/*
 * If the page can not be invalidated, it is moved to the
 * inactive list to speed up its reclaim.  It is moved to the
 * head of the list, rather than the tail, to give the flusher
 * threads some time to write it out, as this is much more
 * effective than the single-page writeout from reclaim.
 *
 * If the page isn't page_mapped and dirty/writeback, the page
 * could reclaim asap using PG_reclaim.
 *
 * 1. active, mapped page -> none
 * 2. active, dirty/writeback page -> inactive, head, PG_reclaim
 * 3. inactive, mapped page -> none
 * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim
 * 5. inactive, clean -> inactive, tail
 * 6. Others -> none
 *
 * In 4, why it moves inactive's head, the VM expects the page would
 * be write it out by flusher threads as this is much more effective
 * than the single-page writeout from reclaim.
 */
static void lru_deactivate_fn(struct page *page, void *arg)
{
	int lru, file;
	bool active;
	struct zone *zone = page_zone(page);

	if (!PageLRU(page))
		return;

	if (PageUnevictable(page))
		return;

	/* Some processes are using the page */
	if (page_mapped(page))
		return;

	active = PageActive(page);

	file = page_is_file_cache(page);
	lru = page_lru_base_type(page);
	del_page_from_lru_list(zone, page, lru + active);
	ClearPageActive(page);
	ClearPageReferenced(page);
	add_page_to_lru_list(zone, page, lru);

	if (PageWriteback(page) || PageDirty(page)) {
		/*
		 * PG_reclaim could be raced with end_page_writeback
		 * It can make readahead confusing.  But race window
		 * is _really_ small and  it's non-critical problem.
		 */
		SetPageReclaim(page);
	} else {
		/*
		 * The page's writeback ends up during pagevec
		 * We moves tha page into tail of inactive.
		 */
		list_move_tail(&page->lru, &zone->lru[lru].list);
		mem_cgroup_rotate_reclaimable_page(page);
		__count_vm_event(PGROTATED);
	}

	if (active)
		__count_vm_event(PGDEACTIVATE);
	update_page_reclaim_stat(zone, page, file, 0);
}

static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
		size_t nr_pages)
{
	struct logfs_super *super = logfs_super(sb);
	struct address_space *mapping = super->s_mapping_inode->i_mapping;
	struct bio *bio;
	struct page *page;
	unsigned int max_pages;
	int i;

	max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev));

	bio = bio_alloc(GFP_NOFS, max_pages);
	BUG_ON(!bio);

	for (i = 0; i < nr_pages; i++) {
		if (i >= max_pages) {
			/* Block layer cannot split bios :( */
			bio->bi_vcnt = i;
			bio->bi_idx = 0;
			bio->bi_size = i * PAGE_SIZE;
			bio->bi_bdev = super->s_bdev;
			bio->bi_sector = ofs >> 9;
			bio->bi_private = sb;
			bio->bi_end_io = writeseg_end_io;
			atomic_inc(&super->s_pending_writes);
			submit_bio(WRITE, bio);

			ofs += i * PAGE_SIZE;
			index += i;
			nr_pages -= i;
			i = 0;

			bio = bio_alloc(GFP_NOFS, max_pages);
			BUG_ON(!bio);
		}
		page = find_lock_page(mapping, index + i);
		BUG_ON(!page);
		bio->bi_io_vec[i].bv_page = page;
		bio->bi_io_vec[i].bv_len = PAGE_SIZE;
		bio->bi_io_vec[i].bv_offset = 0;

		BUG_ON(PageWriteback(page));
		set_page_writeback(page);
		unlock_page(page);
	}

/*
 * This must be called only on pages that have
 * been verified to be in the swap cache.
 */
void __delete_from_swap_cache(struct page *page)
{
    swp_entry_t entry;
    struct address_space *address_space;

    VM_BUG_ON_PAGE(!PageLocked(page), page);
    VM_BUG_ON_PAGE(!PageSwapCache(page), page);
    VM_BUG_ON_PAGE(PageWriteback(page), page);

    entry.val = page_private(page);
    address_space = swap_address_space(entry);
    radix_tree_delete(&address_space->page_tree, page_private(page));
    set_page_private(page, 0);
    ClearPageSwapCache(page);
    address_space->nrpages--;
    __dec_zone_page_state(page, NR_FILE_PAGES);
    INC_CACHE_INFO(del_total);
}

/**
 * Implements Linux VM address_space::invalidatepage() method. This method is
 * called when the page is truncate from a file, either as a result of
 * explicit truncate, or when inode is removed from memory (as a result of
 * final iput(), umount, or memory pressure induced icache shrinking).
 *
 * [0, offset] bytes of the page remain valid (this is for a case of not-page
 * aligned truncate). Lustre leaves partially truncated page in the cache,
 * relying on struct inode::i_size to limit further accesses.
 */
static void ll_invalidatepage(struct page *vmpage,
#ifdef HAVE_INVALIDATE_RANGE
                              unsigned int offset, unsigned int length
#else
                              unsigned long offset
#endif
                             )
{
    struct inode     *inode;
    struct lu_env    *env;
    struct cl_page   *page;
    struct cl_object *obj;

    LASSERT(PageLocked(vmpage));
    LASSERT(!PageWriteback(vmpage));

    /*
     * It is safe to not check anything in invalidatepage/releasepage
     * below because they are run with page locked and all our io is
     * happening with locked page too
     */
#ifdef HAVE_INVALIDATE_RANGE
    if (offset == 0 && length == PAGE_SIZE) {
#else
    if (offset == 0) {
#endif
        /* See the comment in ll_releasepage() */
        env = cl_env_percpu_get();
        LASSERT(!IS_ERR(env));

        inode = vmpage->mapping->host;
        obj = ll_i2info(inode)->lli_clob;
        if (obj != NULL) {
            page = cl_vmpage_page(vmpage, obj);
            if (page != NULL) {
                cl_page_delete(env, page);
                cl_page_put(env, page);
            }
        } else
            LASSERT(vmpage->private == 0);

        cl_env_percpu_put(env);
    }
}

/*
 * write out a page to a file
 */
static int write_page(struct bitmap *bitmap, struct page *page, int wait)
{
    int ret = -ENOMEM;

    if (bitmap->file == NULL)
        return write_sb_page(bitmap->mddev, bitmap->offset, page, wait);

    flush_dcache_page(page); /* make sure visible to anyone reading the file */

    if (wait)
        lock_page(page);
    else {
        if (TestSetPageLocked(page))
            return -EAGAIN; /* already locked */
        if (PageWriteback(page)) {
            unlock_page(page);
            return -EAGAIN;
        }
    }

    ret = page->mapping->a_ops->prepare_write(bitmap->file, page, 0, PAGE_SIZE);
    if (!ret)
        ret = page->mapping->a_ops->commit_write(bitmap->file, page, 0,
                PAGE_SIZE);
    if (ret) {
        unlock_page(page);
        return ret;
    }

    set_page_dirty(page); /* force it to be written out */

    if (!wait) {
        /* add to list to be waited for by daemon */
        struct page_list *item = mempool_alloc(bitmap->write_pool, GFP_NOIO);
        item->page = page;
        get_page(page);
        spin_lock(&bitmap->write_lock);
        list_add(&item->list, &bitmap->complete_pages);
        spin_unlock(&bitmap->write_lock);
        md_wakeup_thread(bitmap->writeback_daemon);
    }
    return write_one_page(page, wait);
}

/**
 * nilfs_copy_page -- copy the page with buffers
 * @dst: destination page
 * @src: source page
 * @copy_dirty: flag whether to copy dirty states on the page's buffer heads.
 *
 * This function is for both data pages and btnode pages.  The dirty flag
 * should be treated by caller.  The page must not be under i/o.
 * Both src and dst page must be locked
 */
static void nilfs_copy_page(struct page *dst, struct page *src, int copy_dirty)
{
	struct buffer_head *dbh, *dbufs, *sbh, *sbufs;
	unsigned long mask = NILFS_BUFFER_INHERENT_BITS;

	BUG_ON(PageWriteback(dst));

	sbh = sbufs = page_buffers(src);
	if (!page_has_buffers(dst))
		create_empty_buffers(dst, sbh->b_size, 0);

	if (copy_dirty)
		mask |= BIT(BH_Dirty);

	dbh = dbufs = page_buffers(dst);
	do {
		lock_buffer(sbh);
		lock_buffer(dbh);
		dbh->b_state = sbh->b_state & mask;
		dbh->b_blocknr = sbh->b_blocknr;
		dbh->b_bdev = sbh->b_bdev;
		sbh = sbh->b_this_page;
		dbh = dbh->b_this_page;
	} while (dbh != dbufs);

	copy_highpage(dst, src);

	if (PageUptodate(src) && !PageUptodate(dst))
		SetPageUptodate(dst);
	else if (!PageUptodate(src) && PageUptodate(dst))
		ClearPageUptodate(dst);
	if (PageMappedToDisk(src) && !PageMappedToDisk(dst))
		SetPageMappedToDisk(dst);
	else if (!PageMappedToDisk(src) && PageMappedToDisk(dst))
		ClearPageMappedToDisk(dst);

	do {
		unlock_buffer(sbh);
		unlock_buffer(dbh);
		sbh = sbh->b_this_page;
		dbh = dbh->b_this_page;
	} while (dbh != dbufs);
}

