goto access_error;
#endif
- if (!(*ptep & PT_ACCESSED_MASK))
- *ptep |= PT_ACCESSED_MASK; /* avoid rmw */
+ if (!(*ptep & PT_ACCESSED_MASK)) {
+ mark_page_dirty(vcpu->kvm, table_gfn);
+ *ptep |= PT_ACCESSED_MASK;
+ }
if (walker->level == PT_PAGE_TABLE_LEVEL) {
walker->gfn = (*ptep & PT_BASE_ADDR_MASK)
break;
}
- if (walker->level != 3 || is_long_mode(vcpu))
- walker->inherited_ar &= walker->table[index];
+ 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);
kunmap_atomic(walker->table, KM_USER0);
}
-static void FNAME(set_pte)(struct kvm_vcpu *vcpu, u64 guest_pte,
- u64 *shadow_pte, u64 access_bits, gfn_t gfn)
+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 write_fault,
+ gfn_t gfn)
+{
+ hpa_t paddr;
+ int dirty = *gpte & PT_DIRTY_MASK;
+
+ *shadow_pte |= access_bits << PT_SHADOW_BITS_OFFSET;
+ if (!dirty)
+ access_bits &= ~PT_WRITABLE_MASK;
+
+ paddr = gpa_to_hpa(vcpu, gaddr & PT64_BASE_ADDR_MASK);
+
+ *shadow_pte |= access_bits;
+
+ if (is_error_hpa(paddr)) {
+ *shadow_pte |= gaddr;
+ *shadow_pte |= PT_SHADOW_IO_MARK;
+ *shadow_pte &= ~PT_PRESENT_MASK;
+ 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;
+ }
+
+ if (access_bits & PT_WRITABLE_MASK) {
+ struct kvm_mmu_page *shadow;
+
+ shadow = kvm_mmu_lookup_page(vcpu, 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 (access_bits & PT_WRITABLE_MASK)
+ mark_page_dirty(vcpu->kvm, gaddr >> PAGE_SHIFT);
+
+ page_header_update_slot(vcpu->kvm, shadow_pte, gaddr);
+ 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 write_fault, gfn_t gfn)
{
ASSERT(*shadow_pte == 0);
- access_bits &= guest_pte;
- *shadow_pte = (guest_pte & PT_PTE_COPY_MASK);
- set_pte_common(vcpu, shadow_pte, guest_pte & PT_BASE_ADDR_MASK,
- guest_pte & PT_DIRTY_MASK, access_bits, gfn);
+ access_bits &= *gpte;
+ *shadow_pte = (*gpte & PT_PTE_COPY_MASK);
+ FNAME(set_pte_common)(vcpu, shadow_pte, *gpte & PT_BASE_ADDR_MASK,
+ gpte, access_bits, write_fault, gfn);
+}
+
+static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
+ u64 *spte, const void *pte, int bytes)
+{
+ 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))
+ 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,
+ (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT);
}
-static void FNAME(set_pde)(struct kvm_vcpu *vcpu, u64 guest_pde,
- u64 *shadow_pte, u64 access_bits, gfn_t gfn)
+static void FNAME(set_pde)(struct kvm_vcpu *vcpu, pt_element_t *gpde,
+ u64 *shadow_pte, u64 access_bits, int write_fault,
+ gfn_t gfn)
{
gpa_t gaddr;
ASSERT(*shadow_pte == 0);
- access_bits &= guest_pde;
+ access_bits &= *gpde;
gaddr = (gpa_t)gfn << PAGE_SHIFT;
if (PTTYPE == 32 && is_cpuid_PSE36())
- gaddr |= (guest_pde & PT32_DIR_PSE36_MASK) <<
+ gaddr |= (*gpde & PT32_DIR_PSE36_MASK) <<
(32 - PT32_DIR_PSE36_SHIFT);
- *shadow_pte = guest_pde & PT_PTE_COPY_MASK;
- set_pte_common(vcpu, shadow_pte, gaddr,
- guest_pde & PT_DIRTY_MASK, access_bits, gfn);
+ *shadow_pte = *gpde & PT_PTE_COPY_MASK;
+ FNAME(set_pte_common)(vcpu, shadow_pte, gaddr,
+ gpde, access_bits, write_fault, gfn);
}
/*
* Fetch a shadow pte for a specific level in the paging hierarchy.
