0753ba01e1
The commit2ff05b2b
(oom: move oom_adj value) moveed the oom_adj value to the mm_struct. It was a very good first step for sanitize OOM. However Paul Menage reported the commit makes regression to his job scheduler. Current OOM logic can kill OOM_DISABLED process. Why? His program has the code of similar to the following. ... set_oom_adj(OOM_DISABLE); /* The job scheduler never killed by oom */ ... if (vfork() == 0) { set_oom_adj(0); /* Invoked child can be killed */ execve("foo-bar-cmd"); } .... vfork() parent and child are shared the same mm_struct. then above set_oom_adj(0) doesn't only change oom_adj for vfork() child, it's also change oom_adj for vfork() parent. Then, vfork() parent (job scheduler) lost OOM immune and it was killed. Actually, fork-setting-exec idiom is very frequently used in userland program. We must not break this assumption. Then, this patch revert commit2ff05b2b
and related commit. Reverted commit list --------------------- - commit2ff05b2b4e
(oom: move oom_adj value from task_struct to mm_struct) - commit4d8b9135c3
(oom: avoid unnecessary mm locking and scanning for OOM_DISABLE) - commit8123681022
(oom: only oom kill exiting tasks with attached memory) - commit933b787b57
(mm: copy over oom_adj value at fork time) Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Paul Menage <menage@google.com> Cc: David Rientjes <rientjes@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Rik van Riel <riel@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
295 lines
9.2 KiB
C
295 lines
9.2 KiB
C
#ifndef _LINUX_MM_TYPES_H
|
|
#define _LINUX_MM_TYPES_H
|
|
|
|
#include <linux/auxvec.h>
|
|
#include <linux/types.h>
|
|
#include <linux/threads.h>
|
|
#include <linux/list.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/prio_tree.h>
|
|
#include <linux/rbtree.h>
|
|
#include <linux/rwsem.h>
|
|
#include <linux/completion.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/page-debug-flags.h>
|
|
#include <asm/page.h>
|
|
#include <asm/mmu.h>
|
|
|
|
#ifndef AT_VECTOR_SIZE_ARCH
|
|
#define AT_VECTOR_SIZE_ARCH 0
|
|
#endif
|
|
#define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
|
|
|
|
struct address_space;
|
|
|
|
#define USE_SPLIT_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
|
|
|
|
#if USE_SPLIT_PTLOCKS
|
|
typedef atomic_long_t mm_counter_t;
|
|
#else /* !USE_SPLIT_PTLOCKS */
|
|
typedef unsigned long mm_counter_t;
|
|
#endif /* !USE_SPLIT_PTLOCKS */
|
|
|
|
/*
|
|
* Each physical page in the system has a struct page associated with
|
|
* it to keep track of whatever it is we are using the page for at the
|
|
* moment. Note that we have no way to track which tasks are using
|
|
* a page, though if it is a pagecache page, rmap structures can tell us
|
|
* who is mapping it.
|
|
*/
|
|
struct page {
|
|
unsigned long flags; /* Atomic flags, some possibly
|
|
* updated asynchronously */
|
|
atomic_t _count; /* Usage count, see below. */
|
|
union {
|
|
atomic_t _mapcount; /* Count of ptes mapped in mms,
|
|
* to show when page is mapped
|
|
* & limit reverse map searches.
|
|
*/
|
|
struct { /* SLUB */
|
|
u16 inuse;
|
|
u16 objects;
|
|
};
|
|
};
|
|
union {
|
|
struct {
|
|
unsigned long private; /* Mapping-private opaque data:
|
|
* usually used for buffer_heads
|
|
* if PagePrivate set; used for
|
|
* swp_entry_t if PageSwapCache;
|
|
* indicates order in the buddy
|
|
* system if PG_buddy is set.
|
|
*/
|
|
struct address_space *mapping; /* If low bit clear, points to
|
|
* inode address_space, or NULL.
|
|
* If page mapped as anonymous
|
|
* memory, low bit is set, and
|
|
* it points to anon_vma object:
|
|
* see PAGE_MAPPING_ANON below.
|
|
*/
|
|
};
|
|
#if USE_SPLIT_PTLOCKS
|
|
spinlock_t ptl;
|
|
#endif
|
|
struct kmem_cache *slab; /* SLUB: Pointer to slab */
|
|
struct page *first_page; /* Compound tail pages */
|
|
};
|
|
union {
|
|
pgoff_t index; /* Our offset within mapping. */
|
|
void *freelist; /* SLUB: freelist req. slab lock */
|
|
};
|
|
struct list_head lru; /* Pageout list, eg. active_list
|
|
* protected by zone->lru_lock !
