ext4: Fix mmap/truncate race when blocksize < pagesize && delayed allocation

It is possible to see buffer_heads which are not mapped in the
writepage callback in the following scneario (where the fs blocksize
is 1k and the page size is 4k):

1) truncate(f, 1024)
2) mmap(f, 0, 4096)
3) a[0] = 'a'
4) truncate(f, 4096)
5) writepage(...)

Now if we get a writepage callback immediately after (4) and before an
attempt to write at any other offset via mmap address (which implies we
are yet to get a pagefault and do a get_block) what we would have is the
page which is dirty have first block allocated and the other three
buffer_heads unmapped.

In the above case the writepage should go ahead and try to write the
first blocks and clear the page_dirty flag. Further attempts to write
to the page will again create a fault and result in allocating blocks
and marking page dirty.  If we don't write any other offset via mmap
address we would still have written the first block to the disk and
rest of the space will be considered as a hole.

So to address this, we change all of the places where we look for
delayed, unmapped, or unwritten buffer heads, and only check for
delayed or unwritten buffer heads instead.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index b87b68cd32413a76654b747cf4d81f739a0e7881..1275f34589c73cf27526253da8064b2471274a94 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2305,15 +2305,9 @@ flush_it:
        return;
 }
 
-static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
+static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
 {
-       /*
-        * unmapped buffer is possible for holes.
-        * delay buffer is possible with delayed allocation.
-        * We also need to consider unwritten buffer as unmapped.
-        */
-       return (!buffer_mapped(bh) || buffer_delay(bh) ||
-                               buffer_unwritten(bh)) && buffer_dirty(bh);
+       return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh);
 }
 
 /*
@@ -2400,7 +2394,7 @@ static int __mpage_da_writepage(struct page *page,
                         * Otherwise we won't make progress
                         * with the page in ext4_da_writepage
                         */
-                       if (ext4_bh_unmapped_or_delay(NULL, bh)) {
+                       if (ext4_bh_delay_or_unwritten(NULL, bh)) {
                                mpage_add_bh_to_extent(mpd, logical,
                                                       bh->b_size,
                                                       bh->b_state);
@@ -2517,7 +2511,6 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
         * so call get_block_wrap with create = 0
         */
        ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0);
-       BUG_ON(create && ret == 0);
        if (ret > 0) {
                bh_result->b_size = (ret << inode->i_blkbits);
                ret = 0;
@@ -2533,7 +2526,7 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
  *   - grab_page_cache when doing write_begin (have journal handle)
  */
 static int ext4_da_writepage(struct page *page,
-                               struct writeback_control *wbc)
+                            struct writeback_control *wbc)
 {
        int ret = 0;
        loff_t size;
@@ -2551,7 +2544,7 @@ static int ext4_da_writepage(struct page *page,
        if (page_has_buffers(page)) {
                page_bufs = page_buffers(page);
                if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
-                                       ext4_bh_unmapped_or_delay)) {
+                                       ext4_bh_delay_or_unwritten)) {
                        /*
                         * We don't want to do  block allocation
                         * So redirty the page and return
@@ -2584,7 +2577,7 @@ static int ext4_da_writepage(struct page *page,
                        page_bufs = page_buffers(page);
                        /* check whether all are mapped and non delay */
                        if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
-                                               ext4_bh_unmapped_or_delay)) {
+                                               ext4_bh_delay_or_unwritten)) {
                                redirty_page_for_writepage(wbc, page);
                                unlock_page(page);
                                return 0;
@@ -3232,7 +3225,7 @@ static int ext4_normal_writepage(struct page *page,
                 * happily proceed with mapping them and writing the page.
                 */
                BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
-                                       ext4_bh_unmapped_or_delay));
+                                       ext4_bh_delay_or_unwritten));
        }
 
        if (!ext4_journal_current_handle())
@@ -3322,7 +3315,7 @@ static int ext4_journalled_writepage(struct page *page,
                 * happily proceed with mapping them and writing the page.
                 */
                BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
-                                       ext4_bh_unmapped_or_delay));
+                                       ext4_bh_delay_or_unwritten));
        }
 
        if (ext4_journal_current_handle())