xfs: try to avoid allocating from sick inode clusters

I noticed that xfs/413 and xfs/375 occasionally failed while fuzzing
core.mode of an inode.  The root cause of these problems is that the
field we fuzzed (core.mode or core.magic, typically) causes the entire
inode cluster buffer verification to fail, which affects several inodes
at once.  The repair process tries to create either a /lost+found or a
temporary repair file, but regrettably it picks the same inode cluster
that we just corrupted, with the result that repair triggers the demise
of the filesystem.

Try avoid this by making the inode allocation path detect when the perag
health status indicates that someone has found bad inode cluster
buffers, and try to read the inode cluster buffer.  If the cluster
buffer fails the verifiers, try another AG.  This isn't foolproof and
can result in premature ENOSPC, but that might be better than shutting
down.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>

diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index cb37f0007731f1248999e165bf8c7c85466e22e1..14c81f227c5bb92c98c742bae20d68364dc1de63 100644 (file)
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1057,6 +1057,33 @@ xfs_inobt_first_free_inode(
        return xfs_lowbit64(realfree);
 }
 
+/*
+ * If this AG has corrupt inodes, check if allocating this inode would fail
+ * with corruption errors.  Returns 0 if we're clear, or EAGAIN to try again
+ * somewhere else.
+ */
+static int
+xfs_dialloc_check_ino(
+       struct xfs_perag        *pag,
+       struct xfs_trans        *tp,
+       xfs_ino_t               ino)
+{
+       struct xfs_imap         imap;
+       struct xfs_buf          *bp;
+       int                     error;
+
+       error = xfs_imap(pag, tp, ino, &imap, 0);
+       if (error)
+               return -EAGAIN;
+
+       error = xfs_imap_to_bp(pag->pag_mount, tp, &imap, &bp);
+       if (error)
+               return -EAGAIN;
+
+       xfs_trans_brelse(tp, bp);
+       return 0;
+}
+
 /*
  * Allocate an inode using the inobt-only algorithm.
  */
@@ -1309,6 +1336,13 @@ alloc_inode:
        ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
                                   XFS_INODES_PER_CHUNK) == 0);
        ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
+
+       if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
+               error = xfs_dialloc_check_ino(pag, tp, ino);
+               if (error)
+                       goto error0;
+       }
+
        rec.ir_free &= ~XFS_INOBT_MASK(offset);
        rec.ir_freecount--;
        error = xfs_inobt_update(cur, &rec);
@@ -1584,6 +1618,12 @@ xfs_dialloc_ag(
                                   XFS_INODES_PER_CHUNK) == 0);
        ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
 
+       if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
+               error = xfs_dialloc_check_ino(pag, tp, ino);
+               if (error)
+                       goto error_cur;
+       }
+
        /*
         * Modify or remove the finobt record.
         */