1 files changed, 103 insertions, 36 deletions

diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 97a972efab83..0ff424c6d17c 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -788,35 +788,34 @@ static inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
 	spin_unlock(&lockres->l_lock);
 }
 
-static inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
-				       struct ocfs2_lock_holder *oh)
-{
-	spin_lock(&lockres->l_lock);
-	list_del(&oh->oh_list);
-	spin_unlock(&lockres->l_lock);
-
-	put_pid(oh->oh_owner_pid);
-}
-
-static inline int ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres)
+static struct ocfs2_lock_holder *
+ocfs2_pid_holder(struct ocfs2_lock_res *lockres,
+		struct pid *pid)
 {
 	struct ocfs2_lock_holder *oh;
-	struct pid *pid;
 
-	/* look in the list of holders for one with the current task as owner */
 	spin_lock(&lockres->l_lock);
-	pid = task_pid(current);
 	list_for_each_entry(oh, &lockres->l_holders, oh_list) {
 		if (oh->oh_owner_pid == pid) {
 			spin_unlock(&lockres->l_lock);
-			return 1;
+			return oh;
 		}
 	}
 	spin_unlock(&lockres->l_lock);
+	return NULL;
+}
 
-	return 0;
+static inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
+				       struct ocfs2_lock_holder *oh)
+{
+	spin_lock(&lockres->l_lock);
+	list_del(&oh->oh_list);
+	spin_unlock(&lockres->l_lock);
+
+	put_pid(oh->oh_owner_pid);
 }
 
+
 static inline void ocfs2_inc_holders(struct ocfs2_lock_res *lockres,
 				     int level)
 {
@@ -2141,6 +2140,7 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode)
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 	struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres;
 	struct ocfs2_meta_lvb *lvb;
+	struct timespec ts;
 
 	lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
 
@@ -2161,12 +2161,15 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode)
 	lvb->lvb_igid      = cpu_to_be32(i_gid_read(inode));
 	lvb->lvb_imode     = cpu_to_be16(inode->i_mode);
 	lvb->lvb_inlink    = cpu_to_be16(inode->i_nlink);
+	ts = timespec64_to_timespec(inode->i_atime);
 	lvb->lvb_iatime_packed  =
-		cpu_to_be64(ocfs2_pack_timespec(&inode->i_atime));
+		cpu_to_be64(ocfs2_pack_timespec(&ts));
+	ts = timespec64_to_timespec(inode->i_ctime);
 	lvb->lvb_ictime_packed =
-		cpu_to_be64(ocfs2_pack_timespec(&inode->i_ctime));
+		cpu_to_be64(ocfs2_pack_timespec(&ts));
+	ts = timespec64_to_timespec(inode->i_mtime);
 	lvb->lvb_imtime_packed =
-		cpu_to_be64(ocfs2_pack_timespec(&inode->i_mtime));
+		cpu_to_be64(ocfs2_pack_timespec(&ts));
 	lvb->lvb_iattr    = cpu_to_be32(oi->ip_attr);
 	lvb->lvb_idynfeatures = cpu_to_be16(oi->ip_dyn_features);
 	lvb->lvb_igeneration = cpu_to_be32(inode->i_generation);
@@ -2184,6 +2187,7 @@ static void ocfs2_unpack_timespec(struct timespec *spec,
 
 static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
 {
+	struct timespec ts;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 	struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres;
 	struct ocfs2_meta_lvb *lvb;
@@ -2211,12 +2215,15 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
 	i_gid_write(inode, be32_to_cpu(lvb->lvb_igid));
 	inode->i_mode    = be16_to_cpu(lvb->lvb_imode);
 	set_nlink(inode, be16_to_cpu(lvb->lvb_inlink));
-	ocfs2_unpack_timespec(&inode->i_atime,
+	ocfs2_unpack_timespec(&ts,
 			      be64_to_cpu(lvb->lvb_iatime_packed));
-	ocfs2_unpack_timespec(&inode->i_mtime,
+	inode->i_atime = timespec_to_timespec64(ts);
+	ocfs2_unpack_timespec(&ts,
 			      be64_to_cpu(lvb->lvb_imtime_packed));
-	ocfs2_unpack_timespec(&inode->i_ctime,
+	inode->i_mtime = timespec_to_timespec64(ts);
+	ocfs2_unpack_timespec(&ts,
 			      be64_to_cpu(lvb->lvb_ictime_packed));
+	inode->i_ctime = timespec_to_timespec64(ts);
 	spin_unlock(&oi->ip_lock);
 }
 
