mirror of
https://github.com/torvalds/linux.git
synced 2024-11-23 12:42:02 +00:00
60f272f6b0
Patch series "memory-failure: fix hwpoison_filter", v2. As well known, the memory failure mechanism handles memory corrupted event, and try to send SIGBUS to the user process which uses this corrupted page. For the virtualization case, QEMU catches SIGBUS and tries to inject MCE into the guest, and the guest handles memory failure again. Thus the guest gets the minimal effect from hardware memory corruption. The further step I'm working on: 1, try to modify code to decrease poisoned pages in a single place (mm/memofy-failure.c: simplify num_poisoned_pages_dec in this series). 2, try to use page_handle_poison() to handle SetPageHWPoison() and num_poisoned_pages_inc() together. It would be best to call num_poisoned_pages_inc() in a single place too. 3, introduce memory failure notifier list in memory-failure.c: notify the corrupted PFN to someone who registers this list. If I can complete [1] and [2] part, [3] will be quite easy(just call notifier list after increasing poisoned page). 4, introduce memory recover VQ for memory balloon device, and registers memory failure notifier list. During the guest kernel handles memory failure, balloon device gets notified by memory failure notifier list, and tells the host to recover the corrupted PFN(GPA) by the new VQ. 5, host side remaps the corrupted page(HVA), and tells the guest side to unpoison the PFN(GPA). Then the guest fixes the corrupted page(GPA) dynamically. This patch (of 5): clear_hwpoisoned_pages() clears HWPoison flag and decreases the number of poisoned pages, this actually works as part of memory failure. Move this function from sparse.c to memory-failure.c, finally there is no CONFIG_MEMORY_FAILURE in sparse.c. Link: https://lkml.kernel.org/r/20220509105641.491313-1-pizhenwei@bytedance.com Link: https://lkml.kernel.org/r/20220509105641.491313-2-pizhenwei@bytedance.com Signed-off-by: zhenwei pi <pizhenwei@bytedance.com> Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
850 lines
27 KiB
C
850 lines
27 KiB
C
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
/* internal.h: mm/ internal definitions
|
|
*
|
|
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
*/
|
|
#ifndef __MM_INTERNAL_H
|
|
#define __MM_INTERNAL_H
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/rmap.h>
|
|
#include <linux/tracepoint-defs.h>
|
|
|
|
struct folio_batch;
|
|
|
|
/*
|
|
* The set of flags that only affect watermark checking and reclaim
|
|
* behaviour. This is used by the MM to obey the caller constraints
|
|
* about IO, FS and watermark checking while ignoring placement
|
|
* hints such as HIGHMEM usage.
|
|
*/
|
|
#define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
|
|
__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\
|
|
__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
|
|
__GFP_ATOMIC|__GFP_NOLOCKDEP)
|
|
|
|
/* The GFP flags allowed during early boot */
|
|
#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))
|
|
|
|
/* Control allocation cpuset and node placement constraints */
|
|
#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE)
|
|
|
|
/* Do not use these with a slab allocator */
|
|
#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
|
|
|
|
void page_writeback_init(void);
|
|
|
|
static inline void *folio_raw_mapping(struct folio *folio)
|
|
{
|
|
unsigned long mapping = (unsigned long)folio->mapping;
|
|
|
|
return (void *)(mapping & ~PAGE_MAPPING_FLAGS);
|
|
}
|
|
|
|
void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
|
|
int nr_throttled);
|
|
static inline void acct_reclaim_writeback(struct folio *folio)
|
|
{
|
|
pg_data_t *pgdat = folio_pgdat(folio);
|
|
int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled);
|
|
|
|
if (nr_throttled)
|
|
__acct_reclaim_writeback(pgdat, folio, nr_throttled);
|
|
}
|
|
|
|
static inline void wake_throttle_isolated(pg_data_t *pgdat)
|
|
{
|
|
wait_queue_head_t *wqh;
|
|
|
|
wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED];
|
|
if (waitqueue_active(wqh))
|
|
wake_up(wqh);
|
|
}
|
|
|
|
vm_fault_t do_swap_page(struct vm_fault *vmf);
|
|
void folio_rotate_reclaimable(struct folio *folio);
|
|
bool __folio_end_writeback(struct folio *folio);
|
|
void deactivate_file_folio(struct folio *folio);
|
|
|
|
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
|
|
unsigned long floor, unsigned long ceiling);
|
|
void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);
|
|
|
|
struct zap_details;
|
|
void unmap_page_range(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
unsigned long addr, unsigned long end,
|
|
struct zap_details *details);
|
|
|
|
void page_cache_ra_order(struct readahead_control *, struct file_ra_state *,
|
|
unsigned int order);
|
|
void force_page_cache_ra(struct readahead_control *, unsigned long nr);
|
|
static inline void force_page_cache_readahead(struct address_space *mapping,
|
|
struct file *file, pgoff_t index, unsigned long nr_to_read)
|
|
{
|
|
DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index);
|
|
force_page_cache_ra(&ractl, nr_to_read);
|
|
}
|
|
|
|
unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
|
|
pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
|
|
unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
|
|
pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
|
|
void filemap_free_folio(struct address_space *mapping, struct folio *folio);
|
|
int truncate_inode_folio(struct address_space *mapping, struct folio *folio);
|
|
bool truncate_inode_partial_folio(struct folio *folio, loff_t start,
|
|
loff_t end);
|
|
long invalidate_inode_page(struct page *page);
|
|
unsigned long invalidate_mapping_pagevec(struct address_space *mapping,
|
|
pgoff_t start, pgoff_t end, unsigned long *nr_pagevec);
|
|
|
|
/**
|
|
* folio_evictable - Test whether a folio is evictable.
|
|
* @folio: The folio to test.
|
|
*
|
|
* Test whether @folio is evictable -- i.e., should be placed on
|
|
* active/inactive lists vs unevictable list.
|
|
*
|
|
* Reasons folio might not be evictable:
|
|
* 1. folio's mapping marked unevictable
|
|
* 2. One of the pages in the folio is part of an mlocked VMA
|
|
*/
|
|
static inline bool folio_evictable(struct folio *folio)
|
|
{
|
|
bool ret;
|
|
|
|
/* Prevent address_space of inode and swap cache from being freed */
|
|
rcu_read_lock();
|
|
ret = !mapping_unevictable(folio_mapping(folio)) &&
|
|
!folio_test_mlocked(folio);
|
|
rcu_read_unlock();
|
|
return ret;
|
|
}
|
|
|
|
static inline bool page_evictable(struct page *page)
|
|
{
|
|
bool ret;
|
|
|
|
/* Prevent address_space of inode and swap cache from being freed */
|
|
rcu_read_lock();
|
|
ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
|
|
rcu_read_unlock();
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Turn a non-refcounted page (->_refcount == 0) into refcounted with
|
|
* a count of one.
|
|
*/
|
|
static inline void set_page_refcounted(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(PageTail(page), page);
|
|
VM_BUG_ON_PAGE(page_ref_count(page), page);
|
|
set_page_count(page, 1);
|
|
}
|
|
|
|
extern unsigned long highest_memmap_pfn;
|
|
|
|
/*
|
|
* Maximum number of reclaim retries without progress before the OOM
|
|
* killer is consider the only way forward.
|
|
*/
|
|
#define MAX_RECLAIM_RETRIES 16
|
|
|
|
/*
|
|
* in mm/early_ioremap.c
|
|
*/
|
|
pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr,
|
|
unsigned long size, pgprot_t prot);
|
|
|
|
/*
|
|
* in mm/vmscan.c:
|
|
*/
|
|
int isolate_lru_page(struct page *page);
|
|
int folio_isolate_lru(struct folio *folio);
|
|
void putback_lru_page(struct page *page);
|
|
void folio_putback_lru(struct folio *folio);
|
|
extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason);
|
|
|
|
/*
|
|
* in mm/rmap.c:
|
|
*/
|
|
extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
|
|
|
|
/*
|
|
* in mm/page_alloc.c
|
|
*/
|
|
|
|
/*
|
|
* Structure for holding the mostly immutable allocation parameters passed
|
|
* between functions involved in allocations, including the alloc_pages*
|
|
* family of functions.
|
|
*
|
|
* nodemask, migratetype and highest_zoneidx are initialized only once in
|
|
* __alloc_pages() and then never change.
|
|
*
|
|
* zonelist, preferred_zone and highest_zoneidx are set first in
|
|
* __alloc_pages() for the fast path, and might be later changed
|
|
* in __alloc_pages_slowpath(). All other functions pass the whole structure
|
|
* by a const pointer.
|
|
*/
|
|
struct alloc_context {
|
|
struct zonelist *zonelist;
|
|
nodemask_t *nodemask;
|
|
struct zoneref *preferred_zoneref;
|
|
int migratetype;
|
|
|
|
/*
|
|
* highest_zoneidx represents highest usable zone index of
|
|
* the allocation request. Due to the nature of the zone,
|
|
* memory on lower zone than the highest_zoneidx will be
|
|
* protected by lowmem_reserve[highest_zoneidx].
|
|
*
|
|
* highest_zoneidx is also used by reclaim/compaction to limit
|
|
* the target zone since higher zone than this index cannot be
|
|
* usable for this allocation request.
|
|
*/
|
|
enum zone_type highest_zoneidx;
|
|
bool spread_dirty_pages;
|
|
};
|
|
|
|
/*
|
|
* This function returns the order of a free page in the buddy system. In
|
|
* general, page_zone(page)->lock must be held by the caller to prevent the
|
|
* page from being allocated in parallel and returning garbage as the order.
|
|
* If a caller does not hold page_zone(page)->lock, it must guarantee that the
|
|
* page cannot be allocated or merged in parallel. Alternatively, it must
|
|
* handle invalid values gracefully, and use buddy_order_unsafe() below.
|
|
*/
|
|
static inline unsigned int buddy_order(struct page *page)
|
|
{
|
|
/* PageBuddy() must be checked by the caller */
|
|
return page_private(page);
|
|
}
|
|
|
|
/*
|
|
* Like buddy_order(), but for callers who cannot afford to hold the zone lock.
|
|
* PageBuddy() should be checked first by the caller to minimize race window,
|
|
* and invalid values must be handled gracefully.
|
|
*
|
|
* READ_ONCE is used so that if the caller assigns the result into a local
|
|
* variable and e.g. tests it for valid range before using, the compiler cannot
|
|
* decide to remove the variable and inline the page_private(page) multiple
|
|
* times, potentially observing different values in the tests and the actual
|
|
* use of the result.
|
|
*/
|
|
#define buddy_order_unsafe(page) READ_ONCE(page_private(page))
|
|
|
|
/*
|
|
* This function checks whether a page is free && is the buddy
|
|
* we can coalesce a page and its buddy if
|
|
* (a) the buddy is not in a hole (check before calling!) &&
|
|
* (b) the buddy is in the buddy system &&
|
|
* (c) a page and its buddy have the same order &&
|
|
* (d) a page and its buddy are in the same zone.
|
|
*
|
|
* For recording whether a page is in the buddy system, we set PageBuddy.
|
|
* Setting, clearing, and testing PageBuddy is serialized by zone->lock.
|
|
*
|
|
* For recording page's order, we use page_private(page).
|
|
*/
|
|
static inline bool page_is_buddy(struct page *page, struct page *buddy,
|
|
unsigned int order)
|
|
{
|
|
if (!page_is_guard(buddy) && !PageBuddy(buddy))
|
|
return false;
|
|
|
|
if (buddy_order(buddy) != order)
|
|
return false;
|
|
|
|
/*
|
|
* zone check is done late to avoid uselessly calculating
|
|
* zone/node ids for pages that could never merge.
|
|
*/
|
|
if (page_zone_id(page) != page_zone_id(buddy))
|
|
return false;
|
|
|
|
VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
|
|
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* Locate the struct page for both the matching buddy in our
|
|
* pair (buddy1) and the combined O(n+1) page they form (page).
|
|
*
|
|
* 1) Any buddy B1 will have an order O twin B2 which satisfies
|
|
* the following equation:
|
|
* B2 = B1 ^ (1 << O)
|
|
* For example, if the starting buddy (buddy2) is #8 its order
|
|
* 1 buddy is #10:
|
|
* B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
|
|
*
|
|
* 2) Any buddy B will have an order O+1 parent P which
|
|
* satisfies the following equation:
|
|
* P = B & ~(1 << O)
|
|
*
|
|
* Assumption: *_mem_map is contiguous at least up to MAX_ORDER
|
|
*/
|
|
static inline unsigned long
|
|
__find_buddy_pfn(unsigned long page_pfn, unsigned int order)
|
|
{
|
|
return page_pfn ^ (1 << order);
|
|
}
|
|
|
|
/*
|
|
* Find the buddy of @page and validate it.
|
|
* @page: The input page
|
|
* @pfn: The pfn of the page, it saves a call to page_to_pfn() when the
|
|
* function is used in the performance-critical __free_one_page().
|
|
* @order: The order of the page
|
|
* @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to
|
|
* page_to_pfn().
|
|
*
|
|
* The found buddy can be a non PageBuddy, out of @page's zone, or its order is
|
|
* not the same as @page. The validation is necessary before use it.
|
|
*
|
|
* Return: the found buddy page or NULL if not found.
|
|
*/
|
|
static inline struct page *find_buddy_page_pfn(struct page *page,
|
|
unsigned long pfn, unsigned int order, unsigned long *buddy_pfn)
|
|
{
|
|
unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order);
|
|
struct page *buddy;
|
|
|
|
buddy = page + (__buddy_pfn - pfn);
|
|
if (buddy_pfn)
|
|
*buddy_pfn = __buddy_pfn;
|
|
|
|
if (page_is_buddy(page, buddy, order))
|
|
return buddy;
|
|
return NULL;
|
|
}
|
|
|
|
extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
|
|
unsigned long end_pfn, struct zone *zone);
|
|
|
|
static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn,
|
|
unsigned long end_pfn, struct zone *zone)
|
|
{
|
|
if (zone->contiguous)
|
|
return pfn_to_page(start_pfn);
|
|
|
|
return __pageblock_pfn_to_page(start_pfn, end_pfn, zone);
|
|
}
|
|
|
|
extern int __isolate_free_page(struct page *page, unsigned int order);
|
|
extern void __putback_isolated_page(struct page *page, unsigned int order,
|
|
int mt);
|
|
extern void memblock_free_pages(struct page *page, unsigned long pfn,
|
|
unsigned int order);
|
|
extern void __free_pages_core(struct page *page, unsigned int order);
|
|
extern void prep_compound_page(struct page *page, unsigned int order);
|
|
extern void post_alloc_hook(struct page *page, unsigned int order,
|
|
gfp_t gfp_flags);
|
|
extern int user_min_free_kbytes;
|
|
|
|
extern void free_unref_page(struct page *page, unsigned int order);
|
|
extern void free_unref_page_list(struct list_head *list);
|
|
|
|
extern void zone_pcp_update(struct zone *zone, int cpu_online);
|
|
extern void zone_pcp_reset(struct zone *zone);
|
|
extern void zone_pcp_disable(struct zone *zone);
|
|
extern void zone_pcp_enable(struct zone *zone);
|
|
|
|
extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
|
|
phys_addr_t min_addr,
|
|
int nid, bool exact_nid);
|
|
|
|
void split_free_page(struct page *free_page,
|
|
int order, unsigned long split_pfn_offset);
|
|
|
|
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
|
|
|
|
/*
|
|
* in mm/compaction.c
|
|
*/
|
|
/*
|
|
* compact_control is used to track pages being migrated and the free pages
|
|
* they are being migrated to during memory compaction. The free_pfn starts
|
|
* at the end of a zone and migrate_pfn begins at the start. Movable pages
|
|
* are moved to the end of a zone during a compaction run and the run
|
|
* completes when free_pfn <= migrate_pfn
|
|
*/
|
|
struct compact_control {
|
|
struct list_head freepages; /* List of free pages to migrate to */
|
|
struct list_head migratepages; /* List of pages being migrated */
|
|
unsigned int nr_freepages; /* Number of isolated free pages */
|
|
unsigned int nr_migratepages; /* Number of pages to migrate */
|
|
unsigned long free_pfn; /* isolate_freepages search base */
|
|
/*
|
|
* Acts as an in/out parameter to page isolation for migration.
|
|
* isolate_migratepages uses it as a search base.
|
|
* isolate_migratepages_block will update the value to the next pfn
|
|
* after the last isolated one.
|
|
*/
|
|
unsigned long migrate_pfn;
|
|
unsigned long fast_start_pfn; /* a pfn to start linear scan from */
|
|
struct zone *zone;
|
|
unsigned long total_migrate_scanned;
|
|
unsigned long total_free_scanned;
|
|
unsigned short fast_search_fail;/* failures to use free list searches */
|
|
short search_order; /* order to start a fast search at */
|
|
const gfp_t gfp_mask; /* gfp mask of a direct compactor */
|
|
int order; /* order a direct compactor needs */
|
|
int migratetype; /* migratetype of direct compactor */
|
|
const unsigned int alloc_flags; /* alloc flags of a direct compactor */
|
|
const int highest_zoneidx; /* zone index of a direct compactor */
|
|
enum migrate_mode mode; /* Async or sync migration mode */
|
|
bool ignore_skip_hint; /* Scan blocks even if marked skip */
|
|
bool no_set_skip_hint; /* Don't mark blocks for skipping */
|
|
bool ignore_block_suitable; /* Scan blocks considered unsuitable */
|
|
bool direct_compaction; /* False from kcompactd or /proc/... */
|
|
bool proactive_compaction; /* kcompactd proactive compaction */
|
|
bool whole_zone; /* Whole zone should/has been scanned */
|
|
bool contended; /* Signal lock contention */
|
|
bool rescan; /* Rescanning the same pageblock */
|
|
bool alloc_contig; /* alloc_contig_range allocation */
|
|
};
|
|
|
|
/*
|
|
* Used in direct compaction when a page should be taken from the freelists
|
|
* immediately when one is created during the free path.
|
|
*/
|
|
struct capture_control {
|
|
struct compact_control *cc;
|
|
struct page *page;
|
|
};
|
|
|
|
unsigned long
|
|
isolate_freepages_range(struct compact_control *cc,
|
|
unsigned long start_pfn, unsigned long end_pfn);
|
|
int
|
|
isolate_migratepages_range(struct compact_control *cc,
|
|
unsigned long low_pfn, unsigned long end_pfn);
|
|
|
|
int __alloc_contig_migrate_range(struct compact_control *cc,
|
|
unsigned long start, unsigned long end);
|
|
#endif
|
|
int find_suitable_fallback(struct free_area *area, unsigned int order,
|
|
int migratetype, bool only_stealable, bool *can_steal);
|
|
|
|
/*
|
|
* These three helpers classifies VMAs for virtual memory accounting.
|
|
*/
|
|
|
|
/*
|
|
* Executable code area - executable, not writable, not stack
|
|
*/
|
|
static inline bool is_exec_mapping(vm_flags_t flags)
|
|
{
|
|
return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC;
|
|
}
|
|
|
|
/*
|
|
* Stack area - automatically grows in one direction
|
|
*
|
|
* VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous:
|
|
* do_mmap() forbids all other combinations.
|
|
*/
|
|
static inline bool is_stack_mapping(vm_flags_t flags)
|
|
{
|
|
return (flags & VM_STACK) == VM_STACK;
|
|
}
|
|
|
|
/*
|
|
* Data area - private, writable, not stack
|
|
*/
|
|
static inline bool is_data_mapping(vm_flags_t flags)
|
|
{
|
|
return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE;
|
|
}
|
|
|
|
/* mm/util.c */
|
|
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
|
|
struct vm_area_struct *prev);
|
|
void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma);
|
|
struct anon_vma *folio_anon_vma(struct folio *folio);
|
|
|
|
#ifdef CONFIG_MMU
|
|
void unmap_mapping_folio(struct folio *folio);
|
|
extern long populate_vma_page_range(struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long end, int *locked);
|
|
extern long faultin_vma_page_range(struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long end,
|
|
bool write, int *locked);
|
|
extern int mlock_future_check(struct mm_struct *mm, unsigned long flags,
|
|
unsigned long len);
|
|
/*
|
|
* mlock_vma_page() and munlock_vma_page():
|
|
* should be called with vma's mmap_lock held for read or write,
|
|
* under page table lock for the pte/pmd being added or removed.
|
|
*
|
|
* mlock is usually called at the end of page_add_*_rmap(),
|
|
* munlock at the end of page_remove_rmap(); but new anon
|
|
* pages are managed by lru_cache_add_inactive_or_unevictable()
|
|
* calling mlock_new_page().
|
|
*
|
|
* @compound is used to include pmd mappings of THPs, but filter out
|
|
* pte mappings of THPs, which cannot be consistently counted: a pte
|
|
* mapping of the THP head cannot be distinguished by the page alone.
