSYS;
+	}
+}
+
 /**
- * clockevents_set_mode - set the operating mode of a clock event device
+ * clockevents_set_state - set the operating state of a clock event device
  * @dev:	device to modify
- * @mode:	new mode
+ * @state:	new state
  *
  * Must be called with interrupts disabled !
  */
-void clockevents_set_mode(struct clock_event_device *dev,
-				 enum clock_event_mode mode)
+void clockevents_set_state(struct clock_event_device *dev,
+			   enum clock_event_state state)
 {
-	if (dev->mode != mode) {
-		dev->set_mode(mode, dev);
-		dev->mode = mode;
+	if (dev->state != state) {
+		if (__clockevents_set_state(dev, state))
+			return;
+
+		dev->state = state;
 
 		/*
 		 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
 		 * on it, so fix it up and emit a warning:
 		 */
-		if (mode == CLOCK_EVT_MODE_ONESHOT) {
+		if (state == CLOCK_EVT_STATE_ONESHOT) {
 			if (unlikely(!dev->mult)) {
 				dev->mult = 1;
 				WARN_ON(1);
@@ -127,10 +178,28 @@ void clockevents_set_mode(struct clock_event_device *dev,
  */
 void clockevents_shutdown(struct clock_event_device *dev)
 {
-	clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+	clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 	dev->next_event.tv64 = KTIME_MAX;
 }
 
+/**
+ * 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->set_mode) {
+		dev->set_mode(CLOCK_EVT_MODE_RESUME, dev);
+		dev->mode = CLOCK_EVT_MODE_RESUME;
+	} else if (dev->tick_resume) {
+		ret = dev->tick_resume(dev);
+	}
+
+	return ret;
+}
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST
 
 /* Limit min_delta to a jiffie */
@@ -183,7 +252,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 		delta = dev->min_delta_ns;
 		dev->next_event = ktime_add_ns(ktime_get(), delta);
 
-		if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
+		if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
 			return 0;
 
 		dev->retries++;
@@ -220,7 +289,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 	delta = dev->min_delta_ns;
 	dev->next_event = ktime_add_ns(ktime_get(), delta);
 
-	if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
+	if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
 		return 0;
 
 	dev->retries++;
@@ -252,7 +321,7 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 
 	dev->next_event = expires;
 
-	if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN)
+	if (dev->state == CLOCK_EVT_STATE_SHUTDOWN)
 		return 0;
 
 	/* Shortcut for clockevent devices that can deal with ktime. */
@@ -297,7 +366,7 @@ 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 || dev->mode != CLOCK_EVT_MODE_UNUSED)
+		if (dev == ced || dev->state != CLOCK_EVT_STATE_DETACHED)
 			continue;
 
 		if (!tick_check_replacement(newdev, dev))
@@ -323,7 +392,7 @@ static int clockevents_replace(struct clock_event_device *ced)
 static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu)
 {
 	/* Fast track. Device is unused */
-	if (ced->mode == CLOCK_EVT_MODE_UNUSED) {
+	if (ced->state == CLOCK_EVT_STATE_DETACHED) {
 		list_del_init(&ced->list);
 		return 0;
 	}
@@ -373,6 +442,37 @@ int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
 }
 EXPORT_SYMBOL_GPL(clockevents_unbind);
 
+/* Sanity check of state 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_state_periodic || dev->set_state_oneshot ||
+			dev->set_state_shutdown || dev->tick_resume);
+
+		BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
+		return 0;
+	}
+
+	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
+		return 0;
+
+	/* New state-specific callbacks */
+	if (!dev->set_state_shutdown)
+		return -EINVAL;
+
+	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
+	    !dev->set_state_periodic)
+		return -EINVAL;
+
+	if ((dev->features & CLOCK_EVT_FEAT_ONESHOT) &&
+	    !dev->set_state_oneshot)
+		return -EINVAL;
+
+	return 0;
+}
+
 /**
  * clockevents_register_device - register a clock event device
  * @dev:	device to register
@@ -381,7 +481,11 @@ 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));
+
+	/* Initialize state to DETACHED */
+	dev->state = CLOCK_EVT_STATE_DETACHED;
+
 	if (!dev->cpumask) {
 		WARN_ON(num_possible_cpus() > 1);
 		dev->cpumask = cpumask_of(smp_processor_id());
@@ -445,11 +549,11 @@ int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
 {
 	clockevents_config(dev, freq);
 
-	if (dev->mode == CLOCK_EVT_MODE_ONESHOT)
+	if (dev->state == CLOCK_EVT_STATE_ONESHOT)
 		return clockevents_program_event(dev, dev->next_event, false);
 
-	if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
-		dev->set_mode(CLOCK_EVT_MODE_PERIODIC, dev);
+	if (dev->state == CLOCK_EVT_STATE_PERIODIC)
+		return __clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
 
 	return 0;
 }
@@ -491,30 +595,27 @@ void clockevents_handle_noop(struct clock_event_device *dev)
  * @old:	device to release (can be NULL)
  * @new:	device to request (can be NULL)
  *
- * Called from the notifier chain. clockevents_lock is held already
+ * 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)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
 	/*
 	 * 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_set_mode(old, CLOCK_EVT_MODE_UNUSED);
+		clockevents_set_state(old, CLOCK_EVT_STATE_DETACHED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
 	}
 
 	if (new) {
-		BUG_ON(new->mode != CLOCK_EVT_MODE_UNUSED);
+		BUG_ON(new->state != CLOCK_EVT_STATE_DETACHED);
 		clockevents_shutdown(new);
 	}
-	local_irq_restore(flags);
 }
 
 /**
@@ -541,74 +642,40 @@ void clockevents_resume(void)
 			dev->resume(dev);
 }
 
-#ifdef CONFIG_GENERIC_CLOCKEVENTS
+#ifdef CONFIG_HOTPLUG_CPU
 /**
- * clockevents_notify - notification about relevant events
- * Returns 0 on success, any other value on error
+ * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu
  */
-int clockevents_notify(unsigned long reason, void *arg)
+void tick_cleanup_dead_cpu(int cpu)
 {
 	struct clock_event_device *dev, *tmp;
 	unsigned long flags;
-	int cpu, ret = 0;
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
-	switch (reason) {
-	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
-	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
-	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
-		tick_broadcast_on_off(reason, arg);
-		break;
-
-	case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
-	case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
-		ret = tick_broadcast_oneshot_control(reason);
-		break;
-
-	case CLOCK_EVT_NOTIFY_CPU_DYING:
-		tick_handover_do_timer(arg);
-		break;
-
-	case CLOCK_EVT_NOTIFY_SUSPEND:
-		tick_suspend();
-		tick_suspend_broadcast();
-		break;
-
-	case CLOCK_EVT_NOTIFY_RESUME:
-		tick_resume();
-		break;
-
-	case CLOCK_EVT_NOTIFY_CPU_DEAD:
-		tick_shutdown_broadcast_oneshot(arg);
-		tick_shutdown_broadcast(arg);
-		tick_shutdown(arg);
-		/*
-		 * Unregister the clock event devices which were
-		 * released from the users in the notify chain.
-		 */
-		list_for_each_entry_safe(dev, tmp, &clockevents_released, list)
+	tick_shutdown_broadcast_oneshot(cpu);
+	tick_shutdown_broadcast(cpu);
+	tick_shutdown(cpu);
+	/*
+	 * Unregister the clock event devices which were
+	 * released from the users in the notify chain.
+	 */
+	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(dev->state != CLOCK_EVT_STATE_DETACHED);
 			list_del(&dev->list);
-		/*
-		 * Now check whether the CPU has left unused per cpu devices
-		 */
-		cpu = *((int *)arg);
-		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(dev->mode != CLOCK_EVT_MODE_UNUSED);
-				list_del(&dev->list);
-			}
 		}
-		break;
-	default:
-		break;
 	}
 	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
-	return ret;
 }
-EXPORT_SYMBOL_GPL(clockevents_notify);
+#endif
 
 #ifdef CONFIG_SYSFS
 struct bus_type clockevents_subsys = {
@@ -727,5 +794,3 @@ static int __init clockevents_init_sysfs(void)
 }
 device_initcall(clockevents_init_sysfs);
 #endif /* SYSFS */
-
-#endif /* GENERIC_CLOCK_EVENTS */

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 +469,25 @@ 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%, in other words, we
+ * return half the number of nanoseconds the hardware counter can technically
+ * cover. This is done so that we can potentially detect problems caused by
+ * delayed timers or bad hardware, which might result in time intervals that
+ * are larger then what the math used can handle without overflows.
  */
-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 +498,26 @@ 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 +646,7 @@ 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 +654,64 @@ 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 +728,7 @@ 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 +740,6 @@ 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/hrtimer.c

@@ -54,7 +54,7 @@
 
 #include <trace/events/timer.h>
 
-#include "timekeeping.h"
+#include "tick-internal.h"
 
 /*
  * The timer bases:
@@ -1707,17 +1707,10 @@ static int hrtimer_cpu_notify(struct notifier_block *self,
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
-	case CPU_DYING:
-	case CPU_DYING_FROZEN:
-		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu);
-		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-	{
-		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu);
 		migrate_hrtimers(scpu);
 		break;
-	}
 #endif
 
 	default:

kernel/time/jiffies.c

@@ -25,7 +25,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 
-#include "tick-internal.h"
+#include "timekeeping.h"
 
 /* The Jiffies based clocksource is the lowest common
  * denominator clock source which should function on
@@ -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/ntp.c

@@ -17,7 +17,6 @@
 #include <linux/module.h>
 #include <linux/rtc.h>
 
-#include "tick-internal.h"
 #include "ntp_internal.h"
 
 /*
@@ -459,6 +458,16 @@ out:
 	return leap;
 }
 
+#ifdef CONFIG_GENERIC_CMOS_UPDATE
+int __weak update_persistent_clock64(struct timespec64 now64)
+{
+	struct timespec now;
+
+	now = timespec64_to_timespec(now64);
+	return update_persistent_clock(now);
+}
+#endif
+
 #if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC)
 static void sync_cmos_clock(struct work_struct *work);
 