@@ -2610,34 +2617,93 @@ void ocfs2_inode_unlock(struct inode *inode,
  *
  * return < 0 on error, return == 0 if there's no lock holder on the stack
  * before this call, return == 1 if this call would be a recursive locking.
+ * return == -1 if this lock attempt will cause an upgrade which is forbidden.
+ *
+ * When taking lock levels into account,we face some different situations.
+ *
+ * 1. no lock is held
+ *    In this case, just lock the inode as requested and return 0
+ *
+ * 2. We are holding a lock
+ *    For this situation, things diverges into several cases
+ *
+ *    wanted     holding	     what to do
+ *    ex		ex	    see 2.1 below
+ *    ex		pr	    see 2.2 below
+ *    pr		ex	    see 2.1 below
+ *    pr		pr	    see 2.1 below
+ *
+ *    2.1 lock level that is been held is compatible
+ *    with the wanted level, so no lock action will be tacken.
+ *
+ *    2.2 Otherwise, an upgrade is needed, but it is forbidden.
+ *
+ * Reason why upgrade within a process is forbidden is that
+ * lock upgrade may cause dead lock. The following illustrates
+ * how it happens.
+ *
+ *         thread on node1                             thread on node2
+ * ocfs2_inode_lock_tracker(ex=0)
+ *
+ *                                <======   ocfs2_inode_lock_tracker(ex=1)
+ *
+ * ocfs2_inode_lock_tracker(ex=1)
  */
 int ocfs2_inode_lock_tracker(struct inode *inode,
 			     struct buffer_head **ret_bh,
 			     int ex,
 			     struct ocfs2_lock_holder *oh)
 {
-	int status;
-	int arg_flags = 0, has_locked;
+	int status = 0;
 	struct ocfs2_lock_res *lockres;
+	struct ocfs2_lock_holder *tmp_oh;
+	struct pid *pid = task_pid(current);
+
 
 	lockres = &OCFS2_I(inode)->ip_inode_lockres;
-	has_locked = ocfs2_is_locked_by_me(lockres);
-	/* Just get buffer head if the cluster lock has been taken */
-	if (has_locked)
-		arg_flags = OCFS2_META_LOCK_GETBH;
+	tmp_oh = ocfs2_pid_holder(lockres, pid);
 
-	if (likely(!has_locked || ret_bh)) {
-		status = ocfs2_inode_lock_full(inode, ret_bh, ex, arg_flags);
+	if (!tmp_oh) {
+		/*
+		 * This corresponds to the case 1.
+		 * We haven't got any lock before.
+		 */
+		status = ocfs2_inode_lock_full(inode, ret_bh, ex, 0);
 		if (status < 0) {
 			if (status != -ENOENT)
 				mlog_errno(status);
 			return status;
 		}
-	}
-	if (!has_locked)
+
+		oh->oh_ex = ex;
 		ocfs2_add_holder(lockres, oh);
+		return 0;
+	}
 
-	return has_locked;
+	if (unlikely(ex && !tmp_oh->oh_ex)) {
+		/*
+		 * case 2.2 upgrade may cause dead lock, forbid it.
+		 */
+		mlog(ML_ERROR, "Recursive locking is not permitted to "
+		     "upgrade to EX level from PR level.\n");
+		dump_stack();
+		return -EINVAL;
+	}
+
+	/*
+	 *  case 2.1 OCFS2_META_LOCK_GETBH flag make ocfs2_inode_lock_full.
+	 *  ignore the lock level and just update it.
+	 */
+	if (ret_bh) {
+		status = ocfs2_inode_lock_full(inode, ret_bh, ex,
+					       OCFS2_META_LOCK_GETBH);
+		if (status < 0) {
+			if (status != -ENOENT)
+				mlog_errno(status);
+			return status;
+		}
+	}
+	return tmp_oh ? 1 : 0;
 }
 
 void ocfs2_inode_unlock_tracker(struct inode *inode,
@@ -2649,12 +2715,13 @@ void ocfs2_inode_unlock_tracker(struct inode *inode,
 
 	lockres = &OCFS2_I(inode)->ip_inode_lockres;
 	/* had_lock means that the currect process already takes the cluster
-	 * lock previously. If had_lock is 1, we have nothing to do here, and
-	 * it will get unlocked where we got the lock.
+	 * lock previously.
+	 * If had_lock is 1, we have nothing to do here.
+	 * If had_lock is 0, we will release the lock.
 	 */
 	if (!had_lock) {
+		ocfs2_inode_unlock(inode, oh->oh_ex);
 		ocfs2_remove_holder(lockres, oh);
-		ocfs2_inode_unlock(inode, ex);
 	}
 }