aboutsummaryrefslogtreecommitdiffstats
path: root/fs/proc/array.c
blob: 77a8eacbe032f22d5bd9514738341a55dcc46b34 (plain) (blame)
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
/*
 *  linux/fs/proc/array.c
 *
 *  Copyright (C) 1992  by Linus Torvalds
 *  based on ideas by Darren Senn
 *
 * Fixes:
 * Michael. K. Johnson: stat,statm extensions.
 *                      <johnsonm@stolaf.edu>
 *
 * Pauline Middelink :  Made cmdline,envline only break at '\0's, to
 *                      make sure SET_PROCTITLE works. Also removed
 *                      bad '!' which forced address recalculation for
 *                      EVERY character on the current page.
 *                      <middelin@polyware.iaf.nl>
 *
 * Danny ter Haar    :	added cpuinfo
 *			<dth@cistron.nl>
 *
 * Alessandro Rubini :  profile extension.
 *                      <rubini@ipvvis.unipv.it>
 *
 * Jeff Tranter      :  added BogoMips field to cpuinfo
 *                      <Jeff_Tranter@Mitel.COM>
 *
 * Bruno Haible      :  remove 4K limit for the maps file
 *			<haible@ma2s2.mathematik.uni-karlsruhe.de>
 *
 * Yves Arrouye      :  remove removal of trailing spaces in get_array.
 *			<Yves.Arrouye@marin.fdn.fr>
 *
 * Jerome Forissier  :  added per-CPU time information to /proc/stat
 *                      and /proc/<pid>/cpu extension
 *                      <forissier@isia.cma.fr>
 *			- Incorporation and non-SMP safe operation
 *			of forissier patch in 2.1.78 by
 *			Hans Marcus <crowbar@concepts.nl>
 *
 * aeb@cwi.nl        :  /proc/partitions
 *
 *
 * Alan Cox	     :  security fixes.
 *			<alan@lxorguk.ukuu.org.uk>
 *
 * Al Viro           :  safe handling of mm_struct
 *
 * Gerhard Wichert   :  added BIGMEM support
 * Siemens AG           <Gerhard.Wichert@pdb.siemens.de>
 *
 * Al Viro & Jeff Garzik :  moved most of the thing into base.c and
 *			 :  proc_misc.c. The rest may eventually go into
 *			 :  base.c too.
 */

#include <linux/types.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/kernel_stat.h>
#include <linux/tty.h>
#include <linux/string.h>
#include <linux/mman.h>
#include <linux/sched/mm.h>
#include <linux/sched/numa_balancing.h>
#include <linux/sched/task_stack.h>
#include <linux/sched/task.h>
#include <linux/sched/cputime.h>
#include <linux/proc_fs.h>
#include <linux/ioport.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/signal.h>
#include <linux/highmem.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/times.h>
#include <linux/cpuset.h>
#include <linux/rcupdate.h>
#include <linux/delayacct.h>
#include <linux/seq_file.h>
#include <linux/pid_namespace.h>
#include <linux/ptrace.h>
#include <linux/tracehook.h>
#include <linux/string_helpers.h>
#include <linux/user_namespace.h>
#include <linux/fs_struct.h>

#include <asm/pgtable.h>
#include <asm/processor.h>
#include "internal.h"

static inline void task_name(struct seq_file *m, struct task_struct *p)
{
	char *buf;
	size_t size;
	char tcomm[sizeof(p->comm)];
	int ret;

	get_task_comm(tcomm, p);

	seq_puts(m, "Name:\t");

	size = seq_get_buf(m, &buf);
	ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
	seq_commit(m, ret < size ? ret : -1);

	seq_putc(m, '\n');
}

/*
 * The task state array is a strange "bitmap" of
 * reasons to sleep. Thus "running" is zero, and
 * you can test for combinations of others with
 * simple bit tests.
 */
static const char * const task_state_array[] = {

	/* states in TASK_REPORT: */
	"R (running)",		/* 0x00 */
	"S (sleeping)",		/* 0x01 */
	"D (disk sleep)",	/* 0x02 */
	"T (stopped)",		/* 0x04 */
	"t (tracing stop)",	/* 0x08 */
	"X (dead)",		/* 0x10 */
	"Z (zombie)",		/* 0x20 */
	"P (parked)",		/* 0x40 */

	/* states beyond TASK_REPORT: */
	"I (idle)",		/* 0x80 */
};

static inline const char *get_task_state(struct task_struct *tsk)
{
	BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array));
	return task_state_array[__get_task_state(tsk)];
}

static inline int get_task_umask(struct task_struct *tsk)
{
	struct fs_struct *fs;
	int umask = -ENOENT;

	task_lock(tsk);
	fs = tsk->fs;
	if (fs)
		umask = fs->umask;
	task_unlock(tsk);
	return umask;
}

static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
				struct pid *pid, struct task_struct *p)
{
	struct user_namespace *user_ns = seq_user_ns(m);
	struct group_info *group_info;
	int g, umask;
	struct task_struct *tracer;
	const struct cred *cred;
	pid_t ppid, tpid = 0, tgid, ngid;
	unsigned int max_fds = 0;

	rcu_read_lock();
	ppid = pid_alive(p) ?
		task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;

	tracer = ptrace_parent(p);
	if (tracer)
		tpid = task_pid_nr_ns(tracer, ns);

	tgid = task_tgid_nr_ns(p, ns);
	ngid = task_numa_group_id(p);
	cred = get_task_cred(p);

	umask = get_task_umask(p);
	if (umask >= 0)
		seq_printf(m, "Umask:\t%#04o\n", umask);

	task_lock(p);
	if (p->files)
		max_fds = files_fdtable(p->files)->max_fds;
	task_unlock(p);
	rcu_read_unlock();

	seq_printf(m, "State:\t%s", get_task_state(p));

	seq_put_decimal_ull(m, "\nTgid:\t", tgid);
	seq_put_decimal_ull(m, "\nNgid:\t", ngid);
	seq_put_decimal_ull(m, "\nPid:\t", pid_nr_ns(pid, ns));
	seq_put_decimal_ull(m, "\nPPid:\t", ppid);
	seq_put_decimal_ull(m, "\nTracerPid:\t", tpid);
	seq_put_decimal_ull(m, "\nUid:\t", from_kuid_munged(user_ns, cred->uid));
	seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->euid));
	seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->suid));
	seq_put_decimal_ull(m, "\t", from_kuid_munged(user_ns, cred->fsuid));
	seq_put_decimal_ull(m, "\nGid:\t", from_kgid_munged(user_ns, cred->gid));
	seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->egid));
	seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->sgid));
	seq_put_decimal_ull(m, "\t", from_kgid_munged(user_ns, cred->fsgid));
	seq_put_decimal_ull(m, "\nFDSize:\t", max_fds);

	seq_puts(m, "\nGroups:\t");
	group_info = cred->group_info;
	for (g = 0; g < group_info->ngroups; g++)
		seq_put_decimal_ull(m, g ? " " : "",
				from_kgid_munged(user_ns, group_info->gid[g]));
	put_cred(cred);
	/* Trailing space shouldn't have been added in the first place. */
	seq_putc(m, ' ');

#ifdef CONFIG_PID_NS
	seq_puts(m, "\nNStgid:");
	for (g = ns->level; g <= pid->level; g++)
		seq_put_decimal_ull(m, "\t", task_tgid_nr_ns(p, pid->numbers[g].ns));
	seq_puts(m, "\nNSpid:");
	for (g = ns->level; g <= pid->level; g++)
		seq_put_decimal_ull(m, "\t", task_pid_nr_ns(p, pid->numbers[g].ns));
	seq_puts(m, "\nNSpgid:");
	for (g = ns->level; g <= pid->level; g++)
		seq_put_decimal_ull(m, "\t", task_pgrp_nr_ns(p, pid->numbers[g].ns));
	seq_puts(m, "\nNSsid:");
	for (g = ns->level; g <= pid->level; g++)
		seq_put_decimal_ull(m, "\t", task_session_nr_ns(p, pid->numbers[g].ns));
#endif
	seq_putc(m, '\n');
}

void render_sigset_t(struct seq_file *m, const char *header,
				sigset_t *set)
{
	int i;

	seq_puts(m, header);

	i = _NSIG;
	do {
		int x = 0;

		i -= 4;
		if (sigismember(set, i+1)) x |= 1;
		if (sigismember(set, i+2)) x |= 2;
		if (sigismember(set, i+3)) x |= 4;
		if (sigismember(set, i+4)) x |= 8;
		seq_putc(m, hex_asc[x]);
	} while (i >= 4);

	seq_putc(m, '\n');
}

static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign,
				    sigset_t *catch)
{
	struct k_sigaction *k;
	int i;

	k = p->sighand->action;
	for (i = 1; i <= _NSIG; ++i, ++k) {
		if (k->sa.sa_handler == SIG_IGN)
			sigaddset(ign, i);
		else if (k->sa.sa_handler != SIG_DFL)
			sigaddset(catch, i);
	}
}

static inline void task_sig(struct seq_file *m, struct task_struct *p)
{
	unsigned long flags;
	sigset_t pending, shpending, blocked, ignored, caught;
	int num_threads = 0;
	unsigned long qsize = 0;
	unsigned long qlim = 0;

	sigemptyset(&pending);
	sigemptyset(&shpending);
	sigemptyset(&blocked);
	sigemptyset(&ignored);
	sigemptyset(&caught);

	if (lock_task_sighand(p, &flags)) {
		pending = p->pending.signal;
		shpending = p->signal->shared_pending.signal;
		blocked = p->blocked;
		collect_sigign_sigcatch(p, &ignored, &caught);
		num_threads = get_nr_threads(p);
		rcu_read_lock();  /* FIXME: is this correct? */
		qsize = atomic_read(&__task_cred(p)->user->sigpending);
		rcu_read_unlock();
		qlim = task_rlimit(p, RLIMIT_SIGPENDING);
		unlock_task_sighand(p, &flags);
	}

	seq_put_decimal_ull(m, "Threads:\t", num_threads);
	seq_put_decimal_ull(m, "\nSigQ:\t", qsize);
	seq_put_decimal_ull(m, "/", qlim);

	/* render them all */
	render_sigset_t(m, "\nSigPnd:\t", &pending);
	render_sigset_t(m, "ShdPnd:\t", &shpending);
	render_sigset_t(m, "SigBlk:\t", &blocked);
	render_sigset_t(m, "SigIgn:\t", &ignored);
	render_sigset_t(m, "SigCgt:\t", &caught);
}

static void render_cap_t(struct seq_file *m, const char *header,
			kernel_cap_t *a)
{
	unsigned __capi;

	seq_puts(m, header);
	CAP_FOR_EACH_U32(__capi) {
		seq_printf(m, "%08x",
			   a->cap[CAP_LAST_U32 - __capi]);
	}
	seq_putc(m, '\n');
}

static inline void task_cap(struct seq_file *m, struct task_struct *p)
{
	const struct cred *cred;
	kernel_cap_t cap_inheritable, cap_permitted, cap_effective,
			cap_bset, cap_ambient;

	rcu_read_lock();
	cred = __task_cred(p);
	cap_inheritable	= cred->cap_inheritable;
	cap_permitted	= cred->cap_permitted;
	cap_effective	= cred->cap_effective;
	cap_bset	= cred->cap_bset;
	cap_ambient	= cred->cap_ambient;
	rcu_read_unlock();

	render_cap_t(m, "CapInh:\t", &cap_inheritable);
	render_cap_t(m, "CapPrm:\t", &cap_permitted);
	render_cap_t(m, "CapEff:\t", &cap_effective);
	render_cap_t(m, "CapBnd:\t", &cap_bset);
	render_cap_t(m, "CapAmb:\t", &cap_ambient);
}

static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
{
	seq_put_decimal_ull(m, "NoNewPrivs:\t", task_no_new_privs(p));
#ifdef CONFIG_SECCOMP
	seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode);
#endif
	seq_putc(m, '\n');
}

static inline void task_context_switch_counts(struct seq_file *m,
						struct task_struct *p)
{
	seq_put_decimal_ull(m, "voluntary_ctxt_switches:\t", p->nvcsw);
	seq_put_decimal_ull(m, "\nnonvoluntary_ctxt_switches:\t", p->nivcsw);
	seq_putc(m, '\n');
}

static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
{
	seq_printf(m, "Cpus_allowed:\t%*pb\n",
		   cpumask_pr_args(&task->cpus_allowed));
	seq_printf(m, "Cpus_allowed_list:\t%*pbl\n",
		   cpumask_pr_args(&task->cpus_allowed));
}

int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
			struct pid *pid, struct task_struct *task)
{
	struct mm_struct *mm = get_task_mm(task);

	task_name(m, task);
	task_state(m, ns, pid, task);

	if (mm) {
		task_mem(m, mm);
		mmput(mm);
	}
	task_sig(m, task);
	task_cap(m, task);
	task_seccomp(m, task);
	task_cpus_allowed(m, task);
	cpuset_task_status_allowed(m, task);
	task_context_switch_counts(m, task);
	return 0;
}

static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
			struct pid *pid, struct task_struct *task, int whole)
{
	unsigned long vsize, eip, esp, wchan = 0;
	int priority, nice;
	int tty_pgrp = -1, tty_nr = 0;
	sigset_t sigign, sigcatch;
	char state;
	pid_t ppid = 0, pgid = -1, sid = -1;
	int num_threads = 0;
	int permitted;
	struct mm_struct *mm;
	unsigned long long start_time;
	unsigned long cmin_flt = 0, cmaj_flt = 0;
	unsigned long  min_flt = 0,  maj_flt = 0;
	u64 cutime, cstime, utime, stime;
	u64 cgtime, gtime;
	unsigned long rsslim = 0;
	char tcomm[sizeof(task->comm)];
	unsigned long flags;

	state = *get_task_state(task);
	vsize = eip = esp = 0;
	permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT);
	mm = get_task_mm(task);
	if (mm) {
		vsize = task_vsize(mm);
		/*
		 * esp and eip are intentionally zeroed out.  There is no
		 * non-racy way to read them without freezing the task.
		 * Programs that need reliable values can use ptrace(2).
		 *
		 * The only exception is if the task is core dumping because
		 * a program is not able to use ptrace(2) in that case. It is
		 * safe because the task has stopped executing permanently.
		 */
		if (permitted && (task->flags & PF_DUMPCORE)) {
			eip = KSTK_EIP(task);
			esp = KSTK_ESP(task);
		}
	}

	get_task_comm(tcomm, task);

	sigemptyset(&sigign);
	sigemptyset(&sigcatch);
	cutime = cstime = utime = stime = 0;
	cgtime = gtime = 0;

	if (lock_task_sighand(task, &flags)) {
		struct signal_struct *sig = task->signal;

		if (sig->tty) {
			struct pid *pgrp = tty_get_pgrp(sig->tty);
			tty_pgrp = pid_nr_ns(pgrp, ns);
			put_pid(pgrp);
			tty_nr = new_encode_dev(tty_devnum(sig->tty));
		}

		num_threads = get_nr_threads(task);
		collect_sigign_sigcatch(task, &sigign, &sigcatch);

		cmin_flt = sig->cmin_flt;
		cmaj_flt = sig->cmaj_flt;
		cutime = sig->cutime;
		cstime = sig->cstime;
		cgtime = sig->cgtime;
		rsslim = ACCESS_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur);

		/* add up live thread stats at the group level */
		if (whole) {
			struct task_struct *t = task;
			do {
				min_flt += t->min_flt;
				maj_flt += t->maj_flt;
				gtime += task_gtime(t);
			} while_each_thread(task, t);

			min_flt += sig->min_flt;
			maj_flt += sig->maj_flt;
			thread_group_cputime_adjusted(task, &utime, &stime);
			gtime += sig->gtime;
		}

		sid = task_session_nr_ns(task, ns);
		ppid = task_tgid_nr_ns(task->real_parent, ns);
		pgid = task_pgrp_nr_ns(task, ns);

		unlock_task_sighand(task, &flags);
	}

	if (permitted && (!whole || num_threads < 2))
		wchan = get_wchan(task);
	if (!whole) {
		min_flt = task->min_flt;
		maj_flt = task->maj_flt;
		task_cputime_adjusted(task, &utime, &stime);
		gtime = task_gtime(task);
	}

	/* scale priority and nice values from timeslices to -20..20 */
	/* to make it look like a "normal" Unix priority/nice value  */
	priority = task_prio(task);
	nice = task_nice(task);

	/* convert nsec -> ticks */
	start_time = nsec_to_clock_t(task->real_start_time);

	seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state);
	seq_put_decimal_ll(m, " ", ppid);
	seq_put_decimal_ll(m, " ", pgid);
	seq_put_decimal_ll(m, " ", sid);
	seq_put_decimal_ll(m, " ", tty_nr);
	seq_put_decimal_ll(m, " ", tty_pgrp);
	seq_put_decimal_ull(m, " ", task->flags);
	seq_put_decimal_ull(m, " ", min_flt);
	seq_put_decimal_ull(m, " ", cmin_flt);
	seq_put_decimal_ull(m, " ", maj_flt);
	seq_put_decimal_ull(m, " ", cmaj_flt);
	seq_put_decimal_ull(m, " ", nsec_to_clock_t(utime));
	seq_put_decimal_ull(m, " ", nsec_to_clock_t(stime));
	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cutime));
	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cstime));
	seq_put_decimal_ll(m, " ", priority);
	seq_put_decimal_ll(m, " ", nice);
	seq_put_decimal_ll(m, " ", num_threads);
	seq_put_decimal_ull(m, " ", 0);
	seq_put_decimal_ull(m, " ", start_time);
	seq_put_decimal_ull(m, " ", vsize);
	seq_put_decimal_ull(m, " ", mm ? get_mm_rss(mm) : 0);
	seq_put_decimal_ull(m, " ", rsslim);
	seq_put_decimal_ull(m, " ", mm ? (permitted ? mm->start_code : 1) : 0);
	seq_put_decimal_ull(m, " ", mm ? (permitted ? mm->end_code : 1) : 0);
	seq_put_decimal_ull(m, " ", (permitted && mm) ? mm->start_stack : 0);
	seq_put_decimal_ull(m, " ", esp);
	seq_put_decimal_ull(m, " ", eip);
	/* The signal information here is obsolete.
	 * It must be decimal for Linux 2.0 compatibility.
	 * Use /proc/#/status for real-time signals.
	 */
	seq_put_decimal_ull(m, " ", task->pending.signal.sig[0] & 0x7fffffffUL);
	seq_put_decimal_ull(m, " ", task->blocked.sig[0] & 0x7fffffffUL);
	seq_put_decimal_ull(m, " ", sigign.sig[0] & 0x7fffffffUL);
	seq_put_decimal_ull(m, " ", sigcatch.sig[0] & 0x7fffffffUL);

	/*
	 * We used to output the absolute kernel address, but that's an
	 * information leak - so instead we show a 0/1 flag here, to signal
	 * to user-space whether there's a wchan field in /proc/PID/wchan.
	 *
	 * This works with older implementations of procps as well.
	 */
	if (wchan)
		seq_puts(m, " 1");
	else
		seq_puts(m, " 0");

	seq_put_decimal_ull(m, " ", 0);
	seq_put_decimal_ull(m, " ", 0);
	seq_put_decimal_ll(m, " ", task->exit_signal);
	seq_put_decimal_ll(m, " ", task_cpu(task));
	seq_put_decimal_ull(m, " ", task->rt_priority);
	seq_put_decimal_ull(m, " ", task->policy);
	seq_put_decimal_ull(m, " ", delayacct_blkio_ticks(task));
	seq_put_decimal_ull(m, " ", nsec_to_clock_t(gtime));
	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cgtime));

	if (mm && permitted) {
		seq_put_decimal_ull(m, " ", mm->start_data);
		seq_put_decimal_ull(m, " ", mm->end_data);
		seq_put_decimal_ull(m, " ", mm->start_brk);
		seq_put_decimal_ull(m, " ", mm->arg_start);
		seq_put_decimal_ull(m, " ", mm->arg_end);
		seq_put_decimal_ull(m, " ", mm->env_start);
		seq_put_decimal_ull(m, " ", mm->env_end);
	} else
		seq_puts(m, " 0 0 0 0 0 0 0");

	if (permitted)
		seq_put_decimal_ll(m, " ", task->exit_code);
	else
		seq_puts(m, " 0");

