aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/power/swap.c
blob: 8b1a1b8371459eb7bb2d4b8ba34fbdc98e95ccdd (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
/*
 * linux/kernel/power/swap.c
 *
 * This file provides functions for reading the suspend image from
 * and writing it to a swap partition.
 *
 * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@suse.cz>
 * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
 *
 * This file is released under the GPLv2.
 *
 */

#include <linux/module.h>
#include <linux/file.h>
#include <linux/utsname.h>
#include <linux/version.h>
#include <linux/delay.h>
#include <linux/bitops.h>
#include <linux/genhd.h>
#include <linux/device.h>
#include <linux/buffer_head.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pm.h>

#include "power.h"

extern char resume_file[];

#define SWSUSP_SIG	"S1SUSPEND"

struct swsusp_header {
	char reserved[PAGE_SIZE - 20 - sizeof(sector_t)];
	sector_t image;
	char	orig_sig[10];
	char	sig[10];
} __attribute__((packed));

static struct swsusp_header *swsusp_header;

/*
 * General things
 */

static unsigned short root_swap = 0xffff;
static struct block_device *resume_bdev;

/**
 *	submit - submit BIO request.
 *	@rw:	READ or WRITE.
 *	@off	physical offset of page.
 *	@page:	page we're reading or writing.
 *	@bio_chain: list of pending biod (for async reading)
 *
 *	Straight from the textbook - allocate and initialize the bio.
 *	If we're reading, make sure the page is marked as dirty.
 *	Then submit it and, if @bio_chain == NULL, wait.
 */
static int submit(int rw, pgoff_t page_off, struct page *page,
			struct bio **bio_chain)
{
	struct bio *bio;

	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
	if (!bio)
		return -ENOMEM;
	bio->bi_sector = page_off * (PAGE_SIZE >> 9);
	bio->bi_bdev = resume_bdev;
	bio->bi_end_io = end_swap_bio_read;

	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
		printk("swsusp: ERROR: adding page to bio at %ld\n", page_off);
		bio_put(bio);
		return -EFAULT;
	}

	lock_page(page);
	bio_get(bio);

	if (bio_chain == NULL) {
		submit_bio(rw | (1 << BIO_RW_SYNC), bio);
		wait_on_page_locked(page);
		if (rw == READ)
			bio_set_pages_dirty(bio);
		bio_put(bio);
	} else {
		if (rw == READ)
			get_page(page);	/* These pages are freed later */
		bio->bi_private = *bio_chain;
		*bio_chain = bio;
		submit_bio(rw | (1 << BIO_RW_SYNC), bio);
	}
	return 0;
}

static int bio_read_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
{
	return submit(READ, page_off, virt_to_page(addr), bio_chain);
}

static int bio_write_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
{
	return submit(WRITE, page_off, virt_to_page(addr), bio_chain);
}

static int wait_on_bio_chain(struct bio **bio_chain)
{
	struct bio *bio;
	struct bio *next_bio;
	int ret = 0;

	if (bio_chain == NULL)
		return 0;

	bio = *bio_chain;
	if (bio == NULL)
		return 0;
	while (bio) {
		struct page *page;

		next_bio = bio->bi_private;
		page = bio->bi_io_vec[0].bv_page;
		wait_on_page_locked(page);
		if (!PageUptodate(page) || PageError(page))
			ret = -EIO;
		put_page(page);
		bio_put(bio);
		bio = next_bio;
	}
	*bio_chain = NULL;
	return ret;
}

/*
 * Saving part
 */

static int mark_swapfiles(sector_t start)
{
	int error;

	bio_read_page(swsusp_resume_block, swsusp_header, NULL);
	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
		memcpy(swsusp_header->sig,SWSUSP_SIG, 10);
		swsusp_header->image = start;
		error = bio_write_page(swsusp_resume_block,
					swsusp_header, NULL);
	} else {
		printk(KERN_ERR "swsusp: Swap header not found!\n");
		error = -ENODEV;
	}
	return error;
}

/**
 *	swsusp_swap_check - check if the resume device is a swap device
 *	and get its index (if so)
 */

static int swsusp_swap_check(void) /* This is called before saving image */
{
	int res;

	res = swap_type_of(swsusp_resume_device, swsusp_resume_block,
			&resume_bdev);
	if (res < 0)
		return res;

	root_swap = res;
	res = blkdev_get(resume_bdev, FMODE_WRITE, O_RDWR);
	if (res)
		return res;

	res = set_blocksize(resume_bdev, PAGE_SIZE);
	if (res < 0)
		blkdev_put(resume_bdev);

	return res;
}

/**
 *	write_page - Write one page to given swap location.
 *	@buf:		Address we're writing.
 *	@offset:	Offset of the swap page we're writing to.
 *	@bio_chain:	Link the next write BIO here
 */

static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
{
	void *src;

	if (!offset)
		return -ENOSPC;

	if (bio_chain) {
		src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
		if (src) {
			memcpy(src, buf, PAGE_SIZE);
		} else {
			WARN_ON_ONCE(1);
			bio_chain = NULL;	/* Go synchronous */
			src = buf;
		}
	} else {
		src = buf;
	}
	return bio_write_page(offset, src, bio_chain);
}

/*
 *	The swap map is a data structure used for keeping track of each page
 *	written to a swap partition.  It consists of many swap_map_page
 *	structures that contain each an array of MAP_PAGE_SIZE swap entries.
 *	These structures are stored on the swap and linked together with the
 *	help of the .next_swap member.
 *
 *	The swap map is created during suspend.  The swap map pages are
 *	allocated and populated one at a time, so we only need one memory
 *	page to set up the entire structure.
 *
 *	During resume we also only need to use one swap_map_page structure
 *	at a time.
 */

#define MAP_PAGE_ENTRIES	(PAGE_SIZE / sizeof(sector_t) - 1)

struct swap_map_page {
	sector_t entries[MAP_PAGE_ENTRIES];
	sector_t next_swap;
};

/**
 *	The swap_map_handle structure is used for handling swap in
 *	a file-alike way
 */

struct swap_map_handle {
	struct swap_map_page *cur;
	sector_t cur_swap;
	unsigned int k;
};

static void release_swap_writer(struct swap_map_handle *handle)
{
	if (handle->cur)
		free_page((unsigned long)handle->cur);
	handle->cur = NULL;
}

static int get_swap_writer(struct swap_map_handle *handle)
{
	handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_KERNEL);
	if (!handle->cur)
		return -ENOMEM;
	handle->cur_swap = alloc_swapdev_block(root_swap);
	if (!handle->cur_swap) {
		release_swap_writer(handle);
		return -ENOSPC;
	}
	handle->k = 0;
	return 0;
}

static int swap_write_page(struct swap_map_handle *handle, void *buf,
				struct bio **bio_chain)
{
	int error = 0;
	sector_t offset;

	if (!handle->cur)
		return -EINVAL;
	offset = alloc_swapdev_block(root_swap);
	error = write_page(buf, offset, bio_chain);
	if (error)
		return error;
	handle->cur->entries[handle->k++] = offset;
	if (handle->k >= MAP_PAGE_ENTRIES) {
		error = wait_on_bio_chain(bio_chain);
		if (error)
			goto out;
		offset = alloc_swapdev_block(root_swap);
		if (!offset)
			return -ENOSPC;
		handle->cur->next_swap = offset;
		error = write_page(handle->cur, handle->cur_swap, NULL);
		if (error)
			goto out;
		memset(handle->cur, 0, PAGE_SIZE);
		handle->cur_swap = offset;
		handle->k = 0;
	}
 out:
	return error;
}

static int flush_swap_writer(struct swap_map_handle *handle)
{
	if (handle->cur && handle->cur_swap)
		return write_page(handle->cur, handle->cur_swap, NULL);
	else
		return -EINVAL;
}

/**
 *	save_image - save the suspend image data
 */

static int save_image(struct swap_map_handle *handle,
                      struct snapshot_handle *snapshot,
                      unsigned int nr_to_write)
{
	unsigned int m;
	int ret;
	int error = 0;
	int nr_pages;
	int err2;
	struct bio *bio;
	struct timeval start;
	struct timeval stop;

	printk("Saving image data pages (%u pages) ...     ", nr_to_write);
	m = nr_to_write / 100;
	if (!m)
		m = 1;
	nr_pages = 0;
	bio = NULL;
	do_gettimeofday(&start);
	do {
		ret = snapshot_read_next(snapshot, PAGE_SIZE);
		if (ret > 0) {
			error = swap_write_page(handle, data_of(*snapshot),
						&bio);
			if (error)
				break;
			if (!(nr_pages % m))
				printk("\b\b\b\b%3d%%", nr_pages / m);
			nr_pages++;
		}
	} while (ret > 0);
	err2 = wait_on_bio_chain(&bio);
	do_gettimeofday(&stop);
	if (!error)
		error = err2;
	if (!error)
		printk("\b\b\b\bdone\n");
	swsusp_show_speed(&start, &stop, nr_to_write, "Wrote");
	return error;
}

/**
 *	enough_swap - Make sure we have enough swap to save the image.
 *
 *	Returns TRUE or FALSE after checking the total amount of swap
 *	space avaiable from the resume partition.
 */

static int enough_swap(unsigned int nr_pages)
{
	unsigned int free_swap = count_swap_pages(root_swap, 1);

	pr_debug("swsusp: free swap pages: %u\n", free_swap);
	return free_swap > nr_pages + PAGES_FOR_IO;
}

/**
 *	swsusp_write - Write entire image and metadata.
 *
 *	It is important _NOT_ to umount filesystems at this point. We want
 *	them synced (in case something goes wrong) but we DO not want to mark
 *	filesystem clean: it is not. (And it does not matter, if we resume
 *	correctly, we'll mark system clean, anyway.)
 */

int swsusp_write(void)
{
	struct swap_map_handle handle;
	struct snapshot_handle snapshot;
	struct swsusp_info *header;
	int error;

	error = swsusp_swap_check();
	if (error) {
		printk(KERN_ERR "swsusp: Cannot find swap device, try "
				"swapon -a.\n");
		return error;
	}
	memset(&snapshot, 0, sizeof(struct snapshot_handle));
	error = snapshot_read_next(&snapshot, PAGE_SIZE);
	if (error < PAGE_SIZE) {
		if (error >= 0)
			error = -EFAULT;

		goto out;
	}
	header = (struct swsusp_info *)data_of(snapshot);
	if (!enough_swap(header->pages)) {
		printk(KERN_ERR "swsusp: Not enough free swap\n");
		error = -ENOSPC;
		goto out;
	}
	error = get_swap_writer(&handle);
	if (!error) {
		sector_t start = handle.cur_swap;

		error = swap_write_page(&handle, header, NULL);
		if (!error)
			error = save_image(&handle, &snapshot,
					header->pages - 1);

		if (!error) {
			flush_swap_writer(&handle);
			printk("S");
			error = mark_swapfiles(start);
			printk("|\n");
		}
	}
	if (error)
		free_all_swap_pages(root_swap);

	release_swap_writer(&handle);
 out:
	swsusp_close();
	return error;
}

/**
 *	The following functions allow us to read data using a swap map
 *	in a file-alike way
 */

static void release_swap_reader(struct swap_map_handle *handle)
{
	if (handle->cur)
		free_page((unsigned long)handle->cur);
	handle->cur = NULL;
}

static int get_swap_reader(struct swap_map_handle *handle, sector_t start)
{
	int error;

	if (!start)
		return -EINVAL;

	handle->cur = (struct swap_map_page *)get_zeroed_page(__GFP_WAIT | __GFP_HIGH);
	if (!handle->cur)
		return -ENOMEM;

	error = bio_read_page(start, handle->cur, NULL);
	if (error) {
		release_swap_reader(handle);
		return error;
	}
	handle->k = 0;
	return 0;
}

static int swap_read_page(struct swap_map_handle *handle, void *buf,
				struct bio **bio_chain)
{
	sector_t offset;
	int error;

	if (!handle->cur)
		return -EINVAL;
	offset = handle->cur->entries[handle->k];
	if (!offset)
		return -EFAULT;
	error = bio_read_page(offset, buf, bio_chain);
	if (error)
		return error;
	if (++handle->k >= MAP_PAGE_ENTRIES) {
		error = wait_on_bio_chain(bio_chain);
		handle->k = 0;
		offset = handle->cur->next_swap;
		if (!offset)
			release_swap_reader(handle);
		else if (!error)
			error = bio_read_page(offset, handle->cur, NULL);
	}
	return error;
}

