Merge tag 'wq-for-6.9-rc6-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue fixes from Tejun Heo:
 "Two doc update patches and the following three fixes:

   - On single node systems, the default pool is used but the
     node_nr_active for the default pool was set to min_active. This
     effectively limited the max concurrency of unbound pools on single
     node systems to 8 causing performance regressions on some
     workloads. Fixed by setting the default pool's node_nr_active to
     max_active.

   - wq_update_node_max_active() could trigger divide-by-zero if the
     intersection between the allowed CPUs for an unbound workqueue and
     online CPUs becomes empty.

   - When kick_pool() was trying to repatriate a worker to a CPU in its
     pod by setting task->wake_cpu, it didn't consider whether the CPU
     being selected is online or not which obviously can lead to
     subobtimal behaviors. On s390, this triggered a crash in arch code.
     The workqueue patch removes the gross misbehavior but doesn't fix
     the crash completely as there's a race window in which CPUs can go
     down after wake_cpu is set. Need to decide whether the fix should
     be on the core or arch side"

* tag 'wq-for-6.9-rc6-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: Fix divide error in wq_update_node_max_active()
  workqueue: The default node_nr_active should have its max set to max_active
  workqueue: Fix selection of wake_cpu in kick_pool()
  docs/zh_CN: core-api: Update translation of workqueue.rst to 6.9-rc1
  Documentation/core-api: Update events_freezable_power references.

Documentation/core-api/workqueue.rst

@@ -671,7 +671,7 @@ configuration, worker pools and how workqueues map to the pools: ::
   events_unbound           unbound  9  9 10 10  8
   events_freezable         percpu   0  2  4  6
   events_power_efficient   percpu   0  2  4  6
-  events_freezable_power_  percpu   0  2  4  6
+  events_freezable_pwr_ef  percpu   0  2  4  6
   rcu_gp                   percpu   0  2  4  6
   rcu_par_gp               percpu   0  2  4  6
   slub_flushwq             percpu   0  2  4  6
@@ -694,7 +694,7 @@ Use tools/workqueue/wq_monitor.py to monitor workqueue operations: ::
   events_unbound              38306     0      0.1       -       7       -       -
   events_freezable                0     0      0.0       0       0       -       -
   events_power_efficient      29598     0      0.2       0       0       -       -
-  events_freezable_power_        10     0      0.0       0       0       -       -
+  events_freezable_pwr_ef        10     0      0.0       0       0       -       -
   sock_diag_events                0     0      0.0       0       0       -       -
 
                               total  infl  CPUtime  CPUhog CMW/RPR  mayday rescued
@@ -704,7 +704,7 @@ Use tools/workqueue/wq_monitor.py to monitor workqueue operations: ::
   events_unbound              38322     0      0.1       -       7       -       -
   events_freezable                0     0      0.0       0       0       -       -
   events_power_efficient      29603     0      0.2       0       0       -       -
-  events_freezable_power_        10     0      0.0       0       0       -       -
+  events_freezable_pwr_ef        10     0      0.0       0       0       -       -
   sock_diag_events                0     0      0.0       0       0       -       -
 
   ...

kernel/workqueue.c

@@ -1277,9 +1277,13 @@ static bool kick_pool(struct worker_pool *pool)
 	    !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) {
 		struct work_struct *work = list_first_entry(&pool->worklist,
 						struct work_struct, entry);
-		p->wake_cpu = cpumask_any_distribute(pool->attrs->__pod_cpumask);
+		int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask,
+							  cpu_online_mask);
+		if (wake_cpu < nr_cpu_ids) {
+			p->wake_cpu = wake_cpu;
 			get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++;
 		}
+	}
 #endif
 	wake_up_process(p);
 	return true;
@@ -1594,6 +1598,15 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu)
 	if (off_cpu >= 0)
 		total_cpus--;
 
+	/* If all CPUs of the wq get offline, use the default values */
+	if (unlikely(!total_cpus)) {
+		for_each_node(node)
+			wq_node_nr_active(wq, node)->max = min_active;
+
+		wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active;
+		return;
+	}
+
 	for_each_node(node) {
 		int node_cpus;
 
@@ -1606,7 +1619,7 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu)
 			      min_active, max_active);
 	}
 
-	wq_node_nr_active(wq, NUMA_NO_NODE)->max = min_active;
+	wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active;
 }
 
 /**