Release 4.17 mm/oom_kill.c

/*
 *  linux/mm/oom_kill.c
 * 
 *  Copyright (C)  1998,2000  Rik van Riel
 *      Thanks go out to Claus Fischer for some serious inspiration and
 *      for goading me into coding this file...
 *  Copyright (C)  2010  Google, Inc.
 *      Rewritten by David Rientjes
 *
 *  The routines in this file are used to kill a process when
 *  we're seriously out of memory. This gets called from __alloc_pages()
 *  in mm/page_alloc.c when we really run out of memory.
 *
 *  Since we won't call these routines often (on a well-configured
 *  machine) this file will double as a 'coding guide' and a signpost
 *  for newbie kernel hackers. It features several pointers to major
 *  kernel subsystems and hints as to where to find out what things do.
 */

#include <linux/oom.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
#include <linux/swap.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/cpuset.h>
#include <linux/export.h>
#include <linux/notifier.h>
#include <linux/memcontrol.h>
#include <linux/mempolicy.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/freezer.h>
#include <linux/ftrace.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
#include <linux/init.h>
#include <linux/mmu_notifier.h>

#include <asm/tlb.h>
#include "internal.h"
#include "slab.h"


#define CREATE_TRACE_POINTS
#include <trace/events/oom.h>


int sysctl_panic_on_oom;

int sysctl_oom_kill_allocating_task;

int sysctl_oom_dump_tasks = 1;

DEFINE_MUTEX(oom_lock);

#ifdef CONFIG_NUMA
/**
 * has_intersects_mems_allowed() - check task eligiblity for kill
 * @start: task struct of which task to consider
 * @mask: nodemask passed to page allocator for mempolicy ooms
 *
 * Task eligibility is determined by whether or not a candidate task, @tsk,
 * shares the same mempolicy nodes as current if it is bound by such a policy
 * and whether or not it has the same set of allowed cpuset nodes.
 */


static bool has_intersects_mems_allowed(struct task_struct *start,
					const nodemask_t *mask)
{
	struct task_struct *tsk;
	bool ret = false;

	rcu_read_lock();
	for_each_thread(start, tsk) {
		if (mask) {
			/*
                         * If this is a mempolicy constrained oom, tsk's
                         * cpuset is irrelevant.  Only return true if its
                         * mempolicy intersects current, otherwise it may be
                         * needlessly killed.
                         */
			ret = mempolicy_nodemask_intersects(tsk, mask);
		} else {
			/*
                         * This is not a mempolicy constrained oom, so only
                         * check the mems of tsk's cpuset.
                         */
			ret = cpuset_mems_allowed_intersects(current, tsk);
		}
		if (ret)
			break;
	}
	rcu_read_unlock();

	return ret;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Oleg Nesterov
31
40.26%
2
50.00%
Motohiro Kosaki
23
29.87%
1
25.00%
David Rientjes
23
29.87%
1
25.00%
Total
77
100.00%
4
100.00%

#else


static bool has_intersects_mems_allowed(struct task_struct *tsk,
					const nodemask_t *mask)
{
	return true;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
18
94.74%
1
50.00%
Oleg Nesterov
1
5.26%
1
50.00%
Total
19
100.00%
2
100.00%

#endif /* CONFIG_NUMA */

/*
 * The process p may have detached its own ->mm while exiting or through
 * use_mm(), but one or more of its subthreads may still have a valid
 * pointer.  Return p, or any of its subthreads with a valid ->mm, with
 * task_lock() held.
 */


struct task_struct *find_lock_task_mm(struct task_struct *p)
{
	struct task_struct *t;

	rcu_read_lock();

	for_each_thread(p, t) {
		task_lock(t);
		if (likely(t->mm))
			goto found;
		task_unlock(t);
	}
	t = NULL;
found:
	rcu_read_unlock();

	return t;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Oleg Nesterov
62
100.00%
3
100.00%
Total
62
100.00%
3
100.00%

/*
 * order == -1 means the oom kill is required by sysrq, otherwise only
 * for display purposes.
 */


static inline bool is_sysrq_oom(struct oom_control *oc)
{
	return oc->order == -1;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Yaowei Bai
20
100.00%
1
100.00%
Total
20
100.00%
1
100.00%



static inline bool is_memcg_oom(struct oom_control *oc)
{
	return oc->memcg != NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Vladimir Davydov
19
100.00%
1
100.00%
Total
19
100.00%
1
100.00%

/* return true if the task is not adequate as candidate victim task. */


static bool oom_unkillable_task(struct task_struct *p,
		struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
	if (is_global_init(p))
		return true;
	if (p->flags & PF_KTHREAD)
		return true;

	/* When mem_cgroup_out_of_memory() and p is not member of the group */
	if (memcg && !task_in_mem_cgroup(p, memcg))
		return true;

	/* p may not have freeable memory in nodemask */
	if (!has_intersects_mems_allowed(p, nodemask))
		return true;

	return false;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Motohiro Kosaki
71
94.67%
1
33.33%
Johannes Weiner
3
4.00%
1
33.33%
Oleg Nesterov
1
1.33%
1
33.33%
Total
75
100.00%
3
100.00%

