1 files changed, 32 insertions, 171 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 240f6e2dc7ee..feaa82fe629d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -18,7 +18,6 @@
  *  Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000
  */
 
-#include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/time.h>
 #include <linux/jbd2.h>
@@ -72,6 +71,9 @@ static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
 static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
 static int __ext4_journalled_writepage(struct page *page, unsigned int len);
 static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh);
+static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+		struct inode *inode, struct page *page, loff_t from,
+		loff_t length, int flags);
 
 /*
  * Test whether an inode is a fast symlink.
@@ -1339,8 +1341,11 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 					clear_buffer_unwritten(bh);
 				}
 
-				/* skip page if block allocation undone */
-				if (buffer_delay(bh) || buffer_unwritten(bh))
+				/*
+				 * skip page if block allocation undone and
+				 * block is dirty
+				 */
+				if (ext4_bh_delay_or_unwritten(NULL, bh))
 					skip_page = 1;
 				bh = bh->b_this_page;
 				block_start += bh->b_size;
@@ -1878,7 +1883,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
  * a[0] = 'a';
  * truncate(f, 4096);
  * we have in the page first buffer_head mapped via page_mkwrite call back
- * but other bufer_heads would be unmapped but dirty(dirty done via the
+ * but other buffer_heads would be unmapped but dirty (dirty done via the
  * do_wp_page). So writepage should write the first block. If we modify
  * the mmap area beyond 1024 we will again get a page_fault and the
  * page_mkwrite callback will do the block allocation and mark the
@@ -2270,6 +2275,7 @@ retry:
 			ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
 			       "%ld pages, ino %lu; err %d", __func__,
 				wbc->nr_to_write, inode->i_ino, ret);
+			blk_finish_plug(&plug);
 			goto out_writepages;
 		}
 
@@ -2386,7 +2392,6 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	pgoff_t index;
 	struct inode *inode = mapping->host;
 	handle_t *handle;
-	loff_t page_len;
 
 	index = pos >> PAGE_CACHE_SHIFT;
 
@@ -2433,13 +2438,6 @@ retry:
 		 */
 		if (pos + len > inode->i_size)
 			ext4_truncate_failed_write(inode);
-	} else {
-		page_len = pos & (PAGE_CACHE_SIZE - 1);
-		if (page_len > 0) {
-			ret = ext4_discard_partial_page_buffers_no_lock(handle,
-				inode, page, pos - page_len, page_len,
-				EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
-		}
 	}
 
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -2482,7 +2480,6 @@ static int ext4_da_write_end(struct file *file,
 	loff_t new_i_size;
 	unsigned long start, end;
 	int write_mode = (int)(unsigned long)fsdata;
-	loff_t page_len;
 
 	if (write_mode == FALL_BACK_TO_NONDELALLOC) {
 		if (ext4_should_order_data(inode)) {
@@ -2507,7 +2504,7 @@ static int ext4_da_write_end(struct file *file,
 	 */
 
 	new_i_size = pos + copied;
-	if (new_i_size > EXT4_I(inode)->i_disksize) {
+	if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
 		if (ext4_da_should_update_i_disksize(page, end)) {
 			down_write(&EXT4_I(inode)->i_data_sem);
 			if (new_i_size > EXT4_I(inode)->i_disksize) {
@@ -2531,16 +2528,6 @@ static int ext4_da_write_end(struct file *file,
 	}
 	ret2 = generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
-
-	page_len = PAGE_CACHE_SIZE -
-			((pos + copied - 1) & (PAGE_CACHE_SIZE - 1));
-
-	if (page_len > 0) {
-		ret = ext4_discard_partial_page_buffers_no_lock(handle,
-			inode, page, pos + copied - 1, page_len,
-			EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
-	}
-
 	copied = ret2;
 	if (ret2 < 0)
 		ret = ret2;
@@ -2775,15 +2762,16 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 	if (!io_end || !size)
 		goto out;
 
-	ext_debug("ext4_end_io_dio(): io_end 0x%p"
+	ext_debug("ext4_end_io_dio(): io_end 0x%p "
 		  "for inode %lu, iocb 0x%p, offset %llu, size %llu\n",
  		  iocb->private, io_end->inode->i_ino, iocb, offset,
 		  size);
 
+	iocb->private = NULL;
+
 	/* if not aio dio with unwritten extents, just free io and return */
 	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
 		ext4_free_io_end(io_end);
-		iocb->private = NULL;
 out:
 		if (is_async)
 			aio_complete(iocb, ret, 0);
@@ -2807,7 +2795,6 @@ out:
 
 	/* queue the work to convert unwritten extents to written */
 	queue_work(wq, &io_end->work);
-	iocb->private = NULL;
 
 	/* XXX: probably should move into the real I/O completion handler */
 	inode_dio_done(inode);
@@ -3176,7 +3163,7 @@ int ext4_discard_partial_page_buffers(handle_t *handle,
  *
  * Returns zero on sucess or negative on failure.
  */
-int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
 		struct inode *inode, struct page *page, loff_t from,
 		loff_t length, int flags)
 {
@@ -3202,26 +3189,8 @@ int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
 
 	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
 
-	if (!page_has_buffers(page)) {
-		/*
-		 * If the range to be discarded covers a partial block
-		 * we need to get the page buffers.  This is because
-		 * partial blocks cannot be released and the page needs
-		 * to be updated with the contents of the block before
-		 * we write the zeros on top of it.
-		 */
-		if ((from & (blocksize - 1)) ||
-		    ((from + length) & (blocksize - 1))) {
-			create_empty_buffers(page, blocksize, 0);
-		} else {
-			/*
-			 * If there are no partial blocks,
-			 * there is nothing to update,
-			 * so we can return now
-			 */
-			return 0;
-		}
-	}
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, blocksize, 0);
 
