xfs: update the finobt on inode free

An inode free operation can have several effects on the finobt. If
all inodes have been freed and the chunk deallocated, we remove the
finobt record. If the inode chunk was previously full, we must
insert a new record based on the existing inobt record. Otherwise,
we modify the record in place.

Create the xfs_ifree_finobt() function to identify the potential
scenarios and update the finobt appropriately.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>

diff --git a/libxfs/xfs_ialloc.c b/libxfs/xfs_ialloc.c
index d81ae0a8d7a1acc0a8c5aeaccc168bd8dc90ac15..5462c54d046e4eb52b48a74b65ef3ab8062d2069 100644 (file)
--- a/libxfs/xfs_ialloc.c
+++ b/libxfs/xfs_ialloc.c
@@ -1453,6 +1453,106 @@ error0:
        return error;
 }
 
+/*
+ * Free an inode in the free inode btree.
+ */
+STATIC int
+xfs_difree_finobt(
+       struct xfs_mount                *mp,
+       struct xfs_trans                *tp,
+       struct xfs_buf                  *agbp,
+       xfs_agino_t                     agino,
+       struct xfs_inobt_rec_incore     *ibtrec) /* inobt record */
+{
+       struct xfs_agi                  *agi = XFS_BUF_TO_AGI(agbp);
+       xfs_agnumber_t                  agno = be32_to_cpu(agi->agi_seqno);
+       struct xfs_btree_cur            *cur;
+       struct xfs_inobt_rec_incore     rec;
+       int                             offset = agino - ibtrec->ir_startino;
+       int                             error;
+       int                             i;
+
+       cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_FINO);
+
+       error = xfs_inobt_lookup(cur, ibtrec->ir_startino, XFS_LOOKUP_EQ, &i);
+       if (error)
+               goto error;
+       if (i == 0) {
+               /*
+                * If the record does not exist in the finobt, we must have just
+                * freed an inode in a previously fully allocated chunk. If not,
+                * something is out of sync.
+                */
+               XFS_WANT_CORRUPTED_GOTO(ibtrec->ir_freecount == 1, error);
+
+               error = xfs_inobt_insert_rec(cur, ibtrec->ir_freecount,
+                                            ibtrec->ir_free, &i);
+               if (error)
+                       goto error;
+               ASSERT(i == 1);
+
+               goto out;
+       }
+
+       /*
+        * Read and update the existing record.
+        */
+       error = xfs_inobt_get_rec(cur, &rec, &i);
+       if (error)
+               goto error;
+       XFS_WANT_CORRUPTED_GOTO(i == 1, error);
+
+       rec.ir_free |= XFS_INOBT_MASK(offset);
+       rec.ir_freecount++;
+
+       XFS_WANT_CORRUPTED_GOTO((rec.ir_free == ibtrec->ir_free) &&
+                               (rec.ir_freecount == ibtrec->ir_freecount),
+                               error);
+
+       /*
+        * The content of inobt records should always match between the inobt
+        * and finobt. The lifecycle of records in the finobt is different from
+        * the inobt in that the finobt only tracks records with at least one
+        * free inode. This is to optimize lookup for inode allocation purposes.
+        * The following checks determine whether to update the existing record or
+        * remove it entirely.
+        */
+
+       if (rec.ir_freecount == XFS_IALLOC_INODES(mp) &&
+           !(mp->m_flags & XFS_MOUNT_IKEEP)) {
+               /*
+                * If all inodes are free and we're in !ikeep mode, the entire
+                * inode chunk has been deallocated. Remove the record from the
+                * finobt.
+                */
+               error = xfs_btree_delete(cur, &i);
+               if (error)
+                       goto error;
+               ASSERT(i == 1);
+       } else {
+               /*
+                * The existing finobt record was modified and has a combination
+                * of allocated and free inodes or is completely free and ikeep
+                * is enabled. Update the record.
+                */
+               error = xfs_inobt_update(cur, &rec);
+               if (error)
+                       goto error;
+       }
+
+out:
+       error = xfs_check_agi_freecount(cur, agi);
+       if (error)
+               goto error;
+
+       xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+       return 0;
+
+error:
+       xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+       return error;
+}
+
 /*
  * Free disk inode.  Carefully avoids touching the incore inode, all
  * manipulations incore are the caller's responsibility.
@@ -1521,6 +1621,15 @@ xfs_difree(
        if (error)
                goto error0;
 
+       /*
+        * Fix up the free inode btree.
+        */
+       if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+               error = xfs_difree_finobt(mp, tp, agbp, agino, &rec);
+               if (error)
+                       goto error0;
+       }
+
        return 0;
 
 error0: