Ultimately, it is up to userspace to decide what capabilities should be
advertised to the guest, including the VMX capability MSRs. Furthermore,
there shouldn't be any ordering requirements around the KVM_SET_MSR and
KVM_SET_CPUID2 ioctls. However, KVM has not respected the values written
by userspace for IA32_VMX_TRUE_{ENTRY,EXIT}_CTLS. Instead, KVM
updates the value of these MSRs when CPUID is changed. If userspace
advertises a PMU to the guest that supports IA32_PERF_GLOBAL_CTRL
(CPUID.0AH:EAX[7:0] > 1), KVM will adjust the values for
MSR_IA32_VMX_TRUE_{ENTRY,EXIT}_CTLS to unconditionally advertise the
"load IA32_PERF_GLOBAL_CTRL" control bit (or not, if the PMU doesn't
support the MSR).
The end result of these shenanigans is that VMMs that clear the "load
PERF_GLOBAL_CTRL" bits before setting CPUID will see the bits re-enabled
if it provides a supporting vPMU to the guest. Only if the MSR writes
happen after setting CPUID will userspace's intentions be upheld.
Since there are no ordering expectations around these ioctls, fix the
issue by simply not touching the VMX capability MSRs during an update
to guest CPUID. Note that the "load IA32_PERF_GLOBAL_CTRL" bits are
already set by default in the respective VMX capability MSRs,
if supported by hardware.
Fixes: 03a8871add95 ("KVM: nVMX: Expose load IA32_PERF_GLOBAL_CTRL VM-{Entry,Exit} control")
Reported-by: Jim Mattson <jmattson@xxxxxxxxxx>
Signed-off-by: Oliver Upton <oupton@xxxxxxxxxx>
---
arch/x86/kvm/vmx/nested.c | 21 ---------------------
arch/x86/kvm/vmx/nested.h | 1 -
arch/x86/kvm/vmx/pmu_intel.c | 2 --
3 files changed, 24 deletions(-)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index ba34e94049c7..4ed2409c2bd7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4797,27 +4797,6 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
return 0;
}
-void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx;
-
- if (!nested_vmx_allowed(vcpu))
- return;
-
- vmx = to_vmx(vcpu);
- if (kvm_x86_ops.pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) {
- vmx->nested.msrs.entry_ctls_high |=
- VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
- vmx->nested.msrs.exit_ctls_high |=
- VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
- } else {
- vmx->nested.msrs.entry_ctls_high &=
- ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
- vmx->nested.msrs.exit_ctls_high &=
- ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
- }
-}
-
static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer,
int *ret)
{
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index b69a80f43b37..14ad756aac46 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -32,7 +32,6 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata);
int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
u32 vmx_instruction_info, bool wr, int len, gva_t *ret);
-void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu);
void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu);
bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
int size);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 466d18fc0c5d..ad1adbaa7d9e 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -541,8 +541,6 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
bitmap_set(pmu->all_valid_pmc_idx,
INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters);
- nested_vmx_pmu_entry_exit_ctls_update(vcpu);
-
if (intel_pmu_lbr_is_compatible(vcpu))
x86_perf_get_lbr(&lbr_desc->records);
else
--
2.35.0.rc2.247.g8bbb082509-goog
