Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2

* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2:
  ocfs2/trivial: Wrap ocfs2_sysfile_cluster_lock_key within define.
  ocfs2: Add lockdep annotations
  vfs: Set special lockdep map for dirs only if not set by fs
  ocfs2: Disable orphan scanning for local and hard-ro mounts
  ocfs2: Do not initialize lvb in ocfs2_orphan_scan_lock_res_init()
  ocfs2: Stop orphan scan as early as possible during umount
  ocfs2: Fix ocfs2_osb_dump()
  ocfs2: Pin journal head before accessing jh->b_committed_data
  ocfs2: Update atime in splice read if necessary.
  ocfs2: Provide the ocfs2_dlm_lvb_valid() stack API.

16 files changed, 294 insertions, 111 deletions

diff --git a/fs/inode.c b/fs/inode.c
index f643be565df..04c785bb63c 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -665,12 +665,17 @@ void unlock_new_inode(struct inode *inode)
 	if (inode->i_mode & S_IFDIR) {
 		struct file_system_type *type = inode->i_sb->s_type;
 
-		/*
-		 * ensure nobody is actually holding i_mutex
-		 */
-		mutex_destroy(&inode->i_mutex);
-		mutex_init(&inode->i_mutex);
-		lockdep_set_class(&inode->i_mutex, &type->i_mutex_dir_key);
+		/* Set new key only if filesystem hasn't already changed it */
+		if (!lockdep_match_class(&inode->i_mutex,
+		    &type->i_mutex_key)) {
+			/*
+			 * ensure nobody is actually holding i_mutex
+			 */
+			mutex_destroy(&inode->i_mutex);
+			mutex_init(&inode->i_mutex);
+			lockdep_set_class(&inode->i_mutex,
+					  &type->i_mutex_dir_key);
+		}
 	}
 #endif
 	/*
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 6cdeaa76f27..110bb57c46a 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -92,6 +92,9 @@ struct ocfs2_unblock_ctl {
 	enum ocfs2_unblock_action unblock_action;
 };
 
+/* Lockdep class keys */
+struct lock_class_key lockdep_keys[OCFS2_NUM_LOCK_TYPES];
+
 static int ocfs2_check_meta_downconvert(struct ocfs2_lock_res *lockres,
 					int new_level);
 static void ocfs2_set_meta_lvb(struct ocfs2_lock_res *lockres);
@@ -317,9 +320,16 @@ static int ocfs2_lock_create(struct ocfs2_super *osb,
 			     u32 dlm_flags);
 static inline int ocfs2_may_continue_on_blocked_lock(struct ocfs2_lock_res *lockres,
 						     int wanted);
-static void ocfs2_cluster_unlock(struct ocfs2_super *osb,
-				 struct ocfs2_lock_res *lockres,
-				 int level);
+static void __ocfs2_cluster_unlock(struct ocfs2_super *osb,
+				   struct ocfs2_lock_res *lockres,
+				   int level, unsigned long caller_ip);
+static inline void ocfs2_cluster_unlock(struct ocfs2_super *osb,
+					struct ocfs2_lock_res *lockres,
+					int level)
+{
+	__ocfs2_cluster_unlock(osb, lockres, level, _RET_IP_);
+}
+
 static inline void ocfs2_generic_handle_downconvert_action(struct ocfs2_lock_res *lockres);
 static inline void ocfs2_generic_handle_convert_action(struct ocfs2_lock_res *lockres);
 static inline void ocfs2_generic_handle_attach_action(struct ocfs2_lock_res *lockres);
@@ -489,6 +499,13 @@ static void ocfs2_lock_res_init_common(struct ocfs2_super *osb,
 	ocfs2_add_lockres_tracking(res, osb->osb_dlm_debug);
 
 	ocfs2_init_lock_stats(res);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	if (type != OCFS2_LOCK_TYPE_OPEN)
+		lockdep_init_map(&res->l_lockdep_map, ocfs2_lock_type_strings[type],
+				 &lockdep_keys[type], 0);
+	else
+		res->l_lockdep_map.key = NULL;
+#endif
 }
 
 void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res)
@@ -644,14 +661,10 @@ static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res,
 static void ocfs2_orphan_scan_lock_res_init(struct ocfs2_lock_res *res,
 					    struct ocfs2_super *osb)
 {
-	struct ocfs2_orphan_scan_lvb *lvb;
-
 	ocfs2_lock_res_init_once(res);
 	ocfs2_build_lock_name(OCFS2_LOCK_TYPE_ORPHAN_SCAN, 0, 0, res->l_name);
 	ocfs2_lock_res_init_common(osb, res, OCFS2_LOCK_TYPE_ORPHAN_SCAN,
 				   &ocfs2_orphan_scan_lops, osb);
-	lvb = ocfs2_dlm_lvb(&res->l_lksb);
-	lvb->lvb_version = OCFS2_ORPHAN_LVB_VERSION;
 }
 
 void ocfs2_file_lock_res_init(struct ocfs2_lock_res *lockres,
@@ -1256,11 +1269,13 @@ static int ocfs2_wait_for_mask_interruptible(struct ocfs2_mask_waiter *mw,
 	return ret;
 }
 
