summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/mmu
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm/mmu')
-rw-r--r--arch/x86/kvm/mmu/mmu.c6961
-rw-r--r--arch/x86/kvm/mmu/mmu_internal.h320
-rw-r--r--arch/x86/kvm/mmu/mmutrace.h451
-rw-r--r--arch/x86/kvm/mmu/page_track.c302
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h1116
-rw-r--r--arch/x86/kvm/mmu/spte.c507
-rw-r--r--arch/x86/kvm/mmu/spte.h474
-rw-r--r--arch/x86/kvm/mmu/tdp_iter.c180
-rw-r--r--arch/x86/kvm/mmu/tdp_iter.h118
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c1885
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.h95
11 files changed, 12409 insertions, 0 deletions
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
new file mode 100644
index 000000000..d30325e29
--- /dev/null
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -0,0 +1,6961 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Kernel-based Virtual Machine driver for Linux
+ *
+ * This module enables machines with Intel VT-x extensions to run virtual
+ * machines without emulation or binary translation.
+ *
+ * MMU support
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ *
+ * Authors:
+ * Yaniv Kamay <yaniv@qumranet.com>
+ * Avi Kivity <avi@qumranet.com>
+ */
+
+#include "irq.h"
+#include "ioapic.h"
+#include "mmu.h"
+#include "mmu_internal.h"
+#include "tdp_mmu.h"
+#include "x86.h"
+#include "kvm_cache_regs.h"
+#include "kvm_emulate.h"
+#include "cpuid.h"
+#include "spte.h"
+
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/moduleparam.h>
+#include <linux/export.h>
+#include <linux/swap.h>
+#include <linux/hugetlb.h>
+#include <linux/compiler.h>
+#include <linux/srcu.h>
+#include <linux/slab.h>
+#include <linux/sched/signal.h>
+#include <linux/uaccess.h>
+#include <linux/hash.h>
+#include <linux/kern_levels.h>
+#include <linux/kstrtox.h>
+#include <linux/kthread.h>
+
+#include <asm/page.h>
+#include <asm/memtype.h>
+#include <asm/cmpxchg.h>
+#include <asm/io.h>
+#include <asm/set_memory.h>
+#include <asm/vmx.h>
+#include <asm/kvm_page_track.h>
+#include "trace.h"
+
+extern bool itlb_multihit_kvm_mitigation;
+
+static bool nx_hugepage_mitigation_hard_disabled;
+
+int __read_mostly nx_huge_pages = -1;
+static uint __read_mostly nx_huge_pages_recovery_period_ms;
+#ifdef CONFIG_PREEMPT_RT
+/* Recovery can cause latency spikes, disable it for PREEMPT_RT. */
+static uint __read_mostly nx_huge_pages_recovery_ratio = 0;
+#else
+static uint __read_mostly nx_huge_pages_recovery_ratio = 60;
+#endif
+
+static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp);
+static int set_nx_huge_pages(const char *val, const struct kernel_param *kp);
+static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp);
+
+static const struct kernel_param_ops nx_huge_pages_ops = {
+ .set = set_nx_huge_pages,
+ .get = get_nx_huge_pages,
+};
+
+static const struct kernel_param_ops nx_huge_pages_recovery_param_ops = {
+ .set = set_nx_huge_pages_recovery_param,
+ .get = param_get_uint,
+};
+
+module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644);
+__MODULE_PARM_TYPE(nx_huge_pages, "bool");
+module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_param_ops,
+ &nx_huge_pages_recovery_ratio, 0644);
+__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint");
+module_param_cb(nx_huge_pages_recovery_period_ms, &nx_huge_pages_recovery_param_ops,
+ &nx_huge_pages_recovery_period_ms, 0644);
+__MODULE_PARM_TYPE(nx_huge_pages_recovery_period_ms, "uint");
+
+static bool __read_mostly force_flush_and_sync_on_reuse;
+module_param_named(flush_on_reuse, force_flush_and_sync_on_reuse, bool, 0644);
+
+/*
+ * When setting this variable to true it enables Two-Dimensional-Paging
+ * where the hardware walks 2 page tables:
+ * 1. the guest-virtual to guest-physical
+ * 2. while doing 1. it walks guest-physical to host-physical
+ * If the hardware supports that we don't need to do shadow paging.
+ */
+bool tdp_enabled = false;
+
+static int max_huge_page_level __read_mostly;
+static int tdp_root_level __read_mostly;
+static int max_tdp_level __read_mostly;
+
+#ifdef MMU_DEBUG
+bool dbg = 0;
+module_param(dbg, bool, 0644);
+#endif
+
+#define PTE_PREFETCH_NUM 8
+
+#include <trace/events/kvm.h>
+
+/* make pte_list_desc fit well in cache lines */
+#define PTE_LIST_EXT 14
+
+/*
+ * Slight optimization of cacheline layout, by putting `more' and `spte_count'
+ * at the start; then accessing it will only use one single cacheline for
+ * either full (entries==PTE_LIST_EXT) case or entries<=6.
+ */
+struct pte_list_desc {
+ struct pte_list_desc *more;
+ /*
+ * Stores number of entries stored in the pte_list_desc. No need to be
+ * u64 but just for easier alignment. When PTE_LIST_EXT, means full.
+ */
+ u64 spte_count;
+ u64 *sptes[PTE_LIST_EXT];
+};
+
+struct kvm_shadow_walk_iterator {
+ u64 addr;
+ hpa_t shadow_addr;
+ u64 *sptep;
+ int level;
+ unsigned index;
+};
+
+#define for_each_shadow_entry_using_root(_vcpu, _root, _addr, _walker) \
+ for (shadow_walk_init_using_root(&(_walker), (_vcpu), \
+ (_root), (_addr)); \
+ shadow_walk_okay(&(_walker)); \
+ shadow_walk_next(&(_walker)))
+
+#define for_each_shadow_entry(_vcpu, _addr, _walker) \
+ for (shadow_walk_init(&(_walker), _vcpu, _addr); \
+ shadow_walk_okay(&(_walker)); \
+ shadow_walk_next(&(_walker)))
+
+#define for_each_shadow_entry_lockless(_vcpu, _addr, _walker, spte) \
+ for (shadow_walk_init(&(_walker), _vcpu, _addr); \
+ shadow_walk_okay(&(_walker)) && \
+ ({ spte = mmu_spte_get_lockless(_walker.sptep); 1; }); \
+ __shadow_walk_next(&(_walker), spte))
+
+static struct kmem_cache *pte_list_desc_cache;
+struct kmem_cache *mmu_page_header_cache;
+static struct percpu_counter kvm_total_used_mmu_pages;
+
+static void mmu_spte_set(u64 *sptep, u64 spte);
+
+struct kvm_mmu_role_regs {
+ const unsigned long cr0;
+ const unsigned long cr4;
+ const u64 efer;
+};
+
+#define CREATE_TRACE_POINTS
+#include "mmutrace.h"
+
+/*
+ * Yes, lot's of underscores. They're a hint that you probably shouldn't be
+ * reading from the role_regs. Once the root_role is constructed, it becomes
+ * the single source of truth for the MMU's state.
+ */
+#define BUILD_MMU_ROLE_REGS_ACCESSOR(reg, name, flag) \
+static inline bool __maybe_unused \
+____is_##reg##_##name(const struct kvm_mmu_role_regs *regs) \
+{ \
+ return !!(regs->reg & flag); \
+}
+BUILD_MMU_ROLE_REGS_ACCESSOR(cr0, pg, X86_CR0_PG);
+BUILD_MMU_ROLE_REGS_ACCESSOR(cr0, wp, X86_CR0_WP);
+BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pse, X86_CR4_PSE);
+BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pae, X86_CR4_PAE);
+BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, smep, X86_CR4_SMEP);
+BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, smap, X86_CR4_SMAP);
+BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pke, X86_CR4_PKE);
+BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, la57, X86_CR4_LA57);
+BUILD_MMU_ROLE_REGS_ACCESSOR(efer, nx, EFER_NX);
+BUILD_MMU_ROLE_REGS_ACCESSOR(efer, lma, EFER_LMA);
+
+/*
+ * The MMU itself (with a valid role) is the single source of truth for the
+ * MMU. Do not use the regs used to build the MMU/role, nor the vCPU. The
+ * regs don't account for dependencies, e.g. clearing CR4 bits if CR0.PG=1,
+ * and the vCPU may be incorrect/irrelevant.
+ */
+#define BUILD_MMU_ROLE_ACCESSOR(base_or_ext, reg, name) \
+static inline bool __maybe_unused is_##reg##_##name(struct kvm_mmu *mmu) \
+{ \
+ return !!(mmu->cpu_role. base_or_ext . reg##_##name); \
+}
+BUILD_MMU_ROLE_ACCESSOR(base, cr0, wp);
+BUILD_MMU_ROLE_ACCESSOR(ext, cr4, pse);
+BUILD_MMU_ROLE_ACCESSOR(ext, cr4, smep);
+BUILD_MMU_ROLE_ACCESSOR(ext, cr4, smap);
+BUILD_MMU_ROLE_ACCESSOR(ext, cr4, pke);
+BUILD_MMU_ROLE_ACCESSOR(ext, cr4, la57);
+BUILD_MMU_ROLE_ACCESSOR(base, efer, nx);
+BUILD_MMU_ROLE_ACCESSOR(ext, efer, lma);
+
+static inline bool is_cr0_pg(struct kvm_mmu *mmu)
+{
+ return mmu->cpu_role.base.level > 0;
+}
+
+static inline bool is_cr4_pae(struct kvm_mmu *mmu)
+{
+ return !mmu->cpu_role.base.has_4_byte_gpte;
+}
+
+static struct kvm_mmu_role_regs vcpu_to_role_regs(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu_role_regs regs = {
+ .cr0 = kvm_read_cr0_bits(vcpu, KVM_MMU_CR0_ROLE_BITS),
+ .cr4 = kvm_read_cr4_bits(vcpu, KVM_MMU_CR4_ROLE_BITS),
+ .efer = vcpu->arch.efer,
+ };
+
+ return regs;
+}
+
+static unsigned long get_guest_cr3(struct kvm_vcpu *vcpu)
+{
+ return kvm_read_cr3(vcpu);
+}
+
+static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *mmu)
+{
+ if (IS_ENABLED(CONFIG_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3)
+ return kvm_read_cr3(vcpu);
+
+ return mmu->get_guest_pgd(vcpu);
+}
+
+static inline bool kvm_available_flush_tlb_with_range(void)
+{
+ return kvm_x86_ops.tlb_remote_flush_with_range;
+}
+
+static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm,
+ struct kvm_tlb_range *range)
+{
+ int ret = -ENOTSUPP;
+
+ if (range && kvm_x86_ops.tlb_remote_flush_with_range)
+ ret = static_call(kvm_x86_tlb_remote_flush_with_range)(kvm, range);
+
+ if (ret)
+ kvm_flush_remote_tlbs(kvm);
+}
+
+void kvm_flush_remote_tlbs_with_address(struct kvm *kvm,
+ u64 start_gfn, u64 pages)
+{
+ struct kvm_tlb_range range;
+
+ range.start_gfn = start_gfn;
+ range.pages = pages;
+
+ kvm_flush_remote_tlbs_with_range(kvm, &range);
+}
+
+static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
+ unsigned int access)
+{
+ u64 spte = make_mmio_spte(vcpu, gfn, access);
+
+ trace_mark_mmio_spte(sptep, gfn, spte);
+ mmu_spte_set(sptep, spte);
+}
+
+static gfn_t get_mmio_spte_gfn(u64 spte)
+{
+ u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
+
+ gpa |= (spte >> SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)
+ & shadow_nonpresent_or_rsvd_mask;
+
+ return gpa >> PAGE_SHIFT;
+}
+
+static unsigned get_mmio_spte_access(u64 spte)
+{
+ return spte & shadow_mmio_access_mask;
+}
+
+static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
+{
+ u64 kvm_gen, spte_gen, gen;
+
+ gen = kvm_vcpu_memslots(vcpu)->generation;
+ if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS))
+ return false;
+
+ kvm_gen = gen & MMIO_SPTE_GEN_MASK;
+ spte_gen = get_mmio_spte_generation(spte);
+
+ trace_check_mmio_spte(spte, kvm_gen, spte_gen);
+ return likely(kvm_gen == spte_gen);
+}
+
+static int is_cpuid_PSE36(void)
+{
+ return 1;
+}
+
+#ifdef CONFIG_X86_64
+static void __set_spte(u64 *sptep, u64 spte)
+{
+ WRITE_ONCE(*sptep, spte);
+}
+
+static void __update_clear_spte_fast(u64 *sptep, u64 spte)
+{
+ WRITE_ONCE(*sptep, spte);
+}
+
+static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
+{
+ return xchg(sptep, spte);
+}
+
+static u64 __get_spte_lockless(u64 *sptep)
+{
+ return READ_ONCE(*sptep);
+}
+#else
+union split_spte {
+ struct {
+ u32 spte_low;
+ u32 spte_high;
+ };
+ u64 spte;
+};
+
+static void count_spte_clear(u64 *sptep, u64 spte)
+{
+ struct kvm_mmu_page *sp = sptep_to_sp(sptep);
+
+ if (is_shadow_present_pte(spte))
+ return;
+
+ /* Ensure the spte is completely set before we increase the count */
+ smp_wmb();
+ sp->clear_spte_count++;
+}
+
+static void __set_spte(u64 *sptep, u64 spte)
+{
+ union split_spte *ssptep, sspte;
+
+ ssptep = (union split_spte *)sptep;
+ sspte = (union split_spte)spte;
+
+ ssptep->spte_high = sspte.spte_high;
+
+ /*
+ * If we map the spte from nonpresent to present, We should store
+ * the high bits firstly, then set present bit, so cpu can not
+ * fetch this spte while we are setting the spte.
+ */
+ smp_wmb();
+
+ WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
+}
+
+static void __update_clear_spte_fast(u64 *sptep, u64 spte)
+{
+ union split_spte *ssptep, sspte;
+
+ ssptep = (union split_spte *)sptep;
+ sspte = (union split_spte)spte;
+
+ WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
+
+ /*
+ * If we map the spte from present to nonpresent, we should clear
+ * present bit firstly to avoid vcpu fetch the old high bits.
+ */
+ smp_wmb();
+
+ ssptep->spte_high = sspte.spte_high;
+ count_spte_clear(sptep, spte);
+}
+
+static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
+{
+ union split_spte *ssptep, sspte, orig;
+
+ ssptep = (union split_spte *)sptep;
+ sspte = (union split_spte)spte;
+
+ /* xchg acts as a barrier before the setting of the high bits */
+ orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low);
+ orig.spte_high = ssptep->spte_high;
+ ssptep->spte_high = sspte.spte_high;
+ count_spte_clear(sptep, spte);
+
+ return orig.spte;
+}
+
+/*
+ * The idea using the light way get the spte on x86_32 guest is from
+ * gup_get_pte (mm/gup.c).
+ *
+ * An spte tlb flush may be pending, because kvm_set_pte_rmap
+ * coalesces them and we are running out of the MMU lock. Therefore
+ * we need to protect against in-progress updates of the spte.
+ *
+ * Reading the spte while an update is in progress may get the old value
+ * for the high part of the spte. The race is fine for a present->non-present
+ * change (because the high part of the spte is ignored for non-present spte),
+ * but for a present->present change we must reread the spte.
+ *
+ * All such changes are done in two steps (present->non-present and
+ * non-present->present), hence it is enough to count the number of
+ * present->non-present updates: if it changed while reading the spte,
+ * we might have hit the race. This is done using clear_spte_count.
+ */
+static u64 __get_spte_lockless(u64 *sptep)
+{
+ struct kvm_mmu_page *sp = sptep_to_sp(sptep);
+ union split_spte spte, *orig = (union split_spte *)sptep;
+ int count;
+
+retry:
+ count = sp->clear_spte_count;
+ smp_rmb();
+
+ spte.spte_low = orig->spte_low;
+ smp_rmb();
+
+ spte.spte_high = orig->spte_high;
+ smp_rmb();
+
+ if (unlikely(spte.spte_low != orig->spte_low ||
+ count != sp->clear_spte_count))
+ goto retry;
+
+ return spte.spte;
+}
+#endif
+
+/* Rules for using mmu_spte_set:
+ * Set the sptep from nonpresent to present.
+ * Note: the sptep being assigned *must* be either not present
+ * or in a state where the hardware will not attempt to update
+ * the spte.
+ */
+static void mmu_spte_set(u64 *sptep, u64 new_spte)
+{
+ WARN_ON(is_shadow_present_pte(*sptep));
+ __set_spte(sptep, new_spte);
+}
+
+/*
+ * Update the SPTE (excluding the PFN), but do not track changes in its
+ * accessed/dirty status.
+ */
+static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte)
+{
+ u64 old_spte = *sptep;
+
+ WARN_ON(!is_shadow_present_pte(new_spte));
+ check_spte_writable_invariants(new_spte);
+
+ if (!is_shadow_present_pte(old_spte)) {
+ mmu_spte_set(sptep, new_spte);
+ return old_spte;
+ }
+
+ if (!spte_has_volatile_bits(old_spte))
+ __update_clear_spte_fast(sptep, new_spte);
+ else
+ old_spte = __update_clear_spte_slow(sptep, new_spte);
+
+ WARN_ON(spte_to_pfn(old_spte) != spte_to_pfn(new_spte));
+
+ return old_spte;
+}
+
+/* Rules for using mmu_spte_update:
+ * Update the state bits, it means the mapped pfn is not changed.
+ *
+ * Whenever an MMU-writable SPTE is overwritten with a read-only SPTE, remote
+ * TLBs must be flushed. Otherwise rmap_write_protect will find a read-only
+ * spte, even though the writable spte might be cached on a CPU's TLB.
+ *
+ * Returns true if the TLB needs to be flushed
+ */
+static bool mmu_spte_update(u64 *sptep, u64 new_spte)
+{
+ bool flush = false;
+ u64 old_spte = mmu_spte_update_no_track(sptep, new_spte);
+
+ if (!is_shadow_present_pte(old_spte))
+ return false;
+
+ /*
+ * For the spte updated out of mmu-lock is safe, since
+ * we always atomically update it, see the comments in
+ * spte_has_volatile_bits().
+ */
+ if (is_mmu_writable_spte(old_spte) &&
+ !is_writable_pte(new_spte))
+ flush = true;
+
+ /*
+ * Flush TLB when accessed/dirty states are changed in the page tables,
+ * to guarantee consistency between TLB and page tables.
+ */
+
+ if (is_accessed_spte(old_spte) && !is_accessed_spte(new_spte)) {
+ flush = true;
+ kvm_set_pfn_accessed(spte_to_pfn(old_spte));
+ }
+
+ if (is_dirty_spte(old_spte) && !is_dirty_spte(new_spte)) {
+ flush = true;
+ kvm_set_pfn_dirty(spte_to_pfn(old_spte));
+ }
+
+ return flush;
+}
+
+/*
+ * Rules for using mmu_spte_clear_track_bits:
+ * It sets the sptep from present to nonpresent, and track the
+ * state bits, it is used to clear the last level sptep.
+ * Returns the old PTE.
+ */
+static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
+{
+ kvm_pfn_t pfn;
+ u64 old_spte = *sptep;
+ int level = sptep_to_sp(sptep)->role.level;
+ struct page *page;
+
+ if (!is_shadow_present_pte(old_spte) ||
+ !spte_has_volatile_bits(old_spte))
+ __update_clear_spte_fast(sptep, 0ull);
+ else
+ old_spte = __update_clear_spte_slow(sptep, 0ull);
+
+ if (!is_shadow_present_pte(old_spte))
+ return old_spte;
+
+ kvm_update_page_stats(kvm, level, -1);
+
+ pfn = spte_to_pfn(old_spte);
+
+ /*
+ * KVM doesn't hold a reference to any pages mapped into the guest, and
+ * instead uses the mmu_notifier to ensure that KVM unmaps any pages
+ * before they are reclaimed. Sanity check that, if the pfn is backed
+ * by a refcounted page, the refcount is elevated.
+ */
+ page = kvm_pfn_to_refcounted_page(pfn);
+ WARN_ON(page && !page_count(page));
+
+ if (is_accessed_spte(old_spte))
+ kvm_set_pfn_accessed(pfn);
+
+ if (is_dirty_spte(old_spte))
+ kvm_set_pfn_dirty(pfn);
+
+ return old_spte;
+}
+
+/*
+ * Rules for using mmu_spte_clear_no_track:
+ * Directly clear spte without caring the state bits of sptep,
+ * it is used to set the upper level spte.
+ */
+static void mmu_spte_clear_no_track(u64 *sptep)
+{
+ __update_clear_spte_fast(sptep, 0ull);
+}
+
+static u64 mmu_spte_get_lockless(u64 *sptep)
+{
+ return __get_spte_lockless(sptep);
+}
+
+/* Returns the Accessed status of the PTE and resets it at the same time. */
+static bool mmu_spte_age(u64 *sptep)
+{
+ u64 spte = mmu_spte_get_lockless(sptep);
+
+ if (!is_accessed_spte(spte))
+ return false;
+
+ if (spte_ad_enabled(spte)) {
+ clear_bit((ffs(shadow_accessed_mask) - 1),
+ (unsigned long *)sptep);
+ } else {
+ /*
+ * Capture the dirty status of the page, so that it doesn't get
+ * lost when the SPTE is marked for access tracking.
+ */
+ if (is_writable_pte(spte))
+ kvm_set_pfn_dirty(spte_to_pfn(spte));
+
+ spte = mark_spte_for_access_track(spte);
+ mmu_spte_update_no_track(sptep, spte);
+ }
+
+ return true;
+}
+
+static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu)
+{
+ if (is_tdp_mmu(vcpu->arch.mmu)) {
+ kvm_tdp_mmu_walk_lockless_begin();
+ } else {
+ /*
+ * Prevent page table teardown by making any free-er wait during
+ * kvm_flush_remote_tlbs() IPI to all active vcpus.
+ */
+ local_irq_disable();
+
+ /*
+ * Make sure a following spte read is not reordered ahead of the write
+ * to vcpu->mode.
+ */
+ smp_store_mb(vcpu->mode, READING_SHADOW_PAGE_TABLES);
+ }
+}
+
+static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
+{
+ if (is_tdp_mmu(vcpu->arch.mmu)) {
+ kvm_tdp_mmu_walk_lockless_end();
+ } else {
+ /*
+ * Make sure the write to vcpu->mode is not reordered in front of
+ * reads to sptes. If it does, kvm_mmu_commit_zap_page() can see us
+ * OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
+ */
+ smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE);
+ local_irq_enable();
+ }
+}
+
+static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect)
+{
+ int r;
+
+ /* 1 rmap, 1 parent PTE per level, and the prefetched rmaps. */
+ r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache,
+ 1 + PT64_ROOT_MAX_LEVEL + PTE_PREFETCH_NUM);
+ if (r)
+ return r;
+ r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache,
+ PT64_ROOT_MAX_LEVEL);
+ if (r)
+ return r;
+ if (maybe_indirect) {
+ r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadowed_info_cache,
+ PT64_ROOT_MAX_LEVEL);
+ if (r)
+ return r;
+ }
+ return kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_page_header_cache,
+ PT64_ROOT_MAX_LEVEL);
+}
+
+static void mmu_free_memory_caches(struct kvm_vcpu *vcpu)
+{
+ kvm_mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache);
+ kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadow_page_cache);
+ kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadowed_info_cache);
+ kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache);
+}
+
+static void mmu_free_pte_list_desc(struct pte_list_desc *pte_list_desc)
+{
+ kmem_cache_free(pte_list_desc_cache, pte_list_desc);
+}
+
+static bool sp_has_gptes(struct kvm_mmu_page *sp);
+
+static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index)
+{
+ if (sp->role.passthrough)
+ return sp->gfn;
+
+ if (!sp->role.direct)
+ return sp->shadowed_translation[index] >> PAGE_SHIFT;
+
+ return sp->gfn + (index << ((sp->role.level - 1) * SPTE_LEVEL_BITS));
+}
+
+/*
+ * For leaf SPTEs, fetch the *guest* access permissions being shadowed. Note
+ * that the SPTE itself may have a more constrained access permissions that
+ * what the guest enforces. For example, a guest may create an executable
+ * huge PTE but KVM may disallow execution to mitigate iTLB multihit.
+ */
+static u32 kvm_mmu_page_get_access(struct kvm_mmu_page *sp, int index)
+{
+ if (sp_has_gptes(sp))
+ return sp->shadowed_translation[index] & ACC_ALL;
+
+ /*
+ * For direct MMUs (e.g. TDP or non-paging guests) or passthrough SPs,
+ * KVM is not shadowing any guest page tables, so the "guest access
+ * permissions" are just ACC_ALL.
+ *
+ * For direct SPs in indirect MMUs (shadow paging), i.e. when KVM
+ * is shadowing a guest huge page with small pages, the guest access
+ * permissions being shadowed are the access permissions of the huge
+ * page.
+ *
+ * In both cases, sp->role.access contains the correct access bits.
+ */
+ return sp->role.access;
+}
+
+static void kvm_mmu_page_set_translation(struct kvm_mmu_page *sp, int index,
+ gfn_t gfn, unsigned int access)
+{
+ if (sp_has_gptes(sp)) {
+ sp->shadowed_translation[index] = (gfn << PAGE_SHIFT) | access;
+ return;
+ }
+
+ WARN_ONCE(access != kvm_mmu_page_get_access(sp, index),
+ "access mismatch under %s page %llx (expected %u, got %u)\n",
+ sp->role.passthrough ? "passthrough" : "direct",
+ sp->gfn, kvm_mmu_page_get_access(sp, index), access);
+
+ WARN_ONCE(gfn != kvm_mmu_page_get_gfn(sp, index),
+ "gfn mismatch under %s page %llx (expected %llx, got %llx)\n",
+ sp->role.passthrough ? "passthrough" : "direct",
+ sp->gfn, kvm_mmu_page_get_gfn(sp, index), gfn);
+}
+
+static void kvm_mmu_page_set_access(struct kvm_mmu_page *sp, int index,
+ unsigned int access)
+{
+ gfn_t gfn = kvm_mmu_page_get_gfn(sp, index);
+
+ kvm_mmu_page_set_translation(sp, index, gfn, access);
+}
+
+/*
+ * Return the pointer to the large page information for a given gfn,
+ * handling slots that are not large page aligned.
+ */
+static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
+ const struct kvm_memory_slot *slot, int level)
+{
+ unsigned long idx;
+
+ idx = gfn_to_index(gfn, slot->base_gfn, level);
+ return &slot->arch.lpage_info[level - 2][idx];
+}
+
+static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot,
+ gfn_t gfn, int count)
+{
+ struct kvm_lpage_info *linfo;
+ int i;
+
+ for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) {
+ linfo = lpage_info_slot(gfn, slot, i);
+ linfo->disallow_lpage += count;
+ WARN_ON(linfo->disallow_lpage < 0);
+ }
+}
+
+void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn)
+{
+ update_gfn_disallow_lpage_count(slot, gfn, 1);
+}
+
+void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn)
+{
+ update_gfn_disallow_lpage_count(slot, gfn, -1);
+}
+
+static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *slot;
+ gfn_t gfn;
+
+ kvm->arch.indirect_shadow_pages++;
+ gfn = sp->gfn;
+ slots = kvm_memslots_for_spte_role(kvm, sp->role);
+ slot = __gfn_to_memslot(slots, gfn);
+
+ /* the non-leaf shadow pages are keeping readonly. */
+ if (sp->role.level > PG_LEVEL_4K)
+ return kvm_slot_page_track_add_page(kvm, slot, gfn,
+ KVM_PAGE_TRACK_WRITE);
+
+ kvm_mmu_gfn_disallow_lpage(slot, gfn);
+
+ if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
+ kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
+}
+
+void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ if (sp->lpage_disallowed)
+ return;
+
+ ++kvm->stat.nx_lpage_splits;
+ list_add_tail(&sp->lpage_disallowed_link,
+ &kvm->arch.lpage_disallowed_mmu_pages);
+ sp->lpage_disallowed = true;
+}
+
+static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *slot;
+ gfn_t gfn;
+
+ kvm->arch.indirect_shadow_pages--;
+ gfn = sp->gfn;
+ slots = kvm_memslots_for_spte_role(kvm, sp->role);
+ slot = __gfn_to_memslot(slots, gfn);
+ if (sp->role.level > PG_LEVEL_4K)
+ return kvm_slot_page_track_remove_page(kvm, slot, gfn,
+ KVM_PAGE_TRACK_WRITE);
+
+ kvm_mmu_gfn_allow_lpage(slot, gfn);
+}
+
+void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ --kvm->stat.nx_lpage_splits;
+ sp->lpage_disallowed = false;
+ list_del(&sp->lpage_disallowed_link);
+}
+
+static struct kvm_memory_slot *
+gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
+ bool no_dirty_log)
+{
+ struct kvm_memory_slot *slot;
+
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
+ return NULL;
+ if (no_dirty_log && kvm_slot_dirty_track_enabled(slot))
+ return NULL;
+
+ return slot;
+}
+
+/*
+ * About rmap_head encoding:
+ *
+ * If the bit zero of rmap_head->val is clear, then it points to the only spte
+ * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct
+ * pte_list_desc containing more mappings.
+ */
+
+/*
+ * Returns the number of pointers in the rmap chain, not counting the new one.
+ */
+static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
+ struct kvm_rmap_head *rmap_head)
+{
+ struct pte_list_desc *desc;
+ int count = 0;
+
+ if (!rmap_head->val) {
+ rmap_printk("%p %llx 0->1\n", spte, *spte);
+ rmap_head->val = (unsigned long)spte;
+ } else if (!(rmap_head->val & 1)) {
+ rmap_printk("%p %llx 1->many\n", spte, *spte);
+ desc = kvm_mmu_memory_cache_alloc(cache);
+ desc->sptes[0] = (u64 *)rmap_head->val;
+ desc->sptes[1] = spte;
+ desc->spte_count = 2;
+ rmap_head->val = (unsigned long)desc | 1;
+ ++count;
+ } else {
+ rmap_printk("%p %llx many->many\n", spte, *spte);
+ desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
+ while (desc->spte_count == PTE_LIST_EXT) {
+ count += PTE_LIST_EXT;
+ if (!desc->more) {
+ desc->more = kvm_mmu_memory_cache_alloc(cache);
+ desc = desc->more;
+ desc->spte_count = 0;
+ break;
+ }
+ desc = desc->more;
+ }
+ count += desc->spte_count;
+ desc->sptes[desc->spte_count++] = spte;
+ }
+ return count;
+}
+
+static void
+pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
+ struct pte_list_desc *desc, int i,
+ struct pte_list_desc *prev_desc)
+{
+ int j = desc->spte_count - 1;
+
+ desc->sptes[i] = desc->sptes[j];
+ desc->sptes[j] = NULL;
+ desc->spte_count--;
+ if (desc->spte_count)
+ return;
+ if (!prev_desc && !desc->more)
+ rmap_head->val = 0;
+ else
+ if (prev_desc)
+ prev_desc->more = desc->more;
+ else
+ rmap_head->val = (unsigned long)desc->more | 1;
+ mmu_free_pte_list_desc(desc);
+}
+
+static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
+{
+ struct pte_list_desc *desc;
+ struct pte_list_desc *prev_desc;
+ int i;
+
+ if (!rmap_head->val) {
+ pr_err("%s: %p 0->BUG\n", __func__, spte);
+ BUG();
+ } else if (!(rmap_head->val & 1)) {
+ rmap_printk("%p 1->0\n", spte);
+ if ((u64 *)rmap_head->val != spte) {
+ pr_err("%s: %p 1->BUG\n", __func__, spte);
+ BUG();
+ }
+ rmap_head->val = 0;
+ } else {
+ rmap_printk("%p many->many\n", spte);
+ desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
+ prev_desc = NULL;
+ while (desc) {
+ for (i = 0; i < desc->spte_count; ++i) {
+ if (desc->sptes[i] == spte) {
+ pte_list_desc_remove_entry(rmap_head,
+ desc, i, prev_desc);
+ return;
+ }
+ }
+ prev_desc = desc;
+ desc = desc->more;
+ }
+ pr_err("%s: %p many->many\n", __func__, spte);
+ BUG();
+ }
+}
+
+static void kvm_zap_one_rmap_spte(struct kvm *kvm,
+ struct kvm_rmap_head *rmap_head, u64 *sptep)
+{
+ mmu_spte_clear_track_bits(kvm, sptep);
+ pte_list_remove(sptep, rmap_head);
+}
+
+/* Return true if at least one SPTE was zapped, false otherwise */
+static bool kvm_zap_all_rmap_sptes(struct kvm *kvm,
+ struct kvm_rmap_head *rmap_head)
+{
+ struct pte_list_desc *desc, *next;
+ int i;
+
+ if (!rmap_head->val)
+ return false;
+
+ if (!(rmap_head->val & 1)) {
+ mmu_spte_clear_track_bits(kvm, (u64 *)rmap_head->val);
+ goto out;
+ }
+
+ desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
+
+ for (; desc; desc = next) {
+ for (i = 0; i < desc->spte_count; i++)
+ mmu_spte_clear_track_bits(kvm, desc->sptes[i]);
+ next = desc->more;
+ mmu_free_pte_list_desc(desc);
+ }
+out:
+ /* rmap_head is meaningless now, remember to reset it */
+ rmap_head->val = 0;
+ return true;
+}
+
+unsigned int pte_list_count(struct kvm_rmap_head *rmap_head)
+{
+ struct pte_list_desc *desc;
+ unsigned int count = 0;
+
+ if (!rmap_head->val)
+ return 0;
+ else if (!(rmap_head->val & 1))
+ return 1;
+
+ desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
+
+ while (desc) {
+ count += desc->spte_count;
+ desc = desc->more;
+ }
+
+ return count;
+}
+
+static struct kvm_rmap_head *gfn_to_rmap(gfn_t gfn, int level,
+ const struct kvm_memory_slot *slot)
+{
+ unsigned long idx;
+
+ idx = gfn_to_index(gfn, slot->base_gfn, level);
+ return &slot->arch.rmap[level - PG_LEVEL_4K][idx];
+}
+
+static bool rmap_can_add(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu_memory_cache *mc;
+
+ mc = &vcpu->arch.mmu_pte_list_desc_cache;
+ return kvm_mmu_memory_cache_nr_free_objects(mc);
+}
+
+static void rmap_remove(struct kvm *kvm, u64 *spte)
+{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *slot;
+ struct kvm_mmu_page *sp;
+ gfn_t gfn;
+ struct kvm_rmap_head *rmap_head;
+
+ sp = sptep_to_sp(spte);
+ gfn = kvm_mmu_page_get_gfn(sp, spte_index(spte));
+
+ /*
+ * Unlike rmap_add, rmap_remove does not run in the context of a vCPU
+ * so we have to determine which memslots to use based on context
+ * information in sp->role.
+ */
+ slots = kvm_memslots_for_spte_role(kvm, sp->role);
+
+ slot = __gfn_to_memslot(slots, gfn);
+ rmap_head = gfn_to_rmap(gfn, sp->role.level, slot);
+
+ pte_list_remove(spte, rmap_head);
+}
+
+/*
+ * Used by the following functions to iterate through the sptes linked by a
+ * rmap. All fields are private and not assumed to be used outside.
+ */
+struct rmap_iterator {
+ /* private fields */
+ struct pte_list_desc *desc; /* holds the sptep if not NULL */
+ int pos; /* index of the sptep */
+};
+
+/*
+ * Iteration must be started by this function. This should also be used after
+ * removing/dropping sptes from the rmap link because in such cases the
+ * information in the iterator may not be valid.
+ *
+ * Returns sptep if found, NULL otherwise.
+ */
+static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head,
+ struct rmap_iterator *iter)
+{
+ u64 *sptep;
+
+ if (!rmap_head->val)
+ return NULL;
+
+ if (!(rmap_head->val & 1)) {
+ iter->desc = NULL;
+ sptep = (u64 *)rmap_head->val;
+ goto out;
+ }
+
+ iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
+ iter->pos = 0;
+ sptep = iter->desc->sptes[iter->pos];
+out:
+ BUG_ON(!is_shadow_present_pte(*sptep));
+ return sptep;
+}
+
+/*
+ * Must be used with a valid iterator: e.g. after rmap_get_first().
+ *
+ * Returns sptep if found, NULL otherwise.
+ */
+static u64 *rmap_get_next(struct rmap_iterator *iter)
+{
+ u64 *sptep;
+
+ if (iter->desc) {
+ if (iter->pos < PTE_LIST_EXT - 1) {
+ ++iter->pos;
+ sptep = iter->desc->sptes[iter->pos];
+ if (sptep)
+ goto out;
+ }
+
+ iter->desc = iter->desc->more;
+
+ if (iter->desc) {
+ iter->pos = 0;
+ /* desc->sptes[0] cannot be NULL */
+ sptep = iter->desc->sptes[iter->pos];
+ goto out;
+ }
+ }
+
+ return NULL;
+out:
+ BUG_ON(!is_shadow_present_pte(*sptep));
+ return sptep;
+}
+
+#define for_each_rmap_spte(_rmap_head_, _iter_, _spte_) \
+ for (_spte_ = rmap_get_first(_rmap_head_, _iter_); \
+ _spte_; _spte_ = rmap_get_next(_iter_))
+
+static void drop_spte(struct kvm *kvm, u64 *sptep)
+{
+ u64 old_spte = mmu_spte_clear_track_bits(kvm, sptep);
+
+ if (is_shadow_present_pte(old_spte))
+ rmap_remove(kvm, sptep);
+}
+
+static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush)
+{
+ struct kvm_mmu_page *sp;
+
+ sp = sptep_to_sp(sptep);
+ WARN_ON(sp->role.level == PG_LEVEL_4K);
+
+ drop_spte(kvm, sptep);
+
+ if (flush)
+ kvm_flush_remote_tlbs_with_address(kvm, sp->gfn,
+ KVM_PAGES_PER_HPAGE(sp->role.level));
+}
+
+/*
+ * Write-protect on the specified @sptep, @pt_protect indicates whether
+ * spte write-protection is caused by protecting shadow page table.
+ *
+ * Note: write protection is difference between dirty logging and spte
+ * protection:
+ * - for dirty logging, the spte can be set to writable at anytime if
+ * its dirty bitmap is properly set.
+ * - for spte protection, the spte can be writable only after unsync-ing
+ * shadow page.
+ *
+ * Return true if tlb need be flushed.
+ */
+static bool spte_write_protect(u64 *sptep, bool pt_protect)
+{
+ u64 spte = *sptep;
+
+ if (!is_writable_pte(spte) &&
+ !(pt_protect && is_mmu_writable_spte(spte)))
+ return false;
+
+ rmap_printk("spte %p %llx\n", sptep, *sptep);
+
+ if (pt_protect)
+ spte &= ~shadow_mmu_writable_mask;
+ spte = spte & ~PT_WRITABLE_MASK;
+
+ return mmu_spte_update(sptep, spte);
+}
+
+static bool rmap_write_protect(struct kvm_rmap_head *rmap_head,
+ bool pt_protect)
+{
+ u64 *sptep;
+ struct rmap_iterator iter;
+ bool flush = false;
+
+ for_each_rmap_spte(rmap_head, &iter, sptep)
+ flush |= spte_write_protect(sptep, pt_protect);
+
+ return flush;
+}
+
+static bool spte_clear_dirty(u64 *sptep)
+{
+ u64 spte = *sptep;
+
+ rmap_printk("spte %p %llx\n", sptep, *sptep);
+
+ MMU_WARN_ON(!spte_ad_enabled(spte));
+ spte &= ~shadow_dirty_mask;
+ return mmu_spte_update(sptep, spte);
+}
+
+static bool spte_wrprot_for_clear_dirty(u64 *sptep)
+{
+ bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT,
+ (unsigned long *)sptep);
+ if (was_writable && !spte_ad_enabled(*sptep))
+ kvm_set_pfn_dirty(spte_to_pfn(*sptep));
+
+ return was_writable;
+}
+
+/*
+ * Gets the GFN ready for another round of dirty logging by clearing the
+ * - D bit on ad-enabled SPTEs, and
+ * - W bit on ad-disabled SPTEs.
+ * Returns true iff any D or W bits were cleared.
+ */
+static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
+ const struct kvm_memory_slot *slot)
+{
+ u64 *sptep;
+ struct rmap_iterator iter;
+ bool flush = false;
+
+ for_each_rmap_spte(rmap_head, &iter, sptep)
+ if (spte_ad_need_write_protect(*sptep))
+ flush |= spte_wrprot_for_clear_dirty(sptep);
+ else
+ flush |= spte_clear_dirty(sptep);
+
+ return flush;
+}
+
+/**
+ * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages
+ * @kvm: kvm instance
+ * @slot: slot to protect
+ * @gfn_offset: start of the BITS_PER_LONG pages we care about
+ * @mask: indicates which pages we should protect
+ *
+ * Used when we do not need to care about huge page mappings.
+ */
+static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ gfn_t gfn_offset, unsigned long mask)
+{
+ struct kvm_rmap_head *rmap_head;
+
+ if (is_tdp_mmu_enabled(kvm))
+ kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
+ slot->base_gfn + gfn_offset, mask, true);
+
+ if (!kvm_memslots_have_rmaps(kvm))
+ return;
+
+ while (mask) {
+ rmap_head = gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
+ PG_LEVEL_4K, slot);
+ rmap_write_protect(rmap_head, false);
+
+ /* clear the first set bit */
+ mask &= mask - 1;
+ }
+}
+
+/**
+ * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages, or write
+ * protect the page if the D-bit isn't supported.
+ * @kvm: kvm instance
+ * @slot: slot to clear D-bit
+ * @gfn_offset: start of the BITS_PER_LONG pages we care about
+ * @mask: indicates which pages we should clear D-bit
+ *
+ * Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap.
+ */
+static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ gfn_t gfn_offset, unsigned long mask)
+{
+ struct kvm_rmap_head *rmap_head;
+
+ if (is_tdp_mmu_enabled(kvm))
+ kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
+ slot->base_gfn + gfn_offset, mask, false);
+
+ if (!kvm_memslots_have_rmaps(kvm))
+ return;
+
+ while (mask) {
+ rmap_head = gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
+ PG_LEVEL_4K, slot);
+ __rmap_clear_dirty(kvm, rmap_head, slot);
+
+ /* clear the first set bit */
+ mask &= mask - 1;
+ }
+}
+
+/**
+ * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
+ * PT level pages.
+ *
+ * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to
+ * enable dirty logging for them.
+ *
+ * We need to care about huge page mappings: e.g. during dirty logging we may
+ * have such mappings.
+ */
+void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ gfn_t gfn_offset, unsigned long mask)
+{
+ /*
+ * Huge pages are NOT write protected when we start dirty logging in
+ * initially-all-set mode; must write protect them here so that they
+ * are split to 4K on the first write.
+ *
+ * The gfn_offset is guaranteed to be aligned to 64, but the base_gfn
+ * of memslot has no such restriction, so the range can cross two large
+ * pages.
