Skip to content

KVM: x86/pmu: Add support for AMD Host-Only/Guest-Only bits

Yosry Ahmed kvm lkml sashiko-reviews 4 versions – In review

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v7 Latest17 patches 16 repliesIn review
  2. v616 patches 8 repliesSuperseded
  3. v513 patches 10 repliesSuperseded
Earlier versions · 1
VersionPostedPatchesRepliesStatus
v46 patches31 repliesSuperseded

Changes in v7 from the cover letter

- Instead of creating __kvm_skip_emulated_instruction(), call svm_skip_emulated_instruction() directly when emulating VMRUN [Sean].
- Split bailing early on failed VMRUN into two patches, one for the actual fix (patch 2) and one for the code cleanup (patch 3).
- Add a Fixes tag for patch 3.
- Indentation fixes and changelog updates.

Patches in v7 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/17KVM: nSVM: Stop leaking single-stepping on VMRUN into L2arch/x86/kvm/svm/nested.c arch/x86/kvm/svm/svm.c arch/x86/kvm/svm/svm.h+18 -40 replies
2/17KVM: nSVM: Bail early out of VMRUN emulation if advancing RIP failsarch/x86/kvm/svm/nested.c+5 -40 replies
3/17KVM: nSVM: Unify RIP and PMU handling calls when emulating VMRUNarch/x86/kvm/svm/nested.c+8 -120 replies
4/17KVM: nSVM: Move VMRUN instruction retirement after entering guest modearch/x86/kvm/svm/nested.c+7 -30 replies
5/17KVM: x86: Move enable_pmu/enable_mediated_pmu to pmu.h and pmu.carch/x86/kvm/pmu.c arch/x86/kvm/pmu.h arch/x86/kvm/x86.c +1 more+13 -120 replies
6/17KVM: x86/pmu: Rename reprogram_counters() to clarify usagearch/x86/kvm/pmu.c arch/x86/kvm/pmu.h arch/x86/kvm/vmx/pmu_intel.c+6 -50 replies
7/17KVM: x86/pmu: Do a single atomic OR when reprogramming countersarch/x86/kvm/pmu.h+1 -40 replies
8/17KVM: x86/pmu: Check mediated PMU counter enablement before event filtersarch/x86/kvm/pmu.c+1 -11 reply
9/17KVM: x86/pmu: Add support for KVM_X86_PMU_OP_OPTIONAL_RET0arch/x86/include/asm/kvm-x86-pmu-ops.h arch/x86/include/asm/kvm_host.h arch/x86/kvm/pmu.c +1 more+15 -20 replies
10/17KVM: x86/pmu: Disable counters based on Host-Only/Guest-Only bits in SVMarch/x86/include/asm/kvm-x86-pmu-ops.h arch/x86/include/asm/perf_event.h arch/x86/kvm/pmu.c +2 more+39 -11 reply
11/17KVM: x86/pmu: Track mediated PMU counters with mode-specific enablesarch/x86/include/asm/kvm_host.h arch/x86/kvm/pmu.c arch/x86/kvm/pmu.h +1 more+16 -20 replies
12/17KVM: x86/pmu: Reprogram Host/Guest-Only counters on nested transitionsarch/x86/kvm/pmu.c arch/x86/kvm/pmu.h arch/x86/kvm/svm/nested.c +2 more+50 -40 replies
13/17KVM: x86/pmu: Allow Host-Only/Guest-Only bits with nSVM and mediated PMUarch/x86/kvm/svm/pmu.c+4 -00 replies
14/17KVM: selftests: Refactor allocating guest stack into a helpertools/testing/selftests/kvm/lib/x86/processor.c+25 -200 replies
15/17KVM: selftests: Allocate a dedicated guest page for x86 L2 guest stacktools/testing/selftests/kvm/include/x86/processor.h tools/testing/selftests/kvm/include/x86/svm_util.h tools/testing/selftests/kvm/include/x86/vmx.h +4 more+16 -64 replies
16/17KVM: selftests: Drop L1-provided stacks for L2 guests on x86tools/testing/selftests/kvm/include/x86/svm_util.h tools/testing/selftests/kvm/include/x86/vmx.h tools/testing/selftests/kvm/lib/x86/memstress.c +31 more+51 -1840 replies
17/17KVM: selftests: Add svm_pmu_host_guest_test for Host-Only/Guest-Only bitstools/testing/selftests/kvm/Makefile.kvm tools/testing/selftests/kvm/include/x86/pmu.h tools/testing/selftests/kvm/x86/svm_pmu_host_guest_test.c+223 -04 replies

Reviews trailers per patch

None of the 17 patches has a Reviewed-by or Acked-by.

