summaryrefslogtreecommitdiff
path: root/virt/kvm/vfio.c
blob: 37d9118fd84be07bc119d40efe58b8edc1f2a889 (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
/*
 * VFIO-KVM bridge pseudo device
 *
 * Copyright (C) 2013 Red Hat, Inc.  All rights reserved.
 *     Author: Alex Williamson <alex.williamson@redhat.com>
 *
 * 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.
 */

#include <linux/errno.h>
#include <linux/file.h>
#include <linux/kvm_host.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include "vfio.h"

#ifdef CONFIG_SPAPR_TCE_IOMMU
#include <asm/kvm_ppc.h>
#endif

struct kvm_vfio_group {
	struct list_head node;
	struct vfio_group *vfio_group;
};

struct kvm_vfio {
	struct list_head group_list;
	struct mutex lock;
	bool noncoherent;
};

static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
{
	struct vfio_group *vfio_group;
	struct vfio_group *(*fn)(struct file *);

	fn = symbol_get(vfio_group_get_external_user);
	if (!fn)
		return ERR_PTR(-EINVAL);

	vfio_group = fn(filep);

	symbol_put(vfio_group_get_external_user);

	return vfio_group;
}

static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
{
	void (*fn)(struct vfio_group *);

	fn = symbol_get(vfio_group_put_external_user);
	if (!fn)
		return;

	fn(vfio_group);

	symbol_put(vfio_group_put_external_user);
}

static void kvm_vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm)
{
	void (*fn)(struct vfio_group *, struct kvm *);

	fn = symbol_get(vfio_group_set_kvm);
	if (!fn)
		return;

	fn(group, kvm);

	symbol_put(vfio_group_set_kvm);
}

static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
{
	long (*fn)(struct vfio_group *, unsigned long);
	long ret;

	fn = symbol_get(vfio_external_check_extension);
	if (!fn)
		return false;

	ret = fn(vfio_group, VFIO_DMA_CC_IOMMU);

	symbol_put(vfio_external_check_extension);

	return ret > 0;
}

#ifdef CONFIG_SPAPR_TCE_IOMMU
static int kvm_vfio_external_user_iommu_id(struct vfio_group *vfio_group)
{
	int (*fn)(struct vfio_group *);
	int ret = -EINVAL;

	fn = symbol_get(vfio_external_user_iommu_id);
	if (!fn)
		return ret;

	ret = fn(vfio_group);

	symbol_put(vfio_external_user_iommu_id);

	return ret;
}

static struct iommu_group *kvm_vfio_group_get_iommu_group(
		struct vfio_group *group)
{
	int group_id = kvm_vfio_external_user_iommu_id(group);

	if (group_id < 0)
		return NULL;

	return iommu_group_get_by_id(group_id);
}

static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
		struct vfio_group *vfio_group)
{
	struct iommu_group *grp = kvm_vfio_group_get_iommu_group(vfio_group);

	if (WARN_ON_ONCE(!grp))
		return;

	kvm_spapr_tce_release_iommu_group(kvm, grp);
	iommu_group_put(grp);
}
#endif

/*
 * Groups can use the same or different IOMMU domains.  If the same then
 * adding a new group may change the coherency of groups we've previously
 * been told about.  We don't want to care about any of that so we retest
 * each group and bail as soon as we find one that's noncoherent.  This
 * means we only ever [un]register_noncoherent_dma once for the whole device.
 */
static void kvm_vfio_update_coherency(struct kvm_device *dev)
{
	struct kvm_vfio *kv = dev->private;
	bool noncoherent = false;
	struct kvm_vfio_group *kvg;

	mutex_lock(&kv->lock);

	list_for_each_entry(kvg, &kv->group_list, node) {
		if (!kvm_vfio_group_is_coherent(kvg->vfio_group)) {
			noncoherent = true;
			break;
		}
	}

	if (noncoherent != kv->noncoherent) {
		kv->noncoherent = noncoherent;

		if (kv->noncoherent)
			kvm_arch_register_noncoherent_dma(dev->kvm);
		else
			kvm_arch_unregister_noncoherent_dma(dev->kvm);
	}

	mutex_unlock(&kv->lock);
}

static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
{
	struct kvm_vfio *kv = dev->private;
	struct vfio_group *vfio_group;
	struct kvm_vfio_group *kvg;
	int32_t __user *argp = (int32_t __user *)(unsigned long)arg;
	struct fd f;
	int32_t fd;
	int ret;

	switch (attr) {
	case KVM_DEV_VFIO_GROUP_ADD:
		if (get_user(fd, argp))
			return -EFAULT;

		f = fdget(fd);
		if (!f.file)
			return -EBADF;

		vfio_group = kvm_vfio_group_get_external_user(f.file);
		fdput(f);

		if (IS_ERR(vfio_group))
			return PTR_ERR(vfio_group);

		mutex_lock(&kv->lock);

		list_for_each_entry(kvg, &kv->group_list, node) {
			if (kvg->vfio_group == vfio_group) {
				mutex_unlock(&kv->lock);
				kvm_vfio_group_put_external_user(vfio_group);
				return -EEXIST;
			}
		}

		kvg = kzalloc(sizeof(*kvg), GFP_KERNEL);
		if (!kvg) {
			mutex_unlock(&kv->lock);
			kvm_vfio_group_put_external_user(vfio_group);
			return -ENOMEM;
		}

		list_add_tail(&kvg->node, &kv->group_list);
		kvg->vfio_group = vfio_group;

		kvm_arch_start_assignment(dev->kvm);

		mutex_unlock(&kv->lock);

		kvm_vfio_group_set_kvm(vfio_group, dev->kvm);

		kvm_vfio_update_coherency(dev);

		return 0;

	case KVM_DEV_VFIO_GROUP_DEL:
		if (get_user(fd, argp))
			return -EFAULT;

		f = fdget(fd);
		if (!f.file)
			return -EBADF;

		vfio_group = kvm_vfio_group_get_external_user(f.file);
		fdput(f);

		if (IS_ERR(vfio_group))
			return PTR_ERR(vfio_group);

		ret = -ENOENT;

		mutex_lock(&kv->lock);

		list_for_each_entry(kvg, &kv->group_list, node) {
			if (kvg->vfio_group != vfio_group)
				continue;

			list_del(&kvg->node);
			kvm_vfio_group_put_external_user(kvg->vfio_group);
			kfree(kvg);
			ret = 0;
			break;
		}

		kvm_arch_end_assignment(dev->kvm);

		mutex_unlock(&kv->lock);

#ifdef CONFIG_SPAPR_TCE_IOMMU
		kvm_spapr_tce_release_vfio_group(dev->kvm, vfio_group);
#endif
		kvm_vfio_group_set_kvm(vfio_group, NULL);

		kvm_vfio_group_put_external_user(vfio_group);

		kvm_vfio_update_coherency(dev);

		return ret;

#ifdef CONFIG_SPAPR_TCE_IOMMU
	case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: {
		struct kvm_vfio_spapr_tce param;
		struct kvm_vfio *kv = dev->private;
		struct vfio_group *vfio_group;
		struct kvm_vfio_group *kvg;
		struct fd f;
		struct iommu_group *grp;

		if (copy_from_user(&param, (void __user *)arg,
				sizeof(struct kvm_vfio_spapr_tce)))
			return -EFAULT;

		f = fdget(param.groupfd);
		if (!f.file)
			return -EBADF;

		vfio_group = kvm_vfio_group_get_external_user(f.file);
		fdput(f);

		if (IS_ERR(vfio_group))
			return PTR_ERR(vfio_group);

		grp = kvm_vfio_group_get_iommu_group(vfio_group);
		if (WARN_ON_ONCE(!grp)) {
			kvm_vfio_group_put_external_user(vfio_group);
			return -EIO;
		}

		ret = -ENOENT;

		mutex_lock(&kv->lock);

		list_for_each_entry(kvg, &kv->group_list, node) {
			if (kvg->vfio_group != vfio_group)
				continue;

			ret = kvm_spapr_tce_attach_iommu_group(dev->kvm,
					param.tablefd, grp);
			break;
		}

		mutex_unlock(&kv->lock);

		iommu_group_put(grp);
		kvm_vfio_group_put_external_user(vfio_group);

		return ret;
	}
#endif /* CONFIG_SPAPR_TCE_IOMMU */
	}

	return -ENXIO;
}

static int kvm_vfio_set_attr(struct kvm_device *dev,
			     struct kvm_device_attr *attr)
{
	switch (attr->group) {
	case KVM_DEV_VFIO_GROUP:
		return kvm_vfio_set_group(dev, attr->attr, attr->addr);
	}

	return -ENXIO;
}

static int kvm_vfio_has_attr(struct kvm_device *dev,
			     struct kvm_device_attr *attr)
{
	switch (attr->group) {
	case KVM_DEV_VFIO_GROUP:
		switch (attr->attr) {
		case KVM_DEV_VFIO_GROUP_ADD:
		case KVM_DEV_VFIO_GROUP_DEL:
#ifdef CONFIG_SPAPR_TCE_IOMMU
		case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
#endif
			return 0;
		}

		break;
	}

	return -ENXIO;
}

static void kvm_vfio_destroy(struct kvm_device *dev)
{
	struct kvm_vfio *kv = dev->private;
	struct kvm_vfio_group *kvg, *tmp;

	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
#ifdef CONFIG_SPAPR_TCE_IOMMU
		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg->vfio_group);
#endif
		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
		kvm_vfio_group_put_external_user(kvg->vfio_group);
		list_del(&kvg->node);
		kfree(kvg);
		kvm_arch_end_assignment(dev->kvm);
	}

	kvm_vfio_update_coherency(dev);

	kfree(kv);
	kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
}

static int kvm_vfio_create(struct kvm_device *dev, u32 type);

static struct kvm_device_ops kvm_vfio_ops = {
	.name = "kvm-vfio",
	.create = kvm_vfio_create,
	.destroy = kvm_vfio_destroy,
	.set_attr = kvm_vfio_set_attr,
	.has_attr = kvm_vfio_has_attr,
};

static int kvm_vfio_create(struct kvm_device *dev, u32 type)
{
	struct kvm_device *tmp;
	struct kvm_vfio *kv;

	/* Only one VFIO "device" per VM */
	list_for_each_entry(tmp, &dev->kvm->devices, vm_node)
		if (tmp->ops == &kvm_vfio_ops)
			return -EBUSY;

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

	INIT_LIST_HEAD(&kv->group_list);
	mutex_init(&kv->lock);

	dev->private = kv;

	return 0;
}

int kvm_vfio_ops_init(void)
{
	return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO);
}

void kvm_vfio_ops_exit(void)
{
	kvm_unregister_device_ops(KVM_DEV_TYPE_VFIO);
}