Merge branch 'kvm-tdx-enter-exit' into HEAD

This series introduces callbacks to facilitate the entry of a TD VCPU
and the corresponding save/restore of host state.

A TD VCPU is entered via the SEAMCALL TDH.VP.ENTER. The TDX Module manages
the save/restore of guest state and, in conjunction with the SEAMCALL
interface, handles certain aspects of host state. However, there are
specific elements of the host state that require additional attention, as
detailed in the Intel TDX ABI documentation for TDH.VP.ENTER.

TDX is quite different from VMX in this regard.  For VMX, the host VMM is
heavily involved in restoring, managing and saving guest CPU state, whereas
for TDX this is handled by the TDX Module.  In that way, the TDX Module can
protect the confidentiality and integrity of TD CPU state.

The TDX Module does not save/restore all host CPU state because the host
VMM can do it more efficiently and selectively.  CPU state referred to
below is host CPU state.  Often values are already held in memory so no
explicit save is needed, and restoration may not be needed if the kernel
is not using a feature.

TDX does not support PAUSE-loop exiting.  According to the TDX Module
Base arch. spec., hypercalls are expected to be used instead.  Note that
the Linux TDX guest supports existing hypercalls via TDG.VP.VMCALL.

This series requires TDX module 1.5.06.00.0744, or later, due to removal
of the workarounds for the lack of the NO_RBP_MOD feature required by the
kernel. NO_RBP_MOD is now required.

1 files changed, 44 insertions, 4 deletions

diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index ec8223ee9d28..c0497ed0c9be 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -10,6 +10,10 @@
 #include "tdx.h"
 #include "tdx_arch.h"
 
+#ifdef CONFIG_KVM_INTEL_TDX
+static_assert(offsetof(struct vcpu_vmx, vt) == offsetof(struct vcpu_tdx, vt));
+#endif
+
 static void vt_disable_virtualization_cpu(void)
 {
 	/* Note, TDX *and* VMX need to be disabled if TDX is enabled. */
@@ -141,6 +145,42 @@ static void vt_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
 	vmx_update_cpu_dirty_logging(vcpu);
 }
 
+static void vt_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu)) {
+		tdx_prepare_switch_to_guest(vcpu);
+		return;
+	}
+
+	vmx_prepare_switch_to_guest(vcpu);
+}
+
+static void vt_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu)) {
+		tdx_vcpu_put(vcpu);
+		return;
+	}
+
+	vmx_vcpu_put(vcpu);
+}
+
+static int vt_vcpu_pre_run(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu))
+		return tdx_vcpu_pre_run(vcpu);
+
+	return vmx_vcpu_pre_run(vcpu);
+}
+
+static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+{
+	if (is_td_vcpu(vcpu))
+		return tdx_vcpu_run(vcpu, force_immediate_exit);
+
+	return vmx_vcpu_run(vcpu, force_immediate_exit);
+}
+
 static void vt_flush_tlb_all(struct kvm_vcpu *vcpu)
 {
 	if (is_td_vcpu(vcpu)) {
@@ -245,9 +285,9 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.vcpu_free = vt_vcpu_free,
 	.vcpu_reset = vt_vcpu_reset,
 
-	.prepare_switch_to_guest = vmx_prepare_switch_to_guest,
+	.prepare_switch_to_guest = vt_prepare_switch_to_guest,
 	.vcpu_load = vt_vcpu_load,
-	.vcpu_put = vmx_vcpu_put,
+	.vcpu_put = vt_vcpu_put,
 
 	.update_exception_bitmap = vmx_update_exception_bitmap,
 	.get_feature_msr = vmx_get_feature_msr,
@@ -281,8 +321,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.flush_tlb_gva = vt_flush_tlb_gva,
 	.flush_tlb_guest = vt_flush_tlb_guest,
 
-	.vcpu_pre_run = vmx_vcpu_pre_run,
-	.vcpu_run = vmx_vcpu_run,
+	.vcpu_pre_run = vt_vcpu_pre_run,
+	.vcpu_run = vt_vcpu_run,
 	.handle_exit = vmx_handle_exit,
 	.skip_emulated_instruction = vmx_skip_emulated_instruction,
 	.update_emulated_instruction = vmx_update_emulated_instruction,