diff mbox series

irq: synchronize irq_thread startup

Message ID f18798-9e66-66e7-8c9d-cb8eeda364c4@pcs.com
State New
Headers show
Series irq: synchronize irq_thread startup | expand

Commit Message

Thomas Pfaff April 28, 2022, 10:49 a.m. UTC
From: Thomas Pfaff <tpfaff@pcs.com>

While running
"while /bin/true; do setserial /dev/ttyS0 uart none;
setserial /dev/ttyS0 uart 16550A; done"
on a kernel with threaded irqs, setserial is hung after some calls.

setserial opens the device, this will install an irq handler if the uart is
not none, followed by TIOCGSERIAL and TIOCSSERIAL ioctls.
Then the device is closed. On close, synchronize_irq() is called by
serial_core.

If the close comes too fast, the irq_thread does not really start,
it is terminated immediately without going into irq_thread().
But an interrupt might already been handled by
irq_default_primary_handler(), going to __irq_wake_thread() and
incrementing threads_active.
If this happens, synchronize_irq() will hang forever, because the
irq_thread is already dead, and threads_active will never be decremented.

The fix is to make sure that the irq_thread is really started
during __setup_irq().

Signed-off-by: Thomas Pfaff <tpfaff@pcs.com>
---

Comments

Thomas Gleixner April 28, 2022, 3:42 p.m. UTC | #1
Thomas,

On Thu, Apr 28 2022 at 12:49, Thomas Pfaff wrote:

please always Cc maintainers when sending patches and please also have a
look at:

https://www.kernel.org/doc/html/latest/process/maintainer-tip.html#patch-submission-notes

> While running
> "while /bin/true; do setserial /dev/ttyS0 uart none;
> setserial /dev/ttyS0 uart 16550A; done"
> on a kernel with threaded irqs, setserial is hung after some calls.
>
> setserial opens the device, this will install an irq handler if the uart is
> not none, followed by TIOCGSERIAL and TIOCSSERIAL ioctls.
> Then the device is closed. On close, synchronize_irq() is called by
> serial_core.
>
> If the close comes too fast, the irq_thread does not really start,
> it is terminated immediately without going into irq_thread().
> But an interrupt might already been handled by
> irq_default_primary_handler(), going to __irq_wake_thread() and
> incrementing threads_active.
> If this happens, synchronize_irq() will hang forever, because the
> irq_thread is already dead, and threads_active will never be decremented.
>
> The fix is to make sure that the irq_thread is really started
> during __setup_irq().

Right. Nice detective work.

> @@ -127,6 +129,8 @@ struct irqaction {
>  	unsigned int		flags;
>  	unsigned long		thread_flags;
>  	unsigned long		thread_mask;
> +	atomic_t		thread_is_up;
> +	wait_queue_head_t	wait_for_thread;

I don't think we need any of this extra ballast per irqaction.

irqaction::thread_flags is already there and can be used as indicator.
There are enough bits left.

irq_desc already has a wait queue, which is used for synchronize_irq()
to wait for threads to complete. That wait queue is unused at the point
where an interrupt is set up, so there is no reason to introduce a new
one which is only used once.

This is not a problem in the rare case that the interrupt fires and
wakes the thread which then in consequence might wake the waiter via
wake_threads_waitq().

> -	if (new->thread)
> +	if (new->thread) {
>  		wake_up_process(new->thread);
> -	if (new->secondary)
> +		wait_event(new->wait_for_thread,
> +			   atomic_read(&new->thread_is_up));

Please stick this into a helper function.

Thanks,

        tglx
diff mbox series

Patch

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index f40754caaefa..82a16a12d472 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -113,6 +113,8 @@  typedef irqreturn_t (*irq_handler_t)(int, void *);
  * @secondary:	pointer to secondary irqaction (force threading)
  * @thread_flags:	flags related to @thread
  * @thread_mask:	bitmask for keeping track of @thread activity
+ * @thread_is_up:	threaded irq handler initializated
+ * @wait_for_thread:	wait queue to wait for thread initialization
  * @dir:	pointer to the proc/irq/NN/name entry
  */
 struct irqaction {
@@ -127,6 +129,8 @@  struct irqaction {
 	unsigned int		flags;
 	unsigned long		thread_flags;
 	unsigned long		thread_mask;
+	atomic_t		thread_is_up;
+	wait_queue_head_t	wait_for_thread;
 	const char		*name;
 	struct proc_dir_entry	*dir;
 } ____cacheline_internodealigned_in_smp;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index c03f71d5ec10..345e4f824c58 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1272,6 +1272,9 @@  static int irq_thread(void *data)
 
 	irq_thread_check_affinity(desc, action);
 
+	atomic_set(&action->thread_is_up, 1);
+	wake_up(&action->wait_for_thread);
+
 	while (!irq_wait_for_interrupt(action)) {
 		irqreturn_t action_ret;
 
@@ -1415,6 +1418,8 @@  setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
 {
 	struct task_struct *t;
 
+	init_waitqueue_head(&new->wait_for_thread);
+
 	if (!secondary) {
 		t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
 				   new->name);
@@ -1781,13 +1786,18 @@  __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	irq_setup_timings(desc, new);
 
 	/*
-	 * Strictly no need to wake it up, but hung_task complains
-	 * when no hard interrupt wakes the thread up.
+	 * wake thread up, and wait until it is really up
 	 */
-	if (new->thread)
+	if (new->thread) {
 		wake_up_process(new->thread);
-	if (new->secondary)
+		wait_event(new->wait_for_thread,
+			   atomic_read(&new->thread_is_up));
+	}
+	if (new->secondary) {
 		wake_up_process(new->secondary->thread);
+		wait_event(new->secondary->wait_for_thread,
+			   atomic_read(&new->secondary->thread_is_up));
+	}
 
 	register_irq_proc(irq, desc);
 	new->dir = NULL;