memory.c

				NULL);
}
EXPORT_SYMBOL(get_user_pages);

/**
 * get_dump_page() - pin user page in memory while writing it to core dump
 * @addr: user address
 *
 * Returns struct page pointer of user page pinned for dump,
 * to be freed afterwards by page_cache_release() or put_page().
 *
 * Returns NULL on any kind of failure - a hole must then be inserted into
 * the corefile, to preserve alignment with its headers; and also returns
 * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
 * allowing a hole to be left in the corefile to save diskspace.
 *
 * Called without mmap_sem, but after all other threads have been killed.
 */
#ifdef CONFIG_ELF_CORE
struct page *get_dump_page(unsigned long addr)
{
	struct vm_area_struct *vma;
	struct page *page;

	if (__get_user_pages(current, current->mm, addr, 1,
			     FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
			     NULL) < 1)
		return NULL;
	flush_cache_page(vma, addr, page_to_pfn(page));
	return page;
}
#endif /* CONFIG_ELF_CORE */

pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
			spinlock_t **ptl)
{
	pgd_t * pgd = pgd_offset(mm, addr);
	pud_t * pud = pud_alloc(mm, pgd, addr);
	if (pud) {
		pmd_t * pmd = pmd_alloc(mm, pud, addr);
		if (pmd) {
			VM_BUG_ON(pmd_trans_huge(*pmd));
			return pte_alloc_map_lock(mm, pmd, addr, ptl);
		}
	}
	return NULL;
}

/*
 * This is the old fallback for page remapping.
 *
 * For historical reasons, it only allows reserved pages. Only
 * old drivers should use this, and they needed to mark their
 * pages reserved for the old functions anyway.
 */
static int insert_page(struct vm_area_struct *vma, unsigned long addr,
			struct page *page, pgprot_t prot)
{
	struct mm_struct *mm = vma->vm_mm;
	int retval;
	pte_t *pte;
	spinlock_t *ptl;

	retval = -EINVAL;
	if (PageAnon(page))
		goto out;
	retval = -ENOMEM;
	flush_dcache_page(page);
	pte = get_locked_pte(mm, addr, &ptl);
	if (!pte)
		goto out;
	retval = -EBUSY;
	if (!pte_none(*pte))
		goto out_unlock;

	/* Ok, finally just insert the thing.. */
	get_page(page);
	inc_mm_counter_fast(mm, MM_FILEPAGES);
	page_add_file_rmap(page);
	set_pte_at(mm, addr, pte, mk_pte(page, prot));

	retval = 0;
	pte_unmap_unlock(pte, ptl);
	return retval;
out_unlock:
	pte_unmap_unlock(pte, ptl);
out:
	return retval;
}

/**
 * vm_insert_page - insert single page into user vma
 * @vma: user vma to map to
 * @addr: target user address of this page
 * @page: source kernel page
 *
 * This allows drivers to insert individual pages they've allocated
 * into a user vma.
 *
 * The page has to be a nice clean _individual_ kernel allocation.
 * If you allocate a compound page, you need to have marked it as
 * such (__GFP_COMP), or manually just split the page up yourself
 * (see split_page()).
 *
 * NOTE! Traditionally this was done with "remap_pfn_range()" which
 * took an arbitrary page protection parameter. This doesn't allow
 * that. Your vma protection will have to be set up correctly, which
 * means that if you want a shared writable mapping, you'd better
 * ask for a shared writable mapping!
 *
 * The page does not need to be reserved.
 *
 * Usually this function is called from f_op->mmap() handler
 * under mm->mmap_sem write-lock, so it can change vma->vm_flags.
 * Caller must set VM_MIXEDMAP on vma if it wants to call this
 * function from other places, for example from page-fault handler.
 */
int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
			struct page *page)
{
	if (addr < vma->vm_start || addr >= vma->vm_end)
		return -EFAULT;
	if (!page_count(page))
		return -EINVAL;
	if (!(vma->vm_flags & VM_MIXEDMAP)) {
		BUG_ON(down_read_trylock(&vma->vm_mm->mmap_sem));
		BUG_ON(vma->vm_flags & VM_PFNMAP);
		vma->vm_flags |= VM_MIXEDMAP;
	}
	return insert_page(vma, addr, page, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_insert_page);

static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
			unsigned long pfn, pgprot_t prot)
{
	struct mm_struct *mm = vma->vm_mm;
	int retval;
	pte_t *pte, entry;
	spinlock_t *ptl;

	retval = -ENOMEM;
	pte = get_locked_pte(mm, addr, &ptl);
	if (!pte)
		goto out;
	retval = -EBUSY;
	if (!pte_none(*pte))
		goto out_unlock;

	/* Ok, finally just insert the thing.. */
	entry = pte_mkspecial(pfn_pte(pfn, prot));
	set_pte_at(mm, addr, pte, entry);
	update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */

	retval = 0;
out_unlock:
	pte_unmap_unlock(pte, ptl);
out:
	return retval;
}

/**
 * vm_insert_pfn - insert single pfn into user vma
 * @vma: user vma to map to
 * @addr: target user address of this page
 * @pfn: source kernel pfn
 *
 * Similar to vm_insert_page, this allows drivers to insert individual pages
 * they've allocated into a user vma. Same comments apply.
 *
 * This function should only be called from a vm_ops->fault handler, and
 * in that case the handler should return NULL.
 *
 * vma cannot be a COW mapping.
 *
 * As this is called only for pages that do not currently exist, we
 * do not need to flush old virtual caches or the TLB.
 */
int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
			unsigned long pfn)
{
	int ret;
	pgprot_t pgprot = vma->vm_page_prot;
	/*
	 * Technically, architectures with pte_special can avoid all these
	 * restrictions (same for remap_pfn_range).  However we would like
	 * consistency in testing and feature parity among all, so we should
	 * try to keep these invariants in place for everybody.
	 */
	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
						(VM_PFNMAP|VM_MIXEDMAP));
	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
	BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));

	if (addr < vma->vm_start || addr >= vma->vm_end)
		return -EFAULT;
	if (track_pfn_insert(vma, &pgprot, pfn))
		return -EINVAL;

	ret = insert_pfn(vma, addr, pfn, pgprot);

	return ret;
}
EXPORT_SYMBOL(vm_insert_pfn);

int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
			unsigned long pfn)
{
	BUG_ON(!(vma->vm_flags & VM_MIXEDMAP));

	if (addr < vma->vm_start || addr >= vma->vm_end)
		return -EFAULT;

	/*
	 * If we don't have pte special, then we have to use the pfn_valid()
	 * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
	 * refcount the page if pfn_valid is true (hence insert_page rather
	 * than insert_pfn).  If a zero_pfn were inserted into a VM_MIXEDMAP
	 * without pte special, it would there be refcounted as a normal page.
	 */
	if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) {
		struct page *page;

		page = pfn_to_page(pfn);
		return insert_page(vma, addr, page, vma->vm_page_prot);
	}
	return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_insert_mixed);

/*
 * maps a range of physical memory into the requested pages. the old
 * mappings are removed. any references to nonexistent pages results
 * in null mappings (currently treated as "copy-on-access")
 */
static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pte_t *pte;
	spinlock_t *ptl;

	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
	if (!pte)
		return -ENOMEM;
	arch_enter_lazy_mmu_mode();
	do {
		BUG_ON(!pte_none(*pte));
		set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
		pfn++;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	arch_leave_lazy_mmu_mode();
	pte_unmap_unlock(pte - 1, ptl);
	return 0;
}

static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pmd_t *pmd;
	unsigned long next;

	pfn -= addr >> PAGE_SHIFT;
	pmd = pmd_alloc(mm, pud, addr);
	if (!pmd)
		return -ENOMEM;
	VM_BUG_ON(pmd_trans_huge(*pmd));
	do {
		next = pmd_addr_end(addr, end);
		if (remap_pte_range(mm, pmd, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot))
			return -ENOMEM;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pud_t *pud;
	unsigned long next;

	pfn -= addr >> PAGE_SHIFT;
	pud = pud_alloc(mm, pgd, addr);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);
		if (remap_pmd_range(mm, pud, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot))
			return -ENOMEM;
	} while (pud++, addr = next, addr != end);
	return 0;
}

/**
 * remap_pfn_range - remap kernel memory to userspace
 * @vma: user vma to map to
 * @addr: target user address to start at
 * @pfn: physical address of kernel memory
 * @size: size of map area
 * @prot: page protection flags for this mapping
 *
 *  Note: this is only safe if the mm semaphore is held when called.
 */
int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
		    unsigned long pfn, unsigned long size, pgprot_t prot)
{
	pgd_t *pgd;
	unsigned long next;
	unsigned long end = addr + PAGE_ALIGN(size);
	struct mm_struct *mm = vma->vm_mm;
	int err;

	/*
	 * Physically remapped pages are special. Tell the
	 * rest of the world about it:
	 *   VM_IO tells people not to look at these pages
	 *	(accesses can have side effects).
	 *   VM_PFNMAP tells the core MM that the base pages are just
	 *	raw PFN mappings, and do not have a "struct page" associated
	 *	with them.
	 *   VM_DONTEXPAND
	 *      Disable vma merging and expanding with mremap().
	 *   VM_DONTDUMP
	 *      Omit vma from core dump, even when VM_IO turned off.
	 *
	 * There's a horrible special case to handle copy-on-write
	 * behaviour that some programs depend on. We mark the "original"
	 * un-COW'ed pages by matching them up with "vma->vm_pgoff".
	 * See vm_normal_page() for details.
	 */
	if (is_cow_mapping(vma->vm_flags)) {
		if (addr != vma->vm_start || end != vma->vm_end)
			return -EINVAL;
		vma->vm_pgoff = pfn;
	}

	err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size));
	if (err)
		return -EINVAL;

	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;

	BUG_ON(addr >= end);
	pfn -= addr >> PAGE_SHIFT;
	pgd = pgd_offset(mm, addr);
	flush_cache_range(vma, addr, end);
	do {
		next = pgd_addr_end(addr, end);
		err = remap_pud_range(mm, pgd, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);

	if (err)
		untrack_pfn(vma, pfn, PAGE_ALIGN(size));

	return err;
}
EXPORT_SYMBOL(remap_pfn_range);

static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
				     unsigned long addr, unsigned long end,
				     pte_fn_t fn, void *data)
{
	pte_t *pte;
	int err;
	pgtable_t token;
	spinlock_t *uninitialized_var(ptl);

	pte = (mm == &init_mm) ?
		pte_alloc_kernel(pmd, addr) :
		pte_alloc_map_lock(mm, pmd, addr, &ptl);
	if (!pte)
		return -ENOMEM;

	BUG_ON(pmd_huge(*pmd));

	arch_enter_lazy_mmu_mode();

	token = pmd_pgtable(*pmd);

	do {
		err = fn(pte++, token, addr, data);
		if (err)
			break;
	} while (addr += PAGE_SIZE, addr != end);

	arch_leave_lazy_mmu_mode();

	if (mm != &init_mm)
		pte_unmap_unlock(pte-1, ptl);
	return err;
}

static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
				     unsigned long addr, unsigned long end,
				     pte_fn_t fn, void *data)
{
	pmd_t *pmd;
	unsigned long next;
	int err;

	BUG_ON(pud_huge(*pud));

	pmd = pmd_alloc(mm, pud, addr);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);
		err = apply_to_pte_range(mm, pmd, addr, next, fn, data);
		if (err)
			break;
	} while (pmd++, addr = next, addr != end);
	return err;
}

static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
				     unsigned long addr, unsigned long end,
				     pte_fn_t fn, void *data)
{
	pud_t *pud;
	unsigned long next;
	int err;

	pud = pud_alloc(mm, pgd, addr);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);
		err = apply_to_pmd_range(mm, pud, addr, next, fn, data);
		if (err)
			break;
	} while (pud++, addr = next, addr != end);
	return err;
}

/*
 * Scan a region of virtual memory, filling in page tables as necessary
 * and calling a provided function on each leaf page table.
 */
int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
			unsigned long size, pte_fn_t fn, void *data)
{
	pgd_t *pgd;
	unsigned long next;
	unsigned long end = addr + size;
	int err;

	BUG_ON(addr >= end);
	pgd = pgd_offset(mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		err = apply_to_pud_range(mm, pgd, addr, next, fn, data);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);

	return err;
}
EXPORT_SYMBOL_GPL(apply_to_page_range);

/*
 * handle_pte_fault chooses page fault handler according to an entry
 * which was read non-atomically.  Before making any commitment, on
 * those architectures or configurations (e.g. i386 with PAE) which
 * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault
 * must check under lock before unmapping the pte and proceeding
 * (but do_wp_page is only called after already making such a check;
 * and do_anonymous_page can safely check later on).
 */
static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
				pte_t *page_table, pte_t orig_pte)
{
	int same = 1;
#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
	if (sizeof(pte_t) > sizeof(unsigned long)) {
		spinlock_t *ptl = pte_lockptr(mm, pmd);
		spin_lock(ptl);
		same = pte_same(*page_table, orig_pte);
		spin_unlock(ptl);
	}
#endif
	pte_unmap(page_table);
	return same;
}

static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
{
	/*
	 * If the source page was a PFN mapping, we don't have
	 * a "struct page" for it. We do a best-effort copy by
	 * just copying from the original user address. If that
	 * fails, we just zero-fill it. Live with it.
	 */
	if (unlikely(!src)) {
		void *kaddr = kmap_atomic(dst);
		void __user *uaddr = (void __user *)(va & PAGE_MASK);

		/*
		 * This really shouldn't fail, because the page is there
		 * in the page tables. But it might just be unreadable,
		 * in which case we just give up and fill the result with
		 * zeroes.
		 */
		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
			clear_page(kaddr);
		kunmap_atomic(kaddr);
		flush_dcache_page(dst);
	} else
		copy_user_highpage(dst, src, va, vma);
}

/*
 * 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.
 *
 * 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 non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), with pte both mapped and locked.
 * We return with mmap_sem still held, but pte unmapped and unlocked.
 */
static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		spinlock_t *ptl, pte_t orig_pte)
	__releases(ptl)
{
	struct page *old_page, *new_page = NULL;
	pte_t entry;
	int ret = 0;
	int page_mkwrite = 0;
	struct page *dirty_page = NULL;
	unsigned long mmun_start = 0;	/* For mmu_notifiers */
	unsigned long mmun_end = 0;	/* For mmu_notifiers */

	old_page = vm_normal_page(vma, address, orig_pte);
	if (!old_page) {
		/*
		 * VM_MIXEDMAP !pfn_valid() case
		 *
		 * We should not cow pages in a shared writeable mapping.
		 * Just mark the pages writable as we can't do any dirty
		 * accounting on raw pfn maps.
		 */
		if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
				     (VM_WRITE|VM_SHARED))
			goto reuse;
		goto gotten;
	}

	/*
	 * Take out anonymous pages first, anonymous shared vmas are
	 * not dirty accountable.
	 */
	if (PageAnon(old_page) && !PageKsm(old_page)) {
		if (!trylock_page(old_page)) {
			page_cache_get(old_page);
			pte_unmap_unlock(page_table, ptl);
			lock_page(old_page);
			page_table = pte_offset_map_lock(mm, pmd, address,
							 &ptl);
			if (!pte_same(*page_table, orig_pte)) {
				unlock_page(old_page);
				goto unlock;
			}
			page_cache_release(old_page);
		}
		if (reuse_swap_page(old_page)) {
			/*
			 * The page is all ours.  Move it to our anon_vma so
			 * the rmap code will not search our parent or siblings.
			 * Protected against the rmap code by the page lock.
			 */
			page_move_anon_rmap(old_page, vma, address);
			unlock_page(old_page);
			goto reuse;
		}
		unlock_page(old_page);
	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
					(VM_WRITE|VM_SHARED))) {
		/*
		 * Only catch write-faults on shared writable pages,
		 * read-only shared pages can get COWed by
		 * get_user_pages(.write=1, .force=1).
		 */
		if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
			struct vm_fault vmf;
			int tmp;

			vmf.virtual_address = (void __user *)(address &
								PAGE_MASK);
			vmf.pgoff = old_page->index;
			vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
			vmf.page = old_page;

			/*
			 * Notify the address space that the page is about to
			 * become writable so that it can prohibit this or wait
			 * for the page to get into an appropriate state.
			 *
			 * We do this without the lock held, so that it can
			 * sleep if it needs to.
			 */
			page_cache_get(old_page);
			pte_unmap_unlock(page_table, ptl);

			tmp = vma->vm_ops->page_mkwrite(vma, &vmf);
			if (unlikely(tmp &
					(VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
				ret = tmp;
				goto unwritable_page;
			}
			if (unlikely(!(tmp & VM_FAULT_LOCKED))) {
				lock_page(old_page);
				if (!old_page->mapping) {
					ret = 0; /* retry the fault */
					unlock_page(old_page);
					goto unwritable_page;
				}
			} else
				VM_BUG_ON(!PageLocked(old_page));

			/*
			 * Since we dropped the lock we need to revalidate
			 * the PTE as someone else may have changed it.  If
			 * they did, we just return, as we can count on the
			 * MMU to tell us if they didn't also make it writable.
			 */
			page_table = pte_offset_map_lock(mm, pmd, address,
							 &ptl);
			if (!pte_same(*page_table, orig_pte)) {
				unlock_page(old_page);
				goto unlock;
			}

			page_mkwrite = 1;
		}
		dirty_page = old_page;
		get_page(dirty_page);

reuse:
		flush_cache_page(vma, address, pte_pfn(orig_pte));
		entry = pte_mkyoung(orig_pte);
		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
		if (ptep_set_access_flags(vma, address, page_table, entry,1))
			update_mmu_cache(vma, address, page_table);
		pte_unmap_unlock(page_table, ptl);
		ret |= VM_FAULT_WRITE;

		if (!dirty_page)
			return ret;

		/*
		 * Yes, Virginia, this is actually required to prevent a race
		 * with clear_page_dirty_for_io() from clearing the page dirty
		 * bit after it clear all dirty ptes, but before a racing
		 * do_wp_page installs a dirty pte.
		 *
		 * __do_fault is protected similarly.
		 */
		if (!page_mkwrite) {
			wait_on_page_locked(dirty_page);
			set_page_dirty_balance(dirty_page, page_mkwrite);
			/* file_update_time outside page_lock */
			if (vma->vm_file)
				file_update_time(vma->vm_file);
		}
		put_page(dirty_page);
		if (page_mkwrite) {
			struct address_space *mapping = dirty_page->mapping;

			set_page_dirty(dirty_page);
			unlock_page(dirty_page);
			page_cache_release(dirty_page);
			if (mapping)	{
				/*
				 * Some device drivers do not set page.mapping
				 * but still dirty their pages
				 */
				balance_dirty_pages_ratelimited(mapping);
			}
		}

		return ret;
	}

	/*
	 * Ok, we need to copy. Oh, well..
	 */
	page_cache_get(old_page);
gotten:
	pte_unmap_unlock(page_table, ptl);

	if (unlikely(anon_vma_prepare(vma)))
		goto oom;

	if (is_zero_pfn(pte_pfn(orig_pte))) {
		new_page = alloc_zeroed_user_highpage_movable(vma, address);
		if (!new_page)
			goto oom;
	} else {
		new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
		if (!new_page)
			goto oom;
		cow_user_page(new_page, old_page, address, vma);
	}
	__SetPageUptodate(new_page);

	if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
		goto oom_free_new;

	mmun_start  = address & PAGE_MASK;
	mmun_end    = mmun_start + PAGE_SIZE;
	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

	/*
	 * Re-check the pte - we dropped the lock
	 */
	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (likely(pte_same(*page_table, orig_pte))) {
		if (old_page) {
			if (!PageAnon(old_page)) {
				dec_mm_counter_fast(mm, MM_FILEPAGES);
				inc_mm_counter_fast(mm, MM_ANONPAGES);
			}
		} else
			inc_mm_counter_fast(mm, MM_ANONPAGES);
		flush_cache_page(vma, address, pte_pfn(orig_pte));
		entry = mk_pte(new_page, vma->vm_page_prot);
		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
		/*
		 * Clear the pte entry and flush it first, before updating the
		 * pte with the new entry. This will avoid a race condition
		 * seen in the presence of one thread doing SMC and another
		 * thread doing COW.
		 */
		ptep_clear_flush(vma, address, page_table);
		page_add_new_anon_rmap(new_page, vma, address);
		/*
		 * We call the notify macro here because, when using secondary
		 * mmu page tables (such as kvm shadow page tables), we want the
		 * new page to be mapped directly into the secondary page table.
		 */
		set_pte_at_notify(mm, address, page_table, entry);
		update_mmu_cache(vma, address, page_table);
		if (old_page) {
			/*
			 * Only after switching the pte to the new page may
			 * we remove the mapcount here. Otherwise another
			 * process may come and find the rmap count decremented
			 * before the pte is switched to the new page, and
			 * "reuse" the old page writing into it while our pte
			 * here still points into it and can be read by other
			 * threads.
			 *
			 * The critical issue is to order this
			 * page_remove_rmap with the ptp_clear_flush above.
			 * Those stores are ordered by (if nothing else,)
			 * the barrier present in the atomic_add_negative
			 * in page_remove_rmap.
			 *
			 * Then the TLB flush in ptep_clear_flush ensures that
			 * no process can access the old page before the
			 * decremented mapcount is visible. And the old page
			 * cannot be reused until after the decremented
			 * mapcount is visible. So transitively, TLBs to
			 * old page will be flushed before it can be reused.
			 */
			page_remove_rmap(old_page);
		}

		/* Free the old page.. */
		new_page = old_page;
		ret |= VM_FAULT_WRITE;
	} else
		mem_cgroup_uncharge_page(new_page);

	if (new_page)
		page_cache_release(new_page);
unlock:
	pte_unmap_unlock(page_table, ptl);
	if (mmun_end > mmun_start)
		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
	if (old_page) {
		/*
		 * Don't let another task, with possibly unlocked vma,
		 * keep the mlocked page.
		 */
		if ((ret & VM_FAULT_WRITE) && (vma->vm_flags & VM_LOCKED)) {
			lock_page(old_page);	/* LRU manipulation */
			munlock_vma_page(old_page);
			unlock_page(old_page);
		}
		page_cache_release(old_page);
	}
	return ret;
oom_free_new:
	page_cache_release(new_page);
oom:
	if (old_page) {
		if (page_mkwrite) {
			unlock_page(old_page);
			page_cache_release(old_page);
		}
		page_cache_release(old_page);
	}
	return VM_FAULT_OOM;

unwritable_page:
	page_cache_release(old_page);
	return ret;
}

static void unmap_mapping_range_vma(struct vm_area_struct *vma,
		unsigned long start_addr, unsigned long end_addr,
		struct zap_details *details)
{
	zap_page_range_single(vma, start_addr, end_addr - start_addr, details);
}

static inline void unmap_mapping_range_tree(struct rb_root *root,
					    struct zap_details *details)
{
	struct vm_area_struct *vma;
	pgoff_t vba, vea, zba, zea;

	vma_interval_tree_foreach(vma, root,
			details->first_index, details->last_index) {

		vba = vma->vm_pgoff;
		vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
		/* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
		zba = details->first_index;
		if (zba < vba)
			zba = vba;
		zea = details->last_index;
		if (zea > vea)
			zea = vea;

		unmap_mapping_range_vma(vma,
			((zba - vba) << PAGE_SHIFT) + vma->vm_start,
			((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
				details);
	}
}

static inline void unmap_mapping_range_list(struct list_head *head,
					    struct zap_details *details)
{
	struct vm_area_struct *vma;

	/*
	 * In nonlinear VMAs there is no correspondence between virtual address
	 * offset and file offset.  So we must perform an exhaustive search
	 * across *all* the pages in each nonlinear VMA, not just the pages
	 * whose virtual address lies outside the file truncation point.
	 */
	list_for_each_entry(vma, head, shared.nonlinear) {
		details->nonlinear_vma = vma;
		unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details);
	}
}

