Merge branch 'powerpc.cherry-picks' into timers/clocksource

Conflicts:
	arch/powerpc/kernel/time.c

Reason: The powerpc next tree contains two commits which conflict with
the timekeeping changes:

8fd63a9e powerpc: Rework VDSO gettimeofday to prevent time going backwards
c1aa687d powerpc: Clean up obsolete code relating to decrementer and timebase

John Stultz identified them and provided the conflict resolution.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

11 files changed, 80 insertions, 363 deletions

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 9f0fc9e6ce0..7716e68f7b1 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -366,8 +366,5 @@ static inline void log_error(char *buf, unsigned int err_type, int fatal)
 #define machine_late_initcall(mach,fn)		__define_machine_initcall(mach,"7",fn,7)
 #define machine_late_initcall_sync(mach,fn)	__define_machine_initcall(mach,"7s",fn,7s)
 
-void generic_suspend_disable_irqs(void);
-void generic_suspend_enable_irqs(void);
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_MACHDEP_H */
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 27ccb764fda..dc779dfcf25 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -28,16 +28,12 @@
 extern unsigned long tb_ticks_per_jiffy;
 extern unsigned long tb_ticks_per_usec;
 extern unsigned long tb_ticks_per_sec;
-extern u64 tb_to_xs;
-extern unsigned      tb_to_us;
 
 struct rtc_time;
 extern void to_tm(int tim, struct rtc_time * tm);
 extern void GregorianDay(struct rtc_time *tm);
-extern time_t last_rtc_update;
 
 extern void generic_calibrate_decr(void);
-extern void wakeup_decrementer(void);
 extern void snapshot_timebase(void);
 
 extern void set_dec_cpu6(unsigned int val);
@@ -204,9 +200,6 @@ static inline unsigned long tb_ticks_since(unsigned long tstamp)
 extern u64 mulhdu(u64, u64);
 #endif
 
-extern void smp_space_timers(unsigned int);
-
-extern unsigned mulhwu_scale_factor(unsigned, unsigned);
 extern void div128_by_32(u64 dividend_high, u64 dividend_low,
 			 unsigned divisor, struct div_result *dr);
 
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index 13c2c283e17..08679c5319b 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -85,6 +85,7 @@ struct vdso_data {
 	__s32 wtom_clock_sec;			/* Wall to monotonic clock */
 	__s32 wtom_clock_nsec;
 	struct timespec stamp_xtime;	/* xtime as at tb_orig_stamp */
+	__u32 stamp_sec_fraction;	/* fractional seconds of stamp_xtime */
    	__u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls  */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
 };
@@ -105,6 +106,7 @@ struct vdso_data {
 	__s32 wtom_clock_sec;			/* Wall to monotonic clock */
 	__s32 wtom_clock_nsec;
 	struct timespec stamp_xtime;	/* xtime as at tb_orig_stamp */
+	__u32 stamp_sec_fraction;	/* fractional seconds of stamp_xtime */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
 	__u32 dcache_block_size;	/* L1 d-cache block size     */
 	__u32 icache_block_size;	/* L1 i-cache block size     */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 496cc5b3984..acbbac6aaa2 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -342,6 +342,7 @@ int main(void)
 	DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec));
 	DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
 	DEFINE(STAMP_XTIME, offsetof(struct vdso_data, stamp_xtime));
+	DEFINE(STAMP_SEC_FRAC, offsetof(struct vdso_data, stamp_sec_fraction));
 	DEFINE(CFG_ICACHE_BLOCKSZ, offsetof(struct vdso_data, icache_block_size));
 	DEFINE(CFG_DCACHE_BLOCKSZ, offsetof(struct vdso_data, dcache_block_size));
 	DEFINE(CFG_ICACHE_LOGBLOCKSZ, offsetof(struct vdso_data, icache_log_block_size));
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 5c196d1086d..8764daad309 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -288,8 +288,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 			max_cpus = NR_CPUS;
 	else
 		max_cpus = 1;
- 
-	smp_space_timers(max_cpus);
 
 	for_each_possible_cpu(cpu)
 		if (cpu != boot_cpuid)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index e215f76bba1..ce53dfa7130 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -149,16 +149,6 @@ 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	NTP_SCALE_SHIFT
-static u64 last_tick_len;	/* units are ns / 2^TICKLEN_SCALE */
-static 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);
@@ -174,7 +164,6 @@ unsigned long ppc_proc_freq;
 EXPORT_SYMBOL(ppc_proc_freq);
 unsigned long ppc_tb_freq;
 
-static u64 tb_last_jiffy __cacheline_aligned_in_smp;
 static DEFINE_PER_CPU(u64, last_jiffy);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
@@ -446,7 +435,6 @@ EXPORT_SYMBOL(profile_pc);
 
 static int __init iSeries_tb_recal(void)
 {
-	struct div_result divres;
 	unsigned long titan, tb;
 
 	/* Make sure we only run on iSeries */
@@ -477,10 +465,7 @@ static int __init iSeries_tb_recal(void)
 				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 );
-				tb_to_xs = divres.result_low;
 				vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
-				vdso_data->tb_to_xs = tb_to_xs;
 				setup_cputime_one_jiffy();
 			}
 			else {
@@ -643,27 +628,9 @@ void timer_interrupt(struct pt_regs * regs)
 	trace_timer_interrupt_exit(regs);
 }
 
-void wakeup_decrementer(void)
-{
-	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.
 	 */
@@ -673,12 +640,9 @@ void generic_suspend_disable_irqs(void)
 	set_dec(0x7fffffff);
 }
 
-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 */
@@ -698,23 +662,6 @@ 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.
  *
@@ -853,6 +800,7 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
 			struct clocksource *clock, u32 mult)
 {
 	u64 new_tb_to_xs, new_stamp_xsec;
+	u32 frac_sec;
 
 	if (clock != &clocksource_timebase)
 		return;
@@ -868,6 +816,10 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
 	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
@@ -885,6 +837,7 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
 	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);
 }
@@ -1002,15 +955,13 @@ 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();
@@ -1018,50 +969,15 @@ 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();
 	setup_cputime_one_jiffy();
 
 	/*
-	 * 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);
-
-	/*
 	 * Compute scale factor for sched_clock.
 	 * The calibrate_decr() function has set tb_ticks_per_sec,
 	 * which is the timebase frequency.
@@ -1082,21 +998,14 @@ 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) {
 		sys_tz.tz_minuteswest = -timezone_offset / 60;
 		sys_tz.tz_dsttime = 0;
         }
 
-	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) get_seconds() * XSEC_PER_SEC;
-	vdso_data->tb_to_xs = tb_to_xs;
-
-	write_sequnlock_irqrestore(&xtime_lock, flags);
 
 	/* Start the decrementer on CPUs that have manual control
 	 * such as BookE
@@ -1190,39 +1099,6 @@ 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.
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index ee038d4bf25..4ee09ee2e83 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -19,8 +19,10 @@
 /* Offset for the low 32-bit part of a field of long type */
 #ifdef CONFIG_PPC64
 #define LOPART	4
+#define TSPEC_TV_SEC	TSPC64_TV_SEC+LOPART
 #else
 #define LOPART	0
+#define TSPEC_TV_SEC	TSPC32_TV_SEC
 #endif
 
 	.text
@@ -41,23 +43,11 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
 	mr	r9, r3			/* datapage ptr in r9 */
 	cmplwi	r10,0			/* check if tv is NULL */
 	beq	3f
-	bl	__do_get_xsec@local	/* get xsec from tb & kernel */
-	bne-	2f			/* out of line -> do syscall */
-
-	/* seconds are xsec >> 20 */
-	rlwinm	r5,r4,12,20,31
-	rlwimi	r5,r3,12,0,19
-	stw	r5,TVAL32_TV_SEC(r10)
-
-	/* get remaining xsec and convert to usec. we scale
-	 * up remaining xsec by 12 bits and get the top 32 bits
-	 * of the multiplication
-	 */
-	rlwinm	r5,r4,12,0,19
-	lis	r6,1000000@h
-	ori	r6,r6,1000000@l
-	mulhwu	r5,r5,r6
-	stw	r5,TVAL32_TV_USEC(r10)
+	lis	r7,1000000@ha		/* load up USEC_PER_SEC */
+	addi	r7,r7,1000000@l		/* so we get microseconds in r4 */
+	bl	__do_get_tspec@local	/* get sec/usec from tb & kernel */
+	stw	r3,TVAL32_TV_SEC(r10)
+	stw	r4,TVAL32_TV_USEC(r10)
 
 3:	cmplwi	r11,0			/* check if tz is NULL */
 	beq	1f
@@ -70,14 +60,6 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
 	crclr	cr0*4+so
 	li	r3,0
 	blr
-
-2:
-	mtlr	r12
-	mr	r3,r10
-	mr	r4,r11
-	li	r0,__NR_gettimeofday
-	sc
-	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_gettimeofday)
 
@@ -100,7 +82,8 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	mr	r11,r4			/* r11 saves tp */
 	bl	__get_datapage@local	/* get data page */
 	mr	r9,r3			/* datapage ptr in r9 */
-
+	lis	r7,NSEC_PER_SEC@h	/* want nanoseconds */
+	ori	r7,r7,NSEC_PER_SEC@l
 50:	bl	__do_get_tspec@local	/* get sec/nsec from tb & kernel */
 	bne	cr1,80f			/* not monotonic -> all done */
 
@@ -198,83 +181,12 @@ V_FUNCTION_END(__kernel_clock_getres)
 
 
 /*
- * This is the core of gettimeofday() & friends, it returns the xsec
- * value in r3 & r4 and expects the datapage ptr (non clobbered)
- * in r9. clobbers r0,r4,r5,r6,r7,r8.
- * When returning, r8 contains the counter value that can be reused
- * by the monotonic clock implementation
- */
-__do_get_xsec:
-  .cfi_startproc
-	/* Check for update count & load values. We use the low
-	 * order 32 bits of the update count
-	 */
-1:	lwz	r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
-	andi.	r0,r8,1			/* pending update ? loop */
-	bne-	1b
-	xor	r0,r8,r8		/* create dependency */
-	add	r9,r9,r0
-
-	/* Load orig stamp (offset to TB) */
-	lwz	r5,CFG_TB_ORIG_STAMP(r9)
-	lwz	r6,(CFG_TB_ORIG_STAMP+4)(r9)
-
-	/* Get a stable TB value */
-2:	mftbu	r3
-	mftbl	r4
-	mftbu	r0
-	cmpl	cr0,r3,r0
-	bne-	2b
-
-	/* Substract tb orig stamp. If the high part is non-zero, we jump to
-	 * the slow path which call the syscall.
-	 * If it's ok, then we have our 32 bits tb_ticks value in r7
-	 */
-	subfc	r7,r6,r4
-	subfe.	r0,r5,r3
-	bne-	3f
-
-	/* Load scale factor & do multiplication */
-	lwz	r5,CFG_TB_TO_XS(r9)	/* load values */
-	lwz	r6,(CFG_TB_TO_XS+4)(r9)
-	mulhwu	r4,r7,r5
-	mulhwu	r6,r7,r6
-	mullw	r0,r7,r5
-	addc	r6,r6,r0
-
-	/* At this point, we have the scaled xsec value in r4 + XER:CA
-	 * we load & add the stamp since epoch
-	 */
-	lwz	r5,CFG_STAMP_XSEC(r9)
-	lwz	r6,(CFG_STAMP_XSEC+4)(r9)
-	adde	r4,r4,r6
-	addze	r3,r5
-
-	/* We now have our result in r3,r4. We create a fake dependency
-	 * on that result and re-check the counter
-	 */
-	or	r6,r4,r3
-	xor	r0,r6,r6
-	add	r9,r9,r0
-	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
-        cmpl    cr0,r8,r0		/* check if updated */
-	bne-	1b
-
-	/* Warning ! The caller expects CR:EQ to be set to indicate a
-	 * successful calculation (so it won't fallback to the syscall
-	 * method). We have overriden that CR bit in the counter check,
-	 * but fortunately, the loop exit condition _is_ CR:EQ set, so
-	 * we can exit safely here. If you change this code, be careful
-	 * of that side effect.
-	 */
-3:	blr
-  .cfi_endproc
-
-/*
- * This is the core of clock_gettime(), it returns the current
- * time in seconds and nanoseconds in r3 and r4.
+ * This is the core of clock_gettime() and gettimeofday(),
+ * it returns the current time in r3 (seconds) and r4.
+ * On entry, r7 gives the resolution of r4, either USEC_PER_SEC
+ * or NSEC_PER_SEC, giving r4 in microseconds or nanoseconds.
  * It expects the datapage ptr in r9 and doesn't clobber it.
- * It clobbers r0, r5, r6, r10 and returns NSEC_PER_SEC in r7.
+ * It clobbers r0, r5 and r6.
  * On return, r8 contains the counter value that can be reused.
  * This clobbers cr0 but not any other cr field.
  */
@@ -297,70 +209,58 @@ __do_get_tspec:
 2:	mftbu	r3
 	mftbl	r4
 	mftbu	r0
-	cmpl	cr0,r3,r0
+	cmplw	cr0,r3,r0
 	bne-	2b
 
 	/* Subtract tb orig stamp and shift left 12 bits.
 	 */
-	subfc	r7,r6,r4
+	subfc	r4,r6,r4
 	subfe	r0,r5,r3
 	slwi	r0,r0,12
-	rlwimi.	r0,r7,12,20,31
-	slwi	r7,r7,12
+	rlwimi.	r0,r4,12,20,31
+	slwi	r4,r4,12
 
-	/* Load scale factor & do multiplication */
+	/*
+	 * Load scale factor & do multiplication.
+	 * We only use the high 32 bits of the tb_to_xs value.
+	 * Even with a 1GHz timebase clock, the high 32 bits of
+	 * tb_to_xs will be at least 4 million, so the error from
+	 * ignoring the low 32 bits will be no more than 0.25ppm.
+	 * The error will just make the clock run very very slightly
+	 * slow until the next time the kernel updates the VDSO data,
+	 * at which point the clock will catch up to the kernel's value,
+	 * so there is no long-term error accumulation.
+	 */
 	lwz	r5,CFG_TB_TO_XS(r9)	/* load values */
-	lwz	r6,(CFG_TB_TO_XS+4)(r9)
-	mulhwu	r3,r7,r6
-	mullw	r10,r7,r5
-	mulhwu	r4,r7,r5
-	addc	r10,r3,r10
+	mulhwu	r4,r4,r5
 	li	r3,0
 
 	beq+	4f			/* skip high part computation if 0 */
 	mulhwu	r3,r0,r5
-	mullw	r7,r0,r5
-	mulhwu	r5,r0,r6
-	mullw	r6,r0,r6
-	adde	r4,r4,r7
-	addze	r3,r3
+	mullw	r5,r0,r5
 	addc	r4,r4,r5
 	addze	r3,r3
-	addc	r10,r10,r6
-
-4:	addze	r4,r4			/* add in carry */
-	lis	r7,NSEC_PER_SEC@h
-	ori	r7,r7,NSEC_PER_SEC@l
-	mulhwu	r4,r4,r7		/* convert to nanoseconds */
-
-	/* At this point, we have seconds & nanoseconds since the xtime
-	 * stamp in r3+CA and r4.  Load & add the xtime stamp.
+4:
+	/* At this point, we have seconds since the xtime stamp
+	 * as a 32.32 fixed-point number in r3 and r4.
+	 * Load & add the xtime stamp.
 	 */
-#ifdef CONFIG_PPC64
-	lwz	r5,STAMP_XTIME+TSPC64_TV_SEC+LOPART(r9)
-	lwz	r6,STAMP_XTIME+TSPC64_TV_NSEC+LOPART(r9)
-#else
-	lwz	r5,STAMP_XTIME+TSPC32_TV_SEC(r9)
-	lwz	r6,STAMP_XTIME+TSPC32_TV_NSEC(r9)
-#endif
-	add	r4,r4,r6
+	lwz	r5,STAMP_XTIME+TSPEC_TV_SEC(r9)
+	lwz	r6,STAMP_SEC_FRAC(r9)
+	addc	r4,r4,r6
 	adde	r3,r3,r5
 
-	/* We now have our result in r3,r4. We create a fake dependency
-	 * on that result and re-check the counter
+	/* We create a fake dependency on the result in r3/r4
+	 * and re-check the counter
 	 */
 	or	r6,r4,r3
 	xor	r0,r6,r6
 	add	r9,r9,r0
 	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
-        cmpl    cr0,r8,r0		/* check if updated */
+        cmplw	cr0,r8,r0		/* check if updated */
 	bne-	1b
 
