static int dbg = 1;
#endif
+#ifndef MMU_DEBUG
+#define ASSERT(x) do { } while (0)
+#else
#define ASSERT(x) \
if (!(x)) { \
printk(KERN_WARNING "assertion failed %s:%d: %s\n", \
__FILE__, __LINE__, #x); \
}
+#endif
#define PT64_PT_BITS 9
#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS)
(((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))
-#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & PAGE_MASK)
+#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
#define PT64_DIR_BASE_ADDR_MASK \
(PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1))
struct kvm_rmap_desc *more;
};
+static struct kmem_cache *pte_chain_cache;
+static struct kmem_cache *rmap_desc_cache;
+static struct kmem_cache *mmu_page_cache;
+static struct kmem_cache *mmu_page_header_cache;
+
static int is_write_protection(struct kvm_vcpu *vcpu)
{
return vcpu->cr0 & CR0_WP_MASK;
}
static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
- size_t objsize, int min)
+ struct kmem_cache *base_cache, int min,
+ gfp_t gfp_flags)
{
void *obj;
if (cache->nobjs >= min)
return 0;
while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
- obj = kzalloc(objsize, GFP_NOWAIT);
+ obj = kmem_cache_zalloc(base_cache, gfp_flags);
if (!obj)
return -ENOMEM;
cache->objects[cache->nobjs++] = obj;
kfree(mc->objects[--mc->nobjs]);
}
-static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu)
+static int __mmu_topup_memory_caches(struct kvm_vcpu *vcpu, gfp_t gfp_flags)
{
int r;
r = mmu_topup_memory_cache(&vcpu->mmu_pte_chain_cache,
- sizeof(struct kvm_pte_chain), 4);
+ pte_chain_cache, 4, gfp_flags);
if (r)
goto out;
r = mmu_topup_memory_cache(&vcpu->mmu_rmap_desc_cache,
- sizeof(struct kvm_rmap_desc), 1);
+ rmap_desc_cache, 1, gfp_flags);
+ if (r)
+ goto out;
+ r = mmu_topup_memory_cache(&vcpu->mmu_page_cache,
+ mmu_page_cache, 4, gfp_flags);
+ if (r)
+ goto out;
+ r = mmu_topup_memory_cache(&vcpu->mmu_page_header_cache,
+ mmu_page_header_cache, 4, gfp_flags);
out:
return r;
}
+static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu)
+{
+ int r;
+
+ r = __mmu_topup_memory_caches(vcpu, GFP_NOWAIT);
+ if (r < 0) {
+ spin_unlock(&vcpu->kvm->lock);
+ kvm_arch_ops->vcpu_put(vcpu);
+ r = __mmu_topup_memory_caches(vcpu, GFP_KERNEL);
+ kvm_arch_ops->vcpu_load(vcpu);
+ spin_lock(&vcpu->kvm->lock);
+ }
+ return r;
+}
+
static void mmu_free_memory_caches(struct kvm_vcpu *vcpu)
{
mmu_free_memory_cache(&vcpu->mmu_pte_chain_cache);
mmu_free_memory_cache(&vcpu->mmu_rmap_desc_cache);
+ mmu_free_memory_cache(&vcpu->mmu_page_cache);
+ mmu_free_memory_cache(&vcpu->mmu_page_header_cache);
}
static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc,
{
struct kvm *kvm = vcpu->kvm;
struct page *page;
- struct kvm_memory_slot *slot;
struct kvm_rmap_desc *desc;
u64 *spte;
- slot = gfn_to_memslot(kvm, gfn);
- BUG_ON(!slot);
- page = gfn_to_page(slot, gfn);
+ page = gfn_to_page(kvm, gfn);
+ BUG_ON(!page);
while (page_private(page)) {
if (!(page_private(page) & 1))
spte = desc->shadow_ptes[0];
}
BUG_ON(!spte);
- BUG_ON((*spte & PT64_BASE_ADDR_MASK) !=
- page_to_pfn(page) << PAGE_SHIFT);
+ BUG_ON((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT
+ != page_to_pfn(page));
BUG_ON(!(*spte & PT_PRESENT_MASK));
BUG_ON(!(*spte & PT_WRITABLE_MASK));
rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
}
}
-static int is_empty_shadow_page(hpa_t page_hpa)
+#ifdef MMU_DEBUG
+static int is_empty_shadow_page(u64 *spt)
{
u64 *pos;
u64 *end;
- for (pos = __va(page_hpa), end = pos + PAGE_SIZE / sizeof(u64);
- pos != end; pos++)
+ for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
if (*pos != 0) {
printk(KERN_ERR "%s: %p %llx\n", __FUNCTION__,
pos, *pos);
}
return 1;
}
+#endif
-static void kvm_mmu_free_page(struct kvm_vcpu *vcpu, hpa_t page_hpa)
+static void kvm_mmu_free_page(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *page_head)
{
- struct kvm_mmu_page *page_head = page_header(page_hpa);
-
- ASSERT(is_empty_shadow_page(page_hpa));
+ ASSERT(is_empty_shadow_page(page_head->spt));
list_del(&page_head->link);
- page_head->page_hpa = page_hpa;
- list_add(&page_head->link, &vcpu->free_pages);
+ mmu_memory_cache_free(&vcpu->mmu_page_cache, page_head->spt);
+ mmu_memory_cache_free(&vcpu->mmu_page_header_cache, page_head);
++vcpu->kvm->n_free_mmu_pages;
}
{
struct kvm_mmu_page *page;
- if (list_empty(&vcpu->free_pages))
+ if (!vcpu->kvm->n_free_mmu_pages)
return NULL;
- page = list_entry(vcpu->free_pages.next, struct kvm_mmu_page, link);
- list_del(&page->link);
+ page = mmu_memory_cache_alloc(&vcpu->mmu_page_header_cache,
+ sizeof *page);
+ page->spt = mmu_memory_cache_alloc(&vcpu->mmu_page_cache, PAGE_SIZE);
+ set_page_private(virt_to_page(page->spt), (unsigned long)page);
list_add(&page->link, &vcpu->kvm->active_mmu_pages);
- ASSERT(is_empty_shadow_page(page->page_hpa));
+ ASSERT(is_empty_shadow_page(page->spt));
page->slot_bitmap = 0;
- page->global = 1;
page->multimapped = 0;
page->parent_pte = parent_pte;
--vcpu->kvm->n_free_mmu_pages;
gva_t gaddr,
unsigned level,
int metaphysical,
+ unsigned hugepage_access,
u64 *parent_pte)
{
union kvm_mmu_page_role role;
role.glevels = vcpu->mmu.root_level;
role.level = level;
role.metaphysical = metaphysical;
+ role.hugepage_access = hugepage_access;
if (vcpu->mmu.root_level <= PT32_ROOT_LEVEL) {
quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
u64 *pt;
u64 ent;
- pt = __va(page->page_hpa);
+ pt = page->spt;
if (page->role.level == PT_PAGE_TABLE_LEVEL) {
for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
kvm_mmu_page_unlink_children(vcpu, page);
if (!page->root_count) {
hlist_del(&page->hash_link);
- kvm_mmu_free_page(vcpu, page->page_hpa);
- } else {
- list_del(&page->link);
- list_add(&page->link, &vcpu->kvm->active_mmu_pages);
- }
+ kvm_mmu_free_page(vcpu, page);
+ } else
+ list_move(&page->link, &vcpu->kvm->active_mmu_pages);
}
static int kvm_mmu_unprotect_page(struct kvm_vcpu *vcpu, gfn_t gfn)
hpa_t gpa_to_hpa(struct kvm_vcpu *vcpu, gpa_t gpa)
{
- struct kvm_memory_slot *slot;
struct page *page;
ASSERT((gpa & HPA_ERR_MASK) == 0);
- slot = gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT);
- if (!slot)
+ page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+ if (!page)
return gpa | HPA_ERR_MASK;
- page = gfn_to_page(slot, gpa >> PAGE_SHIFT);
return ((hpa_t)page_to_pfn(page) << PAGE_SHIFT)
| (gpa & (PAGE_SIZE-1));
}
return gpa_to_hpa(vcpu, gpa);
}
+struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva)
+{
+ gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, gva);
+
+ if (gpa == UNMAPPED_GVA)
+ return NULL;
+ return pfn_to_page(gpa_to_hpa(vcpu, gpa) >> PAGE_SHIFT);
+}
+
static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
{
}
>> PAGE_SHIFT;
new_table = kvm_mmu_get_page(vcpu, pseudo_gfn,
v, level - 1,
- 1, &table[index]);
+ 1, 0, &table[index]);
if (!new_table) {
pgprintk("nonpaging_map: ENOMEM\n");
return -ENOMEM;
}
- table[index] = new_table->page_hpa | PT_PRESENT_MASK
+ table[index] = __pa(new_table->spt) | PT_PRESENT_MASK
| PT_WRITABLE_MASK | PT_USER_MASK;
}
table_addr = table[index] & PT64_BASE_ADDR_MASK;
for (i = 0; i < 4; ++i) {
hpa_t root = vcpu->mmu.pae_root[i];
- ASSERT(VALID_PAGE(root));
- root &= PT64_BASE_ADDR_MASK;
- page = page_header(root);
- --page->root_count;
+ if (root) {
+ ASSERT(VALID_PAGE(root));
+ root &= PT64_BASE_ADDR_MASK;
+ page = page_header(root);
+ --page->root_count;
+ }
vcpu->mmu.pae_root[i] = INVALID_PAGE;
}
vcpu->mmu.root_hpa = INVALID_PAGE;
ASSERT(!VALID_PAGE(root));
page = kvm_mmu_get_page(vcpu, root_gfn, 0,
- PT64_ROOT_LEVEL, 0, NULL);
- root = page->page_hpa;
+ PT64_ROOT_LEVEL, 0, 0, NULL);
+ root = __pa(page->spt);
++page->root_count;
vcpu->mmu.root_hpa = root;
return;
hpa_t root = vcpu->mmu.pae_root[i];
ASSERT(!VALID_PAGE(root));
- if (vcpu->mmu.root_level == PT32E_ROOT_LEVEL)
+ if (vcpu->mmu.root_level == PT32E_ROOT_LEVEL) {
+ if (!is_present_pte(vcpu->pdptrs[i])) {
+ vcpu->mmu.pae_root[i] = 0;
+ continue;
+ }
root_gfn = vcpu->pdptrs[i] >> PAGE_SHIFT;
- else if (vcpu->mmu.root_level == 0)
+ } else if (vcpu->mmu.root_level == 0)
root_gfn = 0;
page = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
PT32_ROOT_LEVEL, !is_paging(vcpu),
- NULL);
- root = page->page_hpa;
+ 0, NULL);
+ root = __pa(page->spt);
++page->root_count;
vcpu->mmu.pae_root[i] = root | PT_PRESENT_MASK;
}
static void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
{
- ++kvm_stat.tlb_flush;
+ ++vcpu->stat.tlb_flush;
kvm_arch_ops->tlb_flush(vcpu);
}
kvm_arch_ops->set_cr3(vcpu, vcpu->mmu.root_hpa);
}
-static void mark_pagetable_nonglobal(void *shadow_pte)
-{
- page_header(__pa(shadow_pte))->global = 0;
-}
-
static inline void set_pte_common(struct kvm_vcpu *vcpu,
u64 *shadow_pte,
gpa_t gaddr,
*shadow_pte |= access_bits;
- if (!(*shadow_pte & PT_GLOBAL_MASK))
- mark_pagetable_nonglobal(shadow_pte);
-
if (is_error_hpa(paddr)) {
*shadow_pte |= gaddr;
*shadow_pte |= PT_SHADOW_IO_MARK;
ASSERT(vcpu);
ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa));
+ mmu_topup_memory_caches(vcpu);
if (!is_paging(vcpu))
return nonpaging_init_context(vcpu);
else if (is_long_mode(vcpu))
return r;
}
-void kvm_mmu_pre_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes)
+static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *page,
+ u64 *spte)
+{
+ u64 pte;
+ struct kvm_mmu_page *child;
+
+ pte = *spte;
+ if (is_present_pte(pte)) {
+ if (page->role.level == PT_PAGE_TABLE_LEVEL)
+ rmap_remove(vcpu, spte);
+ else {
+ child = page_header(pte & PT64_BASE_ADDR_MASK);
