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>

arch/arm/mm/proc-arm9tdmi.S

@@ -36,8 +36,6 @@ ENTRY(cpu_arm9tdmi_switch_mm)
  * cpu_arm9tdmi_proc_fin()
  */
 ENTRY(cpu_arm9tdmi_proc_fin)
-		mov	r0, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
-		msr	cpsr_c, r0
 		mov	pc, lr
 
 /*