diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0280dea..bc2e09a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * kernel/workqueue.c - generic async execution with shared worker pool
  *
@@ -127,16 +128,16 @@
  *
  * PL: wq_pool_mutex protected.
  *
- * PR: wq_pool_mutex protected for writes.  Sched-RCU protected for reads.
+ * PR: wq_pool_mutex protected for writes.  RCU protected for reads.
  *
  * PW: wq_pool_mutex and wq->mutex protected for writes.  Either for reads.
  *
  * PWR: wq_pool_mutex and wq->mutex protected for writes.  Either or
- *      sched-RCU for reads.
+ *      RCU for reads.
  *
  * WQ: wq->mutex protected.
  *
- * WR: wq->mutex protected for writes.  Sched-RCU protected for reads.
+ * WR: wq->mutex protected for writes.  RCU protected for reads.
  *
  * MD: wq_mayday_lock protected.
  */
@@ -183,7 +184,7 @@
 	atomic_t		nr_running ____cacheline_aligned_in_smp;
 
 	/*
-	 * Destruction of pool is sched-RCU protected to allow dereferences
+	 * Destruction of pool is RCU protected to allow dereferences
 	 * from get_work_pool().
 	 */
 	struct rcu_head		rcu;
@@ -212,7 +213,7 @@
 	/*
 	 * Release of unbound pwq is punted to system_wq.  See put_pwq()
 	 * and pwq_unbound_release_workfn() for details.  pool_workqueue
-	 * itself is also sched-RCU protected so that the first pwq can be
+	 * itself is also RCU protected so that the first pwq can be
 	 * determined without grabbing wq->mutex.
 	 */
 	struct work_struct	unbound_release_work;
@@ -259,13 +260,15 @@
 	struct wq_device	*wq_dev;	/* I: for sysfs interface */
 #endif
 #ifdef CONFIG_LOCKDEP
+	char			*lock_name;
+	struct lock_class_key	key;
 	struct lockdep_map	lockdep_map;
 #endif
 	char			name[WQ_NAME_LEN]; /* I: workqueue name */
 
 	/*
-	 * Destruction of workqueue_struct is sched-RCU protected to allow
-	 * walking the workqueues list without grabbing wq_pool_mutex.
+	 * Destruction of workqueue_struct is RCU protected to allow walking
+	 * the workqueues list without grabbing wq_pool_mutex.
 	 * This is used to dump all workqueues from sysrq.
 	 */
 	struct rcu_head		rcu;
@@ -357,20 +360,20 @@
 #include <trace/events/workqueue.h>
 
 #define assert_rcu_or_pool_mutex()					\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() &&			\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
 			 !lockdep_is_held(&wq_pool_mutex),		\
-			 "sched RCU or wq_pool_mutex should be held")
+			 "RCU or wq_pool_mutex should be held")
 
 #define assert_rcu_or_wq_mutex(wq)					\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() &&			\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
 			 !lockdep_is_held(&wq->mutex),			\
-			 "sched RCU or wq->mutex should be held")
+			 "RCU or wq->mutex should be held")
 
 #define assert_rcu_or_wq_mutex_or_pool_mutex(wq)			\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() &&			\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
 			 !lockdep_is_held(&wq->mutex) &&		\
 			 !lockdep_is_held(&wq_pool_mutex),		\
-			 "sched RCU, wq->mutex or wq_pool_mutex should be held")
+			 "RCU, wq->mutex or wq_pool_mutex should be held")
 
