1 files changed, 38 insertions, 18 deletions

diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index e2c835482791..b258b87a3ec2 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -57,6 +57,13 @@ struct workqueue_struct *rpciod_workqueue __read_mostly;
 struct workqueue_struct *xprtiod_workqueue __read_mostly;
 EXPORT_SYMBOL_GPL(xprtiod_workqueue);
 
+gfp_t rpc_task_gfp_mask(void)
+{
+	if (current->flags & PF_WQ_WORKER)
+		return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
+	return GFP_KERNEL;
+}
+
 unsigned long
 rpc_task_timeout(const struct rpc_task *task)
 {
@@ -186,11 +193,6 @@ static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue,
 
 /*
  * Add new request to wait queue.
- *
- * Swapper tasks always get inserted at the head of the queue.
- * This should avoid many nasty memory deadlocks and hopefully
- * improve overall performance.
- * Everyone else gets appended to the queue to ensure proper FIFO behavior.
  */
 static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
 		struct rpc_task *task,
@@ -199,8 +201,6 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
 	INIT_LIST_HEAD(&task->u.tk_wait.timer_list);
 	if (RPC_IS_PRIORITY(queue))
 		__rpc_add_wait_queue_priority(queue, task, queue_priority);
-	else if (RPC_IS_SWAPPER(task))
-		list_add(&task->u.tk_wait.list, &queue->tasks[0]);
 	else
 		list_add_tail(&task->u.tk_wait.list, &queue->tasks[0]);
 	task->tk_waitqueue = queue;
@@ -876,6 +876,15 @@ void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata)
 		ops->rpc_release(calldata);
 }
 
+static bool xprt_needs_memalloc(struct rpc_xprt *xprt, struct rpc_task *tk)
+{
+	if (!xprt)
+		return false;
+	if (!atomic_read(&xprt->swapper))
+		return false;
+	return test_bit(XPRT_LOCKED, &xprt->state) && xprt->snd_task == tk;
+}
+
 /*
  * This is the RPC `scheduler' (or rather, the finite state machine).
  */
@@ -884,6 +893,7 @@ static void __rpc_execute(struct rpc_task *task)
 	struct rpc_wait_queue *queue;
 	int task_is_async = RPC_IS_ASYNC(task);
 	int status = 0;
+	unsigned long pflags = current->flags;
 
 	WARN_ON_ONCE(RPC_IS_QUEUED(task));
 	if (RPC_IS_QUEUED(task))
@@ -906,6 +916,10 @@ static void __rpc_execute(struct rpc_task *task)
 		}
 		if (!do_action)
 			break;
+		if (RPC_IS_SWAPPER(task) ||
+		    xprt_needs_memalloc(task->tk_xprt, task))
+			current->flags |= PF_MEMALLOC;
+
 		trace_rpc_task_run_action(task, do_action);
 		do_action(task);
 
@@ -943,7 +957,7 @@ static void __rpc_execute(struct rpc_task *task)
 		rpc_clear_running(task);
 		spin_unlock(&queue->lock);
 		if (task_is_async)
-			return;
+			goto out;
 
 		/* sync task: sleep here */
 		trace_rpc_task_sync_sleep(task, task->tk_action);
@@ -967,6 +981,8 @@ static void __rpc_execute(struct rpc_task *task)
 
 	/* Release all resources associated with the task */
 	rpc_release_task(task);
+out:
+	current_restore_flags(pflags, PF_MEMALLOC);
 }
 
 /*
@@ -1021,15 +1037,15 @@ int rpc_malloc(struct rpc_task *task)
 	struct rpc_rqst *rqst = task->tk_rqstp;
 	size_t size = rqst->rq_callsize + rqst->rq_rcvsize;
 	struct rpc_buffer *buf;
-	gfp_t gfp = GFP_NOFS;
-
-	if (RPC_IS_SWAPPER(task))
-		gfp = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN;
+	gfp_t gfp = rpc_task_gfp_mask();
 
 	size += sizeof(struct rpc_buffer);
-	if (size <= RPC_BUFFER_MAXSIZE)
-		buf = mempool_alloc(rpc_buffer_mempool, gfp);
-	else
+	if (size <= RPC_BUFFER_MAXSIZE) {
+		buf = kmem_cache_alloc(rpc_buffer_slabp, gfp);
+		/* Reach for the mempool if dynamic allocation fails */
+		if (!buf && RPC_IS_ASYNC(task))
+			buf = mempool_alloc(rpc_buffer_mempool, GFP_NOWAIT);
+	} else
 		buf = kmalloc(size, gfp);
 
 	if (!buf)
@@ -1092,10 +1108,14 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
 	rpc_init_task_statistics(task);
 }
 
-static struct rpc_task *
-rpc_alloc_task(void)
+static struct rpc_task *rpc_alloc_task(void)
 {
-	return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOFS);
+	struct rpc_task *task;
+
+	task = kmem_cache_alloc(rpc_task_slabp, rpc_task_gfp_mask());
+	if (task)
+		return task;
+	return mempool_alloc(rpc_task_mempool, GFP_NOWAIT);
 }
 
 /*