linux-sg2042/arch/powerpc/mm/hash_low_32.S

610 lines
17 KiB
ArmAsm

/*
* $Id: hashtable.S,v 1.6 1999/10/08 01:56:15 paulus Exp $
*
* PowerPC version
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
* Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
* Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
* Adapted for Power Macintosh by Paul Mackerras.
* Low-level exception handlers and MMU support
* rewritten by Paul Mackerras.
* Copyright (C) 1996 Paul Mackerras.
*
* This file contains low-level assembler routines for managing
* the PowerPC MMU hash table. (PPC 8xx processors don't use a
* hash table, so this file is not used on them.)
*
* 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/reg.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/cputable.h>
#include <asm/ppc_asm.h>
#include <asm/thread_info.h>
#include <asm/asm-offsets.h>
#ifdef CONFIG_SMP
.section .bss
.align 2
.globl mmu_hash_lock
mmu_hash_lock:
.space 4
#endif /* CONFIG_SMP */
/*
* Sync CPUs with hash_page taking & releasing the hash
* table lock
*/
#ifdef CONFIG_SMP
.text
_GLOBAL(hash_page_sync)
lis r8,mmu_hash_lock@h
ori r8,r8,mmu_hash_lock@l
lis r0,0x0fff
b 10f
11: lwz r6,0(r8)
cmpwi 0,r6,0
bne 11b
10: lwarx r6,0,r8
cmpwi 0,r6,0
bne- 11b
stwcx. r0,0,r8
bne- 10b
isync
eieio
li r0,0
stw r0,0(r8)
blr
#endif
/*
* Load a PTE into the hash table, if possible.
* The address is in r4, and r3 contains an access flag:
* _PAGE_RW (0x400) if a write.
* r9 contains the SRR1 value, from which we use the MSR_PR bit.
* SPRG3 contains the physical address of the current task's thread.
*
* Returns to the caller if the access is illegal or there is no
* mapping for the address. Otherwise it places an appropriate PTE
* in the hash table and returns from the exception.
* Uses r0, r3 - r8, ctr, lr.
*/
.text
_GLOBAL(hash_page)
tophys(r7,0) /* gets -KERNELBASE into r7 */
#ifdef CONFIG_SMP
addis r8,r7,mmu_hash_lock@h
ori r8,r8,mmu_hash_lock@l
lis r0,0x0fff
b 10f
11: lwz r6,0(r8)
cmpwi 0,r6,0
bne 11b
10: lwarx r6,0,r8
cmpwi 0,r6,0
bne- 11b
stwcx. r0,0,r8
bne- 10b
isync
#endif
/* Get PTE (linux-style) and check access */
lis r0,KERNELBASE@h /* check if kernel address */
cmplw 0,r4,r0
mfspr r8,SPRN_SPRG3 /* current task's THREAD (phys) */
ori r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */
lwz r5,PGDIR(r8) /* virt page-table root */
blt+ 112f /* assume user more likely */
lis r5,swapper_pg_dir@ha /* if kernel address, use */
addi r5,r5,swapper_pg_dir@l /* kernel page table */
rlwimi r3,r9,32-12,29,29 /* MSR_PR -> _PAGE_USER */
112: add r5,r5,r7 /* convert to phys addr */
rlwimi r5,r4,12,20,29 /* insert top 10 bits of address */
lwz r8,0(r5) /* get pmd entry */
rlwinm. r8,r8,0,0,19 /* extract address of pte page */
#ifdef CONFIG_SMP
beq- hash_page_out /* return if no mapping */
#else
/* XXX it seems like the 601 will give a machine fault on the
rfi if its alignment is wrong (bottom 4 bits of address are
8 or 0xc) and we have had a not-taken conditional branch
to the address following the rfi. */
beqlr-
#endif
rlwimi r8,r4,22,20,29 /* insert next 10 bits of address */
rlwinm r0,r3,32-3,24,24 /* _PAGE_RW access -> _PAGE_DIRTY */
ori r0,r0,_PAGE_ACCESSED|_PAGE_HASHPTE
/*
* Update the linux PTE atomically. We do the lwarx up-front
* because almost always, there won't be a permission violation
* and there won't already be an HPTE, and thus we will have
* to update the PTE to set _PAGE_HASHPTE. -- paulus.
