aboutsummaryrefslogtreecommitdiffstats
path: root/fs/btrfs/compression.c
blob: df05f513e1ebcb2f4ae20511c1cc1165f26f83e4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
/*
 * Copyright (C) 2008 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/smp_lock.h>
#include <linux/backing-dev.h>
#include <linux/mpage.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/bit_spinlock.h>
#include <linux/version.h>
#include <linux/pagevec.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "volumes.h"
#include "ordered-data.h"
#include "compat.h"
#include "compression.h"
#include "extent_io.h"
#include "extent_map.h"

struct compressed_bio {
	/* number of bios pending for this compressed extent */
	atomic_t pending_bios;

	/* the pages with the compressed data on them */
	struct page **compressed_pages;

	/* inode that owns this data */
	struct inode *inode;

	/* starting offset in the inode for our pages */
	u64 start;

	/* number of bytes in the inode we're working on */
	unsigned long len;

	/* number of bytes on disk */
	unsigned long compressed_len;

	/* number of compressed pages in the array */
	unsigned long nr_pages;

	/* IO errors */
	int errors;

	/* for reads, this is the bio we are copying the data into */
	struct bio *orig_bio;
};

static struct bio *compressed_bio_alloc(struct block_device *bdev,
					u64 first_byte, gfp_t gfp_flags)
{
	struct bio *bio;
	int nr_vecs;

	nr_vecs = bio_get_nr_vecs(bdev);
	bio = bio_alloc(gfp_flags, nr_vecs);

	if (bio == NULL && (current->flags & PF_MEMALLOC)) {
		while (!bio && (nr_vecs /= 2))
			bio = bio_alloc(gfp_flags, nr_vecs);
	}

	if (bio) {
		bio->bi_size = 0;
		bio->bi_bdev = bdev;
		bio->bi_sector = first_byte >> 9;
	}
	return bio;
}

/* when we finish reading compressed pages from the disk, we
 * decompress them and then run the bio end_io routines on the
 * decompressed pages (in the inode address space).
 *
 * This allows the checksumming and other IO error handling routines
 * to work normally
 *
 * The compressed pages are freed here, and it must be run
 * in process context
 */
static void end_compressed_bio_read(struct bio *bio, int err)
{
	struct extent_io_tree *tree;
	struct compressed_bio *cb = bio->bi_private;
	struct inode *inode;
	struct page *page;
	unsigned long index;
	int ret;

	if (err)
		cb->errors = 1;

	/* if there are more bios still pending for this compressed
	 * extent, just exit
	 */
	if (!atomic_dec_and_test(&cb->pending_bios))
		goto out;

	/* ok, we're the last bio for this extent, lets start
	 * the decompression.
	 */
	inode = cb->inode;
	tree = &BTRFS_I(inode)->io_tree;
	ret = btrfs_zlib_decompress_biovec(cb->compressed_pages,
					cb->start,
					cb->orig_bio->bi_io_vec,
					cb->orig_bio->bi_vcnt,
					cb->compressed_len);
	if (ret)
		cb->errors = 1;

	/* release the compressed pages */
	index = 0;
	for (index = 0; index < cb->nr_pages; index++) {
		page = cb->compressed_pages[index];
		page->mapping = NULL;
		page_cache_release(page);
	}

	/* do io completion on the original bio */
	if (cb->errors) {
		bio_io_error(cb->orig_bio);
	} else
		bio_endio(cb->orig_bio, 0);

	/* finally free the cb struct */
	kfree(cb->compressed_pages);
	kfree(cb);
out:
	bio_put(bio);
}

/*
 * Clear the writeback bits on all of the file
 * pages for a compressed write
 */
static noinline int end_compressed_writeback(struct inode *inode, u64 start,
					     unsigned long ram_size)
{
	unsigned long index = start >> PAGE_CACHE_SHIFT;
	unsigned long end_index = (start + ram_size - 1) >> PAGE_CACHE_SHIFT;
	struct page *pages[16];
	unsigned long nr_pages = end_index - index + 1;
	int i;
	int ret;

	while(nr_pages > 0) {
		ret = find_get_pages_contig(inode->i_mapping, index,
				     min_t(unsigned long,
				     nr_pages, ARRAY_SIZE(pages)), pages);
		if (ret == 0) {
			nr_pages -= 1;
			index += 1;
			continue;
		}
		for (i = 0; i < ret; i++) {
			end_page_writeback(pages[i]);
			page_cache_release(pages[i]);
		}
		nr_pages -= ret;
		index += ret;
	}
	/* the inode may be gone now */
	return 0;
}

