Resguardo inicial

linux-7.2.3/arch/x86/kvm/mmu/mmu_internal.h

@@ -0,0 +1,414 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_MMU_INTERNAL_H
+#define __KVM_X86_MMU_INTERNAL_H
+
+#include <linux/types.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_host.h>
+
+#include "mmu.h"
+
+#ifdef CONFIG_KVM_PROVE_MMU
+#define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x)
+#else
+#define KVM_MMU_WARN_ON(x) BUILD_BUG_ON_INVALID(x)
+#endif
+
+/* Page table builder macros common to shadow (host) PTEs and guest PTEs. */
+#define __PT_BASE_ADDR_MASK GENMASK_ULL(51, 12)
+#define __PT_LEVEL_SHIFT(level, bits_per_level)	\
+	(PAGE_SHIFT + ((level) - 1) * (bits_per_level))
+#define __PT_INDEX(address, level, bits_per_level) \
+	(((address) >> __PT_LEVEL_SHIFT(level, bits_per_level)) & ((1 << (bits_per_level)) - 1))
+
+#define __PT_LVL_ADDR_MASK(base_addr_mask, level, bits_per_level) \
+	((base_addr_mask) & ~((1ULL << (PAGE_SHIFT + (((level) - 1) * (bits_per_level)))) - 1))
+
+#define __PT_LVL_OFFSET_MASK(base_addr_mask, level, bits_per_level) \
+	((base_addr_mask) & ((1ULL << (PAGE_SHIFT + (((level) - 1) * (bits_per_level)))) - 1))
+
+#define __PT_ENT_PER_PAGE(bits_per_level)  (1 << (bits_per_level))
+
+/*
+ * Unlike regular MMU roots, PAE "roots", a.k.a. PDPTEs/PDPTRs, have a PRESENT
+ * bit, and thus are guaranteed to be non-zero when valid.  And, when a guest
+ * PDPTR is !PRESENT, its corresponding PAE root cannot be set to INVALID_PAGE,
+ * as the CPU would treat that as PRESENT PDPTR with reserved bits set.  Use
+ * '0' instead of INVALID_PAGE to indicate an invalid PAE root.
+ */
+#define INVALID_PAE_ROOT	0
+#define IS_VALID_PAE_ROOT(x)	(!!(x))
+
+typedef u64 __rcu *tdp_ptep_t;
+
+struct kvm_mmu_page {
+	/*
+	 * Note, "link" through "spt" fit in a single 64 byte cache line on
+	 * 64-bit kernels, keep it that way unless there's a reason not to.
+	 */
+	struct list_head link;
+	struct hlist_node hash_link;
+
+	bool tdp_mmu_page;
+	bool unsync;
+	union {
+		u8 mmu_valid_gen;
+
+		/* Only accessed under slots_lock.  */
+		bool tdp_mmu_scheduled_root_to_zap;
+	};
+
+	 /*
+	  * The shadow page can't be replaced by an equivalent huge page
+	  * because it is being used to map an executable page in the guest
+	  * and the NX huge page mitigation is enabled.
+	  */
+	bool nx_huge_page_disallowed;
+
+	/*
+	 * The following two entries are used to key the shadow page in the
+	 * hash table.
+	 */
+	union kvm_mmu_page_role role;
+	gfn_t gfn;
+
+	u64 *spt;
+
+	/*
+	 * Stores the result of the guest translation being shadowed by each
+	 * SPTE.  KVM shadows two types of guest translations: nGPA -> GPA
+	 * (shadow EPT/NPT) and GVA -> GPA (traditional shadow paging). In both
+	 * cases the result of the translation is a GPA and a set of access
+	 * constraints.
+	 *
+	 * The GFN is stored in the upper bits (PAGE_SHIFT) and the shadowed
+	 * access permissions are stored in the lower bits. Note, for
+	 * convenience and uniformity across guests, the access permissions are
+	 * stored in KVM format (e.g.  ACC_EXEC_MASK) not the raw guest format.
+	 */
+	u64 *shadowed_translation;
+
+	/* Currently serving as active root */
+	union {
+		int root_count;
+		refcount_t tdp_mmu_root_count;
+	};
+
+	bool has_mapped_host_mmio;
+
+	union {
+		/* These two members aren't used for TDP MMU */
+		struct {
+			unsigned int unsync_children;
+			/*
+			 * Number of writes since the last time traversal
+			 * visited this page.
+			 */
+			atomic_t write_flooding_count;
+		};
+		/*
+		 * Page table page of external PT.
+		 * Passed to TDX module, not accessed by KVM.
+		 */
+		void *external_spt;
+	};
+	union {
+		struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
+		tdp_ptep_t ptep;
+	};
+	DECLARE_BITMAP(unsync_child_bitmap, 512);
+
+	/*
+	 * Tracks shadow pages that, if zapped, would allow KVM to create an NX
+	 * huge page.  A shadow page will have nx_huge_page_disallowed set but
+	 * not be on the list if a huge page is disallowed for other reasons,
+	 * e.g. because KVM is shadowing a PTE at the same gfn, the memslot
+	 * isn't properly aligned, etc...
+	 */
+	struct list_head possible_nx_huge_page_link;
+#ifdef CONFIG_X86_32
+	/*
+	 * Used out of the mmu-lock to avoid reading spte values while an
+	 * update is in progress; see the comments in __get_spte_lockless().
+	 */
+	int clear_spte_count;
+#endif
+
+#ifdef CONFIG_X86_64
+	/* Used for freeing the page asynchronously if it is a TDP MMU page. */
+	struct rcu_head rcu_head;
+#endif
+};
+
+extern struct kmem_cache *mmu_page_header_cache;
+
+static inline int kvm_mmu_role_as_id(union kvm_mmu_page_role role)
+{
+	return role.smm ? 1 : 0;
+}
+
+static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
+{
+	return kvm_mmu_role_as_id(sp->role);
+}
+
+static inline bool is_mirror_sp(const struct kvm_mmu_page *sp)
+{
+	return sp->role.is_mirror;
+}
+
+static inline void kvm_mmu_alloc_external_spt(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+{
+	/*
+	 * external_spt is allocated for TDX module to hold private EPT mappings,
+	 * TDX module will initialize the page by itself.
+	 * Therefore, KVM does not need to initialize or access external_spt.
+	 * KVM only interacts with sp->spt for private EPT operations.
+	 */
+	sp->external_spt = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_external_spt_cache);
+}
+
+static inline gfn_t kvm_gfn_root_bits(const struct kvm *kvm, const struct kvm_mmu_page *root)
+{
+	/*
+	 * Since mirror SPs are used only for TDX, which maps private memory
+	 * at its "natural" GFN, no mask needs to be applied to them - and, dually,
+	 * we expect that the bits is only used for the shared PT.
+	 */
+	if (is_mirror_sp(root))
+		return 0;
+	return kvm_gfn_direct_bits(kvm);
+}
+
+static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm *kvm,
+						      struct kvm_mmu_page *sp)
+{
+	/*
+	 * When using the EPT page-modification log, the GPAs in the CPU dirty
+	 * log would come from L2 rather than L1.  Therefore, we need to rely
+	 * on write protection to record dirty pages, which bypasses PML, since
+	 * writes now result in a vmexit.  Note, the check on CPU dirty logging
+	 * being enabled is mandatory as the bits used to denote WP-only SPTEs
+	 * are reserved for PAE paging (32-bit KVM).
+	 */
+	return kvm->arch.cpu_dirty_log_size && sp->role.guest_mode;
+}
+
+static inline gfn_t gfn_round_for_level(gfn_t gfn, int level)
+{
+	return gfn & -KVM_PAGES_PER_HPAGE(level);
+}
+
+int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
+			    gfn_t gfn, bool synchronizing, bool prefetch);
+
+void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn);
+void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn);
+bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
+				    struct kvm_memory_slot *slot, u64 gfn,
+				    int min_level);
+
+/* Flush the given page (huge or not) of guest memory. */
+static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level)
+{
+	kvm_flush_remote_tlbs_range(kvm, gfn_round_for_level(gfn, level),
+				    KVM_PAGES_PER_HPAGE(level));
+}
+
+unsigned int pte_list_count(struct kvm_rmap_head *rmap_head);
+
+extern int nx_huge_pages;
+static inline bool is_nx_huge_page_enabled(struct kvm *kvm)
+{
+	return READ_ONCE(nx_huge_pages) && !kvm->arch.disable_nx_huge_pages;
+}
+
+struct kvm_page_fault {
+	/* arguments to kvm_mmu_do_page_fault.  */
+	const gpa_t addr;
+	const u64 error_code;
+	const bool prefetch;
+
+	/* Derived from error_code.  */
+	const bool exec;
+	const bool write;
+	const bool present;
+	const bool rsvd;
+	const bool user;
+
+	/* Derived from mmu and global state.  */
+	const bool is_tdp;
+	const bool is_private;
+	const bool nx_huge_page_workaround_enabled;
+
+	/*
+	 * Whether a >4KB mapping can be created or is forbidden due to NX
+	 * hugepages.
+	 */
+	bool huge_page_disallowed;
+
+	/*
+	 * Maximum page size that can be created for this fault; input to
+	 * FNAME(fetch), direct_map() and kvm_tdp_mmu_map().
+	 */
+	u8 max_level;
+
+	/*
+	 * Page size that can be created based on the max_level and the
+	 * page size used by the host mapping.
+	 */
+	u8 req_level;
+
+	/*
+	 * Page size that will be created based on the req_level and
+	 * huge_page_disallowed.
+	 */
+	u8 goal_level;
+
+	/*
+	 * Shifted addr, or result of guest page table walk if addr is a gva. In
+	 * the case of VM where memslot's can be mapped at multiple GPA aliases
+	 * (i.e. TDX), the gfn field does not contain the bit that selects between
+	 * the aliases (i.e. the shared bit for TDX).
+	 */
+	gfn_t gfn;
+
+	/* The memslot containing gfn. May be NULL. */
+	struct kvm_memory_slot *slot;
+
+	/* Outputs of kvm_mmu_faultin_pfn().  */
+	unsigned long mmu_seq;
+	kvm_pfn_t pfn;
+	struct page *refcounted_page;
+	bool map_writable;
+
+	/*
+	 * Indicates the guest is trying to write a gfn that contains one or
+	 * more of the PTEs used to translate the write itself, i.e. the access
+	 * is changing its own translation in the guest page tables.
+	 */
+	bool write_fault_to_shadow_pgtable;
+};
+
+int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
+
+/*
+ * Return values of handle_mmio_page_fault(), mmu.page_fault(), fast_page_fault(),
+ * and of course kvm_mmu_do_page_fault().
+ *
+ * RET_PF_CONTINUE: So far, so good, keep handling the page fault.
+ * RET_PF_RETRY: let CPU fault again on the address.
+ * RET_PF_EMULATE: mmio page fault, emulate the instruction directly.
+ * RET_PF_WRITE_PROTECTED: the gfn is write-protected, either unprotected the
+ *                         gfn and retry, or emulate the instruction directly.
+ * RET_PF_INVALID: the spte is invalid, let the real page fault path update it.
+ * RET_PF_FIXED: The faulting entry has been fixed.
+ * RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU.
+ *
+ * Any names added to this enum should be exported to userspace for use in
+ * tracepoints via TRACE_DEFINE_ENUM() in mmutrace.h
+ *
+ * Note, all values must be greater than or equal to zero so as not to encroach
+ * on -errno return values.
+ */
+enum {
+	RET_PF_CONTINUE = 0,
+	RET_PF_RETRY,
+	RET_PF_EMULATE,
+	RET_PF_WRITE_PROTECTED,
+	RET_PF_INVALID,
+	RET_PF_FIXED,
+	RET_PF_SPURIOUS,
+};
+
+/*
+ * Define RET_PF_CONTINUE as 0 to allow for
+ * - efficient machine code when checking for CONTINUE, e.g.
+ *   "TEST %rax, %rax, JNZ", as all "stop!" values are non-zero,
+ * - kvm_mmu_do_page_fault() to return other RET_PF_* as a positive value.
+ */
+static_assert(RET_PF_CONTINUE == 0);
+
+static inline void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+						     struct kvm_page_fault *fault)
+{
+	kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
+				      PAGE_SIZE, fault->write, fault->exec,
+				      fault->is_private);
+}
+
+static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+					u64 err, bool prefetch,
+					int *emulation_type, u8 *level)
+{
+	struct kvm_page_fault fault = {
+		.addr = cr2_or_gpa,
+		.error_code = err,
+		.exec = err & PFERR_FETCH_MASK,
+		.write = err & PFERR_WRITE_MASK,
+		.present = err & PFERR_PRESENT_MASK,
+		.rsvd = err & PFERR_RSVD_MASK,
+		.user = err & PFERR_USER_MASK,
+		.prefetch = prefetch,
+		.is_tdp = likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault),
+		.nx_huge_page_workaround_enabled =
+			is_nx_huge_page_enabled(vcpu->kvm),
+
+		.max_level = KVM_MAX_HUGEPAGE_LEVEL,
+		.req_level = PG_LEVEL_4K,
+		.goal_level = PG_LEVEL_4K,
+		.is_private = err & PFERR_PRIVATE_ACCESS,
+
+		.pfn = KVM_PFN_ERR_FAULT,
+	};
+	int r;
+
+	if (vcpu->arch.mmu->root_role.direct) {
+		/*
+		 * Things like memslots don't understand the concept of a shared
+		 * bit. Strip it so that the GFN can be used like normal, and the
+		 * fault.addr can be used when the shared bit is needed.
+		 */
+		fault.gfn = gpa_to_gfn(fault.addr) & ~kvm_gfn_direct_bits(vcpu->kvm);
+		fault.slot = kvm_vcpu_gfn_to_memslot(vcpu, fault.gfn);
+	}
+
+	/*
+	 * With retpoline being active an indirect call is rather expensive,
+	 * so do a direct call in the most common case.
+	 */
+	if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && fault.is_tdp)
+		r = kvm_tdp_page_fault(vcpu, &fault);
+	else
+		r = vcpu->arch.mmu->page_fault(vcpu, &fault);
+
+	/*
+	 * Not sure what's happening, but punt to userspace and hope that
+	 * they can fix it by changing memory to shared, or they can
+	 * provide a better error.
+	 */
+	if (r == RET_PF_EMULATE && fault.is_private) {
+		pr_warn_ratelimited("kvm: unexpected emulation request on private memory\n");
+		kvm_mmu_prepare_memory_fault_exit(vcpu, &fault);
+		return -EFAULT;
+	}
+
+	if (fault.write_fault_to_shadow_pgtable && emulation_type)
+		*emulation_type |= EMULTYPE_WRITE_PF_TO_SP;
+	if (level)
+		*level = fault.goal_level;
+
+	return r;
+}
+
+int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault,
+			      const struct kvm_memory_slot *slot, gfn_t gfn);
+void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
+void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level);
+
+void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+				 enum kvm_mmu_type mmu_type);
+void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+				   enum kvm_mmu_type mmu_type);
+
+#endif /* __KVM_X86_MMU_INTERNAL_H */

linux-7.2.3/arch/x86/kvm/mmu/mmutrace.h

@@ -0,0 +1,458 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if !defined(_TRACE_KVMMMU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVMMMU_H
+
+#include <linux/tracepoint.h>
+#include <linux/trace_events.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvmmmu
+
+#define KVM_MMU_PAGE_FIELDS		\
+	__field(__u8, mmu_valid_gen)	\
+	__field(__u64, gfn)		\
+	__field(__u32, role)		\
+	__field(__u32, root_count)	\
+	__field(bool, unsync)
+
+#define KVM_MMU_PAGE_ASSIGN(sp)				\
+	__entry->mmu_valid_gen = sp->mmu_valid_gen;	\
+	__entry->gfn = sp->gfn;				\
+	__entry->role = sp->role.word;			\
+	__entry->root_count = sp->root_count;		\
+	__entry->unsync = sp->unsync;
+
+#define KVM_MMU_PAGE_PRINTK() ({				        \
+	const char *saved_ptr = trace_seq_buffer_ptr(p);		\
+	static const char *access_str[] = {			        \
+		"----", "r---", "-w--", "rw--", "--u-", "r-u-", "-wu-", "rwu-", \
+		"---x", "r--x", "-w-x", "rw-x", "--ux", "r-ux", "-wux", "rwux"	\
+	};							        \
+	union kvm_mmu_page_role role;				        \
+								        \
+	role.word = __entry->role;					\
+									\
+	trace_seq_printf(p, "sp gen %u gfn %llx l%u %u-byte q%u%s %s%s"	\
+			 " %snxe %sad root %u %s%c",			\
+			 __entry->mmu_valid_gen,			\
+			 __entry->gfn, role.level,			\
+			 role.has_4_byte_gpte ? 4 : 8,			\
+			 role.quadrant,					\
+			 role.direct ? " direct" : "",			\
+			 access_str[role.access],			\
+			 role.invalid ? " invalid" : "",		\
+			 role.efer_nx ? "" : "!",			\
+			 role.ad_disabled ? "!" : "",			\
+			 __entry->root_count,				\
+			 __entry->unsync ? "unsync" : "sync", 0);	\
+	saved_ptr;							\
+		})
+
+#define kvm_mmu_trace_pferr_flags       \
+	{ PFERR_PRESENT_MASK, "P" },	\
+	{ PFERR_WRITE_MASK, "W" },	\
+	{ PFERR_USER_MASK, "U" },	\
+	{ PFERR_PK_MASK, "PK" },	\
+	{ PFERR_SS_MASK, "SS" },	\
+	{ PFERR_SGX_MASK, "SGX" },	\
+	{ PFERR_RSVD_MASK, "RSVD" },	\
+	{ PFERR_FETCH_MASK, "F" }
+
+TRACE_DEFINE_ENUM(RET_PF_CONTINUE);
+TRACE_DEFINE_ENUM(RET_PF_RETRY);
+TRACE_DEFINE_ENUM(RET_PF_EMULATE);
+TRACE_DEFINE_ENUM(RET_PF_WRITE_PROTECTED);
+TRACE_DEFINE_ENUM(RET_PF_INVALID);
+TRACE_DEFINE_ENUM(RET_PF_FIXED);
+TRACE_DEFINE_ENUM(RET_PF_SPURIOUS);
+
+/*
+ * A pagetable walk has started
+ */
+TRACE_EVENT(
+	kvm_mmu_pagetable_walk,
+	TP_PROTO(u64 addr, u32 pferr),
+	TP_ARGS(addr, pferr),
+
+	TP_STRUCT__entry(
+		__field(__u64, addr)
+		__field(__u32, pferr)
+	),
+
+	TP_fast_assign(
+		__entry->addr = addr;
+		__entry->pferr = pferr;
+	),
+
+	TP_printk("addr %llx pferr %x %s", __entry->addr, __entry->pferr,
+		  __print_flags(__entry->pferr, "|", kvm_mmu_trace_pferr_flags))
+);
+
+
+/* We just walked a paging element */
+TRACE_EVENT(
+	kvm_mmu_paging_element,
+	TP_PROTO(u64 pte, int level),
+	TP_ARGS(pte, level),
+
+	TP_STRUCT__entry(
+		__field(__u64, pte)
+		__field(__u32, level)
+		),
+
+	TP_fast_assign(
+		__entry->pte = pte;
+		__entry->level = level;
+		),
+
+	TP_printk("pte %llx level %u", __entry->pte, __entry->level)
+);
+
+DECLARE_EVENT_CLASS(kvm_mmu_set_bit_class,
+
+	TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size),
+
+	TP_ARGS(table_gfn, index, size),
+
+	TP_STRUCT__entry(
+		__field(__u64, gpa)
+	),
+
+	TP_fast_assign(
+		__entry->gpa = ((u64)table_gfn << PAGE_SHIFT)
+				+ index * size;
+		),
+
+	TP_printk("gpa %llx", __entry->gpa)
+);
+
+/* We set a pte accessed bit */
+DEFINE_EVENT(kvm_mmu_set_bit_class, kvm_mmu_set_accessed_bit,
+
+	TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size),
+
+	TP_ARGS(table_gfn, index, size)
+);
+
+/* We set a pte dirty bit */
+DEFINE_EVENT(kvm_mmu_set_bit_class, kvm_mmu_set_dirty_bit,
+
+	TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size),
+
+	TP_ARGS(table_gfn, index, size)
+);
+
+TRACE_EVENT(
+	kvm_mmu_walker_error,
+	TP_PROTO(u32 pferr),
+	TP_ARGS(pferr),
+
+	TP_STRUCT__entry(
+		__field(__u32, pferr)
+		),
+
+	TP_fast_assign(
+		__entry->pferr = pferr;
+		),
+
+	TP_printk("pferr %x %s", __entry->pferr,
+		  __print_flags(__entry->pferr, "|", kvm_mmu_trace_pferr_flags))
+);
+
+TRACE_EVENT(
+	kvm_mmu_get_page,
+	TP_PROTO(struct kvm_mmu_page *sp, bool created),
+	TP_ARGS(sp, created),
+
+	TP_STRUCT__entry(
+		KVM_MMU_PAGE_FIELDS
+		__field(bool, created)
+		),
+
+	TP_fast_assign(
+		KVM_MMU_PAGE_ASSIGN(sp)
+		__entry->created = created;
+		),
+
+	TP_printk("%s %s", KVM_MMU_PAGE_PRINTK(),
+		  __entry->created ? "new" : "existing")
+);
+
+DECLARE_EVENT_CLASS(kvm_mmu_page_class,
+
+	TP_PROTO(struct kvm_mmu_page *sp),
+	TP_ARGS(sp),
+
+	TP_STRUCT__entry(
+		KVM_MMU_PAGE_FIELDS
+	),
+
+	TP_fast_assign(
+		KVM_MMU_PAGE_ASSIGN(sp)
+	),
+
+	TP_printk("%s", KVM_MMU_PAGE_PRINTK())
+);
+
+DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_sync_page,
+	TP_PROTO(struct kvm_mmu_page *sp),
+
+	TP_ARGS(sp)
+);
+
+DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_unsync_page,
+	TP_PROTO(struct kvm_mmu_page *sp),
+
+	TP_ARGS(sp)
+);
+
+DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_prepare_zap_page,
+	TP_PROTO(struct kvm_mmu_page *sp),
+
+	TP_ARGS(sp)
+);
+
+TRACE_EVENT(
+	mark_mmio_spte,
+	TP_PROTO(u64 *sptep, gfn_t gfn, u64 spte),
+	TP_ARGS(sptep, gfn, spte),
+
+	TP_STRUCT__entry(
+		__field(void *, sptep)
+		__field(gfn_t, gfn)
+		__field(unsigned, access)
+		__field(unsigned int, gen)
+	),
+
+	TP_fast_assign(
+		__entry->sptep = sptep;
+		__entry->gfn = gfn;
+		__entry->access = spte & ACC_ALL;
+		__entry->gen = get_mmio_spte_generation(spte);
+	),
+
+	TP_printk("sptep:%p gfn %llx access %x gen %x", __entry->sptep,
+		  __entry->gfn, __entry->access, __entry->gen)
+);
+
+TRACE_EVENT(
+	handle_mmio_page_fault,
+	TP_PROTO(u64 addr, gfn_t gfn, unsigned access),
+	TP_ARGS(addr, gfn, access),
+
+	TP_STRUCT__entry(
+		__field(u64, addr)
+		__field(gfn_t, gfn)
+		__field(unsigned, access)
+	),
+
+	TP_fast_assign(
+		__entry->addr = addr;
+		__entry->gfn = gfn;
+		__entry->access = access;
+	),
+
+	TP_printk("addr:%llx gfn %llx access %x", __entry->addr, __entry->gfn,
+		  __entry->access)
+);
+
+TRACE_EVENT(
+	fast_page_fault,
+	TP_PROTO(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
+		 u64 *sptep, u64 old_spte, int ret),
+	TP_ARGS(vcpu, fault, sptep, old_spte, ret),
+
+	TP_STRUCT__entry(
+		__field(int, vcpu_id)
+		__field(gpa_t, cr2_or_gpa)
+		__field(u64, error_code)
+		__field(u64 *, sptep)
+		__field(u64, old_spte)
+		__field(u64, new_spte)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id = vcpu->vcpu_id;
+		__entry->cr2_or_gpa = fault->addr;
+		__entry->error_code = fault->error_code;
+		__entry->sptep = sptep;
+		__entry->old_spte = old_spte;
+		__entry->new_spte = *sptep;
+		__entry->ret = ret;
+	),
+
+	TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx"
+		  " new %llx spurious %d fixed %d", __entry->vcpu_id,
+		  __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|",
+		  kvm_mmu_trace_pferr_flags), __entry->sptep,
+		  __entry->old_spte, __entry->new_spte,
+		  __entry->ret == RET_PF_SPURIOUS, __entry->ret == RET_PF_FIXED
+	)
+);
+
+TRACE_EVENT(
+	kvm_mmu_zap_all_fast,
+	TP_PROTO(struct kvm *kvm),
+	TP_ARGS(kvm),
+
+	TP_STRUCT__entry(
+		__field(__u8, mmu_valid_gen)
+		__field(unsigned int, mmu_used_pages)
+	),
+
+	TP_fast_assign(
+		__entry->mmu_valid_gen = kvm->arch.mmu_valid_gen;
+		__entry->mmu_used_pages = kvm->stat.mmu_shadow_pages;
+	),
+
+	TP_printk("kvm-mmu-valid-gen %u used_pages %x",
+		  __entry->mmu_valid_gen, __entry->mmu_used_pages
+	)
+);
+
+
+TRACE_EVENT(
+	check_mmio_spte,
+	TP_PROTO(u64 spte, unsigned int kvm_gen, unsigned int spte_gen),
+	TP_ARGS(spte, kvm_gen, spte_gen),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, kvm_gen)
+		__field(unsigned int, spte_gen)
+		__field(u64, spte)
+	),
+
+	TP_fast_assign(
+		__entry->kvm_gen = kvm_gen;
+		__entry->spte_gen = spte_gen;
+		__entry->spte = spte;
+	),
+
+	TP_printk("spte %llx kvm_gen %x spte-gen %x valid %d", __entry->spte,
+		  __entry->kvm_gen, __entry->spte_gen,
+		  __entry->kvm_gen == __entry->spte_gen
+	)
+);
+
+TRACE_EVENT(
+	kvm_mmu_set_spte,
+	TP_PROTO(int level, gfn_t gfn, u64 *sptep),
+	TP_ARGS(level, gfn, sptep),
+
+	TP_STRUCT__entry(
+		__field(u64, gfn)
+		__field(u64, spte)
+		__field(u64, sptep)
+		__field(u8, level)
+		/* These depend on page entry type, so compute them now.  */
+		__field(bool, r)
+		__field(bool, x)
+		__field(signed char, u)
+	),
+
+	TP_fast_assign(
+		__entry->gfn = gfn;
+		__entry->spte = *sptep;
+		__entry->sptep = virt_to_phys(sptep);
+		__entry->level = level;
+		__entry->r = shadow_present_mask || (__entry->spte & PT_PRESENT_MASK);
+		__entry->x = (__entry->spte & (shadow_xs_mask | shadow_nx_mask)) == shadow_xs_mask;
+		__entry->u = !!(__entry->spte & (shadow_xu_mask | shadow_user_mask));
+	),
+
+	TP_printk("gfn %llx spte %llx (%s%s%s%s) level %d at %llx",
+		  __entry->gfn, __entry->spte,
+		  __entry->r ? "r" : "-",
+		  __entry->spte & PT_WRITABLE_MASK ? "w" : "-",
+		  __entry->x ? "x" : "-",
+		  __entry->u ? "u" : "-",
+		  __entry->level, __entry->sptep
+	)
+);
+
+TRACE_EVENT(
+	kvm_mmu_spte_requested,
+	TP_PROTO(struct kvm_page_fault *fault, u8 access),
+	TP_ARGS(fault, access),
+
+	TP_STRUCT__entry(
+		__field(u64, gfn)
+		__field(u64, pfn)
+		__field(u8, level)
+		__field(u8, access)
+	),
+
+	TP_fast_assign(
+		__entry->gfn = fault->gfn;
+		__entry->pfn = fault->pfn | (fault->gfn & (KVM_PAGES_PER_HPAGE(fault->goal_level) - 1));
+		__entry->level = fault->goal_level;
+		__entry->access = access;
+	),
+
+	TP_printk("gfn %llx pfn %llx level %d access %x",
+		  __entry->gfn, __entry->pfn, __entry->level, __entry->access
+	)
+);
+
+TRACE_EVENT(
+	kvm_tdp_mmu_spte_changed,
+	TP_PROTO(int as_id, gfn_t gfn, int level, u64 old_spte, u64 new_spte),
+	TP_ARGS(as_id, gfn, level, old_spte, new_spte),
+
+	TP_STRUCT__entry(
+		__field(u64, gfn)
+		__field(u64, old_spte)
+		__field(u64, new_spte)
+		/* Level cannot be larger than 5 on x86, so it fits in a u8. */
+		__field(u8, level)
+		/* as_id can only be 0 or 1 x86, so it fits in a u8. */
+		__field(u8, as_id)
+	),
+
+	TP_fast_assign(
+		__entry->gfn = gfn;
+		__entry->old_spte = old_spte;
+		__entry->new_spte = new_spte;
+		__entry->level = level;
+		__entry->as_id = as_id;
+	),
+
+	TP_printk("as id %d gfn %llx level %d old_spte %llx new_spte %llx",
+		  __entry->as_id, __entry->gfn, __entry->level,
+		  __entry->old_spte, __entry->new_spte
+	)
+);
+
+TRACE_EVENT(
+	kvm_mmu_split_huge_page,
+	TP_PROTO(u64 gfn, u64 spte, int level, int errno),
+	TP_ARGS(gfn, spte, level, errno),
+
+	TP_STRUCT__entry(
+		__field(u64, gfn)
+		__field(u64, spte)
+		__field(int, level)
+		__field(int, errno)
+	),
+
+	TP_fast_assign(
+		__entry->gfn = gfn;
+		__entry->spte = spte;
+		__entry->level = level;
+		__entry->errno = errno;
+	),
+
+	TP_printk("gfn %llx spte %llx level %d errno %d",
+		  __entry->gfn, __entry->spte, __entry->level, __entry->errno)
+);
+
+#endif /* _TRACE_KVMMMU_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH mmu
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE mmutrace
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

linux-7.2.3/arch/x86/kvm/mmu/page_track.c

@@ -0,0 +1,394 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Support KVM gust page tracking
+ *
+ * This feature allows us to track page access in guest. Currently, only
+ * write access is tracked.
+ *
+ * Copyright(C) 2015 Intel Corporation.
+ *
+ * Author:
+ *   Xiao Guangrong <guangrong.xiao@linux.intel.com>
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/lockdep.h>
+#include <linux/kvm_host.h>
+#include <linux/rculist.h>
+
+#include "mmu.h"
+#include "mmu_internal.h"
+#include "page_track.h"
+
+static bool kvm_external_write_tracking_enabled(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
+	/*
+	 * Read external_write_tracking_enabled before related pointers.  Pairs
+	 * with the smp_store_release in kvm_page_track_write_tracking_enable().
+	 */
+	return smp_load_acquire(&kvm->arch.external_write_tracking_enabled);
+#else
+	return false;
+#endif
+}
+
+bool kvm_page_track_write_tracking_enabled(struct kvm *kvm)
+{
+	return kvm_external_write_tracking_enabled(kvm) ||
+	       kvm_shadow_root_allocated(kvm) || !tdp_enabled;
+}
+
+void kvm_page_track_free_memslot(struct kvm_memory_slot *slot)
+{
+	vfree(slot->arch.gfn_write_track);
+	slot->arch.gfn_write_track = NULL;
+}
+
+static int __kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot,
+						 unsigned long npages)
+{
+	const size_t size = sizeof(*slot->arch.gfn_write_track);
+
+	if (!slot->arch.gfn_write_track)
+		slot->arch.gfn_write_track = __vcalloc(npages, size,
+						       GFP_KERNEL_ACCOUNT);
+
+	return slot->arch.gfn_write_track ? 0 : -ENOMEM;
+}
+
+int kvm_page_track_create_memslot(struct kvm *kvm,
+				  struct kvm_memory_slot *slot,
+				  unsigned long npages)
+{
+	if (!kvm_page_track_write_tracking_enabled(kvm))
+		return 0;
+
+	return __kvm_page_track_write_tracking_alloc(slot, npages);
+}
+
+int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot)
+{
+	return __kvm_page_track_write_tracking_alloc(slot, slot->npages);
+}
+
+static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn,
+				   short count)
+{
+	int index, val;
+
+	index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
+
+	val = slot->arch.gfn_write_track[index];
+
+	if (WARN_ON_ONCE(val + count < 0 || val + count > USHRT_MAX))
+		return;
+
+	slot->arch.gfn_write_track[index] += count;
+}
+
+void __kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+			       gfn_t gfn)
+{
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	lockdep_assert_once(lockdep_is_held(&kvm->slots_lock) ||
+			    srcu_read_lock_held(&kvm->srcu));
+
+	if (KVM_BUG_ON(!kvm_page_track_write_tracking_enabled(kvm), kvm))
+		return;
+
+	update_gfn_write_track(slot, gfn, 1);
+
+	/*
+	 * new track stops large page mapping for the
+	 * tracked page.
+	 */
+	kvm_mmu_gfn_disallow_lpage(slot, gfn);
+
+	if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
+		kvm_flush_remote_tlbs(kvm);
+}
+
+void __kvm_write_track_remove_gfn(struct kvm *kvm,
+				  struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	lockdep_assert_once(lockdep_is_held(&kvm->slots_lock) ||
+			    srcu_read_lock_held(&kvm->srcu));
+
+	if (KVM_BUG_ON(!kvm_page_track_write_tracking_enabled(kvm), kvm))
+		return;
+
+	update_gfn_write_track(slot, gfn, -1);
+
+	/*
+	 * allow large page mapping for the tracked page
+	 * after the tracker is gone.
+	 */
+	kvm_mmu_gfn_allow_lpage(slot, gfn);
+}
+
+static bool __kvm_gfn_is_write_tracked(const struct kvm_memory_slot *slot,
+				       gfn_t gfn)
+{
+	int index;
+
+	if (!slot)
+		return false;
+
+	index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
+	return !!READ_ONCE(slot->arch.gfn_write_track[index]);
+}
+
+/* check if write access is tracked on the specified guest page.  */
+bool kvm_gfn_is_write_tracked(struct kvm *kvm,
+			      const struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	const struct kvm_memory_slot *other_slot;
+
+	if (!slot)
+		return false;
+
+	if (!kvm_page_track_write_tracking_enabled(kvm))
+		return false;
+
+	BUILD_BUG_ON(KVM_MAX_NR_ADDRESS_SPACES > 2);
+
+	if (__kvm_gfn_is_write_tracked(slot, gfn))
+		return true;
+
+	if (kvm_arch_nr_memslot_as_ids(kvm) > 1) {
+		other_slot = __gfn_to_memslot(__kvm_memslots(kvm, slot->as_id ^ 1), gfn);
+		if (__kvm_gfn_is_write_tracked(other_slot, gfn))
+			return true;
+	}
+
+	return false;
+}
+
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
+void kvm_page_track_cleanup(struct kvm *kvm)
+{
+	struct kvm_page_track_notifier_head *head;
+
+	head = &kvm->arch.track_notifier_head;
+	cleanup_srcu_struct(&head->track_srcu);
+}
+
+int kvm_page_track_init(struct kvm *kvm)
+{
+	struct kvm_page_track_notifier_head *head;
+
+	head = &kvm->arch.track_notifier_head;
+	INIT_HLIST_HEAD(&head->track_notifier_list);
+	return init_srcu_struct(&head->track_srcu);
+}
+
+static int kvm_enable_external_write_tracking(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *slot;
+	int r = 0, i, bkt;
+
+	if (kvm->arch.vm_type == KVM_X86_TDX_VM)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&kvm->slots_arch_lock);
+
+	/*
+	 * Check for *any* write tracking user (not just external users) under
+	 * lock.  This avoids unnecessary work, e.g. if KVM itself is using
+	 * write tracking, or if two external users raced when registering.
+	 */
+	if (kvm_page_track_write_tracking_enabled(kvm))
+		goto out_success;
+
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
+		slots = __kvm_memslots(kvm, i);
+		kvm_for_each_memslot(slot, bkt, slots) {
+			/*
+			 * Intentionally do NOT free allocations on failure to
+			 * avoid having to track which allocations were made
+			 * now versus when the memslot was created.  The
+			 * metadata is guaranteed to be freed when the slot is
+			 * freed, and will be kept/used if userspace retries
+			 * the failed ioctl() instead of killing the VM.
+			 */
+			r = kvm_page_track_write_tracking_alloc(slot);
+			if (r)
+				goto out_unlock;
+		}
+	}
+
+out_success:
+	/*
+	 * Ensure that external_write_tracking_enabled becomes true strictly
+	 * after all the related pointers are set.
+	 */
+	smp_store_release(&kvm->arch.external_write_tracking_enabled, true);
+out_unlock:
+	mutex_unlock(&kvm->slots_arch_lock);
+	return r;
+}
+
+/*
+ * register the notifier so that event interception for the tracked guest
+ * pages can be received.
+ */
+int kvm_page_track_register_notifier(struct kvm *kvm,
+				     struct kvm_page_track_notifier_node *n)
+{
+	struct kvm_page_track_notifier_head *head;
+	int r;
+
+	if (!kvm || kvm->mm != current->mm)
+		return -ESRCH;
+
+	if (!kvm_external_write_tracking_enabled(kvm)) {
+		r = kvm_enable_external_write_tracking(kvm);
+		if (r)
+			return r;
+	}
+
+	kvm_get_kvm(kvm);
+
+	head = &kvm->arch.track_notifier_head;
+
+	write_lock(&kvm->mmu_lock);
+	hlist_add_head_rcu(&n->node, &head->track_notifier_list);
+	write_unlock(&kvm->mmu_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier);
+
+/*
+ * stop receiving the event interception. It is the opposed operation of
+ * kvm_page_track_register_notifier().
+ */
+void kvm_page_track_unregister_notifier(struct kvm *kvm,
+					struct kvm_page_track_notifier_node *n)
+{
+	struct kvm_page_track_notifier_head *head;
+
+	head = &kvm->arch.track_notifier_head;
+
+	write_lock(&kvm->mmu_lock);
+	hlist_del_rcu(&n->node);
+	write_unlock(&kvm->mmu_lock);
+	synchronize_srcu(&head->track_srcu);
+
+	kvm_put_kvm(kvm);
+}
+EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier);
+
+/*
+ * Notify the node that write access is intercepted and write emulation is
+ * finished at this time.
+ *
+ * The node should figure out if the written page is the one that node is
+ * interested in by itself.
+ */
+void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa, const u8 *new, int bytes)
+{
+	struct kvm_page_track_notifier_head *head;
+	struct kvm_page_track_notifier_node *n;
+	int idx;
+
+	head = &kvm->arch.track_notifier_head;
+
+	if (hlist_empty(&head->track_notifier_list))
+		return;
+
+	idx = srcu_read_lock(&head->track_srcu);
+	hlist_for_each_entry_srcu(n, &head->track_notifier_list, node,
+				  srcu_read_lock_held(&head->track_srcu))
+		if (n->track_write)
+			n->track_write(gpa, new, bytes, n);
+	srcu_read_unlock(&head->track_srcu, idx);
+}
+
+/*
+ * Notify external page track nodes that a memory region is being removed from
+ * the VM, e.g. so that users can free any associated metadata.
+ */
+void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	struct kvm_page_track_notifier_head *head;
+	struct kvm_page_track_notifier_node *n;
+	int idx;
+
+	head = &kvm->arch.track_notifier_head;
+
+	if (hlist_empty(&head->track_notifier_list))
+		return;
+
+	idx = srcu_read_lock(&head->track_srcu);
+	hlist_for_each_entry_srcu(n, &head->track_notifier_list, node,
+				  srcu_read_lock_held(&head->track_srcu))
+		if (n->track_remove_region)
+			n->track_remove_region(slot->base_gfn, slot->npages, n);
+	srcu_read_unlock(&head->track_srcu, idx);
+}
+
+/*
+ * add guest page to the tracking pool so that corresponding access on that
+ * page will be intercepted.
+ *
+ * @kvm: the guest instance we are interested in.
+ * @gfn: the guest page.
+ */
+int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn)
+{
+	struct kvm_memory_slot *slot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+
+	slot = gfn_to_memslot(kvm, gfn);
+	if (!slot) {
+		srcu_read_unlock(&kvm->srcu, idx);
+		return -EINVAL;
+	}
+
+	write_lock(&kvm->mmu_lock);
+	__kvm_write_track_add_gfn(kvm, slot, gfn);
+	write_unlock(&kvm->mmu_lock);
+
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn);
+
+/*
+ * remove the guest page from the tracking pool which stops the interception
+ * of corresponding access on that page.
+ *
+ * @kvm: the guest instance we are interested in.
+ * @gfn: the guest page.
+ */
+int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn)
+{
+	struct kvm_memory_slot *slot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+
+	slot = gfn_to_memslot(kvm, gfn);
+	if (!slot) {
+		srcu_read_unlock(&kvm->srcu, idx);
+		return -EINVAL;
+	}
+
+	write_lock(&kvm->mmu_lock);
+	__kvm_write_track_remove_gfn(kvm, slot, gfn);
+	write_unlock(&kvm->mmu_lock);
+
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_write_track_remove_gfn);
+#endif

linux-7.2.3/arch/x86/kvm/mmu/page_track.h

@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_PAGE_TRACK_H
+#define __KVM_X86_PAGE_TRACK_H
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_page_track.h>
+
+
+bool kvm_page_track_write_tracking_enabled(struct kvm *kvm);
+int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot);
+
+void kvm_page_track_free_memslot(struct kvm_memory_slot *slot);
+int kvm_page_track_create_memslot(struct kvm *kvm,
+				  struct kvm_memory_slot *slot,
+				  unsigned long npages);
+
+void __kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+			       gfn_t gfn);
+void __kvm_write_track_remove_gfn(struct kvm *kvm,
+				  struct kvm_memory_slot *slot, gfn_t gfn);
+
+bool kvm_gfn_is_write_tracked(struct kvm *kvm,
+			      const struct kvm_memory_slot *slot, gfn_t gfn);
+
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
+int kvm_page_track_init(struct kvm *kvm);
+void kvm_page_track_cleanup(struct kvm *kvm);
+
+void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa, const u8 *new, int bytes);
+void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
+
+static inline bool kvm_page_track_has_external_user(struct kvm *kvm)
+{
+	return !hlist_empty(&kvm->arch.track_notifier_head.track_notifier_list);
+}
+#else
+static inline int kvm_page_track_init(struct kvm *kvm) { return 0; }
+static inline void kvm_page_track_cleanup(struct kvm *kvm) { }
+
+static inline void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa,
+					  const u8 *new, int bytes) { }
+static inline void kvm_page_track_delete_slot(struct kvm *kvm,
+					      struct kvm_memory_slot *slot) { }
+
+static inline bool kvm_page_track_has_external_user(struct kvm *kvm) { return false; }
+
+#endif /* CONFIG_KVM_EXTERNAL_WRITE_TRACKING */
+
+static inline void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa,
+					const u8 *new, int bytes)
+{
+	__kvm_page_track_write(vcpu->kvm, gpa, new, bytes);
+
+	kvm_mmu_track_write(vcpu, gpa, new, bytes);
+}
+
+#endif /* __KVM_X86_PAGE_TRACK_H */

linux-7.2.3/arch/x86/kvm/mmu/spte.c

@@ -0,0 +1,603 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Kernel-based Virtual Machine driver for Linux
+ *
+ * Macros and functions to access KVM PTEs (also known as SPTEs)
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright 2020 Red Hat, Inc. and/or its affiliates.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kvm_host.h>
+#include "mmu.h"
+#include "mmu_internal.h"
+#include "x86.h"
+#include "spte.h"
+
+#include <asm/cpuid/api.h>
+#include <asm/e820/api.h>
+#include <asm/memtype.h>
+#include <asm/vmx.h>
+
+bool __read_mostly enable_mmio_caching = true;
+static bool __ro_after_init allow_mmio_caching;
+module_param_named(mmio_caching, enable_mmio_caching, bool, 0444);
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_mmio_caching);
+
+bool __read_mostly kvm_ad_enabled;
+
+u64 __read_mostly shadow_host_writable_mask;
+u64 __read_mostly shadow_mmu_writable_mask;
+u64 __read_mostly shadow_nx_mask;
+u64 __read_mostly shadow_user_mask;
+u64 __read_mostly shadow_xs_mask; /* mutual exclusive with nx_mask and user_mask */
+u64 __read_mostly shadow_xu_mask; /* mutual exclusive with nx_mask and user_mask */
+u64 __read_mostly shadow_accessed_mask;
+u64 __read_mostly shadow_dirty_mask;
+u64 __read_mostly shadow_mmio_value;
+u64 __read_mostly shadow_mmio_mask;
+u64 __read_mostly shadow_mmio_access_mask;
+u64 __read_mostly shadow_present_mask;
+u64 __read_mostly shadow_me_value;
+u64 __read_mostly shadow_me_mask;
+u64 __read_mostly shadow_acc_track_mask;
+
+u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
+u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
+
+static u8 __init kvm_get_host_maxphyaddr(void)
+{
+	/*
+	 * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected
+	 * in CPU detection code, but the processor treats those reduced bits as
+	 * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at
+	 * the physical address bits reported by CPUID, i.e. the raw MAXPHYADDR,
+	 * when reasoning about CPU behavior with respect to MAXPHYADDR.
+	 */
+	if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008))
+		return cpuid_eax(0x80000008) & 0xff;
+
+	/*
+	 * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with
+	 * custom CPUID.  Proceed with whatever the kernel found since these features
+	 * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008).
+	 */
+	return boot_cpu_data.x86_phys_bits;
+}
+
+void __init kvm_mmu_spte_module_init(void)
+{
+	/*
+	 * Snapshot userspace's desire to allow MMIO caching.  Whether or not
+	 * KVM can actually enable MMIO caching depends on vendor-specific
+	 * hardware capabilities and other module params that can't be resolved
+	 * until the vendor module is loaded, i.e. enable_mmio_caching can and
+	 * will change when the vendor module is (re)loaded.
+	 */
+	allow_mmio_caching = enable_mmio_caching;
+
+	kvm_host.maxphyaddr = kvm_get_host_maxphyaddr();
+}
+
+static u64 generation_mmio_spte_mask(u64 gen)
+{
+	u64 mask;
+
+	WARN_ON_ONCE(gen & ~MMIO_SPTE_GEN_MASK);
+
+	mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK;
+	mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK;
+	return mask;
+}
+
+u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access)
+{
+	u64 gen = kvm_vcpu_memslots(vcpu)->generation & MMIO_SPTE_GEN_MASK;
+	u64 spte = generation_mmio_spte_mask(gen);
+	u64 gpa = gfn << PAGE_SHIFT;
+
+	access &= shadow_mmio_access_mask;
+	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;
+
+	return spte;
+}
+
+static bool __kvm_is_mmio_pfn(kvm_pfn_t pfn)
+{
+	if (pfn_valid(pfn))
+		return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)) &&
+			/*
+			 * Some reserved pages, such as those from NVDIMM
+			 * DAX devices, are not for MMIO, and can be mapped
+			 * with cached memory type for better performance.
+			 * However, the above check misconceives those pages
+			 * as MMIO, and results in KVM mapping them with UC
+			 * memory type, which would hurt the performance.
+			 * Therefore, we check the host memory type in addition
+			 * and only treat UC/UC-/WC pages as MMIO.
+			 */
+			(!pat_enabled() || pat_pfn_immune_to_uc_mtrr(pfn));
+
+	return !e820__mapped_raw_any(pfn_to_hpa(pfn),
+				     pfn_to_hpa(pfn + 1) - 1,
+				     E820_TYPE_RAM);
+}
+
+static bool kvm_is_mmio_pfn(kvm_pfn_t pfn, int *is_host_mmio)
+{
+	/*
+	 * Determining if a PFN is host MMIO is relative expensive.  Cache the
+	 * result locally (in the sole caller) to avoid doing the full query
+	 * multiple times when creating a single SPTE.
+	 */
+	if (*is_host_mmio < 0)
+		*is_host_mmio = __kvm_is_mmio_pfn(pfn);
+
+	return *is_host_mmio;
+}
+
+static void kvm_track_host_mmio_mapping(struct kvm_vcpu *vcpu)
+{
+	struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa);
+
+	if (root)
+		WRITE_ONCE(root->has_mapped_host_mmio, true);
+	else
+		WRITE_ONCE(vcpu->kvm->arch.has_mapped_host_mmio, true);
+
+	/*
+	 * Force vCPUs to exit and flush CPU buffers if the vCPU is using the
+	 * affected root(s).
+	 */
+	kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_OUTSIDE_GUEST_MODE);
+}
+
+/*
+ * Returns true if the SPTE needs to be updated atomically due to having bits
+ * that may be changed without holding mmu_lock, and for which KVM must not
+ * lose information.  E.g. KVM must not drop Dirty bit information.  The caller
+ * is responsible for checking if the SPTE is shadow-present, and for
+ * determining whether or not the caller cares about non-leaf SPTEs.
+ */
+bool spte_needs_atomic_update(u64 spte)
+{
+	/* SPTEs can be made Writable bit by KVM's fast page fault handler. */
+	if (!is_writable_pte(spte) && is_mmu_writable_spte(spte))
+		return true;
+
+	/*
+	 * A/D-disabled SPTEs can be access-tracked by aging, and access-tracked
+	 * SPTEs can be restored by KVM's fast page fault handler.
+	 */
+	if (!spte_ad_enabled(spte))
+		return true;
+
+	/*
+	 * Dirty and Accessed bits can be set by the CPU.  Ignore the Accessed
+	 * bit, as KVM tolerates false negatives/positives, e.g. KVM doesn't
+	 * invalidate TLBs when aging SPTEs, and so it's safe to clobber the
+	 * Accessed bit (and rare in practice).
+	 */
+	return is_writable_pte(spte) && !(spte & shadow_dirty_mask);
+}
+
+bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+	       const struct kvm_memory_slot *slot,
+	       unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn,
+	       u64 old_spte, bool prefetch, bool synchronizing,
+	       bool host_writable, u64 *new_spte)
+{
+	int level = sp->role.level;
+	u64 spte = SPTE_MMU_PRESENT_MASK;
+	int is_host_mmio = -1;
+	bool wrprot = false;
+
+	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(vcpu->kvm, sp))
+		spte |= SPTE_TDP_AD_WRPROT_ONLY;
+
+	spte |= shadow_present_mask;
+	if (!prefetch || synchronizing)
+		spte |= shadow_accessed_mask;
+
+	/*
+	 * For simplicity, enforce the NX huge page mitigation even if not
+	 * strictly necessary.  KVM could ignore the mitigation if paging is
+	 * disabled in the guest, as the guest doesn't have any page tables to
+	 * abuse.  But to safely ignore the mitigation, KVM would have to
+	 * ensure a new MMU is loaded (or all shadow pages zapped) when CR0.PG
+	 * is toggled on, and that's a net negative for performance when TDP is
+	 * enabled.  When TDP is disabled, KVM will always switch to a new MMU
+	 * when CR0.PG is toggled, but leveraging that to ignore the mitigation
+	 * would tie make_spte() further to vCPU/MMU state, and add complexity
+	 * just to optimize a mode that is anything but performance critical.
+	 */
+	if (level > PG_LEVEL_4K && is_nx_huge_page_enabled(vcpu->kvm)) {
+		pte_access &= ~ACC_EXEC_MASK;
+		if (shadow_xu_mask)
+			pte_access &= ~ACC_USER_EXEC_MASK;
+	}
+
+	if (pte_access & ACC_READ_MASK)
+		spte |= PT_PRESENT_MASK; /* or VMX_EPT_READABLE_MASK */
+
+	if (shadow_nx_mask) {
+		if (!(pte_access & ACC_EXEC_MASK))
+			spte |= shadow_nx_mask;
+		if (pte_access & ACC_USER_MASK)
+			spte |= shadow_user_mask;
+	} else {
+		if (pte_access & ACC_EXEC_MASK)
+			spte |= shadow_xs_mask;
+		if (pte_access & ACC_USER_EXEC_MASK)
+			spte |= shadow_xu_mask;
+	}
+
+	if (level > PG_LEVEL_4K)
+		spte |= PT_PAGE_SIZE_MASK;
+
+	if (kvm_x86_ops.get_mt_mask)
+		spte |= kvm_x86_call(get_mt_mask)(vcpu, gfn,
+						  kvm_is_mmio_pfn(pfn, &is_host_mmio));
+	if (host_writable)
+		spte |= shadow_host_writable_mask;
+	else
+		pte_access &= ~ACC_WRITE_MASK;
+
+	if (shadow_me_value && !kvm_is_mmio_pfn(pfn, &is_host_mmio))
+		spte |= shadow_me_value;
+
+	spte |= (u64)pfn << PAGE_SHIFT;
+
+	if (pte_access & ACC_WRITE_MASK) {
+		/*
+		 * Unsync shadow pages that are reachable by the new, writable
+		 * SPTE.  Write-protect the SPTE if the page can't be unsync'd,
+		 * e.g. it's write-tracked (upper-level SPs) or has one or more
+		 * shadow pages and unsync'ing pages is not allowed.
+		 *
+		 * When overwriting an existing leaf SPTE, and the old SPTE was
+		 * writable, skip trying to unsync shadow pages as any relevant
+		 * shadow pages must already be unsync, i.e. the hash lookup is
+		 * unnecessary (and expensive).  Note, this relies on KVM not
+		 * changing PFNs without first zapping the old SPTE, which is
+		 * guaranteed by both the shadow MMU and the TDP MMU.
+		 */
+		if ((!is_last_spte(old_spte, level) || !is_writable_pte(old_spte)) &&
+		    mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, synchronizing, prefetch))
+			wrprot = true;
+		else
+			spte |= PT_WRITABLE_MASK | shadow_mmu_writable_mask |
+				shadow_dirty_mask;
+	}
+
+	if (prefetch && !synchronizing)
+		spte = mark_spte_for_access_track(spte);
+
+	WARN_ONCE(is_rsvd_spte(&vcpu->arch.mmu->shadow_zero_check, spte, level),
+		  "spte = 0x%llx, level = %d, rsvd bits = 0x%llx", spte, level,
+		  get_rsvd_bits(&vcpu->arch.mmu->shadow_zero_check, spte, level));
+
+	/*
+	 * Mark the memslot dirty *after* modifying it for access tracking.
+	 * Unlike folios, memslots can be safely marked dirty out of mmu_lock,
+	 * i.e. in the fast page fault handler.
+	 */
+	if ((spte & PT_WRITABLE_MASK) && kvm_slot_dirty_track_enabled(slot)) {
+		/* Enforced by kvm_mmu_hugepage_adjust. */
+		WARN_ON_ONCE(level > PG_LEVEL_4K);
+		mark_page_dirty_in_slot(vcpu->kvm, slot, gfn);
+	}
+
+	if (cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF_VM_MMIO) &&
+	    !kvm_vcpu_can_access_host_mmio(vcpu) &&
+	    kvm_is_mmio_pfn(pfn, &is_host_mmio))
+		kvm_track_host_mmio_mapping(vcpu);
+
+	*new_spte = spte;
+	return wrprot;
+}
+
+static u64 modify_spte_protections(u64 spte, u64 set, u64 clear)
+{
+	bool is_access_track = is_access_track_spte(spte);
+
+	if (is_access_track)
+		spte = restore_acc_track_spte(spte);
+
+	KVM_MMU_WARN_ON(set & clear);
+	spte = (spte | set) & ~clear;
+
+	if (is_access_track)
+		spte = mark_spte_for_access_track(spte);
+
+	return spte;
+}
+
+static u64 change_spte_executable(u64 spte, u8 access)
+{
+	u64 set, clear;
+
+	if (shadow_nx_mask)
+		set = (access & ACC_EXEC_MASK) ? 0 : shadow_nx_mask;
+	else
+		set =
+			(access & ACC_EXEC_MASK ? shadow_xs_mask : 0) |
+			(access & ACC_USER_EXEC_MASK ? shadow_xu_mask : 0);
+	clear = set ^ (shadow_nx_mask | shadow_xs_mask | shadow_xu_mask);
+	return modify_spte_protections(spte, set, clear);
+}
+
+/*
+ * Construct an SPTE that maps a sub-page of the given huge page SPTE where
+ * `index` identifies which sub-page.
+ *
+ * This is used during huge page splitting to build the SPTEs that make up the
+ * new page table.
+ */
+u64 make_small_spte(struct kvm *kvm, u64 huge_spte,
+		    union kvm_mmu_page_role role, int index)
+{
+	u64 child_spte = huge_spte;
+
+	KVM_BUG_ON(!is_shadow_present_pte(huge_spte) || !is_large_pte(huge_spte), kvm);
+
+	/*
+	 * The child_spte already has the base address of the huge page being
+	 * split. So we just have to OR in the offset to the page at the next
+	 * lower level for the given index.
+	 */
+	child_spte |= (index * KVM_PAGES_PER_HPAGE(role.level)) << PAGE_SHIFT;
+
+	if (role.level == PG_LEVEL_4K) {
+		child_spte &= ~PT_PAGE_SIZE_MASK;
+
+		/*
+		 * When splitting to a 4K page where execution is allowed, mark
+		 * the page executable as the NX hugepage mitigation no longer
+		 * applies.
+		 */
+		if (is_nx_huge_page_enabled(kvm))
+			child_spte = change_spte_executable(child_spte, role.access);
+	}
+
+	return child_spte;
+}
+
+u64 make_huge_spte(struct kvm *kvm, u64 small_spte, int level)
+{
+	u64 huge_spte;
+
+	KVM_BUG_ON(!is_shadow_present_pte(small_spte) || level == PG_LEVEL_4K, kvm);
+
+	huge_spte = small_spte | PT_PAGE_SIZE_MASK;
+
+	/*
+	 * huge_spte already has the address of the sub-page being collapsed
+	 * from small_spte, so just clear the lower address bits to create the
+	 * huge page address.
+	 */
+	huge_spte &= KVM_HPAGE_MASK(level) | ~PAGE_MASK;
+
+	if (is_nx_huge_page_enabled(kvm))
+		huge_spte = change_spte_executable(huge_spte, 0);
+
+	return huge_spte;
+}
+
+u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled)
+{
+	u64 spte = SPTE_MMU_PRESENT_MASK;
+
+	spte |= __pa(child_pt) | shadow_present_mask | PT_WRITABLE_MASK |
+		PT_PRESENT_MASK /* or VMX_EPT_READABLE_MASK */ |
+		shadow_user_mask | shadow_xs_mask | shadow_xu_mask | shadow_me_value;
+
+	if (ad_disabled)
+		spte |= SPTE_TDP_AD_DISABLED;
+	else
+		spte |= shadow_accessed_mask;
+
+	return spte;
+}
+
+u64 mark_spte_for_access_track(u64 spte)
+{
+	if (spte_ad_enabled(spte))
+		return spte & ~shadow_accessed_mask;
+
+	if (is_access_track_spte(spte))
+		return spte;
+
+	check_spte_writable_invariants(spte);
+
+	WARN_ONCE(spte & (SHADOW_ACC_TRACK_SAVED_BITS_MASK <<
+			  SHADOW_ACC_TRACK_SAVED_BITS_SHIFT),
+		  "Access Tracking saved bit locations are not zero\n");
+
+	spte |= (spte & SHADOW_ACC_TRACK_SAVED_BITS_MASK) <<
+		SHADOW_ACC_TRACK_SAVED_BITS_SHIFT;
+	spte &= ~(shadow_acc_track_mask | shadow_accessed_mask);
+
+	return spte;
+}
+
+void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask)
+{
+	BUG_ON((u64)(unsigned)access_mask != access_mask);
+	WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);
+
+	/*
+	 * Reset to the original module param value to honor userspace's desire
+	 * to (dis)allow MMIO caching.  Update the param itself so that
+	 * userspace can see whether or not KVM is actually using MMIO caching.
+	 */
+	enable_mmio_caching = allow_mmio_caching;
+	if (!enable_mmio_caching)
+		mmio_value = 0;
+
+	/*
+	 * The mask must contain only bits that are carved out specifically for
+	 * the MMIO SPTE mask, e.g. to ensure there's no overlap with the MMIO
+	 * generation.
+	 */
+	if (WARN_ON(mmio_mask & ~SPTE_MMIO_ALLOWED_MASK))
+		mmio_value = 0;
+
+	/*
+	 * Disable MMIO caching if the MMIO value collides with the bits that
+	 * are used to hold the relocated GFN when the L1TF mitigation is
+	 * enabled.  This should never fire as there is no known hardware that
+	 * can trigger this condition, e.g. SME/SEV CPUs that require a custom
+	 * MMIO value are not susceptible to L1TF.
+	 */
+	if (WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask <<
+				  SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)))
+		mmio_value = 0;
+
+	/*
+	 * The masked MMIO value must obviously match itself and a frozen SPTE
+	 * must not get a false positive.  Frozen SPTEs and MMIO SPTEs should
+	 * never collide as MMIO must set some RWX bits, and frozen SPTEs must
+	 * not set any RWX bits.
+	 */
+	if (WARN_ON((mmio_value & mmio_mask) != mmio_value) ||
+	    WARN_ON(mmio_value && (FROZEN_SPTE & mmio_mask) == mmio_value))
+		mmio_value = 0;
+
+	if (!mmio_value)
+		enable_mmio_caching = false;
+
+	shadow_mmio_value = mmio_value;
+	shadow_mmio_mask  = mmio_mask;
+	shadow_mmio_access_mask = access_mask;
+}
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_set_mmio_spte_mask);
+
+void kvm_mmu_set_mmio_spte_value(struct kvm *kvm, u64 mmio_value)
+{
+	kvm->arch.shadow_mmio_value = mmio_value;
+}
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_set_mmio_spte_value);
+
+void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask)
+{
+	/* shadow_me_value must be a subset of shadow_me_mask */
+	if (WARN_ON(me_value & ~me_mask))
+		me_value = me_mask = 0;
+
+	shadow_me_value = me_value;
+	shadow_me_mask = me_mask;
+}
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_set_me_spte_mask);
+
+void kvm_mmu_set_ept_masks(bool has_ad_bits)
+{
+	kvm_ad_enabled		= has_ad_bits;
+
+	shadow_user_mask	= 0;
+	shadow_accessed_mask	= VMX_EPT_ACCESS_BIT;
+	shadow_dirty_mask	= VMX_EPT_DIRTY_BIT;
+	shadow_nx_mask		= 0ull;
+	shadow_xs_mask		= VMX_EPT_EXECUTABLE_MASK;
+
+	/*
+	 * The MMU always maps ACC_EXEC_MASK and ACC_USER_EXEC_MASK to the
+	 * XS and XU bits of shadow EPT entries, regardless of whether MBEC
+	 * is available on the host or enabled in the VMCS.
+	 *
+	 * For the non-nested case, pages are mapped with ACC_EXEC_MASK
+	 * and ACC_USER_EXEC_MASK set in tandem, so XS == XU and the
+	 * host's MBEC setting does not matter.  On hardware without MBEC
+	 * the XU bit is reserved-as-ignored, and setting it does no harm.
+	 *
+	 * For nested EPT, when MBEC is disabled by L1, correctness relies
+	 * on (a) ignoring bit 10 of the gPTE in is_present_gpte(), rather
+	 * than treating it as a present bit, and (b) permission_fault()
+	 * using an mmu->permissions[] array that effectively ignores
+	 * ACC_USER_EXEC_MASK.  Bit 10 of the gPTE does end up mirrored
+	 * in the sPTEs but is ignored because L2 runs with MBEC disabled.
+	 */
+	shadow_xu_mask		= VMX_EPT_USER_EXECUTABLE_MASK;
+	shadow_present_mask	= VMX_EPT_SUPPRESS_VE_BIT;
+
+	shadow_acc_track_mask	= VMX_EPT_RWX_MASK | VMX_EPT_USER_EXECUTABLE_MASK;
+	shadow_host_writable_mask = EPT_SPTE_HOST_WRITABLE;
+	shadow_mmu_writable_mask  = EPT_SPTE_MMU_WRITABLE;
+
+	/*
+	 * EPT Misconfigurations are generated if the value of bits 2:0
+	 * 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 | VMX_EPT_SUPPRESS_VE_BIT, 0);
+}
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_set_ept_masks);
+
+void kvm_mmu_reset_all_pte_masks(void)
+{
+	u8 low_phys_bits;
+	u64 mask;
+
+	kvm_ad_enabled = true;
+
+	/*
+	 * If the CPU has 46 or less physical address bits, then set an
+	 * appropriate mask to guard against L1TF attacks. Otherwise, it is
+	 * assumed that the CPU is not vulnerable to L1TF.
+	 *
+	 * Some Intel CPUs address the L1 cache using more PA bits than are
+	 * reported by CPUID. Use the PA width of the L1 cache when possible
+	 * to achieve more effective mitigation, e.g. if system RAM overlaps
+	 * the most significant bits of legal physical address space.
+	 */
+	shadow_nonpresent_or_rsvd_mask = 0;
+	low_phys_bits = boot_cpu_data.x86_phys_bits;
+	if (boot_cpu_has_bug(X86_BUG_L1TF) &&
+	    !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >=
+			  52 - SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)) {
+		low_phys_bits = boot_cpu_data.x86_cache_bits
+			- SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
+		shadow_nonpresent_or_rsvd_mask =
+			rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1);
+	}
+
+	shadow_nonpresent_or_rsvd_lower_gfn_mask =
+		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
+
+	shadow_user_mask	= PT_USER_MASK;
+	shadow_accessed_mask	= PT_ACCESSED_MASK;
+	shadow_dirty_mask	= PT_DIRTY_MASK;
+	shadow_nx_mask		= PT64_NX_MASK;
+	shadow_xs_mask		= 0;
+	shadow_xu_mask		= 0;
+	shadow_present_mask	= PT_PRESENT_MASK;
+
+	shadow_acc_track_mask	= 0;
+	shadow_me_mask		= 0;
+	shadow_me_value		= 0;
+
+	shadow_host_writable_mask = DEFAULT_SPTE_HOST_WRITABLE;
+	shadow_mmu_writable_mask  = DEFAULT_SPTE_MMU_WRITABLE;
+
+	/*
+	 * Set a reserved PA bit in MMIO SPTEs to generate page faults with
+	 * PFEC.RSVD=1 on MMIO accesses.  64-bit PTEs (PAE, x86-64, and EPT
+	 * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports
+	 * 52-bit physical addresses then there are no reserved PA bits in the
+	 * PTEs and so the reserved PA approach must be disabled.
+	 */
+	if (kvm_host.maxphyaddr < 52)
+		mask = BIT_ULL(51) | PT_PRESENT_MASK;
+	else
+		mask = 0;
+
+	kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);
+}

