* the COPYING file in the top-level directory.
*
*/
+
+#include "vmx.h"
+#include "kvm.h"
+
#include <linux/types.h>
#include <linux/string.h>
-#include <asm/page.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/module.h>
-#include "vmx.h"
-#include "kvm.h"
+#include <asm/page.h>
+#include <asm/cmpxchg.h>
#undef MMU_DEBUG
#define PT32_DIR_PSE36_MASK (((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT)
-#define PT32_PTE_COPY_MASK \
- (PT_PRESENT_MASK | PT_ACCESSED_MASK | PT_DIRTY_MASK | PT_GLOBAL_MASK)
-
-#define PT64_PTE_COPY_MASK (PT64_NX_MASK | PT32_PTE_COPY_MASK)
-
#define PT_FIRST_AVAIL_BITS_SHIFT 9
#define PT64_SECOND_AVAIL_BITS_SHIFT 52
-#define PT_SHADOW_PS_MARK (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
#define PT_SHADOW_IO_MARK (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
-#define PT_SHADOW_WRITABLE_SHIFT (PT_FIRST_AVAIL_BITS_SHIFT + 1)
-#define PT_SHADOW_WRITABLE_MASK (1ULL << PT_SHADOW_WRITABLE_SHIFT)
-
-#define PT_SHADOW_USER_SHIFT (PT_SHADOW_WRITABLE_SHIFT + 1)
-#define PT_SHADOW_USER_MASK (1ULL << (PT_SHADOW_USER_SHIFT))
-
-#define PT_SHADOW_BITS_OFFSET (PT_SHADOW_WRITABLE_SHIFT - PT_WRITABLE_SHIFT)
-
#define VALID_PAGE(x) ((x) != INVALID_PAGE)
#define PT64_LEVEL_BITS 9
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;
+ return vcpu->cr0 & X86_CR0_WP;
}
static int is_cpuid_PSE36(void)
== (PT_WRITABLE_MASK | PT_PRESENT_MASK);
}
+static void set_shadow_pte(u64 *sptep, u64 spte)
+{
+#ifdef CONFIG_X86_64
+ set_64bit((unsigned long *)sptep, spte);
+#else
+ set_64bit((unsigned long long *)sptep, spte);
+#endif
+}
+
static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
struct kmem_cache *base_cache, int min,
gfp_t gfp_flags)
kfree(mc->objects[--mc->nobjs]);
}
+static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
+ int min, gfp_t gfp_flags)
+{
+ struct page *page;
+
+ if (cache->nobjs >= min)
+ return 0;
+ while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
+ page = alloc_page(gfp_flags);
+ if (!page)
+ return -ENOMEM;
+ set_page_private(page, 0);
+ cache->objects[cache->nobjs++] = page_address(page);
+ }
+ return 0;
+}
+
+static void mmu_free_memory_cache_page(struct kvm_mmu_memory_cache *mc)
+{
+ while (mc->nobjs)
+ free_page((unsigned long)mc->objects[--mc->nobjs]);
+}
+
static int __mmu_topup_memory_caches(struct kvm_vcpu *vcpu, gfp_t gfp_flags)
{
int r;
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);
+ r = mmu_topup_memory_cache_page(&vcpu->mmu_page_cache, 4, gfp_flags);
if (r)
goto out;
r = mmu_topup_memory_cache(&vcpu->mmu_page_header_cache,
int r;
r = __mmu_topup_memory_caches(vcpu, GFP_NOWAIT);
+ kvm_mmu_free_some_pages(vcpu);
if (r < 0) {
- spin_unlock(&vcpu->kvm->lock);
- kvm_arch_ops->vcpu_put(vcpu);
+ mutex_unlock(&vcpu->kvm->lock);
r = __mmu_topup_memory_caches(vcpu, GFP_KERNEL);
- kvm_arch_ops->vcpu_load(vcpu);
- spin_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->lock);
}
return r;
}
{
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_page(&vcpu->mmu_page_cache);
mmu_free_memory_cache(&vcpu->mmu_page_header_cache);
}
return p;
}
-static void mmu_memory_cache_free(struct kvm_mmu_memory_cache *mc, void *obj)
-{
- if (mc->nobjs < KVM_NR_MEM_OBJS)
- mc->objects[mc->nobjs++] = obj;
- else
- kfree(obj);
-}
-
static struct kvm_pte_chain *mmu_alloc_pte_chain(struct kvm_vcpu *vcpu)
{
return mmu_memory_cache_alloc(&vcpu->mmu_pte_chain_cache,
sizeof(struct kvm_pte_chain));
}
-static void mmu_free_pte_chain(struct kvm_vcpu *vcpu,
- struct kvm_pte_chain *pc)
+static void mmu_free_pte_chain(struct kvm_pte_chain *pc)
{
- mmu_memory_cache_free(&vcpu->mmu_pte_chain_cache, pc);
+ kfree(pc);
}
static struct kvm_rmap_desc *mmu_alloc_rmap_desc(struct kvm_vcpu *vcpu)
sizeof(struct kvm_rmap_desc));
}
-static void mmu_free_rmap_desc(struct kvm_vcpu *vcpu,
- struct kvm_rmap_desc *rd)
+static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd)
{
- mmu_memory_cache_free(&vcpu->mmu_rmap_desc_cache, rd);
+ kfree(rd);
}
/*
}
}
-static void rmap_desc_remove_entry(struct kvm_vcpu *vcpu,
- struct page *page,
+static void rmap_desc_remove_entry(struct page *page,
struct kvm_rmap_desc *desc,
int i,
struct kvm_rmap_desc *prev_desc)
prev_desc->more = desc->more;
else
set_page_private(page,(unsigned long)desc->more | 1);
- mmu_free_rmap_desc(vcpu, desc);
+ mmu_free_rmap_desc(desc);
}
-static void rmap_remove(struct kvm_vcpu *vcpu, u64 *spte)
+static void rmap_remove(u64 *spte)
{
struct page *page;
struct kvm_rmap_desc *desc;
while (desc) {
for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i)
if (desc->shadow_ptes[i] == spte) {
- rmap_desc_remove_entry(vcpu, page,
+ rmap_desc_remove_entry(page,
desc, i,
prev_desc);
return;
BUG_ON(!(*spte & PT_PRESENT_MASK));
BUG_ON(!(*spte & PT_WRITABLE_MASK));
rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
- rmap_remove(vcpu, spte);
- kvm_arch_ops->tlb_flush(vcpu);
- *spte &= ~(u64)PT_WRITABLE_MASK;
+ rmap_remove(spte);
+ set_shadow_pte(spte, *spte & ~PT_WRITABLE_MASK);
+ kvm_flush_remote_tlbs(vcpu->kvm);
}
}
}
#endif
-static void kvm_mmu_free_page(struct kvm_vcpu *vcpu,
+static void kvm_mmu_free_page(struct kvm *kvm,
struct kvm_mmu_page *page_head)
{
ASSERT(is_empty_shadow_page(page_head->spt));
list_del(&page_head->link);
- 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;
+ __free_page(virt_to_page(page_head->spt));
+ kfree(page_head);
+ ++kvm->n_free_mmu_pages;
}
static unsigned kvm_page_table_hashfn(gfn_t gfn)
pte_chain->parent_ptes[0] = parent_pte;
}
-static void mmu_page_remove_parent_pte(struct kvm_vcpu *vcpu,
- struct kvm_mmu_page *page,
+static void mmu_page_remove_parent_pte(struct kvm_mmu_page *page,
u64 *parent_pte)
{
struct kvm_pte_chain *pte_chain;
pte_chain->parent_ptes[i] = NULL;
if (i == 0) {
hlist_del(&pte_chain->link);
- mmu_free_pte_chain(vcpu, pte_chain);
+ mmu_free_pte_chain(pte_chain);
if (hlist_empty(&page->parent_ptes)) {
page->multimapped = 0;
page->parent_pte = NULL;
return page;
}
-static void kvm_mmu_page_unlink_children(struct kvm_vcpu *vcpu,
+static void kvm_mmu_page_unlink_children(struct kvm *kvm,
struct kvm_mmu_page *page)
{
unsigned i;
if (page->role.level == PT_PAGE_TABLE_LEVEL) {
for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
if (pt[i] & PT_PRESENT_MASK)
- rmap_remove(vcpu, &pt[i]);
+ rmap_remove(&pt[i]);
pt[i] = 0;
}
- kvm_arch_ops->tlb_flush(vcpu);
+ kvm_flush_remote_tlbs(kvm);
return;
}
if (!(ent & PT_PRESENT_MASK))
continue;
ent &= PT64_BASE_ADDR_MASK;
- mmu_page_remove_parent_pte(vcpu, page_header(ent), &pt[i]);
+ mmu_page_remove_parent_pte(page_header(ent), &pt[i]);
}
+ kvm_flush_remote_tlbs(kvm);
}
-static void kvm_mmu_put_page(struct kvm_vcpu *vcpu,
- struct kvm_mmu_page *page,
+static void kvm_mmu_put_page(struct kvm_mmu_page *page,
u64 *parent_pte)
{
