summaryrefslogtreecommitdiffstats
path: root/drivers/dax/dax.c
blob: 17715773c097de0b5bbc07067cf6e06df2caf6f8 (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
/*
 * Copyright(c) 2016 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/device.h>
#include <linux/pfn_t.h>
#include <linux/cdev.h>
#include <linux/slab.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include "dax.h"

static dev_t dax_devt;
static struct class *dax_class;
static DEFINE_IDA(dax_minor_ida);
static int nr_dax = CONFIG_NR_DEV_DAX;
module_param(nr_dax, int, S_IRUGO);
MODULE_PARM_DESC(nr_dax, "max number of device-dax instances");

/**
 * struct dax_region - mapping infrastructure for dax devices
 * @id: kernel-wide unique region for a memory range
 * @base: linear address corresponding to @res
 * @kref: to pin while other agents have a need to do lookups
 * @dev: parent device backing this region
 * @align: allocation and mapping alignment for child dax devices
 * @res: physical address range of the region
 * @pfn_flags: identify whether the pfns are paged back or not
 */
struct dax_region {
	int id;
	struct ida ida;
	void *base;
	struct kref kref;
	struct device *dev;
	unsigned int align;
	struct resource res;
	unsigned long pfn_flags;
};

/**
 * struct dax_dev - subdivision of a dax region
 * @region - parent region
 * @dev - device backing the character device
 * @cdev - core chardev data
 * @alive - !alive + rcu grace period == no new mappings can be established
 * @id - child id in the region
 * @num_resources - number of physical address extents in this device
 * @res - array of physical address ranges
 */
struct dax_dev {
	struct dax_region *region;
	struct device dev;
	struct cdev cdev;
	bool alive;
	int id;
	int num_resources;
	struct resource res[0];
};

static void dax_region_free(struct kref *kref)
{
	struct dax_region *dax_region;

	dax_region = container_of(kref, struct dax_region, kref);
	kfree(dax_region);
}

void dax_region_put(struct dax_region *dax_region)
{
	kref_put(&dax_region->kref, dax_region_free);
}
EXPORT_SYMBOL_GPL(dax_region_put);

struct dax_region *alloc_dax_region(struct device *parent, int region_id,
		struct resource *res, unsigned int align, void *addr,
		unsigned long pfn_flags)
{
	struct dax_region *dax_region;

	dax_region = kzalloc(sizeof(*dax_region), GFP_KERNEL);

	if (!dax_region)
		return NULL;

	memcpy(&dax_region->res, res, sizeof(*res));
	dax_region->pfn_flags = pfn_flags;
	kref_init(&dax_region->kref);
	dax_region->id = region_id;
	ida_init(&dax_region->ida);
	dax_region->align = align;
	dax_region->dev = parent;
	dax_region->base = addr;

	return dax_region;
}
EXPORT_SYMBOL_GPL(alloc_dax_region);

static struct dax_dev *to_dax_dev(struct device *dev)
{
	return container_of(dev, struct dax_dev, dev);
}

static ssize_t size_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct dax_dev *dax_dev = to_dax_dev(dev);
	unsigned long long size = 0;
	int i;

	for (i = 0; i < dax_dev->num_resources; i++)
		size += resource_size(&dax_dev->res[i]);

	return sprintf(buf, "%llu\n", size);
}
static DEVICE_ATTR_RO(size);

static struct attribute *dax_device_attributes[] = {
	&dev_attr_size.attr,
	NULL,
};

static const struct attribute_group dax_device_attribute_group = {
	.attrs = dax_device_attributes,
};

static const struct attribute_group *dax_attribute_groups[] = {
	&dax_device_attribute_group,
	NULL,
};

static int check_vma(struct dax_dev *dax_dev, struct vm_area_struct *vma,
		const char *func)
{
	struct dax_region *dax_region = dax_dev->region;
	struct device *dev = &dax_dev->dev;
	unsigned long mask;

	if (!dax_dev->alive)
		return -ENXIO;

	/* prevent private / writable mappings from being established */
	if ((vma->vm_flags & (VM_NORESERVE|VM_SHARED|VM_WRITE)) == VM_WRITE) {
		dev_info(dev, "%s: %s: fail, attempted private mapping\n",
				current->comm, func);
		return -EINVAL;
	}

	mask = dax_region->align - 1;
	if (vma->vm_start & mask || vma->vm_end & mask) {
		dev_info(dev, "%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
				current->comm, func, vma->vm_start, vma->vm_end,
				mask);
		return -EINVAL;
	}

	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) == PFN_DEV
			&& (vma->vm_flags & VM_DONTCOPY) == 0) {
		dev_info(dev, "%s: %s: fail, dax range requires MADV_DONTFORK\n",
				current->comm, func);
		return -EINVAL;
	}

	if (!vma_is_dax(vma)) {
		dev_info(dev, "%s: %s: fail, vma is not DAX capable\n",
				current->comm, func);
		return -EINVAL;
	}

	return 0;
}

static phys_addr_t pgoff_to_phys(struct dax_dev *dax_dev, pgoff_t pgoff,
		unsigned long size)
{
	struct resource *res;
	phys_addr_t phys;
	int i;

	for (i = 0; i < dax_dev->num_resources; i++) {
		res = &dax_dev->res[i];
		phys = pgoff * PAGE_SIZE + res->start;
		if (phys >= res->start && phys <= res->end)
			break;
		pgoff -= PHYS_PFN(resource_size(res));
	}

	if (i < dax_dev->num_resources) {
		res = &dax_dev->res[i];
		if (phys + size - 1 <= res->end)
			return phys;
	}

	return -1;
}

static int __dax_dev_fault(struct dax_dev *dax_dev, struct vm_area_struct *vma,
		struct vm_fault *vmf)
{
	unsigned long vaddr = (unsigned long) vmf->virtual_address;
	struct device *dev = &dax_dev->dev;
	struct dax_region *dax_region;
	int rc = VM_FAULT_SIGBUS;
	phys_addr_t phys;
	pfn_t pfn;

	if (check_vma(dax_dev, vma, __func__))
		return VM_FAULT_SIGBUS;

	dax_region = dax_dev->region;
	if (dax_region->align > PAGE_SIZE) {
		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
		return VM_FAULT_SIGBUS;
	}

	phys = pgoff_to_phys(dax_dev, vmf->pgoff, PAGE_SIZE);
	if (phys == -1) {
		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
				vmf->pgoff);
		return VM_FAULT_SIGBUS;
	}

	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);

	rc = vm_insert_mixed(vma, vaddr, pfn);

	if (rc == -ENOMEM)
		return VM_FAULT_OOM;
	if (rc < 0 && rc != -EBUSY)
		return VM_FAULT_SIGBUS;

	return VM_FAULT_NOPAGE;
}

static int dax_dev_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	int rc;
	struct file *filp = vma->vm_file;
	struct dax_dev *dax_dev = filp->private_data;

	dev_dbg(&dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
			current->comm, (vmf->flags & FAULT_FLAG_WRITE)
			? "write" : "read", vma->vm_start, vma->vm_end);
	rcu_read_lock();
	rc = __dax_dev_fault(dax_dev, vma, vmf);
	rcu_read_unlock();

	return rc;
}

static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
		struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd,
		unsigned int flags)
{
	unsigned long pmd_addr = addr & PMD_MASK;
	struct device *dev = &dax_dev->dev;
	struct dax_region *dax_region;
	phys_addr_t phys;
	pgoff_t pgoff;
	pfn_t pfn;

	if (check_vma(dax_dev, vma, __func__))
		return VM_FAULT_SIGBUS;

	dax_region = dax_dev->region;
	if (dax_region->align > PMD_SIZE) {
		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
		return VM_FAULT_SIGBUS;
	}

	/* dax pmd mappings require pfn_t_devmap() */
	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) {
		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
		return VM_FAULT_SIGBUS;
	}

	pgoff = linear_page_index(vma, pmd_addr);
	phys = pgoff_to_phys(dax_dev, pgoff, PAGE_SIZE);
	if (phys == -1) {
		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
				pgoff);
		return VM_FAULT_SIGBUS;
	}

	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);

	return vmf_insert_pfn_pmd(vma, addr, pmd, pfn,
			flags & FAULT_FLAG_WRITE);
}

static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
		pmd_t *pmd, unsigned int flags)
{
	int rc;
	struct file *filp = vma->vm_file;
	struct dax_dev *dax_dev = filp->private_data;

	dev_dbg(&dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
			current->comm, (flags & FAULT_FLAG_WRITE)
			? "write" : "read", vma->vm_start, vma->vm_end);

	rcu_read_lock();
	rc = __dax_dev_pmd_fault(dax_dev, vma, addr, pmd, flags);
	rcu_read_unlock();

	return rc;
}

static const struct vm_operations_struct dax_dev_vm_ops = {
	.fault = dax_dev_fault,
	.pmd_fault = dax_dev_pmd_fault,
};

static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
{
	struct dax_dev *dax_dev = filp->private_data;
	int rc;

	dev_dbg(&dax_dev->dev, "%s\n", __func__);

	rc = check_vma(dax_dev, vma, __func__);
	if (rc)
		return rc;

	vma->vm_ops = &dax_dev_vm_ops;
	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
	return 0;
}

/* return an unmapped area aligned to the dax region specified alignment */
static unsigned long dax_get_unmapped_area(struct file *filp,
		unsigned long addr, unsigned long len, unsigned long pgoff,
		unsigned long flags)
{
	unsigned long off, off_end, off_align, len_align, addr_align, align;
	struct dax_dev *dax_dev = filp ? filp->private_data : NULL;
	struct dax_region *dax_region;

	if (!dax_dev || addr)
		goto out;

	dax_region = dax_dev->region;
	align = dax_region->align;
	off = pgoff << PAGE_SHIFT;
	off_end = off + len;
	off_align = round_up(off, align);

	if ((off_end <= off_align) || ((off_end - off_align) < align))
		goto out;

	len_align = len + align;
	if ((off + len_align) < off)
		goto out;

	addr_align = current->mm->get_unmapped_area(filp, addr, len_align,
			pgoff, flags);
	if (!IS_ERR_VALUE(addr_align)) {
		addr_align += (off - addr_align) & (align - 1);
		return addr_align;
	}
 out:
	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
}

static int dax_open(struct inode *inode, struct file *filp)
{
	struct dax_dev *dax_dev;

	dax_dev = container_of(inode->i_cdev, struct dax_dev, cdev);
	dev_dbg(&dax_dev->dev, "%s\n", __func__);
	filp->private_data = dax_dev;
	inode->i_flags = S_DAX;

	return 0;
}

static int dax_release(struct inode *inode, struct file *filp)
{
	struct dax_dev *dax_dev = filp->private_data;

	dev_dbg(&dax_dev->dev, "%s\n", __func__);
	return 0;
}

static const struct file_operations dax_fops = {
	.llseek = noop_llseek,
	.owner = THIS_MODULE,
	.open = dax_open,
	.release = dax_release,
	.get_unmapped_area = dax_get_unmapped_area,
	.mmap = dax_mmap,
};

static void dax_dev_release(struct device *dev)
{
	struct dax_dev *dax_dev = to_dax_dev(dev);
	struct dax_region *dax_region = dax_dev->region;

	ida_simple_remove(&dax_region->ida, dax_dev->id);
	ida_simple_remove(&dax_minor_ida, MINOR(dev->devt));
	dax_region_put(dax_region);
	kfree(dax_dev);
}

static void unregister_dax_dev(void *dev)
{
	struct dax_dev *dax_dev = to_dax_dev(dev);
	struct cdev *cdev = &dax_dev->cdev;

	dev_dbg(dev, "%s\n", __func__);

	/*
	 * Note, rcu is not protecting the liveness of dax_dev, rcu is
	 * ensuring that any fault handlers that might have seen
	 * dax_dev->alive == true, have completed.  Any fault handlers
	 * that start after synchronize_rcu() has started will abort
	 * upon seeing dax_dev->alive == false.
	 */
	dax_dev->alive = false;
	synchronize_rcu();
	cdev_del(cdev);
	device_unregister(dev);
}

int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
		int count)
{
	struct device *parent = dax_region->dev;
	struct dax_dev *dax_dev;
	struct device *dev;
	struct cdev *cdev;
	int rc, minor;
	dev_t dev_t;

	dax_dev = kzalloc(sizeof(*dax_dev) + sizeof(*res) * count, GFP_KERNEL);
	if (!dax_dev)
		return -ENOMEM;

	dax_dev->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL);
	if (dax_dev->id < 0) {
		rc = dax_dev->id;
		goto err_id;
	}

	minor = ida_simple_get(&dax_minor_ida, 0, 0, GFP_KERNEL);
	if (minor < 0) {
		rc = minor;
		goto err_minor;
	}

	/* device_initialize() so cdev can reference kobj parent */
	dev_t = MKDEV(MAJOR(dax_devt), minor);
	dev = &dax_dev->dev;
	device_initialize(dev);

	cdev = &dax_dev->cdev;
	cdev_init(cdev, &dax_fops);
	cdev->owner = parent->driver->owner;
	cdev->kobj.parent = &dev->kobj;
	rc = cdev_add(&dax_dev->cdev, dev_t, 1);
	if (rc)
		goto err_cdev;

	/* from here on we're committed to teardown via dax_dev_release() */
	memcpy(dax_dev->res, res, sizeof(*res) * count);
	dax_dev->num_resources = count;
	dax_dev->alive = true;
	dax_dev->region = dax_region;
	kref_get(&dax_region->kref);

	dev->devt = dev_t;
	dev->class = dax_class;
	dev->parent = parent;
	dev->groups = dax_attribute_groups;
	dev->release = dax_dev_release;
	dev_set_name(dev, "dax%d.%d", dax_region->id, dax_dev->id);
	rc = device_add(dev);
	if (rc) {
		put_device(dev);
		return rc;
	}

	return devm_add_action_or_reset(dax_region->dev, unregister_dax_dev, dev);

 err_cdev:
	ida_simple_remove(&dax_minor_ida, minor);
 err_minor:
	ida_simple_remove(&dax_region->ida, dax_dev->id);
 err_id:
	kfree(dax_dev);

	return rc;
}
EXPORT_SYMBOL_GPL(devm_create_dax_dev);

static int __init dax_init(void)
{
	int rc;

	nr_dax = max(nr_dax, 256);
	rc = alloc_chrdev_region(&dax_devt, 0, nr_dax, "dax");
	if (rc)
		return rc;

	dax_class = class_create(THIS_MODULE, "dax");
	if (IS_ERR(dax_class))
		unregister_chrdev_region(dax_devt, nr_dax);

	return PTR_ERR_OR_ZERO(dax_class);
}

static void __exit dax_exit(void)
{
	class_destroy(dax_class);
	unregister_chrdev_region(dax_devt, nr_dax);
	ida_destroy(&dax_minor_ida);
}

MODULE_AUTHOR("Intel Corporation");
MODULE_LICENSE("GPL v2");
subsys_initcall(dax_init);
module_exit(dax_exit);