ext4: refactor punch hole code

Move common code in ext4_ind_punch_hole() and ext4_ext_punch_hole()
into ext4_punch_hole().  This saves over 150 lines of code.

This also fixes a potential bug when the punch_hole() code is racing
against indirect-to-extents or extents-to-indirect migation.  We are
currently using i_mutex to protect against changes to the inode flag;
specifically, the append-only, immutable, and extents inode flags.  So
we need to take i_mutex before deciding whether to use the
extents-specific or indirect-specific punch_hole code.

Also, there was a missing call to ext4_inode_block_unlocked_dio() in
the indirect punch codepath.  This was added in commit 02d262dffcf4c
to block DIO readers racing against the punch operation in the
codepath for extent-mapped inodes, but it was missing for
indirect-block mapped inodes.  One of the advantages of refactoring
the code is that it makes such oversights much less likely.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

1 files changed, 2 insertions, 156 deletions

diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index c0f9e4699f0..d8846779f4e 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -1434,8 +1434,8 @@ err:
 	return ret;
 }
 
-static int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
-				 ext4_lblk_t first, ext4_lblk_t stop)
+int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
+			  ext4_lblk_t first, ext4_lblk_t stop)
 {
 	int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
 	int level, ret = 0;
@@ -1469,157 +1469,3 @@ err:
 	return ret;
 }
 
-int ext4_ind_punch_hole(struct file *file, loff_t offset, loff_t length)
-{
-	struct inode *inode = file_inode(file);
-	struct super_block *sb = inode->i_sb;
-	ext4_lblk_t first_block, stop_block;
-	struct address_space *mapping = inode->i_mapping;
-	handle_t *handle = NULL;
-	loff_t first_page, last_page, page_len;
-	loff_t first_page_offset, last_page_offset;
-	int err = 0;
-
-	/*
-	 * Write out all dirty pages to avoid race conditions
-	 * Then release them.
-	 */
-	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
-		err = filemap_write_and_wait_range(mapping,
-			offset, offset + length - 1);
-		if (err)
-			return err;
-	}
-
-	mutex_lock(&inode->i_mutex);
-	/* It's not possible punch hole on append only file */
-	if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
-		err = -EPERM;
-		goto out_mutex;
-	}
-	if (IS_SWAPFILE(inode)) {
-		err = -ETXTBSY;
-		goto out_mutex;
-	}
-
-	/* No need to punch hole beyond i_size */
-	if (offset >= inode->i_size)
-		goto out_mutex;
-
-	/*
-	 * If the hole extents beyond i_size, set the hole
-	 * to end after the page that contains i_size
-	 */
-	if (offset + length > inode->i_size) {
-		length = inode->i_size +
-		    PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
-		    offset;
-	}
-
-	first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	last_page = (offset + length) >> PAGE_CACHE_SHIFT;
-
-	first_page_offset = first_page << PAGE_CACHE_SHIFT;
-	last_page_offset = last_page << PAGE_CACHE_SHIFT;
-
-	/* Now release the pages */
-	if (last_page_offset > first_page_offset) {
-		truncate_pagecache_range(inode, first_page_offset,
-					 last_page_offset - 1);
-	}
-
-	/* Wait all existing dio works, newcomers will block on i_mutex */
-	inode_dio_wait(inode);
-
-	handle = start_transaction(inode);
-	if (IS_ERR(handle))
-		goto out_mutex;
-
-	/*
-	 * Now we need to zero out the non-page-aligned data in the
-	 * pages at the start and tail of the hole, and unmap the buffer
-	 * heads for the block aligned regions of the page that were
-	 * completely zerod.
-	 */
-	if (first_page > last_page) {
-		/*
-		 * If the file space being truncated is contained within a page
-		 * just zero out and unmap the middle of that page
-		 */
-		err = ext4_discard_partial_page_buffers(handle,
-			mapping, offset, length, 0);
-		if (err)
-			goto out;
-	} else {
-		/*
-		 * Zero out and unmap the paritial page that contains
-		 * the start of the hole
-		 */
-		page_len = first_page_offset - offset;
-		if (page_len > 0) {
-			err = ext4_discard_partial_page_buffers(handle, mapping,
-							offset, page_len, 0);
-			if (err)
-				goto out;
-		}
-
-		/*
-		 * Zero out and unmap the partial page that contains
-		 * the end of the hole
-		 */
-		page_len = offset + length - last_page_offset;
-		if (page_len > 0) {
-			err = ext4_discard_partial_page_buffers(handle, mapping,
-						last_page_offset, page_len, 0);
-			if (err)
-				goto out;
-		}
-	}
-
-	/*
-	 * If i_size contained in the last page, we need to
-	 * unmap and zero the paritial page after i_size
-	 */
-	if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
-	    inode->i_size % PAGE_CACHE_SIZE != 0) {
-		page_len = PAGE_CACHE_SIZE -
-			(inode->i_size & (PAGE_CACHE_SIZE - 1));
-		if (page_len > 0) {
-			err = ext4_discard_partial_page_buffers(handle,
-				mapping, inode->i_size, page_len, 0);
-			if (err)
-				goto out;
-		}
-	}
-
-	first_block = (offset + sb->s_blocksize - 1) >>
-		EXT4_BLOCK_SIZE_BITS(sb);
-	stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
-
-	if (first_block >= stop_block)
-		goto out;
-
-	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode);
-
-	err = ext4_es_remove_extent(inode, first_block,
-				    stop_block - first_block);
-	err = ext4_free_hole_blocks(handle, inode, first_block, stop_block);
-
-	ext4_discard_preallocations(inode);
-
-	if (IS_SYNC(inode))
-		ext4_handle_sync(handle);
-
-	up_write(&EXT4_I(inode)->i_data_sem);
-
-out:
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
-	ext4_journal_stop(handle);
-
-out_mutex:
-	mutex_unlock(&inode->i_mutex);
-
-	return err;
-}