KVM: x86: Extend KVM_{G,S}ET_VCPU_EVENTS to support pending triple fault

For the triple fault sythesized by KVM, e.g. the RSM path or
nested_vmx_abort(), if KVM exits to userspace before the request is
serviced, userspace could migrate the VM and lose the triple fault.

Extend KVM_{G,S}ET_VCPU_EVENTS to support pending triple fault with a
new event KVM_VCPUEVENT_VALID_FAULT_FAULT so that userspace can save and
restore the triple fault event. This extension is guarded by a new KVM
capability KVM_CAP_TRIPLE_FAULT_EVENT.

Note that in the set_vcpu_events path, userspace is able to set/clear
the triple fault request through triple_fault.pending field.

Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Message-Id: <20220524135624.22988-2-chenyi.qiang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

5 files changed, 36 insertions, 2 deletions

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 421479a67da5..f67e367c4059 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -1150,6 +1150,10 @@ The following bits are defined in the flags field:
   fields contain a valid state. This bit will be set whenever
   KVM_CAP_EXCEPTION_PAYLOAD is enabled.
 
+- KVM_VCPUEVENT_VALID_TRIPLE_FAULT may be set to signal that the
+  triple_fault_pending field contains a valid state. This bit will
+  be set whenever KVM_CAP_TRIPLE_FAULT_EVENT is enabled.
+
 ARM64:
 ^^^^^^
 
@@ -1245,6 +1249,10 @@ can be set in the flags field to signal that the
 exception_has_payload, exception_payload, and exception.pending fields
 contain a valid state and shall be written into the VCPU.
 
+If KVM_CAP_TRIPLE_FAULT_EVENT is enabled, KVM_VCPUEVENT_VALID_TRIPLE_FAULT
+can be set in flags field to signal that the triple_fault field contains
+a valid state and shall be written into the VCPU.
+
 ARM64:
 ^^^^^^
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 032278f0ee6d..d6c62276e131 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1174,6 +1174,8 @@ struct kvm_arch {
 	bool guest_can_read_msr_platform_info;
 	bool exception_payload_enabled;
 
+	bool triple_fault_event;
+
 	bool bus_lock_detection_enabled;
 	bool enable_pmu;
 	/*
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 21614807a2cb..24c807c8d5f7 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -325,6 +325,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
 #define KVM_VCPUEVENT_VALID_SMM		0x00000008
 #define KVM_VCPUEVENT_VALID_PAYLOAD	0x00000010
+#define KVM_VCPUEVENT_VALID_TRIPLE_FAULT	0x00000020
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -359,7 +360,10 @@ struct kvm_vcpu_events {
 		__u8 smm_inside_nmi;
 		__u8 latched_init;
 	} smi;
-	__u8 reserved[27];
+	struct {
+		__u8 pending;
+	} triple_fault;
+	__u8 reserved[26];
 	__u8 exception_has_payload;
 	__u64 exception_payload;
 };
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c8dfdef9e52f..422fbb0d7518 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4296,6 +4296,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_GET_MSR_FEATURES:
 	case KVM_CAP_MSR_PLATFORM_INFO:
 	case KVM_CAP_EXCEPTION_PAYLOAD:
+	case KVM_CAP_X86_TRIPLE_FAULT_EVENT:
 	case KVM_CAP_SET_GUEST_DEBUG:
 	case KVM_CAP_LAST_CPU:
 	case KVM_CAP_X86_USER_SPACE_MSR:
@@ -4942,6 +4943,10 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 			 | KVM_VCPUEVENT_VALID_SMM);
 	if (vcpu->kvm->arch.exception_payload_enabled)
 		events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD;
+	if (vcpu->kvm->arch.triple_fault_event) {
+		events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+		events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT;
+	}
 
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
@@ -4955,7 +4960,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR
 			      | KVM_VCPUEVENT_VALID_SHADOW
 			      | KVM_VCPUEVENT_VALID_SMM
-			      | KVM_VCPUEVENT_VALID_PAYLOAD))
+			      | KVM_VCPUEVENT_VALID_PAYLOAD
+			      | KVM_VCPUEVENT_VALID_TRIPLE_FAULT))
 		return -EINVAL;
 
 	if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) {
@@ -5028,6 +5034,15 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		}
 	}
 
+	if (events->flags & KVM_VCPUEVENT_VALID_TRIPLE_FAULT) {
+		if (!vcpu->kvm->arch.triple_fault_event)
+			return -EINVAL;
+		if (events->triple_fault.pending)
+			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+		else
+			kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+	}
+
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	return 0;
@@ -6029,6 +6044,10 @@ split_irqchip_unlock:
 		kvm->arch.exception_payload_enabled = cap->args[0];
 		r = 0;
 		break;
+	case KVM_CAP_X86_TRIPLE_FAULT_EVENT:
+		kvm->arch.triple_fault_event = cap->args[0];
+		r = 0;
+		break;
 	case KVM_CAP_X86_USER_SPACE_MSR:
 		kvm->arch.user_space_msr_mask = cap->args[0];
 		r = 0;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index c4a32910b88a..ca799319acfd 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1158,6 +1158,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_SYSTEM_EVENT_DATA 215
 #define KVM_CAP_ARM_SYSTEM_SUSPEND 216
 #define KVM_CAP_S390_PROTECTED_DUMP 217
+#define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218
 
 #ifdef KVM_CAP_IRQ_ROUTING