1 files changed, 443 insertions, 526 deletions

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 3b26fbd6bec..9fff9cdcc51 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -17,8 +17,7 @@
  *
  * TODO (not necessarily in this file):
  * - improve precision and reproducibility of timebase frequency
- * measurement at boot time. (for iSeries, we calibrate the timebase
- * against the Titan chip's clock.)
+ * measurement at boot time.
  * - for astronomical applications: add a new function to get
  * non ambiguous timestamps even around leap seconds. This needs
  * a new timestamp format and a good name.
@@ -33,7 +32,7 @@
  */
 
 #include <linux/errno.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
@@ -43,6 +42,7 @@
 #include <linux/timex.h>
 #include <linux/kernel_stat.h>
 #include <linux/time.h>
+#include <linux/clockchips.h>
 #include <linux/init.h>
 #include <linux/profile.h>
 #include <linux/cpu.h>
@@ -52,6 +52,9 @@
 #include <linux/jiffies.h>
 #include <linux/posix-timers.h>
 #include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/irq_work.h>
+#include <asm/trace.h>
 
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -67,35 +70,27 @@
 #include <asm/vdso_datapage.h>
 #include <asm/firmware.h>
 #include <asm/cputime.h>
-#ifdef CONFIG_PPC_ISERIES
-#include <asm/iseries/it_lp_queue.h>
-#include <asm/iseries/hv_call_xm.h>
-#endif
 
 /* powerpc clocksource/clockevent code */
 
 #include <linux/clockchips.h>
-#include <linux/clocksource.h>
+#include <linux/timekeeper_internal.h>
 
-static cycle_t rtc_read(void);
+static cycle_t rtc_read(struct clocksource *);
 static struct clocksource clocksource_rtc = {
 	.name         = "rtc",
 	.rating       = 400,
 	.flags        = CLOCK_SOURCE_IS_CONTINUOUS,
 	.mask         = CLOCKSOURCE_MASK(64),
-	.shift        = 22,
-	.mult         = 0,	/* To be filled in */
 	.read         = rtc_read,
 };
 
-static cycle_t timebase_read(void);
+static cycle_t timebase_read(struct clocksource *);
 static struct clocksource clocksource_timebase = {
 	.name         = "timebase",
 	.rating       = 400,
 	.flags        = CLOCK_SOURCE_IS_CONTINUOUS,
 	.mask         = CLOCKSOURCE_MASK(64),
-	.shift        = 22,
-	.mult         = 0,	/* To be filled in */
 	.read         = timebase_read,
 };
 
@@ -106,31 +101,18 @@ static int decrementer_set_next_event(unsigned long evt,
 static void decrementer_set_mode(enum clock_event_mode mode,
 				 struct clock_event_device *dev);
 
-static struct clock_event_device decrementer_clockevent = {
-       .name           = "decrementer",
-       .rating         = 200,
-       .shift          = 16,
-       .mult           = 0,	/* To be filled in */
-       .irq            = 0,
-       .set_next_event = decrementer_set_next_event,
-       .set_mode       = decrementer_set_mode,
-       .features       = CLOCK_EVT_FEAT_ONESHOT,
+struct clock_event_device decrementer_clockevent = {
+	.name           = "decrementer",
+	.rating         = 200,
+	.irq            = 0,
+	.set_next_event = decrementer_set_next_event,
+	.set_mode       = decrementer_set_mode,
+	.features       = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP,
 };
+EXPORT_SYMBOL(decrementer_clockevent);
 
-struct decrementer_clock {
-	struct clock_event_device event;
-	u64 next_tb;
-};
-
-static DEFINE_PER_CPU(struct decrementer_clock, decrementers);
-
-#ifdef CONFIG_PPC_ISERIES
-static unsigned long __initdata iSeries_recal_titan;
-static signed long __initdata iSeries_recal_tb;
-
-/* Forward declaration is only needed for iSereis compiles */
-void __init clocksource_init(void);
-#endif
+DEFINE_PER_CPU(u64, decrementers_next_tb);
+static DEFINE_PER_CPU(struct clock_event_device, decrementers);
 
 #define XSEC_PER_SEC (1024*1024)
 
@@ -146,46 +128,32 @@ unsigned long tb_ticks_per_usec = 100; /* sane default */
 EXPORT_SYMBOL(tb_ticks_per_usec);
 unsigned long tb_ticks_per_sec;
 EXPORT_SYMBOL(tb_ticks_per_sec);	/* for cputime_t conversions */
-u64 tb_to_xs;
-unsigned tb_to_us;
-
-#define TICKLEN_SCALE	TICK_LENGTH_SHIFT
-u64 last_tick_len;	/* units are ns / 2^TICKLEN_SCALE */
-u64 ticklen_to_xs;	/* 0.64 fraction */
-
-/* If last_tick_len corresponds to about 1/HZ seconds, then
-   last_tick_len << TICKLEN_SHIFT will be about 2^63. */
-#define TICKLEN_SHIFT	(63 - 30 - TICKLEN_SCALE + SHIFT_HZ)
 
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL_GPL(rtc_lock);
 
 static u64 tb_to_ns_scale __read_mostly;
 static unsigned tb_to_ns_shift __read_mostly;
-static unsigned long boot_tb __read_mostly;
-
-struct gettimeofday_struct do_gtod;
+static u64 boot_tb __read_mostly;
 
 extern struct timezone sys_tz;
 static long timezone_offset;
 
 unsigned long ppc_proc_freq;
-EXPORT_SYMBOL(ppc_proc_freq);
+EXPORT_SYMBOL_GPL(ppc_proc_freq);
 unsigned long ppc_tb_freq;
+EXPORT_SYMBOL_GPL(ppc_tb_freq);
 
-static u64 tb_last_jiffy __cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(u64, last_jiffy);
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /*
  * Factors for converting from cputime_t (timebase ticks) to
- * jiffies, milliseconds, seconds, and clock_t (1/USER_HZ seconds).
+ * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds).
  * These are all stored as 0.64 fixed-point binary fractions.
  */
 u64 __cputime_jiffies_factor;
 EXPORT_SYMBOL(__cputime_jiffies_factor);
-u64 __cputime_msec_factor;
-EXPORT_SYMBOL(__cputime_msec_factor);
+u64 __cputime_usec_factor;
+EXPORT_SYMBOL(__cputime_usec_factor);
 u64 __cputime_sec_factor;
 EXPORT_SYMBOL(__cputime_sec_factor);
 u64 __cputime_clockt_factor;
@@ -193,14 +161,18 @@ EXPORT_SYMBOL(__cputime_clockt_factor);
 DEFINE_PER_CPU(unsigned long, cputime_last_delta);
 DEFINE_PER_CPU(unsigned long, cputime_scaled_last_delta);
 
+cputime_t cputime_one_jiffy;
+
+void (*dtl_consumer)(struct dtl_entry *, u64);
+
 static void calc_cputime_factors(void)
 {
 	struct div_result res;
 
 	div128_by_32(HZ, 0, tb_ticks_per_sec, &res);
 	__cputime_jiffies_factor = res.result_low;
-	div128_by_32(1000, 0, tb_ticks_per_sec, &res);
-	__cputime_msec_factor = res.result_low;
+	div128_by_32(1000000, 0, tb_ticks_per_sec, &res);
+	__cputime_usec_factor = res.result_low;
 	div128_by_32(1, 0, tb_ticks_per_sec, &res);
 	__cputime_sec_factor = res.result_low;
 	div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res);
@@ -208,185 +180,209 @@ static void calc_cputime_factors(void)
 }
 
 /*
- * Read the PURR on systems that have it, otherwise the timebase.
+ * Read the SPURR on systems that have it, otherwise the PURR,
+ * or if that doesn't exist return the timebase value passed in.
  */
-static u64 read_purr(void)
+static u64 read_spurr(u64 tb)
 {
+	if (cpu_has_feature(CPU_FTR_SPURR))
+		return mfspr(SPRN_SPURR);
 	if (cpu_has_feature(CPU_FTR_PURR))
 		return mfspr(SPRN_PURR);
-	return mftb();
+	return tb;
 }
 
-/*
- * Read the SPURR on systems that have it, otherwise the purr
- */
-static u64 read_spurr(u64 purr)
-{
-	/*
-	 * cpus without PURR won't have a SPURR
-	 * We already know the former when we use this, so tell gcc
-	 */
-	if (cpu_has_feature(CPU_FTR_PURR) && cpu_has_feature(CPU_FTR_SPURR))
-		return mfspr(SPRN_SPURR);
-	return purr;
-}
+#ifdef CONFIG_PPC_SPLPAR
 
 /*
- * Account time for a transition between system, hard irq
- * or soft irq state.
+ * Scan the dispatch trace log and count up the stolen time.
+ * Should be called with interrupts disabled.
  */
-void account_system_vtime(struct task_struct *tsk)
+static u64 scan_dispatch_log(u64 stop_tb)
 {
-	u64 now, nowscaled, delta, deltascaled, sys_time;
-	unsigned long flags;
+	u64 i = local_paca->dtl_ridx;
+	struct dtl_entry *dtl = local_paca->dtl_curr;
+	struct dtl_entry *dtl_end = local_paca->dispatch_log_end;
+	struct lppaca *vpa = local_paca->lppaca_ptr;
+	u64 tb_delta;
+	u64 stolen = 0;
+	u64 dtb;
+
+	if (!dtl)
+		return 0;
 
-	local_irq_save(flags);
-	now = read_purr();
-	nowscaled = read_spurr(now);
-	delta = now - get_paca()->startpurr;
-	deltascaled = nowscaled - get_paca()->startspurr;
-	get_paca()->startpurr = now;
-	get_paca()->startspurr = nowscaled;
-	if (!in_interrupt()) {
-		/* deltascaled includes both user and system time.
-		 * Hence scale it based on the purr ratio to estimate
-		 * the system time */
-		sys_time = get_paca()->system_time;
-		if (get_paca()->user_time)
-			deltascaled = deltascaled * sys_time /
-			     (sys_time + get_paca()->user_time);
-		delta += sys_time;
-		get_paca()->system_time = 0;
+	if (i == be64_to_cpu(vpa->dtl_idx))
+		return 0;
+	while (i < be64_to_cpu(vpa->dtl_idx)) {
+		dtb = be64_to_cpu(dtl->timebase);
+		tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) +
+			be32_to_cpu(dtl->ready_to_enqueue_time);
+		barrier();
+		if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) {
+			/* buffer has overflowed */
+			i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG;
+			dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
+			continue;
+		}
+		if (dtb > stop_tb)
+			break;
+		if (dtl_consumer)
+			dtl_consumer(dtl, i);
+		stolen += tb_delta;
+		++i;
+		++dtl;
+		if (dtl == dtl_end)
+			dtl = local_paca->dispatch_log;
 	}
-	account_system_time(tsk, 0, delta);
-	account_system_time_scaled(tsk, deltascaled);
-	per_cpu(cputime_last_delta, smp_processor_id()) = delta;
-	per_cpu(cputime_scaled_last_delta, smp_processor_id()) = deltascaled;
-	local_irq_restore(flags);
+	local_paca->dtl_ridx = i;
+	local_paca->dtl_curr = dtl;
+	return stolen;
 }
 
 /*
- * Transfer the user and system times accumulated in the paca
- * by the exception entry and exit code to the generic process
- * user and system time records.
- * Must be called with interrupts disabled.
+ * Accumulate stolen time by scanning the dispatch trace log.
+ * Called on entry from user mode.
  */
-void account_process_tick(struct task_struct *tsk, int user_tick)
+void accumulate_stolen_time(void)
 {
-	cputime_t utime, utimescaled;
+	u64 sst, ust;
 
-	utime = get_paca()->user_time;
-	get_paca()->user_time = 0;
-	account_user_time(tsk, utime);
+	u8 save_soft_enabled = local_paca->soft_enabled;
 
-	utimescaled = cputime_to_scaled(utime);
-	account_user_time_scaled(tsk, utimescaled);
-}
+	/* We are called early in the exception entry, before
+	 * soft/hard_enabled are sync'ed to the expected state
+	 * for the exception. We are hard disabled but the PACA
+	 * needs to reflect that so various debug stuff doesn't
+	 * complain
+	 */
+	local_paca->soft_enabled = 0;
 
-/*
- * Stuff for accounting stolen time.
- */
-struct cpu_purr_data {
-	int	initialized;			/* thread is running */
-	u64	tb;			/* last TB value read */
-	u64	purr;			/* last PURR value read */
-	u64	spurr;			/* last SPURR value read */
-};
+	sst = scan_dispatch_log(local_paca->starttime_user);
+	ust = scan_dispatch_log(local_paca->starttime);
+	local_paca->system_time -= sst;
+	local_paca->user_time -= ust;
+	local_paca->stolen_time += ust + sst;
 
-/*
- * Each entry in the cpu_purr_data array is manipulated only by its
- * "owner" cpu -- usually in the timer interrupt but also occasionally
- * in process context for cpu online.  As long as cpus do not touch
- * each others' cpu_purr_data, disabling local interrupts is
- * sufficient to serialize accesses.
- */
-static DEFINE_PER_CPU(struct cpu_purr_data, cpu_purr_data);
+	local_paca->soft_enabled = save_soft_enabled;
+}
 
-static void snapshot_tb_and_purr(void *data)
+static inline u64 calculate_stolen_time(u64 stop_tb)
 {
-	unsigned long flags;
-	struct cpu_purr_data *p = &__get_cpu_var(cpu_purr_data);
-
-	local_irq_save(flags);
-	p->tb = get_tb_or_rtc();
-	p->purr = mfspr(SPRN_PURR);
-	wmb();
-	p->initialized = 1;
-	local_irq_restore(flags);
+	u64 stolen = 0;
+
+	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
+		stolen = scan_dispatch_log(stop_tb);
+		get_paca()->system_time -= stolen;
+	}
+
+	stolen += get_paca()->stolen_time;
+	get_paca()->stolen_time = 0;
+	return stolen;
 }
 
-/*
- * Called during boot when all cpus have come up.
- */
-void snapshot_timebases(void)
+#else /* CONFIG_PPC_SPLPAR */
+static inline u64 calculate_stolen_time(u64 stop_tb)
 {
-	if (!cpu_has_feature(CPU_FTR_PURR))
-		return;
-	on_each_cpu(snapshot_tb_and_purr, NULL, 0, 1);
+	return 0;
 }
 
+#endif /* CONFIG_PPC_SPLPAR */
+
 /*
- * Must be called with interrupts disabled.
+ * Account time for a transition between system, hard irq
+ * or soft irq state.
  */
-void calculate_steal_time(void)
+static u64 vtime_delta(struct task_struct *tsk,
+			u64 *sys_scaled, u64 *stolen)
 {
-	u64 tb, purr;
-	s64 stolen;
-	struct cpu_purr_data *pme;
-
-	pme = &__get_cpu_var(cpu_purr_data);
-	if (!pme->initialized)
-		return;		/* !CPU_FTR_PURR or early in early boot */
-	tb = mftb();
-	purr = mfspr(SPRN_PURR);
-	stolen = (tb - pme->tb) - (purr - pme->purr);
-	if (stolen > 0)
-		account_steal_time(current, stolen);
-	pme->tb = tb;
-	pme->purr = purr;
+	u64 now, nowscaled, deltascaled;
+	u64 udelta, delta, user_scaled;
+
+	WARN_ON_ONCE(!irqs_disabled());
+
+	now = mftb();
+	nowscaled = read_spurr(now);
+	get_paca()->system_time += now - get_paca()->starttime;
+	get_paca()->starttime = now;
+	deltascaled = nowscaled - get_paca()->startspurr;
+	get_paca()->startspurr = nowscaled;
+
+	*stolen = calculate_stolen_time(now);
+
+	delta = get_paca()->system_time;
+	get_paca()->system_time = 0;
+	udelta = get_paca()->user_time - get_paca()->utime_sspurr;
+	get_paca()->utime_sspurr = get_paca()->user_time;
+
+	/*
+	 * Because we don't read the SPURR on every kernel entry/exit,
+	 * deltascaled includes both user and system SPURR ticks.
+	 * Apportion these ticks to system SPURR ticks and user
+	 * SPURR ticks in the same ratio as the system time (delta)
+	 * and user time (udelta) values obtained from the timebase
+	 * over the same interval.  The system ticks get accounted here;
+	 * the user ticks get saved up in paca->user_time_scaled to be
+	 * used by account_process_tick.
+	 */
+	*sys_scaled = delta;
+	user_scaled = udelta;
+	if (deltascaled != delta + udelta) {
+		if (udelta) {
+			*sys_scaled = deltascaled * delta / (delta + udelta);
+			user_scaled = deltascaled - *sys_scaled;
+		} else {
+			*sys_scaled = deltascaled;
+		}
+	}
+	get_paca()->user_time_scaled += user_scaled;
+
+	return delta;
 }
 
-#ifdef CONFIG_PPC_SPLPAR
-/*
- * Must be called before the cpu is added to the online map when
- * a cpu is being brought up at runtime.
- */
-static void snapshot_purr(void)
+void vtime_account_system(struct task_struct *tsk)
 {
-	struct cpu_purr_data *pme;
-	unsigned long flags;
+	u64 delta, sys_scaled, stolen;
 
-	if (!cpu_has_feature(CPU_FTR_PURR))
-		return;
-	local_irq_save(flags);
-	pme = &__get_cpu_var(cpu_purr_data);
-	pme->tb = mftb();
-	pme->purr = mfspr(SPRN_PURR);
-	pme->initialized = 1;
-	local_irq_restore(flags);
+	delta = vtime_delta(tsk, &sys_scaled, &stolen);
+	account_system_time(tsk, 0, delta, sys_scaled);
+	if (stolen)
+		account_steal_time(stolen);
 }
+EXPORT_SYMBOL_GPL(vtime_account_system);
 
-#endif /* CONFIG_PPC_SPLPAR */
-
-#else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
-#define calc_cputime_factors()
-#define calculate_steal_time()		do { } while (0)
-#endif
+void vtime_account_idle(struct task_struct *tsk)
+{
+	u64 delta, sys_scaled, stolen;
 
-#if !(defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR))
-#define snapshot_purr()			do { } while (0)
-#endif
+	delta = vtime_delta(tsk, &sys_scaled, &stolen);
+	account_idle_time(delta + stolen);
+}
 
 /*
- * Called when a cpu comes up after the system has finished booting,
- * i.e. as a result of a hotplug cpu action.
+ * Transfer the user time accumulated in the paca
+ * by the exception entry and exit code to the generic
+ * process user time records.
+ * Must be called with interrupts disabled.
+ * Assumes that vtime_account_system/idle() has been called
+ * recently (i.e. since the last entry from usermode) so that
+ * get_paca()->user_time_scaled is up to date.
  */
-void snapshot_timebase(void)
+void vtime_account_user(struct task_struct *tsk)
 {
-	__get_cpu_var(last_jiffy) = get_tb_or_rtc();
-	snapshot_purr();
+	cputime_t utime, utimescaled;
+
+	utime = get_paca()->user_time;
+	utimescaled = get_paca()->user_time_scaled;
+	get_paca()->user_time = 0;
+	get_paca()->user_time_scaled = 0;
+	get_paca()->utime_sspurr = 0;
+	account_user_time(tsk, utime, utimescaled);
 }
 
+#else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+#define calc_cputime_factors()
+#endif
+
 void __delay(unsigned long loops)
 {
 	unsigned long start;
@@ -415,51 +411,6 @@ void udelay(unsigned long usecs)
 }
 EXPORT_SYMBOL(udelay);
 
-
-/*
- * There are two copies of tb_to_xs and stamp_xsec so that no
- * lock is needed to access and use these values in
- * do_gettimeofday.  We alternate the copies and as long as a
- * reasonable time elapses between changes, there will never
- * be inconsistent values.  ntpd has a minimum of one minute
- * between updates.
- */
-static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
-			       u64 new_tb_to_xs)
-{
-	unsigned temp_idx;
-	struct gettimeofday_vars *temp_varp;
-
-	temp_idx = (do_gtod.var_idx == 0);
-	temp_varp = &do_gtod.vars[temp_idx];
-
-	temp_varp->tb_to_xs = new_tb_to_xs;
-	temp_varp->tb_orig_stamp = new_tb_stamp;
-	temp_varp->stamp_xsec = new_stamp_xsec;
-	smp_mb();
-	do_gtod.varp = temp_varp;
-	do_gtod.var_idx = temp_idx;
-
-	/*
-	 * tb_update_count is used to allow the userspace gettimeofday code
-	 * to assure itself that it sees a consistent view of the tb_to_xs and
-	 * stamp_xsec variables.  It reads the tb_update_count, then reads
-	 * tb_to_xs and stamp_xsec and then reads tb_update_count again.  If
-	 * the two values of tb_update_count match and are even then the
-	 * tb_to_xs and stamp_xsec values are consistent.  If not, then it
-	 * loops back and reads them again until this criteria is met.
-	 * We expect the caller to have done the first increment of
-	 * vdso_data->tb_update_count already.
-	 */
-	vdso_data->tb_orig_stamp = new_tb_stamp;
-	vdso_data->stamp_xsec = new_stamp_xsec;
-	vdso_data->tb_to_xs = new_tb_to_xs;
-	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
-	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
-	smp_wmb();
-	++(vdso_data->tb_update_count);
-}
-
 #ifdef CONFIG_SMP
 unsigned long profile_pc(struct pt_regs *regs)
 {
@@ -473,87 +424,101 @@ unsigned long profile_pc(struct pt_regs *regs)
 EXPORT_SYMBOL(profile_pc);
 #endif
 
-#ifdef CONFIG_PPC_ISERIES
+#ifdef CONFIG_IRQ_WORK
 
-/* 
- * This function recalibrates the timebase based on the 49-bit time-of-day
- * value in the Titan chip.  The Titan is much more accurate than the value
- * returned by the service processor for the timebase frequency.  
+/*
+ * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
  */
-
-static int __init iSeries_tb_recal(void)
+#ifdef CONFIG_PPC64
+static inline unsigned long test_irq_work_pending(void)
 {
-	struct div_result divres;
-	unsigned long titan, tb;
+	unsigned long x;
 
-	/* Make sure we only run on iSeries */
-	if (!firmware_has_feature(FW_FEATURE_ISERIES))
-		return -ENODEV;
+	asm volatile("lbz %0,%1(13)"
+		: "=r" (x)
+		: "i" (offsetof(struct paca_struct, irq_work_pending)));
+	return x;
+}
 
-	tb = get_tb();
-	titan = HvCallXm_loadTod();
-	if ( iSeries_recal_titan ) {
-		unsigned long tb_ticks = tb - iSeries_recal_tb;
-		unsigned long titan_usec = (titan - iSeries_recal_titan) >> 12;
-		unsigned long new_tb_ticks_per_sec   = (tb_ticks * USEC_PER_SEC)/titan_usec;
-		unsigned long new_tb_ticks_per_jiffy = (new_tb_ticks_per_sec+(HZ/2))/HZ;
-		long tick_diff = new_tb_ticks_per_jiffy - tb_ticks_per_jiffy;
-		char sign = '+';		
-		/* make sure tb_ticks_per_sec and tb_ticks_per_jiffy are consistent */
-		new_tb_ticks_per_sec = new_tb_ticks_per_jiffy * HZ;
-
-		if ( tick_diff < 0 ) {
-			tick_diff = -tick_diff;
-			sign = '-';
-		}
-		if ( tick_diff ) {
-			if ( tick_diff < tb_ticks_per_jiffy/25 ) {
-				printk( "Titan recalibrate: new tb_ticks_per_jiffy = %lu (%c%ld)\n",
-						new_tb_ticks_per_jiffy, sign, tick_diff );
-				tb_ticks_per_jiffy = new_tb_ticks_per_jiffy;
-				tb_ticks_per_sec   = new_tb_ticks_per_sec;
-				calc_cputime_factors();
-				div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres );
-				do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
-				tb_to_xs = divres.result_low;
-				do_gtod.varp->tb_to_xs = tb_to_xs;
-				vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
-				vdso_data->tb_to_xs = tb_to_xs;
-			}
-			else {
-				printk( "Titan recalibrate: FAILED (difference > 4 percent)\n"
-					"                   new tb_ticks_per_jiffy = %lu\n"
-					"                   old tb_ticks_per_jiffy = %lu\n",
-					new_tb_ticks_per_jiffy, tb_ticks_per_jiffy );
-			}
-		}
-	}
-	iSeries_recal_titan = titan;
-	iSeries_recal_tb = tb;
+static inline void set_irq_work_pending_flag(void)
+{
+	asm volatile("stb %0,%1(13)" : :
+		"r" (1),
+		"i" (offsetof(struct paca_struct, irq_work_pending)));
+}
 
-	/* Called here as now we know accurate values for the timebase */
-	clocksource_init();
-	return 0;
+static inline void clear_irq_work_pending(void)
+{
+	asm volatile("stb %0,%1(13)" : :
+		"r" (0),
+		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
-late_initcall(iSeries_tb_recal);
 
-/* Called from platform early init */
-void __init iSeries_time_init_early(void)
+#else /* 32-bit */
+
+DEFINE_PER_CPU(u8, irq_work_pending);
+
+#define set_irq_work_pending_flag()	__get_cpu_var(irq_work_pending) = 1
+#define test_irq_work_pending()		__get_cpu_var(irq_work_pending)
+#define clear_irq_work_pending()	__get_cpu_var(irq_work_pending) = 0
+
+#endif /* 32 vs 64 bit */
+
+void arch_irq_work_raise(void)
 {
-	iSeries_recal_tb = get_tb();
-	iSeries_recal_titan = HvCallXm_loadTod();
+	preempt_disable();
+	set_irq_work_pending_flag();
+	set_dec(1);
+	preempt_enable();
 }
-#endif /* CONFIG_PPC_ISERIES */
 
-/*
- * For iSeries shared processors, we have to let the hypervisor
- * set the hardware decrementer.  We set a virtual decrementer
- * in the lppaca and call the hypervisor if the virtual
- * decrementer is less than the current value in the hardware
- * decrementer. (almost always the new decrementer value will
- * be greater than the current hardware decementer so the hypervisor
- * call will not be needed)
- */
+#else  /* CONFIG_IRQ_WORK */
+
+#define test_irq_work_pending()	0
+#define clear_irq_work_pending()
+
+#endif /* CONFIG_IRQ_WORK */
+
+void __timer_interrupt(void)
+{
+	struct pt_regs *regs = get_irq_regs();
+	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	struct clock_event_device *evt = &__get_cpu_var(decrementers);
+	u64 now;
+
+	trace_timer_interrupt_entry(regs);
+
+	if (test_irq_work_pending()) {
+		clear_irq_work_pending();
+		irq_work_run();
+	}
+
+	now = get_tb_or_rtc();
+	if (now >= *next_tb) {
+		*next_tb = ~(u64)0;
+		if (evt->event_handler)
+			evt->event_handler(evt);
+		__get_cpu_var(irq_stat).timer_irqs_event++;
+	} else {
+		now = *next_tb - now;
+		if (now <= DECREMENTER_MAX)
+			set_dec((int)now);
+		/* We may have raced with new irq work */
+		if (test_irq_work_pending())
+			set_dec(1);
+		__get_cpu_var(irq_stat).timer_irqs_others++;
+	}
+
+#ifdef CONFIG_PPC64
+	/* collect purr register values often, for accurate calculations */
+	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
+		cu->current_tb = mfspr(SPRN_PURR);
+	}
+#endif
+
+	trace_timer_interrupt_exit(regs);
+}
 
 /*
  * timer_interrupt - gets called when the decrementer overflows,
@@ -562,93 +527,67 @@ void __init iSeries_time_init_early(void)
 void timer_interrupt(struct pt_regs * regs)
 {
 	struct pt_regs *old_regs;
-	struct decrementer_clock *decrementer =  &__get_cpu_var(decrementers);
-	struct clock_event_device *evt = &decrementer->event;
-	u64 now;
+	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
 
 	/* Ensure a positive value is written to the decrementer, or else
-	 * some CPUs will continuue to take decrementer exceptions */
+	 * some CPUs will continue to take decrementer exceptions.
+	 */
 	set_dec(DECREMENTER_MAX);
 
-#ifdef CONFIG_PPC32
-	if (atomic_read(&ppc_n_lost_interrupts) != 0)
-		do_IRQ(regs);
-#endif
-
-	now = get_tb_or_rtc();
-	if (now < decrementer->next_tb) {
-		/* not time for this event yet */
-		now = decrementer->next_tb - now;
-		if (now <= DECREMENTER_MAX)
-			set_dec((int)now);
+	/* Some implementations of hotplug will get timer interrupts while
+	 * offline, just ignore these and we also need to set
+	 * decrementers_next_tb as MAX to make sure __check_irq_replay
+	 * don't replay timer interrupt when return, otherwise we'll trap
+	 * here infinitely :(
+	 */
+	if (!cpu_online(smp_processor_id())) {
+		*next_tb = ~(u64)0;
 		return;
 	}
-	old_regs = set_irq_regs(regs);
-	irq_enter();
-
-	calculate_steal_time();
 
-#ifdef CONFIG_PPC_ISERIES
-	if (firmware_has_feature(FW_FEATURE_ISERIES))
-		get_lppaca()->int_dword.fields.decr_int = 0;
-#endif
+	/* Conditionally hard-enable interrupts now that the DEC has been
+	 * bumped to its maximum value
+	 */
+	may_hard_irq_enable();
 
-	if (evt->event_handler)
-		evt->event_handler(evt);
 
-#ifdef CONFIG_PPC_ISERIES
-	if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending())
-		process_hvlpevents();
+#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
+	if (atomic_read(&ppc_n_lost_interrupts) != 0)
+		do_IRQ(regs);
 #endif
 
-#ifdef CONFIG_PPC64
-	/* collect purr register values often, for accurate calculations */
-	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
-		cu->current_tb = mfspr(SPRN_PURR);
-	}
-#endif
+	old_regs = set_irq_regs(regs);
+	irq_enter();
 
+	__timer_interrupt();
 	irq_exit();
 	set_irq_regs(old_regs);
 }
 
-void wakeup_decrementer(void)
+/*
+ * Hypervisor decrementer interrupts shouldn't occur but are sometimes
+ * left pending on exit from a KVM guest.  We don't need to do anything
+ * to clear them, as they are edge-triggered.
+ */
+void hdec_interrupt(struct pt_regs *regs)
 {
-	unsigned long ticks;
-
-	/*
-	 * The timebase gets saved on sleep and restored on wakeup,
-	 * so all we need to do is to reset the decrementer.
-	 */
-	ticks = tb_ticks_since(__get_cpu_var(last_jiffy));
-	if (ticks < tb_ticks_per_jiffy)
-		ticks = tb_ticks_per_jiffy - ticks;
-	else
-		ticks = 1;
-	set_dec(ticks);
 }
 
 #ifdef CONFIG_SUSPEND
-void generic_suspend_disable_irqs(void)
+static void generic_suspend_disable_irqs(void)
 {
-	preempt_disable();
-
 	/* Disable the decrementer, so that it doesn't interfere
 	 * with suspending.
 	 */
 
-	set_dec(0x7fffffff);
+	set_dec(DECREMENTER_MAX);
 	local_irq_disable();
-	set_dec(0x7fffffff);
+	set_dec(DECREMENTER_MAX);
 }
 
-void generic_suspend_enable_irqs(void)
+static void generic_suspend_enable_irqs(void)
 {
-	wakeup_decrementer();
-
 	local_irq_enable();
-	preempt_enable();
 }
 
 /* Overrides the weak version in kernel/power/main.c */
@@ -668,23 +607,6 @@ void arch_suspend_enable_irqs(void)
 }
 #endif
 
-#ifdef CONFIG_SMP
-void __init smp_space_timers(unsigned int max_cpus)
-{
-	int i;
-	u64 previous_tb = per_cpu(last_jiffy, boot_cpuid);
-
-	/* make sure tb > per_cpu(last_jiffy, cpu) for all cpus always */
-	previous_tb -= tb_ticks_per_jiffy;
-
-	for_each_possible_cpu(i) {
-		if (i == boot_cpuid)
-			continue;
-		per_cpu(last_jiffy, i) = previous_tb;
-	}
-}
-#endif
-
 /*
  * Scheduler clock - returns current time in nanosec units.
  *
@@ -702,7 +624,7 @@ unsigned long long sched_clock(void)
 static int __init get_freq(char *name, int cells, unsigned long *val)
 {
 	struct device_node *cpu;
-	const unsigned int *fp;
+	const __be32 *fp;
 	int found = 0;
 
 	/* The cpu node should have timebase and clock frequency properties */
@@ -721,6 +643,17 @@ static int __init get_freq(char *name, int cells, unsigned long *val)
 	return found;
 }
 
+void start_cpu_decrementer(void)
+{
+#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
+	/* Clear any pending timer interrupts */
+	mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS);
+
+	/* Enable decrementer interrupt */
+	mtspr(SPRN_TCR, TCR_DIE);
+#endif /* defined(CONFIG_BOOKE) || defined(CONFIG_40x) */
+}
+
 void __init generic_calibrate_decr(void)
 {
 	ppc_tb_freq = DEFAULT_TB_FREQ;		/* hardcoded default */
@@ -740,18 +673,6 @@ void __init generic_calibrate_decr(void)
 		printk(KERN_ERR "WARNING: Estimating processor frequency "
 				"(not found)\n");
 	}
-
-#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
-	/* Set the time base to zero */
-	mtspr(SPRN_TBWL, 0);
-	mtspr(SPRN_TBWU, 0);
-
-	/* Clear any pending timer interrupts */
-	mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS);
-
-	/* Enable decrementer interrupt */
-	mtspr(SPRN_TCR, TCR_DIE);
-#endif
 }
 
 int update_persistent_clock(struct timespec now)
@@ -759,7 +680,7 @@ int update_persistent_clock(struct timespec now)
 	struct rtc_time tm;
 
 	if (!ppc_md.set_rtc_time)
-		return 0;
+		return -ENODEV;
 
 	to_tm(now.tv_sec + 1 + timezone_offset, &tm);
 	tm.tm_year -= 1900;
@@ -768,11 +689,12 @@ int update_persistent_clock(struct timespec now)
 	return ppc_md.set_rtc_time(&tm);
 }
 
-unsigned long read_persistent_clock(void)
+static void __read_persistent_clock(struct timespec *ts)
 {
 	struct rtc_time tm;
 	static int first = 1;
 
+	ts->tv_nsec = 0;
 	/* XXX this is a litle fragile but will work okay in the short term */
 	if (first) {
 		first = 0;
@@ -780,30 +702,49 @@ unsigned long read_persistent_clock(void)
 			timezone_offset = ppc_md.time_init();
 
 		/* get_boot_time() isn't guaranteed to be safe to call late */
-		if (ppc_md.get_boot_time)
-			return ppc_md.get_boot_time() -timezone_offset;
+		if (ppc_md.get_boot_time) {
+			ts->tv_sec = ppc_md.get_boot_time() - timezone_offset;
+			return;
+		}
+	}
+	if (!ppc_md.get_rtc_time) {
+		ts->tv_sec = 0;
+		return;
 	}
-	if (!ppc_md.get_rtc_time)
-		return 0;
 	ppc_md.get_rtc_time(&tm);
-	return mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday,
-		      tm.tm_hour, tm.tm_min, tm.tm_sec);
+
+	ts->tv_sec = mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday,
+			    tm.tm_hour, tm.tm_min, tm.tm_sec);
+}
+
+void read_persistent_clock(struct timespec *ts)
+{
+	__read_persistent_clock(ts);
+
+	/* Sanitize it in case real time clock is set below EPOCH */
+	if (ts->tv_sec < 0) {
+		ts->tv_sec = 0;
+		ts->tv_nsec = 0;
+	}
+		
 }
 
 /* clocksource code */
-static cycle_t rtc_read(void)
+static cycle_t rtc_read(struct clocksource *cs)
 {
 	return (cycle_t)get_rtc();
 }
 
-static cycle_t timebase_read(void)
+static cycle_t timebase_read(struct clocksource *cs)
 {
 	return (cycle_t)get_tb();
 }
 
-void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
+void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm,
+			struct clocksource *clock, u32 mult)
 {
-	u64 t2x, stamp_xsec;
+	u64 new_tb_to_xs, new_stamp_xsec;
+	u32 frac_sec;
 
 	if (clock != &clocksource_timebase)
 		return;
@@ -812,27 +753,45 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
 	++vdso_data->tb_update_count;
 	smp_mb();
 
-	/* XXX this assumes clock->shift == 22 */
-	/* 4611686018 ~= 2^(20+64-22) / 1e9 */
-	t2x = (u64) clock->mult * 4611686018ULL;
-	stamp_xsec = (u64) xtime.tv_nsec * XSEC_PER_SEC;
-	do_div(stamp_xsec, 1000000000);
-	stamp_xsec += (u64) xtime.tv_sec * XSEC_PER_SEC;
-	update_gtod(clock->cycle_last, stamp_xsec, t2x);
+	/* 19342813113834067 ~= 2^(20+64) / 1e9 */
+	new_tb_to_xs = (u64) mult * (19342813113834067ULL >> clock->shift);
+	new_stamp_xsec = (u64) wall_time->tv_nsec * XSEC_PER_SEC;
+	do_div(new_stamp_xsec, 1000000000);
+	new_stamp_xsec += (u64) wall_time->tv_sec * XSEC_PER_SEC;
+
+	BUG_ON(wall_time->tv_nsec >= NSEC_PER_SEC);
+	/* this is tv_nsec / 1e9 as a 0.32 fraction */
+	frac_sec = ((u64) wall_time->tv_nsec * 18446744073ULL) >> 32;
+
+	/*
+	 * tb_update_count is used to allow the userspace gettimeofday code
+	 * to assure itself that it sees a consistent view of the tb_to_xs and
+	 * stamp_xsec variables.  It reads the tb_update_count, then reads
+	 * tb_to_xs and stamp_xsec and then reads tb_update_count again.  If
+	 * the two values of tb_update_count match and are even then the
+	 * tb_to_xs and stamp_xsec values are consistent.  If not, then it
+	 * loops back and reads them again until this criteria is met.
+	 * 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->stamp_xsec = new_stamp_xsec;
+	vdso_data->tb_to_xs = new_tb_to_xs;
+	vdso_data->wtom_clock_sec = wtm->tv_sec;
+	vdso_data->wtom_clock_nsec = wtm->tv_nsec;
+	vdso_data->stamp_xtime = *wall_time;
+	vdso_data->stamp_sec_fraction = frac_sec;
+	smp_wmb();
+	++(vdso_data->tb_update_count);
 }
 
 void update_vsyscall_tz(void)
 {
-	/* Make userspace gettimeofday spin until we're done. */
-	++vdso_data->tb_update_count;
-	smp_mb();
 	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
 	vdso_data->tz_dsttime = sys_tz.tz_dsttime;
-	smp_mb();
-	++vdso_data->tb_update_count;
 }
 
-void __init clocksource_init(void)
+static void __init clocksource_init(void)
 {
 	struct clocksource *clock;
 
@@ -841,9 +800,7 @@ void __init clocksource_init(void)
 	else
 		clock = &clocksource_timebase;
 
-	clock->mult = clocksource_hz2mult(tb_ticks_per_sec, clock->shift);
-
-	if (clocksource_register(clock)) {
+	if (clocksource_register_hz(clock, tb_ticks_per_sec)) {
 		printk(KERN_ERR "clocksource: %s is already registered\n",
 		       clock->name);
 		return;
@@ -856,8 +813,13 @@ void __init clocksource_init(void)
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {
-	__get_cpu_var(decrementers).next_tb = get_tb_or_rtc() + evt;
+	__get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt;
 	set_dec(evt);
+
+	/* We may have raced with new irq work */
+	if (test_irq_work_pending())
+		set_dec(1);
+
 	return 0;
 }
 
@@ -868,15 +830,24 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 		decrementer_set_next_event(DECREMENTER_MAX, dev);
 }
 
+/* Interrupt handler for the timer broadcast IPI */
+void tick_broadcast_ipi_handler(void)
+{
+	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+
+	*next_tb = get_tb_or_rtc();
+	__timer_interrupt();
+}
+
 static void register_decrementer_clockevent(int cpu)
 {
-	struct clock_event_device *dec = &per_cpu(decrementers, cpu).event;
+	struct clock_event_device *dec = &per_cpu(decrementers, cpu);
 
 	*dec = decrementer_clockevent;
-	dec->cpumask = cpumask_of_cpu(cpu);
+	dec->cpumask = cpumask_of(cpu);
 
-	printk(KERN_DEBUG "clockevent: %s mult[%lx] shift[%d] cpu[%d]\n",
-	       dec->name, dec->mult, dec->shift, cpu);
+	printk_once(KERN_DEBUG "clockevent: %s mult[%x] shift[%d] cpu[%d]\n",
+		    dec->name, dec->mult, dec->shift, cpu);
 
 	clockevents_register_device(dec);
 }
@@ -885,8 +856,8 @@ static void __init init_decrementer_clockevent(void)
 {
 	int cpu = smp_processor_id();
 
-	decrementer_clockevent.mult = div_sc(ppc_tb_freq, NSEC_PER_SEC,
-					     decrementer_clockevent.shift);
+	clockevents_calc_mult_shift(&decrementer_clockevent, ppc_tb_freq, 4);
+
 	decrementer_clockevent.max_delta_ns =
 		clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent);
 	decrementer_clockevent.min_delta_ns =
@@ -897,6 +868,11 @@ static void __init init_decrementer_clockevent(void)
 
 void secondary_cpu_time_init(void)
 {
+	/* Start the decrementer on CPUs that have manual control
+	 * such as BookE
+	 */
+	start_cpu_decrementer();
+
 	/* FIME: Should make unrelatred change to move snapshot_timebase
 	 * call here ! */
 	register_decrementer_clockevent(smp_processor_id());
@@ -905,15 +881,13 @@ void secondary_cpu_time_init(void)
 /* This function is only called on the boot processor */
 void __init time_init(void)
 {
-	unsigned long flags;
 	struct div_result res;
-	u64 scale, x;
+	u64 scale;
 	unsigned shift;
 
 	if (__USE_RTC()) {
 		/* 601 processor: dec counts down by 128 every 128ns */
 		ppc_tb_freq = 1000000000;
-		tb_last_jiffy = get_rtcl();
 	} else {
 		/* Normal PowerPC with timebase register */
 		ppc_md.calibrate_decr();
@@ -921,47 +895,13 @@ void __init time_init(void)
 		       ppc_tb_freq / 1000000, ppc_tb_freq % 1000000);
 		printk(KERN_DEBUG "time_init: processor frequency   = %lu.%.6lu MHz\n",
 		       ppc_proc_freq / 1000000, ppc_proc_freq % 1000000);
-		tb_last_jiffy = get_tb();
 	}
 
 	tb_ticks_per_jiffy = ppc_tb_freq / HZ;
 	tb_ticks_per_sec = ppc_tb_freq;
 	tb_ticks_per_usec = ppc_tb_freq / 1000000;
-	tb_to_us = mulhwu_scale_factor(ppc_tb_freq, 1000000);
 	calc_cputime_factors();
-
-	/*
-	 * Calculate the length of each tick in ns.  It will not be
-	 * exactly 1e9/HZ unless ppc_tb_freq is divisible by HZ.
-	 * We compute 1e9 * tb_ticks_per_jiffy / ppc_tb_freq,
-	 * rounded up.
-	 */
-	x = (u64) NSEC_PER_SEC * tb_ticks_per_jiffy + ppc_tb_freq - 1;
-	do_div(x, ppc_tb_freq);
-	tick_nsec = x;
-	last_tick_len = x << TICKLEN_SCALE;
-
-	/*
-	 * Compute ticklen_to_xs, which is a factor which gets multiplied
-	 * by (last_tick_len << TICKLEN_SHIFT) to get a tb_to_xs value.
-	 * It is computed as:
-	 * ticklen_to_xs = 2^N / (tb_ticks_per_jiffy * 1e9)
-	 * where N = 64 + 20 - TICKLEN_SCALE - TICKLEN_SHIFT
-	 * which turns out to be N = 51 - SHIFT_HZ.
-	 * This gives the result as a 0.64 fixed-point fraction.
-	 * That value is reduced by an offset amounting to 1 xsec per
-	 * 2^31 timebase ticks to avoid problems with time going backwards
-	 * by 1 xsec when we do timer_recalc_offset due to losing the
-	 * fractional xsec.  That offset is equal to ppc_tb_freq/2^51
-	 * since there are 2^20 xsec in a second.
-	 */
-	div128_by_32((1ULL << 51) - ppc_tb_freq, 0,
-		     tb_ticks_per_jiffy << SHIFT_HZ, &res);
-	div128_by_32(res.result_high, res.result_low, NSEC_PER_SEC, &res);
-	ticklen_to_xs = res.result_low;
-
-	/* Compute tb_to_xs from tick_nsec */
-	tb_to_xs = mulhdu(last_tick_len << TICKLEN_SHIFT, ticklen_to_xs);
+	setup_cputime_one_jiffy();
 
 	/*
 	 * Compute scale factor for sched_clock.
@@ -984,38 +924,25 @@ void __init time_init(void)
 	/* Save the current timebase to pretty up CONFIG_PRINTK_TIME */
 	boot_tb = get_tb_or_rtc();
 
-	write_seqlock_irqsave(&xtime_lock, flags);
-
 	/* If platform provided a timezone (pmac), we correct the time */
-        if (timezone_offset) {
+	if (timezone_offset) {
 		sys_tz.tz_minuteswest = -timezone_offset / 60;
 		sys_tz.tz_dsttime = 0;
-        }
-
-	do_gtod.varp = &do_gtod.vars[0];
-	do_gtod.var_idx = 0;
-	do_gtod.varp->tb_orig_stamp = tb_last_jiffy;
-	__get_cpu_var(last_jiffy) = tb_last_jiffy;
-	do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC;
-	do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
-	do_gtod.varp->tb_to_xs = tb_to_xs;
-	do_gtod.tb_to_us = tb_to_us;
-
-	vdso_data->tb_orig_stamp = tb_last_jiffy;
+	}
+
 	vdso_data->tb_update_count = 0;
 	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
-	vdso_data->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC;
-	vdso_data->tb_to_xs = tb_to_xs;
 
-	time_freq = 0;
-
-	write_sequnlock_irqrestore(&xtime_lock, flags);
+	/* Start the decrementer on CPUs that have manual control
+	 * such as BookE
+	 */
+	start_cpu_decrementer();
 
-	/* Register the clocksource, if we're not running on iSeries */
-	if (!firmware_has_feature(FW_FEATURE_ISERIES))
-		clocksource_init();
+	/* Register the clocksource */
+	clocksource_init();
 
 	init_decrementer_clockevent();
+	tick_setup_hrtimer_broadcast();
 }
 
 
@@ -1098,39 +1025,6 @@ void to_tm(int tim, struct rtc_time * tm)
 	GregorianDay(tm);
 }
 
-/* Auxiliary function to compute scaling factors */
-/* Actually the choice of a timebase running at 1/4 the of the bus
- * frequency giving resolution of a few tens of nanoseconds is quite nice.
- * It makes this computation very precise (27-28 bits typically) which
- * is optimistic considering the stability of most processor clock
- * oscillators and the precision with which the timebase frequency
- * is measured but does not harm.
- */
-unsigned mulhwu_scale_factor(unsigned inscale, unsigned outscale)
-{
-        unsigned mlt=0, tmp, err;
-        /* No concern for performance, it's done once: use a stupid
-         * but safe and compact method to find the multiplier.
-         */
-  
-        for (tmp = 1U<<31; tmp != 0; tmp >>= 1) {
-                if (mulhwu(inscale, mlt|tmp) < outscale)
-			mlt |= tmp;
-        }
-  
-        /* We might still be off by 1 for the best approximation.
-         * A side effect of this is that if outscale is too large
-         * the returned value will be zero.
-         * Many corner cases have been checked and seem to work,
-         * some might have been forgotten in the test however.
-         */
-  
-        err = inscale * (mlt+1);
-        if (err <= inscale/2)
-		mlt++;
-        return mlt;
-}
-
 /*
  * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
  * result.
@@ -1163,3 +1057,26 @@ void div128_by_32(u64 dividend_high, u64 dividend_low,
 	dr->result_low  = ((u64)y << 32) + z;
 
 }
+
+/* We don't need to calibrate delay, we use the CPU timebase for that */
+void calibrate_delay(void)
+{
+	/* Some generic code (such as spinlock debug) use loops_per_jiffy
+	 * as the number of __delay(1) in a jiffy, so make it so
+	 */
+	loops_per_jiffy = tb_ticks_per_jiffy;
+}
+
+static int __init rtc_init(void)
+{
+	struct platform_device *pdev;
+
+	if (!ppc_md.get_rtc_time)
+		return -ENODEV;
+
+	pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0);
+
+	return PTR_ERR_OR_ZERO(pdev);
+}
+
+module_init(rtc_init);