#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
#define PT_LEVEL_MASK(level) PT64_LEVEL_MASK(level)
- #define PT_PTE_COPY_MASK PT64_PTE_COPY_MASK
+ #define PT_LEVEL_BITS PT64_LEVEL_BITS
#ifdef CONFIG_X86_64
#define PT_MAX_FULL_LEVELS 4
#else
#define PT_INDEX(addr, level) PT32_INDEX(addr, level)
#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
#define PT_LEVEL_MASK(level) PT32_LEVEL_MASK(level)
- #define PT_PTE_COPY_MASK PT32_PTE_COPY_MASK
+ #define PT_LEVEL_BITS PT32_LEVEL_BITS
#define PT_MAX_FULL_LEVELS 2
#else
#error Invalid PTTYPE value
#endif
+#define gpte_to_gfn FNAME(gpte_to_gfn)
+#define gpte_to_gfn_pde FNAME(gpte_to_gfn_pde)
+
/*
* The guest_walker structure emulates the behavior of the hardware page
* table walker.
struct guest_walker {
int level;
gfn_t table_gfn[PT_MAX_FULL_LEVELS];
- pt_element_t *table;
- pt_element_t *ptep;
+ pt_element_t pte;
pt_element_t inherited_ar;
gfn_t gfn;
u32 error_code;
};
+static gfn_t gpte_to_gfn(pt_element_t gpte)
+{
+ return (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT;
+}
+
+static gfn_t gpte_to_gfn_pde(pt_element_t gpte)
+{
+ return (gpte & PT_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT;
+}
+
/*
* Fetch a guest pte for a guest virtual address
*/
struct kvm_vcpu *vcpu, gva_t addr,
int write_fault, int user_fault, int fetch_fault)
{
- hpa_t hpa;
- struct kvm_memory_slot *slot;
- pt_element_t *ptep;
- pt_element_t root;
+ pt_element_t pte;
gfn_t table_gfn;
+ unsigned index;
+ gpa_t pte_gpa;
pgprintk("%s: addr %lx\n", __FUNCTION__, addr);
walker->level = vcpu->mmu.root_level;
- walker->table = NULL;
- root = vcpu->cr3;
+ pte = vcpu->cr3;
#if PTTYPE == 64
if (!is_long_mode(vcpu)) {
- walker->ptep = &vcpu->pdptrs[(addr >> 30) & 3];
- root = *walker->ptep;
- if (!(root & PT_PRESENT_MASK))
+ pte = vcpu->pdptrs[(addr >> 30) & 3];
+ if (!is_present_pte(pte))
goto not_present;
--walker->level;
}
#endif
- table_gfn = (root & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
- walker->table_gfn[walker->level - 1] = table_gfn;
- pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__,
- walker->level - 1, table_gfn);
- slot = gfn_to_memslot(vcpu->kvm, table_gfn);
- hpa = safe_gpa_to_hpa(vcpu, root & PT64_BASE_ADDR_MASK);
- walker->table = kmap_atomic(pfn_to_page(hpa >> PAGE_SHIFT), KM_USER0);
-
ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
- (vcpu->cr3 & ~(PAGE_MASK | CR3_FLAGS_MASK)) == 0);
+ (vcpu->cr3 & CR3_NONPAE_RESERVED_BITS) == 0);
walker->inherited_ar = PT_USER_MASK | PT_WRITABLE_MASK;
for (;;) {
- int index = PT_INDEX(addr, walker->level);
- hpa_t paddr;
+ index = PT_INDEX(addr, walker->level);
+
+ table_gfn = gpte_to_gfn(pte);
+ pte_gpa = gfn_to_gpa(table_gfn);
+ pte_gpa += index * sizeof(pt_element_t);
+ walker->table_gfn[walker->level - 1] = table_gfn;
+ pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__,
+ walker->level - 1, table_gfn);
- ptep = &walker->table[index];
- ASSERT(((unsigned long)walker->table & PAGE_MASK) ==
- ((unsigned long)ptep & PAGE_MASK));
+ kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte));
- if (!is_present_pte(*ptep))
+ if (!is_present_pte(pte))
goto not_present;
- if (write_fault && !is_writeble_pte(*ptep))
+ if (write_fault && !is_writeble_pte(pte))
if (user_fault || is_write_protection(vcpu))
goto access_error;
- if (user_fault && !(*ptep & PT_USER_MASK))
+ if (user_fault && !(pte & PT_USER_MASK))
goto access_error;
#if PTTYPE == 64
- if (fetch_fault && is_nx(vcpu) && (*ptep & PT64_NX_MASK))
+ if (fetch_fault && is_nx(vcpu) && (pte & PT64_NX_MASK))
goto access_error;
#endif
- if (!(*ptep & PT_ACCESSED_MASK)) {
+ if (!(pte & PT_ACCESSED_MASK)) {
mark_page_dirty(vcpu->kvm, table_gfn);
- *ptep |= PT_ACCESSED_MASK;
+ pte |= PT_ACCESSED_MASK;
+ kvm_write_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte));
}
if (walker->level == PT_PAGE_TABLE_LEVEL) {
- walker->gfn = (*ptep & PT_BASE_ADDR_MASK)
- >> PAGE_SHIFT;
+ walker->gfn = gpte_to_gfn(pte);
break;
}
if (walker->level == PT_DIRECTORY_LEVEL
- && (*ptep & PT_PAGE_SIZE_MASK)
+ && (pte & PT_PAGE_SIZE_MASK)
&& (PTTYPE == 64 || is_pse(vcpu))) {
- walker->gfn = (*ptep & PT_DIR_BASE_ADDR_MASK)
- >> PAGE_SHIFT;
+ walker->gfn = gpte_to_gfn_pde(pte);
walker->gfn += PT_INDEX(addr, PT_PAGE_TABLE_LEVEL);
+ if (PTTYPE == 32 && is_cpuid_PSE36())
+ walker->gfn += pse36_gfn_delta(pte);
break;
}
- walker->inherited_ar &= walker->table[index];
- table_gfn = (*ptep & PT_BASE_ADDR_MASK) >> PAGE_SHIFT;
- paddr = safe_gpa_to_hpa(vcpu, *ptep & PT_BASE_ADDR_MASK);
- kunmap_atomic(walker->table, KM_USER0);
- walker->table = kmap_atomic(pfn_to_page(paddr >> PAGE_SHIFT),
- KM_USER0);
+ walker->inherited_ar &= pte;
--walker->level;
- walker->table_gfn[walker->level - 1 ] = table_gfn;
- pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__,
- walker->level - 1, table_gfn);
}
- walker->ptep = ptep;
- pgprintk("%s: pte %llx\n", __FUNCTION__, (u64)*ptep);
+
+ if (write_fault && !is_dirty_pte(pte)) {
+ mark_page_dirty(vcpu->kvm, table_gfn);
+ pte |= PT_DIRTY_MASK;
+ kvm_write_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte));
+ kvm_mmu_pte_write(vcpu, pte_gpa, (u8 *)&pte, sizeof(pte));
+ }
+
+ walker->pte = pte;
+ pgprintk("%s: pte %llx\n", __FUNCTION__, (u64)pte);
return 1;
not_present:
return 0;
}
-static void FNAME(release_walker)(struct guest_walker *walker)
-{
- if (walker->table)
- kunmap_atomic(walker->table, KM_USER0);
-}
-
-static void FNAME(mark_pagetable_dirty)(struct kvm *kvm,
- struct guest_walker *walker)
-{
- mark_page_dirty(kvm, walker->table_gfn[walker->level - 1]);
-}
-
-static void FNAME(set_pte_common)(struct kvm_vcpu *vcpu,
- u64 *shadow_pte,
- gpa_t gaddr,
- pt_element_t *gpte,
- u64 access_bits,
- int user_fault,
- int write_fault,
- int *ptwrite,
- struct guest_walker *walker,
- gfn_t gfn)
+static void FNAME(set_pte)(struct kvm_vcpu *vcpu, pt_element_t gpte,
+ u64 *shadow_pte, u64 access_bits,
+ int user_fault, int write_fault,
+ int *ptwrite, struct guest_walker *walker,
+ gfn_t gfn)
{
- hpa_t paddr;
- int dirty = *gpte & PT_DIRTY_MASK;
+ int dirty = gpte & PT_DIRTY_MASK;
+ u64 spte;
int was_rmapped = is_rmap_pte(*shadow_pte);
+ struct page *page;
pgprintk("%s: spte %llx gpte %llx access %llx write_fault %d"
" user_fault %d gfn %lx\n",
- __FUNCTION__, *shadow_pte, (u64)*gpte, access_bits,
+ __FUNCTION__, *shadow_pte, (u64)gpte, access_bits,
write_fault, user_fault, gfn);
- if (write_fault && !dirty) {
- *gpte |= PT_DIRTY_MASK;
- dirty = 1;
- FNAME(mark_pagetable_dirty)(vcpu->kvm, walker);
- }
-
- *shadow_pte |= *gpte & PT_PTE_COPY_MASK;
- *shadow_pte |= access_bits << PT_SHADOW_BITS_OFFSET;
+ access_bits &= gpte;
+ /*
+ * We don't set the accessed bit, since we sometimes want to see
+ * whether the guest actually used the pte (in order to detect
+ * demand paging).
+ */
+ spte = PT_PRESENT_MASK | PT_DIRTY_MASK;
+ spte |= gpte & PT64_NX_MASK;
if (!dirty)
access_bits &= ~PT_WRITABLE_MASK;
- paddr = gpa_to_hpa(vcpu, gaddr & PT64_BASE_ADDR_MASK);
+ page = gfn_to_page(vcpu->kvm, gfn);
- *shadow_pte |= PT_PRESENT_MASK;
+ spte |= PT_PRESENT_MASK;
if (access_bits & PT_USER_MASK)
- *shadow_pte |= PT_USER_MASK;
+ spte |= PT_USER_MASK;
- if (is_error_hpa(paddr)) {
- *shadow_pte |= gaddr;
- *shadow_pte |= PT_SHADOW_IO_MARK;
- *shadow_pte &= ~PT_PRESENT_MASK;
+ if (is_error_page(page)) {
+ set_shadow_pte(shadow_pte,
+ shadow_trap_nonpresent_pte | PT_SHADOW_IO_MARK);
+ kvm_release_page_clean(page);
return;
}
- *shadow_pte |= paddr;
-
- if (!write_fault && (*shadow_pte & PT_SHADOW_USER_MASK) &&
- !(*shadow_pte & PT_USER_MASK)) {
- /*
- * If supervisor write protect is disabled, we shadow kernel
- * pages as user pages so we can trap the write access.
- */
- *shadow_pte |= PT_USER_MASK;
- *shadow_pte &= ~PT_WRITABLE_MASK;
- access_bits &= ~PT_WRITABLE_MASK;
- }
+ spte |= page_to_phys(page);
if ((access_bits & PT_WRITABLE_MASK)
|| (write_fault && !is_write_protection(vcpu) && !user_fault)) {
struct kvm_mmu_page *shadow;
- *shadow_pte |= PT_WRITABLE_MASK;
+ spte |= PT_WRITABLE_MASK;
if (user_fault) {
- mmu_unshadow(vcpu, gfn);
+ mmu_unshadow(vcpu->kvm, gfn);
goto unshadowed;
}
- shadow = kvm_mmu_lookup_page(vcpu, gfn);
+ shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
if (shadow) {
pgprintk("%s: found shadow page for %lx, marking ro\n",
__FUNCTION__, gfn);
access_bits &= ~PT_WRITABLE_MASK;
- if (is_writeble_pte(*shadow_pte)) {
- *shadow_pte &= ~PT_WRITABLE_MASK;
- kvm_arch_ops->tlb_flush(vcpu);
+ if (is_writeble_pte(spte)) {
+ spte &= ~PT_WRITABLE_MASK;
+ kvm_x86_ops->tlb_flush(vcpu);
}
if (write_fault)
*ptwrite = 1;
unshadowed:
