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
|
/*
* Copyright(c) 2013-2015 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/device.h>
#include <linux/sizes.h>
#include "nd-core.h"
#include "pmem.h"
#include "pfn.h"
#include "btt.h"
#include "nd.h"
void __nd_detach_ndns(struct device *dev, struct nd_namespace_common **_ndns)
{
struct nd_namespace_common *ndns = *_ndns;
struct nvdimm_bus *nvdimm_bus;
if (!ndns)
return;
nvdimm_bus = walk_to_nvdimm_bus(&ndns->dev);
lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
dev_WARN_ONCE(dev, ndns->claim != dev, "%s: invalid claim\n", __func__);
ndns->claim = NULL;
*_ndns = NULL;
put_device(&ndns->dev);
}
void nd_detach_ndns(struct device *dev,
struct nd_namespace_common **_ndns)
{
struct nd_namespace_common *ndns = *_ndns;
if (!ndns)
return;
get_device(&ndns->dev);
nvdimm_bus_lock(&ndns->dev);
__nd_detach_ndns(dev, _ndns);
nvdimm_bus_unlock(&ndns->dev);
put_device(&ndns->dev);
}
bool __nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach,
struct nd_namespace_common **_ndns)
{
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&attach->dev);
if (attach->claim)
return false;
lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
dev_WARN_ONCE(dev, *_ndns, "%s: invalid claim\n", __func__);
attach->claim = dev;
*_ndns = attach;
get_device(&attach->dev);
return true;
}
bool nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach,
struct nd_namespace_common **_ndns)
{
bool claimed;
nvdimm_bus_lock(&attach->dev);
claimed = __nd_attach_ndns(dev, attach, _ndns);
nvdimm_bus_unlock(&attach->dev);
return claimed;
}
static int namespace_match(struct device *dev, void *data)
{
char *name = data;
return strcmp(name, dev_name(dev)) == 0;
}
static bool is_idle(struct device *dev, struct nd_namespace_common *ndns)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
struct device *seed = NULL;
if (is_nd_btt(dev))
seed = nd_region->btt_seed;
else if (is_nd_pfn(dev))
seed = nd_region->pfn_seed;
else if (is_nd_dax(dev))
seed = nd_region->dax_seed;
if (seed == dev || ndns || dev->driver)
return false;
return true;
}
struct nd_pfn *to_nd_pfn_safe(struct device *dev)
{
/*
* pfn device attributes are re-used by dax device instances, so we
* need to be careful to correct device-to-nd_pfn conversion.
*/
if (is_nd_pfn(dev))
return to_nd_pfn(dev);
if (is_nd_dax(dev)) {
struct nd_dax *nd_dax = to_nd_dax(dev);
return &nd_dax->nd_pfn;
}
WARN_ON(1);
return NULL;
}
static void nd_detach_and_reset(struct device *dev,
struct nd_namespace_common **_ndns)
{
/* detach the namespace and destroy / reset the device */
__nd_detach_ndns(dev, _ndns);
if (is_idle(dev, *_ndns)) {
nd_device_unregister(dev, ND_ASYNC);
} else if (is_nd_btt(dev)) {
struct nd_btt *nd_btt = to_nd_btt(dev);
nd_btt->lbasize = 0;
kfree(nd_btt->uuid);
nd_btt->uuid = NULL;
} else if (is_nd_pfn(dev) || is_nd_dax(dev)) {
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
kfree(nd_pfn->uuid);
nd_pfn->uuid = NULL;
nd_pfn->mode = PFN_MODE_NONE;
}
}
ssize_t nd_namespace_store(struct device *dev,
struct nd_namespace_common **_ndns, const char *buf,
size_t len)
{
struct nd_namespace_common *ndns;
struct device *found;
char *name;
if (dev->driver) {
dev_dbg(dev, "%s: -EBUSY\n", __func__);
return -EBUSY;
}
name = kstrndup(buf, len, GFP_KERNEL);
if (!name)
return -ENOMEM;
strim(name);
if (strncmp(name, "namespace", 9) == 0 || strcmp(name, "") == 0)
/* pass */;
else {
len = -EINVAL;
goto out;
}
ndns = *_ndns;
if (strcmp(name, "") == 0) {
nd_detach_and_reset(dev, _ndns);
goto out;
} else if (ndns) {
dev_dbg(dev, "namespace already set to: %s\n",
dev_name(&ndns->dev));
len = -EBUSY;
goto out;
}
found = device_find_child(dev->parent, name, namespace_match);
if (!found) {
dev_dbg(dev, "'%s' not found under %s\n", name,
dev_name(dev->parent));
len = -ENODEV;
goto out;
}
ndns = to_ndns(found);
switch (ndns->claim_class) {
case NVDIMM_CCLASS_NONE:
break;
case NVDIMM_CCLASS_BTT:
case NVDIMM_CCLASS_BTT2:
if (!is_nd_btt(dev)) {
len = -EBUSY;
goto out_attach;
}
break;
case NVDIMM_CCLASS_PFN:
if (!is_nd_pfn(dev)) {
len = -EBUSY;
goto out_attach;
}
break;
case NVDIMM_CCLASS_DAX:
if (!is_nd_dax(dev)) {
len = -EBUSY;
goto out_attach;
}
break;
default:
len = -EBUSY;
goto out_attach;
break;
}
if (__nvdimm_namespace_capacity(ndns) < SZ_16M) {
dev_dbg(dev, "%s too small to host\n", name);
len = -ENXIO;
goto out_attach;
}
WARN_ON_ONCE(!is_nvdimm_bus_locked(dev));
if (!__nd_attach_ndns(dev, ndns, _ndns)) {
dev_dbg(dev, "%s already claimed\n",
dev_name(&ndns->dev));
len = -EBUSY;
}
out_attach:
put_device(&ndns->dev); /* from device_find_child */
out:
kfree(name);
return len;
}
/*
* nd_sb_checksum: compute checksum for a generic info block
*
* Returns a fletcher64 checksum of everything in the given info block
* except the last field (since that's where the checksum lives).
