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
|
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright(c) 2015 Intel Corporation. All rights reserved. */
#include <linux/device.h>
#include <linux/io.h>
#include <linux/kasan.h>
#include <linux/memory_hotplug.h>
#include <linux/mm.h>
#include <linux/pfn_t.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/types.h>
#include <linux/wait_bit.h>
#include <linux/xarray.h>
static DEFINE_XARRAY(pgmap_array);
#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
#ifdef CONFIG_DEV_PAGEMAP_OPS
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
EXPORT_SYMBOL(devmap_managed_key);
static atomic_t devmap_managed_enable;
static void devmap_managed_enable_put(void *data)
{
if (atomic_dec_and_test(&devmap_managed_enable))
static_branch_disable(&devmap_managed_key);
}
static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
{
if (!pgmap->ops || !pgmap->ops->page_free) {
WARN(1, "Missing page_free method\n");
return -EINVAL;
}
if (atomic_inc_return(&devmap_managed_enable) == 1)
static_branch_enable(&devmap_managed_key);
return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL);
}
#else
static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
{
return -EINVAL;
}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
static void pgmap_array_delete(struct resource *res)
{
xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
NULL, GFP_KERNEL);
synchronize_rcu();
}
static unsigned long pfn_first(struct dev_pagemap *pgmap)
{
return PHYS_PFN(pgmap->res.start) +
vmem_altmap_offset(pgmap_altmap(pgmap));
}
static unsigned long pfn_end(struct dev_pagemap *pgmap)
{
const struct resource *res = &pgmap->res;
return (res->start + resource_size(res)) >> PAGE_SHIFT;
}
static unsigned long pfn_next(unsigned long pfn)
{
if (pfn % 1024 == 0)
cond_resched();
return pfn + 1;
}
#define for_each_device_pfn(pfn, map) \
for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
static void dev_pagemap_kill(struct dev_pagemap *pgmap)
{
if (pgmap->ops && pgmap->ops->kill)
pgmap->ops->kill(pgmap);
else
percpu_ref_kill(pgmap->ref);
}
static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
{
if (pgmap->ops && pgmap->ops->cleanup) {
pgmap->ops->cleanup(pgmap);
} else {
wait_for_completion(&pgmap->done);
percpu_ref_exit(pgmap->ref);
}
/*
* Undo the pgmap ref assignment for the internal case as the
* caller may re-enable the same pgmap.
*/
if (pgmap->ref == &pgmap->internal_ref)
pgmap->ref = NULL;
}
static void devm_memremap_pages_release(void *data)
{
struct dev_pagemap *pgmap = data;
struct device *dev = pgmap->dev;
struct resource *res = &pgmap->res;
unsigned long pfn;
int nid;
dev_pagemap_kill(pgmap);
for_each_device_pfn(pfn, pgmap)
put_page(pfn_to_page(pfn));
dev_pagemap_cleanup(pgmap);
/* pages are dead and unused, undo the arch mapping */
nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start)));
mem_hotplug_begin();
if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
pfn = PHYS_PFN(res->start);
__remove_pages(page_zone(pfn_to_page(pfn)), pfn,
PHYS_PFN(resource_size(res)), NULL);
} else {
arch_remove_memory(nid, res->start, resource_size(res),
pgmap_altmap(pgmap));
kasan_remove_zero_shadow(__va(res->start), resource_size(res));
}
mem_hotplug_done();
untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
pgmap_array_delete(res);
dev_WARN_ONCE(dev, pgmap->altmap.alloc,
"%s: failed to free all reserved pages\n", __func__);
}
static void dev_pagemap_percpu_release(struct percpu_ref *ref)
{
struct dev_pagemap *pgmap =
container_of(ref, struct dev_pagemap, internal_ref);
complete(&pgmap->done);
}
/**
* devm_memremap_pages - remap and provide memmap backing for the given resource
* @dev: hosting device for @res
* @pgmap: pointer to a struct dev_pagemap
*
* Notes:
* 1/ At a minimum the res and type members of @pgmap must be initialized
* by the caller before passing it to this function
*
* 2/ The altmap field may optionally be initialized, in which case
* PGMAP_ALTMAP_VALID must be set in pgmap->flags.
*
* 3/ The ref field may optionally be provided, in which pgmap->ref must be
* 'live' on entry and will be killed and reaped at
* devm_memremap_pages_release() time, or if this routine fails.
*
* 4/ res is expected to be a host memory range that could feasibly be
* treated as a "System RAM" range, i.e. not a device mmio range, but
* this is not enforced.
*/
void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
{
struct resource *res = &pgmap->res;
struct dev_pagemap *conflict_pgmap;
struct mhp_restrictions restrictions = {
/*
* We do not want any optional features only our own memmap
*/
.altmap = pgmap_altmap(pgmap),
};
pgprot_t pgprot = PAGE_KERNEL;
int error, nid, is_ram;
bool need_devmap_managed = true;
switch (pgmap->type) {
case MEMORY_DEVICE_PRIVATE:
if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
WARN(1, "Device private memory not supported\n");
return ERR_PTR(-EINVAL);
}
if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
WARN(1, "Missing migrate_to_ram method\n");
return ERR_PTR(-EINVAL);
}
break;
case MEMORY_DEVICE_FS_DAX:
if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
WARN(1, "File system DAX not supported\n");
return ERR_PTR(-EINVAL);
}
break;
case MEMORY_DEVICE_DEVDAX:
case MEMORY_DEVICE_PCI_P2PDMA:
need_devmap_managed = false;
break;
default:
WARN(1, "Invalid pgmap type %d\n", pgmap->type);
break;
}
if (!pgmap->ref) {
if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
return ERR_PTR(-EINVAL);
init_completion(&pgmap->done);
error = percpu_ref_init(&pgmap->internal_ref,
dev_pagemap_percpu_release, 0, GFP_KERNEL);
if (error)
return ERR_PTR(error);
pgmap->ref = &pgmap->internal_ref;
} else {
if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
WARN(1, "Missing reference count teardown definition\n");
return ERR_PTR(-EINVAL);
}
}
if (need_devmap_managed) {
error = devmap_managed_enable_get(dev, pgmap);
if (error)
return ERR_PTR(error);
}
conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL);
if (conflict_pgmap) {
dev_WARN(dev, "Conflicting mapping in same section\n");
put_dev_pagemap(conflict_pgmap);
error = -ENOMEM;
goto err_array;
}
conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL);
if (conflict_pgmap) {
dev_WARN(dev, "Conflicting mapping in same section\n");
put_dev_pagemap(conflict_pgmap);
error = -ENOMEM;
goto err_array;
}
is_ram = region_intersects(res->start, resource_size(res),
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
if (is_ram != REGION_DISJOINT) {
WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
is_ram == REGION_MIXED ? "mixed" : "ram", res);
error = -ENXIO;
goto err_array;
}
pgmap->dev = dev;
error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
PHYS_PFN(res->end
|