	seq_putc(m, '\n');
	if (mm)
		mmput(mm);
	return 0;
}

int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
			struct pid *pid, struct task_struct *task)
{
	return do_task_stat(m, ns, pid, task, 0);
}

int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
			struct pid *pid, struct task_struct *task)
{
	return do_task_stat(m, ns, pid, task, 1);
}

int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
			struct pid *pid, struct task_struct *task)
{
	unsigned long size = 0, resident = 0, shared = 0, text = 0, data = 0;
	struct mm_struct *mm = get_task_mm(task);

	if (mm) {
		size = task_statm(mm, &shared, &text, &data, &resident);
		mmput(mm);
	}
	/*
	 * For quick read, open code by putting numbers directly
	 * expected format is
	 * seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n",
	 *               size, resident, shared, text, data);
	 */
	seq_put_decimal_ull(m, "", size);
	seq_put_decimal_ull(m, " ", resident);
	seq_put_decimal_ull(m, " ", shared);
	seq_put_decimal_ull(m, " ", text);
	seq_put_decimal_ull(m, " ", 0);
	seq_put_decimal_ull(m, " ", data);
	seq_put_decimal_ull(m, " ", 0);
	seq_putc(m, '\n');

	return 0;
}

#ifdef CONFIG_PROC_CHILDREN
static struct pid *
get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos)
{
	struct task_struct *start, *task;
	struct pid *pid = NULL;

	read_lock(&tasklist_lock);

	start = pid_task(proc_pid(inode), PIDTYPE_PID);
	if (!start)
		goto out;

	/*
	 * Lets try to continue searching first, this gives
	 * us significant speedup on children-rich processes.
	 */
	if (pid_prev) {
		task = pid_task(pid_prev, PIDTYPE_PID);
		if (task && task->real_parent == start &&
		    !(list_empty(&task->sibling))) {
			if (list_is_last(&task->sibling, &start->children))
				goto out;
			task = list_first_entry(&task->sibling,
						struct task_struct, sibling);
			pid = get_pid(task_pid(task));
			goto out;
		}
	}

	/*
	 * Slow search case.
	 *
	 * We might miss some children here if children
	 * are exited while we were not holding the lock,
	 * but it was never promised to be accurate that
	 * much.
	 *
	 * "Just suppose that the parent sleeps, but N children
	 *  exit after we printed their tids. Now the slow paths
	 *  skips N extra children, we miss N tasks." (c)
	 *
	 * So one need to stop or freeze the leader and all
	 * its children to get a precise result.
	 */
	list_for_each_entry(task, &start->children, sibling) {
		if (pos-- == 0) {
			pid = get_pid(task_pid(task));
			break;
		}
	}

out:
	read_unlock(&tasklist_lock);
	return pid;
}

static int children_seq_show(struct seq_file *seq, void *v)
{
	struct inode *inode = seq->private;
	pid_t pid;

	pid = pid_nr_ns(v, inode->i_sb->s_fs_info);
	seq_printf(seq, "%d ", pid);

	return 0;
}

static void *children_seq_start(struct seq_file *seq, loff_t *pos)
{
	return get_children_pid(seq->private, NULL, *pos);
}

static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct pid *pid;

	pid = get_children_pid(seq->private, v, *pos + 1);
	put_pid(v);

	++*pos;
	return pid;
}

static void children_seq_stop(struct seq_file *seq, void *v)
{
	put_pid(v);
}

static const struct seq_operations children_seq_ops = {
	.start	= children_seq_start,
	.next	= children_seq_next,
	.stop	= children_seq_stop,
	.show	= children_seq_show,
};

static int children_seq_open(struct inode *inode, struct file *file)
{
	struct seq_file *m;
	int ret;

	ret = seq_open(file, &children_seq_ops);
	if (ret)
		return ret;

	m = file->private_data;
	m->private = inode;

	return ret;
}

int children_seq_release(struct inode *inode, struct file *file)
{
	seq_release(inode, file);
	return 0;
}

const struct file_operations proc_tid_children_operations = {
	.open    = children_seq_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = children_seq_release,
};
#endif /* CONFIG_PROC_CHILDREN */