KVM: arm64: Filtering PMU events
Get series with b4
b4 am [email protected]Versions newest first · linked by author and title
- v3 Latest5 patches 13 repliesIn review
- v22 patches 12 repliesSuperseded
- v12 patches 4 repliesSuperseded
Patches in v3 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/5 | KVM: arm64: Refactor PMU attribute error handlingarch/ | +9 | 2 replies | |
| 2/5 | KVM: arm64: Use event mask matching architecture revisionarch/ arch/ | +78 | 4 replies | |
| 3/5 | KVM: arm64: Add PMU event filtering infrastructurearch/ arch/ arch/ +1 more | +87 | 2 replies | |
| 4/5 | KVM: arm64: Mask out filtered events in PCMEID{0,1}_EL1arch/ arch/ include/ | +35 | 3 replies | |
| 5/5 | KVM: arm64: Document PMU filtering APIDocumentation/ | +46 | 2 replies |
Reviews trailers per patch
3 of 5 patches have a Reviewed-by or Acked-by.
| Patch | Andrew Jones | Eric Auger |
|---|---|---|
| 1/5 | ||
| 2/5 | ||
| 3/5 | R-b | |
| 4/5 | R-b | |
| 5/5 | R-b |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [PATCH v3 0/5] KVM: arm64: Filtering PMU events
It is at times necessary to prevent a guest from being able to sample certain events if multiple CPUs share resources such as a cache level. In this case, it would be interesting if the VMM could simply prevent certain events from being counted instead of hiding the PMU.
Given that most events are not architected, there is no easy way to designate which events shouldn't be counted other than specifying the raw event number.
Since I have no idea whether it is better to use an event whitelist or blacklist, the proposed API takes a cue from the x86 version and allows either allowing or denying counting of ranges of events. The event space being pretty large (16bits on ARMv8.1), the default policy is set by the first filter that gets installed (default deny if we first allow, default allow if we first deny).
The filter state is global to the guest, despite the PMU being per CPU. I'm not sure whether it would be worth it making it CPU-private.
As an example of what can be done in userspace, I have the corresponding kvmtool hack here[1].
* From v2:
- Split out the error handling refactor for clarity
- Added a terrible hack to fish out the PMU version, because BL is great
- Update the guest's view of PCMEID{0,1}_EL1
- General tidying up
* From v1:
- Cleaned up handling of the cycle counter
- Documented restrictions on SW_INC, CHAIN and CPU_CYCLES events
[1] https://git.kernel.org/pub/scm/linux/kernel/git/maz/kvmtool.git/commit/?h=pmu-filter
Marc Zyngier (5):
KVM: arm64: Refactor PMU attribute error handling
KVM: arm64: Use event mask matching architecture revision
KVM: arm64: Add PMU event filtering infrastructure
KVM: arm64: Mask out filtered events in PCMEID{0,1}_EL1
KVM: arm64: Document PMU filtering API
Documentation/virt/kvm/devices/vcpu.rst | 46 ++++++ arch/arm64/include/asm/kvm_host.h | 7 + arch/arm64/include/uapi/asm/kvm.h | 16 ++ arch/arm64/kvm/arm.c | 2 + arch/arm64/kvm/pmu-emul.c | 199 +++++++++++++++++++++--- arch/arm64/kvm/sys_regs.c | 5 +- include/kvm/arm_pmu.h | 5 + 7 files changed, 254 insertions(+), 26 deletions(-)
Signature · 6 lines
2.28.0 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm