[PATCH v5] kernel/fork: beware of __put_task_struct calling context

[Wander Lairson Costa]

Under PREEMPT_RT, __put_task_struct() indirectly acquires sleeping
locks. Therefore, it can't be called from an non-preemptible context.

One practical example is splat inside inactive_task_timer(), which is
called in a interrupt context:

CPU: 1 PID: 2848 Comm: life Kdump: loaded Tainted: G W ---------
 Hardware name: HP ProLiant DL388p Gen8, BIOS P70 07/15/2012
 Call Trace:
 dump_stack_lvl+0x57/0x7d
 mark_lock_irq.cold+0x33/0xba
 ? stack_trace_save+0x4b/0x70
 ? save_trace+0x55/0x150
 mark_lock+0x1e7/0x400
 mark_usage+0x11d/0x140
 __lock_acquire+0x30d/0x930
 lock_acquire.part.0+0x9c/0x210
 ? refill_obj_stock+0x3d/0x3a0
 ? rcu_read_lock_sched_held+0x3f/0x70
 ? trace_lock_acquire+0x38/0x140
 ? lock_acquire+0x30/0x80
 ? refill_obj_stock+0x3d/0x3a0
 rt_spin_lock+0x27/0xe0
 ? refill_obj_stock+0x3d/0x3a0
 refill_obj_stock+0x3d/0x3a0
 ? inactive_task_timer+0x1ad/0x340
 kmem_cache_free+0x357/0x560
 inactive_task_timer+0x1ad/0x340
 ? switched_from_dl+0x2d0/0x2d0
 __run_hrtimer+0x8a/0x1a0
 __hrtimer_run_queues+0x91/0x130
 hrtimer_interrupt+0x10f/0x220
 __sysvec_apic_timer_interrupt+0x7b/0xd0
 sysvec_apic_timer_interrupt+0x4f/0xd0
 ? asm_sysvec_apic_timer_interrupt+0xa/0x20
 asm_sysvec_apic_timer_interrupt+0x12/0x20
 RIP: 0033:0x7fff196bf6f5

Instead of calling __put_task_struct() directly, we defer it using
call_rcu(). A more natural approach would use a workqueue, but since
in PREEMPT_RT, we can't allocate dynamic memory from atomic context,
the code would become more complex because we would need to put the
work_struct instance in the task_struct and initialize it when we
allocate a new task_struct.

Changelog
=========

v1:
* Initial implementation fixing the splat.

v2:
* Isolate the logic in its own function.
* Fix two more cases caught in review.

v3:
* Change __put_task_struct() to handle the issue internally.

v4:
* Explain why call_rcu() is safe to call from interrupt context.

v5:
* Explain why __put_task_struct() doesn't conflict with
  put_task_sruct_rcu_user.

Signed-off-by: Wander Lairson Costa <wander@xxxxxxxxxx>
Reported-by: Hu Chunyu <chuhu@xxxxxxxxxx>
Suggested-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Suggested-by: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: Paul McKenney <paulmck@xxxxxxxxxx>
---
 kernel/fork.c | 33 ++++++++++++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 9f7fe3541897..9bf30c725ed8 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -840,7 +840,7 @@ static inline void put_signal_struct(struct signal_struct *sig)
 		free_signal_struct(sig);
 }
 
-void __put_task_struct(struct task_struct *tsk)
+static void ___put_task_struct(struct task_struct *tsk)
 {
 	WARN_ON(!tsk->exit_state);
 	WARN_ON(refcount_read(&tsk->usage));
@@ -857,6 +857,37 @@ void __put_task_struct(struct task_struct *tsk)
 	sched_core_free(tsk);
 	free_task(tsk);
 }
+
+static void __put_task_struct_rcu(struct rcu_head *rhp)
+{
+	struct task_struct *task = container_of(rhp, struct task_struct, rcu);
+
+	___put_task_struct(task);
+}
+
+void __put_task_struct(struct task_struct *tsk)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT) && (!preemptible() || !in_task()))
+		/*
+		 * 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_rcu()
+		 * to be called in process context.
+		 *
+		 * __put_task_struct() is called 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.
+		 */
+		call_rcu(&tsk->rcu, __put_task_struct_rcu);
+	else
+		___put_task_struct(tsk);
+}
 EXPORT_SYMBOL_GPL(__put_task_struct);
 
 void __init __weak arch_task_cache_init(void) { }
-- 
2.39.1