aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/dma/direct.c
blob: 06c111544f61d630c79d722111e8b0e573de8782 (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
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2018-2020 Christoph Hellwig.
 *
 * DMA operations that map physical memory directly without using an IOMMU.
 */
#include <linux/memblock.h> /* for max_pfn */
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/dma-map-ops.h>
#include <linux/scatterlist.h>
#include <linux/pfn.h>
#include <linux/vmalloc.h>
#include <linux/set_memory.h>
#include <linux/slab.h>
#include "direct.h"

/*
 * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use
 * it for entirely different regions. In that case the arch code needs to
 * override the variable below for dma-direct to work properly.
 */
unsigned int zone_dma_bits __ro_after_init = 24;

static inline dma_addr_t phys_to_dma_direct(struct device *dev,
		phys_addr_t phys)
{
	if (force_dma_unencrypted(dev))
		return phys_to_dma_unencrypted(dev, phys);
	return phys_to_dma(dev, phys);
}

static inline struct page *dma_direct_to_page(struct device *dev,
		dma_addr_t dma_addr)
{
	return pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_addr)));
}

u64 dma_direct_get_required_mask(struct device *dev)
{
	phys_addr_t phys = (phys_addr_t)(max_pfn - 1) << PAGE_SHIFT;
	u64 max_dma = phys_to_dma_direct(dev, phys);

	return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
}

static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
				  u64 *phys_limit)
{
	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);

	/*
	 * Optimistically try the zone that the physical address mask falls
	 * into first.  If that returns memory that isn't actually addressable
	 * we will fallback to the next lower zone and try again.
	 *
	 * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding
	 * zones.
	 */
	*phys_limit = dma_to_phys(dev, dma_limit);
	if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits))
		return GFP_DMA;
	if (*phys_limit <= DMA_BIT_MASK(32))
		return GFP_DMA32;
	return 0;
}

static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
{
	dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);

	if (dma_addr == DMA_MAPPING_ERROR)
		return false;
	return dma_addr + size - 1 <=
		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
}

static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
		gfp_t gfp)
{
	int node = dev_to_node(dev);
	struct page *page = NULL;
	u64 phys_limit;

	WARN_ON_ONCE(!PAGE_ALIGNED(size));

	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
					   &phys_limit);
	page = dma_alloc_contiguous(dev, size, gfp);
	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
		dma_free_contiguous(dev, page, size);
		page = NULL;
	}
again:
	if (!page)
		page = alloc_pages_node(node, gfp, get_order(size));
	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
		dma_free_contiguous(dev, page, size);
		page = NULL;

		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
		    phys_limit < DMA_BIT_MASK(64) &&
		    !(gfp & (GFP_DMA32 | GFP_DMA))) {
			gfp |= GFP_DMA32;
			goto again;
		}

		if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) {
			gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
			goto again;
		}
	}

	return page;
}

static void *dma_direct_alloc_from_pool(struct device *dev, size_t size,
		dma_addr_t *dma_handle, gfp_t gfp)
{
	struct page *page;
	u64 phys_mask;
	void *ret;

	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
					   &phys_mask);
	page = dma_alloc_from_pool(dev, size, &ret, gfp, dma_coherent_ok);
	if (!page)
		return NULL;
	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
	return ret;
}

void *dma_direct_alloc(struct device *dev, size_t size,
		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
	struct page *page;
	void *ret;
	int err;

	size = PAGE_ALIGN(size);
	if (attrs & DMA_ATTR_NO_WARN)
		gfp |= __GFP_NOWARN;

	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
	    !force_dma_unencrypted(dev)) {
		page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
		if (!page)
			return NULL;
		/* remove any dirty cache lines on the kernel alias */
		if (!PageHighMem(page))
			arch_dma_prep_coherent(page, size);
		*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
		/* return the page pointer as the opaque cookie */
		return page;
	}

	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
	    !dev_is_dma_coherent(dev))
		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);

	/*
	 * Remapping or decrypting memory may block. If either is required and
	 * we can't block, allocate the memory from the atomic pools.
	 */
	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
	    !gfpflags_allow_blocking(gfp) &&
	    (force_dma_unencrypted(dev) ||
	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev))))
		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);

	/* we always manually zero the memory once we are done */
	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
	if (!page)
		return NULL;

	if ((IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
	     !dev_is_dma_coherent(dev)) ||
	    (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) {
		/* remove any dirty cache lines on the kernel alias */
		arch_dma_prep_coherent(page, size);

