powerpc/lib: optimise PPC32 memcmp

At the time being, memcmp() compares two chunks of memory
byte per byte.

This patch optimises the comparison by comparing word by word.

On the same way as commit 15c2d45d ("powerpc: Add 64bit
optimised memcmp"), this patch moves memcmp() into a dedicated
file named memcmp_32.S

A small benchmark performed on an 8xx comparing two chuncks
of 512 bytes performed 100000 times gives:

Before : 5852274 TB ticks
After:   1488638 TB ticks

This is almost 4 times faster
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/lib/Makefile

@@ -26,14 +26,14 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
 			       memcpy_power7.o
 
 obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
-	   memcpy_64.o memcmp_64.o pmem.o
+	   memcpy_64.o pmem.o
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o
 obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
 
 obj-y			+= checksum_$(BITS).o checksum_wrappers.o \
-			   string_$(BITS).o
+			   string_$(BITS).o memcmp_$(BITS).o
 
 obj-y			+= sstep.o ldstfp.o quad.o
 obj64-y			+= quad.o

arch/powerpc/lib/memcmp_32.S

+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * memcmp for PowerPC32
+ *
+ * Copyright (C) 1996 Paul Mackerras.
+ *
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+
+	.text
+
+_GLOBAL(memcmp)
+	srawi.	r7, r5, 2		/* Divide len by 4 */
+	mr	r6, r3
+	beq-	3f
+	mtctr	r7
+	li	r7, 0
+1:	lwzx	r3, r6, r7
+	lwzx	r0, r4, r7
+	addi	r7, r7, 4
+	cmplw	cr0, r3, r0
+	bdnzt	eq, 1b
+	bne	5f
+3:	andi.	r3, r5, 3
+	beqlr
+	cmplwi	cr1, r3, 2
+	blt-	cr1, 4f
+	lhzx	r3, r6, r7
+	lhzx	r0, r4, r7
+	addi	r7, r7, 2
+	subf.	r3, r0, r3
+	beqlr	cr1
+	bnelr
+4:	lbzx	r3, r6, r7
+	lbzx	r0, r4, r7
+	subf.	r3, r0, r3
+	blr
+5:	li	r3, 1
+	bgtlr
+	li	r3, -1
+	blr
+EXPORT_SYMBOL(memcmp)

arch/powerpc/lib/string.S

@@ -54,23 +54,6 @@ _GLOBAL(strncmp)
 	blr
 EXPORT_SYMBOL(strncmp)
 
-#ifdef CONFIG_PPC32
-_GLOBAL(memcmp)
-	PPC_LCMPI 0,r5,0
-	beq-	2f
-	mtctr	r5
-	addi	r6,r3,-1
-	addi	r4,r4,-1
-1:	lbzu	r3,1(r6)
-	lbzu	r0,1(r4)
-	subf.	r3,r0,r3
-	bdnzt	2,1b
-	blr
-2:	li	r3,0
-	blr
-EXPORT_SYMBOL(memcmp)
-#endif
-
 _GLOBAL(memchr)
 	PPC_LCMPI 0,r5,0
 	beq-	2f