All of lore.kernel.org
 help / color / mirror / Atom feed
From: Zide Chen <zide.chen@intel.com>
To: Sean Christopherson <seanjc@google.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>
Cc: kvm@vger.kernel.org, Jim Mattson <jmattson@google.com>,
	Yosry Ahmed <yosry@kernel.org>, Andi Kleen <ak@linux.intel.com>,
	Stephane Eranian <eranian@google.com>,
	linux-kernel@vger.kernel.org, Mingwei Zhang <mizhang@google.com>,
	Zide Chen <zide.chen@intel.com>,
	Das Sandipan <Sandipan.Das@amd.com>,
	Shukla Manali <Manali.Shukla@amd.com>,
	Dapeng Mi <dapeng1.mi@linux.intel.com>,
	Xudong Hao <xudong.hao@intel.com>
Subject: [PATCH v3 10/18] KVM: x86/pmu: Document GLOBAL_STATUS_RESET passthrough erratum
Date: Thu,  5 Nov 2026 18:39:19 -0700	[thread overview]
Message-ID: <20261106013927.166209-11-zide.chen@intel.com> (raw)
In-Reply-To: <20261106013927.166209-1-zide.chen@intel.com>

IA32_PERF_GLOBAL_STATUS_RESET, introduced in PerfMon version 4,
inherits the MSR address and architecturally defined bits from
IA32_PERF_GLOBAL_OVF_CTRL, while providing additional bits to clear
new indicators in IA32_PERF_GLOBAL_STATUS.

From an emulation perspective, KVM handles it identically to the
OVF_CTRL MSR: reads return zero, and intercepted writes are guarded
against pmu->global_status_rsvd. No code changes are needed in KVM
to emulate this MSR.

However, to reduce VM exits, KVM passes through this MSR in mediated
PMU mode when GLOBAL_STATUS is also passed through. Consequently,
writes to bits that are valid on the host but unvirtualized by KVM
will not trigger a #GP (unlike when the MSR is intercepted). Except
for the known limitation where host Intel PT in system mode can
assert Trace_ToPA_PMI (bit 55), unvirtualized status bits are not set
while the guest is running, so clearing them has no negative effects.

Document this divergence in errata.rst.

Signed-off-by: Zide Chen <zide.chen@intel.com>
---
v3:
- New patch prompted by Jim and Yosry's review on unvirtualized
  status bits.
---
 Documentation/virt/kvm/x86/errata.rst | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/Documentation/virt/kvm/x86/errata.rst b/Documentation/virt/kvm/x86/errata.rst
index a9cf0e004651..161ba6d1beb4 100644
--- a/Documentation/virt/kvm/x86/errata.rst
+++ b/Documentation/virt/kvm/x86/errata.rst
@@ -84,4 +84,12 @@ memory.
 
 Note, this erratum does not affect AMD CPUs, which fully virtualize CR0.CD in
 hardware, i.e. put the CPU caches into "no fill" mode when CR0.CD=1, even when
-running in the guest.
\ No newline at end of file
+running in the guest.
+
+IA32_PERF_GLOBAL_STATUS_RESET
+-----------------------------
+To reduce VM-exits on performance-critical paths, KVM passes through writes
+to IA32_PERF_GLOBAL_STATUS_RESET (0x390) in mediated PMU mode when the guest's
+counters match hardware, without injecting #GP on unvirtualized bits.  Because
+the MSR is read-as-zero and write-to-clear, this cannot leak host information
+to the guest.
-- 
2.56.0


  parent reply	other threads:[~2026-11-06  1:50 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-06  1:39 [PATCH v3 00/18] KVM: x86/pmu: Add mediated vPMU PerfMon v5 support Zide Chen
2026-11-06  1:39 ` [PATCH v3 01/18] KVM: x86/pmu: Remove redundant Perf Global Status MSR bit definitions Zide Chen
2026-11-06 18:19   ` Yosry Ahmed
2026-11-06  1:39 ` [PATCH v3 02/18] KVM: x86/pmu: Rename all_valid_pmc_idx to pmc_exists Zide Chen
2026-11-06 18:21   ` Yosry Ahmed
2026-11-06  1:39 ` [PATCH v3 03/18] KVM: x86/pmu: Rename reserved_bits to eventsel_rsvd in kvm_pmu Zide Chen
2026-11-06 18:37   ` Yosry Ahmed
2026-11-06 21:16     ` Chen, Zide
2026-11-06 22:38       ` Yosry Ahmed
2026-11-06  1:39 ` [PATCH v3 04/18] KVM: x86/pmu: Add PMC bitmap accessor helpers Zide Chen
2026-11-06 19:09   ` Yosry Ahmed
2026-11-06 22:19     ` Chen, Zide
2026-11-06 22:35       ` Yosry Ahmed
2026-11-09  7:53         ` Mi, Dapeng
2026-11-09 17:56           ` Chen, Zide
2026-11-09 17:55         ` Chen, Zide
2026-11-09 18:07           ` Yosry Ahmed
2026-11-09 18:59             ` Chen, Zide
2026-11-09 21:12               ` Yosry Ahmed
2026-11-09 21:59                 ` Chen, Zide
2026-11-09 22:07                   ` Yosry Ahmed
2026-11-09 22:26                     ` Chen, Zide
2026-11-06  1:39 ` [PATCH v3 05/18] KVM: x86/pmu: Drop nr_arch_{gp,fixed}_counters from kvm_pmu Zide Chen
2026-11-06 19:34   ` Yosry Ahmed
2026-11-07  0:42     ` Jim Mattson
2026-11-07  2:26       ` Yosry Ahmed
2026-11-09 22:42       ` Chen, Zide
2026-11-09 22:47     ` Chen, Zide
2026-11-06  1:39 ` [PATCH v3 06/18] KVM: x86/pmu: Expose kvm_host_pmu to vendor modules Zide Chen
2026-11-06 19:37   ` Yosry Ahmed
2026-11-06  1:39 ` [PATCH v3 07/18] perf/x86: Plumb counter bitmap from x86_pmu to x86_pmu_cap Zide Chen
2026-11-06  1:39 ` [PATCH v3 08/18] KVM: x86/pmu: Switch to bitmask-based KVM PMU capabilities Zide Chen
2026-11-06 20:05   ` Yosry Ahmed
2026-11-09 21:22     ` Chen, Zide
2026-11-09 20:50   ` Jim Mattson
2026-11-06  1:39 ` [PATCH v3 09/18] perf/x86: Remove num_counters_{gp,fixed} from x86_pmu_capability Zide Chen
2026-11-06  1:39 ` Zide Chen [this message]
2026-11-06 20:14   ` [PATCH v3 10/18] KVM: x86/pmu: Document GLOBAL_STATUS_RESET passthrough erratum Yosry Ahmed
2026-11-10  0:41     ` Chen, Zide
2026-11-09 20:51   ` Jim Mattson
2026-11-06  1:39 ` [PATCH v3 11/18] KVM: x86/pmu: Emulate IA32_PERF_GLOBAL_STATUS_SET MSR Zide Chen
2026-11-06 20:35   ` Yosry Ahmed
2026-11-09 23:44     ` Chen, Zide
2026-11-09 20:53   ` Jim Mattson
2026-11-06  1:39 ` [PATCH v3 12/18] KVM: x86/pmu: Emulate IA32_PERF_GLOBAL_INUSE MSR Zide Chen
2026-11-09 20:54   ` Jim Mattson
2026-11-06  1:39 ` [PATCH v3 13/18] KVM: x86/pmu: Populate CPUID.0AH:ECX fixed-counter bitmap Zide Chen
2026-11-06 21:00   ` Yosry Ahmed
2026-11-09 20:41     ` Chen, Zide
2026-11-10  6:28       ` Mi, Dapeng
2026-11-10 16:29         ` Chen, Zide
2026-11-10 22:56           ` Chen, Zide
2026-11-11  0:25             ` Mi, Dapeng
2026-11-11  3:28               ` Chen, Zide
2026-11-11 15:37                 ` Sean Christopherson
2026-11-11 17:06                   ` Chen, Zide
2026-11-12 17:09                     ` Sean Christopherson
2026-11-12 17:47                       ` Chen, Zide
2026-11-06  1:39 ` [PATCH v3 14/18] KVM: x86/pmu: Factor out fixed counter control bit calculation Zide Chen
2026-11-06  1:39 ` [PATCH v3 15/18] KVM: x86/pmu: Mask only OS/USR bits when filtering fixed counters Zide Chen
2026-11-06 21:19   ` Jim Mattson
2026-11-06  1:39 ` [PATCH v3 16/18] KVM: x86/pmu: Ignore AnyThread bit if CPUID.0AH:EDX[15] is set Zide Chen
2026-11-09 20:56   ` Jim Mattson
2026-11-06  1:39 ` [PATCH v3 17/18] KVM: x86/pmu: Advertise PerfMon version 5 on Intel hosts Zide Chen
2026-11-06 21:20   ` Jim Mattson
2026-11-06  1:39 ` [PATCH v3 18/18] KVM: selftests: Support fixed counters bitmap in pmu_counters_test Zide Chen

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=20261106013927.166209-11-zide.chen@intel.com \
    --to=zide.chen@intel.com \
    --cc=Manali.Shukla@amd.com \
    --cc=Sandipan.Das@amd.com \
    --cc=ak@linux.intel.com \
    --cc=dapeng1.mi@linux.intel.com \
    --cc=eranian@google.com \
    --cc=jmattson@google.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mizhang@google.com \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=seanjc@google.com \
    --cc=xudong.hao@intel.com \
    --cc=yosry@kernel.org \
    /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.