mirror of
https://github.com/adulau/aha.git
synced 2024-12-30 20:56:23 +00:00
7e675137a8
s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory
model (which is more dynamic than most). Instead, they had proposed to
implement it with an additional path through vm_normal_page(), using a bit in
the pte to determine whether or not the page should be refcounted:
vm_normal_page()
{
...
if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
if (vma->vm_flags & VM_MIXEDMAP) {
#ifdef s390
if (!mixedmap_refcount_pte(pte))
return NULL;
#else
if (!pfn_valid(pfn))
return NULL;
#endif
goto out;
}
...
}
This is fine, however if we are allowed to use a bit in the pte to determine
refcountedness, we can use that to _completely_ replace all the vma based
schemes. So instead of adding more cases to the already complex vma-based
scheme, we can have a clearly seperate and simple pte-based scheme (and get
slightly better code generation in the process):
vm_normal_page()
{
#ifdef s390
if (!mixedmap_refcount_pte(pte))
return NULL;
return pte_page(pte);
#else
...
#endif
}
And finally, we may rather make this concept usable by any architecture rather
than making it s390 only, so implement a new type of pte state for this.
Unfortunately the old vma based code must stay, because some architectures may
not be able to spare pte bits. This makes vm_normal_page a little bit more
ugly than we would like, but the 2 cases are clearly seperate.
So introduce a pte_special pte state, and use it in mm/memory.c. It is
currently a noop for all architectures, so this doesn't actually result in any
compiled code changes to mm/memory.o.
BTW:
I haven't put vm_normal_page() into arch code as-per an earlier suggestion.
The reason is that, regardless of where vm_normal_page is actually
implemented, the *abstraction* is still exactly the same. Also, while it
depends on whether the architecture has pte_special or not, that is the
only two possible cases, and it really isn't an arch specific function --
the role of the arch code should be to provide primitive functions and
accessors with which to build the core code; pte_special does that. We do
not want architectures to know or care about vm_normal_page itself, and
we definitely don't want them being able to invent something new there
out of sight of mm/ code. If we made vm_normal_page an arch function, then
we have to make vm_insert_mixed (next patch) an arch function too. So I
don't think moving it to arch code fundamentally improves any abstractions,
while it does practically make the code more difficult to follow, for both
mm and arch developers, and easier to misuse.
[akpm@linux-foundation.org: build fix]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Carsten Otte <cotte@de.ibm.com>
Cc: Jared Hulbert <jaredeh@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
358 lines
9.4 KiB
C
358 lines
9.4 KiB
C
/*
|
|
* Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
|
|
* Copyright 2003 PathScale, Inc.
|
|
* Derived from include/asm-i386/pgtable.h
|
|
* Licensed under the GPL
|
|
*/
|
|
|
|
#ifndef __UM_PGTABLE_H
|
|
#define __UM_PGTABLE_H
|
|
|
|
#include <asm/fixmap.h>
|
|
|
|
#define _PAGE_PRESENT 0x001
|
|
#define _PAGE_NEWPAGE 0x002
|
|
#define _PAGE_NEWPROT 0x004
|
|
#define _PAGE_RW 0x020
|
|
#define _PAGE_USER 0x040
|
|
#define _PAGE_ACCESSED 0x080
|
|
#define _PAGE_DIRTY 0x100
|
|
/* If _PAGE_PRESENT is clear, we use these: */
|
|
#define _PAGE_FILE 0x008 /* nonlinear file mapping, saved PTE; unset:swap */
|
|
#define _PAGE_PROTNONE 0x010 /* if the user mapped it with PROT_NONE;
|
|
pte_present gives true */
|
|
|
|
#ifdef CONFIG_3_LEVEL_PGTABLES
|
|
#include "asm/pgtable-3level.h"
|
|
#else
|
|
#include "asm/pgtable-2level.h"
|
|
#endif
|
|
|
|
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
|
|
|
|
/* zero page used for uninitialized stuff */
|
|
extern unsigned long *empty_zero_page;
|
|
|
|
#define pgtable_cache_init() do ; while (0)
|
|
|
|
/* Just any arbitrary offset to the start of the vmalloc VM area: the
|
|
* current 8MB value just means that there will be a 8MB "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. ;)
|
|
*/
|
|
|
|
extern unsigned long end_iomem;
|
|
|
|
#define VMALLOC_OFFSET (__va_space)
|
|
#define VMALLOC_START ((end_iomem + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
|
|
#ifdef CONFIG_HIGHMEM
|
|
# define VMALLOC_END (PKMAP_BASE-2*PAGE_SIZE)
|
|
#else
|
|
# define VMALLOC_END (FIXADDR_START-2*PAGE_SIZE)
|
|
#endif
|
|
|
|
#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
|
|
#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
|
|
#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
|
|
|
|
#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
|
|
#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
|
|
#define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
|
|
#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
|
|
#define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
|
|
|
|
/*
|
|
* The i386 can't do page protection for execute, and considers that the same
|
|
* are read.
