mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 17:30:02 +00:00
![Michal Hocko](/assets/img/avatar_default.png)
This patch (of 5): This is based on the idea from Mel Gorman discussed during LSFMM 2015 and independently brought up by Oleg Nesterov. The OOM killer currently allows to kill only a single task in a good hope that the task will terminate in a reasonable time and frees up its memory. Such a task (oom victim) will get an access to memory reserves via mark_oom_victim to allow a forward progress should there be a need for additional memory during exit path. It has been shown (e.g. by Tetsuo Handa) that it is not that hard to construct workloads which break the core assumption mentioned above and the OOM victim might take unbounded amount of time to exit because it might be blocked in the uninterruptible state waiting for an event (e.g. lock) which is blocked by another task looping in the page allocator. This patch reduces the probability of such a lockup by introducing a specialized kernel thread (oom_reaper) which tries to reclaim additional memory by preemptively reaping the anonymous or swapped out memory owned by the oom victim under an assumption that such a memory won't be needed when its owner is killed and kicked from the userspace anyway. There is one notable exception to this, though, if the OOM victim was in the process of coredumping the result would be incomplete. This is considered a reasonable constrain because the overall system health is more important than debugability of a particular application. A kernel thread has been chosen because we need a reliable way of invocation so workqueue context is not appropriate because all the workers might be busy (e.g. allocating memory). Kswapd which sounds like another good fit is not appropriate as well because it might get blocked on locks during reclaim as well. oom_reaper has to take mmap_sem on the target task for reading so the solution is not 100% because the semaphore might be held or blocked for write but the probability is reduced considerably wrt. basically any lock blocking forward progress as described above. In order to prevent from blocking on the lock without any forward progress we are using only a trylock and retry 10 times with a short sleep in between. Users of mmap_sem which need it for write should be carefully reviewed to use _killable waiting as much as possible and reduce allocations requests done with the lock held to absolute minimum to reduce the risk even further. The API between oom killer and oom reaper is quite trivial. wake_oom_reaper updates mm_to_reap with cmpxchg to guarantee only NULL->mm transition and oom_reaper clear this atomically once it is done with the work. This means that only a single mm_struct can be reaped at the time. As the operation is potentially disruptive we are trying to limit it to the ncessary minimum and the reaper blocks any updates while it operates on an mm. mm_struct is pinned by mm_count to allow parallel exit_mmap and a race is detected by atomic_inc_not_zero(mm_users). Signed-off-by: Michal Hocko <mhocko@suse.com> Suggested-by: Oleg Nesterov <oleg@redhat.com> Suggested-by: Mel Gorman <mgorman@suse.de> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Andrea Argangeli <andrea@kernel.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
485 lines
15 KiB
C
485 lines
15 KiB
C
/* internal.h: mm/ internal definitions
|
|
*
|
|
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
#ifndef __MM_INTERNAL_H
|
|
#define __MM_INTERNAL_H
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/tracepoint-defs.h>
|
|
|
|
/*
|
|
* 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_REPEAT|__GFP_NOFAIL|\
|
|
__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
|
|
|
|
/* 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 free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
|
|
unsigned long floor, unsigned long ceiling);
|
|
|
|
void unmap_page_range(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
unsigned long addr, unsigned long end,
|
|
struct zap_details *details);
|
|
|
|
extern int __do_page_cache_readahead(struct address_space *mapping,
|
|
struct file *filp, pgoff_t offset, unsigned long nr_to_read,
|
|
unsigned long lookahead_size);
|
|
|
|
/*
|
|
* Submit IO for the read-ahead request in file_ra_state.
|
|
*/
|
|
static inline unsigned long ra_submit(struct file_ra_state *ra,
|
|
struct address_space *mapping, struct file *filp)
|
|
{
|
|
return __do_page_cache_readahead(mapping, filp,
|
|
ra->start, ra->size, ra->async_size);
|
|
}
|
|
|
|
/*
|
|
* Turn a non-refcounted page (->_count == 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;
|
|
|
|
/*
|
|
* in mm/vmscan.c:
|
|
*/
|
|
extern int isolate_lru_page(struct page *page);
|
|
extern void putback_lru_page(struct page *page);
|
|
extern bool zone_reclaimable(struct zone *zone);
|
|
|
|
/*
|
|
* 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 high_zoneidx are initialized only once in
|
|
* __alloc_pages_nodemask() and then never change.
|
|
*
|
|
* zonelist, preferred_zone and classzone_idx are set first in
|
|
* __alloc_pages_nodemask() for the fast path, and might be later changed
|
|
* in __alloc_pages_slowpath(). All other functions pass the whole strucure
|
|
* by a const pointer.
|
|
*/
|
|
struct alloc_context {
|
|
struct zonelist *zonelist;
|
|
nodemask_t *nodemask;
|
|
struct zone *preferred_zone;
|
|
int classzone_idx;
|
|
int migratetype;
|
|
enum zone_type high_zoneidx;
|
|
bool spread_dirty_pages;
|
|
};
|
|
|
|
/*
|
|
* 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_index(unsigned long page_idx, unsigned int order)
|
|
{
|
|
return page_idx ^ (1 << order);
|
|
}
|
|
|
|
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 __free_pages_bootmem(struct page *page, unsigned long pfn,
|
|
unsigned int order);
|
|
extern void prep_compound_page(struct page *page, unsigned int order);
|
|
extern int user_min_free_kbytes;
|
|
|
|
#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 long nr_freepages; /* Number of isolated free pages */
|
|
unsigned long nr_migratepages; /* Number of pages to migrate */
|
|
unsigned long free_pfn; /* isolate_freepages search base */
|
|
unsigned long migrate_pfn; /* isolate_migratepages search base */
|
|
unsigned long last_migrated_pfn;/* Not yet flushed page being freed */
|
|
enum migrate_mode mode; /* Async or sync migration mode */
|
|
bool ignore_skip_hint; /* Scan blocks even if marked skip */
|
|
bool direct_compaction; /* False from kcompactd or /proc/... */
|
|
int order; /* order a direct compactor needs */
|
|
const gfp_t gfp_mask; /* gfp mask of a direct compactor */
|
|
const int alloc_flags; /* alloc flags of a direct compactor */
|
|
const int classzone_idx; /* zone index of a direct compactor */
|
|
struct zone *zone;
|
|
int contended; /* Signal need_sched() or lock
|
|
* contention detected during
|
|
* compaction
|
|
*/
|
|
};
|
|
|
|
unsigned long
|
|
isolate_freepages_range(struct compact_control *cc,
|
|
unsigned long start_pfn, unsigned long end_pfn);
|
|
unsigned long
|
|
isolate_migratepages_range(struct compact_control *cc,
|
|
unsigned long low_pfn, unsigned long end_pfn);
|
|
int find_suitable_fallback(struct free_area *area, unsigned int order,
|
|
int migratetype, bool only_stealable, bool *can_steal);
|
|
|
|
#endif
|
|
|
|
/*
|
|
* 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 page_order_unsafe() below.
|
|
*/
|
|
static inline unsigned int page_order(struct page *page)
|
|
{
|
|
/* PageBuddy() must be checked by the caller */
|
|
return page_private(page);
|
|
}
|
|
|
|
/*
|
|
* Like page_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 page_order_unsafe(page) READ_ONCE(page_private(page))
|
|
|
|
static inline bool is_cow_mapping(vm_flags_t flags)
|
|
{
|
|
return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
|
|
}
|
|
|
|
/*
|
|
* 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 - atomatically 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, struct rb_node *rb_parent);
|
|
|
|
#ifdef CONFIG_MMU
|
|
extern long populate_vma_page_range(struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long end, int *nonblocking);
|
|
extern void munlock_vma_pages_range(struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long end);
|
|
static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
|
|
{
|
|
munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end);
|
|
}
|
|
|
|
/*
|
|
* must be called with vma's mmap_sem held for read or write, and page locked.
|
|
*/
|
|
extern void mlock_vma_page(struct page *page);
|
|
extern unsigned int munlock_vma_page(struct page *page);
|
|
|
|
/*
|
|
* Clear the page's PageMlocked(). This can be useful in a situation where
|
|
* we want to unconditionally remove a page from the pagecache -- e.g.,
|
|
* on truncation or freeing.
