int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty)
{
int ncontig, i, changed = 0;
size_t pgsize = 0;
unsigned long pfn = pte_pfn(pte), dpfn;
pgprot_t hugeprot;
pte_t orig_pte;
if (!pte_cont(pte))
return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
dpfn = pgsize >> PAGE_SHIFT;
orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
if (!pte_same(orig_pte, pte))
changed = 1;
/* Make sure we don't lose the dirty state */
if (pte_dirty(orig_pte))
pte = pte_mkdirty(pte);
hugeprot = pte_pgprot(pte);
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
return changed;
}
/*
* No need to decide whether this PTE shares the swap entry with others,
* just let do_wp_page work it out if a write is requested later - to
* force COW, vm_page_prot omits write permission from any private vma.
*/
static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, swp_entry_t entry, struct page *page)
{
spinlock_t *ptl;
pte_t *pte;
int ret = 1;
if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
ret = -ENOMEM;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
if (ret > 0)
mem_cgroup_uncharge_page(page);
ret = 0;
goto out;
}
inc_mm_counter(vma->vm_mm, anon_rss);
get_page(page);
set_pte_at(vma->vm_mm, addr, pte,
pte_mkold(mk_pte(page, vma->vm_page_prot)));
page_add_anon_rmap(page, vma, addr);
swap_free(entry);
/*
* Move the page to the active list so it is not
* immediately swapped out again after swapon.
*/
activate_page(page);
out:
pte_unmap_unlock(pte, ptl);
return ret;
}
static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
pte_t swp_pte = swp_entry_to_pte(entry);
pte_t *pte;
int ret = 0;
/*
* We don't actually need pte lock while scanning for swp_pte: since
* we hold page lock and mmap_sem, swp_pte cannot be inserted into the
* page table while we're scanning; though it could get zapped, and on
* some architectures (e.g. x86_32 with PAE) we might catch a glimpse
* of unmatched parts which look like swp_pte, so unuse_pte must
* recheck under pte lock. Scanning without pte lock lets it be
* preemptible whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE.
*/
pte = pte_offset_map(pmd, addr);
do {
/*
* swapoff spends a _lot_ of time in this loop!
* Test inline before going to call unuse_pte.
*/
if (unlikely(pte_same(*pte, swp_pte))) {
pte_unmap(pte);
ret = unuse_pte(vma, pmd, addr, entry, page);
if (ret)
goto out;
pte = pte_offset_map(pmd, addr);
}
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap(pte - 1);
out:
return ret;
}
/*
* This routine handles present pages, when users try to write
* to a shared page. It is done by copying the page to a new address
* and decrementing the shared-page counter for the old page.
*
* Goto-purists beware: the only reason for goto's here is that it results
* in better assembly code.. The "default" path will see no jumps at all.
*
* Note that this routine assumes that the protection checks have been
* done by the caller (the low-level page fault routine in most cases).
* Thus we can safely just mark it writable once we've done any necessary
* COW.
*
* We also mark the page dirty at this point even though the page will
* change only once the write actually happens. This avoids a few races,
* and potentially makes it more efficient.
*
* We hold the mm semaphore and the page_table_lock on entry and exit
* with the page_table_lock released.
*/
static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
unsigned long address, pte_t *page_table, pte_t pte)
{
struct page *old_page, *new_page;
old_page = pte_page(pte);
if (!VALID_PAGE(old_page))
goto bad_wp_page;
if (!TryLockPage(old_page)) {
int reuse = can_share_swap_page(old_page);
unlock_page(old_page);
if (reuse) {
#ifndef CONFIG_SUPERH
/* Not needed for VIPT cache */
flush_cache_page(vma, address);
#endif
establish_pte(vma, address, page_table, pte_mkyoung(pte_mkdirty(pte_mkwrite(pte))));
spin_unlock(&mm->page_table_lock);
return 1; /* Minor fault */
}
}
/*
* Ok, we need to copy. Oh, well..
*/
page_cache_get(old_page);
spin_unlock(&mm->page_table_lock);
new_page = alloc_page(GFP_HIGHUSER);
if (!new_page)
goto no_mem;
copy_cow_page(old_page,new_page,address);
/*
* Re-check the pte - we dropped the lock
*/
spin_lock(&mm->page_table_lock);
if (pte_same(*page_table, pte)) {
if (PageReserved(old_page))
++mm->rss;
break_cow(vma, new_page, address, page_table);
lru_cache_add(new_page);
/* Free the old page.. */
new_page = old_page;
}
spin_unlock(&mm->page_table_lock);
page_cache_release(new_page);
page_cache_release(old_page);
return 1; /* Minor fault */
bad_wp_page:
spin_unlock(&mm->page_table_lock);
printk("do_wp_page: bogus page at address %08lx (page 0x%lx)\n",address,(unsigned long)old_page);
return -1;
no_mem:
page_cache_release(old_page);
return -1;
}
/*
* Only sets the access flags (dirty, accessed), as well as write
* permission. Furthermore, we know it always gets set to a "more
* permissive" setting, which allows most architectures to optimize
* this. We return whether the PTE actually changed, which in turn
* instructs the caller to do things like update__mmu_cache. This
* used to be done in the caller, but sparc needs minor faults to
* force that call on sun4c so we changed this macro slightly
*/
int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
pte_t entry, int dirty)
{
int changed = !pte_same(*ptep, entry);
if (changed) {
set_pte_at(vma->vm_mm, address, ptep, entry);
flush_tlb_fix_spurious_fault(vma, address);
}
return changed;
}
/*
* This is called when relaxing access to a PTE. It's also called in the page
* fault path when we don't hit any of the major fault cases, ie, a minor
* update of _PAGE_ACCESSED, _PAGE_DIRTY, etc... The generic code will have
* handled those two for us, we additionally deal with missing execute
* permission here on some processors
*/
int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep, pte_t entry, int dirty)
{
int changed;
entry = set_access_flags_filter(entry, vma, dirty);
changed = !pte_same(*(ptep), entry);
if (changed) {
assert_pte_locked(vma->vm_mm, address);
__ptep_set_access_flags(vma, ptep, entry,
address, mmu_virtual_psize);
}
return changed;
}
/*
* This is called when relaxing access to a PTE. It's also called in the page
* fault path when we don't hit any of the major fault cases, ie, a minor
* update of _PAGE_ACCESSED, _PAGE_DIRTY, etc... The generic code will have
* handled those two for us, we additionally deal with missing execute
* permission here on some processors
*/
int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep, pte_t entry, int dirty)
{
int changed;
entry = set_access_flags_filter(entry, vma, dirty);
changed = !pte_same(*(ptep), entry);
if (changed) {
if (!is_vm_hugetlb_page(vma))
assert_pte_locked(vma->vm_mm, address);
__ptep_set_access_flags(ptep, entry);
flush_tlb_page_nohash(vma, address);
}
return changed;
}
/*
* This is called when relaxing access to a PTE. It's also called in the page
* fault path when we don't hit any of the major fault cases, ie, a minor
* update of _PAGE_ACCESSED, _PAGE_DIRTY, etc... The generic code will have
* handled those two for us, we additionally deal with missing execute
* permission here on some processors
*/
int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep, pte_t entry, int dirty)
{
int changed;
if (!dirty && pte_need_exec_flush(entry, 0))
entry = do_dcache_icache_coherency(entry);
changed = !pte_same(*(ptep), entry);
if (changed) {
assert_pte_locked(vma->vm_mm, address);
__ptep_set_access_flags(ptep, entry);
flush_tlb_page_nohash(vma, address);
}
return changed;
}
extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty)
{
#ifdef HUGETLB_NEED_PRELOAD
/*
* The "return 1" forces a call of update_mmu_cache, which will write a
* TLB entry. Without this, platforms that don't do a write of the TLB
* entry in the TLB miss handler asm will fault ad infinitum.
*/
ptep_set_access_flags(vma, addr, ptep, pte, dirty);
return 1;
#else
int changed, psize;
pte = set_access_flags_filter(pte, vma, dirty);
changed = !pte_same(*(ptep), pte);
if (changed) {
#ifdef CONFIG_PPC_BOOK3S_64
struct hstate *h = hstate_vma(vma);
psize = hstate_get_psize(h);
#ifdef CONFIG_DEBUG_VM
assert_spin_locked(huge_pte_lockptr(h, vma->vm_mm, ptep));
#endif
#else
/*
* Not used on non book3s64 platforms. But 8xx
* can possibly use tsize derived from hstate.
*/
psize = 0;
#endif
__ptep_set_access_flags(vma, ptep, pte, addr, psize);
}
return changed;
#endif
}
static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
pte_t *pte, unsigned int flags)
{
/* No page to get reference */
if (flags & FOLL_GET)
return -EFAULT;
if (flags & FOLL_TOUCH) {
pte_t entry = *pte;
if (flags & FOLL_WRITE)
entry = pte_mkdirty(entry);
entry = pte_mkyoung(entry);
if (!pte_same(*pte, entry)) {
set_pte_at(vma->vm_mm, address, pte, entry);
update_mmu_cache(vma, address, pte);
}
}
/* Proper page table entry exists, but no corresponding struct page */
return -EEXIST;
}
static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
pte_t swp_pte = swp_entry_to_pte(entry);
pte_t *pte;
spinlock_t *ptl;
int found = 0;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
do {
/*
* swapoff spends a _lot_ of time in this loop!