/*
 * Print out unreclaimble slabs info when unreclaimable slabs amount is greater
 * than all user memory (LRU pages)
 */


static bool is_dump_unreclaim_slabs(void)
{
	unsigned long nr_lru;

	nr_lru = global_node_page_state(NR_ACTIVE_ANON) +
		 global_node_page_state(NR_INACTIVE_ANON) +
		 global_node_page_state(NR_ACTIVE_FILE) +
		 global_node_page_state(NR_INACTIVE_FILE) +
		 global_node_page_state(NR_ISOLATED_ANON) +
		 global_node_page_state(NR_ISOLATED_FILE) +
		 global_node_page_state(NR_UNEVICTABLE);

	return (global_node_page_state(NR_SLAB_UNRECLAIMABLE) > nr_lru);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Yang Shi
59
100.00%
1
100.00%
Total
59
100.00%
1
100.00%

/**
 * oom_badness - heuristic function to determine which candidate task to kill
 * @p: task struct of which task we should calculate
 * @totalpages: total present RAM allowed for page allocation
 * @memcg: task's memory controller, if constrained
 * @nodemask: nodemask passed to page allocator for mempolicy ooms
 *
 * The heuristic for determining which task to kill is made to be as simple and
 * predictable as possible.  The goal is to return the highest value for the
 * task consuming the most memory to avoid subsequent oom failures.
 */


unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
			  const nodemask_t *nodemask, unsigned long totalpages)
{
	long points;
	long adj;

	if (oom_unkillable_task(p, memcg, nodemask))
		return 0;

	p = find_lock_task_mm(p);
	if (!p)
		return 0;

	/*
         * Do not even consider tasks which are explicitly marked oom
         * unkillable or have been already oom reaped or the are in
         * the middle of vfork
         */
	adj = (long)p->signal->oom_score_adj;
	if (adj == OOM_SCORE_ADJ_MIN ||
			test_bit(MMF_OOM_SKIP, &p->mm->flags) ||
			in_vfork(p)) {
		task_unlock(p);
		return 0;
	}

	/*
         * The baseline for the badness score is the proportion of RAM that each
         * task's rss, pagetable and swap space use.
         */
	points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) +
		mm_pgtables_bytes(p->mm) / PAGE_SIZE;
	task_unlock(p);

	/* Normalize to oom_score_adj units */
	adj *= totalpages / 1000;
	points += adj;

	/*
         * Never return 0 for an eligible task regardless of the root bonus and
         * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
         */
	return points > 0 ? points : 1;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
39
24.53%
5
20.00%
Michal Hocko
36
22.64%
4
16.00%
Motohiro Kosaki
26
16.35%
5
20.00%
Linus Torvalds (pre-git)
23
14.47%
1
4.00%
Kirill A. Shutemov
17
10.69%
3
12.00%
Andrew Morton
5
3.14%
1
4.00%
Oleg Nesterov
4
2.52%
1
4.00%
Tim Schmielau
3
1.89%
1
4.00%
Johannes Weiner
2
1.26%
1
4.00%
Ingo Molnar
2
1.26%
1
4.00%
Cyrill V. Gorcunov
1
0.63%
1
4.00%
Frantisek Hrbata
1
0.63%
1
4.00%
Total
159
100.00%
25
100.00%


enum oom_constraint {
	
CONSTRAINT_NONE,
	
CONSTRAINT_CPUSET,
	
CONSTRAINT_MEMORY_POLICY,
	
CONSTRAINT_MEMCG,
};

/*
 * Determine the type of allocation constraint.
 */


static enum oom_constraint constrained_alloc(struct oom_control *oc)
{
	struct zone *zone;
	struct zoneref *z;
	enum zone_type high_zoneidx = gfp_zone(oc->gfp_mask);
	bool cpuset_limited = false;
	int nid;

	if (is_memcg_oom(oc)) {
		oc->totalpages = mem_cgroup_get_limit(oc->memcg) ?: 1;
		return CONSTRAINT_MEMCG;
	}

	/* Default to all available memory */
	oc->totalpages = totalram_pages + total_swap_pages;

	if (!IS_ENABLED(CONFIG_NUMA))
		return CONSTRAINT_NONE;

	if (!oc->zonelist)
		return CONSTRAINT_NONE;
	/*
         * Reach here only when __GFP_NOFAIL is used. So, we should avoid
         * to kill current.We have to random task kill in this case.
         * Hopefully, CONSTRAINT_THISNODE...but no way to handle it, now.
         */
	if (oc->gfp_mask & __GFP_THISNODE)
		return CONSTRAINT_NONE;

	/*
         * This is not a __GFP_THISNODE allocation, so a truncated nodemask in
         * the page allocator means a mempolicy is in effect.  Cpuset policy
         * is enforced in get_page_from_freelist().
         */
	if (oc->nodemask &&
	    !nodes_subset(node_states[N_MEMORY], *oc->nodemask)) {
		oc->totalpages = total_swap_pages;
		for_each_node_mask(nid, *oc->nodemask)
			oc->totalpages += node_spanned_pages(nid);
		return CONSTRAINT_MEMORY_POLICY;
	}

	/* Check this allocation failure is caused by cpuset's wall function */
	for_each_zone_zonelist_nodemask(zone, z, oc->zonelist,
			high_zoneidx, oc->nodemask)
		if (!cpuset_zone_allowed(zone, oc->gfp_mask))
			cpuset_limited = true;

	if (cpuset_limited) {
		oc->totalpages = total_swap_pages;
		for_each_node_mask(nid, cpuset_current_mems_allowed)
			oc->totalpages += node_spanned_pages(nid);
		return CONSTRAINT_CPUSET;
	}
	return CONSTRAINT_NONE;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
86
39.45%
3
27.27%
Vladimir Davydov
51
23.39%
2
18.18%
Kamezawa Hiroyuki
31
14.22%
1
9.09%
Christoph Lameter
27
12.39%
2
18.18%
Mel Gorman
22
10.09%
2
18.18%
Lai Jiangshan
1
0.46%
1
9.09%
Total
218
100.00%
11
100.00%



static int oom_evaluate_task(struct task_struct *task, void *arg)
{
	struct oom_control *oc = arg;
	unsigned long points;

	if (oom_unkillable_task(task, NULL, oc->nodemask))
		goto next;

