mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-17 01:37:59 +07:00
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>
192 lines
5.1 KiB
C
192 lines
5.1 KiB
C
/*
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
* for more details.
|
|
*
|
|
* Copyright (C) 1994 - 1999, 2000, 03 Ralf Baechle
|
|
* Copyright (C) 1999, 2000 Silicon Graphics, Inc.
|
|
*/
|
|
#ifndef _ASM_PAGE_H
|
|
#define _ASM_PAGE_H
|
|
|
|
#include <spaces.h>
|
|
|
|
/*
|
|
* PAGE_SHIFT determines the page size
|
|
*/
|
|
#ifdef CONFIG_PAGE_SIZE_4KB
|
|
#define PAGE_SHIFT 12
|
|
#endif
|
|
#ifdef CONFIG_PAGE_SIZE_8KB
|
|
#define PAGE_SHIFT 13
|
|
#endif
|
|
#ifdef CONFIG_PAGE_SIZE_16KB
|
|
#define PAGE_SHIFT 14
|
|
#endif
|
|
#ifdef CONFIG_PAGE_SIZE_64KB
|
|
#define PAGE_SHIFT 16
|
|
#endif
|
|
#define PAGE_SIZE (1UL << PAGE_SHIFT)
|
|
#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1))
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#include <linux/pfn.h>
|
|
#include <asm/io.h>
|
|
|
|
/*
|
|
* It's normally defined only for FLATMEM config but it's
|
|
* used in our early mem init code for all memory models.
|
|
* So always define it.
|
|
*/
|
|
#define ARCH_PFN_OFFSET PFN_UP(PHYS_OFFSET)
|
|
|
|
extern void clear_page(void * page);
|
|
extern void copy_page(void * to, void * from);
|
|
|
|
extern unsigned long shm_align_mask;
|
|
|
|
static inline unsigned long pages_do_alias(unsigned long addr1,
|
|
unsigned long addr2)
|
|
{
|
|
return (addr1 ^ addr2) & shm_align_mask;
|
|
}
|
|
|
|
struct page;
|
|
|
|
static inline void clear_user_page(void *addr, unsigned long vaddr,
|
|
struct page *page)
|
|
{
|
|
extern void (*flush_data_cache_page)(unsigned long addr);
|
|
|
|
clear_page(addr);
|
|
if (pages_do_alias((unsigned long) addr, vaddr & PAGE_MASK))
|
|
flush_data_cache_page((unsigned long)addr);
|
|
}
|
|
|
|
extern void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
|
|
struct page *to);
|
|
struct vm_area_struct;
|
|
extern void copy_user_highpage(struct page *to, struct page *from,
|
|
unsigned long vaddr, struct vm_area_struct *vma);
|
|
|
|
#define __HAVE_ARCH_COPY_USER_HIGHPAGE
|
|
|
|
/*
|
|
* These are used to make use of C type-checking..
|
|
*/
|
|
#ifdef CONFIG_64BIT_PHYS_ADDR
|
|
#ifdef CONFIG_CPU_MIPS32
|
|
typedef struct { unsigned long pte_low, pte_high; } pte_t;
|
|
#define pte_val(x) ((x).pte_low | ((unsigned long long)(x).pte_high << 32))
|
|
#define __pte(x) ({ pte_t __pte = {(x), ((unsigned long long)(x)) >> 32}; __pte; })
|
|
#else
|
|
typedef struct { unsigned long long pte; } pte_t;
|
|
#define pte_val(x) ((x).pte)
|
|
#define __pte(x) ((pte_t) { (x) } )
|
|
#endif
|
|
#else
|
|
typedef struct { unsigned long pte; } pte_t;
|
|
#define pte_val(x) ((x).pte)
|
|
#define __pte(x) ((pte_t) { (x) } )
|
|
#endif
|
|
typedef struct page *pgtable_t;
|
|
|
|
/*
|
|
* For 3-level pagetables we defines these ourselves, for 2-level the
|
|
* definitions are supplied by <asm-generic/pgtable-nopmd.h>.
