/proc/stat: fix scalability of irq sum of all cpu

In /proc/stat, the number of per-IRQ event is shown by making a sum each
irq's events on all cpus.  But we can make use of kstat_irqs().

kstat_irqs() do the same calculation, If !CONFIG_GENERIC_HARDIRQ,
it's not a big cost. (Both of the number of cpus and irqs are small.)

If a system is very big and CONFIG_GENERIC_HARDIRQ, it does

	for_each_irq()
		for_each_cpu()
			- look up a radix tree
			- read desc->irq_stat[cpu]
This seems not efficient. This patch adds kstat_irqs() for
CONFIG_GENRIC_HARDIRQ and change the calculation as

	for_each_irq()
		look up radix tree
		for_each_cpu()
			- read desc->irq_stat[cpu]

This reduces cost.

A test on (4096cpusp, 256 nodes, 4592 irqs) host (by Jack Steiner)

%time cat /proc/stat > /dev/null

Before Patch:	 2.459 sec
After Patch :	  .561 sec

[akpm@linux-foundation.org: unexport kstat_irqs, coding-style tweaks]
[akpm@linux-foundation.org: fix unused variable 'per_irq_sum']
Signed-off-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Tested-by: NJack Steiner <steiner@sgi.com>
Acked-by: NJack Steiner <steiner@sgi.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

fs/proc/stat.c

@@ -31,7 +31,6 @@ static int show_stat(struct seq_file *p, void *v)
 	u64 sum_softirq = 0;
 	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
 	struct timespec boottime;
-	unsigned int per_irq_sum;
 
 	user = nice = system = idle = iowait =
 		irq = softirq = steal = cputime64_zero;
@@ -108,13 +107,8 @@ static int show_stat(struct seq_file *p, void *v)
 	seq_printf(p, "intr %llu", (unsigned long long)sum);
 
 	/* sum again ? it could be updated? */
-	for_each_irq_nr(j) {
-		per_irq_sum = 0;
-		for_each_possible_cpu(i)
-			per_irq_sum += kstat_irqs_cpu(j, i);
-
-		seq_printf(p, " %u", per_irq_sum);
-	}
+	for_each_irq_nr(j)
+		seq_printf(p, " %u", kstat_irqs(j));
 
 	seq_printf(p,
 		"\nctxt %llu\n"

include/linux/kernel_stat.h

@@ -86,6 +86,7 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu)
 /*
  * Number of interrupts per specific IRQ source, since bootup
  */
+#ifndef CONFIG_GENERIC_HARDIRQS
 static inline unsigned int kstat_irqs(unsigned int irq)
 {
 	unsigned int sum = 0;
@@ -96,6 +97,9 @@ static inline unsigned int kstat_irqs(unsigned int irq)
 
 	return sum;
 }
+#else
+extern unsigned int kstat_irqs(unsigned int irq);
+#endif
 
 /*
  * Number of interrupts per cpu, since bootup

kernel/irq/irqdesc.c

@@ -393,3 +393,18 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 	struct irq_desc *desc = irq_to_desc(irq);
 	return desc ? desc->kstat_irqs[cpu] : 0;
 }
+
+#ifdef CONFIG_GENERIC_HARDIRQS
+unsigned int kstat_irqs(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	int cpu;
+	int sum = 0;
+
+	if (!desc)
+		return 0;
+	for_each_possible_cpu(cpu)
+		sum += desc->kstat_irqs[cpu];
+	return sum;
+}
+#endif /* CONFIG_GENERIC_HARDIRQS */