/**
 * unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file.
 * @mapping: the address space containing mmaps to be unmapped.
 * @holebegin: byte in first page to unmap, relative to the start of
 * the underlying file.  This will be rounded down to a PAGE_SIZE
 * boundary.  Note that this is different from truncate_pagecache(), which
 * must keep the partial page.  In contrast, we must get rid of
 * partial pages.
 * @holelen: size of prospective hole in bytes.  This will be rounded
 * up to a PAGE_SIZE boundary.  A holelen of zero truncates to the
 * end of the file.
 * @even_cows: 1 when truncating a file, unmap even private COWed pages;
 * but 0 when invalidating pagecache, don't throw away private data.
 */
void unmap_mapping_range(struct address_space *mapping,
		loff_t const holebegin, loff_t const holelen, int even_cows)
{
	struct zap_details details;
	pgoff_t hba = holebegin >> PAGE_SHIFT;
	pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;

	/* Check for overflow. */
	if (sizeof(holelen) > sizeof(hlen)) {
		long long holeend =
			(holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
		if (holeend & ~(long long)ULONG_MAX)
			hlen = ULONG_MAX - hba + 1;
	}

	details.check_mapping = even_cows? NULL: mapping;
	details.nonlinear_vma = NULL;
	details.first_index = hba;
	details.last_index = hba + hlen - 1;
	if (details.last_index < details.first_index)
		details.last_index = ULONG_MAX;


	mutex_lock(&mapping->i_mmap_mutex);
	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
		unmap_mapping_range_tree(&mapping->i_mmap, &details);
	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
	mutex_unlock(&mapping->i_mmap_mutex);
}
EXPORT_SYMBOL(unmap_mapping_range);

/*
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with mmap_sem still held, but pte unmapped and unlocked.
 */
static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		unsigned int flags, pte_t orig_pte)
{
	spinlock_t *ptl;
	struct page *page, *swapcache = NULL;
	swp_entry_t entry;
	pte_t pte;
	int locked;
	struct mem_cgroup *ptr;
	int exclusive = 0;
	int ret = 0;

	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
		goto out;

	entry = pte_to_swp_entry(orig_pte);
	if (unlikely(non_swap_entry(entry))) {
		if (is_migration_entry(entry)) {
			migration_entry_wait(mm, pmd, address);
		} else if (is_hwpoison_entry(entry)) {
			ret = VM_FAULT_HWPOISON;
		} else {
			print_bad_pte(vma, address, orig_pte, NULL);
			ret = VM_FAULT_SIGBUS;
		}
		goto out;
	}
	delayacct_set_flag(DELAYACCT_PF_SWAPIN);
	page = lookup_swap_cache(entry);
	if (!page) {
		page = swapin_readahead(entry,
					GFP_HIGHUSER_MOVABLE, vma, address);
		if (!page) {
			/*
			 * Back out if somebody else faulted in this pte
			 * while we released the pte lock.
			 */
			page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
			if (likely(pte_same(*page_table, orig_pte)))
				ret = VM_FAULT_OOM;
			delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
			goto unlock;
		}

		/* Had to read the page from swap area: Major fault */
		ret = VM_FAULT_MAJOR;
		count_vm_event(PGMAJFAULT);
		mem_cgroup_count_vm_event(mm, PGMAJFAULT);
	} else if (PageHWPoison(page)) {
		/*
		 * hwpoisoned dirty swapcache pages are kept for killing
		 * owner processes (which may be unknown at hwpoison time)
		 */
		ret = VM_FAULT_HWPOISON;
		delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
		goto out_release;
	}

	locked = lock_page_or_retry(page, mm, flags);

	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
	if (!locked) {
		ret |= VM_FAULT_RETRY;
		goto out_release;
	}

	/*
	 * Make sure try_to_free_swap or reuse_swap_page or swapoff did not
	 * release the swapcache from under us.  The page pin, and pte_same
	 * test below, are not enough to exclude that.  Even if it is still
	 * swapcache, we need to check that the page's swap has not changed.