-static int ocfs2_cluster_lock(struct ocfs2_super *osb,
-			      struct ocfs2_lock_res *lockres,
-			      int level,
-			      u32 lkm_flags,
-			      int arg_flags)
+static int __ocfs2_cluster_lock(struct ocfs2_super *osb,
+				struct ocfs2_lock_res *lockres,
+				int level,
+				u32 lkm_flags,
+				int arg_flags,
+				int l_subclass,
+				unsigned long caller_ip)
 {
 	struct ocfs2_mask_waiter mw;
 	int wait, catch_signals = !(osb->s_mount_opt & OCFS2_MOUNT_NOINTR);
@@ -1403,13 +1418,37 @@ out:
 	}
 	ocfs2_update_lock_stats(lockres, level, &mw, ret);
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	if (!ret && lockres->l_lockdep_map.key != NULL) {
+		if (level == DLM_LOCK_PR)
+			rwsem_acquire_read(&lockres->l_lockdep_map, l_subclass,
+				!!(arg_flags & OCFS2_META_LOCK_NOQUEUE),
+				caller_ip);
+		else
+			rwsem_acquire(&lockres->l_lockdep_map, l_subclass,
+				!!(arg_flags & OCFS2_META_LOCK_NOQUEUE),
+				caller_ip);
+	}
+#endif
 	mlog_exit(ret);
 	return ret;
 }
 
-static void ocfs2_cluster_unlock(struct ocfs2_super *osb,
-				 struct ocfs2_lock_res *lockres,
-				 int level)
+static inline int ocfs2_cluster_lock(struct ocfs2_super *osb,
+				     struct ocfs2_lock_res *lockres,
+				     int level,
+				     u32 lkm_flags,
+				     int arg_flags)
+{
+	return __ocfs2_cluster_lock(osb, lockres, level, lkm_flags, arg_flags,
+				    0, _RET_IP_);
+}
+
+
+static void __ocfs2_cluster_unlock(struct ocfs2_super *osb,
+				   struct ocfs2_lock_res *lockres,
+				   int level,
+				   unsigned long caller_ip)
 {
 	unsigned long flags;
 
@@ -1418,6 +1457,10 @@ static void ocfs2_cluster_unlock(struct ocfs2_super *osb,
 	ocfs2_dec_holders(lockres, level);
 	ocfs2_downconvert_on_unlock(osb, lockres);
 	spin_unlock_irqrestore(&lockres->l_lock, flags);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	if (lockres->l_lockdep_map.key != NULL)
+		rwsem_release(&lockres->l_lockdep_map, 1, caller_ip);
+#endif
 	mlog_exit_void();
 }
 
@@ -1989,7 +2032,8 @@ static inline int ocfs2_meta_lvb_is_trustable(struct inode *inode,
 {
 	struct ocfs2_meta_lvb *lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
 
-	if (lvb->lvb_version == OCFS2_LVB_VERSION
+	if (ocfs2_dlm_lvb_valid(&lockres->l_lksb)
+	    && lvb->lvb_version == OCFS2_LVB_VERSION
 	    && be32_to_cpu(lvb->lvb_igeneration) == inode->i_generation)
 		return 1;
 	return 0;
@@ -2162,10 +2206,11 @@ static int ocfs2_assign_bh(struct inode *inode,
  * returns < 0 error if the callback will never be called, otherwise
  * the result of the lock will be communicated via the callback.
  */
-int ocfs2_inode_lock_full(struct inode *inode,
-			 struct buffer_head **ret_bh,
-			 int ex,
-			 int arg_flags)
+int ocfs2_inode_lock_full_nested(struct inode *inode,
+				 struct buffer_head **ret_bh,
+				 int ex,
+				 int arg_flags,
+				 int subclass)
 {
 	int status, level, acquired;
 	u32 dlm_flags;
@@ -2203,7 +2248,8 @@ int ocfs2_inode_lock_full(struct inode *inode,
 	if (arg_flags & OCFS2_META_LOCK_NOQUEUE)
 		dlm_flags |= DLM_LKF_NOQUEUE;
 
-	status = ocfs2_cluster_lock(osb, lockres, level, dlm_flags, arg_flags);
+	status = __ocfs2_cluster_lock(osb, lockres, level, dlm_flags,
+				      arg_flags, subclass, _RET_IP_);
 	if (status < 0) {
 		if (status != -EAGAIN && status != -EIOCBRETRY)
 			mlog_errno(status);
@@ -2369,35 +2415,45 @@ void ocfs2_inode_unlock(struct inode *inode,
 	mlog_exit_void();
 }
 
-int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno, int ex)
+int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno)
 {
 	struct ocfs2_lock_res *lockres;
 	struct ocfs2_orphan_scan_lvb *lvb;
-	int level = ex ? DLM_LOCK_EX : DLM_LOCK_PR;
 	int status = 0;
 
