swiotlb-xen.c 16.5 KB
Newer Older
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
/*
 *  Copyright 2010
 *  by Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
 *
 * This code provides a IOMMU for Xen PV guests with PCI passthrough.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License v2.0 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.
 *
 * 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.
 *
 */

36
37
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt

38
39
#include <linux/bootmem.h>
#include <linux/dma-mapping.h>
40
#include <linux/export.h>
41
42
43
#include <xen/swiotlb-xen.h>
#include <xen/page.h>
#include <xen/xen-ops.h>
44
#include <xen/hvc-console.h>
45
46
47
48
49
50
51
52
53
54
55
56
/*
 * Used to do a quick range check in swiotlb_tbl_unmap_single and
 * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
 * API.
 */

static char *xen_io_tlb_start, *xen_io_tlb_end;
static unsigned long xen_io_tlb_nslabs;
/*
 * Quick lookup value of the bus address of the IOTLB.
 */

57
static u64 start_dma_addr;
58
59
60

static dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
{
61
	return phys_to_machine(XPADDR(paddr)).maddr;
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
}

static phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
{
	return machine_to_phys(XMADDR(baddr)).paddr;
}

static dma_addr_t xen_virt_to_bus(void *address)
{
	return xen_phys_to_bus(virt_to_phys(address));
}

static int check_pages_physically_contiguous(unsigned long pfn,
					     unsigned int offset,
					     size_t length)
{
	unsigned long next_mfn;
	int i;
	int nr_pages;

	next_mfn = pfn_to_mfn(pfn);
	nr_pages = (offset + length + PAGE_SIZE-1) >> PAGE_SHIFT;

	for (i = 1; i < nr_pages; i++) {
		if (pfn_to_mfn(++pfn) != ++next_mfn)
			return 0;
	}
	return 1;
}

static int range_straddles_page_boundary(phys_addr_t p, size_t size)
{
	unsigned long pfn = PFN_DOWN(p);
	unsigned int offset = p & ~PAGE_MASK;

	if (offset + size <= PAGE_SIZE)
		return 0;
	if (check_pages_physically_contiguous(pfn, offset, size))
		return 0;
	return 1;
}

static int is_xen_swiotlb_buffer(dma_addr_t dma_addr)
{
	unsigned long mfn = PFN_DOWN(dma_addr);
	unsigned long pfn = mfn_to_local_pfn(mfn);
	phys_addr_t paddr;

	/* 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)) {
		paddr = PFN_PHYS(pfn);
		return paddr >= virt_to_phys(xen_io_tlb_start) &&
		       paddr < virt_to_phys(xen_io_tlb_end);
	}
	return 0;
}

static int max_dma_bits = 32;

static int
xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
{
	int i, rc;
	int dma_bits;

	dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;

	i = 0;
	do {
		int slabs = min(nslabs - i, (unsigned long)IO_TLB_SEGSIZE);

		do {
			rc = xen_create_contiguous_region(
				(unsigned long)buf + (i << IO_TLB_SHIFT),
				get_order(slabs << IO_TLB_SHIFT),
				dma_bits);
		} while (rc && dma_bits++ < max_dma_bits);
		if (rc)
			return rc;

		i += slabs;
	} while (i < nslabs);
	return 0;
}
149
150
151
152
153
154
155
static unsigned long xen_set_nslabs(unsigned long nr_tbl)
{
	if (!nr_tbl) {
		xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
		xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
	} else
		xen_io_tlb_nslabs = nr_tbl;
156

157
158
	return xen_io_tlb_nslabs << IO_TLB_SHIFT;
}
159

160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
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 "";
}
181
int __ref xen_swiotlb_init(int verbose, bool early)
182
{
183
	unsigned long bytes, order;
184
	int rc = -ENOMEM;
185
	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
186
	unsigned int repeat = 3;
187

