static int tdp_root_level __read_mostly;
static int max_tdp_level __read_mostly;
-enum {
- AUDIT_PRE_PAGE_FAULT,
- AUDIT_POST_PAGE_FAULT,
- AUDIT_PRE_PTE_WRITE,
- AUDIT_POST_PTE_WRITE,
- AUDIT_PRE_SYNC,
- AUDIT_POST_SYNC
-};
-
#ifdef MMU_DEBUG
bool dbg = 0;
module_param(dbg, bool, 0644);
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);
/* Rules for using mmu_spte_update:
* Update the state bits, it means the mapped pfn is not changed.
*
- * Whenever we overwrite a writable spte with a read-only one we
- * should flush remote TLBs. Otherwise rmap_write_protect
- * will find a read-only spte, even though the writable spte
- * might be cached on a CPU's TLB, the return value indicates this
- * case.
+ * 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
*/
return __get_spte_lockless(sptep);
}
-/* Restore an acc-track PTE back to a regular PTE */
-static u64 restore_acc_track_spte(u64 spte)
-{
- u64 new_spte = spte;
- u64 saved_bits = (spte >> SHADOW_ACC_TRACK_SAVED_BITS_SHIFT)
- & SHADOW_ACC_TRACK_SAVED_BITS_MASK;
-
- WARN_ON_ONCE(spte_ad_enabled(spte));
- WARN_ON_ONCE(!is_access_track_spte(spte));
-
- new_spte &= ~shadow_acc_track_mask;
- new_spte &= ~(SHADOW_ACC_TRACK_SAVED_BITS_MASK <<
- SHADOW_ACC_TRACK_SAVED_BITS_SHIFT);
- new_spte |= saved_bits;
-
- return new_spte;
-}
-
/* Returns the Accessed status of the PTE and resets it at the same time. */
static bool mmu_spte_age(u64 *sptep)
{
return mmu_spte_update(sptep, spte);
}
-static bool __rmap_write_protect(struct kvm *kvm,
- struct kvm_rmap_head *rmap_head,
- bool pt_protect)
+static bool rmap_write_protect(struct kvm_rmap_head *rmap_head,
+ bool pt_protect)
{
u64 *sptep;
struct rmap_iterator iter;
while (mask) {
rmap_head = gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
PG_LEVEL_4K, slot);
- __rmap_write_protect(kvm, rmap_head, false);
+ rmap_write_protect(rmap_head, false);
/* clear the first set bit */
mask &= mask - 1;
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 (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(kvm, rmap_head, true);
+ write_protected |= rmap_write_protect(rmap_head, true);
}
}
return write_protected;
}
-static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
+static bool kvm_vcpu_write_protect_gfn(struct kvm_vcpu *vcpu, u64 gfn)
{
struct kvm_memory_slot *slot;
return true;
}
-#ifdef CONFIG_KVM_MMU_AUDIT
-#include "mmu_audit.c"
-#else
-static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { }
-static void mmu_audit_disable(void) { }
-#endif
-
static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
{
if (sp->role.invalid)
bool protected = false;
for_each_sp(pages, sp, parents, i)
- protected |= rmap_write_protect(vcpu, sp->gfn);
+ protected |= kvm_vcpu_write_protect_gfn(vcpu, sp->gfn);
if (protected) {
kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, true);
hlist_add_head(&sp->hash_link, sp_list);
if (!direct) {
account_shadowed(vcpu->kvm, sp);
- if (level == PG_LEVEL_4K && rmap_write_protect(vcpu, gfn))
+ if (level == PG_LEVEL_4K && kvm_vcpu_write_protect_gfn(vcpu, gfn))
kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn, 1);
}
trace_kvm_mmu_get_page(sp, true);
* 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);
+ BUG_ON(root != vcpu->arch.mmu->root.hpa);
iterator->shadow_addr
= vcpu->arch.mmu->pae_root[(addr >> 30) & 3];
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,
+ shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu->root.hpa,
addr);
}
return zapped;
}
-static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
+static void kvm_mmu_unlink_parents(struct kvm_mmu_page *sp)
{
u64 *sptep;
struct rmap_iterator iter;
++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(kvm, sp);
+ kvm_mmu_unlink_parents(sp);
/* Zapping children means active_mmu_pages has become unstable. */
list_unstable = *nr_zapped;
return;
sp = to_shadow_page(*root_hpa & PT64_BASE_ADDR_MASK);
+ if (WARN_ON(!sp))
+ return;
if (is_tdp_mmu_page(sp))
kvm_tdp_mmu_put_root(kvm, sp, false);
}
/* roots_to_free must be some combination of the KVM_MMU_ROOT_* flags */
-void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu,
ulong roots_to_free)
{
- struct kvm *kvm = vcpu->kvm;
