/*
 * support function for mpage_readpages.  The fs supplied get_block might
 * return an up to date buffer.  This is used to map that buffer into
 * the page, which allows readpage to avoid triggering a duplicate call
 * to get_block.
 *
 * The idea is to avoid adding buffers to pages that don't already have
 * them.  So when the buffer is up to date and the page size == block size,
 * this marks the page up to date instead of adding new buffers.
 */
static void 
map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block) 
{
	struct inode *inode = page->mapping->host;
	struct buffer_head *page_bh, *head;
	int block = 0;

	if (!page_has_buffers(page)) {
		/*
		 * don't make any buffers if there is only one buffer on
		 * the page and the page just needs to be set up to date
		 */
		if (inode->i_blkbits == PAGE_CACHE_SHIFT && 
		    buffer_uptodate(bh)) {
			SetPageUptodate(page);    
			return;
		}
		create_empty_buffers(page, 1 << inode->i_blkbits, 0);
	}
	head = page_buffers(page);
	page_bh = head;
	do {
		if (block == page_block) {
			page_bh->b_state = bh->b_state;
			page_bh->b_bdev = bh->b_bdev;
			page_bh->b_blocknr = bh->b_blocknr;
			break;
		}
		page_bh = page_bh->b_this_page;
		block++;
	} while (page_bh != head);
}

/*
 * If a ramdisk page has buffers, some may be uptodate and some may be not.
 * To bring the page uptodate we zero out the non-uptodate buffers.  The
 * page must be locked.
 */
static void make_page_uptodate(struct page *page)
{
	if (page_has_buffers(page)) {
		struct buffer_head *bh = page_buffers(page);
		struct buffer_head *head = bh;

		do {
			if (!buffer_uptodate(bh)) {
				memset(bh->b_data, 0, bh->b_size);
				/*
				 * akpm: I'm totally undecided about this.  The
				 * buffer has just been magically brought "up to
				 * date", but nobody should want to be reading
				 * it anyway, because it hasn't been used for
				 * anything yet.  It is still in a "not read
				 * from disk yet" state.
				 *
				 * But non-uptodate buffers against an uptodate
				 * page are against the rules.  So do it anyway.
				 */
				 set_buffer_uptodate(bh);
			}
		} while ((bh = bh->b_this_page) != head);
	} else {
		memset(page_address(page), 0, PAGE_CACHE_SIZE);
	}
	flush_dcache_page(page);
	SetPageUptodate(page);
}

void nilfs_page_bug(struct page *page)
{
	struct address_space *m;
	unsigned long ino;

	if (unlikely(!page)) {
		printk(KERN_CRIT "NILFS_PAGE_BUG(NULL)\n");
		return;
	}

	m = page->mapping;
	ino = m ? m->host->i_ino : 0;

	printk(KERN_CRIT "NILFS_PAGE_BUG(%p): cnt=%d index#=%llu flags=0x%lx "
	       "mapping=%p ino=%lu\n",
	       page, page_ref_count(page),
	       (unsigned long long)page->index, page->flags, m, ino);

	if (page_has_buffers(page)) {
		struct buffer_head *bh, *head;
		int i = 0;

		bh = head = page_buffers(page);
		do {
			printk(KERN_CRIT
			       " BH[%d] %p: cnt=%d block#=%llu state=0x%lx\n",
			       i++, bh, atomic_read(&bh->b_count),
			       (unsigned long long)bh->b_blocknr, bh->b_state);
			bh = bh->b_this_page;
		} while (bh != head);
	}
}

static void gfs2_invalidatepage(struct page *page, unsigned int offset,
				unsigned int length)
{
	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
	unsigned int stop = offset + length;
	int partial_page = (offset || length < PAGE_CACHE_SIZE);
	struct buffer_head *bh, *head;
	unsigned long pos = 0;

	BUG_ON(!PageLocked(page));
	if (!partial_page)
		ClearPageChecked(page);
	if (!page_has_buffers(page))
		goto out;

	bh = head = page_buffers(page);
	do {
		if (pos + bh->b_size > stop)
			return;

		if (offset <= pos)
			gfs2_discard(sdp, bh);
		pos += bh->b_size;
		bh = bh->b_this_page;
	} while (bh != head);
out:
	if (!partial_page)
		try_to_release_page(page, 0);
}

static void
unmap_buffers(struct page *page, loff_t pos) {
  struct buffer_head *bh ;
  struct buffer_head *head ;
  struct buffer_head *next ;
  unsigned long tail_index ;
  unsigned long cur_index ;

  if (page) {
    if (page_has_buffers(page)) {
      tail_index = pos & (PAGE_CACHE_SIZE - 1) ;
      cur_index = 0 ;
      head = page_buffers(page) ;
      bh = head ;
      do {
	next = bh->b_this_page ;

        /* we want to unmap the buffers that contain the tail, and
        ** all the buffers after it (since the tail must be at the
        ** end of the file).  We don't want to unmap file data 
        ** before the tail, since it might be dirty and waiting to 
        ** reach disk
        */
        cur_index += bh->b_size ;
        if (cur_index > tail_index) {
          reiserfs_unmap_buffer(bh) ;
        }
	bh = next ;
      } while (bh != head) ;
      if ( PAGE_SIZE == bh->b_size ) {
	clear_page_dirty(page);
      }
    }
  } 
}

static int nilfs_set_page_dirty(struct page *page)
{
	int ret = __set_page_dirty_nobuffers(page);

	if (page_has_buffers(page)) {
		struct inode *inode = page->mapping->host;
		unsigned nr_dirty = 0;
		struct buffer_head *bh, *head;

		/*
		 * This page is locked by callers, and no other thread
		 * concurrently marks its buffers dirty since they are
		 * only dirtied through routines in fs/buffer.c in
		 * which call sites of mark_buffer_dirty are protected
		 * by page lock.
		 */
		bh = head = page_buffers(page);
		do {
			/* Do not mark hole blocks dirty */
			if (buffer_dirty(bh) || !buffer_mapped(bh))
				continue;

			set_buffer_dirty(bh);
			nr_dirty++;
		} while (bh = bh->b_this_page, bh != head);

		if (nr_dirty)
			nilfs_set_file_dirty(inode, nr_dirty);
	}
	return ret;
}

/*
 * We're now finished for good with this page.  Update the page state via the
 * associated buffer_heads, paying attention to the start and end offsets that
 * we need to process on the page.
 *
 * Landmine Warning: bh->b_end_io() will call end_page_writeback() on the last
 * buffer in the IO. Once it does this, it is unsafe to access the bufferhead or
 * the page at all, as we may be racing with memory reclaim and it can free both
 * the bufferhead chain and the page as it will see the page as clean and
 * unused.
 */
static void
xfs_finish_page_writeback(
	struct inode		*inode,
	struct bio_vec		*bvec,
	int			error)
{
	unsigned int		end = bvec->bv_offset + bvec->bv_len - 1;
	struct buffer_head	*head, *bh, *next;
	unsigned int		off = 0;
	unsigned int		bsize;

	ASSERT(bvec->bv_offset < PAGE_SIZE);
	ASSERT((bvec->bv_offset & ((1 << inode->i_blkbits) - 1)) == 0);
	ASSERT(end < PAGE_SIZE);
	ASSERT((bvec->bv_len & ((1 << inode->i_blkbits) - 1)) == 0);

	bh = head = page_buffers(bvec->bv_page);

	bsize = bh->b_size;
	do {
		next = bh->b_this_page;
		if (off < bvec->bv_offset)
			goto next_bh;
		if (off > end)
			break;
		bh->b_end_io(bh, !error);
next_bh:
		off += bsize;
	} while ((bh = next) != head);
}

static void ext4_finish_bio(struct bio *bio)
{
	int i;
	struct bio_vec *bvec;

	bio_for_each_segment_all(bvec, bio, i) {
		struct page *page = bvec->bv_page;
#ifdef CONFIG_EXT4_FS_ENCRYPTION
		struct page *data_page = NULL;
#endif
		struct buffer_head *bh, *head;
		unsigned bio_start = bvec->bv_offset;
		unsigned bio_end = bio_start + bvec->bv_len;
		unsigned under_io = 0;
		unsigned long flags;

		if (!page)
			continue;

#ifdef CONFIG_EXT4_FS_ENCRYPTION
		if (!page->mapping) {
			/* The bounce data pages are unmapped. */
			data_page = page;
			fscrypt_pullback_bio_page(&page, false);
		}
#endif

		if (bio->bi_status) {
			SetPageError(page);
			mapping_set_error(page->mapping, -EIO);
		}
		bh = head = page_buffers(page);
		/*
		 * We check all buffers in the page under BH_Uptodate_Lock
		 * to avoid races with other end io clearing async_write flags
		 */
		local_irq_save(flags);
		bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
		do {
			if (bh_offset(bh) < bio_start ||
			    bh_offset(bh) + bh->b_size > bio_end) {
				if (buffer_async_write(bh))
					under_io++;
				continue;
			}
			clear_buffer_async_write(bh);
			if (bio->bi_status)
				buffer_io_error(bh);
		} while ((bh = bh->b_this_page) != head);
		bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
		local_irq_restore(flags);
		if (!under_io) {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
			if (data_page)
				fscrypt_restore_control_page(data_page);
#endif
			end_page_writeback(page);
		}
	}
}

void nilfs_clear_dirty_pages(struct address_space *mapping)
{
	struct pagevec pvec;
	unsigned int i;
	pgoff_t index = 0;

	pagevec_init(&pvec, 0);

	while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
				  PAGEVEC_SIZE)) {
		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];
			struct buffer_head *bh, *head;

			lock_page(page);
			ClearPageUptodate(page);
			ClearPageMappedToDisk(page);
			bh = head = page_buffers(page);
			do {
				lock_buffer(bh);
				clear_buffer_dirty(bh);
				clear_buffer_nilfs_volatile(bh);
				clear_buffer_uptodate(bh);
				clear_buffer_mapped(bh);
				unlock_buffer(bh);
				bh = bh->b_this_page;
			} while (bh != head);

			__nilfs_clear_page_dirty(page);
			unlock_page(page);
		}
		pagevec_release(&pvec);
		cond_resched();
	}
}

///////////////////////////////////////////////////////////
// TracePageBuffers
//
//
///////////////////////////////////////////////////////////
void
TracePageBuffers(
    IN struct page* page,
    IN int hdr
    )
{
  if ( hdr ) {
    DebugTrace(+1, UFSD_LEVEL_PAGE_BH, ("p=%p f=%lx:\n", page, page->flags ));
  } else if ( UFSD_TraceLevel & UFSD_LEVEL_PAGE_BH ) {
    UFSD_TraceInc( +1 );
  }

  if ( page_has_buffers( page ) ) {
    struct buffer_head* head  = page_buffers(page);
    struct buffer_head* bh    = head;
    do {
      if ( (sector_t)-1 == bh->b_blocknr ) {
        DebugTrace( 0, UFSD_LEVEL_PAGE_BH, ("bh=%p,%lx\n", bh, bh->b_state) );
      } else {
        DebugTrace( 0, UFSD_LEVEL_PAGE_BH, ("bh=%p,%lx,%"PSCT"x\n", bh, bh->b_state, bh->b_blocknr ) );
      }
      bh = bh->b_this_page;
    } while( bh != head );
  } else {
    DebugTrace(0, UFSD_LEVEL_PAGE_BH, ("no buffers\n" ));
  }

  if ( UFSD_TraceLevel & UFSD_LEVEL_PAGE_BH )
    UFSD_TraceInc( -1 );
}

handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
							 struct page *page,
							 unsigned from,
							 unsigned to)
{
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	handle_t *handle;
	int ret = 0;

	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
	if (IS_ERR(handle)) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}

	if (ocfs2_should_order_data(inode)) {
		ret = walk_page_buffers(handle,
					page_buffers(page),
					from, to, NULL,
					ocfs2_journal_dirty_data);
		if (ret < 0) 
			mlog_errno(ret);
	}
out:
	if (ret) {
		if (!IS_ERR(handle))
			ocfs2_commit_trans(osb, handle);
		handle = ERR_PTR(ret);
	}
	return handle;
}

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(PageWriteback(page));
	set_page_writeback(page);
	ClearPageError(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);

	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;
		}
		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;
}

static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc)
{
	struct buffer_head *bh, *head;
	int nr_underway = 0;
	int write_op = REQ_META |
		(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC_PLUG : WRITE);

	BUG_ON(!PageLocked(page));
	BUG_ON(!page_has_buffers(page));

	head = page_buffers(page);
	bh = head;

	do {
		if (!buffer_mapped(bh))
			continue;
		/*
		 * If it's a fully non-blocking write attempt and we cannot
		 * lock the buffer then redirty the page.  Note that this can
		 * potentially cause a busy-wait loop from pdflush and kswapd
		 * activity, but those code paths have their own higher-level
		 * throttling.
		 */
		if (wbc->sync_mode != WB_SYNC_NONE) {
			lock_buffer(bh);
		} else if (!trylock_buffer(bh)) {
			redirty_page_for_writepage(wbc, page);
			continue;
		}
		if (test_clear_buffer_dirty(bh)) {
			mark_buffer_async_write(bh);
		} else {
			unlock_buffer(bh);
		}
	} while ((bh = bh->b_this_page) != head);

	/*
	 * The page and its buffers are protected by PageWriteback(), so we can
	 * drop the bh refcounts early.
	 */
	BUG_ON(PageWriteback(page));
	set_page_writeback(page);

	do {
		struct buffer_head *next = bh->b_this_page;
		if (buffer_async_write(bh)) {
			submit_bh(write_op, bh);
			nr_underway++;
		}
		bh = next;
	} while (bh != head);
	unlock_page(page);

	if (nr_underway == 0)
		end_page_writeback(page);

	return 0;
}

static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct page *page = vmf->page;
	struct inode *inode = vma->vm_file->f_dentry->d_inode;
	struct nilfs_transaction_info ti;
	int ret;

	if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
		return VM_FAULT_SIGBUS; 

	lock_page(page);
	if (page->mapping != inode->i_mapping ||
	    page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
		unlock_page(page);
		return VM_FAULT_NOPAGE; 
	}

	if (PageMappedToDisk(page))
		goto mapped;

	if (page_has_buffers(page)) {
		struct buffer_head *bh, *head;
		int fully_mapped = 1;

		bh = head = page_buffers(page);
		do {
			if (!buffer_mapped(bh)) {
				fully_mapped = 0;
				break;
			}
		} while (bh = bh->b_this_page, bh != head);

		if (fully_mapped) {
			SetPageMappedToDisk(page);
			goto mapped;
		}
	}
	unlock_page(page);

	ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
	
	if (unlikely(ret))
		return VM_FAULT_SIGBUS;

	ret = block_page_mkwrite(vma, vmf, nilfs_get_block);
	if (ret != VM_FAULT_LOCKED) {
		nilfs_transaction_abort(inode->i_sb);
		return ret;
	}
	nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
	nilfs_transaction_commit(inode->i_sb);

 mapped:
	wait_on_page_writeback(page);
	return VM_FAULT_LOCKED;
}

/**
 * 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);
}

void nilfs_invalidatepage(struct page *page, unsigned long offset)
{
	struct buffer_head *bh = NULL;

	if (PagePrivate(page)) {
		bh = page_buffers(page);
		BUG_ON(buffer_nilfs_allocated(bh));
	}
	block_invalidatepage(page, offset);
}

/**
 * nilfs_page_buffers_clean - check if a page has dirty buffers or not.
 * @page: page to be checked
 *
 * nilfs_page_buffers_clean() returns zero if the page has dirty buffers.
 * Otherwise, it returns non-zero value.
 */
int nilfs_page_buffers_clean(struct page *page)
{
	struct buffer_head *bh, *head;

	bh = head = page_buffers(page);
	do {
		if (buffer_dirty(bh))
			return 0;
		bh = bh->b_this_page;
	} while (bh != head);
	return 1;
}

static void free_buffers(struct page *page)
{
	struct buffer_head *bh = page_buffers(page);

	while (bh) {
		struct buffer_head *next = bh->b_this_page;
		free_buffer_head(bh);
		bh = next;
	}
	__clear_page_buffers(page);
	put_page(page);
}

int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
{
	struct inode *aspace = page->mapping->host;
	struct gfs2_sbd *sdp = aspace->i_sb->s_fs_info;
	struct buffer_head *bh, *head;
	struct gfs2_bufdata *bd;
	unsigned long t = jiffies + gfs2_tune_get(sdp, gt_stall_secs) * HZ;

	if (!page_has_buffers(page))
		goto out;

	head = bh = page_buffers(page);
	do {
		while (atomic_read(&bh->b_count)) {
			if (!atomic_read(&aspace->i_writecount))
				return 0;

			if (!(gfp_mask & __GFP_WAIT))
				return 0;

			if (time_after_eq(jiffies, t)) {
				stuck_releasepage(bh);
				/* should we withdraw here? */
				return 0;
			}

			yield();
		}

		gfs2_assert_warn(sdp, !buffer_pinned(bh));
		gfs2_assert_warn(sdp, !buffer_dirty(bh));

		gfs2_log_lock(sdp);
		bd = bh->b_private;
		if (bd) {
			gfs2_assert_warn(sdp, bd->bd_bh == bh);
			gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr));
			gfs2_assert_warn(sdp, !bd->bd_ail);
			bd->bd_bh = NULL;
			if (!list_empty(&bd->bd_le.le_list))
				bd = NULL;
			bh->b_private = NULL;
		}
		gfs2_log_unlock(sdp);
		if (bd)
			kmem_cache_free(gfs2_bufdata_cachep, bd);

		bh = bh->b_this_page;
	} while (bh != head);

out:
	return try_to_free_buffers(page);
}

static int ufs_alloc_lastblock(struct inode *inode)
{
    int err = 0;
    struct address_space *mapping = inode->i_mapping;
    struct ufs_sb_private_info *uspi = UFS_SB(inode->i_sb)->s_uspi;
    unsigned lastfrag, i, end;
    struct page *lastpage;
    struct buffer_head *bh;

    lastfrag = (i_size_read(inode) + uspi->s_fsize - 1) >> uspi->s_fshift;

    if (!lastfrag)
        goto out;

    lastfrag--;

    lastpage = ufs_get_locked_page(mapping, lastfrag >>
                                   (PAGE_CACHE_SHIFT - inode->i_blkbits));
    if (IS_ERR(lastpage)) {
        err = -EIO;
        goto out;
    }

    end = lastfrag & ((1 << (PAGE_CACHE_SHIFT - inode->i_blkbits)) - 1);
    bh = page_buffers(lastpage);
    for (i = 0; i < end; ++i)
        bh = bh->b_this_page;


    err = ufs_getfrag_block(inode, lastfrag, bh, 1);

    if (unlikely(err))
        goto out_unlock;

    if (buffer_new(bh)) {
        clear_buffer_new(bh);
        unmap_underlying_metadata(bh->b_bdev,
                                  bh->b_blocknr);
        /*
        * we do not zeroize fragment, because of
        * if it maped to hole, it already contains zeroes
        */
        set_buffer_uptodate(bh);
        mark_buffer_dirty(bh);
        set_page_dirty(lastpage);
    }

out_unlock:
    ufs_put_locked_page(lastpage);
out:
    return err;
}