Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index bc2e09a..885d479 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"
 
@@ -425,7 +426,8 @@
  * ignored.
  */
 #define for_each_pwq(pwq, wq)						\
-	list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node)		\
+	list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node,		\
+				lockdep_is_held(&wq->mutex))		\
 		if (({ assert_rcu_or_wq_mutex(wq); false; })) { }	\
 		else
 
@@ -863,7 +865,8 @@
  * @task: task going to sleep
  *
  * This function is called from schedule() when a busy worker is
- * going to sleep.
+ * going to sleep. Preemption needs to be disabled to protect ->sleeping
+ * assignment.
  */
 void wq_worker_sleeping(struct task_struct *task)
 {
@@ -880,7 +883,8 @@
 
 	pool = worker->pool;
 
-	if (WARN_ON_ONCE(worker->sleeping))
+	/* Return if preempted before wq_worker_running() was reached */
+	if (worker->sleeping)
 		return;
 
 	worker->sleeping = 1;
@@ -1408,7 +1412,6 @@
 	 */
 	lockdep_assert_irqs_disabled();
 
-	debug_work_activate(work);
 
 	/* if draining, only works from the same workqueue are allowed */
 	if (unlikely(wq->flags & __WQ_DRAINING) &&
@@ -1416,14 +1419,16 @@
 		return;
 	rcu_read_lock();
 retry:
-	if (req_cpu == WORK_CPU_UNBOUND)
-		cpu = wq_select_unbound_cpu(raw_smp_processor_id());
-
 	/* pwq which will be used unless @work is executing elsewhere */
-	if (!(wq->flags & WQ_UNBOUND))
-		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
-	else
+	if (wq->flags & WQ_UNBOUND) {
+		if (req_cpu == WORK_CPU_UNBOUND)
+			cpu = wq_select_unbound_cpu(raw_smp_processor_id());
 		pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu));
+	} else {
+		if (req_cpu == WORK_CPU_UNBOUND)
+			cpu = raw_smp_processor_id();
+		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
+	}
 
 	/*
 	 * If @work was previously on a different pool, it might still be
@@ -1488,6 +1493,7 @@
 		worklist = &pwq->delayed_works;
 	}
 
+	debug_work_activate(work);
 	insert_work(pwq, work, worklist, work_flags);
 
 out:
@@ -1843,12 +1849,6 @@
 	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.
@@ -1856,6 +1856,9 @@
 	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;
 
@@ -2532,8 +2535,14 @@
 			 */
 			if (need_to_create_worker(pool)) {
 				spin_lock(&wq_mayday_lock);
-				get_pwq(pwq);
-				list_move_tail(&pwq->mayday_node, &wq->maydays);
+				/*
+				 * Queue iff we aren't racing destruction
+				 * and somebody else hasn't queued it already.
+				 */
+				if (wq->rescuer && list_empty(&pwq->mayday_node)) {
+					get_pwq(pwq);
+					list_add_tail(&pwq->mayday_node, &wq->maydays);
+				}
 				spin_unlock(&wq_mayday_lock);
 			}
 		}
@@ -3651,15 +3660,21 @@
 						  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);
@@ -3707,17 +3722,24 @@
 	 * is updated and visible.
 	 */
 	if (!freezable || !workqueue_freezing) {
+		bool kick = false;
+
 		pwq->max_active = wq->saved_max_active;
 
 		while (!list_empty(&pwq->delayed_works) &&
-		       pwq->nr_active < pwq->max_active)
+		       pwq->nr_active < pwq->max_active) {
 			pwq_activate_first_delayed(pwq);
+			kick = true;
+		}
 
 		/*
 		 * Need to kick a worker after thawed or an unbound wq's
-		 * max_active is bumped.  It's a slow path.  Do it always.
+		 * max_active is bumped. In realtime scenarios, always kicking a
+		 * worker will cause interference on the isolated cpu cores, so
+		 * let's kick iff work items were activated.
 		 */
-		wake_up_worker(pwq->pool);
+		if (kick)
+			wake_up_worker(pwq->pool);
 	} else {
 		pwq->max_active = 0;
 	}
@@ -4325,9 +4347,29 @@
 	struct pool_workqueue *pwq;
 	int node;
 
+	/*
+	 * Remove it from sysfs first so that sanity check failure doesn't
+	 * lead to sysfs name conflicts.
+	 */
+	workqueue_sysfs_unregister(wq);
+
 	/* drain it before proceeding with destruction */
 	drain_workqueue(wq);
 
+	/* kill rescuer, if sanity checks fail, leave it w/o rescuer */
+	if (wq->rescuer) {
+		struct worker *rescuer = wq->rescuer;
+
+		/* this prevents new queueing */
+		spin_lock_irq(&wq_mayday_lock);
+		wq->rescuer = NULL;
+		spin_unlock_irq(&wq_mayday_lock);
+
+		/* rescuer will empty maydays list before exiting */
+		kthread_stop(rescuer->task);
+		kfree(rescuer);
+	}
+
 	/* sanity checks */
 	mutex_lock(&wq->mutex);
 	for_each_pwq(pwq, wq) {
@@ -4359,11 +4401,6 @@
 	list_del_rcu(&wq->list);
 	mutex_unlock(&wq_pool_mutex);
 
-	workqueue_sysfs_unregister(wq);
-
-	if (wq->rescuer)
-		kthread_stop(wq->rescuer->task);
-
 	if (!(wq->flags & WQ_UNBOUND)) {
 		wq_unregister_lockdep(wq);
 		/*
@@ -4638,7 +4675,8 @@
 	pr_info("  pwq %d:", pool->id);
 	pr_cont_pool_info(pool);
 
-	pr_cont(" active=%d/%d%s\n", pwq->nr_active, pwq->max_active,
+	pr_cont(" active=%d/%d refcnt=%d%s\n",
+		pwq->nr_active, pwq->max_active, pwq->refcnt,
 		!list_empty(&pwq->mayday_node) ? " MAYDAY" : "");
 
 	hash_for_each(pool->busy_hash, bkt, worker, hentry) {
@@ -5703,6 +5741,7 @@
 {
 	unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ;
 	bool lockup_detected = false;
+	unsigned long now = jiffies;
 	struct worker_pool *pool;
 	int pi;
 
@@ -5717,6 +5756,12 @@
 		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);
@@ -5735,12 +5780,12 @@
 		}
 
 		/* 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);
 		}
 	}
 
@@ -5824,6 +5869,13 @@
 		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);
 
@@ -5841,11 +5893,6 @@
 
 	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]);
 	}