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

Pull timer core updates from Thomas Gleixner:
 "The timer changes contain:

   - posix timer code consolidation and fixes for odd corner cases

   - sched_clock implementation moved from ARM to core code to avoid
     duplication by other architectures

   - alarm timer updates

   - clocksource and clockevents unregistration facilities

   - clocksource/events support for new hardware

   - precise nanoseconds RTC readout (Xen feature)

   - generic support for Xen suspend/resume oddities

   - the usual lot of fixes and cleanups all over the place

  The parts which touch other areas (ARM/XEN) have been coordinated with
  the relevant maintainers.  Though this results in an handful of
  trivial to solve merge conflicts, which we preferred over nasty cross
  tree merge dependencies.

  The patches which have been committed in the last few days are bug
  fixes plus the posix timer lot.  The latter was in akpms queue and
  next for quite some time; they just got forgotten and Frederic
  collected them last minute."

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (59 commits)
  hrtimer: Remove unused variable
  hrtimers: Move SMP function call to thread context
  clocksource: Reselect clocksource when watchdog validated high-res capability
  posix-cpu-timers: don't account cpu timer after stopped thread runtime accounting
  posix_timers: fix racy timer delta caching on task exit
  posix-timers: correctly get dying task time sample in posix_cpu_timer_schedule()
  selftests: add basic posix timers selftests
  posix_cpu_timers: consolidate expired timers check
  posix_cpu_timers: consolidate timer list cleanups
  posix_cpu_timer: consolidate expiry time type
  tick: Sanitize broadcast control logic
  tick: Prevent uncontrolled switch to oneshot mode
  tick: Make oneshot broadcast robust vs. CPU offlining
  x86: xen: Sync the CMOS RTC as well as the Xen wallclock
  x86: xen: Sync the wallclock when the system time is set
  timekeeping: Indicate that clock was set in the pvclock gtod notifier
  timekeeping: Pass flags instead of multiple bools to timekeeping_update()
  xen: Remove clock_was_set() call in the resume path
  hrtimers: Support resuming with two or more CPUs online (but stopped)
  timer: Fix jiffies wrap behavior of round_jiffies_common()
  ...

32 files changed, 99 insertions, 302 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 531cdda016f..5ef7af01373 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -14,6 +14,7 @@ config ARM
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
+	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_STRNCPY_FROM_USER
diff --git a/arch/arm/common/timer-sp.c b/arch/arm/common/timer-sp.c
index ddc74076960..023ee63827a 100644
--- a/arch/arm/common/timer-sp.c
+++ b/arch/arm/common/timer-sp.c
@@ -28,8 +28,8 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <asm/hardware/arm_timer.h>
 #include <asm/hardware/timer-sp.h>
 
diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h
index 3d520ddca61..2389b71a8e7 100644
--- a/arch/arm/include/asm/sched_clock.h
+++ b/arch/arm/include/asm/sched_clock.h
@@ -1,16 +1,4 @@
-/*
- * sched_clock.h: support for extending counters to full 64-bit ns counter
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+/* You shouldn't include this file. Use linux/sched_clock.h instead.
+ * Temporary file until all asm/sched_clock.h users are gone
  */
-#ifndef ASM_SCHED_CLOCK
-#define ASM_SCHED_CLOCK
-
-extern void sched_clock_postinit(void);
-extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
-
-extern unsigned long long (*sched_clock_func)(void);
-
-#endif
+#include <linux/sched_clock.h>
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index fccfbdb03df..86d10dd47dc 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -16,7 +16,7 @@ CFLAGS_REMOVE_return_address.o = -pg
 # Object file lists.
 
 obj-y		:= elf.o entry-common.o irq.o opcodes.o \
-		   process.o ptrace.o return_address.o sched_clock.o \
+		   process.o ptrace.o return_address.o \
 		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
 
 obj-$(CONFIG_ATAGS)		+= atags_parse.o
diff --git a/arch/arm/kernel/arch_timer.c b/arch/arm/kernel/arch_timer.c
index 59dcdced6e3..221f07b11cc 100644
--- a/arch/arm/kernel/arch_timer.c
+++ b/arch/arm/kernel/arch_timer.c
@@ -11,9 +11,9 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/errno.h>
+#include <linux/sched_clock.h>
 
