--- arch/x86/lib/delay_32.c-orig	2008-05-31 23:44:34.000000000 +0200
+++ arch/x86/lib/delay_32.c	2008-06-02 11:55:50.000000000 +0200
@@ -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 +29,32 @@
 /* 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));
+/*
+ * Translates to
+#APP
+	test %eax,%eax
+	jz 3f
+	jmp 1f
+.align 16
+1:      jmp 2f
+.align 16
+2:      decl %eax
+        jnz 2b
+3:			decl %eax
+#NO_APP
+*/
+__asm__ __volatile__(
+       "test %0,%0\n"
+       "\tjz 3f\n"
+       "\tjmp 1f\n"
+       ".align 16\n"
+       "1:\tjmp 2f\n"
+       ".align 16\n"
+       "2:\tdecl %0\n\tjnz 2b\n"
+       "3:\tdecl %0"
+       :/*we don't need output */
+       :"a" (loops));
+}
 }
 
 /* TSC based delay: */