+ mmu_page_remove_parent_pte(vcpu, child, spte);
+ }
+ }
+ *spte = 0;
+}
+
+static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *page,
+ u64 *spte,
+ const void *new, int bytes)
+{
+ if (page->role.level != PT_PAGE_TABLE_LEVEL)
+ return;
+
+ if (page->role.glevels == PT32_ROOT_LEVEL)
+ paging32_update_pte(vcpu, page, spte, new, bytes);
+ else
+ paging64_update_pte(vcpu, page, spte, new, bytes);
+}
+
+void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
+ const u8 *old, const u8 *new, int bytes)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
struct kvm_mmu_page *page;
- struct kvm_mmu_page *child;
struct hlist_node *node, *n;
struct hlist_head *bucket;
unsigned index;
u64 *spte;
- u64 pte;
unsigned offset = offset_in_page(gpa);
unsigned pte_size;
unsigned page_offset;
unsigned misaligned;
+ unsigned quadrant;
int level;
int flooded = 0;
+ int npte;
pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes);
if (gfn == vcpu->last_pt_write_gfn) {
continue;
pte_size = page->role.glevels == PT32_ROOT_LEVEL ? 4 : 8;
misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
+ misaligned |= bytes < 4;
if (misaligned || flooded) {
/*
* Misaligned accesses are too much trouble to fix
}
page_offset = offset;
level = page->role.level;
+ npte = 1;
if (page->role.glevels == PT32_ROOT_LEVEL) {
- page_offset <<= 1; /* 32->64 */
+ 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;
+ npte = 2;
+ }
+ quadrant = page_offset >> PAGE_SHIFT;
page_offset &= ~PAGE_MASK;
+ if (quadrant != page->role.quadrant)
+ continue;
}
- spte = __va(page->page_hpa);
- spte += page_offset / sizeof(*spte);
- pte = *spte;
- if (is_present_pte(pte)) {
- if (level == PT_PAGE_TABLE_LEVEL)
- rmap_remove(vcpu, spte);
- else {
- child = page_header(pte & PT64_BASE_ADDR_MASK);
- mmu_page_remove_parent_pte(vcpu, child, spte);
- }
+ spte = &page->spt[page_offset / sizeof(*spte)];
+ while (npte--) {
+ mmu_pte_write_zap_pte(vcpu, page, spte);
+ mmu_pte_write_new_pte(vcpu, page, spte, new, bytes);
+ ++spte;
}
- *spte = 0;
}
}
-void kvm_mmu_post_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes)
-{
-}
-
int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
{
gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, gva);
struct kvm_mmu_page, link);
kvm_mmu_zap_page(vcpu, page);
}
- while (!list_empty(&vcpu->free_pages)) {
- page = list_entry(vcpu->free_pages.next,
- struct kvm_mmu_page, link);
- list_del(&page->link);
- __free_page(pfn_to_page(page->page_hpa >> PAGE_SHIFT));
- page->page_hpa = INVALID_PAGE;
- }
free_page((unsigned long)vcpu->mmu.pae_root);
}
ASSERT(vcpu);
- for (i = 0; i < KVM_NUM_MMU_PAGES; i++) {
- struct kvm_mmu_page *page_header = &vcpu->page_header_buf[i];
-
- INIT_LIST_HEAD(&page_header->link);
- if ((page = alloc_page(GFP_KERNEL)) == NULL)
- goto error_1;
- set_page_private(page, (unsigned long)page_header);
- page_header->page_hpa = (hpa_t)page_to_pfn(page) << PAGE_SHIFT;
- memset(__va(page_header->page_hpa), 0, PAGE_SIZE);
- list_add(&page_header->link, &vcpu->free_pages);
- ++vcpu->kvm->n_free_mmu_pages;
- }
+ vcpu->kvm->n_free_mmu_pages = KVM_NUM_MMU_PAGES;
/*
* When emulating 32-bit mode, cr3 is only 32 bits even on x86_64.
