summaryrefslogtreecommitdiff
path: root/drivers/dax/super.c
blob: e16d1d40d7738acaa89f9572ae62c3ab773e9e66 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright(c) 2017 Intel Corporation. All rights reserved.
 */
#include <linux/pagemap.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/pseudo_fs.h>
#include <linux/magic.h>
#include <linux/pfn_t.h>
#include <linux/cdev.h>
#include <linux/slab.h>
#include <linux/uio.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/cacheinfo.h>
#include "dax-private.h"

/**
 * struct dax_device - anchor object for dax services
 * @inode: core vfs
 * @cdev: optional character interface for "device dax"
 * @private: dax driver private data
 * @flags: state and boolean properties
 * @ops: operations for this device
 * @holder_data: holder of a dax_device: could be filesystem or mapped device
 * @holder_ops: operations for the inner holder
 */
struct dax_device {
	struct inode inode;
	struct cdev cdev;
	void *private;
	unsigned long flags;
	const struct dax_operations *ops;
	void *holder_data;
	const struct dax_holder_operations *holder_ops;
};

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;

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);

#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
#include <linux/blkdev.h>

static DEFINE_XARRAY(dax_hosts);

int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
{
	return xa_insert(&dax_hosts, (unsigned long)disk, dax_dev, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(dax_add_host);

void dax_remove_host(struct gendisk *disk)
{
	xa_erase(&dax_hosts, (unsigned long)disk);
}
EXPORT_SYMBOL_GPL(dax_remove_host);

/**
 * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax
 * @bdev: block device to find a dax_device for
 * @start_off: returns the byte offset into the dax_device that @bdev starts
 * @holder: filesystem or mapped device inside the dax_device
 * @ops: operations for the inner holder
 */
struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off,
		void *holder, const struct dax_holder_operations *ops)
{
	struct dax_device *dax_dev;
	u64 part_size;
	int id;

	if (!blk_queue_dax(bdev->bd_disk->queue))
		return NULL;

	*start_off = get_start_sect(bdev) * SECTOR_SIZE;
	part_size = bdev_nr_sectors(bdev) * SECTOR_SIZE;
	if (*start_off % PAGE_SIZE || part_size % PAGE_SIZE) {
		pr_info("%pg: error: unaligned partition for dax\n", bdev);
		return NULL;
	}

	id = dax_read_lock();
	dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk);
	if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode))
		dax_dev = NULL;
	else if (holder) {
		if (!cmpxchg(&dax_dev->holder_data, NULL, holder))
			dax_dev->holder_ops = ops;
		else
			dax_dev = NULL;
	}
	dax_read_unlock(id);

	return dax_dev;
}
EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);

void fs_put_dax(struct dax_device *dax_dev, void *holder)
{
	if (dax_dev && holder &&
	    cmpxchg(&dax_dev->holder_data, holder, NULL) == holder)
		dax_dev->holder_ops = NULL;
	put_dax(dax_dev);
}
EXPORT_SYMBOL_GPL(fs_put_dax);
#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */

enum dax_device_flags {
	/* !alive + rcu grace period == no new operations / mappings */
	DAXDEV_ALIVE,
	/* gate whether dax_flush() calls the low level flush routine */
	DAXDEV_WRITE_CACHE,
	/* flag to check if device supports synchronous flush */
	DAXDEV_SYNC,
	/* do not leave the caches dirty after writes */
	DAXDEV_NOCACHE,
	/* handle CPU fetch exceptions during reads */
	DAXDEV_NOMC,
};

/**
 * 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
 * @mode: indicator on normal access or recovery write
 * @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,
		enum dax_access_mode mode, void **kaddr, pfn_t *pfn)
{
	long avail;

	if (!dax_dev)
		return -EOPNOTSUPP;

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

	if (nr_pages < 0)
		return -EINVAL;

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

size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
		size_t bytes, struct iov_iter *i)
{
	if (!dax_alive(dax_dev))
		return 0;

	/*
	 * The userspace address for the memory copy has already been validated
	 * via access_ok() in vfs_write, so use the 'no check' version to bypass
	 * the HARDENED_USERCOPY overhead.
	 */
	if (test_bit(DAXDEV_NOCACHE, &dax_dev->flags))
		return _copy_from_iter_flushcache(addr, bytes, i);
	return _copy_from_iter(addr, bytes, i);
}

size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
		size_t bytes, struct iov_iter *i)
{
	if (!dax_alive(dax_dev))
		return 0;

	/*
	 * The userspace address for the memory copy has already been validated
	 * via access_ok() in vfs_red, so use the 'no check' version to bypass
	 * the HARDENED_USERCOPY overhead.
	 */
	if (test_bit(DAXDEV_NOMC, &dax_dev->flags))
		return _copy_mc_to_iter(addr, bytes, i);
	return _copy_to_iter(addr, bytes, i);
}

int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
			size_t nr_pages)
{
	int ret;

	if (!dax_alive(dax_dev))
		return -ENXIO;
	/*
	 * There are no callers that want to zero more than one page as of now.
	 * Once users are there, this check can be removed after the
	 * device mapper code has been updated to split ranges across targets.
	 */
	if (nr_pages != 1)
		return -EIO;

	ret = dax_dev->ops->zero_page_range(dax_dev, pgoff, nr_pages);
	return dax_mem2blk_err(ret);
}
EXPORT_SYMBOL_GPL(dax_zero_page_range);

size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
		void *addr, size_t bytes, struct iov_iter *iter)
{
	if (!dax_dev->ops->recovery_write)
		return 0;
	return dax_dev->ops->recovery_write(dax_dev, pgoff, addr, bytes, iter);
}
EXPORT_SYMBOL_GPL(dax_recovery_write);

int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off,
			      u64 len, int mf_flags)
{
	int rc, id;

	id = dax_read_lock();
	if (!dax_alive(dax_dev)) {
		rc = -ENXIO;
		goto out;
	}

	if (!dax_dev->holder_ops) {
		rc = -EOPNOTSUPP;
		goto out;
	}

	rc = dax_dev->holder_ops->notify_failure(dax_dev, off, len, mf_flags);
out:
	dax_read_unlock(id);
	return rc;
}
EXPORT_SYMBOL_GPL(dax_holder_notify_failure);

#ifdef CONFIG_ARCH_HAS_PMEM_API
void arch_wb_cache_pmem(void *addr, size_t size);
void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
{
	if (unlikely(!dax_write_cache_enabled(dax_dev)))
		return;

	arch_wb_cache_pmem(addr, size);
}
#else
void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
{
}
#endif
EXPORT_SYMBOL_GPL(dax_flush);

void dax_write_cache(struct dax_device *dax_dev, bool wc)
{
	if (wc)
		set_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
	else
		clear_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(dax_write_cache);

bool dax_write_cache_enabled(struct dax_device *dax_dev)
{
	return test_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(dax_write_cache_enabled);

bool dax_synchronous(struct dax_device *dax_dev)
{
	return test_bit(DAXDEV_SYNC, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(dax_synchronous);

void set_dax_synchronous(struct dax_device *dax_dev)
{
	set_bit(DAXDEV_SYNC, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(set_dax_synchronous);

void set_dax_nocache(struct dax_device *dax_dev)
{
	set_bit(DAXDEV_NOCACHE, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(set_dax_nocache);

void set_dax_nomc(struct dax_device *dax_dev)
{
	set_bit(DAXDEV_NOMC, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(set_dax_nomc);

bool dax_alive(struct dax_device *dax_dev)
{
	lockdep_assert_held(&dax_srcu);
	return test_bit(DAXDEV_ALIVE, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(dax_alive);

/*
 * 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().
 *
 * Note, because alloc_dax() returns an ERR_PTR() on error, callers
 * typically store its result into a local variable in order to check
 * the result. Therefore, care must be taken to populate the struct
 * device dax_dev field make sure the dax_dev is not leaked.
 */
void kill_dax(struct dax_device *dax_dev)
{
	if (!dax_dev)
		return;

	if (dax_dev->holder_data != NULL)
		dax_holder_notify_failure(dax_dev, 0, U64_MAX,
				MF_MEM_PRE_REMOVE);

	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
	synchronize_srcu(&dax_srcu);

