genirq: Avoid summation loops for /proc/stat

Waiman reported that on large systems with a large amount of interrupts the
readout of /proc/stat takes a long time to sum up the interrupt
statistics. In principle this is not a problem. but for unknown reasons
some enterprise quality software reads /proc/stat with a high frequency.

The reason for this is that interrupt statistics are accounted per cpu. So
the /proc/stat logic has to sum up the interrupt stats for each interrupt.

This can be largely avoided for interrupts which are not marked as
'PER_CPU' interrupts by simply adding a per interrupt summation counter
which is incremented along with the per interrupt per cpu counter.

The PER_CPU interrupts need to avoid that and use only per cpu accounting
because they share the interrupt number and the interrupt descriptor and
concurrent updates would conflict or require unwanted synchronization.

Reported-by: Waiman Long <longman@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Waiman Long <longman@redhat.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Daniel Colascione <dancol@google.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Link: https://lkml.kernel.org/r/20190208135020.925487496@linutronix.de
8<-------------

v2: Undo the unintentional layout change of struct irq_desc.

 include/linux/irqdesc.h |    1 +
 kernel/irq/chip.c       |   12 ++++++++++--
 kernel/irq/internals.h  |    8 +++++++-
 kernel/irq/irqdesc.c    |    7 ++++++-
 4 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index dd1e40ddac7d8235e31aeb96fe460c77a70ac681..875c41b23f2031d6d8e9bd21b682397097b26ad4 100644 (file)
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -65,6 +65,7 @@ struct irq_desc {
        unsigned int            core_internal_state__do_not_mess_with_it;
        unsigned int            depth;          /* nested irq disables */
        unsigned int            wake_depth;     /* nested wake enables */
+       unsigned int            tot_count;
        unsigned int            irq_count;      /* For detecting broken IRQs */
        unsigned long           last_unhandled; /* Aging timer for unhandled count */
        unsigned int            irqs_unhandled;

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 34e969069488882d234c94b0466af0591c965ea1..e960c4f46ee06474d49de9230f62a7cb43fa8905 100644 (file)
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -855,7 +855,11 @@ void handle_percpu_irq(struct irq_desc *desc)
 {
        struct irq_chip *chip = irq_desc_get_chip(desc);
 
-       kstat_incr_irqs_this_cpu(desc);
+       /*
+        * PER CPU interrupts are not serialized. Do not touch
+        * desc->tot_count.
+        */
+       __kstat_incr_irqs_this_cpu(desc);
 
        if (chip->irq_ack)
                chip->irq_ack(&desc->irq_data);
@@ -884,7 +888,11 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
        unsigned int irq = irq_desc_get_irq(desc);
        irqreturn_t res;
 
-       kstat_incr_irqs_this_cpu(desc);
+       /*
+        * PER CPU interrupts are not serialized. Do not touch
+        * desc->tot_count.
+        */
+       __kstat_incr_irqs_this_cpu(desc);
 
        if (chip->irq_ack)
                chip->irq_ack(&desc->irq_data);

diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index ca6afa26707006faa59fff84b082f4dc96ec8294..e74e7eea76cf1996e11bfd31bf71dc59903dce7c 100644 (file)
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -242,12 +242,18 @@ static inline void irq_state_set_masked(struct irq_desc *desc)
 
 #undef __irqd_to_state
 
-static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc)
 {
        __this_cpu_inc(*desc->kstat_irqs);
        __this_cpu_inc(kstat.irqs_sum);
 }
 
+static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+{
+       __kstat_incr_irqs_this_cpu(desc);
+       desc->tot_count++;
+}
+
 static inline int irq_desc_get_node(struct irq_desc *desc)
 {
        return irq_common_data_get_node(&desc->irq_common_data);

diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index ee062b7939d3fce9f2813e2bb8f37c5159448631..f98293d0e17329300b8b0fc0dd2d390453713706 100644 (file)
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -119,6 +119,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
        desc->depth = 1;
        desc->irq_count = 0;
        desc->irqs_unhandled = 0;
+       desc->tot_count = 0;
        desc->name = NULL;
        desc->owner = owner;
        for_each_possible_cpu(cpu)
@@ -919,11 +920,15 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 unsigned int kstat_irqs(unsigned int irq)
 {
        struct irq_desc *desc = irq_to_desc(irq);
-       int cpu;
        unsigned int sum = 0;
+       int cpu;
 
        if (!desc || !desc->kstat_irqs)
                return 0;
+       if (!irq_settings_is_per_cpu_devid(desc) &&
+           !irq_settings_is_per_cpu(desc))
+           return desc->tot_count;
+
        for_each_possible_cpu(cpu)
                sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
        return sum;