Messages in this thread |  | | Subject | Re: [PATCH v1 2/2] perf/core: Fake regs for leaked kernel samples | From | "Jin, Yao" <> | Date | Mon, 10 Aug 2020 10:03:18 +0800 |
| |
Hi Peter,
On 8/7/2020 5:02 PM, peterz@infradead.org wrote: > On Fri, Aug 07, 2020 at 02:24:30PM +0800, Jin, Yao wrote: >> Hi Peter, >> >> On 8/6/2020 7:00 PM, peterz@infradead.org wrote: >>> On Thu, Aug 06, 2020 at 11:18:27AM +0200, peterz@infradead.org 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
|  |