aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/taskstats.c
blob: 4a23517169a6495cf1aa1bc689137e1c38698c62 (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
/*
 * taskstats.c - Export per-task statistics to userland
 *
 * Copyright (C) Shailabh Nagar, IBM Corp. 2006
 *           (C) Balbir Singh,   IBM Corp. 2006
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 */

#include <linux/kernel.h>
#include <linux/taskstats_kern.h>
#include <linux/tsacct_kern.h>
#include <linux/delayacct.h>
#include <linux/cpumask.h>
#include <linux/percpu.h>
#include <linux/cgroupstats.h>
#include <linux/cgroup.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <net/genetlink.h>
#include <asm/atomic.h>

/*
 * Maximum length of a cpumask that can be specified in
 * the TASKSTATS_CMD_ATTR_REGISTER/DEREGISTER_CPUMASK attribute
 */
#define TASKSTATS_CPUMASK_MAXLEN	(100+6*NR_CPUS)

static DEFINE_PER_CPU(__u32, taskstats_seqnum) = { 0 };
static int family_registered;
struct kmem_cache *taskstats_cache;

static struct genl_family family = {
	.id		= GENL_ID_GENERATE,
	.name		= TASKSTATS_GENL_NAME,
	.version	= TASKSTATS_GENL_VERSION,
	.maxattr	= TASKSTATS_CMD_ATTR_MAX,
};

static struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1]
__read_mostly = {
	[TASKSTATS_CMD_ATTR_PID]  = { .type = NLA_U32 },
	[TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 },
	[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING },
	[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },};

static struct nla_policy
cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] __read_mostly = {
	[CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 },
};

struct listener {
	struct list_head list;
	pid_t pid;
	char valid;
};

struct listener_list {
	struct rw_semaphore sem;
	struct list_head list;
};
static DEFINE_PER_CPU(struct listener_list, listener_array);

enum actions {
	REGISTER,
	DEREGISTER,
	CPU_DONT_CARE
};

static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp,
				size_t size)
{
	struct sk_buff *skb;
	void *reply;

	/*
	 * If new attributes are added, please revisit this allocation
	 */
	skb = genlmsg_new(size, GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	if (!info) {
		int seq = get_cpu_var(taskstats_seqnum)++;
		put_cpu_var(taskstats_seqnum);

		reply = genlmsg_put(skb, 0, seq, &family, 0, cmd);
	} else
		reply = genlmsg_put_reply(skb, info, &family, 0, cmd);
	if (reply == NULL) {
		nlmsg_free(skb);
		return -EINVAL;
	}

	*skbp = skb;
	return 0;
}

/*
 * Send taskstats data in @skb to listener with nl_pid @pid
 */
static int send_reply(struct sk_buff *skb, pid_t pid)
{
	struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb));
	void *reply = genlmsg_data(genlhdr);
	int rc;

	rc = genlmsg_end(skb, reply);
	if (rc < 0) {
		nlmsg_free(skb);
		return rc;
	}

	return genlmsg_unicast(skb, pid);
}

/*
 * Send taskstats data in @skb to listeners registered for @cpu's exit data
 */
static void send_cpu_listeners(struct sk_buff *skb,
					struct listener_list *listeners)
{
	struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb));
	struct listener *s, *tmp;
	struct sk_buff *skb_next, *skb_cur = skb;
	void *reply = genlmsg_data(genlhdr);
	int rc, delcount = 0;

	rc = genlmsg_end(skb, reply);
	if (rc < 0) {
		nlmsg_free(skb);
		return;
	}

	rc = 0;
	down_read(&listeners->sem);
	list_for_each_entry(s, &listeners->list, list) {
		skb_next = NULL;
		if (!list_is_last(&s->list, &listeners->list)) {
			skb_next = skb_clone(skb_cur, GFP_KERNEL);
			if (!skb_next)
				break;
		}
		rc = genlmsg_unicast(skb_cur, s->pid);
		if (rc == -ECONNREFUSED) {
			s->valid = 0;
			delcount++;
		}
		skb_cur = skb_next;
	}
	up_read(&listeners->sem);

	if (skb_cur)
		nlmsg_free(skb_cur);

	if (!delcount)
		return;

