genirq: Provide a snapshot mechanism for interrupt statistics

The soft lockup detector lacks a mechanism to identify interrupt storms as
root cause of a lockup. To enable this the detector needs a mechanism to
snapshot the interrupt count statistics on a CPU when the detector observes
a potential lockup scenario and compare that against the interrupt count
when it warns about the lockup later on. The number of interrupts in that
period give a hint whether the lockup might have been caused by an interrupt
storm.

Instead of having extra storage in the lockup detector and accessing the
internals of the interrupt descriptor directly, add a snapshot member to
the per CPU irq_desc::kstat_irq structure and provide interfaces to take a
snapshot of all interrupts on the current CPU and to retrieve the delta of
a specific interrupt later on.

Originally-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Bitao Hu <yaoma@linux.alibaba.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20240411074134.30922-3-yaoma@linux.alibaba.com
This commit is contained in:
Bitao Hu 2024-04-11 15:41:31 +08:00 committed by Thomas Gleixner
parent 86d2a2f51f
commit 99cf63c566
4 changed files with 41 additions and 0 deletions

View file

@ -20,9 +20,13 @@ struct pt_regs;
/**
* struct irqstat - interrupt statistics
* @cnt: real-time interrupt count
* @ref: snapshot of interrupt count
*/
struct irqstat {
unsigned int cnt;
#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT
unsigned int ref;
#endif
};
/**

View file

@ -79,6 +79,14 @@ static inline unsigned int kstat_cpu_softirqs_sum(int cpu)
return sum;
}
#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT
extern void kstat_snapshot_irqs(void);
extern unsigned int kstat_get_irq_since_snapshot(unsigned int irq);
#else
static inline void kstat_snapshot_irqs(void) { }
static inline unsigned int kstat_get_irq_since_snapshot(unsigned int irq) { return 0; }
#endif
/*
* Number of interrupts per specific IRQ source, since bootup
*/

View file

@ -108,6 +108,10 @@ config GENERIC_IRQ_MATRIX_ALLOCATOR
config GENERIC_IRQ_RESERVATION_MODE
bool
# Snapshot for interrupt statistics
config GENERIC_IRQ_STAT_SNAPSHOT
bool
# Support forced irq threading
config IRQ_FORCED_THREADING
bool

View file

@ -994,6 +994,31 @@ static unsigned int kstat_irqs(unsigned int irq)
return sum;
}
#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT
void kstat_snapshot_irqs(void)
{
struct irq_desc *desc;
unsigned int irq;
for_each_irq_desc(irq, desc) {
if (!desc->kstat_irqs)
continue;
this_cpu_write(desc->kstat_irqs->ref, this_cpu_read(desc->kstat_irqs->cnt));
}
}
unsigned int kstat_get_irq_since_snapshot(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
if (!desc || !desc->kstat_irqs)
return 0;
return this_cpu_read(desc->kstat_irqs->cnt) - this_cpu_read(desc->kstat_irqs->ref);
}
#endif
/**
* kstat_irqs_usr - Get the statistics for an interrupt from thread context
* @irq: The interrupt number