All of lore.kernel.org
 help / color / mirror / Atom feed
From: Yosry Ahmed <yosry@kernel.org>
To: Sean Christopherson <seanjc@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>,
	Jim Mattson <jmattson@google.com>,
	kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	Yosry Ahmed <yosry@kernel.org>
Subject: [PATCH v4 0/6] KVM: x86/pmu: Add support for AMD Host-Only/Guest-Only bits
Date: Thu, 26 Mar 2026 03:11:44 +0000	[thread overview]
Message-ID: <20260326031150.3774017-1-yosry@kernel.org> (raw)

v4 of Jim's series adding support for AMD's Host-Only and Guest-Only
performance counter eventsel bits in KVM's mediated PMU passthrough
implementation.

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 the following state
transitions to ensure counters only count in the appropriate mode:

  - EFER.SVME changes: Enable/disable Guest-Only counters
  - Nested VMRUN: Disable Host-Only, enable Guest-Only counters
  - Nested VMEXIT: Enable Host-Only, disable Guest-Only counters

v3 -> v4:
- Dropped amd_pmu_set_eventsel_hw(), moved handling of
  Host-Only/Guest-Only bits to PMU counter reprogramming and funnelled
  all processing through KVM_REQ_PMU [Sean].
  - For this to work, added a per-vendor callback for reprogramming PMU
    counters.
- Sorta restored the bitmask from v1, except now it's a single bitmask
  tracking all counters that need to be reprogrammed on nested
  transitions. The bitmask is used to avoid unnecessary KVM_REQ_PMU
  requests and only reprogram counters as needed  [Jim].
  - This is also needed to avoid directling calling vendor code from
    {enter/leave}_guest_mode() as requested by Sean.
- Added prep patches moving enable_pmu/enable_mediated_pmu and
  guest_mode helpers to facilitate following changes without circular
  dependencies and to avoid including new headers from leaf headers.

v3: https://lore.kernel.org/kvm/20260207012339.2646196-1-jmattson@google.com/

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 (4):
  KVM: x86: Move enable_pmu/enable_mediated_pmu to pmu.h and pmu.c
  KVM: x86: Move guest_mode helpers to x86.h
  KVM: x86/pmu: Disable counters based on Host-Only/Guest-Only bits in
    SVM
  KVM: x86/pmu: Re-evaluate Host-Only/Guest-Only on nested SVM
    transitions

 arch/x86/include/asm/kvm-x86-pmu-ops.h        |   1 +
 arch/x86/include/asm/kvm_host.h               |   6 +
 arch/x86/include/asm/perf_event.h             |   2 +
 arch/x86/kvm/kvm_cache_regs.h                 |  23 --
 arch/x86/kvm/pmu.c                            |  12 ++
 arch/x86/kvm/pmu.h                            |  17 ++
 arch/x86/kvm/svm/pmu.c                        |  44 ++++
 arch/x86/kvm/svm/svm.c                        |   1 +
 arch/x86/kvm/x86.c                            |   9 -
 arch/x86/kvm/x86.h                            |  31 ++-
 tools/testing/selftests/kvm/Makefile.kvm      |   1 +
 tools/testing/selftests/kvm/include/x86/pmu.h |   6 +
 .../selftests/kvm/include/x86/processor.h     |   2 +
 .../kvm/x86/svm_pmu_host_guest_test.c         | 199 ++++++++++++++++++
 14 files changed, 319 insertions(+), 35 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/x86/svm_pmu_host_guest_test.c


base-commit: 3d6cdcc8883b5726513d245eef0e91cabfc397f7
-- 
2.53.0.1018.g2bb0e51243-goog


             reply	other threads:[~2026-03-26  3:12 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-26  3:11 Yosry Ahmed [this message]
2026-03-26  3:11 ` [PATCH v4 1/6] KVM: x86: Move enable_pmu/enable_mediated_pmu to pmu.h and pmu.c Yosry Ahmed
2026-03-26  3:11 ` [PATCH v4 2/6] KVM: x86: Move guest_mode helpers to x86.h Yosry Ahmed
2026-03-26 22:48   ` kernel test robot
2026-03-26 23:18     ` Yosry Ahmed
2026-03-27  3:15   ` kernel test robot
2026-03-26  3:11 ` [PATCH v4 3/6] KVM: x86/pmu: Disable counters based on Host-Only/Guest-Only bits in SVM Yosry Ahmed
2026-04-07  1:30   ` Sean Christopherson
2026-04-24  6:55     ` Yosry Ahmed
2026-04-27 18:50       ` Sean Christopherson
2026-04-27 19:11         ` Yosry Ahmed
2026-04-27 19:54           ` Sean Christopherson
2026-04-27 20:02             ` Yosry Ahmed
2026-04-27 20:06               ` Sean Christopherson
2026-04-27 23:20         ` Yosry Ahmed
2026-04-27 23:53           ` Sean Christopherson
2026-04-28  0:34             ` Yosry Ahmed
2026-04-28  0:35               ` Yosry Ahmed
2026-04-28  0:37                 ` Yosry Ahmed
2026-03-26  3:11 ` [PATCH v4 4/6] KVM: x86/pmu: Re-evaluate Host-Only/Guest-Only on nested SVM transitions Yosry Ahmed
2026-04-07  1:35   ` Sean Christopherson
2026-04-09  4:59   ` Jim Mattson
2026-04-09 17:22     ` Sean Christopherson
2026-04-09 17:29       ` Jim Mattson
2026-04-09 17:48         ` Sean Christopherson
2026-04-09 18:35           ` Jim Mattson
2026-04-09 18:38             ` Sean Christopherson
2026-04-09 21:21               ` Sean Christopherson
2026-04-10  3:50                 ` Jim Mattson
2026-04-15 21:26                   ` Sean Christopherson
2026-04-15 23:07                     ` Jim Mattson
2026-04-16  0:29                       ` Sean Christopherson
2026-04-17 22:51                         ` Jim Mattson
2026-04-21 20:01                 ` Yosry Ahmed
2026-04-22 22:42                   ` Sean Christopherson
2026-04-24  6:57                     ` Yosry Ahmed
2026-03-26  3:11 ` [PATCH v4 5/6] KVM: x86/pmu: Allow Host-Only/Guest-Only bits with nSVM and mediated PMU Yosry Ahmed
2026-03-26  3:11 ` [PATCH v4 6/6] KVM: selftests: Add svm_pmu_host_guest_test for Host-Only/Guest-Only bits Yosry Ahmed
2026-04-07  1:39   ` Sean Christopherson
2026-04-07  3:23     ` Jim Mattson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260326031150.3774017-1-yosry@kernel.org \
    --to=yosry@kernel.org \
    --cc=jmattson@google.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=seanjc@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.