cpuset: Honour task_cpu_possible_mask() in guarantee_online_cpus()

Asymmetric systems may not offer the same level of userspace ISA support
across all CPUs, meaning that some applications cannot be executed by
some CPUs. As a concrete example, upcoming arm64 big.LITTLE designs do
not feature support for 32-bit applications on both clusters.

Modify guarantee_online_cpus() to take task_cpu_possible_mask() into
account when trying to find a suitable set of online CPUs for a given
task. This will avoid passing an invalid mask to set_cpus_allowed_ptr()
during ->attach() and will subsequently allow the cpuset hierarchy to be
taken into account when forcefully overriding the affinity mask for a
task which requires migration to a compatible CPU.

Signed-off-by: Will Deacon <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Valentin Schneider <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

include/linux/cpuset.h

@@ -185,7 +185,7 @@ static inline void cpuset_read_unlock(void) { }
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
 {
-	cpumask_copy(mask, cpu_possible_mask);
+	cpumask_copy(mask, task_cpu_possible_mask(p));
 }
 
 static inline void cpuset_cpus_allowed_fallback(struct task_struct *p)

kernel/cgroup/cpuset.c

@@ -372,18 +372,29 @@ static inline bool is_in_v2_mode(void)
 }
 
 /*
- * Return in pmask the portion of a cpusets's cpus_allowed that
- * are online.  If none are online, walk up the cpuset hierarchy
- * until we find one that does have some online cpus.
+ * Return in pmask the portion of a task's cpusets's cpus_allowed that
+ * are online and are capable of running the task.  If none are found,
+ * walk up the cpuset hierarchy until we find one that does have some
+ * appropriate cpus.
  *
  * One way or another, we guarantee to return some non-empty subset
  * of cpu_online_mask.
  *
  * Call with callback_lock or cpuset_mutex held.
  */
-static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
+static void guarantee_online_cpus(struct task_struct *tsk,
+				  struct cpumask *pmask)
 {
-	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) {
+	const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+	struct cpuset *cs;
+
+	if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask)))
+		cpumask_copy(pmask, cpu_online_mask);
+
+	rcu_read_lock();
+	cs = task_cs(tsk);
+
+	while (!cpumask_intersects(cs->effective_cpus, pmask)) {
 		cs = parent_cs(cs);
 		if (unlikely(!cs)) {
 			/*
@@ -393,11 +404,13 @@ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
 			 * cpuset's effective_cpus is on its way to be
 			 * identical to cpu_online_mask.
 			 */
-			cpumask_copy(pmask, cpu_online_mask);
-			return;
+			goto out_unlock;
 		}
 	}
-	cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
+	cpumask_and(pmask, pmask, cs->effective_cpus);
+
+out_unlock:
+	rcu_read_unlock();
 }
 
 /*
@@ -2199,15 +2212,13 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 
 	percpu_down_write(&cpuset_rwsem);
 
-	/* prepare for attach */
-	if (cs == &top_cpuset)
-		cpumask_copy(cpus_attach, cpu_possible_mask);
-	else
-		guarantee_online_cpus(cs, cpus_attach);
-
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 
 	cgroup_taskset_for_each(task, css, tset) {
+		if (cs != &top_cpuset)
+			guarantee_online_cpus(task, cpus_attach);
+		else
+			cpumask_copy(cpus_attach, task_cpu_possible_mask(task));
 		/*
 		 * can_attach beforehand should guarantee that this doesn't
 		 * fail.  TODO: have a better way to handle failure here
@@ -3302,9 +3313,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 	unsigned long flags;
 
 	spin_lock_irqsave(&callback_lock, flags);
-	rcu_read_lock();
-	guarantee_online_cpus(task_cs(tsk), pmask);
-	rcu_read_unlock();
+	guarantee_online_cpus(tsk, pmask);
 	spin_unlock_irqrestore(&callback_lock, flags);
 }