genirq/timings: Add infrastructure to track the interrupt timings

The interrupt framework gives a lot of information about each interrupt. It
does not keep track of when those interrupts occur though, which is a
prerequisite for estimating the next interrupt arrival for power management
purposes.

Add a mechanism 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 up to 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 high 48 bits are used
for the timestamp and the low 16 bits are for the irq number.

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

It results in most of the code in internals.h for inline reasons 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.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: "Rafael J . Wysocki" <rafael@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Link: http://lkml.kernel.org/r/1498227072-5980-1-git-send-email-daniel.lezcano@linaro.org

6 files changed, 129 insertions, 0 deletions

diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index fcbb1d6d51cb..27c4e774071c 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -85,6 +85,9 @@ 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 c61fc9c2d1f7..e4aef7351f2b 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -1,5 +1,6 @@
 
 obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o
+obj-$(CONFIG_IRQ_TIMINGS) += timings.o
 obj-$(CONFIG_GENERIC_IRQ_CHIP) += generic-chip.o
 obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
 obj-$(CONFIG_IRQ_DOMAIN) += irqdomain.o
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index d3f24905852c..eb4d3e8945b8 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 a573e0771baf..b95b74920433 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"
@@ -255,6 +257,94 @@ 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 - irq timings storing structure
+ * @values: a circular buffer of u64 encoded <timestamp,irq> values
+ * @count: the number of elements in the array
+ */
+struct irq_timings {
+	u64	values[IRQ_TIMINGS_SIZE];
+	int	count;
+};
+
+DECLARE_PER_CPU(struct irq_timings, irq_timings);
+
+static inline void irq_remove_timings(struct irq_desc *desc)
+{
+	desc->istate &= ~IRQS_TIMINGS;
+}
+
+static inline void irq_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);
+
+DECLARE_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 int irq_timing_decode(u64 value, u64 *timestamp)
+{
+	*timestamp = value >> 16;
+	return 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 irq_remove_timings(struct irq_desc *desc) {}
+static inline void irq_setup_timings(struct irq_desc *desc,
+				     struct irqaction *act) {};
+static inline void record_irq_time(struct irq_desc *desc) {}
+#endif /* CONFIG_IRQ_TIMINGS */
+
+
 #ifdef CONFIG_GENERIC_IRQ_CHIP
 void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name,
 			   int num_ct, unsigned int irq_base,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 3577c091ac7b..5c11c1730ba5 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1348,6 +1348,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
+	irq_setup_timings(desc, new);
+
 	/*
 	 * Strictly no need to wake it up, but hung_task complains
 	 * when no hard interrupt wakes the thread up.
@@ -1474,6 +1476,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 		irq_settings_clr_disable_unlazy(desc);
 		irq_shutdown(desc);
 		irq_release_resources(desc);
+		irq_remove_timings(desc);
 	}
 
 #ifdef CONFIG_SMP
diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c
new file mode 100644
index 000000000000..56cf6870fa26
--- /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@linaro.org>
+ *
+ * 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);
+}