+ */
+ if (kvm_dirty_log_manual_protect_and_init_set(kvm)) {
+ gfn_t start = slot->base_gfn + gfn_offset + __ffs(mask);
+ gfn_t end = slot->base_gfn + gfn_offset + __fls(mask);
+
+ if (READ_ONCE(eager_page_split))
+ kvm_mmu_try_split_huge_pages(kvm, slot, start, end, PG_LEVEL_4K);
+
+ kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M);
+
+ /* Cross two large pages? */
+ if (ALIGN(start << PAGE_SHIFT, PMD_SIZE) !=
+ ALIGN(end << PAGE_SHIFT, PMD_SIZE))
+ kvm_mmu_slot_gfn_write_protect(kvm, slot, end,
+ PG_LEVEL_2M);
+ }
+
+ /* Now handle 4K PTEs. */
+ if (kvm_x86_ops.cpu_dirty_log_size)
+ kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask);
+ else
+ kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
+}
+
+int kvm_cpu_dirty_log_size(void)
+{
+ return kvm_x86_ops.cpu_dirty_log_size;
+}
+
+bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
+ struct kvm_memory_slot *slot, u64 gfn,
+ int min_level)
+{
+ struct kvm_rmap_head *rmap_head;
+ int i;
+ bool write_protected = false;
+
+ if (kvm_memslots_have_rmaps(kvm)) {
+ for (i = min_level; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) {
+ rmap_head = gfn_to_rmap(gfn, i, slot);
+ write_protected |= rmap_write_protect(rmap_head, true);
+ }
+ }
+
+ if (is_tdp_mmu_enabled(kvm))
+ write_protected |=
+ kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn, min_level);
+
+ return write_protected;
+}
+
+static bool kvm_vcpu_write_protect_gfn(struct kvm_vcpu *vcpu, u64 gfn)
+{
+ struct kvm_memory_slot *slot;
+
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn, PG_LEVEL_4K);
+}
+
+static bool __kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
+ const struct kvm_memory_slot *slot)
+{
+ return kvm_zap_all_rmap_sptes(kvm, rmap_head);
+}
+
+static bool kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
+ struct kvm_memory_slot *slot, gfn_t gfn, int level,
+ pte_t unused)
+{
+ return __kvm_zap_rmap(kvm, rmap_head, slot);
+}
+
+static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
+ struct kvm_memory_slot *slot, gfn_t gfn, int level,
+ pte_t pte)
+{
+ u64 *sptep;
+ struct rmap_iterator iter;
+ bool need_flush = false;
+ u64 new_spte;
+ kvm_pfn_t new_pfn;
+
+ WARN_ON(pte_huge(pte));
+ new_pfn = pte_pfn(pte);
+
+restart:
+ for_each_rmap_spte(rmap_head, &iter, sptep) {
+ rmap_printk("spte %p %llx gfn %llx (%d)\n",
+ sptep, *sptep, gfn, level);
+
+ need_flush = true;
+
+ if (pte_write(pte)) {
+ kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
+ goto restart;
+ } else {
+ new_spte = kvm_mmu_changed_pte_notifier_make_spte(
+ *sptep, new_pfn);
+
+ mmu_spte_clear_track_bits(kvm, sptep);
+ mmu_spte_set(sptep, new_spte);
+ }
+ }
+
+ if (need_flush && kvm_available_flush_tlb_with_range()) {
+ kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
+ return false;
+ }
+
+ return need_flush;
+}
+
+struct slot_rmap_walk_iterator {
+ /* input fields. */
+ const struct kvm_memory_slot *slot;
+ gfn_t start_gfn;
+ gfn_t end_gfn;
+ int start_level;
+ int end_level;
+
+ /* output fields. */
+ gfn_t gfn;
+ struct kvm_rmap_head *rmap;
+ int level;
+
+ /* private field. */
+ struct kvm_rmap_head *end_rmap;
+};
+
+static void
+rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level)
+{
+ iterator->level = level;
+ iterator->gfn = iterator->start_gfn;
+ iterator->rmap = gfn_to_rmap(iterator->gfn, level, iterator->slot);
+ iterator->end_rmap = gfn_to_rmap(iterator->end_gfn, level, iterator->slot);
+}
+
+static void
+slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator,
+ const struct kvm_memory_slot *slot, int start_level,
+ int end_level, gfn_t start_gfn, gfn_t end_gfn)
+{
+ iterator->slot = slot;
+ iterator->start_level = start_level;
+ iterator->end_level = end_level;
+ iterator->start_gfn = start_gfn;
+ iterator->end_gfn = end_gfn;
+
+ rmap_walk_init_level(iterator, iterator->start_level);
+}
+
+static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator)
+{
+ return !!iterator->rmap;
+}
+
+static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator)
+{
+ while (++iterator->rmap <= iterator->end_rmap) {
+ iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level));
+
+ if (iterator->rmap->val)
+ return;
+ }
+
+ if (++iterator->level > iterator->end_level) {
+ iterator->rmap = NULL;
+ return;
+ }
+
+ rmap_walk_init_level(iterator, iterator->level);
+}
+
+#define for_each_slot_rmap_range(_slot_, _start_level_, _end_level_, \
+ _start_gfn, _end_gfn, _iter_) \
+ for (slot_rmap_walk_init(_iter_, _slot_, _start_level_, \
+ _end_level_, _start_gfn, _end_gfn); \
+ slot_rmap_walk_okay(_iter_); \
+ slot_rmap_walk_next(_iter_))
+
+typedef bool (*rmap_handler_t)(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
+ struct kvm_memory_slot *slot, gfn_t gfn,
+ int level, pte_t pte);
+
+static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm,
+ struct kvm_gfn_range *range,
+ rmap_handler_t handler)
+{
+ struct slot_rmap_walk_iterator iterator;
+ bool ret = false;
+
+ for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL,
+ range->start, range->end - 1, &iterator)
+ ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn,
+ iterator.level, range->pte);
+
+ return ret;
+}
+
+bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+ bool flush = false;
+
+ if (kvm_memslots_have_rmaps(kvm))
+ flush = kvm_handle_gfn_range(kvm, range, kvm_zap_rmap);
+
+ if (is_tdp_mmu_enabled(kvm))
+ flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
+
+ return flush;
+}
+
+bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+ bool flush = false;
+
+ if (kvm_memslots_have_rmaps(kvm))
+ flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmap);
+
+ if (is_tdp_mmu_enabled(kvm))
+ flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range);
+
+ return flush;
+}
+
+static bool kvm_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
+ struct kvm_memory_slot *slot, gfn_t gfn, int level,
+ pte_t unused)
+{
+ u64 *sptep;
+ struct rmap_iterator iter;
+ int young = 0;
+
+ for_each_rmap_spte(rmap_head, &iter, sptep)
+ young |= mmu_spte_age(sptep);
+
+ return young;
+}
+
+static bool kvm_test_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
+ struct kvm_memory_slot *slot, gfn_t gfn,
+ int level, pte_t unused)
+{
+ u64 *sptep;
+ struct rmap_iterator iter;
+
+ for_each_rmap_spte(rmap_head, &iter, sptep)
+ if (is_accessed_spte(*sptep))
+ return true;
+ return false;
+}
+
+#define RMAP_RECYCLE_THRESHOLD 1000
+
+static void __rmap_add(struct kvm *kvm,
+ struct kvm_mmu_memory_cache *cache,
+ const struct kvm_memory_slot *slot,
+ u64 *spte, gfn_t gfn, unsigned int access)
+{
+ struct kvm_mmu_page *sp;
+ struct kvm_rmap_head *rmap_head;
+ int rmap_count;
+
+ sp = sptep_to_sp(spte);
+ kvm_mmu_page_set_translation(sp, spte_index(spte), gfn, access);
+ kvm_update_page_stats(kvm, sp->role.level, 1);
+
+ rmap_head = gfn_to_rmap(gfn, sp->role.level, slot);
+ rmap_count = pte_list_add(cache, spte, rmap_head);
+
+ if (rmap_count > kvm->stat.max_mmu_rmap_size)
+ kvm->stat.max_mmu_rmap_size = rmap_count;
+ if (rmap_count > RMAP_RECYCLE_THRESHOLD) {
+ kvm_zap_all_rmap_sptes(kvm, rmap_head);
+ kvm_flush_remote_tlbs_with_address(
+ kvm, sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level));
+ }
+}
+
+static void rmap_add(struct kvm_vcpu *vcpu, const struct kvm_memory_slot *slot,
+ u64 *spte, gfn_t gfn, unsigned int access)
+{
+ struct kvm_mmu_memory_cache *cache = &vcpu->arch.mmu_pte_list_desc_cache;
+
+ __rmap_add(vcpu->kvm, cache, slot, spte, gfn, access);
+}
+
+bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+ bool young = false;
+
+ if (kvm_memslots_have_rmaps(kvm))
+ young = kvm_handle_gfn_range(kvm, range, kvm_age_rmap);
+
+ if (is_tdp_mmu_enabled(kvm))
+ young |= kvm_tdp_mmu_age_gfn_range(kvm, range);
+
+ return young;
+}
+
+bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+ bool young = false;
+
+ if (kvm_memslots_have_rmaps(kvm))
+ young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmap);
+
+ if (is_tdp_mmu_enabled(kvm))
+ young |= kvm_tdp_mmu_test_age_gfn(kvm, range);
+
+ return young;
+}
+
+#ifdef MMU_DEBUG
+static int is_empty_shadow_page(u64 *spt)
+{
+ u64 *pos;
+ u64 *end;
+
+ for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
+ if (is_shadow_present_pte(*pos)) {
+ printk(KERN_ERR "%s: %p %llx\n", __func__,
+ pos, *pos);
+ return 0;
+ }
+ return 1;
+}
+#endif
+
+/*
+ * This value is the sum of all of the kvm instances's
+ * kvm->arch.n_used_mmu_pages values. We need a global,
+ * aggregate version in order to make the slab shrinker
+ * faster
+ */
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
+{
+ kvm->arch.n_used_mmu_pages += nr;
+ percpu_counter_add(&kvm_total_used_mmu_pages, nr);
+}
+
+static void kvm_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ kvm_mod_used_mmu_pages(kvm, +1);
+ kvm_account_pgtable_pages((void *)sp->spt, +1);
+}
+
+static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ kvm_mod_used_mmu_pages(kvm, -1);
+ kvm_account_pgtable_pages((void *)sp->spt, -1);
+}
+
+static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp)
+{
+ MMU_WARN_ON(!is_empty_shadow_page(sp->spt));
+ hlist_del(&sp->hash_link);
+ list_del(&sp->link);
+ free_page((unsigned long)sp->spt);
+ if (!sp->role.direct)
+ free_page((unsigned long)sp->shadowed_translation);
+ kmem_cache_free(mmu_page_header_cache, sp);
+}
+
+static unsigned kvm_page_table_hashfn(gfn_t gfn)
+{
+ return hash_64(gfn, KVM_MMU_HASH_SHIFT);
+}
+
+static void mmu_page_add_parent_pte(struct kvm_mmu_memory_cache *cache,
+ struct kvm_mmu_page *sp, u64 *parent_pte)
+{
+ if (!parent_pte)
+ return;
+
+ pte_list_add(cache, parent_pte, &sp->parent_ptes);
+}
+
+static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
+ u64 *parent_pte)
+{
+ pte_list_remove(parent_pte, &sp->parent_ptes);
+}
+
+static void drop_parent_pte(struct kvm_mmu_page *sp,
+ u64 *parent_pte)
+{
+ mmu_page_remove_parent_pte(sp, parent_pte);
+ mmu_spte_clear_no_track(parent_pte);
+}
+
+static void mark_unsync(u64 *spte);
+static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp)
+{
+ u64 *sptep;
+ struct rmap_iterator iter;
+
+ for_each_rmap_spte(&sp->parent_ptes, &iter, sptep) {
+ mark_unsync(sptep);
+ }
+}
+
+static void mark_unsync(u64 *spte)
+{
+ struct kvm_mmu_page *sp;
+
+ sp = sptep_to_sp(spte);
+ if (__test_and_set_bit(spte_index(spte), sp->unsync_child_bitmap))
+ return;
+ if (sp->unsync_children++)
+ return;
+ kvm_mmu_mark_parents_unsync(sp);
+}
+
+static int nonpaging_sync_page(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *sp)
+{
+ return -1;
+}
+
+#define KVM_PAGE_ARRAY_NR 16
+
+struct kvm_mmu_pages {
+ struct mmu_page_and_offset {
+ struct kvm_mmu_page *sp;
+ unsigned int idx;
+ } page[KVM_PAGE_ARRAY_NR];
+ unsigned int nr;
+};
+
+static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
+ int idx)
+{
+ int i;
+
+ if (sp->unsync)
+ for (i=0; i < pvec->nr; i++)
+ if (pvec->page[i].sp == sp)
+ return 0;
+
+ pvec->page[pvec->nr].sp = sp;
+ pvec->page[pvec->nr].idx = idx;
+ pvec->nr++;
+ return (pvec->nr == KVM_PAGE_ARRAY_NR);
+}
+
+static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx)
+{
+ --sp->unsync_children;
+ WARN_ON((int)sp->unsync_children < 0);
+ __clear_bit(idx, sp->unsync_child_bitmap);
+}
+
+static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
+ struct kvm_mmu_pages *pvec)
+{
+ int i, ret, nr_unsync_leaf = 0;
+
+ for_each_set_bit(i, sp->unsync_child_bitmap, 512) {
+ struct kvm_mmu_page *child;
+ u64 ent = sp->spt[i];
+
+ if (!is_shadow_present_pte(ent) || is_large_pte(ent)) {
+ clear_unsync_child_bit(sp, i);
+ continue;
+ }
+
+ child = to_shadow_page(ent & SPTE_BASE_ADDR_MASK);
+
+ if (child->unsync_children) {
+ if (mmu_pages_add(pvec, child, i))
+ return -ENOSPC;
+
+ ret = __mmu_unsync_walk(child, pvec);
+ if (!ret) {
+ clear_unsync_child_bit(sp, i);
+ continue;
+ } else if (ret > 0) {
+ nr_unsync_leaf += ret;
+ } else
+ return ret;
+ } else if (child->unsync) {
+ nr_unsync_leaf++;
+ if (mmu_pages_add(pvec, child, i))
+ return -ENOSPC;
+ } else
+ clear_unsync_child_bit(sp, i);
+ }
+
+ return nr_unsync_leaf;
+}
+
+#define INVALID_INDEX (-1)
+
+static int mmu_unsync_walk(struct kvm_mmu_page *sp,
+ struct kvm_mmu_pages *pvec)
+{
+ pvec->nr = 0;
+ if (!sp->unsync_children)
+ return 0;
+
+ mmu_pages_add(pvec, sp, INVALID_INDEX);
+ return __mmu_unsync_walk(sp, pvec);
+}
+
+static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ WARN_ON(!sp->unsync);
+ trace_kvm_mmu_sync_page(sp);
+ sp->unsync = 0;
+ --kvm->stat.mmu_unsync;
+}
+
+static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+ struct list_head *invalid_list);
+static void kvm_mmu_commit_zap_page(struct kvm *kvm,
+ struct list_head *invalid_list);
+
+static bool sp_has_gptes(struct kvm_mmu_page *sp)
+{
+ if (sp->role.direct)
+ return false;
+
+ if (sp->role.passthrough)
+ return false;
+
+ return true;
+}
+
+#define for_each_valid_sp(_kvm, _sp, _list) \
+ hlist_for_each_entry(_sp, _list, hash_link) \
+ if (is_obsolete_sp((_kvm), (_sp))) { \
+ } else
+
+#define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn) \
+ for_each_valid_sp(_kvm, _sp, \
+ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \
+ if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else
+
+static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+ struct list_head *invalid_list)
+{
+ int ret = vcpu->arch.mmu->sync_page(vcpu, sp);
+
+ if (ret < 0)
+ kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
+ return ret;
+}
+
+static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
+ struct list_head *invalid_list,
+ bool remote_flush)
+{
+ if (!remote_flush && list_empty(invalid_list))
+ return false;
+
+ if (!list_empty(invalid_list))
+ kvm_mmu_commit_zap_page(kvm, invalid_list);
+ else
+ kvm_flush_remote_tlbs(kvm);
+ return true;
+}
+
+static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ if (sp->role.invalid)
+ return true;
+
+ /* TDP MMU pages due not use the MMU generation. */
+ return !sp->tdp_mmu_page &&
+ unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
+}
+
+struct mmu_page_path {
+ struct kvm_mmu_page *parent[PT64_ROOT_MAX_LEVEL];
+ unsigned int idx[PT64_ROOT_MAX_LEVEL];
+};
+
+#define for_each_sp(pvec, sp, parents, i) \
+ for (i = mmu_pages_first(&pvec, &parents); \
+ i < pvec.nr && ({ sp = pvec.page[i].sp; 1;}); \
+ i = mmu_pages_next(&pvec, &parents, i))
+
+static int mmu_pages_next(struct kvm_mmu_pages *pvec,
+ struct mmu_page_path *parents,
+ int i)
+{
+ int n;
+
+ for (n = i+1; n < pvec->nr; n++) {
+ struct kvm_mmu_page *sp = pvec->page[n].sp;
+ unsigned idx = pvec->page[n].idx;
+ int level = sp->role.level;
+
+ parents->idx[level-1] = idx;
+ if (level == PG_LEVEL_4K)
+ break;
+
+ parents->parent[level-2] = sp;
+ }
+
+ return n;
+}
+
+static int mmu_pages_first(struct kvm_mmu_pages *pvec,
+ struct mmu_page_path *parents)
+{
+ struct kvm_mmu_page *sp;
+ int level;
+
+ if (pvec->nr == 0)
+ return 0;
+
+ WARN_ON(pvec->page[0].idx != INVALID_INDEX);
+
+ sp = pvec->page[0].sp;
+ level = sp->role.level;
+ WARN_ON(level == PG_LEVEL_4K);
+
+ parents->parent[level-2] = sp;
+
+ /* Also set up a sentinel. Further entries in pvec are all
+ * children of sp, so this element is never overwritten.
+ */
+ parents->parent[level-1] = NULL;
+ return mmu_pages_next(pvec, parents, 0);
+}
+
+static void mmu_pages_clear_parents(struct mmu_page_path *parents)
+{
+ struct kvm_mmu_page *sp;
+ unsigned int level = 0;
+
+ do {
+ unsigned int idx = parents->idx[level];
+ sp = parents->parent[level];
+ if (!sp)
+ return;
+
+ WARN_ON(idx == INVALID_INDEX);
+ clear_unsync_child_bit(sp, idx);
+ level++;
+ } while (!sp->unsync_children);
+}
+
+static int mmu_sync_children(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *parent, bool can_yield)
+{
+ int i;
+ struct kvm_mmu_page *sp;
+ struct mmu_page_path parents;
+ struct kvm_mmu_pages pages;
+ LIST_HEAD(invalid_list);
+ bool flush = false;
+
+ while (mmu_unsync_walk(parent, &pages)) {
+ bool protected = false;
+
+ for_each_sp(pages, sp, parents, i)
+ protected |= kvm_vcpu_write_protect_gfn(vcpu, sp->gfn);
+
+ if (protected) {
+ kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, true);
+ flush = false;
+ }
+
+ for_each_sp(pages, sp, parents, i) {
+ kvm_unlink_unsync_page(vcpu->kvm, sp);
+ flush |= kvm_sync_page(vcpu, sp, &invalid_list) > 0;
+ mmu_pages_clear_parents(&parents);
+ }
+ if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) {
+ kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, flush);
+ if (!can_yield) {
+ kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
+ return -EINTR;
+ }
+
+ cond_resched_rwlock_write(&vcpu->kvm->mmu_lock);
+ flush = false;
+ }
+ }
+
+ kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, flush);
+ return 0;
+}
+
+static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
+{
+ atomic_set(&sp->write_flooding_count, 0);
+}
+
+static void clear_sp_write_flooding_count(u64 *spte)
+{
+ __clear_sp_write_flooding_count(sptep_to_sp(spte));
+}
+
+/*
+ * The vCPU is required when finding indirect shadow pages; the shadow
+ * page may already exist and syncing it needs the vCPU pointer in
+ * order to read guest page tables. Direct shadow pages are never
+ * unsync, thus @vcpu can be NULL if @role.direct is true.
+ */
+static struct kvm_mmu_page *kvm_mmu_find_shadow_page(struct kvm *kvm,
+ struct kvm_vcpu *vcpu,
+ gfn_t gfn,
+ struct hlist_head *sp_list,
+ union kvm_mmu_page_role role)
+{
+ struct kvm_mmu_page *sp;
+ int ret;
+ int collisions = 0;
+ LIST_HEAD(invalid_list);
+
+ for_each_valid_sp(kvm, sp, sp_list) {
+ if (sp->gfn != gfn) {
+ collisions++;
+ continue;
+ }
+
+ if (sp->role.word != role.word) {
+ /*
+ * If the guest is creating an upper-level page, zap
+ * unsync pages for the same gfn. While it's possible
+ * the guest is using recursive page tables, in all
+ * likelihood the guest has stopped using the unsync
+ * page and is installing a completely unrelated page.
+ * Unsync pages must not be left as is, because the new
+ * upper-level page will be write-protected.
+ */
+ if (role.level > PG_LEVEL_4K && sp->unsync)
+ kvm_mmu_prepare_zap_page(kvm, sp,
+ &invalid_list);
+ continue;
+ }
+
+ /* unsync and write-flooding only apply to indirect SPs. */
+ if (sp->role.direct)
+ goto out;
+
+ if (sp->unsync) {
+ if (KVM_BUG_ON(!vcpu, kvm))
+ break;
+
+ /*
+ * The page is good, but is stale. kvm_sync_page does
+ * get the latest guest state, but (unlike mmu_unsync_children)
+ * it doesn't write-protect the page or mark it synchronized!
+ * This way the validity of the mapping is ensured, but the
+ * overhead of write protection is not incurred until the
+ * guest invalidates the TLB mapping. This allows multiple
+ * SPs for a single gfn to be unsync.
+ *
+ * If the sync fails, the page is zapped. If so, break
+ * in order to rebuild it.
+ */
+ ret = kvm_sync_page(vcpu, sp, &invalid_list);
+ if (ret < 0)
+ break;
+
+ WARN_ON(!list_empty(&invalid_list));
+ if (ret > 0)
+ kvm_flush_remote_tlbs(kvm);
+ }
+
+ __clear_sp_write_flooding_count(sp);
+
+ goto out;
+ }
+
+ sp = NULL;
+ ++kvm->stat.mmu_cache_miss;
+
+out:
+ kvm_mmu_commit_zap_page(kvm, &invalid_list);
+
+ if (collisions > kvm->stat.max_mmu_page_hash_collisions)
+ kvm->stat.max_mmu_page_hash_collisions = collisions;
+ return sp;
+}
+
+/* Caches used when allocating a new shadow page. */
+struct shadow_page_caches {
+ struct kvm_mmu_memory_cache *page_header_cache;
+ struct kvm_mmu_memory_cache *shadow_page_cache;
+ struct kvm_mmu_memory_cache *shadowed_info_cache;
+};
+
+static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm,
+ struct shadow_page_caches *caches,
+ gfn_t gfn,
+ struct hlist_head *sp_list,
+ union kvm_mmu_page_role role)
+{
+ struct kvm_mmu_page *sp;
+
+ sp = kvm_mmu_memory_cache_alloc(caches->page_header_cache);
+ sp->spt = kvm_mmu_memory_cache_alloc(caches->shadow_page_cache);
+ if (!role.direct)
+ sp->shadowed_translation = kvm_mmu_memory_cache_alloc(caches->shadowed_info_cache);
+
+ set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
+
+ /*
+ * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages()
+ * depends on valid pages being added to the head of the list. See
+ * comments in kvm_zap_obsolete_pages().
+ */
+ sp->mmu_valid_gen = kvm->arch.mmu_valid_gen;
+ list_add(&sp->link, &kvm->arch.active_mmu_pages);
+ kvm_account_mmu_page(kvm, sp);
+
+ sp->gfn = gfn;
+ sp->role = role;
+ hlist_add_head(&sp->hash_link, sp_list);
+ if (sp_has_gptes(sp))
+ account_shadowed(kvm, sp);
+
+ return sp;
+}
+
+/* Note, @vcpu may be NULL if @role.direct is true; see kvm_mmu_find_shadow_page. */
+static struct kvm_mmu_page *__kvm_mmu_get_shadow_page(struct kvm *kvm,
+ struct kvm_vcpu *vcpu,
+ struct shadow_page_caches *caches,
+ gfn_t gfn,
+ union kvm_mmu_page_role role)
+{
+ struct hlist_head *sp_list;
+ struct kvm_mmu_page *sp;
+ bool created = false;
+
+ sp_list = &kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)];
+
+ sp = kvm_mmu_find_shadow_page(kvm, vcpu, gfn, sp_list, role);
+ if (!sp) {
+ created = true;
+ sp = kvm_mmu_alloc_shadow_page(kvm, caches, gfn, sp_list, role);
+ }
+
+ trace_kvm_mmu_get_page(sp, created);
+ return sp;
+}
+
+static struct kvm_mmu_page *kvm_mmu_get_shadow_page(struct kvm_vcpu *vcpu,
+ gfn_t gfn,
+ union kvm_mmu_page_role role)
+{
+ struct shadow_page_caches caches = {
+ .page_header_cache = &vcpu->arch.mmu_page_header_cache,
+ .shadow_page_cache = &vcpu->arch.mmu_shadow_page_cache,
+ .shadowed_info_cache = &vcpu->arch.mmu_shadowed_info_cache,
+ };
+
+ return __kvm_mmu_get_shadow_page(vcpu->kvm, vcpu, &caches, gfn, role);
+}
+
+static union kvm_mmu_page_role kvm_mmu_child_role(u64 *sptep, bool direct,
+ unsigned int access)
+{
+ struct kvm_mmu_page *parent_sp = sptep_to_sp(sptep);
+ union kvm_mmu_page_role role;
+
+ role = parent_sp->role;
+ role.level--;
+ role.access = access;
+ role.direct = direct;
+ role.passthrough = 0;
+
+ /*
+ * If the guest has 4-byte PTEs then that means it's using 32-bit,
+ * 2-level, non-PAE paging. KVM shadows such guests with PAE paging
+ * (i.e. 8-byte PTEs). The difference in PTE size means that KVM must
+ * shadow each guest page table with multiple shadow page tables, which
+ * requires extra bookkeeping in the role.
+ *
+ * Specifically, to shadow the guest's page directory (which covers a
+ * 4GiB address space), KVM uses 4 PAE page directories, each mapping
+ * 1GiB of the address space. @role.quadrant encodes which quarter of
+ * the address space each maps.
+ *
+ * To shadow the guest's page tables (which each map a 4MiB region), KVM
+ * uses 2 PAE page tables, each mapping a 2MiB region. For these,
+ * @role.quadrant encodes which half of the region they map.
+ *
+ * Concretely, a 4-byte PDE consumes bits 31:22, while an 8-byte PDE
+ * consumes bits 29:21. To consume bits 31:30, KVM's uses 4 shadow
+ * PDPTEs; those 4 PAE page directories are pre-allocated and their
+ * quadrant is assigned in mmu_alloc_root(). A 4-byte PTE consumes
+ * bits 21:12, while an 8-byte PTE consumes bits 20:12. To consume
+ * bit 21 in the PTE (the child here), KVM propagates that bit to the
+ * quadrant, i.e. sets quadrant to '0' or '1'. The parent 8-byte PDE
+ * covers bit 21 (see above), thus the quadrant is calculated from the
+ * _least_ significant bit of the PDE index.
+ */
+ if (role.has_4_byte_gpte) {
+ WARN_ON_ONCE(role.level != PG_LEVEL_4K);
+ role.quadrant = spte_index(sptep) & 1;
+ }
+
+ return role;
+}
+
+static struct kvm_mmu_page *kvm_mmu_get_child_sp(struct kvm_vcpu *vcpu,
+ u64 *sptep, gfn_t gfn,
+ bool direct, unsigned int access)
+{
+ union kvm_mmu_page_role role;
+
+ if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep))
+ return ERR_PTR(-EEXIST);
+
+ role = kvm_mmu_child_role(sptep, direct, access);
+ return kvm_mmu_get_shadow_page(vcpu, gfn, role);
+}
+
+static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterator,
+ struct kvm_vcpu *vcpu, hpa_t root,
+ u64 addr)
+{
+ iterator->addr = addr;
+ iterator->shadow_addr = root;
+ iterator->level = vcpu->arch.mmu->root_role.level;
+
+ if (iterator->level >= PT64_ROOT_4LEVEL &&
+ vcpu->arch.mmu->cpu_role.base.level < PT64_ROOT_4LEVEL &&
+ !vcpu->arch.mmu->root_role.direct)
+ iterator->level = PT32E_ROOT_LEVEL;
+
+ if (iterator->level == PT32E_ROOT_LEVEL) {
+ /*
+ * prev_root is currently only used for 64-bit hosts. So only
+ * the active root_hpa is valid here.
+ */
+ BUG_ON(root != vcpu->arch.mmu->root.hpa);
+
+ iterator->shadow_addr
+ = vcpu->arch.mmu->pae_root[(addr >> 30) & 3];
+ iterator->shadow_addr &= SPTE_BASE_ADDR_MASK;
+ --iterator->level;
+ if (!iterator->shadow_addr)
+ iterator->level = 0;
+ }
+}
+
+static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
+ struct kvm_vcpu *vcpu, u64 addr)
+{
+ shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu->root.hpa,
+ addr);
+}
+
+static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator)
+{
+ if (iterator->level < PG_LEVEL_4K)
+ return false;
+
+ iterator->index = SPTE_INDEX(iterator->addr, iterator->level);
+ iterator->sptep = ((u64 *)__va(iterator->shadow_addr)) + iterator->index;
+ return true;
+}
+
+static void __shadow_walk_next(struct kvm_shadow_walk_iterator *iterator,
+ u64 spte)
+{
+ if (!is_shadow_present_pte(spte) || is_last_spte(spte, iterator->level)) {
+ iterator->level = 0;
+ return;
+ }
+
+ iterator->shadow_addr = spte & SPTE_BASE_ADDR_MASK;
+ --iterator->level;
+}
+
+static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator)
+{
+ __shadow_walk_next(iterator, *iterator->sptep);
+}
+
+static void __link_shadow_page(struct kvm *kvm,
+ struct kvm_mmu_memory_cache *cache, u64 *sptep,
+ struct kvm_mmu_page *sp, bool flush)
+{
+ u64 spte;
+
+ BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
+
+ /*
+ * If an SPTE is present already, it must be a leaf and therefore
+ * a large one. Drop it, and flush the TLB if needed, before
+ * installing sp.
+ */
+ if (is_shadow_present_pte(*sptep))
+ drop_large_spte(kvm, sptep, flush);
+
+ spte = make_nonleaf_spte(sp->spt, sp_ad_disabled(sp));
+
+ mmu_spte_set(sptep, spte);
+
+ mmu_page_add_parent_pte(cache, sp, sptep);
+
+ if (sp->unsync_children || sp->unsync)
+ mark_unsync(sptep);
+}
+
+static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
+ struct kvm_mmu_page *sp)
+{
+ __link_shadow_page(vcpu->kvm, &vcpu->arch.mmu_pte_list_desc_cache, sptep, sp, true);
+}
+
+static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
+ unsigned direct_access)
+{
+ if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) {
+ struct kvm_mmu_page *child;
+
+ /*
+ * For the direct sp, if the guest pte's dirty bit
+ * changed form clean to dirty, it will corrupt the
+ * sp's access: allow writable in the read-only sp,
+ * so we should update the spte at this point to get
+ * a new sp with the correct access.
+ */
+ child = to_shadow_page(*sptep & SPTE_BASE_ADDR_MASK);
+ if (child->role.access == direct_access)
+ return;
+
+ drop_parent_pte(child, sptep);
+ kvm_flush_remote_tlbs_with_address(vcpu->kvm, child->gfn, 1);
+ }
+}
+
+/* Returns the number of zapped non-leaf child shadow pages. */
+static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
+ u64 *spte, struct list_head *invalid_list)
+{
+ u64 pte;
+ struct kvm_mmu_page *child;
+
+ pte = *spte;
+ if (is_shadow_present_pte(pte)) {
+ if (is_last_spte(pte, sp->role.level)) {
+ drop_spte(kvm, spte);
+ } else {
+ child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK);
+ drop_parent_pte(child, spte);
+
+ /*
+ * Recursively zap nested TDP SPs, parentless SPs are
+ * unlikely to be used again in the near future. This
+ * avoids retaining a large number of stale nested SPs.
+ */
+ if (tdp_enabled && invalid_list &&
+ child->role.guest_mode && !child->parent_ptes.val)
+ return kvm_mmu_prepare_zap_page(kvm, child,
+ invalid_list);
+ }
+ } else if (is_mmio_spte(pte)) {
+ mmu_spte_clear_no_track(spte);
+ }
+ return 0;
+}
+
+static int kvm_mmu_page_unlink_children(struct kvm *kvm,
+ struct kvm_mmu_page *sp,
+ struct list_head *invalid_list)
+{
+ int zapped = 0;
+ unsigned i;
+
+ for (i = 0; i < SPTE_ENT_PER_PAGE; ++i)
+ zapped += mmu_page_zap_pte(kvm, sp, sp->spt + i, invalid_list);
+
+ return zapped;
+}
+
+static void kvm_mmu_unlink_parents(struct kvm_mmu_page *sp)
+{
+ u64 *sptep;
+ struct rmap_iterator iter;
+
+ while ((sptep = rmap_get_first(&sp->parent_ptes, &iter)))
+ drop_parent_pte(sp, sptep);
+}
+
+static int mmu_zap_unsync_children(struct kvm *kvm,
+ struct kvm_mmu_page *parent,
+ struct list_head *invalid_list)
+{
+ int i, zapped = 0;
+ struct mmu_page_path parents;
+ struct kvm_mmu_pages pages;
+
+ if (parent->role.level == PG_LEVEL_4K)
+ return 0;
+
+ while (mmu_unsync_walk(parent, &pages)) {
+ struct kvm_mmu_page *sp;
+
+ for_each_sp(pages, sp, parents, i) {
+ kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
+ mmu_pages_clear_parents(&parents);
+ zapped++;
+ }
+ }
+
+ return zapped;
+}
+
+static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
+ struct kvm_mmu_page *sp,
+ struct list_head *invalid_list,
+ int *nr_zapped)
+{
+ bool list_unstable, zapped_root = false;
+
+ lockdep_assert_held_write(&kvm->mmu_lock);
+ trace_kvm_mmu_prepare_zap_page(sp);
+ ++kvm->stat.mmu_shadow_zapped;
+ *nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list);
+ *nr_zapped += kvm_mmu_page_unlink_children(kvm, sp, invalid_list);
+ kvm_mmu_unlink_parents(sp);
+
+ /* Zapping children means active_mmu_pages has become unstable. */
+ list_unstable = *nr_zapped;
+
+ if (!sp->role.invalid && sp_has_gptes(sp))
+ unaccount_shadowed(kvm, sp);
+
+ if (sp->unsync)
+ kvm_unlink_unsync_page(kvm, sp);
+ if (!sp->root_count) {
+ /* Count self */
+ (*nr_zapped)++;
+
+ /*
+ * Already invalid pages (previously active roots) are not on
+ * the active page list. See list_del() in the "else" case of
+ * !sp->root_count.
+ */
+ if (sp->role.invalid)
+ list_add(&sp->link, invalid_list);
+ else
+ list_move(&sp->link, invalid_list);
+ kvm_unaccount_mmu_page(kvm, sp);
+ } else {
+ /*
+ * Remove the active root from the active page list, the root
+ * will be explicitly freed when the root_count hits zero.
+ */
+ list_del(&sp->link);
+
+ /*
+ * Obsolete pages cannot be used on any vCPUs, see the comment
+ * in kvm_mmu_zap_all_fast(). Note, is_obsolete_sp() also
+ * treats invalid shadow pages as being obsolete.
+ */
+ zapped_root = !is_obsolete_sp(kvm, sp);
+ }
+
+ if (sp->lpage_disallowed)
+ unaccount_huge_nx_page(kvm, sp);
+
+ sp->role.invalid = 1;
+
+ /*
+ * Make the request to free obsolete roots after marking the root
+ * invalid, otherwise other vCPUs may not see it as invalid.
+ */
+ if (zapped_root)
+ kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_FREE_OBSOLETE_ROOTS);
+ return list_unstable;
+}
+
+static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+ struct list_head *invalid_list)
+{
+ int nr_zapped;
+
+ __kvm_mmu_prepare_zap_page(kvm, sp, invalid_list, &nr_zapped);
+ return nr_zapped;
+}
+
+static void kvm_mmu_commit_zap_page(struct kvm *kvm,
+ struct list_head *invalid_list)
+{
+ struct kvm_mmu_page *sp, *nsp;
+
+ if (list_empty(invalid_list))
+ return;
+
+ /*
+ * We need to make sure everyone sees our modifications to
+ * the page tables and see changes to vcpu->mode here. The barrier
+ * in the kvm_flush_remote_tlbs() achieves this. This pairs
+ * with vcpu_enter_guest and walk_shadow_page_lockless_begin/end.
+ *
+ * In addition, kvm_flush_remote_tlbs waits for all vcpus to exit
+ * guest mode and/or lockless shadow page table walks.
+ */
+ kvm_flush_remote_tlbs(kvm);
+
+ list_for_each_entry_safe(sp, nsp, invalid_list, link) {
+ WARN_ON(!sp->role.invalid || sp->root_count);
+ kvm_mmu_free_shadow_page(sp);
+ }
+}
+
+static unsigned long kvm_mmu_zap_oldest_mmu_pages(struct kvm *kvm,
+ unsigned long nr_to_zap)
+{
+ unsigned long total_zapped = 0;
+ struct kvm_mmu_page *sp, *tmp;
+ LIST_HEAD(invalid_list);
+ bool unstable;
+ int nr_zapped;
+
+ if (list_empty(&kvm->arch.active_mmu_pages))
+ return 0;
+
+restart:
+ list_for_each_entry_safe_reverse(sp, tmp, &kvm->arch.active_mmu_pages, link) {
+ /*
+ * Don't zap active root pages, the page itself can't be freed
+ * and zapping it will just force vCPUs to realloc and reload.
+ */
+ if (sp->root_count)
+ continue;
+
+ unstable = __kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list,
+ &nr_zapped);
+ total_zapped += nr_zapped;
+ if (total_zapped >= nr_to_zap)
+ break;
+
+ if (unstable)
+ goto restart;
+ }
+
+ kvm_mmu_commit_zap_page(kvm, &invalid_list);
+
+ kvm->stat.mmu_recycled += total_zapped;
+ return total_zapped;
+}
+
+static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
+{
+ if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
+ return kvm->arch.n_max_mmu_pages -
+ kvm->arch.n_used_mmu_pages;
+
+ return 0;
+}
+
+static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
+{
+ unsigned long avail = kvm_mmu_available_pages(vcpu->kvm);
+
+ if (likely(avail >= KVM_MIN_FREE_MMU_PAGES))
+ return 0;
+
+ kvm_mmu_zap_oldest_mmu_pages(vcpu->kvm, KVM_REFILL_PAGES - avail);
+
+ /*
+ * Note, this check is intentionally soft, it only guarantees that one
+ * page is available, while the caller may end up allocating as many as
+ * four pages, e.g. for PAE roots or for 5-level paging. Temporarily
+ * exceeding the (arbitrary by default) limit will not harm the host,
+ * being too aggressive may unnecessarily kill the guest, and getting an
+ * exact count is far more trouble than it's worth, especially in the
+ * page fault paths.
+ */
+ if (!kvm_mmu_available_pages(vcpu->kvm))
+ return -ENOSPC;
+ return 0;
+}
+
+/*
+ * Changing the number of mmu pages allocated to the vm
+ * Note: if goal_nr_mmu_pages is too small, you will get dead lock
+ */
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
+{
+ write_lock(&kvm->mmu_lock);
+
+ if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) {
+ kvm_mmu_zap_oldest_mmu_pages(kvm, kvm->arch.n_used_mmu_pages -
+ goal_nr_mmu_pages);
+
+ goal_nr_mmu_pages = kvm->arch.n_used_mmu_pages;
+ }
+
+ kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages;
+
+ write_unlock(&kvm->mmu_lock);
+}
+
+int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
+{
+ struct kvm_mmu_page *sp;
+ LIST_HEAD(invalid_list);
+ int r;
+
+ pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
+ r = 0;
+ write_lock(&kvm->mmu_lock);
+ for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) {
+ pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
+ sp->role.word);
+ r = 1;
+ kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
+ }
+ kvm_mmu_commit_zap_page(kvm, &invalid_list);
+ write_unlock(&kvm->mmu_lock);
+
+ return r;
+}
+
+static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
+{
+ gpa_t gpa;
+ int r;
+
+ if (vcpu->arch.mmu->root_role.direct)
+ return 0;
+
+ gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
+
+ r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+
+ return r;
+}
+
+static void kvm_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ trace_kvm_mmu_unsync_page(sp);
+ ++kvm->stat.mmu_unsync;
+ sp->unsync = 1;
+
+ kvm_mmu_mark_parents_unsync(sp);
+}
+
+/*
+ * Attempt to unsync any shadow pages that can be reached by the specified gfn,
+ * KVM is creating a writable mapping for said gfn. Returns 0 if all pages
+ * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must
+ * be write-protected.
+ */
+int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
+ gfn_t gfn, bool can_unsync, bool prefetch)
+{
+ struct kvm_mmu_page *sp;
+ bool locked = false;
+
+ /*
+ * Force write-protection if the page is being tracked. Note, the page
+ * track machinery is used to write-protect upper-level shadow pages,
+ * i.e. this guards the role.level == 4K assertion below!
+ */
+ if (kvm_slot_page_track_is_active(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE))
+ return -EPERM;
+
+ /*
+ * The page is not write-tracked, mark existing shadow pages unsync
+ * unless KVM is synchronizing an unsync SP (can_unsync = false). In
+ * that case, KVM must complete emulation of the guest TLB flush before
+ * allowing shadow pages to become unsync (writable by the guest).
+ */
+ for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) {
+ if (!can_unsync)
+ return -EPERM;
+
+ if (sp->unsync)
+ continue;
+
+ if (prefetch)
+ return -EEXIST;
+
+ /*
+ * TDP MMU page faults require an additional spinlock as they
+ * run with mmu_lock held for read, not write, and the unsync
+ * logic is not thread safe. Take the spinklock regardless of
+ * the MMU type to avoid extra conditionals/parameters, there's
+ * no meaningful penalty if mmu_lock is held for write.
+ */
+ if (!locked) {
+ locked = true;
+ spin_lock(&kvm->arch.mmu_unsync_pages_lock);
+
+ /*
+ * Recheck after taking the spinlock, a different vCPU
+ * may have since marked the page unsync. A false
+ * positive on the unprotected check above is not
+ * possible as clearing sp->unsync _must_ hold mmu_lock
+ * for write, i.e. unsync cannot transition from 0->1
+ * while this CPU holds mmu_lock for read (or write).
+ */
+ if (READ_ONCE(sp->unsync))
+ continue;
+ }
+
+ WARN_ON(sp->role.level != PG_LEVEL_4K);
+ kvm_unsync_page(kvm, sp);
+ }
+ if (locked)
+ spin_unlock(&kvm->arch.mmu_unsync_pages_lock);
+
+ /*
+ * We need to ensure that the marking of unsync pages is visible
+ * before the SPTE is updated to allow writes because
+ * kvm_mmu_sync_roots() checks the unsync flags without holding
+ * the MMU lock and so can race with this. If the SPTE was updated
+ * before the page had been marked as unsync-ed, something like the
+ * following could happen:
+ *
+ * CPU 1 CPU 2
+ * ---------------------------------------------------------------------
+ * 1.2 Host updates SPTE
+ * to be writable
+ * 2.1 Guest writes a GPTE for GVA X.
+ * (GPTE being in the guest page table shadowed
+ * by the SP from CPU 1.)
+ * This reads SPTE during the page table walk.
+ * Since SPTE.W is read as 1, there is no
+ * fault.
+ *
+ * 2.2 Guest issues TLB flush.
+ * That causes a VM Exit.
+ *
+ * 2.3 Walking of unsync pages sees sp->unsync is
+ * false and skips the page.
+ *
+ * 2.4 Guest accesses GVA X.
+ * Since the mapping in the SP was not updated,
+ * so the old mapping for GVA X incorrectly
+ * gets used.
+ * 1.1 Host marks SP
+ * as unsync
+ * (sp->unsync = true)
+ *
+ * The write barrier below ensures that 1.1 happens before 1.2 and thus
+ * the situation in 2.4 does not arise. It pairs with the read barrier
+ * in is_unsync_root(), placed between 2.1's load of SPTE.W and 2.3.
+ */
+ smp_wmb();
+
+ return 0;
+}
+
+static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
+ u64 *sptep, unsigned int pte_access, gfn_t gfn,
+ kvm_pfn_t pfn, struct kvm_page_fault *fault)
+{
+ struct kvm_mmu_page *sp = sptep_to_sp(sptep);
+ int level = sp->role.level;
+ int was_rmapped = 0;
+ int ret = RET_PF_FIXED;
+ bool flush = false;
+ bool wrprot;
+ u64 spte;
+
+ /* Prefetching always gets a writable pfn. */
+ bool host_writable = !fault || fault->map_writable;
+ bool prefetch = !fault || fault->prefetch;
+ bool write_fault = fault && fault->write;
+
+ pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
+ *sptep, write_fault, gfn);
+
+ if (unlikely(is_noslot_pfn(pfn))) {
+ vcpu->stat.pf_mmio_spte_created++;
+ mark_mmio_spte(vcpu, sptep, gfn, pte_access);
+ return RET_PF_EMULATE;
+ }
+
+ if (is_shadow_present_pte(*sptep)) {
+ /*
+ * If we overwrite a PTE page pointer with a 2MB PMD, unlink
+ * the parent of the now unreachable PTE.