188
	xen_io_tlb_nslabs = swiotlb_nr_tbl();
189
retry:
190
	bytes = xen_set_nslabs(xen_io_tlb_nslabs);
191
	order = get_order(xen_io_tlb_nslabs << IO_TLB_SHIFT);
192
193
194
	/*
	 * Get IO TLB memory from any location.
	 */
195
196
197
198
199
200
201
202
203
204
205
206
	if (early)
		xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
	else {
#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) {
			xen_io_tlb_start = (void *)__get_free_pages(__GFP_NOWARN, order);
			if (xen_io_tlb_start)
				break;
			order--;
		}
		if (order != get_order(bytes)) {
207
208
			pr_warn("Warning: only able to allocate %ld MB for software IO TLB\n",
				(PAGE_SIZE << order) >> 20);
209
210
211
212
			xen_io_tlb_nslabs = SLABS_PER_PAGE << order;
			bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
		}
	}
213
	if (!xen_io_tlb_start) {
214
		m_ret = XEN_SWIOTLB_ENOMEM;
215
216
		goto error;
	}
217
218
219
220
221
222
223
	xen_io_tlb_end = xen_io_tlb_start + bytes;
	/*
	 * And replace that memory with pages under 4GB.
	 */
	rc = xen_swiotlb_fixup(xen_io_tlb_start,
			       bytes,
			       xen_io_tlb_nslabs);
224
	if (rc) {
225
226
227
228
229
230
		if (early)
			free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
		else {
			free_pages((unsigned long)xen_io_tlb_start, order);
			xen_io_tlb_start = NULL;
		}
231
		m_ret = XEN_SWIOTLB_EFIXUP;
232
		goto error;
233
	}
234
	start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
235
	if (early) {
236
237
238
		if (swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs,
			 verbose))
			panic("Cannot allocate SWIOTLB buffer");
239
240
		rc = 0;
	} else
241
242
		rc = swiotlb_late_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs);
	return rc;
243
error:
244
245
246
	if (repeat--) {
		xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */
					(xen_io_tlb_nslabs >> 1));
247
248
		pr_info("Lowering to %luMB\n",
			(xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20);
249
250
		goto retry;
	}
251
	pr_err("%s (rc:%d)\n", xen_swiotlb_error(m_ret), rc);
252
253
254
255
256
	if (early)
		panic("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
	else
		free_pages((unsigned long)xen_io_tlb_start, order);
	return rc;
257
258
259
}
void *
xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
260
261
			   dma_addr_t *dma_handle, gfp_t flags,
			   struct dma_attrs *attrs)
262
263
264
265
266
{
	void *ret;
	int order = get_order(size);
	u64 dma_mask = DMA_BIT_MASK(32);
	unsigned long vstart;
267
268
	phys_addr_t phys;
	dma_addr_t dev_addr;
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283

	/*
	* 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);

	if (dma_alloc_from_coherent(hwdev, size, dma_handle, &ret))
		return ret;

	vstart = __get_free_pages(flags, order);
	ret = (void *)vstart;

284
285
286
	if (!ret)
		return ret;

287
	if (hwdev && hwdev->coherent_dma_mask)
288
		dma_mask = dma_alloc_coherent_mask(hwdev, flags);
289

290
291
292
293
294
295
	phys = virt_to_phys(ret);
	dev_addr = xen_phys_to_bus(phys);
	if (((dev_addr + size - 1 <= dma_mask)) &&
	    !range_straddles_page_boundary(phys, size))
		*dma_handle = dev_addr;
	else {
296
297
298
299
300
301
302
		if (xen_create_contiguous_region(vstart, order,
						 fls64(dma_mask)) != 0) {
			free_pages(vstart, order);
			return NULL;
		}
		*dma_handle = virt_to_machine(ret).maddr;
	}
303
	memset(ret, 0, size);
304
305
306
307
308
309
	return ret;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_alloc_coherent);

void
xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
310
			  dma_addr_t dev_addr, struct dma_attrs *attrs)
311
312
{
	int order = get_order(size);
313
314
	phys_addr_t phys;
	u64 dma_mask = DMA_BIT_MASK(32);
315
316
317
318

	if (dma_release_from_coherent(hwdev, order, vaddr))
		return;

319
320
321
322
323
324
325
326
327
	if (hwdev && hwdev->coherent_dma_mask)
		dma_mask = hwdev->coherent_dma_mask;

	phys = virt_to_phys(vaddr);

	if (((dev_addr + size - 1 > dma_mask)) ||
	    range_straddles_page_boundary(phys, size))
		xen_destroy_contiguous_region((unsigned long)vaddr, order);

328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
	free_pages((unsigned long)vaddr, order);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);


/*
 * 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.
 */
dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
				unsigned long offset, size_t size,
				enum dma_data_direction dir,
				struct dma_attrs *attrs)
{
345
	phys_addr_t map, phys = page_to_phys(page) + offset;
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
	dma_addr_t dev_addr = xen_phys_to_bus(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) &&
	    !range_straddles_page_boundary(phys, size) && !swiotlb_force)
		return dev_addr;

	/*
	 * Oh well, have to allocate and map a bounce buffer.
	 */
	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir);
362
	if (map == SWIOTLB_MAP_ERROR)
363
364
		return DMA_ERROR_CODE;

365
	dev_addr = xen_phys_to_bus(map);
366
367
368
369

	/*
	 * Ensure that the address returned is DMA'ble
	 */
370
	if (!dma_capable(dev, dev_addr, size)) {
371
		swiotlb_tbl_unmap_single(dev, map, size, dir);
372
373
		dev_addr = 0;
	}
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
	return dev_addr;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);

/*
 * 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_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
			     size_t size, enum dma_data_direction dir)
{
	phys_addr_t paddr = xen_bus_to_phys(dev_addr);

	BUG_ON(dir == DMA_NONE);