/*
 * invalidate part or all of a page
 */
static void afs_file_invalidatepage(struct page *page, unsigned long offset)
{
	_enter("{%lu},%lu", page->index, offset);

	BUG_ON(!PageLocked(page));

	if (PagePrivate(page)) {
		/* We release buffers only if the entire page is being
		 * invalidated.
		 * The get_block cached value has been unconditionally
		 * invalidated, so real IO is not possible anymore.
		 */
		if (offset == 0 && !PageWriteback(page))
			page->mapping->a_ops->releasepage(page, 0);
	}

	_leave("");

} /* end afs_file_invalidatepage() */

int
zpl_putpage(struct page *pp, struct writeback_control *wbc, void *data)
{
	struct address_space *mapping = data;

	ASSERT(PageLocked(pp));
	ASSERT(!PageWriteback(pp));
	ASSERT(!(current->flags & PF_NOFS));

	/*
	 * Annotate this call path with a flag that indicates that it is
	 * unsafe to use KM_SLEEP during memory allocations due to the
	 * potential for a deadlock.  KM_PUSHPAGE should be used instead.
	 */
	current->flags |= PF_NOFS;
	(void) zfs_putpage(mapping->host, pp, wbc);
	current->flags &= ~PF_NOFS;

	return (0);
}

/**
 * Implements Linux VM address_space::invalidatepage() method. This method is
 * called when the page is truncate from a file, either as a result of
 * explicit truncate, or when inode is removed from memory (as a result of
 * final iput(), umount, or memory pressure induced icache shrinking).
 *
 * [0, offset] bytes of the page remain valid (this is for a case of not-page
 * aligned truncate). Lustre leaves partially truncated page in the cache,
 * relying on struct inode::i_size to limit further accesses.
 */
static int cl_invalidatepage(struct page *vmpage, unsigned long offset)
{
        struct inode     *inode;
        struct lu_env    *env;
        struct cl_page   *page;
        struct cl_object *obj;

        int result;
        int refcheck;

        LASSERT(PageLocked(vmpage));
        LASSERT(!PageWriteback(vmpage));

        /*
         * It is safe to not check anything in invalidatepage/releasepage
         * below because they are run with page locked and all our io is
         * happening with locked page too
         */
        result = 0;
        if (offset == 0) {
                env = cl_env_get(&refcheck);
                if (!IS_ERR(env)) {
                        inode = vmpage->mapping->host;
                        obj = ll_i2info(inode)->lli_clob;
                        if (obj != NULL) {
                                page = cl_vmpage_page(vmpage, obj);
                                if (page != NULL) {
                                        lu_ref_add(&page->cp_reference,
                                                   "delete", vmpage);
                                        cl_page_delete(env, page);
                                        result = 1;
                                        lu_ref_del(&page->cp_reference,
                                                   "delete", vmpage);
                                        cl_page_put(env, page);
                                }
                        } else
                                LASSERT(vmpage->private == 0);
                        cl_env_put(env, &refcheck);
                }

/*
 * This must be called only on pages that have
 * been verified to be in the swap cache.
 */
void __delete_from_swap_cache(struct page *page)
{
	struct address_space *address_space;
	int i, nr = hpage_nr_pages(page);
	swp_entry_t entry;
	pgoff_t idx;

	VM_BUG_ON_PAGE(!PageLocked(page), page);
	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
	VM_BUG_ON_PAGE(PageWriteback(page), page);

	entry.val = page_private(page);
	address_space = swap_address_space(entry);
	idx = swp_offset(entry);
	for (i = 0; i < nr; i++) {
		radix_tree_delete(&address_space->page_tree, idx + i);
		set_page_private(page + i, 0);
	}
	ClearPageSwapCache(page);
	address_space->nrpages -= nr;
	__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
	ADD_CACHE_INFO(del_total, nr);
}