/*
 * do the cleanup once all the compressed pages hit the disk.
 * This will clear writeback on the file pages and free the compressed
 * pages.
 *
 * This also calls the writeback end hooks for the file pages so that
 * metadata and checksums can be updated in the file.
 */
static void end_compressed_bio_write(struct bio *bio, int err)
{
	struct extent_io_tree *tree;
	struct compressed_bio *cb = bio->bi_private;
	struct inode *inode;
	struct page *page;
	unsigned long index;

	if (err)
		cb->errors = 1;

	/* if there are more bios still pending for this compressed
	 * extent, just exit
	 */
	if (!atomic_dec_and_test(&cb->pending_bios))
		goto out;

	/* ok, we're the last bio for this extent, step one is to
	 * call back into the FS and do all the end_io operations
	 */
	inode = cb->inode;
	tree = &BTRFS_I(inode)->io_tree;
	cb->compressed_pages[0]->mapping = cb->inode->i_mapping;
	tree->ops->writepage_end_io_hook(cb->compressed_pages[0],
					 cb->start,
					 cb->start + cb->len - 1,
					 NULL, 1);
	cb->compressed_pages[0]->mapping = NULL;

	end_compressed_writeback(inode, cb->start, cb->len);
	/* note, our inode could be gone now */

	/*
	 * release the compressed pages, these came from alloc_page and
	 * are not attached to the inode at all
	 */
	index = 0;
	for (index = 0; index < cb->nr_pages; index++) {
		page = cb->compressed_pages[index];
		page->mapping = NULL;
		page_cache_release(page);
	}

	/* finally free the cb struct */
	kfree(cb->compressed_pages);
	kfree(cb);
out:
	bio_put(bio);
}

/*
 * worker function to build and submit bios for previously compressed pages.
 * The corresponding pages in the inode should be marked for writeback
 * and the compressed pages should have a reference on them for dropping
 * when the IO is complete.
 *
 * This also checksums the file bytes and gets things ready for
 * the end io hooks.
 */
int btrfs_submit_compressed_write(struct inode *inode, u64 start,
				 unsigned long len, u64 disk_start,
				 unsigned long compressed_len,
				 struct page **compressed_pages,
				 unsigned long nr_pages)
{
	struct bio *bio = NULL;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct compressed_bio *cb;
	unsigned long bytes_left;
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	int page_index = 0;
	struct page *page;
	u64 first_byte = disk_start;
	struct block_device *bdev;
	int ret;

	WARN_ON(start & ((u64)PAGE_CACHE_SIZE - 1));
	cb = kmalloc(sizeof(*cb), GFP_NOFS);
	atomic_set(&cb->pending_bios, 0);
	cb->errors = 0;
	cb->inode = inode;
	cb->start = start;
	cb->len = len;
	cb->compressed_pages = compressed_pages;
	cb->compressed_len = compressed_len;
	cb->orig_bio = NULL;
	cb->nr_pages = nr_pages;

	bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;

	ret = btrfs_csum_file_bytes(root, inode, start, len);
	BUG_ON(ret);

	bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS);
	bio->bi_private = cb;
	bio->bi_end_io = end_compressed_bio_write;
	atomic_inc(&cb->pending_bios);

	/* create and submit bios for the compressed pages */
	bytes_left = compressed_len;
	for (page_index = 0; page_index < cb->nr_pages; page_index++) {
		page = compressed_pages[page_index];
		page->mapping = inode->i_mapping;
		if (bio->bi_size)
			ret = io_tree->ops->merge_bio_hook(page, 0,
							   PAGE_CACHE_SIZE,
							   bio, 0);
		else
			ret = 0;

		page->mapping = NULL;
		if (ret || bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) <
		    PAGE_CACHE_SIZE) {
			bio_get(bio);

			/*
			 * inc the count before we submit the bio so
			 * we know the end IO handler won't happen before
			 * we inc the count.  Otherwise, the cb might get
			 * freed before we're done setting it up
			 */
			atomic_inc(&cb->pending_bios);
			ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
			BUG_ON(ret);

			ret = btrfs_map_bio(root, WRITE, bio, 0, 1);
			BUG_ON(ret);

			bio_put(bio);

			bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS);
			bio->bi_private = cb;
			bio->bi_end_io = end_compressed_bio_write;
			bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
		}
		if (bytes_left < PAGE_CACHE_SIZE) {
			printk("bytes left %lu compress len %lu nr %lu\n",
			       bytes_left, cb->compressed_len, cb->nr_pages);
		}
		bytes_left -= PAGE_CACHE_SIZE;
		first_byte += PAGE_CACHE_SIZE;
		cond_resched();
	}
	bio_get(bio);

	ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
	BUG_ON(ret);

	ret = btrfs_map_bio(root, WRITE, bio, 0, 1);
	BUG_ON(ret);

	bio_put(bio);
	return 0;
}

static noinline int add_ra_bio_pages(struct inode *inode,
				     u64 compressed_end,
				     struct compressed_bio *cb)
{
	unsigned long end_index;
	unsigned long page_index;
	u64 last_offset;
	u64 isize = i_size_read(inode);
	int ret;
	struct page *page;
	unsigned long nr_pages = 0;
	struct extent_map *em;
	struct address_space *mapping = inode->i_mapping;
	struct pagevec pvec;
	struct extent_map_tree *em_tree;
	struct extent_io_tree *tree;
	u64 end;
	int misses = 0;

	page = cb->orig_bio->bi_io_vec[cb->orig_bio->bi_vcnt - 1].bv_page;
	last_offset = (page_offset(page) + PAGE_CACHE_SIZE);
	em_tree = &BTRFS_I(inode)->extent_tree;
	tree = &BTRFS_I(inode)->io_tree;

	if (isize == 0)
		return 0;

	end_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;

	pagevec_init(&pvec, 0);
	while(last_offset < compressed_end) {
		page_index = last_offset >> PAGE_CACHE_SHIFT;

		if (page_index > end_index)
			break;

		rcu_read_lock();
		page = radix_tree_lookup(&mapping->page_tree, page_index);
		rcu_read_unlock();
		if (page) {
			misses++;
			if (misses > 4)
				break;
			goto next;
		}

		page = alloc_page(mapping_gfp_mask(mapping) | GFP_NOFS);
		if (!page)
			break;

		page->index = page_index;
		/*
		 * what we want to do here is call add_to_page_cache_lru,
		 * but that isn't exported, so we reproduce it here
		 */
		if (add_to_page_cache(page, mapping,
				      page->index, GFP_NOFS)) {
			page_cache_release(page);
			goto next;
		}

		/* open coding of lru_cache_add, also not exported */
		page_cache_get(page);
		if (!pagevec_add(&pvec, page))
			__pagevec_lru_add_file(&pvec);

		end = last_offset + PAGE_CACHE_SIZE - 1;
		/*
		 * at this point, we have a locked page in the page cache
		 * for these bytes in the file.  But, we have to make
		 * sure they map to this compressed extent on disk.
		 */
		set_page_extent_mapped(page);
		lock_extent(tree, last_offset, end, GFP_NOFS);
		spin_lock(&em_tree->lock);
		em = lookup_extent_mapping(em_tree, last_offset,
					   PAGE_CACHE_SIZE);
		spin_unlock(&em_tree->lock);

		if (!em || last_offset < em->start ||
		    (last_offset + PAGE_CACHE_SIZE > extent_map_end(em)) ||
		    (em->block_start >> 9) != cb->orig_bio->bi_sector) {
			free_extent_map(em);
			unlock_extent(tree, last_offset, end, GFP_NOFS);
			unlock_page(page);
			page_cache_release(page);
			break;
		}
		free_extent_map(em);

		if (page->index == end_index) {
			char *userpage;
			size_t zero_offset = isize & (PAGE_CACHE_SIZE - 1);

			if (zero_offset) {
				int zeros;
				zeros = PAGE_CACHE_SIZE - zero_offset;
				userpage = kmap_atomic(page, KM_USER0);
				memset(userpage + zero_offset, 0, zeros);
				flush_dcache_page(page);
				kunmap_atomic(userpage, KM_USER0);
			}
		}

		ret = bio_add_page(cb->orig_bio, page,
				   PAGE_CACHE_SIZE, 0);

		if (ret == PAGE_CACHE_SIZE) {
			nr_pages++;
			page_cache_release(page);
		} else {
			unlock_extent(tree, last_offset, end, GFP_NOFS);
			unlock_page(page);
			page_cache_release(page);
			break;
		}
next:
		last_offset += PAGE_CACHE_SIZE;
	}
	if (pagevec_count(&pvec))
		__pagevec_lru_add_file(&pvec);
	return 0;
}

