Merge branch 'linus' into timers/urgent

Get upstream changes so dependent patches can be applied.

kernel/time/Kconfig

@@ -56,7 +56,7 @@ menu "Timers subsystem"
 
 # Core internal switch. Selected by NO_HZ_COMMON / HIGH_RES_TIMERS. This is
 # only related to the tick functionality. Oneshot clockevent devices
-# are supported independ of this.
+# are supported independent of this.
 config TICK_ONESHOT
 	bool
 

kernel/time/clockevents.c

@@ -280,17 +280,22 @@ static int clockevents_program_min_delta(struct clock_event_device *dev)
 static int clockevents_program_min_delta(struct clock_event_device *dev)
 {
 	unsigned long long clc;
-	int64_t delta;
+	int64_t delta = 0;
+	int i;
 
-	delta = dev->min_delta_ns;
-	dev->next_event = ktime_add_ns(ktime_get(), delta);
+	for (i = 0; i < 10; i++) {
+		delta += dev->min_delta_ns;
+		dev->next_event = ktime_add_ns(ktime_get(), delta);
 
-	if (clockevent_state_shutdown(dev))
-		return 0;
+		if (clockevent_state_shutdown(dev))
+			return 0;
 
-	dev->retries++;
-	clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
-	return dev->set_next_event((unsigned long) clc, dev);
+		dev->retries++;
+		clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
+		if (dev->set_next_event((unsigned long) clc, dev) == 0)
+			return 0;
+	}
+	return -ETIME;
 }
 
 #endif /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */

kernel/time/hrtimer.c

@@ -758,9 +758,7 @@ void clock_was_set(void)
  */
 void hrtimers_resume(void)
 {
-	WARN_ONCE(!irqs_disabled(),
-		  KERN_INFO "hrtimers_resume() called with IRQs enabled!");
-
+	lockdep_assert_irqs_disabled();
 	/* Retrigger on the local CPU */
 	retrigger_next_event(NULL);
 	/* And schedule a retrigger for all others */

kernel/time/ntp.c

@@ -493,6 +493,67 @@ out:
 	return leap;
 }
 
+static void sync_hw_clock(struct work_struct *work);
+static DECLARE_DELAYED_WORK(sync_work, sync_hw_clock);
+
+static void sched_sync_hw_clock(struct timespec64 now,
+				unsigned long target_nsec, bool fail)
+
+{
+	struct timespec64 next;
+
+	getnstimeofday64(&next);
+	if (!fail)
+		next.tv_sec = 659;
+	else {
+		/*
+		 * Try again as soon as possible. Delaying long periods
+		 * decreases the accuracy of the work queue timer. Due to this
+		 * the algorithm is very likely to require a short-sleep retry
+		 * after the above long sleep to synchronize ts_nsec.
+		 */
+		next.tv_sec = 0;
+	}
+
+	/* Compute the needed delay that will get to tv_nsec == target_nsec */
+	next.tv_nsec = target_nsec - next.tv_nsec;
+	if (next.tv_nsec <= 0)
+		next.tv_nsec += NSEC_PER_SEC;
+	if (next.tv_nsec >= NSEC_PER_SEC) {
+		next.tv_sec++;
+		next.tv_nsec -= NSEC_PER_SEC;
+	}
+
+	queue_delayed_work(system_power_efficient_wq, &sync_work,
+			   timespec64_to_jiffies(&next));
+}
+
+static void sync_rtc_clock(void)
+{
+	unsigned long target_nsec;
+	struct timespec64 adjust, now;
+	int rc;
+
+	if (!IS_ENABLED(CONFIG_RTC_SYSTOHC))
+		return;
+
+	getnstimeofday64(&now);
+
+	adjust = now;
+	if (persistent_clock_is_local)
+		adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
+
+	/*
+	 * The current RTC in use will provide the target_nsec it wants to be
+	 * called at, and does rtc_tv_nsec_ok internally.
+	 */
+	rc = rtc_set_ntp_time(adjust, &target_nsec);
+	if (rc == -ENODEV)
+		return;
+
+	sched_sync_hw_clock(now, target_nsec, rc);
+}
+
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
 int __weak update_persistent_clock(struct timespec now)
 {
@@ -508,77 +569,76 @@ int __weak update_persistent_clock64(struct timespec64 now64)
 }
 #endif
 
-#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);
-
-static void sync_cmos_clock(struct work_struct *work)
+static bool sync_cmos_clock(void)
 {
+	static bool no_cmos;
 	struct timespec64 now;
-	struct timespec64 next;
-	int fail = 1;
+	struct timespec64 adjust;
+	int rc = -EPROTO;
+	long target_nsec = NSEC_PER_SEC / 2;
+
+	if (!IS_ENABLED(CONFIG_GENERIC_CMOS_UPDATE))
+		return false;
+
+	if (no_cmos)
+		return false;
 
 	/*
-	 * If we have an externally synchronized Linux clock, then update
-	 * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
-	 * called as close as possible to 500 ms before the new second starts.
-	 * This code is run on a timer.  If the clock is set, that timer
-	 * may not expire at the correct time.  Thus, we adjust...
-	 * We want the clock to be within a couple of ticks from the target.
+	 * Historically update_persistent_clock64() has followed x86
+	 * semantics, which match the MC146818A/etc RTC. This RTC will store
+	 * 'adjust' and then in .5s it will advance once second.
+	 *
+	 * Architectures are strongly encouraged to use rtclib and not
+	 * implement this legacy API.
 	 */
-	if (!ntp_synced()) {
-		/*
-		 * Not synced, exit, do not restart a timer (if one is
-		 * running, let it run out).
-		 */
-		return;
-	}
-
 	getnstimeofday64(&now);
-	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) {
-		struct timespec64 adjust = now;
-
-		fail = -ENODEV;
+	if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) {
 		if (persistent_clock_is_local)
 			adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
-#ifdef CONFIG_GENERIC_CMOS_UPDATE
-		fail = update_persistent_clock64(adjust);
-#endif
-
-#ifdef CONFIG_RTC_SYSTOHC
-		if (fail == -ENODEV)
-			fail = rtc_set_ntp_time(adjust);
-#endif
+		rc = update_persistent_clock64(adjust);
+		/*
+		 * The machine does not support update_persistent_clock64 even
+		 * though it defines CONFIG_GENERIC_CMOS_UPDATE.
+		 */
+		if (rc == -ENODEV) {
+			no_cmos = true;
+			return false;
+		}
 	}
 
-	next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2);
-	if (next.tv_nsec <= 0)
-		next.tv_nsec += NSEC_PER_SEC;
+	sched_sync_hw_clock(now, target_nsec, rc);
+	return true;
+}
 
-	if (!fail || fail == -ENODEV)
-		next.tv_sec = 659;
-	else
-		next.tv_sec = 0;
+/*
+ * If we have an externally synchronized Linux clock, then update RTC clock
+ * accordingly every ~11 minutes. Generally RTCs can only store second
+ * precision, but many RTCs will adjust the phase of their second tick to
+ * match the moment of update. This infrastructure arranges to call to the RTC
+ * set at the correct moment to phase synchronize the RTC second tick over
+ * with the kernel clock.
+ */
+static void sync_hw_clock(struct work_struct *work)
+{
+	if (!ntp_synced())
+		return;
 
-	if (next.tv_nsec >= NSEC_PER_SEC) {
-		next.tv_sec++;
-		next.tv_nsec -= NSEC_PER_SEC;
-	}
-	queue_delayed_work(system_power_efficient_wq,
-			   &sync_cmos_work, timespec64_to_jiffies(&next));
+	if (sync_cmos_clock())
+		return;
+
+	sync_rtc_clock();
 }
 
 void ntp_notify_cmos_timer(void)
 {
-	queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0);
+	if (!ntp_synced())
+		return;
+
+	if (IS_ENABLED(CONFIG_GENERIC_CMOS_UPDATE) ||
+	    IS_ENABLED(CONFIG_RTC_SYSTOHC))
+		queue_delayed_work(system_power_efficient_wq, &sync_work, 0);
 }
 
-#else
-void ntp_notify_cmos_timer(void) { }
-#endif
-
-
 /*
  * Propagate a new txc->status value into the NTP state:
  */
@@ -654,67 +714,6 @@ static inline void process_adjtimex_modes(struct timex *txc,
 }
 
