powerpc: Remove arch/powerpc's dependence on asm-ppc/pg{alloc, table}.h

David Gibson david at gibson.dropbear.id.au
Mon Apr 30 16:30:56 EST 2007


powerpc: Remove arch/powerpc's dependence on asm-ppc/pg{alloc,table}.h

Currently, all 32-bit powerpc platforms use asm-ppc/pgtable.h and
asm-ppc/pgalloc.h, even when otherwise compiled with ARCH=powerpc.
Those asm-ppc files are a fairly nasty tangle of #ifdefs including a
bunch of things which shouldn't be necessary any more in arch/powerpc.

Cleaning up that mess is going to take a while, but this patch is a
first step.  It separates the asm-powerpc/pg{alloc,table}.h into 64
bit and 32 bit versions in asm-powerpc, which the basic .h files in
asm-powerpc select based on config.  We make a few tiny tweaks to the
innards of the files along the way, making the outermost ifdefs
(double-inclusion protection and __KERNEL__) a little cleaner, and
#including asm-generic/pgtable.h from the top-level
asm-powerpc/pgtable.h (since both the old 32-bit and 64-bit versions
ended with such an #include).

Signed-off-by: David Gibson <david at gibson.dropbear.id.au>

---

Eck.  There was an idiotic typo in the first version (PPG64 instead of
PPC64 in the #ifndef for pgtable-ppc64.h).  Fixed below.

 include/asm-powerpc/pgalloc-32.h    |   41 +
 include/asm-powerpc/pgalloc-64.h    |  152 ++++++
 include/asm-powerpc/pgalloc.h       |  154 ------
 include/asm-powerpc/pgtable-4k.h    |    3 
 include/asm-powerpc/pgtable-64k.h   |    5 
 include/asm-powerpc/pgtable-ppc32.h |  838 ++++++++++++++++++++++++++++++++++++
 include/asm-powerpc/pgtable-ppc64.h |  492 +++++++++++++++++++++
 include/asm-powerpc/pgtable.h       |  493 ---------------------
 8 files changed, 1532 insertions(+), 646 deletions(-)

Index: working-2.6/include/asm-powerpc/pgtable.h
===================================================================
--- working-2.6.orig/include/asm-powerpc/pgtable.h	2007-04-30 15:36:22.000000000 +1000
+++ working-2.6/include/asm-powerpc/pgtable.h	2007-04-30 15:36:29.000000000 +1000
@@ -2,502 +2,15 @@
 #define _ASM_POWERPC_PGTABLE_H
 #ifdef __KERNEL__
 
-#ifndef CONFIG_PPC64
-#include <asm-ppc/pgtable.h>
+#if defined(CONFIG_PPC64)
+#  include <asm/pgtable-ppc64.h>
 #else
-
-/*
- * This file contains the functions and defines necessary to modify and use
- * the ppc64 hashed page table.
- */
-
-#ifndef __ASSEMBLY__
-#include <linux/stddef.h>
-#include <asm/processor.h>		/* For TASK_SIZE */
-#include <asm/mmu.h>
-#include <asm/page.h>
-#include <asm/tlbflush.h>
-struct mm_struct;
-#endif /* __ASSEMBLY__ */
-
-#ifdef CONFIG_PPC_64K_PAGES
-#include <asm/pgtable-64k.h>
-#else
-#include <asm/pgtable-4k.h>
-#endif
-
-#define FIRST_USER_ADDRESS	0
-
-/*
- * Size of EA range mapped by our pagetables.
- */
-#define PGTABLE_EADDR_SIZE (PTE_INDEX_SIZE + PMD_INDEX_SIZE + \
-                	    PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
-#define PGTABLE_RANGE (1UL << PGTABLE_EADDR_SIZE)
-
-#if TASK_SIZE_USER64 > PGTABLE_RANGE
-#error TASK_SIZE_USER64 exceeds pagetable range
-#endif
-
-#if TASK_SIZE_USER64 > (1UL << (USER_ESID_BITS + SID_SHIFT))
-#error TASK_SIZE_USER64 exceeds user VSID range
+#  include <asm/pgtable-ppc32.h>
 #endif
 
-/*
- * Define the address range of the vmalloc VM area.
- */
-#define VMALLOC_START ASM_CONST(0xD000000000000000)
-#define VMALLOC_SIZE  ASM_CONST(0x80000000000)
-#define VMALLOC_END   (VMALLOC_START + VMALLOC_SIZE)
-
-/*
- * Define the address range of the imalloc VM area.
- */
-#define PHBS_IO_BASE	VMALLOC_END
-#define IMALLOC_BASE	(PHBS_IO_BASE + 0x80000000ul)	/* Reserve 2 gigs for PHBs */
-#define IMALLOC_END	(VMALLOC_START + PGTABLE_RANGE)
-
-/*
- * Region IDs
- */
-#define REGION_SHIFT		60UL
-#define REGION_MASK		(0xfUL << REGION_SHIFT)
-#define REGION_ID(ea)		(((unsigned long)(ea)) >> REGION_SHIFT)
-
-#define VMALLOC_REGION_ID	(REGION_ID(VMALLOC_START))
-#define KERNEL_REGION_ID	(REGION_ID(PAGE_OFFSET))
-#define USER_REGION_ID		(0UL)
-
-/*
- * Common bits in a linux-style PTE.  These match the bits in the
- * (hardware-defined) PowerPC PTE as closely as possible. Additional
- * bits may be defined in pgtable-*.h
- */
-#define _PAGE_PRESENT	0x0001 /* software: pte contains a translation */
-#define _PAGE_USER	0x0002 /* matches one of the PP bits */
-#define _PAGE_FILE	0x0002 /* (!present only) software: pte holds file offset */
-#define _PAGE_EXEC	0x0004 /* No execute on POWER4 and newer (we invert) */
-#define _PAGE_GUARDED	0x0008
-#define _PAGE_COHERENT	0x0010 /* M: enforce memory coherence (SMP systems) */
-#define _PAGE_NO_CACHE	0x0020 /* I: cache inhibit */
-#define _PAGE_WRITETHRU	0x0040 /* W: cache write-through */
-#define _PAGE_DIRTY	0x0080 /* C: page changed */
-#define _PAGE_ACCESSED	0x0100 /* R: page referenced */
-#define _PAGE_RW	0x0200 /* software: user write access allowed */
-#define _PAGE_HASHPTE	0x0400 /* software: pte has an associated HPTE */
-#define _PAGE_BUSY	0x0800 /* software: PTE & hash are busy */ 
-
-#define _PAGE_BASE	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_COHERENT)
-
-#define _PAGE_WRENABLE	(_PAGE_RW | _PAGE_DIRTY)
-
-/* __pgprot defined in asm-powerpc/page.h */
-#define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED)
-
-#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_USER)
-#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_USER | _PAGE_EXEC)
-#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
-#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
-#define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_WRENABLE)
-#define PAGE_KERNEL_CI	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED | \
-			       _PAGE_WRENABLE | _PAGE_NO_CACHE | _PAGE_GUARDED)
-#define PAGE_KERNEL_EXEC __pgprot(_PAGE_BASE | _PAGE_WRENABLE | _PAGE_EXEC)
-
-#define PAGE_AGP	__pgprot(_PAGE_BASE | _PAGE_WRENABLE | _PAGE_NO_CACHE)
-#define HAVE_PAGE_AGP
-
-/* PTEIDX nibble */
-#define _PTEIDX_SECONDARY	0x8
-#define _PTEIDX_GROUP_IX	0x7
-
-
-/*
- * POWER4 and newer have per page execute protection, older chips can only
- * do this on a segment (256MB) basis.
- *
- * Also, write permissions imply read permissions.
- * This is the closest we can get..
- *
- * Note due to the way vm flags are laid out, the bits are XWR
- */
-#define __P000	PAGE_NONE
-#define __P001	PAGE_READONLY
-#define __P010	PAGE_COPY
-#define __P011	PAGE_COPY
-#define __P100	PAGE_READONLY_X
-#define __P101	PAGE_READONLY_X
-#define __P110	PAGE_COPY_X
-#define __P111	PAGE_COPY_X
-
-#define __S000	PAGE_NONE
-#define __S001	PAGE_READONLY
-#define __S010	PAGE_SHARED
-#define __S011	PAGE_SHARED
-#define __S100	PAGE_READONLY_X
-#define __S101	PAGE_READONLY_X
-#define __S110	PAGE_SHARED_X
-#define __S111	PAGE_SHARED_X
-
 #ifndef __ASSEMBLY__
-
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
-#endif /* __ASSEMBLY__ */
-
-#ifdef CONFIG_HUGETLB_PAGE
-
-#define HAVE_ARCH_UNMAPPED_AREA
-#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
-
-#endif
-
-#ifndef __ASSEMBLY__
-
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- *
- * mk_pte takes a (struct page *) as input
- */
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
-
-static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
-{
-	pte_t pte;
-
-
-	pte_val(pte) = (pfn << PTE_RPN_SHIFT) | pgprot_val(pgprot);
-	return pte;
-}
-
-#define pte_modify(_pte, newprot) \
-  (__pte((pte_val(_pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)))
-
-#define pte_none(pte)		((pte_val(pte) & ~_PAGE_HPTEFLAGS) == 0)
-#define pte_present(pte)	(pte_val(pte) & _PAGE_PRESENT)
-
-/* pte_clear moved to later in this file */
-
-#define pte_pfn(x)		((unsigned long)((pte_val(x)>>PTE_RPN_SHIFT)))
-#define pte_page(x)		pfn_to_page(pte_pfn(x))
-
-#define PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
-#define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
-
-#define pmd_set(pmdp, pmdval) 	(pmd_val(*(pmdp)) = (pmdval))
-#define pmd_none(pmd)		(!pmd_val(pmd))
-#define	pmd_bad(pmd)		(!is_kernel_addr(pmd_val(pmd)) \
-				 || (pmd_val(pmd) & PMD_BAD_BITS))
-#define	pmd_present(pmd)	(pmd_val(pmd) != 0)
-#define	pmd_clear(pmdp)		(pmd_val(*(pmdp)) = 0)
-#define pmd_page_vaddr(pmd)	(pmd_val(pmd) & ~PMD_MASKED_BITS)
-#define pmd_page(pmd)		virt_to_page(pmd_page_vaddr(pmd))
-
-#define pud_set(pudp, pudval)	(pud_val(*(pudp)) = (pudval))
-#define pud_none(pud)		(!pud_val(pud))
-#define	pud_bad(pud)		(!is_kernel_addr(pud_val(pud)) \
-				 || (pud_val(pud) & PUD_BAD_BITS))
-#define pud_present(pud)	(pud_val(pud) != 0)
-#define pud_clear(pudp)		(pud_val(*(pudp)) = 0)
-#define pud_page_vaddr(pud)	(pud_val(pud) & ~PUD_MASKED_BITS)
-#define pud_page(pud)		virt_to_page(pud_page_vaddr(pud))
-
-#define pgd_set(pgdp, pudp)	({pgd_val(*(pgdp)) = (unsigned long)(pudp);})
-
-/* 
- * Find an entry in a page-table-directory.  We combine the address region 
- * (the high order N bits) and the pgd portion of the address.
- */
-/* to avoid overflow in free_pgtables we don't use PTRS_PER_PGD here */
-#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & 0x1ff)
-
-#define pgd_offset(mm, address)	 ((mm)->pgd + pgd_index(address))
-
-#define pmd_offset(pudp,addr) \
-  (((pmd_t *) pud_page_vaddr(*(pudp))) + (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)))
-
-#define pte_offset_kernel(dir,addr) \
-  (((pte_t *) pmd_page_vaddr(*(dir))) + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)))
-
-#define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
-#define pte_offset_map_nested(dir,addr)	pte_offset_kernel((dir), (addr))
-#define pte_unmap(pte)			do { } while(0)
-#define pte_unmap_nested(pte)		do { } while(0)
-
-/* to find an entry in a kernel page-table-directory */
-/* This now only contains the vmalloc pages */
-#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
-static inline int pte_read(pte_t pte)  { return pte_val(pte) & _PAGE_USER;}
-static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_RW;}
-static inline int pte_exec(pte_t pte)  { return pte_val(pte) & _PAGE_EXEC;}
-static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY;}
-static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED;}
-static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE;}
-
-static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; }
-static inline void pte_cache(pte_t pte)   { pte_val(pte) &= ~_PAGE_NO_CACHE; }
-
-static inline pte_t pte_rdprotect(pte_t pte) {
-	pte_val(pte) &= ~_PAGE_USER; return pte; }
-static inline pte_t pte_exprotect(pte_t pte) {
-	pte_val(pte) &= ~_PAGE_EXEC; return pte; }
-static inline pte_t pte_wrprotect(pte_t pte) {
-	pte_val(pte) &= ~(_PAGE_RW); return pte; }
-static inline pte_t pte_mkclean(pte_t pte) {
-	pte_val(pte) &= ~(_PAGE_DIRTY); return pte; }
-static inline pte_t pte_mkold(pte_t pte) {
-	pte_val(pte) &= ~_PAGE_ACCESSED; return pte; }
-static inline pte_t pte_mkread(pte_t pte) {
-	pte_val(pte) |= _PAGE_USER; return pte; }
-static inline pte_t pte_mkexec(pte_t pte) {
-	pte_val(pte) |= _PAGE_USER | _PAGE_EXEC; return pte; }
-static inline pte_t pte_mkwrite(pte_t pte) {
-	pte_val(pte) |= _PAGE_RW; return pte; }
-static inline pte_t pte_mkdirty(pte_t pte) {
-	pte_val(pte) |= _PAGE_DIRTY; return pte; }
-static inline pte_t pte_mkyoung(pte_t pte) {
-	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
-static inline pte_t pte_mkhuge(pte_t pte) {
-	return pte; }
-
-/* Atomic PTE updates */
-static inline unsigned long pte_update(struct mm_struct *mm,
-				       unsigned long addr,
-				       pte_t *ptep, unsigned long clr,
-				       int huge)
-{
-	unsigned long old, tmp;
-
-	__asm__ __volatile__(
-	"1:	ldarx	%0,0,%3		# pte_update\n\
-	andi.	%1,%0,%6\n\
-	bne-	1b \n\
-	andc	%1,%0,%4 \n\
-	stdcx.	%1,0,%3 \n\
-	bne-	1b"
-	: "=&r" (old), "=&r" (tmp), "=m" (*ptep)
-	: "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY)
-	: "cc" );
-
-	if (old & _PAGE_HASHPTE)
-		hpte_need_flush(mm, addr, ptep, old, huge);
-	return old;
-}
-
-static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
-					      unsigned long addr, pte_t *ptep)
-{
-	unsigned long old;
-
-       	if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
-		return 0;
-	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0);
-	return (old & _PAGE_ACCESSED) != 0;
-}
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-#define ptep_test_and_clear_young(__vma, __addr, __ptep)		   \
-({									   \
-	int __r;							   \
-	__r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \
-	__r;								   \
-})
-
-/*
- * On RW/DIRTY bit transitions we can avoid flushing the hpte. For the
- * moment we always flush but we need to fix hpte_update and test if the
- * optimisation is worth it.
- */
-static inline int __ptep_test_and_clear_dirty(struct mm_struct *mm,
-					      unsigned long addr, pte_t *ptep)
-{
-	unsigned long old;
-
-       	if ((pte_val(*ptep) & _PAGE_DIRTY) == 0)
-		return 0;
-	old = pte_update(mm, addr, ptep, _PAGE_DIRTY, 0);
-	return (old & _PAGE_DIRTY) != 0;
-}
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
-#define ptep_test_and_clear_dirty(__vma, __addr, __ptep)		   \
-({									   \
-	int __r;							   \
-	__r = __ptep_test_and_clear_dirty((__vma)->vm_mm, __addr, __ptep); \
-	__r;								   \
-})
-
-#define __HAVE_ARCH_PTEP_SET_WRPROTECT
-static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
-				      pte_t *ptep)
-{
-	unsigned long old;
-
-       	if ((pte_val(*ptep) & _PAGE_RW) == 0)
-       		return;
-	old = pte_update(mm, addr, ptep, _PAGE_RW, 0);
-}
-
-/*
- * We currently remove entries from the hashtable regardless of whether
- * the entry was young or dirty. The generic routines only flush if the
- * entry was young or dirty which is not good enough.
- *
- * We should be more intelligent about this but for the moment we override
- * these functions and force a tlb flush unconditionally
- */
-#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
-#define ptep_clear_flush_young(__vma, __address, __ptep)		\
-({									\
-	int __young = __ptep_test_and_clear_young((__vma)->vm_mm, __address, \
-						  __ptep);		\
-	__young;							\
-})
-
-#define __HAVE_ARCH_PTEP_CLEAR_DIRTY_FLUSH
-#define ptep_clear_flush_dirty(__vma, __address, __ptep)		\
-({									\
-	int __dirty = __ptep_test_and_clear_dirty((__vma)->vm_mm, __address, \
-						  __ptep); 		\
-	__dirty;							\
-})
-
-#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
-static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
-				       unsigned long addr, pte_t *ptep)
-{
-	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0);
-	return __pte(old);
-}
-
-static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
-			     pte_t * ptep)
-{
-	pte_update(mm, addr, ptep, ~0UL, 0);
-}
-
-/*
- * set_pte stores a linux PTE into the linux page table.
- */
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pte)
-{
-	if (pte_present(*ptep))
-		pte_clear(mm, addr, ptep);
-	pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
-	*ptep = pte;
-}
-
-/* Set the dirty and/or accessed bits atomically in a linux PTE, this
- * function doesn't need to flush the hash entry
- */
-#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty)
-{
-	unsigned long bits = pte_val(entry) &
-		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
-	unsigned long old, tmp;
-
-	__asm__ __volatile__(
-	"1:	ldarx	%0,0,%4\n\
-		andi.	%1,%0,%6\n\
-		bne-	1b \n\
-		or	%0,%3,%0\n\
-		stdcx.	%0,0,%4\n\
-		bne-	1b"
-	:"=&r" (old), "=&r" (tmp), "=m" (*ptep)
-	:"r" (bits), "r" (ptep), "m" (*ptep), "i" (_PAGE_BUSY)
-	:"cc");
-}
-#define  ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
-	do {								   \
-		__ptep_set_access_flags(__ptep, __entry, __dirty);	   \
-		flush_tlb_page_nohash(__vma, __address);	       	   \
-	} while(0)
-
-/*
- * Macro to mark a page protection value as "uncacheable".
- */
-#define pgprot_noncached(prot)	(__pgprot(pgprot_val(prot) | _PAGE_NO_CACHE | _PAGE_GUARDED))
-
-struct file;
-extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-				     unsigned long size, pgprot_t vma_prot);
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-
-#define __HAVE_ARCH_PTE_SAME
-#define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)
-
-#define pte_ERROR(e) \
-	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
-#define pmd_ERROR(e) \
-	printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
-#define pgd_ERROR(e) \
-	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
-
-extern pgd_t swapper_pg_dir[];
-
-extern void paging_init(void);
-
-/* Encode and de-code a swap entry */
-#define __swp_type(entry)	(((entry).val >> 1) & 0x3f)
-#define __swp_offset(entry)	((entry).val >> 8)
-#define __swp_entry(type, offset) ((swp_entry_t){((type)<< 1)|((offset)<<8)})
-#define __pte_to_swp_entry(pte)	((swp_entry_t){pte_val(pte) >> PTE_RPN_SHIFT})
-#define __swp_entry_to_pte(x)	((pte_t) { (x).val << PTE_RPN_SHIFT })
-#define pte_to_pgoff(pte)	(pte_val(pte) >> PTE_RPN_SHIFT)
-#define pgoff_to_pte(off)	((pte_t) {((off) << PTE_RPN_SHIFT)|_PAGE_FILE})
-#define PTE_FILE_MAX_BITS	(BITS_PER_LONG - PTE_RPN_SHIFT)
-
-/*
- * kern_addr_valid is intended to indicate whether an address is a valid
- * kernel address.  Most 32-bit archs define it as always true (like this)
- * but most 64-bit archs actually perform a test.  What should we do here?
- * The only use is in fs/ncpfs/dir.c
- */
-#define kern_addr_valid(addr)	(1)
-
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)		\
-		remap_pfn_range(vma, vaddr, pfn, size, prot)
-
-void pgtable_cache_init(void);
-
-/*
- * find_linux_pte returns the address of a linux pte for a given 
- * effective address and directory.  If not found, it returns zero.
- */static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea)
-{
-	pgd_t *pg;
-	pud_t *pu;
-	pmd_t *pm;
-	pte_t *pt = NULL;
-
-	pg = pgdir + pgd_index(ea);
-	if (!pgd_none(*pg)) {
-		pu = pud_offset(pg, ea);
-		if (!pud_none(*pu)) {
-			pm = pmd_offset(pu, ea);
-			if (pmd_present(*pm))
-				pt = pte_offset_kernel(pm, ea);
-		}
-	}
-	return pt;
-}
-
-
 #include <asm-generic/pgtable.h>
-
 #endif /* __ASSEMBLY__ */
 
-#endif /* CONFIG_PPC64 */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_PGTABLE_H */
Index: working-2.6/include/asm-powerpc/pgtable-4k.h
===================================================================
--- working-2.6.orig/include/asm-powerpc/pgtable-4k.h	2007-04-30 15:36:22.000000000 +1000
+++ working-2.6/include/asm-powerpc/pgtable-4k.h	2007-04-30 15:36:29.000000000 +1000
@@ -1,3 +1,5 @@
+#ifndef _ASM_POWERPC_PGTABLE_4K_H
+#define _ASM_POWERPC_PGTABLE_4K_H
 /*
  * Entries per page directory level.  The PTE level must use a 64b record
  * for each page table entry.  The PMD and PGD level use a 32b record for
@@ -100,3 +102,4 @@
 