+ */
+ if (level > PG_LEVEL_4K && !is_large_pte(*sptep)) {
+ struct kvm_mmu_page *child;
+ u64 pte = *sptep;
+
+ child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK);
+ drop_parent_pte(child, sptep);
+ flush = true;
+ } else if (pfn != spte_to_pfn(*sptep)) {
+ pgprintk("hfn old %llx new %llx\n",
+ spte_to_pfn(*sptep), pfn);
+ drop_spte(vcpu->kvm, sptep);
+ flush = true;
+ } else
+ was_rmapped = 1;
+ }
+
+ wrprot = make_spte(vcpu, sp, slot, pte_access, gfn, pfn, *sptep, prefetch,
+ true, host_writable, &spte);
+
+ if (*sptep == spte) {
+ ret = RET_PF_SPURIOUS;
+ } else {
+ flush |= mmu_spte_update(sptep, spte);
+ trace_kvm_mmu_set_spte(level, gfn, sptep);
+ }
+
+ if (wrprot) {
+ if (write_fault)
+ ret = RET_PF_EMULATE;
+ }
+
+ if (flush)
+ kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn,
+ KVM_PAGES_PER_HPAGE(level));
+
+ pgprintk("%s: setting spte %llx\n", __func__, *sptep);
+
+ if (!was_rmapped) {
+ WARN_ON_ONCE(ret == RET_PF_SPURIOUS);
+ rmap_add(vcpu, slot, sptep, gfn, pte_access);
+ } else {
+ /* Already rmapped but the pte_access bits may have changed. */
+ kvm_mmu_page_set_access(sp, spte_index(sptep), pte_access);
+ }
+
+ return ret;
+}
+
+static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *sp,
+ u64 *start, u64 *end)
+{
+ struct page *pages[PTE_PREFETCH_NUM];
+ struct kvm_memory_slot *slot;
+ unsigned int access = sp->role.access;
+ int i, ret;
+ gfn_t gfn;
+
+ gfn = kvm_mmu_page_get_gfn(sp, spte_index(start));
+ slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK);
+ if (!slot)
+ return -1;
+
+ ret = gfn_to_page_many_atomic(slot, gfn, pages, end - start);
+ if (ret <= 0)
+ return -1;
+
+ for (i = 0; i < ret; i++, gfn++, start++) {
+ mmu_set_spte(vcpu, slot, start, access, gfn,
+ page_to_pfn(pages[i]), NULL);
+ put_page(pages[i]);
+ }
+
+ return 0;
+}
+
+static void __direct_pte_prefetch(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *sp, u64 *sptep)
+{
+ u64 *spte, *start = NULL;
+ int i;
+
+ WARN_ON(!sp->role.direct);
+
+ i = spte_index(sptep) & ~(PTE_PREFETCH_NUM - 1);
+ spte = sp->spt + i;
+
+ for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) {
+ if (is_shadow_present_pte(*spte) || spte == sptep) {
+ if (!start)
+ continue;
+ if (direct_pte_prefetch_many(vcpu, sp, start, spte) < 0)
+ return;
+ start = NULL;
+ } else if (!start)
+ start = spte;
+ }
+ if (start)
+ direct_pte_prefetch_many(vcpu, sp, start, spte);
+}
+
+static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
+{
+ struct kvm_mmu_page *sp;
+
+ sp = sptep_to_sp(sptep);
+
+ /*
+ * Without accessed bits, there's no way to distinguish between
+ * actually accessed translations and prefetched, so disable pte
+ * prefetch if accessed bits aren't available.
+ */
+ if (sp_ad_disabled(sp))
+ return;
+
+ if (sp->role.level > PG_LEVEL_4K)
+ return;
+
+ /*
+ * If addresses are being invalidated, skip prefetching to avoid
+ * accidentally prefetching those addresses.
+ */
+ if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
+ return;
+
+ __direct_pte_prefetch(vcpu, sp, sptep);
+}
+
+/*
+ * Lookup the mapping level for @gfn in the current mm.
+ *
+ * WARNING! Use of host_pfn_mapping_level() requires the caller and the end
+ * consumer to be tied into KVM's handlers for MMU notifier events!
+ *
+ * There are several ways to safely use this helper:
+ *
+ * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
+ * consuming it. In this case, mmu_lock doesn't need to be held during the
+ * lookup, but it does need to be held while checking the MMU notifier.
+ *
+ * - Hold mmu_lock AND ensure there is no in-progress MMU notifier invalidation
+ * event for the hva. This can be done by explicit checking the MMU notifier
+ * or by ensuring that KVM already has a valid mapping that covers the hva.
+ *
+ * - Do not use the result to install new mappings, e.g. use the host mapping
+ * level only to decide whether or not to zap an entry. In this case, it's
+ * not required to hold mmu_lock (though it's highly likely the caller will
+ * want to hold mmu_lock anyways, e.g. to modify SPTEs).
+ *
+ * Note! The lookup can still race with modifications to host page tables, but
+ * the above "rules" ensure KVM will not _consume_ the result of the walk if a
+ * race with the primary MMU occurs.
+ */
+static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
+ const struct kvm_memory_slot *slot)
+{
+ int level = PG_LEVEL_4K;
+ unsigned long hva;
+ unsigned long flags;
+ pgd_t pgd;
+ p4d_t p4d;
+ pud_t pud;
+ pmd_t pmd;
+
+ /*
+ * Note, using the already-retrieved memslot and __gfn_to_hva_memslot()
+ * is not solely for performance, it's also necessary to avoid the
+ * "writable" check in __gfn_to_hva_many(), which will always fail on
+ * read-only memslots due to gfn_to_hva() assuming writes. Earlier
+ * page fault steps have already verified the guest isn't writing a
+ * read-only memslot.
+ */
+ hva = __gfn_to_hva_memslot(slot, gfn);
+
+ /*
+ * Disable IRQs to prevent concurrent tear down of host page tables,
+ * e.g. if the primary MMU promotes a P*D to a huge page and then frees
+ * the original page table.
+ */
+ local_irq_save(flags);
+
+ /*
+ * Read each entry once. As above, a non-leaf entry can be promoted to
+ * a huge page _during_ this walk. Re-reading the entry could send the
+ * walk into the weeks, e.g. p*d_large() returns false (sees the old
+ * value) and then p*d_offset() walks into the target huge page instead
+ * of the old page table (sees the new value).
+ */
+ pgd = READ_ONCE(*pgd_offset(kvm->mm, hva));
+ if (pgd_none(pgd))
+ goto out;
+
+ p4d = READ_ONCE(*p4d_offset(&pgd, hva));
+ if (p4d_none(p4d) || !p4d_present(p4d))
+ goto out;
+
+ pud = READ_ONCE(*pud_offset(&p4d, hva));
+ if (pud_none(pud) || !pud_present(pud))
+ goto out;
+
+ if (pud_large(pud)) {
+ level = PG_LEVEL_1G;
+ goto out;
+ }
+
+ pmd = READ_ONCE(*pmd_offset(&pud, hva));
+ if (pmd_none(pmd) || !pmd_present(pmd))
+ goto out;
+
+ if (pmd_large(pmd))
+ level = PG_LEVEL_2M;
+
+out:
+ local_irq_restore(flags);
+ return level;
+}
+
+int kvm_mmu_max_mapping_level(struct kvm *kvm,
+ const struct kvm_memory_slot *slot, gfn_t gfn,
+ int max_level)
+{
+ struct kvm_lpage_info *linfo;
+ int host_level;
+
+ max_level = min(max_level, max_huge_page_level);
+ for ( ; max_level > PG_LEVEL_4K; max_level--) {
+ linfo = lpage_info_slot(gfn, slot, max_level);
+ if (!linfo->disallow_lpage)
+ break;
+ }
+
+ if (max_level == PG_LEVEL_4K)
+ return PG_LEVEL_4K;
+
+ host_level = host_pfn_mapping_level(kvm, gfn, slot);
+ return min(host_level, max_level);
+}
+
+void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+{
+ struct kvm_memory_slot *slot = fault->slot;
+ kvm_pfn_t mask;
+
+ fault->huge_page_disallowed = fault->exec && fault->nx_huge_page_workaround_enabled;
+
+ if (unlikely(fault->max_level == PG_LEVEL_4K))
+ return;
+
+ if (is_error_noslot_pfn(fault->pfn))
+ return;
+
+ if (kvm_slot_dirty_track_enabled(slot))
+ return;
+
+ /*
+ * Enforce the iTLB multihit workaround after capturing the requested
+ * level, which will be used to do precise, accurate accounting.
+ */
+ fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
+ fault->gfn, fault->max_level);
+ if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
+ return;
+
+ /*
+ * mmu_invalidate_retry() was successful and mmu_lock is held, so
+ * the pmd can't be split from under us.
+ */
+ fault->goal_level = fault->req_level;
+ mask = KVM_PAGES_PER_HPAGE(fault->goal_level) - 1;
+ VM_BUG_ON((fault->gfn & mask) != (fault->pfn & mask));
+ fault->pfn &= ~mask;
+}
+
+void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level)
+{
+ if (cur_level > PG_LEVEL_4K &&
+ cur_level == fault->goal_level &&
+ is_shadow_present_pte(spte) &&
+ !is_large_pte(spte)) {
+ /*
+ * A small SPTE exists for this pfn, but FNAME(fetch)
+ * and __direct_map would like to create a large PTE
+ * instead: just force them to go down another level,
+ * patching back for them into pfn the next 9 bits of
+ * the address.
+ */
+ u64 page_mask = KVM_PAGES_PER_HPAGE(cur_level) -
+ KVM_PAGES_PER_HPAGE(cur_level - 1);
+ fault->pfn |= fault->gfn & page_mask;
+ fault->goal_level--;
+ }
+}
+
+static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+{
+ struct kvm_shadow_walk_iterator it;
+ struct kvm_mmu_page *sp;
+ int ret;
+ gfn_t base_gfn = fault->gfn;
+
+ kvm_mmu_hugepage_adjust(vcpu, fault);
+
+ trace_kvm_mmu_spte_requested(fault);
+ for_each_shadow_entry(vcpu, fault->addr, it) {
+ /*
+ * We cannot overwrite existing page tables with an NX
+ * large page, as the leaf could be executable.
+ */
+ if (fault->nx_huge_page_workaround_enabled)
+ disallowed_hugepage_adjust(fault, *it.sptep, it.level);
+
+ base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+ if (it.level == fault->goal_level)
+ break;
+
+ sp = kvm_mmu_get_child_sp(vcpu, it.sptep, base_gfn, true, ACC_ALL);
+ if (sp == ERR_PTR(-EEXIST))
+ continue;
+
+ link_shadow_page(vcpu, it.sptep, sp);
+ if (fault->is_tdp && fault->huge_page_disallowed &&
+ fault->req_level >= it.level)
+ account_huge_nx_page(vcpu->kvm, sp);
+ }
+
+ if (WARN_ON_ONCE(it.level != fault->goal_level))
+ return -EFAULT;
+
+ ret = mmu_set_spte(vcpu, fault->slot, it.sptep, ACC_ALL,
+ base_gfn, fault->pfn, fault);
+ if (ret == RET_PF_SPURIOUS)
+ return ret;
+
+ direct_pte_prefetch(vcpu, it.sptep);
+ return ret;
+}
+
+static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk)
+{
+ send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk);
+}
+
+static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
+{
+ /*
+ * Do not cache the mmio info caused by writing the readonly gfn
+ * into the spte otherwise read access on readonly gfn also can
+ * caused mmio page fault and treat it as mmio access.
+ */
+ if (pfn == KVM_PFN_ERR_RO_FAULT)
+ return RET_PF_EMULATE;
+
+ if (pfn == KVM_PFN_ERR_HWPOISON) {
+ kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current);
+ return RET_PF_RETRY;
+ }
+
+ return -EFAULT;
+}
+
+static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
+ unsigned int access)
+{
+ /* The pfn is invalid, report the error! */
+ if (unlikely(is_error_pfn(fault->pfn)))
+ return kvm_handle_bad_page(vcpu, fault->gfn, fault->pfn);
+
+ if (unlikely(!fault->slot)) {
+ gva_t gva = fault->is_tdp ? 0 : fault->addr;
+
+ vcpu_cache_mmio_info(vcpu, gva, fault->gfn,
+ access & shadow_mmio_access_mask);
+ /*
+ * If MMIO caching is disabled, emulate immediately without
+ * touching the shadow page tables as attempting to install an
+ * MMIO SPTE will just be an expensive nop. Do not cache MMIO
+ * whose gfn is greater than host.MAXPHYADDR, any guest that
+ * generates such gfns is running nested and is being tricked
+ * by L0 userspace (you can observe gfn > L1.MAXPHYADDR if
+ * and only if L1's MAXPHYADDR is inaccurate with respect to
+ * the hardware's).
+ */
+ if (unlikely(!enable_mmio_caching) ||
+ unlikely(fault->gfn > kvm_mmu_max_gfn()))
+ return RET_PF_EMULATE;
+ }
+
+ return RET_PF_CONTINUE;
+}
+
+static bool page_fault_can_be_fast(struct kvm_page_fault *fault)
+{
+ /*
+ * Page faults with reserved bits set, i.e. faults on MMIO SPTEs, only
+ * reach the common page fault handler if the SPTE has an invalid MMIO
+ * generation number. Refreshing the MMIO generation needs to go down
+ * the slow path. Note, EPT Misconfigs do NOT set the PRESENT flag!
+ */
+ if (fault->rsvd)
+ return false;
+
+ /*
+ * #PF can be fast if:
+ *
+ * 1. The shadow page table entry is not present and A/D bits are
+ * disabled _by KVM_, which could mean that the fault is potentially
+ * caused by access tracking (if enabled). If A/D bits are enabled
+ * by KVM, but disabled by L1 for L2, KVM is forced to disable A/D
+ * bits for L2 and employ access tracking, but the fast page fault
+ * mechanism only supports direct MMUs.
+ * 2. The shadow page table entry is present, the access is a write,
+ * and no reserved bits are set (MMIO SPTEs cannot be "fixed"), i.e.
+ * the fault was caused by a write-protection violation. If the
+ * SPTE is MMU-writable (determined later), the fault can be fixed
+ * by setting the Writable bit, which can be done out of mmu_lock.
+ */
+ if (!fault->present)
+ return !kvm_ad_enabled();
+
+ /*
+ * Note, instruction fetches and writes are mutually exclusive, ignore
+ * the "exec" flag.
+ */
+ return fault->write;
+}
+
+/*
+ * Returns true if the SPTE was fixed successfully. Otherwise,
+ * someone else modified the SPTE from its original value.
+ */
+static bool
+fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
+ u64 *sptep, u64 old_spte, u64 new_spte)
+{
+ /*
+ * Theoretically we could also set dirty bit (and flush TLB) here in
+ * order to eliminate unnecessary PML logging. See comments in
+ * set_spte. But fast_page_fault is very unlikely to happen with PML
+ * enabled, so we do not do this. This might result in the same GPA
+ * to be logged in PML buffer again when the write really happens, and
+ * eventually to be called by mark_page_dirty twice. But it's also no
+ * harm. This also avoids the TLB flush needed after setting dirty bit
+ * so non-PML cases won't be impacted.
+ *
+ * Compare with set_spte where instead shadow_dirty_mask is set.
+ */
+ if (!try_cmpxchg64(sptep, &old_spte, new_spte))
+ return false;
+
+ if (is_writable_pte(new_spte) && !is_writable_pte(old_spte))
+ mark_page_dirty_in_slot(vcpu->kvm, fault->slot, fault->gfn);
+
+ return true;
+}
+
+static 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;
+}
+
+/*
+ * Returns the last level spte pointer of the shadow page walk for the given
+ * gpa, and sets *spte to the spte value. This spte may be non-preset. If no
+ * walk could be performed, returns NULL and *spte does not contain valid data.
+ *
+ * Contract:
+ * - Must be called between walk_shadow_page_lockless_{begin,end}.
+ * - The returned sptep must not be used after walk_shadow_page_lockless_end.
+ */
+static u64 *fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gpa_t gpa, u64 *spte)
+{
+ struct kvm_shadow_walk_iterator iterator;
+ u64 old_spte;
+ u64 *sptep = NULL;
+
+ for_each_shadow_entry_lockless(vcpu, gpa, iterator, old_spte) {
+ sptep = iterator.sptep;
+ *spte = old_spte;
+ }
+
+ return sptep;
+}
+
+/*
+ * Returns one of RET_PF_INVALID, RET_PF_FIXED or RET_PF_SPURIOUS.
+ */
+static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+{
+ struct kvm_mmu_page *sp;
+ int ret = RET_PF_INVALID;
+ u64 spte = 0ull;
+ u64 *sptep = NULL;
+ uint retry_count = 0;
+
+ if (!page_fault_can_be_fast(fault))
+ return ret;
+
+ walk_shadow_page_lockless_begin(vcpu);
+
+ do {
+ u64 new_spte;
+
+ if (is_tdp_mmu(vcpu->arch.mmu))
+ sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->addr, &spte);
+ else
+ sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte);
+
+ if (!is_shadow_present_pte(spte))
+ break;
+
+ sp = sptep_to_sp(sptep);
+ if (!is_last_spte(spte, sp->role.level))
+ break;
+
+ /*
+ * Check whether the memory access that caused the fault would
+ * still cause it if it were to be performed right now. If not,
+ * then this is a spurious fault caused by TLB lazily flushed,
+ * or some other CPU has already fixed the PTE after the
+ * current CPU took the fault.
+ *
+ * Need not check the access of upper level table entries since
+ * they are always ACC_ALL.
+ */
+ if (is_access_allowed(fault, spte)) {
+ ret = RET_PF_SPURIOUS;
+ break;
+ }
+
+ new_spte = spte;
+
+ /*
+ * KVM only supports fixing page faults outside of MMU lock for
+ * direct MMUs, nested MMUs are always indirect, and KVM always
+ * uses A/D bits for non-nested MMUs. Thus, if A/D bits are
+ * enabled, the SPTE can't be an access-tracked SPTE.
+ */
+ if (unlikely(!kvm_ad_enabled()) && is_access_track_spte(spte))
+ new_spte = restore_acc_track_spte(new_spte);
+
+ /*
+ * To keep things simple, only SPTEs that are MMU-writable can
+ * be made fully writable outside of mmu_lock, e.g. only SPTEs
+ * that were write-protected for dirty-logging or access
+ * tracking are handled here. Don't bother checking if the
+ * SPTE is writable to prioritize running with A/D bits enabled.
+ * The is_access_allowed() check above handles the common case
+ * of the fault being spurious, and the SPTE is known to be
+ * shadow-present, i.e. except for access tracking restoration
+ * making the new SPTE writable, the check is wasteful.
+ */
+ if (fault->write && is_mmu_writable_spte(spte)) {
+ new_spte |= PT_WRITABLE_MASK;
+
+ /*
+ * Do not fix write-permission on the large spte when
+ * dirty logging is enabled. Since we only dirty the
+ * first page into the dirty-bitmap in
+ * fast_pf_fix_direct_spte(), other pages are missed
+ * if its slot has dirty logging enabled.
+ *
+ * Instead, we let the slow page fault path create a
+ * normal spte to fix the access.
+ */
+ if (sp->role.level > PG_LEVEL_4K &&
+ kvm_slot_dirty_track_enabled(fault->slot))
+ break;
+ }
+
+ /* Verify that the fault can be handled in the fast path */
+ if (new_spte == spte ||
+ !is_access_allowed(fault, new_spte))
+ break;
+
+ /*
+ * Currently, fast page fault only works for direct mapping
+ * since the gfn is not stable for indirect shadow page. See
+ * Documentation/virt/kvm/locking.rst to get more detail.
+ */
+ if (fast_pf_fix_direct_spte(vcpu, fault, sptep, spte, new_spte)) {
+ ret = RET_PF_FIXED;
+ break;
+ }
+
+ if (++retry_count > 4) {
+ printk_once(KERN_WARNING
+ "kvm: Fast #PF retrying more than 4 times.\n");
+ break;
+ }
+
+ } while (true);
+
+ trace_fast_page_fault(vcpu, fault, sptep, spte, ret);
+ walk_shadow_page_lockless_end(vcpu);
+
+ if (ret != RET_PF_INVALID)
+ vcpu->stat.pf_fast++;
+
+ return ret;
+}
+
+static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
+ struct list_head *invalid_list)
+{
+ struct kvm_mmu_page *sp;
+
+ if (!VALID_PAGE(*root_hpa))
+ return;
+
+ sp = to_shadow_page(*root_hpa & SPTE_BASE_ADDR_MASK);
+ if (WARN_ON(!sp))
+ return;
+
+ if (is_tdp_mmu_page(sp))
+ kvm_tdp_mmu_put_root(kvm, sp, false);
+ else if (!--sp->root_count && sp->role.invalid)
+ kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
+
+ *root_hpa = INVALID_PAGE;
+}
+
+/* roots_to_free must be some combination of the KVM_MMU_ROOT_* flags */
+void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu,
+ ulong roots_to_free)
+{
+ int i;
+ LIST_HEAD(invalid_list);
+ bool free_active_root;
+
+ BUILD_BUG_ON(KVM_MMU_NUM_PREV_ROOTS >= BITS_PER_LONG);
+
+ /* Before acquiring the MMU lock, see if we need to do any real work. */
+ free_active_root = (roots_to_free & KVM_MMU_ROOT_CURRENT)
+ && VALID_PAGE(mmu->root.hpa);
+
+ if (!free_active_root) {
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+ if ((roots_to_free & KVM_MMU_ROOT_PREVIOUS(i)) &&
+ VALID_PAGE(mmu->prev_roots[i].hpa))
+ break;
+
+ if (i == KVM_MMU_NUM_PREV_ROOTS)
+ return;
+ }
+
+ write_lock(&kvm->mmu_lock);
+
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+ if (roots_to_free & KVM_MMU_ROOT_PREVIOUS(i))
+ mmu_free_root_page(kvm, &mmu->prev_roots[i].hpa,
+ &invalid_list);
+
+ if (free_active_root) {
+ if (to_shadow_page(mmu->root.hpa)) {
+ mmu_free_root_page(kvm, &mmu->root.hpa, &invalid_list);
+ } else if (mmu->pae_root) {
+ for (i = 0; i < 4; ++i) {
+ if (!IS_VALID_PAE_ROOT(mmu->pae_root[i]))
+ continue;
+
+ mmu_free_root_page(kvm, &mmu->pae_root[i],
+ &invalid_list);
+ mmu->pae_root[i] = INVALID_PAE_ROOT;
+ }
+ }
+ mmu->root.hpa = INVALID_PAGE;
+ mmu->root.pgd = 0;
+ }
+
+ kvm_mmu_commit_zap_page(kvm, &invalid_list);
+ write_unlock(&kvm->mmu_lock);
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_free_roots);
+
+void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu)
+{
+ unsigned long roots_to_free = 0;
+ hpa_t root_hpa;
+ int i;
+
+ /*
+ * This should not be called while L2 is active, L2 can't invalidate
+ * _only_ its own roots, e.g. INVVPID unconditionally exits.
+ */
+ WARN_ON_ONCE(mmu->root_role.guest_mode);
+
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
+ root_hpa = mmu->prev_roots[i].hpa;
+ if (!VALID_PAGE(root_hpa))
+ continue;
+
+ if (!to_shadow_page(root_hpa) ||
+ to_shadow_page(root_hpa)->role.guest_mode)
+ roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
+ }
+
+ kvm_mmu_free_roots(kvm, mmu, roots_to_free);
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_free_guest_mode_roots);
+
+
+static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn)
+{
+ int ret = 0;
+
+ if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) {
+ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+ ret = 1;
+ }
+
+ return ret;
+}
+
+static hpa_t mmu_alloc_root(struct kvm_vcpu *vcpu, gfn_t gfn, int quadrant,
+ u8 level)
+{
+ union kvm_mmu_page_role role = vcpu->arch.mmu->root_role;
+ struct kvm_mmu_page *sp;
+
+ role.level = level;
+ role.quadrant = quadrant;
+
+ WARN_ON_ONCE(quadrant && !role.has_4_byte_gpte);
+ WARN_ON_ONCE(role.direct && role.has_4_byte_gpte);
+
+ sp = kvm_mmu_get_shadow_page(vcpu, gfn, role);
+ ++sp->root_count;
+
+ return __pa(sp->spt);
+}
+
+static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
+ u8 shadow_root_level = mmu->root_role.level;
+ hpa_t root;
+ unsigned i;
+ int r;
+
+ write_lock(&vcpu->kvm->mmu_lock);
+ r = make_mmu_pages_available(vcpu);
+ if (r < 0)
+ goto out_unlock;
+
+ if (is_tdp_mmu_enabled(vcpu->kvm)) {
+ root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu);
+ mmu->root.hpa = root;
+ } else if (shadow_root_level >= PT64_ROOT_4LEVEL) {
+ root = mmu_alloc_root(vcpu, 0, 0, shadow_root_level);
+ mmu->root.hpa = root;
+ } else if (shadow_root_level == PT32E_ROOT_LEVEL) {
+ if (WARN_ON_ONCE(!mmu->pae_root)) {
+ r = -EIO;
+ goto out_unlock;
+ }
+
+ for (i = 0; i < 4; ++i) {
+ WARN_ON_ONCE(IS_VALID_PAE_ROOT(mmu->pae_root[i]));
+
+ root = mmu_alloc_root(vcpu, i << (30 - PAGE_SHIFT), 0,
+ PT32_ROOT_LEVEL);
+ mmu->pae_root[i] = root | PT_PRESENT_MASK |
+ shadow_me_value;
+ }
+ mmu->root.hpa = __pa(mmu->pae_root);
+ } else {
+ WARN_ONCE(1, "Bad TDP root level = %d\n", shadow_root_level);
+ r = -EIO;
+ goto out_unlock;
+ }
+
+ /* root.pgd is ignored for direct MMUs. */
+ mmu->root.pgd = 0;
+out_unlock:
+ write_unlock(&vcpu->kvm->mmu_lock);
+ return r;
+}
+
+static int mmu_first_shadow_root_alloc(struct kvm *kvm)
+{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *slot;
+ int r = 0, i, bkt;
+
+ /*
+ * Check if this is the first shadow root being allocated before
+ * taking the lock.
+ */
+ if (kvm_shadow_root_allocated(kvm))
+ return 0;
+
+ mutex_lock(&kvm->slots_arch_lock);
+
+ /* Recheck, under the lock, whether this is the first shadow root. */
+ if (kvm_shadow_root_allocated(kvm))
+ goto out_unlock;
+
+ /*
+ * Check if anything actually needs to be allocated, e.g. all metadata
+ * will be allocated upfront if TDP is disabled.
+ */
+ if (kvm_memslots_have_rmaps(kvm) &&
+ kvm_page_track_write_tracking_enabled(kvm))
+ goto out_success;
+
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ slots = __kvm_memslots(kvm, i);
+ kvm_for_each_memslot(slot, bkt, slots) {
+ /*
+ * Both of these functions are no-ops if the target is
+ * already allocated, so unconditionally calling both
+ * is safe. 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
+ * KVM_RUN instead of killing the VM.
+ */
+ r = memslot_rmap_alloc(slot, slot->npages);
+ if (r)
+ goto out_unlock;
+ r = kvm_page_track_write_tracking_alloc(slot);
+ if (r)
+ goto out_unlock;
+ }
+ }
+
+ /*
+ * Ensure that shadow_root_allocated becomes true strictly after
+ * all the related pointers are set.
+ */
+out_success:
+ smp_store_release(&kvm->arch.shadow_root_allocated, true);
+
+out_unlock:
+ mutex_unlock(&kvm->slots_arch_lock);
+ return r;
+}
+
+static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
+ u64 pdptrs[4], pm_mask;
+ gfn_t root_gfn, root_pgd;
+ int quadrant, i, r;
+ hpa_t root;
+
+ root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu);
+ root_gfn = root_pgd >> PAGE_SHIFT;
+
+ if (mmu_check_root(vcpu, root_gfn))
+ return 1;
+
+ /*
+ * On SVM, reading PDPTRs might access guest memory, which might fault
+ * and thus might sleep. Grab the PDPTRs before acquiring mmu_lock.
+ */
+ if (mmu->cpu_role.base.level == PT32E_ROOT_LEVEL) {
+ for (i = 0; i < 4; ++i) {
+ pdptrs[i] = mmu->get_pdptr(vcpu, i);
+ if (!(pdptrs[i] & PT_PRESENT_MASK))
+ continue;
+
+ if (mmu_check_root(vcpu, pdptrs[i] >> PAGE_SHIFT))
+ return 1;
+ }
+ }
+
+ r = mmu_first_shadow_root_alloc(vcpu->kvm);
+ if (r)
+ return r;
+
+ write_lock(&vcpu->kvm->mmu_lock);
+ r = make_mmu_pages_available(vcpu);
+ if (r < 0)
+ goto out_unlock;
+
+ /*
+ * Do we shadow a long mode page table? If so we need to
+ * write-protect the guests page table root.
+ */
+ if (mmu->cpu_role.base.level >= PT64_ROOT_4LEVEL) {
+ root = mmu_alloc_root(vcpu, root_gfn, 0,
+ mmu->root_role.level);
+ mmu->root.hpa = root;
+ goto set_root_pgd;
+ }
+
+ if (WARN_ON_ONCE(!mmu->pae_root)) {
+ r = -EIO;
+ goto out_unlock;
+ }
+
+ /*
+ * We shadow a 32 bit page table. This may be a legacy 2-level
+ * or a PAE 3-level page table. In either case we need to be aware that
+ * the shadow page table may be a PAE or a long mode page table.
+ */
+ pm_mask = PT_PRESENT_MASK | shadow_me_value;
+ if (mmu->root_role.level >= PT64_ROOT_4LEVEL) {
+ pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK;
+
+ if (WARN_ON_ONCE(!mmu->pml4_root)) {
+ r = -EIO;
+ goto out_unlock;
+ }
+ mmu->pml4_root[0] = __pa(mmu->pae_root) | pm_mask;
+
+ if (mmu->root_role.level == PT64_ROOT_5LEVEL) {
+ if (WARN_ON_ONCE(!mmu->pml5_root)) {
+ r = -EIO;
+ goto out_unlock;
+ }
+ mmu->pml5_root[0] = __pa(mmu->pml4_root) | pm_mask;
+ }
+ }
+
+ for (i = 0; i < 4; ++i) {
+ WARN_ON_ONCE(IS_VALID_PAE_ROOT(mmu->pae_root[i]));
+
+ if (mmu->cpu_role.base.level == PT32E_ROOT_LEVEL) {
+ if (!(pdptrs[i] & PT_PRESENT_MASK)) {
+ mmu->pae_root[i] = INVALID_PAE_ROOT;
+ continue;
+ }
+ root_gfn = pdptrs[i] >> PAGE_SHIFT;
+ }
+
+ /*
+ * If shadowing 32-bit non-PAE page tables, each PAE page
+ * directory maps one quarter of the guest's non-PAE page
+ * directory. Othwerise each PAE page direct shadows one guest
+ * PAE page directory so that quadrant should be 0.
+ */
+ quadrant = (mmu->cpu_role.base.level == PT32_ROOT_LEVEL) ? i : 0;
+
+ root = mmu_alloc_root(vcpu, root_gfn, quadrant, PT32_ROOT_LEVEL);
+ mmu->pae_root[i] = root | pm_mask;
+ }
+
+ if (mmu->root_role.level == PT64_ROOT_5LEVEL)
+ mmu->root.hpa = __pa(mmu->pml5_root);
+ else if (mmu->root_role.level == PT64_ROOT_4LEVEL)
+ mmu->root.hpa = __pa(mmu->pml4_root);
+ else
+ mmu->root.hpa = __pa(mmu->pae_root);
+
+set_root_pgd:
+ mmu->root.pgd = root_pgd;
+out_unlock:
+ write_unlock(&vcpu->kvm->mmu_lock);
+
+ return r;
+}
+
+static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
+ bool need_pml5 = mmu->root_role.level > PT64_ROOT_4LEVEL;
+ u64 *pml5_root = NULL;
+ u64 *pml4_root = NULL;
+ u64 *pae_root;
+
+ /*
+ * When shadowing 32-bit or PAE NPT with 64-bit NPT, the PML4 and PDP
+ * tables are allocated and initialized at root creation as there is no
+ * equivalent level in the guest's NPT to shadow. Allocate the tables
+ * on demand, as running a 32-bit L1 VMM on 64-bit KVM is very rare.
+ */
+ if (mmu->root_role.direct ||
+ mmu->cpu_role.base.level >= PT64_ROOT_4LEVEL ||
+ mmu->root_role.level < PT64_ROOT_4LEVEL)
+ return 0;
+
+ /*
+ * NPT, the only paging mode that uses this horror, uses a fixed number
+ * of levels for the shadow page tables, e.g. all MMUs are 4-level or
+ * all MMus are 5-level. Thus, this can safely require that pml5_root
+ * is allocated if the other roots are valid and pml5 is needed, as any
+ * prior MMU would also have required pml5.
+ */
+ if (mmu->pae_root && mmu->pml4_root && (!need_pml5 || mmu->pml5_root))
+ return 0;
+
+ /*
+ * The special roots should always be allocated in concert. Yell and
+ * bail if KVM ends up in a state where only one of the roots is valid.
+ */
+ if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->pml4_root ||
+ (need_pml5 && mmu->pml5_root)))
+ return -EIO;
+
+ /*
+ * Unlike 32-bit NPT, the PDP table doesn't need to be in low mem, and
+ * doesn't need to be decrypted.
+ */
+ pae_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+ if (!pae_root)
+ return -ENOMEM;
+
+#ifdef CONFIG_X86_64
+ pml4_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+ if (!pml4_root)
+ goto err_pml4;
+
+ if (need_pml5) {
+ pml5_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+ if (!pml5_root)
+ goto err_pml5;
+ }
+#endif
+
+ mmu->pae_root = pae_root;
+ mmu->pml4_root = pml4_root;
+ mmu->pml5_root = pml5_root;
+
+ return 0;
+
+#ifdef CONFIG_X86_64
+err_pml5:
+ free_page((unsigned long)pml4_root);
+err_pml4:
+ free_page((unsigned long)pae_root);
+ return -ENOMEM;
+#endif
+}
+
+static bool is_unsync_root(hpa_t root)
+{
+ struct kvm_mmu_page *sp;
+
+ if (!VALID_PAGE(root))
+ return false;
+
+ /*
+ * The read barrier orders the CPU's read of SPTE.W during the page table
+ * walk before the reads of sp->unsync/sp->unsync_children here.
+ *
+ * Even if another CPU was marking the SP as unsync-ed simultaneously,
+ * any guest page table changes are not guaranteed to be visible anyway
+ * until this VCPU issues a TLB flush strictly after those changes are
+ * made. We only need to ensure that the other CPU sets these flags
+ * before any actual changes to the page tables are made. The comments
+ * in mmu_try_to_unsync_pages() describe what could go wrong if this
+ * requirement isn't satisfied.
+ */
+ smp_rmb();
+ sp = to_shadow_page(root);
+
+ /*
+ * PAE roots (somewhat arbitrarily) aren't backed by shadow pages, the
+ * PDPTEs for a given PAE root need to be synchronized individually.
+ */
+ if (WARN_ON_ONCE(!sp))
+ return false;
+
+ if (sp->unsync || sp->unsync_children)
+ return true;
+
+ return false;
+}
+
+void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
+{
+ int i;
+ struct kvm_mmu_page *sp;
+
+ if (vcpu->arch.mmu->root_role.direct)
+ return;
+
+ if (!VALID_PAGE(vcpu->arch.mmu->root.hpa))
+ return;
+
+ vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
+
+ if (vcpu->arch.mmu->cpu_role.base.level >= PT64_ROOT_4LEVEL) {
+ hpa_t root = vcpu->arch.mmu->root.hpa;
+ sp = to_shadow_page(root);
+
+ if (!is_unsync_root(root))
+ return;
+
+ write_lock(&vcpu->kvm->mmu_lock);
+ mmu_sync_children(vcpu, sp, true);
+ write_unlock(&vcpu->kvm->mmu_lock);
+ return;
+ }
+
+ write_lock(&vcpu->kvm->mmu_lock);
+
+ for (i = 0; i < 4; ++i) {
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
+
+ if (IS_VALID_PAE_ROOT(root)) {
+ root &= SPTE_BASE_ADDR_MASK;
+ sp = to_shadow_page(root);
+ mmu_sync_children(vcpu, sp, true);
+ }
+ }
+
+ write_unlock(&vcpu->kvm->mmu_lock);
+}
+
+void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu)
+{
+ unsigned long roots_to_free = 0;
+ int i;
+
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+ if (is_unsync_root(vcpu->arch.mmu->prev_roots[i].hpa))
+ roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
+
+ /* sync prev_roots by simply freeing them */
+ kvm_mmu_free_roots(vcpu->kvm, vcpu->arch.mmu, roots_to_free);
+}
+
+static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ gpa_t vaddr, u64 access,
+ struct x86_exception *exception)
+{
+ if (exception)
+ exception->error_code = 0;
+ return kvm_translate_gpa(vcpu, mmu, vaddr, access, exception);
+}
+
+static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+{
+ /*
+ * A nested guest cannot use the MMIO cache if it is using nested
+ * page tables, because cr2 is a nGPA while the cache stores GPAs.
+ */
+ if (mmu_is_nested(vcpu))
+ return false;
+
+ if (direct)
+ return vcpu_match_mmio_gpa(vcpu, addr);
+
+ return vcpu_match_mmio_gva(vcpu, addr);
+}
+
+/*
+ * Return the level of the lowest level SPTE added to sptes.
+ * That SPTE may be non-present.
+ *
+ * Must be called between walk_shadow_page_lockless_{begin,end}.
+ */
+static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level)
+{
+ struct kvm_shadow_walk_iterator iterator;
+ int leaf = -1;
+ u64 spte;
+
+ for (shadow_walk_init(&iterator, vcpu, addr),
+ *root_level = iterator.level;
+ shadow_walk_okay(&iterator);
+ __shadow_walk_next(&iterator, spte)) {
+ leaf = iterator.level;
+ spte = mmu_spte_get_lockless(iterator.sptep);
+
+ sptes[leaf] = spte;
+ }
+
+ return leaf;
+}
+
+/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
+static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
+{
+ u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
+ struct rsvd_bits_validate *rsvd_check;
+ int root, leaf, level;
+ bool reserved = false;
+
+ walk_shadow_page_lockless_begin(vcpu);
+
+ if (is_tdp_mmu(vcpu->arch.mmu))
+ leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
+ else
+ leaf = get_walk(vcpu, addr, sptes, &root);
+
+ walk_shadow_page_lockless_end(vcpu);
+
+ if (unlikely(leaf < 0)) {
+ *sptep = 0ull;
+ return reserved;
+ }
+
+ *sptep = sptes[leaf];
+
+ /*
+ * Skip reserved bits checks on the terminal leaf if it's not a valid
+ * SPTE. Note, this also (intentionally) skips MMIO SPTEs, which, by
+ * design, always have reserved bits set. The purpose of the checks is
+ * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs.
+ */
+ if (!is_shadow_present_pte(sptes[leaf]))
+ leaf++;
+
+ rsvd_check = &vcpu->arch.mmu->shadow_zero_check;
+
+ for (level = root; level >= leaf; level--)
+ reserved |= is_rsvd_spte(rsvd_check, sptes[level], level);
+
+ if (reserved) {
+ pr_err("%s: reserved bits set on MMU-present spte, addr 0x%llx, hierarchy:\n",
+ __func__, addr);
+ for (level = root; level >= leaf; level--)
+ pr_err("------ spte = 0x%llx level = %d, rsvd bits = 0x%llx",
+ sptes[level], level,
+ get_rsvd_bits(rsvd_check, sptes[level], level));
+ }
+
+ return reserved;
+}
+
+static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+{
+ u64 spte;
+ bool reserved;
+
+ if (mmio_info_in_cache(vcpu, addr, direct))
+ return RET_PF_EMULATE;
+
+ reserved = get_mmio_spte(vcpu, addr, &spte);
+ if (WARN_ON(reserved))
+ return -EINVAL;
+
+ if (is_mmio_spte(spte)) {
+ gfn_t gfn = get_mmio_spte_gfn(spte);
+ unsigned int access = get_mmio_spte_access(spte);
+
+ if (!check_mmio_spte(vcpu, spte))
+ return RET_PF_INVALID;
+
+ if (direct)
+ addr = 0;
+
+ trace_handle_mmio_page_fault(addr, gfn, access);
+ vcpu_cache_mmio_info(vcpu, addr, gfn, access);
+ return RET_PF_EMULATE;
+ }
+
+ /*
+ * If the page table is zapped by other cpus, let CPU fault again on
+ * the address.
+ */
+ return RET_PF_RETRY;
+}
+
+static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
+ struct kvm_page_fault *fault)
+{
+ if (unlikely(fault->rsvd))
+ return false;
+
+ if (!fault->present || !fault->write)
+ return false;
+
+ /*
+ * guest is writing the page which is write tracked which can
+ * not be fixed by page fault handler.
+ */
+ if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE))
+ return true;
+
+ return false;
+}
+
+static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
+{
+ struct kvm_shadow_walk_iterator iterator;
+ u64 spte;
+
+ walk_shadow_page_lockless_begin(vcpu);
+ for_each_shadow_entry_lockless(vcpu, addr, iterator, spte)
+ clear_sp_write_flooding_count(iterator.sptep);
+ walk_shadow_page_lockless_end(vcpu);
+}
+
+static u32 alloc_apf_token(struct kvm_vcpu *vcpu)
+{
+ /* make sure the token value is not 0 */
+ u32 id = vcpu->arch.apf.id;
+
+ if (id << 12 == 0)
+ vcpu->arch.apf.id = 1;
+
+ return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
+}
+
+static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+ gfn_t gfn)
+{
+ struct kvm_arch_async_pf arch;
+
+ arch.token = alloc_apf_token(vcpu);
+ arch.gfn = gfn;
+ arch.direct_map = vcpu->arch.mmu->root_role.direct;
+ arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu);
+
+ return kvm_setup_async_pf(vcpu, cr2_or_gpa,
+ kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
+}
+
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
+{
+ int r;
+
+ if ((vcpu->arch.mmu->root_role.direct != work->arch.direct_map) ||
+ work->wakeup_all)
+ return;
+
+ r = kvm_mmu_reload(vcpu);
+ if (unlikely(r))
+ return;
+
+ if (!vcpu->arch.mmu->root_role.direct &&
+ work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu))
+ return;
+
+ kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
+}
+
+static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+{
+ struct kvm_memory_slot *slot = fault->slot;
+ bool async;
+
+ /*
+ * Retry the page fault if the gfn hit a memslot that is being deleted
+ * or moved. This ensures any existing SPTEs for the old memslot will
+ * be zapped before KVM inserts a new MMIO SPTE for the gfn.
+ */
+ if (slot && (slot->flags & KVM_MEMSLOT_INVALID))
+ return RET_PF_RETRY;
+
+ if (!kvm_is_visible_memslot(slot)) {
+ /* Don't expose private memslots to L2. */
+ if (is_guest_mode(vcpu)) {
+ fault->slot = NULL;
+ fault->pfn = KVM_PFN_NOSLOT;
+ fault->map_writable = false;
+ return RET_PF_CONTINUE;
+ }
+ /*
+ * If the APIC access page exists but is disabled, go directly
+ * to emulation without caching the MMIO access or creating a
+ * MMIO SPTE. That way the cache doesn't need to be purged
+ * when the AVIC is re-enabled.
