ocfs2: use c_new to indicate newly allocated extents

To support direct io in ocfs2_write_begin_nolock & ocfs2_write_end_nolock.

There is a problem in ocfs2's direct io implement: if system crashed
after extents allocated, and before data return, we will get a extent
with dirty data on disk.  This problem violate the journal=order
semantics, which means meta changes take effect after data written to
disk.  To resolve this issue, direct write can use the UNWRITTEN flag to
describe a extent during direct data writeback.  The direct write
procedure should act in the following order:

phase 1: alloc extent with UNWRITTEN flag
phase 2: submit direct data to disk, add zero page to page cache
phase 3: clear UNWRITTEN flag when data has been written to disk

This patch is to change the 'c_unwritten' member of
ocfs2_write_cluster_desc to 'c_clear_unwritten'.  Means whether to clear
the unwritten flag.  It do not care if a extent is allocated or not.
And use 'c_new' to specify a newly allocated extent.  So the direct io
procedure can use c_clear_unwritten to control the UNWRITTEN bit on
extent.

Signed-off-by: Ryan Ding <ryan.ding@oracle.com>
Reviewed-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 69d7392f56d8322e92964270d922a11982955579..516ea896f13c051f19015af551c6e7258a6e886f 100644 (file)
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1212,7 +1212,7 @@ struct ocfs2_write_cluster_desc {
         * filled.
         */
        unsigned        c_new;
-       unsigned        c_unwritten;
+       unsigned        c_clear_unwritten;
        unsigned        c_needs_zero;
 };
 
@@ -1588,19 +1588,19 @@ out:
  * Prepare a single cluster for write one cluster into the file.
  */
 static int ocfs2_write_cluster(struct address_space *mapping,
-                              u32 phys, unsigned int unwritten,
+                              u32 phys, unsigned int new,
+                              unsigned int clear_unwritten,
                               unsigned int should_zero,
                               struct ocfs2_alloc_context *data_ac,
                               struct ocfs2_alloc_context *meta_ac,
                               struct ocfs2_write_ctxt *wc, u32 cpos,
                               loff_t user_pos, unsigned user_len)
 {
-       int ret, i, new;
+       int ret, i;
        u64 v_blkno, p_blkno;
        struct inode *inode = mapping->host;
        struct ocfs2_extent_tree et;
 
-       new = phys == 0 ? 1 : 0;
        if (new) {
                u32 tmp_pos;
 
@@ -1610,9 +1610,9 @@ static int ocfs2_write_cluster(struct address_space *mapping,
                 */
                tmp_pos = cpos;
                ret = ocfs2_add_inode_data(OCFS2_SB(inode->i_sb), inode,
-                                          &tmp_pos, 1, 0, wc->w_di_bh,
-                                          wc->w_handle, data_ac,
-                                          meta_ac, NULL);
+                                          &tmp_pos, 1, !clear_unwritten,
+                                          wc->w_di_bh, wc->w_handle,
+                                          data_ac, meta_ac, NULL);
                /*
                 * This shouldn't happen because we must have already
                 * calculated the correct meta data allocation required. The
@@ -1629,7 +1629,7 @@ static int ocfs2_write_cluster(struct address_space *mapping,
                        mlog_errno(ret);
                        goto out;
                }
-       } else if (unwritten) {
+       } else if (clear_unwritten) {
                ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode),
                                              wc->w_di_bh);
                ret = ocfs2_mark_extent_written(inode, &et,
@@ -1712,7 +1712,8 @@ static int ocfs2_write_cluster_by_desc(struct address_space *mapping,
                        local_len = osb->s_clustersize - cluster_off;
 
                ret = ocfs2_write_cluster(mapping, desc->c_phys,
-                                         desc->c_unwritten,
+                                         desc->c_new,
+                                         desc->c_clear_unwritten,
                                          desc->c_needs_zero,
                                          data_ac, meta_ac,
                                          wc, desc->c_cpos, pos, local_len);
@@ -1857,11 +1858,12 @@ static int ocfs2_populate_write_desc(struct inode *inode,
                if (phys == 0) {
                        desc->c_new = 1;
                        desc->c_needs_zero = 1;
+                       desc->c_clear_unwritten = 1;
                        *clusters_to_alloc = *clusters_to_alloc + 1;
                }
 
                if (ext_flags & OCFS2_EXT_UNWRITTEN) {
-                       desc->c_unwritten = 1;
+                       desc->c_clear_unwritten = 1;
                        desc->c_needs_zero = 1;
                }