linux-sg2042/arch/arm26/boot/compressed/head.S

517 lines
11 KiB
ArmAsm

/*
* linux/arch/arm26/boot/compressed/head.S
*
* Copyright (C) 1996-2002 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>
/*
* Debugging stuff
*
* Note that these macros must not contain any code which is not
* 100% relocatable. Any attempt to do so will result in a crash.
* Please select one of the following when turning on debugging.
*/
.macro kputc,val
mov r0, \val
bl putc
.endm
.macro kphex,val,len
mov r0, \val
mov r1, #\len
bl phex
.endm
.macro debug_reloc_start
.endm
.macro debug_reloc_end
.endm
.section ".start", #alloc, #execinstr
/*
* sort out different calling conventions
*/
.align
start:
.type start,#function
.rept 8
mov r0, r0
.endr
b 1f
.word 0x016f2818 @ Magic numbers to help the loader
.word start @ absolute load/run zImage address
.word _edata @ zImage end address
1: mov r7, r1 @ save architecture ID
mov r8, #0 @ save r0
teqp pc, #0x0c000003 @ turn off interrupts
.text
adr r0, LC0
ldmia r0, {r1, r2, r3, r4, r5, r6, ip, sp}
subs r0, r0, r1 @ calculate the delta offset
teq r0, #0 @ if delta is zero, we're
beq not_relocated @ running at the address we
@ were linked at.
add r2, r2, r0 @ different address, so we
add r3, r3, r0 @ need to fix up various
add r5, r5, r0 @ pointers.
add r6, r6, r0
add ip, ip, r0
add sp, sp, r0
1: ldr r1, [r6, #0] @ relocate entries in the GOT
add r1, r1, r0 @ table. This fixes up the
str r1, [r6], #4 @ C references.
cmp r6, ip
blo 1b
not_relocated: mov r0, #0
1: str r0, [r2], #4 @ clear bss
str r0, [r2], #4
str r0, [r2], #4
str r0, [r2], #4
cmp r2, r3
blo 1b
bl cache_on
mov r1, sp @ malloc space above stack
add r2, sp, #0x10000 @ 64k max
/*
* Check to see if we will overwrite ourselves.
* r4 = final kernel address
* r5 = start of this image
* r2 = end of malloc space (and therefore this image)
* We basically want:
* r4 >= r2 -> OK
* r4 + image length <= r5 -> OK
*/
cmp r4, r2
bhs wont_overwrite
add r0, r4, #4096*1024 @ 4MB largest kernel size
cmp r0, r5
bls wont_overwrite
mov r5, r2 @ decompress after malloc space
mov r0, r5
mov r3, r7
bl decompress_kernel
add r0, r0, #127
bic r0, r0, #127 @ align the kernel length
/*
* r0 = decompressed kernel length
* r1-r3 = unused
* r4 = kernel execution address
* r5 = decompressed kernel start
* r6 = processor ID
* r7 = architecture ID
* r8-r14 = unused
*/
add r1, r5, r0 @ end of decompressed kernel
adr r2, reloc_start
ldr r3, LC1
add r3, r2, r3
1: ldmia r2!, {r8 - r13} @ copy relocation code
stmia r1!, {r8 - r13}
ldmia r2!, {r8 - r13}
stmia r1!, {r8 - r13}
cmp r2, r3
blo 1b
bl cache_clean_flush
add pc, r5, r0 @ call relocation code
/*
* We're not in danger of overwriting ourselves. Do this the simple way.
*
* r4 = kernel execution address
* r7 = architecture ID
*/
wont_overwrite: mov r0, r4
mov r3, r7
bl decompress_kernel
b call_kernel
.type LC0, #object
LC0: .word LC0 @ r1
.word __bss_start @ r2
.word _end @ r3
.word _load_addr @ r4
.word _start @ r5
.word _got_start @ r6
.word _got_end @ ip
.word user_stack+4096 @ sp
LC1: .word reloc_end - reloc_start
.size LC0, . - LC0
/*
* Turn on the cache. We need to setup some page tables so that we
* can have both the I and D caches on.
*
* We place the page tables 16k down from the kernel execution address,
* and we hope that nothing else is using it. If we're using it, we
* will go pop!
*
* On entry,
* r4 = kernel execution address
* r6 = processor ID
* r7 = architecture number
* r8 = run-time address of "start"
* On exit,
* r1, r2, r3, r8, r9, r12 corrupted
* This routine must preserve:
* r4, r5, r6, r7
*/
.align 5
cache_on: mov r3, #8 @ cache_on function
b call_cache_fn
__setup_mmu: sub r3, r4, #16384 @ Page directory size
bic r3, r3, #0xff @ Align the pointer
bic r3, r3, #0x3f00
/*
* Initialise the page tables, turning on the cacheable and bufferable
* bits for the RAM area only.
*/
mov r0, r3
mov r8, r0, lsr #18
mov r8, r8, lsl #18 @ start of RAM
add r9, r8, #0x10000000 @ a reasonable RAM size
mov r1, #0x12
orr r1, r1, #3 << 10
add r2, r3, #16384
1: cmp r1, r8 @ if virt > start of RAM
orrhs r1, r1, #0x0c @ set cacheable, bufferable
cmp r1, r9 @ if virt > end of RAM
bichs r1, r1, #0x0c @ clear cacheable, bufferable
str r1, [r0], #4 @ 1:1 mapping
add r1, r1, #1048576
teq r0, r2
bne 1b
/*
* If ever we are running from Flash, then we surely want the cache
* to be enabled also for our execution instance... We map 2MB of it
* so there is no map overlap problem for up to 1 MB compressed kernel.
* If the execution is in RAM then we would only be duplicating the above.
*/
mov r1, #0x1e
orr r1, r1, #3 << 10
mov r2, pc, lsr #20
orr r1, r1, r2, lsl #20
add r0, r3, r2, lsl #2
str r1, [r0], #4
add r1, r1, #1048576
str r1, [r0]
mov pc, lr
__armv4_cache_on:
mov r12, lr
bl __setup_mmu
mov r0, #0
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
mcr p15, 0, r0, c8, c7, 0 @ flush I,D TLBs
mrc p15, 0, r0, c1, c0, 0 @ read control reg
orr r0, r0, #0x1000 @ I-cache enable
orr r0, r0, #0x0030
b __common_cache_on
__arm6_cache_on:
mov r12, lr
bl __setup_mmu
mov r0, #0
mcr p15, 0, r0, c7, c0, 0 @ invalidate whole cache v3
mcr p15, 0, r0, c5, c0, 0 @ invalidate whole TLB v3
mov r0, #0x30
__common_cache_on:
#ifndef DEBUG
orr r0, r0, #0x000d @ Write buffer, mmu
#endif
mov r1, #-1
mcr p15, 0, r3, c2, c0, 0 @ load page table pointer
mcr p15, 0, r1, c3, c0, 0 @ load domain access control
mcr p15, 0, r0, c1, c0, 0 @ load control register
mov pc, r12
/*
* All code following this line is relocatable. It is relocated by
* the above code to the end of the decompressed kernel image and
* executed there. During this time, we have no stacks.
*
* r0 = decompressed kernel length
* r1-r3 = unused
* r4 = kernel execution address
* r5 = decompressed kernel start
* r6 = processor ID
* r7 = architecture ID
* r8-r14 = unused
*/
.align 5
reloc_start: add r8, r5, r0
debug_reloc_start
mov r1, r4
1:
.rept 4
ldmia r5!, {r0, r2, r3, r9 - r13} @ relocate kernel
stmia r1!, {r0, r2, r3, r9 - r13}
.endr
cmp r5, r8
blo 1b
debug_reloc_end
call_kernel: bl cache_clean_flush
bl cache_off
mov r0, #0
mov r1, r7 @ restore architecture number
mov pc, r4 @ call kernel
/*
* Here follow the relocatable cache support functions for the
* various processors. This is a generic hook for locating an
* entry and jumping to an instruction at the specified offset
* from the start of the block. Please note this is all position
* independent code.
*
* r1 = corrupted
* r2 = corrupted
* r3 = block offset
* r6 = corrupted
* r12 = corrupted
*/
call_cache_fn: adr r12, proc_types
mrc p15, 0, r6, c0, c0 @ get processor ID
1: ldr r1, [r12, #0] @ get value
ldr r2, [r12, #4] @ get mask
eor r1, r1, r6 @ (real ^ match)
tst r1, r2 @ & mask
addeq pc, r12, r3 @ call cache function
add r12, r12, #4*5
b 1b
/*
* Table for cache operations. This is basically:
* - CPU ID match
* - CPU ID mask
* - 'cache on' method instruction
* - 'cache off' method instruction
* - 'cache flush' method instruction
*
* We match an entry using: ((real_id ^ match) & mask) == 0
*
* Writethrough caches generally only need 'on' and 'off'
* methods. Writeback caches _must_ have the flush method
* defined.
