[PATCH v9 1/4] selftests/powerpc: add test for 32 bits memcmp

@@ -1,10 +1,18 @@
 # SPDX-License-Identifier: GPL-2.0
 # The loops are all 64-bit code
-CFLAGS += -m64 -maltivec
 CFLAGS += -I$(CURDIR)
 
-TEST_GEN_PROGS := memcmp
-EXTRA_SOURCES := memcmp_64.S ../harness.c
+EXTRA_SOURCES := ../harness.c
+
+$(OUTPUT)/memcmp_64: memcmp.c
+$(OUTPUT)/memcmp_64: CFLAGS += -m64 -maltivec
+
+$(OUTPUT)/memcmp_32: memcmp.c
+$(OUTPUT)/memcmp_32: CFLAGS += -m32
+
+ASFLAGS = $(CFLAGS)
+
+TEST_GEN_PROGS := memcmp_32 memcmp_64
 
 include ../../lib.mk
 

@@ -0,0 +1 @@
+../../../../../arch/powerpc/lib/memcmp_32.S

@@ -10,9 +10,12 @@ $(OUTPUT)/memcmp_64: CFLAGS += -m64 -maltivec
 $(OUTPUT)/memcmp_32: memcmp.c
 $(OUTPUT)/memcmp_32: CFLAGS += -m32
 
+$(OUTPUT)/strlen: strlen.c string.o
+$(OUTPUT)/string.o: string.c
+
 ASFLAGS = $(CFLAGS)
 
-TEST_GEN_PROGS := memcmp_32 memcmp_64
+TEST_GEN_PROGS := memcmp_32 memcmp_64 strlen
 
 include ../../lib.mk
 

@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/lib/string.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+/*
+ * stupid library routines.. The optimized versions should generally be found
+ * as inline code in <asm-xx/string.h>
+ *
+ * These are buggy as well..
+ *
+ * * Fri Jun 25 1999, Ingo Oeser <ioe@informatik.tu-chemnitz.de>
+ * -  Added strsep() which will replace strtok() soon (because strsep() is
+ *    reentrant and should be faster). Use only strsep() in new code, please.
+ *
+ * * Sat Feb 09 2002, Jason Thomas <jason@topic.com.au>,
+ *                    Matthew Hawkins <matt@mh.dropbear.id.au>
+ * -  Kissed strtok() goodbye
+ */
+
+#include <stddef.h>
+
+/**
+ * strlen - Find the length of a string
+ * @s: The string to be sized
+ */
+size_t test_strlen(const char *s)
+{
+	const char *sc;
+
+	for (sc = s; *sc != '\0'; ++sc)
+		; /* nothing */
+
+	return sc - s;
+}

@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <malloc.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include "utils.h"
+
+#define SIZE 256
+#define ITERATIONS 1000
+#define ITERATIONS_BENCH 100000
+
+int test_strlen(const void *s);
+
+/* test all offsets and lengths */
+static void test_one(char *s)
+{
+	unsigned long offset;
+
+	for (offset = 0; offset < SIZE; offset++) {
+		int x, y;
+		unsigned long i;
+
+		y = strlen(s + offset);
+		x = test_strlen(s + offset);
+
+		if (x == y)
+			continue;
+
+		printf("strlen() returned %d, should have returned %d (%p offset %ld)\n",
+		       x, y, s, offset);
+
+		for (i = offset; i < SIZE; i++)
+			printf("%02x ", s[i]);
+		printf("\n");
+	}
+}
+
+static void bench_test(char *s)
+{
+	struct timespec ts_start, ts_end;
+	int i;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts_start);
+
+	for (i = 0; i < ITERATIONS_BENCH; i++)
+		test_strlen(s);
+
+	clock_gettime(CLOCK_MONOTONIC, &ts_end);
+
+	printf("len %3.3d : time = %.6f\n", test_strlen(s),
+	       ts_end.tv_sec - ts_start.tv_sec +
+	       (ts_end.tv_nsec - ts_start.tv_nsec) / 1e9);
+}
+
+static int testcase(void)
+{
+	char *s;
+	unsigned long i;
+
+	s = memalign(128, SIZE);
+	if (!s) {
+		perror("memalign");
+		exit(1);
+	}
+
+	srandom(1);
+
+	memset(s, 0, SIZE);
+	for (i = 0; i < SIZE; i++) {
+		char c;
+
+		do {
+			c = random() & 0x7f;
+		} while (!c);
+		s[i] = c;
+		test_one(s);
+	}
+
+	for (i = 0; i < ITERATIONS; i++) {
+		unsigned long j;
+
+		for (j = 0; j < SIZE; j++) {
+			char c;
+
+			do {
+				c = random() & 0x7f;
+			} while (!c);
+			s[j] = c;
+		}
+		for (j = 0; j < sizeof(long); j++) {
+			s[SIZE - 1 - j] = 0;
+			test_one(s);
+		}
+	}
+
+	for (i = 0; i < SIZE; i++) {
+		char c;
+
+		do {
+			c = random() & 0x7f;
+		} while (!c);
+		s[i] = c;
+	}
+
+	bench_test(s);
+
+	s[16] = 0;
+	bench_test(s);
+
+	s[8] = 0;
+	bench_test(s);
+
+	s[4] = 0;
+	bench_test(s);
+
+	s[3] = 0;
+	bench_test(s);
+
+	s[2] = 0;
+	bench_test(s);
+
+	s[1] = 0;
+	bench_test(s);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(testcase, "strlen");
+}