+	if (ocfs2_is_hard_readonly(osb))
+		return -EROFS;
+
+	if (ocfs2_mount_local(osb))
+		return 0;
+
 	lockres = &osb->osb_orphan_scan.os_lockres;
-	status = ocfs2_cluster_lock(osb, lockres, level, 0, 0);
+	status = ocfs2_cluster_lock(osb, lockres, DLM_LOCK_EX, 0, 0);
 	if (status < 0)
 		return status;
 
 	lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
-	if (lvb->lvb_version == OCFS2_ORPHAN_LVB_VERSION)
+	if (ocfs2_dlm_lvb_valid(&lockres->l_lksb) &&
+	    lvb->lvb_version == OCFS2_ORPHAN_LVB_VERSION)
 		*seqno = be32_to_cpu(lvb->lvb_os_seqno);
+	else
+		*seqno = osb->osb_orphan_scan.os_seqno + 1;
+
 	return status;
 }
 
-void ocfs2_orphan_scan_unlock(struct ocfs2_super *osb, u32 seqno, int ex)
+void ocfs2_orphan_scan_unlock(struct ocfs2_super *osb, u32 seqno)
 {
 	struct ocfs2_lock_res *lockres;
 	struct ocfs2_orphan_scan_lvb *lvb;
-	int level = ex ? DLM_LOCK_EX : DLM_LOCK_PR;
 
-	lockres = &osb->osb_orphan_scan.os_lockres;
-	lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
-	lvb->lvb_version = OCFS2_ORPHAN_LVB_VERSION;
-	lvb->lvb_os_seqno = cpu_to_be32(seqno);
-	ocfs2_cluster_unlock(osb, lockres, level);
+	if (!ocfs2_is_hard_readonly(osb) && !ocfs2_mount_local(osb)) {
+		lockres = &osb->osb_orphan_scan.os_lockres;
+		lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
+		lvb->lvb_version = OCFS2_ORPHAN_LVB_VERSION;
+		lvb->lvb_os_seqno = cpu_to_be32(seqno);
+		ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_EX);
+	}
 }
 
 int ocfs2_super_lock(struct ocfs2_super *osb,
@@ -3627,7 +3683,8 @@ static int ocfs2_refresh_qinfo(struct ocfs2_mem_dqinfo *oinfo)
 	struct ocfs2_global_disk_dqinfo *gdinfo;
 	int status = 0;
 
-	if (lvb->lvb_version == OCFS2_QINFO_LVB_VERSION) {
+	if (ocfs2_dlm_lvb_valid(&lockres->l_lksb) &&
+	    lvb->lvb_version == OCFS2_QINFO_LVB_VERSION) {
 		info->dqi_bgrace = be32_to_cpu(lvb->lvb_bgrace);
 		info->dqi_igrace = be32_to_cpu(lvb->lvb_igrace);
 		oinfo->dqi_syncms = be32_to_cpu(lvb->lvb_syncms);
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index 31b90d7b8f5..7553836931d 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -78,6 +78,14 @@ struct ocfs2_orphan_scan_lvb {
 /* don't block waiting for the downconvert thread, instead return -EAGAIN */
 #define OCFS2_LOCK_NONBLOCK		(0x04)
 
+/* Locking subclasses of inode cluster lock */
+enum {
+	OI_LS_NORMAL = 0,
+	OI_LS_PARENT,
+	OI_LS_RENAME1,
+	OI_LS_RENAME2,
+};
+
 int ocfs2_dlm_init(struct ocfs2_super *osb);
 void ocfs2_dlm_shutdown(struct ocfs2_super *osb, int hangup_pending);
 void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res);
@@ -104,25 +112,31 @@ void ocfs2_open_unlock(struct inode *inode);
 int ocfs2_inode_lock_atime(struct inode *inode,
 			  struct vfsmount *vfsmnt,
 			  int *level);
-int ocfs2_inode_lock_full(struct inode *inode,
+int ocfs2_inode_lock_full_nested(struct inode *inode,
 			 struct buffer_head **ret_bh,
 			 int ex,
-			 int arg_flags);
+			 int arg_flags,
+			 int subclass);
 int ocfs2_inode_lock_with_page(struct inode *inode,
 			      struct buffer_head **ret_bh,
 			      int ex,
 			      struct page *page);
+/* Variants without special locking class or flags */
+#define ocfs2_inode_lock_full(i, r, e, f)\
+		ocfs2_inode_lock_full_nested(i, r, e, f, OI_LS_NORMAL)
+#define ocfs2_inode_lock_nested(i, b, e, s)\
+		ocfs2_inode_lock_full_nested(i, b, e, 0, s)
 /* 99% of the time we don't want to supply any additional flags --
  * those are for very specific cases only. */
-#define ocfs2_inode_lock(i, b, e) ocfs2_inode_lock_full(i, b, e, 0)
+#define ocfs2_inode_lock(i, b, e) ocfs2_inode_lock_full_nested(i, b, e, 0, OI_LS_NORMAL)
 void ocfs2_inode_unlock(struct inode *inode,
 		       int ex);
 int ocfs2_super_lock(struct ocfs2_super *osb,
 		     int ex);
 void ocfs2_super_unlock(struct ocfs2_super *osb,
 			int ex);
-int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno, int ex);
-void ocfs2_orphan_scan_unlock(struct ocfs2_super *osb, u32 seqno, int ex);
+int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno);
+void ocfs2_orphan_scan_unlock(struct ocfs2_super *osb, u32 seqno);
 
