kernel_optimize_test/include/asm-um/page.h
Martin Schwidefsky 2f569afd9c CONFIG_HIGHPTE vs. sub-page page tables.
Background: I've implemented 1K/2K page tables for s390.  These sub-page
page tables are required to properly support the s390 virtualization
instruction with KVM.  The SIE instruction requires that the page tables
have 256 page table entries (pte) followed by 256 page status table entries
(pgste).  The pgstes are only required if the process is using the SIE
instruction.  The pgstes are updated by the hardware and by the hypervisor
for a number of reasons, one of them is dirty and reference bit tracking.
To avoid wasting memory the standard pte table allocation should return
1K/2K (31/64 bit) and 2K/4K if the process is using SIE.

Problem: Page size on s390 is 4K, page table size is 1K or 2K.  That means
the s390 version for pte_alloc_one cannot return a pointer to a struct
page.  Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one
cannot return a pointer to a pte either, since that would require more than
32 bit for the return value of pte_alloc_one (and the pte * would not be
accessible since its not kmapped).

Solution: The only solution I found to this dilemma is a new typedef: a
pgtable_t.  For s390 pgtable_t will be a (pte *) - to be introduced with a
later patch.  For everybody else it will be a (struct page *).  The
additional problem with the initialization of the ptl lock and the
NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and
a destructor pgtable_page_dtor.  The page table allocation and free
functions need to call these two whenever a page table page is allocated or
freed.  pmd_populate will get a pgtable_t instead of a struct page pointer.
 To get the pgtable_t back from a pmd entry that has been installed with
pmd_populate a new function pmd_pgtable is added.  It replaces the pmd_page
call in free_pte_range and apply_to_pte_range.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 09:22:42 -08:00

124 lines
3.5 KiB
C

/*
* Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com)
* Copyright 2003 PathScale, Inc.
* Licensed under the GPL
*/
#ifndef __UM_PAGE_H
#define __UM_PAGE_H
struct page;
#include <linux/types.h>
#include <asm/vm-flags.h>
/* PAGE_SHIFT determines the page size */
#define PAGE_SHIFT 12
#define PAGE_SIZE (1UL << PAGE_SHIFT)
#define PAGE_MASK (~(PAGE_SIZE-1))
/*
* These are used to make use of C type-checking..
*/
#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE)
#define copy_page(to,from) memcpy((void *)(to), (void *)(from), PAGE_SIZE)
#define clear_user_page(page, vaddr, pg) clear_page(page)
#define copy_user_page(to, from, vaddr, pg) copy_page(to, from)
#if defined(CONFIG_3_LEVEL_PGTABLES) && !defined(CONFIG_64BIT)
typedef struct { unsigned long pte_low, pte_high; } pte_t;
typedef struct { unsigned long pmd; } pmd_t;
typedef struct { unsigned long pgd; } pgd_t;
#define pte_val(x) ((x).pte_low | ((unsigned long long) (x).pte_high << 32))
#define pte_get_bits(pte, bits) ((pte).pte_low & (bits))
#define pte_set_bits(pte, bits) ((pte).pte_low |= (bits))
#define pte_clear_bits(pte, bits) ((pte).pte_low &= ~(bits))
#define pte_copy(to, from) ({ (to).pte_high = (from).pte_high; \
smp_wmb(); \
(to).pte_low = (from).pte_low; })
#define pte_is_zero(pte) (!((pte).pte_low & ~_PAGE_NEWPAGE) && !(pte).pte_high)
#define pte_set_val(pte, phys, prot) \
({ (pte).pte_high = (phys) >> 32; \
(pte).pte_low = (phys) | pgprot_val(prot); })
#define pmd_val(x) ((x).pmd)
#define __pmd(x) ((pmd_t) { (x) } )
typedef unsigned long long pfn_t;
typedef unsigned long long phys_t;
#else
typedef struct { unsigned long pte; } pte_t;
typedef struct { unsigned long pgd; } pgd_t;
#ifdef CONFIG_3_LEVEL_PGTABLES
typedef struct { unsigned long pmd; } pmd_t;
#define pmd_val(x) ((x).pmd)
#define __pmd(x) ((pmd_t) { (x) } )
#endif
#define pte_val(x) ((x).pte)
#define pte_get_bits(p, bits) ((p).pte & (bits))
#define pte_set_bits(p, bits) ((p).pte |= (bits))
#define pte_clear_bits(p, bits) ((p).pte &= ~(bits))
#define pte_copy(to, from) ((to).pte = (from).pte)
#define pte_is_zero(p) (!((p).pte & ~_PAGE_NEWPAGE))
#define pte_set_val(p, phys, prot) (p).pte = (phys | pgprot_val(prot))
typedef unsigned long pfn_t;
typedef unsigned long phys_t;
#endif
typedef struct { unsigned long pgprot; } pgprot_t;
typedef struct page *pgtable_t;
#define pgd_val(x) ((x).pgd)
#define pgprot_val(x) ((x).pgprot)
#define __pte(x) ((pte_t) { (x) } )
#define __pgd(x) ((pgd_t) { (x) } )
#define __pgprot(x) ((pgprot_t) { (x) } )
/* to align the pointer to the (next) page boundary */
#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK)
extern unsigned long uml_physmem;
#define PAGE_OFFSET (uml_physmem)
#define KERNELBASE PAGE_OFFSET
#define __va_space (8*1024*1024)
#include "mem.h"
/* Cast to unsigned long before casting to void * to avoid a warning from
* mmap_kmem about cutting a long long down to a void *. Not sure that
* casting is the right thing, but 32-bit UML can't have 64-bit virtual
* addresses
*/
#define __pa(virt) to_phys((void *) (unsigned long) (virt))
#define __va(phys) to_virt((unsigned long) (phys))
#define phys_to_pfn(p) ((pfn_t) ((p) >> PAGE_SHIFT))
#define pfn_to_phys(pfn) ((phys_t) ((pfn) << PAGE_SHIFT))
#define pfn_valid(pfn) ((pfn) < max_mapnr)
#define virt_addr_valid(v) pfn_valid(phys_to_pfn(__pa(v)))
extern struct page *arch_validate(struct page *page, gfp_t mask, int order);
#define HAVE_ARCH_VALIDATE
#include <asm-generic/memory_model.h>
#include <asm-generic/page.h>
#endif