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

Pull timer and time updates from Thomas Gleixner:
 "A rather large update of timers, timekeeping & co

   - Core timekeeping code is year-2038 safe now for 32bit machines.
     Now we just need to fix all in kernel users and the gazillion of
     user space interfaces which rely on timespec/timeval :)

   - Better cache layout for the timekeeping internal data structures.

   - Proper nanosecond based interfaces for in kernel users.

   - Tree wide cleanup of code which wants nanoseconds but does hoops
     and loops to convert back and forth from timespecs.  Some of it
     definitely belongs into the ugly code museum.

   - Consolidation of the timekeeping interface zoo.

   - A fast NMI safe accessor to clock monotonic for tracing.  This is a
     long standing request to support correlated user/kernel space
     traces.  With proper NTP frequency correction it's also suitable
     for correlation of traces accross separate machines.

   - Checkpoint/restart support for timerfd.

   - A few NOHZ[_FULL] improvements in the [hr]timer code.

   - Code move from kernel to kernel/time of all time* related code.

   - New clocksource/event drivers from the ARM universe.  I'm really
     impressed that despite an architected timer in the newer chips SoC
     manufacturers insist on inventing new and differently broken SoC
     specific timers.

[ Ed. "Impressed"? I don't think that word means what you think it means ]

   - Another round of code move from arch to drivers.  Looks like most
     of the legacy mess in ARM regarding timers is sorted out except for
     a few obnoxious strongholds.

   - The usual updates and fixlets all over the place"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (114 commits)
  timekeeping: Fixup typo in update_vsyscall_old definition
  clocksource: document some basic timekeeping concepts
  timekeeping: Use cached ntp_tick_length when accumulating error
  timekeeping: Rework frequency adjustments to work better w/ nohz
  timekeeping: Minor fixup for timespec64->timespec assignment
  ftrace: Provide trace clocks monotonic
  timekeeping: Provide fast and NMI safe access to CLOCK_MONOTONIC
  seqcount: Add raw_write_seqcount_latch()
  seqcount: Provide raw_read_seqcount()
  timekeeping: Use tk_read_base as argument for timekeeping_get_ns()
  timekeeping: Create struct tk_read_base and use it in struct timekeeper
  timekeeping: Restructure the timekeeper some more
  clocksource: Get rid of cycle_last
  clocksource: Move cycle_last validation to core code
  clocksource: Make delta calculation a function
  wireless: ath9k: Get rid of timespec conversions
  drm: vmwgfx: Use nsec based interfaces
  drm: i915: Use nsec based interfaces
  timekeeping: Provide ktime_get_raw()
  hangcheck-timer: Use ktime_get_ns()
  ...

21 files changed, 92 insertions, 288 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 1e14b9068a39..d31c500653a2 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -65,7 +65,6 @@ config ARM
 	select HAVE_UID16
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN
 	select IRQ_FORCED_THREADING
-	select KTIME_SCALAR
 	select MODULES_USE_ELF_REL
 	select NO_BOOTMEM
 	select OLD_SIGACTION
@@ -648,6 +647,7 @@ config ARCH_PXA
 	select AUTO_ZRELADDR
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
+	select CLKSRC_OF
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
 	select HAVE_IDE
diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
index 490f3dced749..6eaddc47c43d 100644
--- a/arch/arm/common/bL_switcher.c
+++ b/arch/arm/common/bL_switcher.c
@@ -58,16 +58,6 @@ static int read_mpidr(void)
 }
 
 /*
- * Get a global nanosecond time stamp for tracing.
- */
-static s64 get_ns(void)
-{
-	struct timespec ts;
-	getnstimeofday(&ts);
-	return timespec_to_ns(&ts);
-}
-
-/*
  * bL switcher core code.
  */
 
@@ -224,7 +214,7 @@ static int bL_switch_to(unsigned int new_cluster_id)
 	 */
 	local_irq_disable();
 	local_fiq_disable();
-	trace_cpu_migrate_begin(get_ns(), ob_mpidr);
+	trace_cpu_migrate_begin(ktime_get_real_ns(), ob_mpidr);
 
 	/* redirect GIC's SGIs to our counterpart */
 	gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]);
@@ -267,7 +257,7 @@ static int bL_switch_to(unsigned int new_cluster_id)
 					  tdev->evtdev->next_event, 1);
 	}
 
-	trace_cpu_migrate_finish(get_ns(), ib_mpidr);
+	trace_cpu_migrate_finish(ktime_get_real_ns(), ib_mpidr);
 	local_fiq_enable();
 	local_irq_enable();
 
@@ -558,7 +548,7 @@ int bL_switcher_get_logical_index(u32 mpidr)
 
 static void bL_switcher_trace_trigger_cpu(void *__always_unused info)
 {
-	trace_cpu_migrate_current(get_ns(), read_mpidr());
+	trace_cpu_migrate_current(ktime_get_real_ns(), read_mpidr());
 }
 
 int bL_switcher_trace_trigger(void)
diff --git a/arch/arm/mach-pxa/Makefile b/arch/arm/mach-pxa/Makefile
index 648867a8caa8..2fe1824c6dcb 100644
--- a/arch/arm/mach-pxa/Makefile
+++ b/arch/arm/mach-pxa/Makefile
@@ -4,7 +4,7 @@
 
 # Common support (must be linked before board specific support)
 obj-y				+= clock.o devices.o generic.o irq.o \
-				   time.o reset.o
+				   reset.o
 obj-$(CONFIG_PM)		+= pm.o sleep.o standby.o
 
 # Generic drivers that other drivers may depend upon
diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c
index 42254175fcf4..6f38e1af45af 100644
--- a/arch/arm/mach-pxa/generic.c
+++ b/arch/arm/mach-pxa/generic.c
@@ -25,11 +25,13 @@
 #include <asm/mach/map.h>
 #include <asm/mach-types.h>
 
+#include <mach/irqs.h>
 #include <mach/reset.h>
 #include <mach/smemc.h>
 #include <mach/pxa3xx-regs.h>
 
 #include "generic.h"
+#include <clocksource/pxa.h>
 
 void clear_reset_status(unsigned int mask)
 {
@@ -57,6 +59,15 @@ unsigned long get_clock_tick_rate(void)
 EXPORT_SYMBOL(get_clock_tick_rate);
 
 /*
+ * For non device-tree builds, keep legacy timer init
+ */
+void pxa_timer_init(void)
+{
+	pxa_timer_nodt_init(IRQ_OST0, io_p2v(0x40a00000),
+			    get_clock_tick_rate());
+}
+
+/*
  * Get the clock frequency as reflected by CCCR and the turbo flag.
  * We assume these values have been applied via a fcs.
  * If info is not 0 we also display the current settings.
diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c
deleted file mode 100644
index fca174e3865d..000000000000
--- a/arch/arm/mach-pxa/time.c
+++ /dev/null
@@ -1,162 +0,0 @@
-/*
- * arch/arm/mach-pxa/time.c
- *
- * PXA clocksource, clockevents, and OST interrupt handlers.
- * Copyright (c) 2007 by Bill Gatliff <bgat@billgatliff.com>.
- *
- * Derived from Nicolas Pitre's PXA timer handler Copyright (c) 2001
- * by MontaVista Software, Inc.  (Nico, your code rocks!)
- *
- * 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/kernel.h>
-#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 <mach/regs-ost.h>
-#include <mach/irqs.h>
-
-/*
- * This is PXA's sched_clock implementation. This has a resolution
- * of at least 308 ns and a maximum value of 208 days.
- *
- * The return value is guaranteed to be monotonic in that range as
- * long as there is always less than 582 seconds between successive
- * calls to sched_clock() which should always be the case in practice.
- */
-
-static u64 notrace pxa_read_sched_clock(void)
-{
-	return readl_relaxed(OSCR);
-}
-
-
-#define MIN_OSCR_DELTA 16
-
-static irqreturn_t
-pxa_ost0_interrupt(int irq, void *dev_id)
-{
-	struct clock_event_device *c = dev_id;
-
-	/* Disarm the compare/match, signal the event. */
-	writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER);
-	writel_relaxed(OSSR_M0, OSSR);
-	c->event_handler(c);
-
-	return IRQ_HANDLED;
-}
-
-static int
-pxa_osmr0_set_next_event(unsigned long delta, struct clock_event_device *dev)
-{
-	unsigned long next, oscr;
-
-	writel_relaxed(readl_relaxed(OIER) | OIER_E0, OIER);
-	next = readl_relaxed(OSCR) + delta;
-	writel_relaxed(next, OSMR0);
-	oscr = readl_relaxed(OSCR);
-
-	return (signed)(next - oscr) <= MIN_OSCR_DELTA ? -ETIME : 0;
-}
-
-static void
-pxa_osmr0_set_mode(enum clock_event_mode mode, struct clock_event_device *dev)
-{
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER);
-		writel_relaxed(OSSR_M0, OSSR);
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		/* initializing, released, or preparing for suspend */
-		writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER);
-		writel_relaxed(OSSR_M0, OSSR);
-		break;
-
-	case CLOCK_EVT_MODE_RESUME:
-	case CLOCK_EVT_MODE_PERIODIC:
-		break;
-	}
-}
-
-#ifdef CONFIG_PM
-static unsigned long osmr[4], oier, oscr;
-
-static void pxa_timer_suspend(struct clock_event_device *cedev)
-{
-	osmr[0] = readl_relaxed(OSMR0);
-	osmr[1] = readl_relaxed(OSMR1);
-	osmr[2] = readl_relaxed(OSMR2);
-	osmr[3] = readl_relaxed(OSMR3);
-	oier = readl_relaxed(OIER);
-	oscr = readl_relaxed(OSCR);
-}
-
-static void pxa_timer_resume(struct clock_event_device *cedev)
-{
-	/*
-	 * Ensure that we have at least MIN_OSCR_DELTA between match
-	 * register 0 and the OSCR, to guarantee that we will receive
-	 * the one-shot timer interrupt.  We adjust OSMR0 in preference
-	 * to OSCR to guarantee that OSCR is monotonically incrementing.
-	 */
-	if (osmr[0] - oscr < MIN_OSCR_DELTA)
-		osmr[0] += MIN_OSCR_DELTA;
-
-	writel_relaxed(osmr[0], OSMR0);
-	writel_relaxed(osmr[1], OSMR1);
-	writel_relaxed(osmr[2], OSMR2);
-	writel_relaxed(osmr[3], OSMR3);
-	writel_relaxed(oier, OIER);
-	writel_relaxed(oscr, OSCR);
-}
-#else
-#define pxa_timer_suspend NULL
-#define pxa_timer_resume NULL
-#endif
-
-static struct clock_event_device ckevt_pxa_osmr0 = {
-	.name		= "osmr0",
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 200,
-	.set_next_event	= pxa_osmr0_set_next_event,
-	.set_mode	= pxa_osmr0_set_mode,
-	.suspend	= pxa_timer_suspend,
-	.resume		= pxa_timer_resume,
-};
-
-static struct irqaction pxa_ost0_irq = {
-	.name		= "ost0",
-	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
-	.handler	= pxa_ost0_interrupt,
-	.dev_id		= &ckevt_pxa_osmr0,
-};
-
-void __init pxa_timer_init(void)
-{
-	unsigned long clock_tick_rate = get_clock_tick_rate();
-
-	writel_relaxed(0, OIER);
-	writel_relaxed(OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3, OSSR);
-
-	sched_clock_register(pxa_read_sched_clock, 32, clock_tick_rate);
-
-	ckevt_pxa_osmr0.cpumask = cpumask_of(0);
-
-	setup_irq(IRQ_OST0, &pxa_ost0_irq);
-
-	clocksource_mmio_init(OSCR, "oscr0", clock_tick_rate, 200, 32,
-		clocksource_mmio_readl_up);
-	clockevents_config_and_register(&ckevt_pxa_osmr0, clock_tick_rate,
-		MIN_OSCR_DELTA * 2, 0x7fffffff);
-}
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 24f2e8c62479..a81a446a5786 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -219,7 +219,7 @@ struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 void update_vsyscall(struct timekeeper *tk)
 {
 	struct timespec xtime_coarse;
-	u32 use_syscall = strcmp(tk->clock->name, "arch_sys_counter");
+	u32 use_syscall = strcmp(tk->tkr.clock->name, "arch_sys_counter");
 
 	++vdso_data->tb_seq_count;
 	smp_wmb();
@@ -232,11 +232,11 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 
 	if (!use_syscall) {
-		vdso_data->cs_cycle_last	= tk->clock->cycle_last;
+		vdso_data->cs_cycle_last	= tk->tkr.cycle_last;
 		vdso_data->xtime_clock_sec	= tk->xtime_sec;
-		vdso_data->xtime_clock_nsec	= tk->xtime_nsec;
-		vdso_data->cs_mult		= tk->mult;
-		vdso_data->cs_shift		= tk->shift;
+		vdso_data->xtime_clock_nsec	= tk->tkr.xtime_nsec;
+		vdso_data->cs_mult		= tk->tkr.mult;
+		vdso_data->cs_shift		= tk->tkr.shift;
 	}
 
 	smp_wmb();
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 0fd6138f6203..4dc89d1f9c48 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -23,7 +23,6 @@ config HEXAGON
 	select GENERIC_IOMAP
 	select GENERIC_SMP_IDLE_THREAD
 	select STACKTRACE_SUPPORT
-	select KTIME_SCALAR
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select MODULES_USE_ELF_RELA
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 71c52bc7c28d..3e71ef85e439 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -441,7 +441,7 @@ void update_vsyscall_tz(void)
 }
 
 void update_vsyscall_old(struct timespec *wall, struct timespec *wtm,
-			struct clocksource *c, u32 mult)
+			 struct clocksource *c, u32 mult, cycle_t cycle_last)
 {
 	write_seqcount_begin(&fsyscall_gtod_data.seq);
 
@@ -450,7 +450,7 @@ void update_vsyscall_old(struct timespec *wall, struct timespec *wtm,
         fsyscall_gtod_data.clk_mult = mult;
         fsyscall_gtod_data.clk_shift = c->shift;
         fsyscall_gtod_data.clk_fsys_mmio = c->archdata.fsys_mmio;
-        fsyscall_gtod_data.clk_cycle_last = c->cycle_last;
+        fsyscall_gtod_data.clk_cycle_last = cycle_last;
 
 	/* copy kernel time structures */
         fsyscall_gtod_data.wall_time.tv_sec = wall->tv_sec;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 9fff9cdcc519..368ab374d33c 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -741,7 +741,7 @@ static cycle_t timebase_read(struct clocksource *cs)
 }
 
 void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm,
-			struct clocksource *clock, u32 mult)
+			 struct clocksource *clock, u32 mult, cycle_t cycle_last)
 {
 	u64 new_tb_to_xs, new_stamp_xsec;
 	u32 frac_sec;
@@ -774,7 +774,7 @@ void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm,
 	 * We expect the caller to have done the first increment of
 	 * vdso_data->tb_update_count already.
 	 */
-	vdso_data->tb_orig_stamp = clock->cycle_last;
+	vdso_data->tb_orig_stamp = cycle_last;
 	vdso_data->stamp_xsec = new_stamp_xsec;
 	vdso_data->tb_to_xs = new_tb_to_xs;
 	vdso_data->wtom_clock_sec = wtm->tv_sec;
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index f85db3a69b4a..2930d1e81a05 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -611,7 +611,6 @@ static int __init create_spu(void *data)
 	int ret;
 	static int number;
 	unsigned long flags;
-	struct timespec ts;
 
 	ret = -ENOMEM;
 	spu = kzalloc(sizeof (*spu), GFP_KERNEL);
@@ -652,8 +651,7 @@ static int __init create_spu(void *data)
 	mutex_unlock(&spu_full_list_mutex);
 
 	spu->stats.util_state = SPU_UTIL_IDLE_LOADED;
-	ktime_get_ts(&ts);
-	spu->stats.tstamp = timespec_to_ns(&ts);
+	spu->stats.tstamp = ktime_get_ns();
 
 	INIT_LIST_HEAD(&spu->aff_list);
 
@@ -676,7 +674,6 @@ static const char *spu_state_names[] = {
 static unsigned long long spu_acct_time(struct spu *spu,
 		enum spu_utilization_state state)
 {
-	struct timespec ts;
 	unsigned long long time = spu->stats.times[state];
 
 	/*
@@ -684,10 +681,8 @@ static unsigned long long spu_acct_time(struct spu *spu,
 	 * statistics are not updated.  Apply the time delta from the
 	 * last recorded state of the spu.
 	 */
-	if (spu->stats.util_state == state) {
-		ktime_get_ts(&ts);
-		time += timespec_to_ns(&ts) - spu->stats.tstamp;
-	}
+	if (spu->stats.util_state == state)
+		time += ktime_get_ns() - spu->stats.tstamp;
 
 	return time / NSEC_PER_MSEC;
 }
diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index 9c6790d17eda..3b4152faeb1f 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -36,7 +36,6 @@ atomic_t nr_spu_contexts = ATOMIC_INIT(0);
 struct spu_context *alloc_spu_context(struct spu_gang *gang)
 {
 	struct spu_context *ctx;
-	struct timespec ts;
 
 	ctx = kzalloc(sizeof *ctx, GFP_KERNEL);
 	if (!ctx)
@@ -67,8 +66,7 @@ struct spu_context *alloc_spu_context(struct spu_gang *gang)
 	__spu_update_sched_info(ctx);
 	spu_set_timeslice(ctx);
 	ctx->stats.util_state = SPU_UTIL_IDLE_LOADED;
-	ktime_get_ts(&ts);
-	ctx->stats.tstamp = timespec_to_ns(&ts);
+	ctx->stats.tstamp = ktime_get_ns();
 
 	atomic_inc(&nr_spu_contexts);
 	goto out;
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 90986923a53a..d966bbe58b8f 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -2338,7 +2338,6 @@ static const char *ctx_state_names[] = {
 static unsigned long long spufs_acct_time(struct spu_context *ctx,
 		enum spu_utilization_state state)
 {
-	struct timespec ts;
 	unsigned long long time = ctx->stats.times[state];
 
 	/*
@@ -2351,8 +2350,7 @@ static unsigned long long spufs_acct_time(struct spu_context *ctx,
 	 * of the spu context.
 	 */
 	if (ctx->spu && ctx->stats.util_state == state) {
-		ktime_get_ts(&ts);
-		time += timespec_to_ns(&ts) - ctx->stats.tstamp;
+		time += ktime_get_ns() - ctx->stats.tstamp;
 	}
 
 	return time / NSEC_PER_MSEC;
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 4a0a64fe25df..998f632e7cce 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -1039,13 +1039,11 @@ void spuctx_switch_state(struct spu_context *ctx,
 {
 	unsigned long long curtime;
 	signed long long delta;
-	struct timespec ts;
 	struct spu *spu;
 	enum spu_utilization_state old_state;
 	int node;
 
-	ktime_get_ts(&ts);
-	curtime = timespec_to_ns(&ts);
+	curtime = ktime_get_ns();
 	delta = curtime - ctx->stats.tstamp;
 
 	WARN_ON(!mutex_is_locked(&ctx->state_mutex));
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index f5af5f6ef0f4..720a11d339eb 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -136,7 +136,6 @@ config S390
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UID16 if 32BIT
 	select HAVE_VIRT_CPU_ACCOUNTING
-	select KTIME_SCALAR if 32BIT
 	select MODULES_USE_ELF_RELA
 	select NO_BOOTMEM
 	select OLD_SIGACTION
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 0931b110c826..4cef607f3711 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -214,26 +214,26 @@ void update_vsyscall(struct timekeeper *tk)
 {
 	u64 nsecps;
 
-	if (tk->clock != &clocksource_tod)
+	if (tk->tkr.clock != &clocksource_tod)
 		return;
 
