xfs: xfs_seek_data() refinement with unwritten extents check up from page cache

xfs_seek_data() refinement with unwritten extents check up from page cache.

Signed-off-by: Jie Liu <jeff.liu@oracle.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index d78a746b6c7c73dfd75fd551463361b1a8be0d1b..3f9107431dfb3502ef8de0c2e1c3120fb00d4afe 100644 (file)
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1186,8 +1186,6 @@ xfs_seek_data(
        struct inode            *inode = file->f_mapping->host;
        struct xfs_inode        *ip = XFS_I(inode);
        struct xfs_mount        *mp = ip->i_mount;
-       struct xfs_bmbt_irec    map[2];
-       int                     nmap = 2;
        loff_t                  uninitialized_var(offset);
        xfs_fsize_t             isize;
        xfs_fileoff_t           fsbno;
@@ -1203,36 +1201,74 @@ xfs_seek_data(
                goto out_unlock;
        }
 
-       fsbno = XFS_B_TO_FSBT(mp, start);
-
        /*
         * Try to read extents from the first block indicated
         * by fsbno to the end block of the file.
         */
+       fsbno = XFS_B_TO_FSBT(mp, start);
        end = XFS_B_TO_FSB(mp, isize);
+       for (;;) {
+               struct xfs_bmbt_irec    map[2];
+               int                     nmap = 2;
+               unsigned int            i;
 
-       error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
-                              XFS_BMAPI_ENTIRE);
-       if (error)
-               goto out_unlock;
+               error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
+                                      XFS_BMAPI_ENTIRE);
+               if (error)
+                       goto out_unlock;
 
-       /*
-        * Treat unwritten extent as data extent since it might
-        * contains dirty data in page cache.
-        */
-       if (map[0].br_startblock != HOLESTARTBLOCK) {
-               offset = max_t(loff_t, start,
-                              XFS_FSB_TO_B(mp, map[0].br_startoff));
-       } else {
+               /* No extents at given offset, must be beyond EOF */
+               if (nmap == 0) {
+                       error = ENXIO;
+                       goto out_unlock;
+               }
+
+               for (i = 0; i < nmap; i++) {
+                       offset = max_t(loff_t, start,
+                                      XFS_FSB_TO_B(mp, map[i].br_startoff));
+
+                       /* Landed in a data extent */
+                       if (map[i].br_startblock == DELAYSTARTBLOCK ||
+                           (map[i].br_state == XFS_EXT_NORM &&
+                            !isnullstartblock(map[i].br_startblock)))
+                               goto out;
+
+                       /*
+                        * Landed in an unwritten extent, try to search data
+                        * from page cache.
+                        */
+                       if (map[i].br_state == XFS_EXT_UNWRITTEN) {
+                               if (xfs_find_get_desired_pgoff(inode, &map[i],
+                                                       DATA_OFF, &offset))
+                                       goto out;
+                       }
+               }
+
+               /*
+                * map[0] is hole or its an unwritten extent but
+                * without data in page cache.  Probably means that
+                * we are reading after EOF if nothing in map[1].
+                */
                if (nmap == 1) {
                        error = ENXIO;
                        goto out_unlock;
                }
 
-               offset = max_t(loff_t, start,
-                              XFS_FSB_TO_B(mp, map[1].br_startoff));
+               ASSERT(i > 1);
+
+               /*
+                * Nothing was found, proceed to the next round of search
+                * if reading offset not beyond or hit EOF.
+                */
+               fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
+               start = XFS_FSB_TO_B(mp, fsbno);
+               if (start >= isize) {
+                       error = ENXIO;
+                       goto out_unlock;
+               }
        }
 
+out:
        if (offset != file->f_pos)
                file->f_pos = offset;