[PATCH v7 2/3] sched/task: Add the put_task_struct_atomic_safe() function

[Wander Lairson Costa <wander@redhat.com>]

Due to the possibility of indirectly acquiring sleeping locks, it is
unsafe to call put_task_struct() in atomic contexts when the kernel is
compiled with PREEMPT_RT.

To mitigate this issue, this commit introduces
put_task_struct_atomic_safe(), which schedules __put_task_struct()
through call_rcu() when PREEMPT_RT is enabled. While a workqueue would
be a more natural approach, we cannot allocate dynamic memory from
atomic context in PREEMPT_RT, making the code more complex.

This implementation ensures safe execution in atomic contexts and
avoids any potential issues that may arise from using the non-atomic
version.

Signed-off-by: Wander Lairson Costa <wander@redhat.com>
Reported-by: Hu Chunyu <chuhu@redhat.com>
Reviewed-by: Paul McKenney <paulmck@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/sched/task.h | 35 +++++++++++++++++++++++++++++++++++
 kernel/fork.c              |  8 ++++++++
 2 files changed, 43 insertions(+)

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index b597b97b1f8f..cf774b83b2ec 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -141,6 +141,41 @@ static inline void put_task_struct_many(struct task_struct *t, int nr)
 
 void put_task_struct_rcu_user(struct task_struct *task);
 
+extern void __delayed_put_task_struct(struct rcu_head *rhp);
+
+static inline void put_task_struct_atomic_safe(struct task_struct *task)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		/*
+		 * Decrement the refcount explicitly to avoid unnecessarily
+		 * calling call_rcu.
+		 */
+		if (refcount_dec_and_test(&task->usage))
+			/*
+			 * under PREEMPT_RT, we can't call put_task_struct
+			 * in atomic context because it will indirectly
+			 * acquire sleeping locks.
+			 * call_rcu() will schedule __delayed_put_task_struct()
+			 * to be called in process context.
+			 *
+			 * __put_task_struct() is called when
+			 * refcount_dec_and_test(&t->usage) succeeds.
+			 *
+			 * This means that it can't conflict with
+			 * put_task_struct_rcu_user() which abuses ->rcu the same
+			 * way; rcu_users has a reference so task->usage can't be
+			 * zero after rcu_users 1 -> 0 transition.
+			 *
+			 * delayed_free_task() also uses ->rcu, but it is only called
+			 * when it fails to fork a process. Therefore, there is no
+			 * way it can conflict with put_task_struct().
+			 */
+			call_rcu(&task->rcu, __delayed_put_task_struct);
+	} else {
+		put_task_struct(task);
+	}
+}
+
 /* Free all architecture-specific resources held by a thread. */
 void release_thread(struct task_struct *dead_task);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index ea332319dffe..7f016b691b1d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -854,6 +854,14 @@ void __put_task_struct(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(__put_task_struct);
 
+void __delayed_put_task_struct(struct rcu_head *rhp)
+{
+	struct task_struct *task = container_of(rhp, struct task_struct, rcu);
+
+	__put_task_struct(task);
+}
+EXPORT_SYMBOL_GPL(__delayed_put_task_struct);
+
 void __init __weak arch_task_cache_init(void) { }
 
 /*
-- 
2.40.0