|
|
* Also, write permissions imply read permissions. This is the closest we can
|
|
* get..
|
|
*/
|
|
#define __P000 PAGE_NONE
|
|
#define __P001 PAGE_READONLY
|
|
#define __P010 PAGE_COPY
|
|
#define __P011 PAGE_COPY
|
|
#define __P100 PAGE_READONLY
|
|
#define __P101 PAGE_READONLY
|
|
#define __P110 PAGE_COPY
|
|
#define __P111 PAGE_COPY
|
|
|
|
#define __S000 PAGE_NONE
|
|
#define __S001 PAGE_READONLY
|
|
#define __S010 PAGE_SHARED
|
|
#define __S011 PAGE_SHARED
|
|
#define __S100 PAGE_READONLY
|
|
#define __S101 PAGE_READONLY
|
|
#define __S110 PAGE_SHARED
|
|
#define __S111 PAGE_SHARED
|
|
|
|
/*
|
|
* ZERO_PAGE is a global shared page that is always zero: used
|
|
* for zero-mapped memory areas etc..
|
|
*/
|
|
#define ZERO_PAGE(vaddr) virt_to_page(empty_zero_page)
|
|
|
|
#define pte_clear(mm,addr,xp) pte_set_val(*(xp), (phys_t) 0, __pgprot(_PAGE_NEWPAGE))
|
|
|
|
#define pmd_none(x) (!((unsigned long)pmd_val(x) & ~_PAGE_NEWPAGE))
|
|
#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
|
|
|
|
#define pmd_present(x) (pmd_val(x) & _PAGE_PRESENT)
|
|
#define pmd_clear(xp) do { pmd_val(*(xp)) = _PAGE_NEWPAGE; } while (0)
|
|
|
|
#define pmd_newpage(x) (pmd_val(x) & _PAGE_NEWPAGE)
|
|
#define pmd_mkuptodate(x) (pmd_val(x) &= ~_PAGE_NEWPAGE)
|
|
|
|
#define pud_newpage(x) (pud_val(x) & _PAGE_NEWPAGE)
|
|
#define pud_mkuptodate(x) (pud_val(x) &= ~_PAGE_NEWPAGE)
|
|
|
|
#define pmd_page(pmd) phys_to_page(pmd_val(pmd) & PAGE_MASK)
|
|
|
|
#define pte_page(x) pfn_to_page(pte_pfn(x))
|
|
|
|
#define pte_present(x) pte_get_bits(x, (_PAGE_PRESENT | _PAGE_PROTNONE))
|
|
|
|
/*
|
|
* =================================
|
|
* Flags checking section.
|
|
* =================================
|
|
*/
|
|
|
|
static inline int pte_none(pte_t pte)
|
|
{
|
|
return pte_is_zero(pte);
|
|
}
|
|
|
|
/*
|
|
* The following only work if pte_present() is true.
|
|
* Undefined behaviour if not..
|
|
*/
|
|
static inline int pte_read(pte_t pte)
|
|
{
|
|
return((pte_get_bits(pte, _PAGE_USER)) &&
|
|
!(pte_get_bits(pte, _PAGE_PROTNONE)));
|
|
}
|
|
|
|
static inline int pte_exec(pte_t pte){
|
|
return((pte_get_bits(pte, _PAGE_USER)) &&
|
|
!(pte_get_bits(pte, _PAGE_PROTNONE)));
|
|
}
|
|
|
|
static inline int pte_write(pte_t pte)
|
|
{
|
|
return((pte_get_bits(pte, _PAGE_RW)) &&
|
|
!(pte_get_bits(pte, _PAGE_PROTNONE)));
|
|
}
|
|
|
|
/*
|
|
* The following only works if pte_present() is not true.
|
|
*/
|
|
static inline int pte_file(pte_t pte)
|
|
{
|
|
return pte_get_bits(pte, _PAGE_FILE);
|
|
}
|
|
|
|
static inline int pte_dirty(pte_t pte)
|
|
{
|
|
return pte_get_bits(pte, _PAGE_DIRTY);
|
|
}
|
|
|
|
static inline int pte_young(pte_t pte)
|
|
{
|
|
return pte_get_bits(pte, _PAGE_ACCESSED);
|
|
}
|
|
|
|
static inline int pte_newpage(pte_t pte)
|
|
{
|
|
return pte_get_bits(pte, _PAGE_NEWPAGE);
|
|
}
|
|
|
|
static inline int pte_newprot(pte_t pte)
|
|
{
|
|
return(pte_present(pte) && (pte_get_bits(pte, _PAGE_NEWPROT)));
|
|
}
|
|
|
|
static inline int pte_special(pte_t pte)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* =================================
|
|
* Flags setting section.
|
|
* =================================
|
|
*/
|
|
|
|
static inline pte_t pte_mknewprot(pte_t pte)
|
|
{
|
|
pte_set_bits(pte, _PAGE_NEWPROT);
|
|
return(pte);
|
|
}
|
|
|
|
static inline pte_t pte_mkclean(pte_t pte)
|
|
{
|
|
pte_clear_bits(pte, _PAGE_DIRTY);
|
|
return(pte);
|
|
}
|
|
|
|
static inline pte_t pte_mkold(pte_t pte)
|
|
{
|
|
pte_clear_bits(pte, _PAGE_ACCESSED);
|
|
return(pte);
|
|
}
|
|
|
|
static inline pte_t pte_wrprotect(pte_t pte)
|
|
{
|
|
pte_clear_bits(pte, _PAGE_RW);
|
|
return(pte_mknewprot(pte));
|
|
}
|
|
|
|
static inline pte_t pte_mkread(pte_t pte)
|
|
{
|
|
pte_set_bits(pte, _PAGE_USER);
|
|
return(pte_mknewprot(pte));
|
|
}
|
|
|
|
static inline pte_t pte_mkdirty(pte_t pte)
|
|
{
|
|
pte_set_bits(pte, _PAGE_DIRTY);
|
|
return(pte);
|
|
}
|
|
|
|
static inline pte_t pte_mkyoung(pte_t pte)
|
|
{
|
|
pte_set_bits(pte, _PAGE_ACCESSED);
|
|
return(pte);
|
|
}
|
|
|
|
static inline pte_t pte_mkwrite(pte_t pte)
|
|
{
|
|
pte_set_bits(pte, _PAGE_RW);
|
|
return(pte_mknewprot(pte));
|
|
}
|
|
|
|
static inline pte_t pte_mkuptodate(pte_t pte)
|
|
{
|
|
pte_clear_bits(pte, _PAGE_NEWPAGE);
|
|
if(pte_present(pte))
|
|
pte_clear_bits(pte, _PAGE_NEWPROT);
|
|
return(pte);
|
|
}
|
|
|
|
static inline pte_t pte_mknewpage(pte_t pte)
|
|
{
|
|
pte_set_bits(pte, _PAGE_NEWPAGE);
|
|
return(pte);
|
|
}
|
|
|
|
static inline pte_t pte_mkspecial(pte_t pte)
|
|
{
|
|
return(pte);
|
|
}
|
|
|
|
static inline void set_pte(pte_t *pteptr, pte_t pteval)
|
|
{
|
|
pte_copy(*pteptr, pteval);
|
|
|
|
/* If it's a swap entry, it needs to be marked _PAGE_NEWPAGE so
|
|
* fix_range knows to unmap it. _PAGE_NEWPROT is specific to
|
|
* mapped pages.
|
|
*/
|
|
|
|
*pteptr = pte_mknewpage(*pteptr);
|
|
if(pte_present(*pteptr)) *pteptr = pte_mknewprot(*pteptr);
|
|
}
|
|
#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
|
|
|
|
/*
|
|
* Conversion functions: convert a page and protection to a page entry,
|
|
* and a page entry and page directory to the page they refer to.
|
|
*/
|
|
|
|
#define phys_to_page(phys) pfn_to_page(phys_to_pfn(phys))
|
|
#define __virt_to_page(virt) phys_to_page(__pa(virt))
|
|
#define page_to_phys(page) pfn_to_phys((pfn_t) page_to_pfn(page))
|
|
#define virt_to_page(addr) __virt_to_page((const unsigned long) addr)
|
|
|
|
#define mk_pte(page, pgprot) \
|
|
({ pte_t pte; \
|
|
\
|
|
pte_set_val(pte, page_to_phys(page), (pgprot)); \
|
|
if (pte_present(pte)) \
|
|
pte_mknewprot(pte_mknewpage(pte)); \
|
|
pte;})
|
|
|
|
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
|
|
{
|
|
pte_set_val(pte, (pte_val(pte) & _PAGE_CHG_MASK), newprot);
|
|
return pte;
|
|
}
|
|
|
|
/*
|
|
* the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
|
|
*
|
|
* this macro returns the index of the entry in the pgd page which would
|
|
* control the given virtual address
|
|
*/
|
|
#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
|
|
|
|
/*
|
|
* pgd_offset() returns a (pgd_t *)
|
|
* pgd_index() is used get the offset into the pgd page's array of pgd_t's;
|
|
*/
|
|
#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
|
|
|
|
/*
|
|
* a shortcut which implies the use of the kernel's pgd, instead
|
|
* of a process's
|
|
*/
|
|
#define pgd_offset_k(address) pgd_offset(&init_mm, address)
|
|
|
|
/*
|
|
* the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
|
|
*
|
|
* this macro returns the index of the entry in the pmd page which would
|
|
* control the given virtual address
|
|
*/
|
|
#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
|
|
#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
|
|
|
|
#define pmd_page_vaddr(pmd) \
|
|
((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
|
|
|
|
/*
|
|
* the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
|
|
*
|
|
* this macro returns the index of the entry in the pte page which would
|
|
* control the given virtual address
|
|
*/
|
|
#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
|
|
#define pte_offset_kernel(dir, address) \
|
|
((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address))
|
|
#define pte_offset_map(dir, address) \
|
|
((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address))
|
|
#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address)
|
|
#define pte_unmap(pte) do { } while (0)
|
|
#define pte_unmap_nested(pte) do { } while (0)
|
|
|
|
struct mm_struct;
|
|
extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr);
|
|
|
|
#define update_mmu_cache(vma,address,pte) do ; while (0)
|
|
|
|
/* Encode and de-code a swap entry */
|
|
#define __swp_type(x) (((x).val >> 4) & 0x3f)
|
|
#define __swp_offset(x) ((x).val >> 11)
|
|
|
|
#define __swp_entry(type, offset) \
|
|
((swp_entry_t) { ((type) << 4) | ((offset) << 11) })
|
|
#define __pte_to_swp_entry(pte) \
|
|
((swp_entry_t) { pte_val(pte_mkuptodate(pte)) })
|
|
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
|
|
|
|
#define kern_addr_valid(addr) (1)
|
|
|
|
#include <asm-generic/pgtable.h>
|
|
|
|
#endif
|