From 55a68c23e0a675b2b8ac2656fd6edbf98b78e4c6 Mon Sep 17 00:00:00 2001
From: Pavel Machek
Date: Tue, 7 May 2013 22:11:26 +0200
Subject: dw_apb_timer_of.c: Remove parts that were picoxcell-specific

It seems we made a mistake when creating dw_apb_timer_of.c:
picoxcell sched_clock had parts that were not related to
dw_apb_timer, yet we moved them to dw_apb_timer_of, and tried to
use them on socfpga.

This results in system where user/system time is not measured
properly, as demonstrated by

    time dd if=/dev/urandom of=/dev/zero bs=100000 count=100

So this patch switches sched_clock to hardware that exists on both
platforms, and adds missing of_node_put() in dw_apb_timer_init().

Signed-off-by: Pavel Machek <pavel@denx.de>
Acked-by: Jamie Iles <jamie@jamieiles.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 arch/arm/mach-picoxcell/common.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'arch')

diff --git a/arch/arm/mach-picoxcell/common.h b/arch/arm/mach-picoxcell/common.h
index 481b42a4ef15..237fb3bcbd04 100644
--- a/arch/arm/mach-picoxcell/common.h
+++ b/arch/arm/mach-picoxcell/common.h
@@ -12,6 +12,4 @@
 
 #include <asm/mach/time.h>
 
-extern void dw_apb_timer_init(void);
-
 #endif /* __PICOXCELL_COMMON_H__ */
-- 
cgit v1.2.3-55-g7522


From 3565184ed0c1ea46bea5b792da5f72a83c43e49b Mon Sep 17 00:00:00 2001
From: David Vrabel
Date: Mon, 13 May 2013 18:56:06 +0100
Subject: x86: Increase precision of x86_platform.get/set_wallclock()

All the virtualized platforms (KVM, lguest and Xen) have persistent
wallclocks that have more than one second of precision.

read_persistent_wallclock() and update_persistent_wallclock() allow
for nanosecond precision but their implementation on x86 with
x86_platform.get/set_wallclock() only allows for one second precision.
This means guests may see a wallclock time that is off by up to 1
second.

Make set_wallclock() and get_wallclock() take a struct timespec
parameter (which allows for nanosecond precision) so KVM and Xen
guests may start with a more accurate wallclock time and a Xen dom0
can maintain a more accurate wallclock for guests.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 arch/x86/include/asm/mc146818rtc.h |  4 ++--
 arch/x86/include/asm/x86_init.h    |  6 ++++--
 arch/x86/kernel/kvmclock.c         |  9 +++------
 arch/x86/kernel/rtc.c              | 17 +++++++----------
 arch/x86/lguest/boot.c             |  4 ++--
 arch/x86/platform/efi/efi.c        | 10 ++++++----
 arch/x86/xen/time.c                | 19 ++++++-------------
 include/linux/efi.h                |  4 ++--
 8 files changed, 32 insertions(+), 41 deletions(-)

(limited to 'arch')

diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index d354fb781c57..a55c7efcc4ed 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/x86_init.h b/arch/x86/include/asm/x86_init.h
index d8d99222b36a..828a1565ba57 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 d2c381280e3c..0db81ab511cc 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 198eb201ed3b..0aa29394ed6f 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 7114c63f047d..8424d5adcfa2 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 55856b2310d3..dd3b82530145 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -352,8 +352,9 @@ 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;
@@ -388,7 +389,7 @@ 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;
@@ -398,8 +399,9 @@ 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/xen/time.c b/arch/x86/xen/time.c
index 3d88bfdf9e1c..a1947ac2da82 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -191,32 +191,25 @@ 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(&ts);
-	return ts.tv_sec;
+	xen_read_wallclock(now);
 }
 
-static int xen_set_wallclock(unsigned long now)
+static int xen_set_wallclock(const struct timespec *now)
 {
 	struct xen_platform_op op;
-	int rc;
 
 	/* do nothing for domU */
 	if (!xen_initial_domain())
 		return -1;
 
