summaryrefslogtreecommitdiffstats
path: root/fs/exofs/super.c
blob: b736b117a2a405a08e20444042bb1accfd024aab (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
/*
 * Copyright (C) 2005, 2006
 * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
 * Copyright (C) 2005, 2006
 * International Business Machines
 * Copyright (C) 2008, 2009
 * Boaz Harrosh <bharrosh@panasas.com>
 *
 * Copyrights for code taken from ext2:
 *     Copyright (C) 1992, 1993, 1994, 1995
 *     Remy Card (card@masi.ibp.fr)
 *     Laboratoire MASI - Institut Blaise Pascal
 *     Universite Pierre et Marie Curie (Paris VI)
 *     from
 *     linux/fs/minix/inode.c
 *     Copyright (C) 1991, 1992  Linus Torvalds
 *
 * This file is part of exofs.
 *
 * exofs 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.  Since it is based on ext2, and the only
 * valid version of GPL for the Linux kernel is version 2, the only valid
 * version of GPL for exofs is version 2.
 *
 * exofs 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 exofs; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */

#include <linux/string.h>
#include <linux/parser.h>
#include <linux/vfs.h>
#include <linux/random.h>

#include "exofs.h"

/******************************************************************************
 * MOUNT OPTIONS
 *****************************************************************************/

/*
 * struct to hold what we get from mount options
 */
struct exofs_mountopt {
	const char *dev_name;
	uint64_t pid;
	int timeout;
};

/*
 * exofs-specific mount-time options.
 */
enum { Opt_pid, Opt_to, Opt_mkfs, Opt_format, Opt_err };

/*
 * Our mount-time options.  These should ideally be 64-bit unsigned, but the
 * kernel's parsing functions do not currently support that.  32-bit should be
 * sufficient for most applications now.
 */
static match_table_t tokens = {
	{Opt_pid, "pid=%u"},
	{Opt_to, "to=%u"},
	{Opt_err, NULL}
};

/*
 * The main option parsing method.  Also makes sure that all of the mandatory
 * mount options were set.
 */
static int parse_options(char *options, struct exofs_mountopt *opts)
{
	char *p;
	substring_t args[MAX_OPT_ARGS];
	int option;
	bool s_pid = false;

	EXOFS_DBGMSG("parse_options %s\n", options);
	/* defaults */
	memset(opts, 0, sizeof(*opts));
	opts->timeout = BLK_DEFAULT_SG_TIMEOUT;

	while ((p = strsep(&options, ",")) != NULL) {
		int token;
		char str[32];

		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_pid:
			if (0 == match_strlcpy(str, &args[0], sizeof(str)))
				return -EINVAL;
			opts->pid = simple_strtoull(str, NULL, 0);
			if (opts->pid < EXOFS_MIN_PID) {
				EXOFS_ERR("Partition ID must be >= %u",
					  EXOFS_MIN_PID);
				return -EINVAL;
			}
			s_pid = 1;
			break;
		case Opt_to:
			if (match_int(&args[0], &option))
				return -EINVAL;
			if (option <= 0) {
				EXOFS_ERR("Timout must be > 0");
				return -EINVAL;
			}
			opts->timeout = option * HZ;
			break;
		}
	}

	if (!s_pid) {
		EXOFS_ERR("Need to specify the following options:\n");
		EXOFS_ERR("    -o pid=pid_no_to_use\n");
		return -EINVAL;
	}

	return 0;
}

/******************************************************************************
 * INODE CACHE
 *****************************************************************************/

/*
 * Our inode cache.  Isn't it pretty?
 */
static struct kmem_cache *exofs_inode_cachep;

/*
 * Allocate an inode in the cache
 */
static struct inode *exofs_alloc_inode(struct super_block *sb)
{
	struct exofs_i_info *oi;

	oi = kmem_cache_alloc(exofs_inode_cachep, GFP_KERNEL);
	if (!oi)
		return NULL;

	oi->vfs_inode.i_version = 1;
	return &oi->vfs_inode;
}

/*
 * Remove an inode from the cache
 */
static void exofs_destroy_inode(struct inode *inode)
{
	kmem_cache_free(exofs_inode_cachep, exofs_i(inode));
}

/*
 * Initialize the inode
 */
static void exofs_init_once(void *foo)
{
	struct exofs_i_info *oi = foo;

	inode_init_once(&oi->vfs_inode);
}

/*
 * Create and initialize the inode cache
 */
static int init_inodecache(void)
{
	exofs_inode_cachep = kmem_cache_create("exofs_inode_cache",
				sizeof(struct exofs_i_info), 0,
				SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
				exofs_init_once);
	if (exofs_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

/*
 * Destroy the inode cache
 */
static void destroy_inodecache(void)
{
	kmem_cache_destroy(exofs_inode_cachep);
}

/******************************************************************************
 * SUPERBLOCK FUNCTIONS
 *****************************************************************************/
static const struct super_operations exofs_sops;

/*
 * Write the superblock to the OSD
 */
static void exofs_write_super(struct super_block *sb)
{
	struct exofs_sb_info *sbi;
	struct exofs_fscb *fscb;
	struct osd_request *or;
	struct osd_obj_id obj;
	int ret;

	fscb = kzalloc(sizeof(struct exofs_fscb), GFP_KERNEL);
	if (!fscb) {
		EXOFS_ERR("exofs_write_super: memory allocation failed.\n");
		return;
	}

	lock_kernel();
	sbi = sb->s_fs_info;
	fscb->s_nextid = cpu_to_le64(sbi->s_nextid);
	fscb->s_numfiles = cpu_to_le32(sbi->s_numfiles);
	fscb->s_magic = cpu_to_le16(sb->s_magic);
	fscb->s_newfs = 0;

	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
	if (unlikely(!or)) {
		EXOFS_ERR("exofs_write_super: osd_start_request failed.\n");
		goto out;
	}

	obj.partition = sbi->s_pid;
	obj.id = EXOFS_SUPER_ID;
	ret = osd_req_write_kern(or, &obj, 0, fscb, sizeof(*fscb));
	if (unlikely(ret)) {
		EXOFS_ERR("exofs_write_super: osd_req_write_kern failed.\n");
		goto out;
	}

	ret = exofs_sync_op(or, sbi->s_timeout, sbi->s_cred);
	if (unlikely(ret)) {
		EXOFS_ERR("exofs_write_super: exofs_sync_op failed.\n");
		goto out;
	}
	sb->s_dirt = 0;

out:
	if (or)
		osd_end_request(or);
	unlock_kernel();
	kfree(fscb);
}

/*
 * This function is called when the vfs is freeing the superblock.  We just
 * need to free our own part.
 */
static void exofs_put_super(struct super_block *sb)
{
	int num_pend;
	struct exofs_sb_info *sbi = sb->s_fs_info;

	/* make sure there are no pending commands */
	for (num_pend = atomic_read(&sbi->s_curr_pending); num_pend > 0;
	     num_pend = atomic_read(&sbi->s_curr_pending)) {
		wait_queue_head_t wq;
		init_waitqueue_head(&wq);
		wait_event_timeout(wq,
				  (atomic_read(&sbi->s_curr_pending) == 0),
				  msecs_to_jiffies(100));
	}

	osduld_put_device(sbi->s_dev);
	kfree(sb->s_fs_info);
	sb->s_fs_info = NULL;
}

/*
 * Read the superblock from the OSD and fill in the fields
 */
static int exofs_fill_super(struct super_block *sb, void *data, int silent)
{
	struct inode *root;
	struct exofs_mountopt *opts = data;
	struct exofs_sb_info *sbi;	/*extended info                  */
	struct exofs_fscb fscb;		/*on-disk superblock info        */
	struct osd_request *or = NULL;
	struct osd_obj_id obj;
	int ret;

	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;
	sb->s_fs_info = sbi;

	/* use mount options to fill superblock */
	sbi->s_dev = osduld_path_lookup(opts->dev_name);
	if (IS_ERR(sbi->s_dev)) {
		ret = PTR_ERR(sbi->s_dev);
		sbi->s_dev = NULL;
		goto free_sbi;
	}

	sbi->s_pid = opts->pid;
	sbi->s_timeout = opts->timeout;

	/* fill in some other data by hand */
	memset(sb->s_id, 0, sizeof(sb->s_id));
	strcpy(sb->s_id, "exofs");
	sb->s_blocksize = EXOFS_BLKSIZE;
	sb->s_blocksize_bits = EXOFS_BLKSHIFT;
	sb->s_maxbytes = MAX_LFS_FILESIZE;
	atomic_set(&sbi->s_curr_pending, 0);
	sb->s_bdev = NULL;
	sb->s_dev = 0;

	/* read data from on-disk superblock object */
	obj.partition = sbi->s_pid;
	obj.id = EXOFS_SUPER_ID;
	exofs_make_credential(sbi->s_cred, &obj);

	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
	if (unlikely(!or)) {
		if (!silent)
			EXOFS_ERR(
			       "exofs_fill_super: osd_start_request failed.\n");
		ret = -ENOMEM;
		goto free_sbi;
	}
	ret = osd_req_read_kern(or, &obj, 0, &fscb, sizeof(fscb));
	if (unlikely(ret)) {
		if (!silent)
			EXOFS_ERR(
			       "exofs_fill_super: osd_req_read_kern failed.\n");
		ret = -ENOMEM;
		goto free_sbi;
	}

	ret = exofs_sync_op(or, sbi->s_timeout, sbi->s_cred);
	if (unlikely(ret)) {
		if (!silent)
			EXOFS_ERR("exofs_fill_super: exofs_sync_op failed.\n");
		ret = -EIO;
		goto free_sbi;
	}

	sb->s_magic = le16_to_cpu(fscb.s_magic);
	sbi->s_nextid = le64_to_cpu(fscb.s_nextid);
	sbi->s_numfiles = le32_to_cpu(fscb.s_numfiles);

	/* make sure what we read from the object store is correct */
	if (sb->s_magic != EXOFS_SUPER_MAGIC) {
		if (!silent)
			EXOFS_ERR("ERROR: Bad magic value\n");
		ret = -EINVAL;
		goto free_sbi;
	}

	/* start generation numbers from a random point */
	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
	spin_lock_init(&sbi->s_next_gen_lock);

	/* set up operation vectors */
	sb->s_op = &exofs_sops;
	root = exofs_iget(sb, EXOFS_ROOT_ID - EXOFS_OBJ_OFF);
	if (IS_ERR(root)) {
		EXOFS_ERR("ERROR: exofs_iget failed\n");
		ret = PTR_ERR(root);
		goto free_sbi;
	}
	sb->s_root = d_alloc_root(root);
	if (!sb->s_root) {
		iput(root);
		EXOFS_ERR("ERROR: get root inode failed\n");
		ret = -ENOMEM;
		goto free_sbi;
	}

	if (!S_ISDIR(root->i_mode)) {
		dput(sb->s_root);
		sb->s_root = NULL;
		EXOFS_ERR("ERROR: corrupt root inode (mode = %hd)\n",
		       root->i_mode);
		ret = -EINVAL;
		goto free_sbi;
	}

	ret = 0;
out:
	if (or)
		osd_end_request(or);
	return ret;

free_sbi:
	osduld_put_device(sbi->s_dev); /* NULL safe */
	kfree(sbi);
	goto out;
}

/*
 * Set up the superblock (calls exofs_fill_super eventually)
 */
static int exofs_get_sb(struct file_system_type *type,
			  int flags, const char *dev_name,
			  void *data, struct vfsmount *mnt)
{
	struct exofs_mountopt opts;
	int ret;

	ret = parse_options(data, &opts);
	if (ret)
		return ret;

	opts.dev_name = dev_name;
	return get_sb_nodev(type, flags, &opts, exofs_fill_super, mnt);
}

/*
 * Return information about the file system state in the buffer.  This is used
 * by the 'df' command, for example.
 */
static int exofs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	struct exofs_sb_info *sbi = sb->s_fs_info;
	struct osd_obj_id obj = {sbi->s_pid, 0};
	struct osd_attr attrs[] = {
		ATTR_DEF(OSD_APAGE_PARTITION_QUOTAS,
			OSD_ATTR_PQ_CAPACITY_QUOTA, sizeof(__be64)),
		ATTR_DEF(OSD_APAGE_PARTITION_INFORMATION,
			OSD_ATTR_PI_USED_CAPACITY, sizeof(__be64)),
	};
	uint64_t capacity = ULLONG_MAX;
	uint64_t used = ULLONG_MAX;
	struct osd_request *or;
	uint8_t cred_a[OSD_CAP_LEN];
	int ret;

	/* get used/capacity attributes */
	exofs_make_credential(cred_a, &obj);

	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
	if (unlikely(!or)) {
		EXOFS_DBGMSG("exofs_statfs: osd_start_request failed.\n");
		return -ENOMEM;
	}

	osd_req_get_attributes(or, &obj);
	osd_req_add_get_attr_list(or, attrs, ARRAY_SIZE(attrs));
	ret = exofs_sync_op(or, sbi->s_timeout, cred_a);
	if (unlikely(ret))
		goto out;

	ret = extract_attr_from_req(or, &attrs[0]);
	if (likely(!ret))
		capacity = get_unaligned_be64(attrs[0].val_ptr);
	else
		EXOFS_DBGMSG("exofs_statfs: get capacity failed.\n");

	ret = extract_attr_from_req(or, &attrs[1]);
	if (likely(!ret))
		used = get_unaligned_be64(attrs[1].val_ptr);
	else
		EXOFS_DBGMSG("exofs_statfs: get used-space failed.\n");

	/* fill in the stats buffer */
	buf->f_type = EXOFS_SUPER_MAGIC;
	buf->f_bsize = EXOFS_BLKSIZE;
	buf->f_blocks = (capacity >> EXOFS_BLKSHIFT);
	buf->f_bfree = ((capacity - used) >> EXOFS_BLKSHIFT);
	buf->f_bavail = buf->f_bfree;
	buf->f_files = sbi->s_numfiles;
	buf->f_ffree = EXOFS_MAX_ID - sbi->s_numfiles;
	buf->f_namelen = EXOFS_NAME_LEN;

out:
	osd_end_request(or);
	return ret;
}

static const struct super_operations exofs_sops = {
	.alloc_inode    = exofs_alloc_inode,
	.destroy_inode  = exofs_destroy_inode,
	.write_inode    = exofs_write_inode,
	.delete_inode   = exofs_delete_inode,
	.put_super      = exofs_put_super,
	.write_super    = exofs_write_super,
	.statfs         = exofs_statfs,
};

/******************************************************************************
 * INSMOD/RMMOD
 *****************************************************************************/

/*
 * struct that describes this file system
 */
static struct file_system_type exofs_type = {
	.owner          = THIS_MODULE,
	.name           = "exofs",
	.get_sb         = exofs_get_sb,
	.kill_sb        = generic_shutdown_super,
};

static int __init init_exofs(void)
{
	int err;

	err = init_inodecache();
	if (err)
		goto out;

	err = register_filesystem(&exofs_type);
	if (err)
		goto out_d;

	return 0;
out_d:
	destroy_inodecache();
out:
	return err;
}

static void __exit exit_exofs(void)
{
	unregister_filesystem(&exofs_type);
	destroy_inodecache();
}

MODULE_AUTHOR("Avishay Traeger <avishay@gmail.com>");
MODULE_DESCRIPTION("exofs");
MODULE_LICENSE("GPL");

module_init(init_exofs)
module_exit(exit_exofs)
OpenPOWER on IntegriCloud