From 860aed25a1f0936d4852ab936252b47cd1e630f1 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 1 Jun 2012 18:13:43 +1000 Subject: [PATCH] powerpc/time: Sanity check of decrementer expiration is necessary This reverts 68568add2c ("powerpc/time: Remove unnecessary sanity check of decrementer expiration"). We do need to check whether we have reached the expiration time of the next event, because we sometimes get an early decrementer interrupt, most notably when we set the decrementer to 1 in arch_irq_work_raise(). The effect of not having the sanity check is that if timer_interrupt() gets called early, we leave the decrementer set to its maximum value, which means we then don't get any more decrementer interrupts for about 4 seconds (or longer, depending on timebase frequency). I saw these pauses as a consequence of getting a stray hypervisor decrementer interrupt left over from exiting a KVM guest. This isn't quite a straight revert because of changes to the surrounding code, but it restores the same algorithm as was previously used. Cc: stable@vger.kernel.org Acked-by: Anton Blanchard Acked-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/time.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 99a995c2a3f2..be171ee73bf8 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -475,6 +475,7 @@ void timer_interrupt(struct pt_regs * regs) struct pt_regs *old_regs; u64 *next_tb = &__get_cpu_var(decrementers_next_tb); struct clock_event_device *evt = &__get_cpu_var(decrementers); + u64 now; /* Ensure a positive value is written to the decrementer, or else * some CPUs will continue to take decrementer exceptions. @@ -509,9 +510,16 @@ void timer_interrupt(struct pt_regs * regs) irq_work_run(); } - *next_tb = ~(u64)0; - if (evt->event_handler) - evt->event_handler(evt); + now = get_tb_or_rtc(); + if (now >= *next_tb) { + *next_tb = ~(u64)0; + if (evt->event_handler) + evt->event_handler(evt); + } else { + now = *next_tb - now; + if (now <= DECREMENTER_MAX) + set_dec((int)now); + } #ifdef CONFIG_PPC64 /* collect purr register values often, for accurate calculations */