diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay_32.c
index bf6de05445ba4cc03c3e724e144ca1ffb450b1f8..0b659a320b1ec225dcbc7cee1a3e08f9520dda8a 100644
--- a/arch/x86/lib/delay_32.c
+++ b/arch/x86/lib/delay_32.c
@@ -114,7 +114,7 @@ inline void __const_udelay(unsigned long xloops)
 	int d0;
 
 	xloops *= 4;
-	__asm__("mull %0"
+	__asm__("mull %%edx"
 		:"=d" (xloops), "=&a" (d0)
 		:"1" (xloops), "0"
 		(cpu_data(raw_smp_processor_id()).loops_per_jiffy * (HZ/4)));
diff --git a/arch/x86/lib/delay_64.c b/arch/x86/lib/delay_64.c
index d0326d07c845bb9cfe806ae5b74a4ed14058e427..ff3dfecdb6f9c49589155771c02b8359a08ae3ec 100644
--- a/arch/x86/lib/delay_64.c
+++ b/arch/x86/lib/delay_64.c
@@ -103,9 +103,16 @@ EXPORT_SYMBOL(__delay);
 
 inline void __const_udelay(unsigned long xloops)
 {
-	__delay(((xloops * HZ *
-		cpu_data(raw_smp_processor_id()).loops_per_jiffy) >> 32) + 1);
+	int d0;
+	xloops *= 4;
+	__asm__("mull %%edx"
+		:"=d" (xloops), "=&a" (d0)
+		:"1" (xloops), "0"
+		(cpu_data(raw_smp_processor_id()).loops_per_jiffy * (HZ/4)));
+
+	__delay(++xloops);
 }
+
 EXPORT_SYMBOL(__const_udelay);
 
 void __udelay(unsigned long usecs)