}
#endif
-#define PT64_PT_BITS 9
-#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS)
-#define PT32_PT_BITS 10
-#define PT32_ENT_PER_PAGE (1 << PT32_PT_BITS)
-
-#define PT_WRITABLE_SHIFT 1
-
-#define PT_PRESENT_MASK (1ULL << 0)
-#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT)
-#define PT_USER_MASK (1ULL << 2)
-#define PT_PWT_MASK (1ULL << 3)
-#define PT_PCD_MASK (1ULL << 4)
-#define PT_ACCESSED_MASK (1ULL << 5)
-#define PT_DIRTY_MASK (1ULL << 6)
-#define PT_PAGE_SIZE_MASK (1ULL << 7)
-#define PT_PAT_MASK (1ULL << 7)
-#define PT_GLOBAL_MASK (1ULL << 8)
-#define PT64_NX_SHIFT 63
-#define PT64_NX_MASK (1ULL << PT64_NX_SHIFT)
-
-#define PT_PAT_SHIFT 7
-#define PT_DIR_PAT_SHIFT 12
-#define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT)
-
-#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)
-
-
#define PT_FIRST_AVAIL_BITS_SHIFT 9
#define PT64_SECOND_AVAIL_BITS_SHIFT 52
#define PFERR_USER_MASK (1U << 2)
#define PFERR_FETCH_MASK (1U << 4)
-#define PT64_ROOT_LEVEL 4
-#define PT32_ROOT_LEVEL 2
-#define PT32E_ROOT_LEVEL 3
-
#define PT_DIRECTORY_LEVEL 2
#define PT_PAGE_TABLE_LEVEL 1
static u64 __read_mostly shadow_trap_nonpresent_pte;
static u64 __read_mostly shadow_notrap_nonpresent_pte;
+static u64 __read_mostly shadow_base_present_pte;
+static u64 __read_mostly shadow_nx_mask;
+static u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
+static u64 __read_mostly shadow_user_mask;
+static u64 __read_mostly shadow_accessed_mask;
+static u64 __read_mostly shadow_dirty_mask;
void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
{
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_nonpresent_ptes);
+void kvm_mmu_set_base_ptes(u64 base_pte)
+{
+ shadow_base_present_pte = base_pte;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_set_base_ptes);
+
+void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
+ u64 dirty_mask, u64 nx_mask, u64 x_mask)
+{
+ shadow_user_mask = user_mask;
+ shadow_accessed_mask = accessed_mask;
+ shadow_dirty_mask = dirty_mask;
+ shadow_nx_mask = nx_mask;
+ shadow_x_mask = x_mask;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
+
static int is_write_protection(struct kvm_vcpu *vcpu)
{
return vcpu->arch.cr0 & X86_CR0_WP;
static int is_dirty_pte(unsigned long pte)
{
- return pte & PT_DIRTY_MASK;
+ return pte & shadow_dirty_mask;
}
static int is_rmap_pte(u64 pte)
return is_shadow_present_pte(pte);
}
+static pfn_t spte_to_pfn(u64 pte)
+{
+ return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
+}
+
static gfn_t pse36_gfn_delta(u32 gpte)
{
int shift = 32 - PT32_DIR_PSE36_SHIFT - PAGE_SHIFT;
write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn));
*write_count += 1;
- WARN_ON(*write_count > KVM_PAGES_PER_HPAGE);
}
static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
struct kvm_rmap_desc *desc;
struct kvm_rmap_desc *prev_desc;
struct kvm_mmu_page *sp;
- struct page *page;
+ pfn_t pfn;
unsigned long *rmapp;
int i;
if (!is_rmap_pte(*spte))
return;
sp = page_header(__pa(spte));
- page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT);
- mark_page_accessed(page);
+ pfn = spte_to_pfn(*spte);
+ if (*spte & shadow_accessed_mask)
+ kvm_set_pfn_accessed(pfn);
if (is_writeble_pte(*spte))
- kvm_release_page_dirty(page);
+ kvm_release_pfn_dirty(pfn);
else
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], is_large_pte(*spte));
if (!*rmapp) {
printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
}
spte = rmap_next(kvm, rmapp, spte);
}
+ if (write_protected) {
+ pfn_t pfn;
+
+ spte = rmap_next(kvm, rmapp, NULL);
+ pfn = spte_to_pfn(*spte);
+ kvm_set_pfn_dirty(pfn);
+ }
+
/* check for huge page mappings */
rmapp = gfn_to_rmap(kvm, gfn, 1);
spte = rmap_next(kvm, rmapp, NULL);
rmap_remove(kvm, spte);
--kvm->stat.lpages;
set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+ spte = NULL;
write_protected = 1;
}
spte = rmap_next(kvm, rmapp, spte);
u64 *end;
for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
- if (*pos != shadow_trap_nonpresent_pte) {
+ if (is_shadow_present_pte(*pos)) {
printk(KERN_ERR "%s: %p %llx\n", __func__,
pos, *pos);
return 0;
sp->gfn = gfn;
sp->role = role;
hlist_add_head(&sp->hash_link, bucket);
- vcpu->arch.mmu.prefetch_page(vcpu, sp);
if (!metaphysical)
rmap_write_protect(vcpu->kvm, gfn);
+ vcpu->arch.mmu.prefetch_page(vcpu, sp);
return sp;
}
unsigned pt_access, unsigned pte_access,
int user_fault, int write_fault, int dirty,
int *ptwrite, int largepage, gfn_t gfn,
- struct page *page)
+ pfn_t pfn, bool speculative)
{
u64 spte;
int was_rmapped = 0;
int was_writeble = is_writeble_pte(*shadow_pte);
- hfn_t host_pfn = (*shadow_pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
pgprintk("%s: spte %llx access %x write_fault %d"
" user_fault %d gfn %lx\n",
child = page_header(pte & PT64_BASE_ADDR_MASK);
mmu_page_remove_parent_pte(child, shadow_pte);
- } else if (host_pfn != page_to_pfn(page)) {
+ } else if (pfn != spte_to_pfn(*shadow_pte)) {
pgprintk("hfn old %lx new %lx\n",
- host_pfn, page_to_pfn(page));
+ spte_to_pfn(*shadow_pte), pfn);
rmap_remove(vcpu->kvm, shadow_pte);
} else {
if (largepage)
* whether the guest actually used the pte (in order to detect
* demand paging).
*/
- spte = PT_PRESENT_MASK | PT_DIRTY_MASK;
+ spte = shadow_base_present_pte | shadow_dirty_mask;
+ if (!speculative)
+ pte_access |= PT_ACCESSED_MASK;
if (!dirty)
pte_access &= ~ACC_WRITE_MASK;
- if (!(pte_access & ACC_EXEC_MASK))
- spte |= PT64_NX_MASK;
-
- spte |= PT_PRESENT_MASK;
+ if (pte_access & ACC_EXEC_MASK)
+ spte |= shadow_x_mask;
+ else
+ spte |= shadow_nx_mask;
if (pte_access & ACC_USER_MASK)
- spte |= PT_USER_MASK;
+ spte |= shadow_user_mask;
if (largepage)
spte |= PT_PAGE_SIZE_MASK;
- spte |= page_to_phys(page);
+ spte |= (u64)pfn << PAGE_SHIFT;
if ((pte_access & ACC_WRITE_MASK)
|| (write_fault && !is_write_protection(vcpu) && !user_fault)) {
struct kvm_mmu_page *shadow;
spte |= PT_WRITABLE_MASK;
- if (user_fault) {
- mmu_unshadow(vcpu->kvm, gfn);
- goto unshadowed;
- }
shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
if (shadow ||
}
}
-unshadowed:
-
if (pte_access & ACC_WRITE_MASK)
mark_page_dirty(vcpu->kvm, gfn);
if (!was_rmapped) {
rmap_add(vcpu, shadow_pte, gfn, largepage);
if (!is_rmap_pte(*shadow_pte))
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
} else {
if (was_writeble)
- kvm_release_page_dirty(page);
+ kvm_release_pfn_dirty(pfn);
else
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
}
if (!ptwrite || !*ptwrite)
vcpu->arch.last_pte_updated = shadow_pte;
}
static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
- int largepage, gfn_t gfn, struct page *page,
+ int largepage, gfn_t gfn, pfn_t pfn,
int level)
{
hpa_t table_addr = vcpu->arch.mmu.root_hpa;
if (level == 1) {
mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL,
- 0, write, 1, &pt_write, 0, gfn, page);
+ 0, write, 1, &pt_write, 0, gfn, pfn, false);
return pt_write;
}
if (largepage && level == 2) {
mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL,
- 0, write, 1, &pt_write, 1, gfn, page);
+ 0, write, 1, &pt_write, 1, gfn, pfn, false);
return pt_write;
}
1, ACC_ALL, &table[index]);
if (!new_table) {
pgprintk("nonpaging_map: ENOMEM\n");
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
return -ENOMEM;
}
- table[index] = __pa(new_table->spt) | PT_PRESENT_MASK
