net/mlx4_en: Fix mixed PFC and Global pause user control requests

[pandora-kernel.git] / net / sunrpc / sched.c

diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 00a1a2a..206c61e 100644 (file)
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -139,6 +139,8 @@ 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",
@@ -294,13 +296,20 @@ EXPORT_SYMBOL_GPL(__rpc_wait_for_completion_task);
 /*
  * Make an RPC task runnable.
  *
- * Note: If the task is ASYNC, this must be called with
- * the spinlock held to protect the wait queue operation.
+ * Note: If the task is ASYNC, and is being made runnable after sitting on an
+ * rpc_wait_queue, this must be called with the queue spinlock held to protect
+ * the wait queue operation.
+ * Note the ordering of rpc_test_and_set_running() and rpc_clear_queued(),
+ * which is needed to ensure that __rpc_execute() doesn't loop (due to the
+ * lockless RPC_IS_QUEUED() test) before we've had a chance to test
+ * the RPC_TASK_RUNNING flag.
  */
 static void rpc_make_runnable(struct rpc_task *task)
 {
+       bool need_wakeup = !rpc_test_and_set_running(task);
+
        rpc_clear_queued(task);
-       if (rpc_test_and_set_running(task))
+       if (!need_wakeup)
                return;
        if (RPC_IS_ASYNC(task)) {
                INIT_WORK(&task->u.tk_work, rpc_async_schedule);
@@ -389,8 +398,11 @@ 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);
+       }
 }
 
 /*
@@ -500,14 +512,18 @@ EXPORT_SYMBOL_GPL(rpc_wake_up_next);
  */
 void rpc_wake_up(struct rpc_wait_queue *queue)
 {
-       struct rpc_task *task, *next;
        struct list_head *head;
 
        spin_lock_bh(&queue->lock);
        head = &queue->tasks[queue->maxpriority];
        for (;;) {
-               list_for_each_entry_safe(task, next, head, u.tk_wait.list)
+               while (!list_empty(head)) {
+                       struct rpc_task *task;
+                       task = list_first_entry(head,
+                                       struct rpc_task,
+                                       u.tk_wait.list);
                        rpc_wake_up_task_queue_locked(queue, task);
+               }
                if (head == &queue->tasks[0])
                        break;
                head--;
@@ -525,13 +541,16 @@ EXPORT_SYMBOL_GPL(rpc_wake_up);
  */
 void rpc_wake_up_status(struct rpc_wait_queue *queue, int status)
 {
-       struct rpc_task *task, *next;
        struct list_head *head;
 
        spin_lock_bh(&queue->lock);
        head = &queue->tasks[queue->maxpriority];
        for (;;) {
-               list_for_each_entry_safe(task, next, head, u.tk_wait.list) {
+               while (!list_empty(head)) {
+                       struct rpc_task *task;
+                       task = list_first_entry(head,
+                                       struct rpc_task,
+                                       u.tk_wait.list);
                        task->tk_status = status;
                        rpc_wake_up_task_queue_locked(queue, task);
                }
@@ -748,7 +767,9 @@ void rpc_execute(struct rpc_task *task)
 
 static void rpc_async_schedule(struct work_struct *work)
 {
+       current->flags |= PF_FSTRANS;
        __rpc_execute(container_of(work, struct rpc_task, u.tk_work));
+       current->flags &= ~PF_FSTRANS;
 }
 
 /**
@@ -871,16 +892,35 @@ 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)
@@ -890,8 +930,7 @@ 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;