-	/* check for nanosecond overflow and adjust if necessary */
-	cmpw	r4,r7
-	bltlr				/* all done if no overflow */
-	subf	r4,r7,r4		/* adjust if overflow */
-	addi	r3,r3,1
+	mulhwu	r4,r4,r7		/* convert to micro or nanoseconds */
 
 	blr
   .cfi_endproc
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index 262cd5857a5..e97a9a0dc4a 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -33,18 +33,11 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
 	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
 	cmpldi	r11,0			/* check if tv is NULL */
 	beq	2f
-	bl	V_LOCAL_FUNC(__do_get_xsec)	/* get xsec from tb & kernel */
-	lis     r7,15			/* r7 = 1000000 = USEC_PER_SEC */
-	ori     r7,r7,16960
-	rldicl  r5,r4,44,20		/* r5 = sec = xsec / XSEC_PER_SEC */
-	rldicr  r6,r5,20,43		/* r6 = sec * XSEC_PER_SEC */
-	std	r5,TVAL64_TV_SEC(r11)	/* store sec in tv */
-	subf	r0,r6,r4		/* r0 = xsec = (xsec - r6) */
-	mulld   r0,r0,r7		/* usec = (xsec * USEC_PER_SEC) /
-					 * XSEC_PER_SEC
-					 */
-	rldicl  r0,r0,44,20
-	std	r0,TVAL64_TV_USEC(r11)	/* store usec in tv */
+	lis	r7,1000000@ha		/* load up USEC_PER_SEC */
+	addi	r7,r7,1000000@l
+	bl	V_LOCAL_FUNC(__do_get_tspec) /* get sec/us from tb & kernel */
+	std	r4,TVAL64_TV_SEC(r11)	/* store sec in tv */
+	std	r5,TVAL64_TV_USEC(r11)	/* store usec in tv */
 2:	cmpldi	r10,0			/* check if tz is NULL */
 	beq	1f
 	lwz	r4,CFG_TZ_MINUTEWEST(r3)/* fill tz */
@@ -77,6 +70,8 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
   .cfi_register lr,r12
 	mr	r11,r4			/* r11 saves tp */
 	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
+	lis	r7,NSEC_PER_SEC@h	/* want nanoseconds */
+	ori	r7,r7,NSEC_PER_SEC@l
 50:	bl	V_LOCAL_FUNC(__do_get_tspec)	/* get time from tb & kernel */
 	bne	cr1,80f			/* if not monotonic, all done */
 
@@ -171,49 +166,12 @@ V_FUNCTION_END(__kernel_clock_getres)
 
 
 /*
- * This is the core of gettimeofday(), it returns the xsec
- * value in r4 and expects the datapage ptr (non clobbered)
- * in r3. clobbers r0,r4,r5,r6,r7,r8
- * When returning, r8 contains the counter value that can be reused
- */
-V_FUNCTION_BEGIN(__do_get_xsec)
-  .cfi_startproc
-	/* check for update count & load values */
-1:	ld	r8,CFG_TB_UPDATE_COUNT(r3)
-	andi.	r0,r8,1			/* pending update ? loop */
-	bne-	1b
-	xor	r0,r8,r8		/* create dependency */
-	add	r3,r3,r0
-
-	/* Get TB & offset it. We use the MFTB macro which will generate
-	 * workaround code for Cell.
-	 */
-	MFTB(r7)
-	ld	r9,CFG_TB_ORIG_STAMP(r3)
-	subf	r7,r9,r7
-
-	/* Scale result */
-	ld	r5,CFG_TB_TO_XS(r3)
-	mulhdu	r7,r7,r5
-
-	/* Add stamp since epoch */
-	ld	r6,CFG_STAMP_XSEC(r3)
-	add	r4,r6,r7
-
-	xor	r0,r4,r4
-	add	r3,r3,r0
-	ld	r0,CFG_TB_UPDATE_COUNT(r3)
-        cmpld   cr0,r0,r8		/* check if updated */
-	bne-	1b
-	blr
-  .cfi_endproc
-V_FUNCTION_END(__do_get_xsec)
-
-/*
- * This is the core of clock_gettime(), it returns the current
- * time in seconds and nanoseconds in r4 and r5.
+ * This is the core of clock_gettime() and gettimeofday(),
+ * it returns the current time in r4 (seconds) and r5.
+ * On entry, r7 gives the resolution of r5, either USEC_PER_SEC
+ * or NSEC_PER_SEC, giving r5 in microseconds or nanoseconds.
  * It expects the datapage ptr in r3 and doesn't clobber it.
- * It clobbers r0 and r6 and returns NSEC_PER_SEC in r7.
+ * It clobbers r0, r6 and r9.
  * On return, r8 contains the counter value that can be reused.
  * This clobbers cr0 but not any other cr field.
  */
@@ -229,18 +187,18 @@ V_FUNCTION_BEGIN(__do_get_tspec)
 	/* Get TB & offset it. We use the MFTB macro which will generate
 	 * workaround code for Cell.
 	 */
-	MFTB(r7)
+	MFTB(r6)
 	ld	r9,CFG_TB_ORIG_STAMP(r3)
-	subf	r7,r9,r7
+	subf	r6,r9,r6
 
