[PATCH 4/7] ARM: cache-v7: optimise branches in v7_flush_cache_louis

[Russell King - ARM Linux]

On Thu, Apr 09, 2015 at 10:13:06AM +0200, Arnd Bergmann wrote:
> On Friday 03 April 2015 11:54:32 Russell King wrote:
> > diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
> > index 5b5d0c00bca7..793d061b4dce 100644
> > --- a/arch/arm/mm/cache-v7.S
> > +++ b/arch/arm/mm/cache-v7.S
> > @@ -93,17 +93,18 @@ ENTRY(v7_flush_dcache_louis)
> >  ALT_SMP(mov	r3, r0, lsr #20)		@ move LoUIS into position
> >  ALT_UP(	mov	r3, r0, lsr #26)		@ move LoUU into position
> >  	ands	r3, r3, #7 << 1 		@ extract LoU*2 field from clidr
> > +	bne	start_flush_levels		@ LoU != 0, start flushing
> >  #ifdef CONFIG_ARM_ERRATA_643719
> > -	ALT_SMP(mrceq	p15, 0, r2, c0, c0, 0)	@ read main ID register
> > -	ALT_UP(reteq	lr)			@ LoUU is zero, so nothing to do
> > -	movweq	r1, #:lower16:0x410fc090	@ ID of ARM Cortex A9 r0p?
> > -	movteq	r1, #:upper16:0x410fc090
> > -	biceq	r2, r2, #0x0000000f             @ clear minor revision number
> > -	teqeq	r2, r1                          @ test for errata affected core and if so...
> > -	moveqs	r3, #1 << 1			@   fix LoUIS value (and set flags state to 'ne')
> > +ALT_SMP(mrc	p15, 0, r2, c0, c0, 0)		@ read main ID register
> > +ALT_UP(	ret	lr)				@ LoUU is zero, so nothing to do
> > +	movw	r1, #:lower16:0x410fc090	@ ID of ARM Cortex A9 r0p?
> 
> With this in linux-next, I get a build failure on randconfig kernels with
> THUMB2_KERNEL enabled:
> 
> arch/arm/mm/cache-v7.S: Assembler messages:
> arch/arm/mm/cache-v7.S:99: Error: ALT_UP() content must assemble to exactly 4 bytes
> 
> Any idea for a method that will work with all combinations of SMP/UP
> and ARM/THUMB? The best I could come up with was to add an extra 'mov r0,r0',
> but that gets rather ugly as you then have to do it only for THUMB2.

How about we make ALT_UP() add the additional padding?  Something like
this maybe?

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index f67fd3afebdf..79f421796aab 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -237,6 +237,9 @@
 	.pushsection ".alt.smp.init", "a"			;\
 	.long	9998b						;\
 9997:	instr							;\
+	.if . - 9997b == 2					;\
+		nop						;\
+	.endif
 	.if . - 9997b != 4					;\
 		.error "ALT_UP() content must assemble to exactly 4 bytes";\
 	.endif							;\


-- 
FTTC broadband for 0.8mile line: currently at 10.5Mbps down 400kbps up
according to speedtest.net.