	/* clear holder data */
	dax_dev->holder_ops = NULL;
	dax_dev->holder_data = NULL;
}
EXPORT_SYMBOL_GPL(kill_dax);

void run_dax(struct dax_device *dax_dev)
{
	set_bit(DAXDEV_ALIVE, &dax_dev->flags);
}
EXPORT_SYMBOL_GPL(run_dax);

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

	dax_dev = alloc_inode_sb(sb, dax_cache, GFP_KERNEL);
	if (!dax_dev)
		return NULL;

	inode = &dax_dev->inode;
	inode->i_rdev = 0;
	return inode;
}

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

static void dax_free_inode(struct inode *inode)
{
	struct dax_device *dax_dev = to_dax_dev(inode);
	if (inode->i_rdev)
		ida_free(&dax_minor_ida, iminor(inode));
	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(test_bit(DAXDEV_ALIVE, &dax_dev->flags),
			"kill_dax() must be called before final iput()\n");
}

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

static int dax_init_fs_context(struct fs_context *fc)
{
	struct pseudo_fs_context *ctx = init_pseudo(fc, DAXFS_MAGIC);
	if (!ctx)
		return -ENOMEM;
	ctx->ops = &dax_sops;
	return 0;
}

static struct file_system_type dax_fs_type = {
	.name		= "dax",
	.init_fs_context = dax_init_fs_context,
	.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) {
		set_bit(DAXDEV_ALIVE, &dax_dev->flags);
		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;
}

struct dax_device *alloc_dax(void *private, const struct dax_operations *ops)
{
	struct dax_device *dax_dev;
	dev_t devt;
	int minor;

	/*
	 * Unavailable on architectures with virtually aliased data caches,
	 * except for device-dax (NULL operations pointer), which does
	 * not use aliased mappings from the kernel.
	 */
	if (ops && cpu_dcache_is_aliasing())
		return ERR_PTR(-EOPNOTSUPP);

	if (WARN_ON_ONCE(ops && !ops->zero_page_range))
		return ERR_PTR(-EINVAL);

	minor = ida_alloc_max(&dax_minor_ida, MINORMASK, GFP_KERNEL);
	if (minor < 0)
		return ERR_PTR(-ENOMEM);

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

	dax_dev->ops = ops;
	dax_dev->private = private;
	return dax_dev;

 err_dev:
	ida_free(&dax_minor_ida, minor);
	return ERR_PTR(-ENOMEM);
}
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);

/**
 * dax_holder() - obtain the holder of a dax device
 * @dax_dev: a dax_device instance
 *
 * Return: the holder's data which represents the holder if registered,
 * otherwize NULL.
 */
void *dax_holder(struct dax_device *dax_dev)
{
	return dax_dev->holder_data;
}
EXPORT_SYMBOL_GPL(dax_holder);

/**
 * 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)
{
	if (!test_bit(DAXDEV_ALIVE, &dax_dev->flags))
		return NULL;
	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;

	memset(dax_dev, 0, sizeof(*dax_dev));
	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_ACCOUNT,
			init_once);
	if (!dax_cache)
		return -ENOMEM;

	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:
	kmem_cache_destroy(dax_cache);

	return rc;
}

static void dax_fs_exit(void)
{
	kern_unmount(dax_mnt);
	rcu_barrier();
	kmem_cache_destroy(dax_cache);
}

static int __init dax_core_init(void)
{
	int rc;

	rc = dax_fs_init();
	if (rc)
		return rc;

	rc = alloc_chrdev_region(&dax_devt, 0, MINORMASK+1, "dax");
	if (rc)
		goto err_chrdev;

	rc = dax_bus_init();
	if (rc)
		goto err_bus;
	return 0;

err_bus:
	unregister_chrdev_region(dax_devt, MINORMASK+1);
err_chrdev:
	dax_fs_exit();
	return 0;
}

static void __exit dax_core_exit(void)
{
	dax_bus_exit();
	unregister_chrdev_region(dax_devt, MINORMASK+1);
	ida_destroy(&dax_minor_ida);
	dax_fs_exit();
}

MODULE_AUTHOR("Intel Corporation");
MODULE_DESCRIPTION("DAX: direct access to differentiated memory");
MODULE_LICENSE("GPL v2");
subsys_initcall(dax_core_init);
module_exit(dax_core_exit);