From: Tejun Heo <tj@xxxxxxxxxx>
[ Upstream commit 4f7e7236435ca0abe005c674ebd6892c6e83aeb3 ]
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@xxxxxxxxxx>
Reviewed-and-tested-by: Imran Khan <imran.f.khan@xxxxxxxxxx>
Reported-and-tested-by: Xuewen Yan <xuewen.yan@xxxxxxxxxx>
Fixes: 05c7b7a92cc8 ("cgroup/cpuset: Fix a race between cpuset_attach() and cpu hotplug")
Cc: stable@xxxxxxxxxxxxxxx # v5.17+
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
kernel/cgroup/cgroup.c | 77 +++++++++++++++++++++++++++++-------------
kernel/cgroup/cpuset.c | 3 +-
2 files changed, 55 insertions(+), 25 deletions(-)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 1072843b25709..684c16849eff3 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2304,6 +2304,47 @@ 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
@@ -2780,8 +2821,7 @@ 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;
@@ -2798,12 +2838,8 @@ 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) {
@@ -2834,17 +2870,14 @@ 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;
@@ -2852,8 +2885,8 @@ 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();
@@ -2930,8 +2963,7 @@ 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);
@@ -2952,8 +2984,7 @@ 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;
}
@@ -4809,13 +4840,13 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
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, true, &locked);
+ task = cgroup_procs_write_start(buf, true, &threadgroup_locked);
ret = PTR_ERR_OR_ZERO(task);
if (ret)
goto out_unlock;
@@ -4841,7 +4872,7 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
ret = cgroup_attach_task(dst_cgrp, task, true);
out_finish:
- cgroup_procs_write_finish(task, locked);
+ cgroup_procs_write_finish(task, threadgroup_locked);
out_unlock:
cgroup_kn_unlock(of->kn);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index c51863b63f93a..b7830f1f1f3a5 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2212,7 +2212,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
cgroup_taskset_first(tset, &css);
cs = css_cs(css);
- cpus_read_lock();
+ lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */
percpu_down_write(&cpuset_rwsem);
/* prepare for attach */
@@ -2268,7 +2268,6 @@ static void cpuset_attach(struct cgroup_taskset *tset)
wake_up(&cpuset_attach_wq);
percpu_up_write(&cpuset_rwsem);
- cpus_read_unlock();
}
/* The various types of files and directories in a cpuset file system */
--
2.35.1
