irq: use per_cpu kstat_irqs

Use modern per_cpu API to increment {soft|hard}irq counters, and use
per_cpu allocation for (struct irq_desc)->kstats_irq instead of an array.

This gives better SMP/NUMA locality and saves few instructions per irq.

With small nr_cpuids values (8 for example), kstats_irq was a small array
(less than L1_CACHE_BYTES), potentially source of false sharing.

In the !CONFIG_SPARSE_IRQ case, remove the huge, NUMA/cache unfriendly
kstat_irqs_all[NR_IRQS][NR_CPUS] array.

Note: we still populate kstats_irq for all possible irqs in
early_irq_init().  We probably could use on-demand allocations.  (Code
included in alloc_descs()).  Problem is not all IRQS are used with a prior
alloc_descs() call.

kstat_irqs_this_cpu() is not used anymore, remove it.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 9 insertions, 10 deletions

diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 44e83ba..0cce2db 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -46,16 +46,14 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 extern unsigned long long nr_context_switches(void);
 
 #ifndef CONFIG_GENERIC_HARDIRQS
-#define kstat_irqs_this_cpu(irq) \
-	(this_cpu_read(kstat.irqs[irq])
 
 struct irq_desc;
 
 static inline void kstat_incr_irqs_this_cpu(unsigned int irq,
 					    struct irq_desc *desc)
 {
-	kstat_this_cpu.irqs[irq]++;
-	kstat_this_cpu.irqs_sum++;
+	__this_cpu_inc(kstat.irqs[irq]);
+	__this_cpu_inc(kstat.irqs_sum);
 }
 
 static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
@@ -65,17 +63,18 @@ static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 #else
 #include <linux/irq.h>
 extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu);
-#define kstat_irqs_this_cpu(DESC) \
-	((DESC)->kstat_irqs[smp_processor_id()])
-#define kstat_incr_irqs_this_cpu(irqno, DESC) do {\
-	((DESC)->kstat_irqs[smp_processor_id()]++);\
-	kstat_this_cpu.irqs_sum++; } while (0)
+
+#define kstat_incr_irqs_this_cpu(irqno, DESC)		\
+do {							\
+	__this_cpu_inc(*(DESC)->kstat_irqs);		\
+	__this_cpu_inc(kstat.irqs_sum);			\
+} while (0)
 
 #endif
 
 static inline void kstat_incr_softirqs_this_cpu(unsigned int irq)
 {
-	kstat_this_cpu.softirqs[irq]++;
+	__this_cpu_inc(kstat.softirqs[irq]);
 }
 
 static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu)