[PATCH V10 2/3] irq: Track the interrupt timings

From: Daniel Lezcano
Date: Tue May 16 2017 - 15:46:37 EST

The interrupt framework gives a lot of information about each interrupt.

It does not keep track of when those interrupts occur though.

This patch provides a mean to record the timestamp for each interrupt
occurrences in a per-CPU circular buffer to help with the prediction
of the next occurrence using a statistical model.

Each CPU can store IRQ_TIMINGS_SIZE events <irq, timestamp>, the current
value of IRQ_TIMINGS_SIZE is 32.

Each event is encoded into a single u64, where the 48 bits are used for the
timestamp and the next 16 bits are for the irq number.

A static key is introduced so when the irq prediction is switched off at
runtime, we can reduce the overhead near to zero.

It results in most of the code in internals.h for inline reason and a very
few in the new file timings.c. The latter will contain more in the next patch
which will provide the statistical model for the next event prediction.

Note this code is by default *not* compiled in the kernel.

Signed-off-by: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Acked-by: Nicolas Pitre <nicolas.pitre@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rafael J. Wysocki <rafael@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---
V9:
- Changed indentation level by inverting the static key condition
- Encoded interrupt and timestamp into a u64 variable
- Boolean enable instead of refcount for the static key
V8:
- Replaced percpu field in the irqdesc by a percpu array containing the
timings and the associated irq. The function irq_timings_get_next() is no
longer needed, so it is removed
- Removed all unused code resulting from the conversion irqdesc->percpu
timings storage
V7:
- Mentionned in the irq_timings_get_next() function description,
the function must be called inside a rcu read locked section
V6:
- Renamed handle_irq_timings to record_irq_time
- Stored the event time instead of the interval time
- Removed the 'timestamp' field from the timings structure
- Moved _handle_irq_timings content inside record_irq_time
V5:
- Changed comment about 'deterministic' as the comment is confusing
- Added license comment in the header
- Replaced irq_timings_get/put by irq_timings_enable/disable
- Moved IRQS_TIMINGS check in the handle_timings inline function
- Dropped 'if !prev' as it is pointless
- Stored time interval in nsec basis with u64 instead of u32
- Removed redundant store
- Removed the math
V4:
- Added a static key
- Added more comments for irq_timings_get_next()
- Unified some function names to be prefixed by 'irq_timings_...'
- Fixed a rebase error
V3:
- Replaced ktime_get() by local_clock()
- Shared irq are not handled
- Simplified code by adding the timing in the irqdesc struct
- Added a function to browse the irq timings
V2:
- Fixed kerneldoc comment
- Removed data field from the struct irq timing
- Changed the lock section comment
- Removed semi-colon style with empty stub
- Replaced macro by static inline
- Fixed static functions declaration
RFC:
- initial posting
---
include/linux/interrupt.h | 5 +++
kernel/irq/Kconfig | 3 ++
kernel/irq/Makefile | 1 +
kernel/irq/handle.c | 2 ++
kernel/irq/internals.h | 84 +++++++++++++++++++++++++++++++++++++++++++++++
kernel/irq/manage.c | 3 ++
kernel/irq/timings.c | 30 +++++++++++++++++
7 files changed, 128 insertions(+)
create mode 100644 kernel/irq/timings.c

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 89defd5..4c9d3ca 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -712,6 +712,11 @@ static inline void init_irq_proc(void)
}
#endif

+#ifdef CONFIG_IRQ_TIMINGS
+void irq_timings_enable(void);
+void irq_timings_disable(void);
+#endif
+
struct seq_file;
int show_interrupts(struct seq_file *p, void *v);
int arch_show_interrupts(struct seq_file *p, int prec);
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 3bbfd6a..38e551d 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -81,6 +81,9 @@ config GENERIC_MSI_IRQ_DOMAIN
config HANDLE_DOMAIN_IRQ
bool

+config IRQ_TIMINGS
+ bool
+
config IRQ_DOMAIN_DEBUG
bool "Expose hardware/virtual IRQ mapping via debugfs"
depends on IRQ_DOMAIN && DEBUG_FS
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 1d3ee31..efb5f14 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -10,3 +10,4 @@ obj-$(CONFIG_PM_SLEEP) += pm.o
obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o
obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o
obj-$(CONFIG_SMP) += affinity.o
+obj-$(CONFIG_IRQ_TIMINGS) += timings.o
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index d3f2490..eb4d3e8 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -138,6 +138,8 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags
unsigned int irq = desc->irq_data.irq;
struct irqaction *action;

+ record_irq_time(desc);
+
for_each_action_of_desc(desc, action) {
irqreturn_t res;

diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index bc226e7..df51b5e0 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -8,6 +8,7 @@
#include <linux/irqdesc.h>
#include <linux/kernel_stat.h>
#include <linux/pm_runtime.h>
+#include <linux/sched/clock.h>

#ifdef CONFIG_SPARSE_IRQ
# define IRQ_BITMAP_BITS (NR_IRQS + 8196)
@@ -57,6 +58,7 @@ enum {
IRQS_WAITING = 0x00000080,
IRQS_PENDING = 0x00000200,
IRQS_SUSPENDED = 0x00000800,
+ IRQS_TIMINGS = 0x00001000,
};

#include "debug.h"
@@ -226,3 +228,85 @@ irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { }
static inline void
irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { }
#endif
+
+#ifdef CONFIG_IRQ_TIMINGS
+
+#define IRQ_TIMINGS_SHIFT 5
+#define IRQ_TIMINGS_SIZE (1 << IRQ_TIMINGS_SHIFT)
+#define IRQ_TIMINGS_MASK (IRQ_TIMINGS_SIZE - 1)
+
+struct irq_timings {
+ u64 values[IRQ_TIMINGS_SIZE]; /* our circular buffer */
+ unsigned int count; /* Number of interruptions since last inspection */
+};
+
+DECLARE_PER_CPU(struct irq_timings, irq_timings);
+
+static inline void remove_timings(struct irq_desc *desc)
+{
+ desc->istate &= ~IRQS_TIMINGS;
+}
+
+static inline void setup_timings(struct irq_desc *desc, struct irqaction *act)
+{
+ /*
+ * We don't need the measurement because the idle code already
+ * knows the next expiry event.
+ */
+ if (act->flags & __IRQF_TIMER)
+ return;
+
+ desc->istate |= IRQS_TIMINGS;
+}
+
+extern void irq_timings_enable(void);
+extern void irq_timings_disable(void);
+
+extern struct static_key_false irq_timing_enabled;
+
+/*
+ * The interrupt number and the timestamp are encoded into a single
+ * u64 variable to optimize the size.
+ * 48 bit time stamp and 16 bit IRQ number is way sufficient.
+ * Who cares an IRQ after 78 hours of idle time?
+ */
+static inline u64 irq_timing_encode(u64 timestamp, int irq)
+{
+ return (timestamp << 16) | irq;
+}
+
+static inline void irq_timing_decode(u64 value, u64 *timestamp, int *irq)
+{
+ *timestamp = value >> 16;
+ *irq = value & U16_MAX;
+}
+
+/*
+ * The function record_irq_time is only called in one place in the
+ * interrupts handler. We want this function always inline so the code
+ * inside is embedded in the function and the static key branching
+ * code can act at the higher level. Without the explicit
+ * __always_inline we can end up with a function call and a small
+ * overhead in the hotpath for nothing.
+ */
+static __always_inline void record_irq_time(struct irq_desc *desc)
+{
+ if (!static_branch_likely(&irq_timing_enabled))
+ return;
+
+ if (desc->istate & IRQS_TIMINGS) {
+ struct irq_timings *timings = this_cpu_ptr(&irq_timings);
+
+ timings->values[timings->count & IRQ_TIMINGS_MASK] =
+ irq_timing_encode(local_clock(),
+ irq_desc_get_irq(desc));
+
+ timings->count++;
+ }
+}
+#else
+static inline void remove_timings(struct irq_desc *desc) {}
+static inline void setup_timings(struct irq_desc *desc,
+ struct irqaction *act) {};
+static inline void record_irq_time(struct irq_desc *desc) {}
+#endif /* CONFIG_IRQ_TIMINGS */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 057fde8..5dfa63d 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1372,6 +1372,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)

raw_spin_unlock_irqrestore(&desc->lock, flags);

+ setup_timings(desc, new);
+
/*
* Strictly no need to wake it up, but hung_task complains
* when no hard interrupt wakes the thread up.
@@ -1500,6 +1502,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
irq_settings_clr_disable_unlazy(desc);
irq_shutdown(desc);
irq_release_resources(desc);
+ remove_timings(desc);
}

#ifdef CONFIG_SMP
diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c
new file mode 100644
index 0000000..56cf687
--- /dev/null
+++ b/kernel/irq/timings.c
@@ -0,0 +1,30 @@
+/*
+ * linux/kernel/irq/timings.c
+ *
+ * Copyright (C) 2016, Linaro Ltd - Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include <linux/percpu.h>
+#include <linux/static_key.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+
+#include "internals.h"
+
+DEFINE_STATIC_KEY_FALSE(irq_timing_enabled);
+
+DEFINE_PER_CPU(struct irq_timings, irq_timings);
+
+void irq_timings_enable(void)
+{
+ static_branch_enable(&irq_timing_enabled);
+}
+
+void irq_timings_disable(void)
+{
+ static_branch_disable(&irq_timing_enabled);
+}
--
2.7.4