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>

diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c
index 82004d2bf05e160bfa6faf15745f38eb4ad89f46..bd59090825dbabb96821c30c498d18cf2220857a 100644 (file)
--- 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