aboutsummaryrefslogtreecommitdiff
path: root/mm/oom_kill.c
blob: ed0e19677360fa55f62e3944208e82cab7eeacc8 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
/*
 *  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/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>

#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;
static DEFINE_SPINLOCK(zone_scan_lock);

/*
 * compare_swap_oom_score_adj() - compare and swap current's oom_score_adj
 * @old_val: old oom_score_adj for compare
 * @new_val: new oom_score_adj for swap
 *
 * Sets the oom_score_adj value for current to @new_val iff its present value is
 * @old_val.  Usually used to reinstate a previous value to prevent racing with
 * userspacing tuning the value in the interim.
 */
void compare_swap_oom_score_adj(int old_val, int new_val)
{
	struct sighand_struct *sighand = current->sighand;

	spin_lock_irq(&sighand->siglock);
	if (current->signal->oom_score_adj == old_val)
		current->signal->oom_score_adj = new_val;
	trace_oom_score_adj_update(current);
	spin_unlock_irq(&sighand->siglock);
}

/**
 * test_set_oom_score_adj() - set current's oom_score_adj and return old value
 * @new_val: new oom_score_adj value
 *
 * Sets the oom_score_adj value for current to @new_val with proper
 * synchronization and returns the old value.  Usually used to temporarily
 * set a value, save the old value in the caller, and then reinstate it later.
 */
int test_set_oom_score_adj(int new_val)
{
	struct sighand_struct *sighand = current->sighand;
	int old_val;

	spin_lock_irq(&sighand->siglock);
	old_val = current->signal->oom_score_adj;
	current->signal->oom_score_adj = new_val;
	trace_oom_score_adj_update(current);
	spin_unlock_irq(&sighand->siglock);

	return old_val;
}

#ifdef CONFIG_NUMA
/**
 * has_intersects_mems_allowed() - check task eligiblity for kill
 * @tsk: 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 *tsk,
					const nodemask_t *mask)
{
	struct task_struct *start = tsk;

	do {
		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.
			 */
			if (mempolicy_nodemask_intersects(tsk, mask))
				return true;
		} else {
			/*
			 * This is not a mempolicy constrained oom, so only
			 * check the mems of tsk's cpuset.
			 */
			if (cpuset_mems_allowed_intersects(current, tsk))
				return true;
		}
	} while_each_thread(start, tsk);

	return false;
}
#else
static bool has_intersects_mems_allowed(struct task_struct *tsk,
					const nodemask_t *mask)
{
	return true;
}
#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 = p;

	do {
		task_lock(t);
		if (likely(t->mm))
			return t;
		task_unlock(t);
	} while_each_thread(p, t);

	return NULL;
}

/* return true if the task is not adequate as candidate victim task. */
static bool oom_unkillable_task(struct task_struct *p,
		const 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;
}

/**
 * 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
 *
 * 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)
{
	unsigned long points;

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

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

	if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
		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) + p->mm->nr_ptes +
		 get_mm_counter(p->mm, MM_SWAPENTS);
	task_unlock(p);

	/*
	 * Root processes get 3% bonus, just like the __vm_enough_memory()
	 * implementation used by LSMs.
	 */
	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
		points -= 30 * totalpages / 1000;

	/*
	 * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may
	 * either completely disable oom killing or always prefer a certain
	 * task.
	 */
	points += p->signal->oom_score_adj * totalpages / 1000;

	/*
	 * 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 ? points : 1;
}

/*
 * Determine the type of allocation constraint.
 */
#ifdef CONFIG_NUMA
static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
				gfp_t gfp_mask, nodemask_t *nodemask,
				unsigned long *totalpages)
{
	struct zone *zone;
	struct zoneref *z;
	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
	bool cpuset_limited = false;
	int nid;

