super.c 11.1 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
/*
 * Copyright(c) 2017 Intel Corporation. All rights reserved.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of version 2 of the GNU General Public License 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.
 */
#include <linux/pagemap.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/magic.h>
17
#include <linux/genhd.h>
18
19
20
#include <linux/cdev.h>
#include <linux/hash.h>
#include <linux/slab.h>
Dan Williams's avatar
Dan Williams committed
21
#include <linux/dax.h>
22
23
24
25
26
27
28
29
30
#include <linux/fs.h>

static dev_t dax_devt;
DEFINE_STATIC_SRCU(dax_srcu);
static struct vfsmount *dax_mnt;
static DEFINE_IDA(dax_minor_ida);
static struct kmem_cache *dax_cache __read_mostly;
static struct super_block *dax_superblock __read_mostly;

31
32
33
34
#define DAX_HASH_SIZE (PAGE_SIZE / sizeof(struct hlist_head))
static struct hlist_head dax_host_list[DAX_HASH_SIZE];
static DEFINE_SPINLOCK(dax_host_lock);

35
36
37
38
39
40
41
42
43
44
45
46
int dax_read_lock(void)
{
	return srcu_read_lock(&dax_srcu);
}
EXPORT_SYMBOL_GPL(dax_read_lock);

void dax_read_unlock(int id)
{
	srcu_read_unlock(&dax_srcu, id);
}
EXPORT_SYMBOL_GPL(dax_read_unlock);

47
#ifdef CONFIG_BLOCK
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
int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
		pgoff_t *pgoff)
{
	phys_addr_t phys_off = (get_start_sect(bdev) + sector) * 512;

	if (pgoff)
		*pgoff = PHYS_PFN(phys_off);
	if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
		return -EINVAL;
	return 0;
}
EXPORT_SYMBOL(bdev_dax_pgoff);

/**
 * __bdev_dax_supported() - Check if the device supports dax for filesystem
 * @sb: The superblock of the device
 * @blocksize: The block size of the device
 *
 * This is a library function for filesystems to check if the block device
 * can be mounted with dax option.
 *
 * Return: negative errno if unsupported, 0 if supported.
 */
int __bdev_dax_supported(struct super_block *sb, int blocksize)
{
	struct block_device *bdev = sb->s_bdev;
	struct dax_device *dax_dev;
	pgoff_t pgoff;
	int err, id;
	void *kaddr;
	pfn_t pfn;
	long len;

	if (blocksize != PAGE_SIZE) {
		pr_err("VFS (%s): error: unsupported blocksize for dax\n",
				sb->s_id);
		return -EINVAL;
	}

	err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
	if (err) {
		pr_err("VFS (%s): error: unaligned partition for dax\n",
				sb->s_id);
		return err;
	}

	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
	if (!dax_dev) {
		pr_err("VFS (%s): error: device does not support dax\n",
				sb->s_id);
		return -EOPNOTSUPP;
	}

	id = dax_read_lock();
	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
	dax_read_unlock(id);

	put_dax(dax_dev);

	if (len < 1) {
		pr_err("VFS (%s): error: dax access failed (%ld)",
				sb->s_id, len);
		return len < 0 ? len : -EIO;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(__bdev_dax_supported);
116
#endif
117

118
119
120
121
/**
 * struct dax_device - anchor object for dax services
 * @inode: core vfs
 * @cdev: optional character interface for "device dax"
122
 * @host: optional name for lookups where the device path is not available
123
124
125
126
 * @private: dax driver private data
 * @alive: !alive + rcu grace period == no new operations / mappings
 */
struct dax_device {
127
	struct hlist_node list;
128
129
	struct inode inode;
	struct cdev cdev;
130
	const char *host;
131
132
	void *private;
	bool alive;
Dan Williams's avatar
Dan Williams committed
133
	const struct dax_operations *ops;
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
/**
 * dax_direct_access() - translate a device pgoff to an absolute pfn
 * @dax_dev: a dax_device instance representing the logical memory range
 * @pgoff: offset in pages from the start of the device to translate
 * @nr_pages: number of consecutive pages caller can handle relative to @pfn
 * @kaddr: output parameter that returns a virtual address mapping of pfn
 * @pfn: output parameter that returns an absolute pfn translation of @pgoff
 *
 * Return: negative errno if an error occurs, otherwise the number of
 * pages accessible at the device relative @pgoff.
 */
long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
		void **kaddr, pfn_t *pfn)
{
	long avail;

	/*
	 * The device driver is allowed to sleep, in order to make the
	 * memory directly accessible.
	 */
	might_sleep();

	if (!dax_dev)
		return -EOPNOTSUPP;

	if (!dax_alive(dax_dev))
		return -ENXIO;

	if (nr_pages < 0)
		return nr_pages;

	avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages,
			kaddr, pfn);
	if (!avail)
		return -ERANGE;
	return min(avail, nr_pages);
}
EXPORT_SYMBOL_GPL(dax_direct_access);

175
176
177
178
179
180
181
bool dax_alive(struct dax_device *dax_dev)
{
	lockdep_assert_held(&dax_srcu);
	return dax_dev->alive;
}
EXPORT_SYMBOL_GPL(dax_alive);

182
183
184
185
186
static int dax_host_hash(const char *host)
{
	return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE;
}

187
188
189
190
191
192
193
194
195
196
197
198
/*
 * Note, rcu is not protecting the liveness of dax_dev, rcu is ensuring
 * that any fault handlers or operations that might have seen
 * dax_alive(), have completed.  Any operations that start after
 * synchronize_srcu() has run will abort upon seeing !dax_alive().
 */
void kill_dax(struct dax_device *dax_dev)
{
	if (!dax_dev)
		return;

	dax_dev->alive = false;
199

200
	synchronize_srcu(&dax_srcu);
201
202
203
204
205

	spin_lock(&dax_host_lock);
	hlist_del_init(&dax_dev->list);
	spin_unlock(&dax_host_lock);

206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
	dax_dev->private = NULL;
}
EXPORT_SYMBOL_GPL(kill_dax);

static struct inode *dax_alloc_inode(struct super_block *sb)
{
	struct dax_device *dax_dev;

	dax_dev = kmem_cache_alloc(dax_cache, GFP_KERNEL);
	return &dax_dev->inode;
}

static struct dax_device *to_dax_dev(struct inode *inode)
{
	return container_of(inode, struct dax_device, inode);
}

static void dax_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	struct dax_device *dax_dev = to_dax_dev(inode);

228
229
	kfree(dax_dev->host);
	dax_dev->host = NULL;
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
	ida_simple_remove(&dax_minor_ida, MINOR(inode->i_rdev));
	kmem_cache_free(dax_cache, dax_dev);
}

static void dax_destroy_inode(struct inode *inode)
{
	struct dax_device *dax_dev = to_dax_dev(inode);

	WARN_ONCE(dax_dev->alive,
			"kill_dax() must be called before final iput()\n");
	call_rcu(&inode->i_rcu, dax_i_callback);
}

static const struct super_operations dax_sops = {
	.statfs = simple_statfs,
	.alloc_inode = dax_alloc_inode,
	.destroy_inode = dax_destroy_inode,
	.drop_inode = generic_delete_inode,
};

static struct dentry *dax_mount(struct file_system_type *fs_type,
		int flags, const char *dev_name, void *data)
{
	return mount_pseudo(fs_type, "dax:", &dax_sops, NULL, DAXFS_MAGIC);
}

static struct file_system_type dax_fs_type = {
	.name = "dax",
	.mount = dax_mount,
	.kill_sb = kill_anon_super,
};

static int dax_test(struct inode *inode, void *data)
{
	dev_t devt = *(dev_t *) data;

	return inode->i_rdev == devt;
}

static int dax_set(struct inode *inode, void *data)
{
	dev_t devt = *(dev_t *) data;

	inode->i_rdev = devt;
	return 0;
}

static struct dax_device *dax_dev_get(dev_t devt)
{
	struct dax_device *dax_dev;
	struct inode *inode;

	inode = iget5_locked(dax_superblock, hash_32(devt + DAXFS_MAGIC, 31),
			dax_test, dax_set, &devt);

	if (!inode)
		return NULL;

	dax_dev = to_dax_dev(inode);
	if (inode->i_state & I_NEW) {
		dax_dev->alive = true;
		inode->i_cdev = &dax_dev->cdev;
		inode->i_mode = S_IFCHR;
		inode->i_flags = S_DAX;
		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
		unlock_new_inode(inode);
	}

	return dax_dev;
}

301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
static void dax_add_host(struct dax_device *dax_dev, const char *host)
{
	int hash;

	/*
	 * Unconditionally init dax_dev since it's coming from a
	 * non-zeroed slab cache
	 */
	INIT_HLIST_NODE(&dax_dev->list);
	dax_dev->host = host;
	if (!host)
		return;

	hash = dax_host_hash(host);
	spin_lock(&dax_host_lock);
	hlist_add_head(&dax_dev->list, &dax_host_list[hash]);
	spin_unlock(&dax_host_lock);
}

Dan Williams's avatar
Dan Williams committed
320
321
struct dax_device *alloc_dax(void *private, const char *__host,
		const struct dax_operations *ops)
322
323
{
	struct dax_device *dax_dev;
324
	const char *host;
325
326
327
	dev_t devt;
	int minor;

328
329
330
331
	host = kstrdup(__host, GFP_KERNEL);
	if (__host && !host)
		return NULL;

