cgroup: Fix threadgroup_rwsem <-> cpus_read_lock() deadlock

Bringing up a CPU may involve creating and destroying tasks which requires
read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside
cpus_read_lock(). However, cpuset's ->attach(), which may be called with
thredagroup_rwsem write-locked, also wants to disable CPU hotplug and
acquires cpus_read_lock(), leading to a deadlock.

Fix it by guaranteeing that ->attach() is always called with CPU hotplug
disabled and removing cpus_read_lock() call from cpuset_attach().

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-and-tested-by: Imran Khan <imran.f.khan@oracle.com>
Reported-and-tested-by: Xuewen Yan <xuewen.yan@unisoc.com>
Fixes: 05c7b7a92cc8 ("cgroup/cpuset: Fix a race between cpuset_attach() and cpu hotplug")
Cc: stable@vger.kernel.org # v5.17+

1 files changed, 54 insertions, 23 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index df7df5843b4f..e1387499b336 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2370,6 +2370,47 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 EXPORT_SYMBOL_GPL(task_cgroup_path);
 
 /**
+ * cgroup_attach_lock - Lock for ->attach()
+ * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem
+ *
+ * cgroup migration sometimes needs to stabilize threadgroups against forks and
+ * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach()
+ * implementations (e.g. cpuset), also need to disable CPU hotplug.
+ * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can
+ * lead to deadlocks.
+ *
+ * Bringing up a CPU may involve creating and destroying tasks which requires
+ * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside
+ * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while
+ * write-locking threadgroup_rwsem, the locking order is reversed and we end up
+ * waiting for an on-going CPU hotplug operation which in turn is waiting for
+ * the threadgroup_rwsem to be released to create new tasks. For more details:
+ *
+ *   http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu
+ *
+ * Resolve the situation by always acquiring cpus_read_lock() before optionally
+ * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that
+ * CPU hotplug is disabled on entry.
+ */
+static void cgroup_attach_lock(bool lock_threadgroup)
+{
+	cpus_read_lock();
+	if (lock_threadgroup)
+		percpu_down_write(&cgroup_threadgroup_rwsem);
+}
+
+/**
+ * cgroup_attach_unlock - Undo cgroup_attach_lock()
+ * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem
+ */
+static void cgroup_attach_unlock(bool lock_threadgroup)
+{
+	if (lock_threadgroup)
+		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cpus_read_unlock();
+}
+
+/**
  * cgroup_migrate_add_task - add a migration target task to a migration context
  * @task: target task
  * @mgctx: target migration context
@@ -2841,8 +2882,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
 }
 
 struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
-					     bool *locked)
-	__acquires(&cgroup_threadgroup_rwsem)
+					     bool *threadgroup_locked)
 {
 	struct task_struct *tsk;
 	pid_t pid;
@@ -2859,12 +2899,8 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
 	 * Therefore, we can skip the global lock.
 	 */
 	lockdep_assert_held(&cgroup_mutex);
-	if (pid || threadgroup) {
-		percpu_down_write(&cgroup_threadgroup_rwsem);
-		*locked = true;
-	} else {
-		*locked = false;
-	}
+	*threadgroup_locked = pid || threadgroup;
+	cgroup_attach_lock(*threadgroup_locked);
 
 	rcu_read_lock();
 	if (pid) {
@@ -2895,17 +2931,14 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
 	goto out_unlock_rcu;
 
 out_unlock_threadgroup:
-	if (*locked) {
-		percpu_up_write(&cgroup_threadgroup_rwsem);
-		*locked = false;
-	}
+	cgroup_attach_unlock(*threadgroup_locked);
+	*threadgroup_locked = false;
 out_unlock_rcu:
 	rcu_read_unlock();
 	return tsk;
 }
 
-void cgroup_procs_write_finish(struct task_struct *task, bool locked)
-	__releases(&cgroup_threadgroup_rwsem)
+void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked)
 {
 	struct cgroup_subsys *ss;
 	int ssid;
@@ -2913,8 +2946,8 @@ void cgroup_procs_write_finish(struct task_struct *task, bool locked)
 	/* release reference from cgroup_procs_write_start() */
 	put_task_struct(task);
 
-	if (locked)
-		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(threadgroup_locked);
+
 	for_each_subsys(ss, ssid)
 		if (ss->post_attach)
 			ss->post_attach();
@@ -3000,8 +3033,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	 * write-locking can be skipped safely.
 	 */
 	has_tasks = !list_empty(&mgctx.preloaded_src_csets);
-	if (has_tasks)
-		percpu_down_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_lock(has_tasks);
 
 	/* NULL dst indicates self on default hierarchy */
 	ret = cgroup_migrate_prepare_dst(&mgctx);
@@ -3022,8 +3054,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	ret = cgroup_migrate_execute(&mgctx);
 out_finish:
 	cgroup_migrate_finish(&mgctx);
-	if (has_tasks)
-		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(has_tasks);
 	return ret;
 }
 
@@ -4971,13 +5002,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	struct task_struct *task;
 	const struct cred *saved_cred;
 	ssize_t ret;
-	bool locked;
+	bool threadgroup_locked;
 
 	dst_cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!dst_cgrp)
 		return -ENODEV;
 
-	task = cgroup_procs_write_start(buf, threadgroup, &locked);
+	task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked);
 	ret = PTR_ERR_OR_ZERO(task);
 	if (ret)
 		goto out_unlock;
@@ -5003,7 +5034,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	ret = cgroup_attach_task(dst_cgrp, task, threadgroup);
 
 out_finish:
-	cgroup_procs_write_finish(task, locked);
+	cgroup_procs_write_finish(task, threadgroup_locked);
 out_unlock:
 	cgroup_kn_unlock(of->kn);