 
-
-/**
- * ntp_validate_timex - Ensures the timex is ok for use in do_adjtimex
- */
-int ntp_validate_timex(struct timex *txc)
-{
-	if (txc->modes & ADJ_ADJTIME) {
-		/* singleshot must not be used with any other mode bits */
-		if (!(txc->modes & ADJ_OFFSET_SINGLESHOT))
-			return -EINVAL;
-		if (!(txc->modes & ADJ_OFFSET_READONLY) &&
-		    !capable(CAP_SYS_TIME))
-			return -EPERM;
-	} else {
-		/* In order to modify anything, you gotta be super-user! */
-		 if (txc->modes && !capable(CAP_SYS_TIME))
-			return -EPERM;
-		/*
-		 * if the quartz is off by more than 10% then
-		 * something is VERY wrong!
-		 */
-		if (txc->modes & ADJ_TICK &&
-		    (txc->tick <  900000/USER_HZ ||
-		     txc->tick > 1100000/USER_HZ))
-			return -EINVAL;
-	}
-
-	if (txc->modes & ADJ_SETOFFSET) {
-		/* In order to inject time, you gotta be super-user! */
-		if (!capable(CAP_SYS_TIME))
-			return -EPERM;
-
-		if (txc->modes & ADJ_NANO) {
-			struct timespec ts;
-
-			ts.tv_sec = txc->time.tv_sec;
-			ts.tv_nsec = txc->time.tv_usec;
-			if (!timespec_inject_offset_valid(&ts))
-				return -EINVAL;
-
-		} else {
-			if (!timeval_inject_offset_valid(&txc->time))
-				return -EINVAL;
-		}
-	}
-
-	/*
-	 * Check for potential multiplication overflows that can
-	 * only happen on 64-bit systems:
-	 */
-	if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) {
-		if (LLONG_MIN / PPM_SCALE > txc->freq)
-			return -EINVAL;
-		if (LLONG_MAX / PPM_SCALE < txc->freq)
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-
 /*
  * adjtimex mainly allows reading (and writing, if superuser) of
  * kernel time-keeping variables. used by xntpd.

kernel/time/ntp_internal.h

@@ -8,7 +8,6 @@ extern void ntp_clear(void);
 extern u64 ntp_tick_length(void);
 extern ktime_t ntp_get_next_leap(void);
 extern int second_overflow(time64_t secs);
-extern int ntp_validate_timex(struct timex *);
 extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *);
 extern void __hardpps(const struct timespec64 *, const struct timespec64 *);
 #endif /* _LINUX_NTP_INTERNAL_H */

kernel/time/posix-cpu-timers.c

@@ -603,7 +603,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	/*
 	 * Disarm any old timer after extracting its expiry time.
 	 */
-	WARN_ON_ONCE(!irqs_disabled());
+	lockdep_assert_irqs_disabled();
 
 	ret = 0;
 	old_incr = timer->it.cpu.incr;
@@ -1034,7 +1034,7 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
 	/*
 	 * Now re-arm for the new expiry time.
 	 */
-	WARN_ON_ONCE(!irqs_disabled());
+	lockdep_assert_irqs_disabled();
 	arm_timer(timer);
 unlock:
 	unlock_task_sighand(p, &flags);
@@ -1125,7 +1125,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	struct k_itimer *timer, *next;
 	unsigned long flags;
 
-	WARN_ON_ONCE(!irqs_disabled());
+	lockdep_assert_irqs_disabled();
 
 	/*
 	 * The fast path checks that there are no expired thread or thread

kernel/time/posix-stubs.c

@@ -117,8 +117,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		const struct timespec __user *, rqtp,
 		struct timespec __user *, rmtp)
 {
-	struct timespec64 t64;
-	struct timespec t;
+	struct timespec64 t;
 
 	switch (which_clock) {
 	case CLOCK_REALTIME:
@@ -129,16 +128,15 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		return -EINVAL;
 	}
 
-	if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
+	if (get_timespec64(&t, rqtp))
 		return -EFAULT;
-	t64 = timespec_to_timespec64(t);
-	if (!timespec64_valid(&t64))
+	if (!timespec64_valid(&t))
 		return -EINVAL;
 	if (flags & TIMER_ABSTIME)
 		rmtp = NULL;
 	current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
 	current->restart_block.nanosleep.rmtp = rmtp;
-	return hrtimer_nanosleep(&t64, flags & TIMER_ABSTIME ?
+	return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ?
 				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
 				 which_clock);
 }
@@ -203,8 +201,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
 		       struct compat_timespec __user *, rqtp,
 		       struct compat_timespec __user *, rmtp)
 {
-	struct timespec64 t64;
-	struct timespec t;
+	struct timespec64 t;
 
 	switch (which_clock) {
 	case CLOCK_REALTIME:
@@ -215,16 +212,15 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
 		return -EINVAL;
 	}
 
-	if (compat_get_timespec(&t, rqtp))
+	if (compat_get_timespec64(&t, rqtp))
 		return -EFAULT;
-	t64 = timespec_to_timespec64(t);
-	if (!timespec64_valid(&t64))
+	if (!timespec64_valid(&t))
 		return -EINVAL;
 	if (flags & TIMER_ABSTIME)
 		rmtp = NULL;
 	current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
 	current->restart_block.nanosleep.compat_rmtp = rmtp;
-	return hrtimer_nanosleep(&t64, flags & TIMER_ABSTIME ?
+	return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ?
 				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
 				 which_clock);
 }

kernel/time/tick-oneshot.c

@@ -33,6 +33,7 @@ int tick_program_event(ktime_t expires, int force)
 		 * We don't need the clock event device any more, stop it.
 		 */
 		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED);
+		dev->next_event = KTIME_MAX;
 		return 0;
 	}
 

kernel/time/tick-sched.c

@@ -27,6 +27,7 @@
 #include <linux/irq_work.h>
 #include <linux/posix-timers.h>
 #include <linux/context_tracking.h>
+#include <linux/mm.h>
 
 #include <asm/irq_regs.h>
 
@@ -165,7 +166,6 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 
 #ifdef CONFIG_NO_HZ_FULL
 cpumask_var_t tick_nohz_full_mask;
-cpumask_var_t housekeeping_mask;
 bool tick_nohz_full_running;
 static atomic_t tick_dep_mask;
 
@@ -198,7 +198,7 @@ static bool check_tick_dependency(atomic_t *dep)
 
 static bool can_stop_full_tick(int cpu, struct tick_sched *ts)
 {
-	WARN_ON_ONCE(!irqs_disabled());
+	lockdep_assert_irqs_disabled();
 
 	if (unlikely(!cpu_online(cpu)))
 		return false;
@@ -385,20 +385,13 @@ out:
 	local_irq_restore(flags);
 }
 
-/* Parse the boot-time nohz CPU list from the kernel parameters. */
-static int __init tick_nohz_full_setup(char *str)
+/* Get the boot-time nohz CPU list from the kernel parameters. */
+void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 {
 	alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
-	if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
-		pr_warn("NO_HZ: Incorrect nohz_full cpumask\n");
-		free_bootmem_cpumask_var(tick_nohz_full_mask);
-		return 1;
-	}
+	cpumask_copy(tick_nohz_full_mask, cpumask);
 	tick_nohz_full_running = true;
-
-	return 1;
 }
-__setup("nohz_full=", tick_nohz_full_setup);
 
 static int tick_nohz_cpu_down(unsigned int cpu)
 {
@@ -437,13 +430,6 @@ void __init tick_nohz_init(void)
 			return;
 	}
 
-	if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) {
-		WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n");
-		cpumask_clear(tick_nohz_full_mask);
-		tick_nohz_full_running = false;
-		return;
-	}
-
 	/*
 	 * Full dynticks uses irq work to drive the tick rescheduling on safe
 	 * locking contexts. But then we need irq work to raise its own
@@ -452,7 +438,6 @@ void __init tick_nohz_init(void)
 	if (!arch_irq_work_has_interrupt()) {
 		pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n");
 		cpumask_clear(tick_nohz_full_mask);
-		cpumask_copy(housekeeping_mask, cpu_possible_mask);
 		tick_nohz_full_running = false;
 		return;
 	}
@@ -465,9 +450,6 @@ void __init tick_nohz_init(void)
 		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
 	}
 
-	cpumask_andnot(housekeeping_mask,
-		       cpu_possible_mask, tick_nohz_full_mask);
-
 	for_each_cpu(cpu, tick_nohz_full_mask)
 		context_tracking_cpu_set(cpu);
 
@@ -477,12 +459,6 @@ void __init tick_nohz_init(void)
 	WARN_ON(ret < 0);
 	pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
 		cpumask_pr_args(tick_nohz_full_mask));
-
-	/*
-	 * We need at least one CPU to handle housekeeping work such
-	 * as timekeeping, unbound timers, workqueues, ...
-	 */
-	WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
 }
 #endif
 
@@ -787,6 +763,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	if (!ts->tick_stopped) {
 		calc_load_nohz_start();
 		cpu_load_update_nohz_start();
+		quiet_vmstat();
 
 		ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
 		ts->tick_stopped = 1;
@@ -960,8 +937,7 @@ void tick_nohz_idle_enter(void)
 {
 	struct tick_sched *ts;
 
-	WARN_ON_ONCE(irqs_disabled());
-
+	lockdep_assert_irqs_enabled();
 	/*
 	 * Update the idle state in the scheduler domain hierarchy
 	 * when tick_nohz_stop_sched_tick() is called from the idle loop.

kernel/time/time.c

@@ -82,7 +82,7 @@ SYSCALL_DEFINE1(time, time_t __user *, tloc)
 
 SYSCALL_DEFINE1(stime, time_t __user *, tptr)
 {
-	struct timespec tv;
+	struct timespec64 tv;
 	int err;
 
 	if (get_user(tv.tv_sec, tptr))
@@ -90,11 +90,11 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr)
 
 	tv.tv_nsec = 0;
 
-	err = security_settime(&tv, NULL);
+	err = security_settime64(&tv, NULL);
 	if (err)
 		return err;
 
-	do_settimeofday(&tv);
+	do_settimeofday64(&tv);
 	return 0;
 }
 
@@ -122,7 +122,7 @@ COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc)
 