*/
static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
- struct guest_walker *walker)
+ struct guest_walker *walker, int write_fault)
{
hpa_t shadow_addr;
int level;
+ u64 *shadow_ent;
u64 *prev_shadow_ent = NULL;
pt_element_t *guest_ent = walker->ptep;
for (; ; level--) {
u32 index = SHADOW_PT_INDEX(addr, level);
- u64 *shadow_ent = ((u64 *)__va(shadow_addr)) + index;
struct kvm_mmu_page *shadow_page;
u64 shadow_pte;
int metaphysical;
gfn_t table_gfn;
+ unsigned hugepage_access = 0;
+ shadow_ent = ((u64 *)__va(shadow_addr)) + index;
if (is_present_pte(*shadow_ent) || is_io_pte(*shadow_ent)) {
if (level == PT_PAGE_TABLE_LEVEL)
return shadow_ent;
continue;
}
- if (level == PT_PAGE_TABLE_LEVEL) {
-
- 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,
- walker->gfn);
- } else {
- ASSERT(walker->level == PT_PAGE_TABLE_LEVEL);
- FNAME(set_pte)(vcpu, *guest_ent, shadow_ent,
- walker->inherited_ar,
- walker->gfn);
- }
- return shadow_ent;
- }
+ if (level == PT_PAGE_TABLE_LEVEL)
+ break;
if (level - 1 == PT_PAGE_TABLE_LEVEL
&& walker->level == PT_DIRECTORY_LEVEL) {
metaphysical = 1;
+ hugepage_access = *guest_ent;
+ hugepage_access &= PT_USER_MASK | PT_WRITABLE_MASK;
+ hugepage_access >>= PT_WRITABLE_SHIFT;
table_gfn = (*guest_ent & PT_BASE_ADDR_MASK)
>> PAGE_SHIFT;
} else {
table_gfn = walker->table_gfn[level - 2];
}
shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1,
- metaphysical, shadow_ent);
- shadow_addr = shadow_page->page_hpa;
+ metaphysical, hugepage_access,
+ shadow_ent);
+ shadow_addr = __pa(shadow_page->spt);
shadow_pte = shadow_addr | PT_PRESENT_MASK | PT_ACCESSED_MASK
| PT_WRITABLE_MASK | PT_USER_MASK;
*shadow_ent = shadow_pte;
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, write_fault, walker->gfn);
+ } else {
+ ASSERT(walker->level == PT_PAGE_TABLE_LEVEL);
+ FNAME(set_pte)(vcpu, guest_ent, shadow_ent,
+ walker->inherited_ar,
+ write_fault, walker->gfn);
+ }
+ return shadow_ent;
}
/*
} else if (kvm_mmu_lookup_page(vcpu, gfn)) {
pgprintk("%s: found shadow page for %lx, marking ro\n",
__FUNCTION__, gfn);
+ mark_page_dirty(vcpu->kvm, gfn);
+ FNAME(mark_pagetable_dirty)(vcpu->kvm, walker);
*guest_ent |= PT_DIRTY_MASK;
*write_pt = 1;
return 0;
}
mark_page_dirty(vcpu->kvm, gfn);
*shadow_ent |= PT_WRITABLE_MASK;
+ FNAME(mark_pagetable_dirty)(vcpu->kvm, walker);
*guest_ent |= PT_DIRTY_MASK;
rmap_add(vcpu, shadow_ent);
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;
}
- shadow_pte = FNAME(fetch)(vcpu, addr, &walker);
+ shadow_pte = FNAME(fetch)(vcpu, addr, &walker, write_fault);
pgprintk("%s: shadow pte %p %llx\n", __FUNCTION__,
shadow_pte, *shadow_pte);
if (write_fault)
fixed = FNAME(fix_write_pf)(vcpu, shadow_pte, &walker, addr,
user_fault, &write_pt);
- else
- fixed = fix_read_pf(shadow_pte);
pgprintk("%s: updated shadow pte %p %llx\n", __FUNCTION__,
shadow_pte, *shadow_pte);
FNAME(release_walker)(&walker);
+ if (!write_pt)
+ vcpu->last_pt_write_count = 0; /* reset fork detector */
+
/*
* mmio: emulate if accessible, otherwise its a guest fault.
*/
- if (is_io_pte(*shadow_pte)) {
+ if (is_io_pte(*shadow_pte))
return 1;
- }
- ++kvm_stat.pf_fixed;
+ ++vcpu->stat.pf_fixed;
kvm_mmu_audit(vcpu, "post page fault (fixed)");
return write_pt;
static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
{
struct guest_walker walker;
- pt_element_t guest_pte;
- gpa_t gpa;
-
- FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
- guest_pte = *walker.ptep;
- FNAME(release_walker)(&walker);
-
- if (!is_present_pte(guest_pte))
- return UNMAPPED_GVA;
-
- if (walker.level == PT_DIRECTORY_LEVEL) {
- ASSERT((guest_pte & PT_PAGE_SIZE_MASK));
- ASSERT(PTTYPE == 64 || is_pse(vcpu));
+ gpa_t gpa = UNMAPPED_GVA;
+ int r;
- gpa = (guest_pte & PT_DIR_BASE_ADDR_MASK) | (vaddr &
- (PT_LEVEL_MASK(PT_PAGE_TABLE_LEVEL) | ~PAGE_MASK));
+ r = FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
- if (PTTYPE == 32 && is_cpuid_PSE36())
- gpa |= (guest_pte & PT32_DIR_PSE36_MASK) <<
- (32 - PT32_DIR_PSE36_SHIFT);
- } else {
- gpa = (guest_pte & PT_BASE_ADDR_MASK);
- gpa |= (vaddr & ~PAGE_MASK);
+ if (r) {
+ gpa = (gpa_t)walker.gfn << PAGE_SHIFT;
+ gpa |= vaddr & ~PAGE_MASK;
}
+ FNAME(release_walker)(&walker);
return gpa;
}