2009-01-29 21:33:32

by Cliff Wickman

[permalink] [raw]
Subject: [PATCH] x86: UV fix uv_flush_send_and_wait



From: Cliff Wickman <[email protected]>

uv_flush_send_and_wait() should return a pointer if the broadcast
remote tlb shootdown requests fail. That causes the conventional IPI
method of shootdown to be used.

Diffed against 2.6.29-rc2
(Ingo's tree)

Signed-off-by: Cliff Wickman <[email protected]>
---
arch/x86/kernel/tlb_uv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)

Index: linux/arch/x86/kernel/tlb_uv.c
===================================================================
--- linux.orig/arch/x86/kernel/tlb_uv.c
+++ linux/arch/x86/kernel/tlb_uv.c
@@ -259,7 +259,7 @@ const struct cpumask *uv_flush_send_and_
* the cpu's, all of which are still in the mask.
*/
__get_cpu_var(ptcstats).ptc_i++;
- return 0;
+ return flush_mask;
}

/*


2009-01-30 15:03:17

by Ingo Molnar

[permalink] [raw]
Subject: Re: [PATCH] x86: UV fix uv_flush_send_and_wait


* Cliff Wickman <[email protected]> wrote:

> From: Cliff Wickman <[email protected]>
>
> uv_flush_send_and_wait() should return a pointer if the broadcast
> remote tlb shootdown requests fail. That causes the conventional IPI
> method of shootdown to be used.
>
> Diffed against 2.6.29-rc2
> (Ingo's tree)
>
> Signed-off-by: Cliff Wickman <[email protected]>
> ---
> arch/x86/kernel/tlb_uv.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)

Applied to tip/x86/urgnet, thanks Cliff!

Ingo

2009-01-30 15:21:07

by Tejun Heo

[permalink] [raw]
Subject: Re: [PATCH] x86: UV fix uv_flush_send_and_wait

Ingo Molnar wrote:
> * Cliff Wickman <[email protected]> wrote:
>
>> From: Cliff Wickman <[email protected]>
>>
>> uv_flush_send_and_wait() should return a pointer if the broadcast
>> remote tlb shootdown requests fail. That causes the conventional IPI
>> method of shootdown to be used.
>>
>> Diffed against 2.6.29-rc2
>> (Ingo's tree)
>>
>> Signed-off-by: Cliff Wickman <[email protected]>
>> ---
>> arch/x86/kernel/tlb_uv.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> Applied to tip/x86/urgnet, thanks Cliff!

Ingo, this patch shouldn't go into x86/urgent. This patch is to fix a
bug introduced by a patch in the percpu branch and not applicable to
x86/urgent.

Thanks.

--
tejun

2009-01-30 15:25:08

by Ingo Molnar

[permalink] [raw]
Subject: Re: [PATCH] x86: UV fix uv_flush_send_and_wait


* Tejun Heo <[email protected]> wrote:

> Ingo Molnar wrote:
> > * Cliff Wickman <[email protected]> wrote:
> >
> >> From: Cliff Wickman <[email protected]>
> >>
> >> uv_flush_send_and_wait() should return a pointer if the broadcast
> >> remote tlb shootdown requests fail. That causes the conventional IPI
> >> method of shootdown to be used.
> >>
> >> Diffed against 2.6.29-rc2
> >> (Ingo's tree)
> >>
> >> Signed-off-by: Cliff Wickman <[email protected]>
> >> ---
> >> arch/x86/kernel/tlb_uv.c | 2 +-
> >> 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > Applied to tip/x86/urgnet, thanks Cliff!
>
> Ingo, this patch shouldn't go into x86/urgent. This patch is to fix a
> bug introduced by a patch in the percpu branch and not applicable to
> x86/urgent.

ah, indeed, the UV cleanup you did. Please pick up this fix then too into
your tree - the two should go together. I dropped it from x86/urgent.

Ingo