Re: [PATCH] i386: Disable BTS and PEBS

[Like Xu <like.xu.linux@gmail.com>]

On 20/7/2022 2:53 am, Sean Christopherson wrote:
> On Tue, Jul 19, 2022, Paolo Bonzini wrote:
>> On 7/18/22 22:12, Sean Christopherson wrote:
>>> On Mon, Jul 18, 2022, Paolo Bonzini wrote:
>>>> This needs to be fixed in the kernel because old QEMU/new KVM is supported.
>>>
>>> I can't object to adding a quirk for this since KVM is breaking userspace, but on
>>> the KVM side we really need to stop "sanitizing" userspace inputs unless it puts
>>> the host at risk, because inevitably it leads to needing a quirk.
>>
>> The problem is not the sanitizing, it's that userspace literally cannot know
>> that this needs to be done because the feature bits are "backwards" (1 =
>> unavailable).
> 
> Yes, the bits being inverted contributed to KVM not providing a way for userspace
> to enumerate PEBS and BTS support, but lack of enumeration is a seperate issue.
> 
> If KVM had simply ignored invalid guest state from the get go, then userspace would
> never have gained a dependency on KVM sanitizing guest state.  The fact that KVM
> didn't enumerate support in any way is an orthogonal problem.  To play nice with
> older userspace, KVM will need to add a quirk to restore the sanizting code, but
> that doesn't solve the enumeration issue.  And vice versa, solving the enuemaration
> problem doesn't magically fix old userspace.
> 
>> The right way to fix it is probably to use feature MSRs and, by default,
>> leave the features marked as unavailable.  I'll think it through and post a
>> patch tomorrow for both KVM and QEMU (to enable PEBS).

Try to help:

KVM already have MSR_IA32_PERF_CAPABILITIES as a feature msr (to enable LBR/PEBS),
and KVM_CAP_PMU_CAPABILITY as vm ioctl extension for model specific crappiness.

> 
> Yeah, lack of CPUID bits is annoying.
> 
>