@@ -494,8 +503,9 @@ static void sync_cmos_clock(struct work_struct *work)
 		if (persistent_clock_is_local)
 			adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
-		fail = update_persistent_clock(timespec64_to_timespec(adjust));
+		fail = update_persistent_clock64(adjust);
 #endif
+
 #ifdef CONFIG_RTC_SYSTOHC
 		if (fail == -ENODEV)
 			fail = rtc_set_ntp_time(adjust);

kernel/time/sched_clock.c

@@ -1,5 +1,6 @@
 /*
- * sched_clock.c: support for extending counters to full 64-bit ns counter
+ * sched_clock.c: Generic sched_clock() support, to extend low level
+ *                hardware time counters to full 64-bit ns values.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -18,15 +19,53 @@
 #include <linux/seqlock.h>
 #include <linux/bitops.h>
 
-struct clock_data {
-	ktime_t wrap_kt;
+/**
+ * struct clock_read_data - data required to read from sched_clock()
+ *
+ * @epoch_ns:		sched_clock() value at last update
+ * @epoch_cyc:		Clock cycle value at last update.
+ * @sched_clock_mask:   Bitmask for two's complement subtraction of non 64bit
+ *			clocks.
+ * @read_sched_clock:	Current clock source (or dummy source when suspended).
+ * @mult:		Multipler for scaled math conversion.
+ * @shift:		Shift value for scaled math conversion.
+ *
+ * Care must be taken when updating this structure; it is read by
+ * some very hot code paths. It occupies <=40 bytes and, when combined
+ * with the seqcount used to synchronize access, comfortably fits into
+ * a 64 byte cache line.
+ */
+struct clock_read_data {
 	u64 epoch_ns;
 	u64 epoch_cyc;
-	seqcount_t seq;
-	unsigned long rate;
+	u64 sched_clock_mask;
+	u64 (*read_sched_clock)(void);
 	u32 mult;
 	u32 shift;
-	bool suspended;
+};
+
+/**
+ * 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_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;
@@ -34,12 +73,6 @@ static int irqtime = -1;
 
 core_param(irqtime, irqtime, int, 0400);
 
-static struct clock_data cd = {
-	.mult	= NSEC_PER_SEC / HZ,
-};
-
-static u64 __read_mostly sched_clock_mask;
-
 static u64 notrace jiffy_sched_clock_read(void)
 {
 	/*
@@ -49,7 +82,11 @@ static u64 notrace jiffy_sched_clock_read(void)
 	return (u64)(jiffies - INITIAL_JIFFIES);
 }
 
-static u64 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
+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 inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 {
@@ -58,111 +95,136 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 
 unsigned long long notrace sched_clock(void)
 {
-	u64 epoch_ns;
-	u64 epoch_cyc;
-	u64 cyc;
+	u64 cyc, res;
 	unsigned long seq;
-
-	if (cd.suspended)
-		return cd.epoch_ns;
+	struct clock_read_data *rd;
 
 	do {
-		seq = raw_read_seqcount_begin(&cd.seq);
-		epoch_cyc = cd.epoch_cyc;
-		epoch_ns = cd.epoch_ns;
+		seq = raw_read_seqcount(&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 (read_seqcount_retry(&cd.seq, seq));
 
-	cyc = read_sched_clock();
-	cyc = (cyc - epoch_cyc) & sched_clock_mask;
-	return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift);
+	return res;
+}
+
+/*
+ * 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)
+{
+	/* update the backup (odd) copy with the new data */
+	cd.read_data[1] = *rd;
+
+	/* steer readers towards the odd copy */
+	raw_write_seqcount_latch(&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 */
+	raw_write_seqcount_latch(&cd.seq);
 }
 
 /*
- * Atomically update the sched_clock epoch.
+ * Atomically update the sched_clock() epoch.
  */
-static void notrace update_sched_clock(void)
+static void update_sched_clock(void)
 {
-	unsigned long flags;
 	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;
 
-	cyc = read_sched_clock();
-	ns = cd.epoch_ns +
-		cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
-			  cd.mult, cd.shift);
-
-	raw_local_irq_save(flags);
-	raw_write_seqcount_begin(&cd.seq);
-	cd.epoch_ns = ns;
-	cd.epoch_cyc = cyc;
-	raw_write_seqcount_end(&cd.seq);
-	raw_local_irq_restore(flags);
+	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 __init sched_clock_register(u64 (*read)(void), int bits,
-				 unsigned long rate)
+void __init
+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;
-	ktime_t new_wrap_kt;
 	unsigned long r;
 	char r_unit;
+	struct clock_read_data rd;
 
 	if (cd.rate > rate)
 		return;
 
 	WARN_ON(!irqs_disabled());
 
-	/* calculate the mult/shift to convert counter ticks to ns. */
+	/* 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);
 
-	/* calculate how many ns until we wrap */
-	wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask);
-	new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
+	rd = cd.read_data[0];
 
-	/* update epoch for new counter and update epoch_ns from old counter*/
+	/* Update epoch for new counter and update 'epoch_ns' from old counter*/
 	new_epoch = read();
-	cyc = read_sched_clock();
-	ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
-			  cd.mult, cd.shift);
+	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;
 
-	raw_write_seqcount_begin(&cd.seq);
-	read_sched_clock = read;
-	sched_clock_mask = new_mask;
-	cd.rate = rate;
-	cd.wrap_kt = new_wrap_kt;
-	cd.mult = new_mult;
-	cd.shift = new_shift;
-	cd.epoch_cyc = new_epoch;
-	cd.epoch_ns = ns;
-	raw_write_seqcount_end(&cd.seq);
+	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);
 
 	r = rate;
 	if (r >= 4000000) {
 		r /= 1000000;
 		r_unit = 'M';
-	} else if (r >= 1000) {
-		r /= 1000;
-		r_unit = 'k';
-	} else
-		r_unit = ' ';
-
-	/* calculate the ns resolution of this counter */
+	} else {
+		if (r >= 1000) {
+			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 */
+	/* Enable IRQ time accounting if we have a fast enough sched_clock() */
 	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
 		enable_sched_clock_irqtime();
 
@@ -172,10 +234,10 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
 void __init sched_clock_postinit(void)
 {
 	/*
-	 * If no sched_clock function has been provided at that point,
+	 * If no sched_clock() function has been provided at that point,
 	 * make it the final one one.
 	 */
-	if (read_sched_clock == jiffy_sched_clock_read)
+	if (cd.actual_read_sched_clock == jiffy_sched_clock_read)
 		sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ);
 
 	update_sched_clock();
@@ -189,29 +251,53 @@ void __init sched_clock_postinit(void)
 	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
 }
 
+/*
+ * 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 long seq = raw_read_seqcount(&cd.seq);
+
+	return cd.read_data[seq & 1].epoch_cyc;
+}
+
 static int sched_clock_suspend(void)
 {
+	struct clock_read_data *rd = &cd.read_data[0];
+
 	update_sched_clock();
 	hrtimer_cancel(&sched_clock_timer);
-	cd.suspended = true;
+	rd->read_sched_clock = suspended_sched_clock_read;
+
 	return 0;
 }
 
 static void sched_clock_resume(void)
 {
-	cd.epoch_cyc = read_sched_clock();
+	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);
-	cd.suspended = false;
+	rd->read_sched_clock = cd.actual_read_sched_clock;
 }
 
 static struct syscore_ops sched_clock_ops = {
-	.suspend = sched_clock_suspend,
-	.resume = sched_clock_resume,
+	.suspend	= sched_clock_suspend,
+	.resume		= sched_clock_resume,
 };
 
 static int __init sched_clock_syscore_init(void)
 {
 	register_syscore_ops(&sched_clock_ops);
+
 	return 0;
 }
 device_initcall(sched_clock_syscore_init);

kernel/time/tick-broadcast.c

@@ -33,12 +33,14 @@ static cpumask_var_t tick_broadcast_mask;
 static cpumask_var_t tick_broadcast_on;
 static cpumask_var_t tmpmask;
 static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
-static int tick_broadcast_force;
+static int tick_broadcast_forced;
 
 #ifdef CONFIG_TICK_ONESHOT
 static void tick_broadcast_clear_oneshot(int cpu);
+static void tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 #else
 static inline void tick_broadcast_clear_oneshot(int cpu) { }
+static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { }
 #endif
 
 /*
@@ -303,7 +305,7 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 	/*
 	 * The device is in periodic mode. No reprogramming necessary:
 	 */
-	if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
+	if (dev->state == CLOCK_EVT_STATE_PERIODIC)
 		goto unlock;
 
 	/*
@@ -324,49 +326,54 @@ unlock:
 	raw_spin_unlock(&tick_broadcast_lock);
 }
 
-/*
- * Powerstate information: The system enters/leaves a state, where
- * affected devices might stop
+/**
+ * tick_broadcast_control - Enable/disable or force broadcast mode
+ * @mode:	The selected broadcast mode
+ *
+ * Called when the system enters a state where affected tick devices
+ * might stop. Note: TICK_BROADCAST_FORCE cannot be undone.
+ *
+ * Called with interrupts disabled, so clockevents_lock is not
+ * required here because the local clock event device cannot go away
+ * under us.
  */
-static void tick_do_broadcast_on_off(unsigned long *reason)
+void tick_broadcast_control(enum tick_broadcast_mode mode)
 {
 	struct clock_event_device *bc, *dev;
 	struct tick_device *td;
-	unsigned long flags;
 	int cpu, bc_stopped;
 
-	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-
-	cpu = smp_processor_id();
-	td = &per_cpu(tick_cpu_device, cpu);
+	td = this_cpu_ptr(&tick_cpu_device);
 	dev = td->evtdev;
-	bc = tick_broadcast_device.evtdev;
 
 	/*
 	 * Is the device not affected by the powerstate ?
 	 */
 	if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP))
-		goto out;
+		return;
 
 	if (!tick_device_is_functional(dev))
-		goto out;
+		return;
 
+	raw_spin_lock(&tick_broadcast_lock);
+	cpu = smp_processor_id();
+	bc = tick_broadcast_device.evtdev;
 	bc_stopped = cpumask_empty(tick_broadcast_mask);
 