/**
 *	load_image - load the image using the swap map handle
 *	@handle and the snapshot handle @snapshot
 *	(assume there are @nr_pages pages to load)
 */

static int load_image(struct swap_map_handle *handle,
                      struct snapshot_handle *snapshot,
                      unsigned int nr_to_read)
{
	unsigned int m;
	int error = 0;
	struct timeval start;
	struct timeval stop;
	struct bio *bio;
	int err2;
	unsigned nr_pages;

	printk("Loading image data pages (%u pages) ...     ", nr_to_read);
	m = nr_to_read / 100;
	if (!m)
		m = 1;
	nr_pages = 0;
	bio = NULL;
	do_gettimeofday(&start);
	for ( ; ; ) {
		error = snapshot_write_next(snapshot, PAGE_SIZE);
		if (error <= 0)
			break;
		error = swap_read_page(handle, data_of(*snapshot), &bio);
		if (error)
			break;
		if (snapshot->sync_read)
			error = wait_on_bio_chain(&bio);
		if (error)
			break;
		if (!(nr_pages % m))
			printk("\b\b\b\b%3d%%", nr_pages / m);
		nr_pages++;
	}
	err2 = wait_on_bio_chain(&bio);
	do_gettimeofday(&stop);
	if (!error)
		error = err2;
	if (!error) {
		printk("\b\b\b\bdone\n");
		snapshot_write_finalize(snapshot);
		if (!snapshot_image_loaded(snapshot))
			error = -ENODATA;
	}
	swsusp_show_speed(&start, &stop, nr_to_read, "Read");
	return error;
}

int swsusp_read(void)
{
	int error;
	struct swap_map_handle handle;
	struct snapshot_handle snapshot;
	struct swsusp_info *header;

	if (IS_ERR(resume_bdev)) {
		pr_debug("swsusp: block device not initialised\n");
		return PTR_ERR(resume_bdev);
	}

	memset(&snapshot, 0, sizeof(struct snapshot_handle));
	error = snapshot_write_next(&snapshot, PAGE_SIZE);
	if (error < PAGE_SIZE)
		return error < 0 ? error : -EFAULT;
	header = (struct swsusp_info *)data_of(snapshot);
	error = get_swap_reader(&handle, swsusp_header->image);
	if (!error)
		error = swap_read_page(&handle, header, NULL);
	if (!error)
		error = load_image(&handle, &snapshot, header->pages - 1);
	release_swap_reader(&handle);

	blkdev_put(resume_bdev);

	if (!error)
		pr_debug("swsusp: Reading resume file was successful\n");
	else
		pr_debug("swsusp: Error %d resuming\n", error);
	return error;
}

/**
 *      swsusp_check - Check for swsusp signature in the resume device
 */

int swsusp_check(void)
{
	int error;

	resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
	if (!IS_ERR(resume_bdev)) {
		set_blocksize(resume_bdev, PAGE_SIZE);
		memset(swsusp_header, 0, PAGE_SIZE);
		error = bio_read_page(swsusp_resume_block,
					swsusp_header, NULL);
		if (error)
			return error;

		if (!memcmp(SWSUSP_SIG, swsusp_header->sig, 10)) {
			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
			/* Reset swap signature now */
			error = bio_write_page(swsusp_resume_block,
						swsusp_header, NULL);
		} else {
			return -EINVAL;
		}
		if (error)
			blkdev_put(resume_bdev);
		else
			pr_debug("swsusp: Signature found, resuming\n");
	} else {
		error = PTR_ERR(resume_bdev);
	}

	if (error)
		pr_debug("swsusp: Error %d check for resume file\n", error);

	return error;
}

/**
 *	swsusp_close - close swap device.
 */

void swsusp_close(void)
{
	if (IS_ERR(resume_bdev)) {
		pr_debug("swsusp: block device not initialised\n");
		return;
	}

	blkdev_put(resume_bdev);
}

static int swsusp_header_init(void)
{
	swsusp_header = (struct swsusp_header*) __get_free_page(GFP_KERNEL);
	if (!swsusp_header)
		panic("Could not allocate memory for swsusp_header\n");
	return 0;
}

core_initcall(swsusp_header_init);
href='#n2358'>2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609
/*
 *  Generic process-grouping system.
 *
 *  Based originally on the cpuset system, extracted by Paul Menage
 *  Copyright (C) 2006 Google, Inc
 *
 *  Copyright notices from the original cpuset code:
 *  --------------------------------------------------
 *  Copyright (C) 2003 BULL SA.
 *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
 *
 *  Portions derived from Patrick Mochel's sysfs code.
 *  sysfs is Copyright (c) 2001-3 Patrick Mochel
 *
 *  2003-10-10 Written by Simon Derr.
 *  2003-10-22 Updates by Stephen Hemminger.
 *  2004 May-July Rework by Paul Jackson.
 *  ---------------------------------------------------
 *
 *  This file is subject to the terms and conditions of the GNU General Public
 *  License.  See the file COPYING in the main directory of the Linux
 *  distribution for more details.
 */

#include <linux/cgroup.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/backing-dev.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/magic.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/sort.h>
#include <linux/kmod.h>
#include <linux/delayacct.h>
#include <linux/cgroupstats.h>
#include <linux/hash.h>
#include <linux/namei.h>

#include <asm/atomic.h>

static DEFINE_MUTEX(cgroup_mutex);

/* Generate an array of cgroup subsystem pointers */
#define SUBSYS(_x) &_x ## _subsys,

static struct cgroup_subsys *subsys[] = {
#include <linux/cgroup_subsys.h>
};

/*
 * A cgroupfs_root represents the root of a cgroup hierarchy,
 * and may be associated with a superblock to form an active
 * hierarchy
 */
struct cgroupfs_root {
	struct super_block *sb;

	/*
	 * The bitmask of subsystems intended to be attached to this
	 * hierarchy
	 */
	unsigned long subsys_bits;

	/* The bitmask of subsystems currently attached to this hierarchy */
	unsigned long actual_subsys_bits;

	/* A list running through the attached subsystems */
	struct list_head subsys_list;

	/* The root cgroup for this hierarchy */
	struct cgroup top_cgroup;

	/* Tracks how many cgroups are currently defined in hierarchy.*/
	int number_of_cgroups;

	/* A list running through the active hierarchies */
	struct list_head root_list;

	/* Hierarchy-specific flags */
	unsigned long flags;

	/* The path to use for release notifications. */
	char release_agent_path[PATH_MAX];
};

/*
 * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
 * subsystems that are otherwise unattached - it never has more than a
 * single cgroup, and all tasks are part of that cgroup.
 */
static struct cgroupfs_root rootnode;

/*
 * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when
 * cgroup_subsys->use_id != 0.
 */
#define CSS_ID_MAX	(65535)
struct css_id {
	/*
	 * The css to which this ID points. This pointer is set to valid value
	 * after cgroup is populated. If cgroup is removed, this will be NULL.
	 * This pointer is expected to be RCU-safe because destroy()
	 * is called after synchronize_rcu(). But for safe use, css_is_removed()
	 * css_tryget() should be used for avoiding race.
	 */
	struct cgroup_subsys_state *css;
	/*
	 * ID of this css.
	 */
	unsigned short id;
	/*
	 * Depth in hierarchy which this ID belongs to.
	 */
	unsigned short depth;
	/*
	 * ID is freed by RCU. (and lookup routine is RCU safe.)
	 */
	struct rcu_head rcu_head;
	/*
	 * Hierarchy of CSS ID belongs to.
	 */
	unsigned short stack[0]; /* Array of Length (depth+1) */
};


/* The list of hierarchy roots */

static LIST_HEAD(roots);
static int root_count;

/* dummytop is a shorthand for the dummy hierarchy's top cgroup */
#define dummytop (&rootnode.top_cgroup)

/* This flag indicates whether tasks in the fork and exit paths should
 * check for fork/exit handlers to call. This avoids us having to do
 * extra work in the fork/exit path if none of the subsystems need to
 * be called.
 */
static int need_forkexit_callback __read_mostly;

/* convenient tests for these bits */
inline int cgroup_is_removed(const struct cgroup *cgrp)
{
	return test_bit(CGRP_REMOVED, &cgrp->flags);
}

/* bits in struct cgroupfs_root flags field */
enum {
	ROOT_NOPREFIX, /* mounted subsystems have no named prefix */
};

static int cgroup_is_releasable(const struct cgroup *cgrp)
{
	const int bits =
		(1 << CGRP_RELEASABLE) |
		(1 << CGRP_NOTIFY_ON_RELEASE);
	return (cgrp->flags & bits) == bits;
}

static int notify_on_release(const struct cgroup *cgrp)
{
	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
}

/*
 * for_each_subsys() allows you to iterate on each subsystem attached to
 * an active hierarchy
 */
#define for_each_subsys(_root, _ss) \
list_for_each_entry(_ss, &_root->subsys_list, sibling)

/* for_each_active_root() allows you to iterate across the active hierarchies */
#define for_each_active_root(_root) \
list_for_each_entry(_root, &roots, root_list)

/* the list of cgroups eligible for automatic release. Protected by
 * release_list_lock */
static LIST_HEAD(release_list);
static DEFINE_SPINLOCK(release_list_lock);
static void cgroup_release_agent(struct work_struct *work);
static DECLARE_WORK(release_agent_work, cgroup_release_agent);
static void check_for_release(struct cgroup *cgrp);

/* Link structure for associating css_set objects with cgroups */
struct cg_cgroup_link {
	/*
	 * List running through cg_cgroup_links associated with a
	 * cgroup, anchored on cgroup->css_sets
	 */
	struct list_head cgrp_link_list;
	/*
	 * List running through cg_cgroup_links pointing at a
	 * single css_set object, anchored on css_set->cg_links
	 */
	struct list_head cg_link_list;
	struct css_set *cg;
};

/* The default css_set - used by init and its children prior to any
 * hierarchies being mounted. It contains a pointer to the root state
 * for each subsystem. Also used to anchor the list of css_sets. Not
 * reference-counted, to improve performance when child cgroups
 * haven't been created.
 */

static struct css_set init_css_set;
static struct cg_cgroup_link init_css_set_link;

static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);

/* css_set_lock protects the list of css_set objects, and the
 * chain of tasks off each css_set.  Nests outside task->alloc_lock
 * due to cgroup_iter_start() */
static DEFINE_RWLOCK(css_set_lock);
static int css_set_count;

/* hash table for cgroup groups. This improves the performance to
 * find an existing css_set */
#define CSS_SET_HASH_BITS	7
#define CSS_SET_TABLE_SIZE	(1 << CSS_SET_HASH_BITS)
static struct hlist_head css_set_table[CSS_SET_TABLE_SIZE];

static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
{
	int i;
	int index;
	unsigned long tmp = 0UL;

