Re: [Xen-devel] [PATCH] x86, paravirt, xen: Remove the 64-bit irq_enable_sysexit pvop

[Boris Ostrovsky <boris.ostrovsky@oracle.com>]

On 04/06/2015 04:03 PM, Andy Lutomirski wrote:
> On Mon, Apr 6, 2015 at 11:30 AM, Boris Ostrovsky
> <boris.ostrovsky@oracle.com> wrote:
>> On 04/06/2015 01:44 PM, Andrew Cooper wrote:
>>> On 06/04/2015 16:29, Andy Lutomirski wrote:
>>>> On Mon, Apr 6, 2015 at 7:10 AM, Konrad Rzeszutek Wilk
>>>> <konrad.wilk@oracle.com> wrote:
>>>>> On Fri, Apr 03, 2015 at 03:52:30PM -0700, Andy Lutomirski wrote:
>>>>>> [cc: Boris and Konrad.  Whoops]
>>>>>>
>>>>>> On Fri, Apr 3, 2015 at 3:51 PM, Andy Lutomirski <luto@kernel.org>
>>>>>> wrote:
>>>>>>> We don't use irq_enable_sysexit on 64-bit kernels any more.  Remove
>>>>> Is there an commit (or name of patch) that explains why
>>>>> 32-bit-user-space-on-64-bit
>>>>> kernels is unsavory?
>>>> sysexit never tasted very good :-p
>>>>
>>>> We're (hopefully) not breaking 32-bit-user-space-on-64-bit, but we're
>>>> trying an unconventional approach to making the code faster and less
>>>> scary.  As a result, 64-bit kernels won't use sysexit any more.
>>>> Hopefully Xen is okay with the slightly sneaky thing we're doing.
>>>> AFAICT Xen thinks of sysretl and sysexit as slightly funny irets, so I
>>>> don't expect there to be any problem.
>>> 64bit PV kernels must bounce through Xen to switch from the kernel to
>>> the user pagetables (since both kernel and userspace are both actually
>>> running in ring3 with user pages).
>>>
>>> As a result, exit to userspace ends up as a hypercall into Xen which has
>>> an effect very similar to an `iret`, but with some extra fixup in the
>>> background.
>>>
>>> I can't forsee any Xen issues as a result of this patch.
>>
>>
>> I ran tip plus this patch (plus another patch that fixes an unrelated Xen
>> regression in tip) through our test suite and it completed without problems.
>>
>> I also ran some very simple 32-bit programs in a 64-bit PV guest and didn't
>> see any problems there neither.
> At the risk of redundancy, did you test on Intel hardware?  At least
> on native systems, the code in question never executes on AMD systems.

Yes, the tests ran on Intel. I left them scheduled for overnight runs 
too and that will be executed on both AMD and Intel.

-boris