cpuset: Don't use the cpu_possible_mask as a last resort for cgroup v1

If the scheduler cannot find an allowed CPU for a task,
cpuset_cpus_allowed_fallback() will widen the affinity to cpu_possible_mask
if cgroup v1 is in use.

In preparation for allowing architectures to provide their own fallback
mask, just return early if we're either using cgroup v1 or we're using
cgroup v2 with a mask that contains invalid CPUs. This will allow
select_fallback_rq() to figure out the mask by itself.
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Quentin Perret <qperret@google.com>
Link: https://lkml.kernel.org/r/20210730112443.23245-3-will@kernel.org

include/linux/cpuset.h

@@ -15,6 +15,7 @@
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/mm.h>
+#include <linux/mmu_context.h>
 #include <linux/jump_label.h>
 
 #ifdef CONFIG_CPUSETS

kernel/cgroup/cpuset.c

@@ -3322,9 +3322,13 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 
 void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
+	const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+	const struct cpumask *cs_mask;
+
 	rcu_read_lock();
-	do_set_cpus_allowed(tsk, is_in_v2_mode() ?
-		task_cs(tsk)->cpus_allowed : cpu_possible_mask);
+	cs_mask = task_cs(tsk)->cpus_allowed;
+	if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask))
+		do_set_cpus_allowed(tsk, cs_mask);
 	rcu_read_unlock();
 
 	/*