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

	if (!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 (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 (nodemask && !nodes_subset(node_states[N_HIGH_MEMORY], *nodemask)) {
		*totalpages = total_swap_pages;
		for_each_node_mask(nid, *nodemask)
			*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, zonelist,
			high_zoneidx, nodemask)
		if (!cpuset_zone_allowed_softwall(zone, gfp_mask))
			cpuset_limited = true;

	if (cpuset_limited) {
		*totalpages = total_swap_pages;
		for_each_node_mask(nid, cpuset_current_mems_allowed)
			*totalpages += node_spanned_pages(nid);
		return CONSTRAINT_CPUSET;
	}
	return CONSTRAINT_NONE;
}
#else
static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
				gfp_t gfp_mask, nodemask_t *nodemask,
				unsigned long *totalpages)
{
	*totalpages = totalram_pages + total_swap_pages;
	return CONSTRAINT_NONE;
}
#endif

/*
 * Simple selection loop. We chose the process with the highest
 * number of 'points'. We expect the caller will lock the tasklist.
 *
 * (not docbooked, we don't want this one cluttering up the manual)
 */
static struct task_struct *select_bad_process(unsigned int *ppoints,
		unsigned long totalpages, struct mem_cgroup *memcg,
		const nodemask_t *nodemask, bool force_kill)
{
	struct task_struct *g, *p;
	struct task_struct *chosen = NULL;
	unsigned long chosen_points = 0;

	do_each_thread(g, p) {
		unsigned int points;

		if (p->exit_state)
			continue;
		if (oom_unkillable_task(p, memcg, nodemask))
			continue;

		/*
		 * This task already has access to memory reserves and is
		 * being killed. Don't allow any other task access to the
		 * memory reserve.
		 *
		 * Note: this may have a chance of deadlock if it gets
		 * blocked waiting for another task which itself is waiting
		 * for memory. Is there a better alternative?
		 */
		if (test_tsk_thread_flag(p, TIF_MEMDIE)) {
			if (unlikely(frozen(p)))
				__thaw_task(p);
			if (!force_kill)
				return ERR_PTR(-1UL);
		}
		if (!p->mm)
			continue;

		if (p->flags & PF_EXITING) {
			/*
			 * If p is the current task and is in the process of
			 * releasing memory, we allow the "kill" to set
			 * TIF_MEMDIE, which will allow it to gain access to
			 * memory reserves.  Otherwise, it may stall forever.
			 *
			 * The loop isn't broken here, however, in case other
			 * threads are found to have already been oom killed.
			 */
			if (p == current) {
				chosen = p;
				chosen_points = ULONG_MAX;
			} else if (!force_kill) {
				/*
				 * If this task is not being ptraced on exit,
				 * then wait for it to finish before killing
				 * some other task unnecessarily.
				 */
				if (!(p->group_leader->ptrace & PT_TRACE_EXIT))
					return ERR_PTR(-1UL);
			}
		}

		points = oom_badness(p, memcg, nodemask, totalpages);
		if (points > chosen_points) {
			chosen = p;
			chosen_points = points;
		}
	} while_each_thread(g, p);

	*ppoints = chosen_points * 1000 / totalpages;
	return chosen;
}

/**
 * dump_tasks - dump current memory state of all system tasks
 * @mem: 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, cpu, oom_adj
 * value, oom_score_adj value, and name.
 *
 * Call with tasklist_lock read-locked.
 */
static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
	struct task_struct *p;
	struct task_struct *task;

	pr_info("[ pid ]   uid  tgid total_vm      rss cpu oom_adj oom_score_adj name\n");
	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 %3u     %3d         %5d %s\n",
			task->pid, from_kuid(&init_user_ns, task_uid(task)),
			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
			task_cpu(task), task->signal->oom_adj,
			task->signal->oom_score_adj, task->comm);
		task_unlock(task);
	}
}

static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
			struct mem_cgroup *memcg, const nodemask_t *nodemask)
{
	task_lock(current);
	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
		"oom_adj=%d, oom_score_adj=%d\n",
		current->comm, gfp_mask, order, current->signal->oom_adj,
		current->signal->oom_score_adj);
	cpuset_print_task_mems_allowed(current);
	task_unlock(current);
	dump_stack();
	mem_cgroup_print_oom_info(memcg, p);
	show_mem(SHOW_MEM_FILTER_NODES);
	if (sysctl_oom_dump_tasks)
		dump_tasks(memcg, nodemask);
}

#define K(x) ((x) << (PAGE_SHIFT-10))
static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
			     unsigned int points, unsigned long totalpages,
			     struct mem_cgroup *memcg, nodemask_t *nodemask,
			     const char *message)
{
	struct task_struct *victim = p;
	struct task_struct *child;
	struct task_struct *t = p;
	struct mm_struct *mm;
	unsigned int victim_points = 0;
	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
					      DEFAULT_RATELIMIT_BURST);

	/*
	 * If the task is already exiting, don't alarm the sysadmin or kill
	 * its children or threads, just set TIF_MEMDIE so it can die quickly
	 */
	if (p->flags & PF_EXITING) {
		set_tsk_thread_flag(p, TIF_MEMDIE);
		return;
	}

	if (__ratelimit(&oom_rs))
		dump_header(p, gfp_mask, order, memcg, nodemask);

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

	/*
	 * 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.
	 */
	do {
		list_for_each_entry(child, &t->children, sibling) {
			unsigned int child_points;

			if (child->mm == p->mm)
				continue;
			/*
			 * oom_badness() returns 0 if the thread is unkillable
			 */
			child_points = oom_badness(child, memcg, nodemask,
								totalpages);
			if (child_points > victim_points) {
				victim = child;
				victim_points = child_points;
			}
		}
	} while_each_thread(p, t);

	victim = find_lock_task_mm(victim);
	if (!victim)
		return;

	/* mm cannot safely be dereferenced after task_unlock(victim) */
	mm = victim->mm;
	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-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)));
	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.
	 */
	for_each_process(p)
		if (p->mm == mm && !same_thread_group(p, victim) &&
		    !(p->flags & PF_KTHREAD)) {
			if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
				continue;

			task_lock(p);	/* Protect ->comm from prctl() */
			pr_err("Kill process %d (%s) sharing same memory\n",
				task_pid_nr(p), p->comm);
			task_unlock(p);
			do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
		}

	set_tsk_thread_flag(victim, TIF_MEMDIE);
	do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
}
#undef K

/*
 * Determines whether the kernel must panic because of the panic_on_oom sysctl.
 */
static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
				int order, const nodemask_t *nodemask)
{
	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;
	}
	read_lock(&tasklist_lock);
	dump_header(NULL, gfp_mask, order, NULL, nodemask);
	read_unlock(&tasklist_lock);
	panic("Out of memory: %s panic_on_oom is enabled\n",
		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
}

#ifdef CONFIG_CGROUP_MEM_RES_CTLR
void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
			      int order)
{
	unsigned long limit;
	unsigned int points = 0;
	struct task_struct *p;

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

	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
	limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
	read_lock(&tasklist_lock);
	p = select_bad_process(&points, limit, memcg, NULL, false);
	if (p && PTR_ERR(p) != -1UL)
		oom_kill_process(p, gfp_mask, order, points, limit, memcg, NULL,
				 "Memory cgroup out of memory");
	read_unlock(&tasklist_lock);
}
#endif

static BLOCKING_NOTIFIER_HEAD(oom_notify_list);

int register_oom_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&oom_notify_list, nb);
}
EXPORT_SYMBOL_GPL(register_oom_notifier);

int unregister_oom_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&oom_notify_list, nb);
}
EXPORT_SYMBOL_GPL(unregister_oom_notifier);

/*
 * Try to acquire the OOM killer lock for the zones in zonelist.  Returns zero
 * if a parallel OOM killing is already taking place that includes a zone in
 * the zonelist.  Otherwise, locks all zones in the zonelist and returns 1.
 */
int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
{
	struct zoneref *z;
	struct zone *zone;
	int ret = 1;

	spin_lock(&zone_scan_lock);
	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
		if (zone_is_oom_locked(zone)) {
			ret = 0;
			goto out;
		}
	}

	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
		/*
		 * Lock each zone in the zonelist under zone_scan_lock so a
		 * parallel invocation of try_set_zonelist_oom() doesn't succeed
		 * when it shouldn't.
		 */
		zone_set_flag(zone, ZONE_OOM_LOCKED);
	}

out:
	spin_unlock(&zone_scan_lock);
	return ret;
}

/*
 * Clears the ZONE_OOM_LOCKED flag for all zones in the zonelist so that failed
 * allocation attempts with zonelists containing them may now recall the OOM
 * killer, if necessary.
 */
void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
{
	struct zoneref *z;
	struct zone *zone;

	spin_lock(&zone_scan_lock);
	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
		zone_clear_flag(zone, ZONE_OOM_LOCKED);
	}
	spin_unlock(&zone_scan_lock);
}