 #define for_each_cpu_worker_pool(pool, cpu)				\
 	for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0];		\
@@ -382,7 +385,7 @@
  * @pool: iteration cursor
  * @pi: integer used for iteration
  *
- * This must be called either with wq_pool_mutex held or sched RCU read
+ * This must be called either with wq_pool_mutex held or RCU read
  * locked.  If the pool needs to be used beyond the locking in effect, the
  * caller is responsible for guaranteeing that the pool stays online.
  *
@@ -414,7 +417,7 @@
  * @pwq: iteration cursor
  * @wq: the target workqueue
  *
- * This must be called either with wq->mutex held or sched RCU read locked.
+ * This must be called either with wq->mutex held or RCU read locked.
  * If the pwq needs to be used beyond the locking in effect, the caller is
  * responsible for guaranteeing that the pwq stays online.
  *
@@ -550,7 +553,7 @@
  * @wq: the target workqueue
  * @node: the node ID
  *
- * This must be called with any of wq_pool_mutex, wq->mutex or sched RCU
+ * This must be called with any of wq_pool_mutex, wq->mutex or RCU
  * read locked.
  * If the pwq needs to be used beyond the locking in effect, the caller is
  * responsible for guaranteeing that the pwq stays online.
@@ -646,7 +649,7 @@
 	 * The following mb guarantees that previous clear of a PENDING bit
 	 * will not be reordered with any speculative LOADS or STORES from
 	 * work->current_func, which is executed afterwards.  This possible
-	 * reordering can lead to a missed execution on attempt to qeueue
+	 * reordering can lead to a missed execution on attempt to queue
 	 * the same @work.  E.g. consider this case:
 	 *
 	 *   CPU#0                         CPU#1
@@ -694,8 +697,8 @@
  * @work: the work item of interest
  *
  * Pools are created and destroyed under wq_pool_mutex, and allows read
- * access under sched-RCU read lock.  As such, this function should be
- * called under wq_pool_mutex or with preemption disabled.
+ * access under RCU read lock.  As such, this function should be
+ * called under wq_pool_mutex or inside of a rcu_read_lock() region.
  *
  * All fields of the returned pool are accessible as long as the above
  * mentioned locking is in effect.  If the returned pool needs to be used
@@ -839,43 +842,32 @@
 }
 
 /**
- * wq_worker_waking_up - a worker is waking up
+ * wq_worker_running - a worker is running again
  * @task: task waking up
- * @cpu: CPU @task is waking up to
  *
- * This function is called during try_to_wake_up() when a worker is
- * being awoken.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
+ * This function is called when a worker returns from schedule()
  */
-void wq_worker_waking_up(struct task_struct *task, int cpu)
+void wq_worker_running(struct task_struct *task)
 {
 	struct worker *worker = kthread_data(task);
 
-	if (!(worker->flags & WORKER_NOT_RUNNING)) {
-		WARN_ON_ONCE(worker->pool->cpu != cpu);
+	if (!worker->sleeping)
+		return;
+	if (!(worker->flags & WORKER_NOT_RUNNING))
 		atomic_inc(&worker->pool->nr_running);
-	}
+	worker->sleeping = 0;
 }
 
 /**
  * wq_worker_sleeping - a worker is going to sleep
  * @task: task going to sleep
  *
- * This function is called during schedule() when a busy worker is
- * going to sleep.  Worker on the same cpu can be woken up by
- * returning pointer to its task.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
- *
- * Return:
- * Worker task on @cpu to wake up, %NULL if none.
+ * This function is called from schedule() when a busy worker is
+ * going to sleep.
  */
-struct task_struct *wq_worker_sleeping(struct task_struct *task)
+void wq_worker_sleeping(struct task_struct *task)
 {
-	struct worker *worker = kthread_data(task), *to_wakeup = NULL;
+	struct worker *next, *worker = kthread_data(task);
 	struct worker_pool *pool;
 
 	/*
@@ -884,13 +876,15 @@
 	 * checking NOT_RUNNING.
 	 */
 	if (worker->flags & WORKER_NOT_RUNNING)
-		return NULL;
+		return;
 
 	pool = worker->pool;
 
-	/* this can only happen on the local cpu */
-	if (WARN_ON_ONCE(pool->cpu != raw_smp_processor_id()))
-		return NULL;
+	if (WARN_ON_ONCE(worker->sleeping))
+		return;
+
+	worker->sleeping = 1;
+	spin_lock_irq(&pool->lock);
 
 	/*
 	 * The counterpart of the following dec_and_test, implied mb,
@@ -904,9 +898,43 @@
 	 * lock is safe.
 	 */
 	if (atomic_dec_and_test(&pool->nr_running) &&
-	    !list_empty(&pool->worklist))
-		to_wakeup = first_idle_worker(pool);
-	return to_wakeup ? to_wakeup->task : NULL;
+	    !list_empty(&pool->worklist)) {
+		next = first_idle_worker(pool);
+		if (next)
+			wake_up_process(next->task);
+	}
+	spin_unlock_irq(&pool->lock);
+}
+
+/**
+ * wq_worker_last_func - retrieve worker's last work function
+ * @task: Task to retrieve last work function of.
+ *
+ * Determine the last function a worker executed. This is called from
+ * the scheduler to get a worker's last known identity.
+ *
+ * CONTEXT:
+ * spin_lock_irq(rq->lock)
+ *
+ * This function is called during schedule() when a kworker is going
+ * to sleep. It's used by psi to identify aggregation workers during
+ * dequeuing, to allow periodic aggregation to shut-off when that
+ * worker is the last task in the system or cgroup to go to sleep.
+ *
+ * As this function doesn't involve any workqueue-related locking, it
+ * only returns stable values when called from inside the scheduler's
+ * queuing and dequeuing paths, when @task, which must be a kworker,
+ * is guaranteed to not be processing any works.
+ *
+ * Return:
+ * The last work function %current executed as a worker, NULL if it
+ * hasn't executed any work yet.
+ */
+work_func_t wq_worker_last_func(struct task_struct *task)
+{
+	struct worker *worker = kthread_data(task);
+
+	return worker->last_func;
 }
 
 /**
@@ -1100,7 +1128,7 @@
 {
 	if (pwq) {
 		/*
-		 * As both pwqs and pools are sched-RCU protected, the
+		 * As both pwqs and pools are RCU protected, the
 		 * following lock operations are safe.
 		 */
 		spin_lock_irq(&pwq->pool->lock);
@@ -1228,6 +1256,7 @@
 	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)))
 		return 0;
 
+	rcu_read_lock();
 	/*
 	 * The queueing is in progress, or it is already queued. Try to
 	 * steal it from ->worklist without clearing WORK_STRUCT_PENDING.
@@ -1266,10 +1295,12 @@
 		set_work_pool_and_keep_pending(work, pool->id);
 
 		spin_unlock(&pool->lock);
+		rcu_read_unlock();
 		return 1;
 	}
 	spin_unlock(&pool->lock);
 fail:
+	rcu_read_unlock();
 	local_irq_restore(*flags);
 	if (work_is_canceling(work))
 		return -ENOENT;
@@ -1321,7 +1352,7 @@
 
 	worker = current_wq_worker();
 	/*
-	 * Return %true iff I'm a worker execuing a work item on @wq.  If
+	 * Return %true iff I'm a worker executing a work item on @wq.  If
 	 * I'm @worker, it's safe to dereference it without locking.
 	 */
 	return worker && worker->current_pwq->wq == wq;
@@ -1383,6 +1414,7 @@
 	if (unlikely(wq->flags & __WQ_DRAINING) &&
 	    WARN_ON_ONCE(!is_chained_work(wq)))
 		return;
+	rcu_read_lock();
 retry:
 	if (req_cpu == WORK_CPU_UNBOUND)
 		cpu = wq_select_unbound_cpu(raw_smp_processor_id());
@@ -1439,10 +1471,8 @@
 	/* pwq determined, queue */
 	trace_workqueue_queue_work(req_cpu, pwq, work);
 
-	if (WARN_ON(!list_empty(&work->entry))) {
-		spin_unlock(&pwq->pool->lock);
-		return;
-	}
+	if (WARN_ON(!list_empty(&work->entry)))
+		goto out;
 
 	pwq->nr_in_flight[pwq->work_color]++;
 	work_flags = work_color_to_flags(pwq->work_color);
@@ -1460,7 +1490,9 @@
 
 	insert_work(pwq, work, worklist, work_flags);
 
+out:
 	spin_unlock(&pwq->pool->lock);
+	rcu_read_unlock();
 }
 
 /**
@@ -1492,6 +1524,90 @@
 }
 EXPORT_SYMBOL(queue_work_on);
 
