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

Pull timer changes from Ingo Molnar:
 "Main changes:

   - ntp: Add CONFIG_RTC_SYSTOHC: a generic RTC driver facility
     complementing the existing CONFIG_RTC_HCTOSYS, which uses NTP to
     keep the hardware clock updated.

   - posix-timers: Fix clock_adjtime to always return timex data on
     success.  This is changing the ABI, but no breakage was expected
     and found - caution is warranted nevertheless.

   - platform persistent clock improvements/cleanups.

   - clockevents: refactor timer broadcast handling to be more generic
     and less duplicated with matching architecture code (mostly ARM
     motivated.)

   - various fixes and cleanups"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  timers/x86/hpet: Use HPET_COUNTER to specify the hpet counter in vread_hpet()
  posix-cpu-timers: Fix nanosleep task_struct leak
  clockevents: Fix generic broadcast for FEAT_C3STOP
  time, Fix setting of hardware clock in NTP code
  hrtimer: Prevent hrtimer_enqueue_reprogram race
  clockevents: Add generic timer broadcast function
  clockevents: Add generic timer broadcast receiver
  timekeeping: Switch HAS_PERSISTENT_CLOCK to ALWAYS_USE_PERSISTENT_CLOCK
  x86/time/rtc: Don't print extended CMOS year when reading RTC
  x86: Select HAS_PERSISTENT_CLOCK on x86
  timekeeping: Add CONFIG_HAS_PERSISTENT_CLOCK option
  rtc: Skip the suspend/resume handling if persistent clock exist
  timekeeping: Add persistent_clock_exist flag
  posix-timers: Fix clock_adjtime to always return timex data on success
  Round the calculated scale factor in set_cyc2ns_scale()
  NTP: Add a CONFIG_RTC_SYSTOHC configuration
  MAINTAINERS: Update John Stultz's email
  time: create __getnstimeofday for WARNless calls

kernel/hrtimer.c

@@ -642,21 +642,9 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
  * and expiry check is done in the hrtimer_interrupt or in the softirq.
  */
 static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
-					    struct hrtimer_clock_base *base,
-					    int wakeup)
+					    struct hrtimer_clock_base *base)
 {
-	if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
-		if (wakeup) {
-			raw_spin_unlock(&base->cpu_base->lock);
-			raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-			raw_spin_lock(&base->cpu_base->lock);
-		} else
-			__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-
-		return 1;
-	}
-
-	return 0;
+	return base->cpu_base->hres_active && hrtimer_reprogram(timer, base);
 }
 
 static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
@@ -737,8 +725,7 @@ static inline int hrtimer_switch_to_hres(void) { return 0; }
 static inline void
 hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
 static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
-					    struct hrtimer_clock_base *base,
-					    int wakeup)
+					    struct hrtimer_clock_base *base)
 {
 	return 0;
 }
@@ -997,8 +984,21 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	 *
 	 * XXX send_remote_softirq() ?
 	 */
-	if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
-		hrtimer_enqueue_reprogram(timer, new_base, wakeup);
+	if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)
+		&& hrtimer_enqueue_reprogram(timer, new_base)) {
+		if (wakeup) {
+			/*
+			 * We need to drop cpu_base->lock to avoid a
+			 * lock ordering issue vs. rq->lock.
+			 */
+			raw_spin_unlock(&new_base->cpu_base->lock);
+			raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+			local_irq_restore(flags);
+			return ret;
+		} else {
+			__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+		}
+	}
 
 	unlock_hrtimer_base(timer, &flags);
 

kernel/posix-cpu-timers.c

@@ -1417,8 +1417,10 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 		while (!signal_pending(current)) {
 			if (timer.it.cpu.expires.sched == 0) {
 				/*
-				 * Our timer fired and was reset.
+				 * Our timer fired and was reset, below
+				 * deletion can not fail.
 				 */
+				posix_cpu_timer_del(&timer);
 				spin_unlock_irq(&timer.it_lock);
 				return 0;
 			}
@@ -1436,9 +1438,26 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 		 * We were interrupted by a signal.
 		 */
 		sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp);
-		posix_cpu_timer_set(&timer, 0, &zero_it, it);
+		error = posix_cpu_timer_set(&timer, 0, &zero_it, it);
+		if (!error) {
+			/*
+			 * Timer is now unarmed, deletion can not fail.
+			 */
+			posix_cpu_timer_del(&timer);
+		}
 		spin_unlock_irq(&timer.it_lock);
 
