summaryrefslogtreecommitdiff
path: root/drivers/xen/swiotlb-xen.c
blob: f083194e26344bc37f4597036968db5e555a7865 (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
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  Copyright 2010
 *  by Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
 *
 * This code provides a IOMMU for Xen PV guests with PCI passthrough.
 *
 * PV guests under Xen are running in an non-contiguous memory architecture.
 *
 * When PCI pass-through is utilized, this necessitates an IOMMU for
 * translating bus (DMA) to virtual and vice-versa and also providing a
 * mechanism to have contiguous pages for device drivers operations (say DMA
 * operations).
 *
 * Specifically, under Xen the Linux idea of pages is an illusion. It
 * assumes that pages start at zero and go up to the available memory. To
 * help with that, the Linux Xen MMU provides a lookup mechanism to
 * translate the page frame numbers (PFN) to machine frame numbers (MFN)
 * and vice-versa. The MFN are the "real" frame numbers. Furthermore
 * memory is not contiguous. Xen hypervisor stitches memory for guests
 * from different pools, which means there is no guarantee that PFN==MFN
 * and PFN+1==MFN+1. Lastly with Xen 4.0, pages (in debug mode) are
 * allocated in descending order (high to low), meaning the guest might
 * never get any MFN's under the 4GB mark.
 */

#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt

#include <linux/memblock.h>
#include <linux/dma-direct.h>
#include <linux/dma-map-ops.h>
#include <linux/export.h>
#include <xen/swiotlb-xen.h>
#include <xen/page.h>
#include <xen/xen-ops.h>
#include <xen/hvc-console.h>

#include <asm/dma-mapping.h>
#include <asm/xen/page-coherent.h>

#include <trace/events/swiotlb.h>
#define MAX_DMA_BITS 32

/*
 * Quick lookup value of the bus address of the IOTLB.
 */

static inline phys_addr_t xen_phys_to_bus(struct device *dev, phys_addr_t paddr)
{
	unsigned long bfn = pfn_to_bfn(XEN_PFN_DOWN(paddr));
	phys_addr_t baddr = (phys_addr_t)bfn << XEN_PAGE_SHIFT;

	baddr |= paddr & ~XEN_PAGE_MASK;
	return baddr;
}

static inline dma_addr_t xen_phys_to_dma(struct device *dev, phys_addr_t paddr)
{
	return phys_to_dma(dev, xen_phys_to_bus(dev, paddr));
}

static inline phys_addr_t xen_bus_to_phys(struct device *dev,
					  phys_addr_t baddr)
{
	unsigned long xen_pfn = bfn_to_pfn(XEN_PFN_DOWN(baddr));
	phys_addr_t paddr = (xen_pfn << XEN_PAGE_SHIFT) |
			    (baddr & ~XEN_PAGE_MASK);

	return paddr;
}

static inline phys_addr_t xen_dma_to_phys(struct device *dev,
					  dma_addr_t dma_addr)
{
	return xen_bus_to_phys(dev, dma_to_phys(dev, dma_addr));
}

static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
{
	unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p);
	unsigned int i, nr_pages = XEN_PFN_UP(xen_offset_in_page(p) + size);

	next_bfn = pfn_to_bfn(xen_pfn);

	for (i = 1; i < nr_pages; i++)
		if (pfn_to_bfn(++xen_pfn) != ++next_bfn)
			return 1;

	return 0;
}

static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
{
	unsigned long bfn = XEN_PFN_DOWN(dma_to_phys(dev, dma_addr));
	unsigned long xen_pfn = bfn_to_local_pfn(bfn);
	phys_addr_t paddr = (phys_addr_t)xen_pfn << XEN_PAGE_SHIFT;

	/* If the address is outside our domain, it CAN
	 * have the same virtual address as another address
	 * in our domain. Therefore _only_ check address within our domain.
	 */
	if (pfn_valid(PFN_DOWN(paddr)))
		return is_swiotlb_buffer(dev, paddr);
	return 0;
}

static int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
{
	int rc;
	unsigned int order = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT);
	unsigned int i, dma_bits = order + PAGE_SHIFT;
	dma_addr_t dma_handle;
	phys_addr_t p = virt_to_phys(buf);

