[PATCH 49/52] ext4: fix delalloc i_disksize early update issue

[Theodore Ts'o]

From: Mingming Cao <cmm@xxxxxxxxxx>

Ext4_da_write_end() used walk_page_buffers() with a callback function of
ext4_bh_unmapped_or_delay() to check if it extended the file size
without allocating any blocks (since in this case i_disksize needs to be
updated).  However, this is didn't work proprely because the buffer head
has not been marked dirty yet --- this is done later in
block_commit_write() --- which caused ext4_bh_unmapped_or_delay() to
always return false.

In addition, walk_page_buffers() checks all of the buffer heads covering
the page, and the only buffer_head that should be checked is the one
covering the end of the write.  Otherwise, given a 1k blocksize
filesystem and a 4k page size, the buffer head covering the first 1k
stripe of the file could be unmapped (because it was a sparse file), and
the second or third buffer_head covering that page could be mapped, and
using walk_page_buffers() would fail in this case since it would stop at
the first unmapped buffer_head and return true.

The core problem is that walk_page_buffers() was intended to do work in
a callback function, and a non-zero return value indicated a failure,
which termined the walk of the buffer heads covering the page.  It was
not intended to be used with a boolean function, such as
ext4_bh_unmapped_or_delay().

Add addtional fix from Aneesh to protect i_disksize update rave with truncate.

Signed-off-by: Mingming Cao <cmm@xxxxxxxxxx>
Signed-off-by: Aneesh Kumar <aneesh.kumar@xxxxxxxxx>
Signed-off-by: "Theodore Ts'o" <tytso@xxxxxxx>
---
 fs/ext4/inode.c |   63 +++++++++++++++++++++++++++++++++++++++++--------------
 1 files changed, 47 insertions(+), 16 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 6aa0ea8..5bacf73 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1891,6 +1891,29 @@ out:
 	return ret;
 }
 
+/*
+ * Check if we should update i_disksize
+ * when write to the end of file but not require block allocation
+ */
+static int ext4_da_should_update_i_disksize(struct page *page,
+					 unsigned long offset)
+{
+	struct buffer_head *bh;
+	struct inode *inode = page->mapping->host;
+	unsigned int idx;
+	int i;
+
+	bh = page_buffers(page);
+	idx = offset >> inode->i_blkbits;
+
+	for (i=0; i < idx; i++)
+		bh = bh->b_this_page;
+
+	if (!buffer_mapped(bh) || (buffer_delay(bh)))
+		return 0;
+	return 1;
+}
+
 static int ext4_da_write_end(struct file *file,
 				struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
@@ -1900,6 +1923,10 @@ static int ext4_da_write_end(struct file *file,
 	int ret = 0, ret2;
 	handle_t *handle = ext4_journal_current_handle();
 	loff_t new_i_size;
+	unsigned long start, end;
+
+	start = pos & (PAGE_CACHE_SIZE - 1);
+	end = start + copied -1;
 
 	/*
 	 * generic_write_end() will run mark_inode_dirty() if i_size
@@ -1908,18 +1935,23 @@ static int ext4_da_write_end(struct file *file,
 	 */
 
 	new_i_size = pos + copied;
-	if (new_i_size > EXT4_I(inode)->i_disksize)
-		if (!walk_page_buffers(NULL, page_buffers(page),
-				       0, len, NULL, ext4_bh_unmapped_or_delay)){
-			/*
-			 * Updating i_disksize when extending file without
-			 * needing block allocation
-			 */
-			if (ext4_should_order_data(inode))
-				ret = ext4_jbd2_file_inode(handle, inode);
+	if (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) {
+				/*
+				 * Updating i_disksize when extending file
+				 * without needing block allocation
+				 */
+				if (ext4_should_order_data(inode))
+					ret = ext4_jbd2_file_inode(handle,
+								   inode);
 
-			EXT4_I(inode)->i_disksize = new_i_size;
+				EXT4_I(inode)->i_disksize = new_i_size;
+			}
+			up_write(&EXT4_I(inode)->i_data_sem);
 		}
+	}
 	ret2 = generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
 	copied = ret2;
@@ -2965,6 +2997,11 @@ void ext4_truncate(struct inode *inode)
 		goto out_stop;
 
 	/*
+	 * From here we block out all ext4_get_block() callers who want to
+	 * modify the block allocation tree.
+	 */
+	down_write(&ei->i_data_sem);
+	/*
 	 * The orphan list entry will now protect us from any crash which
 	 * occurs before the truncate completes, so it is now safe to propagate
 	 * the new, shorter inode size (held for now in i_size) into the
@@ -2973,12 +3010,6 @@ void ext4_truncate(struct inode *inode)
 	 */
 	ei->i_disksize = inode->i_size;
 
-	/*
-	 * From here we block out all ext4_get_block() callers who want to
-	 * modify the block allocation tree.
-	 */
-	down_write(&ei->i_data_sem);
-
 	if (n == 1) {		/* direct blocks */
 		ext4_free_data(handle, inode, NULL, i_data+offsets[0],
 			       i_data + EXT4_NDIR_BLOCKS);
-- 
1.5.6.rc3.1.g36b7.dirty

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/