PREEMPT

PREEMPT

[Greg Weeks]

Does anyone know of any current problems with CONFIG_PREEMPT on a 4kc 
malta board? We're seeing some oddness in the floating point emulator 
with PREEMPT_RT and wondered if it was in our RT code, or if it's from 
the base kernel code.

Greg W

Re: PREEMPT

[sjhill]

> The code base I'm dealing with is a 2.6.13 derivative
> with PREEMPT_RT support.  Looks like the problem was
> due to PREEMPT_RT confusing fpu_emulator_cop1Handler()
> resulting in a SIGBUS nailing the associated task.
> 
> I have it sort of working for soft FPU but expect it
> requires some attention to safely access a HW FPU where
> emulation assistance is needed.
> 
Um, did no one have a look at Atsushi Nemoto's patch earlier today
that addressed pre-emption and CPU1, or am I missing something?

-Steve

Re: PREEMPT

[Ralf Baechle]

On Thu, Oct 06, 2005 at 02:36:25PM -0400, Greg Weeks wrote:

> Does anyone know of any current problems with CONFIG_PREEMPT on a 4kc 
> malta board? We're seeing some oddness in the floating point emulator 
> with PREEMPT_RT and wondered if it was in our RT code, or if it's from 
> the base kernel code.

No known problem in current problems in that area.

  Ralf

Re: PREEMPT

[Greg Weeks]

Ralf Baechle wrote:

>On Thu, Oct 06, 2005 at 02:36:25PM -0400, Greg Weeks wrote:
>
>  
>
>>Does anyone know of any current problems with CONFIG_PREEMPT on a 4kc 
>>malta board? We're seeing some oddness in the floating point emulator 
>>with PREEMPT_RT and wondered if it was in our RT code, or if it's from 
>>the base kernel code.
>>    
>>
>
>No known problem in current problems in that area.
>
> 
>
I'd remembered some problems ages ago, but had thought they'd been 
fixed. John was just picking my brain about it so I thought I'd ask to 
be sure.

Greg W

Re: PREEMPT

[Ralf Baechle]

On Thu, Oct 06, 2005 at 02:52:22PM -0400, Greg Weeks wrote:

> I'd remembered some problems ages ago, but had thought they'd been 
> fixed. John was just picking my brain about it so I thought I'd ask to 
> be sure.

The problems I recall were all related to being preempted just while
fiddling with the hardware FPU - can't happen on the fpu-less 4Kc.
Another issue fixesd recently even though more cosmetic were a bunch
of global variables.

  Ralf

Re: PREEMPT

[john cooper]

Ralf Baechle wrote:
> On Thu, Oct 06, 2005 at 02:52:22PM -0400, Greg Weeks wrote:
> 
> 
>>I'd remembered some problems ages ago, but had thought they'd been 
>>fixed. John was just picking my brain about it so I thought I'd ask to 
>>be sure.
> 
> 
> The problems I recall were all related to being preempted just while
> fiddling with the hardware FPU - can't happen on the fpu-less 4Kc.
> Another issue fixesd recently even though more cosmetic were a bunch
> of global variables.

The code base I'm dealing with is a 2.6.13 derivative
with PREEMPT_RT support.  Looks like the problem was
due to PREEMPT_RT confusing fpu_emulator_cop1Handler()
resulting in a SIGBUS nailing the associated task.

I have it sort of working for soft FPU but expect it
requires some attention to safely access a HW FPU where
emulation assistance is needed.

-john

-- 
john.cooper@timesys.com

Re: PREEMPT

[Atsushi Nemoto]

>>>>> On Thu, 6 Oct 2005 13:45:55 -0500 (CDT), sjhill@realitydiluted.com said:

sjhill> Um, did no one have a look at Atsushi Nemoto's patch earlier
sjhill> today that addressed pre-emption and CPU1, or am I missing
sjhill> something?

The patch I posted yesterday affects just for ptrace.  I suppose this
is not irrelevant.

Also, though it might irrelevant too, I think there are still possible
bug related signal and fpu_context.  I'll post a patch again.

---
Atsushi Nemoto