Revert "cpuset: Make cpuset hotplug synchronous"

This reverts commit a49e4629 ("cpuset: Make cpuset hotplug synchronous") as
it may deadlock with cpu hotplug path.

Link: http://lkml.kernel.org/r/F0388D99-84D7-453B-9B6B-EEFF0E7BE4CC@lca.pwSigned-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Qian Cai <cai@lca.pw>
Cc: Prateek Sood <prsood@codeaurora.org>

include/linux/cpuset.h

@@ -54,6 +54,7 @@ extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
 extern void cpuset_force_rebuild(void);
 extern void cpuset_update_active_cpus(void);
+extern void cpuset_wait_for_hotplug(void);
 extern void cpuset_read_lock(void);
 extern void cpuset_read_unlock(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
@@ -175,6 +176,8 @@ static inline void cpuset_update_active_cpus(void)
 	partition_sched_domains(1, NULL, NULL);
 }
 
+static inline void cpuset_wait_for_hotplug(void) { }
+
 static inline void cpuset_read_lock(void) { }
 static inline void cpuset_read_unlock(void) { }
 

kernel/cgroup/cpuset.c

@@ -3101,7 +3101,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 }
 
 /**
- * cpuset_hotplug - handle CPU/memory hotunplug for a cpuset
+ * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset
  *
  * This function is called after either CPU or memory configuration has
  * changed and updates cpuset accordingly.  The top_cpuset is always
@@ -3116,7 +3116,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
  * Note that CPU offlining during suspend is ignored.  We don't modify
  * cpusets across suspend/resume cycles at all.
  */
-static void cpuset_hotplug(bool use_cpu_hp_lock)
+static void cpuset_hotplug_workfn(struct work_struct *work)
 {
 	static cpumask_t new_cpus;
 	static nodemask_t new_mems;
@@ -3201,32 +3201,25 @@ static void cpuset_hotplug(bool use_cpu_hp_lock)
 	/* rebuild sched domains if cpus_allowed has changed */
 	if (cpus_updated || force_rebuild) {
 		force_rebuild = false;
-		if (use_cpu_hp_lock)
-			rebuild_sched_domains();
-		else {
-			/* Acquiring cpu_hotplug_lock is not required.
-			 * When cpuset_hotplug() is called in hotplug path,
-			 * cpu_hotplug_lock is held by the hotplug context
-			 * which is waiting for cpuhp_thread_fun to indicate
-			 * completion of callback.
-			*/
-			percpu_down_write(&cpuset_rwsem);
-			rebuild_sched_domains_locked();
-			percpu_up_write(&cpuset_rwsem);
-		}
+		rebuild_sched_domains();
 	}
 
 	free_cpumasks(NULL, ptmp);
 }
 
-static void cpuset_hotplug_workfn(struct work_struct *work)
+void cpuset_update_active_cpus(void)
 {
-	cpuset_hotplug(true);
+	/*
+	 * We're inside cpu hotplug critical region which usually nests
+	 * inside cgroup synchronization.  Bounce actual hotplug processing
+	 * to a work item to avoid reverse locking order.
+	 */
+	schedule_work(&cpuset_hotplug_work);
 }
 
-void cpuset_update_active_cpus(void)
+void cpuset_wait_for_hotplug(void)
 {
-	cpuset_hotplug(false);
+	flush_work(&cpuset_hotplug_work);
 }
 
 /*

kernel/power/process.c

@@ -204,6 +204,8 @@ void thaw_processes(void)
 	__usermodehelper_set_disable_depth(UMH_FREEZING);
 	thaw_workqueues();
 
+	cpuset_wait_for_hotplug();
+
 	read_lock(&tasklist_lock);
 	for_each_process_thread(g, p) {
 		/* No other threads should have PF_SUSPEND_TASK set */