* [PATCH v9 2/4] selftests/powerpc: Add test for strlen()
2018-08-02 8:26 [PATCH v9 1/4] selftests/powerpc: add test for 32 bits memcmp Christophe Leroy
@ 2018-08-02 8:26 ` Christophe Leroy
2018-08-02 8:26 ` [PATCH v9 3/4] powerpc/lib: implement strlen() in assembly for PPC32 Christophe Leroy
2018-08-02 8:26 ` [PATCH v9 4/4] selftests/powerpc: update strlen() test to test the new assembly function " Christophe Leroy
2 siblings, 0 replies; 4+ messages in thread
From: Christophe Leroy @ 2018-08-02 8:26 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
wei.guo.simon, segher
Cc: linux-kernel, linuxppc-dev
This patch adds a test for strlen()
string.c contains a copy of strlen() from lib/string.c
The test first tests the correctness of strlen() by comparing
the result with libc strlen(). It tests all cases of alignment.
It them tests the duration of an aligned strlen() on a 4 bytes string,
on a 16 bytes string and on a 256 bytes string.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v9: fixed relevant checkpatch warnings
v8: no change
v7: no change
v6: refactorised the benchmark test
v5: no change
v4: new
.../testing/selftests/powerpc/stringloops/Makefile | 5 +-
.../testing/selftests/powerpc/stringloops/string.c | 37 ++++++
.../testing/selftests/powerpc/stringloops/strlen.c | 131 +++++++++++++++++++++
3 files changed, 172 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/powerpc/stringloops/string.c
create mode 100644 tools/testing/selftests/powerpc/stringloops/strlen.c
diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
index 3862256c2b7d..779b644461c4 100644
--- a/tools/testing/selftests/powerpc/stringloops/Makefile
+++ b/tools/testing/selftests/powerpc/stringloops/Makefile
@@ -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
diff --git a/tools/testing/selftests/powerpc/stringloops/string.c b/tools/testing/selftests/powerpc/stringloops/string.c
new file mode 100644
index 000000000000..9dac5ef4f52c
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/string.c
@@ -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;
+}
diff --git a/tools/testing/selftests/powerpc/stringloops/strlen.c b/tools/testing/selftests/powerpc/stringloops/strlen.c
new file mode 100644
index 000000000000..7ea6122ecacb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/strlen.c
@@ -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");
+}
--
2.13.3
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH v9 3/4] powerpc/lib: implement strlen() in assembly for PPC32
2018-08-02 8:26 [PATCH v9 1/4] selftests/powerpc: add test for 32 bits memcmp Christophe Leroy
2018-08-02 8:26 ` [PATCH v9 2/4] selftests/powerpc: Add test for strlen() Christophe Leroy
@ 2018-08-02 8:26 ` Christophe Leroy
2018-08-02 8:26 ` [PATCH v9 4/4] selftests/powerpc: update strlen() test to test the new assembly function " Christophe Leroy
2 siblings, 0 replies; 4+ messages in thread
From: Christophe Leroy @ 2018-08-02 8:26 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
wei.guo.simon, segher
Cc: linux-kernel, linuxppc-dev
The generic implementation of strlen() reads strings byte per byte.
This patch implements strlen() in assembly based on a read of entire
words, in the same spirit as what some other arches and glibc do.
On a 8xx the time spent in strlen is reduced by 3/4 for long strings.
strlen() selftest on an 8xx provides the following values:
Before the patch (ie with the generic strlen() in lib/string.c):
len 256 : time = 1.195055
len 016 : time = 0.083745
len 008 : time = 0.046828
len 004 : time = 0.028390
After the patch:
len 256 : time = 0.272185 ==> 78% improvment
len 016 : time = 0.040632 ==> 51% improvment
len 008 : time = 0.033060 ==> 29% improvment
len 004 : time = 0.029149 ==> 2% degradation
On a 832x:
Before the patch:
len 256 : time = 0.236125
len 016 : time = 0.018136
len 008 : time = 0.011000
len 004 : time = 0.007229
After the patch:
len 256 : time = 0.094950 ==> 60% improvment
len 016 : time = 0.013357 ==> 26% improvment
len 008 : time = 0.010586 ==> 4% improvment
len 004 : time = 0.008784
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
Changes in v9 and v8:
- No change
Changes in v7:
- Reduced the scope to PPC32
- Modified the missalignment handling to be branchless and loopless
Changes in v6:
- Reworked for having branchless conclusion
Changes in v5:
- Fixed for PPC64 LITTLE ENDIAN
Changes in v4:
- Added alignment of the loop
- doing the andc only if still not 0 as it happends only for bytes above 0x7f which is pretty rare in a string
Changes in v3:
- Made it common to PPC32 and PPC64
Changes in v2:
- Moved handling of unaligned strings outside of the main path as it is very unlikely.
- Removed the verification of the fourth byte in case none of the three first ones are NUL.
arch/powerpc/include/asm/string.h | 2 +
arch/powerpc/lib/Makefile | 2 +-
arch/powerpc/lib/strlen_32.S | 78 +++++++++++++++++++++++++++++++++++++++
3 files changed, 81 insertions(+), 1 deletion(-)
create mode 100644 arch/powerpc/lib/strlen_32.S
diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index 9b8cedf618f4..1647de15a31e 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -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__ */
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index d0ca13ad8231..670286808928 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -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),
diff --git a/arch/powerpc/lib/strlen_32.S b/arch/powerpc/lib/strlen_32.S
new file mode 100644
index 000000000000..0a8d3f64d493
--- /dev/null
+++ b/arch/powerpc/lib/strlen_32.S
@@ -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)
--
2.13.3
^ permalink raw reply related [flat|nested] 4+ messages in thread