*/
.type proc_types,#object
proc_types:
.word 0x41560600 @ ARM6/610
.word 0xffffffe0
b __arm6_cache_off @ works, but slow
b __arm6_cache_off
mov pc, lr
@ b __arm6_cache_on @ untested
@ b __arm6_cache_off
@ b __armv3_cache_flush
.word 0x41007000 @ ARM7/710
.word 0xfff8fe00
b __arm7_cache_off
b __arm7_cache_off
mov pc, lr
.word 0x41807200 @ ARM720T (writethrough)
.word 0xffffff00
b __armv4_cache_on
b __armv4_cache_off
mov pc, lr
.word 0x41129200 @ ARM920T
.word 0xff00fff0
b __armv4_cache_on
b __armv4_cache_off
b __armv4_cache_flush
.word 0x4401a100 @ sa110 / sa1100
.word 0xffffffe0
b __armv4_cache_on
b __armv4_cache_off
b __armv4_cache_flush
.word 0x6901b110 @ sa1110
.word 0xfffffff0
b __armv4_cache_on
b __armv4_cache_off
b __armv4_cache_flush
.word 0x69050000 @ xscale
.word 0xffff0000
b __armv4_cache_on
b __armv4_cache_off
b __armv4_cache_flush
.word 0 @ unrecognised type
.word 0
mov pc, lr
mov pc, lr
mov pc, lr
.size proc_types, . - proc_types
/*
* Turn off the Cache and MMU. ARMv3 does not support
* reading the control register, but ARMv4 does.
*
* On entry, r6 = processor ID
* On exit, r0, r1, r2, r3, r12 corrupted
* This routine must preserve: r4, r6, r7
*/
.align 5
cache_off: mov r3, #12 @ cache_off function
b call_cache_fn
__armv4_cache_off:
mrc p15, 0, r0, c1, c0
bic r0, r0, #0x000d
mcr p15, 0, r0, c1, c0 @ turn MMU and cache off
mov r0, #0
mcr p15, 0, r0, c7, c7 @ invalidate whole cache v4
mcr p15, 0, r0, c8, c7 @ invalidate whole TLB v4
mov pc, lr
__arm6_cache_off:
mov r0, #0x00000030 @ ARM6 control reg.
b __armv3_cache_off
__arm7_cache_off:
mov r0, #0x00000070 @ ARM7 control reg.
b __armv3_cache_off
__armv3_cache_off:
mcr p15, 0, r0, c1, c0, 0 @ turn MMU and cache off
mov r0, #0
mcr p15, 0, r0, c7, c0, 0 @ invalidate whole cache v3
mcr p15, 0, r0, c5, c0, 0 @ invalidate whole TLB v3
mov pc, lr
/*
* Clean and flush the cache to maintain consistency.
*
* On entry,
* r6 = processor ID
* On exit,
* r1, r2, r3, r12 corrupted
* This routine must preserve:
* r0, r4, r5, r6, r7
*/
.align 5
cache_clean_flush:
mov r3, #16
b call_cache_fn
__armv4_cache_flush:
bic r1, pc, #31
add r2, r1, #65536 @ 2x the largest dcache size
1: ldr r12, [r1], #32 @ s/w flush D cache
teq r1, r2
bne 1b
mcr p15, 0, r1, c7, c7, 0 @ flush I cache
mcr p15, 0, r1, c7, c10, 4 @ drain WB
mov pc, lr
__armv3_cache_flush:
mov r1, #0
mcr p15, 0, r0, c7, c0, 0 @ invalidate whole cache v3
mov pc, lr
/*
* Various debugging routines for printing hex characters and
* memory, which again must be relocatable.
*/
#ifdef DEBUG
.type phexbuf,#object
phexbuf: .space 12
.size phexbuf, . - phexbuf
phex: adr r3, phexbuf
mov r2, #0
strb r2, [r3, r1]
1: subs r1, r1, #1
movmi r0, r3
bmi puts
and r2, r0, #15
mov r0, r0, lsr #4
cmp r2, #10
addge r2, r2, #7
add r2, r2, #'0'
strb r2, [r3, r1]
b 1b
puts: loadsp r3
1: ldrb r2, [r0], #1
teq r2, #0
moveq pc, lr
2: writeb r2
mov r1, #0x00020000
3: subs r1, r1, #1
bne 3b
teq r2, #'\n'
moveq r2, #'\r'
beq 2b
teq r0, #0
bne 1b
mov pc, lr
putc:
mov r2, r0
mov r0, #0
loadsp r3
b 2b
memdump: mov r12, r0
mov r10, lr
mov r11, #0
2: mov r0, r11, lsl #2
add r0, r0, r12
mov r1, #8
bl phex
mov r0, #':'
bl putc
1: mov r0, #' '
bl putc
ldr r0, [r12, r11, lsl #2]
mov r1, #8
bl phex
and r0, r11, #7
teq r0, #3
moveq r0, #' '
bleq putc
and r0, r11, #7
add r11, r11, #1
teq r0, #7
bne 1b
mov r0, #'\n'
bl putc
cmp r11, #64
blt 2b
mov pc, r10
#endif
reloc_end:
.align
.section ".stack", "aw"
user_stack: .space 4096