| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <2d69e667531e7bd5b4a6953f129143900e67e8df.1531511429.git.christophe.leroy@c-s.fr>
Date: Wed, 1 Aug 2018 09:01:14 +0000 (UTC)
From: Christophe Leroy <christophe.leroy@....fr>
To: Benjamin Herrenschmidt <benh@...nel.crashing.org>,
Paul Mackerras <paulus@...ba.org>,
Michael Ellerman <mpe@...erman.id.au>, wei.guo.simon@...il.com,
segher@...nel.crashing.org
Cc: linux-kernel@...r.kernel.org, linuxppc-dev@...ts.ozlabs.org
Subject: [PATCH v8 3/4] powerpc/lib: implement strlen() in assembly for PPC32
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@....fr>
---
Changes in 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
Powered by blists - more mailing lists