 #define remap_4k_pfn(vma, addr, pfn, prot)	\
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot))
+#endif /* _ASM_POWERPC_PGTABLE_4K_H */
Index: working-2.6/include/asm-powerpc/pgtable-64k.h
===================================================================
--- working-2.6.orig/include/asm-powerpc/pgtable-64k.h	2007-04-30 15:36:22.000000000 +1000
+++ working-2.6/include/asm-powerpc/pgtable-64k.h	2007-04-30 15:36:29.000000000 +1000
@@ -1,6 +1,5 @@
 #ifndef _ASM_POWERPC_PGTABLE_64K_H
 #define _ASM_POWERPC_PGTABLE_64K_H
-#ifdef __KERNEL__
 
 #include <asm-generic/pgtable-nopud.h>
 
@@ -65,8 +64,6 @@
 /* Bits to mask out from a PGD/PUD to get to the PMD page */
 #define PUD_MASKED_BITS		0x1ff
 
-#ifndef __ASSEMBLY__
-
 /* Manipulate "rpte" values */
 #define __real_pte(e,p) 	((real_pte_t) { \
 	(e), pte_val(*((p) + PTRS_PER_PTE)) })
@@ -98,6 +95,4 @@
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE,		\
 			__pgprot(pgprot_val((prot)) | _PAGE_4K_PFN))
 
-#endif /*  __ASSEMBLY__ */
-#endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_PGTABLE_64K_H */
Index: working-2.6/include/asm-powerpc/pgtable-ppc64.h
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ working-2.6/include/asm-powerpc/pgtable-ppc64.h	2007-04-30 16:29:41.000000000 +1000
@@ -0,0 +1,492 @@
+#ifndef _ASM_POWERPC_PGTABLE_PPC64_H_
+#define _ASM_POWERPC_PGTABLE_PPC64_H_
+/*
+ * This file contains the functions and defines necessary to modify and use
+ * the ppc64 hashed page table.
+ */
+
+#ifndef __ASSEMBLY__
+#include <linux/stddef.h>
+#include <asm/processor.h>		/* For TASK_SIZE */
+#include <asm/mmu.h>
+#include <asm/page.h>
+#include <asm/tlbflush.h>
+struct mm_struct;
+#endif /* __ASSEMBLY__ */
+
+#ifdef CONFIG_PPC_64K_PAGES
+#include <asm/pgtable-64k.h>
+#else
+#include <asm/pgtable-4k.h>
+#endif
+
+#define FIRST_USER_ADDRESS	0
+
+/*
+ * Size of EA range mapped by our pagetables.
+ */
+#define PGTABLE_EADDR_SIZE (PTE_INDEX_SIZE + PMD_INDEX_SIZE + \
+                	    PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
+#define PGTABLE_RANGE (1UL << PGTABLE_EADDR_SIZE)
+
+#if TASK_SIZE_USER64 > PGTABLE_RANGE
+#error TASK_SIZE_USER64 exceeds pagetable range
+#endif
+
+#if TASK_SIZE_USER64 > (1UL << (USER_ESID_BITS + SID_SHIFT))
+#error TASK_SIZE_USER64 exceeds user VSID range
+#endif
+
+/*
+ * Define the address range of the vmalloc VM area.
+ */
+#define VMALLOC_START ASM_CONST(0xD000000000000000)
+#define VMALLOC_SIZE  ASM_CONST(0x80000000000)
+#define VMALLOC_END   (VMALLOC_START + VMALLOC_SIZE)
+
+/*
+ * Define the address range of the imalloc VM area.
+ */
+#define PHBS_IO_BASE	VMALLOC_END
+#define IMALLOC_BASE	(PHBS_IO_BASE + 0x80000000ul)	/* Reserve 2 gigs for PHBs */
+#define IMALLOC_END	(VMALLOC_START + PGTABLE_RANGE)
+
+/*
+ * Region IDs
+ */
+#define REGION_SHIFT		60UL
+#define REGION_MASK		(0xfUL << REGION_SHIFT)
+#define REGION_ID(ea)		(((unsigned long)(ea)) >> REGION_SHIFT)
+
+#define VMALLOC_REGION_ID	(REGION_ID(VMALLOC_START))
+#define KERNEL_REGION_ID	(REGION_ID(PAGE_OFFSET))
+#define USER_REGION_ID		(0UL)
+
+/*
+ * Common bits in a linux-style PTE.  These match the bits in the
+ * (hardware-defined) PowerPC PTE as closely as possible. Additional
+ * bits may be defined in pgtable-*.h
+ */
+#define _PAGE_PRESENT	0x0001 /* software: pte contains a translation */
+#define _PAGE_USER	0x0002 /* matches one of the PP bits */
+#define _PAGE_FILE	0x0002 /* (!present only) software: pte holds file offset */
+#define _PAGE_EXEC	0x0004 /* No execute on POWER4 and newer (we invert) */
+#define _PAGE_GUARDED	0x0008
+#define _PAGE_COHERENT	0x0010 /* M: enforce memory coherence (SMP systems) */
+#define _PAGE_NO_CACHE	0x0020 /* I: cache inhibit */
+#define _PAGE_WRITETHRU	0x0040 /* W: cache write-through */
+#define _PAGE_DIRTY	0x0080 /* C: page changed */
+#define _PAGE_ACCESSED	0x0100 /* R: page referenced */
+#define _PAGE_RW	0x0200 /* software: user write access allowed */
+#define _PAGE_HASHPTE	0x0400 /* software: pte has an associated HPTE */
+#define _PAGE_BUSY	0x0800 /* software: PTE & hash are busy */
+
+#define _PAGE_BASE	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_COHERENT)
+
+#define _PAGE_WRENABLE	(_PAGE_RW | _PAGE_DIRTY)
+
+/* __pgprot defined in asm-powerpc/page.h */
+#define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED)
+
+#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_USER)
+#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_USER | _PAGE_EXEC)
+#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER)
+#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER)
+#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+#define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_WRENABLE)
+#define PAGE_KERNEL_CI	__pgprot(_PAGE_PRESENT | _PAGE_ACCESSED | \
+			       _PAGE_WRENABLE | _PAGE_NO_CACHE | _PAGE_GUARDED)
+#define PAGE_KERNEL_EXEC __pgprot(_PAGE_BASE | _PAGE_WRENABLE | _PAGE_EXEC)
+
+#define PAGE_AGP	__pgprot(_PAGE_BASE | _PAGE_WRENABLE | _PAGE_NO_CACHE)
+#define HAVE_PAGE_AGP
+
+/* PTEIDX nibble */
+#define _PTEIDX_SECONDARY	0x8
+#define _PTEIDX_GROUP_IX	0x7
+
+
+/*
+ * POWER4 and newer have per page execute protection, older chips can only
+ * do this on a segment (256MB) basis.
+ *
+ * Also, write permissions imply read permissions.
+ * This is the closest we can get..
+ *
+ * Note due to the way vm flags are laid out, the bits are XWR
+ */
+#define __P000	PAGE_NONE
+#define __P001	PAGE_READONLY
+#define __P010	PAGE_COPY
+#define __P011	PAGE_COPY
+#define __P100	PAGE_READONLY_X
+#define __P101	PAGE_READONLY_X
+#define __P110	PAGE_COPY_X
+#define __P111	PAGE_COPY_X
+
+#define __S000	PAGE_NONE
+#define __S001	PAGE_READONLY
+#define __S010	PAGE_SHARED
+#define __S011	PAGE_SHARED
+#define __S100	PAGE_READONLY_X
+#define __S101	PAGE_READONLY_X
+#define __S110	PAGE_SHARED_X
+#define __S111	PAGE_SHARED_X
+
+#ifndef __ASSEMBLY__
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+#endif /* __ASSEMBLY__ */
+
+#ifdef CONFIG_HUGETLB_PAGE
+
+#define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+
+#endif
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ *
+ * mk_pte takes a (struct page *) as input
+ */
+#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
+
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
+{
+	pte_t pte;
+
+
+	pte_val(pte) = (pfn << PTE_RPN_SHIFT) | pgprot_val(pgprot);
+	return pte;
+}
+
+#define pte_modify(_pte, newprot) \
+  (__pte((pte_val(_pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)))
+
+#define pte_none(pte)		((pte_val(pte) & ~_PAGE_HPTEFLAGS) == 0)
+#define pte_present(pte)	(pte_val(pte) & _PAGE_PRESENT)
+
+/* pte_clear moved to later in this file */
+
+#define pte_pfn(x)		((unsigned long)((pte_val(x)>>PTE_RPN_SHIFT)))
+#define pte_page(x)		pfn_to_page(pte_pfn(x))
+
+#define PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
+#define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
+
+#define pmd_set(pmdp, pmdval) 	(pmd_val(*(pmdp)) = (pmdval))
+#define pmd_none(pmd)		(!pmd_val(pmd))
+#define	pmd_bad(pmd)		(!is_kernel_addr(pmd_val(pmd)) \
+				 || (pmd_val(pmd) & PMD_BAD_BITS))
+#define	pmd_present(pmd)	(pmd_val(pmd) != 0)
+#define	pmd_clear(pmdp)		(pmd_val(*(pmdp)) = 0)
+#define pmd_page_vaddr(pmd)	(pmd_val(pmd) & ~PMD_MASKED_BITS)
+#define pmd_page(pmd)		virt_to_page(pmd_page_vaddr(pmd))
+
+#define pud_set(pudp, pudval)	(pud_val(*(pudp)) = (pudval))
+#define pud_none(pud)		(!pud_val(pud))
+#define	pud_bad(pud)		(!is_kernel_addr(pud_val(pud)) \
+				 || (pud_val(pud) & PUD_BAD_BITS))
+#define pud_present(pud)	(pud_val(pud) != 0)
+#define pud_clear(pudp)		(pud_val(*(pudp)) = 0)
+#define pud_page_vaddr(pud)	(pud_val(pud) & ~PUD_MASKED_BITS)
+#define pud_page(pud)		virt_to_page(pud_page_vaddr(pud))
+
+#define pgd_set(pgdp, pudp)	({pgd_val(*(pgdp)) = (unsigned long)(pudp);})
+
+/*
+ * Find an entry in a page-table-directory.  We combine the address region
+ * (the high order N bits) and the pgd portion of the address.
+ */
+/* to avoid overflow in free_pgtables we don't use PTRS_PER_PGD here */
+#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & 0x1ff)
+
+#define pgd_offset(mm, address)	 ((mm)->pgd + pgd_index(address))
+
+#define pmd_offset(pudp,addr) \
+  (((pmd_t *) pud_page_vaddr(*(pudp))) + (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)))
+
+#define pte_offset_kernel(dir,addr) \
+  (((pte_t *) pmd_page_vaddr(*(dir))) + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)))
+
+#define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
+#define pte_offset_map_nested(dir,addr)	pte_offset_kernel((dir), (addr))
+#define pte_unmap(pte)			do { } while(0)
+#define pte_unmap_nested(pte)		do { } while(0)
+
+/* to find an entry in a kernel page-table-directory */
+/* This now only contains the vmalloc pages */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_read(pte_t pte)  { return pte_val(pte) & _PAGE_USER;}
+static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_RW;}
+static inline int pte_exec(pte_t pte)  { return pte_val(pte) & _PAGE_EXEC;}
+static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY;}
+static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED;}
+static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE;}
+
+static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; }
+static inline void pte_cache(pte_t pte)   { pte_val(pte) &= ~_PAGE_NO_CACHE; }
+
+static inline pte_t pte_rdprotect(pte_t pte) {
+	pte_val(pte) &= ~_PAGE_USER; return pte; }
+static inline pte_t pte_exprotect(pte_t pte) {
+	pte_val(pte) &= ~_PAGE_EXEC; return pte; }
+static inline pte_t pte_wrprotect(pte_t pte) {
+	pte_val(pte) &= ~(_PAGE_RW); return pte; }
+static inline pte_t pte_mkclean(pte_t pte) {
+	pte_val(pte) &= ~(_PAGE_DIRTY); return pte; }
+static inline pte_t pte_mkold(pte_t pte) {
+	pte_val(pte) &= ~_PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkread(pte_t pte) {
+	pte_val(pte) |= _PAGE_USER; return pte; }
+static inline pte_t pte_mkexec(pte_t pte) {
+	pte_val(pte) |= _PAGE_USER | _PAGE_EXEC; return pte; }
+static inline pte_t pte_mkwrite(pte_t pte) {
+	pte_val(pte) |= _PAGE_RW; return pte; }
+static inline pte_t pte_mkdirty(pte_t pte) {
+	pte_val(pte) |= _PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkyoung(pte_t pte) {
+	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkhuge(pte_t pte) {
+	return pte; }
+
+/* Atomic PTE updates */
+static inline unsigned long pte_update(struct mm_struct *mm,
+				       unsigned long addr,
+				       pte_t *ptep, unsigned long clr,
+				       int huge)
+{
+	unsigned long old, tmp;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3		# pte_update\n\
+	andi.	%1,%0,%6\n\
+	bne-	1b \n\
+	andc	%1,%0,%4 \n\
+	stdcx.	%1,0,%3 \n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*ptep)
+	: "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY)
+	: "cc" );
+
+	if (old & _PAGE_HASHPTE)
+		hpte_need_flush(mm, addr, ptep, old, huge);
+	return old;
+}
+
+static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
+					      unsigned long addr, pte_t *ptep)
+{
+	unsigned long old;
+
+       	if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
+		return 0;
+	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0);
+	return (old & _PAGE_ACCESSED) != 0;
+}
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+#define ptep_test_and_clear_young(__vma, __addr, __ptep)		   \
+({									   \
+	int __r;							   \
+	__r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \
+	__r;								   \
+})
+
+/*
+ * On RW/DIRTY bit transitions we can avoid flushing the hpte. For the
+ * moment we always flush but we need to fix hpte_update and test if the
+ * optimisation is worth it.
+ */
+static inline int __ptep_test_and_clear_dirty(struct mm_struct *mm,
+					      unsigned long addr, pte_t *ptep)
+{
+	unsigned long old;
+
+       	if ((pte_val(*ptep) & _PAGE_DIRTY) == 0)
+		return 0;
+	old = pte_update(mm, addr, ptep, _PAGE_DIRTY, 0);
+	return (old & _PAGE_DIRTY) != 0;
+}
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
+#define ptep_test_and_clear_dirty(__vma, __addr, __ptep)		   \
+({									   \
+	int __r;							   \
+	__r = __ptep_test_and_clear_dirty((__vma)->vm_mm, __addr, __ptep); \
+	__r;								   \
+})
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pte_t *ptep)
+{
+	unsigned long old;
+
+       	if ((pte_val(*ptep) & _PAGE_RW) == 0)
+       		return;
+	old = pte_update(mm, addr, ptep, _PAGE_RW, 0);
+}
+
+/*
+ * We currently remove entries from the hashtable regardless of whether
+ * the entry was young or dirty. The generic routines only flush if the
+ * entry was young or dirty which is not good enough.
+ *
+ * We should be more intelligent about this but for the moment we override
+ * these functions and force a tlb flush unconditionally
+ */
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+#define ptep_clear_flush_young(__vma, __address, __ptep)		\
+({									\
+	int __young = __ptep_test_and_clear_young((__vma)->vm_mm, __address, \
+						  __ptep);		\
+	__young;							\
+})
+
+#define __HAVE_ARCH_PTEP_CLEAR_DIRTY_FLUSH
+#define ptep_clear_flush_dirty(__vma, __address, __ptep)		\
+({									\
+	int __dirty = __ptep_test_and_clear_dirty((__vma)->vm_mm, __address, \
+						  __ptep); 		\
+	__dirty;							\
+})
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+				       unsigned long addr, pte_t *ptep)
+{
+	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0);
+	return __pte(old);
+}
+
+static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
+			     pte_t * ptep)
+{
+	pte_update(mm, addr, ptep, ~0UL, 0);
+}
+
+/*
+ * set_pte stores a linux PTE into the linux page table.
+ */
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pte)
+{
+	if (pte_present(*ptep))
+		pte_clear(mm, addr, ptep);
+	pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
+	*ptep = pte;
+}
+
+/* Set the dirty and/or accessed bits atomically in a linux PTE, this
+ * function doesn't need to flush the hash entry
+ */
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty)
+{
+	unsigned long bits = pte_val(entry) &
+		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
+	unsigned long old, tmp;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%4\n\
+		andi.	%1,%0,%6\n\
+		bne-	1b \n\
+		or	%0,%3,%0\n\
+		stdcx.	%0,0,%4\n\
+		bne-	1b"
+	:"=&r" (old), "=&r" (tmp), "=m" (*ptep)
+	:"r" (bits), "r" (ptep), "m" (*ptep), "i" (_PAGE_BUSY)
+	:"cc");
+}
+#define  ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
+	do {								   \
+		__ptep_set_access_flags(__ptep, __entry, __dirty);	   \
+		flush_tlb_page_nohash(__vma, __address);	       	   \
+	} while(0)
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+#define pgprot_noncached(prot)	(__pgprot(pgprot_val(prot) | _PAGE_NO_CACHE | _PAGE_GUARDED))
+
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)
+
+#define pte_ERROR(e) \
+	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
+#define pmd_ERROR(e) \
+	printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+#define pgd_ERROR(e) \
+	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+extern pgd_t swapper_pg_dir[];
+
+extern void paging_init(void);
+
+/* Encode and de-code a swap entry */
+#define __swp_type(entry)	(((entry).val >> 1) & 0x3f)
+#define __swp_offset(entry)	((entry).val >> 8)
+#define __swp_entry(type, offset) ((swp_entry_t){((type)<< 1)|((offset)<<8)})
+#define __pte_to_swp_entry(pte)	((swp_entry_t){pte_val(pte) >> PTE_RPN_SHIFT})
+#define __swp_entry_to_pte(x)	((pte_t) { (x).val << PTE_RPN_SHIFT })
+#define pte_to_pgoff(pte)	(pte_val(pte) >> PTE_RPN_SHIFT)
+#define pgoff_to_pte(off)	((pte_t) {((off) << PTE_RPN_SHIFT)|_PAGE_FILE})
+#define PTE_FILE_MAX_BITS	(BITS_PER_LONG - PTE_RPN_SHIFT)
+
+/*
+ * kern_addr_valid is intended to indicate whether an address is a valid
+ * kernel address.  Most 32-bit archs define it as always true (like this)
+ * but most 64-bit archs actually perform a test.  What should we do here?
+ * The only use is in fs/ncpfs/dir.c
+ */
+#define kern_addr_valid(addr)	(1)
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)		\
+		remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+void pgtable_cache_init(void);
+
+/*
+ * find_linux_pte returns the address of a linux pte for a given
+ * effective address and directory.  If not found, it returns zero.
+ */static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea)
+{
+	pgd_t *pg;
+	pud_t *pu;
+	pmd_t *pm;
+	pte_t *pt = NULL;
+
+	pg = pgdir + pgd_index(ea);
+	if (!pgd_none(*pg)) {
+		pu = pud_offset(pg, ea);
+		if (!pud_none(*pu)) {
+			pm = pmd_offset(pu, ea);
+			if (pmd_present(*pm))
+				pt = pte_offset_kernel(pm, ea);
+		}
+	}
+	return pt;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */
Index: working-2.6/include/asm-powerpc/pgtable-ppc32.h
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ working-2.6/include/asm-powerpc/pgtable-ppc32.h	2007-04-30 15:36:29.000000000 +1000
@@ -0,0 +1,838 @@
+#ifndef _ASM_POWERPC_PGTABLE_PPC32_H
+#define _ASM_POWERPC_PGTABLE_PPC32_H
+
+#include <asm-generic/4level-fixup.h>
+
+#ifndef __ASSEMBLY__
+#include <linux/sched.h>
+#include <linux/threads.h>
+#include <asm/processor.h>		/* For TASK_SIZE */
+#include <asm/mmu.h>
+#include <asm/page.h>
+#include <asm/io.h>			/* For sub-arch specific PPC_PIN_SIZE */
+struct mm_struct;
+
+extern unsigned long va_to_phys(unsigned long address);
+extern pte_t *va_to_pte(unsigned long address);
+extern unsigned long ioremap_bot, ioremap_base;
+#endif /* __ASSEMBLY__ */
+
+/*
+ * The PowerPC MMU uses a hash table containing PTEs, together with
+ * a set of 16 segment registers (on 32-bit implementations), to define
+ * the virtual to physical address mapping.
+ *
+ * We use the hash table as an extended TLB, i.e. a cache of currently
+ * active mappings.  We maintain a two-level page table tree, much
+ * like that used by the i386, for the sake of the Linux memory
+ * management code.  Low-level assembler code in hashtable.S
+ * (procedure hash_page) is responsible for extracting ptes from the
+ * tree and putting them into the hash table when necessary, and
+ * updating the accessed and modified bits in the page table tree.
+ */
+
+/*
+ * The PowerPC MPC8xx uses a TLB with hardware assisted, software tablewalk.
+ * We also use the two level tables, but we can put the real bits in them
+ * needed for the TLB and tablewalk.  These definitions require Mx_CTR.PPM = 0,
+ * Mx_CTR.PPCS = 0, and MD_CTR.TWAM = 1.  The level 2 descriptor has
+ * additional page protection (when Mx_CTR.PPCS = 1) that allows TLB hit
+ * based upon user/super access.  The TLB does not have accessed nor write
+ * protect.  We assume that if the TLB get loaded with an entry it is
+ * accessed, and overload the changed bit for write protect.  We use
+ * two bits in the software pte that are supposed to be set to zero in
+ * the TLB entry (24 and 25) for these indicators.  Although the level 1
+ * descriptor contains the guarded and writethrough/copyback bits, we can
+ * set these at the page level since they get copied from the Mx_TWC
+ * register when the TLB entry is loaded.  We will use bit 27 for guard, since
+ * that is where it exists in the MD_TWC, and bit 26 for writethrough.
+ * These will get masked from the level 2 descriptor at TLB load time, and
+ * copied to the MD_TWC before it gets loaded.
+ * Large page sizes added.  We currently support two sizes, 4K and 8M.
+ * This also allows a TLB hander optimization because we can directly
+ * load the PMD into MD_TWC.  The 8M pages are only used for kernel
+ * mapping of well known areas.  The PMD (PGD) entries contain control
+ * flags in addition to the address, so care must be taken that the
+ * software no longer assumes these are only pointers.
+ */
+
+/*
+ * At present, all PowerPC 400-class processors share a similar TLB
+ * architecture. The instruction and data sides share a unified,
+ * 64-entry, fully-associative TLB which is maintained totally under
+ * software control. In addition, the instruction side has a
+ * hardware-managed, 4-entry, fully-associative TLB which serves as a
+ * first level to the shared TLB. These two TLBs are known as the UTLB
+ * and ITLB, respectively (see "mmu.h" for definitions).
+ */
+
+/*
+ * The normal case is that PTEs are 32-bits and we have a 1-page
+ * 1024-entry pgdir pointing to 1-page 1024-entry PTE pages.  -- paulus
+ *
+ * For any >32-bit physical address platform, we can use the following
+ * two level page table layout where the pgdir is 8KB and the MS 13 bits
+ * are an index to the second level table.  The combined pgdir/pmd first
+ * level has 2048 entries and the second level has 512 64-bit PTE entries.
+ * -Matt
+ */
+/* PMD_SHIFT determines the size of the area mapped by the PTE pages */
+#define PMD_SHIFT	(PAGE_SHIFT + PTE_SHIFT)
+#define PMD_SIZE	(1UL << PMD_SHIFT)
+#define PMD_MASK	(~(PMD_SIZE-1))
+
+/* PGDIR_SHIFT determines what a top-level page table entry can map */
+#define PGDIR_SHIFT	PMD_SHIFT
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+/*
+ * entries per page directory level: our page-table tree is two-level, so
+ * we don't really have any PMD directory.
+ */
+#define PTRS_PER_PTE	(1 << PTE_SHIFT)
+#define PTRS_PER_PMD	1
+#define PTRS_PER_PGD	(1 << (32 - PGDIR_SHIFT))
+
+#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
+#define FIRST_USER_ADDRESS	0
+
+#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
+#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
+
+#define pte_ERROR(e) \
+	printk("%s:%d: bad pte "PTE_FMT".\n", __FILE__, __LINE__, pte_val(e))
+#define pmd_ERROR(e) \
+	printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+#define pgd_ERROR(e) \
+	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/*
+ * Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 64MB value just means that there will be a 64MB "hole" after the
+ * physical memory until the kernel virtual memory starts.  That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ *
+ * We no longer map larger than phys RAM with the BATs so we don't have
+ * to worry about the VMALLOC_OFFSET causing problems.  We do have to worry
+ * about clashes between our early calls to ioremap() that start growing down
+ * from ioremap_base being run into the VM area allocations (growing upwards
+ * from VMALLOC_START).  For this reason we have ioremap_bot to check when
+ * we actually run into our mappings setup in the early boot with the VM
+ * system.  This really does become a problem for machines with good amounts
+ * of RAM.  -- Cort
+ */
+#define VMALLOC_OFFSET (0x1000000) /* 16M */
+#ifdef PPC_PIN_SIZE
+#define VMALLOC_START (((_ALIGN((long)high_memory, PPC_PIN_SIZE) + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
+#else
+#define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
+#endif
+#define VMALLOC_END	ioremap_bot
+
+/*
+ * Bits in a linux-style PTE.  These match the bits in the
+ * (hardware-defined) PowerPC PTE as closely as possible.
+ */
+
+#if defined(CONFIG_40x)
+
+/* There are several potential gotchas here.  The 40x hardware TLBLO
+   field looks like this:
+
+   0  1  2  3  4  ... 18 19 20 21 22 23 24 25 26 27 28 29 30 31
+   RPN.....................  0  0 EX WR ZSEL.......  W  I  M  G
+
+   Where possible we make the Linux PTE bits match up with this
+
+   - bits 20 and 21 must be cleared, because we use 4k pages (40x can
+     support down to 1k pages), this is done in the TLBMiss exception
+     handler.
+   - We use only zones 0 (for kernel pages) and 1 (for user pages)
+     of the 16 available.  Bit 24-26 of the TLB are cleared in the TLB
+     miss handler.  Bit 27 is PAGE_USER, thus selecting the correct
+     zone.
+   - PRESENT *must* be in the bottom two bits because swap cache
+     entries use the top 30 bits.  Because 40x doesn't support SMP
+     anyway, M is irrelevant so we borrow it for PAGE_PRESENT.  Bit 30
+     is cleared in the TLB miss handler before the TLB entry is loaded.
+   - All other bits of the PTE are loaded into TLBLO without
+     modification, leaving us only the bits 20, 21, 24, 25, 26, 30 for
+     software PTE bits.  We actually use use bits 21, 24, 25, and
+     30 respectively for the software bits: ACCESSED, DIRTY, RW, and
+     PRESENT.
+*/
+
+/* Definitions for 40x embedded chips. */
+#define	_PAGE_GUARDED	0x001	/* G: page is guarded from prefetch */
+#define _PAGE_FILE	0x001	/* when !present: nonlinear file mapping */
+#define _PAGE_PRESENT	0x002	/* software: PTE contains a translation */
+#define	_PAGE_NO_CACHE	0x004	/* I: caching is inhibited */
+#define	_PAGE_WRITETHRU	0x008	/* W: caching is write-through */
+#define	_PAGE_USER	0x010	/* matches one of the zone permission bits */
+#define	_PAGE_RW	0x040	/* software: Writes permitted */
+#define	_PAGE_DIRTY	0x080	/* software: dirty page */
+#define _PAGE_HWWRITE	0x100	/* hardware: Dirty & RW, set in exception */
+#define _PAGE_HWEXEC	0x200	/* hardware: EX permission */
+#define _PAGE_ACCESSED	0x400	/* software: R: page referenced */
+
+#define _PMD_PRESENT	0x400	/* PMD points to page of PTEs */
+#define _PMD_BAD	0x802
+#define _PMD_SIZE	0x0e0	/* size field, != 0 for large-page PMD entry */
+#define _PMD_SIZE_4M	0x0c0
+#define _PMD_SIZE_16M	0x0e0
+#define PMD_PAGE_SIZE(pmdval)	(1024 << (((pmdval) & _PMD_SIZE) >> 4))
+
+#elif defined(CONFIG_44x)
+/*
+ * Definitions for PPC440
+ *
+ * Because of the 3 word TLB entries to support 36-bit addressing,
+ * the attribute are difficult to map in such a fashion that they
+ * are easily loaded during exception processing.  I decided to
+ * organize the entry so the ERPN is the only portion in the
+ * upper word of the PTE and the attribute bits below are packed
+ * in as sensibly as they can be in the area below a 4KB page size
+ * oriented RPN.  This at least makes it easy to load the RPN and
+ * ERPN fields in the TLB. -Matt
+ *
+ * Note that these bits preclude future use of a page size
+ * less than 4KB.
+ *
+ *
+ * PPC 440 core has following TLB attribute fields;
+ *
+ *   TLB1:
+ *   0  1  2  3  4  ... 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
+ *   RPN.................................  -  -  -  -  -  - ERPN.......
+ *
+ *   TLB2:
+ *   0  1  2  3  4  ... 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
+ *   -  -  -  -  -    - U0 U1 U2 U3 W  I  M  G  E   - UX UW UR SX SW SR
+ *
+ * There are some constrains and options, to decide mapping software bits
+ * into TLB entry.
+ *
+ *   - PRESENT *must* be in the bottom three bits because swap cache
+ *     entries use the top 29 bits for TLB2.
+ *
+ *   - FILE *must* be in the bottom three bits because swap cache
+ *     entries use the top 29 bits for TLB2.
+ *
+ *   - CACHE COHERENT bit (M) has no effect on PPC440 core, because it
+ *     doesn't support SMP. So we can use this as software bit, like
+ *     DIRTY.
+ *
+ * With the PPC 44x Linux implementation, the 0-11th LSBs of the PTE are used
+ * for memory protection related functions (see PTE structure in
+ * include/asm-ppc/mmu.h).  The _PAGE_XXX definitions in this file map to the
+ * above bits.  Note that the bit values are CPU specific, not architecture
+ * specific.
+ *
+ * The kernel PTE entry holds an arch-dependent swp_entry structure under
+ * certain situations. In other words, in such situations some portion of
+ * the PTE bits are used as a swp_entry. In the PPC implementation, the
+ * 3-24th LSB are shared with swp_entry, however the 0-2nd three LSB still
+ * hold protection values. That means the three protection bits are
+ * reserved for both PTE and SWAP entry at the most significant three
+ * LSBs.
+ *
+ * There are three protection bits available for SWAP entry:
+ *	_PAGE_PRESENT
+ *	_PAGE_FILE
+ *	_PAGE_HASHPTE (if HW has)
+ *
+ * So those three bits have to be inside of 0-2nd LSB of PTE.
+ *
+ */
+
+#define _PAGE_PRESENT	0x00000001		/* S: PTE valid */
+#define	_PAGE_RW	0x00000002		/* S: Write permission */
+#define _PAGE_FILE	0x00000004		/* S: nonlinear file mapping */
+#define _PAGE_ACCESSED	0x00000008		/* S: Page referenced */
+#define _PAGE_HWWRITE	0x00000010		/* H: Dirty & RW */
+#define _PAGE_HWEXEC	0x00000020		/* H: Execute permission */
+#define	_PAGE_USER	0x00000040		/* S: User page */
+#define	_PAGE_ENDIAN	0x00000080		/* H: E bit */
+#define	_PAGE_GUARDED	0x00000100		/* H: G bit */
+#define	_PAGE_DIRTY	0x00000200		/* S: Page dirty */
+#define	_PAGE_NO_CACHE	0x00000400		/* H: I bit */
+#define	_PAGE_WRITETHRU	0x00000800		/* H: W bit */
+
+/* TODO: Add large page lowmem mapping support */
+#define _PMD_PRESENT	0
+#define _PMD_PRESENT_MASK (PAGE_MASK)
+#define _PMD_BAD	(~PAGE_MASK)
+
+/* ERPN in a PTE never gets cleared, ignore it */
+#define _PTE_NONE_MASK	0xffffffff00000000ULL
+
+#elif defined(CONFIG_FSL_BOOKE)
+/*
+   MMU Assist Register 3:
+
+   32 33 34 35 36  ... 50 51 52 53 54 55 56 57 58 59 60 61 62 63
+   RPN......................  0  0 U0 U1 U2 U3 UX SX UW SW UR SR
+
+   - PRESENT *must* be in the bottom three bits because swap cache
+     entries use the top 29 bits.
+
+   - FILE *must* be in the bottom three bits because swap cache
+     entries use the top 29 bits.
+*/
+
+/* Definitions for FSL Book-E Cores */
+#define _PAGE_PRESENT	0x00001	/* S: PTE contains a translation */
+#define _PAGE_USER	0x00002	/* S: User page (maps to UR) */
+#define _PAGE_FILE	0x00002	/* S: when !present: nonlinear file mapping */
+#define _PAGE_ACCESSED	0x00004	/* S: Page referenced */
+#define _PAGE_HWWRITE	0x00008	/* H: Dirty & RW, set in exception */
+#define _PAGE_RW	0x00010	/* S: Write permission */
+#define _PAGE_HWEXEC	0x00020	/* H: UX permission */
+
+#define _PAGE_ENDIAN	0x00040	/* H: E bit */
+#define _PAGE_GUARDED	0x00080	/* H: G bit */
+#define _PAGE_COHERENT	0x00100	/* H: M bit */
+#define _PAGE_NO_CACHE	0x00200	/* H: I bit */
+#define _PAGE_WRITETHRU	0x00400	/* H: W bit */
+
+#ifdef CONFIG_PTE_64BIT
+#define _PAGE_DIRTY	0x08000	/* S: Page dirty */
+
+/* ERPN in a PTE never gets cleared, ignore it */
+#define _PTE_NONE_MASK	0xffffffffffff0000ULL
+#else
+#define _PAGE_DIRTY	0x00800	/* S: Page dirty */
+#endif
+
+#define _PMD_PRESENT	0
+#define _PMD_PRESENT_MASK (PAGE_MASK)
+#define _PMD_BAD	(~PAGE_MASK)
+
+#elif defined(CONFIG_8xx)
+/* Definitions for 8xx embedded chips. */
+#define _PAGE_PRESENT	0x0001	/* Page is valid */
+#define _PAGE_FILE	0x0002	/* when !present: nonlinear file mapping */
+#define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
+#define _PAGE_SHARED	0x0004	/* No ASID (context) compare */
+
+/* These five software bits must be masked out when the entry is loaded
+ * into the TLB.
+ */
+#define _PAGE_EXEC	0x0008	/* software: i-cache coherency required */
+#define _PAGE_GUARDED	0x0010	/* software: guarded access */
+#define _PAGE_DIRTY	0x0020	/* software: page changed */
+#define _PAGE_RW	0x0040	/* software: user write access allowed */
+#define _PAGE_ACCESSED	0x0080	/* software: page referenced */
+
+/* Setting any bits in the nibble with the follow two controls will
+ * require a TLB exception handler change.  It is assumed unused bits
+ * are always zero.
+ */
+#define _PAGE_HWWRITE	0x0100	/* h/w write enable: never set in Linux PTE */
+#define _PAGE_USER	0x0800	/* One of the PP bits, the other is USER&~RW */
+
+#define _PMD_PRESENT	0x0001
+#define _PMD_BAD	0x0ff0
+#define _PMD_PAGE_MASK	0x000c
+#define _PMD_PAGE_8M	0x000c
+
+/*
+ * The 8xx TLB miss handler allegedly sets _PAGE_ACCESSED in the PTE
+ * for an address even if _PAGE_PRESENT is not set, as a performance
+ * optimization.  This is a bug if you ever want to use swap unless
+ * _PAGE_ACCESSED is 2, which it isn't, or unless you have 8xx-specific
+ * definitions for __swp_entry etc. below, which would be gross.
+ *  -- paulus
+ */
+#define _PTE_NONE_MASK _PAGE_ACCESSED
+
+#else /* CONFIG_6xx */
+/* Definitions for 60x, 740/750, etc. */
+#define _PAGE_PRESENT	0x001	/* software: pte contains a translation */
+#define _PAGE_HASHPTE	0x002	/* hash_page has made an HPTE for this pte */
+#define _PAGE_FILE	0x004	/* when !present: nonlinear file mapping */
+#define _PAGE_USER	0x004	/* usermode access allowed */
+#define _PAGE_GUARDED	0x008	/* G: prohibit speculative access */
+#define _PAGE_COHERENT	0x010	/* M: enforce memory coherence (SMP systems) */
+#define _PAGE_NO_CACHE	0x020	/* I: cache inhibit */
+#define _PAGE_WRITETHRU	0x040	/* W: cache write-through */
+#define _PAGE_DIRTY	0x080	/* C: page changed */
+#define _PAGE_ACCESSED	0x100	/* R: page referenced */
+#define _PAGE_EXEC	0x200	/* software: i-cache coherency required */
+#define _PAGE_RW	0x400	/* software: user write access allowed */
+
+#define _PTE_NONE_MASK	_PAGE_HASHPTE
+
+#define _PMD_PRESENT	0
+#define _PMD_PRESENT_MASK (PAGE_MASK)
+#define _PMD_BAD	(~PAGE_MASK)
+#endif
+
+/*
+ * Some bits are only used on some cpu families...
+ */
+#ifndef _PAGE_HASHPTE
+#define _PAGE_HASHPTE	0
+#endif
+#ifndef _PTE_NONE_MASK
+#define _PTE_NONE_MASK 0
+#endif
+#ifndef _PAGE_SHARED
+#define _PAGE_SHARED	0
+#endif
+#ifndef _PAGE_HWWRITE
+#define _PAGE_HWWRITE	0
+#endif
+#ifndef _PAGE_HWEXEC
+#define _PAGE_HWEXEC	0
+#endif
+#ifndef _PAGE_EXEC
+#define _PAGE_EXEC	0
+#endif
+#ifndef _PMD_PRESENT_MASK
+#define _PMD_PRESENT_MASK	_PMD_PRESENT
+#endif
+#ifndef _PMD_SIZE
+#define _PMD_SIZE	0
+#define PMD_PAGE_SIZE(pmd)	bad_call_to_PMD_PAGE_SIZE()
+#endif
+
+#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+/*
+ * Note: the _PAGE_COHERENT bit automatically gets set in the hardware
+ * PTE if CONFIG_SMP is defined (hash_page does this); there is no need
+ * to have it in the Linux PTE, and in fact the bit could be reused for
+ * another purpose.  -- paulus.
+ */
+
+#ifdef CONFIG_44x
+#define _PAGE_BASE	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_GUARDED)
+#else
+#define _PAGE_BASE	(_PAGE_PRESENT | _PAGE_ACCESSED)
+#endif
+#define _PAGE_WRENABLE	(_PAGE_RW | _PAGE_DIRTY | _PAGE_HWWRITE)
+#define _PAGE_KERNEL	(_PAGE_BASE | _PAGE_SHARED | _PAGE_WRENABLE)
+
+#ifdef CONFIG_PPC_STD_MMU
+/* On standard PPC MMU, no user access implies kernel read/write access,
+ * so to write-protect kernel memory we must turn on user access */
+#define _PAGE_KERNEL_RO	(_PAGE_BASE | _PAGE_SHARED | _PAGE_USER)
+#else
+#define _PAGE_KERNEL_RO	(_PAGE_BASE | _PAGE_SHARED)
+#endif
+
+#define _PAGE_IO	(_PAGE_KERNEL | _PAGE_NO_CACHE | _PAGE_GUARDED)
+#define _PAGE_RAM	(_PAGE_KERNEL | _PAGE_HWEXEC)
+
+#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH)
+/* We want the debuggers to be able to set breakpoints anywhere, so
+ * don't write protect the kernel text */
+#define _PAGE_RAM_TEXT	_PAGE_RAM
+#else
+#define _PAGE_RAM_TEXT	(_PAGE_KERNEL_RO | _PAGE_HWEXEC)
+#endif
+
+#define PAGE_NONE	__pgprot(_PAGE_BASE)
+#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER)
+#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW)
+#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC)
+#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER)
+#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+
+#define PAGE_KERNEL		__pgprot(_PAGE_RAM)
+#define PAGE_KERNEL_NOCACHE	__pgprot(_PAGE_IO)
+
+/*
+ * The PowerPC can only do execute protection on a segment (256MB) basis,
+ * not on a page basis.  So we consider execute permission the same as read.
+ * Also, write permissions imply read permissions.
+ * This is the closest we can get..
+ */
+#define __P000	PAGE_NONE
+#define __P001	PAGE_READONLY_X
+#define __P010	PAGE_COPY
+#define __P011	PAGE_COPY_X
+#define __P100	PAGE_READONLY
+#define __P101	PAGE_READONLY_X
+#define __P110	PAGE_COPY
+#define __P111	PAGE_COPY_X
+
+#define __S000	PAGE_NONE
+#define __S001	PAGE_READONLY_X
+#define __S010	PAGE_SHARED
+#define __S011	PAGE_SHARED_X
+#define __S100	PAGE_READONLY
+#define __S101	PAGE_READONLY_X
+#define __S110	PAGE_SHARED
+#define __S111	PAGE_SHARED_X
+
+#ifndef __ASSEMBLY__
+/* Make sure we get a link error if PMD_PAGE_SIZE is ever called on a
+ * kernel without large page PMD support */
+extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
+
+/*
+ * Conversions between PTE values and page frame numbers.
+ */
+
+/* in some case we want to additionaly adjust where the pfn is in the pte to
+ * allow room for more flags */
+#if defined(CONFIG_FSL_BOOKE) && defined(CONFIG_PTE_64BIT)
+#define PFN_SHIFT_OFFSET	(PAGE_SHIFT + 8)
+#else
+#define PFN_SHIFT_OFFSET	(PAGE_SHIFT)
+#endif
+
+#define pte_pfn(x)		(pte_val(x) >> PFN_SHIFT_OFFSET)
+#define pte_page(x)		pfn_to_page(pte_pfn(x))
+
+#define pfn_pte(pfn, prot)	__pte(((pte_basic_t)(pfn) << PFN_SHIFT_OFFSET) |\
+					pgprot_val(prot))
+#define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern unsigned long empty_zero_page[1024];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+#endif /* __ASSEMBLY__ */
+
+#define pte_none(pte)		((pte_val(pte) & ~_PTE_NONE_MASK) == 0)
+#define pte_present(pte)	(pte_val(pte) & _PAGE_PRESENT)
+#define pte_clear(mm,addr,ptep)	do { set_pte_at((mm), (addr), (ptep), __pte(0)); } while (0)
+
+#define pmd_none(pmd)		(!pmd_val(pmd))
+#define	pmd_bad(pmd)		(pmd_val(pmd) & _PMD_BAD)
+#define	pmd_present(pmd)	(pmd_val(pmd) & _PMD_PRESENT_MASK)
+#define	pmd_clear(pmdp)		do { pmd_val(*(pmdp)) = 0; } while (0)
+
+#ifndef __ASSEMBLY__
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the pgd is never bad, and a pmd always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd)		{ return 0; }
+static inline int pgd_bad(pgd_t pgd)		{ return 0; }
+static inline int pgd_present(pgd_t pgd)	{ return 1; }
+#define pgd_clear(xp)				do { } while (0)
+
+#define pgd_page_vaddr(pgd) \
+	((unsigned long) __va(pgd_val(pgd) & PAGE_MASK))
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_read(pte_t pte)		{ return pte_val(pte) & _PAGE_USER; }
+static inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_RW; }
+static inline int pte_exec(pte_t pte)		{ return pte_val(pte) & _PAGE_EXEC; }
+static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+
+static inline void pte_uncache(pte_t pte)       { pte_val(pte) |= _PAGE_NO_CACHE; }
+static inline void pte_cache(pte_t pte)         { pte_val(pte) &= ~_PAGE_NO_CACHE; }
+
+static inline pte_t pte_rdprotect(pte_t pte) {
+	pte_val(pte) &= ~_PAGE_USER; return pte; }
+static inline pte_t pte_wrprotect(pte_t pte) {
+	pte_val(pte) &= ~(_PAGE_RW | _PAGE_HWWRITE); return pte; }
+static inline pte_t pte_exprotect(pte_t pte) {
+	pte_val(pte) &= ~_PAGE_EXEC; return pte; }
+static inline pte_t pte_mkclean(pte_t pte) {
+	pte_val(pte) &= ~(_PAGE_DIRTY | _PAGE_HWWRITE); return pte; }
+static inline pte_t pte_mkold(pte_t pte) {
+	pte_val(pte) &= ~_PAGE_ACCESSED; return pte; }
+
+static inline pte_t pte_mkread(pte_t pte) {
+	pte_val(pte) |= _PAGE_USER; return pte; }
+static inline pte_t pte_mkexec(pte_t pte) {
+	pte_val(pte) |= _PAGE_USER | _PAGE_EXEC; return pte; }
+static inline pte_t pte_mkwrite(pte_t pte) {
+	pte_val(pte) |= _PAGE_RW; return pte; }
+static inline pte_t pte_mkdirty(pte_t pte) {
+	pte_val(pte) |= _PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkyoung(pte_t pte) {
+	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot);
+	return pte;
+}
+
+/*
+ * When flushing the tlb entry for a page, we also need to flush the hash
+ * table entry.  flush_hash_pages is assembler (for speed) in hashtable.S.
+ */
+extern int flush_hash_pages(unsigned context, unsigned long va,
+			    unsigned long pmdval, int count);
+
+/* Add an HPTE to the hash table */
+extern void add_hash_page(unsigned context, unsigned long va,
+			  unsigned long pmdval);
+
+/*
+ * Atomic PTE updates.
+ *
+ * pte_update clears and sets bit atomically, and returns
+ * the old pte value.  In the 64-bit PTE case we lock around the
+ * low PTE word since we expect ALL flag bits to be there
+ */
+#ifndef CONFIG_PTE_64BIT
+static inline unsigned long pte_update(pte_t *p, unsigned long clr,
+				       unsigned long set)
+{
+	unsigned long old, tmp;
+
+	__asm__ __volatile__("\
+1:	lwarx	%0,0,%3\n\
+	andc	%1,%0,%4\n\
+	or	%1,%1,%5\n"
+	PPC405_ERR77(0,%3)
+"	stwcx.	%1,0,%3\n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*p)
+	: "r" (p), "r" (clr), "r" (set), "m" (*p)
+	: "cc" );
+	return old;
+}
+#else
+static inline unsigned long long pte_update(pte_t *p, unsigned long clr,
+				       unsigned long set)
+{
+	unsigned long long old;
+	unsigned long tmp;
+
+	__asm__ __volatile__("\
+1:	lwarx	%L0,0,%4\n\
+	lwzx	%0,0,%3\n\
+	andc	%1,%L0,%5\n\
+	or	%1,%1,%6\n"
+	PPC405_ERR77(0,%3)
+"	stwcx.	%1,0,%4\n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*p)
+	: "r" (p), "r" ((unsigned long)(p) + 4), "r" (clr), "r" (set), "m" (*p)
+	: "cc" );
+	return old;
+}
+#endif
+
+/*
+ * set_pte stores a linux PTE into the linux page table.
+ * On machines which use an MMU hash table we avoid changing the
+ * _PAGE_HASHPTE bit.
+ */
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pte)
+{
+#if _PAGE_HASHPTE != 0
+	pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte) & ~_PAGE_HASHPTE);
+#else
+	*ptep = pte;
+#endif
+}
+
+/*
+ * 2.6 calles this without flushing the TLB entry, this is wrong
+ * for our hash-based implementation, we fix that up here
+ */
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int __ptep_test_and_clear_young(unsigned int context, unsigned long addr, pte_t *ptep)
+{
+	unsigned long old;
+	old = pte_update(ptep, _PAGE_ACCESSED, 0);
+#if _PAGE_HASHPTE != 0
+	if (old & _PAGE_HASHPTE) {
+		unsigned long ptephys = __pa(ptep) & PAGE_MASK;
+		flush_hash_pages(context, addr, ptephys, 1);
+	}
+#endif
+	return (old & _PAGE_ACCESSED) != 0;
+}
+#define ptep_test_and_clear_young(__vma, __addr, __ptep) \
+	__ptep_test_and_clear_young((__vma)->vm_mm->context.id, __addr, __ptep)
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
+static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma,
+					    unsigned long addr, pte_t *ptep)
+{
+	return (pte_update(ptep, (_PAGE_DIRTY | _PAGE_HWWRITE), 0) & _PAGE_DIRTY) != 0;
+}
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				       pte_t *ptep)
+{
+	return __pte(pte_update(ptep, ~_PAGE_HASHPTE, 0));
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pte_t *ptep)
+{
+	pte_update(ptep, (_PAGE_RW | _PAGE_HWWRITE), 0);
+}
+
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty)
+{
+	unsigned long bits = pte_val(entry) &
+		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW);
+	pte_update(ptep, 0, bits);
+}
+
+#define  ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
+	do {								   \
+		__ptep_set_access_flags(__ptep, __entry, __dirty);	   \
+		flush_tlb_page_nohash(__vma, __address);	       	   \
+	} while(0)
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+#define pgprot_noncached(prot)	(__pgprot(pgprot_val(prot) | _PAGE_NO_CACHE | _PAGE_GUARDED))
+
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0)
+
+/*
+ * Note that on Book E processors, the pmd contains the kernel virtual
+ * (lowmem) address of the pte page.  The physical address is less useful
+ * because everything runs with translation enabled (even the TLB miss
+ * handler).  On everything else the pmd contains the physical address
+ * of the pte page.  -- paulus
+ */
+#ifndef CONFIG_BOOKE
+#define pmd_page_vaddr(pmd)	\
+	((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+#define pmd_page(pmd)		\
+	(mem_map + (pmd_val(pmd) >> PAGE_SHIFT))
+#else
+#define pmd_page_vaddr(pmd)	\
+	((unsigned long) (pmd_val(pmd) & PAGE_MASK))
+#define pmd_page(pmd)		\
+	(mem_map + (__pa(pmd_val(pmd)) >> PAGE_SHIFT))
+#endif
+
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+/* to find an entry in a page-table-directory */
+#define pgd_index(address)	 ((address) >> PGDIR_SHIFT)
+#define pgd_offset(mm, address)	 ((mm)->pgd + pgd_index(address))
+
+/* Find an entry in the second-level page table.. */
+static inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address)
+{
+	return (pmd_t *) dir;
+}
+
+/* Find an entry in the third-level page table.. */
+#define pte_index(address)		\
+	(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, addr)	\
+	((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr))
+#define pte_offset_map(dir, addr)		\
+	((pte_t *) kmap_atomic(pmd_page(*(dir)), KM_PTE0) + pte_index(addr))
+#define pte_offset_map_nested(dir, addr)	\
+	((pte_t *) kmap_atomic(pmd_page(*(dir)), KM_PTE1) + pte_index(addr))
+
+#define pte_unmap(pte)		kunmap_atomic(pte, KM_PTE0)
+#define pte_unmap_nested(pte)	kunmap_atomic(pte, KM_PTE1)
+
+extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+
+extern void paging_init(void);
+
+/*
+ * Encode and decode a swap entry.
+ * Note that the bits we use in a PTE for representing a swap entry
+ * must not include the _PAGE_PRESENT bit, the _PAGE_FILE bit, or the
+ *_PAGE_HASHPTE bit (if used).  -- paulus
+ */
+#define __swp_type(entry)		((entry).val & 0x1f)
+#define __swp_offset(entry)		((entry).val >> 5)
+#define __swp_entry(type, offset)	((swp_entry_t) { (type) | ((offset) << 5) })
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
+
+/* Encode and decode a nonlinear file mapping entry */
+#define PTE_FILE_MAX_BITS	29
+#define pte_to_pgoff(pte)	(pte_val(pte) >> 3)
+#define pgoff_to_pte(off)	((pte_t) { ((off) << 3) | _PAGE_FILE })
+
+/* CONFIG_APUS */
+/* For virtual address to physical address conversion */
+extern void cache_clear(__u32 addr, int length);
+extern void cache_push(__u32 addr, int length);
+extern int mm_end_of_chunk (unsigned long addr, int len);
+extern unsigned long iopa(unsigned long addr);
+extern unsigned long mm_ptov(unsigned long addr) __attribute_const__;
+
+/* Values for nocacheflag and cmode */
+/* These are not used by the APUS kernel_map, but prevents
+   compilation errors. */
+#define	KERNELMAP_FULL_CACHING		0
+#define	KERNELMAP_NOCACHE_SER		1
+#define	KERNELMAP_NOCACHE_NONSER	2
+#define	KERNELMAP_NO_COPYBACK		3
+
+/*
+ * Map some physical address range into the kernel address space.
+ */
+extern unsigned long kernel_map(unsigned long paddr, unsigned long size,
+				int nocacheflag, unsigned long *memavailp );
+
+/*
+ * Set cache mode of (kernel space) address range.
+ */
+extern void kernel_set_cachemode (unsigned long address, unsigned long size,
+                                 unsigned int cmode);
+
+/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
+#define kern_addr_valid(addr)	(1)
+
+#ifdef CONFIG_PHYS_64BIT
+extern int remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
+			unsigned long paddr, unsigned long size, pgprot_t prot);
+
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+					unsigned long vaddr,
+					unsigned long pfn,
+					unsigned long size,
+					pgprot_t prot)
+{
+	phys_addr_t paddr64 = fixup_bigphys_addr(pfn << PAGE_SHIFT, size);
+	return remap_pfn_range(vma, vaddr, paddr64 >> PAGE_SHIFT, size, prot);
+}
+#else
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)		\
+		remap_pfn_range(vma, vaddr, pfn, size, prot)
+#endif
+
+/*
+ * No page table caches to initialise
+ */
+#define pgtable_cache_init()	do { } while (0)
+
+extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep,
+		      pmd_t **pmdp);
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_PGTABLE_PPC32_H */
Index: working-2.6/include/asm-powerpc/pgalloc-32.h
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ working-2.6/include/asm-powerpc/pgalloc-32.h	2007-04-30 15:36:29.000000000 +1000
@@ -0,0 +1,41 @@
+#ifndef _ASM_POWERPC_PGALLOC_32_H
+#define _ASM_POWERPC_PGALLOC_32_H
+
+#include <linux/threads.h>
+
+extern void __bad_pte(pmd_t *pmd);
+
+extern pgd_t *pgd_alloc(struct mm_struct *mm);
+extern void pgd_free(pgd_t *pgd);
+
+/*
+ * We don't have any real pmd's, and this code never triggers because
+ * the pgd will always be present..
+ */
+#define pmd_alloc_one(mm,address)       ({ BUG(); ((pmd_t *)2); })
+#define pmd_free(x)                     do { } while (0)
+#define __pmd_free_tlb(tlb,x)		do { } while (0)
+#define pgd_populate(mm, pmd, pte)      BUG()
+
+#ifndef CONFIG_BOOKE
+#define pmd_populate_kernel(mm, pmd, pte)	\
+		(pmd_val(*(pmd)) = __pa(pte) | _PMD_PRESENT)
+#define pmd_populate(mm, pmd, pte)	\
+		(pmd_val(*(pmd)) = (page_to_pfn(pte) << PAGE_SHIFT) | _PMD_PRESENT)
+#else
+#define pmd_populate_kernel(mm, pmd, pte)	\
+		(pmd_val(*(pmd)) = (unsigned long)pte | _PMD_PRESENT)
+#define pmd_populate(mm, pmd, pte)	\
+		(pmd_val(*(pmd)) = (unsigned long)lowmem_page_address(pte) | _PMD_PRESENT)
+#endif
+
+extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
+extern struct page *pte_alloc_one(struct mm_struct *mm, unsigned long addr);
+extern void pte_free_kernel(pte_t *pte);
+extern void pte_free(struct page *pte);
+
+#define __pte_free_tlb(tlb, pte)	pte_free((pte))
+
+#define check_pgt_cache()	do { } while (0)
+
+#endif /* _ASM_POWERPC_PGALLOC_32_H */
Index: working-2.6/include/asm-powerpc/pgalloc-64.h
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ working-2.6/include/asm-powerpc/pgalloc-64.h	2007-04-30 15:36:29.000000000 +1000
@@ -0,0 +1,152 @@
+#ifndef _ASM_POWERPC_PGALLOC_64_H
+#define _ASM_POWERPC_PGALLOC_64_H
+/*
+ * 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/mm.h>
+#include <linux/slab.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+
+extern struct kmem_cache *pgtable_cache[];
+
+#ifdef CONFIG_PPC_64K_PAGES
+#define PTE_CACHE_NUM	0
+#define PMD_CACHE_NUM	1
+#define PGD_CACHE_NUM	2
+#define HUGEPTE_CACHE_NUM 3
+#else
+#define PTE_CACHE_NUM	0
+#define PMD_CACHE_NUM	1
+#define PUD_CACHE_NUM	1
+#define PGD_CACHE_NUM	0
+#define HUGEPTE_CACHE_NUM 2
+#endif
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	return kmem_cache_alloc(pgtable_cache[PGD_CACHE_NUM], GFP_KERNEL);
+}
+
+static inline void pgd_free(pgd_t *pgd)
+{
+	kmem_cache_free(pgtable_cache[PGD_CACHE_NUM], pgd);
+}
+
+#ifndef CONFIG_PPC_64K_PAGES
+
+#define pgd_populate(MM, PGD, PUD)	pgd_set(PGD, PUD)
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return kmem_cache_alloc(pgtable_cache[PUD_CACHE_NUM],
+				GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pud_free(pud_t *pud)
+{
+	kmem_cache_free(pgtable_cache[PUD_CACHE_NUM], pud);
+}
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+	pud_set(pud, (unsigned long)pmd);
+}
+
+#define pmd_populate(mm, pmd, pte_page) \
+	pmd_populate_kernel(mm, pmd, page_address(pte_page))
+#define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, (unsigned long)(pte))
+
+
+#else /* CONFIG_PPC_64K_PAGES */
+
+#define pud_populate(mm, pud, pmd)	pud_set(pud, (unsigned long)pmd)
+
+static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
+				       pte_t *pte)
+{
+	pmd_set(pmd, (unsigned long)pte);
+}
+
+#define pmd_populate(mm, pmd, pte_page) \
+	pmd_populate_kernel(mm, pmd, page_address(pte_page))
+
+#endif /* CONFIG_PPC_64K_PAGES */
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return kmem_cache_alloc(pgtable_cache[PMD_CACHE_NUM],
+				GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pmd_free(pmd_t *pmd)
+{
+	kmem_cache_free(pgtable_cache[PMD_CACHE_NUM], pmd);
+}
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+					  unsigned long address)
+{
+	return kmem_cache_alloc(pgtable_cache[PTE_CACHE_NUM],
+				GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline struct page *pte_alloc_one(struct mm_struct *mm,
+					 unsigned long address)
+{
+	return virt_to_page(pte_alloc_one_kernel(mm, address));
+}
+
+static inline void pte_free_kernel(pte_t *pte)
+{
+	kmem_cache_free(pgtable_cache[PTE_CACHE_NUM], pte);
+}
+
+static inline void pte_free(struct page *ptepage)
+{
+	pte_free_kernel(page_address(ptepage));
+}
+
+#define PGF_CACHENUM_MASK	0x3
+
+typedef struct pgtable_free {
+	unsigned long val;
+} pgtable_free_t;
+
+static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
+						unsigned long mask)
+{
+	BUG_ON(cachenum > PGF_CACHENUM_MASK);
+
+	return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
+}
+
+static inline void pgtable_free(pgtable_free_t pgf)
+{
+	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
+	int cachenum = pgf.val & PGF_CACHENUM_MASK;
+
+	kmem_cache_free(pgtable_cache[cachenum], p);
+}
+
+extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
+
+#define __pte_free_tlb(tlb, ptepage)	\
+	pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
+		PTE_CACHE_NUM, PTE_TABLE_SIZE-1))
+#define __pmd_free_tlb(tlb, pmd) 	\
+	pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
+		PMD_CACHE_NUM, PMD_TABLE_SIZE-1))
+#ifndef CONFIG_PPC_64K_PAGES
+#define __pud_free_tlb(tlb, pud)	\
+	pgtable_free_tlb(tlb, pgtable_free_cache(pud, \
+		PUD_CACHE_NUM, PUD_TABLE_SIZE-1))
+#endif /* CONFIG_PPC_64K_PAGES */
+
+#define check_pgt_cache()	do { } while (0)
+
+#endif /* _ASM_POWERPC_PGALLOC_64_H */
Index: working-2.6/include/asm-powerpc/pgalloc.h
===================================================================
--- working-2.6.orig/include/asm-powerpc/pgalloc.h	2007-04-30 15:36:22.000000000 +1000
+++ working-2.6/include/asm-powerpc/pgalloc.h	2007-04-30 15:36:29.000000000 +1000
@@ -2,159 +2,11 @@
 #define _ASM_POWERPC_PGALLOC_H
 #ifdef __KERNEL__
 
-#ifndef CONFIG_PPC64
-#include <asm-ppc/pgalloc.h>
+#ifdef CONFIG_PPC64
+#include <asm/pgalloc-64.h>
 #else
-
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include <linux/cpumask.h>
-#include <linux/percpu.h>
-
-extern struct kmem_cache *pgtable_cache[];
-
-#ifdef CONFIG_PPC_64K_PAGES
-#define PTE_CACHE_NUM	0
-#define PMD_CACHE_NUM	1
-#define PGD_CACHE_NUM	2
-#define HUGEPTE_CACHE_NUM 3
-#else
-#define PTE_CACHE_NUM	0
-#define PMD_CACHE_NUM	1
-#define PUD_CACHE_NUM	1
-#define PGD_CACHE_NUM	0
-#define HUGEPTE_CACHE_NUM 2
+#include <asm/pgalloc-32.h>
 #endif
 
-/*
- * 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.
- */
-
-static inline pgd_t *pgd_alloc(struct mm_struct *mm)
-{
-	return kmem_cache_alloc(pgtable_cache[PGD_CACHE_NUM], GFP_KERNEL);
-}
-
-static inline void pgd_free(pgd_t *pgd)
-{
-	kmem_cache_free(pgtable_cache[PGD_CACHE_NUM], pgd);
-}
-
-#ifndef CONFIG_PPC_64K_PAGES
-
-#define pgd_populate(MM, PGD, PUD)	pgd_set(PGD, PUD)
-
-static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
-	return kmem_cache_alloc(pgtable_cache[PUD_CACHE_NUM],
-				GFP_KERNEL|__GFP_REPEAT);
-}
-
-static inline void pud_free(pud_t *pud)
-{
-	kmem_cache_free(pgtable_cache[PUD_CACHE_NUM], pud);
-}
-
-static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
-{
-	pud_set(pud, (unsigned long)pmd);
-}
-
-#define pmd_populate(mm, pmd, pte_page) \
-	pmd_populate_kernel(mm, pmd, page_address(pte_page))
-#define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, (unsigned long)(pte))
-
-
-#else /* CONFIG_PPC_64K_PAGES */
-
-#define pud_populate(mm, pud, pmd)	pud_set(pud, (unsigned long)pmd)
-
-static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
-				       pte_t *pte)
-{
-	pmd_set(pmd, (unsigned long)pte);
-}
-
-#define pmd_populate(mm, pmd, pte_page) \
-	pmd_populate_kernel(mm, pmd, page_address(pte_page))
-
-#endif /* CONFIG_PPC_64K_PAGES */
-
-static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
-	return kmem_cache_alloc(pgtable_cache[PMD_CACHE_NUM],
-				GFP_KERNEL|__GFP_REPEAT);
-}
-
-static inline void pmd_free(pmd_t *pmd)
-{
-	kmem_cache_free(pgtable_cache[PMD_CACHE_NUM], pmd);
-}
-
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
-					  unsigned long address)
-{
-	return kmem_cache_alloc(pgtable_cache[PTE_CACHE_NUM],
-				GFP_KERNEL|__GFP_REPEAT);
-}
-
-static inline struct page *pte_alloc_one(struct mm_struct *mm,
-					 unsigned long address)
-{
-	return virt_to_page(pte_alloc_one_kernel(mm, address));
-}
-		
-static inline void pte_free_kernel(pte_t *pte)
-{
-	kmem_cache_free(pgtable_cache[PTE_CACHE_NUM], pte);
-}
-
-static inline void pte_free(struct page *ptepage)
-{
-	pte_free_kernel(page_address(ptepage));
-}
-
-#define PGF_CACHENUM_MASK	0x3
-
-typedef struct pgtable_free {
-	unsigned long val;
-} pgtable_free_t;
-
-static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
-						unsigned long mask)
-{
-	BUG_ON(cachenum > PGF_CACHENUM_MASK);
-
-	return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
-}
-
-static inline void pgtable_free(pgtable_free_t pgf)
-{
-	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
-	int cachenum = pgf.val & PGF_CACHENUM_MASK;
-
-	kmem_cache_free(pgtable_cache[cachenum], p);
-}
-
-extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
-
-#define __pte_free_tlb(tlb, ptepage)	\
-	pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
-		PTE_CACHE_NUM, PTE_TABLE_SIZE-1))
-#define __pmd_free_tlb(tlb, pmd) 	\
-	pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
-		PMD_CACHE_NUM, PMD_TABLE_SIZE-1))
-#ifndef CONFIG_PPC_64K_PAGES
-#define __pud_free_tlb(tlb, pud)	\
-	pgtable_free_tlb(tlb, pgtable_free_cache(pud, \
-		PUD_CACHE_NUM, PUD_TABLE_SIZE-1))
-#endif /* CONFIG_PPC_64K_PAGES */
-
-#define check_pgt_cache()	do { } while (0)
-
-#endif /* CONFIG_PPC64 */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_PGALLOC_H */


-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson



More information about the Linuxppc-dev mailing list