	/*
         * This task already has access to memory reserves and is being killed.
         * Don't allow any other task to have access to the reserves unless
         * the task has MMF_OOM_SKIP because chances that it would release
         * any memory is quite low.
         */
	if (!is_sysrq_oom(oc) && tsk_is_oom_victim(task)) {
		if (test_bit(MMF_OOM_SKIP, &task->signal->oom_mm->flags))
			goto next;
		goto abort;
	}

	/*
         * If task is allocating a lot of memory and has been marked to be
         * killed first if it triggers an oom, then select it.
         */
	if (oom_task_origin(task)) {
		points = ULONG_MAX;
		goto select;
	}

	points = oom_badness(task, NULL, oc->nodemask, oc->totalpages);
	if (!points || points < oc->chosen_points)
		goto next;

	/* Prefer thread group leaders for display purposes */
	if (points == oc->chosen_points && thread_group_leader(oc->chosen))
		goto next;
select:
	if (oc->chosen)
		put_task_struct(oc->chosen);
	get_task_struct(task);
	oc->chosen = task;
	oc->chosen_points = points;
next:
	return 0;
abort:
	if (oc->chosen)
		put_task_struct(oc->chosen);
	oc->chosen = (void *)-1UL;
	return 1;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Vladimir Davydov
144
67.61%
1
5.00%
David Rientjes
30
14.08%
9
45.00%
Michal Hocko
19
8.92%
3
15.00%
Kamezawa Hiroyuki
6
2.82%
1
5.00%
Yaowei Bai
4
1.88%
1
5.00%
Tetsuo Handa
3
1.41%
1
5.00%
Linus Torvalds (pre-git)
3
1.41%
1
5.00%
Nicholas Piggin
2
0.94%
1
5.00%
Motohiro Kosaki
1
0.47%
1
5.00%
Oleg Nesterov
1
0.47%
1
5.00%
Total
213
100.00%
20
100.00%

/*
 * Simple selection loop. We choose the process with the highest number of
 * 'points'. In case scan was aborted, oc->chosen is set to -1.
 */


static void select_bad_process(struct oom_control *oc)
{
	if (is_memcg_oom(oc))
		mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc);
	else {
		struct task_struct *p;

		rcu_read_lock();
		for_each_process(p)
			if (oom_evaluate_task(p, oc))
				break;
		rcu_read_unlock();
	}

	oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
37
52.11%
5
62.50%
Vladimir Davydov
31
43.66%
1
12.50%
Linus Torvalds (pre-git)
2
2.82%
1
12.50%
Tetsuo Handa
1
1.41%
1
12.50%
Total
71
100.00%
8
100.00%

/**
 * dump_tasks - dump current memory state of all system tasks
 * @memcg: current's memory controller, if constrained
 * @nodemask: nodemask passed to page allocator for mempolicy ooms
 *
 * Dumps the current memory state of all eligible tasks.  Tasks not in the same
 * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
 * are not shown.
 * State information includes task's pid, uid, tgid, vm size, rss,
 * pgtables_bytes, swapents, oom_score_adj value, and name.
 */


static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
	struct task_struct *p;
	struct task_struct *task;

	pr_info("[ pid ]   uid  tgid total_vm      rss pgtables_bytes swapents oom_score_adj name\n");
	rcu_read_lock();
	for_each_process(p) {
		if (oom_unkillable_task(p, memcg, nodemask))
			continue;

		task = find_lock_task_mm(p);
		if (!task) {
			/*
                         * This is a kthread or all of p's threads have already
                         * detached their mm's.  There's no need to report
                         * them; they can't be oom killed anyway.
                         */
			continue;
		}

		pr_info("[%5d] %5d %5d %8lu %8lu %8ld %8lu         %5hd %s\n",
			task->pid, from_kuid(&init_user_ns, task_uid(task)),
			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
			mm_pgtables_bytes(task->mm),
			get_mm_counter(task->mm, MM_SWAPENTS),
			task->signal->oom_score_adj, task->comm);
		task_unlock(task);
	}
	rcu_read_unlock();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
99
71.22%
9
56.25%
Motohiro Kosaki
21
15.11%
2
12.50%
Kirill A. Shutemov
9
6.47%
2
12.50%
Eric W. Biedermann
6
4.32%
1
6.25%
David Howells
2
1.44%
1
6.25%
Johannes Weiner
2
1.44%
1
6.25%
Total
139
100.00%
16
100.00%



static void dump_header(struct oom_control *oc, struct task_struct *p)
{
	pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=%*pbl, order=%d, oom_score_adj=%hd\n",
		current->comm, oc->gfp_mask, &oc->gfp_mask,
		nodemask_pr_args(oc->nodemask), oc->order,
			current->signal->oom_score_adj);
	if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order)
		pr_warn("COMPACTION is disabled!!!\n");

	cpuset_print_current_mems_allowed();
	dump_stack();
	if (is_memcg_oom(oc))
		mem_cgroup_print_oom_info(oc->memcg, p);
	else {
		show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask);
		if (is_dump_unreclaim_slabs())
			dump_unreclaimable_slab();
	}
	if (sysctl_oom_dump_tasks)
		dump_tasks(oc->memcg, oc->nodemask);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
68
54.40%
8
44.44%
Michal Hocko
22
17.60%
4
22.22%
Yang Shi
13
10.40%
1
5.56%
Vlastimil Babka
6
4.80%
1
5.56%
Vladimir Davydov
5
4.00%
1
5.56%
Daisuke Nishimura
5
4.00%
1
5.56%
Sha Zhengju
4
3.20%
1
5.56%
Johannes Weiner
2
1.60%
1
5.56%
Total
125
100.00%
18
100.00%

