* 32-bit fp/simd race
@ 2015-06-18 2:56 Mario Smarduch
2015-06-18 3:24 ` 32-bit fp/simd race - never mind :) Mario Smarduch
0 siblings, 1 reply; 2+ messages in thread
From: Mario Smarduch @ 2015-06-18 2:56 UTC (permalink / raw)
To: kvmarm, christoffer.dall, Marc Zyngier, kvm
Maybe I've been looking at this code too long, but it
appears that on __kvm_vcpu_return we save/restore
fp/simd registers and then change to hyp role. In
between if we get an interrupt vCPU may be migrated
to another CPU? Or am I missing something?
Thanks,
- Mario
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: 32-bit fp/simd race - never mind :)
2015-06-18 2:56 32-bit fp/simd race Mario Smarduch
@ 2015-06-18 3:24 ` Mario Smarduch
0 siblings, 0 replies; 2+ messages in thread
From: Mario Smarduch @ 2015-06-18 3:24 UTC (permalink / raw)
To: kvmarm, christoffer.dall, Marc Zyngier, kvm
I have been looking at it for too long, my concepts
got twisted.
On 06/17/2015 07:56 PM, Mario Smarduch wrote:
> Maybe I've been looking at this code too long, but it
> appears that on __kvm_vcpu_return we save/restore
> fp/simd registers and then change to hyp role. In
> between if we get an interrupt vCPU may be migrated
> to another CPU? Or am I missing something?
>
> Thanks,
> - Mario
> _______________________________________________
> kvmarm mailing list
> kvmarm@lists.cs.columbia.edu
> https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
>
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2015-06-18 3:24 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-06-18 2:56 32-bit fp/simd race Mario Smarduch
2015-06-18 3:24 ` 32-bit fp/simd race - never mind :) Mario Smarduch
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).