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>
88 lines
2.3 KiB
C
88 lines
2.3 KiB
C
#ifndef _X86_64_PAGE_H
|
|
#define _X86_64_PAGE_H
|
|
|
|
#define PAGETABLE_LEVELS 4
|
|
|
|
#define THREAD_ORDER 1
|
|
#define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER)
|
|
#define CURRENT_MASK (~(THREAD_SIZE-1))
|
|
|
|
#define EXCEPTION_STACK_ORDER 0
|
|
#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
|
|
|
|
#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
|
|
#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
|
|
|
|
#define IRQSTACK_ORDER 2
|
|
#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER)
|
|
|
|
#define STACKFAULT_STACK 1
|
|
#define DOUBLEFAULT_STACK 2
|
|
#define NMI_STACK 3
|
|
#define DEBUG_STACK 4
|
|
#define MCE_STACK 5
|
|
#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */
|
|
|
|
#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT)
|
|
#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1))
|
|
|
|
#define __PAGE_OFFSET _AC(0xffff810000000000, UL)
|
|
|
|
#define __PHYSICAL_START CONFIG_PHYSICAL_START
|
|
#define __KERNEL_ALIGN 0x200000
|
|
|
|
/*
|
|
* Make sure kernel is aligned to 2MB address. Catching it at compile
|
|
* time is better. Change your config file and compile the kernel
|
|
* for a 2MB aligned address (CONFIG_PHYSICAL_START)
|
|
*/
|
|
#if (CONFIG_PHYSICAL_START % __KERNEL_ALIGN) != 0
|
|
#error "CONFIG_PHYSICAL_START must be a multiple of 2MB"
|
|
#endif
|
|
|
|
#define __START_KERNEL (__START_KERNEL_map + __PHYSICAL_START)
|
|
#define __START_KERNEL_map _AC(0xffffffff80000000, UL)
|
|
|
|
/* See Documentation/x86_64/mm.txt for a description of the memory map. */
|
|
#define __PHYSICAL_MASK_SHIFT 46
|
|
#define __VIRTUAL_MASK_SHIFT 48
|
|
|
|
#define KERNEL_TEXT_SIZE (40*1024*1024)
|
|
#define KERNEL_TEXT_START _AC(0xffffffff80000000, UL)
|
|
|
|
#ifndef __ASSEMBLY__
|
|
void clear_page(void *page);
|
|
void copy_page(void *to, void *from);
|
|
|
|
extern unsigned long end_pfn;
|
|
extern unsigned long end_pfn_map;
|
|
extern unsigned long phys_base;
|
|
|
|
extern unsigned long __phys_addr(unsigned long);
|
|
#define __phys_reloc_hide(x) (x)
|
|
|
|
/*
|
|
* These are used to make use of C type-checking..
|
|
*/
|
|
typedef unsigned long pteval_t;
|
|
typedef unsigned long pmdval_t;
|
|
typedef unsigned long pudval_t;
|
|
typedef unsigned long pgdval_t;
|
|
typedef unsigned long pgprotval_t;
|
|
typedef unsigned long phys_addr_t;
|
|
|
|
typedef struct page *pgtable_t;
|
|
|
|
typedef struct { pteval_t pte; } pte_t;
|
|
|
|
#define vmemmap ((struct page *)VMEMMAP_START)
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
#ifdef CONFIG_FLATMEM
|
|
#define pfn_valid(pfn) ((pfn) < end_pfn)
|
|
#endif
|
|
|
|
|
|
#endif /* _X86_64_PAGE_H */
|