4 files changed, 68 insertions, 79 deletions

diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c
index 02bf17808bdc..18bc101d603f 100644
--- a/fs/ocfs2/dlm/dlmfs.c
+++ b/fs/ocfs2/dlm/dlmfs.c
@@ -205,7 +205,7 @@ static ssize_t dlmfs_file_read(struct file *filp,
 	if ((count + *ppos) > i_size_read(inode))
 		readlen = i_size_read(inode) - *ppos;
 	else
-		readlen = count - *ppos;
+		readlen = count;
 
 	lvb_buf = kmalloc(readlen, GFP_NOFS);
 	if (!lvb_buf)
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 83bcaf266b35..ef1ac9ab4ee1 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -511,8 +511,6 @@ static void dlm_lockres_release(struct kref *kref)
 
 	atomic_dec(&dlm->res_cur_count);
 
-	dlm_put(dlm);
-
 	if (!hlist_unhashed(&res->hash_node) ||
 	    !list_empty(&res->granted) ||
 	    !list_empty(&res->converting) ||
@@ -585,8 +583,6 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm,
 	res->migration_pending = 0;
 	res->inflight_locks = 0;
 
-	/* put in dlm_lockres_release */
-	dlm_grab(dlm);
 	res->dlm = dlm;
 
 	kref_init(&res->refs);
@@ -3046,8 +3042,6 @@ int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data,
 	/* check for pre-existing lock */
 	spin_lock(&dlm->spinlock);
 	res = __dlm_lookup_lockres(dlm, name, namelen, hash);
-	spin_lock(&dlm->master_lock);
-
 	if (res) {
 		spin_lock(&res->spinlock);
 		if (res->state & DLM_LOCK_RES_RECOVERING) {
@@ -3065,14 +3059,15 @@ int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data,
 		spin_unlock(&res->spinlock);
 	}
 
+	spin_lock(&dlm->master_lock);
 	/* ignore status.  only nonzero status would BUG. */
 	ret = dlm_add_migration_mle(dlm, res, mle, &oldmle,
 				    name, namelen,
 				    migrate->new_master,
 				    migrate->master);
 
-unlock:
 	spin_unlock(&dlm->master_lock);
+unlock:
 	spin_unlock(&dlm->spinlock);
 
 	if (oldmle) {
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index d9fa3d22e17c..3492550b70c8 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1941,6 +1941,8 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm,
 	struct list_head *queue;
 	struct dlm_lock *lock, *next;
 
+	assert_spin_locked(&dlm->spinlock);
+	assert_spin_locked(&res->spinlock);
 	res->state |= DLM_LOCK_RES_RECOVERING;
 	if (!list_empty(&res->recovering)) {
 		mlog(0,
@@ -2265,19 +2267,15 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 			/* zero the lvb if necessary */
 			dlm_revalidate_lvb(dlm, res, dead_node);
 			if (res->owner == dead_node) {
-				if (res->state & DLM_LOCK_RES_DROPPING_REF)
-					mlog(0, "%s:%.*s: owned by "
-					     "dead node %u, this node was "
-					     "dropping its ref when it died. "
-					     "continue, dropping the flag.\n",
-					     dlm->name, res->lockname.len,
-					     res->lockname.name, dead_node);
-
-				/* the wake_up for this will happen when the
-				 * RECOVERING flag is dropped later */
-				res->state &= ~DLM_LOCK_RES_DROPPING_REF;
+				if (res->state & DLM_LOCK_RES_DROPPING_REF) {
+					mlog(ML_NOTICE, "Ignore %.*s for "
+					     "recovery as it is being freed\n",
+					     res->lockname.len,
+					     res->lockname.name);
+				} else
+					dlm_move_lockres_to_recovery_list(dlm,
+									  res);
 
-				dlm_move_lockres_to_recovery_list(dlm, res);
 			} else if (res->owner == dlm->node_num) {
 				dlm_free_dead_locks(dlm, res, dead_node);
 				__dlm_lockres_calc_usage(dlm, res);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 52ec020ea78b..86491f583ea5 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -93,19 +93,27 @@ int __dlm_lockres_has_locks(struct dlm_lock_resource *res)
  * truly ready to be freed. */
 int __dlm_lockres_unused(struct dlm_lock_resource *res)
 {
-	if (!__dlm_lockres_has_locks(res) &&
-	    (list_empty(&res->dirty) && !(res->state & DLM_LOCK_RES_DIRTY))) {
-		/* try not to scan the bitmap unless the first two
-		 * conditions are already true */
-		int bit = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
-		if (bit >= O2NM_MAX_NODES) {
-			/* since the bit for dlm->node_num is not
-			 * set, inflight_locks better be zero */
-			BUG_ON(res->inflight_locks != 0);
-			return 1;
-		}
-	}
-	return 0;
+	int bit;
+
+	if (__dlm_lockres_has_locks(res))
+		return 0;
+
+	if (!list_empty(&res->dirty) || res->state & DLM_LOCK_RES_DIRTY)
+		return 0;
+
+	if (res->state & DLM_LOCK_RES_RECOVERING)
+		return 0;
+
+	bit = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
+	if (bit < O2NM_MAX_NODES)
+		return 0;
+
+	/*
+	 * since the bit for dlm->node_num is not set, inflight_locks better
+	 * be zero
+	 */
+	BUG_ON(res->inflight_locks != 0);
+	return 1;
 }
 
 
@@ -153,45 +161,25 @@ void dlm_lockres_calc_usage(struct dlm_ctxt *dlm,
 	spin_unlock(&dlm->spinlock);
 }
 
