summaryrefslogtreecommitdiff
path: root/drivers/vfio/vfio_iommu_spapr_tce.c
blob: a9e2d13c03c0f1d2660e9c66b2374c7d24006c9a (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
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
/*
 * VFIO: IOMMU DMA mapping support for TCE on POWER
 *
 * Copyright (C) 2013 IBM Corp.  All rights reserved.
 *     Author: Alexey Kardashevskiy <aik@ozlabs.ru>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * Derived from original vfio_iommu_type1.c:
 * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
 *     Author: Alex Williamson <alex.williamson@redhat.com>
 */

#include <linux/module.h>
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/err.h>
#include <linux/vfio.h>
#include <asm/iommu.h>
#include <asm/tce.h>

#define DRIVER_VERSION  "0.1"
#define DRIVER_AUTHOR   "aik@ozlabs.ru"
#define DRIVER_DESC     "VFIO IOMMU SPAPR TCE"

static void tce_iommu_detach_group(void *iommu_data,
		struct iommu_group *iommu_group);

static long try_increment_locked_vm(long npages)
{
	long ret = 0, locked, lock_limit;

	if (!current || !current->mm)
		return -ESRCH; /* process exited */

	if (!npages)
		return 0;

	down_write(&current->mm->mmap_sem);
	locked = current->mm->locked_vm + npages;
	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
		ret = -ENOMEM;
	else
		current->mm->locked_vm += npages;

	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
			npages << PAGE_SHIFT,
			current->mm->locked_vm << PAGE_SHIFT,
			rlimit(RLIMIT_MEMLOCK),
			ret ? " - exceeded" : "");

	up_write(&current->mm->mmap_sem);

	return ret;
}

static void decrement_locked_vm(long npages)
{
	if (!current || !current->mm || !npages)
		return; /* process exited */

	down_write(&current->mm->mmap_sem);
	if (WARN_ON_ONCE(npages > current->mm->locked_vm))
		npages = current->mm->locked_vm;
	current->mm->locked_vm -= npages;
	pr_debug("[%d] RLIMIT_MEMLOCK -%ld %ld/%ld\n", current->pid,
			npages << PAGE_SHIFT,
			current->mm->locked_vm << PAGE_SHIFT,
			rlimit(RLIMIT_MEMLOCK));
	up_write(&current->mm->mmap_sem);
}

/*
 * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
 *
 * This code handles mapping and unmapping of user data buffers
 * into DMA'ble space using the IOMMU
 */

/*
 * The container descriptor supports only a single group per container.
 * Required by the API as the container is not supplied with the IOMMU group
 * at the moment of initialization.
 */
struct tce_container {
	struct mutex lock;
	struct iommu_group *grp;
	bool enabled;
	unsigned long locked_pages;
};

static bool tce_page_is_contained(struct page *page, unsigned page_shift)
{
	/*
	 * Check that the TCE table granularity is not bigger than the size of
	 * a page we just found. Otherwise the hardware can get access to
	 * a bigger memory chunk that it should.
	 */
	return (PAGE_SHIFT + compound_order(compound_head(page))) >= page_shift;
}

static long tce_iommu_find_table(struct tce_container *container,
		phys_addr_t ioba, struct iommu_table **ptbl)
{
	long i;
	struct iommu_table_group *table_group;

	table_group = iommu_group_get_iommudata(container->grp);
	if (!table_group)
		return -1;

	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
		struct iommu_table *tbl = table_group->tables[i];

		if (tbl) {
			unsigned long entry = ioba >> tbl->it_page_shift;
			unsigned long start = tbl->it_offset;
			unsigned long end = start + tbl->it_size;

			if ((start <= entry) && (entry < end)) {
				*ptbl = tbl;
				return i;
			}
		}
	}

	return -1;
}

static int tce_iommu_enable(struct tce_container *container)
{
	int ret = 0;
	unsigned long locked;
	struct iommu_table *tbl;
	struct iommu_table_group *table_group;

	if (!container->grp)
		return -ENXIO;

	if (!current->mm)
		return -ESRCH; /* process exited */

	if (container->enabled)
		return -EBUSY;

	/*
	 * When userspace pages are mapped into the IOMMU, they are effectively
	 * locked memory, so, theoretically, we need to update the accounting
	 * of locked pages on each map and unmap.  For powerpc, the map unmap
	 * paths can be very hot, though, and the accounting would kill
	 * performance, especially since it would be difficult to impossible
	 * to handle the accounting in real mode only.
	 *
	 * To address that, rather than precisely accounting every page, we
	 * instead account for a worst case on locked memory when the iommu is
	 * enabled and disabled.  The worst case upper bound on locked memory
	 * is the size of the whole iommu window, which is usually relatively
	 * small (compared to total memory sizes) on POWER hardware.
	 *
	 * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits,
	 * that would effectively kill the guest at random points, much better
	 * enforcing the limit based on the max that the guest can map.
	 *
	 * Unfortunately at the moment it counts whole tables, no matter how
	 * much memory the guest has. I.e. for 4GB guest and 4 IOMMU groups
	 * each with 2GB DMA window, 8GB will be counted here. The reason for
	 * this is that we cannot tell here the amount of RAM used by the guest
	 * as this information is only available from KVM and VFIO is
	 * KVM agnostic.
	 */
	table_group = iommu_group_get_iommudata(container->grp);
	if (!table_group)
		return -ENODEV;

	tbl = table_group->tables[0];
	locked = (tbl->it_size << tbl->it_page_shift) >> PAGE_SHIFT;
	ret = try_increment_locked_vm(locked);
	if (ret)
		return ret;

	container->locked_pages = locked;

	container->enabled = true;

	return ret;
}

static void tce_iommu_disable(struct tce_container *container)
{
	if (!container->enabled)
		return;

	container->enabled = false;

	if (!current->mm)
		return;

	decrement_locked_vm(container->locked_pages);
}

static void *tce_iommu_open(unsigned long arg)
{
	struct tce_container *container;

	if (arg != VFIO_SPAPR_TCE_IOMMU) {
		pr_err("tce_vfio: Wrong IOMMU type\n");
		return ERR_PTR(-EINVAL);
	}

	container = kzalloc(sizeof(*container), GFP_KERNEL);
	if (!container)
		return ERR_PTR(-ENOMEM);

	mutex_init(&container->lock);

	return container;
}

static void tce_iommu_release(void *iommu_data)
{
	struct tce_container *container = iommu_data;

	WARN_ON(container->grp);

	if (container->grp)
		tce_iommu_detach_group(iommu_data, container->grp);

	tce_iommu_disable(container);
	mutex_destroy(&container->lock);

	kfree(container);
}

static void tce_iommu_unuse_page(struct tce_container *container,
		unsigned long hpa)
{
	struct page *page;

	page = pfn_to_page(hpa >> PAGE_SHIFT);
	put_page(page);
}

static int tce_iommu_clear(struct tce_container *container,
		struct iommu_table *tbl,
		unsigned long entry, unsigned long pages)
{
	unsigned long oldhpa;
	long ret;
	enum dma_data_direction direction;

	for ( ; pages; --pages, ++entry) {
		direction = DMA_NONE;
		oldhpa = 0;
		ret = iommu_tce_xchg(tbl, entry, &oldhpa, &direction);
		if (ret)
			continue;

		if (direction == DMA_NONE)
			continue;

		tce_iommu_unuse_page(container, oldhpa);
	}

	return 0;
}

static int tce_iommu_use_page(unsigned long tce, unsigned long *hpa)
{
	struct page *page = NULL;
	enum dma_data_direction direction = iommu_tce_direction(tce);

	if (get_user_pages_fast(tce & PAGE_MASK, 1,
			direction != DMA_TO_DEVICE, &page) != 1)
		return -EFAULT;

	*hpa = __pa((unsigned long) page_address(page));

	return 0;
}

static long tce_iommu_build(struct tce_container *container,
		struct iommu_table *tbl,
		unsigned long entry, unsigned long tce, unsigned long pages,
		enum dma_data_direction direction)
{
	long i, ret = 0;
	struct page *page;
	unsigned long hpa;
	enum dma_data_direction dirtmp;

	for (i = 0; i < pages; ++i) {
		unsigned long offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;

		ret = tce_iommu_use_page(tce, &hpa);
		if (ret)
			break;

		page = pfn_to_page(hpa >> PAGE_SHIFT);
		if (!tce_page_is_contained(page, tbl->it_page_shift)) {
			ret = -EPERM;
			break;
		}

		hpa |= offset;
		dirtmp = direction;
		ret = iommu_tce_xchg(tbl, entry + i, &hpa, &dirtmp);
		if (ret) {
			tce_iommu_unuse_page(container, hpa);
			pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n",
					__func__, entry << tbl->it_page_shift,
					tce, ret);
			break;
		}

		if (dirtmp != DMA_NONE)
			tce_iommu_unuse_page(container, hpa);

		tce += IOMMU_PAGE_SIZE(tbl);
	}

	if (ret)
		tce_iommu_clear(container, tbl, entry, i);

	return ret;
}

static long tce_iommu_ioctl(void *iommu_data,
				 unsigned int cmd, unsigned long arg)
{
	struct tce_container *container = iommu_data;
	unsigned long minsz;
	long ret;

	switch (cmd) {
	case VFIO_CHECK_EXTENSION:
		switch (arg) {
		case VFIO_SPAPR_TCE_IOMMU:
			ret = 1;
			break;
		default:
			ret = vfio_spapr_iommu_eeh_ioctl(NULL, cmd, arg);
			break;
		}

		return (ret < 0) ? 0 : ret;

