aboutsummaryrefslogtreecommitdiffstats
path: root/fs/nilfs2/segbuf.c
blob: d86056ca9a273d61d3eb5330e3df8aed61b177da (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
/*
 * segbuf.c - NILFS segment buffer
 *
 * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * 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., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 *
 * Written by Ryusuke Konishi <ryusuke@osrg.net>
 *
 */

#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/crc32.h>
#include "page.h"
#include "segbuf.h"


static struct kmem_cache *nilfs_segbuf_cachep;

static void nilfs_segbuf_init_once(void *obj)
{
	memset(obj, 0, sizeof(struct nilfs_segment_buffer));
}

int __init nilfs_init_segbuf_cache(void)
{
	nilfs_segbuf_cachep =
		kmem_cache_create("nilfs2_segbuf_cache",
				  sizeof(struct nilfs_segment_buffer),
				  0, SLAB_RECLAIM_ACCOUNT,
				  nilfs_segbuf_init_once);

	return (nilfs_segbuf_cachep == NULL) ? -ENOMEM : 0;
}

void nilfs_destroy_segbuf_cache(void)
{
	kmem_cache_destroy(nilfs_segbuf_cachep);
}

struct nilfs_segment_buffer *nilfs_segbuf_new(struct super_block *sb)
{
	struct nilfs_segment_buffer *segbuf;

	segbuf = kmem_cache_alloc(nilfs_segbuf_cachep, GFP_NOFS);
	if (unlikely(!segbuf))
		return NULL;

	segbuf->sb_super = sb;
	INIT_LIST_HEAD(&segbuf->sb_list);
	INIT_LIST_HEAD(&segbuf->sb_segsum_buffers);
	INIT_LIST_HEAD(&segbuf->sb_payload_buffers);

	init_completion(&segbuf->sb_bio_event);
	atomic_set(&segbuf->sb_err, 0);
	segbuf->sb_nbio = 0;

	return segbuf;
}

void nilfs_segbuf_free(struct nilfs_segment_buffer *segbuf)
{
	kmem_cache_free(nilfs_segbuf_cachep, segbuf);
}

void nilfs_segbuf_map(struct nilfs_segment_buffer *segbuf, __u64 segnum,
		     unsigned long offset, struct the_nilfs *nilfs)
{
	segbuf->sb_segnum = segnum;
	nilfs_get_segment_range(nilfs, segnum, &segbuf->sb_fseg_start,
				&segbuf->sb_fseg_end);

	segbuf->sb_pseg_start = segbuf->sb_fseg_start + offset;
	segbuf->sb_rest_blocks =
		segbuf->sb_fseg_end - segbuf->sb_pseg_start + 1;
}

void nilfs_segbuf_set_next_segnum(struct nilfs_segment_buffer *segbuf,
				  __u64 nextnum, struct the_nilfs *nilfs)
{
	segbuf->sb_nextnum = nextnum;
	segbuf->sb_sum.next = nilfs_get_segment_start_blocknr(nilfs, nextnum);
}

int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *segbuf)
{
	struct buffer_head *bh;

	bh = sb_getblk(segbuf->sb_super,
		       segbuf->sb_pseg_start + segbuf->sb_sum.nsumblk);
	if (unlikely(!bh))
		return -ENOMEM;

	nilfs_segbuf_add_segsum_buffer(segbuf, bh);
	return 0;
}

int nilfs_segbuf_extend_payload(struct nilfs_segment_buffer *segbuf,
				struct buffer_head **bhp)
{
	struct buffer_head *bh;

	bh = sb_getblk(segbuf->sb_super,
		       segbuf->sb_pseg_start + segbuf->sb_sum.nblocks);
	if (unlikely(!bh))
		return -ENOMEM;

	nilfs_segbuf_add_payload_buffer(segbuf, bh);
	*bhp = bh;
	return 0;
}

int nilfs_segbuf_reset(struct nilfs_segment_buffer *segbuf, unsigned flags,
		       time_t ctime)
{
	int err;

	segbuf->sb_sum.nblocks = segbuf->sb_sum.nsumblk = 0;
	err = nilfs_segbuf_extend_segsum(segbuf);
	if (unlikely(err))
		return err;

	segbuf->sb_sum.flags = flags;
	segbuf->sb_sum.sumbytes = sizeof(struct nilfs_segment_summary);
	segbuf->sb_sum.nfinfo = segbuf->sb_sum.nfileblk = 0;
	segbuf->sb_sum.ctime = ctime;
	return 0;
}