|
|
*/
|
|
void mlock_folio(struct folio *folio);
|
|
static inline void mlock_vma_folio(struct folio *folio,
|
|
struct vm_area_struct *vma, bool compound)
|
|
{
|
|
/*
|
|
* The VM_SPECIAL check here serves two purposes.
|
|
* 1) VM_IO check prevents migration from double-counting during mlock.
|
|
* 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED
|
|
* is never left set on a VM_SPECIAL vma, there is an interval while
|
|
* file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may
|
|
* still be set while VM_SPECIAL bits are added: so ignore it then.
|
|
*/
|
|
if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED) &&
|
|
(compound || !folio_test_large(folio)))
|
|
mlock_folio(folio);
|
|
}
|
|
|
|
static inline void mlock_vma_page(struct page *page,
|
|
struct vm_area_struct *vma, bool compound)
|
|
{
|
|
mlock_vma_folio(page_folio(page), vma, compound);
|
|
}
|
|
|
|
void munlock_page(struct page *page);
|
|
static inline void munlock_vma_page(struct page *page,
|
|
struct vm_area_struct *vma, bool compound)
|
|
{
|
|
if (unlikely(vma->vm_flags & VM_LOCKED) &&
|
|
(compound || !PageTransCompound(page)))
|
|
munlock_page(page);
|
|
}
|
|
void mlock_new_page(struct page *page);
|
|
bool need_mlock_page_drain(int cpu);
|
|
void mlock_page_drain_local(void);
|
|
void mlock_page_drain_remote(int cpu);
|
|
|
|
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
|
|
|
|
/*
|
|
* Return the start of user virtual address at the specific offset within
|
|
* a vma.
|
|
*/
|
|
static inline unsigned long
|
|
vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
unsigned long address;
|
|
|
|
if (pgoff >= vma->vm_pgoff) {
|
|
address = vma->vm_start +
|
|
((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
|
|
/* Check for address beyond vma (or wrapped through 0?) */
|
|
if (address < vma->vm_start || address >= vma->vm_end)
|
|
address = -EFAULT;
|
|
} else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) {
|
|
/* Test above avoids possibility of wrap to 0 on 32-bit */
|
|
address = vma->vm_start;
|
|
} else {
|
|
address = -EFAULT;
|
|
}
|
|
return address;
|
|
}
|
|
|
|
/*
|
|
* Return the start of user virtual address of a page within a vma.
|
|
* Returns -EFAULT if all of the page is outside the range of vma.
|
|
* If page is a compound head, the entire compound page is considered.
|
|
*/
|
|
static inline unsigned long
|
|
vma_address(struct page *page, struct vm_area_struct *vma)
|
|
{
|
|
VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
|
|
return vma_pgoff_address(page_to_pgoff(page), compound_nr(page), vma);
|
|
}
|
|
|
|
/*
|
|
* Then at what user virtual address will none of the range be found in vma?
|
|
* Assumes that vma_address() already returned a good starting address.
|
|
*/
|
|
static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw)
|
|
{
|
|
struct vm_area_struct *vma = pvmw->vma;
|
|
pgoff_t pgoff;
|
|
unsigned long address;
|
|
|
|
/* Common case, plus ->pgoff is invalid for KSM */
|
|
if (pvmw->nr_pages == 1)
|
|
return pvmw->address + PAGE_SIZE;
|
|
|
|
pgoff = pvmw->pgoff + pvmw->nr_pages;
|
|
address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
|
|
/* Check for address beyond vma (or wrapped through 0?) */
|
|
if (address < vma->vm_start || address > vma->vm_end)
|
|
address = vma->vm_end;
|
|
return address;
|
|
}
|
|
|
|
static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
|
|
struct file *fpin)
|
|
{
|
|
int flags = vmf->flags;
|
|
|
|
if (fpin)
|
|
return fpin;
|
|
|
|
/*
|
|
* FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
|
|
* anything, so we only pin the file and drop the mmap_lock if only
|
|
* FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt.
