xfs: fix an AGI lock acquisition ordering problem in xrep_dinode_findmode

While reviewing the next patch which fixes an ABBA deadlock between the
AGI and a directory ILOCK, someone asked a question about why we're
holding the AGI in the first place.  The reason for that is to quiesce
the inode structures for that AG while we do a repair.

I then realized that the xrep_dinode_findmode invokes xchk_iscan_iter,
which walks the inobts (and hence the AGIs) to find all the inodes.
This itself is also an ABBA vector, since the damaged inode could be in
AG 5, which we hold while we scan AG 0 for directories.  5 -> 0 is not
allowed.

To address this, modify the iscan to allow trylock of the AGI buffer
using the flags argument to xfs_ialloc_read_agi that the previous patch
added.

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

1 files changed, 15 insertions, 0 deletions

diff --git a/fs/xfs/scrub/iscan.h b/fs/xfs/scrub/iscan.h
index 71f657552dfa..5e0e4ed9dea6 100644
--- a/fs/xfs/scrub/iscan.h
+++ b/fs/xfs/scrub/iscan.h
@@ -59,6 +59,9 @@ struct xchk_iscan {
 /* Set if the scan has been aborted due to some event in the fs. */
 #define XCHK_ISCAN_OPSTATE_ABORTED	(1)
 
+/* Use trylock to acquire the AGI */
+#define XCHK_ISCAN_OPSTATE_TRYLOCK_AGI	(2)
+
 static inline bool
 xchk_iscan_aborted(const struct xchk_iscan *iscan)
 {
@@ -71,6 +74,18 @@ xchk_iscan_abort(struct xchk_iscan *iscan)
 	set_bit(XCHK_ISCAN_OPSTATE_ABORTED, &iscan->__opstate);
 }
 
+static inline bool
+xchk_iscan_agi_needs_trylock(const struct xchk_iscan *iscan)
+{
+	return test_bit(XCHK_ISCAN_OPSTATE_TRYLOCK_AGI, &iscan->__opstate);
+}
+
+static inline void
+xchk_iscan_set_agi_trylock(struct xchk_iscan *iscan)
+{
+	set_bit(XCHK_ISCAN_OPSTATE_TRYLOCK_AGI, &iscan->__opstate);
+}
+
 void xchk_iscan_start(struct xfs_scrub *sc, unsigned int iget_timeout,
 		unsigned int iget_retry_delay, struct xchk_iscan *iscan);
 void xchk_iscan_teardown(struct xchk_iscan *iscan);