Received-SPF: pass (google.com: domain of linux-kernel+bounces-100968-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Reply-To: Mingwei Zhang <mizhang@google.com>
Date: Wed, 13 Mar 2024 00:37:39 +0000
Precedence: bulk
Mime-Version: 1.0
Message-ID: <20240313003739.3365845-1-mizhang@google.com>
Subject: [PATCH] KVM: x86/pmu: Return correct value of IA32_PERF_CAPABILITIES
 for userspace after vCPU has run
From: Mingwei Zhang <mizhang@google.com>
To: Sean Christopherson <seanjc@google.com>, Paolo Bonzini <pbonzini@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>, kvm@vger.kernel.org, linux-kernel@vger.kernel.org, 
	Aaron Lewis <aaronlewis@google.com>, Jim Mattson <jmattson@google.com>, 
	Mingwei Zhang <mizhang@google.com>
Content-Type: text/plain; charset="UTF-8"

Return correct value of IA32_PERF_CAPABILITIES when userspace tries to read
it after vCPU has already run. Previously, KVM will always return the guest
cached value on get_msr() even if guest CPUID lacks X86_FEATURE_PDCM. The
guest cached value on default is kvm_caps.supported_perf_cap. However, when
userspace sets the value during live migration, the call fails because of
the check on X86_FEATURE_PDCM.

Initially, it sounds like a pure userspace issue. It is not. After vCPU has
run, KVM should faithfully return correct value to satisify legitimate
requests from userspace such as VM suspend/resume and live migrartion. In
this case, KVM should return 0 when guest cpuid lacks X86_FEATURE_PDCM. So
fix the problem by adding an additional check in vmx_set_msr().

Note that IA32_PERF_CAPABILITIES is emulated on AMD side, which is fine
because it set_msr() is guarded by kvm_caps.supported_perf_cap which is
always 0.

Cc: Aaron Lewis <aaronlewis@google.com>
Cc: Jim Mattson <jmattson@google.com>
Signed-off-by: Mingwei Zhang <mizhang@google.com>
---
 arch/x86/kvm/vmx/vmx.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 40e3780d73ae..6d8667b56091 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2049,6 +2049,17 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = to_vmx(vcpu)->msr_ia32_sgxlepubkeyhash
 			[msr_info->index - MSR_IA32_SGXLEPUBKEYHASH0];
 		break;
+	case MSR_IA32_PERF_CAPABILITIES:
+		/*
+		 * Host VMM should not get potentially invalid MSR value if vCPU
+		 * has already run but guest cpuid lacks the support for the
+		 * MSR.
+		 */
+		if (msr_info->host_initiated &&
+		    kvm_vcpu_has_run(vcpu) &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_PDCM))
+			return 1;
+		break;
 	case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR:
 		if (!guest_can_use(vcpu, X86_FEATURE_VMX))
 			return 1;

base-commit: fd89499a5151d197ba30f7b801f6d8f4646cf446
-- 
2.44.0.291.gc1ea87d7ee-goog