Re: NMI vs #PF clash

[Avi Kivity]

On 05/22/2012 05:27 PM, Steven Rostedt wrote:
> On Tue, 2012-05-22 at 17:20 +0300, Avi Kivity wrote:
>> On 05/22/2012 05:09 PM, Steven Rostedt wrote:
>> >> > 
>> >> > Or we could just have the NMI always restore the cr2 register.
>> >> 
>> >> IMO that's best.
>> > 
>> > OK, I can whip up a patch, but I wont push that in till 3.6.
>> > 
>> 
>> Thanks.  Something I've noticed is that writing cr2 is slow, so you may
>> want to write it only if it has changed (which should be very rare).
>> 
> 
> Is reading it fast? Then we could do a two reads and only write when
> needed.

The upside is 70 cycles on one machine, see d3edefc0035669.


> 
> Something like this pseudo assembly
>  
> 	mov cr2, rax
> 	push rax
> 
> 	call do_nmi
> 
> 	pop rax
> 	mov cr2, rbx
> 	cmp rax, rbx
> 	be skip
> 	mov rax, cr2
> skip:
> 


Yes, provided no exceptions can happen at those points.


-- 
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/