-	switch (*reason) {
-	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
-	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+	switch (mode) {
+	case TICK_BROADCAST_FORCE:
+		tick_broadcast_forced = 1;
+	case TICK_BROADCAST_ON:
 		cpumask_set_cpu(cpu, tick_broadcast_on);
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
 			if (tick_broadcast_device.mode ==
 			    TICKDEV_MODE_PERIODIC)
 				clockevents_shutdown(dev);
 		}
-		if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
-			tick_broadcast_force = 1;
 		break;
-	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
-		if (tick_broadcast_force)
+
+	case TICK_BROADCAST_OFF:
+		if (tick_broadcast_forced)
 			break;
 		cpumask_clear_cpu(cpu, tick_broadcast_on);
 		if (!tick_device_is_functional(dev))
@@ -388,22 +395,9 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
 		else
 			tick_broadcast_setup_oneshot(bc);
 	}
-out:
-	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
-}
-
-/*
- * Powerstate information: The system enters/leaves a state, where
- * affected devices might stop.
- */
-void tick_broadcast_on_off(unsigned long reason, int *oncpu)
-{
-	if (!cpumask_test_cpu(*oncpu, cpu_online_mask))
-		printk(KERN_ERR "tick-broadcast: ignoring broadcast for "
-		       "offline CPU #%d\n", *oncpu);
-	else
-		tick_do_broadcast_on_off(&reason);
+	raw_spin_unlock(&tick_broadcast_lock);
 }
+EXPORT_SYMBOL_GPL(tick_broadcast_control);
 
 /*
  * Set the periodic handler depending on broadcast on/off
@@ -416,14 +410,14 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
 		dev->event_handler = tick_handle_periodic_broadcast;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * Remove a CPU from broadcasting
  */
-void tick_shutdown_broadcast(unsigned int *cpup)
+void tick_shutdown_broadcast(unsigned int cpu)
 {
 	struct clock_event_device *bc;
 	unsigned long flags;
-	unsigned int cpu = *cpup;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -438,6 +432,7 @@ void tick_shutdown_broadcast(unsigned int *cpup)
 
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
+#endif
 
 void tick_suspend_broadcast(void)
 {
@@ -453,38 +448,48 @@ void tick_suspend_broadcast(void)
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
-int tick_resume_broadcast(void)
+/*
+ * This is called from tick_resume_local() on a resuming CPU. That's
+ * called from the core resume function, tick_unfreeze() and the magic XEN
+ * resume hackery.
+ *
+ * In none of these cases the broadcast device mode can change and the
+ * bit of the resuming CPU in the broadcast mask is safe as well.
+ */
+bool tick_resume_check_broadcast(void)
+{
+	if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT)
+		return false;
+	else
+		return cpumask_test_cpu(smp_processor_id(), tick_broadcast_mask);
+}
+
+void tick_resume_broadcast(void)
 {
 	struct clock_event_device *bc;
 	unsigned long flags;
-	int broadcast = 0;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	bc = tick_broadcast_device.evtdev;
 
 	if (bc) {
-		clockevents_set_mode(bc, CLOCK_EVT_MODE_RESUME);
+		clockevents_tick_resume(bc);
 
 		switch (tick_broadcast_device.mode) {
 		case TICKDEV_MODE_PERIODIC:
 			if (!cpumask_empty(tick_broadcast_mask))
 				tick_broadcast_start_periodic(bc);
-			broadcast = cpumask_test_cpu(smp_processor_id(),
-						     tick_broadcast_mask);
 			break;
 		case TICKDEV_MODE_ONESHOT:
 			if (!cpumask_empty(tick_broadcast_mask))
-				broadcast = tick_resume_broadcast_oneshot(bc);
+				tick_resume_broadcast_oneshot(bc);
 			break;
 		}
 	}
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
-
-	return broadcast;
 }
 
-
 #ifdef CONFIG_TICK_ONESHOT
 
 static cpumask_var_t tick_broadcast_oneshot_mask;
@@ -532,8 +537,8 @@ static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
 {
 	int ret;
 
-	if (bc->mode != CLOCK_EVT_MODE_ONESHOT)
-		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+	if (bc->state != CLOCK_EVT_STATE_ONESHOT)
+		clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
 
 	ret = clockevents_program_event(bc, expires, force);
 	if (!ret)
@@ -541,10 +546,9 @@ static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
 	return ret;
 }
 
-int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
+static void tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
-	clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
-	return 0;
+	clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
 }
 
 /*
@@ -562,8 +566,8 @@ void tick_check_oneshot_broadcast_this_cpu(void)
 		 * switched over, leave the device alone.
 		 */
 		if (td->mode == TICKDEV_MODE_ONESHOT) {
-			clockevents_set_mode(td->evtdev,
-					     CLOCK_EVT_MODE_ONESHOT);
+			clockevents_set_state(td->evtdev,
+					      CLOCK_EVT_STATE_ONESHOT);
 		}
 	}
 }
@@ -666,31 +670,26 @@ static void broadcast_shutdown_local(struct clock_event_device *bc,
 		if (dev->next_event.tv64 < bc->next_event.tv64)
 			return;
 	}
-	clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+	clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 }
 
-static void broadcast_move_bc(int deadcpu)
-{
-	struct clock_event_device *bc = tick_broadcast_device.evtdev;
-
-	if (!bc || !broadcast_needs_cpu(bc, deadcpu))
-		return;
-	/* This moves the broadcast assignment to this cpu */
-	clockevents_program_event(bc, bc->next_event, 1);
-}
-
-/*
- * Powerstate information: The system enters/leaves a state, where
- * affected devices might stop
+/**
+ * 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(unsigned long reason)
+int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 {
 	struct clock_event_device *bc, *dev;
 	struct tick_device *td;
-	unsigned long flags;
-	ktime_t now;
 	int cpu, ret = 0;
+	ktime_t now;
 
 	/*
 	 * Periodic mode does not care about the enter/exit of power
@@ -703,17 +702,17 @@ int tick_broadcast_oneshot_control(unsigned long reason)
 	 * We are called with preemtion disabled from the depth of the
 	 * idle code, so we can't be moved away.
 	 */
-	cpu = smp_processor_id();
-	td = &per_cpu(tick_cpu_device, cpu);
+	td = this_cpu_ptr(&tick_cpu_device);
 	dev = td->evtdev;
 
 	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
 		return 0;
 
+	raw_spin_lock(&tick_broadcast_lock);
 	bc = tick_broadcast_device.evtdev;
+	cpu = smp_processor_id();
 
-	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-	if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
+	if (state == TICK_BROADCAST_ENTER) {
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
 			broadcast_shutdown_local(bc, dev);
@@ -741,7 +740,7 @@ int tick_broadcast_oneshot_control(unsigned long reason)
 			cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	} else {
 		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
-			clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+			clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
 			/*
 			 * The cpu which was handling the broadcast
 			 * timer marked this cpu in the broadcast
@@ -805,9 +804,10 @@ int tick_broadcast_oneshot_control(unsigned long reason)
 		}
 	}
 out:
-	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+	raw_spin_unlock(&tick_broadcast_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
 
 /*
  * Reset the one shot broadcast for a cpu
@@ -842,7 +842,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 
 	/* Set it up only once ! */
 	if (bc->event_handler != tick_handle_oneshot_broadcast) {
-		int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
+		int was_periodic = bc->state == CLOCK_EVT_STATE_PERIODIC;
 
 		bc->event_handler = tick_handle_oneshot_broadcast;
 
@@ -858,7 +858,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 			   tick_broadcast_oneshot_mask, tmpmask);
 
 		if (was_periodic && !cpumask_empty(tmpmask)) {
-			clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+			clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT);
 			tick_broadcast_init_next_event(tmpmask,
 						       tick_next_period);
 			tick_broadcast_set_event(bc, cpu, tick_next_period, 1);
@@ -894,14 +894,28 @@ void tick_broadcast_switch_to_oneshot(void)
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+void hotplug_cpu__broadcast_tick_pull(int deadcpu)
+{
+	struct clock_event_device *bc;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+	bc = tick_broadcast_device.evtdev;
+
+	if (bc && broadcast_needs_cpu(bc, deadcpu)) {
+		/* This moves the broadcast assignment to this CPU: */
+		clockevents_program_event(bc, bc->next_event, 1);
+	}
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+}
 
 /*
  * Remove a dead CPU from broadcasting
  */
-void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
+void tick_shutdown_broadcast_oneshot(unsigned int cpu)
 {
 	unsigned long flags;
-	unsigned int cpu = *cpup;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -913,10 +927,9 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 	cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
 	cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
 
-	broadcast_move_bc(cpu);
-
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
+#endif
 
 /*
  * Check, whether the broadcast device is in one shot mode

kernel/time/tick-common.c

@@ -102,7 +102,7 @@ void tick_handle_periodic(struct clock_event_device *dev)
 
 	tick_periodic(cpu);
 
-	if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
+	if (dev->state != CLOCK_EVT_STATE_ONESHOT)
 		return;
 	for (;;) {
 		/*
@@ -140,7 +140,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 
 	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
 	    !tick_broadcast_oneshot_active()) {
-		clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
+		clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC);
 	} else {
 		unsigned long seq;
 		ktime_t next;
@@ -150,7 +150,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 			next = tick_next_period;
 		} while (read_seqretry(&jiffies_lock, seq));
 
-		clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+		clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
 
 		for (;;) {
 			if (!clockevents_program_event(dev, next, false))
@@ -332,14 +332,16 @@ out_bc:
 	tick_install_broadcast_device(newdev);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * Transfer the do_timer job away from a dying cpu.
  *
- * Called with interrupts disabled.
+ * Called with interrupts disabled. Not locking required. If
+ * tick_do_timer_cpu is owned by this cpu, nothing can change it.
  */
-void tick_handover_do_timer(int *cpup)
+void tick_handover_do_timer(void)
 {
-	if (*cpup == tick_do_timer_cpu) {
+	if (tick_do_timer_cpu == smp_processor_id()) {
 		int cpu = cpumask_first(cpu_online_mask);
 