{
ASSERT(vcpu);
ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa));
- ASSERT(list_empty(&vcpu->free_pages));
return alloc_mmu_pages(vcpu);
}
{
ASSERT(vcpu);
ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa));
- ASSERT(!list_empty(&vcpu->free_pages));
return init_kvm_mmu(vcpu);
}
if (!test_bit(slot, &page->slot_bitmap))
continue;
- pt = __va(page->page_hpa);
+ pt = page->spt;
for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
/* avoid RMW */
if (pt[i] & PT_WRITABLE_MASK) {
}
}
+void kvm_mmu_zap_all(struct kvm_vcpu *vcpu)
+{
+ destroy_kvm_mmu(vcpu);
+
+ while (!list_empty(&vcpu->kvm->active_mmu_pages)) {
+ struct kvm_mmu_page *page;
+
+ page = container_of(vcpu->kvm->active_mmu_pages.next,
+ struct kvm_mmu_page, link);
+ kvm_mmu_zap_page(vcpu, page);
+ }
+
+ mmu_free_memory_caches(vcpu);
+ kvm_arch_ops->tlb_flush(vcpu);
+ init_kvm_mmu(vcpu);
+}
+
+void kvm_mmu_module_exit(void)
+{
+ if (pte_chain_cache)
+ kmem_cache_destroy(pte_chain_cache);
+ if (rmap_desc_cache)
+ kmem_cache_destroy(rmap_desc_cache);
+ if (mmu_page_cache)
+ kmem_cache_destroy(mmu_page_cache);
+ if (mmu_page_header_cache)
+ kmem_cache_destroy(mmu_page_header_cache);
+}
+
+int kvm_mmu_module_init(void)
+{
+ pte_chain_cache = kmem_cache_create("kvm_pte_chain",
+ sizeof(struct kvm_pte_chain),
+ 0, 0, NULL, NULL);
+ if (!pte_chain_cache)
+ goto nomem;
+ rmap_desc_cache = kmem_cache_create("kvm_rmap_desc",
+ sizeof(struct kvm_rmap_desc),
+ 0, 0, NULL, NULL);
+ if (!rmap_desc_cache)
+ goto nomem;
+
+ mmu_page_cache = kmem_cache_create("kvm_mmu_page",
+ PAGE_SIZE,
+ PAGE_SIZE, 0, NULL, NULL);
+ if (!mmu_page_cache)
+ goto nomem;
+
+ mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header",
+ sizeof(struct kvm_mmu_page),
+ 0, 0, NULL, NULL);
+ if (!mmu_page_header_cache)
+ goto nomem;
+
+ return 0;
+
+nomem:
+ kvm_mmu_module_exit();
+ return -ENOMEM;
+}
+
#ifdef AUDIT
static const char *audit_msg;
for (i = 0; i < PT64_ENT_PER_PAGE; ++i, va += va_delta) {
u64 ent = pt[i];
- if (!ent & PT_PRESENT_MASK)
+ if (!(ent & PT_PRESENT_MASK))
continue;
va = canonicalize(va);
static void audit_mappings(struct kvm_vcpu *vcpu)
{
- int i;
+ unsigned i;
if (vcpu->mmu.root_level == 4)
audit_mappings_page(vcpu, vcpu->mmu.root_hpa, 0, 4);
int i;
list_for_each_entry(page, &vcpu->kvm->active_mmu_pages, link) {
- u64 *pt = __va(page->page_hpa);
+ u64 *pt = page->spt;
if (page->role.level != PT_PAGE_TABLE_LEVEL)
continue;
projects / ~andy / linux / blobdiff