powerpc/mm: Split hash MMU specific hugepage code into a new file

This patch separates the parts of hugetlbpage.c which are inherently
specific to the hash MMU into a new hugelbpage-hash64.c file.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This commit is contained in:
David Gibson 2009-10-26 19:24:31 +00:00 committed by Benjamin Herrenschmidt
parent d1837cba5d
commit 883a3e5236
4 changed files with 176 additions and 167 deletions

View File

@ -3,6 +3,9 @@
#include <asm/page.h>
pte_t *huge_pte_offset_and_shift(struct mm_struct *mm,
unsigned long addr, unsigned *shift);
int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
unsigned long len);

View File

@ -28,7 +28,10 @@ obj-$(CONFIG_44x) += 44x_mmu.o
obj-$(CONFIG_FSL_BOOKE) += fsl_booke_mmu.o
obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
obj-$(CONFIG_PPC_MM_SLICES) += slice.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
ifeq ($(CONFIG_HUGETLB_PAGE),y)
obj-y += hugetlbpage.o
obj-$(CONFIG_PPC_STD_MMU_64) += hugetlbpage-hash64.o
endif
obj-$(CONFIG_PPC_SUBPAGE_PROT) += subpage-prot.o
obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
obj-$(CONFIG_HIGHMEM) += highmem.o

View File

@ -0,0 +1,167 @@
/*
* PPC64 Huge TLB Page Support for hash based MMUs (POWER4 and later)
*
* Copyright (C) 2003 David Gibson, IBM Corporation.
*
* Based on the IA-32 version:
* Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
*/
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/cacheflush.h>
#include <asm/machdep.h>
/*
* Called by asm hashtable.S for doing lazy icache flush
*/
static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags,
pte_t pte, int trap, unsigned long sz)
{
struct page *page;
int i;
if (!pfn_valid(pte_pfn(pte)))
return rflags;
page = pte_page(pte);
/* page is dirty */
if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
if (trap == 0x400) {
for (i = 0; i < (sz / PAGE_SIZE); i++)
__flush_dcache_icache(page_address(page+i));
set_bit(PG_arch_1, &page->flags);
} else {
rflags |= HPTE_R_N;
}
}
return rflags;
}
int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
pte_t *ptep, unsigned long trap, int local, int ssize,
unsigned int shift, unsigned int mmu_psize)
{
unsigned long old_pte, new_pte;
unsigned long va, rflags, pa, sz;
long slot;
int err = 1;
BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
/* Search the Linux page table for a match with va */
va = hpt_va(ea, vsid, ssize);
/*
* Check the user's access rights to the page. If access should be
* prevented then send the problem up to do_page_fault.
*/
if (unlikely(access & ~pte_val(*ptep)))
goto out;
/*
* At this point, we have a pte (old_pte) which can be used to build
* or update an HPTE. There are 2 cases:
*
* 1. There is a valid (present) pte with no associated HPTE (this is
* the most common case)
* 2. There is a valid (present) pte with an associated HPTE. The
* current values of the pp bits in the HPTE prevent access
* because we are doing software DIRTY bit management and the
* page is currently not DIRTY.
*/
do {
old_pte = pte_val(*ptep);
if (old_pte & _PAGE_BUSY)
goto out;
new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED;
} while(old_pte != __cmpxchg_u64((unsigned long *)ptep,
old_pte, new_pte));
rflags = 0x2 | (!(new_pte & _PAGE_RW));
/* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */
rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N);
sz = ((1UL) << shift);
if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
/* No CPU has hugepages but lacks no execute, so we
* don't need to worry about that case */
rflags = hash_huge_page_do_lazy_icache(rflags, __pte(old_pte),
trap, sz);
/* Check if pte already has an hpte (case 2) */
if (unlikely(old_pte & _PAGE_HASHPTE)) {
/* There MIGHT be an HPTE for this pte */
unsigned long hash, slot;
hash = hpt_hash(va, shift, ssize);
if (old_pte & _PAGE_F_SECOND)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += (old_pte & _PAGE_F_GIX) >> 12;
if (ppc_md.hpte_updatepp(slot, rflags, va, mmu_psize,
ssize, local) == -1)
old_pte &= ~_PAGE_HPTEFLAGS;
}
if (likely(!(old_pte & _PAGE_HASHPTE))) {
unsigned long hash = hpt_hash(va, shift, ssize);
unsigned long hpte_group;
pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT;
repeat:
hpte_group = ((hash & htab_hash_mask) *
HPTES_PER_GROUP) & ~0x7UL;
/* clear HPTE slot informations in new PTE */
#ifdef CONFIG_PPC_64K_PAGES
new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0;
#else
new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
#endif
/* Add in WIMG bits */
rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
_PAGE_COHERENT | _PAGE_GUARDED));
/* Insert into the hash table, primary slot */
slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0,
mmu_psize, ssize);
/* Primary is full, try the secondary */
if (unlikely(slot == -1)) {
hpte_group = ((~hash & htab_hash_mask) *
HPTES_PER_GROUP) & ~0x7UL;
slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags,
HPTE_V_SECONDARY,
mmu_psize, ssize);
if (slot == -1) {
if (mftb() & 0x1)
hpte_group = ((hash & htab_hash_mask) *
HPTES_PER_GROUP)&~0x7UL;
ppc_md.hpte_remove(hpte_group);
goto repeat;
}
}
if (unlikely(slot == -2))
panic("hash_huge_page: pte_insert failed\n");
new_pte |= (slot << 12) & (_PAGE_F_SECOND | _PAGE_F_GIX);
}
/*
* No need to use ldarx/stdcx here
*/
*ptep = __pte(new_pte & ~_PAGE_BUSY);
err = 0;
out:
return err;
}

View File

@ -7,29 +7,17 @@
* Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
*/
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/io.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/sysctl.h>
#include <asm/mman.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/machdep.h>
#include <asm/cputable.h>
#include <asm/spu.h>
#define PAGE_SHIFT_64K 16
#define PAGE_SHIFT_16M 24
#define PAGE_SHIFT_16G 34
#define NUM_LOW_AREAS (0x100000000UL >> SID_SHIFT)
#define NUM_HIGH_AREAS (PGTABLE_RANGE >> HTLB_AREA_SHIFT)
#define MAX_NUMBER_GPAGES 1024
/* Tracks the 16G pages after the device tree is scanned and before the
@ -502,158 +490,6 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
return 1UL << mmu_psize_to_shift(psize);
}
/*
* Called by asm hashtable.S for doing lazy icache flush
*/
static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags,
pte_t pte, int trap, unsigned long sz)
{
struct page *page;
int i;
if (!pfn_valid(pte_pfn(pte)))
return rflags;
page = pte_page(pte);
/* page is dirty */
if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
if (trap == 0x400) {
for (i = 0; i < (sz / PAGE_SIZE); i++)
__flush_dcache_icache(page_address(page+i));
set_bit(PG_arch_1, &page->flags);
} else {
rflags |= HPTE_R_N;
}
}
return rflags;
}
int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
pte_t *ptep, unsigned long trap, int local, int ssize,
unsigned int shift, unsigned int mmu_psize)
{
unsigned long old_pte, new_pte;
unsigned long va, rflags, pa, sz;
long slot;
int err = 1;
BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
/* Search the Linux page table for a match with va */
va = hpt_va(ea, vsid, ssize);
/*
* Check the user's access rights to the page. If access should be
* prevented then send the problem up to do_page_fault.
*/
if (unlikely(access & ~pte_val(*ptep)))
goto out;
/*
* At this point, we have a pte (old_pte) which can be used to build
* or update an HPTE. There are 2 cases:
*
* 1. There is a valid (present) pte with no associated HPTE (this is
* the most common case)
* 2. There is a valid (present) pte with an associated HPTE. The
* current values of the pp bits in the HPTE prevent access
* because we are doing software DIRTY bit management and the
* page is currently not DIRTY.
*/
do {
old_pte = pte_val(*ptep);
if (old_pte & _PAGE_BUSY)
goto out;
new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED;
} while(old_pte != __cmpxchg_u64((unsigned long *)ptep,
old_pte, new_pte));
rflags = 0x2 | (!(new_pte & _PAGE_RW));
/* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */
rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N);
sz = ((1UL) << shift);
if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
/* No CPU has hugepages but lacks no execute, so we
* don't need to worry about that case */
rflags = hash_huge_page_do_lazy_icache(rflags, __pte(old_pte),
trap, sz);
/* Check if pte already has an hpte (case 2) */
if (unlikely(old_pte & _PAGE_HASHPTE)) {
/* There MIGHT be an HPTE for this pte */
unsigned long hash, slot;
hash = hpt_hash(va, shift, ssize);
if (old_pte & _PAGE_F_SECOND)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += (old_pte & _PAGE_F_GIX) >> 12;
if (ppc_md.hpte_updatepp(slot, rflags, va, mmu_psize,
ssize, local) == -1)
old_pte &= ~_PAGE_HPTEFLAGS;
}
if (likely(!(old_pte & _PAGE_HASHPTE))) {
unsigned long hash = hpt_hash(va, shift, ssize);
unsigned long hpte_group;
pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT;
repeat:
hpte_group = ((hash & htab_hash_mask) *
HPTES_PER_GROUP) & ~0x7UL;
/* clear HPTE slot informations in new PTE */
#ifdef CONFIG_PPC_64K_PAGES
new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0;
#else
new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
#endif
/* Add in WIMG bits */
rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
_PAGE_COHERENT | _PAGE_GUARDED));
/* Insert into the hash table, primary slot */
slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0,
mmu_psize, ssize);
/* Primary is full, try the secondary */
if (unlikely(slot == -1)) {
hpte_group = ((~hash & htab_hash_mask) *
HPTES_PER_GROUP) & ~0x7UL;
slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags,
HPTE_V_SECONDARY,
mmu_psize, ssize);
if (slot == -1) {
if (mftb() & 0x1)
hpte_group = ((hash & htab_hash_mask) *
HPTES_PER_GROUP)&~0x7UL;
ppc_md.hpte_remove(hpte_group);
goto repeat;
}
}
if (unlikely(slot == -2))
panic("hash_huge_page: pte_insert failed\n");
new_pte |= (slot << 12) & (_PAGE_F_SECOND | _PAGE_F_GIX);
}
/*
* No need to use ldarx/stdcx here
*/
*ptep = __pte(new_pte & ~_PAGE_BUSY);
err = 0;
out:
return err;
}
static int __init add_huge_page_size(unsigned long long size)
{
int shift = __ffs(size);