 		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
@@ -354,9 +356,9 @@ void tick_handover_do_timer(int *cpup)
  * access the hardware device itself.
  * We just set the mode and remove it from the lists.
  */
-void tick_shutdown(unsigned int *cpup)
+void tick_shutdown(unsigned int cpu)
 {
-	struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
+	struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
 	struct clock_event_device *dev = td->evtdev;
 
 	td->mode = TICKDEV_MODE_PERIODIC;
@@ -365,27 +367,42 @@ void tick_shutdown(unsigned int *cpup)
 		 * Prevent that the clock events layer tries to call
 		 * the set mode function!
 		 */
+		dev->state = CLOCK_EVT_STATE_DETACHED;
 		dev->mode = CLOCK_EVT_MODE_UNUSED;
 		clockevents_exchange_device(dev, NULL);
 		dev->event_handler = clockevents_handle_noop;
 		td->evtdev = NULL;
 	}
 }
+#endif
 
-void tick_suspend(void)
+/**
+ * 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);
 }
 
-void tick_resume(void)
+/**
+ * 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);
-	int broadcast = tick_resume_broadcast();
-
-	clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
+	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);
@@ -394,6 +411,35 @@ void tick_resume(void)
 	}
 }
 
+/**
+ * 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();
+}
+
 static DEFINE_RAW_SPINLOCK(tick_freeze_lock);
 static unsigned int tick_freeze_depth;
 
@@ -411,12 +457,10 @@ void tick_freeze(void)
 	raw_spin_lock(&tick_freeze_lock);
 
 	tick_freeze_depth++;
-	if (tick_freeze_depth == num_online_cpus()) {
+	if (tick_freeze_depth == num_online_cpus())
 		timekeeping_suspend();
-	} else {
-		tick_suspend();
-		tick_suspend_broadcast();
-	}
+	else
+		tick_suspend_local();
 
 	raw_spin_unlock(&tick_freeze_lock);
 }
@@ -437,7 +481,7 @@ void tick_unfreeze(void)
 	if (tick_freeze_depth == num_online_cpus())
 		timekeeping_resume();
 	else
-		tick_resume();
+		tick_resume_local();
 
 	tick_freeze_depth--;
 

kernel/time/tick-internal.h

@@ -5,15 +5,12 @@
 #include <linux/tick.h>
 
 #include "timekeeping.h"
+#include "tick-sched.h"
 
-extern seqlock_t jiffies_lock;
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
 
-#define CS_NAME_LEN	32
-
-#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
-
-#define TICK_DO_TIMER_NONE	-1
-#define TICK_DO_TIMER_BOOT	-2
+# 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;
@@ -23,21 +20,72 @@ 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_handover_do_timer(int *cpup);
-extern void tick_shutdown(unsigned int *cpup);
+extern void tick_shutdown(unsigned int cpu);
 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 void clockevents_shutdown(struct clock_event_device *dev);
+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);
+}
 
+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_set_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);
 extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
 
-/*
- * NO_HZ / high resolution timer shared code
- */
+/* 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);
+extern int tick_is_broadcast_device(struct clock_event_device *dev);
+extern void tick_shutdown_broadcast(unsigned int cpu);
+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);
+# else /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST: */
+static inline void tick_install_broadcast_device(struct clock_event_device *dev) { }
+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_shutdown_broadcast(unsigned int cpu) { }
+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 *),
@@ -46,58 +94,42 @@ 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);
-# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+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_setup_oneshot(struct clock_event_device *bc);
-extern int tick_broadcast_oneshot_control(unsigned long reason);
 extern void tick_broadcast_switch_to_oneshot(void);
-extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
-extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
+extern void tick_shutdown_broadcast_oneshot(unsigned int cpu);
 extern int tick_broadcast_oneshot_active(void);
 extern void tick_check_oneshot_broadcast_this_cpu(void);
 bool tick_broadcast_oneshot_available(void);
-# else /* BROADCAST */
-static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
-{
-	BUG();
-}
-static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
+extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
+#else /* !(BROADCAST && ONESHOT): */
+static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
-static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
+static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { }
 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 true; }
-# endif /* !BROADCAST */
-
-#else /* !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 void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
-{
-	BUG();
-}
-static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
-static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
-static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
-{
-	return 0;
-}
-static inline int tick_broadcast_oneshot_active(void) { return 0; }
-static inline bool tick_broadcast_oneshot_available(void) { return false; }
-#endif /* !TICK_ONESHOT */
+static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
+#endif /* !(BROADCAST && ONESHOT) */
 
 /* NO_HZ_FULL internal */
 #ifdef CONFIG_NO_HZ_FULL
@@ -105,68 +137,3 @@ extern void tick_nohz_init(void);
 # else
 static inline void tick_nohz_init(void) { }
 #endif
-
-/*
- * 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);
-extern int tick_is_broadcast_device(struct clock_event_device *dev);
-extern void tick_broadcast_on_off(unsigned long reason, int *oncpu);
-extern void tick_shutdown_broadcast(unsigned int *cpup);
-extern void tick_suspend_broadcast(void);
-extern int tick_resume_broadcast(void);
-extern void tick_broadcast_init(void);
-extern void
-tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
-int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq);
-
-#else /* !BROADCAST */
-
-static inline void tick_install_broadcast_device(struct clock_event_device *dev)
-{
-}
-
-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_broadcast_on_off(unsigned long reason, int *oncpu) { }
-static inline void tick_shutdown_broadcast(unsigned int *cpup) { }
-static inline void tick_suspend_broadcast(void) { }
-static inline int tick_resume_broadcast(void) { return 0; }
-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 /* !BROADCAST */
-
-/*
- * 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);
-}
-
-int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
-
-#endif
-
-extern void do_timer(unsigned long ticks);
-extern void update_wall_time(void);

kernel/time/tick-oneshot.c

@@ -38,7 +38,7 @@ void tick_resume_oneshot(void)
 {
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 
-	clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+	clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
 	clockevents_program_event(dev, ktime_get(), true);
 }
 
@@ -50,7 +50,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
 			ktime_t next_event)
 {
 	newdev->event_handler = handler;
-	clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
+	clockevents_set_state(newdev, CLOCK_EVT_STATE_ONESHOT);
 	clockevents_program_event(newdev, next_event, true);
 }
 
@@ -81,7 +81,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
 
 	td->mode = TICKDEV_MODE_ONESHOT;
 	dev->event_handler = handler;
-	clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+	clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT);
 	tick_broadcast_switch_to_oneshot();
 	return 0;
 }

kernel/time/tick-sched.c

@@ -34,7 +34,7 @@
 /*
  * Per cpu nohz control structure
  */
-DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
+static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
 
 /*
  * The time, when the last jiffy update happened. Protected by jiffies_lock.
@@ -416,6 +416,11 @@ static int __init setup_tick_nohz(char *str)
 
 __setup("nohz=", setup_tick_nohz);
 
+int tick_nohz_tick_stopped(void)
+{
+	return __this_cpu_read(tick_cpu_sched.tick_stopped);
+}
+
 /**
  * tick_nohz_update_jiffies - update jiffies when idle was interrupted
  *

kernel/time/tick-sched.h

@@ -0,0 +1,74 @@
+#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;
+};
+
+enum tick_nohz_mode {
+	NOHZ_MODE_INACTIVE,
+	NOHZ_MODE_LOWRES,
+	NOHZ_MODE_HIGHRES,
+};
+
+/**
+ * struct tick_sched - sched tick emulation and no idle tick control/stats
+ * @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.
+ * @tick_stopped:	Indicator that the idle tick has been stopped
+ * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
+ * @idle_calls:		Total number of idle calls
+ * @idle_sleeps:	Number of idle calls, where the sched tick was stopped
+ * @idle_entrytime:	Time when the idle call was entered
+ * @idle_waketime:	Time when the idle was interrupted
+ * @idle_exittime:	Time when the idle state was left
+ * @idle_sleeptime:	Sum of the time slept in idle with sched tick stopped
+ * @iowait_sleeptime:	Sum of the time slept in idle with sched tick stopped, with IO outstanding
+ * @sleep_length:	Duration of the current idle sleep
+ * @do_timer_lst:	CPU was the last one doing do_timer before going idle
+ */
+struct tick_sched {
+	struct hrtimer			sched_timer;
+	unsigned long			check_clocks;
+	enum tick_nohz_mode		nohz_mode;
+	ktime_t				last_tick;
+	int				inidle;
+	int				tick_stopped;
+	unsigned long			idle_jiffies;
+	unsigned long			idle_calls;
+	unsigned long			idle_sleeps;
+	int				idle_active;
+	ktime_t				idle_entrytime;
+	ktime_t				idle_waketime;
+	ktime_t				idle_exittime;
+	ktime_t				idle_sleeptime;
+	ktime_t				iowait_sleeptime;
+	ktime_t				sleep_length;
+	unsigned long			last_jiffies;
+	unsigned long			next_jiffies;
+	ktime_t				idle_expires;
+	int				do_timer_last;
+};
+
+extern struct tick_sched *tick_get_tick_sched(int cpu);
+
+extern void tick_setup_sched_timer(void);
+#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
+extern void tick_cancel_sched_timer(int cpu);
+#else
+static inline void tick_cancel_sched_timer(int cpu) { }
+#endif
+
+#endif

kernel/time/timekeeping.c

@@ -59,17 +59,15 @@ struct tk_fast {
 };
 
 static struct tk_fast tk_fast_mono ____cacheline_aligned;
+static struct tk_fast tk_fast_raw  ____cacheline_aligned;
 
