1 files changed, 48 insertions, 9 deletions

diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index d17a704..f8529fc 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -98,9 +98,25 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task)
 	list_add(&task->u.tk_wait.timer_list, &queue->timer_list.list);
 }
 
+static void rpc_rotate_queue_owner(struct rpc_wait_queue *queue)
+{
+	struct list_head *q = &queue->tasks[queue->priority];
+	struct rpc_task *task;
+
+	if (!list_empty(q)) {
+		task = list_first_entry(q, struct rpc_task, u.tk_wait.list);
+		if (task->tk_owner == queue->owner)
+			list_move_tail(&task->u.tk_wait.list, q);
+	}
+}
+
 static void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority)
 {
-	queue->priority = priority;
+	if (queue->priority != priority) {
+		/* Fairness: rotate the list when changing priority */
+		rpc_rotate_queue_owner(queue);
+		queue->priority = priority;
+	}
 }
 
 static void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid)
@@ -164,6 +180,8 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
 		list_add_tail(&task->u.tk_wait.list, &queue->tasks[0]);
 	task->tk_waitqueue = queue;
 	queue->qlen++;
+	/* barrier matches the read in rpc_wake_up_task_queue_locked() */
+	smp_wmb();
 	rpc_set_queued(task);
 
 	dprintk("RPC: %5u added to queue %p \"%s\"\n",
@@ -414,8 +432,11 @@ static void __rpc_do_wake_up_task(struct rpc_wait_queue *queue, struct rpc_task
  */
 static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, struct rpc_task *task)
 {
-	if (RPC_IS_QUEUED(task) && task->tk_waitqueue == queue)
-		__rpc_do_wake_up_task(queue, task);
+	if (RPC_IS_QUEUED(task)) {
+		smp_rmb();
+		if (task->tk_waitqueue == queue)
+			__rpc_do_wake_up_task(queue, task);
+	}
 }
 
 /*
@@ -934,16 +955,35 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data)
 	return task;
 }
 
+/*
+ * rpc_free_task - release rpc task and perform cleanups
+ *
+ * Note that we free up the rpc_task _after_ rpc_release_calldata()
+ * in order to work around a workqueue dependency issue.
+ *
+ * Tejun Heo states:
+ * "Workqueue currently considers two work items to be the same if they're
+ * on the same address and won't execute them concurrently - ie. it
+ * makes a work item which is queued again while being executed wait
+ * for the previous execution to complete.
+ *
+ * If a work function frees the work item, and then waits for an event
+ * which should be performed by another work item and *that* work item
+ * recycles the freed work item, it can create a false dependency loop.
+ * There really is no reliable way to detect this short of verifying
+ * every memory free."
+ *
+ */
 static void rpc_free_task(struct rpc_task *task)
 {
-	const struct rpc_call_ops *tk_ops = task->tk_ops;
-	void *calldata = task->tk_calldata;
+	unsigned short tk_flags = task->tk_flags;
+
+	rpc_release_calldata(task->tk_ops, task->tk_calldata);
 
-	if (task->tk_flags & RPC_TASK_DYNAMIC) {
+	if (tk_flags & RPC_TASK_DYNAMIC) {
 		dprintk("RPC: %5u freeing task\n", task->tk_pid);
 		mempool_free(task, rpc_task_mempool);
 	}
-	rpc_release_calldata(tk_ops, calldata);
 }
 
 static void rpc_async_release(struct work_struct *work)
@@ -953,8 +993,7 @@ static void rpc_async_release(struct work_struct *work)
 
 static void rpc_release_resources_task(struct rpc_task *task)
 {
-	if (task->tk_rqstp)
-		xprt_release(task);
+	xprt_release(task);
 	if (task->tk_msg.rpc_cred) {
 		put_rpccred(task->tk_msg.rpc_cred);
 		task->tk_msg.rpc_cred = NULL;