KVM: nVMX: clear PIN_BASED_POSTED_INTR from nested pinbased_ctls only when...

KVM: nVMX: clear PIN_BASED_POSTED_INTR from nested pinbased_ctls only when apicv is globally disabled

When apicv is disabled on a vCPU (e.g. by enabling KVM_CAP_HYPERV_SYNIC*),
nothing happens to VMX MSRs on the already existing vCPUs, however, all new
ones are created with PIN_BASED_POSTED_INTR filtered out. This is very
confusing and results in the following picture inside the guest:

$ rdmsr -ax 0x48d
ff00000016
7f00000016
7f00000016
7f00000016

This is observed with QEMU and 4-vCPU guest: QEMU creates vCPU0, does
KVM_CAP_HYPERV_SYNIC2 and then creates the remaining three.

L1 hypervisor may only check CPU0's controls to find out what features
are available and it will be very confused later. Switch to setting
PIN_BASED_POSTED_INTR control based on global 'enable_apicv' setting.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/vmx/capabilities.h

@@ -12,6 +12,7 @@ extern bool __read_mostly enable_ept;
 extern bool __read_mostly enable_unrestricted_guest;
 extern bool __read_mostly enable_ept_ad_bits;
 extern bool __read_mostly enable_pml;
+extern bool __read_mostly enable_apicv;
 extern int __read_mostly pt_mode;
 
 #define PT_MODE_SYSTEM		0

arch/x86/kvm/vmx/nested.c

@@ -5949,8 +5949,7 @@ void nested_vmx_set_vmcs_shadowing_bitmap(void)
  * bit in the high half is on if the corresponding bit in the control field
  * may be on. See also vmx_control_verify().
  */
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
-				bool apicv)
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 {
 	/*
 	 * Note that as a general rule, the high half of the MSRs (bits in
@@ -5977,7 +5976,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 		PIN_BASED_EXT_INTR_MASK |
 		PIN_BASED_NMI_EXITING |
 		PIN_BASED_VIRTUAL_NMIS |
-		(apicv ? PIN_BASED_POSTED_INTR : 0);
+		(enable_apicv ? PIN_BASED_POSTED_INTR : 0);
 	msrs->pinbased_ctls_high |=
 		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
 		PIN_BASED_VMX_PREEMPTION_TIMER;

arch/x86/kvm/vmx/nested.h

@@ -17,8 +17,7 @@ enum nvmx_vmentry_status {
 };
 
 void vmx_leave_nested(struct kvm_vcpu *vcpu);
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
-				bool apicv);
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps);
 void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_set_vmcs_shadowing_bitmap(void);

arch/x86/kvm/vmx/vmx.c

@@ -95,7 +95,7 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO);
 static bool __read_mostly fasteoi = 1;
 module_param(fasteoi, bool, S_IRUGO);
 
-static bool __read_mostly enable_apicv = 1;
+bool __read_mostly enable_apicv = 1;
 module_param(enable_apicv, bool, S_IRUGO);
 
 /*
@@ -6769,8 +6769,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 
 	if (nested)
 		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
-					   vmx_capability.ept,
-					   kvm_vcpu_apicv_active(vcpu));
+					   vmx_capability.ept);
 	else
 		memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));
 
@@ -6851,8 +6850,7 @@ static int __init vmx_check_processor_compat(void)
 	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
 		return -EIO;
 	if (nested)
-		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept,
-					   enable_apicv);
+		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
 	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
 		printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
 				smp_processor_id());
@@ -7714,7 +7712,7 @@ static __init int hardware_setup(void)
 
 	if (nested) {
 		nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
-					   vmx_capability.ept, enable_apicv);
+					   vmx_capability.ept);
 
 		r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
 		if (r)