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
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
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
|
/*
* 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.
*
*/
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
#include <linux/bootmem.h>
#include <linux/dma-mapping.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>
/*
* 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.
*/
#ifndef CONFIG_X86
static unsigned long dma_alloc_coherent_mask(struct device *dev,
gfp_t gfp)
{
unsigned long dma_mask = 0;
dma_mask = dev->coherent_dma_mask;
if (!dma_mask)
dma_mask = (gfp & GFP_DMA) ? DMA_BIT_MASK(24) : DMA_BIT_MASK(32);
return dma_mask;
}
#endif
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.
*/
static u64 start_dma_addr;
static inline dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
{
return phys_to_machine(XPADDR(paddr)).maddr;
}
static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
{
return machine_to_phys(XMADDR(baddr)).paddr;
}
static inline 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 inline 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_addr_t dma_handle;
phys_addr_t p = virt_to_phys(buf);
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(
p + (i << IO_TLB_SHIFT),
get_order(slabs << IO_TLB_SHIFT),
dma_bits, &dma_handle);
} while (rc && dma_bits++ < max_dma_bits);
if (rc)
return rc;
i += slabs;
} while (i < nslabs);
return 0;
}
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;
return xen_io_tlb_nslabs << IO_TLB_SHIFT;
}
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 __ref xen_swiotlb_init(int verbose, bool early)
{
unsigned long bytes, order;
int rc = -ENOMEM;
enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
unsigned int repeat = 3;
xen_io_tlb_nslabs = swiotlb_nr_tbl();
retry:
bytes = xen_set_nslabs(xen_io_tlb_nslabs);
order = get_order(xen_io_tlb_nslabs << IO_TLB_SHIFT);
/*
* Get IO TLB memory from any location.
*/
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)) {
pr_warn("Warning: only able to allocate %ld MB for software IO TLB\n",
(PAGE_SIZE << order) >> 20);
xen_io_tlb_nslabs = SLABS_PER_PAGE << order;
bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
}
}
if (!xen_io_tlb_start) {
m_ret = XEN_SWIOTLB_ENOMEM;
goto error;
}
xen_io_tlb_end = xen_io_tlb_start
|