2005-04-17 06:20:36 +08:00
|
|
|
#ifndef _ALPHA_PGTABLE_H
|
|
|
|
|
#define _ALPHA_PGTABLE_H
|
|
|
|
|
|
|
|
|
|
#include <asm-generic/4level-fixup.h>
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* This file contains the functions and defines necessary to modify and use
|
|
|
|
|
* the Alpha page table tree.
|
|
|
|
|
*
|
|
|
|
|
* This hopefully works with any standard Alpha page-size, as defined
|
|
|
|
|
* in <asm/page.h> (currently 8192).
|
|
|
|
|
*/
|
|
|
|
|
#include <linux/mmzone.h>
|
|
|
|
|
|
|
|
|
|
#include <asm/page.h>
|
|
|
|
|
#include <asm/processor.h> /* For TASK_SIZE */
|
|
|
|
|
#include <asm/machvec.h>
|
2012-03-29 01:11:12 +08:00
|
|
|
#include <asm/setup.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-11-07 16:59:43 +08:00
|
|
|
struct mm_struct;
|
|
|
|
|
struct vm_area_struct;
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Certain architectures need to do special things when PTEs
|
|
|
|
|
* within a page table are directly modified. Thus, the following
|
|
|
|
|
* hook is made available.
|
|
|
|
|
*/
|
|
|
|
|
#define set_pte(pteptr, pteval) ((*(pteptr)) = (pteval))
|
|
|
|
|
#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
|
|
|
|
|
|
|
|
|
|
/* PMD_SHIFT determines the size of the area a second-level page table can map */
|
|
|
|
|
#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT-3))
|
|
|
|
|
#define PMD_SIZE (1UL << PMD_SHIFT)
|
|
|
|
|
#define PMD_MASK (~(PMD_SIZE-1))
|
|
|
|
|
|
|
|
|
|
/* PGDIR_SHIFT determines what a third-level page table entry can map */
|
|
|
|
|
#define PGDIR_SHIFT (PAGE_SHIFT + 2*(PAGE_SHIFT-3))
|
|
|
|
|
#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
|
|
|
|
|
#define PGDIR_MASK (~(PGDIR_SIZE-1))
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Entries per page directory level: the Alpha is three-level, with
|
|
|
|
|
* all levels having a one-page page table.
|
|
|
|
|
*/
|
|
|
|
|
#define PTRS_PER_PTE (1UL << (PAGE_SHIFT-3))
|
|
|
|
|
#define PTRS_PER_PMD (1UL << (PAGE_SHIFT-3))
|
|
|
|
|
#define PTRS_PER_PGD (1UL << (PAGE_SHIFT-3))
|
|
|
|
|
#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)
|
2005-04-20 04:29:23 +08:00
|
|
|
#define FIRST_USER_ADDRESS 0
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
/* Number of pointers that fit on a page: this will go away. */
|
|
|
|
|
#define PTRS_PER_PAGE (1UL << (PAGE_SHIFT-3))
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
|
|
|
|
|
#define VMALLOC_START 0xfffffe0000000000
|
|
|
|
|
#else
|
|
|
|
|
#define VMALLOC_START (-2*PGDIR_SIZE)
|
|
|
|
|
#endif
|
|
|
|
|
#define VMALLOC_END (-PGDIR_SIZE)
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* OSF/1 PAL-code-imposed page table bits
|
|
|
|
|
*/
|
|
|
|
|
#define _PAGE_VALID 0x0001
|
|
|
|
|
#define _PAGE_FOR 0x0002 /* used for page protection (fault on read) */
|
|
|
|
|
#define _PAGE_FOW 0x0004 /* used for page protection (fault on write) */
|
|
|
|
|
#define _PAGE_FOE 0x0008 /* used for page protection (fault on exec) */
|
|
|
|
|
#define _PAGE_ASM 0x0010
|
|
|
|
|
#define _PAGE_KRE 0x0100 /* xxx - see below on the "accessed" bit */
|
|
|
|
|
#define _PAGE_URE 0x0200 /* xxx */
|
|
|
|
|
#define _PAGE_KWE 0x1000 /* used to do the dirty bit in software */
|
|
|
|
|
#define _PAGE_UWE 0x2000 /* used to do the dirty bit in software */
|
|
|
|
|
|
|
|
|
|
/* .. and these are ours ... */
|
|
|
|
|
#define _PAGE_DIRTY 0x20000
|
|
|
|
|
#define _PAGE_ACCESSED 0x40000
|
|
|
|
|
#define _PAGE_FILE 0x80000 /* set:pagecache, unset:swap */
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* NOTE! The "accessed" bit isn't necessarily exact: it can be kept exactly
|
|
|
|
|
* by software (use the KRE/URE/KWE/UWE bits appropriately), but I'll fake it.
|
|
|
|
|
* Under Linux/AXP, the "accessed" bit just means "read", and I'll just use
|
|
|
|
|
* the KRE/URE bits to watch for it. That way we don't need to overload the
|
|
|
|
|
* KWE/UWE bits with both handling dirty and accessed.
|
|
|
|
|
*
|
|
|
|
|
* Note that the kernel uses the accessed bit just to check whether to page
|
|
|
|
|
* out a page or not, so it doesn't have to be exact anyway.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#define __DIRTY_BITS (_PAGE_DIRTY | _PAGE_KWE | _PAGE_UWE)
|
|
|
|
|
#define __ACCESS_BITS (_PAGE_ACCESSED | _PAGE_KRE | _PAGE_URE)
|
|
|
|
|
|
|
|
|
|
#define _PFN_MASK 0xFFFFFFFF00000000UL
|
|
|
|
|
|
|
|
|
|
#define _PAGE_TABLE (_PAGE_VALID | __DIRTY_BITS | __ACCESS_BITS)
|
|
|
|
|
#define _PAGE_CHG_MASK (_PFN_MASK | __DIRTY_BITS | __ACCESS_BITS)
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* All the normal masks have the "page accessed" bits on, as any time they are used,
|
|
|
|
|
* the page is accessed. They are cleared only by the page-out routines
|
|
|
|
|
*/
|
|
|
|
|
#define PAGE_NONE __pgprot(_PAGE_VALID | __ACCESS_BITS | _PAGE_FOR | _PAGE_FOW | _PAGE_FOE)
|
|
|
|
|
#define PAGE_SHARED __pgprot(_PAGE_VALID | __ACCESS_BITS)
|
|
|
|
|
#define PAGE_COPY __pgprot(_PAGE_VALID | __ACCESS_BITS | _PAGE_FOW)
|
|
|
|
|
#define PAGE_READONLY __pgprot(_PAGE_VALID | __ACCESS_BITS | _PAGE_FOW)
|
|
|
|
|
#define PAGE_KERNEL __pgprot(_PAGE_VALID | _PAGE_ASM | _PAGE_KRE | _PAGE_KWE)
|
|
|
|
|
|
|
|
|
|
#define _PAGE_NORMAL(x) __pgprot(_PAGE_VALID | __ACCESS_BITS | (x))
|
|
|
|
|
|
|
|
|
|
#define _PAGE_P(x) _PAGE_NORMAL((x) | (((x) & _PAGE_FOW)?0:_PAGE_FOW))
|
|
|
|
|
#define _PAGE_S(x) _PAGE_NORMAL(x)
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* The hardware can handle write-only mappings, but as the Alpha
|
|
|
|
|
* architecture does byte-wide writes with a read-modify-write
|
|
|
|
|
* sequence, it's not practical to have write-without-read privs.
