/*
|
* This file contains miscellaneous low-level functions.
|
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
|
*
|
* Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
|
* and Paul Mackerras.
|
* Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com)
|
* PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
|
*
|
* 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; either version
|
* 2 of the License, or (at your option) any later version.
|
*
|
*/
|
|
#include <linux/sys.h>
|
#include <asm/unistd.h>
|
#include <asm/errno.h>
|
#include <asm/processor.h>
|
#include <asm/page.h>
|
#include <asm/cache.h>
|
#include <asm/ppc_asm.h>
|
#include <asm/asm-offsets.h>
|
#include <asm/cputable.h>
|
#include <asm/thread_info.h>
|
#include <asm/kexec.h>
|
#include <asm/ptrace.h>
|
#include <asm/mmu.h>
|
#include <asm/export.h>
|
#include <asm/feature-fixups.h>
|
|
.text
|
|
_GLOBAL(call_do_softirq)
|
mflr r0
|
std r0,16(r1)
|
stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
|
mr r1,r3
|
bl __do_softirq
|
ld r1,0(r1)
|
ld r0,16(r1)
|
mtlr r0
|
blr
|
|
_GLOBAL(call_do_irq)
|
mflr r0
|
std r0,16(r1)
|
stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
|
mr r1,r4
|
bl __do_irq
|
ld r1,0(r1)
|
ld r0,16(r1)
|
mtlr r0
|
blr
|
|
.section ".toc","aw"
|
PPC64_CACHES:
|
.tc ppc64_caches[TC],ppc64_caches
|
.section ".text"
|
|
/*
|
* Write any modified data cache blocks out to memory
|
* and invalidate the corresponding instruction cache blocks.
|
*
|
* flush_icache_range(unsigned long start, unsigned long stop)
|
*
|
* flush all bytes from start through stop-1 inclusive
|
*/
|
|
_GLOBAL_TOC(flush_icache_range)
|
BEGIN_FTR_SECTION
|
PURGE_PREFETCHED_INS
|
blr
|
END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
|
/*
|
* Flush the data cache to memory
|
*
|
* Different systems have different cache line sizes
|
* and in some cases i-cache and d-cache line sizes differ from
|
* each other.
|
*/
|
ld r10,PPC64_CACHES@toc(r2)
|
lwz r7,DCACHEL1BLOCKSIZE(r10)/* Get cache block size */
|
addi r5,r7,-1
|
andc r6,r3,r5 /* round low to line bdy */
|
subf r8,r6,r4 /* compute length */
|
add r8,r8,r5 /* ensure we get enough */
|
lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of cache block size */
|
srd. r8,r8,r9 /* compute line count */
|
beqlr /* nothing to do? */
|
mtctr r8
|
1: dcbst 0,r6
|
add r6,r6,r7
|
bdnz 1b
|
sync
|
|
/* Now invalidate the instruction cache */
|
|
lwz r7,ICACHEL1BLOCKSIZE(r10) /* Get Icache block size */
|
addi r5,r7,-1
|
andc r6,r3,r5 /* round low to line bdy */
|
subf r8,r6,r4 /* compute length */
|
add r8,r8,r5
|
lwz r9,ICACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of Icache block size */
|
srd. r8,r8,r9 /* compute line count */
|
beqlr /* nothing to do? */
|
mtctr r8
|
2: icbi 0,r6
|
add r6,r6,r7
|
bdnz 2b
|
isync
|
blr
|
_ASM_NOKPROBE_SYMBOL(flush_icache_range)
|
EXPORT_SYMBOL(flush_icache_range)
|
|
/*
|
* Like above, but only do the D-cache.
