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
|
/*
* 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.
*
*/
#include <linux/bootmem.h>
#include <linux/dma-mapping.h>
#include <xen/swiotlb-xen.h>
#include <xen/page.h>
#include <xen/xen-ops.h>
/*
* 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.
*/
u64 start_dma_addr;
static dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
{
return phys_to_machine(XPADDR(paddr)).maddr;;
}
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;
}
void __init xen_swiotlb_init(int verbose)
{
unsigned long bytes;
int rc;
xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
/*
* Get IO TLB memory from any location.
*/
xen_io_tlb_start = alloc_bootmem(bytes);
if (!xen_io_tlb_start)
panic("Cannot allocate SWIOTLB buffer");
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);
if (rc)
goto error;
start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
return;
error:
panic("DMA(%d): Failed to exchange pages allocated for DMA with Xen! "\
"We either don't have the permission or you do not have enough"\
"free memory under 4GB!\n", rc);
}
void *
xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags)
{
void *ret;
int order = get_order(size);
u64 dma_mask = DMA_BIT_MASK(32);
unsigned long vstart;
/*
* 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;
if (hwdev && hwdev->coherent_dma_mask)
dma_mask = dma_alloc_coherent_mask(hwdev, flags);
if (ret) {
if (xen_create_contiguous_region(vstart, order,
fls64(dma_mask)) != 0) {
free_pages(vstart, order);
return NULL;
}
memset(ret, 0, size);
*dma_handle = virt_to_machine(ret).maddr;
}
return ret;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_alloc_coherent);
void
xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
dma_addr_t dev_addr)
{
int order = get_order(size);
if (dma_release_from_coherent(hwdev, order, vaddr))
return;
xen_destroy_contiguous_region((unsigned long)vaddr, order);
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)
{
phys_addr_t phys = page_to_phys(page) + offset;
dma_addr_t dev_addr = xen_phys_to_bus(phys);
void *map;
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);
if (!map)
return DMA_ERROR_CODE;
dev_addr = xen_virt_to_bus(map);
/*
* Ensure that the address returned is DMA'ble
*/
if (!dma_capable(dev, dev_addr, size))
panic("map_single: bounce buffer is not DMA'ble");
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
|