+		while (error == TIMER_RETRY) {
+			/*
+			 * We need to handle case when timer was or is in the
+			 * middle of firing. In other cases we already freed
+			 * resources.
+			 */
+			spin_lock_irq(&timer.it_lock);
+			error = posix_cpu_timer_del(&timer);
+			spin_unlock_irq(&timer.it_lock);
+		}
+
 		if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) {
 			/*
 			 * It actually did fire already.

kernel/posix-timers.c

@@ -997,7 +997,7 @@ SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
 
 	err = kc->clock_adj(which_clock, &ktx);
 
-	if (!err && copy_to_user(utx, &ktx, sizeof(ktx)))
+	if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx)))
 		return -EFAULT;
 
 	return err;

kernel/time.c

@@ -114,6 +114,12 @@ SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv,
 	return 0;
 }
 
+/*
+ * Indicates if there is an offset between the system clock and the hardware
+ * clock/persistent clock/rtc.
+ */
+int persistent_clock_is_local;
+
 /*
  * Adjust the time obtained from the CMOS to be UTC time instead of
  * local time.
@@ -135,6 +141,8 @@ static inline void warp_clock(void)
 	struct timespec adjust;
 
 	adjust = current_kernel_time();
+	if (sys_tz.tz_minuteswest != 0)
+		persistent_clock_is_local = 1;
 	adjust.tv_sec += sys_tz.tz_minuteswest * 60;
 	do_settimeofday(&adjust);
 }

kernel/time/Kconfig

@@ -12,6 +12,11 @@ config CLOCKSOURCE_WATCHDOG
 config ARCH_CLOCKSOURCE_DATA
 	bool
 
+# Platforms has a persistent clock
+config ALWAYS_USE_PERSISTENT_CLOCK
+	bool
+	default n
+
 # Timekeeping vsyscall support
 config GENERIC_TIME_VSYSCALL
 	bool
@@ -38,6 +43,10 @@ config GENERIC_CLOCKEVENTS_BUILD
 	default y
 	depends on GENERIC_CLOCKEVENTS
 
+# Architecture can handle broadcast in a driver-agnostic way
+config ARCH_HAS_TICK_BROADCAST
+	bool
+
 # Clockevents broadcasting infrastructure
 config GENERIC_CLOCKEVENTS_BROADCAST
 	bool

kernel/time/ntp.c

@@ -15,6 +15,7 @@
 #include <linux/time.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/rtc.h>
 
 #include "tick-internal.h"
 
@@ -483,8 +484,7 @@ out:
 	return leap;
 }
 
-#ifdef CONFIG_GENERIC_CMOS_UPDATE
-
+#if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC)
 static void sync_cmos_clock(struct work_struct *work);
 
 static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock);
@@ -510,14 +510,26 @@ static void sync_cmos_clock(struct work_struct *work)
 	}
 
 	getnstimeofday(&now);
-	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2)
-		fail = update_persistent_clock(now);
+	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2) {
+		struct timespec adjust = now;
+
+		fail = -ENODEV;
+		if (persistent_clock_is_local)
+			adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
+#ifdef CONFIG_GENERIC_CMOS_UPDATE
+		fail = update_persistent_clock(adjust);
+#endif
+#ifdef CONFIG_RTC_SYSTOHC
+		if (fail == -ENODEV)
+			fail = rtc_set_ntp_time(adjust);
+#endif
+	}
 
 	next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2);
 	if (next.tv_nsec <= 0)
 		next.tv_nsec += NSEC_PER_SEC;
 
-	if (!fail)
+	if (!fail || fail == -ENODEV)
 		next.tv_sec = 659;
 	else
 		next.tv_sec = 0;

kernel/time/tick-broadcast.c

@@ -18,6 +18,7 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
 
 #include "tick-internal.h"
 
@@ -86,6 +87,22 @@ int tick_is_broadcast_device(struct clock_event_device *dev)
 	return (dev && tick_broadcast_device.evtdev == dev);
 }
 
+static void err_broadcast(const struct cpumask *mask)
+{
+	pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n");
+}
+
+static void tick_device_setup_broadcast_func(struct clock_event_device *dev)
+{
+	if (!dev->broadcast)
+		dev->broadcast = tick_broadcast;
+	if (!dev->broadcast) {
+		pr_warn_once("%s depends on broadcast, but no broadcast function available\n",
+			     dev->name);
+		dev->broadcast = err_broadcast;
+	}
+}
+
 /*
  * Check, if the device is disfunctional and a place holder, which
  * needs to be handled by the broadcast device.
@@ -105,6 +122,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 	 */
 	if (!tick_device_is_functional(dev)) {
 		dev->event_handler = tick_handle_periodic;
+		tick_device_setup_broadcast_func(dev);
 		cpumask_set_cpu(cpu, tick_get_broadcast_mask());
 		tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
 		ret = 1;
@@ -116,15 +134,33 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 		 */
 		if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) {
 			int cpu = smp_processor_id();
-
 			cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
 			tick_broadcast_clear_oneshot(cpu);
+		} else {
+			tick_device_setup_broadcast_func(dev);
 		}
 	}
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 	return ret;
 }
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+int tick_receive_broadcast(void)
+{
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+	struct clock_event_device *evt = td->evtdev;
+
+	if (!evt)
+		return -ENODEV;
+
+	if (!evt->event_handler)
+		return -EINVAL;
+
+	evt->event_handler(evt);
+	return 0;
+}
+#endif
+
 /*
  * Broadcast the event to the cpus, which are set in the mask (mangled).
  */

kernel/time/timekeeping.c

@@ -29,6 +29,9 @@ static struct timekeeper timekeeper;
 /* 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->xtime_nsec >= ((u64)NSEC_PER_SEC << tk->shift)) {
@@ -264,19 +267,18 @@ static void timekeeping_forward_now(struct timekeeper *tk)
 }
 
 /**
- * getnstimeofday - Returns the time of day in a timespec
+ * __getnstimeofday - Returns the time of day in a timespec.
  * @ts:		pointer to the timespec to be set
  *
- * Returns the time of day in a timespec.
+ * Updates the time of day in the timespec.
+ * Returns 0 on success, or -ve when suspended (timespec will be undefined).
  */
-void getnstimeofday(struct timespec *ts)
+int __getnstimeofday(struct timespec *ts)
 {
 	struct timekeeper *tk = &timekeeper;
 	unsigned long seq;
 	s64 nsecs = 0;
 
-	WARN_ON(timekeeping_suspended);
-
 	do {
 		seq = read_seqbegin(&tk->lock);
 
@@ -287,6 +289,26 @@ void getnstimeofday(struct timespec *ts)
 
 	ts->tv_nsec = 0;
 	timespec_add_ns(ts, nsecs);
+
+	/*
+	 * Do not bail out early, in case there were callers still using
+	 * the value, even in the face of the WARN_ON.
+	 */
+	if (unlikely(timekeeping_suspended))
+		return -EAGAIN;
+	return 0;
+}
+EXPORT_SYMBOL(__getnstimeofday);
+
+/**
+ * getnstimeofday - Returns the time of day in a timespec.
+ * @ts:		pointer to the timespec to be set
+ *
+ * Returns the time of day in a timespec (WARN if suspended).
+ */
+void getnstimeofday(struct timespec *ts)
+{
+	WARN_ON(__getnstimeofday(ts));
 }
 EXPORT_SYMBOL(getnstimeofday);
 
@@ -640,12 +662,14 @@ void __init timekeeping_init(void)
 	struct timespec now, boot, tmp;
 
 	read_persistent_clock(&now);
+
 	if (!timespec_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;
 
 	read_boot_clock(&boot);
 	if (!timespec_valid_strict(&boot)) {
@@ -718,11 +742,12 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
 {
 	struct timekeeper *tk = &timekeeper;
 	unsigned long flags;
-	struct timespec ts;
 
-	/* Make sure we don't set the clock twice */
-	read_persistent_clock(&ts);
-	if (!(ts.tv_sec == 0 && ts.tv_nsec == 0))
+	/*
+	 * Make sure we don't set the clock twice, as timekeeping_resume()
+	 * already did it
+	 */
+	if (has_persistent_clock())
 		return;
 
 	write_seqlock_irqsave(&tk->lock, flags);