ARM: 7953/1: mm: ensure TLB invalidation is complete before enabling MMU

During __v{6,7}_setup, we invalidate the TLBs since we are about to
enable the MMU on return to head.S. Unfortunately, without a subsequent
dsb instruction, the invalidation is not guaranteed to have completed by
the time we write to the sctlr, potentially exposing us to junk/stale
translations cached in the TLB.

This patch reworks the init functions so that the dsb used to ensure
completion of cache/predictor maintenance is also used to ensure
completion of the TLB invalidation.

Cc: <stable@vger.kernel.org>
Reported-by: NAlbin Tonnerre <Albin.Tonnerre@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

arch/arm/mm/proc-v6.S

@@ -208,7 +208,6 @@ __v6_setup:
 	mcr	p15, 0, r0, c7, c14, 0		@ clean+invalidate D cache
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
 	mcr	p15, 0, r0, c7, c15, 0		@ clean+invalidate cache
-	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r0, c8, c7, 0		@ invalidate I + D TLBs
 	mcr	p15, 0, r0, c2, c0, 2		@ TTB control register
@@ -218,6 +217,8 @@ __v6_setup:
 	ALT_UP(orr	r8, r8, #TTB_FLAGS_UP)
 	mcr	p15, 0, r8, c2, c0, 1		@ load TTB1
 #endif /* CONFIG_MMU */
+	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer and
+						@ complete invalidations
 	adr	r5, v6_crval
 	ldmia	r5, {r5, r6}
  ARM_BE8(orr	r6, r6, #1 << 25)		@ big-endian page tables

arch/arm/mm/proc-v7.S

@@ -351,7 +351,6 @@ __v7_setup:
 
 4:	mov	r10, #0
 	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
-	dsb
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r10, c8, c7, 0		@ invalidate I + D TLBs
 	v7_ttb_setup r10, r4, r8, r5		@ TTBCR, TTBRx setup
@@ -360,6 +359,7 @@ __v7_setup:
 	mcr	p15, 0, r5, c10, c2, 0		@ write PRRR
 	mcr	p15, 0, r6, c10, c2, 1		@ write NMRR
 #endif
+	dsb					@ Complete invalidations
 #ifndef CONFIG_ARM_THUMBEE
 	mrc	p15, 0, r0, c0, c1, 0		@ read ID_PFR0 for ThumbEE
 	and	r0, r0, #(0xf << 12)		@ ThumbEE enabled field