1 files changed, 70 insertions, 45 deletions

diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index ed4357e62f35..70a4752ed913 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -30,8 +30,6 @@ struct plock_async_data {
 struct plock_op {
 	struct list_head list;
 	int done;
-	/* if lock op got interrupted while waiting dlm_controld reply */
-	bool sigint;
 	struct dlm_plock_info info;
 	/* if set indicates async handling */
 	struct plock_async_data *data;
@@ -157,23 +155,29 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 
 	send_op(op);
 
-	rv = wait_event_interruptible(recv_wq, (op->done != 0));
-	if (rv == -ERESTARTSYS) {
-		spin_lock(&ops_lock);
-		/* recheck under ops_lock if we got a done != 0,
-		 * if so this interrupt case should be ignored
-		 */
-		if (op->done != 0) {
+	if (op->info.wait) {
+		rv = wait_event_killable(recv_wq, (op->done != 0));
+		if (rv == -ERESTARTSYS) {
+			spin_lock(&ops_lock);
+			/* recheck under ops_lock if we got a done != 0,
+			 * if so this interrupt case should be ignored
+			 */
+			if (op->done != 0) {
+				spin_unlock(&ops_lock);
+				goto do_lock_wait;
+			}
+			list_del(&op->list);
 			spin_unlock(&ops_lock);
-			goto do_lock_wait;
-		}
 
-		op->sigint = true;
-		spin_unlock(&ops_lock);
-		log_debug(ls, "%s: wait interrupted %x %llx pid %d",
-			  __func__, ls->ls_global_id,
-			  (unsigned long long)number, op->info.pid);
-		goto out;
+			log_debug(ls, "%s: wait interrupted %x %llx pid %d",
+				  __func__, ls->ls_global_id,
+				  (unsigned long long)number, op->info.pid);
+			do_unlock_close(&op->info);
+			dlm_release_plock_op(op);
+			goto out;
+		}
+	} else {
+		wait_event(recv_wq, (op->done != 0));
 	}
 
 do_lock_wait:
@@ -360,7 +364,9 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 		locks_init_lock(fl);
 		fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
 		fl->fl_flags = FL_POSIX;
-		fl->fl_pid = -op->info.pid;
+		fl->fl_pid = op->info.pid;
+		if (op->info.nodeid != dlm_our_nodeid())
+			fl->fl_pid = -fl->fl_pid;
 		fl->fl_start = op->info.start;
 		fl->fl_end = op->info.end;
 		rv = 0;
@@ -389,7 +395,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count,
 		if (op->info.flags & DLM_PLOCK_FL_CLOSE)
 			list_del(&op->list);
 		else
-			list_move(&op->list, &recv_list);
+			list_move_tail(&op->list, &recv_list);
 		memcpy(&info, &op->info, sizeof(info));
 	}
 	spin_unlock(&ops_lock);
@@ -427,34 +433,53 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
 	if (check_version(&info))
 		return -EINVAL;
 
+	/*
+	 * The results for waiting ops (SETLKW) can be returned in any
+	 * order, so match all fields to find the op.  The results for
+	 * non-waiting ops are returned in the order that they were sent
+	 * to userspace, so match the result with the first non-waiting op.
+	 */
 	spin_lock(&ops_lock);
-	list_for_each_entry(iter, &recv_list, list) {
-		if (iter->info.fsid == info.fsid &&
-		    iter->info.number == info.number &&
-		    iter->info.owner == info.owner) {
-			if (iter->sigint) {
-				list_del(&iter->list);
-				spin_unlock(&ops_lock);
-
-				pr_debug("%s: sigint cleanup %x %llx pid %d",
-					  __func__, iter->info.fsid,
-					  (unsigned long long)iter->info.number,
-					  iter->info.pid);
-				do_unlock_close(&iter->info);
-				memcpy(&iter->info, &info, sizeof(info));
-				dlm_release_plock_op(iter);
-				return count;
+	if (info.wait) {
+		list_for_each_entry(iter, &recv_list, list) {
+			if (iter->info.fsid == info.fsid &&
+			    iter->info.number == info.number &&
+			    iter->info.owner == info.owner &&
+			    iter->info.pid == info.pid &&
+			    iter->info.start == info.start &&
+			    iter->info.end == info.end &&
+			    iter->info.ex == info.ex &&
+			    iter->info.wait) {
+				op = iter;
+				break;
+			}
+		}
+	} else {
+		list_for_each_entry(iter, &recv_list, list) {
+			if (!iter->info.wait) {
+				op = iter;
+				break;
 			}
-			list_del_init(&iter->list);
-			memcpy(&iter->info, &info, sizeof(info));
-			if (iter->data)
-				do_callback = 1;
-			else
-				iter->done = 1;
-			op = iter;
-			break;
 		}
 	}
+
+	if (op) {
+		/* Sanity check that op and info match. */
+		if (info.wait)
+			WARN_ON(op->info.optype != DLM_PLOCK_OP_LOCK);
+		else
+			WARN_ON(op->info.fsid != info.fsid ||
+				op->info.number != info.number ||
+				op->info.owner != info.owner ||
+				op->info.optype != info.optype);
+
+		list_del_init(&op->list);
+		memcpy(&op->info, &info, sizeof(info));
+		if (op->data)
+			do_callback = 1;
+		else
+			op->done = 1;
+	}
 	spin_unlock(&ops_lock);
 
 	if (op) {
@@ -463,8 +488,8 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
 		else
 			wake_up(&recv_wq);
 	} else
-		log_print("%s: no op %x %llx", __func__,
-			  info.fsid, (unsigned long long)info.number);
+		pr_debug("%s: no op %x %llx", __func__,
+			 info.fsid, (unsigned long long)info.number);
 	return count;
 }