diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 76f60f52a885246ff1a8f6ce9bad2c3791d1df94..86960a6c41c025c0488045498848e315b2e0754a 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -4,7 +4,7 @@
 
 obj-$(CONFIG_SMP) := msr-on-cpu.o
 
-lib-y := delay_$(BITS).o
+lib-y := delay.o
 lib-y += usercopy_$(BITS).o getuser_$(BITS).o putuser_$(BITS).o
 lib-y += memcpy_$(BITS).o
 
diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay.c
similarity index 98%
rename from arch/x86/lib/delay_32.c
rename to arch/x86/lib/delay.c
index 0b659a320b1ec225dcbc7cee1a3e08f9520dda8a..f4568605d7d5c9fa7281bebfc6d8f5e2b122c8df 100644
--- a/arch/x86/lib/delay_32.c
+++ b/arch/x86/lib/delay.c
@@ -29,7 +29,7 @@
 /* simple loop based delay: */
 static void delay_loop(unsigned long loops)
 {
-	__asm__ __volatile__(
+	asm volatile(
 		"	test %0,%0	\n"
 		"	jz 3f		\n"
 		"	jmp 1f		\n"
@@ -108,31 +108,30 @@ void __delay(unsigned long loops)
 {
 	delay_fn(loops);
 }
+EXPORT_SYMBOL(__delay);
 
 inline void __const_udelay(unsigned long xloops)
 {
 	int d0;
 
 	xloops *= 4;
-	__asm__("mull %%edx"
+	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)
 {
 	__const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
 }
+EXPORT_SYMBOL(__udelay);
 
 void __ndelay(unsigned long nsecs)
 {
 	__const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
 }
-
-EXPORT_SYMBOL(__delay);
-EXPORT_SYMBOL(__const_udelay);
-EXPORT_SYMBOL(__udelay);
 EXPORT_SYMBOL(__ndelay);
diff --git a/arch/x86/lib/delay_64.c b/arch/x86/lib/delay_64.c
deleted file mode 100644
index ff3dfecdb6f9c49589155771c02b8359a08ae3ec..0000000000000000000000000000000000000000
--- a/arch/x86/lib/delay_64.c
+++ /dev/null
@@ -1,128 +0,0 @@
-/*
- *	Precise Delay Loops for x86-64
- *
- *	Copyright (C) 1993 Linus Torvalds
- *	Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
- *
- *	The __delay function must _NOT_ be inlined as its execution time
- *	depends wildly on alignment on many x86 processors. 
- */
-
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/timex.h>
-#include <linux/preempt.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-
-#include <asm/delay.h>
-#include <asm/msr.h>
-
-#ifdef CONFIG_SMP
-#include <asm/smp.h>
-#endif
-
-/* simple loop based delay: */
-static void delay_loop(unsigned long loops)
-{
-	asm volatile(
-		"	test %0,%0	\n"
-		"	jz 3f		\n"
-		"	jmp 1f		\n"
-
-		".align 16		\n"
-		"1:	jmp 2f		\n"
-
-		".align 16		\n"
-		"2:	dec %0		\n"
-		"	jnz 2b		\n"
-		"3:	dec %0		\n"
-
-		: /* we don't need output */
-		:"a" (loops)
-	);
-}
-
-static void delay_tsc(unsigned long loops)
-{
-	unsigned bclock, now;
-	int cpu;
-
-	preempt_disable();
-	cpu = smp_processor_id();
-	rdtscl(bclock);
-	for (;;) {
-		rdtscl(now);
-		if ((now - bclock) >= loops)
-			break;
-
-		/* Allow RT tasks to run */
-		preempt_enable();
-		rep_nop();
-		preempt_disable();
-
-		/*
-		 * It is possible that we moved to another CPU, and
-		 * since TSC's are per-cpu we need to calculate
-		 * that. The delay must guarantee that we wait "at
-		 * least" the amount of time. Being moved to another
-		 * CPU could make the wait longer but we just need to
-		 * make sure we waited long enough. Rebalance the
-		 * counter for this CPU.
-		 */
-		if (unlikely(cpu != smp_processor_id())) {
-			loops -= (now - bclock);
-			cpu = smp_processor_id();
-			rdtscl(bclock);
-		}
-	}
-	preempt_enable();
-}
-
-static void (*delay_fn)(unsigned long) = delay_loop;
-
-void use_tsc_delay(void)
-{
-	delay_fn = delay_tsc;
-}
-
-int __devinit read_current_timer(unsigned long *timer_value)
-{
-	if (delay_fn == delay_tsc) {
-		rdtscll(*timer_value);
-		return 0;
-	}
-	return -1;
-}
-
-void __delay(unsigned long loops)
-{
-	delay_fn(loops);
-}
-EXPORT_SYMBOL(__delay);
-
-inline void __const_udelay(unsigned long xloops)
-{
-	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)
-{
-	__const_udelay(usecs * 0x000010c7);  /* 2**32 / 1000000 (rounded up) */
-}
-EXPORT_SYMBOL(__udelay);
-
-void __ndelay(unsigned long nsecs)
-{
-	__const_udelay(nsecs * 0x00005);  /* 2**32 / 1000000000 (rounded up) */
-}
-EXPORT_SYMBOL(__ndelay);