Re: [PATCH v1 2/2] perf/core: Fake regs for leaked kernel samples

[Jin, Yao]

Hi Peter,

On 8/7/2020 5:02 PM, peterz@xxxxxxxxxxxxx wrote:
> On Fri, Aug 07, 2020 at 02:24:30PM +0800, Jin, Yao wrote:
> > Hi Peter,
> >
> > On 8/6/2020 7:00 PM, peterz@xxxxxxxxxxxxx wrote:
> > > On Thu, Aug 06, 2020 at 11:18:27AM +0200, peterz@xxxxxxxxxxxxx wrote:
> > >
> > > > Suppose we have nested virt:
> > > >
> > > > 	L0-hv
> > > > 	|
> > > > 	G0/L1-hv
> > > > 	   |
> > > > 	   G1
> > > >
> > > > And we're running in G0, then:
> > > >
> > > >    - 'exclude_hv' would exclude L0 events
> > > >    - 'exclude_host' would ... exclude L1-hv events?
> > > >    - 'exclude_guest' would ... exclude G1 events?
> > >
> > > So in arch/x86/events/intel/core.c we have:
> > >
> > > static inline void intel_set_masks(struct perf_event *event, int idx)
> > > {
> > > 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
> > >
> > > 	if (event->attr.exclude_host)
> > > 		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
> > > 	if (event->attr.exclude_guest)
> > > 		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
> > > 	if (event_is_checkpointed(event))
> > > 		__set_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
> > > }
> >
> > exclude_host is now set by guest (pmc_reprogram_counter,
> > arch/x86/kvm/pmu.c). When enabling the event, we can check exclude_host to
> > know if it's a guest.
> >
> > Otherwise we may need more flags in event->attr to indicate the status.
> >
> > > which is, afaict, just plain wrong. Should that not be something like:
> > >
> > > 	if (!event->attr.exclude_host)
> > > 		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
> > > 	if (!event->attr.exclude_guest)
> > > 		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
> >
> > How can we know it's guest or host even if exclude_host is set in guest?
>
> I'm not following you, consider:
>
> 	xh	xg	h	g	h'	g'
> 	0	0	0	0	1	1
> 	0	1	1	0	1	0
> 	1	0	0	1	0	1
> 	1	1	1	1	0	0

Thanks for the table! It clearly shows the combinations of different conditions.

My understanding is:

xh = exclude_host
xg = exclude_guest
h = intel_ctrl_host_mask (before)
g = intel_ctrl_guest_mask (before)
h' = intel_ctrl_host_mask (after)
g' = intel_ctrl_guest_mask (after)


For guest, exclude_host = 1 and exclude_guest = 0

xh	xg	h	g	h'	g'
1	0	0	1	0	1

before/after values are not changed.

For host, exclude_host = 0 and exclude_guest = 1

xh	xg	h	g	h'	g'
0	1	1	0	1	0

before/after values are not changed.

> So the 0,0 and 1,1 cases get flipped. I have a suspicion, but this
> _really_ should have fat comments all over :-(

I'm not very sure about other cases.

xh	xg	h	g	h'	g'
0	0	0	0	1	1
1	1	1	1	0	0

The before/after values are just reversed. I don't know if there will be some negative impacts? 
Maybe we need more reviews here.

> What a sodding trainwreck..

:(

Thanks
Jin Yao