powerpc: Improve decrementer accuracy

I have been looking at sources of OS jitter and notice that after a long
NO_HZ idle period we wakeup too early:

relative time (us)    event
                      timer irq exit
    999946.405        timer irq entry
         4.835        timer irq exit
        21.685        timer irq entry
         3.540          timer (tick_sched_timer) entry

Here we slept for just under a second then took a timer interrupt that did
nothing. 21.685 us later we wake up again and do the work.

We set a rather low shift value of 16 for the decrementer clockevent, which I
think is causing this issue. On this box we have a 207MHz decrementer and see:

clockevent: decrementer mult[3501] shift[16] cpu[0]

For calculations of large intervals this mult/shift combination could be
off by a significant amount. I notice the sparc code has a loop that iterates
to find a mult/shift combination that maximises the shift value while
keeping mult under 32bit. With the patch below we get:

clockevent: decrementer mult[35015c20] shift[32] cpu[15]

And we no longer see the spurious wakeups.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 48571ac56fb7f9747e9e2cea8b05d44acc44802e..bee1443da7634d3cf9a062d9223a11d4a63540de 100644 (file)
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -109,7 +109,7 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 static struct clock_event_device decrementer_clockevent = {
        .name           = "decrementer",
        .rating         = 200,
-       .shift          = 16,
+       .shift          = 0,    /* To be filled in */
        .mult           = 0,    /* To be filled in */
        .irq            = 0,
        .set_next_event = decrementer_set_next_event,
@@ -843,6 +843,22 @@ static void decrementer_set_mode(enum clock_event_mode mode,
                decrementer_set_next_event(DECREMENTER_MAX, dev);
 }
 
+static void __init setup_clockevent_multiplier(unsigned long hz)
+{
+       u64 mult, shift = 32;
+
+       while (1) {
+               mult = div_sc(hz, NSEC_PER_SEC, shift);
+               if (mult && (mult >> 32UL) == 0UL)
+                       break;
+
+               shift--;
+       }
+
+       decrementer_clockevent.shift = shift;
+       decrementer_clockevent.mult = mult;
+}
+
 static void register_decrementer_clockevent(int cpu)
 {
        struct clock_event_device *dec = &per_cpu(decrementers, cpu).event;
@@ -860,8 +876,7 @@ 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);
+       setup_clockevent_multiplier(ppc_tb_freq);
        decrementer_clockevent.max_delta_ns =
                clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent);
        decrementer_clockevent.min_delta_ns =