int i;
LIST_HEAD(invalid_list);
- bool free_active_root = roots_to_free & KVM_MMU_ROOT_CURRENT;
+ 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. */
- if (!(free_active_root && VALID_PAGE(mmu->root_hpa))) {
+ 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))
&invalid_list);
if (free_active_root) {
- if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL &&
- (mmu->root_level >= PT64_ROOT_4LEVEL || mmu->direct_map)) {
- mmu_free_root_page(kvm, &mmu->root_hpa, &invalid_list);
+ 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]))
mmu->pae_root[i] = INVALID_PAE_ROOT;
}
}
- mmu->root_hpa = INVALID_PAGE;
- mmu->root_pgd = 0;
+ mmu->root.hpa = INVALID_PAGE;
+ mmu->root.pgd = 0;
}
kvm_mmu_commit_zap_page(kvm, &invalid_list);
}
EXPORT_SYMBOL_GPL(kvm_mmu_free_roots);
-void kvm_mmu_free_guest_mode_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu)
{
unsigned long roots_to_free = 0;
hpa_t root_hpa;
roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
}
- kvm_mmu_free_roots(vcpu, mmu, roots_to_free);
+ kvm_mmu_free_roots(kvm, mmu, roots_to_free);
}
EXPORT_SYMBOL_GPL(kvm_mmu_free_guest_mode_roots);
if (is_tdp_mmu_enabled(vcpu->kvm)) {
root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu);
- mmu->root_hpa = root;
+ mmu->root.hpa = root;
} else if (shadow_root_level >= PT64_ROOT_4LEVEL) {
root = mmu_alloc_root(vcpu, 0, 0, shadow_root_level, true);
- mmu->root_hpa = root;
+ mmu->root.hpa = root;
} else if (shadow_root_level == PT32E_ROOT_LEVEL) {
if (WARN_ON_ONCE(!mmu->pae_root)) {
r = -EIO;
mmu->pae_root[i] = root | PT_PRESENT_MASK |
shadow_me_mask;
}
- mmu->root_hpa = __pa(mmu->pae_root);
+ 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;
+ /* root.pgd is ignored for direct MMUs. */
+ mmu->root.pgd = 0;
out_unlock:
write_unlock(&vcpu->kvm->mmu_lock);
return r;
if (mmu->root_level >= PT64_ROOT_4LEVEL) {
root = mmu_alloc_root(vcpu, root_gfn, 0,
mmu->shadow_root_level, false);
- mmu->root_hpa = root;
+ mmu->root.hpa = root;
goto set_root_pgd;
}
}
if (mmu->shadow_root_level == PT64_ROOT_5LEVEL)
- mmu->root_hpa = __pa(mmu->pml5_root);
+ mmu->root.hpa = __pa(mmu->pml5_root);
else if (mmu->shadow_root_level == PT64_ROOT_4LEVEL)
- mmu->root_hpa = __pa(mmu->pml4_root);
+ mmu->root.hpa = __pa(mmu->pml4_root);
else
- mmu->root_hpa = __pa(mmu->pae_root);
+ mmu->root.hpa = __pa(mmu->pae_root);
set_root_pgd:
- mmu->root_pgd = root_pgd;
+ mmu->root.pgd = root_pgd;
out_unlock:
write_unlock(&vcpu->kvm->mmu_lock);
if (vcpu->arch.mmu->direct_map)
return;
- if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root.hpa))
return;
vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
- hpa_t root = vcpu->arch.mmu->root_hpa;
+ 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);
- kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
-
mmu_sync_children(vcpu, sp, true);
-
- kvm_mmu_audit(vcpu, AUDIT_POST_SYNC);
write_unlock(&vcpu->kvm->mmu_lock);
return;
}
write_lock(&vcpu->kvm->mmu_lock);
- kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
for (i = 0; i < 4; ++i) {
hpa_t root = vcpu->arch.mmu->pae_root[i];
}
}
- kvm_mmu_audit(vcpu, AUDIT_POST_SYNC);
write_unlock(&vcpu->kvm->mmu_lock);
}
roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
/* sync prev_roots by simply freeing them */
- kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free);
+ 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,
static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
struct kvm_page_fault *fault, int mmu_seq)
{
- struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root_hpa);
+ 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))
/*
* Find out if a previously cached root matching the new pgd/role is available.
* The current root is also inserted into the cache.
- * If a matching root was found, it is assigned to kvm_mmu->root_hpa and true is
+ * If a matching root was found, it is assigned to kvm_mmu->root.hpa and true is
* returned.
- * Otherwise, the LRU root from the cache is assigned to kvm_mmu->root_hpa and
+ * Otherwise, the LRU root from the cache is assigned to kvm_mmu->root.hpa and
* false is returned. This root should now be freed by the caller.