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
 
-/* Flag for if there is a persistent clock on this platform */
-bool __read_mostly persistent_clock_exist = false;
-
 static inline void tk_normalize_xtime(struct timekeeper *tk)
 {
-	while (tk->tkr.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr.shift)) {
-		tk->tkr.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr.shift;
+	while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) {
+		tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift;
 		tk->xtime_sec++;
 	}
 }
@@ -79,20 +77,20 @@ static inline struct timespec64 tk_xtime(struct timekeeper *tk)
 	struct timespec64 ts;
 
 	ts.tv_sec = tk->xtime_sec;
-	ts.tv_nsec = (long)(tk->tkr.xtime_nsec >> tk->tkr.shift);
+	ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
 	return ts;
 }
 
 static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
 {
 	tk->xtime_sec = ts->tv_sec;
-	tk->tkr.xtime_nsec = (u64)ts->tv_nsec << tk->tkr.shift;
+	tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift;
 }
 
 static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
 {
 	tk->xtime_sec += ts->tv_sec;
-	tk->tkr.xtime_nsec += (u64)ts->tv_nsec << tk->tkr.shift;
+	tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift;
 	tk_normalize_xtime(tk);
 }
 
@@ -118,6 +116,117 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
 	tk->offs_boot = ktime_add(tk->offs_boot, delta);
 }
 
+#ifdef CONFIG_DEBUG_TIMEKEEPING
+#define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */
+/*
+ * These simple flag variables are managed
+ * without locks, which is racy, but ok since
+ * we don't really care about being super
+ * precise about how many events were seen,
+ * just that a problem was observed.
+ */
+static int timekeeping_underflow_seen;
+static int timekeeping_overflow_seen;
+
+/* last_warning is only modified under the timekeeping lock */
+static long timekeeping_last_warning;
+
+static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
+{
+
+	cycle_t max_cycles = tk->tkr_mono.clock->max_cycles;
+	const char *name = tk->tkr_mono.clock->name;
+
+	if (offset > max_cycles) {
+		printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n",
+				offset, name, max_cycles);
+		printk_deferred("         timekeeping: Your kernel is sick, but tries to cope by capping time updates\n");
+	} else {
+		if (offset > (max_cycles >> 1)) {
+			printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the the '%s' clock's 50%% safety margin (%lld)\n",
+					offset, name, max_cycles >> 1);
+			printk_deferred("      timekeeping: Your kernel is still fine, but is feeling a bit nervous\n");
+		}
+	}
+
+	if (timekeeping_underflow_seen) {
+		if (jiffies - timekeeping_last_warning > WARNING_FREQ) {
+			printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name);
+			printk_deferred("         Please report this, consider using a different clocksource, if possible.\n");
+			printk_deferred("         Your kernel is probably still fine.\n");
+			timekeeping_last_warning = jiffies;
+		}
+		timekeeping_underflow_seen = 0;
+	}
+
+	if (timekeeping_overflow_seen) {
+		if (jiffies - timekeeping_last_warning > WARNING_FREQ) {
+			printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name);
+			printk_deferred("         Please report this, consider using a different clocksource, if possible.\n");
+			printk_deferred("         Your kernel is probably still fine.\n");
+			timekeeping_last_warning = jiffies;
+		}
+		timekeeping_overflow_seen = 0;
+	}
+}
+
+static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
+{
+	cycle_t now, last, mask, max, delta;
+	unsigned int seq;
+
+	/*
+	 * Since we're called holding a seqlock, the data may shift
+	 * under us while we're doing the calculation. This can cause
+	 * false positives, since we'd note a problem but throw the
+	 * results away. So nest another seqlock here to atomically
+	 * grab the points we are checking with.
+	 */
+	do {
+		seq = read_seqcount_begin(&tk_core.seq);
+		now = tkr->read(tkr->clock);
+		last = tkr->cycle_last;
+		mask = tkr->mask;
+		max = tkr->clock->max_cycles;
+	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+	delta = clocksource_delta(now, last, mask);
+
+	/*
+	 * Try to catch underflows by checking if we are seeing small
+	 * mask-relative negative values.
+	 */
+	if (unlikely((~delta & mask) < (mask >> 3))) {
+		timekeeping_underflow_seen = 1;
+		delta = 0;
+	}
+
+	/* Cap delta value to the max_cycles values to avoid mult overflows */
+	if (unlikely(delta > max)) {
+		timekeeping_overflow_seen = 1;
+		delta = tkr->clock->max_cycles;
+	}
+
+	return delta;
+}
+#else
+static inline void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
+{
+}
+static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
+{
+	cycle_t cycle_now, delta;
+
+	/* read clocksource */
+	cycle_now = tkr->read(tkr->clock);
+
+	/* calculate the delta since the last update_wall_time */
+	delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask);
+
+	return delta;
+}
+#endif
+
 /**
  * tk_setup_internals - Set up internals to use clocksource clock.
  *
@@ -135,11 +244,16 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	u64 tmp, ntpinterval;
 	struct clocksource *old_clock;
 
-	old_clock = tk->tkr.clock;
-	tk->tkr.clock = clock;
-	tk->tkr.read = clock->read;
-	tk->tkr.mask = clock->mask;
-	tk->tkr.cycle_last = tk->tkr.read(clock);
+	old_clock = tk->tkr_mono.clock;
+	tk->tkr_mono.clock = clock;
+	tk->tkr_mono.read = clock->read;
+	tk->tkr_mono.mask = clock->mask;
+	tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock);
+
+	tk->tkr_raw.clock = clock;
+	tk->tkr_raw.read = clock->read;
+	tk->tkr_raw.mask = clock->mask;
+	tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last;
 
 	/* Do the ns -> cycle conversion first, using original mult */
 	tmp = NTP_INTERVAL_LENGTH;
@@ -163,11 +277,14 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	if (old_clock) {
 		int shift_change = clock->shift - old_clock->shift;
 		if (shift_change < 0)
-			tk->tkr.xtime_nsec >>= -shift_change;
+			tk->tkr_mono.xtime_nsec >>= -shift_change;
 		else
-			tk->tkr.xtime_nsec <<= shift_change;
+			tk->tkr_mono.xtime_nsec <<= shift_change;
 	}
-	tk->tkr.shift = clock->shift;
+	tk->tkr_raw.xtime_nsec = 0;
+
+	tk->tkr_mono.shift = clock->shift;
+	tk->tkr_raw.shift = clock->shift;
 
 	tk->ntp_error = 0;
 	tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;
@@ -178,7 +295,8 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	 * active clocksource. These value will be adjusted via NTP
 	 * to counteract clock drifting.
 	 */
-	tk->tkr.mult = clock->mult;
+	tk->tkr_mono.mult = clock->mult;
+	tk->tkr_raw.mult = clock->mult;
 	tk->ntp_err_mult = 0;
 }
 
@@ -193,14 +311,10 @@ static inline u32 arch_gettimeoffset(void) { return 0; }
 
 static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
 {
-	cycle_t cycle_now, delta;
+	cycle_t delta;
 	s64 nsec;
 
-	/* read clocksource: */
-	cycle_now = tkr->read(tkr->clock);
-
-	/* calculate the delta since the last update_wall_time: */
-	delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask);
+	delta = timekeeping_get_delta(tkr);
 
 	nsec = delta * tkr->mult + tkr->xtime_nsec;
 	nsec >>= tkr->shift;
@@ -209,25 +323,6 @@ static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
 	return nsec + arch_gettimeoffset();
 }
 
-static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
-{
-	struct clocksource *clock = tk->tkr.clock;
-	cycle_t cycle_now, delta;
-	s64 nsec;
-
-	/* read clocksource: */
-	cycle_now = tk->tkr.read(clock);
-
-	/* calculate the delta since the last update_wall_time: */
-	delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask);
-
-	/* convert delta to nanoseconds. */
-	nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift);
-
-	/* If arch requires, add in get_arch_timeoffset() */
-	return nsec + arch_gettimeoffset();
-}
-
 /**
  * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper.
  * @tkr: Timekeeping readout base from which we take the update
@@ -267,18 +362,18 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
  * slightly wrong timestamp (a few nanoseconds). See
  * @ktime_get_mono_fast_ns.
  */
-static void update_fast_timekeeper(struct tk_read_base *tkr)
+static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf)
 {
-	struct tk_read_base *base = tk_fast_mono.base;
+	struct tk_read_base *base = tkf->base;
 
 	/* Force readers off to base[1] */
-	raw_write_seqcount_latch(&tk_fast_mono.seq);
+	raw_write_seqcount_latch(&tkf->seq);
 
 	/* Update base[0] */
 	memcpy(base, tkr, sizeof(*base));
 
 	/* Force readers back to base[0] */
-	raw_write_seqcount_latch(&tk_fast_mono.seq);
+	raw_write_seqcount_latch(&tkf->seq);
 
 	/* Update base[1] */
 	memcpy(base + 1, base, sizeof(*base));
@@ -316,22 +411,33 @@ static void update_fast_timekeeper(struct tk_read_base *tkr)
  * of the following timestamps. Callers need to be aware of that and
  * deal with it.
  */
-u64 notrace ktime_get_mono_fast_ns(void)
+static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
 {
 	struct tk_read_base *tkr;
 	unsigned int seq;
 	u64 now;
 
 	do {
-		seq = raw_read_seqcount(&tk_fast_mono.seq);
-		tkr = tk_fast_mono.base + (seq & 0x01);
-		now = ktime_to_ns(tkr->base_mono) + timekeeping_get_ns(tkr);
+		seq = raw_read_seqcount(&tkf->seq);
+		tkr = tkf->base + (seq & 0x01);
+		now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
+	} while (read_seqcount_retry(&tkf->seq, seq));
 
-	} while (read_seqcount_retry(&tk_fast_mono.seq, seq));
 	return now;
 }
+
+u64 ktime_get_mono_fast_ns(void)
+{
+	return __ktime_get_fast_ns(&tk_fast_mono);
+}
 EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns);
 
+u64 ktime_get_raw_fast_ns(void)
+{
+	return __ktime_get_fast_ns(&tk_fast_raw);
+}
+EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
+
 /* Suspend-time cycles value for halted fast timekeeper. */
 static cycle_t cycles_at_suspend;
 
@@ -353,12 +459,17 @@ static cycle_t dummy_clock_read(struct clocksource *cs)
 static void halt_fast_timekeeper(struct timekeeper *tk)
 {
 	static struct tk_read_base tkr_dummy;
-	struct tk_read_base *tkr = &tk->tkr;
+	struct tk_read_base *tkr = &tk->tkr_mono;
 
 	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
 	cycles_at_suspend = tkr->read(tkr->clock);
 	tkr_dummy.read = dummy_clock_read;
-	update_fast_timekeeper(&tkr_dummy);
+	update_fast_timekeeper(&tkr_dummy, &tk_fast_mono);
+
+	tkr = &tk->tkr_raw;
+	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
+	tkr_dummy.read = dummy_clock_read;
+	update_fast_timekeeper(&tkr_dummy, &tk_fast_raw);
 }
 
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD
@@ -369,8 +480,8 @@ static inline void update_vsyscall(struct timekeeper *tk)
 
 	xt = timespec64_to_timespec(tk_xtime(tk));
 	wm = timespec64_to_timespec(tk->wall_to_monotonic);
-	update_vsyscall_old(&xt, &wm, tk->tkr.clock, tk->tkr.mult,
-			    tk->tkr.cycle_last);
+	update_vsyscall_old(&xt, &wm, tk->tkr_mono.clock, tk->tkr_mono.mult,
+			    tk->tkr_mono.cycle_last);
 }
 
 static inline void old_vsyscall_fixup(struct timekeeper *tk)
@@ -387,11 +498,11 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
 	* (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD
 	* users are removed, this can be killed.
 	*/
-	remainder = tk->tkr.xtime_nsec & ((1ULL << tk->tkr.shift) - 1);
-	tk->tkr.xtime_nsec -= remainder;
-	tk->tkr.xtime_nsec += 1ULL << tk->tkr.shift;
+	remainder = tk->tkr_mono.xtime_nsec & ((1ULL << tk->tkr_mono.shift) - 1);
+	tk->tkr_mono.xtime_nsec -= remainder;
+	tk->tkr_mono.xtime_nsec += 1ULL << tk->tkr_mono.shift;
 	tk->ntp_error += remainder << tk->ntp_error_shift;
-	tk->ntp_error -= (1ULL << tk->tkr.shift) << tk->ntp_error_shift;
+	tk->ntp_error -= (1ULL << tk->tkr_mono.shift) << tk->ntp_error_shift;
 }
 #else
 #define old_vsyscall_fixup(tk)
@@ -456,17 +567,17 @@ static inline void tk_update_ktime_data(struct timekeeper *tk)
 	 */
 	seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec);
 	nsec = (u32) tk->wall_to_monotonic.tv_nsec;
-	tk->tkr.base_mono = ns_to_ktime(seconds * NSEC_PER_SEC + nsec);
+	tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec);
 
 	/* Update the monotonic raw base */
-	tk->base_raw = timespec64_to_ktime(tk->raw_time);
+	tk->tkr_raw.base = timespec64_to_ktime(tk->raw_time);
 
 	/*
 	 * The sum of the nanoseconds portions of xtime and
 	 * wall_to_monotonic can be greater/equal one second. Take
 	 * this into account before updating tk->ktime_sec.
 	 */
-	nsec += (u32)(tk->tkr.xtime_nsec >> tk->tkr.shift);
+	nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
 	if (nsec >= NSEC_PER_SEC)
 		seconds++;
 	tk->ktime_sec = seconds;
@@ -489,7 +600,8 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
 		memcpy(&shadow_timekeeper, &tk_core.timekeeper,
 		       sizeof(tk_core.timekeeper));
 
-	update_fast_timekeeper(&tk->tkr);
+	update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
+	update_fast_timekeeper(&tk->tkr_raw,  &tk_fast_raw);
 }
 
 /**
@@ -501,22 +613,23 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
  */
 static void timekeeping_forward_now(struct timekeeper *tk)
 {
-	struct clocksource *clock = tk->tkr.clock;
+	struct clocksource *clock = tk->tkr_mono.clock;
 	cycle_t cycle_now, delta;
 	s64 nsec;
 
-	cycle_now = tk->tkr.read(clock);
-	delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask);
-	tk->tkr.cycle_last = cycle_now;
+	cycle_now = tk->tkr_mono.read(clock);
+	delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
+	tk->tkr_mono.cycle_last = cycle_now;
+	tk->tkr_raw.cycle_last  = cycle_now;
 
-	tk->tkr.xtime_nsec += delta * tk->tkr.mult;
+	tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult;
 
 	/* If arch requires, add in get_arch_timeoffset() */
-	tk->tkr.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr.shift;
+	tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift;
 
 	tk_normalize_xtime(tk);
 
-	nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift);
+	nsec = clocksource_cyc2ns(delta, tk->tkr_raw.mult, tk->tkr_raw.shift);
 	timespec64_add_ns(&tk->raw_time, nsec);
 }
 
@@ -537,7 +650,7 @@ int __getnstimeofday64(struct timespec64 *ts)
 		seq = read_seqcount_begin(&tk_core.seq);
 
 		ts->tv_sec = tk->xtime_sec;
-		nsecs = timekeeping_get_ns(&tk->tkr);
+		nsecs = timekeeping_get_ns(&tk->tkr_mono);
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -577,8 +690,8 @@ ktime_t ktime_get(void)
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		base = tk->tkr.base_mono;
-		nsecs = timekeeping_get_ns(&tk->tkr);
+		base = tk->tkr_mono.base;
+		nsecs = timekeeping_get_ns(&tk->tkr_mono);
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -603,8 +716,8 @@ ktime_t ktime_get_with_offset(enum tk_offsets offs)
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		base = ktime_add(tk->tkr.base_mono, *offset);
-		nsecs = timekeeping_get_ns(&tk->tkr);
+		base = ktime_add(tk->tkr_mono.base, *offset);
+		nsecs = timekeeping_get_ns(&tk->tkr_mono);
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -645,8 +758,8 @@ ktime_t ktime_get_raw(void)
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		base = tk->base_raw;
-		nsecs = timekeeping_get_ns_raw(tk);
+		base = tk->tkr_raw.base;
+		nsecs = timekeeping_get_ns(&tk->tkr_raw);
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -674,7 +787,7 @@ void ktime_get_ts64(struct timespec64 *ts)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 		ts->tv_sec = tk->xtime_sec;
-		nsec = timekeeping_get_ns(&tk->tkr);
+		nsec = timekeeping_get_ns(&tk->tkr_mono);
 		tomono = tk->wall_to_monotonic;
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -759,8 +872,8 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
 		ts_real->tv_sec = tk->xtime_sec;
 		ts_real->tv_nsec = 0;
 
-		nsecs_raw = timekeeping_get_ns_raw(tk);
-		nsecs_real = timekeeping_get_ns(&tk->tkr);
+		nsecs_raw  = timekeeping_get_ns(&tk->tkr_raw);
+		nsecs_real = timekeeping_get_ns(&tk->tkr_mono);
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -943,7 +1056,7 @@ static int change_clocksource(void *data)
 	 */
 	if (try_module_get(new->owner)) {
 		if (!new->enable || new->enable(new) == 0) {
-			old = tk->tkr.clock;
+			old = tk->tkr_mono.clock;
 			tk_setup_internals(tk, new);
 			if (old->disable)
 				old->disable(old);
@@ -971,11 +1084,11 @@ int timekeeping_notify(struct clocksource *clock)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 
-	if (tk->tkr.clock == clock)
+	if (tk->tkr_mono.clock == clock)
 		return 0;
 	stop_machine(change_clocksource, clock, NULL);
 	tick_clock_notify();
-	return tk->tkr.clock == clock ? 0 : -1;
+	return tk->tkr_mono.clock == clock ? 0 : -1;
 }
 
 /**
@@ -993,7 +1106,7 @@ void getrawmonotonic64(struct timespec64 *ts)
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		nsecs = timekeeping_get_ns_raw(tk);
+		nsecs = timekeeping_get_ns(&tk->tkr_raw);
 		ts64 = tk->raw_time;
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -1016,7 +1129,7 @@ int timekeeping_valid_for_hres(void)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		ret = tk->tkr.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
+		ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -1035,7 +1148,7 @@ u64 timekeeping_max_deferment(void)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		ret = tk->tkr.clock->max_idle_ns;
+		ret = tk->tkr_mono.clock->max_idle_ns;
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -1057,6 +1170,14 @@ void __weak read_persistent_clock(struct timespec *ts)
 	ts->tv_nsec = 0;
 }
 
+void __weak read_persistent_clock64(struct timespec64 *ts64)
+{
+	struct timespec ts;
+
+	read_persistent_clock(&ts);
+	*ts64 = timespec_to_timespec64(ts);
+}
+
 /**
  * read_boot_clock -  Return time of the system start.
  *
@@ -1072,6 +1193,20 @@ void __weak read_boot_clock(struct timespec *ts)
 	ts->tv_nsec = 0;
 }
 
+void __weak read_boot_clock64(struct timespec64 *ts64)
+{
+	struct timespec ts;
+
+	read_boot_clock(&ts);
+	*ts64 = timespec_to_timespec64(ts);
+}
+
+/* Flag for if timekeeping_resume() has injected sleeptime */
+static bool sleeptime_injected;
+
+/* Flag for if there is a persistent clock on this platform */
+static bool persistent_clock_exists;
+
 /*
  * timekeeping_init - Initializes the clocksource and common timekeeping values
  */
@@ -1081,20 +1216,17 @@ void __init timekeeping_init(void)
 	struct clocksource *clock;
 	unsigned long flags;
 	struct timespec64 now, boot, tmp;
-	struct timespec ts;
 
-	read_persistent_clock(&ts);
-	now = timespec_to_timespec64(ts);
+	read_persistent_clock64(&now);
 	if (!timespec64_valid_strict(&now)) {
 		pr_warn("WARNING: Persistent clock returned invalid value!\n"
 			"         Check your CMOS/BIOS settings.\n");
 		now.tv_sec = 0;
 		now.tv_nsec = 0;
 	} else if (now.tv_sec || now.tv_nsec)
-		persistent_clock_exist = true;
+		persistent_clock_exists = true;
 
