[PATCH] sched/deadline: fix inactive_task_timer splat with CONFIG_PREEMPT_RT

[Wander Lairson Costa]

inactive_task_timer() executes in interrupt (atomic) context. It calls
put_task_struct(), which indirectly acquires sleeping locks under
PREEMPT_RT.

Below is an example of a splat that happened in a test environment:

 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.

Signed-off-by: Wander Lairson Costa <wander@xxxxxxxxxx>
Cc: Paul McKenney <paulmck@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
 kernel/sched/build_policy.c |  1 +
 kernel/sched/deadline.c     | 24 +++++++++++++++++++++++-
 2 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
index d9dc9ab3773f..f159304ee792 100644
--- a/kernel/sched/build_policy.c
+++ b/kernel/sched/build_policy.c
@@ -28,6 +28,7 @@
 #include <linux/suspend.h>
 #include <linux/tsacct_kern.h>
 #include <linux/vtime.h>
+#include <linux/rcupdate.h>
 
 #include <uapi/linux/sched/types.h>
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 9ae8f41e3372..ab9301d4cc24 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1405,6 +1405,13 @@ static void update_curr_dl(struct rq *rq)
 	}
 }
 
+static void delayed_put_task_struct(struct rcu_head *rhp)
+{
+	struct task_struct *task = container_of(rhp, struct task_struct, rcu);
+
+	__put_task_struct(task);
+}
+
 static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 {
 	struct sched_dl_entity *dl_se = container_of(timer,
@@ -1442,7 +1449,22 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 	dl_se->dl_non_contending = 0;
 unlock:
 	task_rq_unlock(rq, p, &rf);
-	put_task_struct(p);
+
+	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		/*
+		 * Decrement the refcount explicitly to avoid unnecessarily
+		 * calling call_rcu.
+		 */
+		if (refcount_dec_and_test(&p->usage))
+			/*
+			 * under PREEMPT_RT, we can't call put_task_struct
+			 * in atomic context because it will indirectly
+			 * acquire sleeping locks.
+			 */
+			call_rcu(&p->rcu, delayed_put_task_struct);
+	} else {
+		put_task_struct(p);
+	}
 
 	return HRTIMER_NORESTART;
 }
-- 
2.39.0