+ */
+ if (slot && slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT &&
+ !kvm_apicv_activated(vcpu->kvm))
+ return RET_PF_EMULATE;
+ }
+
+ async = false;
+ fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
+ fault->write, &fault->map_writable,
+ &fault->hva);
+ if (!async)
+ return RET_PF_CONTINUE; /* *pfn has correct page already */
+
+ if (!fault->prefetch && kvm_can_do_async_pf(vcpu)) {
+ trace_kvm_try_async_get_page(fault->addr, fault->gfn);
+ if (kvm_find_async_pf_gfn(vcpu, fault->gfn)) {
+ trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn);
+ kvm_make_request(KVM_REQ_APF_HALT, vcpu);
+ return RET_PF_RETRY;
+ } else if (kvm_arch_setup_async_pf(vcpu, fault->addr, fault->gfn)) {
+ return RET_PF_RETRY;
+ }
+ }
+
+ fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, NULL,
+ fault->write, &fault->map_writable,
+ &fault->hva);
+ return RET_PF_CONTINUE;
+}
+
+/*
+ * Returns true if the page fault is stale and needs to be retried, i.e. if the
+ * root was invalidated by a memslot update or a relevant mmu_notifier fired.
+ */
+static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
+ struct kvm_page_fault *fault,
+ unsigned long mmu_seq)
+{
+ struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa);
+
+ /* Special roots, e.g. pae_root, are not backed by shadow pages. */
+ if (sp && is_obsolete_sp(vcpu->kvm, sp))
+ return true;
+
+ /*
+ * Roots without an associated shadow page are considered invalid if
+ * there is a pending request to free obsolete roots. The request is
+ * only a hint that the current root _may_ be obsolete and needs to be
+ * reloaded, e.g. if the guest frees a PGD that KVM is tracking as a
+ * previous root, then __kvm_mmu_prepare_zap_page() signals all vCPUs
+ * to reload even if no vCPU is actively using the root.
+ */
+ if (!sp && kvm_test_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
+ return true;
+
+ return fault->slot &&
+ mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
+}
+
+static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+{
+ bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu);
+
+ unsigned long mmu_seq;
+ int r;
+
+ fault->gfn = fault->addr >> PAGE_SHIFT;
+ fault->slot = kvm_vcpu_gfn_to_memslot(vcpu, fault->gfn);
+
+ if (page_fault_handle_page_track(vcpu, fault))
+ return RET_PF_EMULATE;
+
+ r = fast_page_fault(vcpu, fault);
+ if (r != RET_PF_INVALID)
+ return r;
+
+ r = mmu_topup_memory_caches(vcpu, false);
+ if (r)
+ return r;
+
+ mmu_seq = vcpu->kvm->mmu_invalidate_seq;
+ smp_rmb();
+
+ r = kvm_faultin_pfn(vcpu, fault);
+ if (r != RET_PF_CONTINUE)
+ return r;
+
+ r = handle_abnormal_pfn(vcpu, fault, ACC_ALL);
+ if (r != RET_PF_CONTINUE)
+ return r;
+
+ r = RET_PF_RETRY;
+
+ if (is_tdp_mmu_fault)
+ read_lock(&vcpu->kvm->mmu_lock);
+ else
+ write_lock(&vcpu->kvm->mmu_lock);
+
+ if (is_page_fault_stale(vcpu, fault, mmu_seq))
+ goto out_unlock;
+
+ if (is_tdp_mmu_fault) {
+ r = kvm_tdp_mmu_map(vcpu, fault);
+ } else {
+ r = make_mmu_pages_available(vcpu);
+ if (r)
+ goto out_unlock;
+ r = __direct_map(vcpu, fault);
+ }
+
+out_unlock:
+ if (is_tdp_mmu_fault)
+ read_unlock(&vcpu->kvm->mmu_lock);
+ else
+ write_unlock(&vcpu->kvm->mmu_lock);
+ kvm_release_pfn_clean(fault->pfn);
+ return r;
+}
+
+static int nonpaging_page_fault(struct kvm_vcpu *vcpu,
+ struct kvm_page_fault *fault)
+{
+ pgprintk("%s: gva %lx error %x\n", __func__, fault->addr, fault->error_code);
+
+ /* This path builds a PAE pagetable, we can map 2mb pages at maximum. */
+ fault->max_level = PG_LEVEL_2M;
+ return direct_page_fault(vcpu, fault);
+}
+
+int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
+ u64 fault_address, char *insn, int insn_len)
+{
+ int r = 1;
+ u32 flags = vcpu->arch.apf.host_apf_flags;
+
+#ifndef CONFIG_X86_64
+ /* A 64-bit CR2 should be impossible on 32-bit KVM. */
+ if (WARN_ON_ONCE(fault_address >> 32))
+ return -EFAULT;
+#endif
+
+ vcpu->arch.l1tf_flush_l1d = true;
+ if (!flags) {
+ trace_kvm_page_fault(vcpu, fault_address, error_code);
+
+ if (kvm_event_needs_reinjection(vcpu))
+ kvm_mmu_unprotect_page_virt(vcpu, fault_address);
+ r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn,
+ insn_len);
+ } else if (flags & KVM_PV_REASON_PAGE_NOT_PRESENT) {
+ vcpu->arch.apf.host_apf_flags = 0;
+ local_irq_disable();
+ kvm_async_pf_task_wait_schedule(fault_address);
+ local_irq_enable();
+ } else {
+ WARN_ONCE(1, "Unexpected host async PF flags: %x\n", flags);
+ }
+
+ return r;
+}
+EXPORT_SYMBOL_GPL(kvm_handle_page_fault);
+
+int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+{
+ /*
+ * If the guest's MTRRs may be used to compute the "real" memtype,
+ * restrict the mapping level to ensure KVM uses a consistent memtype
+ * across the entire mapping. If the host MTRRs are ignored by TDP
+ * (shadow_memtype_mask is non-zero), and the VM has non-coherent DMA
+ * (DMA doesn't snoop CPU caches), KVM's ABI is to honor the memtype
+ * from the guest's MTRRs so that guest accesses to memory that is
+ * DMA'd aren't cached against the guest's wishes.
+ *
+ * Note, KVM may still ultimately ignore guest MTRRs for certain PFNs,
+ * e.g. KVM will force UC memtype for host MMIO.
+ */
+ if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+ for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) {
+ int page_num = KVM_PAGES_PER_HPAGE(fault->max_level);
+ gfn_t base = (fault->addr >> PAGE_SHIFT) & ~(page_num - 1);
+
+ if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num))
+ break;
+ }
+ }
+
+ return direct_page_fault(vcpu, fault);
+}
+
+static void nonpaging_init_context(struct kvm_mmu *context)
+{
+ context->page_fault = nonpaging_page_fault;
+ context->gva_to_gpa = nonpaging_gva_to_gpa;
+ context->sync_page = nonpaging_sync_page;
+ context->invlpg = NULL;
+}
+
+static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd,
+ union kvm_mmu_page_role role)
+{
+ return (role.direct || pgd == root->pgd) &&
+ VALID_PAGE(root->hpa) &&
+ role.word == to_shadow_page(root->hpa)->role.word;
+}
+
+/*
+ * Find out if a previously cached root matching the new pgd/role is available,
+ * and insert the current root as the MRU in the cache.
+ * If a matching root is found, it is assigned to kvm_mmu->root and
+ * true is returned.
+ * If no match is found, kvm_mmu->root is left invalid, the LRU root is
+ * evicted to make room for the current root, and false is returned.
+ */
+static bool cached_root_find_and_keep_current(struct kvm *kvm, struct kvm_mmu *mmu,
+ gpa_t new_pgd,
+ union kvm_mmu_page_role new_role)
+{
+ uint i;
+
+ if (is_root_usable(&mmu->root, new_pgd, new_role))
+ return true;
+
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
+ /*
+ * The swaps end up rotating the cache like this:
+ * C 0 1 2 3 (on entry to the function)
+ * 0 C 1 2 3
+ * 1 C 0 2 3
+ * 2 C 0 1 3
+ * 3 C 0 1 2 (on exit from the loop)
+ */
+ swap(mmu->root, mmu->prev_roots[i]);
+ if (is_root_usable(&mmu->root, new_pgd, new_role))
+ return true;
+ }
+
+ kvm_mmu_free_roots(kvm, mmu, KVM_MMU_ROOT_CURRENT);
+ return false;
+}
+
+/*
+ * Find out if a previously cached root matching the new pgd/role is available.
+ * On entry, mmu->root is invalid.
+ * If a matching root is found, it is assigned to kvm_mmu->root, the LRU entry
+ * of the cache becomes invalid, and true is returned.
+ * If no match is found, kvm_mmu->root is left invalid and false is returned.
+ */
+static bool cached_root_find_without_current(struct kvm *kvm, struct kvm_mmu *mmu,
+ gpa_t new_pgd,
+ union kvm_mmu_page_role new_role)
+{
+ uint i;
+
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+ if (is_root_usable(&mmu->prev_roots[i], new_pgd, new_role))
+ goto hit;
+
+ return false;
+
+hit:
+ swap(mmu->root, mmu->prev_roots[i]);
+ /* Bubble up the remaining roots. */
+ for (; i < KVM_MMU_NUM_PREV_ROOTS - 1; i++)
+ mmu->prev_roots[i] = mmu->prev_roots[i + 1];
+ mmu->prev_roots[i].hpa = INVALID_PAGE;
+ return true;
+}
+
+static bool fast_pgd_switch(struct kvm *kvm, struct kvm_mmu *mmu,
+ gpa_t new_pgd, union kvm_mmu_page_role new_role)
+{
+ /*
+ * For now, limit the caching to 64-bit hosts+VMs in order to avoid
+ * having to deal with PDPTEs. We may add support for 32-bit hosts/VMs
+ * later if necessary.
+ */
+ if (VALID_PAGE(mmu->root.hpa) && !to_shadow_page(mmu->root.hpa))
+ kvm_mmu_free_roots(kvm, mmu, KVM_MMU_ROOT_CURRENT);
+
+ if (VALID_PAGE(mmu->root.hpa))
+ return cached_root_find_and_keep_current(kvm, mmu, new_pgd, new_role);
+ else
+ return cached_root_find_without_current(kvm, mmu, new_pgd, new_role);
+}
+
+void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd)
+{
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
+ union kvm_mmu_page_role new_role = mmu->root_role;
+
+ if (!fast_pgd_switch(vcpu->kvm, mmu, new_pgd, new_role)) {
+ /* kvm_mmu_ensure_valid_pgd will set up a new root. */
+ return;
+ }
+
+ /*
+ * It's possible that the cached previous root page is obsolete because
+ * of a change in the MMU generation number. However, changing the
+ * generation number is accompanied by KVM_REQ_MMU_FREE_OBSOLETE_ROOTS,
+ * which will free the root set here and allocate a new one.
+ */
+ kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu);
+
+ if (force_flush_and_sync_on_reuse) {
+ kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
+ kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
+ }
+
+ /*
+ * The last MMIO access's GVA and GPA are cached in the VCPU. When
+ * switching to a new CR3, that GVA->GPA mapping may no longer be
+ * valid. So clear any cached MMIO info even when we don't need to sync
+ * the shadow page tables.
+ */
+ vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
+
+ /*
+ * If this is a direct root page, it doesn't have a write flooding
+ * count. Otherwise, clear the write flooding count.
+ */
+ if (!new_role.direct)
+ __clear_sp_write_flooding_count(
+ to_shadow_page(vcpu->arch.mmu->root.hpa));
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd);
+
+static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
+ unsigned int access)
+{
+ if (unlikely(is_mmio_spte(*sptep))) {
+ if (gfn != get_mmio_spte_gfn(*sptep)) {
+ mmu_spte_clear_no_track(sptep);
+ return true;
+ }
+
+ mark_mmio_spte(vcpu, sptep, gfn, access);
+ return true;
+ }
+
+ return false;
+}
+
+#define PTTYPE_EPT 18 /* arbitrary */
+#define PTTYPE PTTYPE_EPT
+#include "paging_tmpl.h"
+#undef PTTYPE
+
+#define PTTYPE 64
+#include "paging_tmpl.h"
+#undef PTTYPE
+
+#define PTTYPE 32
+#include "paging_tmpl.h"
+#undef PTTYPE
+
+static void
+__reset_rsvds_bits_mask(struct rsvd_bits_validate *rsvd_check,
+ u64 pa_bits_rsvd, int level, bool nx, bool gbpages,
+ bool pse, bool amd)
+{
+ u64 gbpages_bit_rsvd = 0;
+ u64 nonleaf_bit8_rsvd = 0;
+ u64 high_bits_rsvd;
+
+ rsvd_check->bad_mt_xwr = 0;
+
+ if (!gbpages)
+ gbpages_bit_rsvd = rsvd_bits(7, 7);
+
+ if (level == PT32E_ROOT_LEVEL)
+ high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 62);
+ else
+ high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51);
+
+ /* Note, NX doesn't exist in PDPTEs, this is handled below. */
+ if (!nx)
+ high_bits_rsvd |= rsvd_bits(63, 63);
+
+ /*
+ * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
+ * leaf entries) on AMD CPUs only.
+ */
+ if (amd)
+ nonleaf_bit8_rsvd = rsvd_bits(8, 8);
+
+ switch (level) {
+ case PT32_ROOT_LEVEL:
+ /* no rsvd bits for 2 level 4K page table entries */
+ rsvd_check->rsvd_bits_mask[0][1] = 0;
+ rsvd_check->rsvd_bits_mask[0][0] = 0;
+ rsvd_check->rsvd_bits_mask[1][0] =
+ rsvd_check->rsvd_bits_mask[0][0];
+
+ if (!pse) {
+ rsvd_check->rsvd_bits_mask[1][1] = 0;
+ break;
+ }
+
+ if (is_cpuid_PSE36())
+ /* 36bits PSE 4MB page */
+ rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
+ else
+ /* 32 bits PSE 4MB page */
+ rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
+ break;
+ case PT32E_ROOT_LEVEL:
+ rsvd_check->rsvd_bits_mask[0][2] = rsvd_bits(63, 63) |
+ high_bits_rsvd |
+ rsvd_bits(5, 8) |
+ rsvd_bits(1, 2); /* PDPTE */
+ rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd; /* PDE */
+ rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; /* PTE */
+ rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd |
+ rsvd_bits(13, 20); /* large page */
+ rsvd_check->rsvd_bits_mask[1][0] =
+ rsvd_check->rsvd_bits_mask[0][0];
+ break;
+ case PT64_ROOT_5LEVEL:
+ rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd |
+ nonleaf_bit8_rsvd |
+ rsvd_bits(7, 7);
+ rsvd_check->rsvd_bits_mask[1][4] =
+ rsvd_check->rsvd_bits_mask[0][4];
+ fallthrough;
+ case PT64_ROOT_4LEVEL:
+ rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd |
+ nonleaf_bit8_rsvd |
+ rsvd_bits(7, 7);
+ rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd |
+ gbpages_bit_rsvd;
+ rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd;
+ rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd;
+ rsvd_check->rsvd_bits_mask[1][3] =
+ rsvd_check->rsvd_bits_mask[0][3];
+ rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd |
+ gbpages_bit_rsvd |
+ rsvd_bits(13, 29);
+ rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd |
+ rsvd_bits(13, 20); /* large page */
+ rsvd_check->rsvd_bits_mask[1][0] =
+ rsvd_check->rsvd_bits_mask[0][0];
+ break;
+ }
+}
+
+static bool guest_can_use_gbpages(struct kvm_vcpu *vcpu)
+{
+ /*
+ * If TDP is enabled, let the guest use GBPAGES if they're supported in
+ * hardware. The hardware page walker doesn't let KVM disable GBPAGES,
+ * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA
+ * walk for performance and complexity reasons. Not to mention KVM
+ * _can't_ solve the problem because GVA->GPA walks aren't visible to
+ * KVM once a TDP translation is installed. Mimic hardware behavior so
+ * that KVM's is at least consistent, i.e. doesn't randomly inject #PF.
+ */
+ return tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) :
+ guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES);
+}
+
+static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context)
+{
+ __reset_rsvds_bits_mask(&context->guest_rsvd_check,
+ vcpu->arch.reserved_gpa_bits,
+ context->cpu_role.base.level, is_efer_nx(context),
+ guest_can_use_gbpages(vcpu),
+ is_cr4_pse(context),
+ guest_cpuid_is_amd_or_hygon(vcpu));
+}
+
+static void
+__reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
+ u64 pa_bits_rsvd, bool execonly, int huge_page_level)
+{
+ u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51);
+ u64 large_1g_rsvd = 0, large_2m_rsvd = 0;
+ u64 bad_mt_xwr;
+
+ if (huge_page_level < PG_LEVEL_1G)
+ large_1g_rsvd = rsvd_bits(7, 7);
+ if (huge_page_level < PG_LEVEL_2M)
+ large_2m_rsvd = rsvd_bits(7, 7);
+
+ rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | rsvd_bits(3, 7);
+ rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | rsvd_bits(3, 7);
+ rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6) | large_1g_rsvd;
+ rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6) | large_2m_rsvd;
+ rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd;
+
+ /* large page */
+ rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4];
+ rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3];
+ rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29) | large_1g_rsvd;
+ rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20) | large_2m_rsvd;
+ rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0];
+
+ bad_mt_xwr = 0xFFull << (2 * 8); /* bits 3..5 must not be 2 */
+ bad_mt_xwr |= 0xFFull << (3 * 8); /* bits 3..5 must not be 3 */
+ bad_mt_xwr |= 0xFFull << (7 * 8); /* bits 3..5 must not be 7 */
+ bad_mt_xwr |= REPEAT_BYTE(1ull << 2); /* bits 0..2 must not be 010 */
+ bad_mt_xwr |= REPEAT_BYTE(1ull << 6); /* bits 0..2 must not be 110 */
+ if (!execonly) {
+ /* bits 0..2 must not be 100 unless VMX capabilities allow it */
+ bad_mt_xwr |= REPEAT_BYTE(1ull << 4);
+ }
+ rsvd_check->bad_mt_xwr = bad_mt_xwr;
+}
+
+static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context, bool execonly, int huge_page_level)
+{
+ __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check,
+ vcpu->arch.reserved_gpa_bits, execonly,
+ huge_page_level);
+}
+
+static inline u64 reserved_hpa_bits(void)
+{
+ return rsvd_bits(shadow_phys_bits, 63);
+}
+
+/*
+ * the page table on host is the shadow page table for the page
+ * table in guest or amd nested guest, its mmu features completely
+ * follow the features in guest.
+ */
+static void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context)
+{
+ /* @amd adds a check on bit of SPTEs, which KVM shouldn't use anyways. */
+ bool is_amd = true;
+ /* KVM doesn't use 2-level page tables for the shadow MMU. */
+ bool is_pse = false;
+ struct rsvd_bits_validate *shadow_zero_check;
+ int i;
+
+ WARN_ON_ONCE(context->root_role.level < PT32E_ROOT_LEVEL);
+
+ shadow_zero_check = &context->shadow_zero_check;
+ __reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(),
+ context->root_role.level,
+ context->root_role.efer_nx,
+ guest_can_use_gbpages(vcpu), is_pse, is_amd);
+
+ if (!shadow_me_mask)
+ return;
+
+ for (i = context->root_role.level; --i >= 0;) {
+ /*
+ * So far shadow_me_value is a constant during KVM's life
+ * time. Bits in shadow_me_value are allowed to be set.
+ * Bits in shadow_me_mask but not in shadow_me_value are
+ * not allowed to be set.
+ */
+ shadow_zero_check->rsvd_bits_mask[0][i] |= shadow_me_mask;
+ shadow_zero_check->rsvd_bits_mask[1][i] |= shadow_me_mask;
+ shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_value;
+ shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_value;
+ }
+
+}
+
+static inline bool boot_cpu_is_amd(void)
+{
+ WARN_ON_ONCE(!tdp_enabled);
+ return shadow_x_mask == 0;
+}
+
+/*
+ * the direct page table on host, use as much mmu features as
+ * possible, however, kvm currently does not do execution-protection.
+ */
+static void
+reset_tdp_shadow_zero_bits_mask(struct kvm_mmu *context)
+{
+ struct rsvd_bits_validate *shadow_zero_check;
+ int i;
+
+ shadow_zero_check = &context->shadow_zero_check;
+
+ if (boot_cpu_is_amd())
+ __reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(),
+ context->root_role.level, true,
+ boot_cpu_has(X86_FEATURE_GBPAGES),
+ false, true);
+ else
+ __reset_rsvds_bits_mask_ept(shadow_zero_check,
+ reserved_hpa_bits(), false,
+ max_huge_page_level);
+
+ if (!shadow_me_mask)
+ return;
+
+ for (i = context->root_role.level; --i >= 0;) {
+ shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask;
+ shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask;
+ }
+}
+
+/*
+ * as the comments in reset_shadow_zero_bits_mask() except it
+ * is the shadow page table for intel nested guest.
+ */
+static void
+reset_ept_shadow_zero_bits_mask(struct kvm_mmu *context, bool execonly)
+{
+ __reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
+ reserved_hpa_bits(), execonly,
+ max_huge_page_level);
+}
+
+#define BYTE_MASK(access) \
+ ((1 & (access) ? 2 : 0) | \
+ (2 & (access) ? 4 : 0) | \
+ (3 & (access) ? 8 : 0) | \
+ (4 & (access) ? 16 : 0) | \
+ (5 & (access) ? 32 : 0) | \
+ (6 & (access) ? 64 : 0) | \
+ (7 & (access) ? 128 : 0))
+
+
+static void update_permission_bitmask(struct kvm_mmu *mmu, bool ept)
+{
+ unsigned byte;
+
+ const u8 x = BYTE_MASK(ACC_EXEC_MASK);
+ const u8 w = BYTE_MASK(ACC_WRITE_MASK);
+ const u8 u = BYTE_MASK(ACC_USER_MASK);
+
+ bool cr4_smep = is_cr4_smep(mmu);
+ bool cr4_smap = is_cr4_smap(mmu);
+ bool cr0_wp = is_cr0_wp(mmu);
+ bool efer_nx = is_efer_nx(mmu);
+
+ for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) {
+ unsigned pfec = byte << 1;
+
+ /*
+ * Each "*f" variable has a 1 bit for each UWX value
+ * that causes a fault with the given PFEC.
+ */
+
+ /* Faults from writes to non-writable pages */
+ u8 wf = (pfec & PFERR_WRITE_MASK) ? (u8)~w : 0;
+ /* Faults from user mode accesses to supervisor pages */
+ u8 uf = (pfec & PFERR_USER_MASK) ? (u8)~u : 0;
+ /* Faults from fetches of non-executable pages*/
+ u8 ff = (pfec & PFERR_FETCH_MASK) ? (u8)~x : 0;
+ /* Faults from kernel mode fetches of user pages */
+ u8 smepf = 0;
+ /* Faults from kernel mode accesses of user pages */
+ u8 smapf = 0;
+
+ if (!ept) {
+ /* Faults from kernel mode accesses to user pages */
+ u8 kf = (pfec & PFERR_USER_MASK) ? 0 : u;
+
+ /* Not really needed: !nx will cause pte.nx to fault */
+ if (!efer_nx)
+ ff = 0;
+
+ /* Allow supervisor writes if !cr0.wp */
+ if (!cr0_wp)
+ wf = (pfec & PFERR_USER_MASK) ? wf : 0;
+
+ /* Disallow supervisor fetches of user code if cr4.smep */
+ if (cr4_smep)
+ smepf = (pfec & PFERR_FETCH_MASK) ? kf : 0;
+
+ /*
+ * SMAP:kernel-mode data accesses from user-mode
+ * mappings should fault. A fault is considered
+ * as a SMAP violation if all of the following
+ * conditions are true:
+ * - X86_CR4_SMAP is set in CR4
+ * - A user page is accessed
+ * - The access is not a fetch
+ * - The access is supervisor mode
+ * - If implicit supervisor access or X86_EFLAGS_AC is clear
+ *
+ * Here, we cover the first four conditions.
+ * The fifth is computed dynamically in permission_fault();
+ * PFERR_RSVD_MASK bit will be set in PFEC if the access is
+ * *not* subject to SMAP restrictions.
+ */
+ if (cr4_smap)
+ smapf = (pfec & (PFERR_RSVD_MASK|PFERR_FETCH_MASK)) ? 0 : kf;
+ }
+
+ mmu->permissions[byte] = ff | uf | wf | smepf | smapf;
+ }
+}
+
+/*
+* PKU is an additional mechanism by which the paging controls access to
+* user-mode addresses based on the value in the PKRU register. Protection
+* key violations are reported through a bit in the page fault error code.
+* Unlike other bits of the error code, the PK bit is not known at the
+* call site of e.g. gva_to_gpa; it must be computed directly in
+* permission_fault based on two bits of PKRU, on some machine state (CR4,
+* CR0, EFER, CPL), and on other bits of the error code and the page tables.
+*
+* In particular the following conditions come from the error code, the
+* page tables and the machine state:
+* - PK is always zero unless CR4.PKE=1 and EFER.LMA=1
+* - PK is always zero if RSVD=1 (reserved bit set) or F=1 (instruction fetch)
+* - PK is always zero if U=0 in the page tables
+* - PKRU.WD is ignored if CR0.WP=0 and the access is a supervisor access.
+*
+* The PKRU bitmask caches the result of these four conditions. The error
+* code (minus the P bit) and the page table's U bit form an index into the
+* PKRU bitmask. Two bits of the PKRU bitmask are then extracted and ANDed
+* with the two bits of the PKRU register corresponding to the protection key.
+* For the first three conditions above the bits will be 00, thus masking
+* away both AD and WD. For all reads or if the last condition holds, WD
+* only will be masked away.
+*/
+static void update_pkru_bitmask(struct kvm_mmu *mmu)
+{
+ unsigned bit;
+ bool wp;
+
+ mmu->pkru_mask = 0;
+
+ if (!is_cr4_pke(mmu))
+ return;
+
+ wp = is_cr0_wp(mmu);
+
+ for (bit = 0; bit < ARRAY_SIZE(mmu->permissions); ++bit) {
+ unsigned pfec, pkey_bits;
+ bool check_pkey, check_write, ff, uf, wf, pte_user;
+
+ pfec = bit << 1;
+ ff = pfec & PFERR_FETCH_MASK;
+ uf = pfec & PFERR_USER_MASK;
+ wf = pfec & PFERR_WRITE_MASK;
+
+ /* PFEC.RSVD is replaced by ACC_USER_MASK. */
+ pte_user = pfec & PFERR_RSVD_MASK;
+
+ /*
+ * Only need to check the access which is not an
+ * instruction fetch and is to a user page.
+ */
+ check_pkey = (!ff && pte_user);
+ /*
+ * write access is controlled by PKRU if it is a
+ * user access or CR0.WP = 1.
+ */
+ check_write = check_pkey && wf && (uf || wp);
+
+ /* PKRU.AD stops both read and write access. */
+ pkey_bits = !!check_pkey;
+ /* PKRU.WD stops write access. */
+ pkey_bits |= (!!check_write) << 1;
+
+ mmu->pkru_mask |= (pkey_bits & 3) << pfec;
+ }
+}
+
+static void reset_guest_paging_metadata(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *mmu)
+{
+ if (!is_cr0_pg(mmu))
+ return;
+
+ reset_guest_rsvds_bits_mask(vcpu, mmu);
+ update_permission_bitmask(mmu, false);
+ update_pkru_bitmask(mmu);
+}
+
+static void paging64_init_context(struct kvm_mmu *context)
+{
+ context->page_fault = paging64_page_fault;
+ context->gva_to_gpa = paging64_gva_to_gpa;
+ context->sync_page = paging64_sync_page;
+ context->invlpg = paging64_invlpg;
+}
+
+static void paging32_init_context(struct kvm_mmu *context)
+{
+ context->page_fault = paging32_page_fault;
+ context->gva_to_gpa = paging32_gva_to_gpa;
+ context->sync_page = paging32_sync_page;
+ context->invlpg = paging32_invlpg;
+}
+
+static union kvm_cpu_role
+kvm_calc_cpu_role(struct kvm_vcpu *vcpu, const struct kvm_mmu_role_regs *regs)
+{
+ union kvm_cpu_role role = {0};
+
+ role.base.access = ACC_ALL;
+ role.base.smm = is_smm(vcpu);
+ role.base.guest_mode = is_guest_mode(vcpu);
+ role.ext.valid = 1;
+
+ if (!____is_cr0_pg(regs)) {
+ role.base.direct = 1;
+ return role;
+ }
+
+ role.base.efer_nx = ____is_efer_nx(regs);
+ role.base.cr0_wp = ____is_cr0_wp(regs);
+ role.base.smep_andnot_wp = ____is_cr4_smep(regs) && !____is_cr0_wp(regs);
+ role.base.smap_andnot_wp = ____is_cr4_smap(regs) && !____is_cr0_wp(regs);
+ role.base.has_4_byte_gpte = !____is_cr4_pae(regs);
+
+ if (____is_efer_lma(regs))
+ role.base.level = ____is_cr4_la57(regs) ? PT64_ROOT_5LEVEL
+ : PT64_ROOT_4LEVEL;
+ else if (____is_cr4_pae(regs))
+ role.base.level = PT32E_ROOT_LEVEL;
+ else
+ role.base.level = PT32_ROOT_LEVEL;
+
+ role.ext.cr4_smep = ____is_cr4_smep(regs);
+ role.ext.cr4_smap = ____is_cr4_smap(regs);
+ role.ext.cr4_pse = ____is_cr4_pse(regs);
+
+ /* PKEY and LA57 are active iff long mode is active. */
+ role.ext.cr4_pke = ____is_efer_lma(regs) && ____is_cr4_pke(regs);
+ role.ext.cr4_la57 = ____is_efer_lma(regs) && ____is_cr4_la57(regs);
+ role.ext.efer_lma = ____is_efer_lma(regs);
+ return role;
+}
+
+void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *mmu)
+{
+ const bool cr0_wp = !!kvm_read_cr0_bits(vcpu, X86_CR0_WP);
+
+ BUILD_BUG_ON((KVM_MMU_CR0_ROLE_BITS & KVM_POSSIBLE_CR0_GUEST_BITS) != X86_CR0_WP);
+ BUILD_BUG_ON((KVM_MMU_CR4_ROLE_BITS & KVM_POSSIBLE_CR4_GUEST_BITS));
+
+ if (is_cr0_wp(mmu) == cr0_wp)
+ return;
+
+ mmu->cpu_role.base.cr0_wp = cr0_wp;
+ reset_guest_paging_metadata(vcpu, mmu);
+}
+
+static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu)
+{
+ /* tdp_root_level is architecture forced level, use it if nonzero */
+ if (tdp_root_level)
+ return tdp_root_level;
+
+ /* Use 5-level TDP if and only if it's useful/necessary. */
+ if (max_tdp_level == 5 && cpuid_maxphyaddr(vcpu) <= 48)
+ return 4;
+
+ return max_tdp_level;
+}
+
+static union kvm_mmu_page_role
+kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu,
+ union kvm_cpu_role cpu_role)
+{
+ union kvm_mmu_page_role role = {0};
+
+ role.access = ACC_ALL;
+ role.cr0_wp = true;
+ role.efer_nx = true;
+ role.smm = cpu_role.base.smm;
+ role.guest_mode = cpu_role.base.guest_mode;
+ role.ad_disabled = !kvm_ad_enabled();
+ role.level = kvm_mmu_get_tdp_level(vcpu);
+ role.direct = true;
+ role.has_4_byte_gpte = false;
+
+ return role;
+}
+
+static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu,
+ union kvm_cpu_role cpu_role)
+{
+ struct kvm_mmu *context = &vcpu->arch.root_mmu;
+ union kvm_mmu_page_role root_role = kvm_calc_tdp_mmu_root_page_role(vcpu, cpu_role);
+
+ if (cpu_role.as_u64 == context->cpu_role.as_u64 &&
+ root_role.word == context->root_role.word)
+ return;
+
+ context->cpu_role.as_u64 = cpu_role.as_u64;
+ context->root_role.word = root_role.word;
+ context->page_fault = kvm_tdp_page_fault;
+ context->sync_page = nonpaging_sync_page;
+ context->invlpg = NULL;
+ context->get_guest_pgd = get_guest_cr3;
+ context->get_pdptr = kvm_pdptr_read;
+ context->inject_page_fault = kvm_inject_page_fault;
+
+ if (!is_cr0_pg(context))
+ context->gva_to_gpa = nonpaging_gva_to_gpa;
+ else if (is_cr4_pae(context))
+ context->gva_to_gpa = paging64_gva_to_gpa;
+ else
+ context->gva_to_gpa = paging32_gva_to_gpa;
+
+ reset_guest_paging_metadata(vcpu, context);
+ reset_tdp_shadow_zero_bits_mask(context);
+}
+
+static void shadow_mmu_init_context(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
+ union kvm_cpu_role cpu_role,
+ union kvm_mmu_page_role root_role)
+{
+ if (cpu_role.as_u64 == context->cpu_role.as_u64 &&
+ root_role.word == context->root_role.word)
+ return;
+
+ context->cpu_role.as_u64 = cpu_role.as_u64;
+ context->root_role.word = root_role.word;
+
+ if (!is_cr0_pg(context))
+ nonpaging_init_context(context);
+ else if (is_cr4_pae(context))
+ paging64_init_context(context);
+ else
+ paging32_init_context(context);
+
+ reset_guest_paging_metadata(vcpu, context);
+ reset_shadow_zero_bits_mask(vcpu, context);
+}
+
+static void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu,
+ union kvm_cpu_role cpu_role)
+{
+ struct kvm_mmu *context = &vcpu->arch.root_mmu;
+ union kvm_mmu_page_role root_role;
+
+ root_role = cpu_role.base;
+
+ /* KVM uses PAE paging whenever the guest isn't using 64-bit paging. */
+ root_role.level = max_t(u32, root_role.level, PT32E_ROOT_LEVEL);
+
+ /*
+ * KVM forces EFER.NX=1 when TDP is disabled, reflect it in the MMU role.
+ * KVM uses NX when TDP is disabled to handle a variety of scenarios,
+ * notably for huge SPTEs if iTLB multi-hit mitigation is enabled and
+ * to generate correct permissions for CR0.WP=0/CR4.SMEP=1/EFER.NX=0.
+ * The iTLB multi-hit workaround can be toggled at any time, so assume
+ * NX can be used by any non-nested shadow MMU to avoid having to reset
+ * MMU contexts.
+ */
+ root_role.efer_nx = true;
+
+ shadow_mmu_init_context(vcpu, context, cpu_role, root_role);
+}
+
+void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0,
+ unsigned long cr4, u64 efer, gpa_t nested_cr3)
+{
+ struct kvm_mmu *context = &vcpu->arch.guest_mmu;
+ struct kvm_mmu_role_regs regs = {
+ .cr0 = cr0,
+ .cr4 = cr4 & ~X86_CR4_PKE,
+ .efer = efer,
+ };
+ union kvm_cpu_role cpu_role = kvm_calc_cpu_role(vcpu, &regs);
+ union kvm_mmu_page_role root_role;
+
+ /* NPT requires CR0.PG=1. */
+ WARN_ON_ONCE(cpu_role.base.direct);
+
+ root_role = cpu_role.base;
+ root_role.level = kvm_mmu_get_tdp_level(vcpu);
+ if (root_role.level == PT64_ROOT_5LEVEL &&
+ cpu_role.base.level == PT64_ROOT_4LEVEL)
+ root_role.passthrough = 1;
+
+ shadow_mmu_init_context(vcpu, context, cpu_role, root_role);
+ kvm_mmu_new_pgd(vcpu, nested_cr3);
+}
+EXPORT_SYMBOL_GPL(kvm_init_shadow_npt_mmu);
+
+static union kvm_cpu_role
+kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
+ bool execonly, u8 level)
+{
+ union kvm_cpu_role role = {0};
+
+ /*
+ * KVM does not support SMM transfer monitors, and consequently does not
+ * support the "entry to SMM" control either. role.base.smm is always 0.
+ */
+ WARN_ON_ONCE(is_smm(vcpu));
+ role.base.level = level;
+ role.base.has_4_byte_gpte = false;
+ role.base.direct = false;
+ role.base.ad_disabled = !accessed_dirty;
+ role.base.guest_mode = true;
+ role.base.access = ACC_ALL;
+
+ role.ext.word = 0;
+ role.ext.execonly = execonly;
+ role.ext.valid = 1;
+
+ return role;
+}
+
+void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
+ int huge_page_level, bool accessed_dirty,
+ gpa_t new_eptp)
+{
+ struct kvm_mmu *context = &vcpu->arch.guest_mmu;
+ u8 level = vmx_eptp_page_walk_level(new_eptp);
+ union kvm_cpu_role new_mode =
+ kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty,
+ execonly, level);
+
+ if (new_mode.as_u64 != context->cpu_role.as_u64) {
+ /* EPT, and thus nested EPT, does not consume CR0, CR4, nor EFER. */
+ context->cpu_role.as_u64 = new_mode.as_u64;
+ context->root_role.word = new_mode.base.word;
+
+ context->page_fault = ept_page_fault;
+ context->gva_to_gpa = ept_gva_to_gpa;
+ context->sync_page = ept_sync_page;
+ context->invlpg = ept_invlpg;
+
+ update_permission_bitmask(context, true);
+ context->pkru_mask = 0;
+ reset_rsvds_bits_mask_ept(vcpu, context, execonly, huge_page_level);
+ reset_ept_shadow_zero_bits_mask(context, execonly);
+ }
+
+ kvm_mmu_new_pgd(vcpu, new_eptp);
+}
+EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
+
+static void init_kvm_softmmu(struct kvm_vcpu *vcpu,
+ union kvm_cpu_role cpu_role)
+{
+ struct kvm_mmu *context = &vcpu->arch.root_mmu;
+
+ kvm_init_shadow_mmu(vcpu, cpu_role);
+
+ context->get_guest_pgd = get_guest_cr3;
+ context->get_pdptr = kvm_pdptr_read;
+ context->inject_page_fault = kvm_inject_page_fault;
+}
+
+static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu,
+ union kvm_cpu_role new_mode)
+{
+ struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;
+
+ if (new_mode.as_u64 == g_context->cpu_role.as_u64)
+ return;
+
+ g_context->cpu_role.as_u64 = new_mode.as_u64;
+ g_context->get_guest_pgd = get_guest_cr3;
+ g_context->get_pdptr = kvm_pdptr_read;
+ g_context->inject_page_fault = kvm_inject_page_fault;
+
+ /*
+ * L2 page tables are never shadowed, so there is no need to sync
+ * SPTEs.
+ */
+ g_context->invlpg = NULL;
+
+ /*
+ * Note that arch.mmu->gva_to_gpa translates l2_gpa to l1_gpa using
+ * L1's nested page tables (e.g. EPT12). The nested translation
+ * of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using
+ * L2's page tables as the first level of translation and L1's
+ * nested page tables as the second level of translation. Basically
+ * the gva_to_gpa functions between mmu and nested_mmu are swapped.
+ */
+ if (!is_paging(vcpu))
+ g_context->gva_to_gpa = nonpaging_gva_to_gpa;
+ else if (is_long_mode(vcpu))
+ g_context->gva_to_gpa = paging64_gva_to_gpa;
+ else if (is_pae(vcpu))
+ g_context->gva_to_gpa = paging64_gva_to_gpa;
+ else
+ g_context->gva_to_gpa = paging32_gva_to_gpa;
+
+ reset_guest_paging_metadata(vcpu, g_context);
+}
+
+void kvm_init_mmu(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu_role_regs regs = vcpu_to_role_regs(vcpu);
+ union kvm_cpu_role cpu_role = kvm_calc_cpu_role(vcpu, &regs);
+
+ if (mmu_is_nested(vcpu))
+ init_kvm_nested_mmu(vcpu, cpu_role);
+ else if (tdp_enabled)
+ init_kvm_tdp_mmu(vcpu, cpu_role);
+ else
+ init_kvm_softmmu(vcpu, cpu_role);
+}
+EXPORT_SYMBOL_GPL(kvm_init_mmu);
+
+void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
+{
+ /*
+ * Invalidate all MMU roles to force them to reinitialize as CPUID
+ * information is factored into reserved bit calculations.
+ *
+ * Correctly handling multiple vCPU models with respect to paging and
+ * physical address properties) in a single VM would require tracking
+ * all relevant CPUID information in kvm_mmu_page_role. That is very
+ * undesirable as it would increase the memory requirements for
+ * gfn_track (see struct kvm_mmu_page_role comments). For now that
+ * problem is swept under the rug; KVM's CPUID API is horrific and
+ * it's all but impossible to solve it without introducing a new API.
+ */
+ vcpu->arch.root_mmu.root_role.word = 0;
+ vcpu->arch.guest_mmu.root_role.word = 0;
+ vcpu->arch.nested_mmu.root_role.word = 0;
+ vcpu->arch.root_mmu.cpu_role.ext.valid = 0;
+ vcpu->arch.guest_mmu.cpu_role.ext.valid = 0;
+ vcpu->arch.nested_mmu.cpu_role.ext.valid = 0;
+ kvm_mmu_reset_context(vcpu);
+
+ /*
+ * Changing guest CPUID after KVM_RUN is forbidden, see the comment in
+ * kvm_arch_vcpu_ioctl().
+ */
+ KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm);
+}
+
+void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
+{
+ kvm_mmu_unload(vcpu);
+ kvm_init_mmu(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_reset_context);
+
+int kvm_mmu_load(struct kvm_vcpu *vcpu)
+{
+ int r;
+
+ r = mmu_topup_memory_caches(vcpu, !vcpu->arch.mmu->root_role.direct);
+ if (r)
+ goto out;
+ r = mmu_alloc_special_roots(vcpu);
+ if (r)
+ goto out;
+ if (vcpu->arch.mmu->root_role.direct)
+ r = mmu_alloc_direct_roots(vcpu);
+ else
+ r = mmu_alloc_shadow_roots(vcpu);
+ if (r)
+ goto out;
+
+ kvm_mmu_sync_roots(vcpu);
+
+ kvm_mmu_load_pgd(vcpu);
+
+ /*
+ * Flush any TLB entries for the new root, the provenance of the root
+ * is unknown. Even if KVM ensures there are no stale TLB entries
+ * for a freed root, in theory another hypervisor could have left
+ * stale entries. Flushing on alloc also allows KVM to skip the TLB
+ * flush when freeing a root (see kvm_tdp_mmu_put_root()).
+ */
+ static_call(kvm_x86_flush_tlb_current)(vcpu);
+out:
+ return r;
+}
+
+void kvm_mmu_unload(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+
+ kvm_mmu_free_roots(kvm, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL);
+ WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root.hpa));
+ kvm_mmu_free_roots(kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+ WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root.hpa));
+ vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
+}
+
+static bool is_obsolete_root(struct kvm *kvm, hpa_t root_hpa)
+{
+ struct kvm_mmu_page *sp;
+
+ if (!VALID_PAGE(root_hpa))
+ return false;
+
+ /*
+ * When freeing obsolete roots, treat roots as obsolete if they don't
+ * have an associated shadow page. This does mean KVM will get false
+ * positives and free roots that don't strictly need to be freed, but
+ * such false positives are relatively rare:
+ *
+ * (a) only PAE paging and nested NPT has roots without shadow pages
+ * (b) remote reloads due to a memslot update obsoletes _all_ roots
+ * (c) KVM doesn't track previous roots for PAE paging, and the guest
+ * is unlikely to zap an in-use PGD.
+ */
+ sp = to_shadow_page(root_hpa);
+ return !sp || is_obsolete_sp(kvm, sp);
+}
+
+static void __kvm_mmu_free_obsolete_roots(struct kvm *kvm, struct kvm_mmu *mmu)
+{
+ unsigned long roots_to_free = 0;
+ int i;
+
+ if (is_obsolete_root(kvm, mmu->root.hpa))
+ roots_to_free |= KVM_MMU_ROOT_CURRENT;
+
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
+ if (is_obsolete_root(kvm, mmu->prev_roots[i].hpa))
+ roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
+ }
+
+ if (roots_to_free)
+ kvm_mmu_free_roots(kvm, mmu, roots_to_free);
+}
+
+void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu)
+{
+ __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu);
+ __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu);
+}
+
+static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
+ int *bytes)
+{
+ u64 gentry = 0;
+ int r;
+
+ /*
+ * Assume that the pte write on a page table of the same type
+ * as the current vcpu paging mode since we update the sptes only
+ * when they have the same mode.
+ */
+ if (is_pae(vcpu) && *bytes == 4) {
+ /* Handle a 32-bit guest writing two halves of a 64-bit gpte */
+ *gpa &= ~(gpa_t)7;
+ *bytes = 8;
+ }
+
+ if (*bytes == 4 || *bytes == 8) {
+ r = kvm_vcpu_read_guest_atomic(vcpu, *gpa, &gentry, *bytes);
+ if (r)
+ gentry = 0;
+ }
+
+ return gentry;
+}
+
+/*
+ * If we're seeing too many writes to a page, it may no longer be a page table,
+ * or we may be forking, in which case it is better to unmap the page.
+ */
+static bool detect_write_flooding(struct kvm_mmu_page *sp)
+{
+ /*
+ * Skip write-flooding detected for the sp whose level is 1, because
+ * it can become unsync, then the guest page is not write-protected.
+ */
+ if (sp->role.level == PG_LEVEL_4K)
+ return false;
+
+ atomic_inc(&sp->write_flooding_count);
+ return atomic_read(&sp->write_flooding_count) >= 3;
+}
+
+/*
+ * Misaligned accesses are too much trouble to fix up; also, they usually
+ * indicate a page is not used as a page table.
+ */
+static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa,
+ int bytes)
+{
+ unsigned offset, pte_size, misaligned;
+
+ pgprintk("misaligned: gpa %llx bytes %d role %x\n",
+ gpa, bytes, sp->role.word);
+
+ offset = offset_in_page(gpa);
+ pte_size = sp->role.has_4_byte_gpte ? 4 : 8;
+
+ /*
+ * Sometimes, the OS only writes the last one bytes to update status
+ * bits, for example, in linux, andb instruction is used in clear_bit().
+ */
+ if (!(offset & (pte_size - 1)) && bytes == 1)
+ return false;
+
+ misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
+ misaligned |= bytes < 4;
+
+ return misaligned;
+}
+
+static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
+{
+ unsigned page_offset, quadrant;
+ u64 *spte;
+ int level;
+
+ page_offset = offset_in_page(gpa);
+ level = sp->role.level;
+ *nspte = 1;
+ if (sp->role.has_4_byte_gpte) {
+ page_offset <<= 1; /* 32->64 */
+ /*
+ * A 32-bit pde maps 4MB while the shadow pdes map
+ * only 2MB. So we need to double the offset again
+ * and zap two pdes instead of one.
+ */
+ if (level == PT32_ROOT_LEVEL) {
+ page_offset &= ~7; /* kill rounding error */
+ page_offset <<= 1;
+ *nspte = 2;
+ }
+ quadrant = page_offset >> PAGE_SHIFT;
+ page_offset &= ~PAGE_MASK;
+ if (quadrant != sp->role.quadrant)
+ return NULL;
+ }
+
+ spte = &sp->spt[page_offset / sizeof(*spte)];
+ return spte;
+}
+
+static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
+ const u8 *new, int bytes,
+ struct kvm_page_track_notifier_node *node)
+{
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ struct kvm_mmu_page *sp;
+ LIST_HEAD(invalid_list);
+ u64 entry, gentry, *spte;
+ int npte;
+ bool flush = false;
+
+ /*
+ * If we don't have indirect shadow pages, it means no page is
+ * write-protected, so we can exit simply.
+ */
+ if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
+ return;
+
+ pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
+
+ write_lock(&vcpu->kvm->mmu_lock);
+
+ gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes);
+
+ ++vcpu->kvm->stat.mmu_pte_write;
+
+ for_each_gfn_valid_sp_with_gptes(vcpu->kvm, sp, gfn) {
+ if (detect_write_misaligned(sp, gpa, bytes) ||
+ detect_write_flooding(sp)) {
+ kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list);
+ ++vcpu->kvm->stat.mmu_flooded;
+ continue;
+ }
+
+ spte = get_written_sptes(sp, gpa, &npte);
+ if (!spte)
+ continue;
+
+ while (npte--) {
+ entry = *spte;
+ mmu_page_zap_pte(vcpu->kvm, sp, spte, NULL);
+ if (gentry && sp->role.level != PG_LEVEL_4K)
+ ++vcpu->kvm->stat.mmu_pde_zapped;
+ if (is_shadow_present_pte(entry))
+ flush = true;
+ ++spte;
+ }
+ }
+ kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, flush);
+ write_unlock(&vcpu->kvm->mmu_lock);
+}
+
+int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
+ void *insn, int insn_len)
+{
+ int r, emulation_type = EMULTYPE_PF;
+ bool direct = vcpu->arch.mmu->root_role.direct;
+
+ if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
+ return RET_PF_RETRY;
+
+ r = RET_PF_INVALID;
+ if (unlikely(error_code & PFERR_RSVD_MASK)) {
+ r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct);
+ if (r == RET_PF_EMULATE)
+ goto emulate;
+ }
+
+ if (r == RET_PF_INVALID) {
+ r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa,
+ lower_32_bits(error_code), false);
+ if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm))
+ return -EIO;
+ }
+
+ if (r < 0)
+ return r;
+ if (r != RET_PF_EMULATE)
+ return 1;
+
+ /*
+ * Before emulating the instruction, check if the error code
+ * was due to a RO violation while translating the guest page.
+ * This can occur when using nested virtualization with nested
+ * paging in both guests. If true, we simply unprotect the page
+ * and resume the guest.
+ */
+ if (vcpu->arch.mmu->root_role.direct &&
+ (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
+ kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa));
+ return 1;
+ }
+
+ /*
+ * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still
+ * optimistically try to just unprotect the page and let the processor
+ * re-execute the instruction that caused the page fault. Do not allow
+ * retrying MMIO emulation, as it's not only pointless but could also
+ * cause us to enter an infinite loop because the processor will keep
+ * faulting on the non-existent MMIO address. Retrying an instruction
+ * from a nested guest is also pointless and dangerous as we are only
+ * explicitly shadowing L1's page tables, i.e. unprotecting something
+ * for L1 isn't going to magically fix whatever issue cause L2 to fail.
+ */
+ if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu))
+ emulation_type |= EMULTYPE_ALLOW_RETRY_PF;
+emulate:
+ return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn,
+ insn_len);
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
+
+void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ gva_t gva, hpa_t root_hpa)
+{
+ int i;
+
+ /* It's actually a GPA for vcpu->arch.guest_mmu. */
+ if (mmu != &vcpu->arch.guest_mmu) {
+ /* INVLPG on a non-canonical address is a NOP according to the SDM. */
+ if (is_noncanonical_address(gva, vcpu))
+ return;
+
+ static_call(kvm_x86_flush_tlb_gva)(vcpu, gva);
+ }
+
+ if (!mmu->invlpg)
+ return;
+
+ if (root_hpa == INVALID_PAGE) {
+ mmu->invlpg(vcpu, gva, mmu->root.hpa);
+
+ /*
+ * INVLPG is required to invalidate any global mappings for the VA,
+ * irrespective of PCID. Since it would take us roughly similar amount
+ * of work to determine whether any of the prev_root mappings of the VA
+ * is marked global, or to just sync it blindly, so we might as well
+ * just always sync it.
+ *
+ * Mappings not reachable via the current cr3 or the prev_roots will be
+ * synced when switching to that cr3, so nothing needs to be done here
+ * for them.
+ */
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+ if (VALID_PAGE(mmu->prev_roots[i].hpa))
+ mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa);
+ } else {
+ mmu->invlpg(vcpu, gva, root_hpa);
+ }
+}
+
+void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
+{
+ kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE);
+ ++vcpu->stat.invlpg;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
+
+
+void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid)
+{
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
+ bool tlb_flush = false;
+ uint i;
+
+ if (pcid == kvm_get_active_pcid(vcpu)) {
+ if (mmu->invlpg)
+ mmu->invlpg(vcpu, gva, mmu->root.hpa);
+ tlb_flush = true;
+ }
+
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
+ if (VALID_PAGE(mmu->prev_roots[i].hpa) &&
+ pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd)) {
+ if (mmu->invlpg)
+ mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa);
+ tlb_flush = true;
+ }
+ }
+
+ if (tlb_flush)
+ static_call(kvm_x86_flush_tlb_gva)(vcpu, gva);
+
+ ++vcpu->stat.invlpg;
+
+ /*
+ * Mappings not reachable via the current cr3 or the prev_roots will be
+ * synced when switching to that cr3, so nothing needs to be done here
+ * for them.
+ */
+}
+
+void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
+ int tdp_max_root_level, int tdp_huge_page_level)
+{
+ tdp_enabled = enable_tdp;
+ tdp_root_level = tdp_forced_root_level;
+ max_tdp_level = tdp_max_root_level;
+
+ /*
+ * max_huge_page_level reflects KVM's MMU capabilities irrespective
+ * of kernel support, e.g. KVM may be capable of using 1GB pages when
+ * the kernel is not. But, KVM never creates a page size greater than
+ * what is used by the kernel for any given HVA, i.e. the kernel's
+ * capabilities are ultimately consulted by kvm_mmu_hugepage_adjust().
+ */
+ if (tdp_enabled)
+ max_huge_page_level = tdp_huge_page_level;
+ else if (boot_cpu_has(X86_FEATURE_GBPAGES))
+ max_huge_page_level = PG_LEVEL_1G;
+ else
+ max_huge_page_level = PG_LEVEL_2M;
+}
+EXPORT_SYMBOL_GPL(kvm_configure_mmu);
+
+/* The return value indicates if tlb flush on all vcpus is needed. */
+typedef bool (*slot_level_handler) (struct kvm *kvm,
+ struct kvm_rmap_head *rmap_head,
+ const struct kvm_memory_slot *slot);
+
+/* The caller should hold mmu-lock before calling this function. */
+static __always_inline bool
+slot_handle_level_range(struct kvm *kvm, const struct kvm_memory_slot *memslot,
+ slot_level_handler fn, int start_level, int end_level,
+ gfn_t start_gfn, gfn_t end_gfn, bool flush_on_yield,
+ bool flush)
+{
+ struct slot_rmap_walk_iterator iterator;
+
+ for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn,
+ end_gfn, &iterator) {
+ if (iterator.rmap)
+ flush |= fn(kvm, iterator.rmap, memslot);
+
+ if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
+ if (flush && flush_on_yield) {
+ kvm_flush_remote_tlbs_with_address(kvm,
+ start_gfn,
+ iterator.gfn - start_gfn + 1);
+ flush = false;
+ }
+ cond_resched_rwlock_write(&kvm->mmu_lock);
+ }
+ }
+
+ return flush;
+}
+
+static __always_inline bool
+slot_handle_level(struct kvm *kvm, const struct kvm_memory_slot *memslot,
+ slot_level_handler fn, int start_level, int end_level,
+ bool flush_on_yield)
+{
+ return slot_handle_level_range(kvm, memslot, fn, start_level,
+ end_level, memslot->base_gfn,
+ memslot->base_gfn + memslot->npages - 1,
+ flush_on_yield, false);
+}
+
+static __always_inline bool
+slot_handle_level_4k(struct kvm *kvm, const struct kvm_memory_slot *memslot,
+ slot_level_handler fn, bool flush_on_yield)
+{
+ return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K,
+ PG_LEVEL_4K, flush_on_yield);
+}
+
+static void free_mmu_pages(struct kvm_mmu *mmu)
+{
+ if (!tdp_enabled && mmu->pae_root)
+ set_memory_encrypted((unsigned long)mmu->pae_root, 1);
+ free_page((unsigned long)mmu->pae_root);
+ free_page((unsigned long)mmu->pml4_root);
+ free_page((unsigned long)mmu->pml5_root);
+}
+
+static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+{
+ struct page *page;
+ int i;
+
+ mmu->root.hpa = INVALID_PAGE;
+ mmu->root.pgd = 0;
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+ mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
+
+ /* vcpu->arch.guest_mmu isn't used when !tdp_enabled. */
+ if (!tdp_enabled && mmu == &vcpu->arch.guest_mmu)
+ return 0;
+
+ /*
+ * When using PAE paging, the four PDPTEs are treated as 'root' pages,
+ * while the PDP table is a per-vCPU construct that's allocated at MMU
+ * creation. When emulating 32-bit mode, cr3 is only 32 bits even on
+ * x86_64. Therefore we need to allocate the PDP table in the first
+ * 4GB of memory, which happens to fit the DMA32 zone. TDP paging
+ * generally doesn't use PAE paging and can skip allocating the PDP
+ * table. The main exception, handled here, is SVM's 32-bit NPT. The
+ * other exception is for shadowing L1's 32-bit or PAE NPT on 64-bit
+ * KVM; that horror is handled on-demand by mmu_alloc_special_roots().
+ */
+ if (tdp_enabled && kvm_mmu_get_tdp_level(vcpu) > PT32E_ROOT_LEVEL)
+ return 0;
+
+ page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_DMA32);
+ if (!page)
+ return -ENOMEM;
+
+ mmu->pae_root = page_address(page);
+
+ /*
+ * CR3 is only 32 bits when PAE paging is used, thus it's impossible to
+ * get the CPU to treat the PDPTEs as encrypted. Decrypt the page so
+ * that KVM's writes and the CPU's reads get along. Note, this is
+ * only necessary when using shadow paging, as 64-bit NPT can get at
+ * the C-bit even when shadowing 32-bit NPT, and SME isn't supported
+ * by 32-bit kernels (when KVM itself uses 32-bit NPT).
+ */
+ if (!tdp_enabled)
+ set_memory_decrypted((unsigned long)mmu->pae_root, 1);
+ else
+ WARN_ON_ONCE(shadow_me_value);
+
+ for (i = 0; i < 4; ++i)
+ mmu->pae_root[i] = INVALID_PAE_ROOT;
+
+ return 0;
+}
+
+int kvm_mmu_create(struct kvm_vcpu *vcpu)
+{
+ int ret;
+
+ vcpu->arch.mmu_pte_list_desc_cache.kmem_cache = pte_list_desc_cache;
+ vcpu->arch.mmu_pte_list_desc_cache.gfp_zero = __GFP_ZERO;
+
+ vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache;
+ vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO;
+
+ vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
+
+ vcpu->arch.mmu = &vcpu->arch.root_mmu;
+ vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
+
+ ret = __kvm_mmu_create(vcpu, &vcpu->arch.guest_mmu);
+ if (ret)
+ return ret;
+
+ ret = __kvm_mmu_create(vcpu, &vcpu->arch.root_mmu);
+ if (ret)
+ goto fail_allocate_root;
+
+ return ret;
+ fail_allocate_root:
+ free_mmu_pages(&vcpu->arch.guest_mmu);
+ return ret;
+}
+
+#define BATCH_ZAP_PAGES 10
+static void kvm_zap_obsolete_pages(struct kvm *kvm)
+{
+ struct kvm_mmu_page *sp, *node;
+ int nr_zapped, batch = 0;
+ bool unstable;
+
+restart:
+ list_for_each_entry_safe_reverse(sp, node,
+ &kvm->arch.active_mmu_pages, link) {
+ /*
+ * No obsolete valid page exists before a newly created page
+ * since active_mmu_pages is a FIFO list.
+ */
+ if (!is_obsolete_sp(kvm, sp))
+ break;
+
+ /*
+ * Invalid pages should never land back on the list of active
+ * pages. Skip the bogus page, otherwise we'll get stuck in an
+ * infinite loop if the page gets put back on the list (again).
+ */
+ if (WARN_ON(sp->role.invalid))
+ continue;
+
+ /*
+ * No need to flush the TLB since we're only zapping shadow
+ * pages with an obsolete generation number and all vCPUS have
+ * loaded a new root, i.e. the shadow pages being zapped cannot
+ * be in active use by the guest.
+ */
+ if (batch >= BATCH_ZAP_PAGES &&
+ cond_resched_rwlock_write(&kvm->mmu_lock)) {
+ batch = 0;
+ goto restart;
+ }
+
+ unstable = __kvm_mmu_prepare_zap_page(kvm, sp,
+ &kvm->arch.zapped_obsolete_pages, &nr_zapped);
+ batch += nr_zapped;
+
+ if (unstable)
+ goto restart;
+ }
+
+ /*
+ * Kick all vCPUs (via remote TLB flush) before freeing the page tables
+ * to ensure KVM is not in the middle of a lockless shadow page table
+ * walk, which may reference the pages. The remote TLB flush itself is
+ * not required and is simply a convenient way to kick vCPUs as needed.
+ * KVM performs a local TLB flush when allocating a new root (see
+ * kvm_mmu_load()), and the reload in the caller ensure no vCPUs are
+ * running with an obsolete MMU.
+ */
+ kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages);
+}
+
+/*
+ * Fast invalidate all shadow pages and use lock-break technique
+ * to zap obsolete pages.
+ *
+ * It's required when memslot is being deleted or VM is being
+ * destroyed, in these cases, we should ensure that KVM MMU does
+ * not use any resource of the being-deleted slot or all slots
+ * after calling the function.
+ */
+static void kvm_mmu_zap_all_fast(struct kvm *kvm)
+{
+ lockdep_assert_held(&kvm->slots_lock);
+
+ write_lock(&kvm->mmu_lock);
+ trace_kvm_mmu_zap_all_fast(kvm);
+
+ /*
+ * Toggle mmu_valid_gen between '0' and '1'. Because slots_lock is
+ * held for the entire duration of zapping obsolete pages, it's
+ * impossible for there to be multiple invalid generations associated
+ * with *valid* shadow pages at any given time, i.e. there is exactly
+ * one valid generation and (at most) one invalid generation.
+ */
+ kvm->arch.mmu_valid_gen = kvm->arch.mmu_valid_gen ? 0 : 1;
+
+ /*
+ * In order to ensure all vCPUs drop their soon-to-be invalid roots,
+ * invalidating TDP MMU roots must be done while holding mmu_lock for
+ * write and in the same critical section as making the reload request,
+ * e.g. before kvm_zap_obsolete_pages() could drop mmu_lock and yield.
+ */
+ if (is_tdp_mmu_enabled(kvm))
+ kvm_tdp_mmu_invalidate_all_roots(kvm);
+
+ /*
+ * Notify all vcpus to reload its shadow page table and flush TLB.
+ * Then all vcpus will switch to new shadow page table with the new
+ * mmu_valid_gen.
+ *
+ * Note: we need to do this under the protection of mmu_lock,
+ * otherwise, vcpu would purge shadow page but miss tlb flush.
+ */
+ kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_FREE_OBSOLETE_ROOTS);
+
+ kvm_zap_obsolete_pages(kvm);
+
+ write_unlock(&kvm->mmu_lock);
+
+ /*
+ * Zap the invalidated TDP MMU roots, all SPTEs must be dropped before
+ * returning to the caller, e.g. if the zap is in response to a memslot
+ * deletion, mmu_notifier callbacks will be unable to reach the SPTEs
+ * associated with the deleted memslot once the update completes, and
+ * Deferring the zap until the final reference to the root is put would
+ * lead to use-after-free.
+ */
+ if (is_tdp_mmu_enabled(kvm))
+ kvm_tdp_mmu_zap_invalidated_roots(kvm);
+}
+
+static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
+{
+ return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
+}
+
+static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ struct kvm_page_track_notifier_node *node)
+{
+ kvm_mmu_zap_all_fast(kvm);
+}
+
+void kvm_mmu_init_vm(struct kvm *kvm)
+{
+ struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+ INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
+ INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
+ INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
+ spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
+
+ kvm_mmu_init_tdp_mmu(kvm);
+
+ node->track_write = kvm_mmu_pte_write;
+ node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
+ kvm_page_track_register_notifier(kvm, node);
+
+ kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
+ kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO;
+
+ kvm->arch.split_shadow_page_cache.gfp_zero = __GFP_ZERO;
+
+ kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache;
+ kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO;
+}
+
+static void mmu_free_vm_memory_caches(struct kvm *kvm)
+{
+ kvm_mmu_free_memory_cache(&kvm->arch.split_desc_cache);
+ kvm_mmu_free_memory_cache(&kvm->arch.split_page_header_cache);
+ kvm_mmu_free_memory_cache(&kvm->arch.split_shadow_page_cache);
+}
+
+void kvm_mmu_uninit_vm(struct kvm *kvm)
+{
+ struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+ kvm_page_track_unregister_notifier(kvm, node);
+
+ kvm_mmu_uninit_tdp_mmu(kvm);
+
+ mmu_free_vm_memory_caches(kvm);
+}
+
+static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
+{
+ const struct kvm_memory_slot *memslot;
+ struct kvm_memslots *slots;
+ struct kvm_memslot_iter iter;
+ bool flush = false;
+ gfn_t start, end;
+ int i;
+
+ if (!kvm_memslots_have_rmaps(kvm))
+ return flush;
+
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ slots = __kvm_memslots(kvm, i);
+
+ kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) {
+ memslot = iter.slot;
+ start = max(gfn_start, memslot->base_gfn);
+ end = min(gfn_end, memslot->base_gfn + memslot->npages);
+ if (WARN_ON_ONCE(start >= end))
+ continue;
+
+ flush = slot_handle_level_range(kvm, memslot, __kvm_zap_rmap,
+ PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL,
+ start, end - 1, true, flush);
+ }
+ }
+
+ return flush;
+}
+
+/*
+ * Invalidate (zap) SPTEs that cover GFNs from gfn_start and up to gfn_end
+ * (not including it)
+ */
+void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
+{
+ bool flush;
+
+ if (WARN_ON_ONCE(gfn_end <= gfn_start))
+ return;
+
+ write_lock(&kvm->mmu_lock);
+
+ kvm_mmu_invalidate_begin(kvm, 0, -1ul);
+
+ flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
+
+ if (is_tdp_mmu_enabled(kvm))
+ flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush);
+
+ if (flush)
+ kvm_flush_remote_tlbs_with_address(kvm, gfn_start,
+ gfn_end - gfn_start);
+
+ kvm_mmu_invalidate_end(kvm, 0, -1ul);
+
+ write_unlock(&kvm->mmu_lock);
+}
+
+static bool slot_rmap_write_protect(struct kvm *kvm,
+ struct kvm_rmap_head *rmap_head,
+ const struct kvm_memory_slot *slot)
+{
+ return rmap_write_protect(rmap_head, false);
+}
+
+void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot,
+ int start_level)
+{
+ if (kvm_memslots_have_rmaps(kvm)) {
+ write_lock(&kvm->mmu_lock);
+ slot_handle_level(kvm, memslot, slot_rmap_write_protect,
+ start_level, KVM_MAX_HUGEPAGE_LEVEL, false);
+ write_unlock(&kvm->mmu_lock);
+ }
+
+ if (is_tdp_mmu_enabled(kvm)) {
+ read_lock(&kvm->mmu_lock);
+ kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level);
+ read_unlock(&kvm->mmu_lock);
+ }
+}
+
+static inline bool need_topup(struct kvm_mmu_memory_cache *cache, int min)
+{
+ return kvm_mmu_memory_cache_nr_free_objects(cache) < min;
+}
+
+static bool need_topup_split_caches_or_resched(struct kvm *kvm)
+{
+ if (need_resched() || rwlock_needbreak(&kvm->mmu_lock))
+ return true;
+
+ /*
+ * In the worst case, SPLIT_DESC_CACHE_MIN_NR_OBJECTS descriptors are needed
+ * to split a single huge page. Calculating how many are actually needed
+ * is possible but not worth the complexity.
+ */
+ return need_topup(&kvm->arch.split_desc_cache, SPLIT_DESC_CACHE_MIN_NR_OBJECTS) ||
+ need_topup(&kvm->arch.split_page_header_cache, 1) ||
+ need_topup(&kvm->arch.split_shadow_page_cache, 1);
+}
+
+static int topup_split_caches(struct kvm *kvm)
+{
+ /*
+ * Allocating rmap list entries when splitting huge pages for nested
+ * MMUs is uncommon as KVM needs to use a list if and only if there is
+ * more than one rmap entry for a gfn, i.e. requires an L1 gfn to be
+ * aliased by multiple L2 gfns and/or from multiple nested roots with
+ * different roles. Aliasing gfns when using TDP is atypical for VMMs;
+ * a few gfns are often aliased during boot, e.g. when remapping BIOS,
+ * but aliasing rarely occurs post-boot or for many gfns. If there is
+ * only one rmap entry, rmap->val points directly at that one entry and
+ * doesn't need to allocate a list. Buffer the cache by the default
+ * capacity so that KVM doesn't have to drop mmu_lock to topup if KVM
+ * encounters an aliased gfn or two.
+ */
+ const int capacity = SPLIT_DESC_CACHE_MIN_NR_OBJECTS +
+ KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE;
+ int r;
+
+ lockdep_assert_held(&kvm->slots_lock);
+
+ r = __kvm_mmu_topup_memory_cache(&kvm->arch.split_desc_cache, capacity,
+ SPLIT_DESC_CACHE_MIN_NR_OBJECTS);
+ if (r)
+ return r;
+
+ r = kvm_mmu_topup_memory_cache(&kvm->arch.split_page_header_cache, 1);
+ if (r)
+ return r;
+
+ return kvm_mmu_topup_memory_cache(&kvm->arch.split_shadow_page_cache, 1);
+}
+
+static struct kvm_mmu_page *shadow_mmu_get_sp_for_split(struct kvm *kvm, u64 *huge_sptep)
+{
+ struct kvm_mmu_page *huge_sp = sptep_to_sp(huge_sptep);
+ struct shadow_page_caches caches = {};
+ union kvm_mmu_page_role role;
+ unsigned int access;
+ gfn_t gfn;
+
+ gfn = kvm_mmu_page_get_gfn(huge_sp, spte_index(huge_sptep));
+ access = kvm_mmu_page_get_access(huge_sp, spte_index(huge_sptep));
+
+ /*
+ * Note, huge page splitting always uses direct shadow pages, regardless
+ * of whether the huge page itself is mapped by a direct or indirect
+ * shadow page, since the huge page region itself is being directly
+ * mapped with smaller pages.
+ */
+ role = kvm_mmu_child_role(huge_sptep, /*direct=*/true, access);
+
+ /* Direct SPs do not require a shadowed_info_cache. */
+ caches.page_header_cache = &kvm->arch.split_page_header_cache;
+ caches.shadow_page_cache = &kvm->arch.split_shadow_page_cache;
+
+ /* Safe to pass NULL for vCPU since requesting a direct SP. */
+ return __kvm_mmu_get_shadow_page(kvm, NULL, &caches, gfn, role);
+}
+
+static void shadow_mmu_split_huge_page(struct kvm *kvm,
+ const struct kvm_memory_slot *slot,
+ u64 *huge_sptep)
+
+{
+ struct kvm_mmu_memory_cache *cache = &kvm->arch.split_desc_cache;
+ u64 huge_spte = READ_ONCE(*huge_sptep);
+ struct kvm_mmu_page *sp;
+ bool flush = false;
+ u64 *sptep, spte;
+ gfn_t gfn;
+ int index;
+
+ sp = shadow_mmu_get_sp_for_split(kvm, huge_sptep);
+
+ for (index = 0; index < SPTE_ENT_PER_PAGE; index++) {
+ sptep = &sp->spt[index];
+ gfn = kvm_mmu_page_get_gfn(sp, index);
+
+ /*
+ * The SP may already have populated SPTEs, e.g. if this huge
+ * page is aliased by multiple sptes with the same access
+ * permissions. These entries are guaranteed to map the same
+ * gfn-to-pfn translation since the SP is direct, so no need to
+ * modify them.
+ *
+ * However, if a given SPTE points to a lower level page table,
+ * that lower level page table may only be partially populated.
+ * Installing such SPTEs would effectively unmap a potion of the
+ * huge page. Unmapping guest memory always requires a TLB flush
+ * since a subsequent operation on the unmapped regions would
+ * fail to detect the need to flush.
+ */
+ if (is_shadow_present_pte(*sptep)) {
+ flush |= !is_last_spte(*sptep, sp->role.level);
+ continue;
+ }
+
+ spte = make_huge_page_split_spte(kvm, huge_spte, sp->role, index);
+ mmu_spte_set(sptep, spte);
+ __rmap_add(kvm, cache, slot, sptep, gfn, sp->role.access);
+ }
+
+ __link_shadow_page(kvm, cache, huge_sptep, sp, flush);
+}
+
+static int shadow_mmu_try_split_huge_page(struct kvm *kvm,
+ const struct kvm_memory_slot *slot,
+ u64 *huge_sptep)
+{
+ struct kvm_mmu_page *huge_sp = sptep_to_sp(huge_sptep);
+ int level, r = 0;
+ gfn_t gfn;
+ u64 spte;
+
+ /* Grab information for the tracepoint before dropping the MMU lock. */
+ gfn = kvm_mmu_page_get_gfn(huge_sp, spte_index(huge_sptep));
+ level = huge_sp->role.level;
+ spte = *huge_sptep;
+
+ if (kvm_mmu_available_pages(kvm) <= KVM_MIN_FREE_MMU_PAGES) {
+ r = -ENOSPC;
+ goto out;
+ }
+
+ if (need_topup_split_caches_or_resched(kvm)) {
+ write_unlock(&kvm->mmu_lock);
+ cond_resched();
+ /*
+ * If the topup succeeds, return -EAGAIN to indicate that the
+ * rmap iterator should be restarted because the MMU lock was
+ * dropped.
+ */
+ r = topup_split_caches(kvm) ?: -EAGAIN;
+ write_lock(&kvm->mmu_lock);
+ goto out;
+ }
+
+ shadow_mmu_split_huge_page(kvm, slot, huge_sptep);
+
+out:
+ trace_kvm_mmu_split_huge_page(gfn, spte, level, r);
+ return r;
+}
+
+static bool shadow_mmu_try_split_huge_pages(struct kvm *kvm,
+ struct kvm_rmap_head *rmap_head,
+ const struct kvm_memory_slot *slot)
+{
+ struct rmap_iterator iter;
+ struct kvm_mmu_page *sp;
+ u64 *huge_sptep;
+ int r;
+
+restart:
+ for_each_rmap_spte(rmap_head, &iter, huge_sptep) {
+ sp = sptep_to_sp(huge_sptep);
+
+ /* TDP MMU is enabled, so rmap only contains nested MMU SPs. */
+ if (WARN_ON_ONCE(!sp->role.guest_mode))
+ continue;
+
+ /* The rmaps should never contain non-leaf SPTEs. */
+ if (WARN_ON_ONCE(!is_large_pte(*huge_sptep)))
+ continue;
+
+ /* SPs with level >PG_LEVEL_4K should never by unsync. */
+ if (WARN_ON_ONCE(sp->unsync))
+ continue;
+
+ /* Don't bother splitting huge pages on invalid SPs. */
+ if (sp->role.invalid)
+ continue;
+
+ r = shadow_mmu_try_split_huge_page(kvm, slot, huge_sptep);
+
+ /*
+ * The split succeeded or needs to be retried because the MMU
+ * lock was dropped. Either way, restart the iterator to get it
+ * back into a consistent state.
+ */
+ if (!r || r == -EAGAIN)
+ goto restart;
+
+ /* The split failed and shouldn't be retried (e.g. -ENOMEM). */
+ break;
+ }
+
+ return false;
+}
+
+static void kvm_shadow_mmu_try_split_huge_pages(struct kvm *kvm,
+ const struct kvm_memory_slot *slot,
+ gfn_t start, gfn_t end,
+ int target_level)
+{
+ int level;
+
+ /*
+ * Split huge pages starting with KVM_MAX_HUGEPAGE_LEVEL and working
+ * down to the target level. This ensures pages are recursively split
+ * all the way to the target level. There's no need to split pages
+ * already at the target level.
+ */
+ for (level = KVM_MAX_HUGEPAGE_LEVEL; level > target_level; level--) {
+ slot_handle_level_range(kvm, slot, shadow_mmu_try_split_huge_pages,
+ level, level, start, end - 1, true, false);
+ }
+}
+
+/* Must be called with the mmu_lock held in write-mode. */
+void kvm_mmu_try_split_huge_pages(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot,
+ u64 start, u64 end,
+ int target_level)
+{
+ if (!is_tdp_mmu_enabled(kvm))
+ return;
+
+ if (kvm_memslots_have_rmaps(kvm))
+ kvm_shadow_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level);
+
+ kvm_tdp_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level, false);
+
+ /*
+ * A TLB flush is unnecessary at this point for the same resons as in
+ * kvm_mmu_slot_try_split_huge_pages().
+ */
+}
+
+void kvm_mmu_slot_try_split_huge_pages(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot,
+ int target_level)
+{
+ u64 start = memslot->base_gfn;
+ u64 end = start + memslot->npages;
+
+ if (!is_tdp_mmu_enabled(kvm))
+ return;
+
+ if (kvm_memslots_have_rmaps(kvm)) {
+ write_lock(&kvm->mmu_lock);
+ kvm_shadow_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level);
+ write_unlock(&kvm->mmu_lock);
+ }
+
+ read_lock(&kvm->mmu_lock);
+ kvm_tdp_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level, true);
+ read_unlock(&kvm->mmu_lock);
+
+ /*
+ * No TLB flush is necessary here. KVM will flush TLBs after
+ * write-protecting and/or clearing dirty on the newly split SPTEs to
+ * ensure that guest writes are reflected in the dirty log before the
+ * ioctl to enable dirty logging on this memslot completes. Since the
+ * split SPTEs retain the write and dirty bits of the huge SPTE, it is
+ * safe for KVM to decide if a TLB flush is necessary based on the split
+ * SPTEs.
+ */
+}
+
+static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
+ struct kvm_rmap_head *rmap_head,
+ const struct kvm_memory_slot *slot)
+{
+ u64 *sptep;
+ struct rmap_iterator iter;
+ int need_tlb_flush = 0;
+ struct kvm_mmu_page *sp;
+
+restart:
+ for_each_rmap_spte(rmap_head, &iter, sptep) {
+ sp = sptep_to_sp(sptep);
+
+ /*
+ * We cannot do huge page mapping for indirect shadow pages,
+ * which are found on the last rmap (level = 1) when not using
+ * tdp; such shadow pages are synced with the page table in
+ * the guest, and the guest page table is using 4K page size
+ * mapping if the indirect sp has level = 1.
+ */
+ if (sp->role.direct &&
+ sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
+ PG_LEVEL_NUM)) {
+ kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
+
+ if (kvm_available_flush_tlb_with_range())
+ kvm_flush_remote_tlbs_with_address(kvm, sp->gfn,
+ KVM_PAGES_PER_HPAGE(sp->role.level));
+ else
+ need_tlb_flush = 1;
+
+ goto restart;
+ }
+ }
+
+ return need_tlb_flush;
+}
+
+static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm,
+ const struct kvm_memory_slot *slot)
+{
+ /*
+ * Note, use KVM_MAX_HUGEPAGE_LEVEL - 1 since there's no need to zap
+ * pages that are already mapped at the maximum hugepage level.
+ */
+ if (slot_handle_level(kvm, slot, kvm_mmu_zap_collapsible_spte,
+ PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL - 1, true))
+ kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+}
+
+void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
+ const struct kvm_memory_slot *slot)
+{
+ if (kvm_memslots_have_rmaps(kvm)) {
+ write_lock(&kvm->mmu_lock);
+ kvm_rmap_zap_collapsible_sptes(kvm, slot);
+ write_unlock(&kvm->mmu_lock);
+ }
+
+ if (is_tdp_mmu_enabled(kvm)) {
+ read_lock(&kvm->mmu_lock);
+ kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot);
+ read_unlock(&kvm->mmu_lock);
+ }
+}
+
+void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot)
+{
+ /*
+ * All current use cases for flushing the TLBs for a specific memslot
+ * related to dirty logging, and many do the TLB flush out of mmu_lock.
+ * The interaction between the various operations on memslot must be
+ * serialized by slots_locks to ensure the TLB flush from one operation
+ * is observed by any other operation on the same memslot.
+ */
+ lockdep_assert_held(&kvm->slots_lock);
+ kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn,
+ memslot->npages);
+}
+
+void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot)
+{
+ if (kvm_memslots_have_rmaps(kvm)) {
+ write_lock(&kvm->mmu_lock);
+ /*
+ * Clear dirty bits only on 4k SPTEs since the legacy MMU only
+ * support dirty logging at a 4k granularity.
+ */
+ slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false);
+ write_unlock(&kvm->mmu_lock);
+ }
+
+ if (is_tdp_mmu_enabled(kvm)) {
+ read_lock(&kvm->mmu_lock);
+ kvm_tdp_mmu_clear_dirty_slot(kvm, memslot);
+ read_unlock(&kvm->mmu_lock);
+ }
+
+ /*
+ * The caller will flush the TLBs after this function returns.
+ *
+ * It's also safe to flush TLBs out of mmu lock here as currently this
+ * function is only used for dirty logging, in which case flushing TLB
+ * out of mmu lock also guarantees no dirty pages will be lost in
+ * dirty_bitmap.
+ */
+}
+
+void kvm_mmu_zap_all(struct kvm *kvm)
+{
+ struct kvm_mmu_page *sp, *node;
+ LIST_HEAD(invalid_list);
+ int ign;
+
+ write_lock(&kvm->mmu_lock);
+restart:
+ list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) {
+ if (WARN_ON(sp->role.invalid))
+ continue;
+ if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign))
+ goto restart;
+ if (cond_resched_rwlock_write(&kvm->mmu_lock))
+ goto restart;
+ }
+
+ kvm_mmu_commit_zap_page(kvm, &invalid_list);
+
+ if (is_tdp_mmu_enabled(kvm))
+ kvm_tdp_mmu_zap_all(kvm);
+
+ write_unlock(&kvm->mmu_lock);
+}
+
+void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
+{
+ WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
+
+ gen &= MMIO_SPTE_GEN_MASK;
+
+ /*
+ * Generation numbers are incremented in multiples of the number of
+ * address spaces in order to provide unique generations across all
+ * address spaces. Strip what is effectively the address space
+ * modifier prior to checking for a wrap of the MMIO generation so
+ * that a wrap in any address space is detected.
+ */
+ gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1);
+
+ /*
+ * The very rare case: if the MMIO generation number has wrapped,
+ * zap all shadow pages.
+ */
+ if (unlikely(gen == 0)) {
+ kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n");
+ kvm_mmu_zap_all_fast(kvm);
+ }
+}
+
+static unsigned long
+mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+ struct kvm *kvm;
+ int nr_to_scan = sc->nr_to_scan;
+ unsigned long freed = 0;
+
+ mutex_lock(&kvm_lock);
+
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ int idx;
+ LIST_HEAD(invalid_list);
+
+ /*
+ * Never scan more than sc->nr_to_scan VM instances.
+ * Will not hit this condition practically since we do not try
+ * to shrink more than one VM and it is very unlikely to see
+ * !n_used_mmu_pages so many times.
+ */
+ if (!nr_to_scan--)
+ break;
+ /*
+ * n_used_mmu_pages is accessed without holding kvm->mmu_lock
+ * here. We may skip a VM instance errorneosly, but we do not
+ * want to shrink a VM that only started to populate its MMU
+ * anyway.
+ */
+ if (!kvm->arch.n_used_mmu_pages &&
+ !kvm_has_zapped_obsolete_pages(kvm))
+ continue;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ write_lock(&kvm->mmu_lock);
+
+ if (kvm_has_zapped_obsolete_pages(kvm)) {
+ kvm_mmu_commit_zap_page(kvm,
+ &kvm->arch.zapped_obsolete_pages);
+ goto unlock;
+ }
+
+ freed = kvm_mmu_zap_oldest_mmu_pages(kvm, sc->nr_to_scan);
+
+unlock:
+ write_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ /*
+ * unfair on small ones
+ * per-vm shrinkers cry out
+ * sadness comes quickly
+ */
+ list_move_tail(&kvm->vm_list, &vm_list);
+ break;
+ }
+
+ mutex_unlock(&kvm_lock);
+ return freed;
+}
+
+static unsigned long
+mmu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ return percpu_counter_read_positive(&kvm_total_used_mmu_pages);
+}
+
+static struct shrinker mmu_shrinker = {
+ .count_objects = mmu_shrink_count,
+ .scan_objects = mmu_shrink_scan,
+ .seeks = DEFAULT_SEEKS * 10,
+};
+
+static void mmu_destroy_caches(void)
+{
+ kmem_cache_destroy(pte_list_desc_cache);
+ kmem_cache_destroy(mmu_page_header_cache);
+}
+
+static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp)
+{
+ if (nx_hugepage_mitigation_hard_disabled)
+ return sprintf(buffer, "never\n");
+
+ return param_get_bool(buffer, kp);
+}
+
+static bool get_nx_auto_mode(void)
+{
+ /* Return true when CPU has the bug, and mitigations are ON */
+ return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off();
+}
+
+static void __set_nx_huge_pages(bool val)
+{
+ nx_huge_pages = itlb_multihit_kvm_mitigation = val;
+}
+
+static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
+{
+ bool old_val = nx_huge_pages;
+ bool new_val;
+
+ if (nx_hugepage_mitigation_hard_disabled)
+ return -EPERM;
+
+ /* In "auto" mode deploy workaround only if CPU has the bug. */
+ if (sysfs_streq(val, "off")) {
+ new_val = 0;
+ } else if (sysfs_streq(val, "force")) {
+ new_val = 1;
+ } else if (sysfs_streq(val, "auto")) {
+ new_val = get_nx_auto_mode();
+ } else if (sysfs_streq(val, "never")) {
+ new_val = 0;
+
+ mutex_lock(&kvm_lock);
+ if (!list_empty(&vm_list)) {
+ mutex_unlock(&kvm_lock);
+ return -EBUSY;
+ }
+ nx_hugepage_mitigation_hard_disabled = true;
+ mutex_unlock(&kvm_lock);
+ } else if (kstrtobool(val, &new_val) < 0) {
+ return -EINVAL;
+ }
+
+ __set_nx_huge_pages(new_val);
+
+ if (new_val != old_val) {
+ struct kvm *kvm;
+
+ mutex_lock(&kvm_lock);
+
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ mutex_lock(&kvm->slots_lock);
+ kvm_mmu_zap_all_fast(kvm);
+ mutex_unlock(&kvm->slots_lock);
+
+ wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+ }
+ mutex_unlock(&kvm_lock);
+ }
+
+ return 0;
+}
+
+/*
+ * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as
+ * its default value of -1 is technically undefined behavior for a boolean.
+ * Forward the module init call to SPTE code so that it too can handle module
+ * params that need to be resolved/snapshot.
+ */
+void __init kvm_mmu_x86_module_init(void)
+{
+ if (nx_huge_pages == -1)
+ __set_nx_huge_pages(get_nx_auto_mode());
+
+ kvm_mmu_spte_module_init();
+}
+
+/*
+ * The bulk of the MMU initialization is deferred until the vendor module is
+ * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need
+ * to be reset when a potentially different vendor module is loaded.
+ */
+int kvm_mmu_vendor_module_init(void)
+{
+ int ret = -ENOMEM;
+
+ /*
+ * MMU roles use union aliasing which is, generally speaking, an
+ * undefined behavior. However, we supposedly know how compilers behave
+ * and the current status quo is unlikely to change. Guardians below are
+ * supposed to let us know if the assumption becomes false.
+ */
+ BUILD_BUG_ON(sizeof(union kvm_mmu_page_role) != sizeof(u32));
+ BUILD_BUG_ON(sizeof(union kvm_mmu_extended_role) != sizeof(u32));
+ BUILD_BUG_ON(sizeof(union kvm_cpu_role) != sizeof(u64));
+
+ kvm_mmu_reset_all_pte_masks();
+
+ pte_list_desc_cache = kmem_cache_create("pte_list_desc",
+ sizeof(struct pte_list_desc),
+ 0, SLAB_ACCOUNT, NULL);
+ if (!pte_list_desc_cache)
+ goto out;
+
+ mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header",
+ sizeof(struct kvm_mmu_page),
+ 0, SLAB_ACCOUNT, NULL);
+ if (!mmu_page_header_cache)
+ goto out;
+
+ if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL))
+ goto out;
+
+ ret = register_shrinker(&mmu_shrinker, "x86-mmu");
+ if (ret)
+ goto out_shrinker;
+
+ return 0;
+
+out_shrinker:
+ percpu_counter_destroy(&kvm_total_used_mmu_pages);
+out:
+ mmu_destroy_caches();
+ return ret;
+}
+
+void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
+{
+ kvm_mmu_unload(vcpu);
+ free_mmu_pages(&vcpu->arch.root_mmu);
+ free_mmu_pages(&vcpu->arch.guest_mmu);
+ mmu_free_memory_caches(vcpu);
+}
+
+void kvm_mmu_vendor_module_exit(void)
+{
+ mmu_destroy_caches();
+ percpu_counter_destroy(&kvm_total_used_mmu_pages);
+ unregister_shrinker(&mmu_shrinker);
+}
+
+/*
+ * Calculate the effective recovery period, accounting for '0' meaning "let KVM
+ * select a halving time of 1 hour". Returns true if recovery is enabled.
+ */
+static bool calc_nx_huge_pages_recovery_period(uint *period)
+{
+ /*
+ * Use READ_ONCE to get the params, this may be called outside of the
+ * param setters, e.g. by the kthread to compute its next timeout.
+ */
+ bool enabled = READ_ONCE(nx_huge_pages);
+ uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
+
+ if (!enabled || !ratio)
+ return false;
+
+ *period = READ_ONCE(nx_huge_pages_recovery_period_ms);
+ if (!*period) {
+ /* Make sure the period is not less than one second. */
+ ratio = min(ratio, 3600u);
+ *period = 60 * 60 * 1000 / ratio;
+ }
+ return true;
+}
+
+static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp)
+{
+ bool was_recovery_enabled, is_recovery_enabled;
+ uint old_period, new_period;
+ int err;
+
+ if (nx_hugepage_mitigation_hard_disabled)
+ return -EPERM;
+
+ was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period);
+
+ err = param_set_uint(val, kp);
+ if (err)
+ return err;
+
+ is_recovery_enabled = calc_nx_huge_pages_recovery_period(&new_period);
+
+ if (is_recovery_enabled &&
+ (!was_recovery_enabled || old_period > new_period)) {
+ struct kvm *kvm;
+
+ mutex_lock(&kvm_lock);
+
+ list_for_each_entry(kvm, &vm_list, vm_list)
+ wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+
+ mutex_unlock(&kvm_lock);
+ }
+
+ return err;
+}
+
+static void kvm_recover_nx_lpages(struct kvm *kvm)
+{
+ unsigned long nx_lpage_splits = kvm->stat.nx_lpage_splits;
+ int rcu_idx;
+ struct kvm_mmu_page *sp;
+ unsigned int ratio;
+ LIST_HEAD(invalid_list);
+ bool flush = false;
+ ulong to_zap;
+
+ rcu_idx = srcu_read_lock(&kvm->srcu);
+ write_lock(&kvm->mmu_lock);
+
+ /*
+ * Zapping TDP MMU shadow pages, including the remote TLB flush, must
+ * be done under RCU protection, because the pages are freed via RCU
+ * callback.
+ */
+ rcu_read_lock();
+
+ ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
+ to_zap = ratio ? DIV_ROUND_UP(nx_lpage_splits, ratio) : 0;
+ for ( ; to_zap; --to_zap) {
+ if (list_empty(&kvm->arch.lpage_disallowed_mmu_pages))
+ break;
+
+ /*
+ * We use a separate list instead of just using active_mmu_pages
+ * because the number of lpage_disallowed pages is expected to
+ * be relatively small compared to the total.
+ */
+ sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages,
+ struct kvm_mmu_page,
+ lpage_disallowed_link);
+ WARN_ON_ONCE(!sp->lpage_disallowed);
+ if (is_tdp_mmu_page(sp)) {
+ flush |= kvm_tdp_mmu_zap_sp(kvm, sp);
+ } else {
+ kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
+ WARN_ON_ONCE(sp->lpage_disallowed);
+ }
+
+ if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
+ kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
+ rcu_read_unlock();
+
+ cond_resched_rwlock_write(&kvm->mmu_lock);
+ flush = false;
+
+ rcu_read_lock();
+ }
+ }
+ kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
+
+ rcu_read_unlock();
+
+ write_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, rcu_idx);
+}
+
+static long get_nx_lpage_recovery_timeout(u64 start_time)
+{
+ bool enabled;
+ uint period;
+
+ enabled = calc_nx_huge_pages_recovery_period(&period);
+
+ return enabled ? start_time + msecs_to_jiffies(period) - get_jiffies_64()
+ : MAX_SCHEDULE_TIMEOUT;
+}
+
+static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
+{
+ u64 start_time;
+ long remaining_time;
+
+ while (true) {
+ start_time = get_jiffies_64();
+ remaining_time = get_nx_lpage_recovery_timeout(start_time);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop() && remaining_time > 0) {
+ schedule_timeout(remaining_time);
+ remaining_time = get_nx_lpage_recovery_timeout(start_time);
+ set_current_state(TASK_INTERRUPTIBLE);
+ }
+
+ set_current_state(TASK_RUNNING);
+
+ if (kthread_should_stop())
+ return 0;
+
+ kvm_recover_nx_lpages(kvm);
+ }
+}
+
+int kvm_mmu_post_init_vm(struct kvm *kvm)
+{
+ int err;
+
+ if (nx_hugepage_mitigation_hard_disabled)
+ return 0;
+
+ err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0,
+ "kvm-nx-lpage-recovery",
+ &kvm->arch.nx_lpage_recovery_thread);
+ if (!err)
+ kthread_unpark(kvm->arch.nx_lpage_recovery_thread);
+
+ return err;
+}
+
+void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
+{
+ if (kvm->arch.nx_lpage_recovery_thread)
+ kthread_stop(kvm->arch.nx_lpage_recovery_thread);
+}
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
new file mode 100644
index 000000000..0a9d5f292
--- /dev/null
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -0,0 +1,320 @@
+/* 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>
+
+#undef MMU_DEBUG
+
+#ifdef MMU_DEBUG
+extern bool dbg;
+
+#define pgprintk(x...) do { if (dbg) printk(x); } while (0)
+#define rmap_printk(fmt, args...) do { if (dbg) printk("%s: " fmt, __func__, ## args); } while (0)
+#define MMU_WARN_ON(x) WARN_ON(x)
+#else
+#define pgprintk(x...) do { } while (0)
+#define rmap_printk(x...) do { } while (0)
+#define MMU_WARN_ON(x) do { } while (0)
+#endif
+
+/* Page table builder macros common to shadow (host) PTEs and guest PTEs. */
+#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;
+ };
+ bool lpage_disallowed; /* Can't be replaced by an equiv large page */
+
+ /*
+ * 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;
+ };
+ unsigned int unsync_children;
+ union {
+ struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
+ tdp_ptep_t ptep;
+ };
+ DECLARE_BITMAP(unsync_child_bitmap, 512);
+
+ struct list_head lpage_disallowed_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
+
+ /* Number of writes since the last time traversal visited this page. */
+ atomic_t write_flooding_count;
+
+#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 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 *sptep_to_sp(u64 *sptep)
+{
+ return to_shadow_page(__pa(sptep));
+}
+
+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 kvm_mmu_page_ad_need_write_protect(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_x86_ops.cpu_dirty_log_size && sp->role.guest_mode;
+}
+
+int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
+ gfn_t gfn, bool can_unsync, 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);
+void kvm_flush_remote_tlbs_with_address(struct kvm *kvm,
+ u64 start_gfn, u64 pages);
+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 u32 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 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. */
+ gfn_t gfn;
+
+ /* The memslot containing gfn. May be NULL. */
+ struct kvm_memory_slot *slot;
+
+ /* Outputs of kvm_faultin_pfn. */
+ kvm_pfn_t pfn;
+ hva_t hva;
+ bool map_writable;
+};
+
+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_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. Somewhat arbitrarily use '0' for CONTINUE, which
+ * will allow for efficient machine code when checking for CONTINUE, e.g.
+ * "TEST %rax, %rax, JNZ", as all "stop!" values are non-zero.
+ */
+enum {
+ RET_PF_CONTINUE = 0,
+ RET_PF_RETRY,
+ RET_PF_EMULATE,
+ RET_PF_INVALID,
+ RET_PF_FIXED,
+ RET_PF_SPURIOUS,
+};
+
+static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+ u32 err, bool prefetch)
+{
+ 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,
+ };
+ int r;
+
+ /*
+ * Async #PF "faults", a.k.a. prefetch faults, are not faults from the
+ * guest perspective and have already been counted at the time of the
+ * original fault.
+ */
+ if (!prefetch)
+ vcpu->stat.pf_taken++;
+
+ if (IS_ENABLED(CONFIG_RETPOLINE) && fault.is_tdp)
+ r = kvm_tdp_page_fault(vcpu, &fault);
+ else
+ r = vcpu->arch.mmu->page_fault(vcpu, &fault);
+
+ /*
+ * Similar to above, prefetch faults aren't truly spurious, and the
+ * async #PF path doesn't do emulation. Do count faults that are fixed
+ * by the async #PF handler though, otherwise they'll never be counted.
+ */
+ if (r == RET_PF_FIXED)
+ vcpu->stat.pf_fixed++;
+ else if (prefetch)
+ ;
+ else if (r == RET_PF_EMULATE)
+ vcpu->stat.pf_emulate++;
+ else if (r == RET_PF_SPURIOUS)
+ vcpu->stat.pf_spurious++;
+ return r;
+}
+
+int kvm_mmu_max_mapping_level(struct kvm *kvm,
+ const struct kvm_memory_slot *slot, gfn_t gfn,
+ int max_level);
+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 *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
+
+void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
+void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
+
+#endif /* __KVM_X86_MMU_INTERNAL_H */
diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
new file mode 100644
index 000000000..ae86820ce
--- /dev/null
+++ b/arch/x86/kvm/mmu/mmutrace.h
@@ -0,0 +1,451 @@
+/* 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[] = { \
+ "---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux" \
+ }; \
+ 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_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_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(u32, 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->arch.n_used_mmu_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 = is_executable_pte(__entry->spte);
+ __entry->u = shadow_user_mask ? !!(__entry->spte & shadow_user_mask) : -1;
+ ),
+
+ 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 == -1 ? "" : (__entry->u ? "u" : "-"),
+ __entry->level, __entry->sptep
+ )
+);
+
+TRACE_EVENT(
+ kvm_mmu_spte_requested,
+ TP_PROTO(struct kvm_page_fault *fault),
+ TP_ARGS(fault),
+
+ TP_STRUCT__entry(
+ __field(u64, gfn)
+ __field(u64, pfn)
+ __field(u8, level)
+ ),
+
+ 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;
+ ),
+
+ TP_printk("gfn %llx pfn %llx level %d",
+ __entry->gfn, __entry->pfn, __entry->level
+ )
+);
+
+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>
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
new file mode 100644
index 000000000..2e09d1b62
--- /dev/null
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -0,0 +1,302 @@
+// 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>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/rculist.h>
+
+#include <asm/kvm_page_track.h>
+
+#include "mmu.h"
+#include "mmu_internal.h"
+
+bool kvm_page_track_write_tracking_enabled(struct kvm *kvm)
+{
+ return IS_ENABLED(CONFIG_KVM_EXTERNAL_WRITE_TRACKING) ||
+ !tdp_enabled || kvm_shadow_root_allocated(kvm);
+}
+
+void kvm_page_track_free_memslot(struct kvm_memory_slot *slot)
+{
+ int i;
+
+ for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
+ kvfree(slot->arch.gfn_track[i]);
+ slot->arch.gfn_track[i] = NULL;
+ }
+}
+
+int kvm_page_track_create_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ unsigned long npages)
+{
+ int i;
+
+ for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
+ if (i == KVM_PAGE_TRACK_WRITE &&
+ !kvm_page_track_write_tracking_enabled(kvm))
+ continue;
+
+ slot->arch.gfn_track[i] =
+ __vcalloc(npages, sizeof(*slot->arch.gfn_track[i]),
+ GFP_KERNEL_ACCOUNT);
+ if (!slot->arch.gfn_track[i])
+ goto track_free;
+ }
+
+ return 0;
+
+track_free:
+ kvm_page_track_free_memslot(slot);
+ return -ENOMEM;
+}
+
+static inline bool page_track_mode_is_valid(enum kvm_page_track_mode mode)
+{
+ if (mode < 0 || mode >= KVM_PAGE_TRACK_MAX)
+ return false;
+
+ return true;
+}
+
+int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot)
+{
+ unsigned short *gfn_track;
+
+ if (slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE])
+ return 0;
+
+ gfn_track = __vcalloc(slot->npages, sizeof(*gfn_track),
+ GFP_KERNEL_ACCOUNT);
+ if (gfn_track == NULL)
+ return -ENOMEM;
+
+ slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE] = gfn_track;
+ return 0;
+}
+
+static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
+ enum kvm_page_track_mode mode, short count)
+{
+ int index, val;
+
+ index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
+
+ val = slot->arch.gfn_track[mode][index];
+
+ if (WARN_ON(val + count < 0 || val + count > USHRT_MAX))
+ return;
+
+ slot->arch.gfn_track[mode][index] += count;
+}
+
+/*
+ * add guest page to the tracking pool so that corresponding access on that
+ * page will be intercepted.
+ *
+ * It should be called under the protection both of mmu-lock and kvm->srcu
+ * or kvm->slots_lock.
+ *
+ * @kvm: the guest instance we are interested in.
+ * @slot: the @gfn belongs to.
+ * @gfn: the guest page.
+ * @mode: tracking mode, currently only write track is supported.
+ */
+void kvm_slot_page_track_add_page(struct kvm *kvm,
+ struct kvm_memory_slot *slot, gfn_t gfn,
+ enum kvm_page_track_mode mode)
+{
+
+ if (WARN_ON(!page_track_mode_is_valid(mode)))
+ return;
+
+ if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE &&
+ !kvm_page_track_write_tracking_enabled(kvm)))
+ return;
+
+ update_gfn_track(slot, gfn, mode, 1);
+
+ /*
+ * new track stops large page mapping for the
+ * tracked page.
+ */
+ kvm_mmu_gfn_disallow_lpage(slot, gfn);
+
+ if (mode == KVM_PAGE_TRACK_WRITE)
+ if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
+ kvm_flush_remote_tlbs(kvm);
+}
+EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
+
+/*
+ * remove the guest page from the tracking pool which stops the interception
+ * of corresponding access on that page. It is the opposed operation of
+ * kvm_slot_page_track_add_page().
+ *
+ * It should be called under the protection both of mmu-lock and kvm->srcu
+ * or kvm->slots_lock.
+ *
+ * @kvm: the guest instance we are interested in.
+ * @slot: the @gfn belongs to.
+ * @gfn: the guest page.
+ * @mode: tracking mode, currently only write track is supported.
+ */
+void kvm_slot_page_track_remove_page(struct kvm *kvm,
+ struct kvm_memory_slot *slot, gfn_t gfn,
+ enum kvm_page_track_mode mode)
+{
+ if (WARN_ON(!page_track_mode_is_valid(mode)))
+ return;
+
+ if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE &&
+ !kvm_page_track_write_tracking_enabled(kvm)))
+ return;
+
+ update_gfn_track(slot, gfn, mode, -1);
+
+ /*
+ * allow large page mapping for the tracked page
+ * after the tracker is gone.
+ */
+ kvm_mmu_gfn_allow_lpage(slot, gfn);
+}
+EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page);
+
+/*
+ * check if the corresponding access on the specified guest page is tracked.
+ */
+bool kvm_slot_page_track_is_active(struct kvm *kvm,
+ const struct kvm_memory_slot *slot,
+ gfn_t gfn, enum kvm_page_track_mode mode)
+{
+ int index;
+
+ if (WARN_ON(!page_track_mode_is_valid(mode)))
+ return false;
+
+ if (!slot)
+ return false;
+
+ if (mode == KVM_PAGE_TRACK_WRITE &&
+ !kvm_page_track_write_tracking_enabled(kvm))
+ return false;
+
+ index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
+ return !!READ_ONCE(slot->arch.gfn_track[mode][index]);
+}
+
+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);
+}
+
+/*
+ * register the notifier so that event interception for the tracked guest
+ * pages can be received.
+ */
+void
+kvm_page_track_register_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_add_head_rcu(&n->node, &head->track_notifier_list);
+ write_unlock(&kvm->mmu_lock);
+}
+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);
+}
+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_vcpu *vcpu, 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 = &vcpu->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(vcpu, gpa, new, bytes, n);
+ srcu_read_unlock(&head->track_srcu, idx);
+}
+
+/*
+ * Notify the node that memory slot is being removed or moved so that it can
+ * drop write-protection for the pages in the memory slot.
+ *
+ * The node should figure out it has any write-protected pages in this slot
+ * by itself.
+ */
+void kvm_page_track_flush_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_flush_slot)
+ n->track_flush_slot(kvm, slot, n);
+ srcu_read_unlock(&head->track_srcu, idx);
+}
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
new file mode 100644
index 000000000..1f4f5e703
--- /dev/null
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -0,0 +1,1116 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Kernel-based Virtual Machine driver for Linux
+ *
+ * This module enables machines with Intel VT-x extensions to run virtual
+ * machines without emulation or binary translation.
+ *
+ * MMU support
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ *
+ * Authors:
+ * Yaniv Kamay <yaniv@qumranet.com>
+ * Avi Kivity <avi@qumranet.com>
+ */
+
+/*
+ * The MMU needs to be able to access/walk 32-bit and 64-bit guest page tables,
+ * as well as guest EPT tables, so the code in this file is compiled thrice,
+ * once per guest PTE type. The per-type defines are #undef'd at the end.
+ */
+
+#if PTTYPE == 64
+ #define pt_element_t u64
+ #define guest_walker guest_walker64
+ #define FNAME(name) paging##64_##name
+ #define PT_LEVEL_BITS 9
+ #define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
+ #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
+ #define PT_HAVE_ACCESSED_DIRTY(mmu) true
+ #ifdef CONFIG_X86_64
+ #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
+ #else
+ #define PT_MAX_FULL_LEVELS 2
+ #endif
+#elif PTTYPE == 32
+ #define pt_element_t u32
+ #define guest_walker guest_walker32
+ #define FNAME(name) paging##32_##name
+ #define PT_LEVEL_BITS 10
+ #define PT_MAX_FULL_LEVELS 2
+ #define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
+ #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
+ #define PT_HAVE_ACCESSED_DIRTY(mmu) true
+
+ #define PT32_DIR_PSE36_SIZE 4
+ #define PT32_DIR_PSE36_SHIFT 13
+ #define PT32_DIR_PSE36_MASK \
+ (((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT)
+#elif PTTYPE == PTTYPE_EPT
+ #define pt_element_t u64
+ #define guest_walker guest_walkerEPT
+ #define FNAME(name) ept_##name
+ #define PT_LEVEL_BITS 9
+ #define PT_GUEST_DIRTY_SHIFT 9
+ #define PT_GUEST_ACCESSED_SHIFT 8
+ #define PT_HAVE_ACCESSED_DIRTY(mmu) (!(mmu)->cpu_role.base.ad_disabled)
+ #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
+#else
+ #error Invalid PTTYPE value
+#endif
+
+/* Common logic, but per-type values. These also need to be undefined. */
+#define PT_BASE_ADDR_MASK ((pt_element_t)(((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)))
+#define PT_LVL_ADDR_MASK(lvl) __PT_LVL_ADDR_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS)
+#define PT_LVL_OFFSET_MASK(lvl) __PT_LVL_OFFSET_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS)
+#define PT_INDEX(addr, lvl) __PT_INDEX(addr, lvl, PT_LEVEL_BITS)
+
+#define PT_GUEST_DIRTY_MASK (1 << PT_GUEST_DIRTY_SHIFT)
+#define PT_GUEST_ACCESSED_MASK (1 << PT_GUEST_ACCESSED_SHIFT)
+
+#define gpte_to_gfn_lvl FNAME(gpte_to_gfn_lvl)
+#define gpte_to_gfn(pte) gpte_to_gfn_lvl((pte), PG_LEVEL_4K)
+
+/*
+ * The guest_walker structure emulates the behavior of the hardware page
+ * table walker.
+ */
+struct guest_walker {
+ int level;
+ unsigned max_level;
+ gfn_t table_gfn[PT_MAX_FULL_LEVELS];
+ pt_element_t ptes[PT_MAX_FULL_LEVELS];
+ pt_element_t prefetch_ptes[PTE_PREFETCH_NUM];
+ gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
+ pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
+ bool pte_writable[PT_MAX_FULL_LEVELS];
+ unsigned int pt_access[PT_MAX_FULL_LEVELS];
+ unsigned int pte_access;
+ gfn_t gfn;
+ struct x86_exception fault;
+};
+
+#if PTTYPE == 32
+static inline gfn_t pse36_gfn_delta(u32 gpte)
+{
+ int shift = 32 - PT32_DIR_PSE36_SHIFT - PAGE_SHIFT;
+
+ return (gpte & PT32_DIR_PSE36_MASK) << shift;
+}
+#endif
+
+static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl)
+{
+ return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT;
+}
+
+static inline void FNAME(protect_clean_gpte)(struct kvm_mmu *mmu, unsigned *access,
+ unsigned gpte)
+{
+ unsigned mask;
+
+ /* dirty bit is not supported, so no need to track it */
+ if (!PT_HAVE_ACCESSED_DIRTY(mmu))
+ return;
+
+ BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK);
+
+ mask = (unsigned)~ACC_WRITE_MASK;
+ /* Allow write access to dirty gptes */
+ mask |= (gpte >> (PT_GUEST_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) &
+ PT_WRITABLE_MASK;
+ *access &= mask;
+}
+
+static inline int FNAME(is_present_gpte)(unsigned long pte)
+{
+#if PTTYPE != PTTYPE_EPT
+ return pte & PT_PRESENT_MASK;
+#else
+ return pte & 7;
+#endif
+}
+
+static bool FNAME(is_bad_mt_xwr)(struct rsvd_bits_validate *rsvd_check, u64 gpte)
+{
+#if PTTYPE != PTTYPE_EPT
+ return false;
+#else
+ return __is_bad_mt_xwr(rsvd_check, gpte);
+#endif
+}
+
+static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
+{
+ return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level) ||
+ FNAME(is_bad_mt_xwr)(&mmu->guest_rsvd_check, gpte);
+}
+
+static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *sp, u64 *spte,
+ u64 gpte)
+{
+ if (!FNAME(is_present_gpte)(gpte))
+ goto no_present;
+
+ /* Prefetch only accessed entries (unless A/D bits are disabled). */
+ if (PT_HAVE_ACCESSED_DIRTY(vcpu->arch.mmu) &&
+ !(gpte & PT_GUEST_ACCESSED_MASK))
+ goto no_present;
+
+ if (FNAME(is_rsvd_bits_set)(vcpu->arch.mmu, gpte, PG_LEVEL_4K))
+ goto no_present;
+
+ return false;
+
+no_present:
+ drop_spte(vcpu->kvm, spte);
+ return true;
+}
+
+/*
+ * For PTTYPE_EPT, a page table can be executable but not readable
+ * on supported processors. Therefore, set_spte does not automatically
+ * set bit 0 if execute only is supported. Here, we repurpose ACC_USER_MASK
+ * to signify readability since it isn't used in the EPT case
+ */
+static inline unsigned FNAME(gpte_access)(u64 gpte)
+{
+ unsigned access;
+#if PTTYPE == PTTYPE_EPT
+ access = ((gpte & VMX_EPT_WRITABLE_MASK) ? ACC_WRITE_MASK : 0) |
+ ((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) |
+ ((gpte & VMX_EPT_READABLE_MASK) ? ACC_USER_MASK : 0);
+#else
+ BUILD_BUG_ON(ACC_EXEC_MASK != PT_PRESENT_MASK);
+ BUILD_BUG_ON(ACC_EXEC_MASK != 1);
+ access = gpte & (PT_WRITABLE_MASK | PT_USER_MASK | PT_PRESENT_MASK);
+ /* Combine NX with P (which is set here) to get ACC_EXEC_MASK. */
+ access ^= (gpte >> PT64_NX_SHIFT);
+#endif
+
+ return access;
+}
+
+static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *mmu,
+ struct guest_walker *walker,
+ gpa_t addr, int write_fault)
+{
+ unsigned level, index;
+ pt_element_t pte, orig_pte;
+ pt_element_t __user *ptep_user;
+ gfn_t table_gfn;
+ int ret;
+
+ /* dirty/accessed bits are not supported, so no need to update them */
+ if (!PT_HAVE_ACCESSED_DIRTY(mmu))
+ return 0;
+
+ for (level = walker->max_level; level >= walker->level; --level) {
+ pte = orig_pte = walker->ptes[level - 1];
+ table_gfn = walker->table_gfn[level - 1];
+ ptep_user = walker->ptep_user[level - 1];
+ index = offset_in_page(ptep_user) / sizeof(pt_element_t);
+ if (!(pte & PT_GUEST_ACCESSED_MASK)) {
+ trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte));
+ pte |= PT_GUEST_ACCESSED_MASK;
+ }
+ if (level == walker->level && write_fault &&
+ !(pte & PT_GUEST_DIRTY_MASK)) {
+ trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
+#if PTTYPE == PTTYPE_EPT
+ if (kvm_x86_ops.nested_ops->write_log_dirty(vcpu, addr))
+ return -EINVAL;
+#endif
+ pte |= PT_GUEST_DIRTY_MASK;
+ }
+ if (pte == orig_pte)
+ continue;
+
+ /*
+ * If the slot is read-only, simply do not process the accessed
+ * and dirty bits. This is the correct thing to do if the slot
+ * is ROM, and page tables in read-as-ROM/write-as-MMIO slots
+ * are only supported if the accessed and dirty bits are already
+ * set in the ROM (so that MMIO writes are never needed).
+ *
+ * Note that NPT does not allow this at all and faults, since
+ * it always wants nested page table entries for the guest
+ * page tables to be writable. And EPT works but will simply
+ * overwrite the read-only memory to set the accessed and dirty
+ * bits.
+ */
+ if (unlikely(!walker->pte_writable[level - 1]))
+ continue;
+
+ ret = __try_cmpxchg_user(ptep_user, &orig_pte, pte, fault);
+ if (ret)
+ return ret;
+
+ kvm_vcpu_mark_page_dirty(vcpu, table_gfn);
+ walker->ptes[level - 1] = pte;
+ }
+ return 0;
+}
+
+static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte)
+{
+ unsigned pkeys = 0;
+#if PTTYPE == 64
+ pte_t pte = {.pte = gpte};
+
+ pkeys = pte_flags_pkey(pte_flags(pte));
+#endif
+ return pkeys;
+}
+
+static inline bool FNAME(is_last_gpte)(struct kvm_mmu *mmu,
+ unsigned int level, unsigned int gpte)
+{
+ /*
+ * For EPT and PAE paging (both variants), bit 7 is either reserved at
+ * all level or indicates a huge page (ignoring CR3/EPTP). In either
+ * case, bit 7 being set terminates the walk.
+ */
+#if PTTYPE == 32
+ /*
+ * 32-bit paging requires special handling because bit 7 is ignored if
+ * CR4.PSE=0, not reserved. Clear bit 7 in the gpte if the level is
+ * greater than the last level for which bit 7 is the PAGE_SIZE bit.
+ *
+ * The RHS has bit 7 set iff level < (2 + PSE). If it is clear, bit 7
+ * is not reserved and does not indicate a large page at this level,
+ * so clear PT_PAGE_SIZE_MASK in gpte if that is the case.
+ */
+ gpte &= level - (PT32_ROOT_LEVEL + mmu->cpu_role.ext.cr4_pse);
+#endif
+ /*
+ * PG_LEVEL_4K always terminates. The RHS has bit 7 set
+ * iff level <= PG_LEVEL_4K, which for our purpose means
+ * level == PG_LEVEL_4K; set PT_PAGE_SIZE_MASK in gpte then.
+ */
+ gpte |= level - PG_LEVEL_4K - 1;
+
+ return gpte & PT_PAGE_SIZE_MASK;
+}
+/*
+ * Fetch a guest pte for a guest virtual address, or for an L2's GPA.
+ */
+static int FNAME(walk_addr_generic)(struct guest_walker *walker,
+ struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ gpa_t addr, u64 access)
+{
+ int ret;
+ pt_element_t pte;
+ pt_element_t __user *ptep_user;
+ gfn_t table_gfn;
+ u64 pt_access, pte_access;
+ unsigned index, accessed_dirty, pte_pkey;
+ u64 nested_access;
+ gpa_t pte_gpa;
+ bool have_ad;
+ int offset;
+ u64 walk_nx_mask = 0;
+ const int write_fault = access & PFERR_WRITE_MASK;
+ const int user_fault = access & PFERR_USER_MASK;
+ const int fetch_fault = access & PFERR_FETCH_MASK;
+ u16 errcode = 0;
+ gpa_t real_gpa;
+ gfn_t gfn;
+
+ trace_kvm_mmu_pagetable_walk(addr, access);
+retry_walk:
+ walker->level = mmu->cpu_role.base.level;
+ pte = kvm_mmu_get_guest_pgd(vcpu, mmu);
+ have_ad = PT_HAVE_ACCESSED_DIRTY(mmu);
+
+#if PTTYPE == 64
+ walk_nx_mask = 1ULL << PT64_NX_SHIFT;
+ if (walker->level == PT32E_ROOT_LEVEL) {
+ pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
+ trace_kvm_mmu_paging_element(pte, walker->level);
+ if (!FNAME(is_present_gpte)(pte))
+ goto error;
+ --walker->level;
+ }
+#endif
+ walker->max_level = walker->level;
+ ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu)));
+
+ /*
+ * FIXME: on Intel processors, loads of the PDPTE registers for PAE paging
+ * by the MOV to CR instruction are treated as reads and do not cause the
+ * processor to set the dirty flag in any EPT paging-structure entry.
+ */
+ nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK;
+
+ pte_access = ~0;
+ ++walker->level;
+
+ do {
+ unsigned long host_addr;
+
+ pt_access = pte_access;
+ --walker->level;
+
+ index = PT_INDEX(addr, walker->level);
+ table_gfn = gpte_to_gfn(pte);
+ offset = index * sizeof(pt_element_t);
+ pte_gpa = gfn_to_gpa(table_gfn) + offset;
+
+ BUG_ON(walker->level < 1);
+ walker->table_gfn[walker->level - 1] = table_gfn;
+ walker->pte_gpa[walker->level - 1] = pte_gpa;
+
+ real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(table_gfn),
+ nested_access, &walker->fault);
+
+ /*
+ * FIXME: This can happen if emulation (for of an INS/OUTS
+ * instruction) triggers a nested page fault. The exit
+ * qualification / exit info field will incorrectly have
+ * "guest page access" as the nested page fault's cause,
+ * instead of "guest page structure access". To fix this,
+ * the x86_exception struct should be augmented with enough
+ * information to fix the exit_qualification or exit_info_1
+ * fields.
+ */
+ if (unlikely(real_gpa == INVALID_GPA))
+ return 0;
+
+ host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa),
+ &walker->pte_writable[walker->level - 1]);
+ if (unlikely(kvm_is_error_hva(host_addr)))
+ goto error;
+
+ ptep_user = (pt_element_t __user *)((void *)host_addr + offset);
+ if (unlikely(__get_user(pte, ptep_user)))
+ goto error;
+ walker->ptep_user[walker->level - 1] = ptep_user;
+
+ trace_kvm_mmu_paging_element(pte, walker->level);
+
+ /*
+ * Inverting the NX it lets us AND it like other
+ * permission bits.
+ */
+ pte_access = pt_access & (pte ^ walk_nx_mask);
+
+ if (unlikely(!FNAME(is_present_gpte)(pte)))
+ goto error;
+
+ if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, walker->level))) {
+ errcode = PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
+ goto error;
+ }
+
+ walker->ptes[walker->level - 1] = pte;
+
+ /* Convert to ACC_*_MASK flags for struct guest_walker. */
+ walker->pt_access[walker->level - 1] = FNAME(gpte_access)(pt_access ^ walk_nx_mask);
+ } while (!FNAME(is_last_gpte)(mmu, walker->level, pte));
+
+ pte_pkey = FNAME(gpte_pkeys)(vcpu, pte);
+ accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0;
+
+ /* Convert to ACC_*_MASK flags for struct guest_walker. */
+ walker->pte_access = FNAME(gpte_access)(pte_access ^ walk_nx_mask);
+ errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access);
+ if (unlikely(errcode))
+ goto error;
+
+ gfn = gpte_to_gfn_lvl(pte, walker->level);
+ gfn += (addr & PT_LVL_OFFSET_MASK(walker->level)) >> PAGE_SHIFT;
+
+#if PTTYPE == 32
+ if (walker->level > PG_LEVEL_4K && is_cpuid_PSE36())
+ gfn += pse36_gfn_delta(pte);
+#endif
+
+ real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(gfn), access, &walker->fault);
+ if (real_gpa == INVALID_GPA)
+ return 0;
+
+ walker->gfn = real_gpa >> PAGE_SHIFT;
+
+ if (!write_fault)
+ FNAME(protect_clean_gpte)(mmu, &walker->pte_access, pte);
+ else
+ /*
+ * On a write fault, fold the dirty bit into accessed_dirty.
+ * For modes without A/D bits support accessed_dirty will be
+ * always clear.
+ */
+ accessed_dirty &= pte >>
+ (PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
+
+ if (unlikely(!accessed_dirty)) {
+ ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker,
+ addr, write_fault);
+ if (unlikely(ret < 0))
+ goto error;
+ else if (ret)
+ goto retry_walk;
+ }
+
+ pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
+ __func__, (u64)pte, walker->pte_access,
+ walker->pt_access[walker->level - 1]);
+ return 1;
+
+error:
+ errcode |= write_fault | user_fault;
+ if (fetch_fault && (is_efer_nx(mmu) || is_cr4_smep(mmu)))
+ errcode |= PFERR_FETCH_MASK;
+
+ walker->fault.vector = PF_VECTOR;
+ walker->fault.error_code_valid = true;
+ walker->fault.error_code = errcode;
+
+#if PTTYPE == PTTYPE_EPT
+ /*
+ * Use PFERR_RSVD_MASK in error_code to tell if EPT
+ * misconfiguration requires to be injected. The detection is
+ * done by is_rsvd_bits_set() above.
+ *
+ * We set up the value of exit_qualification to inject:
+ * [2:0] - Derive from the access bits. The exit_qualification might be
+ * out of date if it is serving an EPT misconfiguration.
+ * [5:3] - Calculated by the page walk of the guest EPT page tables
+ * [7:8] - Derived from [7:8] of real exit_qualification
+ *
+ * The other bits are set to 0.
+ */
+ if (!(errcode & PFERR_RSVD_MASK)) {
+ vcpu->arch.exit_qualification &= (EPT_VIOLATION_GVA_IS_VALID |
+ EPT_VIOLATION_GVA_TRANSLATED);
+ if (write_fault)
+ vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_WRITE;
+ if (user_fault)
+ vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_READ;
+ if (fetch_fault)
+ vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_INSTR;
+
+ /*
+ * Note, pte_access holds the raw RWX bits from the EPTE, not
+ * ACC_*_MASK flags!
+ */
+ vcpu->arch.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) <<
+ EPT_VIOLATION_RWX_SHIFT;
+ }
+#endif
+ walker->fault.address = addr;
+ walker->fault.nested_page_fault = mmu != vcpu->arch.walk_mmu;
+ walker->fault.async_page_fault = false;
+
+ trace_kvm_mmu_walker_error(walker->fault.error_code);
+ return 0;
+}
+
+static int FNAME(walk_addr)(struct guest_walker *walker,
+ struct kvm_vcpu *vcpu, gpa_t addr, u64 access)
+{
+ return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
+ access);
+}
+
+static bool
+FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+ u64 *spte, pt_element_t gpte, bool no_dirty_log)
+{
+ struct kvm_memory_slot *slot;
+ unsigned pte_access;
+ gfn_t gfn;
+ kvm_pfn_t pfn;
+
+ if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
+ return false;
+
+ pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
+
+ gfn = gpte_to_gfn(gpte);
+ pte_access = sp->role.access & FNAME(gpte_access)(gpte);
+ FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
+
+ slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn,
+ no_dirty_log && (pte_access & ACC_WRITE_MASK));
+ if (!slot)
+ return false;
+
+ pfn = gfn_to_pfn_memslot_atomic(slot, gfn);
+ if (is_error_pfn(pfn))
+ return false;
+
+ mmu_set_spte(vcpu, slot, spte, pte_access, gfn, pfn, NULL);
+ kvm_release_pfn_clean(pfn);
+ return true;
+}
+
+static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu,
+ struct guest_walker *gw, int level)
+{
+ pt_element_t curr_pte;
+ gpa_t base_gpa, pte_gpa = gw->pte_gpa[level - 1];
+ u64 mask;
+ int r, index;
+
+ if (level == PG_LEVEL_4K) {
+ mask = PTE_PREFETCH_NUM * sizeof(pt_element_t) - 1;
+ base_gpa = pte_gpa & ~mask;
+ index = (pte_gpa - base_gpa) / sizeof(pt_element_t);
+
+ r = kvm_vcpu_read_guest_atomic(vcpu, base_gpa,
+ gw->prefetch_ptes, sizeof(gw->prefetch_ptes));
+ curr_pte = gw->prefetch_ptes[index];
+ } else
+ r = kvm_vcpu_read_guest_atomic(vcpu, pte_gpa,
+ &curr_pte, sizeof(curr_pte));
+
+ return r || curr_pte != gw->ptes[level - 1];
+}
+
+static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
+ u64 *sptep)
+{
+ struct kvm_mmu_page *sp;
+ pt_element_t *gptep = gw->prefetch_ptes;
+ u64 *spte;
+ int i;
+
+ sp = sptep_to_sp(sptep);
+
+ if (sp->role.level > PG_LEVEL_4K)
+ return;
+
+ /*
+ * If addresses are being invalidated, skip prefetching to avoid
+ * accidentally prefetching those addresses.
+ */
+ if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
+ return;
+
+ if (sp->role.direct)
+ return __direct_pte_prefetch(vcpu, sp, sptep);
+
+ i = spte_index(sptep) & ~(PTE_PREFETCH_NUM - 1);
+ spte = sp->spt + i;
+
+ for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) {
+ if (spte == sptep)
+ continue;
+
+ if (is_shadow_present_pte(*spte))
+ continue;
+
+ if (!FNAME(prefetch_gpte)(vcpu, sp, spte, gptep[i], true))
+ break;
+ }
+}
+
+/*
+ * Fetch a shadow pte for a specific level in the paging hierarchy.
+ * If the guest tries to write a write-protected page, we need to
+ * emulate this operation, return 1 to indicate this case.
+ */
+static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
+ struct guest_walker *gw)
+{
+ struct kvm_mmu_page *sp = NULL;
+ struct kvm_shadow_walk_iterator it;
+ unsigned int direct_access, access;
+ int top_level, ret;
+ gfn_t base_gfn = fault->gfn;
+
+ WARN_ON_ONCE(gw->gfn != base_gfn);
+ direct_access = gw->pte_access;
+
+ top_level = vcpu->arch.mmu->cpu_role.base.level;
+ if (top_level == PT32E_ROOT_LEVEL)
+ top_level = PT32_ROOT_LEVEL;
+ /*
+ * Verify that the top-level gpte is still there. Since the page
+ * is a root page, it is either write protected (and cannot be
+ * changed from now on) or it is invalid (in which case, we don't
+ * really care if it changes underneath us after this point).
+ */
+ if (FNAME(gpte_changed)(vcpu, gw, top_level))
+ goto out_gpte_changed;
+
+ if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
+ goto out_gpte_changed;
+
+ for (shadow_walk_init(&it, vcpu, fault->addr);
+ shadow_walk_okay(&it) && it.level > gw->level;
+ shadow_walk_next(&it)) {
+ gfn_t table_gfn;
+
+ clear_sp_write_flooding_count(it.sptep);
+
+ table_gfn = gw->table_gfn[it.level - 2];
+ access = gw->pt_access[it.level - 2];
+ sp = kvm_mmu_get_child_sp(vcpu, it.sptep, table_gfn,
+ false, access);
+
+ if (sp != ERR_PTR(-EEXIST)) {
+ /*
+ * We must synchronize the pagetable before linking it
+ * because the guest doesn't need to flush tlb when
+ * the gpte is changed from non-present to present.
+ * Otherwise, the guest may use the wrong mapping.
+ *
+ * For PG_LEVEL_4K, kvm_mmu_get_page() has already
+ * synchronized it transiently via kvm_sync_page().
+ *
+ * For higher level pagetable, we synchronize it via
+ * the slower mmu_sync_children(). If it needs to
+ * break, some progress has been made; return
+ * RET_PF_RETRY and retry on the next #PF.
+ * KVM_REQ_MMU_SYNC is not necessary but it
+ * expedites the process.
+ */
+ if (sp->unsync_children &&
+ mmu_sync_children(vcpu, sp, false))
+ return RET_PF_RETRY;
+ }
+
+ /*
+ * Verify that the gpte in the page we've just write
+ * protected is still there.
+ */
+ if (FNAME(gpte_changed)(vcpu, gw, it.level - 1))
+ goto out_gpte_changed;
+
+ if (sp != ERR_PTR(-EEXIST))
+ link_shadow_page(vcpu, it.sptep, sp);
+ }
+
+ kvm_mmu_hugepage_adjust(vcpu, fault);
+
+ trace_kvm_mmu_spte_requested(fault);
+
+ for (; shadow_walk_okay(&it); shadow_walk_next(&it)) {
+ clear_sp_write_flooding_count(it.sptep);
+
+ /*
+ * We cannot overwrite existing page tables with an NX
+ * large page, as the leaf could be executable.
+ */
+ if (fault->nx_huge_page_workaround_enabled)
+ disallowed_hugepage_adjust(fault, *it.sptep, it.level);
+
+ base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+ if (it.level == fault->goal_level)
+ break;
+
+ validate_direct_spte(vcpu, it.sptep, direct_access);
+
+ sp = kvm_mmu_get_child_sp(vcpu, it.sptep, base_gfn,
+ true, direct_access);
+ if (sp == ERR_PTR(-EEXIST))
+ continue;
+
+ link_shadow_page(vcpu, it.sptep, sp);
+ if (fault->huge_page_disallowed &&
+ fault->req_level >= it.level)
+ account_huge_nx_page(vcpu->kvm, sp);
+ }
+
+ if (WARN_ON_ONCE(it.level != fault->goal_level))
+ return -EFAULT;
+
+ ret = mmu_set_spte(vcpu, fault->slot, it.sptep, gw->pte_access,
+ base_gfn, fault->pfn, fault);
+ if (ret == RET_PF_SPURIOUS)
+ return ret;
+
+ FNAME(pte_prefetch)(vcpu, gw, it.sptep);
+ return ret;
+
+out_gpte_changed:
+ return RET_PF_RETRY;
+}
+
+ /*
+ * To see whether the mapped gfn can write its page table in the current
+ * mapping.
+ *
+ * It is the helper function of FNAME(page_fault). When guest uses large page
+ * size to map the writable gfn which is used as current page table, we should
+ * force kvm to use small page size to map it because new shadow page will be
+ * created when kvm establishes shadow page table that stop kvm using large
+ * page size. Do it early can avoid unnecessary #PF and emulation.
+ *
+ * @write_fault_to_shadow_pgtable will return true if the fault gfn is
+ * currently used as its page table.
+ *
+ * Note: the PDPT page table is not checked for PAE-32 bit guest. It is ok
+ * since the PDPT is always shadowed, that means, we can not use large page
+ * size to map the gfn which is used as PDPT.
+ */
+static bool
+FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
+ struct guest_walker *walker, bool user_fault,
+ bool *write_fault_to_shadow_pgtable)
+{
+ int level;
+ gfn_t mask = ~(KVM_PAGES_PER_HPAGE(walker->level) - 1);
+ bool self_changed = false;
+
+ if (!(walker->pte_access & ACC_WRITE_MASK ||
+ (!is_cr0_wp(vcpu->arch.mmu) && !user_fault)))
+ return false;
+
+ for (level = walker->level; level <= walker->max_level; level++) {
+ gfn_t gfn = walker->gfn ^ walker->table_gfn[level - 1];
+
+ self_changed |= !(gfn & mask);
+ *write_fault_to_shadow_pgtable |= !gfn;
+ }
+
+ return self_changed;
+}
+
+/*
+ * Page fault handler. There are several causes for a page fault:
+ * - there is no shadow pte for the guest pte
+ * - write access through a shadow pte marked read only so that we can set
+ * the dirty bit
+ * - write access to a shadow pte marked read only so we can update the page
+ * dirty bitmap, when userspace requests it
+ * - mmio access; in this case we will never install a present shadow pte
+ * - normal guest page fault due to the guest pte marked not present, not
+ * writable, or not executable
+ *
+ * Returns: 1 if we need to emulate the instruction, 0 otherwise, or
+ * a negative value on error.
+ */
+static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+{
+ struct guest_walker walker;
+ int r;
+ unsigned long mmu_seq;
+ bool is_self_change_mapping;
+
+ pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code);
+ WARN_ON_ONCE(fault->is_tdp);
+
+ /*
+ * Look up the guest pte for the faulting address.
+ * If PFEC.RSVD is set, this is a shadow page fault.
+ * The bit needs to be cleared before walking guest page tables.
+ */
+ r = FNAME(walk_addr)(&walker, vcpu, fault->addr,
+ fault->error_code & ~PFERR_RSVD_MASK);
+
+ /*
+ * The page is not mapped by the guest. Let the guest handle it.
+ */
+ if (!r) {
+ pgprintk("%s: guest page fault\n", __func__);
+ if (!fault->prefetch)
+ kvm_inject_emulated_page_fault(vcpu, &walker.fault);
+
+ return RET_PF_RETRY;
+ }
+
+ fault->gfn = walker.gfn;
+ fault->slot = kvm_vcpu_gfn_to_memslot(vcpu, fault->gfn);
+
+ if (page_fault_handle_page_track(vcpu, fault)) {
+ shadow_page_table_clear_flood(vcpu, fault->addr);
+ return RET_PF_EMULATE;
+ }
+
+ r = mmu_topup_memory_caches(vcpu, true);
+ if (r)
+ return r;
+
+ vcpu->arch.write_fault_to_shadow_pgtable = false;
+
+ is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
+ &walker, fault->user, &vcpu->arch.write_fault_to_shadow_pgtable);
+
+ if (is_self_change_mapping)
+ fault->max_level = PG_LEVEL_4K;
+ else
+ fault->max_level = walker.level;
+
+ mmu_seq = vcpu->kvm->mmu_invalidate_seq;
+ smp_rmb();
+
+ r = kvm_faultin_pfn(vcpu, fault);
+ if (r != RET_PF_CONTINUE)
+ return r;
+
+ r = handle_abnormal_pfn(vcpu, fault, walker.pte_access);
+ if (r != RET_PF_CONTINUE)
+ return r;
+
+ /*
+ * Do not change pte_access if the pfn is a mmio page, otherwise
+ * we will cache the incorrect access into mmio spte.
+ */
+ if (fault->write && !(walker.pte_access & ACC_WRITE_MASK) &&
+ !is_cr0_wp(vcpu->arch.mmu) && !fault->user && fault->slot) {
+ walker.pte_access |= ACC_WRITE_MASK;
+ walker.pte_access &= ~ACC_USER_MASK;
+
+ /*
+ * If we converted a user page to a kernel page,
+ * so that the kernel can write to it when cr0.wp=0,
+ * then we should prevent the kernel from executing it
+ * if SMEP is enabled.
+ */
+ if (is_cr4_smep(vcpu->arch.mmu))
+ walker.pte_access &= ~ACC_EXEC_MASK;
+ }
+
+ r = RET_PF_RETRY;
+ write_lock(&vcpu->kvm->mmu_lock);
+
+ if (is_page_fault_stale(vcpu, fault, mmu_seq))
+ goto out_unlock;
+
+ r = make_mmu_pages_available(vcpu);
+ if (r)
+ goto out_unlock;
+ r = FNAME(fetch)(vcpu, fault, &walker);
+
+out_unlock:
+ write_unlock(&vcpu->kvm->mmu_lock);
+ kvm_release_pfn_clean(fault->pfn);
+ return r;
+}
+
+static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp)
+{
+ int offset = 0;
+
+ WARN_ON(sp->role.level != PG_LEVEL_4K);
+
+ if (PTTYPE == 32)
+ offset = sp->role.quadrant << SPTE_LEVEL_BITS;
+
+ return gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t);
+}
+
+static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
+{
+ struct kvm_shadow_walk_iterator iterator;
+ struct kvm_mmu_page *sp;
+ u64 old_spte;
+ int level;
+ u64 *sptep;
+
+ vcpu_clear_mmio_info(vcpu, gva);
+
+ /*
+ * No need to check return value here, rmap_can_add() can
+ * help us to skip pte prefetch later.
+ */
+ mmu_topup_memory_caches(vcpu, true);
+
+ if (!VALID_PAGE(root_hpa)) {
+ WARN_ON(1);
+ return;
+ }
+
+ write_lock(&vcpu->kvm->mmu_lock);
+ for_each_shadow_entry_using_root(vcpu, root_hpa, gva, iterator) {
+ level = iterator.level;
+ sptep = iterator.sptep;
+
+ sp = sptep_to_sp(sptep);
+ old_spte = *sptep;
+ if (is_last_spte(old_spte, level)) {
+ pt_element_t gpte;
+ gpa_t pte_gpa;
+
+ if (!sp->unsync)
+ break;
+
+ pte_gpa = FNAME(get_level1_sp_gpa)(sp);
+ pte_gpa += spte_index(sptep) * sizeof(pt_element_t);
+
+ mmu_page_zap_pte(vcpu->kvm, sp, sptep, NULL);
+ if (is_shadow_present_pte(old_spte))
+ kvm_flush_remote_tlbs_with_address(vcpu->kvm,
+ sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level));
+
+ if (!rmap_can_add(vcpu))
+ break;
+
+ if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte,
+ sizeof(pt_element_t)))
+ break;
+
+ FNAME(prefetch_gpte)(vcpu, sp, sptep, gpte, false);
+ }
+
+ if (!sp->unsync_children)
+ break;
+ }
+ write_unlock(&vcpu->kvm->mmu_lock);
+}
+
+/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */
+static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ gpa_t addr, u64 access,
+ struct x86_exception *exception)
+{
+ struct guest_walker walker;
+ gpa_t gpa = INVALID_GPA;
+ int r;
+
+#ifndef CONFIG_X86_64
+ /* A 64-bit GVA should be impossible on 32-bit KVM. */
+ WARN_ON_ONCE((addr >> 32) && mmu == vcpu->arch.walk_mmu);
+#endif
+
+ r = FNAME(walk_addr_generic)(&walker, vcpu, mmu, addr, access);
+
+ if (r) {
+ gpa = gfn_to_gpa(walker.gfn);
+ gpa |= addr & ~PAGE_MASK;
+ } else if (exception)
+ *exception = walker.fault;
+
+ return gpa;
+}
+
+/*
+ * Using the information in sp->shadowed_translation (kvm_mmu_page_get_gfn()) is
+ * safe because:
+ * - The spte has a reference to the struct page, so the pfn for a given gfn
+ * can't change unless all sptes pointing to it are nuked first.
+ *
+ * Returns
+ * < 0: the sp should be zapped
+ * 0: the sp is synced and no tlb flushing is required
+ * > 0: the sp is synced and tlb flushing is required
+ */
+static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+{
+ union kvm_mmu_page_role root_role = vcpu->arch.mmu->root_role;
+ int i;
+ bool host_writable;
+ gpa_t first_pte_gpa;
+ bool flush = false;
+
+ /*
+ * Ignore various flags when verifying that it's safe to sync a shadow
+ * page using the current MMU context.
+ *
+ * - level: not part of the overall MMU role and will never match as the MMU's
+ * level tracks the root level
+ * - access: updated based on the new guest PTE
+ * - quadrant: not part of the overall MMU role (similar to level)
+ */
+ const union kvm_mmu_page_role sync_role_ign = {
+ .level = 0xf,
+ .access = 0x7,
+ .quadrant = 0x3,
+ .passthrough = 0x1,
+ };
+
+ /*
+ * Direct pages can never be unsync, and KVM should never attempt to
+ * sync a shadow page for a different MMU context, e.g. if the role
+ * differs then the memslot lookup (SMM vs. non-SMM) will be bogus, the
+ * reserved bits checks will be wrong, etc...
+ */
+ if (WARN_ON_ONCE(sp->role.direct ||
+ (sp->role.word ^ root_role.word) & ~sync_role_ign.word))
+ return -1;
+
+ first_pte_gpa = FNAME(get_level1_sp_gpa)(sp);
+
+ for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
+ u64 *sptep, spte;
+ struct kvm_memory_slot *slot;
+ unsigned pte_access;
+ pt_element_t gpte;
+ gpa_t pte_gpa;
+ gfn_t gfn;
+
+ if (!sp->spt[i])
+ continue;
+
+ pte_gpa = first_pte_gpa + i * sizeof(pt_element_t);
+
+ if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte,
+ sizeof(pt_element_t)))
+ return -1;
+
+ if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
+ flush = true;
+ continue;
+ }
+
+ gfn = gpte_to_gfn(gpte);
+ pte_access = sp->role.access;
+ pte_access &= FNAME(gpte_access)(gpte);
+ FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
+
+ if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access))
+ continue;
+
+ /*
+ * Drop the SPTE if the new protections would result in a RWX=0
+ * SPTE or if the gfn is changing. The RWX=0 case only affects
+ * EPT with execute-only support, i.e. EPT without an effective
+ * "present" bit, as all other paging modes will create a
+ * read-only SPTE if pte_access is zero.
+ */
+ if ((!pte_access && !shadow_present_mask) ||
+ gfn != kvm_mmu_page_get_gfn(sp, i)) {
+ drop_spte(vcpu->kvm, &sp->spt[i]);
+ flush = true;
+ continue;
+ }
+
+ /* Update the shadowed access bits in case they changed. */
+ kvm_mmu_page_set_access(sp, i, pte_access);
+
+ sptep = &sp->spt[i];
+ spte = *sptep;
+ host_writable = spte & shadow_host_writable_mask;
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ make_spte(vcpu, sp, slot, pte_access, gfn,
+ spte_to_pfn(spte), spte, true, false,
+ host_writable, &spte);
+
+ flush |= mmu_spte_update(sptep, spte);
+ }
+
+ /*
+ * Note, any flush is purely for KVM's correctness, e.g. when dropping
+ * an existing SPTE or clearing W/A/D bits to ensure an mmu_notifier
+ * unmap or dirty logging event doesn't fail to flush. The guest is
+ * responsible for flushing the TLB to ensure any changes in protection
+ * bits are recognized, i.e. until the guest flushes or page faults on
+ * a relevant address, KVM is architecturally allowed to let vCPUs use
+ * cached translations with the old protection bits.
+ */
+ return flush;
+}
+
+#undef pt_element_t
+#undef guest_walker
+#undef FNAME
+#undef PT_BASE_ADDR_MASK
+#undef PT_INDEX
+#undef PT_LVL_ADDR_MASK
+#undef PT_LVL_OFFSET_MASK
+#undef PT_LEVEL_BITS
+#undef PT_MAX_FULL_LEVELS
+#undef gpte_to_gfn
+#undef gpte_to_gfn_lvl
+#undef PT_GUEST_ACCESSED_MASK
+#undef PT_GUEST_DIRTY_MASK
+#undef PT_GUEST_DIRTY_SHIFT
+#undef PT_GUEST_ACCESSED_SHIFT
+#undef PT_HAVE_ACCESSED_DIRTY
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
new file mode 100644
index 000000000..2e08b2a45
--- /dev/null
+++ b/arch/x86/kvm/mmu/spte.c
@@ -0,0 +1,507 @@
+// 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.
+ */
+
+
+#include <linux/kvm_host.h>
+#include "mmu.h"
+#include "mmu_internal.h"
+#include "x86.h"
+#include "spte.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_GPL(enable_mmio_caching);
+
+u64 __read_mostly shadow_host_writable_mask;
+u64 __read_mostly shadow_mmu_writable_mask;
+u64 __read_mostly shadow_nx_mask;
+u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
+u64 __read_mostly shadow_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_memtype_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;
+
+u8 __read_mostly shadow_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;
+}
+
+static u64 generation_mmio_spte_mask(u64 gen)
+{
+ u64 mask;
+
+ WARN_ON(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;
+
+ WARN_ON_ONCE(!shadow_mmio_value);
+
+ access &= shadow_mmio_access_mask;
+ spte |= 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);
+}
+
+/*
+ * Returns true if the SPTE has bits that may be set without holding mmu_lock.
+ * 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_has_volatile_bits(u64 spte)
+{
+ /*
+ * Always atomically update spte if it can be updated
+ * out of mmu-lock, it can ensure dirty bit is not lost,
+ * also, it can help us to get a stable is_writable_pte()
+ * to ensure tlb flush is not missed.
+ */
+ if (!is_writable_pte(spte) && is_mmu_writable_spte(spte))
+ return true;
+
+ if (is_access_track_spte(spte))
+ return true;
+
+ if (spte_ad_enabled(spte)) {
+ if (!(spte & shadow_accessed_mask) ||
+ (is_writable_pte(spte) && !(spte & shadow_dirty_mask)))
+ return true;
+ }
+
+ return false;
+}
+
+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 can_unsync,
+ bool host_writable, u64 *new_spte)
+{
+ int level = sp->role.level;
+ u64 spte = SPTE_MMU_PRESENT_MASK;
+ bool wrprot = false;
+
+ WARN_ON_ONCE(!pte_access && !shadow_present_mask);
+
+ if (sp->role.ad_disabled)
+ spte |= SPTE_TDP_AD_DISABLED_MASK;
+ else if (kvm_mmu_page_ad_need_write_protect(sp))
+ spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK;
+
+ /*
+ * For the EPT case, shadow_present_mask is 0 if hardware
+ * supports exec-only page table entries. In that case,
+ * ACC_USER_MASK and shadow_user_mask are used to represent
+ * read access. See FNAME(gpte_access) in paging_tmpl.h.
+ */
+ spte |= shadow_present_mask;
+ if (!prefetch)
+ spte |= spte_shadow_accessed_mask(spte);
+
+ if (level > PG_LEVEL_4K && (pte_access & ACC_EXEC_MASK) &&
+ is_nx_huge_page_enabled(vcpu->kvm)) {
+ pte_access &= ~ACC_EXEC_MASK;
+ }
+
+ if (pte_access & ACC_EXEC_MASK)
+ spte |= shadow_x_mask;
+ else
+ spte |= shadow_nx_mask;
+
+ if (pte_access & ACC_USER_MASK)
+ spte |= shadow_user_mask;
+
+ if (level > PG_LEVEL_4K)
+ spte |= PT_PAGE_SIZE_MASK;
+
+ if (shadow_memtype_mask)
+ spte |= static_call(kvm_x86_get_mt_mask)(vcpu, gfn,
+ kvm_is_mmio_pfn(pfn));
+ if (host_writable)
+ spte |= shadow_host_writable_mask;
+ else
+ pte_access &= ~ACC_WRITE_MASK;
+
+ if (shadow_me_value && !kvm_is_mmio_pfn(pfn))
+ spte |= shadow_me_value;
+
+ spte |= (u64)pfn << PAGE_SHIFT;
+
+ if (pte_access & ACC_WRITE_MASK) {
+ spte |= PT_WRITABLE_MASK | shadow_mmu_writable_mask;
+
+ /*
+ * Optimization: for pte sync, if spte was writable the hash
+ * lookup is unnecessary (and expensive). Write protection
+ * is responsibility of kvm_mmu_get_page / kvm_mmu_sync_roots.
+ * Same reasoning can be applied to dirty page accounting.
+ */
+ if (is_writable_pte(old_spte))
+ goto out;
+
+ /*
+ * 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.
+ */
+ if (mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, can_unsync, prefetch)) {
+ pgprintk("%s: found shadow page for %llx, marking ro\n",
+ __func__, gfn);
+ wrprot = true;
+ pte_access &= ~ACC_WRITE_MASK;
+ spte &= ~(PT_WRITABLE_MASK | shadow_mmu_writable_mask);
+ }
+ }
+
+ if (pte_access & ACC_WRITE_MASK)
+ spte |= spte_shadow_dirty_mask(spte);
+
+out:
+ if (prefetch)
+ 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));
+
+ if ((spte & PT_WRITABLE_MASK) && kvm_slot_dirty_track_enabled(slot)) {
+ /* Enforced by kvm_mmu_hugepage_adjust. */
+ WARN_ON(level > PG_LEVEL_4K);
+ mark_page_dirty_in_slot(vcpu->kvm, slot, gfn);
+ }
+
+ *new_spte = spte;
+ return wrprot;
+}
+
+static u64 make_spte_executable(u64 spte)
+{
+ bool is_access_track = is_access_track_spte(spte);
+
+ if (is_access_track)
+ spte = restore_acc_track_spte(spte);
+
+ spte &= ~shadow_nx_mask;
+ spte |= shadow_x_mask;
+
+ if (is_access_track)
+ spte = mark_spte_for_access_track(spte);
+
+ return spte;
+}
+
+/*
+ * 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_huge_page_split_spte(struct kvm *kvm, u64 huge_spte, union kvm_mmu_page_role role,
+ int index)
+{
+ u64 child_spte;
+
+ if (WARN_ON_ONCE(!is_shadow_present_pte(huge_spte)))
+ return 0;
+
+ if (WARN_ON_ONCE(!is_large_pte(huge_spte)))
+ return 0;
+
+ child_spte = huge_spte;
+
+ /*
+ * 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 ((role.access & ACC_EXEC_MASK) && is_nx_huge_page_enabled(kvm))
+ child_spte = make_spte_executable(child_spte);
+ }
+
+ return child_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 |
+ shadow_user_mask | shadow_x_mask | shadow_me_value;
+
+ if (ad_disabled)
+ spte |= SPTE_TDP_AD_DISABLED_MASK;
+ else
+ spte |= shadow_accessed_mask;
+
+ return spte;
+}
+
+u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn)
+{
+ u64 new_spte;
+
+ new_spte = old_spte & ~SPTE_BASE_ADDR_MASK;
+ new_spte |= (u64)new_pfn << PAGE_SHIFT;
+
+ new_spte &= ~PT_WRITABLE_MASK;
+ new_spte &= ~shadow_host_writable_mask;
+ new_spte &= ~shadow_mmu_writable_mask;
+
+ new_spte = mark_spte_for_access_track(new_spte);
+
+ return new_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),
+ "kvm: 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;
+
+ 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 removed SPTE
+ * must not get a false positive. Removed SPTEs and MMIO SPTEs should
+ * never collide as MMIO must set some RWX bits, and removed SPTEs must
+ * not set any RWX bits.
+ */
+ if (WARN_ON((mmio_value & mmio_mask) != mmio_value) ||
+ WARN_ON(mmio_value && (REMOVED_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_GPL(kvm_mmu_set_mmio_spte_mask);
+
+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_GPL(kvm_mmu_set_me_spte_mask);
+
+void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
+{
+ shadow_user_mask = VMX_EPT_READABLE_MASK;
+ shadow_accessed_mask = has_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull;
+ shadow_dirty_mask = has_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull;
+ shadow_nx_mask = 0ull;
+ shadow_x_mask = VMX_EPT_EXECUTABLE_MASK;
+ shadow_present_mask = has_exec_only ? 0ull : VMX_EPT_READABLE_MASK;
+ /*
+ * EPT overrides the host MTRRs, and so KVM must program the desired
+ * memtype directly into the SPTEs. Note, this mask is just the mask
+ * of all bits that factor into the memtype, the actual memtype must be
+ * dynamically calculated, e.g. to ensure host MMIO is mapped UC.
+ */
+ shadow_memtype_mask = VMX_EPT_MT_MASK | VMX_EPT_IPAT_BIT;
+ shadow_acc_track_mask = VMX_EPT_RWX_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, 0);
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_set_ept_masks);
+
+void kvm_mmu_reset_all_pte_masks(void)
+{
+ u8 low_phys_bits;
+ u64 mask;
+
+ shadow_phys_bits = kvm_get_shadow_phys_bits();
+
+ /*
+ * 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_x_mask = 0;
+ shadow_present_mask = PT_PRESENT_MASK;
+
+ /*
+ * For shadow paging and NPT, KVM uses PAT entry '0' to encode WB
+ * memtype in the SPTEs, i.e. relies on host MTRRs to provide the
+ * correct memtype (WB is the "weakest" memtype).
+ */
+ shadow_memtype_mask = 0;
+ 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 (shadow_phys_bits < 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);
+}
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
new file mode 100644
index 000000000..7670c13ce
--- /dev/null
+++ b/arch/x86/kvm/mmu/spte.h
@@ -0,0 +1,474 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#ifndef KVM_X86_MMU_SPTE_H
+#define KVM_X86_MMU_SPTE_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)
+
+/*
+ * 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 52 and 53 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 52
+#define SPTE_TDP_AD_MASK (3ULL << SPTE_TDP_AD_SHIFT)
+#define SPTE_TDP_AD_ENABLED_MASK (0ULL << SPTE_TDP_AD_SHIFT)
+#define SPTE_TDP_AD_DISABLED_MASK (1ULL << SPTE_TDP_AD_SHIFT)
+#define SPTE_TDP_AD_WRPROT_ONLY_MASK (2ULL << SPTE_TDP_AD_SHIFT)
+static_assert(SPTE_TDP_AD_ENABLED_MASK == 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_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
+ | shadow_x_mask | shadow_nx_mask | shadow_me_mask)
+
+#define ACC_EXEC_MASK 1
+#define ACC_WRITE_MASK PT_WRITABLE_MASK
+#define ACC_USER_MASK PT_USER_MASK
+#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)
+
+/* The mask for the R/X bits in EPT PTEs */
+#define SPTE_EPT_READABLE_MASK 0x1ull
+#define SPTE_EPT_EXECUTABLE_MASK 0x4ull
+
+#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 (SPTE_EPT_READABLE_MASK | \
+ SPTE_EPT_EXECUTABLE_MASK)
+#define SHADOW_ACC_TRACK_SAVED_BITS_SHIFT 54
+#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(57)
+#define EPT_SPTE_MMU_WRITABLE BIT_ULL(58)
+
+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 a 19 bit subset of
+ * the memslots generation and is derived as follows:
+ *
+ * Bits 0-7 of the MMIO generation are propagated to spte bits 3-10
+ * Bits 8-18 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 10
+
+#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) | 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 == 8 && 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)
+
+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_x_mask; /* mutual exclusive with nx_mask */
+extern u64 __read_mostly shadow_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_memtype_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_MASK;
+ * 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 REMOVED_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
+ * bot AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF
+ * vulnerability. Use only low bits to avoid 64-bit immediates.
+ *
+ * Only used by the TDP MMU.
+ */
+#define REMOVED_SPTE 0x5a0ULL
+
+/* Removed SPTEs must not be misconstrued as shadow present PTEs. */
+static_assert(!(REMOVED_SPTE & SPTE_MMU_PRESENT_MASK));
+
+static inline bool is_removed_spte(u64 spte)
+{
+ return spte == REMOVED_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 bool is_mmio_spte(u64 spte)
+{
+ return (spte & shadow_mmio_mask) == shadow_mmio_value &&
+ likely(enable_mmio_caching);
+}
+
+static inline bool is_shadow_present_pte(u64 pte)
+{
+ return !!(pte & SPTE_MMU_PRESENT_MASK);
+}
+
+/*
+ * Returns 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.
+ */
+static inline bool kvm_ad_enabled(void)
+{
+ return !!shadow_accessed_mask;
+}
+
+static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
+{
+ return sp->role.ad_disabled;
+}
+
+static inline bool spte_ad_enabled(u64 spte)
+{
+ MMU_WARN_ON(!is_shadow_present_pte(spte));
+ return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED_MASK;
+}
+
+static inline bool spte_ad_need_write_protect(u64 spte)
+{
+ MMU_WARN_ON(!is_shadow_present_pte(spte));
+ /*
+ * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED_MASK 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_MASK;
+}
+
+static inline u64 spte_shadow_accessed_mask(u64 spte)
+{
+ MMU_WARN_ON(!is_shadow_present_pte(spte));
+ return spte_ad_enabled(spte) ? shadow_accessed_mask : 0;
+}
+
+static inline u64 spte_shadow_dirty_mask(u64 spte)
+{
+ MMU_WARN_ON(!is_shadow_present_pte(spte));
+ return spte_ad_enabled(spte) ? shadow_dirty_mask : 0;
+}
+
+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)
+{
+ return (spte & (shadow_x_mask | shadow_nx_mask)) == shadow_x_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)
+{
+ u64 accessed_mask = spte_shadow_accessed_mask(spte);
+
+ return accessed_mask ? spte & accessed_mask
+ : !is_access_track_spte(spte);
+}
+
+static inline bool is_dirty_spte(u64 spte)
+{
+ u64 dirty_mask = spte_shadow_dirty_mask(spte);
+
+ return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_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)
+{
+ 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 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),
+ "kvm: MMU-writable SPTE is not Host-writable: %llx",
+ spte);
+ else
+ WARN_ONCE(is_writable_pte(spte),
+ "kvm: Writable SPTE is not MMU-writable: %llx", spte);
+}
+
+static inline bool is_mmu_writable_spte(u64 spte)
+{
+ return spte & shadow_mmu_writable_mask;
+}
+
+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_has_volatile_bits(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 can_unsync,
+ bool host_writable, u64 *new_spte);
+u64 make_huge_page_split_spte(struct kvm *kvm, u64 huge_spte,
+ union kvm_mmu_page_role role, int index);
+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;
+}
+
+u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn);
+
+void __init kvm_mmu_spte_module_init(void);
+void kvm_mmu_reset_all_pte_masks(void);
+
+#endif
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
new file mode 100644
index 000000000..39b48e7d7
--- /dev/null
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#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 << PAGE_SHIFT, iter->level);
+ iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
+}
+
+static gfn_t round_gfn_for_level(gfn_t gfn, int level)
+{
+ return gfn & -KVM_PAGES_PER_HPAGE(level);
+}
+
+/*
+ * 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 = round_gfn_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)
+{
+ int root_level = root->role.level;
+
+ WARN_ON(root_level < 1);
+ WARN_ON(root_level > PT64_ROOT_MAX_LEVEL);
+
+ iter->next_last_level_gfn = next_last_level_gfn;
+ iter->root_level = root_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 = round_gfn_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 << 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 = round_gfn_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
+ * highter 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;
+}
+
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
new file mode 100644
index 000000000..f0af385c5
--- /dev/null
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -0,0 +1,118 @@
+// 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)
+{
+ return xchg(rcu_dereference(sptep), new_spte);
+}
+
+static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
+{
+ WRITE_ONCE(*rcu_dereference(sptep), new_spte);
+}
+
+static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte,
+ u64 new_spte, int level)
+{
+ /*
+ * Atomically write the SPTE if it is a shadow-present, leaf SPTE with
+ * volatile bits, i.e. has bits that can be set outside of mmu_lock.
+ * The Writable bit can be set by KVM's fast page fault handler, and
+ * Accessed and Dirty bits can be set by the CPU.
+ *
+ * Note, non-leaf SPTEs do have Accessed bits and those bits are
+ * technically volatile, but KVM doesn't consume the Accessed bit of
+ * non-leaf SPTEs, i.e. KVM doesn't care if it clobbers the bit. This
+ * logic needs to be reassessed if KVM were to use non-leaf Accessed
+ * bits, e.g. to skip stepping down into child SPTEs when aging SPTEs.
+ */
+ if (is_shadow_present_pte(old_spte) && is_last_spte(old_spte, level) &&
+ spte_has_volatile_bits(old_spte))
+ return kvm_tdp_mmu_write_spte_atomic(sptep, new_spte);
+
+ __kvm_tdp_mmu_write_spte(sptep, new_spte);
+ 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 mapped by the current SPTE */
+ gfn_t gfn;
+ /* 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, root, min_level, start, end) \
+ for (tdp_iter_start(&iter, root, min_level, start); \
+ iter.valid && iter.gfn < end; \
+ tdp_iter_next(&iter))
+
+#define for_each_tdp_pte(iter, root, start, end) \
+ for_each_tdp_pte_min_level(iter, 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);
+void tdp_iter_next(struct tdp_iter *iter);
+void tdp_iter_restart(struct tdp_iter *iter);
+
+#endif /* __KVM_X86_MMU_TDP_ITER_H */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
new file mode 100644
index 000000000..c3b0f9733
--- /dev/null
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -0,0 +1,1885 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "mmu.h"
+#include "mmu_internal.h"
+#include "mmutrace.h"
+#include "tdp_iter.h"
+#include "tdp_mmu.h"
+#include "spte.h"
+
+#include <asm/cmpxchg.h>
+#include <trace/events/kvm.h>
+
+static bool __read_mostly tdp_mmu_enabled = true;
+module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644);
+
+/* Initializes the TDP MMU for the VM, if enabled. */
+void kvm_mmu_init_tdp_mmu(struct kvm *kvm)
+{
+ if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled))
+ return;
+
+ /* This should not be changed for the lifetime of the VM. */
+ kvm->arch.tdp_mmu_enabled = true;
+ INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
+ spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
+ INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages);
+}
+
+/* Arbitrarily returns true so that this may be used in if statements. */
+static __always_inline bool kvm_lockdep_assert_mmu_lock_held(struct kvm *kvm,
+ bool shared)
+{
+ if (shared)
+ lockdep_assert_held_read(&kvm->mmu_lock);
+ else
+ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ return true;
+}
+
+void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
+{
+ if (!kvm->arch.tdp_mmu_enabled)
+ return;
+
+ /*
+ * Invalidate all roots, which besides the obvious, schedules all roots
+ * for zapping and thus puts the TDP MMU's reference to each root, i.e.
+ * ultimately frees all roots.
+ */
+ kvm_tdp_mmu_invalidate_all_roots(kvm);
+ kvm_tdp_mmu_zap_invalidated_roots(kvm);
+
+ WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages));
+ WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
+
+ /*
+ * Ensure that all the outstanding RCU callbacks to free shadow pages
+ * can run before the VM is torn down. Putting the last reference to
+ * zapped roots will create new callbacks.
+ */
+ rcu_barrier();
+}
+
+static void tdp_mmu_free_sp(struct kvm_mmu_page *sp)
+{
+ free_page((unsigned long)sp->spt);
+ kmem_cache_free(mmu_page_header_cache, sp);
+}
+
+/*
+ * This is called through call_rcu in order to free TDP page table memory
+ * safely with respect to other kernel threads that may be operating on
+ * the memory.
+ * By only accessing TDP MMU page table memory in an RCU read critical
+ * section, and freeing it after a grace period, lockless access to that
+ * memory won't use it after it is freed.
+ */
+static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
+{
+ struct kvm_mmu_page *sp = container_of(head, struct kvm_mmu_page,
+ rcu_head);
+
+ tdp_mmu_free_sp(sp);
+}
+
+void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
+ bool shared)
+{
+ kvm_lockdep_assert_mmu_lock_held(kvm, shared);
+
+ if (!refcount_dec_and_test(&root->tdp_mmu_root_count))
+ return;
+
+ /*
+ * The TDP MMU itself holds a reference to each root until the root is
+ * explicitly invalidated, i.e. the final reference should be never be
+ * put for a valid root.
+ */
+ KVM_BUG_ON(!is_tdp_mmu_page(root) || !root->role.invalid, kvm);
+
+ spin_lock(&kvm->arch.tdp_mmu_pages_lock);
+ list_del_rcu(&root->link);
+ spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+ call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback);
+}
+
+/*
+ * Returns the next root after @prev_root (or the first root if @prev_root is
+ * NULL). A reference to the returned root is acquired, and the reference to
+ * @prev_root is released (the caller obviously must hold a reference to
+ * @prev_root if it's non-NULL).
+ *
+ * If @only_valid is true, invalid roots are skipped.
+ *
+ * Returns NULL if the end of tdp_mmu_roots was reached.
+ */
+static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
+ struct kvm_mmu_page *prev_root,
+ bool shared, bool only_valid)
+{
+ struct kvm_mmu_page *next_root;
+
+ rcu_read_lock();
+
+ if (prev_root)
+ next_root = list_next_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+ &prev_root->link,
+ typeof(*prev_root), link);
+ else
+ next_root = list_first_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+ typeof(*next_root), link);
+
+ while (next_root) {
+ if ((!only_valid || !next_root->role.invalid) &&
+ kvm_tdp_mmu_get_root(next_root))
+ break;
+
+ next_root = list_next_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+ &next_root->link, typeof(*next_root), link);
+ }
+
+ rcu_read_unlock();
+
+ if (prev_root)
+ kvm_tdp_mmu_put_root(kvm, prev_root, shared);
+
+ return next_root;
+}
+
+/*
+ * Note: this iterator gets and puts references to the roots it iterates over.
+ * This makes it safe to release the MMU lock and yield within the loop, but
+ * if exiting the loop early, the caller must drop the reference to the most
+ * recent root. (Unless keeping a live reference is desirable.)
+ *
+ * If shared is set, this function is operating under the MMU lock in read
+ * mode. In the unlikely event that this thread must free a root, the lock
+ * will be temporarily dropped and reacquired in write mode.
+ */
+#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, _only_valid)\
+ for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, _only_valid); \
+ _root; \
+ _root = tdp_mmu_next_root(_kvm, _root, _shared, _only_valid)) \
+ if (kvm_lockdep_assert_mmu_lock_held(_kvm, _shared) && \
+ kvm_mmu_page_as_id(_root) != _as_id) { \
+ } else
+
+#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \
+ __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true)
+
+#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared) \
+ for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false); \
+ _root; \
+ _root = tdp_mmu_next_root(_kvm, _root, _shared, false)) \
+ if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) { \
+ } else
+
+/*
+ * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write,
+ * the implication being that any flow that holds mmu_lock for read is
+ * inherently yield-friendly and should use the yield-safe variant above.
+ * Holding mmu_lock for write obviates the need for RCU protection as the list
+ * is guaranteed to be stable.
+ */
+#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \
+ list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \
+ if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) && \
+ kvm_mmu_page_as_id(_root) != _as_id) { \
+ } else
+
+static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu_page *sp;
+
+ sp = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache);
+ sp->spt = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_shadow_page_cache);
+
+ return sp;
+}
+
+static void tdp_mmu_init_sp(struct kvm_mmu_page *sp, tdp_ptep_t sptep,
+ gfn_t gfn, union kvm_mmu_page_role role)
+{
+ set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
+
+ sp->role = role;
+ sp->gfn = gfn;
+ sp->ptep = sptep;
+ sp->tdp_mmu_page = true;
+
+ trace_kvm_mmu_get_page(sp, true);
+}
+
+static void tdp_mmu_init_child_sp(struct kvm_mmu_page *child_sp,
+ struct tdp_iter *iter)
+{
+ struct kvm_mmu_page *parent_sp;
+ union kvm_mmu_page_role role;
+
+ parent_sp = sptep_to_sp(rcu_dereference(iter->sptep));
+
+ role = parent_sp->role;
+ role.level--;
+
+ tdp_mmu_init_sp(child_sp, iter->sptep, iter->gfn, role);
+}
+
+hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
+{
+ union kvm_mmu_page_role role = vcpu->arch.mmu->root_role;
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_mmu_page *root;
+
+ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ /*
+ * Check for an existing root before allocating a new one. Note, the
+ * role check prevents consuming an invalid root.
+ */
+ for_each_tdp_mmu_root(kvm, root, kvm_mmu_role_as_id(role)) {
+ if (root->role.word == role.word &&
+ kvm_tdp_mmu_get_root(root))
+ goto out;
+ }
+
+ root = tdp_mmu_alloc_sp(vcpu);
+ tdp_mmu_init_sp(root, NULL, 0, role);
+
+ /*
+ * TDP MMU roots are kept until they are explicitly invalidated, either
+ * by a memslot update or by the destruction of the VM. Initialize the
+ * refcount to two; one reference for the vCPU, and one reference for
+ * the TDP MMU itself, which is held until the root is invalidated and
+ * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots().
+ */
+ refcount_set(&root->tdp_mmu_root_count, 2);
+
+ spin_lock(&kvm->arch.tdp_mmu_pages_lock);
+ list_add_rcu(&root->link, &kvm->arch.tdp_mmu_roots);
+ spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+
+out:
+ return __pa(root->spt);
+}
+
+static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+ u64 old_spte, u64 new_spte, int level,
+ bool shared);
+
+static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level)
+{
+ if (!is_shadow_present_pte(old_spte) || !is_last_spte(old_spte, level))
+ return;
+
+ if (is_accessed_spte(old_spte) &&
+ (!is_shadow_present_pte(new_spte) || !is_accessed_spte(new_spte) ||
+ spte_to_pfn(old_spte) != spte_to_pfn(new_spte)))
+ kvm_set_pfn_accessed(spte_to_pfn(old_spte));
+}
+
+static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
+ u64 old_spte, u64 new_spte, int level)
+{
+ bool pfn_changed;
+ struct kvm_memory_slot *slot;
+
+ if (level > PG_LEVEL_4K)
+ return;
+
+ pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
+
+ if ((!is_writable_pte(old_spte) || pfn_changed) &&
+ is_writable_pte(new_spte)) {
+ slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn);
+ mark_page_dirty_in_slot(kvm, slot, gfn);
+ }
+}
+
+static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ kvm_account_pgtable_pages((void *)sp->spt, +1);
+}
+
+static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ kvm_account_pgtable_pages((void *)sp->spt, -1);
+}
+
+/**
+ * tdp_mmu_unlink_sp() - Remove a shadow page from the list of used pages
+ *
+ * @kvm: kvm instance
+ * @sp: the page to be removed
+ * @shared: This operation may not be running under the exclusive use of
+ * the MMU lock and the operation must synchronize with other
+ * threads that might be adding or removing pages.
+ */
+static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp,
+ bool shared)
+{
+ tdp_unaccount_mmu_page(kvm, sp);
+ if (shared)
+ spin_lock(&kvm->arch.tdp_mmu_pages_lock);
+ else
+ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ list_del(&sp->link);
+ if (sp->lpage_disallowed)
+ unaccount_huge_nx_page(kvm, sp);
+
+ if (shared)
+ spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+}
+
+/**
+ * handle_removed_pt() - handle a page table removed from the TDP structure
+ *
+ * @kvm: kvm instance
+ * @pt: the page removed from the paging structure
+ * @shared: This operation may not be running under the exclusive use
+ * of the MMU lock and the operation must synchronize with other
+ * threads that might be modifying SPTEs.
+ *
+ * Given a page table that has been removed from the TDP paging structure,
+ * iterates through the page table to clear SPTEs and free child page tables.
+ *
+ * Note that pt is passed in as a tdp_ptep_t, but it does not need RCU
+ * protection. Since this thread removed it from the paging structure,
+ * this thread will be responsible for ensuring the page is freed. Hence the
+ * early rcu_dereferences in the function.
+ */
+static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared)
+{
+ struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
+ int level = sp->role.level;
+ gfn_t base_gfn = sp->gfn;
+ int i;
+
+ trace_kvm_mmu_prepare_zap_page(sp);
+
+ tdp_mmu_unlink_sp(kvm, sp, shared);
+
+ for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
+ tdp_ptep_t sptep = pt + i;
+ gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
+ u64 old_spte;
+
+ if (shared) {
+ /*
+ * Set the SPTE to a nonpresent value that other
+ * threads will not overwrite. If the SPTE was
+ * already marked as removed then another thread
+ * handling a page fault could overwrite it, so
+ * set the SPTE until it is set from some other
+ * value to the removed SPTE value.
+ */
+ for (;;) {
+ old_spte = kvm_tdp_mmu_write_spte_atomic(sptep, REMOVED_SPTE);
+ if (!is_removed_spte(old_spte))
+ break;
+ cpu_relax();
+ }
+ } else {
+ /*
+ * If the SPTE is not MMU-present, there is no backing
+ * page associated with the SPTE and so no side effects
+ * that need to be recorded, and exclusive ownership of
+ * mmu_lock ensures the SPTE can't be made present.
+ * Note, zapping MMIO SPTEs is also unnecessary as they
+ * are guarded by the memslots generation, not by being
+ * unreachable.
+ */
+ old_spte = kvm_tdp_mmu_read_spte(sptep);
+ if (!is_shadow_present_pte(old_spte))
+ continue;
+
+ /*
+ * Use the common helper instead of a raw WRITE_ONCE as
+ * the SPTE needs to be updated atomically if it can be
+ * modified by a different vCPU outside of mmu_lock.
+ * Even though the parent SPTE is !PRESENT, the TLB
+ * hasn't yet been flushed, and both Intel and AMD
+ * document that A/D assists can use upper-level PxE
+ * entries that are cached in the TLB, i.e. the CPU can
+ * still access the page and mark it dirty.
+ *
+ * No retry is needed in the atomic update path as the
+ * sole concern is dropping a Dirty bit, i.e. no other
+ * task can zap/remove the SPTE as mmu_lock is held for
+ * write. Marking the SPTE as a removed SPTE is not
+ * strictly necessary for the same reason, but using
+ * the remove SPTE value keeps the shared/exclusive
+ * paths consistent and allows the handle_changed_spte()
+ * call below to hardcode the new value to REMOVED_SPTE.
+ *
+ * Note, even though dropping a Dirty bit is the only
+ * scenario where a non-atomic update could result in a
+ * functional bug, simply checking the Dirty bit isn't
+ * sufficient as a fast page fault could read the upper
+ * level SPTE before it is zapped, and then make this
+ * target SPTE writable, resume the guest, and set the
+ * Dirty bit between reading the SPTE above and writing
+ * it here.
+ */
+ old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte,
+ REMOVED_SPTE, level);
+ }
+ handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn,
+ old_spte, REMOVED_SPTE, level, shared);
+ }
+
+ call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
+}
+
+/**
+ * __handle_changed_spte - handle bookkeeping associated with an SPTE change
+ * @kvm: kvm instance
+ * @as_id: the address space of the paging structure the SPTE was a part of
+ * @gfn: the base GFN that was mapped by the SPTE
+ * @old_spte: The value of the SPTE before the change
+ * @new_spte: The value of the SPTE after the change
+ * @level: the level of the PT the SPTE is part of in the paging structure
+ * @shared: This operation may not be running under the exclusive use of
+ * the MMU lock and the operation must synchronize with other
+ * threads that might be modifying SPTEs.
+ *
+ * Handle bookkeeping that might result from the modification of a SPTE.
+ * This function must be called for all TDP SPTE modifications.
+ */
+static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+ u64 old_spte, u64 new_spte, int level,
+ bool shared)
+{
+ bool was_present = is_shadow_present_pte(old_spte);
+ bool is_present = is_shadow_present_pte(new_spte);
+ bool was_leaf = was_present && is_last_spte(old_spte, level);
+ bool is_leaf = is_present && is_last_spte(new_spte, level);
+ bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
+
+ WARN_ON(level > PT64_ROOT_MAX_LEVEL);
+ WARN_ON(level < PG_LEVEL_4K);
+ WARN_ON(gfn & (KVM_PAGES_PER_HPAGE(level) - 1));
+
+ /*
+ * If this warning were to trigger it would indicate that there was a
+ * missing MMU notifier or a race with some notifier handler.
+ * A present, leaf SPTE should never be directly replaced with another
+ * present leaf SPTE pointing to a different PFN. A notifier handler
+ * should be zapping the SPTE before the main MM's page table is
+ * changed, or the SPTE should be zeroed, and the TLBs flushed by the
+ * thread before replacement.
+ */
+ if (was_leaf && is_leaf && pfn_changed) {
+ pr_err("Invalid SPTE change: cannot replace a present leaf\n"
+ "SPTE with another present leaf SPTE mapping a\n"
+ "different PFN!\n"
+ "as_id: %d gfn: %llx old_spte: %llx new_spte: %llx level: %d",
+ as_id, gfn, old_spte, new_spte, level);
+
+ /*
+ * Crash the host to prevent error propagation and guest data
+ * corruption.
+ */
+ BUG();
+ }
+
+ if (old_spte == new_spte)
+ return;
+
+ trace_kvm_tdp_mmu_spte_changed(as_id, gfn, level, old_spte, new_spte);
+
+ if (is_leaf)
+ check_spte_writable_invariants(new_spte);
+
+ /*
+ * The only times a SPTE should be changed from a non-present to
+ * non-present state is when an MMIO entry is installed/modified/
+ * removed. In that case, there is nothing to do here.
+ */
+ if (!was_present && !is_present) {
+ /*
+ * If this change does not involve a MMIO SPTE or removed SPTE,
+ * it is unexpected. Log the change, though it should not
+ * impact the guest since both the former and current SPTEs
+ * are nonpresent.
