linux_dsm_epyc7002/arch/arm/lib/delay-loop.S
Fabio Estevam 11d4bb1bd0 ARM: 7907/1: lib: delay-loop: Add align directive to fix BogoMIPS calculation
Currently mx53 (CortexA8) running at 1GHz reports:
Calibrating delay loop... 663.55 BogoMIPS (lpj=3317760)

Tom Evans verified that alignments of 0x0 and 0x8 run the two instructions of __loop_delay in one clock cycle (1 clock/loop), while alignments of 0x4 and 0xc take 3 clocks to run the loop twice. (1.5 clock/loop)

The original object code looks like this:

00000010 <__loop_const_udelay>:
  10:	e3e01000 	mvn	r1, #0
  14:	e51f201c 	ldr	r2, [pc, #-28]	; 0 <__loop_udelay-0x8>
  18:	e5922000 	ldr	r2, [r2]
  1c:	e0800921 	add	r0, r0, r1, lsr #18
  20:	e1a00720 	lsr	r0, r0, #14
  24:	e0822b21 	add	r2, r2, r1, lsr #22
  28:	e1a02522 	lsr	r2, r2, #10
  2c:	e0000092 	mul	r0, r2, r0
  30:	e0800d21 	add	r0, r0, r1, lsr #26
  34:	e1b00320 	lsrs	r0, r0, #6
  38:	01a0f00e 	moveq	pc, lr

0000003c <__loop_delay>:
  3c:	e2500001 	subs	r0, r0, #1
  40:	8afffffe 	bhi	3c <__loop_delay>
  44:	e1a0f00e 	mov	pc, lr

After adding the 'align 3' directive to __loop_delay (align to 8 bytes):

00000010 <__loop_const_udelay>:
  10:	e3e01000 	mvn	r1, #0
  14:	e51f201c 	ldr	r2, [pc, #-28]	; 0 <__loop_udelay-0x8>
  18:	e5922000 	ldr	r2, [r2]
  1c:	e0800921 	add	r0, r0, r1, lsr #18
  20:	e1a00720 	lsr	r0, r0, #14
  24:	e0822b21 	add	r2, r2, r1, lsr #22
  28:	e1a02522 	lsr	r2, r2, #10
  2c:	e0000092 	mul	r0, r2, r0
  30:	e0800d21 	add	r0, r0, r1, lsr #26
  34:	e1b00320 	lsrs	r0, r0, #6
  38:	01a0f00e 	moveq	pc, lr
  3c:	e320f000 	nop	{0}

00000040 <__loop_delay>:
  40:	e2500001 	subs	r0, r0, #1
  44:	8afffffe 	bhi	40 <__loop_delay>
  48:	e1a0f00e 	mov	pc, lr
  4c:	e320f000 	nop	{0}

, which now reports:
Calibrating delay loop... 996.14 BogoMIPS (lpj=4980736)

Some more test results:

On mx31 (ARM1136) running at 532 MHz, before the patch:
Calibrating delay loop... 351.43 BogoMIPS (lpj=1757184)

On mx31 (ARM1136) running at 532 MHz after the patch:
Calibrating delay loop... 528.79 BogoMIPS (lpj=2643968)

Also tested on mx6 (CortexA9) and on mx27 (ARM926), which shows the same
BogoMIPS value before and after this patch.

Reported-by: Tom Evans <tom_usenet@optusnet.com.au>
Suggested-by: Tom Evans <tom_usenet@optusnet.com.au>
Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2013-11-30 22:21:03 +00:00

69 lines
1.3 KiB
ArmAsm

/*
* 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/delay.h>
.text
.LC0: .word loops_per_jiffy
.LC1: .word UDELAY_MULT
/*
* r0 <= 2000
* lpj <= 0x01ffffff (max. 3355 bogomips)
* HZ <= 1000
*/
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
moveq pc, lr
/*
* loops = r0 * HZ * loops_per_jiffy / 1000000
*/
.align 3
@ Delay routine
ENTRY(__loop_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 __loop_delay
mov pc, lr
ENDPROC(__loop_udelay)
ENDPROC(__loop_const_udelay)
ENDPROC(__loop_delay)