|
|
|
|
|
* Thus the "-w- -> rw-" and "-wx -> rwx" mapping here (and in
|
|
|
|
|
* arch/alpha/mm/fault.c)
|
|
|
|
|
*/
|
|
|
|
|
/* xwr */
|
|
|
|
|
#define __P000 _PAGE_P(_PAGE_FOE | _PAGE_FOW | _PAGE_FOR)
|
|
|
|
|
#define __P001 _PAGE_P(_PAGE_FOE | _PAGE_FOW)
|
|
|
|
|
#define __P010 _PAGE_P(_PAGE_FOE)
|
|
|
|
|
#define __P011 _PAGE_P(_PAGE_FOE)
|
|
|
|
|
#define __P100 _PAGE_P(_PAGE_FOW | _PAGE_FOR)
|
|
|
|
|
#define __P101 _PAGE_P(_PAGE_FOW)
|
|
|
|
|
#define __P110 _PAGE_P(0)
|
|
|
|
|
#define __P111 _PAGE_P(0)
|
|
|
|
|
|
|
|
|
|
#define __S000 _PAGE_S(_PAGE_FOE | _PAGE_FOW | _PAGE_FOR)
|
|
|
|
|
#define __S001 _PAGE_S(_PAGE_FOE | _PAGE_FOW)
|
|
|
|
|
#define __S010 _PAGE_S(_PAGE_FOE)
|
|
|
|
|
#define __S011 _PAGE_S(_PAGE_FOE)
|
|
|
|
|
#define __S100 _PAGE_S(_PAGE_FOW | _PAGE_FOR)
|
|
|
|
|
#define __S101 _PAGE_S(_PAGE_FOW)
|
|
|
|
|
#define __S110 _PAGE_S(0)
|
|
|
|
|
#define __S111 _PAGE_S(0)
|
|
|
|
|
|
2005-07-13 04:58:19 +08:00
|
|
|
/*
|
|
|
|
|
* pgprot_noncached() is only for infiniband pci support, and a real
|
|
|
|
|
* implementation for RAM would be more complicated.
|
|
|
|
|
*/
|
2005-07-08 08:57:09 +08:00
|
|
|
#define pgprot_noncached(prot) (prot)
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* BAD_PAGETABLE is used when we need a bogus page-table, while
|
|
|
|
|
* BAD_PAGE is used for a bogus page.
|
|
|
|
|
*
|
|
|
|
|
* ZERO_PAGE is a global shared page that is always zero: used
|
|
|
|
|
* for zero-mapped memory areas etc..
|
|
|
|
|
*/
|
|
|
|
|
extern pte_t __bad_page(void);
|
|
|
|
|
extern pmd_t * __bad_pagetable(void);
|
|
|
|
|
|
|
|
|
|
extern unsigned long __zero_page(void);
|
|
|
|
|
|
|
|
|
|
#define BAD_PAGETABLE __bad_pagetable()
|
|
|
|
|
#define BAD_PAGE __bad_page()
|
|
|
|
|
#define ZERO_PAGE(vaddr) (virt_to_page(ZERO_PGE))
|
|
|
|
|
|
|
|
|
|
/* number of bits that fit into a memory pointer */
|
|
|
|
|
#define BITS_PER_PTR (8*sizeof(unsigned long))
|
|
|
|
|
|
|
|
|
|
/* to align the pointer to a pointer address */
|
|
|
|
|
#define PTR_MASK (~(sizeof(void*)-1))
|
|
|
|
|
|
|
|
|
|
/* sizeof(void*)==1<<SIZEOF_PTR_LOG2 */
|
|
|
|
|
#define SIZEOF_PTR_LOG2 3
|
|
|
|
|
|
|
|
|
|
/* to find an entry in a page-table */
|
|
|
|
|
#define PAGE_PTR(address) \
|
|
|
|
|
((unsigned long)(address)>>(PAGE_SHIFT-SIZEOF_PTR_LOG2)&PTR_MASK&~PAGE_MASK)
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* On certain platforms whose physical address space can overlap KSEG,
|
|
|
|
|
* namely EV6 and above, we must re-twiddle the physaddr to restore the
|
|
|
|
|
* correct high-order bits.