- | PT_WRITABLE_MASK | PT_USER_MASK;
+ table[index] = __pa(new_table->spt)
+ | PT_PRESENT_MASK | PT_WRITABLE_MASK
+ | shadow_user_mask | shadow_x_mask;
}
table_addr = table[index] & PT64_BASE_ADDR_MASK;
}
{
int r;
int largepage = 0;
-
- struct page *page;
-
- down_read(&vcpu->kvm->slots_lock);
+ pfn_t pfn;
down_read(¤t->mm->mmap_sem);
if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
largepage = 1;
}
- page = gfn_to_page(vcpu->kvm, gfn);
+ pfn = gfn_to_pfn(vcpu->kvm, gfn);
up_read(¤t->mm->mmap_sem);
/* mmio */
- if (is_error_page(page)) {
- kvm_release_page_clean(page);
- up_read(&vcpu->kvm->slots_lock);
+ if (is_error_pfn(pfn)) {
+ kvm_release_pfn_clean(pfn);
return 1;
}
spin_lock(&vcpu->kvm->mmu_lock);
kvm_mmu_free_some_pages(vcpu);
- r = __direct_map(vcpu, v, write, largepage, gfn, page,
+ r = __direct_map(vcpu, v, write, largepage, gfn, pfn,
PT32E_ROOT_LEVEL);
spin_unlock(&vcpu->kvm->mmu_lock);
- up_read(&vcpu->kvm->slots_lock);
return r;
}
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
spin_lock(&vcpu->kvm->mmu_lock);
-#ifdef CONFIG_X86_64
if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
spin_unlock(&vcpu->kvm->mmu_lock);
return;
}
-#endif
for (i = 0; i < 4; ++i) {
hpa_t root = vcpu->arch.mmu.pae_root[i];
root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT;
-#ifdef CONFIG_X86_64
if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
vcpu->arch.mmu.root_hpa = root;
return;
}
-#endif
metaphysical = !is_paging(vcpu);
if (tdp_enabled)
metaphysical = 1;
static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
u32 error_code)
{
- struct page *page;
+ pfn_t pfn;
int r;
int largepage = 0;
gfn_t gfn = gpa >> PAGE_SHIFT;
gfn &= ~(KVM_PAGES_PER_HPAGE-1);
largepage = 1;
}
- page = gfn_to_page(vcpu->kvm, gfn);
- if (is_error_page(page)) {
- kvm_release_page_clean(page);
- up_read(¤t->mm->mmap_sem);
+ pfn = gfn_to_pfn(vcpu->kvm, gfn);
+ up_read(¤t->mm->mmap_sem);
+ if (is_error_pfn(pfn)) {
+ kvm_release_pfn_clean(pfn);
return 1;
}
spin_lock(&vcpu->kvm->mmu_lock);
kvm_mmu_free_some_pages(vcpu);
r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK,
- largepage, gfn, page, TDP_ROOT_LEVEL);
+ largepage, gfn, pfn, kvm_x86_ops->get_tdp_level());
spin_unlock(&vcpu->kvm->mmu_lock);
- up_read(¤t->mm->mmap_sem);
return r;
}
context->page_fault = tdp_page_fault;
context->free = nonpaging_free;
context->prefetch_page = nonpaging_prefetch_page;
- context->shadow_root_level = TDP_ROOT_LEVEL;
+ context->shadow_root_level = kvm_x86_ops->get_tdp_level();
context->root_hpa = INVALID_PAGE;
if (!is_paging(vcpu)) {
static int init_kvm_mmu(struct kvm_vcpu *vcpu)
{
+ vcpu->arch.update_pte.pfn = bad_pfn;
+
if (tdp_enabled)
return init_kvm_tdp_mmu(vcpu);
else
u64 *spte,
const void *new)
{
- if ((sp->role.level != PT_PAGE_TABLE_LEVEL)
- && !vcpu->arch.update_pte.largepage) {
- ++vcpu->kvm->stat.mmu_pde_zapped;
- return;
- }
+ if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
+ if (!vcpu->arch.update_pte.largepage ||
+ sp->role.glevels == PT32_ROOT_LEVEL) {
+ ++vcpu->kvm->stat.mmu_pde_zapped;
+ return;
+ }
+ }
++vcpu->kvm->stat.mmu_pte_updated;
if (sp->role.glevels == PT32_ROOT_LEVEL)
{
u64 *spte = vcpu->arch.last_pte_updated;
- return !!(spte && (*spte & PT_ACCESSED_MASK));
+ return !!(spte && (*spte & shadow_accessed_mask));
}
static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
gfn_t gfn;
int r;
u64 gpte = 0;
- struct page *page;
+ pfn_t pfn;
vcpu->arch.update_pte.largepage = 0;
gfn &= ~(KVM_PAGES_PER_HPAGE-1);
vcpu->arch.update_pte.largepage = 1;
}
- page = gfn_to_page(vcpu->kvm, gfn);
+ pfn = gfn_to_pfn(vcpu->kvm, gfn);
up_read(¤t->mm->mmap_sem);
