kernel_optimize_test/arch/arm/kernel/head-common.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

224 lines
5.4 KiB
ArmAsm

/*
* linux/arch/arm/kernel/head-common.S
*
* Copyright (C) 1994-2002 Russell King
* Copyright (c) 2003 ARM Limited
* All Rights Reserved
*
* 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 <asm/assembler.h>
#define ATAG_CORE 0x54410001
#define ATAG_CORE_SIZE ((2*4 + 3*4) >> 2)
#define ATAG_CORE_SIZE_EMPTY ((2*4) >> 2)
#ifdef CONFIG_CPU_BIG_ENDIAN
#define OF_DT_MAGIC 0xd00dfeed
#else
#define OF_DT_MAGIC 0xedfe0dd0 /* 0xd00dfeed in big-endian */
#endif
/*
* Exception handling. Something went wrong and we can't proceed. We
* ought to tell the user, but since we don't have any guarantee that
* we're even running on the right architecture, we do virtually nothing.
*
* If CONFIG_DEBUG_LL is set we try to print out something about the error
* and hope for the best (useful if bootloader fails to pass a proper
* machine ID for example).
*/
__HEAD
/* Determine validity of the r2 atags pointer. The heuristic requires
* that the pointer be aligned, in the first 16k of physical RAM and
* that the ATAG_CORE marker is first and present. If CONFIG_OF_FLATTREE
* is selected, then it will also accept a dtb pointer. Future revisions
* of this function may be more lenient with the physical address and
* may also be able to move the ATAGS block if necessary.
*
* Returns:
* r2 either valid atags pointer, valid dtb pointer, or zero
* r5, r6 corrupted
*/
__vet_atags:
tst r2, #0x3 @ aligned?
bne 1f
ldr r5, [r2, #0]
#ifdef CONFIG_OF_FLATTREE
ldr r6, =OF_DT_MAGIC @ is it a DTB?
cmp r5, r6
beq 2f
#endif
cmp r5, #ATAG_CORE_SIZE @ is first tag ATAG_CORE?
cmpne r5, #ATAG_CORE_SIZE_EMPTY
bne 1f
ldr r5, [r2, #4]
ldr r6, =ATAG_CORE
cmp r5, r6
bne 1f
2: ret lr @ atag/dtb pointer is ok
1: mov r2, #0
ret lr
ENDPROC(__vet_atags)
/*
* The following fragment of code is executed with the MMU on in MMU mode,
* and uses absolute addresses; this is not position independent.
*
* r0 = cp#15 control register
* r1 = machine ID
* r2 = atags/dtb pointer
* r9 = processor ID
*/
__INIT
__mmap_switched:
adr r3, __mmap_switched_data
ldmia r3!, {r4, r5, r6, r7}
cmp r4, r5 @ Copy data segment if needed
1: cmpne r5, r6
ldrne fp, [r4], #4
strne fp, [r5], #4
bne 1b
mov fp, #0 @ Clear BSS (and zero fp)
1: cmp r6, r7
strcc fp, [r6],#4
bcc 1b
ARM( ldmia r3, {r4, r5, r6, r7, sp})
THUMB( ldmia r3, {r4, r5, r6, r7} )
THUMB( ldr sp, [r3, #16] )
str r9, [r4] @ Save processor ID
str r1, [r5] @ Save machine type
str r2, [r6] @ Save atags pointer
cmp r7, #0
strne r0, [r7] @ Save control register values
b start_kernel
ENDPROC(__mmap_switched)
.align 2
.type __mmap_switched_data, %object
__mmap_switched_data:
.long __data_loc @ r4
.long _sdata @ r5
.long __bss_start @ r6
.long _end @ r7
.long processor_id @ r4
.long __machine_arch_type @ r5
.long __atags_pointer @ r6
#ifdef CONFIG_CPU_CP15
.long cr_alignment @ r7
#else
.long 0 @ r7
#endif
.long init_thread_union + THREAD_START_SP @ sp
.size __mmap_switched_data, . - __mmap_switched_data
/*
* This provides a C-API version of __lookup_processor_type
*/
ENTRY(lookup_processor_type)
stmfd sp!, {r4 - r6, r9, lr}
mov r9, r0
bl __lookup_processor_type
mov r0, r5
ldmfd sp!, {r4 - r6, r9, pc}
ENDPROC(lookup_processor_type)
__FINIT
.text
/*
* Read processor ID register (CP#15, CR0), and look up in the linker-built
* supported processor list. Note that we can't use the absolute addresses
* for the __proc_info lists since we aren't running with the MMU on
* (and therefore, we are not in the correct address space). We have to
* calculate the offset.
*
* r9 = cpuid
* Returns:
* r3, r4, r6 corrupted
* r5 = proc_info pointer in physical address space
* r9 = cpuid (preserved)
*/
__lookup_processor_type:
adr r3, __lookup_processor_type_data
ldmia r3, {r4 - r6}
sub r3, r3, r4 @ get offset between virt&phys
add r5, r5, r3 @ convert virt addresses to
add r6, r6, r3 @ physical address space
1: ldmia r5, {r3, r4} @ value, mask
and r4, r4, r9 @ mask wanted bits
teq r3, r4
beq 2f
add r5, r5, #PROC_INFO_SZ @ sizeof(proc_info_list)
cmp r5, r6
blo 1b
mov r5, #0 @ unknown processor
2: ret lr
ENDPROC(__lookup_processor_type)
/*
* Look in <asm/procinfo.h> for information about the __proc_info structure.
*/
.align 2
.type __lookup_processor_type_data, %object
__lookup_processor_type_data:
.long .
.long __proc_info_begin
.long __proc_info_end
.size __lookup_processor_type_data, . - __lookup_processor_type_data
__error_lpae:
#ifdef CONFIG_DEBUG_LL
adr r0, str_lpae
bl printascii
b __error
str_lpae: .asciz "\nError: Kernel with LPAE support, but CPU does not support LPAE.\n"
#else
b __error
#endif
.align
ENDPROC(__error_lpae)
__error_p:
#ifdef CONFIG_DEBUG_LL
adr r0, str_p1
bl printascii
mov r0, r9
bl printhex8
adr r0, str_p2
bl printascii
b __error
str_p1: .asciz "\nError: unrecognized/unsupported processor variant (0x"
str_p2: .asciz ").\n"
.align
#endif
ENDPROC(__error_p)
__error:
#ifdef CONFIG_ARCH_RPC
/*
* Turn the screen red on a error - RiscPC only.
*/
mov r0, #0x02000000
mov r3, #0x11
orr r3, r3, r3, lsl #8
orr r3, r3, r3, lsl #16
str r3, [r0], #4
str r3, [r0], #4
str r3, [r0], #4
str r3, [r0], #4
#endif
1: mov r0, r0
b 1b
ENDPROC(__error)