mirror of
https://github.com/torvalds/linux.git
synced 2024-12-25 20:32:22 +00:00
2f569afd9c
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>
199 lines
5.3 KiB
C
199 lines
5.3 KiB
C
#ifndef _ASM_POWERPC_PAGE_H
|
|
#define _ASM_POWERPC_PAGE_H
|
|
|
|
/*
|
|
* Copyright (C) 2001,2005 IBM Corporation.
|
|
*
|
|
* 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 <asm/asm-compat.h>
|
|
#include <asm/kdump.h>
|
|
|
|
/*
|
|
* On PPC32 page size is 4K. For PPC64 we support either 4K or 64K software
|
|
* page size. When using 64K pages however, whether we are really supporting
|
|
* 64K pages in HW or not is irrelevant to those definitions.
|
|
*/
|
|
#ifdef CONFIG_PPC_64K_PAGES
|
|
#define PAGE_SHIFT 16
|
|
#else
|
|
#define PAGE_SHIFT 12
|
|
#endif
|
|
|
|
#define PAGE_SIZE (ASM_CONST(1) << PAGE_SHIFT)
|
|
|
|
/* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
|
|
#define __HAVE_ARCH_GATE_AREA 1
|
|
|
|
/*
|
|
* Subtle: (1 << PAGE_SHIFT) is an int, not an unsigned long. So if we
|
|
* assign PAGE_MASK to a larger type it gets extended the way we want
|
|
* (i.e. with 1s in the high bits)
|
|
*/
|
|
#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1))
|
|
|
|
/*
|
|
* KERNELBASE is the virtual address of the start of the kernel, it's often
|
|
* the same as PAGE_OFFSET, but _might not be_.
|
|
*
|
|
* The kdump dump kernel is one example where KERNELBASE != PAGE_OFFSET.
|
|
*
|
|
* To get a physical address from a virtual one you subtract PAGE_OFFSET,
|
|
* _not_ KERNELBASE.
|
|
*
|
|
* If you want to know something's offset from the start of the kernel you
|
|
* should subtract KERNELBASE.
|
|
*
|
|
* If you want to test if something's a kernel address, use is_kernel_addr().
|
|
*/
|
|
|
|
#define PAGE_OFFSET ASM_CONST(CONFIG_KERNEL_START)
|
|
#define KERNELBASE (PAGE_OFFSET + PHYSICAL_START)
|
|
|
|
#ifdef CONFIG_FLATMEM
|
|
#define pfn_valid(pfn) ((pfn) < max_mapnr)
|
|
#endif
|
|
|
|
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
|
|
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
|
|
#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
|
|
|
|
#define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET))
|
|
#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET)
|
|
|
|
/*
|
|
* Unfortunately the PLT is in the BSS in the PPC32 ELF ABI,
|
|
* and needs to be executable. This means the whole heap ends
|
|
* up being executable.
|
|
*/
|
|
#define VM_DATA_DEFAULT_FLAGS32 (VM_READ | VM_WRITE | VM_EXEC | \
|
|
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
|
|
|
|
#define VM_DATA_DEFAULT_FLAGS64 (VM_READ | VM_WRITE | \
|
|
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
|
|
|
|
#ifdef __powerpc64__
|
|
#include <asm/page_64.h>
|
|
#else
|
|
#include <asm/page_32.h>
|
|
#endif
|
|
|
|
/* align addr on a size boundary - adjust address up/down if needed */
|
|
#define _ALIGN_UP(addr,size) (((addr)+((size)-1))&(~((size)-1)))
|
|
#define _ALIGN_DOWN(addr,size) ((addr)&(~((size)-1)))
|
|
|
|
/* align addr on a size boundary - adjust address up if needed */
|
|
#define _ALIGN(addr,size) _ALIGN_UP(addr,size)
|
|
|
|
/* to align the pointer to the (next) page boundary */
|
|
#define PAGE_ALIGN(addr) _ALIGN(addr, PAGE_SIZE)
|
|
|
|
/*
|
|
* Don't compare things with KERNELBASE or PAGE_OFFSET to test for
|
|
* "kernelness", use is_kernel_addr() - it should do what you want.
