void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd)
{
pmd_t orig = *pmdp;
*pmdp = pmd;
if (mm == &init_mm)
return;
if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
/*
* Note that this routine only sets pmds for THP pages.
* Hugetlb pages are handled elsewhere. We need to check
* for huge zero page. Huge zero pages are like hugetlb
* pages in that there is no RSS, but there is the need
* for TSB entries. So, huge zero page counts go into
* hugetlb_pte_count.
*/
if (pmd_val(pmd) & _PAGE_PMD_HUGE) {
if (is_huge_zero_page(pmd_page(pmd)))
mm->context.hugetlb_pte_count++;
else
mm->context.thp_pte_count++;
} else {
if (is_huge_zero_page(pmd_page(orig)))
mm->context.hugetlb_pte_count--;
else
mm->context.thp_pte_count--;
}
/* Do not try to allocate the TSB hash table if we
* don't have one already. We have various locks held
* and thus we'll end up doing a GFP_KERNEL allocation
* in an atomic context.
*
* Instead, we let the first TLB miss on a hugepage
* take care of this.
*/
}
if (!pmd_none(orig)) {
addr &= HPAGE_MASK;
if (pmd_trans_huge(orig)) {
pte_t orig_pte = __pte(pmd_val(orig));
bool exec = pte_exec(orig_pte);
tlb_batch_add_one(mm, addr, exec, REAL_HPAGE_SHIFT);
tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
REAL_HPAGE_SHIFT);
} else {
tlb_batch_pmd_scan(mm, addr, orig);
}
}
}
static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct clear_refs_private *cp = walk->private;
struct vm_area_struct *vma = walk->vma;
pte_t *pte, ptent;
spinlock_t *ptl;
struct page *page;
if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
clear_soft_dirty_pmd(vma, addr, pmd);
goto out;
}
page = pmd_page(*pmd);
/* Clear accessed and referenced bits. */
pmdp_test_and_clear_young(vma, addr, pmd);
ClearPageReferenced(page);
out:
spin_unlock(ptl);
return 0;
}
if (pmd_trans_unstable(pmd))
return 0;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
clear_soft_dirty(vma, addr, pte);
continue;
}
if (!pte_present(ptent))
continue;
page = vm_normal_page(vma, addr, ptent);
if (!page)
continue;
/* Clear accessed and referenced bits. */
ptep_test_and_clear_young(vma, addr, pte);
ClearPageReferenced(page);
}
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
return 0;
}
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmdp, int write)
{
struct page *page;
if (!MACHINE_HAS_HPAGE)
return NULL;
page = pmd_page(*pmdp);
if (page)
page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
return page;
}
static void free_pmd_range(pud_t *pud)
{
int i;
pmd_t *pmd;
pmd = pmd_offset(pud, 0);
for (i=0 ; i<PTRS_PER_PMD ; i++, pmd++) {
struct page *page;
if (oleole_pmd_none_or_clear_bad(pmd))
continue;
page = pmd_page(*pmd);
__free_page(page);
pmd_clear(pmd);
}
}
/*
* This routine is only called when splitting a THP
*/
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
pmd_t entry = *pmdp;
pmd_val(entry) &= ~_PAGE_VALID;
set_pmd_at(vma->vm_mm, address, pmdp, entry);
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
/*
* set_pmd_at() will not be called in a way to decrement
* thp_pte_count when splitting a THP, so do it now.
* Sanity check pmd before doing the actual decrement.
*/
if ((pmd_val(entry) & _PAGE_PMD_HUGE) &&
!is_huge_zero_page(pmd_page(entry)))
(vma->vm_mm)->context.thp_pte_count--;
}
pte_t *get_pte_slow(pmd_t *pmd, unsigned long offset)
{
pte_t *page;
page = (pte_t *) __get_free_page(GFP_KERNEL);
if (pmd_none(*pmd)) {
if (page) {
clear_page((unsigned long)page);
pmd_val(*pmd) = (unsigned long)page;
return page + offset;
}
pmd_val(*pmd) = BAD_PAGETABLE;
return NULL;
}
free_page((unsigned long)page);
if (pmd_bad(*pmd)) {
__bad_pte(pmd);
return NULL;
}
return (pte_t *) pmd_page(*pmd) + offset;
}
pte_t *get_pte_slow(pmd_t *pmd, unsigned long offset)
{
pte_t *pte;
pte = (pte_t *)alloc_pte_table(PTRS_PER_PTE * sizeof(pte_t), GFP_KERNEL);
if (pmd_none(*pmd)) {
if (pte) {
memzero(pte, PTRS_PER_PTE * sizeof(pte_t));
set_pmd(pmd, mk_user_pmd(pte));
return pte + offset;
}
set_pmd(pmd, mk_user_pmd(get_bad_pte_table()));
return NULL;
}
free_pte_slow(pte);
if (pmd_bad(*pmd)) {
__handle_bad_pmd(pmd);
return NULL;
}
return (pte_t *) pmd_page(*pmd) + offset;
}
pte_t *get_pte_kernel_slow(pmd_t *pmd, unsigned long offset)
{
pte_t *pte;
pte = (pte_t *)get_page_2k(GFP_KERNEL);
if (pmd_none(*pmd)) {
if (pte) {
memzero(pte, 2 * PTRS_PER_PTE * BYTES_PER_PTR);
clean_cache_area(pte, PTRS_PER_PTE * BYTES_PER_PTR);
pte += PTRS_PER_PTE;
set_pmd(pmd, mk_kernel_pmd(pte));
return pte + offset;
}
set_pmd(pmd, mk_kernel_pmd(BAD_PAGETABLE));
return NULL;
}
free_page_2k((unsigned long)pte);
if (pmd_bad(*pmd)) {
__bad_pmd_kernel(pmd);
return NULL;
}
return (pte_t *) pmd_page(*pmd) + offset;
}
/**
* follow_page_mask - look up a page descriptor from a user-virtual address
* @vma: vm_area_struct mapping @address
* @address: virtual address to look up
* @flags: flags modifying lookup behaviour
* @page_mask: on output, *page_mask is set according to the size of the page
*
* @flags can have FOLL_ flags set, defined in <linux/mm.h>
*
* Returns the mapped (struct page *), %NULL if no mapping exists, or
* an error pointer if there is a mapping to something not represented
* by a page descriptor (see also vm_normal_page()).
*/
struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
unsigned int *page_mask)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
spinlock_t *ptl;
struct page *page;
struct mm_struct *mm = vma->vm_mm;
*page_mask = 0;
page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
if (!IS_ERR(page)) {
BUG_ON(flags & FOLL_GET);
return page;
}
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
return no_page_table(vma, flags);
p4d = p4d_offset(pgd, address);
if (p4d_none(*p4d))
return no_page_table(vma, flags);
BUILD_BUG_ON(p4d_huge(*p4d));
if (unlikely(p4d_bad(*p4d)))
return no_page_table(vma, flags);
pud = pud_offset(p4d, address);
if (pud_none(*pud))
return no_page_table(vma, flags);
if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
page = follow_huge_pud(mm, address, pud, flags);
if (page)
return page;
return no_page_table(vma, flags);
}
if (pud_devmap(*pud)) {
ptl = pud_lock(mm, pud);
page = follow_devmap_pud(vma, address, pud, flags);
spin_unlock(ptl);
if (page)
return page;
}
if (unlikely(pud_bad(*pud)))
return no_page_table(vma, flags);
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd))
return no_page_table(vma, flags);
if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
page = follow_huge_pmd(mm, address, pmd, flags);
if (page)
return page;
return no_page_table(vma, flags);
}
if (pmd_devmap(*pmd)) {
ptl = pmd_lock(mm, pmd);
page = follow_devmap_pmd(vma, address, pmd, flags);
spin_unlock(ptl);
if (page)
return page;
}
if (likely(!pmd_trans_huge(*pmd)))
return follow_page_pte(vma, address, pmd, flags);
if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
return no_page_table(vma, flags);
ptl = pmd_lock(mm, pmd);
if (unlikely(!pmd_trans_huge(*pmd))) {
spin_unlock(ptl);
return follow_page_pte(vma, address, pmd, flags);
}
if (flags & FOLL_SPLIT) {
int ret;
page = pmd_page(*pmd);
if (is_huge_zero_page(page)) {
spin_unlock(ptl);
ret = 0;
split_huge_pmd(vma, pmd, address);
if (pmd_trans_unstable(pmd))
ret = -EBUSY;
} else {
get_page(page);
spin_unlock(ptl);
lock_page(page);
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
if (pmd_none(*pmd))
return no_page_table(vma, flags);
}
return ret ? ERR_PTR(ret) :
follow_page_pte(vma, address, pmd, flags);
}
page = follow_trans_huge_pmd(vma, address, pmd, flags);
spin_unlock(ptl);
*page_mask = HPAGE_PMD_NR - 1;
return page;
}
pte_t *_pte_offset_map(pmd_t *dir, unsigned long address, enum km_type type)
{
pte_t *pte = kmap_atomic(pmd_page(*dir), type) +
(pmd_ptfn(*dir) << HV_LOG2_PAGE_TABLE_ALIGN) & ~PAGE_MASK;
return &pte[pte_index(address)];
}
/**
* page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at
* @pvmw->address
* @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags
* must be set. pmd, pte and ptl must be NULL.
*
* Returns true if the page is mapped in the vma. @pvmw->pmd and @pvmw->pte point
* to relevant page table entries. @pvmw->ptl is locked. @pvmw->address is
* adjusted if needed (for PTE-mapped THPs).
*
* If @pvmw->pmd is set but @pvmw->pte is not, you have found PMD-mapped page
* (usually THP). For PTE-mapped THP, you should run page_vma_mapped_walk() in
* a loop to find all PTEs that map the THP.
*
* For HugeTLB pages, @pvmw->pte is set to the relevant page table entry
* regardless of which page table level the page is mapped at. @pvmw->pmd is
* NULL.
*
* Retruns false if there are no more page table entries for the page in
* the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped.
*
* If you need to stop the walk before page_vma_mapped_walk() returned false,
* use page_vma_mapped_walk_done(). It will do the housekeeping.
*/
bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
{
struct mm_struct *mm = pvmw->vma->vm_mm;
struct page *page = pvmw->page;
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t pmde;
/* The only possible pmd mapping has been handled on last iteration */
if (pvmw->pmd && !pvmw->pte)
return not_found(pvmw);
if (pvmw->pte)
goto next_pte;
if (unlikely(PageHuge(pvmw->page))) {
/* when pud is not present, pte will be NULL */
pvmw->pte = huge_pte_offset(mm, pvmw->address,
PAGE_SIZE << compound_order(page));
if (!pvmw->pte)
return false;
pvmw->ptl = huge_pte_lockptr(page_hstate(page), mm, pvmw->pte);
spin_lock(pvmw->ptl);
if (!check_pte(pvmw))
return not_found(pvmw);
return true;
}
restart:
pgd = pgd_offset(mm, pvmw->address);
if (!pgd_present(*pgd))
return false;
p4d = p4d_offset(pgd, pvmw->address);
if (!p4d_present(*p4d))
return false;
pud = pud_offset(p4d, pvmw->address);
if (!pud_present(*pud))
return false;
pvmw->pmd = pmd_offset(pud, pvmw->address);
/*
* Make sure the pmd value isn't cached in a register by the
* compiler and used as a stale value after we've observed a
* subsequent update.
*/
pmde = READ_ONCE(*pvmw->pmd);
if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
pvmw->ptl = pmd_lock(mm, pvmw->pmd);
if (likely(pmd_trans_huge(*pvmw->pmd))) {
if (pvmw->flags & PVMW_MIGRATION)
return not_found(pvmw);
if (pmd_page(*pvmw->pmd) != page)
return not_found(pvmw);
return true;
} else if (!pmd_present(*pvmw->pmd)) {
if (thp_migration_supported()) {
if (!(pvmw->flags & PVMW_MIGRATION))
return not_found(pvmw);
if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) {
swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd);
if (migration_entry_to_page(entry) != page)
return not_found(pvmw);
return true;
}
}
return not_found(pvmw);
} else {
/* THP pmd was split under us: handle on pte level */
spin_unlock(pvmw->ptl);
pvmw->ptl = NULL;
}
} else if (!pmd_present(pmde)) {
return false;
}
if (!map_pte(pvmw))
goto next_pte;
while (1) {
if (check_pte(pvmw))
return true;
next_pte:
/* Seek to next pte only makes sense for THP */
if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
return not_found(pvmw);
do {
pvmw->address += PAGE_SIZE;
if (pvmw->address >= pvmw->vma->vm_end ||
pvmw->address >=
__vma_address(pvmw->page, pvmw->vma) +
hpage_nr_pages(pvmw->page) * PAGE_SIZE)
return not_found(pvmw);
/* Did we cross page table boundary? */
if (pvmw->address % PMD_SIZE == 0) {
pte_unmap(pvmw->pte);
if (pvmw->ptl) {
spin_unlock(pvmw->ptl);
pvmw->ptl = NULL;
}
goto restart;
} else {
pvmw->pte++;
}
} while (pte_none(*pvmw->pte));
if (!pvmw->ptl) {
pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
spin_lock(pvmw->ptl);
}
}
}
/*
(Yet another) pagetable walker. This one is intended for pinning a
pagetable. This means that it walks a pagetable and calls the
callback function on each page it finds making up the page table,
at every level. It walks the entire pagetable, but it only bothers
pinning pte pages which are below pte_limit. In the normal case
this will be TASK_SIZE, but at boot we need to pin up to
FIXADDR_TOP. But the important bit is that we don't pin beyond
there, because then we start getting into Xen's ptes.
*/
static int pgd_walk(pgd_t *pgd_base, int (*func)(struct page *, unsigned),
unsigned long limit)
{
pgd_t *pgd = pgd_base;
int flush = 0;
unsigned long addr = 0;
unsigned long pgd_next;
BUG_ON(limit > FIXADDR_TOP);
if (xen_feature(XENFEAT_auto_translated_physmap))
return 0;
for (; addr != FIXADDR_TOP; pgd++, addr = pgd_next) {
pud_t *pud;
unsigned long pud_limit, pud_next;
pgd_next = pud_limit = pgd_addr_end(addr, FIXADDR_TOP);
if (!pgd_val(*pgd))
continue;
pud = pud_offset(pgd, 0);
if (PTRS_PER_PUD > 1) /* not folded */
flush |= (*func)(virt_to_page(pud), 0);
for (; addr != pud_limit; pud++, addr = pud_next) {
pmd_t *pmd;
unsigned long pmd_limit;
pud_next = pud_addr_end(addr, pud_limit);
if (pud_next < limit)
pmd_limit = pud_next;
else
pmd_limit = limit;
if (pud_none(*pud))
continue;
pmd = pmd_offset(pud, 0);
if (PTRS_PER_PMD > 1) /* not folded */
flush |= (*func)(virt_to_page(pmd), 0);
for (; addr != pmd_limit; pmd++) {
addr += (PAGE_SIZE * PTRS_PER_PTE);
if ((pmd_limit-1) < (addr-1)) {
addr = pmd_limit;
break;
}
if (pmd_none(*pmd))
continue;
flush |= (*func)(pmd_page(*pmd), 0);
}
}
}
flush |= (*func)(virt_to_page(pgd_base), UVMF_TLB_FLUSH);
return flush;
}
