Merge branch 'kvm-vmx-ve' into HEAD

Allow a non-zero value for non-present SPTE and removed SPTE,
so that TDX can set the "suppress VE" bit.

Author: bonzini

arch/x86/include/asm/kvm_host.h

@@ -1313,6 +1313,8 @@ struct kvm_arch {
 	 */
 	spinlock_t mmu_unsync_pages_lock;
 
+	u64 shadow_mmio_value;
+
 	struct iommu_domain *iommu_domain;
 	bool iommu_noncoherent;
 #define __KVM_HAVE_ARCH_NONCOHERENT_DMA

arch/x86/include/asm/vmx.h

@@ -71,6 +71,7 @@
 #define SECONDARY_EXEC_ENCLS_EXITING		VMCS_CONTROL_BIT(ENCLS_EXITING)
 #define SECONDARY_EXEC_RDSEED_EXITING		VMCS_CONTROL_BIT(RDSEED_EXITING)
 #define SECONDARY_EXEC_ENABLE_PML               VMCS_CONTROL_BIT(PAGE_MOD_LOGGING)
+#define SECONDARY_EXEC_EPT_VIOLATION_VE		VMCS_CONTROL_BIT(EPT_VIOLATION_VE)
 #define SECONDARY_EXEC_PT_CONCEAL_VMX		VMCS_CONTROL_BIT(PT_CONCEAL_VMX)
 #define SECONDARY_EXEC_ENABLE_XSAVES		VMCS_CONTROL_BIT(XSAVES)
 #define SECONDARY_EXEC_MODE_BASED_EPT_EXEC	VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC)
@@ -226,6 +227,8 @@ enum vmcs_field {
 	VMREAD_BITMAP_HIGH              = 0x00002027,
 	VMWRITE_BITMAP                  = 0x00002028,
 	VMWRITE_BITMAP_HIGH             = 0x00002029,
+	VE_INFORMATION_ADDRESS		= 0x0000202A,
+	VE_INFORMATION_ADDRESS_HIGH	= 0x0000202B,
 	XSS_EXIT_BITMAP                 = 0x0000202C,
 	XSS_EXIT_BITMAP_HIGH            = 0x0000202D,
 	ENCLS_EXITING_BITMAP		= 0x0000202E,
@@ -514,6 +517,7 @@ enum vmcs_field {
 #define VMX_EPT_IPAT_BIT    			(1ull << 6)
 #define VMX_EPT_ACCESS_BIT			(1ull << 8)
 #define VMX_EPT_DIRTY_BIT			(1ull << 9)
+#define VMX_EPT_SUPPRESS_VE_BIT			(1ull << 63)
 #define VMX_EPT_RWX_MASK                        (VMX_EPT_READABLE_MASK |       \
 						 VMX_EPT_WRITABLE_MASK |       \
 						 VMX_EPT_EXECUTABLE_MASK)
@@ -630,4 +634,13 @@ enum vmx_l1d_flush_state {
 
 extern enum vmx_l1d_flush_state l1tf_vmx_mitigation;
 
+struct vmx_ve_information {
+	u32 exit_reason;
+	u32 delivery;
+	u64 exit_qualification;
+	u64 guest_linear_address;
+	u64 guest_physical_address;
+	u16 eptp_index;
+};
+
 #endif

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

arch/x86/kvm/mmu/mmu.c

@@ -567,9 +567,9 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
 
 	if (!is_shadow_present_pte(old_spte) ||
 	    !spte_has_volatile_bits(old_spte))
-		__update_clear_spte_fast(sptep, 0ull);
+		__update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE);
 	else
-		old_spte = __update_clear_spte_slow(sptep, 0ull);
+		old_spte = __update_clear_spte_slow(sptep, SHADOW_NONPRESENT_VALUE);
 
 	if (!is_shadow_present_pte(old_spte))
 		return old_spte;
@@ -603,7 +603,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
  */
 static void mmu_spte_clear_no_track(u64 *sptep)
 {
-	__update_clear_spte_fast(sptep, 0ull);
+	__update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE);
 }
 
 static u64 mmu_spte_get_lockless(u64 *sptep)
@@ -1897,7 +1897,8 @@ static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 static int kvm_sync_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i)
 {
-	if (!sp->spt[i])
+	/* sp->spt[i] has initial value of shadow page table allocation */
+	if (sp->spt[i] == SHADOW_NONPRESENT_VALUE)
 		return 0;
 
 	return vcpu->arch.mmu->sync_spte(vcpu, sp, i);
@@ -2461,7 +2462,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 				return kvm_mmu_prepare_zap_page(kvm, child,
 								invalid_list);
 		}
-	} else if (is_mmio_spte(pte)) {
+	} else if (is_mmio_spte(kvm, pte)) {
 		mmu_spte_clear_no_track(spte);
 	}
 	return 0;
@@ -4143,7 +4144,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 	if (WARN_ON_ONCE(reserved))
 		return -EINVAL;
 
-	if (is_mmio_spte(spte)) {
+	if (is_mmio_spte(vcpu->kvm, spte)) {
 		gfn_t gfn = get_mmio_spte_gfn(spte);
 		unsigned int access = get_mmio_spte_access(spte);
 
@@ -4759,7 +4760,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd);
 static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
 			   unsigned int access)
 {
-	if (unlikely(is_mmio_spte(*sptep))) {
+	if (unlikely(is_mmio_spte(vcpu->kvm, *sptep))) {
 		if (gfn != get_mmio_spte_gfn(*sptep)) {
 			mmu_spte_clear_no_track(sptep);
 			return true;
@@ -6120,7 +6121,10 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache;
 	vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO;
 
-	vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
+	vcpu->arch.mmu_shadow_page_cache.init_value =
+		SHADOW_NONPRESENT_VALUE;
+	if (!vcpu->arch.mmu_shadow_page_cache.init_value)
+		vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
 
 	vcpu->arch.mmu = &vcpu->arch.root_mmu;
 	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
@@ -6263,6 +6267,7 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
 
 void kvm_mmu_init_vm(struct kvm *kvm)
 {
+	kvm->arch.shadow_mmio_value = shadow_mmio_value;
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
 	INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);

arch/x86/kvm/mmu/paging_tmpl.h

@@ -911,7 +911,7 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int
 	gpa_t pte_gpa;
 	gfn_t gfn;
 
-	if (WARN_ON_ONCE(!sp->spt[i]))
+	if (WARN_ON_ONCE(sp->spt[i] == SHADOW_NONPRESENT_VALUE))
 		return 0;
 
 	first_pte_gpa = FNAME(get_level1_sp_gpa)(sp);
@@ -933,13 +933,13 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int
 		return 0;
 
 	/*
-	 * Drop the SPTE if the new protections would result in a RWX=0
-	 * SPTE or if the gfn is changing.  The RWX=0 case only affects
-	 * EPT with execute-only support, i.e. EPT without an effective
-	 * "present" bit, as all other paging modes will create a
-	 * read-only SPTE if pte_access is zero.
+	 * Drop the SPTE if the new protections result in no effective
+	 * "present" bit or if the gfn is changing.  The former case
+	 * only affects EPT with execute-only support with pte_access==0;
+	 * all other paging modes will create a read-only SPTE if
+	 * pte_access is zero.
 	 */
-	if ((!pte_access && !shadow_present_mask) ||
+	if ((pte_access | shadow_present_mask) == SHADOW_NONPRESENT_VALUE ||
 	    gfn != kvm_mmu_page_get_gfn(sp, i)) {
 		drop_spte(vcpu->kvm, &sp->spt[i]);
 		return 1;

arch/x86/kvm/mmu/spte.c

@@ -74,10 +74,10 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access)
 	u64 spte = generation_mmio_spte_mask(gen);
 	u64 gpa = gfn << PAGE_SHIFT;
 
