summaryrefslogtreecommitdiffstats
path: root/kernel/memremap.c
blob: 4dd4274cabe252ecaa64e1c9a5a9d4f5478f1e24 (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
/*
 * Copyright(c) 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/radix-tree.h>
#include <linux/device.h>
#include <linux/types.h>
#include <linux/pfn_t.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/memory_hotplug.h>
#include <linux/swap.h>
#include <linux/swapops.h>

#ifndef ioremap_cache
/* temporary while we convert existing ioremap_cache users to memremap */
__weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size)
{
	return ioremap(offset, size);
}
#endif

#ifndef arch_memremap_wb
static void *arch_memremap_wb(resource_size_t offset, unsigned long size)
{
	return (__force void *)ioremap_cache(offset, size);
}
#endif

#ifndef arch_memremap_can_ram_remap
static bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size,
					unsigned long flags)
{
	return true;
}
#endif

static void *try_ram_remap(resource_size_t offset, size_t size,
			   unsigned long flags)
{
	unsigned long pfn = PHYS_PFN(offset);

	/* In the simple case just return the existing linear address */
	if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)) &&
	    arch_memremap_can_ram_remap(offset, size, flags))
		return __va(offset);

	return NULL; /* fallback to arch_memremap_wb */
}

/**
 * memremap() - remap an iomem_resource as cacheable memory
 * @offset: iomem resource start address
 * @size: size of remap
 * @flags: any of MEMREMAP_WB, MEMREMAP_WT, MEMREMAP_WC,
 *		  MEMREMAP_ENC, MEMREMAP_DEC
 *
 * memremap() is "ioremap" for cases where it is known that the resource
 * being mapped does not have i/o side effects and the __iomem
 * annotation is not applicable. In the case of multiple flags, the different
 * mapping types will be attempted in the order listed below until one of
 * them succeeds.
 *
 * MEMREMAP_WB - matches the default mapping for System RAM on
 * the architecture.  This is usually a read-allocate write-back cache.
 * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM
 * memremap() will bypass establishing a new mapping and instead return
 * a pointer into the direct map.
 *
 * MEMREMAP_WT - establish a mapping whereby writes either bypass the
 * cache or are written through to memory and never exist in a
 * cache-dirty state with respect to program visibility.  Attempts to
 * map System RAM with this mapping type will fail.
 *
 * MEMREMAP_WC - establish a writecombine mapping, whereby writes may
 * be coalesced together (e.g. in the CPU's write buffers), but is otherwise
 * uncached. Attempts to map System RAM with this mapping type will fail.
 */
void *memremap(resource_size_t offset, size_t size, unsigned long flags)
{
	int is_ram = region_intersects(offset, size,
				       IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
	void *addr = NULL;

	if (!flags)
		return NULL;

	if (is_ram == REGION_MIXED) {
		WARN_ONCE(1, "memremap attempted on mixed range %pa size: %#lx\n",
				&offset, (unsigned long) size);
		return NULL;
	}

	/* Try all mapping types requested until one returns non-NULL */
	if (flags & MEMREMAP_WB) {
		/*
		 * MEMREMAP_WB is special in that it can be satisifed
		 * from the direct map.  Some archs depend on the
		 * capability of memremap() to autodetect cases where
		 * the requested range is potentially in System RAM.
		 */
		if (is_ram == REGION_INTERSECTS)
			addr = try_ram_remap(offset, size, flags);
		if (!addr)
			addr = arch_memremap_wb(offset, size);
	}

	/*
	 * If we don't have a mapping yet and other request flags are
	 * present then we will be attempting to establish a new virtual
	 * address mapping.  Enforce that this mapping is not aliasing
	 * System RAM.
	 */
	if (!addr && is_ram == REGION_INTERSECTS && flags != MEMREMAP_WB) {
		WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n",
				&offset, (unsigned long) size);
		return NULL;
	}

	if (!addr && (flags & MEMREMAP_WT))
		addr = ioremap_wt(offset, size);

	if (!addr && (flags & MEMREMAP_WC))
		addr = ioremap_wc(offset, size);

	return addr;
}
EXPORT_SYMBOL(memremap);

void memunmap(void *addr)
{
	if (is_vmalloc_addr(addr))
		iounmap((void __iomem *) addr);
}
EXPORT_SYMBOL(memunmap);

static void devm_memremap_release(struct device *dev, void *res)
{
	memunmap(*(void **)res);
}

static int devm_memremap_match(struct device *dev, void *res, void *match_data)
{
	return *(void **)res == match_data;
}