@@ -50,6 +50,8 @@ static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n)
 	return __memset64(p, v, n * 8);
 }
 #else
+#define __HAVE_ARCH_STRLEN
+
 extern void *memset16(uint16_t *, uint16_t, __kernel_size_t);
 #endif
 #endif /* __KERNEL__ */

@@ -12,7 +12,7 @@ CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE)
 
 obj-y += string.o alloc.o code-patching.o feature-fixups.o
 
-obj-$(CONFIG_PPC32)	+= div64.o copy_32.o crtsavres.o
+obj-$(CONFIG_PPC32)	+= div64.o copy_32.o crtsavres.o strlen_32.o
 
 # See corresponding test in arch/powerpc/Makefile
 # 64-bit linker creates .sfpr on demand for final link (vmlinux),

@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * strlen() for PPC32
+ *
+ * Copyright (C) 2018 Christophe Leroy CS Systemes d'Information.
+ *
+ * Inspired from glibc implementation
+ */
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+#include <asm/cache.h>
+
+	.text
+
+/*
+ * Algorithm:
+ *
+ * 1) Given a word 'x', we can test to see if it contains any 0 bytes
+ *    by subtracting 0x01010101, and seeing if any of the high bits of each
+ *    byte changed from 0 to 1. This works because the least significant
+ *    0 byte must have had no incoming carry (otherwise it's not the least
+ *    significant), so it is 0x00 - 0x01 == 0xff. For all other
+ *    byte values, either they have the high bit set initially, or when
+ *    1 is subtracted you get a value in the range 0x00-0x7f, none of which
+ *    have their high bit set. The expression here is
+ *    (x - 0x01010101) & ~x & 0x80808080), which gives 0x00000000 when
+ *    there were no 0x00 bytes in the word.  You get 0x80 in bytes that
+ *    match, but possibly false 0x80 matches in the next more significant
+ *    byte to a true match due to carries.  For little-endian this is
+ *    of no consequence since the least significant match is the one
+ *    we're interested in, but big-endian needs method 2 to find which
+ *    byte matches.
+ * 2) Given a word 'x', we can test to see _which_ byte was zero by
+ *    calculating ~(((x & ~0x80808080) - 0x80808080 - 1) | x | ~0x80808080).
+ *    This produces 0x80 in each byte that was zero, and 0x00 in all
+ *    the other bytes. The '| ~0x80808080' clears the low 7 bits in each
+ *    byte, and the '| x' part ensures that bytes with the high bit set
+ *    produce 0x00. The addition will carry into the high bit of each byte
+ *    iff that byte had one of its low 7 bits set. We can then just see
+ *    which was the most significant bit set and divide by 8 to find how
+ *    many to add to the index.
+ *    This is from the book 'The PowerPC Compiler Writer's Guide',
+ *    by Steve Hoxey, Faraydon Karim, Bill Hay and Hank Warren.
+ */
+
+_GLOBAL(strlen)
+	andi.   r0, r3, 3
+	lis	r7, 0x0101
+	addi	r10, r3, -4
+	addic	r7, r7, 0x0101	/* r7 = 0x01010101 (lomagic) & clear XER[CA] */
+	rotlwi	r6, r7, 31 	/* r6 = 0x80808080 (himagic) */
+	bne-	3f
+	.balign IFETCH_ALIGN_BYTES
+1:	lwzu	r9, 4(r10)
+2:	subf	r8, r7, r9
+	and.	r8, r8, r6
+	beq+	1b
+	andc.	r8, r8, r9
+	beq+	1b
+	andc	r8, r9, r6
+	orc	r9, r9, r6
+	subfe	r8, r6, r8
+	nor	r8, r8, r9
+	cntlzw	r8, r8
+	subf	r3, r3, r10
+	srwi	r8, r8, 3
+	add	r3, r3, r8
+	blr
+
+	/* Missaligned string: make sure bytes before string are seen not 0 */
+3:	xor	r10, r10, r0
+	orc	r8, r8, r8
+	lwzu	r9, 4(r10)
+	slwi	r0, r0, 3
+	srw	r8, r8, r0
+	orc	r9, r9, r8
+	b	2b
+EXPORT_SYMBOL(strlen)

@@ -13,9 +13,12 @@ $(OUTPUT)/memcmp_32: CFLAGS += -m32
 $(OUTPUT)/strlen: strlen.c string.o
 $(OUTPUT)/string.o: string.c
 
+$(OUTPUT)/strlen_32: strlen.c
+$(OUTPUT)/strlen_32: CFLAGS += -m32
+
 ASFLAGS = $(CFLAGS)
 
-TEST_GEN_PROGS := memcmp_32 memcmp_64 strlen
+TEST_GEN_PROGS := memcmp_32 memcmp_64 strlen strlen_32
 
 include ../../lib.mk
 

@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define	IFETCH_ALIGN_BYTES 4

@@ -0,0 +1 @@
+../../../../../arch/powerpc/lib/strlen_32.S