 COMPAT_SYSCALL_DEFINE1(stime, compat_time_t __user *, tptr)
 {
-	struct timespec tv;
+	struct timespec64 tv;
 	int err;
 
 	if (get_user(tv.tv_sec, tptr))
@@ -130,11 +130,11 @@ COMPAT_SYSCALL_DEFINE1(stime, compat_time_t __user *, tptr)
 
 	tv.tv_nsec = 0;
 
-	err = security_settime(&tv, NULL);
+	err = security_settime64(&tv, NULL);
 	if (err)
 		return err;
 
-	do_settimeofday(&tv);
+	do_settimeofday64(&tv);
 	return 0;
 }
 
@@ -157,40 +157,6 @@ 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.
- *
- * This is ugly, but preferable to the alternatives.  Otherwise we
- * would either need to write a program to do it in /etc/rc (and risk
- * confusion if the program gets run more than once; it would also be
- * hard to make the program warp the clock precisely n hours)  or
- * compile in the timezone information into the kernel.  Bad, bad....
- *
- *						- TYT, 1992-01-01
- *
- * The best thing to do is to keep the CMOS clock in universal time (UTC)
- * as real UNIX machines always do it. This avoids all headaches about
- * daylight saving times and warping kernel clocks.
- */
-static inline void warp_clock(void)
-{
-	if (sys_tz.tz_minuteswest != 0) {
-		struct timespec adjust;
-
-		persistent_clock_is_local = 1;
-		adjust.tv_sec = sys_tz.tz_minuteswest * 60;
-		adjust.tv_nsec = 0;
-		timekeeping_inject_offset(&adjust);
-	}
-}
-
 /*
  * In case for some reason the CMOS clock has not already been running
  * in UTC, but in some local time: The first time we set the timezone,
@@ -224,7 +190,7 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz
 		if (firsttime) {
 			firsttime = 0;
 			if (!tv)
-				warp_clock();
+				timekeeping_warp_clock();
 		}
 	}
 	if (tv)
@@ -441,6 +407,7 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0,
 }
 EXPORT_SYMBOL(mktime64);
 
+#if __BITS_PER_LONG == 32
 /**
  * set_normalized_timespec - set timespec sec and nsec parts and normalize
  *
@@ -501,6 +468,7 @@ struct timespec ns_to_timespec(const s64 nsec)
 	return ts;
 }
 EXPORT_SYMBOL(ns_to_timespec);
+#endif
 
 /**
  * ns_to_timeval - Convert nanoseconds to timeval
@@ -520,7 +488,6 @@ struct timeval ns_to_timeval(const s64 nsec)
 }
 EXPORT_SYMBOL(ns_to_timeval);
 
-#if BITS_PER_LONG == 32
 /**
  * set_normalized_timespec - set timespec sec and nsec parts and normalize
  *
@@ -581,7 +548,7 @@ struct timespec64 ns_to_timespec64(const s64 nsec)
 	return ts;
 }
 EXPORT_SYMBOL(ns_to_timespec64);
-#endif
+
 /**
  * msecs_to_jiffies: - convert milliseconds to jiffies
  * @m:	time in milliseconds
@@ -852,24 +819,6 @@ unsigned long nsecs_to_jiffies(u64 n)
 }
 EXPORT_SYMBOL_GPL(nsecs_to_jiffies);
 
-/*
- * Add two timespec values and do a safety check for overflow.
- * It's assumed that both values are valid (>= 0)
- */
-struct timespec timespec_add_safe(const struct timespec lhs,
-				  const struct timespec rhs)
-{
-	struct timespec res;
-
-	set_normalized_timespec(&res, lhs.tv_sec + rhs.tv_sec,
-				lhs.tv_nsec + rhs.tv_nsec);
-
-	if (res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)
-		res.tv_sec = TIME_T_MAX;
-
-	return res;
-}
-
 /*
  * Add two timespec64 values and do a safety check for overflow.
  * It's assumed that both values are valid (>= 0).

kernel/time/timekeeping.c

@@ -60,8 +60,27 @@ struct tk_fast {
 	struct tk_read_base	base[2];
 };
 
-static struct tk_fast tk_fast_mono ____cacheline_aligned;
-static struct tk_fast tk_fast_raw  ____cacheline_aligned;
+/* Suspend-time cycles value for halted fast timekeeper. */
+static u64 cycles_at_suspend;
+
+static u64 dummy_clock_read(struct clocksource *cs)
+{
+	return cycles_at_suspend;
+}
+
+static struct clocksource dummy_clock = {
+	.read = dummy_clock_read,
+};
+
+static struct tk_fast tk_fast_mono ____cacheline_aligned = {
+	.base[0] = { .clock = &dummy_clock, },
+	.base[1] = { .clock = &dummy_clock, },
+};
+
+static struct tk_fast tk_fast_raw  ____cacheline_aligned = {
+	.base[0] = { .clock = &dummy_clock, },
+	.base[1] = { .clock = &dummy_clock, },
+};
 
