1 files changed, 54 insertions, 25 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 28e52657e093..e90f37e22202 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -50,6 +50,7 @@
 #include <linux/uaccess.h>
 #include <linux/sched/isolation.h>
 #include <linux/nmi.h>
+#include <linux/kvm_para.h>
 
 #include "workqueue_internal.h"
 
@@ -854,8 +855,17 @@ void wq_worker_running(struct task_struct *task)
 
 	if (!worker->sleeping)
 		return;
+
+	/*
+	 * If preempted by unbind_workers() between the WORKER_NOT_RUNNING check
+	 * and the nr_running increment below, we may ruin the nr_running reset
+	 * and leave with an unexpected pool->nr_running == 1 on the newly unbound
+	 * pool. Protect against such race.
+	 */
+	preempt_disable();
 	if (!(worker->flags & WORKER_NOT_RUNNING))
 		atomic_inc(&worker->pool->nr_running);
+	preempt_enable();
 	worker->sleeping = 0;
 }
 
@@ -1411,7 +1421,6 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	 */
 	lockdep_assert_irqs_disabled();
 
-	debug_work_activate(work);
 
 	/* if draining, only works from the same workqueue are allowed */
 	if (unlikely(wq->flags & __WQ_DRAINING) &&
@@ -1493,6 +1502,7 @@ retry:
 		worklist = &pwq->delayed_works;
 	}
 
+	debug_work_activate(work);
 	insert_work(pwq, work, worklist, work_flags);
 
 out:
@@ -1848,12 +1858,6 @@ static void worker_attach_to_pool(struct worker *worker,
 	mutex_lock(&wq_pool_attach_mutex);
 
 	/*
-	 * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
-	 * online CPUs.  It'll be re-applied when any of the CPUs come up.
-	 */
-	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
-
-	/*
 	 * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains
 	 * stable across this function.  See the comments above the flag
 	 * definition for details.
@@ -1861,6 +1865,9 @@ static void worker_attach_to_pool(struct worker *worker,
 	if (pool->flags & POOL_DISASSOCIATED)
 		worker->flags |= WORKER_UNBOUND;
 
+	if (worker->rescue_wq)
+		set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
+
 	list_add_tail(&worker->node, &pool->workers);
 	worker->pool = pool;
 
@@ -3662,15 +3669,21 @@ static void pwq_unbound_release_workfn(struct work_struct *work)
 						  unbound_release_work);
 	struct workqueue_struct *wq = pwq->wq;
 	struct worker_pool *pool = pwq->pool;
-	bool is_last;
+	bool is_last = false;
 
-	if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
-		return;
+	/*
+	 * when @pwq is not linked, it doesn't hold any reference to the
+	 * @wq, and @wq is invalid to access.
+	 */
+	if (!list_empty(&pwq->pwqs_node)) {
+		if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
+			return;
 
-	mutex_lock(&wq->mutex);
-	list_del_rcu(&pwq->pwqs_node);
-	is_last = list_empty(&wq->pwqs);
-	mutex_unlock(&wq->mutex);
+		mutex_lock(&wq->mutex);
+		list_del_rcu(&pwq->pwqs_node);
+		is_last = list_empty(&wq->pwqs);
+		mutex_unlock(&wq->mutex);
+	}
 
 	mutex_lock(&wq_pool_mutex);
 	put_unbound_pool(pool);
@@ -5298,9 +5311,6 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
 	int ret = -EINVAL;
 	cpumask_var_t saved_cpumask;
 
-	if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL))
-		return -ENOMEM;
-
 	/*
 	 * Not excluding isolated cpus on purpose.
 	 * If the user wishes to include them, we allow that.
@@ -5308,6 +5318,15 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
 	cpumask_and(cpumask, cpumask, cpu_possible_mask);
 	if (!cpumask_empty(cpumask)) {
 		apply_wqattrs_lock();
+		if (cpumask_equal(cpumask, wq_unbound_cpumask)) {
+			ret = 0;
+			goto out_unlock;
+		}
+
+		if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL)) {
+			ret = -ENOMEM;
+			goto out_unlock;
+		}
 
 		/* save the old wq_unbound_cpumask. */
 		cpumask_copy(saved_cpumask, wq_unbound_cpumask);
@@ -5320,10 +5339,11 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
 		if (ret < 0)
 			cpumask_copy(wq_unbound_cpumask, saved_cpumask);
 
+		free_cpumask_var(saved_cpumask);
+out_unlock:
 		apply_wqattrs_unlock();
 	}
 
-	free_cpumask_var(saved_cpumask);
 	return ret;
 }
 
@@ -5737,6 +5757,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 {
 	unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ;
 	bool lockup_detected = false;
+	unsigned long now = jiffies;
 	struct worker_pool *pool;
 	int pi;
 
@@ -5751,6 +5772,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 		if (list_empty(&pool->worklist))
 			continue;
 
+		/*
+		 * If a virtual machine is stopped by the host it can look to
+		 * the watchdog like a stall.
+		 */
+		kvm_check_and_clear_guest_paused();
+
 		/* get the latest of pool and touched timestamps */
 		pool_ts = READ_ONCE(pool->watchdog_ts);
 		touched = READ_ONCE(wq_watchdog_touched);
@@ -5769,12 +5796,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 		}
 
 		/* did we stall? */
-		if (time_after(jiffies, ts + thresh)) {
+		if (time_after(now, ts + thresh)) {
 			lockup_detected = true;
 			pr_emerg("BUG: workqueue lockup - pool");
 			pr_cont_pool_info(pool);
 			pr_cont(" stuck for %us!\n",
-				jiffies_to_msecs(jiffies - pool_ts) / 1000);
+				jiffies_to_msecs(now - pool_ts) / 1000);
 		}
 	}
 
@@ -5858,6 +5885,13 @@ static void __init wq_numa_init(void)
 		return;
 	}
 
+	for_each_possible_cpu(cpu) {
+		if (WARN_ON(cpu_to_node(cpu) == NUMA_NO_NODE)) {
+			pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu);
+			return;
+		}
+	}
+
 	wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs();
 	BUG_ON(!wq_update_unbound_numa_attrs_buf);
 
@@ -5875,11 +5909,6 @@ static void __init wq_numa_init(void)
 
 	for_each_possible_cpu(cpu) {
 		node = cpu_to_node(cpu);
-		if (WARN_ON(node == NUMA_NO_NODE)) {
-			pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu);
-			/* happens iff arch is bonkers, let's just proceed */
-			return;
-		}
 		cpumask_set_cpu(cpu, tbl[node]);
 	}