linux-kernel - [PATCH v3] genirq: Fix nested thread vs synchronize

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230613-genirq-nested-v3-1-ae58221143eb@axis.com>
Date:   Thu, 6 Jul 2023 16:22:25 +0200
From:   Vincent Whitchurch <vincent.whitchurch@...s.com>
To:     Thomas Gleixner <tglx@...utronix.de>
CC:     <linux-kernel@...r.kernel.org>, <kernel@...s.com>,
        Vincent Whitchurch <vincent.whitchurch@...s.com>
Subject: [PATCH v3] genirq: Fix nested thread vs synchronize_hardirq()
 deadlock

There is a possibility of deadlock if synchronize_hardirq() is called
when the nested threaded interrupt is active.  The following scenario
was observed on a uniprocessor PREEMPT_NONE system:

 Thread 1                      Thread 2

 handle_nested_thread()
  Set INPROGRESS
  Call ->thread_fn()
   thread_fn goes to sleep

                              free_irq()
                               __synchronize_hardirq()
                                Busy-loop forever waiting for INPROGRESS
                                to be cleared

The INPROGRESS flag is only supposed to be used for hard interrupt
handlers.  Remove the incorrect usage in the nested threaded interrupt
case and instead re-use the threads_active / wait_for_threads mechanism
to wait for nested threaded interrupts to complete.

Signed-off-by: Vincent Whitchurch <vincent.whitchurch@...s.com>
---
Changes in v3:
- Do not take spinlock around wake_up(), to fix -rt.
- Reuse wake_threads_waitq().
- Reflow synchronize_irq() after refactoring.
- Link to v2: https://lore.kernel.org/r/20230613-genirq-nested-v2-1-fd5114b1e90c@axis.com

Changes in v2:
- Reword commit message.
- Refactor and reuse synchronize_irq() instead of ending up open coding
  it.
- Link to v1: https://lore.kernel.org/r/20230613-genirq-nested-v1-1-289dc15b7669@axis.com
---
 kernel/irq/chip.c      | 11 ++++-------
 kernel/irq/internals.h |  2 ++
 kernel/irq/manage.c    | 26 ++++++++++++++------------
 3 files changed, 20 insertions(+), 19 deletions(-)

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 49e7bc871fece..c5d722f1903c9 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -472,11 +472,12 @@ void handle_nested_irq(unsigned int irq)
 	action = desc->action;
 	if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) {
 		desc->istate |= IRQS_PENDING;
-		goto out_unlock;
+		raw_spin_unlock_irq(&desc->lock);
+		return;
 	}
 
 	kstat_incr_irqs_this_cpu(desc);
-	irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
+	atomic_inc(&desc->threads_active);
 	raw_spin_unlock_irq(&desc->lock);
 
 	action_ret = IRQ_NONE;
@@ -486,11 +487,7 @@ void handle_nested_irq(unsigned int irq)
 	if (!irq_settings_no_debug(desc))
 		note_interrupt(desc, action_ret);
 
-	raw_spin_lock_irq(&desc->lock);
-	irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);
-
-out_unlock:
-	raw_spin_unlock_irq(&desc->lock);
+	wake_threads_waitq(desc);
 }
 EXPORT_SYMBOL_GPL(handle_nested_irq);
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 5fdc0b5575797..f7e2be805b53f 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -116,6 +116,8 @@ int check_irq_resend(struct irq_desc *desc, bool inject);
 bool irq_wait_for_poll(struct irq_desc *desc);
 void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action);
 
+void wake_threads_waitq(struct irq_desc *desc);
+
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
 extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index d2742af0f0fd8..d309ba84e08a9 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -108,6 +108,16 @@ bool synchronize_hardirq(unsigned int irq)
 }
 EXPORT_SYMBOL(synchronize_hardirq);
 
+static void __synchronize_irq(struct irq_desc *desc)
+{
+	__synchronize_hardirq(desc, true);
+	/*
+	 * We made sure that no hardirq handler is running. Now verify that no
+	 * threaded handlers are active.
+	 */
+	wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active));
+}
+
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *	@irq: interrupt number to wait for
@@ -127,16 +137,8 @@ void synchronize_irq(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (desc) {
-		__synchronize_hardirq(desc, true);
-		/*
-		 * We made sure that no hardirq handler is
-		 * running. Now verify that no threaded handlers are
-		 * active.
-		 */
-		wait_event(desc->wait_for_threads,
-			   !atomic_read(&desc->threads_active));
-	}
+	if (desc)
+		__synchronize_irq(desc);
 }
 EXPORT_SYMBOL(synchronize_irq);
 
@@ -1216,7 +1218,7 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
 	return ret;
 }
 
-static void wake_threads_waitq(struct irq_desc *desc)
+void wake_threads_waitq(struct irq_desc *desc)
 {
 	if (atomic_dec_and_test(&desc->threads_active))
 		wake_up(&desc->wait_for_threads);
@@ -1944,7 +1946,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	 * supports it also make sure that there is no (not yet serviced)
 	 * interrupt in flight at the hardware level.
 	 */
-	__synchronize_hardirq(desc, true);
+	__synchronize_irq(desc);
 
 #ifdef CONFIG_DEBUG_SHIRQ
 	/*

---
base-commit: 858fd168a95c5b9669aac8db6c14a9aeab446375
change-id: 20230613-genirq-nested-625612a6fa05

Best regards,
-- 
Vincent Whitchurch <vincent.whitchurch@...s.com>