2 files changed, 26 insertions, 33 deletions

diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index db4674211f36..54ae6a569f6a 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -510,7 +510,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 		pool->sp_id = i;
 		INIT_LIST_HEAD(&pool->sp_sockets);
 		INIT_LIST_HEAD(&pool->sp_all_threads);
-		INIT_LIST_HEAD(&pool->sp_idle_threads);
+		init_llist_head(&pool->sp_idle_threads);
 		spin_lock_init(&pool->sp_lock);
 
 		percpu_counter_init(&pool->sp_messages_arrived, 0, GFP_KERNEL);
@@ -642,7 +642,7 @@ svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node)
 
 	folio_batch_init(&rqstp->rq_fbatch);
 
-	svc_thread_set_busy(rqstp);
+	init_llist_node(&rqstp->rq_idle);
 	rqstp->rq_server = serv;
 	rqstp->rq_pool = pool;
 
@@ -701,15 +701,15 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 void svc_pool_wake_idle_thread(struct svc_pool *pool)
 {
 	struct svc_rqst	*rqstp;
+	struct llist_node *ln;
 
 	rcu_read_lock();
 	spin_lock_bh(&pool->sp_lock);
-	rqstp = list_first_entry_or_null(&pool->sp_idle_threads,
-					 struct svc_rqst, rq_idle);
-	if (rqstp)
-		list_del_init(&rqstp->rq_idle);
+	ln = llist_del_first_init(&pool->sp_idle_threads);
 	spin_unlock_bh(&pool->sp_lock);
-	if (rqstp) {
+	if (ln) {
+		rqstp = llist_entry(ln, struct svc_rqst, rq_idle);
+
 		WRITE_ONCE(rqstp->rq_qtime, ktime_get());
 		wake_up_process(rqstp->rq_task);
 		rcu_read_unlock();
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index fa0d854a5596..17c43bde35c9 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -715,10 +715,6 @@ rqst_should_sleep(struct svc_rqst *rqstp)
 	if (svc_thread_should_stop(rqstp))
 		return false;
 
-	/* are we freezing? */
-	if (freezing(current))
-		return false;
-
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 	if (svc_is_backchannel(rqstp)) {
 		if (!list_empty(&rqstp->rq_server->sv_cb_list))
@@ -734,30 +730,26 @@ static void svc_rqst_wait_for_work(struct svc_rqst *rqstp)
 	struct svc_pool *pool = rqstp->rq_pool;
 
 	if (rqst_should_sleep(rqstp)) {
-		set_current_state(TASK_IDLE);
-		spin_lock_bh(&pool->sp_lock);
-		list_add(&rqstp->rq_idle, &pool->sp_idle_threads);
-		spin_unlock_bh(&pool->sp_lock);
+		set_current_state(TASK_IDLE | TASK_FREEZABLE);
+		llist_add(&rqstp->rq_idle, &pool->sp_idle_threads);
+
+		if (unlikely(!rqst_should_sleep(rqstp)))
+			/* Work just became available.  This thread cannot simply
+			 * choose not to sleep as it *must* wait until removed.
+			 * So wake the first waiter - whether it is this
+			 * thread or some other, it will get the work done.
+			 */
+			svc_pool_wake_idle_thread(pool);
 
-		/* Need to check should_sleep() again after
-		 * setting task state in case a wakeup happened
-		 * between testing and setting.
+		/* Since a thread cannot remove itself from an llist,
+		 * schedule until someone else removes @rqstp from
+		 * the idle list.
 		 */
-		if (rqst_should_sleep(rqstp)) {
+		while (!svc_thread_busy(rqstp)) {
 			schedule();
-		} else {
-			__set_current_state(TASK_RUNNING);
-			cond_resched();
-		}
-
-		/* We *must* be removed from the list before we can continue.
-		 * If we were woken, this is already done
-		 */
-		if (!svc_thread_busy(rqstp)) {
-			spin_lock_bh(&pool->sp_lock);
-			list_del_init(&rqstp->rq_idle);
-			spin_unlock_bh(&pool->sp_lock);
+			set_current_state(TASK_IDLE | TASK_FREEZABLE);
 		}
+		__set_current_state(TASK_RUNNING);
 	} else {
 		cond_resched();
 	}
@@ -870,9 +862,10 @@ void svc_recv(struct svc_rqst *rqstp)
 		struct svc_xprt *xprt = rqstp->rq_xprt;
 
 		/* Normally we will wait up to 5 seconds for any required
-		 * cache information to be provided.
+		 * cache information to be provided.  When there are no
+		 * idle threads, we reduce the wait time.
 		 */
-		if (!list_empty(&pool->sp_idle_threads))
+		if (pool->sp_idle_threads.first)
 			rqstp->rq_chandle.thread_wait = 5 * HZ;
 		else
 			rqstp->rq_chandle.thread_wait = 1 * HZ;