mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 08:19:28 +00:00
![Martin Schwidefsky](/assets/img/avatar_default.png)
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>
109 lines
3.2 KiB
C
109 lines
3.2 KiB
C
/*
|
|
* Copyright (C) 2004-2006 Atmel Corporation
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
#ifndef __ASM_AVR32_PAGE_H
|
|
#define __ASM_AVR32_PAGE_H
|
|
|
|
/* PAGE_SHIFT determines the page size */
|
|
#define PAGE_SHIFT 12
|
|
#ifdef __ASSEMBLY__
|
|
#define PAGE_SIZE (1 << PAGE_SHIFT)
|
|
#else
|
|
#define PAGE_SIZE (1UL << PAGE_SHIFT)
|
|
#endif
|
|
#define PAGE_MASK (~(PAGE_SIZE-1))
|
|
#define PTE_MASK PAGE_MASK
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#include <asm/addrspace.h>
|
|
|
|
extern void clear_page(void *to);
|
|
extern void copy_page(void *to, void *from);
|
|
|
|
#define clear_user_page(page, vaddr, pg) clear_page(page)
|
|
#define copy_user_page(to, from, vaddr, pg) copy_page(to, from)
|
|
|
|
/*
|
|
* These are used to make use of C type-checking..
|
|
*/
|
|
typedef struct { unsigned long pte; } pte_t;
|
|
typedef struct { unsigned long pgd; } pgd_t;
|
|
typedef struct { unsigned long pgprot; } pgprot_t;
|
|
typedef struct page *pgtable_t;
|
|
|
|
#define pte_val(x) ((x).pte)
|
|
#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) })
|
|
|
|
/* FIXME: These should be removed soon */
|
|
extern unsigned long memory_start, memory_end;
|
|
|
|
/* Pure 2^n version of get_order */
|
|
static inline int get_order(unsigned long size)
|
|
{
|
|
unsigned lz;
|
|
|
|
size = (size - 1) >> PAGE_SHIFT;
|
|
asm("clz %0, %1" : "=r"(lz) : "r"(size));
|
|
return 32 - lz;
|
|
}
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
/* Align the pointer to the (next) page boundary */
|
|
#define PAGE_ALIGN(addr) (((addr) + PAGE_SIZE - 1) & PAGE_MASK)
|
|
|
|
/*
|
|
* The hardware maps the virtual addresses 0x80000000 -> 0x9fffffff
|
|
* permanently to the physical addresses 0x00000000 -> 0x1fffffff when
|
|
* segmentation is enabled. We want to make use of this in order to
|
|
* minimize TLB pressure.
|
|
*/
|
|
#define PAGE_OFFSET (0x80000000UL)
|
|
|
|
/*
|
|
* ALSA uses virt_to_page() on DMA pages, which I'm not entirely sure
|
|
* is a good idea. Anyway, we can't simply subtract PAGE_OFFSET here
|
|
* in that case, so we'll have to mask out the three most significant
|
|
* bits of the address instead...
|
|
*
|
|
* What's the difference between __pa() and virt_to_phys() anyway?
|
|
*/
|
|
#define __pa(x) PHYSADDR(x)
|
|
#define __va(x) ((void *)(P1SEGADDR(x)))
|
|
|
|
#define MAP_NR(addr) (((unsigned long)(addr) - PAGE_OFFSET) >> PAGE_SHIFT)
|
|
|
|
#define phys_to_page(phys) (pfn_to_page(phys >> PAGE_SHIFT))
|
|
#define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT)
|
|
|
|
#ifndef CONFIG_NEED_MULTIPLE_NODES
|
|
|
|
#define PHYS_PFN_OFFSET (CONFIG_PHYS_OFFSET >> PAGE_SHIFT)
|
|
|
|
#define pfn_to_page(pfn) (mem_map + ((pfn) - PHYS_PFN_OFFSET))
|
|
#define page_to_pfn(page) ((unsigned long)((page) - mem_map) + PHYS_PFN_OFFSET)
|
|
#define pfn_valid(pfn) ((pfn) >= PHYS_PFN_OFFSET && (pfn) < (PHYS_PFN_OFFSET + max_mapnr))
|
|
#endif /* CONFIG_NEED_MULTIPLE_NODES */
|
|
|
|
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
|
|
#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
|
|
|
|
#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \
|
|
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
|
|
|
|
/*
|
|
* Memory above this physical address will be considered highmem.
|
|
*/
|
|
#define HIGHMEM_START 0x20000000UL
|
|
|
|
#endif /* __ASM_AVR32_PAGE_H */
|