 	/* Find the buffer that contains "offset" */
 	bh = page_buffers(page);
@@ -3334,126 +3303,6 @@ next:
 	return err;
 }
 
-/*
- * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
- * up to the end of the block which corresponds to `from'.
- * This required during truncate. We need to physically zero the tail end
- * of that block so it doesn't yield old data if the file is later grown.
- */
-int ext4_block_truncate_page(handle_t *handle,
-		struct address_space *mapping, loff_t from)
-{
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned length;
-	unsigned blocksize;
-	struct inode *inode = mapping->host;
-
-	blocksize = inode->i_sb->s_blocksize;
-	length = blocksize - (offset & (blocksize - 1));
-
-	return ext4_block_zero_page_range(handle, mapping, from, length);
-}
-
-/*
- * ext4_block_zero_page_range() zeros out a mapping of length 'length'
- * starting from file offset 'from'.  The range to be zero'd must
- * be contained with in one block.  If the specified range exceeds
- * the end of the block it will be shortened to end of the block
- * that cooresponds to 'from'
- */
-int ext4_block_zero_page_range(handle_t *handle,
-		struct address_space *mapping, loff_t from, loff_t length)
-{
-	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
-	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned blocksize, max, pos;
-	ext4_lblk_t iblock;
-	struct inode *inode = mapping->host;
-	struct buffer_head *bh;
-	struct page *page;
-	int err = 0;
-
-	page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
-				   mapping_gfp_mask(mapping) & ~__GFP_FS);
-	if (!page)
-		return -ENOMEM;
-
-	blocksize = inode->i_sb->s_blocksize;
-	max = blocksize - (offset & (blocksize - 1));
-
-	/*
-	 * correct length if it does not fall between
-	 * 'from' and the end of the block
-	 */
-	if (length > max || length < 0)
-		length = max;
-
-	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
-
-	if (!page_has_buffers(page))
-		create_empty_buffers(page, blocksize, 0);
-
-	/* Find the buffer that contains "offset" */
-	bh = page_buffers(page);
-	pos = blocksize;
-	while (offset >= pos) {
-		bh = bh->b_this_page;
-		iblock++;
-		pos += blocksize;
-	}
-
-	err = 0;
-	if (buffer_freed(bh)) {
-		BUFFER_TRACE(bh, "freed: skip");
-		goto unlock;
-	}
-
-	if (!buffer_mapped(bh)) {
-		BUFFER_TRACE(bh, "unmapped");
-		ext4_get_block(inode, iblock, bh, 0);
-		/* unmapped? It's a hole - nothing to do */
-		if (!buffer_mapped(bh)) {
-			BUFFER_TRACE(bh, "still unmapped");
-			goto unlock;
-		}
-	}
-
-	/* Ok, it's mapped. Make sure it's up-to-date */
-	if (PageUptodate(page))
-		set_buffer_uptodate(bh);
-
-	if (!buffer_uptodate(bh)) {
-		err = -EIO;
-		ll_rw_block(READ, 1, &bh);
-		wait_on_buffer(bh);
-		/* Uhhuh. Read error. Complain and punt. */
-		if (!buffer_uptodate(bh))
-			goto unlock;
-	}
-
-	if (ext4_should_journal_data(inode)) {
-		BUFFER_TRACE(bh, "get write access");
-		err = ext4_journal_get_write_access(handle, bh);
-		if (err)
-			goto unlock;
-	}
-
-	zero_user(page, offset, length);
-
-	BUFFER_TRACE(bh, "zeroed end of block");
-
-	err = 0;
-	if (ext4_should_journal_data(inode)) {
-		err = ext4_handle_dirty_metadata(handle, inode, bh);
-	} else
-		mark_buffer_dirty(bh);
-
-unlock:
-	unlock_page(page);
-	page_cache_release(page);
-	return err;
-}
-
 int ext4_can_truncate(struct inode *inode)
 {
 	if (S_ISREG(inode->i_mode))
@@ -3502,7 +3351,7 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
  * transaction, and VFS/VM ensures that ext4_truncate() cannot run
  * simultaneously on behalf of the same inode.
  *
- * As we work through the truncate and commmit bits of it to the journal there
+ * As we work through the truncate and commit bits of it to the journal there
  * is one core, guiding principle: the file's tree must always be consistent on
  * disk.  We must be able to restart the truncate after a crash.
  *
@@ -4680,9 +4529,19 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		return 0;
 	if (is_journal_aborted(journal))
 		return -EROFS;
+	/* We have to allocate physical blocks for delalloc blocks
+	 * before flushing journal. otherwise delalloc blocks can not
+	 * be allocated any more. even more truncate on delalloc blocks
+	 * could trigger BUG by flushing delalloc blocks in journal.
+	 * There is no delalloc block in non-journal data mode.
+	 */
+	if (val && test_opt(inode->i_sb, DELALLOC)) {
+		err = ext4_alloc_da_blocks(inode);
+		if (err < 0)
+			return err;
+	}
 
 	jbd2_journal_lock_updates(journal);
-	jbd2_journal_flush(journal);
 
 	/*
 	 * OK, there are no updates running now, and all cached data is
@@ -4694,8 +4553,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 
 	if (val)
 		ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
-	else
+	else {
+		jbd2_journal_flush(journal);
 		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
+	}
 	ext4_set_aops(inode);
 
 	jbd2_journal_unlock_updates(journal);