.../admin-guide/kernel-parameters.txt | 5 ++ kernel/irq/handle.c | 49 ++++++++++++++++++- 2 files changed, 53 insertions(+), 1 deletion(-)
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@nokia.com>
---
V4 -> V5: be more precise in duration print resolution, use div_u64 instead of bit shift
for printing the IRQ duration:
https://lore.kernel.org/lkml/20250724155059.2992-1-wladislav.wiebe@nokia.com/
V3 -> V4: convert us to ns in setup path to avoid shift operation in compare path
based on V3 review:
https://lore.kernel.org/lkml/20250723182836.1177-1-wladislav.wiebe@nokia.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 e4b7015718bb..441943dfd0f3 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2259,6 +2259,11 @@
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 088e5c01075c..b2b0600aa5ba 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -141,6 +141,44 @@ 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_ns __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_ns = val * 1000;
+ 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)
+{
+ u64 delta_ns = local_clock() - ts_start;
+
+ if (unlikely(delta_ns > irqhandler_duration_threshold_ns)) {
+ pr_warn_ratelimited("[CPU%u] long duration of IRQ[%u:%ps], took: %llu us\n",
+ smp_processor_id(), irq, action->handler,
+ div_u64(delta_ns, NSEC_PER_USEC));
+ }
+}
+
irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc)
{
irqreturn_t retval = IRQ_NONE;
@@ -160,7 +198,16 @@ 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.dirtyOn 04. 08. 25, 11:35, Wladislav Wiebe wrote: > 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. Reviewed-by: Jiri Slaby <jirislaby@kernel.org> -- js suse labs
On 04. 08. 25, 11:35, Wladislav Wiebe wrote: > 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@nokia.com> OK: Reviewed-by: Jiri Slaby <jirislaby@kernel.org> -- js suse labs
The following commit has been merged into the irq/core branch of tip:
Commit-ID: 673f1244b3d47c9b41cda3473c062bec586387be
Gitweb: https://git.kernel.org/tip/673f1244b3d47c9b41cda3473c062bec586387be
Author: Wladislav Wiebe <wladislav.wiebe@nokia.com>
AuthorDate: Mon, 04 Aug 2025 11:35:25 +02:00
Committer: Thomas Gleixner <tglx@linutronix.de>
CommitterDate: Wed, 03 Sep 2025 16:10:40 +02:00
genirq: Add support for warning on long-running interrupt handlers
Introduce a mechanism to detect and warn about prolonged interrupt 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@nokia.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Link: https://lore.kernel.org/all/20250804093525.851-1-wladislav.wiebe@nokia.com
---
Documentation/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 747a55a..bdbc44f 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2606,6 +2606,11 @@
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 9489f93..e103451 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_ns __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_ns = val * 1000;
+ 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)
+{
+ u64 delta_ns = local_clock() - ts_start;
+
+ if (unlikely(delta_ns > irqhandler_duration_threshold_ns)) {
+ pr_warn_ratelimited("[CPU%u] long duration of IRQ[%u:%ps], took: %llu us\n",
+ smp_processor_id(), irq, action->handler,
+ div_u64(delta_ns, NSEC_PER_USEC));
+ }
+}
+
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",© 2016 - 2025 Red Hat, Inc.