summaryrefslogtreecommitdiffstats
path: root/kernel/dma/direct.c
blob: fcdb23e8d2fccf1e6d27f64a23a66f7878224c04 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2018 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-direct.h>
#include <linux/scatterlist.h>
#include <linux/dma-contiguous.h>
#include <linux/dma-noncoherent.h>
#include <linux/pfn.h>
#include <linux/set_memory.h>
#include <linux/swiotlb.h>

/*
 * Most architectures use ZONE_DMA for the first 16 Megabytes, but
 * some use it for entirely different regions:
 */
#ifndef ARCH_ZONE_DMA_BITS
#define ARCH_ZONE_DMA_BITS 24
#endif

/*
 * For AMD SEV all DMA must be to unencrypted addresses.
 */
static inline bool force_dma_unencrypted(void)
{
	return sev_active();
}

static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
{
	if (!dev->dma_mask) {
		dev_err_once(dev, "DMA map on device without dma_mask\n");
	} else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) {
		dev_err_once(dev,
			"overflow %pad+%zu of DMA mask %llx bus mask %llx\n",
			&dma_addr, size, *dev->dma_mask, dev->bus_dma_mask);
	}
	WARN_ON_ONCE(1);
}

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

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

	if (dev->bus_dma_mask && dev->bus_dma_mask < max_dma)
		max_dma = dev->bus_dma_mask;

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

static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
		u64 *phys_mask)
{
	if (dev->bus_dma_mask && dev->bus_dma_mask < dma_mask)
		dma_mask = dev->bus_dma_mask;

	if (force_dma_unencrypted())
		*phys_mask = __dma_to_phys(dev, dma_mask);
	else
		*phys_mask = dma_to_phys(dev, dma_mask);

	/*
	 * 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.
	 */
	if (*phys_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
		return GFP_DMA;
	if (*phys_mask <= DMA_BIT_MASK(32))
		return GFP_DMA32;
	return 0;
}

static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
{
	return phys_to_dma_direct(dev, phys) + size - 1 <=
			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_mask);
}

struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
	int page_order = get_order(size);
	struct page *page = NULL;
	u64 phys_mask;

	if (attrs & DMA_ATTR_NO_WARN)
		gfp |= __GFP_NOWARN;

	/* we always manually zero the memory once we are done: */
	gfp &= ~__GFP_ZERO;
	gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
			&phys_mask);
again:
	/* CMA can be used only in the context which permits sleeping */
	if (gfpflags_allow_blocking(gfp)) {
		page = dma_alloc_from_contiguous(dev, count, page_order,
						 gfp & __GFP_NOWARN);
		if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
			dma_release_from_contiguous(dev, page, count);
			page = NULL;
		}
	}
	if (!page)
		page = alloc_pages_node(dev_to_node(dev), gfp, page_order);

	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
		__free_pages(page, page_order);
		page = NULL;

		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
		    phys_mask < 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;
}

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

	page = __dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
	if (!page)
		return NULL;

	if (PageHighMem(page)) {
		/*
		 * Depending on the cma= arguments and per-arch setup
		 * dma_alloc_from_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");
		__dma_direct_free_pages(dev, size, page);
		return NULL;
	}

	ret = page_address(page);
	if (force_dma_unencrypted()) {
		set_memory_decrypted((unsigned long)ret, 1 << get_order(size));
		*dma_handle = __phys_to_dma(dev, page_to_phys(page));
	} else {
		*dma_handle = phys_to_dma(dev, page_to_phys(page));
	}
	memset(ret, 0, size);
	return ret;
}

void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page)
{
	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;

	if (!dma_release_from_contiguous(dev, page, count))
		__free_pages(page, get_order(size));
}

void dma_direct_free_pages(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 (force_dma_unencrypted())
		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
	__dma_direct_free_pages(dev, size, virt_to_page(cpu_addr));
}

void *dma_direct_alloc(struct device *dev, size_t size,
		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
	if (!dev_is_dma_coherent(dev))
		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
	return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
}

void dma_direct_free(struct device *dev, size_t size,
		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
{
	if (!dev_is_dma_coherent(dev))
		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
	else
		dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
}

#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
    defined(CONFIG_SWIOTLB)
void dma_direct_sync_single_for_device(struct device *dev,
		dma_addr_t addr, size_t size, enum dma_data_direction dir)
{
	phys_addr_t paddr = dma_to_phys(dev, addr);

	if (unlikely(is_swiotlb_buffer(paddr)))
		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);

	if (!dev_is_dma_coherent(dev))
		arch_sync_dma_for_device(dev, paddr, size, dir);
}
EXPORT_SYMBOL(dma_direct_sync_single_for_device);

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

		if (!dev_is_dma_coherent(dev))
			arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
					dir);
	}
}
EXPORT_SYMBOL(dma_direct_sync_sg_for_device);
#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_single_for_cpu(struct device *dev,
		dma_addr_t addr, size_t size, enum dma_data_direction dir)
{
	phys_addr_t paddr = dma_to_phys(dev, addr);

	if (!dev_is_dma_coherent(dev)) {
		arch_sync_dma_for_cpu(dev, paddr, size, dir);
		arch_sync_dma_for_cpu_all(dev);
	}

	if (unlikely(is_swiotlb_buffer(paddr)))
		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
}
EXPORT_SYMBOL(dma_direct_sync_single_for_cpu);

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) {
		if (!dev_is_dma_coherent(dev))
			arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
	
		if (unlikely(is_swiotlb_buffer(sg_phys(sg))))
			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, dir,
					SYNC_FOR_CPU);
	}

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

void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
		size_t size, enum dma_data_direction dir, unsigned long attrs)
{
	phys_addr_t phys = dma_to_phys(dev, addr);

	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
		dma_direct_sync_single_for_cpu(dev, addr, size, dir);

	if (unlikely(is_swiotlb_buffer(phys)))
		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
}
EXPORT_SYMBOL(dma_direct_unmap_page);

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);
}
EXPORT_SYMBOL(dma_direct_unmap_sg);
#endif

static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr,
		size_t size)
{
	return swiotlb_force != SWIOTLB_FORCE &&
		(!dev || dma_capable(dev, dma_addr, size));
}

dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
		unsigned long offset, size_t size, enum dma_data_direction dir,
		unsigned long attrs)
{
	phys_addr_t phys = page_to_phys(page) + offset;
	dma_addr_t dma_addr = phys_to_dma(dev, phys);

	if (unlikely(!dma_direct_possible(dev, dma_addr, size)) &&
	    !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) {
		report_addr(dev, dma_addr, size);
		return DMA_MAPPING_ERROR;
	}

	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
		arch_sync_dma_for_device(dev, phys, size, dir);
	return dma_addr;
}
EXPORT_SYMBOL(dma_direct_map_page);

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;
}
EXPORT_SYMBOL(dma_direct_map_sg);

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_direct_possible(dev, dma_addr, size))) {
		report_addr(dev, dma_addr, size);
		return DMA_MAPPING_ERROR;
	}

	return dma_addr;
}
EXPORT_SYMBOL(dma_direct_map_resource);

/*
 * 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.
 */
int dma_direct_supported(struct device *dev, u64 mask)
{
	u64 min_mask;

	if (IS_ENABLED(CONFIG_ZONE_DMA))
		min_mask = DMA_BIT_MASK(ARCH_ZONE_DMA_BITS);
	else
		min_mask = DMA_BIT_MASK(32);

	min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT);

	/*
	 * This check needs to be against the actual bit mask value, so
	 * use __phys_to_dma() here so that the SME encryption mask isn't
	 * part of the check.
	 */
	return mask >= __phys_to_dma(dev, min_mask);
}

size_t dma_direct_max_mapping_size(struct device *dev)
{
	size_t size = SIZE_MAX;

	/* If SWIOTLB is active, use its maximum mapping size */
	if (is_swiotlb_active())
		size = swiotlb_max_mapping_size(dev);

	return size;
}