linux-7.2.3/arch/x86/kvm/mmu/spte.h

@@ -0,0 +1,582 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#ifndef KVM_X86_MMU_SPTE_H
+#define KVM_X86_MMU_SPTE_H
+
+#include <asm/vmx.h>
+
+#include "mmu.h"
+#include "mmu_internal.h"
+
+/*
+ * A MMU present SPTE is backed by actual memory and may or may not be present
+ * in hardware.  E.g. MMIO SPTEs are not considered present.  Use bit 11, as it
+ * is ignored by all flavors of SPTEs and checking a low bit often generates
+ * better code than for a high bit, e.g. 56+.  MMU present checks are pervasive
+ * enough that the improved code generation is noticeable in KVM's footprint.
+ */
+#define SPTE_MMU_PRESENT_MASK		BIT_ULL(11)
+
+/*
+ * The ignored high bits are allocated as follows:
+ * - bits 52, 54: saved X-R bits for access tracking when EPT does not have A/D
+ * - bits 53 (EPT only): host writable
+ * - bits 55 (EPT only): MMU-writable
+ * - bits 56-59: unused
+ * - bits 60-61: type of A/D tracking
+ * - bits 62 (EPT only): saved XU bit for disabled AD
+ */
+
+/*
+ * TDP SPTES (more specifically, EPT SPTEs) may not have A/D bits, and may also
+ * be restricted to using write-protection (for L2 when CPU dirty logging, i.e.
+ * PML, is enabled).  Use bits 60 and 61 to hold the type of A/D tracking that
+ * is must be employed for a given TDP SPTE.
+ *
+ * Note, the "enabled" mask must be '0', as bits 62:52 are _reserved_ for PAE
+ * paging, including NPT PAE.  This scheme works because legacy shadow paging
+ * is guaranteed to have A/D bits and write-protection is forced only for
+ * TDP with CPU dirty logging (PML).  If NPT ever gains PML-like support, it
+ * must be restricted to 64-bit KVM.
+ */
+#define SPTE_TDP_AD_SHIFT		60
+#define SPTE_TDP_AD_MASK		(3ULL << SPTE_TDP_AD_SHIFT)
+#define SPTE_TDP_AD_ENABLED		(0ULL << SPTE_TDP_AD_SHIFT)
+#define SPTE_TDP_AD_DISABLED		(1ULL << SPTE_TDP_AD_SHIFT)
+#define SPTE_TDP_AD_WRPROT_ONLY		(2ULL << SPTE_TDP_AD_SHIFT)
+static_assert(SPTE_TDP_AD_ENABLED == 0);
+
+#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
+#define SPTE_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1))
+#else
+#define SPTE_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#endif
+
+#define SPTE_LEVEL_BITS			9
+#define SPTE_LEVEL_SHIFT(level)		__PT_LEVEL_SHIFT(level, SPTE_LEVEL_BITS)
+#define SPTE_INDEX(address, level)	__PT_INDEX(address, level, SPTE_LEVEL_BITS)
+#define SPTE_ENT_PER_PAGE		__PT_ENT_PER_PAGE(SPTE_LEVEL_BITS)
+
+/*
+ * The mask/shift to use for saving the original R/X bits when marking the PTE
+ * as not-present for access tracking purposes. We do not save the W bit as the
+ * PTEs being access tracked also need to be dirty tracked, so the W bit will be
+ * restored only when a write is attempted to the page.  This mask obviously
+ * must not overlap the A/D type mask.
+ */
+#define SHADOW_ACC_TRACK_SAVED_BITS_MASK (VMX_EPT_READABLE_MASK | \
+					  VMX_EPT_EXECUTABLE_MASK | \
+					  VMX_EPT_USER_EXECUTABLE_MASK)
+#define SHADOW_ACC_TRACK_SAVED_BITS_SHIFT 52
+#define SHADOW_ACC_TRACK_SAVED_MASK	(SHADOW_ACC_TRACK_SAVED_BITS_MASK << \
+					 SHADOW_ACC_TRACK_SAVED_BITS_SHIFT)
+static_assert(!(SPTE_TDP_AD_MASK & SHADOW_ACC_TRACK_SAVED_MASK));
+
+/*
+ * {DEFAULT,EPT}_SPTE_{HOST,MMU}_WRITABLE are used to keep track of why a given
+ * SPTE is write-protected. See is_writable_pte() for details.
+ */
+
+/* Bits 9 and 10 are ignored by all non-EPT PTEs. */
+#define DEFAULT_SPTE_HOST_WRITABLE	BIT_ULL(9)
+#define DEFAULT_SPTE_MMU_WRITABLE	BIT_ULL(10)
+
+/*
+ * Low ignored bits are at a premium for EPT, use high ignored bits, taking care
+ * to not overlap the A/D type mask or the saved access bits of access-tracked
+ * SPTEs when A/D bits are disabled.
+ */
+#define EPT_SPTE_HOST_WRITABLE		BIT_ULL(53)
+#define EPT_SPTE_MMU_WRITABLE		BIT_ULL(55)
+
+static_assert(!(EPT_SPTE_HOST_WRITABLE & SPTE_TDP_AD_MASK));
+static_assert(!(EPT_SPTE_MMU_WRITABLE & SPTE_TDP_AD_MASK));
+static_assert(!(EPT_SPTE_HOST_WRITABLE & SHADOW_ACC_TRACK_SAVED_MASK));
+static_assert(!(EPT_SPTE_MMU_WRITABLE & SHADOW_ACC_TRACK_SAVED_MASK));
+
+/* Defined only to keep the above static asserts readable. */
+#undef SHADOW_ACC_TRACK_SAVED_MASK
+
+/*
+ * Due to limited space in PTEs, the MMIO generation is an 18 bit subset of
+ * the memslots generation and is derived as follows:
+ *
+ * Bits 0-6 of the MMIO generation are propagated to spte bits 3-9
+ * Bits 7-17 of the MMIO generation are propagated to spte bits 52-62
+ *
+ * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in
+ * the MMIO generation number, as doing so would require stealing a bit from
+ * the "real" generation number and thus effectively halve the maximum number
+ * of MMIO generations that can be handled before encountering a wrap (which
+ * requires a full MMU zap).  The flag is instead explicitly queried when
+ * checking for MMIO spte cache hits.
+ */
+
+#define MMIO_SPTE_GEN_LOW_START		3
+#define MMIO_SPTE_GEN_LOW_END		9
+
+#define MMIO_SPTE_GEN_HIGH_START	52
+#define MMIO_SPTE_GEN_HIGH_END		62
+
+#define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
+						    MMIO_SPTE_GEN_LOW_START)
+#define MMIO_SPTE_GEN_HIGH_MASK		GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \
+						    MMIO_SPTE_GEN_HIGH_START)
+static_assert(!(SPTE_MMU_PRESENT_MASK &
+		(MMIO_SPTE_GEN_LOW_MASK | MMIO_SPTE_GEN_HIGH_MASK)));
+
+/*
+ * The SPTE MMIO mask must NOT overlap the MMIO generation bits or the
+ * MMU-present bit.  The generation obviously co-exists with the magic MMIO
+ * mask/value, and MMIO SPTEs are considered !MMU-present.
+ *
+ * The SPTE MMIO mask is allowed to use hardware "present" bits (i.e. all EPT
+ * RWX bits), all physical address bits (legal PA bits are used for "fast" MMIO
+ * and so they're off-limits for generation; additional checks ensure the mask
+ * doesn't overlap legal PA bits), and bit 63 (carved out for future usage).
+ */
+#define SPTE_MMIO_ALLOWED_MASK (BIT_ULL(63) | GENMASK_ULL(51, 12) | \
+				BIT_ULL(10) | GENMASK_ULL(2, 0))
+static_assert(!(SPTE_MMIO_ALLOWED_MASK &
+		(SPTE_MMU_PRESENT_MASK | MMIO_SPTE_GEN_LOW_MASK | MMIO_SPTE_GEN_HIGH_MASK)));
+
+#define MMIO_SPTE_GEN_LOW_BITS		(MMIO_SPTE_GEN_LOW_END - MMIO_SPTE_GEN_LOW_START + 1)
+#define MMIO_SPTE_GEN_HIGH_BITS		(MMIO_SPTE_GEN_HIGH_END - MMIO_SPTE_GEN_HIGH_START + 1)
+
+/* remember to adjust the comment above as well if you change these */
+static_assert(MMIO_SPTE_GEN_LOW_BITS == 7 && MMIO_SPTE_GEN_HIGH_BITS == 11);
+
+#define MMIO_SPTE_GEN_LOW_SHIFT		(MMIO_SPTE_GEN_LOW_START - 0)
+#define MMIO_SPTE_GEN_HIGH_SHIFT	(MMIO_SPTE_GEN_HIGH_START - MMIO_SPTE_GEN_LOW_BITS)
+
+#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
+
+
+/*
+ * True if A/D bits are supported in hardware and are enabled by KVM.  When
+ * enabled, KVM uses A/D bits for all non-nested MMUs.  Because L1 can disable
+ * A/D bits in EPTP12, SP and SPTE variants are needed to handle the scenario
+ * where KVM is using A/D bits for L1, but not L2.
+ */
+extern bool __read_mostly kvm_ad_enabled;
+
+extern u64 __read_mostly shadow_host_writable_mask;
+extern u64 __read_mostly shadow_mmu_writable_mask;
+extern u64 __read_mostly shadow_nx_mask;
+extern u64 __read_mostly shadow_user_mask;
+extern u64 __read_mostly shadow_xs_mask; /* mutual exclusive with nx_mask and user_mask */
+extern u64 __read_mostly shadow_xu_mask; /* mutual exclusive with nx_mask and user_mask */
+extern u64 __read_mostly shadow_accessed_mask;
+extern u64 __read_mostly shadow_dirty_mask;
+extern u64 __read_mostly shadow_mmio_value;
+extern u64 __read_mostly shadow_mmio_mask;
+extern u64 __read_mostly shadow_mmio_access_mask;
+extern u64 __read_mostly shadow_present_mask;
+extern u64 __read_mostly shadow_me_value;
+extern u64 __read_mostly shadow_me_mask;
+
+/*
+ * SPTEs in MMUs without A/D bits are marked with SPTE_TDP_AD_DISABLED;
+ * shadow_acc_track_mask is the set of bits to be cleared in non-accessed
+ * pages.
+ */
+extern u64 __read_mostly shadow_acc_track_mask;
+
+/*
+ * This mask must be set on all non-zero Non-Present or Reserved SPTEs in order
+ * to guard against L1TF attacks.
+ */
+extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
+
+/*
+ * The number of high-order 1 bits to use in the mask above.
+ */
+#define SHADOW_NONPRESENT_OR_RSVD_MASK_LEN 5
+
+/*
+ * If a thread running without exclusive control of the MMU lock must perform a
+ * multi-part operation on an SPTE, it can set the SPTE to FROZEN_SPTE as a
+ * non-present intermediate value. Other threads which encounter this value
+ * should not modify the SPTE.
+ *
+ * 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.
+ *
+ * Only used by the TDP MMU.
+ */
+#define FROZEN_SPTE	(SHADOW_NONPRESENT_VALUE | 0x1a0ULL)
+
+/* Frozen SPTEs must not be misconstrued as shadow or MMU present PTEs. */
+static_assert(!(FROZEN_SPTE & (SPTE_MMU_PRESENT_MASK |
+			       VMX_EPT_RWX_MASK | VMX_EPT_USER_EXECUTABLE_MASK)));
+
+static inline bool is_frozen_spte(u64 spte)
+{
+	return spte == FROZEN_SPTE;
+}
+
+/* Get an SPTE's index into its parent's page table (and the spt array). */
+static inline int spte_index(u64 *sptep)
+{
+	return ((unsigned long)sptep / sizeof(*sptep)) & (SPTE_ENT_PER_PAGE - 1);
+}
+
+/*
+ * In some cases, we need to preserve the GFN of a non-present or reserved
+ * SPTE when we usurp the upper five bits of the physical address space to
+ * defend against L1TF, e.g. for MMIO SPTEs.  To preserve the GFN, we'll
+ * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask
+ * left into the reserved bits, i.e. the GFN in the SPTE will be split into
+ * high and low parts.  This mask covers the lower bits of the GFN.
+ */
+extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
+
+static inline hpa_t kvm_mmu_get_dummy_root(void)
+{
+	return zero_pfn(0) << PAGE_SHIFT;
+}
+
+static inline bool kvm_mmu_is_dummy_root(hpa_t shadow_page)
+{
+	return is_zero_pfn(shadow_page >> PAGE_SHIFT);
+}
+
+static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page)
+{
+	struct page *page = pfn_to_page((shadow_page) >> PAGE_SHIFT);
+
+	return (struct kvm_mmu_page *)page_private(page);
+}
+
+static inline struct kvm_mmu_page *spte_to_child_sp(u64 spte)
+{
+	return to_shadow_page(spte & SPTE_BASE_ADDR_MASK);
+}
+
+static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
+{
+	return to_shadow_page(__pa(sptep));
+}
+
+static inline struct kvm_mmu_page *root_to_sp(hpa_t root)
+{
+	if (kvm_mmu_is_dummy_root(root))
+		return NULL;
+
+	/*
+	 * The "root" may be a special root, e.g. a PAE entry, treat it as a
+	 * SPTE to ensure any non-PA bits are dropped.
+	 */
+	return spte_to_child_sp(root);
+}
+
+static inline bool is_mirror_sptep(tdp_ptep_t sptep)
+{
