sched/core: Force proper alignment of 'struct util_est'

For some as yet not understood reason, Tony gets unaligned access
traps on IA64 because of:

  struct util_est ue = READ_ONCE(p->se.avg.util_est);

and:

  WRITE_ONCE(p->se.avg.util_est, ue);

introduced by commit:

  d519329 ("sched/fair: Update util_est only on util_avg updates")

Normally those two fields should end up on an 8-byte aligned location,
but UP and RANDSTRUCT can mess that up so enforce the alignment
explicitly.

Also make the alignment on sched_avg unconditional, as it is really
about data locality, not false-sharing.

With or without this patch the layout for sched_avg on a
ia64-defconfig build looks like:

	$ pahole -EC sched_avg ia64-defconfig/kernel/sched/core.o
	die__process_function: tag not supported (INVALID)!
	struct sched_avg {
		/* typedef u64 */ long long unsigned int     last_update_time;                   /*     0     8 */
		/* typedef u64 */ long long unsigned int     load_sum;                           /*     8     8 */
		/* typedef u64 */ long long unsigned int     runnable_load_sum;                  /*    16     8 */
		/* typedef u32 */ unsigned int               util_sum;                           /*    24     4 */
		/* typedef u32 */ unsigned int               period_contrib;                     /*    28     4 */
		long unsigned int          load_avg;                                             /*    32     8 */
		long unsigned int          runnable_load_avg;                                    /*    40     8 */
		long unsigned int          util_avg;                                             /*    48     8 */
		struct util_est {
			unsigned int       enqueued;                                             /*    56     4 */
			unsigned int       ewma;                                                 /*    60     4 */
		} util_est; /*    56     8 */
		/* --- cacheline 1 boundary (64 bytes) --- */

		/* size: 64, cachelines: 1, members: 9 */
	};

Reported-and-Tested-by: Tony Luck <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Norbert Manthey <[email protected]>
Cc: Patrick Bellasi <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tony <[email protected]>
Cc: Vincent Guittot <[email protected]>
Fixes: d519329 ("sched/fair: Update util_est only on util_avg updates")
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: Peter Zijlstra

include/linux/sched.h

@@ -300,7 +300,7 @@ struct util_est {
 	unsigned int			enqueued;
 	unsigned int			ewma;
 #define UTIL_EST_WEIGHT_SHIFT		2
-};
+} __attribute__((__aligned__(sizeof(u64))));
 
 /*
  * The load_avg/util_avg accumulates an infinite geometric series
@@ -364,7 +364,7 @@ struct sched_avg {
 	unsigned long			runnable_load_avg;
 	unsigned long			util_avg;
 	struct util_est			util_est;
-};
+} ____cacheline_aligned;
 
 struct sched_statistics {
 #ifdef CONFIG_SCHEDSTATS
@@ -435,7 +435,7 @@ struct sched_entity {
 	 * Put into separate cache line so it does not
 	 * collide with read-mostly values above.
 	 */
-	struct sched_avg		avg ____cacheline_aligned_in_smp;
+	struct sched_avg		avg;
 #endif
 };