ARM: 8306/1: loop_udelay: remove bogomips value limitation

Now that we don't support ARMv3 anymore, the loop based delay code can
convert microsecs into number of loops using a 64-bit multiplication
and more precision.

This allows us to lift the hard limit of 3355 on the bogomips value as
loops_per_jiffy may now safely span the full 32-bit range.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/include/asm/delay.h

@@ -10,8 +10,8 @@
 #include <asm/param.h>	/* HZ */
 
 #define MAX_UDELAY_MS	2
-#define UDELAY_MULT	((UL(2199023) * HZ) >> 11)
-#define UDELAY_SHIFT	30
+#define UDELAY_MULT	UL(2047 * HZ + 483648 * HZ / 1000000)
+#define UDELAY_SHIFT	31
 
 #ifndef __ASSEMBLY__
 
@@ -34,7 +34,7 @@ extern struct arm_delay_ops {
  * it, it means that you're calling udelay() with an out of range value.
  *
  * With currently imposed limits, this means that we support a max delay
- * of 2000us. Further limits: HZ<=1000 and bogomips<=3355
+ * of 2000us. Further limits: HZ<=1000
  */
 extern void __bad_udelay(void);
 

arch/arm/lib/Makefile

@@ -29,7 +29,10 @@ else
   lib-y	+= io-readsw-armv4.o io-writesw-armv4.o
 endif
 
-lib-$(CONFIG_ARCH_RPC)		+= ecard.o io-acorn.o floppydma.o
+ifeq ($(CONFIG_ARCH_RPC),y)
+  lib-y				+= ecard.o io-acorn.o floppydma.o
+  AFLAGS_delay-loop.o		+= -march=armv4
+endif
 
 $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S

arch/arm/lib/delay-loop.S

@@ -10,6 +10,7 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 #include <asm/delay.h>
+
 		.text
 
 .LC0:		.word	loops_per_jiffy
@@ -17,7 +18,6 @@
 
 /*
  * r0  <= 2000
- * lpj <= 0x01ffffff (max. 3355 bogomips)
  * HZ  <= 1000
  */
 
@@ -25,16 +25,11 @@ ENTRY(__loop_udelay)
 		ldr	r2, .LC1
 		mul	r0, r2, r0
 ENTRY(__loop_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
+		ldr	r2, [r2]
+		umull	r1, r0, r2, r0
+		adds	r1, r1, #0xffffffff
+		adcs	r0, r0, r0
 		reteq	lr
 
 /*