*/
retry:
lwarx r6,0,r8 /* get linux-style pte */
andc. r5,r3,r6 /* check access & ~permission */
#ifdef CONFIG_SMP
bne- hash_page_out /* return if access not permitted */
#else
bnelr-
#endif
or r5,r0,r6 /* set accessed/dirty bits */
stwcx. r5,0,r8 /* attempt to update PTE */
bne- retry /* retry if someone got there first */
mfsrin r3,r4 /* get segment reg for segment */
mfctr r0
stw r0,_CTR(r11)
bl create_hpte /* add the hash table entry */
#ifdef CONFIG_SMP
eieio
addis r8,r7,mmu_hash_lock@ha
li r0,0
stw r0,mmu_hash_lock@l(r8)
#endif
/* Return from the exception */
lwz r5,_CTR(r11)
mtctr r5
lwz r0,GPR0(r11)
lwz r7,GPR7(r11)
lwz r8,GPR8(r11)
b fast_exception_return
#ifdef CONFIG_SMP
hash_page_out:
eieio
addis r8,r7,mmu_hash_lock@ha
li r0,0
stw r0,mmu_hash_lock@l(r8)
blr
#endif /* CONFIG_SMP */
/*
* Add an entry for a particular page to the hash table.
*
* add_hash_page(unsigned context, unsigned long va, unsigned long pmdval)
*
* We assume any necessary modifications to the pte (e.g. setting
* the accessed bit) have already been done and that there is actually
* a hash table in use (i.e. we're not on a 603).
*/
_GLOBAL(add_hash_page)
mflr r0
stw r0,4(r1)
/* Convert context and va to VSID */
mulli r3,r3,897*16 /* multiply context by context skew */
rlwinm r0,r4,4,28,31 /* get ESID (top 4 bits of va) */
mulli r0,r0,0x111 /* multiply by ESID skew */
add r3,r3,r0 /* note create_hpte trims to 24 bits */
#ifdef CONFIG_SMP
rlwinm r8,r1,0,0,18 /* use cpu number to make tag */
lwz r8,TI_CPU(r8) /* to go in mmu_hash_lock */
oris r8,r8,12
#endif /* CONFIG_SMP */
/*
* We disable interrupts here, even on UP, because we don't
* want to race with hash_page, and because we want the
* _PAGE_HASHPTE bit to be a reliable indication of whether
* the HPTE exists (or at least whether one did once).
* We also turn off the MMU for data accesses so that we
* we can't take a hash table miss (assuming the code is
* covered by a BAT). -- paulus
*/
mfmsr r10
SYNC
rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */
rlwinm r0,r0,0,28,26 /* clear MSR_DR */
mtmsr r0
SYNC_601
isync
tophys(r7,0)
#ifdef CONFIG_SMP
addis r9,r7,mmu_hash_lock@ha
addi r9,r9,mmu_hash_lock@l
10: lwarx r0,0,r9 /* take the mmu_hash_lock */
cmpi 0,r0,0
bne- 11f
stwcx. r8,0,r9
beq+ 12f
11: lwz r0,0(r9)
cmpi 0,r0,0
beq 10b
b 11b
12: isync
#endif
/*
* Fetch the linux pte and test and set _PAGE_HASHPTE atomically.
* If _PAGE_HASHPTE was already set, we don't replace the existing
* HPTE, so we just unlock and return.
*/
mr r8,r5
rlwimi r8,r4,22,20,29
1: lwarx r6,0,r8
andi. r0,r6,_PAGE_HASHPTE
bne 9f /* if HASHPTE already set, done */
ori r5,r6,_PAGE_HASHPTE
stwcx. r5,0,r8
bne- 1b
bl create_hpte
9:
#ifdef CONFIG_SMP
eieio
li r0,0
stw r0,0(r9) /* clear mmu_hash_lock */
#endif
/* reenable interrupts and DR */
mtmsr r10
SYNC_601
isync
lwz r0,4(r1)
mtlr r0
blr
/*
* This routine adds a hardware PTE to the hash table.
* It is designed to be called with the MMU either on or off.
* r3 contains the VSID, r4 contains the virtual address,
* r5 contains the linux PTE, r6 contains the old value of the
* linux PTE (before setting _PAGE_HASHPTE) and r7 contains the
* offset to be added to addresses (0 if the MMU is on,
* -KERNELBASE if it is off).
* On SMP, the caller should have the mmu_hash_lock held.
* We assume that the caller has (or will) set the _PAGE_HASHPTE
* bit in the linux PTE in memory. The value passed in r6 should
* be the old linux PTE value; if it doesn't have _PAGE_HASHPTE set
* this routine will skip the search for an existing HPTE.
* This procedure modifies r0, r3 - r6, r8, cr0.
* -- paulus.
*
* For speed, 4 of the instructions get patched once the size and
* physical address of the hash table are known. These definitions
* of Hash_base and Hash_bits below are just an example.
*/
Hash_base = 0xc0180000
Hash_bits = 12 /* e.g. 256kB hash table */
Hash_msk = (((1 << Hash_bits) - 1) * 64)
/* defines for the PTE format for 32-bit PPCs */
#define PTE_SIZE 8
#define PTEG_SIZE 64
#define LG_PTEG_SIZE 6
#define LDPTEu lwzu
#define LDPTE lwz
#define STPTE stw
#define CMPPTE cmpw
#define PTE_H 0x40
#define PTE_V 0x80000000
#define TST_V(r) rlwinm. r,r,0,0,0
#define SET_V(r) oris r,r,PTE_V@h
#define CLR_V(r,t) rlwinm r,r,0,1,31
#define HASH_LEFT 31-(LG_PTEG_SIZE+Hash_bits-1)
#define HASH_RIGHT 31-LG_PTEG_SIZE
_GLOBAL(create_hpte)
/* Convert linux-style PTE (r5) to low word of PPC-style PTE (r8) */
rlwinm r8,r5,32-10,31,31 /* _PAGE_RW -> PP lsb */
rlwinm r0,r5,32-7,31,31 /* _PAGE_DIRTY -> PP lsb */
and r8,r8,r0 /* writable if _RW & _DIRTY */
rlwimi r5,r5,32-1,30,30 /* _PAGE_USER -> PP msb */
rlwimi r5,r5,32-2,31,31 /* _PAGE_USER -> PP lsb */
ori r8,r8,0xe14 /* clear out reserved bits and M */
andc r8,r5,r8 /* PP = user? (rw&dirty? 2: 3): 0 */
BEGIN_FTR_SECTION
ori r8,r8,_PAGE_COHERENT /* set M (coherence required) */
END_FTR_SECTION_IFSET(CPU_FTR_NEED_COHERENT)
/* Construct the high word of the PPC-style PTE (r5) */
rlwinm r5,r3,7,1,24 /* put VSID in 0x7fffff80 bits */
rlwimi r5,r4,10,26,31 /* put in API (abbrev page index) */
SET_V(r5) /* set V (valid) bit */
/* Get the address of the primary PTE group in the hash table (r3) */
_GLOBAL(hash_page_patch_A)
addis r0,r7,Hash_base@h /* base address of hash table */
rlwimi r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* VSID -> hash */
rlwinm r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */
xor r3,r3,r0 /* make primary hash */
li r0,8 /* PTEs/group */
/*
* Test the _PAGE_HASHPTE bit in the old linux PTE, and skip the search
* if it is clear, meaning that the HPTE isn't there already...
*/
andi. r6,r6,_PAGE_HASHPTE
beq+ 10f /* no PTE: go look for an empty slot */
tlbie r4
addis r4,r7,htab_hash_searches@ha
lwz r6,htab_hash_searches@l(r4)
addi r6,r6,1 /* count how many searches we do */
stw r6,htab_hash_searches@l(r4)
/* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */
mtctr r0
addi r4,r3,-PTE_SIZE
1: LDPTEu r6,PTE_SIZE(r4) /* get next PTE */
CMPPTE 0,r6,r5
bdnzf 2,1b /* loop while ctr != 0 && !cr0.eq */
beq+ found_slot
/* Search the secondary PTEG for a matching PTE */
ori r5,r5,PTE_H /* set H (secondary hash) bit */
_GLOBAL(hash_page_patch_B)
xoris r4,r3,Hash_msk>>16 /* compute secondary hash */
xori r4,r4,(-PTEG_SIZE & 0xffff)
addi r4,r4,-PTE_SIZE
mtctr r0
2: LDPTEu r6,PTE_SIZE(r4)
CMPPTE 0,r6,r5
bdnzf 2,2b
beq+ found_slot
xori r5,r5,PTE_H /* clear H bit again */
/* Search the primary PTEG for an empty slot */
10: mtctr r0
addi r4,r3,-PTE_SIZE /* search primary PTEG */
1: LDPTEu r6,PTE_SIZE(r4) /* get next PTE */
TST_V(r6) /* test valid bit */
bdnzf 2,1b /* loop while ctr != 0 && !cr0.eq */
beq+ found_empty
/* update counter of times that the primary PTEG is full */
addis r4,r7,primary_pteg_full@ha
lwz r6,primary_pteg_full@l(r4)
addi r6,r6,1
stw r6,primary_pteg_full@l(r4)
/* Search the secondary PTEG for an empty slot */
ori r5,r5,PTE_H /* set H (secondary hash) bit */
_GLOBAL(hash_page_patch_C)
xoris r4,r3,Hash_msk>>16 /* compute secondary hash */
xori r4,r4,(-PTEG_SIZE & 0xffff)
addi r4,r4,-PTE_SIZE
mtctr r0
2: LDPTEu r6,PTE_SIZE(r4)
TST_V(r6)
bdnzf 2,2b
beq+ found_empty
xori r5,r5,PTE_H /* clear H bit again */
/*
* Choose an arbitrary slot in the primary PTEG to overwrite.
* Since both the primary and secondary PTEGs are full, and we
* have no information that the PTEs in the primary PTEG are
* more important or useful than those in the secondary PTEG,
* and we know there is a definite (although small) speed
* advantage to putting the PTE in the primary PTEG, we always
* put the PTE in the primary PTEG.
*
* In addition, we skip any slot that is mapping kernel text in
* order to avoid a deadlock when not using BAT mappings if
* trying to hash in the kernel hash code itself after it has
* already taken the hash table lock. This works in conjunction
* with pre-faulting of the kernel text.
*
* If the hash table bucket is full of kernel text entries, we'll
* lockup here but that shouldn't happen
*/
1: addis r4,r7,next_slot@ha /* get next evict slot */
lwz r6,next_slot@l(r4)
addi r6,r6,PTE_SIZE /* search for candidate */
andi. r6,r6,7*PTE_SIZE
stw r6,next_slot@l(r4)
add r4,r3,r6
LDPTE r0,PTE_SIZE/2(r4) /* get PTE second word */
clrrwi r0,r0,12
lis r6,etext@h
ori r6,r6,etext@l /* get etext */
tophys(r6,r6)
cmpl cr0,r0,r6 /* compare and try again */
blt 1b
#ifndef CONFIG_SMP
/* Store PTE in PTEG */
found_empty:
STPTE r5,0(r4)
found_slot:
STPTE r8,PTE_SIZE/2(r4)
#else /* CONFIG_SMP */
/*
* Between the tlbie above and updating the hash table entry below,
* another CPU could read the hash table entry and put it in its TLB.
* There are 3 cases:
* 1. using an empty slot
* 2. updating an earlier entry to change permissions (i.e. enable write)
* 3. taking over the PTE for an unrelated address
*
* In each case it doesn't really matter if the other CPUs have the old
* PTE in their TLB. So we don't need to bother with another tlbie here,
* which is convenient as we've overwritten the register that had the
* address. :-) The tlbie above is mainly to make sure that this CPU comes
* and gets the new PTE from the hash table.
*
* We do however have to make sure that the PTE is never in an invalid
* state with the V bit set.
*/
found_empty:
found_slot:
CLR_V(r5,r0) /* clear V (valid) bit in PTE */
STPTE r5,0(r4)
sync
TLBSYNC
STPTE r8,PTE_SIZE/2(r4) /* put in correct RPN, WIMG, PP bits */
sync
SET_V(r5)
STPTE r5,0(r4) /* finally set V bit in PTE */
#endif /* CONFIG_SMP */
sync /* make sure pte updates get to memory */
blr
.section .bss
.align 2
next_slot:
.space 4
primary_pteg_full:
.space 4
htab_hash_searches:
.space 4
.previous
/*
* Flush the entry for a particular page from the hash table.
*
* flush_hash_pages(unsigned context, unsigned long va, unsigned long pmdval,
* int count)
*
* We assume that there is a hash table in use (Hash != 0).
*/
_GLOBAL(flush_hash_pages)
tophys(r7,0)
/*
* We disable interrupts here, even on UP, because we want
* the _PAGE_HASHPTE bit to be a reliable indication of
* whether the HPTE exists (or at least whether one did once).
* We also turn off the MMU for data accesses so that we
* we can't take a hash table miss (assuming the code is
* covered by a BAT). -- paulus
*/
mfmsr r10
SYNC
rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */
rlwinm r0,r0,0,28,26 /* clear MSR_DR */
mtmsr r0
SYNC_601
isync
/* First find a PTE in the range that has _PAGE_HASHPTE set */
rlwimi r5,r4,22,20,29
1: lwz r0,0(r5)
cmpwi cr1,r6,1
andi. r0,r0,_PAGE_HASHPTE
bne 2f
ble cr1,19f
addi r4,r4,0x1000
addi r5,r5,4
addi r6,r6,-1
b 1b
/* Convert context and va to VSID */
2: mulli r3,r3,897*16 /* multiply context by context skew */
rlwinm r0,r4,4,28,31 /* get ESID (top 4 bits of va) */
mulli r0,r0,0x111 /* multiply by ESID skew */
add r3,r3,r0 /* note code below trims to 24 bits */
/* Construct the high word of the PPC-style PTE (r11) */
rlwinm r11,r3,7,1,24 /* put VSID in 0x7fffff80 bits */
rlwimi r11,r4,10,26,31 /* put in API (abbrev page index) */
SET_V(r11) /* set V (valid) bit */
#ifdef CONFIG_SMP
addis r9,r7,mmu_hash_lock@ha
addi r9,r9,mmu_hash_lock@l
rlwinm r8,r1,0,0,18
add r8,r8,r7
lwz r8,TI_CPU(r8)
oris r8,r8,9
10: lwarx r0,0,r9
cmpi 0,r0,0
bne- 11f
stwcx. r8,0,r9
beq+ 12f
11: lwz r0,0(r9)
cmpi 0,r0,0
beq 10b
b 11b
12: isync
#endif
/*
* Check the _PAGE_HASHPTE bit in the linux PTE. If it is
* already clear, we're done (for this pte). If not,
* clear it (atomically) and proceed. -- paulus.
*/
33: lwarx r8,0,r5 /* fetch the pte */
andi. r0,r8,_PAGE_HASHPTE
beq 8f /* done if HASHPTE is already clear */
rlwinm r8,r8,0,31,29 /* clear HASHPTE bit */
stwcx. r8,0,r5 /* update the pte */
bne- 33b
/* Get the address of the primary PTE group in the hash table (r3) */
_GLOBAL(flush_hash_patch_A)
addis r8,r7,Hash_base@h /* base address of hash table */
rlwimi r8,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* VSID -> hash */
rlwinm r0,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */
xor r8,r0,r8 /* make primary hash */
/* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */
li r0,8 /* PTEs/group */
mtctr r0
addi r12,r8,-PTE_SIZE
1: LDPTEu r0,PTE_SIZE(r12) /* get next PTE */
CMPPTE 0,r0,r11
bdnzf 2,1b /* loop while ctr != 0 && !cr0.eq */
beq+ 3f
/* Search the secondary PTEG for a matching PTE */
ori r11,r11,PTE_H /* set H (secondary hash) bit */
li r0,8 /* PTEs/group */
_GLOBAL(flush_hash_patch_B)
xoris r12,r8,Hash_msk>>16 /* compute secondary hash */
xori r12,r12,(-PTEG_SIZE & 0xffff)
addi r12,r12,-PTE_SIZE
mtctr r0
2: LDPTEu r0,PTE_SIZE(r12)
CMPPTE 0,r0,r11
bdnzf 2,2b
xori r11,r11,PTE_H /* clear H again */
bne- 4f /* should rarely fail to find it */
3: li r0,0
STPTE r0,0(r12) /* invalidate entry */
4: sync
tlbie r4 /* in hw tlb too */
sync
8: ble cr1,9f /* if all ptes checked */
81: addi r6,r6,-1
addi r5,r5,4 /* advance to next pte */
addi r4,r4,0x1000
lwz r0,0(r5) /* check next pte */
cmpwi cr1,r6,1
andi. r0,r0,_PAGE_HASHPTE
bne 33b
bgt cr1,81b
9:
#ifdef CONFIG_SMP
TLBSYNC
li r0,0
stw r0,0(r9) /* clear mmu_hash_lock */
#endif
19: mtmsr r10
SYNC_601
isync
blr