generic-ipi: Optimize accesses by using DEFINE_PER_CPU_SHARED_ALIGNED for IPI data

The smp ipi data is passed around and given write access by
other cpus and should be separated from per-cpu data consumed by
this cpu.

Looking for hot lines, I saw call_function_data shared with
tick_cpu_sched.

Signed-off-by: Milton Miller <miltonm@bga.com>
Acked-by: Anton Blanchard <anton@samba.org>
Acked-by: Jens Axboe <jens.axboe@oracle.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: : Nick Piggin <npiggin@suse.de>
LKML-Reference: <20100118020051.GR12666@kryten>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/smp.c

@@ -12,8 +12,6 @@
 #include <linux/smp.h>
 #include <linux/cpu.h>
 
-static DEFINE_PER_CPU(struct call_single_queue, call_single_queue);
-
 static struct {
 	struct list_head	queue;
 	raw_spinlock_t		lock;
@@ -33,12 +31,14 @@ struct call_function_data {
 	cpumask_var_t		cpumask;
 };
 
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
+
 struct call_single_queue {
 	struct list_head	list;
 	raw_spinlock_t		lock;
 };
 
-static DEFINE_PER_CPU(struct call_function_data, cfd_data);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_queue, call_single_queue);
 
 static int
 hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
@@ -256,7 +256,7 @@ void generic_smp_call_function_single_interrupt(void)
 	}
 }
 
-static DEFINE_PER_CPU(struct call_single_data, csd_data);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
 
 /*
  * smp_call_function_single - Run a function on a specific CPU