 int ocfs2_rename_lock(struct ocfs2_super *osb);
 void ocfs2_rename_unlock(struct ocfs2_super *osb);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 07267e0da90..62442e413a0 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2026,7 +2026,7 @@ static ssize_t ocfs2_file_splice_read(struct file *in,
 				      size_t len,
 				      unsigned int flags)
 {
-	int ret = 0;
+	int ret = 0, lock_level = 0;
 	struct inode *inode = in->f_path.dentry->d_inode;
 
 	mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", in, pipe,
@@ -2037,12 +2037,12 @@ static ssize_t ocfs2_file_splice_read(struct file *in,
 	/*
 	 * See the comment in ocfs2_file_aio_read()
 	 */
-	ret = ocfs2_inode_lock(inode, NULL, 0);
+	ret = ocfs2_inode_lock_atime(inode, in->f_vfsmnt, &lock_level);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto bail;
 	}
-	ocfs2_inode_unlock(inode, 0);
+	ocfs2_inode_unlock(inode, lock_level);
 
 	ret = generic_file_splice_read(in, ppos, pipe, len, flags);
 
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 10e1fa87396..4dc8890ba31 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -215,6 +215,8 @@ bail:
 static int ocfs2_init_locked_inode(struct inode *inode, void *opaque)
 {
 	struct ocfs2_find_inode_args *args = opaque;
+	static struct lock_class_key ocfs2_quota_ip_alloc_sem_key,
+				     ocfs2_file_ip_alloc_sem_key;
 
 	mlog_entry("inode = %p, opaque = %p\n", inode, opaque);
 
@@ -223,6 +225,15 @@ static int ocfs2_init_locked_inode(struct inode *inode, void *opaque)
 	if (args->fi_sysfile_type != 0)
 		lockdep_set_class(&inode->i_mutex,
 			&ocfs2_sysfile_lock_key[args->fi_sysfile_type]);
+	if (args->fi_sysfile_type == USER_QUOTA_SYSTEM_INODE ||
+	    args->fi_sysfile_type == GROUP_QUOTA_SYSTEM_INODE ||
+	    args->fi_sysfile_type == LOCAL_USER_QUOTA_SYSTEM_INODE ||
+	    args->fi_sysfile_type == LOCAL_GROUP_QUOTA_SYSTEM_INODE)
+		lockdep_set_class(&OCFS2_I(inode)->ip_alloc_sem,
+				  &ocfs2_quota_ip_alloc_sem_key);
+	else
+		lockdep_set_class(&OCFS2_I(inode)->ip_alloc_sem,
+				  &ocfs2_file_ip_alloc_sem_key);
 
 	mlog_exit(0);
 	return 0;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 4a3b9e6b31a..f033760ecbe 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1880,13 +1880,20 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
 
 	os = &osb->osb_orphan_scan;
 
-	status = ocfs2_orphan_scan_lock(osb, &seqno, DLM_LOCK_EX);
+	if (atomic_read(&os->os_state) == ORPHAN_SCAN_INACTIVE)
+		goto out;
+
+	status = ocfs2_orphan_scan_lock(osb, &seqno);
 	if (status < 0) {
 		if (status != -EAGAIN)
 			mlog_errno(status);
 		goto out;
 	}
 
+	/* Do no queue the tasks if the volume is being umounted */
+	if (atomic_read(&os->os_state) == ORPHAN_SCAN_INACTIVE)
+		goto unlock;
+
 	if (os->os_seqno != seqno) {
 		os->os_seqno = seqno;
 		goto unlock;
@@ -1903,7 +1910,7 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
 	os->os_count++;
 	os->os_scantime = CURRENT_TIME;
 unlock:
-	ocfs2_orphan_scan_unlock(osb, seqno, DLM_LOCK_EX);
+	ocfs2_orphan_scan_unlock(osb, seqno);
 out:
 	return;
 }
@@ -1920,8 +1927,9 @@ void ocfs2_orphan_scan_work(struct work_struct *work)
 
 	mutex_lock(&os->os_lock);
 	ocfs2_queue_orphan_scan(osb);
-	schedule_delayed_work(&os->os_orphan_scan_work,
-			      ocfs2_orphan_scan_timeout());
+	if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE)
+		schedule_delayed_work(&os->os_orphan_scan_work,
+				      ocfs2_orphan_scan_timeout());
 	mutex_unlock(&os->os_lock);
 }
 
@@ -1930,26 +1938,33 @@ void ocfs2_orphan_scan_stop(struct ocfs2_super *osb)
 	struct ocfs2_orphan_scan *os;
 
 	os = &osb->osb_orphan_scan;
-	mutex_lock(&os->os_lock);
-	cancel_delayed_work(&os->os_orphan_scan_work);
-	mutex_unlock(&os->os_lock);
+	if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE) {
+		atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE);
+		mutex_lock(&os->os_lock);
+		cancel_delayed_work(&os->os_orphan_scan_work);
+		mutex_unlock(&os->os_lock);
+	}
 }
 
