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-arm1020.S b/arch/arm/mm/proc-arm1020.S
index 72507c6..203a4e9 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -79,15 +79,11 @@
  * cpu_arm1020_proc_fin()
  */
 ENTRY(cpu_arm1020_proc_fin)
-	stmfd	sp!, {lr}
-	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-	msr	cpsr_c, ip
-	bl	arm1020_flush_kern_cache_all
 	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
 	bic	r0, r0, #0x1000 		@ ...i............
 	bic	r0, r0, #0x000e 		@ ............wca.
 	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
-	ldmfd	sp!, {pc}
+	mov	pc, lr
 
 /*
  * cpu_arm1020_reset(loc)