 	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);
-
-	return rc;
+	return HYPERVISOR_dom0_op(&op);
 }
 
 static struct clocksource xen_clocksource __read_mostly = {
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 2bc0ad78d058..0068bba6f8b6 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -594,8 +594,8 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size);
 extern int __init efi_uart_console_only (void);
 extern void efi_initialize_iomem_resources(struct resource *code_resource,
 		struct resource *data_resource, struct resource *bss_resource);
-extern unsigned long efi_get_time(void);
-extern int efi_set_rtc_mmss(unsigned long nowtime);
+extern void efi_get_time(struct timespec *now);
+extern int efi_set_rtc_mmss(const struct timespec *now);
 extern void efi_reserve_boot_services(void);
 extern struct efi_memory_map memmap;
 
-- 
cgit v1.2.3-55-g7522


From ce0b098981544d9f4e910ea48f3af3e726ca6d6b Mon Sep 17 00:00:00 2001
From: John Stultz
Date: Tue, 28 May 2013 17:03:09 -0700
Subject: x86: Fix vrtc_get_time/set_mmss to use new timespec interface

The patch "x86: Increase precision of x86_platform.get/set_wallclock"
changed the x86 platform set_wallclock/get_wallclock interfaces to
use nsec granular timespecs instead of a second granular interface.

However, that patch missed converting the vrtc code, so this patch
converts those functions to use timespecs.

Many thanks to the kbuild test robot for finding this!

Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 arch/x86/include/asm/mrst-vrtc.h |  4 ++--
 arch/x86/platform/mrst/vrtc.c    | 11 ++++++-----
 2 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'arch')

diff --git a/arch/x86/include/asm/mrst-vrtc.h b/arch/x86/include/asm/mrst-vrtc.h
index 73668abdbedf..1e69a75412a4 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/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index d62b0a3b5c14..5e355b134ba4 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;
-- 
cgit v1.2.3-55-g7522


From 5a9b5855c248d0298eac4d5490c7bc11c2f1983b Mon Sep 17 00:00:00 2001
From: Stephen Boyd
Date: Sat, 1 Jun 2013 23:39:38 -0700
Subject: ARM: sched_clock: Remove unused needs_suspend member

The needs_suspend member is unused now that we always do the
suspend/resume handling (see 6a4dae5 (ARM: 7565/1: sched: stop
sched_clock() during suspend, 2012-10-23)).

Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 arch/arm/kernel/sched_clock.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch')

diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index e8edcaa0e432..45efe86e8b08 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -24,7 +24,6 @@ struct clock_data {
 	u32 mult;
 	u32 shift;
 	bool suspended;
-	bool needs_suspend;
 };
 
 static void sched_clock_poll(unsigned long wrap_ticks);
-- 
cgit v1.2.3-55-g7522


From ffbfb5e316f0db486798ccf1db36a577ffe79637 Mon Sep 17 00:00:00 2001
From: Stephen Boyd
Date: Sat, 1 Jun 2013 23:39:39 -0700
Subject: ARM: sched_clock: Return suspended count earlier

If we're suspended and sched_clock() is called we're going to
read the hardware one more time and throw away that value and
return back the cached value we saved during the suspend
callback. This is wasteful. Let's short circuit all that and
return the cached value as early as possible if we're suspended.

Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 arch/arm/kernel/sched_clock.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch')

diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index 45efe86e8b08..a781c59b93c0 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -55,9 +55,6 @@ 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
@@ -174,6 +171,9 @@ unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32;
 
 unsigned long long notrace sched_clock(void)
 {
+	if (cd.suspended)
+		return cd.epoch_ns;
+
 	return sched_clock_func();
 }
 
-- 
cgit v1.2.3-55-g7522


From 38ff87f77af0b5a93fc8581cff1d6e5692ab8970 Mon Sep 17 00:00:00 2001
From: Stephen Boyd
Date: Sat, 1 Jun 2013 23:39:40 -0700
Subject: sched_clock: Make ARM's sched_clock generic for all architectures

Nothing about the sched_clock implementation in the ARM port is
specific to the architecture. Generalize the code so that other
architectures can use it by selecting GENERIC_SCHED_CLOCK.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
[jstultz: Merge minor collisions with other patches in my tree]
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 arch/arm/Kconfig                          |   1 +
 arch/arm/common/timer-sp.c                |   2 +-
 arch/arm/include/asm/sched_clock.h        |  16 ---
 arch/arm/kernel/Makefile                  |   2 +-
 arch/arm/kernel/arch_timer.c              |   2 +-
 arch/arm/kernel/sched_clock.c             | 216 ------------------------------
 arch/arm/kernel/time.c                    |   4 +-
 arch/arm/mach-davinci/time.c              |   2 +-
 arch/arm/mach-imx/time.c                  |   2 +-
 arch/arm/mach-integrator/integrator_ap.c  |   2 +-
 arch/arm/mach-ixp4xx/common.c             |   2 +-
 arch/arm/mach-mmp/time.c                  |   2 +-
 arch/arm/mach-msm/timer.c                 |   2 +-
 arch/arm/mach-omap1/time.c                |   2 +-
 arch/arm/mach-omap2/timer.c               |   2 +-
 arch/arm/mach-pxa/time.c                  |   2 +-
 arch/arm/mach-sa1100/time.c               |   2 +-
 arch/arm/mach-u300/timer.c                |   2 +-
 arch/arm/plat-iop/time.c                  |   2 +-
 arch/arm/plat-omap/counter_32k.c          |   2 +-
 arch/arm/plat-orion/time.c                |   2 +-
 arch/arm/plat-samsung/samsung-time.c      |   2 +-
 arch/arm/plat-versatile/sched-clock.c     |   2 +-
 drivers/clocksource/bcm2835_timer.c       |   2 +-
 drivers/clocksource/clksrc-dbx500-prcmu.c |   3 +-
 drivers/clocksource/dw_apb_timer_of.c     |   3 +-
 drivers/clocksource/mxs_timer.c           |   2 +-
 drivers/clocksource/nomadik-mtu.c         |   2 +-
 drivers/clocksource/samsung_pwm_timer.c   |   2 +-
 drivers/clocksource/tegra20_timer.c       |   2 +-
 drivers/clocksource/time-armada-370-xp.c  |   2 +-
 drivers/clocksource/timer-marco.c         |   2 +-
 drivers/clocksource/timer-prima2.c        |   2 +-
 include/linux/sched_clock.h               |  21 +++
 init/Kconfig                              |   3 +
 init/main.c                               |   2 +
 kernel/time/Makefile                      |   1 +
 kernel/time/sched_clock.c                 | 215 +++++++++++++++++++++++++++++
 38 files changed, 273 insertions(+), 266 deletions(-)
 delete mode 100644 arch/arm/include/asm/sched_clock.h
 delete mode 100644 arch/arm/kernel/sched_clock.c
 create mode 100644 include/linux/sched_clock.h
 create mode 100644 kernel/time/sched_clock.c

(limited to 'arch')

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 49d993cee512..53d3a356f61f 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 ddc740769601..023ee63827a2 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
deleted file mode 100644
index 3d520ddca61b..000000000000
--- a/arch/arm/include/asm/sched_clock.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * 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.
- */
-#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
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 5f3338eacad2..97cb0576d07c 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-armv.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 59dcdced6e30..221f07b11ccb 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 a781c59b93c0..000000000000
--- a/arch/arm/kernel/sched_clock.c
+++ /dev/null
@@ -1,216 +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;
-};
-
-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;
-
-	/*
-	 * 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)
-{
-	if (cd.suspended)
-		return cd.epoch_ns;
-
-	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 abff4e9aaee0..98aee3258398 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 bad361ec1666..7a55b5c95971 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 fea91313678b..cd46529e9eaa 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 b23c8e4f28e8..aa4346227c41 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 <video/vga.h>
 
 #include <mach/hardware.h>
@@ -49,7 +50,6 @@
 #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 6600cff6bd92..58307cff1f18 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 86a18b3d252e..7ac41e83cfef 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 284313f3e02c..b6418fd5fe0d 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 726ec23d29c7..80603d2fef77 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 f8b23b8040d9..4c069b0cab21 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 8f1ee92aea30..9aa852a8fab9 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 a59a13a665a6..713c86cd3d64 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 d9e73209c9b8..af771b76fe1c 100644
--- a/arch/arm/mach-u300/timer.c
+++ b/arch/arm/mach-u300/timer.c
@@ -18,12 +18,12 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/irq.h>
+#include <linux/sched_clock.h>
 
 #include <mach/hardware.h>
 #include <mach/irqs.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 837a2d52e9db..29606bd75f3f 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 5b0b86bb34bb..d9bc98eb2a6b 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 5d5ac0f05422..9d2b2ac74938 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 f899cbc9b288..2957075ca836 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 b33b74c87232..51b109e3b6c3 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/drivers/clocksource/bcm2835_timer.c b/drivers/clocksource/bcm2835_timer.c
index 766611d29945..07ea7ce900dc 100644
--- a/drivers/clocksource/bcm2835_timer.c
+++ b/drivers/clocksource/bcm2835_timer.c
@@ -28,8 +28,8 @@
 #include <linux/of_platform.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <asm/irq.h>
 
 #define REG_CONTROL	0x00
diff --git a/drivers/clocksource/clksrc-dbx500-prcmu.c b/drivers/clocksource/clksrc-dbx500-prcmu.c
index 54f3d119d99c..0a7fb2440e29 100644
--- a/drivers/clocksource/clksrc-dbx500-prcmu.c
+++ b/drivers/clocksource/clksrc-dbx500-prcmu.c
@@ -14,8 +14,7 @@
  */
 #include <linux/clockchips.h>
 #include <linux/clksrc-dbx500-prcmu.h>
-
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 
 #define RATE_32K		32768
 
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index af13b8559b61..a97b4065dacf 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -20,8 +20,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 
 static void timer_get_base_and_rate(struct device_node *np,
 				    void __iomem **base, u32 *rate)
diff --git a/drivers/clocksource/mxs_timer.c b/drivers/clocksource/mxs_timer.c
index 02af4204af86..0f5e65f74dc3 100644
--- a/drivers/clocksource/mxs_timer.c
+++ b/drivers/clocksource/mxs_timer.c
@@ -29,9 +29,9 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/stmp_device.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
-#include <asm/sched_clock.h>
 
 /*
  * There are 2 versions of the timrot on Freescale MXS-based SoCs.
diff --git a/drivers/clocksource/nomadik-mtu.c b/drivers/clocksource/nomadik-mtu.c
index e405531e1cc5..8864c17841c8 100644
--- a/drivers/clocksource/nomadik-mtu.c
+++ b/drivers/clocksource/nomadik-mtu.c
@@ -18,8 +18,8 @@
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/platform_data/clocksource-nomadik-mtu.h>
+#include <linux/sched_clock.h>
 #include <asm/mach/time.h>
-#include <asm/sched_clock.h>
 
 /*
  * The MTU device hosts four different counters, with 4 set of
diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c
index 0234c8d2c8f2..584b5472eea3 100644
--- a/drivers/clocksource/samsung_pwm_timer.c
+++ b/drivers/clocksource/samsung_pwm_timer.c
@@ -21,10 +21,10 @@
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/sched_clock.h>
 
 #include <clocksource/samsung_pwm.h>
 
-#include <asm/sched_clock.h>
 
 /*
  * Clocksource driver
diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c
index ae877b021b54..93961703b887 100644
--- a/drivers/clocksource/tegra20_timer.c
+++ b/drivers/clocksource/tegra20_timer.c
@@ -26,10 +26,10 @@
 #include <linux/io.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
 #include <asm/smp_twd.h>
-#include <asm/sched_clock.h>
 
 #define RTC_SECONDS            0x08
 #define RTC_SHADOW_SECONDS     0x0c
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index 47a673070d70..efdca3263afe 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -27,8 +27,8 @@
 #include <linux/of_address.h>
 #include <linux/irq.h>
 #include <linux/module.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <asm/localtimer.h>
 #include <linux/percpu.h>
 /*
diff --git a/drivers/clocksource/timer-marco.c b/drivers/clocksource/timer-marco.c
index 97738dbf3e3b..e5dc9129ca26 100644
--- a/drivers/clocksource/timer-marco.c
+++ b/drivers/clocksource/timer-marco.c
@@ -17,7 +17,7 @@
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 #include <asm/localtimer.h>
 #include <asm/mach/time.h>
 
diff --git a/drivers/clocksource/timer-prima2.c b/drivers/clocksource/timer-prima2.c
index 760882665d7a..ef3cfb269d8b 100644
--- a/drivers/clocksource/timer-prima2.c
+++ b/drivers/clocksource/timer-prima2.c
@@ -18,7 +18,7 @@
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 #include <asm/mach/time.h>
 
 #define SIRFSOC_TIMER_COUNTER_LO	0x0000
diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h
new file mode 100644
index 000000000000..fa7922c80a41
--- /dev/null
+++ b/include/linux/sched_clock.h
@@ -0,0 +1,21 @@
+/*
+ * 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.
+ */
+#ifndef LINUX_SCHED_CLOCK
+#define LINUX_SCHED_CLOCK
+
+#ifdef CONFIG_GENERIC_SCHED_CLOCK
+extern void sched_clock_postinit(void);
+#else
+static inline void sched_clock_postinit(void) { }
+#endif
+
+extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
+
+extern unsigned long long (*sched_clock_func)(void);
+
+#endif
diff --git a/init/Kconfig b/init/Kconfig
index 9d3a7887a6d3..1a3f93329a67 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -757,6 +757,9 @@ config LOG_BUF_SHIFT
 config HAVE_UNSTABLE_SCHED_CLOCK
 	bool
 
+config GENERIC_SCHED_CLOCK
+	bool
+
 #
 # For architectures that want to enable the support for NUMA-affine scheduler
 # balancing logic:
diff --git a/init/main.c b/init/main.c
index 9484f4ba88d0..bef4a6ac7c76 100644
--- a/init/main.c
+++ b/init/main.c
@@ -74,6 +74,7 @@
 #include <linux/ptrace.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
+#include <linux/sched_clock.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -555,6 +556,7 @@ asmlinkage void __init start_kernel(void)
 	softirq_init();
 	timekeeping_init();
 	time_init();
+	sched_clock_postinit();
 	profile_init();
 	call_function_init();
 	WARN(!irqs_disabled(), "Interrupts were enabled early\n");
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index d52ac8bf0006..9250130646f5 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -4,6 +4,7 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)	+= tick-broadcast.o
+obj-$(CONFIG_GENERIC_SCHED_CLOCK)		+= sched_clock.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-sched.o
 obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
new file mode 100644
index 000000000000..aad1ae6077ef
--- /dev/null
+++ b/kernel/time/sched_clock.c
@@ -0,0 +1,215 @@
+/*
+ * 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 <linux/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;
+};
+
+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;
+
+	/*
+	 * 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)
+{
+	if (cd.suspended)
+		return cd.epoch_ns;
+
+	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);
-- 
cgit v1.2.3-55-g7522


From d3d8fee4138a06b4b9ca172d25b8412fc33ad3f3 Mon Sep 17 00:00:00 2001
From: John Stultz
Date: Mon, 17 Jun 2013 19:34:57 -0700
Subject: Revert "dw_apb_timer_of.c: Remove parts that were picoxcell-specific"

This reverts commit 55a68c23e0a675b2b8ac2656fd6edbf98b78e4c6.

In order to avoid a collision with dw_apb_timer changes in
the arm-soc tree, revert this change.

I'm leaving it to the arm-soc folks to sort out if they want
to keep the other side of the collision or if they're just going
to back it all out and try again during the next release cycle.

Reported-by: Dinh Nguyen <dinguyen@altera.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 arch/arm/mach-picoxcell/common.h      |  2 ++
 drivers/clocksource/dw_apb_timer.c    |  6 ++++
 drivers/clocksource/dw_apb_timer_of.c | 52 +++++++++++++++++++----------------
 include/linux/dw_apb_timer.h          |  6 ----
 4 files changed, 37 insertions(+), 29 deletions(-)

(limited to 'arch')

diff --git a/arch/arm/mach-picoxcell/common.h b/arch/arm/mach-picoxcell/common.h
index 237fb3bcbd04..481b42a4ef15 100644
--- a/arch/arm/mach-picoxcell/common.h
+++ b/arch/arm/mach-picoxcell/common.h
@@ -12,4 +12,6 @@
 
 #include <asm/mach/time.h>
 
+extern void dw_apb_timer_init(void);
+
 #endif /* __PICOXCELL_COMMON_H__ */
diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c
index e7042bc5c7d2..e54ca1062d8e 100644
--- a/drivers/clocksource/dw_apb_timer.c
+++ b/drivers/clocksource/dw_apb_timer.c
@@ -21,6 +21,12 @@
 #define APBT_MIN_PERIOD			4
 #define APBT_MIN_DELTA_USEC		200
 
+#define APBTMR_N_LOAD_COUNT		0x00
+#define APBTMR_N_CURRENT_VALUE		0x04
+#define APBTMR_N_CONTROL		0x08
+#define APBTMR_N_EOI			0x0c
+#define APBTMR_N_INT_STATUS		0x10
+
 #define APBTMRS_INT_STATUS		0xa0
 #define APBTMRS_EOI			0xa4
 #define APBTMRS_RAW_INT_STATUS		0xa8
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index a97b4065dacf..d9a1e8d51751 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -55,15 +55,6 @@ static void add_clockevent(struct device_node *event_timer)
 	dw_apb_clockevent_register(ced);
 }
 
-static void __iomem *sched_io_base;
-
-/* This is actually same as __apbt_read_clocksource(), but with
-   different interface */
-static u32 read_sched_clock_sptimer(void)
-{
-	return ~__raw_readl(sched_io_base + APBTMR_N_CURRENT_VALUE);
-}
-
 static void add_clocksource(struct device_node *source_timer)
 {
 	void __iomem *iobase;
@@ -78,27 +69,41 @@ static void add_clocksource(struct device_node *source_timer)
 
 	dw_apb_clocksource_start(cs);
 	dw_apb_clocksource_register(cs);
+}
 
-	sched_io_base = iobase;
-	setup_sched_clock(read_sched_clock_sptimer, 32, rate);
+static void __iomem *sched_io_base;
+
+static u32 read_sched_clock(void)
+{
+	return __raw_readl(sched_io_base);
 }
 
-static const struct of_device_id osctimer_ids[] __initconst = {
-	{ .compatible = "picochip,pc3x2-timer" },
-	{ .compatible = "snps,dw-apb-timer-osc" },
+static const struct of_device_id sptimer_ids[] __initconst = {
+	{ .compatible = "picochip,pc3x2-rtc" },
 	{ .compatible = "snps,dw-apb-timer-sp" },
-	{  /* Sentinel */ },
+	{ /* Sentinel */ },
 };
 
-/*
-   You don't have to use dw_apb_timer for scheduler clock,
-   this should also work fine on arm:
+static void init_sched_clock(void)
+{
+	struct device_node *sched_timer;
+	u32 rate;
 
-  twd_local_timer_of_register();
-  arch_timer_of_register();
-  arch_timer_sched_clock_init();
-*/
+	sched_timer = of_find_matching_node(NULL, sptimer_ids);
+	if (!sched_timer)
+		panic("No RTC for sched clock to use");
 
+	timer_get_base_and_rate(sched_timer, &sched_io_base, &rate);
+	of_node_put(sched_timer);
+
+	setup_sched_clock(read_sched_clock, 32, rate);
+}
+
+static const struct of_device_id osctimer_ids[] __initconst = {
+	{ .compatible = "picochip,pc3x2-timer" },
+	{ .compatible = "snps,dw-apb-timer-osc" },
+	{},
+};
 
 void __init dw_apb_timer_init(void)
 {
@@ -114,6 +119,7 @@ void __init dw_apb_timer_init(void)
 		panic("No timer for clocksource");
 	add_clocksource(source_timer);
 
-	of_node_put(event_timer);
 	of_node_put(source_timer);
+
+	init_sched_clock();
 }
diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h
index de0904e38f33..b1cd9597c241 100644
--- a/include/linux/dw_apb_timer.h
+++ b/include/linux/dw_apb_timer.h
@@ -17,12 +17,6 @@
 #include <linux/clocksource.h>
 #include <linux/interrupt.h>
 
-#define APBTMR_N_LOAD_COUNT		0x00
-#define APBTMR_N_CURRENT_VALUE		0x04
-#define APBTMR_N_CONTROL		0x08
-#define APBTMR_N_EOI			0x0c
-#define APBTMR_N_INT_STATUS		0x10
-
 #define APBTMRS_REG_SIZE       0x14
 
 struct dw_apb_timer {
-- 
cgit v1.2.3-55-g7522


From 629a6a2b7762a474177d08043bea094dd27e0a54 Mon Sep 17 00:00:00 2001
From: Stephen Boyd
Date: Fri, 21 Jun 2013 10:05:24 -0700
Subject: sched_clock: Add temporary asm/sched_clock.h

Some new users of the ARM sched_clock framework are going through
the arm-soc tree. Before 38ff87f (sched_clock: Make ARM's
sched_clock generic for all architectures, 2013-06-01) the header
file was in asm, but now it's in linux. One solution would be to
do an evil merge of the arm-soc tree and fix up the asm users,
but it's easier to add a temporary asm header that we can remove
along with the few stragglers after the merge window is over.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 arch/arm/include/asm/sched_clock.h | 4 ++++
 1 file changed, 4 insertions(+)
 create mode 100644 arch/arm/include/asm/sched_clock.h

(limited to 'arch')

diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h
new file mode 100644
index 000000000000..2389b71a8e7c
--- /dev/null
+++ b/arch/arm/include/asm/sched_clock.h
@@ -0,0 +1,4 @@
+/* You shouldn't include this file. Use linux/sched_clock.h instead.
+ * Temporary file until all asm/sched_clock.h users are gone
+ */
+#include <linux/sched_clock.h>
-- 
cgit v1.2.3-55-g7522


From 5584880e44e49c587059801faa2a9f7d22619c48 Mon Sep 17 00:00:00 2001
From: David Vrabel
Date: Thu, 27 Jun 2013 11:35:47 +0100
Subject: x86: xen: Sync the wallclock when the system time is set

Currently the Xen wallclock is only updated every 11 minutes if NTP is
synchronized to its clock source (using the sync_cmos_clock() work).
If a guest is started before NTP is synchronized it may see an
incorrect wallclock time.

Use the pvclock_gtod notifier chain to receive a notification when the
system time has changed and update the wallclock to match.

This chain is called on every timer tick and we want to avoid an extra
(expensive) hypercall on every tick.  Because dom0 has historically
never provided a very accurate wallclock and guests do not expect one,
we can do this simply: the wallclock is only updated if the clock was
set.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: <xen-devel@lists.xen.org>
Link: http://lkml.kernel.org/r/1372329348-20841-5-git-send-email-david.vrabel@citrix.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/time.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

(limited to 'arch')

diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index a1947ac2da82..3364850d23e6 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -14,6 +14,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/math64.h>
 #include <linux/gfp.h>
+#include <linux/pvclock_gtod.h>
 
 #include <asm/pvclock.h>
 #include <asm/xen/hypervisor.h>
@@ -212,6 +213,30 @@ static int xen_set_wallclock(const struct timespec *now)
 	return HYPERVISOR_dom0_op(&op);
 }
 
+static int xen_pvclock_gtod_notify(struct notifier_block *nb, unsigned long was_set,
+				   void *priv)
+{
+	struct timespec now;
+	struct xen_platform_op op;
+
+	if (!was_set)
+		return NOTIFY_OK;
+
+	now = __current_kernel_time();
+
+	op.cmd = XENPF_settime;
+	op.u.settime.secs = now.tv_sec;
+	op.u.settime.nsecs = now.tv_nsec;
+	op.u.settime.system_time = xen_clocksource_read();
+
+	(void)HYPERVISOR_dom0_op(&op);
+	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,
@@ -473,6 +498,9 @@ 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)
-- 
cgit v1.2.3-55-g7522


From 47433b8c9d7480a3eebd99df38e857ce85a37cee Mon Sep 17 00:00:00 2001
From: David Vrabel
Date: Thu, 27 Jun 2013 11:35:48 +0100
Subject: x86: xen: Sync the CMOS RTC as well as the Xen wallclock

Adjustments to Xen's persistent clock via update_persistent_clock()
don't actually persist, as the Xen wallclock is a software only clock
and modifications to it do not modify the underlying CMOS RTC.

The x86_platform.set_wallclock hook is there to keep the hardware RTC
synchronized. On a guest this is pointless.

On Dom0 we can use the native implementaion which actually updates the
hardware RTC, but we still need to keep the software emulation of RTC
for the guests up to date. The subscription to the pvclock_notifier
allows us to emulate this easily. The notifier is called at every tick
and when the clock was set.

Right now we only use that notifier when the clock was set, but due to
the fact that it is called periodically from the timekeeping update
code, we can utilize it to emulate the NTP driven drift compensation
of update_persistant_clock() for the Xen wall (software) clock.

Add a 11 minutes periodic update to the pvclock_gtod notifier callback
to achieve that. The static variable 'next' which maintains that 11
minutes update cycle is protected by the core code serialization so
there is no need to add a Xen specific serialization mechanism.

[ tglx: Massaged changelog and added a few comments ]

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: <xen-devel@lists.xen.org>
Link: http://lkml.kernel.org/r/1372329348-20841-6-git-send-email-david.vrabel@citrix.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/xen/time.c | 45 ++++++++++++++++++++++++++-------------------
 1 file changed, 26 insertions(+), 19 deletions(-)

(limited to 'arch')

diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 3364850d23e6..7a5671b4fec6 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -199,37 +199,42 @@ static void xen_get_wallclock(struct timespec *now)
 
 static int xen_set_wallclock(const struct timespec *now)
 {
-	struct xen_platform_op op;
-
-	/* do nothing for domU */
-	if (!xen_initial_domain())
-		return -1;
-
-	op.cmd = XENPF_settime;
-	op.u.settime.secs = now->tv_sec;
-	op.u.settime.nsecs = now->tv_nsec;
-	op.u.settime.system_time = xen_clocksource_read();
-
-	return HYPERVISOR_dom0_op(&op);
+	return -1;
 }
 
-static int xen_pvclock_gtod_notify(struct notifier_block *nb, unsigned long was_set,
-				   void *priv)
+static int xen_pvclock_gtod_notify(struct notifier_block *nb,
+				   unsigned long was_set, void *priv)
 {
-	struct timespec now;
-	struct xen_platform_op op;
+	/* Protected by the calling core code serialization */
+	static struct timespec next_sync;
 
-	if (!was_set)
-		return NOTIFY_OK;
+	struct xen_platform_op op;
+	struct timespec now;
 
 	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.tv_sec;
 	op.u.settime.nsecs = now.tv_nsec;
 	op.u.settime.system_time = xen_clocksource_read();
 
 	(void)HYPERVISOR_dom0_op(&op);
+
+	/*
+	 * 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;
 }
 
@@ -513,7 +518,9 @@ 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
-- 
cgit v1.2.3-55-g7522