if (access_bits & PT_WRITABLE_MASK)
- mark_page_dirty(vcpu->kvm, gaddr >> PAGE_SHIFT);
-
- page_header_update_slot(vcpu->kvm, shadow_pte, gaddr);
- if (!was_rmapped)
- rmap_add(vcpu, shadow_pte);
-}
-
-static void FNAME(set_pte)(struct kvm_vcpu *vcpu, pt_element_t *gpte,
- u64 *shadow_pte, u64 access_bits,
- int user_fault, int write_fault, int *ptwrite,
- struct guest_walker *walker, gfn_t gfn)
-{
- access_bits &= *gpte;
- FNAME(set_pte_common)(vcpu, shadow_pte, *gpte & PT_BASE_ADDR_MASK,
- gpte, access_bits, user_fault, write_fault,
- ptwrite, walker, gfn);
+ mark_page_dirty(vcpu->kvm, gfn);
+
+ pgprintk("%s: setting spte %llx\n", __FUNCTION__, spte);
+ set_shadow_pte(shadow_pte, spte);
+ page_header_update_slot(vcpu->kvm, shadow_pte, gfn);
+ if (!was_rmapped) {
+ rmap_add(vcpu, shadow_pte, gfn);
+ if (!is_rmap_pte(*shadow_pte))
+ kvm_release_page_clean(page);
+ }
+ else
+ kvm_release_page_clean(page);
+ if (!ptwrite || !*ptwrite)
+ vcpu->last_pte_updated = shadow_pte;
}
static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
- u64 *spte, const void *pte, int bytes)
+ u64 *spte, const void *pte, int bytes,
+ int offset_in_pte)
{
pt_element_t gpte;
- if (bytes < sizeof(pt_element_t))
- return;
gpte = *(const pt_element_t *)pte;
- if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK))
+ if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
+ if (!offset_in_pte && !is_present_pte(gpte))
+ set_shadow_pte(spte, shadow_notrap_nonpresent_pte);
+ return;
+ }
+ if (bytes < sizeof(pt_element_t))
return;
pgprintk("%s: gpte %llx spte %p\n", __FUNCTION__, (u64)gpte, spte);
- FNAME(set_pte)(vcpu, &gpte, spte, PT_USER_MASK | PT_WRITABLE_MASK, 0,
- 0, NULL, NULL,
- (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT);
-}
-
-static void FNAME(set_pde)(struct kvm_vcpu *vcpu, pt_element_t *gpde,
- u64 *shadow_pte, u64 access_bits,
- int user_fault, int write_fault, int *ptwrite,
- struct guest_walker *walker, gfn_t gfn)
-{
- gpa_t gaddr;
-
- access_bits &= *gpde;
- gaddr = (gpa_t)gfn << PAGE_SHIFT;
- if (PTTYPE == 32 && is_cpuid_PSE36())
- gaddr |= (*gpde & PT32_DIR_PSE36_MASK) <<
- (32 - PT32_DIR_PSE36_SHIFT);
- FNAME(set_pte_common)(vcpu, shadow_pte, gaddr,
- gpde, access_bits, user_fault, write_fault,
- ptwrite, walker, gfn);
+ FNAME(set_pte)(vcpu, gpte, spte, PT_USER_MASK | PT_WRITABLE_MASK, 0,
+ 0, NULL, NULL, gpte_to_gfn(gpte));
}
/*
int level;
u64 *shadow_ent;
u64 *prev_shadow_ent = NULL;
- pt_element_t *guest_ent = walker->ptep;
- if (!is_present_pte(*guest_ent))
+ if (!is_present_pte(walker->pte))
return NULL;
shadow_addr = vcpu->mmu.root_hpa;
unsigned hugepage_access = 0;
shadow_ent = ((u64 *)__va(shadow_addr)) + index;
- if (is_present_pte(*shadow_ent) || is_io_pte(*shadow_ent)) {
+ if (is_shadow_present_pte(*shadow_ent)) {
if (level == PT_PAGE_TABLE_LEVEL)
break;
shadow_addr = *shadow_ent & PT64_BASE_ADDR_MASK;
if (level - 1 == PT_PAGE_TABLE_LEVEL
&& walker->level == PT_DIRECTORY_LEVEL) {
metaphysical = 1;
- hugepage_access = *guest_ent;
+ hugepage_access = walker->pte;
hugepage_access &= PT_USER_MASK | PT_WRITABLE_MASK;
+ if (!is_dirty_pte(walker->pte))
+ hugepage_access &= ~PT_WRITABLE_MASK;
hugepage_access >>= PT_WRITABLE_SHIFT;
- table_gfn = (*guest_ent & PT_BASE_ADDR_MASK)
- >> PAGE_SHIFT;
+ if (walker->pte & PT64_NX_MASK)
+ hugepage_access |= (1 << 2);
+ table_gfn = gpte_to_gfn(walker->pte);
} else {
metaphysical = 0;
table_gfn = walker->table_gfn[level - 2];
prev_shadow_ent = shadow_ent;
}
- if (walker->level == PT_DIRECTORY_LEVEL) {
- if (prev_shadow_ent)
- *prev_shadow_ent |= PT_SHADOW_PS_MARK;
- FNAME(set_pde)(vcpu, guest_ent, shadow_ent,
- walker->inherited_ar, user_fault, write_fault,
- ptwrite, walker, walker->gfn);
- } else {
- ASSERT(walker->level == PT_PAGE_TABLE_LEVEL);
- FNAME(set_pte)(vcpu, guest_ent, shadow_ent,
- walker->inherited_ar, user_fault, write_fault,
- ptwrite, walker, walker->gfn);
- }
+ FNAME(set_pte)(vcpu, walker->pte, shadow_ent,
+ walker->inherited_ar, user_fault, write_fault,
+ ptwrite, walker, walker->gfn);
+
return shadow_ent;
}
if (!r) {
pgprintk("%s: guest page fault\n", __FUNCTION__);
inject_page_fault(vcpu, addr, walker.error_code);
- FNAME(release_walker)(&walker);
vcpu->last_pt_write_count = 0; /* reset fork detector */
return 0;
}
pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __FUNCTION__,
shadow_pte, *shadow_pte, write_pt);
- FNAME(release_walker)(&walker);
-
if (!write_pt)
vcpu->last_pt_write_count = 0; /* reset fork detector */
r = FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
if (r) {
- gpa = (gpa_t)walker.gfn << PAGE_SHIFT;
+ gpa = gfn_to_gpa(walker.gfn);
gpa |= vaddr & ~PAGE_MASK;
}
- FNAME(release_walker)(&walker);
return gpa;
}
+static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *sp)
+{
+ int i, offset = 0;
+ pt_element_t *gpt;
+ struct page *page;
+
+ if (sp->role.metaphysical
+ || (PTTYPE == 32 && sp->role.level > PT_PAGE_TABLE_LEVEL)) {
+ nonpaging_prefetch_page(vcpu, sp);
+ return;
+ }
+
+ if (PTTYPE == 32)
+ offset = sp->role.quadrant << PT64_LEVEL_BITS;
+ page = gfn_to_page(vcpu->kvm, sp->gfn);
+ gpt = kmap_atomic(page, KM_USER0);
+ for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
+ if (is_present_pte(gpt[offset + i]))
+ sp->spt[i] = shadow_trap_nonpresent_pte;
+ else
+ sp->spt[i] = shadow_notrap_nonpresent_pte;
+ kunmap_atomic(gpt, KM_USER0);
+ kvm_release_page_clean(page);
+}
+
#undef pt_element_t
#undef guest_walker
#undef FNAME
#undef PT_INDEX
#undef SHADOW_PT_INDEX
#undef PT_LEVEL_MASK
-#undef PT_PTE_COPY_MASK
-#undef PT_NON_PTE_COPY_MASK
#undef PT_DIR_BASE_ADDR_MASK
+#undef PT_LEVEL_BITS
#undef PT_MAX_FULL_LEVELS
+#undef gpte_to_gfn
+#undef gpte_to_gfn_pde
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff