From: Isaku Yamahata <isaku.yamahata@intel.com>

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: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Message-Id: <d6db6ba836605c0412e166359ba5c46a63c22f86.1705965635.git.isaku.yamahata@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/Kconfig    | 13 ++++++++++++
 arch/x86/kvm/vmx/vmcs.h |  5 +++++
 arch/x86/kvm/vmx/vmx.c  | 47 ++++++++++++++++++++++++++++++++++++++++-
 arch/x86/kvm/vmx/vmx.h  |  6 +++++-
 4 files changed, 69 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 3aaf7e86a859..7632fe6e4db9 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -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
diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h
index 7c1996b433e2..b25625314658 100644
--- a/arch/x86/kvm/vmx/vmcs.h
+++ b/arch/x86/kvm/vmx/vmcs.h
@@ -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)
 {
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 2c746318c6c3..3c2fb1310aaa 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -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 +4722,21 @@ 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));
+		} else {
+			/*
+			 * Because SECONDARY_EXEC_EPT_VIOLATION_VE is
+			 * used only for debugging, it's okay to leave
+			 * it disabled.
+			 */
+			secondary_exec_controls_clearbit(vmx,
+							 SECONDARY_EXEC_EPT_VIOLATION_VE);
+		}
+	}
 
 	if (cpu_has_tertiary_exec_ctrls())
 		tertiary_exec_controls_set(vmx, vmx_tertiary_exec_control(vmx));
@@ -5200,6 +5224,12 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	if (is_invalid_opcode(intr_info))
 		return handle_ud(vcpu);
 
+	/*
+	 * #VE isn't supposed to happen.  Block the VM if it does.
+	 */
+	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);
@@ -7474,6 +7504,8 @@ void vmx_vcpu_free(struct kvm_vcpu *vcpu)
 	free_vpid(vmx->vpid);
 	nested_vmx_free_vcpu(vcpu);
 	free_loaded_vmcs(vmx->loaded_vmcs);
+	if (vmx->ve_info)
+		free_page((unsigned long)vmx->ve_info);
 }
 
 int vmx_vcpu_create(struct kvm_vcpu *vcpu)
@@ -7567,6 +7599,19 @@ int vmx_vcpu_create(struct kvm_vcpu *vcpu)
 			goto free_vmcs;
 	}
 
+	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)
+			vmx->ve_info = page_to_virt(page);
+		else
+			pr_err("Failed to allocate ve_info. disabling EPT_VIOLATION_VE.\n");
+	}
+
 	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);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 65786dbe7d60..0da79a386825 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -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			\
-- 
2.43.0

On Tue, Apr 16, 2024, Paolo Bonzini wrote:
> @@ -4711,8 +4722,21 @@ 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));
> +		} else {
> +			/*
> +			 * Because SECONDARY_EXEC_EPT_VIOLATION_VE is
> +			 * used only for debugging, it's okay to leave
> +			 * it disabled.
> +			 */
> +			secondary_exec_controls_clearbit(vmx,
> +							 SECONDARY_EXEC_EPT_VIOLATION_VE);

As below, this is silly.

> +		}
> +	}
>  
>  	if (cpu_has_tertiary_exec_ctrls())
>  		tertiary_exec_controls_set(vmx, vmx_tertiary_exec_control(vmx));
> @@ -5200,6 +5224,12 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
>  	if (is_invalid_opcode(intr_info))
>  		return handle_ud(vcpu);
>  
> +	/*
> +	 * #VE isn't supposed to happen.  Block the VM if it does.
> +	 */

Doesn't need to be a multi-line comment.  Though I would just drop the comment,
the KVM_BUG_ON() makes it pretty darn clear #VE is unexpected.

> +	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);
> @@ -7474,6 +7504,8 @@ void vmx_vcpu_free(struct kvm_vcpu *vcpu)
>  	free_vpid(vmx->vpid);
>  	nested_vmx_free_vcpu(vcpu);
>  	free_loaded_vmcs(vmx->loaded_vmcs);
> +	if (vmx->ve_info)

free_page() handles '0', though hopefully this becomes a moot point.

> +		free_page((unsigned long)vmx->ve_info);
>  }
>  
>  int vmx_vcpu_create(struct kvm_vcpu *vcpu)
> @@ -7567,6 +7599,19 @@ int vmx_vcpu_create(struct kvm_vcpu *vcpu)
>  			goto free_vmcs;
>  	}
>  
> +	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)

Can we please just treat this as an error.  The odds of us screwing up checks
against vmx->ve_info are higher than the odds of someone enabling KVM_INTEL_PROVE_VE
on a machine with such high memory pressure that a 4KiB allocation fails, all
subequent memory allocations succeeding, *and* caring that VM creation fails.

The pr_err() in the failure path is even more ridiculous.

> +			vmx->ve_info = page_to_virt(page);
> +		else
> +			pr_err("Failed to allocate ve_info. disabling EPT_VIOLATION_VE.\n");
> +	}
> +
>  	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);