	/* Delete invalidated entries */
	down_write(&listeners->sem);
	list_for_each_entry_safe(s, tmp, &listeners->list, list) {
		if (!s->valid) {
			list_del(&s->list);
			kfree(s);
		}
	}
	up_write(&listeners->sem);
}

static int fill_pid(pid_t pid, struct task_struct *tsk,
		struct taskstats *stats)
{
	int rc = 0;

	if (!tsk) {
		rcu_read_lock();
		tsk = find_task_by_vpid(pid);
		if (tsk)
			get_task_struct(tsk);
		rcu_read_unlock();
		if (!tsk)
			return -ESRCH;
	} else
		get_task_struct(tsk);

	memset(stats, 0, sizeof(*stats));
	/*
	 * Each accounting subsystem adds calls to its functions to
	 * fill in relevant parts of struct taskstsats as follows
	 *
	 *	per-task-foo(stats, tsk);
	 */

	delayacct_add_tsk(stats, tsk);

	/* fill in basic acct fields */
	stats->version = TASKSTATS_VERSION;
	stats->nvcsw = tsk->nvcsw;
	stats->nivcsw = tsk->nivcsw;
	bacct_add_tsk(stats, tsk);

	/* fill in extended acct fields */
	xacct_add_tsk(stats, tsk);

	/* Define err: label here if needed */
	put_task_struct(tsk);
	return rc;

}

static int fill_tgid(pid_t tgid, struct task_struct *first,
		struct taskstats *stats)
{
	struct task_struct *tsk;
	unsigned long flags;
	int rc = -ESRCH;

	/*
	 * Add additional stats from live tasks except zombie thread group
	 * leaders who are already counted with the dead tasks
	 */
	rcu_read_lock();
	if (!first)
		first = find_task_by_vpid(tgid);

	if (!first || !lock_task_sighand(first, &flags))
		goto out;

	if (first->signal->stats)
		memcpy(stats, first->signal->stats, sizeof(*stats));
	else
		memset(stats, 0, sizeof(*stats));

	tsk = first;
	do {
		if (tsk->exit_state)
			continue;
		/*
		 * Accounting subsystem can call its functions here to
		 * fill in relevant parts of struct taskstsats as follows
		 *
		 *	per-task-foo(stats, tsk);
		 */
		delayacct_add_tsk(stats, tsk);

		stats->nvcsw += tsk->nvcsw;
		stats->nivcsw += tsk->nivcsw;
	} while_each_thread(first, tsk);

	unlock_task_sighand(first, &flags);
	rc = 0;
out:
	rcu_read_unlock();

	stats->version = TASKSTATS_VERSION;
	/*
	 * Accounting subsystems can also add calls here to modify
	 * fields of taskstats.
	 */
	return rc;
}


static void fill_tgid_exit(struct task_struct *tsk)
{
	unsigned long flags;

	spin_lock_irqsave(&tsk->sighand->siglock, flags);
	if (!tsk->signal->stats)
		goto ret;

	/*
	 * Each accounting subsystem calls its functions here to
	 * accumalate its per-task stats for tsk, into the per-tgid structure
	 *
	 *	per-task-foo(tsk->signal->stats, tsk);
	 */
	delayacct_add_tsk(tsk->signal->stats, tsk);
ret:
	spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
	return;
}

static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd)
{
	struct listener_list *listeners;
	struct listener *s, *tmp;
	unsigned int cpu;
	cpumask_t mask = *maskp;

	if (!cpus_subset(mask, cpu_possible_map))
		return -EINVAL;

	if (isadd == REGISTER) {
		for_each_cpu_mask(cpu, mask) {
			s = kmalloc_node(sizeof(struct listener), GFP_KERNEL,
					 cpu_to_node(cpu));
			if (!s)
				goto cleanup;
			s->pid = pid;
			INIT_LIST_HEAD(&s->list);
			s->valid = 1;

			listeners = &per_cpu(listener_array, cpu);
			down_write(&listeners->sem);
			list_add(&s->list, &listeners->list);
			up_write(&listeners->sem);
		}
		return 0;
	}

	/* Deregister or cleanup */
cleanup:
	for_each_cpu_mask(cpu, mask) {
		listeners = &per_cpu(listener_array, cpu);
		down_write(&listeners->sem);
		list_for_each_entry_safe(s, tmp, &listeners->list, list) {
			if (s->pid == pid) {
				list_del(&s->list);
				kfree(s);
				break;
			}
		}
		up_write(&listeners->sem);
	}
	return 0;
}

static int parse(struct nlattr *na, cpumask_t *mask)
{
	char *data;
	int len;
	int ret;

	if (na == NULL)
		return 1;
	len = nla_len(na);
	if (len > TASKSTATS_CPUMASK_MAXLEN)
		return -E2BIG;
	if (len < 1)
		return -EINVAL;
	data = kmalloc(len, GFP_KERNEL);
	if (!data)
		return -ENOMEM;
	nla_strlcpy(data, na, len);
	ret = cpulist_parse(data, *mask);
	kfree(data);
	return ret;
}

static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
{
	struct nlattr *na, *ret;
	int aggr;

	aggr = (type == TASKSTATS_TYPE_PID)
			? TASKSTATS_TYPE_AGGR_PID
			: TASKSTATS_TYPE_AGGR_TGID;

	na = nla_nest_start(skb, aggr);
	if (!na)
		goto err;
	if (nla_put(skb, type, sizeof(pid), &pid) < 0)
		goto err;
	ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats));
	if (!ret)
		goto err;
	nla_nest_end(skb, na);

	return nla_data(ret);
err:
	return NULL;
}

static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
{
	int rc = 0;
	struct sk_buff *rep_skb;
	struct cgroupstats *stats;
	struct nlattr *na;
	size_t size;
	u32 fd;
	struct file *file;
	int fput_needed;

	na = info->attrs[CGROUPSTATS_CMD_ATTR_FD];
	if (!na)
		return -EINVAL;

	fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]);
	file = fget_light(fd, &fput_needed);
	if (!file)
		return 0;

	size = nla_total_size(sizeof(struct cgroupstats));

	rc = prepare_reply(info, CGROUPSTATS_CMD_NEW, &rep_skb,
				size);
	if (rc < 0)
		goto err;

	na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS,
				sizeof(struct cgroupstats));
	stats = nla_data(na);
	memset(stats, 0, sizeof(*stats));

	rc = cgroupstats_build(stats, file->f_dentry);
	if (rc < 0) {
		nlmsg_free(rep_skb);
		goto err;
	}

	rc = send_reply(rep_skb, info->snd_pid);

err:
	fput_light(file, fput_needed);
	return rc;
}

static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
{
	int rc = 0;
	struct sk_buff *rep_skb;
	struct taskstats *stats;
	size_t size;
	cpumask_t mask;

	rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], &mask);
	if (rc < 0)
		return rc;
	if (rc == 0)
		return add_del_listener(info->snd_pid, &mask, REGISTER);

	rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], &mask);
	if (rc < 0)
		return rc;
	if (rc == 0)
		return add_del_listener(info->snd_pid, &mask, DEREGISTER);

	/*
	 * Size includes space for nested attributes
	 */
	size = nla_total_size(sizeof(u32)) +
		nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);

	rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
	if (rc < 0)
		return rc;

	rc = -EINVAL;
	if (info->attrs[TASKSTATS_CMD_ATTR_PID]) {
		u32 pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]);
		stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid);
		if (!stats)
			goto err;

		rc = fill_pid(pid, NULL, stats);
		if (rc < 0)
			goto err;
	} else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) {
		u32 tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]);
		stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid);
		if (!stats)
			goto err;

		rc = fill_tgid(tgid, NULL, stats);
		if (rc < 0)
			goto err;
	} else
		goto err;

	return send_reply(rep_skb, info->snd_pid);
err:
	nlmsg_free(rep_skb);
	return rc;
}

static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
{
	struct signal_struct *sig = tsk->signal;
	struct taskstats *stats;

	if (sig->stats || thread_group_empty(tsk))
		goto ret;

