aboutsummaryrefslogtreecommitdiff
path: root/fs/logfs/dev_bdev.c
blob: a322fec101736919918fbce7d6defe1c07f4f753 (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
/*
 * fs/logfs/dev_bdev.c	- Device access methods for block devices
 *
 * As should be obvious for Linux kernel code, license is GPLv2
 *
 * Copyright (c) 2005-2008 Joern Engel <joern@logfs.org>
 */
#include "logfs.h"
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/slab.h>
#include <linux/gfp.h>

#define PAGE_OFS(ofs) ((ofs) & (PAGE_SIZE-1))

static void request_complete(struct bio *bio, int err)
{
	complete((struct completion *)bio->bi_private);
}

static int sync_request(struct page *page, struct block_device *bdev, int rw)
{
	struct bio bio;
	struct bio_vec bio_vec;
	struct completion complete;

	bio_init(&bio);
	bio.bi_io_vec = &bio_vec;
	bio_vec.bv_page = page;
	bio_vec.bv_len = PAGE_SIZE;
	bio_vec.bv_offset = 0;
	bio.bi_vcnt = 1;
	bio.bi_idx = 0;
	bio.bi_size = PAGE_SIZE;
	bio.bi_bdev = bdev;
	bio.bi_sector = page->index * (PAGE_SIZE >> 9);
	init_completion(&complete);
	bio.bi_private = &complete;
	bio.bi_end_io = request_complete;

	submit_bio(rw, &bio);
	generic_unplug_device(bdev_get_queue(bdev));
	wait_for_completion(&complete);
	return test_bit(BIO_UPTODATE, &bio.bi_flags) ? 0 : -EIO;
}

static int bdev_readpage(void *_sb, struct page *page)
{
	struct super_block *sb = _sb;
	struct block_device *bdev = logfs_super(sb)->s_bdev;
	int err;

	err = sync_request(page, bdev, READ);
	if (err) {
		ClearPageUptodate(page);
		SetPageError(page);
	} else {
		SetPageUptodate(page);
		ClearPageError(page);
	}
	unlock_page(page);
	return err;
}

static DECLARE_WAIT_QUEUE_HEAD(wq);

static void writeseg_end_io(struct bio *bio, int err)
{
	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
	struct super_block *sb = bio->bi_private;
	struct logfs_super *super = logfs_super(sb);
	struct page *page;

	BUG_ON(!uptodate); /* FIXME: Retry io or write elsewhere */
	BUG_ON(err);
	BUG_ON(bio->bi_vcnt == 0);
	do {
		page = bvec->bv_page;
		if (--bvec >= bio->bi_io_vec)
			prefetchw(&bvec->bv_page->flags);

		end_page_writeback(page);
		page_cache_release(page);
	} while (bvec >= bio->bi_io_vec);
	bio_put(bio);
	if (atomic_dec_and_test(&super->s_pending_writes))
		wake_up(&wq);
}

static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
		size_t nr_pages)
{
	struct logfs_super *super = logfs_super(sb);
	struct address_space *mapping = super->s_mapping_inode->i_mapping;
	struct bio *bio;
	struct page *page;
	struct request_queue *q = bdev_get_queue(sb->s_bdev);
	unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9);
	int i;

	if (max_pages > BIO_MAX_PAGES)
		max_pages = BIO_MAX_PAGES;
	bio = bio_alloc(GFP_NOFS, max_pages);
	BUG_ON(!bio);

	for (i = 0; i < nr_pages; i++) {
		if (i >= max_pages) {
			/* Block layer cannot split bios :( */
			bio->bi_vcnt = i;
			bio->bi_idx = 0;
			bio->bi_size = i * PAGE_SIZE;
			bio->bi_bdev = super->s_bdev;
			bio->bi_sector = ofs >> 9;
			bio->bi_private = sb;
			bio->bi_end_io = writeseg_end_io;
			atomic_inc(&super->s_pending_writes);
			submit_bio(WRITE, bio);

			ofs += i * PAGE_SIZE;
			index += i;
			nr_pages -= i;
			i = 0;

			bio = bio_alloc(GFP_NOFS, max_pages);
			BUG_ON(!bio);
		}
		page = find_lock_page(mapping, index + i);
		BUG_ON(!page);
		bio->bi_io_vec[i].bv_page = page;
		bio->bi_io_vec[i].bv_len = PAGE_SIZE;
		bio->bi_io_vec[i].bv_offset = 0;

		BUG_ON(PageWriteback(page));
		set_page_writeback(page);
		unlock_page(page);
	}
	bio->bi_vcnt = nr_pages;
	bio->bi_idx = 0;
	bio->bi_size = nr_pages * PAGE_SIZE;
	bio->bi_bdev = super->s_bdev;
	bio->bi_sector = ofs >> 9;
	bio->bi_private = sb;
	bio->bi_end_io = writeseg_end_io;
	atomic_inc(&super->s_pending_writes);
	submit_bio(WRITE, bio);
	return 0;
}

static void bdev_writeseg(struct super_block *sb, u64 ofs, size_t len)
{
	struct logfs_super *super = logfs_super(sb);
	int head;

	BUG_ON(super->s_flags & LOGFS_SB_FLAG_RO);

	if (len == 0) {
		/* This can happen when the object fit perfectly into a
		 * segment, the segment gets written per sync and subsequently
		 * closed.
		 */
		return;
	}
	head = ofs & (PAGE_SIZE - 1);
	if (head) {
		ofs -= head;
		len += head;
	}
	len = PAGE_ALIGN(len);
	__bdev_writeseg(sb, ofs, ofs >> PAGE_SHIFT, len >> PAGE_SHIFT);
	generic_unplug_device(bdev_get_queue(logfs_super(sb)->s_bdev));
}


static void erase_end_io(struct bio *bio, int err) 
{ 
	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); 
	struct super_block *sb = bio->bi_private; 
	struct logfs_super *super = logfs_super(sb); 

	BUG_ON(!uptodate); /* FIXME: Retry io or write elsewhere */ 
	BUG_ON(err); 
	BUG_ON(bio->bi_vcnt == 0); 
	bio_put(bio); 
	if (atomic_dec_and_test(&super->s_pending_writes))
		wake_up(&wq); 
} 

static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index,
		size_t nr_pages)
{
	struct logfs_super *super = logfs_super(sb);
	struct bio *bio;
	struct request_queue *q = bdev_get_queue(sb->s_bdev);
	unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9);
	int i;

	if (max_pages > BIO_MAX_PAGES)
		max_pages = BIO_MAX_PAGES;
	bio = bio_alloc(GFP_NOFS, max_pages);
	BUG_ON(!bio);

	for (i = 0; i < nr_pages; i++) {
		if (i >= max_pages) {
			/* Block layer cannot split bios :( */
			bio->bi_vcnt = i;
			bio->bi_idx = 0;
			bio->bi_size = i * PAGE_SIZE;
			bio->bi_bdev = super->s_bdev;
			bio->bi_sector = ofs >> 9;
			bio->bi_private = sb;
			bio->bi_end_io = erase_end_io;
			atomic_inc(&super->s_pending_writes);
			submit_bio(WRITE, bio);

			ofs += i * PAGE_SIZE;
			index += i;
			nr_pages -= i;
			i = 0;

			bio = bio_alloc(GFP_NOFS, max_pages);
			BUG_ON(!bio);
		}
		bio->bi_io_vec[i].bv_page = super->s_erase_page;
		bio->bi_io_vec[i].bv_len = PAGE_SIZE;
		bio->bi_io_vec[i].bv_offset = 0;
	}
	bio->bi_vcnt = nr_pages;
	bio->bi_idx = 0;
	bio->bi_size = nr_pages * PAGE_SIZE;
	bio->bi_bdev = super->s_bdev;
	bio->bi_sector = ofs >> 9;
	bio->bi_private = sb;
	bio->bi_end_io = erase_end_io;
	atomic_inc(&super->s_pending_writes);
	submit_bio(WRITE, bio);
	return 0;
}

static int bdev_erase(struct super_block *sb, loff_t to, size_t len,
		int ensure_write)
{
	struct logfs_super *super = logfs_super(sb);

	BUG_ON(to & (PAGE_SIZE - 1));
	BUG_ON(len & (PAGE_SIZE - 1));

	if (super->s_flags & LOGFS_SB_FLAG_RO)
		return -EROFS;

	if (ensure_write) {
		/*
		 * Object store doesn't care whether erases happen or not.
		 * But for the journal they are required.  Otherwise a scan
		 * can find an old commit entry and assume it is the current
		 * one, travelling back in time.
		 */
		do_erase(sb, to, to >> PAGE_SHIFT, len >> PAGE_SHIFT);
	}

	return 0;
}

static void bdev_sync(struct super_block *sb)
{
	struct logfs_super *super = logfs_super(sb);

	wait_event(wq, atomic_read(&super->s_pending_writes) == 0);
}

static struct page *bdev_find_first_sb(struct super_block *sb, u64 *ofs)
{
	struct logfs_super *super = logfs_super(sb);
	struct address_space *mapping = super->s_mapping_inode->i_mapping;
	filler_t *filler = bdev_readpage;

	*ofs = 0;
	return read_cache_page(mapping, 0, filler, sb);
}

static struct page *bdev_find_last_sb(struct super_block *sb, u64 *ofs)
{
	struct logfs_super *super = logfs_super(sb);
	struct address_space *mapping = super->s_mapping_inode->i_mapping;
	filler_t *filler = bdev_readpage;
	u64 pos = (super->s_bdev->bd_inode->i_size & ~0xfffULL) - 0x1000;
	pgoff_t index = pos >> PAGE_SHIFT;

	*ofs = pos;
	return read_cache_page(mapping, index, filler, sb);
}

static int bdev_write_sb(struct super_block *sb, struct page *page)
{
	struct block_device *bdev = logfs_super(sb)->s_bdev;

	/* Nothing special to do for block devices. */
	return sync_request(page, bdev, WRITE);
}

static void bdev_put_device(struct super_block *sb)
{
	close_bdev_exclusive(logfs_super(sb)->s_bdev, FMODE_READ|FMODE_WRITE);
}

static int bdev_can_write_buf(struct super_block *sb, u64 ofs)
{
	return 0;
}

static const struct logfs_device_ops bd_devops = {
	.find_first_sb	= bdev_find_first_sb,
	.find_last_sb	= bdev_find_last_sb,
	.write_sb	= bdev_write_sb,
	.readpage	= bdev_readpage,
	.writeseg	= bdev_writeseg,
	.erase		= bdev_erase,
	.can_write_buf	= bdev_can_write_buf,
	.sync		= bdev_sync,
	.put_device	= bdev_put_device,
};

int logfs_get_sb_bdev(struct logfs_super *p,
		struct file_system_type *type, int flags,
		const char *devname, struct vfsmount *mnt)
{
	struct block_device *bdev;

	bdev = open_bdev_exclusive(devname, FMODE_READ|FMODE_WRITE, type);
	if (IS_ERR(bdev)) {
		kfree(p);
		return PTR_ERR(bdev);
	}

	if (MAJOR(bdev->bd_dev) == MTD_BLOCK_MAJOR) {
		int mtdnr = MINOR(bdev->bd_dev);
		close_bdev_exclusive(bdev, FMODE_READ|FMODE_WRITE);
		return logfs_get_sb_mtd(p, type, flags, mtdnr, mnt);
	}

	p->s_bdev = bdev;
	p->s_mtd = NULL;
	p->s_devops = &bd_devops;

	return logfs_get_sb_device(p, type, flags, mnt);
}