Consider the case L1 had a IRQ/NMI event until it executed
VMLAUNCH/VMRESUME which wasn't delivered because it was disallowed
(e.g. interrupts disabled). When L1 executes VMLAUNCH/VMRESUME,
L0 needs to evaluate if this pending event should cause an exit from
L2 to L1 or delivered directly to L2 (e.g. In case L1 don't intercept
EXTERNAL_INTERRUPT).
Usually this would be handled by L0 requesting a IRQ/NMI window
by setting VMCS accordingly. However, this setting was done on
VMCS01 and now VMCS02 is active instead. Thus, when L1 executes
VMLAUNCH/VMRESUME we force L0 to perform pending event evaluation by
requesting a KVM_REQ_EVENT.
Note that above scenario exists when L1 KVM is about to enter L2 but
requests an "immediate-exit". As in this case, L1 will
disable-interrupts and then send a self-IPI before entering L2.
Co-authored-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Signed-off-by: Liran Alon <liran.alon@xxxxxxxxxx>
---
arch/x86/kvm/vmx.c | 25 ++++++++++++++++++++++++-
1 file changed, 24 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1d26f3c4985b..3348bc7ac566 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -12537,8 +12537,11 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
bool from_vmentry = !!exit_qual;
u32 dummy_exit_qual;
+ u32 vmcs01_cpu_exec_ctrl;
int r = 0;
+ vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+
enter_guest_mode(vcpu);
if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
@@ -12574,6 +12577,25 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
kvm_make_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
}
+ /*
+ * If L1 had a pending IRQ/NMI until it executed
+ * VMLAUNCH/VMRESUME which wasn't delivered because it was
+ * disallowed (e.g. interrupts disabled), L0 needs to
+ * evaluate if this pending event should cause an exit from L2
+ * to L1 or delivered directly to L2 (e.g. In case L1 don't
+ * intercept EXTERNAL_INTERRUPT).
+ *
+ * Usually this would be handled by L0 requesting a
+ * IRQ/NMI window by setting VMCS accordingly. However,
+ * this setting was done on VMCS01 and now VMCS02 is active
+ * instead. Thus, we force L0 to perform pending event
+ * evaluation by requesting a KVM_REQ_EVENT.
+ */
+ if (vmcs01_cpu_exec_ctrl &
+ (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING)) {
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ }
+
/*
* Note no nested_vmx_succeed or nested_vmx_fail here. At this point
* we are no longer running L1, and VMLAUNCH/VMRESUME has not yet
@@ -12702,7 +12724,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
* by event injection, halt vcpu.
*/
if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
- !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK)) {
+ !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) &&
+ !kvm_test_request(KVM_REQ_EVENT, vcpu)) {
vmx->nested.nested_run_pending = 0;
return kvm_vcpu_halt(vcpu);
}
--
2.16.1
