OpenCloudOS-Kernel/arch/tile/kernel/relocate_kernel.S

281 lines
6.4 KiB
ArmAsm
Raw Normal View History

/*
* Copyright 2010 Tilera Corporation. 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
* as published by the Free Software Foundation, version 2.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for
* more details.
*
* copy new kernel into place and then call hv_reexec
*
*/
#include <linux/linkage.h>
#include <arch/chip.h>
#include <asm/page.h>
#include <hv/hypervisor.h>
#define ___hvb MEM_SV_INTRPT + HV_GLUE_START_CPA
#define ___hv_dispatch(f) (___hvb + (HV_DISPATCH_ENTRY_SIZE * f))
#define ___hv_console_putc ___hv_dispatch(HV_DISPATCH_CONSOLE_PUTC)
#define ___hv_halt ___hv_dispatch(HV_DISPATCH_HALT)
#define ___hv_reexec ___hv_dispatch(HV_DISPATCH_REEXEC)
#define ___hv_flush_remote ___hv_dispatch(HV_DISPATCH_FLUSH_REMOTE)
#undef RELOCATE_NEW_KERNEL_VERBOSE
STD_ENTRY(relocate_new_kernel)
move r30, r0 /* page list */
move r31, r1 /* address of page we are on */
move r32, r2 /* start address of new kernel */
shri r1, r1, PAGE_SHIFT
addi r1, r1, 1
shli sp, r1, PAGE_SHIFT
addi sp, sp, -8
/* we now have a stack (whether we need one or not) */
moveli r40, lo16(___hv_console_putc)
auli r40, r40, ha16(___hv_console_putc)
#ifdef RELOCATE_NEW_KERNEL_VERBOSE
moveli r0, 'r'
jalr r40
moveli r0, '_'
jalr r40
moveli r0, 'n'
jalr r40
moveli r0, '_'
jalr r40
moveli r0, 'k'
jalr r40
moveli r0, '\n'
jalr r40
#endif
/*
* Throughout this code r30 is pointer to the element of page
* list we are working on.
*
* Normally we get to the next element of the page list by
* incrementing r30 by four. The exception is if the element
* on the page list is an IND_INDIRECTION in which case we use
* the element with the low bits masked off as the new value
* of r30.
*
* To get this started, we need the value passed to us (which
* will always be an IND_INDIRECTION) in memory somewhere with
* r30 pointing at it. To do that, we push the value passed
* to us on the stack and make r30 point to it.
*/
sw sp, r30
move r30, sp
addi sp, sp, -8
#if CHIP_HAS_CBOX_HOME_MAP()
/*
* On TILEPro, we need to flush all tiles' caches, since we may
* have been doing hash-for-home caching there. Note that we
* must do this _after_ we're completely done modifying any memory
* other than our output buffer (which we know is locally cached).
* We want the caches to be fully clean when we do the reexec,
* because the hypervisor is going to do this flush again at that
* point, and we don't want that second flush to overwrite any memory.
*/
{
move r0, zero /* cache_pa */
move r1, zero
}
{
auli r2, zero, ha16(HV_FLUSH_EVICT_L2) /* cache_control */
movei r3, -1 /* cache_cpumask; -1 means all client tiles */
}
{
move r4, zero /* tlb_va */
move r5, zero /* tlb_length */
}
{
move r6, zero /* tlb_pgsize */
move r7, zero /* tlb_cpumask */
}
{
move r8, zero /* asids */
moveli r20, lo16(___hv_flush_remote)
}
{
move r9, zero /* asidcount */
auli r20, r20, ha16(___hv_flush_remote)
}
jalr r20
#endif
/* r33 is destination pointer, default to zero */
moveli r33, 0
.Lloop: lw r10, r30
andi r9, r10, 0xf /* low 4 bits tell us what type it is */
xor r10, r10, r9 /* r10 is now value with low 4 bits stripped */
seqi r0, r9, 0x1 /* IND_DESTINATION */
bzt r0, .Ltry2
move r33, r10
#ifdef RELOCATE_NEW_KERNEL_VERBOSE
moveli r0, 'd'
jalr r40
#endif
addi r30, r30, 4
j .Lloop
.Ltry2:
seqi r0, r9, 0x2 /* IND_INDIRECTION */
bzt r0, .Ltry4
move r30, r10
#ifdef RELOCATE_NEW_KERNEL_VERBOSE
moveli r0, 'i'
jalr r40
#endif
j .Lloop
.Ltry4:
seqi r0, r9, 0x4 /* IND_DONE */
bzt r0, .Ltry8
mf
#ifdef RELOCATE_NEW_KERNEL_VERBOSE
moveli r0, 'D'
jalr r40
moveli r0, '\n'
jalr r40
#endif
move r0, r32
moveli r1, 0 /* arg to hv_reexec is 64 bits */
moveli r41, lo16(___hv_reexec)
auli r41, r41, ha16(___hv_reexec)
jalr r41
/* we should not get here */
moveli r0, '?'
jalr r40
moveli r0, '\n'
jalr r40
j .Lhalt
.Ltry8: seqi r0, r9, 0x8 /* IND_SOURCE */
bz r0, .Lerr /* unknown type */
/* copy page at r10 to page at r33 */
move r11, r33
moveli r0, lo16(PAGE_SIZE)
auli r0, r0, ha16(PAGE_SIZE)
add r33, r33, r0
/* copy word at r10 to word at r11 until r11 equals r33 */
/* We know page size must be multiple of 16, so we can unroll
* 16 times safely without any edge case checking.
*
* Issue a flush of the destination every 16 words to avoid
* incoherence when starting the new kernel. (Now this is
* just good paranoia because the hv_reexec call will also
* take care of this.)
*/
1:
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0; addi r11, r11, 4 }
{ lw r0, r10; addi r10, r10, 4 }
{ sw r11, r0 }
{ flush r11 ; addi r11, r11, 4 }
seq r0, r33, r11
bzt r0, 1b
#ifdef RELOCATE_NEW_KERNEL_VERBOSE
moveli r0, 's'
jalr r40
#endif
addi r30, r30, 4
j .Lloop
.Lerr: moveli r0, 'e'
jalr r40
moveli r0, 'r'
jalr r40
moveli r0, 'r'
jalr r40
moveli r0, '\n'
jalr r40
.Lhalt:
moveli r41, lo16(___hv_halt)
auli r41, r41, ha16(___hv_halt)
jalr r41
STD_ENDPROC(relocate_new_kernel)
.section .rodata,"a"
.globl relocate_new_kernel_size
relocate_new_kernel_size:
.long .Lend_relocate_new_kernel - relocate_new_kernel