-static int dlm_purge_lockres(struct dlm_ctxt *dlm,
+static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 			     struct dlm_lock_resource *res)
 {
 	int master;
 	int ret = 0;
 
-	spin_lock(&res->spinlock);
-	if (!__dlm_lockres_unused(res)) {
-		mlog(0, "%s:%.*s: tried to purge but not unused\n",
-		     dlm->name, res->lockname.len, res->lockname.name);
-		__dlm_print_one_lock_resource(res);
-		spin_unlock(&res->spinlock);
-		BUG();
-	}
-
-	if (res->state & DLM_LOCK_RES_MIGRATING) {
-		mlog(0, "%s:%.*s: Delay dropref as this lockres is "
-		     "being remastered\n", dlm->name, res->lockname.len,
-		     res->lockname.name);
-		/* Re-add the lockres to the end of the purge list */
-		if (!list_empty(&res->purge)) {
-			list_del_init(&res->purge);
-			list_add_tail(&res->purge, &dlm->purge_list);
-		}
-		spin_unlock(&res->spinlock);
-		return 0;
-	}
+	assert_spin_locked(&dlm->spinlock);
+	assert_spin_locked(&res->spinlock);
 
 	master = (res->owner == dlm->node_num);
 
-	if (!master)
-		res->state |= DLM_LOCK_RES_DROPPING_REF;
-	spin_unlock(&res->spinlock);
 
 	mlog(0, "purging lockres %.*s, master = %d\n", res->lockname.len,
 	     res->lockname.name, master);
 
 	if (!master) {
+		res->state |= DLM_LOCK_RES_DROPPING_REF;
 		/* drop spinlock...  retake below */
+		spin_unlock(&res->spinlock);
 		spin_unlock(&dlm->spinlock);
 
 		spin_lock(&res->spinlock);
@@ -209,31 +197,35 @@ static int dlm_purge_lockres(struct dlm_ctxt *dlm,
 		mlog(0, "%s:%.*s: dlm_deref_lockres returned %d\n",
 		     dlm->name, res->lockname.len, res->lockname.name, ret);
 		spin_lock(&dlm->spinlock);
+		spin_lock(&res->spinlock);
 	}
 
-	spin_lock(&res->spinlock);
 	if (!list_empty(&res->purge)) {
 		mlog(0, "removing lockres %.*s:%p from purgelist, "
 		     "master = %d\n", res->lockname.len, res->lockname.name,
 		     res, master);
 		list_del_init(&res->purge);
-		spin_unlock(&res->spinlock);
 		dlm_lockres_put(res);
 		dlm->purge_count--;
-	} else
-		spin_unlock(&res->spinlock);
+	}
+
+	if (!__dlm_lockres_unused(res)) {
+		mlog(ML_ERROR, "found lockres %s:%.*s: in use after deref\n",
+		     dlm->name, res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+		BUG();
+	}
 
 	__dlm_unhash_lockres(res);
 
 	/* lockres is not in the hash now.  drop the flag and wake up
 	 * any processes waiting in dlm_get_lock_resource. */
 	if (!master) {
-		spin_lock(&res->spinlock);
 		res->state &= ~DLM_LOCK_RES_DROPPING_REF;
 		spin_unlock(&res->spinlock);
 		wake_up(&res->wq);
-	}
-	return 0;
+	} else
+		spin_unlock(&res->spinlock);
 }
 
 static void dlm_run_purge_list(struct dlm_ctxt *dlm,
@@ -252,17 +244,7 @@ static void dlm_run_purge_list(struct dlm_ctxt *dlm,
 		lockres = list_entry(dlm->purge_list.next,
 				     struct dlm_lock_resource, purge);
 
-		/* Status of the lockres *might* change so double
-		 * check. If the lockres is unused, holding the dlm
-		 * spinlock will prevent people from getting and more
-		 * refs on it -- there's no need to keep the lockres
-		 * spinlock. */
 		spin_lock(&lockres->spinlock);
-		unused = __dlm_lockres_unused(lockres);
-		spin_unlock(&lockres->spinlock);
-
-		if (!unused)
-			continue;
 
 		purge_jiffies = lockres->last_used +
 			msecs_to_jiffies(DLM_PURGE_INTERVAL_MS);
@@ -274,15 +256,29 @@ static void dlm_run_purge_list(struct dlm_ctxt *dlm,
 			 * in tail order, we can stop at the first
 			 * unpurgable resource -- anyone added after
 			 * him will have a greater last_used value */
+			spin_unlock(&lockres->spinlock);
 			break;
 		}
 
+		/* Status of the lockres *might* change so double
+		 * check. If the lockres is unused, holding the dlm
+		 * spinlock will prevent people from getting and more
+		 * refs on it. */
+		unused = __dlm_lockres_unused(lockres);
+		if (!unused ||
+		    (lockres->state & DLM_LOCK_RES_MIGRATING)) {
+			mlog(0, "lockres %s:%.*s: is in use or "
+			     "being remastered, used %d, state %d\n",
+			     dlm->name, lockres->lockname.len,
+			     lockres->lockname.name, !unused, lockres->state);
+			list_move_tail(&dlm->purge_list, &lockres->purge);
+			spin_unlock(&lockres->spinlock);
+			continue;
+		}
+
 		dlm_lockres_get(lockres);
 
-		/* This may drop and reacquire the dlm spinlock if it
-		 * has to do migration. */
-		if (dlm_purge_lockres(dlm, lockres))
-			BUG();
+		dlm_purge_lockres(dlm, lockres);
 
 		dlm_lockres_put(lockres);