memory.c

 * 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_file_page
 * 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 and do_no_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;
}

/*
 * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
 * servicing faults for write access.  In the normal case, do always want
 * pte_mkwrite.  But get_user_pages can cause write faults for mappings
 * that do not have writing enabled, when used by access_process_vm.
 */
static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
	if (likely(vma->vm_flags & VM_WRITE))
		pte = pte_mkwrite(pte);
	return pte;
}

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, KM_USER0);
		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))
			memset(kaddr, 0, PAGE_SIZE);
		kunmap_atomic(kaddr, KM_USER0);
		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)
{
	struct page *old_page, *new_page;
	pte_t entry;
	int reuse = 0, ret = 0;
	int page_mkwrite = 0;
	struct page *dirty_page = NULL;

	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);
				page_cache_release(old_page);
				goto unlock;
			}
			page_cache_release(old_page);
		}
		reuse = reuse_swap_page(old_page);
		if (reuse)
			/*
			 * 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);
	} 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);
				page_cache_release(old_page);
				goto unlock;
			}

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

	if (reuse) {
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);
		ret |= VM_FAULT_WRITE;
		goto unlock;
	}

	/*
	 * 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);

	/*
	 * Don't let another task, with possibly unlocked vma,
	 * keep the mlocked page.
	 */
	if ((vma->vm_flags & VM_LOCKED) && old_page) {
		lock_page(old_page);	/* for LRU manipulation */
		clear_page_mlock(old_page);
		unlock_page(old_page);
	}

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

	/*
	 * 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);
	if (old_page)
		page_cache_release(old_page);
unlock:
	pte_unmap_unlock(page_table, ptl);
	if (dirty_page) {
		/*
		 * 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_no_page is protected similarly.
		 */
		if (!page_mkwrite) {
			wait_on_page_locked(dirty_page);
			set_page_dirty_balance(dirty_page, page_mkwrite);
		}
		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);
			}
		}

		/* file_update_time outside page_lock */
		if (vma->vm_file)
			file_update_time(vma->vm_file);
	}
	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;
}

/*
 * Helper functions for unmap_mapping_range().
 *
 * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
 *
 * We have to restart searching the prio_tree whenever we drop the lock,
 * since the iterator is only valid while the lock is held, and anyway
 * a later vma might be split and reinserted earlier while lock dropped.
 *
 * The list of nonlinear vmas could be handled more efficiently, using
 * a placeholder, but handle it in the same way until a need is shown.
 * It is important to search the prio_tree before nonlinear list: a vma
 * may become nonlinear and be shifted from prio_tree to nonlinear list
 * while the lock is dropped; but never shifted from list to prio_tree.
 *
 * In order to make forward progress despite restarting the search,
 * vm_truncate_count is used to mark a vma as now dealt with, so we can
 * quickly skip it next time around.  Since the prio_tree search only
 * shows us those vmas affected by unmapping the range in question, we
 * can't efficiently keep all vmas in step with mapping->truncate_count:
 * so instead reset them all whenever it wraps back to 0 (then go to 1).
 * mapping->truncate_count and vma->vm_truncate_count are protected by
 * i_mmap_lock.
 *
 * In order to make forward progress despite repeatedly restarting some
 * large vma, note the restart_addr from unmap_vmas when it breaks out:
 * and restart from that address when we reach that vma again.  It might
 * have been split or merged, shrunk or extended, but never shifted: so
 * restart_addr remains valid so long as it remains in the vma's range.
 * unmap_mapping_range forces truncate_count to leap over page-aligned
 * values so we can save vma's restart_addr in its truncate_count field.
 */
#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))

static void reset_vma_truncate_counts(struct address_space *mapping)
{
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;

	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
		vma->vm_truncate_count = 0;
	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
		vma->vm_truncate_count = 0;
}

static int unmap_mapping_range_vma(struct vm_area_struct *vma,
		unsigned long start_addr, unsigned long end_addr,
		struct zap_details *details)
{
	unsigned long restart_addr;
	int need_break;

	/*
	 * files that support invalidating or truncating portions of the
	 * file from under mmaped areas must have their ->fault function
	 * return a locked page (and set VM_FAULT_LOCKED in the return).
	 * This provides synchronisation against concurrent unmapping here.
	 */

again:
	restart_addr = vma->vm_truncate_count;
	if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
		start_addr = restart_addr;
		if (start_addr >= end_addr) {
			/* Top of vma has been split off since last time */
			vma->vm_truncate_count = details->truncate_count;
			return 0;
		}
	}

	restart_addr = zap_page_range(vma, start_addr,
					end_addr - start_addr, details);
	need_break = need_resched() || spin_needbreak(details->i_mmap_lock);

	if (restart_addr >= end_addr) {
		/* We have now completed this vma: mark it so */
		vma->vm_truncate_count = details->truncate_count;
		if (!need_break)
			return 0;
	} else {
		/* Note restart_addr in vma's truncate_count field */
		vma->vm_truncate_count = restart_addr;
		if (!need_break)
			goto again;
	}

	spin_unlock(details->i_mmap_lock);
	cond_resched();
	spin_lock(details->i_mmap_lock);
	return -EINTR;
}

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

restart:
	vma_prio_tree_foreach(vma, &iter, root,
			details->first_index, details->last_index) {
		/* Skip quickly over those we have already dealt with */
		if (vma->vm_truncate_count == details->truncate_count)
			continue;

		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;

		if (unmap_mapping_range_vma(vma,
			((zba - vba) << PAGE_SHIFT) + vma->vm_start,
			((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
				details) < 0)
			goto restart;
	}
}

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.
	 */
restart:
	list_for_each_entry(vma, head, shared.vm_set.list) {
		/* Skip quickly over those we have already dealt with */
		if (vma->vm_truncate_count == details->truncate_count)
			continue;
		details->nonlinear_vma = vma;
		if (unmap_mapping_range_vma(vma, vma->vm_start,
					vma->vm_end, details) < 0)
			goto restart;
	}
}

/**
 * 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;
	details.i_mmap_lock = &mapping->i_mmap_lock;

	spin_lock(&mapping->i_mmap_lock);

	/* Protect against endless unmapping loops */
	mapping->truncate_count++;
	if (unlikely(is_restart_addr(mapping->truncate_count))) {
		if (mapping->truncate_count == 0)
			reset_vma_truncate_counts(mapping);
		mapping->truncate_count++;
	}
	details.truncate_count = mapping->truncate_count;

	if (unlikely(!prio_tree_empty(&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);
	spin_unlock(&mapping->i_mmap_lock);
}
EXPORT_SYMBOL(unmap_mapping_range);

int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
{
	struct address_space *mapping = inode->i_mapping;

	/*
	 * If the underlying filesystem is not going to provide
	 * a way to truncate a range of blocks (punch a hole) -
	 * we should return failure right now.
	 */
	if (!inode->i_op->truncate_range)
		return -ENOSYS;

	mutex_lock(&inode->i_mutex);
	down_write(&inode->i_alloc_sem);
	unmap_mapping_range(mapping, offset, (end - offset), 1);
	truncate_inode_pages_range(mapping, offset, end);
	unmap_mapping_range(mapping, offset, (end - offset), 1);
	inode->i_op->truncate_range(inode, offset, end);
	up_write(&inode->i_alloc_sem);
	mutex_unlock(&inode->i_mutex);

	return 0;
}

/*
 * 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;
	swp_entry_t entry;
	pte_t pte;
	struct mem_cgroup *ptr = NULL;
	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) {
		grab_swap_token(mm); /* Contend for token _before_ read-in */
		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);
	} 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;
	}

	lock_page(page);
	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);

	page = ksm_might_need_to_copy(page, vma, address);
	if (!page) {
		ret = VM_FAULT_OOM;
		goto out;
	}

	if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
		ret = VM_FAULT_OOM;
		goto out_page;
	}

	/*
	 * Back out if somebody else already faulted in this pte.
	 */
	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (unlikely(!pte_same(*page_table, orig_pte)))
		goto out_nomap;

	if (unlikely(!PageUptodate(page))) {
		ret = VM_FAULT_SIGBUS;
		goto out_nomap;
	}

	/*
	 * The page isn't present yet, go ahead with the fault.
	 *
	 * Be careful about the sequence of operations here.
	 * To get its accounting right, reuse_swap_page() must be called
	 * while the page is counted on swap but not yet in mapcount i.e.
	 * before page_add_anon_rmap() and swap_free(); try_to_free_swap()
	 * must be called after the swap_free(), or it will never succeed.
	 * Because delete_from_swap_page() may be called by reuse_swap_page(),
	 * mem_cgroup_commit_charge_swapin() may not be able to find swp_entry
	 * in page->private. In this case, a record in swap_cgroup  is silently
	 * discarded at swap_free().
	 */

	inc_mm_counter_fast(mm, MM_ANONPAGES);
	dec_mm_counter_fast(mm, MM_SWAPENTS);
	pte = mk_pte(page, vma->vm_page_prot);
	if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) {
		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
		flags &= ~FAULT_FLAG_WRITE;
		ret |= VM_FAULT_WRITE;
		exclusive = 1;
	}
	flush_icache_page(vma, page);
	set_pte_at(mm, address, page_table, pte);
	do_page_add_anon_rmap(page, vma, address, exclusive);
	/* It's better to call commit-charge after rmap is established */
	mem_cgroup_commit_charge_swapin(page, ptr);

	swap_free(entry);
	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
		try_to_free_swap(page);
	unlock_page(page);

	if (flags & FAULT_FLAG_WRITE) {
		ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte);
		if (ret & VM_FAULT_ERROR)
			ret &= VM_FAULT_ERROR;
		goto out;
	}

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, address, page_table);
unlock:
	pte_unmap_unlock(page_table, ptl);
out:
	return ret;
out_nomap:
	mem_cgroup_cancel_charge_swapin(ptr);
	pte_unmap_unlock(page_table, ptl);
out_page:
	unlock_page(page);
out_release:
	page_cache_release(page);
	return ret;
}

/*
 * This is like a special single-page "expand_{down|up}wards()",
 * except we must first make sure that 'address{-|+}PAGE_SIZE'
 * doesn't hit another vma.
 */
static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
{
	address &= PAGE_MASK;
	if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
		struct vm_area_struct *prev = vma->vm_prev;

		/*
		 * Is there a mapping abutting this one below?
		 *
		 * That's only ok if it's the same stack mapping
		 * that has gotten split..
		 */
		if (prev && prev->vm_end == address)
			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;

		expand_stack(vma, address - PAGE_SIZE);
	}
	if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
		struct vm_area_struct *next = vma->vm_next;

		/* As VM_GROWSDOWN but s/below/above/ */
		if (next && next->vm_start == address + PAGE_SIZE)
			return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;

		expand_upwards(vma, address + PAGE_SIZE);
	}
	return 0;
}

/*
 * 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_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		unsigned int flags)
{
	struct page *page;
	spinlock_t *ptl;
	pte_t entry;

	pte_unmap(page_table);

	/* Check if we need to add a guard page to the stack */
	if (check_stack_guard_page(vma, address) < 0)
		return VM_FAULT_SIGBUS;

	/* Use the zero-page for reads */
	if (!(flags & FAULT_FLAG_WRITE)) {
		entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
						vma->vm_page_prot));
		page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
		if (!pte_none(*page_table))
			goto unlock;
		goto setpte;
	}

	/* Allocate our own private page. */
	if (unlikely(anon_vma_prepare(vma)))
		goto oom;
	page = alloc_zeroed_user_highpage_movable(vma, address);
	if (!page)
		goto oom;
	__SetPageUptodate(page);

	if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))
		goto oom_free_page;

	entry = mk_pte(page, vma->vm_page_prot);
	if (vma->vm_flags & VM_WRITE)
		entry = pte_mkwrite(pte_mkdirty(entry));

	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (!pte_none(*page_table))
		goto release;

	inc_mm_counter_fast(mm, MM_ANONPAGES);
	page_add_new_anon_rmap(page, vma, address);
setpte:
	set_pte_at(mm, address, page_table, entry);

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, address, page_table);
unlock:
	pte_unmap_unlock(page_table, ptl);
	return 0;
release:
	mem_cgroup_uncharge_page(page);
	page_cache_release(page);
	goto unlock;
oom_free_page:
	page_cache_release(page);
oom:
	return VM_FAULT_OOM;
}

/*
 * __do_fault() tries to create a new page mapping. It aggressively
 * tries to share with existing pages, but makes a separate copy if
 * the FAULT_FLAG_WRITE is set in the flags parameter in order to avoid
 * the next page fault.
 *
 * As this is called only for pages that do not currently exist, we
 * do not need to flush old virtual caches or the TLB.
 *
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte neither mapped nor locked.
 * We return with mmap_sem still held, but pte unmapped and unlocked.
 */
static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pmd_t *pmd,
		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
{
	pte_t *page_table;
	spinlock_t *ptl;
	struct page *page;
	pte_t entry;
	int anon = 0;
	int charged = 0;
	struct page *dirty_page = NULL;
	struct vm_fault vmf;
	int ret;
	int page_mkwrite = 0;

	vmf.virtual_address = (void __user *)(address & PAGE_MASK);
	vmf.pgoff = pgoff;
	vmf.flags = flags;
	vmf.page = NULL;

	ret = vma->vm_ops->fault(vma, &vmf);
	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
		return ret;

	if (unlikely(PageHWPoison(vmf.page))) {
		if (ret & VM_FAULT_LOCKED)
			unlock_page(vmf.page);
		return VM_FAULT_HWPOISON;
	}

	/*
	 * For consistency in subsequent calls, make the faulted page always
	 * locked.
	 */
	if (unlikely(!(ret & VM_FAULT_LOCKED)))
		lock_page(vmf.page);
	else
		VM_BUG_ON(!PageLocked(vmf.page));

	/*
	 * Should we do an early C-O-W break?
	 */
	page = vmf.page;
	if (flags & FAULT_FLAG_WRITE) {
		if (!(vma->vm_flags & VM_SHARED)) {
			anon = 1;
			if (unlikely(anon_vma_prepare(vma))) {
				ret = VM_FAULT_OOM;
				goto out;
			}
			page = alloc_page_vma(GFP_HIGHUSER_MOVABLE,
						vma, address);
			if (!page) {
				ret = VM_FAULT_OOM;
				goto out;
			}
			if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) {
				ret = VM_FAULT_OOM;
				page_cache_release(page);
				goto out;
			}
			charged = 1;
			/*
			 * Don't let another task, with possibly unlocked vma,
			 * keep the mlocked page.
			 */
			if (vma->vm_flags & VM_LOCKED)
				clear_page_mlock(vmf.page);
			copy_user_highpage(page, vmf.page, address, vma);
			__SetPageUptodate(page);
		} else {
			/*
			 * If the page will be shareable, see if the backing
			 * address space wants to know that the page is about
			 * to become writable
			 */
			if (vma->vm_ops->page_mkwrite) {
				int tmp;

				unlock_page(page);
				vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
				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(page);
					if (!page->mapping) {
						ret = 0; /* retry the fault */
						unlock_page(page);
						goto unwritable_page;
					}
				} else
					VM_BUG_ON(!PageLocked(page));
				page_mkwrite = 1;
			}
		}

	}

	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);

	/*
	 * This silly early PAGE_DIRTY setting removes a race
	 * due to the bad i386 page protection. But it's valid
	 * for other architectures too.
	 *
	 * Note that if FAULT_FLAG_WRITE is set, we either now have
	 * an exclusive copy of the page, or this is a shared mapping,
	 * so we can make it writable and dirty to avoid having to
	 * handle that later.
	 */
	/* Only go through if we didn't race with anybody else... */
	if (likely(pte_same(*page_table, orig_pte))) {
		flush_icache_page(vma, page);
		entry = mk_pte(page, vma->vm_page_prot);
		if (flags & FAULT_FLAG_WRITE)
			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
		if (anon) {
			inc_mm_counter_fast(mm, MM_ANONPAGES);
			page_add_new_anon_rmap(page, vma, address);
		} else {