PatchJim Mattson
1/17
2/17
3/17
4/17
5/17
6/17
7/17
8/17
9/17
10/17Originally-by
11/17
12/17
13/17
14/17
15/17
16/17
17/17

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.

Read the v7 thread

Cover letter [PATCH v7 00/17] KVM: x86/pmu: Add support for AMD Host-Only/Guest-Only bits

v7 of Jim and myself's series adding support for AMD's Host-Only and Guest-Only performance counter eventsel bits in KVM's mediated PMU passthrough implementation. The series keeps growing in size over versions. This is Sean's fault (as usual), as he keeps finding subtle problems and making excellent suggestions.

These bits allow an nSVM-enabled guest to configure performance counters that count only during L1 execution (Host-Only) or only during L2 execution (Guest-Only).

KVM updates the hardware event selector ENABLE bit at nested transitions and EFER.SVME changes such that counters only count in the appropriate mode.

The series grew significantly after v4, as it now includes semi-related nSVM fixups and selftests cleanups needed for the series. I think parts of this series can land independently (patches 1-8 and patches 14-16), but then the remaining series would depend on both.

v6 -> v7:
- Instead of creating __kvm_skip_emulated_instruction(), call svm_skip_emulated_instruction() directly when emulating VMRUN [Sean].
- Split bailing early on failed VMRUN into two patches, one for the actual fix (patch 2) and one for the code cleanup (patch 3).
- Add a Fixes tag for patch 3.
- Indentation fixes and changelog updates.

v5 -> v6:
- Use a per-counter PMU callback that is called from pmc_is_locally_enabled(), rather than a single callback for all counters from kvm_pmu_handle_event(). This is mainly to address the problem Sashiko found where kvm_pmu_recalc_pmc_emulation() does not capture counter disablement due to Host-Only/Guest-Only bits [Sean].
- Move the bitmap tracking counters using Host-Only/Guest-Only bits from SVM code to the generic PMU code (and in its own patch), as it's now a generic optimization for pmc_is_locally_enabled() that is reused by SVM code on nested transitions [Sean].

v4 -> v5:
- Dropped moving leave_guest_mode() and enter_guest_mode() definitions, since the calls to update the vPMU no longer happen within these functions.
- Add PMU helpers refactoring to facilitate SVM usage.
- Added nested SVM fixups to count VMRUN correctly in guest mode when Host-Only/Guest-Only support is enabled [Jim/Sean].
- Update the vPMU synchronously on nested VM-Enter/VM-Exit and EFER.SVME changes, such that counter enablement is reevaluated before the instructions are counted, as the vPMU counts based on the vCPU state at instruction retirement (e.g. using new EFER value when EFER.SVME changes) [Jim/Sean].
- Keep deferring vPMU updates using KVM_REQ_PMU in the svm_leave_nested() path to avoid KVM potentially consuming stale state [Sean].
- Use a single PMU callback for reprogramming counters instead of a per-counter callback [Sean].
- Move the bitmap tracking counters into SVM code. The generic vPMU code now only exposes an API to reprogram counters, and an SVM wrapper uses it on nested transitions [Sean].
- Drop the manual stack-alignment fixes in the vPMU selftest, instead rework L2 stack setup in all nested selftests to reuse the allocation and alignment logic used by L1, and completely drop L1-provided stacks for L2 [Sean].

v6: https://lore.kernel.org/kvm/[email protected]/
v5: https://lore.kernel.org/kvm/[email protected]/
v4: https://lore.kernel.org/kvm/[email protected]/

Jim Mattson (2):
KVM: x86/pmu: Allow Host-Only/Guest-Only bits with nSVM and mediated
PMU
KVM: selftests: Add svm_pmu_host_guest_test for Host-Only/Guest-Only
bits

Yosry Ahmed (15):
KVM: nSVM: Stop leaking single-stepping on VMRUN into L2
KVM: nSVM: Bail early out of VMRUN emulation if advancing RIP fails
KVM: nSVM: Unify RIP and PMU handling calls when emulating VMRUN
KVM: nSVM: Move VMRUN instruction retirement after entering guest mode
KVM: x86: Move enable_pmu/enable_mediated_pmu to pmu.h and pmu.c
KVM: x86/pmu: Rename reprogram_counters() to clarify usage
KVM: x86/pmu: Do a single atomic OR when reprogramming counters
KVM: x86/pmu: Check mediated PMU counter enablement before event
filters
KVM: x86/pmu: Add support for KVM_X86_PMU_OP_OPTIONAL_RET0
KVM: x86/pmu: Disable counters based on Host-Only/Guest-Only bits in
SVM
KVM: x86/pmu: Track mediated PMU counters with mode-specific enables
KVM: x86/pmu: Reprogram Host/Guest-Only counters on nested transitions
KVM: selftests: Refactor allocating guest stack into a helper
KVM: selftests: Allocate a dedicated guest page for x86 L2 guest stack
KVM: selftests: Drop L1-provided stacks for L2 guests on x86

 arch/x86/include/asm/kvm-x86-pmu-ops.h        |   5 +-
 arch/x86/include/asm/kvm_host.h               |   3 +-
 arch/x86/include/asm/perf_event.h             |   2 +
 arch/x86/kvm/pmu.c                            |  21 +-
 arch/x86/kvm/pmu.h                            |  44 +++-
 arch/x86/kvm/svm/nested.c                     |  43 +++-
 arch/x86/kvm/svm/pmu.c                        |  42 ++++
 arch/x86/kvm/svm/svm.c                        |   3 +-
 arch/x86/kvm/svm/svm.h                        |  24 ++
 arch/x86/kvm/vmx/pmu_intel.c                  |   2 +-
 arch/x86/kvm/x86.c                            |   9 -
 arch/x86/kvm/x86.h                            |   3 -
 tools/testing/selftests/kvm/Makefile.kvm      |   1 +
 tools/testing/selftests/kvm/include/x86/pmu.h |   6 +
 .../selftests/kvm/include/x86/processor.h     |   2 +
 .../selftests/kvm/include/x86/svm_util.h      |   5 +-
 tools/testing/selftests/kvm/include/x86/vmx.h |   4 +-
 .../testing/selftests/kvm/lib/x86/memstress.c |  19 +-
 .../testing/selftests/kvm/lib/x86/processor.c |  45 ++--
 tools/testing/selftests/kvm/lib/x86/svm.c     |   6 +-
 tools/testing/selftests/kvm/lib/x86/vmx.c     |   6 +-
 .../selftests/kvm/x86/aperfmperf_test.c       |   9 +-
 .../kvm/x86/evmcs_smm_controls_test.c         |   5 +-
 .../testing/selftests/kvm/x86/hyperv_evmcs.c  |   6 +-
 .../selftests/kvm/x86/hyperv_svm_test.c       |   6 +-
 .../selftests/kvm/x86/kvm_buslock_test.c      |   9 +-
 .../selftests/kvm/x86/nested_close_kvm_test.c |  12 +-
 .../selftests/kvm/x86/nested_dirty_log_test.c |   8 +-
 .../selftests/kvm/x86/nested_emulation_test.c |   4 +-
 .../kvm/x86/nested_exceptions_test.c          |   9 +-
 .../kvm/x86/nested_invalid_cr3_test.c         |  10 +-
 .../selftests/kvm/x86/nested_tdp_fault_test.c |   9 +-
 .../kvm/x86/nested_tsc_adjust_test.c          |  10 +-
 .../kvm/x86/nested_tsc_scaling_test.c         |  10 +-
 .../kvm/x86/nested_vmsave_vmload_test.c       |   6 +-
 tools/testing/selftests/kvm/x86/smm_test.c    |   8 +-
 tools/testing/selftests/kvm/x86/state_test.c  |  11 +-
 .../selftests/kvm/x86/svm_int_ctl_test.c      |   5 +-
 .../selftests/kvm/x86/svm_lbr_nested_state.c  |   6 +-
 .../kvm/x86/svm_nested_clear_efer_svme.c      |   7 +-
 .../kvm/x86/svm_nested_shutdown_test.c        |   5 +-
 .../kvm/x86/svm_nested_soft_inject_test.c     |   6 +-
 .../selftests/kvm/x86/svm_nested_vmcb12_gpa.c |  13 +-
 .../kvm/x86/svm_pmu_host_guest_test.c         | 216 ++++++++++++++++++
 .../selftests/kvm/x86/svm_vmcall_test.c       |   5 +-
 .../kvm/x86/triple_fault_event_test.c         |   9 +-
 .../selftests/kvm/x86/vmx_apic_access_test.c  |   5 +-
 .../kvm/x86/vmx_apicv_updates_test.c          |   4 +-
 .../kvm/x86/vmx_invalid_nested_guest_state.c  |   6 +-
 .../kvm/x86/vmx_nested_la57_state_test.c      |   5 +-
 .../kvm/x86/vmx_preemption_timer_test.c       |   5 +-
 51 files changed, 479 insertions(+), 245 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/x86/svm_pmu_host_guest_test.c

base-commit: 9f2a49c511cb05b85745e1578e4fd425bff87f58

Signature · 1 line
2.54.0.794.g4f17f83d09-goog