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
@@ -477,17 +496,39 @@ u64 notrace ktime_get_boot_fast_ns(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
 
-/* Suspend-time cycles value for halted fast timekeeper. */
-static u64 cycles_at_suspend;
 
-static u64 dummy_clock_read(struct clocksource *cs)
+/*
+ * See comment for __ktime_get_fast_ns() vs. timestamp ordering
+ */
+static __always_inline u64 __ktime_get_real_fast_ns(struct tk_fast *tkf)
 {
-	return cycles_at_suspend;
+	struct tk_read_base *tkr;
+	unsigned int seq;
+	u64 now;
+
+	do {
+		seq = raw_read_seqcount_latch(&tkf->seq);
+		tkr = tkf->base + (seq & 0x01);
+		now = ktime_to_ns(tkr->base_real);
+
+		now += timekeeping_delta_to_ns(tkr,
+				clocksource_delta(
+					tk_clock_read(tkr),
+					tkr->cycle_last,
+					tkr->mask));
+	} while (read_seqcount_retry(&tkf->seq, seq));
+
+	return now;
 }
 
-static struct clocksource dummy_clock = {
-	.read = dummy_clock_read,
-};
+/**
+ * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime.
+ */
+u64 ktime_get_real_fast_ns(void)
+{
+	return __ktime_get_real_fast_ns(&tk_fast_mono);
+}
+EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns);
 
 /**
  * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource.
@@ -507,6 +548,7 @@ static void halt_fast_timekeeper(struct timekeeper *tk)
 	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
 	cycles_at_suspend = tk_clock_read(tkr);
 	tkr_dummy.clock = &dummy_clock;
+	tkr_dummy.base_real = tkr->base + tk->offs_real;
 	update_fast_timekeeper(&tkr_dummy, &tk_fast_mono);
 
 	tkr = &tk->tkr_raw;
@@ -654,6 +696,7 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
 	update_vsyscall(tk);
 	update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
 
+	tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real;
 	update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
 	update_fast_timekeeper(&tk->tkr_raw,  &tk_fast_raw);
 
@@ -1264,33 +1307,31 @@ EXPORT_SYMBOL(do_settimeofday64);
  *
  * Adds or subtracts an offset value from the current time.
  */
-int timekeeping_inject_offset(struct timespec *ts)
+static int timekeeping_inject_offset(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
-	struct timespec64 ts64, tmp;
+	struct timespec64 tmp;
 	int ret = 0;
 
-	if (!timespec_inject_offset_valid(ts))
+	if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC)
 		return -EINVAL;
 
-	ts64 = timespec_to_timespec64(*ts);
-
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 
 	timekeeping_forward_now(tk);
 
 	/* Make sure the proposed value is valid */
-	tmp = timespec64_add(tk_xtime(tk),  ts64);
-	if (timespec64_compare(&tk->wall_to_monotonic, &ts64) > 0 ||
+	tmp = timespec64_add(tk_xtime(tk), *ts);
+	if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 ||
 	    !timespec64_valid_strict(&tmp)) {
 		ret = -EINVAL;
 		goto error;
 	}
 
-	tk_xtime_add(tk, &ts64);
-	tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts64));
+	tk_xtime_add(tk, ts);
+	tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *ts));
 
 error: /* even if we error out, we forwarded the time, so call update */
 	timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
@@ -1303,7 +1344,40 @@ error: /* even if we error out, we forwarded the time, so call update */
 
 	return ret;
 }
-EXPORT_SYMBOL(timekeeping_inject_offset);
+
+/*
+ * 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.
+ *
+ * This is ugly, but preferable to the alternatives.  Otherwise we
+ * would either need to write a program to do it in /etc/rc (and risk
+ * confusion if the program gets run more than once; it would also be
+ * hard to make the program warp the clock precisely n hours)  or
+ * compile in the timezone information into the kernel.  Bad, bad....
+ *
+ *						- TYT, 1992-01-01
+ *
+ * The best thing to do is to keep the CMOS clock in universal time (UTC)
+ * as real UNIX machines always do it. This avoids all headaches about
+ * daylight saving times and warping kernel clocks.
+ */
+void timekeeping_warp_clock(void)
+{
+	if (sys_tz.tz_minuteswest != 0) {
+		struct timespec64 adjust;
+
+		persistent_clock_is_local = 1;
+		adjust.tv_sec = sys_tz.tz_minuteswest * 60;
+		adjust.tv_nsec = 0;
+		timekeeping_inject_offset(&adjust);
+	}
+}
 
 /**
  * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic
@@ -2247,6 +2321,72 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
 	return base;
 }
 