|
*
|
* flush_dcache_range(unsigned long start, unsigned long stop)
|
*
|
* flush all bytes from start to stop-1 inclusive
|
*/
|
_GLOBAL_TOC(flush_dcache_range)
|
|
/*
|
* Flush the data cache to memory
|
*
|
* Different systems have different cache line sizes
|
*/
|
ld r10,PPC64_CACHES@toc(r2)
|
lwz r7,DCACHEL1BLOCKSIZE(r10) /* Get dcache block size */
|
addi r5,r7,-1
|
andc r6,r3,r5 /* round low to line bdy */
|
subf r8,r6,r4 /* compute length */
|
add r8,r8,r5 /* ensure we get enough */
|
lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of dcache block size */
|
srd. r8,r8,r9 /* compute line count */
|
beqlr /* nothing to do? */
|
mtctr r8
|
0: dcbst 0,r6
|
add r6,r6,r7
|
bdnz 0b
|
sync
|
blr
|
EXPORT_SYMBOL(flush_dcache_range)
|
|
_GLOBAL(flush_inval_dcache_range)
|
ld r10,PPC64_CACHES@toc(r2)
|
lwz r7,DCACHEL1BLOCKSIZE(r10) /* Get dcache block size */
|
addi r5,r7,-1
|
andc r6,r3,r5 /* round low to line bdy */
|
subf r8,r6,r4 /* compute length */
|
add r8,r8,r5 /* ensure we get enough */
|
lwz r9,DCACHEL1LOGBLOCKSIZE(r10)/* Get log-2 of dcache block size */
|
srd. r8,r8,r9 /* compute line count */
|
beqlr /* nothing to do? */
|
sync
|
isync
|
mtctr r8
|
0: dcbf 0,r6
|
add r6,r6,r7
|
bdnz 0b
|
sync
|
isync
|
blr
|
|
|
/*
|
* Flush a particular page from the data cache to RAM.
|
* Note: this is necessary because the instruction cache does *not*
|
* snoop from the data cache.
|
*
|
* void __flush_dcache_icache(void *page)
|
*/
|
_GLOBAL(__flush_dcache_icache)
|
/*
|
* Flush the data cache to memory
|
*
|
* Different systems have different cache line sizes
|
*/
|
|
BEGIN_FTR_SECTION
|
PURGE_PREFETCHED_INS
|
blr
|
END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
|
|
/* Flush the dcache */
|
ld r7,PPC64_CACHES@toc(r2)
|
clrrdi r3,r3,PAGE_SHIFT /* Page align */
|
lwz r4,DCACHEL1BLOCKSPERPAGE(r7) /* Get # dcache blocks per page */
|
lwz r5,DCACHEL1BLOCKSIZE(r7) /* Get dcache block size */
|
mr r6,r3
|
mtctr r4
|
0: dcbst 0,r6
|
add r6,r6,r5
|
bdnz 0b
|
sync
|
|
/* Now invalidate the icache */
|
|
lwz r4,ICACHEL1BLOCKSPERPAGE(r7) /* Get # icache blocks per page */
|
lwz r5,ICACHEL1BLOCKSIZE(r7) /* Get icache block size */
|
mtctr r4
|
1: icbi 0,r3
|
add r3,r3,r5
|
bdnz 1b
|
isync
|
blr
|
|
_GLOBAL(__bswapdi2)
|
EXPORT_SYMBOL(__bswapdi2)
|
srdi r8,r3,32
|
rlwinm r7,r3,8,0xffffffff
|
rlwimi r7,r3,24,0,7
|
rlwinm r9,r8,8,0xffffffff
|
rlwimi r7,r3,24,16,23
|
rlwimi r9,r8,24,0,7
|
rlwimi r9,r8,24,16,23
|
sldi r7,r7,32
|
or r3,r7,r9
|
blr
|
|
|
#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
|
_GLOBAL(rmci_on)
|
sync
|
isync
|
li r3,0x100
|
rldicl r3,r3,32,0
|
mfspr r5,SPRN_HID4
|
or r5,r5,r3
|
sync
|
mtspr SPRN_HID4,r5
|
isync
|
slbia
|
isync
|
sync
|
blr
|
|
_GLOBAL(rmci_off)
|
sync
|
isync
|
li r3,0x100
|
rldicl r3,r3,32,0
|
mfspr r5,SPRN_HID4
|
andc r5,r5,r3
|
sync
|
mtspr SPRN_HID4,r5
|
isync
|
slbia
|
isync
|
sync
|
blr
|
#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
|
|
#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
|
|
/*
|
* Do an IO access in real mode
|
*/
|
_GLOBAL(real_readb)
|
mfmsr r7
|
ori r0,r7,MSR_DR
|
xori r0,r0,MSR_DR
|
sync
|
mtmsrd r0
|
sync
|
isync
|
mfspr r6,SPRN_HID4
|
rldicl r5,r6,32,0
|
ori r5,r5,0x100
|
rldicl r5,r5,32,0
|
sync
|
mtspr SPRN_HID4,r5
|
isync
|
slbia
|
isync
|
lbz r3,0(r3)
|
sync
|
mtspr SPRN_HID4,r6
|
isync
|
slbia
|
isync
|
mtmsrd r7
|
sync
|
isync
|
blr
|
|
/*
|
* Do an IO access in real mode
|
*/
|
_GLOBAL(real_writeb)
|
mfmsr r7
|
ori r0,r7,MSR_DR
|
xori r0,r0,MSR_DR
|
sync
|
mtmsrd r0
|
sync
|
isync
|
mfspr r6,SPRN_HID4
|
rldicl r5,r6,32,0
|
ori r5,r5,0x100
|
rldicl r5,r5,32,0
|
sync
|
mtspr SPRN_HID4,r5
|
isync
|
slbia
|
isync
|
stb r3,0(r4)
|
sync
|
mtspr SPRN_HID4,r6
|
isync
|
slbia
|
isync
|
mtmsrd r7
|
sync
|
isync
|
blr
|
#endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) */
|
|
#ifdef CONFIG_PPC_PASEMI
|
|
_GLOBAL(real_205_readb)
|
mfmsr r7
|
ori r0,r7,MSR_DR
|
xori r0,r0,MSR_DR
|
sync
|
mtmsrd r0
|
sync
|
isync
|
LBZCIX(R3,R0,R3)
|
isync
|
mtmsrd r7
|
sync
|
isync
|
blr
|
|
_GLOBAL(real_205_writeb)
|
mfmsr r7
|
ori r0,r7,MSR_DR
|
xori r0,r0,MSR_DR
|
sync
|
mtmsrd r0
|
sync
|
isync
|
STBCIX(R3,R0,R4)
|
isync
|
mtmsrd r7
|
sync
|
isync
|
blr
|
|
#endif /* CONFIG_PPC_PASEMI */
|
|
|
#if defined(CONFIG_CPU_FREQ_PMAC64) || defined(CONFIG_CPU_FREQ_MAPLE)
|
/*
|
* SCOM access functions for 970 (FX only for now)
|
*
|
* unsigned long scom970_read(unsigned int address);
|
* void scom970_write(unsigned int address, unsigned long value);
|
*
|
* The address passed in is the 24 bits register address. This code
|
* is 970 specific and will not check the status bits, so you should
|
* know what you are doing.
|
*/
|
_GLOBAL(scom970_read)
|
/* interrupts off */
|
mfmsr r4
|
ori r0,r4,MSR_EE
|
xori r0,r0,MSR_EE
|
mtmsrd r0,1
|
|
/* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits
|
* (including parity). On current CPUs they must be 0'd,
|
* and finally or in RW bit
|
*/
|
rlwinm r3,r3,8,0,15
|
ori r3,r3,0x8000
|
|
/* do the actual scom read */
|
sync
|
mtspr SPRN_SCOMC,r3
|
isync
|
mfspr r3,SPRN_SCOMD
|
isync
|
mfspr r0,SPRN_SCOMC
|
isync
|
|
/* XXX: fixup result on some buggy 970's (ouch ! we lost a bit, bah
|
* that's the best we can do). Not implemented yet as we don't use
|
* the scom on any of the bogus CPUs yet, but may have to be done
|
* ultimately
|
*/
|
|
/* restore interrupts */
|
mtmsrd r4,1
|
blr
|
|
|
_GLOBAL(scom970_write)
|
/* interrupts off */
|
mfmsr r5
|
ori r0,r5,MSR_EE
|
xori r0,r0,MSR_EE
|
mtmsrd r0,1
|
|
/* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits
|
* (including parity). On current CPUs they must be 0'd.
|
*/
|
|
rlwinm r3,r3,8,0,15
|
|
sync
|
mtspr SPRN_SCOMD,r4 /* write data */
|
isync
|
mtspr SPRN_SCOMC,r3 /* write command */
|
isync
|
mfspr 3,SPRN_SCOMC
|
isync
|
|
/* restore interrupts */
|
mtmsrd r5,1
|
blr
|
#endif /* CONFIG_CPU_FREQ_PMAC64 || CONFIG_CPU_FREQ_MAPLE */
|
|
/* kexec_wait(phys_cpu)
|
*
|
* wait for the flag to change, indicating this kernel is going away but
|
* the slave code for the next one is at addresses 0 to 100.
|
*
|
* This is used by all slaves, even those that did not find a matching
|
* paca in the secondary startup code.
|
*
|
* Physical (hardware) cpu id should be in r3.
|
*/
|
_GLOBAL(kexec_wait)
|
bl 1f
|
1: mflr r5
|
addi r5,r5,kexec_flag-1b
|
|
99: HMT_LOW
|
#ifdef CONFIG_KEXEC_CORE /* use no memory without kexec */
|
lwz r4,0(r5)
|
cmpwi 0,r4,0
|
beq 99b
|
#ifdef CONFIG_PPC_BOOK3S_64
|
li r10,0x60
|
mfmsr r11
|
clrrdi r11,r11,1 /* Clear MSR_LE */
|
mtsrr0 r10
|
mtsrr1 r11
|
rfid
|
#else
|
/* Create TLB entry in book3e_secondary_core_init */
|
li r4,0
|
ba 0x60
|
#endif
|
#endif
|
|
/* this can be in text because we won't change it until we are
|
* running in real anyways
|
*/
|
kexec_flag:
|
.long 0
|
|
|
#ifdef CONFIG_KEXEC_CORE
|
#ifdef CONFIG_PPC_BOOK3E
|
/*
|
* BOOK3E has no real MMU mode, so we have to setup the initial TLB
|
* for a core to identity map v:0 to p:0. This current implementation
|
* assumes that 1G is enough for kexec.
|
*/
|
kexec_create_tlb:
|
/*
|
* Invalidate all non-IPROT TLB entries to avoid any TLB conflict.
|
* IPROT TLB entries should be >= PAGE_OFFSET and thus not conflict.
|
*/
|
PPC_TLBILX_ALL(0,R0)
|
sync
|
isync
|
|
mfspr r10,SPRN_TLB1CFG
|
andi. r10,r10,TLBnCFG_N_ENTRY /* Extract # entries */
|
subi r10,r10,1 /* Last entry: no conflict with kernel text */
|
lis r9,MAS0_TLBSEL(1)@h
|
rlwimi r9,r10,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r9) */
|
|
/* Set up a temp identity mapping v:0 to p:0 and return to it. */
|
#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
|
#define M_IF_NEEDED MAS2_M
|
#else
|
#define M_IF_NEEDED 0
|
#endif
|
mtspr SPRN_MAS0,r9
|
|
lis r9,(MAS1_VALID|MAS1_IPROT)@h
|
ori r9,r9,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l
|
mtspr SPRN_MAS1,r9
|
|
LOAD_REG_IMMEDIATE(r9, 0x0 | M_IF_NEEDED)
|
mtspr SPRN_MAS2,r9
|
|
LOAD_REG_IMMEDIATE(r9, 0x0 | MAS3_SR | MAS3_SW | MAS3_SX)
|
mtspr SPRN_MAS3,r9
|
li r9,0
|
mtspr SPRN_MAS7,r9
|
|
tlbwe
|
isync
|
blr
|
#endif
|
|
/* kexec_smp_wait(void)
|
*
|
* call with interrupts off
|
* note: this is a terminal routine, it does not save lr
|
*
|
* get phys id from paca
|
* switch to real mode
|
* mark the paca as no longer used
|
* join other cpus in kexec_wait(phys_id)
|
*/
|
_GLOBAL(kexec_smp_wait)
|
lhz r3,PACAHWCPUID(r13)
|
bl real_mode
|
|
li r4,KEXEC_STATE_REAL_MODE
|
stb r4,PACAKEXECSTATE(r13)
|
SYNC
|
|
b kexec_wait
|
|
/*
|
* switch to real mode (turn mmu off)
|
* we use the early kernel trick that the hardware ignores bits
|
* 0 and 1 (big endian) of the effective address in real mode
|
*
|
* don't overwrite r3 here, it is live for kexec_wait above.
|
*/
|
real_mode: /* assume normal blr return */
|
#ifdef CONFIG_PPC_BOOK3E
|
/* Create an identity mapping. */
|
b kexec_create_tlb
|
#else
|
1: li r9,MSR_RI
|
li r10,MSR_DR|MSR_IR
|
mflr r11 /* return address to SRR0 */
|
mfmsr r12
|
andc r9,r12,r9
|
andc r10,r12,r10
|
|
mtmsrd r9,1
|
mtspr SPRN_SRR1,r10
|
mtspr SPRN_SRR0,r11
|
rfid
|
#endif
|
|
/*
|
* kexec_sequence(newstack, start, image, control, clear_all(),
|
copy_with_mmu_off)
|
*
|
* does the grungy work with stack switching and real mode switches
|
* also does simple calls to other code
|
*/
|
|
_GLOBAL(kexec_sequence)
|
mflr r0
|
std r0,16(r1)
|
|
/* switch stacks to newstack -- &kexec_stack.stack */
|
stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
|
mr r1,r3
|
|
li r0,0
|
std r0,16(r1)
|
|
BEGIN_FTR_SECTION
|
/*
|
* This is the best time to turn AMR/IAMR off.
|
* key 0 is used in radix for supervisor<->user
|
* protection, but on hash key 0 is reserved
|
* ideally we want to enter with a clean state.
|
* NOTE, we rely on r0 being 0 from above.
|
*/
|
mtspr SPRN_IAMR,r0
|
BEGIN_FTR_SECTION_NESTED(42)
|
mtspr SPRN_AMOR,r0
|
END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42)
|
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
|
|
/* save regs for local vars on new stack.
|
* yes, we won't go back, but ...
|
*/
|
std r31,-8(r1)
|
std r30,-16(r1)
|
std r29,-24(r1)
|
std r28,-32(r1)
|
std r27,-40(r1)
|
std r26,-48(r1)
|
std r25,-56(r1)
|
|
stdu r1,-STACK_FRAME_OVERHEAD-64(r1)
|
|
/* save args into preserved regs */
|
mr r31,r3 /* newstack (both) */
|
mr r30,r4 /* start (real) */
|
mr r29,r5 /* image (virt) */
|
mr r28,r6 /* control, unused */
|
mr r27,r7 /* clear_all() fn desc */
|
mr r26,r8 /* copy_with_mmu_off */
|
lhz r25,PACAHWCPUID(r13) /* get our phys cpu from paca */
|
|
/* disable interrupts, we are overwriting kernel data next */
|
#ifdef CONFIG_PPC_BOOK3E
|
wrteei 0
|
#else
|
mfmsr r3
|
rlwinm r3,r3,0,17,15
|
mtmsrd r3,1
|
#endif
|
|
/* We need to turn the MMU off unless we are in hash mode
|
* under a hypervisor
|
*/
|
cmpdi r26,0
|
beq 1f
|
bl real_mode
|
1:
|
/* copy dest pages, flush whole dest image */
|
mr r3,r29
|
bl kexec_copy_flush /* (image) */
|
|
/* turn off mmu now if not done earlier */
|
cmpdi r26,0
|
bne 1f
|
bl real_mode
|
|
/* copy 0x100 bytes starting at start to 0 */
|
1: li r3,0
|
mr r4,r30 /* start, aka phys mem offset */
|
li r5,0x100
|
li r6,0
|
bl copy_and_flush /* (dest, src, copy limit, start offset) */
|
1: /* assume normal blr return */
|
|
/* release other cpus to the new kernel secondary start at 0x60 */
|
mflr r5
|
li r6,1
|
stw r6,kexec_flag-1b(5)
|
|
cmpdi r27,0
|
beq 1f
|
|
/* clear out hardware hash page table and tlb */
|
#ifdef PPC64_ELF_ABI_v1
|
ld r12,0(r27) /* deref function descriptor */
|
#else
|
mr r12,r27
|
#endif
|
mtctr r12
|
bctrl /* mmu_hash_ops.hpte_clear_all(void); */
|
|
/*
|
* kexec image calling is:
|
* the first 0x100 bytes of the entry point are copied to 0
|
*
|
* all slaves branch to slave = 0x60 (absolute)
|
* slave(phys_cpu_id);
|
*
|
* master goes to start = entry point
|
* start(phys_cpu_id, start, 0);
|
*
|
*
|
* a wrapper is needed to call existing kernels, here is an approximate
|
* description of one method:
|
*
|
* v2: (2.6.10)
|
* start will be near the boot_block (maybe 0x100 bytes before it?)
|
* it will have a 0x60, which will b to boot_block, where it will wait
|
* and 0 will store phys into struct boot-block and load r3 from there,
|
* copy kernel 0-0x100 and tell slaves to back down to 0x60 again
|
*
|
* v1: (2.6.9)
|
* boot block will have all cpus scanning device tree to see if they
|
* are the boot cpu ?????
|
* other device tree differences (prop sizes, va vs pa, etc)...
|
*/
|
1: mr r3,r25 # my phys cpu
|
mr r4,r30 # start, aka phys mem offset
|
mtlr 4
|
li r5,0
|
blr /* image->start(physid, image->start, 0); */
|
#endif /* CONFIG_KEXEC_CORE */
|
