Commit a3203381 authored by Sean Christopherson's avatar Sean Christopherson Committed by Paolo Bonzini
Browse files

KVM: VMX: Move the hardware {un}setup functions to the bottom 



...so that future patches can reference e.g. @kvm_vmx_exit_handlers
without having to simultaneously move a big chunk of code.  Speaking
from experience, resolving merge conflicts is an absolute nightmare
without pre-moving the code.

Signed-off-by: default avatarSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
parent 5158917c

arch/x86/kvm/vmx/vmx.c

+184 −184
Original line number Diff line number Diff line
@@ -6067,190 +6067,6 @@ static void vmx_enable_tdp(void) 
	kvm_enable_tdp();

}



static __exit void nested_vmx_hardware_unsetup(void)

{

	int i;



	if (enable_shadow_vmcs) {

		for (i = 0; i < VMX_BITMAP_NR; i++)

			free_page((unsigned long)vmx_bitmap[i]);

	}

}



static __init int nested_vmx_hardware_setup(void)

{

	int i;



	if (enable_shadow_vmcs) {

		for (i = 0; i < VMX_BITMAP_NR; i++) {

			vmx_bitmap[i] = (unsigned long *)

				__get_free_page(GFP_KERNEL);

			if (!vmx_bitmap[i]) {

				nested_vmx_hardware_unsetup();

				return -ENOMEM;

			}

		}



		init_vmcs_shadow_fields();

	}



	return 0;

}



static __init int hardware_setup(void)

{

	unsigned long host_bndcfgs;

	int r, i;



	rdmsrl_safe(MSR_EFER, &host_efer);



	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i)

		kvm_define_shared_msr(i, vmx_msr_index[i]);



	if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0)

		return -EIO;



	if (boot_cpu_has(X86_FEATURE_NX))

		kvm_enable_efer_bits(EFER_NX);



	if (boot_cpu_has(X86_FEATURE_MPX)) {

		rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs);

		WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost");

	}



	if (boot_cpu_has(X86_FEATURE_XSAVES))

		rdmsrl(MSR_IA32_XSS, host_xss);



	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||

		!(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))

		enable_vpid = 0;



	if (!cpu_has_vmx_ept() ||

	    !cpu_has_vmx_ept_4levels() ||

	    !cpu_has_vmx_ept_mt_wb() ||

	    !cpu_has_vmx_invept_global())

		enable_ept = 0;



	if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)

		enable_ept_ad_bits = 0;



	if (!cpu_has_vmx_unrestricted_guest() || !enable_ept)

		enable_unrestricted_guest = 0;



	if (!cpu_has_vmx_flexpriority())

		flexpriority_enabled = 0;



	if (!cpu_has_virtual_nmis())

		enable_vnmi = 0;



	/*

	 * set_apic_access_page_addr() is used to reload apic access

	 * page upon invalidation.  No need to do anything if not

	 * using the APIC_ACCESS_ADDR VMCS field.

	 */

	if (!flexpriority_enabled)

		kvm_x86_ops->set_apic_access_page_addr = NULL;



	if (!cpu_has_vmx_tpr_shadow())

		kvm_x86_ops->update_cr8_intercept = NULL;



	if (enable_ept && !cpu_has_vmx_ept_2m_page())

		kvm_disable_largepages();



#if IS_ENABLED(CONFIG_HYPERV)

	if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH

	    && enable_ept)

		kvm_x86_ops->tlb_remote_flush = vmx_hv_remote_flush_tlb;

#endif



	if (!cpu_has_vmx_ple()) {

		ple_gap = 0;

		ple_window = 0;

		ple_window_grow = 0;

		ple_window_max = 0;

		ple_window_shrink = 0;

	}



	if (!cpu_has_vmx_apicv()) {

		enable_apicv = 0;

		kvm_x86_ops->sync_pir_to_irr = NULL;

	}



	if (cpu_has_vmx_tsc_scaling()) {

		kvm_has_tsc_control = true;

		kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX;

		kvm_tsc_scaling_ratio_frac_bits = 48;

	}



	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */



	if (enable_ept)

		vmx_enable_tdp();

	else

		kvm_disable_tdp();



	if (!nested) {

		kvm_x86_ops->get_nested_state = NULL;

		kvm_x86_ops->set_nested_state = NULL;

	}



	/*

	 * Only enable PML when hardware supports PML feature, and both EPT

	 * and EPT A/D bit features are enabled -- PML depends on them to work.

	 */

	if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml())

		enable_pml = 0;



	if (!enable_pml) {

		kvm_x86_ops->slot_enable_log_dirty = NULL;

		kvm_x86_ops->slot_disable_log_dirty = NULL;

		kvm_x86_ops->flush_log_dirty = NULL;

		kvm_x86_ops->enable_log_dirty_pt_masked = NULL;

	}



	if (!cpu_has_vmx_preemption_timer())

		kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit;



	if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) {

		u64 vmx_msr;



		rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);

		cpu_preemption_timer_multi =

			 vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;

	} else {

		kvm_x86_ops->set_hv_timer = NULL;

		kvm_x86_ops->cancel_hv_timer = NULL;

	}



	if (!cpu_has_vmx_shadow_vmcs() || !nested)

		enable_shadow_vmcs = 0;



	kvm_set_posted_intr_wakeup_handler(wakeup_handler);

	nested_vmx_setup_ctls_msrs(&vmcs_config.nested, vmx_capability.ept,

				   enable_apicv);



	kvm_mce_cap_supported |= MCG_LMCE_P;



	if (nested) {

		r = nested_vmx_hardware_setup();

		if (r)

			return r;

	}



	r = alloc_kvm_area();

	if (r)

		nested_vmx_hardware_unsetup();

	return r;

}



static __exit void hardware_unsetup(void)

{

	if (nested)

		nested_vmx_hardware_unsetup();



	free_kvm_area();

}



/*

 * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE

 * exiting, so only get here on cpu with PAUSE-Loop-Exiting.
@@ -13152,6 +12968,190 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, 
	return 0;

}



static __exit void nested_vmx_hardware_unsetup(void)

{

	int i;



	if (enable_shadow_vmcs) {

		for (i = 0; i < VMX_BITMAP_NR; i++)

			free_page((unsigned long)vmx_bitmap[i]);

	}

}



static __init int nested_vmx_hardware_setup(void)

{

	int i;



	if (enable_shadow_vmcs) {

		for (i = 0; i < VMX_BITMAP_NR; i++) {

			vmx_bitmap[i] = (unsigned long *)

				__get_free_page(GFP_KERNEL);

			if (!vmx_bitmap[i]) {

				nested_vmx_hardware_unsetup();

				return -ENOMEM;

			}

		}



		init_vmcs_shadow_fields();

	}



	return 0;

}



static __init int hardware_setup(void)

{

	unsigned long host_bndcfgs;

	int r, i;



	rdmsrl_safe(MSR_EFER, &host_efer);



	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i)

		kvm_define_shared_msr(i, vmx_msr_index[i]);



	if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0)

		return -EIO;



	if (boot_cpu_has(X86_FEATURE_NX))

		kvm_enable_efer_bits(EFER_NX);



	if (boot_cpu_has(X86_FEATURE_MPX)) {

		rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs);

		WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost");

	}



	if (boot_cpu_has(X86_FEATURE_XSAVES))

		rdmsrl(MSR_IA32_XSS, host_xss);



	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||

	    !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))

		enable_vpid = 0;



	if (!cpu_has_vmx_ept() ||

	    !cpu_has_vmx_ept_4levels() ||

	    !cpu_has_vmx_ept_mt_wb() ||

	    !cpu_has_vmx_invept_global())

		enable_ept = 0;



	if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)

		enable_ept_ad_bits = 0;



	if (!cpu_has_vmx_unrestricted_guest() || !enable_ept)

		enable_unrestricted_guest = 0;



	if (!cpu_has_vmx_flexpriority())

		flexpriority_enabled = 0;



	if (!cpu_has_virtual_nmis())

		enable_vnmi = 0;



	/*

	 * set_apic_access_page_addr() is used to reload apic access

	 * page upon invalidation.  No need to do anything if not

	 * using the APIC_ACCESS_ADDR VMCS field.

	 */

	if (!flexpriority_enabled)

		kvm_x86_ops->set_apic_access_page_addr = NULL;



	if (!cpu_has_vmx_tpr_shadow())

		kvm_x86_ops->update_cr8_intercept = NULL;



	if (enable_ept && !cpu_has_vmx_ept_2m_page())

		kvm_disable_largepages();



#if IS_ENABLED(CONFIG_HYPERV)

	if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH

	    && enable_ept)

		kvm_x86_ops->tlb_remote_flush = vmx_hv_remote_flush_tlb;

#endif



	if (!cpu_has_vmx_ple()) {

		ple_gap = 0;

		ple_window = 0;

		ple_window_grow = 0;

		ple_window_max = 0;

		ple_window_shrink = 0;

	}



	if (!cpu_has_vmx_apicv()) {

		enable_apicv = 0;

		kvm_x86_ops->sync_pir_to_irr = NULL;

	}



	if (cpu_has_vmx_tsc_scaling()) {

		kvm_has_tsc_control = true;

		kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX;

		kvm_tsc_scaling_ratio_frac_bits = 48;

	}



	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */



	if (enable_ept)

		vmx_enable_tdp();

	else

		kvm_disable_tdp();



	if (!nested) {

		kvm_x86_ops->get_nested_state = NULL;

		kvm_x86_ops->set_nested_state = NULL;

	}



	/*

	 * Only enable PML when hardware supports PML feature, and both EPT

	 * and EPT A/D bit features are enabled -- PML depends on them to work.

	 */

	if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml())

		enable_pml = 0;



	if (!enable_pml) {

		kvm_x86_ops->slot_enable_log_dirty = NULL;

		kvm_x86_ops->slot_disable_log_dirty = NULL;

		kvm_x86_ops->flush_log_dirty = NULL;

		kvm_x86_ops->enable_log_dirty_pt_masked = NULL;

	}



	if (!cpu_has_vmx_preemption_timer())

		kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit;



	if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) {

		u64 vmx_msr;



		rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);

		cpu_preemption_timer_multi =

			vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;

	} else {

		kvm_x86_ops->set_hv_timer = NULL;

		kvm_x86_ops->cancel_hv_timer = NULL;

	}



	if (!cpu_has_vmx_shadow_vmcs() || !nested)

		enable_shadow_vmcs = 0;



	kvm_set_posted_intr_wakeup_handler(wakeup_handler);

	nested_vmx_setup_ctls_msrs(&vmcs_config.nested, vmx_capability.ept,

				   enable_apicv);



	kvm_mce_cap_supported |= MCG_LMCE_P;



	if (nested) {

		r = nested_vmx_hardware_setup();

		if (r)

			return r;

	}



	r = alloc_kvm_area();

	if (r)

		nested_vmx_hardware_unsetup();

	return r;

}



static __exit void hardware_unsetup(void)

{

	if (nested)

		nested_vmx_hardware_unsetup();



	free_kvm_area();

}



static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {

	.cpu_has_kvm_support = cpu_has_kvm_support,

	.disabled_by_bios = vmx_disabled_by_bios,