Re: [RFC PATCH 04/11] x86,fpu: defer FPU restore until return to userspace

[Oleg Nesterov]

On 01/13, Oleg Nesterov wrote:
>
> But yes, I think we need the per-cpu "in_kernel_fpu" and irq_fpu_usable()
> must die. Please look at http://marc.info/?l=linux-kernel&m=14096628660929

Plus I think we need this to fix the race with math_state_restore()...
Please see http://marc.info/?l=linux-kernel&m=140992479607206

Unfortunately I forgot other problems I found in this area... And
I completely forgot the plan I had in mind ;)

Oleg.

--
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/