/*
 * Number of OOM victims in flight
 */

static atomic_t oom_victims = ATOMIC_INIT(0);
static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait);


static bool oom_killer_disabled __read_mostly;


#define K(x) ((x) << (PAGE_SHIFT-10))

/*
 * task->mm can be NULL if the task is the exited group leader.  So to
 * determine whether the task is using a particular mm, we examine all the
 * task's threads: if one of those is using this mm then this task was also
 * using it.
 */


bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
{
	struct task_struct *t;

	for_each_thread(p, t) {
		struct mm_struct *t_mm = READ_ONCE(t->mm);
		if (t_mm)
			return t_mm == mm;
	}
	return false;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
52
100.00%
1
100.00%
Total
52
100.00%
1
100.00%

#ifdef CONFIG_MMU
/*
 * OOM Reaper kernel thread which tries to reap the memory used by the OOM
 * victim (if that is possible) to help the OOM killer to move on.
 */

static struct task_struct *oom_reaper_th;
static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);

static struct task_struct *oom_reaper_list;
static DEFINE_SPINLOCK(oom_reaper_lock);



void __oom_reap_task_mm(struct mm_struct *mm)
{
	struct vm_area_struct *vma;

	/*
         * Tell all users of get_user/copy_from_user etc... that the content
         * is no longer stable. No barriers really needed because unmapping
         * should imply barriers already and the reader would hit a page fault
         * if it stumbled over a reaped memory.
         */
	set_bit(MMF_UNSTABLE, &mm->flags);

	for (vma = mm->mmap ; vma; vma = vma->vm_next) {
		if (!can_madv_dontneed_vma(vma))
			continue;

		/*
                 * Only anonymous pages have a good chance to be dropped
                 * without additional steps which we cannot afford as we
                 * are OOM already.
                 *
                 * We do not even care about fs backed pages because all
                 * which are reclaimable have already been reclaimed and
                 * we do not want to block exit_mmap by keeping mm ref
                 * count elevated without a good reason.
                 */
		if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
			const unsigned long start = vma->vm_start;
			const unsigned long end = vma->vm_end;
			struct mmu_gather tlb;

			tlb_gather_mmu(&tlb, mm, start, end);
			mmu_notifier_invalidate_range_start(mm, start, end);
			unmap_page_range(&tlb, vma, start, end, NULL);
			mmu_notifier_invalidate_range_end(mm, start, end);
			tlb_finish_mmu(&tlb, start, end);
		}
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
80
54.05%
2
25.00%
David Rientjes
48
32.43%
2
25.00%
Wang Nan
13
8.78%
1
12.50%
Tetsuo Handa
4
2.70%
1
12.50%
Kirill A. Shutemov
3
2.03%
2
25.00%
Total
148
100.00%
8
100.00%



static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
{
	bool ret = true;

	/*
         * We have to make sure to not race with the victim exit path
         * and cause premature new oom victim selection:
         * oom_reap_task_mm             exit_mm
         *   mmget_not_zero
         *                                mmput
         *                                  atomic_dec_and_test
         *                                exit_oom_victim
         *                              [...]
         *                              out_of_memory
         *                                select_bad_process
         *                                  # no TIF_MEMDIE task selects new victim
         *  unmap_page_range # frees some memory
         */
	mutex_lock(&oom_lock);

	if (!down_read_trylock(&mm->mmap_sem)) {
		ret = false;
		trace_skip_task_reaping(tsk->pid);
		goto unlock_oom;
	}

	/*
         * If the mm has invalidate_{start,end}() notifiers that could block,
         * sleep to give the oom victim some more time.
         * TODO: we really want to get rid of this ugly hack and make sure that
         * notifiers cannot block for unbounded amount of time
         */
	if (mm_has_blockable_invalidate_notifiers(mm)) {
		up_read(&mm->mmap_sem);
		schedule_timeout_idle(HZ);
		goto unlock_oom;
	}

	/*
         * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't
         * work on the mm anymore. The check for MMF_OOM_SKIP must run
         * under mmap_sem for reading because it serializes against the
         * down_write();up_write() cycle in exit_mmap().
         */
	if (test_bit(MMF_OOM_SKIP, &mm->flags)) {
		up_read(&mm->mmap_sem);
		trace_skip_task_reaping(tsk->pid);
		goto unlock_oom;
	}

	trace_start_task_reaping(tsk->pid);

	__oom_reap_task_mm(mm);

	pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
			task_pid_nr(tsk), tsk->comm,
			K(get_mm_counter(mm, MM_ANONPAGES)),
			K(get_mm_counter(mm, MM_FILEPAGES)),
			K(get_mm_counter(mm, MM_SHMEMPAGES)));
	up_read(&mm->mmap_sem);

	trace_finish_task_reaping(tsk->pid);
unlock_oom:
	mutex_unlock(&oom_lock);
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
125
63.78%
1
20.00%
Michal Hocko
64
32.65%
3
60.00%
Roman Gushchin
7
3.57%
1
20.00%
Total
196
100.00%
5
100.00%


