ext4: fix unwritten counter leakage

ext4_set_io_unwritten_flag() will increment i_unwritten counter, so
once we mark end_io with EXT4_END_IO_UNWRITTEN we have to revert it back
on error path.

 - add missed error checks to prevent counter leakage
 - ext4_end_io_nolock() will clear EXT4_END_IO_UNWRITTEN flag to signal
   that conversion finished.
 - add BUG_ON to ext4_free_end_io() to prevent similar leakage in future.

Visible effect of this bug is that unaligned aio_stress may deadlock

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index a1f56c3e773b2e2b5ab9c4be3f38f4716d0e9159..54a94426ef7b2ef91d4b9105280399e3addc8144 100644 (file)
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3633,6 +3633,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
        if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
                ret = ext4_split_unwritten_extents(handle, inode, map,
                                                   path, flags);
+               if (ret <= 0)
+                       goto out;
                /*
                 * Flag the inode(non aio case) or end_io struct (aio case)
                 * that this IO needs to conversion to written when IO is
@@ -3878,6 +3880,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
        struct ext4_allocation_request ar;
        ext4_io_end_t *io = ext4_inode_aio(inode);
        ext4_lblk_t cluster_offset;
+       int set_unwritten = 0;
 
        ext_debug("blocks %u/%u requested for inode %lu\n",
                  map->m_lblk, map->m_len, inode->i_ino);
@@ -4100,13 +4103,8 @@ got_allocated_blocks:
                 * For non asycn direct IO case, flag the inode state
                 * that we need to perform conversion when IO is done.
                 */
-               if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
-                       if (io)
-                               ext4_set_io_unwritten_flag(inode, io);
-                       else
-                               ext4_set_inode_state(inode,
-                                                    EXT4_STATE_DIO_UNWRITTEN);
-               }
+               if ((flags & EXT4_GET_BLOCKS_PRE_IO))
+                       set_unwritten = 1;
                if (ext4_should_dioread_nolock(inode))
                        map->m_flags |= EXT4_MAP_UNINIT;
        }
@@ -4118,6 +4116,15 @@ got_allocated_blocks:
        if (!err)
                err = ext4_ext_insert_extent(handle, inode, path,
                                             &newex, flags);
+
+       if (!err && set_unwritten) {
+               if (io)
+                       ext4_set_io_unwritten_flag(inode, io);
+               else
+                       ext4_set_inode_state(inode,
+                                            EXT4_STATE_DIO_UNWRITTEN);
+       }
+
        if (err && free_on_err) {
                int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
                        EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;

diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index de77e31cc1191e2588308b64a67a418740cf290b..997002218228424a39c6c415225368e41c076aea 100644 (file)
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -71,6 +71,8 @@ void ext4_free_io_end(ext4_io_end_t *io)
        int i;
 
        BUG_ON(!io);
+       BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN);
+
        if (io->page)
                put_page(io->page);
        for (i = 0; i < io->num_io_pages; i++)
@@ -94,6 +96,8 @@ int ext4_end_io_nolock(ext4_io_end_t *io)
        ssize_t size = io->size;
        int ret = 0;
 
+       BUG_ON(!(io->flag & EXT4_IO_END_UNWRITTEN));
+
        ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
                   "list->prev 0x%p\n",
                   io, inode->i_ino, io->list.next, io->list.prev);
@@ -106,7 +110,7 @@ int ext4_end_io_nolock(ext4_io_end_t *io)
                         "(inode %lu, offset %llu, size %zd, error %d)",
                         inode->i_ino, offset, size, ret);
        }
-
+       io->flag &= ~EXT4_IO_END_UNWRITTEN;
        if (io->iocb)
                aio_complete(io->iocb, io->result, 0);