[PATCH v6 2/4] powerpc/64: enhance memcmp() with VMX instruction for long bytes comparision

[Michael Ellerman]

Hi Simon,

wei.guo.simon at gmail.com writes:
> diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S
> index f20e883..4ba7bb6 100644
> --- a/arch/powerpc/lib/memcmp_64.S
> +++ b/arch/powerpc/lib/memcmp_64.S
> @@ -174,6 +235,13 @@ _GLOBAL(memcmp)
>  	blr
>  
>  .Llong:
> +#ifdef CONFIG_ALTIVEC
> +	/* Try to use vmx loop if length is equal or greater than 4K */
> +	cmpldi  cr6,r5,VMX_THRESH
> +	bge	cr6,.Lsameoffset_vmx_cmp
> +

Here we decide to use vmx, but we don't do any CPU feature checks.


> @@ -332,7 +400,94 @@ _GLOBAL(memcmp)
>  8:
>  	blr
>  
> +#ifdef CONFIG_ALTIVEC
> +.Lsameoffset_vmx_cmp:
> +	/* Enter with src/dst addrs has the same offset with 8 bytes
> +	 * align boundary
> +	 */
> +	ENTER_VMX_OPS
> +	beq     cr1,.Llong_novmx_cmp
> +
> +3:
> +	/* need to check whether r4 has the same offset with r3
> +	 * for 16 bytes boundary.
> +	 */
> +	xor	r0,r3,r4
> +	andi.	r0,r0,0xf
> +	bne	.Ldiffoffset_vmx_cmp_start
> +
> +	/* len is no less than 4KB. Need to align with 16 bytes further.
> +	 */
> +	andi.	rA,r3,8
> +	LD	rA,0,r3
> +	beq	4f
> +	LD	rB,0,r4
> +	cmpld	cr0,rA,rB
> +	addi	r3,r3,8
> +	addi	r4,r4,8
> +	addi	r5,r5,-8
> +
> +	beq	cr0,4f
> +	/* save and restore cr0 */
> +	mfocrf  r5,64
> +	EXIT_VMX_OPS
> +	mtocrf	64,r5
> +	b	.LcmpAB_lightweight
> +
> +4:
> +	/* compare 32 bytes for each loop */
> +	srdi	r0,r5,5
> +	mtctr	r0
> +	clrldi  r5,r5,59
> +	li	off16,16
> +
> +.balign 16
> +5:
> +	lvx 	v0,0,r3
> +	lvx 	v1,0,r4
> +	vcmpequd. v0,v0,v1

vcmpequd is only available on Power8 and later CPUs.

Which means this will crash on Power7 or earlier.

Something like this should fix it I think.

diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S
index 96eb08b2be2e..0a11ff14dcd9 100644
--- a/arch/powerpc/lib/memcmp_64.S
+++ b/arch/powerpc/lib/memcmp_64.S
@@ -236,9 +236,11 @@ _GLOBAL(memcmp)
 
 .Llong:
 #ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
 	/* Try to use vmx loop if length is equal or greater than 4K */
 	cmpldi  cr6,r5,VMX_THRESH
 	bge	cr6,.Lsameoffset_vmx_cmp
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 .Llong_novmx_cmp:
 #endif


There's another problem which is that old toolchains don't know about
vcmpequd. To fix that we'll need to add a macro that uses .long to
construct the instruction.

cheers