/*
 * Setup segument summary
 */
void nilfs_segbuf_fill_in_segsum(struct nilfs_segment_buffer *segbuf)
{
	struct nilfs_segment_summary *raw_sum;
	struct buffer_head *bh_sum;

	bh_sum = list_entry(segbuf->sb_segsum_buffers.next,
			    struct buffer_head, b_assoc_buffers);
	raw_sum = (struct nilfs_segment_summary *)bh_sum->b_data;

	raw_sum->ss_magic    = cpu_to_le32(NILFS_SEGSUM_MAGIC);
	raw_sum->ss_bytes    = cpu_to_le16(sizeof(*raw_sum));
	raw_sum->ss_flags    = cpu_to_le16(segbuf->sb_sum.flags);
	raw_sum->ss_seq      = cpu_to_le64(segbuf->sb_sum.seg_seq);
	raw_sum->ss_create   = cpu_to_le64(segbuf->sb_sum.ctime);
	raw_sum->ss_next     = cpu_to_le64(segbuf->sb_sum.next);
	raw_sum->ss_nblocks  = cpu_to_le32(segbuf->sb_sum.nblocks);
	raw_sum->ss_nfinfo   = cpu_to_le32(segbuf->sb_sum.nfinfo);
	raw_sum->ss_sumbytes = cpu_to_le32(segbuf->sb_sum.sumbytes);
	raw_sum->ss_pad      = 0;
}

/*
 * CRC calculation routines
 */
void nilfs_segbuf_fill_in_segsum_crc(struct nilfs_segment_buffer *segbuf,
				     u32 seed)
{
	struct buffer_head *bh;
	struct nilfs_segment_summary *raw_sum;
	unsigned long size, bytes = segbuf->sb_sum.sumbytes;
	u32 crc;

	bh = list_entry(segbuf->sb_segsum_buffers.next, struct buffer_head,
			b_assoc_buffers);

	raw_sum = (struct nilfs_segment_summary *)bh->b_data;
	size = min_t(unsigned long, bytes, bh->b_size);
	crc = crc32_le(seed,
		       (unsigned char *)raw_sum +
		       sizeof(raw_sum->ss_datasum) + sizeof(raw_sum->ss_sumsum),
		       size - (sizeof(raw_sum->ss_datasum) +
			       sizeof(raw_sum->ss_sumsum)));

	list_for_each_entry_continue(bh, &segbuf->sb_segsum_buffers,
				     b_assoc_buffers) {
		bytes -= size;
		size = min_t(unsigned long, bytes, bh->b_size);
		crc = crc32_le(crc, bh->b_data, size);
	}
	raw_sum->ss_sumsum = cpu_to_le32(crc);
}

void nilfs_segbuf_fill_in_data_crc(struct nilfs_segment_buffer *segbuf,
				   u32 seed)
{
	struct buffer_head *bh;
	struct nilfs_segment_summary *raw_sum;
	void *kaddr;
	u32 crc;

	bh = list_entry(segbuf->sb_segsum_buffers.next, struct buffer_head,
			b_assoc_buffers);
	raw_sum = (struct nilfs_segment_summary *)bh->b_data;
	crc = crc32_le(seed,
		       (unsigned char *)raw_sum + sizeof(raw_sum->ss_datasum),
		       bh->b_size - sizeof(raw_sum->ss_datasum));

	list_for_each_entry_continue(bh, &segbuf->sb_segsum_buffers,
				     b_assoc_buffers) {
		crc = crc32_le(crc, bh->b_data, bh->b_size);
	}
	list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) {
		kaddr = kmap_atomic(bh->b_page, KM_USER0);
		crc = crc32_le(crc, kaddr + bh_offset(bh), bh->b_size);
		kunmap_atomic(kaddr, KM_USER0);
	}
	raw_sum->ss_datasum = cpu_to_le32(crc);
}

void nilfs_release_buffers(struct list_head *list)
{
	struct buffer_head *bh, *n;

	list_for_each_entry_safe(bh, n, list, b_assoc_buffers) {
		list_del_init(&bh->b_assoc_buffers);
		if (buffer_nilfs_allocated(bh)) {
			struct page *clone_page = bh->b_page;

			/* remove clone page */
			brelse(bh);
			page_cache_release(clone_page); /* for each bh */
			if (page_count(clone_page) <= 2) {
				lock_page(clone_page);
				nilfs_free_private_page(clone_page);
			}
			continue;
		}
		brelse(bh);
	}
}

/*
 * BIO operations
 */
static void nilfs_end_bio_write(struct bio *bio, int err)
{
	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	struct nilfs_segment_buffer *segbuf = bio->bi_private;

	if (err == -EOPNOTSUPP) {
		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
		bio_put(bio);
		/* to be detected by submit_seg_bio() */
	}

	if (!uptodate)
		atomic_inc(&segbuf->sb_err);

	bio_put(bio);
	complete(&segbuf->sb_bio_event);
}

static int nilfs_segbuf_submit_bio(struct nilfs_segment_buffer *segbuf,
				   struct nilfs_write_info *wi, int mode)
{
	struct bio *bio = wi->bio;
	int err;

	if (segbuf->sb_nbio > 0 && bdi_write_congested(wi->bdi)) {
		wait_for_completion(&segbuf->sb_bio_event);
		segbuf->sb_nbio--;
		if (unlikely(atomic_read(&segbuf->sb_err))) {
			bio_put(bio);
			err = -EIO;
			goto failed;
		}
	}

	bio->bi_end_io = nilfs_end_bio_write;
	bio->bi_private = segbuf;
	bio_get(bio);
	submit_bio(mode, bio);
	if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
		bio_put(bio);
		err = -EOPNOTSUPP;
		goto failed;
	}
	segbuf->sb_nbio++;
	bio_put(bio);

	wi->bio = NULL;
	wi->rest_blocks -= wi->end - wi->start;
	wi->nr_vecs = min(wi->max_pages, wi->rest_blocks);
	wi->start = wi->end;
	return 0;

 failed:
	wi->bio = NULL;
	return err;
}

/**
 * nilfs_alloc_seg_bio - allocate a bio for writing segment.
 * @sb: super block
 * @start: beginning disk block number of this BIO.
 * @nr_vecs: request size of page vector.
 *
 * alloc_seg_bio() allocates a new BIO structure and initialize it.
 *
 * Return Value: On success, pointer to the struct bio is returned.
 * On error, NULL is returned.
 */
static struct bio *nilfs_alloc_seg_bio(struct super_block *sb, sector_t start,
				       int nr_vecs)
{
	struct bio *bio;

	bio = bio_alloc(GFP_NOIO, nr_vecs);
	if (bio == NULL) {
		while (!bio && (nr_vecs >>= 1))
			bio = bio_alloc(GFP_NOIO, nr_vecs);
	}
	if (likely(bio)) {
		bio->bi_bdev = sb->s_bdev;
		bio->bi_sector = (sector_t)start << (sb->s_blocksize_bits - 9);
	}
	return bio;
}

void nilfs_segbuf_prepare_write(struct nilfs_segment_buffer *segbuf,
				struct nilfs_write_info *wi)
{
	wi->bio = NULL;
	wi->rest_blocks = segbuf->sb_sum.nblocks;
	wi->max_pages = bio_get_nr_vecs(wi->sb->s_bdev);
	wi->nr_vecs = min(wi->max_pages, wi->rest_blocks);
	wi->start = wi->end = 0;
	wi->blocknr = segbuf->sb_pseg_start;
}

static int nilfs_segbuf_submit_bh(struct nilfs_segment_buffer *segbuf,
				  struct nilfs_write_info *wi,
				  struct buffer_head *bh, int mode)
{
	int len, err;

	BUG_ON(wi->nr_vecs <= 0);
 repeat:
	if (!wi->bio) {
		wi->bio = nilfs_alloc_seg_bio(wi->sb, wi->blocknr + wi->end,
					      wi->nr_vecs);
		if (unlikely(!wi->bio))
			return -ENOMEM;
	}

	len = bio_add_page(wi->bio, bh->b_page, bh->b_size, bh_offset(bh));
	if (len == bh->b_size) {
		wi->end++;
		return 0;
	}
	/* bio is FULL */
	err = nilfs_segbuf_submit_bio(segbuf, wi, mode);
	/* never submit current bh */
	if (likely(!err))
		goto repeat;
	return err;
}

int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf,
		       struct nilfs_write_info *wi)
{
	struct buffer_head *bh;
	int res = 0, rw = WRITE;

	list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) {
		res = nilfs_segbuf_submit_bh(segbuf, wi, bh, rw);
		if (unlikely(res))
			goto failed_bio;
	}

	list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) {
		res = nilfs_segbuf_submit_bh(segbuf, wi, bh, rw);
		if (unlikely(res))
			goto failed_bio;
	}

	if (wi->bio) {
		/*
		 * Last BIO is always sent through the following
		 * submission.
		 */
		rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG);
		res = nilfs_segbuf_submit_bio(segbuf, wi, rw);
	}

 failed_bio:
	return res;
}

/**
 * nilfs_segbuf_wait - wait for completion of requested BIOs
 * @segbuf: segment buffer
 *
 * Return Value: On Success, 0 is returned. On Error, one of the following
 * negative error code is returned.
 *
 * %-EIO - I/O error
 */
int nilfs_segbuf_wait(struct nilfs_segment_buffer *segbuf)
{
	int err = 0;

	if (!segbuf->sb_nbio)
		return 0;

	do {
		wait_for_completion(&segbuf->sb_bio_event);
	} while (--segbuf->sb_nbio > 0);

	if (unlikely(atomic_read(&segbuf->sb_err) > 0)) {
		printk(KERN_ERR "NILFS: IO error writing segment\n");
		err = -EIO;
	}
	return err;
}