-	WARN_ON_ONCE(!shadow_mmio_value);
+	WARN_ON_ONCE(!vcpu->kvm->arch.shadow_mmio_value);
 
 	access &= shadow_mmio_access_mask;
-	spte |= shadow_mmio_value | access;
+	spte |= vcpu->kvm->arch.shadow_mmio_value | access;
 	spte |= gpa | shadow_nonpresent_or_rsvd_mask;
 	spte |= (gpa & shadow_nonpresent_or_rsvd_mask)
 		<< SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
@@ -144,19 +144,19 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	u64 spte = SPTE_MMU_PRESENT_MASK;
 	bool wrprot = false;
 
-	WARN_ON_ONCE(!pte_access && !shadow_present_mask);
+	/*
+	 * For the EPT case, shadow_present_mask has no RWX bits set if
+	 * exec-only page table entries are supported.  In that case,
+	 * ACC_USER_MASK and shadow_user_mask are used to represent
+	 * read access.  See FNAME(gpte_access) in paging_tmpl.h.
+	 */
+	WARN_ON_ONCE((pte_access | shadow_present_mask) == SHADOW_NONPRESENT_VALUE);
 
 	if (sp->role.ad_disabled)
 		spte |= SPTE_TDP_AD_DISABLED;
 	else if (kvm_mmu_page_ad_need_write_protect(sp))
 		spte |= SPTE_TDP_AD_WRPROT_ONLY;
 
-	/*
-	 * For the EPT case, shadow_present_mask is 0 if hardware
-	 * supports exec-only page table entries.  In that case,
-	 * ACC_USER_MASK and shadow_user_mask are used to represent
-	 * read access.  See FNAME(gpte_access) in paging_tmpl.h.
-	 */
 	spte |= shadow_present_mask;
 	if (!prefetch)
 		spte |= spte_shadow_accessed_mask(spte);
@@ -413,7 +413,9 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
 	shadow_dirty_mask	= has_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull;
 	shadow_nx_mask		= 0ull;
 	shadow_x_mask		= VMX_EPT_EXECUTABLE_MASK;
-	shadow_present_mask	= has_exec_only ? 0ull : VMX_EPT_READABLE_MASK;
+	/* VMX_EPT_SUPPRESS_VE_BIT is needed for W or X violation. */
+	shadow_present_mask	=
+		(has_exec_only ? 0ull : VMX_EPT_READABLE_MASK) | VMX_EPT_SUPPRESS_VE_BIT;
 	/*
 	 * EPT overrides the host MTRRs, and so KVM must program the desired
 	 * memtype directly into the SPTEs.  Note, this mask is just the mask
@@ -430,7 +432,7 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
 	 * of an EPT paging-structure entry is 110b (write/execute).
 	 */
 	kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE,
-				   VMX_EPT_RWX_MASK, 0);
+				   VMX_EPT_RWX_MASK | VMX_EPT_SUPPRESS_VE_BIT, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_ept_masks);
 

arch/x86/kvm/mmu/spte.h

@@ -149,6 +149,22 @@ static_assert(MMIO_SPTE_GEN_LOW_BITS == 8 && MMIO_SPTE_GEN_HIGH_BITS == 11);
 
 #define MMIO_SPTE_GEN_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)
 
+/*
+ * Non-present SPTE value needs to set bit 63 for TDX, in order to suppress
+ * #VE and get EPT violations on non-present PTEs.  We can use the
+ * same value also without TDX for both VMX and SVM:
+ *
+ * For SVM NPT, for non-present spte (bit 0 = 0), other bits are ignored.
+ * For VMX EPT, bit 63 is ignored if #VE is disabled. (EPT_VIOLATION_VE=0)
+ *              bit 63 is #VE suppress if #VE is enabled. (EPT_VIOLATION_VE=1)
+ */
+#ifdef CONFIG_X86_64
+#define SHADOW_NONPRESENT_VALUE	BIT_ULL(63)
+static_assert(!(SHADOW_NONPRESENT_VALUE & SPTE_MMU_PRESENT_MASK));
+#else
+#define SHADOW_NONPRESENT_VALUE	0ULL
+#endif
+
 extern u64 __read_mostly shadow_host_writable_mask;
 extern u64 __read_mostly shadow_mmu_writable_mask;
 extern u64 __read_mostly shadow_nx_mask;
@@ -190,11 +206,11 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
  *
  * Use a semi-arbitrary value that doesn't set RWX bits, i.e. is not-present on
  * both AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF
- * vulnerability.  Use only low bits to avoid 64-bit immediates.
+ * vulnerability.
  *
  * Only used by the TDP MMU.
  */
-#define REMOVED_SPTE	0x5a0ULL
+#define REMOVED_SPTE	(SHADOW_NONPRESENT_VALUE | 0x5a0ULL)
 
 /* Removed SPTEs must not be misconstrued as shadow present PTEs. */
 static_assert(!(REMOVED_SPTE & SPTE_MMU_PRESENT_MASK));
@@ -249,9 +265,9 @@ static inline struct kvm_mmu_page *root_to_sp(hpa_t root)
 	return spte_to_child_sp(root);
 }
 
-static inline bool is_mmio_spte(u64 spte)
+static inline bool is_mmio_spte(struct kvm *kvm, u64 spte)
 {
-	return (spte & shadow_mmio_mask) == shadow_mmio_value &&
+	return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value &&
 	       likely(enable_mmio_caching);
 }
 

arch/x86/kvm/mmu/tdp_mmu.c

@@ -495,8 +495,8 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 		 * impact the guest since both the former and current SPTEs
 		 * are nonpresent.
 		 */
-		if (WARN_ON_ONCE(!is_mmio_spte(old_spte) &&
-				 !is_mmio_spte(new_spte) &&
+		if (WARN_ON_ONCE(!is_mmio_spte(kvm, old_spte) &&
+				 !is_mmio_spte(kvm, new_spte) &&
 				 !is_removed_spte(new_spte)))
 			pr_err("Unexpected SPTE change! Nonpresent SPTEs\n"
 			       "should not be replaced with another,\n"
@@ -603,7 +603,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
 	 * here since the SPTE is going from non-present to non-present.  Use
 	 * the raw write helper to avoid an unnecessary check on volatile bits.
 	 */
-	__kvm_tdp_mmu_write_spte(iter->sptep, 0);
+	__kvm_tdp_mmu_write_spte(iter->sptep, SHADOW_NONPRESENT_VALUE);
 
 	return 0;
 }
@@ -740,8 +740,8 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
 			continue;
 
 		if (!shared)
-			tdp_mmu_iter_set_spte(kvm, &iter, 0);
-		else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0))
+			tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
+		else if (tdp_mmu_set_spte_atomic(kvm, &iter, SHADOW_NONPRESENT_VALUE))
 			goto retry;
 	}
 }
@@ -808,8 +808,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 	if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte)))
 		return false;
 
-	tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0,
-			 sp->gfn, sp->role.level + 1);
+	tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte,
+			 SHADOW_NONPRESENT_VALUE, sp->gfn, sp->role.level + 1);
 
 	return true;
 }
@@ -843,7 +843,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
 		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
 
-		tdp_mmu_iter_set_spte(kvm, &iter, 0);
+		tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
 
 		/*
 		 * Zappings SPTEs in invalid roots doesn't require a TLB flush,
@@ -1028,7 +1028,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
 	}
 
 	/* If a MMIO SPTE is installed, the MMIO will need to be emulated. */
-	if (unlikely(is_mmio_spte(new_spte))) {
+	if (unlikely(is_mmio_spte(vcpu->kvm, new_spte))) {
 		vcpu->stat.pf_mmio_spte_created++;
 		trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn,
 				     new_spte);

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)
 {