powerpc/lib: Adjust .balign inside string functions for PPC32

commit 87a156fb18fe1 ("Align hot loops of some string functions")
degraded the performance of string functions by adding useless
nops

A simple benchmark on an 8xx calling 100000x a memchr() that
matches the first byte runs in 41668 TB ticks before this patch
and in 35986 TB ticks after this patch. So this gives an
improvement of approx 10%

Another benchmark doing the same with a memchr() matching the 128th
byte runs in 1011365 TB ticks before this patch and 1005682 TB ticks
after this patch, so regardless on the number of loops, removing
those useless nops improves the test by 5683 TB ticks.

Fixes: 87a156fb18fe1 ("Align hot loops of some string functions")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/cache.h

@@ -9,11 +9,14 @@
 #if defined(CONFIG_PPC_8xx) || defined(CONFIG_403GCX)
 #define L1_CACHE_SHIFT		4
 #define MAX_COPY_PREFETCH	1
+#define IFETCH_ALIGN_SHIFT	2
 #elif defined(CONFIG_PPC_E500MC)
 #define L1_CACHE_SHIFT		6
 #define MAX_COPY_PREFETCH	4
+#define IFETCH_ALIGN_SHIFT	3
 #elif defined(CONFIG_PPC32)
 #define MAX_COPY_PREFETCH	4
+#define IFETCH_ALIGN_SHIFT	3	/* 603 fetches 2 insn at a time */
 #if defined(CONFIG_PPC_47x)
 #define L1_CACHE_SHIFT		7
 #else

arch/powerpc/lib/string.S

@@ -12,6 +12,7 @@
 #include <asm/errno.h>
 #include <asm/ppc_asm.h>
 #include <asm/export.h>
+#include <asm/cache.h>
 
 	.text
 	
@@ -23,7 +24,7 @@ _GLOBAL(strncpy)
 	mtctr	r5
 	addi	r6,r3,-1
 	addi	r4,r4,-1
-	.balign 16
+	.balign IFETCH_ALIGN_BYTES
 1:	lbzu	r0,1(r4)
 	cmpwi	0,r0,0
 	stbu	r0,1(r6)
@@ -43,7 +44,7 @@ _GLOBAL(strncmp)
 	mtctr	r5
 	addi	r5,r3,-1
 	addi	r4,r4,-1
-	.balign 16
+	.balign IFETCH_ALIGN_BYTES
 1:	lbzu	r3,1(r5)
 	cmpwi	1,r3,0
 	lbzu	r0,1(r4)
@@ -77,7 +78,7 @@ _GLOBAL(memchr)
 	beq-	2f
 	mtctr	r5
 	addi	r3,r3,-1
-	.balign 16
+	.balign IFETCH_ALIGN_BYTES
 1:	lbzu	r0,1(r3)
 	cmpw	0,r0,r4
 	bdnzf	2,1b