	BUILD_BUG_ON(IO_TLB_SEGSIZE & (IO_TLB_SEGSIZE - 1));
	BUG_ON(nslabs % IO_TLB_SEGSIZE);

	i = 0;
	do {
		do {
			rc = xen_create_contiguous_region(
				p + (i << IO_TLB_SHIFT), order,
				dma_bits, &dma_handle);
		} while (rc && dma_bits++ < MAX_DMA_BITS);
		if (rc)
			return rc;

		i += IO_TLB_SEGSIZE;
	} while (i < nslabs);
	return 0;
}

enum xen_swiotlb_err {
	XEN_SWIOTLB_UNKNOWN = 0,
	XEN_SWIOTLB_ENOMEM,
	XEN_SWIOTLB_EFIXUP
};

static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
{
	switch (err) {
	case XEN_SWIOTLB_ENOMEM:
		return "Cannot allocate Xen-SWIOTLB buffer\n";
	case XEN_SWIOTLB_EFIXUP:
		return "Failed to get contiguous memory for DMA from Xen!\n"\
		    "You either: don't have the permissions, do not have"\
		    " enough free memory under 4GB, or the hypervisor memory"\
		    " is too fragmented!";
	default:
		break;
	}
	return "";
}

int xen_swiotlb_init(void)
{
	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
	unsigned long bytes = swiotlb_size_or_default();
	unsigned long nslabs = bytes >> IO_TLB_SHIFT;
	unsigned int order, repeat = 3;
	int rc = -ENOMEM;
	char *start;

	if (io_tlb_default_mem.nslabs) {
		pr_warn("swiotlb buffer already initialized\n");
		return -EEXIST;
	}

retry:
	m_ret = XEN_SWIOTLB_ENOMEM;
	order = get_order(bytes);

	/*
	 * Get IO TLB memory from any location.
	 */
#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
		start = (void *)xen_get_swiotlb_free_pages(order);
		if (start)
			break;
		order--;
	}
	if (!start)
		goto exit;
	if (order != get_order(bytes)) {
		pr_warn("Warning: only able to allocate %ld MB for software IO TLB\n",
			(PAGE_SIZE << order) >> 20);
		nslabs = SLABS_PER_PAGE << order;
		bytes = nslabs << IO_TLB_SHIFT;
	}

	/*
	 * And replace that memory with pages under 4GB.
	 */
	rc = xen_swiotlb_fixup(start, nslabs);
	if (rc) {
		free_pages((unsigned long)start, order);
		m_ret = XEN_SWIOTLB_EFIXUP;
		goto error;
	}
	rc = swiotlb_late_init_with_tbl(start, nslabs);
	if (rc)
		return rc;
	swiotlb_set_max_segment(PAGE_SIZE);
	return 0;
error:
	if (nslabs > 1024 && repeat--) {
		/* Min is 2MB */
		nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE));
		bytes = nslabs << IO_TLB_SHIFT;
		pr_info("Lowering to %luMB\n", bytes >> 20);
		goto retry;
	}
exit:
	pr_err("%s (rc:%d)\n", xen_swiotlb_error(m_ret), rc);
	return rc;
}

#ifdef CONFIG_X86
void __init xen_swiotlb_init_early(void)
{
	unsigned long bytes = swiotlb_size_or_default();
	unsigned long nslabs = bytes >> IO_TLB_SHIFT;
	unsigned int repeat = 3;
	char *start;
	int rc;

retry:
	/*
	 * Get IO TLB memory from any location.
	 */
	start = memblock_alloc(PAGE_ALIGN(bytes),
			       IO_TLB_SEGSIZE << IO_TLB_SHIFT);
	if (!start)
		panic("%s: Failed to allocate %lu bytes\n",
		      __func__, PAGE_ALIGN(bytes));

	/*
	 * And replace that memory with pages under 4GB.
	 */
	rc = xen_swiotlb_fixup(start, nslabs);
	if (rc) {
		memblock_free(start, PAGE_ALIGN(bytes));
		if (nslabs > 1024 && repeat--) {
			/* Min is 2MB */
			nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE));
			bytes = nslabs << IO_TLB_SHIFT;
			pr_info("Lowering to %luMB\n", bytes >> 20);
			goto retry;
		}
		panic("%s (rc:%d)", xen_swiotlb_error(XEN_SWIOTLB_EFIXUP), rc);
	}

	if (swiotlb_init_with_tbl(start, nslabs, true))
		panic("Cannot allocate SWIOTLB buffer");
	swiotlb_set_max_segment(PAGE_SIZE);
}
#endif /* CONFIG_X86 */

static void *
xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
			   dma_addr_t *dma_handle, gfp_t flags,
			   unsigned long attrs)
{
	void *ret;
	int order = get_order(size);
	u64 dma_mask = DMA_BIT_MASK(32);
	phys_addr_t phys;
	dma_addr_t dev_addr;

	/*
	* Ignore region specifiers - the kernel's ideas of
	* pseudo-phys memory layout has nothing to do with the
	* machine physical layout.  We can't allocate highmem
	* because we can't return a pointer to it.
	*/
	flags &= ~(__GFP_DMA | __GFP_HIGHMEM);

	/* Convert the size to actually allocated. */
	size = 1UL << (order + XEN_PAGE_SHIFT);

	/* On ARM this function returns an ioremap'ped virtual address for
	 * which virt_to_phys doesn't return the corresponding physical
	 * address. In fact on ARM virt_to_phys only works for kernel direct
	 * mapped RAM memory. Also see comment below.
	 */
	ret = xen_alloc_coherent_pages(hwdev, size, dma_handle, flags, attrs);

	if (!ret)
		return ret;

	if (hwdev && hwdev->coherent_dma_mask)
		dma_mask = hwdev->coherent_dma_mask;

	/* At this point dma_handle is the dma address, next we are
	 * going to set it to the machine address.
	 * Do not use virt_to_phys(ret) because on ARM it doesn't correspond
	 * to *dma_handle. */
	phys = dma_to_phys(hwdev, *dma_handle);
	dev_addr = xen_phys_to_dma(hwdev, phys);
	if (((dev_addr + size - 1 <= dma_mask)) &&
	    !range_straddles_page_boundary(phys, size))
		*dma_handle = dev_addr;
	else {
		if (xen_create_contiguous_region(phys, order,
						 fls64(dma_mask), dma_handle) != 0) {
			xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs);
			return NULL;
		}
		*dma_handle = phys_to_dma(hwdev, *dma_handle);
		SetPageXenRemapped(virt_to_page(ret));
	}
	memset(ret, 0, size);
	return ret;
}

static void
xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
			  dma_addr_t dev_addr, unsigned long attrs)
{
	int order = get_order(size);
	phys_addr_t phys;
	u64 dma_mask = DMA_BIT_MASK(32);
	struct page *page;

	if (hwdev && hwdev->coherent_dma_mask)
		dma_mask = hwdev->coherent_dma_mask;

	/* do not use virt_to_phys because on ARM it doesn't return you the
	 * physical address */
	phys = xen_dma_to_phys(hwdev, dev_addr);

	/* Convert the size to actually allocated. */
	size = 1UL << (order + XEN_PAGE_SHIFT);

	if (is_vmalloc_addr(vaddr))
		page = vmalloc_to_page(vaddr);
	else
		page = virt_to_page(vaddr);

	if (!WARN_ON((dev_addr + size - 1 > dma_mask) ||
		     range_straddles_page_boundary(phys, size)) &&
	    TestClearPageXenRemapped(page))
		xen_destroy_contiguous_region(phys, order);

	xen_free_coherent_pages(hwdev, size, vaddr, phys_to_dma(hwdev, phys),
				attrs);
}

/*
 * Map a single buffer of the indicated size for DMA in streaming mode.  The
 * physical address to use is returned.
 *
 * Once the device is given the dma address, the device owns this memory until
 * either xen_swiotlb_unmap_page or xen_swiotlb_dma_sync_single is performed.
 */
static dma_addr_t xen_swiotlb_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 map, phys = page_to_phys(page) + offset;
	dma_addr_t dev_addr = xen_phys_to_dma(dev, phys);

	BUG_ON(dir == DMA_NONE);
	/*
	 * If the address happens to be in the device's DMA window,
	 * we can safely return the device addr and not worry about bounce
	 * buffering it.
	 */
	if (dma_capable(dev, dev_addr, size, true) &&
	    !range_straddles_page_boundary(phys, size) &&
		!xen_arch_need_swiotlb(dev, phys, dev_addr) &&
		!is_swiotlb_force_bounce(dev))
		goto done;

	/*
	 * Oh well, have to allocate and map a bounce buffer.
	 */
	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);

	map = swiotlb_tbl_map_single(dev, phys, size, size, dir, attrs);
	if (map == (phys_addr_t)DMA_MAPPING_ERROR)
		return DMA_MAPPING_ERROR;

	phys = map;
	dev_addr = xen_phys_to_dma(dev, map);

	/*
	 * Ensure that the address returned is DMA'ble
	 */
	if (unlikely(!dma_capable(dev, dev_addr, size, true))) {
		swiotlb_tbl_unmap_single(dev, map, size, dir,
				attrs | DMA_ATTR_SKIP_CPU_SYNC);
		return DMA_MAPPING_ERROR;
	}

done:
	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
		if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dev_addr))))
			arch_sync_dma_for_device(phys, size, dir);
		else
			xen_dma_sync_for_device(dev, dev_addr, size, dir);
	}
	return dev_addr;
}

/*
 * Unmap a single streaming mode DMA translation.  The dma_addr and size must
 * match what was provided for in a previous xen_swiotlb_map_page call.  All
 * other usages are undefined.
 *
 * After this call, reads by the cpu to the buffer are guaranteed to see
 * whatever the device wrote there.
 */
static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
		size_t size, enum dma_data_direction dir, unsigned long attrs)
{
	phys_addr_t paddr = xen_dma_to_phys(hwdev, dev_addr);

	BUG_ON(dir == DMA_NONE);

	if (!dev_is_dma_coherent(hwdev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
		if (pfn_valid(PFN_DOWN(dma_to_phys(hwdev, dev_addr))))
			arch_sync_dma_for_cpu(paddr, size, dir);
		else
			xen_dma_sync_for_cpu(hwdev, dev_addr, size, dir);
	}

	/* NOTE: We use dev_addr here, not paddr! */
	if (is_xen_swiotlb_buffer(hwdev, dev_addr))
		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
}

static void
xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr,
		size_t size, enum dma_data_direction dir)
{
	phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr);

	if (!dev_is_dma_coherent(dev)) {
		if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr))))
			arch_sync_dma_for_cpu(paddr, size, dir);
		else
			xen_dma_sync_for_cpu(dev, dma_addr, size, dir);
	}

	if (is_xen_swiotlb_buffer(dev, dma_addr))
		swiotlb_sync_single_for_cpu(dev, paddr, size, dir);
}

static void
xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr,
		size_t size, enum dma_data_direction dir)
{
	phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr);

	if (is_xen_swiotlb_buffer(dev, dma_addr))
		swiotlb_sync_single_for_device(dev, paddr, size, dir);

	if (!dev_is_dma_coherent(dev)) {
		if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr))))
			arch_sync_dma_for_device(paddr, size, dir);
		else
			xen_dma_sync_for_device(dev, dma_addr, size, dir);
	}
}

/*
 * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
 * concerning calls here are the same as for swiotlb_unmap_page() above.
 */
static void
xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
		enum dma_data_direction dir, unsigned long attrs)
{
	struct scatterlist *sg;
	int i;

	BUG_ON(dir == DMA_NONE);

	for_each_sg(sgl, sg, nelems, i)
		xen_swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg),
				dir, attrs);

}

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

	BUG_ON(dir == DMA_NONE);

	for_each_sg(sgl, sg, nelems, i) {
		sg->dma_address = xen_swiotlb_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 nelems;
out_unmap:
	xen_swiotlb_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
	sg_dma_len(sgl) = 0;
	return -EIO;
}

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

	for_each_sg(sgl, sg, nelems, i) {
		xen_swiotlb_sync_single_for_cpu(dev, sg->dma_address,
				sg->length, dir);
	}
}

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

	for_each_sg(sgl, sg, nelems, i) {
		xen_swiotlb_sync_single_for_device(dev, sg->dma_address,
				sg->length, dir);
	}
}

/*
 * Return whether the given device DMA address mask can be supported
 * properly.  For example, if your device can only drive the low 24-bits
 * during bus mastering, then you would pass 0x00ffffff as the mask to
 * this function.
 */
static int
xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
{
	return xen_phys_to_dma(hwdev, io_tlb_default_mem.end - 1) <= mask;
}

const struct dma_map_ops xen_swiotlb_dma_ops = {
	.alloc = xen_swiotlb_alloc_coherent,
	.free = xen_swiotlb_free_coherent,
	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
	.sync_sg_for_device = xen_swiotlb_sync_sg_for_device,
	.map_sg = xen_swiotlb_map_sg,
	.unmap_sg = xen_swiotlb_unmap_sg,
	.map_page = xen_swiotlb_map_page,
	.unmap_page = xen_swiotlb_unmap_page,
	.dma_supported = xen_swiotlb_dma_supported,
	.mmap = dma_common_mmap,
	.get_sgtable = dma_common_get_sgtable,
	.alloc_pages = dma_common_alloc_pages,
	.free_pages = dma_common_free_pages,
};