linux-kernel - [PATCH v3] genirq: add support for warning on long-running IRQ handlers

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: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250723182836.1177-1-wladislav.wiebe@nokia.com>
Date: Wed, 23 Jul 2025 20:28:36 +0200
From: Wladislav Wiebe <wladislav.wiebe@...ia.com>
To: tglx@...utronix.de,
	corbet@....net,
	jirislaby@...nel.org
Cc: akpm@...ux-foundation.org,
	paulmck@...nel.org,
	rostedt@...dmis.org,
	Neeraj.Upadhyay@....com,
	david@...hat.com,
	bp@...en8.de,
	arnd@...db.de,
	fvdl@...gle.com,
	linux-doc@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	wladislav.wiebe@...ia.com,
	peterz@...radead.org
Subject: [PATCH v3] genirq: add support for warning on long-running IRQ handlers

Introduce a mechanism to detect and warn about prolonged IRQ handlers.
With a new command-line parameter (irqhandler.duration_warn_us=),
users can configure the duration threshold in microseconds when a warning
in such format should be emitted:

"[CPU14] long duration of IRQ[159:bad_irq_handler [long_irq]], took: 1330 us"

The implementation uses local_clock() to measure the execution duration of the
generic IRQ per-CPU event handler.

Signed-off-by: Wladislav Wiebe <wladislav.wiebe@...ia.com>
---
V2 -> V3: Addressed review comments based on v2:
	  https://lore.kernel.org/lkml/20250714084209.918-1-wladislav.wiebe@nokia.com/
	  - refactor commit message
	  - switch from early_param() to __setup()
	  - comment on approximation of nano to microseconds conversion
	  - move ts_start to if() branch
	  - align pr_warn arguments
	  - surround else block with brackets as well
	  - invert the condition and drop the "else {}" in cmdline arg. check
	  - make struct irqaction *action function param. const
	    in irqhandler_duration_check()
	  - print smp_processor_id() return as unsigned int
	  - fix warning text "on IRQ[...]" -> "of IRQ[...]"
V1 -> V2: refactor to use local_clock() instead of jiffies and replace
	  Kconfig knobs by a new command-line parameter.
V1 link:  https://lore.kernel.org/lkml/20250630124721.18232-1-wladislav.wiebe@nokia.com/
---
 .../admin-guide/kernel-parameters.txt         |  5 ++
 kernel/irq/handle.c                           | 49 ++++++++++++++++++-
 2 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 07e22ba5bfe3..7a2d0338ee91 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2543,6 +2543,11 @@
 			for it. Intended to get systems with badly broken
 			firmware running.
 
+	irqhandler.duration_warn_us= [KNL]
+			Warn if an IRQ handler exceeds the specified duration
+			threshold in microseconds. Useful for identifying
+			long-running IRQs in the system.
+
 	irqpoll		[HW]
 			When an interrupt is not handled search all handlers
 			for it. Also check all handlers each timer
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 9489f93b3db3..258f40ad8cb1 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -136,6 +136,44 @@ void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
 	wake_up_process(action->thread);
 }
 
+static DEFINE_STATIC_KEY_FALSE(irqhandler_duration_check_enabled);
+static u64 irqhandler_duration_threshold_us __ro_after_init;
+
+static int __init irqhandler_duration_check_setup(char *arg)
+{
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(arg, 0, &val);
+	if (ret) {
+		pr_err("Unable to parse irqhandler.duration_warn_us setting: ret=%d\n", ret);
+		return 0;
+	}
+
+	if (!val) {
+		pr_err("Invalid irqhandler.duration_warn_us setting, must be > 0\n");
+		return 0;
+	}
+
+	irqhandler_duration_threshold_us = val;
+	static_branch_enable(&irqhandler_duration_check_enabled);
+
+	return 1;
+}
+__setup("irqhandler.duration_warn_us=", irqhandler_duration_check_setup);
+
+static inline void irqhandler_duration_check(u64 ts_start, unsigned int irq,
+					     const struct irqaction *action)
+{
+	/* Approx. conversion to microseconds */
+	u64 delta_us = (local_clock() - ts_start) >> 10;
+
+	if (unlikely(delta_us > irqhandler_duration_threshold_us)) {
+		pr_warn_ratelimited("[CPU%u] long duration of IRQ[%u:%ps], took: %llu us\n",
+				    smp_processor_id(), irq, action->handler, delta_us);
+	}
+}
+
 irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc)
 {
 	irqreturn_t retval = IRQ_NONE;
@@ -155,7 +193,16 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc)
 			lockdep_hardirq_threaded();
 
 		trace_irq_handler_entry(irq, action);
-		res = action->handler(irq, action->dev_id);
+
+		if (static_branch_unlikely(&irqhandler_duration_check_enabled)) {
+			u64 ts_start = local_clock();
+
+			res = action->handler(irq, action->dev_id);
+			irqhandler_duration_check(ts_start, irq, action);
+		} else {
+			res = action->handler(irq, action->dev_id);
+		}
+
 		trace_irq_handler_exit(irq, action, res);
 
 		if (WARN_ONCE(!irqs_disabled(),"irq %u handler %pS enabled interrupts\n",
-- 
2.39.3.dirty