KVM: VMX: Fake emulate Intel perfctr MSRs

Older linux guests (in this case, 2.6.9) can attempt to
access the performance counter MSRs without a fixup section, and injecting
a GPF kills the guest.  Work around by allowing the guest to write those MSRs.

Tested by me on RHEL-4 i386 and x86_64 guests, as well as F-9 guests.

Signed-off-by: Chris Lalancette <clalance@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6a3a4038f3b941eabb09276dcf4837bf25bccfc3..d493a97e78877eebe5623fecb0e316aca6a2b318 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -920,6 +920,18 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
                break;
        case MSR_IA32_TIME_STAMP_COUNTER:
                guest_write_tsc(data);
+               break;
+       case MSR_P6_PERFCTR0:
+       case MSR_P6_PERFCTR1:
+       case MSR_P6_EVNTSEL0:
+       case MSR_P6_EVNTSEL1:
+               /*
+                * Just discard all writes to the performance counters; this
+                * should keep both older linux and windows 64-bit guests
+                * happy
+                */
+               pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", msr_index, data);
+
                break;
        default:
                vmx_load_host_state(vmx);