+	return is_mirror_sp(sptep_to_sp(rcu_dereference(sptep)));
+}
+
+static inline bool kvm_vcpu_can_access_host_mmio(struct kvm_vcpu *vcpu)
+{
+	struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa);
+
+	if (root)
+		return READ_ONCE(root->has_mapped_host_mmio);
+
+	return READ_ONCE(vcpu->kvm->arch.has_mapped_host_mmio);
+}
+
+static inline bool is_mmio_spte(struct kvm *kvm, u64 spte)
+{
+	return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value &&
+	       likely(enable_mmio_caching);
+}
+
+static inline bool is_shadow_present_pte(u64 pte)
+{
+	return !!(pte & SPTE_MMU_PRESENT_MASK);
+}
+
+static inline bool is_ept_ve_possible(u64 spte)
+{
+	return (shadow_present_mask & VMX_EPT_SUPPRESS_VE_BIT) &&
+	       !(spte & VMX_EPT_SUPPRESS_VE_BIT) &&
+	       (spte & VMX_EPT_RWX_MASK) != VMX_EPT_MISCONFIG_WX_VALUE;
+}
+
+static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
+{
+	return sp->role.ad_disabled;
+}
+
+static inline bool spte_ad_enabled(u64 spte)
+{
+	KVM_MMU_WARN_ON(!is_shadow_present_pte(spte));
+	return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED;
+}
+
+static inline bool spte_ad_need_write_protect(u64 spte)
+{
+	KVM_MMU_WARN_ON(!is_shadow_present_pte(spte));
+	/*
+	 * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED is '0',
+	 * and non-TDP SPTEs will never set these bits.  Optimize for 64-bit
+	 * TDP and do the A/D type check unconditionally.
+	 */
+	return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_ENABLED;
+}
+
+static inline bool is_access_track_spte(u64 spte)
+{
+	return !spte_ad_enabled(spte) && (spte & shadow_acc_track_mask) == 0;
+}
+
+static inline bool is_large_pte(u64 pte)
+{
+	return pte & PT_PAGE_SIZE_MASK;
+}
+
+static inline bool is_last_spte(u64 pte, int level)
+{
+	return (level == PG_LEVEL_4K) || is_large_pte(pte);
+}
+
+static inline bool is_executable_pte(u64 spte)
+{
+	/*
+	 * For now, return true if either the XS or XU bit is set
+	 * This function is only used for fast_page_fault,
+	 * which never processes shadow EPT, and regular page
+	 * tables always have XS==XU.
+	 */
+	return (spte & (shadow_xs_mask | shadow_xu_mask | shadow_nx_mask)) != shadow_nx_mask;
+}
+
+static inline kvm_pfn_t spte_to_pfn(u64 pte)
+{
+	return (pte & SPTE_BASE_ADDR_MASK) >> PAGE_SHIFT;
+}
+
+static inline bool is_accessed_spte(u64 spte)
+{
+	return spte & shadow_accessed_mask;
+}
+
+static inline u64 get_rsvd_bits(struct rsvd_bits_validate *rsvd_check, u64 pte,
+				int level)
+{
+	int bit7 = (pte >> 7) & 1;
+
+	return rsvd_check->rsvd_bits_mask[bit7][level-1];
+}
+
+static inline bool __is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check,
+				      u64 pte, int level)
+{
+	return pte & get_rsvd_bits(rsvd_check, pte, level);
+}
+
+static inline bool __is_bad_mt_xwr(struct rsvd_bits_validate *rsvd_check,
+				   u64 pte)
+{
+	if (pte & VMX_EPT_USER_EXECUTABLE_MASK)
+		pte |= VMX_EPT_EXECUTABLE_MASK;
+	return rsvd_check->bad_mt_xwr & BIT_ULL(pte & 0x3f);
+}
+
+static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check,
+					 u64 spte, int level)
+{
+	return __is_bad_mt_xwr(rsvd_check, spte) ||
+	       __is_rsvd_bits_set(rsvd_check, spte, level);
+}
+
+/*
+ * A shadow-present leaf SPTE may be non-writable for 4 possible reasons:
+ *
+ *  1. To intercept writes for dirty logging. KVM write-protects huge pages
+ *     so that they can be split down into the dirty logging
+ *     granularity (4KiB) whenever the guest writes to them. KVM also
+ *     write-protects 4KiB pages so that writes can be recorded in the dirty log
+ *     (e.g. if not using PML). SPTEs are write-protected for dirty logging
+ *     during the VM-iotcls that enable dirty logging.
+ *
+ *  2. To intercept writes to guest page tables that KVM is shadowing. When a
+ *     guest writes to its page table the corresponding shadow page table will
+ *     be marked "unsync". That way KVM knows which shadow page tables need to
+ *     be updated on the next TLB flush, INVLPG, etc. and which do not.
+ *
+ *  3. To prevent guest writes to read-only memory, such as for memory in a
+ *     read-only memslot or guest memory backed by a read-only VMA. Writes to
+ *     such pages are disallowed entirely.
+ *
+ *  4. To emulate the Accessed bit for SPTEs without A/D bits.  Note, in this
+ *     case, the SPTE is access-protected, not just write-protected!
+ *
+ * For cases #1 and #4, KVM can safely make such SPTEs writable without taking
+ * mmu_lock as capturing the Accessed/Dirty state doesn't require taking it.
+ * To differentiate #1 and #4 from #2 and #3, KVM uses two software-only bits
+ * in the SPTE:
+ *
+ *  shadow_mmu_writable_mask, aka MMU-writable -
+ *    Cleared on SPTEs that KVM is currently write-protecting for shadow paging
+ *    purposes (case 2 above).
+ *
+ *  shadow_host_writable_mask, aka Host-writable -
+ *    Cleared on SPTEs that are not host-writable (case 3 above)
+ *
+ * Note, not all possible combinations of PT_WRITABLE_MASK,
+ * shadow_mmu_writable_mask, and shadow_host_writable_mask are valid. A given
+ * SPTE can be in only one of the following states, which map to the
+ * aforementioned 3 cases:
+ *
+ *   shadow_host_writable_mask | shadow_mmu_writable_mask | PT_WRITABLE_MASK
+ *   ------------------------- | ------------------------ | ----------------
+ *   1                         | 1                        | 1       (writable)
+ *   1                         | 1                        | 0       (case 1)
+ *   1                         | 0                        | 0       (case 2)
+ *   0                         | 0                        | 0       (case 3)
+ *
+ * The valid combinations of these bits are checked by
+ * check_spte_writable_invariants() whenever an SPTE is modified.
+ *
+ * Clearing the MMU-writable bit is always done under the MMU lock and always
+ * accompanied by a TLB flush before dropping the lock to avoid corrupting the
+ * shadow page tables between vCPUs. Write-protecting an SPTE for dirty logging
+ * (which does not clear the MMU-writable bit), does not flush TLBs before
+ * dropping the lock, as it only needs to synchronize guest writes with the
+ * dirty bitmap. Similarly, making the SPTE inaccessible (and non-writable) for
+ * access-tracking via the clear_young() MMU notifier also does not flush TLBs.
+ *
+ * So, there is the problem: clearing the MMU-writable bit can encounter a
+ * write-protected SPTE while CPUs still have writable mappings for that SPTE
+ * cached in their TLB. To address this, KVM always flushes TLBs when
+ * write-protecting SPTEs if the MMU-writable bit is set on the old SPTE.
+ *
+ * The Host-writable bit is not modified on present SPTEs, it is only set or
+ * cleared when an SPTE is first faulted in from non-present and then remains
+ * immutable.
+ */
+static inline bool is_writable_pte(unsigned long pte)
+{
+	return pte & PT_WRITABLE_MASK;
+}
+
+/* Note: spte must be a shadow-present leaf SPTE. */
+static inline void check_spte_writable_invariants(u64 spte)
+{
+	if (spte & shadow_mmu_writable_mask)
+		WARN_ONCE(!(spte & shadow_host_writable_mask),
+			  KBUILD_MODNAME ": MMU-writable SPTE is not Host-writable: %llx",
+			  spte);
+	else
+		WARN_ONCE(is_writable_pte(spte),
+			  KBUILD_MODNAME ": Writable SPTE is not MMU-writable: %llx", spte);
+}
+
+static inline bool is_mmu_writable_spte(u64 spte)
+{
+	return spte & shadow_mmu_writable_mask;
+}
+
+/*
+ * Returns true if the access indicated by @fault is allowed by the existing
+ * SPTE protections.  Note, the caller is responsible for checking that the
+ * SPTE is a shadow-present, leaf SPTE (either before or after).
+ */
+static inline bool is_access_allowed(struct kvm_page_fault *fault, u64 spte)
+{
+	if (fault->exec)
+		return is_executable_pte(spte);
+
+	if (fault->write)
+		return is_writable_pte(spte);
+
+	/* Fault was on Read access */
+	return spte & PT_PRESENT_MASK;
+}
+
+/*
+ * If the MMU-writable flag is cleared, i.e. the SPTE is write-protected for
+ * write-tracking, remote TLBs must be flushed, even if the SPTE was read-only,
+ * as KVM allows stale Writable TLB entries to exist.  When dirty logging, KVM
+ * flushes TLBs based on whether or not dirty bitmap/ring entries were reaped,
+ * not whether or not SPTEs were modified, i.e. only the write-tracking case
+ * needs to flush at the time the SPTEs is modified, before dropping mmu_lock.
+ *
+ * Don't flush if the Accessed bit is cleared, as access tracking tolerates
+ * false negatives, e.g. KVM x86 omits TLB flushes even when aging SPTEs for a
+ * mmu_notifier.clear_flush_young() event.
+ *
+ * Lastly, don't flush if the Dirty bit is cleared, as KVM unconditionally
+ * flushes when enabling dirty logging (see kvm_mmu_slot_apply_flags()), and
+ * when clearing dirty logs, KVM flushes based on whether or not dirty entries
+ * were reaped from the bitmap/ring, not whether or not dirty SPTEs were found.
+ *
+ * Note, this logic only applies to shadow-present leaf SPTEs.  The caller is
+ * responsible for checking that the old SPTE is shadow-present, and is also
+ * responsible for determining whether or not a TLB flush is required when
+ * modifying a shadow-present non-leaf SPTE.
+ */
+static inline bool leaf_spte_change_needs_tlb_flush(u64 old_spte, u64 new_spte)
+{
+	return is_mmu_writable_spte(old_spte) && !is_mmu_writable_spte(new_spte);
+}
+
+static inline u64 get_mmio_spte_generation(u64 spte)
+{
+	u64 gen;
+
+	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_SHIFT;
+	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_SHIFT;
+	return gen;
+}
+
+bool spte_needs_atomic_update(u64 spte);
+
+bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+	       const struct kvm_memory_slot *slot,
+	       unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn,
+	       u64 old_spte, bool prefetch, bool synchronizing,
+	       bool host_writable, u64 *new_spte);
+u64 make_small_spte(struct kvm *kvm, u64 huge_spte,
+		    union kvm_mmu_page_role role, int index);
+u64 make_huge_spte(struct kvm *kvm, u64 small_spte, int level);
+u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled);
+u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access);
+u64 mark_spte_for_access_track(u64 spte);
+
+/* Restore an acc-track PTE back to a regular PTE */
+static inline u64 restore_acc_track_spte(u64 spte)
+{
+	u64 saved_bits = (spte >> SHADOW_ACC_TRACK_SAVED_BITS_SHIFT)
+			 & SHADOW_ACC_TRACK_SAVED_BITS_MASK;
+
+	spte &= ~shadow_acc_track_mask;
+	spte &= ~(SHADOW_ACC_TRACK_SAVED_BITS_MASK <<
+		  SHADOW_ACC_TRACK_SAVED_BITS_SHIFT);
+	spte |= saved_bits;
+
+	return spte;
+}
+
+void __init kvm_mmu_spte_module_init(void);
+void kvm_mmu_reset_all_pte_masks(void);
+
+#endif

linux-7.2.3/arch/x86/kvm/mmu/tdp_iter.c

@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include "mmu_internal.h"
+#include "tdp_iter.h"
+#include "spte.h"
+
+/*
+ * Recalculates the pointer to the SPTE for the current GFN and level and
+ * reread the SPTE.
+ */
+static void tdp_iter_refresh_sptep(struct tdp_iter *iter)
+{
+	iter->sptep = iter->pt_path[iter->level - 1] +
+		SPTE_INDEX((iter->gfn | iter->gfn_bits) << PAGE_SHIFT, iter->level);
+	iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
+}
+
+/*
+ * Return the TDP iterator to the root PT and allow it to continue its
+ * traversal over the paging structure from there.
+ */
+void tdp_iter_restart(struct tdp_iter *iter)
+{
+	iter->yielded = false;
+	iter->yielded_gfn = iter->next_last_level_gfn;
+	iter->level = iter->root_level;
+
+	iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level);
+	tdp_iter_refresh_sptep(iter);
+
+	iter->valid = true;
+}
+
+/*
+ * Sets a TDP iterator to walk a pre-order traversal of the paging structure
+ * rooted at root_pt, starting with the walk to translate next_last_level_gfn.
+ */
+void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root,
+		    int min_level, gfn_t next_last_level_gfn, gfn_t gfn_bits)
+{
+	if (WARN_ON_ONCE(!root || (root->role.level < 1) ||
+			 (root->role.level > PT64_ROOT_MAX_LEVEL) ||
+			 (gfn_bits && next_last_level_gfn >= gfn_bits))) {
+		iter->valid = false;
+		return;
+	}
+
+	iter->next_last_level_gfn = next_last_level_gfn;
+	iter->gfn_bits = gfn_bits;
+	iter->root_level = root->role.level;
+	iter->min_level = min_level;
+	iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root->spt;
+	iter->as_id = kvm_mmu_page_as_id(root);
+
+	tdp_iter_restart(iter);
+}
+
+/*
+ * Given an SPTE and its level, returns a pointer containing the host virtual
+ * address of the child page table referenced by the SPTE. Returns null if
+ * there is no such entry.
+ */
+tdp_ptep_t spte_to_child_pt(u64 spte, int level)
+{
+	/*
+	 * There's no child entry if this entry isn't present or is a
+	 * last-level entry.
+	 */
+	if (!is_shadow_present_pte(spte) || is_last_spte(spte, level))
+		return NULL;
+
+	return (tdp_ptep_t)__va(spte_to_pfn(spte) << PAGE_SHIFT);
+}
+
+/*
+ * Steps down one level in the paging structure towards the goal GFN. Returns
+ * true if the iterator was able to step down a level, false otherwise.
+ */
+static bool try_step_down(struct tdp_iter *iter)
+{
+	tdp_ptep_t child_pt;
+
+	if (iter->level == iter->min_level)
+		return false;
+
+	/*
+	 * Reread the SPTE before stepping down to avoid traversing into page
+	 * tables that are no longer linked from this entry.
+	 */
+	iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
+
+	child_pt = spte_to_child_pt(iter->old_spte, iter->level);
+	if (!child_pt)
+		return false;
+
+	iter->level--;
+	iter->pt_path[iter->level - 1] = child_pt;
+	iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level);
+	tdp_iter_refresh_sptep(iter);
+
+	return true;
+}
+
+/*
+ * Steps to the next entry in the current page table, at the current page table
+ * level. The next entry could point to a page backing guest memory or another
+ * page table, or it could be non-present. Returns true if the iterator was
+ * able to step to the next entry in the page table, false if the iterator was
+ * already at the end of the current page table.
+ */
+static bool try_step_side(struct tdp_iter *iter)
+{
+	/*
+	 * Check if the iterator is already at the end of the current page
+	 * table.
+	 */
+	if (SPTE_INDEX((iter->gfn | iter->gfn_bits) << PAGE_SHIFT, iter->level) ==
+	    (SPTE_ENT_PER_PAGE - 1))
+		return false;
+
+	iter->gfn += KVM_PAGES_PER_HPAGE(iter->level);
+	iter->next_last_level_gfn = iter->gfn;
+	iter->sptep++;
+	iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
+
+	return true;
+}
+
+/*
+ * Tries to traverse back up a level in the paging structure so that the walk
+ * can continue from the next entry in the parent page table. Returns true on a
+ * successful step up, false if already in the root page.
+ */
+static bool try_step_up(struct tdp_iter *iter)
+{
+	if (iter->level == iter->root_level)
+		return false;
+
+	iter->level++;
+	iter->gfn = gfn_round_for_level(iter->gfn, iter->level);
+	tdp_iter_refresh_sptep(iter);
+
+	return true;
+}
+
+/*
+ * Step to the next SPTE in a pre-order traversal of the paging structure.
+ * To get to the next SPTE, the iterator either steps down towards the goal
+ * GFN, if at a present, non-last-level SPTE, or over to a SPTE mapping a
+ * higher GFN.
+ *
+ * The basic algorithm is as follows:
+ * 1. If the current SPTE is a non-last-level SPTE, step down into the page
+ *    table it points to.
+ * 2. If the iterator cannot step down, it will try to step to the next SPTE
+ *    in the current page of the paging structure.
+ * 3. If the iterator cannot step to the next entry in the current page, it will
+ *    try to step up to the parent paging structure page. In this case, that
+ *    SPTE will have already been visited, and so the iterator must also step
+ *    to the side again.
+ */
+void tdp_iter_next(struct tdp_iter *iter)
+{
+	if (iter->yielded) {
+		tdp_iter_restart(iter);
+		return;
+	}
+
+	if (try_step_down(iter))
+		return;
+
+	do {
+		if (try_step_side(iter))
+			return;
+	} while (try_step_up(iter));
+	iter->valid = false;
+}
+

linux-7.2.3/arch/x86/kvm/mmu/tdp_iter.h

@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef __KVM_X86_MMU_TDP_ITER_H
+#define __KVM_X86_MMU_TDP_ITER_H
+
+#include <linux/kvm_host.h>
+
+#include "mmu.h"
+#include "spte.h"
+
+/*
+ * TDP MMU SPTEs are RCU protected to allow paging structures (non-leaf SPTEs)
+ * to be zapped while holding mmu_lock for read, and to allow TLB flushes to be
+ * batched without having to collect the list of zapped SPs.  Flows that can
+ * remove SPs must service pending TLB flushes prior to dropping RCU protection.
+ */
+static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep)
+{
+	return READ_ONCE(*rcu_dereference(sptep));
+}
+
+static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte)
+{
+	KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
+	return xchg(rcu_dereference(sptep), new_spte);
+}
+
+static inline u64 tdp_mmu_clear_spte_bits_atomic(tdp_ptep_t sptep, u64 mask)
+{
+	atomic64_t *sptep_atomic = (atomic64_t *)rcu_dereference(sptep);
+
+	return (u64)atomic64_fetch_and(~mask, sptep_atomic);
+}
+
+static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
+{
+	KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
+	WRITE_ONCE(*rcu_dereference(sptep), new_spte);
+}
+
+/*
+ * SPTEs must be modified atomically if they are shadow-present, leaf SPTEs,
+ * and have volatile bits (bits that can be set outside of mmu_lock) that
+ * must not be clobbered.
+ */
+static inline bool kvm_tdp_mmu_spte_need_atomic_update(u64 old_spte, int level)
+{
+	return is_shadow_present_pte(old_spte) &&
+	       is_last_spte(old_spte, level) &&
+	       spte_needs_atomic_update(old_spte);
+}
+
+static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte,
+					 u64 new_spte, int level)
+{
+	if (kvm_tdp_mmu_spte_need_atomic_update(old_spte, level))
+		return kvm_tdp_mmu_write_spte_atomic(sptep, new_spte);
+
+	__kvm_tdp_mmu_write_spte(sptep, new_spte);
+	return old_spte;
+}
+
+static inline u64 tdp_mmu_clear_spte_bits(tdp_ptep_t sptep, u64 old_spte,
+					  u64 mask, int level)
+{
+	if (kvm_tdp_mmu_spte_need_atomic_update(old_spte, level))
+		return tdp_mmu_clear_spte_bits_atomic(sptep, mask);
+
+	__kvm_tdp_mmu_write_spte(sptep, old_spte & ~mask);
+	return old_spte;
+}
+
+/*
+ * A TDP iterator performs a pre-order walk over a TDP paging structure.
+ */
+struct tdp_iter {
+	/*
+	 * The iterator will traverse the paging structure towards the mapping
+	 * for this GFN.
+	 */
+	gfn_t next_last_level_gfn;
+	/*
+	 * The next_last_level_gfn at the time when the thread last
+	 * yielded. Only yielding when the next_last_level_gfn !=
+	 * yielded_gfn helps ensure forward progress.
+	 */
+	gfn_t yielded_gfn;
+	/* Pointers to the page tables traversed to reach the current SPTE */
+	tdp_ptep_t pt_path[PT64_ROOT_MAX_LEVEL];
+	/* A pointer to the current SPTE */
+	tdp_ptep_t sptep;
+	/* The lowest GFN (mask bits excluded) mapped by the current SPTE */
+	gfn_t gfn;
+	/* Mask applied to convert the GFN to the mapping GPA */
+	gfn_t gfn_bits;
+	/* The level of the root page given to the iterator */
+	int root_level;
+	/* The lowest level the iterator should traverse to */
+	int min_level;
+	/* The iterator's current level within the paging structure */
+	int level;
+	/* The address space ID, i.e. SMM vs. regular. */
+	int as_id;
+	/* A snapshot of the value at sptep */
+	u64 old_spte;
+	/*
+	 * Whether the iterator has a valid state. This will be false if the
+	 * iterator walks off the end of the paging structure.
+	 */
+	bool valid;
+	/*
+	 * True if KVM dropped mmu_lock and yielded in the middle of a walk, in
+	 * which case tdp_iter_next() needs to restart the walk at the root
+	 * level instead of advancing to the next entry.
+	 */
+	bool yielded;
+};
+
+/*
+ * Iterates over every SPTE mapping the GFN range [start, end) in a
+ * preorder traversal.
+ */
+#define for_each_tdp_pte_min_level(iter, kvm, root, min_level, start, end)		  \
+	for (tdp_iter_start(&iter, root, min_level, start, kvm_gfn_root_bits(kvm, root)); \
+	     iter.valid && iter.gfn < end;						  \
+	     tdp_iter_next(&iter))
+
+#define for_each_tdp_pte_min_level_all(iter, root, min_level)		\
+	for (tdp_iter_start(&iter, root, min_level, 0, 0);		\
+		iter.valid && iter.gfn < tdp_mmu_max_gfn_exclusive();	\
+		tdp_iter_next(&iter))
+
+#define for_each_tdp_pte(iter, kvm, root, start, end)				\
+	for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_4K, start, end)
+
+tdp_ptep_t spte_to_child_pt(u64 pte, int level);
+
+void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root,
+		    int min_level, gfn_t next_last_level_gfn, gfn_t gfn_bits);
+void tdp_iter_next(struct tdp_iter *iter);
+void tdp_iter_restart(struct tdp_iter *iter);
+
+#endif /* __KVM_X86_MMU_TDP_ITER_H */

linux-7.2.3/arch/x86/kvm/mmu/tdp_mmu.h

@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef __KVM_X86_MMU_TDP_MMU_H
+#define __KVM_X86_MMU_TDP_MMU_H
+
+#include <linux/kvm_host.h>
+
+#include "spte.h"
+
+void kvm_mmu_init_tdp_mmu(struct kvm *kvm);
+void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm);
+
+void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu, bool private);
+
+__must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
+{
+	return refcount_inc_not_zero(&root->tdp_mmu_root_count);
+}
+
+void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root);
+
+enum kvm_tdp_mmu_root_types {
+	KVM_INVALID_ROOTS = BIT(0),
+	KVM_DIRECT_ROOTS = BIT(1),
+	KVM_MIRROR_ROOTS = BIT(2),
+	KVM_VALID_ROOTS = KVM_DIRECT_ROOTS | KVM_MIRROR_ROOTS,
+	KVM_ALL_ROOTS = KVM_VALID_ROOTS | KVM_INVALID_ROOTS,
+};
+
+static inline enum kvm_tdp_mmu_root_types kvm_gfn_range_filter_to_root_types(struct kvm *kvm,
+							     enum kvm_gfn_range_filter process)
+{
+	enum kvm_tdp_mmu_root_types ret = 0;
+
+	if (!kvm_has_mirrored_tdp(kvm))
+		return KVM_DIRECT_ROOTS;
+
+	if (process & KVM_FILTER_PRIVATE)
+		ret |= KVM_MIRROR_ROOTS;
+	if (process & KVM_FILTER_SHARED)
+		ret |= KVM_DIRECT_ROOTS;
+
+	WARN_ON_ONCE(!ret);
+
+	return ret;
+}
+
+static inline struct kvm_mmu_page *tdp_mmu_get_root_for_fault(struct kvm_vcpu *vcpu,
+							      struct kvm_page_fault *fault)
+{
+	if (unlikely(!kvm_is_addr_direct(vcpu->kvm, fault->addr)))
+		return root_to_sp(vcpu->arch.mmu->mirror_root_hpa);
+
+	return root_to_sp(vcpu->arch.mmu->root.hpa);
+}
+
+static inline struct kvm_mmu_page *tdp_mmu_get_root(struct kvm_vcpu *vcpu,
+						    enum kvm_tdp_mmu_root_types type)
+{
+	if (unlikely(type == KVM_MIRROR_ROOTS))
+		return root_to_sp(vcpu->arch.mmu->mirror_root_hpa);
+
+	return root_to_sp(vcpu->arch.mmu->root.hpa);
+}
+
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush);
+bool kvm_tdp_mmu_zap_possible_nx_huge_page(struct kvm *kvm,
+					   struct kvm_mmu_page *sp);
+void kvm_tdp_mmu_zap_all(struct kvm *kvm);
+void kvm_tdp_mmu_invalidate_roots(struct kvm *kvm,
+				  enum kvm_tdp_mmu_root_types root_types);
+void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared);
+
+int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
+
+bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
+				 bool flush);
+bool kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
+bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
+
+bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm,
+			     const struct kvm_memory_slot *slot, int min_level);
+void kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
+				  const struct kvm_memory_slot *slot);
+void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
+				       struct kvm_memory_slot *slot,
+				       gfn_t gfn, unsigned long mask,
+				       bool wrprot);
+void kvm_tdp_mmu_recover_huge_pages(struct kvm *kvm,
+				    const struct kvm_memory_slot *slot);
+
+bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
+				   struct kvm_memory_slot *slot, gfn_t gfn,
+				   int min_level);
+
+void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm,
+				      const struct kvm_memory_slot *slot,
+				      gfn_t start, gfn_t end,
+				      int target_level, bool shared);
+
+static inline void kvm_tdp_mmu_walk_lockless_begin(void)
+{
+	rcu_read_lock();
+}
+
+static inline void kvm_tdp_mmu_walk_lockless_end(void)
+{
+	rcu_read_unlock();
+}
+
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			 int *root_level);
+u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn,
+					u64 *spte);
+
+#ifdef CONFIG_X86_64
+static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; }
+#else
+static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; }
+#endif
+
+#endif /* __KVM_X86_MMU_TDP_MMU_H */