summaryrefslogtreecommitdiff
path: root/mm/memremap.c
blob: 9e9fb1972fff0af257d8b278012b44d7c7820bcd (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
// 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/memremap.h>
#include <linux/pfn_t.h>
#include <linux/swap.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/swapops.h>
#include <linux/types.h>
#include <linux/wait_bit.h>
#include <linux/xarray.h>
#include "internal.h"

static DEFINE_XARRAY(pgmap_array);

/*
 * The memremap() and memremap_pages() interfaces are alternately used
 * to map persistent memory namespaces. These interfaces place different
 * constraints on the alignment and size of the mapping (namespace).
 * memremap() can map individual PAGE_SIZE pages. memremap_pages() can
 * only map subsections (2MB), and at least one architecture (PowerPC)
 * the minimum mapping granularity of memremap_pages() is 16MB.
 *
 * The role of memremap_compat_align() is to communicate the minimum
 * arch supported alignment of a namespace such that it can freely
 * switch modes without violating the arch constraint. Namely, do not
 * allow a namespace to be PAGE_SIZE aligned since that namespace may be
 * reconfigured into a mode that requires SUBSECTION_SIZE alignment.
 */
#ifndef CONFIG_ARCH_HAS_MEMREMAP_COMPAT_ALIGN
unsigned long memremap_compat_align(void)
{
	return SUBSECTION_SIZE;
}
EXPORT_SYMBOL_GPL(memremap_compat_align);
#endif

#ifdef CONFIG_FS_DAX
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
EXPORT_SYMBOL(devmap_managed_key);

static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
	if (pgmap->type == MEMORY_DEVICE_FS_DAX)
		static_branch_dec(&devmap_managed_key);
}

static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
	if (pgmap->type == MEMORY_DEVICE_FS_DAX)
		static_branch_inc(&devmap_managed_key);
}
#else
static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
}
static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
}
#endif /* CONFIG_FS_DAX */

static void pgmap_array_delete(struct range *range)
{
	xa_store_range(&pgmap_array, PHYS_PFN(range->start), PHYS_PFN(range->end),
			NULL, GFP_KERNEL);
	synchronize_rcu();
}

static unsigned long pfn_first(struct dev_pagemap *pgmap, int range_id)
{
	struct range *range = &pgmap->ranges[range_id];
	unsigned long pfn = PHYS_PFN(range->start);

	if (range_id)
		return pfn;
	return pfn + vmem_altmap_offset(pgmap_altmap(pgmap));
}

bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
{
	int i;

	for (i = 0; i < pgmap->nr_range; i++) {
		struct range *range = &pgmap->ranges[i];

		if (pfn >= PHYS_PFN(range->start) &&
		    pfn <= PHYS_PFN(range->end))
			return pfn >= pfn_first(pgmap, i);
	}

	return false;
}

static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id)
{
	const struct range *range = &pgmap->ranges[range_id];

	return (range->start + range_len(range)) >> PAGE_SHIFT;
}

static unsigned long pfn_len(struct dev_pagemap *pgmap, unsigned long range_id)
{
	return (pfn_end(pgmap, range_id) -
		pfn_first(pgmap, range_id)) >> pgmap->vmemmap_shift;
}

static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
{
	struct range *range = &pgmap->ranges[range_id];
	struct page *first_page;

	/* make sure to access a memmap that was actually initialized */
	first_page = pfn_to_page(pfn_first(pgmap, range_id));

	/* pages are dead and unused, undo the arch mapping */
	mem_hotplug_begin();
	remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(range->start),
				   PHYS_PFN(range_len(range)));
	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
		__remove_pages(PHYS_PFN(range->start),
			       PHYS_PFN(range_len(range)), NULL);
	} else {
		arch_remove_memory(range->start, range_len(range),
				pgmap_altmap(pgmap));
		kasan_remove_zero_shadow(__va(range->start), range_len(range));
	}
	mem_hotplug_done();

	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true);
	pgmap_array_delete(range);
}

void memunmap_pages(struct dev_pagemap *pgmap)
{
	int i;

	percpu_ref_kill(&pgmap->ref);
	if (pgmap->type != MEMORY_DEVICE_PRIVATE &&
	    pgmap->type != MEMORY_DEVICE_COHERENT)
		for (i = 0; i < pgmap->nr_range; i++)
			percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i));

	wait_for_completion(&pgmap->done);

	for (i = 0; i < pgmap->nr_range; i++)
		pageunmap_range(pgmap, i);
	percpu_ref_exit(&pgmap->ref);

	WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
	devmap_managed_enable_put(pgmap);
}
EXPORT_SYMBOL_GPL(memunmap_pages);

static void devm_memremap_pages_release(void *data)
{
	memunmap_pages(data);
}

static void dev_pagemap_percpu_release(struct percpu_ref *ref)
{
	struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref);

	complete(&pgmap->done);
}

static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
		int range_id, int nid)
{
	const bool is_private = pgmap->type == MEMORY_DEVICE_PRIVATE;
	struct range *range = &pgmap->ranges[range_id];
	struct dev_pagemap *conflict_pgmap;
	int error, is_ram;

	if (WARN_ONCE(pgmap_altmap(pgmap) && range_id > 0,
				"altmap not supported for multiple ranges\n"))
		return -EINVAL;

	conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->start), NULL);
	if (conflict_pgmap) {
		WARN(1, "Conflicting mapping in same section\n");
		put_dev_pagemap(conflict_pgmap);
		return -ENOMEM;
	}

	conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->end), NULL);
	if (conflict_pgmap) {
		WARN(1, "Conflicting mapping in same section\n");
		put_dev_pagemap(conflict_pgmap);
		return -ENOMEM;
	}

	is_ram = region_intersects(range->start, range_len(range),
		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);

	if (is_ram != REGION_DISJOINT) {
		WARN_ONCE(1, "attempted on %s region %#llx-%#llx\n",
				is_ram == REGION_MIXED ? "mixed" : "ram",
				range->start, range->end);
		return -ENXIO;
	}

	error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(range->start),
				PHYS_PFN(range->end), pgmap, GFP_KERNEL));
	if (error)
		return error;

	if (nid < 0)
		nid = numa_mem_id();

	error = track_pfn_remap(NULL, &params->pgprot, PHYS_PFN(range->start), 0,
			range_len(range));
	if (error)
		goto err_pfn_remap;

	if (!mhp_range_allowed(range->start, range_len(range), !is_private)) {
		error = -EINVAL;
		goto err_kasan;
	}

	mem_hotplug_begin();

	/*
	 * For device private memory we call add_pages() as we only need to
	 * allocate and initialize struct page for the device memory. More-
	 * over the device memory is un-accessible thus we do not want to
	 * create a linear mapping for the memory like arch_add_memory()
	 * would do.
	 *
	 * For all other device memory types, which are accessible by
	 * the CPU, we do want the linear mapping and thus use
	 * arch_add_memory().
	 */
	if (is_private) {
		error = add_pages(nid, PHYS_PFN(range->start),
				PHYS_PFN(range_len(range)), params);
	} else {
		error = kasan_add_zero_shadow(__va(range->start), range_len(range));
		if (error) {
			mem_hotplug_done();
			goto err_kasan;
		}

		error = arch_add_memory(nid, range->start, range_len(range),
					params);
	}

	if (!error) {
		struct zone *zone;

		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
		move_pfn_range_to_zone(zone, PHYS_PFN(range->start),
				PHYS_PFN(range_len(range)), params->altmap,
				MIGRATE_MOVABLE);
	}

	mem_hotplug_done();
	if (error)
		goto err_add_memory;

	/*
	 * Initialization of the pages has been deferred until now in order
	 * to allow us to do the work while not holding the hotplug lock.
	 */
	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
				PHYS_PFN(range->start),
				PHYS_PFN(range_len(range)), pgmap);
	if (pgmap->type != MEMORY_DEVICE_PRIVATE &&
	    pgmap->type != MEMORY_DEVICE_COHERENT)
		percpu_ref_get_many(&pgmap->ref, pfn_len(pgmap, range_id));
	return 0;

err_add_memory:
	if (!is_private)
		kasan_remove_zero_shadow(__va(range->start), range_len(range));
err_kasan:
	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true);
err_pfn_remap:
	pgmap_array_delete(range);
	return error;
}


/*
 * Not device managed version of devm_memremap_pages, undone by
 * memunmap_pages().  Please use devm_memremap_pages if you have a struct
 * device available.
 */
void *memremap_pages(struct dev_pagemap *pgmap, int nid)
{
	struct mhp_params params = {
		.altmap = pgmap_altmap(pgmap),
		.pgmap = pgmap,
		.pgprot = PAGE_KERNEL,
	};
	const int nr_range = pgmap->nr_range;
	int error, i;

	if (WARN_ONCE(!nr_range, "nr_range must be specified\n"))
		return ERR_PTR(-EINVAL);

	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);
		}
		if (!pgmap->ops->page_free) {
			WARN(1, "Missing page_free method\n");
			return ERR_PTR(-EINVAL);
		}
		if (!pgmap->owner) {
			WARN(1, "Missing owner\n");
			return ERR_PTR(-EINVAL);
		}
		break;
	case MEMORY_DEVICE_COHERENT:
		if (!pgmap->ops->page_free) {
			WARN(1, "Missing page_free method\n");
			return ERR_PTR(-EINVAL);
		}
		if (!pgmap->owner) {
			WARN(1, "Missing owner\n");
			return ERR_PTR(-EINVAL);
		}
		break;
	case MEMORY_DEVICE_FS_DAX:
		if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
			WARN(1, "File system DAX not supported\n");
			return ERR_PTR(-EINVAL);
		}
		params.pgprot = pgprot_decrypted(params.pgprot);
		break;
	case MEMORY_DEVICE_GENERIC:
		break;
	case MEMORY_DEVICE_PCI_P2PDMA:
		params.pgprot = pgprot_noncached(params.pgprot);
		break;
	default:
		WARN(1, "Invalid pgmap type %d\n", pgmap->type);
		break;
	}

	init_completion(&pgmap->done);
	error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0,
				GFP_KERNEL);
	if (error)
		return ERR_PTR(error);

	devmap_managed_enable_get(pgmap);

	/*
	 * Clear the pgmap nr_range as it will be incremented for each
	 * successfully processed range. This communicates how many
	 * regions to unwind in the abort case.
	 */
	pgmap->nr_range = 0;
	error = 0;
	for (i = 0; i < nr_range; i++) {
		error = pagemap_range(pgmap, &params, i, nid);
		if (error)
			break;
		pgmap->nr_range++;
	}

	if (i < nr_range) {
		memunmap_pages(pgmap);
		pgmap->nr_range = nr_range;
		return ERR_PTR(error);
	}

	return __va(pgmap->ranges[0].start);
}
EXPORT_SYMBOL_GPL(memremap_pages);

/**
 * 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 range 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/ range 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)
{
	int error;
	void *ret;

	ret = memremap_pages(pgmap, dev_to_node(dev));
	if (IS_ERR(ret))
		return ret;

	error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
			pgmap);
	if (error)
		return ERR_PTR(error);
	return ret;
}
EXPORT_SYMBOL_GPL(devm_memremap_pages);

void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap)
{
	devm_release_action(dev, devm_memremap_pages_release, pgmap);
}
EXPORT_SYMBOL_GPL(devm_memunmap_pages);

/**
 * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
 * @pfn: page frame number to lookup page_map
 * @pgmap: optional known pgmap that already has a reference
 *
 * If @pgmap is non-NULL and covers @pfn it will be returned as-is.  If @pgmap
 * is non-NULL but does not cover @pfn the reference to it will be released.
 */
struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
		struct dev_pagemap *pgmap)
{
	resource_size_t phys = PFN_PHYS(pfn);

	/*
	 * In the cached case we're already holding a live reference.
	 */
	if (pgmap) {
		if (phys >= pgmap->range.start && phys <= pgmap->range.end)
			return pgmap;
		put_dev_pagemap(pgmap);
	}

	/* fall back to slow path lookup */
	rcu_read_lock();
	pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
	if (pgmap && !percpu_ref_tryget_live_rcu(&pgmap->ref))
		pgmap = NULL;
	rcu_read_unlock();

	return pgmap;
}
EXPORT_SYMBOL_GPL(get_dev_pagemap);

void free_zone_device_page(struct page *page)
{
	if (WARN_ON_ONCE(!page->pgmap->ops || !page->pgmap->ops->page_free))
		return;

	mem_cgroup_uncharge(page_folio(page));

	/*
	 * Note: we don't expect anonymous compound pages yet. Once supported
	 * and we could PTE-map them similar to THP, we'd have to clear
	 * PG_anon_exclusive on all tail pages.
	 */
	VM_BUG_ON_PAGE(PageAnon(page) && PageCompound(page), page);
	if (PageAnon(page))
		__ClearPageAnonExclusive(page);

	/*
	 * When a device managed page is freed, the folio->mapping field
	 * may still contain a (stale) mapping value. For example, the
	 * lower bits of folio->mapping may still identify the folio as an
	 * anonymous folio. Ultimately, this entire field is just stale
	 * and wrong, and it will cause errors if not cleared.
	 *
	 * For other types of ZONE_DEVICE pages, migration is either
	 * handled differently or not done at all, so there is no need
	 * to clear page->mapping.
	 */
	page->mapping = NULL;
	page->pgmap->ops->page_free(page);

	if (page->pgmap->type != MEMORY_DEVICE_PRIVATE &&
	    page->pgmap->type != MEMORY_DEVICE_COHERENT)
		/*
		 * Reset the page count to 1 to prepare for handing out the page
		 * again.
		 */
		set_page_count(page, 1);
	else
		put_dev_pagemap(page->pgmap);
}

void zone_device_page_init(struct page *page)
{
	/*
	 * Drivers shouldn't be allocating pages after calling
	 * memunmap_pages().
	 */
	WARN_ON_ONCE(!percpu_ref_tryget_live(&page->pgmap->ref));
	set_page_count(page, 1);
	lock_page(page);
}
EXPORT_SYMBOL_GPL(zone_device_page_init);

#ifdef CONFIG_FS_DAX
bool __put_devmap_managed_page_refs(struct page *page, int refs)
{
	if (page->pgmap->type != MEMORY_DEVICE_FS_DAX)
		return false;

	/*
	 * fsdax page refcounts are 1-based, rather than 0-based: if
	 * refcount is 1, then the page is free and the refcount is
	 * stable because nobody holds a reference on the page.
	 */
	if (page_ref_sub_return(page, refs) == 1)
		wake_up_var(&page->_refcount);
	return true;
}
EXPORT_SYMBOL(__put_devmap_managed_page_refs);
#endif /* CONFIG_FS_DAX */