summaryrefslogtreecommitdiffstats
path: root/kernel/pid.c
blob: 686255e2c39e4874a13d78051afc8f54c7d4ae63 (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
/*
 * Generic pidhash and scalable, time-bounded PID allocator
 *
 * (C) 2002-2003 Nadia Yvette Chambers, IBM
 * (C) 2004 Nadia Yvette Chambers, Oracle
 * (C) 2002-2004 Ingo Molnar, Red Hat
 *
 * pid-structures are backing objects for tasks sharing a given ID to chain
 * against. There is very little to them aside from hashing them and
 * parking tasks using given ID's on a list.
 *
 * The hash is always changed with the tasklist_lock write-acquired,
 * and the hash is only accessed with the tasklist_lock at least
 * read-acquired, so there's no additional SMP locking needed here.
 *
 * We have a list of bitmap pages, which bitmaps represent the PID space.
 * Allocating and freeing PIDs is completely lockless. The worst-case
 * allocation scenario when all but one out of 1 million PIDs possible are
 * allocated already: the scanning of 32 list entries and at most PAGE_SIZE
 * bytes. The typical fastpath is a single successful setbit. Freeing is O(1).
 *
 * Pid namespaces:
 *    (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc.
 *    (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM
 *     Many thanks to Oleg Nesterov for comments and help
 *
 */

#include <linux/mm.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/rculist.h>
#include <linux/bootmem.h>
#include <linux/hash.h>
#include <linux/pid_namespace.h>
#include <linux/init_task.h>
#include <linux/syscalls.h>
#include <linux/proc_ns.h>
#include <linux/proc_fs.h>

#define pid_hashfn(nr, ns)	\
	hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
static struct hlist_head *pid_hash;
static unsigned int pidhash_shift = 4;
struct pid init_struct_pid = INIT_STRUCT_PID;

int pid_max = PID_MAX_DEFAULT;

#define RESERVED_PIDS		300

int pid_max_min = RESERVED_PIDS + 1;
int pid_max_max = PID_MAX_LIMIT;

#define BITS_PER_PAGE		(PAGE_SIZE*8)
#define BITS_PER_PAGE_MASK	(BITS_PER_PAGE-1)

static inline int mk_pid(struct pid_namespace *pid_ns,
		struct pidmap *map, int off)
{
	return (map - pid_ns->pidmap)*BITS_PER_PAGE + off;
}

#define find_next_offset(map, off)					\
		find_next_zero_bit((map)->page, BITS_PER_PAGE, off)

/*
 * PID-map pages start out as NULL, they get allocated upon
 * first use and are never deallocated. This way a low pid_max
 * value does not cause lots of bitmaps to be allocated, but
 * the scheme scales to up to 4 million PIDs, runtime.
 */
struct pid_namespace init_pid_ns = {
	.kref = {
		.refcount       = ATOMIC_INIT(2),
	},
	.pidmap = {
		[ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL }
	},
	.last_pid = 0,
	.level = 0,
	.child_reaper = &init_task,
	.user_ns = &init_user_ns,
	.proc_inum = PROC_PID_INIT_INO,
};
EXPORT_SYMBOL_GPL(init_pid_ns);

/*
 * Note: disable interrupts while the pidmap_lock is held as an
 * interrupt might come in and do read_lock(&tasklist_lock).
 *
 * If we don't disable interrupts there is a nasty deadlock between
 * detach_pid()->free_pid() and another cpu that does
 * spin_lock(&pidmap_lock) followed by an interrupt routine that does
 * read_lock(&tasklist_lock);
 *
 * After we clean up the tasklist_lock and know there are no
 * irq handlers that take it we can leave the interrupts enabled.
 * For now it is easier to be safe than to prove it can't happen.
 */

static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);

static void free_pidmap(struct upid *upid)
{
	int nr = upid->nr;
	struct pidmap *map = upid->ns->pidmap + nr / BITS_PER_PAGE;
	int offset = nr & BITS_PER_PAGE_MASK;

	clear_bit(offset, map->page);
	atomic_inc(&map->nr_free);
}

/*
 * If we started walking pids at 'base', is 'a' seen before 'b'?
 */
static int pid_before(int base, int a, int b)
{
	/*
	 * This is the same as saying
	 *
	 * (a - base + MAXUINT) % MAXUINT < (b - base + MAXUINT) % MAXUINT
	 * and that mapping orders 'a' and 'b' with respect to 'base'.
	 */
	return (unsigned)(a - base) < (unsigned)(b - base);
}

/*
 * We might be racing with someone else trying to set pid_ns->last_pid
 * at the pid allocation time (there's also a sysctl for this, but racing
 * with this one is OK, see comment in kernel/pid_namespace.c about it).
 * We want the winner to have the "later" value, because if the
 * "earlier" value prevails, then a pid may get reused immediately.
 *
 * Since pids rollover, it is not sufficient to just pick the bigger
 * value.  We have to consider where we started counting from.
 *
 * 'base' is the value of pid_ns->last_pid that we observed when
 * we started looking for a pid.
 *
 * 'pid' is the pid that we eventually found.
 */
static void set_last_pid(struct pid_namespace *pid_ns, int base, int pid)
{
	int prev;
	int last_write = base;
	do {
		prev = last_write;
		last_write = cmpxchg(&pid_ns->last_pid, prev, pid);
	} while ((prev != last_write) && (pid_before(base, last_write, pid)));
}

static int alloc_pidmap(struct pid_namespace *pid_ns)
{
	int i, offset, max_scan, pid, last = pid_ns->last_pid;
	struct pidmap *map;

	pid = last + 1;
	if (pid >= pid_max)
		pid = RESERVED_PIDS;
	offset = pid & BITS_PER_PAGE_MASK;
	map = &pid_ns->pidmap[pid/BITS_PER_PAGE];
	/*
	 * If last_pid points into the middle of the map->page we
	 * want to scan this bitmap block twice, the second time
	 * we start with offset == 0 (or RESERVED_PIDS).
	 */
	max_scan = DIV_ROUND_UP(pid_max, BITS_PER_PAGE) - !offset;
	for (i = 0; i <= max_scan; ++i) {
		if (unlikely(!map->page)) {
			void *page = kzalloc(PAGE_SIZE, GFP_KERNEL);
			/*
			 * Free the page if someone raced with us
			 * installing it:
			 */
			spin_lock_irq(&pidmap_lock);
			if (!map->page) {
				map->page = page;
				page = NULL;
			}
			spin_unlock_irq(&pidmap_lock);
			kfree(page);
			if (unlikely(!map->page))
				break;
		}
		if (likely(atomic_read(&map->nr_free))) {
			do {
				if (!test_and_set_bit(offset, map->page)) {
					atomic_dec(&map->nr_free);
					set_last_pid(pid_ns, last, pid);
					return pid;
				}
				offset = find_next_offset(map, offset);
				pid = mk_pid(pid_ns, map, offset);
			} while (offset < BITS_PER_PAGE && pid < pid_max);
		}
		if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
			++map;
			offset = 0;
		} else {
			map = &pid_ns->pidmap[0];
			offset = RESERVED_PIDS;
			if (unlikely(last == offset))
				break;
		}
		pid = mk_pid(pid_ns, map, offset);
	}
	return -1;
}

int next_pidmap(struct pid_namespace *pid_ns, unsigned int last)
{
	int offset;
	struct pidmap *map, *end;

	if (last >= PID_MAX_LIMIT)
		return -1;

	offset = (last + 1) & BITS_PER_PAGE_MASK;
	map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE];
	end = &pid_ns->pidmap[PIDMAP_ENTRIES];
	for (; map < end; map++, offset = 0) {
		if (unlikely(!map->page))
			continue;
		offset = find_next_bit((map)->page, BITS_PER_PAGE, offset);
		if (offset < BITS_PER_PAGE)
			return mk_pid(pid_ns, map, offset);
	}
	return -1;
}

void put_pid(struct pid *pid)
{
	struct pid_namespace *ns;

	if (!pid)
		return;

	ns = pid->numbers[pid->level].ns;
	if ((atomic_read(&pid->count) == 1) ||
	     atomic_dec_and_test(&pid->count)) {
		kmem_cache_free(ns->pid_cachep, pid);
		put_pid_ns(ns);
	}
}
EXPORT_SYMBOL_GPL(put_pid);

static void delayed_put_pid(struct rcu_head *rhp)
{
	struct pid *pid = container_of(rhp, struct pid, rcu);
	put_pid(pid);
}

void free_pid(struct pid *pid)
{
	/* We can be called with write_lock_irq(&tasklist_lock) held */
	int i;
	unsigned long flags;

	spin_lock_irqsave(&pidmap_lock, flags);
	for (i = 0; i <= pid->level; i++) {
		struct upid *upid = pid->numbers + i;
		struct pid_namespace *ns = upid->ns;
		hlist_del_rcu(&upid->pid_chain);
		switch(--ns->nr_hashed) {
		case 1:
			/* When all that is left in the pid namespace
			 * is the reaper wake up the reaper.  The reaper
			 * may be sleeping in zap_pid_ns_processes().
			 */
			wake_up_process(ns->child_reaper);
			break;
		case 0:
			schedule_work(&ns->proc_work);
			break;
		}
	}
	spin_unlock_irqrestore(&pidmap_lock, flags);