- mmu_page_remove_parent_pte(vcpu, page, parent_pte);
+ mmu_page_remove_parent_pte(page, parent_pte);
}
-static void kvm_mmu_zap_page(struct kvm_vcpu *vcpu,
+static void kvm_mmu_zap_page(struct kvm *kvm,
struct kvm_mmu_page *page)
{
u64 *parent_pte;
parent_pte = chain->parent_ptes[0];
}
BUG_ON(!parent_pte);
- kvm_mmu_put_page(vcpu, page, parent_pte);
- *parent_pte = 0;
+ kvm_mmu_put_page(page, parent_pte);
+ set_shadow_pte(parent_pte, 0);
}
- kvm_mmu_page_unlink_children(vcpu, page);
+ kvm_mmu_page_unlink_children(kvm, page);
if (!page->root_count) {
hlist_del(&page->hash_link);
- kvm_mmu_free_page(vcpu, page);
+ kvm_mmu_free_page(kvm, page);
} else
- list_move(&page->link, &vcpu->kvm->active_mmu_pages);
+ list_move(&page->link, &kvm->active_mmu_pages);
}
static int kvm_mmu_unprotect_page(struct kvm_vcpu *vcpu, gfn_t gfn)
if (page->gfn == gfn && !page->role.metaphysical) {
pgprintk("%s: gfn %lx role %x\n", __FUNCTION__, gfn,
page->role.word);
- kvm_mmu_zap_page(vcpu, page);
+ kvm_mmu_zap_page(vcpu->kvm, page);
r = 1;
}
return r;
}
+static void mmu_unshadow(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ struct kvm_mmu_page *page;
+
+ while ((page = kvm_mmu_lookup_page(vcpu, gfn)) != NULL) {
+ pgprintk("%s: zap %lx %x\n",
+ __FUNCTION__, gfn, page->role.word);
+ kvm_mmu_zap_page(vcpu->kvm, page);
+ }
+}
+
static void page_header_update_slot(struct kvm *kvm, void *pte, gpa_t gpa)
{
int slot = memslot_id(kvm, gfn_to_memslot(kvm, gpa >> PAGE_SHIFT));
int i;
struct kvm_mmu_page *page;
+ if (!VALID_PAGE(vcpu->mmu.root_hpa))
+ return;
#ifdef CONFIG_X86_64
if (vcpu->mmu.shadow_root_level == PT64_ROOT_LEVEL) {
hpa_t root = vcpu->mmu.root_hpa;
- ASSERT(VALID_PAGE(root));
page = page_header(root);
--page->root_count;
vcpu->mmu.root_hpa = INVALID_PAGE;
hpa_t root = vcpu->mmu.pae_root[i];
if (root) {
- ASSERT(VALID_PAGE(root));
root &= PT64_BASE_ADDR_MASK;
page = page_header(root);
--page->root_count;
context->free = nonpaging_free;
context->root_level = 0;
context->shadow_root_level = PT32E_ROOT_LEVEL;
- mmu_alloc_roots(vcpu);
- ASSERT(VALID_PAGE(context->root_hpa));
- kvm_arch_ops->set_cr3(vcpu, context->root_hpa);
+ context->root_hpa = INVALID_PAGE;
return 0;
}
{
pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->cr3);
mmu_free_roots(vcpu);
- if (unlikely(vcpu->kvm->n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES))
- kvm_mmu_free_some_pages(vcpu);
- mmu_alloc_roots(vcpu);
- kvm_mmu_flush_tlb(vcpu);
- kvm_arch_ops->set_cr3(vcpu, vcpu->mmu.root_hpa);
}
static void inject_page_fault(struct kvm_vcpu *vcpu,
context->free = paging_free;
context->root_level = level;
context->shadow_root_level = level;
- mmu_alloc_roots(vcpu);
- ASSERT(VALID_PAGE(context->root_hpa));
- kvm_arch_ops->set_cr3(vcpu, context->root_hpa |
- (vcpu->cr3 & (CR3_PCD_MASK | CR3_WPT_MASK)));
+ context->root_hpa = INVALID_PAGE;
return 0;
}
context->free = paging_free;
context->root_level = PT32_ROOT_LEVEL;
context->shadow_root_level = PT32E_ROOT_LEVEL;
- mmu_alloc_roots(vcpu);
- ASSERT(VALID_PAGE(context->root_hpa));
- kvm_arch_ops->set_cr3(vcpu, context->root_hpa |
- (vcpu->cr3 & (CR3_PCD_MASK | CR3_WPT_MASK)));
+ context->root_hpa = INVALID_PAGE;
return 0;
}
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))
}
int kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
+{
+ destroy_kvm_mmu(vcpu);
+ return init_kvm_mmu(vcpu);
+}
+
+int kvm_mmu_load(struct kvm_vcpu *vcpu)
{
int r;
- destroy_kvm_mmu(vcpu);
- r = init_kvm_mmu(vcpu);
- if (r < 0)
- goto out;
+ mutex_lock(&vcpu->kvm->lock);
r = mmu_topup_memory_caches(vcpu);
+ if (r)
+ goto out;
+ mmu_alloc_roots(vcpu);
+ kvm_arch_ops->set_cr3(vcpu, vcpu->mmu.root_hpa);
+ kvm_mmu_flush_tlb(vcpu);
out:
+ mutex_unlock(&vcpu->kvm->lock);
return r;
}
+EXPORT_SYMBOL_GPL(kvm_mmu_load);
+
+void kvm_mmu_unload(struct kvm_vcpu *vcpu)
+{
+ mmu_free_roots(vcpu);
+}
static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *page,
pte = *spte;
if (is_present_pte(pte)) {
if (page->role.level == PT_PAGE_TABLE_LEVEL)
- rmap_remove(vcpu, spte);
+ rmap_remove(spte);
else {
child = page_header(pte & PT64_BASE_ADDR_MASK);
- mmu_page_remove_parent_pte(vcpu, child, spte);
+ mmu_page_remove_parent_pte(child, spte);
}
}
*spte = 0;
+ kvm_flush_remote_tlbs(vcpu->kvm);
}
static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
}
void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
- const u8 *old, const u8 *new, int bytes)
+ const u8 *new, int bytes)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
struct kvm_mmu_page *page;
*/
pgprintk("misaligned: gpa %llx bytes %d role %x\n",
gpa, bytes, page->role.word);
- kvm_mmu_zap_page(vcpu, page);
+ kvm_mmu_zap_page(vcpu->kvm, page);
continue;
}
page_offset = offset;
return kvm_mmu_unprotect_page(vcpu, gpa >> PAGE_SHIFT);
}
-void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
+void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
{
while (vcpu->kvm->n_free_mmu_pages < KVM_REFILL_PAGES) {
struct kvm_mmu_page *page;
page = container_of(vcpu->kvm->active_mmu_pages.prev,
struct kvm_mmu_page, link);
- kvm_mmu_zap_page(vcpu, page);
+ kvm_mmu_zap_page(vcpu->kvm, page);
}
}
-EXPORT_SYMBOL_GPL(kvm_mmu_free_some_pages);
static void free_mmu_pages(struct kvm_vcpu *vcpu)
{
while (!list_empty(&vcpu->kvm->active_mmu_pages)) {
page = container_of(vcpu->kvm->active_mmu_pages.next,
struct kvm_mmu_page, link);
- kvm_mmu_zap_page(vcpu, page);
+ kvm_mmu_zap_page(vcpu->kvm, page);
}
free_page((unsigned long)vcpu->mmu.pae_root);
}
mmu_free_memory_caches(vcpu);
}
-void kvm_mmu_slot_remove_write_access(struct kvm_vcpu *vcpu, int slot)
+void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
{
- struct kvm *kvm = vcpu->kvm;
struct kvm_mmu_page *page;
list_for_each_entry(page, &kvm->active_mmu_pages, link) {
for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
/* avoid RMW */
if (pt[i] & PT_WRITABLE_MASK) {
- rmap_remove(vcpu, &pt[i]);
+ rmap_remove(&pt[i]);
pt[i] &= ~PT_WRITABLE_MASK;
}
}
}
-void kvm_mmu_zap_all(struct kvm_vcpu *vcpu)
+void kvm_mmu_zap_all(struct kvm *kvm)
{
- destroy_kvm_mmu(vcpu);
+ struct kvm_mmu_page *page, *node;
- 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);
- }
+ list_for_each_entry_safe(page, node, &kvm->active_mmu_pages, link)
+ kvm_mmu_zap_page(kvm, page);
- mmu_free_memory_caches(vcpu);
- kvm_arch_ops->tlb_flush(vcpu);
- init_kvm_mmu(vcpu);
+ kvm_flush_remote_tlbs(kvm);
}
void kvm_mmu_module_exit(void)
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);
}
{
pte_chain_cache = kmem_cache_create("kvm_pte_chain",
sizeof(struct kvm_pte_chain),
- 0, 0, NULL, NULL);
+ 0, 0, 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);
+ 0, 0, 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);
+ 0, 0, NULL);
if (!mmu_page_header_cache)
goto nomem;
projects / linux-2.6 / blobdiff