2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-27 14:43:58 +08:00
linux-next/arch/arm/kernel/head-nommu.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

261 lines
7.4 KiB
ArmAsm

/*
* linux/arch/arm/kernel/head-nommu.S
*
* Copyright (C) 1994-2002 Russell King
* Copyright (C) 2003-2006 Hyok S. Choi
*
* 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.
*
* Common kernel startup code (non-paged MM)
*
*/
#include <linux/linkage.h>
#include <linux/init.h>
#include <asm/assembler.h>
#include <asm/ptrace.h>
#include <asm/asm-offsets.h>
#include <asm/memory.h>
#include <asm/cp15.h>
#include <asm/thread_info.h>
#include <asm/v7m.h>
#include <asm/mpu.h>
#include <asm/page.h>
/*
* Kernel startup entry point.
* ---------------------------
*
* This is normally called from the decompressor code. The requirements
* are: MMU = off, D-cache = off, I-cache = dont care, r0 = 0,
* r1 = machine nr.
*
* See linux/arch/arm/tools/mach-types for the complete list of machine
* numbers for r1.
*
*/
__HEAD
#ifdef CONFIG_CPU_THUMBONLY
.thumb
ENTRY(stext)
#else
.arm
ENTRY(stext)
THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM.
THUMB( bx r9 ) @ If this is a Thumb-2 kernel,
THUMB( .thumb ) @ switch to Thumb now.
THUMB(1: )
#endif
setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
@ and irqs disabled
#if defined(CONFIG_CPU_CP15)
mrc p15, 0, r9, c0, c0 @ get processor id
#elif defined(CONFIG_CPU_V7M)
ldr r9, =BASEADDR_V7M_SCB
ldr r9, [r9, V7M_SCB_CPUID]
#else
ldr r9, =CONFIG_PROCESSOR_ID
#endif
bl __lookup_processor_type @ r5=procinfo r9=cpuid
movs r10, r5 @ invalid processor (r5=0)?
beq __error_p @ yes, error 'p'
#ifdef CONFIG_ARM_MPU
/* Calculate the size of a region covering just the kernel */
ldr r5, =PLAT_PHYS_OFFSET @ Region start: PHYS_OFFSET
ldr r6, =(_end) @ Cover whole kernel
sub r6, r6, r5 @ Minimum size of region to map
clz r6, r6 @ Region size must be 2^N...
rsb r6, r6, #31 @ ...so round up region size
lsl r6, r6, #MPU_RSR_SZ @ Put size in right field
orr r6, r6, #(1 << MPU_RSR_EN) @ Set region enabled bit
bl __setup_mpu
#endif
ldr r13, =__mmap_switched @ address to jump to after
@ initialising sctlr
adr lr, BSYM(1f) @ return (PIC) address
ARM( add pc, r10, #PROCINFO_INITFUNC )
THUMB( add r12, r10, #PROCINFO_INITFUNC )
THUMB( ret r12 )
1: b __after_proc_init
ENDPROC(stext)
#ifdef CONFIG_SMP
.text
ENTRY(secondary_startup)
/*
* Common entry point for secondary CPUs.
*
* Ensure that we're in SVC mode, and IRQs are disabled. Lookup
* the processor type - there is no need to check the machine type
* as it has already been validated by the primary processor.
*/
setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9
#ifndef CONFIG_CPU_CP15
ldr r9, =CONFIG_PROCESSOR_ID
#else
mrc p15, 0, r9, c0, c0 @ get processor id
#endif
bl __lookup_processor_type @ r5=procinfo r9=cpuid
movs r10, r5 @ invalid processor?
beq __error_p @ yes, error 'p'
adr r4, __secondary_data
ldmia r4, {r7, r12}
#ifdef CONFIG_ARM_MPU
/* Use MPU region info supplied by __cpu_up */
ldr r6, [r7] @ get secondary_data.mpu_szr
bl __setup_mpu @ Initialize the MPU
#endif
adr lr, BSYM(__after_proc_init) @ return address
mov r13, r12 @ __secondary_switched address
ARM( add pc, r10, #PROCINFO_INITFUNC )
THUMB( add r12, r10, #PROCINFO_INITFUNC )
THUMB( ret r12 )
ENDPROC(secondary_startup)
ENTRY(__secondary_switched)
ldr sp, [r7, #8] @ set up the stack pointer
mov fp, #0
b secondary_start_kernel
ENDPROC(__secondary_switched)
.type __secondary_data, %object
__secondary_data:
.long secondary_data
.long __secondary_switched
#endif /* CONFIG_SMP */
/*
* Set the Control Register and Read the process ID.
*/
__after_proc_init:
#ifdef CONFIG_CPU_CP15
/*
* CP15 system control register value returned in r0 from
* the CPU init function.
