cgroup/cpuset: Make cpuset_fork() handle CLONE_INTO_CGROUP properly

By default, the clone(2) syscall spawn a child process into the same
cgroup as its parent. With the use of the CLONE_INTO_CGROUP flag
introduced by commit ef2c41cf ("clone3: allow spawning processes
into cgroups"), the child will be spawned into a different cgroup which
is somewhat similar to writing the child's tid into "cgroup.threads".

The current cpuset_fork() method does not properly handle the
CLONE_INTO_CGROUP case where the cpuset of the child may be different
from that of its parent.  Update the cpuset_fork() method to treat the
CLONE_INTO_CGROUP case similar to cpuset_attach().

Since the newly cloned task has not been running yet, its actual
memory usage isn't known. So it is not necessary to make change to mm
in cpuset_fork().

Fixes: ef2c41cf ("clone3: allow spawning processes into cgroups")
Reported-by: Giuseppe Scrivano <gscrivan@redhat.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Cc: stable@vger.kernel.org # v5.7+
Signed-off-by: Tejun Heo <tj@kernel.org>

kernel/cgroup/cpuset.c

@@ -2515,16 +2515,33 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset)
 }
 
 /*
- * Protected by cpuset_rwsem.  cpus_attach is used only by cpuset_attach()
+ * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach_task()
  * but we can't allocate it dynamically there.  Define it global and
  * allocate from cpuset_init().
  */
 static cpumask_var_t cpus_attach;
+static nodemask_t cpuset_attach_nodemask_to;
+
+static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task)
+{
+	percpu_rwsem_assert_held(&cpuset_rwsem);
+
+	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
+	 */
+	WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach));
+
+	cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to);
+	cpuset_update_task_spread_flags(cs, task);
+}
 
 static void cpuset_attach(struct cgroup_taskset *tset)
 {
-	/* static buf protected by cpuset_rwsem */
-	static nodemask_t cpuset_attach_nodemask_to;
 	struct task_struct *task;
 	struct task_struct *leader;
 	struct cgroup_subsys_state *css;
@@ -2555,20 +2572,8 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 
 	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
-		 */
-		WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach));
-
-		cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to);
-		cpuset_update_task_spread_flags(cs, task);
-	}
+	cgroup_taskset_for_each(task, css, tset)
+		cpuset_attach_task(cs, task);
 
 	/*
 	 * Change mm for all threadgroup leaders. This is expensive and may
@@ -3266,11 +3271,28 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
  */
 static void cpuset_fork(struct task_struct *task)
 {
-	if (task_css_is_root(task, cpuset_cgrp_id))
+	struct cpuset *cs;
+	bool same_cs;
+
+	rcu_read_lock();
+	cs = task_cs(task);
+	same_cs = (cs == task_cs(current));
+	rcu_read_unlock();
+
+	if (same_cs) {
+		if (cs == &top_cpuset)
+			return;
+
+		set_cpus_allowed_ptr(task, current->cpus_ptr);
+		task->mems_allowed = current->mems_allowed;
 		return;
+	}
 
-	set_cpus_allowed_ptr(task, current->cpus_ptr);
-	task->mems_allowed = current->mems_allowed;
+	/* CLONE_INTO_CGROUP */
+	percpu_down_write(&cpuset_rwsem);
+	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
+	cpuset_attach_task(cs, task);
+	percpu_up_write(&cpuset_rwsem);
 }
 
 struct cgroup_subsys cpuset_cgrp_subsys = {