/**
 * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
 * @mapping: the address_space which holds the pages to invalidate
 * @start: the offset 'from' which to invalidate
 * @end: the offset 'to' which to invalidate (inclusive)
 *
 * This function only removes the unlocked pages, if you want to
 * remove all the pages of one inode, you must call truncate_inode_pages.
 *
 * invalidate_mapping_pages() will not block on IO activity. It will not
 * invalidate pages which are dirty, locked, under writeback or mapped into
 * pagetables.
 */
unsigned long invalidate_mapping_pages(struct address_space *mapping,
				pgoff_t start, pgoff_t end)
{
	struct pagevec pvec;
	pgoff_t next = start;
	unsigned long ret = 0;
	int i;

	pagevec_init(&pvec, 0);
	while (next <= end &&
			pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];

			if (TestSetPageLocked(page)) {
				next++;
				continue;
			}
			if (page->index > next)
				next = page->index;
			next++;
			if (PageDirty(page) || PageWriteback(page))
				goto unlock;
			if (page_mapped(page))
				goto unlock;
			ret += invalidate_complete_page(mapping, page);
unlock:
			unlock_page(page);
			if (next > end)
				break;
		}
		pagevec_release(&pvec);
		cond_resched();
	}
	return ret;
}

/**
 * truncate_inode_pages - truncate *all* the pages from an offset
 * @mapping: mapping to truncate
 * @lstart: offset from which to truncate
 *
 * Truncate the page cache at a set offset, removing the pages that are beyond
 * that offset (and zeroing out partial pages).
 *
 * Truncate takes two passes - the first pass is nonblocking.  It will not
 * block on page locks and it will not block on writeback.  The second pass
 * will wait.  This is to prevent as much IO as possible in the affected region.
 * The first pass will remove most pages, so the search cost of the second pass
 * is low.
 *
 * When looking at page->index outside the page lock we need to be careful to
 * copy it into a local to avoid races (it could change at any time).
 *
 * We pass down the cache-hot hint to the page freeing code.  Even if the
 * mapping is large, it is probably the case that the final pages are the most
 * recently touched, and freeing happens in ascending file offset order.
 *
 * Called under (and serialised by) inode->i_sem.
 */
void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
{
	const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
	const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
	struct pagevec pvec;
	pgoff_t next;
	int i;

	if (mapping->nrpages == 0)
		return;

	pagevec_init(&pvec, 0);
	next = start;
	while (pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];
			pgoff_t page_index = page->index;

			if (page_index > next)
				next = page_index;
			next++;
			if (TestSetPageLocked(page))
				continue;
			if (PageWriteback(page)) {
				unlock_page(page);
				continue;
			}
			truncate_complete_page(mapping, page);
			unlock_page(page);
		}
		pagevec_release(&pvec);
		cond_resched();
	}

	if (partial) {
		struct page *page = find_lock_page(mapping, start - 1);
		if (page) {
			wait_on_page_writeback(page);
			truncate_partial_page(page, partial);
			unlock_page(page);
			page_cache_release(page);
		}
	}

	next = start;
	for ( ; ; ) {
		cond_resched();
		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
			if (next == start)
				break;
			next = start;
			continue;
		}
		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];

			lock_page(page);
			wait_on_page_writeback(page);
			if (page->index > next)
				next = page->index;
			next++;
			truncate_complete_page(mapping, page);
			unlock_page(page);
		}
		pagevec_release(&pvec);
	}
}

static int ll_write_begin(struct file *file, struct address_space *mapping,
                          loff_t pos, unsigned len, unsigned flags,
                          struct page **pagep, void **fsdata)
{
    struct ll_cl_context *lcc;
    const struct lu_env  *env = NULL;
    struct cl_io   *io;
    struct cl_page *page = NULL;

    struct cl_object *clob = ll_i2info(mapping->host)->lli_clob;
    pgoff_t index = pos >> PAGE_SHIFT;
    struct page *vmpage = NULL;
    unsigned from = pos & (PAGE_SIZE - 1);
    unsigned to = from + len;
    int result = 0;
    ENTRY;

    CDEBUG(D_VFSTRACE, "Writing %lu of %d to %d bytes\n", index, from, len);

    lcc = ll_cl_find(file);
    if (lcc == NULL) {
        io = NULL;
        GOTO(out, result = -EIO);
    }

    env = lcc->lcc_env;
    io  = lcc->lcc_io;

    /* To avoid deadlock, try to lock page first. */
    vmpage = grab_cache_page_nowait(mapping, index);

    if (unlikely(vmpage == NULL ||
                 PageDirty(vmpage) || PageWriteback(vmpage))) {
        struct vvp_io *vio = vvp_env_io(env);
        struct cl_page_list *plist = &vio->u.write.vui_queue;

        /* if the page is already in dirty cache, we have to commit
        * the pages right now; otherwise, it may cause deadlock
        	 * because it holds page lock of a dirty page and request for
        	 * more grants. It's okay for the dirty page to be the first
        	 * one in commit page list, though. */
        if (vmpage != NULL && plist->pl_nr > 0) {
            unlock_page(vmpage);
            put_page(vmpage);
            vmpage = NULL;
        }

        /* commit pages and then wait for page lock */
        result = vvp_io_write_commit(env, io);
        if (result < 0)
            GOTO(out, result);

        if (vmpage == NULL) {
            vmpage = grab_cache_page_write_begin(mapping, index,
                                                 flags);
            if (vmpage == NULL)
                GOTO(out, result = -ENOMEM);
        }
    }

    page = cl_page_find(env, clob, vmpage->index, vmpage, CPT_CACHEABLE);
    if (IS_ERR(page))
        GOTO(out, result = PTR_ERR(page));

    lcc->lcc_page = page;
    lu_ref_add(&page->cp_reference, "cl_io", io);

    cl_page_assume(env, io, page);
    if (!PageUptodate(vmpage)) {
        /*
         * We're completely overwriting an existing page,
         * so _don't_ set it up to date until commit_write
         */
        if (from == 0 && to == PAGE_SIZE) {
            CL_PAGE_HEADER(D_PAGE, env, page, "full page write\n");
            POISON_PAGE(vmpage, 0x11);
        } else {
            /* TODO: can be optimized at OSC layer to check if it
             * is a lockless IO. In that case, it's not necessary
             * to read the data. */
            result = ll_prepare_partial_page(env, io, page);
            if (result == 0)
                SetPageUptodate(vmpage);
        }
    }
    if (result < 0)
        cl_page_unassume(env, io, page);
    EXIT;
out:
    if (result < 0) {
        if (vmpage != NULL) {
            unlock_page(vmpage);
            put_page(vmpage);
        }
        if (!IS_ERR_OR_NULL(page)) {
            lu_ref_del(&page->cp_reference, "cl_io", io);
            cl_page_put(env, page);
        }
        if (io)
            io->ci_result = result;
//.........这里部分代码省略.........

/**
 * write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
 * @mapping: address space structure to write
 * @wbc: subtract the number of written pages from *@wbc->nr_to_write
 * @writepage: function called for each page
 * @data: data passed to writepage function
 *
 * If a page is already under I/O, write_cache_pages() skips it, even
 * if it's dirty.  This is desirable behaviour for memory-cleaning writeback,
 * but it is INCORRECT for data-integrity system calls such as fsync().  fsync()
 * and msync() need to guarantee that all the data which was dirty at the time
 * the call was made get new I/O started against them.  If wbc->sync_mode is
 * WB_SYNC_ALL then we were called for data integrity and we must wait for
 * existing IO to complete.
 */
int write_cache_pages(struct address_space *mapping,
		      struct writeback_control *wbc, writepage_t writepage,
		      void *data)
{
	struct backing_dev_info *bdi = mapping->backing_dev_info;
	int ret = 0;
	int done = 0;
	struct pagevec pvec;
	int nr_pages;
	pgoff_t index;
	pgoff_t end;		/* Inclusive */
	int scanned = 0;
	int range_whole = 0;
	long nr_to_write = wbc->nr_to_write;

	if (wbc->nonblocking && bdi_write_congested(bdi)) {
		wbc->encountered_congestion = 1;
		return 0;
	}

	pagevec_init(&pvec, 0);
	if (wbc->range_cyclic) {
		index = mapping->writeback_index; /* Start from prev offset */
		end = -1;
	} else {
		index = wbc->range_start >> PAGE_CACHE_SHIFT;
		end = wbc->range_end >> PAGE_CACHE_SHIFT;
		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
			range_whole = 1;
		scanned = 1;
	}
retry:
	while (!done && (index <= end) &&
	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
					      PAGECACHE_TAG_DIRTY,
					      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
		unsigned i;

		scanned = 1;
		for (i = 0; i < nr_pages; i++) {
			struct page *page = pvec.pages[i];

			/*
			 * At this point we hold neither mapping->tree_lock nor
			 * lock on the page itself: the page may be truncated or
			 * invalidated (changing page->mapping to NULL), or even
			 * swizzled back from swapper_space to tmpfs file
			 * mapping
			 */
			lock_page(page);

			if (unlikely(page->mapping != mapping)) {
				unlock_page(page);
				continue;
			}

			if (!wbc->range_cyclic && page->index > end) {
				done = 1;
				unlock_page(page);
				continue;
			}

			if (wbc->sync_mode != WB_SYNC_NONE)
				wait_on_page_writeback(page);

			if (PageWriteback(page) ||
			    !clear_page_dirty_for_io(page)) {
				unlock_page(page);
				continue;
			}

			ret = (*writepage)(page, wbc, data);

			if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) {
				unlock_page(page);
				ret = 0;
			}
			if (ret || (--nr_to_write <= 0))
				done = 1;
			if (wbc->nonblocking && bdi_write_congested(bdi)) {
				wbc->encountered_congestion = 1;
				done = 1;
			}
		}
		pagevec_release(&pvec);
//.........这里部分代码省略.........