|
|
*
|
|
* It is legal to call this function for any page, mlocked or not.
|
|
* If called for a page that is still mapped by mlocked vmas, all we do
|
|
* is revert to lazy LRU behaviour -- semantics are not broken.
|
|
*/
|
|
extern void clear_page_mlock(struct page *page);
|
|
|
|
/*
|
|
* mlock_migrate_page - called only from migrate_misplaced_transhuge_page()
|
|
* (because that does not go through the full procedure of migration ptes):
|
|
* to migrate the Mlocked page flag; update statistics.
|
|
*/
|
|
static inline void mlock_migrate_page(struct page *newpage, struct page *page)
|
|
{
|
|
if (TestClearPageMlocked(page)) {
|
|
int nr_pages = hpage_nr_pages(page);
|
|
|
|
/* Holding pmd lock, no change in irq context: __mod is safe */
|
|
__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
|
|
SetPageMlocked(newpage);
|
|
__mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages);
|
|
}
|
|
}
|
|
|
|
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
|
|
|
|
/*
|
|
* At what user virtual address is page expected in @vma?
|
|
*/
|
|
static inline unsigned long
|
|
__vma_address(struct page *page, struct vm_area_struct *vma)
|
|
{
|
|
pgoff_t pgoff = page_to_pgoff(page);
|
|
return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
|
|
}
|
|
|
|
static inline unsigned long
|
|
vma_address(struct page *page, struct vm_area_struct *vma)
|
|
{
|
|
unsigned long address = __vma_address(page, vma);
|
|
|
|
/* page should be within @vma mapping range */
|
|
VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
|
|
|
|
return address;
|
|
}
|
|
|
|
#else /* !CONFIG_MMU */
|
|
static inline void clear_page_mlock(struct page *page) { }
|
|
static inline void mlock_vma_page(struct page *page) { }
|
|
static inline void mlock_migrate_page(struct page *new, struct page *old) { }
|
|
|
|
#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;
|
|
}
|
|
|
|
/*
|
|
* FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
|
|
* so all functions starting at paging_init should be marked __init
|
|
* in those cases. SPARSEMEM, however, allows for memory hotplug,
|
|
* and alloc_bootmem_node is not used.
|
|
*/
|
|
#ifdef CONFIG_SPARSEMEM
|
|
#define __paginginit __meminit
|
|
#else
|
|
#define __paginginit __init
|
|
#endif
|
|
|
|
/* 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 */
|
|
|
|
/* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */
|
|
#if defined(CONFIG_SPARSEMEM)
|
|
extern void mminit_validate_memmodel_limits(unsigned long *start_pfn,
|
|
unsigned long *end_pfn);
|
|
#else
|
|
static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
|
|
unsigned long *end_pfn)
|
|
{
|
|
}
|
|
#endif /* CONFIG_SPARSEMEM */
|
|
|
|
#define ZONE_RECLAIM_NOSCAN -2
|
|
#define ZONE_RECLAIM_FULL -1
|
|
#define ZONE_RECLAIM_SOME 0
|
|
#define ZONE_RECLAIM_SUCCESS 1
|
|
|
|
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;
|
|
|
|
extern unsigned long vm_mmap_pgoff(struct file *, unsigned long,
|
|
unsigned long, unsigned long,
|
|
unsigned long, unsigned long);
|
|
|
|
extern void set_pageblock_order(void);
|
|
unsigned long 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)
|
|
|
|
#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 */
|
|
#define ALLOC_FAIR 0x100 /* fair zone allocation */
|
|
|
|
enum ttu_flags;
|
|
struct tlbflush_unmap_batch;
|
|
|
|
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
|
|
void try_to_unmap_flush(void);
|
|
void try_to_unmap_flush_dirty(void);
|
|
#else
|
|
static inline void try_to_unmap_flush(void)
|
|
{
|
|
}
|
|
static inline void try_to_unmap_flush_dirty(void)
|
|
{
|
|
}
|
|
|
|
#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[];
|
|
|
|
#endif /* __MM_INTERNAL_H */
|