#define MAX_OOM_REAP_RETRIES 10


static void oom_reap_task(struct task_struct *tsk)
{
	int attempts = 0;
	struct mm_struct *mm = tsk->signal->oom_mm;

	/* Retry the down_read_trylock(mmap_sem) a few times */
	while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm))
		schedule_timeout_idle(HZ/10);

	if (attempts <= MAX_OOM_REAP_RETRIES ||
	    test_bit(MMF_OOM_SKIP, &mm->flags))
		goto done;

	pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
		task_pid_nr(tsk), tsk->comm);
	debug_show_all_locks();

done:
	tsk->oom_reaper_list = NULL;

	/*
         * Hide this mm from OOM killer because it has been either reaped or
         * somebody can't call up_write(mmap_sem).
         */
	set_bit(MMF_OOM_SKIP, &mm->flags);

	/* Drop a reference taken by wake_oom_reaper */
	put_task_struct(tsk);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
80
72.07%
7
63.64%
Tetsuo Handa
30
27.03%
3
27.27%
David Rientjes
1
0.90%
1
9.09%
Total
111
100.00%
11
100.00%



static int oom_reaper(void *unused)
{
	while (true) {
		struct task_struct *tsk = NULL;

		wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL);
		spin_lock(&oom_reaper_lock);
		if (oom_reaper_list != NULL) {
			tsk = oom_reaper_list;
			oom_reaper_list = tsk->oom_reaper_list;
		}
		spin_unlock(&oom_reaper_lock);

		if (tsk)
			oom_reap_task(tsk);
	}

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
68
91.89%
3
75.00%
Vladimir Davydov
6
8.11%
1
25.00%
Total
74
100.00%
4
100.00%



static void wake_oom_reaper(struct task_struct *tsk)
{
	/* tsk is already queued? */
	if (tsk == oom_reaper_list || tsk->oom_reaper_list)
		return;

	get_task_struct(tsk);

	spin_lock(&oom_reaper_lock);
	tsk->oom_reaper_list = oom_reaper_list;
	oom_reaper_list = tsk;
	spin_unlock(&oom_reaper_lock);
	trace_wake_reaper(tsk->pid);
	wake_up(&oom_reaper_wait);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
46
73.02%
4
50.00%
Roman Gushchin
7
11.11%
1
12.50%
Vladimir Davydov
6
9.52%
2
25.00%
Tetsuo Handa
4
6.35%
1
12.50%
Total
63
100.00%
8
100.00%



static int __init oom_init(void)
{
	oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper");
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
23
100.00%
1
100.00%
Total
23
100.00%
1
100.00%


subsys_initcall(oom_init)
#else

static inline void wake_oom_reaper(struct task_struct *tsk)
{
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Vladimir Davydov
11
100.00%
1
100.00%
Total
11
100.00%
1
100.00%

#endif /* CONFIG_MMU */

/**
 * mark_oom_victim - mark the given task as OOM victim
 * @tsk: task to mark
 *
 * Has to be called with oom_lock held and never after
 * oom has been disabled already.
 *
 * tsk->mm has to be non NULL and caller has to guarantee it is stable (either
 * under task_lock or operate on the current).
 */

static void mark_oom_victim(struct task_struct *tsk)
{
	struct mm_struct *mm = tsk->mm;

	WARN_ON(oom_killer_disabled);
	/* OOM killer might race with memcg OOM */
	if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE))
		return;

	/* oom_mm is bound to the signal struct life time. */
	if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) {
		mmgrab(tsk->signal->oom_mm);
		set_bit(MMF_OOM_VICTIM, &mm->flags);
	}

	/*
         * Make sure that the task is woken up from uninterruptible sleep
         * if it is frozen because OOM killer wouldn't be able to free
         * any memory and livelock. freezing_slow_path will tell the freezer
         * that TIF_MEMDIE tasks should be ignored.
         */
	__thaw_task(tsk);
	atomic_inc(&oom_victims);
	trace_mark_victim(tsk->pid);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
84
89.36%
4
50.00%
Roman Gushchin
7
7.45%
1
12.50%
Vegard Nossum
1
1.06%
1
12.50%
Johannes Weiner
1
1.06%
1
12.50%
Vladimir Davydov
1
1.06%
1
12.50%
Total
94
100.00%
8
100.00%

/**
 * exit_oom_victim - note the exit of an OOM victim
 */


void exit_oom_victim(void)
{
	clear_thread_flag(TIF_MEMDIE);

	if (!atomic_dec_return(&oom_victims))
		wake_up_all(&oom_victims_wait);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
23
85.19%
2
50.00%
Tetsuo Handa
3
11.11%
1
25.00%
Johannes Weiner
1
3.70%
1
25.00%
Total
27
100.00%
4
100.00%

/**
 * oom_killer_enable - enable OOM killer
 */


void oom_killer_enable(void)
{
	oom_killer_disabled = false;
	pr_info("OOM killer enabled.\n");
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
16
100.00%
2
100.00%
Total
16
100.00%
2
100.00%

/**
 * oom_killer_disable - disable OOM killer
 * @timeout: maximum timeout to wait for oom victims in jiffies
 *
 * Forces all page allocations to fail rather than trigger OOM killer.
 * Will block and wait until all OOM victims are killed or the given
 * timeout expires.
 *
 * The function cannot be called when there are runnable user tasks because
 * the userspace would see unexpected allocation failures as a result. Any
 * new usage of this function should be consulted with MM people.
 *
 * Returns true if successful and false if the OOM killer cannot be
 * disabled.
 */


bool oom_killer_disable(signed long timeout)
{
	signed long ret;

	/*
         * Make sure to not race with an ongoing OOM killer. Check that the
         * current is not killed (possibly due to sharing the victim's memory).
         */
	if (mutex_lock_killable(&oom_lock))
		return false;
	oom_killer_disabled = true;
	mutex_unlock(&oom_lock);

	ret = wait_event_interruptible_timeout(oom_victims_wait,
			!atomic_read(&oom_victims), timeout);
	if (ret <= 0) {
		oom_killer_enable();
		return false;
	}
	pr_info("OOM killer disabled.\n");

	return true;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
67
91.78%
5
71.43%
Tetsuo Handa
3
4.11%
1
14.29%
Johannes Weiner
3
4.11%
1
14.29%
Total
73
100.00%
7
100.00%



static inline bool __task_will_free_mem(struct task_struct *task)
{
	struct signal_struct *sig = task->signal;

	/*
         * A coredumping process may sleep for an extended period in exit_mm(),
         * so the oom killer cannot assume that the process will promptly exit
         * and release memory.
         */
	if (sig->flags & SIGNAL_GROUP_COREDUMP)
		return false;

	if (sig->flags & SIGNAL_GROUP_EXIT)
		return true;

	if (thread_group_empty(task) && (task->flags & PF_EXITING))
		return true;

	return false;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
65
100.00%
1
100.00%
Total
65
100.00%
1
100.00%

/*
 * Checks whether the given task is dying or exiting and likely to
 * release its address space. This means that all threads and processes
 * sharing the same mm have to be killed or exiting.
 * Caller has to make sure that task->mm is stable (hold task_lock or
 * it operates on the current).
 */


static bool task_will_free_mem(struct task_struct *task)
{
	struct mm_struct *mm = task->mm;
	struct task_struct *p;
	bool ret = true;

	/*
         * Skip tasks without mm because it might have passed its exit_mm and
         * exit_oom_victim. oom_reaper could have rescued that but do not rely
         * on that for now. We can consider find_lock_task_mm in future.
         */
	if (!mm)
		return false;

	if (!__task_will_free_mem(task))
		return false;

	/*
         * This task has already been drained by the oom reaper so there are
         * only small chances it will free some more
         */
	if (test_bit(MMF_OOM_SKIP, &mm->flags))
		return false;

	if (atomic_read(&mm->mm_users) <= 1)
		return true;

	/*
         * Make sure that all tasks which share the mm with the given tasks
         * are dying as well to make sure that a) nobody pins its mm and
         * b) the task is also reapable by the oom reaper.
         */
	rcu_read_lock();
	for_each_process(p) {
		if (!process_shares_mm(p, mm))
			continue;
		if (same_thread_group(task, p))
			continue;
		ret = __task_will_free_mem(p);
		if (!ret)
			break;
	}
	rcu_read_unlock();

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
128
97.71%
5
71.43%
Geert Uytterhoeven
2
1.53%
1
14.29%
Vladimir Davydov
1
0.76%
1
14.29%
Total
131
100.00%
7
100.00%



static void oom_kill_process(struct oom_control *oc, const char *message)
{
	struct task_struct *p = oc->chosen;
	unsigned int points = oc->chosen_points;
	struct task_struct *victim = p;
	struct task_struct *child;
	struct task_struct *t;
	struct mm_struct *mm;
	unsigned int victim_points = 0;
	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
					      DEFAULT_RATELIMIT_BURST);
	bool can_oom_reap = true;

	/*
         * If the task is already exiting, don't alarm the sysadmin or kill
         * its children or threads, just give it access to memory reserves
         * so it can die quickly
         */
	task_lock(p);
	if (task_will_free_mem(p)) {
		mark_oom_victim(p);
		wake_oom_reaper(p);
		task_unlock(p);
		put_task_struct(p);
		return;
	}
	task_unlock(p);

	if (__ratelimit(&oom_rs))
		dump_header(oc, p);

	pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
		message, task_pid_nr(p), p->comm, points);

	/*
         * If any of p's children has a different mm and is eligible for kill,
         * the one with the highest oom_badness() score is sacrificed for its
         * parent.  This attempts to lose the minimal amount of work done while
         * still freeing memory.
         */
	read_lock(&tasklist_lock);
	for_each_thread(p, t) {
		list_for_each_entry(child, &t->children, sibling) {
			unsigned int child_points;

			if (process_shares_mm(child, p->mm))
				continue;
			/*
                         * oom_badness() returns 0 if the thread is unkillable
                         */
			child_points = oom_badness(child,
				oc->memcg, oc->nodemask, oc->totalpages);
			if (child_points > victim_points) {
				put_task_struct(victim);
				victim = child;
				victim_points = child_points;
				get_task_struct(victim);
			}
		}
	}
	read_unlock(&tasklist_lock);

	p = find_lock_task_mm(victim);
	if (!p) {
		put_task_struct(victim);
		return;
	} else if (victim != p) {
		get_task_struct(p);
		put_task_struct(victim);
		victim = p;
	}

	/* Get a reference to safely compare mm after task_unlock(victim) */
	mm = victim->mm;
	mmgrab(mm);

	/* Raise event before sending signal: task reaper must see this */
	count_vm_event(OOM_KILL);
	count_memcg_event_mm(mm, OOM_KILL);

	/*
         * We should send SIGKILL before granting access to memory reserves
         * in order to prevent the OOM victim from depleting the memory
         * reserves from the user space under its control.
         */
	do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
	mark_oom_victim(victim);
	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
		task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
		K(get_mm_counter(victim->mm, MM_ANONPAGES)),
		K(get_mm_counter(victim->mm, MM_FILEPAGES)),
		K(get_mm_counter(victim->mm, MM_SHMEMPAGES)));
	task_unlock(victim);

	/*
         * Kill all user processes sharing victim->mm in other thread groups, if
         * any.  They don't get access to memory reserves, though, to avoid
         * depletion of all memory.  This prevents mm->mmap_sem livelock when an
         * oom killed thread cannot exit because it requires the semaphore and
         * its contended by another thread trying to allocate memory itself.
         * That thread will now get access to memory reserves since it has a
         * pending fatal signal.
         */
	rcu_read_lock();
	for_each_process(p) {
		if (!process_shares_mm(p, mm))
			continue;
		if (same_thread_group(p, victim))
			continue;
		if (is_global_init(p)) {
			can_oom_reap = false;
			set_bit(MMF_OOM_SKIP, &mm->flags);
			pr_info("oom killer %d (%s) has mm pinned by %d (%s)\n",
					task_pid_nr(victim), victim->comm,
					task_pid_nr(p), p->comm);
			continue;
		}
		/*
                 * No use_mm() user needs to read from the userspace so we are
                 * ok to reap it.
                 */
		if (unlikely(p->flags & PF_KTHREAD))
			continue;
		do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
	}
	rcu_read_unlock();

	if (can_oom_reap)
		wake_oom_reaper(victim);

	mmdrop(mm);
	put_task_struct(victim);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
246
47.67%
10
20.83%
Michal Hocko
90
17.44%
9
18.75%
Oleg Nesterov
44
8.53%
7
14.58%
Tetsuo Handa
23
4.46%
3
6.25%
Vladimir Davydov
21
4.07%
2
4.17%
Andrea Arcangeli
17
3.29%
1
2.08%
Jerome Marchand
13
2.52%
1
2.08%
Konstantin Khlebnikov
13
2.52%
1
2.08%
Nicholas Piggin
12
2.33%
2
4.17%
Kurt Garloff
12
2.33%
1
2.08%
Linus Torvalds
6
1.16%
2
4.17%
Chen Jie
4
0.78%
1
2.08%
Pavel Emelyanov
3
0.58%
1
2.08%
Motohiro Kosaki
3
0.58%
1
2.08%
Matthias Kaehlcke
3
0.58%
1
2.08%
Johannes Weiner
3
0.58%
2
4.17%
Vegard Nossum
1
0.19%
1
2.08%
Wang Long
1
0.19%
1
2.08%
Andrew Morton
1
0.19%
1
2.08%
Total
516
100.00%
48
100.00%

#undef K

/*
 * Determines whether the kernel must panic because of the panic_on_oom sysctl.
 */


static void check_panic_on_oom(struct oom_control *oc,
			       enum oom_constraint constraint)
{
	if (likely(!sysctl_panic_on_oom))
		return;
	if (sysctl_panic_on_oom != 2) {
		/*
                 * panic_on_oom == 1 only affects CONSTRAINT_NONE, the kernel
                 * does not panic for cpuset, mempolicy, or memcg allocation
                 * failures.
                 */
		if (constraint != CONSTRAINT_NONE)
			return;
	}
	/* Do not panic for oom kills triggered by sysrq */
	if (is_sysrq_oom(oc))
		return;
	dump_header(oc, NULL);
	panic("Out of memory: %s panic_on_oom is enabled\n",
		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
59
85.51%
3
50.00%
Oleg Nesterov
6
8.70%
1
16.67%
Yaowei Bai
3
4.35%
1
16.67%
Vladimir Davydov
1
1.45%
1
16.67%
Total
69
100.00%
6
100.00%

static BLOCKING_NOTIFIER_HEAD(oom_notify_list);



int register_oom_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&oom_notify_list, nb);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin Schwidefsky
19
100.00%
1
100.00%
Total
19
100.00%
1
100.00%

EXPORT_SYMBOL_GPL(register_oom_notifier);



int unregister_oom_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&oom_notify_list, nb);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin Schwidefsky
19
100.00%
1
100.00%
Total
19
100.00%
1
100.00%

EXPORT_SYMBOL_GPL(unregister_oom_notifier);

/**
 * out_of_memory - kill the "best" process when we run out of memory
 * @oc: pointer to struct oom_control
 *
 * If we run out of memory, we have the choice between either
 * killing a random task (bad), letting the system crash (worse)
 * OR try to be smart about which process to kill. Note that we
 * don't have to be perfect here, we just have to be good.
 */


bool out_of_memory(struct oom_control *oc)
{
	unsigned long freed = 0;
	enum oom_constraint constraint = CONSTRAINT_NONE;

	if (oom_killer_disabled)
		return false;

	if (!is_memcg_oom(oc)) {
		blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
		if (freed > 0)
			/* Got some memory back in the last second. */
			return true;
	}

	/*
         * If current has a pending SIGKILL or is exiting, then automatically
         * select it.  The goal is to allow it to allocate so that it may
         * quickly exit and free its memory.
         */
	if (task_will_free_mem(current)) {
		mark_oom_victim(current);
		wake_oom_reaper(current);
		return true;
	}

	/*
         * The OOM killer does not compensate for IO-less reclaim.
         * pagefault_out_of_memory lost its gfp context so we have to
         * make sure exclude 0 mask - all other users should have at least
         * ___GFP_DIRECT_RECLAIM to get here.
         */
	if (oc->gfp_mask && !(oc->gfp_mask & __GFP_FS))
		return true;

