On 5/29/20 8:39 AM, Paolo Bonzini wrote:
The control state changes on every L2->L0 vmexit, and we will have to
serialize it in the nested state. So keep it up to date in svm->nested.ctl
and just copy them back to the nested VMCB in nested_svm_vmexit.
Signed-off-by: Paolo Bonzini
---
arch/x86/kvm/svm/nested.c | 57 ++-
arch/x86/kvm/svm/svm.c| 5 +++-
arch/x86/kvm/svm/svm.h| 1 +
3 files changed, 38 insertions(+), 25 deletions(-)
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 1e5f460b5540..921466eba556 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -234,6 +234,34 @@ static void load_nested_vmcb_control(struct vcpu_svm *svm,
svm->nested.ctl.iopm_base_pa &= ~0x0fffULL;
}
+/*
+ * Synchronize fields that are written by the processor, so that
+ * they can be copied back into the nested_vmcb.
+ */
+void sync_nested_vmcb_control(struct vcpu_svm *svm)
+{
+ u32 mask;
+ svm->nested.ctl.event_inj = svm->vmcb->control.event_inj;
+ svm->nested.ctl.event_inj_err = svm->vmcb->control.event_inj_err;
+
+ /* Only a few fields of int_ctl are written by the processor. */
+ mask = V_IRQ_MASK | V_TPR_MASK;
+ if (!(svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) &&
+ is_intercept(svm, SVM_EXIT_VINTR)) {
+ /*
+* In order to request an interrupt window, L0 is usurping
+* svm->vmcb->control.int_ctl and possibly setting V_IRQ
+* even if it was clear in L1's VMCB. Restoring it would be
+* wrong. However, in this case V_IRQ will remain true until
+* interrupt_window_interception calls svm_clear_vintr and
+* restores int_ctl. We can just leave it aside.
+*/
+ mask &= ~V_IRQ_MASK;
+ }
+ svm->nested.ctl.int_ctl&= ~mask;
+ svm->nested.ctl.int_ctl|= svm->vmcb->control.int_ctl & mask;
+}
+
static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb
*nested_vmcb)
{
/* Load the nested guest state */
@@ -471,6 +499,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
/* Exit Guest-Mode */
leave_guest_mode(>vcpu);
svm->nested.vmcb = 0;
+ WARN_ON_ONCE(svm->nested.nested_run_pending);
/* in case we halted in L2 */
svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -497,8 +526,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
nested_vmcb->save.dr6= svm->vcpu.arch.dr6;
nested_vmcb->save.cpl= vmcb->save.cpl;
- nested_vmcb->control.int_ctl = vmcb->control.int_ctl;
- nested_vmcb->control.int_vector= vmcb->control.int_vector;
While it's not related to this patch, I am wondering if we need the
following line in enter_svm_guest_mode():
svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
If int_vector is used only to trigger a #VMEXIT after we have decided to
inject a virtual interrupt, we probably don't the vector value from the
nested vmcb.
nested_vmcb->control.int_state = vmcb->control.int_state;
nested_vmcb->control.exit_code = vmcb->control.exit_code;
nested_vmcb->control.exit_code_hi = vmcb->control.exit_code_hi;
@@ -510,34 +537,16 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
if (svm->nrips_enabled)
nested_vmcb->control.next_rip = vmcb->control.next_rip;
- /*
-* If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have
-* to make sure that we do not lose injected events. So check event_inj
-* here and copy it to exit_int_info if it is valid.
-* Exit_int_info and event_inj can't be both valid because the case
-* below only happens on a VMRUN instruction intercept which has
-* no valid exit_int_info set.
-*/
- if (vmcb->control.event_inj & SVM_EVTINJ_VALID) {
- struct vmcb_control_area *nc = _vmcb->control;
-
- nc->exit_int_info = vmcb->control.event_inj;
- nc->exit_int_info_err = vmcb->control.event_inj_err;
- }
-
- nested_vmcb->control.tlb_ctl = 0;
- nested_vmcb->control.event_inj = 0;
- nested_vmcb->control.event_inj_err = 0;
+ nested_vmcb->control.int_ctl = svm->nested.ctl.int_ctl;
+ nested_vmcb->control.tlb_ctl = svm->nested.ctl.tlb_ctl;
+ nested_vmcb->control.event_inj = svm->nested.ctl.event_inj;
+ nested_vmcb->control.event_inj_err = svm->nested.ctl.event_inj_err;
nested_vmcb->control.pause_filter_count =
svm->vmcb->control.pause_filter_count;
nested_vmcb->control.pause_filter_thresh =
svm->vmcb->control.pause_filter_thresh;
- /* We always set V_INTR_MASKING and remember the old value in hflags */
- if