|
|
*/
|
|
#ifdef CONFIG_64BIT
|
|
|
|
typedef struct { unsigned long pmd; } pmd_t;
|
|
#define pmd_val(x) ((x).pmd)
|
|
#define __pmd(x) ((pmd_t) { (x) } )
|
|
|
|
#endif
|
|
|
|
/*
|
|
* Right now we don't support 4-level pagetables, so all pud-related
|
|
* definitions come from <asm-generic/pgtable-nopud.h>.
|
|
*/
|
|
|
|
/*
|
|
* Finall the top of the hierarchy, the pgd
|
|
*/
|
|
typedef struct { unsigned long pgd; } pgd_t;
|
|
#define pgd_val(x) ((x).pgd)
|
|
#define __pgd(x) ((pgd_t) { (x) } )
|
|
|
|
/*
|
|
* Manipulate page protection bits
|
|
*/
|
|
typedef struct { unsigned long pgprot; } pgprot_t;
|
|
#define pgprot_val(x) ((x).pgprot)
|
|
#define __pgprot(x) ((pgprot_t) { (x) } )
|
|
|
|
/*
|
|
* On R4000-style MMUs where a TLB entry is mapping a adjacent even / odd
|
|
* pair of pages we only have a single global bit per pair of pages. When
|
|
* writing to the TLB make sure we always have the bit set for both pages
|
|
* or none. This macro is used to access the `buddy' of the pte we're just
|
|
* working on.
|
|
*/
|
|
#define ptep_buddy(x) ((pte_t *)((unsigned long)(x) ^ sizeof(pte_t)))
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
/* to align the pointer to the (next) page boundary */
|
|
#define PAGE_ALIGN(addr) (((addr) + PAGE_SIZE - 1) & PAGE_MASK)
|
|
|
|
/*
|
|
* __pa()/__va() should be used only during mem init.
|
|
*/
|
|
#ifdef CONFIG_64BIT
|
|
#define __pa(x) \
|
|
({ \
|
|
unsigned long __x = (unsigned long)(x); \
|
|
__x < CKSEG0 ? XPHYSADDR(__x) : CPHYSADDR(__x); \
|
|
})
|
|
#else
|
|
#define __pa(x) \
|
|
((unsigned long)(x) - PAGE_OFFSET + PHYS_OFFSET)
|
|
#endif
|
|
#define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET - PHYS_OFFSET))
|
|
#define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0))
|
|
|
|
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
|
|
|
|
#ifdef CONFIG_FLATMEM
|
|
|
|
#define pfn_valid(pfn) ((pfn) >= ARCH_PFN_OFFSET && (pfn) < max_mapnr)
|
|
|
|
#elif defined(CONFIG_SPARSEMEM)
|
|
|
|
/* pfn_valid is defined in linux/mmzone.h */
|
|
|
|
#elif defined(CONFIG_NEED_MULTIPLE_NODES)
|
|
|
|
#define pfn_valid(pfn) \
|
|
({ \
|
|
unsigned long __pfn = (pfn); \
|
|
int __n = pfn_to_nid(__pfn); \
|
|
((__n >= 0) ? (__pfn < NODE_DATA(__n)->node_start_pfn + \
|
|
NODE_DATA(__n)->node_spanned_pages) \
|
|
: 0); \
|
|
})
|
|
|
|
#endif
|
|
|
|
#define virt_to_page(kaddr) pfn_to_page(PFN_DOWN(virt_to_phys(kaddr)))
|
|
#define virt_addr_valid(kaddr) pfn_valid(PFN_DOWN(virt_to_phys(kaddr)))
|
|
|
|
#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \
|
|
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
|
|
|
|
#define UNCAC_ADDR(addr) ((addr) - PAGE_OFFSET + UNCAC_BASE)
|
|
#define CAC_ADDR(addr) ((addr) - UNCAC_BASE + PAGE_OFFSET)
|
|
|
|
#include <asm-generic/memory_model.h>
|
|
#include <asm-generic/page.h>
|
|
|
|
#endif /* _ASM_PAGE_H */
|