linux_dsm_epyc7002/arch/arm/include/asm/pgtable.h

336 lines
11 KiB
C
Raw Normal View History

/*
* arch/arm/include/asm/pgtable.h
*
* Copyright (C) 1995-2002 Russell King
*
* 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 _ASMARM_PGTABLE_H
#define _ASMARM_PGTABLE_H
#include <linux/const.h>
#include <asm/proc-fns.h>
#ifndef CONFIG_MMU
#include <asm-generic/4level-fixup.h>
#include <asm/pgtable-nommu.h>
#else
#include <asm-generic/pgtable-nopud.h>
#include <asm/memory.h>
#include <asm/pgtable-hwdef.h>
#include <asm/tlbflush.h>
#ifdef CONFIG_ARM_LPAE
#include <asm/pgtable-3level.h>
#else
#include <asm/pgtable-2level.h>
#endif
/*
* Just any arbitrary offset to the start of the vmalloc VM area: the
* current 8MB value just means that there will be a 8MB "hole" after the
* physical memory until the kernel virtual memory starts. That means that
* any out-of-bounds memory accesses will hopefully be caught.
* The vmalloc() routines leaves a hole of 4kB between each vmalloced
* area for the same reason. ;)
*/
#define VMALLOC_OFFSET (8*1024*1024)
#define VMALLOC_START (((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
#define VMALLOC_END 0xff000000UL
#define LIBRARY_TEXT_START 0x0c000000
#ifndef __ASSEMBLY__
extern void __pte_error(const char *file, int line, pte_t);
extern void __pmd_error(const char *file, int line, pmd_t);
extern void __pgd_error(const char *file, int line, pgd_t);
#define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte)
#define pmd_ERROR(pmd) __pmd_error(__FILE__, __LINE__, pmd)
#define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd)
/*
* This is the lowest virtual address we can permit any user space
* mapping to be mapped at. This is particularly important for
* non-high vector CPUs.
*/
#define FIRST_USER_ADDRESS (PAGE_SIZE * 2)
/*
* Use TASK_SIZE as the ceiling argument for free_pgtables() and
* free_pgd_range() to avoid freeing the modules pmd when LPAE is enabled (pmd
* page shared between user and kernel).
*/
#ifdef CONFIG_ARM_LPAE
#define USER_PGTABLES_CEILING TASK_SIZE
#endif
/*
* The pgprot_* and protection_map entries will be fixed up in runtime
* to include the cachable and bufferable bits based on memory policy,
* as well as any architecture dependent bits like global/ASID and SMP
* shared mapping bits.
*/
#define _L_PTE_DEFAULT L_PTE_PRESENT | L_PTE_YOUNG
extern pgprot_t pgprot_user;
extern pgprot_t pgprot_kernel;
extern pgprot_t pgprot_hyp_device;
extern pgprot_t pgprot_s2;
extern pgprot_t pgprot_s2_device;
#define _MOD_PROT(p, b) __pgprot(pgprot_val(p) | (b))
#define PAGE_NONE _MOD_PROT(pgprot_user, L_PTE_XN | L_PTE_RDONLY | L_PTE_NONE)
#define PAGE_SHARED _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_XN)
#define PAGE_SHARED_EXEC _MOD_PROT(pgprot_user, L_PTE_USER)
#define PAGE_COPY _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
#define PAGE_COPY_EXEC _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY)
#define PAGE_READONLY _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
#define PAGE_READONLY_EXEC _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY)
#define PAGE_KERNEL _MOD_PROT(pgprot_kernel, L_PTE_XN)
#define PAGE_KERNEL_EXEC pgprot_kernel
#define PAGE_HYP _MOD_PROT(pgprot_kernel, L_PTE_HYP)
#define PAGE_HYP_DEVICE _MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
#define PAGE_S2 _MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_S2_RDWR)
#define __PAGE_NONE __pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE)
#define __PAGE_SHARED __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)
#define __PAGE_SHARED_EXEC __pgprot(_L_PTE_DEFAULT | L_PTE_USER)
#define __PAGE_COPY __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
#define __PAGE_COPY_EXEC __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY)
#define __PAGE_READONLY __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
#define __PAGE_READONLY_EXEC __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY)
#define __pgprot_modify(prot,mask,bits) \
__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
#define pgprot_noncached(prot) \
__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
#define pgprot_writecombine(prot) \
__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE)
#define pgprot_stronglyordered(prot) \
__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
#define pgprot_dmacoherent(prot) \
__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE | L_PTE_XN)
#define __HAVE_PHYS_MEM_ACCESS_PROT
struct file;
extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot);
#else
#define pgprot_dmacoherent(prot) \
__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED | L_PTE_XN)
#endif
#endif /* __ASSEMBLY__ */
/*
* The table below defines the page protection levels that we insert into our
* Linux page table version. These get translated into the best that the
* architecture can perform. Note that on most ARM hardware:
* 1) We cannot do execute protection
* 2) If we could do execute protection, then read is implied
* 3) write implies read permissions
*/
#define __P000 __PAGE_NONE
#define __P001 __PAGE_READONLY
#define __P010 __PAGE_COPY
#define __P011 __PAGE_COPY
#define __P100 __PAGE_READONLY_EXEC
#define __P101 __PAGE_READONLY_EXEC
#define __P110 __PAGE_COPY_EXEC
#define __P111 __PAGE_COPY_EXEC
#define __S000 __PAGE_NONE
#define __S001 __PAGE_READONLY
#define __S010 __PAGE_SHARED
#define __S011 __PAGE_SHARED
#define __S100 __PAGE_READONLY_EXEC
#define __S101 __PAGE_READONLY_EXEC
#define __S110 __PAGE_SHARED_EXEC
#define __S111 __PAGE_SHARED_EXEC
#ifndef __ASSEMBLY__
/*
* ZERO_PAGE is a global shared page that is always zero: used
* for zero-mapped memory areas etc..
*/
extern struct page *empty_zero_page;
#define ZERO_PAGE(vaddr) (empty_zero_page)
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
/* to find an entry in a page-table-directory */
#define pgd_index(addr) ((addr) >> PGDIR_SHIFT)
#define pgd_offset(mm, addr) ((mm)->pgd + pgd_index(addr))
/* to find an entry in a kernel page-table-directory */
#define pgd_offset_k(addr) pgd_offset(&init_mm, addr)
#define pmd_none(pmd) (!pmd_val(pmd))
#define pmd_present(pmd) (pmd_val(pmd))
static inline pte_t *pmd_page_vaddr(pmd_t pmd)
{
return __va(pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK);
}
#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
#ifndef CONFIG_HIGHPTE
#define __pte_map(pmd) pmd_page_vaddr(*(pmd))
#define __pte_unmap(pte) do { } while (0)
#else
#define __pte_map(pmd) (pte_t *)kmap_atomic(pmd_page(*(pmd)))
#define __pte_unmap(pte) kunmap_atomic(pte)
#endif
#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
#define pte_offset_kernel(pmd,addr) (pmd_page_vaddr(*(pmd)) + pte_index(addr))
#define pte_offset_map(pmd,addr) (__pte_map(pmd) + pte_index(addr))
#define pte_unmap(pte) __pte_unmap(pte)
#define pte_pfn(pte) ((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT)
#define pfn_pte(pfn,prot) __pte(__pfn_to_phys(pfn) | pgprot_val(prot))
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
#define mk_pte(page,prot) pfn_pte(page_to_pfn(page), prot)
#define pte_clear(mm,addr,ptep) set_pte_ext(ptep, __pte(0), 0)
#define pte_none(pte) (!pte_val(pte))
#define pte_present(pte) (pte_val(pte) & L_PTE_PRESENT)
#define pte_valid(pte) (pte_val(pte) & L_PTE_VALID)
#define pte_accessible(mm, pte) (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))
#define pte_write(pte) (!(pte_val(pte) & L_PTE_RDONLY))
#define pte_dirty(pte) (pte_val(pte) & L_PTE_DIRTY)
#define pte_young(pte) (pte_val(pte) & L_PTE_YOUNG)
#define pte_exec(pte) (!(pte_val(pte) & L_PTE_XN))
#define pte_special(pte) (0)
#define pte_valid_user(pte) \
(pte_valid(pte) && (pte_val(pte) & L_PTE_USER) && pte_young(pte))
#if __LINUX_ARM_ARCH__ < 6
static inline void __sync_icache_dcache(pte_t pteval)
{
}
#else
extern void __sync_icache_dcache(pte_t pteval);
#endif
static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval)
{
unsigned long ext = 0;
if (addr < TASK_SIZE && pte_valid_user(pteval)) {
__sync_icache_dcache(pteval);
ext |= PTE_EXT_NG;
}
set_pte_ext(ptep, pteval, ext);
}
#define PTE_BIT_FUNC(fn,op) \
static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
PTE_BIT_FUNC(wrprotect, |= L_PTE_RDONLY);
PTE_BIT_FUNC(mkwrite, &= ~L_PTE_RDONLY);
PTE_BIT_FUNC(mkclean, &= ~L_PTE_DIRTY);
PTE_BIT_FUNC(mkdirty, |= L_PTE_DIRTY);
PTE_BIT_FUNC(mkold, &= ~L_PTE_YOUNG);
PTE_BIT_FUNC(mkyoung, |= L_PTE_YOUNG);
PTE_BIT_FUNC(mkexec, &= ~L_PTE_XN);
PTE_BIT_FUNC(mknexec, |= L_PTE_XN);
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 16:13:00 +07:00
static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER |
L_PTE_NONE | L_PTE_VALID;
pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
return pte;
}
/*
* Encode and decode a swap entry. Swap entries are stored in the Linux
* page tables as follows:
*
* 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
* 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
* <--------------- offset ----------------------> < type -> 0 0 0
*
* This gives us up to 31 swap files and 64GB per swap file. Note that
* the offset field is always non-zero.
*/
#define __SWP_TYPE_SHIFT 3
#define __SWP_TYPE_BITS 5
#define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1)
#define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
#define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
#define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT)
#define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(swp) ((pte_t) { (swp).val })
/*
* It is an error for the kernel to have more swap files than we can
* encode in the PTEs. This ensures that we know when MAX_SWAPFILES
* is increased beyond what we presently support.
*/
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
/*
* Encode and decode a file entry. File entries are stored in the Linux
* page tables as follows:
*
* 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
* 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
* <----------------------- offset ------------------------> 1 0 0
*/
#define pte_file(pte) (pte_val(pte) & L_PTE_FILE)
#define pte_to_pgoff(x) (pte_val(x) >> 3)
#define pgoff_to_pte(x) __pte(((x) << 3) | L_PTE_FILE)
#define PTE_FILE_MAX_BITS 29
/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
/* FIXME: this is not correct */
#define kern_addr_valid(addr) (1)
#include <asm-generic/pgtable.h>
/*
* We provide our own arch_get_unmapped_area to cope with VIPT caches.
*/
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
#define pgtable_cache_init() do { } while (0)
#endif /* !__ASSEMBLY__ */
#endif /* CONFIG_MMU */
#endif /* _ASMARM_PGTABLE_H */