1 files changed, 61 insertions, 35 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ca937b0c3a96..a2dccfe1acec 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -21,7 +21,7 @@
  * pools for workqueues which are not bound to any specific CPU - the
  * number of these backing pools is dynamic.
  *
- * Please read Documentation/workqueue.txt for details.
+ * Please read Documentation/core-api/workqueue.rst for details.
  */
 
 #include <linux/export.h>
@@ -68,6 +68,7 @@ enum {
 	 * attach_mutex to avoid changing binding state while
 	 * worker_attach_to_pool() is in progress.
 	 */
+	POOL_MANAGER_ACTIVE	= 1 << 0,	/* being managed */
 	POOL_DISASSOCIATED	= 1 << 2,	/* cpu can't serve workers */
 
 	/* worker flags */
@@ -165,7 +166,6 @@ struct worker_pool {
 						/* L: hash of busy workers */
 
 	/* see manage_workers() for details on the two manager mutexes */
-	struct mutex		manager_arb;	/* manager arbitration */
 	struct worker		*manager;	/* L: purely informational */
 	struct mutex		attach_mutex;	/* attach/detach exclusion */
 	struct list_head	workers;	/* A: attached workers */
@@ -299,6 +299,7 @@ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf;
 
 static DEFINE_MUTEX(wq_pool_mutex);	/* protects pools and workqueues list */
 static DEFINE_SPINLOCK(wq_mayday_lock);	/* protects wq->maydays list */
+static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */
 
 static LIST_HEAD(workqueues);		/* PR: list of all workqueues */
 static bool workqueue_freezing;		/* PL: have wqs started freezing? */
@@ -801,7 +802,7 @@ static bool need_to_create_worker(struct worker_pool *pool)
 /* Do we have too many workers and should some go away? */
 static bool too_many_workers(struct worker_pool *pool)
 {
-	bool managing = mutex_is_locked(&pool->manager_arb);
+	bool managing = pool->flags & POOL_MANAGER_ACTIVE;
 	int nr_idle = pool->nr_idle + managing; /* manager is considered idle */
 	int nr_busy = pool->nr_workers - nr_idle;
 
@@ -1980,24 +1981,17 @@ static bool manage_workers(struct worker *worker)
 {
 	struct worker_pool *pool = worker->pool;
 
-	/*
-	 * Anyone who successfully grabs manager_arb wins the arbitration
-	 * and becomes the manager.  mutex_trylock() on pool->manager_arb
-	 * failure while holding pool->lock reliably indicates that someone
-	 * else is managing the pool and the worker which failed trylock
-	 * can proceed to executing work items.  This means that anyone
-	 * grabbing manager_arb is responsible for actually performing
-	 * manager duties.  If manager_arb is grabbed and released without
-	 * actual management, the pool may stall indefinitely.
-	 */
-	if (!mutex_trylock(&pool->manager_arb))
+	if (pool->flags & POOL_MANAGER_ACTIVE)
 		return false;
+
+	pool->flags |= POOL_MANAGER_ACTIVE;
 	pool->manager = worker;
 
 	maybe_create_worker(pool);
 
 	pool->manager = NULL;
-	mutex_unlock(&pool->manager_arb);
+	pool->flags &= ~POOL_MANAGER_ACTIVE;
+	wake_up(&wq_manager_wait);
 	return true;
 }
 
@@ -2091,8 +2085,30 @@ __acquires(&pool->lock)
 
 	spin_unlock_irq(&pool->lock);
 
-	lock_map_acquire_read(&pwq->wq->lockdep_map);
+	lock_map_acquire(&pwq->wq->lockdep_map);
 	lock_map_acquire(&lockdep_map);
+	/*
+	 * Strictly speaking we should mark the invariant state without holding
+	 * any locks, that is, before these two lock_map_acquire()'s.
+	 *
+	 * However, that would result in:
+	 *
+	 *   A(W1)
+	 *   WFC(C)
+	 *		A(W1)
+	 *		C(C)
+	 *
+	 * Which would create W1->C->W1 dependencies, even though there is no
+	 * actual deadlock possible. There are two solutions, using a
+	 * read-recursive acquire on the work(queue) 'locks', but this will then
+	 * hit the lockdep limitation on recursive locks, or simply discard
+	 * these locks.
+	 *
+	 * AFAICT there is no possible deadlock scenario between the
+	 * flush_work() and complete() primitives (except for single-threaded
+	 * workqueues), so hiding them isn't a problem.
+	 */
+	lockdep_invariant_state(true);
 	trace_workqueue_execute_start(work);
 	worker->current_func(work);
 	/*
@@ -2247,7 +2263,7 @@ sleep:
 	 * event.
 	 */
 	worker_enter_idle(worker);
-	__set_current_state(TASK_INTERRUPTIBLE);
+	__set_current_state(TASK_IDLE);
 	spin_unlock_irq(&pool->lock);
 	schedule();
 	goto woke_up;
@@ -2289,7 +2305,7 @@ static int rescuer_thread(void *__rescuer)
 	 */
 	rescuer->task->flags |= PF_WQ_WORKER;
 repeat:
-	set_current_state(TASK_INTERRUPTIBLE);
+	set_current_state(TASK_IDLE);
 
