aops.c

ocfs1.4.1 oracle分布式文件系统

}

static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
{
	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);

	brelse(wc->w_di_bh);
	kfree(wc);
}

static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
				  struct ocfs2_super *osb, loff_t pos,
				  unsigned len, struct buffer_head *di_bh)
{
	u32 cend;
	struct ocfs2_write_ctxt *wc;

	wc = kzalloc(sizeof(struct ocfs2_write_ctxt), GFP_NOFS);
	if (!wc)
		return -ENOMEM;

	wc->w_cpos = pos >> osb->s_clustersize_bits;
	cend = (pos + len - 1) >> osb->s_clustersize_bits;
	wc->w_clen = cend - wc->w_cpos + 1;
	get_bh(di_bh);
	wc->w_di_bh = di_bh;

	if (unlikely(PAGE_CACHE_SHIFT > osb->s_clustersize_bits))
		wc->w_large_pages = 1;
	else
		wc->w_large_pages = 0;

	ocfs2_init_dealloc_ctxt(&wc->w_dealloc);

	*wcp = wc;

	return 0;
}

/*
 * If a page has any new buffers, zero them out here, and mark them uptodate
 * and dirty so they'll be written out (in order to prevent uninitialised
 * block data from leaking). And clear the new bit.
 */
static void ocfs2_zero_new_buffers(struct page *page, unsigned from, unsigned to)
{
	unsigned int block_start, block_end;
	struct buffer_head *head, *bh;

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

	bh = head = page_buffers(page);
	block_start = 0;
	do {
		block_end = block_start + bh->b_size;

		if (buffer_new(bh)) {
			if (block_end > from && block_start < to) {
				if (!PageUptodate(page)) {
					unsigned start, end;

					start = max(from, block_start);
					end = min(to, block_end);

					zero_user_page(page, start, end - start, KM_USER0);
					set_buffer_uptodate(bh);
				}

				clear_buffer_new(bh);
				mark_buffer_dirty(bh);
			}
		}

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

/*
 * Only called when we have a failure during allocating write to write
 * zero's to the newly allocated region.
 */
static void ocfs2_write_failure(struct inode *inode,
				struct ocfs2_write_ctxt *wc,
				loff_t user_pos, unsigned user_len)
{
	int i;
	unsigned from = user_pos & (PAGE_CACHE_SIZE - 1),
		to = user_pos + user_len;
	struct page *tmppage;

	ocfs2_zero_new_buffers(wc->w_target_page, from, to);

	for(i = 0; i < wc->w_num_pages; i++) {
		tmppage = wc->w_pages[i];

		if (page_has_buffers(tmppage)) {
			if (ocfs2_should_order_data(inode))
				walk_page_buffers(wc->w_handle,
						  page_buffers(tmppage),
						  from, to, NULL,
						  ocfs2_journal_dirty_data);

			block_commit_write(tmppage, from, to);
		}
	}
}

static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno,
					struct ocfs2_write_ctxt *wc,
					struct page *page, u32 cpos,
					loff_t user_pos, unsigned user_len,
					int new)
{
	int ret;
	unsigned int map_from = 0, map_to = 0;
	unsigned int cluster_start, cluster_end;
	unsigned int user_data_from = 0, user_data_to = 0;

	ocfs2_figure_cluster_boundaries(OCFS2_SB(inode->i_sb), cpos,
					&cluster_start, &cluster_end);

	if (page == wc->w_target_page) {
		map_from = user_pos & (PAGE_CACHE_SIZE - 1);
		map_to = map_from + user_len;

		if (new)
			ret = ocfs2_map_page_blocks(page, p_blkno, inode,
						    cluster_start, cluster_end,
						    new);
		else
			ret = ocfs2_map_page_blocks(page, p_blkno, inode,
						    map_from, map_to, new);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		user_data_from = map_from;
		user_data_to = map_to;
		if (new) {
			map_from = cluster_start;
			map_to = cluster_end;
		}
	} else {
		/*
		 * If we haven't allocated the new page yet, we
		 * shouldn't be writing it out without copying user
		 * data. This is likely a math error from the caller.
		 */
		BUG_ON(!new);

		map_from = cluster_start;
		map_to = cluster_end;

		ret = ocfs2_map_page_blocks(page, p_blkno, inode,
					    cluster_start, cluster_end, new);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	/*
	 * Parts of newly allocated pages need to be zero'd.
	 *
	 * Above, we have also rewritten 'to' and 'from' - as far as
	 * the rest of the function is concerned, the entire cluster
	 * range inside of a page needs to be written.
	 *
	 * We can skip this if the page is up to date - it's already
	 * been zero'd from being read in as a hole.
	 */
	if (new && !PageUptodate(page))
		ocfs2_clear_page_regions(page, OCFS2_SB(inode->i_sb),
					 cpos, user_data_from, user_data_to);

	flush_dcache_page(page);

out:
	return ret;
}

/*
 * This function will only grab one clusters worth of pages.
 */
static int ocfs2_grab_pages_for_write(struct address_space *mapping,
				      struct ocfs2_write_ctxt *wc,
				      u32 cpos, loff_t user_pos, int new,
				      struct page *mmap_page)
{
	int ret = 0, i;
	unsigned long start, target_index, index;
	struct inode *inode = mapping->host;

	target_index = user_pos >> PAGE_CACHE_SHIFT;