*/
u64 nd_sb_checksum(struct nd_gen_sb *nd_gen_sb)
{
u64 sum;
__le64 sum_save;
BUILD_BUG_ON(sizeof(struct btt_sb) != SZ_4K);
BUILD_BUG_ON(sizeof(struct nd_pfn_sb) != SZ_4K);
BUILD_BUG_ON(sizeof(struct nd_gen_sb) != SZ_4K);
sum_save = nd_gen_sb->checksum;
nd_gen_sb->checksum = 0;
sum = nd_fletcher64(nd_gen_sb, sizeof(*nd_gen_sb), 1);
nd_gen_sb->checksum = sum_save;
return sum;
}
EXPORT_SYMBOL(nd_sb_checksum);
static int nsio_rw_bytes(struct nd_namespace_common *ndns,
resource_size_t offset, void *buf, size_t size, int rw,
unsigned long flags)
{
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
unsigned int sz_align = ALIGN(size + (offset & (512 - 1)), 512);
sector_t sector = offset >> 9;
int rc = 0;
if (unlikely(!size))
return 0;
if (unlikely(offset + size > nsio->size)) {
dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
return -EFAULT;
}
if (rw == READ) {
if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align)))
return -EIO;
return memcpy_mcsafe(buf, nsio->addr + offset, size);
}
if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) {
/*
* FIXME: nsio_rw_bytes() may be called from atomic
* context in the btt case and the ACPI DSM path for
* clearing the error takes sleeping locks and allocates
* memory. An explicit error clearing path, and support
* for tracking badblocks in BTT metadata is needed to
* work around this collision.
*/
if (IS_ALIGNED(offset, 512) && IS_ALIGNED(size, 512)
&& !(flags & NVDIMM_IO_ATOMIC)) {
long cleared;
might_sleep();
cleared = nvdimm_clear_poison(&ndns->dev,
nsio->res.start + offset, size);
if (cleared < size)
rc = -EIO;
if (cleared > 0 && cleared / 512) {
cleared /= 512;
badblocks_clear(&nsio->bb, sector, cleared);
}
arch_invalidate_pmem(nsio->addr + offset, size);
} else
rc = -EIO;
}
memcpy_flushcache(nsio->addr + offset, buf, size);
nvdimm_flush(to_nd_region(ndns->dev.parent));
return rc;
}
int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio)
{
struct resource *res = &nsio->res;
struct nd_namespace_common *ndns = &nsio->common;
nsio->size = resource_size(res);
if (!devm_request_mem_region(dev, res->start, resource_size(res),
dev_name(&ndns->dev))) {
dev_warn(dev, "could not reserve region %pR\n", res);
return -EBUSY;
}
ndns->rw_bytes = nsio_rw_bytes;
if (devm_init_badblocks(dev, &nsio->bb))
return -ENOMEM;
nvdimm_badblocks_populate(to_nd_region(ndns->dev.parent), &nsio->bb,
&nsio->res);
nsio->addr = devm_memremap(dev, res->start, resource_size(res),
ARCH_MEMREMAP_PMEM);
return PTR_ERR_OR_ZERO(nsio->addr);
}
EXPORT_SYMBOL_GPL(devm_nsio_enable);
void devm_nsio_disable(struct device *dev, struct nd_namespace_io *nsio)
{
struct resource *res = &nsio->res;
devm_memunmap(dev, nsio->addr);
devm_exit_badblocks(dev, &nsio->bb);
devm_release_mem_region(dev, res->start, resource_size(res));
}
EXPORT_SYMBOL_GPL(devm_nsio_disable);
|