-int ocfs2_orphan_scan_init(struct ocfs2_super *osb)
+void ocfs2_orphan_scan_init(struct ocfs2_super *osb)
 {
 	struct ocfs2_orphan_scan *os;
 
 	os = &osb->osb_orphan_scan;
 	os->os_osb = osb;
 	os->os_count = 0;
+	os->os_seqno = 0;
 	os->os_scantime = CURRENT_TIME;
 	mutex_init(&os->os_lock);
-
-	INIT_DELAYED_WORK(&os->os_orphan_scan_work,
-			  ocfs2_orphan_scan_work);
-	schedule_delayed_work(&os->os_orphan_scan_work,
-			      ocfs2_orphan_scan_timeout());
-	return 0;
+	INIT_DELAYED_WORK(&os->os_orphan_scan_work, ocfs2_orphan_scan_work);
+
+	if (ocfs2_is_hard_readonly(osb) || ocfs2_mount_local(osb))
+		atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE);
+	else {
+		atomic_set(&os->os_state, ORPHAN_SCAN_ACTIVE);
+		schedule_delayed_work(&os->os_orphan_scan_work,
+				      ocfs2_orphan_scan_timeout());
+	}
 }
 
 struct ocfs2_orphan_filldir_priv {
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 61045eeb3f6..5432c7f79cc 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -144,7 +144,7 @@ static inline void ocfs2_inode_set_new(struct ocfs2_super *osb,
 }
 
 /* Exported only for the journal struct init code in super.c. Do not call. */
-int ocfs2_orphan_scan_init(struct ocfs2_super *osb);
+void ocfs2_orphan_scan_init(struct ocfs2_super *osb);
 void ocfs2_orphan_scan_stop(struct ocfs2_super *osb);
 void ocfs2_orphan_scan_exit(struct ocfs2_super *osb);
 
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 33464c6b60a..8601f934010 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -118,7 +118,7 @@ static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
 	mlog(0, "find name %.*s in directory %llu\n", dentry->d_name.len,
 	     dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno);
 
-	status = ocfs2_inode_lock(dir, NULL, 0);
+	status = ocfs2_inode_lock_nested(dir, NULL, 0, OI_LS_PARENT);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
@@ -636,7 +636,7 @@ static int ocfs2_link(struct dentry *old_dentry,
 	if (S_ISDIR(inode->i_mode))
 		return -EPERM;
 
-	err = ocfs2_inode_lock(dir, &parent_fe_bh, 1);
+	err = ocfs2_inode_lock_nested(dir, &parent_fe_bh, 1, OI_LS_PARENT);
 	if (err < 0) {
 		if (err != -ENOENT)
 			mlog_errno(err);
@@ -800,7 +800,8 @@ static int ocfs2_unlink(struct inode *dir,
 		return -EPERM;
 	}
 
-	status = ocfs2_inode_lock(dir, &parent_node_bh, 1);
+	status = ocfs2_inode_lock_nested(dir, &parent_node_bh, 1,
+					 OI_LS_PARENT);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
@@ -978,7 +979,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 			inode1 = tmpinode;
 		}
 		/* lock id2 */
-		status = ocfs2_inode_lock(inode2, bh2, 1);
+		status = ocfs2_inode_lock_nested(inode2, bh2, 1,
+						 OI_LS_RENAME1);
 		if (status < 0) {
 			if (status != -ENOENT)
 				mlog_errno(status);
@@ -987,7 +989,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	}
 
 	/* lock id1 */
-	status = ocfs2_inode_lock(inode1, bh1, 1);
+	status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_RENAME2);
 	if (status < 0) {
 		/*
 		 * An error return must mean that no cluster locks
@@ -1103,7 +1105,8 @@ static int ocfs2_rename(struct inode *old_dir,
 	 * won't have to concurrently downconvert the inode and the
 	 * dentry locks.
 	 */
-	status = ocfs2_inode_lock(old_inode, &old_inode_bh, 1);
+	status = ocfs2_inode_lock_nested(old_inode, &old_inode_bh, 1,
+					 OI_LS_PARENT);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 18c1d9ec1c9..c9345ebb849 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -34,6 +34,7 @@
 #include <linux/workqueue.h>
 #include <linux/kref.h>
 #include <linux/mutex.h>
+#include <linux/lockdep.h>
 #ifndef CONFIG_OCFS2_COMPAT_JBD
 # include <linux/jbd2.h>
 #else
@@ -152,6 +153,14 @@ struct ocfs2_lock_res {
 	unsigned int		 l_lock_max_exmode; 	   /* Max wait for EX */
 	unsigned int		 l_lock_refresh;	   /* Disk refreshes */
 #endif
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	 l_lockdep_map;
+#endif
+};
+
+enum ocfs2_orphan_scan_state {
+	ORPHAN_SCAN_ACTIVE,
+	ORPHAN_SCAN_INACTIVE
 };
 
 struct ocfs2_orphan_scan {
@@ -162,6 +171,7 @@ struct ocfs2_orphan_scan {
 	struct timespec		os_scantime;  /* time this node ran the scan */
 	u32			os_count;      /* tracks node specific scans */
 	u32  			os_seqno;       /* tracks cluster wide scans */
+	atomic_t		os_state;              /* ACTIVE or INACTIVE */
 };
 
 struct ocfs2_dlm_debug {
diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index fcd120f1493..3f661376a2d 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -236,6 +236,16 @@ static int o2cb_dlm_lock_status(union ocfs2_dlm_lksb *lksb)
 	return dlm_status_to_errno(lksb->lksb_o2dlm.status);
 }
 
+/*
+ * o2dlm aways has a "valid" LVB. If the dlm loses track of the LVB
+ * contents, it will zero out the LVB.  Thus the caller can always trust
+ * the contents.
+ */
+static int o2cb_dlm_lvb_valid(union ocfs2_dlm_lksb *lksb)
+{
+	return 1;
+}
+
 static void *o2cb_dlm_lvb(union ocfs2_dlm_lksb *lksb)
 {
 	return (void *)(lksb->lksb_o2dlm.lvb);
@@ -354,6 +364,7 @@ static struct ocfs2_stack_operations o2cb_stack_ops = {
 	.dlm_lock	= o2cb_dlm_lock,
 	.dlm_unlock	= o2cb_dlm_unlock,
 	.lock_status	= o2cb_dlm_lock_status,
+	.lvb_valid	= o2cb_dlm_lvb_valid,
 	.lock_lvb	= o2cb_dlm_lvb,
 	.dump_lksb	= o2cb_dump_lksb,
 };
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 9b76d41a8ac..ff4c798a563 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -738,6 +738,13 @@ static int user_dlm_lock_status(union ocfs2_dlm_lksb *lksb)
 	return lksb->lksb_fsdlm.sb_status;
 }
 
+static int user_dlm_lvb_valid(union ocfs2_dlm_lksb *lksb)
+{
+	int invalid = lksb->lksb_fsdlm.sb_flags & DLM_SBF_VALNOTVALID;
+
+	return !invalid;
+}
+
 static void *user_dlm_lvb(union ocfs2_dlm_lksb *lksb)
 {
 	if (!lksb->lksb_fsdlm.sb_lvbptr)
@@ -873,6 +880,7 @@ static struct ocfs2_stack_operations ocfs2_user_plugin_ops = {
 	.dlm_lock	= user_dlm_lock,
 	.dlm_unlock	= user_dlm_unlock,
 	.lock_status	= user_dlm_lock_status,
+	.lvb_valid	= user_dlm_lvb_valid,
 	.lock_lvb	= user_dlm_lvb,
 	.plock		= user_plock,
 	.dump_lksb	= user_dlm_dump_lksb,
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 68b668b0e60..3f2f1c45b7b 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -6,7 +6,7 @@
  * Code which implements an OCFS2 specific interface to underlying
  * cluster stacks.
  *
- * Copyright (C) 2007 Oracle.  All rights reserved.
+ * Copyright (C) 2007, 2009 Oracle.  All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public
@@ -271,11 +271,12 @@ int ocfs2_dlm_lock_status(union ocfs2_dlm_lksb *lksb)
 }
 EXPORT_SYMBOL_GPL(ocfs2_dlm_lock_status);
 
-/*
- * Why don't we cast to ocfs2_meta_lvb?  The "clean" answer is that we
- * don't cast at the glue level.  The real answer is that the header
- * ordering is nigh impossible.
- */
+int ocfs2_dlm_lvb_valid(union ocfs2_dlm_lksb *lksb)
+{
+	return active_stack->sp_ops->lvb_valid(lksb);
+}
+EXPORT_SYMBOL_GPL(ocfs2_dlm_lvb_valid);
+
 void *ocfs2_dlm_lvb(union ocfs2_dlm_lksb *lksb)
 {
 	return active_stack->sp_ops->lock_lvb(lksb);
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index c571af375ef..03a44d60eac 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -186,6 +186,11 @@ struct ocfs2_stack_operations {
 	int (*lock_status)(union ocfs2_dlm_lksb *lksb);
 
 	/*
+	 * Return non-zero if the LVB is valid.
+	 */
+	int (*lvb_valid)(union ocfs2_dlm_lksb *lksb);
+
+	/*
 	 * Pull the lvb pointer off of the stack-specific lksb.
 	 */
 	void *(*lock_lvb)(union ocfs2_dlm_lksb *lksb);
@@ -252,6 +257,7 @@ int ocfs2_dlm_unlock(struct ocfs2_cluster_connection *conn,
 		     struct ocfs2_lock_res *astarg);
 
 int ocfs2_dlm_lock_status(union ocfs2_dlm_lksb *lksb);
+int ocfs2_dlm_lvb_valid(union ocfs2_dlm_lksb *lksb);
 void *ocfs2_dlm_lvb(union ocfs2_dlm_lksb *lksb);
 void ocfs2_dlm_dump_lksb(union ocfs2_dlm_lksb *lksb);
 
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 8439f6b324b..73a16d4666d 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -923,14 +923,23 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
 					 int nr)
 {
 	struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
+	int ret;
 
 	if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap))
 		return 0;
-	if (!buffer_jbd(bg_bh) || !bh2jh(bg_bh)->b_committed_data)
+
+	if (!buffer_jbd(bg_bh))
 		return 1;
 
+	jbd_lock_bh_state(bg_bh);
 	bg = (struct ocfs2_group_desc *) bh2jh(bg_bh)->b_committed_data;
-	return !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
+	if (bg)
+		ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
+	else
+		ret = 1;
+	jbd_unlock_bh_state(bg_bh);
+
+	return ret;
 }
 
 static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
@@ -1885,6 +1894,7 @@ static inline int ocfs2_block_group_clear_bits(handle_t *handle,
 	unsigned int tmp;
 	int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
 	struct ocfs2_group_desc *undo_bg = NULL;
+	int cluster_bitmap = 0;
 
 	mlog_entry_void();
 
@@ -1905,18 +1915,28 @@ static inline int ocfs2_block_group_clear_bits(handle_t *handle,
 	}
 
 	if (ocfs2_is_cluster_bitmap(alloc_inode))
-		undo_bg = (struct ocfs2_group_desc *) bh2jh(group_bh)->b_committed_data;
+		cluster_bitmap = 1;
+
+	if (cluster_bitmap) {
+		jbd_lock_bh_state(group_bh);
+		undo_bg = (struct ocfs2_group_desc *)
+					bh2jh(group_bh)->b_committed_data;
+		BUG_ON(!undo_bg);
+	}
 
 	tmp = num_bits;
 	while(tmp--) {
 		ocfs2_clear_bit((bit_off + tmp),
 				(unsigned long *) bg->bg_bitmap);
-		if (ocfs2_is_cluster_bitmap(alloc_inode))
+		if (cluster_bitmap)
 			ocfs2_set_bit(bit_off + tmp,
 				      (unsigned long *) undo_bg->bg_bitmap);
 	}
 	le16_add_cpu(&bg->bg_free_bits_count, num_bits);
 
+	if (cluster_bitmap)
+		jbd_unlock_bh_state(group_bh);
+
 	status = ocfs2_journal_dirty(handle, group_bh);
 	if (status < 0)
 		mlog_errno(status);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 0d3ed7407a0..7efb349fb9b 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -205,11 +205,10 @@ static const match_table_t tokens = {
 #ifdef CONFIG_DEBUG_FS
 static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
 {
-	int out = 0;
-	int i;
 	struct ocfs2_cluster_connection *cconn = osb->cconn;
 	struct ocfs2_recovery_map *rm = osb->recovery_map;
-	struct ocfs2_orphan_scan *os;
+	struct ocfs2_orphan_scan *os = &osb->osb_orphan_scan;
+	int i, out = 0;
 
 	out += snprintf(buf + out, len - out,
 			"%10s => Id: %-s  Uuid: %-s  Gen: 0x%X  Label: %-s\n",
@@ -234,20 +233,24 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
 			"%10s => Opts: 0x%lX  AtimeQuanta: %u\n", "Mount",
 			osb->s_mount_opt, osb->s_atime_quantum);
 
-	out += snprintf(buf + out, len - out,
-			"%10s => Stack: %s  Name: %*s  Version: %d.%d\n",
-			"Cluster",
-			(*osb->osb_cluster_stack == '\0' ?
-			 "o2cb" : osb->osb_cluster_stack),
-			cconn->cc_namelen, cconn->cc_name,
-			cconn->cc_version.pv_major, cconn->cc_version.pv_minor);
+	if (cconn) {
+		out += snprintf(buf + out, len - out,
+				"%10s => Stack: %s  Name: %*s  "
+				"Version: %d.%d\n", "Cluster",
+				(*osb->osb_cluster_stack == '\0' ?
+				 "o2cb" : osb->osb_cluster_stack),
+				cconn->cc_namelen, cconn->cc_name,
+				cconn->cc_version.pv_major,
+				cconn->cc_version.pv_minor);
+	}
 
 	spin_lock(&osb->dc_task_lock);
 	out += snprintf(buf + out, len - out,
 			"%10s => Pid: %d  Count: %lu  WakeSeq: %lu  "
 			"WorkSeq: %lu\n", "DownCnvt",
-			task_pid_nr(osb->dc_task), osb->blocked_lock_count,
-			osb->dc_wake_sequence, osb->dc_work_sequence);
+			(osb->dc_task ?  task_pid_nr(osb->dc_task) : -1),
+			osb->blocked_lock_count, osb->dc_wake_sequence,
+			osb->dc_work_sequence);
 	spin_unlock(&osb->dc_task_lock);
 
 	spin_lock(&osb->osb_lock);
@@ -267,14 +270,15 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
 
 	out += snprintf(buf + out, len - out,
 			"%10s => Pid: %d  Interval: %lu  Needs: %d\n", "Commit",
-			task_pid_nr(osb->commit_task), osb->osb_commit_interval,
+			(osb->commit_task ? task_pid_nr(osb->commit_task) : -1),
+			osb->osb_commit_interval,
 			atomic_read(&osb->needs_checkpoint));
 
