KVM: nVMX: Additional TSC-offset handling

In the unlikely case that L1 does not capture MSR_IA32_TSC, L0 needs to
emulate this MSR write by L2 by modifying vmcs02.tsc_offset. We also need to
set vmcs12.tsc_offset, for this change to survive the next nested entry (see
prepare_vmcs02()).
Additionally, we also need to modify vmx_adjust_tsc_offset: The semantics
of this function is that the TSC of all guests on this vcpu, L1 and possibly
several L2s, need to be adjusted. To do this, we need to adjust vmcs01's
tsc_offset (this offset will also apply to each L2s we enter). We can't set
vmcs01 now, so we have to remember this adjustment and apply it when we
later exit to L1.

Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

1 files changed, 12 insertions, 0 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 10b2261..afc1f06 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1766,12 +1766,24 @@ static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
 static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
 	vmcs_write64(TSC_OFFSET, offset);
+	if (is_guest_mode(vcpu))
+		/*
+		 * We're here if L1 chose not to trap the TSC MSR. Since
+		 * prepare_vmcs12() does not copy tsc_offset, we need to also
+		 * set the vmcs12 field here.
+		 */
+		get_vmcs12(vcpu)->tsc_offset = offset -
+			to_vmx(vcpu)->nested.vmcs01_tsc_offset;
 }
 
 static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment)
 {
 	u64 offset = vmcs_read64(TSC_OFFSET);
 	vmcs_write64(TSC_OFFSET, offset + adjustment);
+	if (is_guest_mode(vcpu)) {
+		/* Even when running L2, the adjustment needs to apply to L1 */
+		to_vmx(vcpu)->nested.vmcs01_tsc_offset += adjustment;
+	}
 }
 
 static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)