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++)
		tmp += (unsigned long)css[i];
	tmp = (tmp >> 16) ^ tmp;

	index = hash_long(tmp, CSS_SET_HASH_BITS);

	return &css_set_table[index];
}

/* We don't maintain the lists running through each css_set to its
 * task until after the first call to cgroup_iter_start(). This
 * reduces the fork()/exit() overhead for people who have cgroups
 * compiled into their kernel but not actually in use */
static int use_task_css_set_links __read_mostly;

/* When we create or destroy a css_set, the operation simply
 * takes/releases a reference count on all the cgroups referenced
 * by subsystems in this css_set. This can end up multiple-counting
 * some cgroups, but that's OK - the ref-count is just a
 * busy/not-busy indicator; ensuring that we only count each cgroup
 * once would require taking a global lock to ensure that no
 * subsystems moved between hierarchies while we were doing so.
 *
 * Possible TODO: decide at boot time based on the number of
 * registered subsystems and the number of CPUs or NUMA nodes whether
 * it's better for performance to ref-count every subsystem, or to
 * take a global lock and only add one ref count to each hierarchy.
 */

/*
 * unlink a css_set from the list and free it
 */
static void unlink_css_set(struct css_set *cg)
{
	struct cg_cgroup_link *link;
	struct cg_cgroup_link *saved_link;

	hlist_del(&cg->hlist);
	css_set_count--;

	list_for_each_entry_safe(link, saved_link, &cg->cg_links,
				 cg_link_list) {
		list_del(&link->cg_link_list);
		list_del(&link->cgrp_link_list);
		kfree(link);
	}
}

static void __put_css_set(struct css_set *cg, int taskexit)
{
	int i;
	/*
	 * Ensure that the refcount doesn't hit zero while any readers
	 * can see it. Similar to atomic_dec_and_lock(), but for an
	 * rwlock
	 */
	if (atomic_add_unless(&cg->refcount, -1, 1))
		return;
	write_lock(&css_set_lock);
	if (!atomic_dec_and_test(&cg->refcount)) {
		write_unlock(&css_set_lock);
		return;
	}
	unlink_css_set(cg);
	write_unlock(&css_set_lock);

	rcu_read_lock();
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup);
		if (atomic_dec_and_test(&cgrp->count) &&
		    notify_on_release(cgrp)) {
			if (taskexit)
				set_bit(CGRP_RELEASABLE, &cgrp->flags);
			check_for_release(cgrp);
		}
	}
	rcu_read_unlock();
	kfree(cg);
}

/*
 * refcounted get/put for css_set objects
 */
static inline void get_css_set(struct css_set *cg)
{
	atomic_inc(&cg->refcount);
}

static inline void put_css_set(struct css_set *cg)
{
	__put_css_set(cg, 0);
}

static inline void put_css_set_taskexit(struct css_set *cg)
{
	__put_css_set(cg, 1);
}

/*
 * find_existing_css_set() is a helper for
 * find_css_set(), and checks to see whether an existing
 * css_set is suitable.
 *
 * oldcg: the cgroup group that we're using before the cgroup
 * transition
 *
 * cgrp: the cgroup that we're moving into
 *
 * template: location in which to build the desired set of subsystem
 * state objects for the new cgroup group
 */
static struct css_set *find_existing_css_set(
	struct css_set *oldcg,
	struct cgroup *cgrp,
	struct cgroup_subsys_state *template[])
{
	int i;
	struct cgroupfs_root *root = cgrp->root;
	struct hlist_head *hhead;
	struct hlist_node *node;
	struct css_set *cg;

	/* Built the set of subsystem state objects that we want to
	 * see in the new css_set */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		if (root->subsys_bits & (1UL << i)) {
			/* Subsystem is in this hierarchy. So we want
			 * the subsystem state from the new
			 * cgroup */
			template[i] = cgrp->subsys[i];
		} else {
			/* Subsystem is not in this hierarchy, so we
			 * don't want to change the subsystem state */
			template[i] = oldcg->subsys[i];
		}
	}

	hhead = css_set_hash(template);
	hlist_for_each_entry(cg, node, hhead, hlist) {
		if (!memcmp(template, cg->subsys, sizeof(cg->subsys))) {
			/* All subsystems matched */
			return cg;
		}
	}

	/* No existing cgroup group matched */
	return NULL;
}

static void free_cg_links(struct list_head *tmp)
{
	struct cg_cgroup_link *link;
	struct cg_cgroup_link *saved_link;

	list_for_each_entry_safe(link, saved_link, tmp, cgrp_link_list) {
		list_del(&link->cgrp_link_list);
		kfree(link);
	}
}

/*
 * allocate_cg_links() allocates "count" cg_cgroup_link structures
 * and chains them on tmp through their cgrp_link_list fields. Returns 0 on
 * success or a negative error
 */
static int allocate_cg_links(int count, struct list_head *tmp)
{
	struct cg_cgroup_link *link;
	int i;
	INIT_LIST_HEAD(tmp);
	for (i = 0; i < count; i++) {
		link = kmalloc(sizeof(*link), GFP_KERNEL);
		if (!link) {
			free_cg_links(tmp);
			return -ENOMEM;
		}
		list_add(&link->cgrp_link_list, tmp);
	}
	return 0;
}

/**
 * link_css_set - a helper function to link a css_set to a cgroup
 * @tmp_cg_links: cg_cgroup_link objects allocated by allocate_cg_links()
 * @cg: the css_set to be linked
 * @cgrp: the destination cgroup
 */
static void link_css_set(struct list_head *tmp_cg_links,
			 struct css_set *cg, struct cgroup *cgrp)
{
	struct cg_cgroup_link *link;

	BUG_ON(list_empty(tmp_cg_links));
	link = list_first_entry(tmp_cg_links, struct cg_cgroup_link,
				cgrp_link_list);
	link->cg = cg;
	list_move(&link->cgrp_link_list, &cgrp->css_sets);
	list_add(&link->cg_link_list, &cg->cg_links);
}

/*
 * find_css_set() takes an existing cgroup group and a
 * cgroup object, and returns a css_set object that's
 * equivalent to the old group, but with the given cgroup
 * substituted into the appropriate hierarchy. Must be called with
 * cgroup_mutex held
 */
static struct css_set *find_css_set(
	struct css_set *oldcg, struct cgroup *cgrp)
{
	struct css_set *res;
	struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];
	int i;

	struct list_head tmp_cg_links;

	struct hlist_head *hhead;

	/* First see if we already have a cgroup group that matches
	 * the desired set */
	read_lock(&css_set_lock);
	res = find_existing_css_set(oldcg, cgrp, template);
	if (res)
		get_css_set(res);
	read_unlock(&css_set_lock);

	if (res)
		return res;

	res = kmalloc(sizeof(*res), GFP_KERNEL);
	if (!res)
		return NULL;

	/* Allocate all the cg_cgroup_link objects that we'll need */
	if (allocate_cg_links(root_count, &tmp_cg_links) < 0) {
		kfree(res);
		return NULL;
	}

	atomic_set(&res->refcount, 1);
	INIT_LIST_HEAD(&res->cg_links);
	INIT_LIST_HEAD(&res->tasks);
	INIT_HLIST_NODE(&res->hlist);

	/* Copy the set of subsystem state objects generated in
	 * find_existing_css_set() */
	memcpy(res->subsys, template, sizeof(res->subsys));

	write_lock(&css_set_lock);
	/* Add reference counts and links from the new css_set. */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup *cgrp = res->subsys[i]->cgroup;
		struct cgroup_subsys *ss = subsys[i];
		atomic_inc(&cgrp->count);
		/*
		 * We want to add a link once per cgroup, so we
		 * only do it for the first subsystem in each
		 * hierarchy
		 */
		if (ss->root->subsys_list.next == &ss->sibling)
			link_css_set(&tmp_cg_links, res, cgrp);
	}
	if (list_empty(&rootnode.subsys_list))
		link_css_set(&tmp_cg_links, res, dummytop);

	BUG_ON(!list_empty(&tmp_cg_links));

	css_set_count++;

	/* Add this cgroup group to the hash table */
	hhead = css_set_hash(res->subsys);
	hlist_add_head(&res->hlist, hhead);

	write_unlock(&css_set_lock);

	return res;
}

/*
 * There is one global cgroup mutex. We also require taking
 * task_lock() when dereferencing a task's cgroup subsys pointers.
 * See "The task_lock() exception", at the end of this comment.
 *
 * A task must hold cgroup_mutex to modify cgroups.
 *
 * Any task can increment and decrement the count field without lock.
 * So in general, code holding cgroup_mutex can't rely on the count
 * field not changing.  However, if the count goes to zero, then only
 * cgroup_attach_task() can increment it again.  Because a count of zero
 * means that no tasks are currently attached, therefore there is no
 * way a task attached to that cgroup can fork (the other way to
 * increment the count).  So code holding cgroup_mutex can safely
 * assume that if the count is zero, it will stay zero. Similarly, if
 * a task holds cgroup_mutex on a cgroup with zero count, it
 * knows that the cgroup won't be removed, as cgroup_rmdir()
 * needs that mutex.
 *
 * The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't
 * (usually) take cgroup_mutex.  These are the two most performance
 * critical pieces of code here.  The exception occurs on cgroup_exit(),
 * when a task in a notify_on_release cgroup exits.  Then cgroup_mutex
 * is taken, and if the cgroup count is zero, a usermode call made
 * to the release agent with the name of the cgroup (path relative to
 * the root of cgroup file system) as the argument.
 *
 * A cgroup can only be deleted if both its 'count' of using tasks
 * is zero, and its list of 'children' cgroups is empty.  Since all
 * tasks in the system use _some_ cgroup, and since there is always at
 * least one task in the system (init, pid == 1), therefore, top_cgroup
 * always has either children cgroups and/or using tasks.  So we don't
 * need a special hack to ensure that top_cgroup cannot be deleted.
 *
 *	The task_lock() exception
 *
 * The need for this exception arises from the action of
 * cgroup_attach_task(), which overwrites one tasks cgroup pointer with
 * another.  It does so using cgroup_mutex, however there are
 * several performance critical places that need to reference
 * task->cgroup without the expense of grabbing a system global
 * mutex.  Therefore except as noted below, when dereferencing or, as
 * in cgroup_attach_task(), modifying a task'ss cgroup pointer we use
 * task_lock(), which acts on a spinlock (task->alloc_lock) already in
 * the task_struct routinely used for such matters.
 *
 * P.S.  One more locking exception.  RCU is used to guard the
 * update of a tasks cgroup pointer by cgroup_attach_task()
 */

/**
 * cgroup_lock - lock out any changes to cgroup structures
 *
 */
void cgroup_lock(void)
{
	mutex_lock(&cgroup_mutex);
}

/**
 * cgroup_unlock - release lock on cgroup changes
 *
 * Undo the lock taken in a previous cgroup_lock() call.
 */
void cgroup_unlock(void)
{
	mutex_unlock(&cgroup_mutex);
}

/*
 * A couple of forward declarations required, due to cyclic reference loop:
 * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
 * cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations
 * -> cgroup_mkdir.
 */

static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
static struct inode_operations cgroup_dir_inode_operations;
static struct file_operations proc_cgroupstats_operations;

static struct backing_dev_info cgroup_backing_dev_info = {
	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
};

static int alloc_css_id(struct cgroup_subsys *ss,
			struct cgroup *parent, struct cgroup *child);

static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
{
	struct inode *inode = new_inode(sb);

	if (inode) {
		inode->i_mode = mode;
		inode->i_uid = current_fsuid();
		inode->i_gid = current_fsgid();
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
	}
	return inode;
}

/*
 * Call subsys's pre_destroy handler.
 * This is called before css refcnt check.
 */
static int cgroup_call_pre_destroy(struct cgroup *cgrp)
{
	struct cgroup_subsys *ss;
	int ret = 0;

	for_each_subsys(cgrp->root, ss)
		if (ss->pre_destroy) {
			ret = ss->pre_destroy(ss, cgrp);
			if (ret)
				break;
		}
	return ret;
}

static void free_cgroup_rcu(struct rcu_head *obj)
{
	struct cgroup *cgrp = container_of(obj, struct cgroup, rcu_head);

	kfree(cgrp);
}

static void cgroup_diput(struct dentry *dentry, struct inode *inode)
{
	/* is dentry a directory ? if so, kfree() associated cgroup */
	if (S_ISDIR(inode->i_mode)) {
		struct cgroup *cgrp = dentry->d_fsdata;
		struct cgroup_subsys *ss;
		BUG_ON(!(cgroup_is_removed(cgrp)));
		/* It's possible for external users to be holding css
		 * reference counts on a cgroup; css_put() needs to
		 * be able to access the cgroup after decrementing
		 * the reference count in order to know if it needs to
		 * queue the cgroup to be handled by the release
		 * agent */
		synchronize_rcu();

		mutex_lock(&cgroup_mutex);
		/*
		 * Release the subsystem state objects.
		 */
		for_each_subsys(cgrp->root, ss)
			ss->destroy(ss, cgrp);

		cgrp->root->number_of_cgroups--;
		mutex_unlock(&cgroup_mutex);

		/*
		 * Drop the active superblock reference that we took when we
		 * created the cgroup
		 */
		deactivate_super(cgrp->root->sb);

		call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
	}
	iput(inode);
}

static void remove_dir(struct dentry *d)
{
	struct dentry *parent = dget(d->d_parent);

	d_delete(d);
	simple_rmdir(parent->d_inode, d);
	dput(parent);
}

static void cgroup_clear_directory(struct dentry *dentry)
{
	struct list_head *node;

	BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
	spin_lock(&dcache_lock);
	node = dentry->d_subdirs.next;
	while (node != &dentry->d_subdirs) {
		struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
		list_del_init(node);
		if (d->d_inode) {
			/* This should never be called on a cgroup
			 * directory with child cgroups */
			BUG_ON(d->d_inode->i_mode & S_IFDIR);
			d = dget_locked(d);
			spin_unlock(&dcache_lock);
			d_delete(d);
			simple_unlink(dentry->d_inode, d);
			dput(d);
			spin_lock(&dcache_lock);
		}
		node = dentry->d_subdirs.next;
	}
	spin_unlock(&dcache_lock);
}

/*
 * NOTE : the dentry must have been dget()'ed
 */
static void cgroup_d_remove_dir(struct dentry *dentry)
{
	cgroup_clear_directory(dentry);

	spin_lock(&dcache_lock);
	list_del_init(&dentry->d_u.d_child);
	spin_unlock(&dcache_lock);
	remove_dir(dentry);
}

/*
 * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
 * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
 * reference to css->refcnt. In general, this refcnt is expected to goes down
 * to zero, soon.
 *
 * CGRP_WAIT_ON_RMDIR flag is modified under cgroup's inode->i_mutex;
 */
DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);

static void cgroup_wakeup_rmdir_waiters(const struct cgroup *cgrp)
{
	if (unlikely(test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
		wake_up_all(&cgroup_rmdir_waitq);
}

static int rebind_subsystems(struct cgroupfs_root *root,
			      unsigned long final_bits)
{
	unsigned long added_bits, removed_bits;
	struct cgroup *cgrp = &root->top_cgroup;
	int i;

	removed_bits = root->actual_subsys_bits & ~final_bits;
	added_bits = final_bits & ~root->actual_subsys_bits;
	/* Check that any added subsystems are currently free */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		unsigned long bit = 1UL << i;
		struct cgroup_subsys *ss = subsys[i];
		if (!(bit & added_bits))
			continue;
		if (ss->root != &rootnode) {
			/* Subsystem isn't free */
			return -EBUSY;
		}
	}

	/* Currently we don't handle adding/removing subsystems when
	 * any child cgroups exist. This is theoretically supportable
	 * but involves complex error handling, so it's being left until
	 * later */
	if (root->number_of_cgroups > 1)
		return -EBUSY;

	/* Process each subsystem */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		unsigned long bit = 1UL << i;
		if (bit & added_bits) {
			/* We're binding this subsystem to this hierarchy */
			BUG_ON(cgrp->subsys[i]);
			BUG_ON(!dummytop->subsys[i]);
			BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
			mutex_lock(&ss->hierarchy_mutex);
			cgrp->subsys[i] = dummytop->subsys[i];
			cgrp->subsys[i]->cgroup = cgrp;
			list_move(&ss->sibling, &root->subsys_list);
			ss->root = root;
			if (ss->bind)
				ss->bind(ss, cgrp);
			mutex_unlock(&ss->hierarchy_mutex);
		} else if (bit & removed_bits) {
			/* We're removing this subsystem */
			BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]);
			BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
			mutex_lock(&ss->hierarchy_mutex);
			if (ss->bind)
				ss->bind(ss, dummytop);
			dummytop->subsys[i]->cgroup = dummytop;
			cgrp->subsys[i] = NULL;
			subsys[i]->root = &rootnode;
			list_move(&ss->sibling, &rootnode.subsys_list);
			mutex_unlock(&ss->hierarchy_mutex);
		} else if (bit & final_bits) {
			/* Subsystem state should already exist */
			BUG_ON(!cgrp->subsys[i]);
		} else {
			/* Subsystem state shouldn't exist */
			BUG_ON(cgrp->subsys[i]);
		}
	}
	root->subsys_bits = root->actual_subsys_bits = final_bits;
	synchronize_rcu();

	return 0;
}

static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
	struct cgroupfs_root *root = vfs->mnt_sb->s_fs_info;
	struct cgroup_subsys *ss;

	mutex_lock(&cgroup_mutex);
	for_each_subsys(root, ss)
		seq_printf(seq, ",%s", ss->name);
	if (test_bit(ROOT_NOPREFIX, &root->flags))
		seq_puts(seq, ",noprefix");
	if (strlen(root->release_agent_path))
		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
	mutex_unlock(&cgroup_mutex);
	return 0;
}

struct cgroup_sb_opts {
	unsigned long subsys_bits;
	unsigned long flags;
	char *release_agent;
};

/* Convert a hierarchy specifier into a bitmask of subsystems and
 * flags. */
static int parse_cgroupfs_options(char *data,
				     struct cgroup_sb_opts *opts)
{
	char *token, *o = data ?: "all";

	opts->subsys_bits = 0;
	opts->flags = 0;
	opts->release_agent = NULL;

	while ((token = strsep(&o, ",")) != NULL) {
		if (!*token)
			return -EINVAL;
		if (!strcmp(token, "all")) {
			/* Add all non-disabled subsystems */
			int i;
			opts->subsys_bits = 0;
			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
				struct cgroup_subsys *ss = subsys[i];
				if (!ss->disabled)
					opts->subsys_bits |= 1ul << i;
			}
		} else if (!strcmp(token, "noprefix")) {
			set_bit(ROOT_NOPREFIX, &opts->flags);
		} else if (!strncmp(token, "release_agent=", 14)) {
			/* Specifying two release agents is forbidden */
			if (opts->release_agent)
				return -EINVAL;
			opts->release_agent = kzalloc(PATH_MAX, GFP_KERNEL);
			if (!opts->release_agent)
				return -ENOMEM;
			strncpy(opts->release_agent, token + 14, PATH_MAX - 1);
			opts->release_agent[PATH_MAX - 1] = 0;
		} else {
			struct cgroup_subsys *ss;
			int i;
			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
				ss = subsys[i];
				if (!strcmp(token, ss->name)) {
					if (!ss->disabled)
						set_bit(i, &opts->subsys_bits);
					break;
				}
			}
			if (i == CGROUP_SUBSYS_COUNT)
				return -ENOENT;
		}
	}

	/* We can't have an empty hierarchy */
	if (!opts->subsys_bits)
		return -EINVAL;

	return 0;
}

static int cgroup_remount(struct super_block *sb, int *flags, char *data)
{
	int ret = 0;
	struct cgroupfs_root *root = sb->s_fs_info;
	struct cgroup *cgrp = &root->top_cgroup;
	struct cgroup_sb_opts opts;

	mutex_lock(&cgrp->dentry->d_inode->i_mutex);
	mutex_lock(&cgroup_mutex);

	/* See what subsystems are wanted */
	ret = parse_cgroupfs_options(data, &opts);
	if (ret)
		goto out_unlock;

	/* Don't allow flags to change at remount */
	if (opts.flags != root->flags) {
		ret = -EINVAL;
		goto out_unlock;
	}

	ret = rebind_subsystems(root, opts.subsys_bits);
	if (ret)
		goto out_unlock;

	/* (re)populate subsystem files */
	cgroup_populate_dir(cgrp);

	if (opts.release_agent)
		strcpy(root->release_agent_path, opts.release_agent);
 out_unlock:
	kfree(opts.release_agent);
	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
	return ret;
}

static struct super_operations cgroup_ops = {
	.statfs = simple_statfs,
	.drop_inode = generic_delete_inode,
	.show_options = cgroup_show_options,
	.remount_fs = cgroup_remount,
};

static void init_cgroup_housekeeping(struct cgroup *cgrp)
{
	INIT_LIST_HEAD(&cgrp->sibling);
	INIT_LIST_HEAD(&cgrp->children);
	INIT_LIST_HEAD(&cgrp->css_sets);
	INIT_LIST_HEAD(&cgrp->release_list);
	init_rwsem(&cgrp->pids_mutex);
}
static void init_cgroup_root(struct cgroupfs_root *root)
{
	struct cgroup *cgrp = &root->top_cgroup;
	INIT_LIST_HEAD(&root->subsys_list);
	INIT_LIST_HEAD(&root->root_list);
	root->number_of_cgroups = 1;
	cgrp->root = root;
	cgrp->top_cgroup = cgrp;
	init_cgroup_housekeeping(cgrp);
}

static int cgroup_test_super(struct super_block *sb, void *data)
{
	struct cgroupfs_root *new = data;
	struct cgroupfs_root *root = sb->s_fs_info;

	/* First check subsystems */
	if (new->subsys_bits != root->subsys_bits)
	    return 0;

	/* Next check flags */
	if (new->flags != root->flags)
		return 0;

	return 1;
}

static int cgroup_set_super(struct super_block *sb, void *data)
{
	int ret;
	struct cgroupfs_root *root = data;

	ret = set_anon_super(sb, NULL);
	if (ret)
		return ret;

	sb->s_fs_info = root;
	root->sb = sb;

	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = CGROUP_SUPER_MAGIC;
	sb->s_op = &cgroup_ops;

	return 0;
}

static int cgroup_get_rootdir(struct super_block *sb)
{
	struct inode *inode =
		cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
	struct dentry *dentry;

	if (!inode)
		return -ENOMEM;

	inode->i_fop = &simple_dir_operations;
	inode->i_op = &cgroup_dir_inode_operations;
	/* directories start off with i_nlink == 2 (for "." entry) */
	inc_nlink(inode);
	dentry = d_alloc_root(inode);
	if (!dentry) {
		iput(inode);
		return -ENOMEM;
	}
	sb->s_root = dentry;
	return 0;
}

static int cgroup_get_sb(struct file_system_type *fs_type,
			 int flags, const char *unused_dev_name,
			 void *data, struct vfsmount *mnt)
{
	struct cgroup_sb_opts opts;
	int ret = 0;
	struct super_block *sb;
	struct cgroupfs_root *root;
	struct list_head tmp_cg_links;

	/* First find the desired set of subsystems */
	ret = parse_cgroupfs_options(data, &opts);
	if (ret) {
		kfree(opts.release_agent);
		return ret;
	}

	root = kzalloc(sizeof(*root), GFP_KERNEL);
	if (!root) {
		kfree(opts.release_agent);
		return -ENOMEM;
	}

	init_cgroup_root(root);
	root->subsys_bits = opts.subsys_bits;
	root->flags = opts.flags;
	if (opts.release_agent) {
		strcpy(root->release_agent_path, opts.release_agent);
		kfree(opts.release_agent);
	}

	sb = sget(fs_type, cgroup_test_super, cgroup_set_super, root);

	if (IS_ERR(sb)) {
		kfree(root);
		return PTR_ERR(sb);
	}

	if (sb->s_fs_info != root) {
		/* Reusing an existing superblock */
		BUG_ON(sb->s_root == NULL);
		kfree(root);
		root = NULL;
	} else {
		/* New superblock */
		struct cgroup *root_cgrp = &root->top_cgroup;
		struct inode *inode;
		int i;

		BUG_ON(sb->s_root != NULL);

		ret = cgroup_get_rootdir(sb);
		if (ret)
			goto drop_new_super;
		inode = sb->s_root->d_inode;

		mutex_lock(&inode->i_mutex);
		mutex_lock(&cgroup_mutex);

		/*
		 * We're accessing css_set_count without locking
		 * css_set_lock here, but that's OK - it can only be
		 * increased by someone holding cgroup_lock, and
		 * that's us. The worst that can happen is that we
		 * have some link structures left over
		 */
		ret = allocate_cg_links(css_set_count, &tmp_cg_links);
		if (ret) {
			mutex_unlock(&cgroup_mutex);
			mutex_unlock(&inode->i_mutex);
			goto drop_new_super;
		}

		ret = rebind_subsystems(root, root->subsys_bits);
		if (ret == -EBUSY) {
			mutex_unlock(&cgroup_mutex);
			mutex_unlock(&inode->i_mutex);
			goto free_cg_links;
		}

		/* EBUSY should be the only error here */
		BUG_ON(ret);

		list_add(&root->root_list, &roots);
		root_count++;

		sb->s_root->d_fsdata = root_cgrp;
		root->top_cgroup.dentry = sb->s_root;

		/* Link the top cgroup in this hierarchy into all
		 * the css_set objects */
		write_lock(&css_set_lock);
		for (i = 0; i < CSS_SET_TABLE_SIZE; i++) {
			struct hlist_head *hhead = &css_set_table[i];
			struct hlist_node *node;
			struct css_set *cg;

			hlist_for_each_entry(cg, node, hhead, hlist)
				link_css_set(&tmp_cg_links, cg, root_cgrp);
		}
		write_unlock(&css_set_lock);

		free_cg_links(&tmp_cg_links);

		BUG_ON(!list_empty(&root_cgrp->sibling));
		BUG_ON(!list_empty(&root_cgrp->children));
		BUG_ON(root->number_of_cgroups != 1);

		cgroup_populate_dir(root_cgrp);
		mutex_unlock(&inode->i_mutex);
		mutex_unlock(&cgroup_mutex);
	}

	simple_set_mnt(mnt, sb);
	return 0;

 free_cg_links:
	free_cg_links(&tmp_cg_links);
 drop_new_super:
	up_write(&sb->s_umount);
	deactivate_super(sb);
	return ret;
}

static void cgroup_kill_sb(struct super_block *sb) {
	struct cgroupfs_root *root = sb->s_fs_info;
	struct cgroup *cgrp = &root->top_cgroup;
	int ret;
	struct cg_cgroup_link *link;
	struct cg_cgroup_link *saved_link;

	BUG_ON(!root);

	BUG_ON(root->number_of_cgroups != 1);
	BUG_ON(!list_empty(&cgrp->children));
	BUG_ON(!list_empty(&cgrp->sibling));

	mutex_lock(&cgroup_mutex);

	/* Rebind all subsystems back to the default hierarchy */
	ret = rebind_subsystems(root, 0);
	/* Shouldn't be able to fail ... */
	BUG_ON(ret);

	/*
	 * Release all the links from css_sets to this hierarchy's
	 * root cgroup
	 */
	write_lock(&css_set_lock);

	list_for_each_entry_safe(link, saved_link, &cgrp->css_sets,
				 cgrp_link_list) {
		list_del(&link->cg_link_list);
		list_del(&link->cgrp_link_list);
		kfree(link);
	}
	write_unlock(&css_set_lock);

	if (!list_empty(&root->root_list)) {
		list_del(&root->root_list);
		root_count--;
	}

	mutex_unlock(&cgroup_mutex);

	kill_litter_super(sb);
	kfree(root);
}

static struct file_system_type cgroup_fs_type = {
	.name = "cgroup",
	.get_sb = cgroup_get_sb,
	.kill_sb = cgroup_kill_sb,
};

static inline struct cgroup *__d_cgrp(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

static inline struct cftype *__d_cft(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

/**
 * cgroup_path - generate the path of a cgroup
 * @cgrp: the cgroup in question
 * @buf: the buffer to write the path into
 * @buflen: the length of the buffer
 *
 * Called with cgroup_mutex held or else with an RCU-protected cgroup
 * reference.  Writes path of cgroup into buf.  Returns 0 on success,
 * -errno on error.
 */
int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
{
	char *start;
	struct dentry *dentry = rcu_dereference(cgrp->dentry);

	if (!dentry || cgrp == dummytop) {
		/*
		 * Inactive subsystems have no dentry for their root
		 * cgroup
		 */
		strcpy(buf, "/");
		return 0;
	}

	start = buf + buflen;

	*--start = '\0';
	for (;;) {
		int len = dentry->d_name.len;
		if ((start -= len) < buf)
			return -ENAMETOOLONG;
		memcpy(start, cgrp->dentry->d_name.name, len);
		cgrp = cgrp->parent;
		if (!cgrp)
			break;
		dentry = rcu_dereference(cgrp->dentry);
		if (!cgrp->parent)
			continue;
		if (--start < buf)
			return -ENAMETOOLONG;
		*start = '/';
	}
	memmove(buf, start, buf + buflen - start);
	return 0;
}

/*
 * Return the first subsystem attached to a cgroup's hierarchy, and
 * its subsystem id.
 */

static void get_first_subsys(const struct cgroup *cgrp,
			struct cgroup_subsys_state **css, int *subsys_id)
{
	const struct cgroupfs_root *root = cgrp->root;
	const struct cgroup_subsys *test_ss;
	BUG_ON(list_empty(&root->subsys_list));
	test_ss = list_entry(root->subsys_list.next,
			     struct cgroup_subsys, sibling);
	if (css) {
		*css = cgrp->subsys[test_ss->subsys_id];
		BUG_ON(!*css);
	}
	if (subsys_id)
		*subsys_id = test_ss->subsys_id;
}

/**
 * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
 * @cgrp: the cgroup the task is attaching to
 * @tsk: the task to be attached
 *
 * Call holding cgroup_mutex. May take task_lock of
 * the task 'tsk' during call.
 */
int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
{
	int retval = 0;
	struct cgroup_subsys *ss;
	struct cgroup *oldcgrp;
	struct css_set *cg;
	struct css_set *newcg;
	struct cgroupfs_root *root = cgrp->root;
	int subsys_id;

	get_first_subsys(cgrp, NULL, &subsys_id);

	/* Nothing to do if the task is already in that cgroup */
	oldcgrp = task_cgroup(tsk, subsys_id);
	if (cgrp == oldcgrp)
		return 0;

	for_each_subsys(root, ss) {
		if (ss->can_attach) {
			retval = ss->can_attach(ss, cgrp, tsk);
			if (retval)
				return retval;
		}
	}

	task_lock(tsk);
	cg = tsk->cgroups;
	get_css_set(cg);
	task_unlock(tsk);
	/*
	 * Locate or allocate a new css_set for this task,
	 * based on its final set of cgroups
	 */
	newcg = find_css_set(cg, cgrp);
	put_css_set(cg);
	if (!newcg)
		return -ENOMEM;

	task_lock(tsk);
	if (tsk->flags & PF_EXITING) {
		task_unlock(tsk);
		put_css_set(newcg);
		return -ESRCH;
	}
	rcu_assign_pointer(tsk->cgroups, newcg);
	task_unlock(tsk);

	/* Update the css_set linked lists if we're using them */
	write_lock(&css_set_lock);
	if (!list_empty(&tsk->cg_list)) {
		list_del(&tsk->cg_list);
		list_add(&tsk->cg_list, &newcg->tasks);
	}
	write_unlock(&css_set_lock);

	for_each_subsys(root, ss) {
		if (ss->attach)
			ss->attach(ss, cgrp, oldcgrp, tsk);
	}
	set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
	synchronize_rcu();
	put_css_set(cg);

	/*
	 * wake up rmdir() waiter. the rmdir should fail since the cgroup
	 * is no longer empty.
	 */
	cgroup_wakeup_rmdir_waiters(cgrp);
	return 0;
}

/*
 * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
 * held. May take task_lock of task
 */
static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
{
	struct task_struct *tsk;
	const struct cred *cred = current_cred(), *tcred;
	int ret;

	if (pid) {
		rcu_read_lock();
		tsk = find_task_by_vpid(pid);
		if (!tsk || tsk->flags & PF_EXITING) {
			rcu_read_unlock();
			return -ESRCH;
		}

		tcred = __task_cred(tsk);
		if (cred->euid &&
		    cred->euid != tcred->uid &&
		    cred->euid != tcred->suid) {
			rcu_read_unlock();
			return -EACCES;
		}
		get_task_struct(tsk);
		rcu_read_unlock();
	} else {
		tsk = current;
		get_task_struct(tsk);
	}

	ret = cgroup_attach_task(cgrp, tsk);
	put_task_struct(tsk);
	return ret;
}

static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
{
	int ret;
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;
	ret = attach_task_by_pid(cgrp, pid);
	cgroup_unlock();
	return ret;
}

/* The various types of files and directories in a cgroup file system */
enum cgroup_filetype {
	FILE_ROOT,
	FILE_DIR,
	FILE_TASKLIST,
	FILE_NOTIFY_ON_RELEASE,
	FILE_RELEASE_AGENT,
};

/**
 * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
 * @cgrp: the cgroup to be checked for liveness
 *
 * On success, returns true; the lock should be later released with
 * cgroup_unlock(). On failure returns false with no lock held.
 */
bool cgroup_lock_live_group(struct cgroup *cgrp)
{
	mutex_lock(&cgroup_mutex);
	if (cgroup_is_removed(cgrp)) {
		mutex_unlock(&cgroup_mutex);
		return false;
	}
	return true;
}

static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
				      const char *buffer)
{
	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;
	strcpy(cgrp->root->release_agent_path, buffer);
	cgroup_unlock();
	return 0;
}

static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft,
				     struct seq_file *seq)
{
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;
	seq_puts(seq, cgrp->root->release_agent_path);
	seq_putc(seq, '\n');
	cgroup_unlock();
	return 0;
}

/* A buffer size big enough for numbers or short strings */
#define CGROUP_LOCAL_BUFFER_SIZE 64

static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
				struct file *file,
				const char __user *userbuf,
				size_t nbytes, loff_t *unused_ppos)
{
	char buffer[CGROUP_LOCAL_BUFFER_SIZE];
	int retval = 0;
	char *end;

	if (!nbytes)
		return -EINVAL;
	if (nbytes >= sizeof(buffer))
		return -E2BIG;
	if (copy_from_user(buffer, userbuf, nbytes))
		return -EFAULT;

	buffer[nbytes] = 0;     /* nul-terminate */
	strstrip(buffer);
	if (cft->write_u64) {
		u64 val = simple_strtoull(buffer, &end, 0);
		if (*end)
			return -EINVAL;
		retval = cft->write_u64(cgrp, cft, val);
	} else {
		s64 val = simple_strtoll(buffer, &end, 0);
		if (*end)
			return -EINVAL;
		retval = cft->write_s64(cgrp, cft, val);
	}
	if (!retval)
		retval = nbytes;
	return retval;
}

static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft,
				   struct file *file,
				   const char __user *userbuf,
				   size_t nbytes, loff_t *unused_ppos)
{
	char local_buffer[CGROUP_LOCAL_BUFFER_SIZE];
	int retval = 0;
	size_t max_bytes = cft->max_write_len;
	char *buffer = local_buffer;

	if (!max_bytes)
		max_bytes = sizeof(local_buffer) - 1;
	if (nbytes >= max_bytes)
		return -E2BIG;
	/* Allocate a dynamic buffer if we need one */
	if (nbytes >= sizeof(local_buffer)) {
		buffer = kmalloc(nbytes + 1, GFP_KERNEL);
		if (buffer == NULL)
			return -ENOMEM;
	}
	if (nbytes && copy_from_user(buffer, userbuf, nbytes)) {
		retval = -EFAULT;
		goto out;
	}

	buffer[nbytes] = 0;     /* nul-terminate */
	strstrip(buffer);
	retval = cft->write_string(cgrp, cft, buffer);
	if (!retval)
		retval = nbytes;
out:
	if (buffer != local_buffer)
		kfree(buffer);
	return retval;
}

static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
						size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);

	if (cgroup_is_removed(cgrp))
		return -ENODEV;
	if (cft->write)
		return cft->write(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->write_u64 || cft->write_s64)
		return cgroup_write_X64(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->write_string)
		return cgroup_write_string(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->trigger) {
		int ret = cft->trigger(cgrp, (unsigned int)cft->private);
		return ret ? ret : nbytes;
	}
	return -EINVAL;
}

static ssize_t cgroup_read_u64(struct cgroup *cgrp, struct cftype *cft,
			       struct file *file,
			       char __user *buf, size_t nbytes,
			       loff_t *ppos)
{
	char tmp[CGROUP_LOCAL_BUFFER_SIZE];
	u64 val = cft->read_u64(cgrp, cft);
	int len = sprintf(tmp, "%llu\n", (unsigned long long) val);

	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}

static ssize_t cgroup_read_s64(struct cgroup *cgrp, struct cftype *cft,
			       struct file *file,
			       char __user *buf, size_t nbytes,
			       loff_t *ppos)
{
	char tmp[CGROUP_LOCAL_BUFFER_SIZE];
	s64 val = cft->read_s64(cgrp, cft);
	int len = sprintf(tmp, "%lld\n", (long long) val);

	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}

static ssize_t cgroup_file_read(struct file *file, char __user *buf,
				   size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);

	if (cgroup_is_removed(cgrp))
		return -ENODEV;

	if (cft->read)
		return cft->read(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->read_u64)
		return cgroup_read_u64(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->read_s64)
		return cgroup_read_s64(cgrp, cft, file, buf, nbytes, ppos);
	return -EINVAL;
}

/*
 * seqfile ops/methods for returning structured data. Currently just
 * supports string->u64 maps, but can be extended in future.
 */

struct cgroup_seqfile_state {
	struct cftype *cft;
	struct cgroup *cgroup;
};

static int cgroup_map_add(struct cgroup_map_cb *cb, const char *key, u64 value)
{
	struct seq_file *sf = cb->state;
	return seq_printf(sf, "%s %llu\n", key, (unsigned long long)value);
}

static int cgroup_seqfile_show(struct seq_file *m, void *arg)
{
	struct cgroup_seqfile_state *state = m->private;
	struct cftype *cft = state->cft;
	if (cft->read_map) {
		struct cgroup_map_cb cb = {
			.fill = cgroup_map_add,
			.state = m,
		};
		return cft->read_map(state->cgroup, cft, &cb);
	}
	return cft->read_seq_string(state->cgroup, cft, m);
}

static int cgroup_seqfile_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	kfree(seq->private);
	return single_release(inode, file);
}

static struct file_operations cgroup_seqfile_operations = {
	.read = seq_read,
	.write = cgroup_file_write,
	.llseek = seq_lseek,
	.release = cgroup_seqfile_release,
};

static int cgroup_file_open(struct inode *inode, struct file *file)
{
	int err;
	struct cftype *cft;

	err = generic_file_open(inode, file);
	if (err)
		return err;
	cft = __d_cft(file->f_dentry);

	if (cft->read_map || cft->read_seq_string) {
		struct cgroup_seqfile_state *state =
			kzalloc(sizeof(*state), GFP_USER);
		if (!state)
			return -ENOMEM;
		state->cft = cft;
		state->cgroup = __d_cgrp(file->f_dentry->d_parent);
		file->f_op = &cgroup_seqfile_operations;
		err = single_open(file, cgroup_seqfile_show, state);
		if (err < 0)
			kfree(state);
	} else if (cft->open)
		err = cft->open(inode, file);
	else
		err = 0;

	return err;
}

static int cgroup_file_release(struct inode *inode, struct file *file)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	if (cft->release)
		return cft->release(inode, file);
	return 0;
}

/*
 * cgroup_rename - Only allow simple rename of directories in place.
 */
static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
			    struct inode *new_dir, struct dentry *new_dentry)
{
	if (!S_ISDIR(old_dentry->d_inode->i_mode))
		return -ENOTDIR;
	if (new_dentry->d_inode)
		return -EEXIST;
	if (old_dir != new_dir)
		return -EIO;
	return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
}

static struct file_operations cgroup_file_operations = {
	.read = cgroup_file_read,
	.write = cgroup_file_write,
	.llseek = generic_file_llseek,
	.open = cgroup_file_open,
	.release = cgroup_file_release,
};

static struct inode_operations cgroup_dir_inode_operations = {
	.lookup = simple_lookup,
	.mkdir = cgroup_mkdir,
	.rmdir = cgroup_rmdir,
	.rename = cgroup_rename,
};

static int cgroup_create_file(struct dentry *dentry, mode_t mode,
				struct super_block *sb)
{
	static const struct dentry_operations cgroup_dops = {
		.d_iput = cgroup_diput,
	};

	struct inode *inode;

	if (!dentry)
		return -ENOENT;
	if (dentry->d_inode)
		return -EEXIST;

	inode = cgroup_new_inode(mode, sb);
	if (!inode)
		return -ENOMEM;

	if (S_ISDIR(mode)) {
		inode->i_op = &cgroup_dir_inode_operations;
		inode->i_fop = &simple_dir_operations;

		/* start off with i_nlink == 2 (for "." entry) */
		inc_nlink(inode);

		/* start with the directory inode held, so that we can
		 * populate it without racing with another mkdir */
		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
	} else if (S_ISREG(mode)) {
		inode->i_size = 0;
		inode->i_fop = &cgroup_file_operations;
	}
	dentry->d_op = &cgroup_dops;
	d_instantiate(dentry, inode);
	dget(dentry);	/* Extra count - pin the dentry in core */
	return 0;
}

/*
 * cgroup_create_dir - create a directory for an object.
 * @cgrp: the cgroup we create the directory for. It must have a valid
 *        ->parent field. And we are going to fill its ->dentry field.
 * @dentry: dentry of the new cgroup
 * @mode: mode to set on new directory.
 */
static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
				mode_t mode)
{
	struct dentry *parent;
	int error = 0;

	parent = cgrp->parent->dentry;
	error = cgroup_create_file(dentry, S_IFDIR | mode, cgrp->root->sb);
	if (!error) {
		dentry->d_fsdata = cgrp;
		inc_nlink(parent->d_inode);
		rcu_assign_pointer(cgrp->dentry, dentry);
		dget(dentry);
	}
	dput(dentry);

	return error;
}

/**
 * cgroup_file_mode - deduce file mode of a control file
 * @cft: the control file in question
 *
 * returns cft->mode if ->mode is not 0
 * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
 * returns S_IRUGO if it has only a read handler
 * returns S_IWUSR if it has only a write hander
 */
static mode_t cgroup_file_mode(const struct cftype *cft)
{
	mode_t mode = 0;

	if (cft->mode)
		return cft->mode;

	if (cft->read || cft->read_u64 || cft->read_s64 ||
	    cft->read_map || cft->read_seq_string)
		mode |= S_IRUGO;

	if (cft->write || cft->write_u64 || cft->write_s64 ||
	    cft->write_string || cft->trigger)
		mode |= S_IWUSR;

	return mode;
}

int cgroup_add_file(struct cgroup *cgrp,
		       struct cgroup_subsys *subsys,
		       const struct cftype *cft)
{
	struct dentry *dir = cgrp->dentry;
	struct dentry *dentry;
	int error;
	mode_t mode;

	char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
	if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
		strcpy(name, subsys->name);
		strcat(name, ".");
	}
	strcat(name, cft->name);
	BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
	dentry = lookup_one_len(name, dir, strlen(name));
	if (!IS_ERR(dentry)) {
		mode = cgroup_file_mode(cft);
		error = cgroup_create_file(dentry, mode | S_IFREG,
						cgrp->root->sb);
		if (!error)
			dentry->d_fsdata = (void *)cft;
		dput(dentry);
	} else
		error = PTR_ERR(dentry);
	return error;
}

int cgroup_add_files(struct cgroup *cgrp,
			struct cgroup_subsys *subsys,
			const struct cftype cft[],
			int count)
{
	int i, err;
	for (i = 0; i < count; i++) {
		err = cgroup_add_file(cgrp, subsys, &cft[i]);
		if (err)
			return err;
	}
	return 0;
}

/**
 * cgroup_task_count - count the number of tasks in a cgroup.
 * @cgrp: the cgroup in question
 *
 * Return the number of tasks in the cgroup.
 */
int cgroup_task_count(const struct cgroup *cgrp)
{
	int count = 0;
	struct cg_cgroup_link *link;

	read_lock(&css_set_lock);
	list_for_each_entry(link, &cgrp->css_sets, cgrp_link_list) {
		count += atomic_read(&link->cg->refcount);
	}
	read_unlock(&css_set_lock);
	return count;
}

/*
 * Advance a list_head iterator.  The iterator should be positioned at
 * the start of a css_set
 */
static void cgroup_advance_iter(struct cgroup *cgrp,
					  struct cgroup_iter *it)
{
	struct list_head *l = it->cg_link;
	struct cg_cgroup_link *link;
	struct css_set *cg;

	/* Advance to the next non-empty css_set */
	do {
		l = l->next;
		if (l == &cgrp->css_sets) {
			it->cg_link = NULL;
			return;
		}
		link = list_entry(l, struct cg_cgroup_link, cgrp_link_list);
		cg = link->cg;
	} while (list_empty(&cg->tasks));
	it->cg_link = l;
	it->task = cg->tasks.next;
}

/*
 * To reduce the fork() overhead for systems that are not actually
 * using their cgroups capability, we don't maintain the lists running
 * through each css_set to its tasks until we see the list actually
 * used - in other words after the first call to cgroup_iter_start().
 *
 * The tasklist_lock is not held here, as do_each_thread() and
 * while_each_thread() are protected by RCU.
 */
static void cgroup_enable_task_cg_lists(void)
{
	struct task_struct *p, *g;
	write_lock(&css_set_lock);
	use_task_css_set_links = 1;
	do_each_thread(g, p) {
		task_lock(p);
		/*
		 * We should check if the process is exiting, otherwise
		 * it will race with cgroup_exit() in that the list
		 * entry won't be deleted though the process has exited.
		 */
		if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
			list_add(&p->cg_list, &p->cgroups->tasks);
		task_unlock(p);
	} while_each_thread(g, p);
	write_unlock(&css_set_lock);
}

void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
{
	/*
	 * The first time anyone tries to iterate across a cgroup,
	 * we need to enable the list linking each css_set to its
	 * tasks, and fix up all existing tasks.
	 */
	if (!use_task_css_set_links)
		cgroup_enable_task_cg_lists();

	read_lock(&css_set_lock);
	it->cg_link = &cgrp->css_sets;
	cgroup_advance_iter(cgrp, it);
}

struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
					struct cgroup_iter *it)
{
	struct task_struct *res;
	struct list_head *l = it->task;
	struct cg_cgroup_link *link;

	/* If the iterator cg is NULL, we have no tasks */
	if (!it->cg_link)
		return NULL;
	res = list_entry(l, struct task_struct, cg_list);
	/* Advance iterator to find next entry */
	l = l->next;
	link = list_entry(it->cg_link, struct cg_cgroup_link, cgrp_link_list);
	if (l == &link->cg->tasks) {
		/* We reached the end of this task list - move on to
		 * the next cg_cgroup_link */
		cgroup_advance_iter(cgrp, it);
	} else {
		it->task = l;
	}
	return res;
}

void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it)
{
	read_unlock(&css_set_lock);
}

static inline int started_after_time(struct task_struct *t1,
				     struct timespec *time,
				     struct task_struct *t2)
{
	int start_diff = timespec_compare(&t1->start_time, time);
	if (start_diff > 0) {
		return 1;
	} else if (start_diff < 0) {
		return 0;
	} else {
		/*
		 * Arbitrarily, if two processes started at the same
		 * time, we'll say that the lower pointer value
		 * started first. Note that t2 may have exited by now
		 * so this may not be a valid pointer any longer, but
		 * that's fine - it still serves to distinguish
		 * between two tasks started (effectively) simultaneously.
		 */
		return t1 > t2;
	}
}

/*
 * This function is a callback from heap_insert() and is used to order
 * the heap.
 * In this case we order the heap in descending task start time.
 */
static inline int started_after(void *p1, void *p2)
{
	struct task_struct *t1 = p1;
	struct task_struct *t2 = p2;
	return started_after_time(t1, &t2->start_time, t2);
}

/**
 * cgroup_scan_tasks - iterate though all the tasks in a cgroup
 * @scan: struct cgroup_scanner containing arguments for the scan
 *
 * Arguments include pointers to callback functions test_task() and
 * process_task().
 * Iterate through all the tasks in a cgroup, calling test_task() for each,
 * and if it returns true, call process_task() for it also.
 * The test_task pointer may be NULL, meaning always true (select all tasks).
 * Effectively duplicates cgroup_iter_{start,next,end}()
 * but does not lock css_set_lock for the call to process_task().
 * The struct cgroup_scanner may be embedded in any structure of the caller's
 * creation.
 * It is guaranteed that process_task() will act on every task that
 * is a member of the cgroup for the duration of this call. This
 * function may or may not call process_task() for tasks that exit
 * or move to a different cgroup during the call, or are forked or
 * move into the cgroup during the call.
 *
 * Note that test_task() may be called with locks held, and may in some
 * situations be called multiple times for the same task, so it should
 * be cheap.
 * If the heap pointer in the struct cgroup_scanner is non-NULL, a heap has been
 * pre-allocated and will be used for heap operations (and its "gt" member will
 * be overwritten), else a temporary heap will be used (allocation of which
 * may cause this function to fail).
 */
int cgroup_scan_tasks(struct cgroup_scanner *scan)
{
	int retval, i;
	struct cgroup_iter it;
	struct task_struct *p, *dropped;
	/* Never dereference latest_task, since it's not refcounted */
	struct task_struct *latest_task = NULL;
	struct ptr_heap tmp_heap;
	struct ptr_heap *heap;
	struct timespec latest_time = { 0, 0 };

	if (scan->heap) {
		/* The caller supplied our heap and pre-allocated its memory */
		heap = scan->heap;
		heap->gt = &started_after;
	} else {
		/* We need to allocate our own heap memory */
		heap = &tmp_heap;
		retval = heap_init(heap, PAGE_SIZE, GFP_KERNEL, &started_after);
		if (retval)
			/* cannot allocate the heap */
			return retval;
	}

 again:
	/*
	 * Scan tasks in the cgroup, using the scanner's "test_task" callback
	 * to determine which are of interest, and using the scanner's
	 * "process_task" callback to process any of them that need an update.
	 * Since we don't want to hold any locks during the task updates,
	 * gather tasks to be processed in a heap structure.
	 * The heap is sorted by descending task start time.
	 * If the statically-sized heap fills up, we overflow tasks that
	 * started later, and in future iterations only consider tasks that
	 * started after the latest task in the previous pass. This
	 * guarantees forward progress and that we don't miss any tasks.
	 */
	heap->size = 0;
	cgroup_iter_start(scan->cg, &it);
	while ((p = cgroup_iter_next(scan->cg, &it))) {
		/*
		 * Only affect tasks that qualify per the caller's callback,
		 * if he provided one
		 */
		if (scan->test_task && !scan->test_task(p, scan))
			continue;
		/*
		 * Only process tasks that started after the last task
		 * we processed
		 */
		if (!started_after_time(p, &latest_time, latest_task))
			continue;
		dropped = heap_insert(heap, p);
		if (dropped == NULL) {
			/*
			 * The new task was inserted; the heap wasn't
			 * previously full
			 */
			get_task_struct(p);
		} else if (dropped != p) {
			/*
			 * The new task was inserted, and pushed out a
			 * different task
			 */
			get_task_struct(p);
			put_task_struct(dropped);
		}
		/*
		 * Else the new task was newer than anything already in
		 * the heap and wasn't inserted
		 */
	}
	cgroup_iter_end(scan->cg, &it);

	if (heap->size) {
		for (i = 0; i < heap->size; i++) {
			struct task_struct *q = heap->ptrs[i];
			if (i == 0) {
				latest_time = q->start_time;
				latest_task = q;
			}
			/* Process the task per the caller's callback */
			scan->process_task(q, scan);
			put_task_struct(q);
		}
		/*
		 * If we had to process any tasks at all, scan again
		 * in case some of them were in the middle of forking
		 * children that didn't get processed.
		 * Not the most efficient way to do it, but it avoids
		 * having to take callback_mutex in the fork path
		 */
		goto again;
	}
	if (heap == &tmp_heap)
		heap_free(&tmp_heap);
	return 0;
}

/*
 * Stuff for reading the 'tasks' file.
 *
 * Reading this file can return large amounts of data if a cgroup has
 * *lots* of attached tasks. So it may need several calls to read(),
 * but we cannot guarantee that the information we produce is correct
 * unless we produce it entirely atomically.
 *
 */

/*
 * Load into 'pidarray' up to 'npids' of the tasks using cgroup
 * 'cgrp'.  Return actual number of pids loaded.  No need to
 * task_lock(p) when reading out p->cgroup, since we're in an RCU
 * read section, so the css_set can't go away, and is
 * immutable after creation.
 */
static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp)
{
	int n = 0, pid;
	struct cgroup_iter it;
	struct task_struct *tsk;
	cgroup_iter_start(cgrp, &it);
	while ((tsk = cgroup_iter_next(cgrp, &it))) {
		if (unlikely(n == npids))
			break;
		pid = task_pid_vnr(tsk);
		if (pid > 0)
			pidarray[n++] = pid;
	}
	cgroup_iter_end(cgrp, &it);
	return n;
}

/**
 * cgroupstats_build - build and fill cgroupstats
 * @stats: cgroupstats to fill information into
 * @dentry: A dentry entry belonging to the cgroup for which stats have
 * been requested.
 *
 * Build and fill cgroupstats so that taskstats can export it to user
 * space.
 */
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
{
	int ret = -EINVAL;
	struct cgroup *cgrp;
	struct cgroup_iter it;
	struct task_struct *tsk;

	/*
	 * Validate dentry by checking the superblock operations,
	 * and make sure it's a directory.
	 */
	if (dentry->d_sb->s_op != &cgroup_ops ||
	    !S_ISDIR(dentry->d_inode->i_mode))
		 goto err;

	ret = 0;
	cgrp = dentry->d_fsdata;

	cgroup_iter_start(cgrp, &it);
	while ((tsk = cgroup_iter_next(cgrp, &it))) {
		switch (tsk->state) {
		case TASK_RUNNING:
			stats->nr_running++;
			break;
		case TASK_INTERRUPTIBLE:
			stats->nr_sleeping++;
			break;
		case TASK_UNINTERRUPTIBLE:
			stats->nr_uninterruptible++;
			break;
		case TASK_STOPPED:
			stats->nr_stopped++;
			break;
		default:
			if (delayacct_is_task_waiting_on_io(tsk))
				stats->nr_io_wait++;
			break;
		}
	}
	cgroup_iter_end(cgrp, &it);

err:
	return ret;
}

static int cmppid(const void *a, const void *b)
{
	return *(pid_t *)a - *(pid_t *)b;
}


/*
 * seq_file methods for the "tasks" file. The seq_file position is the
 * next pid to display; the seq_file iterator is a pointer to the pid
 * in the cgroup->tasks_pids array.
 */

static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
{
	/*
	 * Initially we receive a position value that corresponds to
	 * one more than the last pid shown (or 0 on the first call or
	 * after a seek to the start). Use a binary-search to find the
	 * next pid to display, if any
	 */
	struct cgroup *cgrp = s->private;
	int index = 0, pid = *pos;
	int *iter;

	down_read(&cgrp->pids_mutex);
	if (pid) {
		int end = cgrp->pids_length;

		while (index < end) {
			int mid = (index + end) / 2;
			if (cgrp->tasks_pids[mid] == pid) {
				index = mid;
				break;
			} else if (cgrp->tasks_pids[mid] <= pid)
				index = mid + 1;
			else
				end = mid;
		}
	}
	/* If we're off the end of the array, we're done */
	if (index >= cgrp->pids_length)
		return NULL;
	/* Update the abstract position to be the actual pid that we found */
	iter = cgrp->tasks_pids + index;
	*pos = *iter;
	return iter;
}

static void cgroup_tasks_stop(struct seq_file *s, void *v)
{
	struct cgroup *cgrp = s->private;
	up_read(&cgrp->pids_mutex);
}

static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
{
	struct cgroup *cgrp = s->private;
	int *p = v;
	int *end = cgrp->tasks_pids + cgrp->pids_length;

	/*
	 * Advance to the next pid in the array. If this goes off the
	 * end, we're done
	 */
	p++;
	if (p >= end) {
		return NULL;
	} else {
		*pos = *p;
		return p;
	}
}

static int cgroup_tasks_show(struct seq_file *s, void *v)
{
	return seq_printf(s, "%d\n", *(int *)v);
}

static struct seq_operations cgroup_tasks_seq_operations = {
	.start = cgroup_tasks_start,
	.stop = cgroup_tasks_stop,
	.next = cgroup_tasks_next,
	.show = cgroup_tasks_show,
};

static void release_cgroup_pid_array(struct cgroup *cgrp)
{
	down_write(&cgrp->pids_mutex);
	BUG_ON(!cgrp->pids_use_count);
	if (!--cgrp->pids_use_count) {
		kfree(cgrp->tasks_pids);
		cgrp->tasks_pids = NULL;
		cgrp->pids_length = 0;
	}
	up_write(&cgrp->pids_mutex);
}

static int cgroup_tasks_release(struct inode *inode, struct file *file)
{
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);

	if (!(file->f_mode & FMODE_READ))
		return 0;

	release_cgroup_pid_array(cgrp);
	return seq_release(inode, file);
}

static struct file_operations cgroup_tasks_operations = {
	.read = seq_read,
	.llseek = seq_lseek,
	.write = cgroup_file_write,
	.release = cgroup_tasks_release,
};

/*
 * Handle an open on 'tasks' file.  Prepare an array containing the
 * process id's of tasks currently attached to the cgroup being opened.
 */

static int cgroup_tasks_open(struct inode *unused, struct file *file)
{
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
	pid_t *pidarray;
	int npids;
	int retval;

	/* Nothing to do for write-only files */
	if (!(file->f_mode & FMODE_READ))
		return 0;

	/*
	 * If cgroup gets more users after we read count, we won't have
	 * enough space - tough.  This race is indistinguishable to the
	 * caller from the case that the additional cgroup users didn't
	 * show up until sometime later on.
	 */
	npids = cgroup_task_count(cgrp);
	pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
	if (!pidarray)
		return -ENOMEM;
	npids = pid_array_load(pidarray, npids, cgrp);
	sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);

	/*
	 * Store the array in the cgroup, freeing the old
	 * array if necessary
	 */
	down_write(&cgrp->pids_mutex);
	kfree(cgrp->tasks_pids);
	cgrp->tasks_pids = pidarray;
	cgrp->pids_length = npids;
	cgrp->pids_use_count++;
	up_write(&cgrp->pids_mutex);

	file->f_op = &cgroup_tasks_operations;

	retval = seq_open(file, &cgroup_tasks_seq_operations);
	if (retval) {
		release_cgroup_pid_array(cgrp);
		return retval;
	}
	((struct seq_file *)file->private_data)->private = cgrp;
	return 0;
}

static u64 cgroup_read_notify_on_release(struct cgroup *cgrp,
					    struct cftype *cft)
{
	return notify_on_release(cgrp);
}

static int cgroup_write_notify_on_release(struct cgroup *cgrp,
					  struct cftype *cft,
					  u64 val)
{
	clear_bit(CGRP_RELEASABLE, &cgrp->flags);
	if (val)
		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
	else
		clear_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
	return 0;
}

/*
 * for the common functions, 'private' gives the type of file
 */
static struct cftype files[] = {
	{
		.name = "tasks",
		.open = cgroup_tasks_open,
		.write_u64 = cgroup_tasks_write,
		.release = cgroup_tasks_release,
		.private = FILE_TASKLIST,
		.mode = S_IRUGO | S_IWUSR,
	},

	{
		.name = "notify_on_release",
		.read_u64 = cgroup_read_notify_on_release,
		.write_u64 = cgroup_write_notify_on_release,
		.private = FILE_NOTIFY_ON_RELEASE,
	},
};

static struct cftype cft_release_agent = {
	.name = "release_agent",
	.read_seq_string = cgroup_release_agent_show,
	.write_string = cgroup_release_agent_write,
	.max_write_len = PATH_MAX,
	.private = FILE_RELEASE_AGENT,
};

static int cgroup_populate_dir(struct cgroup *cgrp)
{
	int err;
	struct cgroup_subsys *ss;

	/* First clear out any existing files */
	cgroup_clear_directory(cgrp->dentry);

	err = cgroup_add_files(cgrp, NULL, files, ARRAY_SIZE(files));
	if (err < 0)
		return err;

	if (cgrp == cgrp->top_cgroup) {
		if ((err = cgroup_add_file(cgrp, NULL, &cft_release_agent)) < 0)
			return err;
	}

	for_each_subsys(cgrp->root, ss) {
		if (ss->populate && (err = ss->populate(ss, cgrp)) < 0)
			return err;
	}
	/* This cgroup is ready now */
	for_each_subsys(cgrp->root, ss) {
		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
		/*
		 * Update id->css pointer and make this css visible from
		 * CSS ID functions. This pointer will be dereferened
		 * from RCU-read-side without locks.
		 */
		if (css->id)
			rcu_assign_pointer(css->id->css, css);
	}

	return 0;
}

static void init_cgroup_css(struct cgroup_subsys_state *css,
			       struct cgroup_subsys *ss,
			       struct cgroup *cgrp)
{
	css->cgroup = cgrp;
	atomic_set(&css->refcnt, 1);
	css->flags = 0;
	css->id = NULL;
	if (cgrp == dummytop)
		set_bit(CSS_ROOT, &css->flags);
	BUG_ON(cgrp->subsys[ss->subsys_id]);
	cgrp->subsys[ss->subsys_id] = css;
}

static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
{
	/* We need to take each hierarchy_mutex in a consistent order */
	int i;

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		if (ss->root == root)
			mutex_lock(&ss->hierarchy_mutex);
	}
}

static void cgroup_unlock_hierarchy(struct cgroupfs_root *root)
{
	int i;

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		if (ss->root == root)
			mutex_unlock(&ss->hierarchy_mutex);
	}
}

/*
 * cgroup_create - create a cgroup
 * @parent: cgroup that will be parent of the new cgroup
 * @dentry: dentry of the new cgroup
 * @mode: mode to set on new inode
 *
 * Must be called with the mutex on the parent inode held
 */
static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
			     mode_t mode)
{
	struct cgroup *cgrp;
	struct cgroupfs_root *root = parent->root;
	int err = 0;
	struct cgroup_subsys *ss;
	struct super_block *sb = root->sb;

	cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
	if (!cgrp)
		return -ENOMEM;

	/* Grab a reference on the superblock so the hierarchy doesn't
	 * get deleted on unmount if there are child cgroups.  This
	 * can be done outside cgroup_mutex, since the sb can't
	 * disappear while someone has an open control file on the
	 * fs */
	atomic_inc(&sb->s_active);

	mutex_lock(&cgroup_mutex);

	init_cgroup_housekeeping(cgrp);

	cgrp->parent = parent;
	cgrp->root = parent->root;
	cgrp->top_cgroup = parent->top_cgroup;

	if (notify_on_release(parent))
		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);

	for_each_subsys(root, ss) {
		struct cgroup_subsys_state *css = ss->create(ss, cgrp);
		if (IS_ERR(css)) {
			err = PTR_ERR(css);
			goto err_destroy;
		}
		init_cgroup_css(css, ss, cgrp);
		if (ss->use_id)
			if (alloc_css_id(ss, parent, cgrp))
				goto err_destroy;
		/* At error, ->destroy() callback has to free assigned ID. */
	}

	cgroup_lock_hierarchy(root);
	list_add(&cgrp->sibling, &cgrp->parent->children);
	cgroup_unlock_hierarchy(root);
	root->number_of_cgroups++;

	err = cgroup_create_dir(cgrp, dentry, mode);
	if (err < 0)
		goto err_remove;

	/* The cgroup directory was pre-locked for us */
	BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex));

	err = cgroup_populate_dir(cgrp);
	/* If err < 0, we have a half-filled directory - oh well ;) */

	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);

	return 0;

 err_remove:

	cgroup_lock_hierarchy(root);
	list_del(&cgrp->sibling);
	cgroup_unlock_hierarchy(root);
	root->number_of_cgroups--;

 err_destroy:

	for_each_subsys(root, ss) {
		if (cgrp->subsys[ss->subsys_id])
			ss->destroy(ss, cgrp);
	}

	mutex_unlock(&cgroup_mutex);

	/* Release the reference count that we took on the superblock */
	deactivate_super(sb);

	kfree(cgrp);
	return err;
}

static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	struct cgroup *c_parent = dentry->d_parent->d_fsdata;

	/* the vfs holds inode->i_mutex already */
	return cgroup_create(c_parent, dentry, mode | S_IFDIR);
}

static int cgroup_has_css_refs(struct cgroup *cgrp)
{
	/* Check the reference count on each subsystem. Since we
	 * already established that there are no tasks in the
	 * cgroup, if the css refcount is also 1, then there should
	 * be no outstanding references, so the subsystem is safe to
	 * destroy. We scan across all subsystems rather than using
	 * the per-hierarchy linked list of mounted subsystems since
	 * we can be called via check_for_release() with no
	 * synchronization other than RCU, and the subsystem linked
	 * list isn't RCU-safe */
	int i;
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		struct cgroup_subsys_state *css;
		/* Skip subsystems not in this hierarchy */
		if (ss->root != cgrp->root)
			continue;
		css = cgrp->subsys[ss->subsys_id];
		/* When called from check_for_release() it's possible
		 * that by this point the cgroup has been removed
		 * and the css deleted. But a false-positive doesn't
		 * matter, since it can only happen if the cgroup
		 * has been deleted and hence no longer needs the
		 * release agent to be called anyway. */
		if (css && (atomic_read(&css->refcnt) > 1))
			return 1;
	}
	return 0;
}

/*
 * Atomically mark all (or else none) of the cgroup's CSS objects as
 * CSS_REMOVED. Return true on success, or false if the cgroup has
 * busy subsystems. Call with cgroup_mutex held
 */

static int cgroup_clear_css_refs(struct cgroup *cgrp)
{
	struct cgroup_subsys *ss;
	unsigned long flags;
	bool failed = false;
	local_irq_save(flags);
	for_each_subsys(cgrp->root, ss) {
		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
		int refcnt;
		while (1) {
			/* We can only remove a CSS with a refcnt==1 */
			refcnt = atomic_read(&css->refcnt);
			if (refcnt > 1) {
				failed = true;
				goto done;
			}
			BUG_ON(!refcnt);
			/*
			 * Drop the refcnt to 0 while we check other
			 * subsystems. This will cause any racing
			 * css_tryget() to spin until we set the
			 * CSS_REMOVED bits or abort
			 */
			if (atomic_cmpxchg(&css->refcnt, refcnt, 0) == refcnt)
				break;
			cpu_relax();
		}
	}
 done:
	for_each_subsys(cgrp->root, ss) {
		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
		if (failed) {
			/*
			 * Restore old refcnt if we previously managed
			 * to clear it from 1 to 0
			 */
			if (!atomic_read(&css->refcnt))
				atomic_set(&css->refcnt, 1);
		} else {
			/* Commit the fact that the CSS is removed */
			set_bit(CSS_REMOVED, &css->flags);
		}
	}
	local_irq_restore(flags);
	return !failed;
}

static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
{
	struct cgroup *cgrp = dentry->d_fsdata;
	struct dentry *d;
	struct cgroup *parent;
	DEFINE_WAIT(wait);
	int ret;

	/* the vfs holds both inode->i_mutex already */
again:
	mutex_lock(&cgroup_mutex);
	if (atomic_read(&cgrp->count) != 0) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	if (!list_empty(&cgrp->children)) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	mutex_unlock(&cgroup_mutex);

	/*
	 * Call pre_destroy handlers of subsys. Notify subsystems
	 * that rmdir() request comes.
	 */
	ret = cgroup_call_pre_destroy(cgrp);
	if (ret)
		return ret;

	mutex_lock(&cgroup_mutex);
	parent = cgrp->parent;
	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	/*
	 * css_put/get is provided for subsys to grab refcnt to css. In typical
	 * case, subsystem has no reference after pre_destroy(). But, under
	 * hierarchy management, some *temporal* refcnt can be hold.