* Test inline before going to call unuse_pte.
*/
if (unlikely(pte_same(*pte, swp_pte))) {
unuse_pte(vma, pte++, addr, entry, page);
found = 1;
break;
}
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap_unlock(pte - 1, ptl);
return found;
}
/*
* This routine handles present pages, when users try to write
* to a shared page. It is done by copying the page to a new address
* and decrementing the shared-page counter for the old page.
*
* Goto-purists beware: the only reason for goto's here is that it results
* in better assembly code.. The "default" path will see no jumps at all.
*
* Note that this routine assumes that the protection checks have been
* done by the caller (the low-level page fault routine in most cases).
* Thus we can safely just mark it writable once we've done any necessary
* COW.
*
* We also mark the page dirty at this point even though the page will
* change only once the write actually happens. This avoids a few races,
* and potentially makes it more efficient.
*
* We enter with the page table read-lock held, and need to exit without
* it.
*/
static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
unsigned long address, pte_t *page_table, pte_t pte)
{
struct page *old_page, *new_page;
old_page = pte_page(pte);
if (!VALID_PAGE(old_page))
goto bad_wp_page;
/*
* We can avoid the copy if:
* - we're the only user (count == 1)
* - the only other user is the swap cache,
* and the only swap cache user is itself,
* in which case we can just continue to
* use the same swap cache (it will be
* marked dirty).
*/
switch (page_count(old_page)) {
case 2:
/*
* Lock the page so that no one can look it up from
* the swap cache, grab a reference and start using it.
* Can not do lock_page, holding page_table_lock.
*/
if (!PageSwapCache(old_page) || TryLockPage(old_page))
break;
if (is_page_shared(old_page)) {
UnlockPage(old_page);
break;
}
UnlockPage(old_page);
/* FallThrough */
case 1:
flush_cache_page(vma, address);
establish_pte(vma, address, page_table, pte_mkyoung(pte_mkdirty(pte_mkwrite(pte))));
spin_unlock(&mm->page_table_lock);
return 1; /* Minor fault */
}
/*
* Ok, we need to copy. Oh, well..
*/
spin_unlock(&mm->page_table_lock);
new_page = page_cache_alloc();
if (!new_page)
return -1;
spin_lock(&mm->page_table_lock);
/*
* Re-check the pte - we dropped the lock
*/
if (pte_same(*page_table, pte)) {
if (PageReserved(old_page))
++mm->rss;
break_cow(vma, old_page, new_page, address, page_table);
/* Free the old page.. */
new_page = old_page;
}
spin_unlock(&mm->page_table_lock);
page_cache_release(new_page);
return 1; /* Minor fault */
bad_wp_page:
spin_unlock(&mm->page_table_lock);
printk("do_wp_page: bogus page at address %08lx (page 0x%lx)\n",address,(unsigned long)old_page);
return -1;
}
/*
* We hold the mm semaphore and the page_table_lock on entry and
* should release the pagetable lock on exit..
*/
static int do_swap_page(struct mm_struct * mm,
struct vm_area_struct * vma, unsigned long address,
pte_t * page_table, pte_t orig_pte, int write_access)
{
struct page *page;
swp_entry_t entry = pte_to_swp_entry(orig_pte);
pte_t pte;
int ret = 1;
spin_unlock(&mm->page_table_lock);
page = lookup_swap_cache(entry);
if (!page) {
swapin_readahead(entry);
page = read_swap_cache_async(entry);
if (!page) {
/*
* Back out if somebody else faulted in this pte while
* we released the page table lock.
*/
int retval;
spin_lock(&mm->page_table_lock);
retval = pte_same(*page_table, orig_pte) ? -1 : 1;
spin_unlock(&mm->page_table_lock);
return retval;
}
/* Had to read the page from swap area: Major fault */
ret = 2;
}
lock_page(page);
/*
* Back out if somebody else faulted in this pte while we
* released the page table lock.
*/
spin_lock(&mm->page_table_lock);
if (!pte_same(*page_table, orig_pte)) {
spin_unlock(&mm->page_table_lock);
unlock_page(page);
page_cache_release(page);
return 1;
}
/* The page isn't present yet, go ahead with the fault. */
swap_free(entry);
if (vm_swap_full())
remove_exclusive_swap_page(page);
mm->rss++;
pte = mk_pte(page, vma->vm_page_prot);
if (write_access && can_share_swap_page(page))
pte = pte_mkdirty(pte_mkwrite(pte));
unlock_page(page);
flush_page_to_ram(page);
flush_icache_page(vma, page);
set_pte(page_table, pte);
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, pte);
spin_unlock(&mm->page_table_lock);
return ret;
}