 	/* Make userspace gettimeofday spin until we're done. */
 	++vdso_data->tb_update_count;
 	smp_wmb();
-	vdso_data->xtime_tod_stamp = tk->clock->cycle_last;
+	vdso_data->xtime_tod_stamp = tk->tkr.cycle_last;
 	vdso_data->xtime_clock_sec = tk->xtime_sec;
-	vdso_data->xtime_clock_nsec = tk->xtime_nsec;
+	vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec;
 	vdso_data->wtom_clock_sec =
 		tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
-	vdso_data->wtom_clock_nsec = tk->xtime_nsec +
-		+ ((u64) tk->wall_to_monotonic.tv_nsec << tk->shift);
-	nsecps = (u64) NSEC_PER_SEC << tk->shift;
+	vdso_data->wtom_clock_nsec = tk->tkr.xtime_nsec +
+		+ ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr.shift);
+	nsecps = (u64) NSEC_PER_SEC << tk->tkr.shift;
 	while (vdso_data->wtom_clock_nsec >= nsecps) {
 		vdso_data->wtom_clock_nsec -= nsecps;
 		vdso_data->wtom_clock_sec++;
 	}
-	vdso_data->tk_mult = tk->mult;
-	vdso_data->tk_shift = tk->shift;
+	vdso_data->tk_mult = tk->tkr.mult;
+	vdso_data->tk_shift = tk->tkr.shift;
 	smp_wmb();
 	++vdso_data->tb_update_count;
 }
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index 462dcd0c1700..d8fbc289e680 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -260,9 +260,8 @@ void update_vsyscall_tz(void)
 
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct timespec wall_time = tk_xtime(tk);
 	struct timespec *wtm = &tk->wall_to_monotonic;
-	struct clocksource *clock = tk->clock;
+	struct clocksource *clock = tk->tkr.clock;
 
 	if (clock != &cycle_counter_cs)
 		return;
@@ -270,13 +269,13 @@ void update_vsyscall(struct timekeeper *tk)
 	/* Userspace gettimeofday will spin while this value is odd. */
 	++vdso_data->tb_update_count;
 	smp_wmb();
-	vdso_data->xtime_tod_stamp = clock->cycle_last;
-	vdso_data->xtime_clock_sec = wall_time.tv_sec;
-	vdso_data->xtime_clock_nsec = wall_time.tv_nsec;
+	vdso_data->xtime_tod_stamp = tk->tkr.cycle_last;
+	vdso_data->xtime_clock_sec = tk->xtime_sec;
+	vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec;
 	vdso_data->wtom_clock_sec = wtm->tv_sec;
 	vdso_data->wtom_clock_nsec = wtm->tv_nsec;
-	vdso_data->mult = clock->mult;
-	vdso_data->shift = clock->shift;
+	vdso_data->mult = tk->tkr.mult;
+	vdso_data->shift = tk->tkr.shift;
 	smp_wmb();
 	++vdso_data->tb_update_count;
 }
diff --git a/arch/tile/kernel/vdso/vgettimeofday.c b/arch/tile/kernel/vdso/vgettimeofday.c
index 51ec8e46f5f9..e933fb9fbf5c 100644
--- a/arch/tile/kernel/vdso/vgettimeofday.c
+++ b/arch/tile/kernel/vdso/vgettimeofday.c
@@ -83,10 +83,11 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 		if (count & 1)
 			continue;
 
-		cycles = (get_cycles() - vdso_data->xtime_tod_stamp);
-		ns = (cycles * vdso_data->mult) >> vdso_data->shift;
 		sec = vdso_data->xtime_clock_sec;
-		ns += vdso_data->xtime_clock_nsec;
+		cycles = get_cycles() - vdso_data->xtime_tod_stamp;
+		ns = (cycles * vdso_data->mult) + vdso_data->xtime_clock_nsec;
+		ns >>= vdso_data->shift;
+
 		if (ns >= NSEC_PER_SEC) {
 			ns -= NSEC_PER_SEC;
 			sec += 1;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6b71f0417293..6cfeb082a422 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -108,9 +108,9 @@ config X86
 	select CLOCKSOURCE_WATCHDOG
 	select GENERIC_CLOCKEVENTS
 	select ARCH_CLOCKSOURCE_DATA
+	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
 	select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
 	select GENERIC_TIME_VSYSCALL
-	select KTIME_SCALAR if X86_32
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select HAVE_CONTEXT_TRACKING if X86_64
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 56b0c338061e..b6025f9e36c6 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -950,7 +950,7 @@ core_initcall(cpufreq_tsc);
 static struct clocksource clocksource_tsc;
 
 /*
- * We compare the TSC to the cycle_last value in the clocksource
+ * We used to compare the TSC to the cycle_last value in the clocksource
  * structure to avoid a nasty time-warp. This can be observed in a
  * very small window right after one CPU updated cycle_last under
  * xtime/vsyscall_gtod lock and the other CPU reads a TSC value which
@@ -960,26 +960,23 @@ static struct clocksource clocksource_tsc;
  * due to the unsigned delta calculation of the time keeping core
  * code, which is necessary to support wrapping clocksources like pm
  * timer.
+ *
+ * This sanity check is now done in the core timekeeping code.
+ * checking the result of read_tsc() - cycle_last for being negative.
+ * That works because CLOCKSOURCE_MASK(64) does not mask out any bit.
  */
 static cycle_t read_tsc(struct clocksource *cs)
 {
-	cycle_t ret = (cycle_t)get_cycles();
-
-	return ret >= clocksource_tsc.cycle_last ?
-		ret : clocksource_tsc.cycle_last;
-}
-
-static void resume_tsc(struct clocksource *cs)
-{
-	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
-		clocksource_tsc.cycle_last = 0;
+	return (cycle_t)get_cycles();
 }
 
+/*
+ * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
+ */
 static struct clocksource clocksource_tsc = {
 	.name                   = "tsc",
 	.rating                 = 300,
 	.read                   = read_tsc,
-	.resume			= resume_tsc,
 	.mask                   = CLOCKSOURCE_MASK(64),
 	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS |
 				  CLOCK_SOURCE_MUST_VERIFY,
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c
index 9531fbb123ba..c7d791f32b98 100644
--- a/arch/x86/kernel/vsyscall_gtod.c
+++ b/arch/x86/kernel/vsyscall_gtod.c
@@ -31,29 +31,30 @@ void update_vsyscall(struct timekeeper *tk)
 	gtod_write_begin(vdata);
 
 	/* copy vsyscall data */
-	vdata->vclock_mode	= tk->clock->archdata.vclock_mode;
-	vdata->cycle_last	= tk->clock->cycle_last;
-	vdata->mask		= tk->clock->mask;
-	vdata->mult		= tk->mult;
-	vdata->shift		= tk->shift;
+	vdata->vclock_mode	= tk->tkr.clock->archdata.vclock_mode;
+	vdata->cycle_last	= tk->tkr.cycle_last;
+	vdata->mask		= tk->tkr.mask;
+	vdata->mult		= tk->tkr.mult;
+	vdata->shift		= tk->tkr.shift;
 
 	vdata->wall_time_sec		= tk->xtime_sec;
-	vdata->wall_time_snsec		= tk->xtime_nsec;
+	vdata->wall_time_snsec		= tk->tkr.xtime_nsec;
 
 	vdata->monotonic_time_sec	= tk->xtime_sec
 					+ tk->wall_to_monotonic.tv_sec;
-	vdata->monotonic_time_snsec	= tk->xtime_nsec
+	vdata->monotonic_time_snsec	= tk->tkr.xtime_nsec
 					+ ((u64)tk->wall_to_monotonic.tv_nsec
-						<< tk->shift);
+						<< tk->tkr.shift);
 	while (vdata->monotonic_time_snsec >=
-					(((u64)NSEC_PER_SEC) << tk->shift)) {
+					(((u64)NSEC_PER_SEC) << tk->tkr.shift)) {
 		vdata->monotonic_time_snsec -=
-					((u64)NSEC_PER_SEC) << tk->shift;
+					((u64)NSEC_PER_SEC) << tk->tkr.shift;
 		vdata->monotonic_time_sec++;
 	}
 
 	vdata->wall_time_coarse_sec	= tk->xtime_sec;
-	vdata->wall_time_coarse_nsec	= (long)(tk->xtime_nsec >> tk->shift);
+	vdata->wall_time_coarse_nsec	= (long)(tk->tkr.xtime_nsec >>
+						 tk->tkr.shift);
 
 	vdata->monotonic_time_coarse_sec =
 		vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b86d329b953a..ca3d760dd581 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1020,9 +1020,8 @@ struct pvclock_gtod_data {
 		u32	shift;
 	} clock;
 
-	/* open coded 'struct timespec' */
-	u64		monotonic_time_snsec;
-	time_t		monotonic_time_sec;
+	u64		boot_ns;
+	u64		nsec_base;
 };
 
 static struct pvclock_gtod_data pvclock_gtod_data;
@@ -1030,27 +1029,21 @@ static struct pvclock_gtod_data pvclock_gtod_data;
 static void update_pvclock_gtod(struct timekeeper *tk)
 {
 	struct pvclock_gtod_data *vdata = &pvclock_gtod_data;
+	u64 boot_ns;
+
+	boot_ns = ktime_to_ns(ktime_add(tk->tkr.base_mono, tk->offs_boot));
 
 	write_seqcount_begin(&vdata->seq);
 
 	/* copy pvclock gtod data */
-	vdata->clock.vclock_mode	= tk->clock->archdata.vclock_mode;
-	vdata->clock.cycle_last		= tk->clock->cycle_last;
-	vdata->clock.mask		= tk->clock->mask;
-	vdata->clock.mult		= tk->mult;
-	vdata->clock.shift		= tk->shift;
-
-	vdata->monotonic_time_sec	= tk->xtime_sec
-					+ tk->wall_to_monotonic.tv_sec;
-	vdata->monotonic_time_snsec	= tk->xtime_nsec
-					+ (tk->wall_to_monotonic.tv_nsec
-						<< tk->shift);
-	while (vdata->monotonic_time_snsec >=
-					(((u64)NSEC_PER_SEC) << tk->shift)) {
-		vdata->monotonic_time_snsec -=
-					((u64)NSEC_PER_SEC) << tk->shift;
-		vdata->monotonic_time_sec++;
-	}
+	vdata->clock.vclock_mode	= tk->tkr.clock->archdata.vclock_mode;
+	vdata->clock.cycle_last		= tk->tkr.cycle_last;
+	vdata->clock.mask		= tk->tkr.mask;
+	vdata->clock.mult		= tk->tkr.mult;
+	vdata->clock.shift		= tk->tkr.shift;
+
+	vdata->boot_ns			= boot_ns;
+	vdata->nsec_base		= tk->tkr.xtime_nsec;
 
 	write_seqcount_end(&vdata->seq);
 }
@@ -1145,11 +1138,7 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
 
 static inline u64 get_kernel_ns(void)
 {
-	struct timespec ts;
-
-	ktime_get_ts(&ts);
-	monotonic_to_bootbased(&ts);
-	return timespec_to_ns(&ts);
+	return ktime_get_boot_ns();
 }
 
 #ifdef CONFIG_X86_64
@@ -1414,23 +1403,22 @@ static inline u64 vgettsc(cycle_t *cycle_now)
 	return v * gtod->clock.mult;
 }
 
-static int do_monotonic(struct timespec *ts, cycle_t *cycle_now)
+static int do_monotonic_boot(s64 *t, cycle_t *cycle_now)
 {
+	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	unsigned long seq;
-	u64 ns;
 	int mode;
-	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
+	u64 ns;
 
-	ts->tv_nsec = 0;
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
-		ts->tv_sec = gtod->monotonic_time_sec;
-		ns = gtod->monotonic_time_snsec;
+		ns = gtod->nsec_base;
 		ns += vgettsc(cycle_now);
 		ns >>= gtod->clock.shift;
+		ns += gtod->boot_ns;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
-	timespec_add_ns(ts, ns);
+	*t = ns;
 
 	return mode;
 }
@@ -1438,19 +1426,11 @@ static int do_monotonic(struct timespec *ts, cycle_t *cycle_now)
 /* returns true if host is using tsc clocksource */
 static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now)
 {
-	struct timespec ts;
-
 	/* checked again under seqlock below */
 	if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
 		return false;
 
-	if (do_monotonic(&ts, cycle_now) != VCLOCK_TSC)
-		return false;
-
-	monotonic_to_bootbased(&ts);
-	*kernel_ns = timespec_to_ns(&ts);
-
-	return true;
+	return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC;
 }
 #endif