From b49571191ee1eaa40ab896ae0d2177e41ae4f7dd Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Tue, 30 Nov 2010 15:15:46 +1100
Subject: [PATCH] --- yaml --- r: 222791 b: refs/heads/master c:
 de25c1818c44f580ff556cb9e0f7a1c687ed870b h: refs/heads/master i:   222789:
 23fd758adda6fb8c722f326d3f52f86175ca01ed   222787:
 f7b0afbe14c9bc856c57b7bcede037067934bef7   222783:
 8e9b032e58d02ffcb5834b9a336c8f696218da39 v: v3

---
 [refs]                        |  2 +-
 trunk/fs/xfs/xfs_inode_item.c | 31 +++++++++++++++++++++++++------
 2 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/[refs] b/[refs]
index 04635ec920dd..2a84f405c160 100644
--- a/[refs]
+++ b/[refs]
@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 309c848002052edbec650075a1eb098b17c17f35
+refs/heads/master: de25c1818c44f580ff556cb9e0f7a1c687ed870b
diff --git a/trunk/fs/xfs/xfs_inode_item.c b/trunk/fs/xfs/xfs_inode_item.c
index c7ac020705df..7c8d30c453c3 100644
--- a/trunk/fs/xfs/xfs_inode_item.c
+++ b/trunk/fs/xfs/xfs_inode_item.c
@@ -657,18 +657,37 @@ xfs_inode_item_unlock(
 }
 
 /*
- * This is called to find out where the oldest active copy of the
- * inode log item in the on disk log resides now that the last log
- * write of it completed at the given lsn.  Since we always re-log
- * all dirty data in an inode, the latest copy in the on disk log
- * is the only one that matters.  Therefore, simply return the
- * given lsn.
+ * This is called to find out where the oldest active copy of the inode log
+ * item in the on disk log resides now that the last log write of it completed
+ * at the given lsn.  Since we always re-log all dirty data in an inode, the
+ * latest copy in the on disk log is the only one that matters.  Therefore,
+ * simply return the given lsn.
+ *
+ * If the inode has been marked stale because the cluster is being freed, we
+ * don't want to (re-)insert this inode into the AIL. There is a race condition
+ * where the cluster buffer may be unpinned before the inode is inserted into
+ * the AIL during transaction committed processing. If the buffer is unpinned
+ * before the inode item has been committed and inserted, then it is possible
+ * for the buffer to be written and IO completions before the inode is inserted
+ * into the AIL. In that case, we'd be inserting a clean, stale inode into the
+ * AIL which will never get removed. It will, however, get reclaimed which
+ * triggers an assert in xfs_inode_free() complaining about freein an inode
+ * still in the AIL.
+ *
+ * To avoid this, return a lower LSN than the one passed in so that the
+ * transaction committed code will not move the inode forward in the AIL but
+ * will still unpin it properly.
  */
 STATIC xfs_lsn_t
 xfs_inode_item_committed(
 	struct xfs_log_item	*lip,
 	xfs_lsn_t		lsn)
 {
+	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
+	struct xfs_inode	*ip = iip->ili_inode;
+
+	if (xfs_iflags_test(ip, XFS_ISTALE))
+		return lsn - 1;
 	return lsn;
 }