- if (is_error_page(page)) {
- kvm_release_page_clean(page);
+ if (is_error_pfn(pfn)) {
+ kvm_release_pfn_clean(pfn);
return;
}
vcpu->arch.update_pte.gfn = gfn;
- vcpu->arch.update_pte.page = page;
+ vcpu->arch.update_pte.pfn = pfn;
}
void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
}
kvm_mmu_audit(vcpu, "post pte write");
spin_unlock(&vcpu->kvm->mmu_lock);
- if (vcpu->arch.update_pte.page) {
- kvm_release_page_clean(vcpu->arch.update_pte.page);
- vcpu->arch.update_pte.page = NULL;
+ if (!is_error_pfn(vcpu->arch.update_pte.pfn)) {
+ kvm_release_pfn_clean(vcpu->arch.update_pte.pfn);
+ vcpu->arch.update_pte.pfn = bad_pfn;
}
}
gpa_t gpa;
int r;
- down_read(&vcpu->kvm->slots_lock);
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva);
- up_read(&vcpu->kvm->slots_lock);
spin_lock(&vcpu->kvm->mmu_lock);
r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
sp = container_of(vcpu->kvm->arch.active_mmu_pages.next,
struct kvm_mmu_page, link);
kvm_mmu_zap_page(vcpu->kvm, sp);
+ cond_resched();
}
free_page((unsigned long)vcpu->arch.mmu.pae_root);
}
kvm_flush_remote_tlbs(kvm);
}
-void kvm_mmu_module_exit(void)
+void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm)
+{
+ struct kvm_mmu_page *page;
+
+ page = container_of(kvm->arch.active_mmu_pages.prev,
+ struct kvm_mmu_page, link);
+ kvm_mmu_zap_page(kvm, page);
+}
+
+static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
+{
+ struct kvm *kvm;
+ struct kvm *kvm_freed = NULL;
+ int cache_count = 0;
+
+ spin_lock(&kvm_lock);
+
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ int npages;
+
+ spin_lock(&kvm->mmu_lock);
+ npages = kvm->arch.n_alloc_mmu_pages -
+ kvm->arch.n_free_mmu_pages;
+ cache_count += npages;
+ if (!kvm_freed && nr_to_scan > 0 && npages > 0) {
+ kvm_mmu_remove_one_alloc_mmu_page(kvm);
+ cache_count--;
+ kvm_freed = kvm;
+ }
+ nr_to_scan--;
+
+ spin_unlock(&kvm->mmu_lock);
+ }
+ if (kvm_freed)
+ list_move_tail(&kvm_freed->vm_list, &vm_list);
+
+ spin_unlock(&kvm_lock);
+
+ return cache_count;
+}
+
+static struct shrinker mmu_shrinker = {
+ .shrink = mmu_shrink,
+ .seeks = DEFAULT_SEEKS * 10,
+};
+
+static void mmu_destroy_caches(void)
{
if (pte_chain_cache)
kmem_cache_destroy(pte_chain_cache);
kmem_cache_destroy(mmu_page_header_cache);
}
+void kvm_mmu_module_exit(void)
+{
+ mmu_destroy_caches();
+ unregister_shrinker(&mmu_shrinker);
+}
+
int kvm_mmu_module_init(void)
{
pte_chain_cache = kmem_cache_create("kvm_pte_chain",
if (!mmu_page_header_cache)
goto nomem;
+ register_shrinker(&mmu_shrinker);
+
return 0;
nomem:
- kvm_mmu_module_exit();
+ mmu_destroy_caches();
return -ENOMEM;
}
if (r)
return r;
- if (!__emulator_write_phys(vcpu, addr, &value, bytes))
+ if (!emulator_write_phys(vcpu, addr, &value, bytes))
return -EFAULT;
return 1;
int r;
struct kvm_pv_mmu_op_buffer buffer;
- down_read(&vcpu->kvm->slots_lock);
- down_read(¤t->mm->mmap_sem);
-
buffer.ptr = buffer.buf;
buffer.len = min_t(unsigned long, bytes, sizeof buffer.buf);
buffer.processed = 0;
r = 1;
out:
*ret = buffer.processed;
- up_read(¤t->mm->mmap_sem);
- up_read(&vcpu->kvm->slots_lock);
return r;
}
audit_mappings_page(vcpu, ent, va, level - 1);
} else {
gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va);
- struct page *page = gpa_to_page(vcpu, gpa);
- hpa_t hpa = page_to_phys(page);
+ hpa_t hpa = (hpa_t)gpa_to_pfn(vcpu, gpa) << PAGE_SHIFT;
if (is_shadow_present_pte(ent)
&& (ent & PT64_BASE_ADDR_MASK) != hpa)
&& !is_error_hpa(hpa))
printk(KERN_ERR "audit: (%s) notrap shadow,"
" valid guest gva %lx\n", audit_msg, va);
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
}
}
projects / linux-2.6-omap-h63xx.git / blobdiff