Merge tag 'gfs2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-fixes

Pull GFS2 fixes from Steven Whitehouse:
 "Here is a set of small fixes for GFS2.  There is a fix to drop
  s_umount which is copied in from the core vfs, two patches relate to a
  hard to hit "use after free" and memory leak.  Two patches related to
  using DIO and buffered I/O on the same file to ensure correct
  operation in relation to glock state changes.  The final patch adds an
  RCU read lock to ensure correct locking on an error path"

* tag 'gfs2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-fixes:
  GFS2: Fix unsafe dereference in dump_holder()
  GFS2: Wait for async DIO in glock state changes
  GFS2: Fix incorrect invalidation for DIO/buffered I/O
  GFS2: Fix slab memory leak in gfs2_bufdata
  GFS2: Fix use-after-free race when calling gfs2_remove_from_ail
  GFS2: don't hold s_umount over blkdev_put

1 files changed, 30 insertions, 0 deletions

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index b7fc035a694..73f3e4ee403 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -986,6 +986,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	struct address_space *mapping = inode->i_mapping;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	int rv;
@@ -1006,6 +1007,35 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 	if (rv != 1)
 		goto out; /* dio not valid, fall back to buffered i/o */
 
+	/*
+	 * Now since we are holding a deferred (CW) lock at this point, you
+	 * might be wondering why this is ever needed. There is a case however
+	 * where we've granted a deferred local lock against a cached exclusive
+	 * glock. That is ok provided all granted local locks are deferred, but
+	 * it also means that it is possible to encounter pages which are
+	 * cached and possibly also mapped. So here we check for that and sort
+	 * them out ahead of the dio. The glock state machine will take care of
+	 * everything else.
+	 *
+	 * If in fact the cached glock state (gl->gl_state) is deferred (CW) in
+	 * the first place, mapping->nr_pages will always be zero.
+	 */
+	if (mapping->nrpages) {
+		loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
+		loff_t len = iov_length(iov, nr_segs);
+		loff_t end = PAGE_ALIGN(offset + len) - 1;
+
+		rv = 0;
+		if (len == 0)
+			goto out;
+		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+			unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
+		rv = filemap_write_and_wait_range(mapping, lstart, end);
+		if (rv)
+			return rv;
+		truncate_inode_pages_range(mapping, lstart, end);
+	}
+
 	rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
 				  offset, nr_segs, gfs2_get_block_direct,
 				  NULL, NULL, 0);