|
|
*/
|
|
/*
|
|
* On machines where all RAM is mapped into kernel address space,
|
|
* we can simply calculate the virtual address. On machines with
|
|
* highmem some memory is mapped into kernel virtual memory
|
|
* dynamically, so we need a place to store that address.
|
|
* Note that this field could be 16 bits on x86 ... ;)
|
|
*
|
|
* Architectures with slow multiplication can define
|
|
* WANT_PAGE_VIRTUAL in asm/page.h
|
|
*/
|
|
#if defined(WANT_PAGE_VIRTUAL)
|
|
void *virtual; /* Kernel virtual address (NULL if
|
|
not kmapped, ie. highmem) */
|
|
#endif /* WANT_PAGE_VIRTUAL */
|
|
#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS
|
|
unsigned long debug_flags; /* Use atomic bitops on this */
|
|
#endif
|
|
|
|
#ifdef CONFIG_KMEMCHECK
|
|
/*
|
|
* kmemcheck wants to track the status of each byte in a page; this
|
|
* is a pointer to such a status block. NULL if not tracked.
|
|
*/
|
|
void *shadow;
|
|
#endif
|
|
};
|
|
|
|
/*
|
|
* A region containing a mapping of a non-memory backed file under NOMMU
|
|
* conditions. These are held in a global tree and are pinned by the VMAs that
|
|
* map parts of them.
|
|
*/
|
|
struct vm_region {
|
|
struct rb_node vm_rb; /* link in global region tree */
|
|
unsigned long vm_flags; /* VMA vm_flags */
|
|
unsigned long vm_start; /* start address of region */
|
|
unsigned long vm_end; /* region initialised to here */
|
|
unsigned long vm_top; /* region allocated to here */
|
|
unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */
|
|
struct file *vm_file; /* the backing file or NULL */
|
|
|
|
atomic_t vm_usage; /* region usage count */
|
|
};
|
|
|
|
/*
|
|
* This struct defines a memory VMM memory area. There is one of these
|
|
* per VM-area/task. A VM area is any part of the process virtual memory
|
|
* space that has a special rule for the page-fault handlers (ie a shared
|
|
* library, the executable area etc).
|
|
*/
|
|
struct vm_area_struct {
|
|
struct mm_struct * vm_mm; /* The address space we belong to. */
|
|
unsigned long vm_start; /* Our start address within vm_mm. */
|
|
unsigned long vm_end; /* The first byte after our end address
|
|
within vm_mm. */
|
|
|
|
/* linked list of VM areas per task, sorted by address */
|
|
struct vm_area_struct *vm_next;
|
|
|
|
pgprot_t vm_page_prot; /* Access permissions of this VMA. */
|
|
unsigned long vm_flags; /* Flags, see mm.h. */
|
|
|
|
struct rb_node vm_rb;
|
|
|
|
/*
|
|
* For areas with an address space and backing store,
|
|
* linkage into the address_space->i_mmap prio tree, or
|
|
* linkage to the list of like vmas hanging off its node, or
|
|
* linkage of vma in the address_space->i_mmap_nonlinear list.
|
|
*/
|
|
union {
|
|
struct {
|
|
struct list_head list;
|
|
void *parent; /* aligns with prio_tree_node parent */
|
|
struct vm_area_struct *head;
|
|
} vm_set;
|
|
|
|
struct raw_prio_tree_node prio_tree_node;
|
|
} shared;
|
|
|
|
/*
|
|
* A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
|
|
* list, after a COW of one of the file pages. A MAP_SHARED vma
|
|
* can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack
|
|
* or brk vma (with NULL file) can only be in an anon_vma list.