 	out += snprintf(buf + out, len - out,
-			"%10s => State: %d  NumTxns: %d  TxnId: %lu\n",
+			"%10s => State: %d  TxnId: %lu  NumTxns: %d\n",
 			"Journal", osb->journal->j_state,
-			atomic_read(&osb->journal->j_num_trans),
-			osb->journal->j_trans_id);
+			osb->journal->j_trans_id,
+			atomic_read(&osb->journal->j_num_trans));
 
 	out += snprintf(buf + out, len - out,
 			"%10s => GlobalAllocs: %d  LocalAllocs: %d  "
@@ -300,9 +304,18 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
 			atomic_read(&osb->s_num_inodes_stolen));
 	spin_unlock(&osb->osb_lock);
 
+	out += snprintf(buf + out, len - out, "OrphanScan => ");
+	out += snprintf(buf + out, len - out, "Local: %u  Global: %u ",
+			os->os_count, os->os_seqno);
+	out += snprintf(buf + out, len - out, " Last Scan: ");
+	if (atomic_read(&os->os_state) == ORPHAN_SCAN_INACTIVE)
+		out += snprintf(buf + out, len - out, "Disabled\n");
+	else
+		out += snprintf(buf + out, len - out, "%lu seconds ago\n",
+				(get_seconds() - os->os_scantime.tv_sec));
+
 	out += snprintf(buf + out, len - out, "%10s => %3s  %10s\n",
 			"Slots", "Num", "RecoGen");
-
 	for (i = 0; i < osb->max_slots; ++i) {
 		out += snprintf(buf + out, len - out,
 				"%10s  %c %3d  %10d\n",
@@ -311,13 +324,6 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
 				i, osb->slot_recovery_generations[i]);
 	}
 
-	os = &osb->osb_orphan_scan;
-	out += snprintf(buf + out, len - out, "Orphan Scan=> ");
-	out += snprintf(buf + out, len - out, "Local: %u  Global: %u ",
-			os->os_count, os->os_seqno);
-	out += snprintf(buf + out, len - out, " Last Scan: %lu seconds ago\n",
-			(get_seconds() - os->os_scantime.tv_sec));
-
 	return out;
 }
 
@@ -1175,6 +1181,9 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 	atomic_set(&osb->vol_state, VOLUME_MOUNTED_QUOTAS);
 	wake_up(&osb->osb_mount_event);
 
+	/* Start this when the mount is almost sure of being successful */
+	ocfs2_orphan_scan_init(osb);
+
 	mlog_exit(status);
 	return status;
 
@@ -1810,14 +1819,15 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
 	debugfs_remove(osb->osb_ctxt);
 
+	/* Orphan scan should be stopped as early as possible */
+	ocfs2_orphan_scan_stop(osb);
+
 	ocfs2_disable_quotas(osb);
 
 	ocfs2_shutdown_local_alloc(osb);
 
 	ocfs2_truncate_log_shutdown(osb);
 
-	ocfs2_orphan_scan_stop(osb);
-
 	/* This will disable recovery and flush any recovery work. */
 	ocfs2_recovery_exit(osb);
 
@@ -1978,13 +1988,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 		goto bail;
 	}
 
-	status = ocfs2_orphan_scan_init(osb);
-	if (status) {
-		mlog(ML_ERROR, "Unable to initialize delayed orphan scan\n");
-		mlog_errno(status);
-		goto bail;
-	}
-
 	init_waitqueue_head(&osb->checkpoint_event);
 	atomic_set(&osb->needs_checkpoint, 0);
 
diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c
index ab713ebdd54..40e53702948 100644
--- a/fs/ocfs2/sysfile.c
+++ b/fs/ocfs2/sysfile.c
@@ -50,6 +50,10 @@ static inline int is_in_system_inode_array(struct ocfs2_super *osb,
 					   int type,
 					   u32 slot);
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key ocfs2_sysfile_cluster_lock_key[NUM_SYSTEM_INODES];
+#endif
+
 static inline int is_global_system_inode(int type)
 {
 	return type >= OCFS2_FIRST_ONLINE_SYSTEM_INODE &&
@@ -118,6 +122,21 @@ static struct inode * _ocfs2_get_system_file_inode(struct ocfs2_super *osb,
 		inode = NULL;
 		goto bail;
 	}
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	if (type == LOCAL_USER_QUOTA_SYSTEM_INODE ||
+	    type == LOCAL_GROUP_QUOTA_SYSTEM_INODE ||
+	    type == JOURNAL_SYSTEM_INODE) {
+		/* Ignore inode lock on these inodes as the lock does not
+		 * really belong to any process and lockdep cannot handle
+		 * that */
+		OCFS2_I(inode)->ip_inode_lockres.l_lockdep_map.key = NULL;
+	} else {
+		lockdep_init_map(&OCFS2_I(inode)->ip_inode_lockres.
+								l_lockdep_map,
+				 ocfs2_system_inodes[type].si_name,
+				 &ocfs2_sysfile_cluster_lock_key[type], 0);
+	}
+#endif
 bail:
 
 	return inode;