	/* NOTE: We use dev_addr here, not paddr! */
	if (is_xen_swiotlb_buffer(dev_addr)) {
395
		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir);
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
		return;
	}

	if (dir != DMA_FROM_DEVICE)
		return;

	/*
	 * phys_to_virt doesn't work with hihgmem page but we could
	 * call dma_mark_clean() with hihgmem page here. However, we
	 * are fine since dma_mark_clean() is null on POWERPC. We can
	 * make dma_mark_clean() take a physical address if necessary.
	 */
	dma_mark_clean(phys_to_virt(paddr), size);
}

void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
			    size_t size, enum dma_data_direction dir,
			    struct dma_attrs *attrs)
{
	xen_unmap_single(hwdev, dev_addr, size, dir);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_page);

/*
 * Make physical memory consistent for a single streaming mode DMA translation
 * after a transfer.
 *
 * If you perform a xen_swiotlb_map_page() but wish to interrogate the buffer
 * using the cpu, yet do not wish to teardown the dma mapping, you must
 * call this function before doing so.  At the next point you give the dma
 * address back to the card, you must first perform a
 * xen_swiotlb_dma_sync_for_device, and then the device again owns the buffer
 */
static void
xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
			size_t size, enum dma_data_direction dir,
			enum dma_sync_target target)
{
	phys_addr_t paddr = xen_bus_to_phys(dev_addr);

	BUG_ON(dir == DMA_NONE);

	/* NOTE: We use dev_addr here, not paddr! */
	if (is_xen_swiotlb_buffer(dev_addr)) {
440
		swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
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
		return;
	}

	if (dir != DMA_FROM_DEVICE)
		return;

	dma_mark_clean(phys_to_virt(paddr), size);
}

void
xen_swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
				size_t size, enum dma_data_direction dir)
{
	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_cpu);

void
xen_swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
				   size_t size, enum dma_data_direction dir)
{
	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_device);

/*
 * Map a set of buffers described by scatterlist in streaming mode for DMA.
 * This is the scatter-gather version of the above xen_swiotlb_map_page
 * interface.  Here the scatter gather list elements are each tagged with the
 * appropriate dma address and length.  They are obtained via
 * sg_dma_{address,length}(SG).
 *
 * NOTE: An implementation may be able to use a smaller number of
 *       DMA address/length pairs than there are SG table elements.
 *       (for example via virtual mapping capabilities)
 *       The routine returns the number of addr/length pairs actually
 *       used, at most nents.
 *
 * Device ownership issues as mentioned above for xen_swiotlb_map_page are the
 * same here.
 */
int
xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
			 int nelems, enum dma_data_direction dir,
			 struct dma_attrs *attrs)
{
	struct scatterlist *sg;
	int i;

	BUG_ON(dir == DMA_NONE);

	for_each_sg(sgl, sg, nelems, i) {
		phys_addr_t paddr = sg_phys(sg);
		dma_addr_t dev_addr = xen_phys_to_bus(paddr);

		if (swiotlb_force ||
		    !dma_capable(hwdev, dev_addr, sg->length) ||
		    range_straddles_page_boundary(paddr, sg->length)) {
499
500
501
502
503
504
			phys_addr_t map = swiotlb_tbl_map_single(hwdev,
								 start_dma_addr,
								 sg_phys(sg),
								 sg->length,
								 dir);
			if (map == SWIOTLB_MAP_ERROR) {
505
506
507
508
509
510
511
				/* Don't panic here, we expect map_sg users
				   to do proper error handling. */
				xen_swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
							   attrs);
				sgl[0].dma_length = 0;
				return DMA_ERROR_CODE;
			}
512
			sg->dma_address = xen_phys_to_bus(map);
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
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
		} else
			sg->dma_address = dev_addr;
		sg->dma_length = sg->length;
	}
	return nelems;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg_attrs);

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

	BUG_ON(dir == DMA_NONE);

	for_each_sg(sgl, sg, nelems, i)
		xen_unmap_single(hwdev, sg->dma_address, sg->dma_length, dir);

}
EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg_attrs);

/*
 * Make physical memory consistent for a set of streaming mode DMA translations
 * after a transfer.
 *
 * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
 * and usage.
 */
static void
xen_swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
		    int nelems, enum dma_data_direction dir,
		    enum dma_sync_target target)
{
	struct scatterlist *sg;
	int i;

	for_each_sg(sgl, sg, nelems, i)
		xen_swiotlb_sync_single(hwdev, sg->dma_address,
					sg->dma_length, dir, target);
}

void
xen_swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
			    int nelems, enum dma_data_direction dir)
{
	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_cpu);

void
xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
			       int nelems, enum dma_data_direction dir)
{
	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_device);

int
xen_swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
{
	return !dma_addr;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mapping_error);

/*
 * 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.
 */
int
xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
{
	return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_dma_supported);