|
|
*/
|
|
struct list_head anon_vma_node; /* Serialized by anon_vma->lock */
|
|
struct anon_vma *anon_vma; /* Serialized by page_table_lock */
|
|
|
|
/* Function pointers to deal with this struct. */
|
|
struct vm_operations_struct * vm_ops;
|
|
|
|
/* Information about our backing store: */
|
|
unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
|
|
units, *not* PAGE_CACHE_SIZE */
|
|
struct file * vm_file; /* File we map to (can be NULL). */
|
|
void * vm_private_data; /* was vm_pte (shared mem) */
|
|
unsigned long vm_truncate_count;/* truncate_count or restart_addr */
|
|
|
|
#ifndef CONFIG_MMU
|
|
struct vm_region *vm_region; /* NOMMU mapping region */
|
|
#endif
|
|
#ifdef CONFIG_NUMA
|
|
struct mempolicy *vm_policy; /* NUMA policy for the VMA */
|
|
#endif
|
|
};
|
|
|
|
struct core_thread {
|
|
struct task_struct *task;
|
|
struct core_thread *next;
|
|
};
|
|
|
|
struct core_state {
|
|
atomic_t nr_threads;
|
|
struct core_thread dumper;
|
|
struct completion startup;
|
|
};
|
|
|
|
struct mm_struct {
|
|
struct vm_area_struct * mmap; /* list of VMAs */
|
|
struct rb_root mm_rb;
|
|
struct vm_area_struct * mmap_cache; /* last find_vma result */
|
|
unsigned long (*get_unmapped_area) (struct file *filp,
|
|
unsigned long addr, unsigned long len,
|
|
unsigned long pgoff, unsigned long flags);
|
|
void (*unmap_area) (struct mm_struct *mm, unsigned long addr);
|
|
unsigned long mmap_base; /* base of mmap area */
|
|
unsigned long task_size; /* size of task vm space */
|
|
unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */
|
|
unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */
|
|
pgd_t * pgd;
|
|
atomic_t mm_users; /* How many users with user space? */
|
|
atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */
|
|
int map_count; /* number of VMAs */
|
|
struct rw_semaphore mmap_sem;
|
|
spinlock_t page_table_lock; /* Protects page tables and some counters */
|
|
|
|
struct list_head mmlist; /* List of maybe swapped mm's. These are globally strung
|
|
* together off init_mm.mmlist, and are protected
|
|
* by mmlist_lock
|
|
*/
|
|
|
|
/* Special counters, in some configurations protected by the
|
|
* page_table_lock, in other configurations by being atomic.
|
|
*/
|
|
mm_counter_t _file_rss;
|
|
mm_counter_t _anon_rss;
|
|
|
|
unsigned long hiwater_rss; /* High-watermark of RSS usage */
|
|
unsigned long hiwater_vm; /* High-water virtual memory usage */
|
|
|
|
unsigned long total_vm, locked_vm, shared_vm, exec_vm;
|
|
unsigned long stack_vm, reserved_vm, def_flags, nr_ptes;
|
|
unsigned long start_code, end_code, start_data, end_data;
|
|
unsigned long start_brk, brk, start_stack;
|
|
unsigned long arg_start, arg_end, env_start, env_end;
|
|
|
|
unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
|
|
|
|
cpumask_t cpu_vm_mask;
|
|
|
|
/* Architecture-specific MM context */
|
|
mm_context_t context;
|
|
|
|
/* Swap token stuff */
|
|
/*
|
|
* Last value of global fault stamp as seen by this process.
|
|
* In other words, this value gives an indication of how long
|
|
* it has been since this task got the token.
|
|
* Look at mm/thrash.c
|
|
*/
|
|
unsigned int faultstamp;
|
|
unsigned int token_priority;
|
|
unsigned int last_interval;
|
|
|
|
unsigned long flags; /* Must use atomic bitops to access the bits */
|
|
|
|
struct core_state *core_state; /* coredumping support */
|
|
|
|
/* aio bits */
|
|
spinlock_t ioctx_lock;
|
|
struct hlist_head ioctx_list;
|
|
|
|
#ifdef CONFIG_MM_OWNER
|
|
/*
|
|
* "owner" points to a task that is regarded as the canonical
|
|
* user/owner of this mm. All of the following must be true in
|
|
* order for it to be changed:
|
|
*
|
|
* current == mm->owner
|
|
* current->mm != mm
|
|
* new_owner->mm == mm
|
|
* new_owner->alloc_lock is held
|
|
*/
|
|
struct task_struct *owner;
|
|
#endif
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
/* store ref to file /proc/<pid>/exe symlink points to */
|
|
struct file *exe_file;
|
|
unsigned long num_exe_file_vmas;
|
|
#endif
|
|
#ifdef CONFIG_MMU_NOTIFIER
|
|
struct mmu_notifier_mm *mmu_notifier_mm;
|
|
#endif
|
|
};
|
|
|
|
/* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
|
|
#define mm_cpumask(mm) (&(mm)->cpu_vm_mask)
|
|
|
|
#endif /* _LINUX_MM_TYPES_H */
|