*/
static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_pgd,
union kvm_mmu_page_role new_role)
{
uint i;
- struct kvm_mmu_root_info root;
struct kvm_mmu *mmu = vcpu->arch.mmu;
- root.pgd = mmu->root_pgd;
- root.hpa = mmu->root_hpa;
-
- if (is_root_usable(&root, new_pgd, new_role))
+ if (is_root_usable(&mmu->root, new_pgd, new_role))
return true;
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
- swap(root, mmu->prev_roots[i]);
+ swap(mmu->root, mmu->prev_roots[i]);
- if (is_root_usable(&root, new_pgd, new_role))
+ if (is_root_usable(&mmu->root, new_pgd, new_role))
break;
}
- mmu->root_hpa = root.hpa;
- mmu->root_pgd = root.pgd;
-
return i < KVM_MMU_NUM_PREV_ROOTS;
}
static void __kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd,
union kvm_mmu_page_role new_role)
{
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
+
if (!fast_pgd_switch(vcpu, new_pgd, new_role)) {
- kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, KVM_MMU_ROOT_CURRENT);
+ kvm_mmu_free_roots(vcpu->kvm, mmu, KVM_MMU_ROOT_CURRENT);
return;
}
*/
if (!new_role.direct)
__clear_sp_write_flooding_count(
- to_shadow_page(vcpu->arch.mmu->root_hpa));
+ to_shadow_page(vcpu->arch.mmu->root.hpa));
}
void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd)
* possible, however, kvm currently does not do execution-protection.
*/
static void
-reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
- struct kvm_mmu *context)
+reset_tdp_shadow_zero_bits_mask(struct kvm_mmu *context)
{
struct rsvd_bits_validate *shadow_zero_check;
int i;
* is the shadow page table for intel nested guest.
*/
static void
-reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
- struct kvm_mmu *context, bool execonly)
+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,
context->gva_to_gpa = paging32_gva_to_gpa;
reset_guest_paging_metadata(vcpu, context);
- reset_tdp_shadow_zero_bits_mask(vcpu, context);
+ reset_tdp_shadow_zero_bits_mask(context);
}
static union kvm_mmu_role
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(vcpu, context, execonly);
+ reset_ept_shadow_zero_bits_mask(context, execonly);
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
kvm_mmu_sync_roots(vcpu);
kvm_mmu_load_pgd(vcpu);
- static_call(kvm_x86_tlb_flush_current)(vcpu);
+ static_call(kvm_x86_flush_tlb_current)(vcpu);
out:
return r;
}
void kvm_mmu_unload(struct kvm_vcpu *vcpu)
{
- kvm_mmu_free_roots(vcpu, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL);
- WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root_hpa));
- kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
- WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root_hpa));
+ 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));
}
static bool need_remote_flush(u64 old, u64 new)
gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes);
++vcpu->kvm->stat.mmu_pte_write;
- kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (detect_write_misaligned(sp, gpa, bytes) ||
}
}
kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, flush);
- kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE);
write_unlock(&vcpu->kvm->mmu_lock);
}
int r, emulation_type = EMULTYPE_PF;
bool direct = vcpu->arch.mmu->direct_map;
- if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)))
+ if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
return RET_PF_RETRY;
r = RET_PF_INVALID;
if (is_noncanonical_address(gva, vcpu))
return;
- static_call(kvm_x86_tlb_flush_gva)(vcpu, gva);
+ 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);
+ mmu->invlpg(vcpu, gva, mmu->root.hpa);
/*
* INVLPG is required to invalidate any global mappings for the VA,
uint i;
if (pcid == kvm_get_active_pcid(vcpu)) {
- mmu->invlpg(vcpu, gva, mmu->root_hpa);
+ mmu->invlpg(vcpu, gva, mmu->root.hpa);
tlb_flush = true;
}
}
if (tlb_flush)
- static_call(kvm_x86_tlb_flush_gva)(vcpu, gva);
+ static_call(kvm_x86_flush_tlb_gva)(vcpu, gva);
++vcpu->stat.invlpg;
struct page *page;
int i;
- mmu->root_hpa = INVALID_PAGE;
- mmu->root_pgd = 0;
+ 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;
struct kvm_rmap_head *rmap_head,
const struct kvm_memory_slot *slot)
{
- return __rmap_write_protect(kvm, rmap_head, false);
+ return rmap_write_protect(rmap_head, false);
}
void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
* will clear a separate software-only bit (MMU-writable) and skip the
* flush if-and-only-if this bit was already clear.
*
- * See DEFAULT_SPTE_MMU_WRITEABLE for more details.
+ * See is_writable_pte() for more details.
*/
if (flush)
kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
}
+/* 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))
+ 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)) {
+ 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)
mmu_destroy_caches();
percpu_counter_destroy(&kvm_total_used_mmu_pages);
unregister_shrinker(&mmu_shrinker);
- mmu_audit_disable();
}
/*