diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index b2deda18154..ccc5ed573fa 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -8,7 +8,7 @@
 
 #include <asm/param.h>	/* HZ */
 
-extern void __delay(int loops);
+extern void __delay(unsigned long loops);
 
 /*
  * This function intentionally does not exist; if you see references to
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index b57c75e0b01..f1a50f37efd 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -48,10 +48,6 @@ extern void __aeabi_ulcmp(void);
 
 extern void fpundefinstr(void);
 
-	/* platform dependent support */
-EXPORT_SYMBOL(__udelay);
-EXPORT_SYMBOL(__const_udelay);
-
 	/* networking */
 EXPORT_SYMBOL(csum_partial);
 EXPORT_SYMBOL(csum_partial_copy_from_user);
diff --git a/arch/arm/lib/delay.S b/arch/arm/lib/delay.S
deleted file mode 100644
index 3c9a05c8d20..00000000000
--- a/arch/arm/lib/delay.S
+++ /dev/null
@@ -1,69 +0,0 @@
-/*
- *  linux/arch/arm/lib/delay.S
- *
- *  Copyright (C) 1995, 1996 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/param.h>
-		.text
-
-.LC0:		.word	loops_per_jiffy
-.LC1:		.word	(2199023*HZ)>>11
-
-/*
- * r0  <= 2000
- * lpj <= 0x01ffffff (max. 3355 bogomips)
- * HZ  <= 1000
- */
-
-ENTRY(__udelay)
-		ldr	r2, .LC1
-		mul	r0, r2, r0
-ENTRY(__const_udelay)				@ 0 <= r0 <= 0x7fffff06
-		mov	r1, #-1
-		ldr	r2, .LC0
-		ldr	r2, [r2]		@ max = 0x01ffffff
-		add	r0, r0, r1, lsr #32-14
-		mov	r0, r0, lsr #14		@ max = 0x0001ffff
-		add	r2, r2, r1, lsr #32-10
-		mov	r2, r2, lsr #10		@ max = 0x00007fff
-		mul	r0, r2, r0		@ max = 2^32-1
-		add	r0, r0, r1, lsr #32-6
-		movs	r0, r0, lsr #6
-		moveq	pc, lr
-
-/*
- * loops = r0 * HZ * loops_per_jiffy / 1000000
- *
- * Oh, if only we had a cycle counter...
- */
-
-@ Delay routine
-ENTRY(__delay)
-		subs	r0, r0, #1
-#if 0
-		movls	pc, lr
-		subs	r0, r0, #1
-		movls	pc, lr
-		subs	r0, r0, #1
-		movls	pc, lr
-		subs	r0, r0, #1
-		movls	pc, lr
-		subs	r0, r0, #1
-		movls	pc, lr
-		subs	r0, r0, #1
-		movls	pc, lr
-		subs	r0, r0, #1
-		movls	pc, lr
-		subs	r0, r0, #1
-#endif
-		bhi	__delay
-		mov	pc, lr
-ENDPROC(__udelay)
-ENDPROC(__const_udelay)
-ENDPROC(__delay)
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
new file mode 100644
index 00000000000..5ee0adc7b4d
--- /dev/null
+++ b/arch/arm/lib/delay.c
@@ -0,0 +1,57 @@
+/*
+ *  Originally from linux/arch/arm/lib/delay.S
+ *
+ *  Copyright (C) 1995, 1996 Russell King
+ *  Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/module.h>
+#include <linux/delay.h>
+
+/*
+ * loops = usecs * HZ * loops_per_jiffy / 1000000
+ *
+ * Oh, if only we had a cycle counter...
+ */
+void __delay(unsigned long loops)
+{
+	asm volatile(
+	"1:	subs %0, %0, #1 \n"
+	"	bhi 1b		\n"
+	: /* No output */
+	: "r" (loops)
+	);
+}
+EXPORT_SYMBOL(__delay);
+
+/*
+ * 0 <= xloops <= 0x7fffff06
+ * loops_per_jiffy <= 0x01ffffff (max. 3355 bogomips)
+ */
+void __const_udelay(unsigned long xloops)
+{
+	unsigned long lpj;
+	unsigned long loops;
+
+	xloops >>= 14;			/* max = 0x01ffffff */
+	lpj = loops_per_jiffy >> 10;	/* max = 0x0001ffff */
+	loops = lpj * xloops;		/* max = 0x00007fff */
+	loops >>= 6;			/* max = 2^32-1 */
+
+	if (loops)
+		__delay(loops);
+}
+EXPORT_SYMBOL(__const_udelay);
+
+/*
+ * usecs  <= 2000
+ * HZ  <= 1000
+ */
+void __udelay(unsigned long usecs)
+{
+	__const_udelay(usecs * ((2199023*HZ)>>11));
+}
+EXPORT_SYMBOL(__udelay);