*/
#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6
orr r0, r0, #CR_A
#else
bic r0, r0, #CR_A
#endif
#ifdef CONFIG_CPU_DCACHE_DISABLE
bic r0, r0, #CR_C
#endif
#ifdef CONFIG_CPU_BPREDICT_DISABLE
bic r0, r0, #CR_Z
#endif
#ifdef CONFIG_CPU_ICACHE_DISABLE
bic r0, r0, #CR_I
#endif
#ifdef CONFIG_CPU_HIGH_VECTOR
orr r0, r0, #CR_V
#else
bic r0, r0, #CR_V
#endif
mcr p15, 0, r0, c1, c0, 0 @ write control reg
#endif /* CONFIG_CPU_CP15 */
ret r13
ENDPROC(__after_proc_init)
.ltorg
#ifdef CONFIG_ARM_MPU
/* Set which MPU region should be programmed */
.macro set_region_nr tmp, rgnr
mov \tmp, \rgnr @ Use static region numbers
mcr p15, 0, \tmp, c6, c2, 0 @ Write RGNR
.endm
/* Setup a single MPU region, either D or I side (D-side for unified) */
.macro setup_region bar, acr, sr, side = MPU_DATA_SIDE
mcr p15, 0, \bar, c6, c1, (0 + \side) @ I/DRBAR
mcr p15, 0, \acr, c6, c1, (4 + \side) @ I/DRACR
mcr p15, 0, \sr, c6, c1, (2 + \side) @ I/DRSR
.endm
/*
* Setup the MPU and initial MPU Regions. We create the following regions:
* Region 0: Use this for probing the MPU details, so leave disabled.
* Region 1: Background region - covers the whole of RAM as strongly ordered
* Region 2: Normal, Shared, cacheable for RAM. From PHYS_OFFSET, size from r6
* Region 3: Normal, shared, inaccessible from PL0 to protect the vectors page
*
* r6: Value to be written to DRSR (and IRSR if required) for MPU_RAM_REGION
*/
ENTRY(__setup_mpu)
/* Probe for v7 PMSA compliance */
mrc p15, 0, r0, c0, c1, 4 @ Read ID_MMFR0
and r0, r0, #(MMFR0_PMSA) @ PMSA field
teq r0, #(MMFR0_PMSAv7) @ PMSA v7
bne __error_p @ Fail: ARM_MPU on NOT v7 PMSA
/* Determine whether the D/I-side memory map is unified. We set the
* flags here and continue to use them for the rest of this function */
mrc p15, 0, r0, c0, c0, 4 @ MPUIR
ands r5, r0, #MPUIR_DREGION_SZMASK @ 0 size d region => No MPU
beq __error_p @ Fail: ARM_MPU and no MPU
tst r0, #MPUIR_nU @ MPUIR_nU = 0 for unified
/* Setup second region first to free up r6 */
set_region_nr r0, #MPU_RAM_REGION
isb
/* Full access from PL0, PL1, shared for CONFIG_SMP, cacheable */
ldr r0, =PLAT_PHYS_OFFSET @ RAM starts at PHYS_OFFSET
ldr r5,=(MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL)
setup_region r0, r5, r6, MPU_DATA_SIDE @ PHYS_OFFSET, shared, enabled
beq 1f @ Memory-map not unified
setup_region r0, r5, r6, MPU_INSTR_SIDE @ PHYS_OFFSET, shared, enabled
1: isb
/* First/background region */
set_region_nr r0, #MPU_BG_REGION
isb
/* Execute Never, strongly ordered, inaccessible to PL0, rw PL1 */
mov r0, #0 @ BG region starts at 0x0
ldr r5,=(MPU_ACR_XN | MPU_RGN_STRONGLY_ORDERED | MPU_AP_PL1RW_PL0NA)
mov r6, #MPU_RSR_ALL_MEM @ 4GB region, enabled
setup_region r0, r5, r6, MPU_DATA_SIDE @ 0x0, BG region, enabled
beq 2f @ Memory-map not unified
setup_region r0, r5, r6, MPU_INSTR_SIDE @ 0x0, BG region, enabled
2: isb
/* Vectors region */
set_region_nr r0, #MPU_VECTORS_REGION
isb
/* Shared, inaccessible to PL0, rw PL1 */
mov r0, #CONFIG_VECTORS_BASE @ Cover from VECTORS_BASE
ldr r5,=(MPU_AP_PL1RW_PL0NA | MPU_RGN_NORMAL)
/* Writing N to bits 5:1 (RSR_SZ) --> region size 2^N+1 */
mov r6, #(((PAGE_SHIFT - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN)
setup_region r0, r5, r6, MPU_DATA_SIDE @ VECTORS_BASE, PL0 NA, enabled
beq 3f @ Memory-map not unified
setup_region r0, r5, r6, MPU_INSTR_SIDE @ VECTORS_BASE, PL0 NA, enabled
3: isb
/* Enable the MPU */
mrc p15, 0, r0, c1, c0, 0 @ Read SCTLR
bic r0, r0, #CR_BR @ Disable the 'default mem-map'
orr r0, r0, #CR_M @ Set SCTRL.M (MPU on)
mcr p15, 0, r0, c1, c0, 0 @ Enable MPU
isb
ret lr
ENDPROC(__setup_mpu)
#endif
#include "head-common.S"