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

Pull core timer updates from Ingo Molnar:
 "The main changes in this cycle's merge are:

   - Implement shadow timekeeper to shorten in kernel reader side
     blocking, by Thomas Gleixner.

   - Posix timers enhancements by Pavel Emelyanov:

   - allocate timer ID per process, so that exact timer ID allocations
     can be re-created be checkpoint/restore code.

   - debuggability and tooling (/proc/PID/timers, etc.) improvements.

   - suspend/resume enhancements by Feng Tang: on certain new Intel Atom
     processors (Penwell and Cloverview), there is a feature that the
     TSC won't stop in S3 state, so the TSC value won't be reset to 0
     after resume.  This can be taken advantage of by the generic via
     the CLOCK_SOURCE_SUSPEND_NONSTOP flag: instead of using the RTC to
     recover/approximate sleep time, the main (and precise) clocksource
     can be used.

   - Fix /proc/timer_list for 4096 CPUs by Nathan Zimmer: on so many
     CPUs the file goes beyond 4MB of size and thus the current
     simplistic seqfile approach fails.  Convert /proc/timer_list to a
     proper seq_file with its own iterator.

   - Cleanups and refactorings of the core timekeeping code by John
     Stultz.

   - International Atomic Clock time is managed by the NTP code
     internally currently but not exposed externally.  Separate the TAI
     code out and add CLOCK_TAI support and TAI support to the hrtimer
     and posix-timer code, by John Stultz.

   - Add deep idle support enhacement to the broadcast clockevents core
     timer code, by Daniel Lezcano: add an opt-in CLOCK_EVT_FEAT_DYNIRQ
     clockevents feature (which will be utilized by future clockevents
     driver updates), which allows the use of IRQ affinities to avoid
     spurious wakeups of idle CPUs - the right CPU with an expiring
     timer will be woken.

   - Add new ARM bcm281xx clocksource driver, by Christian Daudt

   - ... various other fixes and cleanups"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (52 commits)
  clockevents: Set dummy handler on CPU_DEAD shutdown
  timekeeping: Update tk->cycle_last in resume
  posix-timers: Remove unused variable
  clockevents: Switch into oneshot mode even if broadcast registered late
  timer_list: Convert timer list to be a proper seq_file
  timer_list: Split timer_list_show_tickdevices
  posix-timers: Show sigevent info in proc file
  posix-timers: Introduce /proc/PID/timers file
  posix timers: Allocate timer id per process (v2)
  timekeeping: Make sure to notify hrtimers when TAI offset changes
  hrtimer: Fix ktime_add_ns() overflow on 32bit architectures
  hrtimer: Add expiry time overflow check in hrtimer_interrupt
  timekeeping: Shorten seq_count region
  timekeeping: Implement a shadow timekeeper
  timekeeping: Delay update of clock->cycle_last
  timekeeping: Store cycle_last value in timekeeper struct as well
  ntp: Remove ntp_lock, using the timekeeping locks to protect ntp state
  timekeeping: Simplify tai updating from do_adjtimex
  timekeeping: Hold timekeepering locks in do_adjtimex and hardpps
  timekeeping: Move ADJ_SETOFFSET to top level do_adjtimex()
  ...

9 files changed, 76 insertions, 89 deletions

diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index bf02471d7e7..f11289519c3 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -6,6 +6,7 @@ config ARCH_BCM
 	select ARM_ERRATA_764369 if SMP
 	select ARM_GIC
 	select CPU_V7
+	select CLKSRC_OF
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_TIME
 	select GPIO_BCM
diff --git a/arch/arm/mach-bcm/board_bcm.c b/arch/arm/mach-bcm/board_bcm.c
index f0f9abafad2..25959354047 100644
--- a/arch/arm/mach-bcm/board_bcm.c
+++ b/arch/arm/mach-bcm/board_bcm.c
@@ -16,14 +16,11 @@
 #include <linux/device.h>
 #include <linux/platform_device.h>
 #include <linux/irqchip.h>
+#include <linux/clocksource.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 
-static void timer_init(void)
-{
-}
-
 
 static void __init board_init(void)
 {
@@ -35,7 +32,7 @@ static const char * const bcm11351_dt_compat[] = { "bcm,bcm11351", NULL, };
 
 DT_MACHINE_START(BCM11351_DT, "Broadcom Application Processor")
 	.init_irq = irqchip_init,
-	.init_time = timer_init,
+	.init_time = clocksource_of_init,
 	.init_machine = board_init,
 	.dt_compat = bcm11351_dt_compat,
 MACHINE_END
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d75b48c11be..e93ccb9b1cc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -120,6 +120,7 @@ config X86
 	select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
 	select OLD_SIGACTION if X86_32
 	select COMPAT_OLD_SIGACTION if IA32_EMULATION
+	select RTC_LIB
 
 config INSTRUCTION_DECODER
 	def_bool y
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index ac10df72925..6ce47980025 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -100,6 +100,7 @@
 #define X86_FEATURE_AMD_DCM     (3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF	(3*32+28) /* APERFMPERF */
 #define X86_FEATURE_EAGER_FPU	(3*32+29) /* "eagerfpu" Non lazy FPU restore */
+#define X86_FEATURE_NONSTOP_TSC_S3 (3*32+30) /* TSC doesn't stop in S3 state */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 1905ce98bee..e7ae0d89e7e 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -96,6 +96,18 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 			sched_clock_stable = 1;
 	}
 
+	/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
+	if (c->x86 == 6) {
+		switch (c->x86_model) {
+		case 0x27:	/* Penwell */
+		case 0x35:	/* Cloverview */
+			set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3);
+			break;
+		default:
+			break;
+		}
+	}
+
 	/*
 	 * There is a known erratum on Pentium III and Core Solo
 	 * and Core Duo CPUs.
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 2e8f3d3b564..198eb201ed3 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -13,6 +13,7 @@
 #include <asm/x86_init.h>
 #include <asm/time.h>
 #include <asm/mrst.h>
+#include <asm/rtc.h>
 
 #ifdef CONFIG_X86_32
 /*
@@ -36,70 +37,24 @@ EXPORT_SYMBOL(rtc_lock);
  * nowtime is written into the registers of the CMOS clock, it will
  * jump to the next second precisely 500 ms later. Check the Motorola
  * MC146818A or Dallas DS12887 data sheet for details.
- *
- * BUG: This routine does not handle hour overflow properly; it just
- *      sets the minutes. Usually you'll only notice that after reboot!
  */
 int mach_set_rtc_mmss(unsigned long nowtime)
 {
-	int real_seconds, real_minutes, cmos_minutes;
-	unsigned char save_control, save_freq_select;
-	unsigned long flags;
+	struct rtc_time tm;
 	int retval = 0;
 
-	spin_lock_irqsave(&rtc_lock, flags);
-
-	 /* tell the clock it's being set */
-	save_control = CMOS_READ(RTC_CONTROL);
-	CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
-
-	/* stop and reset prescaler */
-	save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
-	CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
-
-	cmos_minutes = CMOS_READ(RTC_MINUTES);
-	if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
-		cmos_minutes = bcd2bin(cmos_minutes);
-
-	/*
-	 * since we're only adjusting minutes and seconds,
-	 * don't interfere with hour overflow. This avoids
-	 * messing with unknown time zones but requires your
-	 * RTC not to be off by more than 15 minutes
-	 */
-	real_seconds = nowtime % 60;
-	real_minutes = nowtime / 60;
-	/* correct for half hour time zone */
-	if (((abs(real_minutes - cmos_minutes) + 15)/30) & 1)
-		real_minutes += 30;
-	real_minutes %= 60;
-
-	if (abs(real_minutes - cmos_minutes) < 30) {
-		if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-			real_seconds = bin2bcd(real_seconds);
-			real_minutes = bin2bcd(real_minutes);
-		}
-		CMOS_WRITE(real_seconds, RTC_SECONDS);
-		CMOS_WRITE(real_minutes, RTC_MINUTES);
+	rtc_time_to_tm(nowtime, &tm);
+	if (!rtc_valid_tm(&tm)) {
+		retval = set_rtc_time(&tm);
+		if (retval)
+			printk(KERN_ERR "%s: RTC write failed with error %d\n",
+			       __FUNCTION__, retval);
 	} else {
-		printk_once(KERN_NOTICE
-		       "set_rtc_mmss: can't update from %d to %d\n",
-		       cmos_minutes, real_minutes);
-		retval = -1;
+		printk(KERN_ERR
+		       "%s: Invalid RTC value: write of %lx to RTC failed\n",
+			__FUNCTION__, nowtime);
+		retval = -EINVAL;
 	}
-
-	/* The following flags have to be released exactly in this order,
-	 * otherwise the DS12887 (popular MC146818A clone with integrated
-	 * battery and quartz) will not reset the oscillator and will not
-	 * update precisely 500 ms later. You won't find this mentioned in
-	 * the Dallas Semiconductor data sheets, but who believes data
-	 * sheets anyway ...                           -- Markus Kuhn
-	 */
-	CMOS_WRITE(save_control, RTC_CONTROL);
-	CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
-
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
 	return retval;
 }
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 4b9ea101fe3..098b3cfda72 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -768,7 +768,8 @@ static cycle_t read_tsc(struct clocksource *cs)
 