		/* create a coherent mapping */
		ret = dma_common_contiguous_remap(page, size,
				dma_pgprot(dev, PAGE_KERNEL, attrs),
				__builtin_return_address(0));
		if (!ret)
			goto out_free_pages;
		if (force_dma_unencrypted(dev)) {
			err = set_memory_decrypted((unsigned long)ret,
						   1 << get_order(size));
			if (err)
				goto out_free_pages;
		}
		memset(ret, 0, size);
		goto done;
	}

	if (PageHighMem(page)) {
		/*
		 * Depending on the cma= arguments and per-arch setup
		 * dma_alloc_contiguous could return highmem pages.
		 * Without remapping there is no way to return them here,
		 * so log an error and fail.
		 */
		dev_info(dev, "Rejecting highmem page from CMA.\n");
		goto out_free_pages;
	}

	ret = page_address(page);
	if (force_dma_unencrypted(dev)) {
		err = set_memory_decrypted((unsigned long)ret,
					   1 << get_order(size));
		if (err)
			goto out_free_pages;
	}

	memset(ret, 0, size);

	if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
	    !dev_is_dma_coherent(dev)) {
		arch_dma_prep_coherent(page, size);
		ret = arch_dma_set_uncached(ret, size);
		if (IS_ERR(ret))
			goto out_encrypt_pages;
	}
done:
	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
	return ret;

out_encrypt_pages:
	if (force_dma_unencrypted(dev)) {
		err = set_memory_encrypted((unsigned long)page_address(page),
					   1 << get_order(size));
		/* If memory cannot be re-encrypted, it must be leaked */
		if (err)
			return NULL;
	}
out_free_pages:
	dma_free_contiguous(dev, page, size);
	return NULL;
}

void dma_direct_free(struct device *dev, size_t size,
		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
{
	unsigned int page_order = get_order(size);

	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
	    !force_dma_unencrypted(dev)) {
		/* cpu_addr is a struct page cookie, not a kernel address */
		dma_free_contiguous(dev, cpu_addr, size);
		return;
	}

	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
	    !dev_is_dma_coherent(dev)) {
		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
		return;
	}

	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
		return;

	if (force_dma_unencrypted(dev))
		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);

	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr))
		vunmap(cpu_addr);
	else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
		arch_dma_clear_uncached(cpu_addr, size);

	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
}

struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
{
	struct page *page;
	void *ret;

	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp))
		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);

	page = __dma_direct_alloc_pages(dev, size, gfp);
	if (!page)
		return NULL;
	if (PageHighMem(page)) {
		/*
		 * Depending on the cma= arguments and per-arch setup
		 * dma_alloc_contiguous could return highmem pages.
		 * Without remapping there is no way to return them here,
		 * so log an error and fail.
		 */
		dev_info(dev, "Rejecting highmem page from CMA.\n");
		goto out_free_pages;
	}

	ret = page_address(page);
	if (force_dma_unencrypted(dev)) {
		if (set_memory_decrypted((unsigned long)ret,
				1 << get_order(size)))
			goto out_free_pages;
	}
	memset(ret, 0, size);
	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
	return page;
out_free_pages:
	dma_free_contiguous(dev, page, size);
	return NULL;
}

void dma_direct_free_pages(struct device *dev, size_t size,
		struct page *page, dma_addr_t dma_addr,
		enum dma_data_direction dir)
{
	unsigned int page_order = get_order(size);
	void *vaddr = page_address(page);

	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
	    dma_free_from_pool(dev, vaddr, size))
		return;

	if (force_dma_unencrypted(dev))
		set_memory_encrypted((unsigned long)vaddr, 1 << page_order);

	dma_free_contiguous(dev, page, size);
}

#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
    defined(CONFIG_SWIOTLB)
void dma_direct_sync_sg_for_device(struct device *dev,
		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
{
	struct scatterlist *sg;
	int i;

	for_each_sg(sgl, sg, nents, i) {
		phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg));

		if (unlikely(is_swiotlb_buffer(paddr)))
			swiotlb_tbl_sync_single(dev, paddr, sg->length,
					dir, SYNC_FOR_DEVICE);

		if (!dev_is_dma_coherent(dev))
			arch_sync_dma_for_device(paddr, sg->length,
					dir);
	}
}
#endif

#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
    defined(CONFIG_SWIOTLB)
void dma_direct_sync_sg_for_cpu(struct device *dev,
		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
{
	struct scatterlist *sg;
	int i;

	for_each_sg(sgl, sg, nents, i) {
		phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg));

		if (!dev_is_dma_coherent(dev))
			arch_sync_dma_for_cpu(paddr, sg->length, dir);

		if (unlikely(is_swiotlb_buffer(paddr)))
			swiotlb_tbl_sync_single(dev, paddr, sg->length, dir,
					SYNC_FOR_CPU);

		if (dir == DMA_FROM_DEVICE)
			arch_dma_mark_clean(paddr, sg->length);
	}

	if (!dev_is_dma_coherent(dev))
		arch_sync_dma_for_cpu_all();
}

void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
		int nents, enum dma_data_direction dir, unsigned long attrs)
{
	struct scatterlist *sg;
	int i;

	for_each_sg(sgl, sg, nents, i)
		dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir,
			     attrs);
}
#endif

int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
		enum dma_data_direction dir, unsigned long attrs)
{
	int i;
	struct scatterlist *sg;

	for_each_sg(sgl, sg, nents, i) {
		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
				sg->offset, sg->length, dir, attrs);
		if (sg->dma_address == DMA_MAPPING_ERROR)
			goto out_unmap;
		sg_dma_len(sg) = sg->length;
	}

	return nents;

out_unmap:
	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
	return 0;
}

dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
		size_t size, enum dma_data_direction dir, unsigned long attrs)
{
	dma_addr_t dma_addr = paddr;

	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
		dev_err_once(dev,
			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
		WARN_ON_ONCE(1);
		return DMA_MAPPING_ERROR;
	}

	return dma_addr;
}

int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
		void *cpu_addr, dma_addr_t dma_addr, size_t size,
		unsigned long attrs)
{
	struct page *page = dma_direct_to_page(dev, dma_addr);
	int ret;

	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
	if (!ret)
		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
	return ret;
}

bool dma_direct_can_mmap(struct device *dev)
{
	return dev_is_dma_coherent(dev) ||
		IS_ENABLED(CONFIG_DMA_NONCOHERENT_MMAP);
}

int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
		void *cpu_addr, dma_addr_t dma_addr, size_t size,
		unsigned long attrs)
{
	unsigned long user_count = vma_pages(vma);
	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
	unsigned long pfn = PHYS_PFN(dma_to_phys(dev, dma_addr));
	int ret = -ENXIO;

	vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);

	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
		return ret;

	if (vma->vm_pgoff >= count || user_count > count - vma->vm_pgoff)
		return -ENXIO;
	return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff,
			user_count << PAGE_SHIFT, vma->vm_page_prot);
}

int dma_direct_supported(struct device *dev, u64 mask)
{
	u64 min_mask = (max_pfn - 1) << PAGE_SHIFT;

	/*
	 * Because 32-bit DMA masks are so common we expect every architecture
	 * to be able to satisfy them - either by not supporting more physical
	 * memory, or by providing a ZONE_DMA32.  If neither is the case, the
	 * architecture needs to use an IOMMU instead of the direct mapping.
	 */
	if (mask >= DMA_BIT_MASK(32))
		return 1;

	/*
	 * This check needs to be against the actual bit mask value, so use
	 * phys_to_dma_unencrypted() here so that the SME encryption mask isn't
	 * part of the check.
	 */
	if (IS_ENABLED(CONFIG_ZONE_DMA))
		min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits));
	return mask >= phys_to_dma_unencrypted(dev, min_mask);
}

size_t dma_direct_max_mapping_size(struct device *dev)
{
	/* If SWIOTLB is active, use its maximum mapping size */
	if (is_swiotlb_active() &&
	    (dma_addressing_limited(dev) || swiotlb_force == SWIOTLB_FORCE))
		return swiotlb_max_mapping_size(dev);
	return SIZE_MAX;
}

bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
{
	return !dev_is_dma_coherent(dev) ||
		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
}

/**
 * dma_direct_set_offset - Assign scalar offset for a single DMA range.
 * @dev:	device pointer; needed to "own" the alloced memory.
 * @cpu_start:  beginning of memory region covered by this offset.
 * @dma_start:  beginning of DMA/PCI region covered by this offset.
 * @size:	size of the region.
 *
 * This is for the simple case of a uniform offset which cannot
 * be discovered by "dma-ranges".
 *
 * It returns -ENOMEM if out of memory, -EINVAL if a map
 * already exists, 0 otherwise.
 *
 * Note: any call to this from a driver is a bug.  The mapping needs
 * to be described by the device tree or other firmware interfaces.
 */
int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
			 dma_addr_t dma_start, u64 size)
{
	struct bus_dma_region *map;
	u64 offset = (u64)cpu_start - (u64)dma_start;

	if (dev->dma_range_map) {
		dev_err(dev, "attempt to add DMA range to existing map\n");
		return -EINVAL;
	}

	if (!offset)
		return 0;

	map = kcalloc(2, sizeof(*map), GFP_KERNEL);
	if (!map)
		return -ENOMEM;
	map[0].cpu_start = cpu_start;
	map[0].dma_start = dma_start;
	map[0].offset = offset;
	map[0].size = size;
	dev->dma_range_map = map;
	return 0;
}
EXPORT_SYMBOL_GPL(dma_direct_set_offset);

Privacy Policy