+/**
+ * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex
+ */
+static int timekeeping_validate_timex(struct timex *txc)
+{
+	if (txc->modes & ADJ_ADJTIME) {
+		/* singleshot must not be used with any other mode bits */
+		if (!(txc->modes & ADJ_OFFSET_SINGLESHOT))
+			return -EINVAL;
+		if (!(txc->modes & ADJ_OFFSET_READONLY) &&
+		    !capable(CAP_SYS_TIME))
+			return -EPERM;
+	} else {
+		/* In order to modify anything, you gotta be super-user! */
+		if (txc->modes && !capable(CAP_SYS_TIME))
+			return -EPERM;
+		/*
+		 * if the quartz is off by more than 10% then
+		 * something is VERY wrong!
+		 */
+		if (txc->modes & ADJ_TICK &&
+		    (txc->tick <  900000/USER_HZ ||
+		     txc->tick > 1100000/USER_HZ))
+			return -EINVAL;
+	}
+
+	if (txc->modes & ADJ_SETOFFSET) {
+		/* In order to inject time, you gotta be super-user! */
+		if (!capable(CAP_SYS_TIME))
+			return -EPERM;
+
+		/*
+		 * Validate if a timespec/timeval used to inject a time
+		 * offset is valid.  Offsets can be postive or negative, so
+		 * we don't check tv_sec. The value of the timeval/timespec
+		 * is the sum of its fields,but *NOTE*:
+		 * The field tv_usec/tv_nsec must always be non-negative and
+		 * we can't have more nanoseconds/microseconds than a second.
+		 */
+		if (txc->time.tv_usec < 0)
+			return -EINVAL;
+
+		if (txc->modes & ADJ_NANO) {
+			if (txc->time.tv_usec >= NSEC_PER_SEC)
+				return -EINVAL;
+		} else {
+			if (txc->time.tv_usec >= USEC_PER_SEC)
+				return -EINVAL;
+		}
+	}
+
+	/*
+	 * Check for potential multiplication overflows that can
+	 * only happen on 64-bit systems:
+	 */
+	if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) {
+		if (LLONG_MIN / PPM_SCALE > txc->freq)
+			return -EINVAL;
+		if (LLONG_MAX / PPM_SCALE < txc->freq)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+
 /**
  * do_adjtimex() - Accessor function to NTP __do_adjtimex function
  */
@@ -2259,12 +2399,12 @@ int do_adjtimex(struct timex *txc)
 	int ret;
 
 	/* Validate the data before disabling interrupts */
-	ret = ntp_validate_timex(txc);
+	ret = timekeeping_validate_timex(txc);
 	if (ret)
 		return ret;
 
 	if (txc->modes & ADJ_SETOFFSET) {
-		struct timespec delta;
+		struct timespec64 delta;
 		delta.tv_sec  = txc->time.tv_sec;
 		delta.tv_nsec = txc->time.tv_usec;
 		if (!(txc->modes & ADJ_NANO))

kernel/time/timekeeping.h

@@ -11,7 +11,7 @@ extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq,
 
 extern int timekeeping_valid_for_hres(void);
 extern u64 timekeeping_max_deferment(void);
-extern int timekeeping_inject_offset(struct timespec *ts);
+extern void timekeeping_warp_clock(void);
 extern int timekeeping_suspend(void);
 extern void timekeeping_resume(void);
 

kernel/time/timer.c

@@ -610,7 +610,7 @@ static bool timer_fixup_init(void *addr, enum debug_obj_state state)
 }
 
 /* Stub timer callback for improperly used timers. */
-static void stub_timer(unsigned long data)
+static void stub_timer(struct timer_list *unused)
 {
 	WARN_ON(1);
 }
@@ -626,7 +626,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
 
 	switch (state) {
 	case ODEBUG_STATE_NOTAVAILABLE:
-		setup_timer(timer, stub_timer, 0);
+		timer_setup(timer, stub_timer, 0);
 		return true;
 
 	case ODEBUG_STATE_ACTIVE:
@@ -665,7 +665,7 @@ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state)
 
 	switch (state) {
 	case ODEBUG_STATE_NOTAVAILABLE:
-		setup_timer(timer, stub_timer, 0);
+		timer_setup(timer, stub_timer, 0);
 		return true;
 	default:
 		return false;
@@ -929,8 +929,11 @@ static struct timer_base *lock_timer_base(struct timer_list *timer,
 	}
 }
 
+#define MOD_TIMER_PENDING_ONLY		0x01
+#define MOD_TIMER_REDUCE		0x02
+
 static inline int
-__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
+__mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options)
 {
 	struct timer_base *base, *new_base;
 	unsigned int idx = UINT_MAX;
@@ -950,7 +953,11 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		 * larger granularity than you would get from adding a new
 		 * timer with this expiry.
 		 */
-		if (timer->expires == expires)
+		long diff = timer->expires - expires;
+
+		if (!diff)
+			return 1;
+		if (options & MOD_TIMER_REDUCE && diff <= 0)
 			return 1;
 
 		/*
@@ -962,6 +969,12 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		base = lock_timer_base(timer, &flags);
 		forward_timer_base(base);
 
+		if (timer_pending(timer) && (options & MOD_TIMER_REDUCE) &&
+		    time_before_eq(timer->expires, expires)) {
+			ret = 1;
+			goto out_unlock;
+		}
+
 		clk = base->clk;
 		idx = calc_wheel_index(expires, clk);
 
@@ -971,7 +984,10 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		 * subsequent call will exit in the expires check above.
 		 */
 		if (idx == timer_get_idx(timer)) {
-			timer->expires = expires;
+			if (!(options & MOD_TIMER_REDUCE))
+				timer->expires = expires;
+			else if (time_after(timer->expires, expires))
+				timer->expires = expires;
 			ret = 1;
 			goto out_unlock;
 		}
@@ -981,7 +997,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 	}
 
 	ret = detach_if_pending(timer, base, false);
-	if (!ret && pending_only)
+	if (!ret && (options & MOD_TIMER_PENDING_ONLY))
 		goto out_unlock;
 
 	debug_activate(timer, expires);
@@ -1042,7 +1058,7 @@ out_unlock:
  */
 int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 {
-	return __mod_timer(timer, expires, true);
+	return __mod_timer(timer, expires, MOD_TIMER_PENDING_ONLY);
 }
 EXPORT_SYMBOL(mod_timer_pending);
 
@@ -1068,10 +1084,25 @@ EXPORT_SYMBOL(mod_timer_pending);
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
-	return __mod_timer(timer, expires, false);
+	return __mod_timer(timer, expires, 0);
 }
 EXPORT_SYMBOL(mod_timer);
 
+/**
+ * timer_reduce - Modify a timer's timeout if it would reduce the timeout
+ * @timer:	The timer to be modified
+ * @expires:	New timeout in jiffies
+ *
+ * timer_reduce() is very similar to mod_timer(), except that it will only
+ * modify a running timer if that would reduce the expiration time (it will
+ * start a timer that isn't running).
+ */
+int timer_reduce(struct timer_list *timer, unsigned long expires)
+{
+	return __mod_timer(timer, expires, MOD_TIMER_REDUCE);
+}
+EXPORT_SYMBOL(timer_reduce);
+
 /**
  * add_timer - start a timer
  * @timer: the timer to be added
@@ -1560,8 +1591,11 @@ static int collect_expired_timers(struct timer_base *base,
 		 * jiffies, otherwise forward to the next expiry time:
 		 */
 		if (time_after(next, jiffies)) {
-			/* The call site will increment clock! */
-			base->clk = jiffies - 1;
+			/*
+			 * The call site will increment base->clk and then
+			 * terminate the expiry loop immediately.
+			 */
+			base->clk = jiffies;
 			return 0;
 		}
 		base->clk = next;
@@ -1668,9 +1702,20 @@ void run_local_timers(void)
 	raise_softirq(TIMER_SOFTIRQ);
 }
 
-static void process_timeout(unsigned long __data)
+/*
+ * Since schedule_timeout()'s timer is defined on the stack, it must store
+ * the target task on the stack as well.
+ */
+struct process_timer {
+	struct timer_list timer;
+	struct task_struct *task;
+};
+
+static void process_timeout(struct timer_list *t)
 {
-	wake_up_process((struct task_struct *)__data);
+	struct process_timer *timeout = from_timer(timeout, t, timer);
+
+	wake_up_process(timeout->task);
 }
 
 /**
@@ -1704,7 +1749,7 @@ static void process_timeout(unsigned long __data)
  */
 signed long __sched schedule_timeout(signed long timeout)
 {
-	struct timer_list timer;
+	struct process_timer timer;
 	unsigned long expire;
 
 	switch (timeout)
@@ -1738,13 +1783,14 @@ signed long __sched schedule_timeout(signed long timeout)
 
 	expire = timeout + jiffies;
 
-	setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
-	__mod_timer(&timer, expire, false);
+	timer.task = current;
+	timer_setup_on_stack(&timer.timer, process_timeout, 0);
+	__mod_timer(&timer.timer, expire, 0);
 	schedule();
-	del_singleshot_timer_sync(&timer);
+	del_singleshot_timer_sync(&timer.timer);
 
 	/* Remove the timer from the object tracker */
-	destroy_timer_on_stack(&timer);
+	destroy_timer_on_stack(&timer.timer);
 
 	timeout = expire - jiffies;