ocfs2: teach ocfs2_file_aio_write() about sparse files

Unfortunately, ocfs2 can no longer make use of generic_file_aio_write_nlock()
because allocating writes will require zeroing of pages adjacent to the I/O
for cluster sizes greater than page size.

Implement a custom file write here, which can order page locks for zeroing.
This also has the advantage that cluster locks can easily be ordered outside
of the page locks.

Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>

1 files changed, 38 insertions, 0 deletions

diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index f446a15eab88..eeb2c42483e8 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -30,6 +30,44 @@ handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
                                                          unsigned from,
                                                          unsigned to);
 
+struct ocfs2_write_ctxt;
+typedef int (ocfs2_page_writer)(struct inode *, struct ocfs2_write_ctxt *,
+                                u64 *, unsigned int *, unsigned int *);
+
+ssize_t ocfs2_buffered_write_cluster(struct file *file, loff_t pos,
+                                     size_t count, ocfs2_page_writer *actor,
+                                     void *priv);
+
+struct ocfs2_write_ctxt {
+        size_t                          w_count;
+        loff_t                          w_pos;
+        u32                             w_cpos;
+        unsigned int                    w_finished_copy;
+
+        /* This is true if page_size > cluster_size */
+        unsigned int                    w_large_pages;
+
+        /* Filler callback and private data */
+        ocfs2_page_writer               *w_write_data_page;
+        void                            *w_private;
+
+        /* Only valid for the filler callback */
+        struct page                     *w_this_page;
+        unsigned int                    w_this_page_new;
+};
+
+struct ocfs2_buffered_write_priv {
+        char                            *b_src_buf;
+        const struct iovec              *b_cur_iov; /* Current iovec */
+        size_t                          b_cur_off; /* Offset in the
+                                                    * current iovec */
+};
+int ocfs2_map_and_write_user_data(struct inode *inode,
+                                  struct ocfs2_write_ctxt *wc,
+                                  u64 *p_blkno,
+                                  unsigned int *ret_from,
+                                  unsigned int *ret_to);
+
 /* all ocfs2_dio_end_io()'s fault */
 #define ocfs2_iocb_is_rw_locked(iocb) \
         test_bit(0, (unsigned long *)&iocb->private)