KVM: VMX: Move out vmx_x86_ops to 'main.c' to dispatch VMX and TDX

KVM accesses Virtual Machine Control Structure (VMCS) with VMX instructions
to operate on VM.  TDX doesn't allow VMM to operate VMCS directly.
Instead, TDX has its own data structures, and TDX SEAMCALL APIs for VMM to
indirectly operate those data structures.  This means we must have a TDX
version of kvm_x86_ops.

The existing global struct kvm_x86_ops already defines an interface which
can be adapted to TDX, but kvm_x86_ops is a system-wide, not per-VM
structure.  To allow VMX to coexist with TDs, the kvm_x86_ops callbacks
will have wrappers "if (tdx) tdx_op() else vmx_op()" to pick VMX or
TDX at run time.

To split the runtime switch, the VMX implementation, and the TDX
implementation, add main.c, and move out the vmx_x86_ops hooks in
preparation for adding TDX.  Use 'vt' for the naming scheme as a nod to
VT-x and as a concatenation of VmxTdx.

The eventually converted code will look like this:

vmx.c:
  vmx_op() { ... }
  VMX initialization
tdx.c:
  tdx_op() { ... }
  TDX initialization
x86_ops.h:
  vmx_op();
  tdx_op();
main.c:
  static vt_op() { if (tdx) tdx_op() else vmx_op() }
  static struct kvm_x86_ops vt_x86_ops = {
        .op = vt_op,
  initialization functions call both VMX and TDX initialization

Opportunistically, fix the name inconsistency from vmx_create_vcpu() and
vmx_free_vcpu() to vmx_vcpu_create() and vmx_vcpu_free().

Co-developed-by: Xiaoyao Li <[email protected]>
Signed-off-by: Xiaoyao Li <[email protected]>
Signed-off-by: Sean Christopherson <[email protected]>
Signed-off-by: Isaku Yamahata <[email protected]>
Reviewed-by: Binbin Wu <[email protected]>
Reviewed-by: Xiaoyao Li <[email protected]>
Reviewed-by: Yuan Yao <[email protected]>
Message-Id: <e603c317587f933a9d1bee8728c84e4935849c16.1705965634.git.isaku.yamahata@intel.com>
Signed-off-by: Paolo Bonzini <[email protected]>

Author: bonzini

arch/x86/kvm/Makefile

@@ -21,7 +21,7 @@ kvm-$(CONFIG_KVM_XEN)	+= xen.o
 kvm-$(CONFIG_KVM_SMM)	+= smm.o
 
 kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
-			   vmx/nested.o vmx/posted_intr.o
+			   vmx/nested.o vmx/posted_intr.o vmx/main.o
 
 kvm-intel-$(CONFIG_X86_SGX_KVM)	+= vmx/sgx.o
 kvm-intel-$(CONFIG_KVM_HYPERV)	+= vmx/hyperv.o vmx/hyperv_evmcs.o

arch/x86/kvm/vmx/main.c

@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/moduleparam.h>
+
+#include "x86_ops.h"
+#include "vmx.h"
+#include "nested.h"
+#include "pmu.h"
+
+#define VMX_REQUIRED_APICV_INHIBITS				\
+	(BIT(APICV_INHIBIT_REASON_DISABLE)|			\
+	 BIT(APICV_INHIBIT_REASON_ABSENT) |			\
+	 BIT(APICV_INHIBIT_REASON_HYPERV) |			\
+	 BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |			\
+	 BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) |	\
+	 BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |		\
+	 BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED))
+
+struct kvm_x86_ops vt_x86_ops __initdata = {
+	.name = KBUILD_MODNAME,
+
+	.check_processor_compatibility = vmx_check_processor_compat,
+
+	.hardware_unsetup = vmx_hardware_unsetup,
+
+	.hardware_enable = vmx_hardware_enable,
+	.hardware_disable = vmx_hardware_disable,
+	.has_emulated_msr = vmx_has_emulated_msr,
+
+	.vm_size = sizeof(struct kvm_vmx),
+	.vm_init = vmx_vm_init,
+	.vm_destroy = vmx_vm_destroy,
+
+	.vcpu_precreate = vmx_vcpu_precreate,
+	.vcpu_create = vmx_vcpu_create,
+	.vcpu_free = vmx_vcpu_free,
+	.vcpu_reset = vmx_vcpu_reset,
+
+	.prepare_switch_to_guest = vmx_prepare_switch_to_guest,
+	.vcpu_load = vmx_vcpu_load,
+	.vcpu_put = vmx_vcpu_put,
+
+	.update_exception_bitmap = vmx_update_exception_bitmap,
+	.get_msr_feature = vmx_get_msr_feature,
+	.get_msr = vmx_get_msr,
+	.set_msr = vmx_set_msr,
+	.get_segment_base = vmx_get_segment_base,
+	.get_segment = vmx_get_segment,
+	.set_segment = vmx_set_segment,
+	.get_cpl = vmx_get_cpl,
+	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
+	.is_valid_cr0 = vmx_is_valid_cr0,
+	.set_cr0 = vmx_set_cr0,
+	.is_valid_cr4 = vmx_is_valid_cr4,
+	.set_cr4 = vmx_set_cr4,
+	.set_efer = vmx_set_efer,
+	.get_idt = vmx_get_idt,
+	.set_idt = vmx_set_idt,
+	.get_gdt = vmx_get_gdt,
+	.set_gdt = vmx_set_gdt,
+	.set_dr7 = vmx_set_dr7,
+	.sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
+	.cache_reg = vmx_cache_reg,
+	.get_rflags = vmx_get_rflags,
+	.set_rflags = vmx_set_rflags,
+	.get_if_flag = vmx_get_if_flag,
+
+	.flush_tlb_all = vmx_flush_tlb_all,
+	.flush_tlb_current = vmx_flush_tlb_current,
+	.flush_tlb_gva = vmx_flush_tlb_gva,
+	.flush_tlb_guest = vmx_flush_tlb_guest,
+
+	.vcpu_pre_run = vmx_vcpu_pre_run,
+	.vcpu_run = vmx_vcpu_run,
+	.handle_exit = vmx_handle_exit,
+	.skip_emulated_instruction = vmx_skip_emulated_instruction,
+	.update_emulated_instruction = vmx_update_emulated_instruction,
+	.set_interrupt_shadow = vmx_set_interrupt_shadow,
+	.get_interrupt_shadow = vmx_get_interrupt_shadow,
+	.patch_hypercall = vmx_patch_hypercall,
+	.inject_irq = vmx_inject_irq,
+	.inject_nmi = vmx_inject_nmi,
+	.inject_exception = vmx_inject_exception,
+	.cancel_injection = vmx_cancel_injection,
+	.interrupt_allowed = vmx_interrupt_allowed,
+	.nmi_allowed = vmx_nmi_allowed,
+	.get_nmi_mask = vmx_get_nmi_mask,
+	.set_nmi_mask = vmx_set_nmi_mask,
+	.enable_nmi_window = vmx_enable_nmi_window,
+	.enable_irq_window = vmx_enable_irq_window,
+	.update_cr8_intercept = vmx_update_cr8_intercept,
+	.set_virtual_apic_mode = vmx_set_virtual_apic_mode,
+	.set_apic_access_page_addr = vmx_set_apic_access_page_addr,
+	.refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
+	.load_eoi_exitmap = vmx_load_eoi_exitmap,
+	.apicv_pre_state_restore = vmx_apicv_pre_state_restore,
+	.required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS,
+	.hwapic_irr_update = vmx_hwapic_irr_update,
+	.hwapic_isr_update = vmx_hwapic_isr_update,
+	.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
+	.sync_pir_to_irr = vmx_sync_pir_to_irr,
+	.deliver_interrupt = vmx_deliver_interrupt,
+	.dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
+
+	.set_tss_addr = vmx_set_tss_addr,
+	.set_identity_map_addr = vmx_set_identity_map_addr,
+	.get_mt_mask = vmx_get_mt_mask,
+
+	.get_exit_info = vmx_get_exit_info,
+
+	.vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid,
+
+	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
+
+	.get_l2_tsc_offset = vmx_get_l2_tsc_offset,
+	.get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier,
+	.write_tsc_offset = vmx_write_tsc_offset,
+	.write_tsc_multiplier = vmx_write_tsc_multiplier,
+
+	.load_mmu_pgd = vmx_load_mmu_pgd,
+
+	.check_intercept = vmx_check_intercept,
+	.handle_exit_irqoff = vmx_handle_exit_irqoff,
+
+	.sched_in = vmx_sched_in,
+
+	.cpu_dirty_log_size = PML_ENTITY_NUM,
+	.update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
+
+	.nested_ops = &vmx_nested_ops,
+
+	.pi_update_irte = vmx_pi_update_irte,
+	.pi_start_assignment = vmx_pi_start_assignment,
+
+#ifdef CONFIG_X86_64
+	.set_hv_timer = vmx_set_hv_timer,
+	.cancel_hv_timer = vmx_cancel_hv_timer,
+#endif
+
+	.setup_mce = vmx_setup_mce,
+
+#ifdef CONFIG_KVM_SMM
+	.smi_allowed = vmx_smi_allowed,
+	.enter_smm = vmx_enter_smm,
+	.leave_smm = vmx_leave_smm,
+	.enable_smi_window = vmx_enable_smi_window,
+#endif
+
+	.check_emulate_instruction = vmx_check_emulate_instruction,
+	.apic_init_signal_blocked = vmx_apic_init_signal_blocked,
+	.migrate_timers = vmx_migrate_timers,
+
+	.msr_filter_changed = vmx_msr_filter_changed,
+	.complete_emulated_msr = kvm_complete_insn_gp,
+
+	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
+
+	.get_untagged_addr = vmx_get_untagged_addr,
+};
+
+struct kvm_x86_init_ops vt_init_ops __initdata = {
+	.hardware_setup = vmx_hardware_setup,
+	.handle_intel_pt_intr = NULL,
+
+	.runtime_ops = &vt_x86_ops,
+	.pmu_ops = &intel_pmu_ops,
+};