	for (i = 0; i <= pid->level; i++)
		free_pidmap(pid->numbers + i);

	call_rcu(&pid->rcu, delayed_put_pid);
}

struct pid *alloc_pid(struct pid_namespace *ns)
{
	struct pid *pid;
	enum pid_type type;
	int i, nr;
	struct pid_namespace *tmp;
	struct upid *upid;

	pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
	if (!pid)
		goto out;

	tmp = ns;
	pid->level = ns->level;
	for (i = ns->level; i >= 0; i--) {
		nr = alloc_pidmap(tmp);
		if (nr < 0)
			goto out_free;

		pid->numbers[i].nr = nr;
		pid->numbers[i].ns = tmp;
		tmp = tmp->parent;
	}

	if (unlikely(is_child_reaper(pid))) {
		if (pid_ns_prepare_proc(ns))
			goto out_free;
	}

	get_pid_ns(ns);
	atomic_set(&pid->count, 1);
	for (type = 0; type < PIDTYPE_MAX; ++type)
		INIT_HLIST_HEAD(&pid->tasks[type]);

	upid = pid->numbers + ns->level;
	spin_lock_irq(&pidmap_lock);
	if (!(ns->nr_hashed & PIDNS_HASH_ADDING))
		goto out_unlock;
	for ( ; upid >= pid->numbers; --upid) {
		hlist_add_head_rcu(&upid->pid_chain,
				&pid_hash[pid_hashfn(upid->nr, upid->ns)]);
		upid->ns->nr_hashed++;
	}
	spin_unlock_irq(&pidmap_lock);

out:
	return pid;

out_unlock:
	spin_unlock_irq(&pidmap_lock);
out_free:
	while (++i <= ns->level)
		free_pidmap(pid->numbers + i);

	kmem_cache_free(ns->pid_cachep, pid);
	pid = NULL;
	goto out;
}

void disable_pid_allocation(struct pid_namespace *ns)
{
	spin_lock_irq(&pidmap_lock);
	ns->nr_hashed &= ~PIDNS_HASH_ADDING;
	spin_unlock_irq(&pidmap_lock);
}

struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
{
	struct upid *pnr;

	hlist_for_each_entry_rcu(pnr,
			&pid_hash[pid_hashfn(nr, ns)], pid_chain)
		if (pnr->nr == nr && pnr->ns == ns)
			return container_of(pnr, struct pid,
					numbers[ns->level]);

	return NULL;
}
EXPORT_SYMBOL_GPL(find_pid_ns);

struct pid *find_vpid(int nr)
{
	return find_pid_ns(nr, task_active_pid_ns(current));
}
EXPORT_SYMBOL_GPL(find_vpid);

/*
 * attach_pid() must be called with the tasklist_lock write-held.
 */
void attach_pid(struct task_struct *task, enum pid_type type,
		struct pid *pid)
{
	struct pid_link *link;

	link = &task->pids[type];
	link->pid = pid;
	hlist_add_head_rcu(&link->node, &pid->tasks[type]);
}

static void __change_pid(struct task_struct *task, enum pid_type type,
			struct pid *new)
{
	struct pid_link *link;
	struct pid *pid;
	int tmp;

	link = &task->pids[type];
	pid = link->pid;

	hlist_del_rcu(&link->node);
	link->pid = new;

	for (tmp = PIDTYPE_MAX; --tmp >= 0; )
		if (!hlist_empty(&pid->tasks[tmp]))
			return;

	free_pid(pid);
}

void detach_pid(struct task_struct *task, enum pid_type type)
{
	__change_pid(task, type, NULL);
}

void change_pid(struct task_struct *task, enum pid_type type,
		struct pid *pid)
{
	__change_pid(task, type, pid);
	attach_pid(task, type, pid);
}

/* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */
void transfer_pid(struct task_struct *old, struct task_struct *new,
			   enum pid_type type)
{
	new->pids[type].pid = old->pids[type].pid;
	hlist_replace_rcu(&old->pids[type].node, &new->pids[type].node);
}

struct task_struct *pid_task(struct pid *pid, enum pid_type type)
{
	struct task_struct *result = NULL;
	if (pid) {
		struct hlist_node *first;
		first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]),
					      lockdep_tasklist_lock_is_held());
		if (first)
			result = hlist_entry(first, struct task_struct, pids[(type)].node);
	}
	return result;
}
EXPORT_SYMBOL(pid_task);

/*
 * Must be called under rcu_read_lock().
 */
struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
{
	rcu_lockdep_assert(rcu_read_lock_held(),
			   "find_task_by_pid_ns() needs rcu_read_lock()"
			   " protection");
	return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
}

struct task_struct *find_task_by_vpid(pid_t vnr)
{
	return find_task_by_pid_ns(vnr, task_active_pid_ns(current));
}

struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
{
	struct pid *pid;
	rcu_read_lock();
	if (type != PIDTYPE_PID)
		task = task->group_leader;
	pid = get_pid(task->pids[type].pid);
	rcu_read_unlock();
	return pid;
}
EXPORT_SYMBOL_GPL(get_task_pid);

struct task_struct *get_pid_task(struct pid *pid, enum pid_type type)
{
	struct task_struct *result;
	rcu_read_lock();
	result = pid_task(pid, type);
	if (result)
		get_task_struct(result);
	rcu_read_unlock();
	return result;
}
EXPORT_SYMBOL_GPL(get_pid_task);

struct pid *find_get_pid(pid_t nr)
{
	struct pid *pid;

	rcu_read_lock();
	pid = get_pid(find_vpid(nr));
	rcu_read_unlock();

	return pid;
}
EXPORT_SYMBOL_GPL(find_get_pid);

pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns)
{
	struct upid *upid;
	pid_t nr = 0;

	if (pid && ns->level <= pid->level) {
		upid = &pid->numbers[ns->level];
		if (upid->ns == ns)
			nr = upid->nr;
	}
	return nr;
}
EXPORT_SYMBOL_GPL(pid_nr_ns);

pid_t pid_vnr(struct pid *pid)
{
	return pid_nr_ns(pid, task_active_pid_ns(current));
}
EXPORT_SYMBOL_GPL(pid_vnr);

pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
			struct pid_namespace *ns)
{
	pid_t nr = 0;

	rcu_read_lock();
	if (!ns)
		ns = task_active_pid_ns(current);
	if (likely(pid_alive(task))) {
		if (type != PIDTYPE_PID)
			task = task->group_leader;
		nr = pid_nr_ns(task->pids[type].pid, ns);
	}
	rcu_read_unlock();

	return nr;
}
EXPORT_SYMBOL(__task_pid_nr_ns);

pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
{
	return pid_nr_ns(task_tgid(tsk), ns);
}
EXPORT_SYMBOL(task_tgid_nr_ns);

struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
{
	return ns_of_pid(task_pid(tsk));
}
EXPORT_SYMBOL_GPL(task_active_pid_ns);

/*
 * Used by proc to find the first pid that is greater than or equal to nr.
 *
 * If there is a pid at nr this function is exactly the same as find_pid_ns.
 */
struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
{
	struct pid *pid;

	do {
		pid = find_pid_ns(nr, ns);
		if (pid)
			break;
		nr = next_pidmap(ns, nr);
	} while (nr > 0);

	return pid;
}

/*
 * The pid hash table is scaled according to the amount of memory in the
 * machine.  From a minimum of 16 slots up to 4096 slots at one gigabyte or
 * more.
 */
void __init pidhash_init(void)
{
	unsigned int i, pidhash_size;

	pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
					   HASH_EARLY | HASH_SMALL,
					   &pidhash_shift, NULL,
					   0, 4096);
	pidhash_size = 1U << pidhash_shift;

	for (i = 0; i < pidhash_size; i++)
		INIT_HLIST_HEAD(&pid_hash[i]);
}

void __init pidmap_init(void)
{
	/* Veryify no one has done anything silly */
	BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING);

	/* bump default and minimum pid_max based on number of cpus */
	pid_max = min(pid_max_max, max_t(int, pid_max,
				PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
	pid_max_min = max_t(int, pid_max_min,
				PIDS_PER_CPU_MIN * num_possible_cpus());
	pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min);

	init_pid_ns.pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
	/* Reserve PID 0. We never call free_pidmap(0) */
	set_bit(0, init_pid_ns.pidmap[0].page);
	atomic_dec(&init_pid_ns.pidmap[0].nr_free);
	init_pid_ns.nr_hashed = PIDNS_HASH_ADDING;

	init_pid_ns.pid_cachep = KMEM_CACHE(pid,
			SLAB_HWCACHE_ALIGN | SLAB_PANIC);
}