 static void resume_tsc(struct clocksource *cs)
 {
-	clocksource_tsc.cycle_last = 0;
+	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
+		clocksource_tsc.cycle_last = 0;
 }
 
 static struct clocksource clocksource_tsc = {
@@ -939,6 +940,9 @@ static int __init init_tsc_clocksource(void)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
+		clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
+
 	/*
 	 * Trust the results of the earlier calibration on systems
 	 * exporting a reliable TSC.
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index e4a86a677ce..b55d174e503 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -49,6 +49,7 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/x86_init.h>
+#include <asm/rtc.h>
 
 #define EFI_DEBUG	1
 
@@ -352,10 +353,10 @@ static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
 
 int efi_set_rtc_mmss(unsigned long nowtime)
 {
-	int real_seconds, real_minutes;
 	efi_status_t 	status;
 	efi_time_t 	eft;
 	efi_time_cap_t 	cap;
+	struct rtc_time	tm;
 
 	status = efi.get_time(&eft, &cap);
 	if (status != EFI_SUCCESS) {
@@ -363,13 +364,20 @@ int efi_set_rtc_mmss(unsigned long nowtime)
 		return -1;
 	}
 
-	real_seconds = nowtime % 60;
-	real_minutes = nowtime / 60;
-	if (((abs(real_minutes - eft.minute) + 15)/30) & 1)
-		real_minutes += 30;
-	real_minutes %= 60;
-	eft.minute = real_minutes;
-	eft.second = real_seconds;
+	rtc_time_to_tm(nowtime, &tm);
+	if (!rtc_valid_tm(&tm)) {
+		eft.year = tm.tm_year + 1900;
+		eft.month = tm.tm_mon + 1;
+		eft.day = tm.tm_mday;
+		eft.minute = tm.tm_min;
+		eft.second = tm.tm_sec;
+		eft.nanosecond = 0;
+	} else {
+		printk(KERN_ERR
+		       "%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n",
+		       __FUNCTION__, nowtime);
+		return -1;
+	}
 
 	status = efi.set_time(&eft);
 	if (status != EFI_SUCCESS) {
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index 225bd0f0f67..d62b0a3b5c1 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -85,27 +85,35 @@ unsigned long vrtc_get_time(void)
 	return mktime(year, mon, mday, hour, min, sec);
 }
 
-/* Only care about the minutes and seconds */
 int vrtc_set_mmss(unsigned long nowtime)
 {
-	int real_sec, real_min;
 	unsigned long flags;
-	int vrtc_min;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	vrtc_min = vrtc_cmos_read(RTC_MINUTES);
-
-	real_sec = nowtime % 60;
-	real_min = nowtime / 60;
-	if (((abs(real_min - vrtc_min) + 15)/30) & 1)
-		real_min += 30;
-	real_min %= 60;
-
-	vrtc_cmos_write(real_sec, RTC_SECONDS);
-	vrtc_cmos_write(real_min, RTC_MINUTES);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
-	return 0;
+	struct rtc_time tm;
+	int year;
+	int retval = 0;
+
+	rtc_time_to_tm(nowtime, &tm);
+	if (!rtc_valid_tm(&tm) && tm.tm_year >= 72) {
+		/*
+		 * tm.year is the number of years since 1900, and the
+		 * vrtc need the years since 1972.
+		 */
+		year = tm.tm_year - 72;
+		spin_lock_irqsave(&rtc_lock, flags);
+		vrtc_cmos_write(year, RTC_YEAR);
+		vrtc_cmos_write(tm.tm_mon, RTC_MONTH);
+		vrtc_cmos_write(tm.tm_mday, RTC_DAY_OF_MONTH);
+		vrtc_cmos_write(tm.tm_hour, RTC_HOURS);
+		vrtc_cmos_write(tm.tm_min, RTC_MINUTES);
+		vrtc_cmos_write(tm.tm_sec, RTC_SECONDS);
+		spin_unlock_irqrestore(&rtc_lock, flags);
+	} else {
+		printk(KERN_ERR
+		       "%s: Invalid vRTC value: write of %lx to vRTC failed\n",
+			__FUNCTION__, nowtime);
+		retval = -EINVAL;
+	}
+	return retval;
 }
 
 void __init mrst_rtc_init(void)