Commit 8131cf5b authored by Isaku Yamahata's avatar Isaku Yamahata Committed by Paolo Bonzini
Browse files

KVM: VMX: Introduce test mode related to EPT violation VE 



To support TDX, KVM is enhanced to operate with #VE.  For TDX, KVM uses the
suppress #VE bit in EPT entries selectively, in order to be able to trap
non-present conditions.  However, #VE isn't used for VMX and it's a bug
if it happens.  To be defensive and test that VMX case isn't broken
introduce an option ept_violation_ve_test and when it's set, BUG the vm.

Suggested-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: default avatarIsaku Yamahata <isaku.yamahata@intel.com>
Message-Id: <d6db6ba836605c0412e166359ba5c46a63c22f86.1705965635.git.isaku.yamahata@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
parent fb29541e

arch/x86/kvm/Kconfig

+13 −0
Original line number Diff line number Diff line
@@ -95,6 +95,19 @@ config KVM_INTEL 
	  To compile this as a module, choose M here: the module

	  will be called kvm-intel.



config KVM_INTEL_PROVE_VE

        bool "Check that guests do not receive #VE exceptions"

        default KVM_PROVE_MMU || DEBUG_KERNEL

        depends on KVM_INTEL

        help



          Checks that KVM's page table management code will not incorrectly

          let guests receive a virtualization exception.  Virtualization

          exceptions will be trapped by the hypervisor rather than injected

          in the guest.



          If unsure, say N.



config X86_SGX_KVM

	bool "Software Guard eXtensions (SGX) Virtualization"

	depends on X86_SGX && KVM_INTEL

arch/x86/kvm/vmx/vmcs.h

+5 −0
Original line number Diff line number Diff line
@@ -140,6 +140,11 @@ static inline bool is_nm_fault(u32 intr_info) 
	return is_exception_n(intr_info, NM_VECTOR);

}



static inline bool is_ve_fault(u32 intr_info)

{

	return is_exception_n(intr_info, VE_VECTOR);

}



/* Undocumented: icebp/int1 */

static inline bool is_icebp(u32 intr_info)

{

arch/x86/kvm/vmx/vmx.c

+50 −3
Original line number Diff line number Diff line
@@ -869,6 +869,12 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) 


	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |

	     (1u << DB_VECTOR) | (1u << AC_VECTOR);

	/*

	 * #VE isn't used for VMX.  To test against unexpected changes

	 * related to #VE for VMX, intercept unexpected #VE and warn on it.

	 */

	if (IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE))

		eb |= 1u << VE_VECTOR;

	/*

	 * Guest access to VMware backdoor ports could legitimately

	 * trigger #GP because of TSS I/O permission bitmap.
@@ -2602,6 +2608,9 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, 
					&_cpu_based_2nd_exec_control))

			return -EIO;

	}

	if (!IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE))

		_cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE;



#ifndef CONFIG_X86_64

	if (!(_cpu_based_2nd_exec_control &

				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
@@ -2626,6 +2635,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, 
			return -EIO;



		vmx_cap->ept = 0;

		_cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE;

	}

	if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) &&

	    vmx_cap->vpid) {
@@ -4588,6 +4598,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) 
		exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;

	if (!enable_ept) {

		exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;

		exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE;

		enable_unrestricted_guest = 0;

	}

	if (!enable_unrestricted_guest)
@@ -4711,8 +4722,12 @@ static void init_vmcs(struct vcpu_vmx *vmx) 


	exec_controls_set(vmx, vmx_exec_control(vmx));



	if (cpu_has_secondary_exec_ctrls())

	if (cpu_has_secondary_exec_ctrls()) {

		secondary_exec_controls_set(vmx, vmx_secondary_exec_control(vmx));

		if (vmx->ve_info)

			vmcs_write64(VE_INFORMATION_ADDRESS,

				     __pa(vmx->ve_info));

	}



	if (cpu_has_tertiary_exec_ctrls())

		tertiary_exec_controls_set(vmx, vmx_tertiary_exec_control(vmx));
@@ -5200,6 +5215,9 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) 
	if (is_invalid_opcode(intr_info))

		return handle_ud(vcpu);



	if (KVM_BUG_ON(is_ve_fault(intr_info), vcpu->kvm))

		return -EIO;



	error_code = 0;

	if (intr_info & INTR_INFO_DELIVER_CODE_MASK)

		error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
@@ -6409,8 +6427,22 @@ void dump_vmcs(struct kvm_vcpu *vcpu) 
		pr_err("Virtual processor ID = 0x%04x\n",

		       vmcs_read16(VIRTUAL_PROCESSOR_ID));

	if (secondary_exec_control & SECONDARY_EXEC_EPT_VIOLATION_VE) {

		pr_err("VE info address = 0x%016llx\n",

		       vmcs_read64(VE_INFORMATION_ADDRESS));

		struct vmx_ve_information *ve_info = vmx->ve_info;

		u64 ve_info_pa = vmcs_read64(VE_INFORMATION_ADDRESS);



		/*

		 * If KVM is dumping the VMCS, then something has gone wrong

		 * already.  Derefencing an address from the VMCS, which could

		 * very well be corrupted, is a terrible idea.  The virtual

		 * address is known so use it.

		 */

		pr_err("VE info address = 0x%016llx%s\n", ve_info_pa,

		       ve_info_pa == __pa(ve_info) ? "" : "(corrupted!)");

		pr_err("ve_info: 0x%08x 0x%08x 0x%016llx 0x%016llx 0x%016llx 0x%04x\n",

		       ve_info->exit_reason, ve_info->delivery,

		       ve_info->exit_qualification,

		       ve_info->guest_linear_address,

		       ve_info->guest_physical_address, ve_info->eptp_index);

	}

}
@@ -7466,6 +7498,7 @@ void vmx_vcpu_free(struct kvm_vcpu *vcpu) 
	free_vpid(vmx->vpid);

	nested_vmx_free_vcpu(vcpu);

	free_loaded_vmcs(vmx->loaded_vmcs);

	free_page((unsigned long)vmx->ve_info);

}



int vmx_vcpu_create(struct kvm_vcpu *vcpu)
@@ -7559,6 +7592,20 @@ int vmx_vcpu_create(struct kvm_vcpu *vcpu) 
			goto free_vmcs;

	}



	err = -ENOMEM;

	if (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_EPT_VIOLATION_VE) {

		struct page *page;



		BUILD_BUG_ON(sizeof(*vmx->ve_info) > PAGE_SIZE);



		/* ve_info must be page aligned. */

		page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);

		if (!page)

			goto free_vmcs;



		vmx->ve_info = page_to_virt(page);

	}



	if (vmx_can_use_ipiv(vcpu))

		WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id],

			   __pa(&vmx->pi_desc) | PID_TABLE_ENTRY_VALID);

arch/x86/kvm/vmx/vmx.h

+5 −1
Original line number Diff line number Diff line
@@ -362,6 +362,9 @@ struct vcpu_vmx { 
		DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS);

		DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS);

	} shadow_msr_intercept;



	/* ve_info must be page aligned. */

	struct vmx_ve_information *ve_info;

};



struct kvm_vmx {
@@ -574,7 +577,8 @@ static inline u8 vmx_get_rvi(void) 
	 SECONDARY_EXEC_ENABLE_VMFUNC |					\

	 SECONDARY_EXEC_BUS_LOCK_DETECTION |				\

	 SECONDARY_EXEC_NOTIFY_VM_EXITING |				\

	 SECONDARY_EXEC_ENCLS_EXITING)

	 SECONDARY_EXEC_ENCLS_EXITING |					\

	 SECONDARY_EXEC_EPT_VIOLATION_VE)



#define KVM_REQUIRED_VMX_TERTIARY_VM_EXEC_CONTROL 0

#define KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL			\