[S390] mutex: Introduce arch_mutex_cpu_relax()

The spinning mutex implementation uses cpu_relax() in busy loops as a
compiler barrier. Depending on the architecture, cpu_relax() may do more
than needed in this specific mutex spin loops. On System z we also give
up the time slice of the virtual cpu in cpu_relax(), which prevents
effective spinning on the mutex.

This patch replaces cpu_relax() in the spinning mutex code with
arch_mutex_cpu_relax(), which can be defined by each architecture that
selects HAVE_ARCH_MUTEX_CPU_RELAX. The default is still cpu_relax(), so
this patch should not affect other architectures than System z for now.

Signed-off-by: Gerald Schaefer <[e-mail]>
Signed-off-by: Peter Zijlstra <[e-mail]>
LKML-Reference: <1290437256.7455.4.camel@thinkpad>
Signed-off-by: Ingo Molnar <[e-mail]>

arch/Kconfig

···
 config HAVE_ARCH_JUMP_LABEL
 	bool
 
+config HAVE_ARCH_MUTEX_CPU_RELAX
+	bool
+
 source "kernel/gcov/Kconfig"

arch/s390/Kconfig

···
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
 	select HAVE_GET_USER_PAGES_FAST
+	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select ARCH_INLINE_SPIN_TRYLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK_BH
 	select ARCH_INLINE_SPIN_LOCK

arch/s390/include/asm/mutex.h

···
  */
 
 #include <asm-generic/mutex-dec.h>
+
+#define arch_mutex_cpu_relax()	barrier()

include/linux/mutex.h

···
 extern void mutex_unlock(struct mutex *lock);
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
+#ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX
+#define arch_mutex_cpu_relax()	cpu_relax()
+#endif
+
 #endif

kernel/mutex.c

···
 		 * memory barriers as we'll eventually observe the right
 		 * values at the cost of a few extra spins.
 		 */
-		cpu_relax();
+		arch_mutex_cpu_relax();
 	}
 #endif
 	spin_lock_mutex(&lock->wait_lock, flags);

kernel/sched.c

···
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
+#include <asm/mutex.h>
 
 #include "sched_cpupri.h"
 #include "workqueue_sched.h"
···
 		if (task_thread_info(rq->curr) != owner || need_resched())
 			return 0;
 
-		cpu_relax();
+		arch_mutex_cpu_relax();
 	}
 
 	return 1;