 	/*
 	 * By the time the rescuer is requested to stop, the workqueue
@@ -2474,7 +2490,16 @@ static void insert_wq_barrier(struct pool_workqueue *pwq,
 	 */
 	INIT_WORK_ONSTACK(&barr->work, wq_barrier_func);
 	__set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work));
-	init_completion(&barr->done);
+
+	/*
+	 * Explicitly init the crosslock for wq_barrier::done, make its lock
+	 * key a subkey of the corresponding work. As a result we won't
+	 * build a dependency between wq_barrier::done and unrelated work.
+	 */
+	lockdep_init_map_crosslock((struct lockdep_map *)&barr->done.map,
+				   "(complete)wq_barr::done",
+				   target->lockdep_map.key, 1);
+	__init_completion(&barr->done);
 	barr->task = current;
 
 	/*
@@ -2815,16 +2840,18 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
 	spin_unlock_irq(&pool->lock);
 
 	/*
-	 * If @max_active is 1 or rescuer is in use, flushing another work
-	 * item on the same workqueue may lead to deadlock.  Make sure the
-	 * flusher is not running on the same workqueue by verifying write
-	 * access.
+	 * Force a lock recursion deadlock when using flush_work() inside a
+	 * single-threaded or rescuer equipped workqueue.
+	 *
+	 * For single threaded workqueues the deadlock happens when the work
+	 * is after the work issuing the flush_work(). For rescuer equipped
+	 * workqueues the deadlock happens when the rescuer stalls, blocking
+	 * forward progress.
 	 */
-	if (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer)
+	if (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer) {
 		lock_map_acquire(&pwq->wq->lockdep_map);
-	else
-		lock_map_acquire_read(&pwq->wq->lockdep_map);
-	lock_map_release(&pwq->wq->lockdep_map);
+		lock_map_release(&pwq->wq->lockdep_map);
+	}
 
 	return true;
 already_gone:
@@ -3215,7 +3242,6 @@ static int init_worker_pool(struct worker_pool *pool)
 	setup_timer(&pool->mayday_timer, pool_mayday_timeout,
 		    (unsigned long)pool);
 
-	mutex_init(&pool->manager_arb);
 	mutex_init(&pool->attach_mutex);
 	INIT_LIST_HEAD(&pool->workers);
 
@@ -3285,13 +3311,15 @@ static void put_unbound_pool(struct worker_pool *pool)
 	hash_del(&pool->hash_node);
 
 	/*
-	 * Become the manager and destroy all workers.  Grabbing
-	 * manager_arb prevents @pool's workers from blocking on
-	 * attach_mutex.
+	 * Become the manager and destroy all workers.  This prevents
+	 * @pool's workers from blocking on attach_mutex.  We're the last
+	 * manager and @pool gets freed with the flag set.
 	 */
-	mutex_lock(&pool->manager_arb);
-
 	spin_lock_irq(&pool->lock);
+	wait_event_lock_irq(wq_manager_wait,
+			    !(pool->flags & POOL_MANAGER_ACTIVE), pool->lock);
+	pool->flags |= POOL_MANAGER_ACTIVE;
+
 	while ((worker = first_idle_worker(pool)))
 		destroy_worker(worker);
 	WARN_ON(pool->nr_workers || pool->nr_idle);
@@ -3305,8 +3333,6 @@ static void put_unbound_pool(struct worker_pool *pool)
 	if (pool->detach_completion)
 		wait_for_completion(pool->detach_completion);
 
-	mutex_unlock(&pool->manager_arb);
-
 	/* shut down the timers */
 	del_timer_sync(&pool->idle_timer);
 	del_timer_sync(&pool->mayday_timer);