[RFC PATCH 1/3] powerpc/lib: implement strlen() in assembly for PPC64
Christophe Leroy
christophe.leroy at c-s.fr
Thu Jul 5 18:53:57 AEST 2018
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.
strlen() selftest on an XXXXXXXX provides the following values:
Before the patch (ie with the generic strlen() in lib/string.c):
After the patch:
Signed-off-by: Christophe Leroy <christophe.leroy at c-s.fr>
---
This serie applies on top of the PPC32 strlen optimisation serie
Untested
arch/powerpc/include/asm/string.h | 3 +-
arch/powerpc/lib/Makefile | 4 +-
arch/powerpc/lib/strlen_64.S | 88 +++++++++++++++++++++++++++++++++++++++
3 files changed, 91 insertions(+), 4 deletions(-)
create mode 100644 arch/powerpc/lib/strlen_64.S
diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index 1647de15a31e..8fdcb532de72 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -13,6 +13,7 @@
#define __HAVE_ARCH_MEMCHR
#define __HAVE_ARCH_MEMSET16
#define __HAVE_ARCH_MEMCPY_FLUSHCACHE
+#define __HAVE_ARCH_STRLEN
extern char * strcpy(char *,const char *);
extern char * strncpy(char *,const char *, __kernel_size_t);
@@ -50,8 +51,6 @@ 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 670286808928..93706b4cdbde 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 strlen_32.o
+obj-$(CONFIG_PPC32) += div64.o copy_32.o crtsavres.o
# See corresponding test in arch/powerpc/Makefile
# 64-bit linker creates .sfpr on demand for final link (vmlinux),
@@ -33,7 +33,7 @@ obj64-$(CONFIG_ALTIVEC) += vmx-helper.o
obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
obj-y += checksum_$(BITS).o checksum_wrappers.o \
- string_$(BITS).o memcmp_$(BITS).o
+ string_$(BITS).o memcmp_$(BITS).o strlen_$(BITS).o
obj-y += sstep.o ldstfp.o quad.o
obj64-y += quad.o
diff --git a/arch/powerpc/lib/strlen_64.S b/arch/powerpc/lib/strlen_64.S
new file mode 100644
index 000000000000..c9704f2b697d
--- /dev/null
+++ b/arch/powerpc/lib/strlen_64.S
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * strlen() for PPC64
+ *
+ * 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, 7
+ lis r7, 0x0101
+ addi r10, r3, -8
+ addic r7, r7, 0x0101 /* r7 = 0x01010101 (lomagic) & clear XER[CA] */
+ rldimi r7, r7, 32, 0 /* r7 = 0x0101010101010101 (lomagic) */
+ rotldi r6, r7, 31 /* r6 = 0x8080808080808080 (himagic) */
+ bne- 3f
+ .balign IFETCH_ALIGN_BYTES
+1: ldu r9, 8(r10)
+2: subf r8, r7, r9
+ andc r11, r6, r9
+ and. r8, r8, r11
+ beq+ 1b
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ andc r8, r9, r6
+ orc r9, r9, r6
+ subfe r8, r6, r8
+ nor r8, r8, r9
+ cntlzd r8, r8
+ subf r3, r3, r10
+ srdi r8, r8, 3
+ add r3, r3, r8
+#else
+ addi r9, r8, -1
+ addi r10, r10, 7
+ andc r8, r9, r8
+ cntlzd r8, r8
+ subf r3, r3, r10
+ srdi r8, r8, 3
+ subf r3, r8, r3
+#endif
+ blr
+
+ /* Missaligned string: make sure bytes before string are seen not 0 */
+3: xor r10, r10, r0
+ orc r8, r8, r8
+ ldu r9, 8(r10)
+ slwi r0, r0, 3
+ srw r8, r8, r0
+ orc r9, r9, r8
+ b 2b
+EXPORT_SYMBOL(strlen)
--
2.13.3
More information about the Linuxppc-dev
mailing list