+ */
+ if (WARN_ON(!is_mmio_spte(old_spte) &&
+ !is_mmio_spte(new_spte) &&
+ !is_removed_spte(new_spte)))
+ pr_err("Unexpected SPTE change! Nonpresent SPTEs\n"
+ "should not be replaced with another,\n"
+ "different nonpresent SPTE, unless one or both\n"
+ "are MMIO SPTEs, or the new SPTE is\n"
+ "a temporary removed SPTE.\n"
+ "as_id: %d gfn: %llx old_spte: %llx new_spte: %llx level: %d",
+ as_id, gfn, old_spte, new_spte, level);
+ return;
+ }
+
+ if (is_leaf != was_leaf)
+ kvm_update_page_stats(kvm, level, is_leaf ? 1 : -1);
+
+ if (was_leaf && is_dirty_spte(old_spte) &&
+ (!is_present || !is_dirty_spte(new_spte) || pfn_changed))
+ kvm_set_pfn_dirty(spte_to_pfn(old_spte));
+
+ /*
+ * Recursively handle child PTs if the change removed a subtree from
+ * the paging structure. Note the WARN on the PFN changing without the
+ * SPTE being converted to a hugepage (leaf) or being zapped. Shadow
+ * pages are kernel allocations and should never be migrated.
+ */
+ if (was_present && !was_leaf &&
+ (is_leaf || !is_present || WARN_ON_ONCE(pfn_changed)))
+ handle_removed_pt(kvm, spte_to_child_pt(old_spte, level), shared);
+}
+
+static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+ u64 old_spte, u64 new_spte, int level,
+ bool shared)
+{
+ __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level,
+ shared);
+ handle_changed_spte_acc_track(old_spte, new_spte, level);
+ handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte,
+ new_spte, level);
+}
+
+/*
+ * tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically
+ * and handle the associated bookkeeping. Do not mark the page dirty
+ * in KVM's dirty bitmaps.
+ *
+ * If setting the SPTE fails because it has changed, iter->old_spte will be
+ * refreshed to the current value of the spte.
+ *
+ * @kvm: kvm instance
+ * @iter: a tdp_iter instance currently on the SPTE that should be set
+ * @new_spte: The value the SPTE should be set to
+ * Return:
+ * * 0 - If the SPTE was set.
+ * * -EBUSY - If the SPTE cannot be set. In this case this function will have
+ * no side-effects other than setting iter->old_spte to the last
+ * known value of the spte.
+ */
+static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm,
+ struct tdp_iter *iter,
+ u64 new_spte)
+{
+ u64 *sptep = rcu_dereference(iter->sptep);
+
+ /*
+ * The caller is responsible for ensuring the old SPTE is not a REMOVED
+ * SPTE. KVM should never attempt to zap or manipulate a REMOVED SPTE,
+ * and pre-checking before inserting a new SPTE is advantageous as it
+ * avoids unnecessary work.
+ */
+ WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte));
+
+ lockdep_assert_held_read(&kvm->mmu_lock);
+
+ /*
+ * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and
+ * does not hold the mmu_lock.
+ */
+ if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte))
+ return -EBUSY;
+
+ __handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+ new_spte, iter->level, true);
+ handle_changed_spte_acc_track(iter->old_spte, new_spte, iter->level);
+
+ return 0;
+}
+
+static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
+ struct tdp_iter *iter)
+{
+ int ret;
+
+ /*
+ * Freeze the SPTE by setting it to a special,
+ * non-present value. This will stop other threads from
+ * immediately installing a present entry in its place
+ * before the TLBs are flushed.
+ */
+ ret = tdp_mmu_set_spte_atomic(kvm, iter, REMOVED_SPTE);
+ if (ret)
+ return ret;
+
+ kvm_flush_remote_tlbs_with_address(kvm, iter->gfn,
+ KVM_PAGES_PER_HPAGE(iter->level));
+
+ /*
+ * No other thread can overwrite the removed SPTE as they must either
+ * wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not
+ * overwrite the special removed SPTE value. No bookkeeping is needed
+ * here since the SPTE is going from non-present to non-present. Use
+ * the raw write helper to avoid an unnecessary check on volatile bits.
+ */
+ __kvm_tdp_mmu_write_spte(iter->sptep, 0);
+
+ return 0;
+}
+
+
+/*
+ * __tdp_mmu_set_spte - Set a TDP MMU SPTE and handle the associated bookkeeping
+ * @kvm: KVM instance
+ * @as_id: Address space ID, i.e. regular vs. SMM
+ * @sptep: Pointer to the SPTE
+ * @old_spte: The current value of the SPTE
+ * @new_spte: The new value that will be set for the SPTE
+ * @gfn: The base GFN that was (or will be) mapped by the SPTE
+ * @level: The level _containing_ the SPTE (its parent PT's level)
+ * @record_acc_track: Notify the MM subsystem of changes to the accessed state
+ * of the page. Should be set unless handling an MMU
+ * notifier for access tracking. Leaving record_acc_track
+ * unset in that case prevents page accesses from being
+ * double counted.
+ * @record_dirty_log: Record the page as dirty in the dirty bitmap if
+ * appropriate for the change being made. Should be set
+ * unless performing certain dirty logging operations.
+ * Leaving record_dirty_log unset in that case prevents page
+ * writes from being double counted.
+ *
+ * Returns the old SPTE value, which _may_ be different than @old_spte if the
+ * SPTE had voldatile bits.
+ */
+static u64 __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep,
+ u64 old_spte, u64 new_spte, gfn_t gfn, int level,
+ bool record_acc_track, bool record_dirty_log)
+{
+ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ /*
+ * No thread should be using this function to set SPTEs to or from the
+ * temporary removed SPTE value.
+ * If operating under the MMU lock in read mode, tdp_mmu_set_spte_atomic
+ * should be used. If operating under the MMU lock in write mode, the
+ * use of the removed SPTE should not be necessary.
+ */
+ WARN_ON(is_removed_spte(old_spte) || is_removed_spte(new_spte));
+
+ old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level);
+
+ __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false);
+
+ if (record_acc_track)
+ handle_changed_spte_acc_track(old_spte, new_spte, level);
+ if (record_dirty_log)
+ handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte,
+ new_spte, level);
+ return old_spte;
+}
+
+static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
+ u64 new_spte, bool record_acc_track,
+ bool record_dirty_log)
+{
+ WARN_ON_ONCE(iter->yielded);
+
+ iter->old_spte = __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep,
+ iter->old_spte, new_spte,
+ iter->gfn, iter->level,
+ record_acc_track, record_dirty_log);
+}
+
+static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
+ u64 new_spte)
+{
+ _tdp_mmu_set_spte(kvm, iter, new_spte, true, true);
+}
+
+static inline void tdp_mmu_set_spte_no_acc_track(struct kvm *kvm,
+ struct tdp_iter *iter,
+ u64 new_spte)
+{
+ _tdp_mmu_set_spte(kvm, iter, new_spte, false, true);
+}
+
+static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
+ struct tdp_iter *iter,
+ u64 new_spte)
+{
+ _tdp_mmu_set_spte(kvm, iter, new_spte, true, false);
+}
+
+#define tdp_root_for_each_pte(_iter, _root, _start, _end) \
+ for_each_tdp_pte(_iter, _root, _start, _end)
+
+#define tdp_root_for_each_leaf_pte(_iter, _root, _start, _end) \
+ tdp_root_for_each_pte(_iter, _root, _start, _end) \
+ if (!is_shadow_present_pte(_iter.old_spte) || \
+ !is_last_spte(_iter.old_spte, _iter.level)) \
+ continue; \
+ else
+
+#define tdp_mmu_for_each_pte(_iter, _mmu, _start, _end) \
+ for_each_tdp_pte(_iter, to_shadow_page(_mmu->root.hpa), _start, _end)
+
+/*
+ * Yield if the MMU lock is contended or this thread needs to return control
+ * to the scheduler.
+ *
+ * If this function should yield and flush is set, it will perform a remote
+ * TLB flush before yielding.
+ *
+ * If this function yields, iter->yielded is set and the caller must skip to
+ * the next iteration, where tdp_iter_next() will reset the tdp_iter's walk
+ * over the paging structures to allow the iterator to continue its traversal
+ * from the paging structure root.
+ *
+ * Returns true if this function yielded.
+ */
+static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm,
+ struct tdp_iter *iter,
+ bool flush, bool shared)
+{
+ WARN_ON(iter->yielded);
+
+ /* Ensure forward progress has been made before yielding. */
+ if (iter->next_last_level_gfn == iter->yielded_gfn)
+ return false;
+
+ if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
+ if (flush)
+ kvm_flush_remote_tlbs(kvm);
+
+ rcu_read_unlock();
+
+ if (shared)
+ cond_resched_rwlock_read(&kvm->mmu_lock);
+ else
+ cond_resched_rwlock_write(&kvm->mmu_lock);
+
+ rcu_read_lock();
+
+ WARN_ON(iter->gfn > iter->next_last_level_gfn);
+
+ iter->yielded = true;
+ }
+
+ return iter->yielded;
+}
+
+static inline gfn_t tdp_mmu_max_gfn_exclusive(void)
+{
+ /*
+ * Bound TDP MMU walks at host.MAXPHYADDR. KVM disallows memslots with
+ * a gpa range that would exceed the max gfn, and KVM does not create
+ * MMIO SPTEs for "impossible" gfns, instead sending such accesses down
+ * the slow emulation path every time.
+ */
+ return kvm_mmu_max_gfn() + 1;
+}
+
+static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
+ bool shared, int zap_level)
+{
+ struct tdp_iter iter;
+
+ gfn_t end = tdp_mmu_max_gfn_exclusive();
+ gfn_t start = 0;
+
+ for_each_tdp_pte_min_level(iter, root, zap_level, start, end) {
+retry:
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared))
+ continue;
+
+ if (!is_shadow_present_pte(iter.old_spte))
+ continue;
+
+ if (iter.level > zap_level)
+ continue;
+
+ if (!shared)
+ tdp_mmu_set_spte(kvm, &iter, 0);
+ else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0))
+ goto retry;
+ }
+}
+
+static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
+ bool shared)
+{
+
+ /*
+ * The root must have an elevated refcount so that it's reachable via
+ * mmu_notifier callbacks, which allows this path to yield and drop
+ * mmu_lock. When handling an unmap/release mmu_notifier command, KVM
+ * must drop all references to relevant pages prior to completing the
+ * callback. Dropping mmu_lock with an unreachable root would result
+ * in zapping SPTEs after a relevant mmu_notifier callback completes
+ * and lead to use-after-free as zapping a SPTE triggers "writeback" of
+ * dirty accessed bits to the SPTE's associated struct page.
+ */
+ WARN_ON_ONCE(!refcount_read(&root->tdp_mmu_root_count));
+
+ kvm_lockdep_assert_mmu_lock_held(kvm, shared);
+
+ rcu_read_lock();
+
+ /*
+ * To avoid RCU stalls due to recursively removing huge swaths of SPs,
+ * split the zap into two passes. On the first pass, zap at the 1gb
+ * level, and then zap top-level SPs on the second pass. "1gb" is not
+ * arbitrary, as KVM must be able to zap a 1gb shadow page without
+ * inducing a stall to allow in-place replacement with a 1gb hugepage.
+ *
+ * Because zapping a SP recurses on its children, stepping down to
+ * PG_LEVEL_4K in the iterator itself is unnecessary.
+ */
+ __tdp_mmu_zap_root(kvm, root, shared, PG_LEVEL_1G);
+ __tdp_mmu_zap_root(kvm, root, shared, root->role.level);
+
+ rcu_read_unlock();
+}
+
+bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ u64 old_spte;
+
+ /*
+ * This helper intentionally doesn't allow zapping a root shadow page,
+ * which doesn't have a parent page table and thus no associated entry.
+ */
+ if (WARN_ON_ONCE(!sp->ptep))
+ return false;
+
+ old_spte = kvm_tdp_mmu_read_spte(sp->ptep);
+ if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte)))
+ return false;
+
+ __tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0,
+ sp->gfn, sp->role.level + 1, true, true);
+
+ return true;
+}
+
+/*
+ * If can_yield is true, will release the MMU lock and reschedule if the
+ * scheduler needs the CPU or there is contention on the MMU lock. If this
+ * function cannot yield, it will not release the MMU lock or reschedule and
+ * the caller must ensure it does not supply too large a GFN range, or the
+ * operation can cause a soft lockup.
+ */
+static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
+ gfn_t start, gfn_t end, bool can_yield, bool flush)
+{
+ struct tdp_iter iter;
+
+ end = min(end, tdp_mmu_max_gfn_exclusive());
+
+ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ rcu_read_lock();
+
+ for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) {
+ if (can_yield &&
+ tdp_mmu_iter_cond_resched(kvm, &iter, flush, false)) {
+ flush = false;
+ continue;
+ }
+
+ if (!is_shadow_present_pte(iter.old_spte) ||
+ !is_last_spte(iter.old_spte, iter.level))
+ continue;
+
+ tdp_mmu_set_spte(kvm, &iter, 0);
+ flush = true;
+ }
+
+ rcu_read_unlock();
+
+ /*
+ * Because this flow zaps _only_ leaf SPTEs, the caller doesn't need
+ * to provide RCU protection as no 'struct kvm_mmu_page' will be freed.
+ */
+ return flush;
+}
+
+/*
+ * Zap leaf SPTEs for the range of gfns, [start, end), for all roots. Returns
+ * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or
+ * more SPTEs were zapped since the MMU lock was last acquired.
+ */
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush)
+{
+ struct kvm_mmu_page *root;
+
+ for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+ flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush);
+
+ return flush;
+}
+
+void kvm_tdp_mmu_zap_all(struct kvm *kvm)
+{
+ struct kvm_mmu_page *root;
+
+ /*
+ * Zap all roots, including invalid roots, as all SPTEs must be dropped
+ * before returning to the caller. Zap directly even if the root is
+ * also being zapped by a worker. Walking zapped top-level SPTEs isn't
+ * all that expensive and mmu_lock is already held, which means the
+ * worker has yielded, i.e. flushing the work instead of zapping here
+ * isn't guaranteed to be any faster.
+ *
+ * A TLB flush is unnecessary, KVM zaps everything if and only the VM
+ * is being destroyed or the userspace VMM has exited. In both cases,
+ * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request.
+ */
+ for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+ tdp_mmu_zap_root(kvm, root, false);
+}
+
+/*
+ * Zap all invalidated roots to ensure all SPTEs are dropped before the "fast
+ * zap" completes.
+ */
+void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
+{
+ struct kvm_mmu_page *root;
+
+ read_lock(&kvm->mmu_lock);
+
+ for_each_tdp_mmu_root_yield_safe(kvm, root, true) {
+ if (!root->tdp_mmu_scheduled_root_to_zap)
+ continue;
+
+ root->tdp_mmu_scheduled_root_to_zap = false;
+ KVM_BUG_ON(!root->role.invalid, kvm);
+
+ /*
+ * A TLB flush is not necessary as KVM performs a local TLB
+ * flush when allocating a new root (see kvm_mmu_load()), and
+ * when migrating a vCPU to a different pCPU. Note, the local
+ * TLB flush on reuse also invalidates paging-structure-cache
+ * entries, i.e. TLB entries for intermediate paging structures,
+ * that may be zapped, as such entries are associated with the
+ * ASID on both VMX and SVM.
+ */
+ tdp_mmu_zap_root(kvm, root, true);
+
+ /*
+ * The referenced needs to be put *after* zapping the root, as
+ * the root must be reachable by mmu_notifiers while it's being
+ * zapped
+ */
+ kvm_tdp_mmu_put_root(kvm, root, true);
+ }
+
+ read_unlock(&kvm->mmu_lock);
+}
+
+/*
+ * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that
+ * is about to be zapped, e.g. in response to a memslots update. The actual
+ * zapping is done separately so that it happens with mmu_lock with read,
+ * whereas invalidating roots must be done with mmu_lock held for write (unless
+ * the VM is being destroyed).
+ *
+ * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference.
+ * See kvm_tdp_mmu_get_vcpu_root_hpa().
+ */
+void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
+{
+ struct kvm_mmu_page *root;
+
+ /*
+ * mmu_lock must be held for write to ensure that a root doesn't become
+ * invalid while there are active readers (invalidating a root while
+ * there are active readers may or may not be problematic in practice,
+ * but it's uncharted territory and not supported).
+ *
+ * Waive the assertion if there are no users of @kvm, i.e. the VM is
+ * being destroyed after all references have been put, or if no vCPUs
+ * have been created (which means there are no roots), i.e. the VM is
+ * being destroyed in an error path of KVM_CREATE_VM.
+ */
+ if (IS_ENABLED(CONFIG_PROVE_LOCKING) &&
+ refcount_read(&kvm->users_count) && kvm->created_vcpus)
+ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ /*
+ * As above, mmu_lock isn't held when destroying the VM! There can't
+ * be other references to @kvm, i.e. nothing else can invalidate roots
+ * or get/put references to roots.
+ */
+ list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) {
+ /*
+ * Note, invalid roots can outlive a memslot update! Invalid
+ * roots must be *zapped* before the memslot update completes,
+ * but a different task can acquire a reference and keep the
+ * root alive after its been zapped.
+ */
+ if (!root->role.invalid) {
+ root->tdp_mmu_scheduled_root_to_zap = true;
+ root->role.invalid = true;
+ }
+ }
+}
+
+/*
+ * Installs a last-level SPTE to handle a TDP page fault.
+ * (NPT/EPT violation/misconfiguration)
+ */
+static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
+ struct kvm_page_fault *fault,
+ struct tdp_iter *iter)
+{
+ struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(iter->sptep));
+ u64 new_spte;
+ int ret = RET_PF_FIXED;
+ bool wrprot = false;
+
+ WARN_ON(sp->role.level != fault->goal_level);
+ if (unlikely(!fault->slot))
+ new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
+ else
+ wrprot = make_spte(vcpu, sp, fault->slot, ACC_ALL, iter->gfn,
+ fault->pfn, iter->old_spte, fault->prefetch, true,
+ fault->map_writable, &new_spte);
+
+ if (new_spte == iter->old_spte)
+ ret = RET_PF_SPURIOUS;
+ else if (tdp_mmu_set_spte_atomic(vcpu->kvm, iter, new_spte))
+ return RET_PF_RETRY;
+ else if (is_shadow_present_pte(iter->old_spte) &&
+ !is_last_spte(iter->old_spte, iter->level))
+ kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn,
+ KVM_PAGES_PER_HPAGE(iter->level + 1));
+
+ /*
+ * If the page fault was caused by a write but the page is write
+ * protected, emulation is needed. If the emulation was skipped,
+ * the vCPU would have the same fault again.
+ */
+ if (wrprot) {
+ if (fault->write)
+ ret = RET_PF_EMULATE;
+ }
+
+ /* If a MMIO SPTE is installed, the MMIO will need to be emulated. */
+ if (unlikely(is_mmio_spte(new_spte))) {
+ vcpu->stat.pf_mmio_spte_created++;
+ trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn,
+ new_spte);
+ ret = RET_PF_EMULATE;
+ } else {
+ trace_kvm_mmu_set_spte(iter->level, iter->gfn,
+ rcu_dereference(iter->sptep));
+ }
+
+ return ret;
+}
+
+/*
+ * tdp_mmu_link_sp - Replace the given spte with an spte pointing to the
+ * provided page table.
+ *
+ * @kvm: kvm instance
+ * @iter: a tdp_iter instance currently on the SPTE that should be set
+ * @sp: The new TDP page table to install.
+ * @account_nx: True if this page table is being installed to split a
+ * non-executable huge page.
+ * @shared: This operation is running under the MMU lock in read mode.
+ *
+ * Returns: 0 if the new page table was installed. Non-0 if the page table
+ * could not be installed (e.g. the atomic compare-exchange failed).
+ */
+static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
+ struct kvm_mmu_page *sp, bool account_nx,
+ bool shared)
+{
+ u64 spte = make_nonleaf_spte(sp->spt, !kvm_ad_enabled());
+ int ret = 0;
+
+ if (shared) {
+ ret = tdp_mmu_set_spte_atomic(kvm, iter, spte);
+ if (ret)
+ return ret;
+ } else {
+ tdp_mmu_set_spte(kvm, iter, spte);
+ }
+
+ spin_lock(&kvm->arch.tdp_mmu_pages_lock);
+ list_add(&sp->link, &kvm->arch.tdp_mmu_pages);
+ if (account_nx)
+ account_huge_nx_page(kvm, sp);
+ spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+ tdp_account_mmu_page(kvm, sp);
+
+ return 0;
+}
+
+/*
+ * Handle a TDP page fault (NPT/EPT violation/misconfiguration) by installing
+ * page tables and SPTEs to translate the faulting guest physical address.
+ */
+int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+{
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
+ struct tdp_iter iter;
+ struct kvm_mmu_page *sp;
+ int ret;
+
+ kvm_mmu_hugepage_adjust(vcpu, fault);
+
+ trace_kvm_mmu_spte_requested(fault);
+
+ rcu_read_lock();
+
+ tdp_mmu_for_each_pte(iter, mmu, fault->gfn, fault->gfn + 1) {
+ if (fault->nx_huge_page_workaround_enabled)
+ disallowed_hugepage_adjust(fault, iter.old_spte, iter.level);
+
+ if (iter.level == fault->goal_level)
+ break;
+
+ /*
+ * If there is an SPTE mapping a large page at a higher level
+ * than the target, that SPTE must be cleared and replaced
+ * with a non-leaf SPTE.
+ */
+ if (is_shadow_present_pte(iter.old_spte) &&
+ is_large_pte(iter.old_spte)) {
+ if (tdp_mmu_zap_spte_atomic(vcpu->kvm, &iter))
+ break;
+
+ /*
+ * The iter must explicitly re-read the spte here
+ * because the new value informs the !present
+ * path below.
+ */
+ iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
+ }
+
+ if (!is_shadow_present_pte(iter.old_spte)) {
+ bool account_nx = fault->huge_page_disallowed &&
+ fault->req_level >= iter.level;
+
+ /*
+ * If SPTE has been frozen by another thread, just
+ * give up and retry, avoiding unnecessary page table
+ * allocation and free.
+ */
+ if (is_removed_spte(iter.old_spte))
+ break;
+
+ sp = tdp_mmu_alloc_sp(vcpu);
+ tdp_mmu_init_child_sp(sp, &iter);
+
+ if (tdp_mmu_link_sp(vcpu->kvm, &iter, sp, account_nx, true)) {
+ tdp_mmu_free_sp(sp);
+ break;
+ }
+ }
+ }
+
+ /*
+ * Force the guest to retry the access if the upper level SPTEs aren't
+ * in place, or if the target leaf SPTE is frozen by another CPU.
+ */
+ if (iter.level != fault->goal_level || is_removed_spte(iter.old_spte)) {
+ rcu_read_unlock();
+ return RET_PF_RETRY;
+ }
+
+ ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter);
+ rcu_read_unlock();
+
+ return ret;
+}
+
+bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
+ bool flush)
+{
+ struct kvm_mmu_page *root;
+
+ __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false)
+ flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end,
+ range->may_block, flush);
+
+ return flush;
+}
+
+typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter,
+ struct kvm_gfn_range *range);
+
+static __always_inline bool kvm_tdp_mmu_handle_gfn(struct kvm *kvm,
+ struct kvm_gfn_range *range,
+ tdp_handler_t handler)
+{
+ struct kvm_mmu_page *root;
+ struct tdp_iter iter;
+ bool ret = false;
+
+ /*
+ * Don't support rescheduling, none of the MMU notifiers that funnel
+ * into this helper allow blocking; it'd be dead, wasteful code.
+ */
+ for_each_tdp_mmu_root(kvm, root, range->slot->as_id) {
+ rcu_read_lock();
+
+ tdp_root_for_each_leaf_pte(iter, root, range->start, range->end)
+ ret |= handler(kvm, &iter, range);
+
+ rcu_read_unlock();
+ }
+
+ return ret;
+}
+
+/*
+ * Mark the SPTEs range of GFNs [start, end) unaccessed and return non-zero
+ * if any of the GFNs in the range have been accessed.
+ */
+static bool age_gfn_range(struct kvm *kvm, struct tdp_iter *iter,
+ struct kvm_gfn_range *range)
+{
+ u64 new_spte = 0;
+
+ /* If we have a non-accessed entry we don't need to change the pte. */
+ if (!is_accessed_spte(iter->old_spte))
+ return false;
+
+ new_spte = iter->old_spte;
+
+ if (spte_ad_enabled(new_spte)) {
+ new_spte &= ~shadow_accessed_mask;
+ } else {
+ /*
+ * Capture the dirty status of the page, so that it doesn't get
+ * lost when the SPTE is marked for access tracking.
+ */
+ if (is_writable_pte(new_spte))
+ kvm_set_pfn_dirty(spte_to_pfn(new_spte));
+
+ new_spte = mark_spte_for_access_track(new_spte);
+ }
+
+ tdp_mmu_set_spte_no_acc_track(kvm, iter, new_spte);
+
+ return true;
+}
+
+bool kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+ return kvm_tdp_mmu_handle_gfn(kvm, range, age_gfn_range);
+}
+
+static bool test_age_gfn(struct kvm *kvm, struct tdp_iter *iter,
+ struct kvm_gfn_range *range)
+{
+ return is_accessed_spte(iter->old_spte);
+}
+
+bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+ return kvm_tdp_mmu_handle_gfn(kvm, range, test_age_gfn);
+}
+
+static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
+ struct kvm_gfn_range *range)
+{
+ u64 new_spte;
+
+ /* Huge pages aren't expected to be modified without first being zapped. */
+ WARN_ON(pte_huge(range->pte) || range->start + 1 != range->end);
+
+ if (iter->level != PG_LEVEL_4K ||
+ !is_shadow_present_pte(iter->old_spte))
+ return false;
+
+ /*
+ * Note, when changing a read-only SPTE, it's not strictly necessary to
+ * zero the SPTE before setting the new PFN, but doing so preserves the
+ * invariant that the PFN of a present * leaf SPTE can never change.
+ * See __handle_changed_spte().
+ */
+ tdp_mmu_set_spte(kvm, iter, 0);
+
+ if (!pte_write(range->pte)) {
+ new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte,
+ pte_pfn(range->pte));
+
+ tdp_mmu_set_spte(kvm, iter, new_spte);
+ }
+
+ return true;
+}
+
+/*
+ * Handle the changed_pte MMU notifier for the TDP MMU.
+ * data is a pointer to the new pte_t mapping the HVA specified by the MMU
+ * notifier.
+ * Returns non-zero if a flush is needed before releasing the MMU lock.
+ */
+bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+ /*
+ * No need to handle the remote TLB flush under RCU protection, the
+ * target SPTE _must_ be a leaf SPTE, i.e. cannot result in freeing a
+ * shadow page. See the WARN on pfn_changed in __handle_changed_spte().
+ */
+ return kvm_tdp_mmu_handle_gfn(kvm, range, set_spte_gfn);
+}
+
+/*
+ * Remove write access from all SPTEs at or above min_level that map GFNs
+ * [start, end). Returns true if an SPTE has been changed and the TLBs need to
+ * be flushed.
+ */
+static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ gfn_t start, gfn_t end, int min_level)
+{
+ struct tdp_iter iter;
+ u64 new_spte;
+ bool spte_set = false;
+
+ rcu_read_lock();
+
+ BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL);
+
+ for_each_tdp_pte_min_level(iter, root, min_level, start, end) {
+retry:
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
+ continue;
+
+ if (!is_shadow_present_pte(iter.old_spte) ||
+ !is_last_spte(iter.old_spte, iter.level) ||
+ !(iter.old_spte & PT_WRITABLE_MASK))
+ continue;
+
+ new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
+
+ if (tdp_mmu_set_spte_atomic(kvm, &iter, new_spte))
+ goto retry;
+
+ spte_set = true;
+ }
+
+ rcu_read_unlock();
+ return spte_set;
+}
+
+/*
+ * Remove write access from all the SPTEs mapping GFNs in the memslot. Will
+ * only affect leaf SPTEs down to min_level.
+ * Returns true if an SPTE has been changed and the TLBs need to be flushed.
+ */
+bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm,
+ const struct kvm_memory_slot *slot, int min_level)
+{
+ struct kvm_mmu_page *root;
+ bool spte_set = false;
+
+ lockdep_assert_held_read(&kvm->mmu_lock);
+
+ for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+ spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn,
+ slot->base_gfn + slot->npages, min_level);
+
+ return spte_set;
+}
+
+static struct kvm_mmu_page *__tdp_mmu_alloc_sp_for_split(gfp_t gfp)
+{
+ struct kvm_mmu_page *sp;
+
+ gfp |= __GFP_ZERO;
+
+ sp = kmem_cache_alloc(mmu_page_header_cache, gfp);
+ if (!sp)
+ return NULL;
+
+ sp->spt = (void *)__get_free_page(gfp);
+ if (!sp->spt) {
+ kmem_cache_free(mmu_page_header_cache, sp);
+ return NULL;
+ }
+
+ return sp;
+}
+
+static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm,
+ struct tdp_iter *iter,
+ bool shared)
+{
+ struct kvm_mmu_page *sp;
+
+ /*
+ * Since we are allocating while under the MMU lock we have to be
+ * careful about GFP flags. Use GFP_NOWAIT to avoid blocking on direct
+ * reclaim and to avoid making any filesystem callbacks (which can end
+ * up invoking KVM MMU notifiers, resulting in a deadlock).
+ *
+ * If this allocation fails we drop the lock and retry with reclaim
+ * allowed.
+ */
+ sp = __tdp_mmu_alloc_sp_for_split(GFP_NOWAIT | __GFP_ACCOUNT);
+ if (sp)
+ return sp;
+
+ rcu_read_unlock();
+
+ if (shared)
+ read_unlock(&kvm->mmu_lock);
+ else
+ write_unlock(&kvm->mmu_lock);
+
+ iter->yielded = true;
+ sp = __tdp_mmu_alloc_sp_for_split(GFP_KERNEL_ACCOUNT);
+
+ if (shared)
+ read_lock(&kvm->mmu_lock);
+ else
+ write_lock(&kvm->mmu_lock);
+
+ rcu_read_lock();
+
+ return sp;
+}
+
+static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
+ struct kvm_mmu_page *sp, bool shared)
+{
+ const u64 huge_spte = iter->old_spte;
+ const int level = iter->level;
+ int ret, i;
+
+ tdp_mmu_init_child_sp(sp, iter);
+
+ /*
+ * No need for atomics when writing to sp->spt since the page table has
+ * not been linked in yet and thus is not reachable from any other CPU.
+ */
+ for (i = 0; i < SPTE_ENT_PER_PAGE; i++)
+ sp->spt[i] = make_huge_page_split_spte(kvm, huge_spte, sp->role, i);
+
+ /*
+ * Replace the huge spte with a pointer to the populated lower level
+ * page table. Since we are making this change without a TLB flush vCPUs
+ * will see a mix of the split mappings and the original huge mapping,
+ * depending on what's currently in their TLB. This is fine from a
+ * correctness standpoint since the translation will be the same either
+ * way.
+ */
+ ret = tdp_mmu_link_sp(kvm, iter, sp, false, shared);
+ if (ret)
+ goto out;
+
+ /*
+ * tdp_mmu_link_sp_atomic() will handle subtracting the huge page we
+ * are overwriting from the page stats. But we have to manually update
+ * the page stats with the new present child pages.
+ */
+ kvm_update_page_stats(kvm, level - 1, SPTE_ENT_PER_PAGE);
+
+out:
+ trace_kvm_mmu_split_huge_page(iter->gfn, huge_spte, level, ret);
+ return ret;
+}
+
+static int tdp_mmu_split_huge_pages_root(struct kvm *kvm,
+ struct kvm_mmu_page *root,
+ gfn_t start, gfn_t end,
+ int target_level, bool shared)
+{
+ struct kvm_mmu_page *sp = NULL;
+ struct tdp_iter iter;
+ int ret = 0;
+
+ rcu_read_lock();
+
+ /*
+ * Traverse the page table splitting all huge pages above the target
+ * level into one lower level. For example, if we encounter a 1GB page
+ * we split it into 512 2MB pages.
+ *
+ * Since the TDP iterator uses a pre-order traversal, we are guaranteed
+ * to visit an SPTE before ever visiting its children, which means we
+ * will correctly recursively split huge pages that are more than one
+ * level above the target level (e.g. splitting a 1GB to 512 2MB pages,
+ * and then splitting each of those to 512 4KB pages).
+ */
+ for_each_tdp_pte_min_level(iter, root, target_level + 1, start, end) {
+retry:
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared))
+ continue;
+
+ if (!is_shadow_present_pte(iter.old_spte) || !is_large_pte(iter.old_spte))
+ continue;
+
+ if (!sp) {
+ sp = tdp_mmu_alloc_sp_for_split(kvm, &iter, shared);
+ if (!sp) {
+ ret = -ENOMEM;
+ trace_kvm_mmu_split_huge_page(iter.gfn,
+ iter.old_spte,
+ iter.level, ret);
+ break;
+ }
+
+ if (iter.yielded)
+ continue;
+ }
+
+ if (tdp_mmu_split_huge_page(kvm, &iter, sp, shared))
+ goto retry;
+
+ sp = NULL;
+ }
+
+ rcu_read_unlock();
+
+ /*
+ * It's possible to exit the loop having never used the last sp if, for
+ * example, a vCPU doing HugePage NX splitting wins the race and
+ * installs its own sp in place of the last sp we tried to split.
+ */
+ if (sp)
+ tdp_mmu_free_sp(sp);
+
+ return ret;
+}
+
+
+/*
+ * Try to split all huge pages mapped by the TDP MMU down to the target 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)
+{
+ struct kvm_mmu_page *root;
+ int r = 0;
+
+ kvm_lockdep_assert_mmu_lock_held(kvm, shared);
+
+ for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, shared) {
+ r = tdp_mmu_split_huge_pages_root(kvm, root, start, end, target_level, shared);
+ if (r) {
+ kvm_tdp_mmu_put_root(kvm, root, shared);
+ break;
+ }
+ }
+}
+
+/*
+ * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If
+ * AD bits are enabled, this will involve clearing the dirty bit on each SPTE.
+ * If AD bits are not enabled, this will require clearing the writable bit on
+ * each SPTE. Returns true if an SPTE has been changed and the TLBs need to
+ * be flushed.
+ */
+static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ gfn_t start, gfn_t end)
+{
+ struct tdp_iter iter;
+ u64 new_spte;
+ bool spte_set = false;
+
+ rcu_read_lock();
+
+ tdp_root_for_each_leaf_pte(iter, root, start, end) {
+retry:
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
+ continue;
+
+ if (!is_shadow_present_pte(iter.old_spte))
+ continue;
+
+ if (spte_ad_need_write_protect(iter.old_spte)) {
+ if (is_writable_pte(iter.old_spte))
+ new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
+ else
+ continue;
+ } else {
+ if (iter.old_spte & shadow_dirty_mask)
+ new_spte = iter.old_spte & ~shadow_dirty_mask;
+ else
+ continue;
+ }
+
+ if (tdp_mmu_set_spte_atomic(kvm, &iter, new_spte))
+ goto retry;
+
+ spte_set = true;
+ }
+
+ rcu_read_unlock();
+ return spte_set;
+}
+
+/*
+ * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If
+ * AD bits are enabled, this will involve clearing the dirty bit on each SPTE.
+ * If AD bits are not enabled, this will require clearing the writable bit on
+ * each SPTE. Returns true if an SPTE has been changed and the TLBs need to
+ * be flushed.
+ */
+bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
+ const struct kvm_memory_slot *slot)
+{
+ struct kvm_mmu_page *root;
+ bool spte_set = false;
+
+ lockdep_assert_held_read(&kvm->mmu_lock);
+
+ for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+ spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn,
+ slot->base_gfn + slot->npages);
+
+ return spte_set;
+}
+
+/*
+ * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is
+ * set in mask, starting at gfn. The given memslot is expected to contain all
+ * the GFNs represented by set bits in the mask. If AD bits are enabled,
+ * clearing the dirty status will involve clearing the dirty bit on each SPTE
+ * or, if AD bits are not enabled, clearing the writable bit on each SPTE.
+ */
+static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
+ gfn_t gfn, unsigned long mask, bool wrprot)
+{
+ struct tdp_iter iter;
+ u64 new_spte;
+
+ rcu_read_lock();
+
+ tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask),
+ gfn + BITS_PER_LONG) {
+ if (!mask)
+ break;
+
+ if (iter.level > PG_LEVEL_4K ||
+ !(mask & (1UL << (iter.gfn - gfn))))
+ continue;
+
+ mask &= ~(1UL << (iter.gfn - gfn));
+
+ if (wrprot || spte_ad_need_write_protect(iter.old_spte)) {
+ if (is_writable_pte(iter.old_spte))
+ new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
+ else
+ continue;
+ } else {
+ if (iter.old_spte & shadow_dirty_mask)
+ new_spte = iter.old_spte & ~shadow_dirty_mask;
+ else
+ continue;
+ }
+
+ tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+ }
+
+ rcu_read_unlock();
+}
+
+/*
+ * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is
+ * set in mask, starting at gfn. The given memslot is expected to contain all
+ * the GFNs represented by set bits in the mask. If AD bits are enabled,
+ * clearing the dirty status will involve clearing the dirty bit on each SPTE
+ * or, if AD bits are not enabled, clearing the writable bit on each SPTE.
+ */
+void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ gfn_t gfn, unsigned long mask,
+ bool wrprot)
+{
+ struct kvm_mmu_page *root;
+
+ lockdep_assert_held_write(&kvm->mmu_lock);
+ for_each_tdp_mmu_root(kvm, root, slot->as_id)
+ clear_dirty_pt_masked(kvm, root, gfn, mask, wrprot);
+}
+
+static void zap_collapsible_spte_range(struct kvm *kvm,
+ struct kvm_mmu_page *root,
+ const struct kvm_memory_slot *slot)
+{
+ gfn_t start = slot->base_gfn;
+ gfn_t end = start + slot->npages;
+ struct tdp_iter iter;
+ int max_mapping_level;
+
+ rcu_read_lock();
+
+ for_each_tdp_pte_min_level(iter, root, PG_LEVEL_2M, start, end) {
+retry:
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
+ continue;
+
+ if (iter.level > KVM_MAX_HUGEPAGE_LEVEL ||
+ !is_shadow_present_pte(iter.old_spte))
+ continue;
+
+ /*
+ * Don't zap leaf SPTEs, if a leaf SPTE could be replaced with
+ * a large page size, then its parent would have been zapped
+ * instead of stepping down.
+ */
+ if (is_last_spte(iter.old_spte, iter.level))
+ continue;
+
+ /*
+ * If iter.gfn resides outside of the slot, i.e. the page for
+ * the current level overlaps but is not contained by the slot,
+ * then the SPTE can't be made huge. More importantly, trying
+ * to query that info from slot->arch.lpage_info will cause an
+ * out-of-bounds access.
+ */
+ if (iter.gfn < start || iter.gfn >= end)
+ continue;
+
+ max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,
+ iter.gfn, PG_LEVEL_NUM);
+ if (max_mapping_level < iter.level)
+ continue;
+
+ /* Note, a successful atomic zap also does a remote TLB flush. */
+ if (tdp_mmu_zap_spte_atomic(kvm, &iter))
+ goto retry;
+ }
+
+ rcu_read_unlock();
+}
+
+/*
+ * Zap non-leaf SPTEs (and free their associated page tables) which could
+ * be replaced by huge pages, for GFNs within the slot.
+ */
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+ const struct kvm_memory_slot *slot)
+{
+ struct kvm_mmu_page *root;
+
+ lockdep_assert_held_read(&kvm->mmu_lock);
+
+ for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
+ zap_collapsible_spte_range(kvm, root, slot);
+}
+
+/*
+ * Removes write access on the last level SPTE mapping this GFN and unsets the
+ * MMU-writable bit to ensure future writes continue to be intercepted.
+ * Returns true if an SPTE was set and a TLB flush is needed.
+ */
+static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root,
+ gfn_t gfn, int min_level)
+{
+ struct tdp_iter iter;
+ u64 new_spte;
+ bool spte_set = false;
+
+ BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL);
+
+ rcu_read_lock();
+
+ for_each_tdp_pte_min_level(iter, root, min_level, gfn, gfn + 1) {
+ if (!is_shadow_present_pte(iter.old_spte) ||
+ !is_last_spte(iter.old_spte, iter.level))
+ continue;
+
+ new_spte = iter.old_spte &
+ ~(PT_WRITABLE_MASK | shadow_mmu_writable_mask);
+
+ if (new_spte == iter.old_spte)
+ break;
+
+ tdp_mmu_set_spte(kvm, &iter, new_spte);
+ spte_set = true;
+ }
+
+ rcu_read_unlock();
+
+ return spte_set;
+}
+
+/*
+ * Removes write access on the last level SPTE mapping this GFN and unsets the
+ * MMU-writable bit to ensure future writes continue to be intercepted.
+ * Returns true if an SPTE was set and a TLB flush is needed.
+ */
+bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
+ struct kvm_memory_slot *slot, gfn_t gfn,
+ int min_level)
+{
+ struct kvm_mmu_page *root;
+ bool spte_set = false;
+
+ lockdep_assert_held_write(&kvm->mmu_lock);
+ for_each_tdp_mmu_root(kvm, root, slot->as_id)
+ spte_set |= write_protect_gfn(kvm, root, gfn, min_level);
+
+ return spte_set;
+}
+
+/*
+ * Return the level of the lowest level SPTE added to sptes.
+ * That SPTE may be non-present.
+ *
+ * Must be called between kvm_tdp_mmu_walk_lockless_{begin,end}.
+ */
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+ int *root_level)
+{
+ struct tdp_iter iter;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
+ gfn_t gfn = addr >> PAGE_SHIFT;
+ int leaf = -1;
+
+ *root_level = vcpu->arch.mmu->root_role.level;
+
+ tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
+ leaf = iter.level;
+ sptes[leaf] = iter.old_spte;
+ }
+
+ return leaf;
+}
+
+/*
+ * Returns the last level spte pointer of the shadow page walk for the given
+ * gpa, and sets *spte to the spte value. This spte may be non-preset. If no
+ * walk could be performed, returns NULL and *spte does not contain valid data.
+ *
+ * Contract:
+ * - Must be called between kvm_tdp_mmu_walk_lockless_{begin,end}.
+ * - The returned sptep must not be used after kvm_tdp_mmu_walk_lockless_end.
+ *
+ * WARNING: This function is only intended to be called during fast_page_fault.
+ */
+u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr,
+ u64 *spte)
+{
+ struct tdp_iter iter;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
+ gfn_t gfn = addr >> PAGE_SHIFT;
+ tdp_ptep_t sptep = NULL;
+
+ tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
+ *spte = iter.old_spte;
+ sptep = iter.sptep;
+ }
+
+ /*
+ * Perform the rcu_dereference to get the raw spte pointer value since
+ * we are passing it up to fast_page_fault, which is shared with the
+ * legacy MMU and thus does not retain the TDP MMU-specific __rcu
+ * annotation.
+ *
+ * This is safe since fast_page_fault obeys the contracts of this
+ * function as well as all TDP MMU contracts around modifying SPTEs
+ * outside of mmu_lock.
+ */
+ return rcu_dereference(sptep);
+}
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
new file mode 100644
index 000000000..c82a8bb32
--- /dev/null
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -0,0 +1,95 @@
+// 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>
+
+hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
+
+__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,
+ bool shared);
+
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush);
+bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
+void kvm_tdp_mmu_zap_all(struct kvm *kvm);
+void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
+void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm);
+
+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_set_spte_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);
+bool 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_zap_collapsible_sptes(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, u64 addr,
+ u64 *spte);
+
+#ifdef CONFIG_X86_64
+void kvm_mmu_init_tdp_mmu(struct kvm *kvm);
+void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm);
+static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; }
+
+static inline bool is_tdp_mmu(struct kvm_mmu *mmu)
+{
+ struct kvm_mmu_page *sp;
+ hpa_t hpa = mmu->root.hpa;
+
+ if (WARN_ON(!VALID_PAGE(hpa)))
+ return false;
+
+ /*
+ * A NULL shadow page is legal when shadowing a non-paging guest with
+ * PAE paging, as the MMU will be direct with root_hpa pointing at the
+ * pae_root page, not a shadow page.
+ */
+ sp = to_shadow_page(hpa);
+ return sp && is_tdp_mmu_page(sp) && sp->root_count;
+}
+#else
+static inline void kvm_mmu_init_tdp_mmu(struct kvm *kvm) {}
+static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {}
+static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; }
+static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { return false; }
+#endif
+
+#endif /* __KVM_X86_MMU_TDP_MMU_H */