-	read_boot_clock(&ts);
-	boot = timespec_to_timespec64(ts);
+	read_boot_clock64(&boot);
 	if (!timespec64_valid_strict(&boot)) {
 		pr_warn("WARNING: Boot clock returned invalid value!\n"
 			"         Check your CMOS/BIOS settings.\n");
@@ -1114,7 +1246,6 @@ void __init timekeeping_init(void)
 	tk_set_xtime(tk, &now);
 	tk->raw_time.tv_sec = 0;
 	tk->raw_time.tv_nsec = 0;
-	tk->base_raw.tv64 = 0;
 	if (boot.tv_sec == 0 && boot.tv_nsec == 0)
 		boot = tk_xtime(tk);
 
@@ -1127,7 +1258,7 @@ void __init timekeeping_init(void)
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 }
 
-/* time in seconds when suspend began */
+/* time in seconds when suspend began for persistent clock */
 static struct timespec64 timekeeping_suspend_time;
 
 /**
@@ -1152,12 +1283,49 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
 	tk_debug_account_sleep_time(delta);
 }
 
+#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE)
+/**
+ * We have three kinds of time sources to use for sleep time
+ * injection, the preference order is:
+ * 1) non-stop clocksource
+ * 2) persistent clock (ie: RTC accessible when irqs are off)
+ * 3) RTC
+ *
+ * 1) and 2) are used by timekeeping, 3) by RTC subsystem.
+ * If system has neither 1) nor 2), 3) will be used finally.
+ *
+ *
+ * If timekeeping has injected sleeptime via either 1) or 2),
+ * 3) becomes needless, so in this case we don't need to call
+ * rtc_resume(), and this is what timekeeping_rtc_skipresume()
+ * means.
+ */
+bool timekeeping_rtc_skipresume(void)
+{
+	return sleeptime_injected;
+}
+
+/**
+ * 1) can be determined whether to use or not only when doing
+ * timekeeping_resume() which is invoked after rtc_suspend(),
+ * so we can't skip rtc_suspend() surely if system has 1).
+ *
+ * But if system has 2), 2) will definitely be used, so in this
+ * case we don't need to call rtc_suspend(), and this is what
+ * timekeeping_rtc_skipsuspend() means.
+ */
+bool timekeeping_rtc_skipsuspend(void)
+{
+	return persistent_clock_exists;
+}
+
 /**
  * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values
  * @delta: pointer to a timespec64 delta value
  *
- * This hook is for architectures that cannot support read_persistent_clock
+ * This hook is for architectures that cannot support read_persistent_clock64
  * because their RTC/persistent clock is only accessible when irqs are enabled.
+ * and also don't have an effective nonstop clocksource.
  *
  * This function should only be called by rtc_resume(), and allows
  * a suspend offset to be injected into the timekeeping values.
@@ -1167,13 +1335,6 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta)
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
 
-	/*
-	 * Make sure we don't set the clock twice, as timekeeping_resume()
-	 * already did it
-	 */
-	if (has_persistent_clock())
-		return;
-
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 
@@ -1189,26 +1350,21 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta)
 	/* signal hrtimers about time change */
 	clock_was_set();
 }
+#endif
 
 /**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
- *
- * This is for the generic clocksource timekeeping.
- * xtime/wall_to_monotonic/jiffies/etc are
- * still managed by arch specific suspend/resume code.
  */
 void timekeeping_resume(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	struct clocksource *clock = tk->tkr.clock;
+	struct clocksource *clock = tk->tkr_mono.clock;
 	unsigned long flags;
 	struct timespec64 ts_new, ts_delta;
-	struct timespec tmp;
 	cycle_t cycle_now, cycle_delta;
-	bool suspendtime_found = false;
 
-	read_persistent_clock(&tmp);
-	ts_new = timespec_to_timespec64(tmp);
+	sleeptime_injected = false;
+	read_persistent_clock64(&ts_new);
 
 	clockevents_resume();
 	clocksource_resume();
@@ -1228,16 +1384,16 @@ void timekeeping_resume(void)
 	 * The less preferred source will only be tried if there is no better
 	 * usable source. The rtc part is handled separately in rtc core code.
 	 */
-	cycle_now = tk->tkr.read(clock);
+	cycle_now = tk->tkr_mono.read(clock);
 	if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
-		cycle_now > tk->tkr.cycle_last) {
+		cycle_now > tk->tkr_mono.cycle_last) {
 		u64 num, max = ULLONG_MAX;
 		u32 mult = clock->mult;
 		u32 shift = clock->shift;
 		s64 nsec = 0;
 
-		cycle_delta = clocksource_delta(cycle_now, tk->tkr.cycle_last,
-						tk->tkr.mask);
+		cycle_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last,
+						tk->tkr_mono.mask);
 
 		/*
 		 * "cycle_delta * mutl" may cause 64 bits overflow, if the
@@ -1253,17 +1409,19 @@ void timekeeping_resume(void)
 		nsec += ((u64) cycle_delta * mult) >> shift;
 
 		ts_delta = ns_to_timespec64(nsec);
-		suspendtime_found = true;
+		sleeptime_injected = true;
 	} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
 		ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
-		suspendtime_found = true;
+		sleeptime_injected = true;
 	}
 
-	if (suspendtime_found)
+	if (sleeptime_injected)
 		__timekeeping_inject_sleeptime(tk, &ts_delta);
 
 	/* Re-base the last cycle value */
-	tk->tkr.cycle_last = cycle_now;
+	tk->tkr_mono.cycle_last = cycle_now;
+	tk->tkr_raw.cycle_last  = cycle_now;
+
 	tk->ntp_error = 0;
 	timekeeping_suspended = 0;
 	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
@@ -1272,9 +1430,7 @@ void timekeeping_resume(void)
 
 	touch_softlockup_watchdog();
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);
-
-	/* Resume hrtimers */
+	tick_resume();
 	hrtimers_resume();
 }
 
@@ -1284,10 +1440,8 @@ int timekeeping_suspend(void)
 	unsigned long flags;
 	struct timespec64		delta, delta_delta;
 	static struct timespec64	old_delta;
-	struct timespec tmp;
 
-	read_persistent_clock(&tmp);
-	timekeeping_suspend_time = timespec_to_timespec64(tmp);
+	read_persistent_clock64(&timekeeping_suspend_time);
 
 	/*
 	 * On some systems the persistent_clock can not be detected at
@@ -1295,31 +1449,33 @@ int timekeeping_suspend(void)
 	 * value returned, update the persistent_clock_exists flag.
 	 */
 	if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
-		persistent_clock_exist = true;
+		persistent_clock_exists = true;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 	timekeeping_forward_now(tk);
 	timekeeping_suspended = 1;
 
-	/*
-	 * To avoid drift caused by repeated suspend/resumes,
-	 * which each can add ~1 second drift error,
-	 * try to compensate so the difference in system time
-	 * and persistent_clock time stays close to constant.
-	 */
-	delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time);
-	delta_delta = timespec64_sub(delta, old_delta);
-	if (abs(delta_delta.tv_sec)  >= 2) {
+	if (persistent_clock_exists) {
 		/*
-		 * if delta_delta is too large, assume time correction
-		 * has occured and set old_delta to the current delta.
+		 * To avoid drift caused by repeated suspend/resumes,
+		 * which each can add ~1 second drift error,
+		 * try to compensate so the difference in system time
+		 * and persistent_clock time stays close to constant.
 		 */
-		old_delta = delta;
-	} else {
-		/* Otherwise try to adjust old_system to compensate */
-		timekeeping_suspend_time =
-			timespec64_add(timekeeping_suspend_time, delta_delta);
+		delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time);
+		delta_delta = timespec64_sub(delta, old_delta);
+		if (abs(delta_delta.tv_sec) >= 2) {
+			/*
+			 * if delta_delta is too large, assume time correction
+			 * has occurred and set old_delta to the current delta.
+			 */
+			old_delta = delta;
+		} else {
+			/* Otherwise try to adjust old_system to compensate */
+			timekeeping_suspend_time =
+				timespec64_add(timekeeping_suspend_time, delta_delta);
+		}
 	}
 
 	timekeeping_update(tk, TK_MIRROR);
@@ -1327,7 +1483,7 @@ int timekeeping_suspend(void)
 	write_seqcount_end(&tk_core.seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
-	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
+	tick_suspend();
 	clocksource_suspend();
 	clockevents_suspend();
 
@@ -1416,15 +1572,15 @@ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk,
 	 *
 	 * XXX - TODO: Doc ntp_error calculation.
 	 */
-	if ((mult_adj > 0) && (tk->tkr.mult + mult_adj < mult_adj)) {
+	if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) {
 		/* NTP adjustment caused clocksource mult overflow */
 		WARN_ON_ONCE(1);
 		return;
 	}
 
-	tk->tkr.mult += mult_adj;
+	tk->tkr_mono.mult += mult_adj;
 	tk->xtime_interval += interval;
-	tk->tkr.xtime_nsec -= offset;
+	tk->tkr_mono.xtime_nsec -= offset;
 	tk->ntp_error -= (interval - offset) << tk->ntp_error_shift;
 }
 
@@ -1486,13 +1642,13 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 		tk->ntp_err_mult = 0;
 	}
 
-	if (unlikely(tk->tkr.clock->maxadj &&
-		(abs(tk->tkr.mult - tk->tkr.clock->mult)
-			> tk->tkr.clock->maxadj))) {
+	if (unlikely(tk->tkr_mono.clock->maxadj &&
+		(abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult)
+			> tk->tkr_mono.clock->maxadj))) {
 		printk_once(KERN_WARNING
 			"Adjusting %s more than 11%% (%ld vs %ld)\n",
-			tk->tkr.clock->name, (long)tk->tkr.mult,
-			(long)tk->tkr.clock->mult + tk->tkr.clock->maxadj);
+			tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult,
+			(long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj);
 	}
 
 	/*
@@ -1509,9 +1665,9 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 	 * We'll correct this error next time through this function, when
 	 * xtime_nsec is not as small.
 	 */
-	if (unlikely((s64)tk->tkr.xtime_nsec < 0)) {
-		s64 neg = -(s64)tk->tkr.xtime_nsec;
-		tk->tkr.xtime_nsec = 0;
+	if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) {
+		s64 neg = -(s64)tk->tkr_mono.xtime_nsec;
+		tk->tkr_mono.xtime_nsec = 0;
 		tk->ntp_error += neg << tk->ntp_error_shift;
 	}
 }
@@ -1526,13 +1682,13 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
  */
 static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 {
-	u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr.shift;
+	u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift;
 	unsigned int clock_set = 0;
 
