6ebbf2ce43
ARMv6 and greater introduced a new instruction ("bx") which can be used
to return from function calls. Recent CPUs perform better when the
"bx lr" instruction is used rather than the "mov pc, lr" instruction,
and this sequence is strongly recommended to be used by the ARM
architecture manual (section A.4.1.1).
We provide a new macro "ret" with all its variants for the condition
code which will resolve to the appropriate instruction.
Rather than doing this piecemeal, and miss some instances, change all
the "mov pc" instances to use the new macro, with the exception of
the "movs" instruction and the kprobes code. This allows us to detect
the "mov pc, lr" case and fix it up - and also gives us the possibility
of deploying this for other registers depending on the CPU selection.
Reported-by: Will Deacon <will.deacon@arm.com>
Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1
Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S
Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood
Tested-by: Shawn Guo <shawn.guo@freescale.com>
Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs
Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385
Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci
Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp
Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen
Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M
Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
68 lines
1.3 KiB
ArmAsm
68 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
|
|
reteq lr
|
|
|
|
/*
|
|
* loops = r0 * HZ * loops_per_jiffy / 1000000
|
|
*/
|
|
.align 3
|
|
|
|
@ Delay routine
|
|
ENTRY(__loop_delay)
|
|
subs r0, r0, #1
|
|
#if 0
|
|
retls lr
|
|
subs r0, r0, #1
|
|
retls lr
|
|
subs r0, r0, #1
|
|
retls lr
|
|
subs r0, r0, #1
|
|
retls lr
|
|
subs r0, r0, #1
|
|
retls lr
|
|
subs r0, r0, #1
|
|
retls lr
|
|
subs r0, r0, #1
|
|
retls lr
|
|
subs r0, r0, #1
|
|
#endif
|
|
bhi __loop_delay
|
|
ret lr
|
|
ENDPROC(__loop_udelay)
|
|
ENDPROC(__loop_const_udelay)
|
|
ENDPROC(__loop_delay)
|