KVM: VMX: Fix handling of #MC that occurs during VM-Entry

[ Upstream commit beb8d93b ]

A previous fix to prevent KVM from consuming stale VMCS state after a
failed VM-Entry inadvertantly blocked KVM's handling of machine checks
that occur during VM-Entry.

Per Intel's SDM, a #MC during VM-Entry is handled in one of three ways,
depending on when the #MC is recognoized.  As it pertains to this bug
fix, the third case explicitly states EXIT_REASON_MCE_DURING_VMENTRY
is handled like any other VM-Exit during VM-Entry, i.e. sets bit 31 to
indicate the VM-Entry failed.

If a machine-check event occurs during a VM entry, one of the following occurs:
 - The machine-check event is handled as if it occurred before the VM entry:
        ...
 - The machine-check event is handled after VM entry completes:
        ...
 - A VM-entry failure occurs as described in Section 26.7. The basic
   exit reason is 41, for "VM-entry failure due to machine-check event".

Explicitly handle EXIT_REASON_MCE_DURING_VMENTRY as a one-off case in
vmx_vcpu_run() instead of binning it into vmx_complete_atomic_exit().
Doing so allows vmx_vcpu_run() to handle VMX_EXIT_REASONS_FAILED_VMENTRY
in a sane fashion and also simplifies vmx_complete_atomic_exit() since
VMCS.VM_EXIT_INTR_INFO is guaranteed to be fresh.

Fixes: b060ca3b ("kvm: vmx: Handle VMLAUNCH/VMRESUME failure properly")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

arch/x86/kvm/vmx.c

@@ -10438,28 +10438,21 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 
 static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 {
-	u32 exit_intr_info = 0;
-	u16 basic_exit_reason = (u16)vmx->exit_reason;
-
-	if (!(basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY
-	      || basic_exit_reason == EXIT_REASON_EXCEPTION_NMI))
+	if (vmx->exit_reason != EXIT_REASON_EXCEPTION_NMI)
 		return;
 
-	if (!(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
-		exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
-	vmx->exit_intr_info = exit_intr_info;
+	vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
 
 	/* if exit due to PF check for async PF */
-	if (is_page_fault(exit_intr_info))
+	if (is_page_fault(vmx->exit_intr_info))
 		vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason();
 
 	/* Handle machine checks before interrupts are enabled */
-	if (basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY ||
-	    is_machine_check(exit_intr_info))
+	if (is_machine_check(vmx->exit_intr_info))
 		kvm_machine_check();
 
 	/* We need to handle NMIs before interrupts are enabled */
-	if (is_nmi(exit_intr_info)) {
+	if (is_nmi(vmx->exit_intr_info)) {
 		kvm_before_interrupt(&vmx->vcpu);
 		asm("int $2");
 		kvm_after_interrupt(&vmx->vcpu);
@@ -10980,6 +10973,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	vmx->idt_vectoring_info = 0;
 
 	vmx->exit_reason = vmx->fail ? 0xdead : vmcs_read32(VM_EXIT_REASON);
+	if ((u16)vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY)
+		kvm_machine_check();
+
 	if (vmx->fail || (vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
 		return;