Re: [PATCH, RFC] x86-64: properly handle FPU code/dataselectors

[Jan Beulich]

>>> On 16.10.13 at 17:50, Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
> On Wed, Oct 16, 2013 at 8:36 AM, Jan Beulich <JBeulich@xxxxxxxx> wrote:
>>
>> In that case we use a 32-bit operand size [F]XRSTOR, and hence
>> the upper halves get treated as selectors, and the offsets get
>> zero-extended from the low halves, i.e. we preserve even more
>> state for such a 64-bit environment now too (albeit I doubt any
>> 64-bit code actually cares)
> 
> No, it does *not* preserve "more state".

So you're thinking of whenever the state gets copied out to some
(user) memory block, whereas the "more state" I wrote about
applies to what is stored in CPU registers. And I also said that
copying the state to use memory may require extra adjustments.
The question just is how to properly do that - without corrupting
state in the way you validly point out, but also without losing
state.

> It preserves *less* state, because the upper 32 bits of rip are now
> corrupted. Any 64-bit application that actually looks at the FP
> rip/rdp fields now get the WRONG VALUES.

But again - this isn't being done for ordinary 64-bit applications,
this is only happening for KVM guests. And there not being a
protocol for telling the caller whether a certain context hold
64-bit offsets or selector/offset pairs shouldn't be a reason to
think of a solution to the problem.

Jan

--
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/