[PATCH-wq v3 2/4] workqueue: Thaw frozen pwq in workqueue_apply_unbound_cpumask()

[Waiman Long <longman@redhat.com>]

workqueue_apply_unbound_cpumask() cannot proceed with an ordered
workqueue if its dfl_pwq is still frozen. Just do a sleep wait for
it to be thawed may not work in some cases if pwq_release_workfn() is
somehow prevented from being called due to resources (e.g. wq_pool_mutex)
that are held by its caller.

To break the logjam, we have to actively check if the frozen dfl_pwq
is ready to be thawed and call thaw_pwq() directly if so.

Signed-off-by: Waiman Long <longman@redhat.com>
Tested-by: Juri Lelli <juri.lelli@redhat.com>
---
 kernel/workqueue.c | 31 +++++++++++++++++++++++++++++--
 1 file changed, 29 insertions(+), 2 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 9b107e8a2c15..f453f339f74a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -6541,6 +6541,33 @@ void thaw_workqueues(void)
 }
 #endif /* CONFIG_FREEZER */
 
+/*
+ * Check the given ordered workqueue to see if its non-default pwq's have
+ * zero reference count and if so thaw the frozen default pwq.
+ *
+ * Return:
+ * %true if dfl_pwq has been thawed or %false otherwise.
+ */
+static bool ordered_workqueue_ref_check(struct workqueue_struct *wq)
+{
+	struct pool_workqueue *dfl_pwq = rcu_access_pointer(wq->dfl_pwq);
+	struct pool_workqueue *pwq;
+	int refs = 0;
+
+	if (!READ_ONCE(dfl_pwq->frozen))
+		return true;
+	mutex_lock(&wq->mutex);
+	for_each_pwq(pwq, wq) {
+		if (pwq == dfl_pwq)
+			continue;
+		refs += pwq->refcnt;
+	}
+	if (!refs)
+		thaw_pwq(dfl_pwq);
+	mutex_unlock(&wq->mutex);
+	return !refs;
+}
+
 static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
 {
 	LIST_HEAD(ctxs);
@@ -6566,12 +6593,12 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
 			dfl_pwq = rcu_access_pointer(wq->dfl_pwq);
 			if (!(wq->flags & __WQ_ORDERED_EXPLICIT)) {
 				wq->flags &= ~__WQ_ORDERED;
-			} else if (dfl_pwq && dfl_pwq->frozen) {
+			} else if (dfl_pwq && !ordered_workqueue_ref_check(wq)) {
 				int i;
 
 				for (i = 0; i < 10; i++) {
 					msleep(10);
-					if (!dfl_pwq->frozen)
+					if (ordered_workqueue_ref_check(wq))
 						break;
 				}
 				if (WARN_ON_ONCE(dfl_pwq->frozen))
-- 
2.39.3