Merge branch 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (34 commits)
  time: Prevent 32 bit overflow with set_normalized_timespec()
  clocksource: Delay clocksource down rating to late boot
  clocksource: clocksource_select must be called with mutex locked
  clocksource: Resolve cpu hotplug dead lock with TSC unstable, fix crash
  timers: Drop a function prototype
  clocksource: Resolve cpu hotplug dead lock with TSC unstable
  timer.c: Fix S/390 comments
  timekeeping: Fix invalid getboottime() value
  timekeeping: Fix up read_persistent_clock() breakage on sh
  timekeeping: Increase granularity of read_persistent_clock(), build fix
  time: Introduce CLOCK_REALTIME_COARSE
  x86: Do not unregister PIT clocksource on PIT oneshot setup/shutdown
  clocksource: Avoid clocksource watchdog circular locking dependency
  clocksource: Protect the watchdog rating changes with clocksource_mutex
  clocksource: Call clocksource_change_rating() outside of watchdog_lock
  timekeeping: Introduce read_boot_clock
  timekeeping: Increase granularity of read_persistent_clock()
  timekeeping: Update clocksource with stop_machine
  timekeeping: Add timekeeper read_clock helper functions
  timekeeping: Move NTP adjusted clock multiplier to struct timekeeper
  ...

Fix trivial conflict due to MIPS lemote -> loongson renaming.

arch/arm/plat-omap/common.c

@@ -253,11 +253,8 @@ static struct clocksource clocksource_32k = {
  */
 unsigned long long sched_clock(void)
 {
-	unsigned long long ret;
-
-	ret = (unsigned long long)clocksource_32k.read(&clocksource_32k);
-	ret = (ret * clocksource_32k.mult_orig) >> clocksource_32k.shift;
-	return ret;
+	return clocksource_cyc2ns(clocksource_32k.read(&clocksource_32k),
+				  clocksource_32k.mult, clocksource_32k.shift);
 }
 
 static int __init omap_init_clocksource_32k(void)

arch/m68knommu/kernel/time.c

@@ -72,9 +72,10 @@ static unsigned long read_rtc_mmss(void)
 	return  mktime(year, mon, day, hour, min, sec);
 }
 
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
-	return read_rtc_mmss();
+	ts->tv_sec = read_rtc_mmss();
+	ts->tv_nsec = 0;
 }
 
 int update_persistent_clock(struct timespec now)

arch/mips/dec/time.c

@@ -18,7 +18,7 @@
 #include <asm/dec/ioasic.h>
 #include <asm/dec/machtype.h>
 
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	unsigned int year, mon, day, hour, min, sec, real_year;
 	unsigned long flags;
@@ -53,7 +53,8 @@ unsigned long read_persistent_clock(void)
 
 	year += real_year - 72 + 2000;
 
-	return mktime(year, mon, day, hour, min, sec);
+	ts->tv_sec = mktime(year, mon, day, hour, min, sec);
+	ts->tv_nsec = 0;
 }
 
 /*

arch/mips/lasat/ds1603.c

@@ -135,7 +135,7 @@ static void rtc_end_op(void)
 	lasat_ndelay(1000);
 }
 
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	unsigned long word;
 	unsigned long flags;
@@ -147,7 +147,8 @@ unsigned long read_persistent_clock(void)
 	rtc_end_op();
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
-	return word;
+	ts->tv_sec = word;
+	ts->tv_nsec = 0;
 }
 
 int rtc_mips_set_mmss(unsigned long time)

arch/mips/lasat/sysctl.c

@@ -92,10 +92,12 @@ static int rtctmp;
 int proc_dolasatrtc(ctl_table *table, int write, struct file *filp,
 		       void *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct timespec ts;
 	int r;
 
 	if (!write) {
-		rtctmp = read_persistent_clock();
+		read_persistent_clock(&ts);
+		rtctmp = ts.tv_sec;
 		/* check for time < 0 and set to 0 */
 		if (rtctmp < 0)
 			rtctmp = 0;
@@ -134,9 +136,11 @@ int sysctl_lasat_rtc(ctl_table *table,
 		    void *oldval, size_t *oldlenp,
 		    void *newval, size_t newlen)
 {
+	struct timespec ts;
 	int r;
 
-	rtctmp = read_persistent_clock();
+	read_persistent_clock(&ts);
+	rtctmp = ts.tv_sec;
 	if (rtctmp < 0)
 		rtctmp = 0;
 	r = sysctl_intvec(table, oldval, oldlenp, newval, newlen);

arch/mips/loongson/common/time.c

@@ -21,7 +21,8 @@ void __init plat_time_init(void)
 	mips_hpt_frequency = cpu_clock_freq / 2;
 }
 