	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
		struct vfio_iommu_spapr_tce_info info;
		struct iommu_table *tbl;
		struct iommu_table_group *table_group;

		if (WARN_ON(!container->grp))
			return -ENXIO;

		table_group = iommu_group_get_iommudata(container->grp);

		tbl = table_group->tables[0];
		if (WARN_ON_ONCE(!tbl))
			return -ENXIO;

		minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
				dma32_window_size);

		if (copy_from_user(&info, (void __user *)arg, minsz))
			return -EFAULT;

		if (info.argsz < minsz)
			return -EINVAL;

		info.dma32_window_start = tbl->it_offset << tbl->it_page_shift;
		info.dma32_window_size = tbl->it_size << tbl->it_page_shift;
		info.flags = 0;

		if (copy_to_user((void __user *)arg, &info, minsz))
			return -EFAULT;

		return 0;
	}
	case VFIO_IOMMU_MAP_DMA: {
		struct vfio_iommu_type1_dma_map param;
		struct iommu_table *tbl = NULL;
		long num;
		enum dma_data_direction direction;

		if (!container->enabled)
			return -EPERM;

		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);

		if (copy_from_user(&param, (void __user *)arg, minsz))
			return -EFAULT;

		if (param.argsz < minsz)
			return -EINVAL;

		if (param.flags & ~(VFIO_DMA_MAP_FLAG_READ |
				VFIO_DMA_MAP_FLAG_WRITE))
			return -EINVAL;

		num = tce_iommu_find_table(container, param.iova, &tbl);
		if (num < 0)
			return -ENXIO;

		if ((param.size & ~IOMMU_PAGE_MASK(tbl)) ||
				(param.vaddr & ~IOMMU_PAGE_MASK(tbl)))
			return -EINVAL;

		/* iova is checked by the IOMMU API */
		if (param.flags & VFIO_DMA_MAP_FLAG_READ) {
			if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
				direction = DMA_BIDIRECTIONAL;
			else
				direction = DMA_TO_DEVICE;
		} else {
			if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
				direction = DMA_FROM_DEVICE;
			else
				return -EINVAL;
		}

		ret = iommu_tce_put_param_check(tbl, param.iova, param.vaddr);
		if (ret)
			return ret;

		ret = tce_iommu_build(container, tbl,
				param.iova >> tbl->it_page_shift,
				param.vaddr,
				param.size >> tbl->it_page_shift,
				direction);

		iommu_flush_tce(tbl);

		return ret;
	}
	case VFIO_IOMMU_UNMAP_DMA: {
		struct vfio_iommu_type1_dma_unmap param;
		struct iommu_table *tbl = NULL;
		long num;

		if (!container->enabled)
			return -EPERM;

		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap,
				size);

		if (copy_from_user(&param, (void __user *)arg, minsz))
			return -EFAULT;

		if (param.argsz < minsz)
			return -EINVAL;

		/* No flag is supported now */
		if (param.flags)
			return -EINVAL;

		num = tce_iommu_find_table(container, param.iova, &tbl);
		if (num < 0)
			return -ENXIO;

		if (param.size & ~IOMMU_PAGE_MASK(tbl))
			return -EINVAL;

		ret = iommu_tce_clear_param_check(tbl, param.iova, 0,
				param.size >> tbl->it_page_shift);
		if (ret)
			return ret;

		ret = tce_iommu_clear(container, tbl,
				param.iova >> tbl->it_page_shift,
				param.size >> tbl->it_page_shift);
		iommu_flush_tce(tbl);

		return ret;
	}
	case VFIO_IOMMU_ENABLE:
		mutex_lock(&container->lock);
		ret = tce_iommu_enable(container);
		mutex_unlock(&container->lock);
		return ret;


	case VFIO_IOMMU_DISABLE:
		mutex_lock(&container->lock);
		tce_iommu_disable(container);
		mutex_unlock(&container->lock);
		return 0;
	case VFIO_EEH_PE_OP:
		if (!container->grp)
			return -ENODEV;

		return vfio_spapr_iommu_eeh_ioctl(container->grp,
						  cmd, arg);
	}

	return -ENOTTY;
}

static void tce_iommu_release_ownership(struct tce_container *container,
		struct iommu_table_group *table_group)
{
	int i;

	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
		struct iommu_table *tbl = table_group->tables[i];

		if (!tbl)
			continue;

		tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
		if (tbl->it_map)
			iommu_release_ownership(tbl);
	}
}

static int tce_iommu_take_ownership(struct tce_container *container,
		struct iommu_table_group *table_group)
{
	int i, j, rc = 0;

	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
		struct iommu_table *tbl = table_group->tables[i];

		if (!tbl || !tbl->it_map)
			continue;

		rc = iommu_take_ownership(tbl);
		if (rc) {
			for (j = 0; j < i; ++j)
				iommu_release_ownership(
						table_group->tables[j]);

			return rc;
		}
	}

	return 0;
}

static void tce_iommu_release_ownership_ddw(struct tce_container *container,
		struct iommu_table_group *table_group)
{
	table_group->ops->release_ownership(table_group);
}

static long tce_iommu_take_ownership_ddw(struct tce_container *container,
		struct iommu_table_group *table_group)
{
	table_group->ops->take_ownership(table_group);

	return 0;
}

static int tce_iommu_attach_group(void *iommu_data,
		struct iommu_group *iommu_group)
{
	int ret;
	struct tce_container *container = iommu_data;
	struct iommu_table_group *table_group;

	mutex_lock(&container->lock);

	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
			iommu_group_id(iommu_group), iommu_group); */
	if (container->grp) {
		pr_warn("tce_vfio: Only one group per IOMMU container is allowed, existing id=%d, attaching id=%d\n",
				iommu_group_id(container->grp),
				iommu_group_id(iommu_group));
		ret = -EBUSY;
		goto unlock_exit;
	}

	if (container->enabled) {
		pr_err("tce_vfio: attaching group #%u to enabled container\n",
				iommu_group_id(iommu_group));
		ret = -EBUSY;
		goto unlock_exit;
	}

	table_group = iommu_group_get_iommudata(iommu_group);
	if (!table_group) {
		ret = -ENXIO;
		goto unlock_exit;
	}

	if (!table_group->ops || !table_group->ops->take_ownership ||
			!table_group->ops->release_ownership)
		ret = tce_iommu_take_ownership(container, table_group);
	else
		ret = tce_iommu_take_ownership_ddw(container, table_group);

	if (!ret)
		container->grp = iommu_group;

unlock_exit:
	mutex_unlock(&container->lock);

	return ret;
}

static void tce_iommu_detach_group(void *iommu_data,
		struct iommu_group *iommu_group)
{
	struct tce_container *container = iommu_data;
	struct iommu_table_group *table_group;

	mutex_lock(&container->lock);
	if (iommu_group != container->grp) {
		pr_warn("tce_vfio: detaching group #%u, expected group is #%u\n",
				iommu_group_id(iommu_group),
				iommu_group_id(container->grp));
		goto unlock_exit;
	}

	if (container->enabled) {
		pr_warn("tce_vfio: detaching group #%u from enabled container, forcing disable\n",
				iommu_group_id(container->grp));
		tce_iommu_disable(container);
	}

	/* pr_debug("tce_vfio: detaching group #%u from iommu %p\n",
	   iommu_group_id(iommu_group), iommu_group); */
	container->grp = NULL;

	table_group = iommu_group_get_iommudata(iommu_group);
	BUG_ON(!table_group);

	if (!table_group->ops || !table_group->ops->release_ownership)
		tce_iommu_release_ownership(container, table_group);
	else
		tce_iommu_release_ownership_ddw(container, table_group);

unlock_exit:
	mutex_unlock(&container->lock);
}

const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
	.name		= "iommu-vfio-powerpc",
	.owner		= THIS_MODULE,
	.open		= tce_iommu_open,
	.release	= tce_iommu_release,
	.ioctl		= tce_iommu_ioctl,
	.attach_group	= tce_iommu_attach_group,
	.detach_group	= tce_iommu_detach_group,
};

static int __init tce_iommu_init(void)
{
	return vfio_register_iommu_driver(&tce_iommu_driver_ops);
}

static void __exit tce_iommu_cleanup(void)
{
	vfio_unregister_iommu_driver(&tce_iommu_driver_ops);
}

module_init(tce_iommu_init);
module_exit(tce_iommu_cleanup);

MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);