int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
{
	struct f2fs_io_info fio = {
		.sbi = F2FS_I_SB(dn->inode),
		.type = DATA,
		.op = REQ_OP_WRITE,
		.op_flags = REQ_SYNC | REQ_PRIO,
		.page = page,
		.encrypted_page = NULL,
	};
	int dirty, err;

	if (!f2fs_exist_data(dn->inode))
		goto clear_out;

	err = f2fs_reserve_block(dn, 0);
	if (err)
		return err;

	f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));

	read_inline_data(page, dn->inode_page);
	set_page_dirty(page);

	/* clear dirty state */
	dirty = clear_page_dirty_for_io(page);

	/* write data page to try to make data consistent */
	set_page_writeback(page);
	fio.old_blkaddr = dn->data_blkaddr;
	set_inode_flag(dn->inode, FI_HOT_DATA);
	write_data_page(dn, &fio);
	f2fs_wait_on_page_writeback(page, DATA, true);
	if (dirty) {
		inode_dec_dirty_pages(dn->inode);
		remove_dirty_inode(dn->inode);
	}

	/* this converted inline_data should be recovered. */
	set_inode_flag(dn->inode, FI_APPEND_WRITE);

	/* clear inline data and flag after data writeback */
	truncate_inline_inode(dn->inode, dn->inode_page, 0);
	clear_inline_node(dn->inode_page);
clear_out:
	stat_dec_inline_inode(dn->inode);
	clear_inode_flag(dn->inode, FI_INLINE_DATA);
	f2fs_put_dnode(dn);
	return 0;
}

int f2fs_convert_inline_inode(struct inode *inode)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct dnode_of_data dn;
	struct page *ipage, *page;
	int err = 0;

	if (!f2fs_has_inline_data(inode))
		return 0;

	page = f2fs_grab_cache_page(inode->i_mapping, 0, false);
	if (!page)
		return -ENOMEM;

	f2fs_lock_op(sbi);

	ipage = get_node_page(sbi, inode->i_ino);
	if (IS_ERR(ipage)) {
		err = PTR_ERR(ipage);
		goto out;
	}

	set_new_dnode(&dn, inode, ipage, ipage, 0);

	if (f2fs_has_inline_data(inode))
		err = f2fs_convert_inline_page(&dn, page);

	f2fs_put_dnode(&dn);
out:
	f2fs_unlock_op(sbi);

	f2fs_put_page(page, 1);

	f2fs_balance_fs(sbi, dn.node_changed);

	return err;
}

int f2fs_write_inline_data(struct inode *inode, struct page *page)
{
	void *src_addr, *dst_addr;
	struct dnode_of_data dn;
	int err;

	set_new_dnode(&dn, inode, NULL, NULL, 0);
	err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
	if (err)
		return err;

//.........这里部分代码省略.........

//.........这里部分代码省略.........
				goto confused;
		}
		blocks[page_block++] = map_bh.b_blocknr;
		boundary = buffer_boundary(&map_bh);
		bdev = map_bh.b_bdev;
		if (block_in_file == last_block)
			break;
		block_in_file++;
	}
	BUG_ON(page_block == 0);

	first_unmapped = page_block;

page_is_mapped:
	end_index = i_size >> PAGE_CACHE_SHIFT;
	if (page->index >= end_index) {
		/*
		 * The page straddles i_size.  It must be zeroed out on each
		 * and every writepage invocation because it may be mmapped.
		 * "A file is mapped in multiples of the page size.  For a file
		 * that is not a multiple of the page size, the remaining memory
		 * is zeroed when mapped, and writes to that region are not
		 * written out to the file."
		 */
		unsigned offset = i_size & (PAGE_CACHE_SIZE - 1);

		if (page->index > end_index || !offset)
			goto confused;
		zero_user_segment(page, offset, PAGE_CACHE_SIZE);
	}

	/*
	 * This page will go to BIO.  Do we need to send this BIO off first?
	 */
	if (bio && mpd->last_block_in_bio != blocks[0] - 1)
		bio = mpage_bio_submit(wr, bio);

alloc_new:
	if (bio == NULL) {
		if (first_unmapped == blocks_per_page) {
			if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9),
								page, wbc)) {
				clean_buffers(page, first_unmapped);
				goto out;
			}
		}
		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
				BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH);
		if (bio == NULL)
			goto confused;

		wbc_init_bio(wbc, bio);
	}

	/*
	 * Must try to add the page before marking the buffer clean or
	 * the confused fail path above (OOM) will be very confused when
	 * it finds all bh marked clean (i.e. it will not write anything)
	 */
	wbc_account_io(wbc, page, PAGE_SIZE);
	length = first_unmapped << blkbits;
	if (bio_add_page(bio, page, length, 0) < length) {
		bio = mpage_bio_submit(wr, bio);
		goto alloc_new;
	}

	clean_buffers(page, first_unmapped);