	/* No problem if kmem_cache_zalloc() fails */
	stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);

	spin_lock_irq(&tsk->sighand->siglock);
	if (!sig->stats) {
		sig->stats = stats;
		stats = NULL;
	}
	spin_unlock_irq(&tsk->sighand->siglock);

	if (stats)
		kmem_cache_free(taskstats_cache, stats);
ret:
	return sig->stats;
}

/* Send pid data out on exit */
void taskstats_exit(struct task_struct *tsk, int group_dead)
{
	int rc;
	struct listener_list *listeners;
	struct taskstats *stats;
	struct sk_buff *rep_skb;
	size_t size;
	int is_thread_group;

	if (!family_registered)
		return;

	/*
	 * Size includes space for nested attributes
	 */
	size = nla_total_size(sizeof(u32)) +
		nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);

	is_thread_group = !!taskstats_tgid_alloc(tsk);
	if (is_thread_group) {
		/* PID + STATS + TGID + STATS */
		size = 2 * size;
		/* fill the tsk->signal->stats structure */
		fill_tgid_exit(tsk);
	}

	listeners = &__raw_get_cpu_var(listener_array);
	if (list_empty(&listeners->list))
		return;

	rc = prepare_reply(NULL, TASKSTATS_CMD_NEW, &rep_skb, size);
	if (rc < 0)
		return;

	stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, tsk->pid);
	if (!stats)
		goto err;

	rc = fill_pid(-1, tsk, stats);
	if (rc < 0)
		goto err;

	/*
	 * Doesn't matter if tsk is the leader or the last group member leaving
	 */
	if (!is_thread_group || !group_dead)
		goto send;

	stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tsk->tgid);
	if (!stats)
		goto err;

	memcpy(stats, tsk->signal->stats, sizeof(*stats));

send:
	send_cpu_listeners(rep_skb, listeners);
	return;
err:
	nlmsg_free(rep_skb);
}

static struct genl_ops taskstats_ops = {
	.cmd		= TASKSTATS_CMD_GET,
	.doit		= taskstats_user_cmd,
	.policy		= taskstats_cmd_get_policy,
};

static struct genl_ops cgroupstats_ops = {
	.cmd		= CGROUPSTATS_CMD_GET,
	.doit		= cgroupstats_user_cmd,
	.policy		= cgroupstats_cmd_get_policy,
};

/* Needed early in initialization */
void __init taskstats_init_early(void)
{
	unsigned int i;

	taskstats_cache = KMEM_CACHE(taskstats, SLAB_PANIC);
	for_each_possible_cpu(i) {
		INIT_LIST_HEAD(&(per_cpu(listener_array, i).list));
		init_rwsem(&(per_cpu(listener_array, i).sem));
	}
}

static int __init taskstats_init(void)
{
	int rc;

	rc = genl_register_family(&family);
	if (rc)
		return rc;

	rc = genl_register_ops(&family, &taskstats_ops);
	if (rc < 0)
		goto err;

	rc = genl_register_ops(&family, &cgroupstats_ops);
	if (rc < 0)
		goto err_cgroup_ops;

	family_registered = 1;
	printk("registered taskstats version %d\n", TASKSTATS_GENL_VERSION);
	return 0;
err_cgroup_ops:
	genl_unregister_ops(&family, &taskstats_ops);
err:
	genl_unregister_family(&family);
	return rc;
}

/*
 * late initcall ensures initialization of statistics collection
 * mechanisms precedes initialization of the taskstats interface
 */
late_initcall(taskstats_init);