When the TSC MSR is captured while an L2 guest is running then restored,
the 'tsc_offset' ends up capturing the L02 TSC_OFFSET instead of the L01
TSC_OFFSET. So ensure that this is compensated for when storing the value.
Cc: Jim Mattson <jmatt...@google.com>
Cc: Paolo Bonzini <pbonz...@redhat.com>
Cc: Radim Krčmář <rkrc...@redhat.com>
Cc: k...@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: KarimAllah Ahmed <karah...@amazon.de>
---
arch/x86/kvm/vmx.c | 12 +++++++++---
arch/x86/kvm/x86.c | 1 -
2 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index cff2f50..2f57571 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2900,6 +2900,8 @@ static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
*/
static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
{
+ u64 l1_tsc_offset = 0;
+
if (is_guest_mode(vcpu)) {
/*
* We're here if L1 chose not to trap WRMSR to TSC. According
@@ -2908,16 +2910,20 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu,
u64 offset)
* to the newly set TSC to get L2's TSC.
*/
struct vmcs12 *vmcs12;
+
/* 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));
+
+ l1_tsc_offset = nested_cpu_has(vmcs12,
CPU_BASED_USE_TSC_OFFSETING) ?
+ vmcs12->tsc_offset : 0;
+ vmcs_write64(TSC_OFFSET, offset + l1_tsc_offset);
} else {
trace_kvm_write_tsc_offset(vcpu->vcpu_id,
vmcs_read64(TSC_OFFSET), offset);
vmcs_write64(TSC_OFFSET, offset);
}
+
+ vcpu->arch.tsc_offset = offset - l1_tsc_offset;
}
/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ac42c85..1a2ed92 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1539,7 +1539,6 @@ EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
{
kvm_x86_ops->write_tsc_offset(vcpu, offset);
- vcpu->arch.tsc_offset = offset;
}
static inline bool kvm_check_tsc_unstable(void)
--
2.7.4
