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
|
/*
* Persistent Memory Driver
*
* Copyright (c) 2014-2015, Intel Corporation.
* Copyright (c) 2015, Christoph Hellwig <hch@lst.de>.
* Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope 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 <asm/cacheflush.h>
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/slab.h>
#include <linux/nd.h>
#include "nd.h"
struct pmem_device {
struct request_queue *pmem_queue;
struct gendisk *pmem_disk;
/* One contiguous memory region per device */
phys_addr_t phys_addr;
void *virt_addr;
size_t size;
};
static int pmem_major;
static void pmem_do_bvec(struct pmem_device *pmem, struct page *page,
unsigned int len, unsigned int off, int rw,
sector_t sector)
{
void *mem = kmap_atomic(page);
size_t pmem_off = sector << 9;
if (rw == READ) {
memcpy(mem + off, pmem->virt_addr + pmem_off, len);
flush_dcache_page(page);
} else {
flush_dcache_page(page);
memcpy(pmem->virt_addr + pmem_off, mem + off, len);
}
kunmap_atomic(mem);
}
static void pmem_make_request(struct request_queue *q, struct bio *bio)
{
struct bio_vec bvec;
struct bvec_iter iter;
struct block_device *bdev = bio->bi_bdev;
struct pmem_device *pmem = bdev->bd_disk->private_data;
bio_for_each_segment(bvec, bio, iter)
pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, bvec.bv_offset,
bio_data_dir(bio), iter.bi_sector);
bio_endio(bio, 0);
}
static int pmem_rw_page(struct block_device *bdev, sector_t sector,
struct page *page, int rw)
{
struct pmem_device *pmem = bdev->bd_disk->private_data;
pmem_do_bvec(pmem, page, PAGE_CACHE_SIZE, 0, rw, sector);
page_endio(page, rw & WRITE, 0);
return 0;
}
static long pmem_direct_access(struct block_device *bdev, sector_t sector,
void **kaddr, unsigned long *pfn, long size)
{
struct pmem_device *pmem = bdev->bd_disk->private_data;
size_t offset = sector << 9;
if (!pmem)
return -ENODEV;
*kaddr = pmem->virt_addr + offset;
*pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT;
return pmem->size - offset;
}
static const struct block_device_operations pmem_fops = {
.owner = THIS_MODULE,
.rw_page = pmem_rw_page,
.direct_access = pmem_direct_access,
};
static struct pmem_device *pmem_alloc(struct device *dev,
struct resource *res, int id)
{
struct pmem_device *pmem;
pmem = kzalloc(sizeof(*pmem), GFP_KERNEL);
if (!pmem)
return ERR_PTR(-ENOMEM);
pmem->phys_addr = res->start;
pmem->size = resource_size(res);
if (!request_mem_region(pmem->phys_addr, pmem->size, dev_name(dev))) {
dev_warn(dev, "could not reserve region [0x%pa:0x%zx]\n",
&pmem->phys_addr, pmem->size);
kfree(pmem);
return ERR_PTR(-EBUSY);
}
/*
* Map the memory as non-cachable, as we can't write back the contents
* of the CPU caches in case of a crash.
*/
pmem->virt_addr = ioremap_nocache(pmem->phys_addr, pmem->size);
if (!pmem->virt_addr) {
release_mem_region(pmem->phys_addr, pmem->size);
kfree(pmem);
return ERR_PTR(-ENXIO);
}
return pmem;
}
static void pmem_detach_disk(struct pmem_device *pmem)
{
del_gendisk(pmem->pmem_disk);
put_disk(pmem->pmem_disk);
blk_cleanup_queue(pmem->pmem_queue);
}
static int pmem_attach_disk(struct nd_namespace_common *ndns,
struct pmem_device *pmem)
{
struct gendisk *disk;
pmem->pmem_queue = blk_alloc_queue(GFP_KERNEL);
if (!pmem->pmem_queue)
return -ENOMEM;
blk_queue_make_request(pmem->pmem_queue, pmem_make_request);
blk_queue_max_hw_sectors(pmem->pmem_queue, UINT_MAX);
blk_queue_bounce_limit(pmem->pmem_queue, BLK_BOUNCE_ANY);
disk = alloc_disk(0);
if (!disk) {
blk_cleanup_queue(pmem->pmem_queue);
return -ENOMEM;
}
disk->major = pmem_major;
disk->first_minor = 0;
disk->fops = &pmem_fops;
disk->private_data = pmem;
disk->queue = pmem->pmem_queue;
disk->flags = GENHD_FL_EXT_DEVT;
nvdimm_namespace_disk_name(ndns, disk->disk_name);
disk->driverfs_dev = &ndns->dev;
set_capacity(disk, pmem->size >> 9);
pmem->pmem_disk = disk;
add_disk(disk);
return 0;
}
static int pmem_rw_bytes(struct nd_namespace_common *ndns,
resource_size_t offset, void *buf, size_t size, int rw)
{
struct pmem_device *pmem = dev_get_drvdata(ndns->claim);
if (unlikely(offset + size > pmem->size)) {
dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
return -EFAULT;
}
if (rw == READ)
memcpy(buf, pmem->virt_addr + offset, size);
else
memcpy(pmem->virt_addr + offset, buf, size);
return 0;
}
static void pmem_free(struct pmem_device *pmem)
{
iounmap(pmem->virt_addr);
release_mem_region(pmem->phys_addr, pmem->size);
kfree(pmem);
}
static int nd_pmem_probe(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
struct nd_namespace_common *ndns;
struct nd_namespace_io *nsio;
struct pmem_device *pmem;
int rc;
ndns = nvdimm_namespace_common_probe(dev);
if (IS_ERR(ndns))
return PTR_ERR(ndns);
nsio = to_nd_namespace_io(&ndns->dev);
pmem = pmem_alloc(dev, &nsio->res, nd_region->id);
if (IS_ERR(pmem))
return PTR_ERR(pmem);
dev_set_drvdata(dev, pmem);
ndns->rw_bytes = pmem_rw_bytes;
if (is_nd_btt(dev))
rc = nvdimm_namespace_attach_btt(ndns);
else if (nd_btt_probe(ndns, pmem) == 0) {
/* we'll come back as btt-pmem */
rc = -ENXIO;
} else
rc = pmem_attach_disk(ndns, pmem);
if (rc)
pmem_free(pmem);
return rc;
}
static int nd_pmem_remove(struct device *dev)
{
struct pmem_device *pmem = dev_get_drvdata(dev);
if (is_nd_btt(dev))
nvdimm_namespace_detach_btt(to_nd_btt(dev)->ndns);
else
pmem_detach_disk(pmem);
pmem_free(pmem);
return 0;
}
MODULE_ALIAS("pmem");
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO);
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM);
static struct nd_device_driver nd_pmem_driver = {
.probe = nd_pmem_probe,
.remove = nd_pmem_remove,
.drv = {
.name = "nd_pmem",
},
.type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM,
};
static int __init pmem_init(void)
{
int error;
pmem_major = register_blkdev(0, "pmem");
if (pmem_major < 0)
return pmem_major;
error = nd_driver_register(&nd_pmem_driver);
if (error) {
unregister_blkdev(pmem_major, "pmem");
return error;
}
return 0;
}
module_init(pmem_init);
static void pmem_exit(void)
{
driver_unregister(&nd_pmem_driver.
|