 #include <asm/delay.h>
-#include <asm/sched_clock.h>
 
 #include <clocksource/arm_arch_timer.h>
 
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
deleted file mode 100644
index e8edcaa0e43..00000000000
--- a/arch/arm/kernel/sched_clock.c
+++ /dev/null
@@ -1,217 +0,0 @@
-/*
- * sched_clock.c: support for extending counters to full 64-bit ns counter
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clocksource.h>
-#include <linux/init.h>
-#include <linux/jiffies.h>
-#include <linux/kernel.h>
-#include <linux/moduleparam.h>
-#include <linux/sched.h>
-#include <linux/syscore_ops.h>
-#include <linux/timer.h>
-
-#include <asm/sched_clock.h>
-
-struct clock_data {
-	u64 epoch_ns;
-	u32 epoch_cyc;
-	u32 epoch_cyc_copy;
-	unsigned long rate;
-	u32 mult;
-	u32 shift;
-	bool suspended;
-	bool needs_suspend;
-};
-
-static void sched_clock_poll(unsigned long wrap_ticks);
-static DEFINE_TIMER(sched_clock_timer, sched_clock_poll, 0, 0);
-static int irqtime = -1;
-
-core_param(irqtime, irqtime, int, 0400);
-
-static struct clock_data cd = {
-	.mult	= NSEC_PER_SEC / HZ,
-};
-
-static u32 __read_mostly sched_clock_mask = 0xffffffff;
-
-static u32 notrace jiffy_sched_clock_read(void)
-{
-	return (u32)(jiffies - INITIAL_JIFFIES);
-}
-
-static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
-
-static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
-{
-	return (cyc * mult) >> shift;
-}
-
-static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
-{
-	u64 epoch_ns;
-	u32 epoch_cyc;
-
-	if (cd.suspended)
-		return cd.epoch_ns;
-
-	/*
-	 * Load the epoch_cyc and epoch_ns atomically.  We do this by
-	 * ensuring that we always write epoch_cyc, epoch_ns and
-	 * epoch_cyc_copy in strict order, and read them in strict order.
-	 * If epoch_cyc and epoch_cyc_copy are not equal, then we're in
-	 * the middle of an update, and we should repeat the load.
-	 */
-	do {
-		epoch_cyc = cd.epoch_cyc;
-		smp_rmb();
-		epoch_ns = cd.epoch_ns;
-		smp_rmb();
-	} while (epoch_cyc != cd.epoch_cyc_copy);
-
-	return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, cd.mult, cd.shift);
-}
-
-/*
- * Atomically update the sched_clock epoch.
- */
-static void notrace update_sched_clock(void)
-{
-	unsigned long flags;
-	u32 cyc;
-	u64 ns;
-
-	cyc = read_sched_clock();
-	ns = cd.epoch_ns +
-		cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
-			  cd.mult, cd.shift);
-	/*
-	 * Write epoch_cyc and epoch_ns in a way that the update is
-	 * detectable in cyc_to_fixed_sched_clock().
-	 */
-	raw_local_irq_save(flags);
-	cd.epoch_cyc_copy = cyc;
-	smp_wmb();
-	cd.epoch_ns = ns;
-	smp_wmb();
-	cd.epoch_cyc = cyc;
-	raw_local_irq_restore(flags);
-}
-
-static void sched_clock_poll(unsigned long wrap_ticks)
-{
-	mod_timer(&sched_clock_timer, round_jiffies(jiffies + wrap_ticks));
-	update_sched_clock();
-}
-
-void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
-{
-	unsigned long r, w;
-	u64 res, wrap;
-	char r_unit;
-
-	if (cd.rate > rate)
-		return;
-
-	BUG_ON(bits > 32);
-	WARN_ON(!irqs_disabled());
-	read_sched_clock = read;
-	sched_clock_mask = (1 << bits) - 1;
-	cd.rate = rate;
-
-	/* calculate the mult/shift to convert counter ticks to ns. */
-	clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0);
-
-	r = rate;
-	if (r >= 4000000) {
-		r /= 1000000;
-		r_unit = 'M';
-	} else if (r >= 1000) {
-		r /= 1000;
-		r_unit = 'k';
-	} else
-		r_unit = ' ';
-
-	/* calculate how many ns until we wrap */
-	wrap = cyc_to_ns((1ULL << bits) - 1, cd.mult, cd.shift);
-	do_div(wrap, NSEC_PER_MSEC);
-	w = wrap;
-
-	/* calculate the ns resolution of this counter */
-	res = cyc_to_ns(1ULL, cd.mult, cd.shift);
-	pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n",
-		bits, r, r_unit, res, w);
-
-	/*
-	 * Start the timer to keep sched_clock() properly updated and
-	 * sets the initial epoch.
-	 */
-	sched_clock_timer.data = msecs_to_jiffies(w - (w / 10));
-	update_sched_clock();
-
-	/*
-	 * Ensure that sched_clock() starts off at 0ns
-	 */
-	cd.epoch_ns = 0;
-
-	/* Enable IRQ time accounting if we have a fast enough sched_clock */
-	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
-		enable_sched_clock_irqtime();
-
-	pr_debug("Registered %pF as sched_clock source\n", read);
-}
-
-static unsigned long long notrace sched_clock_32(void)
-{
-	u32 cyc = read_sched_clock();
-	return cyc_to_sched_clock(cyc, sched_clock_mask);
-}
-
-unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32;
-
-unsigned long long notrace sched_clock(void)
-{
-	return sched_clock_func();
-}
-
-void __init sched_clock_postinit(void)
-{
-	/*
-	 * If no sched_clock function has been provided at that point,
-	 * make it the final one one.
-	 */
-	if (read_sched_clock == jiffy_sched_clock_read)
-		setup_sched_clock(jiffy_sched_clock_read, 32, HZ);
-
-	sched_clock_poll(sched_clock_timer.data);
-}
-
-static int sched_clock_suspend(void)
-{
-	sched_clock_poll(sched_clock_timer.data);
-	cd.suspended = true;
-	return 0;
-}
-
-static void sched_clock_resume(void)
-{
-	cd.epoch_cyc = read_sched_clock();
-	cd.epoch_cyc_copy = cd.epoch_cyc;
-	cd.suspended = false;
-}
-
-static struct syscore_ops sched_clock_ops = {
-	.suspend = sched_clock_suspend,
-	.resume = sched_clock_resume,
-};
-
-static int __init sched_clock_syscore_init(void)
-{
-	register_syscore_ops(&sched_clock_ops);
-	return 0;
-}
-device_initcall(sched_clock_syscore_init);
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index abff4e9aaee..98aee325839 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -24,9 +24,9 @@
 #include <linux/timer.h>
 #include <linux/clocksource.h>
 #include <linux/irq.h>
+#include <linux/sched_clock.h>
 
 #include <asm/thread_info.h>
-#include <asm/sched_clock.h>
 #include <asm/stacktrace.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
@@ -120,6 +120,4 @@ void __init time_init(void)
 		machine_desc->init_time();
 	else
 		clocksource_of_init();
-
-	sched_clock_postinit();
 }
diff --git a/arch/arm/mach-davinci/time.c b/arch/arm/mach-davinci/time.c
index bad361ec166..7a55b5c9597 100644
--- a/arch/arm/mach-davinci/time.c
+++ b/arch/arm/mach-davinci/time.c
@@ -18,8 +18,8 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/platform_device.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
 
diff --git a/arch/arm/mach-imx/time.c b/arch/arm/mach-imx/time.c
index fea91313678..cd46529e9ea 100644
--- a/arch/arm/mach-imx/time.c
+++ b/arch/arm/mach-imx/time.c
@@ -26,8 +26,8 @@
 #include <linux/clockchips.h>
 #include <linux/clk.h>
 #include <linux/err.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <asm/mach/time.h>
 
 #include "common.h"
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index a5b15c4e8de..d9e95e612fc 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -41,6 +41,7 @@
 #include <linux/stat.h>
 #include <linux/sys_soc.h>
 #include <linux/termios.h>
+#include <linux/sched_clock.h>
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
@@ -48,7 +49,6 @@
 #include <asm/setup.h>
 #include <asm/param.h>		/* HZ */
 #include <asm/mach-types.h>
-#include <asm/sched_clock.h>
 
 #include <mach/lm.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index d7223b3b81f..1f6c1fb353a 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -30,6 +30,7 @@
 #include <linux/export.h>
 #include <linux/gpio.h>
 #include <linux/cpu.h>
+#include <linux/sched_clock.h>
 
 #include <mach/udc.h>
 #include <mach/hardware.h>
@@ -38,7 +39,6 @@
 #include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/irq.h>
-#include <asm/sched_clock.h>
 #include <asm/system_misc.h>
 
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-mmp/time.c b/arch/arm/mach-mmp/time.c
index 86a18b3d252..7ac41e83cfe 100644
--- a/arch/arm/mach-mmp/time.c
+++ b/arch/arm/mach-mmp/time.c
@@ -28,8 +28,8 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <mach/addr-map.h>
 #include <mach/regs-timers.h>
 #include <mach/regs-apbc.h>
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 284313f3e02..b6418fd5fe0 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -23,10 +23,10 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
 #include <asm/localtimer.h>
-#include <asm/sched_clock.h>
 
 #include "common.h"
 
diff --git a/arch/arm/mach-omap1/time.c b/arch/arm/mach-omap1/time.c
index 726ec23d29c..80603d2fef7 100644
--- a/arch/arm/mach-omap1/time.c
+++ b/arch/arm/mach-omap1/time.c
@@ -43,9 +43,9 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/io.h>
+#include <linux/sched_clock.h>
 
 #include <asm/irq.h>
-#include <asm/sched_clock.h>
 
 #include <mach/hardware.h>
 #include <asm/mach/irq.h>
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 3bdb0fb0202..29ac667b7a8 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -41,10 +41,10 @@
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/dmtimer-omap.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
 #include <asm/smp_twd.h>
-#include <asm/sched_clock.h>
 
 #include "omap_hwmod.h"
 #include "omap_device.h"
diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c
index 8f1ee92aea3..9aa852a8fab 100644
--- a/arch/arm/mach-pxa/time.c
+++ b/arch/arm/mach-pxa/time.c
@@ -16,11 +16,11 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/clockchips.h>
+#include <linux/sched_clock.h>
 
 #include <asm/div64.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
-#include <asm/sched_clock.h>
 #include <mach/regs-ost.h>
 #include <mach/irqs.h>
 
diff --git a/arch/arm/mach-sa1100/time.c b/arch/arm/mach-sa1100/time.c
index a59a13a665a..713c86cd3d6 100644
--- a/arch/arm/mach-sa1100/time.c
+++ b/arch/arm/mach-sa1100/time.c
@@ -14,9 +14,9 @@
 #include <linux/irq.h>
 #include <linux/timex.h>
 #include <linux/clockchips.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
-#include <asm/sched_clock.h>
 #include <mach/hardware.h>
 #include <mach/irqs.h>
 
diff --git a/arch/arm/mach-u300/timer.c b/arch/arm/mach-u300/timer.c
index 390ae5feb1d..b5db207dfd1 100644
--- a/arch/arm/mach-u300/timer.c
+++ b/arch/arm/mach-u300/timer.c
@@ -21,9 +21,9 @@
 #include <linux/delay.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sched_clock.h>
 
 /* Generic stuff */
-#include <asm/sched_clock.h>
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
 
diff --git a/arch/arm/plat-iop/time.c b/arch/arm/plat-iop/time.c
index 837a2d52e9d..29606bd75f3 100644
--- a/arch/arm/plat-iop/time.c
+++ b/arch/arm/plat-iop/time.c
@@ -22,9 +22,9 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/export.h>
+#include <linux/sched_clock.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
-#include <asm/sched_clock.h>
 #include <asm/uaccess.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
diff --git a/arch/arm/plat-omap/counter_32k.c b/arch/arm/plat-omap/counter_32k.c
index 5b0b86bb34b..d9bc98eb2a6 100644
--- a/arch/arm/plat-omap/counter_32k.c
+++ b/arch/arm/plat-omap/counter_32k.c
@@ -18,9 +18,9 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/clocksource.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
-#include <asm/sched_clock.h>
 
 #include <plat/counter-32k.h>
 
diff --git a/arch/arm/plat-orion/time.c b/arch/arm/plat-orion/time.c
index 5d5ac0f0542..9d2b2ac7493 100644
--- a/arch/arm/plat-orion/time.c
+++ b/arch/arm/plat-orion/time.c
@@ -16,7 +16,7 @@
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 
 /*
  * MBus bridge block registers.
diff --git a/arch/arm/plat-samsung/samsung-time.c b/arch/arm/plat-samsung/samsung-time.c
index f899cbc9b28..2957075ca83 100644
--- a/arch/arm/plat-samsung/samsung-time.c
+++ b/arch/arm/plat-samsung/samsung-time.c
@@ -15,12 +15,12 @@
 #include <linux/clk.h>
 #include <linux/clockchips.h>
 #include <linux/platform_device.h>
+#include <linux/sched_clock.h>
 
 #include <asm/smp_twd.h>
 #include <asm/mach/time.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
-#include <asm/sched_clock.h>
 
 #include <mach/map.h>
 #include <plat/devs.h>
diff --git a/arch/arm/plat-versatile/sched-clock.c b/arch/arm/plat-versatile/sched-clock.c
index b33b74c8723..51b109e3b6c 100644
--- a/arch/arm/plat-versatile/sched-clock.c
+++ b/arch/arm/plat-versatile/sched-clock.c
@@ -20,8 +20,8 @@
  */
 #include <linux/kernel.h>
 #include <linux/io.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <plat/sched_clock.h>
 
 static void __iomem *ctr;
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index d354fb781c5..a55c7efcc4e 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -95,8 +95,8 @@ static inline unsigned char current_lock_cmos_reg(void)
 unsigned char rtc_cmos_read(unsigned char addr);
 void rtc_cmos_write(unsigned char val, unsigned char addr);
 
-extern int mach_set_rtc_mmss(unsigned long nowtime);
-extern unsigned long mach_get_cmos_time(void);
+extern int mach_set_rtc_mmss(const struct timespec *now);
+extern void mach_get_cmos_time(struct timespec *now);
 
 #define RTC_IRQ 8
 
diff --git a/arch/x86/include/asm/mrst-vrtc.h b/arch/x86/include/asm/mrst-vrtc.h
index 73668abdbed..1e69a75412a 100644
--- a/arch/x86/include/asm/mrst-vrtc.h
+++ b/arch/x86/include/asm/mrst-vrtc.h
@@ -3,7 +3,7 @@
 
 extern unsigned char vrtc_cmos_read(unsigned char reg);
 extern void vrtc_cmos_write(unsigned char val, unsigned char reg);
-extern unsigned long vrtc_get_time(void);
-extern int vrtc_set_mmss(unsigned long nowtime);
+extern void vrtc_get_time(struct timespec *now);
+extern int vrtc_set_mmss(const struct timespec *now);
 
 #endif
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index d8d99222b36..828a1565ba5 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -142,6 +142,8 @@ struct x86_cpuinit_ops {
 	void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node);
 };
 
+struct timespec;
+
 /**
  * struct x86_platform_ops - platform specific runtime functions
  * @calibrate_tsc:		calibrate TSC
@@ -156,8 +158,8 @@ struct x86_cpuinit_ops {
  */
 struct x86_platform_ops {
 	unsigned long (*calibrate_tsc)(void);
-	unsigned long (*get_wallclock)(void);
-	int (*set_wallclock)(unsigned long nowtime);
+	void (*get_wallclock)(struct timespec *ts);
+	int (*set_wallclock)(const struct timespec *ts);
 	void (*iommu_shutdown)(void);
 	bool (*is_untracked_pat_range)(u64 start, u64 end);
 	void (*nmi_init)(void);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 3dd37ebd591..1f354f4b602 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -48,10 +48,9 @@ static struct pvclock_wall_clock wall_clock;
  * have elapsed since the hypervisor wrote the data. So we try to account for
  * that with system time
  */
-static unsigned long kvm_get_wallclock(void)
+static void kvm_get_wallclock(struct timespec *now)
 {
 	struct pvclock_vcpu_time_info *vcpu_time;
-	struct timespec ts;
 	int low, high;
 	int cpu;
 
@@ -64,14 +63,12 @@ static unsigned long kvm_get_wallclock(void)
 	cpu = smp_processor_id();
 
 	vcpu_time = &hv_clock[cpu].pvti;
-	pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
+	pvclock_read_wallclock(&wall_clock, vcpu_time, now);
 
 	preempt_enable();
-
-	return ts.tv_sec;
 }
 
-static int kvm_set_wallclock(unsigned long now)
+static int kvm_set_wallclock(const struct timespec *now)
 {
 	return -1;
 }
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 198eb201ed3..0aa29394ed6 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -38,8 +38,9 @@ EXPORT_SYMBOL(rtc_lock);
  * jump to the next second precisely 500 ms later. Check the Motorola
  * MC146818A or Dallas DS12887 data sheet for details.
  */
-int mach_set_rtc_mmss(unsigned long nowtime)
+int mach_set_rtc_mmss(const struct timespec *now)
 {
+	unsigned long nowtime = now->tv_sec;
 	struct rtc_time tm;
 	int retval = 0;
 
