OpenCloudOS-Kernel/arch/powerpc/mm/slb_low.S

336 lines
9.7 KiB
ArmAsm

/*
* Low-level SLB routines
*
* Copyright (C) 2004 David Gibson <dwg@au.ibm.com>, IBM
*
* Based on earlier C version:
* Dave Engebretsen and Mike Corrigan {engebret|mikejc}@us.ibm.com
* Copyright (c) 2001 Dave Engebretsen
* Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
*
* 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 <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/cputable.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/pgtable.h>
#include <asm/firmware.h>
#include <asm/feature-fixups.h>
/*
* This macro generates asm code to compute the VSID scramble
* function. Used in slb_allocate() and do_stab_bolted. The function
* computed is: (protovsid*VSID_MULTIPLIER) % VSID_MODULUS
*
* rt = register containing the proto-VSID and into which the
* VSID will be stored
* rx = scratch register (clobbered)
* rf = flags
*
* - rt and rx must be different registers
* - The answer will end up in the low VSID_BITS bits of rt. The higher
* bits may contain other garbage, so you may need to mask the
* result.
*/
#define ASM_VSID_SCRAMBLE(rt, rx, rf, size) \
lis rx,VSID_MULTIPLIER_##size@h; \
ori rx,rx,VSID_MULTIPLIER_##size@l; \
mulld rt,rt,rx; /* rt = rt * MULTIPLIER */ \
/* \
* powermac get slb fault before feature fixup, so make 65 bit part \
* the default part of feature fixup \
*/ \
BEGIN_MMU_FTR_SECTION \
srdi rx,rt,VSID_BITS_65_##size; \
clrldi rt,rt,(64-VSID_BITS_65_##size); \
add rt,rt,rx; \
addi rx,rt,1; \
srdi rx,rx,VSID_BITS_65_##size; \
add rt,rt,rx; \
rldimi rf,rt,SLB_VSID_SHIFT_##size,(64 - (SLB_VSID_SHIFT_##size + VSID_BITS_65_##size)); \
MMU_FTR_SECTION_ELSE \
srdi rx,rt,VSID_BITS_##size; \
clrldi rt,rt,(64-VSID_BITS_##size); \
add rt,rt,rx; /* add high and low bits */ \
addi rx,rt,1; \
srdi rx,rx,VSID_BITS_##size; /* extract 2^VSID_BITS bit */ \
add rt,rt,rx; \
rldimi rf,rt,SLB_VSID_SHIFT_##size,(64 - (SLB_VSID_SHIFT_##size + VSID_BITS_##size)); \
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_68_BIT_VA)
/* void slb_allocate(unsigned long ea);
*
* Create an SLB entry for the given EA (user or kernel).
* r3 = faulting address, r13 = PACA
* r9, r10, r11 are clobbered by this function
* r3 is preserved.
* No other registers are examined or changed.
*/
_GLOBAL(slb_allocate)
/*
* Check if the address falls within the range of the first context, or
* if we may need to handle multi context. For the first context we
* allocate the slb entry via the fast path below. For large address we
* branch out to C-code and see if additional contexts have been
* allocated.
* The test here is:
* (ea & ~REGION_MASK) >= (1ull << MAX_EA_BITS_PER_CONTEXT)
*/
rldicr. r9,r3,4,(63 - MAX_EA_BITS_PER_CONTEXT - 4)
bne- 8f
srdi r9,r3,60 /* get region */
srdi r10,r3,SID_SHIFT /* get esid */
cmpldi cr7,r9,0xc /* cmp PAGE_OFFSET for later use */
/* r3 = address, r10 = esid, cr7 = <> PAGE_OFFSET */
blt cr7,0f /* user or kernel? */
/* Check if hitting the linear mapping or some other kernel space
*/
bne cr7,1f
/* Linear mapping encoding bits, the "li" instruction below will
* be patched by the kernel at boot
*/
.globl slb_miss_kernel_load_linear
slb_miss_kernel_load_linear:
li r11,0
/*
* context = (ea >> 60) - (0xc - 1)
* r9 = region id.
*/
subi r9,r9,KERNEL_REGION_CONTEXT_OFFSET
BEGIN_FTR_SECTION
b .Lslb_finish_load
END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
b .Lslb_finish_load_1T
1:
#ifdef CONFIG_SPARSEMEM_VMEMMAP
cmpldi cr0,r9,0xf
bne 1f
/* Check virtual memmap region. To be patched at kernel boot */
.globl slb_miss_kernel_load_vmemmap
slb_miss_kernel_load_vmemmap:
li r11,0
b 6f
1:
#endif /* CONFIG_SPARSEMEM_VMEMMAP */
/*
* r10 contains the ESID, which is the original faulting EA shifted
* right by 28 bits. We need to compare that with (H_VMALLOC_END >> 28)
* which is 0xd00038000. That can't be used as an immediate, even if we
* ignored the 0xd, so we have to load it into a register, and we only
* have one register free. So we must load all of (H_VMALLOC_END >> 28)
* into a register and compare ESID against that.
*/
lis r11,(H_VMALLOC_END >> 32)@h // r11 = 0xffffffffd0000000
ori r11,r11,(H_VMALLOC_END >> 32)@l // r11 = 0xffffffffd0003800
// Rotate left 4, then mask with 0xffffffff0
rldic r11,r11,4,28 // r11 = 0xd00038000
cmpld r10,r11 // if r10 >= r11
bge 5f // goto io_mapping
/*
* vmalloc mapping gets the encoding from the PACA as the mapping
* can be demoted from 64K -> 4K dynamically on some machines.
*/
lhz r11,PACAVMALLOCSLLP(r13)
b 6f
5:
/* IO mapping */
.globl slb_miss_kernel_load_io
slb_miss_kernel_load_io:
li r11,0
6:
/*
* context = (ea >> 60) - (0xc - 1)
* r9 = region id.
*/
subi r9,r9,KERNEL_REGION_CONTEXT_OFFSET
BEGIN_FTR_SECTION
b .Lslb_finish_load
END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
b .Lslb_finish_load_1T
0: /*
* For userspace addresses, make sure this is region 0.
*/
cmpdi r9, 0
bne- 8f
/*
* user space make sure we are within the allowed limit
*/
ld r11,PACA_SLB_ADDR_LIMIT(r13)
cmpld r3,r11
bge- 8f
/* when using slices, we extract the psize off the slice bitmaps
* and then we need to get the sllp encoding off the mmu_psize_defs
* array.
*
* XXX This is a bit inefficient especially for the normal case,
* so we should try to implement a fast path for the standard page
* size using the old sllp value so we avoid the array. We cannot
* really do dynamic patching unfortunately as processes might flip
* between 4k and 64k standard page size
*/
#ifdef CONFIG_PPC_MM_SLICES
/* r10 have esid */
cmpldi r10,16
/* below SLICE_LOW_TOP */
blt 5f
/*
* Handle hpsizes,
* r9 is get_paca()->context.high_slices_psize[index], r11 is mask_index
*/
srdi r11,r10,(SLICE_HIGH_SHIFT - SLICE_LOW_SHIFT + 1) /* index */
addi r9,r11,PACAHIGHSLICEPSIZE
lbzx r9,r13,r9 /* r9 is hpsizes[r11] */
/* r11 = (r10 >> (SLICE_HIGH_SHIFT - SLICE_LOW_SHIFT)) & 0x1 */
rldicl r11,r10,(64 - (SLICE_HIGH_SHIFT - SLICE_LOW_SHIFT)),63
b 6f
5:
/*
* Handle lpsizes
* r9 is get_paca()->context.low_slices_psize[index], r11 is mask_index
*/
srdi r11,r10,1 /* index */
addi r9,r11,PACALOWSLICESPSIZE
lbzx r9,r13,r9 /* r9 is lpsizes[r11] */
rldicl r11,r10,0,63 /* r11 = r10 & 0x1 */
6:
sldi r11,r11,2 /* index * 4 */
/* Extract the psize and multiply to get an array offset */
srd r9,r9,r11
andi. r9,r9,0xf
mulli r9,r9,MMUPSIZEDEFSIZE
/* Now get to the array and obtain the sllp
*/
ld r11,PACATOC(r13)
ld r11,mmu_psize_defs@got(r11)
add r11,r11,r9
ld r11,MMUPSIZESLLP(r11)
ori r11,r11,SLB_VSID_USER
#else
/* paca context sllp already contains the SLB_VSID_USER bits */
lhz r11,PACACONTEXTSLLP(r13)
#endif /* CONFIG_PPC_MM_SLICES */
ld r9,PACACONTEXTID(r13)
BEGIN_FTR_SECTION
cmpldi r10,0x1000
bge .Lslb_finish_load_1T
END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
b .Lslb_finish_load
8: /* invalid EA - return an error indication */
crset 4*cr0+eq /* indicate failure */
blr
/*
* Finish loading of an SLB entry and return
*
* r3 = EA, r9 = context, r10 = ESID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET
*/
.Lslb_finish_load:
rldimi r10,r9,ESID_BITS,0
ASM_VSID_SCRAMBLE(r10,r9,r11,256M)
/* r3 = EA, r11 = VSID data */
/*
* Find a slot, round robin. Previously we tried to find a
* free slot first but that took too long. Unfortunately we
* dont have any LRU information to help us choose a slot.
*/
mr r9,r3
/* slb_finish_load_1T continues here. r9=EA with non-ESID bits clear */
7: ld r10,PACASTABRR(r13)
addi r10,r10,1
/* This gets soft patched on boot. */
.globl slb_compare_rr_to_size
slb_compare_rr_to_size:
cmpldi r10,0
blt+ 4f
li r10,SLB_NUM_BOLTED
4:
std r10,PACASTABRR(r13)
3:
rldimi r9,r10,0,36 /* r9 = EA[0:35] | entry */
oris r10,r9,SLB_ESID_V@h /* r10 = r9 | SLB_ESID_V */
/* r9 = ESID data, r11 = VSID data */
/*
* No need for an isync before or after this slbmte. The exception
* we enter with and the rfid we exit with are context synchronizing.
*/
slbmte r11,r10
/* we're done for kernel addresses */
crclr 4*cr0+eq /* set result to "success" */
bgelr cr7
/* Update the slb cache */
lhz r9,PACASLBCACHEPTR(r13) /* offset = paca->slb_cache_ptr */
cmpldi r9,SLB_CACHE_ENTRIES
bge 1f
/* still room in the slb cache */
sldi r11,r9,2 /* r11 = offset * sizeof(u32) */
srdi r10,r10,28 /* get the 36 bits of the ESID */
add r11,r11,r13 /* r11 = (u32 *)paca + offset */
stw r10,PACASLBCACHE(r11) /* paca->slb_cache[offset] = esid */
addi r9,r9,1 /* offset++ */
b 2f
1: /* offset >= SLB_CACHE_ENTRIES */
li r9,SLB_CACHE_ENTRIES+1
2:
sth r9,PACASLBCACHEPTR(r13) /* paca->slb_cache_ptr = offset */
crclr 4*cr0+eq /* set result to "success" */
blr
/*
* Finish loading of a 1T SLB entry (for the kernel linear mapping) and return.
*
* r3 = EA, r9 = context, r10 = ESID(256MB), r11 = flags, clobbers r9
*/
.Lslb_finish_load_1T:
srdi r10,r10,(SID_SHIFT_1T - SID_SHIFT) /* get 1T ESID */
rldimi r10,r9,ESID_BITS_1T,0
ASM_VSID_SCRAMBLE(r10,r9,r11,1T)
li r10,MMU_SEGSIZE_1T
rldimi r11,r10,SLB_VSID_SSIZE_SHIFT,0 /* insert segment size */
/* r3 = EA, r11 = VSID data */
clrrdi r9,r3,SID_SHIFT_1T /* clear out non-ESID bits */
b 7b
_ASM_NOKPROBE_SYMBOL(slb_allocate)
_ASM_NOKPROBE_SYMBOL(slb_miss_kernel_load_linear)
_ASM_NOKPROBE_SYMBOL(slb_miss_kernel_load_io)
_ASM_NOKPROBE_SYMBOL(slb_compare_rr_to_size)
#ifdef CONFIG_SPARSEMEM_VMEMMAP
_ASM_NOKPROBE_SYMBOL(slb_miss_kernel_load_vmemmap)
#endif