|
|
*/
|
|
if (fault_flag_allow_retry_first(flags) &&
|
|
!(flags & FAULT_FLAG_RETRY_NOWAIT)) {
|
|
fpin = get_file(vmf->vma->vm_file);
|
|
mmap_read_unlock(vmf->vma->vm_mm);
|
|
}
|
|
return fpin;
|
|
}
|
|
#else /* !CONFIG_MMU */
|
|
static inline void unmap_mapping_folio(struct folio *folio) { }
|
|
static inline void mlock_vma_page(struct page *page,
|
|
struct vm_area_struct *vma, bool compound) { }
|
|
static inline void munlock_vma_page(struct page *page,
|
|
struct vm_area_struct *vma, bool compound) { }
|
|
static inline void mlock_new_page(struct page *page) { }
|
|
static inline bool need_mlock_page_drain(int cpu) { return false; }
|
|
static inline void mlock_page_drain_local(void) { }
|
|
static inline void mlock_page_drain_remote(int cpu) { }
|
|
static inline void vunmap_range_noflush(unsigned long start, unsigned long end)
|
|
{
|
|
}
|
|
#endif /* !CONFIG_MMU */
|
|
|
|
/*
|
|
* Return the mem_map entry representing the 'offset' subpage within
|
|
* the maximally aligned gigantic page 'base'. Handle any discontiguity
|
|
* in the mem_map at MAX_ORDER_NR_PAGES boundaries.
|
|
*/
|
|
static inline struct page *mem_map_offset(struct page *base, int offset)
|
|
{
|
|
if (unlikely(offset >= MAX_ORDER_NR_PAGES))
|
|
return nth_page(base, offset);
|
|
return base + offset;
|
|
}
|
|
|
|
/*
|
|
* Iterator over all subpages within the maximally aligned gigantic
|
|
* page 'base'. Handle any discontiguity in the mem_map.
|
|
*/
|
|
static inline struct page *mem_map_next(struct page *iter,
|
|
struct page *base, int offset)
|
|
{
|
|
if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) {
|
|
unsigned long pfn = page_to_pfn(base) + offset;
|
|
if (!pfn_valid(pfn))
|
|
return NULL;
|
|
return pfn_to_page(pfn);
|
|
}
|
|
return iter + 1;
|
|
}
|
|
|
|
/* Memory initialisation debug and verification */
|
|
enum mminit_level {
|
|
MMINIT_WARNING,
|
|
MMINIT_VERIFY,
|
|
MMINIT_TRACE
|
|
};
|
|
|
|
#ifdef CONFIG_DEBUG_MEMORY_INIT
|
|
|
|
extern int mminit_loglevel;
|
|
|
|
#define mminit_dprintk(level, prefix, fmt, arg...) \
|
|
do { \
|
|
if (level < mminit_loglevel) { \
|
|
if (level <= MMINIT_WARNING) \
|
|
pr_warn("mminit::" prefix " " fmt, ##arg); \
|
|
else \
|
|
printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \
|
|
} \
|
|
} while (0)
|
|
|
|
extern void mminit_verify_pageflags_layout(void);
|
|
extern void mminit_verify_zonelist(void);
|
|
#else
|
|
|
|
static inline void mminit_dprintk(enum mminit_level level,
|
|
const char *prefix, const char *fmt, ...)
|
|
{
|
|
}
|
|
|
|
static inline void mminit_verify_pageflags_layout(void)
|
|
{
|
|
}
|
|
|
|
static inline void mminit_verify_zonelist(void)
|
|
{
|
|
}
|
|
#endif /* CONFIG_DEBUG_MEMORY_INIT */
|
|
|
|
#define NODE_RECLAIM_NOSCAN -2
|
|
#define NODE_RECLAIM_FULL -1
|
|
#define NODE_RECLAIM_SOME 0
|
|
#define NODE_RECLAIM_SUCCESS 1
|
|
|
|
#ifdef CONFIG_NUMA
|
|
extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
|
|
extern int find_next_best_node(int node, nodemask_t *used_node_mask);
|
|
#else
|
|
static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
|
|
unsigned int order)
|
|
{
|
|
return NODE_RECLAIM_NOSCAN;
|
|
}
|
|
static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
|
|
{
|
|
return NUMA_NO_NODE;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* mm/memory-failure.c
|
|
*/
|
|
extern int hwpoison_filter(struct page *p);
|
|
|
|
extern u32 hwpoison_filter_dev_major;
|
|
extern u32 hwpoison_filter_dev_minor;
|
|
extern u64 hwpoison_filter_flags_mask;
|
|
extern u64 hwpoison_filter_flags_value;
|
|
extern u64 hwpoison_filter_memcg;
|
|
extern u32 hwpoison_filter_enable;
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
