#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_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_LEVEL_BITS PT32_LEVEL_BITS
#define PT_MAX_FULL_LEVELS 2
#else
#error Invalid PTTYPE value
int level;
gfn_t table_gfn[PT_MAX_FULL_LEVELS];
pt_element_t *table;
+ pt_element_t pte;
pt_element_t *ptep;
+ struct page *page;
+ int index;
pt_element_t inherited_ar;
gfn_t gfn;
u32 error_code;
pgprintk("%s: addr %lx\n", __FUNCTION__, addr);
walker->level = vcpu->mmu.root_level;
walker->table = NULL;
+ walker->page = NULL;
+ walker->ptep = NULL;
root = vcpu->cr3;
#if PTTYPE == 64
if (!is_long_mode(vcpu)) {
walker->ptep = &vcpu->pdptrs[(addr >> 30) & 3];
root = *walker->ptep;
+ walker->pte = root;
if (!(root & PT_PRESENT_MASK))
goto not_present;
--walker->level;
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);
+ walker->page = pfn_to_page(hpa >> PAGE_SHIFT);
+ walker->table = kmap_atomic(walker->page, 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;
hpa_t paddr;
ptep = &walker->table[index];
+ walker->index = index;
ASSERT(((unsigned long)walker->table & PAGE_MASK) ==
((unsigned long)ptep & PAGE_MASK));
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);
+ paddr = safe_gpa_to_hpa(vcpu, table_gfn << PAGE_SHIFT);
+ walker->page = pfn_to_page(paddr >> PAGE_SHIFT);
+ walker->table = kmap_atomic(walker->page, KM_USER0);
--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;
+ walker->pte = *ptep;
+ if (walker->page)
+ walker->ptep = NULL;
+ if (walker->table)
+ kunmap_atomic(walker->table, KM_USER0);
pgprintk("%s: pte %llx\n", __FUNCTION__, (u64)*ptep);
return 1;
walker->error_code |= PFERR_USER_MASK;
if (fetch_fault)
walker->error_code |= PFERR_FETCH_MASK;
- return 0;
-}
-
-static void FNAME(release_walker)(struct guest_walker *walker)
-{
if (walker->table)
kunmap_atomic(walker->table, KM_USER0);
+ return 0;
}
static void FNAME(mark_pagetable_dirty)(struct kvm *kvm,
static void FNAME(set_pte_common)(struct kvm_vcpu *vcpu,
u64 *shadow_pte,
gpa_t gaddr,
- pt_element_t *gpte,
+ pt_element_t gpte,
u64 access_bits,
int user_fault,
int write_fault,
gfn_t gfn)
{
hpa_t paddr;
- int dirty = *gpte & PT_DIRTY_MASK;
- u64 spte = *shadow_pte;
- int was_rmapped = is_rmap_pte(spte);
+ int dirty = gpte & PT_DIRTY_MASK;
+ u64 spte;
+ int was_rmapped = is_rmap_pte(*shadow_pte);
pgprintk("%s: spte %llx gpte %llx access %llx write_fault %d"
" user_fault %d gfn %lx\n",
- __FUNCTION__, spte, (u64)*gpte, access_bits,
+ __FUNCTION__, *shadow_pte, (u64)gpte, access_bits,
write_fault, user_fault, gfn);
if (write_fault && !dirty) {
- *gpte |= PT_DIRTY_MASK;
+ pt_element_t *guest_ent, *tmp = NULL;
+
+ if (walker->ptep)
+ guest_ent = walker->ptep;
+ else {
+ tmp = kmap_atomic(walker->page, KM_USER0);
+ guest_ent = &tmp[walker->index];
+ }
+
+ *guest_ent |= PT_DIRTY_MASK;
+ if (!walker->ptep)
+ kunmap_atomic(tmp, KM_USER0);
dirty = 1;
FNAME(mark_pagetable_dirty)(vcpu->kvm, walker);
}
- spte |= PT_PRESENT_MASK | PT_ACCESSED_MASK | PT_DIRTY_MASK;
- spte |= *gpte & PT64_NX_MASK;
+ /*
+ * 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;
spte |= PT_USER_MASK;
if (is_error_hpa(paddr)) {
- spte |= gaddr;
- spte |= PT_SHADOW_IO_MARK;
- spte &= ~PT_PRESENT_MASK;
- set_shadow_pte(shadow_pte, spte);
+ set_shadow_pte(shadow_pte,
+ shadow_trap_nonpresent_pte | PT_SHADOW_IO_MARK);
return;
}
access_bits &= ~PT_WRITABLE_MASK;
if (is_writeble_pte(spte)) {
spte &= ~PT_WRITABLE_MASK;
- kvm_arch_ops->tlb_flush(vcpu);
+ kvm_x86_ops->tlb_flush(vcpu);
}
if (write_fault)
*ptwrite = 1;
if (access_bits & PT_WRITABLE_MASK)
mark_page_dirty(vcpu->kvm, gaddr >> PAGE_SHIFT);
+ pgprintk("%s: setting spte %llx\n", __FUNCTION__, spte);
set_shadow_pte(shadow_pte, spte);
page_header_update_slot(vcpu->kvm, shadow_pte, gaddr);
if (!was_rmapped)
rmap_add(vcpu, shadow_pte);
+ if (!ptwrite || !*ptwrite)
+ vcpu->last_pte_updated = shadow_pte;
}
-static void FNAME(set_pte)(struct kvm_vcpu *vcpu, pt_element_t *gpte,
+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,
+ 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);
}
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,
+ 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,
+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;
+ access_bits &= gpde;
gaddr = (gpa_t)gfn << PAGE_SHIFT;
if (PTTYPE == 32 && is_cpuid_PSE36())
- gaddr |= (*gpde & PT32_DIR_PSE36_MASK) <<
+ 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,
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 (walker->pte & PT64_NX_MASK)
+ hugepage_access |= (1 << 2);
hugepage_access >>= PT_WRITABLE_SHIFT;
- table_gfn = (*guest_ent & PT_BASE_ADDR_MASK)
+ table_gfn = (walker->pte & PT_BASE_ADDR_MASK)
>> PAGE_SHIFT;
} else {
metaphysical = 0;
}
if (walker->level == PT_DIRECTORY_LEVEL) {
- FNAME(set_pde)(vcpu, guest_ent, shadow_ent,
+ FNAME(set_pde)(vcpu, walker->pte, 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,
+ FNAME(set_pte)(vcpu, walker->pte, shadow_ent,
walker->inherited_ar, user_fault, write_fault,
ptwrite, walker, walker->gfn);
}
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 */
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;
+ pt_element_t *gpt;
+
+ if (sp->role.metaphysical || PTTYPE == 32) {
+ nonpaging_prefetch_page(vcpu, sp);
+ return;
+ }
+
+ gpt = kmap_atomic(gfn_to_page(vcpu->kvm, sp->gfn), KM_USER0);
+ for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
+ if (is_present_pte(gpt[i]))
+ sp->spt[i] = shadow_trap_nonpresent_pte;
+ else
+ sp->spt[i] = shadow_notrap_nonpresent_pte;
+ kunmap_atomic(gpt, KM_USER0);
+}
+
#undef pt_element_t
#undef guest_walker
#undef FNAME
#undef SHADOW_PT_INDEX
#undef PT_LEVEL_MASK
#undef PT_DIR_BASE_ADDR_MASK
+#undef PT_LEVEL_BITS
#undef PT_MAX_FULL_LEVELS
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff