aboutsummaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorJiri Hladky <hladky.jiri@googlemail.com>2008-06-02 12:00:19 +0200
committerIngo Molnar <mingo@elte.hu>2008-06-17 10:55:47 +0200
commite01b70ef3eb3080fecc35e15f68cd274c0a48163 (patch)
tree968f1da3d1f60236df49c24943e99bbf84ce81ca /arch
parent066519068ad2fbe98c7f45552b1f592903a9c8c8 (diff)
x86: fix bug in arch/i386/lib/delay.c file, delay_loop function
when trying to understand how Bogomips are implemented I have found a bug in arch/i386/lib/delay.c file, delay_loop function. The function fails for loops > 2^31+1. It because SF is set when dec returns numbers > 2^31. The fix is to use jnz instruction instead of jns (and add one decl instruction to the end to have exactly the same number of loops as in original version). Martin Mares observed: > It is a long time since I have hacked that file, but you should definitely > make sure that the function is never called with a zero argument. In such > case, the original version made just a single pass, but your version > makes 2^32 of them. fixed that. Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/lib/delay_32.c25
1 files changed, 16 insertions, 9 deletions
diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay_32.c
index d710f2d167b..ef691316f8b 100644
--- a/arch/x86/lib/delay_32.c
+++ b/arch/x86/lib/delay_32.c
@@ -3,6 +3,7 @@
*
* Copyright (C) 1993 Linus Torvalds
* Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ * Copyright (C) 2008 Jiri Hladky <hladky _dot_ jiri _at_ gmail _dot_ com>
*
* The __delay function must _NOT_ be inlined as its execution time
* depends wildly on alignment on many x86 processors. The additional
@@ -28,16 +29,22 @@
/* simple loop based delay: */
static void delay_loop(unsigned long loops)
{
- int d0;
-
__asm__ __volatile__(
- "\tjmp 1f\n"
- ".align 16\n"
- "1:\tjmp 2f\n"
- ".align 16\n"
- "2:\tdecl %0\n\tjns 2b"
- :"=&a" (d0)
- :"0" (loops));
+ " test %0,%0 \n"
+ " jz 3f \n"
+ " jmp 1f \n"
+
+ ".align 16 \n"
+ "1: jmp 2f \n"
+
+ ".align 16 \n"
+ "2: decl %0 \n"
+ " jnz 2b \n"
+ "3: decl %0 \n"
+
+ : /* we don't need output */
+ :"a" (loops)
+ );
}
/* TSC based delay: */