@@ -127,6 +127,17 @@ struct shared_msr_entry {
u64 mask;
};
+/*
+ * The nested_vmx structure is part of vcpu_vmx, and holds information we need
+ * for correct emulation of VMX (i.e., nested VMX) on this vcpu. For example,
+ * the current VMCS set by L1, a list of the VMCSs used to run the active
+ * L2 guests on the hardware, and more.
+ */
+struct nested_vmx {
+ /* Has the level1 guest done vmxon? */
+ bool vmxon;
+};
+
struct vcpu_vmx {
struct kvm_vcpu vcpu;
struct list_head local_vcpus_link;
@@ -174,6 +185,9 @@ struct vcpu_vmx {
u32 exit_reason;
bool rdtscp_enabled;
+
+ /* Support for a guest hypervisor (nested VMX) */
+ struct nested_vmx nested;
};
static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
@@ -3653,6 +3667,90 @@ static int handle_invalid_op(struct kvm_
}
/*
+ * Emulate the VMXON instruction.
+ * Currently, we just remember that VMX is active, and do not save or even
+ * inspect the argument to VMXON (the so-called "VMXON pointer") because we
+ * do not currently need to store anything in that guest-allocated memory
+ * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their
+ * argument is different from the VMXON pointer (which the spec says they do).
+ */
+static int handle_vmon(struct kvm_vcpu *vcpu)
+{
+ struct kvm_segment cs;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ /* The Intel VMX Instruction Reference lists a bunch of bits that
+ * are prerequisite to running VMXON, most notably CR4.VMXE must be
+ * set to 1. Otherwise, we should fail with #UD. We test these now:
+ */
+ if (!nested ||
+ !kvm_read_cr4_bits(vcpu, X86_CR4_VMXE) ||
+ !kvm_read_cr0_bits(vcpu, X86_CR0_PE) ||
+ (vmx_get_rflags(vcpu) & X86_EFLAGS_VM)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+
+ vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
+ if (is_long_mode(vcpu) && !cs.l) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+
+ if (vmx_get_cpl(vcpu)) {
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+
+ vmx->nested.vmxon = true;
+
+ skip_emulated_instruction(vcpu);
+ return 1;
+}
+
+/*
+ * Intel's VMX Instruction Reference specifies a common set of prerequisites
+ * for running VMX instructions (except VMXON, whose prerequisites are
+ * slightly different). It also specifies what exception to inject otherwise.
+ */
+static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
+{
+ struct kvm_segment cs;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (!vmx->nested.vmxon) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 0;
+ }
+
+ vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
+ if ((vmx_get_rflags(vcpu) & X86_EFLAGS_VM) ||
+ (is_long_mode(vcpu) && !cs.l)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 0;
+ }
+
+ if (vmx_get_cpl(vcpu)) {
+ kvm_inject_gp(vcpu, 0);
+ return 0;
+ }
+
+ return 1;
+}
+
+/* Emulate the VMXOFF instruction */
+static int handle_vmoff(struct kvm_vcpu *vcpu)
+{
+ if (!nested_vmx_check_permission(vcpu))
+ return 1;
+
+ to_vmx(vcpu)->nested.vmxon = false;
+
+ skip_emulated_instruction(vcpu);
+ return 1;
+}
+
+/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
* to be done to userspace and return 0.
@@ -3680,8 +3778,8 @@ static int (*kvm_vmx_exit_handlers[])(st
[EXIT_REASON_VMREAD] = handle_vmx_insn,
[EXIT_REASON_VMRESUME] = handle_vmx_insn,
[EXIT_REASON_VMWRITE] = handle_vmx_insn,
- [EXIT_REASON_VMOFF] = handle_vmx_insn,
- [EXIT_REASON_VMON] = handle_vmx_insn,
+ [EXIT_REASON_VMOFF] = handle_vmoff,
+ [EXIT_REASON_VMON] = handle_vmon,
[EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold,
[EXIT_REASON_APIC_ACCESS] = handle_apic_access,
[EXIT_REASON_WBINVD] = handle_wbinvd,