bianbu-linux-6.6-fh/arch/arm/include/asm/pgtable.h
Linus Torvalds e2ca6ba6ba MM patches for 6.2-rc1.
- More userfaultfs work from Peter Xu.
 
 - Several convert-to-folios series from Sidhartha Kumar and Huang Ying.
 
 - Some filemap cleanups from Vishal Moola.
 
 - David Hildenbrand added the ability to selftest anon memory COW handling.
 
 - Some cpuset simplifications from Liu Shixin.
 
 - Addition of vmalloc tracing support by Uladzislau Rezki.
 
 - Some pagecache folioifications and simplifications from Matthew Wilcox.
 
 - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use it.
 
 - Miguel Ojeda contributed some cleanups for our use of the
   __no_sanitize_thread__ gcc keyword.  This series shold have been in the
   non-MM tree, my bad.
 
 - Naoya Horiguchi improved the interaction between memory poisoning and
   memory section removal for huge pages.
 
 - DAMON cleanups and tuneups from SeongJae Park
 
 - Tony Luck fixed the handling of COW faults against poisoned pages.
 
 - Peter Xu utilized the PTE marker code for handling swapin errors.
 
 - Hugh Dickins reworked compound page mapcount handling, simplifying it
   and making it more efficient.
 
 - Removal of the autonuma savedwrite infrastructure from Nadav Amit and
   David Hildenbrand.
 
 - zram support for multiple compression streams from Sergey Senozhatsky.
 
 - David Hildenbrand reworked the GUP code's R/O long-term pinning so
   that drivers no longer need to use the FOLL_FORCE workaround which
   didn't work very well anyway.
 
 - Mel Gorman altered the page allocator so that local IRQs can remnain
   enabled during per-cpu page allocations.
 
 - Vishal Moola removed the try_to_release_page() wrapper.
 
 - Stefan Roesch added some per-BDI sysfs tunables which are used to
   prevent network block devices from dirtying excessive amounts of
   pagecache.
 
 - David Hildenbrand did some cleanup and repair work on KSM COW
   breaking.
 
 - Nhat Pham and Johannes Weiner have implemented writeback in zswap's
   zsmalloc backend.
 
 - Brian Foster has fixed a longstanding corner-case oddity in
   file[map]_write_and_wait_range().
 
 - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang
   Chen.
 
 - Shiyang Ruan has done some work on fsdax, to make its reflink mode
   work better under xfstests.  Better, but still not perfect.
 
 - Christoph Hellwig has removed the .writepage() method from several
   filesystems.  They only need .writepages().
 
 - Yosry Ahmed wrote a series which fixes the memcg reclaim target
   beancounting.
 
 - David Hildenbrand has fixed some of our MM selftests for 32-bit
   machines.
 
 - Many singleton patches, as usual.
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCY5j6ZwAKCRDdBJ7gKXxA
 jkDYAP9qNeVqp9iuHjZNTqzMXkfmJPsw2kmy2P+VdzYVuQRcJgEAgoV9d7oMq4ml
 CodAgiA51qwzId3GRytIo/tfWZSezgA=
 =d19R
 -----END PGP SIGNATURE-----

Merge tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - More userfaultfs work from Peter Xu

 - Several convert-to-folios series from Sidhartha Kumar and Huang Ying

 - Some filemap cleanups from Vishal Moola

 - David Hildenbrand added the ability to selftest anon memory COW
   handling

 - Some cpuset simplifications from Liu Shixin

 - Addition of vmalloc tracing support by Uladzislau Rezki

 - Some pagecache folioifications and simplifications from Matthew
   Wilcox

 - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use
   it

 - Miguel Ojeda contributed some cleanups for our use of the
   __no_sanitize_thread__ gcc keyword.

   This series should have been in the non-MM tree, my bad

 - Naoya Horiguchi improved the interaction between memory poisoning and
   memory section removal for huge pages

 - DAMON cleanups and tuneups from SeongJae Park

 - Tony Luck fixed the handling of COW faults against poisoned pages

 - Peter Xu utilized the PTE marker code for handling swapin errors

 - Hugh Dickins reworked compound page mapcount handling, simplifying it
   and making it more efficient

 - Removal of the autonuma savedwrite infrastructure from Nadav Amit and
   David Hildenbrand

 - zram support for multiple compression streams from Sergey Senozhatsky

 - David Hildenbrand reworked the GUP code's R/O long-term pinning so
   that drivers no longer need to use the FOLL_FORCE workaround which
   didn't work very well anyway

 - Mel Gorman altered the page allocator so that local IRQs can remnain
   enabled during per-cpu page allocations

 - Vishal Moola removed the try_to_release_page() wrapper

 - Stefan Roesch added some per-BDI sysfs tunables which are used to
   prevent network block devices from dirtying excessive amounts of
   pagecache

 - David Hildenbrand did some cleanup and repair work on KSM COW
   breaking

 - Nhat Pham and Johannes Weiner have implemented writeback in zswap's
   zsmalloc backend

 - Brian Foster has fixed a longstanding corner-case oddity in
   file[map]_write_and_wait_range()

 - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang
   Chen

 - Shiyang Ruan has done some work on fsdax, to make its reflink mode
   work better under xfstests. Better, but still not perfect

 - Christoph Hellwig has removed the .writepage() method from several
   filesystems. They only need .writepages()

 - Yosry Ahmed wrote a series which fixes the memcg reclaim target
   beancounting

 - David Hildenbrand has fixed some of our MM selftests for 32-bit
   machines

 - Many singleton patches, as usual

* tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (313 commits)
  mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio
  mm: mmu_gather: allow more than one batch of delayed rmaps
  mm: fix typo in struct pglist_data code comment
  kmsan: fix memcpy tests
  mm: add cond_resched() in swapin_walk_pmd_entry()
  mm: do not show fs mm pc for VM_LOCKONFAULT pages
  selftests/vm: ksm_functional_tests: fixes for 32bit
  selftests/vm: cow: fix compile warning on 32bit
  selftests/vm: madv_populate: fix missing MADV_POPULATE_(READ|WRITE) definitions
  mm/gup_test: fix PIN_LONGTERM_TEST_READ with highmem
  mm,thp,rmap: fix races between updates of subpages_mapcount
  mm: memcg: fix swapcached stat accounting
  mm: add nodes= arg to memory.reclaim
  mm: disable top-tier fallback to reclaim on proactive reclaim
  selftests: cgroup: make sure reclaim target memcg is unprotected
  selftests: cgroup: refactor proactive reclaim code to reclaim_until()
  mm: memcg: fix stale protection of reclaim target memcg
  mm/mmap: properly unaccount memory on mas_preallocate() failure
  omfs: remove ->writepage
  jfs: remove ->writepage
  ...
2022-12-13 19:29:45 -08:00

313 lines
9.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* arch/arm/include/asm/pgtable.h
*
* Copyright (C) 1995-2002 Russell King
*/
#ifndef _ASMARM_PGTABLE_H
#define _ASMARM_PGTABLE_H
#include <linux/const.h>
#include <asm/proc-fns.h>
#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)
#endif
#ifndef CONFIG_MMU
#include <asm-generic/pgtable-nopud.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 0xff800000UL
#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;
#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_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)
#define pgprot_device(prot) \
__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_DEV_SHARED | L_PTE_SHARED | L_PTE_DIRTY | L_PTE_XN)
#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
*/
#ifndef __ASSEMBLY__
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
#define pud_write(pud) pmd_write(__pmd(pud_val(pud)))
#define pmd_none(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))
#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_isset(pte, val) ((u32)(val) == (val) ? pte_val(pte) & (val) \
: !!(pte_val(pte) & (val)))
#define pte_isclear(pte, val) (!(pte_val(pte) & (val)))
#define pte_none(pte) (!pte_val(pte))
#define pte_present(pte) (pte_isset((pte), L_PTE_PRESENT))
#define pte_valid(pte) (pte_isset((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_isclear((pte), L_PTE_RDONLY))
#define pte_dirty(pte) (pte_isset((pte), L_PTE_DIRTY))
#define pte_young(pte) (pte_isset((pte), L_PTE_YOUNG))
#define pte_exec(pte) (pte_isclear((pte), L_PTE_XN))
#define pte_valid_user(pte) \
(pte_valid(pte) && pte_isset((pte), L_PTE_USER) && pte_young(pte))
static inline bool pte_access_permitted(pte_t pte, bool write)
{
pteval_t mask = L_PTE_PRESENT | L_PTE_USER;
pteval_t needed = mask;
if (write)
mask |= L_PTE_RDONLY;
return (pte_val(pte) & mask) == needed;
}
#define pte_access_permitted pte_access_permitted
#if __LINUX_ARM_ARCH__ < 6
static inline void __sync_icache_dcache(pte_t pteval)
{
}
#else
extern void __sync_icache_dcache(pte_t pteval);
#endif
void set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval);
static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
{
pte_val(pte) &= ~pgprot_val(prot);
return pte;
}
static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot)
{
pte_val(pte) |= pgprot_val(prot);
return pte;
}
static inline pte_t pte_wrprotect(pte_t pte)
{
return set_pte_bit(pte, __pgprot(L_PTE_RDONLY));
}
static inline pte_t pte_mkwrite(pte_t pte)
{
return clear_pte_bit(pte, __pgprot(L_PTE_RDONLY));
}
static inline pte_t pte_mkclean(pte_t pte)
{
return clear_pte_bit(pte, __pgprot(L_PTE_DIRTY));
}
static inline pte_t pte_mkdirty(pte_t pte)
{
return set_pte_bit(pte, __pgprot(L_PTE_DIRTY));
}
static inline pte_t pte_mkold(pte_t pte)
{
return clear_pte_bit(pte, __pgprot(L_PTE_YOUNG));
}
static inline pte_t pte_mkyoung(pte_t pte)
{
return set_pte_bit(pte, __pgprot(L_PTE_YOUNG));
}
static inline pte_t pte_mkexec(pte_t pte)
{
return clear_pte_bit(pte, __pgprot(L_PTE_XN));
}
static inline pte_t pte_mknexec(pte_t pte)
{
return set_pte_bit(pte, __pgprot(L_PTE_XN));
}
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
*
* This gives us up to 31 swap files and 128GB per swap file. Note that
* the offset field is always non-zero.
*/
#define __SWP_TYPE_SHIFT 2
#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((swp).val | PTE_TYPE_FAULT)
/*
* 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)
/*
* We provide our own arch_get_unmapped_area to cope with VIPT caches.
*/
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
#endif /* !__ASSEMBLY__ */
#endif /* CONFIG_MMU */
#endif /* _ASMARM_PGTABLE_H */