-	while (tk->tkr.xtime_nsec >= nsecps) {
+	while (tk->tkr_mono.xtime_nsec >= nsecps) {
 		int leap;
 
-		tk->tkr.xtime_nsec -= nsecps;
+		tk->tkr_mono.xtime_nsec -= nsecps;
 		tk->xtime_sec++;
 
 		/* Figure out if its a leap sec and apply if needed */
@@ -1577,9 +1733,10 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 
 	/* Accumulate one shifted interval */
 	offset -= interval;
-	tk->tkr.cycle_last += interval;
+	tk->tkr_mono.cycle_last += interval;
+	tk->tkr_raw.cycle_last  += interval;
 
-	tk->tkr.xtime_nsec += tk->xtime_interval << shift;
+	tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift;
 	*clock_set |= accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
@@ -1622,14 +1779,17 @@ void update_wall_time(void)
 #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
 	offset = real_tk->cycle_interval;
 #else
-	offset = clocksource_delta(tk->tkr.read(tk->tkr.clock),
-				   tk->tkr.cycle_last, tk->tkr.mask);
+	offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock),
+				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
 #endif
 
 	/* Check if there's really nothing to do */
 	if (offset < real_tk->cycle_interval)
 		goto out;
 
+	/* Do some additional sanity checking */
+	timekeeping_check_update(real_tk, offset);
+
 	/*
 	 * With NO_HZ we may have to accumulate many cycle_intervals
 	 * (think "ticks") worth of time at once. To do this efficiently,
@@ -1784,8 +1944,8 @@ ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot,
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		base = tk->tkr.base_mono;
-		nsecs = tk->tkr.xtime_nsec >> tk->tkr.shift;
+		base = tk->tkr_mono.base;
+		nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
 
 		*offs_real = tk->offs_real;
 		*offs_boot = tk->offs_boot;
@@ -1816,8 +1976,8 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot,
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		base = tk->tkr.base_mono;
-		nsecs = timekeeping_get_ns(&tk->tkr);
+		base = tk->tkr_mono.base;
+		nsecs = timekeeping_get_ns(&tk->tkr_mono);
 
 		*offs_real = tk->offs_real;
 		*offs_boot = tk->offs_boot;

kernel/time/timekeeping.h

@@ -19,4 +19,11 @@ extern void timekeeping_clocktai(struct timespec *ts);
 extern int timekeeping_suspend(void);
 extern void timekeeping_resume(void);
 
+extern void do_timer(unsigned long ticks);
+extern void update_wall_time(void);
+
+extern seqlock_t jiffies_lock;
+
+#define CS_NAME_LEN	32
+
 #endif

kernel/time/timer.c

@@ -90,8 +90,18 @@ struct tvec_base {
 	struct tvec tv5;
 } ____cacheline_aligned;
 
+/*
+ * __TIMER_INITIALIZER() needs to set ->base to a valid pointer (because we've
+ * made NULL special, hint: lock_timer_base()) and we cannot get a compile time
+ * pointer to per-cpu entries because we don't know where we'll map the section,
+ * even for the boot cpu.
+ *
+ * And so we use boot_tvec_bases for boot CPU and per-cpu __tvec_bases for the
+ * rest of them.
+ */
 struct tvec_base boot_tvec_bases;
 EXPORT_SYMBOL(boot_tvec_bases);
+
 static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
 
 /* Functions below help us manage 'deferrable' flag */
@@ -1027,6 +1037,8 @@ int try_to_del_timer_sync(struct timer_list *timer)
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
 #ifdef CONFIG_SMP
+static DEFINE_PER_CPU(struct tvec_base, __tvec_bases);
+
 /**
  * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
@@ -1532,64 +1544,6 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout)
 }
 EXPORT_SYMBOL(schedule_timeout_uninterruptible);
 
-static int init_timers_cpu(int cpu)
-{
-	int j;
-	struct tvec_base *base;
-	static char tvec_base_done[NR_CPUS];
-
-	if (!tvec_base_done[cpu]) {
-		static char boot_done;
-
-		if (boot_done) {
-			/*
-			 * The APs use this path later in boot
-			 */
-			base = kzalloc_node(sizeof(*base), GFP_KERNEL,
-					    cpu_to_node(cpu));
-			if (!base)
-				return -ENOMEM;
-
-			/* Make sure tvec_base has TIMER_FLAG_MASK bits free */
-			if (WARN_ON(base != tbase_get_base(base))) {
-				kfree(base);
-				return -ENOMEM;
-			}
-			per_cpu(tvec_bases, cpu) = base;
-		} else {
-			/*
-			 * This is for the boot CPU - we use compile-time
-			 * static initialisation because per-cpu memory isn't
-			 * ready yet and because the memory allocators are not
-			 * initialised either.
-			 */
-			boot_done = 1;
-			base = &boot_tvec_bases;
-		}
-		spin_lock_init(&base->lock);
-		tvec_base_done[cpu] = 1;
-		base->cpu = cpu;
-	} else {
-		base = per_cpu(tvec_bases, cpu);
-	}
-
-
-	for (j = 0; j < TVN_SIZE; j++) {
-		INIT_LIST_HEAD(base->tv5.vec + j);
-		INIT_LIST_HEAD(base->tv4.vec + j);
-		INIT_LIST_HEAD(base->tv3.vec + j);
-		INIT_LIST_HEAD(base->tv2.vec + j);
-	}
-	for (j = 0; j < TVR_SIZE; j++)
-		INIT_LIST_HEAD(base->tv1.vec + j);
-
-	base->timer_jiffies = jiffies;
-	base->next_timer = base->timer_jiffies;
-	base->active_timers = 0;
-	base->all_timers = 0;
-	return 0;
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head)
 {
@@ -1631,55 +1585,86 @@ static void migrate_timers(int cpu)
 		migrate_timer_list(new_base, old_base->tv5.vec + i);
 	}
 
+	old_base->active_timers = 0;
+	old_base->all_timers = 0;
+
 	spin_unlock(&old_base->lock);
 	spin_unlock_irq(&new_base->lock);
 	put_cpu_var(tvec_bases);
 }
-#endif /* CONFIG_HOTPLUG_CPU */
 
 static int timer_cpu_notify(struct notifier_block *self,
 				unsigned long action, void *hcpu)
 {
-	long cpu = (long)hcpu;
-	int err;
-
-	switch(action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		err = init_timers_cpu(cpu);
-		if (err < 0)
-			return notifier_from_errno(err);
-		break;
-#ifdef CONFIG_HOTPLUG_CPU
+	switch (action) {
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		migrate_timers(cpu);
+		migrate_timers((long)hcpu);
 		break;
-#endif
 	default:
 		break;
 	}
+
 	return NOTIFY_OK;
 }
 
-static struct notifier_block timers_nb = {
-	.notifier_call	= timer_cpu_notify,
-};
+static inline void timer_register_cpu_notifier(void)
+{
+	cpu_notifier(timer_cpu_notify, 0);
+}
+#else
+static inline void timer_register_cpu_notifier(void) { }
+#endif /* CONFIG_HOTPLUG_CPU */
 
+static void __init init_timer_cpu(struct tvec_base *base, int cpu)
+{
+	int j;
 
-void __init init_timers(void)
+	BUG_ON(base != tbase_get_base(base));
+
+	base->cpu = cpu;
+	per_cpu(tvec_bases, cpu) = base;
+	spin_lock_init(&base->lock);
+
+	for (j = 0; j < TVN_SIZE; j++) {
+		INIT_LIST_HEAD(base->tv5.vec + j);
+		INIT_LIST_HEAD(base->tv4.vec + j);
+		INIT_LIST_HEAD(base->tv3.vec + j);
+		INIT_LIST_HEAD(base->tv2.vec + j);
+	}
+	for (j = 0; j < TVR_SIZE; j++)
+		INIT_LIST_HEAD(base->tv1.vec + j);
+
+	base->timer_jiffies = jiffies;
+	base->next_timer = base->timer_jiffies;
+}
+
+static void __init init_timer_cpus(void)
 {
-	int err;
+	struct tvec_base *base;
+	int local_cpu = smp_processor_id();
+	int cpu;
 
+	for_each_possible_cpu(cpu) {
+		if (cpu == local_cpu)
+			base = &boot_tvec_bases;
+#ifdef CONFIG_SMP
+		else
+			base = per_cpu_ptr(&__tvec_bases, cpu);
+#endif
+
+		init_timer_cpu(base, cpu);
+	}
+}
+
+void __init init_timers(void)
+{
 	/* ensure there are enough low bits for flags in timer->base pointer */
 	BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK);
 
-	err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
-			       (void *)(long)smp_processor_id());
-	BUG_ON(err != NOTIFY_OK);
-
+	init_timer_cpus();
 	init_timer_stats();
-	register_cpu_notifier(&timers_nb);
+	timer_register_cpu_notifier();
 	open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
 }
 

kernel/time/timer_list.c

@@ -16,10 +16,10 @@
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
-#include <linux/tick.h>
 
 #include <asm/uaccess.h>
 
+#include "tick-internal.h"
 
 struct timer_list_iter {
 	int cpu;
@@ -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_state_shutdown) {
+			SEQ_printf(m, " shutdown: ");
+			print_name_offset(m, dev->set_state_shutdown);
+			SEQ_printf(m, "\n");
+		}
+
+		if (dev->set_state_periodic) {
+			SEQ_printf(m, " periodic: ");
+			print_name_offset(m, dev->set_state_periodic);
+			SEQ_printf(m, "\n");
+		}
+
+		if (dev->set_state_oneshot) {
+			SEQ_printf(m, " oneshot:  ");
+			print_name_offset(m, dev->set_state_oneshot);
+			SEQ_printf(m, "\n");
+		}
+
+		if (dev->tick_resume) {
+			SEQ_printf(m, " resume:   ");
+			print_name_offset(m, dev->tick_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