/* [<][>][^][v][top][bottom][index][help] */
DEFINITIONS
This source file includes following definitions.
- gpte_to_gfn
- gpte_to_gfn_pde
/*
* Kernel-based Virtual Machine driver for Linux
*
* This module enables machines with Intel VT-x extensions to run virtual
* machines without emulation or binary translation.
*
* MMU support
*
* Copyright (C) 2006 Qumranet, Inc.
*
* Authors:
* Yaniv Kamay <yaniv@qumranet.com>
* Avi Kivity <avi@qumranet.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
/*
* We need the mmu code to access both 32-bit and 64-bit guest ptes,
* so the code in this file is compiled twice, once per pte size.
*/
#if PTTYPE == 64
#define pt_element_t u64
#define guest_walker guest_walker64
#define FNAME(name) paging##64_##name
#define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
#define PT_DIR_BASE_ADDR_MASK PT64_DIR_BASE_ADDR_MASK
#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
#define CMPXCHG cmpxchg
#else
#define CMPXCHG cmpxchg64
#define PT_MAX_FULL_LEVELS 2
#endif
#elif PTTYPE == 32
#define pt_element_t u32
#define guest_walker guest_walker32
#define FNAME(name) paging##32_##name
#define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK
#define PT_DIR_BASE_ADDR_MASK PT32_DIR_BASE_ADDR_MASK
#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
#define CMPXCHG cmpxchg
#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 ptes[PT_MAX_FULL_LEVELS];
gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
unsigned pt_access;
unsigned pte_access;
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;
}
static bool FNAME(cmpxchg_gpte)(struct kvm *kvm,
gfn_t table_gfn, unsigned index,
pt_element_t orig_pte, pt_element_t new_pte)
{
pt_element_t ret;
pt_element_t *table;
struct page *page;
down_read(¤t->mm->mmap_sem);
page = gfn_to_page(kvm, table_gfn);
up_read(¤t->mm->mmap_sem);
table = kmap_atomic(page, KM_USER0);
ret = CMPXCHG(&table[index], orig_pte, new_pte);
kunmap_atomic(table, KM_USER0);
kvm_release_page_dirty(page);
return (ret != orig_pte);
}
static unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, pt_element_t gpte)
{
unsigned access;
access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
#if PTTYPE == 64
if (is_nx(vcpu))
access &= ~(gpte >> PT64_NX_SHIFT);
#endif
return access;
}
/*
* Fetch a guest pte for a guest virtual address
*/
static int FNAME(walk_addr)(struct guest_walker *walker,
struct kvm_vcpu *vcpu, gva_t addr,
int write_fault, int user_fault, int fetch_fault)
{
pt_element_t pte;
gfn_t table_gfn;
unsigned index, pt_access, pte_access;
gpa_t pte_gpa;
pgprintk("%s: addr %lx\n", __func__, addr);
walk:
walker->level = vcpu->arch.mmu.root_level;
pte = vcpu->arch.cr3;
#if PTTYPE == 64
if (!is_long_mode(vcpu)) {
pte = vcpu->arch.pdptrs[(addr >> 30) & 3];
if (!is_present_pte(pte))
goto not_present;
--walker->level;
}
#endif
ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
(vcpu->arch.cr3 & CR3_NONPAE_RESERVED_BITS) == 0);
pt_access = ACC_ALL;
for (;;) {
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;
walker->pte_gpa[walker->level - 1] = pte_gpa;
pgprintk("%s: table_gfn[%d] %lx\n", __func__,
walker->level - 1, table_gfn);
kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte));
if (!is_present_pte(pte))
goto not_present;
if (write_fault && !is_writeble_pte(pte))
if (user_fault || is_write_protection(vcpu))
goto access_error;
if (user_fault && !(pte & PT_USER_MASK))
goto access_error;
#if PTTYPE == 64
if (fetch_fault && is_nx(vcpu) && (pte & PT64_NX_MASK))
goto access_error;
#endif
if (!(pte & PT_ACCESSED_MASK)) {
mark_page_dirty(vcpu->kvm, table_gfn);
if (FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn,
index, pte, pte|PT_ACCESSED_MASK))
goto walk;
pte |= PT_ACCESSED_MASK;
}
pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
walker->ptes[walker->level - 1] = pte;
if (walker->level == PT_PAGE_TABLE_LEVEL) {
walker->gfn = gpte_to_gfn(pte);
break;
}
if (walker->level == PT_DIRECTORY_LEVEL
&& (pte & PT_PAGE_SIZE_MASK)
&& (PTTYPE == 64 || is_pse(vcpu))) {
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;
}
pt_access = pte_access;
--walker->level;
}
if (write_fault && !is_dirty_pte(pte)) {
bool ret;
mark_page_dirty(vcpu->kvm, table_gfn);
ret = FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, index, pte,
pte|PT_DIRTY_MASK);
if (ret)
goto walk;
pte |= PT_DIRTY_MASK;
kvm_mmu_pte_write(vcpu, pte_gpa, (u8 *)&pte, sizeof(pte));
walker->ptes[walker->level - 1] = pte;
}
walker->pt_access = pt_access;
walker->pte_access = pte_access;
pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
__func__, (u64)pte, pt_access, pte_access);
return 1;
not_present:
walker->error_code = 0;
goto err;
access_error:
walker->error_code = PFERR_PRESENT_MASK;
err:
if (write_fault)
walker->error_code |= PFERR_WRITE_MASK;
if (user_fault)
walker->error_code |= PFERR_USER_MASK;
if (fetch_fault)
walker->error_code |= PFERR_FETCH_MASK;
return 0;
}
static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
u64 *spte, const void *pte)
{
pt_element_t gpte;
unsigned pte_access;
pfn_t pfn;
int largepage = vcpu->arch.update_pte.largepage;
gpte = *(const pt_element_t *)pte;
if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
if (!is_present_pte(gpte))
set_shadow_pte(spte, shadow_notrap_nonpresent_pte);
return;
}
pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
pte_access = page->role.access & FNAME(gpte_access)(vcpu, gpte);
if (gpte_to_gfn(gpte) != vcpu->arch.update_pte.gfn)
return;
pfn = vcpu->arch.update_pte.pfn;
if (is_error_pfn(pfn))
return;
if (mmu_notifier_retry(vcpu, vcpu->arch.update_pte.mmu_seq))
return;
kvm_get_pfn(pfn);
mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
gpte & PT_DIRTY_MASK, NULL, largepage, gpte_to_gfn(gpte),
pfn, true);
}
/*
* 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,
int user_fault, int write_fault, int largepage,
int *ptwrite, pfn_t pfn)
{
hpa_t shadow_addr;
int level;
u64 *shadow_ent;
unsigned access = walker->pt_access;
if (!is_present_pte(walker->ptes[walker->level - 1]))
return NULL;
shadow_addr = vcpu->arch.mmu.root_hpa;
level = vcpu->arch.mmu.shadow_root_level;
if (level == PT32E_ROOT_LEVEL) {
shadow_addr = vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
shadow_addr &= PT64_BASE_ADDR_MASK;
--level;
}
for (; ; level--) {
u32 index = SHADOW_PT_INDEX(addr, level);
struct kvm_mmu_page *shadow_page;
u64 shadow_pte;
int metaphysical;
gfn_t table_gfn;
shadow_ent = ((u64 *)__va(shadow_addr)) + index;
if (level == PT_PAGE_TABLE_LEVEL)
break;
if (largepage && level == PT_DIRECTORY_LEVEL)
break;
if (is_shadow_present_pte(*shadow_ent)
&& !is_large_pte(*shadow_ent)) {
shadow_addr = *shadow_ent & PT64_BASE_ADDR_MASK;
continue;
}
if (is_large_pte(*shadow_ent))
rmap_remove(vcpu->kvm, shadow_ent);
if (level - 1 == PT_PAGE_TABLE_LEVEL
&& walker->level == PT_DIRECTORY_LEVEL) {
metaphysical = 1;
if (!is_dirty_pte(walker->ptes[level - 1]))
access &= ~ACC_WRITE_MASK;
table_gfn = gpte_to_gfn(walker->ptes[level - 1]);
} else {
metaphysical = 0;
table_gfn = walker->table_gfn[level - 2];
}
shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1,
metaphysical, access,
shadow_ent);
if (!metaphysical) {
int r;
pt_element_t curr_pte;
r = kvm_read_guest_atomic(vcpu->kvm,
walker->pte_gpa[level - 2],
&curr_pte, sizeof(curr_pte));
if (r || curr_pte != walker->ptes[level - 2]) {
kvm_release_pfn_clean(pfn);
return NULL;
}
}
shadow_addr = __pa(shadow_page->spt);
shadow_pte = shadow_addr | PT_PRESENT_MASK | PT_ACCESSED_MASK
| PT_WRITABLE_MASK | PT_USER_MASK;
set_shadow_pte(shadow_ent, shadow_pte);
}
mmu_set_spte(vcpu, shadow_ent, access, walker->pte_access & access,
user_fault, write_fault,
walker->ptes[walker->level-1] & PT_DIRTY_MASK,
ptwrite, largepage, walker->gfn, pfn, false);
return shadow_ent;
}
/*
* Page fault handler. There are several causes for a page fault:
* - there is no shadow pte for the guest pte
* - write access through a shadow pte marked read only so that we can set
* the dirty bit
* - write access to a shadow pte marked read only so we can update the page
* dirty bitmap, when userspace requests it
* - mmio access; in this case we will never install a present shadow pte
* - normal guest page fault due to the guest pte marked not present, not
* writable, or not executable
*
* Returns: 1 if we need to emulate the instruction, 0 otherwise, or
* a negative value on error.
*/
static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
u32 error_code)
{
int write_fault = error_code & PFERR_WRITE_MASK;
int user_fault = error_code & PFERR_USER_MASK;
int fetch_fault = error_code & PFERR_FETCH_MASK;
struct guest_walker walker;
u64 *shadow_pte;
int write_pt = 0;
int r;
pfn_t pfn;
int largepage = 0;
unsigned long mmu_seq;
pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
kvm_mmu_audit(vcpu, "pre page fault");
r = mmu_topup_memory_caches(vcpu);
if (r)
return r;
/*
* Look up the shadow pte for the faulting address.
*/
r = FNAME(walk_addr)(&walker, vcpu, addr, write_fault, user_fault,
fetch_fault);
/*
* The page is not mapped by the guest. Let the guest handle it.
*/
if (!r) {
pgprintk("%s: guest page fault\n", __func__);
inject_page_fault(vcpu, addr, walker.error_code);
vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
return 0;
}
down_read(¤t->mm->mmap_sem);
if (walker.level == PT_DIRECTORY_LEVEL) {
gfn_t large_gfn;
large_gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE-1);
if (is_largepage_backed(vcpu, large_gfn)) {
walker.gfn = large_gfn;
largepage = 1;
}
}
mmu_seq = vcpu->kvm->mmu_notifier_seq;
/* implicit mb(), we'll read before PT lock is unlocked */
pfn = gfn_to_pfn(vcpu->kvm, walker.gfn);
up_read(¤t->mm->mmap_sem);
/* mmio */
if (is_error_pfn(pfn)) {
pgprintk("gfn %lx is mmio\n", walker.gfn);
kvm_release_pfn_clean(pfn);
return 1;
}
spin_lock(&vcpu->kvm->mmu_lock);
if (mmu_notifier_retry(vcpu, mmu_seq))
goto out_unlock;
kvm_mmu_free_some_pages(vcpu);
shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
largepage, &write_pt, pfn);
pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __func__,
shadow_pte, *shadow_pte, write_pt);
if (!write_pt)
vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
++vcpu->stat.pf_fixed;
kvm_mmu_audit(vcpu, "post page fault (fixed)");
spin_unlock(&vcpu->kvm->mmu_lock);
return write_pt;
out_unlock:
spin_unlock(&vcpu->kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
return 0;
}
static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
{
struct guest_walker walker;
gpa_t gpa = UNMAPPED_GVA;
int r;
r = FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
if (r) {
gpa = gfn_to_gpa(walker.gfn);
gpa |= vaddr & ~PAGE_MASK;
}
return gpa;
}
static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp)
{
int i, j, offset, r;
pt_element_t pt[256 / sizeof(pt_element_t)];
gpa_t pte_gpa;
if (sp->role.metaphysical
|| (PTTYPE == 32 && sp->role.level > PT_PAGE_TABLE_LEVEL)) {
nonpaging_prefetch_page(vcpu, sp);
return;
}
pte_gpa = gfn_to_gpa(sp->gfn);
if (PTTYPE == 32) {
offset = sp->role.quadrant << PT64_LEVEL_BITS;
pte_gpa += offset * sizeof(pt_element_t);
}
for (i = 0; i < PT64_ENT_PER_PAGE; i += ARRAY_SIZE(pt)) {
r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa, pt, sizeof pt);
pte_gpa += ARRAY_SIZE(pt) * sizeof(pt_element_t);
for (j = 0; j < ARRAY_SIZE(pt); ++j)
if (r || is_present_pte(pt[j]))
sp->spt[i+j] = shadow_trap_nonpresent_pte;
else
sp->spt[i+j] = shadow_notrap_nonpresent_pte;
}
}
#undef pt_element_t
#undef guest_walker
#undef FNAME
#undef PT_BASE_ADDR_MASK
#undef PT_INDEX
#undef SHADOW_PT_INDEX
#undef PT_LEVEL_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
#undef CMPXCHG