	/*
	 * Figure out how many pages we'll be manipulating here. For
	 * non allocating write, we just change the one
	 * page. Otherwise, we'll need a whole clusters worth.
	 */
	if (new) {
		wc->w_num_pages = ocfs2_pages_per_cluster(inode->i_sb);
		start = ocfs2_align_clusters_to_page_index(inode->i_sb, cpos);
	} else {
		wc->w_num_pages = 1;
		start = target_index;
	}

	for(i = 0; i < wc->w_num_pages; i++) {
		index = start + i;

		if (index == target_index && mmap_page) {
			/*
			 * ocfs2_pagemkwrite() is a little different
			 * and wants us to directly use the page
			 * passed in.
			 */
			lock_page(mmap_page);

			if (mmap_page->mapping != mapping) {
				unlock_page(mmap_page);
				/*
				 * Sanity check - the locking in
				 * ocfs2_pagemkwrite() should ensure
				 * that this code doesn't trigger.
				 */
				ret = -EINVAL;
				mlog_errno(ret);
				goto out;
			}

			page_cache_get(mmap_page);
			wc->w_pages[i] = mmap_page;
		} else {
			wc->w_pages[i] = find_or_create_page(mapping, index,
							     GFP_NOFS);
			if (!wc->w_pages[i]) {
				ret = -ENOMEM;
				mlog_errno(ret);
				goto out;
			}
		}

		if (index == target_index)
			wc->w_target_page = wc->w_pages[i];
	}
out:
	return ret;
}

/*
 * Prepare a single cluster for write one cluster into the file.
 */
static int ocfs2_write_cluster(struct address_space *mapping,
			       u32 phys, unsigned int unwritten,
			       struct ocfs2_alloc_context *data_ac,
			       struct ocfs2_alloc_context *meta_ac,
			       struct ocfs2_write_ctxt *wc, u32 cpos,
			       loff_t user_pos, unsigned user_len)
{
	int ret, i, new, should_zero = 0;
	u64 v_blkno, p_blkno;
	struct inode *inode = mapping->host;

	new = phys == 0 ? 1 : 0;
	if (new || unwritten)
		should_zero = 1;

	if (new) {
		u32 tmp_pos;

		/*
		 * This is safe to call with the page locks - it won't take
		 * any additional semaphores or cluster locks.
		 */
		tmp_pos = cpos;
		ret = ocfs2_do_extend_allocation(OCFS2_SB(inode->i_sb), inode,
						 &tmp_pos, 1, 0, wc->w_di_bh,
						 wc->w_handle, data_ac,
						 meta_ac, NULL);
		/*
		 * This shouldn't happen because we must have already
		 * calculated the correct meta data allocation required. The
		 * internal tree allocation code should know how to increase
		 * transaction credits itself.
		 *
		 * If need be, we could handle -EAGAIN for a
		 * RESTART_TRANS here.
		 */
		mlog_bug_on_msg(ret == -EAGAIN,
				"Inode %llu: EAGAIN return during allocation.\n",
				(unsigned long long)OCFS2_I(inode)->ip_blkno);
		if (ret < 0) {
			mlog_errno(ret);
			goto out;
		}
	} else if (unwritten) {
		ret = ocfs2_mark_extent_written(inode, wc->w_di_bh,
						wc->w_handle, cpos, 1, phys,
						meta_ac, &wc->w_dealloc);
		if (ret < 0) {
			mlog_errno(ret);
			goto out;
		}
	}

	if (should_zero)
		v_blkno = ocfs2_clusters_to_blocks(inode->i_sb, cpos);
	else
		v_blkno = user_pos >> inode->i_sb->s_blocksize_bits;

	/*
	 * The only reason this should fail is due to an inability to
	 * find the extent added.
	 */
	ret = ocfs2_extent_map_get_blocks(inode, v_blkno, &p_blkno, NULL,
					  NULL);
	if (ret < 0) {
		ocfs2_error(inode->i_sb, "Corrupting extend for inode %llu, "
			    "at logical block %llu",
			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
			    (unsigned long long)v_blkno);
		goto out;
	}

	BUG_ON(p_blkno == 0);

	for(i = 0; i < wc->w_num_pages; i++) {
		int tmpret;

		tmpret = ocfs2_prepare_page_for_write(inode, &p_blkno, wc,
						      wc->w_pages[i], cpos,
						      user_pos, user_len,
						      should_zero);
		if (tmpret) {
			mlog_errno(tmpret);
			if (ret == 0)
				tmpret = ret;
		}
	}

	/*
	 * We only have cleanup to do in case of allocating write.
	 */
	if (ret && new)
		ocfs2_write_failure(inode, wc, user_pos, user_len);

out:

	return ret;
}

static int ocfs2_write_cluster_by_desc(struct address_space *mapping,
				       struct ocfs2_alloc_context *data_ac,
				       struct ocfs2_alloc_context *meta_ac,
				       struct ocfs2_write_ctxt *wc,
				       loff_t pos, unsigned len)
{
	int ret, i;
	loff_t cluster_off;
	unsigned int local_len = len;
	struct ocfs2_write_cluster_desc *desc;
	struct ocfs2_super *osb = OCFS2_SB(mapping->host->i_sb);

	for (i = 0; i < wc->w_clen; i++) {
		desc = &wc->w_desc[i];

		/*
		 * We have to make sure that the total write passed in
		 * doesn't extend past a single cluster.
		 */
		local_len = len;
		cluster_off = pos & (osb->s_clustersize - 1);
		if ((cluster_off + local_len) > osb->s_clustersize)
			local_len = osb->s_clustersize - cluster_off;

		ret = ocfs2_write_cluster(mapping, desc->c_phys,
					  desc->c_unwritten, data_ac, meta_ac,
					  wc, desc->c_cpos, pos, local_len);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		len -= local_len;
		pos += local_len;
	}

	ret = 0;
out:
	return ret;
}

/*
 * ocfs2_write_end() wants to know which parts of the target page it
 * should complete the write on. It's easiest to compute them ahead of
 * time when a more complete view of the write is available.
 */
static void ocfs2_set_target_boundaries(struct ocfs2_super *osb,
					struct ocfs2_write_ctxt *wc,
					loff_t pos, unsigned len, int alloc)
{
	struct ocfs2_write_cluster_desc *desc;

	wc->w_target_from = pos & (PAGE_CACHE_SIZE - 1);
	wc->w_target_to = wc->w_target_from + len;

	if (alloc == 0)
		return;

	/*
	 * Allocating write - we may have different boundaries based
	 * on page size and cluster size.
	 *
	 * NOTE: We can no longer compute one value from the other as
	 * the actual write length and user provided length may be
	 * different.
	 */

	if (wc->w_large_pages) {
		/*
		 * We only care about the 1st and last cluster within
		 * our range and whether they should be zero'd or not. Either
		 * value may be extended out to the start/end of a
		 * newly allocated cluster.
		 */
		desc = &wc->w_desc[0];
		if (ocfs2_should_zero_cluster(desc))
			ocfs2_figure_cluster_boundaries(osb,
							desc->c_cpos,
							&wc->w_target_from,
							NULL);

		desc = &wc->w_desc[wc->w_clen - 1];
		if (ocfs2_should_zero_cluster(desc))
			ocfs2_figure_cluster_boundaries(osb,
							desc->c_cpos,
							NULL,
							&wc->w_target_to);
	} else {
		wc->w_target_from = 0;
		wc->w_target_to = PAGE_CACHE_SIZE;
	}
}

/*
 * Populate each single-cluster write descriptor in the write context
 * with information about the i/o to be done.
 *
 * Returns the number of clusters that will have to be allocated, as
 * well as a worst case estimate of the number of extent records that
 * would have to be created during a write to an unwritten region.
 */
static int ocfs2_populate_write_desc(struct inode *inode,
				     struct ocfs2_write_ctxt *wc,
				     unsigned int *clusters_to_alloc,
				     unsigned int *extents_to_split)
{
	int ret;
	struct ocfs2_write_cluster_desc *desc;
	unsigned int num_clusters = 0;
	unsigned int ext_flags = 0;
	u32 phys = 0;
	int i;

	*clusters_to_alloc = 0;
	*extents_to_split = 0;

	for (i = 0; i < wc->w_clen; i++) {
		desc = &wc->w_desc[i];
		desc->c_cpos = wc->w_cpos + i;

		if (num_clusters == 0) {
			/*
			 * Need to look up the next extent record.
			 */
			ret = ocfs2_get_clusters(inode, desc->c_cpos, &phys,
						 &num_clusters, &ext_flags);
			if (ret) {
				mlog_errno(ret);
				goto out;
			}

			/*
			 * Assume worst case - that we're writing in
			 * the middle of the extent.
			 *
			 * We can assume that the write proceeds from
			 * left to right, in which case the extent
			 * insert code is smart enough to coalesce the
			 * next splits into the previous records created.
			 */