Merge tag 'cgroup-for-6.2-rc7-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:
 "During the v6.2 cycle, there were a series of changes to task cpu
  affinity handling which fixed cpuset inadvertently clobbering
  user-configured affinity masks. Unfortunately, they broke the affinity
  handling on hybrid heterogeneous CPUs which have cores that can
  execute both 64 and 32bit along with cores that can only execute 32bit
  code.

  This contains two fix patches for the above issue. While reverting the
  changes that caused the regression is definitely an option, the
  origial patches do improve how cpuset behave signficantly in some
  cases and the fixes seem fairly safe, so I think it'd be better to try
  to fix them first"

* tag 'cgroup-for-6.2-rc7-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cpuset: Call set_cpus_allowed_ptr() with appropriate mask for task
  cgroup/cpuset: Don't filter offline CPUs in cpuset_cpus_allowed() for top cpuset tasks

kernel/cgroup/cpuset.c

@@ -1205,12 +1205,13 @@ void rebuild_sched_domains(void)
 /**
  * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
+ * @new_cpus: the temp variable for the new effective_cpus mask
  *
  * Iterate through each task of @cs updating its cpus_allowed to the
  * effective cpuset's.  As this function is called with cpuset_rwsem held,
  * cpuset membership stays stable.
  */
-static void update_tasks_cpumask(struct cpuset *cs)
+static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 {
 	struct css_task_iter it;
 	struct task_struct *task;
@@ -1224,7 +1225,10 @@ static void update_tasks_cpumask(struct cpuset *cs)
 		if (top_cs && (task->flags & PF_KTHREAD) &&
 		    kthread_is_per_cpu(task))
 			continue;
-		set_cpus_allowed_ptr(task, cs->effective_cpus);
+
+		cpumask_and(new_cpus, cs->effective_cpus,
+			    task_cpu_possible_mask(task));
+		set_cpus_allowed_ptr(task, new_cpus);
 	}
 	css_task_iter_end(&it);
 }
@@ -1509,7 +1513,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
 	spin_unlock_irq(&callback_lock);
 
 	if (adding || deleting)
-		update_tasks_cpumask(parent);
+		update_tasks_cpumask(parent, tmp->new_cpus);
 
 	/*
 	 * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary.
@@ -1661,7 +1665,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
 		WARN_ON(!is_in_v2_mode() &&
 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
 
-		update_tasks_cpumask(cp);
+		update_tasks_cpumask(cp, tmp->new_cpus);
 
 		/*
 		 * On legacy hierarchy, if the effective cpumask of any non-
@@ -2309,7 +2313,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		}
 	}
 
-	update_tasks_cpumask(parent);
+	update_tasks_cpumask(parent, tmpmask.new_cpus);
 
 	if (parent->child_ecpus_count)
 		update_sibling_cpumasks(parent, cs, &tmpmask);
@@ -3348,7 +3352,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
 	 * as the tasks will be migrated to an ancestor.
 	 */
 	if (cpus_updated && !cpumask_empty(cs->cpus_allowed))
-		update_tasks_cpumask(cs);
+		update_tasks_cpumask(cs, new_cpus);
 	if (mems_updated && !nodes_empty(cs->mems_allowed))
 		update_tasks_nodemask(cs);
 
@@ -3385,7 +3389,7 @@ hotplug_update_tasks(struct cpuset *cs,
 	spin_unlock_irq(&callback_lock);
 
 	if (cpus_updated)
-		update_tasks_cpumask(cs);
+		update_tasks_cpumask(cs, new_cpus);
 	if (mems_updated)
 		update_tasks_nodemask(cs);
 }
@@ -3692,15 +3696,38 @@ void __init cpuset_init_smp(void)
  * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
  * attached to the specified @tsk.  Guaranteed to return some non-empty
  * subset of cpu_online_mask, even if this means going outside the
- * tasks cpuset.
+ * tasks cpuset, except when the task is in the top cpuset.
  **/
 
 void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
 	unsigned long flags;
+	struct cpuset *cs;
 
 	spin_lock_irqsave(&callback_lock, flags);
-	guarantee_online_cpus(tsk, pmask);
+	rcu_read_lock();
+
+	cs = task_cs(tsk);
+	if (cs != &top_cpuset)
+		guarantee_online_cpus(tsk, pmask);
+	/*
+	 * Tasks in the top cpuset won't get update to their cpumasks
+	 * when a hotplug online/offline event happens. So we include all
+	 * offline cpus in the allowed cpu list.
+	 */
+	if ((cs == &top_cpuset) || cpumask_empty(pmask)) {
+		const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+
+		/*
+		 * We first exclude cpus allocated to partitions. If there is no
+		 * allowable online cpu left, we fall back to all possible cpus.
+		 */
+		cpumask_andnot(pmask, possible_mask, top_cpuset.subparts_cpus);
+		if (!cpumask_intersects(pmask, cpu_online_mask))
+			cpumask_copy(pmask, possible_mask);
+	}
+
+	rcu_read_unlock();
 	spin_unlock_irqrestore(&callback_lock, flags);
 }