Dan Williams's avatar
Dan Williams committed
332
	minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL);
333
	if (minor < 0)
334
		goto err_minor;
335
336
337
338

	devt = MKDEV(MAJOR(dax_devt), minor);
	dax_dev = dax_dev_get(devt);
	if (!dax_dev)
339
		goto err_dev;
340

341
	dax_add_host(dax_dev, host);
Dan Williams's avatar
Dan Williams committed
342
	dax_dev->ops = ops;
343
344
345
	dax_dev->private = private;
	return dax_dev;

346
 err_dev:
347
	ida_simple_remove(&dax_minor_ida, minor);
348
349
 err_minor:
	kfree(host);
350
351
352
353
354
355
356
357
358
359
360
361
	return NULL;
}
EXPORT_SYMBOL_GPL(alloc_dax);

void put_dax(struct dax_device *dax_dev)
{
	if (!dax_dev)
		return;
	iput(&dax_dev->inode);
}
EXPORT_SYMBOL_GPL(put_dax);

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
/**
 * dax_get_by_host() - temporary lookup mechanism for filesystem-dax
 * @host: alternate name for the device registered by a dax driver
 */
struct dax_device *dax_get_by_host(const char *host)
{
	struct dax_device *dax_dev, *found = NULL;
	int hash, id;

	if (!host)
		return NULL;

	hash = dax_host_hash(host);

	id = dax_read_lock();
	spin_lock(&dax_host_lock);
	hlist_for_each_entry(dax_dev, &dax_host_list[hash], list) {
		if (!dax_alive(dax_dev)
				|| strcmp(host, dax_dev->host) != 0)
			continue;

		if (igrab(&dax_dev->inode))
			found = dax_dev;
		break;
	}
	spin_unlock(&dax_host_lock);
	dax_read_unlock(id);

	return found;
}
EXPORT_SYMBOL_GPL(dax_get_by_host);

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
/**
 * inode_dax: convert a public inode into its dax_dev
 * @inode: An inode with i_cdev pointing to a dax_dev
 *
 * Note this is not equivalent to to_dax_dev() which is for private
 * internal use where we know the inode filesystem type == dax_fs_type.
 */
struct dax_device *inode_dax(struct inode *inode)
{
	struct cdev *cdev = inode->i_cdev;

	return container_of(cdev, struct dax_device, cdev);
}
EXPORT_SYMBOL_GPL(inode_dax);

struct inode *dax_inode(struct dax_device *dax_dev)
{
	return &dax_dev->inode;
}
EXPORT_SYMBOL_GPL(dax_inode);

void *dax_get_private(struct dax_device *dax_dev)
{
	return dax_dev->private;
}
EXPORT_SYMBOL_GPL(dax_get_private);

static void init_once(void *_dax_dev)
{
	struct dax_device *dax_dev = _dax_dev;
	struct inode *inode = &dax_dev->inode;

	inode_init_once(inode);
}

static int __dax_fs_init(void)
{
	int rc;

	dax_cache = kmem_cache_create("dax_cache", sizeof(struct dax_device), 0,
			(SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
			 SLAB_MEM_SPREAD|SLAB_ACCOUNT),
			init_once);
	if (!dax_cache)
		return -ENOMEM;

	rc = register_filesystem(&dax_fs_type);
	if (rc)
		goto err_register_fs;

	dax_mnt = kern_mount(&dax_fs_type);
	if (IS_ERR(dax_mnt)) {
		rc = PTR_ERR(dax_mnt);
		goto err_mount;
	}
	dax_superblock = dax_mnt->mnt_sb;

	return 0;

 err_mount:
	unregister_filesystem(&dax_fs_type);
 err_register_fs:
	kmem_cache_destroy(dax_cache);

	return rc;
}

static void __dax_fs_exit(void)
{
	kern_unmount(dax_mnt);
	unregister_filesystem(&dax_fs_type);
	kmem_cache_destroy(dax_cache);
}

static int __init dax_fs_init(void)
{
	int rc;

	rc = __dax_fs_init();
	if (rc)
		return rc;

Dan Williams's avatar
Dan Williams committed
476
	rc = alloc_chrdev_region(&dax_devt, 0, MINORMASK+1, "dax");
477
478
479
480
481
482
483
	if (rc)
		__dax_fs_exit();
	return rc;
}

static void __exit dax_fs_exit(void)
{
Dan Williams's avatar
Dan Williams committed
484
	unregister_chrdev_region(dax_devt, MINORMASK+1);
485
486
487
488
489
490
491
492
	ida_destroy(&dax_minor_ida);
	__dax_fs_exit();
}

MODULE_AUTHOR("Intel Corporation");
MODULE_LICENSE("GPL v2");
subsys_initcall(dax_fs_init);
module_exit(dax_fs_exit);