/*
 * for a compressed read, the bio we get passed has all the inode pages
 * in it.  We don't actually do IO on those pages but allocate new ones
 * to hold the compressed pages on disk.
 *
 * bio->bi_sector points to the compressed extent on disk
 * bio->bi_io_vec points to all of the inode pages
 * bio->bi_vcnt is a count of pages
 *
 * After the compressed pages are read, we copy the bytes into the
 * bio we were passed and then call the bio end_io calls
 */
int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
				 int mirror_num, unsigned long bio_flags)
{
	struct extent_io_tree *tree;
	struct extent_map_tree *em_tree;
	struct compressed_bio *cb;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	unsigned long uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
	unsigned long compressed_len;
	unsigned long nr_pages;
	unsigned long page_index;
	struct page *page;
	struct block_device *bdev;
	struct bio *comp_bio;
	u64 cur_disk_byte = (u64)bio->bi_sector << 9;
	u64 em_len;
	u64 em_start;
	struct extent_map *em;
	int ret;

	tree = &BTRFS_I(inode)->io_tree;
	em_tree = &BTRFS_I(inode)->extent_tree;

	/* we need the actual starting offset of this extent in the file */
	spin_lock(&em_tree->lock);
	em = lookup_extent_mapping(em_tree,
				   page_offset(bio->bi_io_vec->bv_page),
				   PAGE_CACHE_SIZE);
	spin_unlock(&em_tree->lock);

	cb = kmalloc(sizeof(*cb), GFP_NOFS);
	atomic_set(&cb->pending_bios, 0);
	cb->errors = 0;
	cb->inode = inode;

	cb->start = em->orig_start;
	compressed_len = em->block_len;
	em_len = em->len;
	em_start = em->start;
	free_extent_map(em);
	em = NULL;

	cb->len = uncompressed_len;
	cb->compressed_len = compressed_len;
	cb->orig_bio = bio;

	nr_pages = (compressed_len + PAGE_CACHE_SIZE - 1) /
				 PAGE_CACHE_SIZE;
	cb->compressed_pages = kmalloc(sizeof(struct page *) * nr_pages,
				       GFP_NOFS);
	bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;

	for (page_index = 0; page_index < nr_pages; page_index++) {
		cb->compressed_pages[page_index] = alloc_page(GFP_NOFS |
							      __GFP_HIGHMEM);
	}
	cb->nr_pages = nr_pages;

	add_ra_bio_pages(inode, em_start + em_len, cb);

	if (!btrfs_test_opt(root, NODATASUM) &&
	    !btrfs_test_flag(inode, NODATASUM)) {
		btrfs_lookup_bio_sums(root, inode, cb->orig_bio);
	}

	/* include any pages we added in add_ra-bio_pages */
	uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
	cb->len = uncompressed_len;

	comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS);
	comp_bio->bi_private = cb;
	comp_bio->bi_end_io = end_compressed_bio_read;
	atomic_inc(&cb->pending_bios);

	for (page_index = 0; page_index < nr_pages; page_index++) {
		page = cb->compressed_pages[page_index];
		page->mapping = inode->i_mapping;
		if (comp_bio->bi_size)
			ret = tree->ops->merge_bio_hook(page, 0,
							PAGE_CACHE_SIZE,
							comp_bio, 0);
		else
			ret = 0;

		page->mapping = NULL;
		if (ret || bio_add_page(comp_bio, page, PAGE_CACHE_SIZE, 0) <
		    PAGE_CACHE_SIZE) {
			bio_get(comp_bio);

			ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio, 0);
			BUG_ON(ret);

			/*
			 * inc the count before we submit the bio so
			 * we know the end IO handler won't happen before
			 * we inc the count.  Otherwise, the cb might get
			 * freed before we're done setting it up
			 */
			atomic_inc(&cb->pending_bios);

			ret = btrfs_map_bio(root, READ, comp_bio, 0, 0);
			BUG_ON(ret);

			bio_put(comp_bio);

			comp_bio = compressed_bio_alloc(bdev, cur_disk_byte,
							GFP_NOFS);
			comp_bio->bi_private = cb;
			comp_bio->bi_end_io = end_compressed_bio_read;

			bio_add_page(comp_bio, page, PAGE_CACHE_SIZE, 0);
		}
		cur_disk_byte += PAGE_CACHE_SIZE;
	}
	bio_get(comp_bio);

	ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio, 0);
	BUG_ON(ret);

	ret = btrfs_map_bio(root, READ, comp_bio, 0, 0);
	BUG_ON(ret);

	bio_put(comp_bio);
	return 0;
}