	BUG_ON(PageWriteback(page));
	set_page_writeback(page);
	unlock_page(page);
	if (boundary || (first_unmapped != blocks_per_page)) {
		bio = mpage_bio_submit(wr, bio);
		if (boundary_block) {
			write_boundary_block(boundary_bdev,
					boundary_block, 1 << blkbits);
		}
	} else {
		mpd->last_block_in_bio = blocks[blocks_per_page - 1];
	}
	goto out;

confused:
	if (bio)
		bio = mpage_bio_submit(wr, bio);

	if (mpd->use_writepage) {
		ret = mapping->a_ops->writepage(page, wbc);
	} else {
		ret = -EAGAIN;
		goto out;
	}
	/*
	 * The caller has a ref on the inode, so *mapping is stable
	 */
	mapping_set_error(mapping, ret);
out:
	mpd->bio = bio;
	return ret;
}

int ext4_bio_write_page(struct ext4_io_submit *io,
			struct page *page,
			int len,
			struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	unsigned block_start, block_end, blocksize;
	struct ext4_io_page *io_page;
	struct buffer_head *bh, *head;
	int ret = 0;

	blocksize = 1 << inode->i_blkbits;

	BUG_ON(!PageLocked(page));
	BUG_ON(PageWriteback(page));

	io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
	if (!io_page) {
		set_page_dirty(page);
		unlock_page(page);
		return -ENOMEM;
	}
	io_page->p_page = page;
	atomic_set(&io_page->p_count, 1);
	get_page(page);
	set_page_writeback(page);
	ClearPageError(page);

	for (bh = head = page_buffers(page), block_start = 0;
	     bh != head || !block_start;
	     block_start = block_end, bh = bh->b_this_page) {

		block_end = block_start + blocksize;
		if (block_start >= len) {
			clear_buffer_dirty(bh);
			set_buffer_uptodate(bh);
			continue;
		}
		clear_buffer_dirty(bh);
		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
		if (ret) {
			/*
			 * We only get here on ENOMEM.  Not much else
			 * we can do but mark the page as dirty, and
			 * better luck next time.
			 */
			set_page_dirty(page);
			break;
		}
	}
	unlock_page(page);
	/*
	 * If the page was truncated before we could do the writeback,
	 * or we had a memory allocation error while trying to write
	 * the first buffer head, we won't have submitted any pages for
	 * I/O.  In that case we need to make sure we've cleared the
	 * PageWriteback bit from the page to prevent the system from
	 * wedging later on.
	 */
	put_io_page(io_page);
	return ret;
}

int ext4_bio_write_page(struct ext4_io_submit *io,
			struct page *page,
			int len,
			struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	unsigned block_start, block_end, blocksize;
	struct ext4_io_page *io_page;
	struct buffer_head *bh, *head;
	int ret = 0;

	blocksize = 1 << inode->i_blkbits;

	BUG_ON(!PageLocked(page));
	BUG_ON(PageWriteback(page));

	io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
	if (!io_page) {
		set_page_dirty(page);
		unlock_page(page);
		return -ENOMEM;
	}
	io_page->p_page = page;
	atomic_set(&io_page->p_count, 1);
	get_page(page);
	set_page_writeback(page);
	ClearPageError(page);

	/*
	 * Comments copied from block_write_full_page_endio:
	 *
	 * The page straddles i_size.  It must be zeroed out on each and every
	 * writepage invocation because it may be mmapped.  "A file is mapped
	 * in multiples of the page size.  For a file that is not a multiple of
	 * the page size, the remaining memory is zeroed when mapped, and
	 * writes to that region are not written out to the file."
	 */
	if (len < PAGE_CACHE_SIZE)
		zero_user_segment(page, len, PAGE_CACHE_SIZE);

	for (bh = head = page_buffers(page), block_start = 0;
	     bh != head || !block_start;
	     block_start = block_end, bh = bh->b_this_page) {

		block_end = block_start + blocksize;
		if (block_start >= len) {
			clear_buffer_dirty(bh);
			set_buffer_uptodate(bh);
			continue;
		}
		clear_buffer_dirty(bh);
		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
		if (ret) {
			/*
			 * We only get here on ENOMEM.  Not much else
			 * we can do but mark the page as dirty, and
			 * better luck next time.
			 */
			set_page_dirty(page);
			break;
		}
	}
	unlock_page(page);
	/*
	 * If the page was truncated before we could do the writeback,
	 * or we had a memory allocation error while trying to write
	 * the first buffer head, we won't have submitted any pages for
	 * I/O.  In that case we need to make sure we've cleared the
	 * PageWriteback bit from the page to prevent the system from
	 * wedging later on.
	 */
	put_io_page(io_page);
	return ret;
}

