summaryrefslogtreecommitdiffstats
path: root/mm/oom_kill.c
blob: 6969cfb33901e1e21defc992eda34cd0d6363264 (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
/*
 *  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...
 *
 *  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/sched.h>
#include <linux/swap.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/cpuset.h>
#include <linux/module.h>
#include <linux/notifier.h>

int sysctl_panic_on_oom;
/* #define DEBUG */

/**
 * badness - calculate a numeric value for how bad this task has been
 * @p: task struct of which task we should calculate
 * @uptime: current uptime in seconds
 *
 * The formula used is relatively simple and documented inline in the
 * function. The main rationale is that we want to select a good task
 * to kill when we run out of memory.
 *
 * Good in this context means that:
 * 1) we lose the minimum amount of work done
 * 2) we recover a large amount of memory
 * 3) we don't kill anything innocent of eating tons of memory
 * 4) we want to kill the minimum amount of processes (one)
 * 5) we try to kill the process the user expects us to kill, this
 *    algorithm has been meticulously tuned to meet the principle
 *    of least surprise ... (be careful when you change it)
 */

unsigned long badness(struct task_struct *p, unsigned long uptime)
{
	unsigned long points, cpu_time, run_time, s;
	struct mm_struct *mm;
	struct task_struct *child;

	task_lock(p);
	mm = p->mm;
	if (!mm) {
		task_unlock(p);
		return 0;
	}

	/*
	 * swapoff can easily use up all memory, so kill those first.
	 */
	if (p->flags & PF_SWAPOFF)
		return ULONG_MAX;

	/*
	 * The memory size of the process is the basis for the badness.
	 */
	points = mm->total_vm;

	/*
	 * After this unlock we can no longer dereference local variable `mm'
	 */
	task_unlock(p);

	/*
	 * Processes which fork a lot of child processes are likely
	 * a good choice. We add half the vmsize of the children if they
	 * have an own mm. This prevents forking servers to flood the
	 * machine with an endless amount of children. In case a single
	 * child is eating the vast majority of memory, adding only half
	 * to the parents will make the child our kill candidate of choice.
	 */
	list_for_each_entry(child, &p->children, sibling) {
		task_lock(child);
		if (child->mm != mm && child->mm)
			points += child->mm->total_vm/2 + 1;
		task_unlock(child);
	}

	/*
	 * CPU time is in tens of seconds and run time is in thousands
         * of seconds. There is no particular reason for this other than
         * that it turned out to work very well in practice.
	 */
	cpu_time = (cputime_to_jiffies(p->utime) + cputime_to_jiffies(p->stime))
		>> (SHIFT_HZ + 3);

	if (uptime >= p->start_time.tv_sec)
		run_time = (uptime - p->start_time.tv_sec) >> 10;
	else
		run_time = 0;

	s = int_sqrt(cpu_time);
	if (s)
		points /= s;
	s = int_sqrt(int_sqrt(run_time));
	if (s)
		points /= s;

	/*
	 * Niced processes are most likely less important, so double
	 * their badness points.
	 */
	if (task_nice(p) > 0)
		points *= 2;

	/*
	 * Superuser processes are usually more important, so we make it
	 * less likely that we kill those.
	 */
	if (cap_t(p->cap_effective) & CAP_TO_MASK(CAP_SYS_ADMIN) ||
				p->uid == 0 || p->euid == 0)
		points /= 4;

	/*
	 * We don't want to kill a process with direct hardware access.
	 * Not only could that mess up the hardware, but usually users
	 * tend to only have this flag set on applications they think
	 * of as important.
	 */
	if (cap_t(p->cap_effective) & CAP_TO_MASK(CAP_SYS_RAWIO))
		points /= 4;

	/*
	 * If p's nodes don't overlap ours, it may still help to kill p
	 * because p may have allocated or otherwise mapped memory on
	 * this node before. However it will be less likely.
	 */
	if (!cpuset_excl_nodes_overlap(p))
		points /= 8;

	/*
	 * Adjust the score by oomkilladj.
	 */
	if (p->oomkilladj) {
		if (p->oomkilladj > 0)
			points <<= p->oomkilladj;
		else
			points >>= -(p->oomkilladj);
	}

#ifdef DEBUG
	printk(KERN_DEBUG "OOMkill: task %d (%s) got %d points\n",
	p->pid, p->comm, points);
#endif
	return points;
}

/*
 * Types of limitations to the nodes from which allocations may occur
 */
#define CONSTRAINT_NONE 1
#define CONSTRAINT_MEMORY_POLICY 2
#define CONSTRAINT_CPUSET 3

/*
 * Determine the type of allocation constraint.
 */
static inline int constrained_alloc(struct zonelist *zonelist, gfp_t gfp_mask)
{
#ifdef CONFIG_NUMA
	struct zone **z;
	nodemask_t nodes;
	int node;
	/* node has memory ? */
	for_each_online_node(node)
		if (NODE_DATA(node)->node_present_pages)
			node_set(node, nodes);

	for (z = zonelist->zones; *z; z++)
		if (cpuset_zone_allowed_softwall(*z, gfp_mask))
			node_clear(zone_to_nid(*z), nodes);
		else
			return CONSTRAINT_CPUSET;

	if (!nodes_empty(nodes))
		return CONSTRAINT_MEMORY_POLICY;
#endif

	return CONSTRAINT_NONE;
}

/*
 * 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 long *ppoints)
{
	struct task_struct *g, *p;
	struct task_struct *chosen = NULL;
	struct timespec uptime;
	*ppoints = 0;

	do_posix_clock_monotonic_gettime(&uptime);
	do_each_thread(g, p) {
		unsigned long points;

		/*
		 * skip kernel threads and tasks which have already released
		 * their mm.
		 */
		if (!p->mm)
			continue;
		/* skip the init task */
		if (is_init(p))
			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))
			return ERR_PTR(-1UL);

		/*
		 * This is in the process of releasing memory so wait for it
		 * to finish before killing some other task by mistake.
		 *
		 * However, if p is the current task, we allow the 'kill' to
		 * go ahead if it is exiting: this will simply set TIF_MEMDIE,
		 * which will allow it to gain access to memory reserves in
		 * the process of exiting and releasing its resources.
		 * Otherwise we could get an easy OOM deadlock.
		 */
		if (p->flags & PF_EXITING) {
			if (p != current)
				return ERR_PTR(-1UL);

			chosen = p;
			*ppoints = ULONG_MAX;
		}

		if (p->oomkilladj == OOM_DISABLE)
			continue;

		points = badness(p, uptime.tv_sec);
		if (points > *ppoints || !chosen) {
			chosen = p;
			*ppoints = points;
		}
	} while_each_thread(g, p);

	return chosen;
}

/**
 * Send SIGKILL to the selected  process irrespective of  CAP_SYS_RAW_IO
 * flag though it's unlikely that  we select a process with CAP_SYS_RAW_IO
 * set.
 */
static void __oom_kill_task(struct task_struct *p, int verbose)
{
	if (is_init(p)) {
		WARN_ON(1);
		printk(KERN_WARNING "tried to kill init!\n");
		return;
	}

	if (!p->mm) {
		WARN_ON(1);
		printk(KERN_WARNING "tried to kill an mm-less task!\n");
		return;
	}

	if (verbose)
		printk(KERN_ERR "Killed process %d (%s)\n", p->pid, p->comm);

	/*
	 * We give our sacrificial lamb high priority and access to
	 * all the memory it needs. That way it should be able to
	 * exit() and clear out its resources quickly...
	 */
	p->time_slice = HZ;
	set_tsk_thread_flag(p, TIF_MEMDIE);

	force_sig(SIGKILL, p);
}

static int oom_kill_task(struct task_struct *p)
{
	struct mm_struct *mm;
	struct task_struct *g, *q;

	mm = p->mm;

	/* WARNING: mm may not be dereferenced since we did not obtain its
	 * value from get_task_mm(p).  This is OK since all we need to do is
	 * compare mm to q->mm below.
	 *
	 * Furthermore, even if mm contains a non-NULL value, p->mm may
	 * change to NULL at any time since we do not hold task_lock(p).
	 * However, this is of no concern to us.
	 */

	if (mm == NULL)
		return 1;

	/*
	 * Don't kill the process if any threads are set to OOM_DISABLE
	 */
	do_each_thread(g, q) {
		if (q->mm == mm && p->oomkilladj == OOM_DISABLE)
			return 1;
	} while_each_thread(g, q);

	__oom_kill_task(p, 1);

	/*
	 * kill all processes that share the ->mm (i.e. all threads),
	 * but are in a different thread group. Don't let them have access
	 * to memory reserves though, otherwise we might deplete all memory.
	 */
	do_each_thread(g, q) {
		if (q->mm == mm && q->tgid != p->tgid)
			force_sig(SIGKILL, p);
	} while_each_thread(g, q);

	return 0;
}

static int oom_kill_process(struct task_struct *p, unsigned long points,
		const char *message)
{
	struct task_struct *c;
	struct list_head *tsk;

	/*
	 * 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) {
		__oom_kill_task(p, 0);
		return 0;
	}

	printk(KERN_ERR "%s: kill process %d (%s) score %li or a child\n",
					message, p->pid, p->comm, points);

	/* Try to kill a child first */
	list_for_each(tsk, &p->children) {
		c = list_entry(tsk, struct task_struct, sibling);
		if (c->mm == p->mm)
			continue;
		if (!oom_kill_task(c))
			return 0;
	}
	return oom_kill_task(p);
}

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);

/**
 * out_of_memory - kill the "best" process when we run out of memory
 *
 * 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)
{
	struct task_struct *p;
	unsigned long points = 0;
	unsigned long freed = 0;

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

	if (printk_ratelimit()) {
		printk(KERN_WARNING "%s invoked oom-killer: "
			"gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
			current->comm, gfp_mask, order, current->oomkilladj);
		dump_stack();
		show_mem();
	}

	cpuset_lock();
	read_lock(&tasklist_lock);

	/*
	 * Check if there were limitations on the allocation (only relevant for
	 * NUMA) that may require different handling.
	 */
	switch (constrained_alloc(zonelist, gfp_mask)) {
	case CONSTRAINT_MEMORY_POLICY:
		oom_kill_process(current, points,
				"No available memory (MPOL_BIND)");
		break;

	case CONSTRAINT_CPUSET:
		oom_kill_process(current, points,
				"No available memory in cpuset");
		break;

	case CONSTRAINT_NONE:
		if (sysctl_panic_on_oom)
			panic("out of memory. panic_on_oom is selected\n");
retry:
		/*
		 * Rambo mode: Shoot down a process and hope it solves whatever
		 * issues we may have.
		 */
		p = select_bad_process(&points);

		if (PTR_ERR(p) == -1UL)
			goto out;

		/* Found nothing?!?! Either we hang forever, or we panic. */
		if (!p) {
			read_unlock(&tasklist_lock);
			cpuset_unlock();
			panic("Out of memory and no killable processes...\n");
		}

		if (oom_kill_process(p, points, "Out of memory"))
			goto retry;

		break;
	}

out:
	read_unlock(&tasklist_lock);
	cpuset_unlock();

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