ARMv7: Add extra barriers for flush_cache_all compressed/head.S

The flush_cache_all function on ARMv7 is implemented as a series of
cache operations by set/way. These are not guaranteed to be ordered with
previous memory accesses, requiring a DMB. This patch also adds barriers
for the TLB operations in compressed/head.S

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm/mm/cache-v7.S

@@ -26,6 +26,7 @@
  *	- mm    - mm_struct describing address space
  */
 ENTRY(v7_flush_dcache_all)
+	dmb					@ ensure ordering with previous memory accesses
 	mrc	p15, 1, r0, c0, c0, 1		@ read clidr
 	ands	r3, r0, #0x7000000		@ extract loc from clidr
 	mov	r3, r3, lsr #23			@ left align loc bit field
@@ -64,6 +65,7 @@ skip:
 finished:
 	mov	r10, #0				@ swith back to cache level 0
 	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
+	dsb
 	isb
 	mov	pc, lr
 ENDPROC(v7_flush_dcache_all)