2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 21:24:00 +08:00
linux-next/arch/arm/mm/proc-v6.S
Russell King 6ebbf2ce43 ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+
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>
2014-07-18 12:29:04 +01:00

301 lines
8.2 KiB
ArmAsm

/*
* linux/arch/arm/mm/proc-v6.S
*
* Copyright (C) 2001 Deep Blue Solutions Ltd.
* Modified by Catalin Marinas for noMMU support
*
* 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.
*
* This is the "shell" of the ARMv6 processor support.
*/
#include <linux/init.h>
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/asm-offsets.h>
#include <asm/hwcap.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
#include "proc-macros.S"
#define D_CACHE_LINE_SIZE 32
#define TTB_C (1 << 0)
#define TTB_S (1 << 1)
#define TTB_IMP (1 << 2)
#define TTB_RGN_NC (0 << 3)
#define TTB_RGN_WBWA (1 << 3)
#define TTB_RGN_WT (2 << 3)
#define TTB_RGN_WB (3 << 3)
#define TTB_FLAGS_UP TTB_RGN_WBWA
#define PMD_FLAGS_UP PMD_SECT_WB
#define TTB_FLAGS_SMP TTB_RGN_WBWA|TTB_S
#define PMD_FLAGS_SMP PMD_SECT_WBWA|PMD_SECT_S
ENTRY(cpu_v6_proc_init)
ret lr
ENTRY(cpu_v6_proc_fin)
mrc p15, 0, r0, c1, c0, 0 @ ctrl register
bic r0, r0, #0x1000 @ ...i............
bic r0, r0, #0x0006 @ .............ca.
mcr p15, 0, r0, c1, c0, 0 @ disable caches
ret lr
/*
* cpu_v6_reset(loc)
*
* Perform a soft reset of the system. Put the CPU into the
* same state as it would be if it had been reset, and branch
* to what would be the reset vector.
*
* - loc - location to jump to for soft reset
*/
.align 5
.pushsection .idmap.text, "ax"
ENTRY(cpu_v6_reset)
mrc p15, 0, r1, c1, c0, 0 @ ctrl register
bic r1, r1, #0x1 @ ...............m
mcr p15, 0, r1, c1, c0, 0 @ disable MMU
mov r1, #0
mcr p15, 0, r1, c7, c5, 4 @ ISB
ret r0
ENDPROC(cpu_v6_reset)
.popsection
/*
* cpu_v6_do_idle()
*
* Idle the processor (eg, wait for interrupt).
*
* IRQs are already disabled.
*/
ENTRY(cpu_v6_do_idle)
mov r1, #0
mcr p15, 0, r1, c7, c10, 4 @ DWB - WFI may enter a low-power mode
mcr p15, 0, r1, c7, c0, 4 @ wait for interrupt
ret lr
ENTRY(cpu_v6_dcache_clean_area)
1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry
add r0, r0, #D_CACHE_LINE_SIZE
subs r1, r1, #D_CACHE_LINE_SIZE
bhi 1b
ret lr
/*
* cpu_v6_switch_mm(pgd_phys, tsk)
*
* Set the translation table base pointer to be pgd_phys
*
* - pgd_phys - physical address of new TTB
*
* It is assumed that:
* - we are not using split page tables
*/
ENTRY(cpu_v6_switch_mm)
#ifdef CONFIG_MMU
mov r2, #0
mmid r1, r1 @ get mm->context.id
ALT_SMP(orr r0, r0, #TTB_FLAGS_SMP)
ALT_UP(orr r0, r0, #TTB_FLAGS_UP)
mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB
mcr p15, 0, r2, c7, c10, 4 @ drain write buffer
mcr p15, 0, r0, c2, c0, 0 @ set TTB 0
#ifdef CONFIG_PID_IN_CONTEXTIDR
mrc p15, 0, r2, c13, c0, 1 @ read current context ID
bic r2, r2, #0xff @ extract the PID
and r1, r1, #0xff
orr r1, r1, r2 @ insert into new context ID
#endif
mcr p15, 0, r1, c13, c0, 1 @ set context ID
#endif
ret lr
/*
* cpu_v6_set_pte_ext(ptep, pte, ext)
*
* Set a level 2 translation table entry.
*
* - ptep - pointer to level 2 translation table entry
* (hardware version is stored at -1024 bytes)
* - pte - PTE value to store
* - ext - value for extended PTE bits
*/
armv6_mt_table cpu_v6
ENTRY(cpu_v6_set_pte_ext)
#ifdef CONFIG_MMU
armv6_set_pte_ext cpu_v6
#endif
ret lr
/* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */
.globl cpu_v6_suspend_size
.equ cpu_v6_suspend_size, 4 * 6
#ifdef CONFIG_ARM_CPU_SUSPEND
ENTRY(cpu_v6_do_suspend)
stmfd sp!, {r4 - r9, lr}
mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID
#ifdef CONFIG_MMU
mrc p15, 0, r5, c3, c0, 0 @ Domain ID
mrc p15, 0, r6, c2, c0, 1 @ Translation table base 1
#endif
mrc p15, 0, r7, c1, c0, 1 @ auxiliary control register
mrc p15, 0, r8, c1, c0, 2 @ co-processor access control
mrc p15, 0, r9, c1, c0, 0 @ control register
stmia r0, {r4 - r9}
ldmfd sp!, {r4- r9, pc}
ENDPROC(cpu_v6_do_suspend)
ENTRY(cpu_v6_do_resume)
mov ip, #0
mcr p15, 0, ip, c7, c14, 0 @ clean+invalidate D cache
mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache
mcr p15, 0, ip, c7, c15, 0 @ clean+invalidate cache
mcr p15, 0, ip, c7, c10, 4 @ drain write buffer
mcr p15, 0, ip, c13, c0, 1 @ set reserved context ID
ldmia r0, {r4 - r9}
mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID
#ifdef CONFIG_MMU
mcr p15, 0, r5, c3, c0, 0 @ Domain ID
ALT_SMP(orr r1, r1, #TTB_FLAGS_SMP)
ALT_UP(orr r1, r1, #TTB_FLAGS_UP)
mcr p15, 0, r1, c2, c0, 0 @ Translation table base 0
mcr p15, 0, r6, c2, c0, 1 @ Translation table base 1
mcr p15, 0, ip, c2, c0, 2 @ TTB control register
#endif
mcr p15, 0, r7, c1, c0, 1 @ auxiliary control register
mcr p15, 0, r8, c1, c0, 2 @ co-processor access control
mcr p15, 0, ip, c7, c5, 4 @ ISB
mov r0, r9 @ control register
b cpu_resume_mmu
ENDPROC(cpu_v6_do_resume)
#endif
string cpu_v6_name, "ARMv6-compatible processor"
.align
/*
* __v6_setup
*
* Initialise TLB, Caches, and MMU state ready to switch the MMU
* on. Return in r0 the new CP15 C1 control register setting.
*
* We automatically detect if we have a Harvard cache, and use the
* Harvard cache control instructions insead of the unified cache
* control instructions.
*
* This should be able to cover all ARMv6 cores.
*
* It is assumed that:
* - cache type register is implemented
*/
__v6_setup:
#ifdef CONFIG_SMP
ALT_SMP(mrc p15, 0, r0, c1, c0, 1) @ Enable SMP/nAMP mode
ALT_UP(nop)
orr r0, r0, #0x20
ALT_SMP(mcr p15, 0, r0, c1, c0, 1)
ALT_UP(nop)
#endif
mov r0, #0
mcr p15, 0, r0, c7, c14, 0 @ clean+invalidate D cache
mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache
mcr p15, 0, r0, c7, c15, 0 @ clean+invalidate cache
#ifdef CONFIG_MMU
mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs
mcr p15, 0, r0, c2, c0, 2 @ TTB control register
ALT_SMP(orr r4, r4, #TTB_FLAGS_SMP)
ALT_UP(orr r4, r4, #TTB_FLAGS_UP)
ALT_SMP(orr r8, r8, #TTB_FLAGS_SMP)
ALT_UP(orr r8, r8, #TTB_FLAGS_UP)
mcr p15, 0, r8, c2, c0, 1 @ load TTB1
#endif /* CONFIG_MMU */
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer and
@ complete invalidations
adr r5, v6_crval
ldmia r5, {r5, r6}
ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables
mrc p15, 0, r0, c1, c0, 0 @ read control register
bic r0, r0, r5 @ clear bits them
orr r0, r0, r6 @ set them
#ifdef CONFIG_ARM_ERRATA_364296
/*
* Workaround for the 364296 ARM1136 r0p2 erratum (possible cache data
* corruption with hit-under-miss enabled). The conditional code below
* (setting the undocumented bit 31 in the auxiliary control register
* and the FI bit in the control register) disables hit-under-miss
* without putting the processor into full low interrupt latency mode.
*/
ldr r6, =0x4107b362 @ id for ARM1136 r0p2
mrc p15, 0, r5, c0, c0, 0 @ get processor id
teq r5, r6 @ check for the faulty core
mrceq p15, 0, r5, c1, c0, 1 @ load aux control reg
orreq r5, r5, #(1 << 31) @ set the undocumented bit 31
mcreq p15, 0, r5, c1, c0, 1 @ write aux control reg
orreq r0, r0, #(1 << 21) @ low interrupt latency configuration
#endif
ret lr @ return to head.S:__ret
/*
* V X F I D LR
* .... ...E PUI. .T.T 4RVI ZFRS BLDP WCAM
* rrrr rrrx xxx0 0101 xxxx xxxx x111 xxxx < forced
* 0 110 0011 1.00 .111 1101 < we want
*/
.type v6_crval, #object
v6_crval:
crval clear=0x01e0fb7f, mmuset=0x00c0387d, ucset=0x00c0187c
__INITDATA
@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
define_processor_functions v6, dabort=v6_early_abort, pabort=v6_pabort, suspend=1
.section ".rodata"
string cpu_arch_name, "armv6"
string cpu_elf_name, "v6"
.align
.section ".proc.info.init", #alloc, #execinstr
/*
* Match any ARMv6 processor core.
*/
.type __v6_proc_info, #object
__v6_proc_info:
.long 0x0007b000
.long 0x0007f000
ALT_SMP(.long \
PMD_TYPE_SECT | \
PMD_SECT_AP_WRITE | \
PMD_SECT_AP_READ | \
PMD_FLAGS_SMP)
ALT_UP(.long \
PMD_TYPE_SECT | \
PMD_SECT_AP_WRITE | \
PMD_SECT_AP_READ | \
PMD_FLAGS_UP)
.long PMD_TYPE_SECT | \
PMD_SECT_XN | \
PMD_SECT_AP_WRITE | \
PMD_SECT_AP_READ
b __v6_setup
.long cpu_arch_name
.long cpu_elf_name
/* See also feat_v6_fixup() for HWCAP_TLS */
.long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_JAVA|HWCAP_TLS
.long cpu_v6_name
.long v6_processor_functions
.long v6wbi_tlb_fns
.long v6_user_fns
.long v6_cache_fns
.size __v6_proc_info, . - __v6_proc_info