On 21/05/2019 16:46, Jan Beulich wrote:
>>>> On 21.05.19 at 13:33, <andrew.coop...@citrix.com> wrote:
>> On 15/03/2019 10:47, Jan Beulich wrote:
>>> @@ -9312,7 +9386,8 @@ x86_emulate(
>>>
>>> if ( ea.type == OP_MEM )
>>> {
>>> - rc = ops->write(ea.mem.seg, ea.mem.off, mmvalp, 8 << vex.l,
>>> ctxt);
>>> + rc = ops->write(ea.mem.seg, truncate_ea(ea.mem.off +
>>> first_byte),
>>> + (void *)mmvalp + first_byte, op_bytes, ctxt);
>>> if ( rc != X86EMUL_OKAY )
>>> {
>>> asm volatile ( "ldmxcsr %0" :: "m" (mxcsr) );
>> This hunk doesn't appear to fit with the rest of the patch, because it
>> isn't the first use of first_byte.
>>
>> Have we been subtly broken before?
> I don't think so, no, but I admit I'm not sure I understand what
> you're saying above. The use of first_byte here is of course not
> the first use - it gets set in the hunk further up. The AVX form of
> VCVTPS2PH does not support fault suppression (as that's an
> AVX512 feature), and hence no such adjustment was needed
> here before.
Ah - what I hadn't spotted was that this is the special case for
vcvtps2ph, so this change is fine in context.
Acked-by: Andrew Cooper <andrew.coop...@citrix.com>
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