void *devm_memremap(struct device *dev, resource_size_t offset,
		size_t size, unsigned long flags)
{
	void **ptr, *addr;

	ptr = devres_alloc_node(devm_memremap_release, sizeof(*ptr), GFP_KERNEL,
			dev_to_node(dev));
	if (!ptr)
		return ERR_PTR(-ENOMEM);

	addr = memremap(offset, size, flags);
	if (addr) {
		*ptr = addr;
		devres_add(dev, ptr);
	} else {
		devres_free(ptr);
		return ERR_PTR(-ENXIO);
	}

	return addr;
}
EXPORT_SYMBOL(devm_memremap);

void devm_memunmap(struct device *dev, void *addr)
{
	WARN_ON(devres_release(dev, devm_memremap_release,
				devm_memremap_match, addr));
}
EXPORT_SYMBOL(devm_memunmap);

#ifdef CONFIG_ZONE_DEVICE
static DEFINE_MUTEX(pgmap_lock);
static RADIX_TREE(pgmap_radix, GFP_KERNEL);
#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)

static unsigned long order_at(struct resource *res, unsigned long pgoff)
{
	unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff;
	unsigned long nr_pages, mask;

	nr_pages = PHYS_PFN(resource_size(res));
	if (nr_pages == pgoff)
		return ULONG_MAX;

	/*
	 * What is the largest aligned power-of-2 range available from
	 * this resource pgoff to the end of the resource range,
	 * considering the alignment of the current pgoff?
	 */
	mask = phys_pgoff | rounddown_pow_of_two(nr_pages - pgoff);
	if (!mask)
		return ULONG_MAX;

	return find_first_bit(&mask, BITS_PER_LONG);
}

#define foreach_order_pgoff(res, order, pgoff) \
	for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \
			pgoff += 1UL << order, order = order_at((res), pgoff))

#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
int device_private_entry_fault(struct vm_area_struct *vma,
		       unsigned long addr,
		       swp_entry_t entry,
		       unsigned int flags,
		       pmd_t *pmdp)
{
	struct page *page = device_private_entry_to_page(entry);

	/*
	 * The page_fault() callback must migrate page back to system memory
	 * so that CPU can access it. This might fail for various reasons
	 * (device issue, device was unsafely unplugged, ...). When such
	 * error conditions happen, the callback must return VM_FAULT_SIGBUS.
	 *
	 * Note that because memory cgroup charges are accounted to the device
	 * memory, this should never fail because of memory restrictions (but
	 * allocation of regular system page might still fail because we are
	 * out of memory).
	 *
	 * There is a more in-depth description of what that callback can and
	 * cannot do, in include/linux/memremap.h
	 */
	return page->pgmap->page_fault(vma, addr, page, flags, pmdp);
}
EXPORT_SYMBOL(device_private_entry_fault);
#endif /* CONFIG_DEVICE_PRIVATE */

static void pgmap_radix_release(struct resource *res, unsigned long end_pgoff)
{
	unsigned long pgoff, order;

	mutex_lock(&pgmap_lock);
	foreach_order_pgoff(res, order, pgoff) {
		if (pgoff >= end_pgoff)
			break;
		radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff);
	}
	mutex_unlock(&pgmap_lock);

	synchronize_rcu();
}

static unsigned long pfn_first(struct dev_pagemap *pgmap)
{
	const struct resource *res = &pgmap->res;
	struct vmem_altmap *altmap = &pgmap->altmap;
	unsigned long pfn;

	pfn = res->start >> PAGE_SHIFT;
	if (pgmap->altmap_valid)
		pfn += vmem_altmap_offset(altmap);
	return pfn;
}

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 devm_memremap_pages_release(void *data)
{
	struct dev_pagemap *pgmap = data;
	struct device *dev = pgmap->dev;
	struct resource *res = &pgmap->res;
	resource_size_t align_start, align_size;
	unsigned long pfn;

	for_each_device_pfn(pfn, pgmap)
		put_page(pfn_to_page(pfn));

	if (percpu_ref_tryget_live(pgmap->ref)) {
		dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
		percpu_ref_put(pgmap->ref);
	}

	/* pages are dead and unused, undo the arch mapping */
	align_start = res->start & ~(SECTION_SIZE - 1);
	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
		- align_start;

	mem_hotplug_begin();
	arch_remove_memory(align_start, align_size, pgmap->altmap_valid ?
			&pgmap->altmap : NULL);
	mem_hotplug_done();