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
-	return mc146818_get_cmos_time();
+	ts->tv_sec = return mc146818_get_cmos_time();
+	ts->tv_nsec = 0;
 }

arch/mips/mti-malta/malta-time.c

@@ -100,9 +100,10 @@ static unsigned int __init estimate_cpu_frequency(void)
 	return count;
 }
 
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
-	return mc146818_get_cmos_time();
+	ts->tv_sec = mc146818_get_cmos_time();
+	ts->tv_nsec = 0;
 }
 
 static void __init plat_perf_setup(void)

arch/mips/pmc-sierra/yosemite/setup.c

@@ -70,7 +70,7 @@ void __init bus_error_init(void)
 }
 
 
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	unsigned int year, month, day, hour, min, sec;
 	unsigned long flags;
@@ -92,7 +92,8 @@ unsigned long read_persistent_clock(void)
 	m48t37_base->control = 0x00;
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
-	return mktime(year, month, day, hour, min, sec);
+	ts->tv_sec = mktime(year, month, day, hour, min, sec);
+	ts->tv_nsec = 0;
 }
 
 int rtc_mips_set_time(unsigned long tim)

arch/mips/sibyte/swarm/setup.c

@@ -87,19 +87,26 @@ enum swarm_rtc_type {
 
 enum swarm_rtc_type swarm_rtc_type;
 
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
+	unsigned long sec;
+
 	switch (swarm_rtc_type) {
 	case RTC_XICOR:
-		return xicor_get_time();
+		sec = xicor_get_time();
+		break;
 
 	case RTC_M4LT81:
-		return m41t81_get_time();
+		sec = m41t81_get_time();
+		break;
 
 	case RTC_NONE:
 	default:
-		return mktime(2000, 1, 1, 0, 0, 0);
+		sec = mktime(2000, 1, 1, 0, 0, 0);
+		break;
 	}
+	ts->tv_sec = sec;
+	tv->tv_nsec = 0;
 }
 
 int rtc_mips_set_time(unsigned long sec)

arch/mips/sni/time.c

@@ -182,7 +182,8 @@ void __init plat_time_init(void)
 	setup_pit_timer();
 }
 
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
-	return -1;
+	ts->tv_sec = -1;
+	ts->tv_nsec = 0;
 }

arch/powerpc/kernel/time.c

@@ -774,11 +774,12 @@ int update_persistent_clock(struct timespec now)
 	return ppc_md.set_rtc_time(&tm);
 }
 
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	struct rtc_time tm;
 	static int first = 1;
 
+	ts->tv_nsec = 0;
 	/* XXX this is a litle fragile but will work okay in the short term */
 	if (first) {
 		first = 0;
@@ -786,13 +787,17 @@ unsigned long read_persistent_clock(void)
 			timezone_offset = ppc_md.time_init();
 
 		/* get_boot_time() isn't guaranteed to be safe to call late */
-		if (ppc_md.get_boot_time)
-			return ppc_md.get_boot_time() -timezone_offset;
+		if (ppc_md.get_boot_time) {
+			ts->tv_sec = ppc_md.get_boot_time() - timezone_offset;
+			return;
+		}
+	}
+	if (!ppc_md.get_rtc_time) {
+		ts->tv_sec = 0;
+		return;
 	}
-	if (!ppc_md.get_rtc_time)
-		return 0;
 	ppc_md.get_rtc_time(&tm);
-	return mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday,
+	ts->tv_sec = mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday,
 			    tm.tm_hour, tm.tm_min, tm.tm_sec);
 }
 

arch/s390/kernel/time.c

@@ -184,12 +184,14 @@ static void timing_alert_interrupt(__u16 code)
 static void etr_reset(void);
 static void stp_reset(void);
 
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
-	struct timespec ts;
+	tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, ts);
+}
 
-	tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, &ts);
-	return ts.tv_sec;
+void read_boot_clock(struct timespec *ts)
+{
+	tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts);
 }
 
 static cycle_t read_tod_clock(struct clocksource *cs)
@@ -207,6 +209,10 @@ static struct clocksource clocksource_tod = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
+struct clocksource * __init clocksource_default_clock(void)
+{
+	return &clocksource_tod;
+}
 
 void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
 {
@@ -244,10 +250,6 @@ void update_vsyscall_tz(void)
  */
 void __init time_init(void)
 {
-	struct timespec ts;
-	unsigned long flags;
-	cycle_t now;
-
 	/* Reset time synchronization interfaces. */
 	etr_reset();
 	stp_reset();
@@ -263,26 +265,6 @@ void __init time_init(void)
 	if (clocksource_register(&clocksource_tod) != 0)
 		panic("Could not register TOD clock source");
 
-	/*
-	 * The TOD clock is an accurate clock. The xtime should be
-	 * initialized in a way that the difference between TOD and
-	 * xtime is reasonably small. Too bad that timekeeping_init
-	 * sets xtime.tv_nsec to zero. In addition the clock source
-	 * change from the jiffies clock source to the TOD clock
-	 * source add another error of up to 1/HZ second. The same
-	 * function sets wall_to_monotonic to a value that is too
-	 * small for /proc/uptime to be accurate.
-	 * Reset xtime and wall_to_monotonic to sane values.
-	 */
-	write_seqlock_irqsave(&xtime_lock, flags);
-	now = get_clock();
-	tod_to_timeval(now - TOD_UNIX_EPOCH, &xtime);
-	clocksource_tod.cycle_last = now;
-	clocksource_tod.raw_time = xtime;
-	tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, &ts);
-	set_normalized_timespec(&wall_to_monotonic, -ts.tv_sec, -ts.tv_nsec);
-	write_sequnlock_irqrestore(&xtime_lock, flags);
-
 	/* Enable TOD clock interrupts on the boot cpu. */
 	init_cpu_timer();
 

arch/sh/kernel/time.c

@@ -39,11 +39,9 @@ void (*rtc_sh_get_time)(struct timespec *) = null_rtc_get_time;
 int (*rtc_sh_set_time)(const time_t) = null_rtc_set_time;
 
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
-	struct timespec tv;
-	rtc_sh_get_time(&tv);
-	return tv.tv_sec;
+	rtc_sh_get_time(ts);
 }
 
 int update_persistent_clock(struct timespec now)

arch/x86/include/asm/vgtod.h

@@ -21,6 +21,7 @@ struct vsyscall_gtod_data {
 		u32	shift;
 	} clock;
 	struct timespec wall_to_monotonic;
+	struct timespec wall_time_coarse;
 };
 extern struct vsyscall_gtod_data __vsyscall_gtod_data
 __section_vsyscall_gtod_data;

arch/x86/kernel/i8253.c

@@ -19,12 +19,6 @@
 DEFINE_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
-#ifdef CONFIG_X86_32
-static void pit_disable_clocksource(void);
-#else
-static inline void pit_disable_clocksource(void) { }
-#endif
-
 /*
  * HPET replaces the PIT, when enabled. So we need to know, which of
  * the two timers is used
@@ -57,12 +51,10 @@ static void init_pit_timer(enum clock_event_mode mode,
 			outb_pit(0, PIT_CH0);
 			outb_pit(0, PIT_CH0);
 		}
-		pit_disable_clocksource();
 		break;
 
 	case CLOCK_EVT_MODE_ONESHOT:
 		/* One shot setup */
-		pit_disable_clocksource();
 		outb_pit(0x38, PIT_MODE);
 		break;
 
@@ -200,17 +192,6 @@ static struct clocksource pit_cs = {
 	.shift		= 20,
 };
 
-static void pit_disable_clocksource(void)
-{
-	/*
-	 * Use mult to check whether it is registered or not
-	 */
-	if (pit_cs.mult) {
-		clocksource_unregister(&pit_cs);
-		pit_cs.mult = 0;
-	}
-}
-
 static int __init init_pit_clocksource(void)
 {
 	 /*

arch/x86/kernel/rtc.c

@@ -178,7 +178,7 @@ static int set_rtc_mmss(unsigned long nowtime)
 }
 
 /* not static: needed by APM */
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	unsigned long retval, flags;
 
@@ -186,7 +186,8 @@ unsigned long read_persistent_clock(void)
 	retval = get_wallclock();
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
-	return retval;
+	ts->tv_sec = retval;
+	ts->tv_nsec = 0;
 }
 
 int update_persistent_clock(struct timespec now)

arch/x86/kernel/tsc.c

@@ -744,10 +744,16 @@ static cycle_t __vsyscall_fn vread_tsc(void)
 }
 #endif
 
+static void resume_tsc(void)
+{
+	clocksource_tsc.cycle_last = 0;
+}
+
 static struct clocksource clocksource_tsc = {
 	.name                   = "tsc",
 	.rating                 = 300,
 	.read                   = read_tsc,
+	.resume			= resume_tsc,
 	.mask                   = CLOCKSOURCE_MASK(64),
 	.shift                  = 22,
 	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS |
@@ -761,13 +767,15 @@ void mark_tsc_unstable(char *reason)
 {
 	if (!tsc_unstable) {
 		tsc_unstable = 1;
-		printk("Marking TSC unstable due to %s\n", reason);
+		printk(KERN_INFO "Marking TSC unstable due to %s\n", reason);
 		/* Change only the rating, when not registered */
 		if (clocksource_tsc.mult)
-			clocksource_change_rating(&clocksource_tsc, 0);
-		else
+			clocksource_mark_unstable(&clocksource_tsc);
+		else {
+			clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
 			clocksource_tsc.rating = 0;
 		}
+	}
 }
 
 EXPORT_SYMBOL_GPL(mark_tsc_unstable);

arch/x86/kernel/vsyscall_64.c

@@ -87,6 +87,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
 	vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
 	vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
 	vsyscall_gtod_data.wall_to_monotonic = wall_to_monotonic;
+	vsyscall_gtod_data.wall_time_coarse = __current_kernel_time();
 	write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
 }
 

arch/x86/vdso/vclock_gettime.c

@@ -86,14 +86,47 @@ notrace static noinline int do_monotonic(struct timespec *ts)
 	return 0;
 }
 
+notrace static noinline int do_realtime_coarse(struct timespec *ts)
+{
+	unsigned long seq;
+	do {
+		seq = read_seqbegin(&gtod->lock);
+		ts->tv_sec = gtod->wall_time_coarse.tv_sec;
+		ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
+	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	return 0;
+}
+
+notrace static noinline int do_monotonic_coarse(struct timespec *ts)
+{
+	unsigned long seq, ns, secs;
+	do {
+		seq = read_seqbegin(&gtod->lock);
+		secs = gtod->wall_time_coarse.tv_sec;
+		ns = gtod->wall_time_coarse.tv_nsec;
+		secs += gtod->wall_to_monotonic.tv_sec;
+		ns += gtod->wall_to_monotonic.tv_nsec;
+	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	vset_normalized_timespec(ts, secs, ns);
+	return 0;
+}
+
 notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 {
-	if (likely(gtod->sysctl_enabled && gtod->clock.vread))
+	if (likely(gtod->sysctl_enabled))
 		switch (clock) {
 		case CLOCK_REALTIME:
+			if (likely(gtod->clock.vread))
 				return do_realtime(ts);
+			break;
 		case CLOCK_MONOTONIC:
+			if (likely(gtod->clock.vread))
 				return do_monotonic(ts);
+			break;
+		case CLOCK_REALTIME_COARSE:
+			return do_realtime_coarse(ts);
+		case CLOCK_MONOTONIC_COARSE:
+			return do_monotonic_coarse(ts);
 		}
 	return vdso_fallback_gettime(clock, ts);
 }

arch/xtensa/kernel/time.c

@@ -59,9 +59,8 @@ static struct irqaction timer_irqaction = {
 
 void __init time_init(void)
 {
-	xtime.tv_nsec = 0;
-	xtime.tv_sec = read_persistent_clock();
-
+	/* FIXME: xtime&wall_to_monotonic are set in timekeeping_init. */
+	read_persistent_clock(&xtime);
 	set_normalized_timespec(&wall_to_monotonic,
 		-xtime.tv_sec, -xtime.tv_nsec);
 

include/linux/clocksource.h

@@ -14,6 +14,7 @@
 #include <linux/list.h>
 #include <linux/cache.h>
 #include <linux/timer.h>
+#include <linux/init.h>
 #include <asm/div64.h>
 #include <asm/io.h>
 
@@ -148,14 +149,11 @@ extern u64 timecounter_cyc2time(struct timecounter *tc,
  * @disable:		optional function to disable the clocksource
  * @mask:		bitmask for two's complement
  *			subtraction of non 64 bit counters
- * @mult:		cycle to nanosecond multiplier (adjusted by NTP)
- * @mult_orig:		cycle to nanosecond multiplier (unadjusted by NTP)
+ * @mult:		cycle to nanosecond multiplier
  * @shift:		cycle to nanosecond divisor (power of two)
  * @flags:		flags describing special properties
  * @vread:		vsyscall based read
  * @resume:		resume function for the clocksource, if necessary
- * @cycle_interval:	Used internally by timekeeping core, please ignore.
- * @xtime_interval:	Used internally by timekeeping core, please ignore.
  */
 struct clocksource {
 	/*
@@ -169,7 +167,6 @@ struct clocksource {
 	void (*disable)(struct clocksource *cs);
 	cycle_t mask;
 	u32 mult;
-	u32 mult_orig;
 	u32 shift;
 	unsigned long flags;
 	cycle_t (*vread)(void);
@@ -181,19 +178,12 @@ struct clocksource {
 #define CLKSRC_FSYS_MMIO_SET(mmio, addr)      do { } while (0)
 #endif
 
-	/* timekeeping specific data, ignore */
-	cycle_t cycle_interval;
-	u64	xtime_interval;
-	u32	raw_interval;
 	/*
 	 * Second part is written at each timer interrupt
 	 * Keep it in a different cache line to dirty no
 	 * more than one cache line.
 	 */
 	cycle_t cycle_last ____cacheline_aligned_in_smp;
-	u64 xtime_nsec;
-	s64 error;
-	struct timespec raw_time;
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 	/* Watchdog related data, used by the framework */
@@ -202,8 +192,6 @@ struct clocksource {
 #endif
 };
 
-extern struct clocksource *clock;	/* current clocksource */
-
 /*
  * Clock source flags bits::
  */
@@ -212,6 +200,7 @@ extern struct clocksource *clock;	/* current clocksource */
 
 #define CLOCK_SOURCE_WATCHDOG			0x10
 #define CLOCK_SOURCE_VALID_FOR_HRES		0x20
+#define CLOCK_SOURCE_UNSTABLE			0x40
 
 /* simplify initialization of mask field */
 #define CLOCKSOURCE_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)
@@ -268,108 +257,15 @@ static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant)
 }
 
 /**
- * clocksource_read: - Access the clocksource's current cycle value
- * @cs:		pointer to clocksource being read
- *
- * Uses the clocksource to return the current cycle_t value
- */
-static inline cycle_t clocksource_read(struct clocksource *cs)
-{
-	return cs->read(cs);
-}
-
-/**
- * clocksource_enable: - enable clocksource
- * @cs:		pointer to clocksource
- *
- * Enables the specified clocksource. The clocksource callback
- * function should start up the hardware and setup mult and field
- * members of struct clocksource to reflect hardware capabilities.
- */
-static inline int clocksource_enable(struct clocksource *cs)
-{
-	int ret = 0;
-
-	if (cs->enable)
-		ret = cs->enable(cs);
-
-	/*
-	 * The frequency may have changed while the clocksource
-	 * was disabled. If so the code in ->enable() must update
-	 * the mult value to reflect the new frequency. Make sure
-	 * mult_orig follows this change.
-	 */
-	cs->mult_orig = cs->mult;
-
-	return ret;
-}
-
-/**
- * clocksource_disable: - disable clocksource
- * @cs:		pointer to clocksource
- *
- * Disables the specified clocksource. The clocksource callback
- * function should power down the now unused hardware block to
- * save power.
- */
-static inline void clocksource_disable(struct clocksource *cs)
-{
-	/*
-	 * Save mult_orig in mult so clocksource_enable() can
-	 * restore the value regardless if ->enable() updates
-	 * the value of mult or not.
-	 */
-	cs->mult = cs->mult_orig;
-
-	if (cs->disable)
-		cs->disable(cs);
-}
-
-/**
- * cyc2ns - converts clocksource cycles to nanoseconds
- * @cs:		Pointer to clocksource
- * @cycles:	Cycles
+ * clocksource_cyc2ns - converts clocksource cycles to nanoseconds
  *
- * Uses the clocksource and ntp ajdustment to convert cycle_ts to nanoseconds.
+ * Converts cycles to nanoseconds, using the given mult and shift.
  *
  * XXX - This could use some mult_lxl_ll() asm optimization
  */
-static inline s64 cyc2ns(struct clocksource *cs, cycle_t cycles)
-{
-	u64 ret = (u64)cycles;
-	ret = (ret * cs->mult) >> cs->shift;
-	return ret;
-}
-
-/**
- * clocksource_calculate_interval - Calculates a clocksource interval struct
- *
- * @c:		Pointer to clocksource.
- * @length_nsec: Desired interval length in nanoseconds.
- *
- * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
- * pair and interval request.
- *
- * Unless you're the timekeeping code, you should not be using this!
- */
-static inline void clocksource_calculate_interval(struct clocksource *c,
-					  	  unsigned long length_nsec)
+static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift)
 {
-	u64 tmp;
-
-	/* Do the ns -> cycle conversion first, using original mult */
-	tmp = length_nsec;
-	tmp <<= c->shift;
-	tmp += c->mult_orig/2;
-	do_div(tmp, c->mult_orig);
-
-	c->cycle_interval = (cycle_t)tmp;
-	if (c->cycle_interval == 0)
-		c->cycle_interval = 1;
-
-	/* Go back from cycles -> shifted ns, this time use ntp adjused mult */
-	c->xtime_interval = (u64)c->cycle_interval * c->mult;
-	c->raw_interval = ((u64)c->cycle_interval * c->mult_orig) >> c->shift;
+	return ((u64) cycles * mult) >> shift;
 }
 
 
@@ -380,6 +276,8 @@ extern void clocksource_touch_watchdog(void);
 extern struct clocksource* clocksource_get_next(void);
 extern void clocksource_change_rating(struct clocksource *cs, int rating);
 extern void clocksource_resume(void);
+extern struct clocksource * __init __weak clocksource_default_clock(void);
+extern void clocksource_mark_unstable(struct clocksource *cs);
 
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL
 extern void update_vsyscall(struct timespec *ts, struct clocksource *c);
@@ -394,4 +292,6 @@ static inline void update_vsyscall_tz(void)
 }
 #endif
 
+extern void timekeeping_notify(struct clocksource *clock);
+
 #endif /* _LINUX_CLOCKSOURCE_H */

include/linux/hrtimer.h

@@ -91,7 +91,6 @@ enum hrtimer_restart {
  * @function:	timer expiry callback function
  * @base:	pointer to the timer base (per cpu and per clock)
  * @state:	state information (See bit values above)
- * @cb_entry:	list head to enqueue an expired timer into the callback list
  * @start_site:	timer statistics field to store the site where the timer
  *		was started
  * @start_comm: timer statistics field to store the name of the process which
@@ -108,7 +107,6 @@ struct hrtimer {
 	enum hrtimer_restart		(*function)(struct hrtimer *);
 	struct hrtimer_clock_base	*base;
 	unsigned long			state;
-	struct list_head		cb_entry;
 #ifdef CONFIG_TIMER_STATS
 	int				start_pid;
 	void				*start_site;

include/linux/time.h

@@ -75,7 +75,7 @@ extern unsigned long mktime(const unsigned int year, const unsigned int mon,
 			    const unsigned int day, const unsigned int hour,
 			    const unsigned int min, const unsigned int sec);
 
-extern void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec);
+extern void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec);
 extern struct timespec timespec_add_safe(const struct timespec lhs,
 					 const struct timespec rhs);
 
@@ -101,7 +101,8 @@ extern struct timespec xtime;
 extern struct timespec wall_to_monotonic;
 extern seqlock_t xtime_lock;
 
-extern unsigned long read_persistent_clock(void);
+extern void read_persistent_clock(struct timespec *ts);
+extern void read_boot_clock(struct timespec *ts);
 extern int update_persistent_clock(struct timespec now);
 extern int no_sync_cmos_clock __read_mostly;
 void timekeeping_init(void);
@@ -109,6 +110,8 @@ extern int timekeeping_suspended;
 
 unsigned long get_seconds(void);
 struct timespec current_kernel_time(void);
+struct timespec __current_kernel_time(void); /* does not hold xtime_lock */
+struct timespec get_monotonic_coarse(void);
 
 #define CURRENT_TIME		(current_kernel_time())
 #define CURRENT_TIME_SEC	((struct timespec) { get_seconds(), 0 })
@@ -147,6 +150,7 @@ extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 extern int timekeeping_valid_for_hres(void);
 extern void update_wall_time(void);
 extern void update_xtime_cache(u64 nsec);
+extern void timekeeping_leap_insert(int leapsecond);
 
 struct tms;
 extern void do_sys_times(struct tms *);
@@ -241,6 +245,8 @@ struct itimerval {
 #define CLOCK_PROCESS_CPUTIME_ID	2
 #define CLOCK_THREAD_CPUTIME_ID		3
 #define CLOCK_MONOTONIC_RAW		4
+#define CLOCK_REALTIME_COARSE		5
+#define CLOCK_MONOTONIC_COARSE		6
 
 /*
  * The IDs of various hardware clocks:

include/linux/timer.h

@@ -173,11 +173,6 @@ extern int mod_timer_pinned(struct timer_list *timer, unsigned long expires);
  */
 #define NEXT_TIMER_MAX_DELTA	((1UL << 30) - 1)
 
-/*
- * Return when the next timer-wheel timeout occurs (in absolute jiffies),
- * locks the timer base:
- */
-extern unsigned long next_timer_interrupt(void);
 /*
  * Return when the next timer-wheel timeout occurs (in absolute jiffies),
  * locks the timer base and does the comparison against the given

kernel/hrtimer.c

@@ -48,37 +48,6 @@
 
 #include <asm/uaccess.h>
 
-/**
- * ktime_get - get the monotonic time in ktime_t format
- *
- * returns the time in ktime_t format
- */
-ktime_t ktime_get(void)
-{
-	struct timespec now;
-
-	ktime_get_ts(&now);
-
-	return timespec_to_ktime(now);
-}
-EXPORT_SYMBOL_GPL(ktime_get);
-
-/**
- * ktime_get_real - get the real (wall-) time in ktime_t format
- *
- * returns the time in ktime_t format
- */
-ktime_t ktime_get_real(void)
-{
-	struct timespec now;
-
-	getnstimeofday(&now);
-
-	return timespec_to_ktime(now);
-}
-
-EXPORT_SYMBOL_GPL(ktime_get_real);
-
 /*
  * The timer bases:
  *
@@ -106,31 +75,6 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 	}
 };
 
-/**
- * ktime_get_ts - get the monotonic clock in timespec format
- * @ts:		pointer to timespec variable
- *
- * The function calculates the monotonic clock from the realtime
- * clock and the wall_to_monotonic offset and stores the result
- * in normalized timespec format in the variable pointed to by @ts.
- */
-void ktime_get_ts(struct timespec *ts)
-{
-	struct timespec tomono;
-	unsigned long seq;
-
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		getnstimeofday(ts);
-		tomono = wall_to_monotonic;
-
-	} while (read_seqretry(&xtime_lock, seq));
-
-	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
-				ts->tv_nsec + tomono.tv_nsec);
-}
-EXPORT_SYMBOL_GPL(ktime_get_ts);
-
 /*
  * Get the coarse grained time at the softirq based on xtime and
  * wall_to_monotonic.
@@ -1155,7 +1099,6 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 		clock_id = CLOCK_MONOTONIC;
 
 	timer->base = &cpu_base->clock_base[clock_id];
-	INIT_LIST_HEAD(&timer->cb_entry);
 	hrtimer_init_timer_hres(timer);
 
 #ifdef CONFIG_TIMER_STATS

kernel/posix-timers.c

@@ -242,6 +242,25 @@ static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
 	return 0;
 }
 
+
+static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec *tp)
+{
+	*tp = current_kernel_time();
+	return 0;
+}
+
+static int posix_get_monotonic_coarse(clockid_t which_clock,
+						struct timespec *tp)
+{
+	*tp = get_monotonic_coarse();
+	return 0;
+}
+
+int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp)
+{
+	*tp = ktime_to_timespec(KTIME_LOW_RES);
+	return 0;
+}
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
@@ -262,10 +281,26 @@ static __init int init_posix_timers(void)
 		.timer_create = no_timer_create,
 		.nsleep = no_nsleep,
 	};
+	struct k_clock clock_realtime_coarse = {
+		.clock_getres = posix_get_coarse_res,
+		.clock_get = posix_get_realtime_coarse,
+		.clock_set = do_posix_clock_nosettime,
+		.timer_create = no_timer_create,
+		.nsleep = no_nsleep,
+	};
+	struct k_clock clock_monotonic_coarse = {
+		.clock_getres = posix_get_coarse_res,
+		.clock_get = posix_get_monotonic_coarse,
+		.clock_set = do_posix_clock_nosettime,
+		.timer_create = no_timer_create,
+		.nsleep = no_nsleep,
+	};
 
 	register_posix_clock(CLOCK_REALTIME, &clock_realtime);
 	register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
 	register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
+	register_posix_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
+	register_posix_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,

kernel/time.c

@@ -370,13 +370,20 @@ EXPORT_SYMBOL(mktime);
  *	0 <= tv_nsec < NSEC_PER_SEC
  * For negative values only the tv_sec field is negative !
  */
-void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec)
+void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec)
 {
 	while (nsec >= NSEC_PER_SEC) {
+		/*
+		 * The following asm() prevents the compiler from
+		 * optimising this loop into a modulo operation. See
+		 * also __iter_div_u64_rem() in include/linux/time.h
+		 */
+		asm("" : "+rm"(nsec));
 		nsec -= NSEC_PER_SEC;
 		++sec;
 	}
 	while (nsec < 0) {
+		asm("" : "+rm"(nsec));
 		nsec += NSEC_PER_SEC;
 		--sec;
 	}

kernel/time/jiffies.c

@@ -61,7 +61,6 @@ struct clocksource clocksource_jiffies = {
 	.read		= jiffies_read,
 	.mask		= 0xffffffff, /*32bits*/
 	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
-	.mult_orig	= NSEC_PER_JIFFY << JIFFIES_SHIFT,
 	.shift		= JIFFIES_SHIFT,
 };
 
@@ -71,3 +70,8 @@ static int __init init_jiffies_clocksource(void)
 }
 
 core_initcall(init_jiffies_clocksource);
+
+struct clocksource * __init __weak clocksource_default_clock(void)
+{
+	return &clocksource_jiffies;
+}

kernel/time/ntp.c

@@ -194,8 +194,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 	case TIME_OK:
 		break;
 	case TIME_INS:
-		xtime.tv_sec--;
-		wall_to_monotonic.tv_sec++;
+		timekeeping_leap_insert(-1);
 		time_state = TIME_OOP;
 		printk(KERN_NOTICE
 			"Clock: inserting leap second 23:59:60 UTC\n");
@@ -203,9 +202,8 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 		res = HRTIMER_RESTART;
 		break;
 	case TIME_DEL:
-		xtime.tv_sec++;
+		timekeeping_leap_insert(1);
 		time_tai--;
-		wall_to_monotonic.tv_sec--;
 		time_state = TIME_WAIT;
 		printk(KERN_NOTICE
 			"Clock: deleting leap second 23:59:59 UTC\n");
@@ -219,7 +217,6 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 			time_state = TIME_OK;
 		break;
 	}
-	update_vsyscall(&xtime, clock);
 
 	write_sequnlock(&xtime_lock);
 

kernel/timer.c

@@ -72,6 +72,7 @@ struct tvec_base {
 	spinlock_t lock;
 	struct timer_list *running_timer;
 	unsigned long timer_jiffies;
+	unsigned long next_timer;
 	struct tvec_root tv1;
 	struct tvec tv2;
 	struct tvec tv3;
@@ -622,6 +623,9 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 
 	if (timer_pending(timer)) {
 		detach_timer(timer, 0);
+		if (timer->expires == base->next_timer &&
+		    !tbase_get_deferrable(timer->base))
+			base->next_timer = base->timer_jiffies;
 		ret = 1;
 	} else {
 		if (pending_only)
@@ -663,6 +667,9 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 	}
 
 	timer->expires = expires;
+	if (time_before(timer->expires, base->next_timer) &&
+	    !tbase_get_deferrable(timer->base))
+		base->next_timer = timer->expires;
 	internal_add_timer(base, timer);
 
 out_unlock:
@@ -781,6 +788,9 @@ void add_timer_on(struct timer_list *timer, int cpu)
 	spin_lock_irqsave(&base->lock, flags);
 	timer_set_base(timer, base);
 	debug_timer_activate(timer);
+	if (time_before(timer->expires, base->next_timer) &&
+	    !tbase_get_deferrable(timer->base))
+		base->next_timer = timer->expires;
 	internal_add_timer(base, timer);
 	/*
 	 * Check whether the other CPU is idle and needs to be
@@ -817,6 +827,9 @@ int del_timer(struct timer_list *timer)
 		base = lock_timer_base(timer, &flags);
 		if (timer_pending(timer)) {
 			detach_timer(timer, 1);
+			if (timer->expires == base->next_timer &&
+			    !tbase_get_deferrable(timer->base))
+				base->next_timer = base->timer_jiffies;
 			ret = 1;
 		}
 		spin_unlock_irqrestore(&base->lock, flags);
@@ -850,6 +863,9 @@ int try_to_del_timer_sync(struct timer_list *timer)
 	ret = 0;
 	if (timer_pending(timer)) {
 		detach_timer(timer, 1);
+		if (timer->expires == base->next_timer &&
+		    !tbase_get_deferrable(timer->base))
+			base->next_timer = base->timer_jiffies;
 		ret = 1;
 	}
 out:
@@ -1007,8 +1023,8 @@ static inline void __run_timers(struct tvec_base *base)
 #ifdef CONFIG_NO_HZ
 /*
  * Find out when the next timer event is due to happen. This
- * is used on S/390 to stop all activity when a cpus is idle.
- * This functions needs to be called disabled.
+ * is used on S/390 to stop all activity when a CPU is idle.
+ * This function needs to be called with interrupts disabled.
  */
 static unsigned long __next_timer_interrupt(struct tvec_base *base)
 {
@@ -1134,7 +1150,9 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 	unsigned long expires;
 
 	spin_lock(&base->lock);
-	expires = __next_timer_interrupt(base);
+	if (time_before_eq(base->next_timer, base->timer_jiffies))
+		base->next_timer = __next_timer_interrupt(base);
+	expires = base->next_timer;
 	spin_unlock(&base->lock);
 
 	if (time_before_eq(expires, now))
@@ -1522,6 +1540,7 @@ static int __cpuinit init_timers_cpu(int cpu)
 		INIT_LIST_HEAD(base->tv1.vec + j);
 
 	base->timer_jiffies = jiffies;
+	base->next_timer = base->timer_jiffies;
 	return 0;
 }
 
@@ -1534,6 +1553,9 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea
 		timer = list_first_entry(head, struct timer_list, entry);
 		detach_timer(timer, 0);
 		timer_set_base(timer, new_base);
+		if (time_before(timer->expires, new_base->next_timer) &&
+		    !tbase_get_deferrable(timer->base))
+			new_base->next_timer = timer->expires;
 		internal_add_timer(new_base, timer);
 	}
 }