[PATCH AUTOSEL 5.15 2/9] kernel/fork: beware of __put_task_struct() calling context

From: Sasha Levin
Date: Fri Sep 08 2023 - 14:03:36 EST


From: Wander Lairson Costa <wander@xxxxxxxxxx>

[ Upstream commit d243b34459cea30cfe5f3a9b2feb44e7daff9938 ]

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
mark_lock+0x1e7/0x400
mark_usage+0x11d/0x140
__lock_acquire+0x30d/0x930
lock_acquire.part.0+0x9c/0x210
rt_spin_lock+0x27/0xe0
refill_obj_stock+0x3d/0x3a0
kmem_cache_free+0x357/0x560
inactive_task_timer+0x1ad/0x340
__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+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.

The issue is reproducible with stress-ng:

while true; do
stress-ng --sched deadline --sched-period 1000000000 \
--sched-runtime 800000000 --sched-deadline \
1000000000 --mmapfork 23 -t 20
done

Reported-by: Hu Chunyu <chuhu@xxxxxxxxxx>
Suggested-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Suggested-by: Valentin Schneider <vschneid@xxxxxxxxxx>
Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Wander Lairson Costa <wander@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20230614122323.37957-2-wander@xxxxxxxxxx
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
include/linux/sched/task.h | 28 +++++++++++++++++++++++++++-
kernel/fork.c | 8 ++++++++
2 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index d23977e9035d4..0c2d008099151 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -108,10 +108,36 @@ static inline struct task_struct *get_task_struct(struct task_struct *t)
}

extern void __put_task_struct(struct task_struct *t);
+extern void __put_task_struct_rcu_cb(struct rcu_head *rhp);

static inline void put_task_struct(struct task_struct *t)
{
- if (refcount_dec_and_test(&t->usage))
+ if (!refcount_dec_and_test(&t->usage))
+ return;
+
+ /*
+ * 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 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().
+ */
+ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !preemptible())
+ call_rcu(&t->rcu, __put_task_struct_rcu_cb);
+ else
__put_task_struct(t);
}

diff --git a/kernel/fork.c b/kernel/fork.c
index ace0717c71e27..753e641f617bd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -764,6 +764,14 @@ void __put_task_struct(struct task_struct *tsk)
}
EXPORT_SYMBOL_GPL(__put_task_struct);

+void __put_task_struct_rcu_cb(struct rcu_head *rhp)
+{
+ struct task_struct *task = container_of(rhp, struct task_struct, rcu);
+
+ __put_task_struct(task);
+}
+EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb);
+
void __init __weak arch_task_cache_init(void) { }

/*
--
2.40.1