	/*
         * Check if there were limitations on the allocation (only relevant for
         * NUMA and memcg) that may require different handling.
         */
	constraint = constrained_alloc(oc);
	if (constraint != CONSTRAINT_MEMORY_POLICY)
		oc->nodemask = NULL;
	check_panic_on_oom(oc, constraint);

	if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task &&
	    current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) &&
	    current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
		get_task_struct(current);
		oc->chosen = current;
		oom_kill_process(oc, "Out of memory (oom_kill_allocating_task)");
		return true;
	}

	select_bad_process(oc);
	/* Found nothing?!?! Either we hang forever, or we panic. */
	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
		dump_header(oc, NULL);
		panic("Out of memory and no killable processes...\n");
	}
	if (oc->chosen && oc->chosen != (void *)-1UL) {
		oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" :
				 "Memory cgroup out of memory");
		/*
                 * Give the killed process a good chance to exit before trying
                 * to allocate memory again.
                 */
		schedule_timeout_killable(1);
	}
	return !!oc->chosen;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
119
43.75%
13
41.94%
Vladimir Davydov
51
18.75%
1
3.23%
Nicholas Piggin
32
11.76%
1
3.23%
Michal Hocko
29
10.66%
6
19.35%
Motohiro Kosaki
13
4.78%
2
6.45%
Johannes Weiner
10
3.68%
2
6.45%
Yaowei Bai
4
1.47%
1
3.23%
Rusty Russell
4
1.47%
1
3.23%
Andrew Morton
3
1.10%
1
3.23%
Linus Torvalds
3
1.10%
1
3.23%
Oleg Nesterov
3
1.10%
1
3.23%
Andrea Arcangeli
1
0.37%
1
3.23%
Total
272
100.00%
31
100.00%

/*
 * The pagefault handler calls here because it is out of memory, so kill a
 * memory-hogging task. If oom_lock is held by somebody else, a parallel oom
 * killing is already in progress so do nothing.
 */


void pagefault_out_of_memory(void)
{
	struct oom_control oc = {
		.zonelist = NULL,
		.nodemask = NULL,
		.memcg = NULL,
		.gfp_mask = 0,
		.order = 0,
        };

	if (mem_cgroup_oom_synchronize(true))
		return;

	if (!mutex_trylock(&oom_lock))
		return;
	out_of_memory(&oc);
	mutex_unlock(&oom_lock);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
42
61.76%
3
37.50%
Johannes Weiner
16
23.53%
3
37.50%
Vladimir Davydov
5
7.35%
1
12.50%
Michal Hocko
5
7.35%
1
12.50%
Total
68
100.00%
8
100.00%

Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
Michal Hocko
1078
30.51%
36
19.78%
David Rientjes
1078
30.51%
49
26.92%
Vladimir Davydov
375
10.61%
5
2.75%
Motohiro Kosaki
159
4.50%
9
4.95%
Oleg Nesterov
154
4.36%
9
4.95%
Yang Shi
76
2.15%
1
0.55%
Tetsuo Handa
71
2.01%
9
4.95%
Martin Schwidefsky
59
1.67%
1
0.55%
Kamezawa Hiroyuki
49
1.39%
3
1.65%
Johannes Weiner
46
1.30%
5
2.75%
Nicholas Piggin
46
1.30%
3
1.65%
Linus Torvalds (pre-git)
40
1.13%
1
0.55%
Yaowei Bai
32
0.91%
1
0.55%
Kirill A. Shutemov
30
0.85%
5
2.75%
Christoph Lameter
28
0.79%
2
1.10%
Mel Gorman
22
0.62%
2
1.10%
Roman Gushchin
21
0.59%
1
0.55%
Andrea Arcangeli
18
0.51%
1
0.55%
Wang Nan
13
0.37%
1
0.55%
Jerome Marchand
13
0.37%
1
0.55%
Konstantin Khlebnikov
13
0.37%
1
0.55%
Kurt Garloff
12
0.34%
1
0.55%
Ingo Molnar
11
0.31%
4
2.20%
Andrew Morton
9
0.25%
3
1.65%
Linus Torvalds
9
0.25%
3
1.65%
Alexey Dobriyan
6
0.17%
2
1.10%
Tim Schmielau
6
0.17%
2
1.10%
Pavel Emelyanov
6
0.17%
2
1.10%
Vlastimil Babka
6
0.17%
1
0.55%
Eric W. Biedermann
6
0.17%
1
0.55%
David Howells
5
0.14%
2
1.10%
Daisuke Nishimura
5
0.14%
1
0.55%
Rusty Russell
4
0.11%
1
0.55%
Sha Zhengju
4
0.11%
1
0.55%
Chen Jie
4
0.11%
1
0.55%
Paul Jackson
3
0.08%
1
0.55%
Matthias Kaehlcke
3
0.08%
1
0.55%
Tejun Heo
3
0.08%
1
0.55%
Geert Uytterhoeven
2
0.06%
1
0.55%
Vegard Nossum
2
0.06%
1
0.55%
Lai Jiangshan
1
0.03%
1
0.55%
Cyrill V. Gorcunov
1
0.03%
1
0.55%
Wang Long
1
0.03%
1
0.55%
Mike Rapoport
1
0.03%
1
0.55%
Frantisek Hrbata
1
0.03%
1
0.55%
Paul Gortmaker
1
0.03%
1
0.55%
Total
3533
100.00%
182
100.00%
Directory: mm

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.