	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
	pgmap_radix_release(res, -1);
	dev_WARN_ONCE(dev, pgmap->altmap.alloc,
		      "%s: failed to free all reserved pages\n", __func__);
}

/**
 * devm_memremap_pages - remap and provide memmap backing for the given resource
 * @dev: hosting device for @res
 * @pgmap: pointer to a struct dev_pgmap
 *
 * Notes:
 * 1/ At a minimum the res, ref 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 altmap_valid
 *    must be set to true
 *
 * 3/ pgmap.ref must be 'live' on entry and 'dead' before devm_memunmap_pages()
 *    time (or devm release event). The expected order of events is that ref has
 *    been through percpu_ref_kill() before devm_memremap_pages_release(). The
 *    wait for the completion of all references being dropped and
 *    percpu_ref_exit() must occur after devm_memremap_pages_release().
 *
 * 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)
{
	resource_size_t align_start, align_size, align_end;
	struct vmem_altmap *altmap = pgmap->altmap_valid ?
			&pgmap->altmap : NULL;
	struct resource *res = &pgmap->res;
	unsigned long pfn, pgoff, order;
	pgprot_t pgprot = PAGE_KERNEL;
	int error, nid, is_ram;

	align_start = res->start & ~(SECTION_SIZE - 1);
	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
		- align_start;
	is_ram = region_intersects(align_start, align_size,
		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);

	if (is_ram == REGION_MIXED) {
		WARN_ONCE(1, "%s attempted on mixed region %pr\n",
				__func__, res);
		return ERR_PTR(-ENXIO);
	}

	if (is_ram == REGION_INTERSECTS)
		return __va(res->start);

	if (!pgmap->ref)
		return ERR_PTR(-EINVAL);

	pgmap->dev = dev;

	mutex_lock(&pgmap_lock);
	error = 0;
	align_end = align_start + align_size - 1;

	foreach_order_pgoff(res, order, pgoff) {
		error = __radix_tree_insert(&pgmap_radix,
				PHYS_PFN(res->start) + pgoff, order, pgmap);
		if (error) {
			dev_err(dev, "%s: failed: %d\n", __func__, error);
			break;
		}
	}
	mutex_unlock(&pgmap_lock);
	if (error)
		goto err_radix;

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

	error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0,
			align_size);
	if (error)
		goto err_pfn_remap;

	mem_hotplug_begin();
	error = arch_add_memory(nid, align_start, align_size, altmap, false);
	if (!error)
		move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
					align_start >> PAGE_SHIFT,
					align_size >> PAGE_SHIFT, altmap);
	mem_hotplug_done();
	if (error)
		goto err_add_memory;

	for_each_device_pfn(pfn, pgmap) {
		struct page *page = pfn_to_page(pfn);

		/*
		 * ZONE_DEVICE pages union ->lru with a ->pgmap back
		 * pointer.  It is a bug if a ZONE_DEVICE page is ever
		 * freed or placed on a driver-private list.  Seed the
		 * storage with LIST_POISON* values.
		 */
		list_del(&page->lru);
		page->pgmap = pgmap;
		percpu_ref_get(pgmap->ref);
	}

	devm_add_action(dev, devm_memremap_pages_release, pgmap);

	return __va(res->start);

 err_add_memory:
	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
 err_pfn_remap:
 err_radix:
	pgmap_radix_release(res, pgoff);
	devres_free(pgmap);
	return ERR_PTR(error);
}
EXPORT_SYMBOL(devm_memremap_pages);

unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
{
	/* number of pfns from base where pfn_to_page() is valid */
	return altmap->reserve + altmap->free;
}

void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
{
	altmap->alloc -= nr_pfns;
}

/**
 * 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->res.start && phys <= pgmap->res.end)
			return pgmap;
		put_dev_pagemap(pgmap);
	}

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

	return pgmap;
}
#endif /* CONFIG_ZONE_DEVICE */

#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
void put_zone_device_private_or_public_page(struct page *page)
{
	int count = page_ref_dec_return(page);

	/*
	 * If refcount is 1 then page is freed and refcount is stable as nobody
	 * holds a reference on the page.
	 */
	if (count == 1) {
		/* Clear Active bit in case of parallel mark_page_accessed */
		__ClearPageActive(page);
		__ClearPageWaiters(page);

		page->mapping = NULL;
		mem_cgroup_uncharge(page);

		page->pgmap->page_free(page, page->pgmap->data);
	} else if (!count)
		__put_page(page);
}
EXPORT_SYMBOL(put_zone_device_private_or_public_page);
#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */