summaryrefslogtreecommitdiff
path: root/arch/arm64/mm/dma-mapping.c
blob: 1d17dbeafe7605f6c5efe63ae192b35e27046faf (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * SWIOTLB-based DMA API implementation
 *
 * Copyright (C) 2012 ARM Ltd.
 * Author: Catalin Marinas <catalin.marinas@arm.com>
 */

#include <linux/gfp.h>
#include <linux/acpi.h>
#include <linux/memblock.h>
#include <linux/cache.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/genalloc.h>
#include <linux/dma-direct.h>
#include <linux/dma-noncoherent.h>
#include <linux/dma-contiguous.h>
#include <linux/vmalloc.h>
#include <linux/swiotlb.h>
#include <linux/pci.h>

#include <asm/cacheflush.h>

pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
		unsigned long attrs)
{
	if (!dev_is_dma_coherent(dev) || (attrs & DMA_ATTR_WRITE_COMBINE))
		return pgprot_writecombine(prot);
	return prot;
}

void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
		size_t size, enum dma_data_direction dir)
{
	__dma_map_area(phys_to_virt(paddr), size, dir);
}

void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
		size_t size, enum dma_data_direction dir)
{
	__dma_unmap_area(phys_to_virt(paddr), size, dir);
}

void arch_dma_prep_coherent(struct page *page, size_t size)
{
	__dma_flush_area(page_address(page), size);
}

#ifdef CONFIG_IOMMU_DMA
static int __swiotlb_get_sgtable_page(struct sg_table *sgt,
				      struct page *page, size_t size)
{
	int ret = sg_alloc_table(sgt, 1, GFP_KERNEL);

	if (!ret)
		sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);

	return ret;
}

static int __swiotlb_mmap_pfn(struct vm_area_struct *vma,
			      unsigned long pfn, size_t size)
{
	int ret = -ENXIO;
	unsigned long nr_vma_pages = vma_pages(vma);
	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
	unsigned long off = vma->vm_pgoff;

	if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
		ret = remap_pfn_range(vma, vma->vm_start,
				      pfn + off,
				      vma->vm_end - vma->vm_start,
				      vma->vm_page_prot);
	}

	return ret;
}
#endif /* CONFIG_IOMMU_DMA */

static int __init arm64_dma_init(void)
{
	return dma_atomic_pool_init(GFP_DMA32, __pgprot(PROT_NORMAL_NC));
}
arch_initcall(arm64_dma_init);

#ifdef CONFIG_IOMMU_DMA
#include <linux/dma-iommu.h>
#include <linux/platform_device.h>
#include <linux/amba/bus.h>

/* Thankfully, all cache ops are by VA so we can ignore phys here */
static void flush_page(struct device *dev, const void *virt, phys_addr_t phys)
{
	__dma_flush_area(virt, PAGE_SIZE);
}

static void *__iommu_alloc_attrs(struct device *dev, size_t size,
				 dma_addr_t *handle, gfp_t gfp,
				 unsigned long attrs)
{
	bool coherent = dev_is_dma_coherent(dev);
	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
	size_t iosize = size;
	void *addr;

	if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n"))
		return NULL;

	size = PAGE_ALIGN(size);

	/*
	 * Some drivers rely on this, and we probably don't want the
	 * possibility of stale kernel data being read by devices anyway.
	 */
	gfp |= __GFP_ZERO;

	if (!gfpflags_allow_blocking(gfp)) {
		struct page *page;
		/*
		 * In atomic context we can't remap anything, so we'll only
		 * get the virtually contiguous buffer we need by way of a
		 * physically contiguous allocation.
		 */
		if (coherent) {
			page = alloc_pages(gfp, get_order(size));
			addr = page ? page_address(page) : NULL;
		} else {
			addr = dma_alloc_from_pool(size, &page, gfp);
		}
		if (!addr)
			return NULL;

		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
		if (*handle == DMA_MAPPING_ERROR) {
			if (coherent)
				__free_pages(page, get_order(size));
			else
				dma_free_from_pool(addr, size);
			addr = NULL;
		}
	} else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
		pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
		struct page *page;

		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
					get_order(size), gfp & __GFP_NOWARN);
		if (!page)
			return NULL;

		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
		if (*handle == DMA_MAPPING_ERROR) {
			dma_release_from_contiguous(dev, page,
						    size >> PAGE_SHIFT);
			return NULL;
		}
		addr = dma_common_contiguous_remap(page, size, VM_USERMAP,
						   prot,
						   __builtin_return_address(0));
		if (addr) {
			if (!coherent)
				__dma_flush_area(page_to_virt(page), iosize);
			memset(addr, 0, size);
		} else {
			iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs);
			dma_release_from_contiguous(dev, page,
						    size >> PAGE_SHIFT);
		}
	} else {
		pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
		struct page **pages;

		pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot,
					handle, flush_page);
		if (!pages)
			return NULL;

		addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
					      __builtin_return_address(0));
		if (!addr)
			iommu_dma_free(dev, pages, iosize, handle);
	}
	return addr;
}

static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
			       dma_addr_t handle, unsigned long attrs)
{
	size_t iosize = size;

	size = PAGE_ALIGN(size);
	/*
	 * @cpu_addr will be one of 4 things depending on how it was allocated:
	 * - A remapped array of pages for contiguous allocations.
	 * - A remapped array of pages from iommu_dma_alloc(), for all
	 *   non-atomic allocations.
	 * - A non-cacheable alias from the atomic pool, for atomic
	 *   allocations by non-coherent devices.
	 * - A normal lowmem address, for atomic allocations by
	 *   coherent devices.
	 * Hence how dodgy the below logic looks...
	 */
	if (dma_in_atomic_pool(cpu_addr, size)) {
		iommu_dma_unmap_page(dev, handle, iosize, 0, 0);
		dma_free_from_pool(cpu_addr, size);
	} else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
		struct page *page = vmalloc_to_page(cpu_addr);

		iommu_dma_unmap_page(dev, handle, iosize, 0, attrs);
		dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
	} else if (is_vmalloc_addr(cpu_addr)){
		struct vm_struct *area = find_vm_area(cpu_addr);

		if (WARN_ON(!area || !area->pages))
			return;
		iommu_dma_free(dev, area->pages, iosize, &handle);
		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
	} else {
		iommu_dma_unmap_page(dev, handle, iosize, 0, 0);
		__free_pages(virt_to_page(cpu_addr), get_order(size));
	}
}

static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
			      void *cpu_addr, dma_addr_t dma_addr, size_t size,
			      unsigned long attrs)
{
	struct vm_struct *area;
	int ret;

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

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

	if (!is_vmalloc_addr(cpu_addr)) {
		unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
		return __swiotlb_mmap_pfn(vma, pfn, size);
	}

	if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
		/*
		 * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
		 * hence in the vmalloc space.
		 */
		unsigned long pfn = vmalloc_to_pfn(cpu_addr);
		return __swiotlb_mmap_pfn(vma, pfn, size);
	}

	area = find_vm_area(cpu_addr);
	if (WARN_ON(!area || !area->pages))
		return -ENXIO;

	return iommu_dma_mmap(area->pages, size, vma);
}

static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
			       void *cpu_addr, dma_addr_t dma_addr,
			       size_t size, unsigned long attrs)
{
	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
	struct vm_struct *area = find_vm_area(cpu_addr);

	if (!is_vmalloc_addr(cpu_addr)) {
		struct page *page = virt_to_page(cpu_addr);
		return __swiotlb_get_sgtable_page(sgt, page, size);
	}

	if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
		/*
		 * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
		 * hence in the vmalloc space.
		 */
		struct page *page = vmalloc_to_page(cpu_addr);
		return __swiotlb_get_sgtable_page(sgt, page, size);
	}

	if (WARN_ON(!area || !area->pages))
		return -ENXIO;

	return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size,
					 GFP_KERNEL);
}

static void __iommu_sync_single_for_cpu(struct device *dev,
					dma_addr_t dev_addr, size_t size,
					enum dma_data_direction dir)
{
	phys_addr_t phys;

	if (dev_is_dma_coherent(dev))
		return;

	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr);
	arch_sync_dma_for_cpu(dev, phys, size, dir);
}

static void __iommu_sync_single_for_device(struct device *dev,
					   dma_addr_t dev_addr, size_t size,
					   enum dma_data_direction dir)
{
	phys_addr_t phys;

	if (dev_is_dma_coherent(dev))
		return;

	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr);
	arch_sync_dma_for_device(dev, phys, size, dir);
}

static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
				   unsigned long offset, size_t size,
				   enum dma_data_direction dir,
				   unsigned long attrs)
{
	bool coherent = dev_is_dma_coherent(dev);
	int prot = dma_info_to_prot(dir, coherent, attrs);
	dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);

	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
	    dev_addr != DMA_MAPPING_ERROR)
		__dma_map_area(page_address(page) + offset, size, dir);

	return dev_addr;
}

static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr,
			       size_t size, enum dma_data_direction dir,
			       unsigned long attrs)
{
	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
		__iommu_sync_single_for_cpu(dev, dev_addr, size, dir);

	iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs);
}

static void __iommu_sync_sg_for_cpu(struct device *dev,
				    struct scatterlist *sgl, int nelems,
				    enum dma_data_direction dir)
{
	struct scatterlist *sg;
	int i;

	if (dev_is_dma_coherent(dev))
		return;

	for_each_sg(sgl, sg, nelems, i)
		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
}

static void __iommu_sync_sg_for_device(struct device *dev,
				       struct scatterlist *sgl, int nelems,
				       enum dma_data_direction dir)
{
	struct scatterlist *sg;
	int i;

	if (dev_is_dma_coherent(dev))
		return;

	for_each_sg(sgl, sg, nelems, i)
		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
}

static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
				int nelems, enum dma_data_direction dir,
				unsigned long attrs)
{
	bool coherent = dev_is_dma_coherent(dev);

	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
		__iommu_sync_sg_for_device(dev, sgl, nelems, dir);

	return iommu_dma_map_sg(dev, sgl, nelems,
				dma_info_to_prot(dir, coherent, attrs));
}

static void __iommu_unmap_sg_attrs(struct device *dev,
				   struct scatterlist *sgl, int nelems,
				   enum dma_data_direction dir,
				   unsigned long attrs)
{
	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
		__iommu_sync_sg_for_cpu(dev, sgl, nelems, dir);

	iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs);
}

static const struct dma_map_ops iommu_dma_ops = {
	.alloc = __iommu_alloc_attrs,
	.free = __iommu_free_attrs,
	.mmap = __iommu_mmap_attrs,
	.get_sgtable = __iommu_get_sgtable,
	.map_page = __iommu_map_page,
	.unmap_page = __iommu_unmap_page,
	.map_sg = __iommu_map_sg_attrs,
	.unmap_sg = __iommu_unmap_sg_attrs,
	.sync_single_for_cpu = __iommu_sync_single_for_cpu,
	.sync_single_for_device = __iommu_sync_single_for_device,
	.sync_sg_for_cpu = __iommu_sync_sg_for_cpu,
	.sync_sg_for_device = __iommu_sync_sg_for_device,
	.map_resource = iommu_dma_map_resource,
	.unmap_resource = iommu_dma_unmap_resource,
};

static int __init __iommu_dma_init(void)
{
	return iommu_dma_init();
}
arch_initcall(__iommu_dma_init);

static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
				  const struct iommu_ops *ops)
{
	struct iommu_domain *domain;

	if (!ops)
		return;

	/*
	 * The IOMMU core code allocates the default DMA domain, which the
	 * underlying IOMMU driver needs to support via the dma-iommu layer.
	 */
	domain = iommu_get_domain_for_dev(dev);

	if (!domain)
		goto out_err;

	if (domain->type == IOMMU_DOMAIN_DMA) {
		if (iommu_dma_init_domain(domain, dma_base, size, dev))
			goto out_err;

		dev->dma_ops = &iommu_dma_ops;
	}

	return;

out_err:
	 pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
		 dev_name(dev));
}

void arch_teardown_dma_ops(struct device *dev)
{
	dev->dma_ops = NULL;
}

#else

static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
				  const struct iommu_ops *iommu)
{ }

#endif  /* CONFIG_IOMMU_DMA */

void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
			const struct iommu_ops *iommu, bool coherent)
{
	int cls = cache_line_size_of_cpu();

	WARN_TAINT(!coherent && cls > ARCH_DMA_MINALIGN,
		   TAINT_CPU_OUT_OF_SPEC,
		   "%s %s: ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)",
		   dev_driver_string(dev), dev_name(dev),
		   ARCH_DMA_MINALIGN, cls);

	dev->dma_coherent = coherent;
	__iommu_setup_dma_ops(dev, dma_base, size, iommu);

#ifdef CONFIG_XEN
	if (xen_initial_domain())
		dev->dma_ops = xen_dma_ops;
#endif
}