 	/* Scale result */
 	ld	r5,CFG_TB_TO_XS(r3)
-	sldi	r7,r7,12		/* compute time since stamp_xtime */
-	mulhdu	r6,r7,r5		/* in units of 2^-32 seconds */
+	sldi	r6,r6,12		/* compute time since stamp_xtime */
+	mulhdu	r6,r6,r5		/* in units of 2^-32 seconds */
 
 	/* Add stamp since epoch */
 	ld	r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
-	ld	r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
+	lwz	r5,STAMP_SEC_FRAC(r3)
 	or	r0,r4,r5
 	or	r0,r0,r6
 	xor	r0,r0,r0
@@ -250,17 +208,11 @@ V_FUNCTION_BEGIN(__do_get_tspec)
 	bne-	1b			/* reload if so */
 
 	/* convert to seconds & nanoseconds and add to stamp */
-	lis	r7,NSEC_PER_SEC@h
-	ori	r7,r7,NSEC_PER_SEC@l
-	mulhwu	r0,r6,r7		/* compute nanoseconds and */
+	add	r6,r6,r5		/* add on fractional seconds of xtime */
+	mulhwu	r5,r6,r7		/* compute micro or nanoseconds and */
 	srdi	r6,r6,32		/* seconds since stamp_xtime */
-	clrldi	r0,r0,32
-	add	r5,r5,r0		/* add nanoseconds together */
-	cmpd	r5,r7			/* overflow? */
+	clrldi	r5,r5,32
 	add	r4,r4,r6
-	bltlr				/* all done if no overflow */
-	subf	r5,r7,r5		/* if overflow, adjust */
-	addi	r4,r4,1
 	blr
   .cfi_endproc
 V_FUNCTION_END(__do_get_tspec)
diff --git a/arch/powerpc/platforms/52xx/lite5200_pm.c b/arch/powerpc/platforms/52xx/lite5200_pm.c
index b5c753db125..80234e5921f 100644
--- a/arch/powerpc/platforms/52xx/lite5200_pm.c
+++ b/arch/powerpc/platforms/52xx/lite5200_pm.c
@@ -216,9 +216,6 @@ static int lite5200_pm_enter(suspend_state_t state)
 
 	lite5200_restore_regs();
 
-	/* restart jiffies */
-	wakeup_decrementer();
-
 	iounmap(mbar);
 	return 0;
 }
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pm.c b/arch/powerpc/platforms/52xx/mpc52xx_pm.c
index 76722532bd9..568cef63627 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pm.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pm.c
@@ -171,9 +171,6 @@ int mpc52xx_pm_enter(suspend_state_t state)
 	/* restore SRAM */
 	memcpy(sram, saved_sram, sram_size);
 
-	/* restart jiffies */
-	wakeup_decrementer();
-
 	/* reenable interrupts in PIC */
 	out_be32(&intr->main_mask, intr_main_mask);
 
diff --git a/arch/powerpc/platforms/powermac/cpufreq_32.c b/arch/powerpc/platforms/powermac/cpufreq_32.c
index 1e9eba175ff..415ca6d6b27 100644
--- a/arch/powerpc/platforms/powermac/cpufreq_32.c
+++ b/arch/powerpc/platforms/powermac/cpufreq_32.c
@@ -310,8 +310,12 @@ static int pmu_set_cpu_speed(int low_speed)
 	/* Restore low level PMU operations */
 	pmu_unlock();
 
-	/* Restore decrementer */
-	wakeup_decrementer();
+	/*
+	 * Restore decrementer; we'll take a decrementer interrupt
+	 * as soon as interrupts are re-enabled and the generic
+	 * clockevents code will reprogram it with the right value.
+	 */
+	set_dec(1);
 
 	/* Restore interrupts */
  	mpic_cpu_set_priority(pic_prio);