@@ -467,10 +467,6 @@ struct kvm_mmu {
*/
u32 pkru_mask;
- u64 *pae_root;
- u64 *pml4_root;
- u64 *pml5_root;
-
/*
* check zero bits on shadow page table entries, these
* bits include not only hardware reserved bits but also
@@ -2196,26 +2196,6 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
iterator->addr = addr;
iterator->shadow_addr = root;
iterator->level = vcpu->arch.mmu->shadow_root_level;
-
- if (iterator->level >= PT64_ROOT_4LEVEL &&
- vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
- !vcpu->arch.mmu->direct_map)
- 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 &= PT64_BASE_ADDR_MASK;
- --iterator->level;
- if (!iterator->shadow_addr)
- iterator->level = 0;
- }
}
static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
@@ -3328,18 +3308,7 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu,
&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_free_root_page(kvm, &mmu->root.hpa, &invalid_list);
mmu->root.hpa = INVALID_PAGE;
mmu->root.pgd = 0;
}
@@ -3404,7 +3373,6 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
struct kvm_mmu *mmu = vcpu->arch.mmu;
u8 shadow_root_level = mmu->shadow_root_level;
hpa_t root;
- unsigned i;
int r;
write_lock(&vcpu->kvm->mmu_lock);
@@ -3415,24 +3383,9 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
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) {
+ } else if (shadow_root_level >= PT32E_ROOT_LEVEL) {
root = mmu_alloc_root(vcpu, 0, 0, shadow_root_level, true);
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),
- i << 30, PT32_ROOT_LEVEL, true);
- mmu->pae_root[i] = root | PT_PRESENT_MASK |
- shadow_me_mask;
- }
- mmu->root.hpa = __pa(mmu->pae_root);
} else {
WARN_ONCE(1, "Bad TDP root level = %d\n", shadow_root_level);
r = -EIO;
@@ -3510,10 +3463,8 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm)
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;
hpa_t root;
- unsigned i;
int r;
root_pgd = mmu->get_guest_pgd(vcpu);
@@ -3522,21 +3473,6 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
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->root_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;
@@ -3546,70 +3482,9 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *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->root_level >= PT64_ROOT_4LEVEL) {
- root = mmu_alloc_root(vcpu, root_gfn, 0,
- mmu->shadow_root_level, false);
- 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_mask;
- if (mmu->shadow_root_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->shadow_root_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->root_level == PT32E_ROOT_LEVEL) {
- if (!(pdptrs[i] & PT_PRESENT_MASK)) {
- mmu->pae_root[i] = INVALID_PAE_ROOT;
- continue;
- }
- root_gfn = pdptrs[i] >> PAGE_SHIFT;
- }
-
- root = mmu_alloc_root(vcpu, root_gfn, i << 30,
- PT32_ROOT_LEVEL, false);
- mmu->pae_root[i] = root | pm_mask;
- }
-
- if (mmu->shadow_root_level == PT64_ROOT_5LEVEL)
- mmu->root.hpa = __pa(mmu->pml5_root);
- else if (mmu->shadow_root_level == PT64_ROOT_4LEVEL)
- mmu->root.hpa = __pa(mmu->pml4_root);
- else
- mmu->root.hpa = __pa(mmu->pae_root);
-
-set_root_pgd:
+ root = mmu_alloc_root(vcpu, root_gfn, 0,
+ mmu->shadow_root_level, false);
+ mmu->root.hpa = root;
mmu->root.pgd = root_pgd;
out_unlock:
write_unlock(&vcpu->kvm->mmu_lock);
@@ -3617,77 +3492,6 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
return r;
}
-static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
-{
- struct kvm_mmu *mmu = vcpu->arch.mmu;
- bool need_pml5 = mmu->shadow_root_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->direct_map || mmu->root_level >= PT64_ROOT_4LEVEL ||
- mmu->shadow_root_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;
@@ -3725,8 +3529,7 @@ static bool is_unsync_root(hpa_t root)
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
{
- int i;
- struct kvm_mmu_page *sp;
+ hpa_t root = vcpu->arch.mmu->root.hpa;
if (vcpu->arch.mmu->direct_map)
return;
@@ -3736,31 +3539,11 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
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;
- 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);
+ if (!is_unsync_root(root))
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 &= PT64_BASE_ADDR_MASK;
- sp = to_shadow_page(root);
- mmu_sync_children(vcpu, sp, true);
- }
- }
-
+ mmu_sync_children(vcpu, to_shadow_page(root), true);
write_unlock(&vcpu->kvm->mmu_lock);
}
@@ -5162,9 +4945,6 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
int r;
r = mmu_topup_memory_caches(vcpu, !vcpu->arch.mmu->direct_map);
- if (r)
- goto out;
- r = mmu_alloc_special_roots(vcpu);
if (r)
goto out;
if (vcpu->arch.mmu->direct_map)
@@ -5635,65 +5415,14 @@ slot_handle_level_4k(struct kvm *kvm, const struct kvm_memory_slot *memslot,
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_mask);
-
- for (i = 0; i < 4; ++i)
- mmu->pae_root[i] = INVALID_PAE_ROOT;
-
return 0;
}
@@ -5722,7 +5451,6 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
return ret;
fail_allocate_root:
- free_mmu_pages(&vcpu->arch.guest_mmu);
return ret;
}
@@ -6363,8 +6091,6 @@ int kvm_mmu_module_init(void)
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);
}
@@ -365,6 +365,16 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
pte = mmu->get_guest_pgd(vcpu);
have_ad = PT_HAVE_ACCESSED_DIRTY(mmu);
+ /* kvm_mmu_get_page() might use this values for allocating passthrough
+ * shadow page.
+ */
+ walker->table_gfn[4] = gpte_to_gfn(pte);
+ walker->pt_access[4] = ACC_ALL;
+ walker->table_gfn[3] = gpte_to_gfn(pte);
+ walker->pt_access[3] = ACC_ALL;
+ walker->table_gfn[2] = gpte_to_gfn(pte);
+ walker->pt_access[2] = ACC_ALL;
+
#if PTTYPE == 64
walk_nx_mask = 1ULL << PT64_NX_SHIFT;
if (walker->level == PT32E_ROOT_LEVEL) {
@@ -710,7 +720,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
* Verify that the gpte in the page we've just write
* protected is still there.
*/
- if (FNAME(gpte_changed)(vcpu, gw, it.level - 1))
+ if (it.level - 1 < top_level &&
+ FNAME(gpte_changed)(vcpu, gw, it.level - 1))
goto out_gpte_changed;
if (sp)