ARM: 7583/1: decompressor: Enable unaligned memory access for v6 and above

Modern GCC can generate code which makes use of the CPU's native
unaligned memory access capabilities.  This is useful for the C
decompressor implementations used for unpacking compressed kernels.

This patch disables alignment faults and enables the v6 unaligned
access model on CPUs which support these features (i.e., v6 and
later), allowing full unaligned access support for C code in the
decompressor.

The decompressor C code must not be built to assume that unaligned
access works if support for v5 or older platforms is included in
the kernel.

For correct code generation, C decompressor code must always use
the get_unaligned and put_unaligned accessors when dealing with
unaligned pointers, regardless of this patch.
Signed-off-by: Dave Martin <dave.martin@linaro.org>
Acked-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/boot/compressed/head.S

@@ -652,6 +652,15 @@ __setup_mmu:	sub	r3, r4, #16384		@ Page directory size
 		mov	pc, lr
 ENDPROC(__setup_mmu)
 
+@ Enable unaligned access on v6, to allow better code generation
+@ for the decompressor C code:
+__armv6_mmu_cache_on:
+		mrc	p15, 0, r0, c1, c0, 0	@ read SCTLR
+		bic	r0, r0, #2		@ A (no unaligned access fault)
+		orr	r0, r0, #1 << 22	@ U (v6 unaligned access model)
+		mcr	p15, 0, r0, c1, c0, 0	@ write SCTLR
+		b	__armv4_mmu_cache_on
+
 __arm926ejs_mmu_cache_on:
 #ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
 		mov	r0, #4			@ put dcache in WT mode
@@ -694,6 +703,9 @@ __armv7_mmu_cache_on:
 		bic	r0, r0, #1 << 28	@ clear SCTLR.TRE
 		orr	r0, r0, #0x5000		@ I-cache enable, RR cache replacement
 		orr	r0, r0, #0x003c		@ write buffer
+		bic	r0, r0, #2		@ A (no unaligned access fault)
+		orr	r0, r0, #1 << 22	@ U (v6 unaligned access model)
+						@ (needed for ARM1176)
 #ifdef CONFIG_MMU
 #ifdef CONFIG_CPU_ENDIAN_BE8
 		orr	r0, r0, #1 << 25	@ big-endian page tables
@@ -914,7 +926,7 @@ proc_types:
 
 		.word	0x0007b000		@ ARMv6
 		.word	0x000ff000
-		W(b)	__armv4_mmu_cache_on
+		W(b)	__armv6_mmu_cache_on
 		W(b)	__armv4_mmu_cache_off
 		W(b)	__armv6_mmu_cache_flush