ARM: Factor out common code from cpu_proc_fin()

All implementations of cpu_proc_fin() start by disabling interrupts
and then flush caches.  Rather than have every processors proc_fin()
implementation do this, move it out into generic code - and move the
cache flush past setup_mm_for_reboot() (so it can benefit from having
caches still enabled.)

This allows cpu_proc_fin() to become independent of the L1/L2 cache
types, and eventually move the L2 cache flushing into the L2 support
code.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 63037e2..1407597 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -124,15 +124,11 @@
  * cpu_xscale_proc_fin()
  */
 ENTRY(cpu_xscale_proc_fin)
-	str	lr, [sp, #-4]!
-	mov	r0, #PSR_F_BIT|PSR_I_BIT|SVC_MODE
-	msr	cpsr_c, r0
-	bl	xscale_flush_kern_cache_all	@ clean caches
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1800			@ ...IZ...........
 	bic	r0, r0, #0x0006			@ .............CA.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldr	pc, [sp], #4
+	mov	pc, lr
 
 /*
  * cpu_xscale_reset(loc)