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>
127 lines
2.1 KiB
ArmAsm
127 lines
2.1 KiB
ArmAsm
/*
|
|
* linux/arch/arm/lib/io-writesw-armv3.S
|
|
*
|
|
* Copyright (C) 1995-2000 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>
|
|
|
|
.Loutsw_bad_alignment:
|
|
adr r0, .Loutsw_bad_align_msg
|
|
mov r2, lr
|
|
b panic
|
|
.Loutsw_bad_align_msg:
|
|
.asciz "outsw: bad buffer alignment (0x%p, lr=0x%08lX)\n"
|
|
.align
|
|
|
|
.Loutsw_align: tst r1, #1
|
|
bne .Loutsw_bad_alignment
|
|
|
|
add r1, r1, #2
|
|
|
|
ldr r3, [r1, #-4]
|
|
mov r3, r3, lsr #16
|
|
orr r3, r3, r3, lsl #16
|
|
str r3, [r0]
|
|
subs r2, r2, #1
|
|
reteq lr
|
|
|
|
ENTRY(__raw_writesw)
|
|
teq r2, #0 @ do we have to check for the zero len?
|
|
reteq lr
|
|
tst r1, #3
|
|
bne .Loutsw_align
|
|
|
|
stmfd sp!, {r4, r5, r6, lr}
|
|
|
|
subs r2, r2, #8
|
|
bmi .Lno_outsw_8
|
|
|
|
.Loutsw_8_lp: ldmia r1!, {r3, r4, r5, r6}
|
|
|
|
mov ip, r3, lsl #16
|
|
orr ip, ip, ip, lsr #16
|
|
str ip, [r0]
|
|
|
|
mov ip, r3, lsr #16
|
|
orr ip, ip, ip, lsl #16
|
|
str ip, [r0]
|
|
|
|
mov ip, r4, lsl #16
|
|
orr ip, ip, ip, lsr #16
|
|
str ip, [r0]
|
|
|
|
mov ip, r4, lsr #16
|
|
orr ip, ip, ip, lsl #16
|
|
str ip, [r0]
|
|
|
|
mov ip, r5, lsl #16
|
|
orr ip, ip, ip, lsr #16
|
|
str ip, [r0]
|
|
|
|
mov ip, r5, lsr #16
|
|
orr ip, ip, ip, lsl #16
|
|
str ip, [r0]
|
|
|
|
mov ip, r6, lsl #16
|
|
orr ip, ip, ip, lsr #16
|
|
str ip, [r0]
|
|
|
|
mov ip, r6, lsr #16
|
|
orr ip, ip, ip, lsl #16
|
|
str ip, [r0]
|
|
|
|
subs r2, r2, #8
|
|
bpl .Loutsw_8_lp
|
|
|
|
tst r2, #7
|
|
ldmeqfd sp!, {r4, r5, r6, pc}
|
|
|
|
.Lno_outsw_8: tst r2, #4
|
|
beq .Lno_outsw_4
|
|
|
|
ldmia r1!, {r3, r4}
|
|
|
|
mov ip, r3, lsl #16
|
|
orr ip, ip, ip, lsr #16
|
|
str ip, [r0]
|
|
|
|
mov ip, r3, lsr #16
|
|
orr ip, ip, ip, lsl #16
|
|
str ip, [r0]
|
|
|
|
mov ip, r4, lsl #16
|
|
orr ip, ip, ip, lsr #16
|
|
str ip, [r0]
|
|
|
|
mov ip, r4, lsr #16
|
|
orr ip, ip, ip, lsl #16
|
|
str ip, [r0]
|
|
|
|
.Lno_outsw_4: tst r2, #2
|
|
beq .Lno_outsw_2
|
|
|
|
ldr r3, [r1], #4
|
|
|
|
mov ip, r3, lsl #16
|
|
orr ip, ip, ip, lsr #16
|
|
str ip, [r0]
|
|
|
|
mov ip, r3, lsr #16
|
|
orr ip, ip, ip, lsl #16
|
|
str ip, [r0]
|
|
|
|
.Lno_outsw_2: tst r2, #1
|
|
|
|
ldrne r3, [r1]
|
|
|
|
movne ip, r3, lsl #16
|
|
orrne ip, ip, ip, lsr #16
|
|
strne ip, [r0]
|
|
|
|
ldmfd sp!, {r4, r5, r6, pc}
|