@@ -58,7 +59,7 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 	return retval;
 }
 
-unsigned long mach_get_cmos_time(void)
+void mach_get_cmos_time(struct timespec *now)
 {
 	unsigned int status, year, mon, day, hour, min, sec, century = 0;
 	unsigned long flags;
@@ -107,7 +108,8 @@ unsigned long mach_get_cmos_time(void)
 	} else
 		year += CMOS_YEARS_OFFS;
 
-	return mktime(year, mon, day, hour, min, sec);
+	now->tv_sec = mktime(year, mon, day, hour, min, sec);
+	now->tv_nsec = 0;
 }
 
 /* Routines for accessing the CMOS RAM/RTC. */
@@ -135,18 +137,13 @@ EXPORT_SYMBOL(rtc_cmos_write);
 
 int update_persistent_clock(struct timespec now)
 {
-	return x86_platform.set_wallclock(now.tv_sec);
+	return x86_platform.set_wallclock(&now);
 }
 
 /* not static: needed by APM */
 void read_persistent_clock(struct timespec *ts)
 {
-	unsigned long retval;
-
-	retval = x86_platform.get_wallclock();
-
-	ts->tv_sec = retval;
-	ts->tv_nsec = 0;
+	x86_platform.get_wallclock(ts);
 }
 
 
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index d482bcaf61c..6a22c19da66 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -882,9 +882,9 @@ int lguest_setup_irq(unsigned int irq)
  * It would be far better for everyone if the Guest had its own clock, but
  * until then the Host gives us the time on every interrupt.
  */
-static unsigned long lguest_get_wallclock(void)
+static void lguest_get_wallclock(struct timespec *now)
 {
-	return lguest_data.time.tv_sec;
+	*now = lguest_data.time;
 }
 
 /*
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index b410b71bdcf..c8d5577044b 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -274,8 +274,9 @@ static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
 	return status;
 }
 
-int efi_set_rtc_mmss(unsigned long nowtime)
+int efi_set_rtc_mmss(const struct timespec *now)
 {
+	unsigned long nowtime = now->tv_sec;
 	efi_status_t 	status;
 	efi_time_t 	eft;
 	efi_time_cap_t 	cap;
@@ -310,7 +311,7 @@ int efi_set_rtc_mmss(unsigned long nowtime)
 	return 0;
 }
 
-unsigned long efi_get_time(void)
+void efi_get_time(struct timespec *now)
 {
 	efi_status_t status;
 	efi_time_t eft;
@@ -320,8 +321,9 @@ unsigned long efi_get_time(void)
 	if (status != EFI_SUCCESS)
 		pr_err("Oops: efitime: can't read time!\n");
 
-	return mktime(eft.year, eft.month, eft.day, eft.hour,
-		      eft.minute, eft.second);
+	now->tv_sec = mktime(eft.year, eft.month, eft.day, eft.hour,
+			     eft.minute, eft.second);
+	now->tv_nsec = 0;
 }
 
 /*
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index d62b0a3b5c1..5e355b134ba 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -56,7 +56,7 @@ void vrtc_cmos_write(unsigned char val, unsigned char reg)
 }
 EXPORT_SYMBOL_GPL(vrtc_cmos_write);
 
-unsigned long vrtc_get_time(void)
+void vrtc_get_time(struct timespec *now)
 {
 	u8 sec, min, hour, mday, mon;
 	unsigned long flags;
@@ -82,17 +82,18 @@ unsigned long vrtc_get_time(void)
 	printk(KERN_INFO "vRTC: sec: %d min: %d hour: %d day: %d "
 		"mon: %d year: %d\n", sec, min, hour, mday, mon, year);
 
-	return mktime(year, mon, mday, hour, min, sec);
+	now->tv_sec = mktime(year, mon, mday, hour, min, sec);
+	now->tv_nsec = 0;
 }
 
-int vrtc_set_mmss(unsigned long nowtime)
+int vrtc_set_mmss(const struct timespec *now)
 {
 	unsigned long flags;
 	struct rtc_time tm;
 	int year;
 	int retval = 0;
 
-	rtc_time_to_tm(nowtime, &tm);
+	rtc_time_to_tm(now->tv_sec, &tm);
 	if (!rtc_valid_tm(&tm) && tm.tm_year >= 72) {
 		/*
 		 * tm.year is the number of years since 1900, and the
@@ -110,7 +111,7 @@ int vrtc_set_mmss(unsigned long nowtime)
 	} else {
 		printk(KERN_ERR
 		       "%s: Invalid vRTC value: write of %lx to vRTC failed\n",
-			__FUNCTION__, nowtime);
+			__FUNCTION__, now->tv_sec);
 		retval = -EINVAL;
 	}
 	return retval;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index a690868be83..ee365895b06 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -15,6 +15,7 @@
 #include <linux/math64.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/pvclock_gtod.h>
 
 #include <asm/pvclock.h>
 #include <asm/xen/hypervisor.h>
@@ -179,34 +180,56 @@ static void xen_read_wallclock(struct timespec *ts)
 	put_cpu_var(xen_vcpu);
 }
 
-static unsigned long xen_get_wallclock(void)
+static void xen_get_wallclock(struct timespec *now)
 {
-	struct timespec ts;
+	xen_read_wallclock(now);
+}
 
-	xen_read_wallclock(&ts);
-	return ts.tv_sec;
+static int xen_set_wallclock(const struct timespec *now)
+{
+	return -1;
 }
 
-static int xen_set_wallclock(unsigned long now)
+static int xen_pvclock_gtod_notify(struct notifier_block *nb,
+				   unsigned long was_set, void *priv)
 {
+	/* Protected by the calling core code serialization */
+	static struct timespec next_sync;
+
 	struct xen_platform_op op;
-	int rc;
+	struct timespec now;
 
-	/* do nothing for domU */
-	if (!xen_initial_domain())
-		return -1;
+	now = __current_kernel_time();
+
+	/*
+	 * We only take the expensive HV call when the clock was set
+	 * or when the 11 minutes RTC synchronization time elapsed.
+	 */
+	if (!was_set && timespec_compare(&now, &next_sync) < 0)
+		return NOTIFY_OK;
 
 	op.cmd = XENPF_settime;
-	op.u.settime.secs = now;
-	op.u.settime.nsecs = 0;
+	op.u.settime.secs = now.tv_sec;
+	op.u.settime.nsecs = now.tv_nsec;
 	op.u.settime.system_time = xen_clocksource_read();
 
-	rc = HYPERVISOR_dom0_op(&op);
-	WARN(rc != 0, "XENPF_settime failed: now=%ld\n", now);
+	(void)HYPERVISOR_dom0_op(&op);
 
-	return rc;
+	/*
+	 * Move the next drift compensation time 11 minutes
+	 * ahead. That's emulating the sync_cmos_clock() update for
+	 * the hardware RTC.
+	 */
+	next_sync = now;
+	next_sync.tv_sec += 11 * 60;
+
+	return NOTIFY_OK;
 }
 
+static struct notifier_block xen_pvclock_gtod_notifier = {
+	.notifier_call = xen_pvclock_gtod_notify,
+};
+
 static struct clocksource xen_clocksource __read_mostly = {
 	.name = "xen",
 	.rating = 400,
@@ -482,6 +505,9 @@ static void __init xen_time_init(void)
 	xen_setup_runstate_info(cpu);
 	xen_setup_timer(cpu);
 	xen_setup_cpu_clockevents();
+
+	if (xen_initial_domain())
+		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 }
 
 void __init xen_init_time_ops(void)
@@ -494,7 +520,9 @@ void __init xen_init_time_ops(void)
 
 	x86_platform.calibrate_tsc = xen_tsc_khz;
 	x86_platform.get_wallclock = xen_get_wallclock;
-	x86_platform.set_wallclock = xen_set_wallclock;
+	/* Dom0 uses the native method to set the hardware RTC. */
+	if (!xen_initial_domain())
+		x86_platform.set_wallclock = xen_set_wallclock;
 }
 
 #ifdef CONFIG_XEN_PVHVM