|
|
*/
|
|
#define is_kernel_addr(x) ((x) >= PAGE_OFFSET)
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#undef STRICT_MM_TYPECHECKS
|
|
|
|
#ifdef STRICT_MM_TYPECHECKS
|
|
/* These are used to make use of C type-checking. */
|
|
|
|
/* PTE level */
|
|
typedef struct { pte_basic_t pte; } pte_t;
|
|
#define pte_val(x) ((x).pte)
|
|
#define __pte(x) ((pte_t) { (x) })
|
|
|
|
/* 64k pages additionally define a bigger "real PTE" type that gathers
|
|
* the "second half" part of the PTE for pseudo 64k pages
|
|
*/
|
|
#ifdef CONFIG_PPC_64K_PAGES
|
|
typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
|
|
#else
|
|
typedef struct { pte_t pte; } real_pte_t;
|
|
#endif
|
|
|
|
/* PMD level */
|
|
#ifdef CONFIG_PPC64
|
|
typedef struct { unsigned long pmd; } pmd_t;
|
|
#define pmd_val(x) ((x).pmd)
|
|
#define __pmd(x) ((pmd_t) { (x) })
|
|
|
|
/* PUD level exusts only on 4k pages */
|
|
#ifndef CONFIG_PPC_64K_PAGES
|
|
typedef struct { unsigned long pud; } pud_t;
|
|
#define pud_val(x) ((x).pud)
|
|
#define __pud(x) ((pud_t) { (x) })
|
|
#endif /* !CONFIG_PPC_64K_PAGES */
|
|
#endif /* CONFIG_PPC64 */
|
|
|
|
/* PGD level */
|
|
typedef struct { unsigned long pgd; } pgd_t;
|
|
#define pgd_val(x) ((x).pgd)
|
|
#define __pgd(x) ((pgd_t) { (x) })
|
|
|
|
/* Page protection bits */
|
|
typedef struct { unsigned long pgprot; } pgprot_t;
|
|
#define pgprot_val(x) ((x).pgprot)
|
|
#define __pgprot(x) ((pgprot_t) { (x) })
|
|
|
|
#else
|
|
|
|
/*
|
|
* .. while these make it easier on the compiler
|
|
*/
|
|
|
|
typedef pte_basic_t pte_t;
|
|
#define pte_val(x) (x)
|
|
#define __pte(x) (x)
|
|
|
|
#ifdef CONFIG_PPC_64K_PAGES
|
|
typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
|
|
#else
|
|
typedef unsigned long real_pte_t;
|
|
#endif
|
|
|
|
|
|
#ifdef CONFIG_PPC64
|
|
typedef unsigned long pmd_t;
|
|
#define pmd_val(x) (x)
|
|
#define __pmd(x) (x)
|
|
|
|
#ifndef CONFIG_PPC_64K_PAGES
|
|
typedef unsigned long pud_t;
|
|
#define pud_val(x) (x)
|
|
#define __pud(x) (x)
|
|
#endif /* !CONFIG_PPC_64K_PAGES */
|
|
#endif /* CONFIG_PPC64 */
|
|
|
|
typedef unsigned long pgd_t;
|
|
#define pgd_val(x) (x)
|
|
#define pgprot_val(x) (x)
|
|
|
|
typedef unsigned long pgprot_t;
|
|
#define __pgd(x) (x)
|
|
#define __pgprot(x) (x)
|
|
|
|
#endif
|
|
|
|
struct page;
|
|
extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
|
|
extern void copy_user_page(void *to, void *from, unsigned long vaddr,
|
|
struct page *p);
|
|
extern int page_is_ram(unsigned long pfn);
|
|
|
|
struct vm_area_struct;
|
|
|
|
typedef struct page *pgtable_t;
|
|
|
|
#include <asm-generic/memory_model.h>
|
|
#endif /* __ASSEMBLY__ */
|
|
|
|
#endif /* _ASM_POWERPC_PAGE_H */
|