/*
 * Try to acquire the oom killer lock for all system zones.  Returns zero if a
 * parallel oom killing is taking place, otherwise locks all zones and returns
 * non-zero.
 */
static int try_set_system_oom(void)
{
	struct zone *zone;
	int ret = 1;

	spin_lock(&zone_scan_lock);
	for_each_populated_zone(zone)
		if (zone_is_oom_locked(zone)) {
			ret = 0;
			goto out;
		}
	for_each_populated_zone(zone)
		zone_set_flag(zone, ZONE_OOM_LOCKED);
out:
	spin_unlock(&zone_scan_lock);
	return ret;
}

/*
 * Clears ZONE_OOM_LOCKED for all system zones so that failed allocation
 * attempts or page faults may now recall the oom killer, if necessary.
 */
static void clear_system_oom(void)
{
	struct zone *zone;

	spin_lock(&zone_scan_lock);
	for_each_populated_zone(zone)
		zone_clear_flag(zone, ZONE_OOM_LOCKED);
	spin_unlock(&zone_scan_lock);
}

/**
 * out_of_memory - kill the "best" process when we run out of memory
 * @zonelist: zonelist pointer
 * @gfp_mask: memory allocation flags
 * @order: amount of memory being requested as a power of 2
 * @nodemask: nodemask passed to page allocator
 * @force_kill: true if a task must be killed, even if others are exiting
 *
 * 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.
 */
void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
		int order, nodemask_t *nodemask, bool force_kill)
{
	const nodemask_t *mpol_mask;
	struct task_struct *p;
	unsigned long totalpages;
	unsigned long freed = 0;
	unsigned int points;
	enum oom_constraint constraint = CONSTRAINT_NONE;
	int killed = 0;

	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
	if (freed > 0)
		/* Got some memory back in the last second. */
		return;

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

	/*
	 * Check if there were limitations on the allocation (only relevant for
	 * NUMA) that may require different handling.
	 */
	constraint = constrained_alloc(zonelist, gfp_mask, nodemask,
						&totalpages);
	mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL;
	check_panic_on_oom(constraint, gfp_mask, order, mpol_mask);

	read_lock(&tasklist_lock);
	if (sysctl_oom_kill_allocating_task &&
	    !oom_unkillable_task(current, NULL, nodemask) &&
	    current->mm) {
		oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL,
				 nodemask,
				 "Out of memory (oom_kill_allocating_task)");
		goto out;
	}

	p = select_bad_process(&points, totalpages, NULL, mpol_mask,
			       force_kill);
	/* Found nothing?!?! Either we hang forever, or we panic. */
	if (!p) {
		dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
		read_unlock(&tasklist_lock);
		panic("Out of memory and no killable processes...\n");
	}
	if (PTR_ERR(p) != -1UL) {
		oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
				 nodemask, "Out of memory");
		killed = 1;
	}
out:
	read_unlock(&tasklist_lock);

	/*
	 * Give "p" a good chance of killing itself before we
	 * retry to allocate memory unless "p" is current
	 */
	if (killed && !test_thread_flag(TIF_MEMDIE))
		schedule_timeout_uninterruptible(1);
}

/*
 * The pagefault handler calls here because it is out of memory, so kill a
 * memory-hogging task.  If a populated zone has ZONE_OOM_LOCKED set, a parallel
 * oom killing is already in progress so do nothing.  If a task is found with
 * TIF_MEMDIE set, it has been killed so do nothing and allow it to exit.
 */
void pagefault_out_of_memory(void)
{
	if (try_set_system_oom()) {
		out_of_memory(NULL, 0, 0, NULL, false);
		clear_system_oom();
	}
	if (!test_thread_flag(TIF_MEMDIE))
		schedule_timeout_uninterruptible(1);
}