|
|
|
|
|
*
|
|
|
|
|
* This is extremely confusing until you realize that this is actually
|
|
|
|
|
* just working around a userspace bug. The X server was intending to
|
|
|
|
|
* provide the physical address but instead provided the KSEG address.
|
|
|
|
|
* Or tried to, except it's not representable.
|
|
|
|
|
*
|
|
|
|
|
* On Tsunami there's nothing meaningful at 0x40000000000, so this is
|
|
|
|
|
* a safe thing to do. Come the first core logic that does put something
|
|
|
|
|
* in this area -- memory or whathaveyou -- then this hack will have
|
|
|
|
|
* to go away. So be prepared!
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#if defined(CONFIG_ALPHA_GENERIC) && defined(USE_48_BIT_KSEG)
|
|
|
|
|
#error "EV6-only feature in a generic kernel"
|
|
|
|
|
#endif
|
|
|
|
|
#if defined(CONFIG_ALPHA_GENERIC) || \
|
|
|
|
|
(defined(CONFIG_ALPHA_EV6) && !defined(USE_48_BIT_KSEG))
|
|
|
|
|
#define KSEG_PFN (0xc0000000000UL >> PAGE_SHIFT)
|
|
|
|
|
#define PHYS_TWIDDLE(pfn) \
|
|
|
|
|
((((pfn) & KSEG_PFN) == (0x40000000000UL >> PAGE_SHIFT)) \
|
|
|
|
|
? ((pfn) ^= KSEG_PFN) : (pfn))
|
|
|
|
|
#else
|
|
|
|
|
#define PHYS_TWIDDLE(pfn) (pfn)
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Conversion functions: convert a page and protection to a page entry,
|
|
|
|
|
* and a page entry and page directory to the page they refer to.
|
|
|
|
|
*/
|
|
|
|
|
#ifndef CONFIG_DISCONTIGMEM
|
|
|
|
|
#define page_to_pa(page) (((page) - mem_map) << PAGE_SHIFT)
|
|
|
|
|
|
|
|
|
|
#define pte_pfn(pte) (pte_val(pte) >> 32)
|
|
|
|
|
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
|
|
|
|
|
#define mk_pte(page, pgprot) \
|
|
|
|
|
({ \
|
|
|
|
|
pte_t pte; \
|
|
|
|
|
\
|
|
|
|
|
pte_val(pte) = (page_to_pfn(page) << 32) | pgprot_val(pgprot); \
|
|
|
|
|
pte; \
|
|
|
|
|
})
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
extern inline pte_t pfn_pte(unsigned long physpfn, pgprot_t pgprot)
|
|
|
|
|
{ pte_t pte; pte_val(pte) = (PHYS_TWIDDLE(physpfn) << 32) | pgprot_val(pgprot); return pte; }
|
|
|
|
|
|
|
|
|
|
extern 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; }
|
|
|
|
|
|
|
|
|
|
extern inline void pmd_set(pmd_t * pmdp, pte_t * ptep)
|
|
|
|
|
{ pmd_val(*pmdp) = _PAGE_TABLE | ((((unsigned long) ptep) - PAGE_OFFSET) << (32-PAGE_SHIFT)); }
|
|
|
|
|
|
|
|
|
|
extern inline void pgd_set(pgd_t * pgdp, pmd_t * pmdp)
|
|
|
|
|
{ pgd_val(*pgdp) = _PAGE_TABLE | ((((unsigned long) pmdp) - PAGE_OFFSET) << (32-PAGE_SHIFT)); }
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
extern inline unsigned long
|
2006-09-26 14:31:48 +08:00
|
|
|
pmd_page_vaddr(pmd_t pmd)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
return ((pmd_val(pmd) & _PFN_MASK) >> (32-PAGE_SHIFT)) + PAGE_OFFSET;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#ifndef CONFIG_DISCONTIGMEM
|
|
|
|
|
#define pmd_page(pmd) (mem_map + ((pmd_val(pmd) & _PFN_MASK) >> 32))
|
2006-09-26 14:31:48 +08:00
|
|
|
#define pgd_page(pgd) (mem_map + ((pgd_val(pgd) & _PFN_MASK) >> 32))
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
2006-09-26 14:31:48 +08:00
|
|
|
extern inline unsigned long pgd_page_vaddr(pgd_t pgd)
|
2005-04-17 06:20:36 +08:00
|
|
|
{ return PAGE_OFFSET + ((pgd_val(pgd) & _PFN_MASK) >> (32-PAGE_SHIFT)); }
|
|
|
|
|
|
|
|
|
|
extern inline int pte_none(pte_t pte) { return !pte_val(pte); }
|
|
|
|
|
extern inline int pte_present(pte_t pte) { return pte_val(pte) & _PAGE_VALID; }
|
|
|
|
|
extern inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
|
|
|
|
|
{
|
|
|
|
|
pte_val(*ptep) = 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
extern inline int pmd_none(pmd_t pmd) { return !pmd_val(pmd); }
|
|
|
|
|
extern inline int pmd_bad(pmd_t pmd) { return (pmd_val(pmd) & ~_PFN_MASK) != _PAGE_TABLE; }
|
|
|
|
|
extern inline int pmd_present(pmd_t pmd) { return pmd_val(pmd) & _PAGE_VALID; }
|
|
|
|
|
extern inline void pmd_clear(pmd_t * pmdp) { pmd_val(*pmdp) = 0; }
|
|
|
|
|
|
|
|
|
|
extern inline int pgd_none(pgd_t pgd) { return !pgd_val(pgd); }
|
|
|
|
|
extern inline int pgd_bad(pgd_t pgd) { return (pgd_val(pgd) & ~_PFN_MASK) != _PAGE_TABLE; }
|
|
|
|
|
extern inline int pgd_present(pgd_t pgd) { return pgd_val(pgd) & _PAGE_VALID; }
|
|
|
|
|
extern inline void pgd_clear(pgd_t * pgdp) { pgd_val(*pgdp) = 0; }
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* The following only work if pte_present() is true.
|
|
|
|
|
* Undefined behaviour if not..
|
|
|
|
|
*/
|
|
|
|
|
extern inline int pte_write(pte_t pte) { return !(pte_val(pte) & _PAGE_FOW); }
|
|
|
|
|
extern inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; }
|
|
|
|
|
extern inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; }
|
|
|
|
|
extern inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; }
|
mm: introduce pte_special pte bit
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>
2008-04-28 17:13:00 +08:00
|
|
|
extern inline int pte_special(pte_t pte) { return 0; }
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
extern inline pte_t pte_wrprotect(pte_t pte) { pte_val(pte) |= _PAGE_FOW; return pte; }
|
|
|
|
|
extern inline pte_t pte_mkclean(pte_t pte) { pte_val(pte) &= ~(__DIRTY_BITS); return pte; }
|
|
|
|
|
extern inline pte_t pte_mkold(pte_t pte) { pte_val(pte) &= ~(__ACCESS_BITS); return pte; }
|
|
|
|
|
extern inline pte_t pte_mkwrite(pte_t pte) { pte_val(pte) &= ~_PAGE_FOW; return pte; }
|
|
|
|
|
extern inline pte_t pte_mkdirty(pte_t pte) { pte_val(pte) |= __DIRTY_BITS; return pte; }
|
|
|
|
|
extern inline pte_t pte_mkyoung(pte_t pte) { pte_val(pte) |= __ACCESS_BITS; return pte; }
|
mm: introduce pte_special pte bit
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>
2008-04-28 17:13:00 +08:00
|
|
|
extern inline pte_t pte_mkspecial(pte_t pte) { return pte; }
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#define PAGE_DIR_OFFSET(tsk,address) pgd_offset((tsk),(address))
|
|
|
|
|
|
|
|
|
|
/* 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) & (PTRS_PER_PGD-1))
|
|
|
|
|
#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
|
|
|
|
|
|
fix SMP data race in pagetable setup vs walking
There is a possible data race in the page table walking code. After the split
ptlock patches, it actually seems to have been introduced to the core code, but
even before that I think it would have impacted some architectures (powerpc
and sparc64, at least, walk the page tables without taking locks eg. see
find_linux_pte()).
The race is as follows:
The pte page is allocated, zeroed, and its struct page gets its spinlock
initialized. The mm-wide ptl is then taken, and then the pte page is inserted
into the pagetables.
At this point, the spinlock is not guaranteed to have ordered the previous
stores to initialize the pte page with the subsequent store to put it in the
page tables. So another Linux page table walker might be walking down (without
any locks, because we have split-leaf-ptls), and find that new pte we've
inserted. It might try to take the spinlock before the store from the other
CPU initializes it. And subsequently it might read a pte_t out before stores
from the other CPU have cleared the memory.
There are also similar races in higher levels of the page tables. They
obviously don't involve the spinlock, but could see uninitialized memory.
Arch code and hardware pagetable walkers that walk the pagetables without
locks could see similar uninitialized memory problems, regardless of whether
split ptes are enabled or not.
I prefer to put the barriers in core code, because that's where the higher
level logic happens, but the page table accessors are per-arch, and open-coding
them everywhere I don't think is an option. I'll put the read-side barriers
in alpha arch code for now (other architectures perform data-dependent loads
in order).
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-14 12:37:36 +08:00
|
|
|
/*
|
|
|
|
|
* The smp_read_barrier_depends() in the following functions are required to
|
|
|
|
|
* order the load of *dir (the pointer in the top level page table) with any
|
|
|
|
|
* subsequent load of the returned pmd_t *ret (ret is data dependent on *dir).
|
|
|
|
|
*
|
|
|
|
|
* If this ordering is not enforced, the CPU might load an older value of
|
|
|
|
|
* *ret, which may be uninitialized data. See mm/memory.c:__pte_alloc for
|
|
|
|
|
* more details.
|
|
|
|
|
*
|
|
|
|
|
* Note that we never change the mm->pgd pointer after the task is running, so
|
|
|
|
|
* pgd_offset does not require such a barrier.
|
|
|
|
|
*/
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Find an entry in the second-level page table.. */
|
|
|
|
|
extern inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address)
|
|
|
|
|
{
|
fix SMP data race in pagetable setup vs walking
There is a possible data race in the page table walking code. After the split
ptlock patches, it actually seems to have been introduced to the core code, but
even before that I think it would have impacted some architectures (powerpc
and sparc64, at least, walk the page tables without taking locks eg. see
find_linux_pte()).
The race is as follows:
The pte page is allocated, zeroed, and its struct page gets its spinlock
initialized. The mm-wide ptl is then taken, and then the pte page is inserted
into the pagetables.
At this point, the spinlock is not guaranteed to have ordered the previous
stores to initialize the pte page with the subsequent store to put it in the
page tables. So another Linux page table walker might be walking down (without
any locks, because we have split-leaf-ptls), and find that new pte we've
inserted. It might try to take the spinlock before the store from the other
CPU initializes it. And subsequently it might read a pte_t out before stores
from the other CPU have cleared the memory.
There are also similar races in higher levels of the page tables. They
obviously don't involve the spinlock, but could see uninitialized memory.
Arch code and hardware pagetable walkers that walk the pagetables without
locks could see similar uninitialized memory problems, regardless of whether
split ptes are enabled or not.
I prefer to put the barriers in core code, because that's where the higher
level logic happens, but the page table accessors are per-arch, and open-coding
them everywhere I don't think is an option. I'll put the read-side barriers
in alpha arch code for now (other architectures perform data-dependent loads
in order).
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-14 12:37:36 +08:00
|
|
|
pmd_t *ret = (pmd_t *) pgd_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
|
|
|
|
|
smp_read_barrier_depends(); /* see above */
|
|
|
|
|
return ret;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Find an entry in the third-level page table.. */
|
|
|
|
|
extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address)
|
|
|
|
|
{
|
fix SMP data race in pagetable setup vs walking
There is a possible data race in the page table walking code. After the split
ptlock patches, it actually seems to have been introduced to the core code, but
even before that I think it would have impacted some architectures (powerpc
and sparc64, at least, walk the page tables without taking locks eg. see
find_linux_pte()).
The race is as follows:
The pte page is allocated, zeroed, and its struct page gets its spinlock
initialized. The mm-wide ptl is then taken, and then the pte page is inserted
into the pagetables.
At this point, the spinlock is not guaranteed to have ordered the previous
stores to initialize the pte page with the subsequent store to put it in the
page tables. So another Linux page table walker might be walking down (without
any locks, because we have split-leaf-ptls), and find that new pte we've
inserted. It might try to take the spinlock before the store from the other
CPU initializes it. And subsequently it might read a pte_t out before stores
from the other CPU have cleared the memory.
There are also similar races in higher levels of the page tables. They
obviously don't involve the spinlock, but could see uninitialized memory.
Arch code and hardware pagetable walkers that walk the pagetables without
locks could see similar uninitialized memory problems, regardless of whether
split ptes are enabled or not.
I prefer to put the barriers in core code, because that's where the higher
level logic happens, but the page table accessors are per-arch, and open-coding
them everywhere I don't think is an option. I'll put the read-side barriers
in alpha arch code for now (other architectures perform data-dependent loads
in order).
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-14 12:37:36 +08:00
|
|
|
pte_t *ret = (pte_t *) pmd_page_vaddr(*dir)
|
2005-04-17 06:20:36 +08:00
|
|
|
+ ((address >> PAGE_SHIFT) & (PTRS_PER_PAGE - 1));
|
fix SMP data race in pagetable setup vs walking
There is a possible data race in the page table walking code. After the split
ptlock patches, it actually seems to have been introduced to the core code, but
even before that I think it would have impacted some architectures (powerpc
and sparc64, at least, walk the page tables without taking locks eg. see
find_linux_pte()).
The race is as follows:
The pte page is allocated, zeroed, and its struct page gets its spinlock
initialized. The mm-wide ptl is then taken, and then the pte page is inserted
into the pagetables.
At this point, the spinlock is not guaranteed to have ordered the previous
stores to initialize the pte page with the subsequent store to put it in the
page tables. So another Linux page table walker might be walking down (without
any locks, because we have split-leaf-ptls), and find that new pte we've
inserted. It might try to take the spinlock before the store from the other
CPU initializes it. And subsequently it might read a pte_t out before stores
from the other CPU have cleared the memory.
There are also similar races in higher levels of the page tables. They
obviously don't involve the spinlock, but could see uninitialized memory.
Arch code and hardware pagetable walkers that walk the pagetables without
locks could see similar uninitialized memory problems, regardless of whether
split ptes are enabled or not.
I prefer to put the barriers in core code, because that's where the higher
level logic happens, but the page table accessors are per-arch, and open-coding
them everywhere I don't think is an option. I'll put the read-side barriers
in alpha arch code for now (other architectures perform data-dependent loads
in order).
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-14 12:37:36 +08:00
|
|
|
smp_read_barrier_depends(); /* see above */
|
|
|
|
|
return ret;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define pte_offset_map(dir,addr) pte_offset_kernel((dir),(addr))
|
|
|
|
|
#define pte_unmap(pte) do { } while (0)
|
|
|
|
|
|
|
|
|
|
extern pgd_t swapper_pg_dir[1024];
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* The Alpha doesn't have any external MMU info: the kernel page
|
|
|
|
|
* tables contain all the necessary information.
|
|
|
|
|
*/
|
|
|
|
|
extern inline void update_mmu_cache(struct vm_area_struct * vma,
|
MM: Pass a PTE pointer to update_mmu_cache() rather than the PTE itself
On VIVT ARM, when we have multiple shared mappings of the same file
in the same MM, we need to ensure that we have coherency across all
copies. We do this via make_coherent() by making the pages
uncacheable.
This used to work fine, until we allowed highmem with highpte - we
now have a page table which is mapped as required, and is not available
for modification via update_mmu_cache().
Ralf Beache suggested getting rid of the PTE value passed to
update_mmu_cache():
On MIPS update_mmu_cache() calls __update_tlb() which walks pagetables
to construct a pointer to the pte again. Passing a pte_t * is much
more elegant. Maybe we might even replace the pte argument with the
pte_t?
Ben Herrenschmidt would also like the pte pointer for PowerPC:
Passing the ptep in there is exactly what I want. I want that
-instead- of the PTE value, because I have issue on some ppc cases,
for I$/D$ coherency, where set_pte_at() may decide to mask out the
_PAGE_EXEC.
So, pass in the mapped page table pointer into update_mmu_cache(), and
remove the PTE value, updating all implementations and call sites to
suit.
Includes a fix from Stephen Rothwell:
sparc: fix fallout from update_mmu_cache API change
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2009-12-19 00:40:18 +08:00
|
|
|
unsigned long address, pte_t *ptep)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Non-present pages: high 24 bits are offset, next 8 bits type,
|
|
|
|
|
* low 32 bits zero.
|
|
|
|
|
*/
|
|
|
|
|
extern inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
|
|
|
|
|
{ pte_t pte; pte_val(pte) = (type << 32) | (offset << 40); return pte; }
|
|
|
|
|
|
|
|
|
|
#define __swp_type(x) (((x).val >> 32) & 0xff)
|
|
|
|
|
#define __swp_offset(x) ((x).val >> 40)
|
|
|
|
|
#define __swp_entry(type, off) ((swp_entry_t) { pte_val(mk_swap_pte((type), (off))) })
|
|
|
|
|
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
|
|
|
|
|
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
|
|
|
|
|
|
|
|
|
|
#define pte_to_pgoff(pte) (pte_val(pte) >> 32)
|
|
|
|
|
#define pgoff_to_pte(off) ((pte_t) { ((off) << 32) | _PAGE_FILE })
|
|
|
|
|
|
|
|
|
|
#define PTE_FILE_MAX_BITS 32
|
|
|
|
|
|
|
|
|
|
#ifndef CONFIG_DISCONTIGMEM
|
|
|
|
|
#define kern_addr_valid(addr) (1)
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#define pte_ERROR(e) \
|
|
|
|
|
printk("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e))
|
|
|
|
|
#define pmd_ERROR(e) \
|
|
|
|
|
printk("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
|
|
|
|
|
#define pgd_ERROR(e) \
|
|
|
|
|
printk("%s:%d: bad pgd %016lx.\n", __FILE__, __LINE__, pgd_val(e))
|
|
|
|
|
|
|
|
|
|
extern void paging_init(void);
|
|
|
|
|
|
|
|
|
|
#include <asm-generic/pgtable.h>
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* No page table caches to initialise
|
|
|
|
|
*/
|
|
|
|
|
#define pgtable_cache_init() do { } while (0)
|
|
|
|
|
|
|
|
|
|
/* We have our own get_unmapped_area to cope with ADDR_LIMIT_32BIT. */
|
|
|
|
|
#define HAVE_ARCH_UNMAPPED_AREA
|
|
|
|
|
|
|
|
|
|
#endif /* _ALPHA_PGTABLE_H */
|
