Patchwork powerpc/time: Sanity check of decrementer expiration is necessary

login
register
mail settings
Submitter Paul Mackerras
Date June 1, 2012, 10:01 a.m.
Message ID <20120601100102.GA11714@pale.ozlabs.ibm.com>
Download mbox | patch
Permalink /patch/162303/
State Accepted, archived
Delegated to: Paul Mackerras
Headers show

Comments

Paul Mackerras - June 1, 2012, 10:01 a.m.
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@kernel.org
Cc: Anton Blanchard <anton@samba.org>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
If there are no objections, I'll send this to Linus shortly.  This
regression is present in 3.3 and 3.4 as well as current upstream.

 arch/powerpc/kernel/time.c |   14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)
Anton Blanchard - June 4, 2012, 2:31 a.m.
Hi Paul,

> 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.

Urgh, sorry for that mess.

Acked-by: Anton Blanchard <anton@samba.org>

Anton

> 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@kernel.org
> Cc: Anton Blanchard <anton@samba.org>
> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Signed-off-by: Paul Mackerras <paulus@samba.org>
> ---
> If there are no objections, I'll send this to Linus shortly.  This
> regression is present in 3.3 and 3.4 as well as current upstream.
> 
>  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 99a995c..be171ee 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 */

Patch

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 99a995c..be171ee 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 */