summaryrefslogtreecommitdiffstats
path: root/arch/x86/lib
diff options
context:
space:
mode:
authorAlexey Dobriyan <adobriyan@gmail.com>2011-12-11 21:13:19 +0300
committerIngo Molnar <mingo@elte.hu>2011-12-12 18:33:42 +0100
commit890890cb8e415e1e7a61bfe3c8e246f710196824 (patch)
treea4694f6470484ebac1d82ed317fa5ce5c198006e /arch/x86/lib
parent79f1ddd06471b094ae30eb17b33beb9f1234ca93 (diff)
downloadop-kernel-dev-890890cb8e415e1e7a61bfe3c8e246f710196824.zip
op-kernel-dev-890890cb8e415e1e7a61bfe3c8e246f710196824.tar.gz
x86/i386: Use less assembly in strlen(), speed things up a bit
Current i386 strlen() hardcodes NOT/DEC sequence. DEC is mentioned to be suboptimal on Core2. So, put only REPNE SCASB sequence in assembly, compiler can do the rest. The difference in generated code is like below (MCORE2=y): <strlen>: push %edi mov $0xffffffff,%ecx mov %eax,%edi xor %eax,%eax repnz scas %es:(%edi),%al not %ecx - dec %ecx - mov %ecx,%eax + lea -0x1(%ecx),%eax pop %edi ret Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Beulich <JBeulich@suse.com> Link: http://lkml.kernel.org/r/20111211181319.GA17097@p183.telecom.by Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86/lib')
-rw-r--r--arch/x86/lib/string_32.c8
1 files changed, 3 insertions, 5 deletions
diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c
index 82004d2..bd59090 100644
--- a/arch/x86/lib/string_32.c
+++ b/arch/x86/lib/string_32.c
@@ -164,15 +164,13 @@ EXPORT_SYMBOL(strchr);
size_t strlen(const char *s)
{
int d0;
- int res;
+ size_t res;
asm volatile("repne\n\t"
- "scasb\n\t"
- "notl %0\n\t"
- "decl %0"
+ "scasb"
: "=c" (res), "=&D" (d0)
: "1" (s), "a" (0), "0" (0xffffffffu)
: "memory");
- return res;
+ return ~res - 1;
}
EXPORT_SYMBOL(strlen);
#endif
OpenPOWER on IntegriCloud