+/**
+ * workqueue_select_cpu_near - Select a CPU based on NUMA node
+ * @node: NUMA node ID that we want to select a CPU from
+ *
+ * This function will attempt to find a "random" cpu available on a given
+ * node. If there are no CPUs available on the given node it will return
+ * WORK_CPU_UNBOUND indicating that we should just schedule to any
+ * available CPU if we need to schedule this work.
+ */
+static int workqueue_select_cpu_near(int node)
+{
+	int cpu;
+
+	/* No point in doing this if NUMA isn't enabled for workqueues */
+	if (!wq_numa_enabled)
+		return WORK_CPU_UNBOUND;
+
+	/* Delay binding to CPU if node is not valid or online */
+	if (node < 0 || node >= MAX_NUMNODES || !node_online(node))
+		return WORK_CPU_UNBOUND;
+
+	/* Use local node/cpu if we are already there */
+	cpu = raw_smp_processor_id();
+	if (node == cpu_to_node(cpu))
+		return cpu;
+
+	/* Use "random" otherwise know as "first" online CPU of node */
+	cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask);
+
+	/* If CPU is valid return that, otherwise just defer */
+	return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND;
+}
+
+/**
+ * queue_work_node - queue work on a "random" cpu for a given NUMA node
+ * @node: NUMA node that we are targeting the work for
+ * @wq: workqueue to use
+ * @work: work to queue
+ *
+ * We queue the work to a "random" CPU within a given NUMA node. The basic
+ * idea here is to provide a way to somehow associate work with a given
+ * NUMA node.
+ *
+ * This function will only make a best effort attempt at getting this onto
+ * the right NUMA node. If no node is requested or the requested node is
+ * offline then we just fall back to standard queue_work behavior.
+ *
+ * Currently the "random" CPU ends up being the first available CPU in the
+ * intersection of cpu_online_mask and the cpumask of the node, unless we
+ * are running on the node. In that case we just use the current CPU.
+ *
+ * Return: %false if @work was already on a queue, %true otherwise.
+ */
+bool queue_work_node(int node, struct workqueue_struct *wq,
+		     struct work_struct *work)
+{
+	unsigned long flags;
+	bool ret = false;
+
+	/*
+	 * This current implementation is specific to unbound workqueues.
+	 * Specifically we only return the first available CPU for a given
+	 * node instead of cycling through individual CPUs within the node.
+	 *
+	 * If this is used with a per-cpu workqueue then the logic in
+	 * workqueue_select_cpu_near would need to be updated to allow for
+	 * some round robin type logic.
+	 */
+	WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND));
+
+	local_irq_save(flags);
+
+	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
+		int cpu = workqueue_select_cpu_near(node);
+
+		__queue_work(cpu, wq, work);
+		ret = true;
+	}
+
+	local_irq_restore(flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(queue_work_node);
+
 void delayed_work_timer_fn(struct timer_list *t)
 {
 	struct delayed_work *dwork = from_timer(dwork, t, timer);
@@ -1619,7 +1735,7 @@
  *
  * Return: %false if @rwork was already pending, %true otherwise.  Note
  * that a full RCU grace period is guaranteed only after a %true return.
- * While @rwork is guarnateed to be executed after a %false return, the
+ * While @rwork is guaranteed to be executed after a %false return, the
  * execution may happen before a full RCU grace period has passed.
  */
 bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork)
@@ -2161,7 +2277,7 @@
 
 	if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
 		pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n"
-		       "     last function: %pf\n",
+		       "     last function: %ps\n",
 		       current->comm, preempt_count(), task_pid_nr(current),
 		       worker->current_func);
 		debug_show_held_locks(current);
@@ -2184,6 +2300,9 @@
 	if (unlikely(cpu_intensive))
 		worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
 
+	/* tag the worker for identification in schedule() */
+	worker->last_func = worker->current_func;
+
 	/* we're done with it, release */
 	hash_del(&worker->hentry);
 	worker->current_work = NULL;
@@ -2477,11 +2596,11 @@
 	worker = current_wq_worker();
 
 	WARN_ONCE(current->flags & PF_MEMALLOC,
-		  "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%pf",
+		  "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps",
 		  current->pid, current->comm, target_wq->name, target_func);
 	WARN_ONCE(worker && ((worker->current_pwq->wq->flags &
 			      (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM),
-		  "workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf",
+		  "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps",
 		  worker->current_pwq->wq->name, worker->current_func,
 		  target_wq->name, target_func);
 }
@@ -2855,14 +2974,14 @@
 
 	might_sleep();
 
-	local_irq_disable();
+	rcu_read_lock();
 	pool = get_work_pool(work);
 	if (!pool) {
-		local_irq_enable();
+		rcu_read_unlock();
 		return false;
 	}
 
-	spin_lock(&pool->lock);
+	spin_lock_irq(&pool->lock);
 	/* see the comment in try_to_grab_pending() with the same code */
 	pwq = get_work_pwq(work);
 	if (pwq) {
@@ -2894,10 +3013,11 @@
 		lock_map_acquire(&pwq->wq->lockdep_map);
 		lock_map_release(&pwq->wq->lockdep_map);
 	}
-
+	rcu_read_unlock();
 	return true;
 already_gone:
 	spin_unlock_irq(&pool->lock);
+	rcu_read_unlock();
 	return false;
 }
 
@@ -2908,6 +3028,9 @@
 	if (WARN_ON(!wq_online))
 		return false;
 
+	if (WARN_ON(!work->func))
+		return false;
+
 	if (!from_cancel) {
 		lock_map_acquire(&work->lockdep_map);
 		lock_map_release(&work->lockdep_map);
@@ -3216,21 +3339,20 @@
 
 /**
  * alloc_workqueue_attrs - allocate a workqueue_attrs
- * @gfp_mask: allocation mask to use
  *
  * Allocate a new workqueue_attrs, initialize with default settings and
  * return it.
  *
  * Return: The allocated new workqueue_attr on success. %NULL on failure.
  */
-struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask)
+struct workqueue_attrs *alloc_workqueue_attrs(void)
 {
 	struct workqueue_attrs *attrs;
 
-	attrs = kzalloc(sizeof(*attrs), gfp_mask);
+	attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
 	if (!attrs)
 		goto fail;
-	if (!alloc_cpumask_var(&attrs->cpumask, gfp_mask))
+	if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL))
 		goto fail;
 
 	cpumask_copy(attrs->cpumask, cpu_possible_mask);
@@ -3308,17 +3430,57 @@
 	pool->refcnt = 1;
 
 	/* shouldn't fail above this point */
-	pool->attrs = alloc_workqueue_attrs(GFP_KERNEL);
+	pool->attrs = alloc_workqueue_attrs();
 	if (!pool->attrs)
 		return -ENOMEM;
 	return 0;
 }
 
+#ifdef CONFIG_LOCKDEP
+static void wq_init_lockdep(struct workqueue_struct *wq)
+{
+	char *lock_name;
+
+	lockdep_register_key(&wq->key);
+	lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name);
+	if (!lock_name)
+		lock_name = wq->name;
+
+	wq->lock_name = lock_name;
+	lockdep_init_map(&wq->lockdep_map, lock_name, &wq->key, 0);
+}
+
+static void wq_unregister_lockdep(struct workqueue_struct *wq)
+{
+	lockdep_unregister_key(&wq->key);
+}
+
+static void wq_free_lockdep(struct workqueue_struct *wq)
+{
+	if (wq->lock_name != wq->name)
+		kfree(wq->lock_name);
+}
+#else
+static void wq_init_lockdep(struct workqueue_struct *wq)
+{
+}
+
+static void wq_unregister_lockdep(struct workqueue_struct *wq)
+{
+}
+
+static void wq_free_lockdep(struct workqueue_struct *wq)
+{
+}
+#endif
+
 static void rcu_free_wq(struct rcu_head *rcu)
 {
 	struct workqueue_struct *wq =
 		container_of(rcu, struct workqueue_struct, rcu);
 
+	wq_free_lockdep(wq);
+
 	if (!(wq->flags & WQ_UNBOUND))
 		free_percpu(wq->cpu_pwqs);
 	else
@@ -3341,7 +3503,7 @@
  * put_unbound_pool - put a worker_pool
  * @pool: worker_pool to put
  *
- * Put @pool.  If its refcnt reaches zero, it gets destroyed in sched-RCU
+ * Put @pool.  If its refcnt reaches zero, it gets destroyed in RCU
  * safe manner.  get_unbound_pool() calls this function on its failure path
  * and this function should be able to release pools which went through,
  * successfully or not, init_worker_pool().
@@ -3395,8 +3557,8 @@
 	del_timer_sync(&pool->idle_timer);
 	del_timer_sync(&pool->mayday_timer);
 
-	/* sched-RCU protected to allow dereferences from get_work_pool() */
-	call_rcu_sched(&pool->rcu, rcu_free_pool);
+	/* RCU protected to allow dereferences from get_work_pool() */
+	call_rcu(&pool->rcu, rcu_free_pool);
 }
 
 /**
@@ -3503,14 +3665,16 @@
 	put_unbound_pool(pool);
 	mutex_unlock(&wq_pool_mutex);
 
-	call_rcu_sched(&pwq->rcu, rcu_free_pwq);
+	call_rcu(&pwq->rcu, rcu_free_pwq);
 
 	/*
 	 * If we're the last pwq going away, @wq is already dead and no one
 	 * is gonna access it anymore.  Schedule RCU free.
 	 */
-	if (is_last)
-		call_rcu_sched(&wq->rcu, rcu_free_wq);
+	if (is_last) {
+		wq_unregister_lockdep(wq);
+		call_rcu(&wq->rcu, rcu_free_wq);
+	}
 }
 
 /**
@@ -3731,8 +3895,8 @@
 
 	ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_node_ids), GFP_KERNEL);
 
-	new_attrs = alloc_workqueue_attrs(GFP_KERNEL);
-	tmp_attrs = alloc_workqueue_attrs(GFP_KERNEL);
+	new_attrs = alloc_workqueue_attrs();
+	tmp_attrs = alloc_workqueue_attrs();
 	if (!ctx || !new_attrs || !tmp_attrs)
 		goto out_free;
 
@@ -3866,6 +4030,8 @@
  *
  * Performs GFP_KERNEL allocations.
  *
+ * Assumes caller has CPU hotplug read exclusion, i.e. get_online_cpus().
+ *
  * Return: 0 on success and -errno on failure.
  */
 int apply_workqueue_attrs(struct workqueue_struct *wq,
@@ -3873,13 +4039,14 @@
 {
 	int ret;
 
-	apply_wqattrs_lock();
+	lockdep_assert_cpus_held();
+
+	mutex_lock(&wq_pool_mutex);
 	ret = apply_workqueue_attrs_locked(wq, attrs);
-	apply_wqattrs_unlock();
+	mutex_unlock(&wq_pool_mutex);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(apply_workqueue_attrs);
 
 /**
  * wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug
@@ -3989,16 +4156,21 @@
 			mutex_unlock(&wq->mutex);
 		}
 		return 0;
-	} else if (wq->flags & __WQ_ORDERED) {
+	}
+
+	get_online_cpus();
+	if (wq->flags & __WQ_ORDERED) {
 		ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
 		/* there should only be single pwq for ordering guarantee */
 		WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
 			      wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
 		     "ordering guarantee broken for workqueue %s\n", wq->name);
-		return ret;
 	} else {
-		return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
+		ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
 	}
+	put_online_cpus();
+
+	return ret;
 }
 
 static int wq_clamp_max_active(int max_active, unsigned int flags,
@@ -4044,11 +4216,10 @@
 	return 0;
 }
 
-struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
-					       unsigned int flags,
-					       int max_active,
-					       struct lock_class_key *key,
-					       const char *lock_name, ...)
+__printf(1, 4)
+struct workqueue_struct *alloc_workqueue(const char *fmt,
+					 unsigned int flags,
+					 int max_active, ...)
 {
 	size_t tbl_size = 0;
 	va_list args;
@@ -4078,12 +4249,12 @@
 		return NULL;
 
 	if (flags & WQ_UNBOUND) {
-		wq->unbound_attrs = alloc_workqueue_attrs(GFP_KERNEL);
+		wq->unbound_attrs = alloc_workqueue_attrs();
 		if (!wq->unbound_attrs)
 			goto err_free_wq;
 	}
 
-	va_start(args, lock_name);
+	va_start(args, max_active);
 	vsnprintf(wq->name, sizeof(wq->name), fmt, args);
 	va_end(args);
 
@@ -4100,11 +4271,11 @@
 	INIT_LIST_HEAD(&wq->flusher_overflow);
 	INIT_LIST_HEAD(&wq->maydays);
 
-	lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
+	wq_init_lockdep(wq);
 	INIT_LIST_HEAD(&wq->list);
 
 	if (alloc_and_link_pwqs(wq) < 0)
-		goto err_free_wq;
+		goto err_unreg_lockdep;
 
 	if (wq_online && init_rescuer(wq) < 0)
 		goto err_destroy;
@@ -4130,6 +4301,9 @@
 
 	return wq;
 
+err_unreg_lockdep:
+	wq_unregister_lockdep(wq);
+	wq_free_lockdep(wq);
 err_free_wq:
 	free_workqueue_attrs(wq->unbound_attrs);
 	kfree(wq);
@@ -4138,7 +4312,7 @@
 	destroy_workqueue(wq);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(__alloc_workqueue_key);
+EXPORT_SYMBOL_GPL(alloc_workqueue);
 
 /**
  * destroy_workqueue - safely terminate a workqueue
@@ -4191,11 +4365,12 @@
 		kthread_stop(wq->rescuer->task);
 
 	if (!(wq->flags & WQ_UNBOUND)) {
+		wq_unregister_lockdep(wq);
 		/*
 		 * The base ref is never dropped on per-cpu pwqs.  Directly
 		 * schedule RCU free.
 		 */
-		call_rcu_sched(&wq->rcu, rcu_free_wq);
+		call_rcu(&wq->rcu, rcu_free_wq);
 	} else {
 		/*
 		 * We're the sole accessor of @wq at this point.  Directly
@@ -4305,7 +4480,8 @@
 	struct pool_workqueue *pwq;
 	bool ret;
 
-	rcu_read_lock_sched();
+	rcu_read_lock();
+	preempt_disable();
 
 	if (cpu == WORK_CPU_UNBOUND)
 		cpu = smp_processor_id();
@@ -4316,7 +4492,8 @@
 		pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
 
 	ret = !list_empty(&pwq->delayed_works);
-	rcu_read_unlock_sched();
+	preempt_enable();
+	rcu_read_unlock();
 
 	return ret;
 }
@@ -4342,15 +4519,15 @@
 	if (work_pending(work))
 		ret |= WORK_BUSY_PENDING;
 
-	local_irq_save(flags);
+	rcu_read_lock();
 	pool = get_work_pool(work);
 	if (pool) {
-		spin_lock(&pool->lock);
+		spin_lock_irqsave(&pool->lock, flags);
 		if (find_worker_executing_work(pool, work))
 			ret |= WORK_BUSY_RUNNING;
-		spin_unlock(&pool->lock);
+		spin_unlock_irqrestore(&pool->lock, flags);
 	}
-	local_irq_restore(flags);
+	rcu_read_unlock();
 
 	return ret;
 }
@@ -4421,7 +4598,7 @@
 	probe_kernel_read(desc, worker->desc, sizeof(desc) - 1);
 
 	if (fn || name[0] || desc[0]) {
-		printk("%sWorkqueue: %s %pf", log_lvl, name, fn);
+		printk("%sWorkqueue: %s %ps", log_lvl, name, fn);
 		if (strcmp(name, desc))
 			pr_cont(" (%s)", desc);
 		pr_cont("\n");
@@ -4446,7 +4623,7 @@
 		pr_cont("%s BAR(%d)", comma ? "," : "",
 			task_pid_nr(barr->task));
 	} else {
-		pr_cont("%s %pf", comma ? "," : "", work->func);
+		pr_cont("%s %ps", comma ? "," : "", work->func);
 	}
 }
 
@@ -4478,7 +4655,7 @@
 			if (worker->current_pwq != pwq)
 				continue;
 
-			pr_cont("%s %d%s:%pf", comma ? "," : "",
+			pr_cont("%s %d%s:%ps", comma ? "," : "",
 				task_pid_nr(worker->task),
 				worker == pwq->wq->rescuer ? "(RESCUER)" : "",
 				worker->current_func);
@@ -4534,7 +4711,7 @@
 	unsigned long flags;
 	int pi;
 
-	rcu_read_lock_sched();
+	rcu_read_lock();
 
 	pr_info("Showing busy workqueues and worker pools:\n");
 
@@ -4599,7 +4776,7 @@
 		touch_nmi_watchdog();
 	}
 
-	rcu_read_unlock_sched();
+	rcu_read_unlock();
 }
 
 /* used to show worker information through /proc/PID/{comm,stat,status} */
@@ -4763,7 +4940,7 @@
 		 *
 		 * WRITE_ONCE() is necessary because @worker->flags may be
 		 * tested without holding any lock in
-		 * wq_worker_waking_up().  Without it, NOT_RUNNING test may
+		 * wq_worker_running().  Without it, NOT_RUNNING test may
 		 * fail incorrectly leading to premature concurrency
 		 * management operations.
 		 */
@@ -4986,16 +5163,16 @@
 		 * nr_active is monotonically decreasing.  It's safe
 		 * to peek without lock.
 		 */
-		rcu_read_lock_sched();
+		rcu_read_lock();
 		for_each_pwq(pwq, wq) {
 			WARN_ON_ONCE(pwq->nr_active < 0);
 			if (pwq->nr_active) {
 				busy = true;
-				rcu_read_unlock_sched();
+				rcu_read_unlock();
 				goto out_unlock;
 			}
 		}
-		rcu_read_unlock_sched();
+		rcu_read_unlock();
 	}
 out_unlock:
 	mutex_unlock(&wq_pool_mutex);
@@ -5190,7 +5367,8 @@
 	const char *delim = "";
 	int node, written = 0;
 
-	rcu_read_lock_sched();
+	get_online_cpus();
+	rcu_read_lock();
 	for_each_node(node) {
 		written += scnprintf(buf + written, PAGE_SIZE - written,
 				     "%s%d:%d", delim, node,
@@ -5198,7 +5376,8 @@
 		delim = " ";
 	}
 	written += scnprintf(buf + written, PAGE_SIZE - written, "\n");
-	rcu_read_unlock_sched();
+	rcu_read_unlock();
+	put_online_cpus();
 
 	return written;
 }
@@ -5223,7 +5402,7 @@
 
 	lockdep_assert_held(&wq_pool_mutex);
 
-	attrs = alloc_workqueue_attrs(GFP_KERNEL);
+	attrs = alloc_workqueue_attrs();
 	if (!attrs)
 		return NULL;
 
@@ -5645,7 +5824,7 @@
 		return;
 	}
 
-	wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(GFP_KERNEL);
+	wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs();
 	BUG_ON(!wq_update_unbound_numa_attrs_buf);
 
 	/*
@@ -5720,7 +5899,7 @@
 	for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
 		struct workqueue_attrs *attrs;
 
-		BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
+		BUG_ON(!(attrs = alloc_workqueue_attrs()));
 		attrs->nice = std_nice[i];
 		unbound_std_wq_attrs[i] = attrs;
 
@@ -5729,7 +5908,7 @@
 		 * guaranteed by max_active which is enforced by pwqs.
 		 * Turn off NUMA so that dfl_pwq is used for all nodes.
 		 */
-		BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
+		BUG_ON(!(attrs = alloc_workqueue_attrs()));
 		attrs->nice = std_nice[i];
 		attrs->no_numa = true;
 		ordered_wq_attrs[i] = attrs;