void clear_hwpoisoned_pages(struct page *memmap, int nr_pages);
|
|
#else
|
|
static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long,
|
|
unsigned long, unsigned long,
|
|
unsigned long, unsigned long);
|
|
|
|
extern void set_pageblock_order(void);
|
|
unsigned int reclaim_clean_pages_from_list(struct zone *zone,
|
|
struct list_head *page_list);
|
|
/* The ALLOC_WMARK bits are used as an index to zone->watermark */
|
|
#define ALLOC_WMARK_MIN WMARK_MIN
|
|
#define ALLOC_WMARK_LOW WMARK_LOW
|
|
#define ALLOC_WMARK_HIGH WMARK_HIGH
|
|
#define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */
|
|
|
|
/* Mask to get the watermark bits */
|
|
#define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1)
|
|
|
|
/*
|
|
* Only MMU archs have async oom victim reclaim - aka oom_reaper so we
|
|
* cannot assume a reduced access to memory reserves is sufficient for
|
|
* !MMU
|
|
*/
|
|
#ifdef CONFIG_MMU
|
|
#define ALLOC_OOM 0x08
|
|
#else
|
|
#define ALLOC_OOM ALLOC_NO_WATERMARKS
|
|
#endif
|
|
|
|
#define ALLOC_HARDER 0x10 /* try to alloc harder */
|
|
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
|
|
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
|
|
#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
|
|
#ifdef CONFIG_ZONE_DMA32
|
|
#define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */
|
|
#else
|
|
#define ALLOC_NOFRAGMENT 0x0
|
|
#endif
|
|
#define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
|
|
|
|
enum ttu_flags;
|
|
struct tlbflush_unmap_batch;
|
|
|
|
|
|
/*
|
|
* only for MM internal work items which do not depend on
|
|
* any allocations or locks which might depend on allocations
|
|
*/
|
|
extern struct workqueue_struct *mm_percpu_wq;
|
|
|
|
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
|
|
void try_to_unmap_flush(void);
|
|
void try_to_unmap_flush_dirty(void);
|
|
void flush_tlb_batched_pending(struct mm_struct *mm);
|
|
#else
|
|
static inline void try_to_unmap_flush(void)
|
|
{
|
|
}
|
|
static inline void try_to_unmap_flush_dirty(void)
|
|
{
|
|
}
|
|
static inline void flush_tlb_batched_pending(struct mm_struct *mm)
|
|
{
|
|
}
|
|
#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
|
|
|
|
extern const struct trace_print_flags pageflag_names[];
|
|
extern const struct trace_print_flags vmaflag_names[];
|
|
extern const struct trace_print_flags gfpflag_names[];
|
|
|
|
static inline bool is_migrate_highatomic(enum migratetype migratetype)
|
|
{
|
|
return migratetype == MIGRATE_HIGHATOMIC;
|
|
}
|
|
|
|
static inline bool is_migrate_highatomic_page(struct page *page)
|
|
{
|
|
return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC;
|
|
}
|
|
|
|
void setup_zone_pageset(struct zone *zone);
|
|
|
|
struct migration_target_control {
|
|
int nid; /* preferred node id */
|
|
nodemask_t *nmask;
|
|
gfp_t gfp_mask;
|
|
};
|
|
|
|
/*
|
|
* mm/vmalloc.c
|
|
*/
|
|
#ifdef CONFIG_MMU
|
|
int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
|
|
pgprot_t prot, struct page **pages, unsigned int page_shift);
|
|
#else
|
|
static inline
|
|
int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
|
|
pgprot_t prot, struct page **pages, unsigned int page_shift)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
#endif
|
|
|
|
void vunmap_range_noflush(unsigned long start, unsigned long end);
|
|
|
|
int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
|
|
unsigned long addr, int page_nid, int *flags);
|
|
|
|
void free_zone_device_page(struct page *page);
|
|
|
|
/*
|
|
* mm/gup.c
|
|
*/
|
|
struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags);
|
|
|
|
DECLARE_PER_CPU(struct per_cpu_nodestat, boot_nodestats);
|
|
|
|
#endif /* __MM_INTERNAL_H */
|