//.........这里部分代码省略.........
			 */
			if (page->index > end) {
				/*
				 * can't be range_cyclic (1st pass) because
				 * end == -1 in that case.
				 */
				done = 1;
				break;
			}

			done_index = page->index + 1;

			lock_page(page);

			/*
			 * Page truncated or invalidated. We can freely skip it
			 * then, even for data integrity operations: the page
			 * has disappeared concurrently, so there could be no
			 * real expectation of this data interity operation
			 * even if there is now a new, dirty page at the same
			 * pagecache address.
			 */
			if (unlikely(page->mapping != mapping)) {
continue_unlock:
				unlock_page(page);
				continue;
			}

			if (!PageDirty(page)) {
				/* someone wrote it for us */
				goto continue_unlock;
			}

			if (PageWriteback(page)) {
				if (wbc->sync_mode != WB_SYNC_NONE)
					wait_on_page_writeback(page);
				else
					goto continue_unlock;
			}

			BUG_ON(PageWriteback(page));
			if (!clear_page_dirty_for_io(page))
				goto continue_unlock;

			ret = (*writepage)(page, wbc, data);

			if (unlikely(ret)) {
				if (ret == AOP_WRITEPAGE_ACTIVATE) {
					unlock_page(page);
					ret = 0;
				} else {
					/*
					 * done_index is set past this page,
					 * so media errors will not choke
					 * background writeout for the entire
					 * file. This has consequences for
					 * range_cyclic semantics (ie. it may
					 * not be suitable for data integrity
					 * writeout).
					 */
					done = 1;
					break;
				}
 			}

			if (wbc->nr_to_write > 0) {

static int gfs2_write_jdata_pagevec(struct address_space *mapping,
				    struct writeback_control *wbc,
				    struct pagevec *pvec,
				    int nr_pages, pgoff_t end,
				    pgoff_t *done_index)
{
	struct inode *inode = mapping->host;
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize);
	int i;
	int ret;

	ret = gfs2_trans_begin(sdp, nrblocks, nrblocks);
	if (ret < 0)
		return ret;

	for(i = 0; i < nr_pages; i++) {
		struct page *page = pvec->pages[i];

		/*
		 * At this point, the page may be truncated or
		 * invalidated (changing page->mapping to NULL), or
		 * even swizzled back from swapper_space to tmpfs file
		 * mapping. However, page->index will not change
		 * because we have a reference on the page.
		 */
		if (page->index > end) {
			/*
			 * can't be range_cyclic (1st pass) because
			 * end == -1 in that case.
			 */
			ret = 1;
			break;
		}

		*done_index = page->index;

		lock_page(page);

		if (unlikely(page->mapping != mapping)) {
continue_unlock:
			unlock_page(page);
			continue;
		}

		if (!PageDirty(page)) {
			/* someone wrote it for us */
			goto continue_unlock;
		}

		if (PageWriteback(page)) {
			if (wbc->sync_mode != WB_SYNC_NONE)
				wait_on_page_writeback(page);
			else
				goto continue_unlock;
		}

		BUG_ON(PageWriteback(page));
		if (!clear_page_dirty_for_io(page))
			goto continue_unlock;

		trace_wbc_writepage(wbc, mapping->backing_dev_info);

		ret = __gfs2_jdata_writepage(page, wbc);
		if (unlikely(ret)) {
			if (ret == AOP_WRITEPAGE_ACTIVATE) {
				unlock_page(page);
				ret = 0;
			} else {

				/*
				 * done_index is set past this page,
				 * so media errors will not choke
				 * background writeout for the entire
				 * file. This has consequences for
				 * range_cyclic semantics (ie. it may
				 * not be suitable for data integrity
				 * writeout).
				 */
				*done_index = page->index + 1;
				ret = 1;
				break;
			}
		}

		/*
		 * We stop writing back only if we are not doing
		 * integrity sync. In case of integrity sync we have to
		 * keep going until we have written all the pages
		 * we tagged for writeback prior to entering this loop.
		 */
		if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) {
			ret = 1;
			break;
		}

	}
	gfs2_trans_end(sdp);
	return ret;
}