KVM: nVMX: Fix nested VMX TSC emulation

This patch fixes two corner cases in nested (L2) handling of TSC-related
issues:

1. Somewhat suprisingly, according to the Intel spec, if L1 allows WRMSR to
the TSC MSR without an exit, then this should set L1's TSC value itself - not
offset by vmcs12.TSC_OFFSET (like was wrongly done in the previous code).

2. Allow L1 to disable the TSC_OFFSETING control, and then correctly ignore
the vmcs12.TSC_OFFSET.

Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

1 files changed, 21 insertions, 10 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 97b64543d4ed..5e8d411b0a81 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1777,15 +1777,23 @@ 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))
+        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.
+                 * We're here if L1 chose not to trap WRMSR to TSC. According
+                 * to the spec, this should set L1's TSC; The offset that L1
+                 * set for L2 remains unchanged, and still needs to be added
+                 * to the newly set TSC to get L2's TSC.
                  */
-                get_vmcs12(vcpu)->tsc_offset = offset -
-                        to_vmx(vcpu)->nested.vmcs01_tsc_offset;
+                struct vmcs12 *vmcs12;
+                to_vmx(vcpu)->nested.vmcs01_tsc_offset = offset;
+                /* recalculate vmcs02.TSC_OFFSET: */
+                vmcs12 = get_vmcs12(vcpu);
+                vmcs_write64(TSC_OFFSET, offset +
+                        (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING) ?
+                         vmcs12->tsc_offset : 0));
+        } else {
+                vmcs_write64(TSC_OFFSET, offset);
+        }
 }
 
 static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment)
@@ -6485,8 +6493,11 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
         set_cr4_guest_host_mask(vmx);
 
-        vmcs_write64(TSC_OFFSET,
-                vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
+        if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+                vmcs_write64(TSC_OFFSET,
+                        vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
+        else
+                vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
 
         if (enable_vpid) {
                 /*
@@ -6893,7 +6904,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu)
 
         load_vmcs12_host_state(vcpu, vmcs12);
 
-        /* Update TSC_OFFSET if vmx_adjust_tsc_offset() was used while L2 ran */
+        /* Update TSC_OFFSET if TSC was changed while L2 ran */
         vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
 
         /* This is needed for same reason as it was needed in prepare_vmcs02 */